From 354e57f3a0a26120af3bcd6c92c355ad00a057c1 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Thu, 7 Nov 2013 10:25:55 +0100
Subject: ARM/serial: at91: switch atmel serial to use gpiolib
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This passes the errata fix using a GPIO to control the RTS pin
on one of the AT91 chips to use gpiolib instead of the
AT91-specific interfaces. Also remove the reliance on
compile-time #defines and the cpu_* check and rely on the
platform passing down the proper GPIO pin through platform
data.

This is a prerequisite for getting rid of the local GPIO
implementation in the AT91 platform and move toward
multiplatform.

The patch also adds device tree support for getting the
RTS GPIO pin from the device tree on DT boot paths.

Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Acked-by: Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
---
 include/linux/platform_data/atmel.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/atmel.h b/include/linux/platform_data/atmel.h
index cea9f70133c5..e26b0c14edea 100644
--- a/include/linux/platform_data/atmel.h
+++ b/include/linux/platform_data/atmel.h
@@ -84,6 +84,7 @@ struct atmel_uart_data {
 	short			use_dma_rx;	/* use receive DMA? */
 	void __iomem		*regs;		/* virt. base address, if any */
 	struct serial_rs485	rs485;		/* rs485 settings */
+	int			rts_gpio;	/* optional RTS GPIO */
 };
 
  /* Touchscreen Controller */
-- 
cgit v1.2.3


From ee1e0994ab1bd302fd03432de79c07751df47ffa Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Date: Fri, 24 Jan 2014 14:37:57 +0100
Subject: regulator: s5m8767: Use GPIO for controlling Buck9/eMMC

Add support for GPIO control (enable/disable) over Buck9. The Buck9
Converter is used as a supply for eMMC Host Controller.

BUCK9EN GPIO of S5M8767 chip may be used by application processor to
enable or disable the Buck9. This has two benefits:
 - It is faster than toggling it over I2C bus.
 - It allows disabling the regulator during suspend to RAM; The AP will
   enable it during resume; Without the patch the regulator supplying
   eMMC must be defined as fixed-regulator.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/regulator/s5m8767.c         | 87 +++++++++++++++++++++++++++++++++++--
 include/linux/mfd/samsung/core.h    |  3 +-
 include/linux/mfd/samsung/s5m8767.h |  7 +++
 3 files changed, 93 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/regulator/s5m8767.c b/drivers/regulator/s5m8767.c
index d7164bb75d3e..6850a25a41c4 100644
--- a/drivers/regulator/s5m8767.c
+++ b/drivers/regulator/s5m8767.c
@@ -11,11 +11,8 @@
  *
  */
 
-#include <linux/bug.h>
 #include <linux/err.h>
-#include <linux/gpio.h>
 #include <linux/of_gpio.h>
-#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/driver.h>
@@ -483,6 +480,65 @@ static struct regulator_desc regulators[] = {
 	s5m8767_regulator_desc(BUCK9),
 };
 
+/*
+ * Enable GPIO control over BUCK9 in regulator_config for that regulator.
+ */
+static void s5m8767_regulator_config_ext_control(struct s5m8767_info *s5m8767,
+		struct sec_regulator_data *rdata,
+		struct regulator_config *config)
+{
+	int i, mode = 0;
+
+	if (rdata->id != S5M8767_BUCK9)
+		return;
+
+	/* Check if opmode for regulator matches S5M8767_ENCTRL_USE_GPIO */
+	for (i = 0; i < s5m8767->num_regulators; i++) {
+		const struct sec_opmode_data *opmode = &s5m8767->opmode[i];
+		if (opmode->id == rdata->id) {
+			mode = s5m8767_opmode_reg[rdata->id][opmode->mode];
+			break;
+		}
+	}
+	if (mode != S5M8767_ENCTRL_USE_GPIO) {
+		dev_warn(s5m8767->dev,
+				"ext-control for %s: mismatched op_mode (%x), ignoring\n",
+				rdata->reg_node->name, mode);
+		return;
+	}
+
+	if (!gpio_is_valid(rdata->ext_control_gpio)) {
+		dev_warn(s5m8767->dev,
+				"ext-control for %s: GPIO not valid, ignoring\n",
+				rdata->reg_node->name);
+		return;
+	}
+
+	config->ena_gpio = rdata->ext_control_gpio;
+	config->ena_gpio_flags = GPIOF_OUT_INIT_HIGH;
+}
+
+/*
+ * Turn on GPIO control over BUCK9.
+ */
+static int s5m8767_enable_ext_control(struct s5m8767_info *s5m8767,
+		struct regulator_dev *rdev)
+{
+	int ret, reg, enable_ctrl;
+
+	if (rdev_get_id(rdev) != S5M8767_BUCK9)
+		return -EINVAL;
+
+	ret = s5m8767_get_register(rdev, &reg, &enable_ctrl);
+	if (ret)
+		return ret;
+
+	return regmap_update_bits(s5m8767->iodev->regmap_pmic,
+			reg, S5M8767_ENCTRL_MASK,
+			S5M8767_ENCTRL_USE_GPIO << S5M8767_ENCTRL_SHIFT);
+}
+
+
 #ifdef CONFIG_OF
 static int s5m8767_pmic_dt_parse_dvs_gpio(struct sec_pmic_dev *iodev,
 			struct sec_platform_data *pdata,
@@ -520,6 +576,16 @@ static int s5m8767_pmic_dt_parse_ds_gpio(struct sec_pmic_dev *iodev,
 	return 0;
 }
 
+static void s5m8767_pmic_dt_parse_ext_control_gpio(struct sec_pmic_dev *iodev,
+		struct sec_regulator_data *rdata,
+		struct device_node *reg_np)
+{
+	rdata->ext_control_gpio = of_get_named_gpio(reg_np,
+			"s5m8767,pmic-ext-control-gpios", 0);
+	if (!gpio_is_valid(rdata->ext_control_gpio))
+		rdata->ext_control_gpio = 0;
+}
+
 static int s5m8767_pmic_dt_parse_pdata(struct platform_device *pdev,
 					struct sec_platform_data *pdata)
 {
@@ -574,6 +640,8 @@ static int s5m8767_pmic_dt_parse_pdata(struct platform_device *pdev,
 			continue;
 		}
 
+		s5m8767_pmic_dt_parse_ext_control_gpio(iodev, rdata, reg_np);
+
 		rdata->id = i;
 		rdata->initdata = of_get_regulator_init_data(
 						&pdev->dev, reg_np);
@@ -940,6 +1008,9 @@ static int s5m8767_pmic_probe(struct platform_device *pdev)
 		config.driver_data = s5m8767;
 		config.regmap = iodev->regmap_pmic;
 		config.of_node = pdata->regulators[i].reg_node;
+		if (pdata->regulators[i].ext_control_gpio)
+			s5m8767_regulator_config_ext_control(s5m8767,
+					&pdata->regulators[i], &config);
 
 		rdev[i] = devm_regulator_register(&pdev->dev, &regulators[id],
 						  &config);
@@ -949,6 +1020,16 @@ static int s5m8767_pmic_probe(struct platform_device *pdev)
 					id);
 			return ret;
 		}
+
+		if (pdata->regulators[i].ext_control_gpio) {
+			ret = s5m8767_enable_ext_control(s5m8767, rdev[i]);
+			if (ret < 0) {
+				dev_err(s5m8767->dev,
+						"failed to enable gpio control over %s: %d\n",
+						rdev[i]->desc->name, ret);
+				return ret;
+			}
+		}
 	}
 
 	return 0;
diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h
index 41c9bde410c5..55510444b9fd 100644
--- a/include/linux/mfd/samsung/core.h
+++ b/include/linux/mfd/samsung/core.h
@@ -119,7 +119,8 @@ struct sec_platform_data {
 struct sec_regulator_data {
 	int				id;
 	struct regulator_init_data	*initdata;
-	struct device_node *reg_node;
+	struct device_node		*reg_node;
+	int				ext_control_gpio;
 };
 
 /*
diff --git a/include/linux/mfd/samsung/s5m8767.h b/include/linux/mfd/samsung/s5m8767.h
index 2ab0b0f03641..243b58fec33d 100644
--- a/include/linux/mfd/samsung/s5m8767.h
+++ b/include/linux/mfd/samsung/s5m8767.h
@@ -183,9 +183,16 @@ enum s5m8767_regulators {
 	S5M8767_REG_MAX,
 };
 
+/* LDO_EN/BUCK_EN field in registers */
 #define S5M8767_ENCTRL_SHIFT		6
 #define S5M8767_ENCTRL_MASK		(0x3 << S5M8767_ENCTRL_SHIFT)
 
+/*
+ * LDO_EN/BUCK_EN register value for controlling this Buck or LDO
+ * by GPIO (PWREN, BUCKEN).
+ */
+#define S5M8767_ENCTRL_USE_GPIO		0x1
+
 /*
  * Values for BUCK_RAMP field in DVS_RAMP register, matching raw values
  * in mV/us.
-- 
cgit v1.2.3


From cd4dc0821bc97947f25c8483a4aa0711bff8619a Mon Sep 17 00:00:00 2001
From: Frank Praznik <frank.praznik@oh.rr.com>
Date: Wed, 22 Jan 2014 13:49:41 -0500
Subject: HID: Add transport-driver callbacks to the hid_ll_driver struct

Add raw_request and output_report callbacks to the hid_ll_driver struct.

Signed-off-by: Frank Praznik <frank.praznik@oh.rr.com>
Acked-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 include/linux/hid.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/hid.h b/include/linux/hid.h
index 31b9d299ef6c..003cc8e89831 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -700,8 +700,14 @@ struct hid_ll_driver {
 			struct hid_report *report, int reqtype);
 
 	int (*wait)(struct hid_device *hdev);
-	int (*idle)(struct hid_device *hdev, int report, int idle, int reqtype);
 
+	int (*raw_request) (struct hid_device *hdev, unsigned char reportnum,
+			    __u8 *buf, size_t len, unsigned char rtype,
+			    int reqtype);
+
+	int (*output_report) (struct hid_device *hdev, __u8 *buf, size_t len);
+
+	int (*idle)(struct hid_device *hdev, int report, int idle, int reqtype);
 };
 
 #define	PM_HINT_FULLON	1<<5
-- 
cgit v1.2.3


From c05c4186bbe4e99d64e8a36f7ca7f480da5d109f Mon Sep 17 00:00:00 2001
From: Jens Freimann <jfrei@linux.vnet.ibm.com>
Date: Mon, 7 Oct 2013 16:13:45 +0200
Subject: KVM: s390: add floating irq controller

This patch adds a floating irq controller as a kvm_device.
It will be necessary for migration of floating interrupts as well
as for hardening the reset code by allowing user space to explicitly
remove all pending floating interrupts.

Signed-off-by: Jens Freimann <jfrei@linux.vnet.ibm.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 Documentation/virtual/kvm/devices/s390_flic.txt |  36 +++
 arch/s390/include/asm/kvm_host.h                |   1 +
 arch/s390/include/uapi/asm/kvm.h                |  14 ++
 arch/s390/kvm/interrupt.c                       | 304 ++++++++++++++++++++----
 arch/s390/kvm/kvm-s390.c                        |   1 +
 include/linux/kvm_host.h                        |   1 +
 include/uapi/linux/kvm.h                        |   1 +
 virt/kvm/kvm_main.c                             |   5 +
 8 files changed, 312 insertions(+), 51 deletions(-)
 create mode 100644 Documentation/virtual/kvm/devices/s390_flic.txt

(limited to 'include/linux')

diff --git a/Documentation/virtual/kvm/devices/s390_flic.txt b/Documentation/virtual/kvm/devices/s390_flic.txt
new file mode 100644
index 000000000000..6b557953066a
--- /dev/null
+++ b/Documentation/virtual/kvm/devices/s390_flic.txt
@@ -0,0 +1,36 @@
+FLIC (floating interrupt controller)
+====================================
+
+FLIC handles floating (non per-cpu) interrupts, i.e. I/O, service and some
+machine check interruptions. All interrupts are stored in a per-vm list of
+pending interrupts. FLIC performs operations on this list.
+
+Only one FLIC instance may be instantiated.
+
+FLIC provides support to
+- add interrupts (KVM_DEV_FLIC_ENQUEUE)
+- inspect currently pending interrupts (KVM_FLIC_GET_ALL_IRQS)
+- purge all pending floating interrupts (KVM_DEV_FLIC_CLEAR_IRQS)
+
+Groups:
+  KVM_DEV_FLIC_ENQUEUE
+    Passes a buffer and length into the kernel which are then injected into
+    the list of pending interrupts.
+    attr->addr contains the pointer to the buffer and attr->attr contains
+    the length of the buffer.
+    The format of the data structure kvm_s390_irq as it is copied from userspace
+    is defined in usr/include/linux/kvm.h.
+
+  KVM_DEV_FLIC_GET_ALL_IRQS
+    Copies all floating interrupts into a buffer provided by userspace.
+    When the buffer is too small it returns -ENOMEM, which is the indication
+    for userspace to try again with a bigger buffer.
+    All interrupts remain pending, i.e. are not deleted from the list of
+    currently pending interrupts.
+    attr->addr contains the userspace address of the buffer into which all
+    interrupt data will be copied.
+    attr->attr contains the size of the buffer in bytes.
+
+  KVM_DEV_FLIC_CLEAR_IRQS
+    Simply deletes all elements from the list of currently pending floating
+    interrupts.  No interrupts are injected into the guest.
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 3ffc9646e742..59635b5c59a6 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -243,6 +243,7 @@ struct kvm_arch{
 	struct sca_block *sca;
 	debug_info_t *dbf;
 	struct kvm_s390_float_interrupt float_int;
+	struct kvm_device *flic;
 	struct gmap *gmap;
 	int css_support;
 };
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index d25da598ec62..38d5f98552bb 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -16,6 +16,20 @@
 
 #define __KVM_S390
 
+/* Device control API: s390-specific devices */
+#define KVM_DEV_FLIC_GET_ALL_IRQS	1
+#define KVM_DEV_FLIC_ENQUEUE		2
+#define KVM_DEV_FLIC_CLEAR_IRQS		3
+/*
+ * We can have up to 4*64k pending subchannels + 8 adapter interrupts,
+ * as well as up  to ASYNC_PF_PER_VCPU*KVM_MAX_VCPUS pfault done interrupts.
+ * There are also sclp and machine checks. This gives us
+ * sizeof(kvm_s390_irq)*(4*65536+8+64*64+1+1) = 72 * 266250 = 19170000
+ * Lets round up to 8192 pages.
+ */
+
+#define KVM_S390_FLIC_MAX_BUFFER	0x2000000
+
 /* for KVM_GET_REGS and KVM_SET_REGS */
 struct kvm_regs {
 	/* general purpose regs for s390 */
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 5f79d2d79ca7..a5f18babed4c 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -659,53 +659,86 @@ struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
 	return inti;
 }
 
-int kvm_s390_inject_vm(struct kvm *kvm,
-		       struct kvm_s390_interrupt *s390int)
+static void __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
 {
 	struct kvm_s390_local_interrupt *li;
 	struct kvm_s390_float_interrupt *fi;
-	struct kvm_s390_interrupt_info *inti, *iter;
+	struct kvm_s390_interrupt_info *iter;
 	int sigcpu;
 
+	mutex_lock(&kvm->lock);
+	fi = &kvm->arch.float_int;
+	spin_lock(&fi->lock);
+	if (!is_ioint(inti->type)) {
+		list_add_tail(&inti->list, &fi->list);
+	} else {
+		u64 isc_bits = int_word_to_isc_bits(inti->io.io_int_word);
+
+		/* Keep I/O interrupts sorted in isc order. */
+		list_for_each_entry(iter, &fi->list, list) {
+			if (!is_ioint(iter->type))
+				continue;
+			if (int_word_to_isc_bits(iter->io.io_int_word)
+			    <= isc_bits)
+				continue;
+			break;
+		}
+		list_add_tail(&inti->list, &iter->list);
+	}
+	atomic_set(&fi->active, 1);
+	sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS);
+	if (sigcpu == KVM_MAX_VCPUS) {
+		do {
+			sigcpu = fi->next_rr_cpu++;
+			if (sigcpu == KVM_MAX_VCPUS)
+				sigcpu = fi->next_rr_cpu = 0;
+		} while (fi->local_int[sigcpu] == NULL);
+	}
+	li = fi->local_int[sigcpu];
+	spin_lock_bh(&li->lock);
+	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+	if (waitqueue_active(li->wq))
+		wake_up_interruptible(li->wq);
+	spin_unlock_bh(&li->lock);
+	spin_unlock(&fi->lock);
+	mutex_unlock(&kvm->lock);
+}
+
+int kvm_s390_inject_vm(struct kvm *kvm,
+		       struct kvm_s390_interrupt *s390int)
+{
+	struct kvm_s390_interrupt_info *inti;
+
 	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
 	if (!inti)
 		return -ENOMEM;
 
-	switch (s390int->type) {
+	inti->type = s390int->type;
+	switch (inti->type) {
 	case KVM_S390_INT_VIRTIO:
 		VM_EVENT(kvm, 5, "inject: virtio parm:%x,parm64:%llx",
 			 s390int->parm, s390int->parm64);
-		inti->type = s390int->type;
 		inti->ext.ext_params = s390int->parm;
 		inti->ext.ext_params2 = s390int->parm64;
 		break;
 	case KVM_S390_INT_SERVICE:
 		VM_EVENT(kvm, 5, "inject: sclp parm:%x", s390int->parm);
-		inti->type = s390int->type;
 		inti->ext.ext_params = s390int->parm;
 		break;
-	case KVM_S390_PROGRAM_INT:
-	case KVM_S390_SIGP_STOP:
-	case KVM_S390_INT_EXTERNAL_CALL:
-	case KVM_S390_INT_EMERGENCY:
-		kfree(inti);
-		return -EINVAL;
 	case KVM_S390_MCHK:
 		VM_EVENT(kvm, 5, "inject: machine check parm64:%llx",
 			 s390int->parm64);
-		inti->type = s390int->type;
 		inti->mchk.cr14 = s390int->parm; /* upper bits are not used */
 		inti->mchk.mcic = s390int->parm64;
 		break;
 	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
-		if (s390int->type & IOINT_AI_MASK)
+		if (inti->type & IOINT_AI_MASK)
 			VM_EVENT(kvm, 5, "%s", "inject: I/O (AI)");
 		else
 			VM_EVENT(kvm, 5, "inject: I/O css %x ss %x schid %04x",
 				 s390int->type & IOINT_CSSID_MASK,
 				 s390int->type & IOINT_SSID_MASK,
 				 s390int->type & IOINT_SCHID_MASK);
-		inti->type = s390int->type;
 		inti->io.subchannel_id = s390int->parm >> 16;
 		inti->io.subchannel_nr = s390int->parm & 0x0000ffffu;
 		inti->io.io_int_parm = s390int->parm64 >> 32;
@@ -718,42 +751,7 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 	trace_kvm_s390_inject_vm(s390int->type, s390int->parm, s390int->parm64,
 				 2);
 
-	mutex_lock(&kvm->lock);
-	fi = &kvm->arch.float_int;
-	spin_lock(&fi->lock);
-	if (!is_ioint(inti->type))
-		list_add_tail(&inti->list, &fi->list);
-	else {
-		u64 isc_bits = int_word_to_isc_bits(inti->io.io_int_word);
-
-		/* Keep I/O interrupts sorted in isc order. */
-		list_for_each_entry(iter, &fi->list, list) {
-			if (!is_ioint(iter->type))
-				continue;
-			if (int_word_to_isc_bits(iter->io.io_int_word)
-			    <= isc_bits)
-				continue;
-			break;
-		}
-		list_add_tail(&inti->list, &iter->list);
-	}
-	atomic_set(&fi->active, 1);
-	sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS);
-	if (sigcpu == KVM_MAX_VCPUS) {
-		do {
-			sigcpu = fi->next_rr_cpu++;
-			if (sigcpu == KVM_MAX_VCPUS)
-				sigcpu = fi->next_rr_cpu = 0;
-		} while (fi->local_int[sigcpu] == NULL);
-	}
-	li = fi->local_int[sigcpu];
-	spin_lock_bh(&li->lock);
-	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
-	if (waitqueue_active(li->wq))
-		wake_up_interruptible(li->wq);
-	spin_unlock_bh(&li->lock);
-	spin_unlock(&fi->lock);
-	mutex_unlock(&kvm->lock);
+	__inject_vm(kvm, inti);
 	return 0;
 }
 
@@ -841,3 +839,207 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 	mutex_unlock(&vcpu->kvm->lock);
 	return 0;
 }
+
+static void clear_floating_interrupts(struct kvm *kvm)
+{
+	struct kvm_s390_float_interrupt *fi;
+	struct kvm_s390_interrupt_info	*n, *inti = NULL;
+
+	mutex_lock(&kvm->lock);
+	fi = &kvm->arch.float_int;
+	spin_lock(&fi->lock);
+	list_for_each_entry_safe(inti, n, &fi->list, list) {
+		list_del(&inti->list);
+		kfree(inti);
+	}
+	atomic_set(&fi->active, 0);
+	spin_unlock(&fi->lock);
+	mutex_unlock(&kvm->lock);
+}
+
+static inline int copy_irq_to_user(struct kvm_s390_interrupt_info *inti,
+				   u8 *addr)
+{
+	struct kvm_s390_irq __user *uptr = (struct kvm_s390_irq __user *) addr;
+	struct kvm_s390_irq irq = {0};
+
+	irq.type = inti->type;
+	switch (inti->type) {
+	case KVM_S390_INT_VIRTIO:
+	case KVM_S390_INT_SERVICE:
+		irq.u.ext = inti->ext;
+		break;
+	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+		irq.u.io = inti->io;
+		break;
+	case KVM_S390_MCHK:
+		irq.u.mchk = inti->mchk;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (copy_to_user(uptr, &irq, sizeof(irq)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int get_all_floating_irqs(struct kvm *kvm, __u8 *buf, __u64 len)
+{
+	struct kvm_s390_interrupt_info *inti;
+	struct kvm_s390_float_interrupt *fi;
+	int ret = 0;
+	int n = 0;
+
+	mutex_lock(&kvm->lock);
+	fi = &kvm->arch.float_int;
+	spin_lock(&fi->lock);
+
+	list_for_each_entry(inti, &fi->list, list) {
+		if (len < sizeof(struct kvm_s390_irq)) {
+			/* signal userspace to try again */
+			ret = -ENOMEM;
+			break;
+		}
+		ret = copy_irq_to_user(inti, buf);
+		if (ret)
+			break;
+		buf += sizeof(struct kvm_s390_irq);
+		len -= sizeof(struct kvm_s390_irq);
+		n++;
+	}
+
+	spin_unlock(&fi->lock);
+	mutex_unlock(&kvm->lock);
+
+	return ret < 0 ? ret : n;
+}
+
+static int flic_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+	int r;
+
+	switch (attr->group) {
+	case KVM_DEV_FLIC_GET_ALL_IRQS:
+		r = get_all_floating_irqs(dev->kvm, (u8 *) attr->addr,
+					  attr->attr);
+		break;
+	default:
+		r = -EINVAL;
+	}
+
+	return r;
+}
+
+static inline int copy_irq_from_user(struct kvm_s390_interrupt_info *inti,
+				     u64 addr)
+{
+	struct kvm_s390_irq __user *uptr = (struct kvm_s390_irq __user *) addr;
+	void *target = NULL;
+	void __user *source;
+	u64 size;
+
+	if (get_user(inti->type, (u64 __user *)addr))
+		return -EFAULT;
+
+	switch (inti->type) {
+	case KVM_S390_INT_VIRTIO:
+	case KVM_S390_INT_SERVICE:
+		target = (void *) &inti->ext;
+		source = &uptr->u.ext;
+		size = sizeof(inti->ext);
+		break;
+	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+		target = (void *) &inti->io;
+		source = &uptr->u.io;
+		size = sizeof(inti->io);
+		break;
+	case KVM_S390_MCHK:
+		target = (void *) &inti->mchk;
+		source = &uptr->u.mchk;
+		size = sizeof(inti->mchk);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (copy_from_user(target, source, size))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int enqueue_floating_irq(struct kvm_device *dev,
+				struct kvm_device_attr *attr)
+{
+	struct kvm_s390_interrupt_info *inti = NULL;
+	int r = 0;
+	int len = attr->attr;
+
+	if (len % sizeof(struct kvm_s390_irq) != 0)
+		return -EINVAL;
+	else if (len > KVM_S390_FLIC_MAX_BUFFER)
+		return -EINVAL;
+
+	while (len >= sizeof(struct kvm_s390_irq)) {
+		inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+		if (!inti)
+			return -ENOMEM;
+
+		r = copy_irq_from_user(inti, attr->addr);
+		if (r) {
+			kfree(inti);
+			return r;
+		}
+		__inject_vm(dev->kvm, inti);
+		len -= sizeof(struct kvm_s390_irq);
+		attr->addr += sizeof(struct kvm_s390_irq);
+	}
+
+	return r;
+}
+
+static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+	int r = 0;
+
+	switch (attr->group) {
+	case KVM_DEV_FLIC_ENQUEUE:
+		r = enqueue_floating_irq(dev, attr);
+		break;
+	case KVM_DEV_FLIC_CLEAR_IRQS:
+		r = 0;
+		clear_floating_interrupts(dev->kvm);
+		break;
+	default:
+		r = -EINVAL;
+	}
+
+	return r;
+}
+
+static int flic_create(struct kvm_device *dev, u32 type)
+{
+	if (!dev)
+		return -EINVAL;
+	if (dev->kvm->arch.flic)
+		return -EINVAL;
+	dev->kvm->arch.flic = dev;
+	return 0;
+}
+
+static void flic_destroy(struct kvm_device *dev)
+{
+	dev->kvm->arch.flic = NULL;
+	kfree(dev);
+}
+
+/* s390 floating irq controller (flic) */
+struct kvm_device_ops kvm_flic_ops = {
+	.name = "kvm-flic",
+	.get_attr = flic_get_attr,
+	.set_attr = flic_set_attr,
+	.create = flic_create,
+	.destroy = flic_destroy,
+};
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index e0676f390d57..782420f3c4d5 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -157,6 +157,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_S390_CSS_SUPPORT:
 	case KVM_CAP_IOEVENTFD:
+	case KVM_CAP_DEVICE_CTRL:
 		r = 1;
 		break;
 	case KVM_CAP_NR_VCPUS:
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index b8e9a43e501a..c0102ef2de48 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1064,6 +1064,7 @@ extern struct kvm_device_ops kvm_mpic_ops;
 extern struct kvm_device_ops kvm_xics_ops;
 extern struct kvm_device_ops kvm_vfio_ops;
 extern struct kvm_device_ops kvm_arm_vgic_v2_ops;
+extern struct kvm_device_ops kvm_flic_ops;
 
 #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 86faf47ae494..19f717b15297 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -918,6 +918,7 @@ struct kvm_device_attr {
 #define   KVM_DEV_VFIO_GROUP_ADD			1
 #define   KVM_DEV_VFIO_GROUP_DEL			2
 #define KVM_DEV_TYPE_ARM_VGIC_V2	5
+#define KVM_DEV_TYPE_FLIC		6
 
 /*
  * ioctls for VM fds
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 03a0381b1cb7..a9e999a48e43 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2283,6 +2283,11 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 	case KVM_DEV_TYPE_ARM_VGIC_V2:
 		ops = &kvm_arm_vgic_v2_ops;
 		break;
+#endif
+#ifdef CONFIG_S390
+	case KVM_DEV_TYPE_FLIC:
+		ops = &kvm_flic_ops;
+		break;
 #endif
 	default:
 		return -ENODEV;
-- 
cgit v1.2.3


From e0ead41a6dac09f86675ce07a66e4b253a9b7bd5 Mon Sep 17 00:00:00 2001
From: Dominik Dingel <dingel@linux.vnet.ibm.com>
Date: Thu, 6 Jun 2013 15:32:37 +0200
Subject: KVM: async_pf: Provide additional direct page notification

By setting a Kconfig option, the architecture can control when
guest notifications will be presented by the apf backend.
There is the default batch mechanism, working as before, where the vcpu
thread should pull in this information.
Opposite to this, there is now the direct mechanism, that will push the
information to the guest.
This way s390 can use an already existing architecture interface.

Still the vcpu thread should call check_completion to cleanup leftovers.

Signed-off-by: Dominik Dingel <dingel@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 arch/x86/kvm/mmu.c       |  2 +-
 include/linux/kvm_host.h |  2 +-
 virt/kvm/Kconfig         |  4 ++++
 virt/kvm/async_pf.c      | 20 ++++++++++++++++++--
 4 files changed, 24 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index e50425d0f5f7..aaa60f347b73 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3328,7 +3328,7 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
 	arch.direct_map = vcpu->arch.mmu.direct_map;
 	arch.cr3 = vcpu->arch.mmu.get_cr3(vcpu);
 
-	return kvm_setup_async_pf(vcpu, gva, gfn, &arch);
+	return kvm_setup_async_pf(vcpu, gva, gfn_to_hva(vcpu->kvm, gfn), &arch);
 }
 
 static bool can_do_async_pf(struct kvm_vcpu *vcpu)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c0102ef2de48..f5937b8188b4 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -192,7 +192,7 @@ struct kvm_async_pf {
 
 void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu);
 void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu);
-int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
+int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
 		       struct kvm_arch_async_pf *arch);
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index fbe1a48bd629..13f2d19793e3 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -22,6 +22,10 @@ config KVM_MMIO
 config KVM_ASYNC_PF
        bool
 
+# Toggle to switch between direct notification and batch job
+config KVM_ASYNC_PF_SYNC
+       bool
+
 config HAVE_KVM_MSI
        bool
 
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 8631d9c14320..00980ab02c45 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -28,6 +28,21 @@
 #include "async_pf.h"
 #include <trace/events/kvm.h>
 
+static inline void kvm_async_page_present_sync(struct kvm_vcpu *vcpu,
+					       struct kvm_async_pf *work)
+{
+#ifdef CONFIG_KVM_ASYNC_PF_SYNC
+	kvm_arch_async_page_present(vcpu, work);
+#endif
+}
+static inline void kvm_async_page_present_async(struct kvm_vcpu *vcpu,
+						struct kvm_async_pf *work)
+{
+#ifndef CONFIG_KVM_ASYNC_PF_SYNC
+	kvm_arch_async_page_present(vcpu, work);
+#endif
+}
+
 static struct kmem_cache *async_pf_cache;
 
 int kvm_async_pf_init(void)
@@ -69,6 +84,7 @@ static void async_pf_execute(struct work_struct *work)
 	down_read(&mm->mmap_sem);
 	get_user_pages(current, mm, addr, 1, 1, 0, NULL, NULL);
 	up_read(&mm->mmap_sem);
+	kvm_async_page_present_sync(vcpu, apf);
 	unuse_mm(mm);
 
 	spin_lock(&vcpu->async_pf.lock);
@@ -138,7 +154,7 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
 	}
 }
 
-int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
+int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
 		       struct kvm_arch_async_pf *arch)
 {
 	struct kvm_async_pf *work;
@@ -159,7 +175,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
 	work->wakeup_all = false;
 	work->vcpu = vcpu;
 	work->gva = gva;
-	work->addr = gfn_to_hva(vcpu->kvm, gfn);
+	work->addr = hva;
 	work->arch = *arch;
 	work->mm = current->mm;
 	atomic_inc(&work->mm->mm_count);
-- 
cgit v1.2.3


From 8cc7212a036118fcb5cfbbdb013c5032677bbd23 Mon Sep 17 00:00:00 2001
From: Vladimir Davydov <vdavydov@parallels.com>
Date: Thu, 30 Jan 2014 19:57:54 +0400
Subject: idr: remove unused prototype of idr_free()

There is no such function. Remove the redundant prototype.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 include/linux/idr.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/idr.h b/include/linux/idr.h
index 871a213a8477..ff94a4875e1c 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -82,7 +82,6 @@ int idr_for_each(struct idr *idp,
 void *idr_get_next(struct idr *idp, int *nextid);
 void *idr_replace(struct idr *idp, void *ptr, int id);
 void idr_remove(struct idr *idp, int id);
-void idr_free(struct idr *idp, int id);
 void idr_destroy(struct idr *idp);
 void idr_init(struct idr *idp);
 
-- 
cgit v1.2.3


From 81993e81a994504f4c8b97d3410c9a052cdbcc9d Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin" <hpa@linux.intel.com>
Date: Sat, 1 Feb 2014 18:54:11 -0800
Subject: compat: Get rid of (get|put)_compat_time(val|spec)

We have two APIs for compatiblity timespec/val, with confusingly
similar names.  compat_(get|put)_time(val|spec) *do* handle the case
where COMPAT_USE_64BIT_TIME is set, whereas
(get|put)_compat_time(val|spec) do not.  This is an accident waiting
to happen.

Clean it up by favoring the full-service version; the limited version
is replaced with double-underscore versions static to kernel/compat.c.

A common pattern is to convert a struct timespec to kernel format in
an allocation on the user stack.  Unfortunately it is open-coded in
several places.  Since this allocation isn't actually needed if
COMPAT_USE_64BIT_TIME is true (since user format == kernel format)
encapsulate that whole pattern into the function
compat_convert_timespec().  An equivalent function should be written
for struct timeval if it is needed in the future.

Finally, get rid of compat_(get|put)_timeval_convert(): each was only
used once, and the latter was not even doing what the function said
(no conversion actually was being done.)  Moving the conversion into
compat_sys_settimeofday() itself makes the code much more similar to
sys_settimeofday() itself.

v3: Remove unused compat_convert_timeval().

v2: Drop bogus "const" in the destination argument for
    compat_convert_time*().

Cc: Mauro Carvalho Chehab <m.chehab@samsung.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Hans Verkuil <hans.verkuil@cisco.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Cc: Mateusz Guzik <mguzik@redhat.com>
Cc: Rafael Aquini <aquini@redhat.com>
Cc: Davidlohr Bueso <davidlohr@hp.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Tested-by: H.J. Lu <hjl.tools@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 drivers/media/v4l2-core/v4l2-compat-ioctl32.c |   2 +-
 fs/compat.c                                   |   6 +-
 include/linux/compat.h                        |  23 +++---
 ipc/compat.c                                  |  12 +--
 ipc/compat_mq.c                               |  19 +----
 kernel/compat.c                               | 108 +++++++++++++-------------
 kernel/futex_compat.c                         |   2 +-
 7 files changed, 75 insertions(+), 97 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
index 8f7a6a454a4c..6191968db8fa 100644
--- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
+++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
@@ -733,7 +733,7 @@ static int put_v4l2_event32(struct v4l2_event *kp, struct v4l2_event32 __user *u
 		copy_to_user(&up->u, &kp->u, sizeof(kp->u)) ||
 		put_user(kp->pending, &up->pending) ||
 		put_user(kp->sequence, &up->sequence) ||
-		put_compat_timespec(&kp->timestamp, &up->timestamp) ||
+		compat_put_timespec(&kp->timestamp, &up->timestamp) ||
 		put_user(kp->id, &up->id) ||
 		copy_to_user(up->reserved, kp->reserved, 8 * sizeof(__u32)))
 			return -EFAULT;
diff --git a/fs/compat.c b/fs/compat.c
index 6af20de2c1a3..62092f433759 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -92,8 +92,8 @@ asmlinkage long compat_sys_utimensat(unsigned int dfd, const char __user *filena
 	struct timespec tv[2];
 
 	if  (t) {
-		if (get_compat_timespec(&tv[0], &t[0]) ||
-		    get_compat_timespec(&tv[1], &t[1]))
+		if (compat_get_timespec(&tv[0], &t[0]) ||
+		    compat_get_timespec(&tv[1], &t[1]))
 			return -EFAULT;
 
 		if (tv[0].tv_nsec == UTIME_OMIT && tv[1].tv_nsec == UTIME_OMIT)
@@ -512,7 +512,7 @@ compat_sys_io_getevents(aio_context_t ctx_id,
 				nr * sizeof(struct io_event))))
 		goto out;
 	if (timeout) {
-		if (get_compat_timespec(&t, timeout))
+		if (compat_get_timespec(&t, timeout))
 			goto out;
 
 		ut = compat_alloc_user_space(sizeof(*ut));
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 3f448c65511b..f7d5bc0a239f 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -140,27 +140,24 @@ struct compat_sigaction {
 	compat_sigset_t			sa_mask __packed;
 };
 
-/*
- * These functions operate strictly on struct compat_time*
- */
-extern int get_compat_timespec(struct timespec *,
-			       const struct compat_timespec __user *);
-extern int put_compat_timespec(const struct timespec *,
-			       struct compat_timespec __user *);
-extern int get_compat_timeval(struct timeval *,
-			      const struct compat_timeval __user *);
-extern int put_compat_timeval(const struct timeval *,
-			      struct compat_timeval __user *);
 /*
  * These functions operate on 32- or 64-bit specs depending on
- * COMPAT_USE_64BIT_TIME, hence the void user pointer arguments and the
- * naming as compat_get/put_ rather than get/put_compat_.
+ * COMPAT_USE_64BIT_TIME, hence the void user pointer arguments.
  */
 extern int compat_get_timespec(struct timespec *, const void __user *);
 extern int compat_put_timespec(const struct timespec *, void __user *);
 extern int compat_get_timeval(struct timeval *, const void __user *);
 extern int compat_put_timeval(const struct timeval *, void __user *);
 
+/*
+ * This function convert a timespec if necessary and returns a *user
+ * space* pointer.  If no conversion is necessary, it returns the
+ * initial pointer.  NULL is a legitimate argument and will always
+ * output NULL.
+ */
+extern int compat_convert_timespec(struct timespec __user **,
+				   const void __user *);
+
 struct compat_iovec {
 	compat_uptr_t	iov_base;
 	compat_size_t	iov_len;
diff --git a/ipc/compat.c b/ipc/compat.c
index f486b0096a67..1048522479e5 100644
--- a/ipc/compat.c
+++ b/ipc/compat.c
@@ -752,14 +752,8 @@ long compat_sys_shmctl(int first, int second, void __user *uptr)
 long compat_sys_semtimedop(int semid, struct sembuf __user *tsems,
 		unsigned nsops, const struct compat_timespec __user *timeout)
 {
-	struct timespec __user *ts64 = NULL;
-	if (timeout) {
-		struct timespec ts;
-		ts64 = compat_alloc_user_space(sizeof(*ts64));
-		if (get_compat_timespec(&ts, timeout))
-			return -EFAULT;
-		if (copy_to_user(ts64, &ts, sizeof(ts)))
-			return -EFAULT;
-	}
+	struct timespec __user *ts64;
+	if (compat_convert_timespec(&ts64, timeout))
+		return -EFAULT;
 	return sys_semtimedop(semid, tsems, nsops, ts64);
 }
diff --git a/ipc/compat_mq.c b/ipc/compat_mq.c
index 63d7c6de335b..a9cf16378d7a 100644
--- a/ipc/compat_mq.c
+++ b/ipc/compat_mq.c
@@ -64,20 +64,6 @@ asmlinkage long compat_sys_mq_open(const char __user *u_name,
 	return sys_mq_open(u_name, oflag, mode, p);
 }
 
-static int compat_prepare_timeout(struct timespec __user **p,
-				  const struct compat_timespec __user *u)
-{
-	struct timespec ts;
-	if (!u) {
-		*p = NULL;
-		return 0;
-	}
-	*p = compat_alloc_user_space(sizeof(ts));
-	if (get_compat_timespec(&ts, u) || copy_to_user(*p, &ts, sizeof(ts)))
-		return -EFAULT;
-	return 0;
-}
-
 asmlinkage long compat_sys_mq_timedsend(mqd_t mqdes,
 			const char __user *u_msg_ptr,
 			size_t msg_len, unsigned int msg_prio,
@@ -85,7 +71,7 @@ asmlinkage long compat_sys_mq_timedsend(mqd_t mqdes,
 {
 	struct timespec __user *u_ts;
 
-	if (compat_prepare_timeout(&u_ts, u_abs_timeout))
+	if (compat_convert_timespec(&u_ts, u_abs_timeout))
 		return -EFAULT;
 
 	return sys_mq_timedsend(mqdes, u_msg_ptr, msg_len,
@@ -98,7 +84,8 @@ asmlinkage ssize_t compat_sys_mq_timedreceive(mqd_t mqdes,
 			const struct compat_timespec __user *u_abs_timeout)
 {
 	struct timespec __user *u_ts;
-	if (compat_prepare_timeout(&u_ts, u_abs_timeout))
+
+	if (compat_convert_timespec(&u_ts, u_abs_timeout))
 		return -EFAULT;
 
 	return sys_mq_timedreceive(mqdes, u_msg_ptr, msg_len,
diff --git a/kernel/compat.c b/kernel/compat.c
index 0a09e481b70b..3afc524a57ad 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -30,28 +30,6 @@
 
 #include <asm/uaccess.h>
 
-/*
- * Get/set struct timeval with struct timespec on the native side
- */
-static int compat_get_timeval_convert(struct timespec *o,
-				      struct compat_timeval __user *i)
-{
-	long usec;
-
-	if (get_user(o->tv_sec, &i->tv_sec) ||
-	    get_user(usec, &i->tv_usec))
-		return -EFAULT;
-	o->tv_nsec = usec * 1000;
-	return 0;
-}
-
-static int compat_put_timeval_convert(struct compat_timeval __user *o,
-				      struct timeval *i)
-{
-	return (put_user(i->tv_sec, &o->tv_sec) ||
-		put_user(i->tv_usec, &o->tv_usec)) ? -EFAULT : 0;
-}
-
 static int compat_get_timex(struct timex *txc, struct compat_timex __user *utp)
 {
 	memset(txc, 0, sizeof(struct timex));
@@ -116,7 +94,7 @@ asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv,
 	if (tv) {
 		struct timeval ktv;
 		do_gettimeofday(&ktv);
-		if (compat_put_timeval_convert(tv, &ktv))
+		if (compat_put_timeval(&ktv, tv))
 			return -EFAULT;
 	}
 	if (tz) {
@@ -130,59 +108,58 @@ asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv,
 asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv,
 		struct timezone __user *tz)
 {
-	struct timespec kts;
-	struct timezone ktz;
+	struct timeval user_tv;
+	struct timespec	new_ts;
+	struct timezone new_tz;
 
 	if (tv) {
-		if (compat_get_timeval_convert(&kts, tv))
+		if (compat_get_timeval(&user_tv, tv))
 			return -EFAULT;
+		new_ts.tv_sec = user_tv.tv_sec;
+		new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC;
 	}
 	if (tz) {
-		if (copy_from_user(&ktz, tz, sizeof(ktz)))
+		if (copy_from_user(&new_tz, tz, sizeof(*tz)))
 			return -EFAULT;
 	}
 
-	return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL);
+	return do_sys_settimeofday(tv ? &new_ts : NULL, tz ? &new_tz : NULL);
 }
 
-int get_compat_timeval(struct timeval *tv, const struct compat_timeval __user *ctv)
+static int __compat_get_timeval(struct timeval *tv, const struct compat_timeval __user *ctv)
 {
 	return (!access_ok(VERIFY_READ, ctv, sizeof(*ctv)) ||
 			__get_user(tv->tv_sec, &ctv->tv_sec) ||
 			__get_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0;
 }
-EXPORT_SYMBOL_GPL(get_compat_timeval);
 
-int put_compat_timeval(const struct timeval *tv, struct compat_timeval __user *ctv)
+static int __compat_put_timeval(const struct timeval *tv, struct compat_timeval __user *ctv)
 {
 	return (!access_ok(VERIFY_WRITE, ctv, sizeof(*ctv)) ||
 			__put_user(tv->tv_sec, &ctv->tv_sec) ||
 			__put_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0;
 }
-EXPORT_SYMBOL_GPL(put_compat_timeval);
 
-int get_compat_timespec(struct timespec *ts, const struct compat_timespec __user *cts)
+static int __compat_get_timespec(struct timespec *ts, const struct compat_timespec __user *cts)
 {
 	return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) ||
 			__get_user(ts->tv_sec, &cts->tv_sec) ||
 			__get_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0;
 }
-EXPORT_SYMBOL_GPL(get_compat_timespec);
 
-int put_compat_timespec(const struct timespec *ts, struct compat_timespec __user *cts)
+static int __compat_put_timespec(const struct timespec *ts, struct compat_timespec __user *cts)
 {
 	return (!access_ok(VERIFY_WRITE, cts, sizeof(*cts)) ||
 			__put_user(ts->tv_sec, &cts->tv_sec) ||
 			__put_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0;
 }
-EXPORT_SYMBOL_GPL(put_compat_timespec);
 
 int compat_get_timeval(struct timeval *tv, const void __user *utv)
 {
 	if (COMPAT_USE_64BIT_TIME)
 		return copy_from_user(tv, utv, sizeof *tv) ? -EFAULT : 0;
 	else
-		return get_compat_timeval(tv, utv);
+		return __compat_get_timeval(tv, utv);
 }
 EXPORT_SYMBOL_GPL(compat_get_timeval);
 
@@ -191,7 +168,7 @@ int compat_put_timeval(const struct timeval *tv, void __user *utv)
 	if (COMPAT_USE_64BIT_TIME)
 		return copy_to_user(utv, tv, sizeof *tv) ? -EFAULT : 0;
 	else
-		return put_compat_timeval(tv, utv);
+		return __compat_put_timeval(tv, utv);
 }
 EXPORT_SYMBOL_GPL(compat_put_timeval);
 
@@ -200,7 +177,7 @@ int compat_get_timespec(struct timespec *ts, const void __user *uts)
 	if (COMPAT_USE_64BIT_TIME)
 		return copy_from_user(ts, uts, sizeof *ts) ? -EFAULT : 0;
 	else
-		return get_compat_timespec(ts, uts);
+		return __compat_get_timespec(ts, uts);
 }
 EXPORT_SYMBOL_GPL(compat_get_timespec);
 
@@ -209,10 +186,33 @@ int compat_put_timespec(const struct timespec *ts, void __user *uts)
 	if (COMPAT_USE_64BIT_TIME)
 		return copy_to_user(uts, ts, sizeof *ts) ? -EFAULT : 0;
 	else
-		return put_compat_timespec(ts, uts);
+		return __compat_put_timespec(ts, uts);
 }
 EXPORT_SYMBOL_GPL(compat_put_timespec);
 
+int compat_convert_timespec(struct timespec __user **kts,
+			    const void __user *cts)
+{
+	struct timespec ts;
+	struct timespec __user *uts;
+
+	if (!cts || COMPAT_USE_64BIT_TIME) {
+		*kts = (struct timespec __user *)cts;
+		return 0;
+	}
+
+	uts = compat_alloc_user_space(sizeof(ts));
+	if (!uts)
+		return -EFAULT;
+	if (compat_get_timespec(&ts, cts))
+		return -EFAULT;
+	if (copy_to_user(uts, &ts, sizeof(ts)))
+		return -EFAULT;
+
+	*kts = uts;
+	return 0;
+}
+
 static long compat_nanosleep_restart(struct restart_block *restart)
 {
 	struct compat_timespec __user *rmtp;
@@ -229,7 +229,7 @@ static long compat_nanosleep_restart(struct restart_block *restart)
 	if (ret) {
 		rmtp = restart->nanosleep.compat_rmtp;
 
-		if (rmtp && put_compat_timespec(&rmt, rmtp))
+		if (rmtp && compat_put_timespec(&rmt, rmtp))
 			return -EFAULT;
 	}
 
@@ -243,7 +243,7 @@ asmlinkage long compat_sys_nanosleep(struct compat_timespec __user *rqtp,
 	mm_segment_t oldfs;
 	long ret;
 
-	if (get_compat_timespec(&tu, rqtp))
+	if (compat_get_timespec(&tu, rqtp))
 		return -EFAULT;
 
 	if (!timespec_valid(&tu))
@@ -263,7 +263,7 @@ asmlinkage long compat_sys_nanosleep(struct compat_timespec __user *rqtp,
 		restart->fn = compat_nanosleep_restart;
 		restart->nanosleep.compat_rmtp = rmtp;
 
-		if (rmtp && put_compat_timespec(&rmt, rmtp))
+		if (rmtp && compat_put_timespec(&rmt, rmtp))
 			return -EFAULT;
 	}
 
@@ -647,8 +647,8 @@ asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, unsigned int len,
 int get_compat_itimerspec(struct itimerspec *dst,
 			  const struct compat_itimerspec __user *src)
 {
-	if (get_compat_timespec(&dst->it_interval, &src->it_interval) ||
-	    get_compat_timespec(&dst->it_value, &src->it_value))
+	if (__compat_get_timespec(&dst->it_interval, &src->it_interval) ||
+	    __compat_get_timespec(&dst->it_value, &src->it_value))
 		return -EFAULT;
 	return 0;
 }
@@ -656,8 +656,8 @@ int get_compat_itimerspec(struct itimerspec *dst,
 int put_compat_itimerspec(struct compat_itimerspec __user *dst,
 			  const struct itimerspec *src)
 {
-	if (put_compat_timespec(&src->it_interval, &dst->it_interval) ||
-	    put_compat_timespec(&src->it_value, &dst->it_value))
+	if (__compat_put_timespec(&src->it_interval, &dst->it_interval) ||
+	    __compat_put_timespec(&src->it_value, &dst->it_value))
 		return -EFAULT;
 	return 0;
 }
@@ -727,7 +727,7 @@ long compat_sys_clock_settime(clockid_t which_clock,
 	mm_segment_t oldfs;
 	struct timespec ts;
 
-	if (get_compat_timespec(&ts, tp))
+	if (compat_get_timespec(&ts, tp))
 		return -EFAULT;
 	oldfs = get_fs();
 	set_fs(KERNEL_DS);
@@ -749,7 +749,7 @@ long compat_sys_clock_gettime(clockid_t which_clock,
 	err = sys_clock_gettime(which_clock,
 				(struct timespec __user *) &ts);
 	set_fs(oldfs);
-	if (!err && put_compat_timespec(&ts, tp))
+	if (!err && compat_put_timespec(&ts, tp))
 		return -EFAULT;
 	return err;
 }
@@ -789,7 +789,7 @@ long compat_sys_clock_getres(clockid_t which_clock,
 	err = sys_clock_getres(which_clock,
 			       (struct timespec __user *) &ts);
 	set_fs(oldfs);
-	if (!err && tp && put_compat_timespec(&ts, tp))
+	if (!err && tp && compat_put_timespec(&ts, tp))
 		return -EFAULT;
 	return err;
 }
@@ -808,7 +808,7 @@ static long compat_clock_nanosleep_restart(struct restart_block *restart)
 	set_fs(oldfs);
 
 	if ((err == -ERESTART_RESTARTBLOCK) && rmtp &&
-	    put_compat_timespec(&tu, rmtp))
+	    compat_put_timespec(&tu, rmtp))
 		return -EFAULT;
 
 	if (err == -ERESTART_RESTARTBLOCK) {
@@ -827,7 +827,7 @@ long compat_sys_clock_nanosleep(clockid_t which_clock, int flags,
 	struct timespec in, out;
 	struct restart_block *restart;
 
-	if (get_compat_timespec(&in, rqtp))
+	if (compat_get_timespec(&in, rqtp))
 		return -EFAULT;
 
 	oldfs = get_fs();
@@ -838,7 +838,7 @@ long compat_sys_clock_nanosleep(clockid_t which_clock, int flags,
 	set_fs(oldfs);
 
 	if ((err == -ERESTART_RESTARTBLOCK) && rmtp &&
-	    put_compat_timespec(&out, rmtp))
+	    compat_put_timespec(&out, rmtp))
 		return -EFAULT;
 
 	if (err == -ERESTART_RESTARTBLOCK) {
@@ -1130,7 +1130,7 @@ COMPAT_SYSCALL_DEFINE2(sched_rr_get_interval,
 	set_fs(KERNEL_DS);
 	ret = sys_sched_rr_get_interval(pid, (struct timespec __user *)&t);
 	set_fs(old_fs);
-	if (put_compat_timespec(&t, interval))
+	if (compat_put_timespec(&t, interval))
 		return -EFAULT;
 	return ret;
 }
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index f9f44fd4d34d..55c8c9349cfe 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -183,7 +183,7 @@ COMPAT_SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
 	if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI ||
 		      cmd == FUTEX_WAIT_BITSET ||
 		      cmd == FUTEX_WAIT_REQUEUE_PI)) {
-		if (get_compat_timespec(&ts, utime))
+		if (compat_get_timespec(&ts, utime))
 			return -EFAULT;
 		if (!timespec_valid(&ts))
 			return -EINVAL;
-- 
cgit v1.2.3


From fc0a5921561c71be2c334a335c1680f7930434d7 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime.ripard@free-electrons.com>
Date: Fri, 20 Dec 2013 22:41:07 +0100
Subject: reset: Add of_reset_control_get

In some cases, you might need to deassert from reset an hardware block that
doesn't associated to a struct device (CPUs, timers, etc.).

Add a small helper to retrieve the reset controller from the device tree
without the need to pass a struct device.

Signed-off-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/reset/core.c  | 39 ++++++++++++++++++++++++++++++---------
 include/linux/reset.h |  4 ++++
 2 files changed, 34 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/reset/core.c b/drivers/reset/core.c
index 217d2fa4fd95..baeaf82d40d9 100644
--- a/drivers/reset/core.c
+++ b/drivers/reset/core.c
@@ -126,15 +126,16 @@ int reset_control_deassert(struct reset_control *rstc)
 EXPORT_SYMBOL_GPL(reset_control_deassert);
 
 /**
- * reset_control_get - Lookup and obtain a reference to a reset controller.
- * @dev: device to be reset by the controller
+ * of_reset_control_get - Lookup and obtain a reference to a reset controller.
+ * @node: device to be reset by the controller
  * @id: reset line name
  *
  * Returns a struct reset_control or IS_ERR() condition containing errno.
  *
  * Use of id names is optional.
  */
-struct reset_control *reset_control_get(struct device *dev, const char *id)
+struct reset_control *of_reset_control_get(struct device_node *node,
+					   const char *id)
 {
 	struct reset_control *rstc = ERR_PTR(-EPROBE_DEFER);
 	struct reset_controller_dev *r, *rcdev;
@@ -143,13 +144,10 @@ struct reset_control *reset_control_get(struct device *dev, const char *id)
 	int rstc_id;
 	int ret;
 
-	if (!dev)
-		return ERR_PTR(-EINVAL);
-
 	if (id)
-		index = of_property_match_string(dev->of_node,
+		index = of_property_match_string(node,
 						 "reset-names", id);
-	ret = of_parse_phandle_with_args(dev->of_node, "resets", "#reset-cells",
+	ret = of_parse_phandle_with_args(node, "resets", "#reset-cells",
 					 index, &args);
 	if (ret)
 		return ERR_PTR(ret);
@@ -184,12 +182,35 @@ struct reset_control *reset_control_get(struct device *dev, const char *id)
 		return ERR_PTR(-ENOMEM);
 	}
 
-	rstc->dev = dev;
 	rstc->rcdev = rcdev;
 	rstc->id = rstc_id;
 
 	return rstc;
 }
+EXPORT_SYMBOL_GPL(of_reset_control_get);
+
+/**
+ * reset_control_get - Lookup and obtain a reference to a reset controller.
+ * @dev: device to be reset by the controller
+ * @id: reset line name
+ *
+ * Returns a struct reset_control or IS_ERR() condition containing errno.
+ *
+ * Use of id names is optional.
+ */
+struct reset_control *reset_control_get(struct device *dev, const char *id)
+{
+	struct reset_control *rstc;
+
+	if (!dev)
+		return ERR_PTR(-EINVAL);
+
+	rstc = of_reset_control_get(dev->of_node, id);
+	if (!IS_ERR(rstc))
+		rstc->dev = dev;
+
+	return rstc;
+}
 EXPORT_SYMBOL_GPL(reset_control_get);
 
 /**
diff --git a/include/linux/reset.h b/include/linux/reset.h
index 6082247feab1..a398025d1138 100644
--- a/include/linux/reset.h
+++ b/include/linux/reset.h
@@ -1,6 +1,8 @@
 #ifndef _LINUX_RESET_H_
 #define _LINUX_RESET_H_
 
+#include <linux/of.h>
+
 struct device;
 struct reset_control;
 
@@ -8,6 +10,8 @@ int reset_control_reset(struct reset_control *rstc);
 int reset_control_assert(struct reset_control *rstc);
 int reset_control_deassert(struct reset_control *rstc);
 
+struct reset_control *of_reset_control_get(struct device_node *node,
+					   const char *id);
 struct reset_control *reset_control_get(struct device *dev, const char *id);
 void reset_control_put(struct reset_control *rstc);
 struct reset_control *devm_reset_control_get(struct device *dev, const char *id);
-- 
cgit v1.2.3


From 99adef310f682d6343cb40c1f6c9c25a4b3a450d Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@linaro.org>
Date: Thu, 16 Jan 2014 12:22:43 +0000
Subject: spi: Provide core support for DMA mapping transfers

The process of DMA mapping buffers for SPI transfers does not vary between
devices so in order to save duplication of code in drivers this can be
factored out into the core, allowing it to be integrated with the work that
is being done on factoring out the common elements from the data path
including more sharing of dmaengine code.

In order to use this masters need to provide a can_dma() operation and while
the hardware is prepared they should ensure that DMA channels are provided
in tx_dma and rx_dma. The core will then ensure that the buffers are mapped
for DMA prior to calling transfer_one_message().

Currently the cleanup on error is not complete, this needs to be improved.

Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/spi/spi.c       | 82 +++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/spi/spi.h | 18 +++++++++++
 2 files changed, 100 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 23756b0f9036..bcdaa74f1c8e 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -24,6 +24,8 @@
 #include <linux/device.h>
 #include <linux/init.h>
 #include <linux/cache.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
 #include <linux/mutex.h>
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
@@ -580,6 +582,77 @@ static void spi_set_cs(struct spi_device *spi, bool enable)
 		spi->master->set_cs(spi, !enable);
 }
 
+static int spi_map_msg(struct spi_master *master, struct spi_message *msg)
+{
+	struct device *dev = master->dev.parent;
+	struct device *tx_dev, *rx_dev;
+	struct spi_transfer *xfer;
+
+	if (msg->is_dma_mapped || !master->can_dma)
+		return 0;
+
+	tx_dev = &master->dma_tx->dev->device;
+	rx_dev = &master->dma_rx->dev->device;
+
+	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+		if (!master->can_dma(master, msg->spi, xfer))
+			continue;
+
+		if (xfer->tx_buf != NULL) {
+			xfer->tx_dma = dma_map_single(tx_dev,
+						      (void *)xfer->tx_buf,
+						      xfer->len,
+						      DMA_TO_DEVICE);
+			if (dma_mapping_error(dev, xfer->tx_dma)) {
+				dev_err(dev, "dma_map_single Tx failed\n");
+				return -ENOMEM;
+			}
+		}
+
+		if (xfer->rx_buf != NULL) {
+			xfer->rx_dma = dma_map_single(rx_dev,
+						      xfer->rx_buf, xfer->len,
+						      DMA_FROM_DEVICE);
+			if (dma_mapping_error(dev, xfer->rx_dma)) {
+				dev_err(dev, "dma_map_single Rx failed\n");
+				dma_unmap_single(tx_dev, xfer->tx_dma,
+						 xfer->len, DMA_TO_DEVICE);
+				return -ENOMEM;
+			}
+		}
+	}
+
+	master->cur_msg_mapped = true;
+
+	return 0;
+}
+
+static int spi_unmap_msg(struct spi_master *master, struct spi_message *msg)
+{
+	struct spi_transfer *xfer;
+	struct device *tx_dev, *rx_dev;
+
+	if (!master->cur_msg_mapped || msg->is_dma_mapped || !master->can_dma)
+		return 0;
+
+	tx_dev = &master->dma_tx->dev->device;
+	rx_dev = &master->dma_rx->dev->device;
+
+	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+		if (!master->can_dma(master, msg->spi, xfer))
+			continue;
+
+		if (xfer->rx_buf)
+			dma_unmap_single(rx_dev, xfer->rx_dma, xfer->len,
+					 DMA_FROM_DEVICE);
+		if (xfer->tx_buf)
+			dma_unmap_single(tx_dev, xfer->tx_dma, xfer->len,
+					 DMA_TO_DEVICE);
+	}
+
+	return 0;
+}
+
 /*
  * spi_transfer_one_message - Default implementation of transfer_one_message()
  *
@@ -752,6 +825,13 @@ static void spi_pump_messages(struct kthread_work *work)
 		master->cur_msg_prepared = true;
 	}
 
+	ret = spi_map_msg(master, master->cur_msg);
+	if (ret) {
+		master->cur_msg->status = ret;
+		spi_finalize_current_message(master);
+		return;
+	}
+
 	ret = master->transfer_one_message(master, master->cur_msg);
 	if (ret) {
 		dev_err(&master->dev,
@@ -841,6 +921,8 @@ void spi_finalize_current_message(struct spi_master *master)
 	queue_kthread_work(&master->kworker, &master->pump_messages);
 	spin_unlock_irqrestore(&master->queue_lock, flags);
 
+	spi_unmap_msg(master, mesg);
+
 	if (master->cur_msg_prepared && master->unprepare_message) {
 		ret = master->unprepare_message(master, mesg);
 		if (ret) {
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index a1d4ca290862..b354dcbed55b 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -25,6 +25,8 @@
 #include <linux/kthread.h>
 #include <linux/completion.h>
 
+struct dma_chan;
+
 /*
  * INTERFACES between SPI master-side drivers and SPI infrastructure.
  * (There's no SPI slave support for Linux yet...)
@@ -386,6 +388,17 @@ struct spi_master {
 	/* called on release() to free memory provided by spi_master */
 	void			(*cleanup)(struct spi_device *spi);
 
+	/*
+	 * Used to enable core support for DMA handling, if can_dma()
+	 * exists and returns true then the transfer will be mapped
+	 * prior to transfer_one() being called.  The driver should
+	 * not modify or store xfer and dma_tx and dma_rx must be set
+	 * while the device is prepared.
+	 */
+	bool			(*can_dma)(struct spi_master *master,
+					   struct spi_device *spi,
+					   struct spi_transfer *xfer);
+
 	/*
 	 * These hooks are for drivers that want to use the generic
 	 * master transfer queueing mechanism. If these are used, the
@@ -404,6 +417,7 @@ struct spi_master {
 	bool				rt;
 	bool				auto_runtime_pm;
 	bool                            cur_msg_prepared;
+	bool				cur_msg_mapped;
 	struct completion               xfer_completion;
 
 	int (*prepare_transfer_hardware)(struct spi_master *master);
@@ -425,6 +439,10 @@ struct spi_master {
 
 	/* gpio chip select */
 	int			*cs_gpios;
+
+	/* DMA channels for use with core dmaengine helpers */
+	struct dma_chan		*dma_tx;
+	struct dma_chan		*dma_rx;
 };
 
 static inline void *spi_master_get_devdata(struct spi_master *master)
-- 
cgit v1.2.3


From 588453c69dace39351129a038dd2796608f74bb3 Mon Sep 17 00:00:00 2001
From: Pantelis Antoniou <panto@antoniou-consulting.com>
Date: Fri, 8 Nov 2013 17:03:56 +0200
Subject: of: Introduce device tree node flag helpers.

Helper functions for working with device node flags.

Signed-off-by: Pantelis Antoniou <panto@antoniou-consulting.com>
Signed-off-by: Grant Likely <grant.likely@linaro.org>
---
 include/linux/of.h | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/of.h b/include/linux/of.h
index 70c64ba17fa5..3d0593943f47 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -114,6 +114,26 @@ static inline void of_node_set_flag(struct device_node *n, unsigned long flag)
 	set_bit(flag, &n->_flags);
 }
 
+static inline void of_node_clear_flag(struct device_node *n, unsigned long flag)
+{
+	clear_bit(flag, &n->_flags);
+}
+
+static inline int of_property_check_flag(struct property *p, unsigned long flag)
+{
+	return test_bit(flag, &p->_flags);
+}
+
+static inline void of_property_set_flag(struct property *p, unsigned long flag)
+{
+	set_bit(flag, &p->_flags);
+}
+
+static inline void of_property_clear_flag(struct property *p, unsigned long flag)
+{
+	clear_bit(flag, &p->_flags);
+}
+
 extern struct device_node *of_find_all_nodes(struct device_node *prev);
 
 /*
-- 
cgit v1.2.3


From 486c79b5002e4a75c1c3614180702196ec6d904d Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Fri, 24 Jan 2014 15:25:10 -0700
Subject: ACPI / numa: Fix acpi_get_node() prototype

acpi_get_node() takes an acpi_handle, not an "acpi_handle *".  This
fixes the prototype and the definitions.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/numa.c  | 2 +-
 include/linux/acpi.h | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c
index 9e6816ef280a..dab7dac6b1a8 100644
--- a/drivers/acpi/numa.c
+++ b/drivers/acpi/numa.c
@@ -331,7 +331,7 @@ int acpi_get_pxm(acpi_handle h)
 	return -1;
 }
 
-int acpi_get_node(acpi_handle *handle)
+int acpi_get_node(acpi_handle handle)
 {
 	int pxm, node = NUMA_NO_NODE;
 
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 1151a1dcfe41..17bee650a0cb 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -260,13 +260,13 @@ extern void acpi_osi_setup(char *str);
 
 #ifdef CONFIG_ACPI_NUMA
 int acpi_get_pxm(acpi_handle handle);
-int acpi_get_node(acpi_handle *handle);
+int acpi_get_node(acpi_handle handle);
 #else
 static inline int acpi_get_pxm(acpi_handle handle)
 {
 	return 0;
 }
-static inline int acpi_get_node(acpi_handle *handle)
+static inline int acpi_get_node(acpi_handle handle)
 {
 	return 0;
 }
-- 
cgit v1.2.3


From d79ed248d923f219053760376a33371894a6d47c Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Fri, 24 Jan 2014 15:48:01 -0700
Subject: ACPI / numa: Make __acpi_map_pxm_to_node(), acpi_get_pxm() static

__acpi_map_pxm_to_node() and acpi_get_pxm() are only used within
drivers/acpi/numa.c.  This makes them static and removes their
declarations.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/numa.c      | 4 ++--
 include/acpi/acpi_numa.h | 1 -
 include/linux/acpi.h     | 5 -----
 3 files changed, 2 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c
index a7e779bfa2f6..359a43bdd948 100644
--- a/drivers/acpi/numa.c
+++ b/drivers/acpi/numa.c
@@ -60,7 +60,7 @@ int node_to_pxm(int node)
 	return node_to_pxm_map[node];
 }
 
-void __acpi_map_pxm_to_node(int pxm, int node)
+static void __acpi_map_pxm_to_node(int pxm, int node)
 {
 	if (pxm_to_node_map[pxm] == NUMA_NO_NODE || node < pxm_to_node_map[pxm])
 		pxm_to_node_map[pxm] = node;
@@ -314,7 +314,7 @@ int __init acpi_numa_init(void)
 	return 0;
 }
 
-int acpi_get_pxm(acpi_handle h)
+static int acpi_get_pxm(acpi_handle h)
 {
 	unsigned long long pxm;
 	acpi_status status;
diff --git a/include/acpi/acpi_numa.h b/include/acpi/acpi_numa.h
index 451823cb8837..94a37cd7fbda 100644
--- a/include/acpi/acpi_numa.h
+++ b/include/acpi/acpi_numa.h
@@ -13,7 +13,6 @@
 
 extern int pxm_to_node(int);
 extern int node_to_pxm(int);
-extern void __acpi_map_pxm_to_node(int, int);
 extern int acpi_map_pxm_to_node(int);
 extern unsigned char acpi_srat_revision;
 
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 17bee650a0cb..6c29abbefd41 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -259,13 +259,8 @@ extern void acpi_dmi_osi_linux(int enable, const struct dmi_system_id *d);
 extern void acpi_osi_setup(char *str);
 
 #ifdef CONFIG_ACPI_NUMA
-int acpi_get_pxm(acpi_handle handle);
 int acpi_get_node(acpi_handle handle);
 #else
-static inline int acpi_get_pxm(acpi_handle handle)
-{
-	return 0;
-}
 static inline int acpi_get_node(acpi_handle handle)
 {
 	return 0;
-- 
cgit v1.2.3


From d1debafc381cb1fa340b5d0dc79637ad1d523770 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@ti.com>
Date: Mon, 3 Feb 2014 14:51:51 +0200
Subject: ASoC: davinci-mcasp: Rename platform data struct

Rename the struct for the platform data:
snd_platform_data -> davinci_mcasp_pdata

Since we have users under arch/arm/mach-davinci/ for this struct add
temporary define to avoid breakage. The arch code can be updated later to
use the new struct name.

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/linux/platform_data/davinci_asp.h |  4 +++-
 sound/soc/davinci/davinci-mcasp.c         | 16 ++++++++--------
 2 files changed, 11 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/davinci_asp.h b/include/linux/platform_data/davinci_asp.h
index 5245992b0367..85ad68f9206a 100644
--- a/include/linux/platform_data/davinci_asp.h
+++ b/include/linux/platform_data/davinci_asp.h
@@ -18,7 +18,7 @@
 
 #include <linux/genalloc.h>
 
-struct snd_platform_data {
+struct davinci_mcasp_pdata {
 	u32 tx_dma_offset;
 	u32 rx_dma_offset;
 	int asp_chan_q;	/* event queue number for ASP channel */
@@ -87,6 +87,8 @@ struct snd_platform_data {
 	int tx_dma_channel;
 	int rx_dma_channel;
 };
+/* TODO: Fix arch/arm/mach-davinci/ users and remove this define */
+#define snd_platform_data davinci_mcasp_pdata
 
 enum {
 	MCASP_VERSION_1 = 0,	/* DM646x */
diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c
index 63b1ecc97cb1..e5fce2ed4dc6 100644
--- a/sound/soc/davinci/davinci-mcasp.c
+++ b/sound/soc/davinci/davinci-mcasp.c
@@ -823,28 +823,28 @@ static const struct snd_soc_component_driver davinci_mcasp_component = {
 };
 
 /* Some HW specific values and defaults. The rest is filled in from DT. */
-static struct snd_platform_data dm646x_mcasp_pdata = {
+static struct davinci_mcasp_pdata dm646x_mcasp_pdata = {
 	.tx_dma_offset = 0x400,
 	.rx_dma_offset = 0x400,
 	.asp_chan_q = EVENTQ_0,
 	.version = MCASP_VERSION_1,
 };
 
-static struct snd_platform_data da830_mcasp_pdata = {
+static struct davinci_mcasp_pdata da830_mcasp_pdata = {
 	.tx_dma_offset = 0x2000,
 	.rx_dma_offset = 0x2000,
 	.asp_chan_q = EVENTQ_0,
 	.version = MCASP_VERSION_2,
 };
 
-static struct snd_platform_data am33xx_mcasp_pdata = {
+static struct davinci_mcasp_pdata am33xx_mcasp_pdata = {
 	.tx_dma_offset = 0,
 	.rx_dma_offset = 0,
 	.asp_chan_q = EVENTQ_0,
 	.version = MCASP_VERSION_3,
 };
 
-static struct snd_platform_data dra7_mcasp_pdata = {
+static struct davinci_mcasp_pdata dra7_mcasp_pdata = {
 	.tx_dma_offset = 0x200,
 	.rx_dma_offset = 0x284,
 	.asp_chan_q = EVENTQ_0,
@@ -912,11 +912,11 @@ err1:
 	return ret;
 }
 
-static struct snd_platform_data *davinci_mcasp_set_pdata_from_of(
+static struct davinci_mcasp_pdata *davinci_mcasp_set_pdata_from_of(
 						struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
-	struct snd_platform_data *pdata = NULL;
+	struct davinci_mcasp_pdata *pdata = NULL;
 	const struct of_device_id *match =
 			of_match_device(mcasp_dt_ids, &pdev->dev);
 	struct of_phandle_args dma_spec;
@@ -929,7 +929,7 @@ static struct snd_platform_data *davinci_mcasp_set_pdata_from_of(
 		pdata = pdev->dev.platform_data;
 		return pdata;
 	} else if (match) {
-		pdata = (struct snd_platform_data *) match->data;
+		pdata = (struct davinci_mcasp_pdata*) match->data;
 	} else {
 		/* control shouldn't reach here. something is wrong */
 		ret = -EINVAL;
@@ -1023,7 +1023,7 @@ static int davinci_mcasp_probe(struct platform_device *pdev)
 {
 	struct davinci_pcm_dma_params *dma_data;
 	struct resource *mem, *ioarea, *res, *dat;
-	struct snd_platform_data *pdata;
+	struct davinci_mcasp_pdata *pdata;
 	struct davinci_mcasp *mcasp;
 	int ret;
 
-- 
cgit v1.2.3


From a028c6da34d434e35ba8322568c756ea97ff3c18 Mon Sep 17 00:00:00 2001
From: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Date: Sat, 14 Dec 2013 16:23:51 +0100
Subject: ARM: shmobile: wait for MSTP clock status to toggle, when enabling it

On r-/sh-mobile SoCs MSTP clocks are used by the runtime PM to dynamically
enable and disable peripheral clocks. To make sure the clock has really
started we have to read back its status register until it confirms success.

Signed-off-by: Guennadi Liakhovetski <g.liakhovetski+renesas@gmail.com>
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
---
 drivers/sh/clk/cpg.c   | 38 ++++++++++++++++++++++++++++++++++++++
 include/linux/sh_clk.h | 19 ++++++++++++-------
 2 files changed, 50 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/sh/clk/cpg.c b/drivers/sh/clk/cpg.c
index 1ebe67cd1833..7442bc130055 100644
--- a/drivers/sh/clk/cpg.c
+++ b/drivers/sh/clk/cpg.c
@@ -36,9 +36,47 @@ static void sh_clk_write(int value, struct clk *clk)
 		iowrite32(value, clk->mapped_reg);
 }
 
+static unsigned int r8(const void __iomem *addr)
+{
+	return ioread8(addr);
+}
+
+static unsigned int r16(const void __iomem *addr)
+{
+	return ioread16(addr);
+}
+
+static unsigned int r32(const void __iomem *addr)
+{
+	return ioread32(addr);
+}
+
 static int sh_clk_mstp_enable(struct clk *clk)
 {
 	sh_clk_write(sh_clk_read(clk) & ~(1 << clk->enable_bit), clk);
+	if (clk->status_reg) {
+		unsigned int (*read)(const void __iomem *addr);
+		int i;
+		void __iomem *mapped_status = (phys_addr_t)clk->status_reg -
+			(phys_addr_t)clk->enable_reg + clk->mapped_reg;
+
+		if (clk->flags & CLK_ENABLE_REG_8BIT)
+			read = r8;
+		else if (clk->flags & CLK_ENABLE_REG_16BIT)
+			read = r16;
+		else
+			read = r32;
+
+		for (i = 1000;
+		     (read(mapped_status) & (1 << clk->enable_bit)) && i;
+		     i--)
+			cpu_relax();
+		if (!i) {
+			pr_err("cpg: failed to enable %p[%d]\n",
+			       clk->enable_reg, clk->enable_bit);
+			return -ETIMEDOUT;
+		}
+	}
 	return 0;
 }
 
diff --git a/include/linux/sh_clk.h b/include/linux/sh_clk.h
index 60c72395ec6b..1f208b2a1ed6 100644
--- a/include/linux/sh_clk.h
+++ b/include/linux/sh_clk.h
@@ -52,6 +52,7 @@ struct clk {
 	unsigned long		flags;
 
 	void __iomem		*enable_reg;
+	void __iomem		*status_reg;
 	unsigned int		enable_bit;
 	void __iomem		*mapped_reg;
 
@@ -116,22 +117,26 @@ long clk_round_parent(struct clk *clk, unsigned long target,
 		      unsigned long *best_freq, unsigned long *parent_freq,
 		      unsigned int div_min, unsigned int div_max);
 
-#define SH_CLK_MSTP(_parent, _enable_reg, _enable_bit, _flags)		\
+#define SH_CLK_MSTP(_parent, _enable_reg, _enable_bit, _status_reg, _flags) \
 {									\
 	.parent		= _parent,					\
 	.enable_reg	= (void __iomem *)_enable_reg,			\
 	.enable_bit	= _enable_bit,					\
+	.status_reg	= _status_reg,					\
 	.flags		= _flags,					\
 }
 
-#define SH_CLK_MSTP32(_p, _r, _b, _f)					\
-	SH_CLK_MSTP(_p, _r, _b, _f | CLK_ENABLE_REG_32BIT)
+#define SH_CLK_MSTP32(_p, _r, _b, _f)				\
+	SH_CLK_MSTP(_p, _r, _b, 0, _f | CLK_ENABLE_REG_32BIT)
 
-#define SH_CLK_MSTP16(_p, _r, _b, _f)					\
-	SH_CLK_MSTP(_p, _r, _b, _f | CLK_ENABLE_REG_16BIT)
+#define SH_CLK_MSTP32_STS(_p, _r, _b, _s, _f)			\
+	SH_CLK_MSTP(_p, _r, _b, _s, _f | CLK_ENABLE_REG_32BIT)
 
-#define SH_CLK_MSTP8(_p, _r, _b, _f)					\
-	SH_CLK_MSTP(_p, _r, _b, _f | CLK_ENABLE_REG_8BIT)
+#define SH_CLK_MSTP16(_p, _r, _b, _f)				\
+	SH_CLK_MSTP(_p, _r, _b, 0, _f | CLK_ENABLE_REG_16BIT)
+
+#define SH_CLK_MSTP8(_p, _r, _b, _f)				\
+	SH_CLK_MSTP(_p, _r, _b, 0, _f | CLK_ENABLE_REG_8BIT)
 
 int sh_clk_mstp_register(struct clk *clks, int nr);
 
-- 
cgit v1.2.3


From cb2518ca9f06dfcfa3d175773631bfb1e461bdc7 Mon Sep 17 00:00:00 2001
From: Stephane Grosjean <s.grosjean@peak-system.com>
Date: Wed, 15 Jan 2014 09:50:13 +0100
Subject: can: add ability to allocate CANFD frame in skb data

This patch adds the ability of allocating a CANFD frame data structure in the
skb data area.

Signed-off-by: Stephane Grosjean <s.grosjean@peak-system.com>
Acked-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dev.c   | 24 ++++++++++++++++++++++++
 include/linux/can/dev.h |  2 ++
 2 files changed, 26 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 13a909822e25..cb584ea00331 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -521,6 +521,30 @@ struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf)
 }
 EXPORT_SYMBOL_GPL(alloc_can_skb);
 
+struct sk_buff *alloc_canfd_skb(struct net_device *dev,
+				struct canfd_frame **cfd)
+{
+	struct sk_buff *skb;
+
+	skb = netdev_alloc_skb(dev, sizeof(struct can_skb_priv) +
+			       sizeof(struct canfd_frame));
+	if (unlikely(!skb))
+		return NULL;
+
+	skb->protocol = htons(ETH_P_CANFD);
+	skb->pkt_type = PACKET_BROADCAST;
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+	can_skb_reserve(skb);
+	can_skb_prv(skb)->ifindex = dev->ifindex;
+
+	*cfd = (struct canfd_frame *)skb_put(skb, sizeof(struct canfd_frame));
+	memset(*cfd, 0, sizeof(struct canfd_frame));
+
+	return skb;
+}
+EXPORT_SYMBOL_GPL(alloc_canfd_skb);
+
 struct sk_buff *alloc_can_err_skb(struct net_device *dev, struct can_frame **cf)
 {
 	struct sk_buff *skb;
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index fb0ab651a041..dc5f9026b67f 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -124,6 +124,8 @@ unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx);
 void can_free_echo_skb(struct net_device *dev, unsigned int idx);
 
 struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf);
+struct sk_buff *alloc_canfd_skb(struct net_device *dev,
+				struct canfd_frame **cfd);
 struct sk_buff *alloc_can_err_skb(struct net_device *dev,
 				  struct can_frame **cf);
 
-- 
cgit v1.2.3


From 3a2eba9bd0a6447dfbc01635e4cd0689f5f2bdad Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@linaro.org>
Date: Tue, 28 Jan 2014 20:17:03 +0000
Subject: spi: Provide core support for full duplex devices

It is fairly common for SPI devices to require that one or both transfer
directions is always active. Currently drivers open code this in various
ways with varying degrees of efficiency. Start factoring this out by
providing flags SPI_MASTER_MUST_TX and SPI_MASTER_MUST_RX. These will cause
the core to provide buffers for the requested direction if none are
specified in the underlying transfer.

Currently this is fairly inefficient since we actually allocate a data
buffer which may get large, support for mapping transfers using a
scatterlist will allow us to avoid this for DMA based transfers.

Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/spi/spi.c       | 47 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/spi/spi.h |  6 ++++++
 2 files changed, 53 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index bcdaa74f1c8e..bb7cf561c311 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -587,6 +587,49 @@ static int spi_map_msg(struct spi_master *master, struct spi_message *msg)
 	struct device *dev = master->dev.parent;
 	struct device *tx_dev, *rx_dev;
 	struct spi_transfer *xfer;
+	void *tmp;
+	size_t max_tx, max_rx;
+
+	if (master->flags & (SPI_MASTER_MUST_RX | SPI_MASTER_MUST_TX)) {
+		max_tx = 0;
+		max_rx = 0;
+
+		list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+			if ((master->flags & SPI_MASTER_MUST_TX) &&
+			    !xfer->tx_buf)
+				max_tx = max(xfer->len, max_tx);
+			if ((master->flags & SPI_MASTER_MUST_RX) &&
+			    !xfer->rx_buf)
+				max_rx = max(xfer->len, max_rx);
+		}
+
+		if (max_tx) {
+			tmp = krealloc(master->dummy_tx, max_tx,
+				       GFP_KERNEL | GFP_DMA);
+			if (!tmp)
+				return -ENOMEM;
+			master->dummy_tx = tmp;
+			memset(tmp, 0, max_tx);
+		}
+
+		if (max_rx) {
+			tmp = krealloc(master->dummy_rx, max_rx,
+				       GFP_KERNEL | GFP_DMA);
+			if (!tmp)
+				return -ENOMEM;
+			master->dummy_rx = tmp;
+		}
+
+		if (max_tx || max_rx) {
+			list_for_each_entry(xfer, &msg->transfers,
+					    transfer_list) {
+				if (!xfer->tx_buf)
+					xfer->tx_buf = master->dummy_tx;
+				if (!xfer->rx_buf)
+					xfer->rx_buf = master->dummy_rx;
+			}
+		}
+	}
 
 	if (msg->is_dma_mapped || !master->can_dma)
 		return 0;
@@ -759,6 +802,10 @@ static void spi_pump_messages(struct kthread_work *work)
 		}
 		master->busy = false;
 		spin_unlock_irqrestore(&master->queue_lock, flags);
+		kfree(master->dummy_rx);
+		master->dummy_rx = NULL;
+		kfree(master->dummy_tx);
+		master->dummy_tx = NULL;
 		if (master->unprepare_transfer_hardware &&
 		    master->unprepare_transfer_hardware(master))
 			dev_err(&master->dev,
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index b354dcbed55b..31a5b0ee93ec 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -347,6 +347,8 @@ struct spi_master {
 #define SPI_MASTER_HALF_DUPLEX	BIT(0)		/* can't do full duplex */
 #define SPI_MASTER_NO_RX	BIT(1)		/* can't do buffer read */
 #define SPI_MASTER_NO_TX	BIT(2)		/* can't do buffer write */
+#define SPI_MASTER_MUST_RX      BIT(3)		/* requires rx */
+#define SPI_MASTER_MUST_TX      BIT(4)		/* requires tx */
 
 	/* lock and mutex for SPI bus locking */
 	spinlock_t		bus_lock_spinlock;
@@ -443,6 +445,10 @@ struct spi_master {
 	/* DMA channels for use with core dmaengine helpers */
 	struct dma_chan		*dma_tx;
 	struct dma_chan		*dma_rx;
+
+	/* dummy data for full duplex devices */
+	void			*dummy_rx;
+	void			*dummy_tx;
 };
 
 static inline void *spi_master_get_devdata(struct spi_master *master)
-- 
cgit v1.2.3


From 6ad45a27cbe343ec8d7888e5edf6335499a4b555 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@linaro.org>
Date: Sun, 2 Feb 2014 13:47:47 +0000
Subject: spi: Make core DMA mapping functions generate scatterlists

We cannot unconditionally use dma_map_single() to map data for use with
SPI since transfers may exceed a page and virtual addresses may not be
provided with physically contiguous pages. Further, addresses allocated
using vmalloc() need to be mapped differently to other addresses.

Currently only the MXS driver handles all this, a few drivers do handle
the possibility that buffers may not be physically contiguous which is
the main potential problem but many don't even do that. Factoring this
out into the core will make it easier for drivers to do a good job so if
the driver is using the core DMA code then generate a scatterlist
instead of mapping to a single address so do that.

This code is mainly based on a combination of the existing code in the MXS
and PXA2xx drivers. In future we should be able to extend it to allow the
core to concatenate adjacent transfers if they are compatible, improving
performance.

Currently for simplicity clients are not allowed to use the scatterlist
when they do DMA mapping, in the future the existing single address
mappings will be replaced with use of the scatterlist most likely as
part of pre-verifying transfers.

This change makes it mandatory to use scatterlists when using the core DMA
mapping so update the s3c64xx driver to do this when used with dmaengine.
Doing so makes the code more ugly but it is expected that the old s3c-dma
code can be removed very soon.

Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/spi/spi-s3c64xx.c |  14 +++++--
 drivers/spi/spi.c         | 101 ++++++++++++++++++++++++++++++++++------------
 include/linux/spi/spi.h   |   7 ++++
 3 files changed, 94 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c
index e515b8a6f590..25c9bd409a87 100644
--- a/drivers/spi/spi-s3c64xx.c
+++ b/drivers/spi/spi-s3c64xx.c
@@ -381,7 +381,7 @@ static void s3c64xx_spi_dma_stop(struct s3c64xx_spi_driver_data *sdd,
 #else
 
 static void prepare_dma(struct s3c64xx_spi_dma_data *dma,
-					unsigned len, dma_addr_t buf)
+			struct sg_table *sgt)
 {
 	struct s3c64xx_spi_driver_data *sdd;
 	struct dma_slave_config config;
@@ -407,8 +407,8 @@ static void prepare_dma(struct s3c64xx_spi_dma_data *dma,
 		dmaengine_slave_config(dma->ch, &config);
 	}
 
-	desc = dmaengine_prep_slave_single(dma->ch, buf, len,
-					dma->direction, DMA_PREP_INTERRUPT);
+	desc = dmaengine_prep_slave_sg(dma->ch, sgt->sgl, sgt->nents,
+				       dma->direction, DMA_PREP_INTERRUPT);
 
 	desc->callback = s3c64xx_spi_dmacb;
 	desc->callback_param = dma;
@@ -515,7 +515,11 @@ static void enable_datapath(struct s3c64xx_spi_driver_data *sdd,
 		chcfg |= S3C64XX_SPI_CH_TXCH_ON;
 		if (dma_mode) {
 			modecfg |= S3C64XX_SPI_MODE_TXDMA_ON;
+#ifndef CONFIG_S3C_DMA
+			prepare_dma(&sdd->tx_dma, &xfer->tx_sg);
+#else
 			prepare_dma(&sdd->tx_dma, xfer->len, xfer->tx_dma);
+#endif
 		} else {
 			switch (sdd->cur_bpw) {
 			case 32:
@@ -547,7 +551,11 @@ static void enable_datapath(struct s3c64xx_spi_driver_data *sdd,
 			writel(((xfer->len * 8 / sdd->cur_bpw) & 0xffff)
 					| S3C64XX_SPI_PACKET_CNT_EN,
 					regs + S3C64XX_SPI_PACKET_CNT);
+#ifndef CONFIG_S3C_DMA
+			prepare_dma(&sdd->rx_dma, &xfer->rx_sg);
+#else
 			prepare_dma(&sdd->rx_dma, xfer->len, xfer->rx_dma);
+#endif
 		}
 	}
 
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index bb7cf561c311..49313dd0a144 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -582,13 +582,70 @@ static void spi_set_cs(struct spi_device *spi, bool enable)
 		spi->master->set_cs(spi, !enable);
 }
 
+static int spi_map_buf(struct spi_master *master, struct device *dev,
+		       struct sg_table *sgt, void *buf, size_t len,
+		       enum dma_data_direction dir)
+{
+	const bool vmalloced_buf = is_vmalloc_addr(buf);
+	const int desc_len = vmalloced_buf ? PAGE_SIZE : master->max_dma_len;
+	const int sgs = DIV_ROUND_UP(len, desc_len);
+	struct page *vm_page;
+	void *sg_buf;
+	size_t min;
+	int i, ret;
+
+	ret = sg_alloc_table(sgt, sgs, GFP_KERNEL);
+	if (ret != 0)
+		return ret;
+
+	for (i = 0; i < sgs; i++) {
+		min = min_t(size_t, len, desc_len);
+
+		if (vmalloced_buf) {
+			vm_page = vmalloc_to_page(buf);
+			if (!vm_page) {
+				sg_free_table(sgt);
+				return -ENOMEM;
+			}
+			sg_buf = page_address(vm_page) +
+				((size_t)buf & ~PAGE_MASK);
+		} else {
+			sg_buf = buf;
+		}
+
+		sg_set_buf(&sgt->sgl[i], sg_buf, min);
+
+		buf += min;
+		len -= min;
+	}
+
+	ret = dma_map_sg(dev, sgt->sgl, sgt->nents, dir);
+	if (ret < 0) {
+		sg_free_table(sgt);
+		return ret;
+	}
+
+	sgt->nents = ret;
+
+	return 0;
+}
+
+static void spi_unmap_buf(struct spi_master *master, struct device *dev,
+			  struct sg_table *sgt, enum dma_data_direction dir)
+{
+	if (sgt->orig_nents) {
+		dma_unmap_sg(dev, sgt->sgl, sgt->orig_nents, dir);
+		sg_free_table(sgt);
+	}
+}
+
 static int spi_map_msg(struct spi_master *master, struct spi_message *msg)
 {
-	struct device *dev = master->dev.parent;
 	struct device *tx_dev, *rx_dev;
 	struct spi_transfer *xfer;
 	void *tmp;
 	size_t max_tx, max_rx;
+	int ret;
 
 	if (master->flags & (SPI_MASTER_MUST_RX | SPI_MASTER_MUST_TX)) {
 		max_tx = 0;
@@ -631,7 +688,7 @@ static int spi_map_msg(struct spi_master *master, struct spi_message *msg)
 		}
 	}
 
-	if (msg->is_dma_mapped || !master->can_dma)
+	if (!master->can_dma)
 		return 0;
 
 	tx_dev = &master->dma_tx->dev->device;
@@ -642,25 +699,21 @@ static int spi_map_msg(struct spi_master *master, struct spi_message *msg)
 			continue;
 
 		if (xfer->tx_buf != NULL) {
-			xfer->tx_dma = dma_map_single(tx_dev,
-						      (void *)xfer->tx_buf,
-						      xfer->len,
-						      DMA_TO_DEVICE);
-			if (dma_mapping_error(dev, xfer->tx_dma)) {
-				dev_err(dev, "dma_map_single Tx failed\n");
-				return -ENOMEM;
-			}
+			ret = spi_map_buf(master, tx_dev, &xfer->tx_sg,
+					  (void *)xfer->tx_buf, xfer->len,
+					  DMA_TO_DEVICE);
+			if (ret != 0)
+				return ret;
 		}
 
 		if (xfer->rx_buf != NULL) {
-			xfer->rx_dma = dma_map_single(rx_dev,
-						      xfer->rx_buf, xfer->len,
-						      DMA_FROM_DEVICE);
-			if (dma_mapping_error(dev, xfer->rx_dma)) {
-				dev_err(dev, "dma_map_single Rx failed\n");
-				dma_unmap_single(tx_dev, xfer->tx_dma,
-						 xfer->len, DMA_TO_DEVICE);
-				return -ENOMEM;
+			ret = spi_map_buf(master, rx_dev, &xfer->rx_sg,
+					  xfer->rx_buf, xfer->len,
+					  DMA_FROM_DEVICE);
+			if (ret != 0) {
+				spi_unmap_buf(master, tx_dev, &xfer->tx_sg,
+					      DMA_TO_DEVICE);
+				return ret;
 			}
 		}
 	}
@@ -675,7 +728,7 @@ static int spi_unmap_msg(struct spi_master *master, struct spi_message *msg)
 	struct spi_transfer *xfer;
 	struct device *tx_dev, *rx_dev;
 
-	if (!master->cur_msg_mapped || msg->is_dma_mapped || !master->can_dma)
+	if (!master->cur_msg_mapped || !master->can_dma)
 		return 0;
 
 	tx_dev = &master->dma_tx->dev->device;
@@ -685,12 +738,8 @@ static int spi_unmap_msg(struct spi_master *master, struct spi_message *msg)
 		if (!master->can_dma(master, msg->spi, xfer))
 			continue;
 
-		if (xfer->rx_buf)
-			dma_unmap_single(rx_dev, xfer->rx_dma, xfer->len,
-					 DMA_FROM_DEVICE);
-		if (xfer->tx_buf)
-			dma_unmap_single(tx_dev, xfer->tx_dma, xfer->len,
-					 DMA_TO_DEVICE);
+		spi_unmap_buf(master, rx_dev, &xfer->rx_sg, DMA_FROM_DEVICE);
+		spi_unmap_buf(master, tx_dev, &xfer->tx_sg, DMA_TO_DEVICE);
 	}
 
 	return 0;
@@ -1503,6 +1552,8 @@ int spi_register_master(struct spi_master *master)
 	mutex_init(&master->bus_lock_mutex);
 	master->bus_lock_flag = 0;
 	init_completion(&master->xfer_completion);
+	if (!master->max_dma_len)
+		master->max_dma_len = INT_MAX;
 
 	/* register the device, then userspace will see it.
 	 * registration fails if the bus ID is in use.
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 31a5b0ee93ec..0c23c835d48b 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/kthread.h>
 #include <linux/completion.h>
+#include <linux/scatterlist.h>
 
 struct dma_chan;
 
@@ -268,6 +269,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  * @auto_runtime_pm: the core should ensure a runtime PM reference is held
  *                   while the hardware is prepared, using the parent
  *                   device for the spidev
+ * @max_dma_len: Maximum length of a DMA transfer for the device.
  * @prepare_transfer_hardware: a message will soon arrive from the queue
  *	so the subsystem requests the driver to prepare the transfer hardware
  *	by issuing this call
@@ -421,6 +423,7 @@ struct spi_master {
 	bool                            cur_msg_prepared;
 	bool				cur_msg_mapped;
 	struct completion               xfer_completion;
+	size_t				max_dma_len;
 
 	int (*prepare_transfer_hardware)(struct spi_master *master);
 	int (*transfer_one_message)(struct spi_master *master,
@@ -533,6 +536,8 @@ extern struct spi_master *spi_busnum_to_master(u16 busnum);
  *	(optionally) changing the chipselect status, then starting
  *	the next transfer or completing this @spi_message.
  * @transfer_list: transfers are sequenced through @spi_message.transfers
+ * @tx_sg: Scatterlist for transmit, currently not for client use
+ * @rx_sg: Scatterlist for receive, currently not for client use
  *
  * SPI transfers always write the same number of bytes as they read.
  * Protocol drivers should always provide @rx_buf and/or @tx_buf.
@@ -600,6 +605,8 @@ struct spi_transfer {
 
 	dma_addr_t	tx_dma;
 	dma_addr_t	rx_dma;
+	struct sg_table tx_sg;
+	struct sg_table rx_sg;
 
 	unsigned	cs_change:1;
 	unsigned	tx_nbits:3;
-- 
cgit v1.2.3


From d8ca16db6bb23d03fcb794df44bae64ae976f27c Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 23 Jan 2014 16:20:29 +0100
Subject: mac80211: add length check in ieee80211_is_robust_mgmt_frame()

A few places weren't checking that the frame passed to the
function actually has enough data even though the function
clearly documents it must have a payload byte. Make this
safer by changing the function to take an skb and checking
the length inside. The old version is preserved for now as
the rtl* drivers use it and don't have a correct skb.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/rtlwifi/rtl8188ee/trx.c |  2 +-
 drivers/net/wireless/rtlwifi/rtl8192ce/trx.c |  2 +-
 drivers/net/wireless/rtlwifi/rtl8192se/trx.c |  2 +-
 drivers/net/wireless/rtlwifi/rtl8723ae/trx.c |  2 +-
 include/linux/ieee80211.h                    | 15 +++++++++++++--
 net/mac80211/rx.c                            | 13 ++++++-------
 net/mac80211/tx.c                            |  9 ++++-----
 net/mac80211/wpa.c                           |  2 +-
 8 files changed, 28 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c b/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c
index aece6c9cccf1..27ace3054d56 100644
--- a/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c
@@ -452,7 +452,7 @@ bool rtl88ee_rx_query_desc(struct ieee80211_hw *hw,
 			/* During testing, hdr was NULL */
 			return false;
 		}
-		if ((ieee80211_is_robust_mgmt_frame(hdr)) &&
+		if ((_ieee80211_is_robust_mgmt_frame(hdr)) &&
 		    (ieee80211_has_protected(hdr->frame_control)))
 			rx_status->flag &= ~RX_FLAG_DECRYPTED;
 		else
diff --git a/drivers/net/wireless/rtlwifi/rtl8192ce/trx.c b/drivers/net/wireless/rtlwifi/rtl8192ce/trx.c
index 52abf0a862fa..114858d46158 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192ce/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192ce/trx.c
@@ -393,7 +393,7 @@ bool rtl92ce_rx_query_desc(struct ieee80211_hw *hw,
 			/* In testing, hdr was NULL here */
 			return false;
 		}
-		if ((ieee80211_is_robust_mgmt_frame(hdr)) &&
+		if ((_ieee80211_is_robust_mgmt_frame(hdr)) &&
 		    (ieee80211_has_protected(hdr->frame_control)))
 			rx_status->flag &= ~RX_FLAG_DECRYPTED;
 		else
diff --git a/drivers/net/wireless/rtlwifi/rtl8192se/trx.c b/drivers/net/wireless/rtlwifi/rtl8192se/trx.c
index 27efbcdac6a9..163a681962c6 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192se/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192se/trx.c
@@ -310,7 +310,7 @@ bool rtl92se_rx_query_desc(struct ieee80211_hw *hw, struct rtl_stats *stats,
 			/* during testing, hdr was NULL here */
 			return false;
 		}
-		if ((ieee80211_is_robust_mgmt_frame(hdr)) &&
+		if ((_ieee80211_is_robust_mgmt_frame(hdr)) &&
 			(ieee80211_has_protected(hdr->frame_control)))
 			rx_status->flag &= ~RX_FLAG_DECRYPTED;
 		else
diff --git a/drivers/net/wireless/rtlwifi/rtl8723ae/trx.c b/drivers/net/wireless/rtlwifi/rtl8723ae/trx.c
index 50b7be3f3a60..721162cacc3a 100644
--- a/drivers/net/wireless/rtlwifi/rtl8723ae/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8723ae/trx.c
@@ -334,7 +334,7 @@ bool rtl8723ae_rx_query_desc(struct ieee80211_hw *hw,
 			/* during testing, hdr could be NULL here */
 			return false;
 		}
-		if ((ieee80211_is_robust_mgmt_frame(hdr)) &&
+		if ((_ieee80211_is_robust_mgmt_frame(hdr)) &&
 			(ieee80211_has_protected(hdr->frame_control)))
 			rx_status->flag &= ~RX_FLAG_DECRYPTED;
 		else
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index e526a8cecb70..923c478030a3 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2192,10 +2192,10 @@ static inline u8 *ieee80211_get_DA(struct ieee80211_hdr *hdr)
 }
 
 /**
- * ieee80211_is_robust_mgmt_frame - check if frame is a robust management frame
+ * _ieee80211_is_robust_mgmt_frame - check if frame is a robust management frame
  * @hdr: the frame (buffer must include at least the first octet of payload)
  */
-static inline bool ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr)
+static inline bool _ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr)
 {
 	if (ieee80211_is_disassoc(hdr->frame_control) ||
 	    ieee80211_is_deauth(hdr->frame_control))
@@ -2223,6 +2223,17 @@ static inline bool ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr)
 	return false;
 }
 
+/**
+ * ieee80211_is_robust_mgmt_frame - check if skb contains a robust mgmt frame
+ * @skb: the skb containing the frame, length will be checked
+ */
+static inline bool ieee80211_is_robust_mgmt_frame(struct sk_buff *skb)
+{
+	if (skb->len < 25)
+		return false;
+	return _ieee80211_is_robust_mgmt_frame((void *)skb->data);
+}
+
 /**
  * ieee80211_is_public_action - check if frame is a public action frame
  * @hdr: the frame
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index c24ca0d0f469..3b7a750ebc70 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -599,10 +599,10 @@ static int ieee80211_is_unicast_robust_mgmt_frame(struct sk_buff *skb)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
 
-	if (skb->len < 24 || is_multicast_ether_addr(hdr->addr1))
+	if (is_multicast_ether_addr(hdr->addr1))
 		return 0;
 
-	return ieee80211_is_robust_mgmt_frame(hdr);
+	return ieee80211_is_robust_mgmt_frame(skb);
 }
 
 
@@ -610,10 +610,10 @@ static int ieee80211_is_multicast_robust_mgmt_frame(struct sk_buff *skb)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
 
-	if (skb->len < 24 || !is_multicast_ether_addr(hdr->addr1))
+	if (!is_multicast_ether_addr(hdr->addr1))
 		return 0;
 
-	return ieee80211_is_robust_mgmt_frame(hdr);
+	return ieee80211_is_robust_mgmt_frame(skb);
 }
 
 
@@ -626,7 +626,7 @@ static int ieee80211_get_mmie_keyidx(struct sk_buff *skb)
 	if (skb->len < 24 + sizeof(*mmie) || !is_multicast_ether_addr(hdr->da))
 		return -1;
 
-	if (!ieee80211_is_robust_mgmt_frame((struct ieee80211_hdr *) hdr))
+	if (!ieee80211_is_robust_mgmt_frame(skb))
 		return -1; /* not a robust management frame */
 
 	mmie = (struct ieee80211_mmie *)
@@ -1845,8 +1845,7 @@ static int ieee80211_drop_unencrypted_mgmt(struct ieee80211_rx_data *rx)
 		 * having configured keys.
 		 */
 		if (unlikely(ieee80211_is_action(fc) && !rx->key &&
-			     ieee80211_is_robust_mgmt_frame(
-				     (struct ieee80211_hdr *) rx->skb->data)))
+			     ieee80211_is_robust_mgmt_frame(rx->skb)))
 			return -EACCES;
 	}
 
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index bb990ecfa655..07a7f38dc348 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -452,8 +452,7 @@ static int ieee80211_use_mfp(__le16 fc, struct sta_info *sta,
 	if (sta == NULL || !test_sta_flag(sta, WLAN_STA_MFP))
 		return 0;
 
-	if (!ieee80211_is_robust_mgmt_frame((struct ieee80211_hdr *)
-					    skb->data))
+	if (!ieee80211_is_robust_mgmt_frame(skb))
 		return 0;
 
 	return 1;
@@ -567,7 +566,7 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx)
 		tx->key = key;
 	else if (ieee80211_is_mgmt(hdr->frame_control) &&
 		 is_multicast_ether_addr(hdr->addr1) &&
-		 ieee80211_is_robust_mgmt_frame(hdr) &&
+		 ieee80211_is_robust_mgmt_frame(tx->skb) &&
 		 (key = rcu_dereference(tx->sdata->default_mgmt_key)))
 		tx->key = key;
 	else if (is_multicast_ether_addr(hdr->addr1) &&
@@ -582,12 +581,12 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx)
 		tx->key = NULL;
 	else if (tx->skb->protocol == tx->sdata->control_port_protocol)
 		tx->key = NULL;
-	else if (ieee80211_is_robust_mgmt_frame(hdr) &&
+	else if (ieee80211_is_robust_mgmt_frame(tx->skb) &&
 		 !(ieee80211_is_action(hdr->frame_control) &&
 		   tx->sta && test_sta_flag(tx->sta, WLAN_STA_MFP)))
 		tx->key = NULL;
 	else if (ieee80211_is_mgmt(hdr->frame_control) &&
-		 !ieee80211_is_robust_mgmt_frame(hdr))
+		 !ieee80211_is_robust_mgmt_frame(tx->skb))
 		tx->key = NULL;
 	else {
 		I802_DEBUG_INC(tx->local->tx_handlers_drop_unencrypted);
diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c
index 4aed45c8ee3b..b8600e3c29c8 100644
--- a/net/mac80211/wpa.c
+++ b/net/mac80211/wpa.c
@@ -494,7 +494,7 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx)
 	hdrlen = ieee80211_hdrlen(hdr->frame_control);
 
 	if (!ieee80211_is_data(hdr->frame_control) &&
-	    !ieee80211_is_robust_mgmt_frame(hdr))
+	    !ieee80211_is_robust_mgmt_frame(skb))
 		return RX_CONTINUE;
 
 	data_len = skb->len - hdrlen - IEEE80211_CCMP_HDR_LEN -
-- 
cgit v1.2.3


From b4ba544c8c1349afd44e10aebec03c90e9b71d98 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 24 Jan 2014 14:41:44 +0100
Subject: mac80211: fix bufferable MMPDU RX handling

Action, disassoc and deauth frames are bufferable, and as such don't
have the PM bit in the frame control field reserved which means we
need to react to the bit when receiving in such a frame.

Fix this by introducing a new helper ieee80211_is_bufferable_mmpdu()
and using it for the RX path that currently ignores the PM bit in
any non-data frames for doze->wake transitions, but listens to it in
all frames for wake->doze transitions, both of which are wrong.

Also use the new helper in the TX path to clean up the code.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 14 ++++++++++++++
 net/mac80211/rx.c         | 19 ++++++++-----------
 net/mac80211/tx.c         |  5 +----
 3 files changed, 23 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 923c478030a3..1e3912d1b029 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -596,6 +596,20 @@ static inline int ieee80211_is_qos_nullfunc(__le16 fc)
 	       cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_NULLFUNC);
 }
 
+/**
+ * ieee80211_is_bufferable_mmpdu - check if frame is bufferable MMPDU
+ * @fc: frame control field in little-endian byteorder
+ */
+static inline bool ieee80211_is_bufferable_mmpdu(__le16 fc)
+{
+	/* IEEE 802.11-2012, definition of "bufferable management frame";
+	 * note that this ignores the IBSS special case. */
+	return ieee80211_is_mgmt(fc) &&
+	       (ieee80211_is_action(fc) ||
+		ieee80211_is_disassoc(fc) ||
+		ieee80211_is_deauth(fc));
+}
+
 /**
  * ieee80211_is_first_frag - check if IEEE80211_SCTL_FRAG is not set
  * @seq_ctrl: frame sequence control bytes in little-endian byteorder
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 3b7a750ebc70..79a89fe9d616 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1311,18 +1311,15 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
 	    !ieee80211_has_morefrags(hdr->frame_control) &&
 	    !(status->rx_flags & IEEE80211_RX_DEFERRED_RELEASE) &&
 	    (rx->sdata->vif.type == NL80211_IFTYPE_AP ||
-	     rx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN)) {
+	     rx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) &&
+	    /* PM bit is only checked in frames where it isn't reserved,
+	     * in AP mode it's reserved in non-bufferable management frames
+	     * (cf. IEEE 802.11-2012 8.2.4.1.7 Power Management field)
+	     */
+	    (!ieee80211_is_mgmt(hdr->frame_control) ||
+	     ieee80211_is_bufferable_mmpdu(hdr->frame_control))) {
 		if (test_sta_flag(sta, WLAN_STA_PS_STA)) {
-			/*
-			 * Ignore doze->wake transitions that are
-			 * indicated by non-data frames, the standard
-			 * is unclear here, but for example going to
-			 * PS mode and then scanning would cause a
-			 * doze->wake transition for the probe request,
-			 * and that is clearly undesirable.
-			 */
-			if (ieee80211_is_data(hdr->frame_control) &&
-			    !ieee80211_has_pm(hdr->frame_control))
+			if (!ieee80211_has_pm(hdr->frame_control))
 				sta_ps_end(sta);
 		} else {
 			if (ieee80211_has_pm(hdr->frame_control))
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 07a7f38dc348..5476a69b45c9 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -522,11 +522,8 @@ ieee80211_tx_h_ps_buf(struct ieee80211_tx_data *tx)
 	if (unlikely(tx->flags & IEEE80211_TX_PS_BUFFERED))
 		return TX_CONTINUE;
 
-	/* only deauth, disassoc and action are bufferable MMPDUs */
 	if (ieee80211_is_mgmt(hdr->frame_control) &&
-	    !ieee80211_is_deauth(hdr->frame_control) &&
-	    !ieee80211_is_disassoc(hdr->frame_control) &&
-	    !ieee80211_is_action(hdr->frame_control)) {
+	    !ieee80211_is_bufferable_mmpdu(hdr->frame_control)) {
 		if (tx->flags & IEEE80211_TX_UNICAST)
 			info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER;
 		return TX_CONTINUE;
-- 
cgit v1.2.3


From b66548e2a9baf65ccebeb3750f0ab9ddbef500f6 Mon Sep 17 00:00:00 2001
From: Andreas Herrmann <andreas.herrmann@calxeda.com>
Date: Fri, 17 Jan 2014 12:08:30 +0100
Subject: of: Increase MAX_PHANDLE_ARGS

arm-smmu driver uses of_parse_phandle_with_args when parsing DT
information to determine stream IDs for a master device.
Thus the number of stream IDs per master device is bound by
MAX_PHANDLE_ARGS.

To support Calxeda ECX-2000 hardware arm-smmu driver requires a
slightly higher value for MAX_PHANDLE_ARGS as this hardware has 10
stream IDs for one master device.

Increasing it to 16 seems a reasonable choice.

Cc: Grant Likely <grant.likely@linaro.org>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: devicetree@vger.kernel.org
Cc: Andreas Herrmann <herrmann.der.user@googlemail.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Andreas Herrmann <andreas.herrmann@calxeda.com>
Signed-off-by: Grant Likely <grant.likely@linaro.org>
---
 include/linux/of.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/of.h b/include/linux/of.h
index 3d0593943f47..0ea516ed22c0 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -67,7 +67,7 @@ struct device_node {
 #endif
 };
 
-#define MAX_PHANDLE_ARGS 8
+#define MAX_PHANDLE_ARGS 16
 struct of_phandle_args {
 	struct device_node *np;
 	int args_count;
-- 
cgit v1.2.3


From 8c78e38025060a00155a73bf722152c156242490 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 4 Feb 2014 09:41:04 +0100
Subject: wireless: sort and extend element ID list

The element ID list is currently almost sorted by amendment
or similar topic, but the order is difficult to maintain and
not very transparent. Sort the list by ID instead, and add
a lot of missing IDs.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 170 +++++++++++++++++++++++++++++-----------------
 1 file changed, 106 insertions(+), 64 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 1e3912d1b029..5f349355ee54 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1650,51 +1650,22 @@ enum ieee80211_reasoncode {
 enum ieee80211_eid {
 	WLAN_EID_SSID = 0,
 	WLAN_EID_SUPP_RATES = 1,
-	WLAN_EID_FH_PARAMS = 2,
+	WLAN_EID_FH_PARAMS = 2, /* reserved now */
 	WLAN_EID_DS_PARAMS = 3,
 	WLAN_EID_CF_PARAMS = 4,
 	WLAN_EID_TIM = 5,
 	WLAN_EID_IBSS_PARAMS = 6,
-	WLAN_EID_CHALLENGE = 16,
-
 	WLAN_EID_COUNTRY = 7,
 	WLAN_EID_HP_PARAMS = 8,
 	WLAN_EID_HP_TABLE = 9,
 	WLAN_EID_REQUEST = 10,
-
 	WLAN_EID_QBSS_LOAD = 11,
 	WLAN_EID_EDCA_PARAM_SET = 12,
 	WLAN_EID_TSPEC = 13,
 	WLAN_EID_TCLAS = 14,
 	WLAN_EID_SCHEDULE = 15,
-	WLAN_EID_TS_DELAY = 43,
-	WLAN_EID_TCLAS_PROCESSING = 44,
-	WLAN_EID_QOS_CAPA = 46,
-	/* 802.11z */
-	WLAN_EID_LINK_ID = 101,
-	/* 802.11s */
-	WLAN_EID_MESH_CONFIG = 113,
-	WLAN_EID_MESH_ID = 114,
-	WLAN_EID_LINK_METRIC_REPORT = 115,
-	WLAN_EID_CONGESTION_NOTIFICATION = 116,
-	WLAN_EID_PEER_MGMT = 117,
-	WLAN_EID_CHAN_SWITCH_PARAM = 118,
-	WLAN_EID_MESH_AWAKE_WINDOW = 119,
-	WLAN_EID_BEACON_TIMING = 120,
-	WLAN_EID_MCCAOP_SETUP_REQ = 121,
-	WLAN_EID_MCCAOP_SETUP_RESP = 122,
-	WLAN_EID_MCCAOP_ADVERT = 123,
-	WLAN_EID_MCCAOP_TEARDOWN = 124,
-	WLAN_EID_GANN = 125,
-	WLAN_EID_RANN = 126,
-	WLAN_EID_PREQ = 130,
-	WLAN_EID_PREP = 131,
-	WLAN_EID_PERR = 132,
-	WLAN_EID_PXU = 137,
-	WLAN_EID_PXUC = 138,
-	WLAN_EID_AUTH_MESH_PEER_EXCH = 139,
-	WLAN_EID_MIC = 140,
-
+	WLAN_EID_CHALLENGE = 16,
+	/* 17-31 reserved for challenge text extension */
 	WLAN_EID_PWR_CONSTRAINT = 32,
 	WLAN_EID_PWR_CAPABILITY = 33,
 	WLAN_EID_TPC_REQUEST = 34,
@@ -1705,66 +1676,114 @@ enum ieee80211_eid {
 	WLAN_EID_MEASURE_REPORT = 39,
 	WLAN_EID_QUIET = 40,
 	WLAN_EID_IBSS_DFS = 41,
-
 	WLAN_EID_ERP_INFO = 42,
-	WLAN_EID_EXT_SUPP_RATES = 50,
-
+	WLAN_EID_TS_DELAY = 43,
+	WLAN_EID_TCLAS_PROCESSING = 44,
 	WLAN_EID_HT_CAPABILITY = 45,
-	WLAN_EID_HT_OPERATION = 61,
-	WLAN_EID_SECONDARY_CHANNEL_OFFSET = 62,
-
+	WLAN_EID_QOS_CAPA = 46,
+	/* 47 reserved for Broadcom */
 	WLAN_EID_RSN = 48,
-	WLAN_EID_MMIE = 76,
-	WLAN_EID_VENDOR_SPECIFIC = 221,
-	WLAN_EID_QOS_PARAMETER = 222,
-
+	WLAN_EID_802_15_COEX = 49,
+	WLAN_EID_EXT_SUPP_RATES = 50,
 	WLAN_EID_AP_CHAN_REPORT = 51,
 	WLAN_EID_NEIGHBOR_REPORT = 52,
 	WLAN_EID_RCPI = 53,
+	WLAN_EID_MOBILITY_DOMAIN = 54,
+	WLAN_EID_FAST_BSS_TRANSITION = 55,
+	WLAN_EID_TIMEOUT_INTERVAL = 56,
+	WLAN_EID_RIC_DATA = 57,
+	WLAN_EID_DSE_REGISTERED_LOCATION = 58,
+	WLAN_EID_SUPPORTED_REGULATORY_CLASSES = 59,
+	WLAN_EID_EXT_CHANSWITCH_ANN = 60,
+	WLAN_EID_HT_OPERATION = 61,
+	WLAN_EID_SECONDARY_CHANNEL_OFFSET = 62,
 	WLAN_EID_BSS_AVG_ACCESS_DELAY = 63,
 	WLAN_EID_ANTENNA_INFO = 64,
 	WLAN_EID_RSNI = 65,
 	WLAN_EID_MEASUREMENT_PILOT_TX_INFO = 66,
 	WLAN_EID_BSS_AVAILABLE_CAPACITY = 67,
 	WLAN_EID_BSS_AC_ACCESS_DELAY = 68,
+	WLAN_EID_TIME_ADVERTISEMENT = 69,
 	WLAN_EID_RRM_ENABLED_CAPABILITIES = 70,
 	WLAN_EID_MULTIPLE_BSSID = 71,
 	WLAN_EID_BSS_COEX_2040 = 72,
 	WLAN_EID_OVERLAP_BSS_SCAN_PARAM = 74,
-	WLAN_EID_EXT_CAPABILITY = 127,
-
-	WLAN_EID_MOBILITY_DOMAIN = 54,
-	WLAN_EID_FAST_BSS_TRANSITION = 55,
-	WLAN_EID_TIMEOUT_INTERVAL = 56,
-	WLAN_EID_RIC_DATA = 57,
 	WLAN_EID_RIC_DESCRIPTOR = 75,
-
-	WLAN_EID_DSE_REGISTERED_LOCATION = 58,
-	WLAN_EID_SUPPORTED_REGULATORY_CLASSES = 59,
-	WLAN_EID_EXT_CHANSWITCH_ANN = 60,
-
-	WLAN_EID_VHT_CAPABILITY = 191,
-	WLAN_EID_VHT_OPERATION = 192,
-	WLAN_EID_OPMODE_NOTIF = 199,
-	WLAN_EID_WIDE_BW_CHANNEL_SWITCH = 194,
-	WLAN_EID_CHANNEL_SWITCH_WRAPPER = 196,
-	WLAN_EID_EXTENDED_BSS_LOAD = 193,
-	WLAN_EID_VHT_TX_POWER_ENVELOPE = 195,
-	WLAN_EID_AID = 197,
-	WLAN_EID_QUIET_CHANNEL = 198,
-
-	/* 802.11ad */
+	WLAN_EID_MMIE = 76,
+	WLAN_EID_ASSOC_COMEBACK_TIME = 77,
+	WLAN_EID_EVENT_REQUEST = 78,
+	WLAN_EID_EVENT_REPORT = 79,
+	WLAN_EID_DIAGNOSTIC_REQUEST = 80,
+	WLAN_EID_DIAGNOSTIC_REPORT = 81,
+	WLAN_EID_LOCATION_PARAMS = 82,
 	WLAN_EID_NON_TX_BSSID_CAP =  83,
+	WLAN_EID_SSID_LIST = 84,
+	WLAN_EID_MULTI_BSSID_IDX = 85,
+	WLAN_EID_FMS_DESCRIPTOR = 86,
+	WLAN_EID_FMS_REQUEST = 87,
+	WLAN_EID_FMS_RESPONSE = 88,
+	WLAN_EID_QOS_TRAFFIC_CAPA = 89,
+	WLAN_EID_BSS_MAX_IDLE_PERIOD = 90,
+	WLAN_EID_TSF_REQUEST = 91,
+	WLAN_EID_TSF_RESPOSNE = 92,
+	WLAN_EID_WNM_SLEEP_MODE = 93,
+	WLAN_EID_TIM_BCAST_REQ = 94,
+	WLAN_EID_TIM_BCAST_RESP = 95,
+	WLAN_EID_COLL_IF_REPORT = 96,
+	WLAN_EID_CHANNEL_USAGE = 97,
+	WLAN_EID_TIME_ZONE = 98,
+	WLAN_EID_DMS_REQUEST = 99,
+	WLAN_EID_DMS_RESPONSE = 100,
+	WLAN_EID_LINK_ID = 101,
+	WLAN_EID_WAKEUP_SCHEDUL = 102,
+	/* 103 reserved */
+	WLAN_EID_CHAN_SWITCH_TIMING = 104,
+	WLAN_EID_PTI_CONTROL = 105,
+	WLAN_EID_PU_BUFFER_STATUS = 106,
+	WLAN_EID_INTERWORKING = 107,
+	WLAN_EID_ADVERTISEMENT_PROTOCOL = 108,
+	WLAN_EID_EXPEDITED_BW_REQ = 109,
+	WLAN_EID_QOS_MAP_SET = 110,
+	WLAN_EID_ROAMING_CONSORTIUM = 111,
+	WLAN_EID_EMERGENCY_ALERT = 112,
+	WLAN_EID_MESH_CONFIG = 113,
+	WLAN_EID_MESH_ID = 114,
+	WLAN_EID_LINK_METRIC_REPORT = 115,
+	WLAN_EID_CONGESTION_NOTIFICATION = 116,
+	WLAN_EID_PEER_MGMT = 117,
+	WLAN_EID_CHAN_SWITCH_PARAM = 118,
+	WLAN_EID_MESH_AWAKE_WINDOW = 119,
+	WLAN_EID_BEACON_TIMING = 120,
+	WLAN_EID_MCCAOP_SETUP_REQ = 121,
+	WLAN_EID_MCCAOP_SETUP_RESP = 122,
+	WLAN_EID_MCCAOP_ADVERT = 123,
+	WLAN_EID_MCCAOP_TEARDOWN = 124,
+	WLAN_EID_GANN = 125,
+	WLAN_EID_RANN = 126,
+	WLAN_EID_EXT_CAPABILITY = 127,
+	/* 128, 129 reserved for Agere */
+	WLAN_EID_PREQ = 130,
+	WLAN_EID_PREP = 131,
+	WLAN_EID_PERR = 132,
+	/* 133-136 reserved for Cisco */
+	WLAN_EID_PXU = 137,
+	WLAN_EID_PXUC = 138,
+	WLAN_EID_AUTH_MESH_PEER_EXCH = 139,
+	WLAN_EID_MIC = 140,
+	WLAN_EID_DESTINATION_URI = 141,
+	WLAN_EID_UAPSD_COEX = 142,
 	WLAN_EID_WAKEUP_SCHEDULE = 143,
 	WLAN_EID_EXT_SCHEDULE = 144,
 	WLAN_EID_STA_AVAILABILITY = 145,
 	WLAN_EID_DMG_TSPEC = 146,
 	WLAN_EID_DMG_AT = 147,
 	WLAN_EID_DMG_CAP = 148,
+	/* 149-150 reserved for Cisco */
 	WLAN_EID_DMG_OPERATION = 151,
 	WLAN_EID_DMG_BSS_PARAM_CHANGE = 152,
 	WLAN_EID_DMG_BEAM_REFINEMENT = 153,
 	WLAN_EID_CHANNEL_MEASURE_FEEDBACK = 154,
+	/* 155-156 reserved for Cisco */
 	WLAN_EID_AWAKE_WINDOW = 157,
 	WLAN_EID_MULTI_BAND = 158,
 	WLAN_EID_ADDBA_EXT = 159,
@@ -1781,11 +1800,34 @@ enum ieee80211_eid {
 	WLAN_EID_MULTIPLE_MAC_ADDR = 170,
 	WLAN_EID_U_PID = 171,
 	WLAN_EID_DMG_LINK_ADAPT_ACK = 172,
+	/* 173 reserved for Symbol */
+	WLAN_EID_MCCAOP_ADV_OVERVIEW = 174,
 	WLAN_EID_QUIET_PERIOD_REQ = 175,
+	/* 176 reserved for Symbol */
 	WLAN_EID_QUIET_PERIOD_RESP = 177,
+	/* 178-179 reserved for Symbol */
+	/* 180 reserved for ISO/IEC 20011 */
 	WLAN_EID_EPAC_POLICY = 182,
 	WLAN_EID_CLISTER_TIME_OFF = 183,
+	WLAN_EID_INTER_AC_PRIO = 184,
+	WLAN_EID_SCS_DESCRIPTOR = 185,
+	WLAN_EID_QLOAD_REPORT = 186,
+	WLAN_EID_HCCA_TXOP_UPDATE_COUNT = 187,
+	WLAN_EID_HL_STREAM_ID = 188,
+	WLAN_EID_GCR_GROUP_ADDR = 189,
 	WLAN_EID_ANTENNA_SECTOR_ID_PATTERN = 190,
+	WLAN_EID_VHT_CAPABILITY = 191,
+	WLAN_EID_VHT_OPERATION = 192,
+	WLAN_EID_EXTENDED_BSS_LOAD = 193,
+	WLAN_EID_WIDE_BW_CHANNEL_SWITCH = 194,
+	WLAN_EID_VHT_TX_POWER_ENVELOPE = 195,
+	WLAN_EID_CHANNEL_SWITCH_WRAPPER = 196,
+	WLAN_EID_AID = 197,
+	WLAN_EID_QUIET_CHANNEL = 198,
+	WLAN_EID_OPMODE_NOTIF = 199,
+
+	WLAN_EID_VENDOR_SPECIFIC = 221,
+	WLAN_EID_QOS_PARAMETER = 222,
 };
 
 /* Action category code */
-- 
cgit v1.2.3


From 006e983bbc805431c44e2135e13841f66059a045 Mon Sep 17 00:00:00 2001
From: Sricharan R <r.sricharan@ti.com>
Date: Tue, 3 Dec 2013 15:57:22 +0530
Subject: DRIVERS: IRQCHIP: IRQ-GIC: Add support for routable irqs

In some socs the gic can be preceded by a crossbar IP which
routes the peripheral interrupts to the gic inputs. The peripheral
interrupts are associated with a fixed crossbar input line and the
crossbar routes that to one of the free gic input line.

The DT entries for peripherals provides the fixed crossbar input line
as its interrupt number and the mapping code should associate this with
a free gic input line. This patch adds the support inside the gic irqchip
to handle such routable irqs. The routable irqs are registered in a linear
domain. The registered routable domain's callback should be implemented
to get a free irq and to configure the IP to route it.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Santosh Shilimkar <santosh.shilimkar@ti.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Tony Lindgren <tony@atomide.com>
Cc: Rajendra Nayak <rnayak@ti.com>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Rob Herring <rob.herring@calxeda.com>
Signed-off-by: Sricharan R <r.sricharan@ti.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
---
 Documentation/devicetree/bindings/arm/gic.txt |  6 ++
 drivers/irqchip/irq-gic.c                     | 82 +++++++++++++++++++++++----
 include/linux/irqchip/arm-gic.h               |  7 ++-
 3 files changed, 84 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/devicetree/bindings/arm/gic.txt b/Documentation/devicetree/bindings/arm/gic.txt
index bae0d87a38b2..5573c08d3180 100644
--- a/Documentation/devicetree/bindings/arm/gic.txt
+++ b/Documentation/devicetree/bindings/arm/gic.txt
@@ -50,6 +50,11 @@ Optional
   regions, used when the GIC doesn't have banked registers. The offset is
   cpu-offset * cpu-nr.
 
+- arm,routable-irqs : Total number of gic irq inputs which are not directly
+		  connected from the peripherals, but are routed dynamically
+		  by a crossbar/multiplexer preceding the GIC. The GIC irq
+		  input line is assigned dynamically when the corresponding
+		  peripheral's crossbar line is mapped.
 Example:
 
 	intc: interrupt-controller@fff11000 {
@@ -57,6 +62,7 @@ Example:
 		#interrupt-cells = <3>;
 		#address-cells = <1>;
 		interrupt-controller;
+		arm,routable-irqs = <160>;
 		reg = <0xfff11000 0x1000>,
 		      <0xfff10100 0x100>;
 	};
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 341c6016812d..07a7050841ec 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -824,16 +824,25 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
 		irq_set_chip_and_handler(irq, &gic_chip,
 					 handle_fasteoi_irq);
 		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+
+		gic_routable_irq_domain_ops->map(d, irq, hw);
 	}
 	irq_set_chip_data(irq, d->host_data);
 	return 0;
 }
 
+static void gic_irq_domain_unmap(struct irq_domain *d, unsigned int irq)
+{
+	gic_routable_irq_domain_ops->unmap(d, irq);
+}
+
 static int gic_irq_domain_xlate(struct irq_domain *d,
 				struct device_node *controller,
 				const u32 *intspec, unsigned int intsize,
 				unsigned long *out_hwirq, unsigned int *out_type)
 {
+	unsigned long ret = 0;
+
 	if (d->of_node != controller)
 		return -EINVAL;
 	if (intsize < 3)
@@ -843,11 +852,20 @@ static int gic_irq_domain_xlate(struct irq_domain *d,
 	*out_hwirq = intspec[1] + 16;
 
 	/* For SPIs, we need to add 16 more to get the GIC irq ID number */
-	if (!intspec[0])
-		*out_hwirq += 16;
+	if (!intspec[0]) {
+		ret = gic_routable_irq_domain_ops->xlate(d, controller,
+							 intspec,
+							 intsize,
+							 out_hwirq,
+							 out_type);
+
+		if (IS_ERR_VALUE(ret))
+			return ret;
+	}
 
 	*out_type = intspec[2] & IRQ_TYPE_SENSE_MASK;
-	return 0;
+
+	return ret;
 }
 
 #ifdef CONFIG_SMP
@@ -871,9 +889,41 @@ static struct notifier_block gic_cpu_notifier = {
 
 const struct irq_domain_ops gic_irq_domain_ops = {
 	.map = gic_irq_domain_map,
+	.unmap = gic_irq_domain_unmap,
 	.xlate = gic_irq_domain_xlate,
 };
 
+/* Default functions for routable irq domain */
+static int gic_routable_irq_domain_map(struct irq_domain *d, unsigned int irq,
+			      irq_hw_number_t hw)
+{
+	return 0;
+}
+
+static void gic_routable_irq_domain_unmap(struct irq_domain *d,
+					  unsigned int irq)
+{
+}
+
+static int gic_routable_irq_domain_xlate(struct irq_domain *d,
+				struct device_node *controller,
+				const u32 *intspec, unsigned int intsize,
+				unsigned long *out_hwirq,
+				unsigned int *out_type)
+{
+	*out_hwirq += 16;
+	return 0;
+}
+
+const struct irq_domain_ops gic_default_routable_irq_domain_ops = {
+	.map = gic_routable_irq_domain_map,
+	.unmap = gic_routable_irq_domain_unmap,
+	.xlate = gic_routable_irq_domain_xlate,
+};
+
+const struct irq_domain_ops *gic_routable_irq_domain_ops =
+					&gic_default_routable_irq_domain_ops;
+
 void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 			   void __iomem *dist_base, void __iomem *cpu_base,
 			   u32 percpu_offset, struct device_node *node)
@@ -881,6 +931,7 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 	irq_hw_number_t hwirq_base;
 	struct gic_chip_data *gic;
 	int gic_irqs, irq_base, i;
+	int nr_routable_irqs;
 
 	BUG_ON(gic_nr >= MAX_GIC_NR);
 
@@ -946,14 +997,25 @@ void __init gic_init_bases(unsigned int gic_nr, int irq_start,
 	gic->gic_irqs = gic_irqs;
 
 	gic_irqs -= hwirq_base; /* calculate # of irqs to allocate */
-	irq_base = irq_alloc_descs(irq_start, 16, gic_irqs, numa_node_id());
-	if (IS_ERR_VALUE(irq_base)) {
-		WARN(1, "Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n",
-		     irq_start);
-		irq_base = irq_start;
+
+	if (of_property_read_u32(node, "arm,routable-irqs",
+				 &nr_routable_irqs)) {
+		irq_base = irq_alloc_descs(irq_start, 16, gic_irqs,
+					   numa_node_id());
+		if (IS_ERR_VALUE(irq_base)) {
+			WARN(1, "Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n",
+			     irq_start);
+			irq_base = irq_start;
+		}
+
+		gic->domain = irq_domain_add_legacy(node, gic_irqs, irq_base,
+					hwirq_base, &gic_irq_domain_ops, gic);
+	} else {
+		gic->domain = irq_domain_add_linear(node, nr_routable_irqs,
+						    &gic_irq_domain_ops,
+						    gic);
 	}
-	gic->domain = irq_domain_add_legacy(node, gic_irqs, irq_base,
-				    hwirq_base, &gic_irq_domain_ops, gic);
+
 	if (WARN_ON(!gic->domain))
 		return;
 
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index 0ceb389dba6c..7ed92d0560d5 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -93,6 +93,11 @@ int gic_get_cpu_id(unsigned int cpu);
 void gic_migrate_target(unsigned int new_cpu_id);
 unsigned long gic_get_sgir_physaddr(void);
 
+extern const struct irq_domain_ops *gic_routable_irq_domain_ops;
+static inline void __init register_routable_domain_ops
+					(const struct irq_domain_ops *ops)
+{
+	gic_routable_irq_domain_ops = ops;
+}
 #endif /* __ASSEMBLY */
-
 #endif
-- 
cgit v1.2.3


From 96ca848ef7ea1be7e92d1cceb34ef3aa86053828 Mon Sep 17 00:00:00 2001
From: Sricharan R <r.sricharan@ti.com>
Date: Tue, 3 Dec 2013 15:57:23 +0530
Subject: DRIVERS: IRQCHIP: CROSSBAR: Add support for Crossbar IP

Some socs have a large number of interrupts requests to service
the needs of its many peripherals and subsystems. All of the
interrupt lines from the subsystems are not needed at the same
time, so they have to be muxed to the irq-controller appropriately.
In such places a interrupt controllers are preceded by an CROSSBAR
that provides flexibility in muxing the device requests to the controller
inputs.

This driver takes care a allocating a free irq and then configuring the
crossbar IP as a part of the mpu's irqchip callbacks. crossbar_init should
be called right before the irqchip_init, so that it is setup to handle the
irqchip callbacks.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Santosh Shilimkar <santosh.shilimkar@ti.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Tony Lindgren <tony@atomide.com>
Cc: Rajendra Nayak <rnayak@ti.com>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Rob Herring <rob.herring@calxeda.com>
Signed-off-by: Sricharan R <r.sricharan@ti.com>
Acked-by: Kumar Gala <galak@codeaurora.org> (for DT binding portion)
Acked-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
---
 .../devicetree/bindings/arm/omap/crossbar.txt      |  27 +++
 drivers/irqchip/Kconfig                            |   8 +
 drivers/irqchip/Makefile                           |   1 +
 drivers/irqchip/irq-crossbar.c                     | 208 +++++++++++++++++++++
 include/linux/irqchip/irq-crossbar.h               |  11 ++
 5 files changed, 255 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/arm/omap/crossbar.txt
 create mode 100644 drivers/irqchip/irq-crossbar.c
 create mode 100644 include/linux/irqchip/irq-crossbar.h

(limited to 'include/linux')

diff --git a/Documentation/devicetree/bindings/arm/omap/crossbar.txt b/Documentation/devicetree/bindings/arm/omap/crossbar.txt
new file mode 100644
index 000000000000..fb88585cfb93
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/omap/crossbar.txt
@@ -0,0 +1,27 @@
+Some socs have a large number of interrupts requests to service
+the needs of its many peripherals and subsystems. All of the
+interrupt lines from the subsystems are not needed at the same
+time, so they have to be muxed to the irq-controller appropriately.
+In such places a interrupt controllers are preceded by an CROSSBAR
+that provides flexibility in muxing the device requests to the controller
+inputs.
+
+Required properties:
+- compatible : Should be "ti,irq-crossbar"
+- reg: Base address and the size of the crossbar registers.
+- ti,max-irqs: Total number of irqs available at the interrupt controller.
+- ti,reg-size: Size of a individual register in bytes. Every individual
+	    register is assumed to be of same size. Valid sizes are 1, 2, 4.
+- ti,irqs-reserved: List of the reserved irq lines that are not muxed using
+		 crossbar. These interrupt lines are reserved in the soc,
+		 so crossbar bar driver should not consider them as free
+		 lines.
+
+Examples:
+		crossbar_mpu: @4a020000 {
+			compatible = "ti,irq-crossbar";
+			reg = <0x4a002a48 0x130>;
+			ti,max-irqs = <160>;
+			ti,reg-size = <2>;
+			ti,irqs-reserved = <0 1 2 3 5 6 131 132 139 140>;
+		};
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 61ffdca96e25..111068782da4 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -69,3 +69,11 @@ config VERSATILE_FPGA_IRQ_NR
 config XTENSA_MX
 	bool
 	select IRQ_DOMAIN
+
+config IRQ_CROSSBAR
+	bool
+	help
+	  Support for a CROSSBAR ip that preceeds the main interrupt controller.
+	  The primary irqchip invokes the crossbar's callback which inturn allocates
+	  a free irq and configures the IP. Thus the peripheral interrupts are
+	  routed to one of the free irqchip interrupt lines.
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 86b484cb3ec2..3e776cb8dd46 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -25,3 +25,4 @@ obj-$(CONFIG_ARCH_VT8500)		+= irq-vt8500.o
 obj-$(CONFIG_TB10X_IRQC)		+= irq-tb10x.o
 obj-$(CONFIG_XTENSA)			+= irq-xtensa-pic.o
 obj-$(CONFIG_XTENSA_MX)			+= irq-xtensa-mx.o
+obj-$(CONFIG_IRQ_CROSSBAR)		+= irq-crossbar.o
diff --git a/drivers/irqchip/irq-crossbar.c b/drivers/irqchip/irq-crossbar.c
new file mode 100644
index 000000000000..fc817d28d1fe
--- /dev/null
+++ b/drivers/irqchip/irq-crossbar.c
@@ -0,0 +1,208 @@
+/*
+ *  drivers/irqchip/irq-crossbar.c
+ *
+ *  Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com
+ *  Author: Sricharan R <r.sricharan@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/slab.h>
+#include <linux/irqchip/arm-gic.h>
+
+#define IRQ_FREE	-1
+#define GIC_IRQ_START	32
+
+/*
+ * @int_max: maximum number of supported interrupts
+ * @irq_map: array of interrupts to crossbar number mapping
+ * @crossbar_base: crossbar base address
+ * @register_offsets: offsets for each irq number
+ */
+struct crossbar_device {
+	uint int_max;
+	uint *irq_map;
+	void __iomem *crossbar_base;
+	int *register_offsets;
+	void (*write) (int, int);
+};
+
+static struct crossbar_device *cb;
+
+static inline void crossbar_writel(int irq_no, int cb_no)
+{
+	writel(cb_no, cb->crossbar_base + cb->register_offsets[irq_no]);
+}
+
+static inline void crossbar_writew(int irq_no, int cb_no)
+{
+	writew(cb_no, cb->crossbar_base + cb->register_offsets[irq_no]);
+}
+
+static inline void crossbar_writeb(int irq_no, int cb_no)
+{
+	writeb(cb_no, cb->crossbar_base + cb->register_offsets[irq_no]);
+}
+
+static inline int allocate_free_irq(int cb_no)
+{
+	int i;
+
+	for (i = 0; i < cb->int_max; i++) {
+		if (cb->irq_map[i] == IRQ_FREE) {
+			cb->irq_map[i] = cb_no;
+			return i;
+		}
+	}
+
+	return -ENODEV;
+}
+
+static int crossbar_domain_map(struct irq_domain *d, unsigned int irq,
+			       irq_hw_number_t hw)
+{
+	cb->write(hw - GIC_IRQ_START, cb->irq_map[hw - GIC_IRQ_START]);
+	return 0;
+}
+
+static void crossbar_domain_unmap(struct irq_domain *d, unsigned int irq)
+{
+	irq_hw_number_t hw = irq_get_irq_data(irq)->hwirq;
+
+	if (hw > GIC_IRQ_START)
+		cb->irq_map[hw - GIC_IRQ_START] = IRQ_FREE;
+}
+
+static int crossbar_domain_xlate(struct irq_domain *d,
+				 struct device_node *controller,
+				 const u32 *intspec, unsigned int intsize,
+				 unsigned long *out_hwirq,
+				 unsigned int *out_type)
+{
+	unsigned long ret;
+
+	ret = allocate_free_irq(intspec[1]);
+
+	if (IS_ERR_VALUE(ret))
+		return ret;
+
+	*out_hwirq = ret + GIC_IRQ_START;
+	return 0;
+}
+
+const struct irq_domain_ops routable_irq_domain_ops = {
+	.map = crossbar_domain_map,
+	.unmap = crossbar_domain_unmap,
+	.xlate = crossbar_domain_xlate
+};
+
+static int __init crossbar_of_init(struct device_node *node)
+{
+	int i, size, max, reserved = 0, entry;
+	const __be32 *irqsr;
+
+	cb = kzalloc(sizeof(struct cb_device *), GFP_KERNEL);
+
+	if (!cb)
+		return -ENOMEM;
+
+	cb->crossbar_base = of_iomap(node, 0);
+	if (!cb->crossbar_base)
+		goto err1;
+
+	of_property_read_u32(node, "ti,max-irqs", &max);
+	cb->irq_map = kzalloc(max * sizeof(int), GFP_KERNEL);
+	if (!cb->irq_map)
+		goto err2;
+
+	cb->int_max = max;
+
+	for (i = 0; i < max; i++)
+		cb->irq_map[i] = IRQ_FREE;
+
+	/* Get and mark reserved irqs */
+	irqsr = of_get_property(node, "ti,irqs-reserved", &size);
+	if (irqsr) {
+		size /= sizeof(__be32);
+
+		for (i = 0; i < size; i++) {
+			of_property_read_u32_index(node,
+						   "ti,irqs-reserved",
+						   i, &entry);
+			if (entry > max) {
+				pr_err("Invalid reserved entry\n");
+				goto err3;
+			}
+			cb->irq_map[entry] = 0;
+		}
+	}
+
+	cb->register_offsets = kzalloc(max * sizeof(int), GFP_KERNEL);
+	if (!cb->register_offsets)
+		goto err3;
+
+	of_property_read_u32(node, "ti,reg-size", &size);
+
+	switch (size) {
+	case 1:
+		cb->write = crossbar_writeb;
+		break;
+	case 2:
+		cb->write = crossbar_writew;
+		break;
+	case 4:
+		cb->write = crossbar_writel;
+		break;
+	default:
+		pr_err("Invalid reg-size property\n");
+		goto err4;
+		break;
+	}
+
+	/*
+	 * Register offsets are not linear because of the
+	 * reserved irqs. so find and store the offsets once.
+	 */
+	for (i = 0; i < max; i++) {
+		if (!cb->irq_map[i])
+			continue;
+
+		cb->register_offsets[i] = reserved;
+		reserved += size;
+	}
+
+	register_routable_domain_ops(&routable_irq_domain_ops);
+	return 0;
+
+err4:
+	kfree(cb->register_offsets);
+err3:
+	kfree(cb->irq_map);
+err2:
+	iounmap(cb->crossbar_base);
+err1:
+	kfree(cb);
+	return -ENOMEM;
+}
+
+static const struct of_device_id crossbar_match[] __initconst = {
+	{ .compatible = "ti,irq-crossbar" },
+	{}
+};
+
+int __init irqcrossbar_init(void)
+{
+	struct device_node *np;
+	np = of_find_matching_node(NULL, crossbar_match);
+	if (!np)
+		return -ENODEV;
+
+	crossbar_of_init(np);
+	return 0;
+}
diff --git a/include/linux/irqchip/irq-crossbar.h b/include/linux/irqchip/irq-crossbar.h
new file mode 100644
index 000000000000..e5537b81df8d
--- /dev/null
+++ b/include/linux/irqchip/irq-crossbar.h
@@ -0,0 +1,11 @@
+/*
+ *  drivers/irqchip/irq-crossbar.h
+ *
+ *  Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+int irqcrossbar_init(void);
-- 
cgit v1.2.3


From 781f6d710d4482eab05cfaad50060a0ea8c0e4e0 Mon Sep 17 00:00:00 2001
From: Pawel Moll <pawel.moll@arm.com>
Date: Thu, 30 Jan 2014 13:18:57 +0000
Subject: gpio: generic: Add label to platform data

When registering more than one platform device, it is
useful to set the gpio chip label in the platform data.

Signed-off-by: Pawel Moll <pawel.moll@arm.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-generic.c     | 2 ++
 include/linux/basic_mmio_gpio.h | 1 +
 2 files changed, 3 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/gpio/gpio-generic.c b/drivers/gpio/gpio-generic.c
index d2196bf73847..8c778afdf49f 100644
--- a/drivers/gpio/gpio-generic.c
+++ b/drivers/gpio/gpio-generic.c
@@ -531,6 +531,8 @@ static int bgpio_pdev_probe(struct platform_device *pdev)
 		return err;
 
 	if (pdata) {
+		if (pdata->label)
+			bgc->gc.label = pdata->label;
 		bgc->gc.base = pdata->base;
 		if (pdata->ngpio > 0)
 			bgc->gc.ngpio = pdata->ngpio;
diff --git a/include/linux/basic_mmio_gpio.h b/include/linux/basic_mmio_gpio.h
index d8a97ec0e2b8..0e97856b2cff 100644
--- a/include/linux/basic_mmio_gpio.h
+++ b/include/linux/basic_mmio_gpio.h
@@ -19,6 +19,7 @@
 #include <linux/spinlock_types.h>
 
 struct bgpio_pdata {
+	const char *label;
 	int base;
 	int ngpio;
 };
-- 
cgit v1.2.3


From 1f7c164b6f2a8a028bfc36097fc42bf061c5212e Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 4 Feb 2014 00:45:13 +0100
Subject: ACPI / hotplug / PCI: Rework acpiphp_check_host_bridge()

Since the only existing caller of acpiphp_check_host_bridge(),
which is acpi_pci_root_scan_dependent(), already has a struct
acpi_device pointer needed to obtain the ACPIPHP context, it
doesn't make sense to execute acpi_bus_get_device() on its
handle in acpiphp_handle_to_bridge() just in order to get that
pointer back.

For this reason, modify acpiphp_check_host_bridge() to take
a struct acpi_device pointer as its argument and rearrange the
code accordingly.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/acpi/pci_root.c            |  2 +-
 drivers/pci/hotplug/acpiphp_glue.c | 11 +++--------
 include/linux/pci-acpi.h           |  4 ++--
 3 files changed, 6 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index c1c4102e6478..c288ff3c6998 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -51,7 +51,7 @@ static void acpi_pci_root_remove(struct acpi_device *device);
 
 static int acpi_pci_root_scan_dependent(struct acpi_device *adev)
 {
-	acpiphp_check_host_bridge(adev->handle);
+	acpiphp_check_host_bridge(adev);
 	return 0;
 }
 
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index b7342d2e819b..11a6117fb358 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -382,15 +382,11 @@ static acpi_status register_slot(acpi_handle handle, u32 lvl, void *data,
 	return AE_OK;
 }
 
-static struct acpiphp_bridge *acpiphp_handle_to_bridge(acpi_handle handle)
+static struct acpiphp_bridge *acpiphp_dev_to_bridge(struct acpi_device *adev)
 {
-	struct acpi_device *adev = acpi_bus_get_acpi_device(handle);
 	struct acpiphp_context *context;
 	struct acpiphp_bridge *bridge = NULL;
 
-	if (!adev)
-		return NULL;
-
 	acpi_lock_hp_context();
 	context = acpiphp_get_context(adev);
 	if (context) {
@@ -401,7 +397,6 @@ static struct acpiphp_bridge *acpiphp_handle_to_bridge(acpi_handle handle)
 		acpiphp_put_context(context);
 	}
 	acpi_unlock_hp_context();
-	acpi_bus_put_acpi_device(adev);
 	return bridge;
 }
 
@@ -768,11 +763,11 @@ static void acpiphp_sanitize_bus(struct pci_bus *bus)
  * ACPI event handlers
  */
 
-void acpiphp_check_host_bridge(acpi_handle handle)
+void acpiphp_check_host_bridge(struct acpi_device *adev)
 {
 	struct acpiphp_bridge *bridge;
 
-	bridge = acpiphp_handle_to_bridge(handle);
+	bridge = acpiphp_dev_to_bridge(adev);
 	if (bridge) {
 		pci_lock_rescan_remove();
 
diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h
index 5a462c4e5009..637a608ded0b 100644
--- a/include/linux/pci-acpi.h
+++ b/include/linux/pci-acpi.h
@@ -59,12 +59,12 @@ static inline void acpi_pci_slot_remove(struct pci_bus *bus) { }
 void acpiphp_init(void);
 void acpiphp_enumerate_slots(struct pci_bus *bus);
 void acpiphp_remove_slots(struct pci_bus *bus);
-void acpiphp_check_host_bridge(acpi_handle handle);
+void acpiphp_check_host_bridge(struct acpi_device *adev);
 #else
 static inline void acpiphp_init(void) { }
 static inline void acpiphp_enumerate_slots(struct pci_bus *bus) { }
 static inline void acpiphp_remove_slots(struct pci_bus *bus) { }
-static inline void acpiphp_check_host_bridge(acpi_handle handle) { }
+static inline void acpiphp_check_host_bridge(struct acpi_device *adev) { }
 #endif
 
 #else	/* CONFIG_ACPI */
-- 
cgit v1.2.3


From ef70bbe1aaa612f75360e5df5952fddec50b7ca9 Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Tue, 7 Jan 2014 12:34:11 +0100
Subject: gpio: make gpiod_direction_output take a logical value

The documentation was not clear about whether
gpio_direction_output should take a logical value or the physical
level on the output line, i.e. whether the ACTIVE_LOW status
would be taken into account.

This converts gpiod_direction_output to use the logical level
and adds a new gpiod_direction_output_raw for the raw value.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Reviewed-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 Documentation/gpio/consumer.txt |  1 +
 drivers/gpio/gpiolib.c          | 67 +++++++++++++++++++++++++++++------------
 include/asm-generic/gpio.h      |  2 +-
 include/linux/gpio/consumer.h   |  7 +++++
 4 files changed, 57 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/gpio/consumer.txt b/Documentation/gpio/consumer.txt
index e42f77d8d4ca..09854fe59307 100644
--- a/Documentation/gpio/consumer.txt
+++ b/Documentation/gpio/consumer.txt
@@ -154,6 +154,7 @@ raw line value:
 	void gpiod_set_raw_value(struct gpio_desc *desc, int value)
 	int gpiod_get_raw_value_cansleep(const struct gpio_desc *desc)
 	void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value)
+	int gpiod_direction_output_raw(struct gpio_desc *desc, int value)
 
 The active-low state of a GPIO can also be queried using the following call:
 
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 50c4922fe53a..80da9f1940c9 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -350,9 +350,9 @@ static ssize_t gpio_direction_store(struct device *dev,
 	if (!test_bit(FLAG_EXPORT, &desc->flags))
 		status = -EIO;
 	else if (sysfs_streq(buf, "high"))
-		status = gpiod_direction_output(desc, 1);
+		status = gpiod_direction_output_raw(desc, 1);
 	else if (sysfs_streq(buf, "out") || sysfs_streq(buf, "low"))
-		status = gpiod_direction_output(desc, 0);
+		status = gpiod_direction_output_raw(desc, 0);
 	else if (sysfs_streq(buf, "in"))
 		status = gpiod_direction_input(desc);
 	else
@@ -1590,7 +1590,7 @@ int gpio_request_one(unsigned gpio, unsigned long flags, const char *label)
 	if (flags & GPIOF_DIR_IN)
 		err = gpiod_direction_input(desc);
 	else
-		err = gpiod_direction_output(desc,
+		err = gpiod_direction_output_raw(desc,
 				(flags & GPIOF_INIT_HIGH) ? 1 : 0);
 
 	if (err)
@@ -1756,28 +1756,13 @@ fail:
 }
 EXPORT_SYMBOL_GPL(gpiod_direction_input);
 
-/**
- * gpiod_direction_output - set the GPIO direction to input
- * @desc:	GPIO to set to output
- * @value:	initial output value of the GPIO
- *
- * Set the direction of the passed GPIO to output, such as gpiod_set_value() can
- * be called safely on it. The initial value of the output must be specified.
- *
- * Return 0 in case of success, else an error code.
- */
-int gpiod_direction_output(struct gpio_desc *desc, int value)
+static int _gpiod_direction_output_raw(struct gpio_desc *desc, int value)
 {
 	unsigned long		flags;
 	struct gpio_chip	*chip;
 	int			status = -EINVAL;
 	int offset;
 
-	if (!desc || !desc->chip) {
-		pr_warn("%s: invalid GPIO\n", __func__);
-		return -EINVAL;
-	}
-
 	/* GPIOs used for IRQs shall not be set as output */
 	if (test_bit(FLAG_USED_AS_IRQ, &desc->flags)) {
 		gpiod_err(desc,
@@ -1840,6 +1825,50 @@ fail:
 		gpiod_dbg(desc, "%s: gpio status %d\n", __func__, status);
 	return status;
 }
+
+/**
+ * gpiod_direction_output_raw - set the GPIO direction to output
+ * @desc:	GPIO to set to output
+ * @value:	initial output value of the GPIO
+ *
+ * Set the direction of the passed GPIO to output, such as gpiod_set_value() can
+ * be called safely on it. The initial value of the output must be specified
+ * as raw value on the physical line without regard for the ACTIVE_LOW status.
+ *
+ * Return 0 in case of success, else an error code.
+ */
+int gpiod_direction_output_raw(struct gpio_desc *desc, int value)
+{
+	if (!desc || !desc->chip) {
+		pr_warn("%s: invalid GPIO\n", __func__);
+		return -EINVAL;
+	}
+	return _gpiod_direction_output_raw(desc, value);
+}
+EXPORT_SYMBOL_GPL(gpiod_direction_output_raw);
+
+/**
+ * gpiod_direction_output - set the GPIO direction to input
+ * @desc:	GPIO to set to output
+ * @value:	initial output value of the GPIO
+ *
+ * Set the direction of the passed GPIO to output, such as gpiod_set_value() can
+ * be called safely on it. The initial value of the output must be specified
+ * as the logical value of the GPIO, i.e. taking its ACTIVE_LOW status into
+ * account.
+ *
+ * Return 0 in case of success, else an error code.
+ */
+int gpiod_direction_output(struct gpio_desc *desc, int value)
+{
+	if (!desc || !desc->chip) {
+		pr_warn("%s: invalid GPIO\n", __func__);
+		return -EINVAL;
+	}
+	if (test_bit(FLAG_ACTIVE_LOW, &desc->flags))
+		value = !value;
+	return _gpiod_direction_output_raw(desc, value);
+}
 EXPORT_SYMBOL_GPL(gpiod_direction_output);
 
 /**
diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h
index a5f56a0213a7..23e364538ab5 100644
--- a/include/asm-generic/gpio.h
+++ b/include/asm-generic/gpio.h
@@ -69,7 +69,7 @@ static inline int gpio_direction_input(unsigned gpio)
 }
 static inline int gpio_direction_output(unsigned gpio, int value)
 {
-	return gpiod_direction_output(gpio_to_desc(gpio), value);
+	return gpiod_direction_output_raw(gpio_to_desc(gpio), value);
 }
 
 static inline int gpio_set_debounce(unsigned gpio, unsigned debounce)
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index 4d34dbbbad4d..387994325122 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -36,6 +36,7 @@ void devm_gpiod_put(struct device *dev, struct gpio_desc *desc);
 int gpiod_get_direction(const struct gpio_desc *desc);
 int gpiod_direction_input(struct gpio_desc *desc);
 int gpiod_direction_output(struct gpio_desc *desc, int value);
+int gpiod_direction_output_raw(struct gpio_desc *desc, int value);
 
 /* Value get/set from non-sleeping context */
 int gpiod_get_value(const struct gpio_desc *desc);
@@ -121,6 +122,12 @@ static inline int gpiod_direction_output(struct gpio_desc *desc, int value)
 	WARN_ON(1);
 	return -ENOSYS;
 }
+static inline int gpiod_direction_output_raw(struct gpio_desc *desc, int value)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+	return -ENOSYS;
+}
 
 
 static inline int gpiod_get_value(const struct gpio_desc *desc)
-- 
cgit v1.2.3


From 91eef3e2fee581b00f027bbb0d144788a3c609a9 Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@ucw.cz>
Date: Tue, 21 Jan 2014 21:56:27 +0100
Subject: staging/bluetooth: Add hci_h4p driver
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add hci_h4p bluetooth driver to staging tree. This device is used
for example on Nokia N900 cell phone.

Signed-off-by: Pali Rohár <pali.rohar@gmail.com>
Signed-off-by: Pavel Machek <pavel@ucw.cz>
Thanks-to: Sebastian Reichel <sre@debian.org>
Thanks-to: Joe Perches <joe@perches.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/Kconfig                     |    2 +
 drivers/staging/Makefile                    |    1 +
 drivers/staging/nokia_h4p/Kconfig           |    9 +
 drivers/staging/nokia_h4p/Makefile          |    6 +
 drivers/staging/nokia_h4p/TODO              |  140 ++++
 drivers/staging/nokia_h4p/hci_h4p.h         |  228 +++++
 drivers/staging/nokia_h4p/nokia_core.c      | 1205 +++++++++++++++++++++++++++
 drivers/staging/nokia_h4p/nokia_fw-bcm.c    |  147 ++++
 drivers/staging/nokia_h4p/nokia_fw-csr.c    |  150 ++++
 drivers/staging/nokia_h4p/nokia_fw-ti1273.c |  110 +++
 drivers/staging/nokia_h4p/nokia_fw.c        |  195 +++++
 drivers/staging/nokia_h4p/nokia_uart.c      |  199 +++++
 include/linux/platform_data/bt-nokia-h4p.h  |   38 +
 13 files changed, 2430 insertions(+)
 create mode 100644 drivers/staging/nokia_h4p/Kconfig
 create mode 100644 drivers/staging/nokia_h4p/Makefile
 create mode 100644 drivers/staging/nokia_h4p/TODO
 create mode 100644 drivers/staging/nokia_h4p/hci_h4p.h
 create mode 100644 drivers/staging/nokia_h4p/nokia_core.c
 create mode 100644 drivers/staging/nokia_h4p/nokia_fw-bcm.c
 create mode 100644 drivers/staging/nokia_h4p/nokia_fw-csr.c
 create mode 100644 drivers/staging/nokia_h4p/nokia_fw-ti1273.c
 create mode 100644 drivers/staging/nokia_h4p/nokia_fw.c
 create mode 100644 drivers/staging/nokia_h4p/nokia_uart.c
 create mode 100644 include/linux/platform_data/bt-nokia-h4p.h

(limited to 'include/linux')

diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig
index 93a7ecf936ac..babb1cf67ce7 100644
--- a/drivers/staging/Kconfig
+++ b/drivers/staging/Kconfig
@@ -148,4 +148,6 @@ source "drivers/staging/dgap/Kconfig"
 
 source "drivers/staging/gs_fpgaboot/Kconfig"
 
+source "drivers/staging/nokia_h4p/Kconfig"
+
 endif # STAGING
diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile
index 399f9fe07014..2c4949a9bd9b 100644
--- a/drivers/staging/Makefile
+++ b/drivers/staging/Makefile
@@ -66,3 +66,4 @@ obj-$(CONFIG_DGNC)			+= dgnc/
 obj-$(CONFIG_DGAP)			+= dgap/
 obj-$(CONFIG_MTD_SPINAND_MT29F)	+= mt29f_spinand/
 obj-$(CONFIG_GS_FPGABOOT)	+= gs_fpgaboot/
+obj-$(CONFIG_BT_NOKIA_H4P)	+= nokia_h4p/
diff --git a/drivers/staging/nokia_h4p/Kconfig b/drivers/staging/nokia_h4p/Kconfig
new file mode 100644
index 000000000000..4336c0ad065b
--- /dev/null
+++ b/drivers/staging/nokia_h4p/Kconfig
@@ -0,0 +1,9 @@
+config BT_NOKIA_H4P
+	tristate "HCI driver with H4 Nokia extensions"
+	depends on BT && ARCH_OMAP
+	help
+	  Bluetooth HCI driver with H4 extensions.  This driver provides
+	  support for H4+ Bluetooth chip with vendor-specific H4 extensions.
+
+	  Say Y here to compile support for h4 extended devices into the kernel
+	  or say M to compile it as module (btnokia_h4p).
diff --git a/drivers/staging/nokia_h4p/Makefile b/drivers/staging/nokia_h4p/Makefile
new file mode 100644
index 000000000000..9625db4a9af3
--- /dev/null
+++ b/drivers/staging/nokia_h4p/Makefile
@@ -0,0 +1,6 @@
+
+obj-$(CONFIG_BT_NOKIA_H4P)		+= btnokia_h4p.o
+btnokia_h4p-objs := nokia_core.o nokia_fw.o nokia_uart.o nokia_fw-csr.o \
+		nokia_fw-bcm.o nokia_fw-ti1273.o
+
+ccflags-y += -D__CHECK_ENDIAN__
diff --git a/drivers/staging/nokia_h4p/TODO b/drivers/staging/nokia_h4p/TODO
new file mode 100644
index 000000000000..d997afe14173
--- /dev/null
+++ b/drivers/staging/nokia_h4p/TODO
@@ -0,0 +1,140 @@
+Few attempts to submission have been made, last review comments were received in
+
+Date: Wed, 15 Jan 2014 19:01:51 -0800
+From: Marcel Holtmann <marcel@holtmann.org>
+Subject: Re: [PATCH v6] Bluetooth: Add hci_h4p driver
+
+Some code refactoring is still needed.
+
+TODO:
+
+> +++ b/drivers/bluetooth/hci_h4p.h
+
+can we please get the naming straight. File names do not start with
+hci_ anymore. We moved away from it since that term is too generic.
+
+> +#define FW_NAME_TI1271_LE    "ti1273_le.bin"
+> +#define FW_NAME_TI1271               "ti1273.bin"
+> +#define FW_NAME_BCM2048              "bcmfw.bin"
+> +#define FW_NAME_CSR          "bc4fw.bin"
+
+We do these have to be global in a header file. This should be
+confined to the specific firmware part.
+
+> +struct hci_h4p_info {
+
+Can we please get rid of the hci_ prefix for everything. Copying from
+drivers that are over 10 years old is not a good idea. Please look at
+recent ones.
+
+> +     struct timer_list lazy_release;
+
+Timer? Not delayed work?
+
+> +void hci_h4p_outb(struct hci_h4p_info *info, unsigned int offset, u8 val);
+> +u8 hci_h4p_inb(struct hci_h4p_info *info, unsigned int offset);
+> +void hci_h4p_set_rts(struct hci_h4p_info *info, int active);
+> +int hci_h4p_wait_for_cts(struct hci_h4p_info *info, int active, int timeout_ms);
+> +void __hci_h4p_set_auto_ctsrts(struct hci_h4p_info *info, int on, u8 which);
+> +void hci_h4p_set_auto_ctsrts(struct hci_h4p_info *info, int on, u8 which);
+> +void hci_h4p_change_speed(struct hci_h4p_info *info, unsigned long speed);
+> +int hci_h4p_reset_uart(struct hci_h4p_info *info);
+> +void hci_h4p_init_uart(struct hci_h4p_info *info);
+> +void hci_h4p_enable_tx(struct hci_h4p_info *info);
+> +void hci_h4p_store_regs(struct hci_h4p_info *info);
+> +void hci_h4p_restore_regs(struct hci_h4p_info *info);
+> +void hci_h4p_smart_idle(struct hci_h4p_info *info, bool enable);
+
+These are a lot of public functions. Are they all really needed or can
+the code be done smart.
+
+> +static ssize_t hci_h4p_store_bdaddr(struct device *dev,
+> +                                 struct device_attribute *attr,
+> +                                 const char *buf, size_t count)
+> +{
+> +     struct hci_h4p_info *info = dev_get_drvdata(dev);
+
+Since none of these devices can function without having a valid
+address, the way this should work is that we should not register the
+HCI device when probing the platform device.
+    
+The HCI device should be registered once a valid address has been
+written into the sysfs file. I do not want to play the tricks with
+bringing up the device without a valid address.
+
+> +     hdev->close = hci_h4p_hci_close;
+> +     hdev->flush = hci_h4p_hci_flush;
+> +     hdev->send = hci_h4p_hci_send_frame;
+    
+It needs to use hdev->setup to load the firmware. I assume the
+firmware only needs to be loaded once. That is exactly what
+hdev->setup does. It gets executed once.
+    
+> +     set_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks);
+
+Is this quirk really needed? Normally only Bluetooth 1.1 and early
+devices qualify for it.
+
+> +static int hci_h4p_bcm_set_bdaddr(struct hci_h4p_info *info, struct sk_buff *skb)
+> +{
+> +     int i;
+> +     static const u8 nokia_oui[3] = {0x00, 0x1f, 0xdf};
+> +     int not_valid;
+
+Has this actually been confirmed that we can just randomly set an
+address out of the Nokia range. I do not think so. This is a pretty
+bad idea.
+
+I have no interest in merging a driver with such a hack.
+
+> +     not_valid = 1;
+> +     for (i = 0; i < 6; i++) {
+> +             if (info->bd_addr[i] != 0x00) {
+> +                     not_valid = 0;
+> +                     break;
+> +             }   
+> +     }
+
+Anybody every heard of memcmp or bacmp and BDADDR_ANY?
+
+> +             if (not_valid) {
+> +                     dev_info(info->dev, "Valid bluetooth address not found,"
+> +                                     " setting some random\n");
+> +                     /* When address is not valid, use some random */
+> +                     memcpy(info->bd_addr, nokia_oui, 3);
+> +                     get_random_bytes(info->bd_addr + 3, 3);
+> +             }
+
+
+And why does every single chip firmware does this differently. Seriously, this is a mess.
+
+> +void hci_h4p_parse_fw_event(struct hci_h4p_info *info, struct sk_buff *skb)
+> +{
+> +     switch (info->man_id) {
+> +     case H4P_ID_CSR:
+> +             hci_h4p_bc4_parse_fw_event(info, skb);
+> +             break;
+...
+> +}
+
+We have proper HCI sync command handling in recent kernels. I really
+do not know why this is hand coded these days. Check how the Intel
+firmware loading inside btusb.c does it.
+
+> +inline u8 hci_h4p_inb(struct hci_h4p_info *info, unsigned int offset)
+> +{ 
+> +     return __raw_readb(info->uart_base + (offset << 2));
+> +}
+
+Inline in a *.c file for a non-static function. Makes no sense to me.
+
+> +/**
+> + * struct hci_h4p_platform data - hci_h4p Platform data structure
+> + */
+> +struct hci_h4p_platform_data {
+
+please have a proper name here. For example
+btnokia_h4p_platform_data.
+
+Please send patches to Greg Kroah-Hartman <greg@kroah.com> and Cc:
+Pavel Machek <pavel@ucw.cz>
diff --git a/drivers/staging/nokia_h4p/hci_h4p.h b/drivers/staging/nokia_h4p/hci_h4p.h
new file mode 100644
index 000000000000..fd7a6407f20c
--- /dev/null
+++ b/drivers/staging/nokia_h4p/hci_h4p.h
@@ -0,0 +1,228 @@
+/*
+ * This file is part of Nokia H4P bluetooth driver
+ *
+ * Copyright (C) 2005-2008 Nokia Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
+ * 02110-1301 USA
+ *
+ */
+
+#ifndef __DRIVERS_BLUETOOTH_HCI_H4P_H
+#define __DRIVERS_BLUETOOTH_HCI_H4P_H
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
+#include <net/bluetooth/hci.h>
+
+#define FW_NAME_TI1271_PRELE	"ti1273_prele.bin"
+#define FW_NAME_TI1271_LE	"ti1273_le.bin"
+#define FW_NAME_TI1271		"ti1273.bin"
+#define FW_NAME_BCM2048		"bcmfw.bin"
+#define FW_NAME_CSR		"bc4fw.bin"
+
+#define UART_SYSC_OMAP_RESET	0x03
+#define UART_SYSS_RESETDONE	0x01
+#define UART_OMAP_SCR_EMPTY_THR	0x08
+#define UART_OMAP_SCR_WAKEUP	0x10
+#define UART_OMAP_SSR_WAKEUP	0x02
+#define UART_OMAP_SSR_TXFULL	0x01
+
+#define UART_OMAP_SYSC_IDLEMODE		0x03
+#define UART_OMAP_SYSC_IDLEMASK		(3 << UART_OMAP_SYSC_IDLEMODE)
+
+#define UART_OMAP_SYSC_FORCE_IDLE	(0 << UART_OMAP_SYSC_IDLEMODE)
+#define UART_OMAP_SYSC_NO_IDLE		(1 << UART_OMAP_SYSC_IDLEMODE)
+#define UART_OMAP_SYSC_SMART_IDLE	(2 << UART_OMAP_SYSC_IDLEMODE)
+
+#define H4P_TRANSFER_MODE		1
+#define H4P_SCHED_TRANSFER_MODE		2
+#define H4P_ACTIVE_MODE			3
+
+struct hci_h4p_info {
+	struct timer_list lazy_release;
+	struct hci_dev *hdev;
+	spinlock_t lock;
+
+	void __iomem *uart_base;
+	unsigned long uart_phys_base;
+	int irq;
+	struct device *dev;
+	u8 chip_type;
+	u8 bt_wakeup_gpio;
+	u8 host_wakeup_gpio;
+	u8 reset_gpio;
+	u8 reset_gpio_shared;
+	u8 bt_sysclk;
+	u8 man_id;
+	u8 ver_id;
+
+	struct sk_buff_head fw_queue;
+	struct sk_buff *alive_cmd_skb;
+	struct completion init_completion;
+	struct completion fw_completion;
+	struct completion test_completion;
+	int fw_error;
+	int init_error;
+
+	struct sk_buff_head txq;
+
+	struct sk_buff *rx_skb;
+	long rx_count;
+	unsigned long rx_state;
+	unsigned long garbage_bytes;
+
+	u8 bd_addr[6];
+	struct sk_buff_head *fw_q;
+
+	int pm_enabled;
+	int tx_enabled;
+	int autorts;
+	int rx_enabled;
+	unsigned long pm_flags;
+
+	int tx_clocks_en;
+	int rx_clocks_en;
+	spinlock_t clocks_lock;
+	struct clk *uart_iclk;
+	struct clk *uart_fclk;
+	atomic_t clk_users;
+	u16 dll;
+	u16 dlh;
+	u16 ier;
+	u16 mdr1;
+	u16 efr;
+};
+
+struct hci_h4p_radio_hdr {
+	__u8 evt;
+	__u8 dlen;
+} __attribute__ ((packed));
+
+struct hci_h4p_neg_hdr {
+	__u8 dlen;
+} __attribute__ ((packed));
+#define H4P_NEG_HDR_SIZE 1
+
+#define H4P_NEG_REQ	0x00
+#define H4P_NEG_ACK	0x20
+#define H4P_NEG_NAK	0x40
+
+#define H4P_PROTO_PKT	0x44
+#define H4P_PROTO_BYTE	0x4c
+
+#define H4P_ID_CSR	0x02
+#define H4P_ID_BCM2048	0x04
+#define H4P_ID_TI1271	0x31
+
+struct hci_h4p_neg_cmd {
+	__u8	ack;
+	__u16	baud;
+	__u16	unused1;
+	__u8	proto;
+	__u16	sys_clk;
+	__u16	unused2;
+} __attribute__ ((packed));
+
+struct hci_h4p_neg_evt {
+	__u8	ack;
+	__u16	baud;
+	__u16	unused1;
+	__u8	proto;
+	__u16	sys_clk;
+	__u16	unused2;
+	__u8	man_id;
+	__u8	ver_id;
+} __attribute__ ((packed));
+
+#define H4P_ALIVE_REQ	0x55
+#define H4P_ALIVE_RESP	0xcc
+
+struct hci_h4p_alive_hdr {
+	__u8	dlen;
+} __attribute__ ((packed));
+#define H4P_ALIVE_HDR_SIZE 1
+
+struct hci_h4p_alive_pkt {
+	__u8	mid;
+	__u8	unused;
+} __attribute__ ((packed));
+
+#define MAX_BAUD_RATE		921600
+#define BC4_MAX_BAUD_RATE	3692300
+#define UART_CLOCK		48000000
+#define BT_INIT_DIVIDER		320
+#define BT_BAUDRATE_DIVIDER	384000000
+#define BT_SYSCLK_DIV		1000
+#define INIT_SPEED		120000
+
+#define H4_TYPE_SIZE		1
+#define H4_RADIO_HDR_SIZE	2
+
+/* H4+ packet types */
+#define H4_CMD_PKT		0x01
+#define H4_ACL_PKT		0x02
+#define H4_SCO_PKT		0x03
+#define H4_EVT_PKT		0x04
+#define H4_NEG_PKT		0x06
+#define H4_ALIVE_PKT		0x07
+#define H4_RADIO_PKT		0x08
+
+/* TX states */
+#define WAIT_FOR_PKT_TYPE	1
+#define WAIT_FOR_HEADER		2
+#define WAIT_FOR_DATA		3
+
+struct hci_fw_event {
+	struct hci_event_hdr hev;
+	struct hci_ev_cmd_complete cmd;
+	u8 status;
+} __attribute__ ((packed));
+
+int hci_h4p_send_alive_packet(struct hci_h4p_info *info);
+
+void hci_h4p_bcm_parse_fw_event(struct hci_h4p_info *info,
+				struct sk_buff *skb);
+int hci_h4p_bcm_send_fw(struct hci_h4p_info *info,
+			struct sk_buff_head *fw_queue);
+
+void hci_h4p_bc4_parse_fw_event(struct hci_h4p_info *info,
+				struct sk_buff *skb);
+int hci_h4p_bc4_send_fw(struct hci_h4p_info *info,
+			struct sk_buff_head *fw_queue);
+
+void hci_h4p_ti1273_parse_fw_event(struct hci_h4p_info *info,
+				    struct sk_buff *skb);
+int hci_h4p_ti1273_send_fw(struct hci_h4p_info *info,
+			    struct sk_buff_head *fw_queue);
+
+int hci_h4p_read_fw(struct hci_h4p_info *info, struct sk_buff_head *fw_queue);
+int hci_h4p_send_fw(struct hci_h4p_info *info, struct sk_buff_head *fw_queue);
+void hci_h4p_parse_fw_event(struct hci_h4p_info *info, struct sk_buff *skb);
+
+void hci_h4p_outb(struct hci_h4p_info *info, unsigned int offset, u8 val);
+u8 hci_h4p_inb(struct hci_h4p_info *info, unsigned int offset);
+void hci_h4p_set_rts(struct hci_h4p_info *info, int active);
+int hci_h4p_wait_for_cts(struct hci_h4p_info *info, int active, int timeout_ms);
+void __hci_h4p_set_auto_ctsrts(struct hci_h4p_info *info, int on, u8 which);
+void hci_h4p_set_auto_ctsrts(struct hci_h4p_info *info, int on, u8 which);
+void hci_h4p_change_speed(struct hci_h4p_info *info, unsigned long speed);
+int hci_h4p_reset_uart(struct hci_h4p_info *info);
+void hci_h4p_init_uart(struct hci_h4p_info *info);
+void hci_h4p_enable_tx(struct hci_h4p_info *info);
+void hci_h4p_store_regs(struct hci_h4p_info *info);
+void hci_h4p_restore_regs(struct hci_h4p_info *info);
+void hci_h4p_smart_idle(struct hci_h4p_info *info, bool enable);
+
+#endif /* __DRIVERS_BLUETOOTH_HCI_H4P_H */
diff --git a/drivers/staging/nokia_h4p/nokia_core.c b/drivers/staging/nokia_h4p/nokia_core.c
new file mode 100644
index 000000000000..5da84b06eff3
--- /dev/null
+++ b/drivers/staging/nokia_h4p/nokia_core.c
@@ -0,0 +1,1205 @@
+/*
+ * This file is part of Nokia H4P bluetooth driver
+ *
+ * Copyright (C) 2005-2008 Nokia Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
+ * 02110-1301 USA
+ *
+ * Thanks to all the Nokia people that helped with this driver,
+ * including Ville Tervo and Roger Quadros.
+ *
+ * Power saving functionality was removed from this driver to make
+ * merging easier.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/serial_reg.h>
+#include <linux/skbuff.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/gpio.h>
+#include <linux/timer.h>
+#include <linux/kthread.h>
+#include <linux/io.h>
+#include <linux/completion.h>
+#include <linux/sizes.h>
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
+#include <net/bluetooth/hci.h>
+
+#include <linux/platform_data/bt-nokia-h4p.h>
+
+#include "hci_h4p.h"
+
+/* This should be used in function that cannot release clocks */
+static void hci_h4p_set_clk(struct hci_h4p_info *info, int *clock, int enable)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&info->clocks_lock, flags);
+	if (enable && !*clock) {
+		BT_DBG("Enabling %p", clock);
+		clk_prepare_enable(info->uart_fclk);
+		clk_prepare_enable(info->uart_iclk);
+		if (atomic_read(&info->clk_users) == 0)
+			hci_h4p_restore_regs(info);
+		atomic_inc(&info->clk_users);
+	}
+
+	if (!enable && *clock) {
+		BT_DBG("Disabling %p", clock);
+		if (atomic_dec_and_test(&info->clk_users))
+			hci_h4p_store_regs(info);
+		clk_disable_unprepare(info->uart_fclk);
+		clk_disable_unprepare(info->uart_iclk);
+	}
+
+	*clock = enable;
+	spin_unlock_irqrestore(&info->clocks_lock, flags);
+}
+
+static void hci_h4p_lazy_clock_release(unsigned long data)
+{
+	struct hci_h4p_info *info = (struct hci_h4p_info *)data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&info->lock, flags);
+	if (!info->tx_enabled)
+		hci_h4p_set_clk(info, &info->tx_clocks_en, 0);
+	spin_unlock_irqrestore(&info->lock, flags);
+}
+
+/* Power management functions */
+void hci_h4p_smart_idle(struct hci_h4p_info *info, bool enable)
+{
+	u8 v;
+
+	v = hci_h4p_inb(info, UART_OMAP_SYSC);
+	v &= ~(UART_OMAP_SYSC_IDLEMASK);
+
+	if (enable)
+		v |= UART_OMAP_SYSC_SMART_IDLE;
+	else
+		v |= UART_OMAP_SYSC_NO_IDLE;
+
+	hci_h4p_outb(info, UART_OMAP_SYSC, v);
+}
+
+static inline void h4p_schedule_pm(struct hci_h4p_info *info)
+{
+}
+
+static void hci_h4p_disable_tx(struct hci_h4p_info *info)
+{
+	if (!info->pm_enabled)
+		return;
+
+	/* Re-enable smart-idle */
+	hci_h4p_smart_idle(info, 1);
+
+	gpio_set_value(info->bt_wakeup_gpio, 0);
+	mod_timer(&info->lazy_release, jiffies + msecs_to_jiffies(100));
+	info->tx_enabled = 0;
+}
+
+void hci_h4p_enable_tx(struct hci_h4p_info *info)
+{
+	unsigned long flags;
+
+	if (!info->pm_enabled)
+		return;
+
+	h4p_schedule_pm(info);
+
+	spin_lock_irqsave(&info->lock, flags);
+	del_timer(&info->lazy_release);
+	hci_h4p_set_clk(info, &info->tx_clocks_en, 1);
+	info->tx_enabled = 1;
+	gpio_set_value(info->bt_wakeup_gpio, 1);
+	hci_h4p_outb(info, UART_IER, hci_h4p_inb(info, UART_IER) |
+		     UART_IER_THRI);
+	/*
+	 * Disable smart-idle as UART TX interrupts
+	 * are not wake-up capable
+	 */
+	hci_h4p_smart_idle(info, 0);
+
+	spin_unlock_irqrestore(&info->lock, flags);
+}
+
+static void hci_h4p_disable_rx(struct hci_h4p_info *info)
+{
+	if (!info->pm_enabled)
+		return;
+
+	info->rx_enabled = 0;
+
+	if (hci_h4p_inb(info, UART_LSR) & UART_LSR_DR)
+		return;
+
+	if (!(hci_h4p_inb(info, UART_LSR) & UART_LSR_TEMT))
+		return;
+
+	__hci_h4p_set_auto_ctsrts(info, 0, UART_EFR_RTS);
+	info->autorts = 0;
+	hci_h4p_set_clk(info, &info->rx_clocks_en, 0);
+}
+
+static void hci_h4p_enable_rx(struct hci_h4p_info *info)
+{
+	if (!info->pm_enabled)
+		return;
+
+	h4p_schedule_pm(info);
+
+	hci_h4p_set_clk(info, &info->rx_clocks_en, 1);
+	info->rx_enabled = 1;
+
+	if (!(hci_h4p_inb(info, UART_LSR) & UART_LSR_TEMT))
+		return;
+
+	__hci_h4p_set_auto_ctsrts(info, 1, UART_EFR_RTS);
+	info->autorts = 1;
+}
+
+/* Negotiation functions */
+int hci_h4p_send_alive_packet(struct hci_h4p_info *info)
+{
+	struct hci_h4p_alive_hdr *hdr;
+	struct hci_h4p_alive_pkt *pkt;
+	struct sk_buff *skb;
+	unsigned long flags;
+	int len;
+
+	BT_DBG("Sending alive packet");
+
+	len = H4_TYPE_SIZE + sizeof(*hdr) + sizeof(*pkt);
+	skb = bt_skb_alloc(len, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	memset(skb->data, 0x00, len);
+	*skb_put(skb, 1) = H4_ALIVE_PKT;
+	hdr = (struct hci_h4p_alive_hdr *)skb_put(skb, sizeof(*hdr));
+	hdr->dlen = sizeof(*pkt);
+	pkt = (struct hci_h4p_alive_pkt *)skb_put(skb, sizeof(*pkt));
+	pkt->mid = H4P_ALIVE_REQ;
+
+	skb_queue_tail(&info->txq, skb);
+	spin_lock_irqsave(&info->lock, flags);
+	hci_h4p_outb(info, UART_IER, hci_h4p_inb(info, UART_IER) |
+		     UART_IER_THRI);
+	spin_unlock_irqrestore(&info->lock, flags);
+
+	BT_DBG("Alive packet sent");
+
+	return 0;
+}
+
+static void hci_h4p_alive_packet(struct hci_h4p_info *info,
+				 struct sk_buff *skb)
+{
+	struct hci_h4p_alive_hdr *hdr;
+	struct hci_h4p_alive_pkt *pkt;
+
+	BT_DBG("Received alive packet");
+	hdr = (struct hci_h4p_alive_hdr *)skb->data;
+	if (hdr->dlen != sizeof(*pkt)) {
+		dev_err(info->dev, "Corrupted alive message\n");
+		info->init_error = -EIO;
+		goto finish_alive;
+	}
+
+	pkt = (struct hci_h4p_alive_pkt *)skb_pull(skb, sizeof(*hdr));
+	if (pkt->mid != H4P_ALIVE_RESP) {
+		dev_err(info->dev, "Could not negotiate hci_h4p settings\n");
+		info->init_error = -EINVAL;
+	}
+
+finish_alive:
+	complete(&info->init_completion);
+	kfree_skb(skb);
+}
+
+static int hci_h4p_send_negotiation(struct hci_h4p_info *info)
+{
+	struct hci_h4p_neg_cmd *neg_cmd;
+	struct hci_h4p_neg_hdr *neg_hdr;
+	struct sk_buff *skb;
+	unsigned long flags;
+	int err, len;
+	u16 sysclk;
+
+	BT_DBG("Sending negotiation..");
+
+	switch (info->bt_sysclk) {
+	case 1:
+		sysclk = 12000;
+		break;
+	case 2:
+		sysclk = 38400;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	len = sizeof(*neg_cmd) + sizeof(*neg_hdr) + H4_TYPE_SIZE;
+	skb = bt_skb_alloc(len, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	memset(skb->data, 0x00, len);
+	*skb_put(skb, 1) = H4_NEG_PKT;
+	neg_hdr = (struct hci_h4p_neg_hdr *)skb_put(skb, sizeof(*neg_hdr));
+	neg_cmd = (struct hci_h4p_neg_cmd *)skb_put(skb, sizeof(*neg_cmd));
+
+	neg_hdr->dlen = sizeof(*neg_cmd);
+	neg_cmd->ack = H4P_NEG_REQ;
+	neg_cmd->baud = cpu_to_le16(BT_BAUDRATE_DIVIDER/MAX_BAUD_RATE);
+	neg_cmd->proto = H4P_PROTO_BYTE;
+	neg_cmd->sys_clk = cpu_to_le16(sysclk);
+
+	hci_h4p_change_speed(info, INIT_SPEED);
+
+	hci_h4p_set_rts(info, 1);
+	info->init_error = 0;
+	init_completion(&info->init_completion);
+	skb_queue_tail(&info->txq, skb);
+	spin_lock_irqsave(&info->lock, flags);
+	hci_h4p_outb(info, UART_IER, hci_h4p_inb(info, UART_IER) |
+		     UART_IER_THRI);
+	spin_unlock_irqrestore(&info->lock, flags);
+
+	if (!wait_for_completion_interruptible_timeout(&info->init_completion,
+				msecs_to_jiffies(1000)))
+		return -ETIMEDOUT;
+
+	if (info->init_error < 0)
+		return info->init_error;
+
+	/* Change to operational settings */
+	hci_h4p_set_auto_ctsrts(info, 0, UART_EFR_RTS);
+	hci_h4p_set_rts(info, 0);
+	hci_h4p_change_speed(info, MAX_BAUD_RATE);
+
+	err = hci_h4p_wait_for_cts(info, 1, 100);
+	if (err < 0)
+		return err;
+
+	hci_h4p_set_auto_ctsrts(info, 1, UART_EFR_RTS);
+	init_completion(&info->init_completion);
+	err = hci_h4p_send_alive_packet(info);
+
+	if (err < 0)
+		return err;
+
+	if (!wait_for_completion_interruptible_timeout(&info->init_completion,
+				msecs_to_jiffies(1000)))
+		return -ETIMEDOUT;
+
+	if (info->init_error < 0)
+		return info->init_error;
+
+	BT_DBG("Negotiation successful");
+	return 0;
+}
+
+static void hci_h4p_negotiation_packet(struct hci_h4p_info *info,
+				       struct sk_buff *skb)
+{
+	struct hci_h4p_neg_hdr *hdr;
+	struct hci_h4p_neg_evt *evt;
+
+	hdr = (struct hci_h4p_neg_hdr *)skb->data;
+	if (hdr->dlen != sizeof(*evt)) {
+		info->init_error = -EIO;
+		goto finish_neg;
+	}
+
+	evt = (struct hci_h4p_neg_evt *)skb_pull(skb, sizeof(*hdr));
+
+	if (evt->ack != H4P_NEG_ACK) {
+		dev_err(info->dev, "Could not negotiate hci_h4p settings\n");
+		info->init_error = -EINVAL;
+	}
+
+	info->man_id = evt->man_id;
+	info->ver_id = evt->ver_id;
+
+finish_neg:
+
+	complete(&info->init_completion);
+	kfree_skb(skb);
+}
+
+/* H4 packet handling functions */
+static int hci_h4p_get_hdr_len(struct hci_h4p_info *info, u8 pkt_type)
+{
+	long retval;
+
+	switch (pkt_type) {
+	case H4_EVT_PKT:
+		retval = HCI_EVENT_HDR_SIZE;
+		break;
+	case H4_ACL_PKT:
+		retval = HCI_ACL_HDR_SIZE;
+		break;
+	case H4_SCO_PKT:
+		retval = HCI_SCO_HDR_SIZE;
+		break;
+	case H4_NEG_PKT:
+		retval = H4P_NEG_HDR_SIZE;
+		break;
+	case H4_ALIVE_PKT:
+		retval = H4P_ALIVE_HDR_SIZE;
+		break;
+	case H4_RADIO_PKT:
+		retval = H4_RADIO_HDR_SIZE;
+		break;
+	default:
+		dev_err(info->dev, "Unknown H4 packet type 0x%.2x\n", pkt_type);
+		retval = -1;
+		break;
+	}
+
+	return retval;
+}
+
+static unsigned int hci_h4p_get_data_len(struct hci_h4p_info *info,
+					 struct sk_buff *skb)
+{
+	long retval = -1;
+	struct hci_acl_hdr *acl_hdr;
+	struct hci_sco_hdr *sco_hdr;
+	struct hci_event_hdr *evt_hdr;
+	struct hci_h4p_neg_hdr *neg_hdr;
+	struct hci_h4p_alive_hdr *alive_hdr;
+	struct hci_h4p_radio_hdr *radio_hdr;
+
+	switch (bt_cb(skb)->pkt_type) {
+	case H4_EVT_PKT:
+		evt_hdr = (struct hci_event_hdr *)skb->data;
+		retval = evt_hdr->plen;
+		break;
+	case H4_ACL_PKT:
+		acl_hdr = (struct hci_acl_hdr *)skb->data;
+		retval = le16_to_cpu(acl_hdr->dlen);
+		break;
+	case H4_SCO_PKT:
+		sco_hdr = (struct hci_sco_hdr *)skb->data;
+		retval = sco_hdr->dlen;
+		break;
+	case H4_RADIO_PKT:
+		radio_hdr = (struct hci_h4p_radio_hdr *)skb->data;
+		retval = radio_hdr->dlen;
+		break;
+	case H4_NEG_PKT:
+		neg_hdr = (struct hci_h4p_neg_hdr *)skb->data;
+		retval = neg_hdr->dlen;
+		break;
+	case H4_ALIVE_PKT:
+		alive_hdr = (struct hci_h4p_alive_hdr *)skb->data;
+		retval = alive_hdr->dlen;
+		break;
+	}
+
+	return retval;
+}
+
+static inline void hci_h4p_recv_frame(struct hci_h4p_info *info,
+				      struct sk_buff *skb)
+{
+	if (unlikely(!test_bit(HCI_RUNNING, &info->hdev->flags))) {
+		switch (bt_cb(skb)->pkt_type) {
+		case H4_NEG_PKT:
+			hci_h4p_negotiation_packet(info, skb);
+			info->rx_state = WAIT_FOR_PKT_TYPE;
+			return;
+		case H4_ALIVE_PKT:
+			hci_h4p_alive_packet(info, skb);
+			info->rx_state = WAIT_FOR_PKT_TYPE;
+			return;
+		}
+
+		if (!test_bit(HCI_UP, &info->hdev->flags)) {
+			BT_DBG("fw_event");
+			hci_h4p_parse_fw_event(info, skb);
+			return;
+		}
+	}
+
+	hci_recv_frame(info->hdev, skb);
+	BT_DBG("Frame sent to upper layer");
+}
+
+static inline void hci_h4p_handle_byte(struct hci_h4p_info *info, u8 byte)
+{
+	switch (info->rx_state) {
+	case WAIT_FOR_PKT_TYPE:
+		bt_cb(info->rx_skb)->pkt_type = byte;
+		info->rx_count = hci_h4p_get_hdr_len(info, byte);
+		if (info->rx_count < 0) {
+			info->hdev->stat.err_rx++;
+			kfree_skb(info->rx_skb);
+			info->rx_skb = NULL;
+		} else {
+			info->rx_state = WAIT_FOR_HEADER;
+		}
+		break;
+	case WAIT_FOR_HEADER:
+		info->rx_count--;
+		*skb_put(info->rx_skb, 1) = byte;
+		if (info->rx_count != 0)
+			break;
+		info->rx_count = hci_h4p_get_data_len(info, info->rx_skb);
+		if (info->rx_count > skb_tailroom(info->rx_skb)) {
+			dev_err(info->dev, "frame too long\n");
+			info->garbage_bytes = info->rx_count
+				- skb_tailroom(info->rx_skb);
+			kfree_skb(info->rx_skb);
+			info->rx_skb = NULL;
+			break;
+		}
+		info->rx_state = WAIT_FOR_DATA;
+		break;
+	case WAIT_FOR_DATA:
+		info->rx_count--;
+		*skb_put(info->rx_skb, 1) = byte;
+		break;
+	default:
+		WARN_ON(1);
+		break;
+	}
+
+	if (info->rx_count == 0) {
+		/* H4+ devices should always send word aligned packets */
+		if (!(info->rx_skb->len % 2))
+			info->garbage_bytes++;
+		hci_h4p_recv_frame(info, info->rx_skb);
+		info->rx_skb = NULL;
+	}
+}
+
+static void hci_h4p_rx_tasklet(unsigned long data)
+{
+	u8 byte;
+	struct hci_h4p_info *info = (struct hci_h4p_info *)data;
+
+	BT_DBG("tasklet woke up");
+	BT_DBG("rx_tasklet woke up");
+
+	while (hci_h4p_inb(info, UART_LSR) & UART_LSR_DR) {
+		byte = hci_h4p_inb(info, UART_RX);
+		if (info->garbage_bytes) {
+			info->garbage_bytes--;
+			continue;
+		}
+		if (info->rx_skb == NULL) {
+			info->rx_skb = bt_skb_alloc(HCI_MAX_FRAME_SIZE,
+						    GFP_ATOMIC | GFP_DMA);
+			if (!info->rx_skb) {
+				dev_err(info->dev,
+					"No memory for new packet\n");
+				goto finish_rx;
+			}
+			info->rx_state = WAIT_FOR_PKT_TYPE;
+			info->rx_skb->dev = (void *)info->hdev;
+		}
+		info->hdev->stat.byte_rx++;
+		hci_h4p_handle_byte(info, byte);
+	}
+
+	if (!info->rx_enabled) {
+		if (hci_h4p_inb(info, UART_LSR) & UART_LSR_TEMT &&
+						  info->autorts) {
+			__hci_h4p_set_auto_ctsrts(info, 0 , UART_EFR_RTS);
+			info->autorts = 0;
+		}
+		/* Flush posted write to avoid spurious interrupts */
+		hci_h4p_inb(info, UART_OMAP_SCR);
+		hci_h4p_set_clk(info, &info->rx_clocks_en, 0);
+	}
+
+finish_rx:
+	BT_DBG("rx_ended");
+}
+
+static void hci_h4p_tx_tasklet(unsigned long data)
+{
+	unsigned int sent = 0;
+	struct sk_buff *skb;
+	struct hci_h4p_info *info = (struct hci_h4p_info *)data;
+
+	BT_DBG("tasklet woke up");
+	BT_DBG("tx_tasklet woke up");
+
+	if (info->autorts != info->rx_enabled) {
+		if (hci_h4p_inb(info, UART_LSR) & UART_LSR_TEMT) {
+			if (info->autorts && !info->rx_enabled) {
+				__hci_h4p_set_auto_ctsrts(info, 0,
+							  UART_EFR_RTS);
+				info->autorts = 0;
+			}
+			if (!info->autorts && info->rx_enabled) {
+				__hci_h4p_set_auto_ctsrts(info, 1,
+							  UART_EFR_RTS);
+				info->autorts = 1;
+			}
+		} else {
+			hci_h4p_outb(info, UART_OMAP_SCR,
+				     hci_h4p_inb(info, UART_OMAP_SCR) |
+				     UART_OMAP_SCR_EMPTY_THR);
+			goto finish_tx;
+		}
+	}
+
+	skb = skb_dequeue(&info->txq);
+	if (!skb) {
+		/* No data in buffer */
+		BT_DBG("skb ready");
+		if (hci_h4p_inb(info, UART_LSR) & UART_LSR_TEMT) {
+			hci_h4p_outb(info, UART_IER,
+				     hci_h4p_inb(info, UART_IER) &
+				     ~UART_IER_THRI);
+			hci_h4p_inb(info, UART_OMAP_SCR);
+			hci_h4p_disable_tx(info);
+			return;
+		}
+		hci_h4p_outb(info, UART_OMAP_SCR,
+			     hci_h4p_inb(info, UART_OMAP_SCR) |
+			     UART_OMAP_SCR_EMPTY_THR);
+		goto finish_tx;
+	}
+
+	/* Copy data to tx fifo */
+	while (!(hci_h4p_inb(info, UART_OMAP_SSR) & UART_OMAP_SSR_TXFULL) &&
+	       (sent < skb->len)) {
+		hci_h4p_outb(info, UART_TX, skb->data[sent]);
+		sent++;
+	}
+
+	info->hdev->stat.byte_tx += sent;
+	if (skb->len == sent) {
+		kfree_skb(skb);
+	} else {
+		skb_pull(skb, sent);
+		skb_queue_head(&info->txq, skb);
+	}
+
+	hci_h4p_outb(info, UART_OMAP_SCR, hci_h4p_inb(info, UART_OMAP_SCR) &
+						     ~UART_OMAP_SCR_EMPTY_THR);
+	hci_h4p_outb(info, UART_IER, hci_h4p_inb(info, UART_IER) |
+						 UART_IER_THRI);
+
+finish_tx:
+	/* Flush posted write to avoid spurious interrupts */
+	hci_h4p_inb(info, UART_OMAP_SCR);
+
+}
+
+static irqreturn_t hci_h4p_interrupt(int irq, void *data)
+{
+	struct hci_h4p_info *info = (struct hci_h4p_info *)data;
+	u8 iir, msr;
+	int ret;
+
+	ret = IRQ_NONE;
+
+	iir = hci_h4p_inb(info, UART_IIR);
+	if (iir & UART_IIR_NO_INT)
+		return IRQ_HANDLED;
+
+	BT_DBG("In interrupt handler iir 0x%.2x", iir);
+
+	iir &= UART_IIR_ID;
+
+	if (iir == UART_IIR_MSI) {
+		msr = hci_h4p_inb(info, UART_MSR);
+		ret = IRQ_HANDLED;
+	}
+	if (iir == UART_IIR_RLSI) {
+		hci_h4p_inb(info, UART_RX);
+		hci_h4p_inb(info, UART_LSR);
+		ret = IRQ_HANDLED;
+	}
+
+	if (iir == UART_IIR_RDI) {
+		hci_h4p_rx_tasklet((unsigned long)data);
+		ret = IRQ_HANDLED;
+	}
+
+	if (iir == UART_IIR_THRI) {
+		hci_h4p_tx_tasklet((unsigned long)data);
+		ret = IRQ_HANDLED;
+	}
+
+	return ret;
+}
+
+static irqreturn_t hci_h4p_wakeup_interrupt(int irq, void *dev_inst)
+{
+	struct hci_h4p_info *info = dev_inst;
+	int should_wakeup;
+	struct hci_dev *hdev;
+
+	if (!info->hdev)
+		return IRQ_HANDLED;
+
+	should_wakeup = gpio_get_value(info->host_wakeup_gpio);
+	hdev = info->hdev;
+
+	if (!test_bit(HCI_RUNNING, &hdev->flags)) {
+		if (should_wakeup == 1)
+			complete_all(&info->test_completion);
+
+		return IRQ_HANDLED;
+	}
+
+	BT_DBG("gpio interrupt %d", should_wakeup);
+
+	/* Check if wee have missed some interrupts */
+	if (info->rx_enabled == should_wakeup)
+		return IRQ_HANDLED;
+
+	if (should_wakeup)
+		hci_h4p_enable_rx(info);
+	else
+		hci_h4p_disable_rx(info);
+
+	return IRQ_HANDLED;
+}
+
+static inline void hci_h4p_set_pm_limits(struct hci_h4p_info *info, bool set)
+{
+	struct hci_h4p_platform_data *bt_plat_data = info->dev->platform_data;
+	const char *sset = set ? "set" : "clear";
+
+	if (unlikely(!bt_plat_data || !bt_plat_data->set_pm_limits))
+		return;
+
+	if (set != !!test_bit(H4P_ACTIVE_MODE, &info->pm_flags)) {
+		bt_plat_data->set_pm_limits(info->dev, set);
+		if (set)
+			set_bit(H4P_ACTIVE_MODE, &info->pm_flags);
+		else
+			clear_bit(H4P_ACTIVE_MODE, &info->pm_flags);
+		BT_DBG("Change pm constraints to: %s", sset);
+		return;
+	}
+
+	BT_DBG("pm constraints remains: %s", sset);
+}
+
+static int hci_h4p_reset(struct hci_h4p_info *info)
+{
+	int err;
+
+	err = hci_h4p_reset_uart(info);
+	if (err < 0) {
+		dev_err(info->dev, "Uart reset failed\n");
+		return err;
+	}
+	hci_h4p_init_uart(info);
+	hci_h4p_set_rts(info, 0);
+
+	gpio_set_value(info->reset_gpio, 0);
+	gpio_set_value(info->bt_wakeup_gpio, 1);
+	msleep(10);
+
+	if (gpio_get_value(info->host_wakeup_gpio) == 1) {
+		dev_err(info->dev, "host_wakeup_gpio not low\n");
+		return -EPROTO;
+	}
+
+	init_completion(&info->test_completion);
+	gpio_set_value(info->reset_gpio, 1);
+
+	if (!wait_for_completion_interruptible_timeout(&info->test_completion,
+						       msecs_to_jiffies(100))) {
+		dev_err(info->dev, "wakeup test timed out\n");
+		complete_all(&info->test_completion);
+		return -EPROTO;
+	}
+
+	err = hci_h4p_wait_for_cts(info, 1, 100);
+	if (err < 0) {
+		dev_err(info->dev, "No cts from bt chip\n");
+		return err;
+	}
+
+	hci_h4p_set_rts(info, 1);
+
+	return 0;
+}
+
+/* hci callback functions */
+static int hci_h4p_hci_flush(struct hci_dev *hdev)
+{
+	struct hci_h4p_info *info = hci_get_drvdata(hdev);
+	skb_queue_purge(&info->txq);
+
+	return 0;
+}
+
+static int hci_h4p_bt_wakeup_test(struct hci_h4p_info *info)
+{
+	/*
+	 * Test Sequence:
+	 * Host de-asserts the BT_WAKE_UP line.
+	 * Host polls the UART_CTS line, waiting for it to be de-asserted.
+	 * Host asserts the BT_WAKE_UP line.
+	 * Host polls the UART_CTS line, waiting for it to be asserted.
+	 * Host de-asserts the BT_WAKE_UP line (allow the Bluetooth device to
+	 * sleep).
+	 * Host polls the UART_CTS line, waiting for it to be de-asserted.
+	 */
+	int err;
+	int ret = -ECOMM;
+
+	if (!info)
+		return -EINVAL;
+
+	/* Disable wakeup interrupts */
+	disable_irq(gpio_to_irq(info->host_wakeup_gpio));
+
+	gpio_set_value(info->bt_wakeup_gpio, 0);
+	err = hci_h4p_wait_for_cts(info, 0, 100);
+	if (err) {
+		dev_warn(info->dev, "bt_wakeup_test: fail: "
+			 "CTS low timed out: %d\n", err);
+		goto out;
+	}
+
+	gpio_set_value(info->bt_wakeup_gpio, 1);
+	err = hci_h4p_wait_for_cts(info, 1, 100);
+	if (err) {
+		dev_warn(info->dev, "bt_wakeup_test: fail: "
+			 "CTS high timed out: %d\n", err);
+		goto out;
+	}
+
+	gpio_set_value(info->bt_wakeup_gpio, 0);
+	err = hci_h4p_wait_for_cts(info, 0, 100);
+	if (err) {
+		dev_warn(info->dev, "bt_wakeup_test: fail: "
+			 "CTS re-low timed out: %d\n", err);
+		goto out;
+	}
+
+	ret = 0;
+
+out:
+
+	/* Re-enable wakeup interrupts */
+	enable_irq(gpio_to_irq(info->host_wakeup_gpio));
+
+	return ret;
+}
+
+static int hci_h4p_hci_open(struct hci_dev *hdev)
+{
+	struct hci_h4p_info *info;
+	int err, retries = 0;
+	struct sk_buff_head fw_queue;
+	unsigned long flags;
+
+	info = hci_get_drvdata(hdev);
+
+	if (test_bit(HCI_RUNNING, &hdev->flags))
+		return 0;
+
+	/* TI1271 has HW bug and boot up might fail. Retry up to three times */
+again:
+
+	info->rx_enabled = 1;
+	info->rx_state = WAIT_FOR_PKT_TYPE;
+	info->rx_count = 0;
+	info->garbage_bytes = 0;
+	info->rx_skb = NULL;
+	info->pm_enabled = 0;
+	init_completion(&info->fw_completion);
+	hci_h4p_set_clk(info, &info->tx_clocks_en, 1);
+	hci_h4p_set_clk(info, &info->rx_clocks_en, 1);
+	skb_queue_head_init(&fw_queue);
+
+	err = hci_h4p_reset(info);
+	if (err < 0)
+		goto err_clean;
+
+	hci_h4p_set_auto_ctsrts(info, 1, UART_EFR_CTS | UART_EFR_RTS);
+	info->autorts = 1;
+
+	err = hci_h4p_send_negotiation(info);
+
+	err = hci_h4p_read_fw(info, &fw_queue);
+	if (err < 0) {
+		dev_err(info->dev, "Cannot read firmware\n");
+		goto err_clean;
+	}
+
+	err = hci_h4p_send_fw(info, &fw_queue);
+	if (err < 0) {
+		dev_err(info->dev, "Sending firmware failed.\n");
+		goto err_clean;
+	}
+
+	info->pm_enabled = 1;
+
+	err = hci_h4p_bt_wakeup_test(info);
+	if (err < 0) {
+		dev_err(info->dev, "BT wakeup test failed.\n");
+		goto err_clean;
+	}
+
+	spin_lock_irqsave(&info->lock, flags);
+	info->rx_enabled = gpio_get_value(info->host_wakeup_gpio);
+	hci_h4p_set_clk(info, &info->rx_clocks_en, info->rx_enabled);
+	spin_unlock_irqrestore(&info->lock, flags);
+
+	hci_h4p_set_clk(info, &info->tx_clocks_en, 0);
+
+	kfree_skb(info->alive_cmd_skb);
+	info->alive_cmd_skb = NULL;
+	set_bit(HCI_RUNNING, &hdev->flags);
+
+	BT_DBG("hci up and running");
+	return 0;
+
+err_clean:
+	hci_h4p_hci_flush(hdev);
+	hci_h4p_reset_uart(info);
+	del_timer_sync(&info->lazy_release);
+	hci_h4p_set_clk(info, &info->tx_clocks_en, 0);
+	hci_h4p_set_clk(info, &info->rx_clocks_en, 0);
+	gpio_set_value(info->reset_gpio, 0);
+	gpio_set_value(info->bt_wakeup_gpio, 0);
+	skb_queue_purge(&fw_queue);
+	kfree_skb(info->alive_cmd_skb);
+	info->alive_cmd_skb = NULL;
+	kfree_skb(info->rx_skb);
+	info->rx_skb = NULL;
+
+	if (retries++ < 3) {
+		dev_err(info->dev, "FW loading try %d fail. Retry.\n", retries);
+		goto again;
+	}
+
+	return err;
+}
+
+static int hci_h4p_hci_close(struct hci_dev *hdev)
+{
+	struct hci_h4p_info *info = hci_get_drvdata(hdev);
+
+	if (!test_and_clear_bit(HCI_RUNNING, &hdev->flags))
+		return 0;
+
+	hci_h4p_hci_flush(hdev);
+	hci_h4p_set_clk(info, &info->tx_clocks_en, 1);
+	hci_h4p_set_clk(info, &info->rx_clocks_en, 1);
+	hci_h4p_reset_uart(info);
+	del_timer_sync(&info->lazy_release);
+	hci_h4p_set_clk(info, &info->tx_clocks_en, 0);
+	hci_h4p_set_clk(info, &info->rx_clocks_en, 0);
+	gpio_set_value(info->reset_gpio, 0);
+	gpio_set_value(info->bt_wakeup_gpio, 0);
+	kfree_skb(info->rx_skb);
+
+	return 0;
+}
+
+static int hci_h4p_hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_h4p_info *info;
+	int err = 0;
+
+	BT_DBG("dev %p, skb %p", hdev, skb);
+
+	info = hci_get_drvdata(hdev);
+
+	if (!test_bit(HCI_RUNNING, &hdev->flags)) {
+		dev_warn(info->dev, "Frame for non-running device\n");
+		return -EIO;
+	}
+
+	switch (bt_cb(skb)->pkt_type) {
+	case HCI_COMMAND_PKT:
+		hdev->stat.cmd_tx++;
+		break;
+	case HCI_ACLDATA_PKT:
+		hdev->stat.acl_tx++;
+		break;
+	case HCI_SCODATA_PKT:
+		hdev->stat.sco_tx++;
+		break;
+	}
+
+	/* Push frame type to skb */
+	*skb_push(skb, 1) = (bt_cb(skb)->pkt_type);
+	/* We should allways send word aligned data to h4+ devices */
+	if (skb->len % 2) {
+		err = skb_pad(skb, 1);
+		if (!err)
+			*skb_put(skb, 1) = 0x00;
+	}
+	if (err)
+		return err;
+
+	skb_queue_tail(&info->txq, skb);
+	hci_h4p_enable_tx(info);
+
+	return 0;
+}
+
+static ssize_t hci_h4p_store_bdaddr(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t count)
+{
+	struct hci_h4p_info *info = dev_get_drvdata(dev);
+	unsigned int bdaddr[6];
+	int ret, i;
+
+	ret = sscanf(buf, "%2x:%2x:%2x:%2x:%2x:%2x\n",
+			&bdaddr[0], &bdaddr[1], &bdaddr[2],
+			&bdaddr[3], &bdaddr[4], &bdaddr[5]);
+
+	if (ret != 6)
+		return -EINVAL;
+
+	for (i = 0; i < 6; i++) {
+		if (bdaddr[i] > 0xff)
+			return -EINVAL;
+		info->bd_addr[i] = bdaddr[i] & 0xff;
+	}
+
+	return count;
+}
+
+static ssize_t hci_h4p_show_bdaddr(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct hci_h4p_info *info = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%pMR\n", info->bd_addr);
+}
+
+static DEVICE_ATTR(bdaddr, S_IRUGO | S_IWUSR, hci_h4p_show_bdaddr,
+		   hci_h4p_store_bdaddr);
+
+static int hci_h4p_sysfs_create_files(struct device *dev)
+{
+	return device_create_file(dev, &dev_attr_bdaddr);
+}
+
+static void hci_h4p_sysfs_remove_files(struct device *dev)
+{
+	device_remove_file(dev, &dev_attr_bdaddr);
+}
+
+static int hci_h4p_register_hdev(struct hci_h4p_info *info)
+{
+	struct hci_dev *hdev;
+
+	/* Initialize and register HCI device */
+
+	hdev = hci_alloc_dev();
+	if (!hdev) {
+		dev_err(info->dev, "Can't allocate memory for device\n");
+		return -ENOMEM;
+	}
+	info->hdev = hdev;
+
+	hdev->bus = HCI_UART;
+	hci_set_drvdata(hdev, info);
+
+	hdev->open = hci_h4p_hci_open;
+	hdev->close = hci_h4p_hci_close;
+	hdev->flush = hci_h4p_hci_flush;
+	hdev->send = hci_h4p_hci_send_frame;
+	set_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks);
+
+	SET_HCIDEV_DEV(hdev, info->dev);
+
+	if (hci_h4p_sysfs_create_files(info->dev) < 0) {
+		dev_err(info->dev, "failed to create sysfs files\n");
+		goto free;
+	}
+
+	if (hci_register_dev(hdev) >= 0)
+		return 0;
+
+	dev_err(info->dev, "hci_register failed %s.\n", hdev->name);
+	hci_h4p_sysfs_remove_files(info->dev);
+free:
+	hci_free_dev(info->hdev);
+	return -ENODEV;
+}
+
+static int hci_h4p_probe(struct platform_device *pdev)
+{
+	struct hci_h4p_platform_data *bt_plat_data;
+	struct hci_h4p_info *info;
+	int err;
+
+	dev_info(&pdev->dev, "Registering HCI H4P device\n");
+	info = devm_kzalloc(&pdev->dev, sizeof(struct hci_h4p_info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->dev = &pdev->dev;
+	info->tx_enabled = 1;
+	info->rx_enabled = 1;
+	spin_lock_init(&info->lock);
+	spin_lock_init(&info->clocks_lock);
+	skb_queue_head_init(&info->txq);
+
+	if (pdev->dev.platform_data == NULL) {
+		dev_err(&pdev->dev, "Could not get Bluetooth config data\n");
+		return -ENODATA;
+	}
+
+	bt_plat_data = pdev->dev.platform_data;
+	info->chip_type = bt_plat_data->chip_type;
+	info->bt_wakeup_gpio = bt_plat_data->bt_wakeup_gpio;
+	info->host_wakeup_gpio = bt_plat_data->host_wakeup_gpio;
+	info->reset_gpio = bt_plat_data->reset_gpio;
+	info->reset_gpio_shared = bt_plat_data->reset_gpio_shared;
+	info->bt_sysclk = bt_plat_data->bt_sysclk;
+
+	BT_DBG("RESET gpio: %d", info->reset_gpio);
+	BT_DBG("BTWU gpio: %d", info->bt_wakeup_gpio);
+	BT_DBG("HOSTWU gpio: %d", info->host_wakeup_gpio);
+	BT_DBG("sysclk: %d", info->bt_sysclk);
+
+	init_completion(&info->test_completion);
+	complete_all(&info->test_completion);
+
+	if (!info->reset_gpio_shared) {
+		err = devm_gpio_request_one(&pdev->dev, info->reset_gpio,
+					    GPIOF_OUT_INIT_LOW, "bt_reset");
+		if (err < 0) {
+			dev_err(&pdev->dev, "Cannot get GPIO line %d\n",
+				info->reset_gpio);
+			return err;
+		}
+	}
+
+	err = devm_gpio_request_one(&pdev->dev, info->bt_wakeup_gpio,
+				    GPIOF_OUT_INIT_LOW, "bt_wakeup");
+
+	if (err < 0) {
+		dev_err(info->dev, "Cannot get GPIO line 0x%d",
+			info->bt_wakeup_gpio);
+		return err;
+	}
+
+	err = devm_gpio_request_one(&pdev->dev, info->host_wakeup_gpio,
+				    GPIOF_DIR_IN, "host_wakeup");
+	if (err < 0) {
+		dev_err(info->dev, "Cannot get GPIO line %d",
+		       info->host_wakeup_gpio);
+		return err;
+	}
+
+	info->irq = bt_plat_data->uart_irq;
+	info->uart_base = devm_ioremap(&pdev->dev, bt_plat_data->uart_base, SZ_2K);
+	info->uart_iclk = devm_clk_get(&pdev->dev, bt_plat_data->uart_iclk);
+	info->uart_fclk = devm_clk_get(&pdev->dev, bt_plat_data->uart_fclk);
+
+	err = devm_request_irq(&pdev->dev, info->irq, hci_h4p_interrupt, IRQF_DISABLED,
+			       "hci_h4p", info);
+	if (err < 0) {
+		dev_err(info->dev, "hci_h4p: unable to get IRQ %d\n", info->irq);
+		return err;
+	}
+
+	err = devm_request_irq(&pdev->dev, gpio_to_irq(info->host_wakeup_gpio),
+			  hci_h4p_wakeup_interrupt,  IRQF_TRIGGER_FALLING |
+			  IRQF_TRIGGER_RISING | IRQF_DISABLED,
+			  "hci_h4p_wkup", info);
+	if (err < 0) {
+		dev_err(info->dev, "hci_h4p: unable to get wakeup IRQ %d\n",
+			  gpio_to_irq(info->host_wakeup_gpio));
+		return err;
+	}
+
+	err = irq_set_irq_wake(gpio_to_irq(info->host_wakeup_gpio), 1);
+	if (err < 0) {
+		dev_err(info->dev, "hci_h4p: unable to set wakeup for IRQ %d\n",
+				gpio_to_irq(info->host_wakeup_gpio));
+		return err;
+	}
+
+	init_timer_deferrable(&info->lazy_release);
+	info->lazy_release.function = hci_h4p_lazy_clock_release;
+	info->lazy_release.data = (unsigned long)info;
+	hci_h4p_set_clk(info, &info->tx_clocks_en, 1);
+	err = hci_h4p_reset_uart(info);
+	if (err < 0)
+		return err;
+	gpio_set_value(info->reset_gpio, 0);
+	hci_h4p_set_clk(info, &info->tx_clocks_en, 0);
+
+	platform_set_drvdata(pdev, info);
+
+	if (hci_h4p_register_hdev(info) < 0) {
+		dev_err(info->dev, "failed to register hci_h4p hci device\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int hci_h4p_remove(struct platform_device *pdev)
+{
+	struct hci_h4p_info *info;
+
+	info = platform_get_drvdata(pdev);
+
+	hci_h4p_sysfs_remove_files(info->dev);
+	hci_h4p_hci_close(info->hdev);
+	hci_unregister_dev(info->hdev);
+	hci_free_dev(info->hdev);
+
+	return 0;
+}
+
+static struct platform_driver hci_h4p_driver = {
+	.probe		= hci_h4p_probe,
+	.remove		= hci_h4p_remove,
+	.driver		= {
+		.name	= "hci_h4p",
+	},
+};
+
+module_platform_driver(hci_h4p_driver);
+
+MODULE_ALIAS("platform:hci_h4p");
+MODULE_DESCRIPTION("Bluetooth h4 driver with nokia extensions");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Ville Tervo");
+MODULE_FIRMWARE(FW_NAME_TI1271_PRELE);
+MODULE_FIRMWARE(FW_NAME_TI1271_LE);
+MODULE_FIRMWARE(FW_NAME_TI1271);
+MODULE_FIRMWARE(FW_NAME_BCM2048);
+MODULE_FIRMWARE(FW_NAME_CSR);
diff --git a/drivers/staging/nokia_h4p/nokia_fw-bcm.c b/drivers/staging/nokia_h4p/nokia_fw-bcm.c
new file mode 100644
index 000000000000..e8912bfc0a91
--- /dev/null
+++ b/drivers/staging/nokia_h4p/nokia_fw-bcm.c
@@ -0,0 +1,147 @@
+/*
+ * This file is part of Nokia H4P bluetooth driver
+ *
+ * Copyright (C) 2005-2008 Nokia Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
+ * 02110-1301 USA
+ *
+ */
+
+#include <linux/skbuff.h>
+#include <linux/delay.h>
+#include <linux/serial_reg.h>
+
+#include "hci_h4p.h"
+
+static int hci_h4p_bcm_set_bdaddr(struct hci_h4p_info *info, struct sk_buff *skb)
+{
+	int i;
+	static const u8 nokia_oui[3] = {0x00, 0x1f, 0xdf};
+	int not_valid;
+
+	not_valid = 1;
+	for (i = 0; i < 6; i++) {
+		if (info->bd_addr[i] != 0x00) {
+			not_valid = 0;
+			break;
+		}
+	}
+
+	if (not_valid) {
+		dev_info(info->dev, "Valid bluetooth address not found, setting some random\n");
+		/* When address is not valid, use some random but Nokia MAC */
+		memcpy(info->bd_addr, nokia_oui, 3);
+		get_random_bytes(info->bd_addr + 3, 3);
+	}
+
+	for (i = 0; i < 6; i++)
+		skb->data[9 - i] = info->bd_addr[i];
+
+	return 0;
+}
+
+void hci_h4p_bcm_parse_fw_event(struct hci_h4p_info *info, struct sk_buff *skb)
+{
+	struct sk_buff *fw_skb;
+	int err;
+	unsigned long flags;
+
+	if (skb->data[5] != 0x00) {
+		dev_err(info->dev, "Firmware sending command failed 0x%.2x\n",
+			skb->data[5]);
+		info->fw_error = -EPROTO;
+	}
+
+	kfree_skb(skb);
+
+	fw_skb = skb_dequeue(info->fw_q);
+	if (fw_skb == NULL || info->fw_error) {
+		complete(&info->fw_completion);
+		return;
+	}
+
+	if (fw_skb->data[1] == 0x01 && fw_skb->data[2] == 0xfc && fw_skb->len >= 10) {
+		BT_DBG("Setting bluetooth address");
+		err = hci_h4p_bcm_set_bdaddr(info, fw_skb);
+		if (err < 0) {
+			kfree_skb(fw_skb);
+			info->fw_error = err;
+			complete(&info->fw_completion);
+			return;
+		}
+	}
+
+	skb_queue_tail(&info->txq, fw_skb);
+	spin_lock_irqsave(&info->lock, flags);
+	hci_h4p_outb(info, UART_IER, hci_h4p_inb(info, UART_IER) |
+			UART_IER_THRI);
+	spin_unlock_irqrestore(&info->lock, flags);
+}
+
+
+int hci_h4p_bcm_send_fw(struct hci_h4p_info *info,
+			struct sk_buff_head *fw_queue)
+{
+	struct sk_buff *skb;
+	unsigned long flags, time;
+
+	info->fw_error = 0;
+
+	BT_DBG("Sending firmware");
+
+	time = jiffies;
+
+	info->fw_q = fw_queue;
+	skb = skb_dequeue(fw_queue);
+	if (!skb)
+		return -ENODATA;
+
+	BT_DBG("Sending commands");
+
+	/*
+	 * Disable smart-idle as UART TX interrupts
+	 * are not wake-up capable
+	 */
+	hci_h4p_smart_idle(info, 0);
+
+	/* Check if this is bd_address packet */
+	init_completion(&info->fw_completion);
+	skb_queue_tail(&info->txq, skb);
+	spin_lock_irqsave(&info->lock, flags);
+	hci_h4p_outb(info, UART_IER, hci_h4p_inb(info, UART_IER) |
+			UART_IER_THRI);
+	spin_unlock_irqrestore(&info->lock, flags);
+
+	if (!wait_for_completion_timeout(&info->fw_completion,
+				msecs_to_jiffies(2000))) {
+		dev_err(info->dev, "No reply to fw command\n");
+		return -ETIMEDOUT;
+	}
+
+	if (info->fw_error) {
+		dev_err(info->dev, "FW error\n");
+		return -EPROTO;
+	}
+
+	BT_DBG("Firmware sent in %d msecs",
+		   jiffies_to_msecs(jiffies-time));
+
+	hci_h4p_set_auto_ctsrts(info, 0, UART_EFR_RTS);
+	hci_h4p_set_rts(info, 0);
+	hci_h4p_change_speed(info, BC4_MAX_BAUD_RATE);
+	hci_h4p_set_auto_ctsrts(info, 1, UART_EFR_RTS);
+
+	return 0;
+}
diff --git a/drivers/staging/nokia_h4p/nokia_fw-csr.c b/drivers/staging/nokia_h4p/nokia_fw-csr.c
new file mode 100644
index 000000000000..e39c4a31a879
--- /dev/null
+++ b/drivers/staging/nokia_h4p/nokia_fw-csr.c
@@ -0,0 +1,150 @@
+/*
+ * This file is part of Nokia H4P bluetooth driver
+ *
+ * Copyright (C) 2005-2008 Nokia Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
+ * 02110-1301 USA
+ *
+ */
+
+#include <linux/skbuff.h>
+#include <linux/delay.h>
+#include <linux/serial_reg.h>
+
+#include "hci_h4p.h"
+
+void hci_h4p_bc4_parse_fw_event(struct hci_h4p_info *info, struct sk_buff *skb)
+{
+	/* Check if this is fw packet */
+	if (skb->data[0] != 0xff) {
+		hci_recv_frame(info->hdev, skb);
+		return;
+	}
+
+	if (skb->data[11] || skb->data[12]) {
+		dev_err(info->dev, "Firmware sending command failed\n");
+		info->fw_error = -EPROTO;
+	}
+
+	kfree_skb(skb);
+	complete(&info->fw_completion);
+}
+
+int hci_h4p_bc4_send_fw(struct hci_h4p_info *info,
+			struct sk_buff_head *fw_queue)
+{
+	static const u8 nokia_oui[3] = {0x00, 0x19, 0x4F};
+	struct sk_buff *skb;
+	unsigned int offset;
+	int retries, count, i, not_valid;
+	unsigned long flags;
+
+	info->fw_error = 0;
+
+	BT_DBG("Sending firmware");
+	skb = skb_dequeue(fw_queue);
+
+	if (!skb)
+		return -ENOMSG;
+
+	/* Check if this is bd_address packet */
+	if (skb->data[15] == 0x01 && skb->data[16] == 0x00) {
+		offset = 21;
+		skb->data[offset + 1] = 0x00;
+		skb->data[offset + 5] = 0x00;
+
+		not_valid = 1;
+		for (i = 0; i < 6; i++) {
+			if (info->bd_addr[i] != 0x00) {
+				not_valid = 0;
+				break;
+			}
+		}
+
+		if (not_valid) {
+			dev_info(info->dev, "Valid bluetooth address not found,"
+					" setting some random\n");
+			/* When address is not valid, use some random */
+			memcpy(info->bd_addr, nokia_oui, 3);
+			get_random_bytes(info->bd_addr + 3, 3);
+		}
+
+		skb->data[offset + 7] = info->bd_addr[0];
+		skb->data[offset + 6] = info->bd_addr[1];
+		skb->data[offset + 4] = info->bd_addr[2];
+		skb->data[offset + 0] = info->bd_addr[3];
+		skb->data[offset + 3] = info->bd_addr[4];
+		skb->data[offset + 2] = info->bd_addr[5];
+	}
+
+	for (count = 1; ; count++) {
+		BT_DBG("Sending firmware command %d", count);
+		init_completion(&info->fw_completion);
+		skb_queue_tail(&info->txq, skb);
+		spin_lock_irqsave(&info->lock, flags);
+		hci_h4p_outb(info, UART_IER, hci_h4p_inb(info, UART_IER) |
+							 UART_IER_THRI);
+		spin_unlock_irqrestore(&info->lock, flags);
+
+		skb = skb_dequeue(fw_queue);
+		if (!skb)
+			break;
+
+		if (!wait_for_completion_timeout(&info->fw_completion,
+						 msecs_to_jiffies(1000))) {
+			dev_err(info->dev, "No reply to fw command\n");
+			return -ETIMEDOUT;
+		}
+
+		if (info->fw_error) {
+			dev_err(info->dev, "FW error\n");
+			return -EPROTO;
+		}
+	};
+
+	/* Wait for chip warm reset */
+	retries = 100;
+	while ((!skb_queue_empty(&info->txq) ||
+	       !(hci_h4p_inb(info, UART_LSR) & UART_LSR_TEMT)) &&
+	       retries--) {
+		msleep(10);
+	}
+	if (!retries) {
+		dev_err(info->dev, "Transmitter not empty\n");
+		return -ETIMEDOUT;
+	}
+
+	hci_h4p_change_speed(info, BC4_MAX_BAUD_RATE);
+
+	if (hci_h4p_wait_for_cts(info, 1, 100)) {
+		dev_err(info->dev, "cts didn't deassert after final speed\n");
+		return -ETIMEDOUT;
+	}
+
+	retries = 100;
+	do {
+		init_completion(&info->init_completion);
+		hci_h4p_send_alive_packet(info);
+		retries--;
+	} while (!wait_for_completion_timeout(&info->init_completion, 100) &&
+		 retries > 0);
+
+	if (!retries) {
+		dev_err(info->dev, "No alive reply after speed change\n");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
diff --git a/drivers/staging/nokia_h4p/nokia_fw-ti1273.c b/drivers/staging/nokia_h4p/nokia_fw-ti1273.c
new file mode 100644
index 000000000000..f5500f71c839
--- /dev/null
+++ b/drivers/staging/nokia_h4p/nokia_fw-ti1273.c
@@ -0,0 +1,110 @@
+/*
+ * This file is part of Nokia H4P bluetooth driver
+ *
+ * Copyright (C) 2009 Nokia Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
+ * 02110-1301 USA
+ *
+ */
+
+#include <linux/skbuff.h>
+#include <linux/delay.h>
+#include <linux/serial_reg.h>
+
+#include "hci_h4p.h"
+
+static struct sk_buff_head *fw_q;
+
+void hci_h4p_ti1273_parse_fw_event(struct hci_h4p_info *info,
+			struct sk_buff *skb)
+{
+	struct sk_buff *fw_skb;
+	unsigned long flags;
+
+	if (skb->data[5] != 0x00) {
+		dev_err(info->dev, "Firmware sending command failed 0x%.2x\n",
+			skb->data[5]);
+		info->fw_error = -EPROTO;
+	}
+
+	kfree_skb(skb);
+
+	fw_skb = skb_dequeue(fw_q);
+	if (fw_skb == NULL || info->fw_error) {
+		complete(&info->fw_completion);
+		return;
+	}
+
+	skb_queue_tail(&info->txq, fw_skb);
+	spin_lock_irqsave(&info->lock, flags);
+	hci_h4p_outb(info, UART_IER, hci_h4p_inb(info, UART_IER) |
+			UART_IER_THRI);
+	spin_unlock_irqrestore(&info->lock, flags);
+}
+
+
+int hci_h4p_ti1273_send_fw(struct hci_h4p_info *info,
+			struct sk_buff_head *fw_queue)
+{
+	struct sk_buff *skb;
+	unsigned long flags, time;
+
+	info->fw_error = 0;
+
+	BT_DBG("Sending firmware");
+
+	time = jiffies;
+
+	fw_q = fw_queue;
+	skb = skb_dequeue(fw_queue);
+	if (!skb)
+		return -ENODATA;
+
+	BT_DBG("Sending commands");
+	/* Check if this is bd_address packet */
+	init_completion(&info->fw_completion);
+	hci_h4p_smart_idle(info, 0);
+	skb_queue_tail(&info->txq, skb);
+	spin_lock_irqsave(&info->lock, flags);
+	hci_h4p_outb(info, UART_IER, hci_h4p_inb(info, UART_IER) |
+			UART_IER_THRI);
+	spin_unlock_irqrestore(&info->lock, flags);
+
+	if (!wait_for_completion_timeout(&info->fw_completion,
+				msecs_to_jiffies(2000))) {
+		dev_err(info->dev, "No reply to fw command\n");
+		return -ETIMEDOUT;
+	}
+
+	if (info->fw_error) {
+		dev_err(info->dev, "FW error\n");
+		return -EPROTO;
+	}
+
+	BT_DBG("Firmware sent in %d msecs",
+		   jiffies_to_msecs(jiffies-time));
+
+	hci_h4p_set_auto_ctsrts(info, 0, UART_EFR_RTS);
+	hci_h4p_set_rts(info, 0);
+	hci_h4p_change_speed(info, BC4_MAX_BAUD_RATE);
+	if (hci_h4p_wait_for_cts(info, 1, 100)) {
+		dev_err(info->dev,
+			"cts didn't go down after final speed change\n");
+		return -ETIMEDOUT;
+	}
+	hci_h4p_set_auto_ctsrts(info, 1, UART_EFR_RTS);
+
+	return 0;
+}
diff --git a/drivers/staging/nokia_h4p/nokia_fw.c b/drivers/staging/nokia_h4p/nokia_fw.c
new file mode 100644
index 000000000000..cfea61cd59e9
--- /dev/null
+++ b/drivers/staging/nokia_h4p/nokia_fw.c
@@ -0,0 +1,195 @@
+/*
+ * This file is part of hci_h4p bluetooth driver
+ *
+ * Copyright (C) 2005, 2006 Nokia Corporation.
+ *
+ * Contact: Ville Tervo <ville.tervo@nokia.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
+ * 02110-1301 USA
+ *
+ */
+
+#include <linux/skbuff.h>
+#include <linux/firmware.h>
+#include <linux/clk.h>
+
+#include <net/bluetooth/bluetooth.h>
+
+#include "hci_h4p.h"
+
+static int fw_pos;
+
+/* Firmware handling */
+static int hci_h4p_open_firmware(struct hci_h4p_info *info,
+				 const struct firmware **fw_entry)
+{
+	int err;
+
+	fw_pos = 0;
+	BT_DBG("Opening firmware man_id 0x%.2x ver_id 0x%.2x",
+			info->man_id, info->ver_id);
+	switch (info->man_id) {
+	case H4P_ID_TI1271:
+		switch (info->ver_id) {
+		case 0xe1:
+			err = request_firmware(fw_entry, FW_NAME_TI1271_PRELE,
+						info->dev);
+			break;
+		case 0xd1:
+		case 0xf1:
+			err = request_firmware(fw_entry, FW_NAME_TI1271_LE,
+						info->dev);
+			break;
+		default:
+			err = request_firmware(fw_entry, FW_NAME_TI1271,
+						info->dev);
+		}
+		break;
+	case H4P_ID_CSR:
+		err = request_firmware(fw_entry, FW_NAME_CSR, info->dev);
+		break;
+	case H4P_ID_BCM2048:
+		err = request_firmware(fw_entry, FW_NAME_BCM2048, info->dev);
+		break;
+	default:
+		dev_err(info->dev, "Invalid chip type\n");
+		*fw_entry = NULL;
+		err = -EINVAL;
+	}
+
+	return err;
+}
+
+static void hci_h4p_close_firmware(const struct firmware *fw_entry)
+{
+	release_firmware(fw_entry);
+}
+
+/* Read fw. Return length of the command. If no more commands in
+ * fw 0 is returned. In error case return value is negative.
+ */
+static int hci_h4p_read_fw_cmd(struct hci_h4p_info *info, struct sk_buff **skb,
+			       const struct firmware *fw_entry, gfp_t how)
+{
+	unsigned int cmd_len;
+
+	if (fw_pos >= fw_entry->size)
+		return 0;
+
+	if (fw_pos + 2 > fw_entry->size) {
+		dev_err(info->dev, "Corrupted firmware image 1\n");
+		return -EMSGSIZE;
+	}
+
+	cmd_len = fw_entry->data[fw_pos++];
+	cmd_len += fw_entry->data[fw_pos++] << 8;
+	if (cmd_len == 0)
+		return 0;
+
+	if (fw_pos + cmd_len > fw_entry->size) {
+		dev_err(info->dev, "Corrupted firmware image 2\n");
+		return -EMSGSIZE;
+	}
+
+	*skb = bt_skb_alloc(cmd_len, how);
+	if (!*skb) {
+		dev_err(info->dev, "Cannot reserve memory for buffer\n");
+		return -ENOMEM;
+	}
+	memcpy(skb_put(*skb, cmd_len), &fw_entry->data[fw_pos], cmd_len);
+
+	fw_pos += cmd_len;
+
+	return (*skb)->len;
+}
+
+int hci_h4p_read_fw(struct hci_h4p_info *info, struct sk_buff_head *fw_queue)
+{
+	const struct firmware *fw_entry = NULL;
+	struct sk_buff *skb = NULL;
+	int err;
+
+	err = hci_h4p_open_firmware(info, &fw_entry);
+	if (err < 0 || !fw_entry)
+		goto err_clean;
+
+	while ((err = hci_h4p_read_fw_cmd(info, &skb, fw_entry, GFP_KERNEL))) {
+		if (err < 0 || !skb)
+			goto err_clean;
+
+		skb_queue_tail(fw_queue, skb);
+	}
+
+	/* Chip detection code does neg and alive stuff
+	 * discard two first skbs */
+	skb = skb_dequeue(fw_queue);
+	if (!skb) {
+		err = -EMSGSIZE;
+		goto err_clean;
+	}
+	kfree_skb(skb);
+	skb = skb_dequeue(fw_queue);
+	if (!skb) {
+		err = -EMSGSIZE;
+		goto err_clean;
+	}
+	kfree_skb(skb);
+
+err_clean:
+	hci_h4p_close_firmware(fw_entry);
+	return err;
+}
+
+int hci_h4p_send_fw(struct hci_h4p_info *info, struct sk_buff_head *fw_queue)
+{
+	int err;
+
+	switch (info->man_id) {
+	case H4P_ID_CSR:
+		err = hci_h4p_bc4_send_fw(info, fw_queue);
+		break;
+	case H4P_ID_TI1271:
+		err = hci_h4p_ti1273_send_fw(info, fw_queue);
+		break;
+	case H4P_ID_BCM2048:
+		err = hci_h4p_bcm_send_fw(info, fw_queue);
+		break;
+	default:
+		dev_err(info->dev, "Don't know how to send firmware\n");
+		err = -EINVAL;
+	}
+
+	return err;
+}
+
+void hci_h4p_parse_fw_event(struct hci_h4p_info *info, struct sk_buff *skb)
+{
+	switch (info->man_id) {
+	case H4P_ID_CSR:
+		hci_h4p_bc4_parse_fw_event(info, skb);
+		break;
+	case H4P_ID_TI1271:
+		hci_h4p_ti1273_parse_fw_event(info, skb);
+		break;
+	case H4P_ID_BCM2048:
+		hci_h4p_bcm_parse_fw_event(info, skb);
+		break;
+	default:
+		dev_err(info->dev, "Don't know how to parse fw event\n");
+		info->fw_error = -EINVAL;
+	}
+
+	return;
+}
diff --git a/drivers/staging/nokia_h4p/nokia_uart.c b/drivers/staging/nokia_h4p/nokia_uart.c
new file mode 100644
index 000000000000..0fb57de4b750
--- /dev/null
+++ b/drivers/staging/nokia_h4p/nokia_uart.c
@@ -0,0 +1,199 @@
+/*
+ * This file is part of Nokia H4P bluetooth driver
+ *
+ * Copyright (C) 2005, 2006 Nokia Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
+ * 02110-1301 USA
+ *
+ */
+
+#include <linux/serial_reg.h>
+#include <linux/delay.h>
+#include <linux/clk.h>
+
+#include <linux/io.h>
+
+#include "hci_h4p.h"
+
+inline void hci_h4p_outb(struct hci_h4p_info *info, unsigned int offset, u8 val)
+{
+	__raw_writeb(val, info->uart_base + (offset << 2));
+}
+
+inline u8 hci_h4p_inb(struct hci_h4p_info *info, unsigned int offset)
+{
+	return __raw_readb(info->uart_base + (offset << 2));
+}
+
+void hci_h4p_set_rts(struct hci_h4p_info *info, int active)
+{
+	u8 b;
+
+	b = hci_h4p_inb(info, UART_MCR);
+	if (active)
+		b |= UART_MCR_RTS;
+	else
+		b &= ~UART_MCR_RTS;
+	hci_h4p_outb(info, UART_MCR, b);
+}
+
+int hci_h4p_wait_for_cts(struct hci_h4p_info *info, int active,
+			 int timeout_ms)
+{
+	unsigned long timeout;
+	int state;
+
+	timeout = jiffies + msecs_to_jiffies(timeout_ms);
+	for (;;) {
+		state = hci_h4p_inb(info, UART_MSR) & UART_MSR_CTS;
+		if (active) {
+			if (state)
+				return 0;
+		} else {
+			if (!state)
+				return 0;
+		}
+		if (time_after(jiffies, timeout))
+			return -ETIMEDOUT;
+		msleep(1);
+	}
+}
+
+void __hci_h4p_set_auto_ctsrts(struct hci_h4p_info *info, int on, u8 which)
+{
+	u8 lcr, b;
+
+	lcr = hci_h4p_inb(info, UART_LCR);
+	hci_h4p_outb(info, UART_LCR, 0xbf);
+	b = hci_h4p_inb(info, UART_EFR);
+	if (on)
+		b |= which;
+	else
+		b &= ~which;
+	hci_h4p_outb(info, UART_EFR, b);
+	hci_h4p_outb(info, UART_LCR, lcr);
+}
+
+void hci_h4p_set_auto_ctsrts(struct hci_h4p_info *info, int on, u8 which)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&info->lock, flags);
+	__hci_h4p_set_auto_ctsrts(info, on, which);
+	spin_unlock_irqrestore(&info->lock, flags);
+}
+
+void hci_h4p_change_speed(struct hci_h4p_info *info, unsigned long speed)
+{
+	unsigned int divisor;
+	u8 lcr, mdr1;
+
+	BT_DBG("Setting speed %lu", speed);
+
+	if (speed >= 460800) {
+		divisor = UART_CLOCK / 13 / speed;
+		mdr1 = 3;
+	} else {
+		divisor = UART_CLOCK / 16 / speed;
+		mdr1 = 0;
+	}
+
+	/* Make sure UART mode is disabled */
+	hci_h4p_outb(info, UART_OMAP_MDR1, 7);
+
+	lcr = hci_h4p_inb(info, UART_LCR);
+	hci_h4p_outb(info, UART_LCR, UART_LCR_DLAB);     /* Set DLAB */
+	hci_h4p_outb(info, UART_DLL, divisor & 0xff);    /* Set speed */
+	hci_h4p_outb(info, UART_DLM, divisor >> 8);
+	hci_h4p_outb(info, UART_LCR, lcr);
+
+	/* Make sure UART mode is enabled */
+	hci_h4p_outb(info, UART_OMAP_MDR1, mdr1);
+}
+
+int hci_h4p_reset_uart(struct hci_h4p_info *info)
+{
+	int count = 0;
+
+	/* Reset the UART */
+	hci_h4p_outb(info, UART_OMAP_SYSC, UART_SYSC_OMAP_RESET);
+	while (!(hci_h4p_inb(info, UART_OMAP_SYSS) & UART_SYSS_RESETDONE)) {
+		if (count++ > 100) {
+			dev_err(info->dev, "hci_h4p: UART reset timeout\n");
+			return -ENODEV;
+		}
+		udelay(1);
+	}
+
+	return 0;
+}
+
+void hci_h4p_store_regs(struct hci_h4p_info *info)
+{
+	u16 lcr = 0;
+
+	lcr = hci_h4p_inb(info, UART_LCR);
+	hci_h4p_outb(info, UART_LCR, 0xBF);
+	info->dll = hci_h4p_inb(info, UART_DLL);
+	info->dlh = hci_h4p_inb(info, UART_DLM);
+	info->efr = hci_h4p_inb(info, UART_EFR);
+	hci_h4p_outb(info, UART_LCR, lcr);
+	info->mdr1 = hci_h4p_inb(info, UART_OMAP_MDR1);
+	info->ier = hci_h4p_inb(info, UART_IER);
+}
+
+void hci_h4p_restore_regs(struct hci_h4p_info *info)
+{
+	u16 lcr = 0;
+
+	hci_h4p_init_uart(info);
+
+	hci_h4p_outb(info, UART_OMAP_MDR1, 7);
+	lcr = hci_h4p_inb(info, UART_LCR);
+	hci_h4p_outb(info, UART_LCR, 0xBF);
+	hci_h4p_outb(info, UART_DLL, info->dll);    /* Set speed */
+	hci_h4p_outb(info, UART_DLM, info->dlh);
+	hci_h4p_outb(info, UART_EFR, info->efr);
+	hci_h4p_outb(info, UART_LCR, lcr);
+	hci_h4p_outb(info, UART_OMAP_MDR1, info->mdr1);
+	hci_h4p_outb(info, UART_IER, info->ier);
+}
+
+void hci_h4p_init_uart(struct hci_h4p_info *info)
+{
+	u8 mcr, efr;
+
+	/* Enable and setup FIFO */
+	hci_h4p_outb(info, UART_OMAP_MDR1, 0x00);
+
+	hci_h4p_outb(info, UART_LCR, 0xbf);
+	efr = hci_h4p_inb(info, UART_EFR);
+	hci_h4p_outb(info, UART_EFR, UART_EFR_ECB);
+	hci_h4p_outb(info, UART_LCR, UART_LCR_DLAB);
+	mcr = hci_h4p_inb(info, UART_MCR);
+	hci_h4p_outb(info, UART_MCR, UART_MCR_TCRTLR);
+	hci_h4p_outb(info, UART_FCR, UART_FCR_ENABLE_FIFO |
+			UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT |
+			(3 << 6) | (0 << 4));
+	hci_h4p_outb(info, UART_LCR, 0xbf);
+	hci_h4p_outb(info, UART_TI752_TLR, 0xed);
+	hci_h4p_outb(info, UART_TI752_TCR, 0xef);
+	hci_h4p_outb(info, UART_EFR, efr);
+	hci_h4p_outb(info, UART_LCR, UART_LCR_DLAB);
+	hci_h4p_outb(info, UART_MCR, 0x00);
+	hci_h4p_outb(info, UART_LCR, UART_LCR_WLEN8);
+	hci_h4p_outb(info, UART_IER, UART_IER_RDI);
+	hci_h4p_outb(info, UART_OMAP_SYSC, (1 << 0) | (1 << 2) | (2 << 3));
+}
diff --git a/include/linux/platform_data/bt-nokia-h4p.h b/include/linux/platform_data/bt-nokia-h4p.h
new file mode 100644
index 000000000000..30d169dfadf3
--- /dev/null
+++ b/include/linux/platform_data/bt-nokia-h4p.h
@@ -0,0 +1,38 @@
+/*
+ * This file is part of Nokia H4P bluetooth driver
+ *
+ * Copyright (C) 2010 Nokia Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
+ * 02110-1301 USA
+ *
+ */
+
+
+/**
+ * struct hci_h4p_platform data - hci_h4p Platform data structure
+ */
+struct hci_h4p_platform_data {
+	int chip_type;
+	int bt_sysclk;
+	unsigned int bt_wakeup_gpio;
+	unsigned int host_wakeup_gpio;
+	unsigned int reset_gpio;
+	int reset_gpio_shared;
+	unsigned int uart_irq;
+	phys_addr_t uart_base;
+	const char *uart_iclk;
+	const char *uart_fclk;
+	void (*set_pm_limits)(struct device *dev, bool set);
+};
-- 
cgit v1.2.3


From b7945b77cd03094458f3624bc82a27e0d36e75d0 Mon Sep 17 00:00:00 2001
From: Valentina Manea <valentina.manea.m@gmail.com>
Date: Thu, 23 Jan 2014 23:12:29 +0200
Subject: staging: usbip: convert usbip-host driver to usb_device_driver

This driver was previously an interface driver. Since USB/IP
exports a whole device, not just an interface, it would make
sense to be a device driver.

This patch also modifies the way userspace sees and uses a
shared device:

* the usbip_status file is no longer created for interface 0, but for
the whole device (such as
/sys/devices/pci0000:00/0000:00:01.2/usb1/1-1/usbip_status).
* per interface information, such as interface class or protocol, is
no longer sent/received; only device specific information is
transmitted.
* since the driver was moved one level below in the USB architecture,
there is no need to bind/unbind each interface, just the device as a
whole.

Signed-off-by: Valentina Manea <valentina.manea.m@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/usbip/stub.h                       |   2 +-
 drivers/staging/usbip/stub_dev.c                   | 150 ++++++++-------------
 drivers/staging/usbip/stub_main.c                  |   6 +-
 drivers/staging/usbip/stub_rx.c                    |   2 +-
 .../usbip/userspace/libsrc/usbip_host_driver.c     |  45 +++----
 drivers/staging/usbip/userspace/src/usbip_bind.c   | 142 ++++++++-----------
 drivers/staging/usbip/userspace/src/usbip_list.c   |  19 +--
 drivers/staging/usbip/userspace/src/usbip_unbind.c |  51 ++-----
 drivers/staging/usbip/userspace/src/usbipd.c       |  15 ---
 drivers/usb/core/generic.c                         |   1 +
 drivers/usb/core/message.c                         |   1 +
 include/linux/usb.h                                |   4 +
 12 files changed, 150 insertions(+), 288 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/staging/usbip/stub.h b/drivers/staging/usbip/stub.h
index a73e437ec215..82e539a4fcff 100644
--- a/drivers/staging/usbip/stub.h
+++ b/drivers/staging/usbip/stub.h
@@ -93,7 +93,7 @@ struct bus_id_priv {
 extern struct kmem_cache *stub_priv_cache;
 
 /* stub_dev.c */
-extern struct usb_driver stub_driver;
+extern struct usb_device_driver stub_driver;
 
 /* stub_main.c */
 struct bus_id_priv *get_busid_priv(const char *busid);
diff --git a/drivers/staging/usbip/stub_dev.c b/drivers/staging/usbip/stub_dev.c
index 76a1ff0e6275..b0bfd3430d47 100644
--- a/drivers/staging/usbip/stub_dev.c
+++ b/drivers/staging/usbip/stub_dev.c
@@ -279,21 +279,19 @@ static void stub_device_unusable(struct usbip_device *ud)
  *
  * Allocates and initializes a new stub_device struct.
  */
-static struct stub_device *stub_device_alloc(struct usb_device *udev,
-					     struct usb_interface *interface)
+static struct stub_device *stub_device_alloc(struct usb_device *udev)
 {
 	struct stub_device *sdev;
-	int busnum = interface_to_busnum(interface);
-	int devnum = interface_to_devnum(interface);
+	int busnum = udev->bus->busnum;
+	int devnum = udev->devnum;
 
-	dev_dbg(&interface->dev, "allocating stub device");
+	dev_dbg(&udev->dev, "allocating stub device");
 
 	/* yes, it's a new device */
 	sdev = kzalloc(sizeof(struct stub_device), GFP_KERNEL);
 	if (!sdev)
 		return NULL;
 
-	sdev->interface = usb_get_intf(interface);
 	sdev->udev = usb_get_dev(udev);
 
 	/*
@@ -322,7 +320,7 @@ static struct stub_device *stub_device_alloc(struct usb_device *udev,
 
 	usbip_start_eh(&sdev->ud);
 
-	dev_dbg(&interface->dev, "register new interface\n");
+	dev_dbg(&udev->dev, "register new device\n");
 
 	return sdev;
 }
@@ -332,32 +330,20 @@ static void stub_device_free(struct stub_device *sdev)
 	kfree(sdev);
 }
 
-/*
- * If a usb device has multiple active interfaces, this driver is bound to all
- * the active interfaces. However, usbip exports *a* usb device (i.e., not *an*
- * active interface). Currently, a userland program must ensure that it
- * looks at the usbip's sysfs entries of only the first active interface.
- *
- * TODO: use "struct usb_device_driver" to bind a usb device.
- * However, it seems it is not fully supported in mainline kernel yet
- * (2.6.19.2).
- */
-static int stub_probe(struct usb_interface *interface,
-		      const struct usb_device_id *id)
+static int stub_probe(struct usb_device *udev)
 {
-	struct usb_device *udev = interface_to_usbdev(interface);
 	struct stub_device *sdev = NULL;
-	const char *udev_busid = dev_name(interface->dev.parent);
-	int err = 0;
+	const char *udev_busid = dev_name(&udev->dev);
+	int err = 0, config;
 	struct bus_id_priv *busid_priv;
 
-	dev_dbg(&interface->dev, "Enter\n");
+	dev_dbg(&udev->dev, "Enter\n");
 
 	/* check we should claim or not by busid_table */
 	busid_priv = get_busid_priv(udev_busid);
 	if (!busid_priv || (busid_priv->status == STUB_BUSID_REMOV) ||
 	    (busid_priv->status == STUB_BUSID_OTHER)) {
-		dev_info(&interface->dev,
+		dev_info(&udev->dev,
 			"%s is not in match_busid table... skip!\n",
 			udev_busid);
 
@@ -383,60 +369,36 @@ static int stub_probe(struct usb_interface *interface,
 		return -ENODEV;
 	}
 
-	if (busid_priv->status == STUB_BUSID_ALLOC) {
-		sdev = busid_priv->sdev;
-		if (!sdev)
-			return -ENODEV;
-
-		busid_priv->interf_count++;
-		dev_info(&interface->dev,
-			"usbip-host: register new interface (bus %u dev %u ifn %u)\n",
-			udev->bus->busnum, udev->devnum,
-			interface->cur_altsetting->desc.bInterfaceNumber);
-
-		/* set private data to usb_interface */
-		usb_set_intfdata(interface, sdev);
-
-		err = stub_add_files(&interface->dev);
-		if (err) {
-			dev_err(&interface->dev, "stub_add_files for %s\n",
-				udev_busid);
-			usb_set_intfdata(interface, NULL);
-			busid_priv->interf_count--;
-			return err;
-		}
-
-		usb_get_intf(interface);
-		return 0;
-	}
-
 	/* ok, this is my device */
-	sdev = stub_device_alloc(udev, interface);
+	sdev = stub_device_alloc(udev);
 	if (!sdev)
 		return -ENOMEM;
 
-	dev_info(&interface->dev,
-		"usbip-host: register new device (bus %u dev %u ifn %u)\n",
-		udev->bus->busnum, udev->devnum,
-		interface->cur_altsetting->desc.bInterfaceNumber);
+	dev_info(&udev->dev,
+		"usbip-host: register new device (bus %u dev %u)\n",
+		udev->bus->busnum, udev->devnum);
 
-	busid_priv->interf_count = 0;
 	busid_priv->shutdown_busid = 0;
 
-	/* set private data to usb_interface */
-	usb_set_intfdata(interface, sdev);
-	busid_priv->interf_count++;
+	config = usb_choose_configuration(udev);
+	if (config >= 0) {
+		err = usb_set_configuration(udev, config);
+		if (err && err != -ENODEV)
+			dev_err(&udev->dev, "can't set config #%d, error %d\n",
+				config, err);
+	}
+
+	/* set private data to usb_device */
+	dev_set_drvdata(&udev->dev, sdev);
 	busid_priv->sdev = sdev;
 
-	err = stub_add_files(&interface->dev);
+	err = stub_add_files(&udev->dev);
 	if (err) {
-		dev_err(&interface->dev, "stub_add_files for %s\n", udev_busid);
-		usb_set_intfdata(interface, NULL);
-		usb_put_intf(interface);
+		dev_err(&udev->dev, "stub_add_files for %s\n", udev_busid);
+		dev_set_drvdata(&udev->dev, NULL);
 		usb_put_dev(udev);
 		kthread_stop_put(sdev->ud.eh);
 
-		busid_priv->interf_count = 0;
 		busid_priv->sdev = NULL;
 		stub_device_free(sdev);
 		return err;
@@ -461,13 +423,13 @@ static void shutdown_busid(struct bus_id_priv *busid_priv)
  * called in usb_disconnect() or usb_deregister()
  * but only if actconfig(active configuration) exists
  */
-static void stub_disconnect(struct usb_interface *interface)
+static void stub_disconnect(struct usb_device *udev)
 {
 	struct stub_device *sdev;
-	const char *udev_busid = dev_name(interface->dev.parent);
+	const char *udev_busid = dev_name(&udev->dev);
 	struct bus_id_priv *busid_priv;
 
-	dev_dbg(&interface->dev, "Enter\n");
+	dev_dbg(&udev->dev, "Enter\n");
 
 	busid_priv = get_busid_priv(udev_busid);
 	if (!busid_priv) {
@@ -475,41 +437,29 @@ static void stub_disconnect(struct usb_interface *interface)
 		return;
 	}
 
-	sdev = usb_get_intfdata(interface);
+	sdev = dev_get_drvdata(&udev->dev);
 
 	/* get stub_device */
 	if (!sdev) {
-		dev_err(&interface->dev, "could not get device");
+		dev_err(&udev->dev, "could not get device");
 		return;
 	}
 
-	usb_set_intfdata(interface, NULL);
+	dev_set_drvdata(&udev->dev, NULL);
 
 	/*
 	 * NOTE: rx/tx threads are invoked for each usb_device.
 	 */
-	stub_remove_files(&interface->dev);
+	stub_remove_files(&udev->dev);
 
 	/* If usb reset is called from event handler */
-	if (busid_priv->sdev->ud.eh == current) {
-		busid_priv->interf_count--;
+	if (busid_priv->sdev->ud.eh == current)
 		return;
-	}
-
-	if (busid_priv->interf_count > 1) {
-		busid_priv->interf_count--;
-		shutdown_busid(busid_priv);
-		usb_put_intf(interface);
-		return;
-	}
-
-	busid_priv->interf_count = 0;
 
 	/* shutdown the current connection */
 	shutdown_busid(busid_priv);
 
 	usb_put_dev(sdev->udev);
-	usb_put_intf(interface);
 
 	/* free sdev */
 	busid_priv->sdev = NULL;
@@ -523,28 +473,34 @@ static void stub_disconnect(struct usb_interface *interface)
 	}
 }
 
-/*
- * Presence of pre_reset and post_reset prevents the driver from being unbound
- * when the device is being reset
- */
+#ifdef CONFIG_PM
 
-static int stub_pre_reset(struct usb_interface *interface)
+/* These functions need usb_port_suspend and usb_port_resume,
+ * which reside in drivers/usb/core/usb.h. Skip for now. */
+
+static int stub_suspend(struct usb_device *udev, pm_message_t message)
 {
-	dev_dbg(&interface->dev, "pre_reset\n");
+	dev_dbg(&udev->dev, "stub_suspend\n");
+
 	return 0;
 }
 
-static int stub_post_reset(struct usb_interface *interface)
+static int stub_resume(struct usb_device *udev, pm_message_t message)
 {
-	dev_dbg(&interface->dev, "post_reset\n");
+	dev_dbg(&udev->dev, "stub_resume\n");
+
 	return 0;
 }
 
-struct usb_driver stub_driver = {
+#endif	/* CONFIG_PM */
+
+struct usb_device_driver stub_driver = {
 	.name		= "usbip-host",
 	.probe		= stub_probe,
 	.disconnect	= stub_disconnect,
-	.id_table	= stub_table,
-	.pre_reset	= stub_pre_reset,
-	.post_reset	= stub_post_reset,
+#ifdef CONFIG_PM
+	.suspend	= stub_suspend,
+	.resume		= stub_resume,
+#endif
+	.supports_autosuspend	=	0,
 };
diff --git a/drivers/staging/usbip/stub_main.c b/drivers/staging/usbip/stub_main.c
index baf857f7cc88..bd7b83a9d758 100644
--- a/drivers/staging/usbip/stub_main.c
+++ b/drivers/staging/usbip/stub_main.c
@@ -254,7 +254,7 @@ static int __init usbip_host_init(void)
 		return -ENOMEM;
 	}
 
-	ret = usb_register(&stub_driver);
+	ret = usb_register_device_driver(&stub_driver, THIS_MODULE);
 	if (ret) {
 		pr_err("usb_register failed %d\n", ret);
 		goto err_usb_register;
@@ -271,7 +271,7 @@ static int __init usbip_host_init(void)
 	return ret;
 
 err_create_file:
-	usb_deregister(&stub_driver);
+	usb_deregister_device_driver(&stub_driver);
 err_usb_register:
 	kmem_cache_destroy(stub_priv_cache);
 	return ret;
@@ -286,7 +286,7 @@ static void __exit usbip_host_exit(void)
 	 * deregister() calls stub_disconnect() for all devices. Device
 	 * specific data is cleared in stub_disconnect().
 	 */
-	usb_deregister(&stub_driver);
+	usb_deregister_device_driver(&stub_driver);
 
 	kmem_cache_destroy(stub_priv_cache);
 }
diff --git a/drivers/staging/usbip/stub_rx.c b/drivers/staging/usbip/stub_rx.c
index 5d1d4a183300..76e44d949232 100644
--- a/drivers/staging/usbip/stub_rx.c
+++ b/drivers/staging/usbip/stub_rx.c
@@ -550,7 +550,7 @@ static void stub_rx_pdu(struct usbip_device *ud)
 	int ret;
 	struct usbip_header pdu;
 	struct stub_device *sdev = container_of(ud, struct stub_device, ud);
-	struct device *dev = &sdev->interface->dev;
+	struct device *dev = &sdev->udev->dev;
 
 	usbip_dbg_stub_rx("Enter\n");
 
diff --git a/drivers/staging/usbip/userspace/libsrc/usbip_host_driver.c b/drivers/staging/usbip/userspace/libsrc/usbip_host_driver.c
index 71a449cf50db..86a867582de6 100644
--- a/drivers/staging/usbip/userspace/libsrc/usbip_host_driver.c
+++ b/drivers/staging/usbip/userspace/libsrc/usbip_host_driver.c
@@ -32,7 +32,6 @@ struct usbip_host_driver *host_driver;
 
 #define SYSFS_OPEN_RETRIES 100
 
-/* only the first interface value is true! */
 static int32_t read_attr_usbip_status(struct usbip_usb_device *udev)
 {
 	char attrpath[SYSFS_PATH_MAX];
@@ -56,8 +55,8 @@ static int32_t read_attr_usbip_status(struct usbip_usb_device *udev)
 	 * usbip_status to reappear.
 	 */
 
-	snprintf(attrpath, SYSFS_PATH_MAX, "%s/%s:%d.%d/usbip_status",
-		 udev->path, udev->busid, udev->bConfigurationValue, 0);
+	snprintf(attrpath, SYSFS_PATH_MAX, "%s/usbip_status",
+		 udev->path);
 
 	while (retries > 0) {
 		if (stat(attrpath, &s) == 0)
@@ -168,19 +167,18 @@ static void delete_nothing(void *unused_data)
 
 static int refresh_exported_devices(void)
 {
-	/* sysfs_device of usb_interface */
-	struct sysfs_device	*suintf;
-	struct dlist		*suintf_list;
 	/* sysfs_device of usb_device */
 	struct sysfs_device	*sudev;
 	struct dlist		*sudev_list;
+	struct dlist		*sudev_unique_list;
 	struct usbip_exported_device *edev;
 
-	sudev_list = dlist_new_with_delete(sizeof(struct sysfs_device),
-					   delete_nothing);
+	sudev_unique_list = dlist_new_with_delete(sizeof(struct sysfs_device),
+						  delete_nothing);
 
-	suintf_list = sysfs_get_driver_devices(host_driver->sysfs_driver);
-	if (!suintf_list) {
+	sudev_list = sysfs_get_driver_devices(host_driver->sysfs_driver);
+
+	if (!sudev_list) {
 		/*
 		 * Not an error condition. There are simply no devices bound to
 		 * the driver yet.
@@ -190,23 +188,13 @@ static int refresh_exported_devices(void)
 		return 0;
 	}
 
-	/* collect unique USB devices (not interfaces) */
-	dlist_for_each_data(suintf_list, suintf, struct sysfs_device) {
-		/* get usb device of this usb interface */
-		sudev = sysfs_get_device_parent(suintf);
-		if (!sudev) {
-			dbg("sysfs_get_device_parent failed: %s", suintf->name);
-			continue;
-		}
+	dlist_for_each_data(sudev_list, sudev, struct sysfs_device)
+		if (check_new(sudev_unique_list, sudev))
+			dlist_unshift(sudev_unique_list, sudev);
 
-		if (check_new(sudev_list, sudev)) {
-			/* insert item at head of list */
-			dlist_unshift(sudev_list, sudev);
-		}
-	}
-
-	dlist_for_each_data(sudev_list, sudev, struct sysfs_device) {
+	dlist_for_each_data(sudev_unique_list, sudev, struct sysfs_device) {
 		edev = usbip_exported_device_new(sudev->path);
+
 		if (!edev) {
 			dbg("usbip_exported_device_new failed");
 			continue;
@@ -216,7 +204,7 @@ static int refresh_exported_devices(void)
 		host_driver->ndevs++;
 	}
 
-	dlist_destroy(sudev_list);
+	dlist_destroy(sudev_unique_list);
 
 	return 0;
 }
@@ -356,9 +344,8 @@ int usbip_host_export_device(struct usbip_exported_device *edev, int sockfd)
 	}
 
 	/* only the first interface is true */
-	snprintf(attr_path, sizeof(attr_path), "%s/%s:%d.%d/%s",
-		 edev->udev.path, edev->udev.busid,
-		 edev->udev.bConfigurationValue, 0, attr_name);
+	snprintf(attr_path, sizeof(attr_path), "%s/%s",
+		 edev->udev.path, attr_name);
 
 	attr = sysfs_open_attribute(attr_path);
 	if (!attr) {
diff --git a/drivers/staging/usbip/userspace/src/usbip_bind.c b/drivers/staging/usbip/userspace/src/usbip_bind.c
index 9ecaf6e574df..8cfd2dbd9510 100644
--- a/drivers/staging/usbip/userspace/src/usbip_bind.c
+++ b/drivers/staging/usbip/userspace/src/usbip_bind.c
@@ -52,12 +52,8 @@ static int bind_usbip(char *busid)
 	char attr_name[] = "bind";
 	char sysfs_mntpath[SYSFS_PATH_MAX];
 	char bind_attr_path[SYSFS_PATH_MAX];
-	char intf_busid[SYSFS_BUS_ID_SIZE];
-	struct sysfs_device *busid_dev;
 	struct sysfs_attribute *bind_attr;
-	struct sysfs_attribute *bConfValue;
-	struct sysfs_attribute *bNumIntfs;
-	int i, failed = 0;
+	int failed = 0;
 	int rc, ret = -1;
 
 	rc = sysfs_get_mnt_path(sysfs_mntpath, SYSFS_PATH_MAX);
@@ -76,39 +72,15 @@ static int bind_usbip(char *busid)
 		return -1;
 	}
 
-	busid_dev = sysfs_open_device(bus_type, busid);
-	if (!busid_dev) {
-		dbg("sysfs_open_device %s failed: %s", busid, strerror(errno));
-		goto err_close_bind_attr;
-	}
-
-	bConfValue = sysfs_get_device_attr(busid_dev, "bConfigurationValue");
-	bNumIntfs  = sysfs_get_device_attr(busid_dev, "bNumInterfaces");
-
-	if (!bConfValue || !bNumIntfs) {
-		dbg("problem getting device attributes: %s",
-		    strerror(errno));
-		goto err_close_busid_dev;
-	}
-
-	for (i = 0; i < atoi(bNumIntfs->value); i++) {
-		snprintf(intf_busid, SYSFS_BUS_ID_SIZE, "%s:%.1s.%d", busid,
-			 bConfValue->value, i);
-
-		rc = sysfs_write_attribute(bind_attr, intf_busid,
-					   SYSFS_BUS_ID_SIZE);
-		if (rc < 0) {
-			dbg("bind driver at %s failed", intf_busid);
-			failed = 1;
-		}
+	rc = sysfs_write_attribute(bind_attr, busid, SYSFS_BUS_ID_SIZE);
+	if (rc < 0) {
+		dbg("bind driver at %s failed", busid);
+		failed = 1;
 	}
 
 	if (!failed)
 		ret = 0;
 
-err_close_busid_dev:
-	sysfs_close_device(busid_dev);
-err_close_bind_attr:
 	sysfs_close_attribute(bind_attr);
 
 	return ret;
@@ -118,15 +90,12 @@ err_close_bind_attr:
 static int unbind_other(char *busid)
 {
 	char bus_type[] = "usb";
-	char intf_busid[SYSFS_BUS_ID_SIZE];
 	struct sysfs_device *busid_dev;
-	struct sysfs_device *intf_dev;
-	struct sysfs_driver *intf_drv;
+	struct sysfs_device *dev;
+	struct sysfs_driver *drv;
 	struct sysfs_attribute *unbind_attr;
-	struct sysfs_attribute *bConfValue;
 	struct sysfs_attribute *bDevClass;
-	struct sysfs_attribute *bNumIntfs;
-	int i, rc;
+	int rc;
 	enum unbind_status status = UNBIND_ST_OK;
 
 	busid_dev = sysfs_open_device(bus_type, busid);
@@ -134,12 +103,11 @@ static int unbind_other(char *busid)
 		dbg("sysfs_open_device %s failed: %s", busid, strerror(errno));
 		return -1;
 	}
+	dbg("busid path: %s", busid_dev->path);
 
-	bConfValue = sysfs_get_device_attr(busid_dev, "bConfigurationValue");
 	bDevClass  = sysfs_get_device_attr(busid_dev, "bDeviceClass");
-	bNumIntfs  = sysfs_get_device_attr(busid_dev, "bNumInterfaces");
-	if (!bConfValue || !bDevClass || !bNumIntfs) {
-		dbg("problem getting device attributes: %s",
+	if (!bDevClass) {
+		dbg("problem getting device attribute: %s",
 		    strerror(errno));
 		goto err_close_busid_dev;
 	}
@@ -149,62 +117,62 @@ static int unbind_other(char *busid)
 		goto err_close_busid_dev;
 	}
 
-	for (i = 0; i < atoi(bNumIntfs->value); i++) {
-		snprintf(intf_busid, SYSFS_BUS_ID_SIZE, "%s:%.1s.%d", busid,
-			 bConfValue->value, i);
-		intf_dev = sysfs_open_device(bus_type, intf_busid);
-		if (!intf_dev) {
-			dbg("could not open interface device: %s",
-			    strerror(errno));
-			goto err_close_busid_dev;
-		}
-
-		dbg("%s -> %s", intf_dev->name,  intf_dev->driver_name);
+	dev = sysfs_open_device(bus_type, busid);
+	if (!dev) {
+		dbg("could not open device: %s",
+				strerror(errno));
+		goto err_close_busid_dev;
+	}
 
-		if (!strncmp("unknown", intf_dev->driver_name, SYSFS_NAME_LEN))
-			/* unbound interface */
-			continue;
+	dbg("%s -> %s", dev->name,  dev->driver_name);
 
-		if (!strncmp(USBIP_HOST_DRV_NAME, intf_dev->driver_name,
-			     SYSFS_NAME_LEN)) {
-			/* already bound to usbip-host */
-			status = UNBIND_ST_USBIP_HOST;
-			continue;
-		}
+	if (!strncmp("unknown", dev->driver_name, SYSFS_NAME_LEN)) {
+		/* unbound interface */
+		sysfs_close_device(dev);
+		goto out;
+	}
 
-		/* unbinding */
-		intf_drv = sysfs_open_driver(bus_type, intf_dev->driver_name);
-		if (!intf_drv) {
-			dbg("could not open interface driver on %s: %s",
-			    intf_dev->name, strerror(errno));
-			goto err_close_intf_dev;
-		}
+	if (!strncmp(USBIP_HOST_DRV_NAME, dev->driver_name,
+				SYSFS_NAME_LEN)) {
+		/* already bound to usbip-host */
+		status = UNBIND_ST_USBIP_HOST;
+		sysfs_close_device(dev);
+		goto out;
+	}
 
-		unbind_attr = sysfs_get_driver_attr(intf_drv, "unbind");
-		if (!unbind_attr) {
-			dbg("problem getting interface driver attribute: %s",
-			    strerror(errno));
-			goto err_close_intf_drv;
-		}
+	/* unbinding */
+	drv = sysfs_open_driver(bus_type, dev->driver_name);
+	if (!drv) {
+		dbg("could not open device driver on %s: %s",
+				dev->name, strerror(errno));
+		goto err_close_intf_dev;
+	}
+	dbg("device driver: %s", drv->path);
 
-		rc = sysfs_write_attribute(unbind_attr, intf_dev->bus_id,
-					   SYSFS_BUS_ID_SIZE);
-		if (rc < 0) {
-			/* NOTE: why keep unbinding other interfaces? */
-			dbg("unbind driver at %s failed", intf_dev->bus_id);
-			status = UNBIND_ST_FAILED;
-		}
+	unbind_attr = sysfs_get_driver_attr(drv, "unbind");
+	if (!unbind_attr) {
+		dbg("problem getting device driver attribute: %s",
+				strerror(errno));
+		goto err_close_intf_drv;
+	}
 
-		sysfs_close_driver(intf_drv);
-		sysfs_close_device(intf_dev);
+	rc = sysfs_write_attribute(unbind_attr, dev->bus_id,
+			SYSFS_BUS_ID_SIZE);
+	if (rc < 0) {
+		/* NOTE: why keep unbinding other interfaces? */
+		dbg("unbind driver at %s failed", dev->bus_id);
+		status = UNBIND_ST_FAILED;
 	}
 
+	sysfs_close_driver(drv);
+	sysfs_close_device(dev);
+
 	goto out;
 
 err_close_intf_drv:
-	sysfs_close_driver(intf_drv);
+	sysfs_close_driver(drv);
 err_close_intf_dev:
-	sysfs_close_device(intf_dev);
+	sysfs_close_device(dev);
 err_close_busid_dev:
 	status = UNBIND_ST_FAILED;
 out:
diff --git a/drivers/staging/usbip/userspace/src/usbip_list.c b/drivers/staging/usbip/userspace/src/usbip_list.c
index 237e099337a1..8864fa2a7f0b 100644
--- a/drivers/staging/usbip/userspace/src/usbip_list.c
+++ b/drivers/staging/usbip/userspace/src/usbip_list.c
@@ -52,9 +52,8 @@ static int get_exported_devices(char *host, int sockfd)
 	struct op_devlist_reply reply;
 	uint16_t code = OP_REP_DEVLIST;
 	struct usbip_usb_device udev;
-	struct usbip_usb_interface uintf;
 	unsigned int i;
-	int j, rc;
+	int rc;
 
 	rc = usbip_net_send_op_common(sockfd, OP_REQ_DEVLIST, 0);
 	if (rc < 0) {
@@ -104,22 +103,6 @@ static int get_exported_devices(char *host, int sockfd)
 		printf("%11s: %s\n", "", udev.path);
 		printf("%11s: %s\n", "", class_name);
 
-		for (j = 0; j < udev.bNumInterfaces; j++) {
-			rc = usbip_net_recv(sockfd, &uintf, sizeof(uintf));
-			if (rc < 0) {
-				dbg("usbip_net_recv failed: usbip_usb_intf[%d]",
-				    j);
-
-				return -1;
-			}
-			usbip_net_pack_usb_interface(0, &uintf);
-
-			usbip_names_get_class(class_name, sizeof(class_name),
-					      uintf.bInterfaceClass,
-					      uintf.bInterfaceSubClass,
-					      uintf.bInterfaceProtocol);
-			printf("%11s: %2d - %s\n", "", j, class_name);
-		}
 		printf("\n");
 	}
 
diff --git a/drivers/staging/usbip/userspace/src/usbip_unbind.c b/drivers/staging/usbip/userspace/src/usbip_unbind.c
index d5a9ab6af2a6..cace87838c24 100644
--- a/drivers/staging/usbip/userspace/src/usbip_unbind.c
+++ b/drivers/staging/usbip/userspace/src/usbip_unbind.c
@@ -47,12 +47,10 @@ static int unbind_device(char *busid)
 	int verified = 0;
 	int rc, ret = -1;
 
-	char attr_name[] = "bConfigurationValue";
+	char attr_name[] = "unbind";
 	char sysfs_mntpath[SYSFS_PATH_MAX];
-	char busid_attr_path[SYSFS_PATH_MAX];
-	struct sysfs_attribute *busid_attr;
-	char *val = NULL;
-	int len;
+	char unbind_attr_path[SYSFS_PATH_MAX];
+	struct sysfs_attribute *unbind_attr;
 
 	/* verify the busid device is using usbip-host */
 	usbip_host_drv = sysfs_open_driver(bus_type, USBIP_HOST_DRV_NAME);
@@ -99,55 +97,34 @@ static int unbind_device(char *busid)
 		return -1;
 	}
 
-	snprintf(busid_attr_path, sizeof(busid_attr_path), "%s/%s/%s/%s/%s/%s",
-		 sysfs_mntpath, SYSFS_BUS_NAME, bus_type, SYSFS_DEVICES_NAME,
-		 busid, attr_name);
+	snprintf(unbind_attr_path, sizeof(unbind_attr_path), "%s/%s/%s/%s/%s/%s",
+		 sysfs_mntpath, SYSFS_BUS_NAME, bus_type, SYSFS_DRIVERS_NAME,
+		 USBIP_HOST_DRV_NAME, attr_name);
 
 	/* read a device attribute */
-	busid_attr = sysfs_open_attribute(busid_attr_path);
-	if (!busid_attr) {
+	unbind_attr = sysfs_open_attribute(unbind_attr_path);
+	if (!unbind_attr) {
 		err("could not open %s/%s: %s", busid, attr_name,
 		    strerror(errno));
 		return -1;
 	}
 
-	if (sysfs_read_attribute(busid_attr) < 0) {
-		err("problem reading attribute: %s", strerror(errno));
-		goto err_out;
-	}
-
-	len = busid_attr->len;
-	val = malloc(len);
-	*val = *busid_attr->value;
-	sysfs_close_attribute(busid_attr);
-
 	/* notify driver of unbind */
 	rc = modify_match_busid(busid, 0);
 	if (rc < 0) {
 		err("unable to unbind device on %s", busid);
-		goto err_out;
-	}
-
-	/* write the device attribute */
-	busid_attr = sysfs_open_attribute(busid_attr_path);
-	if (!busid_attr) {
-		err("could not open %s/%s: %s", busid, attr_name,
-		    strerror(errno));
-		return -1;
 	}
 
-	rc = sysfs_write_attribute(busid_attr, val, len);
-	if (rc < 0) {
-		err("problem writing attribute: %s", strerror(errno));
-		goto err_out;
-	}
-	sysfs_close_attribute(busid_attr);
+	rc = sysfs_write_attribute(unbind_attr, busid,
+				   SYSFS_BUS_ID_SIZE);
+		if (rc < 0) {
+			dbg("bind driver at %s failed", busid);
+		}
+	sysfs_close_attribute(unbind_attr);
 
 	ret = 0;
 	printf("unbind device on busid %s: complete\n", busid);
 
-err_out:
-	free(val);
 err_close_usbip_host_drv:
 	sysfs_close_driver(usbip_host_drv);
 
diff --git a/drivers/staging/usbip/userspace/src/usbipd.c b/drivers/staging/usbip/userspace/src/usbipd.c
index 7980f8b5517b..c2b3ced9ca6e 100644
--- a/drivers/staging/usbip/userspace/src/usbipd.c
+++ b/drivers/staging/usbip/userspace/src/usbipd.c
@@ -159,9 +159,7 @@ static int send_reply_devlist(int connfd)
 {
 	struct usbip_exported_device *edev;
 	struct usbip_usb_device pdu_udev;
-	struct usbip_usb_interface pdu_uinf;
 	struct op_devlist_reply reply;
-	int i;
 	int rc;
 
 	reply.ndev = 0;
@@ -196,19 +194,6 @@ static int send_reply_devlist(int connfd)
 			dbg("usbip_net_send failed: pdu_udev");
 			return -1;
 		}
-
-		for (i = 0; i < edev->udev.bNumInterfaces; i++) {
-			dump_usb_interface(&edev->uinf[i]);
-			memcpy(&pdu_uinf, &edev->uinf[i], sizeof(pdu_uinf));
-			usbip_net_pack_usb_interface(1, &pdu_uinf);
-
-			rc = usbip_net_send(connfd, &pdu_uinf,
-					    sizeof(pdu_uinf));
-			if (rc < 0) {
-				dbg("usbip_net_send failed: pdu_uinf");
-				return -1;
-			}
-		}
 	}
 
 	return 0;
diff --git a/drivers/usb/core/generic.c b/drivers/usb/core/generic.c
index acbfeb0a0119..358ca8dd784f 100644
--- a/drivers/usb/core/generic.c
+++ b/drivers/usb/core/generic.c
@@ -155,6 +155,7 @@ int usb_choose_configuration(struct usb_device *udev)
 	}
 	return i;
 }
+EXPORT_SYMBOL_GPL(usb_choose_configuration);
 
 static int generic_probe(struct usb_device *udev)
 {
diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index f829a1aad1c3..08d95e9d56c2 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -1920,6 +1920,7 @@ free_interfaces:
 	usb_autosuspend_device(dev);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(usb_set_configuration);
 
 static LIST_HEAD(set_config_list);
 static DEFINE_SPINLOCK(set_config_lock);
diff --git a/include/linux/usb.h b/include/linux/usb.h
index c716da18c668..f434619f3975 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1668,6 +1668,10 @@ extern void usb_reset_endpoint(struct usb_device *dev, unsigned int epaddr);
 /* this request isn't really synchronous, but it belongs with the others */
 extern int usb_driver_set_configuration(struct usb_device *udev, int config);
 
+/* choose and set configuration for device */
+extern int usb_choose_configuration(struct usb_device *udev);
+extern int usb_set_configuration(struct usb_device *dev, int configuration);
+
 /*
  * timeouts, in milliseconds, used for sending/receiving control messages
  * they typically complete within a few frames (msec) after they're issued
-- 
cgit v1.2.3


From 5267cf02c7794953d89e9593a0d497bf43e3790d Mon Sep 17 00:00:00 2001
From: Bjarke Istrup Pedersen <gurligebis@gentoo.org>
Date: Wed, 22 Jan 2014 09:16:58 +0000
Subject: hv: Add hyperv.h to uapi headers

This patch adds the hyperv.h header to the uapi folder, and adds it to the Kbuild file.
Doing this enables compiling userspace Hyper-V tools using the installed headers.

Version 2: Split UAPI parts into new header, instead of duplicating.

Signed-off-by: Bjarke Istrup Pedersen <gurligebis@gentoo.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/hyperv.h      | 321 +----------------------------------------
 include/uapi/linux/Kbuild   |   1 +
 include/uapi/linux/hyperv.h | 344 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 347 insertions(+), 319 deletions(-)
 create mode 100644 include/uapi/linux/hyperv.h

(limited to 'include/linux')

diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 15da677478dd..167ef47e3d6e 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -25,325 +25,9 @@
 #ifndef _HYPERV_H
 #define _HYPERV_H
 
-#include <linux/types.h>
-
-/*
- * Framework version for util services.
- */
-#define UTIL_FW_MINOR  0
-
-#define UTIL_WS2K8_FW_MAJOR  1
-#define UTIL_WS2K8_FW_VERSION     (UTIL_WS2K8_FW_MAJOR << 16 | UTIL_FW_MINOR)
-
-#define UTIL_FW_MAJOR  3
-#define UTIL_FW_VERSION     (UTIL_FW_MAJOR << 16 | UTIL_FW_MINOR)
-
-
-/*
- * Implementation of host controlled snapshot of the guest.
- */
-
-#define VSS_OP_REGISTER 128
-
-enum hv_vss_op {
-	VSS_OP_CREATE = 0,
-	VSS_OP_DELETE,
-	VSS_OP_HOT_BACKUP,
-	VSS_OP_GET_DM_INFO,
-	VSS_OP_BU_COMPLETE,
-	/*
-	 * Following operations are only supported with IC version >= 5.0
-	 */
-	VSS_OP_FREEZE, /* Freeze the file systems in the VM */
-	VSS_OP_THAW, /* Unfreeze the file systems */
-	VSS_OP_AUTO_RECOVER,
-	VSS_OP_COUNT /* Number of operations, must be last */
-};
-
-
-/*
- * Header for all VSS messages.
- */
-struct hv_vss_hdr {
-	__u8 operation;
-	__u8 reserved[7];
-} __attribute__((packed));
-
-
-/*
- * Flag values for the hv_vss_check_feature. Linux supports only
- * one value.
- */
-#define VSS_HBU_NO_AUTO_RECOVERY	0x00000005
-
-struct hv_vss_check_feature {
-	__u32 flags;
-} __attribute__((packed));
-
-struct hv_vss_check_dm_info {
-	__u32 flags;
-} __attribute__((packed));
-
-struct hv_vss_msg {
-	union {
-		struct hv_vss_hdr vss_hdr;
-		int error;
-	};
-	union {
-		struct hv_vss_check_feature vss_cf;
-		struct hv_vss_check_dm_info dm_info;
-	};
-} __attribute__((packed));
-
-/*
- * An implementation of HyperV key value pair (KVP) functionality for Linux.
- *
- *
- * Copyright (C) 2010, Novell, Inc.
- * Author : K. Y. Srinivasan <ksrinivasan@novell.com>
- *
- */
-
-/*
- * Maximum value size - used for both key names and value data, and includes
- * any applicable NULL terminators.
- *
- * Note:  This limit is somewhat arbitrary, but falls easily within what is
- * supported for all native guests (back to Win 2000) and what is reasonable
- * for the IC KVP exchange functionality.  Note that Windows Me/98/95 are
- * limited to 255 character key names.
- *
- * MSDN recommends not storing data values larger than 2048 bytes in the
- * registry.
- *
- * Note:  This value is used in defining the KVP exchange message - this value
- * cannot be modified without affecting the message size and compatibility.
- */
-
-/*
- * bytes, including any null terminators
- */
-#define HV_KVP_EXCHANGE_MAX_VALUE_SIZE          (2048)
-
-
-/*
- * Maximum key size - the registry limit for the length of an entry name
- * is 256 characters, including the null terminator
- */
-
-#define HV_KVP_EXCHANGE_MAX_KEY_SIZE            (512)
+#include <uapi/linux/hyperv.h>
 
-/*
- * In Linux, we implement the KVP functionality in two components:
- * 1) The kernel component which is packaged as part of the hv_utils driver
- * is responsible for communicating with the host and responsible for
- * implementing the host/guest protocol. 2) A user level daemon that is
- * responsible for data gathering.
- *
- * Host/Guest Protocol: The host iterates over an index and expects the guest
- * to assign a key name to the index and also return the value corresponding to
- * the key. The host will have atmost one KVP transaction outstanding at any
- * given point in time. The host side iteration stops when the guest returns
- * an error. Microsoft has specified the following mapping of key names to
- * host specified index:
- *
- *	Index		Key Name
- *	0		FullyQualifiedDomainName
- *	1		IntegrationServicesVersion
- *	2		NetworkAddressIPv4
- *	3		NetworkAddressIPv6
- *	4		OSBuildNumber
- *	5		OSName
- *	6		OSMajorVersion
- *	7		OSMinorVersion
- *	8		OSVersion
- *	9		ProcessorArchitecture
- *
- * The Windows host expects the Key Name and Key Value to be encoded in utf16.
- *
- * Guest Kernel/KVP Daemon Protocol: As noted earlier, we implement all of the
- * data gathering functionality in a user mode daemon. The user level daemon
- * is also responsible for binding the key name to the index as well. The
- * kernel and user-level daemon communicate using a connector channel.
- *
- * The user mode component first registers with the
- * the kernel component. Subsequently, the kernel component requests, data
- * for the specified keys. In response to this message the user mode component
- * fills in the value corresponding to the specified key. We overload the
- * sequence field in the cn_msg header to define our KVP message types.
- *
- *
- * The kernel component simply acts as a conduit for communication between the
- * Windows host and the user-level daemon. The kernel component passes up the
- * index received from the Host to the user-level daemon. If the index is
- * valid (supported), the corresponding key as well as its
- * value (both are strings) is returned. If the index is invalid
- * (not supported), a NULL key string is returned.
- */
-
-
-/*
- * Registry value types.
- */
-
-#define REG_SZ 1
-#define REG_U32 4
-#define REG_U64 8
-
-/*
- * As we look at expanding the KVP functionality to include
- * IP injection functionality, we need to maintain binary
- * compatibility with older daemons.
- *
- * The KVP opcodes are defined by the host and it was unfortunate
- * that I chose to treat the registration operation as part of the
- * KVP operations defined by the host.
- * Here is the level of compatibility
- * (between the user level daemon and the kernel KVP driver) that we
- * will implement:
- *
- * An older daemon will always be supported on a newer driver.
- * A given user level daemon will require a minimal version of the
- * kernel driver.
- * If we cannot handle the version differences, we will fail gracefully
- * (this can happen when we have a user level daemon that is more
- * advanced than the KVP driver.
- *
- * We will use values used in this handshake for determining if we have
- * workable user level daemon and the kernel driver. We begin by taking the
- * registration opcode out of the KVP opcode namespace. We will however,
- * maintain compatibility with the existing user-level daemon code.
- */
-
-/*
- * Daemon code not supporting IP injection (legacy daemon).
- */
-
-#define KVP_OP_REGISTER	4
-
-/*
- * Daemon code supporting IP injection.
- * The KVP opcode field is used to communicate the
- * registration information; so define a namespace that
- * will be distinct from the host defined KVP opcode.
- */
-
-#define KVP_OP_REGISTER1 100
-
-enum hv_kvp_exchg_op {
-	KVP_OP_GET = 0,
-	KVP_OP_SET,
-	KVP_OP_DELETE,
-	KVP_OP_ENUMERATE,
-	KVP_OP_GET_IP_INFO,
-	KVP_OP_SET_IP_INFO,
-	KVP_OP_COUNT /* Number of operations, must be last. */
-};
-
-enum hv_kvp_exchg_pool {
-	KVP_POOL_EXTERNAL = 0,
-	KVP_POOL_GUEST,
-	KVP_POOL_AUTO,
-	KVP_POOL_AUTO_EXTERNAL,
-	KVP_POOL_AUTO_INTERNAL,
-	KVP_POOL_COUNT /* Number of pools, must be last. */
-};
-
-/*
- * Some Hyper-V status codes.
- */
-
-#define HV_S_OK				0x00000000
-#define HV_E_FAIL			0x80004005
-#define HV_S_CONT			0x80070103
-#define HV_ERROR_NOT_SUPPORTED		0x80070032
-#define HV_ERROR_MACHINE_LOCKED		0x800704F7
-#define HV_ERROR_DEVICE_NOT_CONNECTED	0x8007048F
-#define HV_INVALIDARG			0x80070057
-#define HV_GUID_NOTFOUND		0x80041002
-
-#define ADDR_FAMILY_NONE	0x00
-#define ADDR_FAMILY_IPV4	0x01
-#define ADDR_FAMILY_IPV6	0x02
-
-#define MAX_ADAPTER_ID_SIZE	128
-#define MAX_IP_ADDR_SIZE	1024
-#define MAX_GATEWAY_SIZE	512
-
-
-struct hv_kvp_ipaddr_value {
-	__u16	adapter_id[MAX_ADAPTER_ID_SIZE];
-	__u8	addr_family;
-	__u8	dhcp_enabled;
-	__u16	ip_addr[MAX_IP_ADDR_SIZE];
-	__u16	sub_net[MAX_IP_ADDR_SIZE];
-	__u16	gate_way[MAX_GATEWAY_SIZE];
-	__u16	dns_addr[MAX_IP_ADDR_SIZE];
-} __attribute__((packed));
-
-
-struct hv_kvp_hdr {
-	__u8 operation;
-	__u8 pool;
-	__u16 pad;
-} __attribute__((packed));
-
-struct hv_kvp_exchg_msg_value {
-	__u32 value_type;
-	__u32 key_size;
-	__u32 value_size;
-	__u8 key[HV_KVP_EXCHANGE_MAX_KEY_SIZE];
-	union {
-		__u8 value[HV_KVP_EXCHANGE_MAX_VALUE_SIZE];
-		__u32 value_u32;
-		__u64 value_u64;
-	};
-} __attribute__((packed));
-
-struct hv_kvp_msg_enumerate {
-	__u32 index;
-	struct hv_kvp_exchg_msg_value data;
-} __attribute__((packed));
-
-struct hv_kvp_msg_get {
-	struct hv_kvp_exchg_msg_value data;
-};
-
-struct hv_kvp_msg_set {
-	struct hv_kvp_exchg_msg_value data;
-};
-
-struct hv_kvp_msg_delete {
-	__u32 key_size;
-	__u8 key[HV_KVP_EXCHANGE_MAX_KEY_SIZE];
-};
-
-struct hv_kvp_register {
-	__u8 version[HV_KVP_EXCHANGE_MAX_KEY_SIZE];
-};
-
-struct hv_kvp_msg {
-	union {
-		struct hv_kvp_hdr	kvp_hdr;
-		int error;
-	};
-	union {
-		struct hv_kvp_msg_get		kvp_get;
-		struct hv_kvp_msg_set		kvp_set;
-		struct hv_kvp_msg_delete	kvp_delete;
-		struct hv_kvp_msg_enumerate	kvp_enum_data;
-		struct hv_kvp_ipaddr_value      kvp_ip_val;
-		struct hv_kvp_register		kvp_register;
-	} body;
-} __attribute__((packed));
-
-struct hv_kvp_ip_msg {
-	__u8 operation;
-	__u8 pool;
-	struct hv_kvp_ipaddr_value      kvp_ip_val;
-} __attribute__((packed));
-
-#ifdef __KERNEL__
+#include <linux/types.h>
 #include <linux/scatterlist.h>
 #include <linux/list.h>
 #include <linux/uuid.h>
@@ -1465,5 +1149,4 @@ void hv_vss_onchannelcallback(void *);
 
 extern __u32 vmbus_proto_version;
 
-#endif /* __KERNEL__ */
 #endif /* _HYPERV_H */
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 3ce25b5d75a9..6929571b79b0 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -139,6 +139,7 @@ header-y += hid.h
 header-y += hiddev.h
 header-y += hidraw.h
 header-y += hpet.h
+header-y += hyperv.h
 header-y += hysdn_if.h
 header-y += i2c-dev.h
 header-y += i2c.h
diff --git a/include/uapi/linux/hyperv.h b/include/uapi/linux/hyperv.h
new file mode 100644
index 000000000000..1861f8e2ce2b
--- /dev/null
+++ b/include/uapi/linux/hyperv.h
@@ -0,0 +1,344 @@
+/*
+ *
+ * Copyright (c) 2011, Microsoft Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * Authors:
+ *   Haiyang Zhang <haiyangz@microsoft.com>
+ *   Hank Janssen  <hjanssen@microsoft.com>
+ *   K. Y. Srinivasan <kys@microsoft.com>
+ *
+ */
+
+#ifndef _UAPI_HYPERV_H
+#define _UAPI_HYPERV_H
+
+/*
+ * Framework version for util services.
+ */
+#define UTIL_FW_MINOR  0
+
+#define UTIL_WS2K8_FW_MAJOR  1
+#define UTIL_WS2K8_FW_VERSION     (UTIL_WS2K8_FW_MAJOR << 16 | UTIL_FW_MINOR)
+
+#define UTIL_FW_MAJOR  3
+#define UTIL_FW_VERSION     (UTIL_FW_MAJOR << 16 | UTIL_FW_MINOR)
+
+
+/*
+ * Implementation of host controlled snapshot of the guest.
+ */
+
+#define VSS_OP_REGISTER 128
+
+enum hv_vss_op {
+	VSS_OP_CREATE = 0,
+	VSS_OP_DELETE,
+	VSS_OP_HOT_BACKUP,
+	VSS_OP_GET_DM_INFO,
+	VSS_OP_BU_COMPLETE,
+	/*
+	 * Following operations are only supported with IC version >= 5.0
+	 */
+	VSS_OP_FREEZE, /* Freeze the file systems in the VM */
+	VSS_OP_THAW, /* Unfreeze the file systems */
+	VSS_OP_AUTO_RECOVER,
+	VSS_OP_COUNT /* Number of operations, must be last */
+};
+
+
+/*
+ * Header for all VSS messages.
+ */
+struct hv_vss_hdr {
+	__u8 operation;
+	__u8 reserved[7];
+} __attribute__((packed));
+
+
+/*
+ * Flag values for the hv_vss_check_feature. Linux supports only
+ * one value.
+ */
+#define VSS_HBU_NO_AUTO_RECOVERY	0x00000005
+
+struct hv_vss_check_feature {
+	__u32 flags;
+} __attribute__((packed));
+
+struct hv_vss_check_dm_info {
+	__u32 flags;
+} __attribute__((packed));
+
+struct hv_vss_msg {
+	union {
+		struct hv_vss_hdr vss_hdr;
+		int error;
+	};
+	union {
+		struct hv_vss_check_feature vss_cf;
+		struct hv_vss_check_dm_info dm_info;
+	};
+} __attribute__((packed));
+
+/*
+ * An implementation of HyperV key value pair (KVP) functionality for Linux.
+ *
+ *
+ * Copyright (C) 2010, Novell, Inc.
+ * Author : K. Y. Srinivasan <ksrinivasan@novell.com>
+ *
+ */
+
+/*
+ * Maximum value size - used for both key names and value data, and includes
+ * any applicable NULL terminators.
+ *
+ * Note:  This limit is somewhat arbitrary, but falls easily within what is
+ * supported for all native guests (back to Win 2000) and what is reasonable
+ * for the IC KVP exchange functionality.  Note that Windows Me/98/95 are
+ * limited to 255 character key names.
+ *
+ * MSDN recommends not storing data values larger than 2048 bytes in the
+ * registry.
+ *
+ * Note:  This value is used in defining the KVP exchange message - this value
+ * cannot be modified without affecting the message size and compatibility.
+ */
+
+/*
+ * bytes, including any null terminators
+ */
+#define HV_KVP_EXCHANGE_MAX_VALUE_SIZE          (2048)
+
+
+/*
+ * Maximum key size - the registry limit for the length of an entry name
+ * is 256 characters, including the null terminator
+ */
+
+#define HV_KVP_EXCHANGE_MAX_KEY_SIZE            (512)
+
+/*
+ * In Linux, we implement the KVP functionality in two components:
+ * 1) The kernel component which is packaged as part of the hv_utils driver
+ * is responsible for communicating with the host and responsible for
+ * implementing the host/guest protocol. 2) A user level daemon that is
+ * responsible for data gathering.
+ *
+ * Host/Guest Protocol: The host iterates over an index and expects the guest
+ * to assign a key name to the index and also return the value corresponding to
+ * the key. The host will have atmost one KVP transaction outstanding at any
+ * given point in time. The host side iteration stops when the guest returns
+ * an error. Microsoft has specified the following mapping of key names to
+ * host specified index:
+ *
+ *	Index		Key Name
+ *	0		FullyQualifiedDomainName
+ *	1		IntegrationServicesVersion
+ *	2		NetworkAddressIPv4
+ *	3		NetworkAddressIPv6
+ *	4		OSBuildNumber
+ *	5		OSName
+ *	6		OSMajorVersion
+ *	7		OSMinorVersion
+ *	8		OSVersion
+ *	9		ProcessorArchitecture
+ *
+ * The Windows host expects the Key Name and Key Value to be encoded in utf16.
+ *
+ * Guest Kernel/KVP Daemon Protocol: As noted earlier, we implement all of the
+ * data gathering functionality in a user mode daemon. The user level daemon
+ * is also responsible for binding the key name to the index as well. The
+ * kernel and user-level daemon communicate using a connector channel.
+ *
+ * The user mode component first registers with the
+ * the kernel component. Subsequently, the kernel component requests, data
+ * for the specified keys. In response to this message the user mode component
+ * fills in the value corresponding to the specified key. We overload the
+ * sequence field in the cn_msg header to define our KVP message types.
+ *
+ *
+ * The kernel component simply acts as a conduit for communication between the
+ * Windows host and the user-level daemon. The kernel component passes up the
+ * index received from the Host to the user-level daemon. If the index is
+ * valid (supported), the corresponding key as well as its
+ * value (both are strings) is returned. If the index is invalid
+ * (not supported), a NULL key string is returned.
+ */
+
+
+/*
+ * Registry value types.
+ */
+
+#define REG_SZ 1
+#define REG_U32 4
+#define REG_U64 8
+
+/*
+ * As we look at expanding the KVP functionality to include
+ * IP injection functionality, we need to maintain binary
+ * compatibility with older daemons.
+ *
+ * The KVP opcodes are defined by the host and it was unfortunate
+ * that I chose to treat the registration operation as part of the
+ * KVP operations defined by the host.
+ * Here is the level of compatibility
+ * (between the user level daemon and the kernel KVP driver) that we
+ * will implement:
+ *
+ * An older daemon will always be supported on a newer driver.
+ * A given user level daemon will require a minimal version of the
+ * kernel driver.
+ * If we cannot handle the version differences, we will fail gracefully
+ * (this can happen when we have a user level daemon that is more
+ * advanced than the KVP driver.
+ *
+ * We will use values used in this handshake for determining if we have
+ * workable user level daemon and the kernel driver. We begin by taking the
+ * registration opcode out of the KVP opcode namespace. We will however,
+ * maintain compatibility with the existing user-level daemon code.
+ */
+
+/*
+ * Daemon code not supporting IP injection (legacy daemon).
+ */
+
+#define KVP_OP_REGISTER	4
+
+/*
+ * Daemon code supporting IP injection.
+ * The KVP opcode field is used to communicate the
+ * registration information; so define a namespace that
+ * will be distinct from the host defined KVP opcode.
+ */
+
+#define KVP_OP_REGISTER1 100
+
+enum hv_kvp_exchg_op {
+	KVP_OP_GET = 0,
+	KVP_OP_SET,
+	KVP_OP_DELETE,
+	KVP_OP_ENUMERATE,
+	KVP_OP_GET_IP_INFO,
+	KVP_OP_SET_IP_INFO,
+	KVP_OP_COUNT /* Number of operations, must be last. */
+};
+
+enum hv_kvp_exchg_pool {
+	KVP_POOL_EXTERNAL = 0,
+	KVP_POOL_GUEST,
+	KVP_POOL_AUTO,
+	KVP_POOL_AUTO_EXTERNAL,
+	KVP_POOL_AUTO_INTERNAL,
+	KVP_POOL_COUNT /* Number of pools, must be last. */
+};
+
+/*
+ * Some Hyper-V status codes.
+ */
+
+#define HV_S_OK				0x00000000
+#define HV_E_FAIL			0x80004005
+#define HV_S_CONT			0x80070103
+#define HV_ERROR_NOT_SUPPORTED		0x80070032
+#define HV_ERROR_MACHINE_LOCKED		0x800704F7
+#define HV_ERROR_DEVICE_NOT_CONNECTED	0x8007048F
+#define HV_INVALIDARG			0x80070057
+#define HV_GUID_NOTFOUND		0x80041002
+
+#define ADDR_FAMILY_NONE	0x00
+#define ADDR_FAMILY_IPV4	0x01
+#define ADDR_FAMILY_IPV6	0x02
+
+#define MAX_ADAPTER_ID_SIZE	128
+#define MAX_IP_ADDR_SIZE	1024
+#define MAX_GATEWAY_SIZE	512
+
+
+struct hv_kvp_ipaddr_value {
+	__u16	adapter_id[MAX_ADAPTER_ID_SIZE];
+	__u8	addr_family;
+	__u8	dhcp_enabled;
+	__u16	ip_addr[MAX_IP_ADDR_SIZE];
+	__u16	sub_net[MAX_IP_ADDR_SIZE];
+	__u16	gate_way[MAX_GATEWAY_SIZE];
+	__u16	dns_addr[MAX_IP_ADDR_SIZE];
+} __attribute__((packed));
+
+
+struct hv_kvp_hdr {
+	__u8 operation;
+	__u8 pool;
+	__u16 pad;
+} __attribute__((packed));
+
+struct hv_kvp_exchg_msg_value {
+	__u32 value_type;
+	__u32 key_size;
+	__u32 value_size;
+	__u8 key[HV_KVP_EXCHANGE_MAX_KEY_SIZE];
+	union {
+		__u8 value[HV_KVP_EXCHANGE_MAX_VALUE_SIZE];
+		__u32 value_u32;
+		__u64 value_u64;
+	};
+} __attribute__((packed));
+
+struct hv_kvp_msg_enumerate {
+	__u32 index;
+	struct hv_kvp_exchg_msg_value data;
+} __attribute__((packed));
+
+struct hv_kvp_msg_get {
+	struct hv_kvp_exchg_msg_value data;
+};
+
+struct hv_kvp_msg_set {
+	struct hv_kvp_exchg_msg_value data;
+};
+
+struct hv_kvp_msg_delete {
+	__u32 key_size;
+	__u8 key[HV_KVP_EXCHANGE_MAX_KEY_SIZE];
+};
+
+struct hv_kvp_register {
+	__u8 version[HV_KVP_EXCHANGE_MAX_KEY_SIZE];
+};
+
+struct hv_kvp_msg {
+	union {
+		struct hv_kvp_hdr	kvp_hdr;
+		int error;
+	};
+	union {
+		struct hv_kvp_msg_get		kvp_get;
+		struct hv_kvp_msg_set		kvp_set;
+		struct hv_kvp_msg_delete	kvp_delete;
+		struct hv_kvp_msg_enumerate	kvp_enum_data;
+		struct hv_kvp_ipaddr_value      kvp_ip_val;
+		struct hv_kvp_register		kvp_register;
+	} body;
+} __attribute__((packed));
+
+struct hv_kvp_ip_msg {
+	__u8 operation;
+	__u8 pool;
+	struct hv_kvp_ipaddr_value      kvp_ip_val;
+} __attribute__((packed));
+
+#endif /* _UAPI_HYPERV_H */
-- 
cgit v1.2.3


From 90f3453585479d5beb75058da46eb573ced0e6ac Mon Sep 17 00:00:00 2001
From: "K. Y. Srinivasan" <kys@microsoft.com>
Date: Wed, 29 Jan 2014 18:14:39 -0800
Subject: Drivers: hv: vmbus: Extract the mmio information from DSDT

On Gen2 firmware, Hyper-V does not emulate the PCI bus. However, the MMIO
information is packaged up in DSDT. Extract this information and export it
for use by the synthetic framebuffer driver. This is the only driver that
needs this currently.

In this version of the patch mmio, I have updated the hyperv header file
(linux/hyperv.h) with mmio definitions.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hv/vmbus_drv.c | 45 ++++++++++++++++++++++++++++++++-------------
 include/linux/hyperv.h |  3 +++
 2 files changed, 35 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 077bb1bdac34..b37c91b6ba80 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -43,6 +43,10 @@ static struct acpi_device  *hv_acpi_dev;
 static struct tasklet_struct msg_dpc;
 static struct completion probe_event;
 static int irq;
+u64 hyperv_mmio_start;
+EXPORT_SYMBOL_GPL(hyperv_mmio_start);
+u64 hyperv_mmio_size;
+EXPORT_SYMBOL_GPL(hyperv_mmio_size);
 
 static int vmbus_exists(void)
 {
@@ -886,18 +890,19 @@ void vmbus_device_unregister(struct hv_device *device_obj)
 
 
 /*
- * VMBUS is an acpi enumerated device. Get the the IRQ information
- * from DSDT.
+ * VMBUS is an acpi enumerated device. Get the the information we
+ * need from DSDT.
  */
 
-static acpi_status vmbus_walk_resources(struct acpi_resource *res, void *irq)
+static acpi_status vmbus_walk_resources(struct acpi_resource *res, void *ctx)
 {
+	switch (res->type) {
+	case ACPI_RESOURCE_TYPE_IRQ:
+		irq = res->data.irq.interrupts[0];
 
-	if (res->type == ACPI_RESOURCE_TYPE_IRQ) {
-		struct acpi_resource_irq *irqp;
-		irqp = &res->data.irq;
-
-		*((unsigned int *)irq) = irqp->interrupts[0];
+	case ACPI_RESOURCE_TYPE_ADDRESS64:
+		hyperv_mmio_start = res->data.address64.minimum;
+		hyperv_mmio_size = res->data.address64.address_length;
 	}
 
 	return AE_OK;
@@ -906,18 +911,32 @@ static acpi_status vmbus_walk_resources(struct acpi_resource *res, void *irq)
 static int vmbus_acpi_add(struct acpi_device *device)
 {
 	acpi_status result;
+	int ret_val = -ENODEV;
 
 	hv_acpi_dev = device;
 
 	result = acpi_walk_resources(device->handle, METHOD_NAME__CRS,
-					vmbus_walk_resources, &irq);
+					vmbus_walk_resources, NULL);
 
-	if (ACPI_FAILURE(result)) {
-		complete(&probe_event);
-		return -ENODEV;
+	if (ACPI_FAILURE(result))
+		goto acpi_walk_err;
+	/*
+	 * The parent of the vmbus acpi device (Gen2 firmware) is the VMOD that
+	 * has the mmio ranges. Get that.
+	 */
+	if (device->parent) {
+		result = acpi_walk_resources(device->parent->handle,
+					METHOD_NAME__CRS,
+					vmbus_walk_resources, NULL);
+
+		if (ACPI_FAILURE(result))
+			goto acpi_walk_err;
 	}
+	ret_val = 0;
+
+acpi_walk_err:
 	complete(&probe_event);
-	return 0;
+	return ret_val;
 }
 
 static const struct acpi_device_id vmbus_acpi_device_ids[] = {
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 167ef47e3d6e..6b862dadbb7a 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1143,6 +1143,9 @@ int hv_vss_init(struct hv_util_service *);
 void hv_vss_deinit(void);
 void hv_vss_onchannelcallback(void *);
 
+extern u64 hyperv_mmio_start;
+extern u64 hyperv_mmio_size;
+
 /*
  * Negotiated version with the Host.
  */
-- 
cgit v1.2.3


From 011a7c3cc3aa60c7ea6bb49d847e80a299ba7b36 Mon Sep 17 00:00:00 2001
From: "K. Y. Srinivasan" <kys@microsoft.com>
Date: Sat, 1 Feb 2014 19:02:20 -0800
Subject: Drivers: hv: vmbus: Cleanup the packet send path

The current channel code is using scatterlist abstraction to pass data to the
ringbuffer API on the send path. This causes unnecessary translations
between virtual and physical addresses. Fix this.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hv/channel.c      | 42 +++++++++++++++++++++++-------------------
 drivers/hv/hyperv_vmbus.h |  4 ++--
 drivers/hv/ring_buffer.c  | 17 +++++++----------
 include/linux/hyperv.h    |  2 +-
 4 files changed, 33 insertions(+), 32 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 69ea36f07b4d..602ca86a6488 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -27,6 +27,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/hyperv.h>
+#include <linux/uio.h>
 
 #include "hyperv_vmbus.h"
 
@@ -554,14 +555,14 @@ EXPORT_SYMBOL_GPL(vmbus_close);
  *
  * Mainly used by Hyper-V drivers.
  */
-int vmbus_sendpacket(struct vmbus_channel *channel, const void *buffer,
+int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer,
 			   u32 bufferlen, u64 requestid,
 			   enum vmbus_packet_type type, u32 flags)
 {
 	struct vmpacket_descriptor desc;
 	u32 packetlen = sizeof(struct vmpacket_descriptor) + bufferlen;
 	u32 packetlen_aligned = ALIGN(packetlen, sizeof(u64));
-	struct scatterlist bufferlist[3];
+	struct kvec bufferlist[3];
 	u64 aligned_data = 0;
 	int ret;
 	bool signal = false;
@@ -575,11 +576,12 @@ int vmbus_sendpacket(struct vmbus_channel *channel, const void *buffer,
 	desc.len8 = (u16)(packetlen_aligned >> 3);
 	desc.trans_id = requestid;
 
-	sg_init_table(bufferlist, 3);
-	sg_set_buf(&bufferlist[0], &desc, sizeof(struct vmpacket_descriptor));
-	sg_set_buf(&bufferlist[1], buffer, bufferlen);
-	sg_set_buf(&bufferlist[2], &aligned_data,
-		   packetlen_aligned - packetlen);
+	bufferlist[0].iov_base = &desc;
+	bufferlist[0].iov_len = sizeof(struct vmpacket_descriptor);
+	bufferlist[1].iov_base = buffer;
+	bufferlist[1].iov_len = bufferlen;
+	bufferlist[2].iov_base = &aligned_data;
+	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
 
 	ret = hv_ringbuffer_write(&channel->outbound, bufferlist, 3, &signal);
 
@@ -605,7 +607,7 @@ int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel,
 	u32 descsize;
 	u32 packetlen;
 	u32 packetlen_aligned;
-	struct scatterlist bufferlist[3];
+	struct kvec bufferlist[3];
 	u64 aligned_data = 0;
 	bool signal = false;
 
@@ -637,11 +639,12 @@ int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel,
 		desc.range[i].pfn	 = pagebuffers[i].pfn;
 	}
 
-	sg_init_table(bufferlist, 3);
-	sg_set_buf(&bufferlist[0], &desc, descsize);
-	sg_set_buf(&bufferlist[1], buffer, bufferlen);
-	sg_set_buf(&bufferlist[2], &aligned_data,
-		packetlen_aligned - packetlen);
+	bufferlist[0].iov_base = &desc;
+	bufferlist[0].iov_len = descsize;
+	bufferlist[1].iov_base = buffer;
+	bufferlist[1].iov_len = bufferlen;
+	bufferlist[2].iov_base = &aligned_data;
+	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
 
 	ret = hv_ringbuffer_write(&channel->outbound, bufferlist, 3, &signal);
 
@@ -665,7 +668,7 @@ int vmbus_sendpacket_multipagebuffer(struct vmbus_channel *channel,
 	u32 descsize;
 	u32 packetlen;
 	u32 packetlen_aligned;
-	struct scatterlist bufferlist[3];
+	struct kvec bufferlist[3];
 	u64 aligned_data = 0;
 	bool signal = false;
 	u32 pfncount = NUM_PAGES_SPANNED(multi_pagebuffer->offset,
@@ -700,11 +703,12 @@ int vmbus_sendpacket_multipagebuffer(struct vmbus_channel *channel,
 	memcpy(desc.range.pfn_array, multi_pagebuffer->pfn_array,
 	       pfncount * sizeof(u64));
 
-	sg_init_table(bufferlist, 3);
-	sg_set_buf(&bufferlist[0], &desc, descsize);
-	sg_set_buf(&bufferlist[1], buffer, bufferlen);
-	sg_set_buf(&bufferlist[2], &aligned_data,
-		packetlen_aligned - packetlen);
+	bufferlist[0].iov_base = &desc;
+	bufferlist[0].iov_len = descsize;
+	bufferlist[1].iov_base = buffer;
+	bufferlist[1].iov_len = bufferlen;
+	bufferlist[2].iov_base = &aligned_data;
+	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
 
 	ret = hv_ringbuffer_write(&channel->outbound, bufferlist, 3, &signal);
 
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index e05517616a06..1544609881fe 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -559,8 +559,8 @@ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info, void *buffer,
 void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info);
 
 int hv_ringbuffer_write(struct hv_ring_buffer_info *ring_info,
-		    struct scatterlist *sglist,
-		    u32 sgcount, bool *signal);
+		    struct kvec *kv_list,
+		    u32 kv_count, bool *signal);
 
 int hv_ringbuffer_peek(struct hv_ring_buffer_info *ring_info, void *buffer,
 		   u32 buflen);
diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index 26c93cf9f6be..15db66b74141 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -26,6 +26,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/hyperv.h>
+#include <linux/uio.h>
 
 #include "hyperv_vmbus.h"
 
@@ -387,23 +388,20 @@ void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info)
  *
  */
 int hv_ringbuffer_write(struct hv_ring_buffer_info *outring_info,
-		    struct scatterlist *sglist, u32 sgcount, bool *signal)
+		    struct kvec *kv_list, u32 kv_count, bool *signal)
 {
 	int i = 0;
 	u32 bytes_avail_towrite;
 	u32 bytes_avail_toread;
 	u32 totalbytes_towrite = 0;
 
-	struct scatterlist *sg;
 	u32 next_write_location;
 	u32 old_write;
 	u64 prev_indices = 0;
 	unsigned long flags;
 
-	for_each_sg(sglist, sg, sgcount, i)
-	{
-		totalbytes_towrite += sg->length;
-	}
+	for (i = 0; i < kv_count; i++)
+		totalbytes_towrite += kv_list[i].iov_len;
 
 	totalbytes_towrite += sizeof(u64);
 
@@ -427,12 +425,11 @@ int hv_ringbuffer_write(struct hv_ring_buffer_info *outring_info,
 
 	old_write = next_write_location;
 
-	for_each_sg(sglist, sg, sgcount, i)
-	{
+	for (i = 0; i < kv_count; i++) {
 		next_write_location = hv_copyto_ringbuffer(outring_info,
 						     next_write_location,
-						     sg_virt(sg),
-						     sg->length);
+						     kv_list[i].iov_base,
+						     kv_list[i].iov_len);
 	}
 
 	/* Set previous packet start */
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 6b862dadbb7a..9b07e1f070ac 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -802,7 +802,7 @@ extern int vmbus_open(struct vmbus_channel *channel,
 extern void vmbus_close(struct vmbus_channel *channel);
 
 extern int vmbus_sendpacket(struct vmbus_channel *channel,
-				  const void *buffer,
+				  void *buffer,
 				  u32 bufferLen,
 				  u64 requestid,
 				  enum vmbus_packet_type type,
-- 
cgit v1.2.3


From 8a7206a89f85c8439561b0eff85bb9440a2e97a9 Mon Sep 17 00:00:00 2001
From: "K. Y. Srinivasan" <kys@microsoft.com>
Date: Mon, 3 Feb 2014 12:42:45 -0800
Subject: Drivers: hv: vmbus: Support per-channel driver state

As we implement Virtual Receive Side Scaling on the networking side
(the VRSS patches are currently under review), it will be useful to have
per-channel state that vmbus drivers can manage. Add support for
managing per-channel state.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/hyperv.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 9b07e1f070ac..d47bab9e7a18 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -727,6 +727,10 @@ struct vmbus_channel {
 	 * This will be NULL for the primary channel.
 	 */
 	struct vmbus_channel *primary_channel;
+	/*
+	 * Support per-channel state for use by vmbus drivers.
+	 */
+	void *per_channel_state;
 };
 
 static inline void set_channel_read_state(struct vmbus_channel *c, bool state)
@@ -734,6 +738,16 @@ static inline void set_channel_read_state(struct vmbus_channel *c, bool state)
 	c->batched_reading = state;
 }
 
+static inline void set_per_channel_state(struct vmbus_channel *c, void *s)
+{
+	c->per_channel_state = s;
+}
+
+static inline void *get_per_channel_state(struct vmbus_channel *c)
+{
+	return c->per_channel_state;
+}
+
 void vmbus_onmessage(void *context);
 
 int vmbus_request_offers(void);
-- 
cgit v1.2.3


From ac8f73305eea8a12fdcb6090417eb93a74efbcbd Mon Sep 17 00:00:00 2001
From: David Fries <David@Fries.net>
Date: Wed, 15 Jan 2014 22:29:19 -0600
Subject: connector: add portid to unicast in addition to broadcasting

This allows replying only to the requestor portid while still
supporting broadcasting.  Pass 0 to portid for the previous behavior.

Signed-off-by: David Fries <David@Fries.net>
Acked-by: Evgeniy Polyakov <zbr@ioremap.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/connector/cn_test.c      |  2 +-
 drivers/connector/cn_proc.c            | 18 +++++++++---------
 drivers/connector/connector.c          | 20 +++++++++++++-------
 drivers/hv/hv_kvp.c                    |  4 ++--
 drivers/hv/hv_snapshot.c               |  2 +-
 drivers/md/dm-log-userspace-transfer.c |  2 +-
 drivers/video/uvesafb.c                |  4 ++--
 drivers/w1/w1_netlink.c                | 14 +++++++-------
 include/linux/connector.h              |  2 +-
 9 files changed, 37 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/connector/cn_test.c b/Documentation/connector/cn_test.c
index adcca0368d60..d12cc944b696 100644
--- a/Documentation/connector/cn_test.c
+++ b/Documentation/connector/cn_test.c
@@ -145,7 +145,7 @@ static void cn_test_timer_func(unsigned long __data)
 
 		memcpy(m + 1, data, m->len);
 
-		cn_netlink_send(m, 0, GFP_ATOMIC);
+		cn_netlink_send(m, 0, 0, GFP_ATOMIC);
 		kfree(m);
 	}
 
diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index 18c5b9b16645..148d707a1d43 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -95,7 +95,7 @@ void proc_fork_connector(struct task_struct *task)
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
 	/*  If cn_netlink_send() failed, the data is not sent */
-	cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
+	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
 }
 
 void proc_exec_connector(struct task_struct *task)
@@ -122,7 +122,7 @@ void proc_exec_connector(struct task_struct *task)
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
+	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
 }
 
 void proc_id_connector(struct task_struct *task, int which_id)
@@ -163,7 +163,7 @@ void proc_id_connector(struct task_struct *task, int which_id)
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
+	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
 }
 
 void proc_sid_connector(struct task_struct *task)
@@ -190,7 +190,7 @@ void proc_sid_connector(struct task_struct *task)
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
+	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
 }
 
 void proc_ptrace_connector(struct task_struct *task, int ptrace_id)
@@ -225,7 +225,7 @@ void proc_ptrace_connector(struct task_struct *task, int ptrace_id)
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
+	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
 }
 
 void proc_comm_connector(struct task_struct *task)
@@ -253,7 +253,7 @@ void proc_comm_connector(struct task_struct *task)
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
+	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
 }
 
 void proc_coredump_connector(struct task_struct *task)
@@ -280,7 +280,7 @@ void proc_coredump_connector(struct task_struct *task)
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
+	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
 }
 
 void proc_exit_connector(struct task_struct *task)
@@ -309,7 +309,7 @@ void proc_exit_connector(struct task_struct *task)
 	msg->ack = 0; /* not used */
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
+	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
 }
 
 /*
@@ -343,7 +343,7 @@ static void cn_proc_ack(int err, int rcvd_seq, int rcvd_ack)
 	msg->ack = rcvd_ack + 1;
 	msg->len = sizeof(*ev);
 	msg->flags = 0; /* not used */
-	cn_netlink_send(msg, CN_IDX_PROC, GFP_KERNEL);
+	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_KERNEL);
 }
 
 /**
diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index a36749f1e44a..77afe7487d34 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -50,7 +50,7 @@ static int cn_already_initialized;
  *
  * Sequence number is incremented with each message to be sent.
  *
- * If we expect reply to our message then the sequence number in
+ * If we expect a reply to our message then the sequence number in
  * received message MUST be the same as in original message, and
  * acknowledge number MUST be the same + 1.
  *
@@ -62,8 +62,11 @@ static int cn_already_initialized;
  * the acknowledgement number in the original message + 1, then it is
  * a new message.
  *
+ * The message is sent to, the portid if given, the group if given, both if
+ * both, or if both are zero then the group is looked up and sent there.
  */
-int cn_netlink_send(struct cn_msg *msg, u32 __group, gfp_t gfp_mask)
+int cn_netlink_send(struct cn_msg *msg, u32 portid, u32 __group,
+	gfp_t gfp_mask)
 {
 	struct cn_callback_entry *__cbq;
 	unsigned int size;
@@ -74,7 +77,9 @@ int cn_netlink_send(struct cn_msg *msg, u32 __group, gfp_t gfp_mask)
 	u32 group = 0;
 	int found = 0;
 
-	if (!__group) {
+	if (portid || __group) {
+		group = __group;
+	} else {
 		spin_lock_bh(&dev->cbdev->queue_lock);
 		list_for_each_entry(__cbq, &dev->cbdev->queue_list,
 				    callback_entry) {
@@ -88,11 +93,9 @@ int cn_netlink_send(struct cn_msg *msg, u32 __group, gfp_t gfp_mask)
 
 		if (!found)
 			return -ENODEV;
-	} else {
-		group = __group;
 	}
 
-	if (!netlink_has_listeners(dev->nls, group))
+	if (!portid && !netlink_has_listeners(dev->nls, group))
 		return -ESRCH;
 
 	size = sizeof(*msg) + msg->len;
@@ -113,7 +116,10 @@ int cn_netlink_send(struct cn_msg *msg, u32 __group, gfp_t gfp_mask)
 
 	NETLINK_CB(skb).dst_group = group;
 
-	return netlink_broadcast(dev->nls, skb, 0, group, gfp_mask);
+	if (group)
+		return netlink_broadcast(dev->nls, skb, portid, group,
+					 gfp_mask);
+	return netlink_unicast(dev->nls, skb, portid, !(gfp_mask&__GFP_WAIT));
 }
 EXPORT_SYMBOL_GPL(cn_netlink_send);
 
diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c
index 09988b289622..ea852537307e 100644
--- a/drivers/hv/hv_kvp.c
+++ b/drivers/hv/hv_kvp.c
@@ -113,7 +113,7 @@ kvp_register(int reg_value)
 		kvp_msg->kvp_hdr.operation = reg_value;
 		strcpy(version, HV_DRV_VERSION);
 		msg->len = sizeof(struct hv_kvp_msg);
-		cn_netlink_send(msg, 0, GFP_ATOMIC);
+		cn_netlink_send(msg, 0, 0, GFP_ATOMIC);
 		kfree(msg);
 	}
 }
@@ -435,7 +435,7 @@ kvp_send_key(struct work_struct *dummy)
 	}
 
 	msg->len = sizeof(struct hv_kvp_msg);
-	cn_netlink_send(msg, 0, GFP_ATOMIC);
+	cn_netlink_send(msg, 0, 0, GFP_ATOMIC);
 	kfree(msg);
 
 	return;
diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c
index 0c3546224376..34f14fddb666 100644
--- a/drivers/hv/hv_snapshot.c
+++ b/drivers/hv/hv_snapshot.c
@@ -98,7 +98,7 @@ static void vss_send_op(struct work_struct *dummy)
 	vss_msg->vss_hdr.operation = op;
 	msg->len = sizeof(struct hv_vss_msg);
 
-	cn_netlink_send(msg, 0, GFP_ATOMIC);
+	cn_netlink_send(msg, 0, 0, GFP_ATOMIC);
 	kfree(msg);
 
 	return;
diff --git a/drivers/md/dm-log-userspace-transfer.c b/drivers/md/dm-log-userspace-transfer.c
index 08d9a207259a..b428c0ae63d5 100644
--- a/drivers/md/dm-log-userspace-transfer.c
+++ b/drivers/md/dm-log-userspace-transfer.c
@@ -66,7 +66,7 @@ static int dm_ulog_sendto_server(struct dm_ulog_request *tfr)
 	msg->seq = tfr->seq;
 	msg->len = sizeof(struct dm_ulog_request) + tfr->data_size;
 
-	r = cn_netlink_send(msg, 0, gfp_any());
+	r = cn_netlink_send(msg, 0, 0, gfp_any());
 
 	return r;
 }
diff --git a/drivers/video/uvesafb.c b/drivers/video/uvesafb.c
index 256fba7f4641..1f38445014c1 100644
--- a/drivers/video/uvesafb.c
+++ b/drivers/video/uvesafb.c
@@ -190,7 +190,7 @@ static int uvesafb_exec(struct uvesafb_ktask *task)
 	uvfb_tasks[seq] = task;
 	mutex_unlock(&uvfb_lock);
 
-	err = cn_netlink_send(m, 0, GFP_KERNEL);
+	err = cn_netlink_send(m, 0, 0, GFP_KERNEL);
 	if (err == -ESRCH) {
 		/*
 		 * Try to start the userspace helper if sending
@@ -204,7 +204,7 @@ static int uvesafb_exec(struct uvesafb_ktask *task)
 					"helper is installed and executable\n");
 		} else {
 			v86d_started = 1;
-			err = cn_netlink_send(m, 0, gfp_any());
+			err = cn_netlink_send(m, 0, 0, gfp_any());
 			if (err == -ENOBUFS)
 				err = 0;
 		}
diff --git a/drivers/w1/w1_netlink.c b/drivers/w1/w1_netlink.c
index 06d614af1166..b63109ada5a7 100644
--- a/drivers/w1/w1_netlink.c
+++ b/drivers/w1/w1_netlink.c
@@ -45,7 +45,7 @@ void w1_netlink_send(struct w1_master *dev, struct w1_netlink_msg *msg)
 
 	memcpy(w, msg, sizeof(struct w1_netlink_msg));
 
-	cn_netlink_send(m, 0, GFP_KERNEL);
+	cn_netlink_send(m, 0, 0, GFP_KERNEL);
 }
 
 static void w1_send_slave(struct w1_master *dev, u64 rn)
@@ -60,7 +60,7 @@ static void w1_send_slave(struct w1_master *dev, u64 rn)
 
 	if (avail < 8) {
 		msg->ack++;
-		cn_netlink_send(msg, 0, GFP_KERNEL);
+		cn_netlink_send(msg, 0, 0, GFP_KERNEL);
 
 		msg->len = sizeof(struct w1_netlink_msg) +
 			sizeof(struct w1_netlink_cmd);
@@ -131,7 +131,7 @@ static int w1_get_slaves(struct w1_master *dev,
 	}
 
 	msg->ack = 0;
-	cn_netlink_send(msg, 0, GFP_KERNEL);
+	cn_netlink_send(msg, 0, 0, GFP_KERNEL);
 
 	dev->priv = NULL;
 	dev->priv_size = 0;
@@ -173,7 +173,7 @@ static int w1_send_read_reply(struct cn_msg *msg, struct w1_netlink_msg *hdr,
 
 	memcpy(c->data, cmd->data, c->len);
 
-	err = cn_netlink_send(cm, 0, GFP_KERNEL);
+	err = cn_netlink_send(cm, 0, 0, GFP_KERNEL);
 
 	kfree(data);
 
@@ -316,7 +316,7 @@ static int w1_process_command_root(struct cn_msg *msg, struct w1_netlink_msg *mc
 	mutex_lock(&w1_mlock);
 	list_for_each_entry(m, &w1_masters, w1_master_entry) {
 		if (cn->len + sizeof(*id) > PAGE_SIZE - sizeof(struct cn_msg)) {
-			cn_netlink_send(cn, 0, GFP_KERNEL);
+			cn_netlink_send(cn, 0, 0, GFP_KERNEL);
 			cn->ack++;
 			cn->len = sizeof(struct w1_netlink_msg);
 			w->len = 0;
@@ -329,7 +329,7 @@ static int w1_process_command_root(struct cn_msg *msg, struct w1_netlink_msg *mc
 		id++;
 	}
 	cn->ack = 0;
-	cn_netlink_send(cn, 0, GFP_KERNEL);
+	cn_netlink_send(cn, 0, 0, GFP_KERNEL);
 	mutex_unlock(&w1_mlock);
 
 	kfree(cn);
@@ -364,7 +364,7 @@ static int w1_netlink_send_error(struct cn_msg *rcmsg, struct w1_netlink_msg *rm
 		cmsg->len += sizeof(*cmd);
 	}
 
-	error = cn_netlink_send(cmsg, 0, GFP_KERNEL);
+	error = cn_netlink_send(cmsg, 0, 0, GFP_KERNEL);
 	kfree(cmsg);
 
 	return error;
diff --git a/include/linux/connector.h b/include/linux/connector.h
index b2b5a41b6a24..be9c4747d511 100644
--- a/include/linux/connector.h
+++ b/include/linux/connector.h
@@ -71,7 +71,7 @@ struct cn_dev {
 int cn_add_callback(struct cb_id *id, const char *name,
 		    void (*callback)(struct cn_msg *, struct netlink_skb_parms *));
 void cn_del_callback(struct cb_id *);
-int cn_netlink_send(struct cn_msg *, u32, gfp_t);
+int cn_netlink_send(struct cn_msg *msg, u32 portid, u32 group, gfp_t gfp_mask);
 
 int cn_queue_add_callback(struct cn_queue_dev *dev, const char *name,
 			  struct cb_id *id,
-- 
cgit v1.2.3


From abd54f028ec30976d6e797e7474ec91d96186a0c Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 3 Feb 2014 14:02:55 -0500
Subject: kernfs: replace kernfs_node->u.completion with
 kernfs_root->deactivate_waitq

kernfs_node->u.completion is used to notify deactivation completion
from kernfs_put_active() to kernfs_deactivate().  We now allow
multiple racing removals of the same node and the current removal
scheme is no longer correct - kernfs_remove() invocation may return
before the node is properly deactivated if it races against another
removal.  The removal path will be restructured to address the issue.

To help such restructure which requires supporting multiple waiters,
this patch replaces kernfs_node->u.completion with
kernfs_root->deactivate_waitq.  This makes deactivation event
notifications share a per-root waitqueue_head; however, the wait path
is quite cold and this will also allow shaving one pointer off
kernfs_node.

v2: Refreshed on top of ("kernfs: make kernfs_deactivate() honor
    KERNFS_LOCKDEP flag").

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/dir.c        | 31 +++++++++++++------------------
 include/linux/kernfs.h |  4 ++--
 2 files changed, 15 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index bd6e18be6e1a..2193d30156ef 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -8,6 +8,7 @@
  * This file is released under the GPLv2.
  */
 
+#include <linux/sched.h>
 #include <linux/fs.h>
 #include <linux/namei.h>
 #include <linux/idr.h>
@@ -151,6 +152,7 @@ struct kernfs_node *kernfs_get_active(struct kernfs_node *kn)
  */
 void kernfs_put_active(struct kernfs_node *kn)
 {
+	struct kernfs_root *root = kernfs_root(kn);
 	int v;
 
 	if (unlikely(!kn))
@@ -162,11 +164,7 @@ void kernfs_put_active(struct kernfs_node *kn)
 	if (likely(v != KN_DEACTIVATED_BIAS))
 		return;
 
-	/*
-	 * atomic_dec_return() is a mb(), we'll always see the updated
-	 * kn->u.completion.
-	 */
-	complete(kn->u.completion);
+	wake_up_all(&root->deactivate_waitq);
 }
 
 /**
@@ -177,28 +175,24 @@ void kernfs_put_active(struct kernfs_node *kn)
  */
 static void kernfs_deactivate(struct kernfs_node *kn)
 {
-	DECLARE_COMPLETION_ONSTACK(wait);
-	int v;
+	struct kernfs_root *root = kernfs_root(kn);
 
 	BUG_ON(!(kn->flags & KERNFS_REMOVED));
 
 	if (!(kernfs_type(kn) & KERNFS_ACTIVE_REF))
 		return;
 
-	kn->u.completion = (void *)&wait;
-
 	if (kn->flags & KERNFS_LOCKDEP)
 		rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_);
-	/* atomic_add_return() is a mb(), put_active() will always see
-	 * the updated kn->u.completion.
-	 */
-	v = atomic_add_return(KN_DEACTIVATED_BIAS, &kn->active);
 
-	if (v != KN_DEACTIVATED_BIAS) {
-		if (kn->flags & KERNFS_LOCKDEP)
-			lock_contended(&kn->dep_map, _RET_IP_);
-		wait_for_completion(&wait);
-	}
+	atomic_add(KN_DEACTIVATED_BIAS, &kn->active);
+
+	if ((kn->flags & KERNFS_LOCKDEP) &&
+	    atomic_read(&kn->active) != KN_DEACTIVATED_BIAS)
+		lock_contended(&kn->dep_map, _RET_IP_);
+
+	wait_event(root->deactivate_waitq,
+		   atomic_read(&kn->active) == KN_DEACTIVATED_BIAS);
 
 	if (kn->flags & KERNFS_LOCKDEP) {
 		lock_acquired(&kn->dep_map, _RET_IP_);
@@ -630,6 +624,7 @@ struct kernfs_root *kernfs_create_root(struct kernfs_dir_ops *kdops, void *priv)
 
 	root->dir_ops = kdops;
 	root->kn = kn;
+	init_waitqueue_head(&root->deactivate_waitq);
 
 	return root;
 }
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 5be9f0228a3b..295a3bf642ba 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -15,7 +15,7 @@
 #include <linux/lockdep.h>
 #include <linux/rbtree.h>
 #include <linux/atomic.h>
-#include <linux/completion.h>
+#include <linux/wait.h>
 
 struct file;
 struct dentry;
@@ -92,7 +92,6 @@ struct kernfs_node {
 	struct rb_node		rb;
 
 	union {
-		struct completion	*completion;
 		struct kernfs_node	*removed_list;
 	} u;
 
@@ -133,6 +132,7 @@ struct kernfs_root {
 	/* private fields, do not use outside kernfs proper */
 	struct ida		ino_ida;
 	struct kernfs_dir_ops	*dir_ops;
+	wait_queue_head_t	deactivate_waitq;
 };
 
 struct kernfs_open_file {
-- 
cgit v1.2.3


From 988cd7afb3f37598891ca70b4c6eb914c338c46a Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 3 Feb 2014 14:02:58 -0500
Subject: kernfs: remove kernfs_addrm_cxt

kernfs_addrm_cxt and the accompanying kernfs_addrm_start/finish() were
added because there were operations which should be performed outside
kernfs_mutex after adding and removing kernfs_nodes.  The necessary
operations were recorded in kernfs_addrm_cxt and performed by
kernfs_addrm_finish(); however, after the recent changes which
relocated deactivation and unmapping so that they're performed
directly during removal, the only operation kernfs_addrm_finish()
performs is kernfs_put(), which can be moved inside the removal path
too.

This patch moves the kernfs_put() of the base ref to __kernfs_remove()
and remove kernfs_addrm_cxt and kernfs_addrm_start/finish().

* kernfs_add_one() is updated to grab and release kernfs_mutex itself.
  sysfs_addrm_start/finish() invocations around it are removed from
  all users.

* __kernfs_remove() puts an unlinked node directly instead of chaining
  it to kernfs_addrm_cxt.  Its callers are updated to grab and release
  kernfs_mutex instead of calling kernfs_addrm_start/finish() around
  it.

v2: Rebased on top of "kernfs: associate a new kernfs_node with its
    parent on creation" which dropped @parent from kernfs_add_one().

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/dir.c             | 109 ++++++++++----------------------------------
 fs/kernfs/file.c            |   6 +--
 fs/kernfs/kernfs-internal.h |  11 +----
 fs/kernfs/symlink.c         |   6 +--
 include/linux/kernfs.h      |   4 --
 5 files changed, 28 insertions(+), 108 deletions(-)

(limited to 'include/linux')

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 9603c06550a0..948551d222b4 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -395,70 +395,45 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
 	return kn;
 }
 
-/**
- *	kernfs_addrm_start - prepare for kernfs_node add/remove
- *	@acxt: pointer to kernfs_addrm_cxt to be used
- *
- *	This function is called when the caller is about to add or remove
- *	kernfs_node.  This function acquires kernfs_mutex.  @acxt is used
- *	to keep and pass context to other addrm functions.
- *
- *	LOCKING:
- *	Kernel thread context (may sleep).  kernfs_mutex is locked on
- *	return.
- */
-void kernfs_addrm_start(struct kernfs_addrm_cxt *acxt)
-	__acquires(kernfs_mutex)
-{
-	memset(acxt, 0, sizeof(*acxt));
-
-	mutex_lock(&kernfs_mutex);
-}
-
 /**
  *	kernfs_add_one - add kernfs_node to parent without warning
- *	@acxt: addrm context to use
  *	@kn: kernfs_node to be added
  *
  *	The caller must already have initialized @kn->parent.  This
  *	function increments nlink of the parent's inode if @kn is a
  *	directory and link into the children list of the parent.
  *
- *	This function should be called between calls to
- *	kernfs_addrm_start() and kernfs_addrm_finish() and should be passed
- *	the same @acxt as passed to kernfs_addrm_start().
- *
- *	LOCKING:
- *	Determined by kernfs_addrm_start().
- *
  *	RETURNS:
  *	0 on success, -EEXIST if entry with the given name already
  *	exists.
  */
-int kernfs_add_one(struct kernfs_addrm_cxt *acxt, struct kernfs_node *kn)
+int kernfs_add_one(struct kernfs_node *kn)
 {
 	struct kernfs_node *parent = kn->parent;
-	bool has_ns = kernfs_ns_enabled(parent);
 	struct kernfs_iattrs *ps_iattr;
+	bool has_ns;
 	int ret;
 
-	if (has_ns != (bool)kn->ns) {
-		WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n",
-		     has_ns ? "required" : "invalid", parent->name, kn->name);
-		return -EINVAL;
-	}
+	mutex_lock(&kernfs_mutex);
+
+	ret = -EINVAL;
+	has_ns = kernfs_ns_enabled(parent);
+	if (WARN(has_ns != (bool)kn->ns, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n",
+		 has_ns ? "required" : "invalid", parent->name, kn->name))
+		goto out_unlock;
 
 	if (kernfs_type(parent) != KERNFS_DIR)
-		return -EINVAL;
+		goto out_unlock;
 
+	ret = -ENOENT;
 	if (parent->flags & KERNFS_REMOVED)
-		return -ENOENT;
+		goto out_unlock;
 
 	kn->hash = kernfs_name_hash(kn->name, kn->ns);
 
 	ret = kernfs_link_sibling(kn);
 	if (ret)
-		return ret;
+		goto out_unlock;
 
 	/* Update timestamps on the parent */
 	ps_iattr = parent->iattr;
@@ -469,35 +444,10 @@ int kernfs_add_one(struct kernfs_addrm_cxt *acxt, struct kernfs_node *kn)
 
 	/* Mark the entry added into directory tree */
 	kn->flags &= ~KERNFS_REMOVED;
-
-	return 0;
-}
-
-/**
- *	kernfs_addrm_finish - finish up kernfs_node add/remove
- *	@acxt: addrm context to finish up
- *
- *	Finish up kernfs_node add/remove.  Resources acquired by
- *	kernfs_addrm_start() are released and removed kernfs_nodes are
- *	cleaned up.
- *
- *	LOCKING:
- *	kernfs_mutex is released.
- */
-void kernfs_addrm_finish(struct kernfs_addrm_cxt *acxt)
-	__releases(kernfs_mutex)
-{
-	/* release resources acquired by kernfs_addrm_start() */
+	ret = 0;
+out_unlock:
 	mutex_unlock(&kernfs_mutex);
-
-	/* kill removed kernfs_nodes */
-	while (acxt->removed) {
-		struct kernfs_node *kn = acxt->removed;
-
-		acxt->removed = kn->u.removed_list;
-
-		kernfs_put(kn);
-	}
+	return ret;
 }
 
 /**
@@ -630,7 +580,6 @@ struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
 					 const char *name, umode_t mode,
 					 void *priv, const void *ns)
 {
-	struct kernfs_addrm_cxt acxt;
 	struct kernfs_node *kn;
 	int rc;
 
@@ -644,10 +593,7 @@ struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
 	kn->priv = priv;
 
 	/* link in */
-	kernfs_addrm_start(&acxt);
-	rc = kernfs_add_one(&acxt, kn);
-	kernfs_addrm_finish(&acxt);
-
+	rc = kernfs_add_one(kn);
 	if (!rc)
 		return kn;
 
@@ -800,8 +746,7 @@ static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos,
 	return pos->parent;
 }
 
-static void __kernfs_remove(struct kernfs_addrm_cxt *acxt,
-			    struct kernfs_node *kn)
+static void __kernfs_remove(struct kernfs_node *kn)
 {
 	struct kernfs_node *pos;
 
@@ -845,8 +790,7 @@ static void __kernfs_remove(struct kernfs_addrm_cxt *acxt,
 				ps_iattr->ia_iattr.ia_mtime = CURRENT_TIME;
 			}
 
-			pos->u.removed_list = acxt->removed;
-			acxt->removed = pos;
+			kernfs_put(pos);
 		}
 
 		kernfs_put(pos);
@@ -861,11 +805,9 @@ static void __kernfs_remove(struct kernfs_addrm_cxt *acxt,
  */
 void kernfs_remove(struct kernfs_node *kn)
 {
-	struct kernfs_addrm_cxt acxt;
-
-	kernfs_addrm_start(&acxt);
-	__kernfs_remove(&acxt, kn);
-	kernfs_addrm_finish(&acxt);
+	mutex_lock(&kernfs_mutex);
+	__kernfs_remove(kn);
+	mutex_unlock(&kernfs_mutex);
 }
 
 /**
@@ -880,7 +822,6 @@ void kernfs_remove(struct kernfs_node *kn)
 int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
 			     const void *ns)
 {
-	struct kernfs_addrm_cxt acxt;
 	struct kernfs_node *kn;
 
 	if (!parent) {
@@ -889,13 +830,13 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
 		return -ENOENT;
 	}
 
-	kernfs_addrm_start(&acxt);
+	mutex_lock(&kernfs_mutex);
 
 	kn = kernfs_find_ns(parent, name, ns);
 	if (kn)
-		__kernfs_remove(&acxt, kn);
+		__kernfs_remove(kn);
 
-	kernfs_addrm_finish(&acxt);
+	mutex_unlock(&kernfs_mutex);
 
 	if (kn)
 		return 0;
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index dbf397bfdff2..10a8c91c49d6 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -820,7 +820,6 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
 					 bool name_is_static,
 					 struct lock_class_key *key)
 {
-	struct kernfs_addrm_cxt acxt;
 	struct kernfs_node *kn;
 	unsigned flags;
 	int rc;
@@ -855,10 +854,7 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
 	if (ops->mmap)
 		kn->flags |= KERNFS_HAS_MMAP;
 
-	kernfs_addrm_start(&acxt);
-	rc = kernfs_add_one(&acxt, kn);
-	kernfs_addrm_finish(&acxt);
-
+	rc = kernfs_add_one(kn);
 	if (rc) {
 		kernfs_put(kn);
 		return ERR_PTR(rc);
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index eb536b76374a..46b58de794d6 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -44,13 +44,6 @@ static inline struct kernfs_root *kernfs_root(struct kernfs_node *kn)
 	return kn->dir.root;
 }
 
-/*
- * Context structure to be used while adding/removing nodes.
- */
-struct kernfs_addrm_cxt {
-	struct kernfs_node	*removed;
-};
-
 /*
  * mount.c
  */
@@ -100,9 +93,7 @@ extern const struct inode_operations kernfs_dir_iops;
 
 struct kernfs_node *kernfs_get_active(struct kernfs_node *kn);
 void kernfs_put_active(struct kernfs_node *kn);
-void kernfs_addrm_start(struct kernfs_addrm_cxt *acxt);
-int kernfs_add_one(struct kernfs_addrm_cxt *acxt, struct kernfs_node *kn);
-void kernfs_addrm_finish(struct kernfs_addrm_cxt *acxt);
+int kernfs_add_one(struct kernfs_node *kn);
 struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
 				    const char *name, umode_t mode,
 				    unsigned flags);
diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c
index 4d457055acb9..8a198898e39a 100644
--- a/fs/kernfs/symlink.c
+++ b/fs/kernfs/symlink.c
@@ -27,7 +27,6 @@ struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
 				       struct kernfs_node *target)
 {
 	struct kernfs_node *kn;
-	struct kernfs_addrm_cxt acxt;
 	int error;
 
 	kn = kernfs_new_node(parent, name, S_IFLNK|S_IRWXUGO, KERNFS_LINK);
@@ -39,10 +38,7 @@ struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
 	kn->symlink.target_kn = target;
 	kernfs_get(target);	/* ref owned by symlink */
 
-	kernfs_addrm_start(&acxt);
-	error = kernfs_add_one(&acxt, kn);
-	kernfs_addrm_finish(&acxt);
-
+	error = kernfs_add_one(kn);
 	if (!error)
 		return kn;
 
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 295a3bf642ba..38646f6096bc 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -91,10 +91,6 @@ struct kernfs_node {
 
 	struct rb_node		rb;
 
-	union {
-		struct kernfs_node	*removed_list;
-	} u;
-
 	const void		*ns;	/* namespace tag */
 	unsigned int		hash;	/* ns + name hash */
 	union {
-- 
cgit v1.2.3


From 182fd64b66342219d6fcf2b84d337529d120d95c Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 3 Feb 2014 14:02:59 -0500
Subject: kernfs: remove KERNFS_ACTIVE_REF and add kernfs_lockdep()

There currently are two mechanisms gating active ref lockdep
annotations - KERNFS_LOCKDEP flag and KERNFS_ACTIVE_REF type mask.
The former disables lockdep annotations in kernfs_get/put_active()
while the latter disables all of kernfs_deactivate().

While KERNFS_ACTIVE_REF also behaves as an optimization to skip the
deactivation step for non-file nodes, the benefit is marginal and it
needlessly diverges code paths.  Let's drop KERNFS_ACTIVE_REF.

While at it, add a test helper kernfs_lockdep() to test KERNFS_LOCKDEP
flag so that it's more convenient and the related code can be compiled
out when not enabled.

v2: Refreshed on top of ("kernfs: make kernfs_deactivate() honor
    KERNFS_LOCKDEP flag").  As the earlier patch already added
    KERNFS_LOCKDEP tests to kernfs_deactivate(), those additions are
    dropped from this patch and the existing ones are simply converted
    to kernfs_lockdep().

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/dir.c        | 20 +++++++++++++-------
 include/linux/kernfs.h |  1 -
 2 files changed, 13 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 948551d222b4..5cf137b63db9 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -22,6 +22,15 @@ DEFINE_MUTEX(kernfs_mutex);
 
 #define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb)
 
+static bool kernfs_lockdep(struct kernfs_node *kn)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	return kn->flags & KERNFS_LOCKDEP;
+#else
+	return false;
+#endif
+}
+
 /**
  *	kernfs_name_hash
  *	@name: Null terminated string to hash
@@ -144,7 +153,7 @@ struct kernfs_node *kernfs_get_active(struct kernfs_node *kn)
 	if (!atomic_inc_unless_negative(&kn->active))
 		return NULL;
 
-	if (kn->flags & KERNFS_LOCKDEP)
+	if (kernfs_lockdep(kn))
 		rwsem_acquire_read(&kn->dep_map, 0, 1, _RET_IP_);
 	return kn;
 }
@@ -164,7 +173,7 @@ void kernfs_put_active(struct kernfs_node *kn)
 	if (unlikely(!kn))
 		return;
 
-	if (kn->flags & KERNFS_LOCKDEP)
+	if (kernfs_lockdep(kn))
 		rwsem_release(&kn->dep_map, 1, _RET_IP_);
 	v = atomic_dec_return(&kn->active);
 	if (likely(v != KN_DEACTIVATED_BIAS))
@@ -190,16 +199,13 @@ static void kernfs_deactivate(struct kernfs_node *kn)
 	lockdep_assert_held(&kernfs_mutex);
 	BUG_ON(!(kn->flags & KERNFS_REMOVED));
 
-	if (!(kernfs_type(kn) & KERNFS_ACTIVE_REF))
-		return;
-
 	/* only the first invocation on @kn should deactivate it */
 	if (atomic_read(&kn->active) >= 0)
 		atomic_add(KN_DEACTIVATED_BIAS, &kn->active);
 
 	mutex_unlock(&kernfs_mutex);
 
-	if (kn->flags & KERNFS_LOCKDEP) {
+	if (kernfs_lockdep(kn)) {
 		rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_);
 		if (atomic_read(&kn->active) != KN_DEACTIVATED_BIAS)
 			lock_contended(&kn->dep_map, _RET_IP_);
@@ -209,7 +215,7 @@ static void kernfs_deactivate(struct kernfs_node *kn)
 	wait_event(root->deactivate_waitq,
 		   atomic_read(&kn->active) == KN_DEACTIVATED_BIAS);
 
-	if (kn->flags & KERNFS_LOCKDEP) {
+	if (kernfs_lockdep(kn)) {
 		lock_acquired(&kn->dep_map, _RET_IP_);
 		rwsem_release(&kn->dep_map, 1, _RET_IP_);
 	}
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 38646f6096bc..dc4cd6c04236 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -35,7 +35,6 @@ enum kernfs_node_type {
 };
 
 #define KERNFS_TYPE_MASK	0x000f
-#define KERNFS_ACTIVE_REF	KERNFS_FILE
 #define KERNFS_FLAG_MASK	~KERNFS_TYPE_MASK
 
 enum kernfs_node_flag {
-- 
cgit v1.2.3


From 81c173cb5e87fbb47ccd80630faefe39bbf68449 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 3 Feb 2014 14:03:00 -0500
Subject: kernfs: remove KERNFS_REMOVED

KERNFS_REMOVED is used to mark half-initialized and dying nodes so
that they don't show up in lookups and deny adding new nodes under or
renaming it; however, its role overlaps that of deactivation.

It's necessary to deny addition of new children while removal is in
progress; however, this role considerably intersects with deactivation
- KERNFS_REMOVED prevents new children while deactivation prevents new
file operations.  There's no reason to have them separate making
things more complex than necessary.

This patch removes KERNFS_REMOVED.

* Instead of KERNFS_REMOVED, each node now starts its life
  deactivated.  This means that we now use both atomic_add() and
  atomic_sub() on KN_DEACTIVATED_BIAS, which is INT_MIN.  The compiler
  generates an overflow warnings when negating INT_MIN as the negation
  can't be represented as a positive number.  Nothing is actually
  broken but let's bump BIAS by one to avoid the warnings for archs
  which negates the subtrahend..

* A new helper kernfs_active() which tests whether kn->active >= 0 is
  added for convenience and lockdep annotation.  All KERNFS_REMOVED
  tests are replaced with negated kernfs_active() tests.

* __kernfs_remove() is updated to deactivate, but not drain, all nodes
  in the subtree instead of setting KERNFS_REMOVED.  This removes
  deactivation from kernfs_deactivate(), which is now renamed to
  kernfs_drain().

* Sanity check on KERNFS_REMOVED in kernfs_put() is replaced with
  checks on the active ref.

* Some comment style updates in the affected area.

v2: Reordered before removal path restructuring.  kernfs_active()
    dropped and kernfs_get/put_active() used instead.  RB_EMPTY_NODE()
    used in the lookup paths.

v3: Reverted most of v2 except for creating a new node with
    KN_DEACTIVATED_BIAS.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/dir.c             | 66 ++++++++++++++++++++++++---------------------
 fs/kernfs/kernfs-internal.h |  3 ++-
 include/linux/kernfs.h      |  1 -
 3 files changed, 37 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 5cf137b63db9..d0fd739bf82d 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -22,6 +22,12 @@ DEFINE_MUTEX(kernfs_mutex);
 
 #define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb)
 
+static bool kernfs_active(struct kernfs_node *kn)
+{
+	lockdep_assert_held(&kernfs_mutex);
+	return atomic_read(&kn->active) >= 0;
+}
+
 static bool kernfs_lockdep(struct kernfs_node *kn)
 {
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -183,25 +189,20 @@ void kernfs_put_active(struct kernfs_node *kn)
 }
 
 /**
- *	kernfs_deactivate - deactivate kernfs_node
- *	@kn: kernfs_node to deactivate
+ * kernfs_drain - drain kernfs_node
+ * @kn: kernfs_node to drain
  *
- *	Deny new active references, drain existing ones and nuke all
- *	existing mmaps.  Mutiple removers may invoke this function
- *	concurrently on @kn and all will return after deactivation and
- *	draining are complete.
+ * Drain existing usages and nuke all existing mmaps of @kn.  Mutiple
+ * removers may invoke this function concurrently on @kn and all will
+ * return after draining is complete.
  */
-static void kernfs_deactivate(struct kernfs_node *kn)
+static void kernfs_drain(struct kernfs_node *kn)
 	__releases(&kernfs_mutex) __acquires(&kernfs_mutex)
 {
 	struct kernfs_root *root = kernfs_root(kn);
 
 	lockdep_assert_held(&kernfs_mutex);
-	BUG_ON(!(kn->flags & KERNFS_REMOVED));
-
-	/* only the first invocation on @kn should deactivate it */
-	if (atomic_read(&kn->active) >= 0)
-		atomic_add(KN_DEACTIVATED_BIAS, &kn->active);
+	WARN_ON_ONCE(kernfs_active(kn));
 
 	mutex_unlock(&kernfs_mutex);
 
@@ -253,13 +254,15 @@ void kernfs_put(struct kernfs_node *kn)
 		return;
 	root = kernfs_root(kn);
  repeat:
-	/* Moving/renaming is always done while holding reference.
+	/*
+	 * Moving/renaming is always done while holding reference.
 	 * kn->parent won't change beneath us.
 	 */
 	parent = kn->parent;
 
-	WARN(!(kn->flags & KERNFS_REMOVED), "kernfs: free using entry: %s/%s\n",
-	     parent ? parent->name : "", kn->name);
+	WARN_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS,
+		  "kernfs_put: %s/%s: released with incorrect active_ref %d\n",
+		  parent ? parent->name : "", kn->name, atomic_read(&kn->active));
 
 	if (kernfs_type(kn) == KERNFS_LINK)
 		kernfs_put(kn->symlink.target_kn);
@@ -301,8 +304,8 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
 	kn = dentry->d_fsdata;
 	mutex_lock(&kernfs_mutex);
 
-	/* The kernfs node has been deleted */
-	if (kn->flags & KERNFS_REMOVED)
+	/* The kernfs node has been deactivated */
+	if (!kernfs_active(kn))
 		goto out_bad;
 
 	/* The kernfs node has been moved? */
@@ -371,12 +374,12 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 	kn->ino = ret;
 
 	atomic_set(&kn->count, 1);
-	atomic_set(&kn->active, 0);
+	atomic_set(&kn->active, KN_DEACTIVATED_BIAS);
 	RB_CLEAR_NODE(&kn->rb);
 
 	kn->name = name;
 	kn->mode = mode;
-	kn->flags = flags | KERNFS_REMOVED;
+	kn->flags = flags;
 
 	return kn;
 
@@ -432,7 +435,7 @@ int kernfs_add_one(struct kernfs_node *kn)
 		goto out_unlock;
 
 	ret = -ENOENT;
-	if (parent->flags & KERNFS_REMOVED)
+	if (!kernfs_active(parent))
 		goto out_unlock;
 
 	kn->hash = kernfs_name_hash(kn->name, kn->ns);
@@ -449,7 +452,7 @@ int kernfs_add_one(struct kernfs_node *kn)
 	}
 
 	/* Mark the entry added into directory tree */
-	kn->flags &= ~KERNFS_REMOVED;
+	atomic_sub(KN_DEACTIVATED_BIAS, &kn->active);
 	ret = 0;
 out_unlock:
 	mutex_unlock(&kernfs_mutex);
@@ -549,7 +552,7 @@ struct kernfs_root *kernfs_create_root(struct kernfs_dir_ops *kdops, void *priv)
 		return ERR_PTR(-ENOMEM);
 	}
 
-	kn->flags &= ~KERNFS_REMOVED;
+	atomic_sub(KN_DEACTIVATED_BIAS, &kn->active);
 	kn->priv = priv;
 	kn->dir.root = root;
 
@@ -763,24 +766,25 @@ static void __kernfs_remove(struct kernfs_node *kn)
 
 	pr_debug("kernfs %s: removing\n", kn->name);
 
-	/* disable lookup and node creation under @kn */
+	/* prevent any new usage under @kn by deactivating all nodes */
 	pos = NULL;
 	while ((pos = kernfs_next_descendant_post(pos, kn)))
-		pos->flags |= KERNFS_REMOVED;
+		if (kernfs_active(pos))
+			atomic_add(KN_DEACTIVATED_BIAS, &pos->active);
 
 	/* deactivate and unlink the subtree node-by-node */
 	do {
 		pos = kernfs_leftmost_descendant(kn);
 
 		/*
-		 * kernfs_deactivate() drops kernfs_mutex temporarily and
-		 * @pos's base ref could have been put by someone else by
-		 * the time the function returns.  Make sure it doesn't go
-		 * away underneath us.
+		 * kernfs_drain() drops kernfs_mutex temporarily and @pos's
+		 * base ref could have been put by someone else by the time
+		 * the function returns.  Make sure it doesn't go away
+		 * underneath us.
 		 */
 		kernfs_get(pos);
 
-		kernfs_deactivate(pos);
+		kernfs_drain(pos);
 
 		/*
 		 * kernfs_unlink_sibling() succeeds once per node.  Use it
@@ -865,7 +869,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 	mutex_lock(&kernfs_mutex);
 
 	error = -ENOENT;
-	if ((kn->flags | new_parent->flags) & KERNFS_REMOVED)
+	if (!kernfs_active(kn) || !kernfs_active(new_parent))
 		goto out;
 
 	error = 0;
@@ -925,7 +929,7 @@ static struct kernfs_node *kernfs_dir_pos(const void *ns,
 	struct kernfs_node *parent, loff_t hash, struct kernfs_node *pos)
 {
 	if (pos) {
-		int valid = !(pos->flags & KERNFS_REMOVED) &&
+		int valid = kernfs_active(pos) &&
 			pos->parent == parent && hash == pos->hash;
 		kernfs_put(pos);
 		if (!valid)
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index 46b58de794d6..a91d7a1113d9 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -26,7 +26,8 @@ struct kernfs_iattrs {
 	struct simple_xattrs	xattrs;
 };
 
-#define KN_DEACTIVATED_BIAS		INT_MIN
+/* +1 to avoid triggering overflow warning when negating it */
+#define KN_DEACTIVATED_BIAS		(INT_MIN + 1)
 
 /* KERNFS_TYPE_MASK and types are defined in include/linux/kernfs.h */
 
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index dc4cd6c04236..917bc6c1eb04 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -38,7 +38,6 @@ enum kernfs_node_type {
 #define KERNFS_FLAG_MASK	~KERNFS_TYPE_MASK
 
 enum kernfs_node_flag {
-	KERNFS_REMOVED		= 0x0010,
 	KERNFS_NS		= 0x0020,
 	KERNFS_HAS_SEQ_SHOW	= 0x0040,
 	KERNFS_HAS_MMAP		= 0x0080,
-- 
cgit v1.2.3


From 6b0afc2a21726b2d6b6aa441af40cafaf5405cc8 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 3 Feb 2014 14:03:01 -0500
Subject: kernfs, sysfs, driver-core: implement kernfs_remove_self() and its
 wrappers

Sometimes it's necessary to implement a node which wants to delete
nodes including itself.  This isn't straightforward because of kernfs
active reference.  While a file operation is in progress, an active
reference is held and kernfs_remove() waits for all such references to
drain before completing.  For a self-deleting node, this is a deadlock
as kernfs_remove() ends up waiting for an active reference that itself
is sitting on top of.

This currently is worked around in the sysfs layer using
sysfs_schedule_callback() which makes such removals asynchronous.
While it works, it's rather cumbersome and inherently breaks
synchronicity of the operation - the file operation which triggered
the operation may complete before the removal is finished (or even
started) and the removal may fail asynchronously.  If a removal
operation is immmediately followed by another operation which expects
the specific name to be available (e.g. removal followed by rename
onto the same name), there's no way to make the latter operation
reliable.

The thing is there's no inherent reason for this to be asynchrnous.
All that's necessary to do this synchronous is a dedicated operation
which drops its own active ref and deactivates self.  This patch
implements kernfs_remove_self() and its wrappers in sysfs and driver
core.  kernfs_remove_self() is to be called from one of the file
operations, drops the active ref the task is holding, removes the self
node, and restores active ref to the dead node so that the ref is
balanced afterwards.  __kernfs_remove() is updated so that it takes an
early exit if the target node is already fully removed so that the
active ref restored by kernfs_remove_self() after removal doesn't
confuse the deactivation path.

This makes implementing self-deleting nodes very easy.  The normal
removal path doesn't even need to be changed to use
kernfs_remove_self() for the self-deleting node.  The method can
invoke kernfs_remove_self() on itself before proceeding the normal
removal path.  kernfs_remove() invoked on the node by the normal
deletion path will simply be ignored.

This will replace sysfs_schedule_callback().  A subtle feature of
sysfs_schedule_callback() is that it collapses multiple invocations -
even if multiple removals are triggered, the removal callback is run
only once.  An equivalent effect can be achieved by testing the return
value of kernfs_remove_self() - only the one which gets %true return
value should proceed with actual deletion.  All other instances of
kernfs_remove_self() will wait till the enclosing kernfs operation
which invoked the winning instance of kernfs_remove_self() finishes
and then return %false.  This trivially makes all users of
kernfs_remove_self() automatically show correct synchronous behavior
even when there are multiple concurrent operations - all "echo 1 >
delete" instances will finish only after the whole operation is
completed by one of the instances.

Note that manipulation of active ref is implemented in separate public
functions - kernfs_[un]break_active_protection().
kernfs_remove_self() is the only user at the moment but this will be
used to cater to more complex cases.

v2: For !CONFIG_SYSFS, dummy version kernfs_remove_self() was missing
    and sysfs_remove_file_self() had incorrect return type.  Fix it.
    Reported by kbuild test bot.

v3: kernfs_[un]break_active_protection() separated out from
    kernfs_remove_self() and exposed as public API.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c    |  17 ++++++
 fs/kernfs/dir.c        | 138 ++++++++++++++++++++++++++++++++++++++++++++++++-
 fs/sysfs/file.c        |  23 +++++++++
 include/linux/device.h |   2 +
 include/linux/kernfs.h |   8 +++
 include/linux/sysfs.h  |   7 +++
 6 files changed, 194 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 2b567177ef78..9db57afcf81f 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -570,6 +570,23 @@ void device_remove_file(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(device_remove_file);
 
+/**
+ * device_remove_file_self - remove sysfs attribute file from its own method.
+ * @dev: device.
+ * @attr: device attribute descriptor.
+ *
+ * See kernfs_remove_self() for details.
+ */
+bool device_remove_file_self(struct device *dev,
+			     const struct device_attribute *attr)
+{
+	if (dev)
+		return sysfs_remove_file_self(&dev->kobj, &attr->attr);
+	else
+		return false;
+}
+EXPORT_SYMBOL_GPL(device_remove_file_self);
+
 /**
  * device_create_bin_file - create sysfs binary attribute file for device.
  * @dev: device.
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index d0fd739bf82d..8c63ae1bccb6 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -761,7 +761,12 @@ static void __kernfs_remove(struct kernfs_node *kn)
 
 	lockdep_assert_held(&kernfs_mutex);
 
-	if (!kn)
+	/*
+	 * Short-circuit if non-root @kn has already finished removal.
+	 * This is for kernfs_remove_self() which plays with active ref
+	 * after removal.
+	 */
+	if (!kn || (kn->parent && RB_EMPTY_NODE(&kn->rb)))
 		return;
 
 	pr_debug("kernfs %s: removing\n", kn->name);
@@ -820,6 +825,137 @@ void kernfs_remove(struct kernfs_node *kn)
 	mutex_unlock(&kernfs_mutex);
 }
 
+/**
+ * kernfs_break_active_protection - break out of active protection
+ * @kn: the self kernfs_node
+ *
+ * The caller must be running off of a kernfs operation which is invoked
+ * with an active reference - e.g. one of kernfs_ops.  Each invocation of
+ * this function must also be matched with an invocation of
+ * kernfs_unbreak_active_protection().
+ *
+ * This function releases the active reference of @kn the caller is
+ * holding.  Once this function is called, @kn may be removed at any point
+ * and the caller is solely responsible for ensuring that the objects it
+ * dereferences are accessible.
+ */
+void kernfs_break_active_protection(struct kernfs_node *kn)
+{
+	/*
+	 * Take out ourself out of the active ref dependency chain.  If
+	 * we're called without an active ref, lockdep will complain.
+	 */
+	kernfs_put_active(kn);
+}
+
+/**
+ * kernfs_unbreak_active_protection - undo kernfs_break_active_protection()
+ * @kn: the self kernfs_node
+ *
+ * If kernfs_break_active_protection() was called, this function must be
+ * invoked before finishing the kernfs operation.  Note that while this
+ * function restores the active reference, it doesn't and can't actually
+ * restore the active protection - @kn may already or be in the process of
+ * being removed.  Once kernfs_break_active_protection() is invoked, that
+ * protection is irreversibly gone for the kernfs operation instance.
+ *
+ * While this function may be called at any point after
+ * kernfs_break_active_protection() is invoked, its most useful location
+ * would be right before the enclosing kernfs operation returns.
+ */
+void kernfs_unbreak_active_protection(struct kernfs_node *kn)
+{
+	/*
+	 * @kn->active could be in any state; however, the increment we do
+	 * here will be undone as soon as the enclosing kernfs operation
+	 * finishes and this temporary bump can't break anything.  If @kn
+	 * is alive, nothing changes.  If @kn is being deactivated, the
+	 * soon-to-follow put will either finish deactivation or restore
+	 * deactivated state.  If @kn is already removed, the temporary
+	 * bump is guaranteed to be gone before @kn is released.
+	 */
+	atomic_inc(&kn->active);
+	if (kernfs_lockdep(kn))
+		rwsem_acquire(&kn->dep_map, 0, 1, _RET_IP_);
+}
+
+/**
+ * kernfs_remove_self - remove a kernfs_node from its own method
+ * @kn: the self kernfs_node to remove
+ *
+ * The caller must be running off of a kernfs operation which is invoked
+ * with an active reference - e.g. one of kernfs_ops.  This can be used to
+ * implement a file operation which deletes itself.
+ *
+ * For example, the "delete" file for a sysfs device directory can be
+ * implemented by invoking kernfs_remove_self() on the "delete" file
+ * itself.  This function breaks the circular dependency of trying to
+ * deactivate self while holding an active ref itself.  It isn't necessary
+ * to modify the usual removal path to use kernfs_remove_self().  The
+ * "delete" implementation can simply invoke kernfs_remove_self() on self
+ * before proceeding with the usual removal path.  kernfs will ignore later
+ * kernfs_remove() on self.
+ *
+ * kernfs_remove_self() can be called multiple times concurrently on the
+ * same kernfs_node.  Only the first one actually performs removal and
+ * returns %true.  All others will wait until the kernfs operation which
+ * won self-removal finishes and return %false.  Note that the losers wait
+ * for the completion of not only the winning kernfs_remove_self() but also
+ * the whole kernfs_ops which won the arbitration.  This can be used to
+ * guarantee, for example, all concurrent writes to a "delete" file to
+ * finish only after the whole operation is complete.
+ */
+bool kernfs_remove_self(struct kernfs_node *kn)
+{
+	bool ret;
+
+	mutex_lock(&kernfs_mutex);
+	kernfs_break_active_protection(kn);
+
+	/*
+	 * SUICIDAL is used to arbitrate among competing invocations.  Only
+	 * the first one will actually perform removal.  When the removal
+	 * is complete, SUICIDED is set and the active ref is restored
+	 * while holding kernfs_mutex.  The ones which lost arbitration
+	 * waits for SUICDED && drained which can happen only after the
+	 * enclosing kernfs operation which executed the winning instance
+	 * of kernfs_remove_self() finished.
+	 */
+	if (!(kn->flags & KERNFS_SUICIDAL)) {
+		kn->flags |= KERNFS_SUICIDAL;
+		__kernfs_remove(kn);
+		kn->flags |= KERNFS_SUICIDED;
+		ret = true;
+	} else {
+		wait_queue_head_t *waitq = &kernfs_root(kn)->deactivate_waitq;
+		DEFINE_WAIT(wait);
+
+		while (true) {
+			prepare_to_wait(waitq, &wait, TASK_UNINTERRUPTIBLE);
+
+			if ((kn->flags & KERNFS_SUICIDED) &&
+			    atomic_read(&kn->active) == KN_DEACTIVATED_BIAS)
+				break;
+
+			mutex_unlock(&kernfs_mutex);
+			schedule();
+			mutex_lock(&kernfs_mutex);
+		}
+		finish_wait(waitq, &wait);
+		WARN_ON_ONCE(!RB_EMPTY_NODE(&kn->rb));
+		ret = false;
+	}
+
+	/*
+	 * This must be done while holding kernfs_mutex; otherwise, waiting
+	 * for SUICIDED && deactivated could finish prematurely.
+	 */
+	kernfs_unbreak_active_protection(kn);
+
+	mutex_unlock(&kernfs_mutex);
+	return ret;
+}
+
 /**
  * kernfs_remove_by_name_ns - find a kernfs_node by name and remove it
  * @parent: parent of the target
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 810cf6e613e5..1b8b91b67fdb 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -372,6 +372,29 @@ void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr,
 }
 EXPORT_SYMBOL_GPL(sysfs_remove_file_ns);
 
+/**
+ * sysfs_remove_file_self - remove an object attribute from its own method
+ * @kobj: object we're acting for
+ * @attr: attribute descriptor
+ *
+ * See kernfs_remove_self() for details.
+ */
+bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr)
+{
+	struct kernfs_node *parent = kobj->sd;
+	struct kernfs_node *kn;
+	bool ret;
+
+	kn = kernfs_find_and_get(parent, attr->name);
+	if (WARN_ON_ONCE(!kn))
+		return false;
+
+	ret = kernfs_remove_self(kn);
+
+	kernfs_put(kn);
+	return ret;
+}
+
 void sysfs_remove_files(struct kobject *kobj, const struct attribute **ptr)
 {
 	int i;
diff --git a/include/linux/device.h b/include/linux/device.h
index 952b01033c32..1ff3f1697513 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -560,6 +560,8 @@ extern int device_create_file(struct device *device,
 			      const struct device_attribute *entry);
 extern void device_remove_file(struct device *dev,
 			       const struct device_attribute *attr);
+extern bool device_remove_file_self(struct device *dev,
+				    const struct device_attribute *attr);
 extern int __must_check device_create_bin_file(struct device *dev,
 					const struct bin_attribute *attr);
 extern void device_remove_bin_file(struct device *dev,
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 917bc6c1eb04..02ac33435808 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -43,6 +43,8 @@ enum kernfs_node_flag {
 	KERNFS_HAS_MMAP		= 0x0080,
 	KERNFS_LOCKDEP		= 0x0100,
 	KERNFS_STATIC_NAME	= 0x0200,
+	KERNFS_SUICIDAL		= 0x0400,
+	KERNFS_SUICIDED		= 0x0800,
 };
 
 /* type-specific structures for kernfs_node union members */
@@ -234,6 +236,9 @@ struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
 				       const char *name,
 				       struct kernfs_node *target);
 void kernfs_remove(struct kernfs_node *kn);
+void kernfs_break_active_protection(struct kernfs_node *kn);
+void kernfs_unbreak_active_protection(struct kernfs_node *kn);
+bool kernfs_remove_self(struct kernfs_node *kn);
 int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
 			     const void *ns);
 int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
@@ -291,6 +296,9 @@ kernfs_create_link(struct kernfs_node *parent, const char *name,
 
 static inline void kernfs_remove(struct kernfs_node *kn) { }
 
+static inline bool kernfs_remove_self(struct kernfs_node *kn)
+{ return false; }
+
 static inline int kernfs_remove_by_name_ns(struct kernfs_node *kn,
 					   const char *name, const void *ns)
 { return -ENOSYS; }
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index 30b2ebee6439..bd96c603ab6c 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -198,6 +198,7 @@ int __must_check sysfs_chmod_file(struct kobject *kobj,
 				  const struct attribute *attr, umode_t mode);
 void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr,
 			  const void *ns);
+bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr);
 void sysfs_remove_files(struct kobject *kobj, const struct attribute **attr);
 
 int __must_check sysfs_create_bin_file(struct kobject *kobj,
@@ -301,6 +302,12 @@ static inline void sysfs_remove_file_ns(struct kobject *kobj,
 {
 }
 
+static inline bool sysfs_remove_file_self(struct kobject *kobj,
+					  const struct attribute *attr)
+{
+	return false;
+}
+
 static inline void sysfs_remove_files(struct kobject *kobj,
 				     const struct attribute **attr)
 {
-- 
cgit v1.2.3


From ce8b04aa6c9bdf211b921fdd18c040ea29516b97 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 3 Feb 2014 14:03:05 -0500
Subject: sysfs, driver-core: remove unused
 {sysfs|device}_schedule_callback_owner()

All device_schedule_callback_owner() users are converted to use
device_remove_file_self().  Remove now unused
{sysfs|device}_schedule_callback_owner().

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c    | 33 ------------------
 fs/sysfs/file.c        | 92 --------------------------------------------------
 include/linux/device.h | 11 +-----
 include/linux/sysfs.h  |  9 -----
 4 files changed, 1 insertion(+), 144 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 9db57afcf81f..4195364f9fdd 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -615,39 +615,6 @@ void device_remove_bin_file(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(device_remove_bin_file);
 
-/**
- * device_schedule_callback_owner - helper to schedule a callback for a device
- * @dev: device.
- * @func: callback function to invoke later.
- * @owner: module owning the callback routine
- *
- * Attribute methods must not unregister themselves or their parent device
- * (which would amount to the same thing).  Attempts to do so will deadlock,
- * since unregistration is mutually exclusive with driver callbacks.
- *
- * Instead methods can call this routine, which will attempt to allocate
- * and schedule a workqueue request to call back @func with @dev as its
- * argument in the workqueue's process context.  @dev will be pinned until
- * @func returns.
- *
- * This routine is usually called via the inline device_schedule_callback(),
- * which automatically sets @owner to THIS_MODULE.
- *
- * Returns 0 if the request was submitted, -ENOMEM if storage could not
- * be allocated, -ENODEV if a reference to @owner isn't available.
- *
- * NOTE: This routine won't work if CONFIG_SYSFS isn't set!  It uses an
- * underlying sysfs routine (since it is intended for use by attribute
- * methods), and if sysfs isn't available you'll get nothing but -ENOSYS.
- */
-int device_schedule_callback_owner(struct device *dev,
-		void (*func)(struct device *), struct module *owner)
-{
-	return sysfs_schedule_callback(&dev->kobj,
-			(void (*)(void *)) func, dev, owner);
-}
-EXPORT_SYMBOL_GPL(device_schedule_callback_owner);
-
 static void klist_children_get(struct klist_node *n)
 {
 	struct device_private *p = to_device_private_parent(n);
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 1b8b91b67fdb..28cc1acd5439 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -453,95 +453,3 @@ void sysfs_remove_bin_file(struct kobject *kobj,
 	kernfs_remove_by_name(kobj->sd, attr->attr.name);
 }
 EXPORT_SYMBOL_GPL(sysfs_remove_bin_file);
-
-struct sysfs_schedule_callback_struct {
-	struct list_head	workq_list;
-	struct kobject		*kobj;
-	void			(*func)(void *);
-	void			*data;
-	struct module		*owner;
-	struct work_struct	work;
-};
-
-static struct workqueue_struct *sysfs_workqueue;
-static DEFINE_MUTEX(sysfs_workq_mutex);
-static LIST_HEAD(sysfs_workq);
-static void sysfs_schedule_callback_work(struct work_struct *work)
-{
-	struct sysfs_schedule_callback_struct *ss = container_of(work,
-			struct sysfs_schedule_callback_struct, work);
-
-	(ss->func)(ss->data);
-	kobject_put(ss->kobj);
-	module_put(ss->owner);
-	mutex_lock(&sysfs_workq_mutex);
-	list_del(&ss->workq_list);
-	mutex_unlock(&sysfs_workq_mutex);
-	kfree(ss);
-}
-
-/**
- * sysfs_schedule_callback - helper to schedule a callback for a kobject
- * @kobj: object we're acting for.
- * @func: callback function to invoke later.
- * @data: argument to pass to @func.
- * @owner: module owning the callback code
- *
- * sysfs attribute methods must not unregister themselves or their parent
- * kobject (which would amount to the same thing).  Attempts to do so will
- * deadlock, since unregistration is mutually exclusive with driver
- * callbacks.
- *
- * Instead methods can call this routine, which will attempt to allocate
- * and schedule a workqueue request to call back @func with @data as its
- * argument in the workqueue's process context.  @kobj will be pinned
- * until @func returns.
- *
- * Returns 0 if the request was submitted, -ENOMEM if storage could not
- * be allocated, -ENODEV if a reference to @owner isn't available,
- * -EAGAIN if a callback has already been scheduled for @kobj.
- */
-int sysfs_schedule_callback(struct kobject *kobj, void (*func)(void *),
-		void *data, struct module *owner)
-{
-	struct sysfs_schedule_callback_struct *ss, *tmp;
-
-	if (!try_module_get(owner))
-		return -ENODEV;
-
-	mutex_lock(&sysfs_workq_mutex);
-	list_for_each_entry_safe(ss, tmp, &sysfs_workq, workq_list)
-		if (ss->kobj == kobj) {
-			module_put(owner);
-			mutex_unlock(&sysfs_workq_mutex);
-			return -EAGAIN;
-		}
-	mutex_unlock(&sysfs_workq_mutex);
-
-	if (sysfs_workqueue == NULL) {
-		sysfs_workqueue = create_singlethread_workqueue("sysfsd");
-		if (sysfs_workqueue == NULL) {
-			module_put(owner);
-			return -ENOMEM;
-		}
-	}
-
-	ss = kmalloc(sizeof(*ss), GFP_KERNEL);
-	if (!ss) {
-		module_put(owner);
-		return -ENOMEM;
-	}
-	kobject_get(kobj);
-	ss->kobj = kobj;
-	ss->func = func;
-	ss->data = data;
-	ss->owner = owner;
-	INIT_WORK(&ss->work, sysfs_schedule_callback_work);
-	INIT_LIST_HEAD(&ss->workq_list);
-	mutex_lock(&sysfs_workq_mutex);
-	list_add_tail(&ss->workq_list, &sysfs_workq);
-	mutex_unlock(&sysfs_workq_mutex);
-	queue_work(sysfs_workqueue, &ss->work);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(sysfs_schedule_callback);
diff --git a/include/linux/device.h b/include/linux/device.h
index 1ff3f1697513..fb1ba13f7665 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -566,12 +566,6 @@ extern int __must_check device_create_bin_file(struct device *dev,
 					const struct bin_attribute *attr);
 extern void device_remove_bin_file(struct device *dev,
 				   const struct bin_attribute *attr);
-extern int device_schedule_callback_owner(struct device *dev,
-		void (*func)(struct device *dev), struct module *owner);
-
-/* This is a macro to avoid include problems with THIS_MODULE */
-#define device_schedule_callback(dev, func)			\
-	device_schedule_callback_owner(dev, func, THIS_MODULE)
 
 /* device resource management */
 typedef void (*dr_release_t)(struct device *dev, void *res);
@@ -931,10 +925,7 @@ extern int device_online(struct device *dev);
 extern struct device *__root_device_register(const char *name,
 					     struct module *owner);
 
-/*
- * This is a macro to avoid include problems with THIS_MODULE,
- * just as per what is done for device_schedule_callback() above.
- */
+/* This is a macro to avoid include problems with THIS_MODULE */
 #define root_device_register(name) \
 	__root_device_register(name, THIS_MODULE)
 
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index bd96c603ab6c..14df05415af9 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -178,9 +178,6 @@ struct sysfs_ops {
 
 #ifdef CONFIG_SYSFS
 
-int sysfs_schedule_callback(struct kobject *kobj, void (*func)(void *),
-			    void *data, struct module *owner);
-
 int __must_check sysfs_create_dir_ns(struct kobject *kobj, const void *ns);
 void sysfs_remove_dir(struct kobject *kobj);
 int __must_check sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name,
@@ -249,12 +246,6 @@ int __must_check sysfs_init(void);
 
 #else /* CONFIG_SYSFS */
 
-static inline int sysfs_schedule_callback(struct kobject *kobj,
-		void (*func)(void *), void *data, struct module *owner)
-{
-	return -ENOSYS;
-}
-
 static inline int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
 {
 	return 0;
-- 
cgit v1.2.3


From 07c7530dd46728e25e938d0eb291f8085435c365 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 3 Feb 2014 14:09:08 -0500
Subject: kernfs: invoke dir_ops while holding active ref of the target node

kernfs_dir_ops are currently being invoked without any active
reference, which makes it tricky for the invoked operations to
determine whether the objects associated those nodes are safe to
access and will remain that way for the duration of such operations.

kernfs already has active_ref mechanism to deal with this which makes
the removal of a given node the synchronization point for gating the
file operations.  There's no reason for dir_ops to be any different.
Update the dir_ops handling so that active_ref is held while the
dir_ops are executing.  This guarantees that while a dir_ops is
executing the target nodes stay alive.

As kernfs_dir_ops doesn't have any in-kernel user at this point, this
doesn't affect anybody.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/dir.c        | 33 ++++++++++++++++++++++++++++++---
 include/linux/kernfs.h |  3 ++-
 2 files changed, 32 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 8c63ae1bccb6..bfbfb48f4ad8 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -654,22 +654,36 @@ static int kernfs_iop_mkdir(struct inode *dir, struct dentry *dentry,
 {
 	struct kernfs_node *parent = dir->i_private;
 	struct kernfs_dir_ops *kdops = kernfs_root(parent)->dir_ops;
+	int ret;
 
 	if (!kdops || !kdops->mkdir)
 		return -EPERM;
 
-	return kdops->mkdir(parent, dentry->d_name.name, mode);
+	if (!kernfs_get_active(parent))
+		return -ENODEV;
+
+	ret = kdops->mkdir(parent, dentry->d_name.name, mode);
+
+	kernfs_put_active(parent);
+	return ret;
 }
 
 static int kernfs_iop_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	struct kernfs_node *kn  = dentry->d_fsdata;
 	struct kernfs_dir_ops *kdops = kernfs_root(kn)->dir_ops;
+	int ret;
 
 	if (!kdops || !kdops->rmdir)
 		return -EPERM;
 
-	return kdops->rmdir(kn);
+	if (!kernfs_get_active(kn))
+		return -ENODEV;
+
+	ret = kdops->rmdir(kn);
+
+	kernfs_put_active(kn);
+	return ret;
 }
 
 static int kernfs_iop_rename(struct inode *old_dir, struct dentry *old_dentry,
@@ -678,11 +692,24 @@ static int kernfs_iop_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct kernfs_node *kn  = old_dentry->d_fsdata;
 	struct kernfs_node *new_parent = new_dir->i_private;
 	struct kernfs_dir_ops *kdops = kernfs_root(kn)->dir_ops;
+	int ret;
 
 	if (!kdops || !kdops->rename)
 		return -EPERM;
 
-	return kdops->rename(kn, new_parent, new_dentry->d_name.name);
+	if (!kernfs_get_active(kn))
+		return -ENODEV;
+
+	if (!kernfs_get_active(new_parent)) {
+		kernfs_put_active(kn);
+		return -ENODEV;
+	}
+
+	ret = kdops->rename(kn, new_parent, new_dentry->d_name.name);
+
+	kernfs_put_active(new_parent);
+	kernfs_put_active(kn);
+	return ret;
 }
 
 const struct inode_operations kernfs_dir_iops = {
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 02ac33435808..58a131ddc6a3 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -111,7 +111,8 @@ struct kernfs_node {
  * kernfs_dir_ops may be specified on kernfs_create_root() to support
  * directory manipulation syscalls.  These optional callbacks are invoked
  * on the matching syscalls and can perform any kernfs operations which
- * don't necessarily have to be the exact operation requested.
+ * don't necessarily have to be the exact operation requested.  An active
+ * reference is held for each kernfs_node parameter.
  */
 struct kernfs_dir_ops {
 	int (*mkdir)(struct kernfs_node *parent, const char *name,
-- 
cgit v1.2.3


From 90c07c895c87d38db100b6afcb686ab3ef0d6a64 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 3 Feb 2014 14:09:09 -0500
Subject: kernfs: rename kernfs_dir_ops to kernfs_syscall_ops

We're gonna need non-dir syscall callbacks, which will make dir_ops a
misnomer.  Let's rename kernfs_dir_ops to kernfs_syscall_ops.

This is pure rename.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/dir.c        | 25 +++++++++++++------------
 include/linux/kernfs.h | 18 +++++++++---------
 2 files changed, 22 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index bfbfb48f4ad8..f58d2f16eaf7 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -527,13 +527,14 @@ EXPORT_SYMBOL_GPL(kernfs_find_and_get_ns);
 
 /**
  * kernfs_create_root - create a new kernfs hierarchy
- * @kdops: optional directory syscall operations for the hierarchy
+ * @scops: optional syscall operations for the hierarchy
  * @priv: opaque data associated with the new directory
  *
  * Returns the root of the new hierarchy on success, ERR_PTR() value on
  * failure.
  */
-struct kernfs_root *kernfs_create_root(struct kernfs_dir_ops *kdops, void *priv)
+struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
+				       void *priv)
 {
 	struct kernfs_root *root;
 	struct kernfs_node *kn;
@@ -556,7 +557,7 @@ struct kernfs_root *kernfs_create_root(struct kernfs_dir_ops *kdops, void *priv)
 	kn->priv = priv;
 	kn->dir.root = root;
 
-	root->dir_ops = kdops;
+	root->syscall_ops = scops;
 	root->kn = kn;
 	init_waitqueue_head(&root->deactivate_waitq);
 
@@ -653,16 +654,16 @@ static int kernfs_iop_mkdir(struct inode *dir, struct dentry *dentry,
 			    umode_t mode)
 {
 	struct kernfs_node *parent = dir->i_private;
-	struct kernfs_dir_ops *kdops = kernfs_root(parent)->dir_ops;
+	struct kernfs_syscall_ops *scops = kernfs_root(parent)->syscall_ops;
 	int ret;
 
-	if (!kdops || !kdops->mkdir)
+	if (!scops || !scops->mkdir)
 		return -EPERM;
 
 	if (!kernfs_get_active(parent))
 		return -ENODEV;
 
-	ret = kdops->mkdir(parent, dentry->d_name.name, mode);
+	ret = scops->mkdir(parent, dentry->d_name.name, mode);
 
 	kernfs_put_active(parent);
 	return ret;
@@ -671,16 +672,16 @@ static int kernfs_iop_mkdir(struct inode *dir, struct dentry *dentry,
 static int kernfs_iop_rmdir(struct inode *dir, struct dentry *dentry)
 {
 	struct kernfs_node *kn  = dentry->d_fsdata;
-	struct kernfs_dir_ops *kdops = kernfs_root(kn)->dir_ops;
+	struct kernfs_syscall_ops *scops = kernfs_root(kn)->syscall_ops;
 	int ret;
 
-	if (!kdops || !kdops->rmdir)
+	if (!scops || !scops->rmdir)
 		return -EPERM;
 
 	if (!kernfs_get_active(kn))
 		return -ENODEV;
 
-	ret = kdops->rmdir(kn);
+	ret = scops->rmdir(kn);
 
 	kernfs_put_active(kn);
 	return ret;
@@ -691,10 +692,10 @@ static int kernfs_iop_rename(struct inode *old_dir, struct dentry *old_dentry,
 {
 	struct kernfs_node *kn  = old_dentry->d_fsdata;
 	struct kernfs_node *new_parent = new_dir->i_private;
-	struct kernfs_dir_ops *kdops = kernfs_root(kn)->dir_ops;
+	struct kernfs_syscall_ops *scops = kernfs_root(kn)->syscall_ops;
 	int ret;
 
-	if (!kdops || !kdops->rename)
+	if (!scops || !scops->rename)
 		return -EPERM;
 
 	if (!kernfs_get_active(kn))
@@ -705,7 +706,7 @@ static int kernfs_iop_rename(struct inode *old_dir, struct dentry *old_dentry,
 		return -ENODEV;
 	}
 
-	ret = kdops->rename(kn, new_parent, new_dentry->d_name.name);
+	ret = scops->rename(kn, new_parent, new_dentry->d_name.name);
 
 	kernfs_put_active(new_parent);
 	kernfs_put_active(kn);
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 58a131ddc6a3..5ddc47450335 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -108,13 +108,13 @@ struct kernfs_node {
 };
 
 /*
- * kernfs_dir_ops may be specified on kernfs_create_root() to support
- * directory manipulation syscalls.  These optional callbacks are invoked
- * on the matching syscalls and can perform any kernfs operations which
- * don't necessarily have to be the exact operation requested.  An active
- * reference is held for each kernfs_node parameter.
+ * kernfs_syscall_ops may be specified on kernfs_create_root() to support
+ * syscalls.  These optional callbacks are invoked on the matching syscalls
+ * and can perform any kernfs operations which don't necessarily have to be
+ * the exact operation requested.  An active reference is held for each
+ * kernfs_node parameter.
  */
-struct kernfs_dir_ops {
+struct kernfs_syscall_ops {
 	int (*mkdir)(struct kernfs_node *parent, const char *name,
 		     umode_t mode);
 	int (*rmdir)(struct kernfs_node *kn);
@@ -128,7 +128,7 @@ struct kernfs_root {
 
 	/* private fields, do not use outside kernfs proper */
 	struct ida		ino_ida;
-	struct kernfs_dir_ops	*dir_ops;
+	struct kernfs_syscall_ops *syscall_ops;
 	wait_queue_head_t	deactivate_waitq;
 };
 
@@ -219,7 +219,7 @@ struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent,
 void kernfs_get(struct kernfs_node *kn);
 void kernfs_put(struct kernfs_node *kn);
 
-struct kernfs_root *kernfs_create_root(struct kernfs_dir_ops *kdops,
+struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
 				       void *priv);
 void kernfs_destroy_root(struct kernfs_root *root);
 
@@ -273,7 +273,7 @@ static inline void kernfs_get(struct kernfs_node *kn) { }
 static inline void kernfs_put(struct kernfs_node *kn) { }
 
 static inline struct kernfs_root *
-kernfs_create_root(struct kernfs_dir_ops *kdops, void *priv)
+kernfs_create_root(struct kernfs_syscall_ops *scops, void *priv)
 { return ERR_PTR(-ENOSYS); }
 
 static inline void kernfs_destroy_root(struct kernfs_root *root) { }
-- 
cgit v1.2.3


From 6a7fed4eefddad48224f1c9d534b4e262f0897f6 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 3 Feb 2014 14:09:10 -0500
Subject: kernfs: implement kernfs_syscall_ops->remount_fs() and
 ->show_options()

Add two super_block related syscall callbacks ->remount_fs() and
->show_options() to kernfs_syscall_ops.  These simply forward the
matching super_operations.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/mount.c      | 23 +++++++++++++++++++++++
 include/linux/kernfs.h |  3 +++
 2 files changed, 26 insertions(+)

(limited to 'include/linux')

diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 0d6ce895a9ee..70cc6983d9b5 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -19,10 +19,33 @@
 
 struct kmem_cache *kernfs_node_cache;
 
+static int kernfs_sop_remount_fs(struct super_block *sb, int *flags, char *data)
+{
+	struct kernfs_root *root = kernfs_info(sb)->root;
+	struct kernfs_syscall_ops *scops = root->syscall_ops;
+
+	if (scops && scops->remount_fs)
+		return scops->remount_fs(root, flags, data);
+	return 0;
+}
+
+static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry)
+{
+	struct kernfs_root *root = kernfs_root(dentry->d_fsdata);
+	struct kernfs_syscall_ops *scops = root->syscall_ops;
+
+	if (scops && scops->show_options)
+		return scops->show_options(sf, root);
+	return 0;
+}
+
 static const struct super_operations kernfs_sops = {
 	.statfs		= simple_statfs,
 	.drop_inode	= generic_delete_inode,
 	.evict_inode	= kernfs_evict_inode,
+
+	.remount_fs	= kernfs_sop_remount_fs,
+	.show_options	= kernfs_sop_show_options,
 };
 
 static int kernfs_fill_super(struct super_block *sb)
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 5ddc47450335..5d5b7e947294 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -115,6 +115,9 @@ struct kernfs_node {
  * kernfs_node parameter.
  */
 struct kernfs_syscall_ops {
+	int (*remount_fs)(struct kernfs_root *root, int *flags, char *data);
+	int (*show_options)(struct seq_file *sf, struct kernfs_root *root);
+
 	int (*mkdir)(struct kernfs_node *parent, const char *name,
 		     umode_t mode);
 	int (*rmdir)(struct kernfs_node *kn);
-- 
cgit v1.2.3


From d35258ef702cca0c4e66d799f8e38b78c02ce8a5 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 3 Feb 2014 14:09:12 -0500
Subject: kernfs: allow nodes to be created in the deactivated state

Currently, kernfs_nodes are made visible to userland on creation,
which makes it difficult for kernfs users to atomically succeed or
fail creation of multiple nodes.  In addition, if something fails
after creating some nodes, the created nodes might already be in use
and their active refs need to be drained for removal, which has the
potential to introduce tricky reverse locking dependency on active_ref
depending on how the error path is synchronized.

This patch introduces per-root flag KERNFS_ROOT_CREATE_DEACTIVATED.
If set, all nodes under the root are created in the deactivated state
and stay invisible to userland until explicitly enabled by the new
kernfs_activate() API.  Also, nodes which have never been activated
are guaranteed to bypass draining on removal thus allowing error paths
to not worry about lockding dependency on active_ref draining.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/dir.c        | 71 +++++++++++++++++++++++++++++++++++++++++++++-----
 fs/sysfs/mount.c       |  2 +-
 include/linux/kernfs.h | 15 +++++++++--
 3 files changed, 78 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 89f8462f337e..3cff0a233cd1 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -435,7 +435,7 @@ int kernfs_add_one(struct kernfs_node *kn)
 		goto out_unlock;
 
 	ret = -ENOENT;
-	if (!kernfs_active(parent))
+	if ((parent->flags & KERNFS_ACTIVATED) && !kernfs_active(parent))
 		goto out_unlock;
 
 	kn->hash = kernfs_name_hash(kn->name, kn->ns);
@@ -451,9 +451,19 @@ int kernfs_add_one(struct kernfs_node *kn)
 		ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME;
 	}
 
-	/* Mark the entry added into directory tree */
-	atomic_sub(KN_DEACTIVATED_BIAS, &kn->active);
-	ret = 0;
+	mutex_unlock(&kernfs_mutex);
+
+	/*
+	 * Activate the new node unless CREATE_DEACTIVATED is requested.
+	 * If not activated here, the kernfs user is responsible for
+	 * activating the node with kernfs_activate().  A node which hasn't
+	 * been activated is not visible to userland and its removal won't
+	 * trigger deactivation.
+	 */
+	if (!(kernfs_root(kn)->flags & KERNFS_ROOT_CREATE_DEACTIVATED))
+		kernfs_activate(kn);
+	return 0;
+
 out_unlock:
 	mutex_unlock(&kernfs_mutex);
 	return ret;
@@ -528,13 +538,14 @@ EXPORT_SYMBOL_GPL(kernfs_find_and_get_ns);
 /**
  * kernfs_create_root - create a new kernfs hierarchy
  * @scops: optional syscall operations for the hierarchy
+ * @flags: KERNFS_ROOT_* flags
  * @priv: opaque data associated with the new directory
  *
  * Returns the root of the new hierarchy on success, ERR_PTR() value on
  * failure.
  */
 struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
-				       void *priv)
+				       unsigned int flags, void *priv)
 {
 	struct kernfs_root *root;
 	struct kernfs_node *kn;
@@ -553,14 +564,17 @@ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	atomic_sub(KN_DEACTIVATED_BIAS, &kn->active);
 	kn->priv = priv;
 	kn->dir.root = root;
 
 	root->syscall_ops = scops;
+	root->flags = flags;
 	root->kn = kn;
 	init_waitqueue_head(&root->deactivate_waitq);
 
+	if (!(root->flags & KERNFS_ROOT_CREATE_DEACTIVATED))
+		kernfs_activate(kn);
+
 	return root;
 }
 
@@ -783,6 +797,40 @@ static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos,
 	return pos->parent;
 }
 
+/**
+ * kernfs_activate - activate a node which started deactivated
+ * @kn: kernfs_node whose subtree is to be activated
+ *
+ * If the root has KERNFS_ROOT_CREATE_DEACTIVATED set, a newly created node
+ * needs to be explicitly activated.  A node which hasn't been activated
+ * isn't visible to userland and deactivation is skipped during its
+ * removal.  This is useful to construct atomic init sequences where
+ * creation of multiple nodes should either succeed or fail atomically.
+ *
+ * The caller is responsible for ensuring that this function is not called
+ * after kernfs_remove*() is invoked on @kn.
+ */
+void kernfs_activate(struct kernfs_node *kn)
+{
+	struct kernfs_node *pos;
+
+	mutex_lock(&kernfs_mutex);
+
+	pos = NULL;
+	while ((pos = kernfs_next_descendant_post(pos, kn))) {
+		if (!pos || (pos->flags & KERNFS_ACTIVATED))
+			continue;
+
+		WARN_ON_ONCE(pos->parent && RB_EMPTY_NODE(&pos->rb));
+		WARN_ON_ONCE(atomic_read(&pos->active) != KN_DEACTIVATED_BIAS);
+
+		atomic_sub(KN_DEACTIVATED_BIAS, &pos->active);
+		pos->flags |= KERNFS_ACTIVATED;
+	}
+
+	mutex_unlock(&kernfs_mutex);
+}
+
 static void __kernfs_remove(struct kernfs_node *kn)
 {
 	struct kernfs_node *pos;
@@ -817,7 +865,16 @@ static void __kernfs_remove(struct kernfs_node *kn)
 		 */
 		kernfs_get(pos);
 
-		kernfs_drain(pos);
+		/*
+		 * Drain iff @kn was activated.  This avoids draining and
+		 * its lockdep annotations for nodes which have never been
+		 * activated and allows embedding kernfs_remove() in create
+		 * error paths without worrying about draining.
+		 */
+		if (kn->flags & KERNFS_ACTIVATED)
+			kernfs_drain(pos);
+		else
+			WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS);
 
 		/*
 		 * kernfs_unlink_sibling() succeeds once per node.  Use it
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 6211230814fd..5c7fdd9c6811 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -62,7 +62,7 @@ int __init sysfs_init(void)
 {
 	int err;
 
-	sysfs_root = kernfs_create_root(NULL, NULL);
+	sysfs_root = kernfs_create_root(NULL, 0, NULL);
 	if (IS_ERR(sysfs_root))
 		return PTR_ERR(sysfs_root);
 
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 5d5b7e947294..4520c86f5cb4 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -38,6 +38,7 @@ enum kernfs_node_type {
 #define KERNFS_FLAG_MASK	~KERNFS_TYPE_MASK
 
 enum kernfs_node_flag {
+	KERNFS_ACTIVATED	= 0x0010,
 	KERNFS_NS		= 0x0020,
 	KERNFS_HAS_SEQ_SHOW	= 0x0040,
 	KERNFS_HAS_MMAP		= 0x0080,
@@ -47,6 +48,11 @@ enum kernfs_node_flag {
 	KERNFS_SUICIDED		= 0x0800,
 };
 
+/* @flags for kernfs_create_root() */
+enum kernfs_root_flag {
+	KERNFS_ROOT_CREATE_DEACTIVATED = 0x0001,
+};
+
 /* type-specific structures for kernfs_node union members */
 struct kernfs_elem_dir {
 	unsigned long		subdirs;
@@ -128,6 +134,7 @@ struct kernfs_syscall_ops {
 struct kernfs_root {
 	/* published fields */
 	struct kernfs_node	*kn;
+	unsigned int		flags;	/* KERNFS_ROOT_* flags */
 
 	/* private fields, do not use outside kernfs proper */
 	struct ida		ino_ida;
@@ -223,7 +230,7 @@ void kernfs_get(struct kernfs_node *kn);
 void kernfs_put(struct kernfs_node *kn);
 
 struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
-				       void *priv);
+				       unsigned int flags, void *priv);
 void kernfs_destroy_root(struct kernfs_root *root);
 
 struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
@@ -239,6 +246,7 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
 struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
 				       const char *name,
 				       struct kernfs_node *target);
+void kernfs_activate(struct kernfs_node *kn);
 void kernfs_remove(struct kernfs_node *kn);
 void kernfs_break_active_protection(struct kernfs_node *kn);
 void kernfs_unbreak_active_protection(struct kernfs_node *kn);
@@ -276,7 +284,8 @@ static inline void kernfs_get(struct kernfs_node *kn) { }
 static inline void kernfs_put(struct kernfs_node *kn) { }
 
 static inline struct kernfs_root *
-kernfs_create_root(struct kernfs_syscall_ops *scops, void *priv)
+kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags,
+		   void *priv)
 { return ERR_PTR(-ENOSYS); }
 
 static inline void kernfs_destroy_root(struct kernfs_root *root) { }
@@ -298,6 +307,8 @@ kernfs_create_link(struct kernfs_node *parent, const char *name,
 		   struct kernfs_node *target)
 { return ERR_PTR(-ENOSYS); }
 
+static inline void kernfs_activate(struct kernfs_node *kn) { }
+
 static inline void kernfs_remove(struct kernfs_node *kn) { }
 
 static inline bool kernfs_remove_self(struct kernfs_node *kn)
-- 
cgit v1.2.3


From 4d3773c4bb41ed5228f1ab7a4a52b79e17b10515 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 3 Feb 2014 14:09:13 -0500
Subject: kernfs: implement kernfs_ops->atomic_write_len

A write to a kernfs_node is buffered through a kernel buffer.  Writes
<= PAGE_SIZE are performed atomically, while larger ones are executed
in PAGE_SIZE chunks.  While this is enough for sysfs, cgroup which is
scheduled to be converted to use kernfs needs a bit more control over
it.

This patch adds kernfs_ops->atomic_write_len.  If not set (zero), the
behavior stays the same.  If set, writes upto the size are executed
atomically and larger writes are rejected with -E2BIG.

A different implementation strategy would be allowing configuring
chunking size while making the original write size available to the
write method; however, such strategy, while being more complicated,
doesn't really buy anything.  If the write implementation has to
handle chunking, the specific chunk size shouldn't matter all that
much.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/file.c       | 49 +++++++++++++++++++++++++++++++------------------
 include/linux/kernfs.h |  8 ++++++--
 2 files changed, 37 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 10a8c91c49d6..ddcb471b9cc9 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -252,19 +252,9 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
 				size_t count, loff_t *ppos)
 {
 	struct kernfs_open_file *of = kernfs_of(file);
-	ssize_t len = min_t(size_t, count, PAGE_SIZE);
 	const struct kernfs_ops *ops;
-	char *buf;
-
-	buf = kmalloc(len + 1, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	if (copy_from_user(buf, user_buf, len)) {
-		len = -EFAULT;
-		goto out_free;
-	}
-	buf[len] = '\0';	/* guarantee string termination */
+	char *buf = NULL;
+	ssize_t len;
 
 	/*
 	 * @of->mutex nests outside active ref and is just to ensure that
@@ -273,22 +263,45 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
 	mutex_lock(&of->mutex);
 	if (!kernfs_get_active(of->kn)) {
 		mutex_unlock(&of->mutex);
-		len = -ENODEV;
-		goto out_free;
+		return -ENODEV;
 	}
 
 	ops = kernfs_ops(of->kn);
-	if (ops->write)
-		len = ops->write(of, buf, len, *ppos);
-	else
+	if (!ops->write) {
 		len = -EINVAL;
+		goto out_unlock;
+	}
+
+	if (ops->atomic_write_len) {
+		len = count;
+		if (len > ops->atomic_write_len) {
+			len = -E2BIG;
+			goto out_unlock;
+		}
+	} else {
+		len = min_t(size_t, count, PAGE_SIZE);
+	}
+
+	buf = kmalloc(len + 1, GFP_KERNEL);
+	if (!buf) {
+		len = -ENOMEM;
+		goto out_unlock;
+	}
 
+	if (copy_from_user(buf, user_buf, len)) {
+		len = -EFAULT;
+		goto out_unlock;
+	}
+	buf[len] = '\0';	/* guarantee string termination */
+
+	len = ops->write(of, buf, len, *ppos);
+out_unlock:
 	kernfs_put_active(of->kn);
 	mutex_unlock(&of->mutex);
 
 	if (len > 0)
 		*ppos += len;
-out_free:
+
 	kfree(buf);
 	return len;
 }
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 4520c86f5cb4..47f5235a097a 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -178,9 +178,13 @@ struct kernfs_ops {
 			loff_t off);
 
 	/*
-	 * write() is bounced through kernel buffer and a write larger than
-	 * PAGE_SIZE results in partial operation of PAGE_SIZE.
+	 * write() is bounced through kernel buffer.  If atomic_write_len
+	 * is not set, a write larger than PAGE_SIZE results in partial
+	 * operations of PAGE_SIZE chunks.  If atomic_write_len is set,
+	 * writes upto the specified size are executed atomically but
+	 * larger ones are rejected with -E2BIG.
 	 */
+	size_t atomic_write_len;
 	ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t bytes,
 			 loff_t off);
 
-- 
cgit v1.2.3


From 2536390da0d300b2734c721235c082498879841d Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 3 Feb 2014 14:09:14 -0500
Subject: kernfs: add kernfs_open_file->priv

Add a private data field to be used by kernfs file operations.  This
generally makes sense and will be used by cgroup.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/kernfs.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 47f5235a097a..9ca0f09757a1 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -146,6 +146,7 @@ struct kernfs_open_file {
 	/* published fields */
 	struct kernfs_node	*kn;
 	struct file		*file;
+	void			*priv;
 
 	/* private fields, do not use outside kernfs proper */
 	struct mutex		mutex;
-- 
cgit v1.2.3


From 0c23b2259a4850494e2c53e864ea840597c6cdd3 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 3 Feb 2014 14:09:15 -0500
Subject: kernfs: implement kernfs_node_from_dentry(), kernfs_root_from_sb()
 and kernfs_rename()

Implement helpers to determine node from dentry and root from
super_block.  Also add a kernfs_rename_ns() wrapper which assumes NULL
namespace.  These generally make sense and will be used by cgroup.

v2: Some dummy implementations for !CONFIG_SYSFS was missing.  Fixed.
    Reported by kbuild test robot.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/dir.c        | 18 ++++++++++++++++++
 fs/kernfs/mount.c      | 14 ++++++++++++++
 include/linux/kernfs.h | 16 ++++++++++++++++
 3 files changed, 48 insertions(+)

(limited to 'include/linux')

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 3cff0a233cd1..42a250f83b98 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -350,6 +350,24 @@ const struct dentry_operations kernfs_dops = {
 	.d_release	= kernfs_dop_release,
 };
 
+/**
+ * kernfs_node_from_dentry - determine kernfs_node associated with a dentry
+ * @dentry: the dentry in question
+ *
+ * Return the kernfs_node associated with @dentry.  If @dentry is not a
+ * kernfs one, %NULL is returned.
+ *
+ * While the returned kernfs_node will stay accessible as long as @dentry
+ * is accessible, the returned node can be in any state and the caller is
+ * fully responsible for determining what's accessible.
+ */
+struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry)
+{
+	if (dentry->d_op == &kernfs_dops)
+		return dentry->d_fsdata;
+	return NULL;
+}
+
 static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 					     const char *name, umode_t mode,
 					     unsigned flags)
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 70cc6983d9b5..e5b28b0ebc37 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -48,6 +48,20 @@ static const struct super_operations kernfs_sops = {
 	.show_options	= kernfs_sop_show_options,
 };
 
+/**
+ * kernfs_root_from_sb - determine kernfs_root associated with a super_block
+ * @sb: the super_block in question
+ *
+ * Return the kernfs_root associated with @sb.  If @sb is not a kernfs one,
+ * %NULL is returned.
+ */
+struct kernfs_root *kernfs_root_from_sb(struct super_block *sb)
+{
+	if (sb->s_op == &kernfs_sops)
+		return kernfs_info(sb)->root;
+	return NULL;
+}
+
 static int kernfs_fill_super(struct super_block *sb)
 {
 	struct kernfs_super_info *info = kernfs_info(sb);
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 9ca0f09757a1..9c899040c05e 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -234,6 +234,9 @@ struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent,
 void kernfs_get(struct kernfs_node *kn);
 void kernfs_put(struct kernfs_node *kn);
 
+struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry);
+struct kernfs_root *kernfs_root_from_sb(struct super_block *sb);
+
 struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
 				       unsigned int flags, void *priv);
 void kernfs_destroy_root(struct kernfs_root *root);
@@ -288,6 +291,12 @@ kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name,
 static inline void kernfs_get(struct kernfs_node *kn) { }
 static inline void kernfs_put(struct kernfs_node *kn) { }
 
+static inline struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry)
+{ return NULL; }
+
+static inline struct kernfs_root *kernfs_root_from_sb(struct super_block *sb)
+{ return NULL; }
+
 static inline struct kernfs_root *
 kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags,
 		   void *priv)
@@ -388,6 +397,13 @@ static inline int kernfs_remove_by_name(struct kernfs_node *parent,
 	return kernfs_remove_by_name_ns(parent, name, NULL);
 }
 
+static inline int kernfs_rename(struct kernfs_node *kn,
+				struct kernfs_node *new_parent,
+				const char *new_name)
+{
+	return kernfs_rename_ns(kn, new_parent, new_name, NULL);
+}
+
 static inline struct dentry *
 kernfs_mount(struct file_system_type *fs_type, int flags,
 	     struct kernfs_root *root)
-- 
cgit v1.2.3


From 3eef34ad7dc369b7183ec383908aff3da2f6e5ec Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 7 Feb 2014 13:32:07 -0500
Subject: kernfs: implement kernfs_get_parent(), kernfs_name/path() and friends

kernfs_node->parent and ->name are currently marked as "published"
indicating that kernfs users may access them directly; however, those
fields may get updated by kernfs_rename[_ns]() and unrestricted access
may lead to erroneous values or oops.

Protect ->parent and ->name updates with a irq-safe spinlock
kernfs_rename_lock and implement the following accessors for these
fields.

* kernfs_name()		- format the node's name into the specified buffer
* kernfs_path()		- format the node's path into the specified buffer
* pr_cont_kernfs_name()	- pr_cont a node's name (doesn't need buffer)
* pr_cont_kernfs_path()	- pr_cont a node's path (doesn't need buffer)
* kernfs_get_parent()	- pin and return a node's parent

All can be called under any context.  The recursive sysfs_pathname()
in fs/sysfs/dir.c is replaced with kernfs_path() and
sysfs_rename_dir_ns() is updated to use kernfs_get_parent() instead of
dereferencing parent directly.

v2: Dummy definition of kernfs_path() for !CONFIG_KERNFS was missing
    static inline making it cause a lot of build warnings.  Add it.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/dir.c        | 175 ++++++++++++++++++++++++++++++++++++++++++++++---
 fs/sysfs/dir.c         |  44 ++++---------
 include/linux/kernfs.h |  26 +++++++-
 3 files changed, 203 insertions(+), 42 deletions(-)

(limited to 'include/linux')

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 42a250f83b98..a347792c2e5a 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -19,6 +19,8 @@
 #include "kernfs-internal.h"
 
 DEFINE_MUTEX(kernfs_mutex);
+static DEFINE_SPINLOCK(kernfs_rename_lock);	/* kn->parent and ->name */
+static char kernfs_pr_cont_buf[PATH_MAX];	/* protected by rename_lock */
 
 #define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb)
 
@@ -37,6 +39,141 @@ static bool kernfs_lockdep(struct kernfs_node *kn)
 #endif
 }
 
+static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen)
+{
+	return strlcpy(buf, kn->parent ? kn->name : "/", buflen);
+}
+
+static char * __must_check kernfs_path_locked(struct kernfs_node *kn, char *buf,
+					      size_t buflen)
+{
+	char *p = buf + buflen;
+	int len;
+
+	*--p = '\0';
+
+	do {
+		len = strlen(kn->name);
+		if (p - buf < len + 1) {
+			buf[0] = '\0';
+			p = NULL;
+			break;
+		}
+		p -= len;
+		memcpy(p, kn->name, len);
+		*--p = '/';
+		kn = kn->parent;
+	} while (kn && kn->parent);
+
+	return p;
+}
+
+/**
+ * kernfs_name - obtain the name of a given node
+ * @kn: kernfs_node of interest
+ * @buf: buffer to copy @kn's name into
+ * @buflen: size of @buf
+ *
+ * Copies the name of @kn into @buf of @buflen bytes.  The behavior is
+ * similar to strlcpy().  It returns the length of @kn's name and if @buf
+ * isn't long enough, it's filled upto @buflen-1 and nul terminated.
+ *
+ * This function can be called from any context.
+ */
+int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&kernfs_rename_lock, flags);
+	ret = kernfs_name_locked(kn, buf, buflen);
+	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+	return ret;
+}
+
+/**
+ * kernfs_path - build full path of a given node
+ * @kn: kernfs_node of interest
+ * @buf: buffer to copy @kn's name into
+ * @buflen: size of @buf
+ *
+ * Builds and returns the full path of @kn in @buf of @buflen bytes.  The
+ * path is built from the end of @buf so the returned pointer usually
+ * doesn't match @buf.  If @buf isn't long enough, @buf is nul terminated
+ * and %NULL is returned.
+ */
+char *kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen)
+{
+	unsigned long flags;
+	char *p;
+
+	spin_lock_irqsave(&kernfs_rename_lock, flags);
+	p = kernfs_path_locked(kn, buf, buflen);
+	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+	return p;
+}
+
+/**
+ * pr_cont_kernfs_name - pr_cont name of a kernfs_node
+ * @kn: kernfs_node of interest
+ *
+ * This function can be called from any context.
+ */
+void pr_cont_kernfs_name(struct kernfs_node *kn)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&kernfs_rename_lock, flags);
+
+	kernfs_name_locked(kn, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf));
+	pr_cont("%s", kernfs_pr_cont_buf);
+
+	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+}
+
+/**
+ * pr_cont_kernfs_path - pr_cont path of a kernfs_node
+ * @kn: kernfs_node of interest
+ *
+ * This function can be called from any context.
+ */
+void pr_cont_kernfs_path(struct kernfs_node *kn)
+{
+	unsigned long flags;
+	char *p;
+
+	spin_lock_irqsave(&kernfs_rename_lock, flags);
+
+	p = kernfs_path_locked(kn, kernfs_pr_cont_buf,
+			       sizeof(kernfs_pr_cont_buf));
+	if (p)
+		pr_cont("%s", p);
+	else
+		pr_cont("<name too long>");
+
+	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+}
+
+/**
+ * kernfs_get_parent - determine the parent node and pin it
+ * @kn: kernfs_node of interest
+ *
+ * Determines @kn's parent, pins and returns it.  This function can be
+ * called from any context.
+ */
+struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn)
+{
+	struct kernfs_node *parent;
+	unsigned long flags;
+
+	spin_lock_irqsave(&kernfs_rename_lock, flags);
+	parent = kn->parent;
+	kernfs_get(parent);
+	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+
+	return parent;
+}
+
 /**
  *	kernfs_name_hash
  *	@name: Null terminated string to hash
@@ -1103,8 +1240,14 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
 int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 		     const char *new_name, const void *new_ns)
 {
+	struct kernfs_node *old_parent;
+	const char *old_name = NULL;
 	int error;
 
+	/* can't move or rename root */
+	if (!kn->parent)
+		return -EINVAL;
+
 	mutex_lock(&kernfs_mutex);
 
 	error = -ENOENT;
@@ -1126,13 +1269,8 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 		new_name = kstrdup(new_name, GFP_KERNEL);
 		if (!new_name)
 			goto out;
-
-		if (kn->flags & KERNFS_STATIC_NAME)
-			kn->flags &= ~KERNFS_STATIC_NAME;
-		else
-			kfree(kn->name);
-
-		kn->name = new_name;
+	} else {
+		new_name = NULL;
 	}
 
 	/*
@@ -1140,12 +1278,29 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 	 */
 	kernfs_unlink_sibling(kn);
 	kernfs_get(new_parent);
-	kernfs_put(kn->parent);
-	kn->ns = new_ns;
-	kn->hash = kernfs_name_hash(kn->name, kn->ns);
+
+	/* rename_lock protects ->parent and ->name accessors */
+	spin_lock_irq(&kernfs_rename_lock);
+
+	old_parent = kn->parent;
 	kn->parent = new_parent;
+
+	kn->ns = new_ns;
+	if (new_name) {
+		if (!(kn->flags & KERNFS_STATIC_NAME))
+			old_name = kn->name;
+		kn->flags &= ~KERNFS_STATIC_NAME;
+		kn->name = new_name;
+	}
+
+	spin_unlock_irq(&kernfs_rename_lock);
+
+	kn->hash = kernfs_name_hash(new_name, new_ns);
 	kernfs_link_sibling(kn);
 
+	kernfs_put(old_parent);
+	kfree(old_name);
+
 	error = 0;
  out:
 	mutex_unlock(&kernfs_mutex);
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index ee0d761c3179..0b45ff42f374 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -19,39 +19,18 @@
 
 DEFINE_SPINLOCK(sysfs_symlink_target_lock);
 
-/**
- *	sysfs_pathname - return full path to sysfs dirent
- *	@kn: kernfs_node whose path we want
- *	@path: caller allocated buffer of size PATH_MAX
- *
- *	Gives the name "/" to the sysfs_root entry; any path returned
- *	is relative to wherever sysfs is mounted.
- */
-static char *sysfs_pathname(struct kernfs_node *kn, char *path)
-{
-	if (kn->parent) {
-		sysfs_pathname(kn->parent, path);
-		strlcat(path, "/", PATH_MAX);
-	}
-	strlcat(path, kn->name, PATH_MAX);
-	return path;
-}
-
 void sysfs_warn_dup(struct kernfs_node *parent, const char *name)
 {
-	char *path;
+	char *buf, *path = NULL;
 
-	path = kzalloc(PATH_MAX, GFP_KERNEL);
-	if (path) {
-		sysfs_pathname(parent, path);
-		strlcat(path, "/", PATH_MAX);
-		strlcat(path, name, PATH_MAX);
-	}
+	buf = kzalloc(PATH_MAX, GFP_KERNEL);
+	if (buf)
+		path = kernfs_path(parent, buf, PATH_MAX);
 
-	WARN(1, KERN_WARNING "sysfs: cannot create duplicate filename '%s'\n",
-	     path ? path : name);
+	WARN(1, KERN_WARNING "sysfs: cannot create duplicate filename '%s/%s'\n",
+	     path, name);
 
-	kfree(path);
+	kfree(buf);
 }
 
 /**
@@ -122,9 +101,13 @@ void sysfs_remove_dir(struct kobject *kobj)
 int sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name,
 			const void *new_ns)
 {
-	struct kernfs_node *parent = kobj->sd->parent;
+	struct kernfs_node *parent;
+	int ret;
 
-	return kernfs_rename_ns(kobj->sd, parent, new_name, new_ns);
+	parent = kernfs_get_parent(kobj->sd);
+	ret = kernfs_rename_ns(kobj->sd, parent, new_name, new_ns);
+	kernfs_put(parent);
+	return ret;
 }
 
 int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj,
@@ -133,7 +116,6 @@ int sysfs_move_dir_ns(struct kobject *kobj, struct kobject *new_parent_kobj,
 	struct kernfs_node *kn = kobj->sd;
 	struct kernfs_node *new_parent;
 
-	BUG_ON(!kn->parent);
 	new_parent = new_parent_kobj && new_parent_kobj->sd ?
 		new_parent_kobj->sd : sysfs_root_kn;
 
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 9c899040c05e..8736ee86a1d6 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -91,7 +91,12 @@ struct kernfs_node {
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map	dep_map;
 #endif
-	/* the following two fields are published */
+	/*
+	 * Use kernfs_get_parent() and kernfs_name/path() instead of
+	 * accessing the following two fields directly.  If the node is
+	 * never moved to a different parent, it is safe to access the
+	 * parent directly.
+	 */
 	struct kernfs_node	*parent;
 	const char		*name;
 
@@ -229,6 +234,12 @@ static inline bool kernfs_ns_enabled(struct kernfs_node *kn)
 	return kn->flags & KERNFS_NS;
 }
 
+int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen);
+char * __must_check kernfs_path(struct kernfs_node *kn, char *buf,
+				size_t buflen);
+void pr_cont_kernfs_name(struct kernfs_node *kn);
+void pr_cont_kernfs_path(struct kernfs_node *kn);
+struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn);
 struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent,
 					   const char *name, const void *ns);
 void kernfs_get(struct kernfs_node *kn);
@@ -283,6 +294,19 @@ static inline void kernfs_enable_ns(struct kernfs_node *kn) { }
 static inline bool kernfs_ns_enabled(struct kernfs_node *kn)
 { return false; }
 
+static inline int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen)
+{ return -ENOSYS; }
+
+static inline char * __must_check kernfs_path(struct kernfs_node *kn, char *buf,
+					      size_t buflen)
+{ return NULL; }
+
+static inline void pr_cont_kernfs_name(struct kernfs_node *kn) { }
+static inline void pr_cont_kernfs_path(struct kernfs_node *kn) { }
+
+static inline struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn)
+{ return NULL; }
+
 static inline struct kernfs_node *
 kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name,
 		       const void *ns)
-- 
cgit v1.2.3


From fa4cd451cceb77e97432b91fcf50a7e4a7361e29 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 7 Feb 2014 13:32:07 -0500
Subject: sysfs, kobject: add sysfs wrapper for kernfs_enable_ns()

Currently, kobject is invoking kernfs_enable_ns() directly.  This is
fine now as sysfs and kernfs are enabled and disabled together.  If
sysfs is disabled, kernfs_enable_ns() is switched to dummy
implementation too and everything is fine; however, kernfs will soon
have its own config option CONFIG_KERNFS and !SYSFS && KERNFS will be
possible, which can make kobject call into non-dummy
kernfs_enable_ns() with NULL kernfs_node pointers leading to an oops.

Introduce sysfs_enable_ns() which is a wrapper around
kernfs_enable_ns() so that it can be made a noop depending only on
CONFIG_SYSFS regardless of the planned CONFIG_KERNFS.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/sysfs.h | 9 +++++++++
 lib/kobject.c         | 2 +-
 2 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index 14df05415af9..fdaa0c6fc7a2 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -244,6 +244,11 @@ void sysfs_notify(struct kobject *kobj, const char *dir, const char *attr);
 
 int __must_check sysfs_init(void);
 
+static inline void sysfs_enable_ns(struct kernfs_node *kn)
+{
+	return kernfs_enable_ns(kn);
+}
+
 #else /* CONFIG_SYSFS */
 
 static inline int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
@@ -416,6 +421,10 @@ static inline int __must_check sysfs_init(void)
 	return 0;
 }
 
+static inline void sysfs_enable_ns(struct kernfs_node *kn)
+{
+}
+
 #endif /* CONFIG_SYSFS */
 
 static inline int __must_check sysfs_create_file(struct kobject *kobj,
diff --git a/lib/kobject.c b/lib/kobject.c
index cb14aeac4cca..58751bb80a7c 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -94,7 +94,7 @@ static int create_dir(struct kobject *kobj)
 		BUG_ON(ops->type >= KOBJ_NS_TYPES);
 		BUG_ON(!kobj_ns_type_registered(ops->type));
 
-		kernfs_enable_ns(kobj->sd);
+		sysfs_enable_ns(kobj->sd);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From ba341d55a420ab4fdd1a53fd395fd59bd65de880 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 3 Feb 2014 14:09:17 -0500
Subject: kernfs: add CONFIG_KERNFS

As sysfs was kernfs's only user, kernfs has been piggybacking on
CONFIG_SYSFS; however, kernfs is scheduled to grow a new user very
soon.  Introduce a separate config option CONFIG_KERNFS which is to be
selected by kernfs users.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/Kconfig             | 1 +
 fs/Makefile            | 3 ++-
 fs/kernfs/Kconfig      | 7 +++++++
 fs/sysfs/Kconfig       | 1 +
 include/linux/kernfs.h | 6 +++---
 5 files changed, 14 insertions(+), 4 deletions(-)
 create mode 100644 fs/kernfs/Kconfig

(limited to 'include/linux')

diff --git a/fs/Kconfig b/fs/Kconfig
index 7385e54be4b9..312393f32948 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -96,6 +96,7 @@ endif # BLOCK
 menu "Pseudo filesystems"
 
 source "fs/proc/Kconfig"
+source "fs/kernfs/Kconfig"
 source "fs/sysfs/Kconfig"
 
 config TMPFS
diff --git a/fs/Makefile b/fs/Makefile
index 47ac07bb4acc..f9cb9876e466 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -52,7 +52,8 @@ obj-$(CONFIG_FHANDLE)		+= fhandle.o
 obj-y				+= quota/
 
 obj-$(CONFIG_PROC_FS)		+= proc/
-obj-$(CONFIG_SYSFS)		+= sysfs/ kernfs/
+obj-$(CONFIG_KERNFS)		+= kernfs/
+obj-$(CONFIG_SYSFS)		+= sysfs/
 obj-$(CONFIG_CONFIGFS_FS)	+= configfs/
 obj-y				+= devpts/
 
diff --git a/fs/kernfs/Kconfig b/fs/kernfs/Kconfig
new file mode 100644
index 000000000000..397b5f7a7a16
--- /dev/null
+++ b/fs/kernfs/Kconfig
@@ -0,0 +1,7 @@
+#
+# KERNFS should be selected by its users
+#
+
+config KERNFS
+	bool
+	default n
diff --git a/fs/sysfs/Kconfig b/fs/sysfs/Kconfig
index 8c41feacbac5..b2756014508c 100644
--- a/fs/sysfs/Kconfig
+++ b/fs/sysfs/Kconfig
@@ -1,6 +1,7 @@
 config SYSFS
 	bool "sysfs file system support" if EXPERT
 	default y
+	select KERNFS
 	help
 	The sysfs filesystem is a virtual filesystem that the kernel uses to
 	export internal kernel objects, their attributes, and their
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 8736ee86a1d6..649497a56a95 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -201,7 +201,7 @@ struct kernfs_ops {
 #endif
 };
 
-#ifdef CONFIG_SYSFS
+#ifdef CONFIG_KERNFS
 
 static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn)
 {
@@ -284,7 +284,7 @@ void kernfs_kill_sb(struct super_block *sb);
 
 void kernfs_init(void);
 
-#else	/* CONFIG_SYSFS */
+#else	/* CONFIG_KERNFS */
 
 static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn)
 { return 0; }	/* whatever */
@@ -379,7 +379,7 @@ static inline void kernfs_kill_sb(struct super_block *sb) { }
 
 static inline void kernfs_init(void) { }
 
-#endif	/* CONFIG_SYSFS */
+#endif	/* CONFIG_KERNFS */
 
 static inline struct kernfs_node *
 kernfs_find_and_get(struct kernfs_node *kn, const char *name)
-- 
cgit v1.2.3


From f315e3fa1cf5b3317fc948708645fff889ce1e63 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Mon, 2 Dec 2013 17:49:41 +0900
Subject: slab: restrict the number of objects in a slab

To prepare to implement byte sized index for managing the freelist
of a slab, we should restrict the number of objects in a slab to be less
or equal to 256, since byte only represent 256 different values.
Setting the size of object to value equal or more than newly introduced
SLAB_OBJ_MIN_SIZE ensures that the number of objects in a slab is less or
equal to 256 for a slab with 1 page.

If page size is rather larger than 4096, above assumption would be wrong.
In this case, we would fall back on 2 bytes sized index.

If minimum size of kmalloc is less than 16, we use it as minimum object
size and give up this optimization.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
---
 include/linux/slab.h | 11 +++++++++++
 mm/slab.c            | 21 +++++++++++++++++++++
 2 files changed, 32 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/slab.h b/include/linux/slab.h
index 9260abdd67df..d015dec02bf3 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -201,6 +201,17 @@ struct kmem_cache {
 #ifndef KMALLOC_SHIFT_LOW
 #define KMALLOC_SHIFT_LOW	5
 #endif
+
+/*
+ * This restriction comes from byte sized index implementation.
+ * Page size is normally 2^12 bytes and, in this case, if we want to use
+ * byte sized index which can represent 2^8 entries, the size of the object
+ * should be equal or greater to 2^12 / 2^8 = 2^4 = 16.
+ * If minimum size of kmalloc is less than 16, we use it as minimum object
+ * size and give up to use byte sized index.
+ */
+#define SLAB_OBJ_MIN_SIZE	(KMALLOC_SHIFT_LOW < 4 ? \
+				(1 << KMALLOC_SHIFT_LOW) : 16)
 #endif
 
 #ifdef CONFIG_SLUB
diff --git a/mm/slab.c b/mm/slab.c
index 878354b26b72..9d4c7b50dfdc 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -157,6 +157,17 @@
 #define ARCH_KMALLOC_FLAGS SLAB_HWCACHE_ALIGN
 #endif
 
+#define FREELIST_BYTE_INDEX (((PAGE_SIZE >> BITS_PER_BYTE) \
+				<= SLAB_OBJ_MIN_SIZE) ? 1 : 0)
+
+#if FREELIST_BYTE_INDEX
+typedef unsigned char freelist_idx_t;
+#else
+typedef unsigned short freelist_idx_t;
+#endif
+
+#define SLAB_OBJ_MAX_NUM (1 << sizeof(freelist_idx_t) * BITS_PER_BYTE)
+
 /*
  * true if a page was allocated from pfmemalloc reserves for network-based
  * swap
@@ -2016,6 +2027,10 @@ static size_t calculate_slab_order(struct kmem_cache *cachep,
 		if (!num)
 			continue;
 
+		/* Can't handle number of objects more than SLAB_OBJ_MAX_NUM */
+		if (num > SLAB_OBJ_MAX_NUM)
+			break;
+
 		if (flags & CFLGS_OFF_SLAB) {
 			/*
 			 * Max number of objs-per-slab for caches which
@@ -2258,6 +2273,12 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 		flags |= CFLGS_OFF_SLAB;
 
 	size = ALIGN(size, cachep->align);
+	/*
+	 * We should restrict the number of objects in a slab to implement
+	 * byte sized index. Refer comment on SLAB_OBJ_MIN_SIZE definition.
+	 */
+	if (FREELIST_BYTE_INDEX && size < SLAB_OBJ_MIN_SIZE)
+		size = ALIGN(SLAB_OBJ_MIN_SIZE, cachep->align);
 
 	left_over = calculate_slab_order(cachep, size, cachep->align, flags);
 
-- 
cgit v1.2.3


From 3ed80a62bf959d34ebd4d553b026fbe7e6fbcc54 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Sat, 8 Feb 2014 10:36:58 -0500
Subject: cgroup: drop module support

With module supported dropped from net_prio, no controller is using
cgroup module support.  None of actual resource controllers can be
built as a module and we aren't gonna add new controllers which don't
control resources.  This patch drops module support from cgroup.

* cgroup_[un]load_subsys() and cgroup_subsys->module removed.

* As there's no point in distinguishing IS_BUILTIN() and IS_MODULE(),
  cgroup_subsys.h now uses IS_ENABLED() directly.

* enum cgroup_subsys_id now exactly matches the list of enabled
  controllers as ordered in cgroup_subsys.h.

* cgroup_subsys[] is now a contiguously occupied array.  Size
  specification is no longer necessary and dropped.

* for_each_builtin_subsys() is removed and for_each_subsys() is
  updated to not require any locking.

* module ref handling is removed from rebind_subsystems().

* Module related comments dropped.

v2: Rebased on top of fe1217c4f3f7 ("net: net_cls: move cgroupfs
    classid handling into core").

v3: Added {} around the if (need_forkexit_callback) block in
    cgroup_post_fork() for readability as suggested by Li.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 block/blk-cgroup.c            |   1 -
 include/linux/cgroup.h        |  29 +----
 include/linux/cgroup_subsys.h |  24 ++--
 kernel/cgroup.c               | 284 +++---------------------------------------
 net/core/netclassid_cgroup.c  |   1 -
 net/core/netprio_cgroup.c     |   1 -
 6 files changed, 32 insertions(+), 308 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 4e491d9b5292..660d419918a7 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -914,7 +914,6 @@ struct cgroup_subsys blkio_subsys = {
 	.can_attach = blkcg_can_attach,
 	.subsys_id = blkio_subsys_id,
 	.base_cftypes = blkcg_files,
-	.module = THIS_MODULE,
 };
 EXPORT_SYMBOL_GPL(blkio_subsys);
 
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 5c097596104b..d842a737d448 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -37,28 +37,13 @@ extern void cgroup_post_fork(struct task_struct *p);
 extern void cgroup_exit(struct task_struct *p, int run_callbacks);
 extern int cgroupstats_build(struct cgroupstats *stats,
 				struct dentry *dentry);
-extern int cgroup_load_subsys(struct cgroup_subsys *ss);
-extern void cgroup_unload_subsys(struct cgroup_subsys *ss);
 
 extern int proc_cgroup_show(struct seq_file *, void *);
 
-/*
- * Define the enumeration of all cgroup subsystems.
- *
- * We define ids for builtin subsystems and then modular ones.
- */
+/* define the enumeration of all cgroup subsystems */
 #define SUBSYS(_x) _x ## _subsys_id,
 enum cgroup_subsys_id {
-#define IS_SUBSYS_ENABLED(option) IS_BUILTIN(option)
 #include <linux/cgroup_subsys.h>
-#undef IS_SUBSYS_ENABLED
-	CGROUP_BUILTIN_SUBSYS_COUNT,
-
-	__CGROUP_SUBSYS_TEMP_PLACEHOLDER = CGROUP_BUILTIN_SUBSYS_COUNT - 1,
-
-#define IS_SUBSYS_ENABLED(option) IS_MODULE(option)
-#include <linux/cgroup_subsys.h>
-#undef IS_SUBSYS_ENABLED
 	CGROUP_SUBSYS_COUNT,
 };
 #undef SUBSYS
@@ -370,10 +355,9 @@ struct css_set {
 	struct list_head cgrp_links;
 
 	/*
-	 * Set of subsystem states, one for each subsystem. This array
-	 * is immutable after creation apart from the init_css_set
-	 * during subsystem registration (at boot time) and modular subsystem
-	 * loading/unloading.
+	 * Set of subsystem states, one for each subsystem. This array is
+	 * immutable after creation apart from the init_css_set during
+	 * subsystem registration (at boot time).
 	 */
 	struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];
 
@@ -620,15 +604,10 @@ struct cgroup_subsys {
 	/* base cftypes, automatically [de]registered with subsys itself */
 	struct cftype *base_cftypes;
 	struct cftype_set base_cftset;
-
-	/* should be defined only by modular subsystems */
-	struct module *module;
 };
 
 #define SUBSYS(_x) extern struct cgroup_subsys _x ## _subsys;
-#define IS_SUBSYS_ENABLED(option) IS_BUILTIN(option)
 #include <linux/cgroup_subsys.h>
-#undef IS_SUBSYS_ENABLED
 #undef SUBSYS
 
 /**
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index 7b99d717411d..11c42f6a25a8 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -3,51 +3,51 @@
  *
  * DO NOT ADD ANY SUBSYSTEM WITHOUT EXPLICIT ACKS FROM CGROUP MAINTAINERS.
  */
-#if IS_SUBSYS_ENABLED(CONFIG_CPUSETS)
+#if IS_ENABLED(CONFIG_CPUSETS)
 SUBSYS(cpuset)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_DEBUG)
+#if IS_ENABLED(CONFIG_CGROUP_DEBUG)
 SUBSYS(debug)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_SCHED)
+#if IS_ENABLED(CONFIG_CGROUP_SCHED)
 SUBSYS(cpu_cgroup)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_CPUACCT)
+#if IS_ENABLED(CONFIG_CGROUP_CPUACCT)
 SUBSYS(cpuacct)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_MEMCG)
+#if IS_ENABLED(CONFIG_MEMCG)
 SUBSYS(mem_cgroup)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_DEVICE)
+#if IS_ENABLED(CONFIG_CGROUP_DEVICE)
 SUBSYS(devices)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_FREEZER)
+#if IS_ENABLED(CONFIG_CGROUP_FREEZER)
 SUBSYS(freezer)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_NET_CLASSID)
+#if IS_ENABLED(CONFIG_CGROUP_NET_CLASSID)
 SUBSYS(net_cls)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_BLK_CGROUP)
+#if IS_ENABLED(CONFIG_BLK_CGROUP)
 SUBSYS(blkio)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_PERF)
+#if IS_ENABLED(CONFIG_CGROUP_PERF)
 SUBSYS(perf)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_NET_PRIO)
+#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
 SUBSYS(net_prio)
 #endif
 
-#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_HUGETLB)
+#if IS_ENABLED(CONFIG_CGROUP_HUGETLB)
 SUBSYS(hugetlb)
 #endif
 /*
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index e2f46ba37f72..ccb16b47e293 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -47,7 +47,6 @@
 #include <linux/string.h>
 #include <linux/sort.h>
 #include <linux/kmod.h>
-#include <linux/module.h>
 #include <linux/delayacct.h>
 #include <linux/cgroupstats.h>
 #include <linux/hashtable.h>
@@ -120,15 +119,9 @@ static struct workqueue_struct *cgroup_destroy_wq;
  */
 static struct workqueue_struct *cgroup_pidlist_destroy_wq;
 
-/*
- * Generate an array of cgroup subsystem pointers. At boot time, this is
- * populated with the built in subsystems, and modular subsystems are
- * registered after that. The mutable section of this array is protected by
- * cgroup_mutex.
- */
+/* generate an array of cgroup subsystem pointers */
 #define SUBSYS(_x) [_x ## _subsys_id] = &_x ## _subsys,
-#define IS_SUBSYS_ENABLED(option) IS_BUILTIN(option)
-static struct cgroup_subsys *cgroup_subsys[CGROUP_SUBSYS_COUNT] = {
+static struct cgroup_subsys *cgroup_subsys[] = {
 #include <linux/cgroup_subsys.h>
 };
 
@@ -258,30 +251,13 @@ static int notify_on_release(const struct cgroup *cgrp)
 		else
 
 /**
- * for_each_subsys - iterate all loaded cgroup subsystems
+ * for_each_subsys - iterate all enabled cgroup subsystems
  * @ss: the iteration cursor
  * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end
- *
- * Iterates through all loaded subsystems.  Should be called under
- * cgroup_mutex or cgroup_root_mutex.
  */
 #define for_each_subsys(ss, ssid)					\
-	for (({ cgroup_assert_mutex_or_root_locked(); (ssid) = 0; });	\
-	     (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++)			\
-		if (!((ss) = cgroup_subsys[(ssid)])) { }		\
-		else
-
-/**
- * for_each_builtin_subsys - iterate all built-in cgroup subsystems
- * @ss: the iteration cursor
- * @i: the index of @ss, CGROUP_BUILTIN_SUBSYS_COUNT after reaching the end
- *
- * Bulit-in subsystems are always present and iteration itself doesn't
- * require any synchronization.
- */
-#define for_each_builtin_subsys(ss, i)					\
-	for ((i) = 0; (i) < CGROUP_BUILTIN_SUBSYS_COUNT &&		\
-	     (((ss) = cgroup_subsys[i]) || true); (i)++)
+	for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT &&		\
+	     (((ss) = cgroup_subsys[ssid]) || true); (ssid)++)
 
 /* iterate across the active hierarchies */
 #define for_each_active_root(root)					\
@@ -975,50 +951,24 @@ static void cgroup_d_remove_dir(struct dentry *dentry)
 	remove_dir(dentry);
 }
 
-/*
- * Call with cgroup_mutex held. Drops reference counts on modules, including
- * any duplicate ones that parse_cgroupfs_options took. If this function
- * returns an error, no reference counts are touched.
- */
 static int rebind_subsystems(struct cgroupfs_root *root,
 			     unsigned long added_mask, unsigned removed_mask)
 {
 	struct cgroup *cgrp = &root->top_cgroup;
 	struct cgroup_subsys *ss;
-	unsigned long pinned = 0;
 	int i, ret;
 
 	BUG_ON(!mutex_is_locked(&cgroup_mutex));
 	BUG_ON(!mutex_is_locked(&cgroup_root_mutex));
 
 	/* Check that any added subsystems are currently free */
-	for_each_subsys(ss, i) {
-		if (!(added_mask & (1 << i)))
-			continue;
-
-		/* is the subsystem mounted elsewhere? */
-		if (ss->root != &cgroup_dummy_root) {
-			ret = -EBUSY;
-			goto out_put;
-		}
-
-		/* pin the module */
-		if (!try_module_get(ss->module)) {
-			ret = -ENOENT;
-			goto out_put;
-		}
-		pinned |= 1 << i;
-	}
-
-	/* subsys could be missing if unloaded between parsing and here */
-	if (added_mask != pinned) {
-		ret = -ENOENT;
-		goto out_put;
-	}
+	for_each_subsys(ss, i)
+		if ((added_mask & (1 << i)) && ss->root != &cgroup_dummy_root)
+			return -EBUSY;
 
 	ret = cgroup_populate_dir(cgrp, added_mask);
 	if (ret)
-		goto out_put;
+		return ret;
 
 	/*
 	 * Nothing can fail from this point on.  Remove files for the
@@ -1057,9 +1007,6 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 			RCU_INIT_POINTER(cgrp->subsys[i], NULL);
 
 			cgroup_subsys[i]->root = &cgroup_dummy_root;
-
-			/* subsystem is now free - drop reference on module */
-			module_put(ss->module);
 			root->subsys_mask &= ~bit;
 		}
 	}
@@ -1071,12 +1018,6 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 	root->flags |= CGRP_ROOT_SUBSYS_BOUND;
 
 	return 0;
-
-out_put:
-	for_each_subsys(ss, i)
-		if (pinned & (1 << i))
-			module_put(ss->module);
-	return ret;
 }
 
 static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry)
@@ -4506,7 +4447,7 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	return ret;
 }
 
-static void __init_or_module cgroup_init_cftsets(struct cgroup_subsys *ss)
+static void __init cgroup_init_cftsets(struct cgroup_subsys *ss)
 {
 	INIT_LIST_HEAD(&ss->cftsets);
 
@@ -4559,185 +4500,8 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	BUG_ON(online_css(css));
 
 	mutex_unlock(&cgroup_mutex);
-
-	/* this function shouldn't be used with modular subsystems, since they
-	 * need to register a subsys_id, among other things */
-	BUG_ON(ss->module);
 }
 
-/**
- * cgroup_load_subsys: load and register a modular subsystem at runtime
- * @ss: the subsystem to load
- *
- * This function should be called in a modular subsystem's initcall. If the
- * subsystem is built as a module, it will be assigned a new subsys_id and set
- * up for use. If the subsystem is built-in anyway, work is delegated to the
- * simpler cgroup_init_subsys.
- */
-int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
-{
-	struct cgroup_subsys_state *css;
-	int i, ret;
-	struct hlist_node *tmp;
-	struct css_set *cset;
-	unsigned long key;
-
-	/* check name and function validity */
-	if (ss->name == NULL || strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN ||
-	    ss->css_alloc == NULL || ss->css_free == NULL)
-		return -EINVAL;
-
-	/*
-	 * we don't support callbacks in modular subsystems. this check is
-	 * before the ss->module check for consistency; a subsystem that could
-	 * be a module should still have no callbacks even if the user isn't
-	 * compiling it as one.
-	 */
-	if (ss->fork || ss->exit)
-		return -EINVAL;
-
-	/*
-	 * an optionally modular subsystem is built-in: we want to do nothing,
-	 * since cgroup_init_subsys will have already taken care of it.
-	 */
-	if (ss->module == NULL) {
-		/* a sanity check */
-		BUG_ON(cgroup_subsys[ss->subsys_id] != ss);
-		return 0;
-	}
-
-	/* init base cftset */
-	cgroup_init_cftsets(ss);
-
-	mutex_lock(&cgroup_mutex);
-	mutex_lock(&cgroup_root_mutex);
-	cgroup_subsys[ss->subsys_id] = ss;
-
-	/*
-	 * no ss->css_alloc seems to need anything important in the ss
-	 * struct, so this can happen first (i.e. before the dummy root
-	 * attachment).
-	 */
-	css = ss->css_alloc(cgroup_css(cgroup_dummy_top, ss));
-	if (IS_ERR(css)) {
-		/* failure case - need to deassign the cgroup_subsys[] slot. */
-		cgroup_subsys[ss->subsys_id] = NULL;
-		mutex_unlock(&cgroup_root_mutex);
-		mutex_unlock(&cgroup_mutex);
-		return PTR_ERR(css);
-	}
-
-	ss->root = &cgroup_dummy_root;
-
-	/* our new subsystem will be attached to the dummy hierarchy. */
-	init_css(css, ss, cgroup_dummy_top);
-
-	/*
-	 * Now we need to entangle the css into the existing css_sets. unlike
-	 * in cgroup_init_subsys, there are now multiple css_sets, so each one
-	 * will need a new pointer to it; done by iterating the css_set_table.
-	 * furthermore, modifying the existing css_sets will corrupt the hash
-	 * table state, so each changed css_set will need its hash recomputed.
-	 * this is all done under the css_set_lock.
-	 */
-	write_lock(&css_set_lock);
-	hash_for_each_safe(css_set_table, i, tmp, cset, hlist) {
-		/* skip entries that we already rehashed */
-		if (cset->subsys[ss->subsys_id])
-			continue;
-		/* remove existing entry */
-		hash_del(&cset->hlist);
-		/* set new value */
-		cset->subsys[ss->subsys_id] = css;
-		/* recompute hash and restore entry */
-		key = css_set_hash(cset->subsys);
-		hash_add(css_set_table, &cset->hlist, key);
-	}
-	write_unlock(&css_set_lock);
-
-	ret = online_css(css);
-	if (ret) {
-		ss->css_free(css);
-		goto err_unload;
-	}
-
-	/* success! */
-	mutex_unlock(&cgroup_root_mutex);
-	mutex_unlock(&cgroup_mutex);
-	return 0;
-
-err_unload:
-	mutex_unlock(&cgroup_root_mutex);
-	mutex_unlock(&cgroup_mutex);
-	/* @ss can't be mounted here as try_module_get() would fail */
-	cgroup_unload_subsys(ss);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(cgroup_load_subsys);
-
-/**
- * cgroup_unload_subsys: unload a modular subsystem
- * @ss: the subsystem to unload
- *
- * This function should be called in a modular subsystem's exitcall. When this
- * function is invoked, the refcount on the subsystem's module will be 0, so
- * the subsystem will not be attached to any hierarchy.
- */
-void cgroup_unload_subsys(struct cgroup_subsys *ss)
-{
-	struct cgrp_cset_link *link;
-	struct cgroup_subsys_state *css;
-
-	BUG_ON(ss->module == NULL);
-
-	/*
-	 * we shouldn't be called if the subsystem is in use, and the use of
-	 * try_module_get() in rebind_subsystems() should ensure that it
-	 * doesn't start being used while we're killing it off.
-	 */
-	BUG_ON(ss->root != &cgroup_dummy_root);
-
-	mutex_lock(&cgroup_mutex);
-	mutex_lock(&cgroup_root_mutex);
-
-	css = cgroup_css(cgroup_dummy_top, ss);
-	if (css)
-		offline_css(css);
-
-	/* deassign the subsys_id */
-	cgroup_subsys[ss->subsys_id] = NULL;
-
-	/*
-	 * disentangle the css from all css_sets attached to the dummy
-	 * top. as in loading, we need to pay our respects to the hashtable
-	 * gods.
-	 */
-	write_lock(&css_set_lock);
-	list_for_each_entry(link, &cgroup_dummy_top->cset_links, cset_link) {
-		struct css_set *cset = link->cset;
-		unsigned long key;
-
-		hash_del(&cset->hlist);
-		cset->subsys[ss->subsys_id] = NULL;
-		key = css_set_hash(cset->subsys);
-		hash_add(css_set_table, &cset->hlist, key);
-	}
-	write_unlock(&css_set_lock);
-
-	/*
-	 * remove subsystem's css from the cgroup_dummy_top and free it -
-	 * need to free before marking as null because ss->css_free needs
-	 * the cgrp->subsys pointer to find their state.
-	 */
-	if (css)
-		ss->css_free(css);
-	RCU_INIT_POINTER(cgroup_dummy_top->subsys[ss->subsys_id], NULL);
-
-	mutex_unlock(&cgroup_root_mutex);
-	mutex_unlock(&cgroup_mutex);
-}
-EXPORT_SYMBOL_GPL(cgroup_unload_subsys);
-
 /**
  * cgroup_init_early - cgroup initialization at system boot
  *
@@ -4763,8 +4527,7 @@ int __init cgroup_init_early(void)
 	list_add(&init_cgrp_cset_link.cset_link, &cgroup_dummy_top->cset_links);
 	list_add(&init_cgrp_cset_link.cgrp_link, &init_css_set.cgrp_links);
 
-	/* at bootup time, we don't worry about modular subsystems */
-	for_each_builtin_subsys(ss, i) {
+	for_each_subsys(ss, i) {
 		BUG_ON(!ss->name);
 		BUG_ON(strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN);
 		BUG_ON(!ss->css_alloc);
@@ -4797,7 +4560,7 @@ int __init cgroup_init(void)
 	if (err)
 		return err;
 
-	for_each_builtin_subsys(ss, i) {
+	for_each_subsys(ss, i) {
 		if (!ss->early_init)
 			cgroup_init_subsys(ss);
 	}
@@ -5032,15 +4795,7 @@ void cgroup_post_fork(struct task_struct *child)
 	 * and addition to css_set.
 	 */
 	if (need_forkexit_callback) {
-		/*
-		 * fork/exit callbacks are supported only for builtin
-		 * subsystems, and the builtin section of the subsys
-		 * array is immutable, so we don't need to lock the
-		 * subsys array here. On the other hand, modular section
-		 * of the array can be freed at module unload, so we
-		 * can't touch that.
-		 */
-		for_each_builtin_subsys(ss, i)
+		for_each_subsys(ss, i)
 			if (ss->fork)
 				ss->fork(child);
 	}
@@ -5105,11 +4860,8 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
 	RCU_INIT_POINTER(tsk->cgroups, &init_css_set);
 
 	if (run_callbacks && need_forkexit_callback) {
-		/*
-		 * fork/exit callbacks are supported only for builtin
-		 * subsystems, see cgroup_post_fork() for details.
-		 */
-		for_each_builtin_subsys(ss, i) {
+		/* see cgroup_post_fork() for details */
+		for_each_subsys(ss, i) {
 			if (ss->exit) {
 				struct cgroup_subsys_state *old_css = cset->subsys[i];
 				struct cgroup_subsys_state *css = task_css(tsk, i);
@@ -5228,11 +4980,7 @@ static int __init cgroup_disable(char *str)
 		if (!*token)
 			continue;
 
-		/*
-		 * cgroup_disable, being at boot time, can't know about
-		 * module subsystems, so we don't worry about them.
-		 */
-		for_each_builtin_subsys(ss, i) {
+		for_each_subsys(ss, i) {
 			if (!strcmp(token, ss->name)) {
 				ss->disabled = 1;
 				printk(KERN_INFO "Disabling %s control group"
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 9fc7f90d034c..9e5ad5d74e60 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -110,5 +110,4 @@ struct cgroup_subsys net_cls_subsys = {
 	.attach			= cgrp_attach,
 	.subsys_id		= net_cls_subsys_id,
 	.base_cftypes		= ss_files,
-	.module			= THIS_MODULE,
 };
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index cc3a31e7dc08..857e1603f9b7 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -252,7 +252,6 @@ struct cgroup_subsys net_prio_subsys = {
 	.attach		= net_prio_attach,
 	.subsys_id	= net_prio_subsys_id,
 	.base_cftypes	= ss_files,
-	.module		= THIS_MODULE,
 };
 
 static int netprio_device_event(struct notifier_block *unused,
-- 
cgit v1.2.3


From 073219e995b4a3f8cf1ce8228b7ef440b6994ac0 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Sat, 8 Feb 2014 10:36:58 -0500
Subject: cgroup: clean up cgroup_subsys names and initialization

cgroup_subsys is a bit messier than it needs to be.

* The name of a subsys can be different from its internal identifier
  defined in cgroup_subsys.h.  Most subsystems use the matching name
  but three - cpu, memory and perf_event - use different ones.

* cgroup_subsys_id enums are postfixed with _subsys_id and each
  cgroup_subsys is postfixed with _subsys.  cgroup.h is widely
  included throughout various subsystems, it doesn't and shouldn't
  have claim on such generic names which don't have any qualifier
  indicating that they belong to cgroup.

* cgroup_subsys->subsys_id should always equal the matching
  cgroup_subsys_id enum; however, we require each controller to
  initialize it and then BUG if they don't match, which is a bit
  silly.

This patch cleans up cgroup_subsys names and initialization by doing
the followings.

* cgroup_subsys_id enums are now postfixed with _cgrp_id, and each
  cgroup_subsys with _cgrp_subsys.

* With the above, renaming subsys identifiers to match the userland
  visible names doesn't cause any naming conflicts.  All non-matching
  identifiers are renamed to match the official names.

  cpu_cgroup -> cpu
  mem_cgroup -> memory
  perf -> perf_event

* controllers no longer need to initialize ->subsys_id and ->name.
  They're generated in cgroup core and set automatically during boot.

* Redundant cgroup_subsys declarations removed.

* While updating BUG_ON()s in cgroup_init_early(), convert them to
  WARN()s.  BUGging that early during boot is stupid - the kernel
  can't print anything, even through serial console and the trap
  handler doesn't even link stack frame properly for back-tracing.

This patch doesn't introduce any behavior changes.

v2: Rebased on top of fe1217c4f3f7 ("net: net_cls: move cgroupfs
    classid handling into core").

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: "David S. Miller" <davem@davemloft.net>
Acked-by: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Aristeu Rozanski <aris@redhat.com>
Acked-by: Ingo Molnar <mingo@redhat.com>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Serge E. Hallyn <serue@us.ibm.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Thomas Graf <tgraf@suug.ch>
---
 block/blk-cgroup.c             |  8 +++-----
 block/blk-cgroup.h             |  2 +-
 fs/bio.c                       |  2 +-
 include/linux/cgroup.h         |  7 ++++---
 include/linux/cgroup_subsys.h  |  6 +++---
 include/linux/hugetlb_cgroup.h |  2 +-
 include/linux/memcontrol.h     |  2 +-
 include/net/cls_cgroup.h       |  2 +-
 include/net/netprio_cgroup.h   |  2 +-
 kernel/cgroup.c                | 34 ++++++++++++++++++++--------------
 kernel/cgroup_freezer.c        |  8 ++------
 kernel/cpuset.c                | 10 ++++------
 kernel/events/core.c           |  8 +++-----
 kernel/sched/core.c            |  6 ++----
 kernel/sched/cpuacct.c         |  6 ++----
 mm/hugetlb_cgroup.c            |  9 +++------
 mm/memcontrol.c                | 22 ++++++++++------------
 net/core/netclassid_cgroup.c   |  6 ++----
 net/core/netprio_cgroup.c      |  4 +---
 net/ipv4/tcp_memcontrol.c      |  2 +-
 security/device_cgroup.c       |  8 ++------
 21 files changed, 68 insertions(+), 88 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 660d419918a7..1cef07cf9c21 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -906,16 +906,14 @@ static int blkcg_can_attach(struct cgroup_subsys_state *css,
 	return ret;
 }
 
-struct cgroup_subsys blkio_subsys = {
-	.name = "blkio",
+struct cgroup_subsys blkio_cgrp_subsys = {
 	.css_alloc = blkcg_css_alloc,
 	.css_offline = blkcg_css_offline,
 	.css_free = blkcg_css_free,
 	.can_attach = blkcg_can_attach,
-	.subsys_id = blkio_subsys_id,
 	.base_cftypes = blkcg_files,
 };
-EXPORT_SYMBOL_GPL(blkio_subsys);
+EXPORT_SYMBOL_GPL(blkio_cgrp_subsys);
 
 /**
  * blkcg_activate_policy - activate a blkcg policy on a request_queue
@@ -1105,7 +1103,7 @@ int blkcg_policy_register(struct blkcg_policy *pol)
 
 	/* everything is in place, add intf files for the new policy */
 	if (pol->cftypes)
-		WARN_ON(cgroup_add_cftypes(&blkio_subsys, pol->cftypes));
+		WARN_ON(cgroup_add_cftypes(&blkio_cgrp_subsys, pol->cftypes));
 	ret = 0;
 out_unlock:
 	mutex_unlock(&blkcg_pol_mutex);
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 86154eab9523..453b528c8e19 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -186,7 +186,7 @@ static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css)
 
 static inline struct blkcg *task_blkcg(struct task_struct *tsk)
 {
-	return css_to_blkcg(task_css(tsk, blkio_subsys_id));
+	return css_to_blkcg(task_css(tsk, blkio_cgrp_id));
 }
 
 static inline struct blkcg *bio_blkcg(struct bio *bio)
diff --git a/fs/bio.c b/fs/bio.c
index 75c49a382239..4872102b839e 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -1965,7 +1965,7 @@ int bio_associate_current(struct bio *bio)
 
 	/* associate blkcg if exists */
 	rcu_read_lock();
-	css = task_css(current, blkio_subsys_id);
+	css = task_css(current, blkio_cgrp_id);
 	if (css && css_tryget(css))
 		bio->bi_css = css;
 	rcu_read_unlock();
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index d842a737d448..cd6611e622fd 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -41,7 +41,7 @@ extern int cgroupstats_build(struct cgroupstats *stats,
 extern int proc_cgroup_show(struct seq_file *, void *);
 
 /* define the enumeration of all cgroup subsystems */
-#define SUBSYS(_x) _x ## _subsys_id,
+#define SUBSYS(_x) _x ## _cgrp_id,
 enum cgroup_subsys_id {
 #include <linux/cgroup_subsys.h>
 	CGROUP_SUBSYS_COUNT,
@@ -573,7 +573,6 @@ struct cgroup_subsys {
 		     struct task_struct *task);
 	void (*bind)(struct cgroup_subsys_state *root_css);
 
-	int subsys_id;
 	int disabled;
 	int early_init;
 
@@ -592,6 +591,8 @@ struct cgroup_subsys {
 	bool broken_hierarchy;
 	bool warned_broken_hierarchy;
 
+	/* the following two fields are initialized automtically during boot */
+	int subsys_id;
 #define MAX_CGROUP_TYPE_NAMELEN 32
 	const char *name;
 
@@ -606,7 +607,7 @@ struct cgroup_subsys {
 	struct cftype_set base_cftset;
 };
 
-#define SUBSYS(_x) extern struct cgroup_subsys _x ## _subsys;
+#define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys;
 #include <linux/cgroup_subsys.h>
 #undef SUBSYS
 
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index 11c42f6a25a8..768fe44e19f0 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -12,7 +12,7 @@ SUBSYS(debug)
 #endif
 
 #if IS_ENABLED(CONFIG_CGROUP_SCHED)
-SUBSYS(cpu_cgroup)
+SUBSYS(cpu)
 #endif
 
 #if IS_ENABLED(CONFIG_CGROUP_CPUACCT)
@@ -20,7 +20,7 @@ SUBSYS(cpuacct)
 #endif
 
 #if IS_ENABLED(CONFIG_MEMCG)
-SUBSYS(mem_cgroup)
+SUBSYS(memory)
 #endif
 
 #if IS_ENABLED(CONFIG_CGROUP_DEVICE)
@@ -40,7 +40,7 @@ SUBSYS(blkio)
 #endif
 
 #if IS_ENABLED(CONFIG_CGROUP_PERF)
-SUBSYS(perf)
+SUBSYS(perf_event)
 #endif
 
 #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
index 787bba3bf552..0129f89cf98d 100644
--- a/include/linux/hugetlb_cgroup.h
+++ b/include/linux/hugetlb_cgroup.h
@@ -49,7 +49,7 @@ int set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg)
 
 static inline bool hugetlb_cgroup_disabled(void)
 {
-	if (hugetlb_subsys.disabled)
+	if (hugetlb_cgrp_subsys.disabled)
 		return true;
 	return false;
 }
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index abd0113b6620..eccfb4a4b379 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -162,7 +162,7 @@ extern int do_swap_account;
 
 static inline bool mem_cgroup_disabled(void)
 {
-	if (mem_cgroup_subsys.disabled)
+	if (memory_cgrp_subsys.disabled)
 		return true;
 	return false;
 }
diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h
index 9cf2d5ef38d9..c15d39456e14 100644
--- a/include/net/cls_cgroup.h
+++ b/include/net/cls_cgroup.h
@@ -34,7 +34,7 @@ static inline u32 task_cls_classid(struct task_struct *p)
 		return 0;
 
 	rcu_read_lock();
-	classid = container_of(task_css(p, net_cls_subsys_id),
+	classid = container_of(task_css(p, net_cls_cgrp_id),
 			       struct cgroup_cls_state, css)->classid;
 	rcu_read_unlock();
 
diff --git a/include/net/netprio_cgroup.h b/include/net/netprio_cgroup.h
index b7ff5bd3c3c3..f2a9597ff53c 100644
--- a/include/net/netprio_cgroup.h
+++ b/include/net/netprio_cgroup.h
@@ -33,7 +33,7 @@ static inline u32 task_netprioidx(struct task_struct *p)
 	u32 idx;
 
 	rcu_read_lock();
-	css = task_css(p, net_prio_subsys_id);
+	css = task_css(p, net_prio_cgrp_id);
 	idx = css->cgroup->id;
 	rcu_read_unlock();
 	return idx;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index ccb16b47e293..fe3f7253aa90 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -120,10 +120,18 @@ static struct workqueue_struct *cgroup_destroy_wq;
 static struct workqueue_struct *cgroup_pidlist_destroy_wq;
 
 /* generate an array of cgroup subsystem pointers */
-#define SUBSYS(_x) [_x ## _subsys_id] = &_x ## _subsys,
+#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys,
 static struct cgroup_subsys *cgroup_subsys[] = {
 #include <linux/cgroup_subsys.h>
 };
+#undef SUBSYS
+
+/* array of cgroup subsystem names */
+#define SUBSYS(_x) [_x ## _cgrp_id] = #_x,
+static const char *cgroup_subsys_name[] = {
+#include <linux/cgroup_subsys.h>
+};
+#undef SUBSYS
 
 /*
  * The dummy hierarchy, reserved for the subsystems that are otherwise
@@ -1076,7 +1084,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 	BUG_ON(!mutex_is_locked(&cgroup_mutex));
 
 #ifdef CONFIG_CPUSETS
-	mask = ~(1UL << cpuset_subsys_id);
+	mask = ~(1UL << cpuset_cgrp_id);
 #endif
 
 	memset(opts, 0, sizeof(*opts));
@@ -4528,15 +4536,15 @@ int __init cgroup_init_early(void)
 	list_add(&init_cgrp_cset_link.cgrp_link, &init_css_set.cgrp_links);
 
 	for_each_subsys(ss, i) {
-		BUG_ON(!ss->name);
-		BUG_ON(strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN);
-		BUG_ON(!ss->css_alloc);
-		BUG_ON(!ss->css_free);
-		if (ss->subsys_id != i) {
-			printk(KERN_ERR "cgroup: Subsys %s id == %d\n",
-			       ss->name, ss->subsys_id);
-			BUG();
-		}
+		WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->subsys_id,
+		     "invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p name:id=%d:%s\n",
+		     i, cgroup_subsys_name[i], ss->css_alloc, ss->css_free,
+		     ss->subsys_id, ss->name);
+		WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN,
+		     "cgroup_subsys_name %s too long\n", cgroup_subsys_name[i]);
+
+		ss->subsys_id = i;
+		ss->name = cgroup_subsys_name[i];
 
 		if (ss->early_init)
 			cgroup_init_subsys(ss);
@@ -5167,11 +5175,9 @@ static struct cftype debug_files[] =  {
 	{ }	/* terminate */
 };
 
-struct cgroup_subsys debug_subsys = {
-	.name = "debug",
+struct cgroup_subsys debug_cgrp_subsys = {
 	.css_alloc = debug_css_alloc,
 	.css_free = debug_css_free,
-	.subsys_id = debug_subsys_id,
 	.base_cftypes = debug_files,
 };
 #endif /* CONFIG_CGROUP_DEBUG */
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index 6c3154e477f6..98ea26a99076 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -52,7 +52,7 @@ static inline struct freezer *css_freezer(struct cgroup_subsys_state *css)
 
 static inline struct freezer *task_freezer(struct task_struct *task)
 {
-	return css_freezer(task_css(task, freezer_subsys_id));
+	return css_freezer(task_css(task, freezer_cgrp_id));
 }
 
 static struct freezer *parent_freezer(struct freezer *freezer)
@@ -84,8 +84,6 @@ static const char *freezer_state_strs(unsigned int state)
 	return "THAWED";
 };
 
-struct cgroup_subsys freezer_subsys;
-
 static struct cgroup_subsys_state *
 freezer_css_alloc(struct cgroup_subsys_state *parent_css)
 {
@@ -473,13 +471,11 @@ static struct cftype files[] = {
 	{ }	/* terminate */
 };
 
-struct cgroup_subsys freezer_subsys = {
-	.name		= "freezer",
+struct cgroup_subsys freezer_cgrp_subsys = {
 	.css_alloc	= freezer_css_alloc,
 	.css_online	= freezer_css_online,
 	.css_offline	= freezer_css_offline,
 	.css_free	= freezer_css_free,
-	.subsys_id	= freezer_subsys_id,
 	.attach		= freezer_attach,
 	.fork		= freezer_fork,
 	.base_cftypes	= files,
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 4410ac6a55f1..2d018c795fea 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -119,7 +119,7 @@ static inline struct cpuset *css_cs(struct cgroup_subsys_state *css)
 /* Retrieve the cpuset for a task */
 static inline struct cpuset *task_cs(struct task_struct *task)
 {
-	return css_cs(task_css(task, cpuset_subsys_id));
+	return css_cs(task_css(task, cpuset_cgrp_id));
 }
 
 static inline struct cpuset *parent_cs(struct cpuset *cs)
@@ -1521,7 +1521,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 	struct task_struct *task;
 	struct task_struct *leader = cgroup_taskset_first(tset);
 	struct cgroup_subsys_state *oldcss = cgroup_taskset_cur_css(tset,
-							cpuset_subsys_id);
+							cpuset_cgrp_id);
 	struct cpuset *cs = css_cs(css);
 	struct cpuset *oldcs = css_cs(oldcss);
 	struct cpuset *cpus_cs = effective_cpumask_cpuset(cs);
@@ -2024,8 +2024,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css)
 	kfree(cs);
 }
 
-struct cgroup_subsys cpuset_subsys = {
-	.name = "cpuset",
+struct cgroup_subsys cpuset_cgrp_subsys = {
 	.css_alloc = cpuset_css_alloc,
 	.css_online = cpuset_css_online,
 	.css_offline = cpuset_css_offline,
@@ -2033,7 +2032,6 @@ struct cgroup_subsys cpuset_subsys = {
 	.can_attach = cpuset_can_attach,
 	.cancel_attach = cpuset_cancel_attach,
 	.attach = cpuset_attach,
-	.subsys_id = cpuset_subsys_id,
 	.base_cftypes = files,
 	.early_init = 1,
 };
@@ -2699,7 +2697,7 @@ int proc_cpuset_show(struct seq_file *m, void *unused_v)
 		goto out_free;
 
 	rcu_read_lock();
-	css = task_css(tsk, cpuset_subsys_id);
+	css = task_css(tsk, cpuset_cgrp_id);
 	retval = cgroup_path(css->cgroup, buf, PAGE_SIZE);
 	rcu_read_unlock();
 	if (retval < 0)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 56003c6edfd3..64903731d834 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -342,7 +342,7 @@ struct perf_cgroup {
 static inline struct perf_cgroup *
 perf_cgroup_from_task(struct task_struct *task)
 {
-	return container_of(task_css(task, perf_subsys_id),
+	return container_of(task_css(task, perf_event_cgrp_id),
 			    struct perf_cgroup, css);
 }
 
@@ -595,7 +595,7 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 
 	rcu_read_lock();
 
-	css = css_from_dir(f.file->f_dentry, &perf_subsys);
+	css = css_from_dir(f.file->f_dentry, &perf_event_cgrp_subsys);
 	if (IS_ERR(css)) {
 		ret = PTR_ERR(css);
 		goto out;
@@ -8055,9 +8055,7 @@ static void perf_cgroup_exit(struct cgroup_subsys_state *css,
 	task_function_call(task, __perf_cgroup_move, task);
 }
 
-struct cgroup_subsys perf_subsys = {
-	.name		= "perf_event",
-	.subsys_id	= perf_subsys_id,
+struct cgroup_subsys perf_event_cgrp_subsys = {
 	.css_alloc	= perf_cgroup_css_alloc,
 	.css_free	= perf_cgroup_css_free,
 	.exit		= perf_cgroup_exit,
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b46131ef6aab..d4cfc5561830 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7176,7 +7176,7 @@ void sched_move_task(struct task_struct *tsk)
 	if (unlikely(running))
 		tsk->sched_class->put_prev_task(rq, tsk);
 
-	tg = container_of(task_css_check(tsk, cpu_cgroup_subsys_id,
+	tg = container_of(task_css_check(tsk, cpu_cgrp_id,
 				lockdep_is_held(&tsk->sighand->siglock)),
 			  struct task_group, css);
 	tg = autogroup_task_group(tsk, tg);
@@ -7957,8 +7957,7 @@ static struct cftype cpu_files[] = {
 	{ }	/* terminate */
 };
 
-struct cgroup_subsys cpu_cgroup_subsys = {
-	.name		= "cpu",
+struct cgroup_subsys cpu_cgrp_subsys = {
 	.css_alloc	= cpu_cgroup_css_alloc,
 	.css_free	= cpu_cgroup_css_free,
 	.css_online	= cpu_cgroup_css_online,
@@ -7966,7 +7965,6 @@ struct cgroup_subsys cpu_cgroup_subsys = {
 	.can_attach	= cpu_cgroup_can_attach,
 	.attach		= cpu_cgroup_attach,
 	.exit		= cpu_cgroup_exit,
-	.subsys_id	= cpu_cgroup_subsys_id,
 	.base_cftypes	= cpu_files,
 	.early_init	= 1,
 };
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index 622e0818f905..c143ee380e3a 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -41,7 +41,7 @@ static inline struct cpuacct *css_ca(struct cgroup_subsys_state *css)
 /* return cpu accounting group to which this task belongs */
 static inline struct cpuacct *task_ca(struct task_struct *tsk)
 {
-	return css_ca(task_css(tsk, cpuacct_subsys_id));
+	return css_ca(task_css(tsk, cpuacct_cgrp_id));
 }
 
 static inline struct cpuacct *parent_ca(struct cpuacct *ca)
@@ -275,11 +275,9 @@ void cpuacct_account_field(struct task_struct *p, int index, u64 val)
 	rcu_read_unlock();
 }
 
-struct cgroup_subsys cpuacct_subsys = {
-	.name		= "cpuacct",
+struct cgroup_subsys cpuacct_cgrp_subsys = {
 	.css_alloc	= cpuacct_css_alloc,
 	.css_free	= cpuacct_css_free,
-	.subsys_id	= cpuacct_subsys_id,
 	.base_cftypes	= files,
 	.early_init	= 1,
 };
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index cb00829bb466..b135853e68f3 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -30,7 +30,6 @@ struct hugetlb_cgroup {
 #define MEMFILE_IDX(val)	(((val) >> 16) & 0xffff)
 #define MEMFILE_ATTR(val)	((val) & 0xffff)
 
-struct cgroup_subsys hugetlb_subsys __read_mostly;
 static struct hugetlb_cgroup *root_h_cgroup __read_mostly;
 
 static inline
@@ -42,7 +41,7 @@ struct hugetlb_cgroup *hugetlb_cgroup_from_css(struct cgroup_subsys_state *s)
 static inline
 struct hugetlb_cgroup *hugetlb_cgroup_from_task(struct task_struct *task)
 {
-	return hugetlb_cgroup_from_css(task_css(task, hugetlb_subsys_id));
+	return hugetlb_cgroup_from_css(task_css(task, hugetlb_cgrp_id));
 }
 
 static inline bool hugetlb_cgroup_is_root(struct hugetlb_cgroup *h_cg)
@@ -358,7 +357,7 @@ static void __init __hugetlb_cgroup_file_init(int idx)
 	cft = &h->cgroup_files[4];
 	memset(cft, 0, sizeof(*cft));
 
-	WARN_ON(cgroup_add_cftypes(&hugetlb_subsys, h->cgroup_files));
+	WARN_ON(cgroup_add_cftypes(&hugetlb_cgrp_subsys, h->cgroup_files));
 
 	return;
 }
@@ -402,10 +401,8 @@ void hugetlb_cgroup_migrate(struct page *oldhpage, struct page *newhpage)
 	return;
 }
 
-struct cgroup_subsys hugetlb_subsys = {
-	.name = "hugetlb",
+struct cgroup_subsys hugetlb_cgrp_subsys = {
 	.css_alloc	= hugetlb_cgroup_css_alloc,
 	.css_offline	= hugetlb_cgroup_css_offline,
 	.css_free	= hugetlb_cgroup_css_free,
-	.subsys_id	= hugetlb_subsys_id,
 };
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 53385cd4e6f0..04a97bce2270 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -66,8 +66,8 @@
 
 #include <trace/events/vmscan.h>
 
-struct cgroup_subsys mem_cgroup_subsys __read_mostly;
-EXPORT_SYMBOL(mem_cgroup_subsys);
+struct cgroup_subsys memory_cgrp_subsys __read_mostly;
+EXPORT_SYMBOL(memory_cgrp_subsys);
 
 #define MEM_CGROUP_RECLAIM_RETRIES	5
 static struct mem_cgroup *root_mem_cgroup __read_mostly;
@@ -538,7 +538,7 @@ static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
 {
 	struct cgroup_subsys_state *css;
 
-	css = css_from_id(id - 1, &mem_cgroup_subsys);
+	css = css_from_id(id - 1, &memory_cgrp_subsys);
 	return mem_cgroup_from_css(css);
 }
 
@@ -1072,7 +1072,7 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 	if (unlikely(!p))
 		return NULL;
 
-	return mem_cgroup_from_css(task_css(p, mem_cgroup_subsys_id));
+	return mem_cgroup_from_css(task_css(p, memory_cgrp_id));
 }
 
 struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
@@ -1702,7 +1702,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 	rcu_read_lock();
 
 	mem_cgrp = memcg->css.cgroup;
-	task_cgrp = task_cgroup(p, mem_cgroup_subsys_id);
+	task_cgrp = task_cgroup(p, memory_cgrp_id);
 
 	ret = cgroup_path(task_cgrp, memcg_name, PATH_MAX);
 	if (ret < 0) {
@@ -6187,7 +6187,7 @@ static int memcg_write_event_control(struct cgroup_subsys_state *css,
 
 	ret = -EINVAL;
 	cfile_css = css_from_dir(cfile.file->f_dentry->d_parent,
-				 &mem_cgroup_subsys);
+				 &memory_cgrp_subsys);
 	if (cfile_css == css && css_tryget(css))
 		ret = 0;
 
@@ -6566,11 +6566,11 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 		 * unfortunate state in our controller.
 		 */
 		if (parent != root_mem_cgroup)
-			mem_cgroup_subsys.broken_hierarchy = true;
+			memory_cgrp_subsys.broken_hierarchy = true;
 	}
 	mutex_unlock(&memcg_create_mutex);
 
-	return memcg_init_kmem(memcg, &mem_cgroup_subsys);
+	return memcg_init_kmem(memcg, &memory_cgrp_subsys);
 }
 
 /*
@@ -7264,9 +7264,7 @@ static void mem_cgroup_bind(struct cgroup_subsys_state *root_css)
 		mem_cgroup_from_css(root_css)->use_hierarchy = true;
 }
 
-struct cgroup_subsys mem_cgroup_subsys = {
-	.name = "memory",
-	.subsys_id = mem_cgroup_subsys_id,
+struct cgroup_subsys memory_cgrp_subsys = {
 	.css_alloc = mem_cgroup_css_alloc,
 	.css_online = mem_cgroup_css_online,
 	.css_offline = mem_cgroup_css_offline,
@@ -7292,7 +7290,7 @@ __setup("swapaccount=", enable_swap_account);
 
 static void __init memsw_file_init(void)
 {
-	WARN_ON(cgroup_add_cftypes(&mem_cgroup_subsys, memsw_cgroup_files));
+	WARN_ON(cgroup_add_cftypes(&memory_cgrp_subsys, memsw_cgroup_files));
 }
 
 static void __init enable_swap_cgroup(void)
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 9e5ad5d74e60..b865662fba71 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -23,7 +23,7 @@ static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state
 
 struct cgroup_cls_state *task_cls_state(struct task_struct *p)
 {
-	return css_cls_state(task_css(p, net_cls_subsys_id));
+	return css_cls_state(task_css(p, net_cls_cgrp_id));
 }
 EXPORT_SYMBOL_GPL(task_cls_state);
 
@@ -102,12 +102,10 @@ static struct cftype ss_files[] = {
 	{ }	/* terminate */
 };
 
-struct cgroup_subsys net_cls_subsys = {
-	.name			= "net_cls",
+struct cgroup_subsys net_cls_cgrp_subsys = {
 	.css_alloc		= cgrp_css_alloc,
 	.css_online		= cgrp_css_online,
 	.css_free		= cgrp_css_free,
 	.attach			= cgrp_attach,
-	.subsys_id		= net_cls_subsys_id,
 	.base_cftypes		= ss_files,
 };
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 857e1603f9b7..d7d23e28fafd 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -244,13 +244,11 @@ static struct cftype ss_files[] = {
 	{ }	/* terminate */
 };
 
-struct cgroup_subsys net_prio_subsys = {
-	.name		= "net_prio",
+struct cgroup_subsys net_prio_cgrp_subsys = {
 	.css_alloc	= cgrp_css_alloc,
 	.css_online	= cgrp_css_online,
 	.css_free	= cgrp_css_free,
 	.attach		= net_prio_attach,
-	.subsys_id	= net_prio_subsys_id,
 	.base_cftypes	= ss_files,
 };
 
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index f7e522c558ba..20a0aca9131e 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -219,7 +219,7 @@ static struct cftype tcp_files[] = {
 
 static int __init tcp_memcontrol_init(void)
 {
-	WARN_ON(cgroup_add_cftypes(&mem_cgroup_subsys, tcp_files));
+	WARN_ON(cgroup_add_cftypes(&memory_cgrp_subsys, tcp_files));
 	return 0;
 }
 __initcall(tcp_memcontrol_init);
diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index d3b6d2cd3a06..7f88bcde7c61 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -58,11 +58,9 @@ static inline struct dev_cgroup *css_to_devcgroup(struct cgroup_subsys_state *s)
 
 static inline struct dev_cgroup *task_devcgroup(struct task_struct *task)
 {
-	return css_to_devcgroup(task_css(task, devices_subsys_id));
+	return css_to_devcgroup(task_css(task, devices_cgrp_id));
 }
 
-struct cgroup_subsys devices_subsys;
-
 /*
  * called under devcgroup_mutex
  */
@@ -684,13 +682,11 @@ static struct cftype dev_cgroup_files[] = {
 	{ }	/* terminate */
 };
 
-struct cgroup_subsys devices_subsys = {
-	.name = "devices",
+struct cgroup_subsys devices_cgrp_subsys = {
 	.css_alloc = devcgroup_css_alloc,
 	.css_free = devcgroup_css_free,
 	.css_online = devcgroup_online,
 	.css_offline = devcgroup_offline,
-	.subsys_id = devices_subsys_id,
 	.base_cftypes = dev_cgroup_files,
 };
 
-- 
cgit v1.2.3


From aec25020f5d4b69aea5317551d1cb7043f6b04fb Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Sat, 8 Feb 2014 10:36:58 -0500
Subject: cgroup: rename cgroup_subsys->subsys_id to ->id

It's no longer referenced outside cgroup core, so renaming is easy.
Let's rename it for consistency & brevity.

This patch is pure rename.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h |  4 ++--
 kernel/cgroup.c        | 20 ++++++++++----------
 2 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index cd6611e622fd..198c7fcd727e 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -548,7 +548,7 @@ int cgroup_taskset_size(struct cgroup_taskset *tset);
 	     (task) = cgroup_taskset_next((tset)))			\
 		if (!(skip_css) ||					\
 		    cgroup_taskset_cur_css((tset),			\
-			(skip_css)->ss->subsys_id) != (skip_css))
+			(skip_css)->ss->id) != (skip_css))
 
 /*
  * Control Group subsystem type.
@@ -592,7 +592,7 @@ struct cgroup_subsys {
 	bool warned_broken_hierarchy;
 
 	/* the following two fields are initialized automtically during boot */
-	int subsys_id;
+	int id;
 #define MAX_CGROUP_TYPE_NAMELEN 32
 	const char *name;
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index fe3f7253aa90..5a77ca0784a6 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -198,7 +198,7 @@ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp,
 					      struct cgroup_subsys *ss)
 {
 	if (ss)
-		return rcu_dereference_check(cgrp->subsys[ss->subsys_id],
+		return rcu_dereference_check(cgrp->subsys[ss->id],
 					     lockdep_is_held(&cgroup_mutex));
 	else
 		return &cgrp->dummy_css;
@@ -3982,7 +3982,7 @@ static void css_release(struct percpu_ref *ref)
 	struct cgroup_subsys_state *css =
 		container_of(ref, struct cgroup_subsys_state, refcnt);
 
-	rcu_assign_pointer(css->cgroup->subsys[css->ss->subsys_id], NULL);
+	rcu_assign_pointer(css->cgroup->subsys[css->ss->id], NULL);
 	call_rcu(&css->rcu_head, css_free_rcu_fn);
 }
 
@@ -4014,7 +4014,7 @@ static int online_css(struct cgroup_subsys_state *css)
 	if (!ret) {
 		css->flags |= CSS_ONLINE;
 		css->cgroup->nr_css++;
-		rcu_assign_pointer(css->cgroup->subsys[ss->subsys_id], css);
+		rcu_assign_pointer(css->cgroup->subsys[ss->id], css);
 	}
 	return ret;
 }
@@ -4034,7 +4034,7 @@ static void offline_css(struct cgroup_subsys_state *css)
 
 	css->flags &= ~CSS_ONLINE;
 	css->cgroup->nr_css--;
-	RCU_INIT_POINTER(css->cgroup->subsys[ss->subsys_id], css);
+	RCU_INIT_POINTER(css->cgroup->subsys[ss->id], css);
 }
 
 /**
@@ -4065,7 +4065,7 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss)
 
 	init_css(css, ss, cgrp);
 
-	err = cgroup_populate_dir(cgrp, 1 << ss->subsys_id);
+	err = cgroup_populate_dir(cgrp, 1 << ss->id);
 	if (err)
 		goto err_free;
 
@@ -4292,7 +4292,7 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
  */
 static void kill_css(struct cgroup_subsys_state *css)
 {
-	cgroup_clear_dir(css->cgroup, 1 << css->ss->subsys_id);
+	cgroup_clear_dir(css->cgroup, 1 << css->ss->id);
 
 	/*
 	 * Killing would put the base ref, but we need to keep it alive
@@ -4496,7 +4496,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	 * pointer to this state - since the subsystem is
 	 * newly registered, all tasks and hence the
 	 * init_css_set is in the subsystem's top cgroup. */
-	init_css_set.subsys[ss->subsys_id] = css;
+	init_css_set.subsys[ss->id] = css;
 
 	need_forkexit_callback |= ss->fork || ss->exit;
 
@@ -4536,14 +4536,14 @@ int __init cgroup_init_early(void)
 	list_add(&init_cgrp_cset_link.cgrp_link, &init_css_set.cgrp_links);
 
 	for_each_subsys(ss, i) {
-		WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->subsys_id,
+		WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->id,
 		     "invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p name:id=%d:%s\n",
 		     i, cgroup_subsys_name[i], ss->css_alloc, ss->css_free,
-		     ss->subsys_id, ss->name);
+		     ss->id, ss->name);
 		WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN,
 		     "cgroup_subsys_name %s too long\n", cgroup_subsys_name[i]);
 
-		ss->subsys_id = i;
+		ss->id = i;
 		ss->name = cgroup_subsys_name[i];
 
 		if (ss->early_init)
-- 
cgit v1.2.3


From c11baa02c5d6ea06362fa61da070af34b7706c83 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Fri, 24 Jan 2014 16:18:02 -0600
Subject: crypto: ccp - Move HMAC calculation down to ccp ops file

Move the support to perform an HMAC calculation into
the CCP operations file.  This eliminates the need to
perform a synchronous SHA operation used to calculate
the HMAC.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccp/ccp-crypto-sha.c | 130 +++++++-----------------------------
 drivers/crypto/ccp/ccp-crypto.h     |   8 +--
 drivers/crypto/ccp/ccp-ops.c        | 104 ++++++++++++++++++++++++++++-
 include/linux/ccp.h                 |   7 ++
 4 files changed, 139 insertions(+), 110 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/crypto/ccp/ccp-crypto-sha.c b/drivers/crypto/ccp/ccp-crypto-sha.c
index 3867290b3531..873f23425245 100644
--- a/drivers/crypto/ccp/ccp-crypto-sha.c
+++ b/drivers/crypto/ccp/ccp-crypto-sha.c
@@ -24,75 +24,10 @@
 #include "ccp-crypto.h"
 
 
-struct ccp_sha_result {
-	struct completion completion;
-	int err;
-};
-
-static void ccp_sync_hash_complete(struct crypto_async_request *req, int err)
-{
-	struct ccp_sha_result *result = req->data;
-
-	if (err == -EINPROGRESS)
-		return;
-
-	result->err = err;
-	complete(&result->completion);
-}
-
-static int ccp_sync_hash(struct crypto_ahash *tfm, u8 *buf,
-			 struct scatterlist *sg, unsigned int len)
-{
-	struct ccp_sha_result result;
-	struct ahash_request *req;
-	int ret;
-
-	init_completion(&result.completion);
-
-	req = ahash_request_alloc(tfm, GFP_KERNEL);
-	if (!req)
-		return -ENOMEM;
-
-	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
-				   ccp_sync_hash_complete, &result);
-	ahash_request_set_crypt(req, sg, buf, len);
-
-	ret = crypto_ahash_digest(req);
-	if ((ret == -EINPROGRESS) || (ret == -EBUSY)) {
-		ret = wait_for_completion_interruptible(&result.completion);
-		if (!ret)
-			ret = result.err;
-	}
-
-	ahash_request_free(req);
-
-	return ret;
-}
-
-static int ccp_sha_finish_hmac(struct crypto_async_request *async_req)
-{
-	struct ahash_request *req = ahash_request_cast(async_req);
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct ccp_ctx *ctx = crypto_ahash_ctx(tfm);
-	struct ccp_sha_req_ctx *rctx = ahash_request_ctx(req);
-	struct scatterlist sg[2];
-	unsigned int block_size =
-		crypto_tfm_alg_blocksize(crypto_ahash_tfm(tfm));
-	unsigned int digest_size = crypto_ahash_digestsize(tfm);
-
-	sg_init_table(sg, ARRAY_SIZE(sg));
-	sg_set_buf(&sg[0], ctx->u.sha.opad, block_size);
-	sg_set_buf(&sg[1], rctx->ctx, digest_size);
-
-	return ccp_sync_hash(ctx->u.sha.hmac_tfm, req->result, sg,
-			     block_size + digest_size);
-}
-
 static int ccp_sha_complete(struct crypto_async_request *async_req, int ret)
 {
 	struct ahash_request *req = ahash_request_cast(async_req);
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct ccp_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct ccp_sha_req_ctx *rctx = ahash_request_ctx(req);
 	unsigned int digest_size = crypto_ahash_digestsize(tfm);
 
@@ -112,10 +47,6 @@ static int ccp_sha_complete(struct crypto_async_request *async_req, int ret)
 	if (req->result)
 		memcpy(req->result, rctx->ctx, digest_size);
 
-	/* If we're doing an HMAC, we need to perform that on the final op */
-	if (rctx->final && ctx->u.sha.key_len)
-		ret = ccp_sha_finish_hmac(async_req);
-
 e_free:
 	sg_free_table(&rctx->data_sg);
 
@@ -126,6 +57,7 @@ static int ccp_do_sha_update(struct ahash_request *req, unsigned int nbytes,
 			     unsigned int final)
 {
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ccp_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct ccp_sha_req_ctx *rctx = ahash_request_ctx(req);
 	struct scatterlist *sg;
 	unsigned int block_size =
@@ -196,6 +128,11 @@ static int ccp_do_sha_update(struct ahash_request *req, unsigned int nbytes,
 	rctx->cmd.u.sha.ctx_len = sizeof(rctx->ctx);
 	rctx->cmd.u.sha.src = sg;
 	rctx->cmd.u.sha.src_len = rctx->hash_cnt;
+	rctx->cmd.u.sha.opad = ctx->u.sha.key_len ?
+		&ctx->u.sha.opad_sg : NULL;
+	rctx->cmd.u.sha.opad_len = ctx->u.sha.key_len ?
+		ctx->u.sha.opad_count : 0;
+	rctx->cmd.u.sha.first = rctx->first;
 	rctx->cmd.u.sha.final = rctx->final;
 	rctx->cmd.u.sha.msg_bits = rctx->msg_bits;
 
@@ -218,7 +155,6 @@ static int ccp_sha_init(struct ahash_request *req)
 
 	memset(rctx, 0, sizeof(*rctx));
 
-	memcpy(rctx->ctx, alg->init, sizeof(rctx->ctx));
 	rctx->type = alg->type;
 	rctx->first = 1;
 
@@ -261,10 +197,13 @@ static int ccp_sha_setkey(struct crypto_ahash *tfm, const u8 *key,
 			  unsigned int key_len)
 {
 	struct ccp_ctx *ctx = crypto_tfm_ctx(crypto_ahash_tfm(tfm));
-	struct scatterlist sg;
-	unsigned int block_size =
-		crypto_tfm_alg_blocksize(crypto_ahash_tfm(tfm));
-	unsigned int digest_size = crypto_ahash_digestsize(tfm);
+	struct crypto_shash *shash = ctx->u.sha.hmac_tfm;
+	struct {
+		struct shash_desc sdesc;
+		char ctx[crypto_shash_descsize(shash)];
+	} desc;
+	unsigned int block_size = crypto_shash_blocksize(shash);
+	unsigned int digest_size = crypto_shash_digestsize(shash);
 	int i, ret;
 
 	/* Set to zero until complete */
@@ -277,8 +216,12 @@ static int ccp_sha_setkey(struct crypto_ahash *tfm, const u8 *key,
 
 	if (key_len > block_size) {
 		/* Must hash the input key */
-		sg_init_one(&sg, key, key_len);
-		ret = ccp_sync_hash(tfm, ctx->u.sha.key, &sg, key_len);
+		desc.sdesc.tfm = shash;
+		desc.sdesc.flags = crypto_ahash_get_flags(tfm) &
+			CRYPTO_TFM_REQ_MAY_SLEEP;
+
+		ret = crypto_shash_digest(&desc.sdesc, key, key_len,
+					  ctx->u.sha.key);
 		if (ret) {
 			crypto_ahash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 			return -EINVAL;
@@ -293,6 +236,9 @@ static int ccp_sha_setkey(struct crypto_ahash *tfm, const u8 *key,
 		ctx->u.sha.opad[i] = ctx->u.sha.key[i] ^ 0x5c;
 	}
 
+	sg_init_one(&ctx->u.sha.opad_sg, ctx->u.sha.opad, block_size);
+	ctx->u.sha.opad_count = block_size;
+
 	ctx->u.sha.key_len = key_len;
 
 	return 0;
@@ -319,10 +265,9 @@ static int ccp_hmac_sha_cra_init(struct crypto_tfm *tfm)
 {
 	struct ccp_ctx *ctx = crypto_tfm_ctx(tfm);
 	struct ccp_crypto_ahash_alg *alg = ccp_crypto_ahash_alg(tfm);
-	struct crypto_ahash *hmac_tfm;
+	struct crypto_shash *hmac_tfm;
 
-	hmac_tfm = crypto_alloc_ahash(alg->child_alg,
-				      CRYPTO_ALG_TYPE_AHASH, 0);
+	hmac_tfm = crypto_alloc_shash(alg->child_alg, 0, 0);
 	if (IS_ERR(hmac_tfm)) {
 		pr_warn("could not load driver %s need for HMAC support\n",
 			alg->child_alg);
@@ -339,35 +284,14 @@ static void ccp_hmac_sha_cra_exit(struct crypto_tfm *tfm)
 	struct ccp_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	if (ctx->u.sha.hmac_tfm)
-		crypto_free_ahash(ctx->u.sha.hmac_tfm);
+		crypto_free_shash(ctx->u.sha.hmac_tfm);
 
 	ccp_sha_cra_exit(tfm);
 }
 
-static const __be32 sha1_init[CCP_SHA_CTXSIZE / sizeof(__be32)] = {
-	cpu_to_be32(SHA1_H0), cpu_to_be32(SHA1_H1),
-	cpu_to_be32(SHA1_H2), cpu_to_be32(SHA1_H3),
-	cpu_to_be32(SHA1_H4), 0, 0, 0,
-};
-
-static const __be32 sha224_init[CCP_SHA_CTXSIZE / sizeof(__be32)] = {
-	cpu_to_be32(SHA224_H0), cpu_to_be32(SHA224_H1),
-	cpu_to_be32(SHA224_H2), cpu_to_be32(SHA224_H3),
-	cpu_to_be32(SHA224_H4), cpu_to_be32(SHA224_H5),
-	cpu_to_be32(SHA224_H6), cpu_to_be32(SHA224_H7),
-};
-
-static const __be32 sha256_init[CCP_SHA_CTXSIZE / sizeof(__be32)] = {
-	cpu_to_be32(SHA256_H0), cpu_to_be32(SHA256_H1),
-	cpu_to_be32(SHA256_H2), cpu_to_be32(SHA256_H3),
-	cpu_to_be32(SHA256_H4), cpu_to_be32(SHA256_H5),
-	cpu_to_be32(SHA256_H6), cpu_to_be32(SHA256_H7),
-};
-
 struct ccp_sha_def {
 	const char *name;
 	const char *drv_name;
-	const __be32 *init;
 	enum ccp_sha_type type;
 	u32 digest_size;
 	u32 block_size;
@@ -377,7 +301,6 @@ static struct ccp_sha_def sha_algs[] = {
 	{
 		.name		= "sha1",
 		.drv_name	= "sha1-ccp",
-		.init		= sha1_init,
 		.type		= CCP_SHA_TYPE_1,
 		.digest_size	= SHA1_DIGEST_SIZE,
 		.block_size	= SHA1_BLOCK_SIZE,
@@ -385,7 +308,6 @@ static struct ccp_sha_def sha_algs[] = {
 	{
 		.name		= "sha224",
 		.drv_name	= "sha224-ccp",
-		.init		= sha224_init,
 		.type		= CCP_SHA_TYPE_224,
 		.digest_size	= SHA224_DIGEST_SIZE,
 		.block_size	= SHA224_BLOCK_SIZE,
@@ -393,7 +315,6 @@ static struct ccp_sha_def sha_algs[] = {
 	{
 		.name		= "sha256",
 		.drv_name	= "sha256-ccp",
-		.init		= sha256_init,
 		.type		= CCP_SHA_TYPE_256,
 		.digest_size	= SHA256_DIGEST_SIZE,
 		.block_size	= SHA256_BLOCK_SIZE,
@@ -460,7 +381,6 @@ static int ccp_register_sha_alg(struct list_head *head,
 
 	INIT_LIST_HEAD(&ccp_alg->entry);
 
-	ccp_alg->init = def->init;
 	ccp_alg->type = def->type;
 
 	alg = &ccp_alg->alg;
diff --git a/drivers/crypto/ccp/ccp-crypto.h b/drivers/crypto/ccp/ccp-crypto.h
index b222231b6169..9aa4ae184f7f 100644
--- a/drivers/crypto/ccp/ccp-crypto.h
+++ b/drivers/crypto/ccp/ccp-crypto.h
@@ -137,11 +137,14 @@ struct ccp_aes_cmac_req_ctx {
 #define MAX_SHA_BLOCK_SIZE	SHA256_BLOCK_SIZE
 
 struct ccp_sha_ctx {
+	struct scatterlist opad_sg;
+	unsigned int opad_count;
+
 	unsigned int key_len;
 	u8 key[MAX_SHA_BLOCK_SIZE];
 	u8 ipad[MAX_SHA_BLOCK_SIZE];
 	u8 opad[MAX_SHA_BLOCK_SIZE];
-	struct crypto_ahash *hmac_tfm;
+	struct crypto_shash *hmac_tfm;
 };
 
 struct ccp_sha_req_ctx {
@@ -167,9 +170,6 @@ struct ccp_sha_req_ctx {
 	unsigned int buf_count;
 	u8 buf[MAX_SHA_BLOCK_SIZE];
 
-	/* HMAC support field */
-	struct scatterlist pad_sg;
-
 	/* CCP driver command */
 	struct ccp_cmd cmd;
 };
diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c
index c266a7b154bb..9ae006d69df4 100644
--- a/drivers/crypto/ccp/ccp-ops.c
+++ b/drivers/crypto/ccp/ccp-ops.c
@@ -23,6 +23,7 @@
 #include <linux/ccp.h>
 #include <linux/scatterlist.h>
 #include <crypto/scatterwalk.h>
+#include <crypto/sha.h>
 
 #include "ccp-dev.h"
 
@@ -132,6 +133,27 @@ struct ccp_op {
 	} u;
 };
 
+/* SHA initial context values */
+static const __be32 ccp_sha1_init[CCP_SHA_CTXSIZE / sizeof(__be32)] = {
+	cpu_to_be32(SHA1_H0), cpu_to_be32(SHA1_H1),
+	cpu_to_be32(SHA1_H2), cpu_to_be32(SHA1_H3),
+	cpu_to_be32(SHA1_H4), 0, 0, 0,
+};
+
+static const __be32 ccp_sha224_init[CCP_SHA_CTXSIZE / sizeof(__be32)] = {
+	cpu_to_be32(SHA224_H0), cpu_to_be32(SHA224_H1),
+	cpu_to_be32(SHA224_H2), cpu_to_be32(SHA224_H3),
+	cpu_to_be32(SHA224_H4), cpu_to_be32(SHA224_H5),
+	cpu_to_be32(SHA224_H6), cpu_to_be32(SHA224_H7),
+};
+
+static const __be32 ccp_sha256_init[CCP_SHA_CTXSIZE / sizeof(__be32)] = {
+	cpu_to_be32(SHA256_H0), cpu_to_be32(SHA256_H1),
+	cpu_to_be32(SHA256_H2), cpu_to_be32(SHA256_H3),
+	cpu_to_be32(SHA256_H4), cpu_to_be32(SHA256_H5),
+	cpu_to_be32(SHA256_H6), cpu_to_be32(SHA256_H7),
+};
+
 /* The CCP cannot perform zero-length sha operations so the caller
  * is required to buffer data for the final operation.  However, a
  * sha operation for a message with a total length of zero is valid
@@ -1411,7 +1433,27 @@ static int ccp_run_sha_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 	if (ret)
 		return ret;
 
-	ccp_set_dm_area(&ctx, 0, sha->ctx, 0, sha->ctx_len);
+	if (sha->first) {
+		const __be32 *init;
+
+		switch (sha->type) {
+		case CCP_SHA_TYPE_1:
+			init = ccp_sha1_init;
+			break;
+		case CCP_SHA_TYPE_224:
+			init = ccp_sha224_init;
+			break;
+		case CCP_SHA_TYPE_256:
+			init = ccp_sha256_init;
+			break;
+		default:
+			ret = -EINVAL;
+			goto e_ctx;
+		}
+		memcpy(ctx.address, init, CCP_SHA_CTXSIZE);
+	} else
+		ccp_set_dm_area(&ctx, 0, sha->ctx, 0, sha->ctx_len);
+
 	ret = ccp_copy_to_ksb(cmd_q, &ctx, op.jobid, op.ksb_ctx,
 			      CCP_PASSTHRU_BYTESWAP_256BIT);
 	if (ret) {
@@ -1451,6 +1493,66 @@ static int ccp_run_sha_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd)
 
 	ccp_get_dm_area(&ctx, 0, sha->ctx, 0, sha->ctx_len);
 
+	if (sha->final && sha->opad) {
+		/* HMAC operation, recursively perform final SHA */
+		struct ccp_cmd hmac_cmd;
+		struct scatterlist sg;
+		u64 block_size, digest_size;
+		u8 *hmac_buf;
+
+		switch (sha->type) {
+		case CCP_SHA_TYPE_1:
+			block_size = SHA1_BLOCK_SIZE;
+			digest_size = SHA1_DIGEST_SIZE;
+			break;
+		case CCP_SHA_TYPE_224:
+			block_size = SHA224_BLOCK_SIZE;
+			digest_size = SHA224_DIGEST_SIZE;
+			break;
+		case CCP_SHA_TYPE_256:
+			block_size = SHA256_BLOCK_SIZE;
+			digest_size = SHA256_DIGEST_SIZE;
+			break;
+		default:
+			ret = -EINVAL;
+			goto e_data;
+		}
+
+		if (sha->opad_len != block_size) {
+			ret = -EINVAL;
+			goto e_data;
+		}
+
+		hmac_buf = kmalloc(block_size + digest_size, GFP_KERNEL);
+		if (!hmac_buf) {
+			ret = -ENOMEM;
+			goto e_data;
+		}
+		sg_init_one(&sg, hmac_buf, block_size + digest_size);
+
+		scatterwalk_map_and_copy(hmac_buf, sha->opad, 0, block_size, 0);
+		memcpy(hmac_buf + block_size, ctx.address, digest_size);
+
+		memset(&hmac_cmd, 0, sizeof(hmac_cmd));
+		hmac_cmd.engine = CCP_ENGINE_SHA;
+		hmac_cmd.u.sha.type = sha->type;
+		hmac_cmd.u.sha.ctx = sha->ctx;
+		hmac_cmd.u.sha.ctx_len = sha->ctx_len;
+		hmac_cmd.u.sha.src = &sg;
+		hmac_cmd.u.sha.src_len = block_size + digest_size;
+		hmac_cmd.u.sha.opad = NULL;
+		hmac_cmd.u.sha.opad_len = 0;
+		hmac_cmd.u.sha.first = 1;
+		hmac_cmd.u.sha.final = 1;
+		hmac_cmd.u.sha.msg_bits = (block_size + digest_size) << 3;
+
+		ret = ccp_run_sha_cmd(cmd_q, &hmac_cmd);
+		if (ret)
+			cmd->engine_error = hmac_cmd.engine_error;
+
+		kfree(hmac_buf);
+	}
+
 e_data:
 	ccp_free_data(&src, cmd_q);
 
diff --git a/include/linux/ccp.h b/include/linux/ccp.h
index b941ab9f762b..ebcc9d146219 100644
--- a/include/linux/ccp.h
+++ b/include/linux/ccp.h
@@ -232,6 +232,9 @@ enum ccp_sha_type {
  * @ctx_len: length in bytes of hash value
  * @src: data to be used for this operation
  * @src_len: length in bytes of data used for this operation
+ * @opad: data to be used for final HMAC operation
+ * @opad_len: length in bytes of data used for final HMAC operation
+ * @first: indicates first SHA operation
  * @final: indicates final SHA operation
  * @msg_bits: total length of the message in bits used in final SHA operation
  *
@@ -251,6 +254,10 @@ struct ccp_sha_engine {
 	struct scatterlist *src;
 	u64 src_len;		/* In bytes */
 
+	struct scatterlist *opad;
+	u32 opad_len;		/* In bytes */
+
+	u32 first;		/* Indicates first sha cmd */
 	u32 final;		/* Indicates final sha cmd */
 	u64 msg_bits;		/* Message length in bits required for
 				 * final sha cmd */
-- 
cgit v1.2.3


From 6039257378e4c84da06e68230b14fef955508ce6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@infradead.org>
Date: Mon, 10 Feb 2014 10:27:11 +1100
Subject: direct-io: add flag to allow aio writes beyond i_size

Some filesystems can handle direct I/O writes beyond i_size safely,
so allow them to opt into receiving them.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
---
 fs/direct-io.c     | 18 ++++++++++++------
 include/linux/fs.h |  3 +++
 2 files changed, 15 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/fs/direct-io.c b/fs/direct-io.c
index 160a5489a939..a701752dd750 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1194,13 +1194,19 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	}
 
 	/*
-	 * For file extending writes updating i_size before data
-	 * writeouts complete can expose uninitialized blocks. So
-	 * even for AIO, we need to wait for i/o to complete before
-	 * returning in this case.
+	 * For file extending writes updating i_size before data writeouts
+	 * complete can expose uninitialized blocks in dumb filesystems.
+	 * In that case we need to wait for I/O completion even if asked
+	 * for an asynchronous write.
 	 */
-	dio->is_async = !is_sync_kiocb(iocb) && !((rw & WRITE) &&
-		(end > i_size_read(inode)));
+	if (is_sync_kiocb(iocb))
+		dio->is_async = false;
+	else if (!(dio->flags & DIO_ASYNC_EXTEND) &&
+            (rw & WRITE) && end > i_size_read(inode))
+		dio->is_async = false;
+	else
+		dio->is_async = true;
+
 	dio->inode = inode;
 	dio->rw = rw;
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 09f553c59813..f7faefcf4843 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2527,6 +2527,9 @@ enum {
 
 	/* filesystem does not support filling holes */
 	DIO_SKIP_HOLES	= 0x02,
+
+	/* filesystem can handle aio writes beyond i_size */
+	DIO_ASYNC_EXTEND = 0x04,
 };
 
 void dio_end_io(struct bio *bio, int error);
-- 
cgit v1.2.3


From 557fe99d9d490fe01c7aa87494313078c4ff939c Mon Sep 17 00:00:00 2001
From: Sascha Hauer <s.hauer@pengutronix.de>
Date: Fri, 24 Jan 2014 08:54:16 +0100
Subject: pwm: Remove obsolete HAVE_PWM Kconfig symbol

Before we had the PWM framework we used to have a barebone PWM api. The
HAVE_PWM Kconfig symbol used to be selected by the PWM drivers to specify
the PWM API is present in the kernel. Since the last legacy driver is gone
the HAVE_PWM symbol can go aswell.

Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Cc: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Cc: Eric Miao <eric.y.miao@gmail.com>
Cc: Haojian Zhuang <haojian.zhuang@gmail.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Cc: Thierry Reding <thierry.reding@gmail.com>
Cc: linux-pwm@vger.kernel.orig
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Thierry Reding <thierry.reding@gmail.com>
---
 arch/arm/Kconfig           |  4 ----
 arch/arm/mach-pxa/Kconfig  | 15 ---------------
 arch/mips/Kconfig          |  1 -
 drivers/input/misc/Kconfig |  4 ++--
 include/linux/pwm.h        |  2 +-
 5 files changed, 3 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index e25419817791..cc6ce44064a2 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -113,9 +113,6 @@ config ARM_DMA_IOMMU_ALIGNMENT
 
 endif
 
-config HAVE_PWM
-	bool
-
 config MIGHT_HAVE_PCI
 	bool
 
@@ -632,7 +629,6 @@ config ARCH_LPC32XX
 	select CPU_ARM926T
 	select GENERIC_CLOCKEVENTS
 	select HAVE_IDE
-	select HAVE_PWM
 	select USB_ARCH_HAS_OHCI
 	select USE_OF
 	help
diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig
index 96100dbf5a2e..b96244c73ea4 100644
--- a/arch/arm/mach-pxa/Kconfig
+++ b/arch/arm/mach-pxa/Kconfig
@@ -7,7 +7,6 @@ comment "Intel/Marvell Dev Platforms (sorted by hardware release time)"
 config MACH_PXA3XX_DT
 	bool "Support PXA3xx platforms from device tree"
 	select CPU_PXA300
-	select HAVE_PWM
 	select POWER_SUPPLY
 	select PXA3xx
 	select USE_OF
@@ -23,12 +22,10 @@ config ARCH_LUBBOCK
 
 config MACH_MAINSTONE
 	bool "Intel HCDDBBVA0 Development Platform (aka Mainstone)"
-	select HAVE_PWM
 	select PXA27x
 
 config MACH_ZYLONITE
 	bool
-	select HAVE_PWM
 	select PXA3xx
 
 config MACH_ZYLONITE300
@@ -69,7 +66,6 @@ config ARCH_PXA_IDP
 config ARCH_VIPER
 	bool "Arcom/Eurotech VIPER SBC"
 	select ARCOM_PCMCIA
-	select HAVE_PWM
 	select I2C_GPIO
 	select ISA
 	select PXA25x
@@ -120,7 +116,6 @@ config MACH_CM_X300
 	bool "CompuLab CM-X300 modules"
 	select CPU_PXA300
 	select CPU_PXA310
-	select HAVE_PWM
 	select PXA3xx
 
 config MACH_CAPC7117
@@ -211,7 +206,6 @@ config TRIZEPS_PCMCIA
 
 config MACH_LOGICPD_PXA270
 	bool "LogicPD PXA270 Card Engine Development Platform"
-	select HAVE_PWM
 	select PXA27x
 
 config MACH_PCM027
@@ -222,7 +216,6 @@ config MACH_PCM027
 config MACH_PCM990_BASEBOARD
 	bool "PHYTEC PCM-990 development board"
 	depends on MACH_PCM027
-	select HAVE_PWM
 
 choice
 	prompt "display on pcm990"
@@ -246,7 +239,6 @@ config MACH_COLIBRI
 config MACH_COLIBRI_PXA270_INCOME
 	bool "Income s.r.o. PXA270 SBC"
 	depends on MACH_COLIBRI
-	select HAVE_PWM
 	select PXA27x
 
 config MACH_COLIBRI300
@@ -275,7 +267,6 @@ comment "End-user Products (sorted by vendor name)"
 
 config MACH_H4700
 	bool "HP iPAQ hx4700"
-	select HAVE_PWM
 	select IWMMXT
 	select PXA27x
 
@@ -289,14 +280,12 @@ config MACH_HIMALAYA
 
 config MACH_MAGICIAN
 	bool "Enable HTC Magician Support"
-	select HAVE_PWM
 	select IWMMXT
 	select PXA27x
 
 config MACH_MIOA701
 	bool "Mitac Mio A701 Support"
 	select GPIO_SYSFS
-	select HAVE_PWM
 	select IWMMXT
 	select PXA27x
 	help
@@ -306,7 +295,6 @@ config MACH_MIOA701
 
 config PXA_EZX
 	bool "Motorola EZX Platform"
-	select HAVE_PWM
 	select IWMMXT
 	select PXA27x
 
@@ -346,7 +334,6 @@ config MACH_MP900C
 
 config ARCH_PXA_PALM
 	bool "PXA based Palm PDAs"
-	select HAVE_PWM
 
 config MACH_PALM27X
 	bool
@@ -444,7 +431,6 @@ config MACH_TREO680
 config MACH_RAUMFELD_RC
 	bool "Raumfeld Controller"
 	select CPU_PXA300
-	select HAVE_PWM
 	select POWER_SUPPLY
 	select PXA3xx
 
@@ -608,7 +594,6 @@ config MACH_E800
 
 config MACH_ZIPIT2
 	bool "Zipit Z2 Handheld"
-	select HAVE_PWM
 	select PXA27x
 endmenu
 
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index dcae3a7035db..d1326032c8c8 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -235,7 +235,6 @@ config MACH_JZ4740
 	select IRQ_CPU
 	select ARCH_REQUIRE_GPIOLIB
 	select SYS_HAS_EARLY_PRINTK
-	select HAVE_PWM
 	select HAVE_CLK
 	select GENERIC_IRQ_CHIP
 
diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig
index 7904ab05527a..762e6d2de3c9 100644
--- a/drivers/input/misc/Kconfig
+++ b/drivers/input/misc/Kconfig
@@ -156,7 +156,7 @@ config INPUT_MAX8925_ONKEY
 
 config INPUT_MAX8997_HAPTIC
 	tristate "MAXIM MAX8997 haptic controller support"
-	depends on PWM && HAVE_PWM && MFD_MAX8997
+	depends on PWM && MFD_MAX8997
 	select INPUT_FF_MEMLESS
 	help
 	  This option enables device driver support for the haptic controller
@@ -470,7 +470,7 @@ config INPUT_PCF8574
 
 config INPUT_PWM_BEEPER
 	tristate "PWM beeper support"
-	depends on PWM && HAVE_PWM
+	depends on PWM
 	help
 	  Say Y here to get support for PWM based beeper devices.
 
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index f0feafd184a0..4717f54051cb 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -7,7 +7,7 @@
 struct pwm_device;
 struct seq_file;
 
-#if IS_ENABLED(CONFIG_PWM) || IS_ENABLED(CONFIG_HAVE_PWM)
+#if IS_ENABLED(CONFIG_PWM)
 /*
  * pwm_request - request a PWM device
  */
-- 
cgit v1.2.3


From b0504e39c27b00101c9c1fa2c58fd896ae0f64f5 Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@xilinx.com>
Date: Mon, 18 Nov 2013 16:48:19 +0100
Subject: ARM: zynq: Map I/O memory on clkc init

The clkc has its registers in the range of the slcr.
Instead of passing around the slcr base address pointer, let the clkc get the
address from the DT.
This prepares the slcr to be a real driver with multiple memory ranges
(slcr, clocks, pinctrl,...)

Signed-off-by: Steffen Trumtrar <s.trumtrar@pengutronix.de>
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
---
 .../devicetree/bindings/clock/zynq-7000.txt        |  4 +-
 arch/arm/boot/dts/zynq-7000.dtsi                   | 42 +++++-----
 arch/arm/mach-zynq/common.c                        |  2 +-
 drivers/clk/zynq/clkc.c                            | 89 +++++++++++++++-------
 include/linux/clk/zynq.h                           |  2 +-
 5 files changed, 88 insertions(+), 51 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/devicetree/bindings/clock/zynq-7000.txt b/Documentation/devicetree/bindings/clock/zynq-7000.txt
index 17b4a94916d6..d93746cf2975 100644
--- a/Documentation/devicetree/bindings/clock/zynq-7000.txt
+++ b/Documentation/devicetree/bindings/clock/zynq-7000.txt
@@ -14,6 +14,7 @@ for all clock consumers of PS clocks.
 Required properties:
  - #clock-cells : Must be 1
  - compatible : "xlnx,ps7-clkc"
+ - reg : SLCR offset and size taken via syscon < 0x100 0x100 >
  - ps-clk-frequency : Frequency of the oscillator providing ps_clk in HZ
 		      (usually 33 MHz oscillators are used for Zynq platforms)
  - clock-output-names : List of strings used to name the clock outputs. Shall be
@@ -87,10 +88,11 @@ Clock outputs:
  47: dbg_apb
 
 Example:
-	clkc: clkc {
+	clkc: clkc@100 {
 		#clock-cells = <1>;
 		compatible = "xlnx,ps7-clkc";
 		ps-clk-frequency = <33333333>;
+		reg = <0x100 0x100>;
 		clock-output-names = "armpll", "ddrpll", "iopll", "cpu_6or4x",
 				"cpu_3or2x", "cpu_2x", "cpu_1x", "ddr2x", "ddr3x",
 				"dci", "lqspi", "smc", "pcap", "gem0", "gem1",
diff --git a/arch/arm/boot/dts/zynq-7000.dtsi b/arch/arm/boot/dts/zynq-7000.dtsi
index 81e5677f25a2..602e12eedb01 100644
--- a/arch/arm/boot/dts/zynq-7000.dtsi
+++ b/arch/arm/boot/dts/zynq-7000.dtsi
@@ -123,30 +123,28 @@
 		} ;
 
 		slcr: slcr@f8000000 {
+			#address-cells = <1>;
+			#size-cells = <1>;
 			compatible = "xlnx,zynq-slcr", "syscon";
 			reg = <0xF8000000 0x1000>;
-
-			clocks {
-				#address-cells = <1>;
-				#size-cells = <0>;
-
-				clkc: clkc {
-					#clock-cells = <1>;
-					compatible = "xlnx,ps7-clkc";
-					ps-clk-frequency = <33333333>;
-					fclk-enable = <0>;
-					clock-output-names = "armpll", "ddrpll", "iopll", "cpu_6or4x",
-							"cpu_3or2x", "cpu_2x", "cpu_1x", "ddr2x", "ddr3x",
-							"dci", "lqspi", "smc", "pcap", "gem0", "gem1",
-							"fclk0", "fclk1", "fclk2", "fclk3", "can0", "can1",
-							"sdio0", "sdio1", "uart0", "uart1", "spi0", "spi1",
-							"dma", "usb0_aper", "usb1_aper", "gem0_aper",
-							"gem1_aper", "sdio0_aper", "sdio1_aper",
-							"spi0_aper", "spi1_aper", "can0_aper", "can1_aper",
-							"i2c0_aper", "i2c1_aper", "uart0_aper", "uart1_aper",
-							"gpio_aper", "lqspi_aper", "smc_aper", "swdt",
-							"dbg_trc", "dbg_apb";
-				};
+			ranges;
+			clkc: clkc@100 {
+				#clock-cells = <1>;
+				compatible = "xlnx,ps7-clkc";
+				ps-clk-frequency = <33333333>;
+				fclk-enable = <0>;
+				clock-output-names = "armpll", "ddrpll", "iopll", "cpu_6or4x",
+						"cpu_3or2x", "cpu_2x", "cpu_1x", "ddr2x", "ddr3x",
+						"dci", "lqspi", "smc", "pcap", "gem0", "gem1",
+						"fclk0", "fclk1", "fclk2", "fclk3", "can0", "can1",
+						"sdio0", "sdio1", "uart0", "uart1", "spi0", "spi1",
+						"dma", "usb0_aper", "usb1_aper", "gem0_aper",
+						"gem1_aper", "sdio0_aper", "sdio1_aper",
+						"spi0_aper", "spi1_aper", "can0_aper", "can1_aper",
+						"i2c0_aper", "i2c1_aper", "uart0_aper", "uart1_aper",
+						"gpio_aper", "lqspi_aper", "smc_aper", "swdt",
+						"dbg_trc", "dbg_apb";
+				reg = <0x100 0x100>;
 			};
 		};
 
diff --git a/arch/arm/mach-zynq/common.c b/arch/arm/mach-zynq/common.c
index 38401cf78383..93ea19b13e6e 100644
--- a/arch/arm/mach-zynq/common.c
+++ b/arch/arm/mach-zynq/common.c
@@ -67,7 +67,7 @@ static void __init zynq_timer_init(void)
 {
 	zynq_early_slcr_init();
 
-	zynq_clock_init(zynq_slcr_base);
+	zynq_clock_init();
 	clocksource_of_init();
 }
 
diff --git a/drivers/clk/zynq/clkc.c b/drivers/clk/zynq/clkc.c
index 09dd0173ea0a..03052d67b197 100644
--- a/drivers/clk/zynq/clkc.c
+++ b/drivers/clk/zynq/clkc.c
@@ -21,34 +21,35 @@
 #include <linux/clk/zynq.h>
 #include <linux/clk-provider.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/io.h>
 
-static void __iomem *zynq_slcr_base_priv;
-
-#define SLCR_ARMPLL_CTRL		(zynq_slcr_base_priv + 0x100)
-#define SLCR_DDRPLL_CTRL		(zynq_slcr_base_priv + 0x104)
-#define SLCR_IOPLL_CTRL			(zynq_slcr_base_priv + 0x108)
-#define SLCR_PLL_STATUS			(zynq_slcr_base_priv + 0x10c)
-#define SLCR_ARM_CLK_CTRL		(zynq_slcr_base_priv + 0x120)
-#define SLCR_DDR_CLK_CTRL		(zynq_slcr_base_priv + 0x124)
-#define SLCR_DCI_CLK_CTRL		(zynq_slcr_base_priv + 0x128)
-#define SLCR_APER_CLK_CTRL		(zynq_slcr_base_priv + 0x12c)
-#define SLCR_GEM0_CLK_CTRL		(zynq_slcr_base_priv + 0x140)
-#define SLCR_GEM1_CLK_CTRL		(zynq_slcr_base_priv + 0x144)
-#define SLCR_SMC_CLK_CTRL		(zynq_slcr_base_priv + 0x148)
-#define SLCR_LQSPI_CLK_CTRL		(zynq_slcr_base_priv + 0x14c)
-#define SLCR_SDIO_CLK_CTRL		(zynq_slcr_base_priv + 0x150)
-#define SLCR_UART_CLK_CTRL		(zynq_slcr_base_priv + 0x154)
-#define SLCR_SPI_CLK_CTRL		(zynq_slcr_base_priv + 0x158)
-#define SLCR_CAN_CLK_CTRL		(zynq_slcr_base_priv + 0x15c)
-#define SLCR_CAN_MIOCLK_CTRL		(zynq_slcr_base_priv + 0x160)
-#define SLCR_DBG_CLK_CTRL		(zynq_slcr_base_priv + 0x164)
-#define SLCR_PCAP_CLK_CTRL		(zynq_slcr_base_priv + 0x168)
-#define SLCR_FPGA0_CLK_CTRL		(zynq_slcr_base_priv + 0x170)
-#define SLCR_621_TRUE			(zynq_slcr_base_priv + 0x1c4)
-#define SLCR_SWDT_CLK_SEL		(zynq_slcr_base_priv + 0x304)
+static void __iomem *zynq_clkc_base;
+
+#define SLCR_ARMPLL_CTRL		(zynq_clkc_base + 0x00)
+#define SLCR_DDRPLL_CTRL		(zynq_clkc_base + 0x04)
+#define SLCR_IOPLL_CTRL			(zynq_clkc_base + 0x08)
+#define SLCR_PLL_STATUS			(zynq_clkc_base + 0x0c)
+#define SLCR_ARM_CLK_CTRL		(zynq_clkc_base + 0x20)
+#define SLCR_DDR_CLK_CTRL		(zynq_clkc_base + 0x24)
+#define SLCR_DCI_CLK_CTRL		(zynq_clkc_base + 0x28)
+#define SLCR_APER_CLK_CTRL		(zynq_clkc_base + 0x2c)
+#define SLCR_GEM0_CLK_CTRL		(zynq_clkc_base + 0x40)
+#define SLCR_GEM1_CLK_CTRL		(zynq_clkc_base + 0x44)
+#define SLCR_SMC_CLK_CTRL		(zynq_clkc_base + 0x48)
+#define SLCR_LQSPI_CLK_CTRL		(zynq_clkc_base + 0x4c)
+#define SLCR_SDIO_CLK_CTRL		(zynq_clkc_base + 0x50)
+#define SLCR_UART_CLK_CTRL		(zynq_clkc_base + 0x54)
+#define SLCR_SPI_CLK_CTRL		(zynq_clkc_base + 0x58)
+#define SLCR_CAN_CLK_CTRL		(zynq_clkc_base + 0x5c)
+#define SLCR_CAN_MIOCLK_CTRL		(zynq_clkc_base + 0x60)
+#define SLCR_DBG_CLK_CTRL		(zynq_clkc_base + 0x64)
+#define SLCR_PCAP_CLK_CTRL		(zynq_clkc_base + 0x68)
+#define SLCR_FPGA0_CLK_CTRL		(zynq_clkc_base + 0x70)
+#define SLCR_621_TRUE			(zynq_clkc_base + 0xc4)
+#define SLCR_SWDT_CLK_SEL		(zynq_clkc_base + 0x204)
 
 #define NUM_MIO_PINS	54
 
@@ -569,8 +570,44 @@ static void __init zynq_clk_setup(struct device_node *np)
 
 CLK_OF_DECLARE(zynq_clkc, "xlnx,ps7-clkc", zynq_clk_setup);
 
-void __init zynq_clock_init(void __iomem *slcr_base)
+void __init zynq_clock_init(void)
 {
-	zynq_slcr_base_priv = slcr_base;
+	struct device_node *np;
+	struct device_node *slcr;
+	struct resource res;
+
+	np = of_find_compatible_node(NULL, NULL, "xlnx,ps7-clkc");
+	if (!np) {
+		pr_err("%s: clkc node not found\n", __func__);
+		goto np_err;
+	}
+
+	if (of_address_to_resource(np, 0, &res)) {
+		pr_err("%s: failed to get resource\n", np->name);
+		goto np_err;
+	}
+
+	slcr = of_get_parent(np);
+
+	if (slcr->data) {
+		zynq_clkc_base = (__force void __iomem *)slcr->data + res.start;
+	} else {
+		pr_err("%s: Unable to get I/O memory\n", np->name);
+		of_node_put(slcr);
+		goto np_err;
+	}
+
+	pr_info("%s: clkc starts at %p\n", __func__, zynq_clkc_base);
+
+	of_node_put(slcr);
+	of_node_put(np);
+
 	of_clk_init(NULL);
+
+	return;
+
+np_err:
+	of_node_put(np);
+	BUG();
+	return;
 }
diff --git a/include/linux/clk/zynq.h b/include/linux/clk/zynq.h
index e062d317ccce..7a5633b71533 100644
--- a/include/linux/clk/zynq.h
+++ b/include/linux/clk/zynq.h
@@ -22,7 +22,7 @@
 
 #include <linux/spinlock.h>
 
-void zynq_clock_init(void __iomem *slcr);
+void zynq_clock_init(void);
 
 struct clk *clk_register_zynq_pll(const char *name, const char *parent,
 		void __iomem *pll_ctrl, void __iomem *pll_status, u8 lock_index,
-- 
cgit v1.2.3


From b02f6695f7601c4f8442b9cf4636802e7fa8d550 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 11 Feb 2014 00:35:23 +0100
Subject: PM / QoS: Rename device resume latency QoS items

Rename symbols, variables, functions and structure fields related do
the resume latency device PM QoS type so that it is clear where they
belong (in particular, to avoid confusion with the latency tolerance
device PM QoS type introduced by a subsequent changeset).

Update the PM QoS documentation to better reflect its current state.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/power/pm_qos_interface.txt | 37 ++++++++++-----------
 Documentation/trace/events-power.txt     |  2 +-
 drivers/base/power/power.h               |  4 +--
 drivers/base/power/qos.c                 | 55 ++++++++++++++++----------------
 drivers/base/power/sysfs.c               | 32 ++++++++++---------
 drivers/mtd/nand/sh_flctl.c              |  2 +-
 include/linux/pm_qos.h                   | 14 ++++----
 include/trace/events/power.h             |  4 +--
 8 files changed, 73 insertions(+), 77 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/power/pm_qos_interface.txt b/Documentation/power/pm_qos_interface.txt
index 483632087788..22cb8f51182a 100644
--- a/Documentation/power/pm_qos_interface.txt
+++ b/Documentation/power/pm_qos_interface.txt
@@ -89,16 +89,16 @@ node.
 2. PM QoS per-device latency and flags framework
 
 For each device, there are two lists of PM QoS requests. One is maintained
-along with the aggregated target of latency value and the other is for PM QoS
-flags. Values are updated in response to changes of the request list.
+along with the aggregated target of resume latency value and the other is for
+PM QoS flags. Values are updated in response to changes of the request list.
 
-Target latency value is simply the minimum of the request values held in the
-parameter list elements.  The PM QoS flags aggregate value is a gather (bitwise
-OR) of all list elements' values. Two device PM QoS flags are defined currently:
-PM_QOS_FLAG_NO_POWER_OFF and PM_QOS_FLAG_REMOTE_WAKEUP.
+Target resume latency value is simply the minimum of the request values held in
+the parameter list elements.  The PM QoS flags aggregate value is a gather
+(bitwise OR) of all list elements' values.  Two device PM QoS flags are defined
+currently: PM_QOS_FLAG_NO_POWER_OFF and PM_QOS_FLAG_REMOTE_WAKEUP.
 
-Note: the aggregated target value is implemented as an atomic variable so that
-reading the aggregated value does not require any locking mechanism.
+Note: the aggregated target value is implemented in such a way that reading the
+aggregated value does not require any locking mechanism.
 
 
 From kernel mode the use of this interface is the following:
@@ -137,14 +137,14 @@ Add a PM QoS request for the first direct ancestor of the given device whose
 power.ignore_children flag is unset.
 
 int dev_pm_qos_expose_latency_limit(device, value)
-Add a request to the device's PM QoS list of latency constraints and create
-a sysfs attribute pm_qos_resume_latency_us under the device's power directory
-allowing user space to manipulate that request.
+Add a request to the device's PM QoS list of resume latency constraints and
+create a sysfs attribute pm_qos_resume_latency_us under the device's power
+directory allowing user space to manipulate that request.
 
 void dev_pm_qos_hide_latency_limit(device)
 Drop the request added by dev_pm_qos_expose_latency_limit() from the device's
-PM QoS list of latency constraints and remove sysfs attribute pm_qos_resume_latency_us
-from the device's power directory.
+PM QoS list of resume latency constraints and remove sysfs attribute
+pm_qos_resume_latency_us from the device's power directory.
 
 int dev_pm_qos_expose_flags(device, value)
 Add a request to the device's PM QoS list of flags and create sysfs attributes
@@ -163,7 +163,7 @@ a per-device notification tree and a global notification tree.
 int dev_pm_qos_add_notifier(device, notifier):
 Adds a notification callback function for the device.
 The callback is called when the aggregated value of the device constraints list
-is changed.
+is changed (for resume latency device PM QoS only).
 
 int dev_pm_qos_remove_notifier(device, notifier):
 Removes the notification callback function for the device.
@@ -171,14 +171,9 @@ Removes the notification callback function for the device.
 int dev_pm_qos_add_global_notifier(notifier):
 Adds a notification callback function in the global notification tree of the
 framework.
-The callback is called when the aggregated value for any device is changed.
+The callback is called when the aggregated value for any device is changed
+(for resume latency device PM QoS only).
 
 int dev_pm_qos_remove_global_notifier(notifier):
 Removes the notification callback function from the global notification tree
 of the framework.
-
-
-From user mode:
-No API for user space access to the per-device latency constraints is provided
-yet - still under discussion.
-
diff --git a/Documentation/trace/events-power.txt b/Documentation/trace/events-power.txt
index 3bd33b8dc7c4..21d514ced212 100644
--- a/Documentation/trace/events-power.txt
+++ b/Documentation/trace/events-power.txt
@@ -92,5 +92,5 @@ dev_pm_qos_remove_request          "device=%s type=%s new_value=%d"
 
 The first parameter gives the device name which tries to add/update/remove
 QoS requests.
-The second parameter gives the request type (e.g. "DEV_PM_QOS_LATENCY").
+The second parameter gives the request type (e.g. "DEV_PM_QOS_RESUME_LATENCY").
 The third parameter is value to be added/updated/removed.
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index cfc3226ec492..a21223d95926 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -89,8 +89,8 @@ extern void dpm_sysfs_remove(struct device *dev);
 extern void rpm_sysfs_remove(struct device *dev);
 extern int wakeup_sysfs_add(struct device *dev);
 extern void wakeup_sysfs_remove(struct device *dev);
-extern int pm_qos_sysfs_add_latency(struct device *dev);
-extern void pm_qos_sysfs_remove_latency(struct device *dev);
+extern int pm_qos_sysfs_add_resume_latency(struct device *dev);
+extern void pm_qos_sysfs_remove_resume_latency(struct device *dev);
 extern int pm_qos_sysfs_add_flags(struct device *dev);
 extern void pm_qos_sysfs_remove_flags(struct device *dev);
 
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 5c1361a9e5dd..67c0f4219b02 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -105,7 +105,7 @@ EXPORT_SYMBOL_GPL(dev_pm_qos_flags);
 s32 __dev_pm_qos_read_value(struct device *dev)
 {
 	return IS_ERR_OR_NULL(dev->power.qos) ?
-		0 : pm_qos_read_value(&dev->power.qos->latency);
+		0 : pm_qos_read_value(&dev->power.qos->resume_latency);
 }
 
 /**
@@ -141,11 +141,11 @@ static int apply_constraint(struct dev_pm_qos_request *req,
 	int ret;
 
 	switch(req->type) {
-	case DEV_PM_QOS_LATENCY:
-		ret = pm_qos_update_target(&qos->latency, &req->data.pnode,
-					   action, value);
+	case DEV_PM_QOS_RESUME_LATENCY:
+		ret = pm_qos_update_target(&qos->resume_latency,
+					   &req->data.pnode, action, value);
 		if (ret) {
-			value = pm_qos_read_value(&qos->latency);
+			value = pm_qos_read_value(&qos->resume_latency);
 			blocking_notifier_call_chain(&dev_pm_notifiers,
 						     (unsigned long)value,
 						     req);
@@ -186,10 +186,10 @@ static int dev_pm_qos_constraints_allocate(struct device *dev)
 	}
 	BLOCKING_INIT_NOTIFIER_HEAD(n);
 
-	c = &qos->latency;
+	c = &qos->resume_latency;
 	plist_head_init(&c->list);
-	c->target_value = PM_QOS_DEV_LAT_DEFAULT_VALUE;
-	c->default_value = PM_QOS_DEV_LAT_DEFAULT_VALUE;
+	c->target_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE;
+	c->default_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE;
 	c->type = PM_QOS_MIN;
 	c->notifiers = n;
 
@@ -224,7 +224,7 @@ void dev_pm_qos_constraints_destroy(struct device *dev)
 	 * If the device's PM QoS resume latency limit or PM QoS flags have been
 	 * exposed to user space, they have to be hidden at this point.
 	 */
-	pm_qos_sysfs_remove_latency(dev);
+	pm_qos_sysfs_remove_resume_latency(dev);
 	pm_qos_sysfs_remove_flags(dev);
 
 	mutex_lock(&dev_pm_qos_mtx);
@@ -237,7 +237,7 @@ void dev_pm_qos_constraints_destroy(struct device *dev)
 		goto out;
 
 	/* Flush the constraints lists for the device. */
-	c = &qos->latency;
+	c = &qos->resume_latency;
 	plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) {
 		/*
 		 * Update constraints list and call the notification
@@ -341,7 +341,7 @@ static int __dev_pm_qos_update_request(struct dev_pm_qos_request *req,
 		return -ENODEV;
 
 	switch(req->type) {
-	case DEV_PM_QOS_LATENCY:
+	case DEV_PM_QOS_RESUME_LATENCY:
 		curr_value = req->data.pnode.prio;
 		break;
 	case DEV_PM_QOS_FLAGS:
@@ -460,8 +460,8 @@ int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier)
 		ret = dev_pm_qos_constraints_allocate(dev);
 
 	if (!ret)
-		ret = blocking_notifier_chain_register(
-				dev->power.qos->latency.notifiers, notifier);
+		ret = blocking_notifier_chain_register(dev->power.qos->resume_latency.notifiers,
+						       notifier);
 
 	mutex_unlock(&dev_pm_qos_mtx);
 	return ret;
@@ -487,9 +487,8 @@ int dev_pm_qos_remove_notifier(struct device *dev,
 
 	/* Silently return if the constraints object is not present. */
 	if (!IS_ERR_OR_NULL(dev->power.qos))
-		retval = blocking_notifier_chain_unregister(
-				dev->power.qos->latency.notifiers,
-				notifier);
+		retval = blocking_notifier_chain_unregister(dev->power.qos->resume_latency.notifiers,
+							    notifier);
 
 	mutex_unlock(&dev_pm_qos_mtx);
 	return retval;
@@ -543,7 +542,7 @@ int dev_pm_qos_add_ancestor_request(struct device *dev,
 
 	if (ancestor)
 		ret = dev_pm_qos_add_request(ancestor, req,
-					     DEV_PM_QOS_LATENCY, value);
+					     DEV_PM_QOS_RESUME_LATENCY, value);
 
 	if (ret < 0)
 		req->dev = NULL;
@@ -559,9 +558,9 @@ static void __dev_pm_qos_drop_user_request(struct device *dev,
 	struct dev_pm_qos_request *req = NULL;
 
 	switch(type) {
-	case DEV_PM_QOS_LATENCY:
-		req = dev->power.qos->latency_req;
-		dev->power.qos->latency_req = NULL;
+	case DEV_PM_QOS_RESUME_LATENCY:
+		req = dev->power.qos->resume_latency_req;
+		dev->power.qos->resume_latency_req = NULL;
 		break;
 	case DEV_PM_QOS_FLAGS:
 		req = dev->power.qos->flags_req;
@@ -597,7 +596,7 @@ int dev_pm_qos_expose_latency_limit(struct device *dev, s32 value)
 	if (!req)
 		return -ENOMEM;
 
-	ret = dev_pm_qos_add_request(dev, req, DEV_PM_QOS_LATENCY, value);
+	ret = dev_pm_qos_add_request(dev, req, DEV_PM_QOS_RESUME_LATENCY, value);
 	if (ret < 0) {
 		kfree(req);
 		return ret;
@@ -609,7 +608,7 @@ int dev_pm_qos_expose_latency_limit(struct device *dev, s32 value)
 
 	if (IS_ERR_OR_NULL(dev->power.qos))
 		ret = -ENODEV;
-	else if (dev->power.qos->latency_req)
+	else if (dev->power.qos->resume_latency_req)
 		ret = -EEXIST;
 
 	if (ret < 0) {
@@ -618,13 +617,13 @@ int dev_pm_qos_expose_latency_limit(struct device *dev, s32 value)
 		mutex_unlock(&dev_pm_qos_mtx);
 		goto out;
 	}
-	dev->power.qos->latency_req = req;
+	dev->power.qos->resume_latency_req = req;
 
 	mutex_unlock(&dev_pm_qos_mtx);
 
-	ret = pm_qos_sysfs_add_latency(dev);
+	ret = pm_qos_sysfs_add_resume_latency(dev);
 	if (ret)
-		dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_LATENCY);
+		dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_RESUME_LATENCY);
 
  out:
 	mutex_unlock(&dev_pm_qos_sysfs_mtx);
@@ -634,8 +633,8 @@ EXPORT_SYMBOL_GPL(dev_pm_qos_expose_latency_limit);
 
 static void __dev_pm_qos_hide_latency_limit(struct device *dev)
 {
-	if (!IS_ERR_OR_NULL(dev->power.qos) && dev->power.qos->latency_req)
-		__dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_LATENCY);
+	if (!IS_ERR_OR_NULL(dev->power.qos) && dev->power.qos->resume_latency_req)
+		__dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_RESUME_LATENCY);
 }
 
 /**
@@ -646,7 +645,7 @@ void dev_pm_qos_hide_latency_limit(struct device *dev)
 {
 	mutex_lock(&dev_pm_qos_sysfs_mtx);
 
-	pm_qos_sysfs_remove_latency(dev);
+	pm_qos_sysfs_remove_resume_latency(dev);
 
 	mutex_lock(&dev_pm_qos_mtx);
 	__dev_pm_qos_hide_latency_limit(dev);
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index 03e089ade5ce..4e24955aac8a 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -218,15 +218,16 @@ static ssize_t autosuspend_delay_ms_store(struct device *dev,
 static DEVICE_ATTR(autosuspend_delay_ms, 0644, autosuspend_delay_ms_show,
 		autosuspend_delay_ms_store);
 
-static ssize_t pm_qos_latency_show(struct device *dev,
-				   struct device_attribute *attr, char *buf)
+static ssize_t pm_qos_resume_latency_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
 {
-	return sprintf(buf, "%d\n", dev_pm_qos_requested_latency(dev));
+	return sprintf(buf, "%d\n", dev_pm_qos_requested_resume_latency(dev));
 }
 
-static ssize_t pm_qos_latency_store(struct device *dev,
-				    struct device_attribute *attr,
-				    const char *buf, size_t n)
+static ssize_t pm_qos_resume_latency_store(struct device *dev,
+					   struct device_attribute *attr,
+					   const char *buf, size_t n)
 {
 	s32 value;
 	int ret;
@@ -237,12 +238,13 @@ static ssize_t pm_qos_latency_store(struct device *dev,
 	if (value < 0)
 		return -EINVAL;
 
-	ret = dev_pm_qos_update_request(dev->power.qos->latency_req, value);
+	ret = dev_pm_qos_update_request(dev->power.qos->resume_latency_req,
+					value);
 	return ret < 0 ? ret : n;
 }
 
 static DEVICE_ATTR(pm_qos_resume_latency_us, 0644,
-		   pm_qos_latency_show, pm_qos_latency_store);
+		   pm_qos_resume_latency_show, pm_qos_resume_latency_store);
 
 static ssize_t pm_qos_no_power_off_show(struct device *dev,
 					struct device_attribute *attr,
@@ -618,15 +620,15 @@ static struct attribute_group pm_runtime_attr_group = {
 	.attrs	= runtime_attrs,
 };
 
-static struct attribute *pm_qos_latency_attrs[] = {
+static struct attribute *pm_qos_resume_latency_attrs[] = {
 #ifdef CONFIG_PM_RUNTIME
 	&dev_attr_pm_qos_resume_latency_us.attr,
 #endif /* CONFIG_PM_RUNTIME */
 	NULL,
 };
-static struct attribute_group pm_qos_latency_attr_group = {
+static struct attribute_group pm_qos_resume_latency_attr_group = {
 	.name	= power_group_name,
-	.attrs	= pm_qos_latency_attrs,
+	.attrs	= pm_qos_resume_latency_attrs,
 };
 
 static struct attribute *pm_qos_flags_attrs[] = {
@@ -681,14 +683,14 @@ void wakeup_sysfs_remove(struct device *dev)
 	sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group);
 }
 
-int pm_qos_sysfs_add_latency(struct device *dev)
+int pm_qos_sysfs_add_resume_latency(struct device *dev)
 {
-	return sysfs_merge_group(&dev->kobj, &pm_qos_latency_attr_group);
+	return sysfs_merge_group(&dev->kobj, &pm_qos_resume_latency_attr_group);
 }
 
-void pm_qos_sysfs_remove_latency(struct device *dev)
+void pm_qos_sysfs_remove_resume_latency(struct device *dev)
 {
-	sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_attr_group);
+	sysfs_unmerge_group(&dev->kobj, &pm_qos_resume_latency_attr_group);
 }
 
 int pm_qos_sysfs_add_flags(struct device *dev)
diff --git a/drivers/mtd/nand/sh_flctl.c b/drivers/mtd/nand/sh_flctl.c
index d72783dd7b96..c0670237e7a2 100644
--- a/drivers/mtd/nand/sh_flctl.c
+++ b/drivers/mtd/nand/sh_flctl.c
@@ -897,7 +897,7 @@ static void flctl_select_chip(struct mtd_info *mtd, int chipnr)
 		if (!flctl->qos_request) {
 			ret = dev_pm_qos_add_request(&flctl->pdev->dev,
 							&flctl->pm_qos,
-							DEV_PM_QOS_LATENCY,
+							DEV_PM_QOS_RESUME_LATENCY,
 							100);
 			if (ret < 0)
 				dev_err(&flctl->pdev->dev,
diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h
index 5a95013905c8..88a3680ae74c 100644
--- a/include/linux/pm_qos.h
+++ b/include/linux/pm_qos.h
@@ -32,7 +32,7 @@ enum pm_qos_flags_status {
 #define PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE	(2000 * USEC_PER_SEC)
 #define PM_QOS_NETWORK_LAT_DEFAULT_VALUE	(2000 * USEC_PER_SEC)
 #define PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE	0
-#define PM_QOS_DEV_LAT_DEFAULT_VALUE		0
+#define PM_QOS_RESUME_LATENCY_DEFAULT_VALUE	0
 
 #define PM_QOS_FLAG_NO_POWER_OFF	(1 << 0)
 #define PM_QOS_FLAG_REMOTE_WAKEUP	(1 << 1)
@@ -49,7 +49,7 @@ struct pm_qos_flags_request {
 };
 
 enum dev_pm_qos_req_type {
-	DEV_PM_QOS_LATENCY = 1,
+	DEV_PM_QOS_RESUME_LATENCY = 1,
 	DEV_PM_QOS_FLAGS,
 };
 
@@ -87,9 +87,9 @@ struct pm_qos_flags {
 };
 
 struct dev_pm_qos {
-	struct pm_qos_constraints latency;
+	struct pm_qos_constraints resume_latency;
 	struct pm_qos_flags flags;
-	struct dev_pm_qos_request *latency_req;
+	struct dev_pm_qos_request *resume_latency_req;
 	struct dev_pm_qos_request *flags_req;
 };
 
@@ -196,9 +196,9 @@ int dev_pm_qos_expose_flags(struct device *dev, s32 value);
 void dev_pm_qos_hide_flags(struct device *dev);
 int dev_pm_qos_update_flags(struct device *dev, s32 mask, bool set);
 
-static inline s32 dev_pm_qos_requested_latency(struct device *dev)
+static inline s32 dev_pm_qos_requested_resume_latency(struct device *dev)
 {
-	return dev->power.qos->latency_req->data.pnode.prio;
+	return dev->power.qos->resume_latency_req->data.pnode.prio;
 }
 
 static inline s32 dev_pm_qos_requested_flags(struct device *dev)
@@ -215,7 +215,7 @@ static inline void dev_pm_qos_hide_flags(struct device *dev) {}
 static inline int dev_pm_qos_update_flags(struct device *dev, s32 m, bool set)
 			{ return 0; }
 
-static inline s32 dev_pm_qos_requested_latency(struct device *dev) { return 0; }
+static inline s32 dev_pm_qos_requested_resume_latency(struct device *dev) { return 0; }
 static inline s32 dev_pm_qos_requested_flags(struct device *dev) { return 0; }
 #endif
 
diff --git a/include/trace/events/power.h b/include/trace/events/power.h
index 9e9475c85de5..f6df9868ea0c 100644
--- a/include/trace/events/power.h
+++ b/include/trace/events/power.h
@@ -412,8 +412,8 @@ DECLARE_EVENT_CLASS(dev_pm_qos_request,
 	TP_printk("device=%s type=%s new_value=%d",
 		  __get_str(name),
 		  __print_symbolic(__entry->type,
-			{ DEV_PM_QOS_LATENCY,	"DEV_PM_QOS_LATENCY" },
-			{ DEV_PM_QOS_FLAGS,	"DEV_PM_QOS_FLAGS" }),
+			{ DEV_PM_QOS_RESUME_LATENCY, "DEV_PM_QOS_RESUME_LATENCY" },
+			{ DEV_PM_QOS_FLAGS, "DEV_PM_QOS_FLAGS" }),
 		  __entry->new_value)
 );
 
-- 
cgit v1.2.3


From 327adaedf2218b0e318eb393aa79cf2be64c199f Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 11 Feb 2014 00:35:29 +0100
Subject: PM / QoS: Add no_constraints_value field to struct pm_qos_constraints

Add a new field, no_constraints_value, to struct pm_qos_constraints
representing a list of PM QoS constraint requests to be returned by
pm_qos_get_value() when that list of requests is empty.

That field will be equal to default_value for all of the existing
global PM QoS classes and for the resume latency device PM QoS type,
but it will be different from default_value for the new latency
tolerance device PM QoS type introduced by the next changeset.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/qos.c | 1 +
 include/linux/pm_qos.h   | 1 +
 kernel/power/qos.c       | 5 ++++-
 3 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 67c0f4219b02..c754e55f9dcb 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -190,6 +190,7 @@ static int dev_pm_qos_constraints_allocate(struct device *dev)
 	plist_head_init(&c->list);
 	c->target_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE;
 	c->default_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE;
+	c->no_constraint_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE;
 	c->type = PM_QOS_MIN;
 	c->notifiers = n;
 
diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h
index 88a3680ae74c..2d8ce50877d8 100644
--- a/include/linux/pm_qos.h
+++ b/include/linux/pm_qos.h
@@ -77,6 +77,7 @@ struct pm_qos_constraints {
 	struct plist_head list;
 	s32 target_value;	/* Do not change to 64 bit */
 	s32 default_value;
+	s32 no_constraint_value;
 	enum pm_qos_type type;
 	struct blocking_notifier_head *notifiers;
 };
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index 8dff9b48075a..e23ae38e647f 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -66,6 +66,7 @@ static struct pm_qos_constraints cpu_dma_constraints = {
 	.list = PLIST_HEAD_INIT(cpu_dma_constraints.list),
 	.target_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
 	.default_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
+	.no_constraint_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
 	.type = PM_QOS_MIN,
 	.notifiers = &cpu_dma_lat_notifier,
 };
@@ -79,6 +80,7 @@ static struct pm_qos_constraints network_lat_constraints = {
 	.list = PLIST_HEAD_INIT(network_lat_constraints.list),
 	.target_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
 	.default_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
+	.no_constraint_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
 	.type = PM_QOS_MIN,
 	.notifiers = &network_lat_notifier,
 };
@@ -93,6 +95,7 @@ static struct pm_qos_constraints network_tput_constraints = {
 	.list = PLIST_HEAD_INIT(network_tput_constraints.list),
 	.target_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
 	.default_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
+	.no_constraint_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
 	.type = PM_QOS_MAX,
 	.notifiers = &network_throughput_notifier,
 };
@@ -128,7 +131,7 @@ static const struct file_operations pm_qos_power_fops = {
 static inline int pm_qos_get_value(struct pm_qos_constraints *c)
 {
 	if (plist_head_empty(&c->list))
-		return c->default_value;
+		return c->no_constraint_value;
 
 	switch (c->type) {
 	case PM_QOS_MIN:
-- 
cgit v1.2.3


From 2d984ad132a87ca2112f81f21039493176a8bca0 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 11 Feb 2014 00:35:38 +0100
Subject: PM / QoS: Introcuce latency tolerance device PM QoS type

Add a new latency tolerance device PM QoS type to be use for
specifying active state (RPM_ACTIVE) memory access (DMA) latency
tolerance requirements for devices.  It may be used to prevent
hardware from choosing overly aggressive energy-saving operation
modes (causing too much latency to appear) for the whole platform.

This feature reqiures hardware support, so it only will be
available for devices having a new .set_latency_tolerance()
callback in struct dev_pm_info populated, in which case the
routine pointed to by it should implement whatever is necessary
to transfer the effective requirement value to the hardware.

Whenever the effective latency tolerance changes for the device,
its .set_latency_tolerance() callback will be executed and the
effective value will be passed to it.  If that value is negative,
which means that the list of latency tolerance requirements for
the device is empty, the callback is expected to switch the
underlying hardware latency tolerance control mechanism to an
autonomous mode if available.  If that value is PM_QOS_LATENCY_ANY,
in turn, and the hardware supports a special "no requirement"
setting, the callback is expected to use it.  That allows software
to prevent the hardware from automatically updating the device's
latency tolerance in response to its power state changes (e.g. during
transitions from D3cold to D0), which generally may be done in the
autonomous latency tolerance control mode.

If .set_latency_tolerance() is present for the device, a new
pm_qos_latency_tolerance_us attribute will be present in the
devivce's power directory in sysfs.  Then, user space can use
that attribute to specify its latency tolerance requirement for
the device, if any.  Writing "any" to it means "no requirement, but
do not let the hardware control latency tolerance" and writing
"auto" to it allows the hardware to be switched to the autonomous
mode if there are no other requirements from the kernel side in the
device's list.

This changeset includes a fix from Mika Westerberg.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/ABI/testing/sysfs-devices-power |  27 ++++-
 Documentation/power/pm_qos_interface.txt      |  59 +++++++++--
 drivers/base/power/qos.c                      | 144 ++++++++++++++++++++++----
 drivers/base/power/sysfs.c                    |  65 ++++++++++--
 include/linux/pm.h                            |   1 +
 include/linux/pm_qos.h                        |  12 +++
 kernel/power/qos.c                            |  13 ++-
 7 files changed, 277 insertions(+), 44 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-devices-power b/Documentation/ABI/testing/sysfs-devices-power
index efe449bdf811..7dbf96b724ed 100644
--- a/Documentation/ABI/testing/sysfs-devices-power
+++ b/Documentation/ABI/testing/sysfs-devices-power
@@ -187,7 +187,7 @@ Description:
 		Not all drivers support this attribute.  If it isn't supported,
 		attempts to read or write it will yield I/O errors.
 
-What:		/sys/devices/.../power/pm_qos_latency_us
+What:		/sys/devices/.../power/pm_qos_resume_latency_us
 Date:		March 2012
 Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
 Description:
@@ -205,6 +205,31 @@ Description:
 		This attribute has no effect on system-wide suspend/resume and
 		hibernation.
 
+What:		/sys/devices/.../power/pm_qos_latency_tolerance_us
+Date:		January 2014
+Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
+Description:
+		The /sys/devices/.../power/pm_qos_latency_tolerance_us attribute
+		contains the PM QoS active state latency tolerance limit for the
+		given device in microseconds.  That is the maximum memory access
+		latency the device can suffer without any visible adverse
+		effects on user space functionality.  If that value is the
+		string "any", the latency does not matter to user space at all,
+		but hardware should not be allowed to set the latency tolerance
+		for the device automatically.
+
+		Reading "auto" from this file means that the maximum memory
+		access latency for the device may be determined automatically
+		by the hardware as needed.  Writing "auto" to it allows the
+		hardware to be switched to this mode if there are no other
+		latency tolerance requirements from the kernel side.
+
+		This attribute is only present if the feature controlled by it
+		is supported by the hardware.
+
+		This attribute has no effect on runtime suspend and resume of
+		devices and on system-wide suspend/resume and hibernation.
+
 What:		/sys/devices/.../power/pm_qos_no_power_off
 Date:		September 2012
 Contact:	Rafael J. Wysocki <rjw@rjwysocki.net>
diff --git a/Documentation/power/pm_qos_interface.txt b/Documentation/power/pm_qos_interface.txt
index 22cb8f51182a..ed743bbad87c 100644
--- a/Documentation/power/pm_qos_interface.txt
+++ b/Documentation/power/pm_qos_interface.txt
@@ -88,17 +88,19 @@ node.
 
 2. PM QoS per-device latency and flags framework
 
-For each device, there are two lists of PM QoS requests. One is maintained
-along with the aggregated target of resume latency value and the other is for
-PM QoS flags. Values are updated in response to changes of the request list.
+For each device, there are three lists of PM QoS requests. Two of them are
+maintained along with the aggregated targets of resume latency and active
+state latency tolerance (in microseconds) and the third one is for PM QoS flags.
+Values are updated in response to changes of the request list.
 
-Target resume latency value is simply the minimum of the request values held in
-the parameter list elements.  The PM QoS flags aggregate value is a gather
-(bitwise OR) of all list elements' values.  Two device PM QoS flags are defined
-currently: PM_QOS_FLAG_NO_POWER_OFF and PM_QOS_FLAG_REMOTE_WAKEUP.
+The target values of resume latency and active state latency tolerance are
+simply the minimum of the request values held in the parameter list elements.
+The PM QoS flags aggregate value is a gather (bitwise OR) of all list elements'
+values.  Two device PM QoS flags are defined currently: PM_QOS_FLAG_NO_POWER_OFF
+and PM_QOS_FLAG_REMOTE_WAKEUP.
 
-Note: the aggregated target value is implemented in such a way that reading the
-aggregated value does not require any locking mechanism.
+Note: The aggregated target values are implemented in such a way that reading
+the aggregated value does not require any locking mechanism.
 
 
 From kernel mode the use of this interface is the following:
@@ -177,3 +179,42 @@ The callback is called when the aggregated value for any device is changed
 int dev_pm_qos_remove_global_notifier(notifier):
 Removes the notification callback function from the global notification tree
 of the framework.
+
+
+Active state latency tolerance
+
+This device PM QoS type is used to support systems in which hardware may switch
+to energy-saving operation modes on the fly.  In those systems, if the operation
+mode chosen by the hardware attempts to save energy in an overly aggressive way,
+it may cause excess latencies to be visible to software, causing it to miss
+certain protocol requirements or target frame or sample rates etc.
+
+If there is a latency tolerance control mechanism for a given device available
+to software, the .set_latency_tolerance callback in that device's dev_pm_info
+structure should be populated.  The routine pointed to by it is should implement
+whatever is necessary to transfer the effective requirement value to the
+hardware.
+
+Whenever the effective latency tolerance changes for the device, its
+.set_latency_tolerance() callback will be executed and the effective value will
+be passed to it.  If that value is negative, which means that the list of
+latency tolerance requirements for the device is empty, the callback is expected
+to switch the underlying hardware latency tolerance control mechanism to an
+autonomous mode if available.  If that value is PM_QOS_LATENCY_ANY, in turn, and
+the hardware supports a special "no requirement" setting, the callback is
+expected to use it.  That allows software to prevent the hardware from
+automatically updating the device's latency tolerance in response to its power
+state changes (e.g. during transitions from D3cold to D0), which generally may
+be done in the autonomous latency tolerance control mode.
+
+If .set_latency_tolerance() is present for the device, sysfs attribute
+pm_qos_latency_tolerance_us will be present in the devivce's power directory.
+Then, user space can use that attribute to specify its latency tolerance
+requirement for the device, if any.  Writing "any" to it means "no requirement,
+but do not let the hardware control latency tolerance" and writing "auto" to it
+allows the hardware to be switched to the autonomous mode if there are no other
+requirements from the kernel side in the device's list.
+
+Kernel code can use the functions described above along with the
+DEV_PM_QOS_LATENCY_TOLERANCE device PM QoS type to add, remove and update
+latency tolerance requirements for devices.
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index c754e55f9dcb..84756f7f09d9 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -151,6 +151,14 @@ static int apply_constraint(struct dev_pm_qos_request *req,
 						     req);
 		}
 		break;
+	case DEV_PM_QOS_LATENCY_TOLERANCE:
+		ret = pm_qos_update_target(&qos->latency_tolerance,
+					   &req->data.pnode, action, value);
+		if (ret) {
+			value = pm_qos_read_value(&qos->latency_tolerance);
+			req->dev->power.set_latency_tolerance(req->dev, value);
+		}
+		break;
 	case DEV_PM_QOS_FLAGS:
 		ret = pm_qos_update_flags(&qos->flags, &req->data.flr,
 					  action, value);
@@ -194,6 +202,13 @@ static int dev_pm_qos_constraints_allocate(struct device *dev)
 	c->type = PM_QOS_MIN;
 	c->notifiers = n;
 
+	c = &qos->latency_tolerance;
+	plist_head_init(&c->list);
+	c->target_value = PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE;
+	c->default_value = PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE;
+	c->no_constraint_value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT;
+	c->type = PM_QOS_MIN;
+
 	INIT_LIST_HEAD(&qos->flags.list);
 
 	spin_lock_irq(&dev->power.lock);
@@ -247,6 +262,11 @@ void dev_pm_qos_constraints_destroy(struct device *dev)
 		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
 		memset(req, 0, sizeof(*req));
 	}
+	c = &qos->latency_tolerance;
+	plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) {
+		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
+		memset(req, 0, sizeof(*req));
+	}
 	f = &qos->flags;
 	list_for_each_entry_safe(req, tmp, &f->list, data.flr.node) {
 		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
@@ -266,6 +286,40 @@ void dev_pm_qos_constraints_destroy(struct device *dev)
 	mutex_unlock(&dev_pm_qos_sysfs_mtx);
 }
 
+static bool dev_pm_qos_invalid_request(struct device *dev,
+				       struct dev_pm_qos_request *req)
+{
+	return !req || (req->type == DEV_PM_QOS_LATENCY_TOLERANCE
+			&& !dev->power.set_latency_tolerance);
+}
+
+static int __dev_pm_qos_add_request(struct device *dev,
+				    struct dev_pm_qos_request *req,
+				    enum dev_pm_qos_req_type type, s32 value)
+{
+	int ret = 0;
+
+	if (!dev || dev_pm_qos_invalid_request(dev, req))
+		return -EINVAL;
+
+	if (WARN(dev_pm_qos_request_active(req),
+		 "%s() called for already added request\n", __func__))
+		return -EINVAL;
+
+	if (IS_ERR(dev->power.qos))
+		ret = -ENODEV;
+	else if (!dev->power.qos)
+		ret = dev_pm_qos_constraints_allocate(dev);
+
+	trace_dev_pm_qos_add_request(dev_name(dev), type, value);
+	if (!ret) {
+		req->dev = dev;
+		req->type = type;
+		ret = apply_constraint(req, PM_QOS_ADD_REQ, value);
+	}
+	return ret;
+}
+
 /**
  * dev_pm_qos_add_request - inserts new qos request into the list
  * @dev: target device for the constraint
@@ -291,31 +345,11 @@ void dev_pm_qos_constraints_destroy(struct device *dev)
 int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req,
 			   enum dev_pm_qos_req_type type, s32 value)
 {
-	int ret = 0;
-
-	if (!dev || !req) /*guard against callers passing in null */
-		return -EINVAL;
-
-	if (WARN(dev_pm_qos_request_active(req),
-		 "%s() called for already added request\n", __func__))
-		return -EINVAL;
+	int ret;
 
 	mutex_lock(&dev_pm_qos_mtx);
-
-	if (IS_ERR(dev->power.qos))
-		ret = -ENODEV;
-	else if (!dev->power.qos)
-		ret = dev_pm_qos_constraints_allocate(dev);
-
-	trace_dev_pm_qos_add_request(dev_name(dev), type, value);
-	if (!ret) {
-		req->dev = dev;
-		req->type = type;
-		ret = apply_constraint(req, PM_QOS_ADD_REQ, value);
-	}
-
+	ret = __dev_pm_qos_add_request(dev, req, type, value);
 	mutex_unlock(&dev_pm_qos_mtx);
-
 	return ret;
 }
 EXPORT_SYMBOL_GPL(dev_pm_qos_add_request);
@@ -343,6 +377,7 @@ static int __dev_pm_qos_update_request(struct dev_pm_qos_request *req,
 
 	switch(req->type) {
 	case DEV_PM_QOS_RESUME_LATENCY:
+	case DEV_PM_QOS_LATENCY_TOLERANCE:
 		curr_value = req->data.pnode.prio;
 		break;
 	case DEV_PM_QOS_FLAGS:
@@ -563,6 +598,10 @@ static void __dev_pm_qos_drop_user_request(struct device *dev,
 		req = dev->power.qos->resume_latency_req;
 		dev->power.qos->resume_latency_req = NULL;
 		break;
+	case DEV_PM_QOS_LATENCY_TOLERANCE:
+		req = dev->power.qos->latency_tolerance_req;
+		dev->power.qos->latency_tolerance_req = NULL;
+		break;
 	case DEV_PM_QOS_FLAGS:
 		req = dev->power.qos->flags_req;
 		dev->power.qos->flags_req = NULL;
@@ -768,6 +807,67 @@ int dev_pm_qos_update_flags(struct device *dev, s32 mask, bool set)
 	pm_runtime_put(dev);
 	return ret;
 }
+
+/**
+ * dev_pm_qos_get_user_latency_tolerance - Get user space latency tolerance.
+ * @dev: Device to obtain the user space latency tolerance for.
+ */
+s32 dev_pm_qos_get_user_latency_tolerance(struct device *dev)
+{
+	s32 ret;
+
+	mutex_lock(&dev_pm_qos_mtx);
+	ret = IS_ERR_OR_NULL(dev->power.qos)
+		|| !dev->power.qos->latency_tolerance_req ?
+			PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT :
+			dev->power.qos->latency_tolerance_req->data.pnode.prio;
+	mutex_unlock(&dev_pm_qos_mtx);
+	return ret;
+}
+
+/**
+ * dev_pm_qos_update_user_latency_tolerance - Update user space latency tolerance.
+ * @dev: Device to update the user space latency tolerance for.
+ * @val: New user space latency tolerance for @dev (negative values disable).
+ */
+int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val)
+{
+	int ret;
+
+	mutex_lock(&dev_pm_qos_mtx);
+
+	if (IS_ERR_OR_NULL(dev->power.qos)
+	    || !dev->power.qos->latency_tolerance_req) {
+		struct dev_pm_qos_request *req;
+
+		if (val < 0) {
+			ret = -EINVAL;
+			goto out;
+		}
+		req = kzalloc(sizeof(*req), GFP_KERNEL);
+		if (!req) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		ret = __dev_pm_qos_add_request(dev, req, DEV_PM_QOS_LATENCY_TOLERANCE, val);
+		if (ret < 0) {
+			kfree(req);
+			goto out;
+		}
+		dev->power.qos->latency_tolerance_req = req;
+	} else {
+		if (val < 0) {
+			__dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_LATENCY_TOLERANCE);
+			ret = 0;
+		} else {
+			ret = __dev_pm_qos_update_request(dev->power.qos->latency_tolerance_req, val);
+		}
+	}
+
+ out:
+	mutex_unlock(&dev_pm_qos_mtx);
+	return ret;
+}
 #else /* !CONFIG_PM_RUNTIME */
 static void __dev_pm_qos_hide_latency_limit(struct device *dev) {}
 static void __dev_pm_qos_hide_flags(struct device *dev) {}
diff --git a/drivers/base/power/sysfs.c b/drivers/base/power/sysfs.c
index 4e24955aac8a..95b181d1ca6d 100644
--- a/drivers/base/power/sysfs.c
+++ b/drivers/base/power/sysfs.c
@@ -246,6 +246,40 @@ static ssize_t pm_qos_resume_latency_store(struct device *dev,
 static DEVICE_ATTR(pm_qos_resume_latency_us, 0644,
 		   pm_qos_resume_latency_show, pm_qos_resume_latency_store);
 
+static ssize_t pm_qos_latency_tolerance_show(struct device *dev,
+					     struct device_attribute *attr,
+					     char *buf)
+{
+	s32 value = dev_pm_qos_get_user_latency_tolerance(dev);
+
+	if (value < 0)
+		return sprintf(buf, "auto\n");
+	else if (value == PM_QOS_LATENCY_ANY)
+		return sprintf(buf, "any\n");
+
+	return sprintf(buf, "%d\n", value);
+}
+
+static ssize_t pm_qos_latency_tolerance_store(struct device *dev,
+					      struct device_attribute *attr,
+					      const char *buf, size_t n)
+{
+	s32 value;
+	int ret;
+
+	if (kstrtos32(buf, 0, &value)) {
+		if (!strcmp(buf, "auto") || !strcmp(buf, "auto\n"))
+			value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT;
+		else if (!strcmp(buf, "any") || !strcmp(buf, "any\n"))
+			value = PM_QOS_LATENCY_ANY;
+	}
+	ret = dev_pm_qos_update_user_latency_tolerance(dev, value);
+	return ret < 0 ? ret : n;
+}
+
+static DEVICE_ATTR(pm_qos_latency_tolerance_us, 0644,
+		   pm_qos_latency_tolerance_show, pm_qos_latency_tolerance_store);
+
 static ssize_t pm_qos_no_power_off_show(struct device *dev,
 					struct device_attribute *attr,
 					char *buf)
@@ -631,6 +665,17 @@ static struct attribute_group pm_qos_resume_latency_attr_group = {
 	.attrs	= pm_qos_resume_latency_attrs,
 };
 
+static struct attribute *pm_qos_latency_tolerance_attrs[] = {
+#ifdef CONFIG_PM_RUNTIME
+	&dev_attr_pm_qos_latency_tolerance_us.attr,
+#endif /* CONFIG_PM_RUNTIME */
+	NULL,
+};
+static struct attribute_group pm_qos_latency_tolerance_attr_group = {
+	.name	= power_group_name,
+	.attrs	= pm_qos_latency_tolerance_attrs,
+};
+
 static struct attribute *pm_qos_flags_attrs[] = {
 #ifdef CONFIG_PM_RUNTIME
 	&dev_attr_pm_qos_no_power_off.attr,
@@ -656,18 +701,23 @@ int dpm_sysfs_add(struct device *dev)
 		if (rc)
 			goto err_out;
 	}
-
 	if (device_can_wakeup(dev)) {
 		rc = sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group);
-		if (rc) {
-			if (pm_runtime_callbacks_present(dev))
-				sysfs_unmerge_group(&dev->kobj,
-						    &pm_runtime_attr_group);
-			goto err_out;
-		}
+		if (rc)
+			goto err_runtime;
+	}
+	if (dev->power.set_latency_tolerance) {
+		rc = sysfs_merge_group(&dev->kobj,
+				       &pm_qos_latency_tolerance_attr_group);
+		if (rc)
+			goto err_wakeup;
 	}
 	return 0;
 
+ err_wakeup:
+	sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group);
+ err_runtime:
+	sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group);
  err_out:
 	sysfs_remove_group(&dev->kobj, &pm_attr_group);
 	return rc;
@@ -710,6 +760,7 @@ void rpm_sysfs_remove(struct device *dev)
 
 void dpm_sysfs_remove(struct device *dev)
 {
+	sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group);
 	dev_pm_qos_constraints_destroy(dev);
 	rpm_sysfs_remove(dev);
 	sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group);
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 8c6583a53a06..db2be5f3e030 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -582,6 +582,7 @@ struct dev_pm_info {
 	unsigned long		accounting_timestamp;
 #endif
 	struct pm_subsys_data	*subsys_data;  /* Owned by the subsystem. */
+	void (*set_latency_tolerance)(struct device *, s32);
 	struct dev_pm_qos	*qos;
 };
 
diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h
index 2d8ce50877d8..0b476019be55 100644
--- a/include/linux/pm_qos.h
+++ b/include/linux/pm_qos.h
@@ -33,6 +33,9 @@ enum pm_qos_flags_status {
 #define PM_QOS_NETWORK_LAT_DEFAULT_VALUE	(2000 * USEC_PER_SEC)
 #define PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE	0
 #define PM_QOS_RESUME_LATENCY_DEFAULT_VALUE	0
+#define PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE	0
+#define PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT	(-1)
+#define PM_QOS_LATENCY_ANY			((s32)(~(__u32)0 >> 1))
 
 #define PM_QOS_FLAG_NO_POWER_OFF	(1 << 0)
 #define PM_QOS_FLAG_REMOTE_WAKEUP	(1 << 1)
@@ -50,6 +53,7 @@ struct pm_qos_flags_request {
 
 enum dev_pm_qos_req_type {
 	DEV_PM_QOS_RESUME_LATENCY = 1,
+	DEV_PM_QOS_LATENCY_TOLERANCE,
 	DEV_PM_QOS_FLAGS,
 };
 
@@ -89,8 +93,10 @@ struct pm_qos_flags {
 
 struct dev_pm_qos {
 	struct pm_qos_constraints resume_latency;
+	struct pm_qos_constraints latency_tolerance;
 	struct pm_qos_flags flags;
 	struct dev_pm_qos_request *resume_latency_req;
+	struct dev_pm_qos_request *latency_tolerance_req;
 	struct dev_pm_qos_request *flags_req;
 };
 
@@ -196,6 +202,8 @@ void dev_pm_qos_hide_latency_limit(struct device *dev);
 int dev_pm_qos_expose_flags(struct device *dev, s32 value);
 void dev_pm_qos_hide_flags(struct device *dev);
 int dev_pm_qos_update_flags(struct device *dev, s32 mask, bool set);
+s32 dev_pm_qos_get_user_latency_tolerance(struct device *dev);
+int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val);
 
 static inline s32 dev_pm_qos_requested_resume_latency(struct device *dev)
 {
@@ -215,6 +223,10 @@ static inline int dev_pm_qos_expose_flags(struct device *dev, s32 value)
 static inline void dev_pm_qos_hide_flags(struct device *dev) {}
 static inline int dev_pm_qos_update_flags(struct device *dev, s32 m, bool set)
 			{ return 0; }
+static inline s32 dev_pm_qos_get_user_latency_tolerance(struct device *dev)
+			{ return PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT; }
+static inline int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val)
+			{ return 0; }
 
 static inline s32 dev_pm_qos_requested_resume_latency(struct device *dev) { return 0; }
 static inline s32 dev_pm_qos_requested_flags(struct device *dev) { return 0; }
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index e23ae38e647f..884b77058864 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -173,6 +173,7 @@ int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node,
 {
 	unsigned long flags;
 	int prev_value, curr_value, new_value;
+	int ret;
 
 	spin_lock_irqsave(&pm_qos_lock, flags);
 	prev_value = pm_qos_get_value(c);
@@ -208,13 +209,15 @@ int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node,
 
 	trace_pm_qos_update_target(action, prev_value, curr_value);
 	if (prev_value != curr_value) {
-		blocking_notifier_call_chain(c->notifiers,
-					     (unsigned long)curr_value,
-					     NULL);
-		return 1;
+		ret = 1;
+		if (c->notifiers)
+			blocking_notifier_call_chain(c->notifiers,
+						     (unsigned long)curr_value,
+						     NULL);
 	} else {
-		return 0;
+		ret = 0;
 	}
+	return ret;
 }
 
 /**
-- 
cgit v1.2.3


From 71d821fdaec08afcbfb3cf258c0d64ea0e336ff3 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Tue, 11 Feb 2014 00:36:00 +0100
Subject: PM / QoS: Add type to dev_pm_qos_add_ancestor_request() arguments

Rework dev_pm_qos_add_ancestor_request() so that device PM QoS type
is passed to it as the third argument and make it support the
DEV_PM_QOS_LATENCY_TOLERANCE device PM QoS type (in addition to
DEV_PM_QOS_RESUME_LATENCY).

That will allow the drivers of devices without latency tolerance
hardware support to use their ancestors having it as proxies for
their latency tolerance requirements.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/power/pm_qos_interface.txt |  6 ++++--
 drivers/base/power/qos.c                 | 22 +++++++++++++++++-----
 drivers/input/touchscreen/st1232.c       |  3 ++-
 include/linux/pm_qos.h                   |  7 +++++--
 4 files changed, 28 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/power/pm_qos_interface.txt b/Documentation/power/pm_qos_interface.txt
index ed743bbad87c..a5da5c7e7128 100644
--- a/Documentation/power/pm_qos_interface.txt
+++ b/Documentation/power/pm_qos_interface.txt
@@ -134,9 +134,11 @@ The meaning of the return values is as follows:
 	PM_QOS_FLAGS_UNDEFINED: The device's PM QoS structure has not been
 			initialized or the list of requests is empty.
 
-int dev_pm_qos_add_ancestor_request(dev, handle, value)
+int dev_pm_qos_add_ancestor_request(dev, handle, type, value)
 Add a PM QoS request for the first direct ancestor of the given device whose
-power.ignore_children flag is unset.
+power.ignore_children flag is unset (for DEV_PM_QOS_RESUME_LATENCY requests)
+or whose power.set_latency_tolerance callback pointer is not NULL (for
+DEV_PM_QOS_LATENCY_TOLERANCE requests).
 
 int dev_pm_qos_expose_latency_limit(device, value)
 Add a request to the device's PM QoS list of resume latency constraints and
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 84756f7f09d9..36b9eb4862cb 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -565,20 +565,32 @@ EXPORT_SYMBOL_GPL(dev_pm_qos_remove_global_notifier);
  * dev_pm_qos_add_ancestor_request - Add PM QoS request for device's ancestor.
  * @dev: Device whose ancestor to add the request for.
  * @req: Pointer to the preallocated handle.
+ * @type: Type of the request.
  * @value: Constraint latency value.
  */
 int dev_pm_qos_add_ancestor_request(struct device *dev,
-				    struct dev_pm_qos_request *req, s32 value)
+				    struct dev_pm_qos_request *req,
+				    enum dev_pm_qos_req_type type, s32 value)
 {
 	struct device *ancestor = dev->parent;
 	int ret = -ENODEV;
 
-	while (ancestor && !ancestor->power.ignore_children)
-		ancestor = ancestor->parent;
+	switch (type) {
+	case DEV_PM_QOS_RESUME_LATENCY:
+		while (ancestor && !ancestor->power.ignore_children)
+			ancestor = ancestor->parent;
 
+		break;
+	case DEV_PM_QOS_LATENCY_TOLERANCE:
+		while (ancestor && !ancestor->power.set_latency_tolerance)
+			ancestor = ancestor->parent;
+
+		break;
+	default:
+		ancestor = NULL;
+	}
 	if (ancestor)
-		ret = dev_pm_qos_add_request(ancestor, req,
-					     DEV_PM_QOS_RESUME_LATENCY, value);
+		ret = dev_pm_qos_add_request(ancestor, req, type, value);
 
 	if (ret < 0)
 		req->dev = NULL;
diff --git a/drivers/input/touchscreen/st1232.c b/drivers/input/touchscreen/st1232.c
index 5c342b3139e8..3c0f57efe7b1 100644
--- a/drivers/input/touchscreen/st1232.c
+++ b/drivers/input/touchscreen/st1232.c
@@ -134,7 +134,8 @@ static irqreturn_t st1232_ts_irq_handler(int irq, void *dev_id)
 	} else if (!ts->low_latency_req.dev) {
 		/* First contact, request 100 us latency. */
 		dev_pm_qos_add_ancestor_request(&ts->client->dev,
-						&ts->low_latency_req, 100);
+						&ts->low_latency_req,
+						DEV_PM_QOS_RESUME_LATENCY, 100);
 	}
 
 	/* SYN_REPORT */
diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h
index 0b476019be55..9ab4bf7c4646 100644
--- a/include/linux/pm_qos.h
+++ b/include/linux/pm_qos.h
@@ -149,7 +149,8 @@ int dev_pm_qos_remove_global_notifier(struct notifier_block *notifier);
 void dev_pm_qos_constraints_init(struct device *dev);
 void dev_pm_qos_constraints_destroy(struct device *dev);
 int dev_pm_qos_add_ancestor_request(struct device *dev,
-				    struct dev_pm_qos_request *req, s32 value);
+				    struct dev_pm_qos_request *req,
+				    enum dev_pm_qos_req_type type, s32 value);
 #else
 static inline enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev,
 							  s32 mask)
@@ -192,7 +193,9 @@ static inline void dev_pm_qos_constraints_destroy(struct device *dev)
 	dev->power.power_state = PMSG_INVALID;
 }
 static inline int dev_pm_qos_add_ancestor_request(struct device *dev,
-				    struct dev_pm_qos_request *req, s32 value)
+						  struct dev_pm_qos_request *req,
+						  enum dev_pm_qos_req_type type,
+						  s32 value)
 			{ return 0; }
 #endif
 
-- 
cgit v1.2.3


From 9fe21fdc5f3d3aa7d6e78ad25668e234330b6974 Mon Sep 17 00:00:00 2001
From: Alexander Shiyan <shc_work@mail.ru>
Date: Sat, 21 Dec 2013 15:08:00 +0400
Subject: video: imxfb: Use regulator API with LCD class for powering

This patch replaces custom lcd_power() callback with
regulator API over LCD class.

Signed-off-by: Alexander Shiyan <shc_work@mail.ru>
Acked-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 .../devicetree/bindings/video/fsl,imx-fb.txt       |  1 +
 arch/arm/mach-imx/mach-mx27ads.c                   | 55 +++++++++++++++--
 drivers/video/imxfb.c                              | 71 +++++++++++++++++++---
 include/linux/platform_data/video-imxfb.h          |  1 -
 4 files changed, 114 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/devicetree/bindings/video/fsl,imx-fb.txt b/Documentation/devicetree/bindings/video/fsl,imx-fb.txt
index 46da08db186a..e6b1ee9b8e2e 100644
--- a/Documentation/devicetree/bindings/video/fsl,imx-fb.txt
+++ b/Documentation/devicetree/bindings/video/fsl,imx-fb.txt
@@ -15,6 +15,7 @@ Required nodes:
 	- fsl,pcr: LCDC PCR value
 
 Optional properties:
+- lcd-supply: Regulator for LCD supply voltage.
 - fsl,dmacr: DMA Control Register value. This is optional. By default, the
 	register is not modified as recommended by the datasheet.
 - fsl,lscr1: LCDC Sharp Configuration Register value.
diff --git a/arch/arm/mach-imx/mach-mx27ads.c b/arch/arm/mach-imx/mach-mx27ads.c
index 9821b824dcaf..a7a4a9c67615 100644
--- a/arch/arm/mach-imx/mach-mx27ads.c
+++ b/arch/arm/mach-imx/mach-mx27ads.c
@@ -21,6 +21,10 @@
 #include <linux/mtd/physmap.h>
 #include <linux/i2c.h>
 #include <linux/irq.h>
+
+#include <linux/regulator/fixed.h>
+#include <linux/regulator/machine.h>
+
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
@@ -195,14 +199,58 @@ static const struct imxi2c_platform_data mx27ads_i2c1_data __initconst = {
 static struct i2c_board_info mx27ads_i2c_devices[] = {
 };
 
-void lcd_power(int on)
+static void vgpio_set(struct gpio_chip *chip, unsigned offset, int value)
 {
-	if (on)
+	if (value)
 		__raw_writew(PBC_BCTRL1_LCDON, PBC_BCTRL1_SET_REG);
 	else
 		__raw_writew(PBC_BCTRL1_LCDON, PBC_BCTRL1_CLEAR_REG);
 }
 
+static int vgpio_dir_out(struct gpio_chip *chip, unsigned offset, int value)
+{
+	return 0;
+}
+
+#define MX27ADS_LCD_GPIO	(6 * 32)
+
+static struct regulator_consumer_supply mx27ads_lcd_regulator_consumer =
+	REGULATOR_SUPPLY("lcd", "imx-fb.0");
+
+static struct regulator_init_data mx27ads_lcd_regulator_init_data = {
+	.constraints	= {
+		.valid_ops_mask	= REGULATOR_CHANGE_STATUS,
+},
+	.consumer_supplies	= &mx27ads_lcd_regulator_consumer,
+	.num_consumer_supplies	= 1,
+};
+
+static struct fixed_voltage_config mx27ads_lcd_regulator_pdata = {
+	.supply_name	= "LCD",
+	.microvolts	= 3300000,
+	.gpio		= MX27ADS_LCD_GPIO,
+	.init_data	= &mx27ads_lcd_regulator_init_data,
+};
+
+static void __init mx27ads_regulator_init(void)
+{
+	struct gpio_chip *vchip;
+
+	vchip = kzalloc(sizeof(*vchip), GFP_KERNEL);
+	vchip->owner		= THIS_MODULE;
+	vchip->label		= "LCD";
+	vchip->base		= MX27ADS_LCD_GPIO;
+	vchip->ngpio		= 1;
+	vchip->direction_output	= vgpio_dir_out;
+	vchip->set		= vgpio_set;
+	gpiochip_add(vchip);
+
+	platform_device_register_data(&platform_bus, "reg-fixed-voltage",
+				      PLATFORM_DEVID_AUTO,
+				      &mx27ads_lcd_regulator_pdata,
+				      sizeof(mx27ads_lcd_regulator_pdata));
+}
+
 static struct imx_fb_videomode mx27ads_modes[] = {
 	{
 		.mode = {
@@ -239,8 +287,6 @@ static const struct imx_fb_platform_data mx27ads_fb_data __initconst = {
 	.pwmr		= 0x00A903FF,
 	.lscr1		= 0x00120300,
 	.dmacr		= 0x00020010,
-
-	.lcd_power	= lcd_power,
 };
 
 static int mx27ads_sdhc1_init(struct device *dev, irq_handler_t detect_irq,
@@ -304,6 +350,7 @@ static void __init mx27ads_board_init(void)
 	i2c_register_board_info(1, mx27ads_i2c_devices,
 				ARRAY_SIZE(mx27ads_i2c_devices));
 	imx27_add_imx_i2c(1, &mx27ads_i2c1_data);
+	mx27ads_regulator_init();
 	imx27_add_imx_fb(&mx27ads_fb_data);
 	imx27_add_mxc_mmc(0, &sdhc1_pdata);
 	imx27_add_mxc_mmc(1, &sdhc2_pdata);
diff --git a/drivers/video/imxfb.c b/drivers/video/imxfb.c
index 44ee678481d5..e50b67fada51 100644
--- a/drivers/video/imxfb.c
+++ b/drivers/video/imxfb.c
@@ -30,10 +30,13 @@
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 #include <linux/io.h>
+#include <linux/lcd.h>
 #include <linux/math64.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 
+#include <linux/regulator/consumer.h>
+
 #include <video/of_display_timing.h>
 #include <video/of_videomode.h>
 #include <video/videomode.h>
@@ -177,8 +180,9 @@ struct imxfb_info {
 	struct backlight_device *bl;
 #endif
 
-	void (*lcd_power)(int);
 	void (*backlight_power)(int);
+
+	struct regulator	*lcd_pwr;
 };
 
 static struct platform_device_id imxfb_devtype[] = {
@@ -591,8 +595,6 @@ static void imxfb_enable_controller(struct imxfb_info *fbi)
 
 	if (fbi->backlight_power)
 		fbi->backlight_power(1);
-	if (fbi->lcd_power)
-		fbi->lcd_power(1);
 }
 
 static void imxfb_disable_controller(struct imxfb_info *fbi)
@@ -604,8 +606,6 @@ static void imxfb_disable_controller(struct imxfb_info *fbi)
 
 	if (fbi->backlight_power)
 		fbi->backlight_power(0);
-	if (fbi->lcd_power)
-		fbi->lcd_power(0);
 
 	clk_disable_unprepare(fbi->clk_per);
 	clk_disable_unprepare(fbi->clk_ipg);
@@ -796,7 +796,6 @@ static int imxfb_init_fbinfo(struct platform_device *pdev)
 		fbi->lscr1			= pdata->lscr1;
 		fbi->dmacr			= pdata->dmacr;
 		fbi->pwmr			= pdata->pwmr;
-		fbi->lcd_power			= pdata->lcd_power;
 		fbi->backlight_power		= pdata->backlight_power;
 	} else {
 		np = pdev->dev.of_node;
@@ -810,9 +809,6 @@ static int imxfb_init_fbinfo(struct platform_device *pdev)
 
 		of_property_read_u32(np, "fsl,dmacr", &fbi->dmacr);
 
-		/* These two function pointers could be used by some specific
-		 * platforms. */
-		fbi->lcd_power = NULL;
 		fbi->backlight_power = NULL;
 	}
 
@@ -856,9 +852,50 @@ static int imxfb_of_read_mode(struct device *dev, struct device_node *np,
 	return 0;
 }
 
+static int imxfb_lcd_check_fb(struct lcd_device *lcddev, struct fb_info *fi)
+{
+	struct imxfb_info *fbi = dev_get_drvdata(&lcddev->dev);
+
+	if (!fi || fi->par == fbi)
+		return 1;
+
+	return 0;
+}
+
+static int imxfb_lcd_get_power(struct lcd_device *lcddev)
+{
+	struct imxfb_info *fbi = dev_get_drvdata(&lcddev->dev);
+
+	if (!IS_ERR(fbi->lcd_pwr))
+		return regulator_is_enabled(fbi->lcd_pwr);
+
+	return 1;
+}
+
+static int imxfb_lcd_set_power(struct lcd_device *lcddev, int power)
+{
+	struct imxfb_info *fbi = dev_get_drvdata(&lcddev->dev);
+
+	if (!IS_ERR(fbi->lcd_pwr)) {
+		if (power)
+			return regulator_enable(fbi->lcd_pwr);
+		else
+			return regulator_disable(fbi->lcd_pwr);
+	}
+
+	return 0;
+}
+
+static struct lcd_ops imxfb_lcd_ops = {
+	.check_fb	= imxfb_lcd_check_fb,
+	.get_power	= imxfb_lcd_get_power,
+	.set_power	= imxfb_lcd_set_power,
+};
+
 static int imxfb_probe(struct platform_device *pdev)
 {
 	struct imxfb_info *fbi;
+	struct lcd_device *lcd;
 	struct fb_info *info;
 	struct imx_fb_platform_data *pdata;
 	struct resource *res;
@@ -1020,6 +1057,19 @@ static int imxfb_probe(struct platform_device *pdev)
 		goto failed_register;
 	}
 
+	fbi->lcd_pwr = devm_regulator_get(&pdev->dev, "lcd");
+	if (IS_ERR(fbi->lcd_pwr) && (PTR_ERR(fbi->lcd_pwr) == -EPROBE_DEFER)) {
+		ret = -EPROBE_DEFER;
+		goto failed_lcd;
+	}
+
+	lcd = devm_lcd_device_register(&pdev->dev, "imxfb-lcd", &pdev->dev, fbi,
+				       &imxfb_lcd_ops);
+	if (IS_ERR(lcd)) {
+		ret = PTR_ERR(lcd);
+		goto failed_lcd;
+	}
+
 	imxfb_enable_controller(fbi);
 	fbi->pdev = pdev;
 #ifdef PWMR_BACKLIGHT_AVAILABLE
@@ -1028,6 +1078,9 @@ static int imxfb_probe(struct platform_device *pdev)
 
 	return 0;
 
+failed_lcd:
+	unregister_framebuffer(info);
+
 failed_register:
 	fb_dealloc_cmap(&info->cmap);
 failed_cmap:
diff --git a/include/linux/platform_data/video-imxfb.h b/include/linux/platform_data/video-imxfb.h
index 9de8f062ad5d..8902706fffa4 100644
--- a/include/linux/platform_data/video-imxfb.h
+++ b/include/linux/platform_data/video-imxfb.h
@@ -76,7 +76,6 @@ struct imx_fb_platform_data {
 	int (*init)(struct platform_device *);
 	void (*exit)(struct platform_device *);
 
-	void (*lcd_power)(int);
 	void (*backlight_power)(int);
 };
 
-- 
cgit v1.2.3


From c4a41bcc17260759645be6833ac7a99a9fb4c363 Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@xilinx.com>
Date: Tue, 11 Feb 2014 07:48:32 +0100
Subject: video: xilinxfb: Move xilinxfb_platform_data directly to the driver

No reason to have separate file in header in include/linux folder
if this is purely driver specific structure.

Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/video/xilinxfb.c | 15 ++++++++++++++-
 include/linux/xilinxfb.h | 30 ------------------------------
 2 files changed, 14 insertions(+), 31 deletions(-)
 delete mode 100644 include/linux/xilinxfb.h

(limited to 'include/linux')

diff --git a/drivers/video/xilinxfb.c b/drivers/video/xilinxfb.c
index 6ff1a91e9dfd..553cff2f3f4c 100644
--- a/drivers/video/xilinxfb.c
+++ b/drivers/video/xilinxfb.c
@@ -33,7 +33,6 @@
 #include <linux/of_platform.h>
 #include <linux/of_address.h>
 #include <linux/io.h>
-#include <linux/xilinxfb.h>
 #include <linux/slab.h>
 
 #ifdef CONFIG_PPC_DCR
@@ -84,6 +83,20 @@
 
 #define PALETTE_ENTRIES_NO	16	/* passed to fb_alloc_cmap() */
 
+/* ML300/403 reference design framebuffer driver platform data struct */
+struct xilinxfb_platform_data {
+	u32 rotate_screen;      /* Flag to rotate display 180 degrees */
+	u32 screen_height_mm;   /* Physical dimensions of screen in mm */
+	u32 screen_width_mm;
+	u32 xres, yres;         /* resolution of screen in pixels */
+	u32 xvirt, yvirt;       /* resolution of memory buffer */
+
+	/* Physical address of framebuffer memory; If non-zero, driver
+	* will use provided memory address instead of allocating one from
+	* the consistent pool. */
+	u32 fb_phys;
+};
+
 /*
  * Default xilinxfb configuration
  */
diff --git a/include/linux/xilinxfb.h b/include/linux/xilinxfb.h
deleted file mode 100644
index 5a155a968054..000000000000
--- a/include/linux/xilinxfb.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * Platform device data for Xilinx Framebuffer device
- *
- * Copyright 2007 Secret Lab Technologies Ltd.
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2.  This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
-
-#ifndef __XILINXFB_H__
-#define __XILINXFB_H__
-
-#include <linux/types.h>
-
-/* ML300/403 reference design framebuffer driver platform data struct */
-struct xilinxfb_platform_data {
-	u32 rotate_screen;	/* Flag to rotate display 180 degrees */
-	u32 screen_height_mm;	/* Physical dimensions of screen in mm */
-	u32 screen_width_mm;
-	u32 xres, yres;		/* resolution of screen in pixels */
-	u32 xvirt, yvirt;	/* resolution of memory buffer */
-
-	/* Physical address of framebuffer memory; If non-zero, driver
-	 * will use provided memory address instead of allocating one from
-	 * the consistent pool. */
-	u32 fb_phys;
-};
-
-#endif  /* __XILINXFB_H__ */
-- 
cgit v1.2.3


From e31108cad3deabb1a63111d7aa699ca67753c01f Mon Sep 17 00:00:00 2001
From: Manish Badarkhe <badarkhe.manish@gmail.com>
Date: Wed, 29 Jan 2014 20:27:27 +0530
Subject: devres: introduce API "devm_kstrdup"

This patch introduces "devm_kstrdup" API so that the
device's driver can allocate memory and copy string.

Signed-off-by: Manish Badarkhe <badarkhe.manish@gmail.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/base/devres.c  | 26 ++++++++++++++++++++++++++
 include/linux/device.h |  1 +
 2 files changed, 27 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/base/devres.c b/drivers/base/devres.c
index 545c4de412c3..db4e264eecb6 100644
--- a/drivers/base/devres.c
+++ b/drivers/base/devres.c
@@ -790,6 +790,32 @@ void * devm_kmalloc(struct device *dev, size_t size, gfp_t gfp)
 }
 EXPORT_SYMBOL_GPL(devm_kmalloc);
 
+/**
+ * devm_kstrdup - Allocate resource managed space and
+ *                copy an existing string into that.
+ * @dev: Device to allocate memory for
+ * @s: the string to duplicate
+ * @gfp: the GFP mask used in the devm_kmalloc() call when
+ *       allocating memory
+ * RETURNS:
+ * Pointer to allocated string on success, NULL on failure.
+ */
+char *devm_kstrdup(struct device *dev, const char *s, gfp_t gfp)
+{
+	size_t size;
+	char *buf;
+
+	if (!s)
+		return NULL;
+
+	size = strlen(s) + 1;
+	buf = devm_kmalloc(dev, size, gfp);
+	if (buf)
+		memcpy(buf, s, size);
+	return buf;
+}
+EXPORT_SYMBOL_GPL(devm_kstrdup);
+
 /**
  * devm_kfree - Resource-managed kfree
  * @dev: Device this memory belongs to
diff --git a/include/linux/device.h b/include/linux/device.h
index 952b01033c32..ec1b6e21f0ef 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -626,6 +626,7 @@ static inline void *devm_kcalloc(struct device *dev,
 	return devm_kmalloc_array(dev, n, size, flags | __GFP_ZERO);
 }
 extern void devm_kfree(struct device *dev, void *p);
+extern char *devm_kstrdup(struct device *dev, const char *s, gfp_t gfp);
 
 void __iomem *devm_ioremap_resource(struct device *dev, struct resource *res);
 void __iomem *devm_request_and_ioremap(struct device *dev,
-- 
cgit v1.2.3


From 5a17f543ed6808e9085063277fe46795dea484bd Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 11 Feb 2014 11:52:47 -0500
Subject: cgroup: improve css_from_dir() into css_tryget_from_dir()

css_from_dir() returns the matching css (cgroup_subsys_state) given a
dentry and subsystem.  The function doesn't pin the css before
returning and requires the caller to be holding RCU read lock or
cgroup_mutex and handling pinning on the caller side.

Given that users of the function are likely to want to pin the
returned css (both existing users do) and that getting and putting
css's are very cheap, there's no reason for the interface to be tricky
like this.

Rename css_from_dir() to css_tryget_from_dir() and make it try to pin
the found css and return it only if pinning succeeded.  The callers
are updated so that they no longer do RCU locking and pinning around
the function and just use the returned css.

This will also ease converting cgroup to kernfs.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
---
 include/linux/cgroup.h |  4 ++--
 kernel/cgroup.c        | 25 ++++++++++++++++---------
 kernel/events/core.c   | 17 +----------------
 mm/memcontrol.c        | 16 +++++++---------
 4 files changed, 26 insertions(+), 36 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index c86ba7ff7a7e..1ba4fc08f776 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -825,8 +825,8 @@ int css_scan_tasks(struct cgroup_subsys_state *css,
 int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
 int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
 
-struct cgroup_subsys_state *css_from_dir(struct dentry *dentry,
-					 struct cgroup_subsys *ss);
+struct cgroup_subsys_state *css_tryget_from_dir(struct dentry *dentry,
+						struct cgroup_subsys *ss);
 
 #else /* !CONFIG_CGROUPS */
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 2de8decfd99f..fc2db071d95e 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4978,28 +4978,35 @@ static int __init cgroup_disable(char *str)
 __setup("cgroup_disable=", cgroup_disable);
 
 /**
- * css_from_dir - get corresponding css from the dentry of a cgroup dir
+ * css_tryget_from_dir - get corresponding css from the dentry of a cgroup dir
  * @dentry: directory dentry of interest
  * @ss: subsystem of interest
  *
- * Must be called under cgroup_mutex or RCU read lock.  The caller is
- * responsible for pinning the returned css if it needs to be accessed
- * outside the critical section.
+ * If @dentry is a directory for a cgroup which has @ss enabled on it, try
+ * to get the corresponding css and return it.  If such css doesn't exist
+ * or can't be pinned, an ERR_PTR value is returned.
  */
-struct cgroup_subsys_state *css_from_dir(struct dentry *dentry,
-					 struct cgroup_subsys *ss)
+struct cgroup_subsys_state *css_tryget_from_dir(struct dentry *dentry,
+						struct cgroup_subsys *ss)
 {
 	struct cgroup *cgrp;
-
-	cgroup_assert_mutex_or_rcu_locked();
+	struct cgroup_subsys_state *css;
 
 	/* is @dentry a cgroup dir? */
 	if (!dentry->d_inode ||
 	    dentry->d_inode->i_op != &cgroup_dir_inode_operations)
 		return ERR_PTR(-EBADF);
 
+	rcu_read_lock();
+
 	cgrp = __d_cgrp(dentry);
-	return cgroup_css(cgrp, ss) ?: ERR_PTR(-ENOENT);
+	css = cgroup_css(cgrp, ss);
+
+	if (!css || !css_tryget(css))
+		css = ERR_PTR(-ENOENT);
+
+	rcu_read_unlock();
+	return css;
 }
 
 /**
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 64903731d834..a3c3ab50271a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -370,11 +370,6 @@ perf_cgroup_match(struct perf_event *event)
 				    event->cgrp->css.cgroup);
 }
 
-static inline bool perf_tryget_cgroup(struct perf_event *event)
-{
-	return css_tryget(&event->cgrp->css);
-}
-
 static inline void perf_put_cgroup(struct perf_event *event)
 {
 	css_put(&event->cgrp->css);
@@ -593,9 +588,7 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 	if (!f.file)
 		return -EBADF;
 
-	rcu_read_lock();
-
-	css = css_from_dir(f.file->f_dentry, &perf_event_cgrp_subsys);
+	css = css_tryget_from_dir(f.file->f_dentry, &perf_event_cgrp_subsys);
 	if (IS_ERR(css)) {
 		ret = PTR_ERR(css);
 		goto out;
@@ -604,13 +597,6 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 	cgrp = container_of(css, struct perf_cgroup, css);
 	event->cgrp = cgrp;
 
-	/* must be done before we fput() the file */
-	if (!perf_tryget_cgroup(event)) {
-		event->cgrp = NULL;
-		ret = -ENOENT;
-		goto out;
-	}
-
 	/*
 	 * all events in a group must monitor
 	 * the same cgroup because a task belongs
@@ -621,7 +607,6 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 		ret = -EINVAL;
 	}
 out:
-	rcu_read_unlock();
 	fdput(f);
 	return ret;
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 04a97bce2270..102ab48ffa13 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -6183,17 +6183,15 @@ static int memcg_write_event_control(struct cgroup_subsys_state *css,
 	 * automatically removed on cgroup destruction but the removal is
 	 * asynchronous, so take an extra ref on @css.
 	 */
-	rcu_read_lock();
-
+	cfile_css = css_tryget_from_dir(cfile.file->f_dentry->d_parent,
+					&memory_cgrp_subsys);
 	ret = -EINVAL;
-	cfile_css = css_from_dir(cfile.file->f_dentry->d_parent,
-				 &memory_cgrp_subsys);
-	if (cfile_css == css && css_tryget(css))
-		ret = 0;
-
-	rcu_read_unlock();
-	if (ret)
+	if (IS_ERR(cfile_css))
 		goto out_put_cfile;
+	if (cfile_css != css) {
+		css_put(cfile_css);
+		goto out_put_cfile;
+	}
 
 	ret = event->register_event(memcg, event->eventfd, buffer);
 	if (ret)
-- 
cgit v1.2.3


From de00ffa56ea3132c6013fc8f07133b8a1014cf53 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 11 Feb 2014 11:52:48 -0500
Subject: cgroup: make cgroup_subsys->base_cftypes use cgroup_add_cftypes()

Currently, cgroup_subsys->base_cftypes registration is different from
dynamic cftypes registartion.  Instead of going through
cgroup_add_cftypes(), cgroup_init_subsys() invokes
cgroup_init_cftsets() which makes use of cgroup_subsys->base_cftset
which doesn't involve dynamic allocation.

While avoiding dynamic allocation is somewhat nice, having two
separate paths for cftypes registration is nasty, especially as we're
planning to add more operations during cftypes registration.

This patch drops cgroup_init_cftsets() and cgroup_subsys->base_cftset
and registers base_cftypes using cgroup_add_cftypes().  This is done
as a separate step in cgroup_init() instead of a part of
cgroup_init_subsys().  This is because cgroup_init_subsys() can be
called very early during boot when kmalloc() isn't available yet.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h |  3 +--
 kernel/cgroup.c        | 29 ++++++++---------------------
 2 files changed, 9 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 1ba4fc08f776..c4350a82320b 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -604,9 +604,8 @@ struct cgroup_subsys {
 	/* list of cftype_sets */
 	struct list_head cftsets;
 
-	/* base cftypes, automatically [de]registered with subsys itself */
+	/* base cftypes, automatically registered with subsys itself */
 	struct cftype *base_cftypes;
-	struct cftype_set base_cftset;
 };
 
 #define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 3f204429d108..eb002c622cd6 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4503,25 +4503,6 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	return ret;
 }
 
-static void __init cgroup_init_cftsets(struct cgroup_subsys *ss)
-{
-	INIT_LIST_HEAD(&ss->cftsets);
-
-	/*
-	 * base_cftset is embedded in subsys itself, no need to worry about
-	 * deregistration.
-	 */
-	if (ss->base_cftypes) {
-		struct cftype *cft;
-
-		for (cft = ss->base_cftypes; cft->name[0] != '\0'; cft++)
-			cft->ss = ss;
-
-		ss->base_cftset.cfts = ss->base_cftypes;
-		list_add_tail(&ss->base_cftset.node, &ss->cftsets);
-	}
-}
-
 static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 {
 	struct cgroup_subsys_state *css;
@@ -4531,8 +4512,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	mutex_lock(&cgroup_tree_mutex);
 	mutex_lock(&cgroup_mutex);
 
-	/* init base cftset */
-	cgroup_init_cftsets(ss);
+	INIT_LIST_HEAD(&ss->cftsets);
 
 	/* Create the top cgroup state for this subsystem */
 	ss->root = &cgroup_dummy_root;
@@ -4621,6 +4601,13 @@ int __init cgroup_init(void)
 	for_each_subsys(ss, i) {
 		if (!ss->early_init)
 			cgroup_init_subsys(ss);
+
+		/*
+		 * cftype registration needs kmalloc and can't be done
+		 * during early_init.  Register base cftypes separately.
+		 */
+		if (ss->base_cftypes)
+			WARN_ON(cgroup_add_cftypes(ss, ss->base_cftypes));
 	}
 
 	/* allocate id for the dummy hierarchy */
-- 
cgit v1.2.3


From 5f46990787e2721b4db190ddc8af6fdbe8f010d7 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 11 Feb 2014 11:52:48 -0500
Subject: cgroup: update the meaning of cftype->max_write_len

cftype->max_write_len is used to extend the maximum size of writes.
It's interpreted in such a way that the actual maximum size is one
less than the specified value.  The default size is defined by
CGROUP_LOCAL_BUFFER_SIZE.  Its interpretation is quite confusing - its
value is decremented by 1 and then compared for equality with max
size, which means that the actual default size is
CGROUP_LOCAL_BUFFER_SIZE - 2, which is 62 chars.

There's no point in having a limit that low.  Update its definition so
that it means the actual string length sans termination and anything
below PAGE_SIZE-1 is treated as PAGE_SIZE-1.

.max_write_len for "release_agent" is updated to PATH_MAX-1 and
cgroup_release_agent_write() is updated so that the redundant strlen()
check is removed and it uses strlcpy() instead of strcpy().
.max_write_len initializations in blk-throttle.c and cfq-iosched.c are
no longer necessary and removed.  The one in cpuset is kept unchanged
as it's an approximated value to begin with.

This will also make transition to kernfs smoother.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 block/blk-throttle.c   |  4 ----
 block/cfq-iosched.c    |  3 ---
 include/linux/cgroup.h |  5 +++--
 kernel/cgroup.c        | 18 ++++++++----------
 4 files changed, 11 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 1474c3ab7e72..861c363e4129 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -1425,28 +1425,24 @@ static struct cftype throtl_files[] = {
 		.private = offsetof(struct throtl_grp, bps[READ]),
 		.seq_show = tg_print_conf_u64,
 		.write_string = tg_set_conf_u64,
-		.max_write_len = 256,
 	},
 	{
 		.name = "throttle.write_bps_device",
 		.private = offsetof(struct throtl_grp, bps[WRITE]),
 		.seq_show = tg_print_conf_u64,
 		.write_string = tg_set_conf_u64,
-		.max_write_len = 256,
 	},
 	{
 		.name = "throttle.read_iops_device",
 		.private = offsetof(struct throtl_grp, iops[READ]),
 		.seq_show = tg_print_conf_uint,
 		.write_string = tg_set_conf_uint,
-		.max_write_len = 256,
 	},
 	{
 		.name = "throttle.write_iops_device",
 		.private = offsetof(struct throtl_grp, iops[WRITE]),
 		.seq_show = tg_print_conf_uint,
 		.write_string = tg_set_conf_uint,
-		.max_write_len = 256,
 	},
 	{
 		.name = "throttle.io_service_bytes",
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 744833b630c6..461187943392 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1838,7 +1838,6 @@ static struct cftype cfq_blkcg_files[] = {
 		.flags = CFTYPE_ONLY_ON_ROOT,
 		.seq_show = cfqg_print_leaf_weight_device,
 		.write_string = cfqg_set_leaf_weight_device,
-		.max_write_len = 256,
 	},
 	{
 		.name = "weight",
@@ -1853,7 +1852,6 @@ static struct cftype cfq_blkcg_files[] = {
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.seq_show = cfqg_print_weight_device,
 		.write_string = cfqg_set_weight_device,
-		.max_write_len = 256,
 	},
 	{
 		.name = "weight",
@@ -1866,7 +1864,6 @@ static struct cftype cfq_blkcg_files[] = {
 		.name = "leaf_weight_device",
 		.seq_show = cfqg_print_leaf_weight_device,
 		.write_string = cfqg_set_leaf_weight_device,
-		.max_write_len = 256,
 	},
 	{
 		.name = "leaf_weight",
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index c4350a82320b..63feaed83bc6 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -400,8 +400,9 @@ struct cftype {
 	umode_t mode;
 
 	/*
-	 * If non-zero, defines the maximum length of string that can
-	 * be passed to write_string; defaults to 64
+	 * The maximum length of string, excluding trailing nul, that can
+	 * be passed to write_string.  If < PAGE_SIZE-1, PAGE_SIZE-1 is
+	 * assumed.
 	 */
 	size_t max_write_len;
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index eb002c622cd6..fde3633ef389 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2213,13 +2213,14 @@ static int cgroup_procs_write(struct cgroup_subsys_state *css,
 static int cgroup_release_agent_write(struct cgroup_subsys_state *css,
 				      struct cftype *cft, const char *buffer)
 {
-	BUILD_BUG_ON(sizeof(css->cgroup->root->release_agent_path) < PATH_MAX);
-	if (strlen(buffer) >= PATH_MAX)
-		return -EINVAL;
+	struct cgroupfs_root *root = css->cgroup->root;
+
+	BUILD_BUG_ON(sizeof(root->release_agent_path) < PATH_MAX);
 	if (!cgroup_lock_live_group(css->cgroup))
 		return -ENODEV;
 	spin_lock(&release_agent_path_lock);
-	strcpy(css->cgroup->root->release_agent_path, buffer);
+	strlcpy(root->release_agent_path, buffer,
+		sizeof(root->release_agent_path));
 	spin_unlock(&release_agent_path_lock);
 	mutex_unlock(&cgroup_mutex);
 	return 0;
@@ -2245,20 +2246,17 @@ static int cgroup_sane_behavior_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-/* A buffer size big enough for numbers or short strings */
-#define CGROUP_LOCAL_BUFFER_SIZE 64
-
 static ssize_t cgroup_file_write(struct file *file, const char __user *userbuf,
 				 size_t nbytes, loff_t *ppos)
 {
 	struct cfent *cfe = __d_cfe(file->f_dentry);
 	struct cftype *cft = __d_cft(file->f_dentry);
 	struct cgroup_subsys_state *css = cfe->css;
-	size_t max_bytes = cft->max_write_len ?: CGROUP_LOCAL_BUFFER_SIZE - 1;
+	size_t max_bytes = max(cft->max_write_len, PAGE_SIZE);
 	char *buf;
 	int ret;
 
-	if (nbytes >= max_bytes)
+	if (nbytes > max_bytes)
 		return -E2BIG;
 
 	buf = kmalloc(nbytes + 1, GFP_KERNEL);
@@ -3919,7 +3917,7 @@ static struct cftype cgroup_base_files[] = {
 		.flags = CFTYPE_INSANE | CFTYPE_ONLY_ON_ROOT,
 		.seq_show = cgroup_release_agent_show,
 		.write_string = cgroup_release_agent_write,
-		.max_write_len = PATH_MAX,
+		.max_write_len = PATH_MAX - 1,
 	},
 	{ }	/* terminate */
 };
-- 
cgit v1.2.3


From b1664924062393bb048203bd4622e0b1c9e1d328 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 11 Feb 2014 11:52:49 -0500
Subject: cgroup: introduce cgroup_ino()

mm/memory-failure.c::hwpoison_filter_task() has been reaching into
cgroup to extract the associated ino to be used as a filtering
criterion.  This is an implementation detail which shouldn't be
depended upon from outside cgroup proper and is about to change with
the scheduled kernfs conversion.

This patch introduces a proper interface to determine the associated
ino, cgroup_ino(), and updates hwpoison_filter_task() to use it
instead of reaching directly into cgroup.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Wu Fengguang <fengguang.wu@intel.com>
---
 include/linux/cgroup.h | 9 +++++++++
 kernel/cgroup.c        | 5 ++++-
 mm/memory-failure.c    | 8 ++------
 3 files changed, 15 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 63feaed83bc6..06f577764414 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -507,6 +507,15 @@ static inline const char *cgroup_name(const struct cgroup *cgrp)
 	return rcu_dereference(cgrp->name)->name;
 }
 
+/* returns ino associated with a cgroup, 0 indicates unmounted root */
+static inline ino_t cgroup_ino(struct cgroup *cgrp)
+{
+	if (cgrp->dentry)
+		return cgrp->dentry->d_inode->i_ino;
+	else
+		return 0;
+}
+
 static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq)
 {
 	struct cgroup_open_file *of = seq->private;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 42e588ef62d1..11f7a05e791e 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -792,7 +792,10 @@ static struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb)
 	struct inode *inode = new_inode(sb);
 
 	if (inode) {
-		inode->i_ino = get_next_ino();
+		do {
+			/* ino 0 is reserved for dummy_root */
+			inode->i_ino = get_next_ino();
+		} while (!inode->i_ino);
 		inode->i_mode = mode;
 		inode->i_uid = current_fsuid();
 		inode->i_gid = current_fsgid();
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 4f08a2d61487..9b5933c66c16 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -145,14 +145,10 @@ static int hwpoison_filter_task(struct page *p)
 		return -EINVAL;
 
 	css = mem_cgroup_css(mem);
-	/* root_mem_cgroup has NULL dentries */
-	if (!css->cgroup->dentry)
-		return -EINVAL;
-
-	ino = css->cgroup->dentry->d_inode->i_ino;
+	ino = cgroup_ino(css->cgroup);
 	css_put(css);
 
-	if (ino != hwpoison_filter_memcg)
+	if (!ino || ino != hwpoison_filter_memcg)
 		return -EINVAL;
 
 	return 0;
-- 
cgit v1.2.3


From 59f5296b51b86718dd6eecf0a268b2f1a1ec0a2d Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 11 Feb 2014 11:52:49 -0500
Subject: cgroup: misc preps for kernfs conversion

* Un-inline seq_css().  After kernfs conversion, the function will
  need to dereference internal data structures.

* Add cgroup_get/put_root() and replace direct super_block->s_active
  manipulatinos with them.  These will be converted to kernfs_root
  refcnting.

* Add cgroup_get/put() and replace dget/put() on cgrp->dentry with
  them.  These will be converted to kernfs refcnting.

* Update current_css_set_cg_links_read() to use cgroup_name() instead
  of reaching into the dentry name.  The end result is the same.

These changes don't make functional differences but will make
transition to kernfs easier.

v2: Rebased on top of 0ab02ca8f887 ("cgroup: protect modifications to
    cgroup_idr with cgroup_mutex").

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h |  8 ++---
 kernel/cgroup.c        | 85 +++++++++++++++++++++++++++++++-------------------
 2 files changed, 55 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 06f577764414..523277871913 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -516,18 +516,14 @@ static inline ino_t cgroup_ino(struct cgroup *cgrp)
 		return 0;
 }
 
-static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq)
-{
-	struct cgroup_open_file *of = seq->private;
-	return of->cfe->css;
-}
-
 static inline struct cftype *seq_cft(struct seq_file *seq)
 {
 	struct cgroup_open_file *of = seq->private;
 	return of->cfe->type;
 }
 
+struct cgroup_subsys_state *seq_css(struct seq_file *seq);
+
 int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
 int cgroup_rm_cftypes(struct cftype *cfts);
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 11f7a05e791e..9e9e8fd632d8 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -169,6 +169,7 @@ static int need_forkexit_callback __read_mostly;
 
 static struct cftype cgroup_base_files[];
 
+static void cgroup_put(struct cgroup *cgrp);
 static void cgroup_destroy_css_killed(struct cgroup *cgrp);
 static int cgroup_destroy_locked(struct cgroup *cgrp);
 static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
@@ -204,6 +205,13 @@ static inline bool cgroup_is_dead(const struct cgroup *cgrp)
 	return test_bit(CGRP_DEAD, &cgrp->flags);
 }
 
+struct cgroup_subsys_state *seq_css(struct seq_file *seq)
+{
+	struct cgroup_open_file *of = seq->private;
+	return of->cfe->css;
+}
+EXPORT_SYMBOL_GPL(seq_css);
+
 /**
  * cgroup_is_descendant - test ancestry
  * @cgrp: the cgroup to be tested
@@ -682,6 +690,16 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 	return cset;
 }
 
+static void cgroup_get_root(struct cgroupfs_root *root)
+{
+	atomic_inc(&root->sb->s_active);
+}
+
+static void cgroup_put_root(struct cgroupfs_root *root)
+{
+	deactivate_super(root->sb);
+}
+
 /*
  * Return the cgroup for "task" from the given hierarchy. Must be
  * called with cgroup_mutex held.
@@ -837,18 +855,14 @@ static void cgroup_free_fn(struct work_struct *work)
 	mutex_unlock(&cgroup_mutex);
 
 	/*
-	 * We get a ref to the parent's dentry, and put the ref when
-	 * this cgroup is being freed, so it's guaranteed that the
-	 * parent won't be destroyed before its children.
+	 * We get a ref to the parent, and put the ref when this cgroup is
+	 * being freed, so it's guaranteed that the parent won't be
+	 * destroyed before its children.
 	 */
-	dput(cgrp->parent->dentry);
+	cgroup_put(cgrp->parent);
 
-	/*
-	 * Drop the active superblock reference that we took when we
-	 * created the cgroup. This will free cgrp->root, if we are
-	 * holding the last reference to @sb.
-	 */
-	deactivate_super(cgrp->root->sb);
+	/* put the root reference that we took when we created the cgroup */
+	cgroup_put_root(cgrp->root);
 
 	cgroup_pidlist_destroy_all(cgrp);
 
@@ -866,6 +880,11 @@ static void cgroup_free_rcu(struct rcu_head *head)
 	queue_work(cgroup_destroy_wq, &cgrp->destroy_work);
 }
 
+static void cgroup_get(struct cgroup *cgrp)
+{
+	dget(cgrp->dentry);
+}
+
 static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 {
 	/* is dentry a directory ? if so, kfree() associated cgroup */
@@ -899,6 +918,11 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode)
 	iput(inode);
 }
 
+static void cgroup_put(struct cgroup *cgrp)
+{
+	dput(cgrp->dentry);
+}
+
 static void remove_dir(struct dentry *d)
 {
 	struct dentry *parent = dget(d->d_parent);
@@ -2724,7 +2748,7 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add)
 	struct cgroup_subsys *ss = cfts[0].ss;
 	struct cgroup *root = &ss->root->top_cgroup;
 	struct super_block *sb = ss->root->sb;
-	struct dentry *prev = NULL;
+	struct cgroup *prev = NULL;
 	struct inode *inode;
 	struct cgroup_subsys_state *css;
 	u64 update_before;
@@ -2754,9 +2778,10 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add)
 			continue;
 
 		inode = cgrp->dentry->d_inode;
-		dget(cgrp->dentry);
-		dput(prev);
-		prev = cgrp->dentry;
+		cgroup_get(cgrp);
+		if (prev)
+			cgroup_put(prev);
+		prev = cgrp;
 
 		mutex_unlock(&cgroup_tree_mutex);
 		mutex_lock(&inode->i_mutex);
@@ -2768,8 +2793,8 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add)
 			break;
 	}
 	mutex_unlock(&cgroup_tree_mutex);
-	dput(prev);
-	deactivate_super(sb);
+	cgroup_put(prev);
+	cgroup_put_root(ss->root);
 	return ret;
 }
 
@@ -3863,11 +3888,9 @@ static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css,
  */
 static void cgroup_dput(struct cgroup *cgrp)
 {
-	struct super_block *sb = cgrp->root->sb;
-
-	atomic_inc(&sb->s_active);
-	dput(cgrp->dentry);
-	deactivate_super(sb);
+	cgroup_get_root(cgrp->root);
+	cgroup_put(cgrp);
+	cgroup_put_root(cgrp->root);
 }
 
 static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css,
@@ -4118,7 +4141,7 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss)
 	if (err)
 		goto err_free;
 
-	dget(cgrp->dentry);
+	cgroup_get(cgrp);
 	css_get(css->parent);
 
 	if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
@@ -4197,7 +4220,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	 * can be done outside cgroup_mutex, since the sb can't
 	 * disappear while someone has an open control file on the
 	 * fs */
-	atomic_inc(&sb->s_active);
+	cgroup_get_root(root);
 
 	init_cgroup_housekeeping(cgrp);
 
@@ -4231,7 +4254,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	root->number_of_cgroups++;
 
 	/* hold a ref to the parent's dentry */
-	dget(parent->dentry);
+	cgroup_get(parent);
 
 	/*
 	 * @cgrp is now fully operational.  If something fails after this
@@ -4261,7 +4284,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 err_free_id:
 	idr_remove(&root->cgroup_idr, cgrp->id);
 	/* Release the reference count that we took on the superblock */
-	deactivate_super(sb);
+	cgroup_put_root(root);
 err_unlock:
 	mutex_unlock(&cgroup_mutex);
 err_unlock_tree:
@@ -4493,7 +4516,6 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 static void cgroup_destroy_css_killed(struct cgroup *cgrp)
 {
 	struct cgroup *parent = cgrp->parent;
-	struct dentry *d = cgrp->dentry;
 
 	lockdep_assert_held(&cgroup_tree_mutex);
 	lockdep_assert_held(&cgroup_mutex);
@@ -4501,7 +4523,7 @@ static void cgroup_destroy_css_killed(struct cgroup *cgrp)
 	/* delete this cgroup from parent->children */
 	list_del_rcu(&cgrp->sibling);
 
-	dput(d);
+	cgroup_put(cgrp);
 
 	set_bit(CGRP_RELEASABLE, &parent->flags);
 	check_for_release(parent);
@@ -5161,12 +5183,11 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
 	cset = rcu_dereference(current->cgroups);
 	list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
 		struct cgroup *c = link->cgrp;
-		const char *name;
+		const char *name = "?";
+
+		if (c != cgroup_dummy_top)
+			name = cgroup_name(c);
 
-		if (c->dentry)
-			name = c->dentry->d_name.name;
-		else
-			name = "?";
 		seq_printf(seq, "Root %d group %s\n",
 			   c->root->hierarchy_id, name);
 	}
-- 
cgit v1.2.3


From 2bd59d48ebfb3df41ee56938946ca0dd30887312 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 11 Feb 2014 11:52:49 -0500
Subject: cgroup: convert to kernfs

cgroup filesystem code was derived from the original sysfs
implementation which was heavily intertwined with vfs objects and
locking with the goal of re-using the existing vfs infrastructure.
That experiment turned out rather disastrous and sysfs switched, a
long time ago, to distributed filesystem model where a separate
representation is maintained which is queried by vfs.  Unfortunately,
cgroup stuck with the failed experiment all these years and
accumulated even more problems over time.

Locking and object lifetime management being entangled with vfs is
probably the most egregious.  vfs is never designed to be misused like
this and cgroup ends up jumping through various convoluted dancing to
make things work.  Even then, operations across multiple cgroups can't
be done safely as it'll deadlock with rename locking.

Recently, kernfs is separated out from sysfs so that it can be used by
users other than sysfs.  This patch converts cgroup to use kernfs,
which will bring the following benefits.

* Separation from vfs internals.  Locking and object lifetime
  management is contained in cgroup proper making things a lot
  simpler.  This removes significant amount of locking convolutions,
  hairy object lifetime rules and the restriction on multi-cgroup
  operations.

* Can drop a lot of code to implement filesystem interface as most are
  provided by kernfs.

* Proper "severing" semantics, which allows controllers to not worry
  about lingering file accesses after offline.

While the preceding patches did as much as possible to make the
transition less painful, large part of the conversion has to be one
discrete step making this patch rather large.  The rest of the commit
message lists notable changes in different areas.

Overall
-------

* vfs constructs replaced with kernfs ones.  cgroup->dentry w/ ->kn,
  cgroupfs_root->sb w/ ->kf_root.

* All dentry accessors are removed.  Helpers to map from kernfs
  constructs are added.

* All vfs plumbing around dentry, inode and bdi removed.

* cgroup_mount() now directly looks for matching root and then
  proceeds to create a new one if not found.

Synchronization and object lifetime
-----------------------------------

* vfs inode locking removed.  Among other things, this removes the
  need for the convolution in cgroup_cfts_commit().  Future patches
  will further simplify it.

* vfs refcnting replaced with cgroup internal ones.  cgroup->refcnt,
  cgroupfs_root->refcnt added.  cgroup_put_root() now directly puts
  root->refcnt and when it reaches zero proceeds to destroy it thus
  merging cgroup_put_root() and the former cgroup_kill_sb().
  Simliarly, cgroup_put() now directly schedules cgroup_free_rcu()
  when refcnt reaches zero.

* Unlike before, kernfs objects don't hold onto cgroup objects.  When
  cgroup destroys a kernfs node, all existing operations are drained
  and the association is broken immediately.  The same for
  cgroupfs_roots and mounts.

* All operations which come through kernfs guarantee that the
  associated cgroup is and stays valid for the duration of operation;
  however, there are two paths which need to find out the associated
  cgroup from dentry without going through kernfs -
  css_tryget_from_dir() and cgroupstats_build().  For these two,
  kernfs_node->priv is RCU managed so that they can dereference it
  under RCU read lock.

File and directory handling
---------------------------

* File and directory operations converted to kernfs_ops and
  kernfs_syscall_ops.

* xattrs is implicitly supported by kernfs.  No need to worry about it
  from cgroup.  This means that "xattr" mount option is no longer
  necessary.  A future patch will add a deprecated warning message
  when sane_behavior.

* When cftype->max_write_len > PAGE_SIZE, it's necessary to make a
  private copy of one of the kernfs_ops to set its atomic_write_len.
  cftype->kf_ops is added and cgroup_init/exit_cftypes() are updated
  to handle it.

* cftype->lockdep_key added so that kernfs lockdep annotation can be
  per cftype.

* Inidividual file entries and open states are now managed by kernfs.
  No need to worry about them from cgroup.  cfent, cgroup_open_file
  and their friends are removed.

* kernfs_nodes are created deactivated and kernfs_activate()
  invocations added to places where creation of new nodes are
  committed.

* cgroup_rmdir() uses kernfs_[un]break_active_protection() for
  self-removal.

v2: - Li pointed out in an earlier patch that specifying "name="
      during mount without subsystem specification should succeed if
      there's an existing hierarchy with a matching name although it
      should fail with -EINVAL if a new hierarchy should be created.
      Prior to the conversion, this used by handled by deferring
      failure from NULL return from cgroup_root_from_opts(), which was
      necessary because root was being created before checking for
      existing ones.  Note that cgroup_root_from_opts() returned an
      ERR_PTR() value for error conditions which require immediate
      mount failure.

      As we now have separate search and creation steps, deferring
      failure from cgroup_root_from_opts() is no longer necessary.
      cgroup_root_from_opts() is updated to always return ERR_PTR()
      value on failure.

    - The logic to match existing roots is updated so that a mount
      attempt with a matching name but different subsys_mask are
      rejected.  This was handled by a separate matching loop under
      the comment "Check for name clashes with existing mounts" but
      got lost during conversion.  Merge the check into the main
      search loop.

    - Add __rcu __force casting in RCU_INIT_POINTER() in
      cgroup_destroy_locked() to avoid the sparse address space
      warning reported by kbuild test bot.  Maybe we want an explicit
      interface to use kn->priv as RCU protected pointer?

v3: Make CONFIG_CGROUPS select CONFIG_KERNFS.

v4: Rebased on top of 0ab02ca8f887 ("cgroup: protect modifications to
    cgroup_idr with cgroup_mutex").

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: kbuild test robot fengguang.wu@intel.com>
---
 include/linux/cgroup.h |   52 +--
 init/Kconfig           |    1 +
 kernel/cgroup.c        | 1115 ++++++++++++++++--------------------------------
 3 files changed, 383 insertions(+), 785 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 523277871913..0e45a932b823 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -18,10 +18,10 @@
 #include <linux/rwsem.h>
 #include <linux/idr.h>
 #include <linux/workqueue.h>
-#include <linux/xattr.h>
 #include <linux/fs.h>
 #include <linux/percpu-refcount.h>
 #include <linux/seq_file.h>
+#include <linux/kernfs.h>
 
 #ifdef CONFIG_CGROUPS
 
@@ -159,16 +159,17 @@ struct cgroup {
 	/* the number of attached css's */
 	int nr_css;
 
+	atomic_t refcnt;
+
 	/*
 	 * We link our 'sibling' struct into our parent's 'children'.
 	 * Our children link their 'sibling' into our 'children'.
 	 */
 	struct list_head sibling;	/* my parent's children */
 	struct list_head children;	/* my children */
-	struct list_head files;		/* my files */
 
 	struct cgroup *parent;		/* my parent */
-	struct dentry *dentry;		/* cgroup fs entry, RCU protected */
+	struct kernfs_node *kn;		/* cgroup kernfs entry */
 
 	/*
 	 * Monotonically increasing unique serial number which defines a
@@ -222,9 +223,6 @@ struct cgroup {
 	/* For css percpu_ref killing and RCU-protected deletion */
 	struct rcu_head rcu_head;
 	struct work_struct destroy_work;
-
-	/* directory xattrs */
-	struct simple_xattrs xattrs;
 };
 
 #define MAX_CGROUP_ROOT_NAMELEN 64
@@ -291,15 +289,17 @@ enum {
 
 /*
  * A cgroupfs_root represents the root of a cgroup hierarchy, and may be
- * associated with a superblock to form an active hierarchy.  This is
+ * associated with a kernfs_root to form an active hierarchy.  This is
  * internal to cgroup core.  Don't access directly from controllers.
  */
 struct cgroupfs_root {
-	struct super_block *sb;
+	struct kernfs_root *kf_root;
 
 	/* The bitmask of subsystems attached to this hierarchy */
 	unsigned long subsys_mask;
 
+	atomic_t refcnt;
+
 	/* Unique id for this hierarchy. */
 	int hierarchy_id;
 
@@ -415,6 +415,9 @@ struct cftype {
 	 */
 	struct cgroup_subsys *ss;
 
+	/* kernfs_ops to use, initialized automatically during registration */
+	struct kernfs_ops *kf_ops;
+
 	/*
 	 * read_u64() is a shortcut for the common case of returning a
 	 * single integer. Use it in place of read()
@@ -460,6 +463,10 @@ struct cftype {
 	 * kick type for multiplexing.
 	 */
 	int (*trigger)(struct cgroup_subsys_state *css, unsigned int event);
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lock_class_key	lockdep_key;
+#endif
 };
 
 /*
@@ -472,26 +479,6 @@ struct cftype_set {
 	struct cftype			*cfts;
 };
 
-/*
- * cgroupfs file entry, pointed to from leaf dentry->d_fsdata.  Don't
- * access directly.
- */
-struct cfent {
-	struct list_head		node;
-	struct dentry			*dentry;
-	struct cftype			*type;
-	struct cgroup_subsys_state	*css;
-
-	/* file xattrs */
-	struct simple_xattrs		xattrs;
-};
-
-/* seq_file->private points to the following, only ->priv is public */
-struct cgroup_open_file {
-	struct cfent			*cfe;
-	void				*priv;
-};
-
 /*
  * See the comment above CGRP_ROOT_SANE_BEHAVIOR for details.  This
  * function can be called as long as @cgrp is accessible.
@@ -510,16 +497,17 @@ static inline const char *cgroup_name(const struct cgroup *cgrp)
 /* returns ino associated with a cgroup, 0 indicates unmounted root */
 static inline ino_t cgroup_ino(struct cgroup *cgrp)
 {
-	if (cgrp->dentry)
-		return cgrp->dentry->d_inode->i_ino;
+	if (cgrp->kn)
+		return cgrp->kn->ino;
 	else
 		return 0;
 }
 
 static inline struct cftype *seq_cft(struct seq_file *seq)
 {
-	struct cgroup_open_file *of = seq->private;
-	return of->cfe->type;
+	struct kernfs_open_file *of = seq->private;
+
+	return of->kn->priv;
 }
 
 struct cgroup_subsys_state *seq_css(struct seq_file *seq);
diff --git a/init/Kconfig b/init/Kconfig
index 009a797dd242..3f74784560a5 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -854,6 +854,7 @@ config NUMA_BALANCING
 
 menuconfig CGROUPS
 	boolean "Control Group support"
+	select KERNFS
 	help
 	  This option adds support for grouping sets of processes together, for
 	  use with process control subsystems such as Cpusets, CFS, memory
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index d8efca44de5f..cda614da40cf 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -40,9 +40,7 @@
 #include <linux/proc_fs.h>
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
-#include <linux/backing-dev.h>
 #include <linux/slab.h>
-#include <linux/magic.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
 #include <linux/sort.h>
@@ -50,7 +48,6 @@
 #include <linux/delayacct.h>
 #include <linux/cgroupstats.h>
 #include <linux/hashtable.h>
-#include <linux/namei.h>
 #include <linux/pid_namespace.h>
 #include <linux/idr.h>
 #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
@@ -176,7 +173,6 @@ static void cgroup_destroy_css_killed(struct cgroup *cgrp);
 static int cgroup_destroy_locked(struct cgroup *cgrp);
 static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
 			      bool is_add);
-static int cgroup_file_release(struct inode *inode, struct file *file);
 static void cgroup_pidlist_destroy_all(struct cgroup *cgrp);
 
 /**
@@ -209,8 +205,22 @@ static inline bool cgroup_is_dead(const struct cgroup *cgrp)
 
 struct cgroup_subsys_state *seq_css(struct seq_file *seq)
 {
-	struct cgroup_open_file *of = seq->private;
-	return of->cfe->css;
+	struct kernfs_open_file *of = seq->private;
+	struct cgroup *cgrp = of->kn->parent->priv;
+	struct cftype *cft = seq_cft(seq);
+
+	/*
+	 * This is open and unprotected implementation of cgroup_css().
+	 * seq_css() is only called from a kernfs file operation which has
+	 * an active reference on the file.  Because all the subsystem
+	 * files are drained before a css is disassociated with a cgroup,
+	 * the matching css from the cgroup's subsys table is guaranteed to
+	 * be and stay valid until the enclosing operation is complete.
+	 */
+	if (cft->ss)
+		return rcu_dereference_raw(cgrp->subsys[cft->ss->id]);
+	else
+		return &cgrp->dummy_css;
 }
 EXPORT_SYMBOL_GPL(seq_css);
 
@@ -276,21 +286,6 @@ static int notify_on_release(const struct cgroup *cgrp)
 #define for_each_active_root(root)					\
 	list_for_each_entry((root), &cgroup_roots, root_list)
 
-static inline struct cgroup *__d_cgrp(struct dentry *dentry)
-{
-	return dentry->d_fsdata;
-}
-
-static inline struct cfent *__d_cfe(struct dentry *dentry)
-{
-	return dentry->d_fsdata;
-}
-
-static inline struct cftype *__d_cft(struct dentry *dentry)
-{
-	return __d_cfe(dentry)->type;
-}
-
 /**
  * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
  * @cgrp: the cgroup to be checked for liveness
@@ -692,6 +687,13 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 	return cset;
 }
 
+static struct cgroupfs_root *cgroup_root_from_kf(struct kernfs_root *kf_root)
+{
+	struct cgroup *top_cgrp = kf_root->kn->priv;
+
+	return top_cgrp->root;
+}
+
 static int cgroup_init_root_id(struct cgroupfs_root *root, int start, int end)
 {
 	int id;
@@ -730,30 +732,37 @@ static void cgroup_free_root(struct cgroupfs_root *root)
 
 static void cgroup_get_root(struct cgroupfs_root *root)
 {
-	atomic_inc(&root->sb->s_active);
+	/*
+	 * The caller must ensure that @root is alive, which can be
+	 * achieved by holding a ref on one of the member cgroups or
+	 * following a registered reference to @root while holding
+	 * cgroup_tree_mutex.
+	 */
+	WARN_ON_ONCE(atomic_read(&root->refcnt) <= 0);
+	atomic_inc(&root->refcnt);
 }
 
 static void cgroup_put_root(struct cgroupfs_root *root)
 {
-	deactivate_super(root->sb);
-}
-
-static void cgroup_kill_sb(struct super_block *sb)
-{
-	struct cgroupfs_root *root = sb->s_fs_info;
 	struct cgroup *cgrp = &root->top_cgroup;
 	struct cgrp_cset_link *link, *tmp_link;
 	int ret;
 
-	BUG_ON(!root);
+	/*
+	 * @root's refcnt reaching zero and its deregistration should be
+	 * atomic w.r.t. cgroup_tree_mutex.  This ensures that
+	 * cgroup_get_root() is safe to invoke if @root is registered.
+	 */
+	mutex_lock(&cgroup_tree_mutex);
+	if (!atomic_dec_and_test(&root->refcnt)) {
+		mutex_unlock(&cgroup_tree_mutex);
+		return;
+	}
+	mutex_lock(&cgroup_mutex);
 
 	BUG_ON(root->number_of_cgroups != 1);
 	BUG_ON(!list_empty(&cgrp->children));
 
-	mutex_lock(&cgrp->dentry->d_inode->i_mutex);
-	mutex_lock(&cgroup_tree_mutex);
-	mutex_lock(&cgroup_mutex);
-
 	/* Rebind all subsystems back to the default hierarchy */
 	if (root->flags & CGRP_ROOT_SUBSYS_BOUND) {
 		ret = rebind_subsystems(root, 0, root->subsys_mask);
@@ -783,11 +792,8 @@ static void cgroup_kill_sb(struct super_block *sb)
 
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&cgroup_tree_mutex);
-	mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
-
-	simple_xattrs_free(&cgrp->xattrs);
 
-	kill_litter_super(sb);
+	kernfs_destroy_root(root->kf_root);
 	cgroup_free_root(root);
 }
 
@@ -878,42 +884,10 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task,
  * update of a tasks cgroup pointer by cgroup_attach_task()
  */
 
-/*
- * A couple of forward declarations required, due to cyclic reference loop:
- * cgroup_mkdir -> cgroup_create -> cgroup_populate_dir ->
- * cgroup_add_file -> cgroup_create_file -> cgroup_dir_inode_operations
- * -> cgroup_mkdir.
- */
-
-static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode);
-static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
 static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask);
-static const struct inode_operations cgroup_dir_inode_operations;
+static struct kernfs_syscall_ops cgroup_kf_syscall_ops;
 static const struct file_operations proc_cgroupstats_operations;
 
-static struct backing_dev_info cgroup_backing_dev_info = {
-	.name		= "cgroup",
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
-};
-
-static struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb)
-{
-	struct inode *inode = new_inode(sb);
-
-	if (inode) {
-		do {
-			/* ino 0 is reserved for dummy_root */
-			inode->i_ino = get_next_ino();
-		} while (!inode->i_ino);
-		inode->i_mode = mode;
-		inode->i_uid = current_fsuid();
-		inode->i_gid = current_fsgid();
-		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-		inode->i_mapping->backing_dev_info = &cgroup_backing_dev_info;
-	}
-	return inode;
-}
-
 static struct cgroup_name *cgroup_alloc_name(const char *name_str)
 {
 	struct cgroup_name *name;
@@ -983,8 +957,6 @@ static void cgroup_free_fn(struct work_struct *work)
 
 	cgroup_pidlist_destroy_all(cgrp);
 
-	simple_xattrs_free(&cgrp->xattrs);
-
 	kfree(rcu_dereference_raw(cgrp->name));
 	kfree(cgrp);
 }
@@ -999,81 +971,38 @@ static void cgroup_free_rcu(struct rcu_head *head)
 
 static void cgroup_get(struct cgroup *cgrp)
 {
-	dget(cgrp->dentry);
-}
-
-static void cgroup_diput(struct dentry *dentry, struct inode *inode)
-{
-	/* is dentry a directory ? if so, kfree() associated cgroup */
-	if (S_ISDIR(inode->i_mode)) {
-		struct cgroup *cgrp = dentry->d_fsdata;
-
-		BUG_ON(!(cgroup_is_dead(cgrp)));
-
-		/*
-		 * XXX: cgrp->id is only used to look up css's.  As cgroup
-		 * and css's lifetimes will be decoupled, it should be made
-		 * per-subsystem and moved to css->id so that lookups are
-		 * successful until the target css is released.
-		 */
-		mutex_lock(&cgroup_mutex);
-		idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
-		mutex_unlock(&cgroup_mutex);
-		cgrp->id = -1;
-
-		call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
-	} else {
-		struct cfent *cfe = __d_cfe(dentry);
-		struct cgroup *cgrp = dentry->d_parent->d_fsdata;
-
-		WARN_ONCE(!list_empty(&cfe->node) &&
-			  cgrp != &cgrp->root->top_cgroup,
-			  "cfe still linked for %s\n", cfe->type->name);
-		simple_xattrs_free(&cfe->xattrs);
-		kfree(cfe);
-	}
-	iput(inode);
+	WARN_ON_ONCE(cgroup_is_dead(cgrp));
+	WARN_ON_ONCE(atomic_read(&cgrp->refcnt) <= 0);
+	atomic_inc(&cgrp->refcnt);
 }
 
 static void cgroup_put(struct cgroup *cgrp)
 {
-	dput(cgrp->dentry);
-}
+	if (!atomic_dec_and_test(&cgrp->refcnt))
+		return;
+	if (WARN_ON_ONCE(!cgroup_is_dead(cgrp)))
+		return;
 
-static void remove_dir(struct dentry *d)
-{
-	struct dentry *parent = dget(d->d_parent);
+	/*
+	 * XXX: cgrp->id is only used to look up css's.  As cgroup and
+	 * css's lifetimes will be decoupled, it should be made
+	 * per-subsystem and moved to css->id so that lookups are
+	 * successful until the target css is released.
+	 */
+	mutex_lock(&cgroup_mutex);
+	idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
+	mutex_unlock(&cgroup_mutex);
+	cgrp->id = -1;
 
-	d_delete(d);
-	simple_rmdir(parent->d_inode, d);
-	dput(parent);
+	call_rcu(&cgrp->rcu_head, cgroup_free_rcu);
 }
 
 static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
 {
-	struct cfent *cfe;
+	char name[CGROUP_FILE_NAME_MAX];
 
-	lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex);
 	lockdep_assert_held(&cgroup_tree_mutex);
-
-	/*
-	 * If we're doing cleanup due to failure of cgroup_create(),
-	 * the corresponding @cfe may not exist.
-	 */
-	list_for_each_entry(cfe, &cgrp->files, node) {
-		struct dentry *d = cfe->dentry;
-
-		if (cft && cfe->type != cft)
-			continue;
-
-		dget(d);
-		d_delete(d);
-		simple_unlink(cgrp->dentry->d_inode, d);
-		list_del_init(&cfe->node);
-		dput(d);
-
-		break;
-	}
+	kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name));
 }
 
 /**
@@ -1096,22 +1025,6 @@ static void cgroup_clear_dir(struct cgroup *cgrp, unsigned long subsys_mask)
 	}
 }
 
-/*
- * NOTE : the dentry must have been dget()'ed
- */
-static void cgroup_d_remove_dir(struct dentry *dentry)
-{
-	struct dentry *parent;
-
-	parent = dentry->d_parent;
-	spin_lock(&parent->d_lock);
-	spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
-	list_del_init(&dentry->d_u.d_child);
-	spin_unlock(&dentry->d_lock);
-	spin_unlock(&parent->d_lock);
-	remove_dir(dentry);
-}
-
 static int rebind_subsystems(struct cgroupfs_root *root,
 			     unsigned long added_mask, unsigned removed_mask)
 {
@@ -1179,13 +1092,15 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 	 * now matches the bound subsystems.
 	 */
 	root->flags |= CGRP_ROOT_SUBSYS_BOUND;
+	kernfs_activate(cgrp->kn);
 
 	return 0;
 }
 
-static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry)
+static int cgroup_show_options(struct seq_file *seq,
+			       struct kernfs_root *kf_root)
 {
-	struct cgroupfs_root *root = dentry->d_sb->s_fs_info;
+	struct cgroupfs_root *root = cgroup_root_from_kf(kf_root);
 	struct cgroup_subsys *ss;
 	int ssid;
 
@@ -1219,9 +1134,6 @@ struct cgroup_sb_opts {
 	char *name;
 	/* User explicitly requested empty subsystem */
 	bool none;
-
-	struct cgroupfs_root *new_root;
-
 };
 
 /*
@@ -1380,11 +1292,10 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 	return 0;
 }
 
-static int cgroup_remount(struct super_block *sb, int *flags, char *data)
+static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
 {
 	int ret = 0;
-	struct cgroupfs_root *root = sb->s_fs_info;
-	struct cgroup *cgrp = &root->top_cgroup;
+	struct cgroupfs_root *root = cgroup_root_from_kf(kf_root);
 	struct cgroup_sb_opts opts;
 	unsigned long added_mask, removed_mask;
 
@@ -1393,7 +1304,6 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
 		return -EINVAL;
 	}
 
-	mutex_lock(&cgrp->dentry->d_inode->i_mutex);
 	mutex_lock(&cgroup_tree_mutex);
 	mutex_lock(&cgroup_mutex);
 
@@ -1439,34 +1349,26 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
 	kfree(opts.name);
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&cgroup_tree_mutex);
-	mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
 	return ret;
 }
 
-static const struct super_operations cgroup_ops = {
-	.statfs = simple_statfs,
-	.drop_inode = generic_delete_inode,
-	.show_options = cgroup_show_options,
-	.remount_fs = cgroup_remount,
-};
-
 static void init_cgroup_housekeeping(struct cgroup *cgrp)
 {
+	atomic_set(&cgrp->refcnt, 1);
 	INIT_LIST_HEAD(&cgrp->sibling);
 	INIT_LIST_HEAD(&cgrp->children);
-	INIT_LIST_HEAD(&cgrp->files);
 	INIT_LIST_HEAD(&cgrp->cset_links);
 	INIT_LIST_HEAD(&cgrp->release_list);
 	INIT_LIST_HEAD(&cgrp->pidlists);
 	mutex_init(&cgrp->pidlist_mutex);
 	cgrp->dummy_css.cgroup = cgrp;
-	simple_xattrs_init(&cgrp->xattrs);
 }
 
 static void init_cgroup_root(struct cgroupfs_root *root)
 {
 	struct cgroup *cgrp = &root->top_cgroup;
 
+	atomic_set(&root->refcnt, 1);
 	INIT_LIST_HEAD(&root->root_list);
 	root->number_of_cgroups = 1;
 	cgrp->root = root;
@@ -1475,32 +1377,12 @@ static void init_cgroup_root(struct cgroupfs_root *root)
 	idr_init(&root->cgroup_idr);
 }
 
-static int cgroup_test_super(struct super_block *sb, void *data)
-{
-	struct cgroup_sb_opts *opts = data;
-	struct cgroupfs_root *root = sb->s_fs_info;
-
-	/* If we asked for a name then it must match */
-	if (opts->name && strcmp(opts->name, root->name))
-		return 0;
-
-	/*
-	 * If we asked for subsystems (or explicitly for no
-	 * subsystems) then they must match
-	 */
-	if ((opts->subsys_mask || opts->none)
-	    && (opts->subsys_mask != root->subsys_mask))
-		return 0;
-
-	return 1;
-}
-
 static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
 {
 	struct cgroupfs_root *root;
 
 	if (!opts->subsys_mask && !opts->none)
-		return NULL;
+		return ERR_PTR(-EINVAL);
 
 	root = kzalloc(sizeof(*root), GFP_KERNEL);
 	if (!root)
@@ -1527,99 +1409,21 @@ static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
 	return root;
 }
 
-static int cgroup_set_super(struct super_block *sb, void *data)
-{
-	int ret;
-	struct cgroup_sb_opts *opts = data;
-
-	/* If we don't have a new root, we can't set up a new sb */
-	if (!opts->new_root)
-		return -EINVAL;
-
-	BUG_ON(!opts->subsys_mask && !opts->none);
-
-	ret = set_anon_super(sb, NULL);
-	if (ret)
-		return ret;
-
-	sb->s_fs_info = opts->new_root;
-	opts->new_root->sb = sb;
-
-	sb->s_blocksize = PAGE_CACHE_SIZE;
-	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
-	sb->s_magic = CGROUP_SUPER_MAGIC;
-	sb->s_op = &cgroup_ops;
-
-	return 0;
-}
-
-static int cgroup_get_rootdir(struct super_block *sb)
-{
-	static const struct dentry_operations cgroup_dops = {
-		.d_iput = cgroup_diput,
-		.d_delete = always_delete_dentry,
-	};
-
-	struct inode *inode =
-		cgroup_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR, sb);
-
-	if (!inode)
-		return -ENOMEM;
-
-	inode->i_fop = &simple_dir_operations;
-	inode->i_op = &cgroup_dir_inode_operations;
-	/* directories start off with i_nlink == 2 (for "." entry) */
-	inc_nlink(inode);
-	sb->s_root = d_make_root(inode);
-	if (!sb->s_root)
-		return -ENOMEM;
-	/* for everything else we want ->d_op set */
-	sb->s_d_op = &cgroup_dops;
-	return 0;
-}
-
 static int cgroup_setup_root(struct cgroupfs_root *root)
 {
 	LIST_HEAD(tmp_links);
-	struct super_block *sb = root->sb;
 	struct cgroup *root_cgrp = &root->top_cgroup;
-	struct cgroupfs_root *existing_root;
 	struct css_set *cset;
-	struct inode *inode;
-	const struct cred *cred;
 	int i, ret;
 
 	lockdep_assert_held(&cgroup_tree_mutex);
 	lockdep_assert_held(&cgroup_mutex);
-	BUG_ON(sb->s_root != NULL);
-
-	mutex_unlock(&cgroup_mutex);
-	mutex_unlock(&cgroup_tree_mutex);
-
-	ret = cgroup_get_rootdir(sb);
-	if (ret) {
-		mutex_lock(&cgroup_tree_mutex);
-		mutex_lock(&cgroup_mutex);
-		return ret;
-	}
-	inode = sb->s_root->d_inode;
-
-	mutex_lock(&inode->i_mutex);
-	mutex_lock(&cgroup_tree_mutex);
-	mutex_lock(&cgroup_mutex);
 
 	ret = idr_alloc(&root->cgroup_idr, root_cgrp, 0, 1, GFP_KERNEL);
 	if (ret < 0)
-		goto out_unlock;
+		goto out;
 	root_cgrp->id = ret;
 
-	/* check for name clashes with existing mounts */
-	ret = -EBUSY;
-	if (strlen(root->name))
-		for_each_active_root(existing_root)
-			if (!strcmp(existing_root->name, root->name))
-				goto out_unlock;
-
 	/*
 	 * We're accessing css_set_count without locking css_set_lock here,
 	 * but that's OK - it can only be increased by someone holding
@@ -1628,34 +1432,29 @@ static int cgroup_setup_root(struct cgroupfs_root *root)
 	 */
 	ret = allocate_cgrp_cset_links(css_set_count, &tmp_links);
 	if (ret)
-		goto out_unlock;
+		goto out;
 
 	/* ID 0 is reserved for dummy root, 1 for unified hierarchy */
 	ret = cgroup_init_root_id(root, 2, 0);
 	if (ret)
-		goto out_unlock;
-
-	sb->s_root->d_fsdata = root_cgrp;
-	root_cgrp->dentry = sb->s_root;
+		goto out;
 
-	/*
-	 * We're inside get_sb() and will call lookup_one_len() to create
-	 * the root files, which doesn't work if SELinux is in use.  The
-	 * following cred dancing somehow works around it.  See 2ce9738ba
-	 * ("cgroupfs: use init_cred when populating new cgroupfs mount")
-	 * for more details.
-	 */
-	cred = override_creds(&init_cred);
+	root->kf_root = kernfs_create_root(&cgroup_kf_syscall_ops,
+					   KERNFS_ROOT_CREATE_DEACTIVATED,
+					   root_cgrp);
+	if (IS_ERR(root->kf_root)) {
+		ret = PTR_ERR(root->kf_root);
+		goto exit_root_id;
+	}
+	root_cgrp->kn = root->kf_root->kn;
 
 	ret = cgroup_addrm_files(root_cgrp, cgroup_base_files, true);
 	if (ret)
-		goto rm_base_files;
+		goto destroy_root;
 
 	ret = rebind_subsystems(root, root->subsys_mask, 0);
 	if (ret)
-		goto rm_base_files;
-
-	revert_creds(cred);
+		goto destroy_root;
 
 	/*
 	 * There must be no failure case after here, since rebinding takes
@@ -1677,15 +1476,16 @@ static int cgroup_setup_root(struct cgroupfs_root *root)
 	BUG_ON(!list_empty(&root_cgrp->children));
 	BUG_ON(root->number_of_cgroups != 1);
 
+	kernfs_activate(root_cgrp->kn);
 	ret = 0;
-	goto out_unlock;
+	goto out;
 
-rm_base_files:
-	cgroup_addrm_files(&root->top_cgroup, cgroup_base_files, false);
-	revert_creds(cred);
+destroy_root:
+	kernfs_destroy_root(root->kf_root);
+	root->kf_root = NULL;
+exit_root_id:
 	cgroup_exit_root_id(root);
-out_unlock:
-	mutex_unlock(&inode->i_mutex);
+out:
 	free_cgrp_cset_links(&tmp_links);
 	return ret;
 }
@@ -1694,10 +1494,9 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 			 int flags, const char *unused_dev_name,
 			 void *data)
 {
-	struct super_block *sb = NULL;
-	struct cgroupfs_root *root = NULL;
+	struct cgroupfs_root *root;
 	struct cgroup_sb_opts opts;
-	struct cgroupfs_root *new_root;
+	struct dentry *dentry;
 	int ret;
 
 	mutex_lock(&cgroup_tree_mutex);
@@ -1708,41 +1507,32 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 	if (ret)
 		goto out_unlock;
 
-	/*
-	 * Allocate a new cgroup root. We may not need it if we're
-	 * reusing an existing hierarchy.
-	 */
-	new_root = cgroup_root_from_opts(&opts);
-	if (IS_ERR(new_root)) {
-		ret = PTR_ERR(new_root);
-		goto out_unlock;
-	}
-	opts.new_root = new_root;
+	/* look for a matching existing root */
+	for_each_active_root(root) {
+		bool name_match = false;
 
-	/* Locate an existing or new sb for this hierarchy */
-	mutex_unlock(&cgroup_mutex);
-	mutex_unlock(&cgroup_tree_mutex);
-	sb = sget(fs_type, cgroup_test_super, cgroup_set_super, 0, &opts);
-	mutex_lock(&cgroup_tree_mutex);
-	mutex_lock(&cgroup_mutex);
-	if (IS_ERR(sb)) {
-		ret = PTR_ERR(sb);
-		cgroup_free_root(opts.new_root);
-		goto out_unlock;
-	}
+		/*
+		 * If we asked for a name then it must match.  Also, if
+		 * name matches but sybsys_mask doesn't, we should fail.
+		 * Remember whether name matched.
+		 */
+		if (opts.name) {
+			if (strcmp(opts.name, root->name))
+				continue;
+			name_match = true;
+		}
 
-	root = sb->s_fs_info;
-	BUG_ON(!root);
-	if (root == opts.new_root) {
-		ret = cgroup_setup_root(root);
-		if (ret)
-			goto out_unlock;
-	} else {
 		/*
-		 * We re-used an existing hierarchy - the new root (if
-		 * any) is not needed
+		 * If we asked for subsystems (or explicitly for no
+		 * subsystems) then they must match.
 		 */
-		cgroup_free_root(opts.new_root);
+		if ((opts.subsys_mask || opts.none) &&
+		    (opts.subsys_mask != root->subsys_mask)) {
+			if (!name_match)
+				continue;
+			ret = -EBUSY;
+			goto out_unlock;
+		}
 
 		if ((root->flags ^ opts.flags) & CGRP_ROOT_OPTION_MASK) {
 			if ((root->flags | opts.flags) & CGRP_ROOT_SANE_BEHAVIOR) {
@@ -1753,23 +1543,45 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 				pr_warning("cgroup: new mount options do not match the existing superblock, will be ignored\n");
 			}
 		}
+
+		cgroup_get_root(root);
+		goto out_unlock;
 	}
 
-	ret = 0;
+	/* no such thing, create a new one */
+	root = cgroup_root_from_opts(&opts);
+	if (IS_ERR(root)) {
+		ret = PTR_ERR(root);
+		goto out_unlock;
+	}
+
+	ret = cgroup_setup_root(root);
+	if (ret)
+		cgroup_free_root(root);
+
 out_unlock:
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&cgroup_tree_mutex);
 
-	if (ret && !IS_ERR_OR_NULL(sb))
-		deactivate_locked_super(sb);
-
 	kfree(opts.release_agent);
 	kfree(opts.name);
 
-	if (!ret)
-		return dget(sb->s_root);
-	else
+	if (ret)
 		return ERR_PTR(ret);
+
+	dentry = kernfs_mount(fs_type, flags, root->kf_root);
+	if (IS_ERR(dentry))
+		cgroup_put_root(root);
+	return dentry;
+}
+
+static void cgroup_kill_sb(struct super_block *sb)
+{
+	struct kernfs_root *kf_root = kernfs_root_from_sb(sb);
+	struct cgroupfs_root *root = cgroup_root_from_kf(kf_root);
+
+	cgroup_put_root(root);
+	kernfs_kill_sb(sb);
 }
 
 static struct file_system_type cgroup_fs_type = {
@@ -2301,29 +2113,23 @@ static int cgroup_sane_behavior_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static ssize_t cgroup_file_write(struct file *file, const char __user *userbuf,
-				 size_t nbytes, loff_t *ppos)
+static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
+				 size_t nbytes, loff_t off)
 {
-	struct cfent *cfe = __d_cfe(file->f_dentry);
-	struct cftype *cft = __d_cft(file->f_dentry);
-	struct cgroup_subsys_state *css = cfe->css;
-	size_t max_bytes = max(cft->max_write_len, PAGE_SIZE);
-	char *buf;
+	struct cgroup *cgrp = of->kn->parent->priv;
+	struct cftype *cft = of->kn->priv;
+	struct cgroup_subsys_state *css;
 	int ret;
 
-	if (nbytes > max_bytes)
-		return -E2BIG;
-
-	buf = kmalloc(nbytes + 1, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	if (copy_from_user(buf, userbuf, nbytes)) {
-		ret = -EFAULT;
-		goto out_free;
-	}
-
-	buf[nbytes] = '\0';
+	/*
+	 * kernfs guarantees that a file isn't deleted with operations in
+	 * flight, which means that the matching css is and stays alive and
+	 * doesn't need to be pinned.  The RCU locking is not necessary
+	 * either.  It's just for the convenience of using cgroup_css().
+	 */
+	rcu_read_lock();
+	css = cgroup_css(cgrp, cft->ss);
+	rcu_read_unlock();
 
 	if (cft->write_string) {
 		ret = cft->write_string(css, cft, strstrip(buf));
@@ -2342,53 +2148,23 @@ static ssize_t cgroup_file_write(struct file *file, const char __user *userbuf,
 	} else {
 		ret = -EINVAL;
 	}
-out_free:
-	kfree(buf);
+
 	return ret ?: nbytes;
 }
 
-/*
- * seqfile ops/methods for returning structured data. Currently just
- * supports string->u64 maps, but can be extended in future.
- */
-
 static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos)
 {
-	struct cftype *cft = seq_cft(seq);
-
-	if (cft->seq_start) {
-		return cft->seq_start(seq, ppos);
-	} else {
-		/*
-		 * The same behavior and code as single_open().  Returns
-		 * !NULL if pos is at the beginning; otherwise, NULL.
-		 */
-		return NULL + !*ppos;
-	}
+	return seq_cft(seq)->seq_start(seq, ppos);
 }
 
 static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos)
 {
-	struct cftype *cft = seq_cft(seq);
-
-	if (cft->seq_next) {
-		return cft->seq_next(seq, v, ppos);
-	} else {
-		/*
-		 * The same behavior and code as single_open(), always
-		 * terminate after the initial read.
-		 */
-		++*ppos;
-		return NULL;
-	}
+	return seq_cft(seq)->seq_next(seq, v, ppos);
 }
 
 static void cgroup_seqfile_stop(struct seq_file *seq, void *v)
 {
-	struct cftype *cft = seq_cft(seq);
-
-	if (cft->seq_stop)
-		cft->seq_stop(seq, v);
+	seq_cft(seq)->seq_stop(seq, v);
 }
 
 static int cgroup_seqfile_show(struct seq_file *m, void *arg)
@@ -2408,96 +2184,36 @@ static int cgroup_seqfile_show(struct seq_file *m, void *arg)
 	return 0;
 }
 
-static struct seq_operations cgroup_seq_operations = {
-	.start		= cgroup_seqfile_start,
-	.next		= cgroup_seqfile_next,
-	.stop		= cgroup_seqfile_stop,
-	.show		= cgroup_seqfile_show,
+static struct kernfs_ops cgroup_kf_single_ops = {
+	.atomic_write_len	= PAGE_SIZE,
+	.write			= cgroup_file_write,
+	.seq_show		= cgroup_seqfile_show,
 };
 
-static int cgroup_file_open(struct inode *inode, struct file *file)
-{
-	struct cfent *cfe = __d_cfe(file->f_dentry);
-	struct cftype *cft = __d_cft(file->f_dentry);
-	struct cgroup *cgrp = __d_cgrp(cfe->dentry->d_parent);
-	struct cgroup_subsys_state *css;
-	struct cgroup_open_file *of;
-	int err;
-
-	err = generic_file_open(inode, file);
-	if (err)
-		return err;
-
-	/*
-	 * If the file belongs to a subsystem, pin the css.  Will be
-	 * unpinned either on open failure or release.  This ensures that
-	 * @css stays alive for all file operations.
-	 */
-	rcu_read_lock();
-	css = cgroup_css(cgrp, cft->ss);
-	if (cft->ss && !css_tryget(css))
-		css = NULL;
-	rcu_read_unlock();
-
-	if (!css)
-		return -ENODEV;
-
-	/*
-	 * @cfe->css is used by read/write/close to determine the
-	 * associated css.  @file->private_data would be a better place but
-	 * that's already used by seqfile.  Multiple accessors may use it
-	 * simultaneously which is okay as the association never changes.
-	 */
-	WARN_ON_ONCE(cfe->css && cfe->css != css);
-	cfe->css = css;
-
-	of = __seq_open_private(file, &cgroup_seq_operations,
-				sizeof(struct cgroup_open_file));
-	if (of) {
-		of->cfe = cfe;
-		return 0;
-	}
-
-	if (css->ss)
-		css_put(css);
-	return -ENOMEM;
-}
-
-static int cgroup_file_release(struct inode *inode, struct file *file)
-{
-	struct cfent *cfe = __d_cfe(file->f_dentry);
-	struct cgroup_subsys_state *css = cfe->css;
-
-	if (css->ss)
-		css_put(css);
-	return seq_release_private(inode, file);
-}
+static struct kernfs_ops cgroup_kf_ops = {
+	.atomic_write_len	= PAGE_SIZE,
+	.write			= cgroup_file_write,
+	.seq_start		= cgroup_seqfile_start,
+	.seq_next		= cgroup_seqfile_next,
+	.seq_stop		= cgroup_seqfile_stop,
+	.seq_show		= cgroup_seqfile_show,
+};
 
 /*
  * cgroup_rename - Only allow simple rename of directories in place.
  */
-static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry,
-			    struct inode *new_dir, struct dentry *new_dentry)
+static int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent,
+			 const char *new_name_str)
 {
-	int ret;
+	struct cgroup *cgrp = kn->priv;
 	struct cgroup_name *name, *old_name;
-	struct cgroup *cgrp;
-
-	/*
-	 * It's convinient to use parent dir's i_mutex to protected
-	 * cgrp->name.
-	 */
-	lockdep_assert_held(&old_dir->i_mutex);
+	int ret;
 
-	if (!S_ISDIR(old_dentry->d_inode->i_mode))
+	if (kernfs_type(kn) != KERNFS_DIR)
 		return -ENOTDIR;
-	if (new_dentry->d_inode)
-		return -EEXIST;
-	if (old_dir != new_dir)
+	if (kn->parent != new_parent)
 		return -EIO;
 
-	cgrp = __d_cgrp(old_dentry);
-
 	/*
 	 * This isn't a proper migration and its usefulness is very
 	 * limited.  Disallow if sane_behavior.
@@ -2505,186 +2221,43 @@ static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (cgroup_sane_behavior(cgrp))
 		return -EPERM;
 
-	name = cgroup_alloc_name(new_dentry->d_name.name);
+	name = cgroup_alloc_name(new_name_str);
 	if (!name)
 		return -ENOMEM;
 
-	ret = simple_rename(old_dir, old_dentry, new_dir, new_dentry);
-	if (ret) {
-		kfree(name);
-		return ret;
+	mutex_lock(&cgroup_tree_mutex);
+	mutex_lock(&cgroup_mutex);
+
+	ret = kernfs_rename(kn, new_parent, new_name_str);
+	if (!ret) {
+		old_name = rcu_dereference_protected(cgrp->name, true);
+		rcu_assign_pointer(cgrp->name, name);
+	} else {
+		old_name = name;
 	}
 
-	old_name = rcu_dereference_protected(cgrp->name, true);
-	rcu_assign_pointer(cgrp->name, name);
+	mutex_unlock(&cgroup_mutex);
+	mutex_unlock(&cgroup_tree_mutex);
 
 	kfree_rcu(old_name, rcu_head);
-	return 0;
-}
-
-static struct simple_xattrs *__d_xattrs(struct dentry *dentry)
-{
-	if (S_ISDIR(dentry->d_inode->i_mode))
-		return &__d_cgrp(dentry)->xattrs;
-	else
-		return &__d_cfe(dentry)->xattrs;
-}
-
-static inline int xattr_enabled(struct dentry *dentry)
-{
-	struct cgroupfs_root *root = dentry->d_sb->s_fs_info;
-	return root->flags & CGRP_ROOT_XATTR;
-}
-
-static bool is_valid_xattr(const char *name)
-{
-	if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) ||
-	    !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN))
-		return true;
-	return false;
-}
-
-static int cgroup_setxattr(struct dentry *dentry, const char *name,
-			   const void *val, size_t size, int flags)
-{
-	if (!xattr_enabled(dentry))
-		return -EOPNOTSUPP;
-	if (!is_valid_xattr(name))
-		return -EINVAL;
-	return simple_xattr_set(__d_xattrs(dentry), name, val, size, flags);
-}
-
-static int cgroup_removexattr(struct dentry *dentry, const char *name)
-{
-	if (!xattr_enabled(dentry))
-		return -EOPNOTSUPP;
-	if (!is_valid_xattr(name))
-		return -EINVAL;
-	return simple_xattr_remove(__d_xattrs(dentry), name);
-}
-
-static ssize_t cgroup_getxattr(struct dentry *dentry, const char *name,
-			       void *buf, size_t size)
-{
-	if (!xattr_enabled(dentry))
-		return -EOPNOTSUPP;
-	if (!is_valid_xattr(name))
-		return -EINVAL;
-	return simple_xattr_get(__d_xattrs(dentry), name, buf, size);
-}
-
-static ssize_t cgroup_listxattr(struct dentry *dentry, char *buf, size_t size)
-{
-	if (!xattr_enabled(dentry))
-		return -EOPNOTSUPP;
-	return simple_xattr_list(__d_xattrs(dentry), buf, size);
-}
-
-static const struct file_operations cgroup_file_operations = {
-	.read = seq_read,
-	.write = cgroup_file_write,
-	.llseek = generic_file_llseek,
-	.open = cgroup_file_open,
-	.release = cgroup_file_release,
-};
-
-static const struct inode_operations cgroup_file_inode_operations = {
-	.setxattr = cgroup_setxattr,
-	.getxattr = cgroup_getxattr,
-	.listxattr = cgroup_listxattr,
-	.removexattr = cgroup_removexattr,
-};
-
-static const struct inode_operations cgroup_dir_inode_operations = {
-	.lookup = simple_lookup,
-	.mkdir = cgroup_mkdir,
-	.rmdir = cgroup_rmdir,
-	.rename = cgroup_rename,
-	.setxattr = cgroup_setxattr,
-	.getxattr = cgroup_getxattr,
-	.listxattr = cgroup_listxattr,
-	.removexattr = cgroup_removexattr,
-};
-
-static int cgroup_create_file(struct dentry *dentry, umode_t mode,
-				struct super_block *sb)
-{
-	struct inode *inode;
-
-	if (!dentry)
-		return -ENOENT;
-	if (dentry->d_inode)
-		return -EEXIST;
-
-	inode = cgroup_new_inode(mode, sb);
-	if (!inode)
-		return -ENOMEM;
-
-	if (S_ISDIR(mode)) {
-		inode->i_op = &cgroup_dir_inode_operations;
-		inode->i_fop = &simple_dir_operations;
-
-		/* start off with i_nlink == 2 (for "." entry) */
-		inc_nlink(inode);
-		inc_nlink(dentry->d_parent->d_inode);
-
-		/*
-		 * Control reaches here with cgroup_mutex held.
-		 * @inode->i_mutex should nest outside cgroup_mutex but we
-		 * want to populate it immediately without releasing
-		 * cgroup_mutex.  As @inode isn't visible to anyone else
-		 * yet, trylock will always succeed without affecting
-		 * lockdep checks.
-		 */
-		WARN_ON_ONCE(!mutex_trylock(&inode->i_mutex));
-	} else if (S_ISREG(mode)) {
-		inode->i_size = 0;
-		inode->i_fop = &cgroup_file_operations;
-		inode->i_op = &cgroup_file_inode_operations;
-	}
-	d_instantiate(dentry, inode);
-	dget(dentry);	/* Extra count - pin the dentry in core */
-	return 0;
+	return ret;
 }
 
 static int cgroup_add_file(struct cgroup *cgrp, struct cftype *cft)
 {
-	struct dentry *dir = cgrp->dentry;
-	struct cgroup *parent = __d_cgrp(dir);
-	struct dentry *dentry;
-	struct cfent *cfe;
-	int error;
-	umode_t mode;
 	char name[CGROUP_FILE_NAME_MAX];
+	struct kernfs_node *kn;
+	struct lock_class_key *key = NULL;
 
-	BUG_ON(!mutex_is_locked(&dir->d_inode->i_mutex));
-
-	cfe = kzalloc(sizeof(*cfe), GFP_KERNEL);
-	if (!cfe)
-		return -ENOMEM;
-
-	cgroup_file_name(cgrp, cft, name);
-	dentry = lookup_one_len(name, dir, strlen(name));
-	if (IS_ERR(dentry)) {
-		error = PTR_ERR(dentry);
-		goto out;
-	}
-
-	cfe->type = (void *)cft;
-	cfe->dentry = dentry;
-	dentry->d_fsdata = cfe;
-	simple_xattrs_init(&cfe->xattrs);
-
-	mode = cgroup_file_mode(cft);
-	error = cgroup_create_file(dentry, mode | S_IFREG, cgrp->root->sb);
-	if (!error) {
-		list_add_tail(&cfe->node, &parent->files);
-		cfe = NULL;
-	}
-	dput(dentry);
-out:
-	kfree(cfe);
-	return error;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	key = &cft->lockdep_key;
+#endif
+	kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name),
+				  cgroup_file_mode(cft), 0, cft->kf_ops, cft,
+				  NULL, false, key);
+	if (IS_ERR(kn))
+		return PTR_ERR(kn);
+	return 0;
 }
 
 /**
@@ -2704,7 +2277,6 @@ static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
 	struct cftype *cft;
 	int ret;
 
-	lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex);
 	lockdep_assert_held(&cgroup_tree_mutex);
 
 	for (cft = cfts; cft->name[0] != '\0'; cft++) {
@@ -2749,9 +2321,7 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add)
 	LIST_HEAD(pending);
 	struct cgroup_subsys *ss = cfts[0].ss;
 	struct cgroup *root = &ss->root->top_cgroup;
-	struct super_block *sb = ss->root->sb;
 	struct cgroup *prev = NULL;
-	struct inode *inode;
 	struct cgroup_subsys_state *css;
 	u64 update_before;
 	int ret = 0;
@@ -2759,12 +2329,13 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add)
 	mutex_unlock(&cgroup_mutex);
 
 	/* %NULL @cfts indicates abort and don't bother if @ss isn't attached */
-	if (!cfts || ss->root == &cgroup_dummy_root ||
-	    !atomic_inc_not_zero(&sb->s_active)) {
+	if (!cfts || ss->root == &cgroup_dummy_root) {
 		mutex_unlock(&cgroup_tree_mutex);
 		return 0;
 	}
 
+	cgroup_get_root(ss->root);
+
 	/*
 	 * All cgroups which are created after we drop cgroup_mutex will
 	 * have the updated set of files, so we only need to update the
@@ -2779,18 +2350,16 @@ static int cgroup_cfts_commit(struct cftype *cfts, bool is_add)
 		if (cgroup_is_dead(cgrp))
 			continue;
 
-		inode = cgrp->dentry->d_inode;
 		cgroup_get(cgrp);
 		if (prev)
 			cgroup_put(prev);
 		prev = cgrp;
 
-		mutex_unlock(&cgroup_tree_mutex);
-		mutex_lock(&inode->i_mutex);
-		mutex_lock(&cgroup_tree_mutex);
-		if (cgrp->serial_nr < update_before && !cgroup_is_dead(cgrp))
+		if (cgrp->serial_nr < update_before && !cgroup_is_dead(cgrp)) {
 			ret = cgroup_addrm_files(cgrp, cfts, is_add);
-		mutex_unlock(&inode->i_mutex);
+			if (is_add)
+				kernfs_activate(cgrp->kn);
+		}
 		if (ret)
 			break;
 	}
@@ -2804,16 +2373,45 @@ static void cgroup_exit_cftypes(struct cftype *cfts)
 {
 	struct cftype *cft;
 
-	for (cft = cfts; cft->name[0] != '\0'; cft++)
+	for (cft = cfts; cft->name[0] != '\0'; cft++) {
+		/* free copy for custom atomic_write_len, see init_cftypes() */
+		if (cft->max_write_len && cft->max_write_len != PAGE_SIZE)
+			kfree(cft->kf_ops);
+		cft->kf_ops = NULL;
 		cft->ss = NULL;
+	}
 }
 
-static void cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
+static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
 {
 	struct cftype *cft;
 
-	for (cft = cfts; cft->name[0] != '\0'; cft++)
+	for (cft = cfts; cft->name[0] != '\0'; cft++) {
+		struct kernfs_ops *kf_ops;
+
+		if (cft->seq_start)
+			kf_ops = &cgroup_kf_ops;
+		else
+			kf_ops = &cgroup_kf_single_ops;
+
+		/*
+		 * Ugh... if @cft wants a custom max_write_len, we need to
+		 * make a copy of kf_ops to set its atomic_write_len.
+		 */
+		if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) {
+			kf_ops = kmemdup(kf_ops, sizeof(*kf_ops), GFP_KERNEL);
+			if (!kf_ops) {
+				cgroup_exit_cftypes(cfts);
+				return -ENOMEM;
+			}
+			kf_ops->atomic_write_len = cft->max_write_len;
+		}
+
+		cft->kf_ops = kf_ops;
 		cft->ss = ss;
+	}
+
+	return 0;
 }
 
 /**
@@ -2839,7 +2437,9 @@ int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
 	if (!set)
 		return -ENOMEM;
 
-	cgroup_init_cftypes(ss, cfts);
+	ret = cgroup_init_cftypes(ss, cfts);
+	if (ret)
+		return ret;
 
 	cgroup_cfts_prepare();
 	set->cfts = cfts;
@@ -3706,21 +3306,27 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type,
  */
 int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 {
-	int ret = -EINVAL;
+	struct kernfs_node *kn = kernfs_node_from_dentry(dentry);
 	struct cgroup *cgrp;
 	struct css_task_iter it;
 	struct task_struct *tsk;
 
+	/* it should be kernfs_node belonging to cgroupfs and is a directory */
+	if (dentry->d_sb->s_type != &cgroup_fs_type || !kn ||
+	    kernfs_type(kn) != KERNFS_DIR)
+		return -EINVAL;
+
 	/*
-	 * Validate dentry by checking the superblock operations,
-	 * and make sure it's a directory.
+	 * We aren't being called from kernfs and there's no guarantee on
+	 * @kn->priv's validity.  For this and css_tryget_from_dir(),
+	 * @kn->priv is RCU safe.  Let's do the RCU dancing.
 	 */
-	if (dentry->d_sb->s_op != &cgroup_ops ||
-	    !S_ISDIR(dentry->d_inode->i_mode))
-		 goto err;
-
-	ret = 0;
-	cgrp = dentry->d_fsdata;
+	rcu_read_lock();
+	cgrp = rcu_dereference(kn->priv);
+	if (!cgrp) {
+		rcu_read_unlock();
+		return -ENOENT;
+	}
 
 	css_task_iter_start(&cgrp->dummy_css, &it);
 	while ((tsk = css_task_iter_next(&it))) {
@@ -3745,8 +3351,8 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
 	}
 	css_task_iter_end(&it);
 
-err:
-	return ret;
+	rcu_read_unlock();
+	return 0;
 }
 
 
@@ -3764,7 +3370,7 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
 	 * after a seek to the start). Use a binary-search to find the
 	 * next pid to display, if any
 	 */
-	struct cgroup_open_file *of = s->private;
+	struct kernfs_open_file *of = s->private;
 	struct cgroup *cgrp = seq_css(s)->cgroup;
 	struct cgroup_pidlist *l;
 	enum cgroup_filetype type = seq_cft(s)->private;
@@ -3819,7 +3425,7 @@ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos)
 
 static void cgroup_pidlist_stop(struct seq_file *s, void *v)
 {
-	struct cgroup_open_file *of = s->private;
+	struct kernfs_open_file *of = s->private;
 	struct cgroup_pidlist *l = of->priv;
 
 	if (l)
@@ -3830,7 +3436,7 @@ static void cgroup_pidlist_stop(struct seq_file *s, void *v)
 
 static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos)
 {
-	struct cgroup_open_file *of = s->private;
+	struct kernfs_open_file *of = s->private;
 	struct cgroup_pidlist *l = of->priv;
 	pid_t *p = v;
 	pid_t *end = l->list + l->length;
@@ -3880,21 +3486,6 @@ static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css,
 	return 0;
 }
 
-/*
- * When dput() is called asynchronously, if umount has been done and
- * then deactivate_super() in cgroup_free_fn() kills the superblock,
- * there's a small window that vfs will see the root dentry with non-zero
- * refcnt and trigger BUG().
- *
- * That's why we hold a reference before dput() and drop it right after.
- */
-static void cgroup_dput(struct cgroup *cgrp)
-{
-	cgroup_get_root(cgrp->root);
-	cgroup_put(cgrp);
-	cgroup_put_root(cgrp->root);
-}
-
 static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css,
 				      struct cftype *cft)
 {
@@ -4029,7 +3620,7 @@ static void css_free_work_fn(struct work_struct *work)
 		css_put(css->parent);
 
 	css->ss->css_free(css);
-	cgroup_dput(cgrp);
+	cgroup_put(cgrp);
 }
 
 static void css_free_rcu_fn(struct rcu_head *rcu_head)
@@ -4037,10 +3628,6 @@ static void css_free_rcu_fn(struct rcu_head *rcu_head)
 	struct cgroup_subsys_state *css =
 		container_of(rcu_head, struct cgroup_subsys_state, rcu_head);
 
-	/*
-	 * css holds an extra ref to @cgrp->dentry which is put on the last
-	 * css_put().  dput() requires process context which we don't have.
-	 */
 	INIT_WORK(&css->destroy_work, css_free_work_fn);
 	queue_work(cgroup_destroy_wq, &css->destroy_work);
 }
@@ -4122,7 +3709,6 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss)
 	struct cgroup_subsys_state *css;
 	int err;
 
-	lockdep_assert_held(&cgrp->dentry->d_inode->i_mutex);
 	lockdep_assert_held(&cgroup_mutex);
 
 	css = ss->css_alloc(cgroup_css(parent, ss));
@@ -4163,30 +3749,28 @@ err_free:
 	return err;
 }
 
-/*
+/**
  * cgroup_create - create a cgroup
  * @parent: cgroup that will be parent of the new cgroup
- * @dentry: dentry of the new cgroup
- * @mode: mode to set on new inode
- *
- * Must be called with the mutex on the parent inode held
+ * @name_str: name of the new cgroup
+ * @mode: mode to set on new cgroup
  */
-static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
-			     umode_t mode)
+static long cgroup_create(struct cgroup *parent, const char *name_str,
+			  umode_t mode)
 {
 	struct cgroup *cgrp;
 	struct cgroup_name *name;
 	struct cgroupfs_root *root = parent->root;
 	int ssid, err;
 	struct cgroup_subsys *ss;
-	struct super_block *sb = root->sb;
+	struct kernfs_node *kn;
 
 	/* allocate the cgroup and its ID, 0 is reserved for the root */
 	cgrp = kzalloc(sizeof(*cgrp), GFP_KERNEL);
 	if (!cgrp)
 		return -ENOMEM;
 
-	name = cgroup_alloc_name(dentry->d_name.name);
+	name = cgroup_alloc_name(name_str);
 	if (!name) {
 		err = -ENOMEM;
 		goto err_free_cgrp;
@@ -4217,18 +3801,8 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 		goto err_unlock;
 	}
 
-	/* Grab a reference on the superblock so the hierarchy doesn't
-	 * get deleted on unmount if there are child cgroups.  This
-	 * can be done outside cgroup_mutex, since the sb can't
-	 * disappear while someone has an open control file on the
-	 * fs */
-	cgroup_get_root(root);
-
 	init_cgroup_housekeeping(cgrp);
 
-	dentry->d_fsdata = cgrp;
-	cgrp->dentry = dentry;
-
 	cgrp->parent = parent;
 	cgrp->dummy_css.parent = &parent->dummy_css;
 	cgrp->root = parent->root;
@@ -4239,15 +3813,13 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags))
 		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
 
-	/*
-	 * Create directory.  cgroup_create_file() returns with the new
-	 * directory locked on success so that it can be populated without
-	 * dropping cgroup_mutex.
-	 */
-	err = cgroup_create_file(dentry, S_IFDIR | mode, sb);
-	if (err < 0)
+	/* create the directory */
+	kn = kernfs_create_dir(parent->kn, name->name, mode, cgrp);
+	if (IS_ERR(kn)) {
+		err = PTR_ERR(kn);
 		goto err_free_id;
-	lockdep_assert_held(&dentry->d_inode->i_mutex);
+	}
+	cgrp->kn = kn;
 
 	cgrp->serial_nr = cgroup_serial_nr_next++;
 
@@ -4255,7 +3827,11 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children);
 	root->number_of_cgroups++;
 
-	/* hold a ref to the parent's dentry */
+	/*
+	 * Grab a reference on the root and parent so that they don't get
+	 * deleted while there are child cgroups.
+	 */
+	cgroup_get_root(root);
 	cgroup_get(parent);
 
 	/*
@@ -4277,16 +3853,15 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 		}
 	}
 
+	kernfs_activate(kn);
+
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&cgroup_tree_mutex);
-	mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
 
 	return 0;
 
 err_free_id:
 	idr_remove(&root->cgroup_idr, cgrp->id);
-	/* Release the reference count that we took on the superblock */
-	cgroup_put_root(root);
 err_unlock:
 	mutex_unlock(&cgroup_mutex);
 err_unlock_tree:
@@ -4300,16 +3875,15 @@ err_destroy:
 	cgroup_destroy_locked(cgrp);
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&cgroup_tree_mutex);
-	mutex_unlock(&dentry->d_inode->i_mutex);
 	return err;
 }
 
-static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
+static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
+			umode_t mode)
 {
-	struct cgroup *c_parent = dentry->d_parent->d_fsdata;
+	struct cgroup *parent = parent_kn->priv;
 
-	/* the vfs holds inode->i_mutex already */
-	return cgroup_create(c_parent, dentry, mode | S_IFDIR);
+	return cgroup_create(parent, name, mode);
 }
 
 /*
@@ -4373,6 +3947,10 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
  */
 static void kill_css(struct cgroup_subsys_state *css)
 {
+	/*
+	 * This must happen before css is disassociated with its cgroup.
+	 * See seq_css() for details.
+	 */
 	cgroup_clear_dir(css->cgroup, 1 << css->ss->id);
 
 	/*
@@ -4421,13 +3999,12 @@ static void kill_css(struct cgroup_subsys_state *css)
 static int cgroup_destroy_locked(struct cgroup *cgrp)
 	__releases(&cgroup_mutex) __acquires(&cgroup_mutex)
 {
-	struct dentry *d = cgrp->dentry;
-	struct cgroup_subsys_state *css;
 	struct cgroup *child;
+	struct cgroup_subsys_state *css;
+	struct kernfs_node *kn;
 	bool empty;
 	int ssid;
 
-	lockdep_assert_held(&d->d_inode->i_mutex);
 	lockdep_assert_held(&cgroup_tree_mutex);
 	lockdep_assert_held(&cgroup_mutex);
 
@@ -4492,15 +4069,24 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	if (!cgrp->nr_css)
 		cgroup_destroy_css_killed(cgrp);
 
+	/* remove @cgrp directory along with the base files */
+	mutex_unlock(&cgroup_mutex);
+
 	/*
-	 * Clear the base files and remove @cgrp directory.  The removal
-	 * puts the base ref but we aren't quite done with @cgrp yet, so
-	 * hold onto it.
+	 * There are two control paths which try to determine cgroup from
+	 * dentry without going through kernfs - cgroupstats_build() and
+	 * css_tryget_from_dir().  Those are supported by RCU protecting
+	 * clearing of cgrp->kn->priv backpointer, which should happen
+	 * after all files under it have been removed.
 	 */
-	mutex_unlock(&cgroup_mutex);
-	cgroup_addrm_files(cgrp, cgroup_base_files, false);
-	dget(d);
-	cgroup_d_remove_dir(d);
+	kn = cgrp->kn;
+	kernfs_get(kn);
+
+	kernfs_remove(cgrp->kn);
+
+	RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL);
+	kernfs_put(kn);
+
 	mutex_lock(&cgroup_mutex);
 
 	return 0;
@@ -4531,19 +4117,46 @@ static void cgroup_destroy_css_killed(struct cgroup *cgrp)
 	check_for_release(parent);
 }
 
-static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
+static int cgroup_rmdir(struct kernfs_node *kn)
 {
-	int ret;
+	struct cgroup *cgrp = kn->priv;
+	int ret = 0;
+
+	/*
+	 * This is self-destruction but @kn can't be removed while this
+	 * callback is in progress.  Let's break active protection.  Once
+	 * the protection is broken, @cgrp can be destroyed at any point.
+	 * Pin it so that it stays accessible.
+	 */
+	cgroup_get(cgrp);
+	kernfs_break_active_protection(kn);
 
 	mutex_lock(&cgroup_tree_mutex);
 	mutex_lock(&cgroup_mutex);
-	ret = cgroup_destroy_locked(dentry->d_fsdata);
+
+	/*
+	 * @cgrp might already have been destroyed while we're trying to
+	 * grab the mutexes.
+	 */
+	if (!cgroup_is_dead(cgrp))
+		ret = cgroup_destroy_locked(cgrp);
+
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&cgroup_tree_mutex);
 
+	kernfs_unbreak_active_protection(kn);
+	cgroup_put(cgrp);
 	return ret;
 }
 
+static struct kernfs_syscall_ops cgroup_kf_syscall_ops = {
+	.remount_fs		= cgroup_remount,
+	.show_options		= cgroup_show_options,
+	.mkdir			= cgroup_mkdir,
+	.rmdir			= cgroup_rmdir,
+	.rename			= cgroup_rename,
+};
+
 static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 {
 	struct cgroup_subsys_state *css;
@@ -4635,11 +4248,7 @@ int __init cgroup_init(void)
 	unsigned long key;
 	int i, err;
 
-	err = bdi_init(&cgroup_backing_dev_info);
-	if (err)
-		return err;
-
-	cgroup_init_cftypes(NULL, cgroup_base_files);
+	BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files));
 
 	for_each_subsys(ss, i) {
 		if (!ss->early_init)
@@ -4669,24 +4278,17 @@ int __init cgroup_init(void)
 	mutex_unlock(&cgroup_mutex);
 
 	cgroup_kobj = kobject_create_and_add("cgroup", fs_kobj);
-	if (!cgroup_kobj) {
-		err = -ENOMEM;
-		goto out;
-	}
+	if (!cgroup_kobj)
+		return -ENOMEM;
 
 	err = register_filesystem(&cgroup_fs_type);
 	if (err < 0) {
 		kobject_put(cgroup_kobj);
-		goto out;
+		return err;
 	}
 
 	proc_create("cgroups", 0, NULL, &proc_cgroupstats_operations);
-
-out:
-	if (err)
-		bdi_destroy(&cgroup_backing_dev_info);
-
-	return err;
+	return 0;
 }
 
 static int __init cgroup_wq_init(void)
@@ -5095,18 +4697,25 @@ __setup("cgroup_disable=", cgroup_disable);
 struct cgroup_subsys_state *css_tryget_from_dir(struct dentry *dentry,
 						struct cgroup_subsys *ss)
 {
+	struct kernfs_node *kn = kernfs_node_from_dentry(dentry);
+	struct cgroup_subsys_state *css = NULL;
 	struct cgroup *cgrp;
-	struct cgroup_subsys_state *css;
 
 	/* is @dentry a cgroup dir? */
-	if (!dentry->d_inode ||
-	    dentry->d_inode->i_op != &cgroup_dir_inode_operations)
+	if (dentry->d_sb->s_type != &cgroup_fs_type || !kn ||
+	    kernfs_type(kn) != KERNFS_DIR)
 		return ERR_PTR(-EBADF);
 
 	rcu_read_lock();
 
-	cgrp = __d_cgrp(dentry);
-	css = cgroup_css(cgrp, ss);
+	/*
+	 * This path doesn't originate from kernfs and @kn could already
+	 * have been or be removed at any point.  @kn->priv is RCU
+	 * protected for this access.  See destroy_locked() for details.
+	 */
+	cgrp = rcu_dereference(kn->priv);
+	if (cgrp)
+		css = cgroup_css(cgrp, ss);
 
 	if (!css || !css_tryget(css))
 		css = ERR_PTR(-ENOENT);
-- 
cgit v1.2.3


From 0f6a928d035b82c0b3aa387d510a73f3e6dbf8e3 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 6 Feb 2014 13:25:40 +0200
Subject: acpi-dma: convert to return error code when asked for channel

Currently acpi_dma_request_slave_chan_by_index() and
acpi_dma_request_slave_chan_by_name() return only requested channel or NULL.
This patch converts them to return appropriate error code instead of NULL in
case of unsuccessfull request.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 drivers/dma/acpi-dma.c   | 15 ++++++++-------
 drivers/dma/dmaengine.c  |  9 ++-------
 include/linux/acpi_dma.h |  5 +++--
 3 files changed, 13 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c
index 1fda371af4b7..de361a156b34 100644
--- a/drivers/dma/acpi-dma.c
+++ b/drivers/dma/acpi-dma.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/device.h>
+#include <linux/err.h>
 #include <linux/module.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
@@ -343,7 +344,7 @@ static int acpi_dma_parse_fixed_dma(struct acpi_resource *res, void *data)
  * @index:	index of FixedDMA descriptor for @dev
  *
  * Return:
- * Pointer to appropriate dma channel on success or NULL on error.
+ * Pointer to appropriate dma channel on success or an error pointer.
  */
 struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev,
 		size_t index)
@@ -358,10 +359,10 @@ struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev,
 
 	/* Check if the device was enumerated by ACPI */
 	if (!dev || !ACPI_HANDLE(dev))
-		return NULL;
+		return ERR_PTR(-ENODEV);
 
 	if (acpi_bus_get_device(ACPI_HANDLE(dev), &adev))
-		return NULL;
+		return ERR_PTR(-ENODEV);
 
 	memset(&pdata, 0, sizeof(pdata));
 	pdata.index = index;
@@ -376,7 +377,7 @@ struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev,
 	acpi_dev_free_resource_list(&resource_list);
 
 	if (dma_spec->slave_id < 0 || dma_spec->chan_id < 0)
-		return NULL;
+		return ERR_PTR(-ENODEV);
 
 	mutex_lock(&acpi_dma_lock);
 
@@ -399,7 +400,7 @@ struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev,
 	}
 
 	mutex_unlock(&acpi_dma_lock);
-	return chan;
+	return chan ? chan : ERR_PTR(-EPROBE_DEFER);
 }
 EXPORT_SYMBOL_GPL(acpi_dma_request_slave_chan_by_index);
 
@@ -413,7 +414,7 @@ EXPORT_SYMBOL_GPL(acpi_dma_request_slave_chan_by_index);
  * the first FixedDMA descriptor is TX and second is RX.
  *
  * Return:
- * Pointer to appropriate dma channel on success or NULL on error.
+ * Pointer to appropriate dma channel on success or an error pointer.
  */
 struct dma_chan *acpi_dma_request_slave_chan_by_name(struct device *dev,
 		const char *name)
@@ -425,7 +426,7 @@ struct dma_chan *acpi_dma_request_slave_chan_by_name(struct device *dev,
 	else if (!strcmp(name, "rx"))
 		index = 1;
 	else
-		return NULL;
+		return ERR_PTR(-ENODEV);
 
 	return acpi_dma_request_slave_chan_by_index(dev, index);
 }
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index ed610b497518..a886713937fd 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -627,18 +627,13 @@ EXPORT_SYMBOL_GPL(__dma_request_channel);
 struct dma_chan *dma_request_slave_channel_reason(struct device *dev,
 						  const char *name)
 {
-	struct dma_chan *chan;
-
 	/* If device-tree is present get slave info from here */
 	if (dev->of_node)
 		return of_dma_request_slave_channel(dev->of_node, name);
 
 	/* If device was enumerated by ACPI get slave info from here */
-	if (ACPI_HANDLE(dev)) {
-		chan = acpi_dma_request_slave_chan_by_name(dev, name);
-		if (chan)
-			return chan;
-	}
+	if (ACPI_HANDLE(dev))
+		return acpi_dma_request_slave_chan_by_name(dev, name);
 
 	return ERR_PTR(-ENODEV);
 }
diff --git a/include/linux/acpi_dma.h b/include/linux/acpi_dma.h
index fb0298082916..329436d38e66 100644
--- a/include/linux/acpi_dma.h
+++ b/include/linux/acpi_dma.h
@@ -16,6 +16,7 @@
 
 #include <linux/list.h>
 #include <linux/device.h>
+#include <linux/err.h>
 #include <linux/dmaengine.h>
 
 /**
@@ -103,12 +104,12 @@ static inline void devm_acpi_dma_controller_free(struct device *dev)
 static inline struct dma_chan *acpi_dma_request_slave_chan_by_index(
 		struct device *dev, size_t index)
 {
-	return NULL;
+	return ERR_PTR(-ENODEV);
 }
 static inline struct dma_chan *acpi_dma_request_slave_chan_by_name(
 		struct device *dev, const char *name)
 {
-	return NULL;
+	return ERR_PTR(-ENODEV);
 }
 
 #define acpi_dma_simple_xlate	NULL
-- 
cgit v1.2.3


From 2ea24497a1b30dd03dd42b873fa5097913587f4d Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@primarydata.com>
Date: Mon, 10 Feb 2014 11:18:39 -0500
Subject: SUNRPC: RPC callbacks may be split across several TCP segments

Since TCP is a stream protocol, our callback read code needs to take into
account the fact that RPC callbacks are not always confined to a single
TCP segment.
This patch adds support for multiple TCP segments by ensuring that we
only remove the rpc_rqst structure from the 'free backchannel requests'
list once the data has been completely received. We rely on the fact
that TCP data is ordered for the duration of the connection.

Reported-by: shaobingqing <shaobingqing@bwstor.com.cn>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 include/linux/sunrpc/bc_xprt.h |  3 +-
 net/sunrpc/backchannel_rqst.c  | 93 +++++++++++++++++++++++++++++-------------
 net/sunrpc/xprtsock.c          | 28 ++++---------
 3 files changed, 74 insertions(+), 50 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h
index 969c0a671dbf..2ca67b55e0fe 100644
--- a/include/linux/sunrpc/bc_xprt.h
+++ b/include/linux/sunrpc/bc_xprt.h
@@ -32,7 +32,8 @@ SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #include <linux/sunrpc/sched.h>
 
 #ifdef CONFIG_SUNRPC_BACKCHANNEL
-struct rpc_rqst *xprt_alloc_bc_request(struct rpc_xprt *xprt);
+struct rpc_rqst *xprt_lookup_bc_request(struct rpc_xprt *xprt, __be32 xid);
+void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied);
 void xprt_free_bc_request(struct rpc_rqst *req);
 int xprt_setup_backchannel(struct rpc_xprt *, unsigned int min_reqs);
 void xprt_destroy_backchannel(struct rpc_xprt *, unsigned int max_reqs);
diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c
index e860d4f7ed2a..3513d559bc45 100644
--- a/net/sunrpc/backchannel_rqst.c
+++ b/net/sunrpc/backchannel_rqst.c
@@ -212,39 +212,23 @@ out:
 }
 EXPORT_SYMBOL_GPL(xprt_destroy_backchannel);
 
-/*
- * One or more rpc_rqst structure have been preallocated during the
- * backchannel setup.  Buffer space for the send and private XDR buffers
- * has been preallocated as well.  Use xprt_alloc_bc_request to allocate
- * to this request.  Use xprt_free_bc_request to return it.
- *
- * We know that we're called in soft interrupt context, grab the spin_lock
- * since there is no need to grab the bottom half spin_lock.
- *
- * Return an available rpc_rqst, otherwise NULL if non are available.
- */
-struct rpc_rqst *xprt_alloc_bc_request(struct rpc_xprt *xprt)
+static struct rpc_rqst *xprt_alloc_bc_request(struct rpc_xprt *xprt, __be32 xid)
 {
-	struct rpc_rqst *req;
+	struct rpc_rqst *req = NULL;
 
 	dprintk("RPC:       allocate a backchannel request\n");
-	spin_lock(&xprt->bc_pa_lock);
-	if (!list_empty(&xprt->bc_pa_list)) {
-		req = list_first_entry(&xprt->bc_pa_list, struct rpc_rqst,
-				rq_bc_pa_list);
-		list_del(&req->rq_bc_pa_list);
-	} else {
-		req = NULL;
-	}
-	spin_unlock(&xprt->bc_pa_lock);
+	if (list_empty(&xprt->bc_pa_list))
+		goto not_found;
 
-	if (req != NULL) {
-		set_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state);
-		req->rq_reply_bytes_recvd = 0;
-		req->rq_bytes_sent = 0;
-		memcpy(&req->rq_private_buf, &req->rq_rcv_buf,
+	req = list_first_entry(&xprt->bc_pa_list, struct rpc_rqst,
+				rq_bc_pa_list);
+	req->rq_reply_bytes_recvd = 0;
+	req->rq_bytes_sent = 0;
+	memcpy(&req->rq_private_buf, &req->rq_rcv_buf,
 			sizeof(req->rq_private_buf));
-	}
+	req->rq_xid = xid;
+	req->rq_connect_cookie = xprt->connect_cookie;
+not_found:
 	dprintk("RPC:       backchannel req=%p\n", req);
 	return req;
 }
@@ -259,6 +243,7 @@ void xprt_free_bc_request(struct rpc_rqst *req)
 
 	dprintk("RPC:       free backchannel req=%p\n", req);
 
+	req->rq_connect_cookie = xprt->connect_cookie - 1;
 	smp_mb__before_clear_bit();
 	WARN_ON_ONCE(!test_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state));
 	clear_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state);
@@ -281,7 +266,57 @@ void xprt_free_bc_request(struct rpc_rqst *req)
 	 * may be reused by a new callback request.
 	 */
 	spin_lock_bh(&xprt->bc_pa_lock);
-	list_add(&req->rq_bc_pa_list, &xprt->bc_pa_list);
+	list_add_tail(&req->rq_bc_pa_list, &xprt->bc_pa_list);
 	spin_unlock_bh(&xprt->bc_pa_lock);
 }
 
+/*
+ * One or more rpc_rqst structure have been preallocated during the
+ * backchannel setup.  Buffer space for the send and private XDR buffers
+ * has been preallocated as well.  Use xprt_alloc_bc_request to allocate
+ * to this request.  Use xprt_free_bc_request to return it.
+ *
+ * We know that we're called in soft interrupt context, grab the spin_lock
+ * since there is no need to grab the bottom half spin_lock.
+ *
+ * Return an available rpc_rqst, otherwise NULL if non are available.
+ */
+struct rpc_rqst *xprt_lookup_bc_request(struct rpc_xprt *xprt, __be32 xid)
+{
+	struct rpc_rqst *req;
+
+	spin_lock(&xprt->bc_pa_lock);
+	list_for_each_entry(req, &xprt->bc_pa_list, rq_bc_pa_list) {
+		if (req->rq_connect_cookie != xprt->connect_cookie)
+			continue;
+		if (req->rq_xid == xid)
+			goto found;
+	}
+	req = xprt_alloc_bc_request(xprt, xid);
+found:
+	spin_unlock(&xprt->bc_pa_lock);
+	return req;
+}
+
+/*
+ * Add callback request to callback list.  The callback
+ * service sleeps on the sv_cb_waitq waiting for new
+ * requests.  Wake it up after adding enqueing the
+ * request.
+ */
+void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied)
+{
+	struct rpc_xprt *xprt = req->rq_xprt;
+	struct svc_serv *bc_serv = xprt->bc_serv;
+
+	req->rq_private_buf.len = copied;
+	set_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state);
+
+	dprintk("RPC:       add callback request to list\n");
+	spin_lock(&bc_serv->sv_cb_lock);
+	list_del(&req->rq_bc_pa_list);
+	list_add(&req->rq_bc_list, &bc_serv->sv_cb_list);
+	wake_up(&bc_serv->sv_cb_waitq);
+	spin_unlock(&bc_serv->sv_cb_lock);
+}
+
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 0addefca8e77..966763d735e9 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1306,41 +1306,29 @@ static inline int xs_tcp_read_reply(struct rpc_xprt *xprt,
  * If we're unable to obtain the rpc_rqst we schedule the closing of the
  * connection and return -1.
  */
-static inline int xs_tcp_read_callback(struct rpc_xprt *xprt,
+static int xs_tcp_read_callback(struct rpc_xprt *xprt,
 				       struct xdr_skb_reader *desc)
 {
 	struct sock_xprt *transport =
 				container_of(xprt, struct sock_xprt, xprt);
 	struct rpc_rqst *req;
 
-	req = xprt_alloc_bc_request(xprt);
+	/* Look up and lock the request corresponding to the given XID */
+	spin_lock(&xprt->transport_lock);
+	req = xprt_lookup_bc_request(xprt, transport->tcp_xid);
 	if (req == NULL) {
+		spin_unlock(&xprt->transport_lock);
 		printk(KERN_WARNING "Callback slot table overflowed\n");
 		xprt_force_disconnect(xprt);
 		return -1;
 	}
 
-	req->rq_xid = transport->tcp_xid;
 	dprintk("RPC:       read callback  XID %08x\n", ntohl(req->rq_xid));
 	xs_tcp_read_common(xprt, desc, req);
 
-	if (!(transport->tcp_flags & TCP_RCV_COPY_DATA)) {
-		struct svc_serv *bc_serv = xprt->bc_serv;
-
-		/*
-		 * Add callback request to callback list.  The callback
-		 * service sleeps on the sv_cb_waitq waiting for new
-		 * requests.  Wake it up after adding enqueing the
-		 * request.
-		 */
-		dprintk("RPC:       add callback request to list\n");
-		spin_lock(&bc_serv->sv_cb_lock);
-		list_add(&req->rq_bc_list, &bc_serv->sv_cb_list);
-		spin_unlock(&bc_serv->sv_cb_lock);
-		wake_up(&bc_serv->sv_cb_waitq);
-	}
-
-	req->rq_private_buf.len = transport->tcp_copied;
+	if (!(transport->tcp_flags & TCP_RCV_COPY_DATA))
+		xprt_complete_bc_request(req, transport->tcp_copied);
+	spin_unlock(&xprt->transport_lock);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 311324ad1713666a6e803aecf0d4e1a136a5b34a Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@primarydata.com>
Date: Fri, 7 Feb 2014 17:02:08 -0500
Subject: NFS: Be more aggressive in using readdirplus for 'ls -l' situations

Try to detect 'ls -l' by having nfs_getattr() look at whether or not
there is an opendir() file descriptor for the parent directory.
If so, then assume that we want to force use of readdirplus in order
to avoid the multiple GETATTR calls over the wire.

Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/nfs/dir.c           | 42 ++++++++++++++++++++++++++++++++++++++----
 fs/nfs/inode.c         | 34 +++++++++++++++++++++++++++-------
 fs/nfs/internal.h      |  1 +
 include/linux/nfs_fs.h |  1 +
 4 files changed, 67 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index be38b573495a..c8e48c26418b 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -69,21 +69,28 @@ const struct address_space_operations nfs_dir_aops = {
 
 static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir, struct rpc_cred *cred)
 {
+	struct nfs_inode *nfsi = NFS_I(dir);
 	struct nfs_open_dir_context *ctx;
 	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
 	if (ctx != NULL) {
 		ctx->duped = 0;
-		ctx->attr_gencount = NFS_I(dir)->attr_gencount;
+		ctx->attr_gencount = nfsi->attr_gencount;
 		ctx->dir_cookie = 0;
 		ctx->dup_cookie = 0;
 		ctx->cred = get_rpccred(cred);
+		spin_lock(&dir->i_lock);
+		list_add(&ctx->list, &nfsi->open_files);
+		spin_unlock(&dir->i_lock);
 		return ctx;
 	}
 	return  ERR_PTR(-ENOMEM);
 }
 
-static void put_nfs_open_dir_context(struct nfs_open_dir_context *ctx)
+static void put_nfs_open_dir_context(struct inode *dir, struct nfs_open_dir_context *ctx)
 {
+	spin_lock(&dir->i_lock);
+	list_del(&ctx->list);
+	spin_unlock(&dir->i_lock);
 	put_rpccred(ctx->cred);
 	kfree(ctx);
 }
@@ -126,7 +133,7 @@ out:
 static int
 nfs_closedir(struct inode *inode, struct file *filp)
 {
-	put_nfs_open_dir_context(filp->private_data);
+	put_nfs_open_dir_context(filp->f_path.dentry->d_inode, filp->private_data);
 	return 0;
 }
 
@@ -437,6 +444,22 @@ void nfs_advise_use_readdirplus(struct inode *dir)
 	set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(dir)->flags);
 }
 
+/*
+ * This function is mainly for use by nfs_getattr().
+ *
+ * If this is an 'ls -l', we want to force use of readdirplus.
+ * Do this by checking if there is an active file descriptor
+ * and calling nfs_advise_use_readdirplus, then forcing a
+ * cache flush.
+ */
+void nfs_force_use_readdirplus(struct inode *dir)
+{
+	if (!list_empty(&NFS_I(dir)->open_files)) {
+		nfs_advise_use_readdirplus(dir);
+		nfs_zap_mapping(dir, dir->i_mapping);
+	}
+}
+
 static
 void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
 {
@@ -815,6 +838,17 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc)
 	goto out;
 }
 
+static bool nfs_dir_mapping_need_revalidate(struct inode *dir)
+{
+	struct nfs_inode *nfsi = NFS_I(dir);
+
+	if (nfs_attribute_cache_expired(dir))
+		return true;
+	if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
+		return true;
+	return false;
+}
+
 /* The file offset position represents the dirent entry number.  A
    last cookie cache takes care of the common case of reading the
    whole directory.
@@ -847,7 +881,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	desc->plus = nfs_use_readdirplus(inode, ctx) ? 1 : 0;
 
 	nfs_block_sillyrename(dentry);
-	if (ctx->pos == 0 || nfs_attribute_cache_expired(inode))
+	if (ctx->pos == 0 || nfs_dir_mapping_need_revalidate(inode))
 		res = nfs_revalidate_mapping(inode, file->f_mapping);
 	if (res < 0)
 		goto out;
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 360114ae8b82..9dbef878a2b2 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -588,6 +588,25 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr)
 }
 EXPORT_SYMBOL_GPL(nfs_setattr_update_inode);
 
+static void nfs_request_parent_use_readdirplus(struct dentry *dentry)
+{
+	struct dentry *parent;
+
+	parent = dget_parent(dentry);
+	nfs_force_use_readdirplus(parent->d_inode);
+	dput(parent);
+}
+
+static bool nfs_need_revalidate_inode(struct inode *inode)
+{
+	if (NFS_I(inode)->cache_validity &
+			(NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL))
+		return true;
+	if (nfs_attribute_cache_expired(inode))
+		return true;
+	return false;
+}
+
 int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 {
 	struct inode *inode = dentry->d_inode;
@@ -616,10 +635,13 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
  	    ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)))
 		need_atime = 0;
 
-	if (need_atime)
-		err = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
-	else
-		err = nfs_revalidate_inode(NFS_SERVER(inode), inode);
+	if (need_atime || nfs_need_revalidate_inode(inode)) {
+		struct nfs_server *server = NFS_SERVER(inode);
+
+		if (server->caps & NFS_CAP_READDIRPLUS)
+			nfs_request_parent_use_readdirplus(dentry);
+		err = __nfs_revalidate_inode(server, inode);
+	}
 	if (!err) {
 		generic_fillattr(inode, stat);
 		stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode));
@@ -961,9 +983,7 @@ int nfs_attribute_cache_expired(struct inode *inode)
  */
 int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
 {
-	if (!(NFS_I(inode)->cache_validity &
-			(NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL))
-			&& !nfs_attribute_cache_expired(inode))
+	if (!nfs_need_revalidate_inode(inode))
 		return NFS_STALE(inode) ? -ESTALE : 0;
 	return __nfs_revalidate_inode(server, inode);
 }
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index fafdddac8271..7f7c476d0c2c 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -300,6 +300,7 @@ extern struct nfs_client *nfs_init_client(struct nfs_client *clp,
 			   const char *ip_addr);
 
 /* dir.c */
+extern void nfs_force_use_readdirplus(struct inode *dir);
 extern unsigned long nfs_access_cache_count(struct shrinker *shrink,
 					    struct shrink_control *sc);
 extern unsigned long nfs_access_cache_scan(struct shrinker *shrink,
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 0ae5807480f4..f55a90bed0b4 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -92,6 +92,7 @@ struct nfs_open_context {
 };
 
 struct nfs_open_dir_context {
+	struct list_head list;
 	struct rpc_cred *cred;
 	unsigned long attr_gencount;
 	__u64 dir_cookie;
-- 
cgit v1.2.3


From 2c74424470a0f98df8d6540642aff96d1a0b94b3 Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Mon, 3 Feb 2014 14:27:33 -0700
Subject: PCI: Add device-specific PCI ACS enable

Some devices support PCI ACS-like features, but don't report it using the
standard PCIe capabilities.  We already provide hooks for device-specific
testing of ACS, but not for device-specific enabling of ACS.  This provides
that setup hook.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.c    | 26 ++++++++++++++++++++------
 drivers/pci/quirks.c | 25 +++++++++++++++++++++++++
 include/linux/pci.h  |  2 ++
 3 files changed, 47 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 1febe90831b4..b89502ff3139 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2180,21 +2180,18 @@ void pci_request_acs(void)
 }
 
 /**
- * pci_enable_acs - enable ACS if hardware support it
+ * pci_std_enable_acs - enable ACS on devices using standard ACS capabilites
  * @dev: the PCI device
  */
-void pci_enable_acs(struct pci_dev *dev)
+static int pci_std_enable_acs(struct pci_dev *dev)
 {
 	int pos;
 	u16 cap;
 	u16 ctrl;
 
-	if (!pci_acs_enable)
-		return;
-
 	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
 	if (!pos)
-		return;
+		return -ENODEV;
 
 	pci_read_config_word(dev, pos + PCI_ACS_CAP, &cap);
 	pci_read_config_word(dev, pos + PCI_ACS_CTRL, &ctrl);
@@ -2212,6 +2209,23 @@ void pci_enable_acs(struct pci_dev *dev)
 	ctrl |= (cap & PCI_ACS_UF);
 
 	pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl);
+
+	return 0;
+}
+
+/**
+ * pci_enable_acs - enable ACS if hardware support it
+ * @dev: the PCI device
+ */
+void pci_enable_acs(struct pci_dev *dev)
+{
+	if (!pci_acs_enable)
+		return;
+
+	if (!pci_std_enable_acs(dev))
+		return;
+
+	pci_dev_specific_enable_acs(dev);
 }
 
 static bool pci_acs_flags_enabled(struct pci_dev *pdev, u16 acs_flags)
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 5cb726c193de..f681fb08f5e4 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3461,3 +3461,28 @@ int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags)
 
 	return -ENOTTY;
 }
+
+static const struct pci_dev_enable_acs {
+	u16 vendor;
+	u16 device;
+	int (*enable_acs)(struct pci_dev *dev);
+} pci_dev_enable_acs[] = {
+	{ 0 }
+};
+
+void pci_dev_specific_enable_acs(struct pci_dev *dev)
+{
+	const struct pci_dev_enable_acs *i;
+	int ret;
+
+	for (i = pci_dev_enable_acs; i->enable_acs; i++) {
+		if ((i->vendor == dev->vendor ||
+		     i->vendor == (u16)PCI_ANY_ID) &&
+		    (i->device == dev->device ||
+		     i->device == (u16)PCI_ANY_ID)) {
+			ret = i->enable_acs(dev);
+			if (ret >= 0)
+				return;
+		}
+	}
+}
diff --git a/include/linux/pci.h b/include/linux/pci.h
index fb57c892b214..0f76d0f66365 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1510,6 +1510,7 @@ enum pci_fixup_pass {
 void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev);
 struct pci_dev *pci_get_dma_source(struct pci_dev *dev);
 int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags);
+void pci_dev_specific_enable_acs(struct pci_dev *dev);
 #else
 static inline void pci_fixup_device(enum pci_fixup_pass pass,
 				    struct pci_dev *dev) { }
@@ -1522,6 +1523,7 @@ static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev,
 {
 	return -ENOTTY;
 }
+static inline void pci_dev_specific_enable_acs(struct pci_dev *dev) { }
 #endif
 
 void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen);
-- 
cgit v1.2.3


From 5757a769ea4e094df6ec92d9ce7d05a90d5bf3e6 Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Mon, 3 Feb 2014 14:27:39 -0700
Subject: PCI: Add pci_dev_flag for ACS enable quirks

Quirks that enable ACS-compatible functionality on a device need some way
to track whether a given device has been enabled.  Rather than create new
data structures for this, allocate one of the pci_dev_flags to indicate
this setup.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/linux/pci.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index 0f76d0f66365..60ab8d782f8c 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -170,6 +170,8 @@ enum pci_dev_flags {
 	PCI_DEV_FLAGS_NO_D3 = (__force pci_dev_flags_t) 2,
 	/* Provide indication device is assigned by a Virtual Machine Manager */
 	PCI_DEV_FLAGS_ASSIGNED = (__force pci_dev_flags_t) 4,
+	/* Flag for quirk use to store if quirk-specific ACS is enabled */
+	PCI_DEV_FLAGS_ACS_ENABLED_QUIRK = (__force pci_dev_flags_t) 8,
 };
 
 enum pci_irq_reroute_variant {
-- 
cgit v1.2.3


From 25a91d8d91911f84a03a039339b29537e7f1970d Mon Sep 17 00:00:00 2001
From: Fan Du <fan.du@windriver.com>
Date: Sat, 18 Jan 2014 09:54:23 +0800
Subject: skbuff: Introduce skb_to_sgvec_nomark to map skb without mark new end

As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given sglist
without mark the sg which contain last skb data as the end. So the caller can
mannipulate sg list as will when padding new data after the first call without
calling sg_unmark_end to expend sg list.

Signed-off-by: Fan Du <fan.du@windriver.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/linux/skbuff.h |  2 ++
 net/core/skbuff.c      | 26 ++++++++++++++++++++++++++
 2 files changed, 28 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index f589c9af8cbf..c574bf3bd6f6 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -691,6 +691,8 @@ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb,
 				     unsigned int headroom);
 struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom,
 				int newtailroom, gfp_t priority);
+int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg,
+			int offset, int len);
 int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset,
 		 int len);
 int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 5976ef0846bd..f28c37996aad 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3281,6 +3281,32 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
 	return elt;
 }
 
+/* As compared with skb_to_sgvec, skb_to_sgvec_nomark only map skb to given
+ * sglist without mark the sg which contain last skb data as the end.
+ * So the caller can mannipulate sg list as will when padding new data after
+ * the first call without calling sg_unmark_end to expend sg list.
+ *
+ * Scenario to use skb_to_sgvec_nomark:
+ * 1. sg_init_table
+ * 2. skb_to_sgvec_nomark(payload1)
+ * 3. skb_to_sgvec_nomark(payload2)
+ *
+ * This is equivalent to:
+ * 1. sg_init_table
+ * 2. skb_to_sgvec(payload1)
+ * 3. sg_unmark_end
+ * 4. skb_to_sgvec(payload2)
+ *
+ * When mapping mutilple payload conditionally, skb_to_sgvec_nomark
+ * is more preferable.
+ */
+int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg,
+			int offset, int len)
+{
+	return __skb_to_sgvec(skb, sg, offset, len);
+}
+EXPORT_SYMBOL_GPL(skb_to_sgvec_nomark);
+
 int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len)
 {
 	int nsg = __skb_to_sgvec(skb, sg, offset, len);
-- 
cgit v1.2.3


From 86bf4b68759141459864ebd36ac3038a9cda895b Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 12 Feb 2014 09:29:48 -0500
Subject: cgroup: warn if "xattr" is specified with "sane_behavior"

Mount option "xattr" is no longer necessary as it's enabled by default
on kernfs.  Warn if "xattr" is specified with "sane_behavior" so that
the option can be removed in the future.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h | 2 ++
 kernel/cgroup.c        | 3 +++
 2 files changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 0e45a932b823..305e94ee17f5 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -264,6 +264,8 @@ enum {
 	 * - "release_agent" and "notify_on_release" are removed.
 	 *   Replacement notification mechanism will be implemented.
 	 *
+	 * - "xattr" mount option is deprecated.  kernfs always enables it.
+	 *
 	 * - cpuset: tasks will be kept in empty cpusets when hotplug happens
 	 *   and take masks of ancestors with non-empty cpus/mems, instead of
 	 *   being moved to an ancestor.
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index cda614da40cf..a0fab71f200f 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1267,6 +1267,9 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 			pr_err("cgroup: sane_behavior: clone_children is not allowed\n");
 			return -EINVAL;
 		}
+
+		if (opts->flags & CGRP_ROOT_XATTR)
+			pr_warning("cgroup: sane_behavior: xattr is always available, flag unnecessary\n");
 	}
 
 	/*
-- 
cgit v1.2.3


From 0adb070426dde2fd0b84e7f4f5cefcd8f0b24410 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 12 Feb 2014 09:29:48 -0500
Subject: cgroup: remove cftype_set

cftype_set was added primarily to allow registering the same cftype
array more than once for different subsystems.  Nobody uses or needs
such thing and it's already broken because each cftype has ->ss
pointer which is initialized during registration.

Let's add list_head ->node to cftype and use the first cftype entry in
the array to link them instead of allocating separate cftype_set.
While at it, trigger WARN if cft seems previously initialized during
registration.

This simplifies cftype handling a bit.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h | 26 +++++++++-----------------
 kernel/cgroup.c        | 41 +++++++++++++----------------------------
 2 files changed, 22 insertions(+), 45 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 305e94ee17f5..b42251a23129 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -412,12 +412,11 @@ struct cftype {
 	unsigned int flags;
 
 	/*
-	 * The subsys this file belongs to.  Initialized automatically
-	 * during registration.  NULL for cgroup core files.
+	 * Fields used for internal bookkeeping.  Initialized automatically
+	 * during registration.
 	 */
-	struct cgroup_subsys *ss;
-
-	/* kernfs_ops to use, initialized automatically during registration */
+	struct cgroup_subsys *ss;	/* NULL for cgroup core files */
+	struct list_head node;		/* anchored at ss->cfts */
 	struct kernfs_ops *kf_ops;
 
 	/*
@@ -471,16 +470,6 @@ struct cftype {
 #endif
 };
 
-/*
- * cftype_sets describe cftypes belonging to a subsystem and are chained at
- * cgroup_subsys->cftsets.  Each cftset points to an array of cftypes
- * terminated by zero length name.
- */
-struct cftype_set {
-	struct list_head		node;	/* chained at subsys->cftsets */
-	struct cftype			*cfts;
-};
-
 /*
  * See the comment above CGRP_ROOT_SANE_BEHAVIOR for details.  This
  * function can be called as long as @cgrp is accessible.
@@ -597,8 +586,11 @@ struct cgroup_subsys {
 	/* link to parent, protected by cgroup_lock() */
 	struct cgroupfs_root *root;
 
-	/* list of cftype_sets */
-	struct list_head cftsets;
+	/*
+	 * List of cftypes.  Each entry is the first entry of an array
+	 * terminated by zero length name.
+	 */
+	struct list_head cfts;
 
 	/* base cftypes, automatically registered with subsys itself */
 	struct cftype *base_cftypes;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index a2cbd1549995..506ebd61d1c2 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1016,12 +1016,12 @@ static void cgroup_clear_dir(struct cgroup *cgrp, unsigned long subsys_mask)
 	int i;
 
 	for_each_subsys(ss, i) {
-		struct cftype_set *set;
+		struct cftype *cfts;
 
 		if (!test_bit(i, &subsys_mask))
 			continue;
-		list_for_each_entry(set, &ss->cftsets, node)
-			cgroup_addrm_files(cgrp, set->cfts, false);
+		list_for_each_entry(cfts, &ss->cfts, node)
+			cgroup_addrm_files(cgrp, cfts, false);
 	}
 }
 
@@ -2392,6 +2392,8 @@ static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
 	for (cft = cfts; cft->name[0] != '\0'; cft++) {
 		struct kernfs_ops *kf_ops;
 
+		WARN_ON(cft->ss || cft->kf_ops);
+
 		if (cft->seq_start)
 			kf_ops = &cgroup_kf_ops;
 		else
@@ -2430,26 +2432,15 @@ static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
  */
 int cgroup_rm_cftypes(struct cftype *cfts)
 {
-	struct cftype *found = NULL;
-	struct cftype_set *set;
-
 	if (!cfts || !cfts[0].ss)
 		return -ENOENT;
 
 	cgroup_cfts_prepare();
+	list_del(&cfts->node);
+	cgroup_cfts_commit(cfts, false);
 
-	list_for_each_entry(set, &cfts[0].ss->cftsets, node) {
-		if (set->cfts == cfts) {
-			list_del(&set->node);
-			kfree(set);
-			found = cfts;
-			break;
-		}
-	}
-
-	cgroup_cfts_commit(found, false);
 	cgroup_exit_cftypes(cfts);
-	return found ? 0 : -ENOENT;
+	return 0;
 }
 
 /**
@@ -2468,20 +2459,14 @@ int cgroup_rm_cftypes(struct cftype *cfts)
  */
 int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
 {
-	struct cftype_set *set;
 	int ret;
 
-	set = kzalloc(sizeof(*set), GFP_KERNEL);
-	if (!set)
-		return -ENOMEM;
-
 	ret = cgroup_init_cftypes(ss, cfts);
 	if (ret)
 		return ret;
 
 	cgroup_cfts_prepare();
-	set->cfts = cfts;
-	list_add_tail(&set->node, &ss->cftsets);
+	list_add_tail(&cfts->node, &ss->cfts);
 	ret = cgroup_cfts_commit(cfts, true);
 	if (ret)
 		cgroup_rm_cftypes(cfts);
@@ -3574,13 +3559,13 @@ static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask)
 
 	/* process cftsets of each subsystem */
 	for_each_subsys(ss, i) {
-		struct cftype_set *set;
+		struct cftype *cfts;
 
 		if (!test_bit(i, &subsys_mask))
 			continue;
 
-		list_for_each_entry(set, &ss->cftsets, node) {
-			ret = cgroup_addrm_files(cgrp, set->cfts, true);
+		list_for_each_entry(cfts, &ss->cfts, node) {
+			ret = cgroup_addrm_files(cgrp, cfts, true);
 			if (ret < 0)
 				goto err;
 		}
@@ -4169,7 +4154,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	mutex_lock(&cgroup_tree_mutex);
 	mutex_lock(&cgroup_mutex);
 
-	INIT_LIST_HEAD(&ss->cftsets);
+	INIT_LIST_HEAD(&ss->cfts);
 
 	/* Create the top cgroup state for this subsystem */
 	ss->root = &cgroup_dummy_root;
-- 
cgit v1.2.3


From e61734c55c24cdf11b07e52a74aec4dc4a7f4bd0 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 12 Feb 2014 09:29:50 -0500
Subject: cgroup: remove cgroup->name

cgroup->name handling became quite complicated over time involving
dedicated struct cgroup_name for RCU protection.  Now that cgroup is
on kernfs, we can drop all of it and simply use kernfs_name/path() and
friends.  Replace cgroup->name and all related code with kernfs
name/path constructs.

* Reimplement cgroup_name() and cgroup_path() as thin wrappers on top
  of kernfs counterparts, which involves semantic changes.
  pr_cont_cgroup_name() and pr_cont_cgroup_path() added.

* cgroup->name handling dropped from cgroup_rename().

* All users of cgroup_name/path() updated to the new semantics.  Users
  which were formatting the string just to printk them are converted
  to use pr_cont_cgroup_name/path() instead, which simplifies things
  quite a bit.  As cgroup_name() no longer requires RCU read lock
  around it, RCU lockings which were protecting only cgroup_name() are
  removed.

v2: Comment above oom_info_lock updated as suggested by Michal.

v3: dummy_top doesn't have a kn associated and
    pr_cont_cgroup_name/path() ended up calling the matching kernfs
    functions with NULL kn leading to oops.  Test for NULL kn and
    print "/" if so.  This issue was reported by Fengguang Wu.

v4: Rebased on top of 0ab02ca8f887 ("cgroup: protect modifications to
    cgroup_idr with cgroup_mutex").

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
---
 block/blk-cgroup.h     |  12 ++--
 fs/kernfs/dir.c        |   1 +
 include/linux/cgroup.h |  63 ++++++++++++---------
 kernel/cgroup.c        | 146 +++++++++++--------------------------------------
 kernel/cpuset.c        |  27 +++++----
 kernel/sched/debug.c   |   3 +-
 mm/memcontrol.c        |  68 ++++++-----------------
 7 files changed, 110 insertions(+), 210 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 453b528c8e19..15a8d640de57 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -241,12 +241,16 @@ static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd)
  */
 static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen)
 {
-	int ret;
+	char *p;
 
-	ret = cgroup_path(blkg->blkcg->css.cgroup, buf, buflen);
-	if (ret)
+	p = cgroup_path(blkg->blkcg->css.cgroup, buf, buflen);
+	if (!p) {
 		strncpy(buf, "<unavailable>", buflen);
-	return ret;
+		return -ENAMETOOLONG;
+	}
+
+	memmove(buf, p, buf + buflen - p);
+	return 0;
 }
 
 /**
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index a347792c2e5a..939684ebff1e 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -112,6 +112,7 @@ char *kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen)
 	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
 	return p;
 }
+EXPORT_SYMBOL_GPL(kernfs_path);
 
 /**
  * pr_cont_kernfs_name - pr_cont name of a kernfs_node
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index b42251a23129..4d6ff7d40cf6 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -138,11 +138,6 @@ enum {
 	CGRP_SANE_BEHAVIOR,
 };
 
-struct cgroup_name {
-	struct rcu_head rcu_head;
-	char name[];
-};
-
 struct cgroup {
 	unsigned long flags;		/* "unsigned long" so bitops work */
 
@@ -179,19 +174,6 @@ struct cgroup {
 	 */
 	u64 serial_nr;
 
-	/*
-	 * This is a copy of dentry->d_name, and it's needed because
-	 * we can't use dentry->d_name in cgroup_path().
-	 *
-	 * You must acquire rcu_read_lock() to access cgrp->name, and
-	 * the only place that can change it is rename(), which is
-	 * protected by parent dir's i_mutex.
-	 *
-	 * Normally you should use cgroup_name() wrapper rather than
-	 * access it directly.
-	 */
-	struct cgroup_name __rcu *name;
-
 	/* Private pointers for each registered subsystem */
 	struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT];
 
@@ -479,12 +461,6 @@ static inline bool cgroup_sane_behavior(const struct cgroup *cgrp)
 	return cgrp->root->flags & CGRP_ROOT_SANE_BEHAVIOR;
 }
 
-/* Caller should hold rcu_read_lock() */
-static inline const char *cgroup_name(const struct cgroup *cgrp)
-{
-	return rcu_dereference(cgrp->name)->name;
-}
-
 /* returns ino associated with a cgroup, 0 indicates unmounted root */
 static inline ino_t cgroup_ino(struct cgroup *cgrp)
 {
@@ -503,14 +479,47 @@ static inline struct cftype *seq_cft(struct seq_file *seq)
 
 struct cgroup_subsys_state *seq_css(struct seq_file *seq);
 
+/*
+ * Name / path handling functions.  All are thin wrappers around the kernfs
+ * counterparts and can be called under any context.
+ */
+
+static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen)
+{
+	return kernfs_name(cgrp->kn, buf, buflen);
+}
+
+static inline char * __must_check cgroup_path(struct cgroup *cgrp, char *buf,
+					      size_t buflen)
+{
+	return kernfs_path(cgrp->kn, buf, buflen);
+}
+
+static inline void pr_cont_cgroup_name(struct cgroup *cgrp)
+{
+	/* dummy_top doesn't have a kn associated */
+	if (cgrp->kn)
+		pr_cont_kernfs_name(cgrp->kn);
+	else
+		pr_cont("/");
+}
+
+static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
+{
+	/* dummy_top doesn't have a kn associated */
+	if (cgrp->kn)
+		pr_cont_kernfs_path(cgrp->kn);
+	else
+		pr_cont("/");
+}
+
+char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen);
+
 int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
 int cgroup_rm_cftypes(struct cftype *cfts);
 
 bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor);
 
-int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen);
-int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen);
-
 int cgroup_task_count(const struct cgroup *cgrp);
 
 /*
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 59dfb025f1ac..638df032fb94 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -145,8 +145,6 @@ static int cgroup_root_count;
 /* hierarchy ID allocation and mapping, protected by cgroup_mutex */
 static DEFINE_IDR(cgroup_hierarchy_idr);
 
-static struct cgroup_name root_cgroup_name = { .name = "/" };
-
 /*
  * Assign a monotonically increasing serial number to cgroups.  It
  * guarantees cgroups with bigger numbers are newer than those with smaller
@@ -888,17 +886,6 @@ static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask);
 static struct kernfs_syscall_ops cgroup_kf_syscall_ops;
 static const struct file_operations proc_cgroupstats_operations;
 
-static struct cgroup_name *cgroup_alloc_name(const char *name_str)
-{
-	struct cgroup_name *name;
-
-	name = kmalloc(sizeof(*name) + strlen(name_str) + 1, GFP_KERNEL);
-	if (!name)
-		return NULL;
-	strcpy(name->name, name_str);
-	return name;
-}
-
 static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft,
 			      char *buf)
 {
@@ -958,8 +945,6 @@ static void cgroup_free_fn(struct work_struct *work)
 	cgroup_pidlist_destroy_all(cgrp);
 
 	kernfs_put(cgrp->kn);
-
-	kfree(rcu_dereference_raw(cgrp->name));
 	kfree(cgrp);
 }
 
@@ -1377,7 +1362,6 @@ static void init_cgroup_root(struct cgroupfs_root *root)
 	INIT_LIST_HEAD(&root->root_list);
 	root->number_of_cgroups = 1;
 	cgrp->root = root;
-	RCU_INIT_POINTER(cgrp->name, &root_cgroup_name);
 	init_cgroup_housekeeping(cgrp);
 	idr_init(&root->cgroup_idr);
 }
@@ -1597,57 +1581,6 @@ static struct file_system_type cgroup_fs_type = {
 
 static struct kobject *cgroup_kobj;
 
-/**
- * cgroup_path - generate the path of a cgroup
- * @cgrp: the cgroup in question
- * @buf: the buffer to write the path into
- * @buflen: the length of the buffer
- *
- * Writes path of cgroup into buf.  Returns 0 on success, -errno on error.
- *
- * We can't generate cgroup path using dentry->d_name, as accessing
- * dentry->name must be protected by irq-unsafe dentry->d_lock or parent
- * inode's i_mutex, while on the other hand cgroup_path() can be called
- * with some irq-safe spinlocks held.
- */
-int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
-{
-	int ret = -ENAMETOOLONG;
-	char *start;
-
-	if (!cgrp->parent) {
-		if (strlcpy(buf, "/", buflen) >= buflen)
-			return -ENAMETOOLONG;
-		return 0;
-	}
-
-	start = buf + buflen - 1;
-	*start = '\0';
-
-	rcu_read_lock();
-	do {
-		const char *name = cgroup_name(cgrp);
-		int len;
-
-		len = strlen(name);
-		if ((start -= len) < buf)
-			goto out;
-		memcpy(start, name, len);
-
-		if (--start < buf)
-			goto out;
-		*start = '/';
-
-		cgrp = cgrp->parent;
-	} while (cgrp->parent);
-	ret = 0;
-	memmove(buf, start, buf + buflen - start);
-out:
-	rcu_read_unlock();
-	return ret;
-}
-EXPORT_SYMBOL_GPL(cgroup_path);
-
 /**
  * task_cgroup_path - cgroup path of a task in the first cgroup hierarchy
  * @task: target task
@@ -1659,16 +1592,14 @@ EXPORT_SYMBOL_GPL(cgroup_path);
  * function grabs cgroup_mutex and shouldn't be used inside locks used by
  * cgroup controller callbacks.
  *
- * Returns 0 on success, fails with -%ENAMETOOLONG if @buflen is too short.
+ * Return value is the same as kernfs_path().
  */
-int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
+char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
 {
 	struct cgroupfs_root *root;
 	struct cgroup *cgrp;
-	int hierarchy_id = 1, ret = 0;
-
-	if (buflen < 2)
-		return -ENAMETOOLONG;
+	int hierarchy_id = 1;
+	char *path = NULL;
 
 	mutex_lock(&cgroup_mutex);
 
@@ -1676,14 +1607,15 @@ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
 
 	if (root) {
 		cgrp = task_cgroup_from_root(task, root);
-		ret = cgroup_path(cgrp, buf, buflen);
+		path = cgroup_path(cgrp, buf, buflen);
 	} else {
 		/* if no hierarchy exists, everyone is in "/" */
-		memcpy(buf, "/", 2);
+		if (strlcpy(buf, "/", buflen) < buflen)
+			path = buf;
 	}
 
 	mutex_unlock(&cgroup_mutex);
-	return ret;
+	return path;
 }
 EXPORT_SYMBOL_GPL(task_cgroup_path);
 
@@ -2211,7 +2143,6 @@ static int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent,
 			 const char *new_name_str)
 {
 	struct cgroup *cgrp = kn->priv;
-	struct cgroup_name *name, *old_name;
 	int ret;
 
 	if (kernfs_type(kn) != KERNFS_DIR)
@@ -2226,25 +2157,13 @@ static int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent,
 	if (cgroup_sane_behavior(cgrp))
 		return -EPERM;
 
-	name = cgroup_alloc_name(new_name_str);
-	if (!name)
-		return -ENOMEM;
-
 	mutex_lock(&cgroup_tree_mutex);
 	mutex_lock(&cgroup_mutex);
 
 	ret = kernfs_rename(kn, new_parent, new_name_str);
-	if (!ret) {
-		old_name = rcu_dereference_protected(cgrp->name, true);
-		rcu_assign_pointer(cgrp->name, name);
-	} else {
-		old_name = name;
-	}
 
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&cgroup_tree_mutex);
-
-	kfree_rcu(old_name, rcu_head);
 	return ret;
 }
 
@@ -3719,14 +3638,13 @@ err_free:
 /**
  * cgroup_create - create a cgroup
  * @parent: cgroup that will be parent of the new cgroup
- * @name_str: name of the new cgroup
+ * @name: name of the new cgroup
  * @mode: mode to set on new cgroup
  */
-static long cgroup_create(struct cgroup *parent, const char *name_str,
+static long cgroup_create(struct cgroup *parent, const char *name,
 			  umode_t mode)
 {
 	struct cgroup *cgrp;
-	struct cgroup_name *name;
 	struct cgroupfs_root *root = parent->root;
 	int ssid, err;
 	struct cgroup_subsys *ss;
@@ -3737,13 +3655,6 @@ static long cgroup_create(struct cgroup *parent, const char *name_str,
 	if (!cgrp)
 		return -ENOMEM;
 
-	name = cgroup_alloc_name(name_str);
-	if (!name) {
-		err = -ENOMEM;
-		goto err_free_cgrp;
-	}
-	rcu_assign_pointer(cgrp->name, name);
-
 	mutex_lock(&cgroup_tree_mutex);
 
 	/*
@@ -3781,7 +3692,7 @@ static long cgroup_create(struct cgroup *parent, const char *name_str,
 		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags);
 
 	/* create the directory */
-	kn = kernfs_create_dir(parent->kn, name->name, mode, cgrp);
+	kn = kernfs_create_dir(parent->kn, name, mode, cgrp);
 	if (IS_ERR(kn)) {
 		err = PTR_ERR(kn);
 		goto err_free_id;
@@ -3839,8 +3750,6 @@ err_unlock:
 	mutex_unlock(&cgroup_mutex);
 err_unlock_tree:
 	mutex_unlock(&cgroup_tree_mutex);
-	kfree(rcu_dereference_raw(cgrp->name));
-err_free_cgrp:
 	kfree(cgrp);
 	return err;
 
@@ -4304,12 +4213,12 @@ int proc_cgroup_show(struct seq_file *m, void *v)
 {
 	struct pid *pid;
 	struct task_struct *tsk;
-	char *buf;
+	char *buf, *path;
 	int retval;
 	struct cgroupfs_root *root;
 
 	retval = -ENOMEM;
-	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	buf = kmalloc(PATH_MAX, GFP_KERNEL);
 	if (!buf)
 		goto out;
 
@@ -4337,10 +4246,12 @@ int proc_cgroup_show(struct seq_file *m, void *v)
 				   root->name);
 		seq_putc(m, ':');
 		cgrp = task_cgroup_from_root(tsk, root);
-		retval = cgroup_path(cgrp, buf, PAGE_SIZE);
-		if (retval < 0)
+		path = cgroup_path(cgrp, buf, PATH_MAX);
+		if (!path) {
+			retval = -ENAMETOOLONG;
 			goto out_unlock;
-		seq_puts(m, buf);
+		}
+		seq_puts(m, path);
 		seq_putc(m, '\n');
 	}
 
@@ -4588,16 +4499,17 @@ static void cgroup_release_agent(struct work_struct *work)
 	while (!list_empty(&release_list)) {
 		char *argv[3], *envp[3];
 		int i;
-		char *pathbuf = NULL, *agentbuf = NULL;
+		char *pathbuf = NULL, *agentbuf = NULL, *path;
 		struct cgroup *cgrp = list_entry(release_list.next,
 						    struct cgroup,
 						    release_list);
 		list_del_init(&cgrp->release_list);
 		raw_spin_unlock(&release_list_lock);
-		pathbuf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+		pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
 		if (!pathbuf)
 			goto continue_free;
-		if (cgroup_path(cgrp, pathbuf, PAGE_SIZE) < 0)
+		path = cgroup_path(cgrp, pathbuf, PATH_MAX);
+		if (!path)
 			goto continue_free;
 		agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
 		if (!agentbuf)
@@ -4605,7 +4517,7 @@ static void cgroup_release_agent(struct work_struct *work)
 
 		i = 0;
 		argv[i++] = agentbuf;
-		argv[i++] = pathbuf;
+		argv[i++] = path;
 		argv[i] = NULL;
 
 		i = 0;
@@ -4755,6 +4667,11 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
 {
 	struct cgrp_cset_link *link;
 	struct css_set *cset;
+	char *name_buf;
+
+	name_buf = kmalloc(NAME_MAX + 1, GFP_KERNEL);
+	if (!name_buf)
+		return -ENOMEM;
 
 	read_lock(&css_set_lock);
 	rcu_read_lock();
@@ -4763,14 +4680,17 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
 		struct cgroup *c = link->cgrp;
 		const char *name = "?";
 
-		if (c != cgroup_dummy_top)
-			name = cgroup_name(c);
+		if (c != cgroup_dummy_top) {
+			cgroup_name(c, name_buf, NAME_MAX + 1);
+			name = name_buf;
+		}
 
 		seq_printf(seq, "Root %d group %s\n",
 			   c->root->hierarchy_id, name);
 	}
 	rcu_read_unlock();
 	read_unlock(&css_set_lock);
+	kfree(name_buf);
 	return 0;
 }
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 2d018c795fea..e97a6e88d036 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2088,10 +2088,9 @@ static void remove_tasks_in_empty_cpuset(struct cpuset *cs)
 		parent = parent_cs(parent);
 
 	if (cgroup_transfer_tasks(parent->css.cgroup, cs->css.cgroup)) {
-		rcu_read_lock();
-		printk(KERN_ERR "cpuset: failed to transfer tasks out of empty cpuset %s\n",
-		       cgroup_name(cs->css.cgroup));
-		rcu_read_unlock();
+		printk(KERN_ERR "cpuset: failed to transfer tasks out of empty cpuset ");
+		pr_cont_cgroup_name(cs->css.cgroup);
+		pr_cont("\n");
 	}
 }
 
@@ -2619,19 +2618,17 @@ void cpuset_print_task_mems_allowed(struct task_struct *tsk)
 	 /* Statically allocated to prevent using excess stack. */
 	static char cpuset_nodelist[CPUSET_NODELIST_LEN];
 	static DEFINE_SPINLOCK(cpuset_buffer_lock);
-
 	struct cgroup *cgrp = task_cs(tsk)->css.cgroup;
 
-	rcu_read_lock();
 	spin_lock(&cpuset_buffer_lock);
 
 	nodelist_scnprintf(cpuset_nodelist, CPUSET_NODELIST_LEN,
 			   tsk->mems_allowed);
-	printk(KERN_INFO "%s cpuset=%s mems_allowed=%s\n",
-	       tsk->comm, cgroup_name(cgrp), cpuset_nodelist);
+	printk(KERN_INFO "%s cpuset=", tsk->comm);
+	pr_cont_cgroup_name(cgrp);
+	pr_cont(" mems_allowed=%s\n", cpuset_nodelist);
 
 	spin_unlock(&cpuset_buffer_lock);
-	rcu_read_unlock();
 }
 
 /*
@@ -2681,12 +2678,12 @@ int proc_cpuset_show(struct seq_file *m, void *unused_v)
 {
 	struct pid *pid;
 	struct task_struct *tsk;
-	char *buf;
+	char *buf, *p;
 	struct cgroup_subsys_state *css;
 	int retval;
 
 	retval = -ENOMEM;
-	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	buf = kmalloc(PATH_MAX, GFP_KERNEL);
 	if (!buf)
 		goto out;
 
@@ -2696,14 +2693,16 @@ int proc_cpuset_show(struct seq_file *m, void *unused_v)
 	if (!tsk)
 		goto out_free;
 
+	retval = -ENAMETOOLONG;
 	rcu_read_lock();
 	css = task_css(tsk, cpuset_cgrp_id);
-	retval = cgroup_path(css->cgroup, buf, PAGE_SIZE);
+	p = cgroup_path(css->cgroup, buf, PATH_MAX);
 	rcu_read_unlock();
-	if (retval < 0)
+	if (!p)
 		goto out_put_task;
-	seq_puts(m, buf);
+	seq_puts(m, p);
 	seq_putc(m, '\n');
+	retval = 0;
 out_put_task:
 	put_task_struct(tsk);
 out_free:
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index dd52e7ffb10e..30eee3b5293d 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -111,8 +111,7 @@ static char *task_group_path(struct task_group *tg)
 	if (autogroup_path(tg, group_path, PATH_MAX))
 		return group_path;
 
-	cgroup_path(tg->css.cgroup, group_path, PATH_MAX);
-	return group_path;
+	return cgroup_path(tg->css.cgroup, group_path, PATH_MAX);
 }
 #endif
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 102ab48ffa13..c1c25494f7ae 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1683,15 +1683,8 @@ static void move_unlock_mem_cgroup(struct mem_cgroup *memcg,
  */
 void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 {
-	/*
-	 * protects memcg_name and makes sure that parallel ooms do not
-	 * interleave
-	 */
+	/* oom_info_lock ensures that parallel ooms do not interleave */
 	static DEFINE_SPINLOCK(oom_info_lock);
-	struct cgroup *task_cgrp;
-	struct cgroup *mem_cgrp;
-	static char memcg_name[PATH_MAX];
-	int ret;
 	struct mem_cgroup *iter;
 	unsigned int i;
 
@@ -1701,36 +1694,14 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 	spin_lock(&oom_info_lock);
 	rcu_read_lock();
 
-	mem_cgrp = memcg->css.cgroup;
-	task_cgrp = task_cgroup(p, memory_cgrp_id);
+	pr_info("Task in ");
+	pr_cont_cgroup_path(task_cgroup(p, memory_cgrp_id));
+	pr_info(" killed as a result of limit of ");
+	pr_cont_cgroup_path(memcg->css.cgroup);
+	pr_info("\n");
 
-	ret = cgroup_path(task_cgrp, memcg_name, PATH_MAX);
-	if (ret < 0) {
-		/*
-		 * Unfortunately, we are unable to convert to a useful name
-		 * But we'll still print out the usage information
-		 */
-		rcu_read_unlock();
-		goto done;
-	}
 	rcu_read_unlock();
 
-	pr_info("Task in %s killed", memcg_name);
-
-	rcu_read_lock();
-	ret = cgroup_path(mem_cgrp, memcg_name, PATH_MAX);
-	if (ret < 0) {
-		rcu_read_unlock();
-		goto done;
-	}
-	rcu_read_unlock();
-
-	/*
-	 * Continues from above, so we don't need an KERN_ level
-	 */
-	pr_cont(" as a result of limit of %s\n", memcg_name);
-done:
-
 	pr_info("memory: usage %llukB, limit %llukB, failcnt %llu\n",
 		res_counter_read_u64(&memcg->res, RES_USAGE) >> 10,
 		res_counter_read_u64(&memcg->res, RES_LIMIT) >> 10,
@@ -1745,13 +1716,8 @@ done:
 		res_counter_read_u64(&memcg->kmem, RES_FAILCNT));
 
 	for_each_mem_cgroup_tree(iter, memcg) {
-		pr_info("Memory cgroup stats");
-
-		rcu_read_lock();
-		ret = cgroup_path(iter->css.cgroup, memcg_name, PATH_MAX);
-		if (!ret)
-			pr_cont(" for %s", memcg_name);
-		rcu_read_unlock();
+		pr_info("Memory cgroup stats for ");
+		pr_cont_cgroup_path(iter->css.cgroup);
 		pr_cont(":");
 
 		for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
@@ -3401,7 +3367,7 @@ static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
 						  struct kmem_cache *s)
 {
 	struct kmem_cache *new = NULL;
-	static char *tmp_name = NULL;
+	static char *tmp_path = NULL, *tmp_name = NULL;
 	static DEFINE_MUTEX(mutex);	/* protects tmp_name */
 
 	BUG_ON(!memcg_can_account_kmem(memcg));
@@ -3413,18 +3379,20 @@ static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
 	 * This static temporary buffer is used to prevent from
 	 * pointless shortliving allocation.
 	 */
-	if (!tmp_name) {
-		tmp_name = kmalloc(PATH_MAX, GFP_KERNEL);
+	if (!tmp_path || !tmp_name) {
+		if (!tmp_path)
+			tmp_path = kmalloc(PATH_MAX, GFP_KERNEL);
 		if (!tmp_name)
+			tmp_name = kmalloc(NAME_MAX + 1, GFP_KERNEL);
+		if (!tmp_path || !tmp_name)
 			goto out;
 	}
 
-	rcu_read_lock();
-	snprintf(tmp_name, PATH_MAX, "%s(%d:%s)", s->name,
-			 memcg_cache_id(memcg), cgroup_name(memcg->css.cgroup));
-	rcu_read_unlock();
+	cgroup_name(memcg->css.cgroup, tmp_name, NAME_MAX + 1);
+	snprintf(tmp_path, PATH_MAX, "%s(%d:%s)", s->name,
+		 memcg_cache_id(memcg), tmp_name);
 
-	new = kmem_cache_create_memcg(memcg, tmp_name, s->object_size, s->align,
+	new = kmem_cache_create_memcg(memcg, tmp_path, s->object_size, s->align,
 				      (s->flags & ~SLAB_PANIC), s->ctor, s);
 	if (new)
 		new->allocflags |= __GFP_KMEMCG;
-- 
cgit v1.2.3


From 3c9c825b8b50de7dbb015e6bfc04bb2da79364d9 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 12 Feb 2014 09:29:50 -0500
Subject: cgroup: rename cgroupfs_root->number_of_cgroups to ->nr_cgrps and
 make it atomic_t

root->number_of_cgroups is currently an integer protected with
cgroup_mutex.  Except for sanity checks and proc reporting, the only
place it's used is to check whether the root has any child during
remount; however, this is a bit flawed as the counter is not
decremented when the cgroup is unlinked but when it's released,
meaning that there could be an extended period where all cgroups are
removed but remount is still not allowed because some internal objects
are lingering.  While not perfect either, it'd be better to use
emptiness test on root->top_cgroup.children.

This patch updates cgroup_remount() to test top_cgroup's children
instead, which makes number_of_cgroups only actual usage statistics
printing in proc implemented in proc_cgroupstats_show().  Let's
shorten its name and make it an atomic_t so that we don't have to
worry about its synchronization.  It's purely auxiliary at this point.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h |  4 ++--
 kernel/cgroup.c        | 16 +++++++---------
 2 files changed, 9 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 4d6ff7d40cf6..f0e6105bbbc1 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -290,8 +290,8 @@ struct cgroupfs_root {
 	/* The root cgroup for this hierarchy */
 	struct cgroup top_cgroup;
 
-	/* Tracks how many cgroups are currently defined in hierarchy.*/
-	int number_of_cgroups;
+	/* Number of cgroups in the hierarchy, used only for /proc/cgroups */
+	atomic_t nr_cgrps;
 
 	/* A list running through the active hierarchies */
 	struct list_head root_list;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 638df032fb94..cffdb6e2ad08 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -758,7 +758,7 @@ static void cgroup_put_root(struct cgroupfs_root *root)
 	}
 	mutex_lock(&cgroup_mutex);
 
-	BUG_ON(root->number_of_cgroups != 1);
+	BUG_ON(atomic_read(&root->nr_cgrps) != 1);
 	BUG_ON(!list_empty(&cgrp->children));
 
 	/* Rebind all subsystems back to the default hierarchy */
@@ -928,9 +928,7 @@ static void cgroup_free_fn(struct work_struct *work)
 {
 	struct cgroup *cgrp = container_of(work, struct cgroup, destroy_work);
 
-	mutex_lock(&cgroup_mutex);
-	cgrp->root->number_of_cgroups--;
-	mutex_unlock(&cgroup_mutex);
+	atomic_dec(&cgrp->root->nr_cgrps);
 
 	/*
 	 * We get a ref to the parent, and put the ref when this cgroup is
@@ -1320,7 +1318,7 @@ static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
 	}
 
 	/* remounting is not allowed for populated hierarchies */
-	if (root->number_of_cgroups > 1) {
+	if (!list_empty(&root->top_cgroup.children)) {
 		ret = -EBUSY;
 		goto out_unlock;
 	}
@@ -1360,7 +1358,7 @@ static void init_cgroup_root(struct cgroupfs_root *root)
 
 	atomic_set(&root->refcnt, 1);
 	INIT_LIST_HEAD(&root->root_list);
-	root->number_of_cgroups = 1;
+	atomic_set(&root->nr_cgrps, 1);
 	cgrp->root = root;
 	init_cgroup_housekeeping(cgrp);
 	idr_init(&root->cgroup_idr);
@@ -1463,7 +1461,7 @@ static int cgroup_setup_root(struct cgroupfs_root *root)
 	write_unlock(&css_set_lock);
 
 	BUG_ON(!list_empty(&root_cgrp->children));
-	BUG_ON(root->number_of_cgroups != 1);
+	BUG_ON(atomic_read(&root->nr_cgrps) != 1);
 
 	kernfs_activate(root_cgrp->kn);
 	ret = 0;
@@ -3709,7 +3707,7 @@ static long cgroup_create(struct cgroup *parent, const char *name,
 
 	/* allocation complete, commit to creation */
 	list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children);
-	root->number_of_cgroups++;
+	atomic_inc(&root->nr_cgrps);
 
 	/*
 	 * Grab a reference on the root and parent so that they don't get
@@ -4281,7 +4279,7 @@ static int proc_cgroupstats_show(struct seq_file *m, void *v)
 	for_each_subsys(ss, i)
 		seq_printf(m, "%s\t%d\t%d\t%d\n",
 			   ss->name, ss->root->hierarchy_id,
-			   ss->root->number_of_cgroups, !ss->disabled);
+			   atomic_read(&ss->root->nr_cgrps), !ss->disabled);
 
 	mutex_unlock(&cgroup_mutex);
 	return 0;
-- 
cgit v1.2.3


From 776f02fa4e1ad70557c0318c70ce928e0642bee0 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 12 Feb 2014 09:29:50 -0500
Subject: cgroup: remove cgroupfs_root->refcnt

Currently, cgroupfs_root and its ->top_cgroup are separated reference
counted and the latter's is ignored.  There's no reason to do this
separately.  This patch removes cgroupfs_root->refcnt and destroys
cgroupfs_root when the top_cgroup is released.

* cgroup_put() updated to ignore cgroup_is_dead() test for top
  cgroups.  cgroup_free_fn() updated to handle root destruction when
  releasing a top cgroup.

* As root destruction is now bounced through cgroup destruction, it is
  asynchronous.  Update cgroup_mount() so that it waits for pending
  release which is currently implemented using msleep().  Converting
  this to proper wait_queue isn't hard but likely unnecessary.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h |  4 +--
 kernel/cgroup.c        | 86 ++++++++++++++++++++++----------------------------
 2 files changed, 39 insertions(+), 51 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index f0e6105bbbc1..298d616e8f40 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -282,12 +282,10 @@ struct cgroupfs_root {
 	/* The bitmask of subsystems attached to this hierarchy */
 	unsigned long subsys_mask;
 
-	atomic_t refcnt;
-
 	/* Unique id for this hierarchy. */
 	int hierarchy_id;
 
-	/* The root cgroup for this hierarchy */
+	/* The root cgroup.  Root is destroyed on its release. */
 	struct cgroup top_cgroup;
 
 	/* Number of cgroups in the hierarchy, used only for /proc/cgroups */
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index cffdb6e2ad08..03845c5d082b 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -53,6 +53,7 @@
 #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
 #include <linux/flex_array.h> /* used in cgroup_attach_task */
 #include <linux/kthread.h>
+#include <linux/delay.h>
 
 #include <linux/atomic.h>
 
@@ -728,37 +729,16 @@ static void cgroup_free_root(struct cgroupfs_root *root)
 	}
 }
 
-static void cgroup_get_root(struct cgroupfs_root *root)
-{
-	/*
-	 * The caller must ensure that @root is alive, which can be
-	 * achieved by holding a ref on one of the member cgroups or
-	 * following a registered reference to @root while holding
-	 * cgroup_tree_mutex.
-	 */
-	WARN_ON_ONCE(atomic_read(&root->refcnt) <= 0);
-	atomic_inc(&root->refcnt);
-}
-
-static void cgroup_put_root(struct cgroupfs_root *root)
+static void cgroup_destroy_root(struct cgroupfs_root *root)
 {
 	struct cgroup *cgrp = &root->top_cgroup;
 	struct cgrp_cset_link *link, *tmp_link;
 	int ret;
 
-	/*
-	 * @root's refcnt reaching zero and its deregistration should be
-	 * atomic w.r.t. cgroup_tree_mutex.  This ensures that
-	 * cgroup_get_root() is safe to invoke if @root is registered.
-	 */
 	mutex_lock(&cgroup_tree_mutex);
-	if (!atomic_dec_and_test(&root->refcnt)) {
-		mutex_unlock(&cgroup_tree_mutex);
-		return;
-	}
 	mutex_lock(&cgroup_mutex);
 
-	BUG_ON(atomic_read(&root->nr_cgrps) != 1);
+	BUG_ON(atomic_read(&root->nr_cgrps));
 	BUG_ON(!list_empty(&cgrp->children));
 
 	/* Rebind all subsystems back to the default hierarchy */
@@ -929,21 +909,24 @@ static void cgroup_free_fn(struct work_struct *work)
 	struct cgroup *cgrp = container_of(work, struct cgroup, destroy_work);
 
 	atomic_dec(&cgrp->root->nr_cgrps);
-
-	/*
-	 * We get a ref to the parent, and put the ref when this cgroup is
-	 * being freed, so it's guaranteed that the parent won't be
-	 * destroyed before its children.
-	 */
-	cgroup_put(cgrp->parent);
-
-	/* put the root reference that we took when we created the cgroup */
-	cgroup_put_root(cgrp->root);
-
 	cgroup_pidlist_destroy_all(cgrp);
 
-	kernfs_put(cgrp->kn);
-	kfree(cgrp);
+	if (cgrp->parent) {
+		/*
+		 * We get a ref to the parent, and put the ref when this
+		 * cgroup is being freed, so it's guaranteed that the
+		 * parent won't be destroyed before its children.
+		 */
+		cgroup_put(cgrp->parent);
+		kernfs_put(cgrp->kn);
+		kfree(cgrp);
+	} else {
+		/*
+		 * This is top cgroup's refcnt reaching zero, which
+		 * indicates that the root should be released.
+		 */
+		cgroup_destroy_root(cgrp->root);
+	}
 }
 
 static void cgroup_free_rcu(struct rcu_head *head)
@@ -965,7 +948,7 @@ static void cgroup_put(struct cgroup *cgrp)
 {
 	if (!atomic_dec_and_test(&cgrp->refcnt))
 		return;
-	if (WARN_ON_ONCE(!cgroup_is_dead(cgrp)))
+	if (WARN_ON_ONCE(cgrp->parent && !cgroup_is_dead(cgrp)))
 		return;
 
 	/*
@@ -1356,7 +1339,6 @@ static void init_cgroup_root(struct cgroupfs_root *root)
 {
 	struct cgroup *cgrp = &root->top_cgroup;
 
-	atomic_set(&root->refcnt, 1);
 	INIT_LIST_HEAD(&root->root_list);
 	atomic_set(&root->nr_cgrps, 1);
 	cgrp->root = root;
@@ -1485,7 +1467,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 	struct cgroup_sb_opts opts;
 	struct dentry *dentry;
 	int ret;
-
+retry:
 	mutex_lock(&cgroup_tree_mutex);
 	mutex_lock(&cgroup_mutex);
 
@@ -1531,7 +1513,21 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 			}
 		}
 
-		cgroup_get_root(root);
+		/*
+		 * A root's lifetime is governed by its top cgroup.  Zero
+		 * ref indicate that the root is being destroyed.  Wait for
+		 * destruction to complete so that the subsystems are free.
+		 * We can use wait_queue for the wait but this path is
+		 * super cold.  Let's just sleep for a bit and retry.
+		 */
+		if (!atomic_inc_not_zero(&root->top_cgroup.refcnt)) {
+			mutex_unlock(&cgroup_mutex);
+			mutex_unlock(&cgroup_tree_mutex);
+			msleep(10);
+			goto retry;
+		}
+
+		ret = 0;
 		goto out_unlock;
 	}
 
@@ -1558,7 +1554,7 @@ out_unlock:
 
 	dentry = kernfs_mount(fs_type, flags, root->kf_root);
 	if (IS_ERR(dentry))
-		cgroup_put_root(root);
+		cgroup_put(&root->top_cgroup);
 	return dentry;
 }
 
@@ -1567,7 +1563,7 @@ static void cgroup_kill_sb(struct super_block *sb)
 	struct kernfs_root *kf_root = kernfs_root_from_sb(sb);
 	struct cgroupfs_root *root = cgroup_root_from_kf(kf_root);
 
-	cgroup_put_root(root);
+	cgroup_put(&root->top_cgroup);
 	kernfs_kill_sb(sb);
 }
 
@@ -3708,12 +3704,6 @@ static long cgroup_create(struct cgroup *parent, const char *name,
 	/* allocation complete, commit to creation */
 	list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children);
 	atomic_inc(&root->nr_cgrps);
-
-	/*
-	 * Grab a reference on the root and parent so that they don't get
-	 * deleted while there are child cgroups.
-	 */
-	cgroup_get_root(root);
 	cgroup_get(parent);
 
 	/*
-- 
cgit v1.2.3


From ad54a0cfbeb4bd4033d09017557ccbc423f9d5ff Mon Sep 17 00:00:00 2001
From: Heiko Stuebner <heiko.stuebner@bqreaders.com>
Date: Wed, 12 Feb 2014 01:00:34 +0100
Subject: of: add functions to count number of elements in a property

The need to know the number of array elements in a property is
a common pattern. To prevent duplication of open-coded implementations
add a helper static function that also centralises strict sanity
checking and DTB format details, as well as a set of wrapper functions
for u8, u16, u32 and u64.

Suggested-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Heiko Stuebner <heiko.stuebner@bqreaders.com>
Acked-by: Rob Herring <robh@kernel.org>
Acked-by: Grant Likely <grant.likely@linaro.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/of/base.c  | 32 +++++++++++++++++++++++
 include/linux/of.h | 76 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 108 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/of/base.c b/drivers/of/base.c
index ff85450d5683..8a2a55c65e5d 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -885,6 +885,38 @@ struct device_node *of_find_node_by_phandle(phandle handle)
 }
 EXPORT_SYMBOL(of_find_node_by_phandle);
 
+/**
+ * of_property_count_elems_of_size - Count the number of elements in a property
+ *
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ * @elem_size:	size of the individual element
+ *
+ * Search for a property in a device node and count the number of elements of
+ * size elem_size in it. Returns number of elements on sucess, -EINVAL if the
+ * property does not exist or its length does not match a multiple of elem_size
+ * and -ENODATA if the property does not have a value.
+ */
+int of_property_count_elems_of_size(const struct device_node *np,
+				const char *propname, int elem_size)
+{
+	struct property *prop = of_find_property(np, propname, NULL);
+
+	if (!prop)
+		return -EINVAL;
+	if (!prop->value)
+		return -ENODATA;
+
+	if (prop->length % elem_size != 0) {
+		pr_err("size of %s in node %s is not a multiple of %d\n",
+		       propname, np->full_name, elem_size);
+		return -EINVAL;
+	}
+
+	return prop->length / elem_size;
+}
+EXPORT_SYMBOL_GPL(of_property_count_elems_of_size);
+
 /**
  * of_find_property_value_of_size
  *
diff --git a/include/linux/of.h b/include/linux/of.h
index 70c64ba17fa5..b59f2e41c7ce 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -250,6 +250,8 @@ extern struct device_node *of_find_node_with_property(
 extern struct property *of_find_property(const struct device_node *np,
 					 const char *name,
 					 int *lenp);
+extern int of_property_count_elems_of_size(const struct device_node *np,
+				const char *propname, int elem_size);
 extern int of_property_read_u32_index(const struct device_node *np,
 				       const char *propname,
 				       u32 index, u32 *out_value);
@@ -431,6 +433,12 @@ static inline struct device_node *of_find_compatible_node(
 	return NULL;
 }
 
+static inline int of_property_count_elems_of_size(const struct device_node *np,
+			const char *propname, int elem_size)
+{
+	return -ENOSYS;
+}
+
 static inline int of_property_read_u32_index(const struct device_node *np,
 			const char *propname, u32 index, u32 *out_value)
 {
@@ -569,6 +577,74 @@ extern int of_node_to_nid(struct device_node *np);
 static inline int of_node_to_nid(struct device_node *device) { return 0; }
 #endif
 
+/**
+ * of_property_count_u8_elems - Count the number of u8 elements in a property
+ *
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ *
+ * Search for a property in a device node and count the number of u8 elements
+ * in it. Returns number of elements on sucess, -EINVAL if the property does
+ * not exist or its length does not match a multiple of u8 and -ENODATA if the
+ * property does not have a value.
+ */
+static inline int of_property_count_u8_elems(const struct device_node *np,
+				const char *propname)
+{
+	return of_property_count_elems_of_size(np, propname, sizeof(u8));
+}
+
+/**
+ * of_property_count_u16_elems - Count the number of u16 elements in a property
+ *
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ *
+ * Search for a property in a device node and count the number of u16 elements
+ * in it. Returns number of elements on sucess, -EINVAL if the property does
+ * not exist or its length does not match a multiple of u16 and -ENODATA if the
+ * property does not have a value.
+ */
+static inline int of_property_count_u16_elems(const struct device_node *np,
+				const char *propname)
+{
+	return of_property_count_elems_of_size(np, propname, sizeof(u16));
+}
+
+/**
+ * of_property_count_u32_elems - Count the number of u32 elements in a property
+ *
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ *
+ * Search for a property in a device node and count the number of u32 elements
+ * in it. Returns number of elements on sucess, -EINVAL if the property does
+ * not exist or its length does not match a multiple of u32 and -ENODATA if the
+ * property does not have a value.
+ */
+static inline int of_property_count_u32_elems(const struct device_node *np,
+				const char *propname)
+{
+	return of_property_count_elems_of_size(np, propname, sizeof(u32));
+}
+
+/**
+ * of_property_count_u64_elems - Count the number of u64 elements in a property
+ *
+ * @np:		device node from which the property value is to be read.
+ * @propname:	name of the property to be searched.
+ *
+ * Search for a property in a device node and count the number of u64 elements
+ * in it. Returns number of elements on sucess, -EINVAL if the property does
+ * not exist or its length does not match a multiple of u64 and -ENODATA if the
+ * property does not have a value.
+ */
+static inline int of_property_count_u64_elems(const struct device_node *np,
+				const char *propname)
+{
+	return of_property_count_elems_of_size(np, propname, sizeof(u64));
+}
+
 /**
  * of_property_read_bool - Findfrom a property
  * @np:		device node from which the property value is to be read.
-- 
cgit v1.2.3


From bb1e88ccb771492ac908ac295ec135efa1d53093 Mon Sep 17 00:00:00 2001
From: Alexandre Courbot <acourbot@nvidia.com>
Date: Sun, 9 Feb 2014 17:43:54 +0900
Subject: gpiolib: add gpiochip_get_desc() driver function

Some drivers dealing with a gpio_chip might need to act on its
descriptors directly; one example is pinctrl drivers that need to lock a
GPIO for being used as IRQ using gpiod_lock_as_irq().

This patch exports a gpiochip_get_desc() function that returns the
GPIO descriptor at the requested index. It also sweeps the
gpio_to_chip() function out of the consumer interface since any holder
of a gpio_chip reference can manipulate its GPIOs way beyond what a
consumer should be allowed to do.

As a result, gpio_chip is not visible anymore to simple GPIO consumers.

Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Reviewed-by: Jean-Jacques Hiblot <jjhiblot@traphandler.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.c        | 17 +++++++++--------
 include/linux/gpio/consumer.h |  8 --------
 include/linux/gpio/driver.h   | 18 ++++++++++++++++++
 3 files changed, 27 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 9b241bcb5107..9cd7082cca08 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -164,16 +164,17 @@ struct gpio_desc *gpio_to_desc(unsigned gpio)
 EXPORT_SYMBOL_GPL(gpio_to_desc);
 
 /**
- * Convert an offset on a certain chip to a corresponding descriptor
+ * Get the GPIO descriptor corresponding to the given hw number for this chip.
  */
-static struct gpio_desc *gpiochip_offset_to_desc(struct gpio_chip *chip,
-						 unsigned int offset)
+struct gpio_desc *gpiochip_get_desc(struct gpio_chip *chip,
+				    u16 hwnum)
 {
-	if (offset >= chip->ngpio)
+	if (hwnum >= chip->ngpio)
 		return ERR_PTR(-EINVAL);
 
-	return &chip->desc[offset];
+	return &chip->desc[hwnum];
 }
+EXPORT_SYMBOL_GPL(gpiochip_get_desc);
 
 /**
  * Convert a GPIO descriptor to the integer namespace.
@@ -2190,7 +2191,7 @@ EXPORT_SYMBOL_GPL(gpiod_lock_as_irq);
 
 int gpio_lock_as_irq(struct gpio_chip *chip, unsigned int offset)
 {
-	return gpiod_lock_as_irq(gpiochip_offset_to_desc(chip, offset));
+	return gpiod_lock_as_irq(gpiochip_get_desc(chip, offset));
 }
 EXPORT_SYMBOL_GPL(gpio_lock_as_irq);
 
@@ -2212,7 +2213,7 @@ EXPORT_SYMBOL_GPL(gpiod_unlock_as_irq);
 
 void gpio_unlock_as_irq(struct gpio_chip *chip, unsigned int offset)
 {
-	return gpiod_unlock_as_irq(gpiochip_offset_to_desc(chip, offset));
+	return gpiod_unlock_as_irq(gpiochip_get_desc(chip, offset));
 }
 EXPORT_SYMBOL_GPL(gpio_unlock_as_irq);
 
@@ -2433,7 +2434,7 @@ static struct gpio_desc *gpiod_find(struct device *dev, const char *con_id,
 			return ERR_PTR(-EINVAL);
 		}
 
-		desc = gpiochip_offset_to_desc(chip, p->chip_hwnum);
+		desc = gpiochip_get_desc(chip, p->chip_hwnum);
 		*flags = p->flags;
 
 		return desc;
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index 387994325122..dccda505ba7c 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -7,7 +7,6 @@
 #ifdef CONFIG_GPIOLIB
 
 struct device;
-struct gpio_chip;
 
 /**
  * Opaque descriptor for a GPIO. These are obtained using gpiod_get() and are
@@ -60,7 +59,6 @@ int gpiod_to_irq(const struct gpio_desc *desc);
 /* Convert between the old gpio_ and new gpiod_ interfaces */
 struct gpio_desc *gpio_to_desc(unsigned gpio);
 int desc_to_gpio(const struct gpio_desc *desc);
-struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc);
 
 #else /* CONFIG_GPIOLIB */
 
@@ -214,12 +212,6 @@ static inline int desc_to_gpio(const struct gpio_desc *desc)
 	WARN_ON(1);
 	return -EINVAL;
 }
-static inline struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc)
-{
-	/* GPIO can never have been requested */
-	WARN_ON(1);
-	return ERR_PTR(-ENODEV);
-}
 
 
 #endif /* CONFIG_GPIOLIB */
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index a3e181e09636..9fe283642253 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -10,6 +10,8 @@ struct of_phandle_args;
 struct device_node;
 struct seq_file;
 
+#ifdef CONFIG_GPIOLIB
+
 /**
  * struct gpio_chip - abstract a GPIO controller
  * @label: for diagnostics
@@ -129,6 +131,11 @@ extern struct gpio_chip *gpiochip_find(void *data,
 int gpiod_lock_as_irq(struct gpio_desc *desc);
 void gpiod_unlock_as_irq(struct gpio_desc *desc);
 
+struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc);
+
+struct gpio_desc *gpiochip_get_desc(struct gpio_chip *chip,
+				    u16 hwnum);
+
 enum gpio_lookup_flags {
 	GPIO_ACTIVE_HIGH = (0 << 0),
 	GPIO_ACTIVE_LOW = (1 << 0),
@@ -183,4 +190,15 @@ struct gpiod_lookup_table {
 
 void gpiod_add_lookup_table(struct gpiod_lookup_table *table);
 
+#else /* CONFIG_GPIOLIB */
+
+static inline struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+	return ERR_PTR(-ENODEV);
+}
+
+#endif /* CONFIG_GPIOLIB */
+
 #endif
-- 
cgit v1.2.3


From 048d4ff81f1cf26b3f3627a9a69d35aff7898bb3 Mon Sep 17 00:00:00 2001
From: Bo Shen <voice.shen@atmel.com>
Date: Mon, 10 Feb 2014 14:09:45 +0800
Subject: ASoC: atmel_ssc_dai: make option to choose clock

When SSC works in slave mode, according to the hardware design, the
clock can get from TK pin, also can get from RK pin. So, add one
parameter to choose where the clock from.

Signed-off-by: Bo Shen <voice.shen@atmel.com>
Acked-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/misc/atmel-ssc.c        |  6 ++++++
 include/linux/atmel-ssc.h       |  1 +
 sound/soc/atmel/atmel_ssc_dai.c | 13 +++++++++----
 3 files changed, 16 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/misc/atmel-ssc.c b/drivers/misc/atmel-ssc.c
index 5be808406edc..22de13727641 100644
--- a/drivers/misc/atmel-ssc.c
+++ b/drivers/misc/atmel-ssc.c
@@ -150,6 +150,12 @@ static int ssc_probe(struct platform_device *pdev)
 		return -ENODEV;
 	ssc->pdata = (struct atmel_ssc_platform_data *)plat_dat;
 
+	if (pdev->dev.of_node) {
+		struct device_node *np = pdev->dev.of_node;
+		ssc->clk_from_rk_pin =
+			of_property_read_bool(np, "atmel,clk-from-rk-pin");
+	}
+
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	ssc->regs = devm_ioremap_resource(&pdev->dev, regs);
 	if (IS_ERR(ssc->regs))
diff --git a/include/linux/atmel-ssc.h b/include/linux/atmel-ssc.h
index 66a0e5384edd..571a12ebb018 100644
--- a/include/linux/atmel-ssc.h
+++ b/include/linux/atmel-ssc.h
@@ -18,6 +18,7 @@ struct ssc_device {
 	struct clk		*clk;
 	int			user;
 	int			irq;
+	bool			clk_from_rk_pin;
 };
 
 struct ssc_device * __must_check ssc_request(unsigned int ssc_num);
diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c
index 1ead3c977a51..de433cfd044c 100644
--- a/sound/soc/atmel/atmel_ssc_dai.c
+++ b/sound/soc/atmel/atmel_ssc_dai.c
@@ -341,6 +341,7 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream,
 {
 	int id = dai->id;
 	struct atmel_ssc_info *ssc_p = &ssc_info[id];
+	struct ssc_device *ssc = ssc_p->ssc;
 	struct atmel_pcm_dma_params *dma_params;
 	int dir, channels, bits;
 	u32 tfmr, rfmr, tcmr, rcmr;
@@ -466,7 +467,8 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream,
 			| SSC_BF(RCMR_START, start_event)
 			| SSC_BF(RCMR_CKI, SSC_CKI_RISING)
 			| SSC_BF(RCMR_CKO, SSC_CKO_NONE)
-			| SSC_BF(RCMR_CKS, SSC_CKS_CLOCK);
+			| SSC_BF(RCMR_CKS, ssc->clk_from_rk_pin ?
+					   SSC_CKS_PIN : SSC_CKS_CLOCK);
 
 		rfmr =	  SSC_BF(RFMR_FSEDGE, SSC_FSEDGE_POSITIVE)
 			| SSC_BF(RFMR_FSOS, SSC_FSOS_NONE)
@@ -481,7 +483,8 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream,
 			| SSC_BF(TCMR_START, start_event)
 			| SSC_BF(TCMR_CKI, SSC_CKI_FALLING)
 			| SSC_BF(TCMR_CKO, SSC_CKO_NONE)
-			| SSC_BF(TCMR_CKS, SSC_CKS_PIN);
+			| SSC_BF(TCMR_CKS, ssc->clk_from_rk_pin ?
+					   SSC_CKS_CLOCK : SSC_CKS_PIN);
 
 		tfmr =	  SSC_BF(TFMR_FSEDGE, SSC_FSEDGE_POSITIVE)
 			| SSC_BF(TFMR_FSDEN, 0)
@@ -550,7 +553,8 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream,
 			| SSC_BF(RCMR_START, SSC_START_RISING_RF)
 			| SSC_BF(RCMR_CKI, SSC_CKI_RISING)
 			| SSC_BF(RCMR_CKO, SSC_CKO_NONE)
-			| SSC_BF(RCMR_CKS, SSC_CKS_PIN);
+			| SSC_BF(RCMR_CKS, ssc->clk_from_rk_pin ?
+					   SSC_CKS_PIN : SSC_CKS_CLOCK);
 
 		rfmr =	  SSC_BF(RFMR_FSEDGE, SSC_FSEDGE_POSITIVE)
 			| SSC_BF(RFMR_FSOS, SSC_FSOS_NONE)
@@ -565,7 +569,8 @@ static int atmel_ssc_hw_params(struct snd_pcm_substream *substream,
 			| SSC_BF(TCMR_START, SSC_START_RISING_RF)
 			| SSC_BF(TCMR_CKI, SSC_CKI_FALLING)
 			| SSC_BF(TCMR_CKO, SSC_CKO_NONE)
-			| SSC_BF(TCMR_CKS, SSC_CKS_PIN);
+			| SSC_BF(RCMR_CKS, ssc->clk_from_rk_pin ?
+					   SSC_CKS_CLOCK : SSC_CKS_PIN);
 
 		tfmr =	  SSC_BF(TFMR_FSEDGE, SSC_FSEDGE_POSITIVE)
 			| SSC_BF(TFMR_FSDEN, 0)
-- 
cgit v1.2.3


From 6e201c857b68ea994c9ac85718eb3d50dcf40d92 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Wed, 12 Feb 2014 22:14:53 +0000
Subject: ethtool: Document the general convention for VLAs in kernel space

Various ethtool command structures are declared with zero-length array
at the end which are intended to be variable-length in userland
(relying on lack of compiler bounds checking).  However, in the kernel
the structure and array are always allocated and passed to driver
operations separately.  Make that explicit.

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ethtool.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index c8e3e7e39c6b..0a114d05f68d 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -183,6 +183,9 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings)
  * hold the RTNL lock.
  *
  * See the structures used by these operations for further documentation.
+ * Note that for all operations using a structure ending with a zero-
+ * length array, the array is allocated separately in the kernel and
+ * is passed to the driver as an additional parameter.
  *
  * See &struct net_device and &struct net_device_ops for documentation
  * of the generic netdev features interface.
-- 
cgit v1.2.3


From e3480a61fca72d40d6dc4baaf37e94fcbfa95e19 Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Date: Thu, 30 Jan 2014 17:20:24 -0800
Subject: Input: uinput - add UI_GET_SYSNAME ioctl to retrieve the sysfs path

uinput is used in the xorg-integration-tests suite and in the wayland
test suite. These automated tests suites create many virtual input
devices and then hook something to read these newly created devices.

Currently, uinput does not provide the created input device, which means
that we rely on an heuristic to guess which input node was created.
The problem is that is heuristic is subjected to races between different
uinput devices or even with physical devices. Having a way to retrieve
the sysfs path allows us to find without any doubts the event node.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Reviewed-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/uinput.c | 43 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/uinput.h      |  2 ++
 include/uapi/linux/uinput.h | 13 ++++++++++++-
 3 files changed, 57 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c
index d8ae08d12abf..856936247500 100644
--- a/drivers/input/misc/uinput.c
+++ b/drivers/input/misc/uinput.c
@@ -20,6 +20,8 @@
  * Author: Aristeu Sergio Rozanski Filho <aris@cathedrallabs.org>
  *
  * Changes/Revisions:
+ *	0.4	01/09/2014 (Benjamin Tissoires <benjamin.tissoires@redhat.com>)
+ *		- add UI_GET_SYSNAME ioctl
  *	0.3	09/04/2006 (Anssi Hannula <anssi.hannula@gmail.com>)
  *		- updated ff support for the changes in kernel interface
  *		- added MODULE_VERSION
@@ -670,6 +672,31 @@ static int uinput_ff_upload_from_user(const char __user *buffer,
 	__ret;						\
 })
 
+static int uinput_str_to_user(void __user *dest, const char *str,
+			      unsigned int maxlen)
+{
+	char __user *p = dest;
+	int len, ret;
+
+	if (!str)
+		return -ENOENT;
+
+	if (maxlen == 0)
+		return -EINVAL;
+
+	len = strlen(str) + 1;
+	if (len > maxlen)
+		len = maxlen;
+
+	ret = copy_to_user(p, str, len);
+	if (ret)
+		return -EFAULT;
+
+	/* force terminating '\0' */
+	ret = put_user(0, p + len - 1);
+	return ret ? -EFAULT : len;
+}
+
 static long uinput_ioctl_handler(struct file *file, unsigned int cmd,
 				 unsigned long arg, void __user *p)
 {
@@ -679,6 +706,8 @@ static long uinput_ioctl_handler(struct file *file, unsigned int cmd,
 	struct uinput_ff_erase  ff_erase;
 	struct uinput_request   *req;
 	char			*phys;
+	const char		*name;
+	unsigned int		size;
 
 	retval = mutex_lock_interruptible(&udev->mutex);
 	if (retval)
@@ -831,6 +860,20 @@ static long uinput_ioctl_handler(struct file *file, unsigned int cmd,
 			goto out;
 	}
 
+	size = _IOC_SIZE(cmd);
+
+	/* Now check variable-length commands */
+	switch (cmd & ~IOCSIZE_MASK) {
+	case UI_GET_SYSNAME(0):
+		if (udev->state != UIST_CREATED) {
+			retval = -ENOENT;
+			goto out;
+		}
+		name = dev_name(&udev->dev->dev);
+		retval = uinput_str_to_user(p, name, size);
+		goto out;
+	}
+
 	retval = -EINVAL;
  out:
 	mutex_unlock(&udev->mutex);
diff --git a/include/linux/uinput.h b/include/linux/uinput.h
index 0a4487d3fb1e..0994c0d01a09 100644
--- a/include/linux/uinput.h
+++ b/include/linux/uinput.h
@@ -20,6 +20,8 @@
  * Author: Aristeu Sergio Rozanski Filho <aris@cathedrallabs.org>
  *
  * Changes/Revisions:
+ *	0.4	01/09/2014 (Benjamin Tissoires <benjamin.tissoires@redhat.com>)
+ *		- add UI_GET_SYSNAME ioctl
  *	0.3	24/05/2006 (Anssi Hannula <anssi.hannulagmail.com>)
  *		- update ff support for the changes in kernel interface
  *		- add UINPUT_VERSION
diff --git a/include/uapi/linux/uinput.h b/include/uapi/linux/uinput.h
index fe46431593f9..0389b489bbba 100644
--- a/include/uapi/linux/uinput.h
+++ b/include/uapi/linux/uinput.h
@@ -20,6 +20,8 @@
  * Author: Aristeu Sergio Rozanski Filho <aris@cathedrallabs.org>
  *
  * Changes/Revisions:
+ *	0.4	01/09/2014 (Benjamin Tissoires <benjamin.tissoires@redhat.com>)
+ *		- add UI_GET_SYSNAME ioctl
  *	0.3	24/05/2006 (Anssi Hannula <anssi.hannulagmail.com>)
  *		- update ff support for the changes in kernel interface
  *		- add UINPUT_VERSION
@@ -35,7 +37,7 @@
 #include <linux/types.h>
 #include <linux/input.h>
 
-#define UINPUT_VERSION		3
+#define UINPUT_VERSION		4
 
 
 struct uinput_ff_upload {
@@ -73,6 +75,15 @@ struct uinput_ff_erase {
 #define UI_BEGIN_FF_ERASE	_IOWR(UINPUT_IOCTL_BASE, 202, struct uinput_ff_erase)
 #define UI_END_FF_ERASE		_IOW(UINPUT_IOCTL_BASE, 203, struct uinput_ff_erase)
 
+/**
+ * UI_GET_SYSNAME - get the sysfs name of the created uinput device
+ *
+ * @return the sysfs name of the created virtual input device.
+ * The complete sysfs path is then /sys/devices/virtual/input/--NAME--
+ * Usually, it is in the form "inputN"
+ */
+#define UI_GET_SYSNAME(len)	_IOC(_IOC_READ, UINPUT_IOCTL_BASE, 300, len)
+
 /*
  * To write a force-feedback-capable driver, the upload_effect
  * and erase_effect callbacks in input_dev must be implemented.
-- 
cgit v1.2.3


From a9fa6e6ac29709e7a623b60695c172da675df045 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 11 Feb 2014 17:27:36 -0800
Subject: net: phy: add genphy_aneg_done()

In preparation for allowing PHY drivers to potentially override their
auto-negotiation done callback, move the contents of phy_aneg_done() to
genphy_aneg_done() since that function really is the generic
implementation based on the BMSR_ANEGCOMPLETE status.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c        |  4 +---
 drivers/net/phy/phy_device.c | 16 ++++++++++++++++
 include/linux/phy.h          |  1 +
 3 files changed, 18 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 36fc6e16b569..db9c543bd2af 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -120,9 +120,7 @@ static int phy_config_interrupt(struct phy_device *phydev, u32 interrupts)
  */
 static inline int phy_aneg_done(struct phy_device *phydev)
 {
-	int retval = phy_read(phydev, MII_BMSR);
-
-	return (retval < 0) ? retval : (retval & BMSR_ANEGCOMPLETE);
+	return genphy_aneg_done(phydev);
 }
 
 /* A structure for mapping a particular speed and duplex
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 82514e72b3d8..4e7db726028f 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -865,6 +865,22 @@ int genphy_config_aneg(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(genphy_config_aneg);
 
+/**
+ * genphy_aneg_done - return auto-negotiation status
+ * @phydev: target phy_device struct
+ *
+ * Description: Reads the status register and returns 0 either if
+ *   auto-negotiation is incomplete, or if there was an error.
+ *   Returns BMSR_ANEGCOMPLETE if auto-negotiation is done.
+ */
+int genphy_aneg_done(struct phy_device *phydev)
+{
+	int retval = phy_read(phydev, MII_BMSR);
+
+	return (retval < 0) ? retval : (retval & BMSR_ANEGCOMPLETE);
+}
+EXPORT_SYMBOL(genphy_aneg_done);
+
 static int gen10g_config_aneg(struct phy_device *phydev)
 {
 	return 0;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 565188ca328f..c572842c9029 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -612,6 +612,7 @@ static inline int phy_read_status(struct phy_device *phydev)
 int genphy_setup_forced(struct phy_device *phydev);
 int genphy_restart_aneg(struct phy_device *phydev);
 int genphy_config_aneg(struct phy_device *phydev);
+int genphy_aneg_done(struct phy_device *phydev);
 int genphy_update_link(struct phy_device *phydev);
 int genphy_read_status(struct phy_device *phydev);
 int genphy_suspend(struct phy_device *phydev);
-- 
cgit v1.2.3


From 76a423a3f8f16bfc7fb86360a620be18c775b94d Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 11 Feb 2014 17:27:37 -0800
Subject: net: phy: allow driver to implement their own aneg_done

Some PHYs out there can be very quirky with respect to how they would
report the auto-negotiation is completed. Allow drivers to override the
generic aneg_done() implementation by providing their own.

Since not all drivers have been updated yet to use genphy_aneg_done() as
aneg_done() callback, we explicitely check that this callback is valid
before calling into it.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c        | 9 ++++++---
 drivers/net/phy/phy_device.c | 1 +
 include/linux/phy.h          | 3 +++
 3 files changed, 10 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index db9c543bd2af..2fa4611709a4 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -114,12 +114,15 @@ static int phy_config_interrupt(struct phy_device *phydev, u32 interrupts)
  * phy_aneg_done - return auto-negotiation status
  * @phydev: target phy_device struct
  *
- * Description: Reads the status register and returns 0 either if
- *   auto-negotiation is incomplete, or if there was an error.
- *   Returns BMSR_ANEGCOMPLETE if auto-negotiation is done.
+ * Description: Return the auto-negotiation status from this @phydev
+ * Returns > 0 on success or < 0 on error. 0 means that auto-negotiation
+ * is still pending.
  */
 static inline int phy_aneg_done(struct phy_device *phydev)
 {
+	if (phydev->drv->aneg_done)
+		return phydev->drv->aneg_done(phydev);
+
 	return genphy_aneg_done(phydev);
 }
 
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 4e7db726028f..7c184208ed4d 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1267,6 +1267,7 @@ static struct phy_driver genphy_driver[] = {
 	.config_init	= genphy_config_init,
 	.features	= 0,
 	.config_aneg	= genphy_config_aneg,
+	.aneg_done	= genphy_aneg_done,
 	.read_status	= genphy_read_status,
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
diff --git a/include/linux/phy.h b/include/linux/phy.h
index c572842c9029..eede6579cae7 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -417,6 +417,9 @@ struct phy_driver {
 	 */
 	int (*config_aneg)(struct phy_device *phydev);
 
+	/* Determines the auto negotiation result */
+	int (*aneg_done)(struct phy_device *phydev);
+
 	/* Determines the negotiated speed and duplex */
 	int (*read_status)(struct phy_device *phydev);
 
-- 
cgit v1.2.3


From 8a2fe56e8827f2b1eb1766702f0215074dd2767e Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 11 Feb 2014 17:27:39 -0800
Subject: net: phy: re-design phy_modes to be self-contained

of_get_phy_mode() uses a local array to map phy_interface_t values from
include/linux/net/phy.h to a string which is read from the 'phy-mode' or
'phy-connection-type' property. In preparation for exposing the PHY
interface mode through sysfs, perform the following:

- mode phy_modes from drivers/of/of_net.c to include/linux/phy.h such
  that it is right below the phy_interface_t enum
- make it a static inline function returning the string such that we can
  use it by just including include/linux/net/phy.h
- add a PHY_INTERFACE_MODE_MAX enum value to guard the iteration in
  of_get_phy_mode()

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/of/of_net.c | 26 ++------------------------
 include/linux/phy.h | 42 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 44 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/of/of_net.c b/drivers/of/of_net.c
index a208a457558c..84215c1929c4 100644
--- a/drivers/of/of_net.c
+++ b/drivers/of/of_net.c
@@ -11,28 +11,6 @@
 #include <linux/phy.h>
 #include <linux/export.h>
 
-/**
- * It maps 'enum phy_interface_t' found in include/linux/phy.h
- * into the device tree binding of 'phy-mode', so that Ethernet
- * device driver can get phy interface from device tree.
- */
-static const char *phy_modes[] = {
-	[PHY_INTERFACE_MODE_NA]		= "",
-	[PHY_INTERFACE_MODE_MII]	= "mii",
-	[PHY_INTERFACE_MODE_GMII]	= "gmii",
-	[PHY_INTERFACE_MODE_SGMII]	= "sgmii",
-	[PHY_INTERFACE_MODE_TBI]	= "tbi",
-	[PHY_INTERFACE_MODE_REVMII]	= "rev-mii",
-	[PHY_INTERFACE_MODE_RMII]	= "rmii",
-	[PHY_INTERFACE_MODE_RGMII]	= "rgmii",
-	[PHY_INTERFACE_MODE_RGMII_ID]	= "rgmii-id",
-	[PHY_INTERFACE_MODE_RGMII_RXID]	= "rgmii-rxid",
-	[PHY_INTERFACE_MODE_RGMII_TXID] = "rgmii-txid",
-	[PHY_INTERFACE_MODE_RTBI]	= "rtbi",
-	[PHY_INTERFACE_MODE_SMII]	= "smii",
-	[PHY_INTERFACE_MODE_XGMII]	= "xgmii",
-};
-
 /**
  * of_get_phy_mode - Get phy mode for given device_node
  * @np:	Pointer to the given device_node
@@ -49,8 +27,8 @@ int of_get_phy_mode(struct device_node *np)
 	if (err < 0)
 		return err;
 
-	for (i = 0; i < ARRAY_SIZE(phy_modes); i++)
-		if (!strcasecmp(pm, phy_modes[i]))
+	for (i = 0; i < PHY_INTERFACE_MODE_MAX; i++)
+		if (!strcasecmp(pm, phy_modes(i)))
 			return i;
 
 	return -ENODEV;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index eede6579cae7..ef7fa1131145 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -74,8 +74,50 @@ typedef enum {
 	PHY_INTERFACE_MODE_RTBI,
 	PHY_INTERFACE_MODE_SMII,
 	PHY_INTERFACE_MODE_XGMII,
+	PHY_INTERFACE_MODE_MAX,
 } phy_interface_t;
 
+/**
+ * It maps 'enum phy_interface_t' found in include/linux/phy.h
+ * into the device tree binding of 'phy-mode', so that Ethernet
+ * device driver can get phy interface from device tree.
+ */
+static inline const char *phy_modes(phy_interface_t interface)
+{
+	switch (interface) {
+	case PHY_INTERFACE_MODE_NA:
+		return "";
+	case PHY_INTERFACE_MODE_MII:
+		return "mii";
+	case PHY_INTERFACE_MODE_GMII:
+		return "gmii";
+	case PHY_INTERFACE_MODE_SGMII:
+		return "sgmii";
+	case PHY_INTERFACE_MODE_TBI:
+		return "tbi";
+	case PHY_INTERFACE_MODE_REVMII:
+		return "rev-mii";
+	case PHY_INTERFACE_MODE_RMII:
+		return "rmii";
+	case PHY_INTERFACE_MODE_RGMII:
+		return "rgmii";
+	case PHY_INTERFACE_MODE_RGMII_ID:
+		return "rgmii-id";
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+		return "rgmii-rxid";
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+		return "rgmii-txid";
+	case PHY_INTERFACE_MODE_RTBI:
+		return "rtbi";
+	case PHY_INTERFACE_MODE_SMII:
+		return "smii";
+	case PHY_INTERFACE_MODE_XGMII:
+		return "xgmii";
+	default:
+		return "unknown";
+	}
+}
+
 
 #define PHY_INIT_TIMEOUT	100000
 #define PHY_STATE_TIME		1
-- 
cgit v1.2.3


From b0ae009f3dc14643e56972cfc08c060dd72cc24d Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 11 Feb 2014 17:27:41 -0800
Subject: net: phy: add "has_fixups" boolean property

Add a boolean property which indicates if the PHY has had any fixup
routine ran on it. We are later going to use that boolean to expose it
as a sysfs property to help troubleshooting.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 1 +
 include/linux/phy.h          | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 7c184208ed4d..c2d778d06405 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -139,6 +139,7 @@ static int phy_scan_fixups(struct phy_device *phydev)
 				mutex_unlock(&phy_fixup_lock);
 				return err;
 			}
+			phydev->has_fixups = true;
 		}
 	}
 	mutex_unlock(&phy_fixup_lock);
diff --git a/include/linux/phy.h b/include/linux/phy.h
index ef7fa1131145..42f1bc7eaeb0 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -350,6 +350,7 @@ struct phy_device {
 	struct phy_c45_device_ids c45_ids;
 	bool is_c45;
 	bool is_internal;
+	bool has_fixups;
 
 	enum phy_state state;
 
-- 
cgit v1.2.3


From 09c978bc7bdcfc3db91801454273a4330e1933bf Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Fri, 10 Jan 2014 15:57:27 +0100
Subject: ARM: integrator: switch to fetch clocks from device tree

This atomic commit changes the Integrator clock implementation
and the machines to register clocks from the device tree and
use these instead of the previous hard-coded clocks.

In the clock implementation all hard-coded clocks and the
special initialization function call goes away, and is
replaced by two compatible strings for the two clocks
available on the core module.

Cc: Mike Turquette <mturquette@linaro.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../devicetree/bindings/clock/arm-integrator.txt   | 34 +++++++++
 arch/arm/mach-integrator/integrator_ap.c           | 19 +++--
 arch/arm/mach-integrator/integrator_cp.c           |  6 --
 drivers/clk/versatile/clk-integrator.c             | 80 +++++++++-------------
 include/linux/platform_data/clk-integrator.h       |  1 -
 5 files changed, 80 insertions(+), 60 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/clock/arm-integrator.txt

(limited to 'include/linux')

diff --git a/Documentation/devicetree/bindings/clock/arm-integrator.txt b/Documentation/devicetree/bindings/clock/arm-integrator.txt
new file mode 100644
index 000000000000..652914b17b95
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/arm-integrator.txt
@@ -0,0 +1,34 @@
+Clock bindings for ARM Integrator Core Module clocks
+
+Auxilary Oscillator Clock
+
+This is a configurable clock fed from a 24 MHz chrystal,
+used for generating e.g. video clocks. It is located on the
+core module and there is only one of these.
+
+This clock node *must* be a subnode of the core module, since
+it obtains the base address for it's address range from its
+parent node.
+
+
+Required properties:
+- compatible: must be "arm,integrator-cm-auxosc"
+- #clock-cells: must be <0>
+
+Optional properties:
+- clocks: parent clock(s)
+
+Example:
+
+core-module@10000000 {
+	xtal24mhz: xtal24mhz@24M {
+		#clock-cells = <0>;
+		compatible = "fixed-clock";
+		clock-frequency = <24000000>;
+	};
+	auxosc: cm_aux_osc@25M {
+		#clock-cells = <0>;
+		compatible = "arm,integrator-cm-auxosc";
+		clocks = <&xtal24mhz>;
+	};
+};
diff --git a/arch/arm/mach-integrator/integrator_ap.c b/arch/arm/mach-integrator/integrator_ap.c
index 17c0fe627435..fedcd2fab094 100644
--- a/arch/arm/mach-integrator/integrator_ap.c
+++ b/arch/arm/mach-integrator/integrator_ap.c
@@ -42,6 +42,7 @@
 #include <linux/sys_soc.h>
 #include <linux/termios.h>
 #include <linux/sched_clock.h>
+#include <linux/clk-provider.h>
 
 #include <mach/hardware.h>
 #include <mach/platform.h>
@@ -402,10 +403,7 @@ static void __init ap_of_timer_init(void)
 	struct clk *clk;
 	unsigned long rate;
 
-	clk = clk_get_sys("ap_timer", NULL);
-	BUG_ON(IS_ERR(clk));
-	clk_prepare_enable(clk);
-	rate = clk_get_rate(clk);
+	of_clk_init(NULL);
 
 	err = of_property_read_string(of_aliases,
 				"arm,timer-primary", &path);
@@ -415,6 +413,12 @@ static void __init ap_of_timer_init(void)
 	base = of_iomap(node, 0);
 	if (WARN_ON(!base))
 		return;
+
+	clk = of_clk_get(node, 0);
+	BUG_ON(IS_ERR(clk));
+	clk_prepare_enable(clk);
+	rate = clk_get_rate(clk);
+
 	writel(0, base + TIMER_CTRL);
 	integrator_clocksource_init(rate, base);
 
@@ -427,6 +431,12 @@ static void __init ap_of_timer_init(void)
 	if (WARN_ON(!base))
 		return;
 	irq = irq_of_parse_and_map(node, 0);
+
+	clk = of_clk_get(node, 0);
+	BUG_ON(IS_ERR(clk));
+	clk_prepare_enable(clk);
+	rate = clk_get_rate(clk);
+
 	writel(0, base + TIMER_CTRL);
 	integrator_clockevent_init(rate, base, irq);
 }
@@ -440,7 +450,6 @@ static void __init ap_init_irq_of(void)
 {
 	cm_init();
 	of_irq_init(fpga_irq_of_match);
-	integrator_clk_init(false);
 }
 
 /* For the Device Tree, add in the UART callbacks as AUXDATA */
diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c
index a3ef961e4a93..0ad5f60598c8 100644
--- a/arch/arm/mach-integrator/integrator_cp.c
+++ b/arch/arm/mach-integrator/integrator_cp.c
@@ -23,7 +23,6 @@
 #include <linux/irqchip/versatile-fpga.h>
 #include <linux/gfp.h>
 #include <linux/mtd/physmap.h>
-#include <linux/platform_data/clk-integrator.h>
 #include <linux/of_irq.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
@@ -33,8 +32,6 @@
 #include <mach/platform.h>
 #include <asm/setup.h>
 #include <asm/mach-types.h>
-#include <asm/hardware/arm_timer.h>
-#include <asm/hardware/icst.h>
 
 #include <mach/lm.h>
 
@@ -43,8 +40,6 @@
 #include <asm/mach/map.h>
 #include <asm/mach/time.h>
 
-#include <asm/hardware/timer-sp.h>
-
 #include <plat/clcd.h>
 #include <plat/sched_clock.h>
 
@@ -250,7 +245,6 @@ static void __init intcp_init_irq_of(void)
 {
 	cm_init();
 	of_irq_init(fpga_irq_of_match);
-	integrator_clk_init(true);
 }
 
 /*
diff --git a/drivers/clk/versatile/clk-integrator.c b/drivers/clk/versatile/clk-integrator.c
index bda8967e09c2..19864b5690e9 100644
--- a/drivers/clk/versatile/clk-integrator.c
+++ b/drivers/clk/versatile/clk-integrator.c
@@ -10,20 +10,17 @@
 #include <linux/clk.h>
 #include <linux/clkdev.h>
 #include <linux/err.h>
-#include <linux/platform_data/clk-integrator.h>
-
-#include <mach/hardware.h>
-#include <mach/platform.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
 
 #include "clk-icst.h"
 
-/*
- * Implementation of the ARM Integrator/AP and Integrator/CP clock tree.
- * Inspired by portions of:
- * plat-versatile/clock.c and plat-versatile/include/plat/clock.h
- */
+#define INTEGRATOR_HDR_LOCK_OFFSET	0x14
 
-static const struct icst_params cp_auxvco_params = {
+/* Base offset for the core module */
+static void __iomem *cm_base;
+
+static const struct icst_params cp_auxosc_params = {
 	.ref		= 24000000,
 	.vco_max	= ICST525_VCO_MAX_5V,
 	.vco_min	= ICST525_VCO_MIN,
@@ -35,50 +32,37 @@ static const struct icst_params cp_auxvco_params = {
 	.idx2s		= icst525_idx2s,
 };
 
-static const struct clk_icst_desc __initdata cp_icst_desc = {
-	.params = &cp_auxvco_params,
+static const struct clk_icst_desc __initdata cm_auxosc_desc = {
+	.params = &cp_auxosc_params,
 	.vco_offset = 0x1c,
 	.lock_offset = INTEGRATOR_HDR_LOCK_OFFSET,
 };
 
-/*
- * integrator_clk_init() - set up the integrator clock tree
- * @is_cp: pass true if it's the Integrator/CP else AP is assumed
- */
-void __init integrator_clk_init(bool is_cp)
+static void __init of_integrator_cm_osc_setup(struct device_node *np)
 {
-	struct clk *clk;
-
-	/* APB clock dummy */
-	clk = clk_register_fixed_rate(NULL, "apb_pclk", NULL, CLK_IS_ROOT, 0);
-	clk_register_clkdev(clk, "apb_pclk", NULL);
-
-	/* UART reference clock */
-	clk = clk_register_fixed_rate(NULL, "uartclk", NULL, CLK_IS_ROOT,
-				14745600);
-	clk_register_clkdev(clk, NULL, "uart0");
-	clk_register_clkdev(clk, NULL, "uart1");
-	if (is_cp)
-		clk_register_clkdev(clk, NULL, "mmci");
-
-	/* 24 MHz clock */
-	clk = clk_register_fixed_rate(NULL, "clk24mhz", NULL, CLK_IS_ROOT,
-				24000000);
-	clk_register_clkdev(clk, NULL, "kmi0");
-	clk_register_clkdev(clk, NULL, "kmi1");
-	if (!is_cp)
-		clk_register_clkdev(clk, NULL, "ap_timer");
+	struct clk *clk = ERR_PTR(-EINVAL);
+	const char *clk_name = np->name;
+	const struct clk_icst_desc *desc = &cm_auxosc_desc;
 
-	if (!is_cp)
-		return;
+	if (!cm_base) {
+		/* Remap the core module base if not done yet */
+		struct device_node *parent;
 
-	/* 1 MHz clock */
-	clk = clk_register_fixed_rate(NULL, "clk1mhz", NULL, CLK_IS_ROOT,
-				1000000);
-	clk_register_clkdev(clk, NULL, "sp804");
+		parent = of_get_parent(np);
+		if (!np) {
+			pr_err("no parent on core module clock\n");
+			return;
+		}
+		cm_base = of_iomap(parent, 0);
+		if (!cm_base) {
+			pr_err("could not remap core module base\n");
+			return;
+		}
+	}
 
-	/* ICST VCO clock used on the Integrator/CP CLCD */
-	clk = icst_clk_register(NULL, &cp_icst_desc, "icst",
-				__io_address(INTEGRATOR_HDR_BASE));
-	clk_register_clkdev(clk, NULL, "clcd");
+	clk = icst_clk_register(NULL, desc, clk_name, cm_base);
+	if (!IS_ERR(clk))
+		of_clk_add_provider(np, of_clk_src_simple_get, clk);
 }
+CLK_OF_DECLARE(integrator_cm_auxosc_clk,
+	"arm,integrator-cm-auxosc", of_integrator_cm_osc_setup);
diff --git a/include/linux/platform_data/clk-integrator.h b/include/linux/platform_data/clk-integrator.h
index 280edac9d0a5..addd48cac625 100644
--- a/include/linux/platform_data/clk-integrator.h
+++ b/include/linux/platform_data/clk-integrator.h
@@ -1,3 +1,2 @@
-void integrator_clk_init(bool is_cp);
 void integrator_impd1_clk_init(void __iomem *base, unsigned int id);
 void integrator_impd1_clk_exit(unsigned int id);
-- 
cgit v1.2.3


From e641b987c20832dfaaa51d7792ed928c2b2d2dbf Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Thu, 21 Nov 2013 23:11:29 +0100
Subject: irqchip: support cascaded VICs

This adds support for a VIC to be cascaded off another IRQ.
On the Integrator/AP logical module IM-PD1 there is a VIC
cascaded off the central FPGA IRQ controller so this is
needed for that to work out.

In order for the plug-in board to be able to register all
the devices with their IRQs relative to the offset of the
base obtained for the cascaded VIC, the base IRQ number
is passed back to the caller.

Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 arch/arm/mach-versatile/core.c  |  2 +-
 drivers/irqchip/irq-vic.c       | 53 ++++++++++++++++++++++++++++++++++++-----
 include/linux/irqchip/arm-vic.h |  6 +++--
 3 files changed, 52 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-versatile/core.c b/arch/arm/mach-versatile/core.c
index a335126ae18f..f2c89fb8fca9 100644
--- a/arch/arm/mach-versatile/core.c
+++ b/arch/arm/mach-versatile/core.c
@@ -108,7 +108,7 @@ void __init versatile_init_irq(void)
 
 	np = of_find_matching_node_by_address(NULL, vic_of_match,
 					      VERSATILE_VIC_BASE);
-	__vic_init(VA_VIC_BASE, IRQ_VIC_START, ~0, 0, np);
+	__vic_init(VA_VIC_BASE, 0, IRQ_VIC_START, ~0, 0, np);
 
 	writel(~0, VA_SIC_BASE + SIC_IRQ_ENABLE_CLEAR);
 
diff --git a/drivers/irqchip/irq-vic.c b/drivers/irqchip/irq-vic.c
index 70108c1491bc..6002942a231c 100644
--- a/drivers/irqchip/irq-vic.c
+++ b/drivers/irqchip/irq-vic.c
@@ -57,6 +57,7 @@
 
 /**
  * struct vic_device - VIC PM device
+ * @parent_irq: The parent IRQ number of the VIC if cascaded, or 0.
  * @irq: The IRQ number for the base of the VIC.
  * @base: The register base for the VIC.
  * @valid_sources: A bitmask of valid interrupts
@@ -224,6 +225,17 @@ static int handle_one_vic(struct vic_device *vic, struct pt_regs *regs)
 	return handled;
 }
 
+static void vic_handle_irq_cascaded(unsigned int irq, struct irq_desc *desc)
+{
+	u32 stat, hwirq;
+	struct vic_device *vic = irq_desc_get_handler_data(desc);
+
+	while ((stat = readl_relaxed(vic->base + VIC_IRQ_STATUS))) {
+		hwirq = ffs(stat) - 1;
+		generic_handle_irq(irq_find_mapping(vic->domain, hwirq));
+	}
+}
+
 /*
  * Keep iterating over all registered VIC's until there are no pending
  * interrupts.
@@ -246,6 +258,7 @@ static struct irq_domain_ops vic_irqdomain_ops = {
 /**
  * vic_register() - Register a VIC.
  * @base: The base address of the VIC.
+ * @parent_irq: The parent IRQ if cascaded, else 0.
  * @irq: The base IRQ for the VIC.
  * @valid_sources: bitmask of valid interrupts
  * @resume_sources: bitmask of interrupts allowed for resume sources.
@@ -257,7 +270,8 @@ static struct irq_domain_ops vic_irqdomain_ops = {
  *
  * This also configures the IRQ domain for the VIC.
  */
-static void __init vic_register(void __iomem *base, unsigned int irq,
+static void __init vic_register(void __iomem *base, unsigned int parent_irq,
+				unsigned int irq,
 				u32 valid_sources, u32 resume_sources,
 				struct device_node *node)
 {
@@ -275,6 +289,12 @@ static void __init vic_register(void __iomem *base, unsigned int irq,
 	v->resume_sources = resume_sources;
 	set_handle_irq(vic_handle_irq);
 	vic_id++;
+
+	if (parent_irq) {
+		irq_set_handler_data(parent_irq, v);
+		irq_set_chained_handler(parent_irq, vic_handle_irq_cascaded);
+	}
+
 	v->domain = irq_domain_add_simple(node, fls(valid_sources), irq,
 					  &vic_irqdomain_ops, v);
 	/* create an IRQ mapping for each valid IRQ */
@@ -413,10 +433,10 @@ static void __init vic_init_st(void __iomem *base, unsigned int irq_start,
 		writel(32, base + VIC_PL190_DEF_VECT_ADDR);
 	}
 
-	vic_register(base, irq_start, vic_sources, 0, node);
+	vic_register(base, 0, irq_start, vic_sources, 0, node);
 }
 
-void __init __vic_init(void __iomem *base, int irq_start,
+void __init __vic_init(void __iomem *base, int parent_irq, int irq_start,
 			      u32 vic_sources, u32 resume_sources,
 			      struct device_node *node)
 {
@@ -453,7 +473,7 @@ void __init __vic_init(void __iomem *base, int irq_start,
 
 	vic_init2(base);
 
-	vic_register(base, irq_start, vic_sources, resume_sources, node);
+	vic_register(base, parent_irq, irq_start, vic_sources, resume_sources, node);
 }
 
 /**
@@ -466,7 +486,28 @@ void __init __vic_init(void __iomem *base, int irq_start,
 void __init vic_init(void __iomem *base, unsigned int irq_start,
 		     u32 vic_sources, u32 resume_sources)
 {
-	__vic_init(base, irq_start, vic_sources, resume_sources, NULL);
+	__vic_init(base, 0, irq_start, vic_sources, resume_sources, NULL);
+}
+
+/**
+ * vic_init_cascaded() - initialise a cascaded vectored interrupt controller
+ * @base: iomem base address
+ * @parent_irq: the parent IRQ we're cascaded off
+ * @irq_start: starting interrupt number, must be muliple of 32
+ * @vic_sources: bitmask of interrupt sources to allow
+ * @resume_sources: bitmask of interrupt sources to allow for resume
+ *
+ * This returns the base for the new interrupts or negative on error.
+ */
+int __init vic_init_cascaded(void __iomem *base, unsigned int parent_irq,
+			      u32 vic_sources, u32 resume_sources)
+{
+	struct vic_device *v;
+
+	v = &vic_devices[vic_id];
+	__vic_init(base, parent_irq, 0, vic_sources, resume_sources, NULL);
+	/* Return out acquired base */
+	return v->irq;
 }
 
 #ifdef CONFIG_OF
@@ -489,7 +530,7 @@ int __init vic_of_init(struct device_node *node, struct device_node *parent)
 	/*
 	 * Passing 0 as first IRQ makes the simple domain allocate descriptors
 	 */
-	__vic_init(regs, 0, interrupt_mask, wakeup_mask, node);
+	__vic_init(regs, 0, 0, interrupt_mask, wakeup_mask, node);
 
 	return 0;
 }
diff --git a/include/linux/irqchip/arm-vic.h b/include/linux/irqchip/arm-vic.h
index e3c82dc95756..ba46c794b4e5 100644
--- a/include/linux/irqchip/arm-vic.h
+++ b/include/linux/irqchip/arm-vic.h
@@ -29,8 +29,10 @@
 struct device_node;
 struct pt_regs;
 
-void __vic_init(void __iomem *base, int irq_start, u32 vic_sources,
-		u32 resume_sources, struct device_node *node);
+void __vic_init(void __iomem *base, int parent_irq, int irq_start,
+		u32 vic_sources, u32 resume_sources, struct device_node *node);
 void vic_init(void __iomem *base, unsigned int irq_start, u32 vic_sources, u32 resume_sources);
+int vic_init_cascaded(void __iomem *base, unsigned int parent_irq,
+		      u32 vic_sources, u32 resume_sources);
 
 #endif
-- 
cgit v1.2.3


From d3ba07c3aa9ae3e03329b0a7f1a067c0647aa2af Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Thu, 13 Feb 2014 06:58:38 -0500
Subject: cgroup: disallow xattr, release_agent and name if sane_behavior

Disallow more mount options if sane_behavior.  Note that xattr used to
generate warning.

While at it, simplify option check in cgroup_mount() and update
sane_behavior comment in cgroup.h.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h |  6 +++---
 kernel/cgroup.c        | 14 ++++----------
 2 files changed, 7 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 298d616e8f40..5f669ca0ee36 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -227,8 +227,8 @@ enum {
 	 *
 	 * The followings are the behaviors currently affected this flag.
 	 *
-	 * - Mount options "noprefix" and "clone_children" are disallowed.
-	 *   Also, cgroupfs file cgroup.clone_children is not created.
+	 * - Mount options "noprefix", "xattr", "clone_children",
+	 *   "release_agent" and "name" are disallowed.
 	 *
 	 * - When mounting an existing superblock, mount options should
 	 *   match.
@@ -246,7 +246,7 @@ enum {
 	 * - "release_agent" and "notify_on_release" are removed.
 	 *   Replacement notification mechanism will be implemented.
 	 *
-	 * - "xattr" mount option is deprecated.  kernfs always enables it.
+	 * - "cgroup.clone_children" is removed.
 	 *
 	 * - cpuset: tasks will be kept in empty cpusets when hotplug happens
 	 *   and take masks of ancestors with non-empty cpus/mems, instead of
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 03845c5d082b..079c478a4735 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1226,18 +1226,12 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 	if (opts->flags & CGRP_ROOT_SANE_BEHAVIOR) {
 		pr_warning("cgroup: sane_behavior: this is still under development and its behaviors will change, proceed at your own risk\n");
 
-		if (opts->flags & CGRP_ROOT_NOPREFIX) {
-			pr_err("cgroup: sane_behavior: noprefix is not allowed\n");
+		if ((opts->flags & (CGRP_ROOT_NOPREFIX | CGRP_ROOT_XATTR)) ||
+		    opts->cpuset_clone_children || opts->release_agent ||
+		    opts->name) {
+			pr_err("cgroup: sane_behavior: noprefix, xattr, clone_children, release_agent and name are not allowed\n");
 			return -EINVAL;
 		}
-
-		if (opts->cpuset_clone_children) {
-			pr_err("cgroup: sane_behavior: clone_children is not allowed\n");
-			return -EINVAL;
-		}
-
-		if (opts->flags & CGRP_ROOT_XATTR)
-			pr_warning("cgroup: sane_behavior: xattr is always available, flag unnecessary\n");
 	}
 
 	/*
-- 
cgit v1.2.3


From 35585573055f37837eb752ee22eb5523682ca742 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Thu, 13 Feb 2014 06:58:38 -0500
Subject: cgroup: drop CGRP_ROOT_SUBSYS_BOUND

Before kernfs conversion, due to the way super_block lookup works,
cgroup roots were created and made visible before being fully
initialized.  This in turn required a special flag to mark that the
root hasn't been fully initialized so that the destruction path can
tell fully bound ones from half initialized.

That flag is CGRP_ROOT_SUBSYS_BOUND and no longer necessary after the
kernfs conversion as the lookup and creation of new root are atomic
w.r.t. cgroup_mutex.  This patch removes the flag and passes the
requests subsystem mask to cgroup_setup_root() so that it can set the
respective mask bits as subsystems are bound.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h |  2 --
 kernel/cgroup.c        | 28 ++++------------------------
 2 files changed, 4 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 5f669ca0ee36..e2ffcdc26cb7 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -267,8 +267,6 @@ enum {
 
 	/* mount options live below bit 16 */
 	CGRP_ROOT_OPTION_MASK	= (1 << 16) - 1,
-
-	CGRP_ROOT_SUBSYS_BOUND	= (1 << 16), /* subsystems finished binding */
 };
 
 /*
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 079c478a4735..878cd1810ad1 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -733,7 +733,6 @@ static void cgroup_destroy_root(struct cgroupfs_root *root)
 {
 	struct cgroup *cgrp = &root->top_cgroup;
 	struct cgrp_cset_link *link, *tmp_link;
-	int ret;
 
 	mutex_lock(&cgroup_tree_mutex);
 	mutex_lock(&cgroup_mutex);
@@ -742,11 +741,7 @@ static void cgroup_destroy_root(struct cgroupfs_root *root)
 	BUG_ON(!list_empty(&cgrp->children));
 
 	/* Rebind all subsystems back to the default hierarchy */
-	if (root->flags & CGRP_ROOT_SUBSYS_BOUND) {
-		ret = rebind_subsystems(root, 0, root->subsys_mask);
-		/* Shouldn't be able to fail ... */
-		BUG_ON(ret);
-	}
+	WARN_ON(rebind_subsystems(root, 0, root->subsys_mask));
 
 	/*
 	 * Release all the links from cset_links to this hierarchy's
@@ -1055,13 +1050,7 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 		}
 	}
 
-	/*
-	 * Mark @root has finished binding subsystems.  @root->subsys_mask
-	 * now matches the bound subsystems.
-	 */
-	root->flags |= CGRP_ROOT_SUBSYS_BOUND;
 	kernfs_activate(cgrp->kn);
-
 	return 0;
 }
 
@@ -1353,15 +1342,6 @@ static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
 
 	init_cgroup_root(root);
 
-	/*
-	 * We need to set @root->subsys_mask now so that @root can be
-	 * matched by cgroup_test_super() before it finishes
-	 * initialization; otherwise, competing mounts with the same
-	 * options may try to bind the same subsystems instead of waiting
-	 * for the first one leading to unexpected mount errors.
-	 * SUBSYS_BOUND will be set once actual binding is complete.
-	 */
-	root->subsys_mask = opts->subsys_mask;
 	root->flags = opts->flags;
 	if (opts->release_agent)
 		strcpy(root->release_agent_path, opts->release_agent);
@@ -1372,7 +1352,7 @@ static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
 	return root;
 }
 
-static int cgroup_setup_root(struct cgroupfs_root *root)
+static int cgroup_setup_root(struct cgroupfs_root *root, unsigned long ss_mask)
 {
 	LIST_HEAD(tmp_links);
 	struct cgroup *root_cgrp = &root->top_cgroup;
@@ -1415,7 +1395,7 @@ static int cgroup_setup_root(struct cgroupfs_root *root)
 	if (ret)
 		goto destroy_root;
 
-	ret = rebind_subsystems(root, root->subsys_mask, 0);
+	ret = rebind_subsystems(root, ss_mask, 0);
 	if (ret)
 		goto destroy_root;
 
@@ -1532,7 +1512,7 @@ retry:
 		goto out_unlock;
 	}
 
-	ret = cgroup_setup_root(root);
+	ret = cgroup_setup_root(root, opts.subsys_mask);
 	if (ret)
 		cgroup_free_root(root);
 
-- 
cgit v1.2.3


From 07bc356ed2950048d33d667e933e1b913c6e6b6d Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Thu, 13 Feb 2014 06:58:39 -0500
Subject: cgroup: implement cgroup_has_tasks() and unexport cgroup_task_count()

cgroup_task_count() read-locks css_set_lock and walks all tasks to
count them and then returns the result.  The only thing all the users
want is determining whether the cgroup is empty or not.  This patch
implements cgroup_has_tasks() which tests whether cgroup->cset_links
is empty, replaces all cgroup_task_count() usages and unexports it.

Note that the test isn't synchronized.  This is the same as before.
The test has always been racy.

This will help planned css_set locking update.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
---
 include/linux/cgroup.h | 8 ++++++--
 kernel/cgroup.c        | 2 +-
 kernel/cpuset.c        | 2 +-
 mm/memcontrol.c        | 4 ++--
 4 files changed, 10 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index e2ffcdc26cb7..72154fb44fb5 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -457,6 +457,12 @@ static inline bool cgroup_sane_behavior(const struct cgroup *cgrp)
 	return cgrp->root->flags & CGRP_ROOT_SANE_BEHAVIOR;
 }
 
+/* no synchronization, the result can only be used as a hint */
+static inline bool cgroup_has_tasks(struct cgroup *cgrp)
+{
+	return !list_empty(&cgrp->cset_links);
+}
+
 /* returns ino associated with a cgroup, 0 indicates unmounted root */
 static inline ino_t cgroup_ino(struct cgroup *cgrp)
 {
@@ -516,8 +522,6 @@ int cgroup_rm_cftypes(struct cftype *cfts);
 
 bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor);
 
-int cgroup_task_count(const struct cgroup *cgrp);
-
 /*
  * Control Group taskset, used to pass around set of tasks to cgroup_subsys
  * methods.
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 2469699408bd..ec7746e5ded1 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2391,7 +2391,7 @@ EXPORT_SYMBOL_GPL(cgroup_add_cftypes);
  *
  * Return the number of tasks in the cgroup.
  */
-int cgroup_task_count(const struct cgroup *cgrp)
+static int cgroup_task_count(const struct cgroup *cgrp)
 {
 	int count = 0;
 	struct cgrp_cset_link *link;
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index e97a6e88d036..ae190b0a196a 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -467,7 +467,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
 	 * be changed to have empty cpus_allowed or mems_allowed.
 	 */
 	ret = -ENOSPC;
-	if ((cgroup_task_count(cur->css.cgroup) || cur->attach_in_progress)) {
+	if ((cgroup_has_tasks(cur->css.cgroup) || cur->attach_in_progress)) {
 		if (!cpumask_empty(cur->cpus_allowed) &&
 		    cpumask_empty(trial->cpus_allowed))
 			goto out;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c1c25494f7ae..d9c6ac1532e6 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4958,7 +4958,7 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
 	struct cgroup *cgrp = memcg->css.cgroup;
 
 	/* returns EBUSY if there is a task or if we come here twice. */
-	if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children))
+	if (cgroup_has_tasks(cgrp) || !list_empty(&cgrp->children))
 		return -EBUSY;
 
 	/* we call try-to-free pages for make this cgroup empty */
@@ -5140,7 +5140,7 @@ static int __memcg_activate_kmem(struct mem_cgroup *memcg,
 	 * of course permitted.
 	 */
 	mutex_lock(&memcg_create_mutex);
-	if (cgroup_task_count(memcg->css.cgroup) || memcg_has_children(memcg))
+	if (cgroup_has_tasks(memcg->css.cgroup) || memcg_has_children(memcg))
 		err = -EBUSY;
 	mutex_unlock(&memcg_create_mutex);
 	if (err)
-- 
cgit v1.2.3


From 889ed9ceaa97bb02bf5d7349e24639f7fc5f4fa0 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Thu, 13 Feb 2014 06:58:40 -0500
Subject: cgroup: remove css_scan_tasks()

css_scan_tasks() doesn't have any user left.  Remove it.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h |   6 --
 kernel/cgroup.c        | 162 -------------------------------------------------
 2 files changed, 168 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 72154fb44fb5..3bd0a7138371 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -14,7 +14,6 @@
 #include <linux/rcupdate.h>
 #include <linux/rculist.h>
 #include <linux/cgroupstats.h>
-#include <linux/prio_heap.h>
 #include <linux/rwsem.h>
 #include <linux/idr.h>
 #include <linux/workqueue.h>
@@ -813,11 +812,6 @@ void css_task_iter_start(struct cgroup_subsys_state *css,
 struct task_struct *css_task_iter_next(struct css_task_iter *it);
 void css_task_iter_end(struct css_task_iter *it);
 
-int css_scan_tasks(struct cgroup_subsys_state *css,
-		   bool (*test)(struct task_struct *, void *),
-		   void (*process)(struct task_struct *, void *),
-		   void *data, struct ptr_heap *heap);
-
 int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
 int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 89428b9d9933..05c0c23549f9 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2697,168 +2697,6 @@ void css_task_iter_end(struct css_task_iter *it)
 	up_read(&css_set_rwsem);
 }
 
-static inline int started_after_time(struct task_struct *t1,
-				     struct timespec *time,
-				     struct task_struct *t2)
-{
-	int start_diff = timespec_compare(&t1->start_time, time);
-	if (start_diff > 0) {
-		return 1;
-	} else if (start_diff < 0) {
-		return 0;
-	} else {
-		/*
-		 * Arbitrarily, if two processes started at the same
-		 * time, we'll say that the lower pointer value
-		 * started first. Note that t2 may have exited by now
-		 * so this may not be a valid pointer any longer, but
-		 * that's fine - it still serves to distinguish
-		 * between two tasks started (effectively) simultaneously.
-		 */
-		return t1 > t2;
-	}
-}
-
-/*
- * This function is a callback from heap_insert() and is used to order
- * the heap.
- * In this case we order the heap in descending task start time.
- */
-static inline int started_after(void *p1, void *p2)
-{
-	struct task_struct *t1 = p1;
-	struct task_struct *t2 = p2;
-	return started_after_time(t1, &t2->start_time, t2);
-}
-
-/**
- * css_scan_tasks - iterate though all the tasks in a css
- * @css: the css to iterate tasks of
- * @test: optional test callback
- * @process: process callback
- * @data: data passed to @test and @process
- * @heap: optional pre-allocated heap used for task iteration
- *
- * Iterate through all the tasks in @css, calling @test for each, and if it
- * returns %true, call @process for it also.
- *
- * @test may be NULL, meaning always true (select all tasks), which
- * effectively duplicates css_task_iter_{start,next,end}() but does not
- * lock css_set_rwsem for the call to @process.
- *
- * It is guaranteed that @process will act on every task that is a member
- * of @css for the duration of this call.  This function may or may not
- * call @process for tasks that exit or move to a different css during the
- * call, or are forked or move into the css during the call.
- *
- * Note that @test may be called with locks held, and may in some
- * situations be called multiple times for the same task, so it should be
- * cheap.
- *
- * If @heap is non-NULL, a heap has been pre-allocated and will be used for
- * heap operations (and its "gt" member will be overwritten), else a
- * temporary heap will be used (allocation of which may cause this function
- * to fail).
- */
-int css_scan_tasks(struct cgroup_subsys_state *css,
-		   bool (*test)(struct task_struct *, void *),
-		   void (*process)(struct task_struct *, void *),
-		   void *data, struct ptr_heap *heap)
-{
-	int retval, i;
-	struct css_task_iter it;
-	struct task_struct *p, *dropped;
-	/* Never dereference latest_task, since it's not refcounted */
-	struct task_struct *latest_task = NULL;
-	struct ptr_heap tmp_heap;
-	struct timespec latest_time = { 0, 0 };
-
-	if (heap) {
-		/* The caller supplied our heap and pre-allocated its memory */
-		heap->gt = &started_after;
-	} else {
-		/* We need to allocate our own heap memory */
-		heap = &tmp_heap;
-		retval = heap_init(heap, PAGE_SIZE, GFP_KERNEL, &started_after);
-		if (retval)
-			/* cannot allocate the heap */
-			return retval;
-	}
-
- again:
-	/*
-	 * Scan tasks in the css, using the @test callback to determine
-	 * which are of interest, and invoking @process callback on the
-	 * ones which need an update.  Since we don't want to hold any
-	 * locks during the task updates, gather tasks to be processed in a
-	 * heap structure.  The heap is sorted by descending task start
-	 * time.  If the statically-sized heap fills up, we overflow tasks
-	 * that started later, and in future iterations only consider tasks
-	 * that started after the latest task in the previous pass. This
-	 * guarantees forward progress and that we don't miss any tasks.
-	 */
-	heap->size = 0;
-	css_task_iter_start(css, &it);
-	while ((p = css_task_iter_next(&it))) {
-		/*
-		 * Only affect tasks that qualify per the caller's callback,
-		 * if he provided one
-		 */
-		if (test && !test(p, data))
-			continue;
-		/*
-		 * Only process tasks that started after the last task
-		 * we processed
-		 */
-		if (!started_after_time(p, &latest_time, latest_task))
-			continue;
-		dropped = heap_insert(heap, p);
-		if (dropped == NULL) {
-			/*
-			 * The new task was inserted; the heap wasn't
-			 * previously full
-			 */
-			get_task_struct(p);
-		} else if (dropped != p) {
-			/*
-			 * The new task was inserted, and pushed out a
-			 * different task
-			 */
-			get_task_struct(p);
-			put_task_struct(dropped);
-		}
-		/*
-		 * Else the new task was newer than anything already in
-		 * the heap and wasn't inserted
-		 */
-	}
-	css_task_iter_end(&it);
-
-	if (heap->size) {
-		for (i = 0; i < heap->size; i++) {
-			struct task_struct *q = heap->ptrs[i];
-			if (i == 0) {
-				latest_time = q->start_time;
-				latest_task = q;
-			}
-			/* Process the task per the caller's callback */
-			process(q, data);
-			put_task_struct(q);
-		}
-		/*
-		 * If we had to process any tasks at all, scan again
-		 * in case some of them were in the middle of forking
-		 * children that didn't get processed.
-		 * Not the most efficient way to do it, but it avoids
-		 * having to take callback_mutex in the fork path
-		 */
-		goto again;
-	}
-	if (heap == &tmp_heap)
-		heap_free(&tmp_heap);
-	return 0;
-}
-
 /**
  * cgroup_trasnsfer_tasks - move tasks from one cgroup to another
  * @to: cgroup to which the tasks will be moved
-- 
cgit v1.2.3


From 924f0d9a2078f49ff331bb43196ec5afadc16b8f Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Thu, 13 Feb 2014 06:58:41 -0500
Subject: cgroup: drop @skip_css from cgroup_taskset_for_each()

If !NULL, @skip_css makes cgroup_taskset_for_each() skip the matching
css.  The intention of the interface is to make it easy to skip css's
(cgroup_subsys_states) which already match the migration target;
however, this is entirely unnecessary as migration taskset doesn't
include tasks which are already in the target cgroup.  Drop @skip_css
from cgroup_taskset_for_each().

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Daniel Borkmann <dborkman@redhat.com>
---
 block/blk-cgroup.c           | 2 +-
 include/linux/cgroup.h       | 8 ++------
 kernel/cgroup_freezer.c      | 2 +-
 kernel/cpuset.c              | 4 ++--
 kernel/events/core.c         | 2 +-
 kernel/sched/core.c          | 4 ++--
 net/core/netclassid_cgroup.c | 2 +-
 net/core/netprio_cgroup.c    | 2 +-
 8 files changed, 11 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 1cef07cf9c21..4aefd46d7d95 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -894,7 +894,7 @@ static int blkcg_can_attach(struct cgroup_subsys_state *css,
 	int ret = 0;
 
 	/* task_lock() is needed to avoid races with exit_io_context() */
-	cgroup_taskset_for_each(task, css, tset) {
+	cgroup_taskset_for_each(task, tset) {
 		task_lock(task);
 		ioc = task->io_context;
 		if (ioc && atomic_read(&ioc->nr_tasks) > 1)
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 3bd0a7138371..581a124c7bc8 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -535,15 +535,11 @@ int cgroup_taskset_size(struct cgroup_taskset *tset);
 /**
  * cgroup_taskset_for_each - iterate cgroup_taskset
  * @task: the loop cursor
- * @skip_css: skip if task's css matches this, %NULL to iterate through all
  * @tset: taskset to iterate
  */
-#define cgroup_taskset_for_each(task, skip_css, tset)			\
+#define cgroup_taskset_for_each(task, tset)				\
 	for ((task) = cgroup_taskset_first((tset)); (task);		\
-	     (task) = cgroup_taskset_next((tset)))			\
-		if (!(skip_css) ||					\
-		    cgroup_taskset_cur_css((tset),			\
-			(skip_css)->ss->id) != (skip_css))
+	     (task) = cgroup_taskset_next((tset)))
 
 /*
  * Control Group subsystem type.
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index 98ea26a99076..7201a637c405 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -187,7 +187,7 @@ static void freezer_attach(struct cgroup_subsys_state *new_css,
 	 * current state before executing the following - !frozen tasks may
 	 * be visible in a FROZEN cgroup and frozen tasks in a THAWED one.
 	 */
-	cgroup_taskset_for_each(task, new_css, tset) {
+	cgroup_taskset_for_each(task, tset) {
 		if (!(freezer->state & CGROUP_FREEZING)) {
 			__thaw_task(task);
 		} else {
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 65ae0bdf4af8..bf20e4ac2f75 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1398,7 +1398,7 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css,
 	    (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)))
 		goto out_unlock;
 
-	cgroup_taskset_for_each(task, css, tset) {
+	cgroup_taskset_for_each(task, tset) {
 		/*
 		 * Kthreads which disallow setaffinity shouldn't be moved
 		 * to a new cpuset; we don't want to change their cpu
@@ -1467,7 +1467,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 
 	guarantee_online_mems(mems_cs, &cpuset_attach_nodemask_to);
 
-	cgroup_taskset_for_each(task, css, tset) {
+	cgroup_taskset_for_each(task, tset) {
 		/*
 		 * can_attach beforehand should guarantee that this doesn't
 		 * fail.  TODO: have a better way to handle failure here
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a3c3ab50271a..6dd714955b04 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8021,7 +8021,7 @@ static void perf_cgroup_attach(struct cgroup_subsys_state *css,
 {
 	struct task_struct *task;
 
-	cgroup_taskset_for_each(task, css, tset)
+	cgroup_taskset_for_each(task, tset)
 		task_function_call(task, __perf_cgroup_move, task);
 }
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d4cfc5561830..ba386a06ab11 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7600,7 +7600,7 @@ static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css,
 {
 	struct task_struct *task;
 
-	cgroup_taskset_for_each(task, css, tset) {
+	cgroup_taskset_for_each(task, tset) {
 #ifdef CONFIG_RT_GROUP_SCHED
 		if (!sched_rt_can_attach(css_tg(css), task))
 			return -EINVAL;
@@ -7618,7 +7618,7 @@ static void cpu_cgroup_attach(struct cgroup_subsys_state *css,
 {
 	struct task_struct *task;
 
-	cgroup_taskset_for_each(task, css, tset)
+	cgroup_taskset_for_each(task, tset)
 		sched_move_task(task);
 }
 
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index b865662fba71..22931e1b99b4 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -73,7 +73,7 @@ static void cgrp_attach(struct cgroup_subsys_state *css,
 	void *v = (void *)(unsigned long)cs->classid;
 	struct task_struct *p;
 
-	cgroup_taskset_for_each(p, css, tset) {
+	cgroup_taskset_for_each(p, tset) {
 		task_lock(p);
 		iterate_fd(p->files, 0, update_classid, v);
 		task_unlock(p);
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index d7d23e28fafd..f9f3a40d3350 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -224,7 +224,7 @@ static void net_prio_attach(struct cgroup_subsys_state *css,
 	struct task_struct *p;
 	void *v = (void *)(unsigned long)css->cgroup->id;
 
-	cgroup_taskset_for_each(p, css, tset) {
+	cgroup_taskset_for_each(p, tset) {
 		task_lock(p);
 		iterate_fd(p->files, 0, update_netprio, v);
 		task_unlock(p);
-- 
cgit v1.2.3


From bc668c7519ff8b4681af80e92f463bec7bf7cf9e Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Thu, 13 Feb 2014 06:58:43 -0500
Subject: cgroup: remove cgroup_taskset_cur_css() and cgroup_taskset_size()

The two functions don't have any users left.  Remove them along with
cgroup_taskset->cur_cgrp.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h |  3 ---
 kernel/cgroup.c        | 30 ------------------------------
 2 files changed, 33 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 581a124c7bc8..ef0b3af0e61c 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -528,9 +528,6 @@ bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor);
 struct cgroup_taskset;
 struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset);
 struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset);
-struct cgroup_subsys_state *cgroup_taskset_cur_css(struct cgroup_taskset *tset,
-						   int subsys_id);
-int cgroup_taskset_size(struct cgroup_taskset *tset);
 
 /**
  * cgroup_taskset_for_each - iterate cgroup_taskset
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 704c590a81d7..a9d9bbb12310 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1647,7 +1647,6 @@ struct cgroup_taskset {
 	struct flex_array	*tc_array;
 	int			tc_array_len;
 	int			idx;
-	struct cgroup		*cur_cgrp;
 };
 
 /**
@@ -1662,7 +1661,6 @@ struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset)
 		tset->idx = 0;
 		return cgroup_taskset_next(tset);
 	} else {
-		tset->cur_cgrp = tset->single.cgrp;
 		return tset->single.task;
 	}
 }
@@ -1683,38 +1681,10 @@ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
 		return NULL;
 
 	tc = flex_array_get(tset->tc_array, tset->idx++);
-	tset->cur_cgrp = tc->cgrp;
 	return tc->task;
 }
 EXPORT_SYMBOL_GPL(cgroup_taskset_next);
 
-/**
- * cgroup_taskset_cur_css - return the matching css for the current task
- * @tset: taskset of interest
- * @subsys_id: the ID of the target subsystem
- *
- * Return the css for the current (last returned) task of @tset for
- * subsystem specified by @subsys_id.  This function must be preceded by
- * either cgroup_taskset_first() or cgroup_taskset_next().
- */
-struct cgroup_subsys_state *cgroup_taskset_cur_css(struct cgroup_taskset *tset,
-						   int subsys_id)
-{
-	return cgroup_css(tset->cur_cgrp, cgroup_subsys[subsys_id]);
-}
-EXPORT_SYMBOL_GPL(cgroup_taskset_cur_css);
-
-/**
- * cgroup_taskset_size - return the number of tasks in taskset
- * @tset: taskset of interest
- */
-int cgroup_taskset_size(struct cgroup_taskset *tset)
-{
-	return tset->tc_array ? tset->tc_array_len : 1;
-}
-EXPORT_SYMBOL_GPL(cgroup_taskset_size);
-
-
 /**
  * cgroup_task_migrate - move a task from one cgroup to another.
  * @old_cgrp; the cgroup @tsk is being migrated from
-- 
cgit v1.2.3


From dc1b5ba150732738f905b277ad7317b188ce09e9 Mon Sep 17 00:00:00 2001
From: Jean-Francois Dagenais <jeff.dagenais@gmail.com>
Date: Mon, 10 Feb 2014 12:24:04 -0500
Subject: gpio: adp5588 - use "unsigned" for the setup and teardown callbacks

to comply with the rest of the GPIO drivers.

Signed-off-by: Jean-Francois Dagenais <jeff.dagenais@gmail.com>
Acked-by: Michael Hennerich <michael.hennerich@analog.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/linux/i2c/adp5588.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/i2c/adp5588.h b/include/linux/i2c/adp5588.h
index d8341cb47b60..c2153049cfbd 100644
--- a/include/linux/i2c/adp5588.h
+++ b/include/linux/i2c/adp5588.h
@@ -161,10 +161,10 @@ struct adp5588_gpio_platform_data {
 	unsigned irq_base;	/* interrupt base # */
 	unsigned pullup_dis_mask; /* Pull-Up Disable Mask */
 	int	(*setup)(struct i2c_client *client,
-				int gpio, unsigned ngpio,
+				unsigned gpio, unsigned ngpio,
 				void *context);
 	int	(*teardown)(struct i2c_client *client,
-				int gpio, unsigned ngpio,
+				unsigned gpio, unsigned ngpio,
 				void *context);
 	void	*context;
 };
-- 
cgit v1.2.3


From 1e6128b63597adf97f1865fba7d778a6f8ccb7a0 Mon Sep 17 00:00:00 2001
From: Alexander Shiyan <shc_work@mail.ru>
Date: Fri, 7 Feb 2014 18:16:05 +0400
Subject: serial: max310x: Remove init() and exit() callbacks

These callbacks were previously used for the IC power initialization.
If this initialization will be needed in the future, it should be
implemented with the regulator API.

Signed-off-by: Alexander Shiyan <shc_work@mail.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/max310x.c          | 7 -------
 include/linux/platform_data/max310x.h | 4 ----
 2 files changed, 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c
index 313bdf0bb21b..202c1fb6542d 100644
--- a/drivers/tty/serial/max310x.c
+++ b/drivers/tty/serial/max310x.c
@@ -1135,10 +1135,6 @@ static int max310x_probe(struct device *dev, int is_spi,
 		return PTR_ERR(s->regmap);
 	}
 
-	/* Board specific configure */
-	if (s->pdata->init)
-		s->pdata->init();
-
 	/* Check device to ensure we are talking to what we expect */
 	ret = devtype->detect(dev);
 	if (ret)
@@ -1265,9 +1261,6 @@ static int max310x_remove(struct device *dev)
 		ret = gpiochip_remove(&s->gpio);
 #endif
 
-	if (s->pdata->exit)
-		s->pdata->exit();
-
 	return ret;
 }
 
diff --git a/include/linux/platform_data/max310x.h b/include/linux/platform_data/max310x.h
index dd11dcd1a184..5f4b35d99c2e 100644
--- a/include/linux/platform_data/max310x.h
+++ b/include/linux/platform_data/max310x.h
@@ -55,10 +55,6 @@ struct max310x_pdata {
 	const int		frequency;
 	/* GPIO base number (can be negative) */
 	const int		gpio_base;
-	/* Called during startup */
-	void (*init)(void);
-	/* Called before finish */
-	void (*exit)(void);
 };
 
 #endif
-- 
cgit v1.2.3


From e7b8a3ceff5e5c4e2bd329717976b18ce033d7cd Mon Sep 17 00:00:00 2001
From: Alexander Shiyan <shc_work@mail.ru>
Date: Fri, 7 Feb 2014 18:16:07 +0400
Subject: serial: max310x: Add the loopback mode support

This patch replaces loopback mode support from platform data to
dynamic setup with TIOCMSET ioctl.

Signed-off-by: Alexander Shiyan <shc_work@mail.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/max310x.c          | 25 ++++++++++++++++++-------
 include/linux/platform_data/max310x.h |  1 -
 2 files changed, 18 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c
index 1fb3895a0a3a..3c93814b1648 100644
--- a/drivers/tty/serial/max310x.c
+++ b/drivers/tty/serial/max310x.c
@@ -283,6 +283,7 @@ struct max310x_devtype {
 struct max310x_one {
 	struct uart_port	port;
 	struct work_struct	tx_work;
+	struct work_struct	md_work;
 };
 
 struct max310x_port {
@@ -790,11 +791,21 @@ static unsigned int max310x_get_mctrl(struct uart_port *port)
 	return TIOCM_DSR | TIOCM_CAR;
 }
 
+static void max310x_md_proc(struct work_struct *ws)
+{
+	struct max310x_one *one = container_of(ws, struct max310x_one, md_work);
+
+	max310x_port_update(&one->port, MAX310X_MODE2_REG,
+			    MAX310X_MODE2_LOOPBACK_BIT,
+			    (one->port.mctrl & TIOCM_LOOP) ?
+			    MAX310X_MODE2_LOOPBACK_BIT : 0);
+}
+
 static void max310x_set_mctrl(struct uart_port *port, unsigned int mctrl)
 {
-	/* DCD and DSR are not wired and CTS/RTS is hadnled automatically
-	 * so do nothing
-	 */
+	struct max310x_one *one = container_of(port, struct max310x_one, port);
+
+	schedule_work(&one->md_work);
 }
 
 static void max310x_break_ctl(struct uart_port *port, int break_state)
@@ -904,8 +915,6 @@ static int max310x_startup(struct uart_port *port)
 
 	/* Configure MODE2 register */
 	val = MAX310X_MODE2_RXEMPTINV_BIT;
-	if (s->pdata->uart_flags[line] & MAX310X_LOOPBACK)
-		val |= MAX310X_MODE2_LOOPBACK_BIT;
 	if (s->pdata->uart_flags[line] & MAX310X_ECHO_SUPRESS)
 		val |= MAX310X_MODE2_ECHOSUPR_BIT;
 
@@ -1176,8 +1185,7 @@ static int max310x_probe(struct device *dev, int is_spi,
 		s->p[i].port.irq	= irq;
 		s->p[i].port.type	= PORT_MAX310X;
 		s->p[i].port.fifosize	= MAX310X_FIFO_SIZE;
-		s->p[i].port.flags	= UPF_SKIP_TEST | UPF_FIXED_TYPE |
-					  UPF_LOW_LATENCY;
+		s->p[i].port.flags	= UPF_FIXED_TYPE | UPF_LOW_LATENCY;
 		s->p[i].port.iotype	= UPIO_PORT;
 		s->p[i].port.iobase	= i * 0x20;
 		s->p[i].port.membase	= (void __iomem *)~0;
@@ -1193,6 +1201,8 @@ static int max310x_probe(struct device *dev, int is_spi,
 				    MAX310X_MODE1_IRQSEL_BIT);
 		/* Initialize queue for start TX */
 		INIT_WORK(&s->p[i].tx_work, max310x_wq_proc);
+		/* Initialize queue for changing mode */
+		INIT_WORK(&s->p[i].md_work, max310x_md_proc);
 		/* Register port */
 		uart_add_one_port(&s->uart, &s->p[i].port);
 		/* Go to suspend mode */
@@ -1244,6 +1254,7 @@ static int max310x_remove(struct device *dev)
 
 	for (i = 0; i < s->uart.nr; i++) {
 		cancel_work_sync(&s->p[i].tx_work);
+		cancel_work_sync(&s->p[i].md_work);
 		uart_remove_one_port(&s->uart, &s->p[i].port);
 		s->devtype->power(&s->p[i].port, 0);
 	}
diff --git a/include/linux/platform_data/max310x.h b/include/linux/platform_data/max310x.h
index 5f4b35d99c2e..9d5f69b2b57c 100644
--- a/include/linux/platform_data/max310x.h
+++ b/include/linux/platform_data/max310x.h
@@ -46,7 +46,6 @@ struct max310x_pdata {
 #define MAX310X_EXT_CLK		(0x00000001)	/* External clock enable */
 	/* Flags global to UART port */
 	const u8		uart_flags[MAX310X_MAX_UARTS];
-#define MAX310X_LOOPBACK	(0x00000001)	/* Loopback mode enable */
 #define MAX310X_ECHO_SUPRESS	(0x00000002)	/* Enable echo supress */
 #define MAX310X_AUTO_DIR_CTRL	(0x00000004)	/* Enable Auto direction
 						 * control (RS-485)
-- 
cgit v1.2.3


From d3a8a252e177cfaa2fb04120dd944104e4417bf5 Mon Sep 17 00:00:00 2001
From: Alexander Shiyan <shc_work@mail.ru>
Date: Mon, 10 Feb 2014 22:18:31 +0400
Subject: serial: max310x: Migrate to CLK API

This patch removes "frequency" parameter from MAX310X platform_data
and uses CLK API for getting clock. Clock type (XTAL/OSC) is
determined by clk name.

Signed-off-by: Alexander Shiyan <shc_work@mail.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/max310x.c          | 86 ++++++++++++++++++++++-------------
 include/linux/platform_data/max310x.h |  7 ---
 2 files changed, 55 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c
index 9e147f3d7291..310ee555fade 100644
--- a/drivers/tty/serial/max310x.c
+++ b/drivers/tty/serial/max310x.c
@@ -17,6 +17,7 @@
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/bitops.h>
+#include <linux/clk.h>
 #include <linux/serial_core.h>
 #include <linux/serial.h>
 #include <linux/tty.h>
@@ -291,6 +292,7 @@ struct max310x_port {
 	struct max310x_devtype	*devtype;
 	struct regmap		*regmap;
 	struct mutex		mutex;
+	struct clk		*clk;
 	struct max310x_pdata	*pdata;
 	int			gpio_used;
 #ifdef CONFIG_GPIOLIB
@@ -546,18 +548,19 @@ static int max310x_update_best_err(unsigned long f, long *besterr)
 	return 1;
 }
 
-static int max310x_set_ref_clk(struct max310x_port *s)
+static int max310x_set_ref_clk(struct max310x_port *s, unsigned long freq,
+			       bool xtal)
 {
 	unsigned int div, clksrc, pllcfg = 0;
 	long besterr = -1;
-	unsigned long fdiv, fmul, bestfreq = s->pdata->frequency;
+	unsigned long fdiv, fmul, bestfreq = freq;
 
 	/* First, update error without PLL */
-	max310x_update_best_err(s->pdata->frequency, &besterr);
+	max310x_update_best_err(freq, &besterr);
 
 	/* Try all possible PLL dividers */
 	for (div = 1; (div <= 63) && besterr; div++) {
-		fdiv = DIV_ROUND_CLOSEST(s->pdata->frequency, div);
+		fdiv = DIV_ROUND_CLOSEST(freq, div);
 
 		/* Try multiplier 6 */
 		fmul = fdiv * 6;
@@ -590,10 +593,7 @@ static int max310x_set_ref_clk(struct max310x_port *s)
 	}
 
 	/* Configure clock source */
-	if (s->pdata->driver_flags & MAX310X_EXT_CLK)
-		clksrc = MAX310X_CLKSRC_EXTCLK_BIT;
-	else
-		clksrc = MAX310X_CLKSRC_CRYST_BIT;
+	clksrc = xtal ? MAX310X_CLKSRC_CRYST_BIT : MAX310X_CLKSRC_EXTCLK_BIT;
 
 	/* Configure PLL */
 	if (pllcfg) {
@@ -605,7 +605,7 @@ static int max310x_set_ref_clk(struct max310x_port *s)
 	regmap_write(s->regmap, MAX310X_CLKSRC_REG, clksrc);
 
 	/* Wait for crystal */
-	if (pllcfg && !(s->pdata->driver_flags & MAX310X_EXT_CLK))
+	if (pllcfg && xtal)
 		msleep(10);
 
 	return (int)bestfreq;
@@ -1078,9 +1078,11 @@ static int max310x_gpio_direction_output(struct gpio_chip *chip,
 static int max310x_probe(struct device *dev, struct max310x_devtype *devtype,
 			 struct regmap *regmap, int irq)
 {
-	struct max310x_port *s;
 	struct max310x_pdata *pdata = dev_get_platdata(dev);
-	int i, ret, uartclk;
+	int i, ret, fmin, fmax, freq, uartclk;
+	struct clk *clk_osc, *clk_xtal;
+	struct max310x_port *s;
+	bool xtal = false;
 
 	if (IS_ERR(regmap))
 		return PTR_ERR(regmap);
@@ -1098,14 +1100,35 @@ static int max310x_probe(struct device *dev, struct max310x_devtype *devtype,
 		return -ENOMEM;
 	}
 
-	/* Check input frequency */
-	if ((pdata->driver_flags & MAX310X_EXT_CLK) &&
-	   ((pdata->frequency < 500000) || (pdata->frequency > 35000000)))
-		goto err_freq;
-	/* Check frequency for quartz */
-	if (!(pdata->driver_flags & MAX310X_EXT_CLK) &&
-	   ((pdata->frequency < 1000000) || (pdata->frequency > 4000000)))
-		goto err_freq;
+	clk_osc = devm_clk_get(dev, "osc");
+	clk_xtal = devm_clk_get(dev, "xtal");
+	if (!IS_ERR(clk_osc)) {
+		s->clk = clk_osc;
+		fmin = 500000;
+		fmax = 35000000;
+	} else if (!IS_ERR(clk_xtal)) {
+		s->clk = clk_xtal;
+		fmin = 1000000;
+		fmax = 4000000;
+		xtal = true;
+	} else if (PTR_ERR(clk_osc) == -EPROBE_DEFER ||
+		   PTR_ERR(clk_xtal) == -EPROBE_DEFER) {
+		return -EPROBE_DEFER;
+	} else {
+		dev_err(dev, "Cannot get clock\n");
+		return -EINVAL;
+	}
+
+	ret = clk_prepare_enable(s->clk);
+	if (ret)
+		return ret;
+
+	freq = clk_get_rate(s->clk);
+	/* Check frequency limits */
+	if (freq < fmin || freq > fmax) {
+		ret = -ERANGE;
+		goto out_clk;
+	}
 
 	s->pdata = pdata;
 	s->regmap = regmap;
@@ -1117,7 +1140,7 @@ static int max310x_probe(struct device *dev, struct max310x_devtype *devtype,
 	/* Check device to ensure we are talking to what we expect */
 	ret = devtype->detect(dev);
 	if (ret)
-		return ret;
+		goto out_clk;
 
 	for (i = 0; i < devtype->nr; i++) {
 		unsigned int offs = i << 5;
@@ -1139,7 +1162,7 @@ static int max310x_probe(struct device *dev, struct max310x_devtype *devtype,
 				   MAX310X_MODE1_AUTOSLEEP_BIT);
 	}
 
-	uartclk = max310x_set_ref_clk(s);
+	uartclk = max310x_set_ref_clk(s, freq, xtal);
 	dev_dbg(dev, "Reference clock set to %i Hz\n", uartclk);
 
 	/* Register UART driver */
@@ -1151,7 +1174,7 @@ static int max310x_probe(struct device *dev, struct max310x_devtype *devtype,
 	ret = uart_register_driver(&s->uart);
 	if (ret) {
 		dev_err(dev, "Registering UART driver failed\n");
-		return ret;
+		goto out_clk;
 	}
 
 	for (i = 0; i < devtype->nr; i++) {
@@ -1208,19 +1231,19 @@ static int max310x_probe(struct device *dev, struct max310x_devtype *devtype,
 	ret = devm_request_threaded_irq(dev, irq, NULL, max310x_ist,
 					IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
 					dev_name(dev), s);
-	if (ret) {
-		dev_err(dev, "Unable to reguest IRQ %i\n", irq);
+	if (!ret)
+		return 0;
+
+	dev_err(dev, "Unable to reguest IRQ %i\n", irq);
 #ifdef CONFIG_GPIOLIB
-		if (s->gpio_used)
-			WARN_ON(gpiochip_remove(&s->gpio));
+	if (s->gpio_used)
+		WARN_ON(gpiochip_remove(&s->gpio));
 #endif
-	}
 
-	return ret;
+out_clk:
+	clk_disable_unprepare(s->clk);
 
-err_freq:
-	dev_err(dev, "Frequency parameter incorrect\n");
-	return -EINVAL;
+	return ret;
 }
 
 static int max310x_remove(struct device *dev)
@@ -1236,6 +1259,7 @@ static int max310x_remove(struct device *dev)
 	}
 
 	uart_unregister_driver(&s->uart);
+	clk_disable_unprepare(s->clk);
 
 #ifdef CONFIG_GPIOLIB
 	if (s->gpio_used)
diff --git a/include/linux/platform_data/max310x.h b/include/linux/platform_data/max310x.h
index 9d5f69b2b57c..57a0cd46b847 100644
--- a/include/linux/platform_data/max310x.h
+++ b/include/linux/platform_data/max310x.h
@@ -20,9 +20,7 @@
  * Example board initialization data:
  *
  * static struct max310x_pdata max3107_pdata = {
- *	.driver_flags	= MAX310X_EXT_CLK,
  *	.uart_flags[0]	= MAX310X_ECHO_SUPRESS | MAX310X_AUTO_DIR_CTRL,
- *	.frequency	= 3686400,
  *	.gpio_base	= -1,
  * };
  *
@@ -41,17 +39,12 @@
 
 /* MAX310X platform data structure */
 struct max310x_pdata {
-	/* Flags global to driver */
-	const u8		driver_flags;
-#define MAX310X_EXT_CLK		(0x00000001)	/* External clock enable */
 	/* Flags global to UART port */
 	const u8		uart_flags[MAX310X_MAX_UARTS];
 #define MAX310X_ECHO_SUPRESS	(0x00000002)	/* Enable echo supress */
 #define MAX310X_AUTO_DIR_CTRL	(0x00000004)	/* Enable Auto direction
 						 * control (RS-485)
 						 */
-	/* Frequency (extrenal clock or crystal) */
-	const int		frequency;
 	/* GPIO base number (can be negative) */
 	const int		gpio_base;
 };
-- 
cgit v1.2.3


From dba29a2894771562d265232ae4b61f0310bab1f5 Mon Sep 17 00:00:00 2001
From: Alexander Shiyan <shc_work@mail.ru>
Date: Mon, 10 Feb 2014 22:18:32 +0400
Subject: serial: max310x: Always use dynamic GPIO ID assignment

Always register GPIOs and use dynamic GPIO ID assignment.
This is no much worth if GPIOs is not used, but helps remove
private driver header and add DT support in the future.
Additionally, patch adds missing uart_unregister_driver()
call if probe() fails.

Signed-off-by: Alexander Shiyan <shc_work@mail.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/max310x.c          | 55 ++++++++++++++++++-----------------
 include/linux/platform_data/max310x.h |  3 --
 2 files changed, 28 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c
index 310ee555fade..2a12cbcbf388 100644
--- a/drivers/tty/serial/max310x.c
+++ b/drivers/tty/serial/max310x.c
@@ -294,7 +294,6 @@ struct max310x_port {
 	struct mutex		mutex;
 	struct clk		*clk;
 	struct max310x_pdata	*pdata;
-	int			gpio_used;
 #ifdef CONFIG_GPIOLIB
 	struct gpio_chip	gpio;
 #endif
@@ -1177,6 +1176,23 @@ static int max310x_probe(struct device *dev, struct max310x_devtype *devtype,
 		goto out_clk;
 	}
 
+#ifdef CONFIG_GPIOLIB
+	/* Setup GPIO cotroller */
+	s->gpio.owner		= THIS_MODULE;
+	s->gpio.dev		= dev;
+	s->gpio.label		= dev_name(dev);
+	s->gpio.direction_input	= max310x_gpio_direction_input;
+	s->gpio.get		= max310x_gpio_get;
+	s->gpio.direction_output= max310x_gpio_direction_output;
+	s->gpio.set		= max310x_gpio_set;
+	s->gpio.base		= -1;
+	s->gpio.ngpio		= devtype->nr * 4;
+	s->gpio.can_sleep	= 1;
+	ret = gpiochip_add(&s->gpio);
+	if (ret)
+		goto out_uart;
+#endif
+
 	for (i = 0; i < devtype->nr; i++) {
 		/* Initialize port data */
 		s->p[i].port.line	= i;
@@ -1208,25 +1224,6 @@ static int max310x_probe(struct device *dev, struct max310x_devtype *devtype,
 		devtype->power(&s->p[i].port, 0);
 	}
 
-#ifdef CONFIG_GPIOLIB
-	/* Setup GPIO cotroller */
-	if (s->pdata->gpio_base) {
-		s->gpio.owner		= THIS_MODULE;
-		s->gpio.dev		= dev;
-		s->gpio.label		= dev_name(dev);
-		s->gpio.direction_input	= max310x_gpio_direction_input;
-		s->gpio.get		= max310x_gpio_get;
-		s->gpio.direction_output= max310x_gpio_direction_output;
-		s->gpio.set		= max310x_gpio_set;
-		s->gpio.base		= s->pdata->gpio_base;
-		s->gpio.ngpio		= devtype->nr * 4;
-		s->gpio.can_sleep	= 1;
-		if (!gpiochip_add(&s->gpio))
-			s->gpio_used = 1;
-	} else
-		dev_info(dev, "GPIO support not enabled\n");
-#endif
-
 	/* Setup interrupt */
 	ret = devm_request_threaded_irq(dev, irq, NULL, max310x_ist,
 					IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
@@ -1235,11 +1232,14 @@ static int max310x_probe(struct device *dev, struct max310x_devtype *devtype,
 		return 0;
 
 	dev_err(dev, "Unable to reguest IRQ %i\n", irq);
+
 #ifdef CONFIG_GPIOLIB
-	if (s->gpio_used)
-		WARN_ON(gpiochip_remove(&s->gpio));
+	WARN_ON(gpiochip_remove(&s->gpio));
 #endif
 
+out_uart:
+	uart_unregister_driver(&s->uart);
+
 out_clk:
 	clk_disable_unprepare(s->clk);
 
@@ -1251,6 +1251,12 @@ static int max310x_remove(struct device *dev)
 	struct max310x_port *s = dev_get_drvdata(dev);
 	int i, ret = 0;
 
+#ifdef CONFIG_GPIOLIB
+	ret = gpiochip_remove(&s->gpio);
+	if (ret)
+		return ret;
+#endif
+
 	for (i = 0; i < s->uart.nr; i++) {
 		cancel_work_sync(&s->p[i].tx_work);
 		cancel_work_sync(&s->p[i].md_work);
@@ -1261,11 +1267,6 @@ static int max310x_remove(struct device *dev)
 	uart_unregister_driver(&s->uart);
 	clk_disable_unprepare(s->clk);
 
-#ifdef CONFIG_GPIOLIB
-	if (s->gpio_used)
-		ret = gpiochip_remove(&s->gpio);
-#endif
-
 	return ret;
 }
 
diff --git a/include/linux/platform_data/max310x.h b/include/linux/platform_data/max310x.h
index 57a0cd46b847..1140a57e735f 100644
--- a/include/linux/platform_data/max310x.h
+++ b/include/linux/platform_data/max310x.h
@@ -21,7 +21,6 @@
  *
  * static struct max310x_pdata max3107_pdata = {
  *	.uart_flags[0]	= MAX310X_ECHO_SUPRESS | MAX310X_AUTO_DIR_CTRL,
- *	.gpio_base	= -1,
  * };
  *
  * static struct spi_board_info spi_device_max3107[] = {
@@ -45,8 +44,6 @@ struct max310x_pdata {
 #define MAX310X_AUTO_DIR_CTRL	(0x00000004)	/* Enable Auto direction
 						 * control (RS-485)
 						 */
-	/* GPIO base number (can be negative) */
-	const int		gpio_base;
 };
 
 #endif
-- 
cgit v1.2.3


From 55367c620aed6bc27a82bb1763366931d7f2ee66 Mon Sep 17 00:00:00 2001
From: Alexander Shiyan <shc_work@mail.ru>
Date: Mon, 10 Feb 2014 22:18:34 +0400
Subject: serial: max310x: Add support for RS-485 mode

This patch adds support for RS-485 (TIOCSRS485/TIOCGRS485) IOCTLs.
As a result this patch eliminate private driver header.

Signed-off-by: Alexander Shiyan <shc_work@mail.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/max310x.c          | 77 +++++++++++++++++++++++++----------
 include/linux/platform_data/max310x.h | 49 ----------------------
 2 files changed, 56 insertions(+), 70 deletions(-)
 delete mode 100644 include/linux/platform_data/max310x.h

(limited to 'include/linux')

diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c
index c180576546ed..090f25d4a019 100644
--- a/drivers/tty/serial/max310x.c
+++ b/drivers/tty/serial/max310x.c
@@ -26,8 +26,6 @@
 #include <linux/gpio.h>
 #include <linux/spi/spi.h>
 
-#include <linux/platform_data/max310x.h>
-
 #define MAX310X_NAME			"max310x"
 #define MAX310X_MAJOR			204
 #define MAX310X_MINOR			209
@@ -293,7 +291,6 @@ struct max310x_port {
 	struct regmap		*regmap;
 	struct mutex		mutex;
 	struct clk		*clk;
-	struct max310x_pdata	*pdata;
 #ifdef CONFIG_GPIOLIB
 	struct gpio_chip	gpio;
 #endif
@@ -898,26 +895,70 @@ static void max310x_set_termios(struct uart_port *port,
 	uart_update_timeout(port, termios->c_cflag, baud);
 }
 
+static int max310x_ioctl(struct uart_port *port, unsigned int cmd,
+			 unsigned long arg)
+{
+	struct serial_rs485 rs485;
+	unsigned int val;
+
+	switch (cmd) {
+	case TIOCSRS485:
+		if (copy_from_user(&rs485, (struct serial_rs485 *)arg,
+				   sizeof(rs485)))
+			return -EFAULT;
+		if (rs485.delay_rts_before_send > 0x0f ||
+		    rs485.delay_rts_after_send > 0x0f)
+			return -ERANGE;
+		val = (rs485.delay_rts_before_send << 4) |
+		      rs485.delay_rts_after_send;
+		max310x_port_write(port, MAX310X_HDPIXDELAY_REG, val);
+		if (rs485.flags & SER_RS485_ENABLED) {
+			max310x_port_update(port, MAX310X_MODE1_REG,
+					    MAX310X_MODE1_TRNSCVCTRL_BIT,
+					    MAX310X_MODE1_TRNSCVCTRL_BIT);
+			max310x_port_update(port, MAX310X_MODE2_REG,
+					    MAX310X_MODE2_ECHOSUPR_BIT,
+					    MAX310X_MODE2_ECHOSUPR_BIT);
+		} else {
+			max310x_port_update(port, MAX310X_MODE1_REG,
+					    MAX310X_MODE1_TRNSCVCTRL_BIT, 0);
+			max310x_port_update(port, MAX310X_MODE2_REG,
+					    MAX310X_MODE2_ECHOSUPR_BIT, 0);
+		}
+		break;
+	case TIOCGRS485:
+		memset(&rs485, 0, sizeof(rs485));
+		val = max310x_port_read(port, MAX310X_MODE1_REG);
+		rs485.flags = (val & MAX310X_MODE1_TRNSCVCTRL_BIT) ?
+			      SER_RS485_ENABLED : 0;
+		rs485.flags |= SER_RS485_RTS_ON_SEND;
+		val = max310x_port_read(port, MAX310X_HDPIXDELAY_REG);
+		rs485.delay_rts_before_send = val >> 4;
+		rs485.delay_rts_after_send = val & 0x0f;
+		if (copy_to_user((struct serial_rs485 *)arg, &rs485,
+				 sizeof(rs485)))
+			return -EFAULT;
+		break;
+	default:
+		return -ENOIOCTLCMD;
+	}
+
+	return 0;
+}
+
 static int max310x_startup(struct uart_port *port)
 {
-	unsigned int val, line = port->line;
 	struct max310x_port *s = dev_get_drvdata(port->dev);
+	unsigned int val;
 
 	s->devtype->power(port, 1);
 
 	/* Configure MODE1 register */
 	max310x_port_update(port, MAX310X_MODE1_REG,
-			    MAX310X_MODE1_TRNSCVCTRL_BIT,
-			    (s->pdata->uart_flags[line] & MAX310X_AUTO_DIR_CTRL)
-			    ? MAX310X_MODE1_TRNSCVCTRL_BIT : 0);
+			    MAX310X_MODE1_TRNSCVCTRL_BIT, 0);
 
-	/* Configure MODE2 register */
-	val = MAX310X_MODE2_RXEMPTINV_BIT;
-	if (s->pdata->uart_flags[line] & MAX310X_ECHO_SUPRESS)
-		val |= MAX310X_MODE2_ECHOSUPR_BIT;
-
-	/* Reset FIFOs */
-	val |= MAX310X_MODE2_FIFORST_BIT;
+	/* Configure MODE2 register & Reset FIFOs*/
+	val = MAX310X_MODE2_RXEMPTINV_BIT | MAX310X_MODE2_FIFORST_BIT;
 	max310x_port_write(port, MAX310X_MODE2_REG, val);
 	max310x_port_update(port, MAX310X_MODE2_REG,
 			    MAX310X_MODE2_FIFORST_BIT, 0);
@@ -998,6 +1039,7 @@ static const struct uart_ops max310x_ops = {
 	.release_port	= max310x_null_void,
 	.config_port	= max310x_config_port,
 	.verify_port	= max310x_verify_port,
+	.ioctl		= max310x_ioctl,
 };
 
 static int __maybe_unused max310x_suspend(struct device *dev)
@@ -1077,7 +1119,6 @@ static int max310x_gpio_direction_output(struct gpio_chip *chip,
 static int max310x_probe(struct device *dev, struct max310x_devtype *devtype,
 			 struct regmap *regmap, int irq)
 {
-	struct max310x_pdata *pdata = dev_get_platdata(dev);
 	int i, ret, fmin, fmax, freq, uartclk;
 	struct clk *clk_osc, *clk_xtal;
 	struct max310x_port *s;
@@ -1086,11 +1127,6 @@ static int max310x_probe(struct device *dev, struct max310x_devtype *devtype,
 	if (IS_ERR(regmap))
 		return PTR_ERR(regmap);
 
-	if (!pdata) {
-		dev_err(dev, "No platform data supplied\n");
-		return -EINVAL;
-	}
-
 	/* Alloc port structure */
 	s = devm_kzalloc(dev, sizeof(*s) +
 			 sizeof(struct max310x_one) * devtype->nr, GFP_KERNEL);
@@ -1129,7 +1165,6 @@ static int max310x_probe(struct device *dev, struct max310x_devtype *devtype,
 		goto out_clk;
 	}
 
-	s->pdata = pdata;
 	s->regmap = regmap;
 	s->devtype = devtype;
 	dev_set_drvdata(dev, s);
diff --git a/include/linux/platform_data/max310x.h b/include/linux/platform_data/max310x.h
deleted file mode 100644
index 1140a57e735f..000000000000
--- a/include/linux/platform_data/max310x.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/*
- *  Maxim (Dallas) MAX3107/8/9, MAX14830 serial driver
- *
- *  Copyright (C) 2012 Alexander Shiyan <shc_work@mail.ru>
- *
- *  Based on max3100.c, by Christian Pellegrin <chripell@evolware.org>
- *  Based on max3110.c, by Feng Tang <feng.tang@intel.com>
- *  Based on max3107.c, by Aavamobile
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- */
-
-#ifndef _MAX310X_H_
-#define _MAX310X_H_
-
-/*
- * Example board initialization data:
- *
- * static struct max310x_pdata max3107_pdata = {
- *	.uart_flags[0]	= MAX310X_ECHO_SUPRESS | MAX310X_AUTO_DIR_CTRL,
- * };
- *
- * static struct spi_board_info spi_device_max3107[] = {
- *	{
- *		.modalias	= "max3107",
- *		.irq		= IRQ_EINT3,
- *		.bus_num	= 1,
- *		.chip_select	= 1,
- *		.platform_data	= &max3107_pdata,
- *	},
- * };
- */
-
-#define MAX310X_MAX_UARTS	4
-
-/* MAX310X platform data structure */
-struct max310x_pdata {
-	/* Flags global to UART port */
-	const u8		uart_flags[MAX310X_MAX_UARTS];
-#define MAX310X_ECHO_SUPRESS	(0x00000002)	/* Enable echo supress */
-#define MAX310X_AUTO_DIR_CTRL	(0x00000004)	/* Enable Auto direction
-						 * control (RS-485)
-						 */
-};
-
-#endif
-- 
cgit v1.2.3


From f7fc32cb2073902b3ee67d036656889ea75ffcb7 Mon Sep 17 00:00:00 2001
From: Alexander Gordeev <agordeev@redhat.com>
Date: Thu, 13 Feb 2014 15:25:02 +0100
Subject: PCI/MSI: Add pci_enable_msi_exact() and pci_enable_msix_exact()

The new functions are special cases for pci_enable_msi_range() and
pci_enable_msix_range() when a particular number of MSI or MSI-X
is needed.

By contrast with pci_enable_msi_range() and pci_enable_msix_range()
functions, pci_enable_msi_exact() and pci_enable_msix_exact()
return zero in case of success, which indicates MSI or MSI-X
interrupts have been successfully allocated.

Signed-off-by: Alexander Gordeev <agordeev@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 Documentation/PCI/MSI-HOWTO.txt | 86 ++++++++++++++++++++++++++++++++++++++++-
 include/linux/pci.h             | 20 ++++++++++
 2 files changed, 104 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt
index 96ee5eb9d4d4..10a93696e55a 100644
--- a/Documentation/PCI/MSI-HOWTO.txt
+++ b/Documentation/PCI/MSI-HOWTO.txt
@@ -159,6 +159,11 @@ static int foo_driver_enable_msi(struct pci_dev *pdev, int nvec)
 	return pci_enable_msi_range(pdev, nvec, nvec);
 }
 
+Note, unlike pci_enable_msi_exact() function, which could be also used to
+enable a particular number of MSI-X interrupts, pci_enable_msi_range()
+returns either a negative errno or 'nvec' (not negative errno or 0 - as
+pci_enable_msi_exact() does).
+
 4.2.1.3 Single MSI mode
 
 The most notorious example of the request type described above is
@@ -175,7 +180,22 @@ enable the single MSI mode, pci_enable_msi_range() returns either a
 negative errno or 1 (not negative errno or 0 - as pci_enable_msi()
 does).
 
-4.2.3 pci_disable_msi
+4.2.3 pci_enable_msi_exact
+
+int pci_enable_msi_exact(struct pci_dev *dev, int nvec)
+
+This variation on pci_enable_msi_range() call allows a device driver to
+request exactly 'nvec' MSIs.
+
+If this function returns a negative number, it indicates an error and
+the driver should not attempt to request any more MSI interrupts for
+this device.
+
+By contrast with pci_enable_msi_range() function, pci_enable_msi_exact()
+returns zero in case of success, which indicates MSI interrupts have been
+successfully allocated.
+
+4.2.4 pci_disable_msi
 
 void pci_disable_msi(struct pci_dev *dev)
 
@@ -303,6 +323,11 @@ static int foo_driver_enable_msix(struct foo_adapter *adapter, int nvec)
 				     nvec, nvec);
 }
 
+Note, unlike pci_enable_msix_exact() function, which could be also used to
+enable a particular number of MSI-X interrupts, pci_enable_msix_range()
+returns either a negative errno or 'nvec' (not negative errno or 0 - as
+pci_enable_msix_exact() does).
+
 4.3.1.3 Specific requirements to the number of MSI-X interrupts
 
 As noted above, there could be devices that can not operate with just any
@@ -349,7 +374,64 @@ Note how pci_enable_msix_range() return value is analized for a fallback -
 any error code other than -ENOSPC indicates a fatal error and should not
 be retried.
 
-4.3.2 pci_disable_msix
+4.3.2 pci_enable_msix_exact
+
+int pci_enable_msix_exact(struct pci_dev *dev,
+			  struct msix_entry *entries, int nvec)
+
+This variation on pci_enable_msix_range() call allows a device driver to
+request exactly 'nvec' MSI-Xs.
+
+If this function returns a negative number, it indicates an error and
+the driver should not attempt to allocate any more MSI-X interrupts for
+this device.
+
+By contrast with pci_enable_msix_range() function, pci_enable_msix_exact()
+returns zero in case of success, which indicates MSI-X interrupts have been
+successfully allocated.
+
+Another version of a routine that enables MSI-X mode for a device with
+specific requirements described in chapter 4.3.1.3 might look like this:
+
+/*
+ * Assume 'minvec' and 'maxvec' are non-zero
+ */
+static int foo_driver_enable_msix(struct foo_adapter *adapter,
+				  int minvec, int maxvec)
+{
+	int rc;
+
+	minvec = roundup_pow_of_two(minvec);
+	maxvec = rounddown_pow_of_two(maxvec);
+
+	if (minvec > maxvec)
+		return -ERANGE;
+
+retry:
+	rc = pci_enable_msix_exact(adapter->pdev,
+				   adapter->msix_entries, maxvec);
+
+	/*
+	 * -ENOSPC is the only error code allowed to be analyzed
+	 */
+	if (rc == -ENOSPC) {
+		if (maxvec == 1)
+			return -ENOSPC;
+
+		maxvec /= 2;
+
+		if (minvec > maxvec)
+			return -ENOSPC;
+
+		goto retry;
+	} else if (rc < 0) {
+		return rc;
+	}
+
+	return maxvec;
+}
+
+4.3.3 pci_disable_msix
 
 void pci_disable_msix(struct pci_dev *dev)
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index fb57c892b214..33aa2caf0f0c 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1169,8 +1169,23 @@ void msi_remove_pci_irq_vectors(struct pci_dev *dev);
 void pci_restore_msi_state(struct pci_dev *dev);
 int pci_msi_enabled(void);
 int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec);
+static inline int pci_enable_msi_exact(struct pci_dev *dev, int nvec)
+{
+	int rc = pci_enable_msi_range(dev, nvec, nvec);
+	if (rc < 0)
+		return rc;
+	return 0;
+}
 int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries,
 			  int minvec, int maxvec);
+static inline int pci_enable_msix_exact(struct pci_dev *dev,
+					struct msix_entry *entries, int nvec)
+{
+	int rc = pci_enable_msix_range(dev, entries, nvec, nvec);
+	if (rc < 0)
+		return rc;
+	return 0;
+}
 #else
 static inline int pci_msi_vec_count(struct pci_dev *dev) { return -ENOSYS; }
 static inline int pci_enable_msi_block(struct pci_dev *dev, int nvec)
@@ -1189,9 +1204,14 @@ static inline int pci_msi_enabled(void) { return 0; }
 static inline int pci_enable_msi_range(struct pci_dev *dev, int minvec,
 				       int maxvec)
 { return -ENOSYS; }
+static inline int pci_enable_msi_exact(struct pci_dev *dev, int nvec)
+{ return -ENOSYS; }
 static inline int pci_enable_msix_range(struct pci_dev *dev,
 		      struct msix_entry *entries, int minvec, int maxvec)
 { return -ENOSYS; }
+static inline int pci_enable_msix_exact(struct pci_dev *dev,
+		      struct msix_entry *entries, int nvec)
+{ return -ENOSYS; }
 #endif
 
 #ifdef CONFIG_PCIEPORTBUS
-- 
cgit v1.2.3


From 2501c9179dff2add6aadd3898cd729e94e777d3a Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Wed, 30 Oct 2013 01:00:18 +0100
Subject: mmc: core: Use MMC_UNSAFE_RESUME as default behavior

Invoking system suspend or shutdown without using the Kconfig option
MMC_UNSAFE_RESUME, did trigger an ungraceful power cut of the card.

To improve the situation, change the behavior to always make use of the
available bus_ops callbacks that handles system suspend and shutdown
properly.

By changing the behavior MMC_UNSAFE_RESUME becomes redundant, so lets's
remove it.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Chris Ball <chris@printf.net>
---
 drivers/mmc/core/Kconfig | 15 ---------------
 drivers/mmc/core/core.c  | 17 -----------------
 drivers/mmc/core/mmc.c   | 23 +----------------------
 drivers/mmc/core/sd.c    | 23 +----------------------
 include/linux/mmc/host.h |  5 +----
 5 files changed, 3 insertions(+), 80 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mmc/core/Kconfig b/drivers/mmc/core/Kconfig
index 269d072ef55e..9ebee72d9c3f 100644
--- a/drivers/mmc/core/Kconfig
+++ b/drivers/mmc/core/Kconfig
@@ -2,21 +2,6 @@
 # MMC core configuration
 #
 
-config MMC_UNSAFE_RESUME
-	bool "Assume MMC/SD cards are non-removable (DANGEROUS)"
-	help
-	  If you say Y here, the MMC layer will assume that all cards
-	  stayed in their respective slots during the suspend. The
-	  normal behaviour is to remove them at suspend and
-	  redetecting them at resume. Breaking this assumption will
-	  in most cases result in data corruption.
-
-	  This option is usually just for embedded systems which use
-	  a MMC/SD card for rootfs. Most people should say N here.
-
-	  This option sets a default which can be overridden by the
-	  module parameter "removable=0" or "removable=1".
-
 config MMC_CLKGATE
 	bool "MMC host clock gating"
 	help
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 098374b1ab2b..10856ec64412 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -64,23 +64,6 @@ static const unsigned freqs[] = { 400000, 300000, 200000, 100000 };
 bool use_spi_crc = 1;
 module_param(use_spi_crc, bool, 0);
 
-/*
- * We normally treat cards as removed during suspend if they are not
- * known to be on a non-removable bus, to avoid the risk of writing
- * back data to a different card after resume.  Allow this to be
- * overridden if necessary.
- */
-#ifdef CONFIG_MMC_UNSAFE_RESUME
-bool mmc_assume_removable;
-#else
-bool mmc_assume_removable = 1;
-#endif
-EXPORT_SYMBOL(mmc_assume_removable);
-module_param_named(removable, mmc_assume_removable, bool, 0644);
-MODULE_PARM_DESC(
-	removable,
-	"MMC/SD cards are removable and may be removed during suspend");
-
 /*
  * Internal function. Schedule delayed work in the MMC work queue.
  */
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 98e9eb0f6643..20f046895228 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1634,16 +1634,6 @@ static int mmc_power_restore(struct mmc_host *host)
 }
 
 static const struct mmc_bus_ops mmc_ops = {
-	.remove = mmc_remove,
-	.detect = mmc_detect,
-	.suspend = NULL,
-	.resume = NULL,
-	.power_restore = mmc_power_restore,
-	.alive = mmc_alive,
-	.shutdown = mmc_shutdown,
-};
-
-static const struct mmc_bus_ops mmc_ops_unsafe = {
 	.remove = mmc_remove,
 	.detect = mmc_detect,
 	.suspend = mmc_suspend,
@@ -1655,17 +1645,6 @@ static const struct mmc_bus_ops mmc_ops_unsafe = {
 	.shutdown = mmc_shutdown,
 };
 
-static void mmc_attach_bus_ops(struct mmc_host *host)
-{
-	const struct mmc_bus_ops *bus_ops;
-
-	if (!mmc_card_is_removable(host))
-		bus_ops = &mmc_ops_unsafe;
-	else
-		bus_ops = &mmc_ops;
-	mmc_attach_bus(host, bus_ops);
-}
-
 /*
  * Starting point for MMC card init.
  */
@@ -1685,7 +1664,7 @@ int mmc_attach_mmc(struct mmc_host *host)
 	if (err)
 		return err;
 
-	mmc_attach_bus_ops(host);
+	mmc_attach_bus(host, &mmc_ops);
 	if (host->ocr_avail_mmc)
 		host->ocr_avail = host->ocr_avail_mmc;
 
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index 692fdb177294..2dd359d2242f 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -1207,16 +1207,6 @@ static int mmc_sd_power_restore(struct mmc_host *host)
 }
 
 static const struct mmc_bus_ops mmc_sd_ops = {
-	.remove = mmc_sd_remove,
-	.detect = mmc_sd_detect,
-	.suspend = NULL,
-	.resume = NULL,
-	.power_restore = mmc_sd_power_restore,
-	.alive = mmc_sd_alive,
-	.shutdown = mmc_sd_suspend,
-};
-
-static const struct mmc_bus_ops mmc_sd_ops_unsafe = {
 	.remove = mmc_sd_remove,
 	.detect = mmc_sd_detect,
 	.runtime_suspend = mmc_sd_runtime_suspend,
@@ -1228,17 +1218,6 @@ static const struct mmc_bus_ops mmc_sd_ops_unsafe = {
 	.shutdown = mmc_sd_suspend,
 };
 
-static void mmc_sd_attach_bus_ops(struct mmc_host *host)
-{
-	const struct mmc_bus_ops *bus_ops;
-
-	if (!mmc_card_is_removable(host))
-		bus_ops = &mmc_sd_ops_unsafe;
-	else
-		bus_ops = &mmc_sd_ops;
-	mmc_attach_bus(host, bus_ops);
-}
-
 /*
  * Starting point for SD card init.
  */
@@ -1254,7 +1233,7 @@ int mmc_attach_sd(struct mmc_host *host)
 	if (err)
 		return err;
 
-	mmc_sd_attach_bus_ops(host);
+	mmc_attach_bus(host, &mmc_sd_ops);
 	if (host->ocr_avail_sd)
 		host->ocr_avail = host->ocr_avail_sd;
 
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 99f5709ac343..2a139b2bdb9e 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -424,12 +424,9 @@ static inline int mmc_regulator_get_supply(struct mmc_host *mmc)
 
 int mmc_pm_notify(struct notifier_block *notify_block, unsigned long, void *);
 
-/* Module parameter */
-extern bool mmc_assume_removable;
-
 static inline int mmc_card_is_removable(struct mmc_host *host)
 {
-	return !(host->caps & MMC_CAP_NONREMOVABLE) && mmc_assume_removable;
+	return !(host->caps & MMC_CAP_NONREMOVABLE);
 }
 
 static inline int mmc_card_keep_power(struct mmc_host *host)
-- 
cgit v1.2.3


From a2d1086de6cc3ae2378d9db8b92712911c9e5fef Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Mon, 16 Dec 2013 14:37:26 +0100
Subject: mmc: card: Remove host cap MMC_CAP2_SANITIZE

There is no need for keeping a host cap for MMC_CAP2_SANITIZE, instead
we just make the feature default available.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Chris Ball <chris@printf.net>
---
 drivers/mmc/card/block.c | 3 +--
 include/linux/mmc/host.h | 1 -
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 7b5424f398ac..c2187d5e9070 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -415,8 +415,7 @@ static int ioctl_do_sanitize(struct mmc_card *card)
 {
 	int err;
 
-	if (!(mmc_can_sanitize(card) &&
-	      (card->host->caps2 & MMC_CAP2_SANITIZE))) {
+	if (!mmc_can_sanitize(card)) {
 			pr_warn("%s: %s - SANITIZE is not supported\n",
 				mmc_hostname(card->host), __func__);
 			err = -EOPNOTSUPP;
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 2a139b2bdb9e..40f832e5db40 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -281,7 +281,6 @@ struct mmc_host {
 #define MMC_CAP2_PACKED_CMD	(MMC_CAP2_PACKED_RD | \
 				 MMC_CAP2_PACKED_WR)
 #define MMC_CAP2_NO_PRESCAN_POWERUP (1 << 14)	/* Don't power up before scan */
-#define MMC_CAP2_SANITIZE	(1 << 15)		/* Support Sanitize */
 
 	mmc_pm_flag_t		pm_caps;	/* supported pm features */
 
-- 
cgit v1.2.3


From 325e2f96b926ae852fa2aa5e64d1040ed9518ae1 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Mon, 16 Dec 2013 14:43:51 +0100
Subject: mmc: core: Remove unused host cap MMC_CAP2_BROKEN_VOLTAGE

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Chris Ball <chris@printf.net>
---
 include/linux/mmc/host.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 40f832e5db40..461c69f19425 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -272,7 +272,6 @@ struct mmc_host {
 #define MMC_CAP2_HS200_1_2V_SDR	(1 << 6)        /* can support */
 #define MMC_CAP2_HS200		(MMC_CAP2_HS200_1_8V_SDR | \
 				 MMC_CAP2_HS200_1_2V_SDR)
-#define MMC_CAP2_BROKEN_VOLTAGE	(1 << 7)	/* Use the broken voltage */
 #define MMC_CAP2_HC_ERASE_SZ	(1 << 9)	/* High-capacity erase size */
 #define MMC_CAP2_CD_ACTIVE_HIGH	(1 << 10)	/* Card-detect signal active high */
 #define MMC_CAP2_RO_ACTIVE_HIGH	(1 << 11)	/* Write-protect signal active high */
-- 
cgit v1.2.3


From 469a00b017a9b2c630bff962ffd64ba626977830 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Mon, 16 Dec 2013 14:46:00 +0100
Subject: mmc: core: Remove support for MMC_CAP2_NO_SLEEP_CMD

There are no active users of this host capability. The primary reason
for adding this cap was due to a bug in ux500 boot loader code, which
is not a relevant issue any more. So, let's remove it.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Chris Ball <chris@printf.net>
---
 drivers/mmc/core/mmc.c   | 3 ---
 include/linux/mmc/host.h | 1 -
 2 files changed, 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 20f046895228..5c4ee6ab2125 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1358,9 +1358,6 @@ static int mmc_sleep(struct mmc_host *host)
 	struct mmc_card *card = host->card;
 	int err;
 
-	if (host->caps2 & MMC_CAP2_NO_SLEEP_CMD)
-		return 0;
-
 	err = mmc_deselect_cards(host);
 	if (err)
 		return err;
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 461c69f19425..4c0176a8e474 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -267,7 +267,6 @@ struct mmc_host {
 #define MMC_CAP2_CACHE_CTRL	(1 << 1)	/* Allow cache control */
 #define MMC_CAP2_FULL_PWR_CYCLE	(1 << 2)	/* Can do full power cycle */
 #define MMC_CAP2_NO_MULTI_READ	(1 << 3)	/* Multiblock reads don't work */
-#define MMC_CAP2_NO_SLEEP_CMD	(1 << 4)	/* Don't allow sleep command */
 #define MMC_CAP2_HS200_1_8V_SDR	(1 << 5)        /* can support */
 #define MMC_CAP2_HS200_1_2V_SDR	(1 << 6)        /* can support */
 #define MMC_CAP2_HS200		(MMC_CAP2_HS200_1_8V_SDR | \
-- 
cgit v1.2.3


From 10e5d9652499a8bc0a99ffc2a96a3030fee576cb Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Mon, 16 Dec 2013 16:23:22 +0100
Subject: mmc: core: Use mmc_flush_cache() during mmc suspend

Earlier we disabled the cache during suspend, which meant a flush was
internally at the eMMC performed as well.

To simplify code we can make use of the mmc_flush_cache(), during mmc
suspend, which makes the mmc_cache_ctrl() redundant so then we can
remove it.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Seungwon Jeon <tgih.jun@samsung.com>
Signed-off-by: Chris Ball <chris@printf.net>
---
 drivers/mmc/core/core.c  | 38 --------------------------------------
 drivers/mmc/core/mmc.c   |  2 +-
 include/linux/mmc/host.h |  2 --
 3 files changed, 1 insertion(+), 41 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 22427c684b36..8928f9f4cfe1 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -2582,44 +2582,6 @@ int mmc_flush_cache(struct mmc_card *card)
 }
 EXPORT_SYMBOL(mmc_flush_cache);
 
-/*
- * Turn the cache ON/OFF.
- * Turning the cache OFF shall trigger flushing of the data
- * to the non-volatile storage.
- * This function should be called with host claimed
- */
-int mmc_cache_ctrl(struct mmc_host *host, u8 enable)
-{
-	struct mmc_card *card = host->card;
-	unsigned int timeout;
-	int err = 0;
-
-	if (!(host->caps2 & MMC_CAP2_CACHE_CTRL) ||
-			mmc_card_is_removable(host))
-		return err;
-
-	if (card && mmc_card_mmc(card) &&
-			(card->ext_csd.cache_size > 0)) {
-		enable = !!enable;
-
-		if (card->ext_csd.cache_ctrl ^ enable) {
-			timeout = enable ? card->ext_csd.generic_cmd6_time : 0;
-			err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-					EXT_CSD_CACHE_CTRL, enable, timeout);
-			if (err)
-				pr_err("%s: cache %s error %d\n",
-						mmc_hostname(card->host),
-						enable ? "on" : "off",
-						err);
-			else
-				card->ext_csd.cache_ctrl = enable;
-		}
-	}
-
-	return err;
-}
-EXPORT_SYMBOL(mmc_cache_ctrl);
-
 #ifdef CONFIG_PM
 
 /* Do the card removal on suspend if card is assumed removeable
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 5c4ee6ab2125..6d446e217f36 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1481,7 +1481,7 @@ static int _mmc_suspend(struct mmc_host *host, bool is_suspend)
 			goto out;
 	}
 
-	err = mmc_cache_ctrl(host, 0);
+	err = mmc_flush_cache(host->card);
 	if (err)
 		goto out;
 
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 4c0176a8e474..f69bd70b1046 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -385,8 +385,6 @@ int mmc_power_restore_host(struct mmc_host *host);
 void mmc_detect_change(struct mmc_host *, unsigned long delay);
 void mmc_request_done(struct mmc_host *, struct mmc_request *);
 
-int mmc_cache_ctrl(struct mmc_host *, u8);
-
 static inline void mmc_signal_sdio_irq(struct mmc_host *host)
 {
 	host->ops->enable_sdio_irq(host, 0);
-- 
cgit v1.2.3


From 7536d3f83aa42ba1a3b1c6b30c2b6d94a820cbb2 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Wed, 18 Dec 2013 11:59:17 +0100
Subject: mmc: core: Enable MMC_CAP2_CACHE_CTRL as default

There are no reason to why the use of a non-volatile internal eMMC
cache should be controlled by a host cap. Instead let's just enable it
if the eMMC card supports it.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Seungwon Jeon <tgih.jun@samsung.com>
Signed-off-by: Chris Ball <chris@printf.net>
---
 drivers/mmc/core/core.c  | 4 ----
 drivers/mmc/core/mmc.c   | 3 +--
 include/linux/mmc/host.h | 1 -
 3 files changed, 1 insertion(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 8928f9f4cfe1..f5a068d55c36 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -2562,12 +2562,8 @@ EXPORT_SYMBOL(mmc_power_restore_host);
  */
 int mmc_flush_cache(struct mmc_card *card)
 {
-	struct mmc_host *host = card->host;
 	int err = 0;
 
-	if (!(host->caps2 & MMC_CAP2_CACHE_CTRL))
-		return err;
-
 	if (mmc_card_mmc(card) &&
 			(card->ext_csd.cache_size > 0) &&
 			(card->ext_csd.cache_ctrl & 1)) {
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 6d446e217f36..072171183d5b 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1287,8 +1287,7 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 	 * If cache size is higher than 0, this indicates
 	 * the existence of cache and it can be turned on.
 	 */
-	if ((host->caps2 & MMC_CAP2_CACHE_CTRL) &&
-			card->ext_csd.cache_size > 0) {
+	if (card->ext_csd.cache_size > 0) {
 		err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
 				EXT_CSD_CACHE_CTRL, 1,
 				card->ext_csd.generic_cmd6_time);
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index f69bd70b1046..719db89ef134 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -264,7 +264,6 @@ struct mmc_host {
 	u32			caps2;		/* More host capabilities */
 
 #define MMC_CAP2_BOOTPART_NOACC	(1 << 0)	/* Boot partition no access */
-#define MMC_CAP2_CACHE_CTRL	(1 << 1)	/* Allow cache control */
 #define MMC_CAP2_FULL_PWR_CYCLE	(1 << 2)	/* Can do full power cycle */
 #define MMC_CAP2_NO_MULTI_READ	(1 << 3)	/* Multiblock reads don't work */
 #define MMC_CAP2_HS200_1_8V_SDR	(1 << 5)        /* can support */
-- 
cgit v1.2.3


From fd70f72c66eeada848abaed9eb6bbdbaf57764e9 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 13 Feb 2014 16:08:42 -0800
Subject: net: phy: add MoCA PHY type

Some Ethernet MACs are connected to a MoCA PHY which will handle the
low-level job of sending Ethernet frames on the coaxial cable, these
Ethernet MACs need to know about it to be properly configured.
Add a new PHY mode "moca" and update the Device Tree parsing logic to
look for it.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/phy.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/phy.h b/include/linux/phy.h
index 42f1bc7eaeb0..f7fe54628424 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -74,6 +74,7 @@ typedef enum {
 	PHY_INTERFACE_MODE_RTBI,
 	PHY_INTERFACE_MODE_SMII,
 	PHY_INTERFACE_MODE_XGMII,
+	PHY_INTERFACE_MODE_MOCA,
 	PHY_INTERFACE_MODE_MAX,
 } phy_interface_t;
 
@@ -113,6 +114,8 @@ static inline const char *phy_modes(phy_interface_t interface)
 		return "smii";
 	case PHY_INTERFACE_MODE_XGMII:
 		return "xgmii";
+	case PHY_INTERFACE_MODE_MOCA:
+		return "moca";
 	default:
 		return "unknown";
 	}
-- 
cgit v1.2.3


From 439d39a9ac8fbbba9c04581361188f33f21ced50 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 13 Feb 2014 16:08:44 -0800
Subject: net: phy: broadcom: extract register definitions

The Broadcom BCM54xx register definitions are shared between BCM54xx and
BCM7xx internal PHYs for which we are adding support. Extract these
register definitions and put them in include/linux/brcmphy.h for use by
the BCM7xxx internal PHY driver.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/broadcom.c | 52 ----------------------------------------------
 include/linux/brcmphy.h    | 51 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 51 insertions(+), 52 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index f8c90ea75108..34088d60da74 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -25,58 +25,6 @@
 #define BRCM_PHY_REV(phydev) \
 	((phydev)->drv->phy_id & ~((phydev)->drv->phy_id_mask))
 
-
-#define MII_BCM54XX_ECR		0x10	/* BCM54xx extended control register */
-#define MII_BCM54XX_ECR_IM	0x1000	/* Interrupt mask */
-#define MII_BCM54XX_ECR_IF	0x0800	/* Interrupt force */
-
-#define MII_BCM54XX_ESR		0x11	/* BCM54xx extended status register */
-#define MII_BCM54XX_ESR_IS	0x1000	/* Interrupt status */
-
-#define MII_BCM54XX_EXP_DATA	0x15	/* Expansion register data */
-#define MII_BCM54XX_EXP_SEL	0x17	/* Expansion register select */
-#define MII_BCM54XX_EXP_SEL_SSD	0x0e00	/* Secondary SerDes select */
-#define MII_BCM54XX_EXP_SEL_ER	0x0f00	/* Expansion register select */
-
-#define MII_BCM54XX_AUX_CTL	0x18	/* Auxiliary control register */
-#define MII_BCM54XX_ISR		0x1a	/* BCM54xx interrupt status register */
-#define MII_BCM54XX_IMR		0x1b	/* BCM54xx interrupt mask register */
-#define MII_BCM54XX_INT_CRCERR	0x0001	/* CRC error */
-#define MII_BCM54XX_INT_LINK	0x0002	/* Link status changed */
-#define MII_BCM54XX_INT_SPEED	0x0004	/* Link speed change */
-#define MII_BCM54XX_INT_DUPLEX	0x0008	/* Duplex mode changed */
-#define MII_BCM54XX_INT_LRS	0x0010	/* Local receiver status changed */
-#define MII_BCM54XX_INT_RRS	0x0020	/* Remote receiver status changed */
-#define MII_BCM54XX_INT_SSERR	0x0040	/* Scrambler synchronization error */
-#define MII_BCM54XX_INT_UHCD	0x0080	/* Unsupported HCD negotiated */
-#define MII_BCM54XX_INT_NHCD	0x0100	/* No HCD */
-#define MII_BCM54XX_INT_NHCDL	0x0200	/* No HCD link */
-#define MII_BCM54XX_INT_ANPR	0x0400	/* Auto-negotiation page received */
-#define MII_BCM54XX_INT_LC	0x0800	/* All counters below 128 */
-#define MII_BCM54XX_INT_HC	0x1000	/* Counter above 32768 */
-#define MII_BCM54XX_INT_MDIX	0x2000	/* MDIX status change */
-#define MII_BCM54XX_INT_PSERR	0x4000	/* Pair swap error */
-
-#define MII_BCM54XX_SHD		0x1c	/* 0x1c shadow registers */
-#define MII_BCM54XX_SHD_WRITE	0x8000
-#define MII_BCM54XX_SHD_VAL(x)	((x & 0x1f) << 10)
-#define MII_BCM54XX_SHD_DATA(x)	((x & 0x3ff) << 0)
-
-/*
- * AUXILIARY CONTROL SHADOW ACCESS REGISTERS.  (PHY REG 0x18)
- */
-#define MII_BCM54XX_AUXCTL_SHDWSEL_AUXCTL	0x0000
-#define MII_BCM54XX_AUXCTL_ACTL_TX_6DB		0x0400
-#define MII_BCM54XX_AUXCTL_ACTL_SMDSP_ENA	0x0800
-
-#define MII_BCM54XX_AUXCTL_MISC_WREN	0x8000
-#define MII_BCM54XX_AUXCTL_MISC_FORCE_AMDIX	0x0200
-#define MII_BCM54XX_AUXCTL_MISC_RDSEL_MISC	0x7000
-#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC	0x0007
-
-#define MII_BCM54XX_AUXCTL_SHDWSEL_AUXCTL	0x0000
-
-
 /*
  * Broadcom LED source encodings.  These are used in BCM5461, BCM5481,
  * BCM5482, and possibly some others.
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 677b4f01b2d0..104e3efe46af 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -33,4 +33,55 @@
 #define PHY_BRCM_DIS_TXCRXC_NOENRGY	0x00008000
 #define PHY_BCM_FLAGS_VALID		0x80000000
 
+/* Broadcom BCM54XX register definitions, common to most Broadcom PHYs */
+#define MII_BCM54XX_ECR		0x10	/* BCM54xx extended control register */
+#define MII_BCM54XX_ECR_IM	0x1000	/* Interrupt mask */
+#define MII_BCM54XX_ECR_IF	0x0800	/* Interrupt force */
+
+#define MII_BCM54XX_ESR		0x11	/* BCM54xx extended status register */
+#define MII_BCM54XX_ESR_IS	0x1000	/* Interrupt status */
+
+#define MII_BCM54XX_EXP_DATA	0x15	/* Expansion register data */
+#define MII_BCM54XX_EXP_SEL	0x17	/* Expansion register select */
+#define MII_BCM54XX_EXP_SEL_SSD	0x0e00	/* Secondary SerDes select */
+#define MII_BCM54XX_EXP_SEL_ER	0x0f00	/* Expansion register select */
+
+#define MII_BCM54XX_AUX_CTL	0x18	/* Auxiliary control register */
+#define MII_BCM54XX_ISR		0x1a	/* BCM54xx interrupt status register */
+#define MII_BCM54XX_IMR		0x1b	/* BCM54xx interrupt mask register */
+#define MII_BCM54XX_INT_CRCERR	0x0001	/* CRC error */
+#define MII_BCM54XX_INT_LINK	0x0002	/* Link status changed */
+#define MII_BCM54XX_INT_SPEED	0x0004	/* Link speed change */
+#define MII_BCM54XX_INT_DUPLEX	0x0008	/* Duplex mode changed */
+#define MII_BCM54XX_INT_LRS	0x0010	/* Local receiver status changed */
+#define MII_BCM54XX_INT_RRS	0x0020	/* Remote receiver status changed */
+#define MII_BCM54XX_INT_SSERR	0x0040	/* Scrambler synchronization error */
+#define MII_BCM54XX_INT_UHCD	0x0080	/* Unsupported HCD negotiated */
+#define MII_BCM54XX_INT_NHCD	0x0100	/* No HCD */
+#define MII_BCM54XX_INT_NHCDL	0x0200	/* No HCD link */
+#define MII_BCM54XX_INT_ANPR	0x0400	/* Auto-negotiation page received */
+#define MII_BCM54XX_INT_LC	0x0800	/* All counters below 128 */
+#define MII_BCM54XX_INT_HC	0x1000	/* Counter above 32768 */
+#define MII_BCM54XX_INT_MDIX	0x2000	/* MDIX status change */
+#define MII_BCM54XX_INT_PSERR	0x4000	/* Pair swap error */
+
+#define MII_BCM54XX_SHD		0x1c	/* 0x1c shadow registers */
+#define MII_BCM54XX_SHD_WRITE	0x8000
+#define MII_BCM54XX_SHD_VAL(x)	((x & 0x1f) << 10)
+#define MII_BCM54XX_SHD_DATA(x)	((x & 0x3ff) << 0)
+
+/*
+ * AUXILIARY CONTROL SHADOW ACCESS REGISTERS.  (PHY REG 0x18)
+ */
+#define MII_BCM54XX_AUXCTL_SHDWSEL_AUXCTL	0x0000
+#define MII_BCM54XX_AUXCTL_ACTL_TX_6DB		0x0400
+#define MII_BCM54XX_AUXCTL_ACTL_SMDSP_ENA	0x0800
+
+#define MII_BCM54XX_AUXCTL_MISC_WREN	0x8000
+#define MII_BCM54XX_AUXCTL_MISC_FORCE_AMDIX	0x0200
+#define MII_BCM54XX_AUXCTL_MISC_RDSEL_MISC	0x7000
+#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC	0x0007
+
+#define MII_BCM54XX_AUXCTL_SHDWSEL_AUXCTL	0x0000
+
 #endif /* _LINUX_BRCMPHY_H */
-- 
cgit v1.2.3


From b560a58c45c66f68936127040e86b7f02e4c5332 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 13 Feb 2014 16:08:45 -0800
Subject: net: phy: add Broadcom BCM7xxx internal PHY driver

This patch adds support for the Broadcom BCM7xxx Set Top Box SoCs
internal PHYs. This driver supports the following generation of SoCs:

- BCM7366, BCM7439, BCM7445 (28nm process)
- all 40nm and 65nm (older MIPS-based SoCs)

The PHYs on these SoCs require a bunch of workarounds to operate
correctly, both during configuration time and at suspend/resume time,
the driver handles that for us.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/Kconfig   |   6 +
 drivers/net/phy/Makefile  |   1 +
 drivers/net/phy/bcm7xxx.c | 343 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/brcmphy.h   |   9 ++
 4 files changed, 359 insertions(+)
 create mode 100644 drivers/net/phy/bcm7xxx.c

(limited to 'include/linux')

diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 9b5d46c03eed..6a17f92153b3 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -71,6 +71,12 @@ config BCM63XX_PHY
 	---help---
 	  Currently supports the 6348 and 6358 PHYs.
 
+config BCM7XXX_PHY
+	tristate "Drivers for Broadcom 7xxx SOCs internal PHYs"
+	---help---
+	  Currently supports the BCM7366, BCM7439, BCM7445, and
+	  40nm and 65nm generation of BCM7xxx Set Top Box SoCs.
+
 config BCM87XX_PHY
 	tristate "Driver for Broadcom BCM8706 and BCM8727 PHYs"
 	help
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index 9013dfa12aa3..07d24024863e 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -12,6 +12,7 @@ obj-$(CONFIG_SMSC_PHY)		+= smsc.o
 obj-$(CONFIG_VITESSE_PHY)	+= vitesse.o
 obj-$(CONFIG_BROADCOM_PHY)	+= broadcom.o
 obj-$(CONFIG_BCM63XX_PHY)	+= bcm63xx.o
+obj-$(CONFIG_BCM7XXX_PHY)	+= bcm7xxx.o
 obj-$(CONFIG_BCM87XX_PHY)	+= bcm87xx.o
 obj-$(CONFIG_ICPLUS_PHY)	+= icplus.o
 obj-$(CONFIG_REALTEK_PHY)	+= realtek.o
diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
new file mode 100644
index 000000000000..697337220016
--- /dev/null
+++ b/drivers/net/phy/bcm7xxx.c
@@ -0,0 +1,343 @@
+/*
+ * Broadcom BCM7xxx internal transceivers support.
+ *
+ * Copyright (C) 2014, Broadcom Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/phy.h>
+#include <linux/delay.h>
+#include <linux/bitops.h>
+#include <linux/brcmphy.h>
+
+/* Broadcom BCM7xxx internal PHY registers */
+#define MII_BCM7XXX_CHANNEL_WIDTH	0x2000
+
+/* 40nm only register definitions */
+#define MII_BCM7XXX_100TX_AUX_CTL	0x10
+#define MII_BCM7XXX_100TX_FALSE_CAR	0x13
+#define MII_BCM7XXX_100TX_DISC		0x14
+#define MII_BCM7XXX_AUX_MODE		0x1d
+#define  MII_BCM7XX_64CLK_MDIO		BIT(12)
+#define MII_BCM7XXX_CORE_BASE1E		0x1e
+#define MII_BCM7XXX_TEST		0x1f
+#define  MII_BCM7XXX_SHD_MODE_2		BIT(2)
+
+static int bcm7445_config_init(struct phy_device *phydev)
+{
+	int ret;
+	const struct bcm7445_regs {
+		int reg;
+		u16 value;
+	} bcm7445_regs_cfg[] = {
+		/* increases ADC latency by 24ns */
+		{ MII_BCM54XX_EXP_SEL, 0x0038 },
+		{ MII_BCM54XX_EXP_DATA, 0xAB95 },
+		/* increases internal 1V LDO voltage by 5% */
+		{ MII_BCM54XX_EXP_SEL, 0x2038 },
+		{ MII_BCM54XX_EXP_DATA, 0xBB22 },
+		/* reduce RX low pass filter corner frequency */
+		{ MII_BCM54XX_EXP_SEL, 0x6038 },
+		{ MII_BCM54XX_EXP_DATA, 0xFFC5 },
+		/* reduce RX high pass filter corner frequency */
+		{ MII_BCM54XX_EXP_SEL, 0x003a },
+		{ MII_BCM54XX_EXP_DATA, 0x2002 },
+	};
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(bcm7445_regs_cfg); i++) {
+		ret = phy_write(phydev,
+				bcm7445_regs_cfg[i].reg,
+				bcm7445_regs_cfg[i].value);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void phy_write_exp(struct phy_device *phydev,
+					u16 reg, u16 value)
+{
+	phy_write(phydev, MII_BCM54XX_EXP_SEL, MII_BCM54XX_EXP_SEL_ER | reg);
+	phy_write(phydev, MII_BCM54XX_EXP_DATA, value);
+}
+
+static void phy_write_misc(struct phy_device *phydev,
+					u16 reg, u16 chl, u16 value)
+{
+	int tmp;
+
+	phy_write(phydev, MII_BCM54XX_AUX_CTL, MII_BCM54XX_AUXCTL_SHDWSEL_MISC);
+
+	tmp = phy_read(phydev, MII_BCM54XX_AUX_CTL);
+	tmp |= MII_BCM54XX_AUXCTL_ACTL_SMDSP_ENA;
+	phy_write(phydev, MII_BCM54XX_AUX_CTL, tmp);
+
+	tmp = (chl * MII_BCM7XXX_CHANNEL_WIDTH) | reg;
+	phy_write(phydev, MII_BCM54XX_EXP_SEL, tmp);
+
+	phy_write(phydev, MII_BCM54XX_EXP_DATA, value);
+}
+
+static int bcm7xxx_28nm_afe_config_init(struct phy_device *phydev)
+{
+	/* write AFE_RXCONFIG_0 */
+	phy_write_misc(phydev, 0x38, 0x0000, 0xeb19);
+
+	/* write AFE_RXCONFIG_1 */
+	phy_write_misc(phydev, 0x38, 0x0001, 0x9a3f);
+
+	/* write AFE_RX_LP_COUNTER */
+	phy_write_misc(phydev, 0x38, 0x0003, 0x7fc7);
+
+	/* write AFE_HPF_TRIM_OTHERS */
+	phy_write_misc(phydev, 0x3A, 0x0000, 0x000b);
+
+	/* write AFTE_TX_CONFIG */
+	phy_write_misc(phydev, 0x39, 0x0000, 0x0800);
+
+	/* Increase VCO range to prevent unlocking problem of PLL at low
+	 * temp
+	 */
+	phy_write_misc(phydev, 0x0032, 0x0001, 0x0048);
+
+	/* Change Ki to 011 */
+	phy_write_misc(phydev, 0x0032, 0x0002, 0x021b);
+
+	/* Disable loading of TVCO buffer to bandgap, set bandgap trim
+	 * to 111
+	 */
+	phy_write_misc(phydev, 0x0033, 0x0000, 0x0e20);
+
+	/* Adjust bias current trim by -3 */
+	phy_write_misc(phydev, 0x000a, 0x0000, 0x690b);
+
+	/* Switch to CORE_BASE1E */
+	phy_write(phydev, MII_BCM7XXX_CORE_BASE1E, 0xd);
+
+	/* Reset R_CAL/RC_CAL Engine */
+	phy_write_exp(phydev, 0x00b0, 0x0010);
+
+	/* Disable Reset R_CAL/RC_CAL Engine */
+	phy_write_exp(phydev, 0x00b0, 0x0000);
+
+	return 0;
+}
+
+static int bcm7xxx_28nm_config_init(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = bcm7445_config_init(phydev);
+	if (ret)
+		return ret;
+
+	return bcm7xxx_28nm_afe_config_init(phydev);
+}
+
+static int phy_set_clr_bits(struct phy_device *dev, int location,
+					int set_mask, int clr_mask)
+{
+	int v, ret;
+
+	v = phy_read(dev, location);
+	if (v < 0)
+		return v;
+
+	v &= ~clr_mask;
+	v |= set_mask;
+
+	ret = phy_write(dev, location, v);
+	if (ret < 0)
+		return ret;
+
+	return v;
+}
+
+static int bcm7xxx_config_init(struct phy_device *phydev)
+{
+	int ret;
+
+	/* Enable 64 clock MDIO */
+	phy_write(phydev, MII_BCM7XXX_AUX_MODE, MII_BCM7XX_64CLK_MDIO);
+	phy_read(phydev, MII_BCM7XXX_AUX_MODE);
+
+	/* Workaround only required for 100Mbits/sec */
+	if (!(phydev->dev_flags & PHY_BRCM_100MBPS_WAR))
+		return 0;
+
+	/* set shadow mode 2 */
+	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST,
+			MII_BCM7XXX_SHD_MODE_2, MII_BCM7XXX_SHD_MODE_2);
+	if (ret < 0)
+		return ret;
+
+	/* set iddq_clkbias */
+	phy_write(phydev, MII_BCM7XXX_100TX_DISC, 0x0F00);
+	udelay(10);
+
+	/* reset iddq_clkbias */
+	phy_write(phydev, MII_BCM7XXX_100TX_DISC, 0x0C00);
+
+	phy_write(phydev, MII_BCM7XXX_100TX_FALSE_CAR, 0x7555);
+
+	/* reset shadow mode 2 */
+	ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, MII_BCM7XXX_SHD_MODE_2, 0);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+/* Workaround for putting the PHY in IDDQ mode, required
+ * for all BCM7XXX PHYs
+ */
+static int bcm7xxx_suspend(struct phy_device *phydev)
+{
+	int ret;
+	const struct bcm7xxx_regs {
+		int reg;
+		u16 value;
+	} bcm7xxx_suspend_cfg[] = {
+		{ MII_BCM7XXX_TEST, 0x008b },
+		{ MII_BCM7XXX_100TX_AUX_CTL, 0x01c0 },
+		{ MII_BCM7XXX_100TX_DISC, 0x7000 },
+		{ MII_BCM7XXX_TEST, 0x000f },
+		{ MII_BCM7XXX_100TX_AUX_CTL, 0x20d0 },
+		{ MII_BCM7XXX_TEST, 0x000b },
+	};
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(bcm7xxx_suspend_cfg); i++) {
+		ret = phy_write(phydev,
+				bcm7xxx_suspend_cfg[i].reg,
+				bcm7xxx_suspend_cfg[i].value);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int bcm7xxx_dummy_config_init(struct phy_device *phydev)
+{
+	return 0;
+}
+
+static struct phy_driver bcm7xxx_driver[] = {
+{
+	.phy_id		= PHY_ID_BCM7366,
+	.phy_id_mask	= 0xfffffff0,
+	.name		= "Broadcom BCM7366",
+	.features	= PHY_GBIT_FEATURES |
+			  SUPPORTED_Pause | SUPPORTED_Asym_Pause,
+	.flags		= PHY_IS_INTERNAL,
+	.config_init	= bcm7xxx_28nm_afe_config_init,
+	.config_aneg	= genphy_config_aneg,
+	.read_status	= genphy_read_status,
+	.suspend	= bcm7xxx_suspend,
+	.resume		= bcm7xxx_28nm_afe_config_init,
+	.driver		= { .owner = THIS_MODULE },
+}, {
+	.phy_id		= PHY_ID_BCM7439,
+	.phy_id_mask	= 0xfffffff0,
+	.name		= "Broadcom BCM7439",
+	.features	= PHY_GBIT_FEATURES |
+			  SUPPORTED_Pause | SUPPORTED_Asym_Pause,
+	.flags		= PHY_IS_INTERNAL,
+	.config_init	= bcm7xxx_28nm_afe_config_init,
+	.config_aneg	= genphy_config_aneg,
+	.read_status	= genphy_read_status,
+	.suspend	= bcm7xxx_suspend,
+	.resume		= bcm7xxx_28nm_afe_config_init,
+	.driver		= { .owner = THIS_MODULE },
+}, {
+	.phy_id		= PHY_ID_BCM7445,
+	.phy_id_mask	= 0xfffffff0,
+	.name		= "Broadcom BCM7445",
+	.features	= PHY_GBIT_FEATURES |
+			  SUPPORTED_Pause | SUPPORTED_Asym_Pause,
+	.flags		= PHY_IS_INTERNAL,
+	.config_init	= bcm7xxx_28nm_config_init,
+	.config_aneg	= genphy_config_aneg,
+	.read_status	= genphy_read_status,
+	.suspend	= bcm7xxx_suspend,
+	.resume		= bcm7xxx_28nm_config_init,
+	.driver		= { .owner = THIS_MODULE },
+}, {
+	.name		= "Broadcom BCM7XXX 28nm",
+	.phy_id		= PHY_ID_BCM7XXX_28,
+	.phy_id_mask	= PHY_BCM_OUI_MASK,
+	.features	= PHY_GBIT_FEATURES |
+			  SUPPORTED_Pause | SUPPORTED_Asym_Pause,
+	.flags		= PHY_IS_INTERNAL,
+	.config_init	= bcm7xxx_28nm_config_init,
+	.config_aneg	= genphy_config_aneg,
+	.read_status	= genphy_read_status,
+	.suspend	= bcm7xxx_suspend,
+	.resume		= bcm7xxx_28nm_config_init,
+	.driver		= { .owner = THIS_MODULE },
+}, {
+	.phy_id		= PHY_BCM_OUI_4,
+	.phy_id_mask	= 0xffff0000,
+	.name		= "Broadcom BCM7XXX 40nm",
+	.features	= PHY_GBIT_FEATURES |
+			  SUPPORTED_Pause | SUPPORTED_Asym_Pause,
+	.flags		= PHY_IS_INTERNAL,
+	.config_init	= bcm7xxx_config_init,
+	.config_aneg	= genphy_config_aneg,
+	.read_status	= genphy_read_status,
+	.suspend	= bcm7xxx_suspend,
+	.resume		= bcm7xxx_config_init,
+	.driver		= { .owner = THIS_MODULE },
+}, {
+	.phy_id		= PHY_BCM_OUI_5,
+	.phy_id_mask	= 0xffffff00,
+	.name		= "Broadcom BCM7XXX 65nm",
+	.features	= PHY_BASIC_FEATURES |
+			  SUPPORTED_Pause | SUPPORTED_Asym_Pause,
+	.flags		= PHY_IS_INTERNAL,
+	.config_init	= bcm7xxx_dummy_config_init,
+	.config_aneg	= genphy_config_aneg,
+	.read_status	= genphy_read_status,
+	.suspend	= bcm7xxx_suspend,
+	.resume		= bcm7xxx_config_init,
+	.driver		= { .owner = THIS_MODULE },
+} };
+
+static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = {
+	{ PHY_ID_BCM7366, 0xfffffff0, },
+	{ PHY_ID_BCM7439, 0xfffffff0, },
+	{ PHY_ID_BCM7445, 0xfffffff0, },
+	{ PHY_ID_BCM7XXX_28, 0xfffffc00 },
+	{ PHY_BCM_OUI_4, 0xffff0000 },
+	{ PHY_BCM_OUI_5, 0xffffff00 },
+	{ }
+};
+
+static int __init bcm7xxx_phy_init(void)
+{
+	return phy_drivers_register(bcm7xxx_driver,
+			ARRAY_SIZE(bcm7xxx_driver));
+}
+
+static void __exit bcm7xxx_phy_exit(void)
+{
+	phy_drivers_unregister(bcm7xxx_driver,
+			ARRAY_SIZE(bcm7xxx_driver));
+}
+
+module_init(bcm7xxx_phy_init);
+module_exit(bcm7xxx_phy_exit);
+
+MODULE_DEVICE_TABLE(mdio, bcm7xxx_tbl);
+
+MODULE_DESCRIPTION("Broadcom BCM7xxx internal PHY driver");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Broadcom Corporation");
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 104e3efe46af..6f76277baf39 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -13,10 +13,17 @@
 #define PHY_ID_BCM5461			0x002060c0
 #define PHY_ID_BCM57780			0x03625d90
 
+#define PHY_ID_BCM7366			0x600d8490
+#define PHY_ID_BCM7439			0x600d8480
+#define PHY_ID_BCM7445			0x600d8510
+#define PHY_ID_BCM7XXX_28		0x600d8400
+
 #define PHY_BCM_OUI_MASK		0xfffffc00
 #define PHY_BCM_OUI_1			0x00206000
 #define PHY_BCM_OUI_2			0x0143bc00
 #define PHY_BCM_OUI_3			0x03625c00
+#define PHY_BCM_OUI_4			0x600d0000
+#define PHY_BCM_OUI_5			0x03625e00
 
 
 #define PHY_BCM_FLAGS_MODE_COPPER	0x00000001
@@ -31,6 +38,8 @@
 #define PHY_BRCM_EXT_IBND_TX_ENABLE	0x00002000
 #define PHY_BRCM_CLEAR_RGMII_MODE	0x00004000
 #define PHY_BRCM_DIS_TXCRXC_NOENRGY	0x00008000
+/* Broadcom BCM7xxx specific workarounds */
+#define PHY_BRCM_100MBPS_WAR		0x00010000
 #define PHY_BCM_FLAGS_VALID		0x80000000
 
 /* Broadcom BCM54XX register definitions, common to most Broadcom PHYs */
-- 
cgit v1.2.3


From 1560a838f1a6402bdb2006cf30221e83106b0d02 Mon Sep 17 00:00:00 2001
From: Sachin Kamat <sachin.kamat@linaro.org>
Date: Thu, 13 Feb 2014 23:57:37 -0800
Subject: Input: s3c2410 - trivial cleanup in header file

Commit 436d42c61c3e ("ARM: samsung: move platform_data definitions")
moved the files to the current location but forgot to remove the pointer
to its previous location. Clean it up. While at it also change the header
file protection macros appropriately and remove whitespace errors.

Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 include/linux/platform_data/touchscreen-s3c2410.h | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/touchscreen-s3c2410.h b/include/linux/platform_data/touchscreen-s3c2410.h
index 26fdb22e0fc2..58dc7c5ae63b 100644
--- a/include/linux/platform_data/touchscreen-s3c2410.h
+++ b/include/linux/platform_data/touchscreen-s3c2410.h
@@ -1,5 +1,4 @@
-/* arch/arm/plat-samsung/include/plat/ts.h
- *
+/*
  * Copyright (c) 2005 Arnaud Patard <arnaud.patard@rtp-net.org>
  *
  * This program is free software; you can redistribute it and/or modify
@@ -7,14 +6,14 @@
  * published by the Free Software Foundation.
 */
 
-#ifndef __ASM_ARM_TS_H
-#define __ASM_ARM_TS_H
+#ifndef __TOUCHSCREEN_S3C2410_H
+#define __TOUCHSCREEN_S3C2410_H
 
 struct s3c2410_ts_mach_info {
-       int             delay;
-       int             presc;
-       int             oversampling_shift;
-	void    (*cfg_gpio)(struct platform_device *dev);
+	int delay;
+	int presc;
+	int oversampling_shift;
+	void (*cfg_gpio)(struct platform_device *dev);
 };
 
 extern void s3c24xx_ts_set_platdata(struct s3c2410_ts_mach_info *);
@@ -22,4 +21,4 @@ extern void s3c24xx_ts_set_platdata(struct s3c2410_ts_mach_info *);
 /* defined by architecture to configure gpio */
 extern void s3c24xx_ts_cfg_gpio(struct platform_device *dev);
 
-#endif /* __ASM_ARM_TS_H */
+#endif /*__TOUCHSCREEN_S3C2410_H */
-- 
cgit v1.2.3


From cc045e3952175e84c38dad22dea14465b9fc8fb5 Mon Sep 17 00:00:00 2001
From: Li Zefan <lizefan@huawei.com>
Date: Fri, 14 Feb 2014 16:56:04 +0800
Subject: cgroup: deal with dummp_top in cgroup_name() and cgroup_path()

My kernel fails to boot, because blkcg calls cgroup_path() while
cgroupfs is not mounted.

Fix both cgroup_name() and cgroup_path().

Signed-off-by: Li Zefan <lizefan@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cgroup.h | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index ef0b3af0e61c..8c283a910b91 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -487,13 +487,21 @@ struct cgroup_subsys_state *seq_css(struct seq_file *seq);
 
 static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen)
 {
-	return kernfs_name(cgrp->kn, buf, buflen);
+	/* dummy_top doesn't have a kn associated */
+	if (cgrp->kn)
+		return kernfs_name(cgrp->kn, buf, buflen);
+	else
+		return strlcpy(buf, "/", buflen);
 }
 
 static inline char * __must_check cgroup_path(struct cgroup *cgrp, char *buf,
 					      size_t buflen)
 {
-	return kernfs_path(cgrp->kn, buf, buflen);
+	/* dummy_top doesn't have a kn associated */
+	if (cgrp->kn)
+		return kernfs_path(cgrp->kn, buf, buflen);
+	strlcpy(buf, "/", buflen);
+	return (buflen <= 2) ? NULL : buf;
 }
 
 static inline void pr_cont_cgroup_name(struct cgroup *cgrp)
-- 
cgit v1.2.3


From 94e6a9b93064b49024b8701d2d81fcb4a821fa09 Mon Sep 17 00:00:00 2001
From: Yijing Wang <wangyijing@huawei.com>
Date: Thu, 13 Feb 2014 21:14:03 +0800
Subject: PCI: Remove pci_bus_b() and use list_for_each_entry() directly

Replace list_for_each() with list_for_each_entry(), which means we no
longer need pci_bus_b() and can remove it.

Signed-off-by: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.c    |  6 +++---
 drivers/pci/search.c | 10 +++++-----
 include/linux/pci.h  |  1 -
 3 files changed, 8 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 1febe90831b4..6f5ed88ca126 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -108,12 +108,12 @@ static bool pcie_ari_disabled;
  */
 unsigned char pci_bus_max_busnr(struct pci_bus* bus)
 {
-	struct list_head *tmp;
+	struct pci_bus *tmp;
 	unsigned char max, n;
 
 	max = bus->busn_res.end;
-	list_for_each(tmp, &bus->children) {
-		n = pci_bus_max_busnr(pci_bus_b(tmp));
+	list_for_each_entry(tmp, &bus->children, node) {
+		n = pci_bus_max_busnr(tmp);
 		if(n > max)
 			max = n;
 	}
diff --git a/drivers/pci/search.c b/drivers/pci/search.c
index 3ff2ac7c14e2..4a1b972efe7f 100644
--- a/drivers/pci/search.c
+++ b/drivers/pci/search.c
@@ -54,14 +54,14 @@ pci_find_upstream_pcie_bridge(struct pci_dev *pdev)
 
 static struct pci_bus *pci_do_find_bus(struct pci_bus *bus, unsigned char busnr)
 {
-	struct pci_bus* child;
-	struct list_head *tmp;
+	struct pci_bus *child;
+	struct pci_bus *tmp;
 
 	if(bus->number == busnr)
 		return bus;
 
-	list_for_each(tmp, &bus->children) {
-		child = pci_do_find_bus(pci_bus_b(tmp), busnr);
+	list_for_each_entry(tmp, &bus->children, node) {
+		child = pci_do_find_bus(tmp, busnr);
 		if(child)
 			return child;
 	}
@@ -111,7 +111,7 @@ pci_find_next_bus(const struct pci_bus *from)
 	down_read(&pci_bus_sem);
 	n = from ? from->node.next : pci_root_buses.next;
 	if (n != &pci_root_buses)
-		b = pci_bus_b(n);
+		b = list_entry(n, struct pci_bus, node);
 	up_read(&pci_bus_sem);
 	return b;
 }
diff --git a/include/linux/pci.h b/include/linux/pci.h
index fb57c892b214..e1b5752f3b1b 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -461,7 +461,6 @@ struct pci_bus {
 	unsigned int		is_added:1;
 };
 
-#define pci_bus_b(n)	list_entry(n, struct pci_bus, node)
 #define to_pci_bus(n)	container_of(n, struct pci_bus, dev)
 
 /*
-- 
cgit v1.2.3


From 1c213bd24ad04f4430031d20d740d7783162b099 Mon Sep 17 00:00:00 2001
From: WANG Cong <xiyou.wangcong@gmail.com>
Date: Thu, 13 Feb 2014 11:46:28 -0800
Subject: net: introduce netdev_alloc_pcpu_stats() for drivers

There are many drivers calling alloc_percpu() to allocate pcpu stats
and then initializing ->syncp. So just introduce a helper function for them.

Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dummy.c                   |  8 +-------
 drivers/net/ethernet/marvell/mvneta.c |  9 +--------
 drivers/net/loopback.c                |  9 +--------
 drivers/net/macvlan.c                 |  9 +--------
 drivers/net/nlmon.c                   | 11 +----------
 drivers/net/team/team.c               |  8 +-------
 drivers/net/veth.c                    | 11 +----------
 drivers/net/vxlan.c                   | 10 +---------
 drivers/net/xen-netfront.c            |  8 +-------
 include/linux/netdevice.h             | 14 ++++++++++++++
 net/8021q/vlan_dev.c                  | 11 ++---------
 net/bridge/br_device.c                |  9 +--------
 net/ipv4/ip_tunnel.c                  | 10 ++--------
 net/ipv6/ip6_gre.c                    |  9 +--------
 net/ipv6/ip6_tunnel.c                 |  9 +--------
 net/ipv6/ip6_vti.c                    |  8 +-------
 net/ipv6/sit.c                        | 18 ++----------------
 net/openvswitch/datapath.c            |  8 +-------
 net/openvswitch/vport.c               | 10 +---------
 19 files changed, 35 insertions(+), 154 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index bd8f84b0b894..1656317c96f8 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -88,16 +88,10 @@ static netdev_tx_t dummy_xmit(struct sk_buff *skb, struct net_device *dev)
 
 static int dummy_dev_init(struct net_device *dev)
 {
-	int i;
-	dev->dstats = alloc_percpu(struct pcpu_dstats);
+	dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats);
 	if (!dev->dstats)
 		return -ENOMEM;
 
-	for_each_possible_cpu(i) {
-		struct pcpu_dstats *dstats;
-		dstats = per_cpu_ptr(dev->dstats, i);
-		u64_stats_init(&dstats->syncp);
-	}
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index f418f4f20f94..12c6a66e54d1 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2784,7 +2784,6 @@ static int mvneta_probe(struct platform_device *pdev)
 	const char *mac_from;
 	int phy_mode;
 	int err;
-	int cpu;
 
 	/* Our multiqueue support is not complete, so for now, only
 	 * allow the usage of the first RX queue
@@ -2845,18 +2844,12 @@ static int mvneta_probe(struct platform_device *pdev)
 	}
 
 	/* Alloc per-cpu stats */
-	pp->stats = alloc_percpu(struct mvneta_pcpu_stats);
+	pp->stats = netdev_alloc_pcpu_stats(struct mvneta_pcpu_stats);
 	if (!pp->stats) {
 		err = -ENOMEM;
 		goto err_unmap;
 	}
 
-	for_each_possible_cpu(cpu) {
-		struct mvneta_pcpu_stats *stats;
-		stats = per_cpu_ptr(pp->stats, cpu);
-		u64_stats_init(&stats->syncp);
-	}
-
 	dt_mac_addr = of_get_mac_address(dn);
 	if (dt_mac_addr) {
 		mac_from = "device tree";
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index e7c1d5f8ab51..771c9bfa7d31 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -136,16 +136,9 @@ static const struct ethtool_ops loopback_ethtool_ops = {
 
 static int loopback_dev_init(struct net_device *dev)
 {
-	int i;
-	dev->lstats = alloc_percpu(struct pcpu_lstats);
+	dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats);
 	if (!dev->lstats)
 		return -ENOMEM;
-
-	for_each_possible_cpu(i) {
-		struct pcpu_lstats *lb_stats;
-		lb_stats = per_cpu_ptr(dev->lstats, i);
-		u64_stats_init(&lb_stats->syncp);
-	}
 	return 0;
 }
 
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 8433de4509c7..25685e3eb472 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -534,7 +534,6 @@ static int macvlan_init(struct net_device *dev)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
 	const struct net_device *lowerdev = vlan->lowerdev;
-	int i;
 
 	dev->state		= (dev->state & ~MACVLAN_STATE_MASK) |
 				  (lowerdev->state & MACVLAN_STATE_MASK);
@@ -546,16 +545,10 @@ static int macvlan_init(struct net_device *dev)
 
 	macvlan_set_lockdep_class(dev);
 
-	vlan->pcpu_stats = alloc_percpu(struct vlan_pcpu_stats);
+	vlan->pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
 	if (!vlan->pcpu_stats)
 		return -ENOMEM;
 
-	for_each_possible_cpu(i) {
-		struct vlan_pcpu_stats *mvlstats;
-		mvlstats = per_cpu_ptr(vlan->pcpu_stats, i);
-		u64_stats_init(&mvlstats->syncp);
-	}
-
 	return 0;
 }
 
diff --git a/drivers/net/nlmon.c b/drivers/net/nlmon.c
index d2bb12bfabd5..14ce7de6a933 100644
--- a/drivers/net/nlmon.c
+++ b/drivers/net/nlmon.c
@@ -47,16 +47,7 @@ static int nlmon_change_mtu(struct net_device *dev, int new_mtu)
 
 static int nlmon_dev_init(struct net_device *dev)
 {
-	int i;
-
-	dev->lstats = alloc_percpu(struct pcpu_lstats);
-
-	for_each_possible_cpu(i) {
-		struct pcpu_lstats *nlmstats;
-		nlmstats = per_cpu_ptr(dev->lstats, i);
-		u64_stats_init(&nlmstats->syncp);
-	}
-
+	dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats);
 	return dev->lstats == NULL ? -ENOMEM : 0;
 }
 
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 28407426fd6f..adb46de7c90d 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1540,16 +1540,10 @@ static int team_init(struct net_device *dev)
 	mutex_init(&team->lock);
 	team_set_no_mode(team);
 
-	team->pcpu_stats = alloc_percpu(struct team_pcpu_stats);
+	team->pcpu_stats = netdev_alloc_pcpu_stats(struct team_pcpu_stats);
 	if (!team->pcpu_stats)
 		return -ENOMEM;
 
-	for_each_possible_cpu(i) {
-		struct team_pcpu_stats *team_stats;
-		team_stats = per_cpu_ptr(team->pcpu_stats, i);
-		u64_stats_init(&team_stats->syncp);
-	}
-
 	for (i = 0; i < TEAM_PORT_HASHENTRIES; i++)
 		INIT_HLIST_HEAD(&team->en_port_hlist[i]);
 	INIT_LIST_HEAD(&team->port_list);
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 2ec2041b62d4..91c33c1d3c9c 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -235,18 +235,9 @@ static int veth_change_mtu(struct net_device *dev, int new_mtu)
 
 static int veth_dev_init(struct net_device *dev)
 {
-	int i;
-
-	dev->vstats = alloc_percpu(struct pcpu_vstats);
+	dev->vstats = netdev_alloc_pcpu_stats(struct pcpu_vstats);
 	if (!dev->vstats)
 		return -ENOMEM;
-
-	for_each_possible_cpu(i) {
-		struct pcpu_vstats *veth_stats;
-		veth_stats = per_cpu_ptr(dev->vstats, i);
-		u64_stats_init(&veth_stats->syncp);
-	}
-
 	return 0;
 }
 
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index b0f705c2378f..dec9820bc182 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1978,19 +1978,11 @@ static int vxlan_init(struct net_device *dev)
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
 	struct vxlan_sock *vs;
-	int i;
 
-	dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 
-	for_each_possible_cpu(i) {
-		struct pcpu_sw_netstats *vxlan_stats;
-		vxlan_stats = per_cpu_ptr(dev->tstats, i);
-		u64_stats_init(&vxlan_stats->syncp);
-	}
-
-
 	spin_lock(&vn->sock_lock);
 	vs = vxlan_find_sock(dev_net(dev), vxlan->dst_port);
 	if (vs) {
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index f9daa9e183f2..2b62d799bfd8 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1281,16 +1281,10 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
 	np->rx_refill_timer.function = rx_refill_timeout;
 
 	err = -ENOMEM;
-	np->stats = alloc_percpu(struct netfront_stats);
+	np->stats = netdev_alloc_pcpu_stats(struct netfront_stats);
 	if (np->stats == NULL)
 		goto exit;
 
-	for_each_possible_cpu(i) {
-		struct netfront_stats *xen_nf_stats;
-		xen_nf_stats = per_cpu_ptr(np->stats, i);
-		u64_stats_init(&xen_nf_stats->syncp);
-	}
-
 	/* Initialise tx_skbs as a free chain containing every entry. */
 	np->tx_skb_freelist = 0;
 	for (i = 0; i < NET_TX_RING_SIZE; i++) {
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 440a02ee6f92..430c51aed6a4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1726,6 +1726,20 @@ struct pcpu_sw_netstats {
 	struct u64_stats_sync   syncp;
 };
 
+#define netdev_alloc_pcpu_stats(type)				\
+({								\
+	typeof(type) *pcpu_stats = alloc_percpu(type);		\
+	if (pcpu_stats)	{					\
+		int i;						\
+		for_each_possible_cpu(i) {			\
+			typeof(type) *stat;			\
+			stat = per_cpu_ptr(pcpu_stats, i);	\
+			u64_stats_init(&stat->syncp);		\
+		}						\
+	}							\
+	pcpu_stats;						\
+})
+
 #include <linux/notifier.h>
 
 /* netdevice notifier chain. Please remember to update the rtnetlink
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index de51c48c4393..566adbf5c506 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -556,7 +556,7 @@ static const struct net_device_ops vlan_netdev_ops;
 static int vlan_dev_init(struct net_device *dev)
 {
 	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
-	int subclass = 0, i;
+	int subclass = 0;
 
 	netif_carrier_off(dev);
 
@@ -606,17 +606,10 @@ static int vlan_dev_init(struct net_device *dev)
 
 	vlan_dev_set_lockdep_class(dev, subclass);
 
-	vlan_dev_priv(dev)->vlan_pcpu_stats = alloc_percpu(struct vlan_pcpu_stats);
+	vlan_dev_priv(dev)->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
 	if (!vlan_dev_priv(dev)->vlan_pcpu_stats)
 		return -ENOMEM;
 
-	for_each_possible_cpu(i) {
-		struct vlan_pcpu_stats *vlan_stat;
-		vlan_stat = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i);
-		u64_stats_init(&vlan_stat->syncp);
-	}
-
-
 	return 0;
 }
 
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 63f0455c0bc3..bf34451743a1 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -88,18 +88,11 @@ out:
 static int br_dev_init(struct net_device *dev)
 {
 	struct net_bridge *br = netdev_priv(dev);
-	int i;
 
-	br->stats = alloc_percpu(struct pcpu_sw_netstats);
+	br->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!br->stats)
 		return -ENOMEM;
 
-	for_each_possible_cpu(i) {
-		struct pcpu_sw_netstats *br_dev_stats;
-		br_dev_stats = per_cpu_ptr(br->stats, i);
-		u64_stats_init(&br_dev_stats->syncp);
-	}
-
 	return 0;
 }
 
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 50228be5c17b..3400d737adc6 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -1041,19 +1041,13 @@ int ip_tunnel_init(struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct iphdr *iph = &tunnel->parms.iph;
-	int i, err;
+	int err;
 
 	dev->destructor	= ip_tunnel_dev_free;
-	dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 
-	for_each_possible_cpu(i) {
-		struct pcpu_sw_netstats *ipt_stats;
-		ipt_stats = per_cpu_ptr(dev->tstats, i);
-		u64_stats_init(&ipt_stats->syncp);
-	}
-
 	tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
 	if (!tunnel->dst_cache) {
 		free_percpu(dev->tstats);
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index f3ffb43f59c0..c98338b81d30 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1454,7 +1454,6 @@ static void ip6gre_netlink_parms(struct nlattr *data[],
 static int ip6gre_tap_init(struct net_device *dev)
 {
 	struct ip6_tnl *tunnel;
-	int i;
 
 	tunnel = netdev_priv(dev);
 
@@ -1464,16 +1463,10 @@ static int ip6gre_tap_init(struct net_device *dev)
 
 	ip6gre_tnl_link_config(tunnel, 1);
 
-	dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 
-	for_each_possible_cpu(i) {
-		struct pcpu_sw_netstats *ip6gre_tap_stats;
-		ip6gre_tap_stats = per_cpu_ptr(dev->tstats, i);
-		u64_stats_init(&ip6gre_tap_stats->syncp);
-	}
-
 	return 0;
 }
 
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 5db8d310f9c0..8ad59f4811df 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1502,19 +1502,12 @@ static inline int
 ip6_tnl_dev_init_gen(struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
-	int i;
 
 	t->dev = dev;
 	t->net = dev_net(dev);
-	dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
-
-	for_each_possible_cpu(i) {
-		struct pcpu_sw_netstats *ip6_tnl_stats;
-		ip6_tnl_stats = per_cpu_ptr(dev->tstats, i);
-		u64_stats_init(&ip6_tnl_stats->syncp);
-	}
 	return 0;
 }
 
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 2d19272b8cee..864914399391 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -731,18 +731,12 @@ static void vti6_dev_setup(struct net_device *dev)
 static inline int vti6_dev_init_gen(struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
-	int i;
 
 	t->dev = dev;
 	t->net = dev_net(dev);
-	dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
-	for_each_possible_cpu(i) {
-		struct pcpu_sw_netstats *stats;
-		stats = per_cpu_ptr(dev->tstats, i);
-		u64_stats_init(&stats->syncp);
-	}
 	return 0;
 }
 
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 3dfbcf1dcb1c..958027be0e94 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1356,7 +1356,6 @@ static void ipip6_tunnel_setup(struct net_device *dev)
 static int ipip6_tunnel_init(struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
-	int i;
 
 	tunnel->dev = dev;
 	tunnel->net = dev_net(dev);
@@ -1365,16 +1364,10 @@ static int ipip6_tunnel_init(struct net_device *dev)
 	memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
 
 	ipip6_tunnel_bind_dev(dev);
-	dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 
-	for_each_possible_cpu(i) {
-		struct pcpu_sw_netstats *ipip6_tunnel_stats;
-		ipip6_tunnel_stats = per_cpu_ptr(dev->tstats, i);
-		u64_stats_init(&ipip6_tunnel_stats->syncp);
-	}
-
 	return 0;
 }
 
@@ -1384,7 +1377,6 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev)
 	struct iphdr *iph = &tunnel->parms.iph;
 	struct net *net = dev_net(dev);
 	struct sit_net *sitn = net_generic(net, sit_net_id);
-	int i;
 
 	tunnel->dev = dev;
 	tunnel->net = dev_net(dev);
@@ -1395,16 +1387,10 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev)
 	iph->ihl		= 5;
 	iph->ttl		= 64;
 
-	dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 
-	for_each_possible_cpu(i) {
-		struct pcpu_sw_netstats *ipip6_fb_stats;
-		ipip6_fb_stats = per_cpu_ptr(dev->tstats, i);
-		u64_stats_init(&ipip6_fb_stats->syncp);
-	}
-
 	dev_hold(dev);
 	rcu_assign_pointer(sitn->tunnels_wc[0], tunnel);
 	return 0;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index e9a48baf8551..3a954067b6a4 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1215,18 +1215,12 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	if (err)
 		goto err_free_dp;
 
-	dp->stats_percpu = alloc_percpu(struct dp_stats_percpu);
+	dp->stats_percpu = netdev_alloc_pcpu_stats(struct dp_stats_percpu);
 	if (!dp->stats_percpu) {
 		err = -ENOMEM;
 		goto err_destroy_table;
 	}
 
-	for_each_possible_cpu(i) {
-		struct dp_stats_percpu *dpath_stats;
-		dpath_stats = per_cpu_ptr(dp->stats_percpu, i);
-		u64_stats_init(&dpath_stats->sync);
-	}
-
 	dp->ports = kmalloc(DP_VPORT_HASH_BUCKETS * sizeof(struct hlist_head),
 			    GFP_KERNEL);
 	if (!dp->ports) {
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 208dd9a26dd1..3b4db3220456 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -121,7 +121,6 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
 {
 	struct vport *vport;
 	size_t alloc_size;
-	int i;
 
 	alloc_size = sizeof(struct vport);
 	if (priv_size) {
@@ -139,19 +138,12 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
 	vport->ops = ops;
 	INIT_HLIST_NODE(&vport->dp_hash_node);
 
-	vport->percpu_stats = alloc_percpu(struct pcpu_sw_netstats);
+	vport->percpu_stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!vport->percpu_stats) {
 		kfree(vport);
 		return ERR_PTR(-ENOMEM);
 	}
 
-	for_each_possible_cpu(i) {
-		struct pcpu_sw_netstats *vport_stats;
-		vport_stats = per_cpu_ptr(vport->percpu_stats, i);
-		u64_stats_init(&vport_stats->syncp);
-	}
-
-
 	spin_lock_init(&vport->stats_lock);
 
 	return vport;
-- 
cgit v1.2.3


From c0fdfb80382e4901473ce0e31d1e7833c1d297be Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Sun, 9 Feb 2014 20:59:04 -0500
Subject: tty: Fix ref counting for port krefs

The tty core supports two models for handling tty_port lifetimes;
the tty_port can use the kref supplied by tty_port (which will
automatically destruct the tty_port when the ref count drops to
zero) or it can destruct the tty_port manually.

For tty drivers that choose to use the port kref to manage the
tty_port lifetime, it is not possible to safely acquire a port
reference conditionally. If the last reference is released after
evaluating the condition but before acquiring the reference, a
bogus reference will be held while the tty_port destruction
commences.

Rather, only acquire a port reference if the ref count is non-zero
and allow the caller to distinguish if a reference has successfully
been acquired.

Cc: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Tested-By: Alexander Holler <holler@ahsoftware.de>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/linux/tty.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tty.h b/include/linux/tty.h
index 90b4fdc8a61f..4781d7b27dd3 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -518,9 +518,9 @@ extern void tty_port_put(struct tty_port *port);
 
 static inline struct tty_port *tty_port_get(struct tty_port *port)
 {
-	if (port)
-		kref_get(&port->kref);
-	return port;
+	if (port && kref_get_unless_zero(&port->kref))
+		return port;
+	return NULL;
 }
 
 /* If the cts flow control is enabled, return true. */
-- 
cgit v1.2.3


From 07d4655b410a4da3bdffbc9ed01d9fef67f682a6 Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <jic23@kernel.org>
Date: Tue, 12 Nov 2013 18:45:00 +0000
Subject: iio:drop IIO_ST macro

This macro no longer allows all the elements of the scan_type structure
to be set.  Missinterpretation of the parameters also caused a couple of
recent bugs.  No mainline drivers now use this macro so drop it.

Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 include/linux/iio/iio.h | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index 75a8a20c8179..5f2d00e7e488 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -254,12 +254,16 @@ static inline bool iio_channel_has_info(const struct iio_chan_spec *chan,
 		(chan->info_mask_shared_by_all & BIT(type));
 }
 
-#define IIO_ST(si, rb, sb, sh)						\
-	{ .sign = si, .realbits = rb, .storagebits = sb, .shift = sh }
-
-#define IIO_CHAN_SOFT_TIMESTAMP(_si)					\
-	{ .type = IIO_TIMESTAMP, .channel = -1,				\
-			.scan_index = _si, .scan_type = IIO_ST('s', 64, 64, 0) }
+#define IIO_CHAN_SOFT_TIMESTAMP(_si) {					\
+	.type = IIO_TIMESTAMP,						\
+	.channel = -1,							\
+	.scan_index = _si,						\
+	.scan_type = {							\
+		.sign = 's',						\
+		.realbits = 64,					\
+		.storagebits = 64,					\
+		},							\
+}
 
 /**
  * iio_get_time_ns() - utility function to get a time stamp for events etc
-- 
cgit v1.2.3


From 5a86bf343976b9c8ab2f240bc866451fa67e5573 Mon Sep 17 00:00:00 2001
From: Kenneth Heitke <kheitke@codeaurora.org>
Date: Wed, 12 Feb 2014 13:44:22 -0600
Subject: spmi: Linux driver framework for SPMI

System Power Management Interface (SPMI) is a specification
developed by the MIPI (Mobile Industry Process Interface) Alliance
optimized for the real time control of Power Management ICs (PMIC).

SPMI is a two-wire serial interface that supports up to 4 master
devices and up to 16 logical slaves.

The framework supports message APIs, multiple busses (1 controller
per bus) and multiple clients/slave devices per controller.

Signed-off-by: Kenneth Heitke <kheitke@codeaurora.org>
Signed-off-by: Michael Bohan <mbohan@codeaurora.org>
Signed-off-by: Josh Cartwright <joshc@codeaurora.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/Kconfig                 |   2 +
 drivers/Makefile                |   1 +
 drivers/spmi/Kconfig            |   9 +
 drivers/spmi/Makefile           |   4 +
 drivers/spmi/spmi.c             | 609 ++++++++++++++++++++++++++++++++++++++++
 include/dt-bindings/spmi/spmi.h |  18 ++
 include/linux/mod_devicetable.h |   8 +
 include/linux/spmi.h            | 191 +++++++++++++
 8 files changed, 842 insertions(+)
 create mode 100644 drivers/spmi/Kconfig
 create mode 100644 drivers/spmi/Makefile
 create mode 100644 drivers/spmi/spmi.c
 create mode 100644 include/dt-bindings/spmi/spmi.h
 create mode 100644 include/linux/spmi.h

(limited to 'include/linux')

diff --git a/drivers/Kconfig b/drivers/Kconfig
index b3138fbb46a4..e0a4ae61a2c4 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -52,6 +52,8 @@ source "drivers/i2c/Kconfig"
 
 source "drivers/spi/Kconfig"
 
+source "drivers/spmi/Kconfig"
+
 source "drivers/hsi/Kconfig"
 
 source "drivers/pps/Kconfig"
diff --git a/drivers/Makefile b/drivers/Makefile
index 8e3b8b06c0b2..3d6de8b489c5 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -66,6 +66,7 @@ obj-$(CONFIG_ATA)		+= ata/
 obj-$(CONFIG_TARGET_CORE)	+= target/
 obj-$(CONFIG_MTD)		+= mtd/
 obj-$(CONFIG_SPI)		+= spi/
+obj-$(CONFIG_SPMI)		+= spmi/
 obj-y				+= hsi/
 obj-y				+= net/
 obj-$(CONFIG_ATM)		+= atm/
diff --git a/drivers/spmi/Kconfig b/drivers/spmi/Kconfig
new file mode 100644
index 000000000000..1dbfee022e90
--- /dev/null
+++ b/drivers/spmi/Kconfig
@@ -0,0 +1,9 @@
+#
+# SPMI driver configuration
+#
+menuconfig SPMI
+	tristate "SPMI support"
+	help
+	  SPMI (System Power Management Interface) is a two-wire
+	  serial interface between baseband and application processors
+	  and Power Management Integrated Circuits (PMIC).
diff --git a/drivers/spmi/Makefile b/drivers/spmi/Makefile
new file mode 100644
index 000000000000..1de1acd6a587
--- /dev/null
+++ b/drivers/spmi/Makefile
@@ -0,0 +1,4 @@
+#
+# Makefile for kernel SPMI framework.
+#
+obj-$(CONFIG_SPMI)	+= spmi.o
diff --git a/drivers/spmi/spmi.c b/drivers/spmi/spmi.c
new file mode 100644
index 000000000000..6122c8f2f4e3
--- /dev/null
+++ b/drivers/spmi/spmi.c
@@ -0,0 +1,609 @@
+/* Copyright (c) 2012-2013, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/idr.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/spmi.h>
+#include <linux/module.h>
+#include <linux/pm_runtime.h>
+
+#include <dt-bindings/spmi/spmi.h>
+
+static DEFINE_IDA(ctrl_ida);
+
+static void spmi_dev_release(struct device *dev)
+{
+	struct spmi_device *sdev = to_spmi_device(dev);
+	kfree(sdev);
+}
+
+static const struct device_type spmi_dev_type = {
+	.release	= spmi_dev_release,
+};
+
+static void spmi_ctrl_release(struct device *dev)
+{
+	struct spmi_controller *ctrl = to_spmi_controller(dev);
+	ida_simple_remove(&ctrl_ida, ctrl->nr);
+	kfree(ctrl);
+}
+
+static const struct device_type spmi_ctrl_type = {
+	.release	= spmi_ctrl_release,
+};
+
+#ifdef CONFIG_PM_RUNTIME
+static int spmi_runtime_suspend(struct device *dev)
+{
+	struct spmi_device *sdev = to_spmi_device(dev);
+	int err;
+
+	err = pm_generic_runtime_suspend(dev);
+	if (err)
+		return err;
+
+	return spmi_command_sleep(sdev);
+}
+
+static int spmi_runtime_resume(struct device *dev)
+{
+	struct spmi_device *sdev = to_spmi_device(dev);
+	int err;
+
+	err = spmi_command_wakeup(sdev);
+	if (err)
+		return err;
+
+	return pm_generic_runtime_resume(dev);
+}
+#endif
+
+static const struct dev_pm_ops spmi_pm_ops = {
+	SET_RUNTIME_PM_OPS(
+		spmi_runtime_suspend,
+		spmi_runtime_resume,
+		NULL
+	)
+};
+
+static int spmi_device_match(struct device *dev, struct device_driver *drv)
+{
+	if (of_driver_match_device(dev, drv))
+		return 1;
+
+	if (drv->name)
+		return strncmp(dev_name(dev), drv->name,
+			       SPMI_NAME_SIZE) == 0;
+
+	return 0;
+}
+
+/**
+ * spmi_device_add() - add a device previously constructed via spmi_device_alloc()
+ * @sdev:	spmi_device to be added
+ */
+int spmi_device_add(struct spmi_device *sdev)
+{
+	struct spmi_controller *ctrl = sdev->ctrl;
+	int err;
+
+	dev_set_name(&sdev->dev, "%d-%02x", ctrl->nr, sdev->usid);
+
+	err = device_add(&sdev->dev);
+	if (err < 0) {
+		dev_err(&sdev->dev, "Can't add %s, status %d\n",
+			dev_name(&sdev->dev), err);
+		goto err_device_add;
+	}
+
+	dev_dbg(&sdev->dev, "device %s registered\n", dev_name(&sdev->dev));
+
+err_device_add:
+	return err;
+}
+EXPORT_SYMBOL_GPL(spmi_device_add);
+
+/**
+ * spmi_device_remove(): remove an SPMI device
+ * @sdev:	spmi_device to be removed
+ */
+void spmi_device_remove(struct spmi_device *sdev)
+{
+	device_unregister(&sdev->dev);
+}
+EXPORT_SYMBOL_GPL(spmi_device_remove);
+
+static inline int
+spmi_cmd(struct spmi_controller *ctrl, u8 opcode, u8 sid)
+{
+	if (!ctrl || !ctrl->cmd || ctrl->dev.type != &spmi_ctrl_type)
+		return -EINVAL;
+
+	return ctrl->cmd(ctrl, opcode, sid);
+}
+
+static inline int spmi_read_cmd(struct spmi_controller *ctrl, u8 opcode,
+				u8 sid, u16 addr, u8 *buf, size_t len)
+{
+	if (!ctrl || !ctrl->read_cmd || ctrl->dev.type != &spmi_ctrl_type)
+		return -EINVAL;
+
+	return ctrl->read_cmd(ctrl, opcode, sid, addr, buf, len);
+}
+
+static inline int spmi_write_cmd(struct spmi_controller *ctrl, u8 opcode,
+				 u8 sid, u16 addr, const u8 *buf, size_t len)
+{
+	if (!ctrl || !ctrl->write_cmd || ctrl->dev.type != &spmi_ctrl_type)
+		return -EINVAL;
+
+	return ctrl->write_cmd(ctrl, opcode, sid, addr, buf, len);
+}
+
+/**
+ * spmi_register_read() - register read
+ * @sdev:	SPMI device.
+ * @addr:	slave register address (5-bit address).
+ * @buf:	buffer to be populated with data from the Slave.
+ *
+ * Reads 1 byte of data from a Slave device register.
+ */
+int spmi_register_read(struct spmi_device *sdev, u8 addr, u8 *buf)
+{
+	/* 5-bit register address */
+	if (addr > 0x1F)
+		return -EINVAL;
+
+	return spmi_read_cmd(sdev->ctrl, SPMI_CMD_READ, sdev->usid, addr,
+			     buf, 1);
+}
+EXPORT_SYMBOL_GPL(spmi_register_read);
+
+/**
+ * spmi_ext_register_read() - extended register read
+ * @sdev:	SPMI device.
+ * @addr:	slave register address (8-bit address).
+ * @buf:	buffer to be populated with data from the Slave.
+ * @len:	the request number of bytes to read (up to 16 bytes).
+ *
+ * Reads up to 16 bytes of data from the extended register space on a
+ * Slave device.
+ */
+int spmi_ext_register_read(struct spmi_device *sdev, u8 addr, u8 *buf,
+			   size_t len)
+{
+	/* 8-bit register address, up to 16 bytes */
+	if (len == 0 || len > 16)
+		return -EINVAL;
+
+	return spmi_read_cmd(sdev->ctrl, SPMI_CMD_EXT_READ, sdev->usid, addr,
+			     buf, len);
+}
+EXPORT_SYMBOL_GPL(spmi_ext_register_read);
+
+/**
+ * spmi_ext_register_readl() - extended register read long
+ * @sdev:	SPMI device.
+ * @addr:	slave register address (16-bit address).
+ * @buf:	buffer to be populated with data from the Slave.
+ * @len:	the request number of bytes to read (up to 8 bytes).
+ *
+ * Reads up to 8 bytes of data from the extended register space on a
+ * Slave device using 16-bit address.
+ */
+int spmi_ext_register_readl(struct spmi_device *sdev, u16 addr, u8 *buf,
+			    size_t len)
+{
+	/* 16-bit register address, up to 8 bytes */
+	if (len == 0 || len > 8)
+		return -EINVAL;
+
+	return spmi_read_cmd(sdev->ctrl, SPMI_CMD_EXT_READL, sdev->usid, addr,
+			     buf, len);
+}
+EXPORT_SYMBOL_GPL(spmi_ext_register_readl);
+
+/**
+ * spmi_register_write() - register write
+ * @sdev:	SPMI device
+ * @addr:	slave register address (5-bit address).
+ * @data:	buffer containing the data to be transferred to the Slave.
+ *
+ * Writes 1 byte of data to a Slave device register.
+ */
+int spmi_register_write(struct spmi_device *sdev, u8 addr, u8 data)
+{
+	/* 5-bit register address */
+	if (addr > 0x1F)
+		return -EINVAL;
+
+	return spmi_write_cmd(sdev->ctrl, SPMI_CMD_WRITE, sdev->usid, addr,
+			      &data, 1);
+}
+EXPORT_SYMBOL_GPL(spmi_register_write);
+
+/**
+ * spmi_register_zero_write() - register zero write
+ * @sdev:	SPMI device.
+ * @data:	the data to be written to register 0 (7-bits).
+ *
+ * Writes data to register 0 of the Slave device.
+ */
+int spmi_register_zero_write(struct spmi_device *sdev, u8 data)
+{
+	return spmi_write_cmd(sdev->ctrl, SPMI_CMD_ZERO_WRITE, sdev->usid, 0,
+			      &data, 1);
+}
+EXPORT_SYMBOL_GPL(spmi_register_zero_write);
+
+/**
+ * spmi_ext_register_write() - extended register write
+ * @sdev:	SPMI device.
+ * @addr:	slave register address (8-bit address).
+ * @buf:	buffer containing the data to be transferred to the Slave.
+ * @len:	the request number of bytes to read (up to 16 bytes).
+ *
+ * Writes up to 16 bytes of data to the extended register space of a
+ * Slave device.
+ */
+int spmi_ext_register_write(struct spmi_device *sdev, u8 addr, const u8 *buf,
+			    size_t len)
+{
+	/* 8-bit register address, up to 16 bytes */
+	if (len == 0 || len > 16)
+		return -EINVAL;
+
+	return spmi_write_cmd(sdev->ctrl, SPMI_CMD_EXT_WRITE, sdev->usid, addr,
+			      buf, len);
+}
+EXPORT_SYMBOL_GPL(spmi_ext_register_write);
+
+/**
+ * spmi_ext_register_writel() - extended register write long
+ * @sdev:	SPMI device.
+ * @addr:	slave register address (16-bit address).
+ * @buf:	buffer containing the data to be transferred to the Slave.
+ * @len:	the request number of bytes to read (up to 8 bytes).
+ *
+ * Writes up to 8 bytes of data to the extended register space of a
+ * Slave device using 16-bit address.
+ */
+int spmi_ext_register_writel(struct spmi_device *sdev, u16 addr, const u8 *buf,
+			     size_t len)
+{
+	/* 4-bit Slave Identifier, 16-bit register address, up to 8 bytes */
+	if (len == 0 || len > 8)
+		return -EINVAL;
+
+	return spmi_write_cmd(sdev->ctrl, SPMI_CMD_EXT_WRITEL, sdev->usid,
+			      addr, buf, len);
+}
+EXPORT_SYMBOL_GPL(spmi_ext_register_writel);
+
+/**
+ * spmi_command_reset() - sends RESET command to the specified slave
+ * @sdev:	SPMI device.
+ *
+ * The Reset command initializes the Slave and forces all registers to
+ * their reset values. The Slave shall enter the STARTUP state after
+ * receiving a Reset command.
+ */
+int spmi_command_reset(struct spmi_device *sdev)
+{
+	return spmi_cmd(sdev->ctrl, SPMI_CMD_RESET, sdev->usid);
+}
+EXPORT_SYMBOL_GPL(spmi_command_reset);
+
+/**
+ * spmi_command_sleep() - sends SLEEP command to the specified SPMI device
+ * @sdev:	SPMI device.
+ *
+ * The Sleep command causes the Slave to enter the user defined SLEEP state.
+ */
+int spmi_command_sleep(struct spmi_device *sdev)
+{
+	return spmi_cmd(sdev->ctrl, SPMI_CMD_SLEEP, sdev->usid);
+}
+EXPORT_SYMBOL_GPL(spmi_command_sleep);
+
+/**
+ * spmi_command_wakeup() - sends WAKEUP command to the specified SPMI device
+ * @sdev:	SPMI device.
+ *
+ * The Wakeup command causes the Slave to move from the SLEEP state to
+ * the ACTIVE state.
+ */
+int spmi_command_wakeup(struct spmi_device *sdev)
+{
+	return spmi_cmd(sdev->ctrl, SPMI_CMD_WAKEUP, sdev->usid);
+}
+EXPORT_SYMBOL_GPL(spmi_command_wakeup);
+
+/**
+ * spmi_command_shutdown() - sends SHUTDOWN command to the specified SPMI device
+ * @sdev:	SPMI device.
+ *
+ * The Shutdown command causes the Slave to enter the SHUTDOWN state.
+ */
+int spmi_command_shutdown(struct spmi_device *sdev)
+{
+	return spmi_cmd(sdev->ctrl, SPMI_CMD_SHUTDOWN, sdev->usid);
+}
+EXPORT_SYMBOL_GPL(spmi_command_shutdown);
+
+static int spmi_drv_probe(struct device *dev)
+{
+	const struct spmi_driver *sdrv = to_spmi_driver(dev->driver);
+	struct spmi_device *sdev = to_spmi_device(dev);
+	int err;
+
+	/* Ensure the slave is in ACTIVE state */
+	err = spmi_command_wakeup(sdev);
+	if (err)
+		goto fail_wakeup;
+
+	pm_runtime_get_noresume(dev);
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+
+	err = sdrv->probe(sdev);
+	if (err)
+		goto fail_probe;
+
+	return 0;
+
+fail_probe:
+	pm_runtime_disable(dev);
+	pm_runtime_set_suspended(dev);
+	pm_runtime_put_noidle(dev);
+fail_wakeup:
+	return err;
+}
+
+static int spmi_drv_remove(struct device *dev)
+{
+	const struct spmi_driver *sdrv = to_spmi_driver(dev->driver);
+
+	pm_runtime_get_sync(dev);
+	sdrv->remove(to_spmi_device(dev));
+	pm_runtime_put_noidle(dev);
+
+	pm_runtime_disable(dev);
+	pm_runtime_set_suspended(dev);
+	pm_runtime_put_noidle(dev);
+	return 0;
+}
+
+static struct bus_type spmi_bus_type = {
+	.name		= "spmi",
+	.match		= spmi_device_match,
+	.pm		= &spmi_pm_ops,
+	.probe		= spmi_drv_probe,
+	.remove		= spmi_drv_remove,
+};
+
+/**
+ * spmi_controller_alloc() - Allocate a new SPMI device
+ * @ctrl:	associated controller
+ *
+ * Caller is responsible for either calling spmi_device_add() to add the
+ * newly allocated controller, or calling spmi_device_put() to discard it.
+ */
+struct spmi_device *spmi_device_alloc(struct spmi_controller *ctrl)
+{
+	struct spmi_device *sdev;
+
+	sdev = kzalloc(sizeof(*sdev), GFP_KERNEL);
+	if (!sdev)
+		return NULL;
+
+	sdev->ctrl = ctrl;
+	device_initialize(&sdev->dev);
+	sdev->dev.parent = &ctrl->dev;
+	sdev->dev.bus = &spmi_bus_type;
+	sdev->dev.type = &spmi_dev_type;
+	return sdev;
+}
+EXPORT_SYMBOL_GPL(spmi_device_alloc);
+
+/**
+ * spmi_controller_alloc() - Allocate a new SPMI controller
+ * @parent:	parent device
+ * @size:	size of private data
+ *
+ * Caller is responsible for either calling spmi_controller_add() to add the
+ * newly allocated controller, or calling spmi_controller_put() to discard it.
+ * The allocated private data region may be accessed via
+ * spmi_controller_get_drvdata()
+ */
+struct spmi_controller *spmi_controller_alloc(struct device *parent,
+					      size_t size)
+{
+	struct spmi_controller *ctrl;
+	int id;
+
+	if (WARN_ON(!parent))
+		return NULL;
+
+	ctrl = kzalloc(sizeof(*ctrl) + size, GFP_KERNEL);
+	if (!ctrl)
+		return NULL;
+
+	device_initialize(&ctrl->dev);
+	ctrl->dev.type = &spmi_ctrl_type;
+	ctrl->dev.bus = &spmi_bus_type;
+	ctrl->dev.parent = parent;
+	ctrl->dev.of_node = parent->of_node;
+	spmi_controller_set_drvdata(ctrl, &ctrl[1]);
+
+	id = ida_simple_get(&ctrl_ida, 0, 0, GFP_KERNEL);
+	if (id < 0) {
+		dev_err(parent,
+			"unable to allocate SPMI controller identifier.\n");
+		spmi_controller_put(ctrl);
+		return NULL;
+	}
+
+	ctrl->nr = id;
+	dev_set_name(&ctrl->dev, "spmi-%d", id);
+
+	dev_dbg(&ctrl->dev, "allocated controller 0x%p id %d\n", ctrl, id);
+	return ctrl;
+}
+EXPORT_SYMBOL_GPL(spmi_controller_alloc);
+
+static void of_spmi_register_devices(struct spmi_controller *ctrl)
+{
+	struct device_node *node;
+	int err;
+
+	if (!ctrl->dev.of_node)
+		return;
+
+	for_each_available_child_of_node(ctrl->dev.of_node, node) {
+		struct spmi_device *sdev;
+		u32 reg[2];
+
+		dev_dbg(&ctrl->dev, "adding child %s\n", node->full_name);
+
+		err = of_property_read_u32_array(node, "reg", reg, 2);
+		if (err) {
+			dev_err(&ctrl->dev,
+				"node %s err (%d) does not have 'reg' property\n",
+				node->full_name, err);
+			continue;
+		}
+
+		if (reg[1] != SPMI_USID) {
+			dev_err(&ctrl->dev,
+				"node %s contains unsupported 'reg' entry\n",
+				node->full_name);
+			continue;
+		}
+
+		if (reg[0] >= SPMI_MAX_SLAVE_ID) {
+			dev_err(&ctrl->dev,
+				"invalid usid on node %s\n",
+				node->full_name);
+			continue;
+		}
+
+		dev_dbg(&ctrl->dev, "read usid %02x\n", reg[0]);
+
+		sdev = spmi_device_alloc(ctrl);
+		if (!sdev)
+			continue;
+
+		sdev->dev.of_node = node;
+		sdev->usid = (u8) reg[0];
+
+		err = spmi_device_add(sdev);
+		if (err) {
+			dev_err(&sdev->dev,
+				"failure adding device. status %d\n", err);
+			spmi_device_put(sdev);
+		}
+	}
+}
+
+/**
+ * spmi_controller_add() - Add an SPMI controller
+ * @ctrl:	controller to be registered.
+ *
+ * Register a controller previously allocated via spmi_controller_alloc() with
+ * the SPMI core.
+ */
+int spmi_controller_add(struct spmi_controller *ctrl)
+{
+	int ret;
+
+	/* Can't register until after driver model init */
+	if (WARN_ON(!spmi_bus_type.p))
+		return -EAGAIN;
+
+	ret = device_add(&ctrl->dev);
+	if (ret)
+		return ret;
+
+	if (IS_ENABLED(CONFIG_OF))
+		of_spmi_register_devices(ctrl);
+
+	dev_dbg(&ctrl->dev, "spmi-%d registered: dev:%p\n",
+		ctrl->nr, &ctrl->dev);
+
+	return 0;
+};
+EXPORT_SYMBOL_GPL(spmi_controller_add);
+
+/* Remove a device associated with a controller */
+static int spmi_ctrl_remove_device(struct device *dev, void *data)
+{
+	struct spmi_device *spmidev = to_spmi_device(dev);
+	if (dev->type == &spmi_dev_type)
+		spmi_device_remove(spmidev);
+	return 0;
+}
+
+/**
+ * spmi_controller_remove(): remove an SPMI controller
+ * @ctrl:	controller to remove
+ *
+ * Remove a SPMI controller.  Caller is responsible for calling
+ * spmi_controller_put() to discard the allocated controller.
+ */
+void spmi_controller_remove(struct spmi_controller *ctrl)
+{
+	int dummy;
+
+	if (!ctrl)
+		return;
+
+	dummy = device_for_each_child(&ctrl->dev, NULL,
+				      spmi_ctrl_remove_device);
+	device_del(&ctrl->dev);
+}
+EXPORT_SYMBOL_GPL(spmi_controller_remove);
+
+/**
+ * spmi_driver_register() - Register client driver with SPMI core
+ * @sdrv:	client driver to be associated with client-device.
+ *
+ * This API will register the client driver with the SPMI framework.
+ * It is typically called from the driver's module-init function.
+ */
+int spmi_driver_register(struct spmi_driver *sdrv)
+{
+	sdrv->driver.bus = &spmi_bus_type;
+	return driver_register(&sdrv->driver);
+}
+EXPORT_SYMBOL_GPL(spmi_driver_register);
+
+static void __exit spmi_exit(void)
+{
+	bus_unregister(&spmi_bus_type);
+}
+module_exit(spmi_exit);
+
+static int __init spmi_init(void)
+{
+	return bus_register(&spmi_bus_type);
+}
+postcore_initcall(spmi_init);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("SPMI module");
+MODULE_ALIAS("platform:spmi");
diff --git a/include/dt-bindings/spmi/spmi.h b/include/dt-bindings/spmi/spmi.h
new file mode 100644
index 000000000000..d11e1e543871
--- /dev/null
+++ b/include/dt-bindings/spmi/spmi.h
@@ -0,0 +1,18 @@
+/* Copyright (c) 2013, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#ifndef __DT_BINDINGS_SPMI_H
+#define __DT_BINDINGS_SPMI_H
+
+#define SPMI_USID	0
+#define SPMI_GSID	1
+
+#endif
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 45e921401b06..677e474fc273 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -432,6 +432,14 @@ struct spi_device_id {
 	kernel_ulong_t driver_data;	/* Data private to the driver */
 };
 
+#define SPMI_NAME_SIZE	32
+#define SPMI_MODULE_PREFIX "spmi:"
+
+struct spmi_device_id {
+	char name[SPMI_NAME_SIZE];
+	kernel_ulong_t driver_data;	/* Data private to the driver */
+};
+
 /* dmi */
 enum dmi_field {
 	DMI_NONE,
diff --git a/include/linux/spmi.h b/include/linux/spmi.h
new file mode 100644
index 000000000000..91f5eab9e428
--- /dev/null
+++ b/include/linux/spmi.h
@@ -0,0 +1,191 @@
+/* Copyright (c) 2012-2013, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#ifndef _LINUX_SPMI_H
+#define _LINUX_SPMI_H
+
+#include <linux/types.h>
+#include <linux/device.h>
+#include <linux/mod_devicetable.h>
+
+/* Maximum slave identifier */
+#define SPMI_MAX_SLAVE_ID		16
+
+/* SPMI Commands */
+#define SPMI_CMD_EXT_WRITE		0x00
+#define SPMI_CMD_RESET			0x10
+#define SPMI_CMD_SLEEP			0x11
+#define SPMI_CMD_SHUTDOWN		0x12
+#define SPMI_CMD_WAKEUP			0x13
+#define SPMI_CMD_AUTHENTICATE		0x14
+#define SPMI_CMD_MSTR_READ		0x15
+#define SPMI_CMD_MSTR_WRITE		0x16
+#define SPMI_CMD_TRANSFER_BUS_OWNERSHIP	0x1A
+#define SPMI_CMD_DDB_MASTER_READ	0x1B
+#define SPMI_CMD_DDB_SLAVE_READ		0x1C
+#define SPMI_CMD_EXT_READ		0x20
+#define SPMI_CMD_EXT_WRITEL		0x30
+#define SPMI_CMD_EXT_READL		0x38
+#define SPMI_CMD_WRITE			0x40
+#define SPMI_CMD_READ			0x60
+#define SPMI_CMD_ZERO_WRITE		0x80
+
+/**
+ * struct spmi_device - Basic representation of an SPMI device
+ * @dev:	Driver model representation of the device.
+ * @ctrl:	SPMI controller managing the bus hosting this device.
+ * @usid:	This devices' Unique Slave IDentifier.
+ */
+struct spmi_device {
+	struct device		dev;
+	struct spmi_controller	*ctrl;
+	u8			usid;
+};
+
+static inline struct spmi_device *to_spmi_device(struct device *d)
+{
+	return container_of(d, struct spmi_device, dev);
+}
+
+static inline void *spmi_device_get_drvdata(const struct spmi_device *sdev)
+{
+	return dev_get_drvdata(&sdev->dev);
+}
+
+static inline void spmi_device_set_drvdata(struct spmi_device *sdev, void *data)
+{
+	dev_set_drvdata(&sdev->dev, data);
+}
+
+struct spmi_device *spmi_device_alloc(struct spmi_controller *ctrl);
+
+static inline void spmi_device_put(struct spmi_device *sdev)
+{
+	if (sdev)
+		put_device(&sdev->dev);
+}
+
+int spmi_device_add(struct spmi_device *sdev);
+
+void spmi_device_remove(struct spmi_device *sdev);
+
+/**
+ * struct spmi_controller - interface to the SPMI master controller
+ * @dev:	Driver model representation of the device.
+ * @nr:		board-specific number identifier for this controller/bus
+ * @cmd:	sends a non-data command sequence on the SPMI bus.
+ * @read_cmd:	sends a register read command sequence on the SPMI bus.
+ * @write_cmd:	sends a register write command sequence on the SPMI bus.
+ */
+struct spmi_controller {
+	struct device		dev;
+	unsigned int		nr;
+	int	(*cmd)(struct spmi_controller *ctrl, u8 opcode, u8 sid);
+	int	(*read_cmd)(struct spmi_controller *ctrl, u8 opcode,
+			    u8 sid, u16 addr, u8 *buf, size_t len);
+	int	(*write_cmd)(struct spmi_controller *ctrl, u8 opcode,
+			     u8 sid, u16 addr, const u8 *buf, size_t len);
+};
+
+static inline struct spmi_controller *to_spmi_controller(struct device *d)
+{
+	return container_of(d, struct spmi_controller, dev);
+}
+
+static inline
+void *spmi_controller_get_drvdata(const struct spmi_controller *ctrl)
+{
+	return dev_get_drvdata(&ctrl->dev);
+}
+
+static inline void spmi_controller_set_drvdata(struct spmi_controller *ctrl,
+					       void *data)
+{
+	dev_set_drvdata(&ctrl->dev, data);
+}
+
+struct spmi_controller *spmi_controller_alloc(struct device *parent,
+					      size_t size);
+
+/**
+ * spmi_controller_put() - decrement controller refcount
+ * @ctrl	SPMI controller.
+ */
+static inline void spmi_controller_put(struct spmi_controller *ctrl)
+{
+	if (ctrl)
+		put_device(&ctrl->dev);
+}
+
+int spmi_controller_add(struct spmi_controller *ctrl);
+void spmi_controller_remove(struct spmi_controller *ctrl);
+
+/**
+ * struct spmi_driver - SPMI slave device driver
+ * @driver:	SPMI device drivers should initialize name and owner field of
+ *		this structure.
+ * @probe:	binds this driver to a SPMI device.
+ * @remove:	unbinds this driver from the SPMI device.
+ * @shutdown:	standard shutdown callback used during powerdown/halt.
+ * @suspend:	standard suspend callback used during system suspend.
+ * @resume:	standard resume callback used during system resume.
+ *
+ * If PM runtime support is desired for a slave, a device driver can call
+ * pm_runtime_put() from their probe() routine (and a balancing
+ * pm_runtime_get() in remove()).  PM runtime support for a slave is
+ * implemented by issuing a SLEEP command to the slave on runtime_suspend(),
+ * transitioning the slave into the SLEEP state.  On runtime_resume(), a WAKEUP
+ * command is sent to the slave to bring it back to ACTIVE.
+ */
+struct spmi_driver {
+	struct device_driver driver;
+	int	(*probe)(struct spmi_device *sdev);
+	void	(*remove)(struct spmi_device *sdev);
+};
+
+static inline struct spmi_driver *to_spmi_driver(struct device_driver *d)
+{
+	return container_of(d, struct spmi_driver, driver);
+}
+
+int spmi_driver_register(struct spmi_driver *sdrv);
+
+/**
+ * spmi_driver_unregister() - unregister an SPMI client driver
+ * @sdrv:	the driver to unregister
+ */
+static inline void spmi_driver_unregister(struct spmi_driver *sdrv)
+{
+	if (sdrv)
+		driver_unregister(&sdrv->driver);
+}
+
+#define module_spmi_driver(__spmi_driver) \
+	module_driver(__spmi_driver, spmi_driver_register, \
+			spmi_driver_unregister)
+
+int spmi_register_read(struct spmi_device *sdev, u8 addr, u8 *buf);
+int spmi_ext_register_read(struct spmi_device *sdev, u8 addr, u8 *buf,
+			   size_t len);
+int spmi_ext_register_readl(struct spmi_device *sdev, u16 addr, u8 *buf,
+			    size_t len);
+int spmi_register_write(struct spmi_device *sdev, u8 addr, u8 data);
+int spmi_register_zero_write(struct spmi_device *sdev, u8 data);
+int spmi_ext_register_write(struct spmi_device *sdev, u8 addr,
+			    const u8 *buf, size_t len);
+int spmi_ext_register_writel(struct spmi_device *sdev, u16 addr,
+			     const u8 *buf, size_t len);
+int spmi_command_reset(struct spmi_device *sdev);
+int spmi_command_sleep(struct spmi_device *sdev);
+int spmi_command_wakeup(struct spmi_device *sdev);
+int spmi_command_shutdown(struct spmi_device *sdev);
+
+#endif
-- 
cgit v1.2.3


From c9afbb05a9ffbef0976242ab1135af6814ccff0f Mon Sep 17 00:00:00 2001
From: Josh Cartwright <joshc@codeaurora.org>
Date: Wed, 12 Feb 2014 13:44:27 -0600
Subject: regmap: spmi: support base and extended register spaces

SPMI states that a slave may contain two register spaces, the Base
register space is a 5-bit byte-addressable space accessed via the
Register Read/Write and Register Zero Write command sequences, and the
Extended register space: a 16-bit byte-addressable space accessed via
the Extended Read/Write and Extended Read/Write Long command sequences.

Provide support for accessing both of these spaces, taking advantage of
the more bandwidth-efficient commands ('Register 0 Write' vs 'Register
Write', and 'Extended Register Read/Write' vs 'Extended Register
Read/Write Long') when possible.

Signed-off-by: Josh Cartwright <joshc@codeaurora.org>
Acked-by: Mark Brown <broonie@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/regmap/regmap-spmi.c | 228 ++++++++++++++++++++++++++++++++------
 include/linux/regmap.h            |  12 +-
 2 files changed, 205 insertions(+), 35 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/regmap/regmap-spmi.c b/drivers/base/regmap/regmap-spmi.c
index ac2391013db1..d7026dc33388 100644
--- a/drivers/base/regmap/regmap-spmi.c
+++ b/drivers/base/regmap/regmap-spmi.c
@@ -22,69 +22,235 @@
 #include <linux/module.h>
 #include <linux/init.h>
 
-static int regmap_spmi_read(void *context,
-			    const void *reg, size_t reg_size,
-			    void *val, size_t val_size)
+static int regmap_spmi_base_read(void *context,
+				 const void *reg, size_t reg_size,
+				 void *val, size_t val_size)
 {
+	u8 addr = *(u8 *)reg;
+	int err = 0;
+
+	BUG_ON(reg_size != 1);
+
+	while (val_size-- && !err)
+		err = spmi_register_read(context, addr++, val++);
+
+	return err;
+}
+
+static int regmap_spmi_base_gather_write(void *context,
+					 const void *reg, size_t reg_size,
+					 const void *val, size_t val_size)
+{
+	const u8 *data = val;
+	u8 addr = *(u8 *)reg;
+	int err = 0;
+
+	BUG_ON(reg_size != 1);
+
+	/*
+	 * SPMI defines a more bandwidth-efficient 'Register 0 Write' sequence,
+	 * use it when possible.
+	 */
+	if (addr == 0 && val_size) {
+		err = spmi_register_zero_write(context, *data);
+		if (err)
+			goto err_out;
+
+		data++;
+		addr++;
+		val_size--;
+	}
+
+	while (val_size) {
+		err = spmi_register_write(context, addr, *data);
+		if (err)
+			goto err_out;
+
+		data++;
+		addr++;
+		val_size--;
+	}
+
+err_out:
+	return err;
+}
+
+static int regmap_spmi_base_write(void *context, const void *data,
+				  size_t count)
+{
+	BUG_ON(count < 1);
+	return regmap_spmi_base_gather_write(context, data, 1, data + 1,
+					     count - 1);
+}
+
+static struct regmap_bus regmap_spmi_base = {
+	.read				= regmap_spmi_base_read,
+	.write				= regmap_spmi_base_write,
+	.gather_write			= regmap_spmi_base_gather_write,
+	.reg_format_endian_default	= REGMAP_ENDIAN_NATIVE,
+	.val_format_endian_default	= REGMAP_ENDIAN_NATIVE,
+};
+
+/**
+ * regmap_init_spmi_base(): Create regmap for the Base register space
+ * @sdev:	SPMI device that will be interacted with
+ * @config:	Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer to
+ * a struct regmap.
+ */
+struct regmap *regmap_init_spmi_base(struct spmi_device *sdev,
+				     const struct regmap_config *config)
+{
+	return regmap_init(&sdev->dev, &regmap_spmi_base, sdev, config);
+}
+EXPORT_SYMBOL_GPL(regmap_init_spmi_base);
+
+/**
+ * devm_regmap_init_spmi_base(): Create managed regmap for Base register space
+ * @sdev:	SPMI device that will be interacted with
+ * @config:	Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer
+ * to a struct regmap.  The regmap will be automatically freed by the
+ * device management code.
+ */
+struct regmap *devm_regmap_init_spmi_base(struct spmi_device *sdev,
+					  const struct regmap_config *config)
+{
+	return devm_regmap_init(&sdev->dev, &regmap_spmi_base, sdev, config);
+}
+EXPORT_SYMBOL_GPL(devm_regmap_init_spmi_base);
+
+static int regmap_spmi_ext_read(void *context,
+				const void *reg, size_t reg_size,
+				void *val, size_t val_size)
+{
+	int err = 0;
+	size_t len;
+	u16 addr;
+
 	BUG_ON(reg_size != 2);
-	return spmi_ext_register_readl(context, *(u16 *)reg,
-				       val, val_size);
+
+	addr = *(u16 *)reg;
+
+	/*
+	 * Split accesses into two to take advantage of the more
+	 * bandwidth-efficient 'Extended Register Read' command when possible
+	 */
+	while (addr <= 0xFF && val_size) {
+		len = min_t(size_t, val_size, 16);
+
+		err = spmi_ext_register_read(context, addr, val, len);
+		if (err)
+			goto err_out;
+
+		addr += len;
+		val += len;
+		val_size -= len;
+	}
+
+	while (val_size) {
+		len = min_t(size_t, val_size, 8);
+
+		err = spmi_ext_register_readl(context, addr, val, val_size);
+		if (err)
+			goto err_out;
+
+		addr += len;
+		val += len;
+		val_size -= len;
+	}
+
+err_out:
+	return err;
 }
 
-static int regmap_spmi_gather_write(void *context,
-				    const void *reg, size_t reg_size,
-				    const void *val, size_t val_size)
+static int regmap_spmi_ext_gather_write(void *context,
+					const void *reg, size_t reg_size,
+					const void *val, size_t val_size)
 {
+	int err = 0;
+	size_t len;
+	u16 addr;
+
 	BUG_ON(reg_size != 2);
-	return spmi_ext_register_writel(context, *(u16 *)reg, val, val_size);
+
+	addr = *(u16 *)reg;
+
+	while (addr <= 0xFF && val_size) {
+		len = min_t(size_t, val_size, 16);
+
+		err = spmi_ext_register_write(context, addr, val, len);
+		if (err)
+			goto err_out;
+
+		addr += len;
+		val += len;
+		val_size -= len;
+	}
+
+	while (val_size) {
+		len = min_t(size_t, val_size, 8);
+
+		err = spmi_ext_register_writel(context, addr, val, len);
+		if (err)
+			goto err_out;
+
+		addr += len;
+		val += len;
+		val_size -= len;
+	}
+
+err_out:
+	return err;
 }
 
-static int regmap_spmi_write(void *context, const void *data,
-			     size_t count)
+static int regmap_spmi_ext_write(void *context, const void *data,
+				 size_t count)
 {
 	BUG_ON(count < 2);
-	return regmap_spmi_gather_write(context, data, 2, data + 2, count - 2);
+	return regmap_spmi_ext_gather_write(context, data, 2, data + 2,
+					    count - 2);
 }
 
-static struct regmap_bus regmap_spmi = {
-	.read				= regmap_spmi_read,
-	.write				= regmap_spmi_write,
-	.gather_write			= regmap_spmi_gather_write,
+static struct regmap_bus regmap_spmi_ext = {
+	.read				= regmap_spmi_ext_read,
+	.write				= regmap_spmi_ext_write,
+	.gather_write			= regmap_spmi_ext_gather_write,
 	.reg_format_endian_default	= REGMAP_ENDIAN_NATIVE,
 	.val_format_endian_default	= REGMAP_ENDIAN_NATIVE,
 };
 
 /**
- * regmap_init_spmi(): Initialize register map
- *
- * @sdev: Device that will be interacted with
- * @config: Configuration for register map
+ * regmap_init_spmi_ext(): Create regmap for Ext register space
+ * @sdev:	Device that will be interacted with
+ * @config:	Configuration for register map
  *
  * The return value will be an ERR_PTR() on error or a valid pointer to
  * a struct regmap.
  */
-struct regmap *regmap_init_spmi(struct spmi_device *sdev,
-				const struct regmap_config *config)
+struct regmap *regmap_init_spmi_ext(struct spmi_device *sdev,
+				    const struct regmap_config *config)
 {
-	return regmap_init(&sdev->dev, &regmap_spmi, sdev, config);
+	return regmap_init(&sdev->dev, &regmap_spmi_ext, sdev, config);
 }
-EXPORT_SYMBOL_GPL(regmap_init_spmi);
+EXPORT_SYMBOL_GPL(regmap_init_spmi_ext);
 
 /**
- * devm_regmap_init_spmi(): Initialise managed register map
- *
- * @sdev: Device that will be interacted with
- * @config: Configuration for register map
+ * devm_regmap_init_spmi_ext(): Create managed regmap for Ext register space
+ * @sdev:	SPMI device that will be interacted with
+ * @config:	Configuration for register map
  *
  * The return value will be an ERR_PTR() on error or a valid pointer
  * to a struct regmap.  The regmap will be automatically freed by the
  * device management code.
  */
-struct regmap *devm_regmap_init_spmi(struct spmi_device *sdev,
+struct regmap *devm_regmap_init_spmi_ext(struct spmi_device *sdev,
 				     const struct regmap_config *config)
 {
-	return devm_regmap_init(&sdev->dev, &regmap_spmi, sdev, config);
+	return devm_regmap_init(&sdev->dev, &regmap_spmi_ext, sdev, config);
 }
-EXPORT_SYMBOL_GPL(devm_regmap_init_spmi);
+EXPORT_SYMBOL_GPL(devm_regmap_init_spmi_ext);
 
 MODULE_LICENSE("GPL");
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 4149f1a9b003..8cc73ac6f888 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -321,8 +321,10 @@ struct regmap *regmap_init_i2c(struct i2c_client *i2c,
 			       const struct regmap_config *config);
 struct regmap *regmap_init_spi(struct spi_device *dev,
 			       const struct regmap_config *config);
-struct regmap *regmap_init_spmi(struct spmi_device *dev,
-			       const struct regmap_config *config);
+struct regmap *regmap_init_spmi_base(struct spmi_device *dev,
+				     const struct regmap_config *config);
+struct regmap *regmap_init_spmi_ext(struct spmi_device *dev,
+				    const struct regmap_config *config);
 struct regmap *regmap_init_mmio_clk(struct device *dev, const char *clk_id,
 				    void __iomem *regs,
 				    const struct regmap_config *config);
@@ -335,8 +337,10 @@ struct regmap *devm_regmap_init_i2c(struct i2c_client *i2c,
 				    const struct regmap_config *config);
 struct regmap *devm_regmap_init_spi(struct spi_device *dev,
 				    const struct regmap_config *config);
-struct regmap *devm_regmap_init_spmi(struct spmi_device *dev,
-				     const struct regmap_config *config);
+struct regmap *devm_regmap_init_spmi_base(struct spmi_device *dev,
+					  const struct regmap_config *config);
+struct regmap *devm_regmap_init_spmi_ext(struct spmi_device *dev,
+					 const struct regmap_config *config);
 struct regmap *devm_regmap_init_mmio_clk(struct device *dev, const char *clk_id,
 					 void __iomem *regs,
 					 const struct regmap_config *config);
-- 
cgit v1.2.3


From 6cfec04bcc05a829179c02584bb55f28fee03795 Mon Sep 17 00:00:00 2001
From: Michal Simek <michal.simek@xilinx.com>
Date: Mon, 10 Feb 2014 16:22:33 +0100
Subject: regmap: Separate regmap dev initialization

Create special function regmap_attach_dev
which can be called separately out of regmap_init.

Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/base/regmap/regmap.c | 41 ++++++++++++++++++++++++++++-------------
 include/linux/regmap.h       |  2 ++
 2 files changed, 30 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 6a19515f8a45..43065ceff90f 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -380,6 +380,28 @@ static void regmap_range_exit(struct regmap *map)
 	kfree(map->selector_work_buf);
 }
 
+int regmap_attach_dev(struct device *dev, struct regmap *map,
+		      const struct regmap_config *config)
+{
+	struct regmap **m;
+
+	map->dev = dev;
+
+	regmap_debugfs_init(map, config->name);
+
+	/* Add a devres resource for dev_get_regmap() */
+	m = devres_alloc(dev_get_regmap_release, sizeof(*m), GFP_KERNEL);
+	if (!m) {
+		regmap_debugfs_exit(map);
+		return -ENOMEM;
+	}
+	*m = map;
+	devres_add(dev, m);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(regmap_attach_dev);
+
 /**
  * regmap_init(): Initialise register map
  *
@@ -397,7 +419,7 @@ struct regmap *regmap_init(struct device *dev,
 			   void *bus_context,
 			   const struct regmap_config *config)
 {
-	struct regmap *map, **m;
+	struct regmap *map;
 	int ret = -EINVAL;
 	enum regmap_endian reg_endian, val_endian;
 	int i, j;
@@ -734,25 +756,18 @@ skip_format_initialization:
 		}
 	}
 
-	regmap_debugfs_init(map, config->name);
-
 	ret = regcache_init(map, config);
 	if (ret != 0)
 		goto err_range;
 
-	/* Add a devres resource for dev_get_regmap() */
-	m = devres_alloc(dev_get_regmap_release, sizeof(*m), GFP_KERNEL);
-	if (!m) {
-		ret = -ENOMEM;
-		goto err_debugfs;
-	}
-	*m = map;
-	devres_add(dev, m);
+	if (dev)
+		ret = regmap_attach_dev(dev, map, config);
+		if (ret != 0)
+			goto err_regcache;
 
 	return map;
 
-err_debugfs:
-	regmap_debugfs_exit(map);
+err_regcache:
 	regcache_exit(map);
 err_range:
 	regmap_range_exit(map);
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 4149f1a9b003..fa4d079fa44c 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -317,6 +317,8 @@ struct regmap *regmap_init(struct device *dev,
 			   const struct regmap_bus *bus,
 			   void *bus_context,
 			   const struct regmap_config *config);
+int regmap_attach_dev(struct device *dev, struct regmap *map,
+				 const struct regmap_config *config);
 struct regmap *regmap_init_i2c(struct i2c_client *i2c,
 			       const struct regmap_config *config);
 struct regmap *regmap_init_spi(struct spi_device *dev,
-- 
cgit v1.2.3


From 963eb4b87dcfc0f9a1ac0ea85ca92832e61544ad Mon Sep 17 00:00:00 2001
From: Sachin Kamat <sachin.kamat@linaro.org>
Date: Fri, 14 Feb 2014 12:26:17 +0530
Subject: spi/s3c64xx: Trivial cleanup in header file

Commit 436d42c61c3e ("ARM: samsung: move platform_data definitions")
moved the files to the current location but forgot to remove the pointer
to its previous location. Clean it up. While at it also change the header
file protection macros appropriately.

Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/linux/platform_data/spi-s3c64xx.h | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/spi-s3c64xx.h b/include/linux/platform_data/spi-s3c64xx.h
index 8447f634c7f5..d3889b98a1a1 100644
--- a/include/linux/platform_data/spi-s3c64xx.h
+++ b/include/linux/platform_data/spi-s3c64xx.h
@@ -1,5 +1,4 @@
-/* linux/arch/arm/plat-samsung/include/plat/s3c64xx-spi.h
- *
+/*
  * Copyright (C) 2009 Samsung Electronics Ltd.
  *	Jaswinder Singh <jassi.brar@samsung.com>
  *
@@ -8,8 +7,8 @@
  * published by the Free Software Foundation.
  */
 
-#ifndef __S3C64XX_PLAT_SPI_H
-#define __S3C64XX_PLAT_SPI_H
+#ifndef __SPI_S3C64XX_H
+#define __SPI_S3C64XX_H
 
 #include <linux/dmaengine.h>
 
@@ -68,4 +67,4 @@ extern int s3c64xx_spi2_cfg_gpio(void);
 extern struct s3c64xx_spi_info s3c64xx_spi0_pdata;
 extern struct s3c64xx_spi_info s3c64xx_spi1_pdata;
 extern struct s3c64xx_spi_info s3c64xx_spi2_pdata;
-#endif /* __S3C64XX_PLAT_SPI_H */
+#endif /*__SPI_S3C64XX_H */
-- 
cgit v1.2.3


From dd5720b3006210ecdf4e3c8889e6051f432c4ba3 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 12 Feb 2014 11:16:17 +0200
Subject: dma: dw: remove leftovers in the comment blocks

There is couple of leftovers in the comment blocks. This patch modifies the
comments accordingly.

There is no functional change.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 drivers/dma/dw/core.c   | 4 ++--
 include/linux/dw_dmac.h | 5 +----
 2 files changed, 3 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 13ac3f240e79..1b4509712847 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -33,8 +33,8 @@
  * of which use ARM any more).  See the "Databook" from Synopsys for
  * information beyond what licensees probably provide.
  *
- * The driver has currently been tested only with the Atmel AT32AP7000,
- * which does not support descriptor writeback.
+ * The driver has been tested with the Atmel AT32AP7000, which does not
+ * support descriptor writeback.
  */
 
 static inline bool is_request_line_unset(struct dw_dma_chan *dwc)
diff --git a/include/linux/dw_dmac.h b/include/linux/dw_dmac.h
index 481ab2345d6b..68b4024184de 100644
--- a/include/linux/dw_dmac.h
+++ b/include/linux/dw_dmac.h
@@ -1,6 +1,5 @@
 /*
- * Driver for the Synopsys DesignWare DMA Controller (aka DMACA on
- * AVR32 systems.)
+ * Driver for the Synopsys DesignWare DMA Controller
  *
  * Copyright (C) 2007 Atmel Corporation
  * Copyright (C) 2010-2011 ST Microelectronics
@@ -44,8 +43,6 @@ struct dw_dma_slave {
  * @nr_masters: Number of AHB masters supported by the controller
  * @data_width: Maximum data width supported by hardware per AHB master
  *		(0 - 8bits, 1 - 16bits, ..., 5 - 256bits)
- * @sd: slave specific data. Used for configuring channels
- * @sd_count: count of slave data structures passed.
  */
 struct dw_dma_platform_data {
 	unsigned int	nr_channels;
-- 
cgit v1.2.3


From b69d6536794c93dda362ab79c9f559382e3465be Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Date: Wed, 5 Feb 2014 16:33:16 -0500
Subject: HID: add inliners for ll_driver transport-layer callbacks

Those callbacks are not mandatory, so it's better to add inliners
to use them safely.

Reviewed-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 include/linux/hid.h | 45 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/hid.h b/include/linux/hid.h
index 003cc8e89831..dddcad07c2d9 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -680,6 +680,8 @@ struct hid_driver {
  *	   shouldn't allocate anything to not leak memory
  * @request: send report request to device (e.g. feature report)
  * @wait: wait for buffered io to complete (send/recv reports)
+ * @raw_request: send raw report request to device (e.g. feature report)
+ * @output_report: send output report to device
  * @idle: send idle request to device
  */
 struct hid_ll_driver {
@@ -973,6 +975,49 @@ static inline void hid_hw_request(struct hid_device *hdev,
 		hdev->ll_driver->request(hdev, report, reqtype);
 }
 
+/**
+ * hid_hw_raw_request - send report request to device
+ *
+ * @hdev: hid device
+ * @reportnum: report ID
+ * @buf: in/out data to transfer
+ * @len: length of buf
+ * @rtype: HID report type
+ * @reqtype: HID_REQ_GET_REPORT or HID_REQ_SET_REPORT
+ *
+ * @return: count of data transfered, negative if error
+ *
+ * Same behavior as hid_hw_request, but with raw buffers instead.
+ */
+static inline int hid_hw_raw_request(struct hid_device *hdev,
+				  unsigned char reportnum, __u8 *buf,
+				  size_t len, unsigned char rtype, int reqtype)
+{
+	if (hdev->ll_driver->raw_request)
+		return hdev->ll_driver->raw_request(hdev, reportnum, buf, len,
+						    rtype, reqtype);
+
+	return -ENOSYS;
+}
+
+/**
+ * hid_hw_output_report - send output report to device
+ *
+ * @hdev: hid device
+ * @buf: raw data to transfer
+ * @len: length of buf
+ *
+ * @return: count of data transfered, negative if error
+ */
+static inline int hid_hw_output_report(struct hid_device *hdev, __u8 *buf,
+					size_t len)
+{
+	if (hdev->ll_driver->output_report)
+		return hdev->ll_driver->output_report(hdev, buf, len);
+
+	return -ENOSYS;
+}
+
 /**
  * hid_hw_idle - send idle request to device
  *
-- 
cgit v1.2.3


From b40272e4d0e6d07a0bf9409e5f95d622422cd73d Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Date: Wed, 5 Feb 2014 16:33:19 -0500
Subject: HID: remove hidinput_input_event handler

All the different transport drivers use now the generic event handling
in hid-input. We can remove the handler definitively now.

Reviewed-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-input.c | 4 +---
 include/linux/hid.h     | 4 ----
 2 files changed, 1 insertion(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index d50e7313b171..e5bb3c378292 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -1263,9 +1263,7 @@ static struct hid_input *hidinput_allocate(struct hid_device *hid)
 	}
 
 	input_set_drvdata(input_dev, hid);
-	if (hid->ll_driver->hidinput_input_event)
-		input_dev->event = hid->ll_driver->hidinput_input_event;
-	else if (hid->ll_driver->request || hid->hid_output_raw_report)
+	if (hid->ll_driver->request || hid->hid_output_raw_report)
 		input_dev->event = hidinput_input_event;
 	input_dev->open = hidinput_open;
 	input_dev->close = hidinput_close;
diff --git a/include/linux/hid.h b/include/linux/hid.h
index dddcad07c2d9..38c307b8138a 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -675,7 +675,6 @@ struct hid_driver {
  * @stop: called on remove
  * @open: called by input layer on open
  * @close: called by input layer on close
- * @hidinput_input_event: event input event (e.g. ff or leds)
  * @parse: this method is called only once to parse the device data,
  *	   shouldn't allocate anything to not leak memory
  * @request: send report request to device (e.g. feature report)
@@ -693,9 +692,6 @@ struct hid_ll_driver {
 
 	int (*power)(struct hid_device *hdev, int level);
 
-	int (*hidinput_input_event) (struct input_dev *idev, unsigned int type,
-			unsigned int code, int value);
-
 	int (*parse)(struct hid_device *hdev);
 
 	void (*request)(struct hid_device *hdev,
-- 
cgit v1.2.3


From cafebc058bf86e63fff5354864781d3de11e41d3 Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Date: Wed, 5 Feb 2014 16:33:22 -0500
Subject: HID: remove hid_get_raw_report in struct hid_device

dev->hid_get_raw_report(X) and hid_hw_raw_request(X, HID_REQ_GET_REPORT)
are strictly equivalent. Switch the hid subsystem to the hid_hw notation
and remove the field .hid_get_raw_report in struct hid_device.

Reviewed-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-input.c       | 6 +++---
 drivers/hid/hid-sony.c        | 3 ++-
 drivers/hid/hidraw.c          | 7 ++++---
 drivers/hid/i2c-hid/i2c-hid.c | 1 -
 drivers/hid/uhid.c            | 1 -
 drivers/hid/usbhid/hid-core.c | 1 -
 include/linux/hid.h           | 3 ---
 net/bluetooth/hidp/core.c     | 1 -
 8 files changed, 9 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index e5bb3c378292..5bd17b256856 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -350,9 +350,9 @@ static int hidinput_get_battery_property(struct power_supply *psy,
 			ret = -ENOMEM;
 			break;
 		}
-		ret = dev->hid_get_raw_report(dev, dev->battery_report_id,
-					      buf, 2,
-					      dev->battery_report_type);
+		ret = hid_hw_raw_request(dev, dev->battery_report_id, buf, 2,
+					 dev->battery_report_type,
+					 HID_REQ_GET_REPORT);
 
 		if (ret != 2) {
 			ret = -ENODATA;
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index 12354055d474..3930acbdee98 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -706,7 +706,8 @@ static int sixaxis_set_operational_usb(struct hid_device *hdev)
 	if (!buf)
 		return -ENOMEM;
 
-	ret = hdev->hid_get_raw_report(hdev, 0xf2, buf, 17, HID_FEATURE_REPORT);
+	ret = hid_hw_raw_request(hdev, 0xf2, buf, 17, HID_FEATURE_REPORT,
+				 HID_REQ_GET_REPORT);
 
 	if (ret < 0)
 		hid_err(hdev, "can't set operational mode\n");
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index cb0137b3718d..4b2dc956c702 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -189,7 +189,7 @@ static ssize_t hidraw_get_report(struct file *file, char __user *buffer, size_t
 
 	dev = hidraw_table[minor]->hid;
 
-	if (!dev->hid_get_raw_report) {
+	if (!dev->ll_driver->raw_request) {
 		ret = -ENODEV;
 		goto out;
 	}
@@ -216,14 +216,15 @@ static ssize_t hidraw_get_report(struct file *file, char __user *buffer, size_t
 
 	/*
 	 * Read the first byte from the user. This is the report number,
-	 * which is passed to dev->hid_get_raw_report().
+	 * which is passed to hid_hw_raw_request().
 	 */
 	if (copy_from_user(&report_number, buffer, 1)) {
 		ret = -EFAULT;
 		goto out_free;
 	}
 
-	ret = dev->hid_get_raw_report(dev, report_number, buf, count, report_type);
+	ret = hid_hw_raw_request(dev, report_number, buf, count, report_type,
+				 HID_REQ_GET_REPORT);
 
 	if (ret < 0)
 		goto out_free;
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index e914f2755491..f4ea7343e823 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -1005,7 +1005,6 @@ static int i2c_hid_probe(struct i2c_client *client,
 
 	hid->driver_data = client;
 	hid->ll_driver = &i2c_hid_ll_driver;
-	hid->hid_get_raw_report = i2c_hid_get_raw_report;
 	hid->hid_output_raw_report = i2c_hid_output_raw_report;
 	hid->dev.parent = &client->dev;
 	ACPI_COMPANION_SET(&hid->dev, ACPI_COMPANION(&client->dev));
diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c
index f5a2b1931143..12439e1eeae2 100644
--- a/drivers/hid/uhid.c
+++ b/drivers/hid/uhid.c
@@ -404,7 +404,6 @@ static int uhid_dev_create(struct uhid_device *uhid,
 	hid->uniq[63] = 0;
 
 	hid->ll_driver = &uhid_hid_driver;
-	hid->hid_get_raw_report = uhid_hid_get_raw;
 	hid->hid_output_raw_report = uhid_hid_output_raw;
 	hid->bus = ev->u.create.bus;
 	hid->vendor = ev->u.create.vendor;
diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index 406497b120ea..b9a770f4d7ae 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -1289,7 +1289,6 @@ static int usbhid_probe(struct usb_interface *intf, const struct usb_device_id *
 
 	usb_set_intfdata(intf, hid);
 	hid->ll_driver = &usb_hid_driver;
-	hid->hid_get_raw_report = usbhid_get_raw_report;
 	hid->hid_output_raw_report = usbhid_output_raw_report;
 	hid->ff_init = hid_pidff_init;
 #ifdef CONFIG_USB_HIDDEV
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 38c307b8138a..c56681a66b0b 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -508,9 +508,6 @@ struct hid_device {							/* device report descriptor */
 				  struct hid_usage *, __s32);
 	void (*hiddev_report_event) (struct hid_device *, struct hid_report *);
 
-	/* handler for raw input (Get_Report) data, used by hidraw */
-	int (*hid_get_raw_report) (struct hid_device *, unsigned char, __u8 *, size_t, unsigned char);
-
 	/* handler for raw output data, used by hidraw */
 	int (*hid_output_raw_report) (struct hid_device *, __u8 *, size_t, unsigned char);
 
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 02670b30895a..77c4badb3e9d 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -773,7 +773,6 @@ static int hidp_setup_hid(struct hidp_session *session,
 	hid->dev.parent = &session->conn->hcon->dev;
 	hid->ll_driver = &hidp_hid_driver;
 
-	hid->hid_get_raw_report = hidp_get_raw_report;
 	hid->hid_output_raw_report = hidp_output_raw_report;
 
 	/* True if device is blacklisted in drivers/hid/hid-core.c */
-- 
cgit v1.2.3


From 7e845d46b13e7730a3720e978c28117ce422edf9 Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Date: Wed, 5 Feb 2014 16:33:23 -0500
Subject: HID: introduce helper to access hid_output_raw_report()

Add a helper to access hdev->hid_output_raw_report().

To convert the drivers, use the following snippets:

for i in drivers/hid/*.c
do
  sed -i.bak "s/[^ \t]*->hid_output_raw_report(/hid_output_raw_report(/g" $i
done

Then manually fix for checkpatch.pl

Reviewed-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-input.c        |  2 +-
 drivers/hid/hid-lg.c           |  6 ++++--
 drivers/hid/hid-magicmouse.c   |  2 +-
 drivers/hid/hid-sony.c         |  6 +++---
 drivers/hid/hid-thingm.c       |  4 ++--
 drivers/hid/hid-wacom.c        | 16 +++++++---------
 drivers/hid/hid-wiimote-core.c |  2 +-
 drivers/hid/hidraw.c           |  2 +-
 include/linux/hid.h            | 16 ++++++++++++++++
 9 files changed, 36 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 5bd17b256856..15959fbae268 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -1184,7 +1184,7 @@ static void hidinput_led_worker(struct work_struct *work)
 
 	hid_output_report(report, buf);
 	/* synchronous output report */
-	hid->hid_output_raw_report(hid, buf, len, HID_OUTPUT_REPORT);
+	hid_output_raw_report(hid, buf, len, HID_OUTPUT_REPORT);
 	kfree(buf);
 }
 
diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c
index 9fe9d4ac3114..76ed7e512dcf 100644
--- a/drivers/hid/hid-lg.c
+++ b/drivers/hid/hid-lg.c
@@ -692,7 +692,8 @@ static int lg_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	if (hdev->product == USB_DEVICE_ID_LOGITECH_WII_WHEEL) {
 		unsigned char buf[] = { 0x00, 0xAF,  0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 };
 
-		ret = hdev->hid_output_raw_report(hdev, buf, sizeof(buf), HID_FEATURE_REPORT);
+		ret = hid_output_raw_report(hdev, buf, sizeof(buf),
+					    HID_FEATURE_REPORT);
 
 		if (ret >= 0) {
 			/* insert a little delay of 10 jiffies ~ 40ms */
@@ -704,7 +705,8 @@ static int lg_probe(struct hid_device *hdev, const struct hid_device_id *id)
 			buf[1] = 0xB2;
 			get_random_bytes(&buf[2], 2);
 
-			ret = hdev->hid_output_raw_report(hdev, buf, sizeof(buf), HID_FEATURE_REPORT);
+			ret = hid_output_raw_report(hdev, buf, sizeof(buf),
+						    HID_FEATURE_REPORT);
 		}
 	}
 
diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c
index 3b43d1cfa936..cb5db3afc690 100644
--- a/drivers/hid/hid-magicmouse.c
+++ b/drivers/hid/hid-magicmouse.c
@@ -538,7 +538,7 @@ static int magicmouse_probe(struct hid_device *hdev,
 	 * but there seems to be no other way of switching the mode.
 	 * Thus the super-ugly hacky success check below.
 	 */
-	ret = hdev->hid_output_raw_report(hdev, feature, sizeof(feature),
+	ret = hid_output_raw_report(hdev, feature, sizeof(feature),
 			HID_FEATURE_REPORT);
 	if (ret != -EIO && ret != sizeof(feature)) {
 		hid_err(hdev, "unable to request touch data (%d)\n", ret);
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index 3930acbdee98..075089b37236 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -720,7 +720,8 @@ static int sixaxis_set_operational_usb(struct hid_device *hdev)
 static int sixaxis_set_operational_bt(struct hid_device *hdev)
 {
 	unsigned char buf[] = { 0xf4,  0x42, 0x03, 0x00, 0x00 };
-	return hdev->hid_output_raw_report(hdev, buf, sizeof(buf), HID_FEATURE_REPORT);
+	return hid_output_raw_report(hdev, buf, sizeof(buf),
+				     HID_FEATURE_REPORT);
 }
 
 static void buzz_set_leds(struct hid_device *hdev, const __u8 *leds)
@@ -942,8 +943,7 @@ static void sixaxis_state_worker(struct work_struct *work)
 	buf[10] |= sc->led_state[2] << 3;
 	buf[10] |= sc->led_state[3] << 4;
 
-	sc->hdev->hid_output_raw_report(sc->hdev, buf, sizeof(buf),
-					HID_OUTPUT_REPORT);
+	hid_output_raw_report(sc->hdev, buf, sizeof(buf), HID_OUTPUT_REPORT);
 }
 
 static void dualshock4_state_worker(struct work_struct *work)
diff --git a/drivers/hid/hid-thingm.c b/drivers/hid/hid-thingm.c
index 99342cfa0ea2..7dd3197f3b3e 100644
--- a/drivers/hid/hid-thingm.c
+++ b/drivers/hid/hid-thingm.c
@@ -48,8 +48,8 @@ static int blink1_send_command(struct blink1_data *data,
 			buf[0], buf[1], buf[2], buf[3], buf[4],
 			buf[5], buf[6], buf[7], buf[8]);
 
-	ret = data->hdev->hid_output_raw_report(data->hdev, buf,
-			BLINK1_CMD_SIZE, HID_FEATURE_REPORT);
+	ret = hid_output_raw_report(data->hdev, buf, BLINK1_CMD_SIZE,
+				    HID_FEATURE_REPORT);
 
 	return ret < 0 ? ret : 0;
 }
diff --git a/drivers/hid/hid-wacom.c b/drivers/hid/hid-wacom.c
index 60c75dcbbdb8..c720db912edb 100644
--- a/drivers/hid/hid-wacom.c
+++ b/drivers/hid/hid-wacom.c
@@ -128,8 +128,7 @@ static void wacom_set_image(struct hid_device *hdev, const char *image,
 
 	rep_data[0] = WAC_CMD_ICON_START_STOP;
 	rep_data[1] = 0;
-	ret = hdev->hid_output_raw_report(hdev, rep_data, 2,
-				HID_FEATURE_REPORT);
+	ret = hid_output_raw_report(hdev, rep_data, 2, HID_FEATURE_REPORT);
 	if (ret < 0)
 		goto err;
 
@@ -143,15 +142,14 @@ static void wacom_set_image(struct hid_device *hdev, const char *image,
 			rep_data[j + 3] = p[(i << 6) + j];
 
 		rep_data[2] = i;
-		ret = hdev->hid_output_raw_report(hdev, rep_data, 67,
+		ret = hid_output_raw_report(hdev, rep_data, 67,
 					HID_FEATURE_REPORT);
 	}
 
 	rep_data[0] = WAC_CMD_ICON_START_STOP;
 	rep_data[1] = 0;
 
-	ret = hdev->hid_output_raw_report(hdev, rep_data, 2,
-				HID_FEATURE_REPORT);
+	ret = hid_output_raw_report(hdev, rep_data, 2, HID_FEATURE_REPORT);
 
 err:
 	return;
@@ -183,7 +181,7 @@ static void wacom_leds_set_brightness(struct led_classdev *led_dev,
 		buf[3] = value;
 		/* use fixed brightness for OLEDs */
 		buf[4] = 0x08;
-		hdev->hid_output_raw_report(hdev, buf, 9, HID_FEATURE_REPORT);
+		hid_output_raw_report(hdev, buf, 9, HID_FEATURE_REPORT);
 		kfree(buf);
 	}
 
@@ -339,7 +337,7 @@ static void wacom_set_features(struct hid_device *hdev, u8 speed)
 		rep_data[0] = 0x03 ; rep_data[1] = 0x00;
 		limit = 3;
 		do {
-			ret = hdev->hid_output_raw_report(hdev, rep_data, 2,
+			ret = hid_output_raw_report(hdev, rep_data, 2,
 					HID_FEATURE_REPORT);
 		} while (ret < 0 && limit-- > 0);
 
@@ -352,7 +350,7 @@ static void wacom_set_features(struct hid_device *hdev, u8 speed)
 			rep_data[1] = 0x00;
 			limit = 3;
 			do {
-				ret = hdev->hid_output_raw_report(hdev,
+				ret = hid_output_raw_report(hdev,
 					rep_data, 2, HID_FEATURE_REPORT);
 			} while (ret < 0 && limit-- > 0);
 
@@ -378,7 +376,7 @@ static void wacom_set_features(struct hid_device *hdev, u8 speed)
 		rep_data[0] = 0x03;
 		rep_data[1] = wdata->features;
 
-		ret = hdev->hid_output_raw_report(hdev, rep_data, 2,
+		ret = hid_output_raw_report(hdev, rep_data, 2,
 					HID_FEATURE_REPORT);
 		if (ret >= 0)
 			wdata->high_speed = speed;
diff --git a/drivers/hid/hid-wiimote-core.c b/drivers/hid/hid-wiimote-core.c
index abb20db2b443..d7dc6c5bc244 100644
--- a/drivers/hid/hid-wiimote-core.c
+++ b/drivers/hid/hid-wiimote-core.c
@@ -35,7 +35,7 @@ static int wiimote_hid_send(struct hid_device *hdev, __u8 *buffer,
 	if (!buf)
 		return -ENOMEM;
 
-	ret = hdev->hid_output_raw_report(hdev, buf, count, HID_OUTPUT_REPORT);
+	ret = hid_output_raw_report(hdev, buf, count, HID_OUTPUT_REPORT);
 
 	kfree(buf);
 	return ret;
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index 4b2dc956c702..f8708c93f85c 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -153,7 +153,7 @@ static ssize_t hidraw_send_report(struct file *file, const char __user *buffer,
 		goto out_free;
 	}
 
-	ret = dev->hid_output_raw_report(dev, buf, count, report_type);
+	ret = hid_output_raw_report(dev, buf, count, report_type);
 out_free:
 	kfree(buf);
 out:
diff --git a/include/linux/hid.h b/include/linux/hid.h
index c56681a66b0b..a837ede65ec6 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -1011,6 +1011,22 @@ static inline int hid_hw_output_report(struct hid_device *hdev, __u8 *buf,
 	return -ENOSYS;
 }
 
+/**
+ * hid_output_raw_report - send an output or a feature report to the device
+ *
+ * @hdev: hid device
+ * @buf: raw data to transfer
+ * @len: length of buf
+ * @report_type: HID_FEATURE_REPORT or HID_OUTPUT_REPORT
+ *
+ * @return: count of data transfered, negative if error
+ */
+static inline int hid_output_raw_report(struct hid_device *hdev, __u8 *buf,
+					size_t len, unsigned char report_type)
+{
+	return hdev->hid_output_raw_report(hdev, buf, len, report_type);
+}
+
 /**
  * hid_hw_idle - send idle request to device
  *
-- 
cgit v1.2.3


From 4fa5a7f76cc7b6ac87f57741edd2b124851d119f Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Date: Mon, 10 Feb 2014 12:58:48 -0500
Subject: HID: core: implement generic .request()

.request() can be emulated through .raw_request()
we can implement this emulation in hid-core, and make .request
not mandatory for transport layer drivers.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Reviewed-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-core.c | 45 ++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/hid.h    |  5 ++++-
 2 files changed, 48 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 026ab0fc06f7..b6ae69711d2a 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1248,6 +1248,11 @@ void hid_output_report(struct hid_report *report, __u8 *data)
 }
 EXPORT_SYMBOL_GPL(hid_output_report);
 
+static int hid_report_len(struct hid_report *report)
+{
+	return ((report->size - 1) >> 3) + 1 + (report->id > 0) + 7;
+}
+
 /*
  * Allocator for buffer that is going to be passed to hid_output_report()
  */
@@ -1258,7 +1263,7 @@ u8 *hid_alloc_report_buf(struct hid_report *report, gfp_t flags)
 	 * of implement() working on 8 byte chunks
 	 */
 
-	int len = ((report->size - 1) >> 3) + 1 + (report->id > 0) + 7;
+	int len = hid_report_len(report);
 
 	return kmalloc(len, flags);
 }
@@ -1314,6 +1319,44 @@ static struct hid_report *hid_get_report(struct hid_report_enum *report_enum,
 	return report;
 }
 
+/*
+ * Implement a generic .request() callback, using .raw_request()
+ * DO NOT USE in hid drivers directly, but through hid_hw_request instead.
+ */
+void __hid_request(struct hid_device *hid, struct hid_report *report,
+		int reqtype)
+{
+	char *buf;
+	int ret;
+	int len;
+
+	if (!hid->ll_driver->raw_request)
+		return;
+
+	buf = hid_alloc_report_buf(report, GFP_KERNEL);
+	if (!buf)
+		return;
+
+	len = hid_report_len(report);
+
+	if (reqtype == HID_REQ_SET_REPORT)
+		hid_output_report(report, buf);
+
+	ret = hid->ll_driver->raw_request(hid, report->id, buf, len,
+					  report->type, reqtype);
+	if (ret < 0) {
+		dbg_hid("unable to complete request: %d\n", ret);
+		goto out;
+	}
+
+	if (reqtype == HID_REQ_GET_REPORT)
+		hid_input_report(hid, report->type, buf, ret, 0);
+
+out:
+	kfree(buf);
+}
+EXPORT_SYMBOL_GPL(__hid_request);
+
 int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, int size,
 		int interrupt)
 {
diff --git a/include/linux/hid.h b/include/linux/hid.h
index a837ede65ec6..09fbbd7fb784 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -753,6 +753,7 @@ struct hid_field *hidinput_get_led_field(struct hid_device *hid);
 unsigned int hidinput_count_leds(struct hid_device *hid);
 __s32 hidinput_calc_abs_res(const struct hid_field *field, __u16 code);
 void hid_output_report(struct hid_report *report, __u8 *data);
+void __hid_request(struct hid_device *hid, struct hid_report *rep, int reqtype);
 u8 *hid_alloc_report_buf(struct hid_report *report, gfp_t flags);
 struct hid_device *hid_allocate_device(void);
 struct hid_report *hid_register_report(struct hid_device *device, unsigned type, unsigned id);
@@ -965,7 +966,9 @@ static inline void hid_hw_request(struct hid_device *hdev,
 				  struct hid_report *report, int reqtype)
 {
 	if (hdev->ll_driver->request)
-		hdev->ll_driver->request(hdev, report, reqtype);
+		return hdev->ll_driver->request(hdev, report, reqtype);
+
+	__hid_request(hdev, report, reqtype);
 }
 
 /**
-- 
cgit v1.2.3


From 5318251744b2c8a288f91f4e53ed69f2a01d6412 Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Date: Mon, 10 Feb 2014 12:58:59 -0500
Subject: HID: core: check parameters when sending/receiving data from the
 device

It is better to check them soon enough before triggering any kernel panic.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Reviewed-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/i2c-hid/i2c-hid.c | 2 +-
 include/linux/hid.h           | 6 ++++++
 2 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index 5308656eec2e..1a955317d05f 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -276,7 +276,7 @@ static int i2c_hid_set_or_send_report(struct i2c_client *client, u8 reportType,
 	u16 outputRegister = le16_to_cpu(ihid->hdesc.wOutputRegister);
 	u16 maxOutputLength = le16_to_cpu(ihid->hdesc.wMaxOutputLength);
 
-	/* hidraw already checked that data_len < HID_MAX_BUFFER_SIZE */
+	/* hid_hw_* already checked that data_len < HID_MAX_BUFFER_SIZE */
 	u16 size =	2			/* size */ +
 			(reportID ? 1 : 0)	/* reportID */ +
 			data_len		/* buf */;
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 09fbbd7fb784..60f3ff762376 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -989,6 +989,9 @@ static inline int hid_hw_raw_request(struct hid_device *hdev,
 				  unsigned char reportnum, __u8 *buf,
 				  size_t len, unsigned char rtype, int reqtype)
 {
+	if (len < 1 || len > HID_MAX_BUFFER_SIZE || !buf)
+		return -EINVAL;
+
 	if (hdev->ll_driver->raw_request)
 		return hdev->ll_driver->raw_request(hdev, reportnum, buf, len,
 						    rtype, reqtype);
@@ -1008,6 +1011,9 @@ static inline int hid_hw_raw_request(struct hid_device *hdev,
 static inline int hid_hw_output_report(struct hid_device *hdev, __u8 *buf,
 					size_t len)
 {
+	if (len < 1 || len > HID_MAX_BUFFER_SIZE || !buf)
+		return -EINVAL;
+
 	if (hdev->ll_driver->output_report)
 		return hdev->ll_driver->output_report(hdev, buf, len);
 
-- 
cgit v1.2.3


From e02cee4819ae51f26333471c8eed50678b08572a Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Thu, 23 Jan 2014 18:50:21 -0800
Subject: HID: hid-sensor-hub: Add selector api

In some report descriptors, they leave holes in the selectors. In
this case if we use hardcoded selector values, this will result
in invalid values. For example, if there is selectors defined for
Power State from OFF to D0 to D3. We can't use indexes of these states
if some states are not implemented or not present in the report decriptors.
In this case, we need to get the indexes from report descriptors.

One API is added to get the index of a selector. This API will
search for usage id in the field usage list and return the index.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-sensor-hub.c   | 22 ++++++++++++++++++++++
 include/linux/hid-sensor-hub.h |  3 +++
 2 files changed, 25 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c
index 46f4480035bc..ad2b8692ad77 100644
--- a/drivers/hid/hid-sensor-hub.c
+++ b/drivers/hid/hid-sensor-hub.c
@@ -291,6 +291,28 @@ err_free:
 }
 EXPORT_SYMBOL_GPL(sensor_hub_input_attr_get_raw_value);
 
+int hid_sensor_get_usage_index(struct hid_sensor_hub_device *hsdev,
+				u32 report_id, int field_index, u32 usage_id)
+{
+	struct hid_report *report;
+	struct hid_field *field;
+	int i;
+
+	report = sensor_hub_report(report_id, hsdev->hdev, HID_FEATURE_REPORT);
+	if (!report || (field_index >= report->maxfield))
+		goto done_proc;
+
+	field = report->field[field_index];
+	for (i = 0; i < field->maxusage; ++i) {
+		if (field->usage[i].hid == usage_id)
+			return field->usage[i].usage_index;
+	}
+
+done_proc:
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(hid_sensor_get_usage_index);
+
 int sensor_hub_input_get_attribute_info(struct hid_sensor_hub_device *hsdev,
 				u8 type,
 				u32 usage_id,
diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h
index b914ca3f57ba..205eba0326af 100644
--- a/include/linux/hid-sensor-hub.h
+++ b/include/linux/hid-sensor-hub.h
@@ -218,4 +218,7 @@ int hid_sensor_write_samp_freq_value(struct hid_sensor_common *st,
 int hid_sensor_read_samp_freq_value(struct hid_sensor_common *st,
 					int *val1, int *val2);
 
+int hid_sensor_get_usage_index(struct hid_sensor_hub_device *hsdev,
+				u32 report_id, int field_index, u32 usage_id);
+
 #endif
-- 
cgit v1.2.3


From 1a214ae5d1a66ead18c5e8c3a8d03b969b0ee647 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Thu, 23 Jan 2014 18:50:22 -0800
Subject: iio: hid-sensor-hub: Remove hard coded indexes

Remove the hard coded indexes, instead search for usage id and
use the index to set the power and report state.
This will fix issue, where the report descriptor doesn't contain
the full list of possible selector for power and report state.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Acked-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 .../iio/common/hid-sensors/hid-sensor-trigger.c    | 39 ++++++++++++++--------
 include/linux/hid-sensor-ids.h                     | 16 ++++-----
 2 files changed, 33 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
index 7dcf83998e6f..dbefbdaf7cd1 100644
--- a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
+++ b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
@@ -38,29 +38,40 @@ static int hid_sensor_data_rdy_trigger_set_state(struct iio_trigger *trig,
 	if (state) {
 		if (sensor_hub_device_open(st->hsdev))
 			return -EIO;
-		state_val =
-		HID_USAGE_SENSOR_PROP_POWER_STATE_D0_FULL_POWER_ENUM;
-		report_val =
-		HID_USAGE_SENSOR_PROP_REPORTING_STATE_ALL_EVENTS_ENUM;
-
+		state_val = hid_sensor_get_usage_index(st->hsdev,
+			st->power_state.report_id,
+			st->power_state.index,
+			HID_USAGE_SENSOR_PROP_POWER_STATE_D0_FULL_POWER_ENUM);
+		report_val = hid_sensor_get_usage_index(st->hsdev,
+			st->report_state.report_id,
+			st->report_state.index,
+			HID_USAGE_SENSOR_PROP_REPORTING_STATE_ALL_EVENTS_ENUM);
 	} else {
 		sensor_hub_device_close(st->hsdev);
-		state_val =
-		HID_USAGE_SENSOR_PROP_POWER_STATE_D4_POWER_OFF_ENUM;
-		report_val =
-		HID_USAGE_SENSOR_PROP_REPORTING_STATE_NO_EVENTS_ENUM;
+		state_val = hid_sensor_get_usage_index(st->hsdev,
+			st->power_state.report_id,
+			st->power_state.index,
+			HID_USAGE_SENSOR_PROP_POWER_STATE_D4_POWER_OFF_ENUM);
+		report_val = hid_sensor_get_usage_index(st->hsdev,
+			st->report_state.report_id,
+			st->report_state.index,
+			HID_USAGE_SENSOR_PROP_REPORTING_STATE_NO_EVENTS_ENUM);
 	}
-
 	st->data_ready = state;
-	state_val += st->power_state.logical_minimum;
-	report_val += st->report_state.logical_minimum;
-	sensor_hub_set_feature(st->hsdev, st->power_state.report_id,
+
+	if (state_val >= 0) {
+		state_val += st->power_state.logical_minimum;
+		sensor_hub_set_feature(st->hsdev, st->power_state.report_id,
 					st->power_state.index,
 					(s32)state_val);
+	}
 
-	sensor_hub_set_feature(st->hsdev, st->report_state.report_id,
+	if (report_val >= 0) {
+		report_val += st->report_state.logical_minimum;
+		sensor_hub_set_feature(st->hsdev, st->report_state.report_id,
 					st->report_state.index,
 					(s32)report_val);
+	}
 
 	return 0;
 }
diff --git a/include/linux/hid-sensor-ids.h b/include/linux/hid-sensor-ids.h
index beaf965621c1..f8607605a31c 100644
--- a/include/linux/hid-sensor-ids.h
+++ b/include/linux/hid-sensor-ids.h
@@ -130,15 +130,15 @@
 #define HID_USAGE_SENSOR_DATA_MOD_CHANGE_SENSITIVITY_ABS		0x1000
 
 /* Power state enumerations */
-#define HID_USAGE_SENSOR_PROP_POWER_STATE_UNDEFINED_ENUM		0x00
-#define HID_USAGE_SENSOR_PROP_POWER_STATE_D0_FULL_POWER_ENUM		0x01
-#define HID_USAGE_SENSOR_PROP_POWER_STATE_D1_LOW_POWER_ENUM		0x02
-#define HID_USAGE_SENSOR_PROP_POWER_STATE_D2_STANDBY_WITH_WAKE_ENUM	0x03
-#define HID_USAGE_SENSOR_PROP_POWER_STATE_D3_SLEEP_WITH_WAKE_ENUM	0x04
-#define HID_USAGE_SENSOR_PROP_POWER_STATE_D4_POWER_OFF_ENUM		0x05
+#define HID_USAGE_SENSOR_PROP_POWER_STATE_UNDEFINED_ENUM	0x200850
+#define HID_USAGE_SENSOR_PROP_POWER_STATE_D0_FULL_POWER_ENUM	0x200851
+#define HID_USAGE_SENSOR_PROP_POWER_STATE_D1_LOW_POWER_ENUM	0x200852
+#define HID_USAGE_SENSOR_PROP_POWER_STATE_D2_STANDBY_WITH_WAKE_ENUM 0x200853
+#define HID_USAGE_SENSOR_PROP_POWER_STATE_D3_SLEEP_WITH_WAKE_ENUM 0x200854
+#define HID_USAGE_SENSOR_PROP_POWER_STATE_D4_POWER_OFF_ENUM	0x200855
 
 /* Report State enumerations */
-#define HID_USAGE_SENSOR_PROP_REPORTING_STATE_NO_EVENTS_ENUM		0x00
-#define HID_USAGE_SENSOR_PROP_REPORTING_STATE_ALL_EVENTS_ENUM		0x01
+#define HID_USAGE_SENSOR_PROP_REPORTING_STATE_NO_EVENTS_ENUM	0x200840
+#define HID_USAGE_SENSOR_PROP_REPORTING_STATE_ALL_EVENTS_ENUM	0x200841
 
 #endif
-- 
cgit v1.2.3


From 05f7a7d6a7d23a877063857cf2df1dffec5a96dc Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruen@linbit.com>
Date: Mon, 8 Aug 2011 23:36:56 +0200
Subject: idr: Add new function idr_is_empty()

Signed-off-by: Andreas Gruenbacher <agruen@linbit.com>
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
---
 include/linux/idr.h |  1 +
 lib/idr.c           | 10 ++++++++++
 2 files changed, 11 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/idr.h b/include/linux/idr.h
index 871a213a8477..9c95d210458b 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -85,6 +85,7 @@ void idr_remove(struct idr *idp, int id);
 void idr_free(struct idr *idp, int id);
 void idr_destroy(struct idr *idp);
 void idr_init(struct idr *idp);
+bool idr_is_empty(struct idr *idp);
 
 /**
  * idr_preload_end - end preload section started with idr_preload()
diff --git a/lib/idr.c b/lib/idr.c
index bfe4db4e165f..1ba4956bfbff 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -869,6 +869,16 @@ void idr_init(struct idr *idp)
 }
 EXPORT_SYMBOL(idr_init);
 
+static int idr_has_entry(int id, void *p, void *data)
+{
+	return 1;
+}
+
+bool idr_is_empty(struct idr *idp)
+{
+	return !idr_for_each(idp, idr_has_entry, NULL);
+}
+EXPORT_SYMBOL(idr_is_empty);
 
 /**
  * DOC: IDA description
-- 
cgit v1.2.3


From 05a10ec7900dbdba008a24bf56b3490c4b568d2c Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruen@linbit.com>
Date: Tue, 7 Jun 2011 22:54:17 +0200
Subject: drbd: Improve some function and variable naming

Rename functions
conn_destroy() -> drbd_destroy_connection(),
drbd_minor_destroy() -> drbd_destroy_device()
drbd_adm_add_minor() -> drbd_adm_add_minor()
drbd_adm_delete_minor() -> drbd_adm_del_minor()

Rename global variable minors to drbd_devices

Signed-off-by: Andreas Gruenbacher <agruen@linbit.com>
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
---
 drivers/block/drbd/drbd_int.h      |  8 ++++----
 drivers/block/drbd/drbd_main.c     | 32 ++++++++++++++++----------------
 drivers/block/drbd/drbd_nl.c       | 32 ++++++++++++++++----------------
 drivers/block/drbd/drbd_proc.c     |  2 +-
 drivers/block/drbd/drbd_receiver.c | 12 ++++++------
 drivers/block/drbd/drbd_state.c    |  2 +-
 drivers/block/drbd/drbd_worker.c   |  6 +++---
 include/linux/drbd_genl.h          |  4 ++--
 8 files changed, 49 insertions(+), 49 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 85e2f4b56a06..b324314768fd 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -166,7 +166,7 @@ drbd_insert_fault(struct drbd_device *device, unsigned int type) {
 #define div_floor(A, B) ((A)/(B))
 
 extern struct ratelimit_state drbd_ratelimit_state;
-extern struct idr minors; /* RCU, updates: genl_lock() */
+extern struct idr drbd_devices; /* RCU, updates: genl_lock() */
 extern struct list_head drbd_connections; /* RCU, updates: genl_lock() */
 
 extern const char *cmdname(enum drbd_packet cmd);
@@ -771,7 +771,7 @@ struct drbd_device {
 
 static inline struct drbd_device *minor_to_device(unsigned int minor)
 {
-	return (struct drbd_device *)idr_find(&minors, minor);
+	return (struct drbd_device *)idr_find(&drbd_devices, minor);
 }
 
 static inline struct drbd_peer_device *first_peer_device(struct drbd_device *device)
@@ -1175,11 +1175,11 @@ extern rwlock_t global_state_lock;
 
 extern int conn_lowest_minor(struct drbd_connection *connection);
 enum drbd_ret_code drbd_create_minor(struct drbd_connection *connection, unsigned int minor, int vnr);
-extern void drbd_minor_destroy(struct kref *kref);
+extern void drbd_destroy_device(struct kref *kref);
 
 extern int set_resource_options(struct drbd_connection *connection, struct res_opts *res_opts);
 extern struct drbd_connection *conn_create(const char *name, struct res_opts *res_opts);
-extern void conn_destroy(struct kref *kref);
+extern void drbd_destroy_connection(struct kref *kref);
 struct drbd_connection *conn_get_by_name(const char *name);
 extern struct drbd_connection *conn_get_by_addrs(void *my_addr, int my_addr_len,
 					    void *peer_addr, int peer_addr_len);
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index b7c858f51fa6..4da017d22f4b 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -117,7 +117,7 @@ module_param_string(usermode_helper, usermode_helper, sizeof(usermode_helper), 0
 /* in 2.6.x, our device mapping and config info contains our virtual gendisks
  * as member "struct gendisk *vdisk;"
  */
-struct idr minors;
+struct idr drbd_devices;
 struct list_head drbd_connections;  /* list of struct drbd_connection */
 
 struct kmem_cache *drbd_request_cache;
@@ -364,7 +364,7 @@ restart:
 
 	/* Release mod reference taken when thread was started */
 
-	kref_put(&connection->kref, &conn_destroy);
+	kref_put(&connection->kref, drbd_destroy_connection);
 	module_put(THIS_MODULE);
 	return retval;
 }
@@ -416,7 +416,7 @@ int drbd_thread_start(struct drbd_thread *thi)
 		if (IS_ERR(nt)) {
 			conn_err(connection, "Couldn't start thread\n");
 
-			kref_put(&connection->kref, &conn_destroy);
+			kref_put(&connection->kref, drbd_destroy_connection);
 			module_put(THIS_MODULE);
 			return false;
 		}
@@ -2158,7 +2158,7 @@ static void drbd_release_all_peer_reqs(struct drbd_device *device)
 }
 
 /* caution. no locking. */
-void drbd_minor_destroy(struct kref *kref)
+void drbd_destroy_device(struct kref *kref)
 {
 	struct drbd_device *device = container_of(kref, struct drbd_device, kref);
 	struct drbd_connection *connection = first_peer_device(device)->connection;
@@ -2195,7 +2195,7 @@ void drbd_minor_destroy(struct kref *kref)
 	kfree(first_peer_device(device));
 	kfree(device);
 
-	kref_put(&connection->kref, &conn_destroy);
+	kref_put(&connection->kref, drbd_destroy_connection);
 }
 
 /* One global retry thread, if we need to push back some bio and have it
@@ -2301,26 +2301,26 @@ static void drbd_cleanup(void)
 
 	drbd_genl_unregister();
 
-	idr_for_each_entry(&minors, device, i) {
-		idr_remove(&minors, device_to_minor(device));
+	idr_for_each_entry(&drbd_devices, device, i) {
+		idr_remove(&drbd_devices, device_to_minor(device));
 		idr_remove(&first_peer_device(device)->connection->volumes, device->vnr);
 		destroy_workqueue(device->submit.wq);
 		del_gendisk(device->vdisk);
 		/* synchronize_rcu(); No other threads running at this point */
-		kref_put(&device->kref, &drbd_minor_destroy);
+		kref_put(&device->kref, drbd_destroy_device);
 	}
 
 	/* not _rcu since, no other updater anymore. Genl already unregistered */
 	list_for_each_entry_safe(connection, tmp, &drbd_connections, connections) {
 		list_del(&connection->connections); /* not _rcu no proc, not other threads */
 		/* synchronize_rcu(); */
-		kref_put(&connection->kref, &conn_destroy);
+		kref_put(&connection->kref, drbd_destroy_connection);
 	}
 
 	drbd_destroy_mempools();
 	unregister_blkdev(DRBD_MAJOR, "drbd");
 
-	idr_destroy(&minors);
+	idr_destroy(&drbd_devices);
 
 	printk(KERN_INFO "drbd: module cleanup done.\n");
 }
@@ -2576,7 +2576,7 @@ fail:
 	return NULL;
 }
 
-void conn_destroy(struct kref *kref)
+void drbd_destroy_connection(struct kref *kref)
 {
 	struct drbd_connection *connection = container_of(kref, struct drbd_connection, kref);
 
@@ -2688,7 +2688,7 @@ enum drbd_ret_code drbd_create_minor(struct drbd_connection *connection, unsigne
 	device->read_requests = RB_ROOT;
 	device->write_requests = RB_ROOT;
 
-	minor_got = idr_alloc(&minors, device, minor, minor + 1, GFP_KERNEL);
+	minor_got = idr_alloc(&drbd_devices, device, minor, minor + 1, GFP_KERNEL);
 	if (minor_got < 0) {
 		if (minor_got == -ENOSPC) {
 			err = ERR_MINOR_EXISTS;
@@ -2725,7 +2725,7 @@ enum drbd_ret_code drbd_create_minor(struct drbd_connection *connection, unsigne
 out_idr_remove_vol:
 	idr_remove(&connection->volumes, vnr_got);
 out_idr_remove_minor:
-	idr_remove(&minors, minor_got);
+	idr_remove(&drbd_devices, minor_got);
 	synchronize_rcu();
 out_no_minor_idr:
 	drbd_bm_cleanup(device);
@@ -2736,7 +2736,7 @@ out_no_io_page:
 out_no_disk:
 	blk_cleanup_queue(q);
 out_no_q:
-	kref_put(&connection->kref, &conn_destroy);
+	kref_put(&connection->kref, drbd_destroy_connection);
 out_no_peer_device:
 	kfree(device);
 	return err;
@@ -2772,7 +2772,7 @@ int __init drbd_init(void)
 	init_waitqueue_head(&drbd_pp_wait);
 
 	drbd_proc = NULL; /* play safe for drbd_cleanup */
-	idr_init(&minors);
+	idr_init(&drbd_devices);
 
 	rwlock_init(&global_state_lock);
 	INIT_LIST_HEAD(&drbd_connections);
@@ -2863,7 +2863,7 @@ void conn_md_sync(struct drbd_connection *connection)
 		kref_get(&device->kref);
 		rcu_read_unlock();
 		drbd_md_sync(device);
-		kref_put(&device->kref, &drbd_minor_destroy);
+		kref_put(&device->kref, drbd_destroy_device);
 		rcu_read_lock();
 	}
 	rcu_read_unlock();
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index a8c9c86e29f5..83d8c18fb84c 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -45,8 +45,8 @@
 // int drbd_adm_create_resource(struct sk_buff *skb, struct genl_info *info);
 // int drbd_adm_delete_resource(struct sk_buff *skb, struct genl_info *info);
 
-int drbd_adm_add_minor(struct sk_buff *skb, struct genl_info *info);
-int drbd_adm_delete_minor(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_new_minor(struct sk_buff *skb, struct genl_info *info);
+int drbd_adm_del_minor(struct sk_buff *skb, struct genl_info *info);
 
 int drbd_adm_new_resource(struct sk_buff *skb, struct genl_info *info);
 int drbd_adm_del_resource(struct sk_buff *skb, struct genl_info *info);
@@ -274,7 +274,7 @@ fail:
 static int drbd_adm_finish(struct genl_info *info, int retcode)
 {
 	if (adm_ctx.connection) {
-		kref_put(&adm_ctx.connection->kref, &conn_destroy);
+		kref_put(&adm_ctx.connection->kref, drbd_destroy_connection);
 		adm_ctx.connection = NULL;
 	}
 
@@ -517,7 +517,7 @@ static int _try_outdate_peer_async(void *data)
 
 	conn_try_outdate_peer(connection);
 
-	kref_put(&connection->kref, &conn_destroy);
+	kref_put(&connection->kref, drbd_destroy_connection);
 	return 0;
 }
 
@@ -529,7 +529,7 @@ void conn_try_outdate_peer_async(struct drbd_connection *connection)
 	opa = kthread_run(_try_outdate_peer_async, connection, "drbd_async_h");
 	if (IS_ERR(opa)) {
 		conn_err(connection, "out of mem, failed to invoke fence-peer helper\n");
-		kref_put(&connection->kref, &conn_destroy);
+		kref_put(&connection->kref, drbd_destroy_connection);
 	}
 }
 
@@ -2924,7 +2924,7 @@ static int get_one_status(struct sk_buff *skb, struct netlink_callback *cb)
 	 * on each iteration.
 	 */
 
-	/* synchronize with conn_create()/conn_destroy() */
+	/* synchronize with conn_create()/drbd_destroy_connection() */
 	rcu_read_lock();
 	/* revalidate iterator position */
 	list_for_each_entry_rcu(tmp, &drbd_connections, connections) {
@@ -3056,7 +3056,7 @@ int drbd_adm_get_status_all(struct sk_buff *skb, struct netlink_callback *cb)
 	if (!connection)
 		return -ENODEV;
 
-	kref_put(&connection->kref, &conn_destroy); /* get_one_status() (re)validates connection by itself */
+	kref_put(&connection->kref, drbd_destroy_connection); /* get_one_status() (re)validates connection by itself */
 
 	/* prime iterators, and set "filter" mode mark:
 	 * only dump this connection. */
@@ -3266,7 +3266,7 @@ out:
 	return 0;
 }
 
-int drbd_adm_add_minor(struct sk_buff *skb, struct genl_info *info)
+int drbd_adm_new_minor(struct sk_buff *skb, struct genl_info *info)
 {
 	struct drbd_genlmsghdr *dh = info->userhdr;
 	enum drbd_ret_code retcode;
@@ -3303,7 +3303,7 @@ out:
 	return 0;
 }
 
-static enum drbd_ret_code adm_delete_minor(struct drbd_device *device)
+static enum drbd_ret_code adm_del_minor(struct drbd_device *device)
 {
 	if (device->state.disk == D_DISKLESS &&
 	    /* no need to be device->state.conn == C_STANDALONE &&
@@ -3313,17 +3313,17 @@ static enum drbd_ret_code adm_delete_minor(struct drbd_device *device)
 		_drbd_request_state(device, NS(conn, C_WF_REPORT_PARAMS),
 				    CS_VERBOSE + CS_WAIT_COMPLETE);
 		idr_remove(&first_peer_device(device)->connection->volumes, device->vnr);
-		idr_remove(&minors, device_to_minor(device));
+		idr_remove(&drbd_devices, device_to_minor(device));
 		destroy_workqueue(device->submit.wq);
 		del_gendisk(device->vdisk);
 		synchronize_rcu();
-		kref_put(&device->kref, &drbd_minor_destroy);
+		kref_put(&device->kref, drbd_destroy_device);
 		return NO_ERROR;
 	} else
 		return ERR_MINOR_CONFIGURED;
 }
 
-int drbd_adm_delete_minor(struct sk_buff *skb, struct genl_info *info)
+int drbd_adm_del_minor(struct sk_buff *skb, struct genl_info *info)
 {
 	enum drbd_ret_code retcode;
 
@@ -3333,7 +3333,7 @@ int drbd_adm_delete_minor(struct sk_buff *skb, struct genl_info *info)
 	if (retcode != NO_ERROR)
 		goto out;
 
-	retcode = adm_delete_minor(adm_ctx.device);
+	retcode = adm_del_minor(adm_ctx.device);
 out:
 	drbd_adm_finish(info, retcode);
 	return 0;
@@ -3389,7 +3389,7 @@ int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 
 	/* delete volumes */
 	idr_for_each_entry(&adm_ctx.connection->volumes, device, i) {
-		retcode = adm_delete_minor(device);
+		retcode = adm_del_minor(device);
 		if (retcode != NO_ERROR) {
 			/* "can not happen" */
 			drbd_msg_put_info("failed to delete volume");
@@ -3401,7 +3401,7 @@ int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 	if (conn_lowest_minor(adm_ctx.connection) < 0) {
 		list_del_rcu(&adm_ctx.connection->connections);
 		synchronize_rcu();
-		kref_put(&adm_ctx.connection->kref, &conn_destroy);
+		kref_put(&adm_ctx.connection->kref, drbd_destroy_connection);
 
 		retcode = NO_ERROR;
 	} else {
@@ -3428,7 +3428,7 @@ int drbd_adm_del_resource(struct sk_buff *skb, struct genl_info *info)
 	if (conn_lowest_minor(adm_ctx.connection) < 0) {
 		list_del_rcu(&adm_ctx.connection->connections);
 		synchronize_rcu();
-		kref_put(&adm_ctx.connection->kref, &conn_destroy);
+		kref_put(&adm_ctx.connection->kref, drbd_destroy_connection);
 
 		retcode = NO_ERROR;
 	} else {
diff --git a/drivers/block/drbd/drbd_proc.c b/drivers/block/drbd/drbd_proc.c
index f1c81c101fad..2f26e8ffa45b 100644
--- a/drivers/block/drbd/drbd_proc.c
+++ b/drivers/block/drbd/drbd_proc.c
@@ -236,7 +236,7 @@ static int drbd_seq_show(struct seq_file *seq, void *v)
 	*/
 
 	rcu_read_lock();
-	idr_for_each_entry(&minors, device, i) {
+	idr_for_each_entry(&drbd_devices, device, i) {
 		if (prev_i != i - 1)
 			seq_printf(seq, "\n");
 		prev_i = i;
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index e08e99f756a5..791005e163db 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1058,7 +1058,7 @@ randomize:
 			clear_bit(DISCARD_MY_DATA, &device->flags);
 
 		drbd_connected(device);
-		kref_put(&device->kref, &drbd_minor_destroy);
+		kref_put(&device->kref, drbd_destroy_device);
 		rcu_read_lock();
 	}
 	rcu_read_unlock();
@@ -1166,7 +1166,7 @@ static void drbd_flush(struct drbd_connection *connection)
 				drbd_bump_write_ordering(connection, WO_drain_io);
 			}
 			put_ldev(device);
-			kref_put(&device->kref, &drbd_minor_destroy);
+			kref_put(&device->kref, drbd_destroy_device);
 
 			rcu_read_lock();
 			if (rv)
@@ -1409,7 +1409,7 @@ static void conn_wait_active_ee_empty(struct drbd_connection *connection)
 		kref_get(&device->kref);
 		rcu_read_unlock();
 		drbd_wait_ee_list_empty(device, &device->active_ee);
-		kref_put(&device->kref, &drbd_minor_destroy);
+		kref_put(&device->kref, drbd_destroy_device);
 		rcu_read_lock();
 	}
 	rcu_read_unlock();
@@ -4459,7 +4459,7 @@ static void conn_disconnect(struct drbd_connection *connection)
 		kref_get(&device->kref);
 		rcu_read_unlock();
 		drbd_disconnected(device);
-		kref_put(&device->kref, &drbd_minor_destroy);
+		kref_put(&device->kref, &drbd_destroy_device);
 		rcu_read_lock();
 	}
 	rcu_read_unlock();
@@ -5199,10 +5199,10 @@ static int connection_finish_peer_reqs(struct drbd_connection *connection)
 			kref_get(&device->kref);
 			rcu_read_unlock();
 			if (drbd_finish_peer_reqs(device)) {
-				kref_put(&device->kref, &drbd_minor_destroy);
+				kref_put(&device->kref, drbd_destroy_device);
 				return 1;
 			}
-			kref_put(&device->kref, &drbd_minor_destroy);
+			kref_put(&device->kref, drbd_destroy_device);
 			rcu_read_lock();
 		}
 		set_bit(SIGNAL_ASENDER, &connection->flags);
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index 22c4e7d57a80..bb3d5947904d 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -1574,7 +1574,7 @@ static int w_after_conn_state_ch(struct drbd_work *w, int unused)
 			spin_unlock_irq(&connection->req_lock);
 		}
 	}
-	kref_put(&connection->kref, &conn_destroy);
+	kref_put(&connection->kref, drbd_destroy_connection);
 
 	conn_md_sync(connection);
 
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index aa1ad7f39786..378e48c983b3 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -1458,7 +1458,7 @@ static int _drbd_pause_after(struct drbd_device *device)
 	int i, rv = 0;
 
 	rcu_read_lock();
-	idr_for_each_entry(&minors, odev, i) {
+	idr_for_each_entry(&drbd_devices, odev, i) {
 		if (odev->state.conn == C_STANDALONE && odev->state.disk == D_DISKLESS)
 			continue;
 		if (!_drbd_may_sync_now(odev))
@@ -1482,7 +1482,7 @@ static int _drbd_resume_next(struct drbd_device *device)
 	int i, rv = 0;
 
 	rcu_read_lock();
-	idr_for_each_entry(&minors, odev, i) {
+	idr_for_each_entry(&drbd_devices, odev, i) {
 		if (odev->state.conn == C_STANDALONE && odev->state.disk == D_DISKLESS)
 			continue;
 		if (odev->state.aftr_isp) {
@@ -1939,7 +1939,7 @@ int drbd_worker(struct drbd_thread *thi)
 		kref_get(&device->kref);
 		rcu_read_unlock();
 		drbd_device_cleanup(device);
-		kref_put(&device->kref, &drbd_minor_destroy);
+		kref_put(&device->kref, drbd_destroy_device);
 		rcu_read_lock();
 	}
 	rcu_read_unlock();
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index e8c44572b8cb..b14a2e899fea 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -276,9 +276,9 @@ GENL_op(
 )
 
 	/* add DRBD minor devices as volumes to resources */
-GENL_op(DRBD_ADM_NEW_MINOR, 5, GENL_doit(drbd_adm_add_minor),
+GENL_op(DRBD_ADM_NEW_MINOR, 5, GENL_doit(drbd_adm_new_minor),
 	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
-GENL_op(DRBD_ADM_DEL_MINOR, 6, GENL_doit(drbd_adm_delete_minor),
+GENL_op(DRBD_ADM_DEL_MINOR, 6, GENL_doit(drbd_adm_del_minor),
 	GENL_tla_expected(DRBD_NLA_CFG_CONTEXT, DRBD_F_REQUIRED))
 
 	/* add or delete resources */
-- 
cgit v1.2.3


From f44d0436db1ea02f2a08bec40a854550a93e90a8 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruen@linbit.com>
Date: Fri, 22 Jul 2011 13:53:19 +0200
Subject: drbd: Define the size of res_opts->cpu_mask in a single place

Signed-off-by: Andreas Gruenbacher <agruen@linbit.com>
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
---
 drivers/block/drbd/drbd_main.c | 3 +--
 include/linux/drbd.h           | 2 ++
 include/linux/drbd_genl.h      | 2 +-
 3 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index e07446e19c74..59a58e896cf5 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2503,8 +2503,7 @@ int set_resource_options(struct drbd_resource *resource, struct res_opts *res_op
 
 	/* silently ignore cpu mask on UP kernel */
 	if (nr_cpu_ids > 1 && res_opts->cpu_mask[0] != 0) {
-		/* FIXME: Get rid of constant 32 here */
-		err = bitmap_parse(res_opts->cpu_mask, 32,
+		err = bitmap_parse(res_opts->cpu_mask, DRBD_CPU_MASK_SIZE,
 				   cpumask_bits(new_cpu_mask), nr_cpu_ids);
 		if (err) {
 			drbd_warn(resource, "bitmap_parse() failed with %d\n", err);
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index de7d74ab3de6..6f60136da873 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -382,4 +382,6 @@ enum drbd_timeout_flag {
 #define DRBD_MD_INDEX_FLEX_EXT -2
 #define DRBD_MD_INDEX_FLEX_INT -3
 
+#define DRBD_CPU_MASK_SIZE 32
+
 #endif
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index b14a2e899fea..4193f5f2636c 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -135,7 +135,7 @@ GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf,
 )
 
 GENL_struct(DRBD_NLA_RESOURCE_OPTS, 4, res_opts,
-	__str_field_def(1,	DRBD_GENLA_F_MANDATORY,	cpu_mask,       32)
+	__str_field_def(1,	DRBD_GENLA_F_MANDATORY,	cpu_mask,       DRBD_CPU_MASK_SIZE)
 	__u32_field_def(2,	DRBD_GENLA_F_MANDATORY,	on_no_data, DRBD_ON_NO_DATA_DEF)
 )
 
-- 
cgit v1.2.3


From d9f65229f6257842eb7badef015719432b3d16a6 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruen@linbit.com>
Date: Thu, 1 Sep 2011 13:18:31 +0200
Subject: drbd: Move string function prototypes from linux/drbd.h to
 drbd_string.h

Signed-off-by: Andreas Gruenbacher <agruen@linbit.com>
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
---
 drivers/block/drbd/drbd_int.h     | 1 +
 drivers/block/drbd/drbd_strings.c | 1 +
 drivers/block/drbd/drbd_strings.h | 9 +++++++++
 include/linux/drbd.h              | 6 ------
 4 files changed, 11 insertions(+), 6 deletions(-)
 create mode 100644 drivers/block/drbd/drbd_strings.h

(limited to 'include/linux')

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 7293ea5ccabb..0840e9c96f42 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -45,6 +45,7 @@
 #include <linux/prefetch.h>
 #include <linux/drbd_genl_api.h>
 #include <linux/drbd.h>
+#include "drbd_strings.h"
 #include "drbd_state.h"
 #include "drbd_protocol.h"
 
diff --git a/drivers/block/drbd/drbd_strings.c b/drivers/block/drbd/drbd_strings.c
index 58e08ff2b2ce..80b0f63c7075 100644
--- a/drivers/block/drbd/drbd_strings.c
+++ b/drivers/block/drbd/drbd_strings.c
@@ -24,6 +24,7 @@
 */
 
 #include <linux/drbd.h>
+#include "drbd_strings.h"
 
 static const char *drbd_conn_s_names[] = {
 	[C_STANDALONE]       = "StandAlone",
diff --git a/drivers/block/drbd/drbd_strings.h b/drivers/block/drbd/drbd_strings.h
new file mode 100644
index 000000000000..f9923cc88afb
--- /dev/null
+++ b/drivers/block/drbd/drbd_strings.h
@@ -0,0 +1,9 @@
+#ifndef __DRBD_STRINGS_H
+#define __DRBD_STRINGS_H
+
+extern const char *drbd_conn_str(enum drbd_conns);
+extern const char *drbd_role_str(enum drbd_role);
+extern const char *drbd_disk_str(enum drbd_disk_state);
+extern const char *drbd_set_st_err_str(enum drbd_state_rv);
+
+#endif  /* __DRBD_STRINGS_H */
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 6f60136da873..3dbe9bd57a09 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -327,12 +327,6 @@ enum drbd_state_rv {
 	SS_AFTER_LAST_ERROR = -22,    /* Keep this at bottom */
 };
 
-/* from drbd_strings.c */
-extern const char *drbd_conn_str(enum drbd_conns);
-extern const char *drbd_role_str(enum drbd_role);
-extern const char *drbd_disk_str(enum drbd_disk_state);
-extern const char *drbd_set_st_err_str(enum drbd_state_rv);
-
 #define SHARED_SECRET_MAX 64
 
 #define MDF_CONSISTENT		(1 << 0)
-- 
cgit v1.2.3


From ca2ed12f163bf430a425ec725ef76df5254b9f45 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Fri, 31 Jan 2014 12:04:10 -0800
Subject: HID: hid-sensor-hub: Processing for duplicate physical ids

In HID sensor hub, HID physical ids are used to represent different sensors.
For example physical id of 0x73 in usage page = 0x20, represents an
accelerometer. The HID sensor hub driver uses this physical ids to create
platform devices using MFD. There is 1:1 correspondence between an phy id and a
client driver.

But in some cases these physical ids are reused. There is a phy id 0xe1, which
specifies a custom sensor, which can exist multiple times to represent various
custom sensors. In this case there can be multiple instances of client MFD
drivers, processing specific custom sensor. In this case when client driver
looks for report id or a field index, it should still get the report id
specific to its own type. This is also true for reports, they should be
directed towards correct instance.  This change introduce a way to parse and
tie physical devices to their correct instance.

Summary of changes:
- To get physical ids, use collections. If a collection of type=physical
  exist then use usage id as in the name of platform device name
- As part of the platform data, we assign a hdsev instance, which has
  start and end of collection indexes. Using these indexes attributes
  can be tied to correct MFD client instances
- When a report is received, call callback with correct hsdev instance.
  In this way using its private data stored as part of its registry, it
  can distinguish different sensors even when they have same physical and
  logical ids.

  This patch is co-authored with Archana Patni <archna.patni@intel.com>.

Reported-by: Archana Patni <archana.patni@intel.com>
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Archana Patni <archana.patni@intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-sensor-hub.c   | 188 ++++++++++++++++++++++-------------------
 include/linux/hid-sensor-hub.h |   6 +-
 2 files changed, 106 insertions(+), 88 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c
index ad2b8692ad77..5ab93cb18b88 100644
--- a/drivers/hid/hid-sensor-hub.c
+++ b/drivers/hid/hid-sensor-hub.c
@@ -56,9 +56,9 @@ struct sensor_hub_pending {
  * @dyn_callback_lock:	spin lock to protect callback list
  * @hid_sensor_hub_client_devs:	Stores all MFD cells for a hub instance.
  * @hid_sensor_client_cnt: Number of MFD cells, (no of sensors attached).
+ * @ref_cnt:		Number of MFD clients have opened this device
  */
 struct sensor_hub_data {
-	struct hid_sensor_hub_device *hsdev;
 	struct mutex mutex;
 	spinlock_t lock;
 	struct sensor_hub_pending pending;
@@ -67,6 +67,7 @@ struct sensor_hub_data {
 	struct mfd_cell *hid_sensor_hub_client_devs;
 	int hid_sensor_client_cnt;
 	unsigned long quirks;
+	int ref_cnt;
 };
 
 /**
@@ -79,6 +80,7 @@ struct sensor_hub_data {
 struct hid_sensor_hub_callbacks_list {
 	struct list_head list;
 	u32 usage_id;
+	struct hid_sensor_hub_device *hsdev;
 	struct hid_sensor_hub_callbacks *usage_callback;
 	void *priv;
 };
@@ -97,20 +99,18 @@ static struct hid_report *sensor_hub_report(int id, struct hid_device *hdev,
 	return NULL;
 }
 
-static int sensor_hub_get_physical_device_count(
-				struct hid_report_enum *report_enum)
+static int sensor_hub_get_physical_device_count(struct hid_device *hdev)
 {
-	struct hid_report *report;
-	struct hid_field *field;
-	int cnt = 0;
+	int i;
+	int count = 0;
 
-	list_for_each_entry(report, &report_enum->report_list, list) {
-		field = report->field[0];
-		if (report->maxfield && field && field->physical)
-			cnt++;
+	for (i = 0; i < hdev->maxcollection; ++i) {
+		struct hid_collection *collection = &hdev->collection[i];
+		if (collection->type == HID_COLLECTION_PHYSICAL)
+			++count;
 	}
 
-	return cnt;
+	return count;
 }
 
 static void sensor_hub_fill_attr_info(
@@ -128,15 +128,23 @@ static void sensor_hub_fill_attr_info(
 
 static struct hid_sensor_hub_callbacks *sensor_hub_get_callback(
 					struct hid_device *hdev,
-					u32 usage_id, void **priv)
+					u32 usage_id,
+					int collection_index,
+					struct hid_sensor_hub_device **hsdev,
+					void **priv)
 {
 	struct hid_sensor_hub_callbacks_list *callback;
 	struct sensor_hub_data *pdata = hid_get_drvdata(hdev);
 
 	spin_lock(&pdata->dyn_callback_lock);
 	list_for_each_entry(callback, &pdata->dyn_callback_list, list)
-		if (callback->usage_id == usage_id) {
+		if (callback->usage_id == usage_id &&
+			(collection_index >=
+				callback->hsdev->start_collection_index) &&
+			(collection_index <
+				callback->hsdev->end_collection_index)) {
 			*priv = callback->priv;
+			*hsdev = callback->hsdev;
 			spin_unlock(&pdata->dyn_callback_lock);
 			return callback->usage_callback;
 		}
@@ -154,7 +162,8 @@ int sensor_hub_register_callback(struct hid_sensor_hub_device *hsdev,
 
 	spin_lock(&pdata->dyn_callback_lock);
 	list_for_each_entry(callback, &pdata->dyn_callback_list, list)
-		if (callback->usage_id == usage_id) {
+		if (callback->usage_id == usage_id &&
+						callback->hsdev == hsdev) {
 			spin_unlock(&pdata->dyn_callback_lock);
 			return -EINVAL;
 		}
@@ -163,6 +172,7 @@ int sensor_hub_register_callback(struct hid_sensor_hub_device *hsdev,
 		spin_unlock(&pdata->dyn_callback_lock);
 		return -ENOMEM;
 	}
+	callback->hsdev = hsdev;
 	callback->usage_callback = usage_callback;
 	callback->usage_id = usage_id;
 	callback->priv = NULL;
@@ -181,7 +191,8 @@ int sensor_hub_remove_callback(struct hid_sensor_hub_device *hsdev,
 
 	spin_lock(&pdata->dyn_callback_lock);
 	list_for_each_entry(callback, &pdata->dyn_callback_list, list)
-		if (callback->usage_id == usage_id) {
+		if (callback->usage_id == usage_id &&
+						callback->hsdev == hsdev) {
 			list_del(&callback->list);
 			kfree(callback);
 			break;
@@ -320,8 +331,7 @@ int sensor_hub_input_get_attribute_info(struct hid_sensor_hub_device *hsdev,
 				struct hid_sensor_hub_attribute_info *info)
 {
 	int ret = -1;
-	int i, j;
-	int collection_index = -1;
+	int i;
 	struct hid_report *report;
 	struct hid_field *field;
 	struct hid_report_enum *report_enum;
@@ -335,44 +345,31 @@ int sensor_hub_input_get_attribute_info(struct hid_sensor_hub_device *hsdev,
 	info->units = -1;
 	info->unit_expo = -1;
 
-	for (i = 0; i < hdev->maxcollection; ++i) {
-		struct hid_collection *collection = &hdev->collection[i];
-		if (usage_id == collection->usage) {
-			collection_index = i;
-			break;
-		}
-	}
-	if (collection_index == -1)
-		goto err_ret;
-
 	report_enum = &hdev->report_enum[type];
 	list_for_each_entry(report, &report_enum->report_list, list) {
 		for (i = 0; i < report->maxfield; ++i) {
 			field = report->field[i];
-			if (field->physical == usage_id &&
-				field->logical == attr_usage_id) {
-				sensor_hub_fill_attr_info(info, i, report->id,
-							  field);
-				ret = 0;
-			} else {
-				for (j = 0; j < field->maxusage; ++j) {
-					if (field->usage[j].hid ==
-					attr_usage_id &&
-					field->usage[j].collection_index ==
-					collection_index) {
-						sensor_hub_fill_attr_info(info,
-							  i, report->id, field);
-						ret = 0;
-						break;
-					}
+			if (field->maxusage) {
+				if (field->physical == usage_id &&
+					(field->logical == attr_usage_id ||
+					field->usage[0].hid ==
+							attr_usage_id) &&
+					(field->usage[0].collection_index >=
+					hsdev->start_collection_index) &&
+					(field->usage[0].collection_index <
+					hsdev->end_collection_index)) {
+
+					sensor_hub_fill_attr_info(info, i,
+								report->id,
+								field);
+					ret = 0;
+					break;
 				}
 			}
-			if (ret == 0)
-				break;
 		}
+
 	}
 
-err_ret:
 	return ret;
 }
 EXPORT_SYMBOL_GPL(sensor_hub_input_get_attribute_info);
@@ -388,7 +385,7 @@ static int sensor_hub_suspend(struct hid_device *hdev, pm_message_t message)
 	list_for_each_entry(callback, &pdata->dyn_callback_list, list) {
 		if (callback->usage_callback->suspend)
 			callback->usage_callback->suspend(
-					pdata->hsdev, callback->priv);
+					callback->hsdev, callback->priv);
 	}
 	spin_unlock(&pdata->dyn_callback_lock);
 
@@ -405,7 +402,7 @@ static int sensor_hub_resume(struct hid_device *hdev)
 	list_for_each_entry(callback, &pdata->dyn_callback_list, list) {
 		if (callback->usage_callback->resume)
 			callback->usage_callback->resume(
-					pdata->hsdev, callback->priv);
+					callback->hsdev, callback->priv);
 	}
 	spin_unlock(&pdata->dyn_callback_lock);
 
@@ -432,6 +429,7 @@ static int sensor_hub_raw_event(struct hid_device *hdev,
 	struct hid_sensor_hub_callbacks *callback = NULL;
 	struct hid_collection *collection = NULL;
 	void *priv = NULL;
+	struct hid_sensor_hub_device *hsdev = NULL;
 
 	hid_dbg(hdev, "sensor_hub_raw_event report id:0x%x size:%d type:%d\n",
 			 report->id, size, report->type);
@@ -466,23 +464,26 @@ static int sensor_hub_raw_event(struct hid_device *hdev,
 				report->field[i]->usage->collection_index];
 		hid_dbg(hdev, "collection->usage %x\n",
 					collection->usage);
-		callback = sensor_hub_get_callback(pdata->hsdev->hdev,
-						report->field[i]->physical,
-							&priv);
+
+		callback = sensor_hub_get_callback(hdev,
+				report->field[i]->physical,
+				report->field[i]->usage[0].collection_index,
+				&hsdev, &priv);
+
 		if (callback && callback->capture_sample) {
 			if (report->field[i]->logical)
-				callback->capture_sample(pdata->hsdev,
+				callback->capture_sample(hsdev,
 					report->field[i]->logical, sz, ptr,
 					callback->pdev);
 			else
-				callback->capture_sample(pdata->hsdev,
+				callback->capture_sample(hsdev,
 					report->field[i]->usage->hid, sz, ptr,
 					callback->pdev);
 		}
 		ptr += sz;
 	}
 	if (callback && collection && callback->send_event)
-		callback->send_event(pdata->hsdev, collection->usage,
+		callback->send_event(hsdev, collection->usage,
 				callback->pdev);
 	spin_unlock_irqrestore(&pdata->lock, flags);
 
@@ -495,7 +496,7 @@ int sensor_hub_device_open(struct hid_sensor_hub_device *hsdev)
 	struct sensor_hub_data *data =  hid_get_drvdata(hsdev->hdev);
 
 	mutex_lock(&data->mutex);
-	if (!hsdev->ref_cnt) {
+	if (!data->ref_cnt) {
 		ret = hid_hw_open(hsdev->hdev);
 		if (ret) {
 			hid_err(hsdev->hdev, "failed to open hid device\n");
@@ -503,7 +504,7 @@ int sensor_hub_device_open(struct hid_sensor_hub_device *hsdev)
 			return ret;
 		}
 	}
-	hsdev->ref_cnt++;
+	data->ref_cnt++;
 	mutex_unlock(&data->mutex);
 
 	return ret;
@@ -515,8 +516,8 @@ void sensor_hub_device_close(struct hid_sensor_hub_device *hsdev)
 	struct sensor_hub_data *data =  hid_get_drvdata(hsdev->hdev);
 
 	mutex_lock(&data->mutex);
-	hsdev->ref_cnt--;
-	if (!hsdev->ref_cnt)
+	data->ref_cnt--;
+	if (!data->ref_cnt)
 		hid_hw_close(hsdev->hdev);
 	mutex_unlock(&data->mutex);
 }
@@ -563,26 +564,19 @@ static int sensor_hub_probe(struct hid_device *hdev,
 	struct sensor_hub_data *sd;
 	int i;
 	char *name;
-	struct hid_report *report;
-	struct hid_report_enum *report_enum;
-	struct hid_field *field;
 	int dev_cnt;
+	struct hid_sensor_hub_device *hsdev;
+	struct hid_sensor_hub_device *last_hsdev = NULL;
 
 	sd = devm_kzalloc(&hdev->dev, sizeof(*sd), GFP_KERNEL);
 	if (!sd) {
 		hid_err(hdev, "cannot allocate Sensor data\n");
 		return -ENOMEM;
 	}
-	sd->hsdev = devm_kzalloc(&hdev->dev, sizeof(*sd->hsdev), GFP_KERNEL);
-	if (!sd->hsdev) {
-		hid_err(hdev, "cannot allocate hid_sensor_hub_device\n");
-		return -ENOMEM;
-	}
+
 	hid_set_drvdata(hdev, sd);
 	sd->quirks = id->driver_data;
-	sd->hsdev->hdev = hdev;
-	sd->hsdev->vendor_id = hdev->vendor;
-	sd->hsdev->product_id = hdev->product;
+
 	spin_lock_init(&sd->lock);
 	spin_lock_init(&sd->dyn_callback_lock);
 	mutex_init(&sd->mutex);
@@ -600,9 +594,8 @@ static int sensor_hub_probe(struct hid_device *hdev,
 	}
 	INIT_LIST_HEAD(&sd->dyn_callback_list);
 	sd->hid_sensor_client_cnt = 0;
-	report_enum = &hdev->report_enum[HID_INPUT_REPORT];
 
-	dev_cnt = sensor_hub_get_physical_device_count(report_enum);
+	dev_cnt = sensor_hub_get_physical_device_count(hdev);
 	if (dev_cnt > HID_MAX_PHY_DEVICES) {
 		hid_err(hdev, "Invalid Physical device count\n");
 		ret = -EINVAL;
@@ -616,42 +609,63 @@ static int sensor_hub_probe(struct hid_device *hdev,
 			ret = -ENOMEM;
 			goto err_stop_hw;
 	}
-	list_for_each_entry(report, &report_enum->report_list, list) {
-		hid_dbg(hdev, "Report id:%x\n", report->id);
-		field = report->field[0];
-		if (report->maxfield && field &&
-					field->physical) {
+
+	for (i = 0; i < hdev->maxcollection; ++i) {
+		struct hid_collection *collection = &hdev->collection[i];
+
+		if (collection->type == HID_COLLECTION_PHYSICAL) {
+
+			hsdev = kzalloc(sizeof(*hsdev), GFP_KERNEL);
+			if (!hsdev) {
+				hid_err(hdev, "cannot allocate hid_sensor_hub_device\n");
+				ret = -ENOMEM;
+				goto err_no_mem;
+			}
+			hsdev->hdev = hdev;
+			hsdev->vendor_id = hdev->vendor;
+			hsdev->product_id = hdev->product;
+			hsdev->start_collection_index = i;
+			if (last_hsdev)
+				last_hsdev->end_collection_index = i;
+			last_hsdev = hsdev;
 			name = kasprintf(GFP_KERNEL, "HID-SENSOR-%x",
-						field->physical);
+					collection->usage);
 			if (name == NULL) {
 				hid_err(hdev, "Failed MFD device name\n");
 					ret = -ENOMEM;
-					goto err_free_names;
+					goto err_no_mem;
 			}
 			sd->hid_sensor_hub_client_devs[
-				sd->hid_sensor_client_cnt].id = PLATFORM_DEVID_AUTO;
+				sd->hid_sensor_client_cnt].id =
+							PLATFORM_DEVID_AUTO;
 			sd->hid_sensor_hub_client_devs[
 				sd->hid_sensor_client_cnt].name = name;
 			sd->hid_sensor_hub_client_devs[
 				sd->hid_sensor_client_cnt].platform_data =
-						sd->hsdev;
+							hsdev;
 			sd->hid_sensor_hub_client_devs[
 				sd->hid_sensor_client_cnt].pdata_size =
-						sizeof(*sd->hsdev);
-			hid_dbg(hdev, "Adding %s:%p\n", name, sd);
+							sizeof(*hsdev);
+			hid_dbg(hdev, "Adding %s:%d\n", name,
+					hsdev->start_collection_index);
 			sd->hid_sensor_client_cnt++;
 		}
 	}
+	if (last_hsdev)
+		last_hsdev->end_collection_index = i;
+
 	ret = mfd_add_devices(&hdev->dev, 0, sd->hid_sensor_hub_client_devs,
 		sd->hid_sensor_client_cnt, NULL, 0, NULL);
 	if (ret < 0)
-		goto err_free_names;
+		goto err_no_mem;
 
 	return ret;
 
-err_free_names:
-	for (i = 0; i < sd->hid_sensor_client_cnt ; ++i)
+err_no_mem:
+	for (i = 0; i < sd->hid_sensor_client_cnt; ++i) {
 		kfree(sd->hid_sensor_hub_client_devs[i].name);
+		kfree(sd->hid_sensor_hub_client_devs[i].platform_data);
+	}
 	kfree(sd->hid_sensor_hub_client_devs);
 err_stop_hw:
 	hid_hw_stop(hdev);
@@ -673,8 +687,10 @@ static void sensor_hub_remove(struct hid_device *hdev)
 		complete(&data->pending.ready);
 	spin_unlock_irqrestore(&data->lock, flags);
 	mfd_remove_devices(&hdev->dev);
-	for (i = 0; i < data->hid_sensor_client_cnt ; ++i)
+	for (i = 0; i < data->hid_sensor_client_cnt; ++i) {
 		kfree(data->hid_sensor_hub_client_devs[i].name);
+		kfree(data->hid_sensor_hub_client_devs[i].platform_data);
+	}
 	kfree(data->hid_sensor_hub_client_devs);
 	hid_set_drvdata(hdev, NULL);
 	mutex_destroy(&data->mutex);
diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h
index 205eba0326af..b70cfd7ff29c 100644
--- a/include/linux/hid-sensor-hub.h
+++ b/include/linux/hid-sensor-hub.h
@@ -51,13 +51,15 @@ struct hid_sensor_hub_attribute_info {
  * @hdev:		Stores the hid instance.
  * @vendor_id:		Vendor id of hub device.
  * @product_id:		Product id of hub device.
- * @ref_cnt:		Number of MFD clients have opened this device
+ * @start_collection_index: Starting index for a phy type collection
+ * @end_collection_index: Last index for a phy type collection
  */
 struct hid_sensor_hub_device {
 	struct hid_device *hdev;
 	u32 vendor_id;
 	u32 product_id;
-	int ref_cnt;
+	int start_collection_index;
+	int end_collection_index;
 };
 
 /**
-- 
cgit v1.2.3


From 797ac07137d9ae8572008e21e6123a9ae17dae50 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 17 Feb 2014 13:34:02 -0800
Subject: net: phy: move PHY software reset to genphy_soft_reset

As pointed out by Shaohui, this function is generic for 10/100/1000
PHYs, but 10G PHYs might have a slightly different reset sequence which
prevents most of them from using this function.

Move the BMCR_RESET based software resent sequence to
genphy_soft_reset() in preparation for allowing PHY drivers to implement
a soft_reset() callback.

Reported-by: Shaohui Xie <Shaohui.Xie@freescale.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 27 ++++++++++++++++++++++-----
 include/linux/phy.h          |  1 +
 2 files changed, 23 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index c2d778d06405..7c21b8214bb9 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -540,11 +540,7 @@ int phy_init_hw(struct phy_device *phydev)
 	if (!phydev->drv || !phydev->drv->config_init)
 		return 0;
 
-	ret = phy_write(phydev, MII_BMCR, BMCR_RESET);
-	if (ret < 0)
-		return ret;
-
-	ret = phy_poll_reset(phydev);
+	ret = genphy_soft_reset(phydev);
 	if (ret < 0)
 		return ret;
 
@@ -1045,6 +1041,27 @@ static int gen10g_read_status(struct phy_device *phydev)
 	return 0;
 }
 
+/**
+ * genphy_soft_reset - software reset the PHY via BMCR_RESET bit
+ * @phydev: target phy_device struct
+ *
+ * Description: Perform a software PHY reset using the standard
+ * BMCR_RESET bit and poll for the reset bit to be cleared.
+ *
+ * Returns: 0 on success, < 0 on failure
+ */
+int genphy_soft_reset(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = phy_write(phydev, MII_BMCR, BMCR_RESET);
+	if (ret < 0)
+		return ret;
+
+	return phy_poll_reset(phydev);
+}
+EXPORT_SYMBOL(genphy_soft_reset);
+
 static int genphy_config_init(struct phy_device *phydev)
 {
 	int val;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index f7fe54628424..bffe0ec1604f 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -666,6 +666,7 @@ int genphy_update_link(struct phy_device *phydev);
 int genphy_read_status(struct phy_device *phydev);
 int genphy_suspend(struct phy_device *phydev);
 int genphy_resume(struct phy_device *phydev);
+int genphy_soft_reset(struct phy_device *phydev);
 void phy_driver_unregister(struct phy_driver *drv);
 void phy_drivers_unregister(struct phy_driver *drv, int n);
 int phy_driver_register(struct phy_driver *new_driver);
-- 
cgit v1.2.3


From 9df81dd7583d14862d0cfb673a941b261f3b2112 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Mon, 17 Feb 2014 13:34:03 -0800
Subject: net: phy: allow PHY drivers to implement their own software reset

As pointed out by Shaohui, most 10G PHYs out there have a non-standard
compliant software reset sequence, eventually something much more
complex than just toggling the BMCR_RESET bit. Allow PHY driver to
implement their own soft_reset() callback to deal with that. If no
callback is provided, call into genphy_soft_reset() which makes sure the
existing behavior is kept intact.

Reported-by: Shaohui Xie <Shaohui.Xie@freescale.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 16 ++++++++++++++--
 include/linux/phy.h          |  5 +++++
 2 files changed, 19 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 7c21b8214bb9..a70b604ac644 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -535,12 +535,16 @@ static int phy_poll_reset(struct phy_device *phydev)
 
 int phy_init_hw(struct phy_device *phydev)
 {
-	int ret;
+	int ret = 0;
 
 	if (!phydev->drv || !phydev->drv->config_init)
 		return 0;
 
-	ret = genphy_soft_reset(phydev);
+	if (phydev->drv->soft_reset)
+		ret = phydev->drv->soft_reset(phydev);
+	else
+		ret = genphy_soft_reset(phydev);
+
 	if (ret < 0)
 		return ret;
 
@@ -1108,6 +1112,12 @@ static int genphy_config_init(struct phy_device *phydev)
 	return 0;
 }
 
+static int gen10g_soft_reset(struct phy_device *phydev)
+{
+	/* Do nothing for now */
+	return 0;
+}
+
 static int gen10g_config_init(struct phy_device *phydev)
 {
 	/* Temporarily just say we support everything */
@@ -1282,6 +1292,7 @@ static struct phy_driver genphy_driver[] = {
 	.phy_id		= 0xffffffff,
 	.phy_id_mask	= 0xffffffff,
 	.name		= "Generic PHY",
+	.soft_reset	= genphy_soft_reset,
 	.config_init	= genphy_config_init,
 	.features	= 0,
 	.config_aneg	= genphy_config_aneg,
@@ -1294,6 +1305,7 @@ static struct phy_driver genphy_driver[] = {
 	.phy_id         = 0xffffffff,
 	.phy_id_mask    = 0xffffffff,
 	.name           = "Generic 10G PHY",
+	.soft_reset	= gen10g_soft_reset,
 	.config_init    = gen10g_config_init,
 	.features       = 0,
 	.config_aneg    = gen10g_config_aneg,
diff --git a/include/linux/phy.h b/include/linux/phy.h
index bffe0ec1604f..24126c4b27b5 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -439,6 +439,11 @@ struct phy_driver {
 	u32 features;
 	u32 flags;
 
+	/*
+	 * Called to issue a PHY software reset
+	 */
+	int (*soft_reset)(struct phy_device *phydev);
+
 	/*
 	 * Called to initialize the PHY,
 	 * including after a reset
-- 
cgit v1.2.3


From 9b2777d6089bcd7fb035847f907280560fe233c8 Mon Sep 17 00:00:00 2001
From: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Date: Mon, 17 Feb 2014 11:34:08 +0100
Subject: ieee802154: add TX power control to wpan_phy

Replace the current u8 transmit_power in wpan_phy with s8 transmit_power.
The u8 field contained the actual tx power and a tolerance field,
which no physical radio every used. Adjust sysfs entries to keep
compatibility with userspace, give tolerances of +-1dB statically there.

This patch only adds support for this in the at86rf230 driver and the
RF212 chip. Configuration calculation for RF212 is also somewhat basic,
but does the job - the RF212 datasheet gives a large table with
suggested values for combinations of TX power and page/channel, if this
does not work well, we might have to copy the whole table.

Signed-off-by: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ieee802154/at86rf230.c | 25 +++++++++++++++++++
 include/linux/nl802154.h           |  4 ++++
 include/net/mac802154.h            |  5 ++++
 include/net/wpan-phy.h             |  6 +++--
 net/ieee802154/ieee802154.h        |  1 +
 net/ieee802154/netlink.c           |  1 +
 net/ieee802154/nl-phy.c            | 49 +++++++++++++++++++++++++++++++++++++-
 net/ieee802154/nl_policy.c         |  2 ++
 net/ieee802154/wpan-class.c        |  4 +---
 net/mac802154/ieee802154_dev.c     | 11 +++++++++
 10 files changed, 102 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index bd1ef0b3bee9..9afb4b9d7c93 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -753,6 +753,30 @@ at86rf230_set_hw_addr_filt(struct ieee802154_dev *dev,
 	return 0;
 }
 
+static int
+at86rf212_set_txpower(struct ieee802154_dev *dev, int db)
+{
+	struct at86rf230_local *lp = dev->priv;
+	int rc;
+
+	/* typical maximum output is 5dBm with RG_PHY_TX_PWR 0x60, lower five
+	 * bits decrease power in 1dB steps. 0x60 represents extra PA gain of
+	 * 0dB.
+	 * thus, supported values for db range from -26 to 5, for 31dB of
+	 * reduction to 0dB of reduction.
+	 */
+	if (db > 5 || db < -26)
+		return -EINVAL;
+
+	db = -(db - 5);
+
+	rc = __at86rf230_write(lp, RG_PHY_TX_PWR, 0x60 | db);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
 static struct ieee802154_ops at86rf230_ops = {
 	.owner = THIS_MODULE,
 	.xmit = at86rf230_xmit,
@@ -771,6 +795,7 @@ static struct ieee802154_ops at86rf212_ops = {
 	.start = at86rf230_start,
 	.stop = at86rf230_stop,
 	.set_hw_addr_filt = at86rf230_set_hw_addr_filt,
+	.set_txpower = at86rf212_set_txpower,
 };
 
 static void at86rf230_irqwork(struct work_struct *work)
diff --git a/include/linux/nl802154.h b/include/linux/nl802154.h
index fd4f2d1cdf6c..625d19e0a1de 100644
--- a/include/linux/nl802154.h
+++ b/include/linux/nl802154.h
@@ -70,6 +70,8 @@ enum {
 	IEEE802154_ATTR_PHY_NAME,
 	IEEE802154_ATTR_DEV_TYPE,
 
+	IEEE802154_ATTR_TXPOWER,
+
 	__IEEE802154_ATTR_MAX,
 };
 
@@ -122,6 +124,8 @@ enum {
 	IEEE802154_ADD_IFACE,
 	IEEE802154_DEL_IFACE,
 
+	IEEE802154_SET_PHYPARAMS,
+
 	__IEEE802154_CMD_MAX,
 };
 
diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 807d6b7a943f..8bd2785a663c 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -113,6 +113,10 @@ struct ieee802154_dev {
  *	  Set radio for listening on specific address.
  *	  Set the device for listening on specified address.
  *	  Returns either zero, or negative errno.
+ *
+ * set_txpower:
+ *	  Set radio transmit power in dB. Called with pib_lock held.
+ *	  Returns either zero, or negative errno.
  */
 struct ieee802154_ops {
 	struct module	*owner;
@@ -129,6 +133,7 @@ struct ieee802154_ops {
 					    unsigned long changed);
 	int		(*ieee_addr)(struct ieee802154_dev *dev,
 				     u8 addr[IEEE802154_ADDR_LEN]);
+	int		(*set_txpower)(struct ieee802154_dev *dev, int db);
 };
 
 /* Basic interface to register ieee802154 device */
diff --git a/include/net/wpan-phy.h b/include/net/wpan-phy.h
index b52bda8d13b1..47fc0c1bc3c7 100644
--- a/include/net/wpan-phy.h
+++ b/include/net/wpan-phy.h
@@ -37,14 +37,14 @@ struct wpan_phy {
 	struct mutex pib_lock;
 
 	/*
-	 * This is a PIB according to 802.15.4-2006.
+	 * This is a PIB according to 802.15.4-2011.
 	 * We do not provide timing-related variables, as they
 	 * aren't used outside of driver
 	 */
 	u8 current_channel;
 	u8 current_page;
 	u32 channels_supported[32];
-	u8 transmit_power;
+	s8 transmit_power;
 	u8 cca_mode;
 
 	struct device dev;
@@ -54,6 +54,8 @@ struct wpan_phy {
 					const char *name, int type);
 	void (*del_iface)(struct wpan_phy *phy, struct net_device *dev);
 
+	int (*set_txpower)(struct wpan_phy *phy, int db);
+
 	char priv[0] __attribute__((__aligned__(NETDEV_ALIGN)));
 };
 
diff --git a/net/ieee802154/ieee802154.h b/net/ieee802154/ieee802154.h
index cee4425b9956..6cbc8965be91 100644
--- a/net/ieee802154/ieee802154.h
+++ b/net/ieee802154/ieee802154.h
@@ -53,6 +53,7 @@ int ieee802154_list_phy(struct sk_buff *skb, struct genl_info *info);
 int ieee802154_dump_phy(struct sk_buff *skb, struct netlink_callback *cb);
 int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info);
 int ieee802154_del_iface(struct sk_buff *skb, struct genl_info *info);
+int ieee802154_set_phyparams(struct sk_buff *skb, struct genl_info *info);
 
 enum ieee802154_mcgrp_ids {
 	IEEE802154_COORD_MCGRP,
diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c
index 43f1b2bf469f..67c151bf4b91 100644
--- a/net/ieee802154/netlink.c
+++ b/net/ieee802154/netlink.c
@@ -115,6 +115,7 @@ static const struct genl_ops ieee8021154_ops[] = {
 			ieee802154_dump_phy),
 	IEEE802154_OP(IEEE802154_ADD_IFACE, ieee802154_add_iface),
 	IEEE802154_OP(IEEE802154_DEL_IFACE, ieee802154_del_iface),
+	IEEE802154_OP(IEEE802154_SET_PHYPARAMS, ieee802154_set_phyparams),
 	/* see nl-mac.c */
 	IEEE802154_OP(IEEE802154_ASSOCIATE_REQ, ieee802154_associate_req),
 	IEEE802154_OP(IEEE802154_ASSOCIATE_RESP, ieee802154_associate_resp),
diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index 89b265aea151..d3ee62fbae99 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -55,7 +55,8 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 portid,
 	mutex_lock(&phy->pib_lock);
 	if (nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) ||
 	    nla_put_u8(msg, IEEE802154_ATTR_PAGE, phy->current_page) ||
-	    nla_put_u8(msg, IEEE802154_ATTR_CHANNEL, phy->current_channel))
+	    nla_put_u8(msg, IEEE802154_ATTR_CHANNEL, phy->current_channel) ||
+	    nla_put_s8(msg, IEEE802154_ATTR_TXPOWER, phy->transmit_power))
 		goto nla_put_failure;
 	for (i = 0; i < 32; i++) {
 		if (phy->channels_supported[i])
@@ -354,3 +355,49 @@ out_dev:
 
 	return rc;
 }
+
+int ieee802154_set_phyparams(struct sk_buff *skb, struct genl_info *info)
+{
+	struct wpan_phy *phy;
+	const char *name;
+	int txpower;
+	int rc = -EINVAL;
+
+	pr_debug("%s\n", __func__);
+
+	if (!info->attrs[IEEE802154_ATTR_PHY_NAME])
+		return -EINVAL;
+
+	name = nla_data(info->attrs[IEEE802154_ATTR_PHY_NAME]);
+	if (name[nla_len(info->attrs[IEEE802154_ATTR_PHY_NAME]) - 1] != '\0')
+		return -EINVAL; /* phy name should be null-terminated */
+
+	txpower = nla_get_s8(info->attrs[IEEE802154_ATTR_TXPOWER]);
+
+	phy = wpan_phy_find(name);
+	if (!phy)
+		return -ENODEV;
+
+	if (!phy->set_txpower)
+		goto out;
+
+	mutex_lock(&phy->pib_lock);
+
+	rc = phy->set_txpower(phy, txpower);
+	if (rc < 0) {
+		mutex_unlock(&phy->pib_lock);
+		goto out;
+	}
+
+	phy->transmit_power = txpower;
+
+	mutex_unlock(&phy->pib_lock);
+
+	wpan_phy_put(phy);
+
+	return 0;
+
+out:
+	wpan_phy_put(phy);
+	return rc;
+}
diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c
index 6adda4d46f95..90b1d0d2c14e 100644
--- a/net/ieee802154/nl_policy.c
+++ b/net/ieee802154/nl_policy.c
@@ -52,5 +52,7 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = {
 	[IEEE802154_ATTR_DURATION] = { .type = NLA_U8, },
 	[IEEE802154_ATTR_ED_LIST] = { .len = 27 },
 	[IEEE802154_ATTR_CHANNEL_PAGE_LIST] = { .len = 32 * 4, },
+
+	[IEEE802154_ATTR_TXPOWER] = { .type = NLA_S8, },
 };
 
diff --git a/net/ieee802154/wpan-class.c b/net/ieee802154/wpan-class.c
index 4dd37615a749..8d6f6704da84 100644
--- a/net/ieee802154/wpan-class.c
+++ b/net/ieee802154/wpan-class.c
@@ -44,9 +44,7 @@ static DEVICE_ATTR_RO(name);
 
 MASTER_SHOW(current_channel, "%d");
 MASTER_SHOW(current_page, "%d");
-MASTER_SHOW_COMPLEX(transmit_power, "%d +- %d dB",
-	((signed char) (phy->transmit_power << 2)) >> 2,
-	(phy->transmit_power >> 6) ? (phy->transmit_power >> 6) * 3 : 1);
+MASTER_SHOW(transmit_power, "%d +- 1 dB");
 MASTER_SHOW(cca_mode, "%d");
 
 static ssize_t channels_supported_show(struct device *dev,
diff --git a/net/mac802154/ieee802154_dev.c b/net/mac802154/ieee802154_dev.c
index 52ae6646a411..9eb49e0886a4 100644
--- a/net/mac802154/ieee802154_dev.c
+++ b/net/mac802154/ieee802154_dev.c
@@ -165,6 +165,16 @@ err:
 	return ERR_PTR(err);
 }
 
+static int mac802154_set_txpower(struct wpan_phy *phy, int db)
+{
+	struct mac802154_priv *priv = wpan_phy_priv(phy);
+
+	if (!priv->ops->set_txpower)
+		return -ENOTSUPP;
+
+	return priv->ops->set_txpower(&priv->hw, db);
+}
+
 struct ieee802154_dev *
 ieee802154_alloc_device(size_t priv_data_len, struct ieee802154_ops *ops)
 {
@@ -242,6 +252,7 @@ int ieee802154_register_device(struct ieee802154_dev *dev)
 
 	priv->phy->add_iface = mac802154_add_iface;
 	priv->phy->del_iface = mac802154_del_iface;
+	priv->phy->set_txpower = mac802154_set_txpower;
 
 	rc = wpan_phy_register(priv->phy);
 	if (rc < 0)
-- 
cgit v1.2.3


From 84dda3c648fd55898064d76366b14f964cdc9d16 Mon Sep 17 00:00:00 2001
From: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Date: Mon, 17 Feb 2014 11:34:10 +0100
Subject: ieee802154: add support for listen-before-talk in wpan_phy

Listen-before-talk is an alternative to CSMA in uncoordinated networks
and prescribed by european regulations if one wants to have a device
with radio duty cycles above 10% (or less in some bands). Add a phy
property to enable/disable LBT in the phy, including support in the
at86rf230 driver for RF212 chips.

Signed-off-by: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ieee802154/at86rf230.c | 11 +++++++-
 include/linux/nl802154.h           |  1 +
 include/net/mac802154.h            |  6 ++++
 include/net/wpan-phy.h             |  3 ++
 net/ieee802154/nl-phy.c            | 58 ++++++++++++++++++++++++++++++--------
 net/ieee802154/nl_policy.c         |  1 +
 net/mac802154/ieee802154_dev.c     | 11 ++++++++
 7 files changed, 78 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index 04a995dad593..3d40c2350261 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -152,7 +152,7 @@ static inline int is_rf212(struct at86rf230_local *local)
 #define	SR_RESERVED_17_5	0x17, 0x08, 3
 #define	SR_AACK_UPLD_RES_FT	0x17, 0x10, 4
 #define	SR_AACK_FLTR_RES_FT	0x17, 0x20, 5
-#define	SR_RESERVED_17_2	0x17, 0x40, 6
+#define	SR_CSMA_LBT_MODE	0x17, 0x40, 6
 #define	SR_RESERVED_17_1	0x17, 0x80, 7
 #define	RG_FTN_CTRL	(0x18)
 #define	SR_RESERVED_18_2	0x18, 0x7f, 0
@@ -786,6 +786,14 @@ at86rf212_set_txpower(struct ieee802154_dev *dev, int db)
 	return 0;
 }
 
+static int
+at86rf212_set_lbt(struct ieee802154_dev *dev, bool on)
+{
+	struct at86rf230_local *lp = dev->priv;
+
+	return at86rf230_write_subreg(lp, SR_CSMA_LBT_MODE, on);
+}
+
 static struct ieee802154_ops at86rf230_ops = {
 	.owner = THIS_MODULE,
 	.xmit = at86rf230_xmit,
@@ -805,6 +813,7 @@ static struct ieee802154_ops at86rf212_ops = {
 	.stop = at86rf230_stop,
 	.set_hw_addr_filt = at86rf230_set_hw_addr_filt,
 	.set_txpower = at86rf212_set_txpower,
+	.set_lbt = at86rf212_set_lbt,
 };
 
 static void at86rf230_irqwork(struct work_struct *work)
diff --git a/include/linux/nl802154.h b/include/linux/nl802154.h
index 625d19e0a1de..326baee227f7 100644
--- a/include/linux/nl802154.h
+++ b/include/linux/nl802154.h
@@ -71,6 +71,7 @@ enum {
 	IEEE802154_ATTR_DEV_TYPE,
 
 	IEEE802154_ATTR_TXPOWER,
+	IEEE802154_ATTR_LBT_ENABLED,
 
 	__IEEE802154_ATTR_MAX,
 };
diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 8bd2785a663c..521edcb0e586 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -117,6 +117,11 @@ struct ieee802154_dev {
  * set_txpower:
  *	  Set radio transmit power in dB. Called with pib_lock held.
  *	  Returns either zero, or negative errno.
+ *
+ * set_lbt
+ *	  Enables or disables listen before talk on the device. Called with
+ *	  pib_lock held.
+ *	  Returns either zero, or negative errno.
  */
 struct ieee802154_ops {
 	struct module	*owner;
@@ -134,6 +139,7 @@ struct ieee802154_ops {
 	int		(*ieee_addr)(struct ieee802154_dev *dev,
 				     u8 addr[IEEE802154_ADDR_LEN]);
 	int		(*set_txpower)(struct ieee802154_dev *dev, int db);
+	int		(*set_lbt)(struct ieee802154_dev *dev, bool on);
 };
 
 /* Basic interface to register ieee802154 device */
diff --git a/include/net/wpan-phy.h b/include/net/wpan-phy.h
index 47fc0c1bc3c7..804e6c4f5f8a 100644
--- a/include/net/wpan-phy.h
+++ b/include/net/wpan-phy.h
@@ -47,6 +47,8 @@ struct wpan_phy {
 	s8 transmit_power;
 	u8 cca_mode;
 
+	bool lbt;
+
 	struct device dev;
 	int idx;
 
@@ -55,6 +57,7 @@ struct wpan_phy {
 	void (*del_iface)(struct wpan_phy *phy, struct net_device *dev);
 
 	int (*set_txpower)(struct wpan_phy *phy, int db);
+	int (*set_lbt)(struct wpan_phy *phy, bool on);
 
 	char priv[0] __attribute__((__aligned__(NETDEV_ALIGN)));
 };
diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index d3ee62fbae99..f029310b0662 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -56,7 +56,8 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 portid,
 	if (nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) ||
 	    nla_put_u8(msg, IEEE802154_ATTR_PAGE, phy->current_page) ||
 	    nla_put_u8(msg, IEEE802154_ATTR_CHANNEL, phy->current_channel) ||
-	    nla_put_s8(msg, IEEE802154_ATTR_TXPOWER, phy->transmit_power))
+	    nla_put_s8(msg, IEEE802154_ATTR_TXPOWER, phy->transmit_power) ||
+	    nla_put_u8(msg, IEEE802154_ATTR_LBT_ENABLED, phy->lbt))
 		goto nla_put_failure;
 	for (i = 0; i < 32; i++) {
 		if (phy->channels_supported[i])
@@ -356,40 +357,71 @@ out_dev:
 	return rc;
 }
 
+static int phy_set_txpower(struct wpan_phy *phy, struct genl_info *info)
+{
+	int txpower = nla_get_s8(info->attrs[IEEE802154_ATTR_TXPOWER]);
+	int rc;
+
+	rc = phy->set_txpower(phy, txpower);
+	if (rc < 0)
+		return rc;
+
+	phy->transmit_power = txpower;
+
+	return 0;
+}
+
+static int phy_set_lbt(struct wpan_phy *phy, struct genl_info *info)
+{
+	u8 on = !!nla_get_u8(info->attrs[IEEE802154_ATTR_LBT_ENABLED]);
+	int rc;
+
+	rc = phy->set_lbt(phy, on);
+	if (rc < 0)
+		return rc;
+
+	phy->lbt = on;
+
+	return 0;
+}
+
 int ieee802154_set_phyparams(struct sk_buff *skb, struct genl_info *info)
 {
 	struct wpan_phy *phy;
 	const char *name;
-	int txpower;
-	int rc = -EINVAL;
+	int rc = -ENOTSUPP;
 
 	pr_debug("%s\n", __func__);
 
-	if (!info->attrs[IEEE802154_ATTR_PHY_NAME])
+	if (!info->attrs[IEEE802154_ATTR_PHY_NAME] &&
+	    !info->attrs[IEEE802154_ATTR_LBT_ENABLED])
 		return -EINVAL;
 
 	name = nla_data(info->attrs[IEEE802154_ATTR_PHY_NAME]);
 	if (name[nla_len(info->attrs[IEEE802154_ATTR_PHY_NAME]) - 1] != '\0')
 		return -EINVAL; /* phy name should be null-terminated */
 
-	txpower = nla_get_s8(info->attrs[IEEE802154_ATTR_TXPOWER]);
-
 	phy = wpan_phy_find(name);
 	if (!phy)
 		return -ENODEV;
 
-	if (!phy->set_txpower)
+	if ((!phy->set_txpower && info->attrs[IEEE802154_ATTR_TXPOWER]) ||
+	    (!phy->set_lbt && info->attrs[IEEE802154_ATTR_LBT_ENABLED]))
 		goto out;
 
 	mutex_lock(&phy->pib_lock);
 
-	rc = phy->set_txpower(phy, txpower);
-	if (rc < 0) {
-		mutex_unlock(&phy->pib_lock);
-		goto out;
+	if (info->attrs[IEEE802154_ATTR_TXPOWER]) {
+		rc = phy_set_txpower(phy, info);
+		if (rc < 0)
+			goto error;
 	}
 
-	phy->transmit_power = txpower;
+	if (info->attrs[IEEE802154_ATTR_LBT_ENABLED]) {
+		rc = phy_set_lbt(phy, info);
+		if (rc < 0)
+			goto error;
+	}
 
 	mutex_unlock(&phy->pib_lock);
 
@@ -397,6 +429,8 @@ int ieee802154_set_phyparams(struct sk_buff *skb, struct genl_info *info)
 
 	return 0;
 
+error:
+	mutex_unlock(&phy->pib_lock);
 out:
 	wpan_phy_put(phy);
 	return rc;
diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c
index 90b1d0d2c14e..a09f6423a6e9 100644
--- a/net/ieee802154/nl_policy.c
+++ b/net/ieee802154/nl_policy.c
@@ -54,5 +54,6 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = {
 	[IEEE802154_ATTR_CHANNEL_PAGE_LIST] = { .len = 32 * 4, },
 
 	[IEEE802154_ATTR_TXPOWER] = { .type = NLA_S8, },
+	[IEEE802154_ATTR_LBT_ENABLED] = { .type = NLA_U8, },
 };
 
diff --git a/net/mac802154/ieee802154_dev.c b/net/mac802154/ieee802154_dev.c
index 9eb49e0886a4..56338c8cfc33 100644
--- a/net/mac802154/ieee802154_dev.c
+++ b/net/mac802154/ieee802154_dev.c
@@ -175,6 +175,16 @@ static int mac802154_set_txpower(struct wpan_phy *phy, int db)
 	return priv->ops->set_txpower(&priv->hw, db);
 }
 
+static int mac802154_set_lbt(struct wpan_phy *phy, bool on)
+{
+	struct mac802154_priv *priv = wpan_phy_priv(phy);
+
+	if (!priv->ops->set_lbt)
+		return -ENOTSUPP;
+
+	return priv->ops->set_lbt(&priv->hw, on);
+}
+
 struct ieee802154_dev *
 ieee802154_alloc_device(size_t priv_data_len, struct ieee802154_ops *ops)
 {
@@ -253,6 +263,7 @@ int ieee802154_register_device(struct ieee802154_dev *dev)
 	priv->phy->add_iface = mac802154_add_iface;
 	priv->phy->del_iface = mac802154_del_iface;
 	priv->phy->set_txpower = mac802154_set_txpower;
+	priv->phy->set_lbt = mac802154_set_lbt;
 
 	rc = wpan_phy_register(priv->phy);
 	if (rc < 0)
-- 
cgit v1.2.3


From ba08fea53a43e02b590d89224afdad976dece841 Mon Sep 17 00:00:00 2001
From: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Date: Mon, 17 Feb 2014 11:34:11 +0100
Subject: ieee802154: add support for CCA mode in wpan phys

The standard describes four modes of clear channel assesment: "energy
above threshold", "carrier found", and the logical and/or of these two.
Support for CCA mode setting is included in the at86rf230 driver,
predicated for RF212 chips.

Signed-off-by: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ieee802154/at86rf230.c |  9 +++++++++
 include/linux/nl802154.h           |  1 +
 include/net/mac802154.h            |  5 +++++
 include/net/wpan-phy.h             |  1 +
 net/ieee802154/nl-phy.c            | 32 +++++++++++++++++++++++++++++---
 net/ieee802154/nl_policy.c         |  1 +
 net/mac802154/ieee802154_dev.c     | 11 +++++++++++
 7 files changed, 57 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index 3d40c2350261..c60871aff333 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -794,6 +794,14 @@ at86rf212_set_lbt(struct ieee802154_dev *dev, bool on)
 	return at86rf230_write_subreg(lp, SR_CSMA_LBT_MODE, on);
 }
 
+static int
+at86rf212_set_cca_mode(struct ieee802154_dev *dev, u8 mode)
+{
+	struct at86rf230_local *lp = dev->priv;
+
+	return at86rf230_write_subreg(lp, SR_CCA_MODE, mode);
+}
+
 static struct ieee802154_ops at86rf230_ops = {
 	.owner = THIS_MODULE,
 	.xmit = at86rf230_xmit,
@@ -814,6 +822,7 @@ static struct ieee802154_ops at86rf212_ops = {
 	.set_hw_addr_filt = at86rf230_set_hw_addr_filt,
 	.set_txpower = at86rf212_set_txpower,
 	.set_lbt = at86rf212_set_lbt,
+	.set_cca_mode = at86rf212_set_cca_mode,
 };
 
 static void at86rf230_irqwork(struct work_struct *work)
diff --git a/include/linux/nl802154.h b/include/linux/nl802154.h
index 326baee227f7..5edefc14bd83 100644
--- a/include/linux/nl802154.h
+++ b/include/linux/nl802154.h
@@ -72,6 +72,7 @@ enum {
 
 	IEEE802154_ATTR_TXPOWER,
 	IEEE802154_ATTR_LBT_ENABLED,
+	IEEE802154_ATTR_CCA_MODE,
 
 	__IEEE802154_ATTR_MAX,
 };
diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 521edcb0e586..1a98e5014e66 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -122,6 +122,10 @@ struct ieee802154_dev {
  *	  Enables or disables listen before talk on the device. Called with
  *	  pib_lock held.
  *	  Returns either zero, or negative errno.
+ *
+ * set_cca_mode
+ *	  Sets the CCA mode used by the device. Called with pib_lock held.
+ *	  Returns either zero, or negative errno.
  */
 struct ieee802154_ops {
 	struct module	*owner;
@@ -140,6 +144,7 @@ struct ieee802154_ops {
 				     u8 addr[IEEE802154_ADDR_LEN]);
 	int		(*set_txpower)(struct ieee802154_dev *dev, int db);
 	int		(*set_lbt)(struct ieee802154_dev *dev, bool on);
+	int		(*set_cca_mode)(struct ieee802154_dev *dev, u8 mode);
 };
 
 /* Basic interface to register ieee802154 device */
diff --git a/include/net/wpan-phy.h b/include/net/wpan-phy.h
index 804e6c4f5f8a..03b59051972d 100644
--- a/include/net/wpan-phy.h
+++ b/include/net/wpan-phy.h
@@ -58,6 +58,7 @@ struct wpan_phy {
 
 	int (*set_txpower)(struct wpan_phy *phy, int db);
 	int (*set_lbt)(struct wpan_phy *phy, bool on);
+	int (*set_cca_mode)(struct wpan_phy *phy, u8 cca_mode);
 
 	char priv[0] __attribute__((__aligned__(NETDEV_ALIGN)));
 };
diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index f029310b0662..36f58d633868 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -57,7 +57,8 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 portid,
 	    nla_put_u8(msg, IEEE802154_ATTR_PAGE, phy->current_page) ||
 	    nla_put_u8(msg, IEEE802154_ATTR_CHANNEL, phy->current_channel) ||
 	    nla_put_s8(msg, IEEE802154_ATTR_TXPOWER, phy->transmit_power) ||
-	    nla_put_u8(msg, IEEE802154_ATTR_LBT_ENABLED, phy->lbt))
+	    nla_put_u8(msg, IEEE802154_ATTR_LBT_ENABLED, phy->lbt) ||
+	    nla_put_u8(msg, IEEE802154_ATTR_CCA_MODE, phy->cca_mode))
 		goto nla_put_failure;
 	for (i = 0; i < 32; i++) {
 		if (phy->channels_supported[i])
@@ -385,6 +386,23 @@ static int phy_set_lbt(struct wpan_phy *phy, struct genl_info *info)
 	return 0;
 }
 
+static int phy_set_cca_mode(struct wpan_phy *phy, struct genl_info *info)
+{
+	u8 mode = nla_get_u8(info->attrs[IEEE802154_ATTR_CCA_MODE]);
+	int rc;
+
+	if (mode > 3)
+		return -EINVAL;
+
+	rc = phy->set_cca_mode(phy, mode);
+	if (rc < 0)
+		return rc;
+
+	phy->cca_mode = mode;
+
+	return 0;
+}
+
 int ieee802154_set_phyparams(struct sk_buff *skb, struct genl_info *info)
 {
 	struct wpan_phy *phy;
@@ -394,7 +412,8 @@ int ieee802154_set_phyparams(struct sk_buff *skb, struct genl_info *info)
 	pr_debug("%s\n", __func__);
 
 	if (!info->attrs[IEEE802154_ATTR_PHY_NAME] &&
-	    !info->attrs[IEEE802154_ATTR_LBT_ENABLED])
+	    !info->attrs[IEEE802154_ATTR_LBT_ENABLED] &&
+	    !info->attrs[IEEE802154_ATTR_CCA_MODE])
 		return -EINVAL;
 
 	name = nla_data(info->attrs[IEEE802154_ATTR_PHY_NAME]);
@@ -406,7 +425,8 @@ int ieee802154_set_phyparams(struct sk_buff *skb, struct genl_info *info)
 		return -ENODEV;
 
 	if ((!phy->set_txpower && info->attrs[IEEE802154_ATTR_TXPOWER]) ||
-	    (!phy->set_lbt && info->attrs[IEEE802154_ATTR_LBT_ENABLED]))
+	    (!phy->set_lbt && info->attrs[IEEE802154_ATTR_LBT_ENABLED]) ||
+	    (!phy->set_cca_mode && info->attrs[IEEE802154_ATTR_CCA_MODE]))
 		goto out;
 
 	mutex_lock(&phy->pib_lock);
@@ -423,6 +443,12 @@ int ieee802154_set_phyparams(struct sk_buff *skb, struct genl_info *info)
 			goto error;
 	}
 
+	if (info->attrs[IEEE802154_ATTR_CCA_MODE]) {
+		rc = phy_set_cca_mode(phy, info);
+		if (rc < 0)
+			goto error;
+	}
+
 	mutex_unlock(&phy->pib_lock);
 
 	wpan_phy_put(phy);
diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c
index a09f6423a6e9..d87c2c904110 100644
--- a/net/ieee802154/nl_policy.c
+++ b/net/ieee802154/nl_policy.c
@@ -55,5 +55,6 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = {
 
 	[IEEE802154_ATTR_TXPOWER] = { .type = NLA_S8, },
 	[IEEE802154_ATTR_LBT_ENABLED] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_CCA_MODE] = { .type = NLA_U8, },
 };
 
diff --git a/net/mac802154/ieee802154_dev.c b/net/mac802154/ieee802154_dev.c
index 56338c8cfc33..4965e4ce6b5b 100644
--- a/net/mac802154/ieee802154_dev.c
+++ b/net/mac802154/ieee802154_dev.c
@@ -185,6 +185,16 @@ static int mac802154_set_lbt(struct wpan_phy *phy, bool on)
 	return priv->ops->set_lbt(&priv->hw, on);
 }
 
+static int mac802154_set_cca_mode(struct wpan_phy *phy, u8 mode)
+{
+	struct mac802154_priv *priv = wpan_phy_priv(phy);
+
+	if (!priv->ops->set_cca_mode)
+		return -ENOTSUPP;
+
+	return priv->ops->set_cca_mode(&priv->hw, mode);
+}
+
 struct ieee802154_dev *
 ieee802154_alloc_device(size_t priv_data_len, struct ieee802154_ops *ops)
 {
@@ -264,6 +274,7 @@ int ieee802154_register_device(struct ieee802154_dev *dev)
 	priv->phy->del_iface = mac802154_del_iface;
 	priv->phy->set_txpower = mac802154_set_txpower;
 	priv->phy->set_lbt = mac802154_set_lbt;
+	priv->phy->set_cca_mode = mac802154_set_cca_mode;
 
 	rc = wpan_phy_register(priv->phy);
 	if (rc < 0)
-- 
cgit v1.2.3


From 6ca001978dce0d50ebac01a38d6287f241a520c6 Mon Sep 17 00:00:00 2001
From: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Date: Mon, 17 Feb 2014 11:34:12 +0100
Subject: ieee802154: add support for setting CCA energy detection levels

Since three of the four clear channel assesment modes make use of energy
detection, provide an API to set the energy detection threshold.
Driver support for this is available in at86rf230 for the RF212 chips.
Since for these chips the minimal energy detection threshold depends on
page and channel used, add a field to struct at86rf230_local that stores
the minimal threshold. Actual ED thresholds are configured as offsets
from this value.

For RF212, setting the ED threshold will not work before a channel/page
has been set due to the dependency of energy detection in the chip and
the actual channel/page selected.

Signed-off-by: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ieee802154/at86rf230.c | 26 ++++++++++++++++++++++++--
 include/linux/nl802154.h           |  1 +
 include/net/mac802154.h            |  7 +++++++
 include/net/wpan-phy.h             |  2 ++
 net/ieee802154/nl-phy.c            | 30 +++++++++++++++++++++++++++---
 net/ieee802154/nl_policy.c         |  1 +
 net/mac802154/ieee802154_dev.c     | 11 +++++++++++
 7 files changed, 73 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index c60871aff333..20596be61028 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -52,6 +52,8 @@ struct at86rf230_local {
 	spinlock_t lock;
 	bool irq_busy;
 	bool is_tx;
+
+	int rssi_base_val;
 };
 
 static inline int is_rf212(struct at86rf230_local *local)
@@ -580,6 +582,8 @@ at86rf230_stop(struct ieee802154_dev *dev)
 static int
 at86rf230_set_channel(struct at86rf230_local *lp, int page, int channel)
 {
+	lp->rssi_base_val = -91;
+
 	return at86rf230_write_subreg(lp, SR_CHANNEL, channel);
 }
 
@@ -595,10 +599,13 @@ at86rf212_set_channel(struct at86rf230_local *lp, int page, int channel)
 	if (rc < 0)
 		return rc;
 
-	if (page == 0)
+	if (page == 0) {
 		rc = at86rf230_write_subreg(lp, SR_BPSK_QPSK, 0);
-	else
+		lp->rssi_base_val = -100;
+	} else {
 		rc = at86rf230_write_subreg(lp, SR_BPSK_QPSK, 1);
+		lp->rssi_base_val = -98;
+	}
 	if (rc < 0)
 		return rc;
 
@@ -802,6 +809,20 @@ at86rf212_set_cca_mode(struct ieee802154_dev *dev, u8 mode)
 	return at86rf230_write_subreg(lp, SR_CCA_MODE, mode);
 }
 
+static int
+at86rf212_set_cca_ed_level(struct ieee802154_dev *dev, s32 level)
+{
+	struct at86rf230_local *lp = dev->priv;
+	int desens_steps;
+
+	if (level < lp->rssi_base_val || level > 30)
+		return -EINVAL;
+
+	desens_steps = (level - lp->rssi_base_val) * 100 / 207;
+
+	return at86rf230_write_subreg(lp, SR_CCA_ED_THRES, desens_steps);
+}
+
 static struct ieee802154_ops at86rf230_ops = {
 	.owner = THIS_MODULE,
 	.xmit = at86rf230_xmit,
@@ -823,6 +844,7 @@ static struct ieee802154_ops at86rf212_ops = {
 	.set_txpower = at86rf212_set_txpower,
 	.set_lbt = at86rf212_set_lbt,
 	.set_cca_mode = at86rf212_set_cca_mode,
+	.set_cca_ed_level = at86rf212_set_cca_ed_level,
 };
 
 static void at86rf230_irqwork(struct work_struct *work)
diff --git a/include/linux/nl802154.h b/include/linux/nl802154.h
index 5edefc14bd83..0594a0ae71ba 100644
--- a/include/linux/nl802154.h
+++ b/include/linux/nl802154.h
@@ -73,6 +73,7 @@ enum {
 	IEEE802154_ATTR_TXPOWER,
 	IEEE802154_ATTR_LBT_ENABLED,
 	IEEE802154_ATTR_CCA_MODE,
+	IEEE802154_ATTR_CCA_ED_LEVEL,
 
 	__IEEE802154_ATTR_MAX,
 };
diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 1a98e5014e66..15fe6bca80f0 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -126,6 +126,11 @@ struct ieee802154_dev {
  * set_cca_mode
  *	  Sets the CCA mode used by the device. Called with pib_lock held.
  *	  Returns either zero, or negative errno.
+ *
+ * set_cca_ed_level
+ *	  Sets the CCA energy detection threshold in dBm. Called with pib_lock
+ *	  held.
+ *	  Returns either zero, or negative errno.
  */
 struct ieee802154_ops {
 	struct module	*owner;
@@ -145,6 +150,8 @@ struct ieee802154_ops {
 	int		(*set_txpower)(struct ieee802154_dev *dev, int db);
 	int		(*set_lbt)(struct ieee802154_dev *dev, bool on);
 	int		(*set_cca_mode)(struct ieee802154_dev *dev, u8 mode);
+	int		(*set_cca_ed_level)(struct ieee802154_dev *dev,
+					    s32 level);
 };
 
 /* Basic interface to register ieee802154 device */
diff --git a/include/net/wpan-phy.h b/include/net/wpan-phy.h
index 03b59051972d..0b570ad5e5fa 100644
--- a/include/net/wpan-phy.h
+++ b/include/net/wpan-phy.h
@@ -48,6 +48,7 @@ struct wpan_phy {
 	u8 cca_mode;
 
 	bool lbt;
+	s32 cca_ed_level;
 
 	struct device dev;
 	int idx;
@@ -59,6 +60,7 @@ struct wpan_phy {
 	int (*set_txpower)(struct wpan_phy *phy, int db);
 	int (*set_lbt)(struct wpan_phy *phy, bool on);
 	int (*set_cca_mode)(struct wpan_phy *phy, u8 cca_mode);
+	int (*set_cca_ed_level)(struct wpan_phy *phy, int level);
 
 	char priv[0] __attribute__((__aligned__(NETDEV_ALIGN)));
 };
diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index 36f58d633868..0af0d424dee0 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -58,7 +58,8 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 portid,
 	    nla_put_u8(msg, IEEE802154_ATTR_CHANNEL, phy->current_channel) ||
 	    nla_put_s8(msg, IEEE802154_ATTR_TXPOWER, phy->transmit_power) ||
 	    nla_put_u8(msg, IEEE802154_ATTR_LBT_ENABLED, phy->lbt) ||
-	    nla_put_u8(msg, IEEE802154_ATTR_CCA_MODE, phy->cca_mode))
+	    nla_put_u8(msg, IEEE802154_ATTR_CCA_MODE, phy->cca_mode) ||
+	    nla_put_s32(msg, IEEE802154_ATTR_CCA_ED_LEVEL, phy->cca_ed_level))
 		goto nla_put_failure;
 	for (i = 0; i < 32; i++) {
 		if (phy->channels_supported[i])
@@ -403,6 +404,20 @@ static int phy_set_cca_mode(struct wpan_phy *phy, struct genl_info *info)
 	return 0;
 }
 
+static int phy_set_cca_ed_level(struct wpan_phy *phy, struct genl_info *info)
+{
+	s32 level = nla_get_s32(info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]);
+	int rc;
+
+	rc = phy->set_cca_ed_level(phy, level);
+	if (rc < 0)
+		return rc;
+
+	phy->cca_ed_level = level;
+
+	return 0;
+}
+
 int ieee802154_set_phyparams(struct sk_buff *skb, struct genl_info *info)
 {
 	struct wpan_phy *phy;
@@ -413,7 +428,8 @@ int ieee802154_set_phyparams(struct sk_buff *skb, struct genl_info *info)
 
 	if (!info->attrs[IEEE802154_ATTR_PHY_NAME] &&
 	    !info->attrs[IEEE802154_ATTR_LBT_ENABLED] &&
-	    !info->attrs[IEEE802154_ATTR_CCA_MODE])
+	    !info->attrs[IEEE802154_ATTR_CCA_MODE] &&
+	    !info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL])
 		return -EINVAL;
 
 	name = nla_data(info->attrs[IEEE802154_ATTR_PHY_NAME]);
@@ -426,7 +442,9 @@ int ieee802154_set_phyparams(struct sk_buff *skb, struct genl_info *info)
 
 	if ((!phy->set_txpower && info->attrs[IEEE802154_ATTR_TXPOWER]) ||
 	    (!phy->set_lbt && info->attrs[IEEE802154_ATTR_LBT_ENABLED]) ||
-	    (!phy->set_cca_mode && info->attrs[IEEE802154_ATTR_CCA_MODE]))
+	    (!phy->set_cca_mode && info->attrs[IEEE802154_ATTR_CCA_MODE]) ||
+	    (!phy->set_cca_ed_level &&
+	     info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]))
 		goto out;
 
 	mutex_lock(&phy->pib_lock);
@@ -449,6 +467,12 @@ int ieee802154_set_phyparams(struct sk_buff *skb, struct genl_info *info)
 			goto error;
 	}
 
+	if (info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]) {
+		rc = phy_set_cca_ed_level(phy, info);
+		if (rc < 0)
+			goto error;
+	}
+
 	mutex_unlock(&phy->pib_lock);
 
 	wpan_phy_put(phy);
diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c
index d87c2c904110..55b5616295ff 100644
--- a/net/ieee802154/nl_policy.c
+++ b/net/ieee802154/nl_policy.c
@@ -56,5 +56,6 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = {
 	[IEEE802154_ATTR_TXPOWER] = { .type = NLA_S8, },
 	[IEEE802154_ATTR_LBT_ENABLED] = { .type = NLA_U8, },
 	[IEEE802154_ATTR_CCA_MODE] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_CCA_ED_LEVEL] = { .type = NLA_S32, },
 };
 
diff --git a/net/mac802154/ieee802154_dev.c b/net/mac802154/ieee802154_dev.c
index 4965e4ce6b5b..4707f36546d3 100644
--- a/net/mac802154/ieee802154_dev.c
+++ b/net/mac802154/ieee802154_dev.c
@@ -195,6 +195,16 @@ static int mac802154_set_cca_mode(struct wpan_phy *phy, u8 mode)
 	return priv->ops->set_cca_mode(&priv->hw, mode);
 }
 
+static int mac802154_set_cca_ed_level(struct wpan_phy *phy, s32 level)
+{
+	struct mac802154_priv *priv = wpan_phy_priv(phy);
+
+	if (!priv->ops->set_cca_ed_level)
+		return -ENOTSUPP;
+
+	return priv->ops->set_cca_ed_level(&priv->hw, level);
+}
+
 struct ieee802154_dev *
 ieee802154_alloc_device(size_t priv_data_len, struct ieee802154_ops *ops)
 {
@@ -275,6 +285,7 @@ int ieee802154_register_device(struct ieee802154_dev *dev)
 	priv->phy->set_txpower = mac802154_set_txpower;
 	priv->phy->set_lbt = mac802154_set_lbt;
 	priv->phy->set_cca_mode = mac802154_set_cca_mode;
+	priv->phy->set_cca_ed_level = mac802154_set_cca_ed_level;
 
 	rc = wpan_phy_register(priv->phy);
 	if (rc < 0)
-- 
cgit v1.2.3


From 4244db1b0b7bc9ab7b67d8c1c38de6cf15bc87a8 Mon Sep 17 00:00:00 2001
From: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Date: Mon, 17 Feb 2014 11:34:14 +0100
Subject: ieee802154: add netlink APIs for smartMAC configuration

Introduce new netlink attributes for SET_PHY_ATTRS:
 * CSMA minimal backoff exponent
 * CSMA maximal backoff exponent
 * CSMA retry limit
 * frame retransmission limit

The CSMA attributes shall correspond to minBE, maxBE and maxCSMABackoffs of
802.15.4, respectively. The frame retransmission shall correspond to
maxFrameRetries of 802.15.4, unless given as -1: then the old behaviour
of the stack shall apply. For RF2xy, the old behaviour is to not do
channel sensing at all and simply send *right now*, which is not
intended behaviour for most applications and actually prohibited for
some channel/page combinations.

For all values except frame retransmission limit, the defaults of
802.15.4 apply. Frame retransmission limits are set to -1 to indicate
backward-compatible behaviour.

Signed-off-by: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/nl802154.h       |  5 +++
 include/net/mac802154.h        | 12 ++++++++
 include/net/wpan-phy.h         |  7 +++++
 net/ieee802154/nl-phy.c        | 69 ++++++++++++++++++++++++++++++++++++++++--
 net/ieee802154/nl_policy.c     |  5 +++
 net/ieee802154/wpan-class.c    |  6 ++++
 net/mac802154/ieee802154_dev.c | 23 ++++++++++++++
 7 files changed, 125 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/nl802154.h b/include/linux/nl802154.h
index 0594a0ae71ba..e110b8c266f5 100644
--- a/include/linux/nl802154.h
+++ b/include/linux/nl802154.h
@@ -74,6 +74,11 @@ enum {
 	IEEE802154_ATTR_LBT_ENABLED,
 	IEEE802154_ATTR_CCA_MODE,
 	IEEE802154_ATTR_CCA_ED_LEVEL,
+	IEEE802154_ATTR_CSMA_RETRIES,
+	IEEE802154_ATTR_CSMA_MIN_BE,
+	IEEE802154_ATTR_CSMA_MAX_BE,
+
+	IEEE802154_ATTR_FRAME_RETRIES,
 
 	__IEEE802154_ATTR_MAX,
 };
diff --git a/include/net/mac802154.h b/include/net/mac802154.h
index 15fe6bca80f0..8ca3d04e7558 100644
--- a/include/net/mac802154.h
+++ b/include/net/mac802154.h
@@ -131,6 +131,14 @@ struct ieee802154_dev {
  *	  Sets the CCA energy detection threshold in dBm. Called with pib_lock
  *	  held.
  *	  Returns either zero, or negative errno.
+ *
+ * set_csma_params
+ *	  Sets the CSMA parameter set for the PHY. Called with pib_lock held.
+ *	  Returns either zero, or negative errno.
+ *
+ * set_frame_retries
+ *	  Sets the retransmission attempt limit. Called with pib_lock held.
+ *	  Returns either zero, or negative errno.
  */
 struct ieee802154_ops {
 	struct module	*owner;
@@ -152,6 +160,10 @@ struct ieee802154_ops {
 	int		(*set_cca_mode)(struct ieee802154_dev *dev, u8 mode);
 	int		(*set_cca_ed_level)(struct ieee802154_dev *dev,
 					    s32 level);
+	int		(*set_csma_params)(struct ieee802154_dev *dev,
+					   u8 min_be, u8 max_be, u8 retries);
+	int		(*set_frame_retries)(struct ieee802154_dev *dev,
+					     s8 retries);
 };
 
 /* Basic interface to register ieee802154 device */
diff --git a/include/net/wpan-phy.h b/include/net/wpan-phy.h
index 0b570ad5e5fa..10ab0fc6d4f7 100644
--- a/include/net/wpan-phy.h
+++ b/include/net/wpan-phy.h
@@ -46,6 +46,10 @@ struct wpan_phy {
 	u32 channels_supported[32];
 	s8 transmit_power;
 	u8 cca_mode;
+	u8 min_be;
+	u8 max_be;
+	u8 csma_retries;
+	s8 frame_retries;
 
 	bool lbt;
 	s32 cca_ed_level;
@@ -61,6 +65,9 @@ struct wpan_phy {
 	int (*set_lbt)(struct wpan_phy *phy, bool on);
 	int (*set_cca_mode)(struct wpan_phy *phy, u8 cca_mode);
 	int (*set_cca_ed_level)(struct wpan_phy *phy, int level);
+	int (*set_csma_params)(struct wpan_phy *phy, u8 min_be, u8 max_be,
+			       u8 retries);
+	int (*set_frame_retries)(struct wpan_phy *phy, s8 retries);
 
 	char priv[0] __attribute__((__aligned__(NETDEV_ALIGN)));
 };
diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index 0af0d424dee0..c9dfd6f59e34 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -59,7 +59,11 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 portid,
 	    nla_put_s8(msg, IEEE802154_ATTR_TXPOWER, phy->transmit_power) ||
 	    nla_put_u8(msg, IEEE802154_ATTR_LBT_ENABLED, phy->lbt) ||
 	    nla_put_u8(msg, IEEE802154_ATTR_CCA_MODE, phy->cca_mode) ||
-	    nla_put_s32(msg, IEEE802154_ATTR_CCA_ED_LEVEL, phy->cca_ed_level))
+	    nla_put_s32(msg, IEEE802154_ATTR_CCA_ED_LEVEL, phy->cca_ed_level) ||
+	    nla_put_u8(msg, IEEE802154_ATTR_CSMA_RETRIES, phy->csma_retries) ||
+	    nla_put_u8(msg, IEEE802154_ATTR_CSMA_MIN_BE, phy->min_be) ||
+	    nla_put_u8(msg, IEEE802154_ATTR_CSMA_MAX_BE, phy->max_be) ||
+	    nla_put_s8(msg, IEEE802154_ATTR_FRAME_RETRIES, phy->frame_retries))
 		goto nla_put_failure;
 	for (i = 0; i < 32; i++) {
 		if (phy->channels_supported[i])
@@ -418,6 +422,49 @@ static int phy_set_cca_ed_level(struct wpan_phy *phy, struct genl_info *info)
 	return 0;
 }
 
+static int phy_set_csma_params(struct wpan_phy *phy, struct genl_info *info)
+{
+	int rc;
+	u8 min_be = phy->min_be;
+	u8 max_be = phy->max_be;
+	u8 retries = phy->csma_retries;
+
+	if (info->attrs[IEEE802154_ATTR_CSMA_RETRIES])
+		retries = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_RETRIES]);
+	if (info->attrs[IEEE802154_ATTR_CSMA_MIN_BE])
+		min_be = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_MIN_BE]);
+	if (info->attrs[IEEE802154_ATTR_CSMA_MAX_BE])
+		max_be = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_MAX_BE]);
+
+	if (retries > 5 || max_be > 8 || min_be > max_be ||
+	    retries < -1 || retries > 7)
+		return -EINVAL;
+
+	rc = phy->set_csma_params(phy, min_be, max_be, retries);
+	if (rc < 0)
+		return rc;
+
+	phy->min_be = min_be;
+	phy->max_be = max_be;
+	phy->csma_retries = retries;
+
+	return 0;
+}
+
+static int phy_set_frame_retries(struct wpan_phy *phy, struct genl_info *info)
+{
+	s8 retries = nla_get_s8(info->attrs[IEEE802154_ATTR_FRAME_RETRIES]);
+	int rc;
+
+	rc = phy->set_frame_retries(phy, retries);
+	if (rc < 0)
+		return rc;
+
+	phy->frame_retries = retries;
+
+	return 0;
+}
+
 int ieee802154_set_phyparams(struct sk_buff *skb, struct genl_info *info)
 {
 	struct wpan_phy *phy;
@@ -429,7 +476,11 @@ int ieee802154_set_phyparams(struct sk_buff *skb, struct genl_info *info)
 	if (!info->attrs[IEEE802154_ATTR_PHY_NAME] &&
 	    !info->attrs[IEEE802154_ATTR_LBT_ENABLED] &&
 	    !info->attrs[IEEE802154_ATTR_CCA_MODE] &&
-	    !info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL])
+	    !info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL] &&
+	    !info->attrs[IEEE802154_ATTR_CSMA_RETRIES] &&
+	    !info->attrs[IEEE802154_ATTR_CSMA_MIN_BE] &&
+	    !info->attrs[IEEE802154_ATTR_CSMA_MAX_BE] &&
+	    !info->attrs[IEEE802154_ATTR_FRAME_RETRIES])
 		return -EINVAL;
 
 	name = nla_data(info->attrs[IEEE802154_ATTR_PHY_NAME]);
@@ -473,6 +524,20 @@ int ieee802154_set_phyparams(struct sk_buff *skb, struct genl_info *info)
 			goto error;
 	}
 
+	if (info->attrs[IEEE802154_ATTR_CSMA_RETRIES] ||
+	    info->attrs[IEEE802154_ATTR_CSMA_MIN_BE] ||
+	    info->attrs[IEEE802154_ATTR_CSMA_MAX_BE]) {
+		rc = phy_set_csma_params(phy, info);
+		if (rc < 0)
+			goto error;
+	}
+
+	if (info->attrs[IEEE802154_ATTR_FRAME_RETRIES]) {
+		rc = phy_set_frame_retries(phy, info);
+		if (rc < 0)
+			goto error;
+	}
+
 	mutex_unlock(&phy->pib_lock);
 
 	wpan_phy_put(phy);
diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c
index 55b5616295ff..fd7be5e45cef 100644
--- a/net/ieee802154/nl_policy.c
+++ b/net/ieee802154/nl_policy.c
@@ -57,5 +57,10 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = {
 	[IEEE802154_ATTR_LBT_ENABLED] = { .type = NLA_U8, },
 	[IEEE802154_ATTR_CCA_MODE] = { .type = NLA_U8, },
 	[IEEE802154_ATTR_CCA_ED_LEVEL] = { .type = NLA_S32, },
+	[IEEE802154_ATTR_CSMA_RETRIES] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_CSMA_MIN_BE] = { .type = NLA_U8, },
+	[IEEE802154_ATTR_CSMA_MAX_BE] = { .type = NLA_U8, },
+
+	[IEEE802154_ATTR_FRAME_RETRIES] = { .type = NLA_S8, },
 };
 
diff --git a/net/ieee802154/wpan-class.c b/net/ieee802154/wpan-class.c
index 8d6f6704da84..edd0962d55f9 100644
--- a/net/ieee802154/wpan-class.c
+++ b/net/ieee802154/wpan-class.c
@@ -169,6 +169,12 @@ struct wpan_phy *wpan_phy_alloc(size_t priv_size)
 	phy->current_channel = -1; /* not initialised */
 	phy->current_page = 0; /* for compatibility */
 
+	/* defaults per 802.15.4-2011 */
+	phy->min_be = 3;
+	phy->max_be = 5;
+	phy->csma_retries = 4;
+	phy->frame_retries = -1; /* for compatibility, actual default is 3 */
+
 	return phy;
 
 out:
diff --git a/net/mac802154/ieee802154_dev.c b/net/mac802154/ieee802154_dev.c
index 4707f36546d3..b75bb01e5c6b 100644
--- a/net/mac802154/ieee802154_dev.c
+++ b/net/mac802154/ieee802154_dev.c
@@ -205,6 +205,27 @@ static int mac802154_set_cca_ed_level(struct wpan_phy *phy, s32 level)
 	return priv->ops->set_cca_ed_level(&priv->hw, level);
 }
 
+static int mac802154_set_csma_params(struct wpan_phy *phy, u8 min_be,
+				     u8 max_be, u8 retries)
+{
+	struct mac802154_priv *priv = wpan_phy_priv(phy);
+
+	if (!priv->ops->set_csma_params)
+		return -ENOTSUPP;
+
+	return priv->ops->set_csma_params(&priv->hw, min_be, max_be, retries);
+}
+
+static int mac802154_set_frame_retries(struct wpan_phy *phy, s8 retries)
+{
+	struct mac802154_priv *priv = wpan_phy_priv(phy);
+
+	if (!priv->ops->set_frame_retries)
+		return -ENOTSUPP;
+
+	return priv->ops->set_frame_retries(&priv->hw, retries);
+}
+
 struct ieee802154_dev *
 ieee802154_alloc_device(size_t priv_data_len, struct ieee802154_ops *ops)
 {
@@ -286,6 +307,8 @@ int ieee802154_register_device(struct ieee802154_dev *dev)
 	priv->phy->set_lbt = mac802154_set_lbt;
 	priv->phy->set_cca_mode = mac802154_set_cca_mode;
 	priv->phy->set_cca_ed_level = mac802154_set_cca_ed_level;
+	priv->phy->set_csma_params = mac802154_set_csma_params;
+	priv->phy->set_frame_retries = mac802154_set_frame_retries;
 
 	rc = wpan_phy_register(priv->phy);
 	if (rc < 0)
-- 
cgit v1.2.3


From 5befdc385ddb2d5ae8995ad89004529a3acf58fc Mon Sep 17 00:00:00 2001
From: Takuya Yoshikawa <yoshikawa_takuya_b1@lab.ntt.co.jp>
Date: Tue, 18 Feb 2014 17:22:47 +0900
Subject: KVM: Simplify kvm->tlbs_dirty handling

When this was introduced, kvm_flush_remote_tlbs() could be called
without holding mmu_lock.  It is now acknowledged that the function
must be called before releasing mmu_lock, and all callers have already
been changed to do so.

There is no need to use smp_mb() and cmpxchg() any more.

Signed-off-by: Takuya Yoshikawa <yoshikawa_takuya_b1@lab.ntt.co.jp>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/paging_tmpl.h | 7 ++++---
 include/linux/kvm_host.h   | 4 +++-
 virt/kvm/kvm_main.c        | 5 +----
 3 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index cba218a2f08d..b1e6c1bf68d3 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -913,7 +913,8 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
  *   and kvm_mmu_notifier_invalidate_range_start detect the mapping page isn't
  *   used by guest then tlbs are not flushed, so guest is allowed to access the
  *   freed pages.
- *   And we increase kvm->tlbs_dirty to delay tlbs flush in this case.
+ *   We set tlbs_dirty to let the notifier know this change and delay the flush
+ *   until such a case actually happens.
  */
 static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 {
@@ -942,7 +943,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 			return -EINVAL;
 
 		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
-			vcpu->kvm->tlbs_dirty++;
+			vcpu->kvm->tlbs_dirty = true;
 			continue;
 		}
 
@@ -957,7 +958,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 
 		if (gfn != sp->gfns[i]) {
 			drop_spte(vcpu->kvm, &sp->spt[i]);
-			vcpu->kvm->tlbs_dirty++;
+			vcpu->kvm->tlbs_dirty = true;
 			continue;
 		}
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index f5937b8188b4..9816b68b085f 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -401,7 +401,9 @@ struct kvm {
 	unsigned long mmu_notifier_seq;
 	long mmu_notifier_count;
 #endif
-	long tlbs_dirty;
+	/* Protected by mmu_lock */
+	bool tlbs_dirty;
+
 	struct list_head devices;
 };
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index a9e999a48e43..f5668a431d54 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -186,12 +186,9 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
 
 void kvm_flush_remote_tlbs(struct kvm *kvm)
 {
-	long dirty_count = kvm->tlbs_dirty;
-
-	smp_mb();
 	if (make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
 		++kvm->stat.remote_tlb_flush;
-	cmpxchg(&kvm->tlbs_dirty, dirty_count, 0);
+	kvm->tlbs_dirty = false;
 }
 EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
 
-- 
cgit v1.2.3


From b075dd40c95d11c2c8690f6c4d6232fc0d9e7f56 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Tue, 18 Feb 2014 02:19:26 -0300
Subject: Bluetooth: allocate static minor for vhci

Commit bfacbb9 (Bluetooth: Use devname:vhci module alias for virtual HCI
driver) added the module alias to hci_vhci module so it's possible to
create the /dev/vhci node. However creating an alias without
specifying the minor doesn't allow us to create the node ahead,
triggerring module auto-load when it's first accessed.

Starting with depmod from kmod 16 we started to warn if there's a
devname alias without specifying the major and minor.

Let's do the same done for uhid, kvm, fuse and others, specifying a
fixed minor. In systems with systemd as the init the following will
happen: on early boot systemd will call "kmod static-nodes" to read
/lib/modules/$(uname -r)/modules.devname and then create the nodes. When
first accessed these "dead" nodes will trigger the module loading.

Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 Documentation/devices.txt    | 1 +
 drivers/bluetooth/hci_vhci.c | 3 ++-
 include/linux/miscdevice.h   | 1 +
 3 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/Documentation/devices.txt b/Documentation/devices.txt
index 10378cc48374..04356f5bc3af 100644
--- a/Documentation/devices.txt
+++ b/Documentation/devices.txt
@@ -353,6 +353,7 @@ Your cooperation is appreciated.
 		133 = /dev/exttrp	External device trap
 		134 = /dev/apm_bios	Advanced Power Management BIOS
 		135 = /dev/rtc		Real Time Clock
+		137 = /dev/vhci		Bluetooth virtual HCI driver
 		139 = /dev/openprom	SPARC OpenBoot PROM
 		140 = /dev/relay8	Berkshire Products Octal relay card
 		141 = /dev/relay16	Berkshire Products ISO-16 relay card
diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c
index 1ef6990a5c7e..add1c6a72063 100644
--- a/drivers/bluetooth/hci_vhci.c
+++ b/drivers/bluetooth/hci_vhci.c
@@ -359,7 +359,7 @@ static const struct file_operations vhci_fops = {
 static struct miscdevice vhci_miscdev= {
 	.name	= "vhci",
 	.fops	= &vhci_fops,
-	.minor	= MISC_DYNAMIC_MINOR,
+	.minor	= VHCI_MINOR,
 };
 
 static int __init vhci_init(void)
@@ -385,3 +385,4 @@ MODULE_DESCRIPTION("Bluetooth virtual HCI driver ver " VERSION);
 MODULE_VERSION(VERSION);
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("devname:vhci");
+MODULE_ALIAS_MISCDEV(VHCI_MINOR);
diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h
index 3737f7218f51..7bb6148d990f 100644
--- a/include/linux/miscdevice.h
+++ b/include/linux/miscdevice.h
@@ -23,6 +23,7 @@
 #define TEMP_MINOR		131	/* Temperature Sensor */
 #define RTC_MINOR		135
 #define EFI_RTC_MINOR		136	/* EFI Time services */
+#define VHCI_MINOR		137
 #define SUN_OPENPROM_MINOR	139
 #define DMAPI_MINOR		140	/* DMAPI */
 #define NVRAM_MINOR		144
-- 
cgit v1.2.3


From 01325476d6e46185031be4a9bc6443832dbc807c Mon Sep 17 00:00:00 2001
From: "K. Y. Srinivasan" <kys@microsoft.com>
Date: Sun, 16 Feb 2014 11:34:30 -0800
Subject: Drivers: hv: Implement the file copy service

Implement the file copy service for Linux guests on Hyper-V. This permits the
host to copy a file (over VMBUS) into the guest. This facility is part of
"guest integration services" supported on the Windows platform.
Here is a link that provides additional details on this functionality:

http://technet.microsoft.com/en-us/library/dn464282.aspx

In V1 version of the patch I have addressed comments from
Olaf Hering <olaf@aepfle.de> and Dan Carpenter <dan.carpenter@oracle.com>

In V2 version of this patch I did some minor cleanup (making some globals
static). In V4 version of the patch I have addressed all of Olaf's
most recent set of comments/concerns.

In V5 version of the patch I had addressed Greg's most recent comments.
I would like to thank Greg for suggesting that I use misc device; it has
significantly simplified the code.

In V6 version of the patch I have cleaned up error message based on Olaf's
comments. I have also rebased the patch based on the current tip.

In this version of the patch, I have addressed the latest comments from Greg.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hv/Makefile         |   2 +-
 drivers/hv/hv_fcopy.c       | 414 ++++++++++++++++++++++++++++++++++++++++++++
 drivers/hv/hv_util.c        |  11 ++
 drivers/hv/hyperv_vmbus.h   |   4 +
 include/linux/hyperv.h      |  12 +-
 include/uapi/linux/hyperv.h |  46 +++++
 tools/hv/hv_fcopy_daemon.c  | 195 +++++++++++++++++++++
 7 files changed, 682 insertions(+), 2 deletions(-)
 create mode 100644 drivers/hv/hv_fcopy.c
 create mode 100644 tools/hv/hv_fcopy_daemon.c

(limited to 'include/linux')

diff --git a/drivers/hv/Makefile b/drivers/hv/Makefile
index 0a74b5661186..5e4dfa4cfe22 100644
--- a/drivers/hv/Makefile
+++ b/drivers/hv/Makefile
@@ -5,4 +5,4 @@ obj-$(CONFIG_HYPERV_BALLOON)	+= hv_balloon.o
 hv_vmbus-y := vmbus_drv.o \
 		 hv.o connection.o channel.o \
 		 channel_mgmt.o ring_buffer.o
-hv_utils-y := hv_util.o hv_kvp.o hv_snapshot.o
+hv_utils-y := hv_util.o hv_kvp.o hv_snapshot.o hv_fcopy.o
diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c
new file mode 100644
index 000000000000..285b5e210a09
--- /dev/null
+++ b/drivers/hv/hv_fcopy.c
@@ -0,0 +1,414 @@
+/*
+ * An implementation of file copy service.
+ *
+ * Copyright (C) 2014, Microsoft, Inc.
+ *
+ * Author : K. Y. Srinivasan <ksrinivasan@novell.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/semaphore.h>
+#include <linux/fs.h>
+#include <linux/nls.h>
+#include <linux/workqueue.h>
+#include <linux/cdev.h>
+#include <linux/hyperv.h>
+#include <linux/sched.h>
+#include <linux/uaccess.h>
+#include <linux/miscdevice.h>
+
+#include "hyperv_vmbus.h"
+
+#define WIN8_SRV_MAJOR		1
+#define WIN8_SRV_MINOR		1
+#define WIN8_SRV_VERSION	(WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR)
+
+/*
+ * Global state maintained for transaction that is being processed.
+ * For a class of integration services, including the "file copy service",
+ * the specified protocol is a "request/response" protocol which means that
+ * there can only be single outstanding transaction from the host at any
+ * given point in time. We use this to simplify memory management in this
+ * driver - we cache and process only one message at a time.
+ *
+ * While the request/response protocol is guaranteed by the host, we further
+ * ensure this by serializing packet processing in this driver - we do not
+ * read additional packets from the VMBUs until the current packet is fully
+ * handled.
+ *
+ * The transaction "active" state is set when we receive a request from the
+ * host and we cleanup this state when the transaction is completed - when we
+ * respond to the host with our response. When the transaction active state is
+ * set, we defer handling incoming packets.
+ */
+
+static struct {
+	bool active; /* transaction status - active or not */
+	int recv_len; /* number of bytes received. */
+	struct hv_fcopy_hdr  *fcopy_msg; /* current message */
+	struct hv_start_fcopy  message; /*  sent to daemon */
+	struct vmbus_channel *recv_channel; /* chn we got the request */
+	u64 recv_req_id; /* request ID. */
+	void *fcopy_context; /* for the channel callback */
+	struct semaphore read_sema;
+} fcopy_transaction;
+
+static bool opened; /* currently device opened */
+
+/*
+ * Before we can accept copy messages from the host, we need
+ * to handshake with the user level daemon. This state tracks
+ * if we are in the handshake phase.
+ */
+static bool in_hand_shake = true;
+static void fcopy_send_data(void);
+static void fcopy_respond_to_host(int error);
+static void fcopy_work_func(struct work_struct *dummy);
+static DECLARE_DELAYED_WORK(fcopy_work, fcopy_work_func);
+static u8 *recv_buffer;
+
+static void fcopy_work_func(struct work_struct *dummy)
+{
+	/*
+	 * If the timer fires, the user-mode component has not responded;
+	 * process the pending transaction.
+	 */
+	fcopy_respond_to_host(HV_E_FAIL);
+}
+
+static int fcopy_handle_handshake(u32 version)
+{
+	switch (version) {
+	case FCOPY_CURRENT_VERSION:
+		break;
+	default:
+		/*
+		 * For now we will fail the registration.
+		 * If and when we have multiple versions to
+		 * deal with, we will be backward compatible.
+		 * We will add this code when needed.
+		 */
+		return -EINVAL;
+	}
+	pr_info("FCP: user-mode registering done. Daemon version: %d\n",
+		version);
+	fcopy_transaction.active = false;
+	if (fcopy_transaction.fcopy_context)
+		hv_fcopy_onchannelcallback(fcopy_transaction.fcopy_context);
+	in_hand_shake = false;
+	return 0;
+}
+
+static void fcopy_send_data(void)
+{
+	struct hv_start_fcopy *smsg_out = &fcopy_transaction.message;
+	int operation = fcopy_transaction.fcopy_msg->operation;
+	struct hv_start_fcopy *smsg_in;
+
+	/*
+	 * The  strings sent from the host are encoded in
+	 * in utf16; convert it to utf8 strings.
+	 * The host assures us that the utf16 strings will not exceed
+	 * the max lengths specified. We will however, reserve room
+	 * for the string terminating character - in the utf16s_utf8s()
+	 * function we limit the size of the buffer where the converted
+	 * string is placed to W_MAX_PATH -1 to guarantee
+	 * that the strings can be properly terminated!
+	 */
+
+	switch (operation) {
+	case START_FILE_COPY:
+		memset(smsg_out, 0, sizeof(struct hv_start_fcopy));
+		smsg_out->hdr.operation = operation;
+		smsg_in = (struct hv_start_fcopy *)fcopy_transaction.fcopy_msg;
+
+		utf16s_to_utf8s((wchar_t *)smsg_in->file_name, W_MAX_PATH,
+				UTF16_LITTLE_ENDIAN,
+				(__u8 *)smsg_out->file_name, W_MAX_PATH - 1);
+
+		utf16s_to_utf8s((wchar_t *)smsg_in->path_name, W_MAX_PATH,
+				UTF16_LITTLE_ENDIAN,
+				(__u8 *)smsg_out->path_name, W_MAX_PATH - 1);
+
+		smsg_out->copy_flags = smsg_in->copy_flags;
+		smsg_out->file_size = smsg_in->file_size;
+		break;
+
+	default:
+		break;
+	}
+	up(&fcopy_transaction.read_sema);
+	return;
+}
+
+/*
+ * Send a response back to the host.
+ */
+
+static void
+fcopy_respond_to_host(int error)
+{
+	struct icmsg_hdr *icmsghdr;
+	u32 buf_len;
+	struct vmbus_channel *channel;
+	u64 req_id;
+
+	/*
+	 * Copy the global state for completing the transaction. Note that
+	 * only one transaction can be active at a time. This is guaranteed
+	 * by the file copy protocol implemented by the host. Furthermore,
+	 * the "transaction active" state we maintain ensures that there can
+	 * only be one active transaction at a time.
+	 */
+
+	buf_len = fcopy_transaction.recv_len;
+	channel = fcopy_transaction.recv_channel;
+	req_id = fcopy_transaction.recv_req_id;
+
+	fcopy_transaction.active = false;
+
+	icmsghdr = (struct icmsg_hdr *)
+			&recv_buffer[sizeof(struct vmbuspipe_hdr)];
+
+	if (channel->onchannel_callback == NULL)
+		/*
+		 * We have raced with util driver being unloaded;
+		 * silently return.
+		 */
+		return;
+
+	icmsghdr->status = error;
+	icmsghdr->icflags = ICMSGHDRFLAG_TRANSACTION | ICMSGHDRFLAG_RESPONSE;
+	vmbus_sendpacket(channel, recv_buffer, buf_len, req_id,
+				VM_PKT_DATA_INBAND, 0);
+}
+
+void hv_fcopy_onchannelcallback(void *context)
+{
+	struct vmbus_channel *channel = context;
+	u32 recvlen;
+	u64 requestid;
+	struct hv_fcopy_hdr *fcopy_msg;
+	struct icmsg_hdr *icmsghdr;
+	struct icmsg_negotiate *negop = NULL;
+	int util_fw_version;
+	int fcopy_srv_version;
+
+	if (fcopy_transaction.active) {
+		/*
+		 * We will defer processing this callback once
+		 * the current transaction is complete.
+		 */
+		fcopy_transaction.fcopy_context = context;
+		return;
+	}
+
+	vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 2, &recvlen,
+			 &requestid);
+	if (recvlen <= 0)
+		return;
+
+	icmsghdr = (struct icmsg_hdr *)&recv_buffer[
+			sizeof(struct vmbuspipe_hdr)];
+	if (icmsghdr->icmsgtype == ICMSGTYPE_NEGOTIATE) {
+		util_fw_version = UTIL_FW_VERSION;
+		fcopy_srv_version = WIN8_SRV_VERSION;
+		vmbus_prep_negotiate_resp(icmsghdr, negop, recv_buffer,
+				util_fw_version, fcopy_srv_version);
+	} else {
+		fcopy_msg = (struct hv_fcopy_hdr *)&recv_buffer[
+				sizeof(struct vmbuspipe_hdr) +
+				sizeof(struct icmsg_hdr)];
+
+		/*
+		 * Stash away this global state for completing the
+		 * transaction; note transactions are serialized.
+		 */
+
+		fcopy_transaction.active = true;
+		fcopy_transaction.recv_len = recvlen;
+		fcopy_transaction.recv_channel = channel;
+		fcopy_transaction.recv_req_id = requestid;
+		fcopy_transaction.fcopy_msg = fcopy_msg;
+
+		/*
+		 * Send the information to the user-level daemon.
+		 */
+		fcopy_send_data();
+		schedule_delayed_work(&fcopy_work, 5*HZ);
+		return;
+	}
+	icmsghdr->icflags = ICMSGHDRFLAG_TRANSACTION | ICMSGHDRFLAG_RESPONSE;
+	vmbus_sendpacket(channel, recv_buffer, recvlen, requestid,
+			VM_PKT_DATA_INBAND, 0);
+}
+
+/*
+ * Create a char device that can support read/write for passing
+ * the payload.
+ */
+
+static ssize_t fcopy_read(struct file *file, char __user *buf,
+		size_t count, loff_t *ppos)
+{
+	void *src;
+	size_t copy_size;
+	int operation;
+
+	/*
+	 * Wait until there is something to be read.
+	 */
+	if (down_interruptible(&fcopy_transaction.read_sema))
+		return -EINTR;
+
+	/*
+	 * The channel may be rescinded and in this case, we will wakeup the
+	 * the thread blocked on the semaphore and we will use the opened
+	 * state to correctly handle this case.
+	 */
+	if (!opened)
+		return -ENODEV;
+
+	operation = fcopy_transaction.fcopy_msg->operation;
+
+	if (operation == START_FILE_COPY) {
+		src = &fcopy_transaction.message;
+		copy_size = sizeof(struct hv_start_fcopy);
+		if (count < copy_size)
+			return 0;
+	} else {
+		src = fcopy_transaction.fcopy_msg;
+		copy_size = sizeof(struct hv_do_fcopy);
+		if (count < copy_size)
+			return 0;
+	}
+	if (copy_to_user(buf, src, copy_size))
+		return -EFAULT;
+
+	return copy_size;
+}
+
+static ssize_t fcopy_write(struct file *file, const char __user *buf,
+			size_t count, loff_t *ppos)
+{
+	int response = 0;
+
+	if (count != sizeof(int))
+		return -EINVAL;
+
+	if (copy_from_user(&response, buf, sizeof(int)))
+		return -EFAULT;
+
+	if (in_hand_shake) {
+		if (fcopy_handle_handshake(response))
+			return -EINVAL;
+		return sizeof(int);
+	}
+
+	/*
+	 * Complete the transaction by forwarding the result
+	 * to the host. But first, cancel the timeout.
+	 */
+	if (cancel_delayed_work_sync(&fcopy_work))
+		fcopy_respond_to_host(response);
+
+	return sizeof(int);
+}
+
+int fcopy_open(struct inode *inode, struct file *f)
+{
+	/*
+	 * The user level daemon that will open this device is
+	 * really an extension of this driver. We can have only
+	 * active open at a time.
+	 */
+	if (opened)
+		return -EBUSY;
+
+	/*
+	 * The daemon is alive; setup the state.
+	 */
+	opened = true;
+	return 0;
+}
+
+int fcopy_release(struct inode *inode, struct file *f)
+{
+	/*
+	 * The daemon has exited; reset the state.
+	 */
+	in_hand_shake = true;
+	opened = false;
+	return 0;
+}
+
+
+static const struct file_operations fcopy_fops = {
+	.read           = fcopy_read,
+	.write          = fcopy_write,
+	.release	= fcopy_release,
+	.open		= fcopy_open,
+};
+
+static struct miscdevice fcopy_misc = {
+	.minor          = MISC_DYNAMIC_MINOR,
+	.name           = "vmbus/hv_fcopy",
+	.fops           = &fcopy_fops,
+};
+
+static int fcopy_dev_init(void)
+{
+	return misc_register(&fcopy_misc);
+}
+
+static void fcopy_dev_deinit(void)
+{
+
+	/*
+	 * The device is going away - perhaps because the
+	 * host has rescinded the channel. Setup state so that
+	 * user level daemon can gracefully exit if it is blocked
+	 * on the read semaphore.
+	 */
+	opened = false;
+	/*
+	 * Signal the semaphore as the device is
+	 * going away.
+	 */
+	up(&fcopy_transaction.read_sema);
+	misc_deregister(&fcopy_misc);
+}
+
+int hv_fcopy_init(struct hv_util_service *srv)
+{
+	recv_buffer = srv->recv_buffer;
+
+	/*
+	 * When this driver loads, the user level daemon that
+	 * processes the host requests may not yet be running.
+	 * Defer processing channel callbacks until the daemon
+	 * has registered.
+	 */
+	fcopy_transaction.active = true;
+	sema_init(&fcopy_transaction.read_sema, 0);
+
+	return fcopy_dev_init();
+}
+
+void hv_fcopy_deinit(void)
+{
+	cancel_delayed_work_sync(&fcopy_work);
+	fcopy_dev_deinit();
+}
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 62dfd246b948..dd761806f0e8 100644
--- a/drivers/hv/hv_util.c
+++ b/drivers/hv/hv_util.c
@@ -28,6 +28,7 @@
 #include <linux/reboot.h>
 #include <linux/hyperv.h>
 
+#include "hyperv_vmbus.h"
 
 #define SD_MAJOR	3
 #define SD_MINOR	0
@@ -82,6 +83,12 @@ static struct hv_util_service util_vss = {
 	.util_deinit = hv_vss_deinit,
 };
 
+static struct hv_util_service util_fcopy = {
+	.util_cb = hv_fcopy_onchannelcallback,
+	.util_init = hv_fcopy_init,
+	.util_deinit = hv_fcopy_deinit,
+};
+
 static void perform_shutdown(struct work_struct *dummy)
 {
 	orderly_poweroff(true);
@@ -401,6 +408,10 @@ static const struct hv_vmbus_device_id id_table[] = {
 	{ HV_VSS_GUID,
 	  .driver_data = (unsigned long)&util_vss
 	},
+	/* File copy GUID */
+	{ HV_FCOPY_GUID,
+	  .driver_data = (unsigned long)&util_fcopy
+	},
 	{ },
 };
 
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 1544609881fe..860134da8039 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -669,5 +669,9 @@ int vmbus_set_event(struct vmbus_channel *channel);
 
 void vmbus_on_event(unsigned long data);
 
+int hv_fcopy_init(struct hv_util_service *);
+void hv_fcopy_deinit(void);
+void hv_fcopy_onchannelcallback(void *);
+
 
 #endif /* _HYPERV_VMBUS_H */
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index fb66fba368d7..62ea1a06836a 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -30,7 +30,6 @@
 #include <linux/types.h>
 #include <linux/scatterlist.h>
 #include <linux/list.h>
-#include <linux/uuid.h>
 #include <linux/timer.h>
 #include <linux/workqueue.h>
 #include <linux/completion.h>
@@ -1049,6 +1048,17 @@ void vmbus_driver_unregister(struct hv_driver *hv_driver);
 			0xB7, 0x6B, 0x6F, 0xD0, 0xBE, 0x52, 0x8C, 0xDA \
 		}
 
+/*
+ * Guest File Copy Service
+ * {34D14BE3-DEE4-41c8-9AE7-6B174977C192}
+ */
+
+#define HV_FCOPY_GUID \
+	.guid = { \
+			0xE3, 0x4B, 0xD1, 0x34, 0xE4, 0xDE, 0xC8, 0x41, \
+			0x9A, 0xE7, 0x6B, 0x17, 0x49, 0x77, 0xC1, 0x92 \
+		}
+
 /*
  * Common header for Hyper-V ICs
  */
diff --git a/include/uapi/linux/hyperv.h b/include/uapi/linux/hyperv.h
index 1861f8e2ce2b..9beb7c991638 100644
--- a/include/uapi/linux/hyperv.h
+++ b/include/uapi/linux/hyperv.h
@@ -25,6 +25,8 @@
 #ifndef _UAPI_HYPERV_H
 #define _UAPI_HYPERV_H
 
+#include <linux/uuid.h>
+
 /*
  * Framework version for util services.
  */
@@ -93,6 +95,50 @@ struct hv_vss_msg {
 	};
 } __attribute__((packed));
 
+/*
+ * Implementation of a host to guest copy facility.
+ */
+
+#define FCOPY_VERSION_0 0
+#define FCOPY_CURRENT_VERSION FCOPY_VERSION_0
+#define W_MAX_PATH 260
+
+enum hv_fcopy_op {
+	START_FILE_COPY = 0,
+	WRITE_TO_FILE,
+	COMPLETE_FCOPY,
+	CANCEL_FCOPY,
+};
+
+struct hv_fcopy_hdr {
+	__u32 operation;
+	uuid_le service_id0; /* currently unused */
+	uuid_le service_id1; /* currently unused */
+} __attribute__((packed));
+
+#define OVER_WRITE	0x1
+#define CREATE_PATH	0x2
+
+struct hv_start_fcopy {
+	struct hv_fcopy_hdr hdr;
+	__u16 file_name[W_MAX_PATH];
+	__u16 path_name[W_MAX_PATH];
+	__u32 copy_flags;
+	__u64 file_size;
+} __attribute__((packed));
+
+/*
+ * The file is chunked into fragments.
+ */
+#define DATA_FRAGMENT	(6 * 1024)
+
+struct hv_do_fcopy {
+	struct hv_fcopy_hdr hdr;
+	__u64	offset;
+	__u32	size;
+	__u8	data[DATA_FRAGMENT];
+};
+
 /*
  * An implementation of HyperV key value pair (KVP) functionality for Linux.
  *
diff --git a/tools/hv/hv_fcopy_daemon.c b/tools/hv/hv_fcopy_daemon.c
new file mode 100644
index 000000000000..4ecc4fd0bc1b
--- /dev/null
+++ b/tools/hv/hv_fcopy_daemon.c
@@ -0,0 +1,195 @@
+/*
+ * An implementation of host to guest copy functionality for Linux.
+ *
+ * Copyright (C) 2014, Microsoft, Inc.
+ *
+ * Author : K. Y. Srinivasan <kys@microsoft.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ */
+
+
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <sys/poll.h>
+#include <linux/types.h>
+#include <linux/kdev_t.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <ctype.h>
+#include <errno.h>
+#include <linux/hyperv.h>
+#include <syslog.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <dirent.h>
+
+static int target_fd;
+static char target_fname[W_MAX_PATH];
+
+static int hv_start_fcopy(struct hv_start_fcopy *smsg)
+{
+	int error = HV_E_FAIL;
+	char *q, *p;
+
+	/*
+	 * If possile append a path seperator to the path.
+	 */
+	if (strlen((char *)smsg->path_name) < (W_MAX_PATH - 2))
+		strcat((char *)smsg->path_name, "/");
+
+	p = (char *)smsg->path_name;
+	snprintf(target_fname, sizeof(target_fname), "%s/%s",
+		(char *)smsg->path_name, smsg->file_name);
+
+	syslog(LOG_INFO, "Target file name: %s", target_fname);
+	/*
+	 * Check to see if the path is already in place; if not,
+	 * create if required.
+	 */
+	while ((q = strchr(p, '/')) != NULL) {
+		if (q == p) {
+			p++;
+			continue;
+		}
+		*q = '\0';
+		if (access((char *)smsg->path_name, F_OK)) {
+			if (smsg->copy_flags & CREATE_PATH) {
+				if (mkdir((char *)smsg->path_name, 0755)) {
+					syslog(LOG_ERR, "Failed to create %s",
+						(char *)smsg->path_name);
+					goto done;
+				}
+			} else {
+				syslog(LOG_ERR, "Invalid path: %s",
+					(char *)smsg->path_name);
+				goto done;
+			}
+		}
+		p = q + 1;
+		*q = '/';
+	}
+
+	if (!access(target_fname, F_OK)) {
+		syslog(LOG_INFO, "File: %s exists", target_fname);
+		if (!smsg->copy_flags & OVER_WRITE)
+			goto done;
+	}
+
+	target_fd = open(target_fname, O_RDWR | O_CREAT | O_CLOEXEC, 0744);
+	if (target_fd == -1) {
+		syslog(LOG_INFO, "Open Failed: %s", strerror(errno));
+		goto done;
+	}
+
+	error = 0;
+done:
+	return error;
+}
+
+static int hv_copy_data(struct hv_do_fcopy *cpmsg)
+{
+	ssize_t bytes_written;
+
+	bytes_written = pwrite(target_fd, cpmsg->data, cpmsg->size,
+				cpmsg->offset);
+
+	if (bytes_written != cpmsg->size)
+		return HV_E_FAIL;
+
+	return 0;
+}
+
+static int hv_copy_finished(void)
+{
+	close(target_fd);
+	return 0;
+}
+static int hv_copy_cancel(void)
+{
+	close(target_fd);
+	unlink(target_fname);
+	return 0;
+
+}
+
+int main(void)
+{
+	int fd, fcopy_fd, len;
+	int error;
+	int version = FCOPY_CURRENT_VERSION;
+	char *buffer[4096 * 2];
+	struct hv_fcopy_hdr *in_msg;
+
+	if (daemon(1, 0)) {
+		syslog(LOG_ERR, "daemon() failed; error: %s", strerror(errno));
+		exit(EXIT_FAILURE);
+	}
+
+	openlog("HV_FCOPY", 0, LOG_USER);
+	syslog(LOG_INFO, "HV_FCOPY starting; pid is:%d", getpid());
+
+	fcopy_fd = open("/dev/vmbus/hv_fcopy", O_RDWR);
+
+	if (fcopy_fd < 0) {
+		syslog(LOG_ERR, "open /dev/vmbus/hv_fcopy failed; error: %d %s",
+			errno, strerror(errno));
+		exit(EXIT_FAILURE);
+	}
+
+	/*
+	 * Register with the kernel.
+	 */
+	if ((write(fcopy_fd, &version, sizeof(int))) != sizeof(int)) {
+		syslog(LOG_ERR, "Registration failed: %s", strerror(errno));
+		exit(EXIT_FAILURE);
+	}
+
+	while (1) {
+		/*
+		 * In this loop we process fcopy messages after the
+		 * handshake is complete.
+		 */
+		len = pread(fcopy_fd, buffer, (4096 * 2), 0);
+		if (len < 0) {
+			syslog(LOG_ERR, "pread failed: %s", strerror(errno));
+			exit(EXIT_FAILURE);
+		}
+		in_msg = (struct hv_fcopy_hdr *)buffer;
+
+		switch (in_msg->operation) {
+		case START_FILE_COPY:
+			error = hv_start_fcopy((struct hv_start_fcopy *)in_msg);
+			break;
+		case WRITE_TO_FILE:
+			error = hv_copy_data((struct hv_do_fcopy *)in_msg);
+			break;
+		case COMPLETE_FCOPY:
+			error = hv_copy_finished();
+			break;
+		case CANCEL_FCOPY:
+			error = hv_copy_cancel();
+			break;
+
+		default:
+			syslog(LOG_ERR, "Unknown operation: %d",
+				in_msg->operation);
+
+		}
+
+		if (pwrite(fcopy_fd, &error, sizeof(int), 0) != sizeof(int)) {
+			syslog(LOG_ERR, "pwrite failed: %s", strerror(errno));
+			exit(EXIT_FAILURE);
+		}
+	}
+}
-- 
cgit v1.2.3


From 3503958cb0a5f183ddbdafe0f352607920cd8668 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Tue, 18 Feb 2014 02:27:24 -0300
Subject: misc: add comment on unused minors

Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/miscdevice.h | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h
index 3737f7218f51..2cf1547096d9 100644
--- a/include/linux/miscdevice.h
+++ b/include/linux/miscdevice.h
@@ -11,23 +11,23 @@
  */
 
 #define PSMOUSE_MINOR		1
-#define MS_BUSMOUSE_MINOR	2
-#define ATIXL_BUSMOUSE_MINOR	3
+#define MS_BUSMOUSE_MINOR	2	/* unused */
+#define ATIXL_BUSMOUSE_MINOR	3	/* unused */
 /*#define AMIGAMOUSE_MINOR	4	FIXME OBSOLETE */
-#define ATARIMOUSE_MINOR	5
-#define SUN_MOUSE_MINOR		6
-#define APOLLO_MOUSE_MINOR	7
-#define PC110PAD_MINOR		9
+#define ATARIMOUSE_MINOR	5	/* unused */
+#define SUN_MOUSE_MINOR		6	/* unused */
+#define APOLLO_MOUSE_MINOR	7	/* unused */
+#define PC110PAD_MINOR		9	/* unused */
 /*#define ADB_MOUSE_MINOR	10	FIXME OBSOLETE */
 #define WATCHDOG_MINOR		130	/* Watchdog timer     */
 #define TEMP_MINOR		131	/* Temperature Sensor */
 #define RTC_MINOR		135
 #define EFI_RTC_MINOR		136	/* EFI Time services */
 #define SUN_OPENPROM_MINOR	139
-#define DMAPI_MINOR		140	/* DMAPI */
+#define DMAPI_MINOR		140	/* unused */
 #define NVRAM_MINOR		144
 #define SGI_MMTIMER		153
-#define STORE_QUEUE_MINOR	155
+#define STORE_QUEUE_MINOR	155	/* unused */
 #define I2O_MINOR		166
 #define MICROCODE_MINOR		184
 #define VFIO_MINOR		196
-- 
cgit v1.2.3


From d2ae2e20fbdde5a65f3a5a153044ab1e5c53f7cc Mon Sep 17 00:00:00 2001
From: Prabhakar Kushwaha <prabhakar@freescale.com>
Date: Fri, 17 Jan 2014 11:15:16 +0530
Subject: driver/memory:Move Freescale IFC driver to a common driver

 Freescale IFC controller has been used for mpc8xxx. It will be used
 for ARM-based SoC as well. This patch moves the driver to driver/memory
 and fix the header file includes.

  Also remove module_platform_driver() and  instead call
  platform_driver_register() from subsys_initcall() to make sure this module
  has been loaded before MTD partition parsing starts.

Signed-off-by: Prabhakar Kushwaha <prabhakar@freescale.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../bindings/memory-controllers/fsl/ifc.txt        |  79 ++
 .../devicetree/bindings/powerpc/fsl/ifc.txt        |  79 --
 arch/powerpc/include/asm/fsl_ifc.h                 | 838 ---------------------
 arch/powerpc/sysdev/Makefile                       |   1 -
 arch/powerpc/sysdev/fsl_ifc.c                      | 305 --------
 drivers/memory/Makefile                            |   1 +
 drivers/memory/fsl_ifc.c                           | 309 ++++++++
 drivers/mtd/nand/fsl_ifc_nand.c                    |   2 +-
 include/linux/fsl_ifc.h                            | 838 +++++++++++++++++++++
 9 files changed, 1228 insertions(+), 1224 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/memory-controllers/fsl/ifc.txt
 delete mode 100644 Documentation/devicetree/bindings/powerpc/fsl/ifc.txt
 delete mode 100644 arch/powerpc/include/asm/fsl_ifc.h
 delete mode 100644 arch/powerpc/sysdev/fsl_ifc.c
 create mode 100644 drivers/memory/fsl_ifc.c
 create mode 100644 include/linux/fsl_ifc.h

(limited to 'include/linux')

diff --git a/Documentation/devicetree/bindings/memory-controllers/fsl/ifc.txt b/Documentation/devicetree/bindings/memory-controllers/fsl/ifc.txt
new file mode 100644
index 000000000000..d5e370450ac0
--- /dev/null
+++ b/Documentation/devicetree/bindings/memory-controllers/fsl/ifc.txt
@@ -0,0 +1,79 @@
+Integrated Flash Controller
+
+Properties:
+- name : Should be ifc
+- compatible : should contain "fsl,ifc". The version of the integrated
+               flash controller can be found in the IFC_REV register at
+               offset zero.
+
+- #address-cells : Should be either two or three.  The first cell is the
+                   chipselect number, and the remaining cells are the
+                   offset into the chipselect.
+- #size-cells : Either one or two, depending on how large each chipselect
+                can be.
+- reg : Offset and length of the register set for the device
+- interrupts: IFC may have one or two interrupts.  If two interrupt
+              specifiers are present, the first is the "common"
+              interrupt (CM_EVTER_STAT), and the second is the NAND
+              interrupt (NAND_EVTER_STAT).  If there is only one,
+              that interrupt reports both types of event.
+
+
+- ranges : Each range corresponds to a single chipselect, and covers
+           the entire access window as configured.
+
+Child device nodes describe the devices connected to IFC such as NOR (e.g.
+cfi-flash) and NAND (fsl,ifc-nand). There might be board specific devices
+like FPGAs, CPLDs, etc.
+
+Example:
+
+	ifc@ffe1e000 {
+		compatible = "fsl,ifc", "simple-bus";
+		#address-cells = <2>;
+		#size-cells = <1>;
+		reg = <0x0 0xffe1e000 0 0x2000>;
+		interrupts = <16 2 19 2>;
+
+		/* NOR, NAND Flashes and CPLD on board */
+		ranges = <0x0 0x0 0x0 0xee000000 0x02000000
+			  0x1 0x0 0x0 0xffa00000 0x00010000
+			  0x3 0x0 0x0 0xffb00000 0x00020000>;
+
+		flash@0,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "cfi-flash";
+			reg = <0x0 0x0 0x2000000>;
+			bank-width = <2>;
+			device-width = <1>;
+
+			partition@0 {
+				/* 32MB for user data */
+				reg = <0x0 0x02000000>;
+				label = "NOR Data";
+			};
+		};
+
+		flash@1,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,ifc-nand";
+			reg = <0x1 0x0 0x10000>;
+
+			partition@0 {
+				/* This location must not be altered  */
+				/* 1MB for u-boot Bootloader Image */
+				reg = <0x0 0x00100000>;
+				label = "NAND U-Boot Image";
+				read-only;
+			};
+		};
+
+		cpld@3,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,p1010rdb-cpld";
+			reg = <0x3 0x0 0x000001f>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/ifc.txt b/Documentation/devicetree/bindings/powerpc/fsl/ifc.txt
deleted file mode 100644
index d5e370450ac0..000000000000
--- a/Documentation/devicetree/bindings/powerpc/fsl/ifc.txt
+++ /dev/null
@@ -1,79 +0,0 @@
-Integrated Flash Controller
-
-Properties:
-- name : Should be ifc
-- compatible : should contain "fsl,ifc". The version of the integrated
-               flash controller can be found in the IFC_REV register at
-               offset zero.
-
-- #address-cells : Should be either two or three.  The first cell is the
-                   chipselect number, and the remaining cells are the
-                   offset into the chipselect.
-- #size-cells : Either one or two, depending on how large each chipselect
-                can be.
-- reg : Offset and length of the register set for the device
-- interrupts: IFC may have one or two interrupts.  If two interrupt
-              specifiers are present, the first is the "common"
-              interrupt (CM_EVTER_STAT), and the second is the NAND
-              interrupt (NAND_EVTER_STAT).  If there is only one,
-              that interrupt reports both types of event.
-
-
-- ranges : Each range corresponds to a single chipselect, and covers
-           the entire access window as configured.
-
-Child device nodes describe the devices connected to IFC such as NOR (e.g.
-cfi-flash) and NAND (fsl,ifc-nand). There might be board specific devices
-like FPGAs, CPLDs, etc.
-
-Example:
-
-	ifc@ffe1e000 {
-		compatible = "fsl,ifc", "simple-bus";
-		#address-cells = <2>;
-		#size-cells = <1>;
-		reg = <0x0 0xffe1e000 0 0x2000>;
-		interrupts = <16 2 19 2>;
-
-		/* NOR, NAND Flashes and CPLD on board */
-		ranges = <0x0 0x0 0x0 0xee000000 0x02000000
-			  0x1 0x0 0x0 0xffa00000 0x00010000
-			  0x3 0x0 0x0 0xffb00000 0x00020000>;
-
-		flash@0,0 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			compatible = "cfi-flash";
-			reg = <0x0 0x0 0x2000000>;
-			bank-width = <2>;
-			device-width = <1>;
-
-			partition@0 {
-				/* 32MB for user data */
-				reg = <0x0 0x02000000>;
-				label = "NOR Data";
-			};
-		};
-
-		flash@1,0 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			compatible = "fsl,ifc-nand";
-			reg = <0x1 0x0 0x10000>;
-
-			partition@0 {
-				/* This location must not be altered  */
-				/* 1MB for u-boot Bootloader Image */
-				reg = <0x0 0x00100000>;
-				label = "NAND U-Boot Image";
-				read-only;
-			};
-		};
-
-		cpld@3,0 {
-			#address-cells = <1>;
-			#size-cells = <1>;
-			compatible = "fsl,p1010rdb-cpld";
-			reg = <0x3 0x0 0x000001f>;
-		};
-	};
diff --git a/arch/powerpc/include/asm/fsl_ifc.h b/arch/powerpc/include/asm/fsl_ifc.h
deleted file mode 100644
index f49ddb1b2273..000000000000
--- a/arch/powerpc/include/asm/fsl_ifc.h
+++ /dev/null
@@ -1,838 +0,0 @@
-/* Freescale Integrated Flash Controller
- *
- * Copyright 2011 Freescale Semiconductor, Inc
- *
- * Author: Dipen Dudhat <dipen.dudhat@freescale.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-
-#ifndef __ASM_FSL_IFC_H
-#define __ASM_FSL_IFC_H
-
-#include <linux/compiler.h>
-#include <linux/types.h>
-#include <linux/io.h>
-
-#include <linux/of_platform.h>
-#include <linux/interrupt.h>
-
-#define FSL_IFC_BANK_COUNT 4
-
-/*
- * CSPR - Chip Select Property Register
- */
-#define CSPR_BA				0xFFFF0000
-#define CSPR_BA_SHIFT			16
-#define CSPR_PORT_SIZE			0x00000180
-#define CSPR_PORT_SIZE_SHIFT		7
-/* Port Size 8 bit */
-#define CSPR_PORT_SIZE_8		0x00000080
-/* Port Size 16 bit */
-#define CSPR_PORT_SIZE_16		0x00000100
-/* Port Size 32 bit */
-#define CSPR_PORT_SIZE_32		0x00000180
-/* Write Protect */
-#define CSPR_WP				0x00000040
-#define CSPR_WP_SHIFT			6
-/* Machine Select */
-#define CSPR_MSEL			0x00000006
-#define CSPR_MSEL_SHIFT			1
-/* NOR */
-#define CSPR_MSEL_NOR			0x00000000
-/* NAND */
-#define CSPR_MSEL_NAND			0x00000002
-/* GPCM */
-#define CSPR_MSEL_GPCM			0x00000004
-/* Bank Valid */
-#define CSPR_V				0x00000001
-#define CSPR_V_SHIFT			0
-
-/*
- * Address Mask Register
- */
-#define IFC_AMASK_MASK			0xFFFF0000
-#define IFC_AMASK_SHIFT			16
-#define IFC_AMASK(n)			(IFC_AMASK_MASK << \
-					(__ilog2(n) - IFC_AMASK_SHIFT))
-
-/*
- * Chip Select Option Register IFC_NAND Machine
- */
-/* Enable ECC Encoder */
-#define CSOR_NAND_ECC_ENC_EN		0x80000000
-#define CSOR_NAND_ECC_MODE_MASK		0x30000000
-/* 4 bit correction per 520 Byte sector */
-#define CSOR_NAND_ECC_MODE_4		0x00000000
-/* 8 bit correction per 528 Byte sector */
-#define CSOR_NAND_ECC_MODE_8		0x10000000
-/* Enable ECC Decoder */
-#define CSOR_NAND_ECC_DEC_EN		0x04000000
-/* Row Address Length */
-#define CSOR_NAND_RAL_MASK		0x01800000
-#define CSOR_NAND_RAL_SHIFT		20
-#define CSOR_NAND_RAL_1			0x00000000
-#define CSOR_NAND_RAL_2			0x00800000
-#define CSOR_NAND_RAL_3			0x01000000
-#define CSOR_NAND_RAL_4			0x01800000
-/* Page Size 512b, 2k, 4k */
-#define CSOR_NAND_PGS_MASK		0x00180000
-#define CSOR_NAND_PGS_SHIFT		16
-#define CSOR_NAND_PGS_512		0x00000000
-#define CSOR_NAND_PGS_2K		0x00080000
-#define CSOR_NAND_PGS_4K		0x00100000
-#define CSOR_NAND_PGS_8K		0x00180000
-/* Spare region Size */
-#define CSOR_NAND_SPRZ_MASK		0x0000E000
-#define CSOR_NAND_SPRZ_SHIFT		13
-#define CSOR_NAND_SPRZ_16		0x00000000
-#define CSOR_NAND_SPRZ_64		0x00002000
-#define CSOR_NAND_SPRZ_128		0x00004000
-#define CSOR_NAND_SPRZ_210		0x00006000
-#define CSOR_NAND_SPRZ_218		0x00008000
-#define CSOR_NAND_SPRZ_224		0x0000A000
-#define CSOR_NAND_SPRZ_CSOR_EXT		0x0000C000
-/* Pages Per Block */
-#define CSOR_NAND_PB_MASK		0x00000700
-#define CSOR_NAND_PB_SHIFT		8
-#define CSOR_NAND_PB(n)		((__ilog2(n) - 5) << CSOR_NAND_PB_SHIFT)
-/* Time for Read Enable High to Output High Impedance */
-#define CSOR_NAND_TRHZ_MASK		0x0000001C
-#define CSOR_NAND_TRHZ_SHIFT		2
-#define CSOR_NAND_TRHZ_20		0x00000000
-#define CSOR_NAND_TRHZ_40		0x00000004
-#define CSOR_NAND_TRHZ_60		0x00000008
-#define CSOR_NAND_TRHZ_80		0x0000000C
-#define CSOR_NAND_TRHZ_100		0x00000010
-/* Buffer control disable */
-#define CSOR_NAND_BCTLD			0x00000001
-
-/*
- * Chip Select Option Register - NOR Flash Mode
- */
-/* Enable Address shift Mode */
-#define CSOR_NOR_ADM_SHFT_MODE_EN	0x80000000
-/* Page Read Enable from NOR device */
-#define CSOR_NOR_PGRD_EN		0x10000000
-/* AVD Toggle Enable during Burst Program */
-#define CSOR_NOR_AVD_TGL_PGM_EN		0x01000000
-/* Address Data Multiplexing Shift */
-#define CSOR_NOR_ADM_MASK		0x0003E000
-#define CSOR_NOR_ADM_SHIFT_SHIFT	13
-#define CSOR_NOR_ADM_SHIFT(n)	((n) << CSOR_NOR_ADM_SHIFT_SHIFT)
-/* Type of the NOR device hooked */
-#define CSOR_NOR_NOR_MODE_AYSNC_NOR	0x00000000
-#define CSOR_NOR_NOR_MODE_AVD_NOR	0x00000020
-/* Time for Read Enable High to Output High Impedance */
-#define CSOR_NOR_TRHZ_MASK		0x0000001C
-#define CSOR_NOR_TRHZ_SHIFT		2
-#define CSOR_NOR_TRHZ_20		0x00000000
-#define CSOR_NOR_TRHZ_40		0x00000004
-#define CSOR_NOR_TRHZ_60		0x00000008
-#define CSOR_NOR_TRHZ_80		0x0000000C
-#define CSOR_NOR_TRHZ_100		0x00000010
-/* Buffer control disable */
-#define CSOR_NOR_BCTLD			0x00000001
-
-/*
- * Chip Select Option Register - GPCM Mode
- */
-/* GPCM Mode - Normal */
-#define CSOR_GPCM_GPMODE_NORMAL		0x00000000
-/* GPCM Mode - GenericASIC */
-#define CSOR_GPCM_GPMODE_ASIC		0x80000000
-/* Parity Mode odd/even */
-#define CSOR_GPCM_PARITY_EVEN		0x40000000
-/* Parity Checking enable/disable */
-#define CSOR_GPCM_PAR_EN		0x20000000
-/* GPCM Timeout Count */
-#define CSOR_GPCM_GPTO_MASK		0x0F000000
-#define CSOR_GPCM_GPTO_SHIFT		24
-#define CSOR_GPCM_GPTO(n)	((__ilog2(n) - 8) << CSOR_GPCM_GPTO_SHIFT)
-/* GPCM External Access Termination mode for read access */
-#define CSOR_GPCM_RGETA_EXT		0x00080000
-/* GPCM External Access Termination mode for write access */
-#define CSOR_GPCM_WGETA_EXT		0x00040000
-/* Address Data Multiplexing Shift */
-#define CSOR_GPCM_ADM_MASK		0x0003E000
-#define CSOR_GPCM_ADM_SHIFT_SHIFT	13
-#define CSOR_GPCM_ADM_SHIFT(n)	((n) << CSOR_GPCM_ADM_SHIFT_SHIFT)
-/* Generic ASIC Parity error indication delay */
-#define CSOR_GPCM_GAPERRD_MASK		0x00000180
-#define CSOR_GPCM_GAPERRD_SHIFT		7
-#define CSOR_GPCM_GAPERRD(n)	(((n) - 1) << CSOR_GPCM_GAPERRD_SHIFT)
-/* Time for Read Enable High to Output High Impedance */
-#define CSOR_GPCM_TRHZ_MASK		0x0000001C
-#define CSOR_GPCM_TRHZ_20		0x00000000
-#define CSOR_GPCM_TRHZ_40		0x00000004
-#define CSOR_GPCM_TRHZ_60		0x00000008
-#define CSOR_GPCM_TRHZ_80		0x0000000C
-#define CSOR_GPCM_TRHZ_100		0x00000010
-/* Buffer control disable */
-#define CSOR_GPCM_BCTLD			0x00000001
-
-/*
- * Ready Busy Status Register (RB_STAT)
- */
-/* CSn is READY */
-#define IFC_RB_STAT_READY_CS0		0x80000000
-#define IFC_RB_STAT_READY_CS1		0x40000000
-#define IFC_RB_STAT_READY_CS2		0x20000000
-#define IFC_RB_STAT_READY_CS3		0x10000000
-
-/*
- * General Control Register (GCR)
- */
-#define IFC_GCR_MASK			0x8000F800
-/* reset all IFC hardware */
-#define IFC_GCR_SOFT_RST_ALL		0x80000000
-/* Turnaroud Time of external buffer */
-#define IFC_GCR_TBCTL_TRN_TIME		0x0000F800
-#define IFC_GCR_TBCTL_TRN_TIME_SHIFT	11
-
-/*
- * Common Event and Error Status Register (CM_EVTER_STAT)
- */
-/* Chip select error */
-#define IFC_CM_EVTER_STAT_CSER		0x80000000
-
-/*
- * Common Event and Error Enable Register (CM_EVTER_EN)
- */
-/* Chip select error checking enable */
-#define IFC_CM_EVTER_EN_CSEREN		0x80000000
-
-/*
- * Common Event and Error Interrupt Enable Register (CM_EVTER_INTR_EN)
- */
-/* Chip select error interrupt enable */
-#define IFC_CM_EVTER_INTR_EN_CSERIREN	0x80000000
-
-/*
- * Common Transfer Error Attribute Register-0 (CM_ERATTR0)
- */
-/* transaction type of error Read/Write */
-#define IFC_CM_ERATTR0_ERTYP_READ	0x80000000
-#define IFC_CM_ERATTR0_ERAID		0x0FF00000
-#define IFC_CM_ERATTR0_ERAID_SHIFT	20
-#define IFC_CM_ERATTR0_ESRCID		0x0000FF00
-#define IFC_CM_ERATTR0_ESRCID_SHIFT	8
-
-/*
- * Clock Control Register (CCR)
- */
-#define IFC_CCR_MASK			0x0F0F8800
-/* Clock division ratio */
-#define IFC_CCR_CLK_DIV_MASK		0x0F000000
-#define IFC_CCR_CLK_DIV_SHIFT		24
-#define IFC_CCR_CLK_DIV(n)		((n-1) << IFC_CCR_CLK_DIV_SHIFT)
-/* IFC Clock Delay */
-#define IFC_CCR_CLK_DLY_MASK		0x000F0000
-#define IFC_CCR_CLK_DLY_SHIFT		16
-#define IFC_CCR_CLK_DLY(n)		((n) << IFC_CCR_CLK_DLY_SHIFT)
-/* Invert IFC clock before sending out */
-#define IFC_CCR_INV_CLK_EN		0x00008000
-/* Fedback IFC Clock */
-#define IFC_CCR_FB_IFC_CLK_SEL		0x00000800
-
-/*
- * Clock Status Register (CSR)
- */
-/* Clk is stable */
-#define IFC_CSR_CLK_STAT_STABLE		0x80000000
-
-/*
- * IFC_NAND Machine Specific Registers
- */
-/*
- * NAND Configuration Register (NCFGR)
- */
-/* Auto Boot Mode */
-#define IFC_NAND_NCFGR_BOOT		0x80000000
-/* Addressing Mode-ROW0+n/COL0 */
-#define IFC_NAND_NCFGR_ADDR_MODE_RC0	0x00000000
-/* Addressing Mode-ROW0+n/COL0+n */
-#define IFC_NAND_NCFGR_ADDR_MODE_RC1	0x00400000
-/* Number of loop iterations of FIR sequences for multi page operations */
-#define IFC_NAND_NCFGR_NUM_LOOP_MASK	0x0000F000
-#define IFC_NAND_NCFGR_NUM_LOOP_SHIFT	12
-#define IFC_NAND_NCFGR_NUM_LOOP(n)	((n) << IFC_NAND_NCFGR_NUM_LOOP_SHIFT)
-/* Number of wait cycles */
-#define IFC_NAND_NCFGR_NUM_WAIT_MASK	0x000000FF
-#define IFC_NAND_NCFGR_NUM_WAIT_SHIFT	0
-
-/*
- * NAND Flash Command Registers (NAND_FCR0/NAND_FCR1)
- */
-/* General purpose FCM flash command bytes CMD0-CMD7 */
-#define IFC_NAND_FCR0_CMD0		0xFF000000
-#define IFC_NAND_FCR0_CMD0_SHIFT	24
-#define IFC_NAND_FCR0_CMD1		0x00FF0000
-#define IFC_NAND_FCR0_CMD1_SHIFT	16
-#define IFC_NAND_FCR0_CMD2		0x0000FF00
-#define IFC_NAND_FCR0_CMD2_SHIFT	8
-#define IFC_NAND_FCR0_CMD3		0x000000FF
-#define IFC_NAND_FCR0_CMD3_SHIFT	0
-#define IFC_NAND_FCR1_CMD4		0xFF000000
-#define IFC_NAND_FCR1_CMD4_SHIFT	24
-#define IFC_NAND_FCR1_CMD5		0x00FF0000
-#define IFC_NAND_FCR1_CMD5_SHIFT	16
-#define IFC_NAND_FCR1_CMD6		0x0000FF00
-#define IFC_NAND_FCR1_CMD6_SHIFT	8
-#define IFC_NAND_FCR1_CMD7		0x000000FF
-#define IFC_NAND_FCR1_CMD7_SHIFT	0
-
-/*
- * Flash ROW and COL Address Register (ROWn, COLn)
- */
-/* Main/spare region locator */
-#define IFC_NAND_COL_MS			0x80000000
-/* Column Address */
-#define IFC_NAND_COL_CA_MASK		0x00000FFF
-
-/*
- * NAND Flash Byte Count Register (NAND_BC)
- */
-/* Byte Count for read/Write */
-#define IFC_NAND_BC			0x000001FF
-
-/*
- * NAND Flash Instruction Registers (NAND_FIR0/NAND_FIR1/NAND_FIR2)
- */
-/* NAND Machine specific opcodes OP0-OP14*/
-#define IFC_NAND_FIR0_OP0		0xFC000000
-#define IFC_NAND_FIR0_OP0_SHIFT		26
-#define IFC_NAND_FIR0_OP1		0x03F00000
-#define IFC_NAND_FIR0_OP1_SHIFT		20
-#define IFC_NAND_FIR0_OP2		0x000FC000
-#define IFC_NAND_FIR0_OP2_SHIFT		14
-#define IFC_NAND_FIR0_OP3		0x00003F00
-#define IFC_NAND_FIR0_OP3_SHIFT		8
-#define IFC_NAND_FIR0_OP4		0x000000FC
-#define IFC_NAND_FIR0_OP4_SHIFT		2
-#define IFC_NAND_FIR1_OP5		0xFC000000
-#define IFC_NAND_FIR1_OP5_SHIFT		26
-#define IFC_NAND_FIR1_OP6		0x03F00000
-#define IFC_NAND_FIR1_OP6_SHIFT		20
-#define IFC_NAND_FIR1_OP7		0x000FC000
-#define IFC_NAND_FIR1_OP7_SHIFT		14
-#define IFC_NAND_FIR1_OP8		0x00003F00
-#define IFC_NAND_FIR1_OP8_SHIFT		8
-#define IFC_NAND_FIR1_OP9		0x000000FC
-#define IFC_NAND_FIR1_OP9_SHIFT		2
-#define IFC_NAND_FIR2_OP10		0xFC000000
-#define IFC_NAND_FIR2_OP10_SHIFT	26
-#define IFC_NAND_FIR2_OP11		0x03F00000
-#define IFC_NAND_FIR2_OP11_SHIFT	20
-#define IFC_NAND_FIR2_OP12		0x000FC000
-#define IFC_NAND_FIR2_OP12_SHIFT	14
-#define IFC_NAND_FIR2_OP13		0x00003F00
-#define IFC_NAND_FIR2_OP13_SHIFT	8
-#define IFC_NAND_FIR2_OP14		0x000000FC
-#define IFC_NAND_FIR2_OP14_SHIFT	2
-
-/*
- * Instruction opcodes to be programmed
- * in FIR registers- 6bits
- */
-enum ifc_nand_fir_opcodes {
-	IFC_FIR_OP_NOP,
-	IFC_FIR_OP_CA0,
-	IFC_FIR_OP_CA1,
-	IFC_FIR_OP_CA2,
-	IFC_FIR_OP_CA3,
-	IFC_FIR_OP_RA0,
-	IFC_FIR_OP_RA1,
-	IFC_FIR_OP_RA2,
-	IFC_FIR_OP_RA3,
-	IFC_FIR_OP_CMD0,
-	IFC_FIR_OP_CMD1,
-	IFC_FIR_OP_CMD2,
-	IFC_FIR_OP_CMD3,
-	IFC_FIR_OP_CMD4,
-	IFC_FIR_OP_CMD5,
-	IFC_FIR_OP_CMD6,
-	IFC_FIR_OP_CMD7,
-	IFC_FIR_OP_CW0,
-	IFC_FIR_OP_CW1,
-	IFC_FIR_OP_CW2,
-	IFC_FIR_OP_CW3,
-	IFC_FIR_OP_CW4,
-	IFC_FIR_OP_CW5,
-	IFC_FIR_OP_CW6,
-	IFC_FIR_OP_CW7,
-	IFC_FIR_OP_WBCD,
-	IFC_FIR_OP_RBCD,
-	IFC_FIR_OP_BTRD,
-	IFC_FIR_OP_RDSTAT,
-	IFC_FIR_OP_NWAIT,
-	IFC_FIR_OP_WFR,
-	IFC_FIR_OP_SBRD,
-	IFC_FIR_OP_UA,
-	IFC_FIR_OP_RB,
-};
-
-/*
- * NAND Chip Select Register (NAND_CSEL)
- */
-#define IFC_NAND_CSEL			0x0C000000
-#define IFC_NAND_CSEL_SHIFT		26
-#define IFC_NAND_CSEL_CS0		0x00000000
-#define IFC_NAND_CSEL_CS1		0x04000000
-#define IFC_NAND_CSEL_CS2		0x08000000
-#define IFC_NAND_CSEL_CS3		0x0C000000
-
-/*
- * NAND Operation Sequence Start (NANDSEQ_STRT)
- */
-/* NAND Flash Operation Start */
-#define IFC_NAND_SEQ_STRT_FIR_STRT	0x80000000
-/* Automatic Erase */
-#define IFC_NAND_SEQ_STRT_AUTO_ERS	0x00800000
-/* Automatic Program */
-#define IFC_NAND_SEQ_STRT_AUTO_PGM	0x00100000
-/* Automatic Copyback */
-#define IFC_NAND_SEQ_STRT_AUTO_CPB	0x00020000
-/* Automatic Read Operation */
-#define IFC_NAND_SEQ_STRT_AUTO_RD	0x00004000
-/* Automatic Status Read */
-#define IFC_NAND_SEQ_STRT_AUTO_STAT_RD	0x00000800
-
-/*
- * NAND Event and Error Status Register (NAND_EVTER_STAT)
- */
-/* Operation Complete */
-#define IFC_NAND_EVTER_STAT_OPC		0x80000000
-/* Flash Timeout Error */
-#define IFC_NAND_EVTER_STAT_FTOER	0x08000000
-/* Write Protect Error */
-#define IFC_NAND_EVTER_STAT_WPER	0x04000000
-/* ECC Error */
-#define IFC_NAND_EVTER_STAT_ECCER	0x02000000
-/* RCW Load Done */
-#define IFC_NAND_EVTER_STAT_RCW_DN	0x00008000
-/* Boot Loadr Done */
-#define IFC_NAND_EVTER_STAT_BOOT_DN	0x00004000
-/* Bad Block Indicator search select */
-#define IFC_NAND_EVTER_STAT_BBI_SRCH_SE	0x00000800
-
-/*
- * NAND Flash Page Read Completion Event Status Register
- * (PGRDCMPL_EVT_STAT)
- */
-#define PGRDCMPL_EVT_STAT_MASK		0xFFFF0000
-/* Small Page 0-15 Done */
-#define PGRDCMPL_EVT_STAT_SECTION_SP(n)	(1 << (31 - (n)))
-/* Large Page(2K) 0-3 Done */
-#define PGRDCMPL_EVT_STAT_LP_2K(n)	(0xF << (28 - (n)*4))
-/* Large Page(4K) 0-1 Done */
-#define PGRDCMPL_EVT_STAT_LP_4K(n)	(0xFF << (24 - (n)*8))
-
-/*
- * NAND Event and Error Enable Register (NAND_EVTER_EN)
- */
-/* Operation complete event enable */
-#define IFC_NAND_EVTER_EN_OPC_EN	0x80000000
-/* Page read complete event enable */
-#define IFC_NAND_EVTER_EN_PGRDCMPL_EN	0x20000000
-/* Flash Timeout error enable */
-#define IFC_NAND_EVTER_EN_FTOER_EN	0x08000000
-/* Write Protect error enable */
-#define IFC_NAND_EVTER_EN_WPER_EN	0x04000000
-/* ECC error logging enable */
-#define IFC_NAND_EVTER_EN_ECCER_EN	0x02000000
-
-/*
- * NAND Event and Error Interrupt Enable Register (NAND_EVTER_INTR_EN)
- */
-/* Enable interrupt for operation complete */
-#define IFC_NAND_EVTER_INTR_OPCIR_EN		0x80000000
-/* Enable interrupt for Page read complete */
-#define IFC_NAND_EVTER_INTR_PGRDCMPLIR_EN	0x20000000
-/* Enable interrupt for Flash timeout error */
-#define IFC_NAND_EVTER_INTR_FTOERIR_EN		0x08000000
-/* Enable interrupt for Write protect error */
-#define IFC_NAND_EVTER_INTR_WPERIR_EN		0x04000000
-/* Enable interrupt for ECC error*/
-#define IFC_NAND_EVTER_INTR_ECCERIR_EN		0x02000000
-
-/*
- * NAND Transfer Error Attribute Register-0 (NAND_ERATTR0)
- */
-#define IFC_NAND_ERATTR0_MASK		0x0C080000
-/* Error on CS0-3 for NAND */
-#define IFC_NAND_ERATTR0_ERCS_CS0	0x00000000
-#define IFC_NAND_ERATTR0_ERCS_CS1	0x04000000
-#define IFC_NAND_ERATTR0_ERCS_CS2	0x08000000
-#define IFC_NAND_ERATTR0_ERCS_CS3	0x0C000000
-/* Transaction type of error Read/Write */
-#define IFC_NAND_ERATTR0_ERTTYPE_READ	0x00080000
-
-/*
- * NAND Flash Status Register (NAND_FSR)
- */
-/* First byte of data read from read status op */
-#define IFC_NAND_NFSR_RS0		0xFF000000
-/* Second byte of data read from read status op */
-#define IFC_NAND_NFSR_RS1		0x00FF0000
-
-/*
- * ECC Error Status Registers (ECCSTAT0-ECCSTAT3)
- */
-/* Number of ECC errors on sector n (n = 0-15) */
-#define IFC_NAND_ECCSTAT0_ERRCNT_SECTOR0_MASK	0x0F000000
-#define IFC_NAND_ECCSTAT0_ERRCNT_SECTOR0_SHIFT	24
-#define IFC_NAND_ECCSTAT0_ERRCNT_SECTOR1_MASK	0x000F0000
-#define IFC_NAND_ECCSTAT0_ERRCNT_SECTOR1_SHIFT	16
-#define IFC_NAND_ECCSTAT0_ERRCNT_SECTOR2_MASK	0x00000F00
-#define IFC_NAND_ECCSTAT0_ERRCNT_SECTOR2_SHIFT	8
-#define IFC_NAND_ECCSTAT0_ERRCNT_SECTOR3_MASK	0x0000000F
-#define IFC_NAND_ECCSTAT0_ERRCNT_SECTOR3_SHIFT	0
-#define IFC_NAND_ECCSTAT1_ERRCNT_SECTOR4_MASK	0x0F000000
-#define IFC_NAND_ECCSTAT1_ERRCNT_SECTOR4_SHIFT	24
-#define IFC_NAND_ECCSTAT1_ERRCNT_SECTOR5_MASK	0x000F0000
-#define IFC_NAND_ECCSTAT1_ERRCNT_SECTOR5_SHIFT	16
-#define IFC_NAND_ECCSTAT1_ERRCNT_SECTOR6_MASK	0x00000F00
-#define IFC_NAND_ECCSTAT1_ERRCNT_SECTOR6_SHIFT	8
-#define IFC_NAND_ECCSTAT1_ERRCNT_SECTOR7_MASK	0x0000000F
-#define IFC_NAND_ECCSTAT1_ERRCNT_SECTOR7_SHIFT	0
-#define IFC_NAND_ECCSTAT2_ERRCNT_SECTOR8_MASK	0x0F000000
-#define IFC_NAND_ECCSTAT2_ERRCNT_SECTOR8_SHIFT	24
-#define IFC_NAND_ECCSTAT2_ERRCNT_SECTOR9_MASK	0x000F0000
-#define IFC_NAND_ECCSTAT2_ERRCNT_SECTOR9_SHIFT	16
-#define IFC_NAND_ECCSTAT2_ERRCNT_SECTOR10_MASK	0x00000F00
-#define IFC_NAND_ECCSTAT2_ERRCNT_SECTOR10_SHIFT	8
-#define IFC_NAND_ECCSTAT2_ERRCNT_SECTOR11_MASK	0x0000000F
-#define IFC_NAND_ECCSTAT2_ERRCNT_SECTOR11_SHIFT	0
-#define IFC_NAND_ECCSTAT3_ERRCNT_SECTOR12_MASK	0x0F000000
-#define IFC_NAND_ECCSTAT3_ERRCNT_SECTOR12_SHIFT	24
-#define IFC_NAND_ECCSTAT3_ERRCNT_SECTOR13_MASK	0x000F0000
-#define IFC_NAND_ECCSTAT3_ERRCNT_SECTOR13_SHIFT	16
-#define IFC_NAND_ECCSTAT3_ERRCNT_SECTOR14_MASK	0x00000F00
-#define IFC_NAND_ECCSTAT3_ERRCNT_SECTOR14_SHIFT	8
-#define IFC_NAND_ECCSTAT3_ERRCNT_SECTOR15_MASK	0x0000000F
-#define IFC_NAND_ECCSTAT3_ERRCNT_SECTOR15_SHIFT	0
-
-/*
- * NAND Control Register (NANDCR)
- */
-#define IFC_NAND_NCR_FTOCNT_MASK	0x1E000000
-#define IFC_NAND_NCR_FTOCNT_SHIFT	25
-#define IFC_NAND_NCR_FTOCNT(n)	((_ilog2(n) - 8)  << IFC_NAND_NCR_FTOCNT_SHIFT)
-
-/*
- * NAND_AUTOBOOT_TRGR
- */
-/* Trigger RCW load */
-#define IFC_NAND_AUTOBOOT_TRGR_RCW_LD	0x80000000
-/* Trigget Auto Boot */
-#define IFC_NAND_AUTOBOOT_TRGR_BOOT_LD	0x20000000
-
-/*
- * NAND_MDR
- */
-/* 1st read data byte when opcode SBRD */
-#define IFC_NAND_MDR_RDATA0		0xFF000000
-/* 2nd read data byte when opcode SBRD */
-#define IFC_NAND_MDR_RDATA1		0x00FF0000
-
-/*
- * NOR Machine Specific Registers
- */
-/*
- * NOR Event and Error Status Register (NOR_EVTER_STAT)
- */
-/* NOR Command Sequence Operation Complete */
-#define IFC_NOR_EVTER_STAT_OPC_NOR	0x80000000
-/* Write Protect Error */
-#define IFC_NOR_EVTER_STAT_WPER		0x04000000
-/* Command Sequence Timeout Error */
-#define IFC_NOR_EVTER_STAT_STOER	0x01000000
-
-/*
- * NOR Event and Error Enable Register (NOR_EVTER_EN)
- */
-/* NOR Command Seq complete event enable */
-#define IFC_NOR_EVTER_EN_OPCEN_NOR	0x80000000
-/* Write Protect Error Checking Enable */
-#define IFC_NOR_EVTER_EN_WPEREN		0x04000000
-/* Timeout Error Enable */
-#define IFC_NOR_EVTER_EN_STOEREN	0x01000000
-
-/*
- * NOR Event and Error Interrupt Enable Register (NOR_EVTER_INTR_EN)
- */
-/* Enable interrupt for OPC complete */
-#define IFC_NOR_EVTER_INTR_OPCEN_NOR	0x80000000
-/* Enable interrupt for write protect error */
-#define IFC_NOR_EVTER_INTR_WPEREN	0x04000000
-/* Enable interrupt for timeout error */
-#define IFC_NOR_EVTER_INTR_STOEREN	0x01000000
-
-/*
- * NOR Transfer Error Attribute Register-0 (NOR_ERATTR0)
- */
-/* Source ID for error transaction */
-#define IFC_NOR_ERATTR0_ERSRCID		0xFF000000
-/* AXI ID for error transation */
-#define IFC_NOR_ERATTR0_ERAID		0x000FF000
-/* Chip select corresponds to NOR error */
-#define IFC_NOR_ERATTR0_ERCS_CS0	0x00000000
-#define IFC_NOR_ERATTR0_ERCS_CS1	0x00000010
-#define IFC_NOR_ERATTR0_ERCS_CS2	0x00000020
-#define IFC_NOR_ERATTR0_ERCS_CS3	0x00000030
-/* Type of transaction read/write */
-#define IFC_NOR_ERATTR0_ERTYPE_READ	0x00000001
-
-/*
- * NOR Transfer Error Attribute Register-2 (NOR_ERATTR2)
- */
-#define IFC_NOR_ERATTR2_ER_NUM_PHASE_EXP	0x000F0000
-#define IFC_NOR_ERATTR2_ER_NUM_PHASE_PER	0x00000F00
-
-/*
- * NOR Control Register (NORCR)
- */
-#define IFC_NORCR_MASK			0x0F0F0000
-/* No. of Address/Data Phase */
-#define IFC_NORCR_NUM_PHASE_MASK	0x0F000000
-#define IFC_NORCR_NUM_PHASE_SHIFT	24
-#define IFC_NORCR_NUM_PHASE(n)	((n-1) << IFC_NORCR_NUM_PHASE_SHIFT)
-/* Sequence Timeout Count */
-#define IFC_NORCR_STOCNT_MASK		0x000F0000
-#define IFC_NORCR_STOCNT_SHIFT		16
-#define IFC_NORCR_STOCNT(n)	((__ilog2(n) - 8) << IFC_NORCR_STOCNT_SHIFT)
-
-/*
- * GPCM Machine specific registers
- */
-/*
- * GPCM Event and Error Status Register (GPCM_EVTER_STAT)
- */
-/* Timeout error */
-#define IFC_GPCM_EVTER_STAT_TOER	0x04000000
-/* Parity error */
-#define IFC_GPCM_EVTER_STAT_PER		0x01000000
-
-/*
- * GPCM Event and Error Enable Register (GPCM_EVTER_EN)
- */
-/* Timeout error enable */
-#define IFC_GPCM_EVTER_EN_TOER_EN	0x04000000
-/* Parity error enable */
-#define IFC_GPCM_EVTER_EN_PER_EN	0x01000000
-
-/*
- * GPCM Event and Error Interrupt Enable Register (GPCM_EVTER_INTR_EN)
- */
-/* Enable Interrupt for timeout error */
-#define IFC_GPCM_EEIER_TOERIR_EN	0x04000000
-/* Enable Interrupt for Parity error */
-#define IFC_GPCM_EEIER_PERIR_EN		0x01000000
-
-/*
- * GPCM Transfer Error Attribute Register-0 (GPCM_ERATTR0)
- */
-/* Source ID for error transaction */
-#define IFC_GPCM_ERATTR0_ERSRCID	0xFF000000
-/* AXI ID for error transaction */
-#define IFC_GPCM_ERATTR0_ERAID		0x000FF000
-/* Chip select corresponds to GPCM error */
-#define IFC_GPCM_ERATTR0_ERCS_CS0	0x00000000
-#define IFC_GPCM_ERATTR0_ERCS_CS1	0x00000040
-#define IFC_GPCM_ERATTR0_ERCS_CS2	0x00000080
-#define IFC_GPCM_ERATTR0_ERCS_CS3	0x000000C0
-/* Type of transaction read/Write */
-#define IFC_GPCM_ERATTR0_ERTYPE_READ	0x00000001
-
-/*
- * GPCM Transfer Error Attribute Register-2 (GPCM_ERATTR2)
- */
-/* On which beat of address/data parity error is observed */
-#define IFC_GPCM_ERATTR2_PERR_BEAT		0x00000C00
-/* Parity Error on byte */
-#define IFC_GPCM_ERATTR2_PERR_BYTE		0x000000F0
-/* Parity Error reported in addr or data phase */
-#define IFC_GPCM_ERATTR2_PERR_DATA_PHASE	0x00000001
-
-/*
- * GPCM Status Register (GPCM_STAT)
- */
-#define IFC_GPCM_STAT_BSY		0x80000000  /* GPCM is busy */
-
-/*
- * IFC Controller NAND Machine registers
- */
-struct fsl_ifc_nand {
-	__be32 ncfgr;
-	u32 res1[0x4];
-	__be32 nand_fcr0;
-	__be32 nand_fcr1;
-	u32 res2[0x8];
-	__be32 row0;
-	u32 res3;
-	__be32 col0;
-	u32 res4;
-	__be32 row1;
-	u32 res5;
-	__be32 col1;
-	u32 res6;
-	__be32 row2;
-	u32 res7;
-	__be32 col2;
-	u32 res8;
-	__be32 row3;
-	u32 res9;
-	__be32 col3;
-	u32 res10[0x24];
-	__be32 nand_fbcr;
-	u32 res11;
-	__be32 nand_fir0;
-	__be32 nand_fir1;
-	__be32 nand_fir2;
-	u32 res12[0x10];
-	__be32 nand_csel;
-	u32 res13;
-	__be32 nandseq_strt;
-	u32 res14;
-	__be32 nand_evter_stat;
-	u32 res15;
-	__be32 pgrdcmpl_evt_stat;
-	u32 res16[0x2];
-	__be32 nand_evter_en;
-	u32 res17[0x2];
-	__be32 nand_evter_intr_en;
-	u32 res18[0x2];
-	__be32 nand_erattr0;
-	__be32 nand_erattr1;
-	u32 res19[0x10];
-	__be32 nand_fsr;
-	u32 res20;
-	__be32 nand_eccstat[4];
-	u32 res21[0x20];
-	__be32 nanndcr;
-	u32 res22[0x2];
-	__be32 nand_autoboot_trgr;
-	u32 res23;
-	__be32 nand_mdr;
-	u32 res24[0x5C];
-};
-
-/*
- * IFC controller NOR Machine registers
- */
-struct fsl_ifc_nor {
-	__be32 nor_evter_stat;
-	u32 res1[0x2];
-	__be32 nor_evter_en;
-	u32 res2[0x2];
-	__be32 nor_evter_intr_en;
-	u32 res3[0x2];
-	__be32 nor_erattr0;
-	__be32 nor_erattr1;
-	__be32 nor_erattr2;
-	u32 res4[0x4];
-	__be32 norcr;
-	u32 res5[0xEF];
-};
-
-/*
- * IFC controller GPCM Machine registers
- */
-struct fsl_ifc_gpcm {
-	__be32 gpcm_evter_stat;
-	u32 res1[0x2];
-	__be32 gpcm_evter_en;
-	u32 res2[0x2];
-	__be32 gpcm_evter_intr_en;
-	u32 res3[0x2];
-	__be32 gpcm_erattr0;
-	__be32 gpcm_erattr1;
-	__be32 gpcm_erattr2;
-	__be32 gpcm_stat;
-	u32 res4[0x1F3];
-};
-
-/*
- * IFC Controller Registers
- */
-struct fsl_ifc_regs {
-	__be32 ifc_rev;
-	u32 res1[0x2];
-	struct {
-		__be32 cspr_ext;
-		__be32 cspr;
-		u32 res2;
-	} cspr_cs[FSL_IFC_BANK_COUNT];
-	u32 res3[0x19];
-	struct {
-		__be32 amask;
-		u32 res4[0x2];
-	} amask_cs[FSL_IFC_BANK_COUNT];
-	u32 res5[0x17];
-	struct {
-		__be32 csor_ext;
-		__be32 csor;
-		u32 res6;
-	} csor_cs[FSL_IFC_BANK_COUNT];
-	u32 res7[0x19];
-	struct {
-		__be32 ftim[4];
-		u32 res8[0x8];
-	} ftim_cs[FSL_IFC_BANK_COUNT];
-	u32 res9[0x60];
-	__be32 rb_stat;
-	u32 res10[0x2];
-	__be32 ifc_gcr;
-	u32 res11[0x2];
-	__be32 cm_evter_stat;
-	u32 res12[0x2];
-	__be32 cm_evter_en;
-	u32 res13[0x2];
-	__be32 cm_evter_intr_en;
-	u32 res14[0x2];
-	__be32 cm_erattr0;
-	__be32 cm_erattr1;
-	u32 res15[0x2];
-	__be32 ifc_ccr;
-	__be32 ifc_csr;
-	u32 res16[0x2EB];
-	struct fsl_ifc_nand ifc_nand;
-	struct fsl_ifc_nor ifc_nor;
-	struct fsl_ifc_gpcm ifc_gpcm;
-};
-
-extern unsigned int convert_ifc_address(phys_addr_t addr_base);
-extern int fsl_ifc_find(phys_addr_t addr_base);
-
-/* overview of the fsl ifc controller */
-
-struct fsl_ifc_ctrl {
-	/* device info */
-	struct device			*dev;
-	struct fsl_ifc_regs __iomem	*regs;
-	int				irq;
-	int				nand_irq;
-	spinlock_t			lock;
-	void				*nand;
-
-	u32 nand_stat;
-	wait_queue_head_t nand_wait;
-};
-
-extern struct fsl_ifc_ctrl *fsl_ifc_ctrl_dev;
-
-
-#endif /* __ASM_FSL_IFC_H */
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index f67ac900d870..afbcc37aa094 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -21,7 +21,6 @@ obj-$(CONFIG_FSL_SOC)		+= fsl_soc.o fsl_mpic_err.o
 obj-$(CONFIG_FSL_PCI)		+= fsl_pci.o $(fsl-msi-obj-y)
 obj-$(CONFIG_FSL_PMC)		+= fsl_pmc.o
 obj-$(CONFIG_FSL_LBC)		+= fsl_lbc.o
-obj-$(CONFIG_FSL_IFC)		+= fsl_ifc.o
 obj-$(CONFIG_FSL_GTM)		+= fsl_gtm.o
 obj-$(CONFIG_FSL_85XX_CACHE_SRAM)	+= fsl_85xx_l2ctlr.o fsl_85xx_cache_sram.o
 obj-$(CONFIG_SIMPLE_GPIO)	+= simple_gpio.o
diff --git a/arch/powerpc/sysdev/fsl_ifc.c b/arch/powerpc/sysdev/fsl_ifc.c
deleted file mode 100644
index fbc885b31946..000000000000
--- a/arch/powerpc/sysdev/fsl_ifc.c
+++ /dev/null
@@ -1,305 +0,0 @@
-/*
- * Copyright 2011 Freescale Semiconductor, Inc
- *
- * Freescale Integrated Flash Controller
- *
- * Author: Dipen Dudhat <Dipen.Dudhat@freescale.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/compiler.h>
-#include <linux/spinlock.h>
-#include <linux/types.h>
-#include <linux/slab.h>
-#include <linux/io.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
-#include <linux/platform_device.h>
-#include <asm/prom.h>
-#include <asm/fsl_ifc.h>
-
-struct fsl_ifc_ctrl *fsl_ifc_ctrl_dev;
-EXPORT_SYMBOL(fsl_ifc_ctrl_dev);
-
-/*
- * convert_ifc_address - convert the base address
- * @addr_base:	base address of the memory bank
- */
-unsigned int convert_ifc_address(phys_addr_t addr_base)
-{
-	return addr_base & CSPR_BA;
-}
-EXPORT_SYMBOL(convert_ifc_address);
-
-/*
- * fsl_ifc_find - find IFC bank
- * @addr_base:	base address of the memory bank
- *
- * This function walks IFC banks comparing "Base address" field of the CSPR
- * registers with the supplied addr_base argument. When bases match this
- * function returns bank number (starting with 0), otherwise it returns
- * appropriate errno value.
- */
-int fsl_ifc_find(phys_addr_t addr_base)
-{
-	int i = 0;
-
-	if (!fsl_ifc_ctrl_dev || !fsl_ifc_ctrl_dev->regs)
-		return -ENODEV;
-
-	for (i = 0; i < ARRAY_SIZE(fsl_ifc_ctrl_dev->regs->cspr_cs); i++) {
-		u32 cspr = in_be32(&fsl_ifc_ctrl_dev->regs->cspr_cs[i].cspr);
-		if (cspr & CSPR_V && (cspr & CSPR_BA) ==
-				convert_ifc_address(addr_base))
-			return i;
-	}
-
-	return -ENOENT;
-}
-EXPORT_SYMBOL(fsl_ifc_find);
-
-static int fsl_ifc_ctrl_init(struct fsl_ifc_ctrl *ctrl)
-{
-	struct fsl_ifc_regs __iomem *ifc = ctrl->regs;
-
-	/*
-	 * Clear all the common status and event registers
-	 */
-	if (in_be32(&ifc->cm_evter_stat) & IFC_CM_EVTER_STAT_CSER)
-		out_be32(&ifc->cm_evter_stat, IFC_CM_EVTER_STAT_CSER);
-
-	/* enable all error and events */
-	out_be32(&ifc->cm_evter_en, IFC_CM_EVTER_EN_CSEREN);
-
-	/* enable all error and event interrupts */
-	out_be32(&ifc->cm_evter_intr_en, IFC_CM_EVTER_INTR_EN_CSERIREN);
-	out_be32(&ifc->cm_erattr0, 0x0);
-	out_be32(&ifc->cm_erattr1, 0x0);
-
-	return 0;
-}
-
-static int fsl_ifc_ctrl_remove(struct platform_device *dev)
-{
-	struct fsl_ifc_ctrl *ctrl = dev_get_drvdata(&dev->dev);
-
-	free_irq(ctrl->nand_irq, ctrl);
-	free_irq(ctrl->irq, ctrl);
-
-	irq_dispose_mapping(ctrl->nand_irq);
-	irq_dispose_mapping(ctrl->irq);
-
-	iounmap(ctrl->regs);
-
-	dev_set_drvdata(&dev->dev, NULL);
-	kfree(ctrl);
-
-	return 0;
-}
-
-/*
- * NAND events are split between an operational interrupt which only
- * receives OPC, and an error interrupt that receives everything else,
- * including non-NAND errors.  Whichever interrupt gets to it first
- * records the status and wakes the wait queue.
- */
-static DEFINE_SPINLOCK(nand_irq_lock);
-
-static u32 check_nand_stat(struct fsl_ifc_ctrl *ctrl)
-{
-	struct fsl_ifc_regs __iomem *ifc = ctrl->regs;
-	unsigned long flags;
-	u32 stat;
-
-	spin_lock_irqsave(&nand_irq_lock, flags);
-
-	stat = in_be32(&ifc->ifc_nand.nand_evter_stat);
-	if (stat) {
-		out_be32(&ifc->ifc_nand.nand_evter_stat, stat);
-		ctrl->nand_stat = stat;
-		wake_up(&ctrl->nand_wait);
-	}
-
-	spin_unlock_irqrestore(&nand_irq_lock, flags);
-
-	return stat;
-}
-
-static irqreturn_t fsl_ifc_nand_irq(int irqno, void *data)
-{
-	struct fsl_ifc_ctrl *ctrl = data;
-
-	if (check_nand_stat(ctrl))
-		return IRQ_HANDLED;
-
-	return IRQ_NONE;
-}
-
-/*
- * NOTE: This interrupt is used to report ifc events of various kinds,
- * such as transaction errors on the chipselects.
- */
-static irqreturn_t fsl_ifc_ctrl_irq(int irqno, void *data)
-{
-	struct fsl_ifc_ctrl *ctrl = data;
-	struct fsl_ifc_regs __iomem *ifc = ctrl->regs;
-	u32 err_axiid, err_srcid, status, cs_err, err_addr;
-	irqreturn_t ret = IRQ_NONE;
-
-	/* read for chip select error */
-	cs_err = in_be32(&ifc->cm_evter_stat);
-	if (cs_err) {
-		dev_err(ctrl->dev, "transaction sent to IFC is not mapped to"
-				"any memory bank 0x%08X\n", cs_err);
-		/* clear the chip select error */
-		out_be32(&ifc->cm_evter_stat, IFC_CM_EVTER_STAT_CSER);
-
-		/* read error attribute registers print the error information */
-		status = in_be32(&ifc->cm_erattr0);
-		err_addr = in_be32(&ifc->cm_erattr1);
-
-		if (status & IFC_CM_ERATTR0_ERTYP_READ)
-			dev_err(ctrl->dev, "Read transaction error"
-				"CM_ERATTR0 0x%08X\n", status);
-		else
-			dev_err(ctrl->dev, "Write transaction error"
-				"CM_ERATTR0 0x%08X\n", status);
-
-		err_axiid = (status & IFC_CM_ERATTR0_ERAID) >>
-					IFC_CM_ERATTR0_ERAID_SHIFT;
-		dev_err(ctrl->dev, "AXI ID of the error"
-					"transaction 0x%08X\n", err_axiid);
-
-		err_srcid = (status & IFC_CM_ERATTR0_ESRCID) >>
-					IFC_CM_ERATTR0_ESRCID_SHIFT;
-		dev_err(ctrl->dev, "SRC ID of the error"
-					"transaction 0x%08X\n", err_srcid);
-
-		dev_err(ctrl->dev, "Transaction Address corresponding to error"
-					"ERADDR 0x%08X\n", err_addr);
-
-		ret = IRQ_HANDLED;
-	}
-
-	if (check_nand_stat(ctrl))
-		ret = IRQ_HANDLED;
-
-	return ret;
-}
-
-/*
- * fsl_ifc_ctrl_probe
- *
- * called by device layer when it finds a device matching
- * one our driver can handled. This code allocates all of
- * the resources needed for the controller only.  The
- * resources for the NAND banks themselves are allocated
- * in the chip probe function.
-*/
-static int fsl_ifc_ctrl_probe(struct platform_device *dev)
-{
-	int ret = 0;
-
-
-	dev_info(&dev->dev, "Freescale Integrated Flash Controller\n");
-
-	fsl_ifc_ctrl_dev = kzalloc(sizeof(*fsl_ifc_ctrl_dev), GFP_KERNEL);
-	if (!fsl_ifc_ctrl_dev)
-		return -ENOMEM;
-
-	dev_set_drvdata(&dev->dev, fsl_ifc_ctrl_dev);
-
-	/* IOMAP the entire IFC region */
-	fsl_ifc_ctrl_dev->regs = of_iomap(dev->dev.of_node, 0);
-	if (!fsl_ifc_ctrl_dev->regs) {
-		dev_err(&dev->dev, "failed to get memory region\n");
-		ret = -ENODEV;
-		goto err;
-	}
-
-	/* get the Controller level irq */
-	fsl_ifc_ctrl_dev->irq = irq_of_parse_and_map(dev->dev.of_node, 0);
-	if (fsl_ifc_ctrl_dev->irq == NO_IRQ) {
-		dev_err(&dev->dev, "failed to get irq resource "
-							"for IFC\n");
-		ret = -ENODEV;
-		goto err;
-	}
-
-	/* get the nand machine irq */
-	fsl_ifc_ctrl_dev->nand_irq =
-			irq_of_parse_and_map(dev->dev.of_node, 1);
-
-	fsl_ifc_ctrl_dev->dev = &dev->dev;
-
-	ret = fsl_ifc_ctrl_init(fsl_ifc_ctrl_dev);
-	if (ret < 0)
-		goto err;
-
-	init_waitqueue_head(&fsl_ifc_ctrl_dev->nand_wait);
-
-	ret = request_irq(fsl_ifc_ctrl_dev->irq, fsl_ifc_ctrl_irq, IRQF_SHARED,
-			  "fsl-ifc", fsl_ifc_ctrl_dev);
-	if (ret != 0) {
-		dev_err(&dev->dev, "failed to install irq (%d)\n",
-			fsl_ifc_ctrl_dev->irq);
-		goto err_irq;
-	}
-
-	if (fsl_ifc_ctrl_dev->nand_irq) {
-		ret = request_irq(fsl_ifc_ctrl_dev->nand_irq, fsl_ifc_nand_irq,
-				0, "fsl-ifc-nand", fsl_ifc_ctrl_dev);
-		if (ret != 0) {
-			dev_err(&dev->dev, "failed to install irq (%d)\n",
-				fsl_ifc_ctrl_dev->nand_irq);
-			goto err_nandirq;
-		}
-	}
-
-	return 0;
-
-err_nandirq:
-	free_irq(fsl_ifc_ctrl_dev->nand_irq, fsl_ifc_ctrl_dev);
-	irq_dispose_mapping(fsl_ifc_ctrl_dev->nand_irq);
-err_irq:
-	free_irq(fsl_ifc_ctrl_dev->irq, fsl_ifc_ctrl_dev);
-	irq_dispose_mapping(fsl_ifc_ctrl_dev->irq);
-err:
-	return ret;
-}
-
-static const struct of_device_id fsl_ifc_match[] = {
-	{
-		.compatible = "fsl,ifc",
-	},
-	{},
-};
-
-static struct platform_driver fsl_ifc_ctrl_driver = {
-	.driver = {
-		.name	= "fsl-ifc",
-		.of_match_table = fsl_ifc_match,
-	},
-	.probe       = fsl_ifc_ctrl_probe,
-	.remove      = fsl_ifc_ctrl_remove,
-};
-
-module_platform_driver(fsl_ifc_ctrl_driver);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Freescale Semiconductor");
-MODULE_DESCRIPTION("Freescale Integrated Flash Controller driver");
diff --git a/drivers/memory/Makefile b/drivers/memory/Makefile
index 969d923dad93..f2bf25c801d0 100644
--- a/drivers/memory/Makefile
+++ b/drivers/memory/Makefile
@@ -6,6 +6,7 @@ ifeq ($(CONFIG_DDR),y)
 obj-$(CONFIG_OF)		+= of_memory.o
 endif
 obj-$(CONFIG_TI_EMIF)		+= emif.o
+obj-$(CONFIG_FSL_IFC)		+= fsl_ifc.o
 obj-$(CONFIG_MVEBU_DEVBUS)	+= mvebu-devbus.o
 obj-$(CONFIG_TEGRA20_MC)	+= tegra20-mc.o
 obj-$(CONFIG_TEGRA30_MC)	+= tegra30-mc.o
diff --git a/drivers/memory/fsl_ifc.c b/drivers/memory/fsl_ifc.c
new file mode 100644
index 000000000000..3d5d792d5cb2
--- /dev/null
+++ b/drivers/memory/fsl_ifc.c
@@ -0,0 +1,309 @@
+/*
+ * Copyright 2011 Freescale Semiconductor, Inc
+ *
+ * Freescale Integrated Flash Controller
+ *
+ * Author: Dipen Dudhat <Dipen.Dudhat@freescale.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/compiler.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/fsl_ifc.h>
+#include <asm/prom.h>
+
+struct fsl_ifc_ctrl *fsl_ifc_ctrl_dev;
+EXPORT_SYMBOL(fsl_ifc_ctrl_dev);
+
+/*
+ * convert_ifc_address - convert the base address
+ * @addr_base:	base address of the memory bank
+ */
+unsigned int convert_ifc_address(phys_addr_t addr_base)
+{
+	return addr_base & CSPR_BA;
+}
+EXPORT_SYMBOL(convert_ifc_address);
+
+/*
+ * fsl_ifc_find - find IFC bank
+ * @addr_base:	base address of the memory bank
+ *
+ * This function walks IFC banks comparing "Base address" field of the CSPR
+ * registers with the supplied addr_base argument. When bases match this
+ * function returns bank number (starting with 0), otherwise it returns
+ * appropriate errno value.
+ */
+int fsl_ifc_find(phys_addr_t addr_base)
+{
+	int i = 0;
+
+	if (!fsl_ifc_ctrl_dev || !fsl_ifc_ctrl_dev->regs)
+		return -ENODEV;
+
+	for (i = 0; i < ARRAY_SIZE(fsl_ifc_ctrl_dev->regs->cspr_cs); i++) {
+		u32 cspr = in_be32(&fsl_ifc_ctrl_dev->regs->cspr_cs[i].cspr);
+		if (cspr & CSPR_V && (cspr & CSPR_BA) ==
+				convert_ifc_address(addr_base))
+			return i;
+	}
+
+	return -ENOENT;
+}
+EXPORT_SYMBOL(fsl_ifc_find);
+
+static int fsl_ifc_ctrl_init(struct fsl_ifc_ctrl *ctrl)
+{
+	struct fsl_ifc_regs __iomem *ifc = ctrl->regs;
+
+	/*
+	 * Clear all the common status and event registers
+	 */
+	if (in_be32(&ifc->cm_evter_stat) & IFC_CM_EVTER_STAT_CSER)
+		out_be32(&ifc->cm_evter_stat, IFC_CM_EVTER_STAT_CSER);
+
+	/* enable all error and events */
+	out_be32(&ifc->cm_evter_en, IFC_CM_EVTER_EN_CSEREN);
+
+	/* enable all error and event interrupts */
+	out_be32(&ifc->cm_evter_intr_en, IFC_CM_EVTER_INTR_EN_CSERIREN);
+	out_be32(&ifc->cm_erattr0, 0x0);
+	out_be32(&ifc->cm_erattr1, 0x0);
+
+	return 0;
+}
+
+static int fsl_ifc_ctrl_remove(struct platform_device *dev)
+{
+	struct fsl_ifc_ctrl *ctrl = dev_get_drvdata(&dev->dev);
+
+	free_irq(ctrl->nand_irq, ctrl);
+	free_irq(ctrl->irq, ctrl);
+
+	irq_dispose_mapping(ctrl->nand_irq);
+	irq_dispose_mapping(ctrl->irq);
+
+	iounmap(ctrl->regs);
+
+	dev_set_drvdata(&dev->dev, NULL);
+	kfree(ctrl);
+
+	return 0;
+}
+
+/*
+ * NAND events are split between an operational interrupt which only
+ * receives OPC, and an error interrupt that receives everything else,
+ * including non-NAND errors.  Whichever interrupt gets to it first
+ * records the status and wakes the wait queue.
+ */
+static DEFINE_SPINLOCK(nand_irq_lock);
+
+static u32 check_nand_stat(struct fsl_ifc_ctrl *ctrl)
+{
+	struct fsl_ifc_regs __iomem *ifc = ctrl->regs;
+	unsigned long flags;
+	u32 stat;
+
+	spin_lock_irqsave(&nand_irq_lock, flags);
+
+	stat = in_be32(&ifc->ifc_nand.nand_evter_stat);
+	if (stat) {
+		out_be32(&ifc->ifc_nand.nand_evter_stat, stat);
+		ctrl->nand_stat = stat;
+		wake_up(&ctrl->nand_wait);
+	}
+
+	spin_unlock_irqrestore(&nand_irq_lock, flags);
+
+	return stat;
+}
+
+static irqreturn_t fsl_ifc_nand_irq(int irqno, void *data)
+{
+	struct fsl_ifc_ctrl *ctrl = data;
+
+	if (check_nand_stat(ctrl))
+		return IRQ_HANDLED;
+
+	return IRQ_NONE;
+}
+
+/*
+ * NOTE: This interrupt is used to report ifc events of various kinds,
+ * such as transaction errors on the chipselects.
+ */
+static irqreturn_t fsl_ifc_ctrl_irq(int irqno, void *data)
+{
+	struct fsl_ifc_ctrl *ctrl = data;
+	struct fsl_ifc_regs __iomem *ifc = ctrl->regs;
+	u32 err_axiid, err_srcid, status, cs_err, err_addr;
+	irqreturn_t ret = IRQ_NONE;
+
+	/* read for chip select error */
+	cs_err = in_be32(&ifc->cm_evter_stat);
+	if (cs_err) {
+		dev_err(ctrl->dev, "transaction sent to IFC is not mapped to"
+				"any memory bank 0x%08X\n", cs_err);
+		/* clear the chip select error */
+		out_be32(&ifc->cm_evter_stat, IFC_CM_EVTER_STAT_CSER);
+
+		/* read error attribute registers print the error information */
+		status = in_be32(&ifc->cm_erattr0);
+		err_addr = in_be32(&ifc->cm_erattr1);
+
+		if (status & IFC_CM_ERATTR0_ERTYP_READ)
+			dev_err(ctrl->dev, "Read transaction error"
+				"CM_ERATTR0 0x%08X\n", status);
+		else
+			dev_err(ctrl->dev, "Write transaction error"
+				"CM_ERATTR0 0x%08X\n", status);
+
+		err_axiid = (status & IFC_CM_ERATTR0_ERAID) >>
+					IFC_CM_ERATTR0_ERAID_SHIFT;
+		dev_err(ctrl->dev, "AXI ID of the error"
+					"transaction 0x%08X\n", err_axiid);
+
+		err_srcid = (status & IFC_CM_ERATTR0_ESRCID) >>
+					IFC_CM_ERATTR0_ESRCID_SHIFT;
+		dev_err(ctrl->dev, "SRC ID of the error"
+					"transaction 0x%08X\n", err_srcid);
+
+		dev_err(ctrl->dev, "Transaction Address corresponding to error"
+					"ERADDR 0x%08X\n", err_addr);
+
+		ret = IRQ_HANDLED;
+	}
+
+	if (check_nand_stat(ctrl))
+		ret = IRQ_HANDLED;
+
+	return ret;
+}
+
+/*
+ * fsl_ifc_ctrl_probe
+ *
+ * called by device layer when it finds a device matching
+ * one our driver can handled. This code allocates all of
+ * the resources needed for the controller only.  The
+ * resources for the NAND banks themselves are allocated
+ * in the chip probe function.
+*/
+static int fsl_ifc_ctrl_probe(struct platform_device *dev)
+{
+	int ret = 0;
+
+
+	dev_info(&dev->dev, "Freescale Integrated Flash Controller\n");
+
+	fsl_ifc_ctrl_dev = kzalloc(sizeof(*fsl_ifc_ctrl_dev), GFP_KERNEL);
+	if (!fsl_ifc_ctrl_dev)
+		return -ENOMEM;
+
+	dev_set_drvdata(&dev->dev, fsl_ifc_ctrl_dev);
+
+	/* IOMAP the entire IFC region */
+	fsl_ifc_ctrl_dev->regs = of_iomap(dev->dev.of_node, 0);
+	if (!fsl_ifc_ctrl_dev->regs) {
+		dev_err(&dev->dev, "failed to get memory region\n");
+		ret = -ENODEV;
+		goto err;
+	}
+
+	/* get the Controller level irq */
+	fsl_ifc_ctrl_dev->irq = irq_of_parse_and_map(dev->dev.of_node, 0);
+	if (fsl_ifc_ctrl_dev->irq == NO_IRQ) {
+		dev_err(&dev->dev, "failed to get irq resource "
+							"for IFC\n");
+		ret = -ENODEV;
+		goto err;
+	}
+
+	/* get the nand machine irq */
+	fsl_ifc_ctrl_dev->nand_irq =
+			irq_of_parse_and_map(dev->dev.of_node, 1);
+
+	fsl_ifc_ctrl_dev->dev = &dev->dev;
+
+	ret = fsl_ifc_ctrl_init(fsl_ifc_ctrl_dev);
+	if (ret < 0)
+		goto err;
+
+	init_waitqueue_head(&fsl_ifc_ctrl_dev->nand_wait);
+
+	ret = request_irq(fsl_ifc_ctrl_dev->irq, fsl_ifc_ctrl_irq, IRQF_SHARED,
+			  "fsl-ifc", fsl_ifc_ctrl_dev);
+	if (ret != 0) {
+		dev_err(&dev->dev, "failed to install irq (%d)\n",
+			fsl_ifc_ctrl_dev->irq);
+		goto err_irq;
+	}
+
+	if (fsl_ifc_ctrl_dev->nand_irq) {
+		ret = request_irq(fsl_ifc_ctrl_dev->nand_irq, fsl_ifc_nand_irq,
+				0, "fsl-ifc-nand", fsl_ifc_ctrl_dev);
+		if (ret != 0) {
+			dev_err(&dev->dev, "failed to install irq (%d)\n",
+				fsl_ifc_ctrl_dev->nand_irq);
+			goto err_nandirq;
+		}
+	}
+
+	return 0;
+
+err_nandirq:
+	free_irq(fsl_ifc_ctrl_dev->nand_irq, fsl_ifc_ctrl_dev);
+	irq_dispose_mapping(fsl_ifc_ctrl_dev->nand_irq);
+err_irq:
+	free_irq(fsl_ifc_ctrl_dev->irq, fsl_ifc_ctrl_dev);
+	irq_dispose_mapping(fsl_ifc_ctrl_dev->irq);
+err:
+	return ret;
+}
+
+static const struct of_device_id fsl_ifc_match[] = {
+	{
+		.compatible = "fsl,ifc",
+	},
+	{},
+};
+
+static struct platform_driver fsl_ifc_ctrl_driver = {
+	.driver = {
+		.name	= "fsl-ifc",
+		.of_match_table = fsl_ifc_match,
+	},
+	.probe       = fsl_ifc_ctrl_probe,
+	.remove      = fsl_ifc_ctrl_remove,
+};
+
+static int __init fsl_ifc_init(void)
+{
+	return platform_driver_register(&fsl_ifc_ctrl_driver);
+}
+subsys_initcall(fsl_ifc_init);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Freescale Semiconductor");
+MODULE_DESCRIPTION("Freescale Integrated Flash Controller driver");
diff --git a/drivers/mtd/nand/fsl_ifc_nand.c b/drivers/mtd/nand/fsl_ifc_nand.c
index 90ca7e75d6f0..50d9161c4faf 100644
--- a/drivers/mtd/nand/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/fsl_ifc_nand.c
@@ -30,7 +30,7 @@
 #include <linux/mtd/nand.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/nand_ecc.h>
-#include <asm/fsl_ifc.h>
+#include <linux/fsl_ifc.h>
 
 #define FSL_IFC_V1_1_0	0x01010000
 #define ERR_BYTE		0xFF /* Value returned for read
diff --git a/include/linux/fsl_ifc.h b/include/linux/fsl_ifc.h
new file mode 100644
index 000000000000..f49ddb1b2273
--- /dev/null
+++ b/include/linux/fsl_ifc.h
@@ -0,0 +1,838 @@
+/* Freescale Integrated Flash Controller
+ *
+ * Copyright 2011 Freescale Semiconductor, Inc
+ *
+ * Author: Dipen Dudhat <dipen.dudhat@freescale.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef __ASM_FSL_IFC_H
+#define __ASM_FSL_IFC_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <linux/io.h>
+
+#include <linux/of_platform.h>
+#include <linux/interrupt.h>
+
+#define FSL_IFC_BANK_COUNT 4
+
+/*
+ * CSPR - Chip Select Property Register
+ */
+#define CSPR_BA				0xFFFF0000
+#define CSPR_BA_SHIFT			16
+#define CSPR_PORT_SIZE			0x00000180
+#define CSPR_PORT_SIZE_SHIFT		7
+/* Port Size 8 bit */
+#define CSPR_PORT_SIZE_8		0x00000080
+/* Port Size 16 bit */
+#define CSPR_PORT_SIZE_16		0x00000100
+/* Port Size 32 bit */
+#define CSPR_PORT_SIZE_32		0x00000180
+/* Write Protect */
+#define CSPR_WP				0x00000040
+#define CSPR_WP_SHIFT			6
+/* Machine Select */
+#define CSPR_MSEL			0x00000006
+#define CSPR_MSEL_SHIFT			1
+/* NOR */
+#define CSPR_MSEL_NOR			0x00000000
+/* NAND */
+#define CSPR_MSEL_NAND			0x00000002
+/* GPCM */
+#define CSPR_MSEL_GPCM			0x00000004
+/* Bank Valid */
+#define CSPR_V				0x00000001
+#define CSPR_V_SHIFT			0
+
+/*
+ * Address Mask Register
+ */
+#define IFC_AMASK_MASK			0xFFFF0000
+#define IFC_AMASK_SHIFT			16
+#define IFC_AMASK(n)			(IFC_AMASK_MASK << \
+					(__ilog2(n) - IFC_AMASK_SHIFT))
+
+/*
+ * Chip Select Option Register IFC_NAND Machine
+ */
+/* Enable ECC Encoder */
+#define CSOR_NAND_ECC_ENC_EN		0x80000000
+#define CSOR_NAND_ECC_MODE_MASK		0x30000000
+/* 4 bit correction per 520 Byte sector */
+#define CSOR_NAND_ECC_MODE_4		0x00000000
+/* 8 bit correction per 528 Byte sector */
+#define CSOR_NAND_ECC_MODE_8		0x10000000
+/* Enable ECC Decoder */
+#define CSOR_NAND_ECC_DEC_EN		0x04000000
+/* Row Address Length */
+#define CSOR_NAND_RAL_MASK		0x01800000
+#define CSOR_NAND_RAL_SHIFT		20
+#define CSOR_NAND_RAL_1			0x00000000
+#define CSOR_NAND_RAL_2			0x00800000
+#define CSOR_NAND_RAL_3			0x01000000
+#define CSOR_NAND_RAL_4			0x01800000
+/* Page Size 512b, 2k, 4k */
+#define CSOR_NAND_PGS_MASK		0x00180000
+#define CSOR_NAND_PGS_SHIFT		16
+#define CSOR_NAND_PGS_512		0x00000000
+#define CSOR_NAND_PGS_2K		0x00080000
+#define CSOR_NAND_PGS_4K		0x00100000
+#define CSOR_NAND_PGS_8K		0x00180000
+/* Spare region Size */
+#define CSOR_NAND_SPRZ_MASK		0x0000E000
+#define CSOR_NAND_SPRZ_SHIFT		13
+#define CSOR_NAND_SPRZ_16		0x00000000
+#define CSOR_NAND_SPRZ_64		0x00002000
+#define CSOR_NAND_SPRZ_128		0x00004000
+#define CSOR_NAND_SPRZ_210		0x00006000
+#define CSOR_NAND_SPRZ_218		0x00008000
+#define CSOR_NAND_SPRZ_224		0x0000A000
+#define CSOR_NAND_SPRZ_CSOR_EXT		0x0000C000
+/* Pages Per Block */
+#define CSOR_NAND_PB_MASK		0x00000700
+#define CSOR_NAND_PB_SHIFT		8
+#define CSOR_NAND_PB(n)		((__ilog2(n) - 5) << CSOR_NAND_PB_SHIFT)
+/* Time for Read Enable High to Output High Impedance */
+#define CSOR_NAND_TRHZ_MASK		0x0000001C
+#define CSOR_NAND_TRHZ_SHIFT		2
+#define CSOR_NAND_TRHZ_20		0x00000000
+#define CSOR_NAND_TRHZ_40		0x00000004
+#define CSOR_NAND_TRHZ_60		0x00000008
+#define CSOR_NAND_TRHZ_80		0x0000000C
+#define CSOR_NAND_TRHZ_100		0x00000010
+/* Buffer control disable */
+#define CSOR_NAND_BCTLD			0x00000001
+
+/*
+ * Chip Select Option Register - NOR Flash Mode
+ */
+/* Enable Address shift Mode */
+#define CSOR_NOR_ADM_SHFT_MODE_EN	0x80000000
+/* Page Read Enable from NOR device */
+#define CSOR_NOR_PGRD_EN		0x10000000
+/* AVD Toggle Enable during Burst Program */
+#define CSOR_NOR_AVD_TGL_PGM_EN		0x01000000
+/* Address Data Multiplexing Shift */
+#define CSOR_NOR_ADM_MASK		0x0003E000
+#define CSOR_NOR_ADM_SHIFT_SHIFT	13
+#define CSOR_NOR_ADM_SHIFT(n)	((n) << CSOR_NOR_ADM_SHIFT_SHIFT)
+/* Type of the NOR device hooked */
+#define CSOR_NOR_NOR_MODE_AYSNC_NOR	0x00000000
+#define CSOR_NOR_NOR_MODE_AVD_NOR	0x00000020
+/* Time for Read Enable High to Output High Impedance */
+#define CSOR_NOR_TRHZ_MASK		0x0000001C
+#define CSOR_NOR_TRHZ_SHIFT		2
+#define CSOR_NOR_TRHZ_20		0x00000000
+#define CSOR_NOR_TRHZ_40		0x00000004
+#define CSOR_NOR_TRHZ_60		0x00000008
+#define CSOR_NOR_TRHZ_80		0x0000000C
+#define CSOR_NOR_TRHZ_100		0x00000010
+/* Buffer control disable */
+#define CSOR_NOR_BCTLD			0x00000001
+
+/*
+ * Chip Select Option Register - GPCM Mode
+ */
+/* GPCM Mode - Normal */
+#define CSOR_GPCM_GPMODE_NORMAL		0x00000000
+/* GPCM Mode - GenericASIC */
+#define CSOR_GPCM_GPMODE_ASIC		0x80000000
+/* Parity Mode odd/even */
+#define CSOR_GPCM_PARITY_EVEN		0x40000000
+/* Parity Checking enable/disable */
+#define CSOR_GPCM_PAR_EN		0x20000000
+/* GPCM Timeout Count */
+#define CSOR_GPCM_GPTO_MASK		0x0F000000
+#define CSOR_GPCM_GPTO_SHIFT		24
+#define CSOR_GPCM_GPTO(n)	((__ilog2(n) - 8) << CSOR_GPCM_GPTO_SHIFT)
+/* GPCM External Access Termination mode for read access */
+#define CSOR_GPCM_RGETA_EXT		0x00080000
+/* GPCM External Access Termination mode for write access */
+#define CSOR_GPCM_WGETA_EXT		0x00040000
+/* Address Data Multiplexing Shift */
+#define CSOR_GPCM_ADM_MASK		0x0003E000
+#define CSOR_GPCM_ADM_SHIFT_SHIFT	13
+#define CSOR_GPCM_ADM_SHIFT(n)	((n) << CSOR_GPCM_ADM_SHIFT_SHIFT)
+/* Generic ASIC Parity error indication delay */
+#define CSOR_GPCM_GAPERRD_MASK		0x00000180
+#define CSOR_GPCM_GAPERRD_SHIFT		7
+#define CSOR_GPCM_GAPERRD(n)	(((n) - 1) << CSOR_GPCM_GAPERRD_SHIFT)
+/* Time for Read Enable High to Output High Impedance */
+#define CSOR_GPCM_TRHZ_MASK		0x0000001C
+#define CSOR_GPCM_TRHZ_20		0x00000000
+#define CSOR_GPCM_TRHZ_40		0x00000004
+#define CSOR_GPCM_TRHZ_60		0x00000008
+#define CSOR_GPCM_TRHZ_80		0x0000000C
+#define CSOR_GPCM_TRHZ_100		0x00000010
+/* Buffer control disable */
+#define CSOR_GPCM_BCTLD			0x00000001
+
+/*
+ * Ready Busy Status Register (RB_STAT)
+ */
+/* CSn is READY */
+#define IFC_RB_STAT_READY_CS0		0x80000000
+#define IFC_RB_STAT_READY_CS1		0x40000000
+#define IFC_RB_STAT_READY_CS2		0x20000000
+#define IFC_RB_STAT_READY_CS3		0x10000000
+
+/*
+ * General Control Register (GCR)
+ */
+#define IFC_GCR_MASK			0x8000F800
+/* reset all IFC hardware */
+#define IFC_GCR_SOFT_RST_ALL		0x80000000
+/* Turnaroud Time of external buffer */
+#define IFC_GCR_TBCTL_TRN_TIME		0x0000F800
+#define IFC_GCR_TBCTL_TRN_TIME_SHIFT	11
+
+/*
+ * Common Event and Error Status Register (CM_EVTER_STAT)
+ */
+/* Chip select error */
+#define IFC_CM_EVTER_STAT_CSER		0x80000000
+
+/*
+ * Common Event and Error Enable Register (CM_EVTER_EN)
+ */
+/* Chip select error checking enable */
+#define IFC_CM_EVTER_EN_CSEREN		0x80000000
+
+/*
+ * Common Event and Error Interrupt Enable Register (CM_EVTER_INTR_EN)
+ */
+/* Chip select error interrupt enable */
+#define IFC_CM_EVTER_INTR_EN_CSERIREN	0x80000000
+
+/*
+ * Common Transfer Error Attribute Register-0 (CM_ERATTR0)
+ */
+/* transaction type of error Read/Write */
+#define IFC_CM_ERATTR0_ERTYP_READ	0x80000000
+#define IFC_CM_ERATTR0_ERAID		0x0FF00000
+#define IFC_CM_ERATTR0_ERAID_SHIFT	20
+#define IFC_CM_ERATTR0_ESRCID		0x0000FF00
+#define IFC_CM_ERATTR0_ESRCID_SHIFT	8
+
+/*
+ * Clock Control Register (CCR)
+ */
+#define IFC_CCR_MASK			0x0F0F8800
+/* Clock division ratio */
+#define IFC_CCR_CLK_DIV_MASK		0x0F000000
+#define IFC_CCR_CLK_DIV_SHIFT		24
+#define IFC_CCR_CLK_DIV(n)		((n-1) << IFC_CCR_CLK_DIV_SHIFT)
+/* IFC Clock Delay */
+#define IFC_CCR_CLK_DLY_MASK		0x000F0000
+#define IFC_CCR_CLK_DLY_SHIFT		16
+#define IFC_CCR_CLK_DLY(n)		((n) << IFC_CCR_CLK_DLY_SHIFT)
+/* Invert IFC clock before sending out */
+#define IFC_CCR_INV_CLK_EN		0x00008000
+/* Fedback IFC Clock */
+#define IFC_CCR_FB_IFC_CLK_SEL		0x00000800
+
+/*
+ * Clock Status Register (CSR)
+ */
+/* Clk is stable */
+#define IFC_CSR_CLK_STAT_STABLE		0x80000000
+
+/*
+ * IFC_NAND Machine Specific Registers
+ */
+/*
+ * NAND Configuration Register (NCFGR)
+ */
+/* Auto Boot Mode */
+#define IFC_NAND_NCFGR_BOOT		0x80000000
+/* Addressing Mode-ROW0+n/COL0 */
+#define IFC_NAND_NCFGR_ADDR_MODE_RC0	0x00000000
+/* Addressing Mode-ROW0+n/COL0+n */
+#define IFC_NAND_NCFGR_ADDR_MODE_RC1	0x00400000
+/* Number of loop iterations of FIR sequences for multi page operations */
+#define IFC_NAND_NCFGR_NUM_LOOP_MASK	0x0000F000
+#define IFC_NAND_NCFGR_NUM_LOOP_SHIFT	12
+#define IFC_NAND_NCFGR_NUM_LOOP(n)	((n) << IFC_NAND_NCFGR_NUM_LOOP_SHIFT)
+/* Number of wait cycles */
+#define IFC_NAND_NCFGR_NUM_WAIT_MASK	0x000000FF
+#define IFC_NAND_NCFGR_NUM_WAIT_SHIFT	0
+
+/*
+ * NAND Flash Command Registers (NAND_FCR0/NAND_FCR1)
+ */
+/* General purpose FCM flash command bytes CMD0-CMD7 */
+#define IFC_NAND_FCR0_CMD0		0xFF000000
+#define IFC_NAND_FCR0_CMD0_SHIFT	24
+#define IFC_NAND_FCR0_CMD1		0x00FF0000
+#define IFC_NAND_FCR0_CMD1_SHIFT	16
+#define IFC_NAND_FCR0_CMD2		0x0000FF00
+#define IFC_NAND_FCR0_CMD2_SHIFT	8
+#define IFC_NAND_FCR0_CMD3		0x000000FF
+#define IFC_NAND_FCR0_CMD3_SHIFT	0
+#define IFC_NAND_FCR1_CMD4		0xFF000000
+#define IFC_NAND_FCR1_CMD4_SHIFT	24
+#define IFC_NAND_FCR1_CMD5		0x00FF0000
+#define IFC_NAND_FCR1_CMD5_SHIFT	16
+#define IFC_NAND_FCR1_CMD6		0x0000FF00
+#define IFC_NAND_FCR1_CMD6_SHIFT	8
+#define IFC_NAND_FCR1_CMD7		0x000000FF
+#define IFC_NAND_FCR1_CMD7_SHIFT	0
+
+/*
+ * Flash ROW and COL Address Register (ROWn, COLn)
+ */
+/* Main/spare region locator */
+#define IFC_NAND_COL_MS			0x80000000
+/* Column Address */
+#define IFC_NAND_COL_CA_MASK		0x00000FFF
+
+/*
+ * NAND Flash Byte Count Register (NAND_BC)
+ */
+/* Byte Count for read/Write */
+#define IFC_NAND_BC			0x000001FF
+
+/*
+ * NAND Flash Instruction Registers (NAND_FIR0/NAND_FIR1/NAND_FIR2)
+ */
+/* NAND Machine specific opcodes OP0-OP14*/
+#define IFC_NAND_FIR0_OP0		0xFC000000
+#define IFC_NAND_FIR0_OP0_SHIFT		26
+#define IFC_NAND_FIR0_OP1		0x03F00000
+#define IFC_NAND_FIR0_OP1_SHIFT		20
+#define IFC_NAND_FIR0_OP2		0x000FC000
+#define IFC_NAND_FIR0_OP2_SHIFT		14
+#define IFC_NAND_FIR0_OP3		0x00003F00
+#define IFC_NAND_FIR0_OP3_SHIFT		8
+#define IFC_NAND_FIR0_OP4		0x000000FC
+#define IFC_NAND_FIR0_OP4_SHIFT		2
+#define IFC_NAND_FIR1_OP5		0xFC000000
+#define IFC_NAND_FIR1_OP5_SHIFT		26
+#define IFC_NAND_FIR1_OP6		0x03F00000
+#define IFC_NAND_FIR1_OP6_SHIFT		20
+#define IFC_NAND_FIR1_OP7		0x000FC000
+#define IFC_NAND_FIR1_OP7_SHIFT		14
+#define IFC_NAND_FIR1_OP8		0x00003F00
+#define IFC_NAND_FIR1_OP8_SHIFT		8
+#define IFC_NAND_FIR1_OP9		0x000000FC
+#define IFC_NAND_FIR1_OP9_SHIFT		2
+#define IFC_NAND_FIR2_OP10		0xFC000000
+#define IFC_NAND_FIR2_OP10_SHIFT	26
+#define IFC_NAND_FIR2_OP11		0x03F00000
+#define IFC_NAND_FIR2_OP11_SHIFT	20
+#define IFC_NAND_FIR2_OP12		0x000FC000
+#define IFC_NAND_FIR2_OP12_SHIFT	14
+#define IFC_NAND_FIR2_OP13		0x00003F00
+#define IFC_NAND_FIR2_OP13_SHIFT	8
+#define IFC_NAND_FIR2_OP14		0x000000FC
+#define IFC_NAND_FIR2_OP14_SHIFT	2
+
+/*
+ * Instruction opcodes to be programmed
+ * in FIR registers- 6bits
+ */
+enum ifc_nand_fir_opcodes {
+	IFC_FIR_OP_NOP,
+	IFC_FIR_OP_CA0,
+	IFC_FIR_OP_CA1,
+	IFC_FIR_OP_CA2,
+	IFC_FIR_OP_CA3,
+	IFC_FIR_OP_RA0,
+	IFC_FIR_OP_RA1,
+	IFC_FIR_OP_RA2,
+	IFC_FIR_OP_RA3,
+	IFC_FIR_OP_CMD0,
+	IFC_FIR_OP_CMD1,
+	IFC_FIR_OP_CMD2,
+	IFC_FIR_OP_CMD3,
+	IFC_FIR_OP_CMD4,
+	IFC_FIR_OP_CMD5,
+	IFC_FIR_OP_CMD6,
+	IFC_FIR_OP_CMD7,
+	IFC_FIR_OP_CW0,
+	IFC_FIR_OP_CW1,
+	IFC_FIR_OP_CW2,
+	IFC_FIR_OP_CW3,
+	IFC_FIR_OP_CW4,
+	IFC_FIR_OP_CW5,
+	IFC_FIR_OP_CW6,
+	IFC_FIR_OP_CW7,
+	IFC_FIR_OP_WBCD,
+	IFC_FIR_OP_RBCD,
+	IFC_FIR_OP_BTRD,
+	IFC_FIR_OP_RDSTAT,
+	IFC_FIR_OP_NWAIT,
+	IFC_FIR_OP_WFR,
+	IFC_FIR_OP_SBRD,
+	IFC_FIR_OP_UA,
+	IFC_FIR_OP_RB,
+};
+
+/*
+ * NAND Chip Select Register (NAND_CSEL)
+ */
+#define IFC_NAND_CSEL			0x0C000000
+#define IFC_NAND_CSEL_SHIFT		26
+#define IFC_NAND_CSEL_CS0		0x00000000
+#define IFC_NAND_CSEL_CS1		0x04000000
+#define IFC_NAND_CSEL_CS2		0x08000000
+#define IFC_NAND_CSEL_CS3		0x0C000000
+
+/*
+ * NAND Operation Sequence Start (NANDSEQ_STRT)
+ */
+/* NAND Flash Operation Start */
+#define IFC_NAND_SEQ_STRT_FIR_STRT	0x80000000
+/* Automatic Erase */
+#define IFC_NAND_SEQ_STRT_AUTO_ERS	0x00800000
+/* Automatic Program */
+#define IFC_NAND_SEQ_STRT_AUTO_PGM	0x00100000
+/* Automatic Copyback */
+#define IFC_NAND_SEQ_STRT_AUTO_CPB	0x00020000
+/* Automatic Read Operation */
+#define IFC_NAND_SEQ_STRT_AUTO_RD	0x00004000
+/* Automatic Status Read */
+#define IFC_NAND_SEQ_STRT_AUTO_STAT_RD	0x00000800
+
+/*
+ * NAND Event and Error Status Register (NAND_EVTER_STAT)
+ */
+/* Operation Complete */
+#define IFC_NAND_EVTER_STAT_OPC		0x80000000
+/* Flash Timeout Error */
+#define IFC_NAND_EVTER_STAT_FTOER	0x08000000
+/* Write Protect Error */
+#define IFC_NAND_EVTER_STAT_WPER	0x04000000
+/* ECC Error */
+#define IFC_NAND_EVTER_STAT_ECCER	0x02000000
+/* RCW Load Done */
+#define IFC_NAND_EVTER_STAT_RCW_DN	0x00008000
+/* Boot Loadr Done */
+#define IFC_NAND_EVTER_STAT_BOOT_DN	0x00004000
+/* Bad Block Indicator search select */
+#define IFC_NAND_EVTER_STAT_BBI_SRCH_SE	0x00000800
+
+/*
+ * NAND Flash Page Read Completion Event Status Register
+ * (PGRDCMPL_EVT_STAT)
+ */
+#define PGRDCMPL_EVT_STAT_MASK		0xFFFF0000
+/* Small Page 0-15 Done */
+#define PGRDCMPL_EVT_STAT_SECTION_SP(n)	(1 << (31 - (n)))
+/* Large Page(2K) 0-3 Done */
+#define PGRDCMPL_EVT_STAT_LP_2K(n)	(0xF << (28 - (n)*4))
+/* Large Page(4K) 0-1 Done */
+#define PGRDCMPL_EVT_STAT_LP_4K(n)	(0xFF << (24 - (n)*8))
+
+/*
+ * NAND Event and Error Enable Register (NAND_EVTER_EN)
+ */
+/* Operation complete event enable */
+#define IFC_NAND_EVTER_EN_OPC_EN	0x80000000
+/* Page read complete event enable */
+#define IFC_NAND_EVTER_EN_PGRDCMPL_EN	0x20000000
+/* Flash Timeout error enable */
+#define IFC_NAND_EVTER_EN_FTOER_EN	0x08000000
+/* Write Protect error enable */
+#define IFC_NAND_EVTER_EN_WPER_EN	0x04000000
+/* ECC error logging enable */
+#define IFC_NAND_EVTER_EN_ECCER_EN	0x02000000
+
+/*
+ * NAND Event and Error Interrupt Enable Register (NAND_EVTER_INTR_EN)
+ */
+/* Enable interrupt for operation complete */
+#define IFC_NAND_EVTER_INTR_OPCIR_EN		0x80000000
+/* Enable interrupt for Page read complete */
+#define IFC_NAND_EVTER_INTR_PGRDCMPLIR_EN	0x20000000
+/* Enable interrupt for Flash timeout error */
+#define IFC_NAND_EVTER_INTR_FTOERIR_EN		0x08000000
+/* Enable interrupt for Write protect error */
+#define IFC_NAND_EVTER_INTR_WPERIR_EN		0x04000000
+/* Enable interrupt for ECC error*/
+#define IFC_NAND_EVTER_INTR_ECCERIR_EN		0x02000000
+
+/*
+ * NAND Transfer Error Attribute Register-0 (NAND_ERATTR0)
+ */
+#define IFC_NAND_ERATTR0_MASK		0x0C080000
+/* Error on CS0-3 for NAND */
+#define IFC_NAND_ERATTR0_ERCS_CS0	0x00000000
+#define IFC_NAND_ERATTR0_ERCS_CS1	0x04000000
+#define IFC_NAND_ERATTR0_ERCS_CS2	0x08000000
+#define IFC_NAND_ERATTR0_ERCS_CS3	0x0C000000
+/* Transaction type of error Read/Write */
+#define IFC_NAND_ERATTR0_ERTTYPE_READ	0x00080000
+
+/*
+ * NAND Flash Status Register (NAND_FSR)
+ */
+/* First byte of data read from read status op */
+#define IFC_NAND_NFSR_RS0		0xFF000000
+/* Second byte of data read from read status op */
+#define IFC_NAND_NFSR_RS1		0x00FF0000
+
+/*
+ * ECC Error Status Registers (ECCSTAT0-ECCSTAT3)
+ */
+/* Number of ECC errors on sector n (n = 0-15) */
+#define IFC_NAND_ECCSTAT0_ERRCNT_SECTOR0_MASK	0x0F000000
+#define IFC_NAND_ECCSTAT0_ERRCNT_SECTOR0_SHIFT	24
+#define IFC_NAND_ECCSTAT0_ERRCNT_SECTOR1_MASK	0x000F0000
+#define IFC_NAND_ECCSTAT0_ERRCNT_SECTOR1_SHIFT	16
+#define IFC_NAND_ECCSTAT0_ERRCNT_SECTOR2_MASK	0x00000F00
+#define IFC_NAND_ECCSTAT0_ERRCNT_SECTOR2_SHIFT	8
+#define IFC_NAND_ECCSTAT0_ERRCNT_SECTOR3_MASK	0x0000000F
+#define IFC_NAND_ECCSTAT0_ERRCNT_SECTOR3_SHIFT	0
+#define IFC_NAND_ECCSTAT1_ERRCNT_SECTOR4_MASK	0x0F000000
+#define IFC_NAND_ECCSTAT1_ERRCNT_SECTOR4_SHIFT	24
+#define IFC_NAND_ECCSTAT1_ERRCNT_SECTOR5_MASK	0x000F0000
+#define IFC_NAND_ECCSTAT1_ERRCNT_SECTOR5_SHIFT	16
+#define IFC_NAND_ECCSTAT1_ERRCNT_SECTOR6_MASK	0x00000F00
+#define IFC_NAND_ECCSTAT1_ERRCNT_SECTOR6_SHIFT	8
+#define IFC_NAND_ECCSTAT1_ERRCNT_SECTOR7_MASK	0x0000000F
+#define IFC_NAND_ECCSTAT1_ERRCNT_SECTOR7_SHIFT	0
+#define IFC_NAND_ECCSTAT2_ERRCNT_SECTOR8_MASK	0x0F000000
+#define IFC_NAND_ECCSTAT2_ERRCNT_SECTOR8_SHIFT	24
+#define IFC_NAND_ECCSTAT2_ERRCNT_SECTOR9_MASK	0x000F0000
+#define IFC_NAND_ECCSTAT2_ERRCNT_SECTOR9_SHIFT	16
+#define IFC_NAND_ECCSTAT2_ERRCNT_SECTOR10_MASK	0x00000F00
+#define IFC_NAND_ECCSTAT2_ERRCNT_SECTOR10_SHIFT	8
+#define IFC_NAND_ECCSTAT2_ERRCNT_SECTOR11_MASK	0x0000000F
+#define IFC_NAND_ECCSTAT2_ERRCNT_SECTOR11_SHIFT	0
+#define IFC_NAND_ECCSTAT3_ERRCNT_SECTOR12_MASK	0x0F000000
+#define IFC_NAND_ECCSTAT3_ERRCNT_SECTOR12_SHIFT	24
+#define IFC_NAND_ECCSTAT3_ERRCNT_SECTOR13_MASK	0x000F0000
+#define IFC_NAND_ECCSTAT3_ERRCNT_SECTOR13_SHIFT	16
+#define IFC_NAND_ECCSTAT3_ERRCNT_SECTOR14_MASK	0x00000F00
+#define IFC_NAND_ECCSTAT3_ERRCNT_SECTOR14_SHIFT	8
+#define IFC_NAND_ECCSTAT3_ERRCNT_SECTOR15_MASK	0x0000000F
+#define IFC_NAND_ECCSTAT3_ERRCNT_SECTOR15_SHIFT	0
+
+/*
+ * NAND Control Register (NANDCR)
+ */
+#define IFC_NAND_NCR_FTOCNT_MASK	0x1E000000
+#define IFC_NAND_NCR_FTOCNT_SHIFT	25
+#define IFC_NAND_NCR_FTOCNT(n)	((_ilog2(n) - 8)  << IFC_NAND_NCR_FTOCNT_SHIFT)
+
+/*
+ * NAND_AUTOBOOT_TRGR
+ */
+/* Trigger RCW load */
+#define IFC_NAND_AUTOBOOT_TRGR_RCW_LD	0x80000000
+/* Trigget Auto Boot */
+#define IFC_NAND_AUTOBOOT_TRGR_BOOT_LD	0x20000000
+
+/*
+ * NAND_MDR
+ */
+/* 1st read data byte when opcode SBRD */
+#define IFC_NAND_MDR_RDATA0		0xFF000000
+/* 2nd read data byte when opcode SBRD */
+#define IFC_NAND_MDR_RDATA1		0x00FF0000
+
+/*
+ * NOR Machine Specific Registers
+ */
+/*
+ * NOR Event and Error Status Register (NOR_EVTER_STAT)
+ */
+/* NOR Command Sequence Operation Complete */
+#define IFC_NOR_EVTER_STAT_OPC_NOR	0x80000000
+/* Write Protect Error */
+#define IFC_NOR_EVTER_STAT_WPER		0x04000000
+/* Command Sequence Timeout Error */
+#define IFC_NOR_EVTER_STAT_STOER	0x01000000
+
+/*
+ * NOR Event and Error Enable Register (NOR_EVTER_EN)
+ */
+/* NOR Command Seq complete event enable */
+#define IFC_NOR_EVTER_EN_OPCEN_NOR	0x80000000
+/* Write Protect Error Checking Enable */
+#define IFC_NOR_EVTER_EN_WPEREN		0x04000000
+/* Timeout Error Enable */
+#define IFC_NOR_EVTER_EN_STOEREN	0x01000000
+
+/*
+ * NOR Event and Error Interrupt Enable Register (NOR_EVTER_INTR_EN)
+ */
+/* Enable interrupt for OPC complete */
+#define IFC_NOR_EVTER_INTR_OPCEN_NOR	0x80000000
+/* Enable interrupt for write protect error */
+#define IFC_NOR_EVTER_INTR_WPEREN	0x04000000
+/* Enable interrupt for timeout error */
+#define IFC_NOR_EVTER_INTR_STOEREN	0x01000000
+
+/*
+ * NOR Transfer Error Attribute Register-0 (NOR_ERATTR0)
+ */
+/* Source ID for error transaction */
+#define IFC_NOR_ERATTR0_ERSRCID		0xFF000000
+/* AXI ID for error transation */
+#define IFC_NOR_ERATTR0_ERAID		0x000FF000
+/* Chip select corresponds to NOR error */
+#define IFC_NOR_ERATTR0_ERCS_CS0	0x00000000
+#define IFC_NOR_ERATTR0_ERCS_CS1	0x00000010
+#define IFC_NOR_ERATTR0_ERCS_CS2	0x00000020
+#define IFC_NOR_ERATTR0_ERCS_CS3	0x00000030
+/* Type of transaction read/write */
+#define IFC_NOR_ERATTR0_ERTYPE_READ	0x00000001
+
+/*
+ * NOR Transfer Error Attribute Register-2 (NOR_ERATTR2)
+ */
+#define IFC_NOR_ERATTR2_ER_NUM_PHASE_EXP	0x000F0000
+#define IFC_NOR_ERATTR2_ER_NUM_PHASE_PER	0x00000F00
+
+/*
+ * NOR Control Register (NORCR)
+ */
+#define IFC_NORCR_MASK			0x0F0F0000
+/* No. of Address/Data Phase */
+#define IFC_NORCR_NUM_PHASE_MASK	0x0F000000
+#define IFC_NORCR_NUM_PHASE_SHIFT	24
+#define IFC_NORCR_NUM_PHASE(n)	((n-1) << IFC_NORCR_NUM_PHASE_SHIFT)
+/* Sequence Timeout Count */
+#define IFC_NORCR_STOCNT_MASK		0x000F0000
+#define IFC_NORCR_STOCNT_SHIFT		16
+#define IFC_NORCR_STOCNT(n)	((__ilog2(n) - 8) << IFC_NORCR_STOCNT_SHIFT)
+
+/*
+ * GPCM Machine specific registers
+ */
+/*
+ * GPCM Event and Error Status Register (GPCM_EVTER_STAT)
+ */
+/* Timeout error */
+#define IFC_GPCM_EVTER_STAT_TOER	0x04000000
+/* Parity error */
+#define IFC_GPCM_EVTER_STAT_PER		0x01000000
+
+/*
+ * GPCM Event and Error Enable Register (GPCM_EVTER_EN)
+ */
+/* Timeout error enable */
+#define IFC_GPCM_EVTER_EN_TOER_EN	0x04000000
+/* Parity error enable */
+#define IFC_GPCM_EVTER_EN_PER_EN	0x01000000
+
+/*
+ * GPCM Event and Error Interrupt Enable Register (GPCM_EVTER_INTR_EN)
+ */
+/* Enable Interrupt for timeout error */
+#define IFC_GPCM_EEIER_TOERIR_EN	0x04000000
+/* Enable Interrupt for Parity error */
+#define IFC_GPCM_EEIER_PERIR_EN		0x01000000
+
+/*
+ * GPCM Transfer Error Attribute Register-0 (GPCM_ERATTR0)
+ */
+/* Source ID for error transaction */
+#define IFC_GPCM_ERATTR0_ERSRCID	0xFF000000
+/* AXI ID for error transaction */
+#define IFC_GPCM_ERATTR0_ERAID		0x000FF000
+/* Chip select corresponds to GPCM error */
+#define IFC_GPCM_ERATTR0_ERCS_CS0	0x00000000
+#define IFC_GPCM_ERATTR0_ERCS_CS1	0x00000040
+#define IFC_GPCM_ERATTR0_ERCS_CS2	0x00000080
+#define IFC_GPCM_ERATTR0_ERCS_CS3	0x000000C0
+/* Type of transaction read/Write */
+#define IFC_GPCM_ERATTR0_ERTYPE_READ	0x00000001
+
+/*
+ * GPCM Transfer Error Attribute Register-2 (GPCM_ERATTR2)
+ */
+/* On which beat of address/data parity error is observed */
+#define IFC_GPCM_ERATTR2_PERR_BEAT		0x00000C00
+/* Parity Error on byte */
+#define IFC_GPCM_ERATTR2_PERR_BYTE		0x000000F0
+/* Parity Error reported in addr or data phase */
+#define IFC_GPCM_ERATTR2_PERR_DATA_PHASE	0x00000001
+
+/*
+ * GPCM Status Register (GPCM_STAT)
+ */
+#define IFC_GPCM_STAT_BSY		0x80000000  /* GPCM is busy */
+
+/*
+ * IFC Controller NAND Machine registers
+ */
+struct fsl_ifc_nand {
+	__be32 ncfgr;
+	u32 res1[0x4];
+	__be32 nand_fcr0;
+	__be32 nand_fcr1;
+	u32 res2[0x8];
+	__be32 row0;
+	u32 res3;
+	__be32 col0;
+	u32 res4;
+	__be32 row1;
+	u32 res5;
+	__be32 col1;
+	u32 res6;
+	__be32 row2;
+	u32 res7;
+	__be32 col2;
+	u32 res8;
+	__be32 row3;
+	u32 res9;
+	__be32 col3;
+	u32 res10[0x24];
+	__be32 nand_fbcr;
+	u32 res11;
+	__be32 nand_fir0;
+	__be32 nand_fir1;
+	__be32 nand_fir2;
+	u32 res12[0x10];
+	__be32 nand_csel;
+	u32 res13;
+	__be32 nandseq_strt;
+	u32 res14;
+	__be32 nand_evter_stat;
+	u32 res15;
+	__be32 pgrdcmpl_evt_stat;
+	u32 res16[0x2];
+	__be32 nand_evter_en;
+	u32 res17[0x2];
+	__be32 nand_evter_intr_en;
+	u32 res18[0x2];
+	__be32 nand_erattr0;
+	__be32 nand_erattr1;
+	u32 res19[0x10];
+	__be32 nand_fsr;
+	u32 res20;
+	__be32 nand_eccstat[4];
+	u32 res21[0x20];
+	__be32 nanndcr;
+	u32 res22[0x2];
+	__be32 nand_autoboot_trgr;
+	u32 res23;
+	__be32 nand_mdr;
+	u32 res24[0x5C];
+};
+
+/*
+ * IFC controller NOR Machine registers
+ */
+struct fsl_ifc_nor {
+	__be32 nor_evter_stat;
+	u32 res1[0x2];
+	__be32 nor_evter_en;
+	u32 res2[0x2];
+	__be32 nor_evter_intr_en;
+	u32 res3[0x2];
+	__be32 nor_erattr0;
+	__be32 nor_erattr1;
+	__be32 nor_erattr2;
+	u32 res4[0x4];
+	__be32 norcr;
+	u32 res5[0xEF];
+};
+
+/*
+ * IFC controller GPCM Machine registers
+ */
+struct fsl_ifc_gpcm {
+	__be32 gpcm_evter_stat;
+	u32 res1[0x2];
+	__be32 gpcm_evter_en;
+	u32 res2[0x2];
+	__be32 gpcm_evter_intr_en;
+	u32 res3[0x2];
+	__be32 gpcm_erattr0;
+	__be32 gpcm_erattr1;
+	__be32 gpcm_erattr2;
+	__be32 gpcm_stat;
+	u32 res4[0x1F3];
+};
+
+/*
+ * IFC Controller Registers
+ */
+struct fsl_ifc_regs {
+	__be32 ifc_rev;
+	u32 res1[0x2];
+	struct {
+		__be32 cspr_ext;
+		__be32 cspr;
+		u32 res2;
+	} cspr_cs[FSL_IFC_BANK_COUNT];
+	u32 res3[0x19];
+	struct {
+		__be32 amask;
+		u32 res4[0x2];
+	} amask_cs[FSL_IFC_BANK_COUNT];
+	u32 res5[0x17];
+	struct {
+		__be32 csor_ext;
+		__be32 csor;
+		u32 res6;
+	} csor_cs[FSL_IFC_BANK_COUNT];
+	u32 res7[0x19];
+	struct {
+		__be32 ftim[4];
+		u32 res8[0x8];
+	} ftim_cs[FSL_IFC_BANK_COUNT];
+	u32 res9[0x60];
+	__be32 rb_stat;
+	u32 res10[0x2];
+	__be32 ifc_gcr;
+	u32 res11[0x2];
+	__be32 cm_evter_stat;
+	u32 res12[0x2];
+	__be32 cm_evter_en;
+	u32 res13[0x2];
+	__be32 cm_evter_intr_en;
+	u32 res14[0x2];
+	__be32 cm_erattr0;
+	__be32 cm_erattr1;
+	u32 res15[0x2];
+	__be32 ifc_ccr;
+	__be32 ifc_csr;
+	u32 res16[0x2EB];
+	struct fsl_ifc_nand ifc_nand;
+	struct fsl_ifc_nor ifc_nor;
+	struct fsl_ifc_gpcm ifc_gpcm;
+};
+
+extern unsigned int convert_ifc_address(phys_addr_t addr_base);
+extern int fsl_ifc_find(phys_addr_t addr_base);
+
+/* overview of the fsl ifc controller */
+
+struct fsl_ifc_ctrl {
+	/* device info */
+	struct device			*dev;
+	struct fsl_ifc_regs __iomem	*regs;
+	int				irq;
+	int				nand_irq;
+	spinlock_t			lock;
+	void				*nand;
+
+	u32 nand_stat;
+	wait_queue_head_t nand_wait;
+};
+
+extern struct fsl_ifc_ctrl *fsl_ifc_ctrl_dev;
+
+
+#endif /* __ASM_FSL_IFC_H */
-- 
cgit v1.2.3


From 67bad2fdb754dbef14596c0b5d28b3a12c8dfe84 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Sat, 8 Feb 2014 13:34:09 +0100
Subject: cpu: add generic support for CPU feature based module autoloading

This patch adds support for advertising optional CPU features over udev
using the modalias, and for declaring compatibility with/dependency upon
such a feature in a module.

The mapping between feature numbers and actual features should be provided
by the architecture in a file called <asm/cpufeature.h> which exports the
following functions/macros:
- cpu_feature(FEAT), a preprocessor macro that maps token FEAT to a
  numeric index;
- bool cpu_have_feature(n), returning whether this CPU has support for
  feature #n;
- MAX_CPU_FEATURES, an upper bound for 'n' in the previous function.

The feature can then be enabled by setting CONFIG_GENERIC_CPU_AUTOPROBE
for the architecture.

For instance, a module that registers its module init function using

  module_cpu_feature_match(FEAT_X, module_init_function)

will be probed automatically when the CPU's support for the 'FEAT_X'
feature is advertised over udev, and will only allow the module to be
loaded by hand if the 'FEAT_X' feature is supported.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/Kconfig              |  8 ++++++
 drivers/base/cpu.c                | 50 ++++++++++++++++++++++++++++----
 include/linux/cpufeature.h        | 60 +++++++++++++++++++++++++++++++++++++++
 include/linux/mod_devicetable.h   |  9 ++++++
 scripts/mod/devicetable-offsets.c |  3 ++
 scripts/mod/file2alias.c          | 10 +++++++
 6 files changed, 135 insertions(+), 5 deletions(-)
 create mode 100644 include/linux/cpufeature.h

(limited to 'include/linux')

diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index ec36e7772e57..3f0d3732df7f 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -185,6 +185,14 @@ config GENERIC_CPU_DEVICES
 	bool
 	default n
 
+config HAVE_CPU_AUTOPROBE
+	def_bool ARCH_HAS_CPU_AUTOPROBE
+
+config GENERIC_CPU_AUTOPROBE
+	bool
+	depends on !ARCH_HAS_CPU_AUTOPROBE
+	select HAVE_CPU_AUTOPROBE
+
 config SOC_BUS
 	bool
 
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index f48370dfc908..8a38bf8c792f 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -15,6 +15,7 @@
 #include <linux/percpu.h>
 #include <linux/acpi.h>
 #include <linux/of.h>
+#include <linux/cpufeature.h>
 
 #include "base.h"
 
@@ -286,6 +287,45 @@ static void cpu_device_release(struct device *dev)
 	 */
 }
 
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
+#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
+static ssize_t print_cpu_modalias(struct device *dev,
+				  struct device_attribute *attr,
+				  char *buf)
+{
+	ssize_t n;
+	u32 i;
+
+	n = sprintf(buf, "cpu:type:" CPU_FEATURE_TYPEFMT ":feature:",
+		    CPU_FEATURE_TYPEVAL);
+
+	for (i = 0; i < MAX_CPU_FEATURES; i++)
+		if (cpu_have_feature(i)) {
+			if (PAGE_SIZE < n + sizeof(",XXXX\n")) {
+				WARN(1, "CPU features overflow page\n");
+				break;
+			}
+			n += sprintf(&buf[n], ",%04X", i);
+		}
+	buf[n++] = '\n';
+	return n;
+}
+#else
+#define print_cpu_modalias	arch_print_cpu_modalias
+#endif
+
+static int cpu_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	char *buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (buf) {
+		print_cpu_modalias(NULL, NULL, buf);
+		add_uevent_var(env, "MODALIAS=%s", buf);
+		kfree(buf);
+	}
+	return 0;
+}
+#endif
+
 /*
  * register_cpu - Setup a sysfs device for a CPU.
  * @cpu - cpu->hotpluggable field set to 1 will generate a control file in
@@ -306,8 +346,8 @@ int register_cpu(struct cpu *cpu, int num)
 	cpu->dev.offline_disabled = !cpu->hotpluggable;
 	cpu->dev.offline = !cpu_online(num);
 	cpu->dev.of_node = of_get_cpu_node(num, NULL);
-#ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE
-	cpu->dev.bus->uevent = arch_cpu_uevent;
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
+	cpu->dev.bus->uevent = cpu_uevent;
 #endif
 	cpu->dev.groups = common_cpu_attr_groups;
 	if (cpu->hotpluggable)
@@ -330,8 +370,8 @@ struct device *get_cpu_device(unsigned cpu)
 }
 EXPORT_SYMBOL_GPL(get_cpu_device);
 
-#ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE
-static DEVICE_ATTR(modalias, 0444, arch_print_cpu_modalias, NULL);
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
+static DEVICE_ATTR(modalias, 0444, print_cpu_modalias, NULL);
 #endif
 
 static struct attribute *cpu_root_attrs[] = {
@@ -344,7 +384,7 @@ static struct attribute *cpu_root_attrs[] = {
 	&cpu_attrs[2].attr.attr,
 	&dev_attr_kernel_max.attr,
 	&dev_attr_offline.attr,
-#ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE
+#ifdef CONFIG_HAVE_CPU_AUTOPROBE
 	&dev_attr_modalias.attr,
 #endif
 	NULL
diff --git a/include/linux/cpufeature.h b/include/linux/cpufeature.h
new file mode 100644
index 000000000000..c4d4eb8ac9fe
--- /dev/null
+++ b/include/linux/cpufeature.h
@@ -0,0 +1,60 @@
+/*
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_CPUFEATURE_H
+#define __LINUX_CPUFEATURE_H
+
+#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
+
+#include <linux/mod_devicetable.h>
+#include <asm/cpufeature.h>
+
+/*
+ * Macros imported from <asm/cpufeature.h>:
+ * - cpu_feature(x)		ordinal value of feature called 'x'
+ * - cpu_have_feature(u32 n)	whether feature #n is available
+ * - MAX_CPU_FEATURES		upper bound for feature ordinal values
+ * Optional:
+ * - CPU_FEATURE_TYPEFMT	format string fragment for printing the cpu type
+ * - CPU_FEATURE_TYPEVAL	set of values matching the format string above
+ */
+
+#ifndef CPU_FEATURE_TYPEFMT
+#define CPU_FEATURE_TYPEFMT	"%s"
+#endif
+
+#ifndef CPU_FEATURE_TYPEVAL
+#define CPU_FEATURE_TYPEVAL	ELF_PLATFORM
+#endif
+
+/*
+ * Use module_cpu_feature_match(feature, module_init_function) to
+ * declare that
+ * a) the module shall be probed upon discovery of CPU feature 'feature'
+ *    (typically at boot time using udev)
+ * b) the module must not be loaded if CPU feature 'feature' is not present
+ *    (not even by manual insmod).
+ *
+ * For a list of legal values for 'feature', please consult the file
+ * 'asm/cpufeature.h' of your favorite architecture.
+ */
+#define module_cpu_feature_match(x, __init)			\
+static struct cpu_feature const cpu_feature_match_ ## x[] =	\
+	{ { .feature = cpu_feature(x) }, { } };			\
+MODULE_DEVICE_TABLE(cpu, cpu_feature_match_ ## x);		\
+								\
+static int cpu_feature_match_ ## x ## _init(void)		\
+{								\
+	if (!cpu_have_feature(cpu_feature(x)))			\
+		return -ENODEV;					\
+	return __init();					\
+}								\
+module_init(cpu_feature_match_ ## x ## _init)
+
+#endif
+#endif
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 45e921401b06..f2ac87c613a5 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -564,6 +564,15 @@ struct x86_cpu_id {
 #define X86_MODEL_ANY  0
 #define X86_FEATURE_ANY 0	/* Same as FPU, you can't test for that */
 
+/*
+ * Generic table type for matching CPU features.
+ * @feature:	the bit number of the feature (0 - 65535)
+ */
+
+struct cpu_feature {
+	__u16	feature;
+};
+
 #define IPACK_ANY_FORMAT 0xff
 #define IPACK_ANY_ID (~0)
 struct ipack_device_id {
diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c
index bb5d115ca671..f282516acc7b 100644
--- a/scripts/mod/devicetable-offsets.c
+++ b/scripts/mod/devicetable-offsets.c
@@ -174,6 +174,9 @@ int main(void)
 	DEVID_FIELD(x86_cpu_id, model);
 	DEVID_FIELD(x86_cpu_id, vendor);
 
+	DEVID(cpu_feature);
+	DEVID_FIELD(cpu_feature, feature);
+
 	DEVID(mei_cl_device_id);
 	DEVID_FIELD(mei_cl_device_id, name);
 
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index 25e5cb0aaef6..506146e5f4a8 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -1135,6 +1135,16 @@ static int do_x86cpu_entry(const char *filename, void *symval,
 }
 ADD_TO_DEVTABLE("x86cpu", x86_cpu_id, do_x86cpu_entry);
 
+/* LOOKS like cpu:type:*:feature:*FEAT* */
+static int do_cpu_entry(const char *filename, void *symval, char *alias)
+{
+	DEF_FIELD(symval, cpu_feature, feature);
+
+	sprintf(alias, "cpu:type:*:feature:*%04X*", feature);
+	return 1;
+}
+ADD_TO_DEVTABLE("cpu", cpu_feature, do_cpu_entry);
+
 /* Looks like: mei:S */
 static int do_mei_entry(const char *filename, void *symval,
 			char *alias)
-- 
cgit v1.2.3


From 2b9c1f03278ab7cd421f14ce24dee39091ecb064 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Sat, 8 Feb 2014 13:34:10 +0100
Subject: x86: align x86 arch with generic CPU modalias handling

The x86 CPU feature modalias handling existed before it was reimplemented
generically. This patch aligns the x86 handling so that it
(a) reuses some more code that is now generic;
(b) uses the generic format for the modalias module metadata entry, i.e., it
    now uses 'cpu:type:x86,venVVVVfamFFFFmodMMMM:feature:,XXXX,YYYY' instead of
    the 'x86cpu:vendor:VVVV:family:FFFF:model:MMMM:feature:,XXXX,YYYY' that was
    used before.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: H. Peter Anvin <hpa@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/x86/Kconfig                  |  4 +---
 arch/x86/include/asm/cpufeature.h |  7 +++++++
 arch/x86/kernel/cpu/match.c       | 42 ---------------------------------------
 drivers/base/Kconfig              |  5 -----
 drivers/base/cpu.c                | 10 +++-------
 include/linux/cpu.h               |  7 -------
 scripts/mod/file2alias.c          | 10 +++++-----
 7 files changed, 16 insertions(+), 69 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0af5250d914f..7fab7e0b1a72 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -127,6 +127,7 @@ config X86
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64
 	select HAVE_CC_STACKPROTECTOR
+	select GENERIC_CPU_AUTOPROBE
 
 config INSTRUCTION_DECODER
 	def_bool y
@@ -195,9 +196,6 @@ config ARCH_HAS_CPU_RELAX
 config ARCH_HAS_CACHE_LINE_SIZE
 	def_bool y
 
-config ARCH_HAS_CPU_AUTOPROBE
-	def_bool y
-
 config HAVE_SETUP_PER_CPU_AREA
 	def_bool y
 
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index e099f9502ace..d86dc3deea6a 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -541,6 +541,13 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
 #define static_cpu_has_bug(bit)	static_cpu_has((bit))
 #define boot_cpu_has_bug(bit)	cpu_has_bug(&boot_cpu_data, (bit))
 
+#define MAX_CPU_FEATURES	(NCAPINTS * 32)
+#define cpu_have_feature	boot_cpu_has
+
+#define CPU_FEATURE_TYPEFMT	"x86,ven%04Xfam%04Xmod%04X"
+#define CPU_FEATURE_TYPEVAL	boot_cpu_data.x86_vendor, boot_cpu_data.x86, \
+				boot_cpu_data.x86_model
+
 #endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */
 
 #endif /* _ASM_X86_CPUFEATURE_H */
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index 36565373af87..afa9f0d487ea 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -47,45 +47,3 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match)
 	return NULL;
 }
 EXPORT_SYMBOL(x86_match_cpu);
-
-ssize_t arch_print_cpu_modalias(struct device *dev,
-				struct device_attribute *attr,
-				char *bufptr)
-{
-	int size = PAGE_SIZE;
-	int i, n;
-	char *buf = bufptr;
-
-	n = snprintf(buf, size, "x86cpu:vendor:%04X:family:%04X:"
-		     "model:%04X:feature:",
-		boot_cpu_data.x86_vendor,
-		boot_cpu_data.x86,
-		boot_cpu_data.x86_model);
-	size -= n;
-	buf += n;
-	size -= 1;
-	for (i = 0; i < NCAPINTS*32; i++) {
-		if (boot_cpu_has(i)) {
-			n = snprintf(buf, size, ",%04X", i);
-			if (n >= size) {
-				WARN(1, "x86 features overflow page\n");
-				break;
-			}
-			size -= n;
-			buf += n;
-		}
-	}
-	*buf++ = '\n';
-	return buf - bufptr;
-}
-
-int arch_cpu_uevent(struct device *dev, struct kobj_uevent_env *env)
-{
-	char *buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
-	if (buf) {
-		arch_print_cpu_modalias(NULL, NULL, buf);
-		add_uevent_var(env, "MODALIAS=%s", buf);
-		kfree(buf);
-	}
-	return 0;
-}
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index 3f0d3732df7f..8fa8deab6449 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -185,13 +185,8 @@ config GENERIC_CPU_DEVICES
 	bool
 	default n
 
-config HAVE_CPU_AUTOPROBE
-	def_bool ARCH_HAS_CPU_AUTOPROBE
-
 config GENERIC_CPU_AUTOPROBE
 	bool
-	depends on !ARCH_HAS_CPU_AUTOPROBE
-	select HAVE_CPU_AUTOPROBE
 
 config SOC_BUS
 	bool
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 8a38bf8c792f..006b1bc5297d 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -287,7 +287,6 @@ static void cpu_device_release(struct device *dev)
 	 */
 }
 
-#ifdef CONFIG_HAVE_CPU_AUTOPROBE
 #ifdef CONFIG_GENERIC_CPU_AUTOPROBE
 static ssize_t print_cpu_modalias(struct device *dev,
 				  struct device_attribute *attr,
@@ -310,9 +309,6 @@ static ssize_t print_cpu_modalias(struct device *dev,
 	buf[n++] = '\n';
 	return n;
 }
-#else
-#define print_cpu_modalias	arch_print_cpu_modalias
-#endif
 
 static int cpu_uevent(struct device *dev, struct kobj_uevent_env *env)
 {
@@ -346,7 +342,7 @@ int register_cpu(struct cpu *cpu, int num)
 	cpu->dev.offline_disabled = !cpu->hotpluggable;
 	cpu->dev.offline = !cpu_online(num);
 	cpu->dev.of_node = of_get_cpu_node(num, NULL);
-#ifdef CONFIG_HAVE_CPU_AUTOPROBE
+#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
 	cpu->dev.bus->uevent = cpu_uevent;
 #endif
 	cpu->dev.groups = common_cpu_attr_groups;
@@ -370,7 +366,7 @@ struct device *get_cpu_device(unsigned cpu)
 }
 EXPORT_SYMBOL_GPL(get_cpu_device);
 
-#ifdef CONFIG_HAVE_CPU_AUTOPROBE
+#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
 static DEVICE_ATTR(modalias, 0444, print_cpu_modalias, NULL);
 #endif
 
@@ -384,7 +380,7 @@ static struct attribute *cpu_root_attrs[] = {
 	&cpu_attrs[2].attr.attr,
 	&dev_attr_kernel_max.attr,
 	&dev_attr_offline.attr,
-#ifdef CONFIG_HAVE_CPU_AUTOPROBE
+#ifdef CONFIG_GENERIC_CPU_AUTOPROBE
 	&dev_attr_modalias.attr,
 #endif
 	NULL
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 03e235ad1bba..03e962e23eaf 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -46,13 +46,6 @@ extern ssize_t arch_cpu_release(const char *, size_t);
 #endif
 struct notifier_block;
 
-#ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE
-extern int arch_cpu_uevent(struct device *dev, struct kobj_uevent_env *env);
-extern ssize_t arch_print_cpu_modalias(struct device *dev,
-				       struct device_attribute *attr,
-				       char *bufptr);
-#endif
-
 /*
  * CPU notifier priorities.
  */
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index 506146e5f4a8..25f6f5970552 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -1110,7 +1110,7 @@ static int do_amba_entry(const char *filename,
 }
 ADD_TO_DEVTABLE("amba", amba_id, do_amba_entry);
 
-/* LOOKS like x86cpu:vendor:VVVV:family:FFFF:model:MMMM:feature:*,FEAT,*
+/* LOOKS like cpu:type:x86,venVVVVfamFFFFmodMMMM:feature:*,FEAT,*
  * All fields are numbers. It would be nicer to use strings for vendor
  * and feature, but getting those out of the build system here is too
  * complicated.
@@ -1124,10 +1124,10 @@ static int do_x86cpu_entry(const char *filename, void *symval,
 	DEF_FIELD(symval, x86_cpu_id, model);
 	DEF_FIELD(symval, x86_cpu_id, vendor);
 
-	strcpy(alias, "x86cpu:");
-	ADD(alias, "vendor:",  vendor != X86_VENDOR_ANY, vendor);
-	ADD(alias, ":family:", family != X86_FAMILY_ANY, family);
-	ADD(alias, ":model:",  model  != X86_MODEL_ANY,  model);
+	strcpy(alias, "cpu:type:x86,");
+	ADD(alias, "ven", vendor != X86_VENDOR_ANY, vendor);
+	ADD(alias, "fam", family != X86_FAMILY_ANY, family);
+	ADD(alias, "mod", model  != X86_MODEL_ANY,  model);
 	strcat(alias, ":feature:*");
 	if (feature != X86_FEATURE_ANY)
 		sprintf(alias + strlen(alias), "%04X*", feature);
-- 
cgit v1.2.3


From c957dd494615ccdb36d4892ef9bfd2287502fbfd Mon Sep 17 00:00:00 2001
From: Sachin Kamat <sachin.kamat@linaro.org>
Date: Mon, 17 Feb 2014 15:19:18 +0530
Subject: tty: tty_ldisc.h: Remove duplicate include

linux/wait.h was included twice.

Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/tty_ldisc.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h
index b8347c207cb8..add26da2faeb 100644
--- a/include/linux/tty_ldisc.h
+++ b/include/linux/tty_ldisc.h
@@ -126,7 +126,6 @@
 
 #include <linux/fs.h>
 #include <linux/wait.h>
-#include <linux/wait.h>
 
 
 /*
-- 
cgit v1.2.3


From f8ff080dacecc5d0ce3579941b664bac3a4405c2 Mon Sep 17 00:00:00 2001
From: Veaceslav Falico <vfalico@redhat.com>
Date: Tue, 18 Feb 2014 07:48:45 +0100
Subject: bonding: remove useless updating of slave->dev->last_rx

Now that all the logic is handled via last_arp_rx, we don't need to use
last_rx.

CC: Jay Vosburgh <fubar@us.ibm.com>
CC: Andy Gospodarek <andy@greyhouse.net>
CC: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Veaceslav Falico <vfalico@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c | 3 ---
 include/linux/netdevice.h       | 8 +-------
 2 files changed, 1 insertion(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index e7aab9a6a670..14e023de09d6 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1115,9 +1115,6 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 	slave = bond_slave_get_rcu(skb->dev);
 	bond = slave->bond;
 
-	if (bond->params.arp_interval)
-		slave->dev->last_rx = jiffies;
-
 	recv_probe = ACCESS_ONCE(bond->recv_probe);
 	if (recv_probe) {
 		ret = recv_probe(skb, bond, slave);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 430c51aed6a4..891432a994c0 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1312,13 +1312,7 @@ struct net_device {
 /*
  * Cache lines mostly used on receive path (including eth_type_trans())
  */
-	unsigned long		last_rx;	/* Time of last Rx
-						 * This should not be set in
-						 * drivers, unless really needed,
-						 * because network stack (bonding)
-						 * use it if/when necessary, to
-						 * avoid dirtying this cache line.
-						 */
+	unsigned long		last_rx;	/* Time of last Rx */
 
 	/* Interface address info used in eth_type_trans() */
 	unsigned char		*dev_addr;	/* hw address, (before bcast
-- 
cgit v1.2.3


From 328281b1cda4dfef5b86c255b0aba8a8a96e0dad Mon Sep 17 00:00:00 2001
From: Hanjun Guo <hanjun.guo@linaro.org>
Date: Wed, 19 Feb 2014 00:23:57 +0800
Subject: ACPI: Move BAD_MADT_ENTRY() to linux/acpi.h

BAD_MADT_ENTRY() is arch independent and will be used for all
architectures which parse MADT, so move it to linux/acpi.h to
reduce code duplication.

Signed-off-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/ia64/kernel/acpi.c     | 4 ----
 arch/x86/kernel/acpi/boot.c | 4 ----
 include/linux/acpi.h        | 4 ++++
 3 files changed, 4 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 07d209c9507f..467497ade45f 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -54,10 +54,6 @@
 #include <asm/sal.h>
 #include <asm/cyclone.h>
 
-#define BAD_MADT_ENTRY(entry, end) (                                        \
-		(!entry) || (unsigned long)entry + sizeof(*entry) > end ||  \
-		((struct acpi_subtable_header *)entry)->length < sizeof(*entry))
-
 #define PREFIX			"ACPI: "
 
 unsigned int acpi_cpei_override;
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 1dac94265b59..123f9e37eee4 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -53,10 +53,6 @@ EXPORT_SYMBOL(acpi_disabled);
 # include <asm/proto.h>
 #endif				/* X86 */
 
-#define BAD_MADT_ENTRY(entry, end) (					    \
-		(!entry) || (unsigned long)entry + sizeof(*entry) > end ||  \
-		((struct acpi_subtable_header *)entry)->length < sizeof(*entry))
-
 #define PREFIX			"ACPI: "
 
 int acpi_noirq;				/* skip ACPI IRQ initialization */
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 1151a1dcfe41..6a15dddbaa09 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -108,6 +108,10 @@ static inline void acpi_initrd_override(void *data, size_t size)
 }
 #endif
 
+#define BAD_MADT_ENTRY(entry, end) (					    \
+		(!entry) || (unsigned long)entry + sizeof(*entry) > end ||  \
+		((struct acpi_subtable_header *)entry)->length < sizeof(*entry))
+
 char * __acpi_map_table (unsigned long phys_addr, unsigned long size);
 void __acpi_unmap_table(char *map, unsigned long size);
 int early_acpi_boot_init(void);
-- 
cgit v1.2.3


From 603597c9375b8162edae3231dd4cc7f1f500de79 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Tue, 18 Feb 2014 15:57:35 +0100
Subject: ASoC: Add ADAU1977 CODEC driver

This patch adds support for the ADAU1977, ADAU1978 and ADAU1979 audio CODEC
devices. They are a family of 4-channel differential input audio ADC devices.
They can be connected to either a SPI or I2C bus. The driver is implemented in
three modules, one main module (adau1977.ko) which implements the device logic
and one module each for SPI (adau1977-spi.ko) and I2C (adau1977-i2c.ko) bus
access.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/linux/platform_data/adau1977.h |   45 ++
 sound/soc/codecs/Kconfig               |   15 +
 sound/soc/codecs/Makefile              |    6 +
 sound/soc/codecs/adau1977-i2c.c        |   59 ++
 sound/soc/codecs/adau1977-spi.c        |   76 +++
 sound/soc/codecs/adau1977.c            | 1018 ++++++++++++++++++++++++++++++++
 sound/soc/codecs/adau1977.h            |   37 ++
 7 files changed, 1256 insertions(+)
 create mode 100644 include/linux/platform_data/adau1977.h
 create mode 100644 sound/soc/codecs/adau1977-i2c.c
 create mode 100644 sound/soc/codecs/adau1977-spi.c
 create mode 100644 sound/soc/codecs/adau1977.c
 create mode 100644 sound/soc/codecs/adau1977.h

(limited to 'include/linux')

diff --git a/include/linux/platform_data/adau1977.h b/include/linux/platform_data/adau1977.h
new file mode 100644
index 000000000000..bed11d908f92
--- /dev/null
+++ b/include/linux/platform_data/adau1977.h
@@ -0,0 +1,45 @@
+/*
+ * ADAU1977/ADAU1978/ADAU1979 driver
+ *
+ * Copyright 2014 Analog Devices Inc.
+ *  Author: Lars-Peter Clausen <lars@metafoo.de>
+ *
+ * Licensed under the GPL-2.
+ */
+
+#ifndef __LINUX_PLATFORM_DATA_ADAU1977_H__
+#define __LINUX_PLATFORM_DATA_ADAU1977_H__
+
+/**
+ * enum adau1977_micbias - ADAU1977 MICBIAS pin voltage setting
+ * @ADAU1977_MICBIAS_5V0: MICBIAS is set to 5.0 V
+ * @ADAU1977_MICBIAS_5V5: MICBIAS is set to 5.5 V
+ * @ADAU1977_MICBIAS_6V0: MICBIAS is set to 6.0 V
+ * @ADAU1977_MICBIAS_6V5: MICBIAS is set to 6.5 V
+ * @ADAU1977_MICBIAS_7V0: MICBIAS is set to 7.0 V
+ * @ADAU1977_MICBIAS_7V5: MICBIAS is set to 7.5 V
+ * @ADAU1977_MICBIAS_8V0: MICBIAS is set to 8.0 V
+ * @ADAU1977_MICBIAS_8V5: MICBIAS is set to 8.5 V
+ * @ADAU1977_MICBIAS_9V0: MICBIAS is set to 9.0 V
+ */
+enum adau1977_micbias {
+	ADAU1977_MICBIAS_5V0 = 0x0,
+	ADAU1977_MICBIAS_5V5 = 0x1,
+	ADAU1977_MICBIAS_6V0 = 0x2,
+	ADAU1977_MICBIAS_6V5 = 0x3,
+	ADAU1977_MICBIAS_7V0 = 0x4,
+	ADAU1977_MICBIAS_7V5 = 0x5,
+	ADAU1977_MICBIAS_8V0 = 0x6,
+	ADAU1977_MICBIAS_8V5 = 0x7,
+	ADAU1977_MICBIAS_9V0 = 0x8,
+};
+
+/**
+ * struct adau1977_platform_data - Platform configuration data for the ADAU1977
+ * @micbias: Specifies the voltage for the MICBIAS pin
+ */
+struct adau1977_platform_data {
+	enum adau1977_micbias micbias;
+};
+
+#endif
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index 9ea428bdd872..4535674f6eba 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -24,6 +24,8 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_ADAU1373 if I2C
 	select SND_SOC_ADAV801 if SPI_MASTER
 	select SND_SOC_ADAV803 if I2C
+	select SND_SOC_ADAU1977_SPI if SPI_MASTER
+	select SND_SOC_ADAU1977_I2C if I2C
 	select SND_SOC_ADAU1701 if I2C
 	select SND_SOC_ADS117X
 	select SND_SOC_AK4104 if SPI_MASTER
@@ -200,6 +202,19 @@ config SND_SOC_ADAU1701
 config SND_SOC_ADAU1373
 	tristate
 
+config SND_SOC_ADAU1977
+	tristate
+
+config SND_SOC_ADAU1977_SPI
+	tristate
+	select SND_SOC_ADAU1977
+	select REGMAP_SPI
+
+config SND_SOC_ADAU1977_I2C
+	tristate
+	select SND_SOC_ADAU1977
+	select REGMAP_I2C
+
 config SND_SOC_ADAV80X
 	tristate
 
diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile
index 1b2c6eca863f..bfd85ec2dfa8 100644
--- a/sound/soc/codecs/Makefile
+++ b/sound/soc/codecs/Makefile
@@ -7,6 +7,9 @@ snd-soc-ad1980-objs := ad1980.o
 snd-soc-ad73311-objs := ad73311.o
 snd-soc-adau1701-objs := adau1701.o
 snd-soc-adau1373-objs := adau1373.o
+snd-soc-adau1977-objs := adau1977.o
+snd-soc-adau1977-spi-objs := adau1977-spi.o
+snd-soc-adau1977-i2c-objs := adau1977-i2c.o
 snd-soc-adav80x-objs := adav80x.o
 snd-soc-adav801-objs := adav801.o
 snd-soc-adav803-objs := adav803.o
@@ -139,6 +142,9 @@ obj-$(CONFIG_SND_SOC_AD193X)	+= snd-soc-ad193x.o
 obj-$(CONFIG_SND_SOC_AD1980)	+= snd-soc-ad1980.o
 obj-$(CONFIG_SND_SOC_AD73311) += snd-soc-ad73311.o
 obj-$(CONFIG_SND_SOC_ADAU1373)	+= snd-soc-adau1373.o
+obj-$(CONFIG_SND_SOC_ADAU1977)		+= snd-soc-adau1977.o
+obj-$(CONFIG_SND_SOC_ADAU1977_SPI)	+= snd-soc-adau1977-spi.o
+obj-$(CONFIG_SND_SOC_ADAU1977_I2C)	+= snd-soc-adau1977-i2c.o
 obj-$(CONFIG_SND_SOC_ADAU1701)  += snd-soc-adau1701.o
 obj-$(CONFIG_SND_SOC_ADAV80X)  += snd-soc-adav80x.o
 obj-$(CONFIG_SND_SOC_ADAV801)  += snd-soc-adav801.o
diff --git a/sound/soc/codecs/adau1977-i2c.c b/sound/soc/codecs/adau1977-i2c.c
new file mode 100644
index 000000000000..9700e8c838c9
--- /dev/null
+++ b/sound/soc/codecs/adau1977-i2c.c
@@ -0,0 +1,59 @@
+/*
+ * ADAU1977/ADAU1978/ADAU1979 driver
+ *
+ * Copyright 2014 Analog Devices Inc.
+ *  Author: Lars-Peter Clausen <lars@metafoo.de>
+ *
+ * Licensed under the GPL-2.
+ */
+
+#include <linux/i2c.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <sound/soc.h>
+
+#include "adau1977.h"
+
+static int adau1977_i2c_probe(struct i2c_client *client,
+	const struct i2c_device_id *id)
+{
+	struct regmap_config config;
+
+	config = adau1977_regmap_config;
+	config.val_bits = 8;
+	config.reg_bits = 8;
+
+	return adau1977_probe(&client->dev,
+		devm_regmap_init_i2c(client, &config),
+		id->driver_data, NULL);
+}
+
+static int adau1977_i2c_remove(struct i2c_client *client)
+{
+	snd_soc_unregister_codec(&client->dev);
+	return 0;
+}
+
+static const struct i2c_device_id adau1977_i2c_ids[] = {
+	{ "adau1977", ADAU1977 },
+	{ "adau1978", ADAU1978 },
+	{ "adau1979", ADAU1978 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, adau1977_i2c_ids);
+
+static struct i2c_driver adau1977_i2c_driver = {
+	.driver = {
+		.name = "adau1977",
+		.owner = THIS_MODULE,
+	},
+	.probe = adau1977_i2c_probe,
+	.remove = adau1977_i2c_remove,
+	.id_table = adau1977_i2c_ids,
+};
+module_i2c_driver(adau1977_i2c_driver);
+
+MODULE_DESCRIPTION("ASoC ADAU1977/ADAU1978/ADAU1979 driver");
+MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/adau1977-spi.c b/sound/soc/codecs/adau1977-spi.c
new file mode 100644
index 000000000000..b05cf5da3a94
--- /dev/null
+++ b/sound/soc/codecs/adau1977-spi.c
@@ -0,0 +1,76 @@
+/*
+ * ADAU1977/ADAU1978/ADAU1979 driver
+ *
+ * Copyright 2014 Analog Devices Inc.
+ *  Author: Lars-Peter Clausen <lars@metafoo.de>
+ *
+ * Licensed under the GPL-2.
+ */
+
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/spi/spi.h>
+#include <sound/soc.h>
+
+#include "adau1977.h"
+
+static void adau1977_spi_switch_mode(struct device *dev)
+{
+	struct spi_device *spi = to_spi_device(dev);
+
+	/*
+	 * To get the device into SPI mode CLATCH has to be pulled low three
+	 * times.  Do this by issuing three dummy reads.
+	 */
+	spi_w8r8(spi, 0x00);
+	spi_w8r8(spi, 0x00);
+	spi_w8r8(spi, 0x00);
+}
+
+static int adau1977_spi_probe(struct spi_device *spi)
+{
+	const struct spi_device_id *id = spi_get_device_id(spi);
+	struct regmap_config config;
+
+	if (!id)
+		return -EINVAL;
+
+	config = adau1977_regmap_config;
+	config.val_bits = 8;
+	config.reg_bits = 16;
+	config.read_flag_mask = 0x1;
+
+	return adau1977_probe(&spi->dev,
+		devm_regmap_init_spi(spi, &config),
+		id->driver_data, adau1977_spi_switch_mode);
+}
+
+static int adau1977_spi_remove(struct spi_device *spi)
+{
+	snd_soc_unregister_codec(&spi->dev);
+	return 0;
+}
+
+static const struct spi_device_id adau1977_spi_ids[] = {
+	{ "adau1977", ADAU1977 },
+	{ "adau1978", ADAU1978 },
+	{ "adau1979", ADAU1978 },
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, adau1977_spi_ids);
+
+static struct spi_driver adau1977_spi_driver = {
+	.driver = {
+		.name = "adau1977",
+		.owner = THIS_MODULE,
+	},
+	.probe = adau1977_spi_probe,
+	.remove = adau1977_spi_remove,
+	.id_table = adau1977_spi_ids,
+};
+module_spi_driver(adau1977_spi_driver);
+
+MODULE_DESCRIPTION("ASoC ADAU1977/ADAU1978/ADAU1979 driver");
+MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/adau1977.c b/sound/soc/codecs/adau1977.c
new file mode 100644
index 000000000000..fd55da7cb9d4
--- /dev/null
+++ b/sound/soc/codecs/adau1977.c
@@ -0,0 +1,1018 @@
+/*
+ * ADAU1977/ADAU1978/ADAU1979 driver
+ *
+ * Copyright 2014 Analog Devices Inc.
+ *  Author: Lars-Peter Clausen <lars@metafoo.de>
+ *
+ * Licensed under the GPL-2.
+ */
+
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/gpio/consumer.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/platform_data/adau1977.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+#include <linux/slab.h>
+
+#include <sound/core.h>
+#include <sound/initval.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/tlv.h>
+
+#include "adau1977.h"
+
+#define ADAU1977_REG_POWER		0x00
+#define ADAU1977_REG_PLL		0x01
+#define ADAU1977_REG_BOOST		0x02
+#define ADAU1977_REG_MICBIAS		0x03
+#define ADAU1977_REG_BLOCK_POWER_SAI	0x04
+#define ADAU1977_REG_SAI_CTRL0		0x05
+#define ADAU1977_REG_SAI_CTRL1		0x06
+#define ADAU1977_REG_CMAP12		0x07
+#define ADAU1977_REG_CMAP34		0x08
+#define ADAU1977_REG_SAI_OVERTEMP	0x09
+#define ADAU1977_REG_POST_ADC_GAIN(x)	(0x0a + (x))
+#define ADAU1977_REG_MISC_CONTROL	0x0e
+#define ADAU1977_REG_DIAG_CONTROL	0x10
+#define ADAU1977_REG_STATUS(x)		(0x11 + (x))
+#define ADAU1977_REG_DIAG_IRQ1		0x15
+#define ADAU1977_REG_DIAG_IRQ2		0x16
+#define ADAU1977_REG_ADJUST1		0x17
+#define ADAU1977_REG_ADJUST2		0x18
+#define ADAU1977_REG_ADC_CLIP		0x19
+#define ADAU1977_REG_DC_HPF_CAL		0x1a
+
+#define ADAU1977_POWER_RESET			BIT(7)
+#define ADAU1977_POWER_PWUP			BIT(0)
+
+#define ADAU1977_PLL_CLK_S			BIT(4)
+#define ADAU1977_PLL_MCS_MASK			0x7
+
+#define ADAU1977_MICBIAS_MB_VOLTS_MASK		0xf0
+#define ADAU1977_MICBIAS_MB_VOLTS_OFFSET	4
+
+#define ADAU1977_BLOCK_POWER_SAI_LR_POL		BIT(7)
+#define ADAU1977_BLOCK_POWER_SAI_BCLK_EDGE	BIT(6)
+#define ADAU1977_BLOCK_POWER_SAI_LDO_EN		BIT(5)
+
+#define ADAU1977_SAI_CTRL0_FMT_MASK		(0x3 << 6)
+#define ADAU1977_SAI_CTRL0_FMT_I2S		(0x0 << 6)
+#define ADAU1977_SAI_CTRL0_FMT_LJ		(0x1 << 6)
+#define ADAU1977_SAI_CTRL0_FMT_RJ_24BIT		(0x2 << 6)
+#define ADAU1977_SAI_CTRL0_FMT_RJ_16BIT		(0x3 << 6)
+
+#define ADAU1977_SAI_CTRL0_SAI_MASK		(0x7 << 3)
+#define ADAU1977_SAI_CTRL0_SAI_I2S		(0x0 << 3)
+#define ADAU1977_SAI_CTRL0_SAI_TDM_2		(0x1 << 3)
+#define ADAU1977_SAI_CTRL0_SAI_TDM_4		(0x2 << 3)
+#define ADAU1977_SAI_CTRL0_SAI_TDM_8		(0x3 << 3)
+#define ADAU1977_SAI_CTRL0_SAI_TDM_16		(0x4 << 3)
+
+#define ADAU1977_SAI_CTRL0_FS_MASK		(0x7)
+#define ADAU1977_SAI_CTRL0_FS_8000_12000	(0x0)
+#define ADAU1977_SAI_CTRL0_FS_16000_24000	(0x1)
+#define ADAU1977_SAI_CTRL0_FS_32000_48000	(0x2)
+#define ADAU1977_SAI_CTRL0_FS_64000_96000	(0x3)
+#define ADAU1977_SAI_CTRL0_FS_128000_192000	(0x4)
+
+#define ADAU1977_SAI_CTRL1_SLOT_WIDTH_MASK	(0x3 << 5)
+#define ADAU1977_SAI_CTRL1_SLOT_WIDTH_32	(0x0 << 5)
+#define ADAU1977_SAI_CTRL1_SLOT_WIDTH_24	(0x1 << 5)
+#define ADAU1977_SAI_CTRL1_SLOT_WIDTH_16	(0x2 << 5)
+#define ADAU1977_SAI_CTRL1_DATA_WIDTH_MASK	(0x1 << 4)
+#define ADAU1977_SAI_CTRL1_DATA_WIDTH_16BIT	(0x1 << 4)
+#define ADAU1977_SAI_CTRL1_DATA_WIDTH_24BIT	(0x0 << 4)
+#define ADAU1977_SAI_CTRL1_LRCLK_PULSE		BIT(3)
+#define ADAU1977_SAI_CTRL1_MSB			BIT(2)
+#define ADAU1977_SAI_CTRL1_BCLKRATE_16		(0x1 << 1)
+#define ADAU1977_SAI_CTRL1_BCLKRATE_32		(0x0 << 1)
+#define ADAU1977_SAI_CTRL1_BCLKRATE_MASK	(0x1 << 1)
+#define ADAU1977_SAI_CTRL1_MASTER		BIT(0)
+
+#define ADAU1977_SAI_OVERTEMP_DRV_C(x)		BIT(4 + (x))
+#define ADAU1977_SAI_OVERTEMP_DRV_HIZ		BIT(3)
+
+#define ADAU1977_MISC_CONTROL_SUM_MODE_MASK	(0x3 << 6)
+#define ADAU1977_MISC_CONTROL_SUM_MODE_1CH	(0x2 << 6)
+#define ADAU1977_MISC_CONTROL_SUM_MODE_2CH	(0x1 << 6)
+#define ADAU1977_MISC_CONTROL_SUM_MODE_4CH	(0x0 << 6)
+#define ADAU1977_MISC_CONTROL_MMUTE		BIT(4)
+#define ADAU1977_MISC_CONTROL_DC_CAL		BIT(0)
+
+#define ADAU1977_CHAN_MAP_SECOND_SLOT_OFFSET	4
+#define ADAU1977_CHAN_MAP_FIRST_SLOT_OFFSET	0
+
+struct adau1977 {
+	struct regmap *regmap;
+	bool right_j;
+	unsigned int sysclk;
+	enum adau1977_sysclk_src sysclk_src;
+	struct gpio_desc *reset_gpio;
+	enum adau1977_type type;
+
+	struct regulator *avdd_reg;
+	struct regulator *dvdd_reg;
+
+	struct snd_pcm_hw_constraint_list constraints;
+
+	struct device *dev;
+	void (*switch_mode)(struct device *dev);
+
+	unsigned int max_master_fs;
+	unsigned int slot_width;
+	bool enabled;
+	bool master;
+};
+
+static const struct reg_default adau1977_reg_defaults[] = {
+	{ 0x00, 0x00 },
+	{ 0x01, 0x41 },
+	{ 0x02, 0x4a },
+	{ 0x03, 0x7d },
+	{ 0x04, 0x3d },
+	{ 0x05, 0x02 },
+	{ 0x06, 0x00 },
+	{ 0x07, 0x10 },
+	{ 0x08, 0x32 },
+	{ 0x09, 0xf0 },
+	{ 0x0a, 0xa0 },
+	{ 0x0b, 0xa0 },
+	{ 0x0c, 0xa0 },
+	{ 0x0d, 0xa0 },
+	{ 0x0e, 0x02 },
+	{ 0x10, 0x0f },
+	{ 0x15, 0x20 },
+	{ 0x16, 0x00 },
+	{ 0x17, 0x00 },
+	{ 0x18, 0x00 },
+	{ 0x1a, 0x00 },
+};
+
+static const DECLARE_TLV_DB_MINMAX_MUTE(adau1977_adc_gain, -3562, 6000);
+
+static const struct snd_soc_dapm_widget adau1977_micbias_dapm_widgets[] = {
+	SND_SOC_DAPM_SUPPLY("MICBIAS", ADAU1977_REG_MICBIAS,
+		3, 0, NULL, 0)
+};
+
+static const struct snd_soc_dapm_widget adau1977_dapm_widgets[] = {
+	SND_SOC_DAPM_SUPPLY("Vref", ADAU1977_REG_BLOCK_POWER_SAI,
+		4, 0, NULL, 0),
+
+	SND_SOC_DAPM_ADC("ADC1", "Capture", ADAU1977_REG_BLOCK_POWER_SAI, 0, 0),
+	SND_SOC_DAPM_ADC("ADC2", "Capture", ADAU1977_REG_BLOCK_POWER_SAI, 1, 0),
+	SND_SOC_DAPM_ADC("ADC3", "Capture", ADAU1977_REG_BLOCK_POWER_SAI, 2, 0),
+	SND_SOC_DAPM_ADC("ADC4", "Capture", ADAU1977_REG_BLOCK_POWER_SAI, 3, 0),
+
+	SND_SOC_DAPM_INPUT("AIN1"),
+	SND_SOC_DAPM_INPUT("AIN2"),
+	SND_SOC_DAPM_INPUT("AIN3"),
+	SND_SOC_DAPM_INPUT("AIN4"),
+
+	SND_SOC_DAPM_OUTPUT("VREF"),
+};
+
+static const struct snd_soc_dapm_route adau1977_dapm_routes[] = {
+	{ "ADC1", NULL, "AIN1" },
+	{ "ADC2", NULL, "AIN2" },
+	{ "ADC3", NULL, "AIN3" },
+	{ "ADC4", NULL, "AIN4" },
+
+	{ "ADC1", NULL, "Vref" },
+	{ "ADC2", NULL, "Vref" },
+	{ "ADC3", NULL, "Vref" },
+	{ "ADC4", NULL, "Vref" },
+
+	{ "VREF", NULL, "Vref" },
+};
+
+#define ADAU1977_VOLUME(x) \
+	SOC_SINGLE_TLV("ADC" #x " Capture Volume", \
+		ADAU1977_REG_POST_ADC_GAIN((x) - 1), \
+		0, 255, 1, adau1977_adc_gain)
+
+#define ADAU1977_HPF_SWITCH(x) \
+	SOC_SINGLE("ADC" #x " Highpass-Filter Capture Switch", \
+		ADAU1977_REG_DC_HPF_CAL, (x) - 1, 1, 0)
+
+#define ADAU1977_DC_SUB_SWITCH(x) \
+	SOC_SINGLE("ADC" #x " DC Substraction Capture Switch", \
+		ADAU1977_REG_DC_HPF_CAL, (x) + 3, 1, 0)
+
+static const struct snd_kcontrol_new adau1977_snd_controls[] = {
+	ADAU1977_VOLUME(1),
+	ADAU1977_VOLUME(2),
+	ADAU1977_VOLUME(3),
+	ADAU1977_VOLUME(4),
+
+	ADAU1977_HPF_SWITCH(1),
+	ADAU1977_HPF_SWITCH(2),
+	ADAU1977_HPF_SWITCH(3),
+	ADAU1977_HPF_SWITCH(4),
+
+	ADAU1977_DC_SUB_SWITCH(1),
+	ADAU1977_DC_SUB_SWITCH(2),
+	ADAU1977_DC_SUB_SWITCH(3),
+	ADAU1977_DC_SUB_SWITCH(4),
+};
+
+static int adau1977_reset(struct adau1977 *adau1977)
+{
+	int ret;
+
+	/*
+	 * The reset bit is obviously volatile, but we need to be able to cache
+	 * the other bits in the register, so we can't just mark the whole
+	 * register as volatile. Since this is the only place where we'll ever
+	 * touch the reset bit just bypass the cache for this operation.
+	 */
+	regcache_cache_bypass(adau1977->regmap, true);
+	ret = regmap_write(adau1977->regmap, ADAU1977_REG_POWER,
+			ADAU1977_POWER_RESET);
+	regcache_cache_bypass(adau1977->regmap, false);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+
+/*
+ * Returns the appropriate setting for ths FS field in the CTRL0 register
+ * depending on the rate.
+ */
+static int adau1977_lookup_fs(unsigned int rate)
+{
+	if (rate >= 8000 && rate <= 12000)
+		return ADAU1977_SAI_CTRL0_FS_8000_12000;
+	else if (rate >= 16000 && rate <= 24000)
+		return ADAU1977_SAI_CTRL0_FS_16000_24000;
+	else if (rate >= 32000 && rate <= 48000)
+		return ADAU1977_SAI_CTRL0_FS_32000_48000;
+	else if (rate >= 64000 && rate <= 96000)
+		return ADAU1977_SAI_CTRL0_FS_64000_96000;
+	else if (rate >= 128000 && rate <= 192000)
+		return ADAU1977_SAI_CTRL0_FS_128000_192000;
+	else
+		return -EINVAL;
+}
+
+static int adau1977_lookup_mcs(struct adau1977 *adau1977, unsigned int rate,
+	unsigned int fs)
+{
+	unsigned int mcs;
+
+	/*
+	 * rate = sysclk / (512 * mcs_lut[mcs]) * 2**fs
+	 * => mcs_lut[mcs] = sysclk / (512 * rate) * 2**fs
+	 * => mcs_lut[mcs] = sysclk / ((512 / 2**fs) * rate)
+	 */
+
+	rate *= 512 >> fs;
+
+	if (adau1977->sysclk % rate != 0)
+		return -EINVAL;
+
+	mcs = adau1977->sysclk / rate;
+
+	/* The factors configured by MCS are 1, 2, 3, 4, 6 */
+	if (mcs < 1 || mcs > 6 || mcs == 5)
+		return -EINVAL;
+
+	mcs = mcs - 1;
+	if (mcs == 5)
+		mcs = 4;
+
+	return mcs;
+}
+
+static int adau1977_hw_params(struct snd_pcm_substream *substream,
+	struct snd_pcm_hw_params *params, struct snd_soc_dai *dai)
+{
+	struct snd_soc_codec *codec = dai->codec;
+	struct adau1977 *adau1977 = snd_soc_codec_get_drvdata(codec);
+	unsigned int rate = params_rate(params);
+	unsigned int slot_width;
+	unsigned int ctrl0, ctrl0_mask;
+	unsigned int ctrl1;
+	int mcs, fs;
+	int ret;
+
+	fs = adau1977_lookup_fs(rate);
+	if (fs < 0)
+		return fs;
+
+	if (adau1977->sysclk_src == ADAU1977_SYSCLK_SRC_MCLK) {
+		mcs = adau1977_lookup_mcs(adau1977, rate, fs);
+		if (mcs < 0)
+			return mcs;
+	} else {
+		mcs = 0;
+	}
+
+	ctrl0_mask = ADAU1977_SAI_CTRL0_FS_MASK;
+	ctrl0 = fs;
+
+	if (adau1977->right_j) {
+		switch (params_width(params)) {
+		case 16:
+			ctrl0 |= ADAU1977_SAI_CTRL0_FMT_RJ_16BIT;
+			break;
+		case 24:
+			ctrl0 |= ADAU1977_SAI_CTRL0_FMT_RJ_24BIT;
+			break;
+		default:
+			return -EINVAL;
+		}
+		ctrl0_mask |= ADAU1977_SAI_CTRL0_FMT_MASK;
+	}
+
+	if (adau1977->master) {
+		switch (params_width(params)) {
+		case 16:
+			ctrl1 = ADAU1977_SAI_CTRL1_DATA_WIDTH_16BIT;
+			slot_width = 16;
+			break;
+		case 24:
+		case 32:
+			ctrl1 = ADAU1977_SAI_CTRL1_DATA_WIDTH_24BIT;
+			slot_width = 32;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		/* In TDM mode there is a fixed slot width */
+		if (adau1977->slot_width)
+			slot_width = adau1977->slot_width;
+
+		if (slot_width == 16)
+			ctrl1 |= ADAU1977_SAI_CTRL1_BCLKRATE_16;
+		else
+			ctrl1 |= ADAU1977_SAI_CTRL1_BCLKRATE_32;
+
+		ret = regmap_update_bits(adau1977->regmap,
+			ADAU1977_REG_SAI_CTRL1,
+			ADAU1977_SAI_CTRL1_DATA_WIDTH_MASK |
+			ADAU1977_SAI_CTRL1_BCLKRATE_MASK,
+			ctrl1);
+		if (ret < 0)
+			return ret;
+	}
+
+	ret = regmap_update_bits(adau1977->regmap, ADAU1977_REG_SAI_CTRL0,
+				ctrl0_mask, ctrl0);
+	if (ret < 0)
+		return ret;
+
+	return regmap_update_bits(adau1977->regmap, ADAU1977_REG_PLL,
+				ADAU1977_PLL_MCS_MASK, mcs);
+}
+
+static int adau1977_power_disable(struct adau1977 *adau1977)
+{
+	int ret = 0;
+
+	if (!adau1977->enabled)
+		return 0;
+
+	ret = regmap_update_bits(adau1977->regmap, ADAU1977_REG_POWER,
+		ADAU1977_POWER_PWUP, 0);
+	if (ret)
+		return ret;
+
+	regcache_mark_dirty(adau1977->regmap);
+
+	if (adau1977->reset_gpio)
+		gpiod_set_value_cansleep(adau1977->reset_gpio, 0);
+
+	regcache_cache_only(adau1977->regmap, true);
+
+	regulator_disable(adau1977->avdd_reg);
+	if (adau1977->dvdd_reg)
+		regulator_disable(adau1977->dvdd_reg);
+
+	adau1977->enabled = false;
+
+	return 0;
+}
+
+static int adau1977_power_enable(struct adau1977 *adau1977)
+{
+	unsigned int val;
+	int ret = 0;
+
+	if (adau1977->enabled)
+		return 0;
+
+	ret = regulator_enable(adau1977->avdd_reg);
+	if (ret)
+		return ret;
+
+	if (adau1977->dvdd_reg) {
+		ret = regulator_enable(adau1977->dvdd_reg);
+		if (ret)
+			goto err_disable_avdd;
+	}
+
+	if (adau1977->reset_gpio)
+		gpiod_set_value_cansleep(adau1977->reset_gpio, 1);
+
+	regcache_cache_only(adau1977->regmap, false);
+
+	if (adau1977->switch_mode)
+		adau1977->switch_mode(adau1977->dev);
+
+	ret = adau1977_reset(adau1977);
+	if (ret)
+		goto err_disable_dvdd;
+
+	ret = regmap_update_bits(adau1977->regmap, ADAU1977_REG_POWER,
+		ADAU1977_POWER_PWUP, ADAU1977_POWER_PWUP);
+	if (ret)
+		goto err_disable_dvdd;
+
+	ret = regcache_sync(adau1977->regmap);
+	if (ret)
+		goto err_disable_dvdd;
+
+	/*
+	 * The PLL register is not affected by the software reset. It is
+	 * possible that the value of the register was changed to the
+	 * default value while we were in cache only mode. In this case
+	 * regcache_sync will skip over it and we have to manually sync
+	 * it.
+	 */
+	ret = regmap_read(adau1977->regmap, ADAU1977_REG_PLL, &val);
+	if (ret)
+		goto err_disable_dvdd;
+
+	if (val == 0x41) {
+		regcache_cache_bypass(adau1977->regmap, true);
+		ret = regmap_write(adau1977->regmap, ADAU1977_REG_PLL,
+			0x41);
+		if (ret)
+			goto err_disable_dvdd;
+		regcache_cache_bypass(adau1977->regmap, false);
+	}
+
+	adau1977->enabled = true;
+
+	return ret;
+
+err_disable_dvdd:
+	if (adau1977->dvdd_reg)
+		regulator_disable(adau1977->dvdd_reg);
+err_disable_avdd:
+		regulator_disable(adau1977->avdd_reg);
+	return ret;
+}
+
+static int adau1977_set_bias_level(struct snd_soc_codec *codec,
+	enum snd_soc_bias_level level)
+{
+	struct adau1977 *adau1977 = snd_soc_codec_get_drvdata(codec);
+	int ret = 0;
+
+	switch (level) {
+	case SND_SOC_BIAS_ON:
+		break;
+	case SND_SOC_BIAS_PREPARE:
+		break;
+	case SND_SOC_BIAS_STANDBY:
+		if (codec->dapm.bias_level == SND_SOC_BIAS_OFF)
+			ret = adau1977_power_enable(adau1977);
+		break;
+	case SND_SOC_BIAS_OFF:
+		ret = adau1977_power_disable(adau1977);
+		break;
+	}
+
+	if (ret)
+		return ret;
+
+	codec->dapm.bias_level = level;
+
+	return 0;
+}
+
+static int adau1977_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask,
+	unsigned int rx_mask, int slots, int width)
+{
+	struct adau1977 *adau1977 = snd_soc_codec_get_drvdata(dai->codec);
+	unsigned int ctrl0, ctrl1, drv;
+	unsigned int slot[4];
+	unsigned int i;
+	int ret;
+
+	if (slots == 0) {
+		/* 0 = No fixed slot width */
+		adau1977->slot_width = 0;
+		adau1977->max_master_fs = 192000;
+		return regmap_update_bits(adau1977->regmap,
+			ADAU1977_REG_SAI_CTRL0, ADAU1977_SAI_CTRL0_SAI_MASK,
+			ADAU1977_SAI_CTRL0_SAI_I2S);
+	}
+
+	if (rx_mask == 0 || tx_mask != 0)
+		return -EINVAL;
+
+	drv = 0;
+	for (i = 0; i < 4; i++) {
+		slot[i] = __ffs(rx_mask);
+		drv |= ADAU1977_SAI_OVERTEMP_DRV_C(i);
+		rx_mask &= ~(1 << slot[i]);
+		if (slot[i] >= slots)
+			return -EINVAL;
+		if (rx_mask == 0)
+			break;
+	}
+
+	if (rx_mask != 0)
+		return -EINVAL;
+
+	switch (width) {
+	case 16:
+		ctrl1 = ADAU1977_SAI_CTRL1_SLOT_WIDTH_16;
+		break;
+	case 24:
+		/* We can only generate 16 bit or 32 bit wide slots */
+		if (adau1977->master)
+			return -EINVAL;
+		ctrl1 = ADAU1977_SAI_CTRL1_SLOT_WIDTH_24;
+		break;
+	case 32:
+		ctrl1 = ADAU1977_SAI_CTRL1_SLOT_WIDTH_32;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (slots) {
+	case 2:
+		ctrl0 = ADAU1977_SAI_CTRL0_SAI_TDM_2;
+		break;
+	case 4:
+		ctrl0 = ADAU1977_SAI_CTRL0_SAI_TDM_4;
+		break;
+	case 8:
+		ctrl0 = ADAU1977_SAI_CTRL0_SAI_TDM_8;
+		break;
+	case 16:
+		ctrl0 = ADAU1977_SAI_CTRL0_SAI_TDM_16;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ret = regmap_update_bits(adau1977->regmap, ADAU1977_REG_SAI_OVERTEMP,
+		ADAU1977_SAI_OVERTEMP_DRV_C(0) |
+		ADAU1977_SAI_OVERTEMP_DRV_C(1) |
+		ADAU1977_SAI_OVERTEMP_DRV_C(2) |
+		ADAU1977_SAI_OVERTEMP_DRV_C(3), drv);
+	if (ret)
+		return ret;
+
+	ret = regmap_write(adau1977->regmap, ADAU1977_REG_CMAP12,
+		(slot[1] << ADAU1977_CHAN_MAP_SECOND_SLOT_OFFSET) |
+		(slot[0] << ADAU1977_CHAN_MAP_FIRST_SLOT_OFFSET));
+	if (ret)
+		return ret;
+
+	ret = regmap_write(adau1977->regmap, ADAU1977_REG_CMAP34,
+		(slot[3] << ADAU1977_CHAN_MAP_SECOND_SLOT_OFFSET) |
+		(slot[2] << ADAU1977_CHAN_MAP_FIRST_SLOT_OFFSET));
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(adau1977->regmap, ADAU1977_REG_SAI_CTRL0,
+		ADAU1977_SAI_CTRL0_SAI_MASK, ctrl0);
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(adau1977->regmap, ADAU1977_REG_SAI_CTRL1,
+		ADAU1977_SAI_CTRL1_SLOT_WIDTH_MASK, ctrl1);
+	if (ret)
+		return ret;
+
+	adau1977->slot_width = width;
+
+	/* In master mode the maximum bitclock is 24.576 MHz */
+	adau1977->max_master_fs = min(192000, 24576000 / width / slots);
+
+	return 0;
+}
+
+static int adau1977_mute(struct snd_soc_dai *dai, int mute, int stream)
+{
+	struct adau1977 *adau1977 = snd_soc_codec_get_drvdata(dai->codec);
+	unsigned int val;
+
+	if (mute)
+		val = ADAU1977_MISC_CONTROL_MMUTE;
+	else
+		val = 0;
+
+	return regmap_update_bits(adau1977->regmap, ADAU1977_REG_MISC_CONTROL,
+			ADAU1977_MISC_CONTROL_MMUTE, val);
+}
+
+static int adau1977_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+{
+	struct adau1977 *adau1977 = snd_soc_codec_get_drvdata(dai->codec);
+	unsigned int ctrl0 = 0, ctrl1 = 0, block_power = 0;
+	bool invert_lrclk;
+	int ret;
+
+	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBS_CFS:
+		adau1977->master = false;
+		break;
+	case SND_SOC_DAIFMT_CBM_CFM:
+		ctrl1 |= ADAU1977_SAI_CTRL1_MASTER;
+		adau1977->master = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+	case SND_SOC_DAIFMT_NB_NF:
+		invert_lrclk = false;
+		break;
+	case SND_SOC_DAIFMT_IB_NF:
+		block_power |= ADAU1977_BLOCK_POWER_SAI_BCLK_EDGE;
+		invert_lrclk = false;
+		break;
+	case SND_SOC_DAIFMT_NB_IF:
+		invert_lrclk = true;
+		break;
+	case SND_SOC_DAIFMT_IB_IF:
+		block_power |= ADAU1977_BLOCK_POWER_SAI_BCLK_EDGE;
+		invert_lrclk = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	adau1977->right_j = false;
+	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+		ctrl0 |= ADAU1977_SAI_CTRL0_FMT_I2S;
+		break;
+	case SND_SOC_DAIFMT_LEFT_J:
+		ctrl0 |= ADAU1977_SAI_CTRL0_FMT_LJ;
+		invert_lrclk = !invert_lrclk;
+		break;
+	case SND_SOC_DAIFMT_RIGHT_J:
+		ctrl0 |= ADAU1977_SAI_CTRL0_FMT_RJ_24BIT;
+		adau1977->right_j = true;
+		invert_lrclk = !invert_lrclk;
+		break;
+	case SND_SOC_DAIFMT_DSP_A:
+		ctrl1 |= ADAU1977_SAI_CTRL1_LRCLK_PULSE;
+		ctrl0 |= ADAU1977_SAI_CTRL0_FMT_I2S;
+		invert_lrclk = false;
+		break;
+	case SND_SOC_DAIFMT_DSP_B:
+		ctrl1 |= ADAU1977_SAI_CTRL1_LRCLK_PULSE;
+		ctrl0 |= ADAU1977_SAI_CTRL0_FMT_LJ;
+		invert_lrclk = false;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (invert_lrclk)
+		block_power |= ADAU1977_BLOCK_POWER_SAI_LR_POL;
+
+	ret = regmap_update_bits(adau1977->regmap, ADAU1977_REG_BLOCK_POWER_SAI,
+		ADAU1977_BLOCK_POWER_SAI_LR_POL |
+		ADAU1977_BLOCK_POWER_SAI_BCLK_EDGE, block_power);
+	if (ret)
+		return ret;
+
+	ret = regmap_update_bits(adau1977->regmap, ADAU1977_REG_SAI_CTRL0,
+		ADAU1977_SAI_CTRL0_FMT_MASK,
+		ctrl0);
+	if (ret)
+		return ret;
+
+	return regmap_update_bits(adau1977->regmap, ADAU1977_REG_SAI_CTRL1,
+		ADAU1977_SAI_CTRL1_MASTER | ADAU1977_SAI_CTRL1_LRCLK_PULSE,
+		ctrl1);
+}
+
+static int adau1977_startup(struct snd_pcm_substream *substream,
+	struct snd_soc_dai *dai)
+{
+	struct adau1977 *adau1977 = snd_soc_codec_get_drvdata(dai->codec);
+	u64 formats = 0;
+
+	if (adau1977->slot_width == 16)
+		formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S16_BE;
+	else if (adau1977->right_j || adau1977->slot_width == 24)
+		formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S16_BE |
+			SNDRV_PCM_FMTBIT_S24_LE | SNDRV_PCM_FMTBIT_S24_BE;
+
+	snd_pcm_hw_constraint_list(substream->runtime, 0,
+		SNDRV_PCM_HW_PARAM_RATE, &adau1977->constraints);
+
+	if (adau1977->master)
+		snd_pcm_hw_constraint_minmax(substream->runtime,
+			SNDRV_PCM_HW_PARAM_RATE, 8000, adau1977->max_master_fs);
+
+	if (formats != 0)
+		snd_pcm_hw_constraint_mask64(substream->runtime,
+			SNDRV_PCM_HW_PARAM_FORMAT, formats);
+
+	return 0;
+}
+
+static int adau1977_set_tristate(struct snd_soc_dai *dai, int tristate)
+{
+	struct adau1977 *adau1977 = snd_soc_codec_get_drvdata(dai->codec);
+	unsigned int val;
+
+	if (tristate)
+		val = ADAU1977_SAI_OVERTEMP_DRV_HIZ;
+	else
+		val = 0;
+
+	return regmap_update_bits(adau1977->regmap, ADAU1977_REG_SAI_OVERTEMP,
+		ADAU1977_SAI_OVERTEMP_DRV_HIZ, val);
+}
+
+static const struct snd_soc_dai_ops adau1977_dai_ops = {
+	.startup	= adau1977_startup,
+	.hw_params	= adau1977_hw_params,
+	.mute_stream	= adau1977_mute,
+	.set_fmt	= adau1977_set_dai_fmt,
+	.set_tdm_slot	= adau1977_set_tdm_slot,
+	.set_tristate	= adau1977_set_tristate,
+};
+
+static struct snd_soc_dai_driver adau1977_dai = {
+	.name = "adau1977-hifi",
+	.capture = {
+		.stream_name = "Capture",
+		.channels_min = 1,
+		.channels_max = 4,
+		.rates = SNDRV_PCM_RATE_KNOT,
+		.formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE |
+		    SNDRV_PCM_FMTBIT_S32_LE,
+		.sig_bits = 24,
+	},
+	.ops = &adau1977_dai_ops,
+};
+
+static const unsigned int adau1977_rates[] = {
+	8000, 16000, 32000, 64000, 128000,
+	11025, 22050, 44100, 88200, 172400,
+	12000, 24000, 48000, 96000, 192000,
+};
+
+#define ADAU1977_RATE_CONSTRAINT_MASK_32000 0x001f
+#define ADAU1977_RATE_CONSTRAINT_MASK_44100 0x03e0
+#define ADAU1977_RATE_CONSTRAINT_MASK_48000 0x7c00
+/* All rates >= 32000 */
+#define ADAU1977_RATE_CONSTRAINT_MASK_LRCLK 0x739c
+
+static bool adau1977_check_sysclk(unsigned int mclk, unsigned int base_freq)
+{
+	unsigned int mcs;
+
+	if (mclk % (base_freq * 128) != 0)
+		return false;
+
+	mcs = mclk / (128 * base_freq);
+	if (mcs < 1 || mcs > 6 || mcs == 5)
+		return false;
+
+	return true;
+}
+
+static int adau1977_set_sysclk(struct snd_soc_codec *codec,
+	int clk_id, int source, unsigned int freq, int dir)
+{
+	struct adau1977 *adau1977 = snd_soc_codec_get_drvdata(codec);
+	unsigned int mask = 0;
+	unsigned int clk_src;
+	unsigned int ret;
+
+	if (dir != SND_SOC_CLOCK_IN)
+		return -EINVAL;
+
+	if (clk_id != ADAU1977_SYSCLK)
+		return -EINVAL;
+
+	switch (source) {
+	case ADAU1977_SYSCLK_SRC_MCLK:
+		clk_src = 0;
+		break;
+	case ADAU1977_SYSCLK_SRC_LRCLK:
+		clk_src = ADAU1977_PLL_CLK_S;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (freq != 0 && source == ADAU1977_SYSCLK_SRC_MCLK) {
+		if (freq < 4000000 || freq > 36864000)
+			return -EINVAL;
+
+		if (adau1977_check_sysclk(freq, 32000))
+			mask |= ADAU1977_RATE_CONSTRAINT_MASK_32000;
+		if (adau1977_check_sysclk(freq, 44100))
+			mask |= ADAU1977_RATE_CONSTRAINT_MASK_44100;
+		if (adau1977_check_sysclk(freq, 48000))
+			mask |= ADAU1977_RATE_CONSTRAINT_MASK_48000;
+
+		if (mask == 0)
+			return -EINVAL;
+	} else if (source == ADAU1977_SYSCLK_SRC_LRCLK) {
+		mask = ADAU1977_RATE_CONSTRAINT_MASK_LRCLK;
+	}
+
+	ret = regmap_update_bits(adau1977->regmap, ADAU1977_REG_PLL,
+		ADAU1977_PLL_CLK_S, clk_src);
+	if (ret)
+		return ret;
+
+	adau1977->constraints.mask = mask;
+	adau1977->sysclk_src = source;
+	adau1977->sysclk = freq;
+
+	return 0;
+}
+
+static int adau1977_codec_probe(struct snd_soc_codec *codec)
+{
+	struct adau1977 *adau1977 = snd_soc_codec_get_drvdata(codec);
+	int ret;
+
+	switch (adau1977->type) {
+	case ADAU1977:
+		ret = snd_soc_dapm_new_controls(&codec->dapm,
+			adau1977_micbias_dapm_widgets,
+			ARRAY_SIZE(adau1977_micbias_dapm_widgets));
+		if (ret < 0)
+			return ret;
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static struct snd_soc_codec_driver adau1977_codec_driver = {
+	.probe = adau1977_codec_probe,
+	.set_bias_level = adau1977_set_bias_level,
+	.set_sysclk = adau1977_set_sysclk,
+	.idle_bias_off = true,
+
+	.controls = adau1977_snd_controls,
+	.num_controls = ARRAY_SIZE(adau1977_snd_controls),
+	.dapm_widgets = adau1977_dapm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(adau1977_dapm_widgets),
+	.dapm_routes = adau1977_dapm_routes,
+	.num_dapm_routes = ARRAY_SIZE(adau1977_dapm_routes),
+};
+
+static int adau1977_setup_micbias(struct adau1977 *adau1977)
+{
+	struct adau1977_platform_data *pdata = adau1977->dev->platform_data;
+	unsigned int micbias;
+
+	if (pdata) {
+		micbias = pdata->micbias;
+		if (micbias > ADAU1977_MICBIAS_9V0)
+			return -EINVAL;
+
+	} else {
+		micbias = ADAU1977_MICBIAS_8V5;
+	}
+
+	return regmap_update_bits(adau1977->regmap, ADAU1977_REG_MICBIAS,
+		ADAU1977_MICBIAS_MB_VOLTS_MASK,
+		micbias << ADAU1977_MICBIAS_MB_VOLTS_OFFSET);
+}
+
+int adau1977_probe(struct device *dev, struct regmap *regmap,
+	enum adau1977_type type, void (*switch_mode)(struct device *dev))
+{
+	unsigned int power_off_mask;
+	struct adau1977 *adau1977;
+	int ret;
+
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	adau1977 = devm_kzalloc(dev, sizeof(*adau1977), GFP_KERNEL);
+	if (adau1977 == NULL)
+		return -ENOMEM;
+
+	adau1977->dev = dev;
+	adau1977->type = type;
+	adau1977->regmap = regmap;
+	adau1977->switch_mode = switch_mode;
+	adau1977->max_master_fs = 192000;
+
+	adau1977->constraints.list = adau1977_rates;
+	adau1977->constraints.count = ARRAY_SIZE(adau1977_rates);
+
+	adau1977->avdd_reg = devm_regulator_get(dev, "AVDD");
+	if (IS_ERR(adau1977->avdd_reg))
+		return PTR_ERR(adau1977->avdd_reg);
+
+	adau1977->dvdd_reg = devm_regulator_get_optional(dev, "DVDD");
+	if (IS_ERR(adau1977->dvdd_reg)) {
+		if (PTR_ERR(adau1977->dvdd_reg) != -ENODEV)
+			return PTR_ERR(adau1977->dvdd_reg);
+		adau1977->dvdd_reg = NULL;
+	}
+
+	adau1977->reset_gpio = devm_gpiod_get(dev, "reset");
+	if (IS_ERR(adau1977->reset_gpio)) {
+		ret = PTR_ERR(adau1977->reset_gpio);
+		if (ret != -ENOENT && ret != -ENOSYS)
+			return PTR_ERR(adau1977->reset_gpio);
+		adau1977->reset_gpio = NULL;
+	}
+
+	dev_set_drvdata(dev, adau1977);
+
+	if (adau1977->reset_gpio) {
+		ret = gpiod_direction_output(adau1977->reset_gpio, 0);
+		if (ret)
+			return ret;
+		ndelay(100);
+	}
+
+	ret = adau1977_power_enable(adau1977);
+	if (ret)
+		return ret;
+
+	if (type == ADAU1977) {
+		ret = adau1977_setup_micbias(adau1977);
+		if (ret)
+			goto err_poweroff;
+	}
+
+	if (adau1977->dvdd_reg)
+		power_off_mask = ~0;
+	else
+		power_off_mask = ~ADAU1977_BLOCK_POWER_SAI_LDO_EN;
+
+	ret = regmap_update_bits(adau1977->regmap, ADAU1977_REG_BLOCK_POWER_SAI,
+				power_off_mask, 0x00);
+	if (ret)
+		goto err_poweroff;
+
+	ret = adau1977_power_disable(adau1977);
+	if (ret)
+		return ret;
+
+	return snd_soc_register_codec(dev, &adau1977_codec_driver,
+			&adau1977_dai, 1);
+
+err_poweroff:
+	adau1977_power_disable(adau1977);
+	return ret;
+
+}
+EXPORT_SYMBOL_GPL(adau1977_probe);
+
+static bool adau1977_register_volatile(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case ADAU1977_REG_STATUS(0):
+	case ADAU1977_REG_STATUS(1):
+	case ADAU1977_REG_STATUS(2):
+	case ADAU1977_REG_STATUS(3):
+	case ADAU1977_REG_ADC_CLIP:
+		return true;
+	}
+
+	return false;
+}
+
+const struct regmap_config adau1977_regmap_config = {
+	.max_register = ADAU1977_REG_DC_HPF_CAL,
+	.volatile_reg = adau1977_register_volatile,
+
+	.cache_type = REGCACHE_RBTREE,
+	.reg_defaults = adau1977_reg_defaults,
+	.num_reg_defaults = ARRAY_SIZE(adau1977_reg_defaults),
+};
+EXPORT_SYMBOL_GPL(adau1977_regmap_config);
+
+MODULE_DESCRIPTION("ASoC ADAU1977/ADAU1978/ADAU1979 driver");
+MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
+MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/adau1977.h b/sound/soc/codecs/adau1977.h
new file mode 100644
index 000000000000..95e714345a86
--- /dev/null
+++ b/sound/soc/codecs/adau1977.h
@@ -0,0 +1,37 @@
+/*
+ * ADAU1977/ADAU1978/ADAU1979 driver
+ *
+ * Copyright 2014 Analog Devices Inc.
+ *  Author: Lars-Peter Clausen <lars@metafoo.de>
+ *
+ * Licensed under the GPL-2.
+ */
+
+#ifndef __SOUND_SOC_CODECS_ADAU1977_H__
+#define __SOUND_SOC_CODECS_ADAU1977_H__
+
+#include <linux/regmap.h>
+
+struct device;
+
+enum adau1977_type {
+	ADAU1977,
+	ADAU1978,
+	ADAU1979,
+};
+
+int adau1977_probe(struct device *dev, struct regmap *regmap,
+	enum adau1977_type type, void (*switch_mode)(struct device *dev));
+
+extern const struct regmap_config adau1977_regmap_config;
+
+enum adau1977_clk_id {
+	ADAU1977_SYSCLK,
+};
+
+enum adau1977_sysclk_src {
+	ADAU1977_SYSCLK_SRC_MCLK,
+	ADAU1977_SYSCLK_SRC_LRCLK,
+};
+
+#endif
-- 
cgit v1.2.3


From b441882dc715ecfd3dcd35e6e7c5778cc1c772a7 Mon Sep 17 00:00:00 2001
From: Sachin Kamat <sachin.kamat@linaro.org>
Date: Mon, 17 Feb 2014 09:11:53 +0530
Subject: ata: ata-samsung_cf: cleanup in header file

Commit 436d42c61c3e ("ARM: samsung: move platform_data definitions")
moved the files to the current location but forgot to remove the pointer
to its previous location. Clean it up. While at it also change the header
file protection macros appropriately.

Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Reviewed-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 include/linux/platform_data/ata-samsung_cf.h | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/ata-samsung_cf.h b/include/linux/platform_data/ata-samsung_cf.h
index 2a3855a8372a..c2049e3d7444 100644
--- a/include/linux/platform_data/ata-samsung_cf.h
+++ b/include/linux/platform_data/ata-samsung_cf.h
@@ -1,5 +1,4 @@
-/* linux/arch/arm/plat-samsung/include/plat/ata.h
- *
+/*
  * Copyright (c) 2010 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  *
@@ -10,8 +9,8 @@
  * published by the Free Software Foundation.
 */
 
-#ifndef __ASM_PLAT_ATA_H
-#define __ASM_PLAT_ATA_H __FILE__
+#ifndef __ATA_SAMSUNG_CF_H
+#define __ATA_SAMSUNG_CF_H __FILE__
 
 /**
  * struct s3c_ide_platdata - S3C IDE driver platform data.
@@ -33,4 +32,4 @@ extern void s3c64xx_ide_setup_gpio(void);
 extern void s5pc100_ide_setup_gpio(void);
 extern void s5pv210_ide_setup_gpio(void);
 
-#endif /*__ASM_PLAT_ATA_H */
+#endif /*__ATA_SAMSUNG_CF_H */
-- 
cgit v1.2.3


From e227867f12302633737bd2a48a10a9a72c0630cb Mon Sep 17 00:00:00 2001
From: Masanari Iida <standby24x7@gmail.com>
Date: Tue, 18 Feb 2014 22:54:36 +0900
Subject: treewide: Fix typo in Documentation/DocBook

This patch fix spelling typo in Documentation/DocBook.
It is because .html and .xml files are generated by make htmldocs,
I have to fix a typo within the source files.

Signed-off-by: Masanari Iida <standby24x7@gmail.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 arch/s390/include/asm/cio.h         | 2 +-
 block/blk-core.c                    | 2 +-
 block/blk-map.c                     | 2 +-
 drivers/ata/libata-core.c           | 4 ++--
 drivers/base/bus.c                  | 2 +-
 drivers/gpu/drm/drm_crtc_helper.c   | 2 +-
 drivers/input/sparse-keymap.c       | 2 +-
 drivers/regulator/core.c            | 2 +-
 drivers/scsi/scsi_transport_iscsi.c | 6 +++---
 drivers/usb/core/message.c          | 2 +-
 drivers/usb/core/urb.c              | 2 +-
 fs/buffer.c                         | 2 +-
 fs/debugfs/inode.c                  | 6 +++---
 include/drm/drm_fb_helper.h         | 2 +-
 include/linux/hsi/hsi.h             | 2 +-
 include/linux/kfifo.h               | 2 +-
 include/linux/pipe_fs_i.h           | 2 +-
 include/linux/skbuff.h              | 2 +-
 include/linux/spi/spi.h             | 8 ++++----
 include/linux/usb/composite.h       | 2 +-
 include/net/mac80211.h              | 6 +++---
 kernel/relay.c                      | 2 +-
 kernel/signal.c                     | 2 +-
 net/core/dev.c                      | 2 +-
 24 files changed, 34 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h
index d42625053c37..096339207764 100644
--- a/arch/s390/include/asm/cio.h
+++ b/arch/s390/include/asm/cio.h
@@ -199,7 +199,7 @@ struct esw_eadm {
 /**
  * struct irb - interruption response block
  * @scsw: subchannel status word
- * @esw: extened status word
+ * @esw: extended status word
  * @ecw: extended control word
  *
  * The irb that is handed to the device driver when an interrupt occurs. For
diff --git a/block/blk-core.c b/block/blk-core.c
index 8bdd0121212a..cd0158163fe0 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1900,7 +1900,7 @@ EXPORT_SYMBOL(submit_bio);
  *    in some cases below, so export this function.
  *    Request stacking drivers like request-based dm may change the queue
  *    limits while requests are in the queue (e.g. dm's table swapping).
- *    Such request stacking drivers should check those requests agaist
+ *    Such request stacking drivers should check those requests against
  *    the new queue limits again when they dispatch those requests,
  *    although such checkings are also done against the old queue limits
  *    when submitting requests.
diff --git a/block/blk-map.c b/block/blk-map.c
index 623e1cd4cffe..62382ad5b010 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -285,7 +285,7 @@ EXPORT_SYMBOL(blk_rq_unmap_user);
  *
  * Description:
  *    Data will be mapped directly if possible. Otherwise a bounce
- *    buffer is used. Can be called multple times to append multple
+ *    buffer is used. Can be called multiple times to append multiple
  *    buffers.
  */
 int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 75b93678bbcd..1274720e6bb9 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -1524,7 +1524,7 @@ static void ata_qc_complete_internal(struct ata_queued_cmd *qc)
  *	@dev: Device to which the command is sent
  *	@tf: Taskfile registers for the command and the result
  *	@cdb: CDB for packet command
- *	@dma_dir: Data tranfer direction of the command
+ *	@dma_dir: Data transfer direction of the command
  *	@sgl: sg list for the data buffer of the command
  *	@n_elem: Number of sg entries
  *	@timeout: Timeout in msecs (0 for default)
@@ -1712,7 +1712,7 @@ unsigned ata_exec_internal_sg(struct ata_device *dev,
  *	@dev: Device to which the command is sent
  *	@tf: Taskfile registers for the command and the result
  *	@cdb: CDB for packet command
- *	@dma_dir: Data tranfer direction of the command
+ *	@dma_dir: Data transfer direction of the command
  *	@buf: Data buffer of the command
  *	@buflen: Length of data buffer
  *	@timeout: Timeout in msecs (0 for default)
diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 73f6c2925281..1db22d3c4036 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -1209,7 +1209,7 @@ err_dev:
  * with the name of the subsystem. The root device can carry subsystem-
  * wide attributes. All registered devices are below this single root
  * device and are named after the subsystem with a simple enumeration
- * number appended. The registered devices are not explicitely named;
+ * number appended. The registered devices are not explicitly named;
  * only 'id' in the device needs to be set.
  *
  * Do not use this interface for anything new, it exists for compatibility
diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
index 01361aba033b..0058fd74063e 100644
--- a/drivers/gpu/drm/drm_crtc_helper.c
+++ b/drivers/gpu/drm/drm_crtc_helper.c
@@ -593,7 +593,7 @@ drm_crtc_helper_disable(struct drm_crtc *crtc)
  * Caller must hold mode config lock.
  *
  * Setup a new configuration, provided by the upper layers (either an ioctl call
- * from userspace or internally e.g. from the fbdev suppport code) in @set, and
+ * from userspace or internally e.g. from the fbdev support code) in @set, and
  * enable it. This is the main helper functions for drivers that implement
  * kernel mode setting with the crtc helper functions and the assorted
  * ->prepare(), ->modeset() and ->commit() helper callbacks.
diff --git a/drivers/input/sparse-keymap.c b/drivers/input/sparse-keymap.c
index a70aa555bbff..e7409c45bdd0 100644
--- a/drivers/input/sparse-keymap.c
+++ b/drivers/input/sparse-keymap.c
@@ -236,7 +236,7 @@ EXPORT_SYMBOL(sparse_keymap_setup);
  * in an input device that was set up by sparse_keymap_setup().
  * NOTE: It is safe to cal this function while input device is
  * still registered (however the drivers should care not to try to
- * use freed keymap and thus have to shut off interrups/polling
+ * use freed keymap and thus have to shut off interrupts/polling
  * before freeing the keymap).
  */
 void sparse_keymap_free(struct input_dev *dev)
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index d85f31385b24..d59aa96a4dc4 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -2134,7 +2134,7 @@ EXPORT_SYMBOL_GPL(regulator_is_enabled);
  * @regulator: regulator source
  *
  * Returns positive if the regulator driver backing the source/client
- * can change its voltage, false otherwise. Usefull for detecting fixed
+ * can change its voltage, false otherwise. Useful for detecting fixed
  * or dummy regulators and disabling voltage change logic in the client
  * driver.
  */
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 63a6ca49d4e5..de5b4d9bb022 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -891,7 +891,7 @@ struct bus_type iscsi_flashnode_bus = {
  * Adds a sysfs entry for the flashnode session attributes
  *
  * Returns:
- *  pointer to allocated flashnode sess on sucess
+ *  pointer to allocated flashnode sess on success
  *  %NULL on failure
  */
 struct iscsi_bus_flash_session *
@@ -1089,7 +1089,7 @@ static int iscsi_iter_destroy_flashnode_conn_fn(struct device *dev, void *data)
 }
 
 /**
- * iscsi_destroy_flashnode_sess - destory flashnode session entry
+ * iscsi_destroy_flashnode_sess - destroy flashnode session entry
  * @fnode_sess: pointer to flashnode session entry to be destroyed
  *
  * Deletes the flashnode session entry and all children flashnode connection
@@ -1119,7 +1119,7 @@ static int iscsi_iter_destroy_flashnode_fn(struct device *dev, void *data)
 }
 
 /**
- * iscsi_destroy_all_flashnode - destory all flashnode session entries
+ * iscsi_destroy_all_flashnode - destroy all flashnode session entries
  * @shost: pointer to host data
  *
  * Destroys all the flashnode session entries and all corresponding children
diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index bb315970e475..874d1a406ebc 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -179,7 +179,7 @@ EXPORT_SYMBOL_GPL(usb_control_msg);
  *
  * Return:
  * If successful, 0. Otherwise a negative error number. The number of actual
- * bytes transferred will be stored in the @actual_length paramater.
+ * bytes transferred will be stored in the @actual_length parameter.
  */
 int usb_interrupt_msg(struct usb_device *usb_dev, unsigned int pipe,
 		      void *data, int len, int *actual_length, int timeout)
diff --git a/drivers/usb/core/urb.c b/drivers/usb/core/urb.c
index e62208356c89..e726f5e80448 100644
--- a/drivers/usb/core/urb.c
+++ b/drivers/usb/core/urb.c
@@ -834,7 +834,7 @@ EXPORT_SYMBOL_GPL(usb_unpoison_anchored_urbs);
  *
  * this allows all outstanding URBs to be unlinked starting
  * from the back of the queue. This function is asynchronous.
- * The unlinking is just tiggered. It may happen after this
+ * The unlinking is just triggered. It may happen after this
  * function has returned.
  *
  * This routine should not be called by a driver after its disconnect
diff --git a/fs/buffer.c b/fs/buffer.c
index 6024877335ca..a20f2eb107ed 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3086,7 +3086,7 @@ EXPORT_SYMBOL(submit_bh);
  * until the buffer gets unlocked).
  *
  * ll_rw_block sets b_end_io to simple completion handler that marks
- * the buffer up-to-date (if approriate), unlocks the buffer and wakes
+ * the buffer up-to-date (if appropriate), unlocks the buffer and wakes
  * any waiters. 
  *
  * All of the buffers must be for the same device, and must also be a
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 9c0444cccbe1..ca4a08f38374 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -358,7 +358,7 @@ exit:
  * @name: a pointer to a string containing the name of the file to create.
  * @mode: the permission that the file should have.
  * @parent: a pointer to the parent dentry for this file.  This should be a
- *          directory dentry if set.  If this paramater is NULL, then the
+ *          directory dentry if set.  If this parameter is NULL, then the
  *          file will be created in the root of the debugfs filesystem.
  * @data: a pointer to something that the caller will want to get to later
  *        on.  The inode.i_private pointer will point to this value on
@@ -400,7 +400,7 @@ EXPORT_SYMBOL_GPL(debugfs_create_file);
  * @name: a pointer to a string containing the name of the directory to
  *        create.
  * @parent: a pointer to the parent dentry for this file.  This should be a
- *          directory dentry if set.  If this paramater is NULL, then the
+ *          directory dentry if set.  If this parameter is NULL, then the
  *          directory will be created in the root of the debugfs filesystem.
  *
  * This function creates a directory in debugfs with the given name.
@@ -425,7 +425,7 @@ EXPORT_SYMBOL_GPL(debugfs_create_dir);
  * @name: a pointer to a string containing the name of the symbolic link to
  *        create.
  * @parent: a pointer to the parent dentry for this symbolic link.  This
- *          should be a directory dentry if set.  If this paramater is NULL,
+ *          should be a directory dentry if set.  If this parameter is NULL,
  *          then the symbolic link will be created in the root of the debugfs
  *          filesystem.
  * @target: a pointer to a string containing the path to the target of the
diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h
index 471f276ce8f7..0145b948b147 100644
--- a/include/drm/drm_fb_helper.h
+++ b/include/drm/drm_fb_helper.h
@@ -55,7 +55,7 @@ struct drm_fb_helper_surface_size {
  *             save the current lut when force-restoring the fbdev for e.g.
  *             kdbg.
  * @fb_probe: Driver callback to allocate and initialize the fbdev info
- *            structure. Futhermore it also needs to allocate the drm
+ *            structure. Furthermore it also needs to allocate the drm
  *            framebuffer used to back the fbdev.
  * @initial_config: Setup an initial fbdev display configuration
  *
diff --git a/include/linux/hsi/hsi.h b/include/linux/hsi/hsi.h
index 0dca785288cf..39bfd5b89077 100644
--- a/include/linux/hsi/hsi.h
+++ b/include/linux/hsi/hsi.h
@@ -178,7 +178,7 @@ static inline void hsi_unregister_client_driver(struct hsi_client_driver *drv)
  * @complete: Transfer completion callback
  * @destructor: Destructor to free resources when flushing
  * @status: Status of the transfer when completed
- * @actual_len: Actual length of data transfered on completion
+ * @actual_len: Actual length of data transferred on completion
  * @channel: Channel were to TX/RX the message
  * @ttype: Transfer type (TX if set, RX otherwise)
  * @break_frame: if true HSI will send/receive a break frame. Data buffers are
diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h
index 552d51efb429..554fde3a3927 100644
--- a/include/linux/kfifo.h
+++ b/include/linux/kfifo.h
@@ -722,7 +722,7 @@ __kfifo_uint_must_check_helper( \
 /**
  * kfifo_dma_out_finish - finish a DMA OUT operation
  * @fifo: address of the fifo to be used
- * @len: number of bytes transferd
+ * @len: number of bytes transferrd
  *
  * This macro finish a DMA OUT operation. The out counter will be updated by
  * the len parameter. No error checking will be done.
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index b8809fef61f5..11982d0ce11b 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -35,7 +35,7 @@ struct pipe_buffer {
  *	@tmp_page: cached released page
  *	@readers: number of current readers of this pipe
  *	@writers: number of current writers of this pipe
- *	@files: number of struct file refering this pipe (protected by ->i_lock)
+ *	@files: number of struct file referring this pipe (protected by ->i_lock)
  *	@waiting_writers: number of writers blocked waiting for room
  *	@r_counter: reader counter
  *	@w_counter: writer counter
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 215b5ea1cb30..cde842513df2 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1951,7 +1951,7 @@ static inline void skb_propagate_pfmemalloc(struct page *page,
 }
 
 /**
- * skb_frag_page - retrieve the page refered to by a paged fragment
+ * skb_frag_page - retrieve the page referred to by a paged fragment
  * @frag: the paged fragment
  *
  * Returns the &struct page associated with @frag.
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 8c62ba74dd91..8d3a37bc6110 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -234,7 +234,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  * @mode_bits: flags understood by this controller driver
  * @bits_per_word_mask: A mask indicating which values of bits_per_word are
  *	supported by the driver. Bit n indicates that a bits_per_word n+1 is
- *	suported. If set, the SPI core will reject any transfer with an
+ *	supported. If set, the SPI core will reject any transfer with an
  *	unsupported bits_per_word. If not set, this value is simply ignored,
  *	and it's up to the individual driver to perform any validation.
  * @min_speed_hz: Lowest supported transfer speed
@@ -259,7 +259,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  * @cur_msg: the currently in-flight message
  * @cur_msg_prepared: spi_prepare_message was called for the currently
  *                    in-flight message
- * @xfer_completion: used by core tranfer_one_message()
+ * @xfer_completion: used by core transfer_one_message()
  * @busy: message pump is busy
  * @running: message pump is running
  * @rt: whether this queue is set to run as a realtime task
@@ -493,7 +493,7 @@ extern struct spi_master *spi_busnum_to_master(u16 busnum);
  * @rx_buf: data to be read (dma-safe memory), or NULL
  * @tx_dma: DMA address of tx_buf, if @spi_message.is_dma_mapped
  * @rx_dma: DMA address of rx_buf, if @spi_message.is_dma_mapped
- * @tx_nbits: number of bits used for writting. If 0 the default
+ * @tx_nbits: number of bits used for writing. If 0 the default
  *      (SPI_NBITS_SINGLE) is used.
  * @rx_nbits: number of bits used for reading. If 0 the default
  *      (SPI_NBITS_SINGLE) is used.
@@ -551,7 +551,7 @@ extern struct spi_master *spi_busnum_to_master(u16 busnum);
  * by the results of previous messages and where the whole transaction
  * ends when the chipselect goes intactive.
  *
- * When SPI can transfer in 1x,2x or 4x. It can get this tranfer information
+ * When SPI can transfer in 1x,2x or 4x. It can get this transfer information
  * from device through @tx_nbits and @rx_nbits. In Bi-direction, these
  * two should both be set. User can set transfer mode with SPI_NBITS_SINGLE(1x)
  * SPI_NBITS_DUAL(2x) and SPI_NBITS_QUAD(4x) to support these three transfer.
diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h
index 5e61589fc166..0e7a555cab1e 100644
--- a/include/linux/usb/composite.h
+++ b/include/linux/usb/composite.h
@@ -92,7 +92,7 @@ struct usb_configuration;
  * @suspend: Notifies functions when the host stops sending USB traffic.
  * @resume: Notifies functions when the host restarts USB traffic.
  * @get_status: Returns function status as a reply to
- *	GetStatus() request when the recepient is Interface.
+ *	GetStatus() request when the recipient is Interface.
  * @func_suspend: callback to be called when
  *	SetFeature(FUNCTION_SUSPEND) is reseived
  *
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 7ceed99a05bc..6b79bfc98175 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1841,7 +1841,7 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb);
  *
  * Driver informs U-APSD client support by enabling
  * %IEEE80211_HW_SUPPORTS_UAPSD flag. The mode is configured through the
- * uapsd paramater in conf_tx() operation. Hardware needs to send the QoS
+ * uapsd parameter in conf_tx() operation. Hardware needs to send the QoS
  * Nullfunc frames and stay awake until the service period has ended. To
  * utilize U-APSD, dynamic powersave is disabled for voip AC and all frames
  * from that AC are transmitted with powersave enabled.
@@ -2047,7 +2047,7 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb);
  * with the number of frames to be released and which TIDs they are
  * to come from. In this case, the driver is responsible for setting
  * the EOSP (for uAPSD) and MORE_DATA bits in the released frames,
- * to help the @more_data paramter is passed to tell the driver if
+ * to help the @more_data parameter is passed to tell the driver if
  * there is more data on other TIDs -- the TIDs to release frames
  * from are ignored since mac80211 doesn't know how many frames the
  * buffers for those TIDs contain.
@@ -2592,7 +2592,7 @@ enum ieee80211_roc_type {
  *	parameters. In the case where the driver buffers some frames for
  *	sleeping stations mac80211 will use this callback to tell the driver
  *	to release some frames, either for PS-poll or uAPSD.
- *	Note that if the @more_data paramter is %false the driver must check
+ *	Note that if the @more_data parameter is %false the driver must check
  *	if there are more frames on the given TIDs, and if there are more than
  *	the frames being released then it must still set the more-data bit in
  *	the frame. If the @more_data parameter is %true, then of course the
diff --git a/kernel/relay.c b/kernel/relay.c
index 5001c9887db1..52d6a6f56261 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -227,7 +227,7 @@ static void relay_destroy_buf(struct rchan_buf *buf)
  *	relay_remove_buf - remove a channel buffer
  *	@kref: target kernel reference that contains the relay buffer
  *
- *	Removes the file from the fileystem, which also frees the
+ *	Removes the file from the filesystem, which also frees the
  *	rchan_buf_struct and the channel buffer.  Should only be called from
  *	kref_put().
  */
diff --git a/kernel/signal.c b/kernel/signal.c
index 940b30ee9a30..f4812283c6e9 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2382,7 +2382,7 @@ relock:
  * @regs:		user register state
  * @stepping:		nonzero if debugger single-step or block-step in use
  *
- * This function should be called when a signal has succesfully been
+ * This function should be called when a signal has successfully been
  * delivered. It updates the blocked signals accordingly (@ka->sa.sa_mask
  * is always blocked, and the signal itself is blocked unless %SA_NODEFER
  * is set in @ka->sa.sa_flags.  Tracing is notified.
diff --git a/net/core/dev.c b/net/core/dev.c
index d2b87dbbbb1a..70d2da3bfb0d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3424,7 +3424,7 @@ out:
  *	@rx_handler: receive handler to register
  *	@rx_handler_data: data pointer that is used by rx handler
  *
- *	Register a receive hander for a device. This handler will then be
+ *	Register a receive handler for a device. This handler will then be
  *	called from __netif_receive_skb. A negative errno code is returned
  *	on a failure.
  *
-- 
cgit v1.2.3


From 46cb7b1bd86fc227a5325ba8fa4c8be70fade4e8 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Thu, 30 Jan 2014 11:28:15 -0700
Subject: PCI: Remove unused SR-IOV VF Migration support

This reverts commit 74bb1bcc7dbb ("PCI: handle SR-IOV Virtual Function
Migration"), removing this exported interface:

  pci_sriov_migration()

Since pci_sriov_migration() is unused, it is impossible to schedule
sriov_migration_task() or use any of the other migration infrastructure.

This is based on Stephen Hemminger's patch (see link below), but goes a bit
further.

Link: http://lkml.kernel.org/r/20131227132710.7190647c@nehalam.linuxnetplumber.net
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
CC: Stephen Hemminger <stephen@networkplumber.org>
---
 Documentation/PCI/pci-iov-howto.txt |   4 --
 drivers/pci/iov.c                   | 119 ------------------------------------
 drivers/pci/pci.h                   |   4 --
 include/linux/pci.h                 |   4 --
 4 files changed, 131 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/PCI/pci-iov-howto.txt b/Documentation/PCI/pci-iov-howto.txt
index 86551cc72e03..2d91ae251982 100644
--- a/Documentation/PCI/pci-iov-howto.txt
+++ b/Documentation/PCI/pci-iov-howto.txt
@@ -68,10 +68,6 @@ To disable SR-IOV capability:
 	echo  0 > \
         /sys/bus/pci/devices/<DOMAIN:BUS:DEVICE.FUNCTION>/sriov_numvfs
 
-To notify SR-IOV core of Virtual Function Migration:
-(a) In the driver:
-	irqreturn_t pci_sriov_migration(struct pci_dev *dev);
-
 3.2 Usage example
 
 Following piece of code illustrates the usage of the SR-IOV API.
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 9dce7c5e2a77..de7a74782f92 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -170,97 +170,6 @@ static void virtfn_remove(struct pci_dev *dev, int id, int reset)
 	pci_dev_put(dev);
 }
 
-static int sriov_migration(struct pci_dev *dev)
-{
-	u16 status;
-	struct pci_sriov *iov = dev->sriov;
-
-	if (!iov->num_VFs)
-		return 0;
-
-	if (!(iov->cap & PCI_SRIOV_CAP_VFM))
-		return 0;
-
-	pci_read_config_word(dev, iov->pos + PCI_SRIOV_STATUS, &status);
-	if (!(status & PCI_SRIOV_STATUS_VFM))
-		return 0;
-
-	schedule_work(&iov->mtask);
-
-	return 1;
-}
-
-static void sriov_migration_task(struct work_struct *work)
-{
-	int i;
-	u8 state;
-	u16 status;
-	struct pci_sriov *iov = container_of(work, struct pci_sriov, mtask);
-
-	for (i = iov->initial_VFs; i < iov->num_VFs; i++) {
-		state = readb(iov->mstate + i);
-		if (state == PCI_SRIOV_VFM_MI) {
-			writeb(PCI_SRIOV_VFM_AV, iov->mstate + i);
-			state = readb(iov->mstate + i);
-			if (state == PCI_SRIOV_VFM_AV)
-				virtfn_add(iov->self, i, 1);
-		} else if (state == PCI_SRIOV_VFM_MO) {
-			virtfn_remove(iov->self, i, 1);
-			writeb(PCI_SRIOV_VFM_UA, iov->mstate + i);
-			state = readb(iov->mstate + i);
-			if (state == PCI_SRIOV_VFM_AV)
-				virtfn_add(iov->self, i, 0);
-		}
-	}
-
-	pci_read_config_word(iov->self, iov->pos + PCI_SRIOV_STATUS, &status);
-	status &= ~PCI_SRIOV_STATUS_VFM;
-	pci_write_config_word(iov->self, iov->pos + PCI_SRIOV_STATUS, status);
-}
-
-static int sriov_enable_migration(struct pci_dev *dev, int nr_virtfn)
-{
-	int bir;
-	u32 table;
-	resource_size_t pa;
-	struct pci_sriov *iov = dev->sriov;
-
-	if (nr_virtfn <= iov->initial_VFs)
-		return 0;
-
-	pci_read_config_dword(dev, iov->pos + PCI_SRIOV_VFM, &table);
-	bir = PCI_SRIOV_VFM_BIR(table);
-	if (bir > PCI_STD_RESOURCE_END)
-		return -EIO;
-
-	table = PCI_SRIOV_VFM_OFFSET(table);
-	if (table + nr_virtfn > pci_resource_len(dev, bir))
-		return -EIO;
-
-	pa = pci_resource_start(dev, bir) + table;
-	iov->mstate = ioremap(pa, nr_virtfn);
-	if (!iov->mstate)
-		return -ENOMEM;
-
-	INIT_WORK(&iov->mtask, sriov_migration_task);
-
-	iov->ctrl |= PCI_SRIOV_CTRL_VFM | PCI_SRIOV_CTRL_INTR;
-	pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
-
-	return 0;
-}
-
-static void sriov_disable_migration(struct pci_dev *dev)
-{
-	struct pci_sriov *iov = dev->sriov;
-
-	iov->ctrl &= ~(PCI_SRIOV_CTRL_VFM | PCI_SRIOV_CTRL_INTR);
-	pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, iov->ctrl);
-
-	cancel_work_sync(&iov->mtask);
-	iounmap(iov->mstate);
-}
-
 static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
 {
 	int rc;
@@ -351,12 +260,6 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn)
 			goto failed;
 	}
 
-	if (iov->cap & PCI_SRIOV_CAP_VFM) {
-		rc = sriov_enable_migration(dev, nr_virtfn);
-		if (rc)
-			goto failed;
-	}
-
 	kobject_uevent(&dev->dev.kobj, KOBJ_CHANGE);
 	iov->num_VFs = nr_virtfn;
 
@@ -387,9 +290,6 @@ static void sriov_disable(struct pci_dev *dev)
 	if (!iov->num_VFs)
 		return;
 
-	if (iov->cap & PCI_SRIOV_CAP_VFM)
-		sriov_disable_migration(dev);
-
 	for (i = 0; i < iov->num_VFs; i++)
 		virtfn_remove(dev, i, 0);
 
@@ -687,25 +587,6 @@ void pci_disable_sriov(struct pci_dev *dev)
 }
 EXPORT_SYMBOL_GPL(pci_disable_sriov);
 
-/**
- * pci_sriov_migration - notify SR-IOV core of Virtual Function Migration
- * @dev: the PCI device
- *
- * Returns IRQ_HANDLED if the IRQ is handled, or IRQ_NONE if not.
- *
- * Physical Function driver is responsible to register IRQ handler using
- * VF Migration Interrupt Message Number, and call this function when the
- * interrupt is generated by the hardware.
- */
-irqreturn_t pci_sriov_migration(struct pci_dev *dev)
-{
-	if (!dev->is_physfn)
-		return IRQ_NONE;
-
-	return sriov_migration(dev) ? IRQ_HANDLED : IRQ_NONE;
-}
-EXPORT_SYMBOL_GPL(pci_sriov_migration);
-
 /**
  * pci_num_vf - return number of VFs associated with a PF device_release_driver
  * @dev: the PCI device
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 4df38df224f4..6bd082299e31 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -1,8 +1,6 @@
 #ifndef DRIVERS_PCI_H
 #define DRIVERS_PCI_H
 
-#include <linux/workqueue.h>
-
 #define PCI_CFG_SPACE_SIZE	256
 #define PCI_CFG_SPACE_EXP_SIZE	4096
 
@@ -240,8 +238,6 @@ struct pci_sriov {
 	struct pci_dev *dev;	/* lowest numbered PF */
 	struct pci_dev *self;	/* this PF */
 	struct mutex lock;	/* lock for VF bus */
-	struct work_struct mtask; /* VF Migration task */
-	u8 __iomem *mstate;	/* VF Migration State Array */
 };
 
 #ifdef CONFIG_PCI_ATS
diff --git a/include/linux/pci.h b/include/linux/pci.h
index fb57c892b214..230a8dabc5a3 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -29,7 +29,6 @@
 #include <linux/atomic.h>
 #include <linux/device.h>
 #include <linux/io.h>
-#include <linux/irqreturn.h>
 #include <uapi/linux/pci.h>
 
 #include <linux/pci_ids.h>
@@ -1577,7 +1576,6 @@ void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar);
 #ifdef CONFIG_PCI_IOV
 int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn);
 void pci_disable_sriov(struct pci_dev *dev);
-irqreturn_t pci_sriov_migration(struct pci_dev *dev);
 int pci_num_vf(struct pci_dev *dev);
 int pci_vfs_assigned(struct pci_dev *dev);
 int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs);
@@ -1586,8 +1584,6 @@ int pci_sriov_get_totalvfs(struct pci_dev *dev);
 static inline int pci_enable_sriov(struct pci_dev *dev, int nr_virtfn)
 { return -ENODEV; }
 static inline void pci_disable_sriov(struct pci_dev *dev) { }
-static inline irqreturn_t pci_sriov_migration(struct pci_dev *dev)
-{ return IRQ_NONE; }
 static inline int pci_num_vf(struct pci_dev *dev) { return 0; }
 static inline int pci_vfs_assigned(struct pci_dev *dev)
 { return 0; }
-- 
cgit v1.2.3


From 3d2699bc179a10eee7d2aa1db50f822be01636f7 Mon Sep 17 00:00:00 2001
From: "Liu, Chuansheng" <chuansheng.liu@intel.com>
Date: Tue, 18 Feb 2014 10:28:44 +0800
Subject: PM / sleep: Two flags for async suspend_noirq and suspend_late

The patch is a helper adding two new flags for implementing
async threads for suspend_noirq and suspend_late.

Signed-off-by: Chuansheng Liu <chuansheng.liu@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/main.c | 24 ++++++++++++++++++++++--
 include/linux/pm.h        |  2 ++
 2 files changed, 24 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 1b41fca3d65a..00c53eb8ebca 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -91,6 +91,8 @@ void device_pm_sleep_init(struct device *dev)
 {
 	dev->power.is_prepared = false;
 	dev->power.is_suspended = false;
+	dev->power.is_noirq_suspended = false;
+	dev->power.is_late_suspended = false;
 	init_completion(&dev->power.completion);
 	complete_all(&dev->power.completion);
 	dev->power.wakeup = NULL;
@@ -479,6 +481,9 @@ static int device_resume_noirq(struct device *dev, pm_message_t state)
 	if (dev->power.syscore)
 		goto Out;
 
+	if (!dev->power.is_noirq_suspended)
+		goto Out;
+
 	if (dev->pm_domain) {
 		info = "noirq power domain ";
 		callback = pm_noirq_op(&dev->pm_domain->ops, state);
@@ -499,6 +504,7 @@ static int device_resume_noirq(struct device *dev, pm_message_t state)
 	}
 
 	error = dpm_run_callback(callback, dev, state, info);
+	dev->power.is_noirq_suspended = false;
 
  Out:
 	TRACE_RESUME(error);
@@ -561,6 +567,9 @@ static int device_resume_early(struct device *dev, pm_message_t state)
 	if (dev->power.syscore)
 		goto Out;
 
+	if (!dev->power.is_late_suspended)
+		goto Out;
+
 	if (dev->pm_domain) {
 		info = "early power domain ";
 		callback = pm_late_early_op(&dev->pm_domain->ops, state);
@@ -581,6 +590,7 @@ static int device_resume_early(struct device *dev, pm_message_t state)
 	}
 
 	error = dpm_run_callback(callback, dev, state, info);
+	dev->power.is_late_suspended = false;
 
  Out:
 	TRACE_RESUME(error);
@@ -917,6 +927,7 @@ static int device_suspend_noirq(struct device *dev, pm_message_t state)
 {
 	pm_callback_t callback = NULL;
 	char *info = NULL;
+	int error;
 
 	if (dev->power.syscore)
 		return 0;
@@ -940,7 +951,11 @@ static int device_suspend_noirq(struct device *dev, pm_message_t state)
 		callback = pm_noirq_op(dev->driver->pm, state);
 	}
 
-	return dpm_run_callback(callback, dev, state, info);
+	error = dpm_run_callback(callback, dev, state, info);
+	if (!error)
+		dev->power.is_noirq_suspended = true;
+
+	return error;
 }
 
 /**
@@ -1003,6 +1018,7 @@ static int device_suspend_late(struct device *dev, pm_message_t state)
 {
 	pm_callback_t callback = NULL;
 	char *info = NULL;
+	int error;
 
 	__pm_runtime_disable(dev, false);
 
@@ -1028,7 +1044,11 @@ static int device_suspend_late(struct device *dev, pm_message_t state)
 		callback = pm_late_early_op(dev->driver->pm, state);
 	}
 
-	return dpm_run_callback(callback, dev, state, info);
+	error = dpm_run_callback(callback, dev, state, info);
+	if (!error)
+		dev->power.is_late_suspended = true;
+
+	return error;
 }
 
 /**
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 8c6583a53a06..f23a4f1c1bfb 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -542,6 +542,8 @@ struct dev_pm_info {
 	unsigned int		async_suspend:1;
 	bool			is_prepared:1;	/* Owned by the PM core */
 	bool			is_suspended:1;	/* Ditto */
+	bool			is_noirq_suspended:1;
+	bool			is_late_suspended:1;
 	bool			ignore_children:1;
 	bool			early_init:1;	/* Owned by the PM core */
 	spinlock_t		lock;
-- 
cgit v1.2.3


From f7b370a3404484cf1c5c0fcda77f9d7d67b53cb5 Mon Sep 17 00:00:00 2001
From: Richard Genoud <richard.genoud@gmail.com>
Date: Tue, 11 Feb 2014 17:25:35 +0100
Subject: gpio: update path to documentation

Signed-off-by: Richard Genoud <richard.genoud@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 include/linux/gpio.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/gpio.h b/include/linux/gpio.h
index 13dfd24d01ab..c177c48f60a2 100644
--- a/include/linux/gpio.h
+++ b/include/linux/gpio.h
@@ -3,7 +3,7 @@
 
 #include <linux/errno.h>
 
-/* see Documentation/gpio.txt */
+/* see Documentation/gpio/gpio-legacy.txt */
 
 /* make these flag values available regardless of GPIO kconfig options */
 #define GPIOF_DIR_OUT	(0 << 0)
-- 
cgit v1.2.3


From b7e00a6c53e9134d5cf7631582acaf027a5ded26 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Thu, 7 Nov 2013 09:36:25 -0500
Subject: ftrace: Add private data to ftrace_ops

Passing data to the function callback was originally done by adding the
ftrace_ops in another structure, and using the container_of() to get
the field. But this adds a bit more complexity than it is worth, and
adding a simple .private field to ftrace_ops makes things a lot easier.

But be warned, the .private data should not be freed once it is used
unless the ftrace_ops itself has gone through the necessary freeing
routines. A simple synchronize_sched() is not enough as functions
can be traced that are called outside the view of RCU and all its
concoctions.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index f4233b195dab..ef1607ed7044 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -105,11 +105,23 @@ enum {
 	FTRACE_OPS_FL_INITIALIZED		= 1 << 8,
 };
 
+/*
+ * Note, ftrace_ops can be referenced outside of RCU protection.
+ * (Although, for perf, the control ops prevent that). If ftrace_ops is
+ * allocated and not part of kernel core data, the unregistering of it will
+ * perform a scheduling on all CPUs to make sure that there are no more users.
+ * Depending on the load of the system that may take a bit of time.
+ *
+ * Any private data added must also take care not to be freed and if private
+ * data is added to a ftrace_ops that is in core code, the user of the
+ * ftrace_ops must perform a schedule_on_each_cpu() before freeing it.
+ */
 struct ftrace_ops {
 	ftrace_func_t			func;
 	struct ftrace_ops		*next;
 	unsigned long			flags;
 	int __percpu			*disabled;
+	void				*private;
 #ifdef CONFIG_DYNAMIC_FTRACE
 	struct ftrace_hash		*notrace_hash;
 	struct ftrace_hash		*filter_hash;
-- 
cgit v1.2.3


From 591dffdade9f07692a7dd3ed16830ec24e901ece Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Fri, 10 Jan 2014 16:17:45 -0500
Subject: ftrace: Allow for function tracing instance to filter functions

Create a "set_ftrace_filter" and "set_ftrace_notrace" files in the instance
directories to let users filter of functions to trace for the given instance.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace.h         |  2 ++
 kernel/trace/ftrace.c          | 39 ++++++++++++++++++++++++++++++++++-----
 kernel/trace/trace.c           |  4 ++++
 kernel/trace/trace.h           | 25 ++++++++++++++++++++++++-
 kernel/trace/trace_functions.c | 40 ++++++++++++++++++++++++++++++++--------
 5 files changed, 96 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index ef1607ed7044..e6141be2fad5 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -92,6 +92,7 @@ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
  * STUB   - The ftrace_ops is just a place holder.
  * INITIALIZED - The ftrace_ops has already been initialized (first use time
  *            register_ftrace_function() is called, it will initialized the ops)
+ * DELETED - The ops are being deleted, do not let them be registered again.
  */
 enum {
 	FTRACE_OPS_FL_ENABLED			= 1 << 0,
@@ -103,6 +104,7 @@ enum {
 	FTRACE_OPS_FL_RECURSION_SAFE		= 1 << 6,
 	FTRACE_OPS_FL_STUB			= 1 << 7,
 	FTRACE_OPS_FL_INITIALIZED		= 1 << 8,
+	FTRACE_OPS_FL_DELETED			= 1 << 9,
 };
 
 /*
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 2b3e23991c8a..dcee546f21bc 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -436,6 +436,9 @@ static int remove_ftrace_list_ops(struct ftrace_ops **list,
 
 static int __register_ftrace_function(struct ftrace_ops *ops)
 {
+	if (ops->flags & FTRACE_OPS_FL_DELETED)
+		return -EINVAL;
+
 	if (FTRACE_WARN_ON(ops == &global_ops))
 		return -EINVAL;
 
@@ -4112,6 +4115,36 @@ static const struct file_operations ftrace_graph_notrace_fops = {
 };
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
+void ftrace_create_filter_files(struct ftrace_ops *ops,
+				struct dentry *parent)
+{
+
+	trace_create_file("set_ftrace_filter", 0644, parent,
+			  ops, &ftrace_filter_fops);
+
+	trace_create_file("set_ftrace_notrace", 0644, parent,
+			  ops, &ftrace_notrace_fops);
+}
+
+/*
+ * The name "destroy_filter_files" is really a misnomer. Although
+ * in the future, it may actualy delete the files, but this is
+ * really intended to make sure the ops passed in are disabled
+ * and that when this function returns, the caller is free to
+ * free the ops.
+ *
+ * The "destroy" name is only to match the "create" name that this
+ * should be paired with.
+ */
+void ftrace_destroy_filter_files(struct ftrace_ops *ops)
+{
+	mutex_lock(&ftrace_lock);
+	if (ops->flags & FTRACE_OPS_FL_ENABLED)
+		ftrace_shutdown(ops, 0);
+	ops->flags |= FTRACE_OPS_FL_DELETED;
+	mutex_unlock(&ftrace_lock);
+}
+
 static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
 {
 
@@ -4121,11 +4154,7 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
 	trace_create_file("enabled_functions", 0444,
 			d_tracer, NULL, &ftrace_enabled_fops);
 
-	trace_create_file("set_ftrace_filter", 0644, d_tracer,
-			&global_ops, &ftrace_filter_fops);
-
-	trace_create_file("set_ftrace_notrace", 0644, d_tracer,
-				    &global_ops, &ftrace_notrace_fops);
+	ftrace_create_filter_files(&global_ops, d_tracer);
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	trace_create_file("set_graph_function", 0444, d_tracer,
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f9f22c435036..d95ec2876bbb 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6161,6 +6161,7 @@ static int instance_delete(const char *name)
 
 	tracing_set_nop(tr);
 	event_trace_del_tracer(tr);
+	ftrace_destroy_function_files(tr);
 	debugfs_remove_recursive(tr->dir);
 	free_percpu(tr->trace_buffer.data);
 	ring_buffer_free(tr->trace_buffer.buffer);
@@ -6291,6 +6292,9 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
 	trace_create_file("tracing_on", 0644, d_tracer,
 			  tr, &rb_simple_fops);
 
+	if (ftrace_create_function_files(tr, d_tracer))
+		WARN(1, "Could not allocate function filter files");
+
 #ifdef CONFIG_TRACER_SNAPSHOT
 	trace_create_file("snapshot", 0644, d_tracer,
 			  tr, &snapshot_fops);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 35cca055da0f..ffc314b7e92b 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -819,13 +819,36 @@ static inline int ftrace_trace_task(struct task_struct *task)
 	return test_tsk_trace_trace(task);
 }
 extern int ftrace_is_dead(void);
+int ftrace_create_function_files(struct trace_array *tr,
+				 struct dentry *parent);
+void ftrace_destroy_function_files(struct trace_array *tr);
 #else
 static inline int ftrace_trace_task(struct task_struct *task)
 {
 	return 1;
 }
 static inline int ftrace_is_dead(void) { return 0; }
-#endif
+static inline int
+ftrace_create_function_files(struct trace_array *tr,
+			     struct dentry *parent)
+{
+	return 0;
+}
+static inline void ftrace_destroy_function_files(struct trace_array *tr) { }
+#endif /* CONFIG_FUNCTION_TRACER */
+
+#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE)
+void ftrace_create_filter_files(struct ftrace_ops *ops,
+				struct dentry *parent);
+void ftrace_destroy_filter_files(struct ftrace_ops *ops);
+#else
+/*
+ * The ops parameter passed in is usually undefined.
+ * This must be a macro.
+ */
+#define ftrace_create_filter_files(ops, parent) do { } while (0)
+#define ftrace_destroy_filter_files(ops) do { } while (0)
+#endif /* CONFIG_FUNCTION_TRACER && CONFIG_DYNAMIC_FTRACE */
 
 int ftrace_event_is_function(struct ftrace_event_call *call);
 
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 3f8dc1ce8b9c..5b781d2be383 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -52,10 +52,34 @@ static int allocate_ftrace_ops(struct trace_array *tr)
 	return 0;
 }
 
+
+int ftrace_create_function_files(struct trace_array *tr,
+				 struct dentry *parent)
+{
+	int ret;
+
+	/* The top level array uses the "global_ops". */
+	if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL)) {
+		ret = allocate_ftrace_ops(tr);
+		if (ret)
+			return ret;
+	}
+
+	ftrace_create_filter_files(tr->ops, parent);
+
+	return 0;
+}
+
+void ftrace_destroy_function_files(struct trace_array *tr)
+{
+	ftrace_destroy_filter_files(tr->ops);
+	kfree(tr->ops);
+	tr->ops = NULL;
+}
+
 static int function_trace_init(struct trace_array *tr)
 {
 	struct ftrace_ops *ops;
-	int ret;
 
 	if (tr->flags & TRACE_ARRAY_FL_GLOBAL) {
 		/* There's only one global tr */
@@ -69,10 +93,13 @@ static int function_trace_init(struct trace_array *tr)
 		else
 			ops = &trace_ops;
 		tr->ops = ops;
-	} else {
-		ret = allocate_ftrace_ops(tr);
-		if (ret)
-			return ret;
+	} else if (!tr->ops) {
+		/*
+		 * Instance trace_arrays get their ops allocated
+		 * at instance creation. Unless it failed
+		 * the allocation.
+		 */
+		return -ENOMEM;
 	}
 
 	tr->trace_buffer.cpu = get_cpu();
@@ -87,9 +114,6 @@ static void function_trace_reset(struct trace_array *tr)
 {
 	tracing_stop_function_trace(tr);
 	tracing_stop_cmdline_record();
-	if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL))
-		kfree(tr->ops);
-	tr->ops = NULL;
 }
 
 static void function_trace_start(struct trace_array *tr)
-- 
cgit v1.2.3


From 39a3a0138f6113805dc9e0813214cd4b03bd8ac0 Mon Sep 17 00:00:00 2001
From: Archana Patni <archana.patni@linux.intel.com>
Date: Thu, 20 Feb 2014 06:29:00 +0000
Subject: iio: hid-sensors: Added Proximity Sensor Driver

Added usage id processing for Proximity (Human Presence).
This uses IIO interfaces for triggered buffer to present data
to user mode. This uses HID sensor framework for registering
callback events from the sensor hub.

Signed-off-by: Archana Patni <archana.patni@intel.com>
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/light/Kconfig           |  14 ++
 drivers/iio/light/Makefile          |   1 +
 drivers/iio/light/hid-sensor-prox.c | 375 ++++++++++++++++++++++++++++++++++++
 include/linux/hid-sensor-ids.h      |   5 +
 4 files changed, 395 insertions(+)
 create mode 100644 drivers/iio/light/hid-sensor-prox.c

(limited to 'include/linux')

diff --git a/drivers/iio/light/Kconfig b/drivers/iio/light/Kconfig
index 3a7a5d9f03a3..c89740d4748f 100644
--- a/drivers/iio/light/Kconfig
+++ b/drivers/iio/light/Kconfig
@@ -73,6 +73,20 @@ config HID_SENSOR_ALS
 	  Say yes here to build support for the HID SENSOR
 	  Ambient light sensor.
 
+config HID_SENSOR_PROX
+	depends on HID_SENSOR_HUB
+	select IIO_BUFFER
+	select IIO_TRIGGERED_BUFFER
+	select HID_SENSOR_IIO_COMMON
+	select HID_SENSOR_IIO_TRIGGER
+	tristate "HID PROX"
+	help
+	  Say yes here to build support for the HID SENSOR
+	  Proximity sensor.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called hid-sensor-prox.
+
 config SENSORS_LM3533
 	tristate "LM3533 ambient light sensor"
 	depends on MFD_LM3533
diff --git a/drivers/iio/light/Makefile b/drivers/iio/light/Makefile
index 924530597f83..3eb36e5151fa 100644
--- a/drivers/iio/light/Makefile
+++ b/drivers/iio/light/Makefile
@@ -9,6 +9,7 @@ obj-$(CONFIG_CM32181)		+= cm32181.o
 obj-$(CONFIG_CM36651)		+= cm36651.o
 obj-$(CONFIG_GP2AP020A00F)	+= gp2ap020a00f.o
 obj-$(CONFIG_HID_SENSOR_ALS)	+= hid-sensor-als.o
+obj-$(CONFIG_HID_SENSOR_PROX)	+= hid-sensor-prox.o
 obj-$(CONFIG_SENSORS_LM3533)	+= lm3533-als.o
 obj-$(CONFIG_LTR501)		+= ltr501.o
 obj-$(CONFIG_SENSORS_TSL2563)	+= tsl2563.o
diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c
new file mode 100644
index 000000000000..1894ab196f97
--- /dev/null
+++ b/drivers/iio/light/hid-sensor-prox.c
@@ -0,0 +1,375 @@
+/*
+ * HID Sensors Driver
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.
+ *
+ */
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/slab.h>
+#include <linux/hid-sensor-hub.h>
+#include <linux/iio/iio.h>
+#include <linux/iio/sysfs.h>
+#include <linux/iio/buffer.h>
+#include <linux/iio/trigger_consumer.h>
+#include <linux/iio/triggered_buffer.h>
+#include "../common/hid-sensors/hid-sensor-trigger.h"
+
+#define CHANNEL_SCAN_INDEX_PRESENCE 0
+
+struct prox_state {
+	struct hid_sensor_hub_callbacks callbacks;
+	struct hid_sensor_common common_attributes;
+	struct hid_sensor_hub_attribute_info prox_attr;
+	u32 human_presence;
+};
+
+/* Channel definitions */
+static const struct iio_chan_spec prox_channels[] = {
+	{
+		.type = IIO_PROXIMITY,
+		.modified = 1,
+		.channel2 = IIO_NO_MOD,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
+		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) |
+		BIT(IIO_CHAN_INFO_SCALE) |
+		BIT(IIO_CHAN_INFO_SAMP_FREQ) |
+		BIT(IIO_CHAN_INFO_HYSTERESIS),
+		.scan_index = CHANNEL_SCAN_INDEX_PRESENCE,
+	}
+};
+
+/* Adjust channel real bits based on report descriptor */
+static void prox_adjust_channel_bit_mask(struct iio_chan_spec *channels,
+					int channel, int size)
+{
+	channels[channel].scan_type.sign = 's';
+	/* Real storage bits will change based on the report desc. */
+	channels[channel].scan_type.realbits = size * 8;
+	/* Maximum size of a sample to capture is u32 */
+	channels[channel].scan_type.storagebits = sizeof(u32) * 8;
+}
+
+/* Channel read_raw handler */
+static int prox_read_raw(struct iio_dev *indio_dev,
+			      struct iio_chan_spec const *chan,
+			      int *val, int *val2,
+			      long mask)
+{
+	struct prox_state *prox_state = iio_priv(indio_dev);
+	int report_id = -1;
+	u32 address;
+	int ret;
+	int ret_type;
+
+	*val = 0;
+	*val2 = 0;
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		switch (chan->scan_index) {
+		case  CHANNEL_SCAN_INDEX_PRESENCE:
+			report_id = prox_state->prox_attr.report_id;
+			address =
+			HID_USAGE_SENSOR_HUMAN_PRESENCE;
+			break;
+		default:
+			report_id = -1;
+			break;
+		}
+		if (report_id >= 0)
+			*val = sensor_hub_input_attr_get_raw_value(
+				prox_state->common_attributes.hsdev,
+				HID_USAGE_SENSOR_PROX, address,
+				report_id);
+		else {
+			*val = 0;
+			return -EINVAL;
+		}
+		ret_type = IIO_VAL_INT;
+		break;
+	case IIO_CHAN_INFO_SCALE:
+		*val = prox_state->prox_attr.units;
+		ret_type = IIO_VAL_INT;
+		break;
+	case IIO_CHAN_INFO_OFFSET:
+		*val = hid_sensor_convert_exponent(
+				prox_state->prox_attr.unit_expo);
+		ret_type = IIO_VAL_INT;
+		break;
+	case IIO_CHAN_INFO_SAMP_FREQ:
+		ret = hid_sensor_read_samp_freq_value(
+				&prox_state->common_attributes, val, val2);
+		ret_type = IIO_VAL_INT_PLUS_MICRO;
+		break;
+	case IIO_CHAN_INFO_HYSTERESIS:
+		ret = hid_sensor_read_raw_hyst_value(
+				&prox_state->common_attributes, val, val2);
+		ret_type = IIO_VAL_INT_PLUS_MICRO;
+		break;
+	default:
+		ret_type = -EINVAL;
+		break;
+	}
+
+	return ret_type;
+}
+
+/* Channel write_raw handler */
+static int prox_write_raw(struct iio_dev *indio_dev,
+			       struct iio_chan_spec const *chan,
+			       int val,
+			       int val2,
+			       long mask)
+{
+	struct prox_state *prox_state = iio_priv(indio_dev);
+	int ret = 0;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_SAMP_FREQ:
+		ret = hid_sensor_write_samp_freq_value(
+				&prox_state->common_attributes, val, val2);
+		break;
+	case IIO_CHAN_INFO_HYSTERESIS:
+		ret = hid_sensor_write_raw_hyst_value(
+				&prox_state->common_attributes, val, val2);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static const struct iio_info prox_info = {
+	.driver_module = THIS_MODULE,
+	.read_raw = &prox_read_raw,
+	.write_raw = &prox_write_raw,
+};
+
+/* Function to push data to buffer */
+static void hid_sensor_push_data(struct iio_dev *indio_dev, const void *data,
+					int len)
+{
+	dev_dbg(&indio_dev->dev, "hid_sensor_push_data\n");
+	iio_push_to_buffers(indio_dev, data);
+}
+
+/* Callback handler to send event after all samples are received and captured */
+static int prox_proc_event(struct hid_sensor_hub_device *hsdev,
+				unsigned usage_id,
+				void *priv)
+{
+	struct iio_dev *indio_dev = platform_get_drvdata(priv);
+	struct prox_state *prox_state = iio_priv(indio_dev);
+
+	dev_dbg(&indio_dev->dev, "prox_proc_event [%d]\n",
+				prox_state->common_attributes.data_ready);
+	if (prox_state->common_attributes.data_ready)
+		hid_sensor_push_data(indio_dev,
+				&prox_state->human_presence,
+				sizeof(prox_state->human_presence));
+
+	return 0;
+}
+
+/* Capture samples in local storage */
+static int prox_capture_sample(struct hid_sensor_hub_device *hsdev,
+				unsigned usage_id,
+				size_t raw_len, char *raw_data,
+				void *priv)
+{
+	struct iio_dev *indio_dev = platform_get_drvdata(priv);
+	struct prox_state *prox_state = iio_priv(indio_dev);
+	int ret = -EINVAL;
+
+	switch (usage_id) {
+	case HID_USAGE_SENSOR_HUMAN_PRESENCE:
+		prox_state->human_presence = *(u32 *)raw_data;
+		ret = 0;
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+/* Parse report which is specific to an usage id*/
+static int prox_parse_report(struct platform_device *pdev,
+				struct hid_sensor_hub_device *hsdev,
+				struct iio_chan_spec *channels,
+				unsigned usage_id,
+				struct prox_state *st)
+{
+	int ret;
+
+	ret = sensor_hub_input_get_attribute_info(hsdev, HID_INPUT_REPORT,
+			usage_id,
+			HID_USAGE_SENSOR_HUMAN_PRESENCE,
+			&st->prox_attr);
+	if (ret < 0)
+		return ret;
+	prox_adjust_channel_bit_mask(channels, CHANNEL_SCAN_INDEX_PRESENCE,
+					st->prox_attr.size);
+
+	dev_dbg(&pdev->dev, "prox %x:%x\n", st->prox_attr.index,
+			st->prox_attr.report_id);
+
+	/* Set Sensitivity field ids, when there is no individual modifier */
+	if (st->common_attributes.sensitivity.index < 0) {
+		sensor_hub_input_get_attribute_info(hsdev,
+			HID_FEATURE_REPORT, usage_id,
+			HID_USAGE_SENSOR_DATA_MOD_CHANGE_SENSITIVITY_ABS |
+			HID_USAGE_SENSOR_DATA_PRESENCE,
+			&st->common_attributes.sensitivity);
+		dev_dbg(&pdev->dev, "Sensitivity index:report %d:%d\n",
+			st->common_attributes.sensitivity.index,
+			st->common_attributes.sensitivity.report_id);
+	}
+	return ret;
+}
+
+/* Function to initialize the processing for usage id */
+static int hid_prox_probe(struct platform_device *pdev)
+{
+	int ret = 0;
+	static const char *name = "prox";
+	struct iio_dev *indio_dev;
+	struct prox_state *prox_state;
+	struct hid_sensor_hub_device *hsdev = pdev->dev.platform_data;
+	struct iio_chan_spec *channels;
+
+	indio_dev = devm_iio_device_alloc(&pdev->dev,
+				sizeof(struct prox_state));
+	if (!indio_dev)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, indio_dev);
+
+	prox_state = iio_priv(indio_dev);
+	prox_state->common_attributes.hsdev = hsdev;
+	prox_state->common_attributes.pdev = pdev;
+
+	ret = hid_sensor_parse_common_attributes(hsdev, HID_USAGE_SENSOR_PROX,
+					&prox_state->common_attributes);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to setup common attributes\n");
+		return ret;
+	}
+
+	channels = kmemdup(prox_channels, sizeof(prox_channels), GFP_KERNEL);
+	if (!channels) {
+		dev_err(&pdev->dev, "failed to duplicate channels\n");
+		return -ENOMEM;
+	}
+
+	ret = prox_parse_report(pdev, hsdev, channels,
+				HID_USAGE_SENSOR_PROX, prox_state);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to setup attributes\n");
+		goto error_free_dev_mem;
+	}
+
+	indio_dev->channels = channels;
+	indio_dev->num_channels =
+				ARRAY_SIZE(prox_channels);
+	indio_dev->dev.parent = &pdev->dev;
+	indio_dev->info = &prox_info;
+	indio_dev->name = name;
+	indio_dev->modes = INDIO_DIRECT_MODE;
+
+	ret = iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time,
+		NULL, NULL);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to initialize trigger buffer\n");
+		goto error_free_dev_mem;
+	}
+	prox_state->common_attributes.data_ready = false;
+	ret = hid_sensor_setup_trigger(indio_dev, name,
+				&prox_state->common_attributes);
+	if (ret) {
+		dev_err(&pdev->dev, "trigger setup failed\n");
+		goto error_unreg_buffer_funcs;
+	}
+
+	ret = iio_device_register(indio_dev);
+	if (ret) {
+		dev_err(&pdev->dev, "device register failed\n");
+		goto error_remove_trigger;
+	}
+
+	prox_state->callbacks.send_event = prox_proc_event;
+	prox_state->callbacks.capture_sample = prox_capture_sample;
+	prox_state->callbacks.pdev = pdev;
+	ret = sensor_hub_register_callback(hsdev, HID_USAGE_SENSOR_PROX,
+					&prox_state->callbacks);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "callback reg failed\n");
+		goto error_iio_unreg;
+	}
+
+	return ret;
+
+error_iio_unreg:
+	iio_device_unregister(indio_dev);
+error_remove_trigger:
+	hid_sensor_remove_trigger(&prox_state->common_attributes);
+error_unreg_buffer_funcs:
+	iio_triggered_buffer_cleanup(indio_dev);
+error_free_dev_mem:
+	kfree(indio_dev->channels);
+	return ret;
+}
+
+/* Function to deinitialize the processing for usage id */
+static int hid_prox_remove(struct platform_device *pdev)
+{
+	struct hid_sensor_hub_device *hsdev = pdev->dev.platform_data;
+	struct iio_dev *indio_dev = platform_get_drvdata(pdev);
+	struct prox_state *prox_state = iio_priv(indio_dev);
+
+	sensor_hub_remove_callback(hsdev, HID_USAGE_SENSOR_PROX);
+	iio_device_unregister(indio_dev);
+	hid_sensor_remove_trigger(&prox_state->common_attributes);
+	iio_triggered_buffer_cleanup(indio_dev);
+	kfree(indio_dev->channels);
+
+	return 0;
+}
+
+static struct platform_device_id hid_prox_ids[] = {
+	{
+		/* Format: HID-SENSOR-usage_id_in_hex_lowercase */
+		.name = "HID-SENSOR-200011",
+	},
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(platform, hid_prox_ids);
+
+static struct platform_driver hid_prox_platform_driver = {
+	.id_table = hid_prox_ids,
+	.driver = {
+		.name	= KBUILD_MODNAME,
+		.owner	= THIS_MODULE,
+	},
+	.probe		= hid_prox_probe,
+	.remove		= hid_prox_remove,
+};
+module_platform_driver(hid_prox_platform_driver);
+
+MODULE_DESCRIPTION("HID Sensor Proximity");
+MODULE_AUTHOR("Archana Patni <archana.patni@intel.com>");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/hid-sensor-ids.h b/include/linux/hid-sensor-ids.h
index beaf965621c1..9bc9e35f1b3f 100644
--- a/include/linux/hid-sensor-ids.h
+++ b/include/linux/hid-sensor-ids.h
@@ -33,6 +33,11 @@
 #define HID_USAGE_SENSOR_DATA_LIGHT				0x2004d0
 #define HID_USAGE_SENSOR_LIGHT_ILLUM				0x2004d1
 
+/* PROX (200011) */
+#define HID_USAGE_SENSOR_PROX                                   0x200011
+#define HID_USAGE_SENSOR_DATA_PRESENCE                          0x2004b0
+#define HID_USAGE_SENSOR_HUMAN_PRESENCE                         0x2004b1
+
 /* Gyro 3D: (200076) */
 #define HID_USAGE_SENSOR_GYRO_3D				0x200076
 #define HID_USAGE_SENSOR_DATA_ANGL_VELOCITY			0x200456
-- 
cgit v1.2.3


From f64a799b8a49e3e26497b26ea78af01fc6302874 Mon Sep 17 00:00:00 2001
From: Archana Patni <archana.patni@linux.intel.com>
Date: Thu, 20 Feb 2014 06:30:00 +0000
Subject: iio: hid-sensors: Added Pressure Sensor driver

Added usage id processing for Pressure Sensor. This uses IIO
interfaces for triggered buffer to present data to user
mode. This uses HID sensor framework for registering callback
events from the sensor hub.

Signed-off-by: Archana Patni <archana.patni@intel.com>
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 drivers/iio/pressure/Kconfig            |  14 ++
 drivers/iio/pressure/Makefile           |   1 +
 drivers/iio/pressure/hid-sensor-press.c | 376 ++++++++++++++++++++++++++++++++
 include/linux/hid-sensor-ids.h          |   5 +
 4 files changed, 396 insertions(+)
 create mode 100644 drivers/iio/pressure/hid-sensor-press.c

(limited to 'include/linux')

diff --git a/drivers/iio/pressure/Kconfig b/drivers/iio/pressure/Kconfig
index a8b9cae5c173..6215761b3c53 100644
--- a/drivers/iio/pressure/Kconfig
+++ b/drivers/iio/pressure/Kconfig
@@ -5,6 +5,20 @@
 
 menu "Pressure sensors"
 
+config HID_SENSOR_PRESS
+	depends on HID_SENSOR_HUB
+	select IIO_BUFFER
+	select IIO_TRIGGERED_BUFFER
+	select HID_SENSOR_IIO_COMMON
+	select HID_SENSOR_IIO_TRIGGER
+	tristate "HID PRESS"
+	help
+	  Say yes here to build support for the HID SENSOR
+	  Pressure driver
+
+          To compile this driver as a module, choose M here: the module
+          will be called hid-sensor-press.
+
 config MPL3115
 	tristate "Freescale MPL3115A2 pressure sensor driver"
 	depends on I2C
diff --git a/drivers/iio/pressure/Makefile b/drivers/iio/pressure/Makefile
index 42bb9fcf5436..4a57bf65b04b 100644
--- a/drivers/iio/pressure/Makefile
+++ b/drivers/iio/pressure/Makefile
@@ -3,6 +3,7 @@
 #
 
 # When adding new entries keep the list in alphabetical order
+obj-$(CONFIG_HID_SENSOR_PRESS)   += hid-sensor-press.o
 obj-$(CONFIG_MPL3115) += mpl3115.o
 obj-$(CONFIG_IIO_ST_PRESS) += st_pressure.o
 st_pressure-y := st_pressure_core.o
diff --git a/drivers/iio/pressure/hid-sensor-press.c b/drivers/iio/pressure/hid-sensor-press.c
new file mode 100644
index 000000000000..e0e6409aa94e
--- /dev/null
+++ b/drivers/iio/pressure/hid-sensor-press.c
@@ -0,0 +1,376 @@
+/*
+ * HID Sensors Driver
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.
+ *
+ */
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/slab.h>
+#include <linux/hid-sensor-hub.h>
+#include <linux/iio/iio.h>
+#include <linux/iio/sysfs.h>
+#include <linux/iio/buffer.h>
+#include <linux/iio/trigger_consumer.h>
+#include <linux/iio/triggered_buffer.h>
+#include "../common/hid-sensors/hid-sensor-trigger.h"
+
+#define CHANNEL_SCAN_INDEX_PRESSURE 0
+
+struct press_state {
+	struct hid_sensor_hub_callbacks callbacks;
+	struct hid_sensor_common common_attributes;
+	struct hid_sensor_hub_attribute_info press_attr;
+	u32 press_data;
+};
+
+/* Channel definitions */
+static const struct iio_chan_spec press_channels[] = {
+	{
+		.type = IIO_PRESSURE,
+		.modified = 1,
+		.channel2 = IIO_NO_MOD,
+		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),
+		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) |
+		BIT(IIO_CHAN_INFO_SCALE) |
+		BIT(IIO_CHAN_INFO_SAMP_FREQ) |
+		BIT(IIO_CHAN_INFO_HYSTERESIS),
+		.scan_index = CHANNEL_SCAN_INDEX_PRESSURE,
+	}
+};
+
+/* Adjust channel real bits based on report descriptor */
+static void press_adjust_channel_bit_mask(struct iio_chan_spec *channels,
+					int channel, int size)
+{
+	channels[channel].scan_type.sign = 's';
+	/* Real storage bits will change based on the report desc. */
+	channels[channel].scan_type.realbits = size * 8;
+	/* Maximum size of a sample to capture is u32 */
+	channels[channel].scan_type.storagebits = sizeof(u32) * 8;
+}
+
+/* Channel read_raw handler */
+static int press_read_raw(struct iio_dev *indio_dev,
+			      struct iio_chan_spec const *chan,
+			      int *val, int *val2,
+			      long mask)
+{
+	struct press_state *press_state = iio_priv(indio_dev);
+	int report_id = -1;
+	u32 address;
+	int ret;
+	int ret_type;
+
+	*val = 0;
+	*val2 = 0;
+	switch (mask) {
+	case IIO_CHAN_INFO_RAW:
+		switch (chan->scan_index) {
+		case  CHANNEL_SCAN_INDEX_PRESSURE:
+			report_id = press_state->press_attr.report_id;
+			address =
+			HID_USAGE_SENSOR_ATMOSPHERIC_PRESSURE;
+			break;
+		default:
+			report_id = -1;
+			break;
+		}
+		if (report_id >= 0)
+			*val = sensor_hub_input_attr_get_raw_value(
+				press_state->common_attributes.hsdev,
+				HID_USAGE_SENSOR_PRESSURE, address,
+				report_id);
+		else {
+			*val = 0;
+			return -EINVAL;
+		}
+		ret_type = IIO_VAL_INT;
+		break;
+	case IIO_CHAN_INFO_SCALE:
+		*val = press_state->press_attr.units;
+		ret_type = IIO_VAL_INT;
+		break;
+	case IIO_CHAN_INFO_OFFSET:
+		*val = hid_sensor_convert_exponent(
+				press_state->press_attr.unit_expo);
+		ret_type = IIO_VAL_INT;
+		break;
+	case IIO_CHAN_INFO_SAMP_FREQ:
+		ret = hid_sensor_read_samp_freq_value(
+				&press_state->common_attributes, val, val2);
+		ret_type = IIO_VAL_INT_PLUS_MICRO;
+		break;
+	case IIO_CHAN_INFO_HYSTERESIS:
+		ret = hid_sensor_read_raw_hyst_value(
+				&press_state->common_attributes, val, val2);
+		ret_type = IIO_VAL_INT_PLUS_MICRO;
+		break;
+	default:
+		ret_type = -EINVAL;
+		break;
+	}
+
+	return ret_type;
+}
+
+/* Channel write_raw handler */
+static int press_write_raw(struct iio_dev *indio_dev,
+			       struct iio_chan_spec const *chan,
+			       int val,
+			       int val2,
+			       long mask)
+{
+	struct press_state *press_state = iio_priv(indio_dev);
+	int ret = 0;
+
+	switch (mask) {
+	case IIO_CHAN_INFO_SAMP_FREQ:
+		ret = hid_sensor_write_samp_freq_value(
+				&press_state->common_attributes, val, val2);
+		break;
+	case IIO_CHAN_INFO_HYSTERESIS:
+		ret = hid_sensor_write_raw_hyst_value(
+				&press_state->common_attributes, val, val2);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static const struct iio_info press_info = {
+	.driver_module = THIS_MODULE,
+	.read_raw = &press_read_raw,
+	.write_raw = &press_write_raw,
+};
+
+/* Function to push data to buffer */
+static void hid_sensor_push_data(struct iio_dev *indio_dev, const void *data,
+					int len)
+{
+	dev_dbg(&indio_dev->dev, "hid_sensor_push_data\n");
+	iio_push_to_buffers(indio_dev, data);
+}
+
+/* Callback handler to send event after all samples are received and captured */
+static int press_proc_event(struct hid_sensor_hub_device *hsdev,
+				unsigned usage_id,
+				void *priv)
+{
+	struct iio_dev *indio_dev = platform_get_drvdata(priv);
+	struct press_state *press_state = iio_priv(indio_dev);
+
+	dev_dbg(&indio_dev->dev, "press_proc_event [%d]\n",
+				press_state->common_attributes.data_ready);
+	if (press_state->common_attributes.data_ready)
+		hid_sensor_push_data(indio_dev,
+				&press_state->press_data,
+				sizeof(press_state->press_data));
+
+	return 0;
+}
+
+/* Capture samples in local storage */
+static int press_capture_sample(struct hid_sensor_hub_device *hsdev,
+				unsigned usage_id,
+				size_t raw_len, char *raw_data,
+				void *priv)
+{
+	struct iio_dev *indio_dev = platform_get_drvdata(priv);
+	struct press_state *press_state = iio_priv(indio_dev);
+	int ret = -EINVAL;
+
+	switch (usage_id) {
+	case HID_USAGE_SENSOR_ATMOSPHERIC_PRESSURE:
+		press_state->press_data = *(u32 *)raw_data;
+		ret = 0;
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+/* Parse report which is specific to an usage id*/
+static int press_parse_report(struct platform_device *pdev,
+				struct hid_sensor_hub_device *hsdev,
+				struct iio_chan_spec *channels,
+				unsigned usage_id,
+				struct press_state *st)
+{
+	int ret;
+
+	ret = sensor_hub_input_get_attribute_info(hsdev, HID_INPUT_REPORT,
+			usage_id,
+			HID_USAGE_SENSOR_ATMOSPHERIC_PRESSURE,
+			&st->press_attr);
+	if (ret < 0)
+		return ret;
+	press_adjust_channel_bit_mask(channels, CHANNEL_SCAN_INDEX_PRESSURE,
+					st->press_attr.size);
+
+	dev_dbg(&pdev->dev, "press %x:%x\n", st->press_attr.index,
+			st->press_attr.report_id);
+
+	/* Set Sensitivity field ids, when there is no individual modifier */
+	if (st->common_attributes.sensitivity.index < 0) {
+		sensor_hub_input_get_attribute_info(hsdev,
+			HID_FEATURE_REPORT, usage_id,
+			HID_USAGE_SENSOR_DATA_MOD_CHANGE_SENSITIVITY_ABS |
+			HID_USAGE_SENSOR_DATA_ATMOSPHERIC_PRESSURE,
+			&st->common_attributes.sensitivity);
+		dev_dbg(&pdev->dev, "Sensitivity index:report %d:%d\n",
+			st->common_attributes.sensitivity.index,
+			st->common_attributes.sensitivity.report_id);
+	}
+	return ret;
+}
+
+/* Function to initialize the processing for usage id */
+static int hid_press_probe(struct platform_device *pdev)
+{
+	int ret = 0;
+	static const char *name = "press";
+	struct iio_dev *indio_dev;
+	struct press_state *press_state;
+	struct hid_sensor_hub_device *hsdev = pdev->dev.platform_data;
+	struct iio_chan_spec *channels;
+
+	indio_dev = devm_iio_device_alloc(&pdev->dev,
+				sizeof(struct press_state));
+	if (!indio_dev)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, indio_dev);
+
+	press_state = iio_priv(indio_dev);
+	press_state->common_attributes.hsdev = hsdev;
+	press_state->common_attributes.pdev = pdev;
+
+	ret = hid_sensor_parse_common_attributes(hsdev,
+					HID_USAGE_SENSOR_PRESSURE,
+					&press_state->common_attributes);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to setup common attributes\n");
+		return ret;
+	}
+
+	channels = kmemdup(press_channels, sizeof(press_channels), GFP_KERNEL);
+	if (!channels) {
+		dev_err(&pdev->dev, "failed to duplicate channels\n");
+		return -ENOMEM;
+	}
+
+	ret = press_parse_report(pdev, hsdev, channels,
+				HID_USAGE_SENSOR_PRESSURE, press_state);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to setup attributes\n");
+		goto error_free_dev_mem;
+	}
+
+	indio_dev->channels = channels;
+	indio_dev->num_channels =
+				ARRAY_SIZE(press_channels);
+	indio_dev->dev.parent = &pdev->dev;
+	indio_dev->info = &press_info;
+	indio_dev->name = name;
+	indio_dev->modes = INDIO_DIRECT_MODE;
+
+	ret = iio_triggered_buffer_setup(indio_dev, &iio_pollfunc_store_time,
+		NULL, NULL);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to initialize trigger buffer\n");
+		goto error_free_dev_mem;
+	}
+	press_state->common_attributes.data_ready = false;
+	ret = hid_sensor_setup_trigger(indio_dev, name,
+				&press_state->common_attributes);
+	if (ret) {
+		dev_err(&pdev->dev, "trigger setup failed\n");
+		goto error_unreg_buffer_funcs;
+	}
+
+	ret = iio_device_register(indio_dev);
+	if (ret) {
+		dev_err(&pdev->dev, "device register failed\n");
+		goto error_remove_trigger;
+	}
+
+	press_state->callbacks.send_event = press_proc_event;
+	press_state->callbacks.capture_sample = press_capture_sample;
+	press_state->callbacks.pdev = pdev;
+	ret = sensor_hub_register_callback(hsdev, HID_USAGE_SENSOR_PRESSURE,
+					&press_state->callbacks);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "callback reg failed\n");
+		goto error_iio_unreg;
+	}
+
+	return ret;
+
+error_iio_unreg:
+	iio_device_unregister(indio_dev);
+error_remove_trigger:
+	hid_sensor_remove_trigger(&press_state->common_attributes);
+error_unreg_buffer_funcs:
+	iio_triggered_buffer_cleanup(indio_dev);
+error_free_dev_mem:
+	kfree(indio_dev->channels);
+	return ret;
+}
+
+/* Function to deinitialize the processing for usage id */
+static int hid_press_remove(struct platform_device *pdev)
+{
+	struct hid_sensor_hub_device *hsdev = pdev->dev.platform_data;
+	struct iio_dev *indio_dev = platform_get_drvdata(pdev);
+	struct press_state *press_state = iio_priv(indio_dev);
+
+	sensor_hub_remove_callback(hsdev, HID_USAGE_SENSOR_PRESSURE);
+	iio_device_unregister(indio_dev);
+	hid_sensor_remove_trigger(&press_state->common_attributes);
+	iio_triggered_buffer_cleanup(indio_dev);
+	kfree(indio_dev->channels);
+
+	return 0;
+}
+
+static struct platform_device_id hid_press_ids[] = {
+	{
+		/* Format: HID-SENSOR-usage_id_in_hex_lowercase */
+		.name = "HID-SENSOR-200031",
+	},
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(platform, hid_press_ids);
+
+static struct platform_driver hid_press_platform_driver = {
+	.id_table = hid_press_ids,
+	.driver = {
+		.name	= KBUILD_MODNAME,
+		.owner	= THIS_MODULE,
+	},
+	.probe		= hid_press_probe,
+	.remove		= hid_press_remove,
+};
+module_platform_driver(hid_press_platform_driver);
+
+MODULE_DESCRIPTION("HID Sensor Pressure");
+MODULE_AUTHOR("Archana Patni <archana.patni@intel.com>");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/hid-sensor-ids.h b/include/linux/hid-sensor-ids.h
index 9bc9e35f1b3f..537161a997ab 100644
--- a/include/linux/hid-sensor-ids.h
+++ b/include/linux/hid-sensor-ids.h
@@ -38,6 +38,11 @@
 #define HID_USAGE_SENSOR_DATA_PRESENCE                          0x2004b0
 #define HID_USAGE_SENSOR_HUMAN_PRESENCE                         0x2004b1
 
+/* Pressure (200031) */
+#define HID_USAGE_SENSOR_PRESSURE                               0x200031
+#define HID_USAGE_SENSOR_DATA_ATMOSPHERIC_PRESSURE              0x200430
+#define HID_USAGE_SENSOR_ATMOSPHERIC_PRESSURE                   0x200431
+
 /* Gyro 3D: (200076) */
 #define HID_USAGE_SENSOR_GYRO_3D				0x200076
 #define HID_USAGE_SENSOR_DATA_ANGL_VELOCITY			0x200456
-- 
cgit v1.2.3


From 9107ebbf9652c033eb5dd10a6ea34a132db3cde1 Mon Sep 17 00:00:00 2001
From: Micky Ching <micky_ching@realsil.com.cn>
Date: Fri, 21 Feb 2014 18:40:35 +0800
Subject: mmc: sdhci: add support for realtek rts5250

Add support for realtek rts5250 pci card reader. The card reader has
some problems with DDR50 mode, so add a new quirks2 for broken ddr50.

Signed-off-by: Micky Ching <micky_ching@realsil.com.cn>
Signed-off-by: Chris Ball <chris@printf.net>
---
 drivers/mmc/host/sdhci-pci.c | 20 ++++++++++++++++++++
 drivers/mmc/host/sdhci.c     |  3 ++-
 include/linux/mmc/sdhci.h    |  2 ++
 3 files changed, 24 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/mmc/host/sdhci-pci.c b/drivers/mmc/host/sdhci-pci.c
index 0955777b6c7e..fdc612120362 100644
--- a/drivers/mmc/host/sdhci-pci.c
+++ b/drivers/mmc/host/sdhci-pci.c
@@ -610,6 +610,18 @@ static const struct sdhci_pci_fixes sdhci_via = {
 	.probe		= via_probe,
 };
 
+static int rtsx_probe_slot(struct sdhci_pci_slot *slot)
+{
+	slot->host->mmc->caps2 |= MMC_CAP2_HS200;
+	return 0;
+}
+
+static const struct sdhci_pci_fixes sdhci_rtsx = {
+	.quirks2	= SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
+			SDHCI_QUIRK2_BROKEN_DDR50,
+	.probe_slot	= rtsx_probe_slot,
+};
+
 static const struct pci_device_id pci_ids[] = {
 	{
 		.vendor		= PCI_VENDOR_ID_RICOH,
@@ -731,6 +743,14 @@ static const struct pci_device_id pci_ids[] = {
 		.driver_data	= (kernel_ulong_t)&sdhci_via,
 	},
 
+	{
+		.vendor		= PCI_VENDOR_ID_REALTEK,
+		.device		= 0x5250,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.driver_data	= (kernel_ulong_t)&sdhci_rtsx,
+	},
+
 	{
 		.vendor		= PCI_VENDOR_ID_INTEL,
 		.device		= PCI_DEVICE_ID_INTEL_MRST_SD0,
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 9ddef4763541..8958edc03e04 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -3020,7 +3020,8 @@ int sdhci_add_host(struct sdhci_host *host)
 	} else if (caps[1] & SDHCI_SUPPORT_SDR50)
 		mmc->caps |= MMC_CAP_UHS_SDR50;
 
-	if (caps[1] & SDHCI_SUPPORT_DDR50)
+	if ((caps[1] & SDHCI_SUPPORT_DDR50) &&
+		!(host->quirks2 & SDHCI_QUIRK2_BROKEN_DDR50))
 		mmc->caps |= MMC_CAP_UHS_DDR50;
 
 	/* Does the host need tuning for SDR50? */
diff --git a/include/linux/mmc/sdhci.h b/include/linux/mmc/sdhci.h
index 362927c48f97..7be12b883485 100644
--- a/include/linux/mmc/sdhci.h
+++ b/include/linux/mmc/sdhci.h
@@ -100,6 +100,8 @@ struct sdhci_host {
 #define SDHCI_QUIRK2_BROKEN_HOST_CONTROL		(1<<5)
 /* Controller does not support HS200 */
 #define SDHCI_QUIRK2_BROKEN_HS200			(1<<6)
+/* Controller does not support DDR50 */
+#define SDHCI_QUIRK2_BROKEN_DDR50			(1<<7)
 
 	int irq;		/* Device IRQ */
 	void __iomem *ioaddr;	/* Mapped address */
-- 
cgit v1.2.3


From abcc6b2943145ae2e17a52632ccab50cd612914c Mon Sep 17 00:00:00 2001
From: Micky Ching <micky_ching@realsil.com.cn>
Date: Mon, 17 Feb 2014 16:45:47 +0800
Subject: mmc: rtsx: modify phase searching method for tuning

The new phase searching method is more concise and easier to
understand.

Signed-off-by: Micky Ching <micky_ching@realsil.com.cn>
Signed-off-by: Chris Ball <chris@printf.net>
---
 drivers/mmc/host/rtsx_pci_sdmmc.c | 112 +++++++++++---------------------------
 include/linux/mfd/rtsx_pci.h      |   2 +-
 2 files changed, 33 insertions(+), 81 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c
index cc80e3119d1d..0b9ded13a3ae 100644
--- a/drivers/mmc/host/rtsx_pci_sdmmc.c
+++ b/drivers/mmc/host/rtsx_pci_sdmmc.c
@@ -31,16 +31,6 @@
 #include <linux/mfd/rtsx_pci.h>
 #include <asm/unaligned.h>
 
-/* SD Tuning Data Structure
- * Record continuous timing phase path
- */
-struct timing_phase_path {
-	int start;
-	int end;
-	int mid;
-	int len;
-};
-
 struct realtek_pci_sdmmc {
 	struct platform_device	*pdev;
 	struct rtsx_pcr		*pcr;
@@ -511,85 +501,47 @@ static int sd_change_phase(struct realtek_pci_sdmmc *host,
 	return 0;
 }
 
-static u8 sd_search_final_phase(struct realtek_pci_sdmmc *host, u32 phase_map)
+static inline u32 test_phase_bit(u32 phase_map, unsigned int bit)
 {
-	struct timing_phase_path path[MAX_PHASE + 1];
-	int i, j, cont_path_cnt;
-	int new_block, max_len, final_path_idx;
-	u8 final_phase = 0xFF;
+	bit %= RTSX_PHASE_MAX;
+	return phase_map & (1 << bit);
+}
 
-	/* Parse phase_map, take it as a bit-ring */
-	cont_path_cnt = 0;
-	new_block = 1;
-	j = 0;
-	for (i = 0; i < MAX_PHASE + 1; i++) {
-		if (phase_map & (1 << i)) {
-			if (new_block) {
-				new_block = 0;
-				j = cont_path_cnt++;
-				path[j].start = i;
-				path[j].end = i;
-			} else {
-				path[j].end = i;
-			}
-		} else {
-			new_block = 1;
-			if (cont_path_cnt) {
-				/* Calculate path length and middle point */
-				int idx = cont_path_cnt - 1;
-				path[idx].len =
-					path[idx].end - path[idx].start + 1;
-				path[idx].mid =
-					path[idx].start + path[idx].len / 2;
-			}
-		}
-	}
+static int sd_get_phase_len(u32 phase_map, unsigned int start_bit)
+{
+	int i;
 
-	if (cont_path_cnt == 0) {
-		dev_dbg(sdmmc_dev(host), "No continuous phase path\n");
-		goto finish;
-	} else {
-		/* Calculate last continuous path length and middle point */
-		int idx = cont_path_cnt - 1;
-		path[idx].len = path[idx].end - path[idx].start + 1;
-		path[idx].mid = path[idx].start + path[idx].len / 2;
+	for (i = 0; i < RTSX_PHASE_MAX; i++) {
+		if (test_phase_bit(phase_map, start_bit + i) == 0)
+			return i;
 	}
+	return RTSX_PHASE_MAX;
+}
+
+static u8 sd_search_final_phase(struct realtek_pci_sdmmc *host, u32 phase_map)
+{
+	int start = 0, len = 0;
+	int start_final = 0, len_final = 0;
+	u8 final_phase = 0xFF;
 
-	/* Connect the first and last continuous paths if they are adjacent */
-	if (!path[0].start && (path[cont_path_cnt - 1].end == MAX_PHASE)) {
-		/* Using negative index */
-		path[0].start = path[cont_path_cnt - 1].start - MAX_PHASE - 1;
-		path[0].len += path[cont_path_cnt - 1].len;
-		path[0].mid = path[0].start + path[0].len / 2;
-		/* Convert negative middle point index to positive one */
-		if (path[0].mid < 0)
-			path[0].mid += MAX_PHASE + 1;
-		cont_path_cnt--;
+	if (phase_map == 0) {
+		dev_err(sdmmc_dev(host), "phase error: [map:%x]\n", phase_map);
+		return final_phase;
 	}
 
-	/* Choose the longest continuous phase path */
-	max_len = 0;
-	final_phase = 0;
-	final_path_idx = 0;
-	for (i = 0; i < cont_path_cnt; i++) {
-		if (path[i].len > max_len) {
-			max_len = path[i].len;
-			final_phase = (u8)path[i].mid;
-			final_path_idx = i;
+	while (start < RTSX_PHASE_MAX) {
+		len = sd_get_phase_len(phase_map, start);
+		if (len_final < len) {
+			start_final = start;
+			len_final = len;
 		}
-
-		dev_dbg(sdmmc_dev(host), "path[%d].start = %d\n",
-				i, path[i].start);
-		dev_dbg(sdmmc_dev(host), "path[%d].end = %d\n",
-				i, path[i].end);
-		dev_dbg(sdmmc_dev(host), "path[%d].len = %d\n",
-				i, path[i].len);
-		dev_dbg(sdmmc_dev(host), "path[%d].mid = %d\n",
-				i, path[i].mid);
+		start += len ? len : 1;
 	}
 
-finish:
-	dev_dbg(sdmmc_dev(host), "Final chosen phase: %d\n", final_phase);
+	final_phase = (start_final + len_final / 2) % RTSX_PHASE_MAX;
+	dev_dbg(sdmmc_dev(host), "phase: [map:%x] [maxlen:%d] [final:%d]\n",
+		phase_map, len_final, final_phase);
+
 	return final_phase;
 }
 
@@ -635,7 +587,7 @@ static int sd_tuning_phase(struct realtek_pci_sdmmc *host,
 	int err, i;
 	u32 raw_phase_map = 0;
 
-	for (i = MAX_PHASE; i >= 0; i--) {
+	for (i = 0; i < RTSX_PHASE_MAX; i++) {
 		err = sd_tuning_rx_cmd(host, opcode, (u8)i);
 		if (err == 0)
 			raw_phase_map |= 1 << i;
diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h
index 0ce772105508..a3835976f7c6 100644
--- a/include/linux/mfd/rtsx_pci.h
+++ b/include/linux/mfd/rtsx_pci.h
@@ -144,7 +144,7 @@
 #define HOST_TO_DEVICE		0
 #define DEVICE_TO_HOST		1
 
-#define MAX_PHASE		31
+#define RTSX_PHASE_MAX		32
 #define RX_TUNING_CNT		3
 
 /* SG descriptor */
-- 
cgit v1.2.3


From c42deffd5b53c9e583d83c7964854ede2f12410d Mon Sep 17 00:00:00 2001
From: Micky Ching <micky_ching@realsil.com.cn>
Date: Mon, 17 Feb 2014 16:45:48 +0800
Subject: mmc: rtsx: add support for pre_req and post_req

Add support for non-blocking request, pre_req() runs dma_map_sg() and
post_req() runs dma_unmap_sg(). This patch can increase card read/write
speed, especially for high speed card and slow CPU(for some embedded
platform).

Users can get a great benefit from this patch. if CPU frequency is 800MHz,
SDR104 or DDR50 card read/write speed may increase more than 15%.

test results:
intel i3(800MHz - 2.3GHz), SD card clock 208MHz

performance mode(2.3GHz):
Before:
dd if=/dev/mmcblk0p1 of=/dev/null bs=64k count=1024
67108864 bytes (67 MB) copied, 1.18191 s, 56.8 MB/s
After:
 dd if=/dev/mmcblk0p1 of=/dev/null bs=64k count=1024
67108864 bytes (67 MB) copied, 1.09276 s, 61.4 MB/s

powersave mode(800MHz):
Before:
dd if=/dev/mmcblk0p1 of=/dev/null bs=64k count=1024
67108864 bytes (67 MB) copied, 1.29569 s, 51.8 MB/s
After:
dd if=/dev/mmcblk0p1 of=/dev/null bs=64k count=1024
67108864 bytes (67 MB) copied, 1.11218 s, 60.3 MB/s

Signed-off-by: Micky Ching <micky_ching@realsil.com.cn>
Signed-off-by: Chris Ball <chris@printf.net>
---
 drivers/mfd/rtsx_pcr.c            | 132 ++++++++----
 drivers/mmc/host/rtsx_pci_sdmmc.c | 418 +++++++++++++++++++++++++++++++-------
 include/linux/mfd/rtsx_common.h   |   1 +
 include/linux/mfd/rtsx_pci.h      |   6 +
 4 files changed, 448 insertions(+), 109 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mfd/rtsx_pcr.c b/drivers/mfd/rtsx_pcr.c
index 1d15735f9ef9..c9de3d598ea5 100644
--- a/drivers/mfd/rtsx_pcr.c
+++ b/drivers/mfd/rtsx_pcr.c
@@ -338,58 +338,28 @@ int rtsx_pci_transfer_data(struct rtsx_pcr *pcr, struct scatterlist *sglist,
 		int num_sg, bool read, int timeout)
 {
 	struct completion trans_done;
-	u8 dir;
-	int err = 0, i, count;
+	int err = 0, count;
 	long timeleft;
 	unsigned long flags;
-	struct scatterlist *sg;
-	enum dma_data_direction dma_dir;
-	u32 val;
-	dma_addr_t addr;
-	unsigned int len;
-
-	dev_dbg(&(pcr->pci->dev), "--> %s: num_sg = %d\n", __func__, num_sg);
-
-	/* don't transfer data during abort processing */
-	if (pcr->remove_pci)
-		return -EINVAL;
-
-	if ((sglist == NULL) || (num_sg <= 0))
-		return -EINVAL;
 
-	if (read) {
-		dir = DEVICE_TO_HOST;
-		dma_dir = DMA_FROM_DEVICE;
-	} else {
-		dir = HOST_TO_DEVICE;
-		dma_dir = DMA_TO_DEVICE;
-	}
-
-	count = dma_map_sg(&(pcr->pci->dev), sglist, num_sg, dma_dir);
+	count = rtsx_pci_dma_map_sg(pcr, sglist, num_sg, read);
 	if (count < 1) {
 		dev_err(&(pcr->pci->dev), "scatterlist map failed\n");
 		return -EINVAL;
 	}
 	dev_dbg(&(pcr->pci->dev), "DMA mapping count: %d\n", count);
 
-	val = ((u32)(dir & 0x01) << 29) | TRIG_DMA | ADMA_MODE;
-	pcr->sgi = 0;
-	for_each_sg(sglist, sg, count, i) {
-		addr = sg_dma_address(sg);
-		len = sg_dma_len(sg);
-		rtsx_pci_add_sg_tbl(pcr, addr, len, i == count - 1);
-	}
 
 	spin_lock_irqsave(&pcr->lock, flags);
 
 	pcr->done = &trans_done;
 	pcr->trans_result = TRANS_NOT_READY;
 	init_completion(&trans_done);
-	rtsx_pci_writel(pcr, RTSX_HDBAR, pcr->host_sg_tbl_addr);
-	rtsx_pci_writel(pcr, RTSX_HDBCTLR, val);
 
 	spin_unlock_irqrestore(&pcr->lock, flags);
 
+	rtsx_pci_dma_transfer(pcr, sglist, count, read);
+
 	timeleft = wait_for_completion_interruptible_timeout(
 			&trans_done, msecs_to_jiffies(timeout));
 	if (timeleft <= 0) {
@@ -413,7 +383,7 @@ out:
 	pcr->done = NULL;
 	spin_unlock_irqrestore(&pcr->lock, flags);
 
-	dma_unmap_sg(&(pcr->pci->dev), sglist, num_sg, dma_dir);
+	rtsx_pci_dma_unmap_sg(pcr, sglist, num_sg, read);
 
 	if ((err < 0) && (err != -ENODEV))
 		rtsx_pci_stop_cmd(pcr);
@@ -425,6 +395,73 @@ out:
 }
 EXPORT_SYMBOL_GPL(rtsx_pci_transfer_data);
 
+int rtsx_pci_dma_map_sg(struct rtsx_pcr *pcr, struct scatterlist *sglist,
+		int num_sg, bool read)
+{
+	enum dma_data_direction dir = read ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+
+	if (pcr->remove_pci)
+		return -EINVAL;
+
+	if ((sglist == NULL) || num_sg < 1)
+		return -EINVAL;
+
+	return dma_map_sg(&(pcr->pci->dev), sglist, num_sg, dir);
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_dma_map_sg);
+
+int rtsx_pci_dma_unmap_sg(struct rtsx_pcr *pcr, struct scatterlist *sglist,
+		int num_sg, bool read)
+{
+	enum dma_data_direction dir = read ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+
+	if (pcr->remove_pci)
+		return -EINVAL;
+
+	if (sglist == NULL || num_sg < 1)
+		return -EINVAL;
+
+	dma_unmap_sg(&(pcr->pci->dev), sglist, num_sg, dir);
+	return num_sg;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_dma_unmap_sg);
+
+int rtsx_pci_dma_transfer(struct rtsx_pcr *pcr, struct scatterlist *sglist,
+		int sg_count, bool read)
+{
+	struct scatterlist *sg;
+	dma_addr_t addr;
+	unsigned int len;
+	int i;
+	u32 val;
+	u8 dir = read ? DEVICE_TO_HOST : HOST_TO_DEVICE;
+	unsigned long flags;
+
+	if (pcr->remove_pci)
+		return -EINVAL;
+
+	if ((sglist == NULL) || (sg_count < 1))
+		return -EINVAL;
+
+	val = ((u32)(dir & 0x01) << 29) | TRIG_DMA | ADMA_MODE;
+	pcr->sgi = 0;
+	for_each_sg(sglist, sg, sg_count, i) {
+		addr = sg_dma_address(sg);
+		len = sg_dma_len(sg);
+		rtsx_pci_add_sg_tbl(pcr, addr, len, i == sg_count - 1);
+	}
+
+	spin_lock_irqsave(&pcr->lock, flags);
+
+	rtsx_pci_writel(pcr, RTSX_HDBAR, pcr->host_sg_tbl_addr);
+	rtsx_pci_writel(pcr, RTSX_HDBCTLR, val);
+
+	spin_unlock_irqrestore(&pcr->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_pci_dma_transfer);
+
 int rtsx_pci_read_ppbuf(struct rtsx_pcr *pcr, u8 *buf, int buf_len)
 {
 	int err;
@@ -836,6 +873,8 @@ static irqreturn_t rtsx_pci_isr(int irq, void *dev_id)
 	int_reg = rtsx_pci_readl(pcr, RTSX_BIPR);
 	/* Clear interrupt flag */
 	rtsx_pci_writel(pcr, RTSX_BIPR, int_reg);
+	dev_dbg(&pcr->pci->dev, "=========== BIPR 0x%8x ==========\n", int_reg);
+
 	if ((int_reg & pcr->bier) == 0) {
 		spin_unlock(&pcr->lock);
 		return IRQ_NONE;
@@ -866,17 +905,28 @@ static irqreturn_t rtsx_pci_isr(int irq, void *dev_id)
 	}
 
 	if (int_reg & (NEED_COMPLETE_INT | DELINK_INT)) {
-		if (int_reg & (TRANS_FAIL_INT | DELINK_INT)) {
+		if (int_reg & (TRANS_FAIL_INT | DELINK_INT))
 			pcr->trans_result = TRANS_RESULT_FAIL;
-			if (pcr->done)
-				complete(pcr->done);
-		} else if (int_reg & TRANS_OK_INT) {
+		else if (int_reg & TRANS_OK_INT)
 			pcr->trans_result = TRANS_RESULT_OK;
-			if (pcr->done)
-				complete(pcr->done);
+
+		if (pcr->done)
+			complete(pcr->done);
+
+		if (int_reg & SD_EXIST) {
+			struct rtsx_slot *slot = &pcr->slots[RTSX_SD_CARD];
+			if (slot && slot->done_transfer)
+				slot->done_transfer(slot->p_dev);
+		}
+
+		if (int_reg & MS_EXIST) {
+			struct rtsx_slot *slot = &pcr->slots[RTSX_SD_CARD];
+			if (slot && slot->done_transfer)
+				slot->done_transfer(slot->p_dev);
 		}
 	}
 
+
 	if (pcr->card_inserted || pcr->card_removed)
 		schedule_delayed_work(&pcr->carddet_work,
 				msecs_to_jiffies(200));
diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c
index 0b9ded13a3ae..5fb994f9a653 100644
--- a/drivers/mmc/host/rtsx_pci_sdmmc.c
+++ b/drivers/mmc/host/rtsx_pci_sdmmc.c
@@ -31,14 +31,28 @@
 #include <linux/mfd/rtsx_pci.h>
 #include <asm/unaligned.h>
 
+struct realtek_next {
+	unsigned int	sg_count;
+	s32		cookie;
+};
+
 struct realtek_pci_sdmmc {
 	struct platform_device	*pdev;
 	struct rtsx_pcr		*pcr;
 	struct mmc_host		*mmc;
 	struct mmc_request	*mrq;
-
-	struct mutex		host_mutex;
-
+	struct mmc_command	*cmd;
+	struct mmc_data		*data;
+
+	spinlock_t		lock;
+	struct timer_list	timer;
+	struct tasklet_struct	cmd_tasklet;
+	struct tasklet_struct	data_tasklet;
+	struct tasklet_struct	finish_tasklet;
+
+	u8			rsp_type;
+	u8			rsp_len;
+	int			sg_count;
 	u8			ssc_depth;
 	unsigned int		clock;
 	bool			vpclk;
@@ -48,8 +62,13 @@ struct realtek_pci_sdmmc {
 	int			power_state;
 #define SDMMC_POWER_ON		1
 #define SDMMC_POWER_OFF		0
+
+	struct realtek_next	next_data;
 };
 
+static int sd_start_multi_rw(struct realtek_pci_sdmmc *host,
+		struct mmc_request *mrq);
+
 static inline struct device *sdmmc_dev(struct realtek_pci_sdmmc *host)
 {
 	return &(host->pdev->dev);
@@ -86,6 +105,95 @@ static void sd_print_debug_regs(struct realtek_pci_sdmmc *host)
 #define sd_print_debug_regs(host)
 #endif /* DEBUG */
 
+static void sd_isr_done_transfer(struct platform_device *pdev)
+{
+	struct realtek_pci_sdmmc *host = platform_get_drvdata(pdev);
+
+	spin_lock(&host->lock);
+	if (host->cmd)
+		tasklet_schedule(&host->cmd_tasklet);
+	if (host->data)
+		tasklet_schedule(&host->data_tasklet);
+	spin_unlock(&host->lock);
+}
+
+static void sd_request_timeout(unsigned long host_addr)
+{
+	struct realtek_pci_sdmmc *host = (struct realtek_pci_sdmmc *)host_addr;
+	unsigned long flags;
+
+	spin_lock_irqsave(&host->lock, flags);
+
+	if (!host->mrq) {
+		dev_err(sdmmc_dev(host), "error: no request exist\n");
+		goto out;
+	}
+
+	if (host->cmd)
+		host->cmd->error = -ETIMEDOUT;
+	if (host->data)
+		host->data->error = -ETIMEDOUT;
+
+	dev_dbg(sdmmc_dev(host), "timeout for request\n");
+
+out:
+	tasklet_schedule(&host->finish_tasklet);
+	spin_unlock_irqrestore(&host->lock, flags);
+}
+
+static void sd_finish_request(unsigned long host_addr)
+{
+	struct realtek_pci_sdmmc *host = (struct realtek_pci_sdmmc *)host_addr;
+	struct rtsx_pcr *pcr = host->pcr;
+	struct mmc_request *mrq;
+	struct mmc_command *cmd;
+	struct mmc_data *data;
+	unsigned long flags;
+	bool any_error;
+
+	spin_lock_irqsave(&host->lock, flags);
+
+	del_timer(&host->timer);
+	mrq = host->mrq;
+	if (!mrq) {
+		dev_err(sdmmc_dev(host), "error: no request need finish\n");
+		goto out;
+	}
+
+	cmd = mrq->cmd;
+	data = mrq->data;
+
+	any_error = (mrq->sbc && mrq->sbc->error) ||
+		(mrq->stop && mrq->stop->error) ||
+		(cmd && cmd->error) || (data && data->error);
+
+	if (any_error) {
+		rtsx_pci_stop_cmd(pcr);
+		sd_clear_error(host);
+	}
+
+	if (data) {
+		if (any_error)
+			data->bytes_xfered = 0;
+		else
+			data->bytes_xfered = data->blocks * data->blksz;
+
+		if (!data->host_cookie)
+			rtsx_pci_dma_unmap_sg(pcr, data->sg, data->sg_len,
+					data->flags & MMC_DATA_READ);
+
+	}
+
+	host->mrq = NULL;
+	host->cmd = NULL;
+	host->data = NULL;
+
+out:
+	spin_unlock_irqrestore(&host->lock, flags);
+	mutex_unlock(&pcr->pcr_mutex);
+	mmc_request_done(host->mmc, mrq);
+}
+
 static int sd_read_data(struct realtek_pci_sdmmc *host, u8 *cmd, u16 byte_cnt,
 		u8 *buf, int buf_len, int timeout)
 {
@@ -203,8 +311,7 @@ static int sd_write_data(struct realtek_pci_sdmmc *host, u8 *cmd, u16 byte_cnt,
 	return 0;
 }
 
-static void sd_send_cmd_get_rsp(struct realtek_pci_sdmmc *host,
-		struct mmc_command *cmd)
+static void sd_send_cmd(struct realtek_pci_sdmmc *host, struct mmc_command *cmd)
 {
 	struct rtsx_pcr *pcr = host->pcr;
 	u8 cmd_idx = (u8)cmd->opcode;
@@ -212,11 +319,14 @@ static void sd_send_cmd_get_rsp(struct realtek_pci_sdmmc *host,
 	int err = 0;
 	int timeout = 100;
 	int i;
-	u8 *ptr;
-	int stat_idx = 0;
 	u8 rsp_type;
 	int rsp_len = 5;
-	bool clock_toggled = false;
+	unsigned long flags;
+
+	if (host->cmd)
+		dev_err(sdmmc_dev(host), "error: cmd already exist\n");
+
+	host->cmd = cmd;
 
 	dev_dbg(sdmmc_dev(host), "%s: SD/MMC CMD %d, arg = 0x%08x\n",
 			__func__, cmd_idx, arg);
@@ -251,6 +361,8 @@ static void sd_send_cmd_get_rsp(struct realtek_pci_sdmmc *host,
 		err = -EINVAL;
 		goto out;
 	}
+	host->rsp_type = rsp_type;
+	host->rsp_len = rsp_len;
 
 	if (rsp_type == SD_RSP_TYPE_R1b)
 		timeout = 3000;
@@ -260,8 +372,6 @@ static void sd_send_cmd_get_rsp(struct realtek_pci_sdmmc *host,
 				0xFF, SD_CLK_TOGGLE_EN);
 		if (err < 0)
 			goto out;
-
-		clock_toggled = true;
 	}
 
 	rtsx_pci_init_cmd(pcr);
@@ -285,25 +395,60 @@ static void sd_send_cmd_get_rsp(struct realtek_pci_sdmmc *host,
 		/* Read data from ping-pong buffer */
 		for (i = PPBUF_BASE2; i < PPBUF_BASE2 + 16; i++)
 			rtsx_pci_add_cmd(pcr, READ_REG_CMD, (u16)i, 0, 0);
-		stat_idx = 16;
 	} else if (rsp_type != SD_RSP_TYPE_R0) {
 		/* Read data from SD_CMDx registers */
 		for (i = SD_CMD0; i <= SD_CMD4; i++)
 			rtsx_pci_add_cmd(pcr, READ_REG_CMD, (u16)i, 0, 0);
-		stat_idx = 5;
 	}
 
 	rtsx_pci_add_cmd(pcr, READ_REG_CMD, SD_STAT1, 0, 0);
 
-	err = rtsx_pci_send_cmd(pcr, timeout);
-	if (err < 0) {
-		sd_print_debug_regs(host);
-		sd_clear_error(host);
-		dev_dbg(sdmmc_dev(host),
-			"rtsx_pci_send_cmd error (err = %d)\n", err);
+	mod_timer(&host->timer, jiffies + msecs_to_jiffies(timeout));
+
+	spin_lock_irqsave(&pcr->lock, flags);
+	pcr->trans_result = TRANS_NOT_READY;
+	rtsx_pci_send_cmd_no_wait(pcr);
+	spin_unlock_irqrestore(&pcr->lock, flags);
+
+	return;
+
+out:
+	cmd->error = err;
+	tasklet_schedule(&host->finish_tasklet);
+}
+
+static void sd_get_rsp(unsigned long host_addr)
+{
+	struct realtek_pci_sdmmc *host = (struct realtek_pci_sdmmc *)host_addr;
+	struct rtsx_pcr *pcr = host->pcr;
+	struct mmc_command *cmd;
+	int i, err = 0, stat_idx;
+	u8 *ptr, rsp_type;
+	unsigned long flags;
+
+	spin_lock_irqsave(&host->lock, flags);
+
+	cmd = host->cmd;
+	host->cmd = NULL;
+
+	if (!cmd) {
+		dev_err(sdmmc_dev(host), "error: cmd not exist\n");
 		goto out;
 	}
 
+	spin_lock(&pcr->lock);
+	if (pcr->trans_result == TRANS_NO_DEVICE)
+		err = -ENODEV;
+	else if (pcr->trans_result != TRANS_RESULT_OK)
+		err = -EINVAL;
+	spin_unlock(&pcr->lock);
+
+	if (err < 0)
+		goto out;
+
+	rsp_type = host->rsp_type;
+	stat_idx = host->rsp_len;
+
 	if (rsp_type == SD_RSP_TYPE_R0) {
 		err = 0;
 		goto out;
@@ -340,26 +485,106 @@ static void sd_send_cmd_get_rsp(struct realtek_pci_sdmmc *host,
 				cmd->resp[0]);
 	}
 
+	if (cmd == host->mrq->sbc) {
+		sd_send_cmd(host, host->mrq->cmd);
+		spin_unlock_irqrestore(&host->lock, flags);
+		return;
+	}
+
+	if (cmd == host->mrq->stop)
+		goto out;
+
+	if (cmd->data) {
+		sd_start_multi_rw(host, host->mrq);
+		spin_unlock_irqrestore(&host->lock, flags);
+		return;
+	}
+
 out:
 	cmd->error = err;
 
-	if (err && clock_toggled)
-		rtsx_pci_write_register(pcr, SD_BUS_STAT,
-				SD_CLK_TOGGLE_EN | SD_CLK_FORCE_STOP, 0);
+	tasklet_schedule(&host->finish_tasklet);
+	spin_unlock_irqrestore(&host->lock, flags);
+}
+
+static int sd_pre_dma_transfer(struct realtek_pci_sdmmc *host,
+			struct mmc_data *data, struct realtek_next *next)
+{
+	struct rtsx_pcr *pcr = host->pcr;
+	int read = data->flags & MMC_DATA_READ;
+	int sg_count = 0;
+
+	if (!next && data->host_cookie &&
+		data->host_cookie != host->next_data.cookie) {
+		dev_err(sdmmc_dev(host),
+			"error: invalid cookie data[%d] host[%d]\n",
+			data->host_cookie, host->next_data.cookie);
+		data->host_cookie = 0;
+	}
+
+	if (next || (!next && data->host_cookie != host->next_data.cookie))
+		sg_count = rtsx_pci_dma_map_sg(pcr,
+				data->sg, data->sg_len, read);
+	else
+		sg_count = host->next_data.sg_count;
+
+	if (next) {
+		next->sg_count = sg_count;
+		if (++next->cookie < 0)
+			next->cookie = 1;
+		data->host_cookie = next->cookie;
+	}
+
+	return sg_count;
+}
+
+static void sdmmc_pre_req(struct mmc_host *mmc, struct mmc_request *mrq,
+		bool is_first_req)
+{
+	struct realtek_pci_sdmmc *host = mmc_priv(mmc);
+	struct mmc_data *data = mrq->data;
+
+	if (data->host_cookie) {
+		dev_err(sdmmc_dev(host),
+			"error: descard already cookie data[%d]\n",
+			data->host_cookie);
+		data->host_cookie = 0;
+	}
+
+	dev_dbg(sdmmc_dev(host), "dma sg prepared: %d\n",
+		sd_pre_dma_transfer(host, data, &host->next_data));
+}
+
+static void sdmmc_post_req(struct mmc_host *mmc, struct mmc_request *mrq,
+		int err)
+{
+	struct realtek_pci_sdmmc *host = mmc_priv(mmc);
+	struct rtsx_pcr *pcr = host->pcr;
+	struct mmc_data *data = mrq->data;
+	int read = data->flags & MMC_DATA_READ;
+
+	rtsx_pci_dma_unmap_sg(pcr, data->sg, data->sg_len, read);
+	data->host_cookie = 0;
 }
 
-static int sd_rw_multi(struct realtek_pci_sdmmc *host, struct mmc_request *mrq)
+static int sd_start_multi_rw(struct realtek_pci_sdmmc *host,
+		struct mmc_request *mrq)
 {
 	struct rtsx_pcr *pcr = host->pcr;
 	struct mmc_host *mmc = host->mmc;
 	struct mmc_card *card = mmc->card;
 	struct mmc_data *data = mrq->data;
 	int uhs = mmc_card_uhs(card);
-	int read = (data->flags & MMC_DATA_READ) ? 1 : 0;
+	int read = data->flags & MMC_DATA_READ;
 	u8 cfg2, trans_mode;
 	int err;
 	size_t data_len = data->blksz * data->blocks;
 
+	if (host->data)
+		dev_err(sdmmc_dev(host), "error: data already exist\n");
+
+	host->data = data;
+
 	if (read) {
 		cfg2 = SD_CALCULATE_CRC7 | SD_CHECK_CRC16 |
 			SD_NO_WAIT_BUSY_END | SD_CHECK_CRC7 | SD_RSP_LEN_0;
@@ -410,17 +635,56 @@ static int sd_rw_multi(struct realtek_pci_sdmmc *host, struct mmc_request *mrq)
 	rtsx_pci_add_cmd(pcr, CHECK_REG_CMD, SD_TRANSFER,
 			SD_TRANSFER_END, SD_TRANSFER_END);
 
+	mod_timer(&host->timer, jiffies + 10 * HZ);
 	rtsx_pci_send_cmd_no_wait(pcr);
 
-	err = rtsx_pci_transfer_data(pcr, data->sg, data->sg_len, read, 10000);
+	err = rtsx_pci_dma_transfer(pcr, data->sg, host->sg_count, read);
 	if (err < 0) {
-		sd_clear_error(host);
-		return err;
+		data->error = err;
+		tasklet_schedule(&host->finish_tasklet);
 	}
-
 	return 0;
 }
 
+static void sd_finish_multi_rw(unsigned long host_addr)
+{
+	struct realtek_pci_sdmmc *host = (struct realtek_pci_sdmmc *)host_addr;
+	struct rtsx_pcr *pcr = host->pcr;
+	struct mmc_data *data;
+	int err = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&host->lock, flags);
+
+	if (!host->data) {
+		dev_err(sdmmc_dev(host), "error: no data exist\n");
+		goto out;
+	}
+
+	data = host->data;
+	host->data = NULL;
+
+	if (pcr->trans_result == TRANS_NO_DEVICE)
+		err = -ENODEV;
+	else if (pcr->trans_result != TRANS_RESULT_OK)
+		err = -EINVAL;
+
+	if (err < 0) {
+		data->error = err;
+		goto out;
+	}
+
+	if (!host->mrq->sbc && data->stop) {
+		sd_send_cmd(host, data->stop);
+		spin_unlock_irqrestore(&host->lock, flags);
+		return;
+	}
+
+out:
+	tasklet_schedule(&host->finish_tasklet);
+	spin_unlock_irqrestore(&host->lock, flags);
+}
+
 static inline void sd_enable_initial_mode(struct realtek_pci_sdmmc *host)
 {
 	rtsx_pci_write_register(host->pcr, SD_CFG1,
@@ -637,6 +901,13 @@ static int sd_tuning_rx(struct realtek_pci_sdmmc *host, u8 opcode)
 	return 0;
 }
 
+static inline bool sd_use_muti_rw(struct mmc_command *cmd)
+{
+	return mmc_op_multi(cmd->opcode) ||
+		(cmd->opcode == MMC_READ_SINGLE_BLOCK) ||
+		(cmd->opcode == MMC_WRITE_BLOCK);
+}
+
 static void sdmmc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 {
 	struct realtek_pci_sdmmc *host = mmc_priv(mmc);
@@ -645,6 +916,14 @@ static void sdmmc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	struct mmc_data *data = mrq->data;
 	unsigned int data_size = 0;
 	int err;
+	unsigned long flags;
+
+	mutex_lock(&pcr->pcr_mutex);
+	spin_lock_irqsave(&host->lock, flags);
+
+	if (host->mrq)
+		dev_err(sdmmc_dev(host), "error: request already exist\n");
+	host->mrq = mrq;
 
 	if (host->eject) {
 		cmd->error = -ENOMEDIUM;
@@ -657,8 +936,6 @@ static void sdmmc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 		goto finish;
 	}
 
-	mutex_lock(&pcr->pcr_mutex);
-
 	rtsx_pci_start_run(pcr);
 
 	rtsx_pci_switch_clock(pcr, host->clock, host->ssc_depth,
@@ -667,46 +944,28 @@ static void sdmmc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	rtsx_pci_write_register(pcr, CARD_SHARE_MODE,
 			CARD_SHARE_MASK, CARD_SHARE_48_SD);
 
-	mutex_lock(&host->host_mutex);
-	host->mrq = mrq;
-	mutex_unlock(&host->host_mutex);
-
 	if (mrq->data)
 		data_size = data->blocks * data->blksz;
 
-	if (!data_size || mmc_op_multi(cmd->opcode) ||
-			(cmd->opcode == MMC_READ_SINGLE_BLOCK) ||
-			(cmd->opcode == MMC_WRITE_BLOCK)) {
-		sd_send_cmd_get_rsp(host, cmd);
-
-		if (!cmd->error && data_size) {
-			sd_rw_multi(host, mrq);
+	if (sd_use_muti_rw(cmd))
+		host->sg_count = sd_pre_dma_transfer(host, data, NULL);
 
-			if (mmc_op_multi(cmd->opcode) && mrq->stop)
-				sd_send_cmd_get_rsp(host, mrq->stop);
-		}
+	if (!data_size || sd_use_muti_rw(cmd)) {
+		if (mrq->sbc)
+			sd_send_cmd(host, mrq->sbc);
+		else
+			sd_send_cmd(host, cmd);
+		spin_unlock_irqrestore(&host->lock, flags);
 	} else {
+		spin_unlock_irqrestore(&host->lock, flags);
 		sd_normal_rw(host, mrq);
+		tasklet_schedule(&host->finish_tasklet);
 	}
-
-	if (mrq->data) {
-		if (cmd->error || data->error)
-			data->bytes_xfered = 0;
-		else
-			data->bytes_xfered = data->blocks * data->blksz;
-	}
-
-	mutex_unlock(&pcr->pcr_mutex);
+	return;
 
 finish:
-	if (cmd->error)
-		dev_dbg(sdmmc_dev(host), "cmd->error = %d\n", cmd->error);
-
-	mutex_lock(&host->host_mutex);
-	host->mrq = NULL;
-	mutex_unlock(&host->host_mutex);
-
-	mmc_request_done(mmc, mrq);
+	tasklet_schedule(&host->finish_tasklet);
+	spin_unlock_irqrestore(&host->lock, flags);
 }
 
 static int sd_set_bus_width(struct realtek_pci_sdmmc *host,
@@ -1141,6 +1400,8 @@ out:
 }
 
 static const struct mmc_host_ops realtek_pci_sdmmc_ops = {
+	.pre_req = sdmmc_pre_req,
+	.post_req = sdmmc_post_req,
 	.request = sdmmc_request,
 	.set_ios = sdmmc_set_ios,
 	.get_ro = sdmmc_get_ro,
@@ -1204,6 +1465,7 @@ static int rtsx_pci_sdmmc_drv_probe(struct platform_device *pdev)
 	struct realtek_pci_sdmmc *host;
 	struct rtsx_pcr *pcr;
 	struct pcr_handle *handle = pdev->dev.platform_data;
+	unsigned long host_addr;
 
 	if (!handle)
 		return -ENXIO;
@@ -1227,8 +1489,15 @@ static int rtsx_pci_sdmmc_drv_probe(struct platform_device *pdev)
 	pcr->slots[RTSX_SD_CARD].p_dev = pdev;
 	pcr->slots[RTSX_SD_CARD].card_event = rtsx_pci_sdmmc_card_event;
 
-	mutex_init(&host->host_mutex);
+	host_addr = (unsigned long)host;
+	host->next_data.cookie = 1;
+	setup_timer(&host->timer, sd_request_timeout, host_addr);
+	tasklet_init(&host->cmd_tasklet, sd_get_rsp, host_addr);
+	tasklet_init(&host->data_tasklet, sd_finish_multi_rw, host_addr);
+	tasklet_init(&host->finish_tasklet, sd_finish_request, host_addr);
+	spin_lock_init(&host->lock);
 
+	pcr->slots[RTSX_SD_CARD].done_transfer = sd_isr_done_transfer;
 	realtek_init_host(host);
 
 	mmc_add_host(mmc);
@@ -1241,6 +1510,8 @@ static int rtsx_pci_sdmmc_drv_remove(struct platform_device *pdev)
 	struct realtek_pci_sdmmc *host = platform_get_drvdata(pdev);
 	struct rtsx_pcr *pcr;
 	struct mmc_host *mmc;
+	struct mmc_request *mrq;
+	unsigned long flags;
 
 	if (!host)
 		return 0;
@@ -1248,22 +1519,33 @@ static int rtsx_pci_sdmmc_drv_remove(struct platform_device *pdev)
 	pcr = host->pcr;
 	pcr->slots[RTSX_SD_CARD].p_dev = NULL;
 	pcr->slots[RTSX_SD_CARD].card_event = NULL;
+	pcr->slots[RTSX_SD_CARD].done_transfer = NULL;
 	mmc = host->mmc;
+	mrq = host->mrq;
 
-	mutex_lock(&host->host_mutex);
+	spin_lock_irqsave(&host->lock, flags);
 	if (host->mrq) {
 		dev_dbg(&(pdev->dev),
 			"%s: Controller removed during transfer\n",
 			mmc_hostname(mmc));
 
-		rtsx_pci_complete_unfinished_transfer(pcr);
+		if (mrq->sbc)
+			mrq->sbc->error = -ENOMEDIUM;
+		if (mrq->cmd)
+			mrq->cmd->error = -ENOMEDIUM;
+		if (mrq->stop)
+			mrq->stop->error = -ENOMEDIUM;
+		if (mrq->data)
+			mrq->data->error = -ENOMEDIUM;
 
-		host->mrq->cmd->error = -ENOMEDIUM;
-		if (host->mrq->stop)
-			host->mrq->stop->error = -ENOMEDIUM;
-		mmc_request_done(mmc, host->mrq);
+		tasklet_schedule(&host->finish_tasklet);
 	}
-	mutex_unlock(&host->host_mutex);
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	del_timer_sync(&host->timer);
+	tasklet_kill(&host->cmd_tasklet);
+	tasklet_kill(&host->data_tasklet);
+	tasklet_kill(&host->finish_tasklet);
 
 	mmc_remove_host(mmc);
 	host->eject = true;
diff --git a/include/linux/mfd/rtsx_common.h b/include/linux/mfd/rtsx_common.h
index 443176ee1ab0..7c36cc55d2c7 100644
--- a/include/linux/mfd/rtsx_common.h
+++ b/include/linux/mfd/rtsx_common.h
@@ -45,6 +45,7 @@ struct platform_device;
 struct rtsx_slot {
 	struct platform_device	*p_dev;
 	void			(*card_event)(struct platform_device *p_dev);
+	void			(*done_transfer)(struct platform_device *p_dev);
 };
 
 #endif
diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h
index a3835976f7c6..8d6bbd609ad9 100644
--- a/include/linux/mfd/rtsx_pci.h
+++ b/include/linux/mfd/rtsx_pci.h
@@ -943,6 +943,12 @@ void rtsx_pci_send_cmd_no_wait(struct rtsx_pcr *pcr);
 int rtsx_pci_send_cmd(struct rtsx_pcr *pcr, int timeout);
 int rtsx_pci_transfer_data(struct rtsx_pcr *pcr, struct scatterlist *sglist,
 		int num_sg, bool read, int timeout);
+int rtsx_pci_dma_map_sg(struct rtsx_pcr *pcr, struct scatterlist *sglist,
+		int num_sg, bool read);
+int rtsx_pci_dma_unmap_sg(struct rtsx_pcr *pcr, struct scatterlist *sglist,
+		int num_sg, bool read);
+int rtsx_pci_dma_transfer(struct rtsx_pcr *pcr, struct scatterlist *sglist,
+		int sg_count, bool read);
 int rtsx_pci_read_ppbuf(struct rtsx_pcr *pcr, u8 *buf, int buf_len);
 int rtsx_pci_write_ppbuf(struct rtsx_pcr *pcr, u8 *buf, int buf_len);
 int rtsx_pci_card_pull_ctl_enable(struct rtsx_pcr *pcr, int card);
-- 
cgit v1.2.3


From 67f5185cad24b3c3d9ab07508dfcab55cdab02de Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@ti.com>
Date: Thu, 30 Jan 2014 13:03:40 +0200
Subject: ARM: davinci: aemif: get rid of davinci-nand driver dependency on
 aemif

The problem that the set timings code contains the call of Davinci
platform function davinci_aemif_setup_timing() which is not
accessible if kernel is built for another platform like Keystone.

The Keysone platform is going to use TI AEMIF driver.
If TI AEMIF is used we don't need to set timings and bus width.
It is done by AEMIF driver.

To get rid of davinci-nand driver dependency on aemif platform code
we moved aemif code to davinci platform.

The platform AEMIF code (aemif.c) has to be removed once Davinci
will be converted to DT and use ti-aemif.c driver.

Acked-by: Brian Norris <computersforpeace@gmail.com>
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@ti.com>
[nsekhar@ti.com: fixed checkpatch error and a build breakage due to
		 missing include, rebased onto l2-mtd/master]
Signed-off-by: Sekhar Nori <nsekhar@ti.com>
---
 arch/arm/mach-davinci/aemif.c                   | 107 +++++++++++++++++++++---
 arch/arm/mach-davinci/board-da830-evm.c         |   3 +
 arch/arm/mach-davinci/board-da850-evm.c         |   3 +
 arch/arm/mach-davinci/board-dm644x-evm.c        |   5 ++
 arch/arm/mach-davinci/board-dm646x-evm.c        |   3 +
 arch/arm/mach-davinci/board-mityomapl138.c      |   4 +
 drivers/mtd/nand/davinci_nand.c                 |  22 -----
 include/linux/platform_data/mtd-davinci-aemif.h |   5 +-
 8 files changed, 117 insertions(+), 35 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-davinci/aemif.c b/arch/arm/mach-davinci/aemif.c
index f091a9010c2f..ff8b7e76b6e9 100644
--- a/arch/arm/mach-davinci/aemif.c
+++ b/arch/arm/mach-davinci/aemif.c
@@ -16,6 +16,7 @@
 #include <linux/time.h>
 
 #include <linux/platform_data/mtd-davinci-aemif.h>
+#include <linux/platform_data/mtd-davinci.h>
 
 /* Timing value configuration */
 
@@ -43,6 +44,17 @@
 				WSTROBE(WSTROBE_MAX) | \
 				WSETUP(WSETUP_MAX))
 
+static inline unsigned int davinci_aemif_readl(void __iomem *base, int offset)
+{
+	return readl_relaxed(base + offset);
+}
+
+static inline void davinci_aemif_writel(void __iomem *base,
+					int offset, unsigned long value)
+{
+	writel_relaxed(value, base + offset);
+}
+
 /*
  * aemif_calc_rate - calculate timing data.
  * @wanted: The cycle time needed in nanoseconds.
@@ -76,6 +88,7 @@ static int aemif_calc_rate(int wanted, unsigned long clk, int max)
  * @t: timing values to be progammed
  * @base: The virtual base address of the AEMIF interface
  * @cs: chip-select to program the timing values for
+ * @clkrate: the AEMIF clkrate
  *
  * This function programs the given timing values (in real clock) into the
  * AEMIF registers taking the AEMIF clock into account.
@@ -86,24 +99,17 @@ static int aemif_calc_rate(int wanted, unsigned long clk, int max)
  *
  * Returns 0 on success, else negative errno.
  */
-int davinci_aemif_setup_timing(struct davinci_aemif_timing *t,
-					void __iomem *base, unsigned cs)
+static int davinci_aemif_setup_timing(struct davinci_aemif_timing *t,
+					void __iomem *base, unsigned cs,
+					unsigned long clkrate)
 {
 	unsigned set, val;
 	int ta, rhold, rstrobe, rsetup, whold, wstrobe, wsetup;
 	unsigned offset = A1CR_OFFSET + cs * 4;
-	struct clk *aemif_clk;
-	unsigned long clkrate;
 
 	if (!t)
 		return 0;	/* Nothing to do */
 
-	aemif_clk = clk_get(NULL, "aemif");
-	if (IS_ERR(aemif_clk))
-		return PTR_ERR(aemif_clk);
-
-	clkrate = clk_get_rate(aemif_clk);
-
 	clkrate /= 1000;	/* turn clock into kHz for ease of use */
 
 	ta	= aemif_calc_rate(t->ta, clkrate, TA_MAX);
@@ -130,4 +136,83 @@ int davinci_aemif_setup_timing(struct davinci_aemif_timing *t,
 
 	return 0;
 }
-EXPORT_SYMBOL(davinci_aemif_setup_timing);
+
+/**
+ * davinci_aemif_setup - setup AEMIF interface by davinci_nand_pdata
+ * @pdev - link to platform device to setup settings for
+ *
+ * This function does not use any locking while programming the AEMIF
+ * because it is expected that there is only one user of a given
+ * chip-select.
+ *
+ * Returns 0 on success, else negative errno.
+ */
+int davinci_aemif_setup(struct platform_device *pdev)
+{
+	struct davinci_nand_pdata *pdata = dev_get_platdata(&pdev->dev);
+	uint32_t val;
+	unsigned long clkrate;
+	struct resource	*res;
+	void __iomem *base;
+	struct clk *clk;
+	int ret = 0;
+
+	clk = clk_get(&pdev->dev, "aemif");
+	if (IS_ERR(clk)) {
+		ret = PTR_ERR(clk);
+		dev_dbg(&pdev->dev, "unable to get AEMIF clock, err %d\n", ret);
+		return ret;
+	}
+
+	ret = clk_prepare_enable(clk);
+	if (ret < 0) {
+		dev_dbg(&pdev->dev, "unable to enable AEMIF clock, err %d\n",
+			ret);
+		goto err_put;
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	if (!res) {
+		dev_err(&pdev->dev, "cannot get IORESOURCE_MEM\n");
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	base = ioremap(res->start, resource_size(res));
+	if (!base) {
+		dev_err(&pdev->dev, "ioremap failed for resource %pR\n", res);
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	/*
+	 * Setup Async configuration register in case we did not boot
+	 * from NAND and so bootloader did not bother to set it up.
+	 */
+	val = davinci_aemif_readl(base, A1CR_OFFSET + pdev->id * 4);
+	/*
+	 * Extended Wait is not valid and Select Strobe mode is not
+	 * used
+	 */
+	val &= ~(ACR_ASIZE_MASK | ACR_EW_MASK | ACR_SS_MASK);
+	if (pdata->options & NAND_BUSWIDTH_16)
+		val |= 0x1;
+
+	davinci_aemif_writel(base, A1CR_OFFSET + pdev->id * 4, val);
+
+	clkrate = clk_get_rate(clk);
+
+	if (pdata->timing)
+		ret = davinci_aemif_setup_timing(pdata->timing, base, pdev->id,
+						 clkrate);
+
+	if (ret < 0)
+		dev_dbg(&pdev->dev, "NAND timing values setup fail\n");
+
+	iounmap(base);
+err:
+	clk_disable_unprepare(clk);
+err_put:
+	clk_put(clk);
+	return ret;
+}
diff --git a/arch/arm/mach-davinci/board-da830-evm.c b/arch/arm/mach-davinci/board-da830-evm.c
index d1f45af7a530..5623131c4f0b 100644
--- a/arch/arm/mach-davinci/board-da830-evm.c
+++ b/arch/arm/mach-davinci/board-da830-evm.c
@@ -419,6 +419,9 @@ static inline void da830_evm_init_nand(int mux_mode)
 	if (ret)
 		pr_warning("da830_evm_init: NAND device not registered.\n");
 
+	if (davinci_aemif_setup(&da830_evm_nand_device))
+		pr_warn("%s: Cannot configure AEMIF.\n", __func__);
+
 	gpio_direction_output(mux_mode, 1);
 }
 #else
diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c
index e0af0eccde8f..234c5bb091f5 100644
--- a/arch/arm/mach-davinci/board-da850-evm.c
+++ b/arch/arm/mach-davinci/board-da850-evm.c
@@ -358,6 +358,9 @@ static inline void da850_evm_setup_nor_nand(void)
 
 		platform_add_devices(da850_evm_devices,
 					ARRAY_SIZE(da850_evm_devices));
+
+		if (davinci_aemif_setup(&da850_evm_nandflash_device))
+			pr_warn("%s: Cannot configure AEMIF.\n", __func__);
 	}
 }
 
diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c
index 987605b78556..5602957b67d7 100644
--- a/arch/arm/mach-davinci/board-dm644x-evm.c
+++ b/arch/arm/mach-davinci/board-dm644x-evm.c
@@ -778,6 +778,11 @@ static __init void davinci_evm_init(void)
 		/* only one device will be jumpered and detected */
 		if (HAS_NAND) {
 			platform_device_register(&davinci_evm_nandflash_device);
+
+			if (davinci_aemif_setup(&davinci_evm_nandflash_device))
+				pr_warn("%s: Cannot configure AEMIF.\n",
+					__func__);
+
 			evm_leds[7].default_trigger = "nand-disk";
 			if (HAS_NOR)
 				pr_warning("WARNING: both NAND and NOR flash "
diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c
index 13d0801fd6b1..ae129bc49273 100644
--- a/arch/arm/mach-davinci/board-dm646x-evm.c
+++ b/arch/arm/mach-davinci/board-dm646x-evm.c
@@ -805,6 +805,9 @@ static __init void evm_init(void)
 
 	platform_device_register(&davinci_nand_device);
 
+	if (davinci_aemif_setup(&davinci_nand_device))
+		pr_warn("%s: Cannot configure AEMIF.\n", __func__);
+
 	dm646x_init_edma(dm646x_edma_rsv);
 
 	if (HAS_ATA)
diff --git a/arch/arm/mach-davinci/board-mityomapl138.c b/arch/arm/mach-davinci/board-mityomapl138.c
index 7aa105b1fd0f..96fc00a167f5 100644
--- a/arch/arm/mach-davinci/board-mityomapl138.c
+++ b/arch/arm/mach-davinci/board-mityomapl138.c
@@ -27,6 +27,7 @@
 #include <mach/cp_intc.h>
 #include <mach/da8xx.h>
 #include <linux/platform_data/mtd-davinci.h>
+#include <linux/platform_data/mtd-davinci-aemif.h>
 #include <mach/mux.h>
 #include <linux/platform_data/spi-davinci.h>
 
@@ -432,6 +433,9 @@ static void __init mityomapl138_setup_nand(void)
 {
 	platform_add_devices(mityomapl138_devices,
 				 ARRAY_SIZE(mityomapl138_devices));
+
+	if (davinci_aemif_setup(&mityomapl138_nandflash_device))
+		pr_warn("%s: Cannot configure AEMIF.\n", __func__);
 }
 
 static const short mityomap_mii_pins[] = {
diff --git a/drivers/mtd/nand/davinci_nand.c b/drivers/mtd/nand/davinci_nand.c
index a4989ec6292e..8eb6a36f125a 100644
--- a/drivers/mtd/nand/davinci_nand.c
+++ b/drivers/mtd/nand/davinci_nand.c
@@ -746,28 +746,6 @@ static int nand_davinci_probe(struct platform_device *pdev)
 		goto err_clk_enable;
 	}
 
-	/*
-	 * Setup Async configuration register in case we did not boot from
-	 * NAND and so bootloader did not bother to set it up.
-	 */
-	val = davinci_nand_readl(info, A1CR_OFFSET + info->core_chipsel * 4);
-
-	/* Extended Wait is not valid and Select Strobe mode is not used */
-	val &= ~(ACR_ASIZE_MASK | ACR_EW_MASK | ACR_SS_MASK);
-	if (info->chip.options & NAND_BUSWIDTH_16)
-		val |= 0x1;
-
-	davinci_nand_writel(info, A1CR_OFFSET + info->core_chipsel * 4, val);
-
-	ret = 0;
-	if (info->timing)
-		ret = davinci_aemif_setup_timing(info->timing, info->base,
-							info->core_chipsel);
-	if (ret < 0) {
-		dev_dbg(&pdev->dev, "NAND timing values setup fail\n");
-		goto err;
-	}
-
 	spin_lock_irq(&davinci_nand_lock);
 
 	/* put CSxNAND into NAND mode */
diff --git a/include/linux/platform_data/mtd-davinci-aemif.h b/include/linux/platform_data/mtd-davinci-aemif.h
index 05b293443097..97948ac2bb9b 100644
--- a/include/linux/platform_data/mtd-davinci-aemif.h
+++ b/include/linux/platform_data/mtd-davinci-aemif.h
@@ -10,6 +10,8 @@
 #ifndef _MACH_DAVINCI_AEMIF_H
 #define _MACH_DAVINCI_AEMIF_H
 
+#include <linux/platform_device.h>
+
 #define NRCSR_OFFSET		0x00
 #define AWCCR_OFFSET		0x04
 #define A1CR_OFFSET		0x10
@@ -31,6 +33,5 @@ struct davinci_aemif_timing {
 	u8	ta;
 };
 
-int davinci_aemif_setup_timing(struct davinci_aemif_timing *t,
-					void __iomem *base, unsigned cs);
+int davinci_aemif_setup(struct platform_device *pdev);
 #endif
-- 
cgit v1.2.3


From 68eb80e06bfa06035d0304686124974780308fae Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Wed, 18 Dec 2013 09:57:38 +0100
Subject: mmc: core: Rename max_discard_to to max_busy_timeout

Rename host->max_discard_to to host->max_busy_timeout, to reflect that
it tells the mmc core layer about the maximum supported busy detection
timeout by the host.

This timeout is at the moment only applicable to erase/trim/discard
commands. By the renaming we provide the option of make use of it for
other commands that cares about busy detection. In other words, those
commands that wants an R1B response, like for example the mmc switch
command.

Do note that the max_busy_timeout is supposed to be specified only by
hosts supporting MMC_CAP_WAIT_WHILE_BUSY.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Chris Ball <chris@printf.net>
---
 drivers/mmc/core/core.c  | 6 +++---
 drivers/mmc/host/sdhci.c | 2 +-
 include/linux/mmc/host.h | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index f5a068d55c36..d9c1efa2ce15 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -2120,7 +2120,7 @@ static unsigned int mmc_do_calc_max_discard(struct mmc_card *card,
 		y = 0;
 		for (x = 1; x && x <= max_qty && max_qty - x >= qty; x <<= 1) {
 			timeout = mmc_erase_timeout(card, arg, qty + x);
-			if (timeout > host->max_discard_to)
+			if (timeout > host->max_busy_timeout)
 				break;
 			if (timeout < last_timeout)
 				break;
@@ -2152,7 +2152,7 @@ unsigned int mmc_calc_max_discard(struct mmc_card *card)
 	struct mmc_host *host = card->host;
 	unsigned int max_discard, max_trim;
 
-	if (!host->max_discard_to)
+	if (!host->max_busy_timeout)
 		return UINT_MAX;
 
 	/*
@@ -2172,7 +2172,7 @@ unsigned int mmc_calc_max_discard(struct mmc_card *card)
 		max_discard = 0;
 	}
 	pr_debug("%s: calculated max. discard sectors %u for timeout %u ms\n",
-		 mmc_hostname(host), max_discard, host->max_discard_to);
+		 mmc_hostname(host), max_discard, host->max_busy_timeout);
 	return max_discard;
 }
 EXPORT_SYMBOL(mmc_calc_max_discard);
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 8958edc03e04..d1e1bf52fe52 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -2941,7 +2941,7 @@ int sdhci_add_host(struct sdhci_host *host)
 	if (host->quirks & SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK)
 		host->timeout_clk = mmc->f_max / 1000;
 
-	mmc->max_discard_to = (1 << 27) / host->timeout_clk;
+	mmc->max_busy_timeout = (1 << 27) / host->timeout_clk;
 
 	mmc->caps |= MMC_CAP_SDIO_IRQ | MMC_CAP_ERASE | MMC_CAP_CMD23;
 
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 719db89ef134..cb61ea4d6945 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -300,7 +300,7 @@ struct mmc_host {
 	unsigned int		max_req_size;	/* maximum number of bytes in one req */
 	unsigned int		max_blk_size;	/* maximum size of one mmc block */
 	unsigned int		max_blk_count;	/* maximum number of blocks in one req */
-	unsigned int		max_discard_to;	/* max. discard timeout in ms */
+	unsigned int		max_busy_timeout; /* max busy timeout in ms */
 
 	/* private data */
 	spinlock_t		lock;		/* lock for claim and bus ops */
-- 
cgit v1.2.3


From 1d4d77444bf4212c44585146a2b353ca24c815f9 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Wed, 8 Jan 2014 15:06:08 +0100
Subject: mmc: core: Rename cmd_timeout_ms to busy_timeout

To better reflect that the cmd_timeout_ms is directly related to the
busy detection timeout, let's rename it.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Chris Ball <chris@printf.net>
---
 drivers/mmc/core/core.c    | 2 +-
 drivers/mmc/core/mmc_ops.c | 2 +-
 drivers/mmc/host/sdhci.c   | 8 ++++----
 include/linux/mmc/core.h   | 2 +-
 4 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index d9c1efa2ce15..1935812e4215 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -1933,7 +1933,7 @@ static int mmc_do_erase(struct mmc_card *card, unsigned int from,
 	cmd.opcode = MMC_ERASE;
 	cmd.arg = arg;
 	cmd.flags = MMC_RSP_SPI_R1B | MMC_RSP_R1B | MMC_CMD_AC;
-	cmd.cmd_timeout_ms = mmc_erase_timeout(card, arg, qty);
+	cmd.busy_timeout = mmc_erase_timeout(card, arg, qty);
 	err = mmc_wait_for_cmd(card->host, &cmd, 0);
 	if (err) {
 		pr_err("mmc_erase: erase error %d, status %#x\n",
diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index e5b5eeb548d1..3377bbfc3585 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -432,7 +432,7 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 		cmd.flags |= MMC_RSP_SPI_R1 | MMC_RSP_R1;
 
 
-	cmd.cmd_timeout_ms = timeout_ms;
+	cmd.busy_timeout = timeout_ms;
 	if (index == EXT_CSD_SANITIZE_START)
 		cmd.sanitize_busy = true;
 
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index d1e1bf52fe52..7f95211e9449 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -675,12 +675,12 @@ static u8 sdhci_calc_timeout(struct sdhci_host *host, struct mmc_command *cmd)
 		return 0xE;
 
 	/* Unspecified timeout, assume max */
-	if (!data && !cmd->cmd_timeout_ms)
+	if (!data && !cmd->busy_timeout)
 		return 0xE;
 
 	/* timeout in us */
 	if (!data)
-		target_timeout = cmd->cmd_timeout_ms * 1000;
+		target_timeout = cmd->busy_timeout * 1000;
 	else {
 		target_timeout = data->timeout_ns / 1000;
 		if (host->clock)
@@ -1019,8 +1019,8 @@ void sdhci_send_command(struct sdhci_host *host, struct mmc_command *cmd)
 	}
 
 	timeout = jiffies;
-	if (!cmd->data && cmd->cmd_timeout_ms > 9000)
-		timeout += DIV_ROUND_UP(cmd->cmd_timeout_ms, 1000) * HZ + HZ;
+	if (!cmd->data && cmd->busy_timeout > 9000)
+		timeout += DIV_ROUND_UP(cmd->busy_timeout, 1000) * HZ + HZ;
 	else
 		timeout += 10 * HZ;
 	mod_timer(&host->timer, timeout);
diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h
index 87079fc38011..b27699612888 100644
--- a/include/linux/mmc/core.h
+++ b/include/linux/mmc/core.h
@@ -95,7 +95,7 @@ struct mmc_command {
  *              actively failing requests
  */
 
-	unsigned int		cmd_timeout_ms;	/* in milliseconds */
+	unsigned int		busy_timeout;	/* busy detect timeout in ms */
 	/* Set this flag only for blocking sanitize request */
 	bool			sanitize_busy;
 
-- 
cgit v1.2.3


From 4509f847751c9d2a724f37fe831393fbac34b80f Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Wed, 8 Jan 2014 16:09:33 +0100
Subject: mmc: core: Add ignore_crc flag to __mmc_switch

Instead of handle specific adaptations, releated to certain switch
operations, inside __mmc_switch, push this to be handled by the caller
instead.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Chris Ball <chris@printf.net>
---
 drivers/mmc/core/core.c    |  3 ++-
 drivers/mmc/core/mmc.c     | 13 +++++++------
 drivers/mmc/core/mmc_ops.c | 19 ++++++++++---------
 include/linux/mmc/core.h   |  2 +-
 4 files changed, 20 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 1935812e4215..dc7a5fb81a5c 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -285,7 +285,8 @@ void mmc_start_bkops(struct mmc_card *card, bool from_exception)
 	}
 
 	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-			EXT_CSD_BKOPS_START, 1, timeout, use_busy_signal, true);
+			EXT_CSD_BKOPS_START, 1, timeout,
+			use_busy_signal, true, false);
 	if (err) {
 		pr_warn("%s: Error %d starting bkops\n",
 			mmc_hostname(card->host), err);
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 072171183d5b..c944692f3c4e 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -856,8 +856,8 @@ static int mmc_select_hs200(struct mmc_card *card)
 
 	/* switch to HS200 mode if bus width set successfully */
 	if (!err)
-		err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-				 EXT_CSD_HS_TIMING, 2, 0);
+		err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
+				EXT_CSD_HS_TIMING, 2, 0, true, true, true);
 err:
 	return err;
 }
@@ -1074,9 +1074,10 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 		    host->caps2 & MMC_CAP2_HS200)
 			err = mmc_select_hs200(card);
 		else if	(host->caps & MMC_CAP_MMC_HIGHSPEED)
-			err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-					 EXT_CSD_HS_TIMING, 1,
-					 card->ext_csd.generic_cmd6_time);
+			err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
+					EXT_CSD_HS_TIMING, 1,
+					card->ext_csd.generic_cmd6_time,
+					true, true, true);
 
 		if (err && err != -EBADMSG)
 			goto free_card;
@@ -1400,7 +1401,7 @@ static int mmc_poweroff_notify(struct mmc_card *card, unsigned int notify_type)
 
 	err = __mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
 			EXT_CSD_POWER_OFF_NOTIFICATION,
-			notify_type, timeout, true, false);
+			notify_type, timeout, true, false, false);
 	if (err)
 		pr_err("%s: Power Off Notification timed out, %u\n",
 		       mmc_hostname(card->host), timeout);
diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index 3377bbfc3585..5e1a2cbdc229 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -405,17 +405,18 @@ int mmc_spi_set_crc(struct mmc_host *host, int use_crc)
  *                   timeout of zero implies maximum possible timeout
  *	@use_busy_signal: use the busy signal as response type
  *	@send_status: send status cmd to poll for busy
+ *	@ignore_crc: ignore CRC errors when sending status cmd to poll for busy
  *
  *	Modifies the EXT_CSD register for selected card.
  */
 int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
-		unsigned int timeout_ms, bool use_busy_signal, bool send_status)
+		unsigned int timeout_ms, bool use_busy_signal, bool send_status,
+		bool ignore_crc)
 {
 	int err;
 	struct mmc_command cmd = {0};
 	unsigned long timeout;
 	u32 status = 0;
-	bool ignore_crc = false;
 
 	BUG_ON(!card);
 	BUG_ON(!card->host);
@@ -445,14 +446,13 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 		return 0;
 
 	/*
-	 * Must check status to be sure of no errors
-	 * If CMD13 is to check the busy completion of the timing change,
-	 * disable the check of CRC error.
+	 * CRC errors shall only be ignored in cases were CMD13 is used to poll
+	 * to detect busy completion.
 	 */
-	if (index == EXT_CSD_HS_TIMING &&
-	    !(card->host->caps & MMC_CAP_WAIT_WHILE_BUSY))
-		ignore_crc = true;
+	if (card->host->caps & MMC_CAP_WAIT_WHILE_BUSY)
+		ignore_crc = false;
 
+	/* Must check status to be sure of no errors. */
 	timeout = jiffies + msecs_to_jiffies(MMC_OPS_TIMEOUT_MS);
 	do {
 		if (send_status) {
@@ -501,7 +501,8 @@ EXPORT_SYMBOL_GPL(__mmc_switch);
 int mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 		unsigned int timeout_ms)
 {
-	return __mmc_switch(card, set, index, value, timeout_ms, true, true);
+	return __mmc_switch(card, set, index, value, timeout_ms, true, true,
+				false);
 }
 EXPORT_SYMBOL_GPL(mmc_switch);
 
diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h
index b27699612888..f206e29f94d7 100644
--- a/include/linux/mmc/core.h
+++ b/include/linux/mmc/core.h
@@ -152,7 +152,7 @@ extern int mmc_wait_for_app_cmd(struct mmc_host *, struct mmc_card *,
 	struct mmc_command *, int);
 extern void mmc_start_bkops(struct mmc_card *card, bool from_exception);
 extern int __mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int, bool,
-			bool);
+			bool, bool);
 extern int mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int);
 extern int mmc_send_ext_csd(struct mmc_card *card, u8 *ext_csd);
 
-- 
cgit v1.2.3


From 3c86726cfe38952f0366f86acfbbb025813ec1c2 Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Date: Thu, 20 Feb 2014 15:24:49 -0500
Subject: HID: make .raw_request mandatory

SET_REPORT and GET_REPORT are mandatory in the HID specification.
Make the corresponding API in hid-core mandatory too, which removes the
need to test against it in some various places.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Reviewed-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 Documentation/hid/hid-transport.txt |  3 ++-
 drivers/hid/hid-core.c              | 11 ++++++++---
 drivers/hid/hid-input.c             |  4 +---
 include/linux/hid.h                 |  5 +----
 4 files changed, 12 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/hid/hid-transport.txt b/Documentation/hid/hid-transport.txt
index 9dbbceaef4f3..3dcba9fd4a3a 100644
--- a/Documentation/hid/hid-transport.txt
+++ b/Documentation/hid/hid-transport.txt
@@ -283,7 +283,8 @@ The available HID callbacks are:
                        int reqtype)
    Same as ->request() but provides the report as raw buffer. This request shall
    be synchronous. A transport driver must not use ->wait() to complete such
-   requests.
+   requests. This request is mandatory and hid core will reject the device if
+   it is missing.
 
  - int (*output_report) (struct hid_device *hdev, __u8 *buf, size_t len)
    Send raw output report via intr channel. Used by some HID device drivers
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index b6ae69711d2a..0b57babe3f9f 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1330,9 +1330,6 @@ void __hid_request(struct hid_device *hid, struct hid_report *report,
 	int ret;
 	int len;
 
-	if (!hid->ll_driver->raw_request)
-		return;
-
 	buf = hid_alloc_report_buf(report, GFP_KERNEL);
 	if (!buf)
 		return;
@@ -2471,6 +2468,14 @@ int hid_add_device(struct hid_device *hdev)
 	if (hid_ignore(hdev))
 		return -ENODEV;
 
+	/*
+	 * Check for the mandatory transport channel.
+	 */
+	 if (!hdev->ll_driver->raw_request) {
+		hid_err(hdev, "transport driver missing .raw_request()\n");
+		return -EINVAL;
+	 }
+
 	/*
 	 * Read the device report descriptor once and use as template
 	 * for the driver-specific modifications.
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 310b96779e8e..f5aef792f13b 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -1266,9 +1266,7 @@ static struct hid_input *hidinput_allocate(struct hid_device *hid)
 	}
 
 	input_set_drvdata(input_dev, hid);
-	if (hid->ll_driver->request || hid->ll_driver->output_report ||
-	    hid->ll_driver->raw_request)
-		input_dev->event = hidinput_input_event;
+	input_dev->event = hidinput_input_event;
 	input_dev->open = hidinput_open;
 	input_dev->close = hidinput_close;
 	input_dev->setkeycode = hidinput_setkeycode;
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 60f3ff762376..5eb282e0dff7 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -992,11 +992,8 @@ static inline int hid_hw_raw_request(struct hid_device *hdev,
 	if (len < 1 || len > HID_MAX_BUFFER_SIZE || !buf)
 		return -EINVAL;
 
-	if (hdev->ll_driver->raw_request)
-		return hdev->ll_driver->raw_request(hdev, reportnum, buf, len,
+	return hdev->ll_driver->raw_request(hdev, reportnum, buf, len,
 						    rtype, reqtype);
-
-	return -ENOSYS;
 }
 
 /**
-- 
cgit v1.2.3


From 8b4922d3173d2eee7b43be8e5caec3ab7d30feff Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Mon, 24 Feb 2014 16:39:52 +0100
Subject: block: Stop abusing csd.list for fifo_time

Block layer currently abuses rq->csd.list.next for storing fifo_time.
That is a terrible hack and completely unnecessary as well. Union
achieves the same space saving in a cleaner way.

Signed-off-by: Jan Kara <jack@suse.cz>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jens Axboe <axboe@fb.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/cfq-iosched.c      | 8 ++++----
 block/deadline-iosched.c | 8 ++++----
 include/linux/blkdev.h   | 1 +
 include/linux/elevator.h | 6 ------
 4 files changed, 9 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 744833b630c6..5873e4ada9eb 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -2367,10 +2367,10 @@ cfq_merged_requests(struct request_queue *q, struct request *rq,
 	 * reposition in fifo if next is older than rq
 	 */
 	if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
-	    time_before(rq_fifo_time(next), rq_fifo_time(rq)) &&
+	    time_before(next->fifo_time, rq->fifo_time) &&
 	    cfqq == RQ_CFQQ(next)) {
 		list_move(&rq->queuelist, &next->queuelist);
-		rq_set_fifo_time(rq, rq_fifo_time(next));
+		rq->fifo_time = next->fifo_time;
 	}
 
 	if (cfqq->next_rq == next)
@@ -2814,7 +2814,7 @@ static struct request *cfq_check_fifo(struct cfq_queue *cfqq)
 		return NULL;
 
 	rq = rq_entry_fifo(cfqq->fifo.next);
-	if (time_before(jiffies, rq_fifo_time(rq)))
+	if (time_before(jiffies, rq->fifo_time))
 		rq = NULL;
 
 	cfq_log_cfqq(cfqq->cfqd, cfqq, "fifo=%p", rq);
@@ -3927,7 +3927,7 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq)
 	cfq_log_cfqq(cfqd, cfqq, "insert_request");
 	cfq_init_prio_data(cfqq, RQ_CIC(rq));
 
-	rq_set_fifo_time(rq, jiffies + cfqd->cfq_fifo_expire[rq_is_sync(rq)]);
+	rq->fifo_time = jiffies + cfqd->cfq_fifo_expire[rq_is_sync(rq)];
 	list_add_tail(&rq->queuelist, &cfqq->fifo);
 	cfq_add_rq_rb(rq);
 	cfqg_stats_update_io_add(RQ_CFQG(rq), cfqd->serving_group,
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index 9ef66406c625..a753df2b3fc2 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -106,7 +106,7 @@ deadline_add_request(struct request_queue *q, struct request *rq)
 	/*
 	 * set expire time and add to fifo list
 	 */
-	rq_set_fifo_time(rq, jiffies + dd->fifo_expire[data_dir]);
+	rq->fifo_time = jiffies + dd->fifo_expire[data_dir];
 	list_add_tail(&rq->queuelist, &dd->fifo_list[data_dir]);
 }
 
@@ -174,9 +174,9 @@ deadline_merged_requests(struct request_queue *q, struct request *req,
 	 * and move into next position (next will be deleted) in fifo
 	 */
 	if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) {
-		if (time_before(rq_fifo_time(next), rq_fifo_time(req))) {
+		if (time_before(next->fifo_time, req->fifo_time)) {
 			list_move(&req->queuelist, &next->queuelist);
-			rq_set_fifo_time(req, rq_fifo_time(next));
+			req->fifo_time = next->fifo_time;
 		}
 	}
 
@@ -230,7 +230,7 @@ static inline int deadline_check_fifo(struct deadline_data *dd, int ddir)
 	/*
 	 * rq is expired!
 	 */
-	if (time_after_eq(jiffies, rq_fifo_time(rq)))
+	if (time_after_eq(jiffies, rq->fifo_time))
 		return 1;
 
 	return 0;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 4afa4f8f6090..1e1fa3f93d5f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -99,6 +99,7 @@ struct request {
 	union {
 		struct call_single_data csd;
 		struct work_struct mq_flush_work;
+		unsigned long fifo_time;
 	};
 
 	struct request_queue *q;
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 306dd8cd0b6f..0bdfd46f4735 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -202,12 +202,6 @@ enum {
 #define rq_end_sector(rq)	(blk_rq_pos(rq) + blk_rq_sectors(rq))
 #define rb_entry_rq(node)	rb_entry((node), struct request, rb_node)
 
-/*
- * Hack to reuse the csd.list list_head as the fifo time holder while
- * the request is in the io scheduler. Saves an unsigned long in rq.
- */
-#define rq_fifo_time(rq)	((unsigned long) (rq)->csd.list.next)
-#define rq_set_fifo_time(rq,exp)	((rq)->csd.list.next = (void *) (exp))
 #define rq_entry_fifo(ptr)	list_entry((ptr), struct request, queuelist)
 #define rq_fifo_clear(rq)	do {		\
 	list_del_init(&(rq)->queuelist);	\
-- 
cgit v1.2.3


From d9a74df512e44580a34bf6e70f5d08c126507354 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Mon, 24 Feb 2014 16:39:53 +0100
Subject: block: Remove useless IPI struct initialization

rq_fifo_clear() reset the csd.list through INIT_LIST_HEAD for no clear
purpose. The csd.list doesn't need to be initialized as a list head
because it's only ever used as a list node.

Lets remove this useless initialization.

Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <axboe@fb.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 include/linux/elevator.h | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 0bdfd46f4735..df63bd3a8cf1 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -203,10 +203,7 @@ enum {
 #define rb_entry_rq(node)	rb_entry((node), struct request, rb_node)
 
 #define rq_entry_fifo(ptr)	list_entry((ptr), struct request, queuelist)
-#define rq_fifo_clear(rq)	do {		\
-	list_del_init(&(rq)->queuelist);	\
-	INIT_LIST_HEAD(&(rq)->csd.list);	\
-	} while (0)
+#define rq_fifo_clear(rq)	list_del_init(&(rq)->queuelist)
 
 #else /* CONFIG_BLOCK */
 
-- 
cgit v1.2.3


From 0ebeb79ce920bed3a4a55113534951d95a444fbb Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Mon, 24 Feb 2014 16:39:56 +0100
Subject: smp: Remove unused list_head from csd

Now that we got rid of all the remaining code which fiddled with csd.list,
lets remove it.

Signed-off-by: Jan Kara <jack@suse.cz>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jens Axboe <axboe@fb.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 include/linux/smp.h | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/smp.h b/include/linux/smp.h
index 6ae004e437ea..4991c6b12831 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -17,10 +17,7 @@ extern void cpu_idle(void);
 
 typedef void (*smp_call_func_t)(void *info);
 struct call_single_data {
-	union {
-		struct list_head list;
-		struct llist_node llist;
-	};
+	struct llist_node llist;
 	smp_call_func_t func;
 	void *info;
 	u16 flags;
-- 
cgit v1.2.3


From 08eed44c7249d381a099bc55577e55c6bb533160 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Mon, 24 Feb 2014 16:39:57 +0100
Subject: smp: Teach __smp_call_function_single() to check for offline cpus

Align __smp_call_function_single() with smp_call_function_single() so
that it also checks whether requested cpu is still online.

Signed-off-by: Jan Kara <jack@suse.cz>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jens Axboe <axboe@fb.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 include/linux/smp.h |  3 +--
 kernel/smp.c        | 11 +++++++----
 kernel/up.c         |  5 +++--
 3 files changed, 11 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/smp.h b/include/linux/smp.h
index 4991c6b12831..c39074c794c5 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -50,8 +50,7 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
 		smp_call_func_t func, void *info, bool wait,
 		gfp_t gfp_flags);
 
-void __smp_call_function_single(int cpuid, struct call_single_data *data,
-				int wait);
+int __smp_call_function_single(int cpu, struct call_single_data *csd, int wait);
 
 #ifdef CONFIG_SMP
 
diff --git a/kernel/smp.c b/kernel/smp.c
index e3852de042a6..5ff14e3739ca 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -276,18 +276,18 @@ EXPORT_SYMBOL_GPL(smp_call_function_any);
 /**
  * __smp_call_function_single(): Run a function on a specific CPU
  * @cpu: The CPU to run on.
- * @data: Pre-allocated and setup data structure
+ * @csd: Pre-allocated and setup data structure
  * @wait: If true, wait until function has completed on specified CPU.
  *
  * Like smp_call_function_single(), but allow caller to pass in a
  * pre-allocated data structure. Useful for embedding @data inside
  * other structures, for instance.
  */
-void __smp_call_function_single(int cpu, struct call_single_data *csd,
-				int wait)
+int __smp_call_function_single(int cpu, struct call_single_data *csd, int wait)
 {
 	unsigned int this_cpu;
 	unsigned long flags;
+	int err = 0;
 
 	this_cpu = get_cpu();
 	/*
@@ -303,11 +303,14 @@ void __smp_call_function_single(int cpu, struct call_single_data *csd,
 		local_irq_save(flags);
 		csd->func(csd->info);
 		local_irq_restore(flags);
-	} else {
+	} else if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
 		csd_lock(csd);
 		generic_exec_single(cpu, csd, wait);
+	} else {
+		err = -ENXIO;	/* CPU not online */
 	}
 	put_cpu();
+	return err;
 }
 EXPORT_SYMBOL_GPL(__smp_call_function_single);
 
diff --git a/kernel/up.c b/kernel/up.c
index 509403e3fbc6..cdf03d16840e 100644
--- a/kernel/up.c
+++ b/kernel/up.c
@@ -22,14 +22,15 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 }
 EXPORT_SYMBOL(smp_call_function_single);
 
-void __smp_call_function_single(int cpu, struct call_single_data *csd,
-				int wait)
+int __smp_call_function_single(int cpu, struct call_single_data *csd,
+			       int wait)
 {
 	unsigned long flags;
 
 	local_irq_save(flags);
 	csd->func(csd->info);
 	local_irq_restore(flags);
+	return 0;
 }
 EXPORT_SYMBOL(__smp_call_function_single);
 
-- 
cgit v1.2.3


From fce8ad1568c57e7f334018dec4fa1744c926c135 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Mon, 24 Feb 2014 16:40:01 +0100
Subject: smp: Remove wait argument from __smp_call_function_single()

The main point of calling __smp_call_function_single() is to send
an IPI in a pure asynchronous way. By embedding a csd in an object,
a caller can send the IPI without waiting for a previous one to complete
as is required by smp_call_function_single() for example. As such,
sending this kind of IPI can be safe even when irqs are disabled.

This flexibility comes at the expense of the caller who then needs to
synchronize the csd lifecycle by himself and make sure that IPIs on a
single csd are serialized.

This is how __smp_call_function_single() works when wait = 0 and this
usecase is relevant.

Now there don't seem to be any usecase with wait = 1 that can't be
covered by smp_call_function_single() instead, which is safer. Lets look
at the two possible scenario:

1) The user calls __smp_call_function_single(wait = 1) on a csd embedded
   in an object. It looks like a nice and convenient pattern at the first
   sight because we can then retrieve the object from the IPI handler easily.

   But actually it is a waste of memory space in the object since the csd
   can be allocated from the stack by smp_call_function_single(wait = 1)
   and the object can be passed an the IPI argument.

   Besides that, embedding the csd in an object is more error prone
   because the caller must take care of the serialization of the IPIs
   for this csd.

2) The user calls __smp_call_function_single(wait = 1) on a csd that
   is allocated on the stack. It's ok but smp_call_function_single()
   can do it as well and it already takes care of the allocation on the
   stack. Again it's more simple and less error prone.

Therefore, using the underscore prepend API version with wait = 1
is a bad pattern and a sign that the caller can do safer and more
simple.

There was a single user of that which has just been converted.
So lets remove this option to discourage further users.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <axboe@fb.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq.c            |  2 +-
 block/blk-softirq.c       |  2 +-
 drivers/cpuidle/coupled.c |  2 +-
 include/linux/smp.h       |  2 +-
 kernel/sched/core.c       |  2 +-
 kernel/smp.c              | 19 ++++---------------
 kernel/up.c               |  3 +--
 net/core/dev.c            |  2 +-
 8 files changed, 11 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 1fa9dd153fde..62154edf1489 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -353,7 +353,7 @@ void __blk_mq_complete_request(struct request *rq)
 		rq->csd.func = __blk_mq_complete_request_remote;
 		rq->csd.info = rq;
 		rq->csd.flags = 0;
-		__smp_call_function_single(ctx->cpu, &rq->csd, 0);
+		__smp_call_function_single(ctx->cpu, &rq->csd);
 	} else {
 		rq->q->softirq_done_fn(rq);
 	}
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index b5c37d96cf0e..6345b7ebd0df 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -70,7 +70,7 @@ static int raise_blk_irq(int cpu, struct request *rq)
 		data->info = rq;
 		data->flags = 0;
 
-		__smp_call_function_single(cpu, data, 0);
+		__smp_call_function_single(cpu, data);
 		return 0;
 	}
 
diff --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c
index e952936418d0..04115947accc 100644
--- a/drivers/cpuidle/coupled.c
+++ b/drivers/cpuidle/coupled.c
@@ -323,7 +323,7 @@ static void cpuidle_coupled_poke(int cpu)
 	struct call_single_data *csd = &per_cpu(cpuidle_coupled_poke_cb, cpu);
 
 	if (!cpumask_test_and_set_cpu(cpu, &cpuidle_coupled_poke_pending))
-		__smp_call_function_single(cpu, csd, 0);
+		__smp_call_function_single(cpu, csd);
 }
 
 /**
diff --git a/include/linux/smp.h b/include/linux/smp.h
index c39074c794c5..b410a1f23281 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -50,7 +50,7 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
 		smp_call_func_t func, void *info, bool wait,
 		gfp_t gfp_flags);
 
-int __smp_call_function_single(int cpu, struct call_single_data *csd, int wait);
+int __smp_call_function_single(int cpu, struct call_single_data *csd);
 
 #ifdef CONFIG_SMP
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b46131ef6aab..eba3d84765f3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -432,7 +432,7 @@ void hrtick_start(struct rq *rq, u64 delay)
 	if (rq == this_rq()) {
 		__hrtick_restart(rq);
 	} else if (!rq->hrtick_csd_pending) {
-		__smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0);
+		__smp_call_function_single(cpu_of(rq), &rq->hrtick_csd);
 		rq->hrtick_csd_pending = 1;
 	}
 }
diff --git a/kernel/smp.c b/kernel/smp.c
index fa04ab938e52..b76763189752 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -241,29 +241,18 @@ EXPORT_SYMBOL(smp_call_function_single);
  * __smp_call_function_single(): Run a function on a specific CPU
  * @cpu: The CPU to run on.
  * @csd: Pre-allocated and setup data structure
- * @wait: If true, wait until function has completed on specified CPU.
  *
  * Like smp_call_function_single(), but allow caller to pass in a
  * pre-allocated data structure. Useful for embedding @data inside
  * other structures, for instance.
  */
-int __smp_call_function_single(int cpu, struct call_single_data *csd, int wait)
+int __smp_call_function_single(int cpu, struct call_single_data *csd)
 {
 	int err = 0;
-	int this_cpu;
 
-	this_cpu = get_cpu();
-	/*
-	 * Can deadlock when called with interrupts disabled.
-	 * We allow cpu's that are not yet online though, as no one else can
-	 * send smp call function interrupt to this cpu and as such deadlocks
-	 * can't happen.
-	 */
-	WARN_ON_ONCE(cpu_online(this_cpu) && wait && irqs_disabled()
-		     && !oops_in_progress);
-
-	err = generic_exec_single(cpu, csd, csd->func, csd->info, wait);
-	put_cpu();
+	preempt_disable();
+	err = generic_exec_single(cpu, csd, csd->func, csd->info, 0);
+	preempt_enable();
 
 	return err;
 }
diff --git a/kernel/up.c b/kernel/up.c
index cdf03d16840e..4e199d4cef8e 100644
--- a/kernel/up.c
+++ b/kernel/up.c
@@ -22,8 +22,7 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 }
 EXPORT_SYMBOL(smp_call_function_single);
 
-int __smp_call_function_single(int cpu, struct call_single_data *csd,
-			       int wait)
+int __smp_call_function_single(int cpu, struct call_single_data *csd)
 {
 	unsigned long flags;
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 4ad1b78c9c77..d1298128bff4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4129,7 +4129,7 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd)
 
 			if (cpu_online(remsd->cpu))
 				__smp_call_function_single(remsd->cpu,
-							   &remsd->csd, 0);
+							   &remsd->csd);
 			remsd = next;
 		}
 	} else
-- 
cgit v1.2.3


From c46fff2a3b29794b35d717b5680a27f31a6a6bc0 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Mon, 24 Feb 2014 16:40:02 +0100
Subject: smp: Rename __smp_call_function_single() to
 smp_call_function_single_async()

The name __smp_call_function_single() doesn't tell much about the
properties of this function, especially when compared to
smp_call_function_single().

The comments above the implementation are also misleading. The main
point of this function is actually not to be able to embed the csd
in an object. This is actually a requirement that result from the
purpose of this function which is to raise an IPI asynchronously.

As such it can be called with interrupts disabled. And this feature
comes at the cost of the caller who then needs to serialize the
IPIs on this csd.

Lets rename the function and enhance the comments so that they reflect
these properties.

Suggested-by: Christoph Hellwig <hch@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <axboe@fb.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq.c            |  2 +-
 block/blk-softirq.c       |  2 +-
 drivers/cpuidle/coupled.c |  2 +-
 include/linux/smp.h       |  2 +-
 kernel/sched/core.c       |  2 +-
 kernel/smp.c              | 19 +++++++++++++------
 kernel/up.c               |  4 ++--
 net/core/dev.c            |  2 +-
 8 files changed, 21 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 62154edf1489..6468a715a0e4 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -353,7 +353,7 @@ void __blk_mq_complete_request(struct request *rq)
 		rq->csd.func = __blk_mq_complete_request_remote;
 		rq->csd.info = rq;
 		rq->csd.flags = 0;
-		__smp_call_function_single(ctx->cpu, &rq->csd);
+		smp_call_function_single_async(ctx->cpu, &rq->csd);
 	} else {
 		rq->q->softirq_done_fn(rq);
 	}
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 6345b7ebd0df..ebd6b6f1bdeb 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -70,7 +70,7 @@ static int raise_blk_irq(int cpu, struct request *rq)
 		data->info = rq;
 		data->flags = 0;
 
-		__smp_call_function_single(cpu, data);
+		smp_call_function_single_async(cpu, data);
 		return 0;
 	}
 
diff --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c
index 04115947accc..cb6654bfad77 100644
--- a/drivers/cpuidle/coupled.c
+++ b/drivers/cpuidle/coupled.c
@@ -323,7 +323,7 @@ static void cpuidle_coupled_poke(int cpu)
 	struct call_single_data *csd = &per_cpu(cpuidle_coupled_poke_cb, cpu);
 
 	if (!cpumask_test_and_set_cpu(cpu, &cpuidle_coupled_poke_pending))
-		__smp_call_function_single(cpu, csd);
+		smp_call_function_single_async(cpu, csd);
 }
 
 /**
diff --git a/include/linux/smp.h b/include/linux/smp.h
index b410a1f23281..633f5edd7470 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -50,7 +50,7 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
 		smp_call_func_t func, void *info, bool wait,
 		gfp_t gfp_flags);
 
-int __smp_call_function_single(int cpu, struct call_single_data *csd);
+int smp_call_function_single_async(int cpu, struct call_single_data *csd);
 
 #ifdef CONFIG_SMP
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index eba3d84765f3..0cca04a53de0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -432,7 +432,7 @@ void hrtick_start(struct rq *rq, u64 delay)
 	if (rq == this_rq()) {
 		__hrtick_restart(rq);
 	} else if (!rq->hrtick_csd_pending) {
-		__smp_call_function_single(cpu_of(rq), &rq->hrtick_csd);
+		smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd);
 		rq->hrtick_csd_pending = 1;
 	}
 }
diff --git a/kernel/smp.c b/kernel/smp.c
index b76763189752..06d574e42c72 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -238,15 +238,22 @@ int smp_call_function_single(int cpu, smp_call_func_t func, void *info,
 EXPORT_SYMBOL(smp_call_function_single);
 
 /**
- * __smp_call_function_single(): Run a function on a specific CPU
+ * smp_call_function_single_async(): Run an asynchronous function on a
+ * 			         specific CPU.
  * @cpu: The CPU to run on.
  * @csd: Pre-allocated and setup data structure
  *
- * Like smp_call_function_single(), but allow caller to pass in a
- * pre-allocated data structure. Useful for embedding @data inside
- * other structures, for instance.
+ * Like smp_call_function_single(), but the call is asynchonous and
+ * can thus be done from contexts with disabled interrupts.
+ *
+ * The caller passes his own pre-allocated data structure
+ * (ie: embedded in an object) and is responsible for synchronizing it
+ * such that the IPIs performed on the @csd are strictly serialized.
+ *
+ * NOTE: Be careful, there is unfortunately no current debugging facility to
+ * validate the correctness of this serialization.
  */
-int __smp_call_function_single(int cpu, struct call_single_data *csd)
+int smp_call_function_single_async(int cpu, struct call_single_data *csd)
 {
 	int err = 0;
 
@@ -256,7 +263,7 @@ int __smp_call_function_single(int cpu, struct call_single_data *csd)
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(__smp_call_function_single);
+EXPORT_SYMBOL_GPL(smp_call_function_single_async);
 
 /*
  * smp_call_function_any - Run a function on any of the given cpus
diff --git a/kernel/up.c b/kernel/up.c
index 4e199d4cef8e..1760bf3d1463 100644
--- a/kernel/up.c
+++ b/kernel/up.c
@@ -22,7 +22,7 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 }
 EXPORT_SYMBOL(smp_call_function_single);
 
-int __smp_call_function_single(int cpu, struct call_single_data *csd)
+int smp_call_function_single_async(int cpu, struct call_single_data *csd)
 {
 	unsigned long flags;
 
@@ -31,7 +31,7 @@ int __smp_call_function_single(int cpu, struct call_single_data *csd)
 	local_irq_restore(flags);
 	return 0;
 }
-EXPORT_SYMBOL(__smp_call_function_single);
+EXPORT_SYMBOL(smp_call_function_single_async);
 
 int on_each_cpu(smp_call_func_t func, void *info, int wait)
 {
diff --git a/net/core/dev.c b/net/core/dev.c
index d1298128bff4..ac7a2abb7f1a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4128,7 +4128,7 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd)
 			struct softnet_data *next = remsd->rps_ipi_next;
 
 			if (cpu_online(remsd->cpu))
-				__smp_call_function_single(remsd->cpu,
+				smp_call_function_single_async(remsd->cpu,
 							   &remsd->csd);
 			remsd = next;
 		}
-- 
cgit v1.2.3


From 90eedf0cbe4ba2a316633d6547d331c8b30517e7 Mon Sep 17 00:00:00 2001
From: Gerd Hoffmann <kraxel@redhat.com>
Date: Mon, 24 Feb 2014 14:17:09 +0100
Subject: vmbus: use resource for hyperv mmio region

Use a resource for the hyperv mmio region instead of start/size
variables.  Register the region properly so it shows up in
/proc/iomem.

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hv/vmbus_drv.c | 16 ++++++++++------
 include/linux/hyperv.h |  3 +--
 2 files changed, 11 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 2352ae481e87..a14f60340bfc 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -43,10 +43,12 @@ static struct acpi_device  *hv_acpi_dev;
 static struct tasklet_struct msg_dpc;
 static struct completion probe_event;
 static int irq;
-u64 hyperv_mmio_start;
-EXPORT_SYMBOL_GPL(hyperv_mmio_start);
-u64 hyperv_mmio_size;
-EXPORT_SYMBOL_GPL(hyperv_mmio_size);
+
+struct resource hyperv_mmio = {
+	.name  = "hyperv mmio",
+	.flags = IORESOURCE_MEM,
+};
+EXPORT_SYMBOL_GPL(hyperv_mmio);
 
 static int vmbus_exists(void)
 {
@@ -902,8 +904,8 @@ static acpi_status vmbus_walk_resources(struct acpi_resource *res, void *ctx)
 		break;
 
 	case ACPI_RESOURCE_TYPE_ADDRESS64:
-		hyperv_mmio_start = res->data.address64.minimum;
-		hyperv_mmio_size = res->data.address64.address_length;
+		hyperv_mmio.start = res->data.address64.minimum;
+		hyperv_mmio.end = res->data.address64.maximum;
 		break;
 	}
 
@@ -933,6 +935,8 @@ static int vmbus_acpi_add(struct acpi_device *device)
 
 		if (ACPI_FAILURE(result))
 			goto acpi_walk_err;
+		if (hyperv_mmio.start && hyperv_mmio.end)
+			request_resource(&iomem_resource, &hyperv_mmio);
 	}
 	ret_val = 0;
 
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 62ea1a06836a..330ec44de575 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1167,8 +1167,7 @@ int hv_vss_init(struct hv_util_service *);
 void hv_vss_deinit(void);
 void hv_vss_onchannelcallback(void *);
 
-extern u64 hyperv_mmio_start;
-extern u64 hyperv_mmio_size;
+extern struct resource hyperv_mmio;
 
 /*
  * Negotiated version with the Host.
-- 
cgit v1.2.3


From 4f6743d5ca97ac66831add302cc5467db4ee3809 Mon Sep 17 00:00:00 2001
From: Michael Grzeschik <m.grzeschik@pengutronix.de>
Date: Wed, 19 Feb 2014 13:41:43 +0800
Subject: usb: chipidea: udc: add maximum-speed = full-speed option

This patch makes it possible to set the chipidea udc into full-speed only mode.
It is set by the oftree property "maximum-speed = full-speed".

Signed-off-by: Peter Chen <peter.chen@freescale.com>
Signed-off-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/devicetree/bindings/usb/ci-hdrc-imx.txt |  2 ++
 drivers/usb/chipidea/bits.h                           |  2 ++
 drivers/usb/chipidea/core.c                           | 11 +++++++++++
 include/linux/usb/chipidea.h                          |  1 +
 4 files changed, 16 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/devicetree/bindings/usb/ci-hdrc-imx.txt b/Documentation/devicetree/bindings/usb/ci-hdrc-imx.txt
index b4b5b7906c88..a6a32cb7f777 100644
--- a/Documentation/devicetree/bindings/usb/ci-hdrc-imx.txt
+++ b/Documentation/devicetree/bindings/usb/ci-hdrc-imx.txt
@@ -18,6 +18,7 @@ Optional properties:
 - vbus-supply: regulator for vbus
 - disable-over-current: disable over current detect
 - external-vbus-divider: enables off-chip resistor divider for Vbus
+- maximum-speed: limit the maximum connection speed to "full-speed".
 
 Examples:
 usb@02184000 { /* USB OTG */
@@ -28,4 +29,5 @@ usb@02184000 { /* USB OTG */
 	fsl,usbmisc = <&usbmisc 0>;
 	disable-over-current;
 	external-vbus-divider;
+	maximum-speed = "full-speed";
 };
diff --git a/drivers/usb/chipidea/bits.h b/drivers/usb/chipidea/bits.h
index a85713165688..83d06c1455b7 100644
--- a/drivers/usb/chipidea/bits.h
+++ b/drivers/usb/chipidea/bits.h
@@ -50,12 +50,14 @@
 #define PORTSC_PTC            (0x0FUL << 16)
 #define PORTSC_PHCD(d)	      ((d) ? BIT(22) : BIT(23))
 /* PTS and PTW for non lpm version only */
+#define PORTSC_PFSC           BIT(24)
 #define PORTSC_PTS(d)						\
 	(u32)((((d) & 0x3) << 30) | (((d) & 0x4) ? BIT(25) : 0))
 #define PORTSC_PTW            BIT(28)
 #define PORTSC_STS            BIT(29)
 
 /* DEVLC */
+#define DEVLC_PFSC            BIT(23)
 #define DEVLC_PSPD            (0x03UL << 25)
 #define DEVLC_PSPD_HS         (0x02UL << 25)
 #define DEVLC_PTW             BIT(27)
diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c
index 47b4bd860b65..65aeaacda6cd 100644
--- a/drivers/usb/chipidea/core.c
+++ b/drivers/usb/chipidea/core.c
@@ -64,6 +64,7 @@
 #include <linux/usb/otg.h>
 #include <linux/usb/chipidea.h>
 #include <linux/usb/of.h>
+#include <linux/of.h>
 #include <linux/phy.h>
 #include <linux/regulator/consumer.h>
 
@@ -298,6 +299,13 @@ int hw_device_reset(struct ci_hdrc *ci, u32 mode)
 	if (ci->platdata->flags & CI_HDRC_DISABLE_STREAMING)
 		hw_write(ci, OP_USBMODE, USBMODE_CI_SDIS, USBMODE_CI_SDIS);
 
+	if (ci->platdata->flags & CI_HDRC_FORCE_FULLSPEED) {
+		if (ci->hw_bank.lpm)
+			hw_write(ci, OP_DEVLC, DEVLC_PFSC, DEVLC_PFSC);
+		else
+			hw_write(ci, OP_PORTSC, PORTSC_PFSC, PORTSC_PFSC);
+	}
+
 	/* USBMODE should be configured step by step */
 	hw_write(ci, OP_USBMODE, USBMODE_CM, USBMODE_CM_IDLE);
 	hw_write(ci, OP_USBMODE, USBMODE_CM, mode);
@@ -412,6 +420,9 @@ static int ci_get_platdata(struct device *dev,
 		}
 	}
 
+	if (of_usb_get_maximum_speed(dev->of_node) == USB_SPEED_FULL)
+		platdata->flags |= CI_HDRC_FORCE_FULLSPEED;
+
 	return 0;
 }
 
diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h
index 708bd119627f..bbe779f640be 100644
--- a/include/linux/usb/chipidea.h
+++ b/include/linux/usb/chipidea.h
@@ -25,6 +25,7 @@ struct ci_hdrc_platform_data {
 	 */
 #define CI_HDRC_DUAL_ROLE_NOT_OTG	BIT(4)
 #define CI_HDRC_IMX28_WRITE_FIX		BIT(5)
+#define CI_HDRC_FORCE_FULLSPEED		BIT(6)
 	enum usb_dr_mode	dr_mode;
 #define CI_HDRC_CONTROLLER_RESET_EVENT		0
 #define CI_HDRC_CONTROLLER_STOPPED_EVENT	1
-- 
cgit v1.2.3


From 86bcfa2e87c42b8af77188e7a939e952199d4da1 Mon Sep 17 00:00:00 2001
From: Mike Turquette <mturquette@linaro.org>
Date: Mon, 24 Feb 2014 16:08:41 -0800
Subject: clk: add pr_debug & kerneldoc around clk notifiers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Both the pr_err and the additional kerneldoc aim to help when debugging
errors thrown from within a clock rate-change notifier callback.

Reported-by: Sören Brinkmann <soren.brinkmann@xilinx.com>
Acked-by: Sören Brinkmann <soren.brinkmann@xilinx.com>
Signed-off-by: Mike Turquette <mturquette@linaro.org>
---
 drivers/clk/clk.c   |  5 ++++-
 include/linux/clk.h | 14 ++++++++++++++
 2 files changed, 18 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index a6f079d23eaa..f30e6af90332 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -1339,8 +1339,11 @@ static int __clk_speculate_rates(struct clk *clk, unsigned long parent_rate)
 	if (clk->notifier_count)
 		ret = __clk_notify(clk, PRE_RATE_CHANGE, clk->rate, new_rate);
 
-	if (ret & NOTIFY_STOP_MASK)
+	if (ret & NOTIFY_STOP_MASK) {
+		pr_debug("%s: clk notifier callback for clock %s aborted with error %d\n",
+				__func__, clk->name, ret);
 		goto out;
+	}
 
 	hlist_for_each_entry(child, &clk->children, child_node) {
 		ret = __clk_speculate_rates(child, new_rate);
diff --git a/include/linux/clk.h b/include/linux/clk.h
index 0dd91148165e..fb5e097d8f72 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -78,8 +78,22 @@ struct clk_notifier_data {
 	unsigned long		new_rate;
 };
 
+/**
+ * clk_notifier_register: register a clock rate-change notifier callback
+ * @clk: clock whose rate we are interested in
+ * @nb: notifier block with callback function pointer
+ *
+ * ProTip: debugging across notifier chains can be frustrating. Make sure that
+ * your notifier callback function prints a nice big warning in case of
+ * failure.
+ */
 int clk_notifier_register(struct clk *clk, struct notifier_block *nb);
 
+/**
+ * clk_notifier_unregister: unregister a clock rate-change notifier callback
+ * @clk: clock whose rate we are no longer interested in
+ * @nb: notifier block which will be unregistered
+ */
 int clk_notifier_unregister(struct clk *clk, struct notifier_block *nb);
 
 /**
-- 
cgit v1.2.3


From 0eb5db7ad302a24fe6f0eb4bfd235357047a28db Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Tue, 18 Feb 2014 18:06:48 +0000
Subject: netfilter: nfnetlink: add rcu_dereference_protected() helpers

Add a lockdep_nfnl_is_held() function and a nfnl_dereference() macro for
RCU dereferences protected by a NFNL subsystem mutex.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/nfnetlink.h | 21 +++++++++++++++++++++
 net/netfilter/nfnetlink.c           |  8 ++++++++
 2 files changed, 29 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index 28c74367e900..e955d4730625 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -44,6 +44,27 @@ int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid,
 
 void nfnl_lock(__u8 subsys_id);
 void nfnl_unlock(__u8 subsys_id);
+#ifdef CONFIG_PROVE_LOCKING
+int lockdep_nfnl_is_held(__u8 subsys_id);
+#else
+static inline int lockdep_nfnl_is_held(__u8 subsys_id)
+{
+	return 1;
+}
+#endif /* CONFIG_PROVE_LOCKING */
+
+/*
+ * nfnl_dereference - fetch RCU pointer when updates are prevented by subsys mutex
+ *
+ * @p: The pointer to read, prior to dereferencing
+ * @ss: The nfnetlink subsystem ID
+ *
+ * Return the value of the specified RCU-protected pointer, but omit
+ * both the smp_read_barrier_depends() and the ACCESS_ONCE(), because
+ * caller holds the NFNL subsystem mutex.
+ */
+#define nfnl_dereference(p, ss)					\
+	rcu_dereference_protected(p, lockdep_nfnl_is_held(ss))
 
 #define MODULE_ALIAS_NFNL_SUBSYS(subsys) \
 	MODULE_ALIAS("nfnetlink-subsys-" __stringify(subsys))
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 046aa13b4fea..e8138da4c14f 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -61,6 +61,14 @@ void nfnl_unlock(__u8 subsys_id)
 }
 EXPORT_SYMBOL_GPL(nfnl_unlock);
 
+#ifdef CONFIG_PROVE_LOCKING
+int lockdep_nfnl_is_held(u8 subsys_id)
+{
+	return lockdep_is_held(&table[subsys_id].mutex);
+}
+EXPORT_SYMBOL_GPL(lockdep_nfnl_is_held);
+#endif
+
 int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n)
 {
 	nfnl_lock(n->subsys_id);
-- 
cgit v1.2.3


From 8d971691834fd5506cb2d7aef71a3717b7ed597d Mon Sep 17 00:00:00 2001
From: Sachin Kamat <sachin.kamat@linaro.org>
Date: Tue, 25 Feb 2014 15:10:39 +0530
Subject: ASoC: samsung: Remove invalid file reference

Remove file references rendered invalid due to relocation.

Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/linux/platform_data/asoc-s3c.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/asoc-s3c.h b/include/linux/platform_data/asoc-s3c.h
index 9efc04dd255a..709c6f7e2f8c 100644
--- a/include/linux/platform_data/asoc-s3c.h
+++ b/include/linux/platform_data/asoc-s3c.h
@@ -1,5 +1,4 @@
-/* arch/arm/plat-samsung/include/plat/audio.h
- *
+/*
  * Copyright (c) 2009 Samsung Electronics Co. Ltd
  * Author: Jaswinder Singh <jassi.brar@samsung.com>
  *
-- 
cgit v1.2.3


From c3c125e294fd4276add6f80d2b333ca7c55e935d Mon Sep 17 00:00:00 2001
From: Sachin Kamat <sachin.kamat@linaro.org>
Date: Tue, 25 Feb 2014 15:10:40 +0530
Subject: ASoC: s3c24xx: Remove invalid file reference

Remove file references rendered invalid due to relocation.

Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/linux/platform_data/asoc-s3c24xx_simtec.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/asoc-s3c24xx_simtec.h b/include/linux/platform_data/asoc-s3c24xx_simtec.h
index 376af5286a3e..d220e54123aa 100644
--- a/include/linux/platform_data/asoc-s3c24xx_simtec.h
+++ b/include/linux/platform_data/asoc-s3c24xx_simtec.h
@@ -1,5 +1,4 @@
-/* arch/arm/plat-samsung/include/plat/audio-simtec.h
- *
+/*
  * Copyright 2008 Simtec Electronics
  *	http://armlinux.simtec.co.uk/
  *	Ben Dooks <ben@simtec.co.uk>
-- 
cgit v1.2.3


From c75611282cf1bf717c1866e7a7eb4d0743815187 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 25 Feb 2014 10:04:01 -0500
Subject: cgroup: add css_set->mg_tasks

Currently, while migrating tasks from one cgroup to another,
cgroup_attach_task() builds a flex array of all target tasks;
unfortunately, this has a couple issues.

* Flex array has size limit.  On 64bit, struct task_and_cgroup is
  24bytes making the flex element limit around 87k.  It is a high
  number but not impossible to hit.  This means that the current
  cgroup implementation can't migrate a process with more than 87k
  threads.

* Process migration involves memory allocation whose size is dependent
  on the number of threads the process has.  This means that cgroup
  core can't guarantee success or failure of multi-process migrations
  as memory allocation failure can happen in the middle.  This is in
  part because cgroup can't grab threadgroup locks of multiple
  processes at the same time, so when there are multiple processes to
  migrate, it is imposible to tell how many tasks are to be migrated
  beforehand.

  Note that this already affects cgroup_transfer_tasks().  cgroup
  currently cannot guarantee atomic success or failure of the
  operation.  It may fail in the middle and after such failure cgroup
  doesn't have enough information to roll back properly.  It just
  aborts with some tasks migrated and others not.

To resolve the situation, we're going to use task->cg_list during
migration too.  Instead of building a separate array, target tasks
will be linked into a dedicated migration list_head on the owning
css_set.  Tasks on the migration list are treated the same as tasks on
the usual tasks list; however, being on a separate list allows cgroup
migration code path to keep track of the target tasks by simply
keeping the list of css_sets with tasks being migrated, making
unpredictable dynamic allocation unnecessary.

In prepartion of such migration path update, this patch introduces
css_set->mg_tasks list and updates css_set task iterations so that
they walk both css_set->tasks and ->mg_tasks.  Note that ->mg_tasks
isn't used yet.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h |  8 ++++++--
 kernel/cgroup.c        | 56 +++++++++++++++++++++++++++++++++-----------------
 2 files changed, 43 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 8c283a910b91..528e2aed36c3 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -324,10 +324,14 @@ struct css_set {
 	struct hlist_node hlist;
 
 	/*
-	 * List running through all tasks using this cgroup
-	 * group. Protected by css_set_lock
+	 * Lists running through all tasks using this cgroup group.
+	 * mg_tasks lists tasks which belong to this cset but are in the
+	 * process of being migrated out or in.  Protected by
+	 * css_set_rwsem, but, during migration, once tasks are moved to
+	 * mg_tasks, it can be read safely while holding cgroup_mutex.
 	 */
 	struct list_head tasks;
+	struct list_head mg_tasks;
 
 	/*
 	 * List of cgrp_cset_links pointing at cgroups referenced from this
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 8ab800c7bac0..b80c611ff836 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -644,6 +644,7 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 	atomic_set(&cset->refcount, 1);
 	INIT_LIST_HEAD(&cset->cgrp_links);
 	INIT_LIST_HEAD(&cset->tasks);
+	INIT_LIST_HEAD(&cset->mg_tasks);
 	INIT_HLIST_NODE(&cset->hlist);
 
 	/* Copy the set of subsystem state objects generated in
@@ -2590,9 +2591,14 @@ static void css_advance_task_iter(struct css_task_iter *it)
 		}
 		link = list_entry(l, struct cgrp_cset_link, cset_link);
 		cset = link->cset;
-	} while (list_empty(&cset->tasks));
+	} while (list_empty(&cset->tasks) && list_empty(&cset->mg_tasks));
+
 	it->cset_link = l;
-	it->task = cset->tasks.next;
+
+	if (!list_empty(&cset->tasks))
+		it->task = cset->tasks.next;
+	else
+		it->task = cset->mg_tasks.next;
 }
 
 /**
@@ -2636,24 +2642,29 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it)
 {
 	struct task_struct *res;
 	struct list_head *l = it->task;
-	struct cgrp_cset_link *link;
+	struct cgrp_cset_link *link = list_entry(it->cset_link,
+					struct cgrp_cset_link, cset_link);
 
 	/* If the iterator cg is NULL, we have no tasks */
 	if (!it->cset_link)
 		return NULL;
 	res = list_entry(l, struct task_struct, cg_list);
-	/* Advance iterator to find next entry */
+
+	/*
+	 * Advance iterator to find next entry.  cset->tasks is consumed
+	 * first and then ->mg_tasks.  After ->mg_tasks, we move onto the
+	 * next cset.
+	 */
 	l = l->next;
-	link = list_entry(it->cset_link, struct cgrp_cset_link, cset_link);
-	if (l == &link->cset->tasks) {
-		/*
-		 * We reached the end of this task list - move on to the
-		 * next cgrp_cset_link.
-		 */
+
+	if (l == &link->cset->tasks)
+		l = link->cset->mg_tasks.next;
+
+	if (l == &link->cset->mg_tasks)
 		css_advance_task_iter(it);
-	} else {
+	else
 		it->task = l;
-	}
+
 	return res;
 }
 
@@ -4502,16 +4513,23 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v)
 		struct css_set *cset = link->cset;
 		struct task_struct *task;
 		int count = 0;
+
 		seq_printf(seq, "css_set %p\n", cset);
+
 		list_for_each_entry(task, &cset->tasks, cg_list) {
-			if (count++ > MAX_TASKS_SHOWN_PER_CSS) {
-				seq_puts(seq, "  ...\n");
-				break;
-			} else {
-				seq_printf(seq, "  task %d\n",
-					   task_pid_vnr(task));
-			}
+			if (count++ > MAX_TASKS_SHOWN_PER_CSS)
+				goto overflow;
+			seq_printf(seq, "  task %d\n", task_pid_vnr(task));
+		}
+
+		list_for_each_entry(task, &cset->mg_tasks, cg_list) {
+			if (count++ > MAX_TASKS_SHOWN_PER_CSS)
+				goto overflow;
+			seq_printf(seq, "  task %d\n", task_pid_vnr(task));
 		}
+		continue;
+	overflow:
+		seq_puts(seq, "  ...\n");
 	}
 	up_read(&css_set_rwsem);
 	return 0;
-- 
cgit v1.2.3


From b3dc094e93905ae9c1bc0815402ad8e5b203d068 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 25 Feb 2014 10:04:01 -0500
Subject: cgroup: use css_set->mg_tasks to track target tasks during migration

Currently, while migrating tasks from one cgroup to another,
cgroup_attach_task() builds a flex array of all target tasks;
unfortunately, this has a couple issues.

* Flex array has size limit.  On 64bit, struct task_and_cgroup is
  24bytes making the flex element limit around 87k.  It is a high
  number but not impossible to hit.  This means that the current
  cgroup implementation can't migrate a process with more than 87k
  threads.

* Process migration involves memory allocation whose size is dependent
  on the number of threads the process has.  This means that cgroup
  core can't guarantee success or failure of multi-process migrations
  as memory allocation failure can happen in the middle.  This is in
  part because cgroup can't grab threadgroup locks of multiple
  processes at the same time, so when there are multiple processes to
  migrate, it is imposible to tell how many tasks are to be migrated
  beforehand.

  Note that this already affects cgroup_transfer_tasks().  cgroup
  currently cannot guarantee atomic success or failure of the
  operation.  It may fail in the middle and after such failure cgroup
  doesn't have enough information to roll back properly.  It just
  aborts with some tasks migrated and others not.

To resolve the situation, this patch updates the migration path to use
task->cg_list to track target tasks.  The previous patch already added
css_set->mg_tasks and updated iterations in non-migration paths to
include them during task migration.  This patch updates migration path
to actually make use of it.

Instead of putting onto a flex_array, each target task is moved from
its css_set->tasks list to css_set->mg_tasks and the migration path
keeps trace of all the source css_sets and the associated cgroups.
Once all source css_sets are determined, the destination css_set for
each is determined, linked to the matching source css_set and put on a
separate list.

To iterate the target tasks, migration path just needs to iterat
through either the source or target css_sets, depending on whether
migration has been committed or not, and the tasks on their ->mg_tasks
lists.  cgroup_taskset is updated to contain the list_heads for source
and target css_sets and the iteration cursor.  cgroup_taskset_*() are
accordingly updated to walk through css_sets and their ->mg_tasks.

This resolves the above listed issues with moderate additional
complexity.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h |  16 ++++
 kernel/cgroup.c        | 223 +++++++++++++++++++++++++------------------------
 2 files changed, 131 insertions(+), 108 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 528e2aed36c3..3a1cb265afd6 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -346,6 +346,22 @@ struct css_set {
 	 */
 	struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];
 
+	/*
+	 * List of csets participating in the on-going migration either as
+	 * source or destination.  Protected by cgroup_mutex.
+	 */
+	struct list_head mg_node;
+
+	/*
+	 * If this cset is acting as the source of migration the following
+	 * two fields are set.  mg_src_cgrp is the source cgroup of the
+	 * on-going migration and mg_dst_cset is the destination cset the
+	 * target tasks on this cset should be migrated to.  Protected by
+	 * cgroup_mutex.
+	 */
+	struct cgroup *mg_src_cgrp;
+	struct css_set *mg_dst_cset;
+
 	/* For RCU-protected deletion */
 	struct rcu_head rcu_head;
 };
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index b80c611ff836..5def4a800425 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -52,7 +52,6 @@
 #include <linux/pid_namespace.h>
 #include <linux/idr.h>
 #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
-#include <linux/flex_array.h> /* used in cgroup_attach_task */
 #include <linux/kthread.h>
 #include <linux/delay.h>
 
@@ -645,6 +644,7 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 	INIT_LIST_HEAD(&cset->cgrp_links);
 	INIT_LIST_HEAD(&cset->tasks);
 	INIT_LIST_HEAD(&cset->mg_tasks);
+	INIT_LIST_HEAD(&cset->mg_node);
 	INIT_HLIST_NODE(&cset->hlist);
 
 	/* Copy the set of subsystem state objects generated in
@@ -1639,20 +1639,26 @@ char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
 }
 EXPORT_SYMBOL_GPL(task_cgroup_path);
 
-/*
- * Control Group taskset
- */
-struct task_and_cgroup {
-	struct task_struct	*task;
-	struct cgroup		*cgrp;
-	struct css_set		*cset;
-};
-
+/* used to track tasks and other necessary states during migration */
 struct cgroup_taskset {
-	struct task_and_cgroup	single;
-	struct flex_array	*tc_array;
-	int			tc_array_len;
-	int			idx;
+	/* the src and dst cset list running through cset->mg_node */
+	struct list_head	src_csets;
+	struct list_head	dst_csets;
+
+	/*
+	 * Fields for cgroup_taskset_*() iteration.
+	 *
+	 * Before migration is committed, the target migration tasks are on
+	 * ->mg_tasks of the csets on ->src_csets.  After, on ->mg_tasks of
+	 * the csets on ->dst_csets.  ->csets point to either ->src_csets
+	 * or ->dst_csets depending on whether migration is committed.
+	 *
+	 * ->cur_csets and ->cur_task point to the current task position
+	 * during iteration.
+	 */
+	struct list_head	*csets;
+	struct css_set		*cur_cset;
+	struct task_struct	*cur_task;
 };
 
 /**
@@ -1663,12 +1669,10 @@ struct cgroup_taskset {
  */
 struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset)
 {
-	if (tset->tc_array) {
-		tset->idx = 0;
-		return cgroup_taskset_next(tset);
-	} else {
-		return tset->single.task;
-	}
+	tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node);
+	tset->cur_task = NULL;
+
+	return cgroup_taskset_next(tset);
 }
 
 /**
@@ -1680,13 +1684,27 @@ struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset)
  */
 struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
 {
-	struct task_and_cgroup *tc;
+	struct css_set *cset = tset->cur_cset;
+	struct task_struct *task = tset->cur_task;
 
-	if (!tset->tc_array || tset->idx >= tset->tc_array_len)
-		return NULL;
+	while (&cset->mg_node != tset->csets) {
+		if (!task)
+			task = list_first_entry(&cset->mg_tasks,
+						struct task_struct, cg_list);
+		else
+			task = list_next_entry(task, cg_list);
 
-	tc = flex_array_get(tset->tc_array, tset->idx++);
-	return tc->task;
+		if (&task->cg_list != &cset->mg_tasks) {
+			tset->cur_cset = cset;
+			tset->cur_task = task;
+			return task;
+		}
+
+		cset = list_next_entry(cset, mg_node);
+		task = NULL;
+	}
+
+	return NULL;
 }
 
 /**
@@ -1714,11 +1732,13 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp,
 	WARN_ON_ONCE(tsk->flags & PF_EXITING);
 	old_cset = task_css_set(tsk);
 
+	get_css_set(new_cset);
+
 	task_lock(tsk);
 	rcu_assign_pointer(tsk->cgroups, new_cset);
 	task_unlock(tsk);
 
-	list_move(&tsk->cg_list, &new_cset->tasks);
+	list_move(&tsk->cg_list, &new_cset->mg_tasks);
 
 	/*
 	 * We just gained a reference on old_cset by taking it from the
@@ -1741,80 +1761,58 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp,
 static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *leader,
 			      bool threadgroup)
 {
-	int ret, i, group_size;
-	struct cgroupfs_root *root = cgrp->root;
+	struct cgroup_taskset tset = {
+		.src_csets	= LIST_HEAD_INIT(tset.src_csets),
+		.dst_csets	= LIST_HEAD_INIT(tset.dst_csets),
+		.csets		= &tset.src_csets,
+	};
 	struct cgroup_subsys_state *css, *failed_css = NULL;
-	/* threadgroup list cursor and array */
-	struct task_struct *task;
-	struct task_and_cgroup *tc;
-	struct flex_array *group;
-	struct cgroup_taskset tset = { };
-
-	/*
-	 * step 0: in order to do expensive, possibly blocking operations for
-	 * every thread, we cannot iterate the thread group list, since it needs
-	 * rcu or tasklist locked. instead, build an array of all threads in the
-	 * group - group_rwsem prevents new threads from appearing, and if
-	 * threads exit, this will just be an over-estimate.
-	 */
-	if (threadgroup)
-		group_size = get_nr_threads(leader);
-	else
-		group_size = 1;
-	/* flex_array supports very large thread-groups better than kmalloc. */
-	group = flex_array_alloc(sizeof(*tc), group_size, GFP_KERNEL);
-	if (!group)
-		return -ENOMEM;
-	/* pre-allocate to guarantee space while iterating in rcu read-side. */
-	ret = flex_array_prealloc(group, 0, group_size, GFP_KERNEL);
-	if (ret)
-		goto out_free_group_list;
+	struct css_set *cset, *tmp_cset;
+	struct task_struct *task, *tmp_task;
+	int i, ret;
 
-	i = 0;
 	/*
 	 * Prevent freeing of tasks while we take a snapshot. Tasks that are
 	 * already PF_EXITING could be freed from underneath us unless we
 	 * take an rcu_read_lock.
 	 */
-	down_read(&css_set_rwsem);
+	down_write(&css_set_rwsem);
 	rcu_read_lock();
 	task = leader;
 	do {
-		struct task_and_cgroup ent;
+		struct cgroup *src_cgrp;
 
 		/* @task either already exited or can't exit until the end */
 		if (task->flags & PF_EXITING)
 			goto next;
 
-		/* as per above, nr_threads may decrease, but not increase. */
-		BUG_ON(i >= group_size);
-		ent.task = task;
-		ent.cgrp = task_cgroup_from_root(task, root);
+		cset = task_css_set(task);
+		src_cgrp = task_cgroup_from_root(task, cgrp->root);
+
 		/* nothing to do if this task is already in the cgroup */
-		if (ent.cgrp == cgrp)
+		if (src_cgrp == cgrp)
 			goto next;
-		/*
-		 * saying GFP_ATOMIC has no effect here because we did prealloc
-		 * earlier, but it's good form to communicate our expectations.
-		 */
-		ret = flex_array_put(group, i, &ent, GFP_ATOMIC);
-		BUG_ON(ret != 0);
-		i++;
+
+		if (!cset->mg_src_cgrp) {
+			WARN_ON(!list_empty(&cset->mg_tasks));
+			WARN_ON(!list_empty(&cset->mg_node));
+
+			cset->mg_src_cgrp = src_cgrp;
+			list_add(&cset->mg_node, &tset.src_csets);
+			get_css_set(cset);
+		}
+
+		list_move(&task->cg_list, &cset->mg_tasks);
 	next:
 		if (!threadgroup)
 			break;
 	} while_each_thread(leader, task);
 	rcu_read_unlock();
-	up_read(&css_set_rwsem);
-	/* remember the number of threads in the array for later. */
-	group_size = i;
-	tset.tc_array = group;
-	tset.tc_array_len = group_size;
+	up_write(&css_set_rwsem);
 
 	/* methods shouldn't be called if no task is actually migrating */
-	ret = 0;
-	if (!group_size)
-		goto out_free_group_list;
+	if (list_empty(&tset.src_csets))
+		return 0;
 
 	/*
 	 * step 1: check that we can legitimately attach to the cgroup.
@@ -1833,16 +1831,21 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *leader,
 	 * step 2: make sure css_sets exist for all threads to be migrated.
 	 * we use find_css_set, which allocates a new one if necessary.
 	 */
-	for (i = 0; i < group_size; i++) {
-		struct css_set *old_cset;
+	list_for_each_entry(cset, &tset.src_csets, mg_node) {
+		struct css_set *dst_cset;
 
-		tc = flex_array_get(group, i);
-		old_cset = task_css_set(tc->task);
-		tc->cset = find_css_set(old_cset, cgrp);
-		if (!tc->cset) {
+		dst_cset = find_css_set(cset, cgrp);
+		if (!dst_cset) {
 			ret = -ENOMEM;
-			goto out_put_css_set_refs;
+			goto out_release_tset;
 		}
+
+		if (list_empty(&dst_cset->mg_node))
+			list_add(&dst_cset->mg_node, &tset.dst_csets);
+		else
+			put_css_set(dst_cset, false);
+
+		cset->mg_dst_cset = dst_cset;
 	}
 
 	/*
@@ -1851,12 +1854,17 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *leader,
 	 * failure cases after here, so this is the commit point.
 	 */
 	down_write(&css_set_rwsem);
-	for (i = 0; i < group_size; i++) {
-		tc = flex_array_get(group, i);
-		cgroup_task_migrate(tc->cgrp, tc->task, tc->cset);
+	list_for_each_entry(cset, &tset.src_csets, mg_node) {
+		list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list)
+			cgroup_task_migrate(cset->mg_src_cgrp, task,
+					    cset->mg_dst_cset);
 	}
 	up_write(&css_set_rwsem);
-	/* nothing is sensitive to fork() after this point. */
+
+	/* migration is committed, all target tasks are now on dst_csets */
+	tset.csets = &tset.dst_csets;
+
+	/* nothing is sensitive to fork() after this point */
 
 	/*
 	 * step 4: do subsystem attach callbacks.
@@ -1865,30 +1873,27 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *leader,
 		if (css->ss->attach)
 			css->ss->attach(css, &tset);
 
-	/*
-	 * step 5: success! and cleanup
-	 */
 	ret = 0;
-out_put_css_set_refs:
-	if (ret) {
-		for (i = 0; i < group_size; i++) {
-			tc = flex_array_get(group, i);
-			if (!tc->cset)
-				break;
-			put_css_set(tc->cset, false);
-		}
-	}
+	goto out_release_tset;
+
 out_cancel_attach:
-	if (ret) {
-		for_each_css(css, i, cgrp) {
-			if (css == failed_css)
-				break;
-			if (css->ss->cancel_attach)
-				css->ss->cancel_attach(css, &tset);
-		}
+	for_each_css(css, i, cgrp) {
+		if (css == failed_css)
+			break;
+		if (css->ss->cancel_attach)
+			css->ss->cancel_attach(css, &tset);
 	}
-out_free_group_list:
-	flex_array_free(group);
+out_release_tset:
+	down_write(&css_set_rwsem);
+	list_splice_init(&tset.dst_csets, &tset.src_csets);
+	list_for_each_entry_safe(cset, tmp_cset, &tset.src_csets, mg_node) {
+		list_splice_init(&cset->mg_tasks, &cset->tasks);
+		cset->mg_dst_cset = NULL;
+		cset->mg_src_cgrp = NULL;
+		list_del_init(&cset->mg_node);
+		put_css_set_locked(cset, false);
+	}
+	up_write(&css_set_rwsem);
 	return ret;
 }
 
@@ -3895,6 +3900,8 @@ int __init cgroup_init_early(void)
 	atomic_set(&init_css_set.refcount, 1);
 	INIT_LIST_HEAD(&init_css_set.cgrp_links);
 	INIT_LIST_HEAD(&init_css_set.tasks);
+	INIT_LIST_HEAD(&init_css_set.mg_tasks);
+	INIT_LIST_HEAD(&init_css_set.mg_node);
 	INIT_HLIST_NODE(&init_css_set.hlist);
 	css_set_count = 1;
 	init_cgroup_root(&cgroup_dummy_root);
-- 
cgit v1.2.3


From 1958d2d53dadbb1c9aaf0b37741f13a60098b243 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 25 Feb 2014 10:04:03 -0500
Subject: cgroup: split process / task migration into four steps

Currently, process / task migration is a single operation which may
fail depending on memory pressure or the involved controllers'
->can_attach() callbacks.  One problem with this approach is migration
of multiple targets.  It's impossible to tell whether a given target
will be successfully migrated beforehand and cgroup core can't keep
track of enough states to roll back after intermediate failure.

This is already an issue with cgroup_transfer_tasks().  Also, we're
gonna need multiple target migration for unified hierarchy.

This patch splits migration into four stages -
cgroup_migrate_add_src(), cgroup_migrate_prepare_dst(),
cgroup_migrate() and cgroup_migrate_finish(), where
cgroup_migrate_prepare_dst() performs all the operations which may
fail due to allocation failure without actually migrating the target.

The four separate stages mean that, disregarding ->can_attach()
failures, the success or failure of multi target migration can be
determined before performing any actual migration.  If preparations of
all targets succeed, the whole thing will succeed.  If not, the whole
operation can fail without any side-effect.

Since the previous patch to use css_set->mg_tasks to keep track of
migration targets, the only thing which may need memory allocation
during migration is the target css_sets.  cgroup_migrate_prepare()
pins all source and target css_sets and link them up.  Note that this
can be performed without holding threadgroup_lock even if the target
is a process.  As long as cgroup_mutex is held, no new css_set can be
put into play.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h |   1 +
 kernel/cgroup.c        | 240 +++++++++++++++++++++++++++++++++++++------------
 2 files changed, 182 insertions(+), 59 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 3a1cb265afd6..4829a577c1b9 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -350,6 +350,7 @@ struct css_set {
 	 * List of csets participating in the on-going migration either as
 	 * source or destination.  Protected by cgroup_mutex.
 	 */
+	struct list_head mg_preload_node;
 	struct list_head mg_node;
 
 	/*
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 23e3a8c74bd4..a93f6f1ebc69 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -644,6 +644,7 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 	INIT_LIST_HEAD(&cset->cgrp_links);
 	INIT_LIST_HEAD(&cset->tasks);
 	INIT_LIST_HEAD(&cset->mg_tasks);
+	INIT_LIST_HEAD(&cset->mg_preload_node);
 	INIT_LIST_HEAD(&cset->mg_node);
 	INIT_HLIST_NODE(&cset->hlist);
 
@@ -1755,16 +1756,137 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp,
 }
 
 /**
- * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup
- * @cgrp: the cgroup to attach to
- * @leader: the task or the leader of the threadgroup to be attached
- * @threadgroup: attach the whole threadgroup?
+ * cgroup_migrate_finish - cleanup after attach
+ * @preloaded_csets: list of preloaded css_sets
  *
- * Call holding cgroup_mutex and the group_rwsem of the leader. Will take
- * task_lock of @tsk or each thread in the threadgroup individually in turn.
+ * Undo cgroup_migrate_add_src() and cgroup_migrate_prepare_dst().  See
+ * those functions for details.
  */
-static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *leader,
-			      bool threadgroup)
+static void cgroup_migrate_finish(struct list_head *preloaded_csets)
+{
+	struct css_set *cset, *tmp_cset;
+
+	lockdep_assert_held(&cgroup_mutex);
+
+	down_write(&css_set_rwsem);
+	list_for_each_entry_safe(cset, tmp_cset, preloaded_csets, mg_preload_node) {
+		cset->mg_src_cgrp = NULL;
+		cset->mg_dst_cset = NULL;
+		list_del_init(&cset->mg_preload_node);
+		put_css_set_locked(cset, false);
+	}
+	up_write(&css_set_rwsem);
+}
+
+/**
+ * cgroup_migrate_add_src - add a migration source css_set
+ * @src_cset: the source css_set to add
+ * @dst_cgrp: the destination cgroup
+ * @preloaded_csets: list of preloaded css_sets
+ *
+ * Tasks belonging to @src_cset are about to be migrated to @dst_cgrp.  Pin
+ * @src_cset and add it to @preloaded_csets, which should later be cleaned
+ * up by cgroup_migrate_finish().
+ *
+ * This function may be called without holding threadgroup_lock even if the
+ * target is a process.  Threads may be created and destroyed but as long
+ * as cgroup_mutex is not dropped, no new css_set can be put into play and
+ * the preloaded css_sets are guaranteed to cover all migrations.
+ */
+static void cgroup_migrate_add_src(struct css_set *src_cset,
+				   struct cgroup *dst_cgrp,
+				   struct list_head *preloaded_csets)
+{
+	struct cgroup *src_cgrp;
+
+	lockdep_assert_held(&cgroup_mutex);
+	lockdep_assert_held(&css_set_rwsem);
+
+	src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root);
+
+	/* nothing to do if this cset already belongs to the cgroup */
+	if (src_cgrp == dst_cgrp)
+		return;
+
+	if (!list_empty(&src_cset->mg_preload_node))
+		return;
+
+	WARN_ON(src_cset->mg_src_cgrp);
+	WARN_ON(!list_empty(&src_cset->mg_tasks));
+	WARN_ON(!list_empty(&src_cset->mg_node));
+
+	src_cset->mg_src_cgrp = src_cgrp;
+	get_css_set(src_cset);
+	list_add(&src_cset->mg_preload_node, preloaded_csets);
+}
+
+/**
+ * cgroup_migrate_prepare_dst - prepare destination css_sets for migration
+ * @dst_cgrp: the destination cgroup
+ * @preloaded_csets: list of preloaded source css_sets
+ *
+ * Tasks are about to be moved to @dst_cgrp and all the source css_sets
+ * have been preloaded to @preloaded_csets.  This function looks up and
+ * pins all destination css_sets, links each to its source, and put them on
+ * @preloaded_csets.
+ *
+ * This function must be called after cgroup_migrate_add_src() has been
+ * called on each migration source css_set.  After migration is performed
+ * using cgroup_migrate(), cgroup_migrate_finish() must be called on
+ * @preloaded_csets.
+ */
+static int cgroup_migrate_prepare_dst(struct cgroup *dst_cgrp,
+				      struct list_head *preloaded_csets)
+{
+	LIST_HEAD(csets);
+	struct css_set *src_cset;
+
+	lockdep_assert_held(&cgroup_mutex);
+
+	/* look up the dst cset for each src cset and link it to src */
+	list_for_each_entry(src_cset, preloaded_csets, mg_preload_node) {
+		struct css_set *dst_cset;
+
+		dst_cset = find_css_set(src_cset, dst_cgrp);
+		if (!dst_cset)
+			goto err;
+
+		WARN_ON_ONCE(src_cset->mg_dst_cset || dst_cset->mg_dst_cset);
+		src_cset->mg_dst_cset = dst_cset;
+
+		if (list_empty(&dst_cset->mg_preload_node))
+			list_add(&dst_cset->mg_preload_node, &csets);
+		else
+			put_css_set(dst_cset, false);
+	}
+
+	list_splice(&csets, preloaded_csets);
+	return 0;
+err:
+	cgroup_migrate_finish(&csets);
+	return -ENOMEM;
+}
+
+/**
+ * cgroup_migrate - migrate a process or task to a cgroup
+ * @cgrp: the destination cgroup
+ * @leader: the leader of the process or the task to migrate
+ * @threadgroup: whether @leader points to the whole process or a single task
+ *
+ * Migrate a process or task denoted by @leader to @cgrp.  If migrating a
+ * process, the caller must be holding threadgroup_lock of @leader.  The
+ * caller is also responsible for invoking cgroup_migrate_add_src() and
+ * cgroup_migrate_prepare_dst() on the targets before invoking this
+ * function and following up with cgroup_migrate_finish().
+ *
+ * As long as a controller's ->can_attach() doesn't fail, this function is
+ * guaranteed to succeed.  This means that, excluding ->can_attach()
+ * failure, when migrating multiple targets, the success or failure can be
+ * decided for all targets by invoking group_migrate_prepare_dst() before
+ * actually starting migrating.
+ */
+static int cgroup_migrate(struct cgroup *cgrp, struct task_struct *leader,
+			  bool threadgroup)
 {
 	struct cgroup_taskset tset = {
 		.src_csets	= LIST_HEAD_INIT(tset.src_csets),
@@ -1785,29 +1907,17 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *leader,
 	rcu_read_lock();
 	task = leader;
 	do {
-		struct cgroup *src_cgrp;
-
 		/* @task either already exited or can't exit until the end */
 		if (task->flags & PF_EXITING)
 			goto next;
 
 		cset = task_css_set(task);
-		src_cgrp = task_cgroup_from_root(task, cgrp->root);
-
-		/* nothing to do if this task is already in the cgroup */
-		if (src_cgrp == cgrp)
+		if (!cset->mg_src_cgrp)
 			goto next;
 
-		if (!cset->mg_src_cgrp) {
-			WARN_ON(!list_empty(&cset->mg_tasks));
-			WARN_ON(!list_empty(&cset->mg_node));
-
-			cset->mg_src_cgrp = src_cgrp;
-			list_add(&cset->mg_node, &tset.src_csets);
-			get_css_set(cset);
-		}
-
 		list_move(&task->cg_list, &cset->mg_tasks);
+		list_move(&cset->mg_node, &tset.src_csets);
+		list_move(&cset->mg_dst_cset->mg_node, &tset.dst_csets);
 	next:
 		if (!threadgroup)
 			break;
@@ -1819,9 +1929,7 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *leader,
 	if (list_empty(&tset.src_csets))
 		return 0;
 
-	/*
-	 * step 1: check that we can legitimately attach to the cgroup.
-	 */
+	/* check that we can legitimately attach to the cgroup */
 	for_each_css(css, i, cgrp) {
 		if (css->ss->can_attach) {
 			ret = css->ss->can_attach(css, &tset);
@@ -1833,30 +1941,9 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *leader,
 	}
 
 	/*
-	 * step 2: make sure css_sets exist for all threads to be migrated.
-	 * we use find_css_set, which allocates a new one if necessary.
-	 */
-	list_for_each_entry(cset, &tset.src_csets, mg_node) {
-		struct css_set *dst_cset;
-
-		dst_cset = find_css_set(cset, cgrp);
-		if (!dst_cset) {
-			ret = -ENOMEM;
-			goto out_release_tset;
-		}
-
-		if (list_empty(&dst_cset->mg_node))
-			list_add(&dst_cset->mg_node, &tset.dst_csets);
-		else
-			put_css_set(dst_cset, false);
-
-		cset->mg_dst_cset = dst_cset;
-	}
-
-	/*
-	 * step 3: now that we're guaranteed success wrt the css_sets,
-	 * proceed to move all tasks to the new cgroup.  There are no
-	 * failure cases after here, so this is the commit point.
+	 * Now that we're guaranteed success, proceed to move all tasks to
+	 * the new cgroup.  There are no failure cases after here, so this
+	 * is the commit point.
 	 */
 	down_write(&css_set_rwsem);
 	list_for_each_entry(cset, &tset.src_csets, mg_node) {
@@ -1866,14 +1953,13 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *leader,
 	}
 	up_write(&css_set_rwsem);
 
-	/* migration is committed, all target tasks are now on dst_csets */
-	tset.csets = &tset.dst_csets;
-
-	/* nothing is sensitive to fork() after this point */
-
 	/*
-	 * step 4: do subsystem attach callbacks.
+	 * Migration is committed, all target tasks are now on dst_csets.
+	 * Nothing is sensitive to fork() after this point.  Notify
+	 * controllers that migration is complete.
 	 */
+	tset.csets = &tset.dst_csets;
+
 	for_each_css(css, i, cgrp)
 		if (css->ss->attach)
 			css->ss->attach(css, &tset);
@@ -1893,15 +1979,50 @@ out_release_tset:
 	list_splice_init(&tset.dst_csets, &tset.src_csets);
 	list_for_each_entry_safe(cset, tmp_cset, &tset.src_csets, mg_node) {
 		list_splice_init(&cset->mg_tasks, &cset->tasks);
-		cset->mg_dst_cset = NULL;
-		cset->mg_src_cgrp = NULL;
 		list_del_init(&cset->mg_node);
-		put_css_set_locked(cset, false);
 	}
 	up_write(&css_set_rwsem);
 	return ret;
 }
 
+/**
+ * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup
+ * @dst_cgrp: the cgroup to attach to
+ * @leader: the task or the leader of the threadgroup to be attached
+ * @threadgroup: attach the whole threadgroup?
+ *
+ * Call holding cgroup_mutex and the group_rwsem of the leader. Will take
+ * task_lock of @tsk or each thread in the threadgroup individually in turn.
+ */
+static int cgroup_attach_task(struct cgroup *dst_cgrp,
+			      struct task_struct *leader, bool threadgroup)
+{
+	LIST_HEAD(preloaded_csets);
+	struct task_struct *task;
+	int ret;
+
+	/* look up all src csets */
+	down_read(&css_set_rwsem);
+	rcu_read_lock();
+	task = leader;
+	do {
+		cgroup_migrate_add_src(task_css_set(task), dst_cgrp,
+				       &preloaded_csets);
+		if (!threadgroup)
+			break;
+	} while_each_thread(leader, task);
+	rcu_read_unlock();
+	up_read(&css_set_rwsem);
+
+	/* prepare dst csets and commit */
+	ret = cgroup_migrate_prepare_dst(dst_cgrp, &preloaded_csets);
+	if (!ret)
+		ret = cgroup_migrate(dst_cgrp, leader, threadgroup);
+
+	cgroup_migrate_finish(&preloaded_csets);
+	return ret;
+}
+
 /*
  * Find the task_struct of the task to attach by vpid and pass it along to the
  * function to attach either it or all tasks in its threadgroup. Will lock
@@ -3906,6 +4027,7 @@ int __init cgroup_init_early(void)
 	INIT_LIST_HEAD(&init_css_set.cgrp_links);
 	INIT_LIST_HEAD(&init_css_set.tasks);
 	INIT_LIST_HEAD(&init_css_set.mg_tasks);
+	INIT_LIST_HEAD(&init_css_set.mg_preload_node);
 	INIT_LIST_HEAD(&init_css_set.mg_node);
 	INIT_HLIST_NODE(&init_css_set.hlist);
 	css_set_count = 1;
-- 
cgit v1.2.3


From 0e1d768f1b1873272ec4e8dc1482bb5281855017 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 25 Feb 2014 10:04:03 -0500
Subject: cgroup: drop task_lock() protection around task->cgroups

For optimization, task_lock() is additionally used to protect
task->cgroups.  The optimization is pretty dubious as either
css_set_rwsem is grabbed anyway or PF_EXITING already protects
task->cgroups.  It adds only overhead and confusion at this point.
Let's drop task_[un]lock() and update comments accordingly.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h |  6 ++--
 kernel/cgroup.c        | 97 +++++++++++++-------------------------------------
 2 files changed, 28 insertions(+), 75 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 4829a577c1b9..acbb9a4cb6e9 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -658,10 +658,12 @@ struct cgroup_subsys_state *css_parent(struct cgroup_subsys_state *css)
  */
 #ifdef CONFIG_PROVE_RCU
 extern struct mutex cgroup_mutex;
+extern struct rw_semaphore css_set_rwsem;
 #define task_css_set_check(task, __c)					\
 	rcu_dereference_check((task)->cgroups,				\
-		lockdep_is_held(&(task)->alloc_lock) ||			\
-		lockdep_is_held(&cgroup_mutex) || (__c))
+		lockdep_is_held(&cgroup_mutex) ||			\
+		lockdep_is_held(&css_set_rwsem) ||			\
+		((task)->flags & PF_EXITING) || (__c))
 #else
 #define task_css_set_check(task, __c)					\
 	rcu_dereference((task)->cgroups)
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index fa0567f4eedd..f783af900208 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -80,12 +80,21 @@ static DEFINE_MUTEX(cgroup_tree_mutex);
 /*
  * cgroup_mutex is the master lock.  Any modification to cgroup or its
  * hierarchy must be performed while holding it.
+ *
+ * css_set_rwsem protects task->cgroups pointer, the list of css_set
+ * objects, and the chain of tasks off each css_set.
+ *
+ * These locks are exported if CONFIG_PROVE_RCU so that accessors in
+ * cgroup.h can use them for lockdep annotations.
  */
 #ifdef CONFIG_PROVE_RCU
 DEFINE_MUTEX(cgroup_mutex);
-EXPORT_SYMBOL_GPL(cgroup_mutex);	/* only for lockdep */
+DECLARE_RWSEM(css_set_rwsem);
+EXPORT_SYMBOL_GPL(cgroup_mutex);
+EXPORT_SYMBOL_GPL(css_set_rwsem);
 #else
 static DEFINE_MUTEX(cgroup_mutex);
+static DECLARE_RWSEM(css_set_rwsem);
 #endif
 
 /*
@@ -338,12 +347,6 @@ struct cgrp_cset_link {
 
 static struct css_set init_css_set;
 static struct cgrp_cset_link init_cgrp_cset_link;
-
-/*
- * css_set_rwsem protects the list of css_set objects, and the chain of
- * tasks off each css_set.
- */
-static DECLARE_RWSEM(css_set_rwsem);
 static int css_set_count;
 
 /*
@@ -803,10 +806,6 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task,
 }
 
 /*
- * There is one global cgroup mutex. We also require taking
- * task_lock() when dereferencing a task's cgroup subsys pointers.
- * See "The task_lock() exception", at the end of this comment.
- *
  * A task must hold cgroup_mutex to modify cgroups.
  *
  * Any task can increment and decrement the count field without lock.
@@ -836,18 +835,6 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task,
  * always has either children cgroups and/or using tasks.  So we don't
  * need a special hack to ensure that top_cgroup cannot be deleted.
  *
- *	The task_lock() exception
- *
- * The need for this exception arises from the action of
- * cgroup_attach_task(), which overwrites one task's cgroup pointer with
- * another.  It does so using cgroup_mutex, however there are
- * several performance critical places that need to reference
- * task->cgroup without the expense of grabbing a system global
- * mutex.  Therefore except as noted below, when dereferencing or, as
- * in cgroup_attach_task(), modifying a task's cgroup pointer we use
- * task_lock(), which acts on a spinlock (task->alloc_lock) already in
- * the task_struct routinely used for such matters.
- *
  * P.S.  One more locking exception.  RCU is used to guard the
  * update of a tasks cgroup pointer by cgroup_attach_task()
  */
@@ -1329,8 +1316,6 @@ static void cgroup_enable_task_cg_lists(void)
 	 */
 	read_lock(&tasklist_lock);
 	do_each_thread(g, p) {
-		task_lock(p);
-
 		WARN_ON_ONCE(!list_empty(&p->cg_list) ||
 			     task_css_set(p) != &init_css_set);
 
@@ -1349,8 +1334,6 @@ static void cgroup_enable_task_cg_lists(void)
 			get_css_set(cset);
 		}
 		spin_unlock_irq(&p->sighand->siglock);
-
-		task_unlock(p);
 	} while_each_thread(g, p);
 	read_unlock(&tasklist_lock);
 out_unlock:
@@ -1743,11 +1726,7 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp,
 	old_cset = task_css_set(tsk);
 
 	get_css_set(new_cset);
-
-	task_lock(tsk);
 	rcu_assign_pointer(tsk->cgroups, new_cset);
-	task_unlock(tsk);
-
 	list_move(&tsk->cg_list, &new_cset->mg_tasks);
 
 	/*
@@ -1999,8 +1978,7 @@ out_release_tset:
  * @leader: the task or the leader of the threadgroup to be attached
  * @threadgroup: attach the whole threadgroup?
  *
- * Call holding cgroup_mutex and the group_rwsem of the leader. Will take
- * task_lock of @tsk or each thread in the threadgroup individually in turn.
+ * Call holding cgroup_mutex and threadgroup_lock of @leader.
  */
 static int cgroup_attach_task(struct cgroup *dst_cgrp,
 			      struct task_struct *leader, bool threadgroup)
@@ -2034,7 +2012,7 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp,
 /*
  * Find the task_struct of the task to attach by vpid and pass it along to the
  * function to attach either it or all tasks in its threadgroup. Will lock
- * cgroup_mutex and threadgroup; may take task_lock of task.
+ * cgroup_mutex and threadgroup.
  */
 static int attach_task_by_pid(struct cgroup *cgrp, u64 pid, bool threadgroup)
 {
@@ -4155,12 +4133,6 @@ core_initcall(cgroup_wq_init);
  * proc_cgroup_show()
  *  - Print task's cgroup paths into seq_file, one line for each hierarchy
  *  - Used for /proc/<pid>/cgroup.
- *  - No need to task_lock(tsk) on this tsk->cgroup reference, as it
- *    doesn't really matter if tsk->cgroup changes after we read it,
- *    and we take cgroup_mutex, keeping cgroup_attach_task() from changing it
- *    anyway.  No need to check that tsk->cgroup != NULL, thanks to
- *    the_top_cgroup_hack in cgroup_exit(), which sets an exiting tasks
- *    cgroup to top_cgroup.
  */
 
 /* TODO: Use a proper seq_file iterator */
@@ -4310,15 +4282,12 @@ void cgroup_post_fork(struct task_struct *child)
 		struct css_set *cset;
 
 		down_write(&css_set_rwsem);
-		cset = task_css_set_check(current,
-					  lockdep_is_held(&css_set_rwsem));
-		task_lock(child);
+		cset = task_css_set(current);
 		if (list_empty(&child->cg_list)) {
 			rcu_assign_pointer(child->cgroups, cset);
 			list_add(&child->cg_list, &cset->tasks);
 			get_css_set(cset);
 		}
-		task_unlock(child);
 		up_write(&css_set_rwsem);
 	}
 
@@ -4347,27 +4316,13 @@ void cgroup_post_fork(struct task_struct *child)
  * use notify_on_release cgroups where very high task exit scaling
  * is required on large systems.
  *
- * the_top_cgroup_hack:
- *
- *    Set the exiting tasks cgroup to the root cgroup (top_cgroup).
- *
- *    We call cgroup_exit() while the task is still competent to
- *    handle notify_on_release(), then leave the task attached to the
- *    root cgroup in each hierarchy for the remainder of its exit.
- *
- *    To do this properly, we would increment the reference count on
- *    top_cgroup, and near the very end of the kernel/exit.c do_exit()
- *    code we would add a second cgroup function call, to drop that
- *    reference.  This would just create an unnecessary hot spot on
- *    the top_cgroup reference count, to no avail.
- *
- *    Normally, holding a reference to a cgroup without bumping its
- *    count is unsafe.   The cgroup could go away, or someone could
- *    attach us to a different cgroup, decrementing the count on
- *    the first cgroup that we never incremented.  But in this case,
- *    top_cgroup isn't going away, and either task has PF_EXITING set,
- *    which wards off any cgroup_attach_task() attempts, or task is a failed
- *    fork, never visible to cgroup_attach_task.
+ * We set the exiting tasks cgroup to the root cgroup (top_cgroup).  We
+ * call cgroup_exit() while the task is still competent to handle
+ * notify_on_release(), then leave the task attached to the root cgroup in
+ * each hierarchy for the remainder of its exit.  No need to bother with
+ * init_css_set refcnting.  init_css_set never goes away and we can't race
+ * with migration path - either PF_EXITING is visible to migration path or
+ * @tsk never got on the tasklist.
  */
 void cgroup_exit(struct task_struct *tsk, int run_callbacks)
 {
@@ -4377,20 +4332,17 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
 	int i;
 
 	/*
-	 * Unlink from the css_set task list if necessary.  Optimistically
-	 * check cg_list before taking css_set_rwsem.
+	 * Unlink from @tsk from its css_set.  As migration path can't race
+	 * with us, we can check cg_list without grabbing css_set_rwsem.
 	 */
 	if (!list_empty(&tsk->cg_list)) {
 		down_write(&css_set_rwsem);
-		if (!list_empty(&tsk->cg_list)) {
-			list_del_init(&tsk->cg_list);
-			put_cset = true;
-		}
+		list_del_init(&tsk->cg_list);
 		up_write(&css_set_rwsem);
+		put_cset = true;
 	}
 
 	/* Reassign the task to the init_css_set. */
-	task_lock(tsk);
 	cset = task_css_set(tsk);
 	RCU_INIT_POINTER(tsk->cgroups, &init_css_set);
 
@@ -4405,7 +4357,6 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
 			}
 		}
 	}
-	task_unlock(tsk);
 
 	if (put_cset)
 		put_css_set(cset, true);
-- 
cgit v1.2.3


From 2a5153aaae498f645573a13f60fed8226cc4e865 Mon Sep 17 00:00:00 2001
From: Sachin Kamat <sachin.kamat@linaro.org>
Date: Tue, 25 Feb 2014 15:18:26 +0530
Subject: mmc: msm: Cleanup mmc-msm_sdcc.h header

Commit 1ef21f6343ff ("ARM: msm: move platform_data definitions")
moved the file to the current location but forgot to remove the pointer
to its previous location. Clean it up. While at it also change the header
file protection macros appropriately.

Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Chris Ball <chris@printf.net>
---
 include/linux/platform_data/mmc-msm_sdcc.h | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/mmc-msm_sdcc.h b/include/linux/platform_data/mmc-msm_sdcc.h
index ffcd9e3a6a7e..55aa873c9396 100644
--- a/include/linux/platform_data/mmc-msm_sdcc.h
+++ b/include/linux/platform_data/mmc-msm_sdcc.h
@@ -1,8 +1,5 @@
-/*
- *  arch/arm/include/asm/mach/mmc.h
- */
-#ifndef ASMARM_MACH_MMC_H
-#define ASMARM_MACH_MMC_H
+#ifndef __MMC_MSM_SDCC_H
+#define __MMC_MSM_SDCC_H
 
 #include <linux/mmc/host.h>
 #include <linux/mmc/card.h>
-- 
cgit v1.2.3


From 550459eeb21b8f3553283d506fdcb92c9147c1eb Mon Sep 17 00:00:00 2001
From: Sachin Kamat <sachin.kamat@linaro.org>
Date: Tue, 25 Feb 2014 15:18:27 +0530
Subject: mmc: mvsdio: Cleanup mmc-mvsdio.h header

Commit c02cecb92ed4 ("ARM: orion: move platform_data definitions")
moved the file to the current location but forgot to remove the pointer
to its previous location. Clean it up. While at it also change the header
file protection macros appropriately.

Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Chris Ball <chris@printf.net>
---
 include/linux/platform_data/mmc-mvsdio.h | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/mmc-mvsdio.h b/include/linux/platform_data/mmc-mvsdio.h
index 1190efedcb94..d02704cd3695 100644
--- a/include/linux/platform_data/mmc-mvsdio.h
+++ b/include/linux/platform_data/mmc-mvsdio.h
@@ -1,13 +1,11 @@
 /*
- * arch/arm/plat-orion/include/plat/mvsdio.h
- *
  * This file is licensed under the terms of the GNU General Public
  * License version 2.  This program is licensed "as is" without any
  * warranty of any kind, whether express or implied.
  */
 
-#ifndef __MACH_MVSDIO_H
-#define __MACH_MVSDIO_H
+#ifndef __MMC_MVSDIO_H
+#define __MMC_MVSDIO_H
 
 #include <linux/mbus.h>
 
-- 
cgit v1.2.3


From f7e2cec02b0e5bfe2180f09de9b0bc724774c51a Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Date: Tue, 25 Feb 2014 13:45:49 +0000
Subject: regmap: Mark reg_defaults in regmap_multi_reg_write as const

There should be no need for the writes supplied to this function to be
edited by it so mark them as const.

Signed-off-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/base/regmap/regmap.c | 4 ++--
 include/linux/regmap.h       | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 6e19560c7a5b..1e3934aea56a 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -1592,8 +1592,8 @@ EXPORT_SYMBOL_GPL(regmap_bulk_write);
  * A value of zero will be returned on success, a negative errno will
  * be returned in error cases.
  */
-int regmap_multi_reg_write(struct regmap *map, struct reg_default *regs,
-				int num_regs)
+int regmap_multi_reg_write(struct regmap *map, const struct reg_default *regs,
+			   int num_regs)
 {
 	int ret = 0, i;
 
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 4149f1a9b003..e97ac6c8b7be 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -386,7 +386,7 @@ int regmap_raw_write(struct regmap *map, unsigned int reg,
 		     const void *val, size_t val_len);
 int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val,
 			size_t val_count);
-int regmap_multi_reg_write(struct regmap *map, struct reg_default *regs,
+int regmap_multi_reg_write(struct regmap *map, const struct reg_default *regs,
 			int num_regs);
 int regmap_raw_write_async(struct regmap *map, unsigned int reg,
 			   const void *val, size_t val_len);
-- 
cgit v1.2.3


From 1d5b40bccf04994248b39e8ce234a7c1f3235cf5 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Date: Tue, 25 Feb 2014 13:45:50 +0000
Subject: regmap: Add bypassed version of regmap_multi_reg_write

Devices with more complex boot proceedures may occasionally apply the
register patch manual. regmap_multi_reg_write is a logical way to do so,
however the patch must be applied with cache bypass on, such that it
doesn't override any user settings. This patch adds a
regmap_multi_reg_write_bypassed function that applies a set of writes
with the bypass enabled.

Signed-off-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/base/regmap/regmap.c | 75 ++++++++++++++++++++++++++++++++++++--------
 include/linux/regmap.h       |  3 ++
 2 files changed, 65 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 1e3934aea56a..e6a2c29c0be4 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -1576,6 +1576,26 @@ out:
 }
 EXPORT_SYMBOL_GPL(regmap_bulk_write);
 
+static int _regmap_multi_reg_write(struct regmap *map,
+				   const struct reg_default *regs,
+				   int num_regs)
+{
+	int i, ret;
+
+	for (i = 0; i < num_regs; i++) {
+		if (regs[i].reg % map->reg_stride)
+			return -EINVAL;
+		ret = _regmap_write(map, regs[i].reg, regs[i].def);
+		if (ret != 0) {
+			dev_err(map->dev, "Failed to write %x = %x: %d\n",
+				regs[i].reg, regs[i].def, ret);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
 /*
  * regmap_multi_reg_write(): Write multiple registers to the device
  *
@@ -1595,28 +1615,57 @@ EXPORT_SYMBOL_GPL(regmap_bulk_write);
 int regmap_multi_reg_write(struct regmap *map, const struct reg_default *regs,
 			   int num_regs)
 {
-	int ret = 0, i;
-
-	for (i = 0; i < num_regs; i++) {
-		int reg = regs[i].reg;
-		if (reg % map->reg_stride)
-			return -EINVAL;
-	}
+	int ret;
 
 	map->lock(map->lock_arg);
 
-	for (i = 0; i < num_regs; i++) {
-		ret = _regmap_write(map, regs[i].reg, regs[i].def);
-		if (ret != 0)
-			goto out;
-	}
-out:
+	ret = _regmap_multi_reg_write(map, regs, num_regs);
+
 	map->unlock(map->lock_arg);
 
 	return ret;
 }
 EXPORT_SYMBOL_GPL(regmap_multi_reg_write);
 
+/*
+ * regmap_multi_reg_write_bypassed(): Write multiple registers to the
+ *                                    device but not the cache
+ *
+ * where the set of register are supplied in any order
+ *
+ * @map: Register map to write to
+ * @regs: Array of structures containing register,value to be written
+ * @num_regs: Number of registers to write
+ *
+ * This function is intended to be used for writing a large block of data
+ * atomically to the device in single transfer for those I2C client devices
+ * that implement this alternative block write mode.
+ *
+ * A value of zero will be returned on success, a negative errno will
+ * be returned in error cases.
+ */
+int regmap_multi_reg_write_bypassed(struct regmap *map,
+				    const struct reg_default *regs,
+				    int num_regs)
+{
+	int ret;
+	bool bypass;
+
+	map->lock(map->lock_arg);
+
+	bypass = map->cache_bypass;
+	map->cache_bypass = true;
+
+	ret = _regmap_multi_reg_write(map, regs, num_regs);
+
+	map->cache_bypass = bypass;
+
+	map->unlock(map->lock_arg);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(regmap_multi_reg_write_bypassed);
+
 /**
  * regmap_raw_write_async(): Write raw values to one or more registers
  *                           asynchronously
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index e97ac6c8b7be..ca2272fbd014 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -388,6 +388,9 @@ int regmap_bulk_write(struct regmap *map, unsigned int reg, const void *val,
 			size_t val_count);
 int regmap_multi_reg_write(struct regmap *map, const struct reg_default *regs,
 			int num_regs);
+int regmap_multi_reg_write_bypassed(struct regmap *map,
+				    const struct reg_default *regs,
+				    int num_regs);
 int regmap_raw_write_async(struct regmap *map, unsigned int reg,
 			   const void *val, size_t val_len);
 int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val);
-- 
cgit v1.2.3


From 88d7ab8949427f492c39f6daf0ac67f0242a88bc Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Wed, 26 Feb 2014 11:38:39 -0700
Subject: vfio: Add external user check extension interface

This lets us check extensions, particularly VFIO_DMA_CC_IOMMU using
the external user interface, allowing KVM to probe IOMMU coherency.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/vfio.c  | 6 ++++++
 include/linux/vfio.h | 2 ++
 2 files changed, 8 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 21271d8df023..512f479d8a50 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -1413,6 +1413,12 @@ int vfio_external_user_iommu_id(struct vfio_group *group)
 }
 EXPORT_SYMBOL_GPL(vfio_external_user_iommu_id);
 
+long vfio_external_check_extension(struct vfio_group *group, unsigned long arg)
+{
+	return vfio_ioctl_check_extension(group->container, arg);
+}
+EXPORT_SYMBOL_GPL(vfio_external_check_extension);
+
 /**
  * Module/class support
  */
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 24579a0312a0..81022a52bc34 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -96,5 +96,7 @@ extern void vfio_unregister_iommu_driver(
 extern struct vfio_group *vfio_group_get_external_user(struct file *filep);
 extern void vfio_group_put_external_user(struct vfio_group *group);
 extern int vfio_external_user_iommu_id(struct vfio_group *group);
+extern long vfio_external_check_extension(struct vfio_group *group,
+					  unsigned long arg);
 
 #endif /* VFIO_H */
-- 
cgit v1.2.3


From 3f85944fe207d0225ef21a2c0951d4946fc9a95d Mon Sep 17 00:00:00 2001
From: Amir Vadai <amirv@mellanox.com>
Date: Tue, 25 Feb 2014 18:17:50 +0200
Subject: net: Add sysfs file for port number

Add a sysfs file to enable user space to query the device
port number used by a netdevice instance. This is needed for
devices that have multiple ports on the same PCI function.

Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 4 ++++
 net/core/net-sysfs.c      | 2 ++
 2 files changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5e4756553c18..5e84483c0650 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1279,6 +1279,10 @@ struct net_device {
 						 * that share the same link
 						 * layer address
 						 */
+	unsigned short          dev_port;	/* Used to differentiate
+						 * devices that share the same
+						 * function
+						 */
 	spinlock_t		addr_list_lock;
 	struct netdev_hw_addr_list	uc;	/* Unicast mac addresses */
 	struct netdev_hw_addr_list	mc;	/* Multicast mac addresses */
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 73aa594674ef..daed9a64c6f6 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -104,6 +104,7 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr,
 }
 
 NETDEVICE_SHOW_RO(dev_id, fmt_hex);
+NETDEVICE_SHOW_RO(dev_port, fmt_dec);
 NETDEVICE_SHOW_RO(addr_assign_type, fmt_dec);
 NETDEVICE_SHOW_RO(addr_len, fmt_dec);
 NETDEVICE_SHOW_RO(iflink, fmt_dec);
@@ -373,6 +374,7 @@ static struct attribute *net_class_attrs[] = {
 	&dev_attr_netdev_group.attr,
 	&dev_attr_type.attr,
 	&dev_attr_dev_id.attr,
+	&dev_attr_dev_port.attr,
 	&dev_attr_iflink.attr,
 	&dev_attr_ifindex.attr,
 	&dev_attr_addr_assign_type.attr,
-- 
cgit v1.2.3


From 5edb93b89f6cc3089ee283656555e7a9ad36a8a0 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Tue, 4 Feb 2014 19:32:28 -0800
Subject: resource: Add resource_contains()

We have two identical copies of resource_contains() already, and more
places that could use it.  This moves it to ioport.h where it can be
shared.

resource_contains(struct resource *r1, struct resource *r2) returns true
iff r1 and r2 are the same type (most callers already checked this
separately) and the r1 address range completely contains r2.

In addition, the new resource_contains() checks that both r1 and r2 have
addresses assigned to them.  If a resource is IORESOURCE_UNSET, it doesn't
have a valid address and can't contain or be contained by another resource.
Some callers already check this or for res->start.

No functional change.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/host-bridge.c |  8 --------
 include/linux/ioport.h    | 10 ++++++++++
 kernel/resource.c         |  8 ++------
 3 files changed, 12 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pci/host-bridge.c b/drivers/pci/host-bridge.c
index 06ace6248c61..47aaf22d814e 100644
--- a/drivers/pci/host-bridge.c
+++ b/drivers/pci/host-bridge.c
@@ -32,11 +32,6 @@ void pci_set_host_bridge_release(struct pci_host_bridge *bridge,
 	bridge->release_data = release_data;
 }
 
-static bool resource_contains(struct resource *res1, struct resource *res2)
-{
-	return res1->start <= res2->start && res1->end >= res2->end;
-}
-
 void pcibios_resource_to_bus(struct pci_bus *bus, struct pci_bus_region *region,
 			     struct resource *res)
 {
@@ -45,9 +40,6 @@ void pcibios_resource_to_bus(struct pci_bus *bus, struct pci_bus_region *region,
 	resource_size_t offset = 0;
 
 	list_for_each_entry(window, &bridge->windows, list) {
-		if (resource_type(res) != resource_type(window->res))
-			continue;
-
 		if (resource_contains(window->res, res)) {
 			offset = window->offset;
 			break;
diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 89b7c24a36e9..9fcaac8bc4f6 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -169,6 +169,16 @@ static inline unsigned long resource_type(const struct resource *res)
 {
 	return res->flags & IORESOURCE_TYPE_BITS;
 }
+/* True iff r1 completely contains r2 */
+static inline bool resource_contains(struct resource *r1, struct resource *r2)
+{
+	if (resource_type(r1) != resource_type(r2))
+		return false;
+	if (r1->flags & IORESOURCE_UNSET || r2->flags & IORESOURCE_UNSET)
+		return false;
+	return r1->start <= r2->start && r1->end >= r2->end;
+}
+
 
 /* Convenience shorthand with allocation */
 #define request_region(start,n,name)		__request_region(&ioport_resource, (start), (n), (name), 0)
diff --git a/kernel/resource.c b/kernel/resource.c
index 3f285dce9347..a8344dda7049 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -432,11 +432,6 @@ static void resource_clip(struct resource *res, resource_size_t min,
 		res->end = max;
 }
 
-static bool resource_contains(struct resource *res1, struct resource *res2)
-{
-	return res1->start <= res2->start && res1->end >= res2->end;
-}
-
 /*
  * Find empty slot in the resource tree with the given range and
  * alignment constraints
@@ -471,10 +466,11 @@ static int __find_resource(struct resource *root, struct resource *old,
 		arch_remove_reservations(&tmp);
 
 		/* Check for overflow after ALIGN() */
-		avail = *new;
 		avail.start = ALIGN(tmp.start, constraint->align);
 		avail.end = tmp.end;
+		avail.flags = new->flags & ~IORESOURCE_UNSET;
 		if (avail.start >= tmp.start) {
+			alloc.flags = avail.flags;
 			alloc.start = constraint->alignf(constraint->alignf_data, &avail,
 					size, constraint->align);
 			alloc.end = alloc.start + size - 1;
-- 
cgit v1.2.3


From d19cb803a2ff85d1b64b9628e1aec2aa76a9260b Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Wed, 26 Feb 2014 11:25:56 -0700
Subject: vsprintf: Add support for IORESOURCE_UNSET in %pR

Sometimes we have a struct resource where we know the type (MEM/IO/etc.)
and the size, but we haven't assigned address space for it.  The
IORESOURCE_UNSET flag is a way to indicate this situation.  For these
"unset" resources, the start address is meaningless, so print only the
size, e.g.,

  - pci 0000:0c:00.0: reg 184: [mem 0x00000000-0x00001fff 64bit]
  + pci 0000:0c:00.0: reg 184: [mem size 0x2000 64bit]

For %pr (printing with raw flags), we still print the address range,
because %pr is mostly used for debugging anyway.

Thanks to Fengguang Wu <fengguang.wu@intel.com> for suggesting
resource_size().

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 include/linux/ioport.h |  2 +-
 lib/vsprintf.c         | 13 +++++++++----
 2 files changed, 10 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 9fcaac8bc4f6..5e3a906cc089 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -51,7 +51,7 @@ struct resource {
 
 #define IORESOURCE_EXCLUSIVE	0x08000000	/* Userland may not map this resource */
 #define IORESOURCE_DISABLED	0x10000000
-#define IORESOURCE_UNSET	0x20000000
+#define IORESOURCE_UNSET	0x20000000	/* No address assigned yet */
 #define IORESOURCE_AUTO		0x40000000
 #define IORESOURCE_BUSY		0x80000000	/* Driver has marked this resource busy */
 
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 185b6d300ebc..5e2cf6f342f8 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -719,10 +719,15 @@ char *resource_string(char *buf, char *end, struct resource *res,
 		specp = &mem_spec;
 		decode = 0;
 	}
-	p = number(p, pend, res->start, *specp);
-	if (res->start != res->end) {
-		*p++ = '-';
-		p = number(p, pend, res->end, *specp);
+	if (decode && res->flags & IORESOURCE_UNSET) {
+		p = string(p, pend, "size ", str_spec);
+		p = number(p, pend, resource_size(res), *specp);
+	} else {
+		p = number(p, pend, res->start, *specp);
+		if (res->start != res->end) {
+			*p++ = '-';
+			p = number(p, pend, res->end, *specp);
+		}
 	}
 	if (decode) {
 		if (res->flags & IORESOURCE_MEM_64)
-- 
cgit v1.2.3


From 363ec392352e55c61ce2799c3f15f89f9429bba7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 26 Feb 2014 14:02:11 -0800
Subject: net: add skb_mstamp infrastructure

ktime_get() is too expensive on some cases, and we'd like to get
usec resolution timestamps in TCP stack.

This patch adds a light weight facility using a combination of
local_clock() and jiffies samples.

Instead of :

        u64 t0, t1;

        t0 = ktime_get();
        // stuff
        t1 = ktime_get();
        delta_us = ktime_us_delta(t1, t0);

use :
        struct skb_mstamp t0, t1;

        skb_mstamp_get(&t0);
        // stuff
        skb_mstamp_get(&t1);
        delta_us = skb_mstamp_us_delta(&t1, &t0);

Note : local_clock() might have a (bounded) drift between cpus.

Do not use this infra in place of ktime_get() without understanding the
issues.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Larry Brakmo <brakmo@google.com>
Cc: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 59 ++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 57 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 11b6925f0e96..6d8ed22accb4 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -32,6 +32,7 @@
 #include <linux/hrtimer.h>
 #include <linux/dma-mapping.h>
 #include <linux/netdev_features.h>
+#include <linux/sched.h>
 #include <net/flow_keys.h>
 
 /* A. Checksumming of received packets by device.
@@ -356,11 +357,62 @@ typedef unsigned int sk_buff_data_t;
 typedef unsigned char *sk_buff_data_t;
 #endif
 
+/**
+ * struct skb_mstamp - multi resolution time stamps
+ * @stamp_us: timestamp in us resolution
+ * @stamp_jiffies: timestamp in jiffies
+ */
+struct skb_mstamp {
+	union {
+		u64		v64;
+		struct {
+			u32	stamp_us;
+			u32	stamp_jiffies;
+		};
+	};
+};
+
+/**
+ * skb_mstamp_get - get current timestamp
+ * @cl: place to store timestamps
+ */
+static inline void skb_mstamp_get(struct skb_mstamp *cl)
+{
+	u64 val = local_clock();
+
+	do_div(val, NSEC_PER_USEC);
+	cl->stamp_us = (u32)val;
+	cl->stamp_jiffies = (u32)jiffies;
+}
+
+/**
+ * skb_mstamp_delta - compute the difference in usec between two skb_mstamp
+ * @t1: pointer to newest sample
+ * @t0: pointer to oldest sample
+ */
+static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1,
+				      const struct skb_mstamp *t0)
+{
+	s32 delta_us = t1->stamp_us - t0->stamp_us;
+	u32 delta_jiffies = t1->stamp_jiffies - t0->stamp_jiffies;
+
+	/* If delta_us is negative, this might be because interval is too big,
+	 * or local_clock() drift is too big : fallback using jiffies.
+	 */
+	if (delta_us <= 0 ||
+	    delta_jiffies >= (INT_MAX / (USEC_PER_SEC / HZ)))
+
+		delta_us = jiffies_to_usecs(delta_jiffies);
+
+	return delta_us;
+}
+
+
 /** 
  *	struct sk_buff - socket buffer
  *	@next: Next buffer in list
  *	@prev: Previous buffer in list
- *	@tstamp: Time we arrived
+ *	@tstamp: Time we arrived/left
  *	@sk: Socket we are owned by
  *	@dev: Device we arrived on/are leaving by
  *	@cb: Control buffer. Free for use by every layer. Put private vars here
@@ -429,7 +481,10 @@ struct sk_buff {
 	struct sk_buff		*next;
 	struct sk_buff		*prev;
 
-	ktime_t			tstamp;
+	union {
+		ktime_t		tstamp;
+		struct skb_mstamp skb_mstamp;
+	};
 
 	struct sock		*sk;
 	struct net_device	*dev;
-- 
cgit v1.2.3


From 740b0f1841f6e39085b711d41db9ffb07198682b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 26 Feb 2014 14:02:48 -0800
Subject: tcp: switch rtt estimations to usec resolution

Upcoming congestion controls for TCP require usec resolution for RTT
estimations. Millisecond resolution is simply not enough these days.

FQ/pacing in DC environments also require this change for finer control
and removal of bimodal behavior due to the current hack in
tcp_update_pacing_rate() for 'small rtt'

TCP_CONG_RTT_STAMP is no longer needed.

As Julian Anastasov pointed out, we need to keep user compatibility :
tcp_metrics used to export RTT and RTTVAR in msec resolution,
so we added RTT_US and RTTVAR_US. An iproute2 patch is needed
to use the new attributes if provided by the kernel.

In this example ss command displays a srtt of 32 usecs (10Gbit link)

lpk51:~# ./ss -i dst lpk52
Netid  State      Recv-Q Send-Q   Local Address:Port       Peer
Address:Port
tcp    ESTAB      0      1         10.246.11.51:42959
10.246.11.52:64614
         cubic wscale:6,6 rto:201 rtt:0.032/0.001 ato:40 mss:1448
cwnd:10 send
3620.0Mbps pacing_rate 7240.0Mbps unacked:1 rcv_rtt:993 rcv_space:29559

Updated iproute2 ip command displays :

lpk51:~# ./ip tcp_metrics | grep 10.246.11.52
10.246.11.52 age 561.914sec cwnd 10 rtt 274us rttvar 213us source
10.246.11.51

Old binary displays :

lpk51:~# ip tcp_metrics | grep 10.246.11.52
10.246.11.52 age 561.914sec cwnd 10 rtt 250us rttvar 125us source
10.246.11.51

With help from Julian Anastasov, Stephen Hemminger and Yuchung Cheng

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Larry Brakmo <brakmo@google.com>
Cc: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h              |   8 +-
 include/net/tcp.h                |  10 ++-
 include/uapi/linux/tcp_metrics.h |   7 +-
 net/ipv4/tcp.c                   |   8 +-
 net/ipv4/tcp_cubic.c             |   4 -
 net/ipv4/tcp_hybla.c             |  12 +--
 net/ipv4/tcp_illinois.c          |   1 -
 net/ipv4/tcp_input.c             | 183 +++++++++++++++++++--------------------
 net/ipv4/tcp_ipv4.c              |   2 +-
 net/ipv4/tcp_lp.c                |   1 -
 net/ipv4/tcp_metrics.c           |  83 ++++++++++--------
 net/ipv4/tcp_minisocks.c         |   4 +-
 net/ipv4/tcp_output.c            |  15 ++--
 net/ipv4/tcp_probe.c             |   2 +-
 net/ipv4/tcp_vegas.c             |   1 -
 net/ipv4/tcp_veno.c              |   1 -
 net/ipv4/tcp_yeah.c              |   1 -
 17 files changed, 174 insertions(+), 169 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 4ad0706d40eb..239946868142 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -201,10 +201,10 @@ struct tcp_sock {
 	u32	tlp_high_seq;	/* snd_nxt at the time of TLP retransmit. */
 
 /* RTT measurement */
-	u32	srtt;		/* smoothed round trip time << 3	*/
-	u32	mdev;		/* medium deviation			*/
-	u32	mdev_max;	/* maximal mdev for the last rtt period	*/
-	u32	rttvar;		/* smoothed mdev_max			*/
+	u32	srtt_us;	/* smoothed round trip time << 3 in usecs */
+	u32	mdev_us;	/* medium deviation			*/
+	u32	mdev_max_us;	/* maximal mdev for the last rtt period	*/
+	u32	rttvar_us;	/* smoothed mdev_max			*/
 	u32	rtt_seq;	/* sequence number to update rttvar	*/
 
 	u32	packets_out;	/* Packets which are "in flight"	*/
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 1f820537741a..93eab0b9da60 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -31,6 +31,7 @@
 #include <linux/crypto.h>
 #include <linux/cryptohash.h>
 #include <linux/kref.h>
+#include <linux/ktime.h>
 
 #include <net/inet_connection_sock.h>
 #include <net/inet_timewait_sock.h>
@@ -478,7 +479,6 @@ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
 struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 			     struct ip_options *opt);
 #ifdef CONFIG_SYN_COOKIES
-#include <linux/ktime.h>
 
 /* Syncookies use a monotonic timer which increments every 64 seconds.
  * This counter is used both as a hash input and partially encoded into
@@ -619,7 +619,7 @@ static inline void tcp_bound_rto(const struct sock *sk)
 
 static inline u32 __tcp_set_rto(const struct tcp_sock *tp)
 {
-	return (tp->srtt >> 3) + tp->rttvar;
+	return usecs_to_jiffies((tp->srtt_us >> 3) + tp->rttvar_us);
 }
 
 static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
@@ -656,6 +656,11 @@ static inline u32 tcp_rto_min(struct sock *sk)
 	return rto_min;
 }
 
+static inline u32 tcp_rto_min_us(struct sock *sk)
+{
+	return jiffies_to_usecs(tcp_rto_min(sk));
+}
+
 /* Compute the actual receive window we are currently advertising.
  * Rcv_nxt can be after the window if our peer push more data
  * than the offered window.
@@ -778,7 +783,6 @@ enum tcp_ca_event {
 #define TCP_CA_BUF_MAX	(TCP_CA_NAME_MAX*TCP_CA_MAX)
 
 #define TCP_CONG_NON_RESTRICTED 0x1
-#define TCP_CONG_RTT_STAMP	0x2
 
 struct tcp_congestion_ops {
 	struct list_head	list;
diff --git a/include/uapi/linux/tcp_metrics.h b/include/uapi/linux/tcp_metrics.h
index 54a37b13f2c4..93533926035c 100644
--- a/include/uapi/linux/tcp_metrics.h
+++ b/include/uapi/linux/tcp_metrics.h
@@ -11,12 +11,15 @@
 #define TCP_METRICS_GENL_VERSION	0x1
 
 enum tcp_metric_index {
-	TCP_METRIC_RTT,
-	TCP_METRIC_RTTVAR,
+	TCP_METRIC_RTT,		/* in ms units */
+	TCP_METRIC_RTTVAR,	/* in ms units */
 	TCP_METRIC_SSTHRESH,
 	TCP_METRIC_CWND,
 	TCP_METRIC_REORDERING,
 
+	TCP_METRIC_RTT_US,	/* in usec units */
+	TCP_METRIC_RTTVAR_US,	/* in usec units */
+
 	/* Always last.  */
 	__TCP_METRIC_MAX,
 };
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bed379c7abcd..7374905b3701 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -387,7 +387,7 @@ void tcp_init_sock(struct sock *sk)
 	INIT_LIST_HEAD(&tp->tsq_node);
 
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
-	tp->mdev = TCP_TIMEOUT_INIT;
+	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 
 	/* So many TCP implementations out there (incorrectly) count the
 	 * initial SYN frame in their delayed-ACK and congestion control
@@ -2339,7 +2339,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 
 	sk->sk_shutdown = 0;
 	sock_reset_flag(sk, SOCK_DONE);
-	tp->srtt = 0;
+	tp->srtt_us = 0;
 	if ((tp->write_seq += tp->max_window + 2) == 0)
 		tp->write_seq = 1;
 	icsk->icsk_backoff = 0;
@@ -2783,8 +2783,8 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info)
 
 	info->tcpi_pmtu = icsk->icsk_pmtu_cookie;
 	info->tcpi_rcv_ssthresh = tp->rcv_ssthresh;
-	info->tcpi_rtt = jiffies_to_usecs(tp->srtt)>>3;
-	info->tcpi_rttvar = jiffies_to_usecs(tp->mdev)>>2;
+	info->tcpi_rtt = tp->srtt_us >> 3;
+	info->tcpi_rttvar = tp->mdev_us >> 2;
 	info->tcpi_snd_ssthresh = tp->snd_ssthresh;
 	info->tcpi_snd_cwnd = tp->snd_cwnd;
 	info->tcpi_advmss = tp->advmss;
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 828e4c3ffbaf..8bf224516ba2 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -476,10 +476,6 @@ static int __init cubictcp_register(void)
 	/* divide by bic_scale and by constant Srtt (100ms) */
 	do_div(cube_factor, bic_scale * 10);
 
-	/* hystart needs ms clock resolution */
-	if (hystart && HZ < 1000)
-		cubictcp.flags |= TCP_CONG_RTT_STAMP;
-
 	return tcp_register_congestion_control(&cubictcp);
 }
 
diff --git a/net/ipv4/tcp_hybla.c b/net/ipv4/tcp_hybla.c
index 2a1a9e2a4e51..a15a799bf768 100644
--- a/net/ipv4/tcp_hybla.c
+++ b/net/ipv4/tcp_hybla.c
@@ -21,7 +21,7 @@ struct hybla {
 	u32   rho2;	      /* Rho * Rho, integer part */
 	u32   rho_3ls;	      /* Rho parameter, <<3 */
 	u32   rho2_7ls;	      /* Rho^2, <<7	*/
-	u32   minrtt;	      /* Minimum smoothed round trip time value seen */
+	u32   minrtt_us;      /* Minimum smoothed round trip time value seen */
 };
 
 /* Hybla reference round trip time (default= 1/40 sec = 25 ms), in ms */
@@ -35,7 +35,9 @@ static inline void hybla_recalc_param (struct sock *sk)
 {
 	struct hybla *ca = inet_csk_ca(sk);
 
-	ca->rho_3ls = max_t(u32, tcp_sk(sk)->srtt / msecs_to_jiffies(rtt0), 8);
+	ca->rho_3ls = max_t(u32,
+			    tcp_sk(sk)->srtt_us / (rtt0 * USEC_PER_MSEC),
+			    8U);
 	ca->rho = ca->rho_3ls >> 3;
 	ca->rho2_7ls = (ca->rho_3ls * ca->rho_3ls) << 1;
 	ca->rho2 = ca->rho2_7ls >> 7;
@@ -59,7 +61,7 @@ static void hybla_init(struct sock *sk)
 	hybla_recalc_param(sk);
 
 	/* set minimum rtt as this is the 1st ever seen */
-	ca->minrtt = tp->srtt;
+	ca->minrtt_us = tp->srtt_us;
 	tp->snd_cwnd = ca->rho;
 }
 
@@ -94,9 +96,9 @@ static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked,
 	int is_slowstart = 0;
 
 	/*  Recalculate rho only if this srtt is the lowest */
-	if (tp->srtt < ca->minrtt){
+	if (tp->srtt_us < ca->minrtt_us) {
 		hybla_recalc_param(sk);
-		ca->minrtt = tp->srtt;
+		ca->minrtt_us = tp->srtt_us;
 	}
 
 	if (!tcp_is_cwnd_limited(sk, in_flight))
diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c
index be047c63ca10..863d105e3015 100644
--- a/net/ipv4/tcp_illinois.c
+++ b/net/ipv4/tcp_illinois.c
@@ -325,7 +325,6 @@ static void tcp_illinois_info(struct sock *sk, u32 ext,
 }
 
 static struct tcp_congestion_ops tcp_illinois __read_mostly = {
-	.flags		= TCP_CONG_RTT_STAMP,
 	.init		= tcp_illinois_init,
 	.ssthresh	= tcp_illinois_ssthresh,
 	.cong_avoid	= tcp_illinois_cong_avoid,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 227cba79fa6b..23a41d978fad 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -667,11 +667,11 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
  * To save cycles in the RFC 1323 implementation it was better to break
  * it up into three procedures. -- erics
  */
-static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt)
+static void tcp_rtt_estimator(struct sock *sk, long mrtt_us)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	long m = mrtt; /* RTT */
-	u32 srtt = tp->srtt;
+	long m = mrtt_us; /* RTT */
+	u32 srtt = tp->srtt_us;
 
 	/*	The following amusing code comes from Jacobson's
 	 *	article in SIGCOMM '88.  Note that rtt and mdev
@@ -694,7 +694,7 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt)
 		srtt += m;		/* rtt = 7/8 rtt + 1/8 new */
 		if (m < 0) {
 			m = -m;		/* m is now abs(error) */
-			m -= (tp->mdev >> 2);   /* similar update on mdev */
+			m -= (tp->mdev_us >> 2);   /* similar update on mdev */
 			/* This is similar to one of Eifel findings.
 			 * Eifel blocks mdev updates when rtt decreases.
 			 * This solution is a bit different: we use finer gain
@@ -706,28 +706,29 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt)
 			if (m > 0)
 				m >>= 3;
 		} else {
-			m -= (tp->mdev >> 2);   /* similar update on mdev */
+			m -= (tp->mdev_us >> 2);   /* similar update on mdev */
 		}
-		tp->mdev += m;	    	/* mdev = 3/4 mdev + 1/4 new */
-		if (tp->mdev > tp->mdev_max) {
-			tp->mdev_max = tp->mdev;
-			if (tp->mdev_max > tp->rttvar)
-				tp->rttvar = tp->mdev_max;
+		tp->mdev_us += m;		/* mdev = 3/4 mdev + 1/4 new */
+		if (tp->mdev_us > tp->mdev_max_us) {
+			tp->mdev_max_us = tp->mdev_us;
+			if (tp->mdev_max_us > tp->rttvar_us)
+				tp->rttvar_us = tp->mdev_max_us;
 		}
 		if (after(tp->snd_una, tp->rtt_seq)) {
-			if (tp->mdev_max < tp->rttvar)
-				tp->rttvar -= (tp->rttvar - tp->mdev_max) >> 2;
+			if (tp->mdev_max_us < tp->rttvar_us)
+				tp->rttvar_us -= (tp->rttvar_us - tp->mdev_max_us) >> 2;
 			tp->rtt_seq = tp->snd_nxt;
-			tp->mdev_max = tcp_rto_min(sk);
+			tp->mdev_max_us = tcp_rto_min_us(sk);
 		}
 	} else {
 		/* no previous measure. */
 		srtt = m << 3;		/* take the measured time to be rtt */
-		tp->mdev = m << 1;	/* make sure rto = 3*rtt */
-		tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk));
+		tp->mdev_us = m << 1;	/* make sure rto = 3*rtt */
+		tp->rttvar_us = max(tp->mdev_us, tcp_rto_min_us(sk));
+		tp->mdev_max_us = tp->rttvar_us;
 		tp->rtt_seq = tp->snd_nxt;
 	}
-	tp->srtt = max(1U, srtt);
+	tp->srtt_us = max(1U, srtt);
 }
 
 /* Set the sk_pacing_rate to allow proper sizing of TSO packets.
@@ -742,20 +743,12 @@ static void tcp_update_pacing_rate(struct sock *sk)
 	u64 rate;
 
 	/* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */
-	rate = (u64)tp->mss_cache * 2 * (HZ << 3);
+	rate = (u64)tp->mss_cache * 2 * (USEC_PER_SEC << 3);
 
 	rate *= max(tp->snd_cwnd, tp->packets_out);
 
-	/* Correction for small srtt and scheduling constraints.
-	 * For small rtt, consider noise is too high, and use
-	 * the minimal value (srtt = 1 -> 125 us for HZ=1000)
-	 *
-	 * We probably need usec resolution in the future.
-	 * Note: This also takes care of possible srtt=0 case,
-	 * when tcp_rtt_estimator() was not yet called.
-	 */
-	if (tp->srtt > 8 + 2)
-		do_div(rate, tp->srtt);
+	if (likely(tp->srtt_us))
+		do_div(rate, tp->srtt_us);
 
 	/* ACCESS_ONCE() is needed because sch_fq fetches sk_pacing_rate
 	 * without any lock. We want to make sure compiler wont store
@@ -1122,10 +1115,10 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb,
 }
 
 struct tcp_sacktag_state {
-	int reord;
-	int fack_count;
-	int flag;
-	s32 rtt; /* RTT measured by SACKing never-retransmitted data */
+	int	reord;
+	int	fack_count;
+	long	rtt_us; /* RTT measured by SACKing never-retransmitted data */
+	int	flag;
 };
 
 /* Check if skb is fully within the SACK block. In presence of GSO skbs,
@@ -1186,7 +1179,8 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
 static u8 tcp_sacktag_one(struct sock *sk,
 			  struct tcp_sacktag_state *state, u8 sacked,
 			  u32 start_seq, u32 end_seq,
-			  int dup_sack, int pcount, u32 xmit_time)
+			  int dup_sack, int pcount,
+			  const struct skb_mstamp *xmit_time)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	int fack_count = state->fack_count;
@@ -1227,8 +1221,13 @@ static u8 tcp_sacktag_one(struct sock *sk,
 				if (!after(end_seq, tp->high_seq))
 					state->flag |= FLAG_ORIG_SACK_ACKED;
 				/* Pick the earliest sequence sacked for RTT */
-				if (state->rtt < 0)
-					state->rtt = tcp_time_stamp - xmit_time;
+				if (state->rtt_us < 0) {
+					struct skb_mstamp now;
+
+					skb_mstamp_get(&now);
+					state->rtt_us = skb_mstamp_us_delta(&now,
+								xmit_time);
+				}
 			}
 
 			if (sacked & TCPCB_LOST) {
@@ -1287,7 +1286,7 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
 	 */
 	tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked,
 			start_seq, end_seq, dup_sack, pcount,
-			TCP_SKB_CB(skb)->when);
+			&skb->skb_mstamp);
 
 	if (skb == tp->lost_skb_hint)
 		tp->lost_cnt_hint += pcount;
@@ -1565,7 +1564,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk,
 						TCP_SKB_CB(skb)->end_seq,
 						dup_sack,
 						tcp_skb_pcount(skb),
-						TCP_SKB_CB(skb)->when);
+						&skb->skb_mstamp);
 
 			if (!before(TCP_SKB_CB(skb)->seq,
 				    tcp_highest_sack_seq(tp)))
@@ -1622,7 +1621,7 @@ static int tcp_sack_cache_ok(const struct tcp_sock *tp, const struct tcp_sack_bl
 
 static int
 tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
-			u32 prior_snd_una, s32 *sack_rtt)
+			u32 prior_snd_una, long *sack_rtt_us)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	const unsigned char *ptr = (skb_transport_header(ack_skb) +
@@ -1640,7 +1639,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
 
 	state.flag = 0;
 	state.reord = tp->packets_out;
-	state.rtt = -1;
+	state.rtt_us = -1L;
 
 	if (!tp->sacked_out) {
 		if (WARN_ON(tp->fackets_out))
@@ -1824,7 +1823,7 @@ out:
 	WARN_ON((int)tp->retrans_out < 0);
 	WARN_ON((int)tcp_packets_in_flight(tp) < 0);
 #endif
-	*sack_rtt = state.rtt;
+	*sack_rtt_us = state.rtt_us;
 	return state.flag;
 }
 
@@ -2034,10 +2033,12 @@ static bool tcp_pause_early_retransmit(struct sock *sk, int flag)
 	 * available, or RTO is scheduled to fire first.
 	 */
 	if (sysctl_tcp_early_retrans < 2 || sysctl_tcp_early_retrans > 3 ||
-	    (flag & FLAG_ECE) || !tp->srtt)
+	    (flag & FLAG_ECE) || !tp->srtt_us)
 		return false;
 
-	delay = max_t(unsigned long, (tp->srtt >> 5), msecs_to_jiffies(2));
+	delay = max(usecs_to_jiffies(tp->srtt_us >> 5),
+		    msecs_to_jiffies(2));
+
 	if (!time_after(inet_csk(sk)->icsk_timeout, (jiffies + delay)))
 		return false;
 
@@ -2884,7 +2885,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked,
 }
 
 static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag,
-				      s32 seq_rtt, s32 sack_rtt)
+				      long seq_rtt_us, long sack_rtt_us)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 
@@ -2894,10 +2895,10 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag,
 	 * is acked (RFC6298).
 	 */
 	if (flag & FLAG_RETRANS_DATA_ACKED)
-		seq_rtt = -1;
+		seq_rtt_us = -1L;
 
-	if (seq_rtt < 0)
-		seq_rtt = sack_rtt;
+	if (seq_rtt_us < 0)
+		seq_rtt_us = sack_rtt_us;
 
 	/* RTTM Rule: A TSecr value received in a segment is used to
 	 * update the averaged RTT measurement only if the segment
@@ -2905,14 +2906,14 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag,
 	 * left edge of the send window.
 	 * See draft-ietf-tcplw-high-performance-00, section 3.3.
 	 */
-	if (seq_rtt < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
+	if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
 	    flag & FLAG_ACKED)
-		seq_rtt = tcp_time_stamp - tp->rx_opt.rcv_tsecr;
+		seq_rtt_us = jiffies_to_usecs(tcp_time_stamp - tp->rx_opt.rcv_tsecr);
 
-	if (seq_rtt < 0)
+	if (seq_rtt_us < 0)
 		return false;
 
-	tcp_rtt_estimator(sk, seq_rtt);
+	tcp_rtt_estimator(sk, seq_rtt_us);
 	tcp_set_rto(sk);
 
 	/* RFC6298: only reset backoff on valid RTT measurement. */
@@ -2924,16 +2925,16 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag,
 static void tcp_synack_rtt_meas(struct sock *sk, const u32 synack_stamp)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	s32 seq_rtt = -1;
+	long seq_rtt_us = -1L;
 
 	if (synack_stamp && !tp->total_retrans)
-		seq_rtt = tcp_time_stamp - synack_stamp;
+		seq_rtt_us = jiffies_to_usecs(tcp_time_stamp - synack_stamp);
 
 	/* If the ACK acks both the SYNACK and the (Fast Open'd) data packets
 	 * sent in SYN_RECV, SYNACK RTT is the smooth RTT computed in tcp_ack()
 	 */
-	if (!tp->srtt)
-		tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1);
+	if (!tp->srtt_us)
+		tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt_us, -1L);
 }
 
 static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 acked, u32 in_flight)
@@ -3022,26 +3023,27 @@ static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb)
  * arrived at the other end.
  */
 static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
-			       u32 prior_snd_una, s32 sack_rtt)
+			       u32 prior_snd_una, long sack_rtt_us)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	struct sk_buff *skb;
-	u32 now = tcp_time_stamp;
+	struct skb_mstamp first_ackt, last_ackt, now;
+	struct tcp_sock *tp = tcp_sk(sk);
+	u32 prior_sacked = tp->sacked_out;
+	u32 reord = tp->packets_out;
 	bool fully_acked = true;
-	int flag = 0;
+	long ca_seq_rtt_us = -1L;
+	long seq_rtt_us = -1L;
+	struct sk_buff *skb;
 	u32 pkts_acked = 0;
-	u32 reord = tp->packets_out;
-	u32 prior_sacked = tp->sacked_out;
-	s32 seq_rtt = -1;
-	s32 ca_seq_rtt = -1;
-	ktime_t last_ackt = net_invalid_timestamp();
 	bool rtt_update;
+	int flag = 0;
+
+	first_ackt.v64 = 0;
 
 	while ((skb = tcp_write_queue_head(sk)) && skb != tcp_send_head(sk)) {
 		struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
-		u32 acked_pcount;
 		u8 sacked = scb->sacked;
+		u32 acked_pcount;
 
 		/* Determine how many packets and what bytes were acked, tso and else */
 		if (after(scb->end_seq, tp->snd_una)) {
@@ -3063,11 +3065,10 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 				tp->retrans_out -= acked_pcount;
 			flag |= FLAG_RETRANS_DATA_ACKED;
 		} else {
-			ca_seq_rtt = now - scb->when;
-			last_ackt = skb->tstamp;
-			if (seq_rtt < 0) {
-				seq_rtt = ca_seq_rtt;
-			}
+			last_ackt = skb->skb_mstamp;
+			if (!first_ackt.v64)
+				first_ackt = last_ackt;
+
 			if (!(sacked & TCPCB_SACKED_ACKED))
 				reord = min(pkts_acked, reord);
 			if (!after(scb->end_seq, tp->high_seq))
@@ -3113,7 +3114,13 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 	if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
 		flag |= FLAG_SACK_RENEGING;
 
-	rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt, sack_rtt);
+	skb_mstamp_get(&now);
+	if (first_ackt.v64) {
+		seq_rtt_us = skb_mstamp_us_delta(&now, &first_ackt);
+		ca_seq_rtt_us = skb_mstamp_us_delta(&now, &last_ackt);
+	}
+
+	rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us);
 
 	if (flag & FLAG_ACKED) {
 		const struct tcp_congestion_ops *ca_ops
@@ -3141,25 +3148,11 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 
 		tp->fackets_out -= min(pkts_acked, tp->fackets_out);
 
-		if (ca_ops->pkts_acked) {
-			s32 rtt_us = -1;
-
-			/* Is the ACK triggering packet unambiguous? */
-			if (!(flag & FLAG_RETRANS_DATA_ACKED)) {
-				/* High resolution needed and available? */
-				if (ca_ops->flags & TCP_CONG_RTT_STAMP &&
-				    !ktime_equal(last_ackt,
-						 net_invalid_timestamp()))
-					rtt_us = ktime_us_delta(ktime_get_real(),
-								last_ackt);
-				else if (ca_seq_rtt >= 0)
-					rtt_us = jiffies_to_usecs(ca_seq_rtt);
-			}
+		if (ca_ops->pkts_acked)
+			ca_ops->pkts_acked(sk, pkts_acked, ca_seq_rtt_us);
 
-			ca_ops->pkts_acked(sk, pkts_acked, rtt_us);
-		}
-	} else if (skb && rtt_update && sack_rtt >= 0 &&
-		   sack_rtt > (s32)(now - TCP_SKB_CB(skb)->when)) {
+	} else if (skb && rtt_update && sack_rtt_us >= 0 &&
+		   sack_rtt_us > skb_mstamp_us_delta(&now, &skb->skb_mstamp)) {
 		/* Do not re-arm RTO if the sack RTT is measured from data sent
 		 * after when the head was last (re)transmitted. Otherwise the
 		 * timeout may continue to extend in loss recovery.
@@ -3369,12 +3362,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	u32 ack_seq = TCP_SKB_CB(skb)->seq;
 	u32 ack = TCP_SKB_CB(skb)->ack_seq;
 	bool is_dupack = false;
-	u32 prior_in_flight, prior_cwnd = tp->snd_cwnd, prior_rtt = tp->srtt;
+	u32 prior_in_flight;
 	u32 prior_fackets;
 	int prior_packets = tp->packets_out;
 	const int prior_unsacked = tp->packets_out - tp->sacked_out;
 	int acked = 0; /* Number of packets newly acked */
-	s32 sack_rtt = -1;
+	long sack_rtt_us = -1L;
 
 	/* If the ack is older than previous acks
 	 * then we can probably ignore it.
@@ -3432,7 +3425,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 		if (TCP_SKB_CB(skb)->sacked)
 			flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
-							&sack_rtt);
+							&sack_rtt_us);
 
 		if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb)))
 			flag |= FLAG_ECE;
@@ -3451,7 +3444,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 	/* See if we can take anything off of the retransmit queue. */
 	acked = tp->packets_out;
-	flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, sack_rtt);
+	flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una,
+				    sack_rtt_us);
 	acked -= tp->packets_out;
 
 	/* Advance cwnd if state allows */
@@ -3474,8 +3468,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 	if (icsk->icsk_pending == ICSK_TIME_RETRANS)
 		tcp_schedule_loss_probe(sk);
-	if (tp->srtt != prior_rtt || tp->snd_cwnd != prior_cwnd)
-		tcp_update_pacing_rate(sk);
+	tcp_update_pacing_rate(sk);
 	return 1;
 
 no_queue:
@@ -3504,7 +3497,7 @@ old_ack:
 	 */
 	if (TCP_SKB_CB(skb)->sacked) {
 		flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
-						&sack_rtt);
+						&sack_rtt_us);
 		tcp_fastretrans_alert(sk, acked, prior_unsacked,
 				      is_dupack, flag);
 	}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3cf976510497..17c0fb172fba 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -435,7 +435,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 			break;
 
 		icsk->icsk_backoff--;
-		inet_csk(sk)->icsk_rto = (tp->srtt ? __tcp_set_rto(tp) :
+		inet_csk(sk)->icsk_rto = (tp->srtt_us ? __tcp_set_rto(tp) :
 			TCP_TIMEOUT_INIT) << icsk->icsk_backoff;
 		tcp_bound_rto(sk);
 
diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c
index 503798f2fcd6..c9aecae31327 100644
--- a/net/ipv4/tcp_lp.c
+++ b/net/ipv4/tcp_lp.c
@@ -315,7 +315,6 @@ static void tcp_lp_pkts_acked(struct sock *sk, u32 num_acked, s32 rtt_us)
 }
 
 static struct tcp_congestion_ops tcp_lp __read_mostly = {
-	.flags = TCP_CONG_RTT_STAMP,
 	.init = tcp_lp_init,
 	.ssthresh = tcp_reno_ssthresh,
 	.cong_avoid = tcp_lp_cong_avoid,
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index d547075d8300..dcaf72f10216 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -33,6 +33,11 @@ struct tcp_fastopen_metrics {
 	struct	tcp_fastopen_cookie	cookie;
 };
 
+/* TCP_METRIC_MAX includes 2 extra fields for userspace compatibility
+ * Kernel only stores RTT and RTTVAR in usec resolution
+ */
+#define TCP_METRIC_MAX_KERNEL (TCP_METRIC_MAX - 2)
+
 struct tcp_metrics_block {
 	struct tcp_metrics_block __rcu	*tcpm_next;
 	struct inetpeer_addr		tcpm_saddr;
@@ -41,7 +46,7 @@ struct tcp_metrics_block {
 	u32				tcpm_ts;
 	u32				tcpm_ts_stamp;
 	u32				tcpm_lock;
-	u32				tcpm_vals[TCP_METRIC_MAX + 1];
+	u32				tcpm_vals[TCP_METRIC_MAX_KERNEL + 1];
 	struct tcp_fastopen_metrics	tcpm_fastopen;
 
 	struct rcu_head			rcu_head;
@@ -59,12 +64,6 @@ static u32 tcp_metric_get(struct tcp_metrics_block *tm,
 	return tm->tcpm_vals[idx];
 }
 
-static u32 tcp_metric_get_jiffies(struct tcp_metrics_block *tm,
-				  enum tcp_metric_index idx)
-{
-	return msecs_to_jiffies(tm->tcpm_vals[idx]);
-}
-
 static void tcp_metric_set(struct tcp_metrics_block *tm,
 			   enum tcp_metric_index idx,
 			   u32 val)
@@ -72,13 +71,6 @@ static void tcp_metric_set(struct tcp_metrics_block *tm,
 	tm->tcpm_vals[idx] = val;
 }
 
-static void tcp_metric_set_msecs(struct tcp_metrics_block *tm,
-				 enum tcp_metric_index idx,
-				 u32 val)
-{
-	tm->tcpm_vals[idx] = jiffies_to_msecs(val);
-}
-
 static bool addr_same(const struct inetpeer_addr *a,
 		      const struct inetpeer_addr *b)
 {
@@ -101,9 +93,11 @@ struct tcpm_hash_bucket {
 
 static DEFINE_SPINLOCK(tcp_metrics_lock);
 
-static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst,
+static void tcpm_suck_dst(struct tcp_metrics_block *tm,
+			  const struct dst_entry *dst,
 			  bool fastopen_clear)
 {
+	u32 msval;
 	u32 val;
 
 	tm->tcpm_stamp = jiffies;
@@ -121,8 +115,11 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, struct dst_entry *dst,
 		val |= 1 << TCP_METRIC_REORDERING;
 	tm->tcpm_lock = val;
 
-	tm->tcpm_vals[TCP_METRIC_RTT] = dst_metric_raw(dst, RTAX_RTT);
-	tm->tcpm_vals[TCP_METRIC_RTTVAR] = dst_metric_raw(dst, RTAX_RTTVAR);
+	msval = dst_metric_raw(dst, RTAX_RTT);
+	tm->tcpm_vals[TCP_METRIC_RTT] = msval * USEC_PER_MSEC;
+
+	msval = dst_metric_raw(dst, RTAX_RTTVAR);
+	tm->tcpm_vals[TCP_METRIC_RTTVAR] = msval * USEC_PER_MSEC;
 	tm->tcpm_vals[TCP_METRIC_SSTHRESH] = dst_metric_raw(dst, RTAX_SSTHRESH);
 	tm->tcpm_vals[TCP_METRIC_CWND] = dst_metric_raw(dst, RTAX_CWND);
 	tm->tcpm_vals[TCP_METRIC_REORDERING] = dst_metric_raw(dst, RTAX_REORDERING);
@@ -384,7 +381,7 @@ void tcp_update_metrics(struct sock *sk)
 		dst_confirm(dst);
 
 	rcu_read_lock();
-	if (icsk->icsk_backoff || !tp->srtt) {
+	if (icsk->icsk_backoff || !tp->srtt_us) {
 		/* This session failed to estimate rtt. Why?
 		 * Probably, no packets returned in time.  Reset our
 		 * results.
@@ -399,8 +396,8 @@ void tcp_update_metrics(struct sock *sk)
 	if (!tm)
 		goto out_unlock;
 
-	rtt = tcp_metric_get_jiffies(tm, TCP_METRIC_RTT);
-	m = rtt - tp->srtt;
+	rtt = tcp_metric_get(tm, TCP_METRIC_RTT);
+	m = rtt - tp->srtt_us;
 
 	/* If newly calculated rtt larger than stored one, store new
 	 * one. Otherwise, use EWMA. Remember, rtt overestimation is
@@ -408,10 +405,10 @@ void tcp_update_metrics(struct sock *sk)
 	 */
 	if (!tcp_metric_locked(tm, TCP_METRIC_RTT)) {
 		if (m <= 0)
-			rtt = tp->srtt;
+			rtt = tp->srtt_us;
 		else
 			rtt -= (m >> 3);
-		tcp_metric_set_msecs(tm, TCP_METRIC_RTT, rtt);
+		tcp_metric_set(tm, TCP_METRIC_RTT, rtt);
 	}
 
 	if (!tcp_metric_locked(tm, TCP_METRIC_RTTVAR)) {
@@ -422,16 +419,16 @@ void tcp_update_metrics(struct sock *sk)
 
 		/* Scale deviation to rttvar fixed point */
 		m >>= 1;
-		if (m < tp->mdev)
-			m = tp->mdev;
+		if (m < tp->mdev_us)
+			m = tp->mdev_us;
 
-		var = tcp_metric_get_jiffies(tm, TCP_METRIC_RTTVAR);
+		var = tcp_metric_get(tm, TCP_METRIC_RTTVAR);
 		if (m >= var)
 			var = m;
 		else
 			var -= (var - m) >> 2;
 
-		tcp_metric_set_msecs(tm, TCP_METRIC_RTTVAR, var);
+		tcp_metric_set(tm, TCP_METRIC_RTTVAR, var);
 	}
 
 	if (tcp_in_initial_slowstart(tp)) {
@@ -528,7 +525,7 @@ void tcp_init_metrics(struct sock *sk)
 		tp->reordering = val;
 	}
 
-	crtt = tcp_metric_get_jiffies(tm, TCP_METRIC_RTT);
+	crtt = tcp_metric_get(tm, TCP_METRIC_RTT);
 	rcu_read_unlock();
 reset:
 	/* The initial RTT measurement from the SYN/SYN-ACK is not ideal
@@ -551,18 +548,20 @@ reset:
 	 * to low value, and then abruptly stops to do it and starts to delay
 	 * ACKs, wait for troubles.
 	 */
-	if (crtt > tp->srtt) {
+	if (crtt > tp->srtt_us) {
 		/* Set RTO like tcp_rtt_estimator(), but from cached RTT. */
-		crtt >>= 3;
+		crtt /= 8 * USEC_PER_MSEC;
 		inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk));
-	} else if (tp->srtt == 0) {
+	} else if (tp->srtt_us == 0) {
 		/* RFC6298: 5.7 We've failed to get a valid RTT sample from
 		 * 3WHS. This is most likely due to retransmission,
 		 * including spurious one. Reset the RTO back to 3secs
 		 * from the more aggressive 1sec to avoid more spurious
 		 * retransmission.
 		 */
-		tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_FALLBACK;
+		tp->rttvar_us = jiffies_to_usecs(TCP_TIMEOUT_FALLBACK);
+		tp->mdev_us = tp->mdev_max_us = tp->rttvar_us;
+
 		inet_csk(sk)->icsk_rto = TCP_TIMEOUT_FALLBACK;
 	}
 	/* Cut cwnd down to 1 per RFC5681 if SYN or SYN-ACK has been
@@ -809,10 +808,26 @@ static int tcp_metrics_fill_info(struct sk_buff *msg,
 		nest = nla_nest_start(msg, TCP_METRICS_ATTR_VALS);
 		if (!nest)
 			goto nla_put_failure;
-		for (i = 0; i < TCP_METRIC_MAX + 1; i++) {
-			if (!tm->tcpm_vals[i])
+		for (i = 0; i < TCP_METRIC_MAX_KERNEL + 1; i++) {
+			u32 val = tm->tcpm_vals[i];
+
+			if (!val)
 				continue;
-			if (nla_put_u32(msg, i + 1, tm->tcpm_vals[i]) < 0)
+			if (i == TCP_METRIC_RTT) {
+				if (nla_put_u32(msg, TCP_METRIC_RTT_US + 1,
+						val) < 0)
+					goto nla_put_failure;
+				n++;
+				val = max(val / 1000, 1U);
+			}
+			if (i == TCP_METRIC_RTTVAR) {
+				if (nla_put_u32(msg, TCP_METRIC_RTTVAR_US + 1,
+						val) < 0)
+					goto nla_put_failure;
+				n++;
+				val = max(val / 1000, 1U);
+			}
+			if (nla_put_u32(msg, i + 1, val) < 0)
 				goto nla_put_failure;
 			n++;
 		}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 7a436c517e44..ca788ada5bd3 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -398,8 +398,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 
 		tcp_init_wl(newtp, treq->rcv_isn);
 
-		newtp->srtt = 0;
-		newtp->mdev = TCP_TIMEOUT_INIT;
+		newtp->srtt_us = 0;
+		newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 		newicsk->icsk_rto = TCP_TIMEOUT_INIT;
 
 		newtp->packets_out = 0;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c5eadec001c1..bf38b1fb63ab 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -866,11 +866,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	if (clone_it) {
 		const struct sk_buff *fclone = skb + 1;
 
-		/* If congestion control is doing timestamping, we must
-		 * take such a timestamp before we potentially clone/copy.
-		 */
-		if (icsk->icsk_ca_ops->flags & TCP_CONG_RTT_STAMP)
-			__net_timestamp(skb);
+		skb_mstamp_get(&skb->skb_mstamp);
 
 		if (unlikely(skb->fclone == SKB_FCLONE_ORIG &&
 			     fclone->fclone == SKB_FCLONE_CLONE))
@@ -1974,7 +1970,7 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 timeout, tlp_time_stamp, rto_time_stamp;
-	u32 rtt = tp->srtt >> 3;
+	u32 rtt = usecs_to_jiffies(tp->srtt_us >> 3);
 
 	if (WARN_ON(icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS))
 		return false;
@@ -1996,7 +1992,7 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 	/* Schedule a loss probe in 2*RTT for SACK capable connections
 	 * in Open state, that are either limited by cwnd or application.
 	 */
-	if (sysctl_tcp_early_retrans < 3 || !tp->srtt || !tp->packets_out ||
+	if (sysctl_tcp_early_retrans < 3 || !tp->srtt_us || !tp->packets_out ||
 	    !tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
 		return false;
 
@@ -3050,8 +3046,9 @@ void tcp_send_delayed_ack(struct sock *sk)
 		 * Do not use inet_csk(sk)->icsk_rto here, use results of rtt measurements
 		 * directly.
 		 */
-		if (tp->srtt) {
-			int rtt = max(tp->srtt >> 3, TCP_DELACK_MIN);
+		if (tp->srtt_us) {
+			int rtt = max_t(int, usecs_to_jiffies(tp->srtt_us >> 3),
+					TCP_DELACK_MIN);
 
 			if (rtt < max_ato)
 				max_ato = rtt;
diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index 1f2d37613c9e..3b66610d4156 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -154,7 +154,7 @@ static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 			p->snd_wnd = tp->snd_wnd;
 			p->rcv_wnd = tp->rcv_wnd;
 			p->ssthresh = tcp_current_ssthresh(sk);
-			p->srtt = tp->srtt >> 3;
+			p->srtt = tp->srtt_us >> 3;
 
 			tcp_probe.head = (tcp_probe.head + 1) & (bufsize - 1);
 		}
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index a022c17c9cf1..48539fff6357 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -306,7 +306,6 @@ void tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb)
 EXPORT_SYMBOL_GPL(tcp_vegas_get_info);
 
 static struct tcp_congestion_ops tcp_vegas __read_mostly = {
-	.flags		= TCP_CONG_RTT_STAMP,
 	.init		= tcp_vegas_init,
 	.ssthresh	= tcp_reno_ssthresh,
 	.cong_avoid	= tcp_vegas_cong_avoid,
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index 326475a94865..1b8e28fcd7e1 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -203,7 +203,6 @@ static u32 tcp_veno_ssthresh(struct sock *sk)
 }
 
 static struct tcp_congestion_ops tcp_veno __read_mostly = {
-	.flags		= TCP_CONG_RTT_STAMP,
 	.init		= tcp_veno_init,
 	.ssthresh	= tcp_veno_ssthresh,
 	.cong_avoid	= tcp_veno_cong_avoid,
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index 8eab02030ed0..5ede0e727945 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -227,7 +227,6 @@ static u32 tcp_yeah_ssthresh(struct sock *sk) {
 }
 
 static struct tcp_congestion_ops tcp_yeah __read_mostly = {
-	.flags		= TCP_CONG_RTT_STAMP,
 	.init		= tcp_yeah_init,
 	.ssthresh	= tcp_yeah_ssthresh,
 	.cong_avoid	= tcp_yeah_cong_avoid,
-- 
cgit v1.2.3


From 3843154598a00408f4214a68bd536fdf27b1df10 Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk.kim@samsung.com>
Date: Thu, 27 Feb 2014 18:20:00 +0900
Subject: f2fs: introduce large directory support

This patch introduces an i_dir_level field to support large directory.

Previously, f2fs maintains multi-level hash tables to find a dentry quickly
from a bunch of chiild dentries in a directory, and the hash tables consist of
the following tree structure as below.

In Documentation/filesystems/f2fs.txt,

----------------------
A : bucket
B : block
N : MAX_DIR_HASH_DEPTH
----------------------

level #0   | A(2B)
           |
level #1   | A(2B) - A(2B)
           |
level #2   | A(2B) - A(2B) - A(2B) - A(2B)
     .     |   .       .       .       .
level #N/2 | A(2B) - A(2B) - A(2B) - A(2B) - A(2B) - ... - A(2B)
     .     |   .       .       .       .
level #N   | A(4B) - A(4B) - A(4B) - A(4B) - A(4B) - ... - A(4B)

But, if we can guess that a directory will handle a number of child files,
we don't need to traverse the tree from level #0 to #N all the time.
Since the lower level tables contain relatively small number of dentries,
the miss ratio of the target dentry is likely to be high.

In order to avoid that, we can configure the hash tables sparsely from level #0
like this.

level #0   | A(2B) - A(2B) - A(2B) - A(2B)

level #1   | A(2B) - A(2B) - A(2B) - A(2B) - A(2B) - ... - A(2B)
     .     |   .       .       .       .
level #N/2 | A(2B) - A(2B) - A(2B) - A(2B) - A(2B) - ... - A(2B)
     .     |   .       .       .       .
level #N   | A(4B) - A(4B) - A(4B) - A(4B) - A(4B) - ... - A(4B)

With this structure, we can skip the ineffective tree searches in lower level
hash tables.

This patch adds just a facility for this by introducing i_dir_level in
f2fs_inode.

Signed-off-by: Jaegeuk Kim <jaegeuk.kim@samsung.com>
---
 Documentation/filesystems/f2fs.txt |  6 ++++--
 fs/f2fs/dir.c                      | 21 ++++++++++++---------
 fs/f2fs/f2fs.h                     |  1 +
 fs/f2fs/inode.c                    |  2 ++
 include/linux/f2fs_fs.h            |  2 +-
 5 files changed, 20 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/f2fs.txt b/Documentation/filesystems/f2fs.txt
index b8d284975f0f..8eb06b0a7d2b 100644
--- a/Documentation/filesystems/f2fs.txt
+++ b/Documentation/filesystems/f2fs.txt
@@ -444,9 +444,11 @@ The number of blocks and buckets are determined by,
   # of blocks in level #n = |
                             `- 4, Otherwise
 
-                             ,- 2^n, if n < MAX_DIR_HASH_DEPTH / 2,
+                             ,- 2^ (n + dir_level),
+			     |            if n < MAX_DIR_HASH_DEPTH / 2,
   # of buckets in level #n = |
-                             `- 2^((MAX_DIR_HASH_DEPTH / 2) - 1), Otherwise
+                             `- 2^((MAX_DIR_HASH_DEPTH / 2 + dir_level) - 1),
+			                  Otherwise
 
 When F2FS finds a file name in a directory, at first a hash value of the file
 name is calculated. Then, F2FS scans the hash table in level #0 to find the
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index c3ea8f8cc80a..582fa00f3597 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -21,12 +21,12 @@ static unsigned long dir_blocks(struct inode *inode)
 							>> PAGE_CACHE_SHIFT;
 }
 
-static unsigned int dir_buckets(unsigned int level)
+static unsigned int dir_buckets(unsigned int level, int dir_level)
 {
 	if (level < MAX_DIR_HASH_DEPTH / 2)
-		return 1 << level;
+		return 1 << (level + dir_level);
 	else
-		return 1 << ((MAX_DIR_HASH_DEPTH / 2) - 1);
+		return 1 << ((MAX_DIR_HASH_DEPTH / 2 + dir_level) - 1);
 }
 
 static unsigned int bucket_blocks(unsigned int level)
@@ -65,13 +65,14 @@ static void set_de_type(struct f2fs_dir_entry *de, struct inode *inode)
 	de->file_type = f2fs_type_by_mode[(mode & S_IFMT) >> S_SHIFT];
 }
 
-static unsigned long dir_block_index(unsigned int level, unsigned int idx)
+static unsigned long dir_block_index(unsigned int level,
+				int dir_level, unsigned int idx)
 {
 	unsigned long i;
 	unsigned long bidx = 0;
 
 	for (i = 0; i < level; i++)
-		bidx += dir_buckets(i) * bucket_blocks(i);
+		bidx += dir_buckets(i, dir_level) * bucket_blocks(i);
 	bidx += idx * bucket_blocks(level);
 	return bidx;
 }
@@ -143,10 +144,11 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 
 	f2fs_bug_on(level > MAX_DIR_HASH_DEPTH);
 
-	nbucket = dir_buckets(level);
+	nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level);
 	nblock = bucket_blocks(level);
 
-	bidx = dir_block_index(level, le32_to_cpu(namehash) % nbucket);
+	bidx = dir_block_index(level, F2FS_I(dir)->i_dir_level,
+					le32_to_cpu(namehash) % nbucket);
 	end_block = bidx + nblock;
 
 	for (; bidx < end_block; bidx++) {
@@ -467,10 +469,11 @@ start:
 	if (level == current_depth)
 		++current_depth;
 
-	nbucket = dir_buckets(level);
+	nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level);
 	nblock = bucket_blocks(level);
 
-	bidx = dir_block_index(level, (le32_to_cpu(dentry_hash) % nbucket));
+	bidx = dir_block_index(level, F2FS_I(dir)->i_dir_level,
+				(le32_to_cpu(dentry_hash) % nbucket));
 
 	for (block = bidx; block <= (bidx + nblock - 1); block++) {
 		dentry_page = get_new_data_page(dir, NULL, block, true);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 4beedccc28a0..a82691674918 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -200,6 +200,7 @@ struct f2fs_inode_info {
 	struct inode vfs_inode;		/* serve a vfs inode */
 	unsigned long i_flags;		/* keep an inode flags for ioctl */
 	unsigned char i_advise;		/* use to give file attribute hints */
+	unsigned char i_dir_level;	/* use for dentry level for large dir */
 	unsigned int i_current_depth;	/* use only in directory structure */
 	unsigned int i_pino;		/* parent inode number */
 	umode_t i_acl_mode;		/* keep file acl mode temporarily */
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 08d69c94ab8b..d518e37df3a7 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -107,6 +107,7 @@ static int do_read_inode(struct inode *inode)
 	fi->flags = 0;
 	fi->i_advise = ri->i_advise;
 	fi->i_pino = le32_to_cpu(ri->i_pino);
+	fi->i_dir_level = ri->i_dir_level;
 
 	get_extent_info(&fi->ext, ri->i_ext);
 	get_inline_info(fi, ri);
@@ -204,6 +205,7 @@ void update_inode(struct inode *inode, struct page *node_page)
 	ri->i_flags = cpu_to_le32(F2FS_I(inode)->i_flags);
 	ri->i_pino = cpu_to_le32(F2FS_I(inode)->i_pino);
 	ri->i_generation = cpu_to_le32(inode->i_generation);
+	ri->i_dir_level = F2FS_I(inode)->i_dir_level;
 
 	__set_inode_rdev(inode, ri);
 	set_cold_node(inode, node_page);
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index da74d878dc4f..df53e1753a76 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -183,7 +183,7 @@ struct f2fs_inode {
 	__le32 i_pino;			/* parent inode number */
 	__le32 i_namelen;		/* file name length */
 	__u8 i_name[F2FS_NAME_LEN];	/* file name for SPOR */
-	__u8 i_reserved2;		/* for backward compatibility */
+	__u8 i_dir_level;		/* dentry_level for large dir */
 
 	struct f2fs_extent i_ext;	/* caching a largest extent */
 
-- 
cgit v1.2.3


From 85a8885bd0e00569108aa7b5e26b89c752e3cd51 Mon Sep 17 00:00:00 2001
From: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>
Date: Thu, 20 Feb 2014 10:28:46 -0600
Subject: amd64_edac: Add support for newer F16h models

Extend ECC decoding support for F16h M30h. Tested on F16h M30h with ECC
turned on using mce_amd_inj module and the patch works fine.

Signed-off-by: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>
Link: http://lkml.kernel.org/r/1392913726-16961-1-git-send-email-Aravind.Gopalakrishnan@amd.com
Tested-by: Arindam Nath <Arindam.Nath@amd.com>
Acked-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
---
 arch/x86/kernel/amd_nb.c  |  2 ++
 drivers/edac/amd64_edac.c | 24 ++++++++++++++++++++++++
 drivers/edac/amd64_edac.h |  3 +++
 include/linux/pci_ids.h   |  2 ++
 4 files changed, 31 insertions(+)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 59554dca96ec..6523534671b6 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -22,6 +22,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) },
 	{}
 };
 EXPORT_SYMBOL(amd_nb_misc_ids);
@@ -30,6 +31,7 @@ static const struct pci_device_id amd_nb_link_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) },
 	{}
 };
 
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 34380ccc3dd9..f8bf00010d45 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -1807,6 +1807,17 @@ static struct amd64_family_type family_types[] = {
 			.read_dct_pci_cfg	= f10_read_dct_pci_cfg,
 		}
 	},
+	[F16_M30H_CPUS] = {
+		.ctl_name = "F16h_M30h",
+		.f1_id = PCI_DEVICE_ID_AMD_16H_M30H_NB_F1,
+		.f3_id = PCI_DEVICE_ID_AMD_16H_M30H_NB_F3,
+		.ops = {
+			.early_channel_count	= f1x_early_channel_count,
+			.map_sysaddr_to_csrow	= f1x_map_sysaddr_to_csrow,
+			.dbam_to_cs		= f16_dbam_to_chip_select,
+			.read_dct_pci_cfg	= f10_read_dct_pci_cfg,
+		}
+	},
 };
 
 /*
@@ -2586,6 +2597,11 @@ static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt)
 		break;
 
 	case 0x16:
+		if (pvt->model == 0x30) {
+			fam_type = &family_types[F16_M30H_CPUS];
+			pvt->ops = &family_types[F16_M30H_CPUS].ops;
+			break;
+		}
 		fam_type	= &family_types[F16_CPUS];
 		pvt->ops	= &family_types[F16_CPUS].ops;
 		break;
@@ -2838,6 +2854,14 @@ static const struct pci_device_id amd64_pci_table[] = {
 		.class		= 0,
 		.class_mask	= 0,
 	},
+	{
+		.vendor		= PCI_VENDOR_ID_AMD,
+		.device		= PCI_DEVICE_ID_AMD_16H_M30H_NB_F2,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.class		= 0,
+		.class_mask	= 0,
+	},
 
 	{0, }
 };
diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h
index 6dc1fcc25afb..d903e0c21144 100644
--- a/drivers/edac/amd64_edac.h
+++ b/drivers/edac/amd64_edac.h
@@ -168,6 +168,8 @@
 #define PCI_DEVICE_ID_AMD_15H_NB_F2	0x1602
 #define PCI_DEVICE_ID_AMD_16H_NB_F1	0x1531
 #define PCI_DEVICE_ID_AMD_16H_NB_F2	0x1532
+#define PCI_DEVICE_ID_AMD_16H_M30H_NB_F1 0x1581
+#define PCI_DEVICE_ID_AMD_16H_M30H_NB_F2 0x1582
 
 /*
  * Function 1 - Address Map
@@ -300,6 +302,7 @@ enum amd_families {
 	F15_CPUS,
 	F15_M30H_CPUS,
 	F16_CPUS,
+	F16_M30H_CPUS,
 	NUM_FAMILIES,
 };
 
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 97fbecdd7a40..e91ad27b1a56 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -528,6 +528,8 @@
 #define PCI_DEVICE_ID_AMD_15H_NB_F5	0x1605
 #define PCI_DEVICE_ID_AMD_16H_NB_F3	0x1533
 #define PCI_DEVICE_ID_AMD_16H_NB_F4	0x1534
+#define PCI_DEVICE_ID_AMD_16H_M30H_NB_F3 0x1583
+#define PCI_DEVICE_ID_AMD_16H_M30H_NB_F4 0x1584
 #define PCI_DEVICE_ID_AMD_CNB17H_F3	0x1703
 #define PCI_DEVICE_ID_AMD_LANCE		0x2000
 #define PCI_DEVICE_ID_AMD_LANCE_HOME	0x2001
-- 
cgit v1.2.3


From a59ce6584d566847980f9dcad5343cd9856145c8 Mon Sep 17 00:00:00 2001
From: Alexander Shiyan <shc_work@mail.ru>
Date: Fri, 31 Jan 2014 22:36:28 -0800
Subject: leds: leds-mc13783: Add MC34708 LED support

This patch adds support for two LEDs on MC34708 PMIC.

Signed-off-by: Alexander Shiyan <shc_work@mail.ru>
Signed-off-by: Bryan Wu <cooloney@gmail.com>
---
 drivers/leds/Kconfig        |  2 +-
 drivers/leds/leds-mc13783.c | 98 ++++++++++++++++++++++-----------------------
 include/linux/mfd/mc13xxx.h |  6 +++
 3 files changed, 55 insertions(+), 51 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 72156c123033..93466d215706 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -416,7 +416,7 @@ config LEDS_MC13783
 	depends on MFD_MC13XXX
 	help
 	  This option enable support for on-chip LED drivers found
-	  on Freescale Semiconductor MC13783/MC13892 PMIC.
+	  on Freescale Semiconductor MC13783/MC13892/MC34708 PMIC.
 
 config LEDS_NS2
 	tristate "LED support for Network Space v2 GPIO LEDs"
diff --git a/drivers/leds/leds-mc13783.c b/drivers/leds/leds-mc13783.c
index ca87a1b4a0db..68f2455c672f 100644
--- a/drivers/leds/leds-mc13783.c
+++ b/drivers/leds/leds-mc13783.c
@@ -1,5 +1,5 @@
 /*
- * LEDs driver for Freescale MC13783/MC13892
+ * LEDs driver for Freescale MC13783/MC13892/MC34708
  *
  * Copyright (C) 2010 Philippe Rétornaz
  *
@@ -23,23 +23,23 @@
 #include <linux/workqueue.h>
 #include <linux/mfd/mc13xxx.h>
 
-#define MC13XXX_REG_LED_CONTROL(x)	(51 + (x))
-
 struct mc13xxx_led_devtype {
 	int	led_min;
 	int	led_max;
 	int	num_regs;
+	u32	ledctrl_base;
 };
 
 struct mc13xxx_led {
 	struct led_classdev	cdev;
 	struct work_struct	work;
-	struct mc13xxx		*master;
 	enum led_brightness	new_brightness;
 	int			id;
+	struct mc13xxx_leds	*leds;
 };
 
 struct mc13xxx_leds {
+	struct mc13xxx			*master;
 	struct mc13xxx_led_devtype	*devtype;
 	int				num_leds;
 	struct mc13xxx_led		led[0];
@@ -48,24 +48,15 @@ struct mc13xxx_leds {
 static void mc13xxx_led_work(struct work_struct *work)
 {
 	struct mc13xxx_led *led = container_of(work, struct mc13xxx_led, work);
-	int reg, mask, value, bank, off, shift;
+	struct mc13xxx_leds *leds = led->leds;
+	unsigned int reg, mask, value, bank, off, shift;
 
 	switch (led->id) {
 	case MC13783_LED_MD:
-		reg = MC13XXX_REG_LED_CONTROL(2);
-		shift = 9;
-		mask = 0x0f;
-		value = led->new_brightness >> 4;
-		break;
 	case MC13783_LED_AD:
-		reg = MC13XXX_REG_LED_CONTROL(2);
-		shift = 13;
-		mask = 0x0f;
-		value = led->new_brightness >> 4;
-		break;
 	case MC13783_LED_KP:
-		reg = MC13XXX_REG_LED_CONTROL(2);
-		shift = 17;
+		reg = 2;
+		shift = 9 + (led->id - MC13783_LED_MD) * 4;
 		mask = 0x0f;
 		value = led->new_brightness >> 4;
 		break;
@@ -80,26 +71,16 @@ static void mc13xxx_led_work(struct work_struct *work)
 	case MC13783_LED_B3:
 		off = led->id - MC13783_LED_R1;
 		bank = off / 3;
-		reg = MC13XXX_REG_LED_CONTROL(3) + bank;
+		reg = 3 + bank;
 		shift = (off - bank * 3) * 5 + 6;
 		value = led->new_brightness >> 3;
 		mask = 0x1f;
 		break;
 	case MC13892_LED_MD:
-		reg = MC13XXX_REG_LED_CONTROL(0);
-		shift = 3;
-		mask = 0x3f;
-		value = led->new_brightness >> 2;
-		break;
 	case MC13892_LED_AD:
-		reg = MC13XXX_REG_LED_CONTROL(0);
-		shift = 15;
-		mask = 0x3f;
-		value = led->new_brightness >> 2;
-		break;
 	case MC13892_LED_KP:
-		reg = MC13XXX_REG_LED_CONTROL(1);
-		shift = 3;
+		reg = (led->id - MC13892_LED_MD) / 2;
+		shift = 3 + (led->id - MC13892_LED_MD) * 12;
 		mask = 0x3f;
 		value = led->new_brightness >> 2;
 		break;
@@ -108,16 +89,24 @@ static void mc13xxx_led_work(struct work_struct *work)
 	case MC13892_LED_B:
 		off = led->id - MC13892_LED_R;
 		bank = off / 2;
-		reg = MC13XXX_REG_LED_CONTROL(2) + bank;
+		reg = 2 + bank;
 		shift = (off - bank * 2) * 12 + 3;
 		value = led->new_brightness >> 2;
 		mask = 0x3f;
 		break;
+	case MC34708_LED_R:
+	case MC34708_LED_G:
+		reg = 0;
+		shift = 3 + (led->id - MC34708_LED_R) * 12;
+		value = led->new_brightness >> 2;
+		mask = 0x3f;
+		break;
 	default:
 		BUG();
 	}
 
-	mc13xxx_reg_rmw(led->master, reg, mask << shift, value << shift);
+	mc13xxx_reg_rmw(leds->master, leds->devtype->ledctrl_base + reg,
+			mask << shift, value << shift);
 }
 
 static void mc13xxx_led_set(struct led_classdev *led_cdev,
@@ -132,16 +121,17 @@ static void mc13xxx_led_set(struct led_classdev *led_cdev,
 
 static int __init mc13xxx_led_probe(struct platform_device *pdev)
 {
-	struct mc13xxx_leds_platform_data *pdata = dev_get_platdata(&pdev->dev);
-	struct mc13xxx *mcdev = dev_get_drvdata(pdev->dev.parent);
+	struct device *dev = &pdev->dev;
+	struct mc13xxx_leds_platform_data *pdata = dev_get_platdata(dev);
+	struct mc13xxx *mcdev = dev_get_drvdata(dev->parent);
 	struct mc13xxx_led_devtype *devtype =
 		(struct mc13xxx_led_devtype *)pdev->id_entry->driver_data;
 	struct mc13xxx_leds *leds;
 	int i, id, num_leds, ret = -ENODATA;
-	u32 reg, init_led = 0;
+	u32 init_led = 0;
 
 	if (!pdata) {
-		dev_err(&pdev->dev, "Missing platform data\n");
+		dev_err(dev, "Missing platform data\n");
 		return -ENODEV;
 	}
 
@@ -149,23 +139,23 @@ static int __init mc13xxx_led_probe(struct platform_device *pdev)
 
 	if ((num_leds < 1) ||
 	    (num_leds > (devtype->led_max - devtype->led_min + 1))) {
-		dev_err(&pdev->dev, "Invalid LED count %d\n", num_leds);
+		dev_err(dev, "Invalid LED count %d\n", num_leds);
 		return -EINVAL;
 	}
 
-	leds = devm_kzalloc(&pdev->dev, num_leds * sizeof(struct mc13xxx_led) +
+	leds = devm_kzalloc(dev, num_leds * sizeof(struct mc13xxx_led) +
 			    sizeof(struct mc13xxx_leds), GFP_KERNEL);
 	if (!leds)
 		return -ENOMEM;
 
 	leds->devtype = devtype;
 	leds->num_leds = num_leds;
+	leds->master = mcdev;
 	platform_set_drvdata(pdev, leds);
 
 	for (i = 0; i < devtype->num_regs; i++) {
-		reg = pdata->led_control[i];
-		WARN_ON(reg >= (1 << 24));
-		ret = mc13xxx_reg_write(mcdev, MC13XXX_REG_LED_CONTROL(i), reg);
+		ret = mc13xxx_reg_write(mcdev, leds->devtype->ledctrl_base + i,
+					pdata->led_control[i]);
 		if (ret)
 			return ret;
 	}
@@ -180,19 +170,18 @@ static int __init mc13xxx_led_probe(struct platform_device *pdev)
 		trig = pdata->led[i].default_trigger;
 
 		if ((id > devtype->led_max) || (id < devtype->led_min)) {
-			dev_err(&pdev->dev, "Invalid ID %i\n", id);
+			dev_err(dev, "Invalid ID %i\n", id);
 			break;
 		}
 
 		if (init_led & (1 << id)) {
-			dev_warn(&pdev->dev,
-				 "LED %i already initialized\n", id);
+			dev_warn(dev, "LED %i already initialized\n", id);
 			break;
 		}
 
 		init_led |= 1 << id;
 		leds->led[i].id = id;
-		leds->led[i].master = mcdev;
+		leds->led[i].leds = leds;
 		leds->led[i].cdev.name = name;
 		leds->led[i].cdev.default_trigger = trig;
 		leds->led[i].cdev.brightness_set = mc13xxx_led_set;
@@ -200,10 +189,9 @@ static int __init mc13xxx_led_probe(struct platform_device *pdev)
 
 		INIT_WORK(&leds->led[i].work, mc13xxx_led_work);
 
-		ret = led_classdev_register(pdev->dev.parent,
-					    &leds->led[i].cdev);
+		ret = led_classdev_register(dev->parent, &leds->led[i].cdev);
 		if (ret) {
-			dev_err(&pdev->dev, "Failed to register LED %i\n", id);
+			dev_err(dev, "Failed to register LED %i\n", id);
 			break;
 		}
 	}
@@ -219,8 +207,8 @@ static int __init mc13xxx_led_probe(struct platform_device *pdev)
 
 static int mc13xxx_led_remove(struct platform_device *pdev)
 {
-	struct mc13xxx *mcdev = dev_get_drvdata(pdev->dev.parent);
 	struct mc13xxx_leds *leds = platform_get_drvdata(pdev);
+	struct mc13xxx *mcdev = leds->master;
 	int i;
 
 	for (i = 0; i < leds->num_leds; i++) {
@@ -229,7 +217,7 @@ static int mc13xxx_led_remove(struct platform_device *pdev)
 	}
 
 	for (i = 0; i < leds->devtype->num_regs; i++)
-		mc13xxx_reg_write(mcdev, MC13XXX_REG_LED_CONTROL(i), 0);
+		mc13xxx_reg_write(mcdev, leds->devtype->ledctrl_base + i, 0);
 
 	return 0;
 }
@@ -238,17 +226,27 @@ static const struct mc13xxx_led_devtype mc13783_led_devtype = {
 	.led_min	= MC13783_LED_MD,
 	.led_max	= MC13783_LED_B3,
 	.num_regs	= 6,
+	.ledctrl_base	= 51,
 };
 
 static const struct mc13xxx_led_devtype mc13892_led_devtype = {
 	.led_min	= MC13892_LED_MD,
 	.led_max	= MC13892_LED_B,
 	.num_regs	= 4,
+	.ledctrl_base	= 51,
+};
+
+static const struct mc13xxx_led_devtype mc34708_led_devtype = {
+	.led_min	= MC34708_LED_R,
+	.led_max	= MC34708_LED_G,
+	.num_regs	= 1,
+	.ledctrl_base	= 54,
 };
 
 static const struct platform_device_id mc13xxx_led_id_table[] = {
 	{ "mc13783-led", (kernel_ulong_t)&mc13783_led_devtype, },
 	{ "mc13892-led", (kernel_ulong_t)&mc13892_led_devtype, },
+	{ "mc34708-led", (kernel_ulong_t)&mc34708_led_devtype, },
 	{ }
 };
 MODULE_DEVICE_TABLE(platform, mc13xxx_led_id_table);
diff --git a/include/linux/mfd/mc13xxx.h b/include/linux/mfd/mc13xxx.h
index ac39d910e70b..a326c850f046 100644
--- a/include/linux/mfd/mc13xxx.h
+++ b/include/linux/mfd/mc13xxx.h
@@ -104,6 +104,9 @@ enum {
 	MC13892_LED_R,
 	MC13892_LED_G,
 	MC13892_LED_B,
+	/* MC34708 LED IDs */
+	MC34708_LED_R,
+	MC34708_LED_G,
 };
 
 struct mc13xxx_led_platform_data {
@@ -163,6 +166,9 @@ struct mc13xxx_leds_platform_data {
 #define MC13892_LED_C2_CURRENT_G(x)	(((x) & 0x7) << 21)
 /* MC13892 LED Control 3 */
 #define MC13892_LED_C3_CURRENT_B(x)	(((x) & 0x7) << 9)
+/* MC34708 LED Control 0 */
+#define MC34708_LED_C0_CURRENT_R(x)	(((x) & 0x3) << 9)
+#define MC34708_LED_C0_CURRENT_G(x)	(((x) & 0x3) << 21)
 	u32 led_control[MAX_LED_CONTROL_REGS];
 };
 
-- 
cgit v1.2.3


From fc87eb0b588394d8304d942bcd5c71d6bcc595c7 Mon Sep 17 00:00:00 2001
From: Sachin Kamat <sachin.kamat@linaro.org>
Date: Thu, 13 Feb 2014 22:37:09 -0800
Subject: leds: leds-s3c24xx: Trivial cleanup in header file

Commit 436d42c61c3e ("ARM: samsung: move platform_data definitions")
moved the files to the current location but forgot to remove the pointer
to its previous location. Clean it up. While at it also change the header
file protection macros appropriately.

Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Bryan Wu <cooloney@gmail.com>
---
 include/linux/platform_data/leds-s3c24xx.h | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/leds-s3c24xx.h b/include/linux/platform_data/leds-s3c24xx.h
index d8a7672519b6..441a6f290649 100644
--- a/include/linux/platform_data/leds-s3c24xx.h
+++ b/include/linux/platform_data/leds-s3c24xx.h
@@ -1,5 +1,4 @@
-/* arch/arm/mach-s3c2410/include/mach/leds-gpio.h
- *
+/*
  * Copyright (c) 2006 Simtec Electronics
  *	http://armlinux.simtec.co.uk/
  *	Ben Dooks <ben@simtec.co.uk>
@@ -11,8 +10,8 @@
  * published by the Free Software Foundation.
 */
 
-#ifndef __ASM_ARCH_LEDSGPIO_H
-#define __ASM_ARCH_LEDSGPIO_H "leds-gpio.h"
+#ifndef __LEDS_S3C24XX_H
+#define __LEDS_S3C24XX_H
 
 #define S3C24XX_LEDF_ACTLOW	(1<<0)		/* LED is on when GPIO low */
 #define S3C24XX_LEDF_TRISTATE	(1<<1)		/* tristate to turn off */
@@ -25,4 +24,4 @@ struct s3c24xx_led_platdata {
 	char			*def_trigger;
 };
 
-#endif /* __ASM_ARCH_LEDSGPIO_H */
+#endif /* __LEDS_S3C24XX_H */
-- 
cgit v1.2.3


From 7aa98047df95d7caf0678e939cdd936dfb99cd06 Mon Sep 17 00:00:00 2001
From: "Luis R. Rodriguez" <mcgrof@suse.com>
Date: Tue, 25 Feb 2014 17:15:13 -0800
Subject: net: move net_device priv_flags out from UAPI

These are private to userspace, and they're unstable
anyway and can be shuffled at will (see 080e4130b1fb)
so any userspace application relying on them is on crack.

Test compiled with allyesconfig.

mcgrof@drvbp1 /pub/mem/mcgrof/net-next (git::master)$ make allyesconfig
mcgrof@drvbp1 /pub/mem/mcgrof/net-next (git::master)$ time make -j 20
...
  BUILD   arch/x86/boot/bzImage
Setup is 16992 bytes (padded to 17408 bytes).
System is 56153 kB
CRC 721d2751
Kernel: arch/x86/boot/bzImage is ready  (#1)
real    19m35.744s
user    280m37.984s
sys     27m54.104s

Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: Ben Hutchings <ben@decadent.org.uk>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Luis R. Rodriguez <mcgrof@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 83 +++++++++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/if.h   | 83 -----------------------------------------------
 2 files changed, 83 insertions(+), 83 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5e84483c0650..1a869488b8ae 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1147,6 +1147,89 @@ struct net_device_ops {
 							void *priv);
 };
 
+/**
+ * enum net_device_priv_flags - &struct net_device priv_flags
+ *
+ * These are the &struct net_device, they are only set internally
+ * by drivers and used in the kernel. These flags are invisible to
+ * userspace, this means that the order of these flags can change
+ * during any kernel release.
+ *
+ * You should have a pretty good reason to be extending these flags.
+ *
+ * @IFF_802_1Q_VLAN: 802.1Q VLAN device
+ * @IFF_EBRIDGE: Ethernet bridging device
+ * @IFF_SLAVE_INACTIVE: bonding slave not the curr. active
+ * @IFF_MASTER_8023AD: bonding master, 802.3ad
+ * @IFF_MASTER_ALB: bonding master, balance-alb
+ * @IFF_BONDING: bonding master or slave
+ * @IFF_SLAVE_NEEDARP: need ARPs for validation
+ * @IFF_ISATAP: ISATAP interface (RFC4214)
+ * @IFF_MASTER_ARPMON: bonding master, ARP mon in use
+ * @IFF_WAN_HDLC: WAN HDLC device
+ * @IFF_XMIT_DST_RELEASE: dev_hard_start_xmit() is allowed to
+ *	release skb->dst
+ * @IFF_DONT_BRIDGE: disallow bridging this ether dev
+ * @IFF_DISABLE_NETPOLL: disable netpoll at run-time
+ * @IFF_MACVLAN_PORT: device used as macvlan port
+ * @IFF_BRIDGE_PORT: device used as bridge port
+ * @IFF_OVS_DATAPATH: device used as Open vSwitch datapath port
+ * @IFF_TX_SKB_SHARING: The interface supports sharing skbs on transmit
+ * @IFF_UNICAST_FLT: Supports unicast filtering
+ * @IFF_TEAM_PORT: device used as team port
+ * @IFF_SUPP_NOFCS: device supports sending custom FCS
+ * @IFF_LIVE_ADDR_CHANGE: device supports hardware address
+ *	change when it's running
+ * @IFF_MACVLAN: Macvlan device
+ */
+enum netdev_priv_flags {
+	IFF_802_1Q_VLAN			= 1<<0,
+	IFF_EBRIDGE			= 1<<1,
+	IFF_SLAVE_INACTIVE		= 1<<2,
+	IFF_MASTER_8023AD		= 1<<3,
+	IFF_MASTER_ALB			= 1<<4,
+	IFF_BONDING			= 1<<5,
+	IFF_SLAVE_NEEDARP		= 1<<6,
+	IFF_ISATAP			= 1<<7,
+	IFF_MASTER_ARPMON		= 1<<8,
+	IFF_WAN_HDLC			= 1<<9,
+	IFF_XMIT_DST_RELEASE		= 1<<10,
+	IFF_DONT_BRIDGE			= 1<<11,
+	IFF_DISABLE_NETPOLL		= 1<<12,
+	IFF_MACVLAN_PORT		= 1<<13,
+	IFF_BRIDGE_PORT			= 1<<14,
+	IFF_OVS_DATAPATH		= 1<<15,
+	IFF_TX_SKB_SHARING		= 1<<16,
+	IFF_UNICAST_FLT			= 1<<17,
+	IFF_TEAM_PORT			= 1<<18,
+	IFF_SUPP_NOFCS			= 1<<19,
+	IFF_LIVE_ADDR_CHANGE		= 1<<20,
+	IFF_MACVLAN			= 1<<21,
+};
+
+#define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
+#define IFF_EBRIDGE			IFF_EBRIDGE
+#define IFF_SLAVE_INACTIVE		IFF_SLAVE_INACTIVE
+#define IFF_MASTER_8023AD		IFF_MASTER_8023AD
+#define IFF_MASTER_ALB			IFF_MASTER_ALB
+#define IFF_BONDING			IFF_BONDING
+#define IFF_SLAVE_NEEDARP		IFF_SLAVE_NEEDARP
+#define IFF_ISATAP			IFF_ISATAP
+#define IFF_MASTER_ARPMON		IFF_MASTER_ARPMON
+#define IFF_WAN_HDLC			IFF_WAN_HDLC
+#define IFF_XMIT_DST_RELEASE		IFF_XMIT_DST_RELEASE
+#define IFF_DONT_BRIDGE			IFF_DONT_BRIDGE
+#define IFF_DISABLE_NETPOLL		IFF_DISABLE_NETPOLL
+#define IFF_MACVLAN_PORT		IFF_MACVLAN_PORT
+#define IFF_BRIDGE_PORT			IFF_BRIDGE_PORT
+#define IFF_OVS_DATAPATH		IFF_OVS_DATAPATH
+#define IFF_TX_SKB_SHARING		IFF_TX_SKB_SHARING
+#define IFF_UNICAST_FLT			IFF_UNICAST_FLT
+#define IFF_TEAM_PORT			IFF_TEAM_PORT
+#define IFF_SUPP_NOFCS			IFF_SUPP_NOFCS
+#define IFF_LIVE_ADDR_CHANGE		IFF_LIVE_ADDR_CHANGE
+#define IFF_MACVLAN			IFF_MACVLAN
+
 /*
  *	The DEVICE structure.
  *	Actually, this whole structure is a big mistake.  It mixes I/O
diff --git a/include/uapi/linux/if.h b/include/uapi/linux/if.h
index 42ec87994cf6..9cf2394f0bcf 100644
--- a/include/uapi/linux/if.h
+++ b/include/uapi/linux/if.h
@@ -112,89 +112,6 @@ enum net_device_flags {
 #define IFF_VOLATILE	(IFF_LOOPBACK|IFF_POINTOPOINT|IFF_BROADCAST|IFF_ECHO|\
 		IFF_MASTER|IFF_SLAVE|IFF_RUNNING|IFF_LOWER_UP|IFF_DORMANT)
 
-/**
- * enum net_device_priv_flags - &struct net_device priv_flags
- *
- * These are the &struct net_device, they are only set internally
- * by drivers and used in the kernel. These flags are invisible to
- * userspace, this means that the order of these flags can change
- * during any kernel release.
- *
- * You should have a pretty good reason to be extending these flags.
- *
- * @IFF_802_1Q_VLAN: 802.1Q VLAN device
- * @IFF_EBRIDGE: Ethernet bridging device
- * @IFF_SLAVE_INACTIVE: bonding slave not the curr. active
- * @IFF_MASTER_8023AD: bonding master, 802.3ad
- * @IFF_MASTER_ALB: bonding master, balance-alb
- * @IFF_BONDING: bonding master or slave
- * @IFF_SLAVE_NEEDARP: need ARPs for validation
- * @IFF_ISATAP: ISATAP interface (RFC4214)
- * @IFF_MASTER_ARPMON: bonding master, ARP mon in use
- * @IFF_WAN_HDLC: WAN HDLC device
- * @IFF_XMIT_DST_RELEASE: dev_hard_start_xmit() is allowed to
- *	release skb->dst
- * @IFF_DONT_BRIDGE: disallow bridging this ether dev
- * @IFF_DISABLE_NETPOLL: disable netpoll at run-time
- * @IFF_MACVLAN_PORT: device used as macvlan port
- * @IFF_BRIDGE_PORT: device used as bridge port
- * @IFF_OVS_DATAPATH: device used as Open vSwitch datapath port
- * @IFF_TX_SKB_SHARING: The interface supports sharing skbs on transmit
- * @IFF_UNICAST_FLT: Supports unicast filtering
- * @IFF_TEAM_PORT: device used as team port
- * @IFF_SUPP_NOFCS: device supports sending custom FCS
- * @IFF_LIVE_ADDR_CHANGE: device supports hardware address
- *	change when it's running
- * @IFF_MACVLAN: Macvlan device
- */
-enum netdev_priv_flags {
-	IFF_802_1Q_VLAN			= 1<<0,
-	IFF_EBRIDGE			= 1<<1,
-	IFF_SLAVE_INACTIVE		= 1<<2,
-	IFF_MASTER_8023AD		= 1<<3,
-	IFF_MASTER_ALB			= 1<<4,
-	IFF_BONDING			= 1<<5,
-	IFF_SLAVE_NEEDARP		= 1<<6,
-	IFF_ISATAP			= 1<<7,
-	IFF_MASTER_ARPMON		= 1<<8,
-	IFF_WAN_HDLC			= 1<<9,
-	IFF_XMIT_DST_RELEASE		= 1<<10,
-	IFF_DONT_BRIDGE			= 1<<11,
-	IFF_DISABLE_NETPOLL		= 1<<12,
-	IFF_MACVLAN_PORT		= 1<<13,
-	IFF_BRIDGE_PORT			= 1<<14,
-	IFF_OVS_DATAPATH		= 1<<15,
-	IFF_TX_SKB_SHARING		= 1<<16,
-	IFF_UNICAST_FLT			= 1<<17,
-	IFF_TEAM_PORT			= 1<<18,
-	IFF_SUPP_NOFCS			= 1<<19,
-	IFF_LIVE_ADDR_CHANGE		= 1<<20,
-	IFF_MACVLAN			= 1<<21,
-};
-
-#define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
-#define IFF_EBRIDGE			IFF_EBRIDGE
-#define IFF_SLAVE_INACTIVE		IFF_SLAVE_INACTIVE
-#define IFF_MASTER_8023AD		IFF_MASTER_8023AD
-#define IFF_MASTER_ALB			IFF_MASTER_ALB
-#define IFF_BONDING			IFF_BONDING
-#define IFF_SLAVE_NEEDARP		IFF_SLAVE_NEEDARP
-#define IFF_ISATAP			IFF_ISATAP
-#define IFF_MASTER_ARPMON		IFF_MASTER_ARPMON
-#define IFF_WAN_HDLC			IFF_WAN_HDLC
-#define IFF_XMIT_DST_RELEASE		IFF_XMIT_DST_RELEASE
-#define IFF_DONT_BRIDGE			IFF_DONT_BRIDGE
-#define IFF_DISABLE_NETPOLL		IFF_DISABLE_NETPOLL
-#define IFF_MACVLAN_PORT		IFF_MACVLAN_PORT
-#define IFF_BRIDGE_PORT			IFF_BRIDGE_PORT
-#define IFF_OVS_DATAPATH		IFF_OVS_DATAPATH
-#define IFF_TX_SKB_SHARING		IFF_TX_SKB_SHARING
-#define IFF_UNICAST_FLT			IFF_UNICAST_FLT
-#define IFF_TEAM_PORT			IFF_TEAM_PORT
-#define IFF_SUPP_NOFCS			IFF_SUPP_NOFCS
-#define IFF_LIVE_ADDR_CHANGE		IFF_LIVE_ADDR_CHANGE
-#define IFF_MACVLAN			IFF_MACVLAN
-
 #define IF_GET_IFACE	0x0001		/* for querying only */
 #define IF_GET_PROTO	0x0002
 
-- 
cgit v1.2.3


From 2516ae8a69c3e21771cd0095a0dd10160fa055a4 Mon Sep 17 00:00:00 2001
From: Alexander Shiyan <shc_work@mail.ru>
Date: Sat, 15 Feb 2014 09:56:22 +0400
Subject: video: imxfb: Remove dead declaration of set_imx_fb_info()

Function set_imx_fb_info() is missing in the kernel code,
so remove the dead declaration.

Signed-off-by: Alexander Shiyan <shc_work@mail.ru>
Acked-by: Sascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 include/linux/platform_data/video-imxfb.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/video-imxfb.h b/include/linux/platform_data/video-imxfb.h
index 8902706fffa4..dd1bed97683c 100644
--- a/include/linux/platform_data/video-imxfb.h
+++ b/include/linux/platform_data/video-imxfb.h
@@ -79,5 +79,4 @@ struct imx_fb_platform_data {
 	void (*backlight_power)(int);
 };
 
-void set_imx_fb_info(struct imx_fb_platform_data *);
 #endif /* ifndef __MACH_IMXFB_H__ */
-- 
cgit v1.2.3


From b7d2d37276c1dce86d9a55239f0686e1bd81a37f Mon Sep 17 00:00:00 2001
From: Alexander Shiyan <shc_work@mail.ru>
Date: Sat, 15 Feb 2014 09:56:23 +0400
Subject: video: imxfb: Remove unused fields from platform data structure

Some fields in platform data structure is never used by boards.
This patch removes these fields and as a result optimizes private
driver structure a bit. Additionally patch removes backligh_power()
callback, so if it will be needed in the future, this feature should
be added as pwm{gpio,etc.}-regulator to the board code or in the DTS.

Signed-off-by: Alexander Shiyan <shc_work@mail.ru>
Acked-by: Sascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/video/imxfb.c                     | 64 ++++++++-----------------------
 include/linux/platform_data/video-imxfb.h | 10 -----
 2 files changed, 17 insertions(+), 57 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/video/imxfb.c b/drivers/video/imxfb.c
index e50b67fada51..5b07053bbd01 100644
--- a/drivers/video/imxfb.c
+++ b/drivers/video/imxfb.c
@@ -156,11 +156,8 @@ struct imxfb_info {
 	 * the framebuffer memory region to.
 	 */
 	dma_addr_t		map_dma;
-	u_char			*map_cpu;
 	u_int			map_size;
 
-	u_char			*screen_cpu;
-	dma_addr_t		screen_dma;
 	u_int			palette_size;
 
 	dma_addr_t		dbar1;
@@ -170,9 +167,8 @@ struct imxfb_info {
 	u_int			pwmr;
 	u_int			lscr1;
 	u_int			dmacr;
-	u_int			cmap_inverse:1,
-				cmap_static:1,
-				unused:30;
+	bool			cmap_inverse;
+	bool			cmap_static;
 
 	struct imx_fb_videomode *mode;
 	int			num_modes;
@@ -180,8 +176,6 @@ struct imxfb_info {
 	struct backlight_device *bl;
 #endif
 
-	void (*backlight_power)(int);
-
 	struct regulator	*lcd_pwr;
 };
 
@@ -573,7 +567,7 @@ static void imxfb_enable_controller(struct imxfb_info *fbi)
 
 	pr_debug("Enabling LCD controller\n");
 
-	writel(fbi->screen_dma, fbi->regs + LCDC_SSA);
+	writel(fbi->map_dma, fbi->regs + LCDC_SSA);
 
 	/* panning offset 0 (0 pixel offset)        */
 	writel(0x00000000, fbi->regs + LCDC_POS);
@@ -592,9 +586,6 @@ static void imxfb_enable_controller(struct imxfb_info *fbi)
 	clk_prepare_enable(fbi->clk_ahb);
 	clk_prepare_enable(fbi->clk_per);
 	fbi->enabled = true;
-
-	if (fbi->backlight_power)
-		fbi->backlight_power(1);
 }
 
 static void imxfb_disable_controller(struct imxfb_info *fbi)
@@ -604,9 +595,6 @@ static void imxfb_disable_controller(struct imxfb_info *fbi)
 
 	pr_debug("Disabling LCD controller\n");
 
-	if (fbi->backlight_power)
-		fbi->backlight_power(0);
-
 	clk_disable_unprepare(fbi->clk_per);
 	clk_disable_unprepare(fbi->clk_ipg);
 	clk_disable_unprepare(fbi->clk_ahb);
@@ -790,13 +778,9 @@ static int imxfb_init_fbinfo(struct platform_device *pdev)
 	info->flags			= FBINFO_FLAG_DEFAULT |
 					  FBINFO_READS_FAST;
 	if (pdata) {
-		info->var.grayscale		= pdata->cmap_greyscale;
-		fbi->cmap_inverse		= pdata->cmap_inverse;
-		fbi->cmap_static		= pdata->cmap_static;
 		fbi->lscr1			= pdata->lscr1;
 		fbi->dmacr			= pdata->dmacr;
 		fbi->pwmr			= pdata->pwmr;
-		fbi->backlight_power		= pdata->backlight_power;
 	} else {
 		np = pdev->dev.of_node;
 		info->var.grayscale = of_property_read_bool(np,
@@ -808,8 +792,6 @@ static int imxfb_init_fbinfo(struct platform_device *pdev)
 		of_property_read_u32(np, "fsl,lscr1", &fbi->lscr1);
 
 		of_property_read_u32(np, "fsl,dmacr", &fbi->dmacr);
-
-		fbi->backlight_power = NULL;
 	}
 
 	return 0;
@@ -1003,32 +985,18 @@ static int imxfb_probe(struct platform_device *pdev)
 		goto failed_ioremap;
 	}
 
-	/* Seems not being used by anyone, so no support for oftree */
-	if (!pdata || !pdata->fixed_screen_cpu) {
-		fbi->map_size = PAGE_ALIGN(info->fix.smem_len);
-		fbi->map_cpu = dma_alloc_writecombine(&pdev->dev,
-				fbi->map_size, &fbi->map_dma, GFP_KERNEL);
+	fbi->map_size = PAGE_ALIGN(info->fix.smem_len);
+	info->screen_base = dma_alloc_writecombine(&pdev->dev, fbi->map_size,
+						   &fbi->map_dma, GFP_KERNEL);
 
-		if (!fbi->map_cpu) {
-			dev_err(&pdev->dev, "Failed to allocate video RAM: %d\n", ret);
-			ret = -ENOMEM;
-			goto failed_map;
-		}
-
-		info->screen_base = fbi->map_cpu;
-		fbi->screen_cpu = fbi->map_cpu;
-		fbi->screen_dma = fbi->map_dma;
-		info->fix.smem_start = fbi->screen_dma;
-	} else {
-		/* Fixed framebuffer mapping enables location of the screen in eSRAM */
-		fbi->map_cpu = pdata->fixed_screen_cpu;
-		fbi->map_dma = pdata->fixed_screen_dma;
-		info->screen_base = fbi->map_cpu;
-		fbi->screen_cpu = fbi->map_cpu;
-		fbi->screen_dma = fbi->map_dma;
-		info->fix.smem_start = fbi->screen_dma;
+	if (!info->screen_base) {
+		dev_err(&pdev->dev, "Failed to allocate video RAM: %d\n", ret);
+		ret = -ENOMEM;
+		goto failed_map;
 	}
 
+	info->fix.smem_start = fbi->map_dma;
+
 	if (pdata && pdata->init) {
 		ret = pdata->init(fbi->pdev);
 		if (ret)
@@ -1087,9 +1055,8 @@ failed_cmap:
 	if (pdata && pdata->exit)
 		pdata->exit(fbi->pdev);
 failed_platform_init:
-	if (pdata && !pdata->fixed_screen_cpu)
-		dma_free_writecombine(&pdev->dev,fbi->map_size,fbi->map_cpu,
-			fbi->map_dma);
+	dma_free_writecombine(&pdev->dev, fbi->map_size, info->screen_base,
+			      fbi->map_dma);
 failed_map:
 	iounmap(fbi->regs);
 failed_ioremap:
@@ -1127,6 +1094,9 @@ static int imxfb_remove(struct platform_device *pdev)
 	kfree(info->pseudo_palette);
 	framebuffer_release(info);
 
+	dma_free_writecombine(&pdev->dev, fbi->map_size, info->screen_base,
+			      fbi->map_dma);
+
 	iounmap(fbi->regs);
 	release_mem_region(res->start, resource_size(res));
 
diff --git a/include/linux/platform_data/video-imxfb.h b/include/linux/platform_data/video-imxfb.h
index dd1bed97683c..18e908324549 100644
--- a/include/linux/platform_data/video-imxfb.h
+++ b/include/linux/platform_data/video-imxfb.h
@@ -61,22 +61,12 @@ struct imx_fb_platform_data {
 	struct imx_fb_videomode *mode;
 	int		num_modes;
 
-	u_int		cmap_greyscale:1,
-			cmap_inverse:1,
-			cmap_static:1,
-			unused:29;
-
 	u_int		pwmr;
 	u_int		lscr1;
 	u_int		dmacr;
 
-	u_char * fixed_screen_cpu;
-	dma_addr_t fixed_screen_dma;
-
 	int (*init)(struct platform_device *);
 	void (*exit)(struct platform_device *);
-
-	void (*backlight_power)(int);
 };
 
 #endif /* ifndef __MACH_IMXFB_H__ */
-- 
cgit v1.2.3


From 946651cba26779864bcdbd7e12502f5a36c2de37 Mon Sep 17 00:00:00 2001
From: Luciano Coelho <coelho@ti.com>
Date: Sat, 15 Feb 2014 00:05:52 +0100
Subject: wl1251: split wl251 platform data to a separate structure

Move the wl1251 part of the wl12xx platform data structure into a new
structure specifically for wl1251.  Change the platform data built-in
block and board files accordingly.

Signed-off-by: Luciano Coelho <coelho@ti.com>
Acked-by: Tony Lindgren <tony@atomide.com>
Reviewed-by: Felipe Balbi <balbi@ti.com>
Reviewed-by: Sebastian Reichel <sre@debian.org>
Reviewed-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 arch/arm/mach-omap2/board-omap3pandora.c       |  4 +--
 arch/arm/mach-omap2/board-rx51-peripherals.c   |  2 +-
 drivers/net/wireless/ti/wilink_platform_data.c | 37 +++++++++++++++++++++-----
 drivers/net/wireless/ti/wl1251/sdio.c          | 12 ++++-----
 drivers/net/wireless/ti/wl1251/spi.c           |  2 +-
 include/linux/wl12xx.h                         | 22 ++++++++++++++-
 6 files changed, 62 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-omap2/board-omap3pandora.c b/arch/arm/mach-omap2/board-omap3pandora.c
index de1bc6bbe585..24f3c1be69a5 100644
--- a/arch/arm/mach-omap2/board-omap3pandora.c
+++ b/arch/arm/mach-omap2/board-omap3pandora.c
@@ -536,7 +536,7 @@ static struct spi_board_info omap3pandora_spi_board_info[] __initdata = {
 
 static void __init pandora_wl1251_init(void)
 {
-	struct wl12xx_platform_data pandora_wl1251_pdata;
+	struct wl1251_platform_data pandora_wl1251_pdata;
 	int ret;
 
 	memset(&pandora_wl1251_pdata, 0, sizeof(pandora_wl1251_pdata));
@@ -550,7 +550,7 @@ static void __init pandora_wl1251_init(void)
 		goto fail_irq;
 
 	pandora_wl1251_pdata.use_eeprom = true;
-	ret = wl12xx_set_platform_data(&pandora_wl1251_pdata);
+	ret = wl1251_set_platform_data(&pandora_wl1251_pdata);
 	if (ret < 0)
 		goto fail_irq;
 
diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c
index 8760bbe3baab..e05e740a4426 100644
--- a/arch/arm/mach-omap2/board-rx51-peripherals.c
+++ b/arch/arm/mach-omap2/board-rx51-peripherals.c
@@ -84,7 +84,7 @@ enum {
 	RX51_SPI_MIPID,		/* LCD panel */
 };
 
-static struct wl12xx_platform_data wl1251_pdata;
+static struct wl1251_platform_data wl1251_pdata;
 static struct tsc2005_platform_data tsc2005_pdata;
 
 #if defined(CONFIG_SENSORS_LIS3_I2C) || defined(CONFIG_SENSORS_LIS3_I2C_MODULE)
diff --git a/drivers/net/wireless/ti/wilink_platform_data.c b/drivers/net/wireless/ti/wilink_platform_data.c
index 998e95895f9d..a92bd3e89796 100644
--- a/drivers/net/wireless/ti/wilink_platform_data.c
+++ b/drivers/net/wireless/ti/wilink_platform_data.c
@@ -23,17 +23,17 @@
 #include <linux/err.h>
 #include <linux/wl12xx.h>
 
-static struct wl12xx_platform_data *platform_data;
+static struct wl12xx_platform_data *wl12xx_platform_data;
 
 int __init wl12xx_set_platform_data(const struct wl12xx_platform_data *data)
 {
-	if (platform_data)
+	if (wl12xx_platform_data)
 		return -EBUSY;
 	if (!data)
 		return -EINVAL;
 
-	platform_data = kmemdup(data, sizeof(*data), GFP_KERNEL);
-	if (!platform_data)
+	wl12xx_platform_data = kmemdup(data, sizeof(*data), GFP_KERNEL);
+	if (!wl12xx_platform_data)
 		return -ENOMEM;
 
 	return 0;
@@ -41,9 +41,34 @@ int __init wl12xx_set_platform_data(const struct wl12xx_platform_data *data)
 
 struct wl12xx_platform_data *wl12xx_get_platform_data(void)
 {
-	if (!platform_data)
+	if (!wl12xx_platform_data)
 		return ERR_PTR(-ENODEV);
 
-	return platform_data;
+	return wl12xx_platform_data;
 }
 EXPORT_SYMBOL(wl12xx_get_platform_data);
+
+static struct wl1251_platform_data *wl1251_platform_data;
+
+int __init wl1251_set_platform_data(const struct wl1251_platform_data *data)
+{
+	if (wl1251_platform_data)
+		return -EBUSY;
+	if (!data)
+		return -EINVAL;
+
+	wl1251_platform_data = kmemdup(data, sizeof(*data), GFP_KERNEL);
+	if (!wl1251_platform_data)
+		return -ENOMEM;
+
+	return 0;
+}
+
+struct wl1251_platform_data *wl1251_get_platform_data(void)
+{
+	if (!wl1251_platform_data)
+		return ERR_PTR(-ENODEV);
+
+	return wl1251_platform_data;
+}
+EXPORT_SYMBOL(wl1251_get_platform_data);
diff --git a/drivers/net/wireless/ti/wl1251/sdio.c b/drivers/net/wireless/ti/wl1251/sdio.c
index e2b3d9c541e8..b75a37a58313 100644
--- a/drivers/net/wireless/ti/wl1251/sdio.c
+++ b/drivers/net/wireless/ti/wl1251/sdio.c
@@ -227,7 +227,7 @@ static int wl1251_sdio_probe(struct sdio_func *func,
 	struct wl1251 *wl;
 	struct ieee80211_hw *hw;
 	struct wl1251_sdio *wl_sdio;
-	const struct wl12xx_platform_data *wl12xx_board_data;
+	const struct wl1251_platform_data *wl1251_board_data;
 
 	hw = wl1251_alloc_hw();
 	if (IS_ERR(hw))
@@ -254,11 +254,11 @@ static int wl1251_sdio_probe(struct sdio_func *func,
 	wl->if_priv = wl_sdio;
 	wl->if_ops = &wl1251_sdio_ops;
 
-	wl12xx_board_data = wl12xx_get_platform_data();
-	if (!IS_ERR(wl12xx_board_data)) {
-		wl->set_power = wl12xx_board_data->set_power;
-		wl->irq = wl12xx_board_data->irq;
-		wl->use_eeprom = wl12xx_board_data->use_eeprom;
+	wl1251_board_data = wl1251_get_platform_data();
+	if (!IS_ERR(wl1251_board_data)) {
+		wl->set_power = wl1251_board_data->set_power;
+		wl->irq = wl1251_board_data->irq;
+		wl->use_eeprom = wl1251_board_data->use_eeprom;
 	}
 
 	if (wl->irq) {
diff --git a/drivers/net/wireless/ti/wl1251/spi.c b/drivers/net/wireless/ti/wl1251/spi.c
index 1342f81e683d..62403a147592 100644
--- a/drivers/net/wireless/ti/wl1251/spi.c
+++ b/drivers/net/wireless/ti/wl1251/spi.c
@@ -238,7 +238,7 @@ static const struct wl1251_if_operations wl1251_spi_ops = {
 
 static int wl1251_spi_probe(struct spi_device *spi)
 {
-	struct wl12xx_platform_data *pdata;
+	struct wl1251_platform_data *pdata;
 	struct ieee80211_hw *hw;
 	struct wl1251 *wl;
 	int ret;
diff --git a/include/linux/wl12xx.h b/include/linux/wl12xx.h
index a54fe82e704b..b516b4fa22de 100644
--- a/include/linux/wl12xx.h
+++ b/include/linux/wl12xx.h
@@ -48,11 +48,15 @@ enum {
 	WL12XX_TCXOCLOCK_33_6	= 7, /* 33.6 MHz */
 };
 
-struct wl12xx_platform_data {
+struct wl1251_platform_data {
 	void (*set_power)(bool enable);
 	/* SDIO only: IRQ number if WLAN_IRQ line is used, 0 for SDIO IRQs */
 	int irq;
 	bool use_eeprom;
+};
+
+struct wl12xx_platform_data {
+	int irq;
 	int board_ref_clock;
 	int board_tcxo_clock;
 	unsigned long platform_quirks;
@@ -68,6 +72,10 @@ int wl12xx_set_platform_data(const struct wl12xx_platform_data *data);
 
 struct wl12xx_platform_data *wl12xx_get_platform_data(void);
 
+int wl1251_set_platform_data(const struct wl1251_platform_data *data);
+
+struct wl1251_platform_data *wl1251_get_platform_data(void);
+
 #else
 
 static inline
@@ -82,6 +90,18 @@ struct wl12xx_platform_data *wl12xx_get_platform_data(void)
 	return ERR_PTR(-ENODATA);
 }
 
+static inline
+int wl1251_set_platform_data(const struct wl1251_platform_data *data)
+{
+	return -ENOSYS;
+}
+
+static inline
+struct wl1251_platform_data *wl1251_get_platform_data(void)
+{
+	return ERR_PTR(-ENODATA);
+}
+
 #endif
 
 #endif
-- 
cgit v1.2.3


From 1d207cd30b65fdd60d952cb9e100b6f776564f06 Mon Sep 17 00:00:00 2001
From: Sebastian Reichel <sre@debian.org>
Date: Sat, 15 Feb 2014 00:05:53 +0100
Subject: wl1251: move power GPIO handling into the driver

Move the power GPIO handling from the board code into
the driver. This is a dependency for device tree support.

Signed-off-by: Sebastian Reichel <sre@debian.org>
Reviewed-by: Pavel Machek <pavel@ucw.cz>
Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 arch/arm/mach-omap2/board-omap3pandora.c     |  2 ++
 arch/arm/mach-omap2/board-rx51-peripherals.c | 11 ++--------
 drivers/net/wireless/ti/wl1251/sdio.c        | 21 +++++++++++++-----
 drivers/net/wireless/ti/wl1251/spi.c         | 33 ++++++++++++++++++----------
 drivers/net/wireless/ti/wl1251/wl1251.h      |  2 +-
 include/linux/wl12xx.h                       |  2 +-
 6 files changed, 43 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-omap2/board-omap3pandora.c b/arch/arm/mach-omap2/board-omap3pandora.c
index 24f3c1be69a5..cf18340eb3bb 100644
--- a/arch/arm/mach-omap2/board-omap3pandora.c
+++ b/arch/arm/mach-omap2/board-omap3pandora.c
@@ -541,6 +541,8 @@ static void __init pandora_wl1251_init(void)
 
 	memset(&pandora_wl1251_pdata, 0, sizeof(pandora_wl1251_pdata));
 
+	pandora_wl1251_pdata.power_gpio = -1;
+
 	ret = gpio_request_one(PANDORA_WIFI_IRQ_GPIO, GPIOF_IN, "wl1251 irq");
 	if (ret < 0)
 		goto fail;
diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c
index e05e740a4426..ddfc8df83c6a 100644
--- a/arch/arm/mach-omap2/board-rx51-peripherals.c
+++ b/arch/arm/mach-omap2/board-rx51-peripherals.c
@@ -1173,13 +1173,7 @@ static inline void board_smc91x_init(void)
 
 #endif
 
-static void rx51_wl1251_set_power(bool enable)
-{
-	gpio_set_value(RX51_WL1251_POWER_GPIO, enable);
-}
-
 static struct gpio rx51_wl1251_gpios[] __initdata = {
-	{ RX51_WL1251_POWER_GPIO, GPIOF_OUT_INIT_LOW,	"wl1251 power"	},
 	{ RX51_WL1251_IRQ_GPIO,	  GPIOF_IN,		"wl1251 irq"	},
 };
 
@@ -1196,17 +1190,16 @@ static void __init rx51_init_wl1251(void)
 	if (irq < 0)
 		goto err_irq;
 
-	wl1251_pdata.set_power = rx51_wl1251_set_power;
+	wl1251_pdata.power_gpio = RX51_WL1251_POWER_GPIO;
 	rx51_peripherals_spi_board_info[RX51_SPI_WL1251].irq = irq;
 
 	return;
 
 err_irq:
 	gpio_free(RX51_WL1251_IRQ_GPIO);
-	gpio_free(RX51_WL1251_POWER_GPIO);
 error:
 	printk(KERN_ERR "wl1251 board initialisation failed\n");
-	wl1251_pdata.set_power = NULL;
+	wl1251_pdata.power_gpio = -1;
 
 	/*
 	 * Now rx51_peripherals_spi_board_info[1].irq is zero and
diff --git a/drivers/net/wireless/ti/wl1251/sdio.c b/drivers/net/wireless/ti/wl1251/sdio.c
index b75a37a58313..b661f896e9fe 100644
--- a/drivers/net/wireless/ti/wl1251/sdio.c
+++ b/drivers/net/wireless/ti/wl1251/sdio.c
@@ -28,6 +28,7 @@
 #include <linux/wl12xx.h>
 #include <linux/irq.h>
 #include <linux/pm_runtime.h>
+#include <linux/gpio.h>
 
 #include "wl1251.h"
 
@@ -182,8 +183,9 @@ static int wl1251_sdio_set_power(struct wl1251 *wl, bool enable)
 		 * callback in case it wants to do any additional setup,
 		 * for example enabling clock buffer for the module.
 		 */
-		if (wl->set_power)
-			wl->set_power(true);
+		if (gpio_is_valid(wl->power_gpio))
+			gpio_set_value(wl->power_gpio, true);
+
 
 		ret = pm_runtime_get_sync(&func->dev);
 		if (ret < 0) {
@@ -203,8 +205,8 @@ static int wl1251_sdio_set_power(struct wl1251 *wl, bool enable)
 		if (ret < 0)
 			goto out;
 
-		if (wl->set_power)
-			wl->set_power(false);
+		if (gpio_is_valid(wl->power_gpio))
+			gpio_set_value(wl->power_gpio, false);
 	}
 
 out:
@@ -256,11 +258,20 @@ static int wl1251_sdio_probe(struct sdio_func *func,
 
 	wl1251_board_data = wl1251_get_platform_data();
 	if (!IS_ERR(wl1251_board_data)) {
-		wl->set_power = wl1251_board_data->set_power;
+		wl->power_gpio = wl1251_board_data->power_gpio;
 		wl->irq = wl1251_board_data->irq;
 		wl->use_eeprom = wl1251_board_data->use_eeprom;
 	}
 
+	if (gpio_is_valid(wl->power_gpio)) {
+		ret = devm_gpio_request(&func->dev, wl->power_gpio,
+								"wl1251 power");
+		if (ret) {
+			wl1251_error("Failed to request gpio: %d\n", ret);
+			goto disable;
+		}
+	}
+
 	if (wl->irq) {
 		irq_set_status_flags(wl->irq, IRQ_NOAUTOEN);
 		ret = request_irq(wl->irq, wl1251_line_irq, 0, "wl1251", wl);
diff --git a/drivers/net/wireless/ti/wl1251/spi.c b/drivers/net/wireless/ti/wl1251/spi.c
index 62403a147592..6abcbc3f7fc7 100644
--- a/drivers/net/wireless/ti/wl1251/spi.c
+++ b/drivers/net/wireless/ti/wl1251/spi.c
@@ -26,6 +26,7 @@
 #include <linux/crc7.h>
 #include <linux/spi/spi.h>
 #include <linux/wl12xx.h>
+#include <linux/gpio.h>
 
 #include "wl1251.h"
 #include "reg.h"
@@ -221,8 +222,8 @@ static void wl1251_spi_disable_irq(struct wl1251 *wl)
 
 static int wl1251_spi_set_power(struct wl1251 *wl, bool enable)
 {
-	if (wl->set_power)
-		wl->set_power(enable);
+	if (gpio_is_valid(wl->power_gpio))
+		gpio_set_value(wl->power_gpio, enable);
 
 	return 0;
 }
@@ -271,22 +272,33 @@ static int wl1251_spi_probe(struct spi_device *spi)
 		goto out_free;
 	}
 
-	wl->set_power = pdata->set_power;
-	if (!wl->set_power) {
-		wl1251_error("set power function missing in platform data");
-		return -ENODEV;
+	wl->power_gpio = pdata->power_gpio;
+
+	if (gpio_is_valid(wl->power_gpio)) {
+		ret = devm_gpio_request_one(&spi->dev, wl->power_gpio,
+					GPIOF_OUT_INIT_LOW, "wl1251 power");
+		if (ret) {
+			wl1251_error("Failed to request gpio: %d\n", ret);
+			goto out_free;
+		}
+	} else {
+		wl1251_error("set power gpio missing in platform data");
+		ret = -ENODEV;
+		goto out_free;
 	}
 
 	wl->irq = spi->irq;
 	if (wl->irq < 0) {
 		wl1251_error("irq missing in platform data");
-		return -ENODEV;
+		ret = -ENODEV;
+		goto out_free;
 	}
 
 	wl->use_eeprom = pdata->use_eeprom;
 
 	irq_set_status_flags(wl->irq, IRQ_NOAUTOEN);
-	ret = request_irq(wl->irq, wl1251_irq, 0, DRIVER_NAME, wl);
+	ret = devm_request_irq(&spi->dev, wl->irq, wl1251_irq, 0,
+							DRIVER_NAME, wl);
 	if (ret < 0) {
 		wl1251_error("request_irq() failed: %d", ret);
 		goto out_free;
@@ -296,13 +308,10 @@ static int wl1251_spi_probe(struct spi_device *spi)
 
 	ret = wl1251_init_ieee80211(wl);
 	if (ret)
-		goto out_irq;
+		goto out_free;
 
 	return 0;
 
- out_irq:
-	free_irq(wl->irq, wl);
-
  out_free:
 	ieee80211_free_hw(hw);
 
diff --git a/drivers/net/wireless/ti/wl1251/wl1251.h b/drivers/net/wireless/ti/wl1251/wl1251.h
index 235617a7716d..389fe25af1b6 100644
--- a/drivers/net/wireless/ti/wl1251/wl1251.h
+++ b/drivers/net/wireless/ti/wl1251/wl1251.h
@@ -276,7 +276,7 @@ struct wl1251 {
 	void *if_priv;
 	const struct wl1251_if_operations *if_ops;
 
-	void (*set_power)(bool enable);
+	int power_gpio;
 	int irq;
 	bool use_eeprom;
 
diff --git a/include/linux/wl12xx.h b/include/linux/wl12xx.h
index b516b4fa22de..a9c723be1acf 100644
--- a/include/linux/wl12xx.h
+++ b/include/linux/wl12xx.h
@@ -49,7 +49,7 @@ enum {
 };
 
 struct wl1251_platform_data {
-	void (*set_power)(bool enable);
+	int power_gpio;
 	/* SDIO only: IRQ number if WLAN_IRQ line is used, 0 for SDIO IRQs */
 	int irq;
 	bool use_eeprom;
-- 
cgit v1.2.3


From 3ebe8e257307a87c33460aa7d2b75dadd374ed9c Mon Sep 17 00:00:00 2001
From: "Zhao, Gang" <gamerh2o@gmail.com>
Date: Tue, 18 Feb 2014 21:36:03 +0800
Subject: ieee80211: remove function ieee80211_{dsss_chan_to_freq,
 freq_to_dsss_chan}

Function ieee80211_{dsss_chan_to_freq, freq_to_dsss_chan} have been
replaced with ieee80211_{channel_to_frequency, frequency_to_channel}.

There should be no users of the two functions now. So remove them.

Cc: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Zhao, Gang <gamerh2o@gmail.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 include/linux/ieee80211.h | 36 ------------------------------------
 1 file changed, 36 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 5f349355ee54..06299048c4f4 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2307,42 +2307,6 @@ static inline bool ieee80211_is_public_action(struct ieee80211_hdr *hdr,
 	return mgmt->u.action.category == WLAN_CATEGORY_PUBLIC;
 }
 
-/**
- * ieee80211_dsss_chan_to_freq - get channel center frequency
- * @channel: the DSSS channel
- *
- * Convert IEEE802.11 DSSS channel to the center frequency (MHz).
- * Ref IEEE 802.11-2007 section 15.6
- */
-static inline int ieee80211_dsss_chan_to_freq(int channel)
-{
-	if ((channel > 0) && (channel < 14))
-		return 2407 + (channel * 5);
-	else if (channel == 14)
-		return 2484;
-	else
-		return -1;
-}
-
-/**
- * ieee80211_freq_to_dsss_chan - get channel
- * @freq: the frequency
- *
- * Convert frequency (MHz) to IEEE802.11 DSSS channel
- * Ref IEEE 802.11-2007 section 15.6
- *
- * This routine selects the channel with the closest center frequency.
- */
-static inline int ieee80211_freq_to_dsss_chan(int freq)
-{
-	if ((freq >= 2410) && (freq < 2475))
-		return (freq - 2405) / 5;
-	else if ((freq >= 2482) && (freq < 2487))
-		return 14;
-	else
-		return -1;
-}
-
 /**
  * ieee80211_tu_to_usec - convert time units (TU) to microseconds
  * @tu: the TUs
-- 
cgit v1.2.3


From 2e70efd9afab7a512b6e2e164bf5c25fd3ce6aae Mon Sep 17 00:00:00 2001
From: Alessandro Rubini <rubini@gnudd.com>
Date: Sat, 22 Feb 2014 09:11:24 +0100
Subject: FMC: show_sdb_tree: dump synthesis/commit ID info

This completes the show_sdb_tree functionality, with the
new informative fields.  The output for a verbose module is now
like this (long lines are unavoidable):

 SDB: 00000651:e6a542c9 WB4-Crossbar-GSI
 SDB: 0000ce42:00000601 WB-DMA.Control      (00001000-0000103f)
 SDB: 0000ce42:779c5443 WB-OneWire-Master   (00001100-000011ff)
 SDB: 0000ce42:00000603 WB-SPEC-CSR         (00001200-0000121f)
 SDB: 0000ce42:00000013 WB-VIC-Int.Control  (00001300-000013ff)
 SDB: 0000ce42:d5735ab4 WB-DMA.EIC          (00001400-0000140f)
 SDB: 00000651:eef0b198 WB4-Bridge-GSI      (bridge: 00002000)
 SDB:    00000651:e6a542c9 WB4-Crossbar-GSI
 SDB:    0000ce42:123c5443 WB-I2C-Master       (00003000-000030ff)
 SDB:    0000ce42:e503947e WB-SPI.Control      (00003100-0000311f)
 SDB:    0000ce42:123c5443 WB-I2C-Master       (00003200-000032ff)
 SDB:    0000ce42:00000608 WB-FMC-ADC-Core     (00003300-0000337f)
 SDB:    0000ce42:779c5443 WB-OneWire-Master   (00003400-000034ff)
 SDB:    0000ce42:26ec6086 WB-FMC-ADC.EIC      (00003500-0000350f)
 SDB:    0000ce42:00000604 WB-Timetag-Core     (00003600-0000367f)
 SDB: Synthesis repository: git://ohwr.org/fmc-projects/fmc-adc-100m14b4cha.git
 SDB: Bitstream 'spec_top_fmc_adcmc-projects/fmc-adc-100m14b4cha.git' \
         synthesized 20140116 by mcattin (ISE version 133), commit f0a539dffe6d

Signed-off-by: Tomasz Wlostowski <tomasz.wlostowski@cern.ch>
Acked-by: Alessandro Rubini <rubini@gnudd.com>
Acked-by: Juan David Gonzalez Cobas <dcobas@cern.ch>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/fmc/fmc-sdb.c   | 34 ++++++++++++++++++++++++++++++----
 include/linux/fmc-sdb.h |  2 ++
 2 files changed, 32 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/fmc/fmc-sdb.c b/drivers/fmc/fmc-sdb.c
index 69f42d70bc74..4603fdb74465 100644
--- a/drivers/fmc/fmc-sdb.c
+++ b/drivers/fmc/fmc-sdb.c
@@ -150,11 +150,27 @@ int fmc_reprogram(struct fmc_device *fmc, struct fmc_driver *d, char *gw,
 }
 EXPORT_SYMBOL(fmc_reprogram);
 
+static char *__strip_trailing_space(char *buf, char *str, int len)
+{
+	int i = len - 1;
+
+	memcpy(buf, str, len);
+	while(i >= 0 && buf[i] == ' ')
+		buf[i--] = '\0';
+	return buf;
+}
+
+#define __sdb_string(buf, field) ({			\
+	BUILD_BUG_ON(sizeof(buf) < sizeof(field));	\
+	__strip_trailing_space(buf, (void *)(field), sizeof(field));	\
+		})
+
 static void __fmc_show_sdb_tree(const struct fmc_device *fmc,
 				const struct sdb_array *arr)
 {
 	unsigned long base = arr->baseaddr;
 	int i, j, n = arr->len, level = arr->level;
+	char buf[64];
 
 	for (i = 0; i < n; i++) {
 		union  sdb_record *r;
@@ -190,8 +206,8 @@ static void __fmc_show_sdb_tree(const struct fmc_device *fmc,
 			       p->name,
 			       __be64_to_cpu(c->addr_first) + base);
 			if (IS_ERR(arr->subtree[i])) {
-				printk(KERN_CONT "(bridge error %li)\n",
-				       PTR_ERR(arr->subtree[i]));
+				dev_info(&fmc->dev, "SDB: (bridge error %li)\n",
+					 PTR_ERR(arr->subtree[i]));
 				break;
 			}
 			__fmc_show_sdb_tree(fmc, arr->subtree[i]);
@@ -200,10 +216,20 @@ static void __fmc_show_sdb_tree(const struct fmc_device *fmc,
 			printk(KERN_CONT "integration\n");
 			break;
 		case sdb_type_repo_url:
-			printk(KERN_CONT "repo-url\n");
+			printk(KERN_CONT "Synthesis repository: %s\n",
+			       __sdb_string(buf, r->repo_url.repo_url));
 			break;
 		case sdb_type_synthesis:
-			printk(KERN_CONT "synthesis-info\n");
+			printk(KERN_CONT "Bitstream '%s' ",
+			       __sdb_string(buf, r->synthesis.syn_name));
+			printk(KERN_CONT "synthesized %08x by %s ",
+			       __be32_to_cpu(r->synthesis.date),
+			       __sdb_string(buf, r->synthesis.user_name));
+			printk(KERN_CONT "(%s version %x), ",
+			       __sdb_string(buf, r->synthesis.tool_name),
+			       __be32_to_cpu(r->synthesis.tool_version));
+			printk(KERN_CONT "commit %pm\n",
+			       r->synthesis.commit_id);
 			break;
 		case sdb_type_empty:
 			printk(KERN_CONT "empty\n");
diff --git a/include/linux/fmc-sdb.h b/include/linux/fmc-sdb.h
index 1974317a9b3d..599bd6bab56d 100644
--- a/include/linux/fmc-sdb.h
+++ b/include/linux/fmc-sdb.h
@@ -14,6 +14,8 @@ union sdb_record {
 	struct sdb_bridge bridge;
 	struct sdb_integration integr;
 	struct sdb_empty empty;
+	struct sdb_synthesis synthesis;
+	struct sdb_repo_url repo_url;
 };
 
 struct fmc_device;
-- 
cgit v1.2.3


From 3764e82e5150d87b205c10cd78a9c9ab86fbfa51 Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <johannes.thumshirn@men.de>
Date: Wed, 26 Feb 2014 17:29:05 +0100
Subject: drivers: Introduce MEN Chameleon Bus

The MCB (MEN Chameleon Bus) is a Bus specific to MEN Mikroelektronik
FPGA based devices. It is used to identify MCB based IP-Cores within
an FPGA and provide the necessary framework for instantiating drivers
for these devices.

Signed-off-by: Johannes Thumshirn <johannes.thumshirn@men.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 MAINTAINERS                     |   6 +
 drivers/Kconfig                 |   2 +
 drivers/Makefile                |   1 +
 drivers/mcb/Kconfig             |  15 ++
 drivers/mcb/Makefile            |   5 +
 drivers/mcb/mcb-core.c          | 414 ++++++++++++++++++++++++++++++++++++++++
 drivers/mcb/mcb-internal.h      | 116 +++++++++++
 drivers/mcb/mcb-parse.c         | 159 +++++++++++++++
 include/linux/mcb.h             | 119 ++++++++++++
 include/linux/mod_devicetable.h |   5 +
 10 files changed, 842 insertions(+)
 create mode 100644 drivers/mcb/Kconfig
 create mode 100644 drivers/mcb/Makefile
 create mode 100644 drivers/mcb/mcb-core.c
 create mode 100644 drivers/mcb/mcb-internal.h
 create mode 100644 drivers/mcb/mcb-parse.c
 create mode 100644 include/linux/mcb.h

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index 85b3dd8008b7..5d35f6cc0b69 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5667,6 +5667,12 @@ L:	linux-watchdog@vger.kernel.org
 S:	Supported
 F:	drivers/watchdog/mena21_wdt.c
 
+MEN CHAMELEON BUS (mcb)
+M:  	Johannes Thumshirn <johannes.thumshirn@men.de>
+S:	Supported
+F:	drivers/mcb/
+F:	include/linux/mcb.h
+
 METAG ARCHITECTURE
 M:	James Hogan <james.hogan@imgtec.com>
 L:	linux-metag@vger.kernel.org
diff --git a/drivers/Kconfig b/drivers/Kconfig
index e0a4ae61a2c4..0a0a90f52d26 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -172,4 +172,6 @@ source "drivers/phy/Kconfig"
 
 source "drivers/powercap/Kconfig"
 
+source "drivers/mcb/Kconfig"
+
 endmenu
diff --git a/drivers/Makefile b/drivers/Makefile
index 3d6de8b489c5..e3ced91b1784 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -156,3 +156,4 @@ obj-$(CONFIG_IPACK_BUS)		+= ipack/
 obj-$(CONFIG_NTB)		+= ntb/
 obj-$(CONFIG_FMC)		+= fmc/
 obj-$(CONFIG_POWERCAP)		+= powercap/
+obj-$(CONFIG_MCB)		+= mcb/
diff --git a/drivers/mcb/Kconfig b/drivers/mcb/Kconfig
new file mode 100644
index 000000000000..44c82d68c563
--- /dev/null
+++ b/drivers/mcb/Kconfig
@@ -0,0 +1,15 @@
+#
+# MEN Chameleon Bus (MCB) support
+#
+
+menuconfig MCB
+	   tristate "MCB support"
+	   default m
+	   help
+
+	   The MCB (MEN Chameleon Bus) is a Bus specific to MEN Mikroelektronik
+	   FPGA based devices. It is used to identify MCB based IP-Cores within
+	   an FPGA and provide the necessary framework for instantiating drivers
+	   for these devices.
+
+	   If build as a module, the module is called mcb.ko
diff --git a/drivers/mcb/Makefile b/drivers/mcb/Makefile
new file mode 100644
index 000000000000..2d9a751e93bd
--- /dev/null
+++ b/drivers/mcb/Makefile
@@ -0,0 +1,5 @@
+
+obj-$(CONFIG_MCB) += mcb.o
+
+mcb-y += mcb-core.o
+mcb-y += mcb-parse.o
diff --git a/drivers/mcb/mcb-core.c b/drivers/mcb/mcb-core.c
new file mode 100644
index 000000000000..bbe12932d404
--- /dev/null
+++ b/drivers/mcb/mcb-core.c
@@ -0,0 +1,414 @@
+/*
+ * MEN Chameleon Bus.
+ *
+ * Copyright (C) 2013 MEN Mikroelektronik GmbH (www.men.de)
+ * Author: Johannes Thumshirn <johannes.thumshirn@men.de>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; version 2 of the License.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/idr.h>
+#include <linux/mcb.h>
+
+static DEFINE_IDA(mcb_ida);
+
+static const struct mcb_device_id *mcb_match_id(const struct mcb_device_id *ids,
+						struct mcb_device *dev)
+{
+	if (ids) {
+		while (ids->device) {
+			if (ids->device == dev->id)
+				return ids;
+			ids++;
+		}
+	}
+
+	return NULL;
+}
+
+static int mcb_match(struct device *dev, struct device_driver *drv)
+{
+	struct mcb_driver *mdrv = to_mcb_driver(drv);
+	struct mcb_device *mdev = to_mcb_device(dev);
+	const struct mcb_device_id *found_id;
+
+	found_id = mcb_match_id(mdrv->id_table, mdev);
+	if (found_id)
+		return 1;
+
+	return 0;
+}
+
+static int mcb_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	struct mcb_device *mdev = to_mcb_device(dev);
+	int ret;
+
+	ret = add_uevent_var(env, "MODALIAS=mcb:16z%03d", mdev->id);
+	if (ret)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int mcb_probe(struct device *dev)
+{
+	struct mcb_driver *mdrv = to_mcb_driver(dev->driver);
+	struct mcb_device *mdev = to_mcb_device(dev);
+	const struct mcb_device_id *found_id;
+
+	found_id = mcb_match_id(mdrv->id_table, mdev);
+	if (!found_id)
+		return -ENODEV;
+
+	return mdrv->probe(mdev, found_id);
+}
+
+static int mcb_remove(struct device *dev)
+{
+	struct mcb_driver *mdrv = to_mcb_driver(dev->driver);
+	struct mcb_device *mdev = to_mcb_device(dev);
+
+	mdrv->remove(mdev);
+
+	put_device(&mdev->dev);
+
+	return 0;
+}
+
+static void mcb_shutdown(struct device *dev)
+{
+	struct mcb_device *mdev = to_mcb_device(dev);
+	struct mcb_driver *mdrv = mdev->driver;
+
+	if (mdrv && mdrv->shutdown)
+		mdrv->shutdown(mdev);
+}
+
+static struct bus_type mcb_bus_type = {
+	.name = "mcb",
+	.match = mcb_match,
+	.uevent = mcb_uevent,
+	.probe = mcb_probe,
+	.remove = mcb_remove,
+	.shutdown = mcb_shutdown,
+};
+
+/**
+ * __mcb_register_driver() - Register a @mcb_driver at the system
+ * @drv: The @mcb_driver
+ * @owner: The @mcb_driver's module
+ * @mod_name: The name of the @mcb_driver's module
+ *
+ * Register a @mcb_driver at the system. Perform some sanity checks, if
+ * the .probe and .remove methods are provided by the driver.
+ */
+int __mcb_register_driver(struct mcb_driver *drv, struct module *owner,
+			const char *mod_name)
+{
+	if (!drv->probe || !drv->remove)
+		return -EINVAL;
+
+	drv->driver.owner = owner;
+	drv->driver.bus = &mcb_bus_type;
+	drv->driver.mod_name = mod_name;
+
+	return driver_register(&drv->driver);
+}
+EXPORT_SYMBOL_GPL(__mcb_register_driver);
+
+/**
+ * mcb_unregister_driver() - Unregister a @mcb_driver from the system
+ * @drv: The @mcb_driver
+ *
+ * Unregister a @mcb_driver from the system.
+ */
+void mcb_unregister_driver(struct mcb_driver *drv)
+{
+	driver_unregister(&drv->driver);
+}
+EXPORT_SYMBOL_GPL(mcb_unregister_driver);
+
+static void mcb_release_dev(struct device *dev)
+{
+	struct mcb_device *mdev = to_mcb_device(dev);
+
+	mcb_bus_put(mdev->bus);
+	kfree(mdev);
+}
+
+/**
+ * mcb_device_register() - Register a mcb_device
+ * @bus: The @mcb_bus of the device
+ * @dev: The @mcb_device
+ *
+ * Register a specific @mcb_device at a @mcb_bus and the system itself.
+ */
+int mcb_device_register(struct mcb_bus *bus, struct mcb_device *dev)
+{
+	int ret;
+	int device_id;
+
+	device_initialize(&dev->dev);
+	dev->dev.bus = &mcb_bus_type;
+	dev->dev.parent = bus->dev.parent;
+	dev->dev.release = mcb_release_dev;
+
+	device_id = dev->id;
+	dev_set_name(&dev->dev, "mcb%d-16z%03d-%d:%d:%d",
+		bus->bus_nr, device_id, dev->inst, dev->group, dev->var);
+
+	ret = device_add(&dev->dev);
+	if (ret < 0) {
+		pr_err("Failed registering device 16z%03d on bus mcb%d (%d)\n",
+			device_id, bus->bus_nr, ret);
+		goto out;
+	}
+
+	return 0;
+
+out:
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mcb_device_register);
+
+/**
+ * mcb_alloc_bus() - Allocate a new @mcb_bus
+ *
+ * Allocate a new @mcb_bus.
+ */
+struct mcb_bus *mcb_alloc_bus(void)
+{
+	struct mcb_bus *bus;
+	int bus_nr;
+
+	bus = kzalloc(sizeof(struct mcb_bus), GFP_KERNEL);
+	if (!bus)
+		return NULL;
+
+	bus_nr = ida_simple_get(&mcb_ida, 0, 0, GFP_KERNEL);
+	if (bus_nr < 0) {
+		kfree(bus);
+		return ERR_PTR(bus_nr);
+	}
+
+	INIT_LIST_HEAD(&bus->children);
+	bus->bus_nr = bus_nr;
+
+	return bus;
+}
+EXPORT_SYMBOL_GPL(mcb_alloc_bus);
+
+static int __mcb_devices_unregister(struct device *dev, void *data)
+{
+	device_unregister(dev);
+	return 0;
+}
+
+static void mcb_devices_unregister(struct mcb_bus *bus)
+{
+	bus_for_each_dev(&mcb_bus_type, NULL, NULL, __mcb_devices_unregister);
+}
+/**
+ * mcb_release_bus() - Free a @mcb_bus
+ * @bus: The @mcb_bus to release
+ *
+ * Release an allocated @mcb_bus from the system.
+ */
+void mcb_release_bus(struct mcb_bus *bus)
+{
+	mcb_devices_unregister(bus);
+
+	ida_simple_remove(&mcb_ida, bus->bus_nr);
+
+	kfree(bus);
+}
+EXPORT_SYMBOL_GPL(mcb_release_bus);
+
+/**
+ * mcb_bus_put() - Increment refcnt
+ * @bus: The @mcb_bus
+ *
+ * Get a @mcb_bus' ref
+ */
+struct mcb_bus *mcb_bus_get(struct mcb_bus *bus)
+{
+	if (bus)
+		get_device(&bus->dev);
+
+	return bus;
+}
+EXPORT_SYMBOL_GPL(mcb_bus_get);
+
+/**
+ * mcb_bus_put() - Decrement refcnt
+ * @bus: The @mcb_bus
+ *
+ * Release a @mcb_bus' ref
+ */
+void mcb_bus_put(struct mcb_bus *bus)
+{
+	if (bus)
+		put_device(&bus->dev);
+}
+EXPORT_SYMBOL_GPL(mcb_bus_put);
+
+/**
+ * mcb_alloc_dev() - Allocate a device
+ * @bus: The @mcb_bus the device is part of
+ *
+ * Allocate a @mcb_device and add bus.
+ */
+struct mcb_device *mcb_alloc_dev(struct mcb_bus *bus)
+{
+	struct mcb_device *dev;
+
+	dev = kzalloc(sizeof(struct mcb_device), GFP_KERNEL);
+	if (!dev)
+		return NULL;
+
+	INIT_LIST_HEAD(&dev->bus_list);
+	dev->bus = bus;
+
+	return dev;
+}
+EXPORT_SYMBOL_GPL(mcb_alloc_dev);
+
+/**
+ * mcb_free_dev() - Free @mcb_device
+ * @dev: The device to free
+ *
+ * Free a @mcb_device
+ */
+void mcb_free_dev(struct mcb_device *dev)
+{
+	kfree(dev);
+}
+EXPORT_SYMBOL_GPL(mcb_free_dev);
+
+static int __mcb_bus_add_devices(struct device *dev, void *data)
+{
+	struct mcb_device *mdev = to_mcb_device(dev);
+	int retval;
+
+	if (mdev->is_added)
+		return 0;
+
+	retval = device_attach(dev);
+	if (retval < 0)
+		dev_err(dev, "Error adding device (%d)\n", retval);
+
+	mdev->is_added = true;
+
+	return 0;
+}
+
+static int __mcb_bus_add_child(struct device *dev, void *data)
+{
+	struct mcb_device *mdev = to_mcb_device(dev);
+	struct mcb_bus *child;
+
+	BUG_ON(!mdev->is_added);
+	child = mdev->subordinate;
+
+	if (child)
+		mcb_bus_add_devices(child);
+
+	return 0;
+}
+
+/**
+ * mcb_bus_add_devices() - Add devices in the bus' internal device list
+ * @bus: The @mcb_bus we add the devices
+ *
+ * Add devices in the bus' internal device list to the system.
+ */
+void mcb_bus_add_devices(const struct mcb_bus *bus)
+{
+	bus_for_each_dev(&mcb_bus_type, NULL, NULL, __mcb_bus_add_devices);
+	bus_for_each_dev(&mcb_bus_type, NULL, NULL, __mcb_bus_add_child);
+
+}
+EXPORT_SYMBOL_GPL(mcb_bus_add_devices);
+
+/**
+ * mcb_request_mem() - Request memory
+ * @dev: The @mcb_device the memory is for
+ * @name: The name for the memory reference.
+ *
+ * Request memory for a @mcb_device. If @name is NULL the driver name will
+ * be used.
+ */
+struct resource *mcb_request_mem(struct mcb_device *dev, const char *name)
+{
+	struct resource *mem;
+	u32 size;
+
+	if (!name)
+		name = dev->dev.driver->name;
+
+	size = resource_size(&dev->mem);
+
+	mem = request_mem_region(dev->mem.start, size, name);
+	if (!mem)
+		return ERR_PTR(-EBUSY);
+
+	return mem;
+}
+EXPORT_SYMBOL_GPL(mcb_request_mem);
+
+/**
+ * mcb_release_mem() - Release memory requested by device
+ * @dev: The @mcb_device that requested the memory
+ *
+ * Release memory that was prior requested via @mcb_request_mem().
+ */
+void mcb_release_mem(struct resource *mem)
+{
+	u32 size;
+
+	size = resource_size(mem);
+	release_mem_region(mem->start, size);
+}
+EXPORT_SYMBOL_GPL(mcb_release_mem);
+
+/**
+ * mcb_get_irq() - Get device's IRQ number
+ * @dev: The @mcb_device the IRQ is for
+ *
+ * Get the IRQ number of a given @mcb_device.
+ */
+int mcb_get_irq(struct mcb_device *dev)
+{
+	struct resource *irq = &dev->irq;
+
+	return irq->start;
+}
+EXPORT_SYMBOL_GPL(mcb_get_irq);
+
+static int mcb_init(void)
+{
+	return bus_register(&mcb_bus_type);
+}
+
+static void mcb_exit(void)
+{
+	bus_unregister(&mcb_bus_type);
+}
+
+/* mcb must be initialized after PCI but before the chameleon drivers.
+ * That means we must use some initcall between subsys_initcall and
+ * device_initcall.
+ */
+fs_initcall(mcb_init);
+module_exit(mcb_exit);
+
+MODULE_DESCRIPTION("MEN Chameleon Bus Driver");
+MODULE_AUTHOR("Johannes Thumshirn <johannes.thumshirn@men.de>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mcb/mcb-internal.h b/drivers/mcb/mcb-internal.h
new file mode 100644
index 000000000000..db22777d0ac8
--- /dev/null
+++ b/drivers/mcb/mcb-internal.h
@@ -0,0 +1,116 @@
+#ifndef __MCB_INTERNAL
+#define __MCB_INTERNAL
+
+#include <linux/types.h>
+
+#define CHAMELEON_FILENAME_LEN		12
+#define CHAMELEONV2_MAGIC		0xabce
+
+enum chameleon_descriptor_type {
+	CHAMELEON_DTYPE_GENERAL = 0x0,
+	CHAMELEON_DTYPE_BRIDGE = 0x1,
+	CHAMELEON_DTYPE_CPU = 0x2,
+	CHAMELEON_DTYPE_BAR = 0x3,
+	CHAMELEON_DTYPE_END = 0xf,
+};
+
+enum chameleon_bus_type {
+	CHAMELEON_BUS_WISHBONE,
+	CHAMELEON_BUS_AVALON,
+	CHAMELEON_BUS_LPC,
+	CHAMELEON_BUS_ISA,
+};
+
+/**
+ * struct chameleon_fpga_header
+ *
+ * @revision:	Revison of Chameleon table in FPGA
+ * @model:	Chameleon table model ASCII char
+ * @minor:	Revision minor
+ * @bus_type:	Bus type (usually %CHAMELEON_BUS_WISHBONE)
+ * @magic:	Chameleon header magic number (0xabce for version 2)
+ * @reserved:	Reserved
+ * @filename:	Filename of FPGA bitstream
+ */
+struct chameleon_fpga_header {
+	u8 revision;
+	char model;
+	u8 minor;
+	u8 bus_type;
+	u16 magic;
+	u16 reserved;
+	/* This one has no '\0' at the end!!! */
+	char filename[CHAMELEON_FILENAME_LEN];
+} __packed;
+#define HEADER_MAGIC_OFFSET 0x4
+
+/**
+ * struct chameleon_gdd - Chameleon General Device Descriptor
+ *
+ * @irq:	the position in the FPGA's IRQ controller vector
+ * @rev:	the revision of the variant's implementation
+ * @var:	the variant of the IP core
+ * @dev:	the device  the IP core is
+ * @dtype:	device descriptor type
+ * @bar:	BAR offset that must be added to module offset
+ * @inst:	the instance number of the device, 0 is first instance
+ * @group:	the group the device belongs to (0 = no group)
+ * @reserved:	reserved
+ * @offset:	beginning of the address window of desired module
+ * @size:	size of the module's address window
+ */
+struct chameleon_gdd {
+	__le32 reg1;
+	__le32 reg2;
+	__le32 offset;
+	__le32 size;
+
+} __packed;
+
+/* GDD Register 1 fields */
+#define GDD_IRQ(x) ((x) & 0x1f)
+#define GDD_REV(x) (((x) >> 5) & 0x3f)
+#define GDD_VAR(x) (((x) >> 11) & 0x3f)
+#define GDD_DEV(x) (((x) >> 18) & 0x3ff)
+#define GDD_DTY(x) (((x) >> 28) & 0xf)
+
+/* GDD Register 2 fields */
+#define GDD_BAR(x) ((x) & 0x7)
+#define GDD_INS(x) (((x) >> 3) & 0x3f)
+#define GDD_GRP(x) (((x) >> 9) & 0x3f)
+
+/**
+ * struct chameleon_bdd - Chameleon Bridge Device Descriptor
+ *
+ * @irq:	the position in the FPGA's IRQ controller vector
+ * @rev:	the revision of the variant's implementation
+ * @var:	the variant of the IP core
+ * @dev:	the device  the IP core is
+ * @dtype:	device descriptor type
+ * @bar:	BAR offset that must be added to module offset
+ * @inst:	the instance number of the device, 0 is first instance
+ * @dbar:	destination bar from the bus _behind_ the bridge
+ * @chamoff:	offset within the BAR of the source bus
+ * @offset:
+ * @size:
+ */
+struct chameleon_bdd {
+	unsigned int irq:6;
+	unsigned int rev:6;
+	unsigned int var:6;
+	unsigned int dev:10;
+	unsigned int dtype:4;
+	unsigned int bar:3;
+	unsigned int inst:6;
+	unsigned int dbar:3;
+	unsigned int group:6;
+	unsigned int reserved:14;
+	u32 chamoff;
+	u32 offset;
+	u32 size;
+} __packed;
+
+int chameleon_parse_cells(struct mcb_bus *bus, phys_addr_t mapbase,
+			  void __iomem *base);
+
+#endif
diff --git a/drivers/mcb/mcb-parse.c b/drivers/mcb/mcb-parse.c
new file mode 100644
index 000000000000..d1278b5f3028
--- /dev/null
+++ b/drivers/mcb/mcb-parse.c
@@ -0,0 +1,159 @@
+#include <linux/types.h>
+#include <linux/ioport.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+#include <linux/io.h>
+#include <linux/mcb.h>
+
+#include "mcb-internal.h"
+
+struct mcb_parse_priv {
+	phys_addr_t mapbase;
+	void __iomem *base;
+};
+
+#define for_each_chameleon_cell(dtype, p)	\
+	for ((dtype) = get_next_dtype((p));	\
+	     (dtype) != CHAMELEON_DTYPE_END;	\
+	     (dtype) = get_next_dtype((p)))
+
+static inline uint32_t get_next_dtype(void __iomem *p)
+{
+	uint32_t dtype;
+
+	dtype = readl(p);
+	return dtype >> 28;
+}
+
+static int chameleon_parse_bdd(struct mcb_bus *bus,
+			phys_addr_t mapbase,
+			void __iomem *base)
+{
+	return 0;
+}
+
+static int chameleon_parse_gdd(struct mcb_bus *bus,
+			phys_addr_t mapbase,
+			void __iomem *base)
+{
+	struct chameleon_gdd __iomem *gdd =
+		(struct chameleon_gdd __iomem *) base;
+	struct mcb_device *mdev;
+	u32 offset;
+	u32 size;
+	int ret;
+	__le32 reg1;
+	__le32 reg2;
+
+	mdev = mcb_alloc_dev(bus);
+	if (!mdev)
+		return -ENOMEM;
+
+	reg1 = readl(&gdd->reg1);
+	reg2 = readl(&gdd->reg2);
+	offset = readl(&gdd->offset);
+	size = readl(&gdd->size);
+
+	mdev->id = GDD_DEV(reg1);
+	mdev->rev = GDD_REV(reg1);
+	mdev->var = GDD_VAR(reg1);
+	mdev->bar = GDD_BAR(reg1);
+	mdev->group = GDD_GRP(reg2);
+	mdev->inst = GDD_INS(reg2);
+
+	pr_debug("Found a 16z%03d\n", mdev->id);
+
+	mdev->irq.start = GDD_IRQ(reg1);
+	mdev->irq.end = GDD_IRQ(reg1);
+	mdev->irq.flags = IORESOURCE_IRQ;
+
+	mdev->mem.start = mapbase + offset;
+	mdev->mem.end = mdev->mem.start + size - 1;
+	mdev->mem.flags = IORESOURCE_MEM;
+
+	mdev->is_added = false;
+
+	ret = mcb_device_register(bus, mdev);
+	if (ret < 0)
+		goto err;
+
+	return 0;
+
+err:
+	mcb_free_dev(mdev);
+
+	return ret;
+}
+
+int chameleon_parse_cells(struct mcb_bus *bus, phys_addr_t mapbase,
+			void __iomem *base)
+{
+	char __iomem *p = base;
+	struct chameleon_fpga_header *header;
+	uint32_t dtype;
+	int num_cells = 0;
+	int ret = 0;
+	u32 hsize;
+
+	hsize = sizeof(struct chameleon_fpga_header);
+
+	header = kzalloc(hsize, GFP_KERNEL);
+	if (!header)
+		return -ENOMEM;
+
+	/* Extract header information */
+	memcpy_fromio(header, p, hsize);
+	/* We only support chameleon v2 at the moment */
+	header->magic = le16_to_cpu(header->magic);
+	if (header->magic != CHAMELEONV2_MAGIC) {
+		pr_err("Unsupported chameleon version 0x%x\n",
+				header->magic);
+		kfree(header);
+		return -ENODEV;
+	}
+	p += hsize;
+
+	pr_debug("header->revision = %d\n", header->revision);
+	pr_debug("header->model = 0x%x ('%c')\n", header->model,
+		header->model);
+	pr_debug("header->minor = %d\n", header->minor);
+	pr_debug("header->bus_type = 0x%x\n", header->bus_type);
+
+
+	pr_debug("header->magic = 0x%x\n", header->magic);
+	pr_debug("header->filename = \"%.*s\"\n", CHAMELEON_FILENAME_LEN,
+		header->filename);
+
+	for_each_chameleon_cell(dtype, p) {
+		switch (dtype) {
+		case CHAMELEON_DTYPE_GENERAL:
+			ret = chameleon_parse_gdd(bus, mapbase, p);
+			if (ret < 0)
+				goto out;
+			p += sizeof(struct chameleon_gdd);
+			break;
+		case CHAMELEON_DTYPE_BRIDGE:
+			chameleon_parse_bdd(bus, mapbase, p);
+			p += sizeof(struct chameleon_bdd);
+			break;
+		case CHAMELEON_DTYPE_END:
+			break;
+		default:
+			pr_err("Invalid chameleon descriptor type 0x%x\n",
+				dtype);
+			return -EINVAL;
+		}
+		num_cells++;
+	}
+
+	if (num_cells == 0)
+		num_cells = -EINVAL;
+
+	kfree(header);
+	return num_cells;
+
+out:
+	kfree(header);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(chameleon_parse_cells);
diff --git a/include/linux/mcb.h b/include/linux/mcb.h
new file mode 100644
index 000000000000..2db284d14064
--- /dev/null
+++ b/include/linux/mcb.h
@@ -0,0 +1,119 @@
+/*
+ * MEN Chameleon Bus.
+ *
+ * Copyright (C) 2014 MEN Mikroelektronik GmbH (www.men.de)
+ * Author: Johannes Thumshirn <johannes.thumshirn@men.de>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; version 2 of the License.
+ */
+#ifndef _LINUX_MCB_H
+#define _LINUX_MCB_H
+
+#include <linux/mod_devicetable.h>
+#include <linux/device.h>
+#include <linux/irqreturn.h>
+
+struct mcb_driver;
+
+/**
+ * struct mcb_bus - MEN Chameleon Bus
+ *
+ * @dev: pointer to carrier device
+ * @children: the child busses
+ * @bus_nr: mcb bus number
+ */
+struct mcb_bus {
+	struct list_head children;
+	struct device dev;
+	int bus_nr;
+};
+#define to_mcb_bus(b) container_of((b), struct mcb_bus, dev)
+
+/**
+ * struct mcb_device - MEN Chameleon Bus device
+ *
+ * @bus_list: internal list handling for bus code
+ * @dev: device in kernel representation
+ * @bus: mcb bus the device is plugged to
+ * @subordinate: subordinate MCBus in case of bridge
+ * @is_added: flag to check if device is added to bus
+ * @driver: associated mcb_driver
+ * @id: mcb device id
+ * @inst: instance in Chameleon table
+ * @group: group in Chameleon table
+ * @var: variant in Chameleon table
+ * @bar: BAR in Chameleon table
+ * @rev: revision in Chameleon table
+ * @irq: IRQ resource
+ * @memory: memory resource
+ */
+struct mcb_device {
+	struct list_head bus_list;
+	struct device dev;
+	struct mcb_bus *bus;
+	struct mcb_bus *subordinate;
+	bool is_added;
+	struct mcb_driver *driver;
+	u16 id;
+	int inst;
+	int group;
+	int var;
+	int bar;
+	int rev;
+	struct resource irq;
+	struct resource mem;
+};
+#define to_mcb_device(x) container_of((x), struct mcb_device, dev)
+
+/**
+ * struct mcb_driver - MEN Chameleon Bus device driver
+ *
+ * @driver: device_driver
+ * @id_table: mcb id table
+ * @probe: probe callback
+ * @remove: remove callback
+ * @shutdown: shutdown callback
+ */
+struct mcb_driver {
+	struct device_driver driver;
+	const struct mcb_device_id *id_table;
+	int (*probe)(struct mcb_device *mdev, const struct mcb_device_id *id);
+	void (*remove)(struct mcb_device *mdev);
+	void (*shutdown)(struct mcb_device *mdev);
+};
+#define to_mcb_driver(x) container_of((x), struct mcb_driver, driver)
+
+static inline void *mcb_get_drvdata(struct mcb_device *dev)
+{
+	return dev_get_drvdata(&dev->dev);
+}
+
+static inline void mcb_set_drvdata(struct mcb_device *dev, void *data)
+{
+	dev_set_drvdata(&dev->dev, data);
+}
+
+extern int __must_check __mcb_register_driver(struct mcb_driver *drv,
+					struct module *owner,
+					const char *mod_name);
+#define mcb_register_driver(driver)		\
+	__mcb_register_driver(driver, THIS_MODULE, KBUILD_MODNAME)
+extern void mcb_unregister_driver(struct mcb_driver *driver);
+#define module_mcb_driver(__mcb_driver)		\
+	module_driver(__mcb_driver, mcb_register_driver, mcb_unregister_driver);
+extern void mcb_bus_add_devices(const struct mcb_bus *bus);
+extern int mcb_device_register(struct mcb_bus *bus, struct mcb_device *dev);
+extern struct mcb_bus *mcb_alloc_bus(void);
+extern struct mcb_bus *mcb_bus_get(struct mcb_bus *bus);
+extern void mcb_bus_put(struct mcb_bus *bus);
+extern struct mcb_device *mcb_alloc_dev(struct mcb_bus *bus);
+extern void mcb_free_dev(struct mcb_device *dev);
+extern void mcb_release_bus(struct mcb_bus *bus);
+extern struct resource *mcb_request_mem(struct mcb_device *dev,
+					const char *name);
+extern void mcb_release_mem(struct resource *mem);
+extern int mcb_get_irq(struct mcb_device *dev);
+
+#endif /* _LINUX_MCB_H */
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 677e474fc273..50f67eff27ef 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -607,4 +607,9 @@ struct rio_device_id {
 	__u16 asm_did, asm_vid;
 };
 
+struct mcb_device_id {
+	__u16 device;
+	kernel_ulong_t driver_data;
+};
+
 #endif /* LINUX_MOD_DEVICETABLE_H */
-- 
cgit v1.2.3


From 3e54d1518f8f31effd487b7609c6779f62b0c04f Mon Sep 17 00:00:00 2001
From: "Lad, Prabhakar" <prabhakar.csengg@gmail.com>
Date: Thu, 20 Feb 2014 13:30:32 +0530
Subject: PM: fix typo in comment

Signed-off-by: Lad, Prabhakar <prabhakar.csengg@gmail.com>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/pm.h b/include/linux/pm.h
index f23a4f1c1bfb..3540ea99717e 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -352,7 +352,7 @@ const struct dev_pm_ops name = { \
 
 /*
  * Use this for defining a set of PM operations to be used in all situations
- * (sustem suspend, hibernation or runtime PM).
+ * (system suspend, hibernation or runtime PM).
  * NOTE: In general, system suspend callbacks, .suspend() and .resume(), should
  * be different from the corresponding runtime PM callbacks, .runtime_suspend(),
  * and .runtime_resume(), because .runtime_suspend() always works on an already
-- 
cgit v1.2.3


From 0a9efc4d91df7b18fb3e97c24ee85a1529618899 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Wed, 19 Feb 2014 13:09:21 +0100
Subject: PM / sleep: Set pm_generic functions to NULL for !CONFIG_PM_SLEEP

Previously only a subset of the functions were defined and set to NULL
while !CONFIG_PM_SLEEP. Let's make them all available so they can be
used no matter of CONFIG_PM_SLEEP or not.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm.h | 28 ++++++++++++++++++++--------
 1 file changed, 20 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pm.h b/include/linux/pm.h
index 3540ea99717e..6fffbcd7bc37 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -719,14 +719,26 @@ static inline void dpm_for_each_dev(void *data, void (*fn)(struct device *, void
 {
 }
 
-#define pm_generic_prepare	NULL
-#define pm_generic_suspend	NULL
-#define pm_generic_resume	NULL
-#define pm_generic_freeze	NULL
-#define pm_generic_thaw		NULL
-#define pm_generic_restore	NULL
-#define pm_generic_poweroff	NULL
-#define pm_generic_complete	NULL
+#define pm_generic_prepare		NULL
+#define pm_generic_suspend_late		NULL
+#define pm_generic_suspend_noirq	NULL
+#define pm_generic_suspend		NULL
+#define pm_generic_resume_early		NULL
+#define pm_generic_resume_noirq		NULL
+#define pm_generic_resume		NULL
+#define pm_generic_freeze_noirq		NULL
+#define pm_generic_freeze_late		NULL
+#define pm_generic_freeze		NULL
+#define pm_generic_thaw_noirq		NULL
+#define pm_generic_thaw_early		NULL
+#define pm_generic_thaw			NULL
+#define pm_generic_restore_noirq	NULL
+#define pm_generic_restore_early	NULL
+#define pm_generic_restore		NULL
+#define pm_generic_poweroff_noirq	NULL
+#define pm_generic_poweroff_late	NULL
+#define pm_generic_poweroff		NULL
+#define pm_generic_complete		NULL
 #endif /* !CONFIG_PM_SLEEP */
 
 /* How to reorder dpm_list after device_move() */
-- 
cgit v1.2.3


From 5811712ffbf593d98b6cc56461df5be4e9580245 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Thu, 20 Feb 2014 10:15:52 -0800
Subject: tty: serial: bcm63xx_uart: define UART_REG_SIZE constant

The bcm63xx_uart driver uses RSET_UART_SIZE which is a constant defined
for MIPS-based BCM63xx platforms, pull this constant value from the
MIPS-specific header and put it in include/linux/serial_bcm63xx.h to
make the driver platform agnostic.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/bcm63xx_uart.c | 4 ++--
 include/linux/serial_bcm63xx.h    | 2 ++
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/serial/bcm63xx_uart.c b/drivers/tty/serial/bcm63xx_uart.c
index d71143e4e9df..37e7e336f70a 100644
--- a/drivers/tty/serial/bcm63xx_uart.c
+++ b/drivers/tty/serial/bcm63xx_uart.c
@@ -589,7 +589,7 @@ static int bcm_uart_request_port(struct uart_port *port)
 {
 	unsigned int size;
 
-	size = RSET_UART_SIZE;
+	size = UART_REG_SIZE;
 	if (!request_mem_region(port->mapbase, size, "bcm63xx")) {
 		dev_err(port->dev, "Memory region busy\n");
 		return -EBUSY;
@@ -609,7 +609,7 @@ static int bcm_uart_request_port(struct uart_port *port)
  */
 static void bcm_uart_release_port(struct uart_port *port)
 {
-	release_mem_region(port->mapbase, RSET_UART_SIZE);
+	release_mem_region(port->mapbase, UART_REG_SIZE);
 	iounmap(port->membase);
 }
 
diff --git a/include/linux/serial_bcm63xx.h b/include/linux/serial_bcm63xx.h
index 570e964dc899..a80aa1a5bee2 100644
--- a/include/linux/serial_bcm63xx.h
+++ b/include/linux/serial_bcm63xx.h
@@ -116,4 +116,6 @@
 					UART_FIFO_PARERR_MASK |		\
 					UART_FIFO_BRKDET_MASK)
 
+#define UART_REG_SIZE			24
+
 #endif /* _LINUX_SERIAL_BCM63XX_H */
-- 
cgit v1.2.3


From a9c3f68f3cd8d55f809fbdb0c138ed061ea1bd25 Mon Sep 17 00:00:00 2001
From: Peter Hurley <peter@hurleysoftware.com>
Date: Sat, 22 Feb 2014 07:31:21 -0500
Subject: tty: Fix low_latency BUG

The user-settable knob, low_latency, has been the source of
several BUG reports which stem from flush_to_ldisc() running
in interrupt context. Since 3.12, which added several sleeping
locks (termios_rwsem and buf->lock) to the input processing path,
the frequency of these BUG reports has increased.

Note that changes in 3.12 did not introduce this regression;
sleeping locks were first added to the input processing path
with the removal of the BKL from N_TTY in commit
a88a69c91256418c5907c2f1f8a0ec0a36f9e6cc,
'n_tty: Fix loss of echoed characters and remove bkl from n_tty'
and later in commit 38db89799bdf11625a831c5af33938dcb11908b6,
'tty: throttling race fix'. Since those changes, executing
flush_to_ldisc() in interrupt_context (ie, low_latency set), is unsafe.

However, since most devices do not validate if the low_latency
setting is appropriate for the context (process or interrupt) in
which they receive data, some reports are due to misconfiguration.
Further, serial dma devices for which dma fails, resort to
interrupt receiving as a backup without resetting low_latency.

Historically, low_latency was used to force wake-up the reading
process rather than wait for the next scheduler tick. The
effect was to trim multiple milliseconds of latency from
when the process would receive new data.

Recent tests [1] have shown that the reading process now receives
data with only 10's of microseconds latency without low_latency set.

Remove the low_latency rx steering from tty_flip_buffer_push();
however, leave the knob as an optional hint to drivers that can
tune their rx fifos and such like. Cleanup stale code comments
regarding low_latency.

[1] https://lkml.org/lkml/2014/2/20/434

"Yay.. thats an annoying historical pain in the butt gone."
	-- Alan Cox

Reported-by: Beat Bolli <bbolli@ewanet.ch>
Reported-by: Pavel Roskin <proski@gnu.org>
Acked-by: David Sterba <dsterba@suse.cz>
Cc: Grant Edwards <grant.b.edwards@gmail.com>
Cc: Stanislaw Gruszka <sgruszka@redhat.com>
Cc: Hal Murray <murray+fedora@ip-64-139-1-69.sjc.megapath.net>
Cc: <stable@vger.kernel.org> # 3.12.x+
Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
Signed-off-by: Alan Cox <alan@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/ipwireless/tty.c  |  3 ---
 drivers/tty/tty_buffer.c      | 20 ++++----------------
 drivers/usb/gadget/u_serial.c |  4 ++--
 include/linux/tty.h           |  2 +-
 4 files changed, 7 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/ipwireless/tty.c b/drivers/tty/ipwireless/tty.c
index ebd5bff0f5c1..17ee3bf0926b 100644
--- a/drivers/tty/ipwireless/tty.c
+++ b/drivers/tty/ipwireless/tty.c
@@ -176,9 +176,6 @@ void ipwireless_tty_received(struct ipw_tty *tty, unsigned char *data,
 				": %d chars not inserted to flip buffer!\n",
 				length - work);
 
-	/*
-	 * This may sleep if ->low_latency is set
-	 */
 	if (work)
 		tty_flip_buffer_push(&tty->port);
 }
diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c
index 765125dff20e..8ebd9f88a6f6 100644
--- a/drivers/tty/tty_buffer.c
+++ b/drivers/tty/tty_buffer.c
@@ -351,14 +351,11 @@ EXPORT_SYMBOL(tty_insert_flip_string_flags);
  *	Takes any pending buffers and transfers their ownership to the
  *	ldisc side of the queue. It then schedules those characters for
  *	processing by the line discipline.
- *	Note that this function can only be used when the low_latency flag
- *	is unset. Otherwise the workqueue won't be flushed.
  */
 
 void tty_schedule_flip(struct tty_port *port)
 {
 	struct tty_bufhead *buf = &port->buf;
-	WARN_ON(port->low_latency);
 
 	buf->tail->commit = buf->tail->used;
 	schedule_work(&buf->work);
@@ -482,17 +479,15 @@ static void flush_to_ldisc(struct work_struct *work)
  */
 void tty_flush_to_ldisc(struct tty_struct *tty)
 {
-	if (!tty->port->low_latency)
-		flush_work(&tty->port->buf.work);
+	flush_work(&tty->port->buf.work);
 }
 
 /**
  *	tty_flip_buffer_push	-	terminal
  *	@port: tty port to push
  *
- *	Queue a push of the terminal flip buffers to the line discipline. This
- *	function must not be called from IRQ context if port->low_latency is
- *	set.
+ *	Queue a push of the terminal flip buffers to the line discipline.
+ *	Can be called from IRQ/atomic context.
  *
  *	In the event of the queue being busy for flipping the work will be
  *	held off and retried later.
@@ -500,14 +495,7 @@ void tty_flush_to_ldisc(struct tty_struct *tty)
 
 void tty_flip_buffer_push(struct tty_port *port)
 {
-	struct tty_bufhead *buf = &port->buf;
-
-	buf->tail->commit = buf->tail->used;
-
-	if (port->low_latency)
-		flush_to_ldisc(&buf->work);
-	else
-		schedule_work(&buf->work);
+	tty_schedule_flip(port);
 }
 EXPORT_SYMBOL(tty_flip_buffer_push);
 
diff --git a/drivers/usb/gadget/u_serial.c b/drivers/usb/gadget/u_serial.c
index b369292d4b90..ad0aca812002 100644
--- a/drivers/usb/gadget/u_serial.c
+++ b/drivers/usb/gadget/u_serial.c
@@ -549,8 +549,8 @@ static void gs_rx_push(unsigned long _port)
 		port->read_started--;
 	}
 
-	/* Push from tty to ldisc; without low_latency set this is handled by
-	 * a workqueue, so we won't get callbacks and can hold port_lock
+	/* Push from tty to ldisc; this is handled by a workqueue,
+	 * so we won't get callbacks and can hold port_lock
 	 */
 	if (do_push)
 		tty_flip_buffer_push(&port->port);
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 90b4fdc8a61f..b90b5c221ff0 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -208,7 +208,7 @@ struct tty_port {
 	wait_queue_head_t	delta_msr_wait;	/* Modem status change */
 	unsigned long		flags;		/* TTY flags ASY_*/
 	unsigned char		console:1,	/* port is a console */
-				low_latency:1;	/* direct buffer flush */
+				low_latency:1;	/* optional: tune for latency */
 	struct mutex		mutex;		/* Locking */
 	struct mutex		buf_mutex;	/* Buffer alloc lock */
 	unsigned char		*xmit_buf;	/* Optional buffer */
-- 
cgit v1.2.3


From 45af780a0fcac8fbba0ac740a671b2af80bcf189 Mon Sep 17 00:00:00 2001
From: Alexander Shiyan <shc_work@mail.ru>
Date: Sat, 22 Feb 2014 16:01:35 +0400
Subject: serial: imx: Remove init() and exit() platform callbacks

Signed-off-by: Alexander Shiyan <shc_work@mail.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/arm/mach-imx/mach-mx31moboard.c     | 21 +++++----------------
 drivers/tty/serial/imx.c                 | 27 ++-------------------------
 include/linux/platform_data/serial-imx.h |  2 --
 3 files changed, 7 insertions(+), 43 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-imx/mach-mx31moboard.c b/arch/arm/mach-imx/mach-mx31moboard.c
index b3738e616f19..8f45afe785f8 100644
--- a/arch/arm/mach-imx/mach-mx31moboard.c
+++ b/arch/arm/mach-imx/mach-mx31moboard.c
@@ -128,27 +128,15 @@ static struct platform_device mx31moboard_flash = {
 	.num_resources = 1,
 };
 
-static int moboard_uart0_init(struct platform_device *pdev)
+static void __init moboard_uart0_init(void)
 {
-	int ret = gpio_request(IOMUX_TO_GPIO(MX31_PIN_CTS1), "uart0-cts-hack");
-	if (ret)
-		return ret;
-
-	ret = gpio_direction_output(IOMUX_TO_GPIO(MX31_PIN_CTS1), 0);
-	if (ret)
+	if (!gpio_request(IOMUX_TO_GPIO(MX31_PIN_CTS1), "uart0-cts-hack")) {
+		gpio_direction_output(IOMUX_TO_GPIO(MX31_PIN_CTS1), 0);
 		gpio_free(IOMUX_TO_GPIO(MX31_PIN_CTS1));
-
-	return ret;
-}
-
-static void moboard_uart0_exit(struct platform_device *pdev)
-{
-	gpio_free(IOMUX_TO_GPIO(MX31_PIN_CTS1));
+	}
 }
 
 static const struct imxuart_platform_data uart0_pdata __initconst = {
-	.init = moboard_uart0_init,
-	.exit = moboard_uart0_exit,
 };
 
 static const struct imxuart_platform_data uart4_pdata __initconst = {
@@ -543,6 +531,7 @@ static void __init mx31moboard_init(void)
 
 	imx31_add_imx2_wdt();
 
+	moboard_uart0_init();
 	imx31_add_imx_uart0(&uart0_pdata);
 	imx31_add_imx_uart4(&uart4_pdata);
 
diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index 37c39390efb7..3b6c1a2e25de 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -1901,7 +1901,6 @@ static void serial_imx_probe_pdata(struct imx_port *sport,
 static int serial_imx_probe(struct platform_device *pdev)
 {
 	struct imx_port *sport;
-	struct imxuart_platform_data *pdata;
 	void __iomem *base;
 	int ret = 0;
 	struct resource *res;
@@ -1955,38 +1954,16 @@ static int serial_imx_probe(struct platform_device *pdev)
 
 	imx_ports[sport->port.line] = sport;
 
-	pdata = dev_get_platdata(&pdev->dev);
-	if (pdata && pdata->init) {
-		ret = pdata->init(pdev);
-		if (ret)
-			return ret;
-	}
-
-	ret = uart_add_one_port(&imx_reg, &sport->port);
-	if (ret)
-		goto deinit;
 	platform_set_drvdata(pdev, sport);
 
-	return 0;
-deinit:
-	if (pdata && pdata->exit)
-		pdata->exit(pdev);
-	return ret;
+	return uart_add_one_port(&imx_reg, &sport->port);
 }
 
 static int serial_imx_remove(struct platform_device *pdev)
 {
-	struct imxuart_platform_data *pdata;
 	struct imx_port *sport = platform_get_drvdata(pdev);
 
-	pdata = dev_get_platdata(&pdev->dev);
-
-	uart_remove_one_port(&imx_reg, &sport->port);
-
-	if (pdata && pdata->exit)
-		pdata->exit(pdev);
-
-	return 0;
+	return uart_remove_one_port(&imx_reg, &sport->port);
 }
 
 static struct platform_driver serial_imx_driver = {
diff --git a/include/linux/platform_data/serial-imx.h b/include/linux/platform_data/serial-imx.h
index 4adec9b154dd..3cc2e3c40914 100644
--- a/include/linux/platform_data/serial-imx.h
+++ b/include/linux/platform_data/serial-imx.h
@@ -23,8 +23,6 @@
 #define IMXUART_IRDA        (1<<1)
 
 struct imxuart_platform_data {
-	int (*init)(struct platform_device *pdev);
-	void (*exit)(struct platform_device *pdev);
 	unsigned int flags;
 	void (*irda_enable)(int enable);
 	unsigned int irda_inv_rx:1;
-- 
cgit v1.2.3


From 37f204164dfb0186a0caf20bc3e3120080bcd788 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Sat, 1 Mar 2014 11:56:05 +0100
Subject: PM: Add pm_runtime_suspend|resume_force functions

This patch provides two new runtime PM helper functions which intend to
be used from system suspend/resume callbacks, to make sure devices are
put into low power state during system suspend and brought back to full
power at system resume.

The prerequisite is to have all levels of a device's runtime PM
callbacks to be defined through the SET_PM_RUNTIME_PM_OPS macro, which
means these are available for CONFIG_PM.

By using the new runtime PM helper functions especially the two
scenarios below will be addressed.

1) The PM core prevents .runtime_suspend callbacks from being invoked
during system suspend. That means even for a runtime PM centric
subsystem and driver, the device needs to be put into low power state
from a system suspend callback. Otherwise it may very well be left in
full power state (runtime resumed) while the system is suspended. By
using the new helper functions, we make sure to walk the hierarchy of
a device's power domain, subsystem and driver.

2) Subsystems and drivers need to cope with all the combinations of
CONFIG_PM_SLEEP and CONFIG_PM_RUNTIME. The two new helper functions
smothly addresses this.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/Makefile  |  3 +-
 drivers/base/power/runtime.c | 84 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/pm_runtime.h   |  4 +++
 3 files changed, 89 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/Makefile b/drivers/base/power/Makefile
index 2e58ebb1f6c0..1cb8544598d5 100644
--- a/drivers/base/power/Makefile
+++ b/drivers/base/power/Makefile
@@ -1,6 +1,5 @@
-obj-$(CONFIG_PM)	+= sysfs.o generic_ops.o common.o qos.o
+obj-$(CONFIG_PM)	+= sysfs.o generic_ops.o common.o qos.o runtime.o
 obj-$(CONFIG_PM_SLEEP)	+= main.o wakeup.o
-obj-$(CONFIG_PM_RUNTIME)	+= runtime.o
 obj-$(CONFIG_PM_TRACE_RTC)	+= trace.o
 obj-$(CONFIG_PM_OPP)	+= opp.o
 obj-$(CONFIG_PM_GENERIC_DOMAINS)	+=  domain.o domain_governor.o
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index ac495b1357fa..4776cf528d08 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -44,6 +44,7 @@ static int (*rpm_get_resume_cb(struct device *dev))(struct device *)
 	return RPM_GET_CALLBACK(dev, runtime_resume);
 }
 
+#ifdef CONFIG_PM_RUNTIME
 static int (*rpm_get_idle_cb(struct device *dev))(struct device *)
 {
 	return RPM_GET_CALLBACK(dev, runtime_idle);
@@ -1401,3 +1402,86 @@ void pm_runtime_remove(struct device *dev)
 	if (dev->power.irq_safe && dev->parent)
 		pm_runtime_put(dev->parent);
 }
+#endif
+
+/**
+ * pm_runtime_force_suspend - Force a device into suspend state if needed.
+ * @dev: Device to suspend.
+ *
+ * Disable runtime PM so we safely can check the device's runtime PM status and
+ * if it is active, invoke it's .runtime_suspend callback to bring it into
+ * suspend state. Keep runtime PM disabled to preserve the state unless we
+ * encounter errors.
+ *
+ * Typically this function may be invoked from a system suspend callback to make
+ * sure the device is put into low power state.
+ */
+int pm_runtime_force_suspend(struct device *dev)
+{
+	int (*callback)(struct device *);
+	int ret = 0;
+
+	pm_runtime_disable(dev);
+
+	/*
+	 * Note that pm_runtime_status_suspended() returns false while
+	 * !CONFIG_PM_RUNTIME, which means the device will be put into low
+	 * power state.
+	 */
+	if (pm_runtime_status_suspended(dev))
+		return 0;
+
+	callback = rpm_get_suspend_cb(dev);
+
+	if (!callback) {
+		ret = -ENOSYS;
+		goto err;
+	}
+
+	ret = callback(dev);
+	if (ret)
+		goto err;
+
+	pm_runtime_set_suspended(dev);
+	return 0;
+err:
+	pm_runtime_enable(dev);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pm_runtime_force_suspend);
+
+/**
+ * pm_runtime_force_resume - Force a device into resume state.
+ * @dev: Device to resume.
+ *
+ * Prior invoking this function we expect the user to have brought the device
+ * into low power state by a call to pm_runtime_force_suspend(). Here we reverse
+ * those actions and brings the device into full power. We update the runtime PM
+ * status and re-enables runtime PM.
+ *
+ * Typically this function may be invoked from a system resume callback to make
+ * sure the device is put into full power state.
+ */
+int pm_runtime_force_resume(struct device *dev)
+{
+	int (*callback)(struct device *);
+	int ret = 0;
+
+	callback = rpm_get_resume_cb(dev);
+
+	if (!callback) {
+		ret = -ENOSYS;
+		goto out;
+	}
+
+	ret = callback(dev);
+	if (ret)
+		goto out;
+
+	pm_runtime_set_active(dev);
+	pm_runtime_mark_last_busy(dev);
+out:
+	pm_runtime_enable(dev);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pm_runtime_force_resume);
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 16c9a62fa1c0..2a5897a4afbc 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -26,9 +26,13 @@
 #ifdef CONFIG_PM
 extern int pm_generic_runtime_suspend(struct device *dev);
 extern int pm_generic_runtime_resume(struct device *dev);
+extern int pm_runtime_force_suspend(struct device *dev);
+extern int pm_runtime_force_resume(struct device *dev);
 #else
 static inline int pm_generic_runtime_suspend(struct device *dev) { return 0; }
 static inline int pm_generic_runtime_resume(struct device *dev) { return 0; }
+static inline int pm_runtime_force_suspend(struct device *dev) { return 0; }
+static inline int pm_runtime_force_resume(struct device *dev) { return 0; }
 #endif
 
 #ifdef CONFIG_PM_RUNTIME
-- 
cgit v1.2.3


From 9813337a4b16ea5b1701b1d00f7e410f5decdfa5 Mon Sep 17 00:00:00 2001
From: Eugenia Emantayev <eugenia@mellanox.com>
Date: Sun, 2 Mar 2014 10:25:01 +0200
Subject: net/mlx4: Replace mlx4_en_mac_to_u64() with mlx4_mac_to_u64()

Currently, the EN driver uses a private static function
mlx4_en_mac_to_u64(). Move it to a common include file (driver.h)
for mlx4_en and mlx4_ib for further use.

Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 32 ++++++++------------------
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h   |  1 -
 include/linux/mlx4/driver.h                    | 12 ++++++++++
 3 files changed, 22 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 2c0823bf3e05..3db594614fd3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -603,7 +603,7 @@ static int mlx4_en_get_qp(struct mlx4_en_priv *priv)
 	int err = 0;
 	u64 reg_id;
 	int *qpn = &priv->base_qpn;
-	u64 mac = mlx4_en_mac_to_u64(priv->dev->dev_addr);
+	u64 mac = mlx4_mac_to_u64(priv->dev->dev_addr);
 
 	en_dbg(DRV, priv, "Registering MAC: %pM for adding\n",
 	       priv->dev->dev_addr);
@@ -672,7 +672,7 @@ static void mlx4_en_put_qp(struct mlx4_en_priv *priv)
 	u64 mac;
 
 	if (dev->caps.steering_mode == MLX4_STEERING_MODE_A0) {
-		mac = mlx4_en_mac_to_u64(priv->dev->dev_addr);
+		mac = mlx4_mac_to_u64(priv->dev->dev_addr);
 		en_dbg(DRV, priv, "Registering MAC: %pM for deleting\n",
 		       priv->dev->dev_addr);
 		mlx4_unregister_mac(dev, priv->port, mac);
@@ -685,7 +685,7 @@ static void mlx4_en_put_qp(struct mlx4_en_priv *priv)
 		for (i = 0; i < MLX4_EN_MAC_HASH_SIZE; ++i) {
 			bucket = &priv->mac_hash[i];
 			hlist_for_each_entry_safe(entry, tmp, bucket, hlist) {
-				mac = mlx4_en_mac_to_u64(entry->mac);
+				mac = mlx4_mac_to_u64(entry->mac);
 				en_dbg(DRV, priv, "Registering MAC: %pM for deleting\n",
 				       entry->mac);
 				mlx4_en_uc_steer_release(priv, entry->mac,
@@ -715,14 +715,14 @@ static int mlx4_en_replace_mac(struct mlx4_en_priv *priv, int qpn,
 	struct mlx4_en_dev *mdev = priv->mdev;
 	struct mlx4_dev *dev = mdev->dev;
 	int err = 0;
-	u64 new_mac_u64 = mlx4_en_mac_to_u64(new_mac);
+	u64 new_mac_u64 = mlx4_mac_to_u64(new_mac);
 
 	if (dev->caps.steering_mode != MLX4_STEERING_MODE_A0) {
 		struct hlist_head *bucket;
 		unsigned int mac_hash;
 		struct mlx4_mac_entry *entry;
 		struct hlist_node *tmp;
-		u64 prev_mac_u64 = mlx4_en_mac_to_u64(prev_mac);
+		u64 prev_mac_u64 = mlx4_mac_to_u64(prev_mac);
 
 		bucket = &priv->mac_hash[prev_mac[MLX4_EN_MAC_HASH_IDX]];
 		hlist_for_each_entry_safe(entry, tmp, bucket, hlist) {
@@ -751,18 +751,6 @@ static int mlx4_en_replace_mac(struct mlx4_en_priv *priv, int qpn,
 	return __mlx4_replace_mac(dev, priv->port, qpn, new_mac_u64);
 }
 
-u64 mlx4_en_mac_to_u64(u8 *addr)
-{
-	u64 mac = 0;
-	int i;
-
-	for (i = 0; i < ETH_ALEN; i++) {
-		mac <<= 8;
-		mac |= addr[i];
-	}
-	return mac;
-}
-
 static int mlx4_en_do_set_mac(struct mlx4_en_priv *priv)
 {
 	int err = 0;
@@ -1081,7 +1069,7 @@ static void mlx4_en_do_multicast(struct mlx4_en_priv *priv,
 		mlx4_en_cache_mclist(dev);
 		netif_addr_unlock_bh(dev);
 		list_for_each_entry(mclist, &priv->mc_list, list) {
-			mcast_addr = mlx4_en_mac_to_u64(mclist->addr);
+			mcast_addr = mlx4_mac_to_u64(mclist->addr);
 			mlx4_SET_MCAST_FLTR(mdev->dev, priv->port,
 					    mcast_addr, 0, MLX4_MCAST_CONFIG);
 		}
@@ -1173,7 +1161,7 @@ static void mlx4_en_do_uc_filter(struct mlx4_en_priv *priv,
 				found = true;
 
 			if (!found) {
-				mac = mlx4_en_mac_to_u64(entry->mac);
+				mac = mlx4_mac_to_u64(entry->mac);
 				mlx4_en_uc_steer_release(priv, entry->mac,
 							 priv->base_qpn,
 							 entry->reg_id);
@@ -1216,7 +1204,7 @@ static void mlx4_en_do_uc_filter(struct mlx4_en_priv *priv,
 				priv->flags |= MLX4_EN_FLAG_FORCE_PROMISC;
 				break;
 			}
-			mac = mlx4_en_mac_to_u64(ha->addr);
+			mac = mlx4_mac_to_u64(ha->addr);
 			memcpy(entry->mac, ha->addr, ETH_ALEN);
 			err = mlx4_register_mac(mdev->dev, priv->port, mac);
 			if (err < 0) {
@@ -2206,7 +2194,7 @@ static int mlx4_en_set_vf_mac(struct net_device *dev, int queue, u8 *mac)
 {
 	struct mlx4_en_priv *en_priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = en_priv->mdev;
-	u64 mac_u64 = mlx4_en_mac_to_u64(mac);
+	u64 mac_u64 = mlx4_mac_to_u64(mac);
 
 	if (!is_valid_ether_addr(mac))
 		return -EINVAL;
@@ -2407,7 +2395,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 		if (mlx4_is_slave(priv->mdev->dev)) {
 			eth_hw_addr_random(dev);
 			en_warn(priv, "Assigned random MAC address %pM\n", dev->dev_addr);
-			mac_u64 = mlx4_en_mac_to_u64(dev->dev_addr);
+			mac_u64 = mlx4_mac_to_u64(dev->dev_addr);
 			mdev->dev->caps.def_mac[priv->port] = mac_u64;
 		} else {
 			en_err(priv, "Port: %d, invalid mac burned: %pM, quiting\n",
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index c59011d4e830..4ff7da83c4b3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -797,7 +797,6 @@ void mlx4_en_cleanup_filters(struct mlx4_en_priv *priv);
 
 #define MLX4_EN_NUM_SELF_TEST	5
 void mlx4_en_ex_selftest(struct net_device *dev, u32 *flags, u64 *buf);
-u64 mlx4_en_mac_to_u64(u8 *addr);
 void mlx4_en_ptp_overflow_check(struct mlx4_en_dev *mdev);
 
 /*
diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h
index c257e1b211be..022055c8fb26 100644
--- a/include/linux/mlx4/driver.h
+++ b/include/linux/mlx4/driver.h
@@ -64,4 +64,16 @@ void mlx4_unregister_interface(struct mlx4_interface *intf);
 
 void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port);
 
+static inline u64 mlx4_mac_to_u64(u8 *addr)
+{
+	u64 mac = 0;
+	int i;
+
+	for (i = 0; i < ETH_ALEN; i++) {
+		mac <<= 8;
+		mac |= addr[i];
+	}
+	return mac;
+}
+
 #endif /* MLX4_DRIVER_H */
-- 
cgit v1.2.3


From ec5709403e6893acb4f7ca40514ebd29c3116836 Mon Sep 17 00:00:00 2001
From: Amir Vadai <amirv@mellanox.com>
Date: Sun, 2 Mar 2014 10:25:04 +0200
Subject: net/mlx4_en: Use union for BlueFlame WQE

When BlueFlame is turned on, control segment of the TX WQE is changed,
and the second line of it is used for QPN.
Changed code to use a union in the mlx4_wqe_ctrl_seg instead of casting.
This makes the code clearer and solves the static checker warning:

drivers/net/ethernet/mellanox/mlx4/en_tx.c:839 mlx4_en_xmit()
	warn: potential memory corrupting cast 4 vs 2 bytes

CC: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c |  3 ++-
 include/linux/mlx4/qp.h                    | 11 ++++++++---
 2 files changed, 10 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 56e8fbc128f8..69c2fcef9d4c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -876,7 +876,8 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	skb_tx_timestamp(skb);
 
 	if (ring->bf_enabled && desc_size <= MAX_BF && !bounce && !vlan_tx_tag_present(skb)) {
-		*(__be32 *) (&tx_desc->ctrl.vlan_tag) |= cpu_to_be32(ring->doorbell_qpn);
+		tx_desc->ctrl.bf_qpn |= cpu_to_be32(ring->doorbell_qpn);
+
 		op_own |= htonl((bf_index & 0xffff) << 8);
 		/* Ensure new descirptor hits memory
 		* before setting ownership of this descriptor to HW */
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index 59f8ba84568b..b66e7610d4ee 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -270,9 +270,14 @@ enum {
 
 struct mlx4_wqe_ctrl_seg {
 	__be32			owner_opcode;
-	__be16			vlan_tag;
-	u8			ins_vlan;
-	u8			fence_size;
+	union {
+		struct {
+			__be16			vlan_tag;
+			u8			ins_vlan;
+			u8			fence_size;
+		};
+		__be32			bf_qpn;
+	};
 	/*
 	 * High 24 bits are SRC remote buffer; low 8 bits are flags:
 	 * [7]   SO (strong ordering)
-- 
cgit v1.2.3


From f864c46aae4cb6aed09e98615c427fcc4f1de104 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 4 Feb 2014 00:35:56 +0100
Subject: mfd: dbx500/abx500: root out hardcoded IRQ assignments

The DBx500 and ABx500 should be getting their IRQs from the
device tree and nowhere else. Get rid of all the static assignments
everywhere, delete it from the driver, platform data and the
board files in one swift strike.

Lots of cross-dependencies in the MFD drivers for PRCMU and
AB8500 makes it necessary to strike everywhere at once to
eradicate IRQs passed as resources and platform data to the left
and right around the platform.

Cc: Mark Brown <broonie@kernel.org>
Cc: Samuel Ortiz <sameo@linux.intel.com>
Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 arch/arm/mach-ux500/board-mop500-audio.c |   1 -
 arch/arm/mach-ux500/cpu-db8500.c         |   4 -
 arch/arm/mach-ux500/irqs-board-mop500.h  |  55 --------------
 arch/arm/mach-ux500/irqs-db8500.h        | 125 -------------------------------
 arch/arm/mach-ux500/irqs.h               |  49 ------------
 drivers/mfd/ab8500-core.c                |  27 +++----
 drivers/mfd/db8500-prcmu.c               |  34 ++++++---
 include/linux/mfd/abx500/ab8500.h        |   2 -
 include/linux/mfd/dbx500-prcmu.h         |   2 -
 9 files changed, 36 insertions(+), 263 deletions(-)
 delete mode 100644 arch/arm/mach-ux500/irqs-board-mop500.h
 delete mode 100644 arch/arm/mach-ux500/irqs-db8500.h
 delete mode 100644 arch/arm/mach-ux500/irqs.h

(limited to 'include/linux')

diff --git a/arch/arm/mach-ux500/board-mop500-audio.c b/arch/arm/mach-ux500/board-mop500-audio.c
index 9309ad4cbd09..b2a0899e7453 100644
--- a/arch/arm/mach-ux500/board-mop500-audio.c
+++ b/arch/arm/mach-ux500/board-mop500-audio.c
@@ -9,7 +9,6 @@
 #include <linux/gpio.h>
 #include <linux/platform_data/dma-ste-dma40.h>
 
-#include "irqs.h"
 #include <linux/platform_data/asoc-ux500-msp.h>
 
 #include "ste-dma40-db8500.h"
diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index 5e8a4021e4e0..8820f602fcd2 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -27,7 +27,6 @@
 #include <asm/mach/map.h>
 
 #include "setup.h"
-#include "irqs.h"
 
 #include "board-mop500-regulators.h"
 #include "board-mop500.h"
@@ -35,14 +34,11 @@
 #include "id.h"
 
 struct ab8500_platform_data ab8500_platdata = {
-	.irq_base	= MOP500_AB8500_IRQ_BASE,
 	.regulator	= &ab8500_regulator_plat_data,
 };
 
 struct prcmu_pdata db8500_prcmu_pdata = {
 	.ab_platdata	= &ab8500_platdata,
-	.ab_irq		= IRQ_DB8500_AB8500,
-	.irq_base	= IRQ_PRCMU_BASE,
 	.version_offset	= DB8500_PRCMU_FW_VERSION_OFFSET,
 	.legacy_offset	= DB8500_PRCMU_LEGACY_OFFSET,
 };
diff --git a/arch/arm/mach-ux500/irqs-board-mop500.h b/arch/arm/mach-ux500/irqs-board-mop500.h
deleted file mode 100644
index d526dd8e87d3..000000000000
--- a/arch/arm/mach-ux500/irqs-board-mop500.h
+++ /dev/null
@@ -1,55 +0,0 @@
-/*
- * Copyright (C) ST-Ericsson SA 2010
- *
- * Author: Rabin Vincent <rabin.vincent@stericsson.com>
- * License terms: GNU General Public License (GPL) version 2
- */
-
-#ifndef __MACH_IRQS_BOARD_MOP500_H
-#define __MACH_IRQS_BOARD_MOP500_H
-
-/* Number of AB8500 irqs is taken from header file */
-#include <linux/mfd/abx500/ab8500.h>
-
-#define MOP500_AB8500_IRQ_BASE		IRQ_BOARD_START
-#define MOP500_AB8500_IRQ_END		(MOP500_AB8500_IRQ_BASE \
-					 + AB8500_MAX_NR_IRQS)
-
-/* TC35892 */
-#define TC35892_NR_INTERNAL_IRQS	8
-#define TC35892_INT_GPIO(x)		(TC35892_NR_INTERNAL_IRQS + (x))
-#define TC35892_NR_GPIOS		24
-#define TC35892_NR_IRQS			TC35892_INT_GPIO(TC35892_NR_GPIOS)
-
-#define MOP500_EGPIO_NR_IRQS		TC35892_NR_IRQS
-
-#define MOP500_EGPIO_IRQ_BASE		MOP500_AB8500_IRQ_END
-#define MOP500_EGPIO_IRQ_END		(MOP500_EGPIO_IRQ_BASE \
-					 + MOP500_EGPIO_NR_IRQS)
-/* STMPE1601 irqs */
-#define STMPE_NR_INTERNAL_IRQS          9
-#define STMPE_INT_GPIO(x)               (STMPE_NR_INTERNAL_IRQS + (x))
-#define STMPE_NR_GPIOS                  24
-#define STMPE_NR_IRQS                   STMPE_INT_GPIO(STMPE_NR_GPIOS)
-
-#define MOP500_STMPE1601_IRQBASE        MOP500_EGPIO_IRQ_END
-#define MOP500_STMPE1601_IRQ(x)         (MOP500_STMPE1601_IRQBASE + (x))
-
-#define MOP500_STMPE1601_IRQ_END	\
-	MOP500_STMPE1601_IRQ(STMPE_NR_INTERNAL_IRQS)
-
-#define MOP500_NR_IRQS		MOP500_STMPE1601_IRQ_END
-
-#define MOP500_IRQ_END		MOP500_NR_IRQS
-
-/*
- * We may have several boards, but only one will run at a
- * time, so the one with most IRQs will bump this ahead,
- * but the IRQ_BOARD_START remains the same for either board.
- */
-#if MOP500_IRQ_END > IRQ_BOARD_END
-#undef IRQ_BOARD_END
-#define IRQ_BOARD_END	MOP500_IRQ_END
-#endif
-
-#endif
diff --git a/arch/arm/mach-ux500/irqs-db8500.h b/arch/arm/mach-ux500/irqs-db8500.h
deleted file mode 100644
index f3a9d5947ef3..000000000000
--- a/arch/arm/mach-ux500/irqs-db8500.h
+++ /dev/null
@@ -1,125 +0,0 @@
-/*
- * Copyright (C) ST-Ericsson SA 2010
- *
- * Author: Rabin Vincent <rabin.vincent@stericsson.com>
- * License terms: GNU General Public License (GPL) version 2
- */
-
-#ifndef __MACH_IRQS_DB8500_H
-#define __MACH_IRQS_DB8500_H
-
-#define IRQ_DB8500_MTU0			(IRQ_SHPI_START + 4)
-#define IRQ_DB8500_SPI2			(IRQ_SHPI_START + 6)
-#define IRQ_DB8500_PMU			(IRQ_SHPI_START + 7)
-#define IRQ_DB8500_SPI0			(IRQ_SHPI_START + 8)
-#define IRQ_DB8500_RTT			(IRQ_SHPI_START + 9)
-#define IRQ_DB8500_PKA			(IRQ_SHPI_START + 10)
-#define IRQ_DB8500_UART0		(IRQ_SHPI_START + 11)
-#define IRQ_DB8500_I2C3			(IRQ_SHPI_START + 12)
-#define IRQ_DB8500_L2CC			(IRQ_SHPI_START + 13)
-#define IRQ_DB8500_SSP0			(IRQ_SHPI_START + 14)
-#define IRQ_DB8500_CRYP1		(IRQ_SHPI_START + 15)
-#define IRQ_DB8500_MSP1_RX		(IRQ_SHPI_START + 16)
-#define IRQ_DB8500_MTU1			(IRQ_SHPI_START + 17)
-#define IRQ_DB8500_RTC			(IRQ_SHPI_START + 18)
-#define IRQ_DB8500_UART1		(IRQ_SHPI_START + 19)
-#define IRQ_DB8500_USB_WAKEUP		(IRQ_SHPI_START + 20)
-#define IRQ_DB8500_I2C0			(IRQ_SHPI_START + 21)
-#define IRQ_DB8500_I2C1			(IRQ_SHPI_START + 22)
-#define IRQ_DB8500_USBOTG		(IRQ_SHPI_START + 23)
-#define IRQ_DB8500_DMA_SECURE		(IRQ_SHPI_START + 24)
-#define IRQ_DB8500_DMA			(IRQ_SHPI_START + 25)
-#define IRQ_DB8500_UART2		(IRQ_SHPI_START + 26)
-#define IRQ_DB8500_ICN_PMU1		(IRQ_SHPI_START + 27)
-#define IRQ_DB8500_ICN_PMU2		(IRQ_SHPI_START + 28)
-#define IRQ_DB8500_HSIR_EXCEP		(IRQ_SHPI_START + 29)
-#define IRQ_DB8500_MSP0			(IRQ_SHPI_START + 31)
-#define IRQ_DB8500_HSIR_CH0_OVRRUN	(IRQ_SHPI_START + 32)
-#define IRQ_DB8500_HSIR_CH1_OVRRUN	(IRQ_SHPI_START + 33)
-#define IRQ_DB8500_HSIR_CH2_OVRRUN	(IRQ_SHPI_START + 34)
-#define IRQ_DB8500_HSIR_CH3_OVRRUN	(IRQ_SHPI_START + 35)
-#define IRQ_DB8500_HSIR_CH4_OVRRUN	(IRQ_SHPI_START + 36)
-#define IRQ_DB8500_HSIR_CH5_OVRRUN	(IRQ_SHPI_START + 37)
-#define IRQ_DB8500_HSIR_CH6_OVRRUN	(IRQ_SHPI_START + 38)
-#define IRQ_DB8500_HSIR_CH7_OVRRUN	(IRQ_SHPI_START + 39)
-#define IRQ_DB8500_AB8500		(IRQ_SHPI_START + 40)
-#define IRQ_DB8500_SDMMC2		(IRQ_SHPI_START + 41)
-#define IRQ_DB8500_SIA			(IRQ_SHPI_START + 42)
-#define IRQ_DB8500_SIA2			(IRQ_SHPI_START + 43)
-#define IRQ_DB8500_SVA			(IRQ_SHPI_START + 44)
-#define IRQ_DB8500_SVA2			(IRQ_SHPI_START + 45)
-#define IRQ_DB8500_PRCMU0		(IRQ_SHPI_START + 46)
-#define IRQ_DB8500_PRCMU1		(IRQ_SHPI_START + 47)
-#define IRQ_DB8500_DISP			(IRQ_SHPI_START + 48)
-#define IRQ_DB8500_SPI3			(IRQ_SHPI_START + 49)
-#define IRQ_DB8500_SDMMC1		(IRQ_SHPI_START + 50)
-#define IRQ_DB8500_I2C4			(IRQ_SHPI_START + 51)
-#define IRQ_DB8500_SSP1			(IRQ_SHPI_START + 52)
-#define IRQ_DB8500_SKE			(IRQ_SHPI_START + 53)
-#define IRQ_DB8500_KB			(IRQ_SHPI_START + 54)
-#define IRQ_DB8500_I2C2			(IRQ_SHPI_START + 55)
-#define IRQ_DB8500_B2R2			(IRQ_SHPI_START + 56)
-#define IRQ_DB8500_CRYP0		(IRQ_SHPI_START + 57)
-#define IRQ_DB8500_SDMMC3		(IRQ_SHPI_START + 59)
-#define IRQ_DB8500_SDMMC0		(IRQ_SHPI_START + 60)
-#define IRQ_DB8500_HSEM			(IRQ_SHPI_START + 61)
-#define IRQ_DB8500_MSP1			(IRQ_SHPI_START + 62)
-#define IRQ_DB8500_SBAG			(IRQ_SHPI_START + 63)
-#define IRQ_DB8500_SPI1			(IRQ_SHPI_START + 96)
-#define IRQ_DB8500_SRPTIMER		(IRQ_SHPI_START + 97)
-#define IRQ_DB8500_MSP2			(IRQ_SHPI_START + 98)
-#define IRQ_DB8500_SDMMC4		(IRQ_SHPI_START + 99)
-#define IRQ_DB8500_SDMMC5		(IRQ_SHPI_START + 100)
-#define IRQ_DB8500_HSIRD0		(IRQ_SHPI_START + 104)
-#define IRQ_DB8500_HSIRD1		(IRQ_SHPI_START + 105)
-#define IRQ_DB8500_HSITD0		(IRQ_SHPI_START + 106)
-#define IRQ_DB8500_HSITD1		(IRQ_SHPI_START + 107)
-#define IRQ_DB8500_CTI0			(IRQ_SHPI_START + 108)
-#define IRQ_DB8500_CTI1			(IRQ_SHPI_START + 109)
-#define IRQ_DB8500_ICN_ERR		(IRQ_SHPI_START + 110)
-#define IRQ_DB8500_MALI_PPMMU		(IRQ_SHPI_START + 112)
-#define IRQ_DB8500_MALI_PP		(IRQ_SHPI_START + 113)
-#define IRQ_DB8500_MALI_GPMMU		(IRQ_SHPI_START + 114)
-#define IRQ_DB8500_MALI_GP		(IRQ_SHPI_START + 115)
-#define IRQ_DB8500_MALI			(IRQ_SHPI_START + 116)
-#define IRQ_DB8500_PRCMU_SEM		(IRQ_SHPI_START + 118)
-#define IRQ_DB8500_GPIO0		(IRQ_SHPI_START + 119)
-#define IRQ_DB8500_GPIO1		(IRQ_SHPI_START + 120)
-#define IRQ_DB8500_GPIO2		(IRQ_SHPI_START + 121)
-#define IRQ_DB8500_GPIO3		(IRQ_SHPI_START + 122)
-#define IRQ_DB8500_GPIO4		(IRQ_SHPI_START + 123)
-#define IRQ_DB8500_GPIO5		(IRQ_SHPI_START + 124)
-#define IRQ_DB8500_GPIO6		(IRQ_SHPI_START + 125)
-#define IRQ_DB8500_GPIO7		(IRQ_SHPI_START + 126)
-#define IRQ_DB8500_GPIO8		(IRQ_SHPI_START + 127)
-
-#define IRQ_CA_WAKE_REQ_ED			(IRQ_SHPI_START + 71)
-#define IRQ_AC_READ_NOTIFICATION_0_ED		(IRQ_SHPI_START + 66)
-#define IRQ_AC_READ_NOTIFICATION_1_ED		(IRQ_SHPI_START + 64)
-#define IRQ_CA_MSG_PEND_NOTIFICATION_0_ED	(IRQ_SHPI_START + 67)
-#define IRQ_CA_MSG_PEND_NOTIFICATION_1_ED	(IRQ_SHPI_START + 65)
-
-#define IRQ_CA_WAKE_REQ_V1			(IRQ_SHPI_START + 83)
-#define IRQ_AC_READ_NOTIFICATION_0_V1		(IRQ_SHPI_START + 78)
-#define IRQ_AC_READ_NOTIFICATION_1_V1		(IRQ_SHPI_START + 76)
-#define IRQ_CA_MSG_PEND_NOTIFICATION_0_V1	(IRQ_SHPI_START + 79)
-#define IRQ_CA_MSG_PEND_NOTIFICATION_1_V1	(IRQ_SHPI_START + 77)
-
-#ifdef CONFIG_UX500_SOC_DB8500
-
-/* Virtual interrupts corresponding to the PRCMU wakeups.  */
-#define IRQ_PRCMU_BASE IRQ_SOC_START
-#define IRQ_PRCMU_END (IRQ_PRCMU_BASE + 23)
-
-/*
- * We may have several SoCs, but only one will run at a
- * time, so the one with most IRQs will bump this ahead,
- * but the IRQ_SOC_START remains the same for either SoC.
- */
-#if IRQ_SOC_END < IRQ_PRCMU_END
-#undef IRQ_SOC_END
-#define IRQ_SOC_END IRQ_PRCMU_END
-#endif
-
-#endif /* CONFIG_UX500_SOC_DB8500 */
-#endif
diff --git a/arch/arm/mach-ux500/irqs.h b/arch/arm/mach-ux500/irqs.h
deleted file mode 100644
index 15b2af698ed7..000000000000
--- a/arch/arm/mach-ux500/irqs.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/*
- *  Copyright (C) 2008 STMicroelectronics
- *  Copyright (C) 2009 ST-Ericsson.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-#ifndef ASM_ARCH_IRQS_H
-#define ASM_ARCH_IRQS_H
-
-#define IRQ_LOCALTIMER			29
-#define IRQ_LOCALWDOG			30
-
-/* Shared Peripheral Interrupt (SHPI) */
-#define IRQ_SHPI_START			32
-
-/*
- * MTU0 preserved for now until plat-nomadik is taught not to use it.  Don't
- * add any other IRQs here, use the irqs-dbx500.h files.
- */
-#define IRQ_MTU0		(IRQ_SHPI_START + 4)
-
-#define DBX500_NR_INTERNAL_IRQS		166
-
-/* After chip-specific IRQ numbers we have the GPIO ones */
-#define NOMADIK_NR_GPIO			288
-#define NOMADIK_GPIO_TO_IRQ(gpio)	((gpio) + DBX500_NR_INTERNAL_IRQS)
-#define NOMADIK_IRQ_TO_GPIO(irq)	((irq) - DBX500_NR_INTERNAL_IRQS)
-#define IRQ_GPIO_END			NOMADIK_GPIO_TO_IRQ(NOMADIK_NR_GPIO)
-
-#define IRQ_SOC_START		IRQ_GPIO_END
-/* This will be overridden by SoC-specific irq headers */
-#define IRQ_SOC_END		IRQ_SOC_START
-
-#include "irqs-db8500.h"
-
-#define IRQ_BOARD_START		IRQ_SOC_END
-/* This will be overridden by board-specific irq headers */
-#define IRQ_BOARD_END		IRQ_BOARD_START
-
-#ifdef CONFIG_MACH_MOP500
-#include "irqs-board-mop500.h"
-#endif
-
-#define UX500_NR_IRQS		IRQ_BOARD_END
-
-#endif /* ASM_ARCH_IRQS_H */
diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c
index aaff683cd37d..a8ee4a36a1d8 100644
--- a/drivers/mfd/ab8500-core.c
+++ b/drivers/mfd/ab8500-core.c
@@ -592,7 +592,7 @@ static int ab8500_irq_init(struct ab8500 *ab8500, struct device_node *np)
 
 	/* If ->irq_base is zero this will give a linear mapping */
 	ab8500->domain = irq_domain_add_simple(NULL,
-			num_irqs, ab8500->irq_base,
+			num_irqs, 0,
 			&ab8500_irq_ops, ab8500);
 
 	if (!ab8500->domain) {
@@ -1583,14 +1583,13 @@ static int ab8500_probe(struct platform_device *pdev)
 	if (!ab8500)
 		return -ENOMEM;
 
-	if (plat)
-		ab8500->irq_base = plat->irq_base;
-
 	ab8500->dev = &pdev->dev;
 
 	resource = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
-	if (!resource)
+	if (!resource) {
+		dev_err(&pdev->dev, "no IRQ resource\n");
 		return -ENODEV;
+	}
 
 	ab8500->irq = resource->start;
 
@@ -1612,8 +1611,10 @@ static int ab8500_probe(struct platform_device *pdev)
 	else {
 		ret = get_register_interruptible(ab8500, AB8500_MISC,
 			AB8500_IC_NAME_REG, &value);
-		if (ret < 0)
+		if (ret < 0) {
+			dev_err(&pdev->dev, "could not probe HW\n");
 			return ret;
+		}
 
 		ab8500->version = value;
 	}
@@ -1759,30 +1760,30 @@ static int ab8500_probe(struct platform_device *pdev)
 	if (is_ab9540(ab8500))
 		ret = mfd_add_devices(ab8500->dev, 0, ab9540_devs,
 				ARRAY_SIZE(ab9540_devs), NULL,
-				ab8500->irq_base, ab8500->domain);
+				0, ab8500->domain);
 	else if (is_ab8540(ab8500)) {
 		ret = mfd_add_devices(ab8500->dev, 0, ab8540_devs,
 			      ARRAY_SIZE(ab8540_devs), NULL,
-			      ab8500->irq_base, NULL);
+			      0, ab8500->domain);
 		if (ret)
 			return ret;
 
 		if (is_ab8540_1p2_or_earlier(ab8500))
 			ret = mfd_add_devices(ab8500->dev, 0, ab8540_cut1_devs,
 			      ARRAY_SIZE(ab8540_cut1_devs), NULL,
-			      ab8500->irq_base, NULL);
+			      0, ab8500->domain);
 		else /* ab8540 >= cut2 */
 			ret = mfd_add_devices(ab8500->dev, 0, ab8540_cut2_devs,
 			      ARRAY_SIZE(ab8540_cut2_devs), NULL,
-			      ab8500->irq_base, NULL);
+			      0, ab8500->domain);
 	} else if (is_ab8505(ab8500))
 		ret = mfd_add_devices(ab8500->dev, 0, ab8505_devs,
 			      ARRAY_SIZE(ab8505_devs), NULL,
-			      ab8500->irq_base, ab8500->domain);
+			      0, ab8500->domain);
 	else
 		ret = mfd_add_devices(ab8500->dev, 0, ab8500_devs,
 				ARRAY_SIZE(ab8500_devs), NULL,
-				ab8500->irq_base, ab8500->domain);
+				0, ab8500->domain);
 	if (ret)
 		return ret;
 
@@ -1790,7 +1791,7 @@ static int ab8500_probe(struct platform_device *pdev)
 		/* Add battery management devices */
 		ret = mfd_add_devices(ab8500->dev, 0, ab8500_bm_devs,
 				      ARRAY_SIZE(ab8500_bm_devs), NULL,
-				      ab8500->irq_base, ab8500->domain);
+				      0, ab8500->domain);
 		if (ret)
 			dev_err(ab8500->dev, "error adding bm devices\n");
 	}
diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c
index e43e6e821117..7694e0700d34 100644
--- a/drivers/mfd/db8500-prcmu.c
+++ b/drivers/mfd/db8500-prcmu.c
@@ -25,6 +25,7 @@
 #include <linux/bitops.h>
 #include <linux/fs.h>
 #include <linux/of.h>
+#include <linux/of_irq.h>
 #include <linux/platform_device.h>
 #include <linux/uaccess.h>
 #include <linux/mfd/core.h>
@@ -2678,16 +2679,12 @@ static struct irq_domain_ops db8500_irq_ops = {
 	.xlate  = irq_domain_xlate_twocell,
 };
 
-static int db8500_irq_init(struct device_node *np, int irq_base)
+static int db8500_irq_init(struct device_node *np)
 {
 	int i;
 
-	/* In the device tree case, just take some IRQs */
-	if (np)
-		irq_base = 0;
-
 	db8500_irq_domain = irq_domain_add_simple(
-		np, NUM_PRCMU_WAKEUPS, irq_base,
+		np, NUM_PRCMU_WAKEUPS, 0,
 		&db8500_irq_ops, NULL);
 
 	if (!db8500_irq_domain) {
@@ -3114,10 +3111,10 @@ static void db8500_prcmu_update_cpufreq(void)
 }
 
 static int db8500_prcmu_register_ab8500(struct device *parent,
-					struct ab8500_platform_data *pdata,
-					int irq)
+					struct ab8500_platform_data *pdata)
 {
-	struct resource ab8500_resource = DEFINE_RES_IRQ(irq);
+	struct device_node *np;
+	struct resource ab8500_resource;
 	struct mfd_cell ab8500_cell = {
 		.name = "ab8500-core",
 		.of_compatible = "stericsson,ab8500",
@@ -3128,6 +3125,20 @@ static int db8500_prcmu_register_ab8500(struct device *parent,
 		.num_resources = 1,
 	};
 
+	if (!parent->of_node)
+		return -ENODEV;
+
+	/* Look up the device node, sneak the IRQ out of it */
+	for_each_child_of_node(parent->of_node, np) {
+		if (of_device_is_compatible(np, ab8500_cell.of_compatible))
+			break;
+	}
+	if (!np) {
+		dev_info(parent, "could not find AB8500 node in the device tree\n");
+		return -ENODEV;
+	}
+	of_irq_to_resource_table(np, &ab8500_resource, 1);
+
 	return mfd_add_devices(parent, 0, &ab8500_cell, 1, NULL, 0, NULL);
 }
 
@@ -3180,7 +3191,7 @@ static int db8500_prcmu_probe(struct platform_device *pdev)
 		goto no_irq_return;
 	}
 
-	db8500_irq_init(np, pdata->irq_base);
+	db8500_irq_init(np);
 
 	prcmu_config_esram0_deep_sleep(ESRAM0_DEEP_SLEEP_STATE_RET);
 
@@ -3205,8 +3216,7 @@ static int db8500_prcmu_probe(struct platform_device *pdev)
 		}
 	}
 
-	err = db8500_prcmu_register_ab8500(&pdev->dev, pdata->ab_platdata,
-					   pdata->ab_irq);
+	err = db8500_prcmu_register_ab8500(&pdev->dev, pdata->ab_platdata);
 	if (err) {
 		mfd_remove_devices(&pdev->dev);
 		pr_err("prcmu: Failed to add ab8500 subdevice\n");
diff --git a/include/linux/mfd/abx500/ab8500.h b/include/linux/mfd/abx500/ab8500.h
index a86ca1406fb8..4e7fe7417fc9 100644
--- a/include/linux/mfd/abx500/ab8500.h
+++ b/include/linux/mfd/abx500/ab8500.h
@@ -347,7 +347,6 @@ struct ab8500 {
 	struct mutex	lock;
 	struct mutex	irq_lock;
 	atomic_t	transfer_ongoing;
-	int		irq_base;
 	int		irq;
 	struct irq_domain  *domain;
 	enum ab8500_version version;
@@ -378,7 +377,6 @@ struct ab8500_sysctrl_platform_data;
  * @regulator: machine-specific constraints for regulators
  */
 struct ab8500_platform_data {
-	int irq_base;
 	void (*init) (struct ab8500 *);
 	struct ab8500_regulator_platform_data *regulator;
 	struct ab8500_codec_platform_data *codec;
diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h
index 060e11256fbc..bf5109d38a26 100644
--- a/include/linux/mfd/dbx500-prcmu.h
+++ b/include/linux/mfd/dbx500-prcmu.h
@@ -183,8 +183,6 @@ struct prcmu_pdata
 	bool enable_set_ddr_opp;
 	bool enable_ape_opp_100_voltage;
 	struct ab8500_platform_data *ab_platdata;
-	int ab_irq;
-	int irq_base;
 	u32 version_offset;
 	u32 legacy_offset;
 	u32 adt_offset;
-- 
cgit v1.2.3


From f2518480c7b744296a5587990a54e3a284d932b8 Mon Sep 17 00:00:00 2001
From: Robin Gong <b38343@freescale.com>
Date: Tue, 4 Mar 2014 17:40:36 +0800
Subject: regulator: pfuze100: add pfuze200 support

support pfuze200 chip which remove SW1C and SW4 based on pfuze100.

Signed-off-by: Robin Gong <b38343@freescale.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 .../devicetree/bindings/regulator/pfuze100.txt     |  96 +++++++++-
 drivers/regulator/pfuze100-regulator.c             | 196 +++++++++++++++------
 include/linux/regulator/pfuze100.h                 |  14 ++
 3 files changed, 251 insertions(+), 55 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/devicetree/bindings/regulator/pfuze100.txt b/Documentation/devicetree/bindings/regulator/pfuze100.txt
index fc989b2e8057..34ef5d16d0f1 100644
--- a/Documentation/devicetree/bindings/regulator/pfuze100.txt
+++ b/Documentation/devicetree/bindings/regulator/pfuze100.txt
@@ -1,7 +1,7 @@
 PFUZE100 family of regulators
 
 Required properties:
-- compatible: "fsl,pfuze100"
+- compatible: "fsl,pfuze100" or "fsl,pfuze200"
 - reg: I2C slave address
 
 Required child node:
@@ -10,11 +10,14 @@ Required child node:
   Documentation/devicetree/bindings/regulator/regulator.txt.
 
   The valid names for regulators are:
+  --PFUZE100
   sw1ab,sw1c,sw2,sw3a,sw3b,sw4,swbst,vsnvs,vrefddr,vgen1~vgen6
+  --PFUZE200
+  sw1ab,sw2,sw3a,sw3b,swbst,vsnvs,vrefddr,vgen1~vgen6
 
 Each regulator is defined using the standard binding for regulators.
 
-Example:
+Example 1: PFUZE100
 
 	pmic: pfuze100@08 {
 		compatible = "fsl,pfuze100";
@@ -113,3 +116,92 @@ Example:
 			};
 		};
 	};
+
+
+Example 2: PFUZE200
+
+	pmic: pfuze200@08 {
+		compatible = "fsl,pfuze200";
+		reg = <0x08>;
+
+		regulators {
+			sw1a_reg: sw1ab {
+				regulator-min-microvolt = <300000>;
+				regulator-max-microvolt = <1875000>;
+				regulator-boot-on;
+				regulator-always-on;
+				regulator-ramp-delay = <6250>;
+			};
+
+			sw2_reg: sw2 {
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			sw3a_reg: sw3a {
+				regulator-min-microvolt = <400000>;
+				regulator-max-microvolt = <1975000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			sw3b_reg: sw3b {
+				regulator-min-microvolt = <400000>;
+				regulator-max-microvolt = <1975000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			swbst_reg: swbst {
+				regulator-min-microvolt = <5000000>;
+				regulator-max-microvolt = <5150000>;
+			};
+
+			snvs_reg: vsnvs {
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			vref_reg: vrefddr {
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			vgen1_reg: vgen1 {
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1550000>;
+			};
+
+			vgen2_reg: vgen2 {
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1550000>;
+			};
+
+			vgen3_reg: vgen3 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+			};
+
+			vgen4_reg: vgen4 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vgen5_reg: vgen5 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vgen6_reg: vgen6 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+		};
+	};
diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c
index 371a55374edc..ef330e69336a 100644
--- a/drivers/regulator/pfuze100-regulator.c
+++ b/drivers/regulator/pfuze100-regulator.c
@@ -56,6 +56,8 @@
 #define PFUZE100_VGEN5VOL	0x70
 #define PFUZE100_VGEN6VOL	0x71
 
+enum chips {PFUZE100, PFUZE200, PFUZE_NUM};
+
 struct pfuze_regulator {
 	struct regulator_desc desc;
 	unsigned char stby_reg;
@@ -63,6 +65,7 @@ struct pfuze_regulator {
 };
 
 struct pfuze_chip {
+	int	chip_id;
 	struct regmap *regmap;
 	struct device *dev;
 	struct pfuze_regulator regulator_descs[PFUZE100_MAX_REGULATOR];
@@ -77,15 +80,15 @@ static const int pfuze100_vsnvs[] = {
 	1000000, 1100000, 1200000, 1300000, 1500000, 1800000, 3000000,
 };
 
-static const struct i2c_device_id pfuze_device_id[] = {
-	{.name = "pfuze100"},
-	{},
+static const struct i2c_device_id pfuze_device_id[PFUZE_NUM] = {
+	{.name = "pfuze100", .driver_data = PFUZE100},
+	{.name = "pfuze200", .driver_data = PFUZE200},
 };
 MODULE_DEVICE_TABLE(i2c, pfuze_device_id);
 
-static const struct of_device_id pfuze_dt_ids[] = {
-	{ .compatible = "fsl,pfuze100" },
-	{},
+static const struct of_device_id pfuze_dt_ids[PFUZE_NUM] = {
+	{ .compatible = "fsl,pfuze100", .data = (void *)PFUZE100},
+	{ .compatible = "fsl,pfuze200", .data = (void *)PFUZE200},
 };
 MODULE_DEVICE_TABLE(of, pfuze_dt_ids);
 
@@ -139,14 +142,14 @@ static struct regulator_ops pfuze100_swb_regulator_ops = {
 
 };
 
-#define PFUZE100_FIXED_REG(_name, base, voltage)	\
-	[PFUZE100_ ## _name] = {	\
+#define PFUZE100_FIXED_REG(_chip, _name, base, voltage)	\
+	[_chip ## _ ## _name] = {	\
 		.desc = {	\
 			.name = #_name,	\
 			.n_voltages = 1,	\
 			.ops = &pfuze100_fixed_regulator_ops,	\
 			.type = REGULATOR_VOLTAGE,	\
-			.id = PFUZE100_ ## _name,	\
+			.id = _chip ## _ ## _name,	\
 			.owner = THIS_MODULE,	\
 			.min_uV = (voltage),	\
 			.enable_reg = (base),	\
@@ -154,14 +157,14 @@ static struct regulator_ops pfuze100_swb_regulator_ops = {
 		},	\
 	}
 
-#define PFUZE100_SW_REG(_name, base, min, max, step)	\
-	[PFUZE100_ ## _name] = {	\
+#define PFUZE100_SW_REG(_chip, _name, base, min, max, step)	\
+	[_chip ## _ ## _name] = {	\
 		.desc = {	\
 			.name = #_name,\
 			.n_voltages = ((max) - (min)) / (step) + 1,	\
 			.ops = &pfuze100_sw_regulator_ops,	\
 			.type = REGULATOR_VOLTAGE,	\
-			.id = PFUZE100_ ## _name,	\
+			.id = _chip ## _ ## _name,	\
 			.owner = THIS_MODULE,	\
 			.min_uV = (min),	\
 			.uV_step = (step),	\
@@ -172,14 +175,14 @@ static struct regulator_ops pfuze100_swb_regulator_ops = {
 		.stby_mask = 0x3f,	\
 	}
 
-#define PFUZE100_SWB_REG(_name, base, mask, voltages)	\
-	[PFUZE100_ ## _name] = {	\
+#define PFUZE100_SWB_REG(_chip, _name, base, mask, voltages)	\
+	[_chip ## _ ##  _name] = {	\
 		.desc = {	\
 			.name = #_name,	\
 			.n_voltages = ARRAY_SIZE(voltages),	\
 			.ops = &pfuze100_swb_regulator_ops,	\
 			.type = REGULATOR_VOLTAGE,	\
-			.id = PFUZE100_ ## _name,	\
+			.id = _chip ## _ ## _name,	\
 			.owner = THIS_MODULE,	\
 			.volt_table = voltages,	\
 			.vsel_reg = (base),	\
@@ -187,14 +190,14 @@ static struct regulator_ops pfuze100_swb_regulator_ops = {
 		},	\
 	}
 
-#define PFUZE100_VGEN_REG(_name, base, min, max, step)	\
-	[PFUZE100_ ## _name] = {	\
+#define PFUZE100_VGEN_REG(_chip, _name, base, min, max, step)	\
+	[_chip ## _ ## _name] = {	\
 		.desc = {	\
 			.name = #_name,	\
 			.n_voltages = ((max) - (min)) / (step) + 1,	\
 			.ops = &pfuze100_ldo_regulator_ops,	\
 			.type = REGULATOR_VOLTAGE,	\
-			.id = PFUZE100_ ## _name,	\
+			.id = _chip ## _ ## _name,	\
 			.owner = THIS_MODULE,	\
 			.min_uV = (min),	\
 			.uV_step = (step),	\
@@ -207,25 +210,45 @@ static struct regulator_ops pfuze100_swb_regulator_ops = {
 		.stby_mask = 0x20,	\
 	}
 
+/* PFUZE100 */
 static struct pfuze_regulator pfuze100_regulators[] = {
-	PFUZE100_SW_REG(SW1AB, PFUZE100_SW1ABVOL, 300000, 1875000, 25000),
-	PFUZE100_SW_REG(SW1C, PFUZE100_SW1CVOL, 300000, 1875000, 25000),
-	PFUZE100_SW_REG(SW2, PFUZE100_SW2VOL, 400000, 1975000, 25000),
-	PFUZE100_SW_REG(SW3A, PFUZE100_SW3AVOL, 400000, 1975000, 25000),
-	PFUZE100_SW_REG(SW3B, PFUZE100_SW3BVOL, 400000, 1975000, 25000),
-	PFUZE100_SW_REG(SW4, PFUZE100_SW4VOL, 400000, 1975000, 25000),
-	PFUZE100_SWB_REG(SWBST, PFUZE100_SWBSTCON1, 0x3 , pfuze100_swbst),
-	PFUZE100_SWB_REG(VSNVS, PFUZE100_VSNVSVOL, 0x7, pfuze100_vsnvs),
-	PFUZE100_FIXED_REG(VREFDDR, PFUZE100_VREFDDRCON, 750000),
-	PFUZE100_VGEN_REG(VGEN1, PFUZE100_VGEN1VOL, 800000, 1550000, 50000),
-	PFUZE100_VGEN_REG(VGEN2, PFUZE100_VGEN2VOL, 800000, 1550000, 50000),
-	PFUZE100_VGEN_REG(VGEN3, PFUZE100_VGEN3VOL, 1800000, 3300000, 100000),
-	PFUZE100_VGEN_REG(VGEN4, PFUZE100_VGEN4VOL, 1800000, 3300000, 100000),
-	PFUZE100_VGEN_REG(VGEN5, PFUZE100_VGEN5VOL, 1800000, 3300000, 100000),
-	PFUZE100_VGEN_REG(VGEN6, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000),
+	PFUZE100_SW_REG(PFUZE100, SW1AB, PFUZE100_SW1ABVOL, 300000, 1875000, 25000),
+	PFUZE100_SW_REG(PFUZE100, SW1C, PFUZE100_SW1CVOL, 300000, 1875000, 25000),
+	PFUZE100_SW_REG(PFUZE100, SW2, PFUZE100_SW2VOL, 400000, 1975000, 25000),
+	PFUZE100_SW_REG(PFUZE100, SW3A, PFUZE100_SW3AVOL, 400000, 1975000, 25000),
+	PFUZE100_SW_REG(PFUZE100, SW3B, PFUZE100_SW3BVOL, 400000, 1975000, 25000),
+	PFUZE100_SW_REG(PFUZE100, SW4, PFUZE100_SW4VOL, 400000, 1975000, 25000),
+	PFUZE100_SWB_REG(PFUZE100, SWBST, PFUZE100_SWBSTCON1, 0x3 , pfuze100_swbst),
+	PFUZE100_SWB_REG(PFUZE100, VSNVS, PFUZE100_VSNVSVOL, 0x7, pfuze100_vsnvs),
+	PFUZE100_FIXED_REG(PFUZE100, VREFDDR, PFUZE100_VREFDDRCON, 750000),
+	PFUZE100_VGEN_REG(PFUZE100, VGEN1, PFUZE100_VGEN1VOL, 800000, 1550000, 50000),
+	PFUZE100_VGEN_REG(PFUZE100, VGEN2, PFUZE100_VGEN2VOL, 800000, 1550000, 50000),
+	PFUZE100_VGEN_REG(PFUZE100, VGEN3, PFUZE100_VGEN3VOL, 1800000, 3300000, 100000),
+	PFUZE100_VGEN_REG(PFUZE100, VGEN4, PFUZE100_VGEN4VOL, 1800000, 3300000, 100000),
+	PFUZE100_VGEN_REG(PFUZE100, VGEN5, PFUZE100_VGEN5VOL, 1800000, 3300000, 100000),
+	PFUZE100_VGEN_REG(PFUZE100, VGEN6, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000),
+};
+
+static struct pfuze_regulator pfuze200_regulators[] = {
+	PFUZE100_SW_REG(PFUZE200, SW1AB, PFUZE100_SW1ABVOL, 300000, 1875000, 25000),
+	PFUZE100_SW_REG(PFUZE200, SW2, PFUZE100_SW2VOL, 400000, 1975000, 25000),
+	PFUZE100_SW_REG(PFUZE200, SW3A, PFUZE100_SW3AVOL, 400000, 1975000, 25000),
+	PFUZE100_SW_REG(PFUZE200, SW3B, PFUZE100_SW3BVOL, 400000, 1975000, 25000),
+	PFUZE100_SWB_REG(PFUZE200, SWBST, PFUZE100_SWBSTCON1, 0x3 , pfuze100_swbst),
+	PFUZE100_SWB_REG(PFUZE200, VSNVS, PFUZE100_VSNVSVOL, 0x7, pfuze100_vsnvs),
+	PFUZE100_FIXED_REG(PFUZE200, VREFDDR, PFUZE100_VREFDDRCON, 750000),
+	PFUZE100_VGEN_REG(PFUZE200, VGEN1, PFUZE100_VGEN1VOL, 800000, 1550000, 50000),
+	PFUZE100_VGEN_REG(PFUZE200, VGEN2, PFUZE100_VGEN2VOL, 800000, 1550000, 50000),
+	PFUZE100_VGEN_REG(PFUZE200, VGEN3, PFUZE100_VGEN3VOL, 1800000, 3300000, 100000),
+	PFUZE100_VGEN_REG(PFUZE200, VGEN4, PFUZE100_VGEN4VOL, 1800000, 3300000, 100000),
+	PFUZE100_VGEN_REG(PFUZE200, VGEN5, PFUZE100_VGEN5VOL, 1800000, 3300000, 100000),
+	PFUZE100_VGEN_REG(PFUZE200, VGEN6, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000),
 };
 
+static struct pfuze_regulator *pfuze_regulators;
+
 #ifdef CONFIG_OF
+/* PFUZE100 */
 static struct of_regulator_match pfuze100_matches[] = {
 	{ .name = "sw1ab",	},
 	{ .name = "sw1c",	},
@@ -244,6 +267,26 @@ static struct of_regulator_match pfuze100_matches[] = {
 	{ .name = "vgen6",	},
 };
 
+/* PFUZE200 */
+static struct of_regulator_match pfuze200_matches[] = {
+
+	{ .name = "sw1ab",	},
+	{ .name = "sw2",	},
+	{ .name = "sw3a",	},
+	{ .name = "sw3b",	},
+	{ .name = "swbst",	},
+	{ .name = "vsnvs",	},
+	{ .name = "vrefddr",	},
+	{ .name = "vgen1",	},
+	{ .name = "vgen2",	},
+	{ .name = "vgen3",	},
+	{ .name = "vgen4",	},
+	{ .name = "vgen5",	},
+	{ .name = "vgen6",	},
+};
+
+static struct of_regulator_match *pfuze_matches;
+
 static int pfuze_parse_regulators_dt(struct pfuze_chip *chip)
 {
 	struct device *dev = chip->dev;
@@ -260,8 +303,20 @@ static int pfuze_parse_regulators_dt(struct pfuze_chip *chip)
 		return -EINVAL;
 	}
 
-	ret = of_regulator_match(dev, parent, pfuze100_matches,
-				 ARRAY_SIZE(pfuze100_matches));
+	switch (chip->chip_id) {
+	case PFUZE200:
+		pfuze_matches = pfuze200_matches;
+		ret = of_regulator_match(dev, parent, pfuze200_matches,
+					 ARRAY_SIZE(pfuze200_matches));
+		break;
+
+	case PFUZE100:
+	default:
+		pfuze_matches = pfuze100_matches;
+		ret = of_regulator_match(dev, parent, pfuze100_matches,
+					 ARRAY_SIZE(pfuze100_matches));
+		break;
+	}
 
 	of_node_put(parent);
 	if (ret < 0) {
@@ -275,12 +330,12 @@ static int pfuze_parse_regulators_dt(struct pfuze_chip *chip)
 
 static inline struct regulator_init_data *match_init_data(int index)
 {
-	return pfuze100_matches[index].init_data;
+	return pfuze_matches[index].init_data;
 }
 
 static inline struct device_node *match_of_node(int index)
 {
-	return pfuze100_matches[index].of_node;
+	return pfuze_matches[index].of_node;
 }
 #else
 static int pfuze_parse_regulators_dt(struct pfuze_chip *chip)
@@ -308,16 +363,14 @@ static int pfuze_identify(struct pfuze_chip *pfuze_chip)
 	if (ret)
 		return ret;
 
-	switch (value & 0x0f) {
-	/*
-	 * Freescale misprogrammed 1-3% of parts prior to week 8 of 2013
-	 * as ID=8
-	 */
-	case 0x8:
+	if (((value & 0x0f) == 0x8) && (pfuze_chip->chip_id == PFUZE100)) {
+		/*
+		 * Freescale misprogrammed 1-3% of parts prior to week 8 of 2013
+		 * as ID=8 in PFUZE100
+		 */
 		dev_info(pfuze_chip->dev, "Assuming misprogrammed ID=0x8");
-	case 0x0:
-		break;
-	default:
+	} else if ((value & 0x0f) != pfuze_chip->chip_id) {
+		/* device id NOT match with your setting */
 		dev_warn(pfuze_chip->dev, "Illegal ID: %x\n", value);
 		return -ENODEV;
 	}
@@ -353,17 +406,31 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 	    dev_get_platdata(&client->dev);
 	struct regulator_config config = { };
 	int i, ret;
+	const struct of_device_id *match;
+	u32 regulator_num;
+	u32 sw_check_start, sw_check_end;
 
 	pfuze_chip = devm_kzalloc(&client->dev, sizeof(*pfuze_chip),
 			GFP_KERNEL);
 	if (!pfuze_chip)
 		return -ENOMEM;
 
-	i2c_set_clientdata(client, pfuze_chip);
-
-	memcpy(pfuze_chip->regulator_descs, pfuze100_regulators,
-		sizeof(pfuze_chip->regulator_descs));
+	if (client->dev.of_node) {
+		match = of_match_device(of_match_ptr(pfuze_dt_ids),
+				&client->dev);
+		if (!match) {
+			dev_err(&client->dev, "Error: No device match found\n");
+			return -ENODEV;
+		}
+		pfuze_chip->chip_id = (int)(long)match->data;
+	} else if (id) {
+		pfuze_chip->chip_id = id->driver_data;
+	} else {
+		dev_err(&client->dev, "No dts match or id table match found\n");
+		return -ENODEV;
+	}
 
+	i2c_set_clientdata(client, pfuze_chip);
 	pfuze_chip->dev = &client->dev;
 
 	pfuze_chip->regmap = devm_regmap_init_i2c(client, &pfuze_regmap_config);
@@ -380,11 +447,34 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 		return ret;
 	}
 
+	/* use the right regulators after identify the right device */
+	switch (pfuze_chip->chip_id) {
+	case PFUZE200:
+		pfuze_regulators = pfuze200_regulators;
+		regulator_num = ARRAY_SIZE(pfuze200_regulators);
+		sw_check_start = PFUZE200_SW2;
+		sw_check_end = PFUZE200_SW3B;
+		break;
+
+	case PFUZE100:
+	default:
+		pfuze_regulators = pfuze100_regulators;
+		regulator_num = ARRAY_SIZE(pfuze100_regulators);
+		sw_check_start = PFUZE100_SW2;
+		sw_check_end = PFUZE100_SW4;
+		break;
+	}
+	dev_info(&client->dev, "pfuze%s found.\n",
+		(pfuze_chip->chip_id == PFUZE100) ? "100" : "200");
+
+	memcpy(pfuze_chip->regulator_descs, pfuze_regulators,
+		sizeof(pfuze_chip->regulator_descs));
+
 	ret = pfuze_parse_regulators_dt(pfuze_chip);
 	if (ret)
 		return ret;
 
-	for (i = 0; i < PFUZE100_MAX_REGULATOR; i++) {
+	for (i = 0; i < regulator_num; i++) {
 		struct regulator_init_data *init_data;
 		struct regulator_desc *desc;
 		int val;
@@ -397,7 +487,7 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 			init_data = match_init_data(i);
 
 		/* SW2~SW4 high bit check and modify the voltage value table */
-		if (i > PFUZE100_SW1C && i < PFUZE100_SWBST) {
+		if (i >= sw_check_start && i <= sw_check_end) {
 			regmap_read(pfuze_chip->regmap, desc->vsel_reg, &val);
 			if (val & 0x40) {
 				desc->min_uV = 800000;
@@ -415,7 +505,7 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 			devm_regulator_register(&client->dev, desc, &config);
 		if (IS_ERR(pfuze_chip->regulators[i])) {
 			dev_err(&client->dev, "register regulator%s failed\n",
-				pfuze100_regulators[i].desc.name);
+				pfuze_regulators[i].desc.name);
 			return PTR_ERR(pfuze_chip->regulators[i]);
 		}
 	}
diff --git a/include/linux/regulator/pfuze100.h b/include/linux/regulator/pfuze100.h
index 65d550bf3954..364f7a7c43db 100644
--- a/include/linux/regulator/pfuze100.h
+++ b/include/linux/regulator/pfuze100.h
@@ -35,6 +35,20 @@
 #define PFUZE100_VGEN6		14
 #define PFUZE100_MAX_REGULATOR	15
 
+#define PFUZE200_SW1AB		0
+#define PFUZE200_SW2		1
+#define PFUZE200_SW3A		2
+#define PFUZE200_SW3B		3
+#define PFUZE200_SWBST		4
+#define PFUZE200_VSNVS		5
+#define PFUZE200_VREFDDR	6
+#define PFUZE200_VGEN1		7
+#define PFUZE200_VGEN2		8
+#define PFUZE200_VGEN3		9
+#define PFUZE200_VGEN4		10
+#define PFUZE200_VGEN5		11
+#define PFUZE200_VGEN6		12
+
 struct regulator_init_data;
 
 struct pfuze_regulator_platform_data {
-- 
cgit v1.2.3


From bb3a6b7845851d23cb826040b4c3c9c294e7cfb4 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Wed, 19 Feb 2014 14:07:24 +0800
Subject: iommu/vt-d: Factor out dmar_alloc_dev_scope() for later reuse

Factor out function dmar_alloc_dev_scope() from dmar_parse_dev_scope()
for later reuse.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Signed-off-by: Joerg Roedel <joro@8bytes.org>
---
 drivers/iommu/dmar.c | 28 ++++++++++++++++------------
 include/linux/dmar.h |  1 +
 2 files changed, 17 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 158156543410..58dde75c5229 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -117,13 +117,9 @@ static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope,
 	return 0;
 }
 
-int __init dmar_parse_dev_scope(void *start, void *end, int *cnt,
-				struct pci_dev ***devices, u16 segment)
+void *dmar_alloc_dev_scope(void *start, void *end, int *cnt)
 {
 	struct acpi_dmar_device_scope *scope;
-	void * tmp = start;
-	int index;
-	int ret;
 
 	*cnt = 0;
 	while (start < end) {
@@ -138,15 +134,24 @@ int __init dmar_parse_dev_scope(void *start, void *end, int *cnt,
 		start += scope->length;
 	}
 	if (*cnt == 0)
-		return 0;
+		return NULL;
+
+	return kcalloc(*cnt, sizeof(struct pci_dev *), GFP_KERNEL);
+}
+
+int __init dmar_parse_dev_scope(void *start, void *end, int *cnt,
+				struct pci_dev ***devices, u16 segment)
+{
+	struct acpi_dmar_device_scope *scope;
+	int index, ret;
 
-	*devices = kcalloc(*cnt, sizeof(struct pci_dev *), GFP_KERNEL);
-	if (!*devices)
+	*devices = dmar_alloc_dev_scope(start, end, cnt);
+	if (*cnt == 0)
+		return 0;
+	else if (!*devices)
 		return -ENOMEM;
 
-	start = tmp;
-	index = 0;
-	while (start < end) {
+	for (index = 0; start < end; start += scope->length) {
 		scope = start;
 		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT ||
 		    scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE) {
@@ -158,7 +163,6 @@ int __init dmar_parse_dev_scope(void *start, void *end, int *cnt,
 			}
 			index ++;
 		}
-		start += scope->length;
 	}
 
 	return 0;
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index eccb0c0c6cf6..1b08ce80bfbf 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -69,6 +69,7 @@ extern int dmar_table_init(void);
 extern int dmar_dev_scope_init(void);
 extern int dmar_parse_dev_scope(void *start, void *end, int *cnt,
 				struct pci_dev ***devices, u16 segment);
+extern void *dmar_alloc_dev_scope(void *start, void *end, int *cnt);
 extern void dmar_free_dev_scope(struct pci_dev ***devices, int *cnt);
 
 /* Intel IOMMU detection */
-- 
cgit v1.2.3


From b94e4117f8c4ffb591b1e462364d725e3a1c63c4 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Wed, 19 Feb 2014 14:07:25 +0800
Subject: iommu/vt-d: Move private structures and variables into intel-iommu.c

Move private structures and variables into intel-iommu.c, which will
help to simplify locking policy for hotplug. Also delete redundant
declarations.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Signed-off-by: Joerg Roedel <joro@8bytes.org>
---
 drivers/iommu/intel-iommu.c | 31 +++++++++++++++++++++++++------
 include/linux/dmar.h        | 23 +----------------------
 2 files changed, 26 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 5a411e83433c..fffe3d166662 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -380,6 +380,29 @@ struct device_domain_info {
 	struct dmar_domain *domain; /* pointer to domain */
 };
 
+struct dmar_rmrr_unit {
+	struct list_head list;		/* list of rmrr units	*/
+	struct acpi_dmar_header *hdr;	/* ACPI header		*/
+	u64	base_address;		/* reserved base address*/
+	u64	end_address;		/* reserved end address */
+	struct pci_dev **devices;	/* target devices */
+	int	devices_cnt;		/* target device count */
+};
+
+struct dmar_atsr_unit {
+	struct list_head list;		/* list of ATSR units */
+	struct acpi_dmar_header *hdr;	/* ACPI header */
+	struct pci_dev **devices;	/* target devices */
+	int devices_cnt;		/* target device count */
+	u8 include_all:1;		/* include all ports */
+};
+
+static LIST_HEAD(dmar_atsr_units);
+static LIST_HEAD(dmar_rmrr_units);
+
+#define for_each_rmrr_units(rmrr) \
+	list_for_each_entry(rmrr, &dmar_rmrr_units, list)
+
 static void flush_unmaps_timeout(unsigned long data);
 
 static DEFINE_TIMER(unmap_timer,  flush_unmaps_timeout, 0, 0);
@@ -403,6 +426,8 @@ static int timer_on;
 static long list_size;
 
 static void domain_remove_dev_info(struct dmar_domain *domain);
+static void domain_remove_one_dev_info(struct dmar_domain *domain,
+				       struct pci_dev *pdev);
 
 #ifdef CONFIG_INTEL_IOMMU_DEFAULT_ON
 int dmar_disabled = 0;
@@ -2243,8 +2268,6 @@ static int __init si_domain_init(int hw)
 	return 0;
 }
 
-static void domain_remove_one_dev_info(struct dmar_domain *domain,
-					  struct pci_dev *pdev);
 static int identity_mapping(struct pci_dev *pdev)
 {
 	struct device_domain_info *info;
@@ -3432,8 +3455,6 @@ static void __init init_iommu_pm_ops(void)
 static inline void init_iommu_pm_ops(void) {}
 #endif	/* CONFIG_PM */
 
-LIST_HEAD(dmar_rmrr_units);
-
 static void __init dmar_register_rmrr_unit(struct dmar_rmrr_unit *rmrr)
 {
 	list_add(&rmrr->list, &dmar_rmrr_units);
@@ -3470,8 +3491,6 @@ rmrr_parse_dev(struct dmar_rmrr_unit *rmrru)
 				    rmrr->segment);
 }
 
-static LIST_HEAD(dmar_atsr_units);
-
 int __init dmar_parse_one_atsr(struct acpi_dmar_header *hdr)
 {
 	struct acpi_dmar_atsr *atsr;
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 1b08ce80bfbf..ea599d4ca9e0 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -139,28 +139,7 @@ extern int arch_setup_dmar_msi(unsigned int irq);
 
 #ifdef CONFIG_INTEL_IOMMU
 extern int iommu_detected, no_iommu;
-extern struct list_head dmar_rmrr_units;
-struct dmar_rmrr_unit {
-	struct list_head list;		/* list of rmrr units	*/
-	struct acpi_dmar_header *hdr;	/* ACPI header		*/
-	u64	base_address;		/* reserved base address*/
-	u64	end_address;		/* reserved end address */
-	struct pci_dev **devices;	/* target devices */
-	int	devices_cnt;		/* target device count */
-};
-
-#define for_each_rmrr_units(rmrr) \
-	list_for_each_entry(rmrr, &dmar_rmrr_units, list)
-
-struct dmar_atsr_unit {
-	struct list_head list;		/* list of ATSR units */
-	struct acpi_dmar_header *hdr;	/* ACPI header */
-	struct pci_dev **devices;	/* target devices */
-	int devices_cnt;		/* target device count */
-	u8 include_all:1;		/* include all ports */
-};
-
-int dmar_parse_rmrr_atsr_dev(void);
+extern int dmar_parse_rmrr_atsr_dev(void);
 extern int dmar_parse_one_rmrr(struct acpi_dmar_header *header);
 extern int dmar_parse_one_atsr(struct acpi_dmar_header *header);
 extern int intel_iommu_init(void);
-- 
cgit v1.2.3


From b683b230a244c3b2b3f6f3292e59d4a63298528b Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Wed, 19 Feb 2014 14:07:32 +0800
Subject: iommu/vt-d: Introduce macro for_each_dev_scope() to walk device scope
 entries

Introduce for_each_dev_scope()/for_each_active_dev_scope() to walk
{active} device scope entries. This will help following RCU lock
related patches.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Signed-off-by: Joerg Roedel <joro@8bytes.org>
---
 drivers/iommu/dmar.c        |  14 ++++---
 drivers/iommu/intel-iommu.c | 100 ++++++++++++++++++++++----------------------
 include/linux/dmar.h        |   6 +++
 3 files changed, 64 insertions(+), 56 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 58dde75c5229..4ae6df27ad5d 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -170,9 +170,12 @@ int __init dmar_parse_dev_scope(void *start, void *end, int *cnt,
 
 void dmar_free_dev_scope(struct pci_dev ***devices, int *cnt)
 {
+	int i;
+	struct pci_dev *tmp_dev;
+
 	if (*devices && *cnt) {
-		while (--*cnt >= 0)
-			pci_dev_put((*devices)[*cnt]);
+		for_each_active_dev_scope(*devices, *cnt, i, tmp_dev)
+			pci_dev_put(tmp_dev);
 		kfree(*devices);
 		*devices = NULL;
 		*cnt = 0;
@@ -402,10 +405,11 @@ static int dmar_pci_device_match(struct pci_dev *devices[], int cnt,
 			  struct pci_dev *dev)
 {
 	int index;
+	struct pci_dev *tmp;
 
 	while (dev) {
-		for (index = 0; index < cnt; index++)
-			if (dev == devices[index])
+		for_each_active_dev_scope(devices, cnt, index, tmp)
+			if (dev == tmp)
 				return 1;
 
 		/* Check our parent */
@@ -452,7 +456,7 @@ int __init dmar_dev_scope_init(void)
 	if (list_empty(&dmar_drhd_units))
 		goto fail;
 
-	list_for_each_entry(drhd, &dmar_drhd_units, list) {
+	for_each_drhd_unit(drhd) {
 		ret = dmar_parse_dev(drhd);
 		if (ret)
 			goto fail;
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 7732c43871fa..bb98e37f2cf7 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -654,29 +654,31 @@ static void domain_update_iommu_cap(struct dmar_domain *domain)
 static struct intel_iommu *device_to_iommu(int segment, u8 bus, u8 devfn)
 {
 	struct dmar_drhd_unit *drhd = NULL;
+	struct intel_iommu *iommu;
+	struct pci_dev *dev;
 	int i;
 
-	for_each_active_drhd_unit(drhd) {
+	for_each_active_iommu(iommu, drhd) {
 		if (segment != drhd->segment)
 			continue;
 
-		for (i = 0; i < drhd->devices_cnt; i++) {
-			if (drhd->devices[i] &&
-			    drhd->devices[i]->bus->number == bus &&
-			    drhd->devices[i]->devfn == devfn)
-				return drhd->iommu;
-			if (drhd->devices[i] &&
-			    drhd->devices[i]->subordinate &&
-			    drhd->devices[i]->subordinate->number <= bus &&
-			    drhd->devices[i]->subordinate->busn_res.end >= bus)
-				return drhd->iommu;
+		for_each_active_dev_scope(drhd->devices,
+					  drhd->devices_cnt, i, dev) {
+			if (dev->bus->number == bus && dev->devfn == devfn)
+				goto out;
+			if (dev->subordinate &&
+			    dev->subordinate->number <= bus &&
+			    dev->subordinate->busn_res.end >= bus)
+				goto out;
 		}
 
 		if (drhd->include_all)
-			return drhd->iommu;
+			goto out;
 	}
+	iommu = NULL;
+out:
 
-	return NULL;
+	return iommu;
 }
 
 static void domain_flush_cache(struct dmar_domain *domain,
@@ -2333,17 +2335,19 @@ static int domain_add_dev_info(struct dmar_domain *domain,
 static bool device_has_rmrr(struct pci_dev *dev)
 {
 	struct dmar_rmrr_unit *rmrr;
+	struct pci_dev *tmp;
 	int i;
 
 	for_each_rmrr_units(rmrr) {
-		for (i = 0; i < rmrr->devices_cnt; i++) {
-			/*
-			 * Return TRUE if this RMRR contains the device that
-			 * is passed in.
-			 */
-			if (rmrr->devices[i] == dev)
+		/*
+		 * Return TRUE if this RMRR contains the device that
+		 * is passed in.
+		 */
+		for_each_active_dev_scope(rmrr->devices,
+					  rmrr->devices_cnt, i, tmp)
+			if (tmp == dev) {
 				return true;
-		}
+			}
 	}
 	return false;
 }
@@ -2593,14 +2597,9 @@ static int __init init_dmars(void)
 	 */
 	printk(KERN_INFO "IOMMU: Setting RMRR:\n");
 	for_each_rmrr_units(rmrr) {
-		for (i = 0; i < rmrr->devices_cnt; i++) {
-			pdev = rmrr->devices[i];
-			/*
-			 * some BIOS lists non-exist devices in DMAR
-			 * table.
-			 */
-			if (!pdev)
-				continue;
+		/* some BIOS lists non-exist devices in DMAR table. */
+		for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt,
+					  i, pdev) {
 			ret = iommu_prepare_rmrr_dev(rmrr, pdev);
 			if (ret)
 				printk(KERN_ERR
@@ -3288,13 +3287,14 @@ DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB, quir
 static void __init init_no_remapping_devices(void)
 {
 	struct dmar_drhd_unit *drhd;
+	struct pci_dev *dev;
+	int i;
 
 	for_each_drhd_unit(drhd) {
 		if (!drhd->include_all) {
-			int i;
-			for (i = 0; i < drhd->devices_cnt; i++)
-				if (drhd->devices[i] != NULL)
-					break;
+			for_each_active_dev_scope(drhd->devices,
+						  drhd->devices_cnt, i, dev)
+				break;
 			/* ignore DMAR unit if no pci devices exist */
 			if (i == drhd->devices_cnt)
 				drhd->ignored = 1;
@@ -3302,15 +3302,13 @@ static void __init init_no_remapping_devices(void)
 	}
 
 	for_each_active_drhd_unit(drhd) {
-		int i;
 		if (drhd->include_all)
 			continue;
 
-		for (i = 0; i < drhd->devices_cnt; i++)
-			if (drhd->devices[i] &&
-			    !IS_GFX_DEVICE(drhd->devices[i]))
+		for_each_active_dev_scope(drhd->devices,
+					  drhd->devices_cnt, i, dev)
+			if (!IS_GFX_DEVICE(dev))
 				break;
-
 		if (i < drhd->devices_cnt)
 			continue;
 
@@ -3320,11 +3318,9 @@ static void __init init_no_remapping_devices(void)
 			intel_iommu_gfx_mapped = 1;
 		} else {
 			drhd->ignored = 1;
-			for (i = 0; i < drhd->devices_cnt; i++) {
-				if (!drhd->devices[i])
-					continue;
-				drhd->devices[i]->dev.archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO;
-			}
+			for_each_active_dev_scope(drhd->devices,
+						  drhd->devices_cnt, i, dev)
+				dev->dev.archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO;
 		}
 	}
 }
@@ -3560,9 +3556,9 @@ static void intel_iommu_free_dmars(void)
 
 int dmar_find_matched_atsr_unit(struct pci_dev *dev)
 {
-	int i;
+	int i, ret = 1;
 	struct pci_bus *bus;
-	struct pci_dev *bridge = NULL;
+	struct pci_dev *bridge = NULL, *tmp;
 	struct acpi_dmar_atsr *atsr;
 	struct dmar_atsr_unit *atsru;
 
@@ -3583,22 +3579,24 @@ int dmar_find_matched_atsr_unit(struct pci_dev *dev)
 		if (atsr->segment != pci_domain_nr(dev->bus))
 			continue;
 
-		for (i = 0; i < atsru->devices_cnt; i++)
-			if (atsru->devices[i] == bridge)
-				return 1;
+		for_each_dev_scope(atsru->devices, atsru->devices_cnt, i, tmp)
+			if (tmp == bridge)
+				goto out;
 
 		if (atsru->include_all)
-			return 1;
+			goto out;
 	}
+	ret = 0;
+out:
 
-	return 0;
+	return ret;
 }
 
 int __init dmar_parse_rmrr_atsr_dev(void)
 {
 	struct dmar_rmrr_unit *rmrr;
 	struct dmar_atsr_unit *atsr;
-	int ret = 0;
+	int ret;
 
 	list_for_each_entry(rmrr, &dmar_rmrr_units, list) {
 		ret = rmrr_parse_dev(rmrr);
@@ -3612,7 +3610,7 @@ int __init dmar_parse_rmrr_atsr_dev(void)
 			return ret;
 	}
 
-	return ret;
+	return 0;
 }
 
 /*
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index ea599d4ca9e0..4b77fd8fde76 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -65,6 +65,12 @@ extern struct list_head dmar_drhd_units;
 	list_for_each_entry(drhd, &dmar_drhd_units, list)		\
 		if (i=drhd->iommu, 0) {} else 
 
+#define	for_each_dev_scope(a, c, p, d)	\
+	for ((p) = 0; ((d) = (p) < (c) ? (a)[(p)] : NULL, (p) < (c)); (p)++)
+
+#define	for_each_active_dev_scope(a, c, p, d)	\
+	for_each_dev_scope((a), (c), (p), (d))	if (!(d)) { continue; } else
+
 extern int dmar_table_init(void);
 extern int dmar_dev_scope_init(void);
 extern int dmar_parse_dev_scope(void *start, void *end, int *cnt,
-- 
cgit v1.2.3


From 3a5670e8ac932c10a3e50d9dc0ab1da4cc3041d7 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Wed, 19 Feb 2014 14:07:33 +0800
Subject: iommu/vt-d: Introduce a rwsem to protect global data structures

Introduce a global rwsem dmar_global_lock, which will be used to
protect DMAR related global data structures from DMAR/PCI/memory
device hotplug operations in process context.

DMA and interrupt remapping related data structures are read most,
and only change when memory/PCI/DMAR hotplug event happens.
So a global rwsem solution is adopted for balance between simplicity
and performance.

For interrupt remapping driver, function intel_irq_remapping_supported(),
dmar_table_init(), intel_enable_irq_remapping(), disable_irq_remapping(),
reenable_irq_remapping() and enable_drhd_fault_handling() etc
are called during booting, suspending and resuming with interrupt
disabled, so no need to take the global lock.

For interrupt remapping entry allocation, the locking model is:
	down_read(&dmar_global_lock);
	/* Find corresponding iommu */
	iommu = map_hpet_to_ir(id);
	if (iommu)
		/*
		 * Allocate remapping entry and mark entry busy,
		 * the IOMMU won't be hot-removed until the
		 * allocated entry has been released.
		 */
		index = alloc_irte(iommu, irq, 1);
	up_read(&dmar_global_lock);

For DMA remmaping driver, we only uses the dmar_global_lock rwsem to
protect functions which are only called in process context. For any
function which may be called in interrupt context, we will use RCU
to protect them in following patches.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Signed-off-by: Joerg Roedel <joro@8bytes.org>
---
 drivers/iommu/dmar.c                |  19 ++++++-
 drivers/iommu/intel-iommu.c         |  22 +++++---
 drivers/iommu/intel_irq_remapping.c | 108 ++++++++++++++++++++++++------------
 include/linux/dmar.h                |   2 +
 4 files changed, 103 insertions(+), 48 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 4ae6df27ad5d..c9aca8841fa0 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -43,10 +43,19 @@
 
 #include "irq_remapping.h"
 
-/* No locks are needed as DMA remapping hardware unit
- * list is constructed at boot time and hotplug of
- * these units are not supported by the architecture.
+/*
+ * Assumptions:
+ * 1) The hotplug framework guarentees that DMAR unit will be hot-added
+ *    before IO devices managed by that unit.
+ * 2) The hotplug framework guarantees that DMAR unit will be hot-removed
+ *    after IO devices managed by that unit.
+ * 3) Hotplug events are rare.
+ *
+ * Locking rules for DMA and interrupt remapping related global data structures:
+ * 1) Use dmar_global_lock in process context
+ * 2) Use RCU in interrupt context
  */
+DECLARE_RWSEM(dmar_global_lock);
 LIST_HEAD(dmar_drhd_units);
 
 struct acpi_table_header * __initdata dmar_tbl;
@@ -565,6 +574,7 @@ int __init detect_intel_iommu(void)
 {
 	int ret;
 
+	down_write(&dmar_global_lock);
 	ret = dmar_table_detect();
 	if (ret)
 		ret = check_zero_address();
@@ -582,6 +592,7 @@ int __init detect_intel_iommu(void)
 	}
 	early_acpi_os_unmap_memory((void __iomem *)dmar_tbl, dmar_tbl_size);
 	dmar_tbl = NULL;
+	up_write(&dmar_global_lock);
 
 	return ret ? 1 : -ENODEV;
 }
@@ -1394,10 +1405,12 @@ static int __init dmar_free_unused_resources(void)
 	if (irq_remapping_enabled || intel_iommu_enabled)
 		return 0;
 
+	down_write(&dmar_global_lock);
 	list_for_each_entry_safe(dmaru, dmaru_n, &dmar_drhd_units, list) {
 		list_del(&dmaru->list);
 		dmar_free_drhd(dmaru);
 	}
+	up_write(&dmar_global_lock);
 
 	return 0;
 }
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index bb98e37f2cf7..50d639a2df88 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3637,11 +3637,13 @@ static int device_notifier(struct notifier_block *nb,
 	if (!domain)
 		return 0;
 
+	down_read(&dmar_global_lock);
 	domain_remove_one_dev_info(domain, pdev);
 	if (!(domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE) &&
 	    !(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY) &&
 	    list_empty(&domain->devices))
 		domain_exit(domain);
+	up_read(&dmar_global_lock);
 
 	return 0;
 }
@@ -3659,6 +3661,13 @@ int __init intel_iommu_init(void)
 	/* VT-d is required for a TXT/tboot launch, so enforce that */
 	force_on = tboot_force_iommu();
 
+	if (iommu_init_mempool()) {
+		if (force_on)
+			panic("tboot: Failed to initialize iommu memory\n");
+		return -ENOMEM;
+	}
+
+	down_write(&dmar_global_lock);
 	if (dmar_table_init()) {
 		if (force_on)
 			panic("tboot: Failed to initialize DMAR table\n");
@@ -3681,12 +3690,6 @@ int __init intel_iommu_init(void)
 	if (no_iommu || dmar_disabled)
 		goto out_free_dmar;
 
-	if (iommu_init_mempool()) {
-		if (force_on)
-			panic("tboot: Failed to initialize iommu memory\n");
-		goto out_free_dmar;
-	}
-
 	if (list_empty(&dmar_rmrr_units))
 		printk(KERN_INFO "DMAR: No RMRR found\n");
 
@@ -3696,7 +3699,7 @@ int __init intel_iommu_init(void)
 	if (dmar_init_reserved_ranges()) {
 		if (force_on)
 			panic("tboot: Failed to reserve iommu ranges\n");
-		goto out_free_mempool;
+		goto out_free_reserved_range;
 	}
 
 	init_no_remapping_devices();
@@ -3708,6 +3711,7 @@ int __init intel_iommu_init(void)
 		printk(KERN_ERR "IOMMU: dmar init failed\n");
 		goto out_free_reserved_range;
 	}
+	up_write(&dmar_global_lock);
 	printk(KERN_INFO
 	"PCI-DMA: Intel(R) Virtualization Technology for Directed I/O\n");
 
@@ -3729,10 +3733,10 @@ int __init intel_iommu_init(void)
 
 out_free_reserved_range:
 	put_iova_domain(&reserved_iova_list);
-out_free_mempool:
-	iommu_exit_mempool();
 out_free_dmar:
 	intel_iommu_free_dmars();
+	up_write(&dmar_global_lock);
+	iommu_exit_mempool();
 	return ret;
 }
 
diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c
index ef5f65dbafe9..9b174893f0f5 100644
--- a/drivers/iommu/intel_irq_remapping.c
+++ b/drivers/iommu/intel_irq_remapping.c
@@ -38,6 +38,17 @@ static struct ioapic_scope ir_ioapic[MAX_IO_APICS];
 static struct hpet_scope ir_hpet[MAX_HPET_TBS];
 static int ir_ioapic_num, ir_hpet_num;
 
+/*
+ * Lock ordering:
+ * ->dmar_global_lock
+ *	->irq_2_ir_lock
+ *		->qi->q_lock
+ *	->iommu->register_lock
+ * Note:
+ * intel_irq_remap_ops.{supported,prepare,enable,disable,reenable} are called
+ * in single-threaded environment with interrupt disabled, so no need to tabke
+ * the dmar_global_lock.
+ */
 static DEFINE_RAW_SPINLOCK(irq_2_ir_lock);
 
 static int __init parse_ioapics_under_ir(void);
@@ -307,12 +318,14 @@ static int set_ioapic_sid(struct irte *irte, int apic)
 	if (!irte)
 		return -1;
 
+	down_read(&dmar_global_lock);
 	for (i = 0; i < MAX_IO_APICS; i++) {
 		if (ir_ioapic[i].id == apic) {
 			sid = (ir_ioapic[i].bus << 8) | ir_ioapic[i].devfn;
 			break;
 		}
 	}
+	up_read(&dmar_global_lock);
 
 	if (sid == 0) {
 		pr_warning("Failed to set source-id of IOAPIC (%d)\n", apic);
@@ -332,12 +345,14 @@ static int set_hpet_sid(struct irte *irte, u8 id)
 	if (!irte)
 		return -1;
 
+	down_read(&dmar_global_lock);
 	for (i = 0; i < MAX_HPET_TBS; i++) {
 		if (ir_hpet[i].id == id) {
 			sid = (ir_hpet[i].bus << 8) | ir_hpet[i].devfn;
 			break;
 		}
 	}
+	up_read(&dmar_global_lock);
 
 	if (sid == 0) {
 		pr_warning("Failed to set source-id of HPET block (%d)\n", id);
@@ -794,10 +809,16 @@ static int __init parse_ioapics_under_ir(void)
 
 static int __init ir_dev_scope_init(void)
 {
+	int ret;
+
 	if (!irq_remapping_enabled)
 		return 0;
 
-	return dmar_dev_scope_init();
+	down_write(&dmar_global_lock);
+	ret = dmar_dev_scope_init();
+	up_write(&dmar_global_lock);
+
+	return ret;
 }
 rootfs_initcall(ir_dev_scope_init);
 
@@ -878,23 +899,27 @@ static int intel_setup_ioapic_entry(int irq,
 				    struct io_apic_irq_attr *attr)
 {
 	int ioapic_id = mpc_ioapic_id(attr->ioapic);
-	struct intel_iommu *iommu = map_ioapic_to_ir(ioapic_id);
+	struct intel_iommu *iommu;
 	struct IR_IO_APIC_route_entry *entry;
 	struct irte irte;
 	int index;
 
+	down_read(&dmar_global_lock);
+	iommu = map_ioapic_to_ir(ioapic_id);
 	if (!iommu) {
 		pr_warn("No mapping iommu for ioapic %d\n", ioapic_id);
-		return -ENODEV;
-	}
-
-	entry = (struct IR_IO_APIC_route_entry *)route_entry;
-
-	index = alloc_irte(iommu, irq, 1);
-	if (index < 0) {
-		pr_warn("Failed to allocate IRTE for ioapic %d\n", ioapic_id);
-		return -ENOMEM;
+		index = -ENODEV;
+	} else {
+		index = alloc_irte(iommu, irq, 1);
+		if (index < 0) {
+			pr_warn("Failed to allocate IRTE for ioapic %d\n",
+				ioapic_id);
+			index = -ENOMEM;
+		}
 	}
+	up_read(&dmar_global_lock);
+	if (index < 0)
+		return index;
 
 	prepare_irte(&irte, vector, destination);
 
@@ -913,6 +938,7 @@ static int intel_setup_ioapic_entry(int irq,
 		irte.avail, irte.vector, irte.dest_id,
 		irte.sid, irte.sq, irte.svt);
 
+	entry = (struct IR_IO_APIC_route_entry *)route_entry;
 	memset(entry, 0, sizeof(*entry));
 
 	entry->index2	= (index >> 15) & 0x1;
@@ -1043,20 +1069,23 @@ static int intel_msi_alloc_irq(struct pci_dev *dev, int irq, int nvec)
 	struct intel_iommu *iommu;
 	int index;
 
+	down_read(&dmar_global_lock);
 	iommu = map_dev_to_ir(dev);
 	if (!iommu) {
 		printk(KERN_ERR
 		       "Unable to map PCI %s to iommu\n", pci_name(dev));
-		return -ENOENT;
+		index = -ENOENT;
+	} else {
+		index = alloc_irte(iommu, irq, nvec);
+		if (index < 0) {
+			printk(KERN_ERR
+			       "Unable to allocate %d IRTE for PCI %s\n",
+			       nvec, pci_name(dev));
+			index = -ENOSPC;
+		}
 	}
+	up_read(&dmar_global_lock);
 
-	index = alloc_irte(iommu, irq, nvec);
-	if (index < 0) {
-		printk(KERN_ERR
-		       "Unable to allocate %d IRTE for PCI %s\n", nvec,
-		       pci_name(dev));
-		return -ENOSPC;
-	}
 	return index;
 }
 
@@ -1064,33 +1093,40 @@ static int intel_msi_setup_irq(struct pci_dev *pdev, unsigned int irq,
 			       int index, int sub_handle)
 {
 	struct intel_iommu *iommu;
+	int ret = -ENOENT;
 
+	down_read(&dmar_global_lock);
 	iommu = map_dev_to_ir(pdev);
-	if (!iommu)
-		return -ENOENT;
-	/*
-	 * setup the mapping between the irq and the IRTE
-	 * base index, the sub_handle pointing to the
-	 * appropriate interrupt remap table entry.
-	 */
-	set_irte_irq(irq, iommu, index, sub_handle);
+	if (iommu) {
+		/*
+		 * setup the mapping between the irq and the IRTE
+		 * base index, the sub_handle pointing to the
+		 * appropriate interrupt remap table entry.
+		 */
+		set_irte_irq(irq, iommu, index, sub_handle);
+		ret = 0;
+	}
+	up_read(&dmar_global_lock);
 
-	return 0;
+	return ret;
 }
 
 static int intel_setup_hpet_msi(unsigned int irq, unsigned int id)
 {
-	struct intel_iommu *iommu = map_hpet_to_ir(id);
+	int ret = -1;
+	struct intel_iommu *iommu;
 	int index;
 
-	if (!iommu)
-		return -1;
-
-	index = alloc_irte(iommu, irq, 1);
-	if (index < 0)
-		return -1;
+	down_read(&dmar_global_lock);
+	iommu = map_hpet_to_ir(id);
+	if (iommu) {
+		index = alloc_irte(iommu, irq, 1);
+		if (index >= 0)
+			ret = 0;
+	}
+	up_read(&dmar_global_lock);
 
-	return 0;
+	return ret;
 }
 
 struct irq_remap_ops intel_irq_remap_ops = {
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 4b77fd8fde76..8f06a0135a84 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -25,6 +25,7 @@
 #include <linux/types.h>
 #include <linux/msi.h>
 #include <linux/irqreturn.h>
+#include <linux/rwsem.h>
 
 struct acpi_dmar_header;
 
@@ -48,6 +49,7 @@ struct dmar_drhd_unit {
 	struct intel_iommu *iommu;
 };
 
+extern struct rw_semaphore dmar_global_lock;
 extern struct list_head dmar_drhd_units;
 
 #define for_each_drhd_unit(drhd) \
-- 
cgit v1.2.3


From 0e242612d9cdb46e878ed1f126c78fe68492af00 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Wed, 19 Feb 2014 14:07:34 +0800
Subject: iommu/vt-d: Use RCU to protect global resources in interrupt context

Global DMA and interrupt remapping resources may be accessed in
interrupt context, so use RCU instead of rwsem to protect them
in such cases.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Signed-off-by: Joerg Roedel <joro@8bytes.org>
---
 drivers/iommu/dmar.c        | 33 ++++++++++++++++++++-------------
 drivers/iommu/intel-iommu.c | 20 ++++++++++++++++----
 include/linux/dmar.h        | 23 +++++++++++++++++------
 3 files changed, 53 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index c9aca8841fa0..6e4d851991f1 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -71,13 +71,13 @@ static void __init dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
 	 * the very end.
 	 */
 	if (drhd->include_all)
-		list_add_tail(&drhd->list, &dmar_drhd_units);
+		list_add_tail_rcu(&drhd->list, &dmar_drhd_units);
 	else
-		list_add(&drhd->list, &dmar_drhd_units);
+		list_add_rcu(&drhd->list, &dmar_drhd_units);
 }
 
 static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope,
-					   struct pci_dev **dev, u16 segment)
+					   struct pci_dev __rcu **dev, u16 segment)
 {
 	struct pci_bus *bus;
 	struct pci_dev *pdev = NULL;
@@ -122,7 +122,9 @@ static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope,
 			pci_name(pdev));
 		return -EINVAL;
 	}
-	*dev = pdev;
+
+	rcu_assign_pointer(*dev, pdev);
+
 	return 0;
 }
 
@@ -149,7 +151,7 @@ void *dmar_alloc_dev_scope(void *start, void *end, int *cnt)
 }
 
 int __init dmar_parse_dev_scope(void *start, void *end, int *cnt,
-				struct pci_dev ***devices, u16 segment)
+				struct pci_dev __rcu ***devices, u16 segment)
 {
 	struct acpi_dmar_device_scope *scope;
 	int index, ret;
@@ -177,7 +179,7 @@ int __init dmar_parse_dev_scope(void *start, void *end, int *cnt,
 	return 0;
 }
 
-void dmar_free_dev_scope(struct pci_dev ***devices, int *cnt)
+void dmar_free_dev_scope(struct pci_dev __rcu ***devices, int *cnt)
 {
 	int i;
 	struct pci_dev *tmp_dev;
@@ -186,9 +188,10 @@ void dmar_free_dev_scope(struct pci_dev ***devices, int *cnt)
 		for_each_active_dev_scope(*devices, *cnt, i, tmp_dev)
 			pci_dev_put(tmp_dev);
 		kfree(*devices);
-		*devices = NULL;
-		*cnt = 0;
 	}
+
+	*devices = NULL;
+	*cnt = 0;
 }
 
 /**
@@ -410,7 +413,7 @@ parse_dmar_table(void)
 	return ret;
 }
 
-static int dmar_pci_device_match(struct pci_dev *devices[], int cnt,
+static int dmar_pci_device_match(struct pci_dev __rcu *devices[], int cnt,
 			  struct pci_dev *dev)
 {
 	int index;
@@ -431,11 +434,12 @@ static int dmar_pci_device_match(struct pci_dev *devices[], int cnt,
 struct dmar_drhd_unit *
 dmar_find_matched_drhd_unit(struct pci_dev *dev)
 {
-	struct dmar_drhd_unit *dmaru = NULL;
+	struct dmar_drhd_unit *dmaru;
 	struct acpi_dmar_hardware_unit *drhd;
 
 	dev = pci_physfn(dev);
 
+	rcu_read_lock();
 	for_each_drhd_unit(dmaru) {
 		drhd = container_of(dmaru->hdr,
 				    struct acpi_dmar_hardware_unit,
@@ -443,14 +447,17 @@ dmar_find_matched_drhd_unit(struct pci_dev *dev)
 
 		if (dmaru->include_all &&
 		    drhd->segment == pci_domain_nr(dev->bus))
-			return dmaru;
+			goto out;
 
 		if (dmar_pci_device_match(dmaru->devices,
 					  dmaru->devices_cnt, dev))
-			return dmaru;
+			goto out;
 	}
+	dmaru = NULL;
+out:
+	rcu_read_unlock();
 
-	return NULL;
+	return dmaru;
 }
 
 int __init dmar_dev_scope_init(void)
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 50d639a2df88..e1679a6fe468 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -385,14 +385,14 @@ struct dmar_rmrr_unit {
 	struct acpi_dmar_header *hdr;	/* ACPI header		*/
 	u64	base_address;		/* reserved base address*/
 	u64	end_address;		/* reserved end address */
-	struct pci_dev **devices;	/* target devices */
+	struct pci_dev __rcu **devices;	/* target devices */
 	int	devices_cnt;		/* target device count */
 };
 
 struct dmar_atsr_unit {
 	struct list_head list;		/* list of ATSR units */
 	struct acpi_dmar_header *hdr;	/* ACPI header */
-	struct pci_dev **devices;	/* target devices */
+	struct pci_dev __rcu **devices;	/* target devices */
 	int devices_cnt;		/* target device count */
 	u8 include_all:1;		/* include all ports */
 };
@@ -634,12 +634,15 @@ static void domain_update_iommu_superpage(struct dmar_domain *domain)
 	}
 
 	/* set iommu_superpage to the smallest common denominator */
+	rcu_read_lock();
 	for_each_active_iommu(iommu, drhd) {
 		mask &= cap_super_page_val(iommu->cap);
 		if (!mask) {
 			break;
 		}
 	}
+	rcu_read_unlock();
+
 	domain->iommu_superpage = fls(mask);
 }
 
@@ -658,6 +661,7 @@ static struct intel_iommu *device_to_iommu(int segment, u8 bus, u8 devfn)
 	struct pci_dev *dev;
 	int i;
 
+	rcu_read_lock();
 	for_each_active_iommu(iommu, drhd) {
 		if (segment != drhd->segment)
 			continue;
@@ -677,6 +681,7 @@ static struct intel_iommu *device_to_iommu(int segment, u8 bus, u8 devfn)
 	}
 	iommu = NULL;
 out:
+	rcu_read_unlock();
 
 	return iommu;
 }
@@ -1535,10 +1540,12 @@ static void domain_exit(struct dmar_domain *domain)
 	dma_pte_free_pagetable(domain, 0, DOMAIN_MAX_PFN(domain->gaw));
 
 	/* clear attached or cached domains */
+	rcu_read_lock();
 	for_each_active_iommu(iommu, drhd)
 		if (domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE ||
 		    test_bit(iommu->seq_id, domain->iommu_bmp))
 			iommu_detach_domain(domain, iommu);
+	rcu_read_unlock();
 
 	free_domain_mem(domain);
 }
@@ -2338,6 +2345,7 @@ static bool device_has_rmrr(struct pci_dev *dev)
 	struct pci_dev *tmp;
 	int i;
 
+	rcu_read_lock();
 	for_each_rmrr_units(rmrr) {
 		/*
 		 * Return TRUE if this RMRR contains the device that
@@ -2346,9 +2354,11 @@ static bool device_has_rmrr(struct pci_dev *dev)
 		for_each_active_dev_scope(rmrr->devices,
 					  rmrr->devices_cnt, i, tmp)
 			if (tmp == dev) {
+				rcu_read_unlock();
 				return true;
 			}
 	}
+	rcu_read_unlock();
 	return false;
 }
 
@@ -3512,7 +3522,7 @@ int __init dmar_parse_one_atsr(struct acpi_dmar_header *hdr)
 	atsru->hdr = hdr;
 	atsru->include_all = atsr->flags & 0x1;
 
-	list_add(&atsru->list, &dmar_atsr_units);
+	list_add_rcu(&atsru->list, &dmar_atsr_units);
 
 	return 0;
 }
@@ -3574,6 +3584,7 @@ int dmar_find_matched_atsr_unit(struct pci_dev *dev)
 	if (!bridge)
 		return 0;
 
+	rcu_read_lock();
 	list_for_each_entry_rcu(atsru, &dmar_atsr_units, list) {
 		atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header);
 		if (atsr->segment != pci_domain_nr(dev->bus))
@@ -3588,6 +3599,7 @@ int dmar_find_matched_atsr_unit(struct pci_dev *dev)
 	}
 	ret = 0;
 out:
+	rcu_read_unlock();
 
 	return ret;
 }
@@ -3604,7 +3616,7 @@ int __init dmar_parse_rmrr_atsr_dev(void)
 			return ret;
 	}
 
-	list_for_each_entry(atsr, &dmar_atsr_units, list) {
+	list_for_each_entry_rcu(atsr, &dmar_atsr_units, list) {
 		ret = atsr_parse_dev(atsr);
 		if (ret)
 			return ret;
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 8f06a0135a84..bedebab934b4 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -26,6 +26,7 @@
 #include <linux/msi.h>
 #include <linux/irqreturn.h>
 #include <linux/rwsem.h>
+#include <linux/rcupdate.h>
 
 struct acpi_dmar_header;
 
@@ -41,7 +42,7 @@ struct dmar_drhd_unit {
 	struct list_head list;		/* list of drhd units	*/
 	struct  acpi_dmar_header *hdr;	/* ACPI header		*/
 	u64	reg_base_addr;		/* register base address*/
-	struct	pci_dev **devices; 	/* target device array	*/
+	struct	pci_dev __rcu **devices;/* target device array	*/
 	int	devices_cnt;		/* target device count	*/
 	u16	segment;		/* PCI domain		*/
 	u8	ignored:1; 		/* ignore drhd		*/
@@ -53,22 +54,31 @@ extern struct rw_semaphore dmar_global_lock;
 extern struct list_head dmar_drhd_units;
 
 #define for_each_drhd_unit(drhd) \
-	list_for_each_entry(drhd, &dmar_drhd_units, list)
+	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list)
 
 #define for_each_active_drhd_unit(drhd)					\
-	list_for_each_entry(drhd, &dmar_drhd_units, list)		\
+	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list)		\
 		if (drhd->ignored) {} else
 
 #define for_each_active_iommu(i, drhd)					\
-	list_for_each_entry(drhd, &dmar_drhd_units, list)		\
+	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list)		\
 		if (i=drhd->iommu, drhd->ignored) {} else
 
 #define for_each_iommu(i, drhd)						\
-	list_for_each_entry(drhd, &dmar_drhd_units, list)		\
+	list_for_each_entry_rcu(drhd, &dmar_drhd_units, list)		\
 		if (i=drhd->iommu, 0) {} else 
 
+static inline bool dmar_rcu_check(void)
+{
+	return rwsem_is_locked(&dmar_global_lock) ||
+	       system_state == SYSTEM_BOOTING;
+}
+
+#define	dmar_rcu_dereference(p)	rcu_dereference_check((p), dmar_rcu_check())
+
 #define	for_each_dev_scope(a, c, p, d)	\
-	for ((p) = 0; ((d) = (p) < (c) ? (a)[(p)] : NULL, (p) < (c)); (p)++)
+	for ((p) = 0; ((d) = (p) < (c) ? dmar_rcu_dereference((a)[(p)]) : \
+			NULL, (p) < (c)); (p)++)
 
 #define	for_each_active_dev_scope(a, c, p, d)	\
 	for_each_dev_scope((a), (c), (p), (d))	if (!(d)) { continue; } else
@@ -78,6 +88,7 @@ extern int dmar_dev_scope_init(void);
 extern int dmar_parse_dev_scope(void *start, void *end, int *cnt,
 				struct pci_dev ***devices, u16 segment);
 extern void *dmar_alloc_dev_scope(void *start, void *end, int *cnt);
+extern void dmar_free_dev_scope(struct pci_dev __rcu ***devices, int *cnt);
 extern void dmar_free_dev_scope(struct pci_dev ***devices, int *cnt);
 
 /* Intel IOMMU detection */
-- 
cgit v1.2.3


From 59ce0515cdaf3b7d47893d12f61e51d691863788 Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Wed, 19 Feb 2014 14:07:35 +0800
Subject: iommu/vt-d: Update DRHD/RMRR/ATSR device scope caches when PCI
 hotplug happens

Current Intel DMAR/IOMMU driver assumes that all PCI devices associated
with DMAR/RMRR/ATSR device scope arrays are created at boot time and
won't change at runtime, so it caches pointers of associated PCI device
object. That assumption may be wrong now due to:
1) introduction of PCI host bridge hotplug
2) PCI device hotplug through sysfs interfaces.

Wang Yijing has tried to solve this issue by caching <bus, dev, func>
tupple instead of the PCI device object pointer, but that's still
unreliable because PCI bus number may change in case of hotplug.
Please refer to http://lkml.org/lkml/2013/11/5/64
Message from Yingjing's mail:
after remove and rescan a pci device
[  611.857095] dmar: DRHD: handling fault status reg 2
[  611.857109] dmar: DMAR:[DMA Read] Request device [86:00.3] fault addr ffff7000
[  611.857109] DMAR:[fault reason 02] Present bit in context entry is clear
[  611.857524] dmar: DRHD: handling fault status reg 102
[  611.857534] dmar: DMAR:[DMA Read] Request device [86:00.3] fault addr ffff6000
[  611.857534] DMAR:[fault reason 02] Present bit in context entry is clear
[  611.857936] dmar: DRHD: handling fault status reg 202
[  611.857947] dmar: DMAR:[DMA Read] Request device [86:00.3] fault addr ffff5000
[  611.857947] DMAR:[fault reason 02] Present bit in context entry is clear
[  611.858351] dmar: DRHD: handling fault status reg 302
[  611.858362] dmar: DMAR:[DMA Read] Request device [86:00.3] fault addr ffff4000
[  611.858362] DMAR:[fault reason 02] Present bit in context entry is clear
[  611.860819] IPv6: ADDRCONF(NETDEV_UP): eth3: link is not ready
[  611.860983] dmar: DRHD: handling fault status reg 402
[  611.860995] dmar: INTR-REMAP: Request device [[86:00.3] fault index a4
[  611.860995] INTR-REMAP:[fault reason 34] Present field in the IRTE entry is clear

This patch introduces a new mechanism to update the DRHD/RMRR/ATSR device scope
caches by hooking PCI bus notification.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Signed-off-by: Joerg Roedel <joro@8bytes.org>
---
 drivers/iommu/dmar.c        | 207 ++++++++++++++++++++++++++++++++++++++++++++
 drivers/iommu/intel-iommu.c |  54 ++++++++++++
 include/linux/dmar.h        |  24 ++++-
 3 files changed, 283 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 6e4d851991f1..bf6bfd1f69aa 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -194,6 +194,209 @@ void dmar_free_dev_scope(struct pci_dev __rcu ***devices, int *cnt)
 	*cnt = 0;
 }
 
+/* Optimize out kzalloc()/kfree() for normal cases */
+static char dmar_pci_notify_info_buf[64];
+
+static struct dmar_pci_notify_info *
+dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event)
+{
+	int level = 0;
+	size_t size;
+	struct pci_dev *tmp;
+	struct dmar_pci_notify_info *info;
+
+	BUG_ON(dev->is_virtfn);
+
+	/* Only generate path[] for device addition event */
+	if (event == BUS_NOTIFY_ADD_DEVICE)
+		for (tmp = dev; tmp; tmp = tmp->bus->self)
+			level++;
+
+	size = sizeof(*info) + level * sizeof(struct acpi_dmar_pci_path);
+	if (size <= sizeof(dmar_pci_notify_info_buf)) {
+		info = (struct dmar_pci_notify_info *)dmar_pci_notify_info_buf;
+	} else {
+		info = kzalloc(size, GFP_KERNEL);
+		if (!info) {
+			pr_warn("Out of memory when allocating notify_info "
+				"for %s.\n", pci_name(dev));
+			return NULL;
+		}
+	}
+
+	info->event = event;
+	info->dev = dev;
+	info->seg = pci_domain_nr(dev->bus);
+	info->level = level;
+	if (event == BUS_NOTIFY_ADD_DEVICE) {
+		for (tmp = dev, level--; tmp; tmp = tmp->bus->self) {
+			info->path[level].device = PCI_SLOT(tmp->devfn);
+			info->path[level].function = PCI_FUNC(tmp->devfn);
+			if (pci_is_root_bus(tmp->bus))
+				info->bus = tmp->bus->number;
+		}
+	}
+
+	return info;
+}
+
+static inline void dmar_free_pci_notify_info(struct dmar_pci_notify_info *info)
+{
+	if ((void *)info != dmar_pci_notify_info_buf)
+		kfree(info);
+}
+
+static bool dmar_match_pci_path(struct dmar_pci_notify_info *info, int bus,
+				struct acpi_dmar_pci_path *path, int count)
+{
+	int i;
+
+	if (info->bus != bus)
+		return false;
+	if (info->level != count)
+		return false;
+
+	for (i = 0; i < count; i++) {
+		if (path[i].device != info->path[i].device ||
+		    path[i].function != info->path[i].function)
+			return false;
+	}
+
+	return true;
+}
+
+/* Return: > 0 if match found, 0 if no match found, < 0 if error happens */
+int dmar_insert_dev_scope(struct dmar_pci_notify_info *info,
+			  void *start, void*end, u16 segment,
+			  struct pci_dev __rcu **devices, int devices_cnt)
+{
+	int i, level;
+	struct pci_dev *tmp, *dev = info->dev;
+	struct acpi_dmar_device_scope *scope;
+	struct acpi_dmar_pci_path *path;
+
+	if (segment != info->seg)
+		return 0;
+
+	for (; start < end; start += scope->length) {
+		scope = start;
+		if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_ENDPOINT &&
+		    scope->entry_type != ACPI_DMAR_SCOPE_TYPE_BRIDGE)
+			continue;
+
+		path = (struct acpi_dmar_pci_path *)(scope + 1);
+		level = (scope->length - sizeof(*scope)) / sizeof(*path);
+		if (!dmar_match_pci_path(info, scope->bus, path, level))
+			continue;
+
+		if ((scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT) ^
+		    (dev->hdr_type == PCI_HEADER_TYPE_NORMAL)) {
+			pr_warn("Device scope type does not match for %s\n",
+				pci_name(dev));
+			return -EINVAL;
+		}
+
+		for_each_dev_scope(devices, devices_cnt, i, tmp)
+			if (tmp == NULL) {
+				rcu_assign_pointer(devices[i],
+						   pci_dev_get(dev));
+				return 1;
+			}
+		BUG_ON(i >= devices_cnt);
+	}
+
+	return 0;
+}
+
+int dmar_remove_dev_scope(struct dmar_pci_notify_info *info, u16 segment,
+			  struct pci_dev __rcu **devices, int count)
+{
+	int index;
+	struct pci_dev *tmp;
+
+	if (info->seg != segment)
+		return 0;
+
+	for_each_active_dev_scope(devices, count, index, tmp)
+		if (tmp == info->dev) {
+			rcu_assign_pointer(devices[index], NULL);
+			synchronize_rcu();
+			pci_dev_put(tmp);
+			return 1;
+		}
+
+	return 0;
+}
+
+static int dmar_pci_bus_add_dev(struct dmar_pci_notify_info *info)
+{
+	int ret = 0;
+	struct dmar_drhd_unit *dmaru;
+	struct acpi_dmar_hardware_unit *drhd;
+
+	for_each_drhd_unit(dmaru) {
+		if (dmaru->include_all)
+			continue;
+
+		drhd = container_of(dmaru->hdr,
+				    struct acpi_dmar_hardware_unit, header);
+		ret = dmar_insert_dev_scope(info, (void *)(drhd + 1),
+				((void *)drhd) + drhd->header.length,
+				dmaru->segment,
+				dmaru->devices, dmaru->devices_cnt);
+		if (ret != 0)
+			break;
+	}
+	if (ret >= 0)
+		ret = dmar_iommu_notify_scope_dev(info);
+
+	return ret;
+}
+
+static void  dmar_pci_bus_del_dev(struct dmar_pci_notify_info *info)
+{
+	struct dmar_drhd_unit *dmaru;
+
+	for_each_drhd_unit(dmaru)
+		if (dmar_remove_dev_scope(info, dmaru->segment,
+			dmaru->devices, dmaru->devices_cnt))
+			break;
+	dmar_iommu_notify_scope_dev(info);
+}
+
+static int dmar_pci_bus_notifier(struct notifier_block *nb,
+				 unsigned long action, void *data)
+{
+	struct pci_dev *pdev = to_pci_dev(data);
+	struct dmar_pci_notify_info *info;
+
+	/* Only care about add/remove events for physical functions */
+	if (pdev->is_virtfn)
+		return NOTIFY_DONE;
+	if (action != BUS_NOTIFY_ADD_DEVICE && action != BUS_NOTIFY_DEL_DEVICE)
+		return NOTIFY_DONE;
+
+	info = dmar_alloc_pci_notify_info(pdev, action);
+	if (!info)
+		return NOTIFY_DONE;
+
+	down_write(&dmar_global_lock);
+	if (action == BUS_NOTIFY_ADD_DEVICE)
+		dmar_pci_bus_add_dev(info);
+	else if (action == BUS_NOTIFY_DEL_DEVICE)
+		dmar_pci_bus_del_dev(info);
+	up_write(&dmar_global_lock);
+
+	dmar_free_pci_notify_info(info);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block dmar_pci_bus_nb = {
+	.notifier_call = dmar_pci_bus_notifier,
+	.priority = INT_MIN,
+};
+
 /**
  * dmar_parse_one_drhd - parses exactly one DMA remapping hardware definition
  * structure which uniquely represent one DMA remapping hardware unit
@@ -482,6 +685,8 @@ int __init dmar_dev_scope_init(void)
 	if (ret)
 		goto fail;
 
+	bus_register_notifier(&pci_bus_type, &dmar_pci_bus_nb);
+
 	dmar_dev_scope_initialized = 1;
 	return 0;
 
@@ -1412,6 +1617,8 @@ static int __init dmar_free_unused_resources(void)
 	if (irq_remapping_enabled || intel_iommu_enabled)
 		return 0;
 
+	bus_unregister_notifier(&pci_bus_type, &dmar_pci_bus_nb);
+
 	down_write(&dmar_global_lock);
 	list_for_each_entry_safe(dmaru, dmaru_n, &dmar_drhd_units, list) {
 		list_del(&dmaru->list);
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index e1679a6fe468..d9c0dc5a5d35 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3625,6 +3625,60 @@ int __init dmar_parse_rmrr_atsr_dev(void)
 	return 0;
 }
 
+int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
+{
+	int ret = 0;
+	struct dmar_rmrr_unit *rmrru;
+	struct dmar_atsr_unit *atsru;
+	struct acpi_dmar_atsr *atsr;
+	struct acpi_dmar_reserved_memory *rmrr;
+
+	if (!intel_iommu_enabled && system_state != SYSTEM_BOOTING)
+		return 0;
+
+	list_for_each_entry(rmrru, &dmar_rmrr_units, list) {
+		rmrr = container_of(rmrru->hdr,
+				    struct acpi_dmar_reserved_memory, header);
+		if (info->event == BUS_NOTIFY_ADD_DEVICE) {
+			ret = dmar_insert_dev_scope(info, (void *)(rmrr + 1),
+				((void *)rmrr) + rmrr->header.length,
+				rmrr->segment, rmrru->devices,
+				rmrru->devices_cnt);
+			if (ret > 0)
+				break;
+			else if(ret < 0)
+				return ret;
+		} else if (info->event == BUS_NOTIFY_DEL_DEVICE) {
+			if (dmar_remove_dev_scope(info, rmrr->segment,
+				rmrru->devices, rmrru->devices_cnt))
+				break;
+		}
+	}
+
+	list_for_each_entry(atsru, &dmar_atsr_units, list) {
+		if (atsru->include_all)
+			continue;
+
+		atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header);
+		if (info->event == BUS_NOTIFY_ADD_DEVICE) {
+			ret = dmar_insert_dev_scope(info, (void *)(atsr + 1),
+					(void *)atsr + atsr->header.length,
+					atsr->segment, atsru->devices,
+					atsru->devices_cnt);
+			if (ret > 0)
+				break;
+			else if(ret < 0)
+				return ret;
+		} else if (info->event == BUS_NOTIFY_DEL_DEVICE) {
+			if (dmar_remove_dev_scope(info, atsr->segment,
+					atsru->devices, atsru->devices_cnt))
+				break;
+		}
+	}
+
+	return 0;
+}
+
 /*
  * Here we only respond to action of unbound device from driver.
  *
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index bedebab934b4..4e196430f1b2 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -50,6 +50,15 @@ struct dmar_drhd_unit {
 	struct intel_iommu *iommu;
 };
 
+struct dmar_pci_notify_info {
+	struct pci_dev			*dev;
+	unsigned long			event;
+	int				bus;
+	u16				seg;
+	u16				level;
+	struct acpi_dmar_pci_path	path[];
+}  __attribute__((packed));
+
 extern struct rw_semaphore dmar_global_lock;
 extern struct list_head dmar_drhd_units;
 
@@ -89,12 +98,18 @@ extern int dmar_parse_dev_scope(void *start, void *end, int *cnt,
 				struct pci_dev ***devices, u16 segment);
 extern void *dmar_alloc_dev_scope(void *start, void *end, int *cnt);
 extern void dmar_free_dev_scope(struct pci_dev __rcu ***devices, int *cnt);
-extern void dmar_free_dev_scope(struct pci_dev ***devices, int *cnt);
-
+extern int dmar_insert_dev_scope(struct dmar_pci_notify_info *info,
+				 void *start, void*end, u16 segment,
+				 struct pci_dev __rcu **devices,
+				 int devices_cnt);
+extern int dmar_remove_dev_scope(struct dmar_pci_notify_info *info,
+				 u16 segment, struct pci_dev __rcu **devices,
+				 int count);
 /* Intel IOMMU detection */
 extern int detect_intel_iommu(void);
 extern int enable_drhd_fault_handling(void);
 #else
+struct dmar_pci_notify_info;
 static inline int detect_intel_iommu(void)
 {
 	return -ENODEV;
@@ -161,6 +176,7 @@ extern int iommu_detected, no_iommu;
 extern int dmar_parse_rmrr_atsr_dev(void);
 extern int dmar_parse_one_rmrr(struct acpi_dmar_header *header);
 extern int dmar_parse_one_atsr(struct acpi_dmar_header *header);
+extern int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info);
 extern int intel_iommu_init(void);
 #else /* !CONFIG_INTEL_IOMMU: */
 static inline int intel_iommu_init(void) { return -ENODEV; }
@@ -176,6 +192,10 @@ static inline int dmar_parse_rmrr_atsr_dev(void)
 {
 	return 0;
 }
+static inline int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
+{
+	return 0;
+}
 #endif /* CONFIG_INTEL_IOMMU */
 
 #endif /* __DMAR_H__ */
-- 
cgit v1.2.3


From 2e45528930388658603ea24d49cf52867b928d3e Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Wed, 19 Feb 2014 14:07:36 +0800
Subject: iommu/vt-d: Unify the way to process DMAR device scope array

Now we have a PCI bus notification based mechanism to update DMAR
device scope array, we could extend the mechanism to support boot
time initialization too, which will help to unify and simplify
the implementation.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Signed-off-by: Joerg Roedel <joro@8bytes.org>
---
 drivers/iommu/dmar.c        | 163 ++++++++++++--------------------------------
 drivers/iommu/intel-iommu.c |  71 +++++--------------
 include/linux/dmar.h        |   5 --
 3 files changed, 61 insertions(+), 178 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index bf6bfd1f69aa..b19f9f4c3584 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -60,6 +60,7 @@ LIST_HEAD(dmar_drhd_units);
 
 struct acpi_table_header * __initdata dmar_tbl;
 static acpi_size dmar_tbl_size;
+static int dmar_dev_scope_status = 1;
 
 static int alloc_iommu(struct dmar_drhd_unit *drhd);
 static void free_iommu(struct intel_iommu *iommu);
@@ -76,58 +77,6 @@ static void __init dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
 		list_add_rcu(&drhd->list, &dmar_drhd_units);
 }
 
-static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope,
-					   struct pci_dev __rcu **dev, u16 segment)
-{
-	struct pci_bus *bus;
-	struct pci_dev *pdev = NULL;
-	struct acpi_dmar_pci_path *path;
-	int count;
-
-	bus = pci_find_bus(segment, scope->bus);
-	path = (struct acpi_dmar_pci_path *)(scope + 1);
-	count = (scope->length - sizeof(struct acpi_dmar_device_scope))
-		/ sizeof(struct acpi_dmar_pci_path);
-
-	while (count) {
-		if (pdev)
-			pci_dev_put(pdev);
-		/*
-		 * Some BIOSes list non-exist devices in DMAR table, just
-		 * ignore it
-		 */
-		if (!bus) {
-			pr_warn("Device scope bus [%d] not found\n", scope->bus);
-			break;
-		}
-		pdev = pci_get_slot(bus, PCI_DEVFN(path->device, path->function));
-		if (!pdev) {
-			/* warning will be printed below */
-			break;
-		}
-		path ++;
-		count --;
-		bus = pdev->subordinate;
-	}
-	if (!pdev) {
-		pr_warn("Device scope device [%04x:%02x:%02x.%02x] not found\n",
-			segment, scope->bus, path->device, path->function);
-		return 0;
-	}
-	if ((scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT && \
-			pdev->subordinate) || (scope->entry_type == \
-			ACPI_DMAR_SCOPE_TYPE_BRIDGE && !pdev->subordinate)) {
-		pci_dev_put(pdev);
-		pr_warn("Device scope type does not match for %s\n",
-			pci_name(pdev));
-		return -EINVAL;
-	}
-
-	rcu_assign_pointer(*dev, pdev);
-
-	return 0;
-}
-
 void *dmar_alloc_dev_scope(void *start, void *end, int *cnt)
 {
 	struct acpi_dmar_device_scope *scope;
@@ -150,35 +99,6 @@ void *dmar_alloc_dev_scope(void *start, void *end, int *cnt)
 	return kcalloc(*cnt, sizeof(struct pci_dev *), GFP_KERNEL);
 }
 
-int __init dmar_parse_dev_scope(void *start, void *end, int *cnt,
-				struct pci_dev __rcu ***devices, u16 segment)
-{
-	struct acpi_dmar_device_scope *scope;
-	int index, ret;
-
-	*devices = dmar_alloc_dev_scope(start, end, cnt);
-	if (*cnt == 0)
-		return 0;
-	else if (!*devices)
-		return -ENOMEM;
-
-	for (index = 0; start < end; start += scope->length) {
-		scope = start;
-		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT ||
-		    scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE) {
-			ret = dmar_parse_one_dev_scope(scope,
-				&(*devices)[index], segment);
-			if (ret) {
-				dmar_free_dev_scope(devices, cnt);
-				return ret;
-			}
-			index ++;
-		}
-	}
-
-	return 0;
-}
-
 void dmar_free_dev_scope(struct pci_dev __rcu ***devices, int *cnt)
 {
 	int i;
@@ -220,6 +140,8 @@ dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event)
 		if (!info) {
 			pr_warn("Out of memory when allocating notify_info "
 				"for %s.\n", pci_name(dev));
+			if (dmar_dev_scope_status == 0)
+				dmar_dev_scope_status = -ENOMEM;
 			return NULL;
 		}
 	}
@@ -349,6 +271,8 @@ static int dmar_pci_bus_add_dev(struct dmar_pci_notify_info *info)
 	}
 	if (ret >= 0)
 		ret = dmar_iommu_notify_scope_dev(info);
+	if (ret < 0 && dmar_dev_scope_status == 0)
+		dmar_dev_scope_status = ret;
 
 	return ret;
 }
@@ -418,9 +342,21 @@ dmar_parse_one_drhd(struct acpi_dmar_header *header)
 	dmaru->reg_base_addr = drhd->address;
 	dmaru->segment = drhd->segment;
 	dmaru->include_all = drhd->flags & 0x1; /* BIT0: INCLUDE_ALL */
+	if (!dmaru->include_all) {
+		dmaru->devices = dmar_alloc_dev_scope((void *)(drhd + 1),
+					((void *)drhd) + drhd->header.length,
+					&dmaru->devices_cnt);
+		if (dmaru->devices_cnt && dmaru->devices == NULL) {
+			kfree(dmaru);
+			return -ENOMEM;
+		}
+	}
 
 	ret = alloc_iommu(dmaru);
 	if (ret) {
+		if (!dmaru->include_all)
+			dmar_free_dev_scope(&dmaru->devices,
+					    &dmaru->devices_cnt);
 		kfree(dmaru);
 		return ret;
 	}
@@ -437,21 +373,6 @@ static void dmar_free_drhd(struct dmar_drhd_unit *dmaru)
 	kfree(dmaru);
 }
 
-static int __init dmar_parse_dev(struct dmar_drhd_unit *dmaru)
-{
-	struct acpi_dmar_hardware_unit *drhd;
-
-	drhd = (struct acpi_dmar_hardware_unit *) dmaru->hdr;
-
-	if (dmaru->include_all)
-		return 0;
-
-	return dmar_parse_dev_scope((void *)(drhd + 1),
-				    ((void *)drhd) + drhd->header.length,
-				    &dmaru->devices_cnt, &dmaru->devices,
-				    drhd->segment);
-}
-
 #ifdef CONFIG_ACPI_NUMA
 static int __init
 dmar_parse_one_rhsa(struct acpi_dmar_header *header)
@@ -665,34 +586,35 @@ out:
 
 int __init dmar_dev_scope_init(void)
 {
-	static int dmar_dev_scope_initialized;
-	struct dmar_drhd_unit *drhd;
-	int ret = -ENODEV;
+	struct pci_dev *dev = NULL;
+	struct dmar_pci_notify_info *info;
 
-	if (dmar_dev_scope_initialized)
-		return dmar_dev_scope_initialized;
+	if (dmar_dev_scope_status != 1)
+		return dmar_dev_scope_status;
 
-	if (list_empty(&dmar_drhd_units))
-		goto fail;
+	if (list_empty(&dmar_drhd_units)) {
+		dmar_dev_scope_status = -ENODEV;
+	} else {
+		dmar_dev_scope_status = 0;
+
+		for_each_pci_dev(dev) {
+			if (dev->is_virtfn)
+				continue;
+
+			info = dmar_alloc_pci_notify_info(dev,
+					BUS_NOTIFY_ADD_DEVICE);
+			if (!info) {
+				return dmar_dev_scope_status;
+			} else {
+				dmar_pci_bus_add_dev(info);
+				dmar_free_pci_notify_info(info);
+			}
+		}
 
-	for_each_drhd_unit(drhd) {
-		ret = dmar_parse_dev(drhd);
-		if (ret)
-			goto fail;
+		bus_register_notifier(&pci_bus_type, &dmar_pci_bus_nb);
 	}
 
-	ret = dmar_parse_rmrr_atsr_dev();
-	if (ret)
-		goto fail;
-
-	bus_register_notifier(&pci_bus_type, &dmar_pci_bus_nb);
-
-	dmar_dev_scope_initialized = 1;
-	return 0;
-
-fail:
-	dmar_dev_scope_initialized = ret;
-	return ret;
+	return dmar_dev_scope_status;
 }
 
 
@@ -1617,7 +1539,8 @@ static int __init dmar_free_unused_resources(void)
 	if (irq_remapping_enabled || intel_iommu_enabled)
 		return 0;
 
-	bus_unregister_notifier(&pci_bus_type, &dmar_pci_bus_nb);
+	if (dmar_dev_scope_status != 1 && !list_empty(&dmar_drhd_units))
+		bus_unregister_notifier(&pci_bus_type, &dmar_pci_bus_nb);
 
 	down_write(&dmar_global_lock);
 	list_for_each_entry_safe(dmaru, dmaru_n, &dmar_drhd_units, list) {
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index d9c0dc5a5d35..dd576c067d0d 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3473,11 +3473,6 @@ static void __init init_iommu_pm_ops(void)
 static inline void init_iommu_pm_ops(void) {}
 #endif	/* CONFIG_PM */
 
-static void __init dmar_register_rmrr_unit(struct dmar_rmrr_unit *rmrr)
-{
-	list_add(&rmrr->list, &dmar_rmrr_units);
-}
-
 
 int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header)
 {
@@ -3492,21 +3487,17 @@ int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header)
 	rmrr = (struct acpi_dmar_reserved_memory *)header;
 	rmrru->base_address = rmrr->base_address;
 	rmrru->end_address = rmrr->end_address;
+	rmrru->devices = dmar_alloc_dev_scope((void *)(rmrr + 1),
+				((void *)rmrr) + rmrr->header.length,
+				&rmrru->devices_cnt);
+	if (rmrru->devices_cnt && rmrru->devices == NULL) {
+		kfree(rmrru);
+		return -ENOMEM;
+	}
 
-	dmar_register_rmrr_unit(rmrru);
-	return 0;
-}
+	list_add(&rmrru->list, &dmar_rmrr_units);
 
-static int __init
-rmrr_parse_dev(struct dmar_rmrr_unit *rmrru)
-{
-	struct acpi_dmar_reserved_memory *rmrr;
-
-	rmrr = (struct acpi_dmar_reserved_memory *) rmrru->hdr;
-	return dmar_parse_dev_scope((void *)(rmrr + 1),
-				    ((void *)rmrr) + rmrr->header.length,
-				    &rmrru->devices_cnt, &rmrru->devices,
-				    rmrr->segment);
+	return 0;
 }
 
 int __init dmar_parse_one_atsr(struct acpi_dmar_header *hdr)
@@ -3521,26 +3512,21 @@ int __init dmar_parse_one_atsr(struct acpi_dmar_header *hdr)
 
 	atsru->hdr = hdr;
 	atsru->include_all = atsr->flags & 0x1;
+	if (!atsru->include_all) {
+		atsru->devices = dmar_alloc_dev_scope((void *)(atsr + 1),
+				(void *)atsr + atsr->header.length,
+				&atsru->devices_cnt);
+		if (atsru->devices_cnt && atsru->devices == NULL) {
+			kfree(atsru);
+			return -ENOMEM;
+		}
+	}
 
 	list_add_rcu(&atsru->list, &dmar_atsr_units);
 
 	return 0;
 }
 
-static int __init atsr_parse_dev(struct dmar_atsr_unit *atsru)
-{
-	struct acpi_dmar_atsr *atsr;
-
-	if (atsru->include_all)
-		return 0;
-
-	atsr = container_of(atsru->hdr, struct acpi_dmar_atsr, header);
-	return dmar_parse_dev_scope((void *)(atsr + 1),
-				    (void *)atsr + atsr->header.length,
-				    &atsru->devices_cnt, &atsru->devices,
-				    atsr->segment);
-}
-
 static void intel_iommu_free_atsr(struct dmar_atsr_unit *atsru)
 {
 	dmar_free_dev_scope(&atsru->devices, &atsru->devices_cnt);
@@ -3604,27 +3590,6 @@ out:
 	return ret;
 }
 
-int __init dmar_parse_rmrr_atsr_dev(void)
-{
-	struct dmar_rmrr_unit *rmrr;
-	struct dmar_atsr_unit *atsr;
-	int ret;
-
-	list_for_each_entry(rmrr, &dmar_rmrr_units, list) {
-		ret = rmrr_parse_dev(rmrr);
-		if (ret)
-			return ret;
-	}
-
-	list_for_each_entry_rcu(atsr, &dmar_atsr_units, list) {
-		ret = atsr_parse_dev(atsr);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
 int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
 {
 	int ret = 0;
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 4e196430f1b2..0a92e4d978bc 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -173,7 +173,6 @@ extern int arch_setup_dmar_msi(unsigned int irq);
 
 #ifdef CONFIG_INTEL_IOMMU
 extern int iommu_detected, no_iommu;
-extern int dmar_parse_rmrr_atsr_dev(void);
 extern int dmar_parse_one_rmrr(struct acpi_dmar_header *header);
 extern int dmar_parse_one_atsr(struct acpi_dmar_header *header);
 extern int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info);
@@ -188,10 +187,6 @@ static inline int dmar_parse_one_atsr(struct acpi_dmar_header *header)
 {
 	return 0;
 }
-static inline int dmar_parse_rmrr_atsr_dev(void)
-{
-	return 0;
-}
 static inline int dmar_iommu_notify_scope_dev(struct dmar_pci_notify_info *info)
 {
 	return 0;
-- 
cgit v1.2.3


From 75f05569d0e51f6332a291c82abbeb7c8262e32d Mon Sep 17 00:00:00 2001
From: Jiang Liu <jiang.liu@linux.intel.com>
Date: Wed, 19 Feb 2014 14:07:37 +0800
Subject: iommu/vt-d: Update IOMMU state when memory hotplug happens

If static identity domain is created, IOMMU driver needs to update
si_domain page table when memory hotplug event happens. Otherwise
PCI device DMA operations can't access the hot-added memory regions.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Signed-off-by: Joerg Roedel <joro@8bytes.org>
---
 drivers/iommu/intel-iommu.c | 71 ++++++++++++++++++++++++++++++++++++++++++++-
 drivers/iommu/iova.c        | 64 ++++++++++++++++++++++++++++++++++++----
 include/linux/iova.h        |  2 ++
 3 files changed, 130 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index dd576c067d0d..484d669d2720 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -33,6 +33,7 @@
 #include <linux/dmar.h>
 #include <linux/dma-mapping.h>
 #include <linux/mempool.h>
+#include <linux/memory.h>
 #include <linux/timer.h>
 #include <linux/iova.h>
 #include <linux/iommu.h>
@@ -3683,6 +3684,73 @@ static struct notifier_block device_nb = {
 	.notifier_call = device_notifier,
 };
 
+static int intel_iommu_memory_notifier(struct notifier_block *nb,
+				       unsigned long val, void *v)
+{
+	struct memory_notify *mhp = v;
+	unsigned long long start, end;
+	unsigned long start_vpfn, last_vpfn;
+
+	switch (val) {
+	case MEM_GOING_ONLINE:
+		start = mhp->start_pfn << PAGE_SHIFT;
+		end = ((mhp->start_pfn + mhp->nr_pages) << PAGE_SHIFT) - 1;
+		if (iommu_domain_identity_map(si_domain, start, end)) {
+			pr_warn("dmar: failed to build identity map for [%llx-%llx]\n",
+				start, end);
+			return NOTIFY_BAD;
+		}
+		break;
+
+	case MEM_OFFLINE:
+	case MEM_CANCEL_ONLINE:
+		start_vpfn = mm_to_dma_pfn(mhp->start_pfn);
+		last_vpfn = mm_to_dma_pfn(mhp->start_pfn + mhp->nr_pages - 1);
+		while (start_vpfn <= last_vpfn) {
+			struct iova *iova;
+			struct dmar_drhd_unit *drhd;
+			struct intel_iommu *iommu;
+
+			iova = find_iova(&si_domain->iovad, start_vpfn);
+			if (iova == NULL) {
+				pr_debug("dmar: failed get IOVA for PFN %lx\n",
+					 start_vpfn);
+				break;
+			}
+
+			iova = split_and_remove_iova(&si_domain->iovad, iova,
+						     start_vpfn, last_vpfn);
+			if (iova == NULL) {
+				pr_warn("dmar: failed to split IOVA PFN [%lx-%lx]\n",
+					start_vpfn, last_vpfn);
+				return NOTIFY_BAD;
+			}
+
+			rcu_read_lock();
+			for_each_active_iommu(iommu, drhd)
+				iommu_flush_iotlb_psi(iommu, si_domain->id,
+					iova->pfn_lo,
+					iova->pfn_hi - iova->pfn_lo + 1, 0);
+			rcu_read_unlock();
+			dma_pte_clear_range(si_domain, iova->pfn_lo,
+					    iova->pfn_hi);
+			dma_pte_free_pagetable(si_domain, iova->pfn_lo,
+					       iova->pfn_hi);
+
+			start_vpfn = iova->pfn_hi + 1;
+			free_iova_mem(iova);
+		}
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block intel_iommu_memory_nb = {
+	.notifier_call = intel_iommu_memory_notifier,
+	.priority = 0
+};
+
 int __init intel_iommu_init(void)
 {
 	int ret = -ENODEV;
@@ -3755,8 +3823,9 @@ int __init intel_iommu_init(void)
 	init_iommu_pm_ops();
 
 	bus_set_iommu(&pci_bus_type, &intel_iommu_ops);
-
 	bus_register_notifier(&pci_bus_type, &device_nb);
+	if (si_domain && !hw_pass_through)
+		register_memory_notifier(&intel_iommu_memory_nb);
 
 	intel_iommu_enabled = 1;
 
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 67da6cff74e8..f6b17e6af2fb 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -342,19 +342,30 @@ __is_range_overlap(struct rb_node *node,
 	return 0;
 }
 
+static inline struct iova *
+alloc_and_init_iova(unsigned long pfn_lo, unsigned long pfn_hi)
+{
+	struct iova *iova;
+
+	iova = alloc_iova_mem();
+	if (iova) {
+		iova->pfn_lo = pfn_lo;
+		iova->pfn_hi = pfn_hi;
+	}
+
+	return iova;
+}
+
 static struct iova *
 __insert_new_range(struct iova_domain *iovad,
 	unsigned long pfn_lo, unsigned long pfn_hi)
 {
 	struct iova *iova;
 
-	iova = alloc_iova_mem();
-	if (!iova)
-		return iova;
+	iova = alloc_and_init_iova(pfn_lo, pfn_hi);
+	if (iova)
+		iova_insert_rbtree(&iovad->rbroot, iova);
 
-	iova->pfn_hi = pfn_hi;
-	iova->pfn_lo = pfn_lo;
-	iova_insert_rbtree(&iovad->rbroot, iova);
 	return iova;
 }
 
@@ -433,3 +444,44 @@ copy_reserved_iova(struct iova_domain *from, struct iova_domain *to)
 	}
 	spin_unlock_irqrestore(&from->iova_rbtree_lock, flags);
 }
+
+struct iova *
+split_and_remove_iova(struct iova_domain *iovad, struct iova *iova,
+		      unsigned long pfn_lo, unsigned long pfn_hi)
+{
+	unsigned long flags;
+	struct iova *prev = NULL, *next = NULL;
+
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	if (iova->pfn_lo < pfn_lo) {
+		prev = alloc_and_init_iova(iova->pfn_lo, pfn_lo - 1);
+		if (prev == NULL)
+			goto error;
+	}
+	if (iova->pfn_hi > pfn_hi) {
+		next = alloc_and_init_iova(pfn_hi + 1, iova->pfn_hi);
+		if (next == NULL)
+			goto error;
+	}
+
+	__cached_rbnode_delete_update(iovad, iova);
+	rb_erase(&iova->node, &iovad->rbroot);
+
+	if (prev) {
+		iova_insert_rbtree(&iovad->rbroot, prev);
+		iova->pfn_lo = pfn_lo;
+	}
+	if (next) {
+		iova_insert_rbtree(&iovad->rbroot, next);
+		iova->pfn_hi = pfn_hi;
+	}
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+
+	return iova;
+
+error:
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
+	if (prev)
+		free_iova_mem(prev);
+	return NULL;
+}
diff --git a/include/linux/iova.h b/include/linux/iova.h
index 76a0759e88ec..3277f4711349 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -47,5 +47,7 @@ void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to);
 void init_iova_domain(struct iova_domain *iovad, unsigned long pfn_32bit);
 struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn);
 void put_iova_domain(struct iova_domain *iovad);
+struct iova *split_and_remove_iova(struct iova_domain *iovad,
+	struct iova *iova, unsigned long pfn_lo, unsigned long pfn_hi);
 
 #endif
-- 
cgit v1.2.3


From f3baa393ffc9a7aefc0bf767729382085e81f606 Mon Sep 17 00:00:00 2001
From: Simon Wunderlich <sw@simonwunderlich.de>
Date: Mon, 3 Mar 2014 17:23:11 +0100
Subject: UAPI: add MPLS label stack definition

Labels for the Multiprotocol Label Switching are defined in RFC 3032
which was superseded by RFC 5462. Add the definition to UAPI and a stub
header for include/linux.

Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
Signed-off-by: Mathias Kretschmer <mathias.kretschmer@fokus.fraunhofer.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mpls.h      |  6 ++++++
 include/uapi/linux/mpls.h | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 40 insertions(+)
 create mode 100644 include/linux/mpls.h
 create mode 100644 include/uapi/linux/mpls.h

(limited to 'include/linux')

diff --git a/include/linux/mpls.h b/include/linux/mpls.h
new file mode 100644
index 000000000000..9999145bc190
--- /dev/null
+++ b/include/linux/mpls.h
@@ -0,0 +1,6 @@
+#ifndef _LINUX_MPLS_H
+#define _LINUX_MPLS_H
+
+#include <uapi/linux/mpls.h>
+
+#endif  /* _LINUX_MPLS_H */
diff --git a/include/uapi/linux/mpls.h b/include/uapi/linux/mpls.h
new file mode 100644
index 000000000000..bc9abfe88c9a
--- /dev/null
+++ b/include/uapi/linux/mpls.h
@@ -0,0 +1,34 @@
+#ifndef _UAPI_MPLS_H
+#define _UAPI_MPLS_H
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+/* Reference: RFC 5462, RFC 3032
+ *
+ *  0                   1                   2                   3
+ *  0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                Label                  | TC  |S|       TTL     |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ *	Label:  Label Value, 20 bits
+ *	TC:     Traffic Class field, 3 bits
+ *	S:      Bottom of Stack, 1 bit
+ *	TTL:    Time to Live, 8 bits
+ */
+
+struct mpls_label {
+	__be32 entry;
+};
+
+#define MPLS_LS_LABEL_MASK      0xFFFFF000
+#define MPLS_LS_LABEL_SHIFT     12
+#define MPLS_LS_TC_MASK         0x00000E00
+#define MPLS_LS_TC_SHIFT        9
+#define MPLS_LS_S_MASK          0x00000100
+#define MPLS_LS_S_SHIFT         8
+#define MPLS_LS_TTL_MASK        0x000000FF
+#define MPLS_LS_TTL_SHIFT       0
+
+#endif /* _UAPI_MPLS_H */
-- 
cgit v1.2.3


From 42c1add97073b5a701b8aee0fdb69ef0345d4c50 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Fri, 28 Feb 2014 21:32:44 +0000
Subject: mmc: sdhci-spear: remove support for power gpio

None of this code is currently used: there are no definitions of
struct sdhci_plat_data in arch/arm, neither are there any DT properties
which use card_power_gpio/power_active_high/power_always_enb.  In any
case, slot power control should be rigged up via vmmc and the regulator
subsystem in the DT case.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: Chris Ball <chris@printf.net>
---
 drivers/mmc/host/sdhci-spear.c  | 32 --------------------------------
 include/linux/mmc/sdhci-spear.h |  8 --------
 2 files changed, 40 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mmc/host/sdhci-spear.c b/drivers/mmc/host/sdhci-spear.c
index fc6eac5b1064..676df4623057 100644
--- a/drivers/mmc/host/sdhci-spear.c
+++ b/drivers/mmc/host/sdhci-spear.c
@@ -56,14 +56,6 @@ static irqreturn_t sdhci_gpio_irq(int irq, void *dev_id)
 	gpio_irq_type = val ? IRQF_TRIGGER_LOW : IRQF_TRIGGER_HIGH;
 	irq_set_irq_type(irq, gpio_irq_type);
 
-	if (sdhci->data->card_power_gpio >= 0) {
-		if (!sdhci->data->power_always_enb) {
-			/* if card inserted, give power, otherwise remove it */
-			val = sdhci->data->power_active_high ? !val : val ;
-			gpio_set_value(sdhci->data->card_power_gpio, val);
-		}
-	}
-
 	/* inform sdhci driver about card insertion/removal */
 	tasklet_schedule(&host->card_tasklet);
 
@@ -179,30 +171,6 @@ static int sdhci_probe(struct platform_device *pdev)
 	if (!sdhci->data)
 		return 0;
 
-	if (sdhci->data->card_power_gpio >= 0) {
-		int val = 0;
-
-		ret = devm_gpio_request(&pdev->dev,
-				sdhci->data->card_power_gpio, "sdhci");
-		if (ret < 0) {
-			dev_dbg(&pdev->dev, "gpio request fail: %d\n",
-					sdhci->data->card_power_gpio);
-			goto set_drvdata;
-		}
-
-		if (sdhci->data->power_always_enb)
-			val = sdhci->data->power_active_high;
-		else
-			val = !sdhci->data->power_active_high;
-
-		ret = gpio_direction_output(sdhci->data->card_power_gpio, val);
-		if (ret) {
-			dev_dbg(&pdev->dev, "gpio set direction fail: %d\n",
-					sdhci->data->card_power_gpio);
-			goto set_drvdata;
-		}
-	}
-
 	if (sdhci->data->card_int_gpio >= 0) {
 		ret = devm_gpio_request(&pdev->dev, sdhci->data->card_int_gpio,
 				"sdhci");
diff --git a/include/linux/mmc/sdhci-spear.h b/include/linux/mmc/sdhci-spear.h
index e78c0e236e9d..8cc095a76cf8 100644
--- a/include/linux/mmc/sdhci-spear.h
+++ b/include/linux/mmc/sdhci-spear.h
@@ -18,17 +18,9 @@
 /*
  * struct sdhci_plat_data: spear sdhci platform data structure
  *
- * @card_power_gpio: gpio pin for enabling/disabling power to sdhci socket
- * @power_active_high: if set, enable power to sdhci socket by setting
- *			card_power_gpio
- * @power_always_enb: If set, then enable power on probe, otherwise enable only
- *			on card insertion and disable on card removal.
  * card_int_gpio: gpio pin used for card detection
  */
 struct sdhci_plat_data {
-	int card_power_gpio;
-	int power_active_high;
-	int power_always_enb;
 	int card_int_gpio;
 };
 
-- 
cgit v1.2.3


From 8f5d35441ff26b31e3812556ce468c76f1eb216b Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 9 Oct 2013 17:19:24 +0200
Subject: usb-core: Move USB_MAXENDPOINTS definitions to usb.h

So that it can be used in other places too.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
---
 drivers/usb/core/config.c | 1 -
 include/linux/usb.h       | 2 ++
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 8d72f0c65937..14ba398d6def 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -10,7 +10,6 @@
 
 
 #define USB_MAXALTSETTING		128	/* Hard limit */
-#define USB_MAXENDPOINTS		30	/* Hard limit */
 
 #define USB_MAXCONFIG			8	/* Arbitrary limit */
 
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 7f6eb859873e..9b73dd782c09 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -202,6 +202,8 @@ static inline void usb_set_intfdata(struct usb_interface *intf, void *data)
 struct usb_interface *usb_get_intf(struct usb_interface *intf);
 void usb_put_intf(struct usb_interface *intf);
 
+/* Hard limit */
+#define USB_MAXENDPOINTS	30
 /* this maximum is arbitrary */
 #define USB_MAXINTERFACES	32
 #define USB_MAXIADS		(USB_MAXINTERFACES/2)
-- 
cgit v1.2.3


From 8d4f70b2fa52ca80f74faebc2471f74ee374cf61 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 9 Oct 2013 17:19:25 +0200
Subject: usb-core: Track if an endpoint has streams

This is a preparation patch for adding support for bulk streams to usbfs.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
---
 drivers/usb/core/hcd.c | 34 ++++++++++++++++++++++++++--------
 include/linux/usb.h    |  2 ++
 2 files changed, 28 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 9b445f43f825..9c4e2922b04d 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -2049,7 +2049,7 @@ int usb_alloc_streams(struct usb_interface *interface,
 {
 	struct usb_hcd *hcd;
 	struct usb_device *dev;
-	int i;
+	int i, ret;
 
 	dev = interface_to_usbdev(interface);
 	hcd = bus_to_hcd(dev->bus);
@@ -2058,13 +2058,24 @@ int usb_alloc_streams(struct usb_interface *interface,
 	if (dev->speed != USB_SPEED_SUPER)
 		return -EINVAL;
 
-	/* Streams only apply to bulk endpoints. */
-	for (i = 0; i < num_eps; i++)
+	for (i = 0; i < num_eps; i++) {
+		/* Streams only apply to bulk endpoints. */
 		if (!usb_endpoint_xfer_bulk(&eps[i]->desc))
 			return -EINVAL;
+		/* Re-alloc is not allowed */
+		if (eps[i]->streams)
+			return -EINVAL;
+	}
 
-	return hcd->driver->alloc_streams(hcd, dev, eps, num_eps,
+	ret = hcd->driver->alloc_streams(hcd, dev, eps, num_eps,
 			num_streams, mem_flags);
+	if (ret < 0)
+		return ret;
+
+	for (i = 0; i < num_eps; i++)
+		eps[i]->streams = ret;
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(usb_alloc_streams);
 
@@ -2086,19 +2097,26 @@ int usb_free_streams(struct usb_interface *interface,
 {
 	struct usb_hcd *hcd;
 	struct usb_device *dev;
-	int i;
+	int i, ret;
 
 	dev = interface_to_usbdev(interface);
 	hcd = bus_to_hcd(dev->bus);
 	if (dev->speed != USB_SPEED_SUPER)
 		return -EINVAL;
 
-	/* Streams only apply to bulk endpoints. */
+	/* Double-free is not allowed */
 	for (i = 0; i < num_eps; i++)
-		if (!eps[i] || !usb_endpoint_xfer_bulk(&eps[i]->desc))
+		if (!eps[i] || !eps[i]->streams)
 			return -EINVAL;
 
-	return hcd->driver->free_streams(hcd, dev, eps, num_eps, mem_flags);
+	ret = hcd->driver->free_streams(hcd, dev, eps, num_eps, mem_flags);
+	if (ret < 0)
+		return ret;
+
+	for (i = 0; i < num_eps; i++)
+		eps[i]->streams = 0;
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(usb_free_streams);
 
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 9b73dd782c09..f1015cee5944 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -57,6 +57,7 @@ struct ep_device;
  * @extra: descriptors following this endpoint in the configuration
  * @extralen: how many bytes of "extra" are valid
  * @enabled: URBs may be submitted to this endpoint
+ * @streams: number of USB-3 streams allocated on the endpoint
  *
  * USB requests are always queued to a given endpoint, identified by a
  * descriptor within an active interface in a given USB configuration.
@@ -71,6 +72,7 @@ struct usb_host_endpoint {
 	unsigned char *extra;   /* Extra descriptors */
 	int extralen;
 	int enabled;
+	int streams;
 };
 
 /* host-side wrapper for one interface setting's parsed descriptors */
-- 
cgit v1.2.3


From e52e031498cb51aff4f80a19a56700a127cf2a9a Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 23 Oct 2013 14:27:09 +0100
Subject: uas: s/response_ui/response_iu/

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
---
 drivers/usb/storage/uas.c | 2 +-
 include/linux/usb/uas.h   | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 0ee5a05c0a7b..33f9dcd68e24 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -46,7 +46,7 @@ struct uas_dev_info {
 	struct usb_anchor sense_urbs;
 	struct usb_anchor data_urbs;
 	int qdepth, resetting;
-	struct response_ui response;
+	struct response_iu response;
 	unsigned cmd_pipe, status_pipe, data_in_pipe, data_out_pipe;
 	unsigned use_streams:1;
 	unsigned uas_sense_old:1;
diff --git a/include/linux/usb/uas.h b/include/linux/usb/uas.h
index 5499ab5c94bd..14041780fb6c 100644
--- a/include/linux/usb/uas.h
+++ b/include/linux/usb/uas.h
@@ -79,7 +79,7 @@ struct sense_iu {
 	__u8 sense[SCSI_SENSE_BUFFERSIZE];
 };
 
-struct response_ui {
+struct response_iu {
 	__u8 iu_id;
 	__u8 rsvd1;
 	__be16 tag;
-- 
cgit v1.2.3


From 00d202cc12127fe9a9fa477a78cb37e32d7f4360 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 31 Oct 2013 09:59:12 +0100
Subject: uas: Fix response iu struct definition
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The response iu struct before this patch has a size of 7 bytes (discounting
padding), which is weird since all other iu-s are explictly padded to
a multiple of 4 bytes.

More over submitting a 7 byte bulk transfer to the status endpoint when
expecting a response iu results in an USB babble error, as the device
actually sends 8 bytes.

Up on closer reading of the UAS spec:
http://www.t10.org/cgi-bin/ac.pl?t=f&f=uas2r00.pdf

The reason for this becomes clear, the 2 entries in "Table 17 — RESPONSE IU"
are numbered 4 and 6, looking at other iu definitions in the spec, esp.
multi-byte fields, this indicates that the ADDITIONAL RESPONSE INFORMATION
field is not a 2 byte field as one might assume at a first look, but is
a multi-byte field containing 3 bytes.

This also aligns with the SCSI Architecture Model 4 spec, which UAS is based
on which states in paragraph "7.1 Task management function procedure calls"
that the "Additional Response Information" output argument for a Task
management function procedure call is 3 bytes.

Last but not least I've verified this by sending a logical unit reset task
management call with an invalid lun to an actual uasp device, and received
back a response-iu with byte 6 being 0, and byte 7 being 9, which is the
responce code for an invalid iu, which confirms that the response code is
being reported in byte 7 of the response iu rather then in byte 6.

Things were working before despite this error in the response iu struct
definition because the additional response info field is normally filled
with zeros, and 0 is the response code value for success.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
---
 include/linux/usb/uas.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/usb/uas.h b/include/linux/usb/uas.h
index 14041780fb6c..772b66bcdd7d 100644
--- a/include/linux/usb/uas.h
+++ b/include/linux/usb/uas.h
@@ -83,7 +83,7 @@ struct response_iu {
 	__u8 iu_id;
 	__u8 rsvd1;
 	__be16 tag;
-	__be16 add_response_info;
+	__u8 add_response_info[3];
 	__u8 response_code;
 };
 
-- 
cgit v1.2.3


From d24354bbf78f9194ec21087130a69b84864e50df Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Mon, 21 Oct 2013 11:15:11 +0100
Subject: uas: Pack iu struct definitions

The iu struct definitions are usb packet definitions, so no alignment should
happen. Notice that assuming 32 bit alignment this does not make any
difference at all.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
---
 include/linux/usb/uas.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/usb/uas.h b/include/linux/usb/uas.h
index 772b66bcdd7d..3fc8e8b9f043 100644
--- a/include/linux/usb/uas.h
+++ b/include/linux/usb/uas.h
@@ -9,7 +9,7 @@ struct iu {
 	__u8 iu_id;
 	__u8 rsvd1;
 	__be16 tag;
-};
+} __attribute__((__packed__));
 
 enum {
 	IU_ID_COMMAND		= 0x01,
@@ -52,7 +52,7 @@ struct command_iu {
 	__u8 rsvd7;
 	struct scsi_lun lun;
 	__u8 cdb[16];	/* XXX: Overflow-checking tools may misunderstand */
-};
+} __attribute__((__packed__));
 
 struct task_mgmt_iu {
 	__u8 iu_id;
@@ -62,7 +62,7 @@ struct task_mgmt_iu {
 	__u8 rsvd2;
 	__be16 task_tag;
 	struct scsi_lun lun;
-};
+} __attribute__((__packed__));
 
 /*
  * Also used for the Read Ready and Write Ready IUs since they have the
@@ -77,7 +77,7 @@ struct sense_iu {
 	__u8 rsvd7[7];
 	__be16 len;
 	__u8 sense[SCSI_SENSE_BUFFERSIZE];
-};
+} __attribute__((__packed__));
 
 struct response_iu {
 	__u8 iu_id;
@@ -85,7 +85,7 @@ struct response_iu {
 	__be16 tag;
 	__u8 add_response_info[3];
 	__u8 response_code;
-};
+} __attribute__((__packed__));
 
 struct usb_pipe_usage_descriptor {
 	__u8  bLength;
-- 
cgit v1.2.3


From 79b4c06112f12c31d03cf22b1ed5ce09423fd887 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Fri, 25 Oct 2013 17:04:33 +0100
Subject: uas: Add the posibilty to blacklist uas devices from using the uas
 driver

Once we start supporting uas hardware, and as more and more uas devices
become available, we will likely start seeing broken devices. This patch
prepares for the inevitable need for blacklisting those devices from
using the uas driver (they will use usb-storage instead).

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
---
 drivers/usb/storage/uas-detect.h  | 11 +++++++++
 drivers/usb/storage/uas.c         | 17 ++++++++++---
 drivers/usb/storage/unusual_uas.h | 52 +++++++++++++++++++++++++++++++++++++++
 include/linux/usb_usual.h         |  6 +++--
 4 files changed, 80 insertions(+), 6 deletions(-)
 create mode 100644 drivers/usb/storage/unusual_uas.h

(limited to 'include/linux')

diff --git a/drivers/usb/storage/uas-detect.h b/drivers/usb/storage/uas-detect.h
index 28101c7e6a9f..02bf5ec957f5 100644
--- a/drivers/usb/storage/uas-detect.h
+++ b/drivers/usb/storage/uas-detect.h
@@ -38,3 +38,14 @@ static int uas_find_uas_alt_setting(struct usb_interface *intf)
 
 	return -ENODEV;
 }
+
+static int uas_use_uas_driver(struct usb_interface *intf,
+			      const struct usb_device_id *id)
+{
+	unsigned long flags = id->driver_info;
+
+	if (flags & US_FL_IGNORE_UAS)
+		return 0;
+
+	return uas_find_uas_alt_setting(intf) >= 0;
+}
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 6ea892f32f74..e817e72d8673 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -13,6 +13,7 @@
 #include <linux/types.h>
 #include <linux/module.h>
 #include <linux/usb.h>
+#include <linux/usb_usual.h>
 #include <linux/usb/hcd.h>
 #include <linux/usb/storage.h>
 #include <linux/usb/uas.h>
@@ -866,7 +867,14 @@ static struct scsi_host_template uas_host_template = {
 	.ordered_tag = 1,
 };
 
+#define UNUSUAL_DEV(id_vendor, id_product, bcdDeviceMin, bcdDeviceMax, \
+		    vendorName, productName, useProtocol, useTransport, \
+		    initFunction, flags) \
+{ USB_DEVICE_VER(id_vendor, id_product, bcdDeviceMin, bcdDeviceMax), \
+	.driver_info = (flags) }
+
 static struct usb_device_id uas_usb_ids[] = {
+#	include "unusual_uas.h"
 	{ USB_INTERFACE_INFO(USB_CLASS_MASS_STORAGE, USB_SC_SCSI, USB_PR_BULK) },
 	{ USB_INTERFACE_INFO(USB_CLASS_MASS_STORAGE, USB_SC_SCSI, USB_PR_UAS) },
 	/* 0xaa is a prototype device I happen to have access to */
@@ -875,6 +883,8 @@ static struct usb_device_id uas_usb_ids[] = {
 };
 MODULE_DEVICE_TABLE(usb, uas_usb_ids);
 
+#undef UNUSUAL_DEV
+
 static int uas_switch_interface(struct usb_device *udev,
 				struct usb_interface *intf)
 {
@@ -973,6 +983,9 @@ static int uas_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	struct uas_dev_info *devinfo;
 	struct usb_device *udev = interface_to_usbdev(intf);
 
+	if (!uas_use_uas_driver(intf, id))
+		return -ENODEV;
+
 	if (uas_switch_interface(udev, intf))
 		return -ENODEV;
 
@@ -1083,10 +1096,6 @@ static void uas_disconnect(struct usb_interface *intf)
 	kfree(devinfo);
 }
 
-/*
- * XXX: Should this plug into libusual so we can auto-upgrade devices from
- * Bulk-Only to UAS?
- */
 static struct usb_driver uas_driver = {
 	.name = "uas",
 	.probe = uas_probe,
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
new file mode 100644
index 000000000000..7244444df8ee
--- /dev/null
+++ b/drivers/usb/storage/unusual_uas.h
@@ -0,0 +1,52 @@
+/* Driver for USB Attached SCSI devices - Unusual Devices File
+ *
+ *   (c) 2013 Hans de Goede <hdegoede@redhat.com>
+ *
+ * Based on the same file for the usb-storage driver, which is:
+ *   (c) 2000-2002 Matthew Dharm (mdharm-usb@one-eyed-alien.net)
+ *   (c) 2000 Adam J. Richter (adam@yggdrasil.com), Yggdrasil Computing, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2, or (at your option) any
+ * later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+/*
+ * IMPORTANT NOTE: This file must be included in another file which defines
+ * a UNUSUAL_DEV macro before this file is included.
+ */
+
+/*
+ * If you edit this file, please try to keep it sorted first by VendorID,
+ * then by ProductID.
+ *
+ * If you want to add an entry for this file, be sure to include the
+ * following information:
+ *	- a patch that adds the entry for your device, including your
+ *	  email address right above the entry (plus maybe a brief
+ *	  explanation of the reason for the entry),
+ *	- lsusb -v output for the device
+ * Send your submission to Hans de Goede <hdegoede@redhat.com>
+ * and don't forget to CC: the USB development list <linux-usb@vger.kernel.org>
+ */
+
+/*
+ * This is an example entry for the US_FL_IGNORE_UAS flag. Once we have an
+ * actual entry using US_FL_IGNORE_UAS this entry should be removed.
+ *
+ * UNUSUAL_DEV(  0xabcd, 0x1234, 0x0100, 0x0100,
+ *		"Example",
+ *		"Storage with broken UAS",
+ *		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+ *		US_FL_IGNORE_UAS),
+ */
diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h
index 630356866030..1a64b26046ed 100644
--- a/include/linux/usb_usual.h
+++ b/include/linux/usb_usual.h
@@ -67,8 +67,10 @@
 		/* Initial READ(10) (and others) must be retried */	\
 	US_FLAG(WRITE_CACHE,	0x00200000)			\
 		/* Write Cache status is not available */	\
-	US_FLAG(NEEDS_CAP16,	0x00400000)
-		/* cannot handle READ_CAPACITY_10 */
+	US_FLAG(NEEDS_CAP16,	0x00400000)			\
+		/* cannot handle READ_CAPACITY_10 */		\
+	US_FLAG(IGNORE_UAS,	0x00800000)			\
+		/* Device advertises UAS but it is broken */
 
 #define US_FLAG(name, value)	US_FL_##name = value ,
 enum { US_DO_ALL_FLAGS };
-- 
cgit v1.2.3


From 14aec589327a6fc4035f5327d90ac5548f501c4c Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.de>
Date: Tue, 11 Feb 2014 20:36:04 +0100
Subject: storage: accept some UAS devices if streams are unavailable

On some older XHCIs streams are not supported and the UAS driver
will fail at probe time. For those devices storage should try
to bind to UAS devices.
This patch adds a flag for stream support to HCDs and evaluates
it.

[Note: Sarah fixed a bug where the USB 2.0 root hub, not USB 3.0 root
hub would get marked as being able to support streams.]

Signed-off-by: Oliver Neukum <oliver@neukum.org>
Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Acked-by: Hans de Goede <hdegoede@redhat.com>
---
 drivers/usb/host/xhci-pci.c      | 3 +++
 drivers/usb/host/xhci-plat.c     | 3 +++
 drivers/usb/storage/uas-detect.h | 4 ++++
 include/linux/usb/hcd.h          | 1 +
 4 files changed, 11 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 6c03584ac15f..cbf0c5cffc92 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -222,6 +222,9 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		goto put_usb3_hcd;
 	/* Roothub already marked as USB 3.0 speed */
 
+	if (HCC_MAX_PSA(xhci->hcc_params) >= 4)
+		xhci->shared_hcd->can_do_streams = 1;
+
 	return 0;
 
 put_usb3_hcd:
diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c
index 8affef910782..151901ce1ba9 100644
--- a/drivers/usb/host/xhci-plat.c
+++ b/drivers/usb/host/xhci-plat.c
@@ -158,6 +158,9 @@ static int xhci_plat_probe(struct platform_device *pdev)
 	 */
 	*((struct xhci_hcd **) xhci->shared_hcd->hcd_priv) = xhci;
 
+	if (HCC_MAX_PSA(xhci->hcc_params) >= 4)
+		xhci->shared_hcd->can_do_streams = 1;
+
 	ret = usb_add_hcd(xhci->shared_hcd, irq, IRQF_SHARED);
 	if (ret)
 		goto put_usb3_hcd;
diff --git a/drivers/usb/storage/uas-detect.h b/drivers/usb/storage/uas-detect.h
index b8a02e12a8a2..bb05b984d5f6 100644
--- a/drivers/usb/storage/uas-detect.h
+++ b/drivers/usb/storage/uas-detect.h
@@ -72,6 +72,7 @@ static int uas_use_uas_driver(struct usb_interface *intf,
 {
 	struct usb_host_endpoint *eps[4] = { };
 	struct usb_device *udev = interface_to_usbdev(intf);
+	struct usb_hcd *hcd = bus_to_hcd(udev->bus);
 	unsigned long flags = id->driver_info;
 	int r, alt;
 
@@ -80,6 +81,9 @@ static int uas_use_uas_driver(struct usb_interface *intf,
 	if (flags & US_FL_IGNORE_UAS)
 		return 0;
 
+	if (udev->speed >= USB_SPEED_SUPER && !hcd->can_do_streams)
+		return 0;
+
 	alt = uas_find_uas_alt_setting(intf);
 	if (alt < 0)
 		return 0;
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index efe8d8a7c7ad..485cd5e2100c 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -143,6 +143,7 @@ struct usb_hcd {
 	unsigned		authorized_default:1;
 	unsigned		has_tt:1;	/* Integrated TT in root hub */
 	unsigned		amd_resume_bug:1; /* AMD remote wakeup quirk */
+	unsigned		can_do_streams:1; /* HC supports streams */
 
 	unsigned int		irq;		/* irq allocated */
 	void __iomem		*regs;		/* device memory/io */
-- 
cgit v1.2.3


From ef3adc187ca6418a376774ebf55d1258d1dc2c31 Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Mon, 24 Feb 2014 14:51:49 +0100
Subject: ARM: imx6q: Add GPR6 and GPR7 register definitions for iomuxc gpr

Masks for IPU AXI transaction QoS settings

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
---
 include/linux/mfd/syscon/imx6q-iomuxc-gpr.h | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h b/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h
index 866e355fa409..ff44374a1a4e 100644
--- a/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h
+++ b/include/linux/mfd/syscon/imx6q-iomuxc-gpr.h
@@ -242,6 +242,24 @@
 
 #define IMX6Q_GPR5_L2_CLK_STOP			BIT(8)
 
+#define IMX6Q_GPR6_IPU1_ID00_WR_QOS_MASK	(0xf << 0)
+#define IMX6Q_GPR6_IPU1_ID01_WR_QOS_MASK	(0xf << 4)
+#define IMX6Q_GPR6_IPU1_ID10_WR_QOS_MASK	(0xf << 8)
+#define IMX6Q_GPR6_IPU1_ID11_WR_QOS_MASK	(0xf << 12)
+#define IMX6Q_GPR6_IPU1_ID00_RD_QOS_MASK	(0xf << 16)
+#define IMX6Q_GPR6_IPU1_ID01_RD_QOS_MASK	(0xf << 20)
+#define IMX6Q_GPR6_IPU1_ID10_RD_QOS_MASK	(0xf << 24)
+#define IMX6Q_GPR6_IPU1_ID11_RD_QOS_MASK	(0xf << 28)
+
+#define IMX6Q_GPR7_IPU2_ID00_WR_QOS_MASK	(0xf << 0)
+#define IMX6Q_GPR7_IPU2_ID01_WR_QOS_MASK	(0xf << 4)
+#define IMX6Q_GPR7_IPU2_ID10_WR_QOS_MASK	(0xf << 8)
+#define IMX6Q_GPR7_IPU2_ID11_WR_QOS_MASK	(0xf << 12)
+#define IMX6Q_GPR7_IPU2_ID00_RD_QOS_MASK	(0xf << 16)
+#define IMX6Q_GPR7_IPU2_ID01_RD_QOS_MASK	(0xf << 20)
+#define IMX6Q_GPR7_IPU2_ID10_RD_QOS_MASK	(0xf << 24)
+#define IMX6Q_GPR7_IPU2_ID11_RD_QOS_MASK	(0xf << 28)
+
 #define IMX6Q_GPR8_TX_SWING_LOW			(0x7f << 25)
 #define IMX6Q_GPR8_TX_SWING_FULL		(0x7f << 18)
 #define IMX6Q_GPR8_TX_DEEMPH_GEN2_6DB		(0x3f << 12)
-- 
cgit v1.2.3


From de15011ac4e03a81e1483ddb7e876e6b64531887 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 26 Feb 2014 13:43:31 +0100
Subject: gpio: remove obsolete tnetv107x driver

The tnetv107x platform is getting removed, so this driver won't
be needed any more.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Alexandre Courbot <gnurou@gmail.com>
Cc: linux-gpio@vger.kernel.org
Acked-by: Sekhar Nori <nsekhar@ti.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/Makefile                      |   1 -
 drivers/gpio/gpio-tnetv107x.c              | 206 -----------------------------
 include/linux/platform_data/gpio-davinci.h |   4 -
 3 files changed, 211 deletions(-)
 delete mode 100644 drivers/gpio/gpio-tnetv107x.c

(limited to 'include/linux')

diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index 7038470c7eaf..aaff7ff9a8f7 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -81,7 +81,6 @@ obj-$(CONFIG_GPIO_TB10X)	+= gpio-tb10x.o
 obj-$(CONFIG_GPIO_TC3589X)	+= gpio-tc3589x.o
 obj-$(CONFIG_ARCH_TEGRA)	+= gpio-tegra.o
 obj-$(CONFIG_GPIO_TIMBERDALE)	+= gpio-timberdale.o
-obj-$(CONFIG_ARCH_DAVINCI_TNETV107X) += gpio-tnetv107x.o
 obj-$(CONFIG_GPIO_PALMAS)	+= gpio-palmas.o
 obj-$(CONFIG_GPIO_TPS6586X)	+= gpio-tps6586x.o
 obj-$(CONFIG_GPIO_TPS65910)	+= gpio-tps65910.o
diff --git a/drivers/gpio/gpio-tnetv107x.c b/drivers/gpio/gpio-tnetv107x.c
deleted file mode 100644
index 4aa481579a05..000000000000
--- a/drivers/gpio/gpio-tnetv107x.c
+++ /dev/null
@@ -1,206 +0,0 @@
-/*
- * Texas Instruments TNETV107X GPIO Controller
- *
- * Copyright (C) 2010 Texas Instruments
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/gpio.h>
-#include <linux/platform_data/gpio-davinci.h>
-
-#include <mach/common.h>
-#include <mach/tnetv107x.h>
-
-struct tnetv107x_gpio_regs {
-	u32	idver;
-	u32	data_in[3];
-	u32	data_out[3];
-	u32	direction[3];
-	u32	enable[3];
-};
-
-#define gpio_reg_index(gpio)	((gpio) >> 5)
-#define gpio_reg_bit(gpio)	BIT((gpio) & 0x1f)
-
-#define gpio_reg_rmw(reg, mask, val)	\
-	__raw_writel((__raw_readl(reg) & ~(mask)) | (val), (reg))
-
-#define gpio_reg_set_bit(reg, gpio)	\
-	gpio_reg_rmw((reg) + gpio_reg_index(gpio), 0, gpio_reg_bit(gpio))
-
-#define gpio_reg_clear_bit(reg, gpio)	\
-	gpio_reg_rmw((reg) + gpio_reg_index(gpio), gpio_reg_bit(gpio), 0)
-
-#define gpio_reg_get_bit(reg, gpio)	\
-	(__raw_readl((reg) + gpio_reg_index(gpio)) & gpio_reg_bit(gpio))
-
-#define chip2controller(chip)		\
-	container_of(chip, struct davinci_gpio_controller, chip)
-
-#define TNETV107X_GPIO_CTLRS	DIV_ROUND_UP(TNETV107X_N_GPIO, 32)
-
-static struct davinci_gpio_controller chips[TNETV107X_GPIO_CTLRS];
-
-static int tnetv107x_gpio_request(struct gpio_chip *chip, unsigned offset)
-{
-	struct davinci_gpio_controller *ctlr = chip2controller(chip);
-	struct tnetv107x_gpio_regs __iomem *regs = ctlr->regs;
-	unsigned gpio = chip->base + offset;
-	unsigned long flags;
-
-	spin_lock_irqsave(&ctlr->lock, flags);
-
-	gpio_reg_set_bit(regs->enable, gpio);
-
-	spin_unlock_irqrestore(&ctlr->lock, flags);
-
-	return 0;
-}
-
-static void tnetv107x_gpio_free(struct gpio_chip *chip, unsigned offset)
-{
-	struct davinci_gpio_controller *ctlr = chip2controller(chip);
-	struct tnetv107x_gpio_regs __iomem *regs = ctlr->regs;
-	unsigned gpio = chip->base + offset;
-	unsigned long flags;
-
-	spin_lock_irqsave(&ctlr->lock, flags);
-
-	gpio_reg_clear_bit(regs->enable, gpio);
-
-	spin_unlock_irqrestore(&ctlr->lock, flags);
-}
-
-static int tnetv107x_gpio_dir_in(struct gpio_chip *chip, unsigned offset)
-{
-	struct davinci_gpio_controller *ctlr = chip2controller(chip);
-	struct tnetv107x_gpio_regs __iomem *regs = ctlr->regs;
-	unsigned gpio = chip->base + offset;
-	unsigned long flags;
-
-	spin_lock_irqsave(&ctlr->lock, flags);
-
-	gpio_reg_set_bit(regs->direction, gpio);
-
-	spin_unlock_irqrestore(&ctlr->lock, flags);
-
-	return 0;
-}
-
-static int tnetv107x_gpio_dir_out(struct gpio_chip *chip,
-		unsigned offset, int value)
-{
-	struct davinci_gpio_controller *ctlr = chip2controller(chip);
-	struct tnetv107x_gpio_regs __iomem *regs = ctlr->regs;
-	unsigned gpio = chip->base + offset;
-	unsigned long flags;
-
-	spin_lock_irqsave(&ctlr->lock, flags);
-
-	if (value)
-		gpio_reg_set_bit(regs->data_out, gpio);
-	else
-		gpio_reg_clear_bit(regs->data_out, gpio);
-
-	gpio_reg_clear_bit(regs->direction, gpio);
-
-	spin_unlock_irqrestore(&ctlr->lock, flags);
-
-	return 0;
-}
-
-static int tnetv107x_gpio_get(struct gpio_chip *chip, unsigned offset)
-{
-	struct davinci_gpio_controller *ctlr = chip2controller(chip);
-	struct tnetv107x_gpio_regs __iomem *regs = ctlr->regs;
-	unsigned gpio = chip->base + offset;
-	int ret;
-
-	ret = gpio_reg_get_bit(regs->data_in, gpio);
-
-	return ret ? 1 : 0;
-}
-
-static void tnetv107x_gpio_set(struct gpio_chip *chip,
-		unsigned offset, int value)
-{
-	struct davinci_gpio_controller *ctlr = chip2controller(chip);
-	struct tnetv107x_gpio_regs __iomem *regs = ctlr->regs;
-	unsigned gpio = chip->base + offset;
-	unsigned long flags;
-
-	spin_lock_irqsave(&ctlr->lock, flags);
-
-	if (value)
-		gpio_reg_set_bit(regs->data_out, gpio);
-	else
-		gpio_reg_clear_bit(regs->data_out, gpio);
-
-	spin_unlock_irqrestore(&ctlr->lock, flags);
-}
-
-static int __init tnetv107x_gpio_setup(void)
-{
-	int i, base;
-	unsigned ngpio;
-	struct davinci_soc_info *soc_info = &davinci_soc_info;
-	struct tnetv107x_gpio_regs *regs;
-	struct davinci_gpio_controller *ctlr;
-
-	if (soc_info->gpio_type != GPIO_TYPE_TNETV107X)
-		return 0;
-
-	ngpio = soc_info->gpio_num;
-	if (ngpio == 0) {
-		pr_err("GPIO setup:  how many GPIOs?\n");
-		return -EINVAL;
-	}
-
-	if (WARN_ON(TNETV107X_N_GPIO < ngpio))
-		ngpio = TNETV107X_N_GPIO;
-
-	regs = ioremap(soc_info->gpio_base, SZ_4K);
-	if (WARN_ON(!regs))
-		return -EINVAL;
-
-	for (i = 0, base = 0; base < ngpio; i++, base += 32) {
-		ctlr = &chips[i];
-
-		ctlr->chip.label	= "tnetv107x";
-		ctlr->chip.can_sleep	= false;
-		ctlr->chip.base		= base;
-		ctlr->chip.ngpio	= ngpio - base;
-		if (ctlr->chip.ngpio > 32)
-			ctlr->chip.ngpio = 32;
-
-		ctlr->chip.request		= tnetv107x_gpio_request;
-		ctlr->chip.free			= tnetv107x_gpio_free;
-		ctlr->chip.direction_input	= tnetv107x_gpio_dir_in;
-		ctlr->chip.get			= tnetv107x_gpio_get;
-		ctlr->chip.direction_output	= tnetv107x_gpio_dir_out;
-		ctlr->chip.set			= tnetv107x_gpio_set;
-
-		spin_lock_init(&ctlr->lock);
-
-		ctlr->regs	= regs;
-		ctlr->set_data	= &regs->data_out[i];
-		ctlr->clr_data	= &regs->data_out[i];
-		ctlr->in_data	= &regs->data_in[i];
-
-		gpiochip_add(&ctlr->chip);
-	}
-
-	soc_info->gpio_ctlrs = chips;
-	soc_info->gpio_ctlrs_num = DIV_ROUND_UP(ngpio, 32);
-	return 0;
-}
-pure_initcall(tnetv107x_gpio_setup);
diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h
index fbe2f7535741..6ace3fd32b6a 100644
--- a/include/linux/platform_data/gpio-davinci.h
+++ b/include/linux/platform_data/gpio-davinci.h
@@ -21,10 +21,6 @@
 
 #include <asm-generic/gpio.h>
 
-enum davinci_gpio_type {
-	GPIO_TYPE_TNETV107X = 0,
-};
-
 struct davinci_gpio_platform_data {
 	u32	ngpio;
 	u32	gpio_unbanked;
-- 
cgit v1.2.3


From 6aef704e38293524067505eeafec9c811b18d66a Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Date: Fri, 28 Feb 2014 11:41:25 -0500
Subject: HID: multitouch: add support of other generic collections in hid-mt

The ANTON Touch Pad is a device which can switch from a multitouch
touchpad to a mouse. It thus presents several generic collections which
are currently ignored by hid-multitouch. Enable them by not ignoring
them in mt_input_mapping.
Adding also a suffix for them depending on their application.

Reported-by: Edel Maks <edelmaks@gmail.com>
Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-ids.h        |  3 ++
 drivers/hid/hid-multitouch.c | 82 ++++++++++++++++++++++++++++++++++++++++----
 include/linux/hid.h          |  3 ++
 3 files changed, 82 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 92b40c09d917..ca9b206a01c1 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -67,6 +67,9 @@
 #define USB_VENDOR_ID_ALPS		0x0433
 #define USB_DEVICE_ID_IBM_GAMEPAD	0x1101
 
+#define USB_VENDOR_ID_ANTON		0x1130
+#define USB_DEVICE_ID_ANTON_TOUCH_PAD	0x3101
+
 #define USB_VENDOR_ID_APPLE		0x05ac
 #define USB_DEVICE_ID_APPLE_MIGHTYMOUSE	0x0304
 #define USB_DEVICE_ID_APPLE_MAGICMOUSE	0x030d
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 8250cc0fd5f4..0d3113969c43 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -84,6 +84,7 @@ struct mt_class {
 	__s32 sn_pressure;	/* Signal/noise ratio for pressure events */
 	__u8 maxcontacts;
 	bool is_indirect;	/* true for touchpads */
+	bool export_all_inputs;	/* do not ignore mouse, keyboards, etc... */
 };
 
 struct mt_fields {
@@ -133,6 +134,7 @@ static void mt_post_parse(struct mt_device *td);
 /* reserved					0x0010 */
 /* reserved					0x0011 */
 #define MT_CLS_WIN_8				0x0012
+#define MT_CLS_EXPORT_ALL_INPUTS		0x0013
 
 /* vendor specific classes */
 #define MT_CLS_3M				0x0101
@@ -196,6 +198,10 @@ static struct mt_class mt_classes[] = {
 			MT_QUIRK_IGNORE_DUPLICATES |
 			MT_QUIRK_HOVERING |
 			MT_QUIRK_CONTACT_CNT_ACCURATE },
+	{ .name = MT_CLS_EXPORT_ALL_INPUTS,
+		.quirks = MT_QUIRK_ALWAYS_VALID |
+			MT_QUIRK_CONTACT_CNT_ACCURATE,
+		.export_all_inputs = true },
 
 	/*
 	 * vendor specific classes
@@ -718,28 +724,52 @@ static int mt_input_mapping(struct hid_device *hdev, struct hid_input *hi,
 		struct hid_field *field, struct hid_usage *usage,
 		unsigned long **bit, int *max)
 {
-	/* Only map fields from TouchScreen or TouchPad collections.
-	* We need to ignore fields that belong to other collections
-	* such as Mouse that might have the same GenericDesktop usages. */
-	if (field->application != HID_DG_TOUCHSCREEN &&
+	struct mt_device *td = hid_get_drvdata(hdev);
+
+	/*
+	 * If mtclass.export_all_inputs is not set, only map fields from
+	 * TouchScreen or TouchPad collections. We need to ignore fields
+	 * that belong to other collections such as Mouse that might have
+	 * the same GenericDesktop usages.
+	 */
+	if (!td->mtclass.export_all_inputs &&
+	    field->application != HID_DG_TOUCHSCREEN &&
 	    field->application != HID_DG_PEN &&
 	    field->application != HID_DG_TOUCHPAD)
 		return -1;
 
+	/*
+	 * some egalax touchscreens have "application == HID_DG_TOUCHSCREEN"
+	 * for the stylus.
+	 */
 	if (field->physical == HID_DG_STYLUS)
 		return 0;
 
-	return mt_touch_input_mapping(hdev, hi, field, usage, bit, max);
+	if (field->application == HID_DG_TOUCHSCREEN ||
+	    field->application == HID_DG_TOUCHPAD)
+		return mt_touch_input_mapping(hdev, hi, field, usage, bit, max);
+
+	/* let hid-core decide for the others */
+	return 0;
 }
 
 static int mt_input_mapped(struct hid_device *hdev, struct hid_input *hi,
 		struct hid_field *field, struct hid_usage *usage,
 		unsigned long **bit, int *max)
 {
+	/*
+	 * some egalax touchscreens have "application == HID_DG_TOUCHSCREEN"
+	 * for the stylus.
+	 */
 	if (field->physical == HID_DG_STYLUS)
 		return 0;
 
-	return mt_touch_input_mapped(hdev, hi, field, usage, bit, max);
+	if (field->application == HID_DG_TOUCHSCREEN ||
+	    field->application == HID_DG_TOUCHPAD)
+		return mt_touch_input_mapped(hdev, hi, field, usage, bit, max);
+
+	/* let hid-core decide for the others */
+	return 0;
 }
 
 static int mt_event(struct hid_device *hid, struct hid_field *field,
@@ -846,14 +876,49 @@ static void mt_input_configured(struct hid_device *hdev, struct hid_input *hi)
 	struct mt_device *td = hid_get_drvdata(hdev);
 	char *name;
 	const char *suffix = NULL;
+	struct hid_field *field = hi->report->field[0];
 
 	if (hi->report->id == td->mt_report_id)
 		mt_touch_input_configured(hdev, hi);
 
+	/*
+	 * some egalax touchscreens have "application == HID_DG_TOUCHSCREEN"
+	 * for the stylus. Check this first, and then rely on the application
+	 * field.
+	 */
 	if (hi->report->field[0]->physical == HID_DG_STYLUS) {
 		suffix = "Pen";
 		/* force BTN_STYLUS to allow tablet matching in udev */
 		__set_bit(BTN_STYLUS, hi->input->keybit);
+	} else {
+		switch (field->application) {
+		case HID_GD_KEYBOARD:
+			suffix = "Keyboard";
+			break;
+		case HID_GD_KEYPAD:
+			suffix = "Keypad";
+			break;
+		case HID_GD_MOUSE:
+			suffix = "Mouse";
+			break;
+		case HID_DG_STYLUS:
+			suffix = "Pen";
+			/* force BTN_STYLUS to allow tablet matching in udev */
+			__set_bit(BTN_STYLUS, hi->input->keybit);
+			break;
+		case HID_DG_TOUCHSCREEN:
+			/* we do not set suffix = "Touchscreen" */
+			break;
+		case HID_GD_SYSTEM_CONTROL:
+			suffix = "System Control";
+			break;
+		case HID_CP_CONSUMER_CONTROL:
+			suffix = "Consumer Control";
+			break;
+		default:
+			suffix = "UNKNOWN";
+			break;
+		}
 	}
 
 	if (suffix) {
@@ -992,6 +1057,11 @@ static const struct hid_device_id mt_devices[] = {
 		MT_USB_DEVICE(USB_VENDOR_ID_3M,
 			USB_DEVICE_ID_3M3266) },
 
+	/* Anton devices */
+	{ .driver_data = MT_CLS_EXPORT_ALL_INPUTS,
+		MT_USB_DEVICE(USB_VENDOR_ID_ANTON,
+			USB_DEVICE_ID_ANTON_TOUCH_PAD) },
+
 	/* Atmel panels */
 	{ .driver_data = MT_CLS_SERIAL,
 		MT_USB_DEVICE(USB_VENDOR_ID_ATMEL,
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 5eb282e0dff7..e224516cc565 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -201,6 +201,7 @@ struct hid_item {
 #define HID_GD_VBRZ		0x00010045
 #define HID_GD_VNO		0x00010046
 #define HID_GD_FEATURE		0x00010047
+#define HID_GD_SYSTEM_CONTROL	0x00010080
 #define HID_GD_UP		0x00010090
 #define HID_GD_DOWN		0x00010091
 #define HID_GD_RIGHT		0x00010092
@@ -208,6 +209,8 @@ struct hid_item {
 
 #define HID_DC_BATTERYSTRENGTH	0x00060020
 
+#define HID_CP_CONSUMER_CONTROL	0x000c0001
+
 #define HID_DG_DIGITIZER	0x000d0001
 #define HID_DG_PEN		0x000d0002
 #define HID_DG_LIGHTPEN		0x000d0003
-- 
cgit v1.2.3


From 0c176170089c3a7f2a891f9860f5cdc5f481ff78 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa@the-dreams.de>
Date: Mon, 10 Feb 2014 11:03:56 +0100
Subject: i2c: add deprecation warning for class based instantiation

Class based instantiation can cause noticeable delays when booting. This
mechanism is used when it is not possible to describe slaves on I2C
busses. As we do have other mechanisms, most embedded I2C will not need
classes and for embedded it is explicitly not recommended to use them. Add
a deprecation warning for drivers which want to disable class based
instantiation in the near future to gain boot-up time, so users relying
on this technique can switch to something better. They really should.

Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 drivers/i2c/i2c-core.c | 7 +++++++
 include/linux/i2c.h    | 1 +
 2 files changed, 8 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 5fb80b8962a2..98a5fd950f16 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -1941,6 +1941,13 @@ static int i2c_detect_address(struct i2c_client *temp_client,
 		struct i2c_client *client;
 
 		/* Detection succeeded, instantiate the device */
+		if (adapter->class & I2C_CLASS_DEPRECATED)
+			dev_warn(&adapter->dev,
+				"This adapter will soon drop class based instantiation of devices. "
+				"Please make sure client 0x%02x gets instantiated by other means. "
+				"Check 'Documentation/i2c/instantiating-devices' for details.\n",
+				info.addr);
+
 		dev_dbg(&adapter->dev, "Creating %s at 0x%02x\n",
 			info.type, info.addr);
 		client = i2c_new_device(adapter, &info);
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index deddeb8c337c..b556e0ab946f 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -487,6 +487,7 @@ void i2c_unlock_adapter(struct i2c_adapter *);
 #define I2C_CLASS_HWMON		(1<<0)	/* lm_sensors, ... */
 #define I2C_CLASS_DDC		(1<<3)	/* DDC bus on graphics adapters */
 #define I2C_CLASS_SPD		(1<<7)	/* Memory modules */
+#define I2C_CLASS_DEPRECATED	(1<<8)	/* Warn users that adapter will stop using classes */
 
 /* Internal numbers to terminate lists */
 #define I2C_CLIENT_END		0xfffeU
-- 
cgit v1.2.3


From 57bf9b09a6ad517b0c790b786845660ec5604774 Mon Sep 17 00:00:00 2001
From: Peter Chen <peter.chen@freescale.com>
Date: Mon, 24 Feb 2014 10:21:01 +0800
Subject: usb: phy: Add set_wakeup API

This API is used to set wakeup enable at PHY registers, in that
case, the PHY can be waken up from suspend due to external events,
like vbus change, dp/dm change and id change.

Signed-off-by: Peter Chen <peter.chen@freescale.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 include/linux/usb/phy.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/usb/phy.h b/include/linux/usb/phy.h
index 6c0b1c513db7..353053a33f21 100644
--- a/include/linux/usb/phy.h
+++ b/include/linux/usb/phy.h
@@ -111,6 +111,13 @@ struct usb_phy {
 	int	(*set_suspend)(struct usb_phy *x,
 				int suspend);
 
+	/*
+	 * Set wakeup enable for PHY, in that case, the PHY can be
+	 * woken up from suspend status due to external events,
+	 * like vbus change, dp/dm change and id.
+	 */
+	int	(*set_wakeup)(struct usb_phy *x, bool enabled);
+
 	/* notify phy connect status change */
 	int	(*notify_connect)(struct usb_phy *x,
 			enum usb_device_speed speed);
@@ -264,6 +271,15 @@ usb_phy_set_suspend(struct usb_phy *x, int suspend)
 		return 0;
 }
 
+static inline int
+usb_phy_set_wakeup(struct usb_phy *x, bool enabled)
+{
+	if (x && x->set_wakeup)
+		return x->set_wakeup(x, enabled);
+	else
+		return 0;
+}
+
 static inline int
 usb_phy_notify_connect(struct usb_phy *x, enum usb_device_speed speed)
 {
-- 
cgit v1.2.3


From 3b02b56cd5988d569731f6c0c26992296e46b758 Mon Sep 17 00:00:00 2001
From: Vytas Dauksa <vytas.dauksa@smoothwall.net>
Date: Tue, 17 Dec 2013 14:01:43 +0000
Subject: netfilter: ipset: add hash:ip,mark data type to ipset

Introduce packet mark support with new ip,mark hash set. This includes
userspace and kernelspace code, hash:ip,mark set tests and man page
updates.

The intended use of ip,mark set is similar to the ip:port type, but for
protocols which don't use a predictable port number. Instead of port
number it matches a firewall mark determined by a layer 7 filtering
program like opendpi.

As well as allowing or blocking traffic it will also be used for
accounting packets and bytes sent for each protocol.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 include/linux/netfilter/ipset/ip_set.h      |  10 +-
 include/uapi/linux/netfilter/ipset/ip_set.h |   1 +
 net/netfilter/ipset/Kconfig                 |   9 +
 net/netfilter/ipset/Makefile                |   1 +
 net/netfilter/ipset/ip_set_hash_ipmark.c    | 312 ++++++++++++++++++++++++++++
 5 files changed, 329 insertions(+), 4 deletions(-)
 create mode 100644 net/netfilter/ipset/ip_set_hash_ipmark.c

(limited to 'include/linux')

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index 0c7d01eae56c..4ac00d4aa87e 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -39,11 +39,13 @@ enum ip_set_feature {
 	IPSET_TYPE_NAME = (1 << IPSET_TYPE_NAME_FLAG),
 	IPSET_TYPE_IFACE_FLAG = 5,
 	IPSET_TYPE_IFACE = (1 << IPSET_TYPE_IFACE_FLAG),
-	IPSET_TYPE_NOMATCH_FLAG = 6,
+	IPSET_TYPE_MARK_FLAG = 6,
+	IPSET_TYPE_MARK = (1 << IPSET_TYPE_MARK_FLAG),
+	IPSET_TYPE_NOMATCH_FLAG = 7,
 	IPSET_TYPE_NOMATCH = (1 << IPSET_TYPE_NOMATCH_FLAG),
 	/* Strictly speaking not a feature, but a flag for dumping:
 	 * this settype must be dumped last */
-	IPSET_DUMP_LAST_FLAG = 7,
+	IPSET_DUMP_LAST_FLAG = 8,
 	IPSET_DUMP_LAST = (1 << IPSET_DUMP_LAST_FLAG),
 };
 
@@ -171,8 +173,6 @@ struct ip_set_type {
 	char name[IPSET_MAXNAMELEN];
 	/* Protocol version */
 	u8 protocol;
-	/* Set features to control swapping */
-	u8 features;
 	/* Set type dimension */
 	u8 dimension;
 	/*
@@ -182,6 +182,8 @@ struct ip_set_type {
 	u8 family;
 	/* Type revisions */
 	u8 revision_min, revision_max;
+	/* Set features to control swapping */
+	u16 features;
 
 	/* Create set */
 	int (*create)(struct net *net, struct ip_set *set,
diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h
index 25d3b2f79c02..5368f8275774 100644
--- a/include/uapi/linux/netfilter/ipset/ip_set.h
+++ b/include/uapi/linux/netfilter/ipset/ip_set.h
@@ -82,6 +82,7 @@ enum {
 	IPSET_ATTR_PROTO,	/* 7 */
 	IPSET_ATTR_CADT_FLAGS,	/* 8 */
 	IPSET_ATTR_CADT_LINENO = IPSET_ATTR_LINENO,	/* 9 */
+	IPSET_ATTR_MARK,	/* 10 */
 	/* Reserve empty slots */
 	IPSET_ATTR_CADT_MAX = 16,
 	/* Create-only specific attributes */
diff --git a/net/netfilter/ipset/Kconfig b/net/netfilter/ipset/Kconfig
index 44cd4f58adf0..2f7f5c32c6f9 100644
--- a/net/netfilter/ipset/Kconfig
+++ b/net/netfilter/ipset/Kconfig
@@ -61,6 +61,15 @@ config IP_SET_HASH_IP
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config IP_SET_HASH_IPMARK
+	tristate "hash:ip,mark set support"
+	depends on IP_SET
+	help
+	  This option adds the hash:ip,mark set type support, by which one
+	  can store IPv4/IPv6 address and mark pairs.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
 config IP_SET_HASH_IPPORT
 	tristate "hash:ip,port set support"
 	depends on IP_SET
diff --git a/net/netfilter/ipset/Makefile b/net/netfilter/ipset/Makefile
index 44b2d38476fa..231f10196cb9 100644
--- a/net/netfilter/ipset/Makefile
+++ b/net/netfilter/ipset/Makefile
@@ -14,6 +14,7 @@ obj-$(CONFIG_IP_SET_BITMAP_PORT) += ip_set_bitmap_port.o
 
 # hash types
 obj-$(CONFIG_IP_SET_HASH_IP) += ip_set_hash_ip.o
+obj-$(CONFIG_IP_SET_HASH_IPMARK) += ip_set_hash_ipmark.o
 obj-$(CONFIG_IP_SET_HASH_IPPORT) += ip_set_hash_ipport.o
 obj-$(CONFIG_IP_SET_HASH_IPPORTIP) += ip_set_hash_ipportip.o
 obj-$(CONFIG_IP_SET_HASH_IPPORTNET) += ip_set_hash_ipportnet.o
diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c
new file mode 100644
index 000000000000..e56c0d916fac
--- /dev/null
+++ b/net/netfilter/ipset/ip_set_hash_ipmark.c
@@ -0,0 +1,312 @@
+/* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ * Copyright (C) 2013 Smoothwall Ltd. <vytas.dauksa@smoothwall.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* Kernel module implementing an IP set type: the hash:ip,mark type */
+
+#include <linux/jhash.h>
+#include <linux/module.h>
+#include <linux/ip.h>
+#include <linux/skbuff.h>
+#include <linux/errno.h>
+#include <linux/random.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/netlink.h>
+#include <net/tcp.h>
+
+#include <linux/netfilter.h>
+#include <linux/netfilter/ipset/pfxlen.h>
+#include <linux/netfilter/ipset/ip_set.h>
+#include <linux/netfilter/ipset/ip_set_hash.h>
+
+#define IPSET_TYPE_REV_MIN	0
+#define IPSET_TYPE_REV_MAX	0
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Vytas Dauksa <vytas.dauksa@smoothwall.net>");
+IP_SET_MODULE_DESC("hash:ip,mark", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
+MODULE_ALIAS("ip_set_hash:ip,mark");
+
+/* Type specific function prefix */
+#define HTYPE		hash_ipmark
+
+/* IPv4 variant */
+
+/* Member elements */
+struct hash_ipmark4_elem {
+	__be32 ip;
+	__u32 mark;
+};
+
+/* Common functions */
+
+static inline bool
+hash_ipmark4_data_equal(const struct hash_ipmark4_elem *ip1,
+			const struct hash_ipmark4_elem *ip2,
+			u32 *multi)
+{
+	return ip1->ip == ip2->ip &&
+	       ip1->mark == ip2->mark;
+}
+
+static bool
+hash_ipmark4_data_list(struct sk_buff *skb,
+		       const struct hash_ipmark4_elem *data)
+{
+	if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) ||
+	    nla_put_net32(skb, IPSET_ATTR_MARK, htonl(data->mark)))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return 1;
+}
+
+static inline void
+hash_ipmark4_data_next(struct hash_ipmark4_elem *next,
+		       const struct hash_ipmark4_elem *d)
+{
+	next->ip = d->ip;
+}
+
+#define MTYPE           hash_ipmark4
+#define PF              4
+#define HOST_MASK       32
+#define HKEY_DATALEN	sizeof(struct hash_ipmark4_elem)
+#include "ip_set_hash_gen.h"
+
+static int
+hash_ipmark4_kadt(struct ip_set *set, const struct sk_buff *skb,
+		  const struct xt_action_param *par,
+		  enum ipset_adt adt, struct ip_set_adt_opt *opt)
+{
+	ipset_adtfn adtfn = set->variant->adt[adt];
+	struct hash_ipmark4_elem e = { };
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
+
+	e.mark = skb->mark;
+
+	ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip);
+	return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
+}
+
+static int
+hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[],
+		  enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
+{
+	const struct hash_ipmark *h = set->data;
+	ipset_adtfn adtfn = set->variant->adt[adt];
+	struct hash_ipmark4_elem e = { };
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+	u32 ip, ip_to = 0;
+	int ret;
+
+	if (unlikely(!tb[IPSET_ATTR_IP] ||
+		     !ip_set_attr_netorder(tb, IPSET_ATTR_MARK) ||
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
+		return -IPSET_ERR_PROTOCOL;
+
+	if (tb[IPSET_ATTR_LINENO])
+		*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+	ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip) ||
+	      ip_set_get_extensions(set, tb, &ext);
+	if (ret)
+		return ret;
+
+	e.mark = ntohl(nla_get_u32(tb[IPSET_ATTR_MARK]));
+
+	if (adt == IPSET_TEST ||
+	    !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR])) {
+		ret = adtfn(set, &e, &ext, &ext, flags);
+		return ip_set_eexist(ret, flags) ? 0 : ret;
+	}
+
+	ip_to = ip = ntohl(e.ip);
+	if (tb[IPSET_ATTR_IP_TO]) {
+		ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to);
+		if (ret)
+			return ret;
+		if (ip > ip_to)
+			swap(ip, ip_to);
+	} else if (tb[IPSET_ATTR_CIDR]) {
+		u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
+
+		if (!cidr || cidr > 32)
+			return -IPSET_ERR_INVALID_CIDR;
+		ip_set_mask_from_to(ip, ip_to, cidr);
+	}
+
+	if (retried)
+		ip = ntohl(h->next.ip);
+	for (; !before(ip_to, ip); ip++) {
+		e.ip = htonl(ip);
+		ret = adtfn(set, &e, &ext, &ext, flags);
+
+		if (ret && !ip_set_eexist(ret, flags))
+			return ret;
+		else
+			ret = 0;
+	}
+	return ret;
+}
+
+/* IPv6 variant */
+
+struct hash_ipmark6_elem {
+	union nf_inet_addr ip;
+	__u32 mark;
+};
+
+/* Common functions */
+
+static inline bool
+hash_ipmark6_data_equal(const struct hash_ipmark6_elem *ip1,
+			const struct hash_ipmark6_elem *ip2,
+			u32 *multi)
+{
+	return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) &&
+	       ip1->mark == ip2->mark;
+}
+
+static bool
+hash_ipmark6_data_list(struct sk_buff *skb,
+		       const struct hash_ipmark6_elem *data)
+{
+	if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) ||
+	    nla_put_net32(skb, IPSET_ATTR_MARK, htonl(data->mark)))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return 1;
+}
+
+static inline void
+hash_ipmark6_data_next(struct hash_ipmark4_elem *next,
+		       const struct hash_ipmark6_elem *d)
+{
+}
+
+#undef MTYPE
+#undef PF
+#undef HOST_MASK
+#undef HKEY_DATALEN
+
+#define MTYPE		hash_ipmark6
+#define PF		6
+#define HOST_MASK	128
+#define HKEY_DATALEN	sizeof(struct hash_ipmark6_elem)
+#define	IP_SET_EMIT_CREATE
+#include "ip_set_hash_gen.h"
+
+
+static int
+hash_ipmark6_kadt(struct ip_set *set, const struct sk_buff *skb,
+		  const struct xt_action_param *par,
+		  enum ipset_adt adt, struct ip_set_adt_opt *opt)
+{
+	ipset_adtfn adtfn = set->variant->adt[adt];
+	struct hash_ipmark6_elem e = { };
+	struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
+
+	e.mark = skb->mark;
+
+	ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6);
+	return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
+}
+
+static int
+hash_ipmark6_uadt(struct ip_set *set, struct nlattr *tb[],
+		  enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
+{
+	ipset_adtfn adtfn = set->variant->adt[adt];
+	struct hash_ipmark6_elem e = { };
+	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+	int ret;
+
+	if (unlikely(!tb[IPSET_ATTR_IP] ||
+		     !ip_set_attr_netorder(tb, IPSET_ATTR_MARK) ||
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+		     !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) ||
+		     tb[IPSET_ATTR_IP_TO] ||
+		     tb[IPSET_ATTR_CIDR]))
+		return -IPSET_ERR_PROTOCOL;
+
+	if (tb[IPSET_ATTR_LINENO])
+		*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+	ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) ||
+	      ip_set_get_extensions(set, tb, &ext);
+	if (ret)
+		return ret;
+
+	e.mark = ntohl(nla_get_u32(tb[IPSET_ATTR_MARK]));
+
+	if (adt == IPSET_TEST) {
+		ret = adtfn(set, &e, &ext, &ext, flags);
+		return ip_set_eexist(ret, flags) ? 0 : ret;
+	}
+
+	ret = adtfn(set, &e, &ext, &ext, flags);
+	if (ret && !ip_set_eexist(ret, flags))
+		return ret;
+	else
+		ret = 0;
+
+	return ret;
+}
+
+static struct ip_set_type hash_ipmark_type __read_mostly = {
+	.name		= "hash:ip,mark",
+	.protocol	= IPSET_PROTOCOL,
+	.features	= IPSET_TYPE_IP | IPSET_TYPE_MARK,
+	.dimension	= IPSET_DIM_TWO,
+	.family		= NFPROTO_UNSPEC,
+	.revision_min	= IPSET_TYPE_REV_MIN,
+	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create		= hash_ipmark_create,
+	.create_policy	= {
+		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
+		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
+		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
+		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
+		[IPSET_ATTR_CADT_FLAGS]	= { .type = NLA_U32 },
+	},
+	.adt_policy	= {
+		[IPSET_ATTR_IP]		= { .type = NLA_NESTED },
+		[IPSET_ATTR_IP_TO]	= { .type = NLA_NESTED },
+		[IPSET_ATTR_MARK]	= { .type = NLA_U32 },
+		[IPSET_ATTR_CIDR]	= { .type = NLA_U8 },
+		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
+		[IPSET_ATTR_LINENO]	= { .type = NLA_U32 },
+		[IPSET_ATTR_BYTES]	= { .type = NLA_U64 },
+		[IPSET_ATTR_PACKETS]	= { .type = NLA_U64 },
+		[IPSET_ATTR_COMMENT]	= { .type = NLA_NUL_STRING },
+	},
+	.me		= THIS_MODULE,
+};
+
+static int __init
+hash_ipmark_init(void)
+{
+	return ip_set_type_register(&hash_ipmark_type);
+}
+
+static void __exit
+hash_ipmark_fini(void)
+{
+	ip_set_type_unregister(&hash_ipmark_type);
+}
+
+module_init(hash_ipmark_init);
+module_exit(hash_ipmark_fini);
-- 
cgit v1.2.3


From af284ece87365f3a69723f5bcc1bcdb505b5eb5d Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Thu, 13 Feb 2014 12:19:56 +0100
Subject: netfilter: ipset: Prepare the kernel for create option flags when no
 extension is needed

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 include/linux/netfilter/ipset/ip_set.h      | 2 ++
 include/uapi/linux/netfilter/ipset/ip_set.h | 6 ++++++
 2 files changed, 8 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index 4ac00d4aa87e..f476bcec25ea 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -219,6 +219,8 @@ struct ip_set {
 	u8 revision;
 	/* Extensions */
 	u8 extensions;
+	/* Create flags */
+	u8 flags;
 	/* Default timeout value, if enabled */
 	u32 timeout;
 	/* Element data size */
diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h
index f636f282b142..a29a378701d2 100644
--- a/include/uapi/linux/netfilter/ipset/ip_set.h
+++ b/include/uapi/linux/netfilter/ipset/ip_set.h
@@ -188,6 +188,12 @@ enum ipset_cadt_flags {
 	IPSET_FLAG_CADT_MAX	= 15,
 };
 
+/* The flag bits which correspond to the non-extension create flags */
+enum ipset_create_flags {
+	IPSET_CREATE_FLAG_NONE = 0,
+	IPSET_CREATE_FLAG_MAX = 7,
+};
+
 /* Commands with settype-specific attributes */
 enum ipset_adt {
 	IPSET_ADD,
-- 
cgit v1.2.3


From 07cf8f5ae2657ac495b906c68ff3441ff8ba80ba Mon Sep 17 00:00:00 2001
From: Josh Hunt <johunt@akamai.com>
Date: Fri, 28 Feb 2014 22:14:57 -0500
Subject: netfilter: ipset: add forceadd kernel support for hash set types

Adds a new property for hash set types, where if a set is created
with the 'forceadd' option and the set becomes full the next addition
to the set may succeed and evict a random entry from the set.

To keep overhead low eviction is done very simply. It checks to see
which bucket the new entry would be added. If the bucket's pos value
is non-zero (meaning there's at least one entry in the bucket) it
replaces the first entry in the bucket. If pos is zero, then it continues
down the normal add process.

This property is useful if you have a set for 'ban' lists where it may
not matter if you release some entries from the set early.

Signed-off-by: Josh Hunt <johunt@akamai.com>
Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
---
 include/linux/netfilter/ipset/ip_set.h       |  3 +++
 include/uapi/linux/netfilter/ipset/ip_set.h  |  7 +++++--
 net/netfilter/ipset/ip_set_core.c            |  2 ++
 net/netfilter/ipset/ip_set_hash_gen.h        | 12 ++++++++++++
 net/netfilter/ipset/ip_set_hash_ip.c         |  3 ++-
 net/netfilter/ipset/ip_set_hash_ipmark.c     |  2 +-
 net/netfilter/ipset/ip_set_hash_ipport.c     |  3 ++-
 net/netfilter/ipset/ip_set_hash_ipportip.c   |  3 ++-
 net/netfilter/ipset/ip_set_hash_ipportnet.c  |  3 ++-
 net/netfilter/ipset/ip_set_hash_net.c        |  3 ++-
 net/netfilter/ipset/ip_set_hash_netiface.c   |  3 ++-
 net/netfilter/ipset/ip_set_hash_netnet.c     |  2 +-
 net/netfilter/ipset/ip_set_hash_netport.c    |  3 ++-
 net/netfilter/ipset/ip_set_hash_netportnet.c |  3 ++-
 14 files changed, 40 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index f476bcec25ea..96afc29184be 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -65,6 +65,7 @@ enum ip_set_extension {
 #define SET_WITH_TIMEOUT(s)	((s)->extensions & IPSET_EXT_TIMEOUT)
 #define SET_WITH_COUNTER(s)	((s)->extensions & IPSET_EXT_COUNTER)
 #define SET_WITH_COMMENT(s)	((s)->extensions & IPSET_EXT_COMMENT)
+#define SET_WITH_FORCEADD(s)	((s)->flags & IPSET_CREATE_FLAG_FORCEADD)
 
 /* Extension id, in size order */
 enum ip_set_ext_id {
@@ -255,6 +256,8 @@ ip_set_put_flags(struct sk_buff *skb, struct ip_set *set)
 		cadt_flags |= IPSET_FLAG_WITH_COUNTERS;
 	if (SET_WITH_COMMENT(set))
 		cadt_flags |= IPSET_FLAG_WITH_COMMENT;
+	if (SET_WITH_FORCEADD(set))
+		cadt_flags |= IPSET_FLAG_WITH_FORCEADD;
 
 	if (!cadt_flags)
 		return 0;
diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h
index a1ca24408206..78c2f2e79920 100644
--- a/include/uapi/linux/netfilter/ipset/ip_set.h
+++ b/include/uapi/linux/netfilter/ipset/ip_set.h
@@ -185,13 +185,16 @@ enum ipset_cadt_flags {
 	IPSET_FLAG_WITH_COUNTERS = (1 << IPSET_FLAG_BIT_WITH_COUNTERS),
 	IPSET_FLAG_BIT_WITH_COMMENT = 4,
 	IPSET_FLAG_WITH_COMMENT = (1 << IPSET_FLAG_BIT_WITH_COMMENT),
+	IPSET_FLAG_BIT_WITH_FORCEADD = 5,
+	IPSET_FLAG_WITH_FORCEADD = (1 << IPSET_FLAG_BIT_WITH_FORCEADD),
 	IPSET_FLAG_CADT_MAX	= 15,
 };
 
 /* The flag bits which correspond to the non-extension create flags */
 enum ipset_create_flags {
-	IPSET_CREATE_FLAG_NONE = 0,
-	IPSET_CREATE_FLAG_MAX = 7,
+	IPSET_CREATE_FLAG_BIT_FORCEADD = 0,
+	IPSET_CREATE_FLAG_FORCEADD = (1 << IPSET_CREATE_FLAG_BIT_FORCEADD),
+	IPSET_CREATE_FLAG_BIT_MAX = 7,
 };
 
 /* Commands with settype-specific attributes */
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 636cb8df5354..117208321f16 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -368,6 +368,8 @@ ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len)
 
 	if (tb[IPSET_ATTR_CADT_FLAGS])
 		cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
+	if (cadt_flags & IPSET_FLAG_WITH_FORCEADD)
+		set->flags |= IPSET_CREATE_FLAG_FORCEADD;
 	for (id = 0; id < IPSET_EXT_ID_MAX; id++) {
 		if (!add_extension(id, cadt_flags, tb))
 			continue;
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index b1eed81e24c5..61c7fb052802 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -633,6 +633,18 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 	bool flag_exist = flags & IPSET_FLAG_EXIST;
 	u32 key, multi = 0;
 
+	if (h->elements >= h->maxelem && SET_WITH_FORCEADD(set)) {
+		rcu_read_lock_bh();
+		t = rcu_dereference_bh(h->table);
+		key = HKEY(value, h->initval, t->htable_bits);
+		n = hbucket(t,key);
+		if (n->pos) {
+			/* Choosing the first entry in the array to replace */
+			j = 0;
+			goto reuse_slot;
+		}
+		rcu_read_unlock_bh();
+	}
 	if (SET_WITH_TIMEOUT(set) && h->elements >= h->maxelem)
 		/* FIXME: when set is full, we slow down here */
 		mtype_expire(set, h, NLEN(set->family), set->dsize);
diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c
index e65fc2423d56..dd40607f878e 100644
--- a/net/netfilter/ipset/ip_set_hash_ip.c
+++ b/net/netfilter/ipset/ip_set_hash_ip.c
@@ -25,7 +25,8 @@
 
 #define IPSET_TYPE_REV_MIN	0
 /*				1	   Counters support */
-#define IPSET_TYPE_REV_MAX	2	/* Comments support */
+/*				2	   Comments support */
+#define IPSET_TYPE_REV_MAX	3	/* Forceadd support */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c
index 1bf8e8524218..4eff0a297254 100644
--- a/net/netfilter/ipset/ip_set_hash_ipmark.c
+++ b/net/netfilter/ipset/ip_set_hash_ipmark.c
@@ -25,7 +25,7 @@
 #include <linux/netfilter/ipset/ip_set_hash.h>
 
 #define IPSET_TYPE_REV_MIN	0
-#define IPSET_TYPE_REV_MAX	0
+#define IPSET_TYPE_REV_MAX	1	/* Forceadd support */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Vytas Dauksa <vytas.dauksa@smoothwall.net>");
diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c
index 525a595dd1fe..7597b82a8b03 100644
--- a/net/netfilter/ipset/ip_set_hash_ipport.c
+++ b/net/netfilter/ipset/ip_set_hash_ipport.c
@@ -27,7 +27,8 @@
 #define IPSET_TYPE_REV_MIN	0
 /*				1    SCTP and UDPLITE support added */
 /*				2    Counters support added */
-#define IPSET_TYPE_REV_MAX	3 /* Comments support added */
+/*				3    Comments support added */
+#define IPSET_TYPE_REV_MAX	4 /* Forceadd support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c
index f5636631466e..672655ffd573 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportip.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportip.c
@@ -27,7 +27,8 @@
 #define IPSET_TYPE_REV_MIN	0
 /*				1    SCTP and UDPLITE support added */
 /*				2    Counters support added */
-#define IPSET_TYPE_REV_MAX	3 /* Comments support added */
+/*				3    Comments support added */
+#define IPSET_TYPE_REV_MAX	4 /* Forceadd support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index 5d87fe8a41ff..7308d84f9277 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -29,7 +29,8 @@
 /*				2    Range as input support for IPv4 added */
 /*				3    nomatch flag support added */
 /*				4    Counters support added */
-#define IPSET_TYPE_REV_MAX	5 /* Comments support added */
+/*				5    Comments support added */
+#define IPSET_TYPE_REV_MAX	6 /* Forceadd support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index 8295cf4f9fdc..4c7d495783a3 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -26,7 +26,8 @@
 /*				1    Range as input support for IPv4 added */
 /*				2    nomatch flag support added */
 /*				3    Counters support added */
-#define IPSET_TYPE_REV_MAX	4 /* Comments support added */
+/*				4    Comments support added */
+#define IPSET_TYPE_REV_MAX	5 /* Forceadd support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index b827a0f1f351..db2606805b35 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -27,7 +27,8 @@
 /*				1    nomatch flag support added */
 /*				2    /0 support added */
 /*				3    Counters support added */
-#define IPSET_TYPE_REV_MAX	4 /* Comments support added */
+/*				4    Comments support added */
+#define IPSET_TYPE_REV_MAX	5 /* Forceadd support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c
index 4e7261df8961..3e99987e4bf2 100644
--- a/net/netfilter/ipset/ip_set_hash_netnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netnet.c
@@ -24,7 +24,7 @@
 #include <linux/netfilter/ipset/ip_set_hash.h>
 
 #define IPSET_TYPE_REV_MIN	0
-#define IPSET_TYPE_REV_MAX	0
+#define IPSET_TYPE_REV_MAX	1	/* Forceadd support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>");
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index 7097fb0141bf..1c645fbd09c7 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -28,7 +28,8 @@
 /*				2    Range as input support for IPv4 added */
 /*				3    nomatch flag support added */
 /*				4    Counters support added */
-#define IPSET_TYPE_REV_MAX	5 /* Comments support added */
+/*				5    Comments support added */
+#define IPSET_TYPE_REV_MAX	6 /* Forceadd support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c
index 703d1192a6a2..c0d2ba73f8b2 100644
--- a/net/netfilter/ipset/ip_set_hash_netportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netportnet.c
@@ -25,7 +25,8 @@
 #include <linux/netfilter/ipset/ip_set_hash.h>
 
 #define IPSET_TYPE_REV_MIN	0
-#define IPSET_TYPE_REV_MAX	0 /* Comments support added */
+/*				0    Comments support added */
+#define IPSET_TYPE_REV_MAX	1 /* Forceadd support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>");
-- 
cgit v1.2.3


From ca5d1b3524b4d90a2e2f1f71583c1dca6b96fd92 Mon Sep 17 00:00:00 2001
From: Carlo Caione <carlo@caione.org>
Date: Wed, 5 Mar 2014 22:11:29 +0100
Subject: regulator: helpers: Modify helpers enabling multi-bit control

This patch extends the regulator helpers to account for device that use
multiple bits for control when using regmap enable/disable/bypass ops.

The actual regulator helpers wrongly assume that the regulator control
is always performed using single bits, using in the regulator_desc
struct only two parameters *_reg and *_mask defining register and mask
for control.

This patch extends this struct and introduces the helpers to take into
account devices where control is performed using multiple bits and
specific multi-bit values are used for enabling/disabling/bypassing the
regulator.

Signed-off-by: Carlo Caione <carlo@caione.org>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/regulator/helpers.c      | 48 ++++++++++++++++++++++++++--------------
 include/linux/regulator/driver.h |  8 +++++++
 2 files changed, 40 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/regulator/helpers.c b/drivers/regulator/helpers.c
index e221a271ba56..cbc39096c78d 100644
--- a/drivers/regulator/helpers.c
+++ b/drivers/regulator/helpers.c
@@ -37,10 +37,17 @@ int regulator_is_enabled_regmap(struct regulator_dev *rdev)
 	if (ret != 0)
 		return ret;
 
-	if (rdev->desc->enable_is_inverted)
-		return (val & rdev->desc->enable_mask) == 0;
-	else
-		return (val & rdev->desc->enable_mask) != 0;
+	val &= rdev->desc->enable_mask;
+
+	if (rdev->desc->enable_is_inverted) {
+		if (rdev->desc->enable_val)
+			return val != rdev->desc->enable_val;
+		return val == 0;
+	} else {
+		if (rdev->desc->enable_val)
+			return val == rdev->desc->enable_val;
+		return val != 0;
+	}
 }
 EXPORT_SYMBOL_GPL(regulator_is_enabled_regmap);
 
@@ -57,10 +64,13 @@ int regulator_enable_regmap(struct regulator_dev *rdev)
 {
 	unsigned int val;
 
-	if (rdev->desc->enable_is_inverted)
-		val = 0;
-	else
-		val = rdev->desc->enable_mask;
+	if (rdev->desc->enable_is_inverted) {
+		val = rdev->desc->disable_val;
+	} else {
+		val = rdev->desc->enable_val;
+		if (!val)
+			val = rdev->desc->enable_mask;
+	}
 
 	return regmap_update_bits(rdev->regmap, rdev->desc->enable_reg,
 				  rdev->desc->enable_mask, val);
@@ -80,10 +90,13 @@ int regulator_disable_regmap(struct regulator_dev *rdev)
 {
 	unsigned int val;
 
-	if (rdev->desc->enable_is_inverted)
-		val = rdev->desc->enable_mask;
-	else
-		val = 0;
+	if (rdev->desc->enable_is_inverted) {
+		val = rdev->desc->enable_val;
+		if (!val)
+			val = rdev->desc->enable_mask;
+	} else {
+		val = rdev->desc->disable_val;
+	}
 
 	return regmap_update_bits(rdev->regmap, rdev->desc->enable_reg,
 				  rdev->desc->enable_mask, val);
@@ -419,10 +432,13 @@ int regulator_set_bypass_regmap(struct regulator_dev *rdev, bool enable)
 {
 	unsigned int val;
 
-	if (enable)
-		val = rdev->desc->bypass_mask;
-	else
-		val = 0;
+	if (enable) {
+		val = rdev->desc->bypass_val_on;
+		if (!val)
+			val = rdev->desc->bypass_mask;
+	} else {
+		val = rdev->desc->bypass_val_off;
+	}
 
 	return regmap_update_bits(rdev->regmap, rdev->desc->bypass_reg,
 				  rdev->desc->bypass_mask, val);
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index 9370e65348a4..bbe03a1924c0 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -228,10 +228,14 @@ enum regulator_type {
  *                output when using regulator_set_voltage_sel_regmap
  * @enable_reg: Register for control when using regmap enable/disable ops
  * @enable_mask: Mask for control when using regmap enable/disable ops
+ * @enable_val: Enabling value for control when using regmap enable/disable ops
+ * @disable_val: Disabling value for control when using regmap enable/disable ops
  * @enable_is_inverted: A flag to indicate set enable_mask bits to disable
  *                      when using regulator_enable_regmap and friends APIs.
  * @bypass_reg: Register for control when using regmap set_bypass
  * @bypass_mask: Mask for control when using regmap set_bypass
+ * @bypass_val_on: Enabling value for control when using regmap set_bypass
+ * @bypass_val_off: Disabling value for control when using regmap set_bypass
  *
  * @enable_time: Time taken for initial enable of regulator (in uS).
  */
@@ -263,9 +267,13 @@ struct regulator_desc {
 	unsigned int apply_bit;
 	unsigned int enable_reg;
 	unsigned int enable_mask;
+	unsigned int enable_val;
+	unsigned int disable_val;
 	bool enable_is_inverted;
 	unsigned int bypass_reg;
 	unsigned int bypass_mask;
+	unsigned int bypass_val_on;
+	unsigned int bypass_val_off;
 
 	unsigned int enable_time;
 };
-- 
cgit v1.2.3


From 13ff50c85846338bb9820abd3933227b678dc086 Mon Sep 17 00:00:00 2001
From: Nenghua Cao <nhcao@marvell.com>
Date: Wed, 19 Feb 2014 18:44:13 +0800
Subject: regmap: add regmap_parse_val api

    In some cases, we need regmap's format parse_val function
to do be/le translation according to the bus configuration.
For example, snd_soc_bytes_put() uses regmap to write/read values,
and use cpu_to_be() directly to covert MASK into big endian. This
is a defect, and should use regmap's format function to do it according
to bus configuration.

Signed-off-by: Nenghua Cao <nhcao@marvell.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/base/regmap/regmap.c | 12 ++++++++++++
 include/linux/regmap.h       |  9 +++++++++
 2 files changed, 21 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 6a19515f8a45..4b2ed0c9e80d 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -2240,6 +2240,18 @@ int regmap_get_val_bytes(struct regmap *map)
 }
 EXPORT_SYMBOL_GPL(regmap_get_val_bytes);
 
+int regmap_parse_val(struct regmap *map, const void *buf,
+			unsigned int *val)
+{
+	if (!map->format.parse_val)
+		return -EINVAL;
+
+	*val = map->format.parse_val(buf);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(regmap_parse_val);
+
 static int __init regmap_initcall(void)
 {
 	regmap_debugfs_initcall();
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 4149f1a9b003..3e1a2e4a92ad 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -423,6 +423,8 @@ bool regmap_check_range_table(struct regmap *map, unsigned int reg,
 
 int regmap_register_patch(struct regmap *map, const struct reg_default *regs,
 			  int num_regs);
+int regmap_parse_val(struct regmap *map, const void *buf,
+				unsigned int *val);
 
 static inline bool regmap_reg_in_range(unsigned int reg,
 				       const struct regmap_range *range)
@@ -695,6 +697,13 @@ static inline int regmap_register_patch(struct regmap *map,
 	return -EINVAL;
 }
 
+static inline int regmap_parse_val(struct regmap *map, const void *buf,
+				unsigned int *val)
+{
+	WARN_ONCE(1, "regmap API is disabled");
+	return -EINVAL;
+}
+
 static inline struct regmap *dev_get_regmap(struct device *dev,
 					    const char *name)
 {
-- 
cgit v1.2.3


From 2f0aea9363609433b38ab13f0f86f38372668c68 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Tue, 4 Mar 2014 11:00:26 +0800
Subject: cpufreq: suspend governors on system suspend/hibernate

This patch adds cpufreq suspend/resume calls to dpm_{suspend|resume}()
for handling suspend/resume of cpufreq governors.

Lan Tianyu (Intel) & Jinhyuk Choi (Broadcom) found an issue where the
tunables configuration for clusters/sockets with non-boot CPUs was
lost after system suspend/resume, as we were notifying governors with
CPUFREQ_GOV_POLICY_EXIT on removal of the last CPU for that policy
which caused the tunables memory to be freed.

This is fixed by preventing any governor operations from being
carried out between the device suspend and device resume stages of
system suspend and resume, respectively.

We could have added these callbacks at dpm_{suspend|resume}_noirq()
level, but there is an additional problem that the majority of I/O
devices is already suspended at that point and if cpufreq drivers
want to change the frequency before suspending, then that not be
possible on some platforms (which depend on peripherals like i2c,
regulators, etc).

Reported-and-tested-by: Lan Tianyu <tianyu.lan@intel.com>
Reported-by: Jinhyuk Choi <jinchoi@broadcom.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
[rjw: Changelog]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/main.c |   5 +++
 drivers/cpufreq/cpufreq.c | 111 +++++++++++++++++++++++-----------------------
 include/linux/cpufreq.h   |   8 ++++
 3 files changed, 69 insertions(+), 55 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 1b41fca3d65a..c9fbb9d5484d 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -29,6 +29,7 @@
 #include <linux/async.h>
 #include <linux/suspend.h>
 #include <trace/events/power.h>
+#include <linux/cpufreq.h>
 #include <linux/cpuidle.h>
 #include <linux/timer.h>
 
@@ -789,6 +790,8 @@ void dpm_resume(pm_message_t state)
 	mutex_unlock(&dpm_list_mtx);
 	async_synchronize_full();
 	dpm_show_time(starttime, state, NULL);
+
+	cpufreq_resume();
 }
 
 /**
@@ -1259,6 +1262,8 @@ int dpm_suspend(pm_message_t state)
 
 	might_sleep();
 
+	cpufreq_suspend();
+
 	mutex_lock(&dpm_list_mtx);
 	pm_transition = state;
 	async_error = 0;
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 2de2f1ddd95f..289a407a9207 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -26,7 +26,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
-#include <linux/syscore_ops.h>
+#include <linux/suspend.h>
 #include <linux/tick.h>
 #include <trace/events/power.h>
 
@@ -45,6 +45,9 @@ static LIST_HEAD(cpufreq_policy_list);
 /* This one keeps track of the previously set governor of a removed CPU */
 static DEFINE_PER_CPU(char[CPUFREQ_NAME_LEN], cpufreq_cpu_governor);
 
+/* Flag to suspend/resume CPUFreq governors */
+static bool cpufreq_suspended;
+
 static inline bool has_target(void)
 {
 	return cpufreq_driver->target_index || cpufreq_driver->target;
@@ -1565,82 +1568,77 @@ static struct subsys_interface cpufreq_interface = {
 };
 
 /**
- * cpufreq_bp_suspend - Prepare the boot CPU for system suspend.
+ * cpufreq_suspend() - Suspend CPUFreq governors
  *
- * This function is only executed for the boot processor.  The other CPUs
- * have been put offline by means of CPU hotplug.
+ * Called during system wide Suspend/Hibernate cycles for suspending governors
+ * as some platforms can't change frequency after this point in suspend cycle.
+ * Because some of the devices (like: i2c, regulators, etc) they use for
+ * changing frequency are suspended quickly after this point.
  */
-static int cpufreq_bp_suspend(void)
+void cpufreq_suspend(void)
 {
-	int ret = 0;
-
-	int cpu = smp_processor_id();
 	struct cpufreq_policy *policy;
 
-	pr_debug("suspending cpu %u\n", cpu);
+	if (!cpufreq_driver)
+		return;
 
-	/* If there's no policy for the boot CPU, we have nothing to do. */
-	policy = cpufreq_cpu_get(cpu);
-	if (!policy)
-		return 0;
+	if (!has_target())
+		return;
 
-	if (cpufreq_driver->suspend) {
-		ret = cpufreq_driver->suspend(policy);
-		if (ret)
-			printk(KERN_ERR "cpufreq: suspend failed in ->suspend "
-					"step on CPU %u\n", policy->cpu);
+	pr_debug("%s: Suspending Governors\n", __func__);
+
+	list_for_each_entry(policy, &cpufreq_policy_list, policy_list) {
+		if (__cpufreq_governor(policy, CPUFREQ_GOV_STOP))
+			pr_err("%s: Failed to stop governor for policy: %p\n",
+				__func__, policy);
+		else if (cpufreq_driver->suspend
+		    && cpufreq_driver->suspend(policy))
+			pr_err("%s: Failed to suspend driver: %p\n", __func__,
+				policy);
 	}
 
-	cpufreq_cpu_put(policy);
-	return ret;
+	cpufreq_suspended = true;
 }
 
 /**
- * cpufreq_bp_resume - Restore proper frequency handling of the boot CPU.
+ * cpufreq_resume() - Resume CPUFreq governors
  *
- *	1.) resume CPUfreq hardware support (cpufreq_driver->resume())
- *	2.) schedule call cpufreq_update_policy() ASAP as interrupts are
- *	    restored. It will verify that the current freq is in sync with
- *	    what we believe it to be. This is a bit later than when it
- *	    should be, but nonethteless it's better than calling
- *	    cpufreq_driver->get() here which might re-enable interrupts...
- *
- * This function is only executed for the boot CPU.  The other CPUs have not
- * been turned on yet.
+ * Called during system wide Suspend/Hibernate cycle for resuming governors that
+ * are suspended with cpufreq_suspend().
  */
-static void cpufreq_bp_resume(void)
+void cpufreq_resume(void)
 {
-	int ret = 0;
-
-	int cpu = smp_processor_id();
 	struct cpufreq_policy *policy;
 
-	pr_debug("resuming cpu %u\n", cpu);
+	if (!cpufreq_driver)
+		return;
 
-	/* If there's no policy for the boot CPU, we have nothing to do. */
-	policy = cpufreq_cpu_get(cpu);
-	if (!policy)
+	if (!has_target())
 		return;
 
-	if (cpufreq_driver->resume) {
-		ret = cpufreq_driver->resume(policy);
-		if (ret) {
-			printk(KERN_ERR "cpufreq: resume failed in ->resume "
-					"step on CPU %u\n", policy->cpu);
-			goto fail;
-		}
-	}
+	pr_debug("%s: Resuming Governors\n", __func__);
 
-	schedule_work(&policy->update);
+	cpufreq_suspended = false;
 
-fail:
-	cpufreq_cpu_put(policy);
-}
+	list_for_each_entry(policy, &cpufreq_policy_list, policy_list) {
+		if (__cpufreq_governor(policy, CPUFREQ_GOV_START)
+		    || __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS))
+			pr_err("%s: Failed to start governor for policy: %p\n",
+				__func__, policy);
+		else if (cpufreq_driver->resume
+		    && cpufreq_driver->resume(policy))
+			pr_err("%s: Failed to resume driver: %p\n", __func__,
+				policy);
 
-static struct syscore_ops cpufreq_syscore_ops = {
-	.suspend	= cpufreq_bp_suspend,
-	.resume		= cpufreq_bp_resume,
-};
+		/*
+		 * schedule call cpufreq_update_policy() for boot CPU, i.e. last
+		 * policy in list. It will verify that the current freq is in
+		 * sync with what we believe it to be.
+		 */
+		if (list_is_last(&policy->policy_list, &cpufreq_policy_list))
+			schedule_work(&policy->update);
+	}
+}
 
 /**
  *	cpufreq_get_current_driver - return current driver's name
@@ -1857,6 +1855,10 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 	struct cpufreq_governor *gov = NULL;
 #endif
 
+	/* Don't start any governor operations if we are entering suspend */
+	if (cpufreq_suspended)
+		return 0;
+
 	if (policy->governor->max_transition_latency &&
 	    policy->cpuinfo.transition_latency >
 	    policy->governor->max_transition_latency) {
@@ -2392,7 +2394,6 @@ static int __init cpufreq_core_init(void)
 
 	cpufreq_global_kobject = kobject_create();
 	BUG_ON(!cpufreq_global_kobject);
-	register_syscore_ops(&cpufreq_syscore_ops);
 
 	return 0;
 }
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 4d89e0e6f9cc..94ed907c6999 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -296,6 +296,14 @@ cpufreq_verify_within_cpu_limits(struct cpufreq_policy *policy)
 			policy->cpuinfo.max_freq);
 }
 
+#ifdef CONFIG_CPU_FREQ
+void cpufreq_suspend(void);
+void cpufreq_resume(void);
+#else
+static inline void cpufreq_suspend(void) {}
+static inline void cpufreq_resume(void) {}
+#endif
+
 /*********************************************************************
  *                     CPUFREQ NOTIFIER INTERFACE                    *
  *********************************************************************/
-- 
cgit v1.2.3


From e28867eab7c0a60cddf0cb59f9f6cbbd9561425d Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Tue, 4 Mar 2014 11:00:27 +0800
Subject: cpufreq: Implement cpufreq_generic_suspend()

Multiple platforms need to set CPUs to a particular frequency before
suspending the system, so provide a common infrastructure for them.

Those platforms only need to point their ->suspend callback pointers
to the generic routine.

Tested-by: Stephen Warren <swarren@nvidia.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
[rjw: Changelog]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cpufreq.c | 26 ++++++++++++++++++++++++++
 include/linux/cpufreq.h   |  3 +++
 2 files changed, 29 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 289a407a9207..61dd72b8c143 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1567,6 +1567,32 @@ static struct subsys_interface cpufreq_interface = {
 	.remove_dev	= cpufreq_remove_dev,
 };
 
+/*
+ * In case platform wants some specific frequency to be configured
+ * during suspend..
+ */
+int cpufreq_generic_suspend(struct cpufreq_policy *policy)
+{
+	int ret;
+
+	if (!policy->suspend_freq) {
+		pr_err("%s: suspend_freq can't be zero\n", __func__);
+		return -EINVAL;
+	}
+
+	pr_debug("%s: Setting suspend-freq: %u\n", __func__,
+			policy->suspend_freq);
+
+	ret = __cpufreq_driver_target(policy, policy->suspend_freq,
+			CPUFREQ_RELATION_H);
+	if (ret)
+		pr_err("%s: unable to set suspend-freq: %u. err: %d\n",
+				__func__, policy->suspend_freq, ret);
+
+	return ret;
+}
+EXPORT_SYMBOL(cpufreq_generic_suspend);
+
 /**
  * cpufreq_suspend() - Suspend CPUFreq governors
  *
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 94ed907c6999..325bab04271b 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -74,6 +74,8 @@ struct cpufreq_policy {
 	unsigned int		max;    /* in kHz */
 	unsigned int		cur;    /* in kHz, only needed if cpufreq
 					 * governors are used */
+	unsigned int		suspend_freq; /* freq to set during suspend */
+
 	unsigned int		policy; /* see above */
 	struct cpufreq_governor	*governor; /* see below */
 	void			*governor_data;
@@ -299,6 +301,7 @@ cpufreq_verify_within_cpu_limits(struct cpufreq_policy *policy)
 #ifdef CONFIG_CPU_FREQ
 void cpufreq_suspend(void);
 void cpufreq_resume(void);
+int cpufreq_generic_suspend(struct cpufreq_policy *policy);
 #else
 static inline void cpufreq_suspend(void) {}
 static inline void cpufreq_resume(void) {}
-- 
cgit v1.2.3


From 7cbccb55f04bef306bc2840185ec8f986bd0df3c Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Sun, 16 Feb 2014 14:21:22 +0100
Subject: dma: Remove comment about embedding dma_slave_config into custom
 structs

The documentation for the dma_slave_config struct recommends that if a DMA
controller has special configuration options, which can not be configured
through the dma_slave_config struct, the driver should create its own custom
config struct and embed the dma_slave_config struct in it and pass the custom
config struct to dmaengine_slave_config(). This overloads the generic
dmaengine_slave_config() API with custom semantics and any caller of the
dmaengine_slave_config() that is not aware of these special semantics will cause
undefined behavior. This means that it is impossible for generic code to make
use of dmaengine_slave_config(). Such a restriction contradicts the very idea of
having a generic API.

E.g. consider the following case of a DMA controller that has an option to
reverse the field polarity of the DMA transfer with the following implementation
for setting the configuration:

	struct my_slave_config {
		struct dma_slave_config config;
		unsigned int field_polarity;
	};

	static int my_dma_controller_slave_config(struct dma_chan *chan,
		struct dma_slave_config *config)
	{
		struct my_slave_config *my_cfg = container_of(config,
				struct my_slave_config, config);

		...
		my_dma_set_field_polarity(chan, my_cfg->field_polarity);
		...
	}

Now a generic user of the dmaengine API might want to configure a DMA channel
for this DMA controller that it obtained using the following code:

	struct dma_slave_config config;

	config.src_addr = ...;
	...
	dmaengine_slave_config(chan, &config);

The call to dmaengine_slave_config() will eventually call into
my_dma_controller_slave_config() which will cast from dma_slave_config to
my_slave_config and then tries to access the field_polarity member. Since the
dma_slave_config struct that was passed in was never embedded into a
my_slave_config struct this attempt will just read random stack garbage and use
that to configure the DMA controller. This is bad. Instead, if a DMA controller
really needs to have custom configuration options, the driver should create a
custom API for it. This makes it very clear that there is a direct dependency
of a user of such an API and the implementer. E.g.:

	int my_dma_set_field_polarity(struct dma_chan *chan,
		unsigned int field_polarity) {
		if (chan->device->dev->driver != &my_dma_controller_driver.driver)
			return -EINVAL;
		...
	}
	EXPORT_SYMBOL_GPL(my_dma_set_field_polarity);

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 include/linux/dmaengine.h | 14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index c5c92d59e531..8300fb87b84a 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -341,15 +341,11 @@ enum dma_slave_buswidth {
  * and this struct will then be passed in as an argument to the
  * DMA engine device_control() function.
  *
- * The rationale for adding configuration information to this struct
- * is as follows: if it is likely that most DMA slave controllers in
- * the world will support the configuration option, then make it
- * generic. If not: if it is fixed so that it be sent in static from
- * the platform data, then prefer to do that. Else, if it is neither
- * fixed at runtime, nor generic enough (such as bus mastership on
- * some CPU family and whatnot) then create a custom slave config
- * struct and pass that, then make this config a member of that
- * struct, if applicable.
+ * The rationale for adding configuration information to this struct is as
+ * follows: if it is likely that more than one DMA slave controllers in
+ * the world will support the configuration option, then make it generic.
+ * If not: if it is fixed so that it be sent in static from the platform
+ * data, then prefer to do that.
  */
 struct dma_slave_config {
 	enum dma_transfer_direction direction;
-- 
cgit v1.2.3


From fd9fdb78a9bf85b94fb2190c82ff280c8f8375cc Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Mon, 10 Feb 2014 22:01:48 +0100
Subject: [media] of: move graph helpers from drivers/media/v4l2-core to
 drivers/of

This patch moves the parsing helpers used to parse connected graphs
in the device tree, like the video interface bindings documented in
Documentation/devicetree/bindings/media/video-interfaces.txt, from
drivers/media/v4l2-core/v4l2-of.c into drivers/of/base.c.

This allows to reuse the same parser code from outside the V4L2
framework, most importantly from display drivers.
The functions v4l2_of_get_next_endpoint, v4l2_of_get_remote_port,
and v4l2_of_get_remote_port_parent are moved. They are renamed to
of_graph_get_next_endpoint, of_graph_get_remote_port, and
of_graph_get_remote_port_parent, respectively.
Since there are not that many current users yet, switch all of
them to the new functions right away.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Acked-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Acked-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
Acked-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
---
 drivers/media/i2c/adv7343.c                   |   4 +-
 drivers/media/i2c/mt9p031.c                   |   4 +-
 drivers/media/i2c/s5k5baf.c                   |   3 +-
 drivers/media/i2c/tvp514x.c                   |   3 +-
 drivers/media/i2c/tvp7002.c                   |   3 +-
 drivers/media/platform/exynos4-is/fimc-is.c   |   6 +-
 drivers/media/platform/exynos4-is/media-dev.c |   3 +-
 drivers/media/platform/exynos4-is/mipi-csis.c |   3 +-
 drivers/media/v4l2-core/v4l2-of.c             | 117 -------------------------
 drivers/of/base.c                             | 118 ++++++++++++++++++++++++++
 include/linux/of_graph.h                      |  46 ++++++++++
 include/media/v4l2-of.h                       |  25 +-----
 12 files changed, 182 insertions(+), 153 deletions(-)
 create mode 100644 include/linux/of_graph.h

(limited to 'include/linux')

diff --git a/drivers/media/i2c/adv7343.c b/drivers/media/i2c/adv7343.c
index d4e15a617c3b..9d38f7b36cd1 100644
--- a/drivers/media/i2c/adv7343.c
+++ b/drivers/media/i2c/adv7343.c
@@ -26,12 +26,12 @@
 #include <linux/videodev2.h>
 #include <linux/uaccess.h>
 #include <linux/of.h>
+#include <linux/of_graph.h>
 
 #include <media/adv7343.h>
 #include <media/v4l2-async.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-ctrls.h>
-#include <media/v4l2-of.h>
 
 #include "adv7343_regs.h"
 
@@ -410,7 +410,7 @@ adv7343_get_pdata(struct i2c_client *client)
 	if (!IS_ENABLED(CONFIG_OF) || !client->dev.of_node)
 		return client->dev.platform_data;
 
-	np = v4l2_of_get_next_endpoint(client->dev.of_node, NULL);
+	np = of_graph_get_next_endpoint(client->dev.of_node, NULL);
 	if (!np)
 		return NULL;
 
diff --git a/drivers/media/i2c/mt9p031.c b/drivers/media/i2c/mt9p031.c
index e5ddf47030fd..192c4aad05d6 100644
--- a/drivers/media/i2c/mt9p031.c
+++ b/drivers/media/i2c/mt9p031.c
@@ -21,6 +21,7 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_gpio.h>
+#include <linux/of_graph.h>
 #include <linux/pm.h>
 #include <linux/regulator/consumer.h>
 #include <linux/slab.h>
@@ -29,7 +30,6 @@
 #include <media/mt9p031.h>
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
-#include <media/v4l2-of.h>
 #include <media/v4l2-subdev.h>
 
 #include "aptina-pll.h"
@@ -943,7 +943,7 @@ mt9p031_get_pdata(struct i2c_client *client)
 	if (!IS_ENABLED(CONFIG_OF) || !client->dev.of_node)
 		return client->dev.platform_data;
 
-	np = v4l2_of_get_next_endpoint(client->dev.of_node, NULL);
+	np = of_graph_get_next_endpoint(client->dev.of_node, NULL);
 	if (!np)
 		return NULL;
 
diff --git a/drivers/media/i2c/s5k5baf.c b/drivers/media/i2c/s5k5baf.c
index 77e10e0fd8d6..2d768ef67cc5 100644
--- a/drivers/media/i2c/s5k5baf.c
+++ b/drivers/media/i2c/s5k5baf.c
@@ -21,6 +21,7 @@
 #include <linux/media.h>
 #include <linux/module.h>
 #include <linux/of_gpio.h>
+#include <linux/of_graph.h>
 #include <linux/regulator/consumer.h>
 #include <linux/slab.h>
 
@@ -1855,7 +1856,7 @@ static int s5k5baf_parse_device_node(struct s5k5baf *state, struct device *dev)
 	if (ret < 0)
 		return ret;
 
-	node_ep = v4l2_of_get_next_endpoint(node, NULL);
+	node_ep = of_graph_get_next_endpoint(node, NULL);
 	if (!node_ep) {
 		dev_err(dev, "no endpoint defined at node %s\n",
 			node->full_name);
diff --git a/drivers/media/i2c/tvp514x.c b/drivers/media/i2c/tvp514x.c
index 83d85df4853a..ca001178c5bf 100644
--- a/drivers/media/i2c/tvp514x.c
+++ b/drivers/media/i2c/tvp514x.c
@@ -36,6 +36,7 @@
 #include <linux/module.h>
 #include <linux/v4l2-mediabus.h>
 #include <linux/of.h>
+#include <linux/of_graph.h>
 
 #include <media/v4l2-async.h>
 #include <media/v4l2-device.h>
@@ -1068,7 +1069,7 @@ tvp514x_get_pdata(struct i2c_client *client)
 	if (!IS_ENABLED(CONFIG_OF) || !client->dev.of_node)
 		return client->dev.platform_data;
 
-	endpoint = v4l2_of_get_next_endpoint(client->dev.of_node, NULL);
+	endpoint = of_graph_get_next_endpoint(client->dev.of_node, NULL);
 	if (!endpoint)
 		return NULL;
 
diff --git a/drivers/media/i2c/tvp7002.c b/drivers/media/i2c/tvp7002.c
index 912e1cccdd1c..c4e1e2cb3094 100644
--- a/drivers/media/i2c/tvp7002.c
+++ b/drivers/media/i2c/tvp7002.c
@@ -30,6 +30,7 @@
 #include <linux/videodev2.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_graph.h>
 #include <linux/v4l2-dv-timings.h>
 #include <media/tvp7002.h>
 #include <media/v4l2-async.h>
@@ -957,7 +958,7 @@ tvp7002_get_pdata(struct i2c_client *client)
 	if (!IS_ENABLED(CONFIG_OF) || !client->dev.of_node)
 		return client->dev.platform_data;
 
-	endpoint = v4l2_of_get_next_endpoint(client->dev.of_node, NULL);
+	endpoint = of_graph_get_next_endpoint(client->dev.of_node, NULL);
 	if (!endpoint)
 		return NULL;
 
diff --git a/drivers/media/platform/exynos4-is/fimc-is.c b/drivers/media/platform/exynos4-is/fimc-is.c
index 13a4228952e3..9bdfa4599bc3 100644
--- a/drivers/media/platform/exynos4-is/fimc-is.c
+++ b/drivers/media/platform/exynos4-is/fimc-is.c
@@ -24,13 +24,13 @@
 #include <linux/i2c.h>
 #include <linux/of_irq.h>
 #include <linux/of_address.h>
+#include <linux/of_graph.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/videodev2.h>
-#include <media/v4l2-of.h>
 #include <media/videobuf2-dma-contig.h>
 
 #include "media-dev.h"
@@ -167,10 +167,10 @@ static int fimc_is_parse_sensor_config(struct fimc_is_sensor *sensor,
 	u32 tmp = 0;
 	int ret;
 
-	np = v4l2_of_get_next_endpoint(np, NULL);
+	np = of_graph_get_next_endpoint(np, NULL);
 	if (!np)
 		return -ENXIO;
-	np = v4l2_of_get_remote_port(np);
+	np = of_graph_get_remote_port(np);
 	if (!np)
 		return -ENXIO;
 
diff --git a/drivers/media/platform/exynos4-is/media-dev.c b/drivers/media/platform/exynos4-is/media-dev.c
index c1bce170df6f..d0f82da59ac5 100644
--- a/drivers/media/platform/exynos4-is/media-dev.c
+++ b/drivers/media/platform/exynos4-is/media-dev.c
@@ -20,6 +20,7 @@
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/of_device.h>
+#include <linux/of_graph.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/types.h>
@@ -473,7 +474,7 @@ static int fimc_md_parse_port_node(struct fimc_md *fmd,
 
 	pd->mux_id = (endpoint.port - 1) & 0x1;
 
-	rem = v4l2_of_get_remote_port_parent(ep);
+	rem = of_graph_get_remote_port_parent(ep);
 	of_node_put(ep);
 	if (rem == NULL) {
 		v4l2_info(&fmd->v4l2_dev, "Remote device at %s not found\n",
diff --git a/drivers/media/platform/exynos4-is/mipi-csis.c b/drivers/media/platform/exynos4-is/mipi-csis.c
index f3c3591fdc5d..fd1ae6549607 100644
--- a/drivers/media/platform/exynos4-is/mipi-csis.c
+++ b/drivers/media/platform/exynos4-is/mipi-csis.c
@@ -20,6 +20,7 @@
 #include <linux/memory.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_graph.h>
 #include <linux/phy/phy.h>
 #include <linux/platform_data/mipi-csis.h>
 #include <linux/platform_device.h>
@@ -762,7 +763,7 @@ static int s5pcsis_parse_dt(struct platform_device *pdev,
 				 &state->max_num_lanes))
 		return -EINVAL;
 
-	node = v4l2_of_get_next_endpoint(node, NULL);
+	node = of_graph_get_next_endpoint(node, NULL);
 	if (!node) {
 		dev_err(&pdev->dev, "No port node at %s\n",
 				pdev->dev.of_node->full_name);
diff --git a/drivers/media/v4l2-core/v4l2-of.c b/drivers/media/v4l2-core/v4l2-of.c
index 42e3e8a5e361..f919db358bbe 100644
--- a/drivers/media/v4l2-core/v4l2-of.c
+++ b/drivers/media/v4l2-core/v4l2-of.c
@@ -152,120 +152,3 @@ int v4l2_of_parse_endpoint(const struct device_node *node,
 	return 0;
 }
 EXPORT_SYMBOL(v4l2_of_parse_endpoint);
-
-/**
- * v4l2_of_get_next_endpoint() - get next endpoint node
- * @parent: pointer to the parent device node
- * @prev: previous endpoint node, or NULL to get first
- *
- * Return: An 'endpoint' node pointer with refcount incremented. Refcount
- * of the passed @prev node is not decremented, the caller have to use
- * of_node_put() on it when done.
- */
-struct device_node *v4l2_of_get_next_endpoint(const struct device_node *parent,
-					struct device_node *prev)
-{
-	struct device_node *endpoint;
-	struct device_node *port = NULL;
-
-	if (!parent)
-		return NULL;
-
-	if (!prev) {
-		struct device_node *node;
-		/*
-		 * It's the first call, we have to find a port subnode
-		 * within this node or within an optional 'ports' node.
-		 */
-		node = of_get_child_by_name(parent, "ports");
-		if (node)
-			parent = node;
-
-		port = of_get_child_by_name(parent, "port");
-
-		if (port) {
-			/* Found a port, get an endpoint. */
-			endpoint = of_get_next_child(port, NULL);
-			of_node_put(port);
-		} else {
-			endpoint = NULL;
-		}
-
-		if (!endpoint)
-			pr_err("%s(): no endpoint nodes specified for %s\n",
-			       __func__, parent->full_name);
-		of_node_put(node);
-	} else {
-		port = of_get_parent(prev);
-		if (!port)
-			/* Hm, has someone given us the root node ?... */
-			return NULL;
-
-		/* Avoid dropping prev node refcount to 0. */
-		of_node_get(prev);
-		endpoint = of_get_next_child(port, prev);
-		if (endpoint) {
-			of_node_put(port);
-			return endpoint;
-		}
-
-		/* No more endpoints under this port, try the next one. */
-		do {
-			port = of_get_next_child(parent, port);
-			if (!port)
-				return NULL;
-		} while (of_node_cmp(port->name, "port"));
-
-		/* Pick up the first endpoint in this port. */
-		endpoint = of_get_next_child(port, NULL);
-		of_node_put(port);
-	}
-
-	return endpoint;
-}
-EXPORT_SYMBOL(v4l2_of_get_next_endpoint);
-
-/**
- * v4l2_of_get_remote_port_parent() - get remote port's parent node
- * @node: pointer to a local endpoint device_node
- *
- * Return: Remote device node associated with remote endpoint node linked
- *	   to @node. Use of_node_put() on it when done.
- */
-struct device_node *v4l2_of_get_remote_port_parent(
-			       const struct device_node *node)
-{
-	struct device_node *np;
-	unsigned int depth;
-
-	/* Get remote endpoint node. */
-	np = of_parse_phandle(node, "remote-endpoint", 0);
-
-	/* Walk 3 levels up only if there is 'ports' node. */
-	for (depth = 3; depth && np; depth--) {
-		np = of_get_next_parent(np);
-		if (depth == 2 && of_node_cmp(np->name, "ports"))
-			break;
-	}
-	return np;
-}
-EXPORT_SYMBOL(v4l2_of_get_remote_port_parent);
-
-/**
- * v4l2_of_get_remote_port() - get remote port node
- * @node: pointer to a local endpoint device_node
- *
- * Return: Remote port node associated with remote endpoint node linked
- *	   to @node. Use of_node_put() on it when done.
- */
-struct device_node *v4l2_of_get_remote_port(const struct device_node *node)
-{
-	struct device_node *np;
-
-	/* Get remote endpoint node. */
-	np = of_parse_phandle(node, "remote-endpoint", 0);
-	if (!np)
-		return NULL;
-	return of_get_next_parent(np);
-}
-EXPORT_SYMBOL(v4l2_of_get_remote_port);
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 89e888a78899..b2f223fa47e9 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -21,6 +21,7 @@
 #include <linux/cpu.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_graph.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/proc_fs.h>
@@ -1982,3 +1983,120 @@ struct device_node *of_find_next_cache_node(const struct device_node *np)
 
 	return NULL;
 }
+
+/**
+ * of_graph_get_next_endpoint() - get next endpoint node
+ * @parent: pointer to the parent device node
+ * @prev: previous endpoint node, or NULL to get first
+ *
+ * Return: An 'endpoint' node pointer with refcount incremented. Refcount
+ * of the passed @prev node is not decremented, the caller have to use
+ * of_node_put() on it when done.
+ */
+struct device_node *of_graph_get_next_endpoint(const struct device_node *parent,
+					struct device_node *prev)
+{
+	struct device_node *endpoint;
+	struct device_node *port = NULL;
+
+	if (!parent)
+		return NULL;
+
+	if (!prev) {
+		struct device_node *node;
+		/*
+		 * It's the first call, we have to find a port subnode
+		 * within this node or within an optional 'ports' node.
+		 */
+		node = of_get_child_by_name(parent, "ports");
+		if (node)
+			parent = node;
+
+		port = of_get_child_by_name(parent, "port");
+
+		if (port) {
+			/* Found a port, get an endpoint. */
+			endpoint = of_get_next_child(port, NULL);
+			of_node_put(port);
+		} else {
+			endpoint = NULL;
+		}
+
+		if (!endpoint)
+			pr_err("%s(): no endpoint nodes specified for %s\n",
+			       __func__, parent->full_name);
+		of_node_put(node);
+	} else {
+		port = of_get_parent(prev);
+		if (!port)
+			/* Hm, has someone given us the root node ?... */
+			return NULL;
+
+		/* Avoid dropping prev node refcount to 0. */
+		of_node_get(prev);
+		endpoint = of_get_next_child(port, prev);
+		if (endpoint) {
+			of_node_put(port);
+			return endpoint;
+		}
+
+		/* No more endpoints under this port, try the next one. */
+		do {
+			port = of_get_next_child(parent, port);
+			if (!port)
+				return NULL;
+		} while (of_node_cmp(port->name, "port"));
+
+		/* Pick up the first endpoint in this port. */
+		endpoint = of_get_next_child(port, NULL);
+		of_node_put(port);
+	}
+
+	return endpoint;
+}
+EXPORT_SYMBOL(of_graph_get_next_endpoint);
+
+/**
+ * of_graph_get_remote_port_parent() - get remote port's parent node
+ * @node: pointer to a local endpoint device_node
+ *
+ * Return: Remote device node associated with remote endpoint node linked
+ *	   to @node. Use of_node_put() on it when done.
+ */
+struct device_node *of_graph_get_remote_port_parent(
+			       const struct device_node *node)
+{
+	struct device_node *np;
+	unsigned int depth;
+
+	/* Get remote endpoint node. */
+	np = of_parse_phandle(node, "remote-endpoint", 0);
+
+	/* Walk 3 levels up only if there is 'ports' node. */
+	for (depth = 3; depth && np; depth--) {
+		np = of_get_next_parent(np);
+		if (depth == 2 && of_node_cmp(np->name, "ports"))
+			break;
+	}
+	return np;
+}
+EXPORT_SYMBOL(of_graph_get_remote_port_parent);
+
+/**
+ * of_graph_get_remote_port() - get remote port node
+ * @node: pointer to a local endpoint device_node
+ *
+ * Return: Remote port node associated with remote endpoint node linked
+ *	   to @node. Use of_node_put() on it when done.
+ */
+struct device_node *of_graph_get_remote_port(const struct device_node *node)
+{
+	struct device_node *np;
+
+	/* Get remote endpoint node. */
+	np = of_parse_phandle(node, "remote-endpoint", 0);
+	if (!np)
+		return NULL;
+	return of_get_next_parent(np);
+}
+EXPORT_SYMBOL(of_graph_get_remote_port);
diff --git a/include/linux/of_graph.h b/include/linux/of_graph.h
new file mode 100644
index 000000000000..3bbeb609a360
--- /dev/null
+++ b/include/linux/of_graph.h
@@ -0,0 +1,46 @@
+/*
+ * OF graph binding parsing helpers
+ *
+ * Copyright (C) 2012 - 2013 Samsung Electronics Co., Ltd.
+ * Author: Sylwester Nawrocki <s.nawrocki@samsung.com>
+ *
+ * Copyright (C) 2012 Renesas Electronics Corp.
+ * Author: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ */
+#ifndef __LINUX_OF_GRAPH_H
+#define __LINUX_OF_GRAPH_H
+
+#ifdef CONFIG_OF
+struct device_node *of_graph_get_next_endpoint(const struct device_node *parent,
+					struct device_node *previous);
+struct device_node *of_graph_get_remote_port_parent(
+					const struct device_node *node);
+struct device_node *of_graph_get_remote_port(const struct device_node *node);
+#else
+
+static inline struct device_node *of_graph_get_next_endpoint(
+					const struct device_node *parent,
+					struct device_node *previous)
+{
+	return NULL;
+}
+
+static inline struct device_node *of_graph_get_remote_port_parent(
+					const struct device_node *node)
+{
+	return NULL;
+}
+
+static inline struct device_node *of_graph_get_remote_port(
+					const struct device_node *node)
+{
+	return NULL;
+}
+
+#endif /* CONFIG_OF */
+
+#endif /* __LINUX_OF_GRAPH_H */
diff --git a/include/media/v4l2-of.h b/include/media/v4l2-of.h
index 541cea4122e9..3a49735c56a0 100644
--- a/include/media/v4l2-of.h
+++ b/include/media/v4l2-of.h
@@ -17,6 +17,7 @@
 #include <linux/list.h>
 #include <linux/types.h>
 #include <linux/errno.h>
+#include <linux/of_graph.h>
 
 #include <media/v4l2-mediabus.h>
 
@@ -72,11 +73,6 @@ struct v4l2_of_endpoint {
 #ifdef CONFIG_OF
 int v4l2_of_parse_endpoint(const struct device_node *node,
 			   struct v4l2_of_endpoint *endpoint);
-struct device_node *v4l2_of_get_next_endpoint(const struct device_node *parent,
-					struct device_node *previous);
-struct device_node *v4l2_of_get_remote_port_parent(
-					const struct device_node *node);
-struct device_node *v4l2_of_get_remote_port(const struct device_node *node);
 #else /* CONFIG_OF */
 
 static inline int v4l2_of_parse_endpoint(const struct device_node *node,
@@ -85,25 +81,6 @@ static inline int v4l2_of_parse_endpoint(const struct device_node *node,
 	return -ENOSYS;
 }
 
-static inline struct device_node *v4l2_of_get_next_endpoint(
-					const struct device_node *parent,
-					struct device_node *previous)
-{
-	return NULL;
-}
-
-static inline struct device_node *v4l2_of_get_remote_port_parent(
-					const struct device_node *node)
-{
-	return NULL;
-}
-
-static inline struct device_node *v4l2_of_get_remote_port(
-					const struct device_node *node)
-{
-	return NULL;
-}
-
 #endif /* CONFIG_OF */
 
 #endif /* _V4L2_OF_H */
-- 
cgit v1.2.3


From f2a575f67695dcba9062acd666ae5aab2380b95c Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Fri, 14 Feb 2014 11:53:56 +0100
Subject: [media] of: move common endpoint parsing to drivers/of

This patch adds a new struct of_endpoint which is then embedded in struct
v4l2_of_endpoint and contains the endpoint properties that are not V4L2
(or even media) specific: the port number, endpoint id, local device tree
node and remote endpoint phandle. of_graph_parse_endpoint parses those
properties and is used by v4l2_of_parse_endpoint, which just adds the
V4L2 MBUS information to the containing v4l2_of_endpoint structure.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Acked-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Acked-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
Acked-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
---
 drivers/media/platform/exynos4-is/media-dev.c | 10 +++++-----
 drivers/media/platform/exynos4-is/mipi-csis.c |  2 +-
 drivers/media/v4l2-core/v4l2-of.c             | 16 +++------------
 drivers/of/base.c                             | 28 +++++++++++++++++++++++++++
 include/linux/of_graph.h                      | 20 +++++++++++++++++++
 include/media/v4l2-of.h                       |  8 ++------
 6 files changed, 59 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/media/platform/exynos4-is/media-dev.c b/drivers/media/platform/exynos4-is/media-dev.c
index d0f82da59ac5..04d6ecdd314c 100644
--- a/drivers/media/platform/exynos4-is/media-dev.c
+++ b/drivers/media/platform/exynos4-is/media-dev.c
@@ -469,10 +469,10 @@ static int fimc_md_parse_port_node(struct fimc_md *fmd,
 		return 0;
 
 	v4l2_of_parse_endpoint(ep, &endpoint);
-	if (WARN_ON(endpoint.port == 0) || index >= FIMC_MAX_SENSORS)
+	if (WARN_ON(endpoint.base.port == 0) || index >= FIMC_MAX_SENSORS)
 		return -EINVAL;
 
-	pd->mux_id = (endpoint.port - 1) & 0x1;
+	pd->mux_id = (endpoint.base.port - 1) & 0x1;
 
 	rem = of_graph_get_remote_port_parent(ep);
 	of_node_put(ep);
@@ -494,13 +494,13 @@ static int fimc_md_parse_port_node(struct fimc_md *fmd,
 		return -EINVAL;
 	}
 
-	if (fimc_input_is_parallel(endpoint.port)) {
+	if (fimc_input_is_parallel(endpoint.base.port)) {
 		if (endpoint.bus_type == V4L2_MBUS_PARALLEL)
 			pd->sensor_bus_type = FIMC_BUS_TYPE_ITU_601;
 		else
 			pd->sensor_bus_type = FIMC_BUS_TYPE_ITU_656;
 		pd->flags = endpoint.bus.parallel.flags;
-	} else if (fimc_input_is_mipi_csi(endpoint.port)) {
+	} else if (fimc_input_is_mipi_csi(endpoint.base.port)) {
 		/*
 		 * MIPI CSI-2: only input mux selection and
 		 * the sensor's clock frequency is needed.
@@ -508,7 +508,7 @@ static int fimc_md_parse_port_node(struct fimc_md *fmd,
 		pd->sensor_bus_type = FIMC_BUS_TYPE_MIPI_CSI2;
 	} else {
 		v4l2_err(&fmd->v4l2_dev, "Wrong port id (%u) at node %s\n",
-			 endpoint.port, rem->full_name);
+			 endpoint.base.port, rem->full_name);
 	}
 	/*
 	 * For FIMC-IS handled sensors, that are placed under i2c-isp device
diff --git a/drivers/media/platform/exynos4-is/mipi-csis.c b/drivers/media/platform/exynos4-is/mipi-csis.c
index fd1ae6549607..3678ba59725c 100644
--- a/drivers/media/platform/exynos4-is/mipi-csis.c
+++ b/drivers/media/platform/exynos4-is/mipi-csis.c
@@ -772,7 +772,7 @@ static int s5pcsis_parse_dt(struct platform_device *pdev,
 	/* Get port node and validate MIPI-CSI channel id. */
 	v4l2_of_parse_endpoint(node, &endpoint);
 
-	state->index = endpoint.port - FIMC_INPUT_MIPI_CSI2_0;
+	state->index = endpoint.base.port - FIMC_INPUT_MIPI_CSI2_0;
 	if (state->index < 0 || state->index >= CSIS_MAX_ENTITIES)
 		return -ENXIO;
 
diff --git a/drivers/media/v4l2-core/v4l2-of.c b/drivers/media/v4l2-core/v4l2-of.c
index f919db358bbe..b4ed9a955fbe 100644
--- a/drivers/media/v4l2-core/v4l2-of.c
+++ b/drivers/media/v4l2-core/v4l2-of.c
@@ -127,17 +127,9 @@ static void v4l2_of_parse_parallel_bus(const struct device_node *node,
 int v4l2_of_parse_endpoint(const struct device_node *node,
 			   struct v4l2_of_endpoint *endpoint)
 {
-	struct device_node *port_node = of_get_parent(node);
-
-	memset(endpoint, 0, offsetof(struct v4l2_of_endpoint, head));
-
-	endpoint->local_node = node;
-	/*
-	 * It doesn't matter whether the two calls below succeed.
-	 * If they don't then the default value 0 is used.
-	 */
-	of_property_read_u32(port_node, "reg", &endpoint->port);
-	of_property_read_u32(node, "reg", &endpoint->id);
+	of_graph_parse_endpoint(node, &endpoint->base);
+	endpoint->bus_type = 0;
+	memset(&endpoint->bus, 0, sizeof(endpoint->bus));
 
 	v4l2_of_parse_csi_bus(node, endpoint);
 	/*
@@ -147,8 +139,6 @@ int v4l2_of_parse_endpoint(const struct device_node *node,
 	if (endpoint->bus.mipi_csi2.flags == 0)
 		v4l2_of_parse_parallel_bus(node, endpoint);
 
-	of_node_put(port_node);
-
 	return 0;
 }
 EXPORT_SYMBOL(v4l2_of_parse_endpoint);
diff --git a/drivers/of/base.c b/drivers/of/base.c
index a8e47d37cc7f..715144af3a83 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -1984,6 +1984,34 @@ struct device_node *of_find_next_cache_node(const struct device_node *np)
 	return NULL;
 }
 
+/**
+ * of_graph_parse_endpoint() - parse common endpoint node properties
+ * @node: pointer to endpoint device_node
+ * @endpoint: pointer to the OF endpoint data structure
+ *
+ * The caller should hold a reference to @node.
+ */
+int of_graph_parse_endpoint(const struct device_node *node,
+			    struct of_endpoint *endpoint)
+{
+	struct device_node *port_node = of_get_parent(node);
+
+	memset(endpoint, 0, sizeof(*endpoint));
+
+	endpoint->local_node = node;
+	/*
+	 * It doesn't matter whether the two calls below succeed.
+	 * If they don't then the default value 0 is used.
+	 */
+	of_property_read_u32(port_node, "reg", &endpoint->port);
+	of_property_read_u32(node, "reg", &endpoint->id);
+
+	of_node_put(port_node);
+
+	return 0;
+}
+EXPORT_SYMBOL(of_graph_parse_endpoint);
+
 /**
  * of_graph_get_next_endpoint() - get next endpoint node
  * @parent: pointer to the parent device node
diff --git a/include/linux/of_graph.h b/include/linux/of_graph.h
index 3bbeb609a360..2b233db76237 100644
--- a/include/linux/of_graph.h
+++ b/include/linux/of_graph.h
@@ -14,7 +14,21 @@
 #ifndef __LINUX_OF_GRAPH_H
 #define __LINUX_OF_GRAPH_H
 
+/**
+ * struct of_endpoint - the OF graph endpoint data structure
+ * @port: identifier (value of reg property) of a port this endpoint belongs to
+ * @id: identifier (value of reg property) of this endpoint
+ * @local_node: pointer to device_node of this endpoint
+ */
+struct of_endpoint {
+	unsigned int port;
+	unsigned int id;
+	const struct device_node *local_node;
+};
+
 #ifdef CONFIG_OF
+int of_graph_parse_endpoint(const struct device_node *node,
+				struct of_endpoint *endpoint);
 struct device_node *of_graph_get_next_endpoint(const struct device_node *parent,
 					struct device_node *previous);
 struct device_node *of_graph_get_remote_port_parent(
@@ -22,6 +36,12 @@ struct device_node *of_graph_get_remote_port_parent(
 struct device_node *of_graph_get_remote_port(const struct device_node *node);
 #else
 
+static inline int of_graph_parse_endpoint(const struct device_node *node,
+					struct of_endpoint *endpoint);
+{
+	return -ENOSYS;
+}
+
 static inline struct device_node *of_graph_get_next_endpoint(
 					const struct device_node *parent,
 					struct device_node *previous)
diff --git a/include/media/v4l2-of.h b/include/media/v4l2-of.h
index 3a49735c56a0..70fa7b7b0487 100644
--- a/include/media/v4l2-of.h
+++ b/include/media/v4l2-of.h
@@ -51,17 +51,13 @@ struct v4l2_of_bus_parallel {
 
 /**
  * struct v4l2_of_endpoint - the endpoint data structure
- * @port: identifier (value of reg property) of a port this endpoint belongs to
- * @id: identifier (value of reg property) of this endpoint
- * @local_node: pointer to device_node of this endpoint
+ * @base: struct of_endpoint containing port, id, and local of_node
  * @bus_type: bus type
  * @bus: bus configuration data structure
  * @head: list head for this structure
  */
 struct v4l2_of_endpoint {
-	unsigned int port;
-	unsigned int id;
-	const struct device_node *local_node;
+	struct of_endpoint base;
 	enum v4l2_mbus_type bus_type;
 	union {
 		struct v4l2_of_bus_parallel parallel;
-- 
cgit v1.2.3


From 9859ccd2c8be63ce939522e63e265f2b0caa1109 Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Fri, 28 Feb 2014 16:36:23 +0100
Subject: can: introduce the data bitrate configuration for CAN FD

As CAN FD offers a second bitrate for the data section of the CAN frame the
infrastructure for storing and configuring this second bitrate is introduced.
Improved the readability of the if-statement by inserting some newlines.

Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Acked-by: Stephane Grosjean <s.grosjean@peak-system.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dev.c            | 45 +++++++++++++++++++++++++++++++++++++++-
 include/linux/can/dev.h          |  6 ++++--
 include/uapi/linux/can/netlink.h |  2 ++
 3 files changed, 50 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 8141290e4c18..8ebe112458c4 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -647,6 +647,10 @@ static const struct nla_policy can_policy[IFLA_CAN_MAX + 1] = {
 				= { .len = sizeof(struct can_bittiming_const) },
 	[IFLA_CAN_CLOCK]	= { .len = sizeof(struct can_clock) },
 	[IFLA_CAN_BERR_COUNTER]	= { .len = sizeof(struct can_berr_counter) },
+	[IFLA_CAN_DATA_BITTIMING]
+				= { .len = sizeof(struct can_bittiming) },
+	[IFLA_CAN_DATA_BITTIMING_CONST]
+				= { .len = sizeof(struct can_bittiming_const) },
 };
 
 static int can_changelink(struct net_device *dev,
@@ -707,6 +711,27 @@ static int can_changelink(struct net_device *dev,
 			return err;
 	}
 
+	if (data[IFLA_CAN_DATA_BITTIMING]) {
+		struct can_bittiming dbt;
+
+		/* Do not allow changing bittiming while running */
+		if (dev->flags & IFF_UP)
+			return -EBUSY;
+		memcpy(&dbt, nla_data(data[IFLA_CAN_DATA_BITTIMING]),
+		       sizeof(dbt));
+		err = can_get_bittiming(dev, &dbt, priv->data_bittiming_const);
+		if (err)
+			return err;
+		memcpy(&priv->data_bittiming, &dbt, sizeof(dbt));
+
+		if (priv->do_set_data_bittiming) {
+			/* Finally, set the bit-timing registers */
+			err = priv->do_set_data_bittiming(dev);
+			if (err)
+				return err;
+		}
+	}
+
 	return 0;
 }
 
@@ -725,6 +750,10 @@ static size_t can_get_size(const struct net_device *dev)
 	size += nla_total_size(sizeof(u32));			/* IFLA_CAN_RESTART_MS */
 	if (priv->do_get_berr_counter)				/* IFLA_CAN_BERR_COUNTER */
 		size += nla_total_size(sizeof(struct can_berr_counter));
+	if (priv->data_bittiming.bitrate)			/* IFLA_CAN_DATA_BITTIMING */
+		size += nla_total_size(sizeof(struct can_bittiming));
+	if (priv->data_bittiming_const)				/* IFLA_CAN_DATA_BITTIMING_CONST */
+		size += nla_total_size(sizeof(struct can_bittiming_const));
 
 	return size;
 }
@@ -738,20 +767,34 @@ static int can_fill_info(struct sk_buff *skb, const struct net_device *dev)
 
 	if (priv->do_get_state)
 		priv->do_get_state(dev, &state);
+
 	if ((priv->bittiming.bitrate &&
 	     nla_put(skb, IFLA_CAN_BITTIMING,
 		     sizeof(priv->bittiming), &priv->bittiming)) ||
+
 	    (priv->bittiming_const &&
 	     nla_put(skb, IFLA_CAN_BITTIMING_CONST,
 		     sizeof(*priv->bittiming_const), priv->bittiming_const)) ||
+
 	    nla_put(skb, IFLA_CAN_CLOCK, sizeof(cm), &priv->clock) ||
 	    nla_put_u32(skb, IFLA_CAN_STATE, state) ||
 	    nla_put(skb, IFLA_CAN_CTRLMODE, sizeof(cm), &cm) ||
 	    nla_put_u32(skb, IFLA_CAN_RESTART_MS, priv->restart_ms) ||
+
 	    (priv->do_get_berr_counter &&
 	     !priv->do_get_berr_counter(dev, &bec) &&
-	     nla_put(skb, IFLA_CAN_BERR_COUNTER, sizeof(bec), &bec)))
+	     nla_put(skb, IFLA_CAN_BERR_COUNTER, sizeof(bec), &bec)) ||
+
+	    (priv->data_bittiming.bitrate &&
+	     nla_put(skb, IFLA_CAN_DATA_BITTIMING,
+		     sizeof(priv->data_bittiming), &priv->data_bittiming)) ||
+
+	    (priv->data_bittiming_const &&
+	     nla_put(skb, IFLA_CAN_DATA_BITTIMING_CONST,
+		     sizeof(*priv->data_bittiming_const),
+		     priv->data_bittiming_const)))
 		return -EMSGSIZE;
+
 	return 0;
 }
 
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index dc5f9026b67f..8adaee96f292 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -33,8 +33,9 @@ enum can_mode {
 struct can_priv {
 	struct can_device_stats can_stats;
 
-	struct can_bittiming bittiming;
-	const struct can_bittiming_const *bittiming_const;
+	struct can_bittiming bittiming, data_bittiming;
+	const struct can_bittiming_const *bittiming_const,
+		*data_bittiming_const;
 	struct can_clock clock;
 
 	enum can_state state;
@@ -45,6 +46,7 @@ struct can_priv {
 	struct timer_list restart_timer;
 
 	int (*do_set_bittiming)(struct net_device *dev);
+	int (*do_set_data_bittiming)(struct net_device *dev);
 	int (*do_set_mode)(struct net_device *dev, enum can_mode mode);
 	int (*do_get_state)(const struct net_device *dev,
 			    enum can_state *state);
diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h
index df944ed206a8..b41933d6bdcd 100644
--- a/include/uapi/linux/can/netlink.h
+++ b/include/uapi/linux/can/netlink.h
@@ -122,6 +122,8 @@ enum {
 	IFLA_CAN_RESTART_MS,
 	IFLA_CAN_RESTART,
 	IFLA_CAN_BERR_COUNTER,
+	IFLA_CAN_DATA_BITTIMING,
+	IFLA_CAN_DATA_BITTIMING_CONST,
 	__IFLA_CAN_MAX
 };
 
-- 
cgit v1.2.3


From bc05a8944a344acdb81a65de055ca6febbf9657c Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Fri, 28 Feb 2014 16:36:24 +0100
Subject: can: allow to change the device mtu for CAN FD capable devices

The configuration for CAN FD depends on CAN_CTRLMODE_FD enabled in the driver
specific ctrlmode_supported capabilities.

The configuration can be done either with the 'fd { on | off }' option in the
'ip' tool from iproute2 or by setting the CAN netdevice MTU to CAN_MTU (16) or
to CANFD_MTU (72).

Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Acked-by: Stephane Grosjean <s.grosjean@peak-system.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dev.c            | 39 +++++++++++++++++++++++++++++++++++++++
 include/linux/can/dev.h          |  1 +
 include/uapi/linux/can/netlink.h |  1 +
 3 files changed, 41 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 8ebe112458c4..4e20d82b799e 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -594,6 +594,39 @@ void free_candev(struct net_device *dev)
 }
 EXPORT_SYMBOL_GPL(free_candev);
 
+/*
+ * changing MTU and control mode for CAN/CANFD devices
+ */
+int can_change_mtu(struct net_device *dev, int new_mtu)
+{
+	struct can_priv *priv = netdev_priv(dev);
+
+	/* Do not allow changing the MTU while running */
+	if (dev->flags & IFF_UP)
+		return -EBUSY;
+
+	/* allow change of MTU according to the CANFD ability of the device */
+	switch (new_mtu) {
+	case CAN_MTU:
+		priv->ctrlmode &= ~CAN_CTRLMODE_FD;
+		break;
+
+	case CANFD_MTU:
+		if (!(priv->ctrlmode_supported & CAN_CTRLMODE_FD))
+			return -EINVAL;
+
+		priv->ctrlmode |= CAN_CTRLMODE_FD;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	dev->mtu = new_mtu;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(can_change_mtu);
+
 /*
  * Common open function when the device gets opened.
  *
@@ -693,6 +726,12 @@ static int can_changelink(struct net_device *dev,
 			return -EOPNOTSUPP;
 		priv->ctrlmode &= ~cm->mask;
 		priv->ctrlmode |= cm->flags;
+
+		/* CAN_CTRLMODE_FD can only be set when driver supports FD */
+		if (priv->ctrlmode & CAN_CTRLMODE_FD)
+			dev->mtu = CANFD_MTU;
+		else
+			dev->mtu = CAN_MTU;
 	}
 
 	if (data[IFLA_CAN_RESTART_MS]) {
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index 8adaee96f292..3ce5e526525f 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -113,6 +113,7 @@ struct can_priv *safe_candev_priv(struct net_device *dev);
 
 int open_candev(struct net_device *dev);
 void close_candev(struct net_device *dev);
+int can_change_mtu(struct net_device *dev, int new_mtu);
 
 int register_candev(struct net_device *dev);
 void unregister_candev(struct net_device *dev);
diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h
index b41933d6bdcd..7e2e1863db16 100644
--- a/include/uapi/linux/can/netlink.h
+++ b/include/uapi/linux/can/netlink.h
@@ -96,6 +96,7 @@ struct can_ctrlmode {
 #define CAN_CTRLMODE_3_SAMPLES		0x04	/* Triple sampling mode */
 #define CAN_CTRLMODE_ONE_SHOT		0x08	/* One-Shot mode */
 #define CAN_CTRLMODE_BERR_REPORTING	0x10	/* Bus-error reporting */
+#define CAN_CTRLMODE_FD			0x20	/* CAN FD mode */
 
 /*
  * CAN device statistics
-- 
cgit v1.2.3


From 00fd9619120db1d6a19be2f9e3df6f76234b311b Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Fri, 7 Mar 2014 15:49:54 +0100
Subject: of: Fix of_graph_parse_endpoint stub for !CONFIG_OF builds

This patch fixes the following build error:

   In file included from drivers/media/i2c/adv7343.c:29:0:
>> include/linux/of_graph.h:41:1: error: expected identifier or '(' before '{' token
    {
    ^
   include/linux/of_graph.h:39:19: warning: 'of_graph_parse_endpoint' declared 'static' but never defined [-Wunused-function]
    static inline int of_graph_parse_endpoint(const struct device_node *node,
                      ^

vim +41 include/linux/of_graph.h

    35                                          const struct device_node *node);
    36  struct device_node *of_graph_get_remote_port(const struct device_node *node);
    37  #else
    38
    39  static inline int of_graph_parse_endpoint(const struct device_node *node,
    40                                          struct of_endpoint *endpoint);
  > 41  {
    42          return -ENOSYS;
    43  }
    44

Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 include/linux/of_graph.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/of_graph.h b/include/linux/of_graph.h
index 2b233db76237..befef42e015b 100644
--- a/include/linux/of_graph.h
+++ b/include/linux/of_graph.h
@@ -37,7 +37,7 @@ struct device_node *of_graph_get_remote_port(const struct device_node *node);
 #else
 
 static inline int of_graph_parse_endpoint(const struct device_node *node,
-					struct of_endpoint *endpoint);
+					struct of_endpoint *endpoint)
 {
 	return -ENOSYS;
 }
-- 
cgit v1.2.3


From 1d6bae966e90134bcfd7807b8f9488d55198de91 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Thu, 9 Aug 2012 19:16:14 -0400
Subject: tracing: Move raw output code from macro to standalone function

The code for trace events to format the raw recorded event data
into human readable format in the 'trace' file is repeated for every
event in the system. When you have over 500 events, this can add up
quite a bit.

By making helper functions in the core kernel to do the work
instead, we can shrink the size of the kernel down a bit.

With a kernel configured with 502 events, the change in size was:

   text    data     bss     dec     hex filename
12991007        1913568 9785344 24689919        178bcff /tmp/vmlinux.orig
12990946        1913568 9785344 24689858        178bcc2 /tmp/vmlinux.patched

Note, this version does not save as much as the version of this patch
I had a few years ago. That is because in the mean time, commit
f71130de5c7f ("tracing: Add a helper function for event print functions")
did a lot of the work my original patch did. But this change helps
slightly, and is part of a larger clean up to reduce the size much further.

Link: http://lkml.kernel.org/r/20120810034707.378538034@goodmis.org

Cc: Li Zefan <lizefan@huawei.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace_event.h |  5 +++++
 include/trace/ftrace.h       | 10 +---------
 kernel/trace/trace_output.c  | 31 +++++++++++++++++++++++++++++++
 3 files changed, 37 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 4e4cc28623ad..a91ab93d7250 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -163,6 +163,8 @@ void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
 
 void tracing_record_cmdline(struct task_struct *tsk);
 
+int ftrace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...);
+
 struct event_filter;
 
 enum trace_reg {
@@ -197,6 +199,9 @@ struct ftrace_event_class {
 extern int ftrace_event_reg(struct ftrace_event_call *event,
 			    enum trace_reg type, void *data);
 
+int ftrace_output_event(struct trace_iterator *iter, struct ftrace_event_call *event,
+			char *fmt, ...);
+
 enum {
 	TRACE_EVENT_FL_FILTERED_BIT,
 	TRACE_EVENT_FL_CAP_ANY_BIT,
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 1a8b28db3775..3873d6e4697f 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -265,11 +265,9 @@ static notrace enum print_line_t					\
 ftrace_raw_output_##call(struct trace_iterator *iter, int flags,	\
 			 struct trace_event *event)			\
 {									\
-	struct trace_seq *s = &iter->seq;				\
 	struct ftrace_raw_##template *field;				\
 	struct trace_entry *entry;					\
 	struct trace_seq *p = &iter->tmp_seq;				\
-	int ret;							\
 									\
 	entry = iter->ent;						\
 									\
@@ -281,13 +279,7 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags,	\
 	field = (typeof(field))entry;					\
 									\
 	trace_seq_init(p);						\
-	ret = trace_seq_printf(s, "%s: ", #call);			\
-	if (ret)							\
-		ret = trace_seq_printf(s, print);			\
-	if (!ret)							\
-		return TRACE_TYPE_PARTIAL_LINE;				\
-									\
-	return TRACE_TYPE_HANDLED;					\
+	return ftrace_output_call(iter, #call, print);			\
 }									\
 static struct trace_event_functions ftrace_event_type_funcs_##call = {	\
 	.trace			= ftrace_raw_output_##call,		\
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index ed32284fbe32..ca0e79e2abaa 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -439,6 +439,37 @@ int ftrace_raw_output_prep(struct trace_iterator *iter,
 }
 EXPORT_SYMBOL(ftrace_raw_output_prep);
 
+static int ftrace_output_raw(struct trace_iterator *iter, char *name,
+			     char *fmt, va_list ap)
+{
+	struct trace_seq *s = &iter->seq;
+	int ret;
+
+	ret = trace_seq_printf(s, "%s: ", name);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	ret = trace_seq_vprintf(s, fmt, ap);
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
+
+int ftrace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...)
+{
+	va_list ap;
+	int ret;
+
+	va_start(ap, fmt);
+	ret = ftrace_output_raw(iter, name, fmt, ap);
+	va_end(ap);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ftrace_output_call);
+
 #ifdef CONFIG_KRETPROBES
 static inline const char *kretprobed(const char *name)
 {
-- 
cgit v1.2.3


From 35bb4399bd0ef16b8a57fccea0047d98b6b0e7fb Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Thu, 9 Aug 2012 22:26:46 -0400
Subject: tracing: Move event storage for array from macro to standalone
 function

The code that shows array fields for events is defined for all events.
This can add up quite a bit when you have over 500 events.

By making helper functions in the core kernel to do the work
instead, we can shrink the size of the kernel down a bit.

With a kernel configured with 502 events, the change in size was:

   text    data     bss     dec     hex filename
12990946        1913568 9785344 24689858        178bcc2 /tmp/vmlinux
12987390        1913504 9785344 24686238        178ae9e /tmp/vmlinux.patched

That's a total of 3556 bytes, which comes down to 7 bytes per event.
Although it's not much, this code is just called at initialization of
the events.

Link: http://lkml.kernel.org/r/20120810034708.084036335@goodmis.org

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace_event.h |  8 ++++----
 include/trace/ftrace.h       | 12 ++++--------
 kernel/trace/trace_events.c  |  6 ------
 kernel/trace/trace_export.c  | 12 ++++--------
 kernel/trace/trace_output.c  | 21 +++++++++++++++++++++
 5 files changed, 33 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index a91ab93d7250..ffe642eb84fa 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -202,6 +202,10 @@ extern int ftrace_event_reg(struct ftrace_event_call *event,
 int ftrace_output_event(struct trace_iterator *iter, struct ftrace_event_call *event,
 			char *fmt, ...);
 
+int ftrace_event_define_field(struct ftrace_event_call *call,
+			      char *type, int len, char *item, int offset,
+			      int field_size, int sign, int filter);
+
 enum {
 	TRACE_EVENT_FL_FILTERED_BIT,
 	TRACE_EVENT_FL_CAP_ANY_BIT,
@@ -500,10 +504,6 @@ enum {
 	FILTER_TRACE_FN,
 };
 
-#define EVENT_STORAGE_SIZE 128
-extern struct mutex event_storage_mutex;
-extern char event_storage[EVENT_STORAGE_SIZE];
-
 extern int trace_event_raw_init(struct ftrace_event_call *call);
 extern int trace_define_field(struct ftrace_event_call *call, const char *type,
 			      const char *name, int offset, int size,
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 3873d6e4697f..54928faf2119 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -302,15 +302,11 @@ static struct trace_event_functions ftrace_event_type_funcs_##call = {	\
 #undef __array
 #define __array(type, item, len)					\
 	do {								\
-		mutex_lock(&event_storage_mutex);			\
 		BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);			\
-		snprintf(event_storage, sizeof(event_storage),		\
-			 "%s[%d]", #type, len);				\
-		ret = trace_define_field(event_call, event_storage, #item, \
-				 offsetof(typeof(field), item),		\
-				 sizeof(field.item),			\
-				 is_signed_type(type), FILTER_OTHER);	\
-		mutex_unlock(&event_storage_mutex);			\
+		ret = ftrace_event_define_field(event_call, #type, len,	\
+				#item, offsetof(typeof(field), item),   \
+				sizeof(field.item),			\
+			 	is_signed_type(type), FILTER_OTHER); \
 		if (ret)						\
 			return ret;					\
 	} while (0);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index e71ffd4eccb5..22826c73a9da 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -27,12 +27,6 @@
 
 DEFINE_MUTEX(event_mutex);
 
-DEFINE_MUTEX(event_storage_mutex);
-EXPORT_SYMBOL_GPL(event_storage_mutex);
-
-char event_storage[EVENT_STORAGE_SIZE];
-EXPORT_SYMBOL_GPL(event_storage);
-
 LIST_HEAD(ftrace_events);
 static LIST_HEAD(ftrace_common_fields);
 
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 7c3e3e72e2b6..39c746c5ae73 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -96,14 +96,10 @@ static void __always_unused ____ftrace_check_##name(void)		\
 #define __array(type, item, len)					\
 	do {								\
 		BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);			\
-		mutex_lock(&event_storage_mutex);			\
-		snprintf(event_storage, sizeof(event_storage),		\
-			 "%s[%d]", #type, len);				\
-		ret = trace_define_field(event_call, event_storage, #item, \
-				 offsetof(typeof(field), item),		\
-				 sizeof(field.item),			\
-				 is_signed_type(type), filter_type);	\
-		mutex_unlock(&event_storage_mutex);			\
+		ret = ftrace_event_define_field(event_call, #type, len,	\
+				#item, offsetof(typeof(field), item),   \
+				sizeof(field.item),			\
+			 	is_signed_type(type), filter_type);	\
 		if (ret)						\
 			return ret;					\
 	} while (0);
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index ca0e79e2abaa..ee8d74840b88 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -20,6 +20,10 @@ static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
 
 static int next_event_type = __TRACE_LAST_TYPE + 1;
 
+#define EVENT_STORAGE_SIZE 128
+static DEFINE_MUTEX(event_storage_mutex);
+static char event_storage[EVENT_STORAGE_SIZE];
+
 int trace_print_seq(struct seq_file *m, struct trace_seq *s)
 {
 	int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
@@ -470,6 +474,23 @@ int ftrace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...)
 }
 EXPORT_SYMBOL_GPL(ftrace_output_call);
 
+int ftrace_event_define_field(struct ftrace_event_call *call,
+			      char *type, int len, char *item, int offset,
+			      int field_size, int sign, int filter)
+{
+	int ret;
+
+	mutex_lock(&event_storage_mutex);
+	snprintf(event_storage, sizeof(event_storage),
+		 "%s[%d]", type, len);
+	ret = trace_define_field(call, event_storage, item, offset,
+				 field_size, sign, filter);
+	mutex_unlock(&event_storage_mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ftrace_event_define_field);
+
 #ifdef CONFIG_KRETPROBES
 static inline const char *kretprobed(const char *name)
 {
-- 
cgit v1.2.3


From 3fd40d1ee6a317523172ab95b6f7ea41ba8fcee3 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Thu, 9 Aug 2012 22:42:57 -0400
Subject: tracing: Use helper functions in event assignment to shrink macro
 size

The functions that assign the contents for the ftrace events are
defined by the TRACE_EVENT() macros. Each event has its own unique
way to assign data to its buffer. When you have over 500 events,
that means there's 500 functions assigning data uniquely for each
event (not really that many, as DECLARE_EVENT_CLASS() and multiple
DEFINE_EVENT()s will only need a single function).

By making helper functions in the core kernel to do some of the work
instead, we can shrink the size of the kernel down a bit.

With a kernel configured with 502 events, the change in size was:

   text    data     bss     dec     hex filename
12987390        1913504 9785344 24686238        178ae9e /tmp/vmlinux
12959102        1913504 9785344 24657950        178401e /tmp/vmlinux.patched

That's a total of 28288 bytes, which comes down to 56 bytes per event.

Link: http://lkml.kernel.org/r/20120810034708.370808175@goodmis.org

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace_event.h | 15 +++++++++++++++
 include/trace/ftrace.h       | 22 ++++++----------------
 kernel/trace/trace_events.c  | 30 ++++++++++++++++++++++++++++++
 3 files changed, 51 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index ffe642eb84fa..9d3fe0658398 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -206,6 +206,21 @@ int ftrace_event_define_field(struct ftrace_event_call *call,
 			      char *type, int len, char *item, int offset,
 			      int field_size, int sign, int filter);
 
+struct ftrace_event_buffer {
+	struct ring_buffer		*buffer;
+	struct ring_buffer_event	*event;
+	struct ftrace_event_file	*ftrace_file;
+	void				*entry;
+	unsigned long			flags;
+	int				pc;
+};
+
+void *ftrace_event_buffer_reserve(struct ftrace_event_buffer *fbuffer,
+				  struct ftrace_event_file *ftrace_file,
+				  unsigned long len);
+
+void ftrace_event_buffer_commit(struct ftrace_event_buffer *fbuffer);
+
 enum {
 	TRACE_EVENT_FL_FILTERED_BIT,
 	TRACE_EVENT_FL_CAP_ANY_BIT,
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 54928faf2119..1cc2265caa52 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -532,37 +532,27 @@ static notrace void							\
 ftrace_raw_event_##call(void *__data, proto)				\
 {									\
 	struct ftrace_event_file *ftrace_file = __data;			\
-	struct ftrace_event_call *event_call = ftrace_file->event_call;	\
 	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
-	struct ring_buffer_event *event;				\
+	struct ftrace_event_buffer fbuffer;				\
 	struct ftrace_raw_##call *entry;				\
-	struct ring_buffer *buffer;					\
-	unsigned long irq_flags;					\
 	int __data_size;						\
-	int pc;								\
 									\
 	if (ftrace_trigger_soft_disabled(ftrace_file))			\
 		return;							\
 									\
-	local_save_flags(irq_flags);					\
-	pc = preempt_count();						\
-									\
 	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
 									\
-	event = trace_event_buffer_lock_reserve(&buffer, ftrace_file,	\
-				 event_call->event.type,		\
-				 sizeof(*entry) + __data_size,		\
-				 irq_flags, pc);			\
-	if (!event)							\
+	entry = ftrace_event_buffer_reserve(&fbuffer, ftrace_file,	\
+				 sizeof(*entry) + __data_size);		\
+									\
+	if (!entry)							\
 		return;							\
-	entry	= ring_buffer_event_data(event);			\
 									\
 	tstruct								\
 									\
 	{ assign; }							\
 									\
-	event_trigger_unlock_commit(ftrace_file, buffer, event, entry, \
-				    irq_flags, pc);		       \
+	ftrace_event_buffer_commit(&fbuffer);				\
 }
 /*
  * The ftrace_test_probe is compiled out, it is only here as a build time check
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 22826c73a9da..b8f73b333a3c 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -188,6 +188,36 @@ int trace_event_raw_init(struct ftrace_event_call *call)
 }
 EXPORT_SYMBOL_GPL(trace_event_raw_init);
 
+void *ftrace_event_buffer_reserve(struct ftrace_event_buffer *fbuffer,
+				  struct ftrace_event_file *ftrace_file,
+				  unsigned long len)
+{
+	struct ftrace_event_call *event_call = ftrace_file->event_call;
+
+	local_save_flags(fbuffer->flags);
+	fbuffer->pc = preempt_count();
+	fbuffer->ftrace_file = ftrace_file;
+
+	fbuffer->event =
+		trace_event_buffer_lock_reserve(&fbuffer->buffer, ftrace_file,
+						event_call->event.type, len,
+						fbuffer->flags, fbuffer->pc);
+	if (!fbuffer->event)
+		return NULL;
+
+	fbuffer->entry = ring_buffer_event_data(fbuffer->event);
+	return fbuffer->entry;
+}
+EXPORT_SYMBOL_GPL(ftrace_event_buffer_reserve);
+
+void ftrace_event_buffer_commit(struct ftrace_event_buffer *fbuffer)
+{
+	event_trigger_unlock_commit(fbuffer->ftrace_file, fbuffer->buffer,
+				    fbuffer->event, fbuffer->entry,
+				    fbuffer->flags, fbuffer->pc);
+}
+EXPORT_SYMBOL_GPL(ftrace_event_buffer_commit);
+
 int ftrace_event_reg(struct ftrace_event_call *call,
 		     enum trace_reg type, void *data)
 {
-- 
cgit v1.2.3


From b2e285fcb46ab4d91ebbc3a9bd5900f544972a47 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Wed, 26 Feb 2014 13:12:06 -0500
Subject: tracing/module: Replace include of tracepoint.h with jump_label.h in
 module.h

There's nothing in the module.h header that requires tracepoint.h to be
included, and there may be cases that tracepoint.h may need to include
module.h, which will cause recursive header issues.

But module.h requires seeing HAVE_JUMP_LABEL which is set in jump_label.h
which it just coincidentally gets from tracepoint.h.

Link: http://lkml.kernel.org/r/20140307084712.5c68641a@gandalf.local.home

Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/module.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/module.h b/include/linux/module.h
index eaf60ff9ba94..5a5053975114 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -15,7 +15,7 @@
 #include <linux/stringify.h>
 #include <linux/kobject.h>
 #include <linux/moduleparam.h>
-#include <linux/tracepoint.h>
+#include <linux/jump_label.h>
 #include <linux/export.h>
 
 #include <linux/percpu.h>
-- 
cgit v1.2.3


From 3a36cb11ca65cd6804972eaf1000378ba4384ea7 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Mon, 24 Feb 2014 19:59:59 +0100
Subject: ftrace: Do not pass data to ftrace_dyn_arch_init

As the data parameter is not really used by any ftrace_dyn_arch_init,
remove that from ftrace_dyn_arch_init. This also removes the addr
local variable from ftrace_init which is now unused.

Note the documentation was imprecise as it did not suggest to set
(*data) to 0.

Link: http://lkml.kernel.org/r/1393268401-24379-4-git-send-email-jslaby@suse.cz

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: linux-arch@vger.kernel.org
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 Documentation/trace/ftrace-design.txt | 2 +-
 arch/arm/kernel/ftrace.c              | 2 +-
 arch/blackfin/kernel/ftrace.c         | 2 +-
 arch/ia64/kernel/ftrace.c             | 2 +-
 arch/metag/kernel/ftrace.c            | 2 +-
 arch/microblaze/kernel/ftrace.c       | 2 +-
 arch/mips/kernel/ftrace.c             | 2 +-
 arch/powerpc/kernel/ftrace.c          | 2 +-
 arch/s390/kernel/ftrace.c             | 2 +-
 arch/sh/kernel/ftrace.c               | 2 +-
 arch/sparc/kernel/ftrace.c            | 2 +-
 arch/tile/kernel/ftrace.c             | 2 +-
 arch/x86/kernel/ftrace.c              | 2 +-
 include/linux/ftrace.h                | 2 +-
 kernel/trace/ftrace.c                 | 7 ++-----
 15 files changed, 16 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/trace/ftrace-design.txt b/Documentation/trace/ftrace-design.txt
index 117168884023..3f669b9e8852 100644
--- a/Documentation/trace/ftrace-design.txt
+++ b/Documentation/trace/ftrace-design.txt
@@ -358,7 +358,7 @@ Every arch has an init callback function.  If you need to do something early on
 to initialize some state, this is the time to do that.  Otherwise, this simple
 function below should be sufficient for most people:
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
 	return 0;
 }
diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index 5cd0d05edf35..c108ddcb9ba4 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -156,7 +156,7 @@ int ftrace_make_nop(struct module *mod,
 	return ret;
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
 	return 0;
 }
diff --git a/arch/blackfin/kernel/ftrace.c b/arch/blackfin/kernel/ftrace.c
index f74c5ae6a25b..095de0fa044d 100644
--- a/arch/blackfin/kernel/ftrace.c
+++ b/arch/blackfin/kernel/ftrace.c
@@ -65,7 +65,7 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return ftrace_modify_code(ip, call, sizeof(call));
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
 	return 0;
 }
diff --git a/arch/ia64/kernel/ftrace.c b/arch/ia64/kernel/ftrace.c
index cfaa93a8bbdf..3b0c2aa07857 100644
--- a/arch/ia64/kernel/ftrace.c
+++ b/arch/ia64/kernel/ftrace.c
@@ -198,7 +198,7 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 }
 
 /* run from kstop_machine */
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
 	return 0;
 }
diff --git a/arch/metag/kernel/ftrace.c b/arch/metag/kernel/ftrace.c
index bf593932b353..ed1d685157c2 100644
--- a/arch/metag/kernel/ftrace.c
+++ b/arch/metag/kernel/ftrace.c
@@ -117,7 +117,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 }
 
 /* run from kstop_machine */
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
 	return 0;
 }
diff --git a/arch/microblaze/kernel/ftrace.c b/arch/microblaze/kernel/ftrace.c
index ffa595c7fec2..bbcd2533766c 100644
--- a/arch/microblaze/kernel/ftrace.c
+++ b/arch/microblaze/kernel/ftrace.c
@@ -171,7 +171,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	return ret;
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
 	return 0;
 }
diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c
index 013016bec9e1..1ba7afe6ab74 100644
--- a/arch/mips/kernel/ftrace.c
+++ b/arch/mips/kernel/ftrace.c
@@ -198,7 +198,7 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return ftrace_modify_code(FTRACE_CALL_IP, new);
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
 	/* Encode the instructions when booting */
 	ftrace_dyn_arch_init_insns();
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index d059664cdf16..71ce4cbb7e9f 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -531,7 +531,7 @@ void arch_ftrace_update_code(int command)
 		ftrace_disable_ftrace_graph_caller();
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
 	return 0;
 }
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 77b2f3a1f50a..54d6493c4a56 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -130,7 +130,7 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return 0;
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
 	return 0;
 }
diff --git a/arch/sh/kernel/ftrace.c b/arch/sh/kernel/ftrace.c
index 493997541d2c..3c74f53db6db 100644
--- a/arch/sh/kernel/ftrace.c
+++ b/arch/sh/kernel/ftrace.c
@@ -272,7 +272,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	return ftrace_modify_code(rec->ip, old, new);
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
 	return 0;
 }
diff --git a/arch/sparc/kernel/ftrace.c b/arch/sparc/kernel/ftrace.c
index ee813b82da49..0a2d2ddff543 100644
--- a/arch/sparc/kernel/ftrace.c
+++ b/arch/sparc/kernel/ftrace.c
@@ -82,7 +82,7 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return ftrace_modify_code(ip, old, new);
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
 	return 0;
 }
diff --git a/arch/tile/kernel/ftrace.c b/arch/tile/kernel/ftrace.c
index 34d9ea0bca9f..8d52d83cc516 100644
--- a/arch/tile/kernel/ftrace.c
+++ b/arch/tile/kernel/ftrace.c
@@ -167,7 +167,7 @@ int ftrace_make_nop(struct module *mod,
 	return ret;
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
 	return 0;
 }
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index bbe5a5b88aad..4b66adf17369 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -668,7 +668,7 @@ void arch_ftrace_update_code(int command)
 	atomic_dec(&modifying_ftrace_code);
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
 	return 0;
 }
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index e6141be2fad5..1bbb2cd631de 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -423,7 +423,7 @@ ftrace_set_early_filter(struct ftrace_ops *ops, char *buf, int enable);
 
 /* defined in arch */
 extern int ftrace_ip_converted(unsigned long ip);
-extern int ftrace_dyn_arch_init(void *data);
+extern int ftrace_dyn_arch_init(void);
 extern void ftrace_replace_code(int enable);
 extern int ftrace_update_ftrace_func(ftrace_func_t func);
 extern void ftrace_caller(void);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 083c6d5fce25..5bd70e8b09b0 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -4372,14 +4372,11 @@ void __init ftrace_init(void)
 {
 	extern unsigned long __start_mcount_loc[];
 	extern unsigned long __stop_mcount_loc[];
-	unsigned long count, addr, flags;
+	unsigned long count, flags;
 	int ret;
 
-	/* Keep the ftrace pointer to the stub */
-	addr = (unsigned long)ftrace_stub;
-
 	local_irq_save(flags);
-	ret = ftrace_dyn_arch_init(&addr);
+	ret = ftrace_dyn_arch_init();
 	local_irq_restore(flags);
 	if (ret)
 		goto failed;
-- 
cgit v1.2.3


From a762782d780b341b1836489692190d26be624ed7 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Mon, 24 Feb 2014 20:00:00 +0100
Subject: ftrace: Remove freelist from struct dyn_ftrace

The 'freelist' member was introduced to 'struct dyn_ftrace' in commit
ee000b7f9fe429d2470c674ccec8d344f6789e0d (tracing: use union for
multi-usages field), but the use of this member was later removed in
3208230983a0ee3d95be22d463257e530c684956 (ftrace: Remove usage of
"freed" records). Remove also the 'freelist' member now.

Link: http://lkml.kernel.org/r/1393268401-24379-5-git-send-email-jslaby@suse.cz

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace.h | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 1bbb2cd631de..20da0561b868 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -330,12 +330,9 @@ enum {
 #define FTRACE_REF_MAX		((1UL << 29) - 1)
 
 struct dyn_ftrace {
-	union {
-		unsigned long		ip; /* address of mcount call-site */
-		struct dyn_ftrace	*freelist;
-	};
+	unsigned long		ip; /* address of mcount call-site */
 	unsigned long		flags;
-	struct dyn_arch_ftrace		arch;
+	struct dyn_arch_ftrace	arch;
 };
 
 int ftrace_force_update(void);
-- 
cgit v1.2.3


From 6284be23db6b32e17ef34d082386967350d10d1a Mon Sep 17 00:00:00 2001
From: Kishon Vijay Abraham I <kishon@ti.com>
Date: Mon, 3 Mar 2014 17:08:14 +0530
Subject: phy: omap-usb2: move omap_usb.h from linux/usb/ to linux/phy/

No functional change. Moved omap_usb.h from linux/usb/ to linux/phy/.
Also removed the unused members of struct omap_usb (after phy-omap-pipe3
started using it's own header file)

Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 drivers/phy/phy-omap-usb2.c       |  2 +-
 drivers/usb/phy/phy-twl6030-usb.c |  2 +-
 include/linux/phy/omap_usb.h      | 64 +++++++++++++++++++++++++++++++++++++
 include/linux/usb/omap_usb.h      | 67 ---------------------------------------
 4 files changed, 66 insertions(+), 69 deletions(-)
 create mode 100644 include/linux/phy/omap_usb.h
 delete mode 100644 include/linux/usb/omap_usb.h

(limited to 'include/linux')

diff --git a/drivers/phy/phy-omap-usb2.c b/drivers/phy/phy-omap-usb2.c
index 705af5a11fb9..9c3f056b3ddf 100644
--- a/drivers/phy/phy-omap-usb2.c
+++ b/drivers/phy/phy-omap-usb2.c
@@ -21,7 +21,7 @@
 #include <linux/slab.h>
 #include <linux/of.h>
 #include <linux/io.h>
-#include <linux/usb/omap_usb.h>
+#include <linux/phy/omap_usb.h>
 #include <linux/usb/phy_companion.h>
 #include <linux/clk.h>
 #include <linux/err.h>
diff --git a/drivers/usb/phy/phy-twl6030-usb.c b/drivers/usb/phy/phy-twl6030-usb.c
index 214172b68d5d..04778cf80d60 100644
--- a/drivers/usb/phy/phy-twl6030-usb.c
+++ b/drivers/usb/phy/phy-twl6030-usb.c
@@ -27,7 +27,7 @@
 #include <linux/io.h>
 #include <linux/usb/musb-omap.h>
 #include <linux/usb/phy_companion.h>
-#include <linux/usb/omap_usb.h>
+#include <linux/phy/omap_usb.h>
 #include <linux/i2c/twl.h>
 #include <linux/regulator/consumer.h>
 #include <linux/err.h>
diff --git a/include/linux/phy/omap_usb.h b/include/linux/phy/omap_usb.h
new file mode 100644
index 000000000000..19d343c37fb5
--- /dev/null
+++ b/include/linux/phy/omap_usb.h
@@ -0,0 +1,64 @@
+/*
+ * omap_usb.h -- omap usb2 phy header file
+ *
+ * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * Author: Kishon Vijay Abraham I <kishon@ti.com>
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __DRIVERS_OMAP_USB2_H
+#define __DRIVERS_OMAP_USB2_H
+
+#include <linux/io.h>
+#include <linux/usb/otg.h>
+
+struct usb_dpll_params {
+	u16	m;
+	u8	n;
+	u8	freq:3;
+	u8	sd;
+	u32	mf;
+};
+
+struct omap_usb {
+	struct usb_phy		phy;
+	struct phy_companion	*comparator;
+	struct device		*dev;
+	struct device		*control_dev;
+	struct clk		*wkupclk;
+	struct clk		*optclk;
+};
+
+#define	phy_to_omapusb(x)	container_of((x), struct omap_usb, phy)
+
+#if defined(CONFIG_OMAP_USB2) || defined(CONFIG_OMAP_USB2_MODULE)
+extern int omap_usb2_set_comparator(struct phy_companion *comparator);
+#else
+static inline int omap_usb2_set_comparator(struct phy_companion *comparator)
+{
+	return -ENODEV;
+}
+#endif
+
+static inline u32 omap_usb_readl(void __iomem *addr, unsigned offset)
+{
+	return __raw_readl(addr + offset);
+}
+
+static inline void omap_usb_writel(void __iomem *addr, unsigned offset,
+	u32 data)
+{
+	__raw_writel(data, addr + offset);
+}
+
+#endif /* __DRIVERS_OMAP_USB_H */
diff --git a/include/linux/usb/omap_usb.h b/include/linux/usb/omap_usb.h
deleted file mode 100644
index 6ae29360e1d2..000000000000
--- a/include/linux/usb/omap_usb.h
+++ /dev/null
@@ -1,67 +0,0 @@
-/*
- * omap_usb.h -- omap usb2 phy header file
- *
- * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * Author: Kishon Vijay Abraham I <kishon@ti.com>
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#ifndef __DRIVERS_OMAP_USB2_H
-#define __DRIVERS_OMAP_USB2_H
-
-#include <linux/io.h>
-#include <linux/usb/otg.h>
-
-struct usb_dpll_params {
-	u16	m;
-	u8	n;
-	u8	freq:3;
-	u8	sd;
-	u32	mf;
-};
-
-struct omap_usb {
-	struct usb_phy		phy;
-	struct phy_companion	*comparator;
-	void __iomem		*pll_ctrl_base;
-	struct device		*dev;
-	struct device		*control_dev;
-	struct clk		*wkupclk;
-	struct clk		*sys_clk;
-	struct clk		*optclk;
-	u8			is_suspended:1;
-};
-
-#define	phy_to_omapusb(x)	container_of((x), struct omap_usb, phy)
-
-#if defined(CONFIG_OMAP_USB2) || defined(CONFIG_OMAP_USB2_MODULE)
-extern int omap_usb2_set_comparator(struct phy_companion *comparator);
-#else
-static inline int omap_usb2_set_comparator(struct phy_companion *comparator)
-{
-	return -ENODEV;
-}
-#endif
-
-static inline u32 omap_usb_readl(void __iomem *addr, unsigned offset)
-{
-	return __raw_readl(addr + offset);
-}
-
-static inline void omap_usb_writel(void __iomem *addr, unsigned offset,
-	u32 data)
-{
-	__raw_writel(data, addr + offset);
-}
-
-#endif /* __DRIVERS_OMAP_USB_H */
-- 
cgit v1.2.3


From d984ea604943bbeedde4e9715984eb942a298383 Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Wed, 11 Dec 2013 15:20:54 -0500
Subject: fs: move i_readcount

On a 64-bit system, a hole exists in the 'inode' structure after
i_writecount.  This patch moves i_readcount to fill this hole.

Reported-by: David Howells <dhowells@redhat.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Acked-by: David Howells <dhowells@redhat.com>
---
 include/linux/fs.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 121f11f001c0..e88219d3f42b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -586,6 +586,9 @@ struct inode {
 	atomic_t		i_count;
 	atomic_t		i_dio_count;
 	atomic_t		i_writecount;
+#ifdef CONFIG_IMA
+	atomic_t		i_readcount; /* struct files open RO */
+#endif
 	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
 	struct file_lock	*i_flock;
 	struct address_space	i_data;
@@ -606,9 +609,6 @@ struct inode {
 	struct hlist_head	i_fsnotify_marks;
 #endif
 
-#ifdef CONFIG_IMA
-	atomic_t		i_readcount; /* struct files open RO */
-#endif
 	void			*i_private; /* fs or device private pointer */
 };
 
-- 
cgit v1.2.3


From a90902531a06a030a252a07fbff7f45a189a64fe Mon Sep 17 00:00:00 2001
From: William Roberts <bill.c.roberts@gmail.com>
Date: Tue, 11 Feb 2014 10:11:59 -0800
Subject: mm: Create utility function for accessing a tasks commandline value

introduce get_cmdline() for retreiving the value of a processes
proc/self/cmdline value.

Acked-by: David Rientjes <rientjes@google.com>
Acked-by: Stephen Smalley <sds@tycho.nsa.gov>
Acked-by: Richard Guy Briggs <rgb@redhat.com>

Signed-off-by: William Roberts <wroberts@tresys.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 include/linux/mm.h |  1 +
 mm/util.c          | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 49 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 35527173cf50..01e797031993 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1134,6 +1134,7 @@ void account_page_writeback(struct page *page);
 int set_page_dirty(struct page *page);
 int set_page_dirty_lock(struct page *page);
 int clear_page_dirty_for_io(struct page *page);
+int get_cmdline(struct task_struct *task, char *buffer, int buflen);
 
 /* Is the vma a continuation of the stack vma above it? */
 static inline int vma_growsdown(struct vm_area_struct *vma, unsigned long addr)
diff --git a/mm/util.c b/mm/util.c
index 808f375648e7..43b44199c5e3 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -413,6 +413,54 @@ unsigned long vm_commit_limit(void)
 		* sysctl_overcommit_ratio / 100) + total_swap_pages;
 }
 
+/**
+ * get_cmdline() - copy the cmdline value to a buffer.
+ * @task:     the task whose cmdline value to copy.
+ * @buffer:   the buffer to copy to.
+ * @buflen:   the length of the buffer. Larger cmdline values are truncated
+ *            to this length.
+ * Returns the size of the cmdline field copied. Note that the copy does
+ * not guarantee an ending NULL byte.
+ */
+int get_cmdline(struct task_struct *task, char *buffer, int buflen)
+{
+	int res = 0;
+	unsigned int len;
+	struct mm_struct *mm = get_task_mm(task);
+	if (!mm)
+		goto out;
+	if (!mm->arg_end)
+		goto out_mm;	/* Shh! No looking before we're done */
+
+	len = mm->arg_end - mm->arg_start;
+
+	if (len > buflen)
+		len = buflen;
+
+	res = access_process_vm(task, mm->arg_start, buffer, len, 0);
+
+	/*
+	 * If the nul at the end of args has been overwritten, then
+	 * assume application is using setproctitle(3).
+	 */
+	if (res > 0 && buffer[res-1] != '\0' && len < buflen) {
+		len = strnlen(buffer, res);
+		if (len < res) {
+			res = len;
+		} else {
+			len = mm->env_end - mm->env_start;
+			if (len > buflen - res)
+				len = buflen - res;
+			res += access_process_vm(task, mm->env_start,
+						 buffer+res, len, 0);
+			res = strnlen(buffer, res);
+		}
+	}
+out_mm:
+	mmput(mm);
+out:
+	return res;
+}
 
 /* Tracepoints definitions. */
 EXPORT_TRACEPOINT_SYMBOL(kmalloc);
-- 
cgit v1.2.3


From 3121e3c441b5eccdd15e6c320ec32215b334b9ec Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagig@mellanox.com>
Date: Sun, 23 Feb 2014 14:19:06 +0200
Subject: mlx5: Implement create_mr and destroy_mr

Support create_mr and destroy_mr verbs.  Creating ib_mr may be done
for either ib_mr that will register regular page lists like
alloc_fast_reg_mr routine, or indirect ib_mrs that can register other
(pre-registered) ib_mrs in an indirect manner.

In addition user may request signature enable, that will mean that the
created ib_mr may be attached with signature attributes (BSF, PSVs).

Currently we only allow direct/indirect registration modes.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx5/main.c            |   2 +
 drivers/infiniband/hw/mlx5/mlx5_ib.h         |   4 +
 drivers/infiniband/hw/mlx5/mr.c              | 111 +++++++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/mr.c |  61 +++++++++++++++
 include/linux/mlx5/device.h                  |  25 ++++++
 include/linux/mlx5/driver.h                  |  19 +++++
 6 files changed, 222 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index aa03e732b6a8..7260a299c6db 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1423,9 +1423,11 @@ static int init_one(struct pci_dev *pdev,
 	dev->ib_dev.get_dma_mr		= mlx5_ib_get_dma_mr;
 	dev->ib_dev.reg_user_mr		= mlx5_ib_reg_user_mr;
 	dev->ib_dev.dereg_mr		= mlx5_ib_dereg_mr;
+	dev->ib_dev.destroy_mr		= mlx5_ib_destroy_mr;
 	dev->ib_dev.attach_mcast	= mlx5_ib_mcg_attach;
 	dev->ib_dev.detach_mcast	= mlx5_ib_mcg_detach;
 	dev->ib_dev.process_mad		= mlx5_ib_process_mad;
+	dev->ib_dev.create_mr		= mlx5_ib_create_mr;
 	dev->ib_dev.alloc_fast_reg_mr	= mlx5_ib_alloc_fast_reg_mr;
 	dev->ib_dev.alloc_fast_reg_page_list = mlx5_ib_alloc_fast_reg_page_list;
 	dev->ib_dev.free_fast_reg_page_list  = mlx5_ib_free_fast_reg_page_list;
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 389e31965773..79c4f14c4d3e 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -265,6 +265,7 @@ struct mlx5_ib_mr {
 	enum ib_wc_status	status;
 	struct mlx5_ib_dev     *dev;
 	struct mlx5_create_mkey_mbox_out out;
+	struct mlx5_core_sig_ctx    *sig;
 };
 
 struct mlx5_ib_fast_reg_page_list {
@@ -495,6 +496,9 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 				  u64 virt_addr, int access_flags,
 				  struct ib_udata *udata);
 int mlx5_ib_dereg_mr(struct ib_mr *ibmr);
+int mlx5_ib_destroy_mr(struct ib_mr *ibmr);
+struct ib_mr *mlx5_ib_create_mr(struct ib_pd *pd,
+				struct ib_mr_init_attr *mr_init_attr);
 struct ib_mr *mlx5_ib_alloc_fast_reg_mr(struct ib_pd *pd,
 					int max_page_list_len);
 struct ib_fast_reg_page_list *mlx5_ib_alloc_fast_reg_page_list(struct ib_device *ibdev,
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 7c95ca1f0c25..032445c47608 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -992,6 +992,117 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr)
 	return 0;
 }
 
+struct ib_mr *mlx5_ib_create_mr(struct ib_pd *pd,
+				struct ib_mr_init_attr *mr_init_attr)
+{
+	struct mlx5_ib_dev *dev = to_mdev(pd->device);
+	struct mlx5_create_mkey_mbox_in *in;
+	struct mlx5_ib_mr *mr;
+	int access_mode, err;
+	int ndescs = roundup(mr_init_attr->max_reg_descriptors, 4);
+
+	mr = kzalloc(sizeof(*mr), GFP_KERNEL);
+	if (!mr)
+		return ERR_PTR(-ENOMEM);
+
+	in = kzalloc(sizeof(*in), GFP_KERNEL);
+	if (!in) {
+		err = -ENOMEM;
+		goto err_free;
+	}
+
+	in->seg.status = 1 << 6; /* free */
+	in->seg.xlt_oct_size = cpu_to_be32(ndescs);
+	in->seg.qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
+	in->seg.flags_pd = cpu_to_be32(to_mpd(pd)->pdn);
+	access_mode = MLX5_ACCESS_MODE_MTT;
+
+	if (mr_init_attr->flags & IB_MR_SIGNATURE_EN) {
+		u32 psv_index[2];
+
+		in->seg.flags_pd = cpu_to_be32(be32_to_cpu(in->seg.flags_pd) |
+							   MLX5_MKEY_BSF_EN);
+		in->seg.bsfs_octo_size = cpu_to_be32(MLX5_MKEY_BSF_OCTO_SIZE);
+		mr->sig = kzalloc(sizeof(*mr->sig), GFP_KERNEL);
+		if (!mr->sig) {
+			err = -ENOMEM;
+			goto err_free_in;
+		}
+
+		/* create mem & wire PSVs */
+		err = mlx5_core_create_psv(&dev->mdev, to_mpd(pd)->pdn,
+					   2, psv_index);
+		if (err)
+			goto err_free_sig;
+
+		access_mode = MLX5_ACCESS_MODE_KLM;
+		mr->sig->psv_memory.psv_idx = psv_index[0];
+		mr->sig->psv_wire.psv_idx = psv_index[1];
+	}
+
+	in->seg.flags = MLX5_PERM_UMR_EN | access_mode;
+	err = mlx5_core_create_mkey(&dev->mdev, &mr->mmr, in, sizeof(*in),
+				    NULL, NULL, NULL);
+	if (err)
+		goto err_destroy_psv;
+
+	mr->ibmr.lkey = mr->mmr.key;
+	mr->ibmr.rkey = mr->mmr.key;
+	mr->umem = NULL;
+	kfree(in);
+
+	return &mr->ibmr;
+
+err_destroy_psv:
+	if (mr->sig) {
+		if (mlx5_core_destroy_psv(&dev->mdev,
+					  mr->sig->psv_memory.psv_idx))
+			mlx5_ib_warn(dev, "failed to destroy mem psv %d\n",
+				     mr->sig->psv_memory.psv_idx);
+		if (mlx5_core_destroy_psv(&dev->mdev,
+					  mr->sig->psv_wire.psv_idx))
+			mlx5_ib_warn(dev, "failed to destroy wire psv %d\n",
+				     mr->sig->psv_wire.psv_idx);
+	}
+err_free_sig:
+	kfree(mr->sig);
+err_free_in:
+	kfree(in);
+err_free:
+	kfree(mr);
+	return ERR_PTR(err);
+}
+
+int mlx5_ib_destroy_mr(struct ib_mr *ibmr)
+{
+	struct mlx5_ib_dev *dev = to_mdev(ibmr->device);
+	struct mlx5_ib_mr *mr = to_mmr(ibmr);
+	int err;
+
+	if (mr->sig) {
+		if (mlx5_core_destroy_psv(&dev->mdev,
+					  mr->sig->psv_memory.psv_idx))
+			mlx5_ib_warn(dev, "failed to destroy mem psv %d\n",
+				     mr->sig->psv_memory.psv_idx);
+		if (mlx5_core_destroy_psv(&dev->mdev,
+					  mr->sig->psv_wire.psv_idx))
+			mlx5_ib_warn(dev, "failed to destroy wire psv %d\n",
+				     mr->sig->psv_wire.psv_idx);
+		kfree(mr->sig);
+	}
+
+	err = mlx5_core_destroy_mkey(&dev->mdev, &mr->mmr);
+	if (err) {
+		mlx5_ib_warn(dev, "failed to destroy mkey 0x%x (%d)\n",
+			     mr->mmr.key, err);
+		return err;
+	}
+
+	kfree(mr);
+
+	return err;
+}
+
 struct ib_mr *mlx5_ib_alloc_fast_reg_mr(struct ib_pd *pd,
 					int max_page_list_len)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index 35e514dc7b7d..bb746bbe73c6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -144,3 +144,64 @@ int mlx5_core_dump_fill_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
 	return err;
 }
 EXPORT_SYMBOL(mlx5_core_dump_fill_mkey);
+
+int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn,
+			 int npsvs, u32 *sig_index)
+{
+	struct mlx5_allocate_psv_in in;
+	struct mlx5_allocate_psv_out out;
+	int i, err;
+
+	if (npsvs > MLX5_MAX_PSVS)
+		return -EINVAL;
+
+	memset(&in, 0, sizeof(in));
+	memset(&out, 0, sizeof(out));
+
+	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_CREATE_PSV);
+	in.npsv_pd = cpu_to_be32((npsvs << 28) | pdn);
+	err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
+	if (err) {
+		mlx5_core_err(dev, "cmd exec failed %d\n", err);
+		return err;
+	}
+
+	if (out.hdr.status) {
+		mlx5_core_err(dev, "create_psv bad status %d\n", out.hdr.status);
+		return mlx5_cmd_status_to_err(&out.hdr);
+	}
+
+	for (i = 0; i < npsvs; i++)
+		sig_index[i] = be32_to_cpu(out.psv_idx[i]) & 0xffffff;
+
+	return err;
+}
+EXPORT_SYMBOL(mlx5_core_create_psv);
+
+int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num)
+{
+	struct mlx5_destroy_psv_in in;
+	struct mlx5_destroy_psv_out out;
+	int err;
+
+	memset(&in, 0, sizeof(in));
+	memset(&out, 0, sizeof(out));
+
+	in.psv_number = cpu_to_be32(psv_num);
+	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_DESTROY_PSV);
+	err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
+	if (err) {
+		mlx5_core_err(dev, "destroy_psv cmd exec failed %d\n", err);
+		goto out;
+	}
+
+	if (out.hdr.status) {
+		mlx5_core_err(dev, "destroy_psv bad status %d\n", out.hdr.status);
+		err = mlx5_cmd_status_to_err(&out.hdr);
+		goto out;
+	}
+
+out:
+	return err;
+}
+EXPORT_SYMBOL(mlx5_core_destroy_psv);
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 817a6fae6d2c..f714fc427765 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -48,6 +48,8 @@ enum {
 	MLX5_MAX_COMMANDS		= 32,
 	MLX5_CMD_DATA_BLOCK_SIZE	= 512,
 	MLX5_PCI_CMD_XPORT		= 7,
+	MLX5_MKEY_BSF_OCTO_SIZE		= 4,
+	MLX5_MAX_PSVS			= 4,
 };
 
 enum {
@@ -936,4 +938,27 @@ enum {
 	MLX_EXT_PORT_CAP_FLAG_EXTENDED_PORT_INFO	= 1 <<  0
 };
 
+struct mlx5_allocate_psv_in {
+	struct mlx5_inbox_hdr   hdr;
+	__be32			npsv_pd;
+	__be32			rsvd_psv0;
+};
+
+struct mlx5_allocate_psv_out {
+	struct mlx5_outbox_hdr  hdr;
+	u8			rsvd[8];
+	__be32			psv_idx[4];
+};
+
+struct mlx5_destroy_psv_in {
+	struct mlx5_inbox_hdr	hdr;
+	__be32                  psv_number;
+	u8                      rsvd[4];
+};
+
+struct mlx5_destroy_psv_out {
+	struct mlx5_outbox_hdr  hdr;
+	u8                      rsvd[8];
+};
+
 #endif /* MLX5_DEVICE_H */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 130bc8d77fa5..e1cb657ccade 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -401,6 +401,22 @@ struct mlx5_eq {
 	struct mlx5_rsc_debug	*dbg;
 };
 
+struct mlx5_core_psv {
+	u32	psv_idx;
+	struct psv_layout {
+		u32	pd;
+		u16	syndrome;
+		u16	reserved;
+		u16	bg;
+		u16	app_tag;
+		u32	ref_tag;
+	} psv;
+};
+
+struct mlx5_core_sig_ctx {
+	struct mlx5_core_psv	psv_memory;
+	struct mlx5_core_psv	psv_wire;
+};
 
 struct mlx5_core_mr {
 	u64			iova;
@@ -746,6 +762,9 @@ void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db);
 const char *mlx5_command_str(int command);
 int mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev);
 void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev);
+int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn,
+			 int npsvs, u32 *sig_index);
+int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num);
 
 static inline u32 mlx5_mkey_to_idx(u32 mkey)
 {
-- 
cgit v1.2.3


From e1e66cc26457c2e9412f67618646ec2a441fc409 Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagig@mellanox.com>
Date: Sun, 23 Feb 2014 14:19:07 +0200
Subject: IB/mlx5: Initialize mlx5_ib_qp signature-related members

If user requested signature enable we initialize relevant mlx5_ib_qp
members.  We mark the qp as sig_enable and we increase the effective
SQ size, but still limit the user max_send_wr to original size
computed.  We also allow the create_qp routine to accept sig_enable
create flag.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx5/mlx5_ib.h |  3 +++
 drivers/infiniband/hw/mlx5/qp.c      | 12 +++++++++---
 include/linux/mlx5/qp.h              |  1 +
 3 files changed, 13 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 79c4f14c4d3e..e438f08899ae 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -189,6 +189,9 @@ struct mlx5_ib_qp {
 
 	int			create_type;
 	u32			pa_lkey;
+
+	/* Store signature errors */
+	bool			signature_en;
 };
 
 struct mlx5_ib_cq_buf {
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 7dfe8a1c84cf..01999f3744fb 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -256,8 +256,11 @@ static int calc_send_wqe(struct ib_qp_init_attr *attr)
 	}
 
 	size += attr->cap.max_send_sge * sizeof(struct mlx5_wqe_data_seg);
-
-	return ALIGN(max_t(int, inl_size, size), MLX5_SEND_WQE_BB);
+	if (attr->create_flags & IB_QP_CREATE_SIGNATURE_EN &&
+	    ALIGN(max_t(int, inl_size, size), MLX5_SEND_WQE_BB) < MLX5_SIG_WQE_SIZE)
+			return MLX5_SIG_WQE_SIZE;
+	else
+		return ALIGN(max_t(int, inl_size, size), MLX5_SEND_WQE_BB);
 }
 
 static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr,
@@ -284,6 +287,9 @@ static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr,
 		sizeof(struct mlx5_wqe_inline_seg);
 	attr->cap.max_inline_data = qp->max_inline_data;
 
+	if (attr->create_flags & IB_QP_CREATE_SIGNATURE_EN)
+		qp->signature_en = true;
+
 	wq_size = roundup_pow_of_two(attr->cap.max_send_wr * wqe_size);
 	qp->sq.wqe_cnt = wq_size / MLX5_SEND_WQE_BB;
 	if (qp->sq.wqe_cnt > dev->mdev.caps.max_wqes) {
@@ -665,7 +671,7 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev,
 	int err;
 
 	uuari = &dev->mdev.priv.uuari;
-	if (init_attr->create_flags)
+	if (init_attr->create_flags & ~IB_QP_CREATE_SIGNATURE_EN)
 		return -EINVAL;
 
 	if (init_attr->qp_type == MLX5_IB_QPT_REG_UMR)
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index d51eff713549..152756eaa8a3 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -37,6 +37,7 @@
 #include <linux/mlx5/driver.h>
 
 #define MLX5_INVALID_LKEY	0x100
+#define MLX5_SIG_WQE_SIZE	(MLX5_SEND_WQE_BB * 5)
 
 enum mlx5_qp_optpar {
 	MLX5_QP_OPTPAR_ALT_ADDR_PATH		= 1 << 0,
-- 
cgit v1.2.3


From 3bcdb17a5e88288ead90be3c107e754a6075a5b0 Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagig@mellanox.com>
Date: Sun, 23 Feb 2014 14:19:10 +0200
Subject: IB/mlx5: Keep mlx5 MRs in a radix tree under device

This will be useful when processing signature errors on a specific
key.  The mlx5 driver will lookup the matching mlx5 memory region
structure and mark it as dirty (contains signature errors).

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/mr.c   | 24 ++++++++++++++++++++++++
 include/linux/mlx5/driver.h                    | 18 ++++++++++++++++++
 3 files changed, 43 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index a064f06e0cb8..96a0617f7609 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -446,6 +446,7 @@ int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev)
 	mlx5_init_cq_table(dev);
 	mlx5_init_qp_table(dev);
 	mlx5_init_srq_table(dev);
+	mlx5_init_mr_table(dev);
 
 	return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index bb746bbe73c6..4cc927649404 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -36,11 +36,24 @@
 #include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
 
+void mlx5_init_mr_table(struct mlx5_core_dev *dev)
+{
+	struct mlx5_mr_table *table = &dev->priv.mr_table;
+
+	rwlock_init(&table->lock);
+	INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
+}
+
+void mlx5_cleanup_mr_table(struct mlx5_core_dev *dev)
+{
+}
+
 int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
 			  struct mlx5_create_mkey_mbox_in *in, int inlen,
 			  mlx5_cmd_cbk_t callback, void *context,
 			  struct mlx5_create_mkey_mbox_out *out)
 {
+	struct mlx5_mr_table *table = &dev->priv.mr_table;
 	struct mlx5_create_mkey_mbox_out lout;
 	int err;
 	u8 key;
@@ -73,14 +86,21 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
 	mlx5_core_dbg(dev, "out 0x%x, key 0x%x, mkey 0x%x\n",
 		      be32_to_cpu(lout.mkey), key, mr->key);
 
+	/* connect to MR tree */
+	write_lock_irq(&table->lock);
+	err = radix_tree_insert(&table->tree, mlx5_base_mkey(mr->key), mr);
+	write_unlock_irq(&table->lock);
+
 	return err;
 }
 EXPORT_SYMBOL(mlx5_core_create_mkey);
 
 int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr)
 {
+	struct mlx5_mr_table *table = &dev->priv.mr_table;
 	struct mlx5_destroy_mkey_mbox_in in;
 	struct mlx5_destroy_mkey_mbox_out out;
+	unsigned long flags;
 	int err;
 
 	memset(&in, 0, sizeof(in));
@@ -95,6 +115,10 @@ int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr)
 	if (out.hdr.status)
 		return mlx5_cmd_status_to_err(&out.hdr);
 
+	write_lock_irqsave(&table->lock, flags);
+	radix_tree_delete(&table->tree, mlx5_base_mkey(mr->key));
+	write_unlock_irqrestore(&table->lock, flags);
+
 	return err;
 }
 EXPORT_SYMBOL(mlx5_core_destroy_mkey);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index e1cb657ccade..e562e01e59c7 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -491,6 +491,13 @@ struct mlx5_srq_table {
 	struct radix_tree_root	tree;
 };
 
+struct mlx5_mr_table {
+	/* protect radix tree
+	 */
+	rwlock_t		lock;
+	struct radix_tree_root	tree;
+};
+
 struct mlx5_priv {
 	char			name[MLX5_MAX_NAME_LEN];
 	struct mlx5_eq_table	eq_table;
@@ -520,6 +527,10 @@ struct mlx5_priv {
 	struct mlx5_cq_table	cq_table;
 	/* end: cq staff */
 
+	/* start: mr staff */
+	struct mlx5_mr_table	mr_table;
+	/* end: mr staff */
+
 	/* start: alloc staff */
 	struct mutex            pgdir_mutex;
 	struct list_head        pgdir_list;
@@ -667,6 +678,11 @@ static inline void mlx5_vfree(const void *addr)
 		kfree(addr);
 }
 
+static inline u32 mlx5_base_mkey(const u32 key)
+{
+	return key & 0xffffff00u;
+}
+
 int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev);
 void mlx5_dev_cleanup(struct mlx5_core_dev *dev);
 int mlx5_cmd_init(struct mlx5_core_dev *dev);
@@ -701,6 +717,8 @@ int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 			struct mlx5_query_srq_mbox_out *out);
 int mlx5_core_arm_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
 		      u16 lwm, int is_srq);
+void mlx5_init_mr_table(struct mlx5_core_dev *dev);
+void mlx5_cleanup_mr_table(struct mlx5_core_dev *dev);
 int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
 			  struct mlx5_create_mkey_mbox_in *in, int inlen,
 			  mlx5_cmd_cbk_t callback, void *context,
-- 
cgit v1.2.3


From e6631814fb3ac454fbbf47ea343c2b9508e4e1ba Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagig@mellanox.com>
Date: Sun, 23 Feb 2014 14:19:11 +0200
Subject: IB/mlx5: Support IB_WR_REG_SIG_MR

This patch implements IB_WR_REG_SIG_MR posted by the user.

Baisically this WR involves 3 WQEs in order to prepare and properly
register the signature layout:

1. post UMR WR to register the sig_mr in one of two possible ways:
    * In case the user registered a single MR for data so the UMR data segment
      consists of:
      - single klm (data MR) passed by the user
      - BSF with signature attributes requested by the user.
    * In case the user registered 2 MRs, one for data and one for protection,
      the UMR consists of:
      - strided block format which includes data and protection MRs and
        their repetitive block format.
      - BSF with signature attributes requested by the user.

2. post SET_PSV in order to set the memory domain initial
   signature parameters passed by the user.
   SET_PSV is not signaled and solicited CQE.

3. post SET_PSV in order to set the wire domain initial
   signature parameters passed by the user.
   SET_PSV is not signaled and solicited CQE.

* After this compound WR we place a small fence for next WR to come.

This patch also introduces some helper functions to set the BSF correctly
and determining the signature format selectors.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx5/qp.c | 422 ++++++++++++++++++++++++++++++++++++++++
 include/linux/mlx5/qp.h         |  61 ++++++
 2 files changed, 483 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 1dbadbfc4474..67e79989b181 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1777,6 +1777,26 @@ static __be64 frwr_mkey_mask(void)
 	return cpu_to_be64(result);
 }
 
+static __be64 sig_mkey_mask(void)
+{
+	u64 result;
+
+	result = MLX5_MKEY_MASK_LEN		|
+		MLX5_MKEY_MASK_PAGE_SIZE	|
+		MLX5_MKEY_MASK_START_ADDR	|
+		MLX5_MKEY_MASK_EN_RINVAL	|
+		MLX5_MKEY_MASK_KEY		|
+		MLX5_MKEY_MASK_LR		|
+		MLX5_MKEY_MASK_LW		|
+		MLX5_MKEY_MASK_RR		|
+		MLX5_MKEY_MASK_RW		|
+		MLX5_MKEY_MASK_SMALL_FENCE	|
+		MLX5_MKEY_MASK_FREE		|
+		MLX5_MKEY_MASK_BSF_EN;
+
+	return cpu_to_be64(result);
+}
+
 static void set_frwr_umr_segment(struct mlx5_wqe_umr_ctrl_seg *umr,
 				 struct ib_send_wr *wr, int li)
 {
@@ -1961,6 +1981,339 @@ static int set_data_inl_seg(struct mlx5_ib_qp *qp, struct ib_send_wr *wr,
 	return 0;
 }
 
+static u16 prot_field_size(enum ib_signature_type type)
+{
+	switch (type) {
+	case IB_SIG_TYPE_T10_DIF:
+		return MLX5_DIF_SIZE;
+	default:
+		return 0;
+	}
+}
+
+static u8 bs_selector(int block_size)
+{
+	switch (block_size) {
+	case 512:	    return 0x1;
+	case 520:	    return 0x2;
+	case 4096:	    return 0x3;
+	case 4160:	    return 0x4;
+	case 1073741824:    return 0x5;
+	default:	    return 0;
+	}
+}
+
+static int format_selector(struct ib_sig_attrs *attr,
+			   struct ib_sig_domain *domain,
+			   int *selector)
+{
+
+#define FORMAT_DIF_NONE		0
+#define FORMAT_DIF_CRC_INC	8
+#define FORMAT_DIF_CRC_NO_INC	12
+#define FORMAT_DIF_CSUM_INC	13
+#define FORMAT_DIF_CSUM_NO_INC	14
+
+	switch (domain->sig.dif.type) {
+	case IB_T10DIF_NONE:
+		/* No DIF */
+		*selector = FORMAT_DIF_NONE;
+		break;
+	case IB_T10DIF_TYPE1: /* Fall through */
+	case IB_T10DIF_TYPE2:
+		switch (domain->sig.dif.bg_type) {
+		case IB_T10DIF_CRC:
+			*selector = FORMAT_DIF_CRC_INC;
+			break;
+		case IB_T10DIF_CSUM:
+			*selector = FORMAT_DIF_CSUM_INC;
+			break;
+		default:
+			return 1;
+		}
+		break;
+	case IB_T10DIF_TYPE3:
+		switch (domain->sig.dif.bg_type) {
+		case IB_T10DIF_CRC:
+			*selector = domain->sig.dif.type3_inc_reftag ?
+					   FORMAT_DIF_CRC_INC :
+					   FORMAT_DIF_CRC_NO_INC;
+			break;
+		case IB_T10DIF_CSUM:
+			*selector = domain->sig.dif.type3_inc_reftag ?
+					   FORMAT_DIF_CSUM_INC :
+					   FORMAT_DIF_CSUM_NO_INC;
+			break;
+		default:
+			return 1;
+		}
+		break;
+	default:
+		return 1;
+	}
+
+	return 0;
+}
+
+static int mlx5_set_bsf(struct ib_mr *sig_mr,
+			struct ib_sig_attrs *sig_attrs,
+			struct mlx5_bsf *bsf, u32 data_size)
+{
+	struct mlx5_core_sig_ctx *msig = to_mmr(sig_mr)->sig;
+	struct mlx5_bsf_basic *basic = &bsf->basic;
+	struct ib_sig_domain *mem = &sig_attrs->mem;
+	struct ib_sig_domain *wire = &sig_attrs->wire;
+	int ret, selector;
+
+	switch (sig_attrs->mem.sig_type) {
+	case IB_SIG_TYPE_T10_DIF:
+		if (sig_attrs->wire.sig_type != IB_SIG_TYPE_T10_DIF)
+			return -EINVAL;
+
+		/* Input domain check byte mask */
+		basic->check_byte_mask = sig_attrs->check_mask;
+		if (mem->sig.dif.pi_interval == wire->sig.dif.pi_interval &&
+		    mem->sig.dif.type == wire->sig.dif.type) {
+			/* Same block structure */
+			basic->bsf_size_sbs = 1 << 4;
+			if (mem->sig.dif.bg_type == wire->sig.dif.bg_type)
+				basic->wire.copy_byte_mask = 0xff;
+			else
+				basic->wire.copy_byte_mask = 0x3f;
+		} else
+			basic->wire.bs_selector = bs_selector(wire->sig.dif.pi_interval);
+
+		basic->mem.bs_selector = bs_selector(mem->sig.dif.pi_interval);
+		basic->raw_data_size = cpu_to_be32(data_size);
+
+		ret = format_selector(sig_attrs, mem, &selector);
+		if (ret)
+			return -EINVAL;
+		basic->m_bfs_psv = cpu_to_be32(selector << 24 |
+					       msig->psv_memory.psv_idx);
+
+		ret = format_selector(sig_attrs, wire, &selector);
+		if (ret)
+			return -EINVAL;
+		basic->w_bfs_psv = cpu_to_be32(selector << 24 |
+					       msig->psv_wire.psv_idx);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int set_sig_data_segment(struct ib_send_wr *wr, struct mlx5_ib_qp *qp,
+				void **seg, int *size)
+{
+	struct ib_sig_attrs *sig_attrs = wr->wr.sig_handover.sig_attrs;
+	struct ib_mr *sig_mr = wr->wr.sig_handover.sig_mr;
+	struct mlx5_bsf *bsf;
+	u32 data_len = wr->sg_list->length;
+	u32 data_key = wr->sg_list->lkey;
+	u64 data_va = wr->sg_list->addr;
+	int ret;
+	int wqe_size;
+
+	if (!wr->wr.sig_handover.prot) {
+		/**
+		 * Source domain doesn't contain signature information
+		 * So need construct:
+		 *                  ------------------
+		 *                 |     data_klm     |
+		 *                  ------------------
+		 *                 |       BSF        |
+		 *                  ------------------
+		 **/
+		struct mlx5_klm *data_klm = *seg;
+
+		data_klm->bcount = cpu_to_be32(data_len);
+		data_klm->key = cpu_to_be32(data_key);
+		data_klm->va = cpu_to_be64(data_va);
+		wqe_size = ALIGN(sizeof(*data_klm), 64);
+	} else {
+		/**
+		 * Source domain contains signature information
+		 * So need construct a strided block format:
+		 *               ---------------------------
+		 *              |     stride_block_ctrl     |
+		 *               ---------------------------
+		 *              |          data_klm         |
+		 *               ---------------------------
+		 *              |          prot_klm         |
+		 *               ---------------------------
+		 *              |             BSF           |
+		 *               ---------------------------
+		 **/
+		struct mlx5_stride_block_ctrl_seg *sblock_ctrl;
+		struct mlx5_stride_block_entry *data_sentry;
+		struct mlx5_stride_block_entry *prot_sentry;
+		u32 prot_key = wr->wr.sig_handover.prot->lkey;
+		u64 prot_va = wr->wr.sig_handover.prot->addr;
+		u16 block_size = sig_attrs->mem.sig.dif.pi_interval;
+		int prot_size;
+
+		sblock_ctrl = *seg;
+		data_sentry = (void *)sblock_ctrl + sizeof(*sblock_ctrl);
+		prot_sentry = (void *)data_sentry + sizeof(*data_sentry);
+
+		prot_size = prot_field_size(sig_attrs->mem.sig_type);
+		if (!prot_size) {
+			pr_err("Bad block size given: %u\n", block_size);
+			return -EINVAL;
+		}
+		sblock_ctrl->bcount_per_cycle = cpu_to_be32(block_size +
+							    prot_size);
+		sblock_ctrl->op = cpu_to_be32(MLX5_STRIDE_BLOCK_OP);
+		sblock_ctrl->repeat_count = cpu_to_be32(data_len / block_size);
+		sblock_ctrl->num_entries = cpu_to_be16(2);
+
+		data_sentry->bcount = cpu_to_be16(block_size);
+		data_sentry->key = cpu_to_be32(data_key);
+		data_sentry->va = cpu_to_be64(data_va);
+		prot_sentry->bcount = cpu_to_be16(prot_size);
+		prot_sentry->key = cpu_to_be32(prot_key);
+
+		if (prot_key == data_key && prot_va == data_va) {
+			/**
+			 * The data and protection are interleaved
+			 * in a single memory region
+			 **/
+			prot_sentry->va = cpu_to_be64(data_va + block_size);
+			prot_sentry->stride = cpu_to_be16(block_size + prot_size);
+			data_sentry->stride = prot_sentry->stride;
+		} else {
+			/* The data and protection are two different buffers */
+			prot_sentry->va = cpu_to_be64(prot_va);
+			data_sentry->stride = cpu_to_be16(block_size);
+			prot_sentry->stride = cpu_to_be16(prot_size);
+		}
+		wqe_size = ALIGN(sizeof(*sblock_ctrl) + sizeof(*data_sentry) +
+				 sizeof(*prot_sentry), 64);
+	}
+
+	*seg += wqe_size;
+	*size += wqe_size / 16;
+	if (unlikely((*seg == qp->sq.qend)))
+		*seg = mlx5_get_send_wqe(qp, 0);
+
+	bsf = *seg;
+	ret = mlx5_set_bsf(sig_mr, sig_attrs, bsf, data_len);
+	if (ret)
+		return -EINVAL;
+
+	*seg += sizeof(*bsf);
+	*size += sizeof(*bsf) / 16;
+	if (unlikely((*seg == qp->sq.qend)))
+		*seg = mlx5_get_send_wqe(qp, 0);
+
+	return 0;
+}
+
+static void set_sig_mkey_segment(struct mlx5_mkey_seg *seg,
+				 struct ib_send_wr *wr, u32 nelements,
+				 u32 length, u32 pdn)
+{
+	struct ib_mr *sig_mr = wr->wr.sig_handover.sig_mr;
+	u32 sig_key = sig_mr->rkey;
+
+	memset(seg, 0, sizeof(*seg));
+
+	seg->flags = get_umr_flags(wr->wr.sig_handover.access_flags) |
+				   MLX5_ACCESS_MODE_KLM;
+	seg->qpn_mkey7_0 = cpu_to_be32((sig_key & 0xff) | 0xffffff00);
+	seg->flags_pd = cpu_to_be32(MLX5_MKEY_REMOTE_INVAL |
+				    MLX5_MKEY_BSF_EN | pdn);
+	seg->len = cpu_to_be64(length);
+	seg->xlt_oct_size = cpu_to_be32(be16_to_cpu(get_klm_octo(nelements)));
+	seg->bsfs_octo_size = cpu_to_be32(MLX5_MKEY_BSF_OCTO_SIZE);
+}
+
+static void set_sig_umr_segment(struct mlx5_wqe_umr_ctrl_seg *umr,
+				struct ib_send_wr *wr, u32 nelements)
+{
+	memset(umr, 0, sizeof(*umr));
+
+	umr->flags = MLX5_FLAGS_INLINE | MLX5_FLAGS_CHECK_FREE;
+	umr->klm_octowords = get_klm_octo(nelements);
+	umr->bsf_octowords = cpu_to_be16(MLX5_MKEY_BSF_OCTO_SIZE);
+	umr->mkey_mask = sig_mkey_mask();
+}
+
+
+static int set_sig_umr_wr(struct ib_send_wr *wr, struct mlx5_ib_qp *qp,
+			  void **seg, int *size)
+{
+	struct mlx5_ib_mr *sig_mr = to_mmr(wr->wr.sig_handover.sig_mr);
+	u32 pdn = get_pd(qp)->pdn;
+	u32 klm_oct_size;
+	int region_len, ret;
+
+	if (unlikely(wr->num_sge != 1) ||
+	    unlikely(wr->wr.sig_handover.access_flags &
+		     IB_ACCESS_REMOTE_ATOMIC) ||
+	    unlikely(!sig_mr->sig) || unlikely(!qp->signature_en))
+		return -EINVAL;
+
+	/* length of the protected region, data + protection */
+	region_len = wr->sg_list->length;
+	if (wr->wr.sig_handover.prot)
+		region_len += wr->wr.sig_handover.prot->length;
+
+	/**
+	 * KLM octoword size - if protection was provided
+	 * then we use strided block format (3 octowords),
+	 * else we use single KLM (1 octoword)
+	 **/
+	klm_oct_size = wr->wr.sig_handover.prot ? 3 : 1;
+
+	set_sig_umr_segment(*seg, wr, klm_oct_size);
+	*seg += sizeof(struct mlx5_wqe_umr_ctrl_seg);
+	*size += sizeof(struct mlx5_wqe_umr_ctrl_seg) / 16;
+	if (unlikely((*seg == qp->sq.qend)))
+		*seg = mlx5_get_send_wqe(qp, 0);
+
+	set_sig_mkey_segment(*seg, wr, klm_oct_size, region_len, pdn);
+	*seg += sizeof(struct mlx5_mkey_seg);
+	*size += sizeof(struct mlx5_mkey_seg) / 16;
+	if (unlikely((*seg == qp->sq.qend)))
+		*seg = mlx5_get_send_wqe(qp, 0);
+
+	ret = set_sig_data_segment(wr, qp, seg, size);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int set_psv_wr(struct ib_sig_domain *domain,
+		      u32 psv_idx, void **seg, int *size)
+{
+	struct mlx5_seg_set_psv *psv_seg = *seg;
+
+	memset(psv_seg, 0, sizeof(*psv_seg));
+	psv_seg->psv_num = cpu_to_be32(psv_idx);
+	switch (domain->sig_type) {
+	case IB_SIG_TYPE_T10_DIF:
+		psv_seg->transient_sig = cpu_to_be32(domain->sig.dif.bg << 16 |
+						     domain->sig.dif.app_tag);
+		psv_seg->ref_tag = cpu_to_be32(domain->sig.dif.ref_tag);
+
+		*seg += sizeof(*psv_seg);
+		*size += sizeof(*psv_seg) / 16;
+		break;
+
+	default:
+		pr_err("Bad signature type given.\n");
+		return 1;
+	}
+
+	return 0;
+}
+
 static int set_frwr_li_wr(void **seg, struct ib_send_wr *wr, int *size,
 			  struct mlx5_core_dev *mdev, struct mlx5_ib_pd *pd, struct mlx5_ib_qp *qp)
 {
@@ -2108,6 +2461,7 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 	struct mlx5_ib_dev *dev = to_mdev(ibqp->device);
 	struct mlx5_core_dev *mdev = &dev->mdev;
 	struct mlx5_ib_qp *qp = to_mqp(ibqp);
+	struct mlx5_ib_mr *mr;
 	struct mlx5_wqe_data_seg *dpseg;
 	struct mlx5_wqe_xrc_seg *xrc;
 	struct mlx5_bf *bf = qp->bf;
@@ -2203,6 +2557,73 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 				num_sge = 0;
 				break;
 
+			case IB_WR_REG_SIG_MR:
+				qp->sq.wr_data[idx] = IB_WR_REG_SIG_MR;
+				mr = to_mmr(wr->wr.sig_handover.sig_mr);
+
+				ctrl->imm = cpu_to_be32(mr->ibmr.rkey);
+				err = set_sig_umr_wr(wr, qp, &seg, &size);
+				if (err) {
+					mlx5_ib_warn(dev, "\n");
+					*bad_wr = wr;
+					goto out;
+				}
+
+				finish_wqe(qp, ctrl, size, idx, wr->wr_id,
+					   nreq, get_fence(fence, wr),
+					   next_fence, MLX5_OPCODE_UMR);
+				/*
+				 * SET_PSV WQEs are not signaled and solicited
+				 * on error
+				 */
+				wr->send_flags &= ~IB_SEND_SIGNALED;
+				wr->send_flags |= IB_SEND_SOLICITED;
+				err = begin_wqe(qp, &seg, &ctrl, wr,
+						&idx, &size, nreq);
+				if (err) {
+					mlx5_ib_warn(dev, "\n");
+					err = -ENOMEM;
+					*bad_wr = wr;
+					goto out;
+				}
+
+				err = set_psv_wr(&wr->wr.sig_handover.sig_attrs->mem,
+						 mr->sig->psv_memory.psv_idx, &seg,
+						 &size);
+				if (err) {
+					mlx5_ib_warn(dev, "\n");
+					*bad_wr = wr;
+					goto out;
+				}
+
+				finish_wqe(qp, ctrl, size, idx, wr->wr_id,
+					   nreq, get_fence(fence, wr),
+					   next_fence, MLX5_OPCODE_SET_PSV);
+				err = begin_wqe(qp, &seg, &ctrl, wr,
+						&idx, &size, nreq);
+				if (err) {
+					mlx5_ib_warn(dev, "\n");
+					err = -ENOMEM;
+					*bad_wr = wr;
+					goto out;
+				}
+
+				next_fence = MLX5_FENCE_MODE_INITIATOR_SMALL;
+				err = set_psv_wr(&wr->wr.sig_handover.sig_attrs->wire,
+						 mr->sig->psv_wire.psv_idx, &seg,
+						 &size);
+				if (err) {
+					mlx5_ib_warn(dev, "\n");
+					*bad_wr = wr;
+					goto out;
+				}
+
+				finish_wqe(qp, ctrl, size, idx, wr->wr_id,
+					   nreq, get_fence(fence, wr),
+					   next_fence, MLX5_OPCODE_SET_PSV);
+				num_sge = 0;
+				goto skip_psv;
+
 			default:
 				break;
 			}
@@ -2286,6 +2707,7 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		finish_wqe(qp, ctrl, size, idx, wr->wr_id, nreq,
 			   get_fence(fence, wr), next_fence,
 			   mlx5_ib_opcode[wr->opcode]);
+skip_psv:
 		if (0)
 			dump_wqe(qp, idx, size);
 	}
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 152756eaa8a3..49af74f90ef9 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -38,6 +38,8 @@
 
 #define MLX5_INVALID_LKEY	0x100
 #define MLX5_SIG_WQE_SIZE	(MLX5_SEND_WQE_BB * 5)
+#define MLX5_DIF_SIZE		8
+#define MLX5_STRIDE_BLOCK_OP	0x400
 
 enum mlx5_qp_optpar {
 	MLX5_QP_OPTPAR_ALT_ADDR_PATH		= 1 << 0,
@@ -152,6 +154,11 @@ enum {
 	MLX5_SND_DBR	= 1,
 };
 
+enum {
+	MLX5_FLAGS_INLINE	= 1<<7,
+	MLX5_FLAGS_CHECK_FREE   = 1<<5,
+};
+
 struct mlx5_wqe_fmr_seg {
 	__be32			flags;
 	__be32			mem_key;
@@ -279,6 +286,60 @@ struct mlx5_wqe_inline_seg {
 	__be32	byte_count;
 };
 
+struct mlx5_bsf {
+	struct mlx5_bsf_basic {
+		u8		bsf_size_sbs;
+		u8		check_byte_mask;
+		union {
+			u8	copy_byte_mask;
+			u8	bs_selector;
+			u8	rsvd_wflags;
+		} wire;
+		union {
+			u8	bs_selector;
+			u8	rsvd_mflags;
+		} mem;
+		__be32		raw_data_size;
+		__be32		w_bfs_psv;
+		__be32		m_bfs_psv;
+	} basic;
+	struct mlx5_bsf_ext {
+		__be32		t_init_gen_pro_size;
+		__be32		rsvd_epi_size;
+		__be32		w_tfs_psv;
+		__be32		m_tfs_psv;
+	} ext;
+	struct mlx5_bsf_inl {
+		__be32		w_inl_vld;
+		__be32		w_rsvd;
+		__be64		w_block_format;
+		__be32		m_inl_vld;
+		__be32		m_rsvd;
+		__be64		m_block_format;
+	} inl;
+};
+
+struct mlx5_klm {
+	__be32		bcount;
+	__be32		key;
+	__be64		va;
+};
+
+struct mlx5_stride_block_entry {
+	__be16		stride;
+	__be16		bcount;
+	__be32		key;
+	__be64		va;
+};
+
+struct mlx5_stride_block_ctrl_seg {
+	__be32		bcount_per_cycle;
+	__be32		op;
+	__be32		repeat_count;
+	u16		rsvd;
+	__be16		num_entries;
+};
+
 struct mlx5_core_qp {
 	void (*event)		(struct mlx5_core_qp *, int);
 	int			qpn;
-- 
cgit v1.2.3


From d5436ba01075ef4629015f7a00914d64ffd795d6 Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagig@mellanox.com>
Date: Sun, 23 Feb 2014 14:19:12 +0200
Subject: IB/mlx5: Collect signature error completion

This commit takes care of the generated signature error CQE generated
by the HW (if happened).  The underlying mlx5 driver will handle
signature error completions and will mark the relevant memory region
as dirty.

Once the consumer gets the completion for the transaction, it must
check for signature errors on signature memory region using a new
lightweight verb ib_check_mr_status().

In case the user doesn't check for signature error (i.e. doesn't call
ib_check_mr_status() with status check IB_MR_CHECK_SIG_STATUS), the
memory region cannot be used for another signature operation
(REG_SIG_MR work request will fail).

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx5/cq.c      | 62 ++++++++++++++++++++++++++++++++++++
 drivers/infiniband/hw/mlx5/main.c    |  1 +
 drivers/infiniband/hw/mlx5/mlx5_ib.h |  7 ++++
 drivers/infiniband/hw/mlx5/mr.c      | 46 ++++++++++++++++++++++++++
 drivers/infiniband/hw/mlx5/qp.c      |  8 +++--
 include/linux/mlx5/cq.h              |  1 +
 include/linux/mlx5/device.h          | 18 +++++++++++
 include/linux/mlx5/driver.h          |  4 +++
 include/linux/mlx5/qp.h              |  5 +++
 9 files changed, 150 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index b1705ce6eb88..62bb6b49dc1d 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -366,6 +366,38 @@ static void free_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf)
 	mlx5_buf_free(&dev->mdev, &buf->buf);
 }
 
+static void get_sig_err_item(struct mlx5_sig_err_cqe *cqe,
+			     struct ib_sig_err *item)
+{
+	u16 syndrome = be16_to_cpu(cqe->syndrome);
+
+#define GUARD_ERR   (1 << 13)
+#define APPTAG_ERR  (1 << 12)
+#define REFTAG_ERR  (1 << 11)
+
+	if (syndrome & GUARD_ERR) {
+		item->err_type = IB_SIG_BAD_GUARD;
+		item->expected = be32_to_cpu(cqe->expected_trans_sig) >> 16;
+		item->actual = be32_to_cpu(cqe->actual_trans_sig) >> 16;
+	} else
+	if (syndrome & REFTAG_ERR) {
+		item->err_type = IB_SIG_BAD_REFTAG;
+		item->expected = be32_to_cpu(cqe->expected_reftag);
+		item->actual = be32_to_cpu(cqe->actual_reftag);
+	} else
+	if (syndrome & APPTAG_ERR) {
+		item->err_type = IB_SIG_BAD_APPTAG;
+		item->expected = be32_to_cpu(cqe->expected_trans_sig) & 0xffff;
+		item->actual = be32_to_cpu(cqe->actual_trans_sig) & 0xffff;
+	} else {
+		pr_err("Got signature completion error with bad syndrome %04x\n",
+		       syndrome);
+	}
+
+	item->sig_err_offset = be64_to_cpu(cqe->err_offset);
+	item->key = be32_to_cpu(cqe->mkey);
+}
+
 static int mlx5_poll_one(struct mlx5_ib_cq *cq,
 			 struct mlx5_ib_qp **cur_qp,
 			 struct ib_wc *wc)
@@ -375,6 +407,9 @@ static int mlx5_poll_one(struct mlx5_ib_cq *cq,
 	struct mlx5_cqe64 *cqe64;
 	struct mlx5_core_qp *mqp;
 	struct mlx5_ib_wq *wq;
+	struct mlx5_sig_err_cqe *sig_err_cqe;
+	struct mlx5_core_mr *mmr;
+	struct mlx5_ib_mr *mr;
 	uint8_t opcode;
 	uint32_t qpn;
 	u16 wqe_ctr;
@@ -475,6 +510,33 @@ repoll:
 			}
 		}
 		break;
+	case MLX5_CQE_SIG_ERR:
+		sig_err_cqe = (struct mlx5_sig_err_cqe *)cqe64;
+
+		read_lock(&dev->mdev.priv.mr_table.lock);
+		mmr = __mlx5_mr_lookup(&dev->mdev,
+				       mlx5_base_mkey(be32_to_cpu(sig_err_cqe->mkey)));
+		if (unlikely(!mmr)) {
+			read_unlock(&dev->mdev.priv.mr_table.lock);
+			mlx5_ib_warn(dev, "CQE@CQ %06x for unknown MR %6x\n",
+				     cq->mcq.cqn, be32_to_cpu(sig_err_cqe->mkey));
+			return -EINVAL;
+		}
+
+		mr = to_mibmr(mmr);
+		get_sig_err_item(sig_err_cqe, &mr->sig->err_item);
+		mr->sig->sig_err_exists = true;
+		mr->sig->sigerr_count++;
+
+		mlx5_ib_warn(dev, "CQN: 0x%x Got SIGERR on key: 0x%x err_type %x err_offset %llx expected %x actual %x\n",
+			     cq->mcq.cqn, mr->sig->err_item.key,
+			     mr->sig->err_item.err_type,
+			     mr->sig->err_item.sig_err_offset,
+			     mr->sig->err_item.expected,
+			     mr->sig->err_item.actual);
+
+		read_unlock(&dev->mdev.priv.mr_table.lock);
+		goto repoll;
 	}
 
 	return 0;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 7260a299c6db..ba3ecec7fa65 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1431,6 +1431,7 @@ static int init_one(struct pci_dev *pdev,
 	dev->ib_dev.alloc_fast_reg_mr	= mlx5_ib_alloc_fast_reg_mr;
 	dev->ib_dev.alloc_fast_reg_page_list = mlx5_ib_alloc_fast_reg_page_list;
 	dev->ib_dev.free_fast_reg_page_list  = mlx5_ib_free_fast_reg_page_list;
+	dev->ib_dev.check_mr_status	= mlx5_ib_check_mr_status;
 
 	if (mdev->caps.flags & MLX5_DEV_CAP_FLAG_XRC) {
 		dev->ib_dev.alloc_xrcd = mlx5_ib_alloc_xrcd;
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index e438f08899ae..50541586e0a6 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -400,6 +400,11 @@ static inline struct mlx5_ib_qp *to_mibqp(struct mlx5_core_qp *mqp)
 	return container_of(mqp, struct mlx5_ib_qp, mqp);
 }
 
+static inline struct mlx5_ib_mr *to_mibmr(struct mlx5_core_mr *mmr)
+{
+	return container_of(mmr, struct mlx5_ib_mr, mmr);
+}
+
 static inline struct mlx5_ib_pd *to_mpd(struct ib_pd *ibpd)
 {
 	return container_of(ibpd, struct mlx5_ib_pd, ibpd);
@@ -537,6 +542,8 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev);
 int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev);
 int mlx5_mr_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift);
 void mlx5_umr_cq_handler(struct ib_cq *cq, void *cq_context);
+int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask,
+			    struct ib_mr_status *mr_status);
 
 static inline void init_query_mad(struct ib_smp *mad)
 {
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 032445c47608..81392b26d078 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1038,6 +1038,11 @@ struct ib_mr *mlx5_ib_create_mr(struct ib_pd *pd,
 		access_mode = MLX5_ACCESS_MODE_KLM;
 		mr->sig->psv_memory.psv_idx = psv_index[0];
 		mr->sig->psv_wire.psv_idx = psv_index[1];
+
+		mr->sig->sig_status_checked = true;
+		mr->sig->sig_err_exists = false;
+		/* Next UMR, Arm SIGERR */
+		++mr->sig->sigerr_count;
 	}
 
 	in->seg.flags = MLX5_PERM_UMR_EN | access_mode;
@@ -1188,3 +1193,44 @@ void mlx5_ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list)
 	kfree(mfrpl->ibfrpl.page_list);
 	kfree(mfrpl);
 }
+
+int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask,
+			    struct ib_mr_status *mr_status)
+{
+	struct mlx5_ib_mr *mmr = to_mmr(ibmr);
+	int ret = 0;
+
+	if (check_mask & ~IB_MR_CHECK_SIG_STATUS) {
+		pr_err("Invalid status check mask\n");
+		ret = -EINVAL;
+		goto done;
+	}
+
+	mr_status->fail_status = 0;
+	if (check_mask & IB_MR_CHECK_SIG_STATUS) {
+		if (!mmr->sig) {
+			ret = -EINVAL;
+			pr_err("signature status check requested on a non-signature enabled MR\n");
+			goto done;
+		}
+
+		mmr->sig->sig_status_checked = true;
+		if (!mmr->sig->sig_err_exists)
+			goto done;
+
+		if (ibmr->lkey == mmr->sig->err_item.key)
+			memcpy(&mr_status->sig_err, &mmr->sig->err_item,
+			       sizeof(mr_status->sig_err));
+		else {
+			mr_status->sig_err.err_type = IB_SIG_BAD_GUARD;
+			mr_status->sig_err.sig_err_offset = 0;
+			mr_status->sig_err.key = mmr->sig->err_item.key;
+		}
+
+		mmr->sig->sig_err_exists = false;
+		mr_status->fail_status |= IB_MR_CHECK_SIG_STATUS;
+	}
+
+done:
+	return ret;
+}
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 67e79989b181..ae788d27b93f 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1784,6 +1784,7 @@ static __be64 sig_mkey_mask(void)
 	result = MLX5_MKEY_MASK_LEN		|
 		MLX5_MKEY_MASK_PAGE_SIZE	|
 		MLX5_MKEY_MASK_START_ADDR	|
+		MLX5_MKEY_MASK_EN_SIGERR	|
 		MLX5_MKEY_MASK_EN_RINVAL	|
 		MLX5_MKEY_MASK_KEY		|
 		MLX5_MKEY_MASK_LR		|
@@ -2219,13 +2220,14 @@ static void set_sig_mkey_segment(struct mlx5_mkey_seg *seg,
 {
 	struct ib_mr *sig_mr = wr->wr.sig_handover.sig_mr;
 	u32 sig_key = sig_mr->rkey;
+	u8 sigerr = to_mmr(sig_mr)->sig->sigerr_count & 1;
 
 	memset(seg, 0, sizeof(*seg));
 
 	seg->flags = get_umr_flags(wr->wr.sig_handover.access_flags) |
 				   MLX5_ACCESS_MODE_KLM;
 	seg->qpn_mkey7_0 = cpu_to_be32((sig_key & 0xff) | 0xffffff00);
-	seg->flags_pd = cpu_to_be32(MLX5_MKEY_REMOTE_INVAL |
+	seg->flags_pd = cpu_to_be32(MLX5_MKEY_REMOTE_INVAL | sigerr << 26 |
 				    MLX5_MKEY_BSF_EN | pdn);
 	seg->len = cpu_to_be64(length);
 	seg->xlt_oct_size = cpu_to_be32(be16_to_cpu(get_klm_octo(nelements)));
@@ -2255,7 +2257,8 @@ static int set_sig_umr_wr(struct ib_send_wr *wr, struct mlx5_ib_qp *qp,
 	if (unlikely(wr->num_sge != 1) ||
 	    unlikely(wr->wr.sig_handover.access_flags &
 		     IB_ACCESS_REMOTE_ATOMIC) ||
-	    unlikely(!sig_mr->sig) || unlikely(!qp->signature_en))
+	    unlikely(!sig_mr->sig) || unlikely(!qp->signature_en) ||
+	    unlikely(!sig_mr->sig->sig_status_checked))
 		return -EINVAL;
 
 	/* length of the protected region, data + protection */
@@ -2286,6 +2289,7 @@ static int set_sig_umr_wr(struct ib_send_wr *wr, struct mlx5_ib_qp *qp,
 	if (ret)
 		return ret;
 
+	sig_mr->sig->sig_status_checked = false;
 	return 0;
 }
 
diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h
index 2202c7f72b75..f6b17ac601bd 100644
--- a/include/linux/mlx5/cq.h
+++ b/include/linux/mlx5/cq.h
@@ -80,6 +80,7 @@ enum {
 	MLX5_CQE_RESP_SEND_IMM	= 3,
 	MLX5_CQE_RESP_SEND_INV	= 4,
 	MLX5_CQE_RESIZE_CQ	= 5,
+	MLX5_CQE_SIG_ERR	= 12,
 	MLX5_CQE_REQ_ERR	= 13,
 	MLX5_CQE_RESP_ERR	= 14,
 	MLX5_CQE_INVALID	= 15,
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index f714fc427765..407bdb67fd4f 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -118,6 +118,7 @@ enum {
 	MLX5_MKEY_MASK_START_ADDR	= 1ull << 6,
 	MLX5_MKEY_MASK_PD		= 1ull << 7,
 	MLX5_MKEY_MASK_EN_RINVAL	= 1ull << 8,
+	MLX5_MKEY_MASK_EN_SIGERR	= 1ull << 9,
 	MLX5_MKEY_MASK_BSF_EN		= 1ull << 12,
 	MLX5_MKEY_MASK_KEY		= 1ull << 13,
 	MLX5_MKEY_MASK_QPN		= 1ull << 14,
@@ -557,6 +558,23 @@ struct mlx5_cqe64 {
 	u8		op_own;
 };
 
+struct mlx5_sig_err_cqe {
+	u8		rsvd0[16];
+	__be32		expected_trans_sig;
+	__be32		actual_trans_sig;
+	__be32		expected_reftag;
+	__be32		actual_reftag;
+	__be16		syndrome;
+	u8		rsvd22[2];
+	__be32		mkey;
+	__be64		err_offset;
+	u8		rsvd30[8];
+	__be32		qpn;
+	u8		rsvd38[2];
+	u8		signature;
+	u8		op_own;
+};
+
 struct mlx5_wqe_srq_next_seg {
 	u8			rsvd0[2];
 	__be16			next_wqe_index;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index e562e01e59c7..93cef6313e72 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -416,6 +416,10 @@ struct mlx5_core_psv {
 struct mlx5_core_sig_ctx {
 	struct mlx5_core_psv	psv_memory;
 	struct mlx5_core_psv	psv_wire;
+	struct ib_sig_err       err_item;
+	bool			sig_status_checked;
+	bool			sig_err_exists;
+	u32			sigerr_count;
 };
 
 struct mlx5_core_mr {
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 49af74f90ef9..f829ad80ff28 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -506,6 +506,11 @@ static inline struct mlx5_core_qp *__mlx5_qp_lookup(struct mlx5_core_dev *dev, u
 	return radix_tree_lookup(&dev->priv.qp_table.tree, qpn);
 }
 
+static inline struct mlx5_core_mr *__mlx5_mr_lookup(struct mlx5_core_dev *dev, u32 key)
+{
+	return radix_tree_lookup(&dev->priv.mr_table.tree, key);
+}
+
 int mlx5_core_create_qp(struct mlx5_core_dev *dev,
 			struct mlx5_core_qp *qp,
 			struct mlx5_create_qp_mbox_in *in,
-- 
cgit v1.2.3


From 0b3f3b2c777a2f7d20c9826a190ffd5bbd288f8f Mon Sep 17 00:00:00 2001
From: Kamil Debski <k.debski@samsung.com>
Date: Thu, 6 Mar 2014 12:16:46 +0100
Subject: phy: core: Add an exported of_phy_get function

Previously the of_phy_get function took a struct device * and
was declared static. It was impossible to call it from
another driver and thus it was impossible to get phy defined
for a given node. The old function was renamed to _of_phy_get
and was left for internal use. of_phy_get function was added
and it was exported. The function enables to get a phy for
a given device tree node.

Signed-off-by: Kamil Debski <k.debski@samsung.com>
Reviewed-by: Tomasz Figa <t.figa@samsung.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 drivers/phy/phy-core.c  | 45 ++++++++++++++++++++++++++++++++++++---------
 include/linux/phy/phy.h |  6 ++++++
 2 files changed, 42 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index 6c738376daff..7c1b0e14a235 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -274,8 +274,8 @@ int phy_power_off(struct phy *phy)
 EXPORT_SYMBOL_GPL(phy_power_off);
 
 /**
- * of_phy_get() - lookup and obtain a reference to a phy by phandle
- * @dev: device that requests this phy
+ * _of_phy_get() - lookup and obtain a reference to a phy by phandle
+ * @np: device_node for which to get the phy
  * @index: the index of the phy
  *
  * Returns the phy associated with the given phandle value,
@@ -284,20 +284,17 @@ EXPORT_SYMBOL_GPL(phy_power_off);
  * not yet loaded. This function uses of_xlate call back function provided
  * while registering the phy_provider to find the phy instance.
  */
-static struct phy *of_phy_get(struct device *dev, int index)
+static struct phy *_of_phy_get(struct device_node *np, int index)
 {
 	int ret;
 	struct phy_provider *phy_provider;
 	struct phy *phy = NULL;
 	struct of_phandle_args args;
 
-	ret = of_parse_phandle_with_args(dev->of_node, "phys", "#phy-cells",
+	ret = of_parse_phandle_with_args(np, "phys", "#phy-cells",
 		index, &args);
-	if (ret) {
-		dev_dbg(dev, "failed to get phy in %s node\n",
-			dev->of_node->full_name);
+	if (ret)
 		return ERR_PTR(-ENODEV);
-	}
 
 	mutex_lock(&phy_provider_mutex);
 	phy_provider = of_phy_provider_lookup(args.np);
@@ -316,6 +313,36 @@ err0:
 	return phy;
 }
 
+/**
+ * of_phy_get() - lookup and obtain a reference to a phy using a device_node.
+ * @np: device_node for which to get the phy
+ * @con_id: name of the phy from device's point of view
+ *
+ * Returns the phy driver, after getting a refcount to it; or
+ * -ENODEV if there is no such phy. The caller is responsible for
+ * calling phy_put() to release that count.
+ */
+struct phy *of_phy_get(struct device_node *np, const char *con_id)
+{
+	struct phy *phy = NULL;
+	int index = 0;
+
+	if (con_id)
+		index = of_property_match_string(np, "phy-names", con_id);
+
+	phy = _of_phy_get(np, index);
+	if (IS_ERR(phy))
+		return phy;
+
+	if (!try_module_get(phy->ops->owner))
+		return ERR_PTR(-EPROBE_DEFER);
+
+	get_device(&phy->dev);
+
+	return phy;
+}
+EXPORT_SYMBOL_GPL(of_phy_get);
+
 /**
  * phy_put() - release the PHY
  * @phy: the phy returned by phy_get()
@@ -407,7 +434,7 @@ struct phy *phy_get(struct device *dev, const char *string)
 	if (dev->of_node) {
 		index = of_property_match_string(dev->of_node, "phy-names",
 			string);
-		phy = of_phy_get(dev, index);
+		phy = _of_phy_get(dev->of_node, index);
 	} else {
 		phy = phy_lookup(dev, string);
 	}
diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h
index 3f83459dbb20..50c7629b5860 100644
--- a/include/linux/phy/phy.h
+++ b/include/linux/phy/phy.h
@@ -151,6 +151,7 @@ struct phy *devm_phy_get(struct device *dev, const char *string);
 struct phy *devm_phy_optional_get(struct device *dev, const char *string);
 void phy_put(struct phy *phy);
 void devm_phy_put(struct device *dev, struct phy *phy);
+struct phy *of_phy_get(struct device_node *np, const char *con_id);
 struct phy *of_phy_simple_xlate(struct device *dev,
 	struct of_phandle_args *args);
 struct phy *phy_create(struct device *dev, const struct phy_ops *ops,
@@ -259,6 +260,11 @@ static inline void devm_phy_put(struct device *dev, struct phy *phy)
 {
 }
 
+static inline struct phy *of_phy_get(struct device_node *np, const char *con_id)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
 static inline struct phy *of_phy_simple_xlate(struct device *dev,
 	struct of_phandle_args *args)
 {
-- 
cgit v1.2.3


From b5d682f4eb76c98f2ca5658926df43dd05cf2c37 Mon Sep 17 00:00:00 2001
From: Kamil Debski <k.debski@samsung.com>
Date: Thu, 6 Mar 2014 12:16:47 +0100
Subject: phy: core: Add devm_of_phy_get to phy-core

Adding devm_of_phy_get will allow to get phys by supplying a
pointer to the struct device_node instead of struct device.

Signed-off-by: Kamil Debski <k.debski@samsung.com>
Reviewed-by: Tomasz Figa <t.figa@samsung.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 drivers/phy/phy-core.c  | 31 +++++++++++++++++++++++++++++++
 include/linux/phy/phy.h |  9 +++++++++
 2 files changed, 40 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index 7c1b0e14a235..623b71c54b3e 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -525,6 +525,37 @@ struct phy *devm_phy_optional_get(struct device *dev, const char *string)
 }
 EXPORT_SYMBOL_GPL(devm_phy_optional_get);
 
+/**
+ * devm_of_phy_get() - lookup and obtain a reference to a phy.
+ * @dev: device that requests this phy
+ * @np: node containing the phy
+ * @con_id: name of the phy from device's point of view
+ *
+ * Gets the phy using of_phy_get(), and associates a device with it using
+ * devres. On driver detach, release function is invoked on the devres data,
+ * then, devres data is freed.
+ */
+struct phy *devm_of_phy_get(struct device *dev, struct device_node *np,
+			    const char *con_id)
+{
+	struct phy **ptr, *phy;
+
+	ptr = devres_alloc(devm_phy_release, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return ERR_PTR(-ENOMEM);
+
+	phy = of_phy_get(np, con_id);
+	if (!IS_ERR(phy)) {
+		*ptr = phy;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return phy;
+}
+EXPORT_SYMBOL_GPL(devm_of_phy_get);
+
 /**
  * phy_create() - create a new phy
  * @dev: device that is creating the new phy
diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h
index 50c7629b5860..e2f5ca96cddc 100644
--- a/include/linux/phy/phy.h
+++ b/include/linux/phy/phy.h
@@ -149,6 +149,8 @@ struct phy *phy_get(struct device *dev, const char *string);
 struct phy *phy_optional_get(struct device *dev, const char *string);
 struct phy *devm_phy_get(struct device *dev, const char *string);
 struct phy *devm_phy_optional_get(struct device *dev, const char *string);
+struct phy *devm_of_phy_get(struct device *dev, struct device_node *np,
+			    const char *con_id);
 void phy_put(struct phy *phy);
 void devm_phy_put(struct device *dev, struct phy *phy);
 struct phy *of_phy_get(struct device_node *np, const char *con_id);
@@ -252,6 +254,13 @@ static inline struct phy *devm_phy_optional_get(struct device *dev,
 	return ERR_PTR(-ENOSYS);
 }
 
+static inline struct phy *devm_of_phy_get(struct device *dev,
+					  struct device_node *np,
+					  const char *con_id)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
 static inline void phy_put(struct phy *phy)
 {
 }
-- 
cgit v1.2.3


From b7ce40cff0b9f6597f8318fd761accd92727f61f Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 4 Mar 2014 15:38:46 -0500
Subject: kernfs: cache atomic_write_len in kernfs_open_file

While implementing atomic_write_len, 4d3773c4bb41 ("kernfs: implement
kernfs_ops->atomic_write_len") moved data copy from userland inside
kernfs_get_active() and kernfs_open_file->mutex so that
kernfs_ops->atomic_write_len can be accessed before copying buffer
from userland; unfortunately, this could lead to locking order
inversion involving mmap_sem if copy_from_user() takes a page fault.

  ======================================================
  [ INFO: possible circular locking dependency detected ]
  3.14.0-rc4-next-20140228-sasha-00011-g4077c67-dirty #26 Tainted: G        W
  -------------------------------------------------------
  trinity-c236/10658 is trying to acquire lock:
   (&of->mutex#2){+.+.+.}, at: [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120

  but task is already holding lock:
   (&mm->mmap_sem){++++++}, at: [<mm/util.c:397>] vm_mmap_pgoff+0x6e/0xe0

  which lock already depends on the new lock.

  the existing dependency chain (in reverse order) is:

 -> #1 (&mm->mmap_sem){++++++}:
	 [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0
	 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0
	 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0
	 [<mm/memory.c:4188>] might_fault+0x7e/0xb0
	 [<arch/x86/include/asm/uaccess.h:713 fs/kernfs/file.c:291>] kernfs_fop_write+0xd8/0x190
	 [<fs/read_write.c:473>] vfs_write+0xe3/0x1d0
	 [<fs/read_write.c:523 fs/read_write.c:515>] SyS_write+0x5d/0xa0
	 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2

 -> #0 (&of->mutex#2){+.+.+.}:
	 [<kernel/locking/lockdep.c:1840>] check_prev_add+0x13f/0x560
	 [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0
	 [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0
	 [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0
	 [<kernel/locking/mutex.c:470 kernel/locking/mutex.c:571>] mutex_lock_nested+0x6a/0x510
	 [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120
	 [<mm/mmap.c:1573>] mmap_region+0x310/0x5c0
	 [<mm/mmap.c:1365>] do_mmap_pgoff+0x385/0x430
	 [<mm/util.c:399>] vm_mmap_pgoff+0x8f/0xe0
	 [<mm/mmap.c:1416 mm/mmap.c:1374>] SyS_mmap_pgoff+0x1b0/0x210
	 [<arch/x86/kernel/sys_x86_64.c:72>] SyS_mmap+0x1d/0x20
	 [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2

  other info that might help us debug this:

   Possible unsafe locking scenario:

	 CPU0                    CPU1
	 ----                    ----
    lock(&mm->mmap_sem);
				 lock(&of->mutex#2);
				 lock(&mm->mmap_sem);
    lock(&of->mutex#2);

   *** DEADLOCK ***

  1 lock held by trinity-c236/10658:
   #0:  (&mm->mmap_sem){++++++}, at: [<mm/util.c:397>] vm_mmap_pgoff+0x6e/0xe0

  stack backtrace:
  CPU: 2 PID: 10658 Comm: trinity-c236 Tainted: G        W 3.14.0-rc4-next-20140228-sasha-00011-g4077c67-dirty #26
   0000000000000000 ffff88011911fa48 ffffffff8438e945 0000000000000000
   0000000000000000 ffff88011911fa98 ffffffff811a0109 ffff88011911fab8
   ffff88011911fab8 ffff88011911fa98 ffff880119128cc0 ffff880119128cf8
  Call Trace:
   [<lib/dump_stack.c:52>] dump_stack+0x52/0x7f
   [<kernel/locking/lockdep.c:1213>] print_circular_bug+0x129/0x160
   [<kernel/locking/lockdep.c:1840>] check_prev_add+0x13f/0x560
   [<include/linux/spinlock.h:343 mm/slub.c:1933>] ? deactivate_slab+0x511/0x550
   [<kernel/locking/lockdep.c:1945 kernel/locking/lockdep.c:2131>] validate_chain+0x6c5/0x7b0
   [<kernel/locking/lockdep.c:3182>] __lock_acquire+0x4cd/0x5a0
   [<mm/mmap.c:1552>] ? mmap_region+0x24a/0x5c0
   [<arch/x86/include/asm/current.h:14 kernel/locking/lockdep.c:3602>] lock_acquire+0x182/0x1d0
   [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120
   [<kernel/locking/mutex.c:470 kernel/locking/mutex.c:571>] mutex_lock_nested+0x6a/0x510
   [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120
   [<kernel/sched/core.c:2477>] ? get_parent_ip+0x11/0x50
   [<fs/kernfs/file.c:487>] ? kernfs_fop_mmap+0x54/0x120
   [<fs/kernfs/file.c:487>] kernfs_fop_mmap+0x54/0x120
   [<mm/mmap.c:1573>] mmap_region+0x310/0x5c0
   [<mm/mmap.c:1365>] do_mmap_pgoff+0x385/0x430
   [<mm/util.c:397>] ? vm_mmap_pgoff+0x6e/0xe0
   [<mm/util.c:399>] vm_mmap_pgoff+0x8f/0xe0
   [<kernel/rcu/update.c:97>] ? __rcu_read_unlock+0x44/0xb0
   [<fs/file.c:641>] ? dup_fd+0x3c0/0x3c0
   [<mm/mmap.c:1416 mm/mmap.c:1374>] SyS_mmap_pgoff+0x1b0/0x210
   [<arch/x86/kernel/sys_x86_64.c:72>] SyS_mmap+0x1d/0x20
   [<arch/x86/kernel/entry_64.S:749>] tracesys+0xdd/0xe2

Fix it by caching atomic_write_len in kernfs_open_file during open so
that it can be determined without accessing kernfs_ops in
kernfs_fop_write().  This restores the structure of kernfs_fop_write()
before 4d3773c4bb41 with updated @len determination logic.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Sasha Levin <sasha.levin@oracle.com>
References: http://lkml.kernel.org/g/53113485.2090407@oracle.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/kernfs/file.c       | 63 +++++++++++++++++++++++++-------------------------
 include/linux/kernfs.h |  1 +
 2 files changed, 33 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index ddcb471b9cc9..8034706a7af8 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -253,55 +253,50 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
 {
 	struct kernfs_open_file *of = kernfs_of(file);
 	const struct kernfs_ops *ops;
-	char *buf = NULL;
-	ssize_t len;
-
-	/*
-	 * @of->mutex nests outside active ref and is just to ensure that
-	 * the ops aren't called concurrently for the same open file.
-	 */
-	mutex_lock(&of->mutex);
-	if (!kernfs_get_active(of->kn)) {
-		mutex_unlock(&of->mutex);
-		return -ENODEV;
-	}
-
-	ops = kernfs_ops(of->kn);
-	if (!ops->write) {
-		len = -EINVAL;
-		goto out_unlock;
-	}
+	size_t len;
+	char *buf;
 
-	if (ops->atomic_write_len) {
+	if (of->atomic_write_len) {
 		len = count;
-		if (len > ops->atomic_write_len) {
-			len = -E2BIG;
-			goto out_unlock;
-		}
+		if (len > of->atomic_write_len)
+			return -E2BIG;
 	} else {
 		len = min_t(size_t, count, PAGE_SIZE);
 	}
 
 	buf = kmalloc(len + 1, GFP_KERNEL);
-	if (!buf) {
-		len = -ENOMEM;
-		goto out_unlock;
-	}
+	if (!buf)
+		return -ENOMEM;
 
 	if (copy_from_user(buf, user_buf, len)) {
 		len = -EFAULT;
-		goto out_unlock;
+		goto out_free;
 	}
 	buf[len] = '\0';	/* guarantee string termination */
 
-	len = ops->write(of, buf, len, *ppos);
-out_unlock:
+	/*
+	 * @of->mutex nests outside active ref and is just to ensure that
+	 * the ops aren't called concurrently for the same open file.
+	 */
+	mutex_lock(&of->mutex);
+	if (!kernfs_get_active(of->kn)) {
+		mutex_unlock(&of->mutex);
+		len = -ENODEV;
+		goto out_free;
+	}
+
+	ops = kernfs_ops(of->kn);
+	if (ops->write)
+		len = ops->write(of, buf, len, *ppos);
+	else
+		len = -EINVAL;
+
 	kernfs_put_active(of->kn);
 	mutex_unlock(&of->mutex);
 
 	if (len > 0)
 		*ppos += len;
-
+out_free:
 	kfree(buf);
 	return len;
 }
@@ -665,6 +660,12 @@ static int kernfs_fop_open(struct inode *inode, struct file *file)
 	of->kn = kn;
 	of->file = file;
 
+	/*
+	 * Write path needs to atomic_write_len outside active reference.
+	 * Cache it in open_file.  See kernfs_fop_write() for details.
+	 */
+	of->atomic_write_len = ops->atomic_write_len;
+
 	/*
 	 * Always instantiate seq_file even if read access doesn't use
 	 * seq_file or is not requested.  This unifies private data access
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 09669d092748..b0122dc6f96a 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -158,6 +158,7 @@ struct kernfs_open_file {
 	int			event;
 	struct list_head	list;
 
+	size_t			atomic_write_len;
 	bool			mmapped;
 	const struct vm_operations_struct *vm_ops;
 };
-- 
cgit v1.2.3


From 7e5ec36834a5752304dc0751dfab42ba6ad64a85 Mon Sep 17 00:00:00 2001
From: "K. Y. Srinivasan" <kys@microsoft.com>
Date: Fri, 7 Mar 2014 00:10:34 -0800
Subject: Drivers: hv: vmbus: Increase the limit on the number of pfns we can
 handle

Increase the number of PFNs we can handle in a single vmbus packet.
Some network packets may have more PFNs than the current limit we have.
This is not a bug and this patch can be applied to the *next tree.

Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/hyperv.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 330ec44de575..ab7359fde987 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -37,7 +37,7 @@
 #include <linux/mod_devicetable.h>
 
 
-#define MAX_PAGE_BUFFER_COUNT				19
+#define MAX_PAGE_BUFFER_COUNT				32
 #define MAX_MULTIPAGE_BUFFER_COUNT			32 /* 128K */
 
 #pragma pack(push, 1)
-- 
cgit v1.2.3


From 6080cd0e9239469524d2aa07250ad4b9f383960d Mon Sep 17 00:00:00 2001
From: Valentina Manea <valentina.manea.m@gmail.com>
Date: Sat, 8 Mar 2014 14:53:34 +0200
Subject: staging: usbip: claim ports used by shared devices

A device should not be able to be used concurrently both by
the server and the client. Claiming the port used by the
shared device ensures no interface drivers bind to it and
that it is not usable from the server.

Signed-off-by: Valentina Manea <valentina.manea.m@gmail.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/usbip/stub_dev.c | 22 ++++++++++++++++++++++
 drivers/usb/core/hub.c           |  2 ++
 drivers/usb/core/usb.h           |  4 ----
 include/linux/usb.h              |  7 +++++++
 4 files changed, 31 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/staging/usbip/stub_dev.c b/drivers/staging/usbip/stub_dev.c
index ee899f01c008..952743c752d7 100644
--- a/drivers/staging/usbip/stub_dev.c
+++ b/drivers/staging/usbip/stub_dev.c
@@ -339,6 +339,7 @@ static int stub_probe(struct usb_device *udev)
 	const char *udev_busid = dev_name(&udev->dev);
 	int err = 0;
 	struct bus_id_priv *busid_priv;
+	int rc;
 
 	dev_dbg(&udev->dev, "Enter\n");
 
@@ -388,6 +389,18 @@ static int stub_probe(struct usb_device *udev)
 	busid_priv->sdev = sdev;
 	busid_priv->udev = udev;
 
+	/*
+	 * Claim this hub port.
+	 * It doesn't matter what value we pass as owner
+	 * (struct dev_state) as long as it is unique.
+	 */
+	rc = usb_hub_claim_port(udev->parent, udev->portnum,
+			(struct dev_state *) udev);
+	if (rc) {
+		dev_dbg(&udev->dev, "unable to claim port\n");
+		return rc;
+	}
+
 	err = stub_add_files(&udev->dev);
 	if (err) {
 		dev_err(&udev->dev, "stub_add_files for %s\n", udev_busid);
@@ -424,6 +437,7 @@ static void stub_disconnect(struct usb_device *udev)
 	struct stub_device *sdev;
 	const char *udev_busid = dev_name(&udev->dev);
 	struct bus_id_priv *busid_priv;
+	int rc;
 
 	dev_dbg(&udev->dev, "Enter\n");
 
@@ -448,6 +462,14 @@ static void stub_disconnect(struct usb_device *udev)
 	 */
 	stub_remove_files(&udev->dev);
 
+	/* release port */
+	rc = usb_hub_release_port(udev->parent, udev->portnum,
+				  (struct dev_state *) udev);
+	if (rc) {
+		dev_dbg(&udev->dev, "unable to release port\n");
+		return;
+	}
+
 	/* If usb reset is called from event handler */
 	if (busid_priv->sdev->ud.eh == current)
 		return;
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 64ea21971be2..e4849333c8de 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -1819,6 +1819,7 @@ int usb_hub_claim_port(struct usb_device *hdev, unsigned port1,
 	*powner = owner;
 	return rc;
 }
+EXPORT_SYMBOL_GPL(usb_hub_claim_port);
 
 int usb_hub_release_port(struct usb_device *hdev, unsigned port1,
 			 struct dev_state *owner)
@@ -1834,6 +1835,7 @@ int usb_hub_release_port(struct usb_device *hdev, unsigned port1,
 	*powner = NULL;
 	return rc;
 }
+EXPORT_SYMBOL_GPL(usb_hub_release_port);
 
 void usb_hub_release_all_ports(struct usb_device *hdev, struct dev_state *owner)
 {
diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h
index 823857767a16..222bbd2618f1 100644
--- a/drivers/usb/core/usb.h
+++ b/drivers/usb/core/usb.h
@@ -57,10 +57,6 @@ extern int usb_match_device(struct usb_device *dev,
 extern void usb_forced_unbind_intf(struct usb_interface *intf);
 extern void usb_rebind_intf(struct usb_interface *intf);
 
-extern int usb_hub_claim_port(struct usb_device *hdev, unsigned port,
-		struct dev_state *owner);
-extern int usb_hub_release_port(struct usb_device *hdev, unsigned port,
-		struct dev_state *owner);
 extern void usb_hub_release_all_ports(struct usb_device *hdev,
 		struct dev_state *owner);
 extern bool usb_device_is_owned(struct usb_device *udev);
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 22de4affe9c8..140a6a3e7d56 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -366,6 +366,8 @@ struct usb_bus {
 #endif
 };
 
+struct dev_state;
+
 /* ----------------------------------------------------------------------- */
 
 struct usb_tt;
@@ -749,6 +751,11 @@ extern struct usb_host_interface *usb_find_alt_setting(
 		unsigned int iface_num,
 		unsigned int alt_num);
 
+/* port claiming functions */
+int usb_hub_claim_port(struct usb_device *hdev, unsigned port1,
+		struct dev_state *owner);
+int usb_hub_release_port(struct usb_device *hdev, unsigned port1,
+		struct dev_state *owner);
 
 /**
  * usb_make_path - returns stable device path in the usb tree
-- 
cgit v1.2.3


From 09a0168de11a4a487c2d1c78366491b695e0c15a Mon Sep 17 00:00:00 2001
From: George Cherian <george.cherian@ti.com>
Date: Thu, 6 Mar 2014 18:11:52 +0530
Subject: phy: omap-usb2: Adapt phy-omap-usb2 for AM437x

Adapt phy-omap-usb2 driver for AM437x.
	- Add new comaptible "ti,am437x-usb2" for AM437x
	- Pass proper data to differentiate AM437x and others.
	- AM437x doesnot support  set_vbus and start_srp.

Signed-off-by: George Cherian <george.cherian@ti.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 drivers/phy/phy-omap-usb2.c  | 49 +++++++++++++++++++++++++++++++++-----------
 include/linux/phy/omap_usb.h |  9 ++++++++
 2 files changed, 46 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/phy/phy-omap-usb2.c b/drivers/phy/phy-omap-usb2.c
index 9c3f056b3ddf..0c78f54d0650 100644
--- a/drivers/phy/phy-omap-usb2.c
+++ b/drivers/phy/phy-omap-usb2.c
@@ -122,6 +122,31 @@ static struct phy_ops ops = {
 	.owner		= THIS_MODULE,
 };
 
+#ifdef CONFIG_OF
+static const struct usb_phy_data omap_usb2_data = {
+	.label = "omap_usb2",
+	.flags = OMAP_USB2_HAS_START_SRP | OMAP_USB2_HAS_SET_VBUS,
+};
+
+static const struct usb_phy_data am437x_usb2_data = {
+	.label = "am437x_usb2",
+	.flags =  0,
+};
+
+static const struct of_device_id omap_usb2_id_table[] = {
+	{
+		.compatible = "ti,omap-usb2",
+		.data = &omap_usb2_data,
+	},
+	{
+		.compatible = "ti,am437x-usb2",
+		.data = &am437x_usb2_data,
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, omap_usb2_id_table);
+#endif
+
 static int omap_usb2_probe(struct platform_device *pdev)
 {
 	struct omap_usb	*phy;
@@ -131,10 +156,16 @@ static int omap_usb2_probe(struct platform_device *pdev)
 	struct device_node *node = pdev->dev.of_node;
 	struct device_node *control_node;
 	struct platform_device *control_pdev;
+	const struct of_device_id *of_id;
+	struct usb_phy_data *phy_data;
+
+	of_id = of_match_device(of_match_ptr(omap_usb2_id_table), &pdev->dev);
 
-	if (!node)
+	if (!of_id)
 		return -EINVAL;
 
+	phy_data = (struct usb_phy_data *)of_id->data;
+
 	phy = devm_kzalloc(&pdev->dev, sizeof(*phy), GFP_KERNEL);
 	if (!phy) {
 		dev_err(&pdev->dev, "unable to allocate memory for USB2 PHY\n");
@@ -150,7 +181,7 @@ static int omap_usb2_probe(struct platform_device *pdev)
 	phy->dev		= &pdev->dev;
 
 	phy->phy.dev		= phy->dev;
-	phy->phy.label		= "omap-usb2";
+	phy->phy.label		= phy_data->label;
 	phy->phy.otg		= otg;
 	phy->phy.type		= USB_PHY_TYPE_USB2;
 
@@ -171,8 +202,10 @@ static int omap_usb2_probe(struct platform_device *pdev)
 
 	otg->set_host		= omap_usb_set_host;
 	otg->set_peripheral	= omap_usb_set_peripheral;
-	otg->set_vbus		= omap_usb_set_vbus;
-	otg->start_srp		= omap_usb_start_srp;
+	if (phy_data->flags & OMAP_USB2_HAS_SET_VBUS)
+		otg->set_vbus		= omap_usb_set_vbus;
+	if (phy_data->flags & OMAP_USB2_HAS_START_SRP)
+		otg->start_srp		= omap_usb_start_srp;
 	otg->phy		= &phy->phy;
 
 	platform_set_drvdata(pdev, phy);
@@ -272,14 +305,6 @@ static const struct dev_pm_ops omap_usb2_pm_ops = {
 #define DEV_PM_OPS     NULL
 #endif
 
-#ifdef CONFIG_OF
-static const struct of_device_id omap_usb2_id_table[] = {
-	{ .compatible = "ti,omap-usb2" },
-	{}
-};
-MODULE_DEVICE_TABLE(of, omap_usb2_id_table);
-#endif
-
 static struct platform_driver omap_usb2_driver = {
 	.probe		= omap_usb2_probe,
 	.remove		= omap_usb2_remove,
diff --git a/include/linux/phy/omap_usb.h b/include/linux/phy/omap_usb.h
index 19d343c37fb5..35989a8fc535 100644
--- a/include/linux/phy/omap_usb.h
+++ b/include/linux/phy/omap_usb.h
@@ -39,6 +39,15 @@ struct omap_usb {
 	struct clk		*optclk;
 };
 
+struct usb_phy_data {
+	const char *label;
+	u8 flags;
+};
+
+/* Driver Flags */
+#define OMAP_USB2_HAS_START_SRP (1 << 0)
+#define OMAP_USB2_HAS_SET_VBUS (1 << 1)
+
 #define	phy_to_omapusb(x)	container_of((x), struct omap_usb, phy)
 
 #if defined(CONFIG_OMAP_USB2) || defined(CONFIG_OMAP_USB2_MODULE)
-- 
cgit v1.2.3


From 7e472402ca308287a2474d4c9011f69f33fa19cb Mon Sep 17 00:00:00 2001
From: Austin Beam <austinbeam@ti.com>
Date: Thu, 6 Mar 2014 18:11:53 +0530
Subject: phy: omap-usb2: Provide workaround for USB2PHY false disconnect

Enable the dra7x errata workaround for false disconnect problem
with USB2PHY. False disconnects were detected with some of the devices.
Reduce the sensitivity of the disconnect logic within the USB2PHY subsystem
to enusre these false disconnects are not registered.

[george.cherian@ti.com]
While at that, pass proper flags for each SoC's. This is a common driver
used across OMAP4,OMAP5,DRA7xx and AM437x USB2PHY.

False disconnect workaround is currently applicable for only DRA7x.

Signed-off-by: Austin Beam <austinbeam@ti.com>
Signed-off-by: George Cherian <george.cherian@ti.com>
Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 drivers/phy/phy-omap-usb2.c  | 44 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/phy/omap_usb.h |  4 ++++
 2 files changed, 48 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/phy/phy-omap-usb2.c b/drivers/phy/phy-omap-usb2.c
index 0c78f54d0650..b220202a3f30 100644
--- a/drivers/phy/phy-omap-usb2.c
+++ b/drivers/phy/phy-omap-usb2.c
@@ -31,6 +31,9 @@
 #include <linux/phy/phy.h>
 #include <linux/of_platform.h>
 
+#define USB2PHY_DISCON_BYP_LATCH (1 << 31)
+#define USB2PHY_ANA_CONFIG1 0x4c
+
 /**
  * omap_usb2_set_comparator - links the comparator present in the sytem with
  *	this phy
@@ -116,7 +119,30 @@ static int omap_usb_power_on(struct phy *x)
 	return 0;
 }
 
+static int omap_usb_init(struct phy *x)
+{
+	struct omap_usb *phy = phy_get_drvdata(x);
+	u32 val;
+
+	if (phy->flags & OMAP_USB2_CALIBRATE_FALSE_DISCONNECT) {
+		/*
+		 *
+		 * Reduce the sensitivity of internal PHY by enabling the
+		 * DISCON_BYP_LATCH of the USB2PHY_ANA_CONFIG1 register. This
+		 * resolves issues with certain devices which can otherwise
+		 * be prone to false disconnects.
+		 *
+		 */
+		val = omap_usb_readl(phy->phy_base, USB2PHY_ANA_CONFIG1);
+		val |= USB2PHY_DISCON_BYP_LATCH;
+		omap_usb_writel(phy->phy_base, USB2PHY_ANA_CONFIG1, val);
+	}
+
+	return 0;
+}
+
 static struct phy_ops ops = {
+	.init		= omap_usb_init,
 	.power_on	= omap_usb_power_on,
 	.power_off	= omap_usb_power_off,
 	.owner		= THIS_MODULE,
@@ -128,6 +154,11 @@ static const struct usb_phy_data omap_usb2_data = {
 	.flags = OMAP_USB2_HAS_START_SRP | OMAP_USB2_HAS_SET_VBUS,
 };
 
+static const struct usb_phy_data dra7x_usb2_data = {
+	.label = "dra7x_usb2",
+	.flags = OMAP_USB2_CALIBRATE_FALSE_DISCONNECT,
+};
+
 static const struct usb_phy_data am437x_usb2_data = {
 	.label = "am437x_usb2",
 	.flags =  0,
@@ -138,6 +169,10 @@ static const struct of_device_id omap_usb2_id_table[] = {
 		.compatible = "ti,omap-usb2",
 		.data = &omap_usb2_data,
 	},
+	{
+		.compatible = "ti,dra7x-usb2",
+		.data = &dra7x_usb2_data,
+	},
 	{
 		.compatible = "ti,am437x-usb2",
 		.data = &am437x_usb2_data,
@@ -151,6 +186,7 @@ static int omap_usb2_probe(struct platform_device *pdev)
 {
 	struct omap_usb	*phy;
 	struct phy *generic_phy;
+	struct resource *res;
 	struct phy_provider *phy_provider;
 	struct usb_otg *otg;
 	struct device_node *node = pdev->dev.of_node;
@@ -185,6 +221,14 @@ static int omap_usb2_probe(struct platform_device *pdev)
 	phy->phy.otg		= otg;
 	phy->phy.type		= USB_PHY_TYPE_USB2;
 
+	if (phy_data->flags & OMAP_USB2_CALIBRATE_FALSE_DISCONNECT) {
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+		phy->phy_base = devm_ioremap_resource(&pdev->dev, res);
+		if (!phy->phy_base)
+			return -ENOMEM;
+		phy->flags |= OMAP_USB2_CALIBRATE_FALSE_DISCONNECT;
+	}
+
 	control_node = of_parse_phandle(node, "ctrl-module", 0);
 	if (!control_node) {
 		dev_err(&pdev->dev, "Failed to get control device phandle\n");
diff --git a/include/linux/phy/omap_usb.h b/include/linux/phy/omap_usb.h
index 35989a8fc535..dc2c541a619b 100644
--- a/include/linux/phy/omap_usb.h
+++ b/include/linux/phy/omap_usb.h
@@ -33,10 +33,13 @@ struct usb_dpll_params {
 struct omap_usb {
 	struct usb_phy		phy;
 	struct phy_companion	*comparator;
+	void __iomem		*pll_ctrl_base;
+	void __iomem		*phy_base;
 	struct device		*dev;
 	struct device		*control_dev;
 	struct clk		*wkupclk;
 	struct clk		*optclk;
+	u8			flags;
 };
 
 struct usb_phy_data {
@@ -47,6 +50,7 @@ struct usb_phy_data {
 /* Driver Flags */
 #define OMAP_USB2_HAS_START_SRP (1 << 0)
 #define OMAP_USB2_HAS_SET_VBUS (1 << 1)
+#define OMAP_USB2_CALIBRATE_FALSE_DISCONNECT (1 << 2)
 
 #define	phy_to_omapusb(x)	container_of((x), struct omap_usb, phy)
 
-- 
cgit v1.2.3


From 14da699bc04212559d5dda19d3f07c807fb58dfd Mon Sep 17 00:00:00 2001
From: Kishon Vijay Abraham I <kishon@ti.com>
Date: Thu, 6 Mar 2014 16:38:37 +0200
Subject: phy: rename struct omap_control_usb to struct omap_control_phy

Rename struct omap_control_usb to struct omap_control_phy since it can
be used to control PHY of USB, SATA and PCIE. Also move the driver and
include files under *phy* and made the corresponding changes in the users
of phy-omap-control.

Signed-off-by: Kishon Vijay Abraham I <kishon@ti.com>
Signed-off-by: Roger Quadros <rogerq@ti.com>
Acked-by: Felipe Balbi <balbi@ti.com>
---
 drivers/phy/Kconfig                  |  14 +-
 drivers/phy/Makefile                 |   1 +
 drivers/phy/phy-omap-control.c       | 320 +++++++++++++++++++++++++++++++++++
 drivers/phy/phy-omap-usb2.c          |   8 +-
 drivers/phy/phy-ti-pipe3.c           |   8 +-
 drivers/usb/musb/omap2430.c          |   2 +-
 drivers/usb/phy/Kconfig              |  10 --
 drivers/usb/phy/Makefile             |   1 -
 drivers/usb/phy/phy-omap-control.c   | 319 ----------------------------------
 include/linux/phy/omap_control_phy.h |  89 ++++++++++
 include/linux/usb/omap_control_usb.h |  89 ----------
 11 files changed, 431 insertions(+), 430 deletions(-)
 create mode 100644 drivers/phy/phy-omap-control.c
 delete mode 100644 drivers/usb/phy/phy-omap-control.c
 create mode 100644 include/linux/phy/omap_control_phy.h
 delete mode 100644 include/linux/usb/omap_control_usb.h

(limited to 'include/linux')

diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index 1b607d7cb03d..fe8c0096f9e4 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -31,12 +31,22 @@ config PHY_MVEBU_SATA
 	depends on OF
 	select GENERIC_PHY
 
+config OMAP_CONTROL_PHY
+	tristate "OMAP CONTROL PHY Driver"
+	help
+	  Enable this to add support for the PHY part present in the control
+	  module. This driver has API to power on the USB2 PHY and to write to
+	  the mailbox. The mailbox is present only in omap4 and the register to
+	  power on the USB2 PHY is present in OMAP4 and OMAP5. OMAP5 has an
+	  additional register to power on USB3 PHY/SATA PHY/PCIE PHY
+	  (PIPE3 PHY).
+
 config OMAP_USB2
 	tristate "OMAP USB2 PHY Driver"
 	depends on ARCH_OMAP2PLUS
 	depends on USB_PHY
 	select GENERIC_PHY
-	select OMAP_CONTROL_USB
+	select OMAP_CONTROL_PHY
 	help
 	  Enable this to support the transceiver that is part of SOC. This
 	  driver takes care of all the PHY functionality apart from comparator.
@@ -47,7 +57,7 @@ config TI_PIPE3
 	tristate "TI PIPE3 PHY Driver"
 	depends on ARCH_OMAP2PLUS || COMPILE_TEST
 	select GENERIC_PHY
-	select OMAP_CONTROL_USB
+	select OMAP_CONTROL_PHY
 	help
 	  Enable this to support the PIPE3 PHY that is part of TI SOCs. This
 	  driver takes care of all the PHY functionality apart from comparator.
diff --git a/drivers/phy/Makefile b/drivers/phy/Makefile
index ecf0d3f5bf1d..8da05a841112 100644
--- a/drivers/phy/Makefile
+++ b/drivers/phy/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_BCM_KONA_USB2_PHY)		+= phy-bcm-kona-usb2.o
 obj-$(CONFIG_PHY_EXYNOS_DP_VIDEO)	+= phy-exynos-dp-video.o
 obj-$(CONFIG_PHY_EXYNOS_MIPI_VIDEO)	+= phy-exynos-mipi-video.o
 obj-$(CONFIG_PHY_MVEBU_SATA)		+= phy-mvebu-sata.o
+obj-$(CONFIG_OMAP_CONTROL_PHY)		+= phy-omap-control.o
 obj-$(CONFIG_OMAP_USB2)			+= phy-omap-usb2.o
 obj-$(CONFIG_TI_PIPE3)			+= phy-ti-pipe3.o
 obj-$(CONFIG_TWL4030_USB)		+= phy-twl4030-usb.o
diff --git a/drivers/phy/phy-omap-control.c b/drivers/phy/phy-omap-control.c
new file mode 100644
index 000000000000..17fc200210c8
--- /dev/null
+++ b/drivers/phy/phy-omap-control.c
@@ -0,0 +1,320 @@
+/*
+ * omap-control-phy.c - The PHY part of control module.
+ *
+ * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * Author: Kishon Vijay Abraham I <kishon@ti.com>
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/phy/omap_control_phy.h>
+
+/**
+ * omap_control_phy_power - power on/off the phy using control module reg
+ * @dev: the control module device
+ * @on: 0 or 1, based on powering on or off the PHY
+ */
+void omap_control_phy_power(struct device *dev, int on)
+{
+	u32 val;
+	unsigned long rate;
+	struct omap_control_phy	*control_phy;
+
+	if (IS_ERR(dev) || !dev) {
+		pr_err("%s: invalid device\n", __func__);
+		return;
+	}
+
+	control_phy = dev_get_drvdata(dev);
+	if (!control_phy) {
+		dev_err(dev, "%s: invalid control phy device\n", __func__);
+		return;
+	}
+
+	if (control_phy->type == OMAP_CTRL_TYPE_OTGHS)
+		return;
+
+	val = readl(control_phy->power);
+
+	switch (control_phy->type) {
+	case OMAP_CTRL_TYPE_USB2:
+		if (on)
+			val &= ~OMAP_CTRL_DEV_PHY_PD;
+		else
+			val |= OMAP_CTRL_DEV_PHY_PD;
+		break;
+
+	case OMAP_CTRL_TYPE_PIPE3:
+		rate = clk_get_rate(control_phy->sys_clk);
+		rate = rate/1000000;
+
+		if (on) {
+			val &= ~(OMAP_CTRL_PIPE3_PHY_PWRCTL_CLK_CMD_MASK |
+				OMAP_CTRL_PIPE3_PHY_PWRCTL_CLK_FREQ_MASK);
+			val |= OMAP_CTRL_PIPE3_PHY_TX_RX_POWERON <<
+				OMAP_CTRL_PIPE3_PHY_PWRCTL_CLK_CMD_SHIFT;
+			val |= rate <<
+				OMAP_CTRL_PIPE3_PHY_PWRCTL_CLK_FREQ_SHIFT;
+		} else {
+			val &= ~OMAP_CTRL_PIPE3_PHY_PWRCTL_CLK_CMD_MASK;
+			val |= OMAP_CTRL_PIPE3_PHY_TX_RX_POWEROFF <<
+				OMAP_CTRL_PIPE3_PHY_PWRCTL_CLK_CMD_SHIFT;
+		}
+		break;
+
+	case OMAP_CTRL_TYPE_DRA7USB2:
+		if (on)
+			val &= ~OMAP_CTRL_USB2_PHY_PD;
+		else
+			val |= OMAP_CTRL_USB2_PHY_PD;
+		break;
+
+	case OMAP_CTRL_TYPE_AM437USB2:
+		if (on) {
+			val &= ~(AM437X_CTRL_USB2_PHY_PD |
+					AM437X_CTRL_USB2_OTG_PD);
+			val |= (AM437X_CTRL_USB2_OTGVDET_EN |
+					AM437X_CTRL_USB2_OTGSESSEND_EN);
+		} else {
+			val &= ~(AM437X_CTRL_USB2_OTGVDET_EN |
+					AM437X_CTRL_USB2_OTGSESSEND_EN);
+			val |= (AM437X_CTRL_USB2_PHY_PD |
+					 AM437X_CTRL_USB2_OTG_PD);
+		}
+		break;
+	default:
+		dev_err(dev, "%s: type %d not recognized\n",
+			__func__, control_phy->type);
+		break;
+	}
+
+	writel(val, control_phy->power);
+}
+EXPORT_SYMBOL_GPL(omap_control_phy_power);
+
+/**
+ * omap_control_usb_host_mode - set AVALID, VBUSVALID and ID pin in grounded
+ * @ctrl_phy: struct omap_control_phy *
+ *
+ * Writes to the mailbox register to notify the usb core that a usb
+ * device has been connected.
+ */
+static void omap_control_usb_host_mode(struct omap_control_phy *ctrl_phy)
+{
+	u32 val;
+
+	val = readl(ctrl_phy->otghs_control);
+	val &= ~(OMAP_CTRL_DEV_IDDIG | OMAP_CTRL_DEV_SESSEND);
+	val |= OMAP_CTRL_DEV_AVALID | OMAP_CTRL_DEV_VBUSVALID;
+	writel(val, ctrl_phy->otghs_control);
+}
+
+/**
+ * omap_control_usb_device_mode - set AVALID, VBUSVALID and ID pin in high
+ * impedance
+ * @ctrl_phy: struct omap_control_phy *
+ *
+ * Writes to the mailbox register to notify the usb core that it has been
+ * connected to a usb host.
+ */
+static void omap_control_usb_device_mode(struct omap_control_phy *ctrl_phy)
+{
+	u32 val;
+
+	val = readl(ctrl_phy->otghs_control);
+	val &= ~OMAP_CTRL_DEV_SESSEND;
+	val |= OMAP_CTRL_DEV_IDDIG | OMAP_CTRL_DEV_AVALID |
+		OMAP_CTRL_DEV_VBUSVALID;
+	writel(val, ctrl_phy->otghs_control);
+}
+
+/**
+ * omap_control_usb_set_sessionend - Enable SESSIONEND and IDIG to high
+ * impedance
+ * @ctrl_phy: struct omap_control_phy *
+ *
+ * Writes to the mailbox register to notify the usb core it's now in
+ * disconnected state.
+ */
+static void omap_control_usb_set_sessionend(struct omap_control_phy *ctrl_phy)
+{
+	u32 val;
+
+	val = readl(ctrl_phy->otghs_control);
+	val &= ~(OMAP_CTRL_DEV_AVALID | OMAP_CTRL_DEV_VBUSVALID);
+	val |= OMAP_CTRL_DEV_IDDIG | OMAP_CTRL_DEV_SESSEND;
+	writel(val, ctrl_phy->otghs_control);
+}
+
+/**
+ * omap_control_usb_set_mode - Calls to functions to set USB in one of host mode
+ * or device mode or to denote disconnected state
+ * @dev: the control module device
+ * @mode: The mode to which usb should be configured
+ *
+ * This is an API to write to the mailbox register to notify the usb core that
+ * a usb device has been connected.
+ */
+void omap_control_usb_set_mode(struct device *dev,
+	enum omap_control_usb_mode mode)
+{
+	struct omap_control_phy	*ctrl_phy;
+
+	if (IS_ERR(dev) || !dev)
+		return;
+
+	ctrl_phy = dev_get_drvdata(dev);
+
+	if (!ctrl_phy) {
+		dev_err(dev, "Invalid control phy device\n");
+		return;
+	}
+
+	if (ctrl_phy->type != OMAP_CTRL_TYPE_OTGHS)
+		return;
+
+	switch (mode) {
+	case USB_MODE_HOST:
+		omap_control_usb_host_mode(ctrl_phy);
+		break;
+	case USB_MODE_DEVICE:
+		omap_control_usb_device_mode(ctrl_phy);
+		break;
+	case USB_MODE_DISCONNECT:
+		omap_control_usb_set_sessionend(ctrl_phy);
+		break;
+	default:
+		dev_vdbg(dev, "invalid omap control usb mode\n");
+	}
+}
+EXPORT_SYMBOL_GPL(omap_control_usb_set_mode);
+
+#ifdef CONFIG_OF
+
+static const enum omap_control_phy_type otghs_data = OMAP_CTRL_TYPE_OTGHS;
+static const enum omap_control_phy_type usb2_data = OMAP_CTRL_TYPE_USB2;
+static const enum omap_control_phy_type pipe3_data = OMAP_CTRL_TYPE_PIPE3;
+static const enum omap_control_phy_type dra7usb2_data = OMAP_CTRL_TYPE_DRA7USB2;
+static const enum omap_control_phy_type am437usb2_data = OMAP_CTRL_TYPE_AM437USB2;
+
+static const struct of_device_id omap_control_phy_id_table[] = {
+	{
+		.compatible = "ti,control-phy-otghs",
+		.data = &otghs_data,
+	},
+	{
+		.compatible = "ti,control-phy-usb2",
+		.data = &usb2_data,
+	},
+	{
+		.compatible = "ti,control-phy-pipe3",
+		.data = &pipe3_data,
+	},
+	{
+		.compatible = "ti,control-phy-dra7usb2",
+		.data = &dra7usb2_data,
+	},
+	{
+		.compatible = "ti,control-phy-am437usb2",
+		.data = &am437usb2_data,
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, omap_control_phy_id_table);
+#endif
+
+
+static int omap_control_phy_probe(struct platform_device *pdev)
+{
+	struct resource	*res;
+	const struct of_device_id *of_id;
+	struct omap_control_phy *control_phy;
+
+	of_id = of_match_device(of_match_ptr(omap_control_phy_id_table),
+				&pdev->dev);
+	if (!of_id)
+		return -EINVAL;
+
+	control_phy = devm_kzalloc(&pdev->dev, sizeof(*control_phy),
+		GFP_KERNEL);
+	if (!control_phy) {
+		dev_err(&pdev->dev, "unable to alloc memory for control phy\n");
+		return -ENOMEM;
+	}
+
+	control_phy->dev = &pdev->dev;
+	control_phy->type = *(enum omap_control_phy_type *)of_id->data;
+
+	if (control_phy->type == OMAP_CTRL_TYPE_OTGHS) {
+		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+			"otghs_control");
+		control_phy->otghs_control = devm_ioremap_resource(
+			&pdev->dev, res);
+		if (IS_ERR(control_phy->otghs_control))
+			return PTR_ERR(control_phy->otghs_control);
+	} else {
+		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+				"power");
+		control_phy->power = devm_ioremap_resource(&pdev->dev, res);
+		if (IS_ERR(control_phy->power)) {
+			dev_err(&pdev->dev, "Couldn't get power register\n");
+			return PTR_ERR(control_phy->power);
+		}
+	}
+
+	if (control_phy->type == OMAP_CTRL_TYPE_PIPE3) {
+		control_phy->sys_clk = devm_clk_get(control_phy->dev,
+			"sys_clkin");
+		if (IS_ERR(control_phy->sys_clk)) {
+			pr_err("%s: unable to get sys_clkin\n", __func__);
+			return -EINVAL;
+		}
+	}
+
+	dev_set_drvdata(control_phy->dev, control_phy);
+
+	return 0;
+}
+
+static struct platform_driver omap_control_phy_driver = {
+	.probe		= omap_control_phy_probe,
+	.driver		= {
+		.name	= "omap-control-phy",
+		.owner	= THIS_MODULE,
+		.of_match_table = of_match_ptr(omap_control_phy_id_table),
+	},
+};
+
+static int __init omap_control_phy_init(void)
+{
+	return platform_driver_register(&omap_control_phy_driver);
+}
+subsys_initcall(omap_control_phy_init);
+
+static void __exit omap_control_phy_exit(void)
+{
+	platform_driver_unregister(&omap_control_phy_driver);
+}
+module_exit(omap_control_phy_exit);
+
+MODULE_ALIAS("platform: omap_control_phy");
+MODULE_AUTHOR("Texas Instruments Inc.");
+MODULE_DESCRIPTION("OMAP Control Module PHY Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/phy/phy-omap-usb2.c b/drivers/phy/phy-omap-usb2.c
index 3cc4aba6e50e..a2205a841e5e 100644
--- a/drivers/phy/phy-omap-usb2.c
+++ b/drivers/phy/phy-omap-usb2.c
@@ -27,7 +27,7 @@
 #include <linux/err.h>
 #include <linux/pm_runtime.h>
 #include <linux/delay.h>
-#include <linux/usb/omap_control_usb.h>
+#include <linux/phy/omap_control_phy.h>
 #include <linux/phy/phy.h>
 #include <linux/of_platform.h>
 
@@ -105,7 +105,7 @@ static int omap_usb_power_off(struct phy *x)
 {
 	struct omap_usb *phy = phy_get_drvdata(x);
 
-	omap_control_usb_phy_power(phy->control_dev, 0);
+	omap_control_phy_power(phy->control_dev, 0);
 
 	return 0;
 }
@@ -114,7 +114,7 @@ static int omap_usb_power_on(struct phy *x)
 {
 	struct omap_usb *phy = phy_get_drvdata(x);
 
-	omap_control_usb_phy_power(phy->control_dev, 1);
+	omap_control_phy_power(phy->control_dev, 1);
 
 	return 0;
 }
@@ -251,7 +251,7 @@ static int omap_usb2_probe(struct platform_device *pdev)
 	}
 
 	phy->control_dev = &control_pdev->dev;
-	omap_control_usb_phy_power(phy->control_dev, 0);
+	omap_control_phy_power(phy->control_dev, 0);
 
 	otg->set_host		= omap_usb_set_host;
 	otg->set_peripheral	= omap_usb_set_peripheral;
diff --git a/drivers/phy/phy-ti-pipe3.c b/drivers/phy/phy-ti-pipe3.c
index c8d16746a5e2..fd029b14cb3e 100644
--- a/drivers/phy/phy-ti-pipe3.c
+++ b/drivers/phy/phy-ti-pipe3.c
@@ -26,7 +26,7 @@
 #include <linux/io.h>
 #include <linux/pm_runtime.h>
 #include <linux/delay.h>
-#include <linux/usb/omap_control_usb.h>
+#include <linux/phy/omap_control_phy.h>
 #include <linux/of_platform.h>
 
 #define	PLL_STATUS		0x00000004
@@ -134,7 +134,7 @@ static int ti_pipe3_power_off(struct phy *x)
 		return -EBUSY;
 	}
 
-	omap_control_usb_phy_power(phy->control_dev, 0);
+	omap_control_phy_power(phy->control_dev, 0);
 
 	return 0;
 }
@@ -232,7 +232,7 @@ static int ti_pipe3_init(struct phy *x)
 	if (ret)
 		return ret;
 
-	omap_control_usb_phy_power(phy->control_dev, 1);
+	omap_control_phy_power(phy->control_dev, 1);
 
 	return 0;
 }
@@ -304,7 +304,7 @@ static int ti_pipe3_probe(struct platform_device *pdev)
 
 	phy->control_dev = &control_pdev->dev;
 
-	omap_control_usb_phy_power(phy->control_dev, 0);
+	omap_control_phy_power(phy->control_dev, 0);
 
 	platform_set_drvdata(pdev, phy);
 	pm_runtime_enable(phy->dev);
diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c
index 8aa59a2c5eb2..d341c149a2f9 100644
--- a/drivers/usb/musb/omap2430.c
+++ b/drivers/usb/musb/omap2430.c
@@ -37,7 +37,7 @@
 #include <linux/err.h>
 #include <linux/delay.h>
 #include <linux/usb/musb-omap.h>
-#include <linux/usb/omap_control_usb.h>
+#include <linux/phy/omap_control_phy.h>
 #include <linux/of_platform.h>
 
 #include "musb_core.h"
diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig
index c337ba2d066b..416e0c8cf6ff 100644
--- a/drivers/usb/phy/Kconfig
+++ b/drivers/usb/phy/Kconfig
@@ -75,16 +75,6 @@ config NOP_USB_XCEIV
 	  built-in with usb ip or which are autonomous and doesn't require any
 	  phy programming such as ISP1x04 etc.
 
-config OMAP_CONTROL_USB
-	tristate "OMAP CONTROL USB Driver"
-	depends on ARCH_OMAP2PLUS || COMPILE_TEST
-	help
-	  Enable this to add support for the USB part present in the control
-	  module. This driver has API to power on the USB2 PHY and to write to
-	  the mailbox. The mailbox is present only in omap4 and the register to
-	  power on the USB2 PHY is present in OMAP4 and OMAP5. OMAP5 has an
-	  additional register to power on USB3 PHY.
-
 config AM335X_CONTROL_USB
 	tristate
 
diff --git a/drivers/usb/phy/Makefile b/drivers/usb/phy/Makefile
index 15f1878388f4..f8fa719a31b9 100644
--- a/drivers/usb/phy/Makefile
+++ b/drivers/usb/phy/Makefile
@@ -13,7 +13,6 @@ obj-$(CONFIG_ISP1301_OMAP)		+= phy-isp1301-omap.o
 obj-$(CONFIG_MV_U3D_PHY)		+= phy-mv-u3d-usb.o
 obj-$(CONFIG_NOP_USB_XCEIV)		+= phy-generic.o
 obj-$(CONFIG_TAHVO_USB)			+= phy-tahvo.o
-obj-$(CONFIG_OMAP_CONTROL_USB)		+= phy-omap-control.o
 obj-$(CONFIG_AM335X_CONTROL_USB)	+= phy-am335x-control.o
 obj-$(CONFIG_AM335X_PHY_USB)		+= phy-am335x.o
 obj-$(CONFIG_OMAP_OTG)			+= phy-omap-otg.o
diff --git a/drivers/usb/phy/phy-omap-control.c b/drivers/usb/phy/phy-omap-control.c
deleted file mode 100644
index e7253182e47d..000000000000
--- a/drivers/usb/phy/phy-omap-control.c
+++ /dev/null
@@ -1,319 +0,0 @@
-/*
- * omap-control-usb.c - The USB part of control module.
- *
- * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * Author: Kishon Vijay Abraham I <kishon@ti.com>
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
-#include <linux/err.h>
-#include <linux/io.h>
-#include <linux/clk.h>
-#include <linux/usb/omap_control_usb.h>
-
-/**
- * omap_control_usb_phy_power - power on/off the phy using control module reg
- * @dev: the control module device
- * @on: 0 or 1, based on powering on or off the PHY
- */
-void omap_control_usb_phy_power(struct device *dev, int on)
-{
-	u32 val;
-	unsigned long rate;
-	struct omap_control_usb	*control_usb;
-
-	if (IS_ERR(dev) || !dev) {
-		pr_err("%s: invalid device\n", __func__);
-		return;
-	}
-
-	control_usb = dev_get_drvdata(dev);
-	if (!control_usb) {
-		dev_err(dev, "%s: invalid control usb device\n", __func__);
-		return;
-	}
-
-	if (control_usb->type == OMAP_CTRL_TYPE_OTGHS)
-		return;
-
-	val = readl(control_usb->power);
-
-	switch (control_usb->type) {
-	case OMAP_CTRL_TYPE_USB2:
-		if (on)
-			val &= ~OMAP_CTRL_DEV_PHY_PD;
-		else
-			val |= OMAP_CTRL_DEV_PHY_PD;
-		break;
-
-	case OMAP_CTRL_TYPE_PIPE3:
-		rate = clk_get_rate(control_usb->sys_clk);
-		rate = rate/1000000;
-
-		if (on) {
-			val &= ~(OMAP_CTRL_USB_PWRCTL_CLK_CMD_MASK |
-					OMAP_CTRL_USB_PWRCTL_CLK_FREQ_MASK);
-			val |= OMAP_CTRL_USB3_PHY_TX_RX_POWERON <<
-				OMAP_CTRL_USB_PWRCTL_CLK_CMD_SHIFT;
-			val |= rate << OMAP_CTRL_USB_PWRCTL_CLK_FREQ_SHIFT;
-		} else {
-			val &= ~OMAP_CTRL_USB_PWRCTL_CLK_CMD_MASK;
-			val |= OMAP_CTRL_USB3_PHY_TX_RX_POWEROFF <<
-				OMAP_CTRL_USB_PWRCTL_CLK_CMD_SHIFT;
-		}
-		break;
-
-	case OMAP_CTRL_TYPE_DRA7USB2:
-		if (on)
-			val &= ~OMAP_CTRL_USB2_PHY_PD;
-		else
-			val |= OMAP_CTRL_USB2_PHY_PD;
-		break;
-
-	case OMAP_CTRL_TYPE_AM437USB2:
-		if (on) {
-			val &= ~(AM437X_CTRL_USB2_PHY_PD |
-					AM437X_CTRL_USB2_OTG_PD);
-			val |= (AM437X_CTRL_USB2_OTGVDET_EN |
-					AM437X_CTRL_USB2_OTGSESSEND_EN);
-		} else {
-			val &= ~(AM437X_CTRL_USB2_OTGVDET_EN |
-					AM437X_CTRL_USB2_OTGSESSEND_EN);
-			val |= (AM437X_CTRL_USB2_PHY_PD |
-					 AM437X_CTRL_USB2_OTG_PD);
-		}
-		break;
-	default:
-		dev_err(dev, "%s: type %d not recognized\n",
-					__func__, control_usb->type);
-		break;
-	}
-
-	writel(val, control_usb->power);
-}
-EXPORT_SYMBOL_GPL(omap_control_usb_phy_power);
-
-/**
- * omap_control_usb_host_mode - set AVALID, VBUSVALID and ID pin in grounded
- * @ctrl_usb: struct omap_control_usb *
- *
- * Writes to the mailbox register to notify the usb core that a usb
- * device has been connected.
- */
-static void omap_control_usb_host_mode(struct omap_control_usb *ctrl_usb)
-{
-	u32 val;
-
-	val = readl(ctrl_usb->otghs_control);
-	val &= ~(OMAP_CTRL_DEV_IDDIG | OMAP_CTRL_DEV_SESSEND);
-	val |= OMAP_CTRL_DEV_AVALID | OMAP_CTRL_DEV_VBUSVALID;
-	writel(val, ctrl_usb->otghs_control);
-}
-
-/**
- * omap_control_usb_device_mode - set AVALID, VBUSVALID and ID pin in high
- * impedance
- * @ctrl_usb: struct omap_control_usb *
- *
- * Writes to the mailbox register to notify the usb core that it has been
- * connected to a usb host.
- */
-static void omap_control_usb_device_mode(struct omap_control_usb *ctrl_usb)
-{
-	u32 val;
-
-	val = readl(ctrl_usb->otghs_control);
-	val &= ~OMAP_CTRL_DEV_SESSEND;
-	val |= OMAP_CTRL_DEV_IDDIG | OMAP_CTRL_DEV_AVALID |
-		OMAP_CTRL_DEV_VBUSVALID;
-	writel(val, ctrl_usb->otghs_control);
-}
-
-/**
- * omap_control_usb_set_sessionend - Enable SESSIONEND and IDIG to high
- * impedance
- * @ctrl_usb: struct omap_control_usb *
- *
- * Writes to the mailbox register to notify the usb core it's now in
- * disconnected state.
- */
-static void omap_control_usb_set_sessionend(struct omap_control_usb *ctrl_usb)
-{
-	u32 val;
-
-	val = readl(ctrl_usb->otghs_control);
-	val &= ~(OMAP_CTRL_DEV_AVALID | OMAP_CTRL_DEV_VBUSVALID);
-	val |= OMAP_CTRL_DEV_IDDIG | OMAP_CTRL_DEV_SESSEND;
-	writel(val, ctrl_usb->otghs_control);
-}
-
-/**
- * omap_control_usb_set_mode - Calls to functions to set USB in one of host mode
- * or device mode or to denote disconnected state
- * @dev: the control module device
- * @mode: The mode to which usb should be configured
- *
- * This is an API to write to the mailbox register to notify the usb core that
- * a usb device has been connected.
- */
-void omap_control_usb_set_mode(struct device *dev,
-	enum omap_control_usb_mode mode)
-{
-	struct omap_control_usb	*ctrl_usb;
-
-	if (IS_ERR(dev) || !dev)
-		return;
-
-	ctrl_usb = dev_get_drvdata(dev);
-
-	if (!ctrl_usb) {
-		dev_err(dev, "Invalid control usb device\n");
-		return;
-	}
-
-	if (ctrl_usb->type != OMAP_CTRL_TYPE_OTGHS)
-		return;
-
-	switch (mode) {
-	case USB_MODE_HOST:
-		omap_control_usb_host_mode(ctrl_usb);
-		break;
-	case USB_MODE_DEVICE:
-		omap_control_usb_device_mode(ctrl_usb);
-		break;
-	case USB_MODE_DISCONNECT:
-		omap_control_usb_set_sessionend(ctrl_usb);
-		break;
-	default:
-		dev_vdbg(dev, "invalid omap control usb mode\n");
-	}
-}
-EXPORT_SYMBOL_GPL(omap_control_usb_set_mode);
-
-#ifdef CONFIG_OF
-
-static const enum omap_control_usb_type otghs_data = OMAP_CTRL_TYPE_OTGHS;
-static const enum omap_control_usb_type usb2_data = OMAP_CTRL_TYPE_USB2;
-static const enum omap_control_usb_type pipe3_data = OMAP_CTRL_TYPE_PIPE3;
-static const enum omap_control_usb_type dra7usb2_data = OMAP_CTRL_TYPE_DRA7USB2;
-static const enum omap_control_usb_type am437usb2_data = OMAP_CTRL_TYPE_AM437USB2;
-
-static const struct of_device_id omap_control_usb_id_table[] = {
-	{
-		.compatible = "ti,control-phy-otghs",
-		.data = &otghs_data,
-	},
-	{
-		.compatible = "ti,control-phy-usb2",
-		.data = &usb2_data,
-	},
-	{
-		.compatible = "ti,control-phy-pipe3",
-		.data = &pipe3_data,
-	},
-	{
-		.compatible = "ti,control-phy-dra7usb2",
-		.data = &dra7usb2_data,
-	},
-	{
-		.compatible = "ti,control-phy-am437usb2",
-		.data = &am437usb2_data,
-	},
-	{},
-};
-MODULE_DEVICE_TABLE(of, omap_control_usb_id_table);
-#endif
-
-
-static int omap_control_usb_probe(struct platform_device *pdev)
-{
-	struct resource	*res;
-	const struct of_device_id *of_id;
-	struct omap_control_usb *control_usb;
-
-	of_id = of_match_device(of_match_ptr(omap_control_usb_id_table),
-								&pdev->dev);
-	if (!of_id)
-		return -EINVAL;
-
-	control_usb = devm_kzalloc(&pdev->dev, sizeof(*control_usb),
-		GFP_KERNEL);
-	if (!control_usb) {
-		dev_err(&pdev->dev, "unable to alloc memory for control usb\n");
-		return -ENOMEM;
-	}
-
-	control_usb->dev = &pdev->dev;
-	control_usb->type = *(enum omap_control_usb_type *)of_id->data;
-
-	if (control_usb->type == OMAP_CTRL_TYPE_OTGHS) {
-		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-			"otghs_control");
-		control_usb->otghs_control = devm_ioremap_resource(
-			&pdev->dev, res);
-		if (IS_ERR(control_usb->otghs_control))
-			return PTR_ERR(control_usb->otghs_control);
-	} else {
-		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-				"power");
-		control_usb->power = devm_ioremap_resource(&pdev->dev, res);
-		if (IS_ERR(control_usb->power)) {
-			dev_err(&pdev->dev, "Couldn't get power register\n");
-			return PTR_ERR(control_usb->power);
-		}
-	}
-
-	if (control_usb->type == OMAP_CTRL_TYPE_PIPE3) {
-		control_usb->sys_clk = devm_clk_get(control_usb->dev,
-			"sys_clkin");
-		if (IS_ERR(control_usb->sys_clk)) {
-			pr_err("%s: unable to get sys_clkin\n", __func__);
-			return -EINVAL;
-		}
-	}
-
-	dev_set_drvdata(control_usb->dev, control_usb);
-
-	return 0;
-}
-
-static struct platform_driver omap_control_usb_driver = {
-	.probe		= omap_control_usb_probe,
-	.driver		= {
-		.name	= "omap-control-usb",
-		.owner	= THIS_MODULE,
-		.of_match_table = of_match_ptr(omap_control_usb_id_table),
-	},
-};
-
-static int __init omap_control_usb_init(void)
-{
-	return platform_driver_register(&omap_control_usb_driver);
-}
-subsys_initcall(omap_control_usb_init);
-
-static void __exit omap_control_usb_exit(void)
-{
-	platform_driver_unregister(&omap_control_usb_driver);
-}
-module_exit(omap_control_usb_exit);
-
-MODULE_ALIAS("platform: omap_control_usb");
-MODULE_AUTHOR("Texas Instruments Inc.");
-MODULE_DESCRIPTION("OMAP Control Module USB Driver");
-MODULE_LICENSE("GPL v2");
diff --git a/include/linux/phy/omap_control_phy.h b/include/linux/phy/omap_control_phy.h
new file mode 100644
index 000000000000..5450403c7546
--- /dev/null
+++ b/include/linux/phy/omap_control_phy.h
@@ -0,0 +1,89 @@
+/*
+ * omap_control_phy.h - Header file for the PHY part of control module.
+ *
+ * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * Author: Kishon Vijay Abraham I <kishon@ti.com>
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __OMAP_CONTROL_PHY_H__
+#define __OMAP_CONTROL_PHY_H__
+
+enum omap_control_phy_type {
+	OMAP_CTRL_TYPE_OTGHS = 1,	/* Mailbox OTGHS_CONTROL */
+	OMAP_CTRL_TYPE_USB2,	/* USB2_PHY, power down in CONTROL_DEV_CONF */
+	OMAP_CTRL_TYPE_PIPE3,	/* PIPE3 PHY, DPLL & seperate Rx/Tx power */
+	OMAP_CTRL_TYPE_DRA7USB2, /* USB2 PHY, power and power_aux e.g. DRA7 */
+	OMAP_CTRL_TYPE_AM437USB2, /* USB2 PHY, power e.g. AM437x */
+};
+
+struct omap_control_phy {
+	struct device *dev;
+
+	u32 __iomem *otghs_control;
+	u32 __iomem *power;
+	u32 __iomem *power_aux;
+
+	struct clk *sys_clk;
+
+	enum omap_control_phy_type type;
+};
+
+enum omap_control_usb_mode {
+	USB_MODE_UNDEFINED = 0,
+	USB_MODE_HOST,
+	USB_MODE_DEVICE,
+	USB_MODE_DISCONNECT,
+};
+
+#define	OMAP_CTRL_DEV_PHY_PD		BIT(0)
+
+#define	OMAP_CTRL_DEV_AVALID		BIT(0)
+#define	OMAP_CTRL_DEV_BVALID		BIT(1)
+#define	OMAP_CTRL_DEV_VBUSVALID		BIT(2)
+#define	OMAP_CTRL_DEV_SESSEND		BIT(3)
+#define	OMAP_CTRL_DEV_IDDIG		BIT(4)
+
+#define	OMAP_CTRL_PIPE3_PHY_PWRCTL_CLK_CMD_MASK		0x003FC000
+#define	OMAP_CTRL_PIPE3_PHY_PWRCTL_CLK_CMD_SHIFT	0xE
+
+#define	OMAP_CTRL_PIPE3_PHY_PWRCTL_CLK_FREQ_MASK	0xFFC00000
+#define	OMAP_CTRL_PIPE3_PHY_PWRCTL_CLK_FREQ_SHIFT	0x16
+
+#define	OMAP_CTRL_PIPE3_PHY_TX_RX_POWERON	0x3
+#define	OMAP_CTRL_PIPE3_PHY_TX_RX_POWEROFF	0x0
+
+#define OMAP_CTRL_USB2_PHY_PD		BIT(28)
+
+#define AM437X_CTRL_USB2_PHY_PD		BIT(0)
+#define AM437X_CTRL_USB2_OTG_PD		BIT(1)
+#define AM437X_CTRL_USB2_OTGVDET_EN	BIT(19)
+#define AM437X_CTRL_USB2_OTGSESSEND_EN	BIT(20)
+
+#if IS_ENABLED(CONFIG_OMAP_CONTROL_PHY)
+void omap_control_phy_power(struct device *dev, int on);
+void omap_control_usb_set_mode(struct device *dev,
+			       enum omap_control_usb_mode mode);
+#else
+
+static inline void omap_control_phy_power(struct device *dev, int on)
+{
+}
+
+static inline void omap_control_usb_set_mode(struct device *dev,
+	enum omap_control_usb_mode mode)
+{
+}
+#endif
+
+#endif	/* __OMAP_CONTROL_PHY_H__ */
diff --git a/include/linux/usb/omap_control_usb.h b/include/linux/usb/omap_control_usb.h
deleted file mode 100644
index 69ae383ee3cc..000000000000
--- a/include/linux/usb/omap_control_usb.h
+++ /dev/null
@@ -1,89 +0,0 @@
-/*
- * omap_control_usb.h - Header file for the USB part of control module.
- *
- * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * Author: Kishon Vijay Abraham I <kishon@ti.com>
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#ifndef __OMAP_CONTROL_USB_H__
-#define __OMAP_CONTROL_USB_H__
-
-enum omap_control_usb_type {
-	OMAP_CTRL_TYPE_OTGHS = 1,	/* Mailbox OTGHS_CONTROL */
-	OMAP_CTRL_TYPE_USB2,	/* USB2_PHY, power down in CONTROL_DEV_CONF */
-	OMAP_CTRL_TYPE_PIPE3,	/* PIPE3 PHY, DPLL & seperate Rx/Tx power */
-	OMAP_CTRL_TYPE_DRA7USB2, /* USB2 PHY, power and power_aux e.g. DRA7 */
-	OMAP_CTRL_TYPE_AM437USB2, /* USB2 PHY, power e.g. AM437x */
-};
-
-struct omap_control_usb {
-	struct device *dev;
-
-	u32 __iomem *otghs_control;
-	u32 __iomem *power;
-	u32 __iomem *power_aux;
-
-	struct clk *sys_clk;
-
-	enum omap_control_usb_type type;
-};
-
-enum omap_control_usb_mode {
-	USB_MODE_UNDEFINED = 0,
-	USB_MODE_HOST,
-	USB_MODE_DEVICE,
-	USB_MODE_DISCONNECT,
-};
-
-#define	OMAP_CTRL_DEV_PHY_PD		BIT(0)
-
-#define	OMAP_CTRL_DEV_AVALID		BIT(0)
-#define	OMAP_CTRL_DEV_BVALID		BIT(1)
-#define	OMAP_CTRL_DEV_VBUSVALID		BIT(2)
-#define	OMAP_CTRL_DEV_SESSEND		BIT(3)
-#define	OMAP_CTRL_DEV_IDDIG		BIT(4)
-
-#define	OMAP_CTRL_USB_PWRCTL_CLK_CMD_MASK	0x003FC000
-#define	OMAP_CTRL_USB_PWRCTL_CLK_CMD_SHIFT	0xE
-
-#define	OMAP_CTRL_USB_PWRCTL_CLK_FREQ_MASK	0xFFC00000
-#define	OMAP_CTRL_USB_PWRCTL_CLK_FREQ_SHIFT	0x16
-
-#define	OMAP_CTRL_USB3_PHY_TX_RX_POWERON	0x3
-#define	OMAP_CTRL_USB3_PHY_TX_RX_POWEROFF	0x0
-
-#define OMAP_CTRL_USB2_PHY_PD		BIT(28)
-
-#define AM437X_CTRL_USB2_PHY_PD		BIT(0)
-#define AM437X_CTRL_USB2_OTG_PD		BIT(1)
-#define AM437X_CTRL_USB2_OTGVDET_EN	BIT(19)
-#define AM437X_CTRL_USB2_OTGSESSEND_EN	BIT(20)
-
-#if IS_ENABLED(CONFIG_OMAP_CONTROL_USB)
-extern void omap_control_usb_phy_power(struct device *dev, int on);
-extern void omap_control_usb_set_mode(struct device *dev,
-	enum omap_control_usb_mode mode);
-#else
-
-static inline void omap_control_usb_phy_power(struct device *dev, int on)
-{
-}
-
-static inline void omap_control_usb_set_mode(struct device *dev,
-	enum omap_control_usb_mode mode)
-{
-}
-#endif
-
-#endif	/* __OMAP_CONTROL_USB_H__ */
-- 
cgit v1.2.3


From 45126da22452ac3d4685401a1e921a39ac0ff2f6 Mon Sep 17 00:00:00 2001
From: Sonic Zhang <sonic.zhang@analog.com>
Date: Tue, 28 Jan 2014 16:55:21 +0800
Subject: i2c: bfin-twi: move bits macros and structs in header from arch
 include to generic include

The ADI TWI peripheral is not binding to the Blackfin processor only.
The bits macros and structs should be put in the generic include header.
And update head file path in drivers accordingly.

Signed-off-by: Sonic Zhang <sonic.zhang@analog.com>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 arch/blackfin/include/asm/bfin_twi.h | 126 +-----------------------------
 arch/blackfin/kernel/debug-mmrs.c    |   1 +
 drivers/i2c/busses/i2c-bfin-twi.c    |   4 +-
 include/linux/i2c/bfin_twi.h         | 145 +++++++++++++++++++++++++++++++++++
 4 files changed, 149 insertions(+), 127 deletions(-)
 create mode 100644 include/linux/i2c/bfin_twi.h

(limited to 'include/linux')

diff --git a/arch/blackfin/include/asm/bfin_twi.h b/arch/blackfin/include/asm/bfin_twi.h
index 90c3c006557d..34cc395f8b77 100644
--- a/arch/blackfin/include/asm/bfin_twi.h
+++ b/arch/blackfin/include/asm/bfin_twi.h
@@ -9,60 +9,7 @@
 #ifndef __ASM_BFIN_TWI_H__
 #define __ASM_BFIN_TWI_H__
 
-#include <linux/types.h>
-#include <linux/i2c.h>
-
-/*
- * All Blackfin system MMRs are padded to 32bits even if the register
- * itself is only 16bits.  So use a helper macro to streamline this.
- */
-#define __BFP(m) u16 m; u16 __pad_##m
-
-/*
- * bfin twi registers layout
- */
-struct bfin_twi_regs {
-	__BFP(clkdiv);
-	__BFP(control);
-	__BFP(slave_ctl);
-	__BFP(slave_stat);
-	__BFP(slave_addr);
-	__BFP(master_ctl);
-	__BFP(master_stat);
-	__BFP(master_addr);
-	__BFP(int_stat);
-	__BFP(int_mask);
-	__BFP(fifo_ctl);
-	__BFP(fifo_stat);
-	u32 __pad[20];
-	__BFP(xmt_data8);
-	__BFP(xmt_data16);
-	__BFP(rcv_data8);
-	__BFP(rcv_data16);
-};
-
-#undef __BFP
-
-struct bfin_twi_iface {
-	int			irq;
-	spinlock_t		lock;
-	char			read_write;
-	u8			command;
-	u8			*transPtr;
-	int			readNum;
-	int			writeNum;
-	int			cur_mode;
-	int			manual_stop;
-	int			result;
-	struct i2c_adapter	adap;
-	struct completion	complete;
-	struct i2c_msg		*pmsg;
-	int			msg_num;
-	int			cur_msg;
-	u16			saved_clkdiv;
-	u16			saved_control;
-	struct bfin_twi_regs __iomem *regs_base;
-};
+#include <asm/blackfin.h>
 
 #define DEFINE_TWI_REG(reg_name, reg) \
 static inline u16 read_##reg_name(struct bfin_twi_iface *iface) \
@@ -113,75 +60,4 @@ static inline u16 read_RCV_DATA16(struct bfin_twi_iface *iface)
 }
 #endif
 
-
-/*  ********************  TWO-WIRE INTERFACE (TWI) MASKS  ***********************/
-/* TWI_CLKDIV Macros (Use: *pTWI_CLKDIV = CLKLOW(x)|CLKHI(y);  )				*/
-#define	CLKLOW(x)	((x) & 0xFF)	/* Periods Clock Is Held Low                    */
-#define CLKHI(y)	(((y)&0xFF)<<0x8)	/* Periods Before New Clock Low                 */
-
-/* TWI_PRESCALE Masks															*/
-#define	PRESCALE	0x007F	/* SCLKs Per Internal Time Reference (10MHz)    */
-#define	TWI_ENA		0x0080	/* TWI Enable                                                                   */
-#define	SCCB		0x0200	/* SCCB Compatibility Enable                                    */
-
-/* TWI_SLAVE_CTL Masks															*/
-#define	SEN			0x0001	/* Slave Enable                                                                 */
-#define	SADD_LEN	0x0002	/* Slave Address Length                                                 */
-#define	STDVAL		0x0004	/* Slave Transmit Data Valid                                    */
-#define	NAK			0x0008	/* NAK/ACK* Generated At Conclusion Of Transfer */
-#define	GEN			0x0010	/* General Call Address Matching Enabled                */
-
-/* TWI_SLAVE_STAT Masks															*/
-#define	SDIR		0x0001	/* Slave Transfer Direction (Transmit/Receive*) */
-#define GCALL		0x0002	/* General Call Indicator                                               */
-
-/* TWI_MASTER_CTL Masks													*/
-#define	MEN			0x0001	/* Master Mode Enable                                           */
-#define	MADD_LEN	0x0002	/* Master Address Length                                        */
-#define	MDIR		0x0004	/* Master Transmit Direction (RX/TX*)           */
-#define	FAST		0x0008	/* Use Fast Mode Timing Specs                           */
-#define	STOP		0x0010	/* Issue Stop Condition                                         */
-#define	RSTART		0x0020	/* Repeat Start or Stop* At End Of Transfer     */
-#define	DCNT		0x3FC0	/* Data Bytes To Transfer                                       */
-#define	SDAOVR		0x4000	/* Serial Data Override                                         */
-#define	SCLOVR		0x8000	/* Serial Clock Override                                        */
-
-/* TWI_MASTER_STAT Masks														*/
-#define	MPROG		0x0001	/* Master Transfer In Progress                                  */
-#define	LOSTARB		0x0002	/* Lost Arbitration Indicator (Xfer Aborted)    */
-#define	ANAK		0x0004	/* Address Not Acknowledged                                             */
-#define	DNAK		0x0008	/* Data Not Acknowledged                                                */
-#define	BUFRDERR	0x0010	/* Buffer Read Error                                                    */
-#define	BUFWRERR	0x0020	/* Buffer Write Error                                                   */
-#define	SDASEN		0x0040	/* Serial Data Sense                                                    */
-#define	SCLSEN		0x0080	/* Serial Clock Sense                                                   */
-#define	BUSBUSY		0x0100	/* Bus Busy Indicator                                                   */
-
-/* TWI_INT_SRC and TWI_INT_ENABLE Masks						*/
-#define	SINIT		0x0001	/* Slave Transfer Initiated     */
-#define	SCOMP		0x0002	/* Slave Transfer Complete      */
-#define	SERR		0x0004	/* Slave Transfer Error         */
-#define	SOVF		0x0008	/* Slave Overflow                       */
-#define	MCOMP		0x0010	/* Master Transfer Complete     */
-#define	MERR		0x0020	/* Master Transfer Error        */
-#define	XMTSERV		0x0040	/* Transmit FIFO Service        */
-#define	RCVSERV		0x0080	/* Receive FIFO Service         */
-
-/* TWI_FIFO_CTRL Masks												*/
-#define	XMTFLUSH	0x0001	/* Transmit Buffer Flush                        */
-#define	RCVFLUSH	0x0002	/* Receive Buffer Flush                         */
-#define	XMTINTLEN	0x0004	/* Transmit Buffer Interrupt Length     */
-#define	RCVINTLEN	0x0008	/* Receive Buffer Interrupt Length      */
-
-/* TWI_FIFO_STAT Masks															*/
-#define	XMTSTAT		0x0003	/* Transmit FIFO Status                                                 */
-#define	XMT_EMPTY	0x0000	/*              Transmit FIFO Empty                                             */
-#define	XMT_HALF	0x0001	/*              Transmit FIFO Has 1 Byte To Write               */
-#define	XMT_FULL	0x0003	/*              Transmit FIFO Full (2 Bytes To Write)   */
-
-#define	RCVSTAT		0x000C	/* Receive FIFO Status                                                  */
-#define	RCV_EMPTY	0x0000	/*              Receive FIFO Empty                                              */
-#define	RCV_HALF	0x0004	/*              Receive FIFO Has 1 Byte To Read                 */
-#define	RCV_FULL	0x000C	/*              Receive FIFO Full (2 Bytes To Read)             */
-
 #endif
diff --git a/arch/blackfin/kernel/debug-mmrs.c b/arch/blackfin/kernel/debug-mmrs.c
index 01232a13470d..947ad0832338 100644
--- a/arch/blackfin/kernel/debug-mmrs.c
+++ b/arch/blackfin/kernel/debug-mmrs.c
@@ -10,6 +10,7 @@
 #include <linux/fs.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/i2c/bfin_twi.h>
 
 #include <asm/blackfin.h>
 #include <asm/gpio.h>
diff --git a/drivers/i2c/busses/i2c-bfin-twi.c b/drivers/i2c/busses/i2c-bfin-twi.c
index c75f0e943b32..c8976a3e03df 100644
--- a/drivers/i2c/busses/i2c-bfin-twi.c
+++ b/drivers/i2c/busses/i2c-bfin-twi.c
@@ -21,10 +21,10 @@
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
 #include <linux/delay.h>
+#include <linux/i2c/bfin_twi.h>
 
-#include <asm/blackfin.h>
-#include <asm/portmux.h>
 #include <asm/irq.h>
+#include <asm/portmux.h>
 #include <asm/bfin_twi.h>
 
 /* SMBus mode*/
diff --git a/include/linux/i2c/bfin_twi.h b/include/linux/i2c/bfin_twi.h
new file mode 100644
index 000000000000..135a4e0876ae
--- /dev/null
+++ b/include/linux/i2c/bfin_twi.h
@@ -0,0 +1,145 @@
+/*
+ * i2c-bfin-twi.h - interface to ADI TWI controller
+ *
+ * Copyright 2005-2014 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#ifndef __I2C_BFIN_TWI_H__
+#define __I2C_BFIN_TWI_H__
+
+#include <linux/types.h>
+#include <linux/i2c.h>
+
+/*
+ * ADI twi registers layout
+ */
+struct bfin_twi_regs {
+	u16 clkdiv;
+	u16 dummy1;
+	u16 control;
+	u16 dummy2;
+	u16 slave_ctl;
+	u16 dummy3;
+	u16 slave_stat;
+	u16 dummy4;
+	u16 slave_addr;
+	u16 dummy5;
+	u16 master_ctl;
+	u16 dummy6;
+	u16 master_stat;
+	u16 dummy7;
+	u16 master_addr;
+	u16 dummy8;
+	u16 int_stat;
+	u16 dummy9;
+	u16 int_mask;
+	u16 dummy10;
+	u16 fifo_ctl;
+	u16 dummy11;
+	u16 fifo_stat;
+	u16 dummy12;
+	u32 __pad[20];
+	u16 xmt_data8;
+	u16 dummy13;
+	u16 xmt_data16;
+	u16 dummy14;
+	u16 rcv_data8;
+	u16 dummy15;
+	u16 rcv_data16;
+	u16 dummy16;
+};
+
+struct bfin_twi_iface {
+	int			irq;
+	spinlock_t		lock;
+	char			read_write;
+	u8			command;
+	u8			*transPtr;
+	int			readNum;
+	int			writeNum;
+	int			cur_mode;
+	int			manual_stop;
+	int			result;
+	struct i2c_adapter	adap;
+	struct completion	complete;
+	struct i2c_msg		*pmsg;
+	int			msg_num;
+	int			cur_msg;
+	u16			saved_clkdiv;
+	u16			saved_control;
+	struct bfin_twi_regs __iomem *regs_base;
+};
+
+/*  ********************  TWO-WIRE INTERFACE (TWI) MASKS  ********************/
+/* TWI_CLKDIV Macros (Use: *pTWI_CLKDIV = CLKLOW(x)|CLKHI(y);  ) */
+#define	CLKLOW(x)	((x) & 0xFF)	/* Periods Clock Is Held Low */
+#define CLKHI(y)	(((y)&0xFF)<<0x8) /* Periods Before New Clock Low */
+
+/* TWI_PRESCALE Masks */
+#define	PRESCALE	0x007F	/* SCLKs Per Internal Time Reference (10MHz) */
+#define	TWI_ENA		0x0080	/* TWI Enable */
+#define	SCCB		0x0200	/* SCCB Compatibility Enable */
+
+/* TWI_SLAVE_CTL Masks */
+#define	SEN		0x0001	/* Slave Enable */
+#define	SADD_LEN	0x0002	/* Slave Address Length */
+#define	STDVAL		0x0004	/* Slave Transmit Data Valid */
+#define	NAK		0x0008	/* NAK Generated At Conclusion Of Transfer */
+#define	GEN		0x0010	/* General Call Address Matching Enabled */
+
+/* TWI_SLAVE_STAT Masks	*/
+#define	SDIR		0x0001	/* Slave Transfer Direction (RX/TX*) */
+#define GCALL		0x0002	/* General Call Indicator */
+
+/* TWI_MASTER_CTL Masks	*/
+#define	MEN		0x0001	/* Master Mode Enable          */
+#define	MADD_LEN	0x0002	/* Master Address Length       */
+#define	MDIR		0x0004	/* Master Transmit Direction (RX/TX*) */
+#define	FAST		0x0008	/* Use Fast Mode Timing Specs  */
+#define	STOP		0x0010	/* Issue Stop Condition        */
+#define	RSTART		0x0020	/* Repeat Start or Stop* At End Of Transfer */
+#define	DCNT		0x3FC0	/* Data Bytes To Transfer      */
+#define	SDAOVR		0x4000	/* Serial Data Override        */
+#define	SCLOVR		0x8000	/* Serial Clock Override       */
+
+/* TWI_MASTER_STAT Masks */
+#define	MPROG		0x0001	/* Master Transfer In Progress */
+#define	LOSTARB		0x0002	/* Lost Arbitration Indicator (Xfer Aborted) */
+#define	ANAK		0x0004	/* Address Not Acknowledged    */
+#define	DNAK		0x0008	/* Data Not Acknowledged       */
+#define	BUFRDERR	0x0010	/* Buffer Read Error           */
+#define	BUFWRERR	0x0020	/* Buffer Write Error          */
+#define	SDASEN		0x0040	/* Serial Data Sense           */
+#define	SCLSEN		0x0080	/* Serial Clock Sense          */
+#define	BUSBUSY		0x0100	/* Bus Busy Indicator          */
+
+/* TWI_INT_SRC and TWI_INT_ENABLE Masks	*/
+#define	SINIT		0x0001	/* Slave Transfer Initiated    */
+#define	SCOMP		0x0002	/* Slave Transfer Complete     */
+#define	SERR		0x0004	/* Slave Transfer Error        */
+#define	SOVF		0x0008	/* Slave Overflow              */
+#define	MCOMP		0x0010	/* Master Transfer Complete    */
+#define	MERR		0x0020	/* Master Transfer Error       */
+#define	XMTSERV		0x0040	/* Transmit FIFO Service       */
+#define	RCVSERV		0x0080	/* Receive FIFO Service        */
+
+/* TWI_FIFO_CTRL Masks */
+#define	XMTFLUSH	0x0001	/* Transmit Buffer Flush                 */
+#define	RCVFLUSH	0x0002	/* Receive Buffer Flush                  */
+#define	XMTINTLEN	0x0004	/* Transmit Buffer Interrupt Length      */
+#define	RCVINTLEN	0x0008	/* Receive Buffer Interrupt Length       */
+
+/* TWI_FIFO_STAT Masks */
+#define	XMTSTAT		0x0003	/* Transmit FIFO Status                  */
+#define	XMT_EMPTY	0x0000	/* Transmit FIFO Empty                   */
+#define	XMT_HALF	0x0001	/* Transmit FIFO Has 1 Byte To Write     */
+#define	XMT_FULL	0x0003	/* Transmit FIFO Full (2 Bytes To Write) */
+
+#define	RCVSTAT		0x000C	/* Receive FIFO Status                   */
+#define	RCV_EMPTY	0x0000	/* Receive FIFO Empty                    */
+#define	RCV_HALF	0x0004	/* Receive FIFO Has 1 Byte To Read       */
+#define	RCV_FULL	0x000C	/* Receive FIFO Full (2 Bytes To Read)   */
+
+#endif
-- 
cgit v1.2.3


From 9dd02e89cb920a727349f8852430fdc92cc729f4 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Date: Fri, 7 Mar 2014 16:34:24 +0000
Subject: mfd: arizona: Add support for new fratio encoding

Newer IP has an expanded encoding for the fratio bits. As the additional
used bits are unused on older IP simply expand the field to the new
size.

Signed-off-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 include/linux/mfd/arizona/registers.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mfd/arizona/registers.h b/include/linux/mfd/arizona/registers.h
index fdf3aa376eb2..3ddaa634b19d 100644
--- a/include/linux/mfd/arizona/registers.h
+++ b/include/linux/mfd/arizona/registers.h
@@ -1702,9 +1702,9 @@
 /*
  * R373 (0x175) - FLL1 Control 5
  */
-#define ARIZONA_FLL1_FRATIO_MASK                 0x0700  /* FLL1_FRATIO - [10:8] */
-#define ARIZONA_FLL1_FRATIO_SHIFT                     8  /* FLL1_FRATIO - [10:8] */
-#define ARIZONA_FLL1_FRATIO_WIDTH                     3  /* FLL1_FRATIO - [10:8] */
+#define ARIZONA_FLL1_FRATIO_MASK                 0x0F00  /* FLL1_FRATIO - [11:8] */
+#define ARIZONA_FLL1_FRATIO_SHIFT                     8  /* FLL1_FRATIO - [11:8] */
+#define ARIZONA_FLL1_FRATIO_WIDTH                     4  /* FLL1_FRATIO - [11:8] */
 #define ARIZONA_FLL1_OUTDIV_MASK                 0x000E  /* FLL1_OUTDIV - [3:1] */
 #define ARIZONA_FLL1_OUTDIV_SHIFT                     1  /* FLL1_OUTDIV - [3:1] */
 #define ARIZONA_FLL1_OUTDIV_WIDTH                     3  /* FLL1_OUTDIV - [3:1] */
-- 
cgit v1.2.3


From b424080a9e086e683ad5fdc624a7cf3c024e0c0f Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Fri, 7 Mar 2014 15:18:47 +0100
Subject: reset: Add optional resets and stubs

This patch adds device_reset_optional and (devm_)reset_control_get_optional
variants that drivers can use to indicate they can function without control
over the reset line. For those functions, stubs are added so the drivers can
be compiled with CONFIG_RESET_CONTROLLER disabled.
Also, device_reset is annotated with __must_check. Drivers ignoring the return
value should use device_reset_optional instead.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Reviewed-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Reviewed-by: Marek Vasut <marex@denx.de>
Acked-by: Wolfram Sang <wsa@the-dreams.de>
---
 include/linux/reset.h | 69 +++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 64 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/reset.h b/include/linux/reset.h
index a398025d1138..c0eda5023d74 100644
--- a/include/linux/reset.h
+++ b/include/linux/reset.h
@@ -1,21 +1,80 @@
 #ifndef _LINUX_RESET_H_
 #define _LINUX_RESET_H_
 
-#include <linux/of.h>
-
 struct device;
 struct reset_control;
 
+#ifdef CONFIG_RESET_CONTROLLER
+
 int reset_control_reset(struct reset_control *rstc);
 int reset_control_assert(struct reset_control *rstc);
 int reset_control_deassert(struct reset_control *rstc);
 
-struct reset_control *of_reset_control_get(struct device_node *node,
-					   const char *id);
 struct reset_control *reset_control_get(struct device *dev, const char *id);
 void reset_control_put(struct reset_control *rstc);
 struct reset_control *devm_reset_control_get(struct device *dev, const char *id);
 
-int device_reset(struct device *dev);
+int __must_check device_reset(struct device *dev);
+
+static inline int device_reset_optional(struct device *dev)
+{
+	return device_reset(dev);
+}
+
+static inline struct reset_control *reset_control_get_optional(
+					struct device *dev, const char *id)
+{
+	return reset_control_get(dev, id);
+}
+
+static inline struct reset_control *devm_reset_control_get_optional(
+					struct device *dev, const char *id)
+{
+	return devm_reset_control_get(dev, id);
+}
+
+#else
+
+static inline int reset_control_reset(struct reset_control *rstc)
+{
+	WARN_ON(1);
+	return 0;
+}
+
+static inline int reset_control_assert(struct reset_control *rstc)
+{
+	WARN_ON(1);
+	return 0;
+}
+
+static inline int reset_control_deassert(struct reset_control *rstc)
+{
+	WARN_ON(1);
+	return 0;
+}
+
+static inline void reset_control_put(struct reset_control *rstc)
+{
+	WARN_ON(1);
+}
+
+static inline int device_reset_optional(struct device *dev)
+{
+	return -ENOSYS;
+}
+
+static inline struct reset_control *reset_control_get_optional(
+					struct device *dev, const char *id)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline struct reset_control *devm_reset_control_get_optional(
+					struct device *dev, const char *id)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+#endif /* CONFIG_RESET_CONTROLLER */
 
 #endif
-- 
cgit v1.2.3


From cd5006db1b6b9128d1f5b0f1ad17cbced9d3841c Mon Sep 17 00:00:00 2001
From: Sachin Kamat <sachin.kamat@linaro.org>
Date: Fri, 14 Feb 2014 12:01:30 +0530
Subject: i2c: s3c2410: Trivial cleanup in header file

Commit 436d42c61c3e ("ARM: samsung: move platform_data definitions")
moved the files to the current location but forgot to remove the pointer
to its previous location. Clean it up. While at it also change the header
file protection macros appropriately.

Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 include/linux/platform_data/i2c-s3c2410.h | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/i2c-s3c2410.h b/include/linux/platform_data/i2c-s3c2410.h
index 2a50048c1c44..05af66b840b9 100644
--- a/include/linux/platform_data/i2c-s3c2410.h
+++ b/include/linux/platform_data/i2c-s3c2410.h
@@ -1,5 +1,4 @@
-/* arch/arm/plat-s3c/include/plat/iic.h
- *
+/*
  * Copyright 2004-2009 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
  *
@@ -10,8 +9,8 @@
  * published by the Free Software Foundation.
 */
 
-#ifndef __ASM_ARCH_IIC_H
-#define __ASM_ARCH_IIC_H __FILE__
+#ifndef __I2C_S3C2410_H
+#define __I2C_S3C2410_H __FILE__
 
 #define S3C_IICFLG_FILTER	(1<<0)	/* enable s3c2440 filter */
 
@@ -76,4 +75,4 @@ extern void s3c_i2c7_cfg_gpio(struct platform_device *dev);
 
 extern struct s3c2410_platform_i2c default_i2c_data;
 
-#endif /* __ASM_ARCH_IIC_H */
+#endif /* __I2C_S3C2410_H */
-- 
cgit v1.2.3


From 9b6f0c4b98171f2a354e1e461fefa90ec2baafa6 Mon Sep 17 00:00:00 2001
From: Valentina Manea <valentina.manea.m@gmail.com>
Date: Mon, 10 Mar 2014 10:36:40 +0200
Subject: usbcore: rename struct dev_state to struct usb_dev_state

Since it is needed outside usbcore and exposed in include/linux/usb.h,
it conflicts with enum dev_state in rt2x00 wireless driver.

Mark it as usb specific to avoid conflicts in the future.

Signed-off-by: Valentina Manea <valentina.manea.m@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/usbip/stub_dev.c |   4 +-
 drivers/usb/core/devio.c         | 112 +++++++++++++++++++--------------------
 drivers/usb/core/hub.c           |  12 ++---
 drivers/usb/core/hub.h           |   2 +-
 drivers/usb/core/usb.h           |   4 +-
 include/linux/usb.h              |   6 +--
 6 files changed, 70 insertions(+), 70 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/staging/usbip/stub_dev.c b/drivers/staging/usbip/stub_dev.c
index 952743c752d7..773d8ca07a00 100644
--- a/drivers/staging/usbip/stub_dev.c
+++ b/drivers/staging/usbip/stub_dev.c
@@ -395,7 +395,7 @@ static int stub_probe(struct usb_device *udev)
 	 * (struct dev_state) as long as it is unique.
 	 */
 	rc = usb_hub_claim_port(udev->parent, udev->portnum,
-			(struct dev_state *) udev);
+			(struct usb_dev_state *) udev);
 	if (rc) {
 		dev_dbg(&udev->dev, "unable to claim port\n");
 		return rc;
@@ -464,7 +464,7 @@ static void stub_disconnect(struct usb_device *udev)
 
 	/* release port */
 	rc = usb_hub_release_port(udev->parent, udev->portnum,
-				  (struct dev_state *) udev);
+				  (struct usb_dev_state *) udev);
 	if (rc) {
 		dev_dbg(&udev->dev, "unable to release port\n");
 		return;
diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c
index 90e18f6fa2bb..2a8afe6754b8 100644
--- a/drivers/usb/core/devio.c
+++ b/drivers/usb/core/devio.c
@@ -62,7 +62,7 @@
 /* Mutual exclusion for removal, open, and release */
 DEFINE_MUTEX(usbfs_mutex);
 
-struct dev_state {
+struct usb_dev_state {
 	struct list_head list;      /* state list */
 	struct usb_device *dev;
 	struct file *file;
@@ -81,7 +81,7 @@ struct dev_state {
 
 struct async {
 	struct list_head asynclist;
-	struct dev_state *ps;
+	struct usb_dev_state *ps;
 	struct pid *pid;
 	const struct cred *cred;
 	unsigned int signr;
@@ -151,7 +151,7 @@ static void usbfs_decrease_memory_usage(unsigned amount)
 	atomic_sub(amount, &usbfs_memory_usage);
 }
 
-static int connected(struct dev_state *ps)
+static int connected(struct usb_dev_state *ps)
 {
 	return (!list_empty(&ps->list) &&
 			ps->dev->state != USB_STATE_NOTATTACHED);
@@ -184,7 +184,7 @@ static loff_t usbdev_lseek(struct file *file, loff_t offset, int orig)
 static ssize_t usbdev_read(struct file *file, char __user *buf, size_t nbytes,
 			   loff_t *ppos)
 {
-	struct dev_state *ps = file->private_data;
+	struct usb_dev_state *ps = file->private_data;
 	struct usb_device *dev = ps->dev;
 	ssize_t ret = 0;
 	unsigned len;
@@ -307,7 +307,7 @@ static void free_async(struct async *as)
 
 static void async_newpending(struct async *as)
 {
-	struct dev_state *ps = as->ps;
+	struct usb_dev_state *ps = as->ps;
 	unsigned long flags;
 
 	spin_lock_irqsave(&ps->lock, flags);
@@ -317,7 +317,7 @@ static void async_newpending(struct async *as)
 
 static void async_removepending(struct async *as)
 {
-	struct dev_state *ps = as->ps;
+	struct usb_dev_state *ps = as->ps;
 	unsigned long flags;
 
 	spin_lock_irqsave(&ps->lock, flags);
@@ -325,7 +325,7 @@ static void async_removepending(struct async *as)
 	spin_unlock_irqrestore(&ps->lock, flags);
 }
 
-static struct async *async_getcompleted(struct dev_state *ps)
+static struct async *async_getcompleted(struct usb_dev_state *ps)
 {
 	unsigned long flags;
 	struct async *as = NULL;
@@ -340,7 +340,7 @@ static struct async *async_getcompleted(struct dev_state *ps)
 	return as;
 }
 
-static struct async *async_getpending(struct dev_state *ps,
+static struct async *async_getpending(struct usb_dev_state *ps,
 					     void __user *userurb)
 {
 	struct async *as;
@@ -448,7 +448,7 @@ static int copy_urb_data_to_user(u8 __user *userbuffer, struct urb *urb)
 #define AS_CONTINUATION	1
 #define AS_UNLINK	2
 
-static void cancel_bulk_urbs(struct dev_state *ps, unsigned bulk_addr)
+static void cancel_bulk_urbs(struct usb_dev_state *ps, unsigned bulk_addr)
 __releases(ps->lock)
 __acquires(ps->lock)
 {
@@ -489,7 +489,7 @@ __acquires(ps->lock)
 static void async_completed(struct urb *urb)
 {
 	struct async *as = urb->context;
-	struct dev_state *ps = as->ps;
+	struct usb_dev_state *ps = as->ps;
 	struct siginfo sinfo;
 	struct pid *pid = NULL;
 	u32 secid = 0;
@@ -529,7 +529,7 @@ static void async_completed(struct urb *urb)
 	wake_up(&ps->wait);
 }
 
-static void destroy_async(struct dev_state *ps, struct list_head *list)
+static void destroy_async(struct usb_dev_state *ps, struct list_head *list)
 {
 	struct urb *urb;
 	struct async *as;
@@ -551,7 +551,7 @@ static void destroy_async(struct dev_state *ps, struct list_head *list)
 	spin_unlock_irqrestore(&ps->lock, flags);
 }
 
-static void destroy_async_on_interface(struct dev_state *ps,
+static void destroy_async_on_interface(struct usb_dev_state *ps,
 				       unsigned int ifnum)
 {
 	struct list_head *p, *q, hitlist;
@@ -566,7 +566,7 @@ static void destroy_async_on_interface(struct dev_state *ps,
 	destroy_async(ps, &hitlist);
 }
 
-static void destroy_all_async(struct dev_state *ps)
+static void destroy_all_async(struct usb_dev_state *ps)
 {
 	destroy_async(ps, &ps->async_pending);
 }
@@ -585,7 +585,7 @@ static int driver_probe(struct usb_interface *intf,
 
 static void driver_disconnect(struct usb_interface *intf)
 {
-	struct dev_state *ps = usb_get_intfdata(intf);
+	struct usb_dev_state *ps = usb_get_intfdata(intf);
 	unsigned int ifnum = intf->altsetting->desc.bInterfaceNumber;
 
 	if (!ps)
@@ -628,7 +628,7 @@ struct usb_driver usbfs_driver = {
 	.resume =	driver_resume,
 };
 
-static int claimintf(struct dev_state *ps, unsigned int ifnum)
+static int claimintf(struct usb_dev_state *ps, unsigned int ifnum)
 {
 	struct usb_device *dev = ps->dev;
 	struct usb_interface *intf;
@@ -650,7 +650,7 @@ static int claimintf(struct dev_state *ps, unsigned int ifnum)
 	return err;
 }
 
-static int releaseintf(struct dev_state *ps, unsigned int ifnum)
+static int releaseintf(struct usb_dev_state *ps, unsigned int ifnum)
 {
 	struct usb_device *dev;
 	struct usb_interface *intf;
@@ -670,7 +670,7 @@ static int releaseintf(struct dev_state *ps, unsigned int ifnum)
 	return err;
 }
 
-static int checkintf(struct dev_state *ps, unsigned int ifnum)
+static int checkintf(struct usb_dev_state *ps, unsigned int ifnum)
 {
 	if (ps->dev->state != USB_STATE_CONFIGURED)
 		return -EHOSTUNREACH;
@@ -710,7 +710,7 @@ static int findintfep(struct usb_device *dev, unsigned int ep)
 	return -ENOENT;
 }
 
-static int check_ctrlrecip(struct dev_state *ps, unsigned int requesttype,
+static int check_ctrlrecip(struct usb_dev_state *ps, unsigned int requesttype,
 			   unsigned int request, unsigned int index)
 {
 	int ret = 0;
@@ -791,11 +791,11 @@ static struct usb_device *usbdev_lookup_by_devt(dev_t devt)
 static int usbdev_open(struct inode *inode, struct file *file)
 {
 	struct usb_device *dev = NULL;
-	struct dev_state *ps;
+	struct usb_dev_state *ps;
 	int ret;
 
 	ret = -ENOMEM;
-	ps = kmalloc(sizeof(struct dev_state), GFP_KERNEL);
+	ps = kmalloc(sizeof(struct usb_dev_state), GFP_KERNEL);
 	if (!ps)
 		goto out_free_ps;
 
@@ -852,7 +852,7 @@ static int usbdev_open(struct inode *inode, struct file *file)
 
 static int usbdev_release(struct inode *inode, struct file *file)
 {
-	struct dev_state *ps = file->private_data;
+	struct usb_dev_state *ps = file->private_data;
 	struct usb_device *dev = ps->dev;
 	unsigned int ifnum;
 	struct async *as;
@@ -883,7 +883,7 @@ static int usbdev_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static int proc_control(struct dev_state *ps, void __user *arg)
+static int proc_control(struct usb_dev_state *ps, void __user *arg)
 {
 	struct usb_device *dev = ps->dev;
 	struct usbdevfs_ctrltransfer ctrl;
@@ -970,7 +970,7 @@ static int proc_control(struct dev_state *ps, void __user *arg)
 	return ret;
 }
 
-static int proc_bulk(struct dev_state *ps, void __user *arg)
+static int proc_bulk(struct usb_dev_state *ps, void __user *arg)
 {
 	struct usb_device *dev = ps->dev;
 	struct usbdevfs_bulktransfer bulk;
@@ -1043,7 +1043,7 @@ static int proc_bulk(struct dev_state *ps, void __user *arg)
 	return ret;
 }
 
-static int proc_resetep(struct dev_state *ps, void __user *arg)
+static int proc_resetep(struct usb_dev_state *ps, void __user *arg)
 {
 	unsigned int ep;
 	int ret;
@@ -1060,7 +1060,7 @@ static int proc_resetep(struct dev_state *ps, void __user *arg)
 	return 0;
 }
 
-static int proc_clearhalt(struct dev_state *ps, void __user *arg)
+static int proc_clearhalt(struct usb_dev_state *ps, void __user *arg)
 {
 	unsigned int ep;
 	int pipe;
@@ -1082,7 +1082,7 @@ static int proc_clearhalt(struct dev_state *ps, void __user *arg)
 	return usb_clear_halt(ps->dev, pipe);
 }
 
-static int proc_getdriver(struct dev_state *ps, void __user *arg)
+static int proc_getdriver(struct usb_dev_state *ps, void __user *arg)
 {
 	struct usbdevfs_getdriver gd;
 	struct usb_interface *intf;
@@ -1101,7 +1101,7 @@ static int proc_getdriver(struct dev_state *ps, void __user *arg)
 	return ret;
 }
 
-static int proc_connectinfo(struct dev_state *ps, void __user *arg)
+static int proc_connectinfo(struct usb_dev_state *ps, void __user *arg)
 {
 	struct usbdevfs_connectinfo ci = {
 		.devnum = ps->dev->devnum,
@@ -1113,12 +1113,12 @@ static int proc_connectinfo(struct dev_state *ps, void __user *arg)
 	return 0;
 }
 
-static int proc_resetdevice(struct dev_state *ps)
+static int proc_resetdevice(struct usb_dev_state *ps)
 {
 	return usb_reset_device(ps->dev);
 }
 
-static int proc_setintf(struct dev_state *ps, void __user *arg)
+static int proc_setintf(struct usb_dev_state *ps, void __user *arg)
 {
 	struct usbdevfs_setinterface setintf;
 	int ret;
@@ -1131,7 +1131,7 @@ static int proc_setintf(struct dev_state *ps, void __user *arg)
 			setintf.altsetting);
 }
 
-static int proc_setconfig(struct dev_state *ps, void __user *arg)
+static int proc_setconfig(struct usb_dev_state *ps, void __user *arg)
 {
 	int u;
 	int status = 0;
@@ -1179,7 +1179,7 @@ static int proc_setconfig(struct dev_state *ps, void __user *arg)
 	return status;
 }
 
-static int proc_do_submiturb(struct dev_state *ps, struct usbdevfs_urb *uurb,
+static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb,
 			struct usbdevfs_iso_packet_desc __user *iso_frame_desc,
 			void __user *arg)
 {
@@ -1508,7 +1508,7 @@ static int proc_do_submiturb(struct dev_state *ps, struct usbdevfs_urb *uurb,
 	return ret;
 }
 
-static int proc_submiturb(struct dev_state *ps, void __user *arg)
+static int proc_submiturb(struct usb_dev_state *ps, void __user *arg)
 {
 	struct usbdevfs_urb uurb;
 
@@ -1520,7 +1520,7 @@ static int proc_submiturb(struct dev_state *ps, void __user *arg)
 			arg);
 }
 
-static int proc_unlinkurb(struct dev_state *ps, void __user *arg)
+static int proc_unlinkurb(struct usb_dev_state *ps, void __user *arg)
 {
 	struct urb *urb;
 	struct async *as;
@@ -1580,7 +1580,7 @@ err_out:
 	return -EFAULT;
 }
 
-static struct async *reap_as(struct dev_state *ps)
+static struct async *reap_as(struct usb_dev_state *ps)
 {
 	DECLARE_WAITQUEUE(wait, current);
 	struct async *as = NULL;
@@ -1603,7 +1603,7 @@ static struct async *reap_as(struct dev_state *ps)
 	return as;
 }
 
-static int proc_reapurb(struct dev_state *ps, void __user *arg)
+static int proc_reapurb(struct usb_dev_state *ps, void __user *arg)
 {
 	struct async *as = reap_as(ps);
 	if (as) {
@@ -1616,7 +1616,7 @@ static int proc_reapurb(struct dev_state *ps, void __user *arg)
 	return -EIO;
 }
 
-static int proc_reapurbnonblock(struct dev_state *ps, void __user *arg)
+static int proc_reapurbnonblock(struct usb_dev_state *ps, void __user *arg)
 {
 	int retval;
 	struct async *as;
@@ -1631,7 +1631,7 @@ static int proc_reapurbnonblock(struct dev_state *ps, void __user *arg)
 }
 
 #ifdef CONFIG_COMPAT
-static int proc_control_compat(struct dev_state *ps,
+static int proc_control_compat(struct usb_dev_state *ps,
 				struct usbdevfs_ctrltransfer32 __user *p32)
 {
 	struct usbdevfs_ctrltransfer __user *p;
@@ -1644,7 +1644,7 @@ static int proc_control_compat(struct dev_state *ps,
 	return proc_control(ps, p);
 }
 
-static int proc_bulk_compat(struct dev_state *ps,
+static int proc_bulk_compat(struct usb_dev_state *ps,
 			struct usbdevfs_bulktransfer32 __user *p32)
 {
 	struct usbdevfs_bulktransfer __user *p;
@@ -1661,7 +1661,7 @@ static int proc_bulk_compat(struct dev_state *ps,
 
 	return proc_bulk(ps, p);
 }
-static int proc_disconnectsignal_compat(struct dev_state *ps, void __user *arg)
+static int proc_disconnectsignal_compat(struct usb_dev_state *ps, void __user *arg)
 {
 	struct usbdevfs_disconnectsignal32 ds;
 
@@ -1699,7 +1699,7 @@ static int get_urb32(struct usbdevfs_urb *kurb,
 	return 0;
 }
 
-static int proc_submiturb_compat(struct dev_state *ps, void __user *arg)
+static int proc_submiturb_compat(struct usb_dev_state *ps, void __user *arg)
 {
 	struct usbdevfs_urb uurb;
 
@@ -1745,7 +1745,7 @@ static int processcompl_compat(struct async *as, void __user * __user *arg)
 	return 0;
 }
 
-static int proc_reapurb_compat(struct dev_state *ps, void __user *arg)
+static int proc_reapurb_compat(struct usb_dev_state *ps, void __user *arg)
 {
 	struct async *as = reap_as(ps);
 	if (as) {
@@ -1758,7 +1758,7 @@ static int proc_reapurb_compat(struct dev_state *ps, void __user *arg)
 	return -EIO;
 }
 
-static int proc_reapurbnonblock_compat(struct dev_state *ps, void __user *arg)
+static int proc_reapurbnonblock_compat(struct usb_dev_state *ps, void __user *arg)
 {
 	int retval;
 	struct async *as;
@@ -1775,7 +1775,7 @@ static int proc_reapurbnonblock_compat(struct dev_state *ps, void __user *arg)
 
 #endif
 
-static int proc_disconnectsignal(struct dev_state *ps, void __user *arg)
+static int proc_disconnectsignal(struct usb_dev_state *ps, void __user *arg)
 {
 	struct usbdevfs_disconnectsignal ds;
 
@@ -1786,7 +1786,7 @@ static int proc_disconnectsignal(struct dev_state *ps, void __user *arg)
 	return 0;
 }
 
-static int proc_claiminterface(struct dev_state *ps, void __user *arg)
+static int proc_claiminterface(struct usb_dev_state *ps, void __user *arg)
 {
 	unsigned int ifnum;
 
@@ -1795,7 +1795,7 @@ static int proc_claiminterface(struct dev_state *ps, void __user *arg)
 	return claimintf(ps, ifnum);
 }
 
-static int proc_releaseinterface(struct dev_state *ps, void __user *arg)
+static int proc_releaseinterface(struct usb_dev_state *ps, void __user *arg)
 {
 	unsigned int ifnum;
 	int ret;
@@ -1808,7 +1808,7 @@ static int proc_releaseinterface(struct dev_state *ps, void __user *arg)
 	return 0;
 }
 
-static int proc_ioctl(struct dev_state *ps, struct usbdevfs_ioctl *ctl)
+static int proc_ioctl(struct usb_dev_state *ps, struct usbdevfs_ioctl *ctl)
 {
 	int			size;
 	void			*buf = NULL;
@@ -1884,7 +1884,7 @@ static int proc_ioctl(struct dev_state *ps, struct usbdevfs_ioctl *ctl)
 	return retval;
 }
 
-static int proc_ioctl_default(struct dev_state *ps, void __user *arg)
+static int proc_ioctl_default(struct usb_dev_state *ps, void __user *arg)
 {
 	struct usbdevfs_ioctl	ctrl;
 
@@ -1894,7 +1894,7 @@ static int proc_ioctl_default(struct dev_state *ps, void __user *arg)
 }
 
 #ifdef CONFIG_COMPAT
-static int proc_ioctl_compat(struct dev_state *ps, compat_uptr_t arg)
+static int proc_ioctl_compat(struct usb_dev_state *ps, compat_uptr_t arg)
 {
 	struct usbdevfs_ioctl32 __user *uioc;
 	struct usbdevfs_ioctl ctrl;
@@ -1912,7 +1912,7 @@ static int proc_ioctl_compat(struct dev_state *ps, compat_uptr_t arg)
 }
 #endif
 
-static int proc_claim_port(struct dev_state *ps, void __user *arg)
+static int proc_claim_port(struct usb_dev_state *ps, void __user *arg)
 {
 	unsigned portnum;
 	int rc;
@@ -1926,7 +1926,7 @@ static int proc_claim_port(struct dev_state *ps, void __user *arg)
 	return rc;
 }
 
-static int proc_release_port(struct dev_state *ps, void __user *arg)
+static int proc_release_port(struct usb_dev_state *ps, void __user *arg)
 {
 	unsigned portnum;
 
@@ -1935,7 +1935,7 @@ static int proc_release_port(struct dev_state *ps, void __user *arg)
 	return usb_hub_release_port(ps->dev, portnum, ps);
 }
 
-static int proc_get_capabilities(struct dev_state *ps, void __user *arg)
+static int proc_get_capabilities(struct usb_dev_state *ps, void __user *arg)
 {
 	__u32 caps;
 
@@ -1951,7 +1951,7 @@ static int proc_get_capabilities(struct dev_state *ps, void __user *arg)
 	return 0;
 }
 
-static int proc_disconnect_claim(struct dev_state *ps, void __user *arg)
+static int proc_disconnect_claim(struct usb_dev_state *ps, void __user *arg)
 {
 	struct usbdevfs_disconnect_claim dc;
 	struct usb_interface *intf;
@@ -1991,7 +1991,7 @@ static int proc_disconnect_claim(struct dev_state *ps, void __user *arg)
 static long usbdev_do_ioctl(struct file *file, unsigned int cmd,
 				void __user *p)
 {
-	struct dev_state *ps = file->private_data;
+	struct usb_dev_state *ps = file->private_data;
 	struct inode *inode = file_inode(file);
 	struct usb_device *dev = ps->dev;
 	int ret = -ENOTTY;
@@ -2192,7 +2192,7 @@ static long usbdev_compat_ioctl(struct file *file, unsigned int cmd,
 static unsigned int usbdev_poll(struct file *file,
 				struct poll_table_struct *wait)
 {
-	struct dev_state *ps = file->private_data;
+	struct usb_dev_state *ps = file->private_data;
 	unsigned int mask = 0;
 
 	poll_wait(file, &ps->wait, wait);
@@ -2218,11 +2218,11 @@ const struct file_operations usbdev_file_operations = {
 
 static void usbdev_remove(struct usb_device *udev)
 {
-	struct dev_state *ps;
+	struct usb_dev_state *ps;
 	struct siginfo sinfo;
 
 	while (!list_empty(&udev->filelist)) {
-		ps = list_entry(udev->filelist.next, struct dev_state, list);
+		ps = list_entry(udev->filelist.next, struct usb_dev_state, list);
 		destroy_all_async(ps);
 		wake_up_all(&ps->wait);
 		list_del_init(&ps->list);
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index e4849333c8de..be6e02e91f56 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -1788,7 +1788,7 @@ hub_ioctl(struct usb_interface *intf, unsigned int code, void *user_data)
  * to one of these "claimed" ports, the program will "own" the device.
  */
 static int find_port_owner(struct usb_device *hdev, unsigned port1,
-		struct dev_state ***ppowner)
+		struct usb_dev_state ***ppowner)
 {
 	struct usb_hub *hub = usb_hub_to_struct_hub(hdev);
 
@@ -1806,10 +1806,10 @@ static int find_port_owner(struct usb_device *hdev, unsigned port1,
 
 /* In the following three functions, the caller must hold hdev's lock */
 int usb_hub_claim_port(struct usb_device *hdev, unsigned port1,
-		       struct dev_state *owner)
+		       struct usb_dev_state *owner)
 {
 	int rc;
-	struct dev_state **powner;
+	struct usb_dev_state **powner;
 
 	rc = find_port_owner(hdev, port1, &powner);
 	if (rc)
@@ -1822,10 +1822,10 @@ int usb_hub_claim_port(struct usb_device *hdev, unsigned port1,
 EXPORT_SYMBOL_GPL(usb_hub_claim_port);
 
 int usb_hub_release_port(struct usb_device *hdev, unsigned port1,
-			 struct dev_state *owner)
+			 struct usb_dev_state *owner)
 {
 	int rc;
-	struct dev_state **powner;
+	struct usb_dev_state **powner;
 
 	rc = find_port_owner(hdev, port1, &powner);
 	if (rc)
@@ -1837,7 +1837,7 @@ int usb_hub_release_port(struct usb_device *hdev, unsigned port1,
 }
 EXPORT_SYMBOL_GPL(usb_hub_release_port);
 
-void usb_hub_release_all_ports(struct usb_device *hdev, struct dev_state *owner)
+void usb_hub_release_all_ports(struct usb_device *hdev, struct usb_dev_state *owner)
 {
 	struct usb_hub *hub = usb_hub_to_struct_hub(hdev);
 	int n;
diff --git a/drivers/usb/core/hub.h b/drivers/usb/core/hub.h
index df629a310e44..33bcb2c6f90a 100644
--- a/drivers/usb/core/hub.h
+++ b/drivers/usb/core/hub.h
@@ -89,7 +89,7 @@ struct usb_hub {
 struct usb_port {
 	struct usb_device *child;
 	struct device dev;
-	struct dev_state *port_owner;
+	struct usb_dev_state *port_owner;
 	enum usb_port_connect_type connect_type;
 	u8 portnum;
 	unsigned power_is_on:1;
diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h
index 222bbd2618f1..a87532845bf9 100644
--- a/drivers/usb/core/usb.h
+++ b/drivers/usb/core/usb.h
@@ -2,7 +2,7 @@
 #include <linux/acpi.h>
 
 struct usb_hub_descriptor;
-struct dev_state;
+struct usb_dev_state;
 
 /* Functions local to drivers/usb/core/ */
 
@@ -58,7 +58,7 @@ extern void usb_forced_unbind_intf(struct usb_interface *intf);
 extern void usb_rebind_intf(struct usb_interface *intf);
 
 extern void usb_hub_release_all_ports(struct usb_device *hdev,
-		struct dev_state *owner);
+		struct usb_dev_state *owner);
 extern bool usb_device_is_owned(struct usb_device *udev);
 
 extern int  usb_hub_init(void);
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 140a6a3e7d56..b55600a1edc3 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -366,7 +366,7 @@ struct usb_bus {
 #endif
 };
 
-struct dev_state;
+struct usb_dev_state;
 
 /* ----------------------------------------------------------------------- */
 
@@ -753,9 +753,9 @@ extern struct usb_host_interface *usb_find_alt_setting(
 
 /* port claiming functions */
 int usb_hub_claim_port(struct usb_device *hdev, unsigned port1,
-		struct dev_state *owner);
+		struct usb_dev_state *owner);
 int usb_hub_release_port(struct usb_device *hdev, unsigned port1,
-		struct dev_state *owner);
+		struct usb_dev_state *owner);
 
 /**
  * usb_make_path - returns stable device path in the usb tree
-- 
cgit v1.2.3


From e894c3f46c302716d2f156b1f3339e2f96ceb65c Mon Sep 17 00:00:00 2001
From: "Opensource [Anthony Olech]" <anthony.olech.opensource@diasemi.com>
Date: Tue, 4 Mar 2014 13:54:02 +0000
Subject: regmap: Implementation for regmap_multi_reg_write

This is the implementation of regmap_multi_reg_write()

There is a new capability 'can_multi_write' that device drivers
must set in order to use this multi reg write mode.

This replaces the first definition, which just defined the API.

Signed-off-by: Anthony Olech <anthony.olech.opensource@diasemi.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/base/regmap/internal.h |   2 +
 drivers/base/regmap/regmap.c   | 188 +++++++++++++++++++++++++++++++++++++----
 include/linux/regmap.h         |   4 +
 3 files changed, 178 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index 33414b1de201..7d1326985bee 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -134,6 +134,8 @@ struct regmap {
 
 	/* if set, converts bulk rw to single rw */
 	bool use_single_rw;
+	/* if set, the device supports multi write mode */
+	bool can_multi_write;
 
 	struct rb_root range_tree;
 	void *selector_work_buf;	/* Scratch buffer used for selector */
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 35ab7baffcc5..c69bbc06dfbb 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -439,6 +439,7 @@ struct regmap *regmap_init(struct device *dev,
 	else
 		map->reg_stride = 1;
 	map->use_single_rw = config->use_single_rw;
+	map->can_multi_write = config->can_multi_write;
 	map->dev = dev;
 	map->bus = bus;
 	map->bus_context = bus_context;
@@ -1576,41 +1577,196 @@ out:
 }
 EXPORT_SYMBOL_GPL(regmap_bulk_write);
 
+/*
+ * _regmap_raw_multi_reg_write()
+ *
+ * the (register,newvalue) pairs in regs have not been formatted, but
+ * they are all in the same page and have been changed to being page
+ * relative. The page register has been written if that was neccessary.
+ */
+static int _regmap_raw_multi_reg_write(struct regmap *map,
+				       const struct reg_default *regs,
+				       size_t num_regs)
+{
+	int ret;
+	void *buf;
+	int i;
+	u8 *u8;
+	size_t val_bytes = map->format.val_bytes;
+	size_t reg_bytes = map->format.reg_bytes;
+	size_t pad_bytes = map->format.pad_bytes;
+	size_t pair_size = reg_bytes + pad_bytes + val_bytes;
+	size_t len = pair_size * num_regs;
+
+	buf = kzalloc(len, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	/* We have to linearise by hand. */
+
+	u8 = buf;
+
+	for (i = 0; i < num_regs; i++) {
+		int reg = regs[i].reg;
+		int val = regs[i].def;
+		trace_regmap_hw_write_start(map->dev, reg, 1);
+		map->format.format_reg(u8, reg, map->reg_shift);
+		u8 += reg_bytes + pad_bytes;
+		map->format.format_val(u8, val, 0);
+		u8 += val_bytes;
+	}
+	u8 = buf;
+	*u8 |= map->write_flag_mask;
+
+	ret = map->bus->write(map->bus_context, buf, len);
+
+	kfree(buf);
+
+	for (i = 0; i < num_regs; i++) {
+		int reg = regs[i].reg;
+		trace_regmap_hw_write_done(map->dev, reg, 1);
+	}
+	return ret;
+}
+
+static unsigned int _regmap_register_page(struct regmap *map,
+					  unsigned int reg,
+					  struct regmap_range_node *range)
+{
+	unsigned int win_page = (reg - range->range_min) / range->window_len;
+
+	return win_page;
+}
+
+static int _regmap_range_multi_paged_reg_write(struct regmap *map,
+					       struct reg_default *regs,
+					       size_t num_regs)
+{
+	int ret;
+	int i, n;
+	struct reg_default *base;
+	unsigned int this_page;
+	/*
+	 * the set of registers are not neccessarily in order, but
+	 * since the order of write must be preserved this algorithm
+	 * chops the set each time the page changes
+	 */
+	base = regs;
+	for (i = 0, n = 0; i < num_regs; i++, n++) {
+		unsigned int reg = regs[i].reg;
+		struct regmap_range_node *range;
+
+		range = _regmap_range_lookup(map, reg);
+		if (range) {
+			unsigned int win_page = _regmap_register_page(map, reg,
+								      range);
+
+			if (i == 0)
+				this_page = win_page;
+			if (win_page != this_page) {
+				this_page = win_page;
+				ret = _regmap_raw_multi_reg_write(map, base, n);
+				if (ret != 0)
+					return ret;
+				base += n;
+				n = 0;
+			}
+			ret = _regmap_select_page(map, &base[n].reg, range, 1);
+			if (ret != 0)
+				return ret;
+		}
+	}
+	if (n > 0)
+		return _regmap_raw_multi_reg_write(map, base, n);
+	return 0;
+}
+
 static int _regmap_multi_reg_write(struct regmap *map,
 				   const struct reg_default *regs,
-				   int num_regs)
+				   size_t num_regs)
 {
-	int i, ret;
+	int i;
+	int ret;
+
+	if (!map->can_multi_write) {
+		for (i = 0; i < num_regs; i++) {
+			ret = _regmap_write(map, regs[i].reg, regs[i].def);
+			if (ret != 0)
+				return ret;
+		}
+		return 0;
+	}
+
+	if (!map->format.parse_inplace)
+		return -EINVAL;
+
+	if (map->writeable_reg)
+		for (i = 0; i < num_regs; i++) {
+			int reg = regs[i].reg;
+			if (!map->writeable_reg(map->dev, reg))
+				return -EINVAL;
+			if (reg % map->reg_stride)
+				return -EINVAL;
+		}
+
+	if (!map->cache_bypass) {
+		for (i = 0; i < num_regs; i++) {
+			unsigned int val = regs[i].def;
+			unsigned int reg = regs[i].reg;
+			ret = regcache_write(map, reg, val);
+			if (ret) {
+				dev_err(map->dev,
+				"Error in caching of register: %x ret: %d\n",
+								reg, ret);
+				return ret;
+			}
+		}
+		if (map->cache_only) {
+			map->cache_dirty = true;
+			return 0;
+		}
+	}
+
+	WARN_ON(!map->bus);
 
 	for (i = 0; i < num_regs; i++) {
-		if (regs[i].reg % map->reg_stride)
-			return -EINVAL;
-		ret = _regmap_write(map, regs[i].reg, regs[i].def);
-		if (ret != 0) {
-			dev_err(map->dev, "Failed to write %x = %x: %d\n",
-				regs[i].reg, regs[i].def, ret);
+		unsigned int reg = regs[i].reg;
+		struct regmap_range_node *range;
+		range = _regmap_range_lookup(map, reg);
+		if (range) {
+			size_t len = sizeof(struct reg_default)*num_regs;
+			struct reg_default *base = kmemdup(regs, len,
+							   GFP_KERNEL);
+			if (!base)
+				return -ENOMEM;
+			ret = _regmap_range_multi_paged_reg_write(map, base,
+								  num_regs);
+			kfree(base);
+
 			return ret;
 		}
 	}
-
-	return 0;
+	return _regmap_raw_multi_reg_write(map, regs, num_regs);
 }
 
 /*
  * regmap_multi_reg_write(): Write multiple registers to the device
  *
- * where the set of register are supplied in any order
+ * where the set of register,value pairs are supplied in any order,
+ * possibly not all in a single range.
  *
  * @map: Register map to write to
  * @regs: Array of structures containing register,value to be written
  * @num_regs: Number of registers to write
  *
- * This function is intended to be used for writing a large block of data
- * atomically to the device in single transfer for those I2C client devices
- * that implement this alternative block write mode.
+ * The 'normal' block write mode will send ultimately send data on the
+ * target bus as R,V1,V2,V3,..,Vn where successively higer registers are
+ * addressed. However, this alternative block multi write mode will send
+ * the data as R1,V1,R2,V2,..,Rn,Vn on the target bus. The target device
+ * must of course support the mode.
  *
- * A value of zero will be returned on success, a negative errno will
- * be returned in error cases.
+ * A value of zero will be returned on success, a negative errno will be
+ * returned in error cases.
  */
 int regmap_multi_reg_write(struct regmap *map, const struct reg_default *regs,
 			   int num_regs)
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index ca2272fbd014..220aec660064 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -164,6 +164,9 @@ typedef void (*regmap_unlock)(void *);
  * @use_single_rw: If set, converts the bulk read and write operations into
  *		    a series of single read and write operations. This is useful
  *		    for device that does not support bulk read and write.
+ * @can_multi_write: If set, the device supports the multi write mode of bulk
+ *                   write operations, if clear multi write requests will be
+ *                   split into individual write operations
  *
  * @cache_type: The actual cache type.
  * @reg_defaults_raw: Power on reset values for registers (for use with
@@ -215,6 +218,7 @@ struct regmap_config {
 	u8 write_flag_mask;
 
 	bool use_single_rw;
+	bool can_multi_write;
 
 	enum regmap_endian reg_format_endian;
 	enum regmap_endian val_format_endian;
-- 
cgit v1.2.3


From f02ea4e6a47d50a38f5baadbe87f5087dd337db0 Mon Sep 17 00:00:00 2001
From: Huang Shijie <b32955@freescale.com>
Date: Mon, 13 Jan 2014 14:27:12 +0800
Subject: mtd: nand: kill the the NAND_MAX_PAGESIZE/NAND_MAX_OOBSIZE for
 nand_buffers{}

The patch converts the arrays to buffer pointers for nand_buffers{}.

The cafe_nand.c is the only NAND_OWN_BUFFERS user which allocates
nand_buffers{} itself.

This patch disables the DMA for nand_scan_ident, and restores the DMA
status after we finish the nand_scan_ident. This way, we can get page
size and OOB size and use them to allocate cafe->dmabuf.

Since the cafe_nand.c uses the NAND_ECC_HW_SYNDROME ECC mode, we do not
allocate the buffers for @ecccalc and @ecccode.

Signed-off-by: Huang Shijie <b32955@freescale.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 drivers/mtd/nand/cafe_nand.c | 68 ++++++++++++++++++++++++++++++--------------
 drivers/mtd/nand/nand_base.c | 19 ++++++++++---
 include/linux/mtd/nand.h     | 12 ++++----
 3 files changed, 67 insertions(+), 32 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/cafe_nand.c b/drivers/mtd/nand/cafe_nand.c
index f2f64addb5e8..4e66726da9aa 100644
--- a/drivers/mtd/nand/cafe_nand.c
+++ b/drivers/mtd/nand/cafe_nand.c
@@ -627,6 +627,8 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 	struct cafe_priv *cafe;
 	uint32_t ctrl;
 	int err = 0;
+	int old_dma;
+	struct nand_buffers *nbuf;
 
 	/* Very old versions shared the same PCI ident for all three
 	   functions on the chip. Verify the class too... */
@@ -655,13 +657,6 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 		err = -ENOMEM;
 		goto out_free_mtd;
 	}
-	cafe->dmabuf = dma_alloc_coherent(&cafe->pdev->dev, 2112 + sizeof(struct nand_buffers),
-					  &cafe->dmaaddr, GFP_KERNEL);
-	if (!cafe->dmabuf) {
-		err = -ENOMEM;
-		goto out_ior;
-	}
-	cafe->nand.buffers = (void *)cafe->dmabuf + 2112;
 
 	cafe->rs = init_rs_non_canonical(12, &cafe_mul, 0, 1, 8);
 	if (!cafe->rs) {
@@ -721,7 +716,7 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 			  "CAFE NAND", mtd);
 	if (err) {
 		dev_warn(&pdev->dev, "Could not register IRQ %d\n", pdev->irq);
-		goto out_free_dma;
+		goto out_ior;
 	}
 
 	/* Disable master reset, enable NAND clock */
@@ -735,6 +730,32 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 	cafe_writel(cafe, 0x7006, GLOBAL_CTRL);
 	cafe_writel(cafe, 0x700a, GLOBAL_CTRL);
 
+	/* Enable NAND IRQ in global IRQ mask register */
+	cafe_writel(cafe, 0x80000007, GLOBAL_IRQ_MASK);
+	cafe_dev_dbg(&cafe->pdev->dev, "Control %x, IRQ mask %x\n",
+		cafe_readl(cafe, GLOBAL_CTRL),
+		cafe_readl(cafe, GLOBAL_IRQ_MASK));
+
+	/* Do not use the DMA for the nand_scan_ident() */
+	old_dma = usedma;
+	usedma = 0;
+
+	/* Scan to find existence of the device */
+	if (nand_scan_ident(mtd, 2, NULL)) {
+		err = -ENXIO;
+		goto out_irq;
+	}
+
+	cafe->dmabuf = dma_alloc_coherent(&cafe->pdev->dev,
+				2112 + sizeof(struct nand_buffers) +
+				mtd->writesize + mtd->oobsize,
+				&cafe->dmaaddr, GFP_KERNEL);
+	if (!cafe->dmabuf) {
+		err = -ENOMEM;
+		goto out_irq;
+	}
+	cafe->nand.buffers = nbuf = (void *)cafe->dmabuf + 2112;
+
 	/* Set up DMA address */
 	cafe_writel(cafe, cafe->dmaaddr & 0xffffffff, NAND_DMA_ADDR0);
 	if (sizeof(cafe->dmaaddr) > 4)
@@ -746,16 +767,13 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 	cafe_dev_dbg(&cafe->pdev->dev, "Set DMA address to %x (virt %p)\n",
 		cafe_readl(cafe, NAND_DMA_ADDR0), cafe->dmabuf);
 
-	/* Enable NAND IRQ in global IRQ mask register */
-	cafe_writel(cafe, 0x80000007, GLOBAL_IRQ_MASK);
-	cafe_dev_dbg(&cafe->pdev->dev, "Control %x, IRQ mask %x\n",
-		cafe_readl(cafe, GLOBAL_CTRL), cafe_readl(cafe, GLOBAL_IRQ_MASK));
+	/* this driver does not need the @ecccalc and @ecccode */
+	nbuf->ecccalc = NULL;
+	nbuf->ecccode = NULL;
+	nbuf->databuf = (uint8_t *)(nbuf + 1);
 
-	/* Scan to find existence of the device */
-	if (nand_scan_ident(mtd, 2, NULL)) {
-		err = -ENXIO;
-		goto out_irq;
-	}
+	/* Restore the DMA flag */
+	usedma = old_dma;
 
 	cafe->ctl2 = 1<<27; /* Reed-Solomon ECC */
 	if (mtd->writesize == 2048)
@@ -773,7 +791,7 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 	} else {
 		printk(KERN_WARNING "Unexpected NAND flash writesize %d. Aborting\n",
 		       mtd->writesize);
-		goto out_irq;
+		goto out_free_dma;
 	}
 	cafe->nand.ecc.mode = NAND_ECC_HW_SYNDROME;
 	cafe->nand.ecc.size = mtd->writesize;
@@ -790,7 +808,7 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 
 	err = nand_scan_tail(mtd);
 	if (err)
-		goto out_irq;
+		goto out_free_dma;
 
 	pci_set_drvdata(pdev, mtd);
 
@@ -799,12 +817,15 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 
 	goto out;
 
+ out_free_dma:
+	dma_free_coherent(&cafe->pdev->dev,
+			2112 + sizeof(struct nand_buffers) +
+			mtd->writesize + mtd->oobsize,
+			cafe->dmabuf, cafe->dmaaddr);
  out_irq:
 	/* Disable NAND IRQ in global IRQ mask register */
 	cafe_writel(cafe, ~1 & cafe_readl(cafe, GLOBAL_IRQ_MASK), GLOBAL_IRQ_MASK);
 	free_irq(pdev->irq, mtd);
- out_free_dma:
-	dma_free_coherent(&cafe->pdev->dev, 2112, cafe->dmabuf, cafe->dmaaddr);
  out_ior:
 	pci_iounmap(pdev, cafe->mmio);
  out_free_mtd:
@@ -824,7 +845,10 @@ static void cafe_nand_remove(struct pci_dev *pdev)
 	nand_release(mtd);
 	free_rs(cafe->rs);
 	pci_iounmap(pdev, cafe->mmio);
-	dma_free_coherent(&cafe->pdev->dev, 2112, cafe->dmabuf, cafe->dmaaddr);
+	dma_free_coherent(&cafe->pdev->dev,
+			2112 + sizeof(struct nand_buffers) +
+			mtd->writesize + mtd->oobsize,
+			cafe->dmabuf, cafe->dmaaddr);
 	kfree(mtd);
 }
 
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 9715a7ba164a..deeaa1cc4a85 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -3696,15 +3696,26 @@ int nand_scan_tail(struct mtd_info *mtd)
 	int i;
 	struct nand_chip *chip = mtd->priv;
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
+	struct nand_buffers *nbuf;
 
 	/* New bad blocks should be marked in OOB, flash-based BBT, or both */
 	BUG_ON((chip->bbt_options & NAND_BBT_NO_OOB_BBM) &&
 			!(chip->bbt_options & NAND_BBT_USE_FLASH));
 
-	if (!(chip->options & NAND_OWN_BUFFERS))
-		chip->buffers = kmalloc(sizeof(*chip->buffers), GFP_KERNEL);
-	if (!chip->buffers)
-		return -ENOMEM;
+	if (!(chip->options & NAND_OWN_BUFFERS)) {
+		nbuf = kzalloc(sizeof(*nbuf) + mtd->writesize
+				+ mtd->oobsize * 3, GFP_KERNEL);
+		if (!nbuf)
+			return -ENOMEM;
+		nbuf->ecccalc = (uint8_t *)(nbuf + 1);
+		nbuf->ecccode = nbuf->ecccalc + mtd->oobsize;
+		nbuf->databuf = nbuf->ecccode + mtd->oobsize;
+
+		chip->buffers = nbuf;
+	} else {
+		if (!chip->buffers)
+			return -ENOMEM;
+	}
 
 	/* Set the internal oob buffer location, just after the page data */
 	chip->oob_poi = chip->buffers->databuf + mtd->writesize;
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 32f8612469d8..520ebca11f5d 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -435,17 +435,17 @@ struct nand_ecc_ctrl {
 
 /**
  * struct nand_buffers - buffer structure for read/write
- * @ecccalc:	buffer for calculated ECC
- * @ecccode:	buffer for ECC read from flash
- * @databuf:	buffer for data - dynamically sized
+ * @ecccalc:	buffer pointer for calculated ECC, size is oobsize.
+ * @ecccode:	buffer pointer for ECC read from flash, size is oobsize.
+ * @databuf:	buffer pointer for data, size is (page size + oobsize).
  *
  * Do not change the order of buffers. databuf and oobrbuf must be in
  * consecutive order.
  */
 struct nand_buffers {
-	uint8_t	ecccalc[NAND_MAX_OOBSIZE];
-	uint8_t	ecccode[NAND_MAX_OOBSIZE];
-	uint8_t databuf[NAND_MAX_PAGESIZE + NAND_MAX_OOBSIZE];
+	uint8_t	*ecccalc;
+	uint8_t	*ecccode;
+	uint8_t *databuf;
 };
 
 /**
-- 
cgit v1.2.3


From 3f172cbdfbb799e35cc972fc9f7e43d0e971577b Mon Sep 17 00:00:00 2001
From: Huang Shijie <shijie8@gmail.com>
Date: Sat, 21 Dec 2013 00:02:30 +0800
Subject: mtd: nand: remove the NAND_MAX_PAGESIZE/NAND_MAX_OOBSIZE

There is no reference to these two macros now.
Just remove them.

Signed-off-by: Huang Shijie <shijie8@gmail.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 include/linux/mtd/nand.h | 8 --------
 1 file changed, 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 520ebca11f5d..a719686c9cce 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -51,14 +51,6 @@ extern int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len);
 /* The maximum number of NAND chips in an array */
 #define NAND_MAX_CHIPS		8
 
-/*
- * This constant declares the max. oobsize / page, which
- * is supported now. If you add a chip with bigger oobsize/page
- * adjust this accordingly.
- */
-#define NAND_MAX_OOBSIZE	744
-#define NAND_MAX_PAGESIZE	8192
-
 /*
  * Constants for hardware specific CLE/ALE/NCE function
  *
-- 
cgit v1.2.3


From 3dad2344e92c6e1aeae42df1c4824f307c51bcc7 Mon Sep 17 00:00:00 2001
From: Brian Norris <computersforpeace@gmail.com>
Date: Wed, 29 Jan 2014 14:08:12 -0800
Subject: mtd: nand: force NAND_CMD_READID onto 8-bit bus

The NAND command helpers tend to automatically shift the column address
for x16 bus devices, since most commands expect a word address, not a
byte address. The Read ID command, however, expects an 8-bit address
(i.e., 0x00, 0x20, or 0x40 should not be translated to 0x00, 0x10, or
0x20).

This fixes the column address for a few drivers which imitate the
nand_base defaults. Note that I don't touch sh_flctl.c, since it already
handles this problem slightly differently (note its comment "READID is
always performed using an 8-bit bus").

I have not tested this patch, as I only have x8 parts up for testing at
this point. Hopefully that can change soon...

Signed-off-by: Brian Norris <computersforpeace@gmail.com>
Tested-by: Ezequiel Garcia <ezequiel.garcia@free-electrons.com>
Tested-By: Pekon Gupta <pekon@ti.com>
---
 drivers/mtd/nand/atmel_nand.c  | 11 ++++++-----
 drivers/mtd/nand/au1550nd.c    |  3 ++-
 drivers/mtd/nand/diskonchip.c  |  3 ++-
 drivers/mtd/nand/nand_base.c   |  6 ++++--
 drivers/mtd/nand/nuc900_nand.c |  3 ++-
 include/linux/mtd/nand.h       | 10 ++++++++++
 6 files changed, 26 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/atmel_nand.c b/drivers/mtd/nand/atmel_nand.c
index c36e9b84487c..1955389c8fa6 100644
--- a/drivers/mtd/nand/atmel_nand.c
+++ b/drivers/mtd/nand/atmel_nand.c
@@ -1659,8 +1659,8 @@ static void nfc_select_chip(struct mtd_info *mtd, int chip)
 		nfc_writel(host->nfc->hsmc_regs, CTRL, NFC_CTRL_ENABLE);
 }
 
-static int nfc_make_addr(struct mtd_info *mtd, int column, int page_addr,
-		unsigned int *addr1234, unsigned int *cycle0)
+static int nfc_make_addr(struct mtd_info *mtd, int command, int column,
+		int page_addr, unsigned int *addr1234, unsigned int *cycle0)
 {
 	struct nand_chip *chip = mtd->priv;
 
@@ -1674,7 +1674,8 @@ static int nfc_make_addr(struct mtd_info *mtd, int column, int page_addr,
 	*addr1234 = 0;
 
 	if (column != -1) {
-		if (chip->options & NAND_BUSWIDTH_16)
+		if (chip->options & NAND_BUSWIDTH_16 &&
+				!nand_opcode_8bits(command))
 			column >>= 1;
 		addr_bytes[acycle++] = column & 0xff;
 		if (mtd->writesize > 512)
@@ -1787,8 +1788,8 @@ static void nfc_nand_command(struct mtd_info *mtd, unsigned int command,
 	}
 
 	if (do_addr)
-		acycle = nfc_make_addr(mtd, column, page_addr, &addr1234,
-				&cycle0);
+		acycle = nfc_make_addr(mtd, command, column, page_addr,
+				&addr1234, &cycle0);
 
 	nfc_addr_cmd = cmd1 | cmd2 | vcmd2 | acycle | csid | dataen | nfcwr;
 	nfc_send_command(host, nfc_addr_cmd, addr1234, cycle0);
diff --git a/drivers/mtd/nand/au1550nd.c b/drivers/mtd/nand/au1550nd.c
index 7d84c4e4bf43..bc5c518828d2 100644
--- a/drivers/mtd/nand/au1550nd.c
+++ b/drivers/mtd/nand/au1550nd.c
@@ -307,7 +307,8 @@ static void au1550_command(struct mtd_info *mtd, unsigned command, int column, i
 		/* Serially input address */
 		if (column != -1) {
 			/* Adjust columns for 16 bit buswidth */
-			if (this->options & NAND_BUSWIDTH_16)
+			if (this->options & NAND_BUSWIDTH_16 &&
+					!nand_opcode_8bits(command))
 				column >>= 1;
 			ctx->write_byte(mtd, column);
 		}
diff --git a/drivers/mtd/nand/diskonchip.c b/drivers/mtd/nand/diskonchip.c
index fec31d71b84e..b9b4db607850 100644
--- a/drivers/mtd/nand/diskonchip.c
+++ b/drivers/mtd/nand/diskonchip.c
@@ -698,7 +698,8 @@ static void doc2001plus_command(struct mtd_info *mtd, unsigned command, int colu
 		/* Serially input address */
 		if (column != -1) {
 			/* Adjust columns for 16 bit buswidth */
-			if (this->options & NAND_BUSWIDTH_16)
+			if (this->options & NAND_BUSWIDTH_16 &&
+					!nand_opcode_8bits(command))
 				column >>= 1;
 			WriteDOC(column, docptr, Mplus_FlashAddress);
 		}
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index deeaa1cc4a85..6281151e4cb7 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -589,7 +589,8 @@ static void nand_command(struct mtd_info *mtd, unsigned int command,
 	/* Serially input address */
 	if (column != -1) {
 		/* Adjust columns for 16 bit buswidth */
-		if (chip->options & NAND_BUSWIDTH_16)
+		if (chip->options & NAND_BUSWIDTH_16 &&
+				!nand_opcode_8bits(command))
 			column >>= 1;
 		chip->cmd_ctrl(mtd, column, ctrl);
 		ctrl &= ~NAND_CTRL_CHANGE;
@@ -680,7 +681,8 @@ static void nand_command_lp(struct mtd_info *mtd, unsigned int command,
 		/* Serially input address */
 		if (column != -1) {
 			/* Adjust columns for 16 bit buswidth */
-			if (chip->options & NAND_BUSWIDTH_16)
+			if (chip->options & NAND_BUSWIDTH_16 &&
+					!nand_opcode_8bits(command))
 				column >>= 1;
 			chip->cmd_ctrl(mtd, column, ctrl);
 			ctrl &= ~NAND_CTRL_CHANGE;
diff --git a/drivers/mtd/nand/nuc900_nand.c b/drivers/mtd/nand/nuc900_nand.c
index 90c99ea5184a..331fccbdde61 100644
--- a/drivers/mtd/nand/nuc900_nand.c
+++ b/drivers/mtd/nand/nuc900_nand.c
@@ -151,7 +151,8 @@ static void nuc900_nand_command_lp(struct mtd_info *mtd, unsigned int command,
 	if (column != -1 || page_addr != -1) {
 
 		if (column != -1) {
-			if (chip->options & NAND_BUSWIDTH_16)
+			if (chip->options & NAND_BUSWIDTH_16 &&
+					!nand_opcode_8bits(command))
 				column >>= 1;
 			write_addr_reg(nand, column);
 			write_addr_reg(nand, column >> 8 | ENDADDR);
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index a719686c9cce..c034dc4224cb 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -832,4 +832,14 @@ static inline bool nand_is_slc(struct nand_chip *chip)
 {
 	return chip->bits_per_cell == 1;
 }
+
+/**
+ * Check if the opcode's address should be sent only on the lower 8 bits
+ * @command: opcode to check
+ */
+static inline int nand_opcode_8bits(unsigned int command)
+{
+	return command == NAND_CMD_READID;
+}
+
 #endif /* __LINUX_MTD_NAND_H */
-- 
cgit v1.2.3


From 91e165030deedc612c153dfeaba294d49632ade3 Mon Sep 17 00:00:00 2001
From: Sachin Kamat <sachin.kamat@linaro.org>
Date: Fri, 14 Feb 2014 12:16:38 +0530
Subject: mtd: nand: s3c2410: Trivial cleanup in header file

Commit 436d42c61c3e ("ARM: samsung: move platform_data definitions")
moved the files to the current location but forgot to remove the pointer
to its previous location. Clean it up. While at it also add the header
file protection macros appropriately.

Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 include/linux/platform_data/mtd-nand-s3c2410.h | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/platform_data/mtd-nand-s3c2410.h b/include/linux/platform_data/mtd-nand-s3c2410.h
index b64115fa93a4..36bb92172f47 100644
--- a/include/linux/platform_data/mtd-nand-s3c2410.h
+++ b/include/linux/platform_data/mtd-nand-s3c2410.h
@@ -1,5 +1,4 @@
-/* arch/arm/mach-s3c2410/include/mach/nand.h
- *
+/*
  * Copyright (c) 2004 Simtec Electronics
  *	Ben Dooks <ben@simtec.co.uk>
  *
@@ -10,6 +9,9 @@
  * published by the Free Software Foundation.
 */
 
+#ifndef __MTD_NAND_S3C2410_H
+#define __MTD_NAND_S3C2410_H
+
 /**
  * struct s3c2410_nand_set - define a set of one or more nand chips
  * @disable_ecc:	Entirely disable ECC - Dangerous
@@ -65,3 +67,5 @@ struct s3c2410_platform_nand {
  * it with the s3c_device_nand. This allows @nand to be __initdata.
 */
 extern void s3c_nand_set_platdata(struct s3c2410_platform_nand *nand);
+
+#endif /*__MTD_NAND_S3C2410_H */
-- 
cgit v1.2.3


From afbfff03d611de22b1ec7127ad56920e02936d5e Mon Sep 17 00:00:00 2001
From: Huang Shijie <b32955@freescale.com>
Date: Fri, 21 Feb 2014 13:39:37 +0800
Subject: mtd: nand: add the data structures for JEDEC parameter page

Create the nand_jedec_params{} and jedec_ecc_info{} according to
the JESD230A (Revision of JESD230, October 2012).

Signed-off-by: Huang Shijie <b32955@freescale.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 include/linux/mtd/nand.h | 75 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 75 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index c034dc4224cb..588f8a4a27af 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -342,6 +342,81 @@ struct nand_onfi_vendor_micron {
 	u8 param_revision;
 } __packed;
 
+struct jedec_ecc_info {
+	u8 ecc_bits;
+	u8 codeword_size;
+	__le16 bb_per_lun;
+	__le16 block_endurance;
+	u8 reserved[2];
+} __packed;
+
+struct nand_jedec_params {
+	/* rev info and features block */
+	/* 'J' 'E' 'S' 'D'  */
+	u8 sig[4];
+	__le16 revision;
+	__le16 features;
+	u8 opt_cmd[3];
+	__le16 sec_cmd;
+	u8 num_of_param_pages;
+	u8 reserved0[18];
+
+	/* manufacturer information block */
+	char manufacturer[12];
+	char model[20];
+	u8 jedec_id[6];
+	u8 reserved1[10];
+
+	/* memory organization block */
+	__le32 byte_per_page;
+	__le16 spare_bytes_per_page;
+	u8 reserved2[6];
+	__le32 pages_per_block;
+	__le32 blocks_per_lun;
+	u8 lun_count;
+	u8 addr_cycles;
+	u8 bits_per_cell;
+	u8 programs_per_page;
+	u8 multi_plane_addr;
+	u8 multi_plane_op_attr;
+	u8 reserved3[38];
+
+	/* electrical parameter block */
+	__le16 async_sdr_speed_grade;
+	__le16 toggle_ddr_speed_grade;
+	__le16 sync_ddr_speed_grade;
+	u8 async_sdr_features;
+	u8 toggle_ddr_features;
+	u8 sync_ddr_features;
+	__le16 t_prog;
+	__le16 t_bers;
+	__le16 t_r;
+	__le16 t_r_multi_plane;
+	__le16 t_ccs;
+	__le16 io_pin_capacitance_typ;
+	__le16 input_pin_capacitance_typ;
+	__le16 clk_pin_capacitance_typ;
+	u8 driver_strength_support;
+	__le16 t_ald;
+	u8 reserved4[36];
+
+	/* ECC and endurance block */
+	u8 guaranteed_good_blocks;
+	__le16 guaranteed_block_endurance;
+	struct jedec_ecc_info ecc_info[4];
+	u8 reserved5[29];
+
+	/* reserved */
+	u8 reserved6[148];
+
+	/* vendor */
+	__le16 vendor_rev_num;
+	u8 reserved7[88];
+
+	/* CRC for Parameter Page */
+	__le16 crc;
+} __packed;
+
 /**
  * struct nand_hw_control - Control structure for hardware controller (e.g ECC generator) shared among independent devices
  * @lock:               protection lock
-- 
cgit v1.2.3


From d94abba7605d3c15123eb3b331a1872ef17d29e0 Mon Sep 17 00:00:00 2001
From: Huang Shijie <b32955@freescale.com>
Date: Fri, 21 Feb 2014 13:39:38 +0800
Subject: mtd: nand: add fields for JEDEC in nand_chip

Add the jedec_version field, and add an anonymous union which
contains the nand_onfi_params and nand_jedec_params.

Signed-off-by: Huang Shijie <b32955@freescale.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 include/linux/mtd/nand.h | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 588f8a4a27af..f9af7564118a 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -590,8 +590,12 @@ struct nand_buffers {
  * @subpagesize:	[INTERN] holds the subpagesize
  * @onfi_version:	[INTERN] holds the chip ONFI version (BCD encoded),
  *			non 0 if ONFI supported.
+ * @jedec_version:	[INTERN] holds the chip JEDEC version (BCD encoded),
+ *			non 0 if JEDEC supported.
  * @onfi_params:	[INTERN] holds the ONFI page parameter when ONFI is
  *			supported, 0 otherwise.
+ * @jedec_params:	[INTERN] holds the JEDEC parameter page when JEDEC is
+ *			supported, 0 otherwise.
  * @read_retries:	[INTERN] the number of read retry modes supported
  * @onfi_set_features:	[REPLACEABLE] set the features for ONFI nand
  * @onfi_get_features:	[REPLACEABLE] get the features for ONFI nand
@@ -664,7 +668,11 @@ struct nand_chip {
 	int badblockbits;
 
 	int onfi_version;
-	struct nand_onfi_params	onfi_params;
+	int jedec_version;
+	union {
+		struct nand_onfi_params	onfi_params;
+		struct nand_jedec_params jedec_params;
+	};
 
 	int read_retries;
 
-- 
cgit v1.2.3


From 7852f8962f0f022b11fc56d63de06226a9f70d88 Mon Sep 17 00:00:00 2001
From: Huang Shijie <b32955@freescale.com>
Date: Fri, 21 Feb 2014 13:39:39 +0800
Subject: mtd: nand: add a helper to get the supported features for JEDEC

Add a helper to get the supported features for JEDEC compliant NAND.
Also add a macro JEDEC_FEATURE_16_BIT_BUS.

Signed-off-by: Huang Shijie <b32955@freescale.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 include/linux/mtd/nand.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index f9af7564118a..afd1cf9b5eaf 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -350,6 +350,9 @@ struct jedec_ecc_info {
 	u8 reserved[2];
 } __packed;
 
+/* JEDEC features */
+#define JEDEC_FEATURE_16_BIT_BUS	(1 << 0)
+
 struct nand_jedec_params {
 	/* rev info and features block */
 	/* 'J' 'E' 'S' 'D'  */
@@ -925,4 +928,10 @@ static inline int nand_opcode_8bits(unsigned int command)
 	return command == NAND_CMD_READID;
 }
 
+/* return the supported JEDEC features. */
+static inline int jedec_feature(struct nand_chip *chip)
+{
+	return chip->jedec_version ? le16_to_cpu(chip->jedec_params.features)
+		: 0;
+}
 #endif /* __LINUX_MTD_NAND_H */
-- 
cgit v1.2.3


From 913618185e51ee1fcbc193b2f121a9d072405619 Mon Sep 17 00:00:00 2001
From: Huang Shijie <b32955@freescale.com>
Date: Fri, 21 Feb 2014 13:39:40 +0800
Subject: mtd: nand: parse out the JEDEC compliant NAND

This patch adds the parsing code for the JEDEC compliant NAND.

Since we need the 0x40 as the column address, this patch also
makes the NAND_CMD_PARAM to use the 8-bit address only.

Signed-off-by: Huang Shijie <b32955@freescale.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 drivers/mtd/nand/nand_base.c | 85 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mtd/nand.h     |  2 +-
 2 files changed, 86 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 3cb1cefcd926..30416ecf44ef 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -3162,6 +3162,87 @@ static int nand_flash_detect_onfi(struct mtd_info *mtd, struct nand_chip *chip,
 	return 1;
 }
 
+/*
+ * Check if the NAND chip is JEDEC compliant, returns 1 if it is, 0 otherwise.
+ */
+static int nand_flash_detect_jedec(struct mtd_info *mtd, struct nand_chip *chip,
+					int *busw)
+{
+	struct nand_jedec_params *p = &chip->jedec_params;
+	struct jedec_ecc_info *ecc;
+	int val;
+	int i, j;
+
+	/* Try JEDEC for unknown chip or LP */
+	chip->cmdfunc(mtd, NAND_CMD_READID, 0x40, -1);
+	if (chip->read_byte(mtd) != 'J' || chip->read_byte(mtd) != 'E' ||
+		chip->read_byte(mtd) != 'D' || chip->read_byte(mtd) != 'E' ||
+		chip->read_byte(mtd) != 'C')
+		return 0;
+
+	chip->cmdfunc(mtd, NAND_CMD_PARAM, 0x40, -1);
+	for (i = 0; i < 3; i++) {
+		for (j = 0; j < sizeof(*p); j++)
+			((uint8_t *)p)[j] = chip->read_byte(mtd);
+
+		if (onfi_crc16(ONFI_CRC_BASE, (uint8_t *)p, 510) ==
+				le16_to_cpu(p->crc))
+			break;
+	}
+
+	if (i == 3) {
+		pr_err("Could not find valid JEDEC parameter page; aborting\n");
+		return 0;
+	}
+
+	/* Check version */
+	val = le16_to_cpu(p->revision);
+	if (val & (1 << 2))
+		chip->jedec_version = 10;
+	else if (val & (1 << 1))
+		chip->jedec_version = 1; /* vendor specific version */
+
+	if (!chip->jedec_version) {
+		pr_info("unsupported JEDEC version: %d\n", val);
+		return 0;
+	}
+
+	sanitize_string(p->manufacturer, sizeof(p->manufacturer));
+	sanitize_string(p->model, sizeof(p->model));
+	if (!mtd->name)
+		mtd->name = p->model;
+
+	mtd->writesize = le32_to_cpu(p->byte_per_page);
+
+	/* Please reference to the comment for nand_flash_detect_onfi. */
+	mtd->erasesize = 1 << (fls(le32_to_cpu(p->pages_per_block)) - 1);
+	mtd->erasesize *= mtd->writesize;
+
+	mtd->oobsize = le16_to_cpu(p->spare_bytes_per_page);
+
+	/* Please reference to the comment for nand_flash_detect_onfi. */
+	chip->chipsize = 1 << (fls(le32_to_cpu(p->blocks_per_lun)) - 1);
+	chip->chipsize *= (uint64_t)mtd->erasesize * p->lun_count;
+	chip->bits_per_cell = p->bits_per_cell;
+
+	if (jedec_feature(chip) & JEDEC_FEATURE_16_BIT_BUS)
+		*busw = NAND_BUSWIDTH_16;
+	else
+		*busw = 0;
+
+	/* ECC info */
+	ecc = &p->ecc_info[0];
+
+	if (ecc->codeword_size >= 9) {
+		chip->ecc_strength_ds = ecc->ecc_bits;
+		chip->ecc_step_ds = 1 << ecc->codeword_size;
+	} else {
+		pr_warn("Invalid codeword size\n");
+	}
+
+	return 1;
+}
+
 /*
  * nand_id_has_period - Check if an ID string has a given wraparound period
  * @id_data: the ID string
@@ -3527,6 +3608,10 @@ static struct nand_flash_dev *nand_get_flash_type(struct mtd_info *mtd,
 		/* Check is chip is ONFI compliant */
 		if (nand_flash_detect_onfi(mtd, chip, &busw))
 			goto ident_done;
+
+		/* Check if the chip is JEDEC compliant */
+		if (nand_flash_detect_jedec(mtd, chip, &busw))
+			goto ident_done;
 	}
 
 	if (!type->name)
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index afd1cf9b5eaf..aa005e87d161 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -925,7 +925,7 @@ static inline bool nand_is_slc(struct nand_chip *chip)
  */
 static inline int nand_opcode_8bits(unsigned int command)
 {
-	return command == NAND_CMD_READID;
+	return command == NAND_CMD_READID || command == NAND_CMD_PARAM;
 }
 
 /* return the supported JEDEC features. */
-- 
cgit v1.2.3


From 4b78fc42f3e3f07687dc27efc1153d29e360afa1 Mon Sep 17 00:00:00 2001
From: Christian Riesch <christian.riesch@omicron.at>
Date: Tue, 28 Jan 2014 09:29:44 +0100
Subject: mtd: Add a retlen parameter to _get_{fact,user}_prot_info

Signed-off-by: Christian Riesch <christian.riesch@omicron.at>
Cc: Artem Bityutskiy <Artem.Bityutskiy@linux.intel.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 drivers/mtd/chips/cfi_cmdset_0001.c | 31 +++++++++++++------------------
 drivers/mtd/devices/mtd_dataflash.c |  7 ++++---
 drivers/mtd/mtdchar.c               | 11 ++++++-----
 drivers/mtd/mtdcore.c               | 12 ++++++------
 drivers/mtd/mtdpart.c               | 14 ++++++++------
 drivers/mtd/onenand/onenand_base.c  | 30 ++++++++++++------------------
 include/linux/mtd/mtd.h             | 16 ++++++++--------
 7 files changed, 57 insertions(+), 64 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/chips/cfi_cmdset_0001.c b/drivers/mtd/chips/cfi_cmdset_0001.c
index 5e74c860e532..e4ec355704a6 100644
--- a/drivers/mtd/chips/cfi_cmdset_0001.c
+++ b/drivers/mtd/chips/cfi_cmdset_0001.c
@@ -68,10 +68,10 @@ static int cfi_intelext_read_fact_prot_reg (struct mtd_info *, loff_t, size_t, s
 static int cfi_intelext_read_user_prot_reg (struct mtd_info *, loff_t, size_t, size_t *, u_char *);
 static int cfi_intelext_write_user_prot_reg (struct mtd_info *, loff_t, size_t, size_t *, u_char *);
 static int cfi_intelext_lock_user_prot_reg (struct mtd_info *, loff_t, size_t);
-static int cfi_intelext_get_fact_prot_info (struct mtd_info *,
-					    struct otp_info *, size_t);
-static int cfi_intelext_get_user_prot_info (struct mtd_info *,
-					    struct otp_info *, size_t);
+static int cfi_intelext_get_fact_prot_info(struct mtd_info *, size_t,
+					   size_t *, struct otp_info *);
+static int cfi_intelext_get_user_prot_info(struct mtd_info *, size_t,
+					   size_t *, struct otp_info *);
 #endif
 static int cfi_intelext_suspend (struct mtd_info *);
 static void cfi_intelext_resume (struct mtd_info *);
@@ -2394,24 +2394,19 @@ static int cfi_intelext_lock_user_prot_reg(struct mtd_info *mtd,
 				     NULL, do_otp_lock, 1);
 }
 
-static int cfi_intelext_get_fact_prot_info(struct mtd_info *mtd,
-					   struct otp_info *buf, size_t len)
-{
-	size_t retlen;
-	int ret;
+static int cfi_intelext_get_fact_prot_info(struct mtd_info *mtd, size_t len,
+					   size_t *retlen, struct otp_info *buf)
 
-	ret = cfi_intelext_otp_walk(mtd, 0, len, &retlen, (u_char *)buf, NULL, 0);
-	return ret ? : retlen;
+{
+	return cfi_intelext_otp_walk(mtd, 0, len, retlen, (u_char *)buf,
+				     NULL, 0);
 }
 
-static int cfi_intelext_get_user_prot_info(struct mtd_info *mtd,
-					   struct otp_info *buf, size_t len)
+static int cfi_intelext_get_user_prot_info(struct mtd_info *mtd, size_t len,
+					   size_t *retlen, struct otp_info *buf)
 {
-	size_t retlen;
-	int ret;
-
-	ret = cfi_intelext_otp_walk(mtd, 0, len, &retlen, (u_char *)buf, NULL, 1);
-	return ret ? : retlen;
+	return cfi_intelext_otp_walk(mtd, 0, len, retlen, (u_char *)buf,
+				     NULL, 1);
 }
 
 #endif
diff --git a/drivers/mtd/devices/mtd_dataflash.c b/drivers/mtd/devices/mtd_dataflash.c
index 8b278d2b15bb..a6fdbe83bad6 100644
--- a/drivers/mtd/devices/mtd_dataflash.c
+++ b/drivers/mtd/devices/mtd_dataflash.c
@@ -439,8 +439,8 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len,
 
 #ifdef CONFIG_MTD_DATAFLASH_OTP
 
-static int dataflash_get_otp_info(struct mtd_info *mtd,
-		struct otp_info *info, size_t len)
+static int dataflash_get_otp_info(struct mtd_info *mtd, size_t len,
+				  size_t *retlen, struct otp_info *info)
 {
 	/* Report both blocks as identical:  bytes 0..64, locked.
 	 * Unless the user block changed from all-ones, we can't
@@ -449,7 +449,8 @@ static int dataflash_get_otp_info(struct mtd_info *mtd,
 	info->start = 0;
 	info->length = 64;
 	info->locked = 1;
-	return sizeof(*info);
+	*retlen = sizeof(*info);
+	return 0;
 }
 
 static ssize_t otp_read(struct spi_device *spi, unsigned base,
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index 2147e733533b..250798cf76aa 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -889,25 +889,26 @@ static int mtdchar_ioctl(struct file *file, u_int cmd, u_long arg)
 	case OTPGETREGIONINFO:
 	{
 		struct otp_info *buf = kmalloc(4096, GFP_KERNEL);
+		size_t retlen;
 		if (!buf)
 			return -ENOMEM;
 		switch (mfi->mode) {
 		case MTD_FILE_MODE_OTP_FACTORY:
-			ret = mtd_get_fact_prot_info(mtd, buf, 4096);
+			ret = mtd_get_fact_prot_info(mtd, 4096, &retlen, buf);
 			break;
 		case MTD_FILE_MODE_OTP_USER:
-			ret = mtd_get_user_prot_info(mtd, buf, 4096);
+			ret = mtd_get_user_prot_info(mtd, 4096, &retlen, buf);
 			break;
 		default:
 			ret = -EINVAL;
 			break;
 		}
-		if (ret >= 0) {
+		if (!ret) {
 			if (cmd == OTPGETREGIONCOUNT) {
-				int nbr = ret / sizeof(struct otp_info);
+				int nbr = retlen / sizeof(struct otp_info);
 				ret = copy_to_user(argp, &nbr, sizeof(int));
 			} else
-				ret = copy_to_user(argp, buf, ret);
+				ret = copy_to_user(argp, buf, retlen);
 			if (ret)
 				ret = -EFAULT;
 		}
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 34c0b16aed5c..0a7d77e65335 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -883,14 +883,14 @@ EXPORT_SYMBOL_GPL(mtd_read_oob);
  * devices. The user data is one time programmable but the factory data is read
  * only.
  */
-int mtd_get_fact_prot_info(struct mtd_info *mtd, struct otp_info *buf,
-			   size_t len)
+int mtd_get_fact_prot_info(struct mtd_info *mtd, size_t len, size_t *retlen,
+			   struct otp_info *buf)
 {
 	if (!mtd->_get_fact_prot_info)
 		return -EOPNOTSUPP;
 	if (!len)
 		return 0;
-	return mtd->_get_fact_prot_info(mtd, buf, len);
+	return mtd->_get_fact_prot_info(mtd, len, retlen, buf);
 }
 EXPORT_SYMBOL_GPL(mtd_get_fact_prot_info);
 
@@ -906,14 +906,14 @@ int mtd_read_fact_prot_reg(struct mtd_info *mtd, loff_t from, size_t len,
 }
 EXPORT_SYMBOL_GPL(mtd_read_fact_prot_reg);
 
-int mtd_get_user_prot_info(struct mtd_info *mtd, struct otp_info *buf,
-			   size_t len)
+int mtd_get_user_prot_info(struct mtd_info *mtd, size_t len, size_t *retlen,
+			   struct otp_info *buf)
 {
 	if (!mtd->_get_user_prot_info)
 		return -EOPNOTSUPP;
 	if (!len)
 		return 0;
-	return mtd->_get_user_prot_info(mtd, buf, len);
+	return mtd->_get_user_prot_info(mtd, len, retlen, buf);
 }
 EXPORT_SYMBOL_GPL(mtd_get_user_prot_info);
 
diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index 3c7d6d7623c1..1ca9aec141ff 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -150,11 +150,12 @@ static int part_read_user_prot_reg(struct mtd_info *mtd, loff_t from,
 						 retlen, buf);
 }
 
-static int part_get_user_prot_info(struct mtd_info *mtd,
-		struct otp_info *buf, size_t len)
+static int part_get_user_prot_info(struct mtd_info *mtd, size_t len,
+				   size_t *retlen, struct otp_info *buf)
 {
 	struct mtd_part *part = PART(mtd);
-	return part->master->_get_user_prot_info(part->master, buf, len);
+	return part->master->_get_user_prot_info(part->master, len, retlen,
+						 buf);
 }
 
 static int part_read_fact_prot_reg(struct mtd_info *mtd, loff_t from,
@@ -165,11 +166,12 @@ static int part_read_fact_prot_reg(struct mtd_info *mtd, loff_t from,
 						 retlen, buf);
 }
 
-static int part_get_fact_prot_info(struct mtd_info *mtd, struct otp_info *buf,
-		size_t len)
+static int part_get_fact_prot_info(struct mtd_info *mtd, size_t len,
+				   size_t *retlen, struct otp_info *buf)
 {
 	struct mtd_part *part = PART(mtd);
-	return part->master->_get_fact_prot_info(part->master, buf, len);
+	return part->master->_get_fact_prot_info(part->master, len, retlen,
+						 buf);
 }
 
 static int part_write(struct mtd_info *mtd, loff_t to, size_t len,
diff --git a/drivers/mtd/onenand/onenand_base.c b/drivers/mtd/onenand/onenand_base.c
index e886d7af868f..635ee0027691 100644
--- a/drivers/mtd/onenand/onenand_base.c
+++ b/drivers/mtd/onenand/onenand_base.c
@@ -3237,20 +3237,17 @@ static int onenand_otp_walk(struct mtd_info *mtd, loff_t from, size_t len,
 /**
  * onenand_get_fact_prot_info - [MTD Interface] Read factory OTP info
  * @param mtd		MTD device structure
- * @param buf		the databuffer to put/get data
  * @param len		number of bytes to read
+ * @param retlen	pointer to variable to store the number of read bytes
+ * @param buf		the databuffer to put/get data
  *
  * Read factory OTP info.
  */
-static int onenand_get_fact_prot_info(struct mtd_info *mtd,
-			struct otp_info *buf, size_t len)
+static int onenand_get_fact_prot_info(struct mtd_info *mtd, size_t len,
+				      size_t *retlen, struct otp_info *buf)
 {
-	size_t retlen;
-	int ret;
-
-	ret = onenand_otp_walk(mtd, 0, len, &retlen, (u_char *) buf, NULL, MTD_OTP_FACTORY);
-
-	return ret ? : retlen;
+	return onenand_otp_walk(mtd, 0, len, retlen, (u_char *) buf, NULL,
+				MTD_OTP_FACTORY);
 }
 
 /**
@@ -3272,20 +3269,17 @@ static int onenand_read_fact_prot_reg(struct mtd_info *mtd, loff_t from,
 /**
  * onenand_get_user_prot_info - [MTD Interface] Read user OTP info
  * @param mtd		MTD device structure
- * @param buf		the databuffer to put/get data
+ * @param retlen	pointer to variable to store the number of read bytes
  * @param len		number of bytes to read
+ * @param buf		the databuffer to put/get data
  *
  * Read user OTP info.
  */
-static int onenand_get_user_prot_info(struct mtd_info *mtd,
-			struct otp_info *buf, size_t len)
+static int onenand_get_user_prot_info(struct mtd_info *mtd, size_t len,
+				      size_t *retlen, struct otp_info *buf)
 {
-	size_t retlen;
-	int ret;
-
-	ret = onenand_otp_walk(mtd, 0, len, &retlen, (u_char *) buf, NULL, MTD_OTP_USER);
-
-	return ret ? : retlen;
+	return onenand_otp_walk(mtd, 0, len, retlen, (u_char *) buf, NULL,
+				MTD_OTP_USER);
 }
 
 /**
diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index 8cc0e2fb6894..a1b0b4c8fd79 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -204,12 +204,12 @@ struct mtd_info {
 			  struct mtd_oob_ops *ops);
 	int (*_write_oob) (struct mtd_info *mtd, loff_t to,
 			   struct mtd_oob_ops *ops);
-	int (*_get_fact_prot_info) (struct mtd_info *mtd, struct otp_info *buf,
-				    size_t len);
+	int (*_get_fact_prot_info) (struct mtd_info *mtd, size_t len,
+				    size_t *retlen, struct otp_info *buf);
 	int (*_read_fact_prot_reg) (struct mtd_info *mtd, loff_t from,
 				    size_t len, size_t *retlen, u_char *buf);
-	int (*_get_user_prot_info) (struct mtd_info *mtd, struct otp_info *buf,
-				    size_t len);
+	int (*_get_user_prot_info) (struct mtd_info *mtd, size_t len,
+				    size_t *retlen, struct otp_info *buf);
 	int (*_read_user_prot_reg) (struct mtd_info *mtd, loff_t from,
 				    size_t len, size_t *retlen, u_char *buf);
 	int (*_write_user_prot_reg) (struct mtd_info *mtd, loff_t to,
@@ -278,12 +278,12 @@ static inline int mtd_write_oob(struct mtd_info *mtd, loff_t to,
 	return mtd->_write_oob(mtd, to, ops);
 }
 
-int mtd_get_fact_prot_info(struct mtd_info *mtd, struct otp_info *buf,
-			   size_t len);
+int mtd_get_fact_prot_info(struct mtd_info *mtd, size_t len, size_t *retlen,
+			   struct otp_info *buf);
 int mtd_read_fact_prot_reg(struct mtd_info *mtd, loff_t from, size_t len,
 			   size_t *retlen, u_char *buf);
-int mtd_get_user_prot_info(struct mtd_info *mtd, struct otp_info *buf,
-			   size_t len);
+int mtd_get_user_prot_info(struct mtd_info *mtd, size_t len, size_t *retlen,
+			   struct otp_info *buf);
 int mtd_read_user_prot_reg(struct mtd_info *mtd, loff_t from, size_t len,
 			   size_t *retlen, u_char *buf);
 int mtd_write_user_prot_reg(struct mtd_info *mtd, loff_t to, size_t len,
-- 
cgit v1.2.3


From 6d9434ebb76157071164b32ad03fbed165c74382 Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel.garcia@free-electrons.com>
Date: Mon, 24 Feb 2014 19:24:48 -0300
Subject: of_mtd: Add helpers to get ECC strength and ECC step size

This commit adds simple helpers to obtain the devicetree properties
that specify the ECC strength and ECC step size to use on a given
NAND controller.

Acked-by: Boris BREZILLON <b.brezillon.dev@gmail.com>
Signed-off-by: Ezequiel Garcia <ezequiel.garcia@free-electrons.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 drivers/of/of_mtd.c    | 34 ++++++++++++++++++++++++++++++++++
 include/linux/of_mtd.h | 12 ++++++++++++
 2 files changed, 46 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/of/of_mtd.c b/drivers/of/of_mtd.c
index a27ec94877e4..b7361ed70537 100644
--- a/drivers/of/of_mtd.c
+++ b/drivers/of/of_mtd.c
@@ -49,6 +49,40 @@ int of_get_nand_ecc_mode(struct device_node *np)
 }
 EXPORT_SYMBOL_GPL(of_get_nand_ecc_mode);
 
+/**
+ * of_get_nand_ecc_step_size - Get ECC step size associated to
+ * the required ECC strength (see below).
+ * @np:	Pointer to the given device_node
+ *
+ * return the ECC step size, or errno in error case.
+ */
+int of_get_nand_ecc_step_size(struct device_node *np)
+{
+	int ret;
+	u32 val;
+
+	ret = of_property_read_u32(np, "nand-ecc-step-size", &val);
+	return ret ? ret : val;
+}
+EXPORT_SYMBOL_GPL(of_get_nand_ecc_step_size);
+
+/**
+ * of_get_nand_ecc_strength - Get required ECC strength over the
+ * correspnding step size as defined by 'nand-ecc-size'
+ * @np:	Pointer to the given device_node
+ *
+ * return the ECC strength, or errno in error case.
+ */
+int of_get_nand_ecc_strength(struct device_node *np)
+{
+	int ret;
+	u32 val;
+
+	ret = of_property_read_u32(np, "nand-ecc-strength", &val);
+	return ret ? ret : val;
+}
+EXPORT_SYMBOL_GPL(of_get_nand_ecc_strength);
+
 /**
  * of_get_nand_bus_width - Get nand bus witdh for given device_node
  * @np:	Pointer to the given device_node
diff --git a/include/linux/of_mtd.h b/include/linux/of_mtd.h
index cb32d9c1e8dc..e266caa36402 100644
--- a/include/linux/of_mtd.h
+++ b/include/linux/of_mtd.h
@@ -13,6 +13,8 @@
 
 #include <linux/of.h>
 int of_get_nand_ecc_mode(struct device_node *np);
+int of_get_nand_ecc_step_size(struct device_node *np);
+int of_get_nand_ecc_strength(struct device_node *np);
 int of_get_nand_bus_width(struct device_node *np);
 bool of_get_nand_on_flash_bbt(struct device_node *np);
 
@@ -23,6 +25,16 @@ static inline int of_get_nand_ecc_mode(struct device_node *np)
 	return -ENOSYS;
 }
 
+static inline int of_get_nand_ecc_step_size(struct device_node *np)
+{
+	return -ENOSYS;
+}
+
+static inline int of_get_nand_ecc_strength(struct device_node *np)
+{
+	return -ENOSYS;
+}
+
 static inline int of_get_nand_bus_width(struct device_node *np)
 {
 	return -ENOSYS;
-- 
cgit v1.2.3


From e004debdadf1a661dcd24e2a654e56b0a113e29e Mon Sep 17 00:00:00 2001
From: Huang Shijie <b32955@freescale.com>
Date: Fri, 3 Jan 2014 11:01:40 +0800
Subject: mtd: nand: add "page" argument for read_subpage hook

Add the "page" argument for the read_subpage hook. With this argument,
the implementation of this hook could prints out more accurate information
for debugging.

Signed-off-by: Huang Shijie <b32955@freescale.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 drivers/mtd/nand/nand_base.c | 7 +++++--
 include/linux/mtd/nand.h     | 2 +-
 2 files changed, 6 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 71c5c7a77053..5826da39216e 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -1162,9 +1162,11 @@ static int nand_read_page_swecc(struct mtd_info *mtd, struct nand_chip *chip,
  * @data_offs: offset of requested data within the page
  * @readlen: data length
  * @bufpoi: buffer to store read data
+ * @page: page number to read
  */
 static int nand_read_subpage(struct mtd_info *mtd, struct nand_chip *chip,
-			uint32_t data_offs, uint32_t readlen, uint8_t *bufpoi)
+			uint32_t data_offs, uint32_t readlen, uint8_t *bufpoi,
+			int page)
 {
 	int start_step, end_step, num_steps;
 	uint32_t *eccpos = chip->ecc.layout->eccpos;
@@ -1540,7 +1542,8 @@ read_retry:
 			else if (!aligned && NAND_HAS_SUBPAGE_READ(chip) &&
 				 !oob)
 				ret = chip->ecc.read_subpage(mtd, chip,
-							col, bytes, bufpoi);
+							col, bytes, bufpoi,
+							page);
 			else
 				ret = chip->ecc.read_page(mtd, chip, bufpoi,
 							  oob_required, page);
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index aa005e87d161..0747fef2bfc6 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -488,7 +488,7 @@ struct nand_ecc_ctrl {
 	int (*read_page)(struct mtd_info *mtd, struct nand_chip *chip,
 			uint8_t *buf, int oob_required, int page);
 	int (*read_subpage)(struct mtd_info *mtd, struct nand_chip *chip,
-			uint32_t offs, uint32_t len, uint8_t *buf);
+			uint32_t offs, uint32_t len, uint8_t *buf, int page);
 	int (*write_subpage)(struct mtd_info *mtd, struct nand_chip *chip,
 			uint32_t offset, uint32_t data_len,
 			const uint8_t *data_buf, int oob_required);
-- 
cgit v1.2.3


From 907e30f1bb4a9656d351aa705c1e5931da908701 Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Mon, 3 Mar 2014 08:48:50 +0100
Subject: idle/cpuidle: Split cpuidle_idle_call main function into smaller
 functions

In order to allow better integration between the cpuidle framework and the
scheduler, reducing the distance between these two sub-components will
facilitate this integration by moving part of the cpuidle code in the idle
task file and, because idle.c is in the sched directory, we have access to
the scheduler's private structures.

This patch splits the cpuidle_idle_call main entry function into 3 calls
to a newly added API:

 1. select the idle state
 2. enter the idle state
 3. reflect the idle state

The cpuidle_idle_call calls these three functions to implement the main
idle entry function.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Acked-by: Nicolas Pitre <nico@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: rjw@rjwysocki.net
Cc: preeti@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/1393832934-11625-1-git-send-email-daniel.lezcano@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/cpuidle/cpuidle.c | 96 ++++++++++++++++++++++++++++++++++++-----------
 include/linux/cpuidle.h   | 19 ++++++++++
 2 files changed, 94 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 09d05ab262be..1506d69b3f0f 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -64,6 +64,26 @@ int cpuidle_play_dead(void)
 	return -ENODEV;
 }
 
+/**
+ * cpuidle_enabled - check if the cpuidle framework is ready
+ * @dev: cpuidle device for this cpu
+ * @drv: cpuidle driver for this cpu
+ *
+ * Return 0 on success, otherwise:
+ * -NODEV : the cpuidle framework is not available
+ * -EBUSY : the cpuidle framework is not initialized
+ */
+int cpuidle_enabled(struct cpuidle_driver *drv, struct cpuidle_device *dev)
+{
+	if (off || !initialized)
+		return -ENODEV;
+
+	if (!drv || !dev || !dev->enabled)
+		return -EBUSY;
+
+	return 0;
+}
+
 /**
  * cpuidle_enter_state - enter the state and update stats
  * @dev: cpuidle device for this cpu
@@ -107,6 +127,51 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	return entered_state;
 }
 
+/**
+ * cpuidle_select - ask the cpuidle framework to choose an idle state
+ *
+ * @drv: the cpuidle driver
+ * @dev: the cpuidle device
+ *
+ * Returns the index of the idle state.
+ */
+int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
+{
+	return cpuidle_curr_governor->select(drv, dev);
+}
+
+/**
+ * cpuidle_enter - enter into the specified idle state
+ *
+ * @drv:   the cpuidle driver tied with the cpu
+ * @dev:   the cpuidle device
+ * @index: the index in the idle state table
+ *
+ * Returns the index in the idle state, < 0 in case of error.
+ * The error code depends on the backend driver
+ */
+int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev,
+		  int index)
+{
+	if (cpuidle_state_is_coupled(dev, drv, index))
+		return cpuidle_enter_state_coupled(dev, drv, index);
+	return cpuidle_enter_state(dev, drv, index);
+}
+
+/**
+ * cpuidle_reflect - tell the underlying governor what was the state
+ * we were in
+ *
+ * @dev  : the cpuidle device
+ * @index: the index in the idle state table
+ *
+ */
+void cpuidle_reflect(struct cpuidle_device *dev, int index)
+{
+	if (cpuidle_curr_governor->reflect)
+		cpuidle_curr_governor->reflect(dev, index);
+}
+
 /**
  * cpuidle_idle_call - the main idle loop
  *
@@ -116,26 +181,21 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 int cpuidle_idle_call(void)
 {
 	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
-	struct cpuidle_driver *drv;
-	int next_state, entered_state;
+	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
+	int next_state, entered_state, ret;
 	bool broadcast;
 
-	if (off || !initialized)
-		return -ENODEV;
-
-	/* check if the device is ready */
-	if (!dev || !dev->enabled)
-		return -EBUSY;
-
-	drv = cpuidle_get_cpu_driver(dev);
+	ret = cpuidle_enabled(drv, dev);
+	if (ret < 0)
+		return ret;
 
 	/* ask the governor for the next state */
-	next_state = cpuidle_curr_governor->select(drv, dev);
+	next_state = cpuidle_select(drv, dev);
+
 	if (need_resched()) {
 		dev->last_residency = 0;
 		/* give the governor an opportunity to reflect on the outcome */
-		if (cpuidle_curr_governor->reflect)
-			cpuidle_curr_governor->reflect(dev, next_state);
+		cpuidle_reflect(dev, next_state);
 		local_irq_enable();
 		return 0;
 	}
@@ -146,14 +206,9 @@ int cpuidle_idle_call(void)
 	    clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu))
 		return -EBUSY;
 
-
 	trace_cpu_idle_rcuidle(next_state, dev->cpu);
 
-	if (cpuidle_state_is_coupled(dev, drv, next_state))
-		entered_state = cpuidle_enter_state_coupled(dev, drv,
-							    next_state);
-	else
-		entered_state = cpuidle_enter_state(dev, drv, next_state);
+	entered_state = cpuidle_enter(drv, dev, next_state);
 
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
 
@@ -161,8 +216,7 @@ int cpuidle_idle_call(void)
 		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
 
 	/* give the governor an opportunity to reflect on the outcome */
-	if (cpuidle_curr_governor->reflect)
-		cpuidle_curr_governor->reflect(dev, entered_state);
+	cpuidle_reflect(dev, entered_state);
 
 	return 0;
 }
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 50fcbb0ac4e7..accc2dd72049 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -119,6 +119,15 @@ struct cpuidle_driver {
 
 #ifdef CONFIG_CPU_IDLE
 extern void disable_cpuidle(void);
+
+extern int cpuidle_enabled(struct cpuidle_driver *drv,
+			  struct cpuidle_device *dev);
+extern int cpuidle_select(struct cpuidle_driver *drv,
+			  struct cpuidle_device *dev);
+extern int cpuidle_enter(struct cpuidle_driver *drv,
+			 struct cpuidle_device *dev, int index);
+extern void cpuidle_reflect(struct cpuidle_device *dev, int index);
+
 extern int cpuidle_idle_call(void);
 extern int cpuidle_register_driver(struct cpuidle_driver *drv);
 extern struct cpuidle_driver *cpuidle_get_driver(void);
@@ -141,6 +150,16 @@ extern int cpuidle_play_dead(void);
 extern struct cpuidle_driver *cpuidle_get_cpu_driver(struct cpuidle_device *dev);
 #else
 static inline void disable_cpuidle(void) { }
+static inline int cpuidle_enabled(struct cpuidle_driver *drv,
+				  struct cpuidle_device *dev)
+{return -ENODEV; }
+static inline int cpuidle_select(struct cpuidle_driver *drv,
+				 struct cpuidle_device *dev)
+{return -ENODEV; }
+static inline int cpuidle_enter(struct cpuidle_driver *drv,
+				struct cpuidle_device *dev, int index)
+{return -ENODEV; }
+static inline void cpuidle_reflect(struct cpuidle_device *dev, int index) { }
 static inline int cpuidle_idle_call(void) { return -ENODEV; }
 static inline int cpuidle_register_driver(struct cpuidle_driver *drv)
 {return -ENODEV; }
-- 
cgit v1.2.3


From 30cdd69e2a266505ca8229c944d361ff350a6959 Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Mon, 3 Mar 2014 08:48:51 +0100
Subject: cpuidle/idle: Move the cpuidle_idle_call function to idle.c

The cpuidle_idle_call does nothing more than calling the three individuals
function and is no longer used by any arch specific code but only in the
cpuidle framework code.

We can move this function into the idle task code to ensure better
proximity to the scheduler code.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Acked-by: Nicolas Pitre <nicolas.pitre@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: rjw@rjwysocki.net
Cc: preeti@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/1393832934-11625-2-git-send-email-daniel.lezcano@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/cpuidle/cpuidle.c | 49 -----------------------------------------
 include/linux/cpuidle.h   |  2 --
 kernel/sched/idle.c       | 56 +++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 56 insertions(+), 51 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 1506d69b3f0f..166a7322a2b6 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -172,55 +172,6 @@ void cpuidle_reflect(struct cpuidle_device *dev, int index)
 		cpuidle_curr_governor->reflect(dev, index);
 }
 
-/**
- * cpuidle_idle_call - the main idle loop
- *
- * NOTE: no locks or semaphores should be used here
- * return non-zero on failure
- */
-int cpuidle_idle_call(void)
-{
-	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
-	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
-	int next_state, entered_state, ret;
-	bool broadcast;
-
-	ret = cpuidle_enabled(drv, dev);
-	if (ret < 0)
-		return ret;
-
-	/* ask the governor for the next state */
-	next_state = cpuidle_select(drv, dev);
-
-	if (need_resched()) {
-		dev->last_residency = 0;
-		/* give the governor an opportunity to reflect on the outcome */
-		cpuidle_reflect(dev, next_state);
-		local_irq_enable();
-		return 0;
-	}
-
-	broadcast = !!(drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP);
-
-	if (broadcast &&
-	    clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu))
-		return -EBUSY;
-
-	trace_cpu_idle_rcuidle(next_state, dev->cpu);
-
-	entered_state = cpuidle_enter(drv, dev, next_state);
-
-	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
-
-	if (broadcast)
-		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
-
-	/* give the governor an opportunity to reflect on the outcome */
-	cpuidle_reflect(dev, entered_state);
-
-	return 0;
-}
-
 /**
  * cpuidle_install_idle_handler - installs the cpuidle idle loop handler
  */
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index accc2dd72049..8d97962d6d64 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -128,7 +128,6 @@ extern int cpuidle_enter(struct cpuidle_driver *drv,
 			 struct cpuidle_device *dev, int index);
 extern void cpuidle_reflect(struct cpuidle_device *dev, int index);
 
-extern int cpuidle_idle_call(void);
 extern int cpuidle_register_driver(struct cpuidle_driver *drv);
 extern struct cpuidle_driver *cpuidle_get_driver(void);
 extern struct cpuidle_driver *cpuidle_driver_ref(void);
@@ -160,7 +159,6 @@ static inline int cpuidle_enter(struct cpuidle_driver *drv,
 				struct cpuidle_device *dev, int index)
 {return -ENODEV; }
 static inline void cpuidle_reflect(struct cpuidle_device *dev, int index) { }
-static inline int cpuidle_idle_call(void) { return -ENODEV; }
 static inline int cpuidle_register_driver(struct cpuidle_driver *drv)
 {return -ENODEV; }
 static inline struct cpuidle_driver *cpuidle_get_driver(void) {return NULL; }
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index b7976a127178..d5aaf5eb4531 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -63,6 +63,62 @@ void __weak arch_cpu_idle(void)
 	local_irq_enable();
 }
 
+#ifdef CONFIG_CPU_IDLE
+/**
+ * cpuidle_idle_call - the main idle function
+ *
+ * NOTE: no locks or semaphores should be used here
+ * return non-zero on failure
+ */
+static int cpuidle_idle_call(void)
+{
+	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
+	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
+	int next_state, entered_state, ret;
+	bool broadcast;
+
+	ret = cpuidle_enabled(drv, dev);
+	if (ret < 0)
+		return ret;
+
+	/* ask the governor for the next state */
+	next_state = cpuidle_select(drv, dev);
+
+	if (need_resched()) {
+		dev->last_residency = 0;
+		/* give the governor an opportunity to reflect on the outcome */
+		cpuidle_reflect(dev, next_state);
+		local_irq_enable();
+		return 0;
+	}
+
+	broadcast = !!(drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP);
+
+	if (broadcast &&
+	    clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu))
+		return -EBUSY;
+
+	trace_cpu_idle_rcuidle(next_state, dev->cpu);
+
+	entered_state = cpuidle_enter(drv, dev, next_state);
+
+	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
+
+	if (broadcast)
+		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
+
+	/* give the governor an opportunity to reflect on the outcome */
+	cpuidle_reflect(dev, entered_state);
+
+	return 0;
+}
+#else
+static inline int cpuidle_idle_call(void)
+{
+	return -ENODEV;
+}
+#endif
+
 /*
  * Generic idle loop implementation
  */
-- 
cgit v1.2.3


From c8cc7d4de7a4f2fb1f8774ec2de5b49c46c42e64 Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Mon, 3 Mar 2014 08:48:52 +0100
Subject: sched/idle: Reorganize the idle loop

Now that we have the main cpuidle function in idle.c, move some code from
the idle mainloop to this function for the sake of clarity.

That removes if then else indentation difficult to follow when looking at the
code. This patch does not change the current behavior.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Acked-by: Nicolas Pitre <nico@linaro.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: tglx@linutronix.de
Cc: rjw@rjwysocki.net
Cc: preeti@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/1393832934-11625-3-git-send-email-daniel.lezcano@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/cpuidle.h |  2 ++
 kernel/sched/idle.c     | 33 +++++++++++++++------------------
 2 files changed, 17 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 8d97962d6d64..b0238cba440b 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -180,6 +180,8 @@ static inline int cpuidle_enable_device(struct cpuidle_device *dev)
 {return -ENODEV; }
 static inline void cpuidle_disable_device(struct cpuidle_device *dev) { }
 static inline int cpuidle_play_dead(void) {return -ENODEV; }
+static inline struct cpuidle_driver *cpuidle_get_cpu_driver(
+	struct cpuidle_device *dev) {return NULL; }
 #endif
 
 #ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index d5aaf5eb4531..dc8a2466418f 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -63,7 +63,6 @@ void __weak arch_cpu_idle(void)
 	local_irq_enable();
 }
 
-#ifdef CONFIG_CPU_IDLE
 /**
  * cpuidle_idle_call - the main idle function
  *
@@ -77,9 +76,14 @@ static int cpuidle_idle_call(void)
 	int next_state, entered_state, ret;
 	bool broadcast;
 
+	stop_critical_timings();
+	rcu_idle_enter();
+
 	ret = cpuidle_enabled(drv, dev);
-	if (ret < 0)
-		return ret;
+	if (ret < 0) {
+		arch_cpu_idle();
+		goto out;
+	}
 
 	/* ask the governor for the next state */
 	next_state = cpuidle_select(drv, dev);
@@ -89,7 +93,7 @@ static int cpuidle_idle_call(void)
 		/* give the governor an opportunity to reflect on the outcome */
 		cpuidle_reflect(dev, next_state);
 		local_irq_enable();
-		return 0;
+		goto out;
 	}
 
 	broadcast = !!(drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP);
@@ -109,15 +113,15 @@ static int cpuidle_idle_call(void)
 
 	/* give the governor an opportunity to reflect on the outcome */
 	cpuidle_reflect(dev, entered_state);
+out:
+	if (WARN_ON_ONCE(irqs_disabled()))
+		local_irq_enable();
+
+	rcu_idle_exit();
+	start_critical_timings();
 
 	return 0;
 }
-#else
-static inline int cpuidle_idle_call(void)
-{
-	return -ENODEV;
-}
-#endif
 
 /*
  * Generic idle loop implementation
@@ -150,14 +154,7 @@ static void cpu_idle_loop(void)
 				cpu_idle_poll();
 			} else {
 				if (!current_clr_polling_and_test()) {
-					stop_critical_timings();
-					rcu_idle_enter();
-					if (cpuidle_idle_call())
-						arch_cpu_idle();
-					if (WARN_ON_ONCE(irqs_disabled()))
-						local_irq_enable();
-					rcu_idle_exit();
-					start_critical_timings();
+					cpuidle_idle_call();
 				} else {
 					local_irq_enable();
 				}
-- 
cgit v1.2.3


From e8d9d1f5485b52ec3c4d7af839e6914438f6c285 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Fri, 28 Feb 2014 14:42:47 +0100
Subject: drivers: of: add initialization code for static reserved memory

This patch adds support for static (defined by 'reg' property) reserved
memory regions declared in device tree.

Memory blocks can be reliably reserved only during early boot. This must
happen before the whole memory management subsystem is initialized,
because we need to ensure that the given contiguous blocks are not yet
allocated by kernel. Also it must happen before kernel mappings for the
whole low memory are created, to ensure that there will be no mappings
(for reserved blocks). Typically, all this happens before device tree
structures are unflattened, so we need to get reserved memory layout
directly from fdt.

Based on previous code provided by Josh Cartwright <joshc@codeaurora.org>

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Grant Likely <grant.likely@linaro.org>
---
 drivers/of/fdt.c       | 131 +++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/of_fdt.h |   4 ++
 2 files changed, 135 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 758b4f8b30b7..819e11209718 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
+#include <linux/sizes.h>
 #include <linux/string.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
@@ -439,6 +440,118 @@ struct boot_param_header *initial_boot_params;
 
 #ifdef CONFIG_OF_EARLY_FLATTREE
 
+/**
+ * res_mem_reserve_reg() - reserve all memory described in 'reg' property
+ */
+static int __init __reserved_mem_reserve_reg(unsigned long node,
+					     const char *uname)
+{
+	int t_len = (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32);
+	phys_addr_t base, size;
+	unsigned long len;
+	__be32 *prop;
+	int nomap;
+
+	prop = of_get_flat_dt_prop(node, "reg", &len);
+	if (!prop)
+		return -ENOENT;
+
+	if (len && len % t_len != 0) {
+		pr_err("Reserved memory: invalid reg property in '%s', skipping node.\n",
+		       uname);
+		return -EINVAL;
+	}
+
+	nomap = of_get_flat_dt_prop(node, "no-map", NULL) != NULL;
+
+	while (len >= t_len) {
+		base = dt_mem_next_cell(dt_root_addr_cells, &prop);
+		size = dt_mem_next_cell(dt_root_size_cells, &prop);
+
+		if (base && size &&
+		    early_init_dt_reserve_memory_arch(base, size, nomap) == 0)
+			pr_debug("Reserved memory: reserved region for node '%s': base %pa, size %ld MiB\n",
+				uname, &base, (unsigned long)size / SZ_1M);
+		else
+			pr_info("Reserved memory: failed to reserve memory for node '%s': base %pa, size %ld MiB\n",
+				uname, &base, (unsigned long)size / SZ_1M);
+
+		len -= t_len;
+	}
+	return 0;
+}
+
+/**
+ * __reserved_mem_check_root() - check if #size-cells, #address-cells provided
+ * in /reserved-memory matches the values supported by the current implementation,
+ * also check if ranges property has been provided
+ */
+static int __reserved_mem_check_root(unsigned long node)
+{
+	__be32 *prop;
+
+	prop = of_get_flat_dt_prop(node, "#size-cells", NULL);
+	if (!prop || be32_to_cpup(prop) != dt_root_size_cells)
+		return -EINVAL;
+
+	prop = of_get_flat_dt_prop(node, "#address-cells", NULL);
+	if (!prop || be32_to_cpup(prop) != dt_root_addr_cells)
+		return -EINVAL;
+
+	prop = of_get_flat_dt_prop(node, "ranges", NULL);
+	if (!prop)
+		return -EINVAL;
+	return 0;
+}
+
+/**
+ * fdt_scan_reserved_mem() - scan a single FDT node for reserved memory
+ */
+static int __init __fdt_scan_reserved_mem(unsigned long node, const char *uname,
+					  int depth, void *data)
+{
+	static int found;
+	const char *status;
+
+	if (!found && depth == 1 && strcmp(uname, "reserved-memory") == 0) {
+		if (__reserved_mem_check_root(node) != 0) {
+			pr_err("Reserved memory: unsupported node format, ignoring\n");
+			/* break scan */
+			return 1;
+		}
+		found = 1;
+		/* scan next node */
+		return 0;
+	} else if (!found) {
+		/* scan next node */
+		return 0;
+	} else if (found && depth < 2) {
+		/* scanning of /reserved-memory has been finished */
+		return 1;
+	}
+
+	status = of_get_flat_dt_prop(node, "status", NULL);
+	if (status && strcmp(status, "okay") != 0 && strcmp(status, "ok") != 0)
+		return 0;
+
+	__reserved_mem_reserve_reg(node, uname);
+
+	/* scan next node */
+	return 0;
+}
+
+/**
+ * early_init_fdt_scan_reserved_mem() - create reserved memory regions
+ *
+ * This function grabs memory from early allocator for device exclusive use
+ * defined in device tree structures. It should be called by arch specific code
+ * once the early allocator (i.e. memblock) has been fully activated.
+ */
+void __init early_init_fdt_scan_reserved_mem(void)
+{
+	of_scan_flat_dt(__fdt_scan_reserved_mem, NULL);
+}
+
 /**
  * of_scan_flat_dt - scan flattened tree blob and call callback on each.
  * @it: callback function
@@ -856,6 +969,16 @@ void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size)
 	memblock_add(base, size);
 }
 
+int __init __weak early_init_dt_reserve_memory_arch(phys_addr_t base,
+					phys_addr_t size, bool nomap)
+{
+	if (memblock_is_region_reserved(base, size))
+		return -EBUSY;
+	if (nomap)
+		return memblock_remove(base, size);
+	return memblock_reserve(base, size);
+}
+
 /*
  * called from unflatten_device_tree() to bootstrap devicetree itself
  * Architectures can override this definition if memblock isn't used
@@ -864,6 +987,14 @@ void * __init __weak early_init_dt_alloc_memory_arch(u64 size, u64 align)
 {
 	return __va(memblock_alloc(size, align));
 }
+#else
+int __init __weak early_init_dt_reserve_memory_arch(phys_addr_t base,
+					phys_addr_t size, bool nomap)
+{
+	pr_err("Reserved memory not supported, ignoring range 0x%llx - 0x%llx%s\n",
+		  base, size, nomap ? " (nomap)" : "");
+	return -ENOSYS;
+}
 #endif
 
 bool __init early_init_dt_scan(void *params)
diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
index 2b77058a7335..ddd7219af8ac 100644
--- a/include/linux/of_fdt.h
+++ b/include/linux/of_fdt.h
@@ -98,7 +98,10 @@ extern int early_init_dt_scan_chosen(unsigned long node, const char *uname,
 				     int depth, void *data);
 extern int early_init_dt_scan_memory(unsigned long node, const char *uname,
 				     int depth, void *data);
+extern void early_init_fdt_scan_reserved_mem(void);
 extern void early_init_dt_add_memory_arch(u64 base, u64 size);
+extern int early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size,
+					     bool no_map);
 extern void * early_init_dt_alloc_memory_arch(u64 size, u64 align);
 extern u64 dt_mem_next_cell(int s, __be32 **cellp);
 
@@ -118,6 +121,7 @@ extern void unflatten_and_copy_device_tree(void);
 extern void early_init_devtree(void *);
 extern void early_get_first_memblock_info(void *, phys_addr_t *);
 #else /* CONFIG_OF_FLATTREE */
+static inline void early_init_fdt_scan_reserved_mem(void) {}
 static inline const char *of_flat_dt_get_machine_name(void) { return NULL; }
 static inline void unflatten_device_tree(void) {}
 static inline void unflatten_and_copy_device_tree(void) {}
-- 
cgit v1.2.3


From 3f0c8206644836e4f10a6b9fc47cda6a9a372f9b Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Fri, 28 Feb 2014 14:42:48 +0100
Subject: drivers: of: add initialization code for dynamic reserved memory

This patch adds support for dynamically allocated reserved memory regions
declared in device tree. Such regions are defined by 'size', 'alignment'
and 'alloc-ranges' properties.

Based on previous code provided by Josh Cartwright <joshc@codeaurora.org>

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Grant Likely <grant.likely@linaro.org>
---
 drivers/of/Kconfig              |   6 ++
 drivers/of/Makefile             |   1 +
 drivers/of/fdt.c                |  13 ++-
 drivers/of/of_reserved_mem.c    | 188 ++++++++++++++++++++++++++++++++++++++++
 include/linux/of_reserved_mem.h |  21 +++++
 5 files changed, 227 insertions(+), 2 deletions(-)
 create mode 100644 drivers/of/of_reserved_mem.c
 create mode 100644 include/linux/of_reserved_mem.h

(limited to 'include/linux')

diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index ffdcb11f75fb..c144b8f990ff 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -79,4 +79,10 @@ config OF_MTD
 	depends on MTD
 	def_bool y
 
+config OF_RESERVED_MEM
+	depends on OF_EARLY_FLATTREE
+	bool
+	help
+	  Helpers to allow for reservation of memory regions
+
 endmenu # OF
diff --git a/drivers/of/Makefile b/drivers/of/Makefile
index efd05102c405..ed9660adad77 100644
--- a/drivers/of/Makefile
+++ b/drivers/of/Makefile
@@ -9,3 +9,4 @@ obj-$(CONFIG_OF_MDIO)	+= of_mdio.o
 obj-$(CONFIG_OF_PCI)	+= of_pci.o
 obj-$(CONFIG_OF_PCI_IRQ)  += of_pci_irq.o
 obj-$(CONFIG_OF_MTD)	+= of_mtd.o
+obj-$(CONFIG_OF_RESERVED_MEM) += of_reserved_mem.o
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 819e11209718..510c0d8de8a0 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
+#include <linux/of_reserved_mem.h>
 #include <linux/sizes.h>
 #include <linux/string.h>
 #include <linux/errno.h>
@@ -450,7 +451,7 @@ static int __init __reserved_mem_reserve_reg(unsigned long node,
 	phys_addr_t base, size;
 	unsigned long len;
 	__be32 *prop;
-	int nomap;
+	int nomap, first = 1;
 
 	prop = of_get_flat_dt_prop(node, "reg", &len);
 	if (!prop)
@@ -477,6 +478,10 @@ static int __init __reserved_mem_reserve_reg(unsigned long node,
 				uname, &base, (unsigned long)size / SZ_1M);
 
 		len -= t_len;
+		if (first) {
+			fdt_reserved_mem_save_node(node, uname, base, size);
+			first = 0;
+		}
 	}
 	return 0;
 }
@@ -512,6 +517,7 @@ static int __init __fdt_scan_reserved_mem(unsigned long node, const char *uname,
 {
 	static int found;
 	const char *status;
+	int err;
 
 	if (!found && depth == 1 && strcmp(uname, "reserved-memory") == 0) {
 		if (__reserved_mem_check_root(node) != 0) {
@@ -534,7 +540,9 @@ static int __init __fdt_scan_reserved_mem(unsigned long node, const char *uname,
 	if (status && strcmp(status, "okay") != 0 && strcmp(status, "ok") != 0)
 		return 0;
 
-	__reserved_mem_reserve_reg(node, uname);
+	err = __reserved_mem_reserve_reg(node, uname);
+	if (err == -ENOENT && of_get_flat_dt_prop(node, "size", NULL))
+		fdt_reserved_mem_save_node(node, uname, 0, 0);
 
 	/* scan next node */
 	return 0;
@@ -550,6 +558,7 @@ static int __init __fdt_scan_reserved_mem(unsigned long node, const char *uname,
 void __init early_init_fdt_scan_reserved_mem(void)
 {
 	of_scan_flat_dt(__fdt_scan_reserved_mem, NULL);
+	fdt_init_reserved_mem();
 }
 
 /**
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
new file mode 100644
index 000000000000..69b811779585
--- /dev/null
+++ b/drivers/of/of_reserved_mem.c
@@ -0,0 +1,188 @@
+/*
+ * Device tree based initialization code for reserved memory.
+ *
+ * Copyright (c) 2013, The Linux Foundation. All Rights Reserved.
+ * Copyright (c) 2013,2014 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ * Author: Marek Szyprowski <m.szyprowski@samsung.com>
+ * Author: Josh Cartwright <joshc@codeaurora.org>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License or (at your optional) any later version of the license.
+ */
+
+#include <linux/err.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/of_platform.h>
+#include <linux/mm.h>
+#include <linux/sizes.h>
+#include <linux/of_reserved_mem.h>
+
+#define MAX_RESERVED_REGIONS	16
+static struct reserved_mem reserved_mem[MAX_RESERVED_REGIONS];
+static int reserved_mem_count;
+
+#if defined(CONFIG_HAVE_MEMBLOCK)
+#include <linux/memblock.h>
+int __init __weak early_init_dt_alloc_reserved_memory_arch(phys_addr_t size,
+	phys_addr_t align, phys_addr_t start, phys_addr_t end, bool nomap,
+	phys_addr_t *res_base)
+{
+	/*
+	 * We use __memblock_alloc_base() because memblock_alloc_base()
+	 * panic()s on allocation failure.
+	 */
+	phys_addr_t base = __memblock_alloc_base(size, align, end);
+	if (!base)
+		return -ENOMEM;
+
+	/*
+	 * Check if the allocated region fits in to start..end window
+	 */
+	if (base < start) {
+		memblock_free(base, size);
+		return -ENOMEM;
+	}
+
+	*res_base = base;
+	if (nomap)
+		return memblock_remove(base, size);
+	return 0;
+}
+#else
+int __init __weak early_init_dt_alloc_reserved_memory_arch(phys_addr_t size,
+	phys_addr_t align, phys_addr_t start, phys_addr_t end, bool nomap,
+	phys_addr_t *res_base)
+{
+	pr_err("Reserved memory not supported, ignoring region 0x%llx%s\n",
+		  size, nomap ? " (nomap)" : "");
+	return -ENOSYS;
+}
+#endif
+
+/**
+ * res_mem_save_node() - save fdt node for second pass initialization
+ */
+void __init fdt_reserved_mem_save_node(unsigned long node, const char *uname,
+				      phys_addr_t base, phys_addr_t size)
+{
+	struct reserved_mem *rmem = &reserved_mem[reserved_mem_count];
+
+	if (reserved_mem_count == ARRAY_SIZE(reserved_mem)) {
+		pr_err("Reserved memory: not enough space all defined regions.\n");
+		return;
+	}
+
+	rmem->fdt_node = node;
+	rmem->name = uname;
+	rmem->base = base;
+	rmem->size = size;
+
+	reserved_mem_count++;
+	return;
+}
+
+/**
+ * res_mem_alloc_size() - allocate reserved memory described by 'size', 'align'
+ *			  and 'alloc-ranges' properties
+ */
+static int __init __reserved_mem_alloc_size(unsigned long node,
+	const char *uname, phys_addr_t *res_base, phys_addr_t *res_size)
+{
+	int t_len = (dt_root_addr_cells + dt_root_size_cells) * sizeof(__be32);
+	phys_addr_t start = 0, end = 0;
+	phys_addr_t base = 0, align = 0, size;
+	unsigned long len;
+	__be32 *prop;
+	int nomap;
+	int ret;
+
+	prop = of_get_flat_dt_prop(node, "size", &len);
+	if (!prop)
+		return -EINVAL;
+
+	if (len != dt_root_size_cells * sizeof(__be32)) {
+		pr_err("Reserved memory: invalid size property in '%s' node.\n",
+				uname);
+		return -EINVAL;
+	}
+	size = dt_mem_next_cell(dt_root_size_cells, &prop);
+
+	nomap = of_get_flat_dt_prop(node, "no-map", NULL) != NULL;
+
+	prop = of_get_flat_dt_prop(node, "alignment", &len);
+	if (prop) {
+		if (len != dt_root_addr_cells * sizeof(__be32)) {
+			pr_err("Reserved memory: invalid alignment property in '%s' node.\n",
+				uname);
+			return -EINVAL;
+		}
+		align = dt_mem_next_cell(dt_root_addr_cells, &prop);
+	}
+
+	prop = of_get_flat_dt_prop(node, "alloc-ranges", &len);
+	if (prop) {
+
+		if (len % t_len != 0) {
+			pr_err("Reserved memory: invalid alloc-ranges property in '%s', skipping node.\n",
+			       uname);
+			return -EINVAL;
+		}
+
+		base = 0;
+
+		while (len > 0) {
+			start = dt_mem_next_cell(dt_root_addr_cells, &prop);
+			end = start + dt_mem_next_cell(dt_root_size_cells,
+						       &prop);
+
+			ret = early_init_dt_alloc_reserved_memory_arch(size,
+					align, start, end, nomap, &base);
+			if (ret == 0) {
+				pr_debug("Reserved memory: allocated memory for '%s' node: base %pa, size %ld MiB\n",
+					uname, &base,
+					(unsigned long)size / SZ_1M);
+				break;
+			}
+			len -= t_len;
+		}
+
+	} else {
+		ret = early_init_dt_alloc_reserved_memory_arch(size, align,
+							0, 0, nomap, &base);
+		if (ret == 0)
+			pr_debug("Reserved memory: allocated memory for '%s' node: base %pa, size %ld MiB\n",
+				uname, &base, (unsigned long)size / SZ_1M);
+	}
+
+	if (base == 0) {
+		pr_info("Reserved memory: failed to allocate memory for node '%s'\n",
+			uname);
+		return -ENOMEM;
+	}
+
+	*res_base = base;
+	*res_size = size;
+
+	return 0;
+}
+
+/**
+ * fdt_init_reserved_mem - allocate and init all saved reserved memory regions
+ */
+void __init fdt_init_reserved_mem(void)
+{
+	int i;
+	for (i = 0; i < reserved_mem_count; i++) {
+		struct reserved_mem *rmem = &reserved_mem[i];
+		unsigned long node = rmem->fdt_node;
+		int err = 0;
+
+		if (rmem->size == 0)
+			err = __reserved_mem_alloc_size(node, rmem->name,
+						 &rmem->base, &rmem->size);
+	}
+}
diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h
new file mode 100644
index 000000000000..89226ed7d954
--- /dev/null
+++ b/include/linux/of_reserved_mem.h
@@ -0,0 +1,21 @@
+#ifndef __OF_RESERVED_MEM_H
+#define __OF_RESERVED_MEM_H
+
+struct reserved_mem {
+	const char			*name;
+	unsigned long			fdt_node;
+	phys_addr_t			base;
+	phys_addr_t			size;
+};
+
+#ifdef CONFIG_OF_RESERVED_MEM
+void fdt_init_reserved_mem(void);
+void fdt_reserved_mem_save_node(unsigned long node, const char *uname,
+			       phys_addr_t base, phys_addr_t size);
+#else
+static inline void fdt_init_reserved_mem(void) { }
+static inline void fdt_reserved_mem_save_node(unsigned long node,
+		const char *uname, phys_addr_t base, phys_addr_t size) { }
+#endif
+
+#endif /* __OF_RESERVED_MEM_H */
-- 
cgit v1.2.3


From f618c4703a14672d27bc2ca5d132a844363d6f5f Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Fri, 28 Feb 2014 14:42:49 +0100
Subject: drivers: of: add support for custom reserved memory drivers

Add support for custom reserved memory drivers. Call their init() function
for each reserved region and prepare for using operations provided by them
with by the reserved_mem->ops array.

Based on previous code provided by Josh Cartwright <joshc@codeaurora.org>

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Grant Likely <grant.likely@linaro.org>
---
 drivers/of/of_reserved_mem.c      | 29 +++++++++++++++++++++++++++++
 include/asm-generic/vmlinux.lds.h | 11 +++++++++++
 include/linux/of_reserved_mem.h   | 32 ++++++++++++++++++++++++++++++++
 3 files changed, 72 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 69b811779585..daaaf935911d 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -170,6 +170,33 @@ static int __init __reserved_mem_alloc_size(unsigned long node,
 	return 0;
 }
 
+static const struct of_device_id __rmem_of_table_sentinel
+	__used __section(__reservedmem_of_table_end);
+
+/**
+ * res_mem_init_node() - call region specific reserved memory init code
+ */
+static int __init __reserved_mem_init_node(struct reserved_mem *rmem)
+{
+	extern const struct of_device_id __reservedmem_of_table[];
+	const struct of_device_id *i;
+
+	for (i = __reservedmem_of_table; i < &__rmem_of_table_sentinel; i++) {
+		reservedmem_of_init_fn initfn = i->data;
+		const char *compat = i->compatible;
+
+		if (!of_flat_dt_is_compatible(rmem->fdt_node, compat))
+			continue;
+
+		if (initfn(rmem, rmem->fdt_node, rmem->name) == 0) {
+			pr_info("Reserved memory: initialized node %s, compatible id %s\n",
+				rmem->name, compat);
+			return 0;
+		}
+	}
+	return -ENOENT;
+}
+
 /**
  * fdt_init_reserved_mem - allocate and init all saved reserved memory regions
  */
@@ -184,5 +211,7 @@ void __init fdt_init_reserved_mem(void)
 		if (rmem->size == 0)
 			err = __reserved_mem_alloc_size(node, rmem->name,
 						 &rmem->base, &rmem->size);
+		if (err == 0)
+			__reserved_mem_init_node(rmem);
 	}
 }
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index bc2121fa9132..f10f64fcc815 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -167,6 +167,16 @@
 #define CLK_OF_TABLES()
 #endif
 
+#ifdef CONFIG_OF_RESERVED_MEM
+#define RESERVEDMEM_OF_TABLES()				\
+	. = ALIGN(8);					\
+	VMLINUX_SYMBOL(__reservedmem_of_table) = .;	\
+	*(__reservedmem_of_table)			\
+	*(__reservedmem_of_table_end)
+#else
+#define RESERVEDMEM_OF_TABLES()
+#endif
+
 #define KERNEL_DTB()							\
 	STRUCT_ALIGN();							\
 	VMLINUX_SYMBOL(__dtb_start) = .;				\
@@ -490,6 +500,7 @@
 	TRACE_SYSCALLS()						\
 	MEM_DISCARD(init.rodata)					\
 	CLK_OF_TABLES()							\
+	RESERVEDMEM_OF_TABLES()						\
 	CLKSRC_OF_TABLES()						\
 	KERNEL_DTB()							\
 	IRQCHIP_OF_MATCH_TABLE()
diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h
index 89226ed7d954..9b1fbb7f29fc 100644
--- a/include/linux/of_reserved_mem.h
+++ b/include/linux/of_reserved_mem.h
@@ -1,21 +1,53 @@
 #ifndef __OF_RESERVED_MEM_H
 #define __OF_RESERVED_MEM_H
 
+struct device;
+struct of_phandle_args;
+struct reserved_mem_ops;
+
 struct reserved_mem {
 	const char			*name;
 	unsigned long			fdt_node;
+	const struct reserved_mem_ops	*ops;
 	phys_addr_t			base;
 	phys_addr_t			size;
+	void				*priv;
+};
+
+struct reserved_mem_ops {
+	void	(*device_init)(struct reserved_mem *rmem,
+			       struct device *dev);
+	void	(*device_release)(struct reserved_mem *rmem,
+				  struct device *dev);
 };
 
+typedef int (*reservedmem_of_init_fn)(struct reserved_mem *rmem,
+				      unsigned long node, const char *uname);
+
 #ifdef CONFIG_OF_RESERVED_MEM
 void fdt_init_reserved_mem(void);
 void fdt_reserved_mem_save_node(unsigned long node, const char *uname,
 			       phys_addr_t base, phys_addr_t size);
+
+#define RESERVEDMEM_OF_DECLARE(name, compat, init)			\
+	static const struct of_device_id __reservedmem_of_table_##name	\
+		__used __section(__reservedmem_of_table)		\
+		 = { .compatible = compat,				\
+		     .data = (init == (reservedmem_of_init_fn)NULL) ?	\
+				init : init }
+
 #else
 static inline void fdt_init_reserved_mem(void) { }
 static inline void fdt_reserved_mem_save_node(unsigned long node,
 		const char *uname, phys_addr_t base, phys_addr_t size) { }
+
+#define RESERVEDMEM_OF_DECLARE(name, compat, init)			\
+	static const struct of_device_id __reservedmem_of_table_##name	\
+		__attribute__((unused))					\
+		 = { .compatible = compat,				\
+		     .data = (init == (reservedmem_of_init_fn)NULL) ?	\
+				init : init }
+
 #endif
 
 #endif /* __OF_RESERVED_MEM_H */
-- 
cgit v1.2.3


From 693350c2ffe42a21185070b1e8ab77959b45d61e Mon Sep 17 00:00:00 2001
From: stephen hemminger <stephen@networkplumber.org>
Date: Mon, 10 Mar 2014 09:41:46 -0700
Subject: netdev: set __percpu attribute on netdev_alloc_pcpu_stats

This patch fixes sparse warnings in vlan driver.
It propagates the sparse __percpu attribute from alloc_percpu
into netdev_alloc_pcpu_stats. I expect it may trigger additional
sparse warnings from other drivers that are missing the __percpu
attribute.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Cong Wang <cwang@twopensource.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 1a869488b8ae..b8d8c805fd75 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1812,7 +1812,7 @@ struct pcpu_sw_netstats {
 
 #define netdev_alloc_pcpu_stats(type)				\
 ({								\
-	typeof(type) *pcpu_stats = alloc_percpu(type);		\
+	typeof(type) __percpu *pcpu_stats = alloc_percpu(type); \
 	if (pcpu_stats)	{					\
 		int i;						\
 		for_each_possible_cpu(i) {			\
-- 
cgit v1.2.3


From 75b57ecf9d1d1e17d099ab13b8f48e6e038676be Mon Sep 17 00:00:00 2001
From: Grant Likely <grant.likely@linaro.org>
Date: Thu, 20 Feb 2014 18:02:11 +0000
Subject: of: Make device nodes kobjects so they show up in sysfs

Device tree nodes are already treated as objects, and we already want to
expose them to userspace which is done using the /proc filesystem today.
Right now the kernel has to do a lot of work to keep the /proc view in
sync with the in-kernel representation. If device_nodes are switched to
be kobjects then the device tree code can be a whole lot simpler. It
also turns out that switching to using /sysfs from /proc results in
smaller code and data size, and the userspace ABI won't change if
/proc/device-tree symlinks to /sys/firmware/devicetree/base.

v7: Add missing sysfs_bin_attr_init()
v6: Add __of_add_property() early init fixes from Pantelis
v5: Rename firmware/ofw to firmware/devicetree
    Fix updating property values in sysfs
v4: Fixed build error on Powerpc
    Fixed handling of dynamic nodes on powerpc
v3: Fixed handling of duplicate attribute and child node names
v2: switch to using sysfs bin_attributes which solve the problem of
    reporting incorrect property size.

Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Tested-by: Sascha Hauer <s.hauer@pengutronix.de>
Cc: Rob Herring <rob.herring@calxeda.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Cc: Pantelis Antoniou <panto@antoniou-consulting.com>
---
 Documentation/ABI/testing/sysfs-firmware-ofw |  28 +++++
 arch/powerpc/platforms/pseries/dlpar.c       |   2 -
 arch/powerpc/platforms/pseries/reconfig.c    |   2 -
 arch/powerpc/sysdev/msi_bitmap.c             |   2 +-
 drivers/of/base.c                            | 174 +++++++++++++++++++++++++--
 drivers/of/fdt.c                             |   3 +-
 drivers/of/pdt.c                             |   4 +-
 drivers/of/testcase-data/tests-phandle.dtsi  |   3 +
 include/linux/of.h                           |   9 +-
 9 files changed, 209 insertions(+), 18 deletions(-)
 create mode 100644 Documentation/ABI/testing/sysfs-firmware-ofw

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-firmware-ofw b/Documentation/ABI/testing/sysfs-firmware-ofw
new file mode 100644
index 000000000000..f562b188e71d
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-firmware-ofw
@@ -0,0 +1,28 @@
+What:		/sys/firmware/devicetree/*
+Date:		November 2013
+Contact:	Grant Likely <grant.likely@linaro.org>
+Description:
+		When using OpenFirmware or a Flattened Device Tree to enumerate
+		hardware, the device tree structure will be exposed in this
+		directory.
+
+		It is possible for multiple device-tree directories to exist.
+		Some device drivers use a separate detached device tree which
+		have no attachment to the system tree and will appear in a
+		different subdirectory under /sys/firmware/devicetree.
+
+		Userspace must not use the /sys/firmware/devicetree/base
+		path directly, but instead should follow /proc/device-tree
+		symlink. It is possible that the absolute path will change
+		in the future, but the symlink is the stable ABI.
+
+		The /proc/device-tree symlink replaces the devicetree /proc
+		filesystem support, and has largely the same semantics and
+		should be compatible with existing userspace.
+
+		The contents of /sys/firmware/devicetree/ is a
+		hierarchy of directories, one per device tree node. The
+		directory name is the resolved path component name (node
+		name plus address). Properties are represented as files
+		in the directory. The contents of each file is the exact
+		binary data from the device tree.
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index a8fe5aa3d34f..022b38e6a80b 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -11,7 +11,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/kref.h>
 #include <linux/notifier.h>
 #include <linux/spinlock.h>
 #include <linux/cpu.h>
@@ -87,7 +86,6 @@ static struct device_node *dlpar_parse_cc_node(struct cc_workarea *ccwa,
 	}
 
 	of_node_set_flag(dn, OF_DYNAMIC);
-	kref_init(&dn->kref);
 
 	return dn;
 }
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index f93cdf55628c..0435bb65d0aa 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -12,7 +12,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/kref.h>
 #include <linux/notifier.h>
 #include <linux/proc_fs.h>
 #include <linux/slab.h>
@@ -70,7 +69,6 @@ static int pSeries_reconfig_add_node(const char *path, struct property *proplist
 
 	np->properties = proplist;
 	of_node_set_flag(np, OF_DYNAMIC);
-	kref_init(&np->kref);
 
 	np->parent = derive_parent(path);
 	if (IS_ERR(np->parent)) {
diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c
index 0968b66b4cf9..8ba60424be95 100644
--- a/arch/powerpc/sysdev/msi_bitmap.c
+++ b/arch/powerpc/sysdev/msi_bitmap.c
@@ -202,7 +202,7 @@ void __init test_of_node(void)
 
 	/* There should really be a struct device_node allocator */
 	memset(&of_node, 0, sizeof(of_node));
-	kref_init(&of_node.kref);
+	kref_init(&of_node.kobj.kref);
 	of_node.full_name = node_name;
 
 	check(0 == msi_bitmap_alloc(&bmp, size, &of_node));
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 48594f334151..3b70a468c8ab 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -23,6 +23,7 @@
 #include <linux/of.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
+#include <linux/string.h>
 #include <linux/proc_fs.h>
 
 #include "of_private.h"
@@ -35,6 +36,12 @@ struct device_node *of_chosen;
 struct device_node *of_aliases;
 static struct device_node *of_stdout;
 
+static struct kset *of_kset;
+
+/*
+ * Used to protect the of_aliases; but also overloaded to hold off addition of
+ * nodes to sysfs
+ */
 DEFINE_MUTEX(of_aliases_mutex);
 
 /* use when traversing tree through the allnext, child, sibling,
@@ -92,14 +99,14 @@ int __weak of_node_to_nid(struct device_node *np)
 struct device_node *of_node_get(struct device_node *node)
 {
 	if (node)
-		kref_get(&node->kref);
+		kobject_get(&node->kobj);
 	return node;
 }
 EXPORT_SYMBOL(of_node_get);
 
-static inline struct device_node *kref_to_device_node(struct kref *kref)
+static inline struct device_node *kobj_to_device_node(struct kobject *kobj)
 {
-	return container_of(kref, struct device_node, kref);
+	return container_of(kobj, struct device_node, kobj);
 }
 
 /**
@@ -109,16 +116,15 @@ static inline struct device_node *kref_to_device_node(struct kref *kref)
  *	In of_node_put() this function is passed to kref_put()
  *	as the destructor.
  */
-static void of_node_release(struct kref *kref)
+static void of_node_release(struct kobject *kobj)
 {
-	struct device_node *node = kref_to_device_node(kref);
+	struct device_node *node = kobj_to_device_node(kobj);
 	struct property *prop = node->properties;
 
 	/* We should never be releasing nodes that haven't been detached. */
 	if (!of_node_check_flag(node, OF_DETACHED)) {
 		pr_err("ERROR: Bad of_node_put() on %s\n", node->full_name);
 		dump_stack();
-		kref_init(&node->kref);
 		return;
 	}
 
@@ -151,11 +157,140 @@ static void of_node_release(struct kref *kref)
 void of_node_put(struct device_node *node)
 {
 	if (node)
-		kref_put(&node->kref, of_node_release);
+		kobject_put(&node->kobj);
 }
 EXPORT_SYMBOL(of_node_put);
+#else
+static void of_node_release(struct kobject *kobj)
+{
+	/* Without CONFIG_OF_DYNAMIC, no nodes gets freed */
+}
 #endif /* CONFIG_OF_DYNAMIC */
 
+struct kobj_type of_node_ktype = {
+	.release = of_node_release,
+};
+
+static ssize_t of_node_property_read(struct file *filp, struct kobject *kobj,
+				struct bin_attribute *bin_attr, char *buf,
+				loff_t offset, size_t count)
+{
+	struct property *pp = container_of(bin_attr, struct property, attr);
+	return memory_read_from_buffer(buf, count, &offset, pp->value, pp->length);
+}
+
+static const char *safe_name(struct kobject *kobj, const char *orig_name)
+{
+	const char *name = orig_name;
+	struct kernfs_node *kn;
+	int i = 0;
+
+	/* don't be a hero. After 16 tries give up */
+	while (i < 16 && (kn = sysfs_get_dirent(kobj->sd, name))) {
+		sysfs_put(kn);
+		if (name != orig_name)
+			kfree(name);
+		name = kasprintf(GFP_KERNEL, "%s#%i", orig_name, ++i);
+	}
+
+	if (name != orig_name)
+		pr_warn("device-tree: Duplicate name in %s, renamed to \"%s\"\n",
+			kobject_name(kobj), name);
+	return name;
+}
+
+static int __of_add_property_sysfs(struct device_node *np, struct property *pp)
+{
+	int rc;
+
+	/* Important: Don't leak passwords */
+	bool secure = strncmp(pp->name, "security-", 9) == 0;
+
+	sysfs_bin_attr_init(&pp->attr);
+	pp->attr.attr.name = safe_name(&np->kobj, pp->name);
+	pp->attr.attr.mode = secure ? S_IRUSR : S_IRUGO;
+	pp->attr.size = secure ? 0 : pp->length;
+	pp->attr.read = of_node_property_read;
+
+	rc = sysfs_create_bin_file(&np->kobj, &pp->attr);
+	WARN(rc, "error adding attribute %s to node %s\n", pp->name, np->full_name);
+	return rc;
+}
+
+static int __of_node_add(struct device_node *np)
+{
+	const char *name;
+	struct property *pp;
+	int rc;
+
+	np->kobj.kset = of_kset;
+	if (!np->parent) {
+		/* Nodes without parents are new top level trees */
+		rc = kobject_add(&np->kobj, NULL, safe_name(&of_kset->kobj, "base"));
+	} else {
+		name = safe_name(&np->parent->kobj, kbasename(np->full_name));
+		if (!name || !name[0])
+			return -EINVAL;
+
+		rc = kobject_add(&np->kobj, &np->parent->kobj, "%s", name);
+	}
+	if (rc)
+		return rc;
+
+	for_each_property_of_node(np, pp)
+		__of_add_property_sysfs(np, pp);
+
+	return 0;
+}
+
+int of_node_add(struct device_node *np)
+{
+	int rc = 0;
+	kobject_init(&np->kobj, &of_node_ktype);
+	mutex_lock(&of_aliases_mutex);
+	if (of_kset)
+		rc = __of_node_add(np);
+	mutex_unlock(&of_aliases_mutex);
+	return rc;
+}
+
+#if defined(CONFIG_OF_DYNAMIC)
+static void of_node_remove(struct device_node *np)
+{
+	struct property *pp;
+
+	for_each_property_of_node(np, pp)
+		sysfs_remove_bin_file(&np->kobj, &pp->attr);
+
+	kobject_del(&np->kobj);
+}
+#endif
+
+static int __init of_init(void)
+{
+	struct device_node *np;
+
+	/* Create the kset, and register existing nodes */
+	mutex_lock(&of_aliases_mutex);
+	of_kset = kset_create_and_add("devicetree", NULL, firmware_kobj);
+	if (!of_kset) {
+		mutex_unlock(&of_aliases_mutex);
+		return -ENOMEM;
+	}
+	for_each_of_allnodes(np)
+		__of_node_add(np);
+	mutex_unlock(&of_aliases_mutex);
+
+#if !defined(CONFIG_PROC_DEVICETREE)
+	/* Symlink to the new tree when PROC_DEVICETREE is disabled */
+	if (of_allnodes)
+		proc_symlink("device-tree", NULL, "/sys/firmware/devicetree/base");
+#endif /* CONFIG_PROC_DEVICETREE */
+
+	return 0;
+}
+core_initcall(of_init);
+
 static struct property *__of_find_property(const struct device_node *np,
 					   const char *name, int *lenp)
 {
@@ -1546,6 +1681,14 @@ int of_add_property(struct device_node *np, struct property *prop)
 	raw_spin_lock_irqsave(&devtree_lock, flags);
 	rc = __of_add_property(np, prop);
 	raw_spin_unlock_irqrestore(&devtree_lock, flags);
+	if (rc)
+		return rc;
+
+	/* at early boot, bail hear and defer setup to of_init() */
+	if (!of_kset)
+		return 0;
+
+	__of_add_property_sysfs(np, prop);
 
 #ifdef CONFIG_PROC_DEVICETREE
 	/* try to add to proc as well if it was initialized */
@@ -1593,6 +1736,12 @@ int of_remove_property(struct device_node *np, struct property *prop)
 	if (!found)
 		return -ENODEV;
 
+	/* at early boot, bail hear and defer setup to of_init() */
+	if (!of_kset)
+		return 0;
+
+	sysfs_remove_bin_file(&np->kobj, &prop->attr);
+
 #ifdef CONFIG_PROC_DEVICETREE
 	/* try to remove the proc node as well */
 	if (np->pde)
@@ -1643,13 +1792,20 @@ int of_update_property(struct device_node *np, struct property *newprop)
 		next = &(*next)->next;
 	}
 	raw_spin_unlock_irqrestore(&devtree_lock, flags);
+	if (rc)
+		return rc;
+
+	/* Update the sysfs attribute */
+	if (oldprop)
+		sysfs_remove_bin_file(&np->kobj, &oldprop->attr);
+	__of_add_property_sysfs(np, newprop);
 
 	if (!found)
 		return -ENODEV;
 
 #ifdef CONFIG_PROC_DEVICETREE
 	/* try to add to proc as well if it was initialized */
-	if (!rc && np->pde)
+	if (np->pde)
 		proc_device_tree_update_prop(np->pde, newprop, oldprop);
 #endif /* CONFIG_PROC_DEVICETREE */
 
@@ -1723,6 +1879,7 @@ int of_attach_node(struct device_node *np)
 	of_node_clear_flag(np, OF_DETACHED);
 	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 
+	of_node_add(np);
 	of_add_proc_dt_entry(np);
 	return 0;
 }
@@ -1795,6 +1952,7 @@ int of_detach_node(struct device_node *np)
 	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 
 	of_remove_proc_dt_entry(np);
+	of_node_remove(np);
 	return rc;
 }
 #endif /* defined(CONFIG_OF_DYNAMIC) */
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 758b4f8b30b7..96ad1ab7f9d6 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -232,7 +232,6 @@ static void * unflatten_dt_node(struct boot_param_header *blob,
 				dad->next->sibling = np;
 			dad->next = np;
 		}
-		kref_init(&np->kref);
 	}
 	/* process properties */
 	while (1) {
@@ -327,6 +326,8 @@ static void * unflatten_dt_node(struct boot_param_header *blob,
 			np->name = "<NULL>";
 		if (!np->type)
 			np->type = "<NULL>";
+
+		of_node_add(np);
 	}
 	while (tag == OF_DT_BEGIN_NODE || tag == OF_DT_NOP) {
 		if (tag == OF_DT_NOP)
diff --git a/drivers/of/pdt.c b/drivers/of/pdt.c
index 7b666736c168..e64fa3d3da5f 100644
--- a/drivers/of/pdt.c
+++ b/drivers/of/pdt.c
@@ -179,8 +179,6 @@ static struct device_node * __init of_pdt_create_node(phandle node,
 	of_pdt_incr_unique_id(dp);
 	dp->parent = parent;
 
-	kref_init(&dp->kref);
-
 	dp->name = of_pdt_get_one_property(node, "name");
 	dp->type = of_pdt_get_one_property(node, "device_type");
 	dp->phandle = node;
@@ -215,6 +213,7 @@ static struct device_node * __init of_pdt_build_tree(struct device_node *parent,
 		*nextp = &dp->allnext;
 
 		dp->full_name = of_pdt_build_full_name(dp);
+		of_node_add(dp);
 
 		dp->child = of_pdt_build_tree(dp,
 				of_pdt_prom_ops->getchild(node), nextp);
@@ -245,6 +244,7 @@ void __init of_pdt_build_devicetree(phandle root_node, struct of_pdt_ops *ops)
 	of_allnodes->path_component_name = "";
 #endif
 	of_allnodes->full_name = "/";
+	of_node_add(of_allnodes);
 
 	nextp = &of_allnodes->allnext;
 	of_allnodes->child = of_pdt_build_tree(of_allnodes,
diff --git a/drivers/of/testcase-data/tests-phandle.dtsi b/drivers/of/testcase-data/tests-phandle.dtsi
index 0007d3cd7dc2..788a4c24b8f5 100644
--- a/drivers/of/testcase-data/tests-phandle.dtsi
+++ b/drivers/of/testcase-data/tests-phandle.dtsi
@@ -1,6 +1,9 @@
 
 / {
 	testcase-data {
+		security-password = "password";
+		duplicate-name = "duplicate";
+		duplicate-name { };
 		phandle-tests {
 			provider0: provider0 {
 				#phandle-cells = <0>;
diff --git a/include/linux/of.h b/include/linux/of.h
index b3d0f6d86e3b..bd45be5bd565 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -18,7 +18,7 @@
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include <linux/errno.h>
-#include <linux/kref.h>
+#include <linux/kobject.h>
 #include <linux/mod_devicetable.h>
 #include <linux/spinlock.h>
 #include <linux/topology.h>
@@ -37,6 +37,7 @@ struct property {
 	struct property *next;
 	unsigned long _flags;
 	unsigned int unique_id;
+	struct bin_attribute attr;
 };
 
 #if defined(CONFIG_SPARC)
@@ -57,7 +58,7 @@ struct device_node {
 	struct	device_node *next;	/* next device of same type */
 	struct	device_node *allnext;	/* next in list of all nodes */
 	struct	proc_dir_entry *pde;	/* this node's proc directory */
-	struct	kref kref;
+	struct	kobject kobj;
 	unsigned long _flags;
 	void	*data;
 #if defined(CONFIG_SPARC)
@@ -74,6 +75,8 @@ struct of_phandle_args {
 	uint32_t args[MAX_PHANDLE_ARGS];
 };
 
+extern int of_node_add(struct device_node *node);
+
 #ifdef CONFIG_OF_DYNAMIC
 extern struct device_node *of_node_get(struct device_node *node);
 extern void of_node_put(struct device_node *node);
@@ -187,6 +190,8 @@ static inline const char *of_node_full_name(const struct device_node *np)
 	return np ? np->full_name : "<no-node>";
 }
 
+#define for_each_of_allnodes(dn) \
+	for (dn = of_allnodes; dn; dn = dn->allnext)
 extern struct device_node *of_find_node_by_name(struct device_node *from,
 	const char *name);
 extern struct device_node *of_find_node_by_type(struct device_node *from,
-- 
cgit v1.2.3


From 8357041a69b368991d1b04d9f1d297f8d71e1314 Mon Sep 17 00:00:00 2001
From: Grant Likely <grant.likely@secretlab.ca>
Date: Tue, 6 Nov 2012 21:03:27 +0000
Subject: of: remove /proc/device-tree

The same data is now available in sysfs, so we can remove the code
that exports it in /proc and replace it with a symlink to the sysfs
version.

Tested on versatile qemu model and mpc5200 eval board. More testing
would be appreciated.

v5: Fixed up conflicts with mainline changes

Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Cc: Rob Herring <rob.herring@calxeda.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Cc: Pantelis Antoniou <panto@antoniou-consulting.com>
---
 drivers/of/Kconfig     |   8 --
 drivers/of/base.c      |  52 +----------
 fs/proc/Makefile       |   1 -
 fs/proc/internal.h     |   7 --
 fs/proc/proc_devtree.c | 241 -------------------------------------------------
 fs/proc/root.c         |   3 -
 include/linux/of.h     |  11 ---
 7 files changed, 1 insertion(+), 322 deletions(-)
 delete mode 100644 fs/proc/proc_devtree.c

(limited to 'include/linux')

diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index ffdcb11f75fb..a46ac1b00032 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -7,14 +7,6 @@ config OF
 menu "Device Tree and Open Firmware support"
 	depends on OF
 
-config PROC_DEVICETREE
-	bool "Support for device tree in /proc"
-	depends on PROC_FS && !SPARC
-	help
-	  This option adds a device-tree directory under /proc which contains
-	  an image of the device tree that the kernel copies from Open
-	  Firmware or other boot firmware. If unsure, say Y here.
-
 config OF_SELFTEST
 	bool "Device Tree Runtime self tests"
 	depends on OF_IRQ
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 3b70a468c8ab..ed3e70b84957 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -281,11 +281,9 @@ static int __init of_init(void)
 		__of_node_add(np);
 	mutex_unlock(&of_aliases_mutex);
 
-#if !defined(CONFIG_PROC_DEVICETREE)
-	/* Symlink to the new tree when PROC_DEVICETREE is disabled */
+	/* Symlink in /proc as required by userspace ABI */
 	if (of_allnodes)
 		proc_symlink("device-tree", NULL, "/sys/firmware/devicetree/base");
-#endif /* CONFIG_PROC_DEVICETREE */
 
 	return 0;
 }
@@ -1690,12 +1688,6 @@ int of_add_property(struct device_node *np, struct property *prop)
 
 	__of_add_property_sysfs(np, prop);
 
-#ifdef CONFIG_PROC_DEVICETREE
-	/* try to add to proc as well if it was initialized */
-	if (!rc && np->pde)
-		proc_device_tree_add_prop(np->pde, prop);
-#endif /* CONFIG_PROC_DEVICETREE */
-
 	return rc;
 }
 
@@ -1742,12 +1734,6 @@ int of_remove_property(struct device_node *np, struct property *prop)
 
 	sysfs_remove_bin_file(&np->kobj, &prop->attr);
 
-#ifdef CONFIG_PROC_DEVICETREE
-	/* try to remove the proc node as well */
-	if (np->pde)
-		proc_device_tree_remove_prop(np->pde, prop);
-#endif /* CONFIG_PROC_DEVICETREE */
-
 	return 0;
 }
 
@@ -1803,12 +1789,6 @@ int of_update_property(struct device_node *np, struct property *newprop)
 	if (!found)
 		return -ENODEV;
 
-#ifdef CONFIG_PROC_DEVICETREE
-	/* try to add to proc as well if it was initialized */
-	if (np->pde)
-		proc_device_tree_update_prop(np->pde, newprop, oldprop);
-#endif /* CONFIG_PROC_DEVICETREE */
-
 	return 0;
 }
 
@@ -1843,22 +1823,6 @@ int of_reconfig_notify(unsigned long action, void *p)
 	return notifier_to_errno(rc);
 }
 
-#ifdef CONFIG_PROC_DEVICETREE
-static void of_add_proc_dt_entry(struct device_node *dn)
-{
-	struct proc_dir_entry *ent;
-
-	ent = proc_mkdir(strrchr(dn->full_name, '/') + 1, dn->parent->pde);
-	if (ent)
-		proc_device_tree_add_node(dn, ent);
-}
-#else
-static void of_add_proc_dt_entry(struct device_node *dn)
-{
-	return;
-}
-#endif
-
 /**
  * of_attach_node - Plug a device node into the tree and global list.
  */
@@ -1880,22 +1844,9 @@ int of_attach_node(struct device_node *np)
 	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 
 	of_node_add(np);
-	of_add_proc_dt_entry(np);
 	return 0;
 }
 
-#ifdef CONFIG_PROC_DEVICETREE
-static void of_remove_proc_dt_entry(struct device_node *dn)
-{
-	proc_remove(dn->pde);
-}
-#else
-static void of_remove_proc_dt_entry(struct device_node *dn)
-{
-	return;
-}
-#endif
-
 /**
  * of_detach_node - "Unplug" a node from the device tree.
  *
@@ -1951,7 +1902,6 @@ int of_detach_node(struct device_node *np)
 	of_node_set_flag(np, OF_DETACHED);
 	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 
-	of_remove_proc_dt_entry(np);
 	of_node_remove(np);
 	return rc;
 }
diff --git a/fs/proc/Makefile b/fs/proc/Makefile
index ab30716584f5..239493ec718e 100644
--- a/fs/proc/Makefile
+++ b/fs/proc/Makefile
@@ -27,6 +27,5 @@ proc-$(CONFIG_PROC_SYSCTL)	+= proc_sysctl.o
 proc-$(CONFIG_NET)		+= proc_net.o
 proc-$(CONFIG_PROC_KCORE)	+= kcore.o
 proc-$(CONFIG_PROC_VMCORE)	+= vmcore.o
-proc-$(CONFIG_PROC_DEVICETREE)	+= proc_devtree.o
 proc-$(CONFIG_PRINTK)	+= kmsg.o
 proc-$(CONFIG_PROC_PAGE_MONITOR)	+= page.o
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 651d09a11dde..3ab6d14e71c5 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -210,13 +210,6 @@ extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry
 extern int proc_fill_super(struct super_block *);
 extern void proc_entry_rundown(struct proc_dir_entry *);
 
-/*
- * proc_devtree.c
- */
-#ifdef CONFIG_PROC_DEVICETREE
-extern void proc_device_tree_init(void);
-#endif
-
 /*
  * proc_namespaces.c
  */
diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c
deleted file mode 100644
index c82dd5147845..000000000000
--- a/fs/proc/proc_devtree.c
+++ /dev/null
@@ -1,241 +0,0 @@
-/*
- * proc_devtree.c - handles /proc/device-tree
- *
- * Copyright 1997 Paul Mackerras
- */
-#include <linux/errno.h>
-#include <linux/init.h>
-#include <linux/time.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/printk.h>
-#include <linux/stat.h>
-#include <linux/string.h>
-#include <linux/of.h>
-#include <linux/export.h>
-#include <linux/slab.h>
-#include <asm/uaccess.h>
-#include "internal.h"
-
-static inline void set_node_proc_entry(struct device_node *np,
-				       struct proc_dir_entry *de)
-{
-	np->pde = de;
-}
-
-static struct proc_dir_entry *proc_device_tree;
-
-/*
- * Supply data on a read from /proc/device-tree/node/property.
- */
-static int property_proc_show(struct seq_file *m, void *v)
-{
-	struct property *pp = m->private;
-
-	seq_write(m, pp->value, pp->length);
-	return 0;
-}
-
-static int property_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, property_proc_show, __PDE_DATA(inode));
-}
-
-static const struct file_operations property_proc_fops = {
-	.owner		= THIS_MODULE,
-	.open		= property_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-/*
- * For a node with a name like "gc@10", we make symlinks called "gc"
- * and "@10" to it.
- */
-
-/*
- * Add a property to a node
- */
-static struct proc_dir_entry *
-__proc_device_tree_add_prop(struct proc_dir_entry *de, struct property *pp,
-		const char *name)
-{
-	struct proc_dir_entry *ent;
-
-	/*
-	 * Unfortunately proc_register puts each new entry
-	 * at the beginning of the list.  So we rearrange them.
-	 */
-	ent = proc_create_data(name,
-			       strncmp(name, "security-", 9) ? S_IRUGO : S_IRUSR,
-			       de, &property_proc_fops, pp);
-	if (ent == NULL)
-		return NULL;
-
-	if (!strncmp(name, "security-", 9))
-		proc_set_size(ent, 0); /* don't leak number of password chars */
-	else
-		proc_set_size(ent, pp->length);
-
-	return ent;
-}
-
-
-void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop)
-{
-	__proc_device_tree_add_prop(pde, prop, prop->name);
-}
-
-void proc_device_tree_remove_prop(struct proc_dir_entry *pde,
-				  struct property *prop)
-{
-	remove_proc_entry(prop->name, pde);
-}
-
-void proc_device_tree_update_prop(struct proc_dir_entry *pde,
-				  struct property *newprop,
-				  struct property *oldprop)
-{
-	struct proc_dir_entry *ent;
-
-	if (!oldprop) {
-		proc_device_tree_add_prop(pde, newprop);
-		return;
-	}
-
-	for (ent = pde->subdir; ent != NULL; ent = ent->next)
-		if (ent->data == oldprop)
-			break;
-	if (ent == NULL) {
-		pr_warn("device-tree: property \"%s\" does not exist\n",
-			oldprop->name);
-	} else {
-		ent->data = newprop;
-		ent->size = newprop->length;
-	}
-}
-
-/*
- * Various dodgy firmware might give us nodes and/or properties with
- * conflicting names. That's generally ok, except for exporting via /proc,
- * so munge names here to ensure they're unique.
- */
-
-static int duplicate_name(struct proc_dir_entry *de, const char *name)
-{
-	struct proc_dir_entry *ent;
-	int found = 0;
-
-	spin_lock(&proc_subdir_lock);
-
-	for (ent = de->subdir; ent != NULL; ent = ent->next) {
-		if (strcmp(ent->name, name) == 0) {
-			found = 1;
-			break;
-		}
-	}
-
-	spin_unlock(&proc_subdir_lock);
-
-	return found;
-}
-
-static const char *fixup_name(struct device_node *np, struct proc_dir_entry *de,
-		const char *name)
-{
-	char *fixed_name;
-	int fixup_len = strlen(name) + 2 + 1; /* name + #x + \0 */
-	int i = 1, size;
-
-realloc:
-	fixed_name = kmalloc(fixup_len, GFP_KERNEL);
-	if (fixed_name == NULL) {
-		pr_err("device-tree: Out of memory trying to fixup "
-		       "name \"%s\"\n", name);
-		return name;
-	}
-
-retry:
-	size = snprintf(fixed_name, fixup_len, "%s#%d", name, i);
-	size++; /* account for NULL */
-
-	if (size > fixup_len) {
-		/* We ran out of space, free and reallocate. */
-		kfree(fixed_name);
-		fixup_len = size;
-		goto realloc;
-	}
-
-	if (duplicate_name(de, fixed_name)) {
-		/* Multiple duplicates. Retry with a different offset. */
-		i++;
-		goto retry;
-	}
-
-	pr_warn("device-tree: Duplicate name in %s, renamed to \"%s\"\n",
-		np->full_name, fixed_name);
-
-	return fixed_name;
-}
-
-/*
- * Process a node, adding entries for its children and its properties.
- */
-void proc_device_tree_add_node(struct device_node *np,
-			       struct proc_dir_entry *de)
-{
-	struct property *pp;
-	struct proc_dir_entry *ent;
-	struct device_node *child;
-	const char *p;
-
-	set_node_proc_entry(np, de);
-	for (child = NULL; (child = of_get_next_child(np, child));) {
-		/* Use everything after the last slash, or the full name */
-		p = kbasename(child->full_name);
-
-		if (duplicate_name(de, p))
-			p = fixup_name(np, de, p);
-
-		ent = proc_mkdir(p, de);
-		if (ent == NULL)
-			break;
-		proc_device_tree_add_node(child, ent);
-	}
-	of_node_put(child);
-
-	for (pp = np->properties; pp != NULL; pp = pp->next) {
-		p = pp->name;
-
-		if (strchr(p, '/'))
-			continue;
-
-		if (duplicate_name(de, p))
-			p = fixup_name(np, de, p);
-
-		ent = __proc_device_tree_add_prop(de, pp, p);
-		if (ent == NULL)
-			break;
-	}
-}
-
-/*
- * Called on initialization to set up the /proc/device-tree subtree
- */
-void __init proc_device_tree_init(void)
-{
-	struct device_node *root;
-
-	proc_device_tree = proc_mkdir("device-tree", NULL);
-	if (proc_device_tree == NULL)
-		return;
-	root = of_find_node_by_path("/");
-	if (root == NULL) {
-		remove_proc_entry("device-tree", NULL);
-		pr_debug("/proc/device-tree: can't find root\n");
-		return;
-	}
-	proc_device_tree_add_node(root, proc_device_tree);
-	of_node_put(root);
-}
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 87dbcbef7fe4..7bbeb5257af1 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -183,9 +183,6 @@ void __init proc_root_init(void)
 	proc_mkdir("openprom", NULL);
 #endif
 	proc_tty_init();
-#ifdef CONFIG_PROC_DEVICETREE
-	proc_device_tree_init();
-#endif
 	proc_mkdir("bus", NULL);
 	proc_sys_init();
 }
diff --git a/include/linux/of.h b/include/linux/of.h
index bd45be5bd565..257994a420f3 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -57,7 +57,6 @@ struct device_node {
 	struct	device_node *sibling;
 	struct	device_node *next;	/* next device of same type */
 	struct	device_node *allnext;	/* next in list of all nodes */
-	struct	proc_dir_entry *pde;	/* this node's proc directory */
 	struct	kobject kobj;
 	unsigned long _flags;
 	void	*data;
@@ -658,14 +657,4 @@ static inline int of_get_available_child_count(const struct device_node *np)
 	return num;
 }
 
-#if defined(CONFIG_PROC_FS) && defined(CONFIG_PROC_DEVICETREE)
-extern void proc_device_tree_add_node(struct device_node *, struct proc_dir_entry *);
-extern void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop);
-extern void proc_device_tree_remove_prop(struct proc_dir_entry *pde,
-					 struct property *prop);
-extern void proc_device_tree_update_prop(struct proc_dir_entry *pde,
-					 struct property *newprop,
-					 struct property *oldprop);
-#endif
-
 #endif /* _LINUX_OF_H */
-- 
cgit v1.2.3


From e0b3165ba521c6824b3e9f563f38a701dfa2d8e6 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 10 Mar 2014 14:53:33 +0530
Subject: cpufreq: add 'freq_table' in struct cpufreq_policy

freq table is not per CPU but per policy, so it makes more sense to
keep it within struct cpufreq_policy instead of a per-cpu variable.

This patch does it. Over that, there is no need to set policy->freq_table
to NULL in ->exit(), as policy structure is going to be freed soon.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/acpi-cpufreq.c        |  1 -
 drivers/cpufreq/arm_big_little.c      |  1 -
 drivers/cpufreq/cpufreq.c             |  7 +++++-
 drivers/cpufreq/e_powersaver.c        |  1 -
 drivers/cpufreq/freq_table.c          | 46 ++++++-----------------------------
 drivers/cpufreq/ia64-acpi-cpufreq.c   |  1 -
 drivers/cpufreq/loongson2_cpufreq.c   |  1 -
 drivers/cpufreq/omap-cpufreq.c        |  1 -
 drivers/cpufreq/pasemi-cpufreq.c      |  1 -
 drivers/cpufreq/powernow-k6.c         |  1 -
 drivers/cpufreq/powernow-k7.c         |  2 --
 drivers/cpufreq/powernow-k8.c         |  2 --
 drivers/cpufreq/ppc-corenet-cpufreq.c |  1 -
 drivers/cpufreq/sh-cpufreq.c          |  1 -
 drivers/cpufreq/sparc-us2e-cpufreq.c  |  4 +--
 drivers/cpufreq/sparc-us3-cpufreq.c   |  4 +--
 drivers/cpufreq/speedstep-centrino.c  |  2 --
 drivers/cpufreq/tegra-cpufreq.c       |  1 -
 include/linux/cpufreq.h               |  6 +----
 19 files changed, 17 insertions(+), 67 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 18448a7e9f86..822ca03a87f7 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -855,7 +855,6 @@ static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 	pr_debug("acpi_cpufreq_cpu_exit\n");
 
 	if (data) {
-		cpufreq_frequency_table_put_attr(policy->cpu);
 		per_cpu(acfreq_data, policy->cpu) = NULL;
 		acpi_processor_unregister_performance(data->acpi_data,
 						      policy->cpu);
diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c
index 72f87e9317e3..3d8707848035 100644
--- a/drivers/cpufreq/arm_big_little.c
+++ b/drivers/cpufreq/arm_big_little.c
@@ -478,7 +478,6 @@ static int bL_cpufreq_exit(struct cpufreq_policy *policy)
 		return -ENODEV;
 	}
 
-	cpufreq_frequency_table_put_attr(policy->cpu);
 	put_cluster_clk_and_freq_table(cpu_dev);
 	dev_dbg(cpu_dev, "%s: Exited, cpu: %d\n", __func__, policy->cpu);
 
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 746f70875078..dddbefb857c9 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -191,6 +191,12 @@ unsigned int cpufreq_generic_get(unsigned int cpu)
 }
 EXPORT_SYMBOL_GPL(cpufreq_generic_get);
 
+/* Only for cpufreq core internal use */
+struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu)
+{
+	return per_cpu(cpufreq_cpu_data, cpu);
+}
+
 struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 {
 	struct cpufreq_policy *policy = NULL;
@@ -1031,7 +1037,6 @@ static void update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu)
 
 	up_write(&policy->rwsem);
 
-	cpufreq_frequency_table_update_policy_cpu(policy);
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 			CPUFREQ_UPDATE_POLICY_CPU, policy);
 }
diff --git a/drivers/cpufreq/e_powersaver.c b/drivers/cpufreq/e_powersaver.c
index 9012b8bb6b64..a0d2a423cea9 100644
--- a/drivers/cpufreq/e_powersaver.c
+++ b/drivers/cpufreq/e_powersaver.c
@@ -382,7 +382,6 @@ static int eps_cpu_exit(struct cpufreq_policy *policy)
 	unsigned int cpu = policy->cpu;
 
 	/* Bye */
-	cpufreq_frequency_table_put_attr(policy->cpu);
 	kfree(eps_cpu[cpu]);
 	eps_cpu[cpu] = NULL;
 	return 0;
diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index 8e54f97899ba..65a477075b3f 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -91,8 +91,8 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy *policy,
 EXPORT_SYMBOL_GPL(cpufreq_frequency_table_verify);
 
 /*
- * Generic routine to verify policy & frequency table, requires driver to call
- * cpufreq_frequency_table_get_attr() prior to it.
+ * Generic routine to verify policy & frequency table, requires driver to set
+ * policy->freq_table prior to it.
  */
 int cpufreq_generic_frequency_table_verify(struct cpufreq_policy *policy)
 {
@@ -203,8 +203,6 @@ int cpufreq_frequency_table_get_index(struct cpufreq_policy *policy,
 }
 EXPORT_SYMBOL_GPL(cpufreq_frequency_table_get_index);
 
-static DEFINE_PER_CPU(struct cpufreq_frequency_table *, cpufreq_show_table);
-
 /**
  * show_available_freqs - show available frequencies for the specified CPU
  */
@@ -212,15 +210,12 @@ static ssize_t show_available_freqs(struct cpufreq_policy *policy, char *buf,
 				    bool show_boost)
 {
 	unsigned int i = 0;
-	unsigned int cpu = policy->cpu;
 	ssize_t count = 0;
-	struct cpufreq_frequency_table *table;
+	struct cpufreq_frequency_table *table = policy->freq_table;
 
-	if (!per_cpu(cpufreq_show_table, cpu))
+	if (!table)
 		return -ENODEV;
 
-	table = per_cpu(cpufreq_show_table, cpu);
-
 	for (i = 0; (table[i].frequency != CPUFREQ_TABLE_END); i++) {
 		if (table[i].frequency == CPUFREQ_ENTRY_INVALID)
 			continue;
@@ -283,49 +278,24 @@ struct freq_attr *cpufreq_generic_attr[] = {
 };
 EXPORT_SYMBOL_GPL(cpufreq_generic_attr);
 
-/*
- * if you use these, you must assure that the frequency table is valid
- * all the time between get_attr and put_attr!
- */
-void cpufreq_frequency_table_get_attr(struct cpufreq_frequency_table *table,
-				      unsigned int cpu)
-{
-	pr_debug("setting show_table for cpu %u to %p\n", cpu, table);
-	per_cpu(cpufreq_show_table, cpu) = table;
-}
-EXPORT_SYMBOL_GPL(cpufreq_frequency_table_get_attr);
-
-void cpufreq_frequency_table_put_attr(unsigned int cpu)
-{
-	pr_debug("clearing show_table for cpu %u\n", cpu);
-	per_cpu(cpufreq_show_table, cpu) = NULL;
-}
-EXPORT_SYMBOL_GPL(cpufreq_frequency_table_put_attr);
-
 int cpufreq_table_validate_and_show(struct cpufreq_policy *policy,
 				      struct cpufreq_frequency_table *table)
 {
 	int ret = cpufreq_frequency_table_cpuinfo(policy, table);
 
 	if (!ret)
-		cpufreq_frequency_table_get_attr(table, policy->cpu);
+		policy->freq_table = table;
 
 	return ret;
 }
 EXPORT_SYMBOL_GPL(cpufreq_table_validate_and_show);
 
-void cpufreq_frequency_table_update_policy_cpu(struct cpufreq_policy *policy)
-{
-	pr_debug("Updating show_table for new_cpu %u from last_cpu %u\n",
-			policy->cpu, policy->last_cpu);
-	per_cpu(cpufreq_show_table, policy->cpu) = per_cpu(cpufreq_show_table,
-			policy->last_cpu);
-	per_cpu(cpufreq_show_table, policy->last_cpu) = NULL;
-}
+struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu);
 
 struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu)
 {
-	return per_cpu(cpufreq_show_table, cpu);
+	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
+	return policy ? policy->freq_table : NULL;
 }
 EXPORT_SYMBOL_GPL(cpufreq_frequency_get_table);
 
diff --git a/drivers/cpufreq/ia64-acpi-cpufreq.c b/drivers/cpufreq/ia64-acpi-cpufreq.c
index 53c6ac637e10..a22b5d182e0e 100644
--- a/drivers/cpufreq/ia64-acpi-cpufreq.c
+++ b/drivers/cpufreq/ia64-acpi-cpufreq.c
@@ -332,7 +332,6 @@ acpi_cpufreq_cpu_exit (
 	pr_debug("acpi_cpufreq_cpu_exit\n");
 
 	if (data) {
-		cpufreq_frequency_table_put_attr(policy->cpu);
 		acpi_io_data[policy->cpu] = NULL;
 		acpi_processor_unregister_performance(&data->acpi_data,
 		                                      policy->cpu);
diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c
index b6581abc9207..a3588d61d933 100644
--- a/drivers/cpufreq/loongson2_cpufreq.c
+++ b/drivers/cpufreq/loongson2_cpufreq.c
@@ -104,7 +104,6 @@ static int loongson2_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
 static int loongson2_cpufreq_exit(struct cpufreq_policy *policy)
 {
-	cpufreq_frequency_table_put_attr(policy->cpu);
 	clk_put(policy->clk);
 	return 0;
 }
diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c
index 590f5b66d181..5f69c9aa703c 100644
--- a/drivers/cpufreq/omap-cpufreq.c
+++ b/drivers/cpufreq/omap-cpufreq.c
@@ -143,7 +143,6 @@ fail:
 
 static int omap_cpu_exit(struct cpufreq_policy *policy)
 {
-	cpufreq_frequency_table_put_attr(policy->cpu);
 	freq_table_free();
 	clk_put(policy->clk);
 	return 0;
diff --git a/drivers/cpufreq/pasemi-cpufreq.c b/drivers/cpufreq/pasemi-cpufreq.c
index 0426008380d8..6a2b7d3e85a7 100644
--- a/drivers/cpufreq/pasemi-cpufreq.c
+++ b/drivers/cpufreq/pasemi-cpufreq.c
@@ -234,7 +234,6 @@ static int pas_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 	if (sdcpwr_mapbase)
 		iounmap(sdcpwr_mapbase);
 
-	cpufreq_frequency_table_put_attr(policy->cpu);
 	return 0;
 }
 
diff --git a/drivers/cpufreq/powernow-k6.c b/drivers/cpufreq/powernow-k6.c
index b9a444e358b5..ce27e6c26c94 100644
--- a/drivers/cpufreq/powernow-k6.c
+++ b/drivers/cpufreq/powernow-k6.c
@@ -231,7 +231,6 @@ static int powernow_k6_cpu_exit(struct cpufreq_policy *policy)
 		if (i == max_multiplier)
 			powernow_k6_target(policy, i);
 	}
-	cpufreq_frequency_table_put_attr(policy->cpu);
 	return 0;
 }
 
diff --git a/drivers/cpufreq/powernow-k7.c b/drivers/cpufreq/powernow-k7.c
index 946708a1d745..0e68e0275621 100644
--- a/drivers/cpufreq/powernow-k7.c
+++ b/drivers/cpufreq/powernow-k7.c
@@ -664,8 +664,6 @@ static int powernow_cpu_init(struct cpufreq_policy *policy)
 
 static int powernow_cpu_exit(struct cpufreq_policy *policy)
 {
-	cpufreq_frequency_table_put_attr(policy->cpu);
-
 #ifdef CONFIG_X86_POWERNOW_K7_ACPI
 	if (acpi_processor_perf) {
 		acpi_processor_unregister_performance(acpi_processor_perf, 0);
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index 6684e0342792..27eb2be44de5 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -1164,8 +1164,6 @@ static int powernowk8_cpu_exit(struct cpufreq_policy *pol)
 
 	powernow_k8_cpu_exit_acpi(data);
 
-	cpufreq_frequency_table_put_attr(pol->cpu);
-
 	kfree(data->powernow_table);
 	kfree(data);
 	for_each_cpu(cpu, pol->cpus)
diff --git a/drivers/cpufreq/ppc-corenet-cpufreq.c b/drivers/cpufreq/ppc-corenet-cpufreq.c
index 051000f44ca2..037949d575bd 100644
--- a/drivers/cpufreq/ppc-corenet-cpufreq.c
+++ b/drivers/cpufreq/ppc-corenet-cpufreq.c
@@ -228,7 +228,6 @@ static int __exit corenet_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 	struct cpu_data *data = per_cpu(cpu_data, policy->cpu);
 	unsigned int cpu;
 
-	cpufreq_frequency_table_put_attr(policy->cpu);
 	of_node_put(data->parent);
 	kfree(data->table);
 	kfree(data);
diff --git a/drivers/cpufreq/sh-cpufreq.c b/drivers/cpufreq/sh-cpufreq.c
index 387af12503a6..696170ebd3a3 100644
--- a/drivers/cpufreq/sh-cpufreq.c
+++ b/drivers/cpufreq/sh-cpufreq.c
@@ -143,7 +143,6 @@ static int sh_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 	unsigned int cpu = policy->cpu;
 	struct clk *cpuclk = &per_cpu(sh_cpuclk, cpu);
 
-	cpufreq_frequency_table_put_attr(cpu);
 	clk_put(cpuclk);
 
 	return 0;
diff --git a/drivers/cpufreq/sparc-us2e-cpufreq.c b/drivers/cpufreq/sparc-us2e-cpufreq.c
index 62aa23e219d4..b73feeb666f9 100644
--- a/drivers/cpufreq/sparc-us2e-cpufreq.c
+++ b/drivers/cpufreq/sparc-us2e-cpufreq.c
@@ -301,10 +301,8 @@ static int __init us2e_freq_cpu_init(struct cpufreq_policy *policy)
 
 static int us2e_freq_cpu_exit(struct cpufreq_policy *policy)
 {
-	if (cpufreq_us2e_driver) {
-		cpufreq_frequency_table_put_attr(policy->cpu);
+	if (cpufreq_us2e_driver)
 		us2e_freq_target(policy, 0);
-	}
 
 	return 0;
 }
diff --git a/drivers/cpufreq/sparc-us3-cpufreq.c b/drivers/cpufreq/sparc-us3-cpufreq.c
index 724ffbd7105d..9bb42ba50efa 100644
--- a/drivers/cpufreq/sparc-us3-cpufreq.c
+++ b/drivers/cpufreq/sparc-us3-cpufreq.c
@@ -156,10 +156,8 @@ static int __init us3_freq_cpu_init(struct cpufreq_policy *policy)
 
 static int us3_freq_cpu_exit(struct cpufreq_policy *policy)
 {
-	if (cpufreq_us3_driver) {
-		cpufreq_frequency_table_put_attr(policy->cpu);
+	if (cpufreq_us3_driver)
 		us3_freq_target(policy, 0);
-	}
 
 	return 0;
 }
diff --git a/drivers/cpufreq/speedstep-centrino.c b/drivers/cpufreq/speedstep-centrino.c
index 4e1daca5ce3b..6723f0390f20 100644
--- a/drivers/cpufreq/speedstep-centrino.c
+++ b/drivers/cpufreq/speedstep-centrino.c
@@ -406,8 +406,6 @@ static int centrino_cpu_exit(struct cpufreq_policy *policy)
 	if (!per_cpu(centrino_model, cpu))
 		return -ENODEV;
 
-	cpufreq_frequency_table_put_attr(cpu);
-
 	per_cpu(centrino_model, cpu) = NULL;
 
 	return 0;
diff --git a/drivers/cpufreq/tegra-cpufreq.c b/drivers/cpufreq/tegra-cpufreq.c
index bcfed7761029..63f00598a251 100644
--- a/drivers/cpufreq/tegra-cpufreq.c
+++ b/drivers/cpufreq/tegra-cpufreq.c
@@ -136,7 +136,6 @@ static int tegra_cpu_init(struct cpufreq_policy *policy)
 
 static int tegra_cpu_exit(struct cpufreq_policy *policy)
 {
-	cpufreq_frequency_table_put_attr(policy->cpu);
 	clk_disable_unprepare(cpu_clk);
 	clk_disable_unprepare(emc_clk);
 	return 0;
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 325bab04271b..79341350f498 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -85,6 +85,7 @@ struct cpufreq_policy {
 					 * called, but you're in IRQ context */
 
 	struct cpufreq_real_policy	user_policy;
+	struct cpufreq_frequency_table	*freq_table;
 
 	struct list_head        policy_list;
 	struct kobject		kobj;
@@ -474,7 +475,6 @@ int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 int cpufreq_frequency_table_get_index(struct cpufreq_policy *policy,
 		unsigned int freq);
 
-void cpufreq_frequency_table_update_policy_cpu(struct cpufreq_policy *policy);
 ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf);
 
 #ifdef CONFIG_CPU_FREQ
@@ -501,9 +501,6 @@ struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu);
 /* the following are really really optional */
 extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs;
 extern struct freq_attr *cpufreq_generic_attr[];
-void cpufreq_frequency_table_get_attr(struct cpufreq_frequency_table *table,
-				      unsigned int cpu);
-void cpufreq_frequency_table_put_attr(unsigned int cpu);
 int cpufreq_table_validate_and_show(struct cpufreq_policy *policy,
 				      struct cpufreq_frequency_table *table);
 
@@ -513,7 +510,6 @@ int cpufreq_generic_init(struct cpufreq_policy *policy,
 		unsigned int transition_latency);
 static inline int cpufreq_generic_exit(struct cpufreq_policy *policy)
 {
-	cpufreq_frequency_table_put_attr(policy->cpu);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 979d86fac5e6dbf5c939e9a2a9fe294c9e05e42f Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 10 Mar 2014 14:53:34 +0530
Subject: cpufreq: Remove cpufreq_generic_exit()

cpufreq_generic_exit() is empty now and can be deleted.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/blackfin-cpufreq.c     | 1 -
 drivers/cpufreq/cpufreq-cpu0.c         | 1 -
 drivers/cpufreq/cris-artpec3-cpufreq.c | 1 -
 drivers/cpufreq/cris-etraxfs-cpufreq.c | 1 -
 drivers/cpufreq/davinci-cpufreq.c      | 1 -
 drivers/cpufreq/elanfreq.c             | 1 -
 drivers/cpufreq/exynos-cpufreq.c       | 1 -
 drivers/cpufreq/exynos5440-cpufreq.c   | 1 -
 drivers/cpufreq/imx6q-cpufreq.c        | 1 -
 drivers/cpufreq/kirkwood-cpufreq.c     | 1 -
 drivers/cpufreq/longhaul.c             | 1 -
 drivers/cpufreq/p4-clockmod.c          | 1 -
 drivers/cpufreq/ppc_cbe_cpufreq.c      | 1 -
 drivers/cpufreq/pxa2xx-cpufreq.c       | 1 -
 drivers/cpufreq/pxa3xx-cpufreq.c       | 1 -
 drivers/cpufreq/sc520_freq.c           | 1 -
 drivers/cpufreq/spear-cpufreq.c        | 1 -
 drivers/cpufreq/speedstep-ich.c        | 1 -
 drivers/cpufreq/speedstep-smi.c        | 1 -
 include/linux/cpufreq.h                | 5 -----
 20 files changed, 24 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/cpufreq/blackfin-cpufreq.c b/drivers/cpufreq/blackfin-cpufreq.c
index e9e63fc9c2c9..a9f8e5bd0716 100644
--- a/drivers/cpufreq/blackfin-cpufreq.c
+++ b/drivers/cpufreq/blackfin-cpufreq.c
@@ -195,7 +195,6 @@ static struct cpufreq_driver bfin_driver = {
 	.target_index = bfin_target,
 	.get = bfin_getfreq_khz,
 	.init = __bfin_cpu_init,
-	.exit = cpufreq_generic_exit,
 	.name = "bfin cpufreq",
 	.attr = cpufreq_generic_attr,
 };
diff --git a/drivers/cpufreq/cpufreq-cpu0.c b/drivers/cpufreq/cpufreq-cpu0.c
index 0c12ffc0ebcb..1bf6bbac3e03 100644
--- a/drivers/cpufreq/cpufreq-cpu0.c
+++ b/drivers/cpufreq/cpufreq-cpu0.c
@@ -109,7 +109,6 @@ static struct cpufreq_driver cpu0_cpufreq_driver = {
 	.target_index = cpu0_set_target,
 	.get = cpufreq_generic_get,
 	.init = cpu0_cpufreq_init,
-	.exit = cpufreq_generic_exit,
 	.name = "generic_cpu0",
 	.attr = cpufreq_generic_attr,
 };
diff --git a/drivers/cpufreq/cris-artpec3-cpufreq.c b/drivers/cpufreq/cris-artpec3-cpufreq.c
index 86559040c54c..d4573032cbbc 100644
--- a/drivers/cpufreq/cris-artpec3-cpufreq.c
+++ b/drivers/cpufreq/cris-artpec3-cpufreq.c
@@ -57,7 +57,6 @@ static struct cpufreq_driver cris_freq_driver = {
 	.verify	= cpufreq_generic_frequency_table_verify,
 	.target_index = cris_freq_target,
 	.init	= cris_freq_cpu_init,
-	.exit	= cpufreq_generic_exit,
 	.name	= "cris_freq",
 	.attr	= cpufreq_generic_attr,
 };
diff --git a/drivers/cpufreq/cris-etraxfs-cpufreq.c b/drivers/cpufreq/cris-etraxfs-cpufreq.c
index 26d940d40b1d..13c3361437f7 100644
--- a/drivers/cpufreq/cris-etraxfs-cpufreq.c
+++ b/drivers/cpufreq/cris-etraxfs-cpufreq.c
@@ -57,7 +57,6 @@ static struct cpufreq_driver cris_freq_driver = {
 	.verify = cpufreq_generic_frequency_table_verify,
 	.target_index = cris_freq_target,
 	.init = cris_freq_cpu_init,
-	.exit = cpufreq_generic_exit,
 	.name = "cris_freq",
 	.attr = cpufreq_generic_attr,
 };
diff --git a/drivers/cpufreq/davinci-cpufreq.c b/drivers/cpufreq/davinci-cpufreq.c
index 2cf33848d86e..28a16dc6e02e 100644
--- a/drivers/cpufreq/davinci-cpufreq.c
+++ b/drivers/cpufreq/davinci-cpufreq.c
@@ -125,7 +125,6 @@ static struct cpufreq_driver davinci_driver = {
 	.target_index	= davinci_target,
 	.get		= cpufreq_generic_get,
 	.init		= davinci_cpu_init,
-	.exit		= cpufreq_generic_exit,
 	.name		= "davinci",
 	.attr		= cpufreq_generic_attr,
 };
diff --git a/drivers/cpufreq/elanfreq.c b/drivers/cpufreq/elanfreq.c
index de08acff5101..c987e94708f5 100644
--- a/drivers/cpufreq/elanfreq.c
+++ b/drivers/cpufreq/elanfreq.c
@@ -198,7 +198,6 @@ static struct cpufreq_driver elanfreq_driver = {
 	.verify		= cpufreq_generic_frequency_table_verify,
 	.target_index	= elanfreq_target,
 	.init		= elanfreq_cpu_init,
-	.exit		= cpufreq_generic_exit,
 	.name		= "elanfreq",
 	.attr		= cpufreq_generic_attr,
 };
diff --git a/drivers/cpufreq/exynos-cpufreq.c b/drivers/cpufreq/exynos-cpufreq.c
index 307f02e0e19c..f99cfe24e7bc 100644
--- a/drivers/cpufreq/exynos-cpufreq.c
+++ b/drivers/cpufreq/exynos-cpufreq.c
@@ -145,7 +145,6 @@ static struct cpufreq_driver exynos_driver = {
 	.target_index	= exynos_target,
 	.get		= cpufreq_generic_get,
 	.init		= exynos_cpufreq_cpu_init,
-	.exit		= cpufreq_generic_exit,
 	.name		= "exynos_cpufreq",
 	.attr		= cpufreq_generic_attr,
 #ifdef CONFIG_ARM_EXYNOS_CPU_FREQ_BOOST_SW
diff --git a/drivers/cpufreq/exynos5440-cpufreq.c b/drivers/cpufreq/exynos5440-cpufreq.c
index 49b756015316..7f776aa91e2f 100644
--- a/drivers/cpufreq/exynos5440-cpufreq.c
+++ b/drivers/cpufreq/exynos5440-cpufreq.c
@@ -312,7 +312,6 @@ static struct cpufreq_driver exynos_driver = {
 	.target_index	= exynos_target,
 	.get		= cpufreq_generic_get,
 	.init		= exynos_cpufreq_cpu_init,
-	.exit		= cpufreq_generic_exit,
 	.name		= CPUFREQ_NAME,
 	.attr		= cpufreq_generic_attr,
 };
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index ce69059be1fc..e27fca86fe4f 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -144,7 +144,6 @@ static struct cpufreq_driver imx6q_cpufreq_driver = {
 	.target_index = imx6q_set_target,
 	.get = cpufreq_generic_get,
 	.init = imx6q_cpufreq_init,
-	.exit = cpufreq_generic_exit,
 	.name = "imx6q-cpufreq",
 	.attr = cpufreq_generic_attr,
 };
diff --git a/drivers/cpufreq/kirkwood-cpufreq.c b/drivers/cpufreq/kirkwood-cpufreq.c
index eb7abe345b50..3d114bc5a97a 100644
--- a/drivers/cpufreq/kirkwood-cpufreq.c
+++ b/drivers/cpufreq/kirkwood-cpufreq.c
@@ -102,7 +102,6 @@ static struct cpufreq_driver kirkwood_cpufreq_driver = {
 	.verify	= cpufreq_generic_frequency_table_verify,
 	.target_index = kirkwood_cpufreq_target,
 	.init	= kirkwood_cpufreq_cpu_init,
-	.exit	= cpufreq_generic_exit,
 	.name	= "kirkwood-cpufreq",
 	.attr	= cpufreq_generic_attr,
 };
diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c
index 45bafddfd8ea..7b94da3d2d10 100644
--- a/drivers/cpufreq/longhaul.c
+++ b/drivers/cpufreq/longhaul.c
@@ -913,7 +913,6 @@ static struct cpufreq_driver longhaul_driver = {
 	.target_index = longhaul_target,
 	.get	= longhaul_get,
 	.init	= longhaul_cpu_init,
-	.exit	= cpufreq_generic_exit,
 	.name	= "longhaul",
 	.attr	= cpufreq_generic_attr,
 };
diff --git a/drivers/cpufreq/p4-clockmod.c b/drivers/cpufreq/p4-clockmod.c
index 3d1cba9fd5f9..74f593e70e19 100644
--- a/drivers/cpufreq/p4-clockmod.c
+++ b/drivers/cpufreq/p4-clockmod.c
@@ -237,7 +237,6 @@ static struct cpufreq_driver p4clockmod_driver = {
 	.verify		= cpufreq_generic_frequency_table_verify,
 	.target_index	= cpufreq_p4_target,
 	.init		= cpufreq_p4_cpu_init,
-	.exit		= cpufreq_generic_exit,
 	.get		= cpufreq_p4_get,
 	.name		= "p4-clockmod",
 	.attr		= cpufreq_generic_attr,
diff --git a/drivers/cpufreq/ppc_cbe_cpufreq.c b/drivers/cpufreq/ppc_cbe_cpufreq.c
index e42ca9c31cea..af7b1cabd1e7 100644
--- a/drivers/cpufreq/ppc_cbe_cpufreq.c
+++ b/drivers/cpufreq/ppc_cbe_cpufreq.c
@@ -141,7 +141,6 @@ static struct cpufreq_driver cbe_cpufreq_driver = {
 	.verify		= cpufreq_generic_frequency_table_verify,
 	.target_index	= cbe_cpufreq_target,
 	.init		= cbe_cpufreq_cpu_init,
-	.exit		= cpufreq_generic_exit,
 	.name		= "cbe-cpufreq",
 	.flags		= CPUFREQ_CONST_LOOPS,
 };
diff --git a/drivers/cpufreq/pxa2xx-cpufreq.c b/drivers/cpufreq/pxa2xx-cpufreq.c
index a9195a86b069..e24269ab4e9b 100644
--- a/drivers/cpufreq/pxa2xx-cpufreq.c
+++ b/drivers/cpufreq/pxa2xx-cpufreq.c
@@ -427,7 +427,6 @@ static struct cpufreq_driver pxa_cpufreq_driver = {
 	.verify	= cpufreq_generic_frequency_table_verify,
 	.target_index = pxa_set_target,
 	.init	= pxa_cpufreq_init,
-	.exit	= cpufreq_generic_exit,
 	.get	= pxa_cpufreq_get,
 	.name	= "PXA2xx",
 };
diff --git a/drivers/cpufreq/pxa3xx-cpufreq.c b/drivers/cpufreq/pxa3xx-cpufreq.c
index 3785687e9d70..a01275900389 100644
--- a/drivers/cpufreq/pxa3xx-cpufreq.c
+++ b/drivers/cpufreq/pxa3xx-cpufreq.c
@@ -205,7 +205,6 @@ static struct cpufreq_driver pxa3xx_cpufreq_driver = {
 	.verify		= cpufreq_generic_frequency_table_verify,
 	.target_index	= pxa3xx_cpufreq_set,
 	.init		= pxa3xx_cpufreq_init,
-	.exit		= cpufreq_generic_exit,
 	.get		= pxa3xx_cpufreq_get,
 	.name		= "pxa3xx-cpufreq",
 };
diff --git a/drivers/cpufreq/sc520_freq.c b/drivers/cpufreq/sc520_freq.c
index 6adb354e359c..69371bf0886d 100644
--- a/drivers/cpufreq/sc520_freq.c
+++ b/drivers/cpufreq/sc520_freq.c
@@ -93,7 +93,6 @@ static struct cpufreq_driver sc520_freq_driver = {
 	.verify	= cpufreq_generic_frequency_table_verify,
 	.target_index = sc520_freq_target,
 	.init	= sc520_freq_cpu_init,
-	.exit	= cpufreq_generic_exit,
 	.name	= "sc520_freq",
 	.attr	= cpufreq_generic_attr,
 };
diff --git a/drivers/cpufreq/spear-cpufreq.c b/drivers/cpufreq/spear-cpufreq.c
index 5c86e3fa5593..410b54a9346c 100644
--- a/drivers/cpufreq/spear-cpufreq.c
+++ b/drivers/cpufreq/spear-cpufreq.c
@@ -163,7 +163,6 @@ static struct cpufreq_driver spear_cpufreq_driver = {
 	.target_index	= spear_cpufreq_target,
 	.get		= cpufreq_generic_get,
 	.init		= spear_cpufreq_init,
-	.exit		= cpufreq_generic_exit,
 	.attr		= cpufreq_generic_attr,
 };
 
diff --git a/drivers/cpufreq/speedstep-ich.c b/drivers/cpufreq/speedstep-ich.c
index 7639b2be2a90..394ac159312a 100644
--- a/drivers/cpufreq/speedstep-ich.c
+++ b/drivers/cpufreq/speedstep-ich.c
@@ -311,7 +311,6 @@ static struct cpufreq_driver speedstep_driver = {
 	.verify	= cpufreq_generic_frequency_table_verify,
 	.target_index = speedstep_target,
 	.init	= speedstep_cpu_init,
-	.exit	= cpufreq_generic_exit,
 	.get	= speedstep_get,
 	.attr	= cpufreq_generic_attr,
 };
diff --git a/drivers/cpufreq/speedstep-smi.c b/drivers/cpufreq/speedstep-smi.c
index 998c17b42200..db5d274dc13a 100644
--- a/drivers/cpufreq/speedstep-smi.c
+++ b/drivers/cpufreq/speedstep-smi.c
@@ -280,7 +280,6 @@ static struct cpufreq_driver speedstep_driver = {
 	.verify		= cpufreq_generic_frequency_table_verify,
 	.target_index	= speedstep_target,
 	.init		= speedstep_cpu_init,
-	.exit		= cpufreq_generic_exit,
 	.get		= speedstep_get,
 	.resume		= speedstep_resume,
 	.attr		= cpufreq_generic_attr,
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 79341350f498..31c431e150a7 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -508,9 +508,4 @@ unsigned int cpufreq_generic_get(unsigned int cpu);
 int cpufreq_generic_init(struct cpufreq_policy *policy,
 		struct cpufreq_frequency_table *table,
 		unsigned int transition_latency);
-static inline int cpufreq_generic_exit(struct cpufreq_policy *policy)
-{
-	return 0;
-}
-
 #endif /* _LINUX_CPUFREQ_H */
-- 
cgit v1.2.3


From fec510141088ca1f15d1b79f9f6838810d668b77 Mon Sep 17 00:00:00 2001
From: Laura Abbott <lauraa@codeaurora.org>
Date: Thu, 27 Feb 2014 01:23:43 +0100
Subject: ARM: 7993/1: mm/memblock: add memblock_get_current_limit

Apart from setting the limit of memblock, it's also useful to be able
to get the limit to avoid recalculating it every time. Add the function
to do so.

Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Nicolas Pitre <nico@linaro.org>
Signed-off-by: Laura Abbott <lauraa@codeaurora.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 include/linux/memblock.h | 2 ++
 mm/memblock.c            | 5 +++++
 2 files changed, 7 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 1ef66360f0b0..8a20a51ed42d 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -252,6 +252,8 @@ static inline void memblock_dump_all(void)
 void memblock_set_current_limit(phys_addr_t limit);
 
 
+phys_addr_t memblock_get_current_limit(void);
+
 /*
  * pfn conversion functions
  *
diff --git a/mm/memblock.c b/mm/memblock.c
index 39a31e7f0045..7fe5354e7552 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1407,6 +1407,11 @@ void __init_memblock memblock_set_current_limit(phys_addr_t limit)
 	memblock.current_limit = limit;
 }
 
+phys_addr_t __init_memblock memblock_get_current_limit(void)
+{
+	return memblock.current_limit;
+}
+
 static void __init_memblock memblock_dump(struct memblock_type *type, char *name)
 {
 	unsigned long long base, size;
-- 
cgit v1.2.3


From d88471cb8b17a72b1edf5ab62e1704d78373c066 Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Wed, 9 Jan 2013 18:09:20 -0500
Subject: ftrace: Constify ftrace_text_reserved

Link: http://lkml.kernel.org/r/1357772960-4436-5-git-send-email-sasha.levin@oracle.com

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace.h | 4 ++--
 kernel/trace/ftrace.c  | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 20da0561b868..9212b017bc72 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -299,7 +299,7 @@ extern void
 unregister_ftrace_function_probe_func(char *glob, struct ftrace_probe_ops *ops);
 extern void unregister_ftrace_function_probe_all(char *glob);
 
-extern int ftrace_text_reserved(void *start, void *end);
+extern int ftrace_text_reserved(const void *start, const void *end);
 
 extern int ftrace_nr_registered_ops(void);
 
@@ -552,7 +552,7 @@ static inline __init int unregister_ftrace_command(char *cmd_name)
 {
 	return -EINVAL;
 }
-static inline int ftrace_text_reserved(void *start, void *end)
+static inline int ftrace_text_reserved(const void *start, const void *end)
 {
 	return 0;
 }
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index b4531b228180..1fd4b9479210 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1555,7 +1555,7 @@ unsigned long ftrace_location(unsigned long ip)
  * the function tracer. It checks the ftrace internal tables to
  * determine if the address belongs or not.
  */
-int ftrace_text_reserved(void *start, void *end)
+int ftrace_text_reserved(const void *start, const void *end)
 {
 	unsigned long ret;
 
-- 
cgit v1.2.3


From 5083fd7bdfe6760577235a724cf6dccae13652c2 Mon Sep 17 00:00:00 2001
From: Johan Hovold <jhovold@gmail.com>
Date: Wed, 12 Mar 2014 19:09:38 +0100
Subject: USB: serial: make bulk_out_size a lower limit

Drivers are allowed to override the default bulk-out buffer size
(endpoint maximum packet size) in order to increase throughput, but it
does not make much sense to allow buffers smaller than the default.

Note that this is already how bulk_in_size is defined.

Signed-off-by: Johan Hovold <jhovold@gmail.com>
Signed-off-by: Greg Kroah-Hartman <greg@kroah.com>
---
 drivers/usb/serial/usb-serial.c | 5 ++---
 include/linux/usb/serial.h      | 3 ++-
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index 7c9dc28640bb..c68fc9fb7598 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -923,9 +923,8 @@ static int usb_serial_probe(struct usb_interface *interface,
 		port = serial->port[i];
 		if (kfifo_alloc(&port->write_fifo, PAGE_SIZE, GFP_KERNEL))
 			goto probe_error;
-		buffer_size = serial->type->bulk_out_size;
-		if (!buffer_size)
-			buffer_size = usb_endpoint_maxp(endpoint);
+		buffer_size = max_t(int, serial->type->bulk_out_size,
+						usb_endpoint_maxp(endpoint));
 		port->bulk_out_size = buffer_size;
 		port->bulk_out_endpointAddress = endpoint->bEndpointAddress;
 
diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h
index 704a1ab8240c..9bb547c7bce7 100644
--- a/include/linux/usb/serial.h
+++ b/include/linux/usb/serial.h
@@ -190,7 +190,8 @@ static inline void usb_set_serial_data(struct usb_serial *serial, void *data)
  * @num_ports: the number of different ports this device will have.
  * @bulk_in_size: minimum number of bytes to allocate for bulk-in buffer
  *	(0 = end-point size)
- * @bulk_out_size: bytes to allocate for bulk-out buffer (0 = end-point size)
+ * @bulk_out_size: minimum number of bytes to allocate for bulk-out buffer
+ *	(0 = end-point size)
  * @calc_num_ports: pointer to a function to determine how many ports this
  *	device has dynamically.  It will be called after the probe()
  *	callback is called, but before attach()
-- 
cgit v1.2.3


From 6ee51a4e866bbb0921180b457ed16cd172859346 Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Wed, 12 Mar 2014 12:00:37 +0200
Subject: mlx4: Adjust QP1 multiplexing for RoCE/SRIOV

This requires the following modifications:
1. Fix build_mlx4_header to properly fill in the ETH fields
2. Adjust mux and demux QP1 flow to support RoCE.

This commit still assumes only one GID per slave for RoCE.
The commit enabling multiple GIDs is a subsequent commit, and
is done separately because of its complexity.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/cm.c           |  8 +++--
 drivers/infiniband/hw/mlx4/mad.c          | 50 +++++++++++++++++++++++++++----
 drivers/infiniband/hw/mlx4/qp.c           | 29 ++++++++++--------
 drivers/net/ethernet/mellanox/mlx4/mlx4.h |  5 ++++
 drivers/net/ethernet/mellanox/mlx4/port.c | 34 +++++++++++++++++++++
 include/linux/mlx4/device.h               |  4 +++
 6 files changed, 110 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx4/cm.c b/drivers/infiniband/hw/mlx4/cm.c
index d1f5f1dd77b0..b8d911543783 100644
--- a/drivers/infiniband/hw/mlx4/cm.c
+++ b/drivers/infiniband/hw/mlx4/cm.c
@@ -315,7 +315,7 @@ int mlx4_ib_multiplex_cm_handler(struct ib_device *ibdev, int port, int slave_id
 }
 
 int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave,
-							     struct ib_mad *mad)
+			     struct ib_mad *mad)
 {
 	u32 pv_cm_id;
 	struct id_map_entry *id;
@@ -323,6 +323,9 @@ int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave,
 	if (mad->mad_hdr.attr_id == CM_REQ_ATTR_ID) {
 		union ib_gid gid;
 
+		if (!slave)
+			return 0;
+
 		gid = gid_from_req_msg(ibdev, mad);
 		*slave = mlx4_ib_find_real_gid(ibdev, port, gid.global.interface_id);
 		if (*slave < 0) {
@@ -341,7 +344,8 @@ int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave,
 		return -ENOENT;
 	}
 
-	*slave = id->slave_id;
+	if (slave)
+		*slave = id->slave_id;
 	set_remote_comm_id(mad, id->sl_cm_id);
 
 	if (mad->mad_hdr.attr_id == CM_DREQ_ATTR_ID)
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index f2a3f48107e7..c2e9879a5a34 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -467,6 +467,7 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
 	int ret = 0;
 	u16 tun_pkey_ix;
 	u16 cached_pkey;
+	u8 is_eth = dev->dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH;
 
 	if (dest_qpt > IB_QPT_GSI)
 		return -EINVAL;
@@ -509,6 +510,12 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
 	 * The driver will set the force loopback bit in post_send */
 	memset(&attr, 0, sizeof attr);
 	attr.port_num = port;
+	if (is_eth) {
+		ret = mlx4_get_roce_gid_from_slave(dev->dev, port, slave, attr.grh.dgid.raw);
+		if (ret)
+			return ret;
+		attr.ah_flags = IB_AH_GRH;
+	}
 	ah = ib_create_ah(tun_ctx->pd, &attr);
 	if (IS_ERR(ah))
 		return -ENOMEM;
@@ -580,6 +587,41 @@ static int mlx4_ib_demux_mad(struct ib_device *ibdev, u8 port,
 	int err;
 	int slave;
 	u8 *slave_id;
+	int is_eth = 0;
+
+	if (rdma_port_get_link_layer(ibdev, port) == IB_LINK_LAYER_INFINIBAND)
+		is_eth = 0;
+	else
+		is_eth = 1;
+
+	if (is_eth) {
+		if (!(wc->wc_flags & IB_WC_GRH)) {
+			mlx4_ib_warn(ibdev, "RoCE grh not present.\n");
+			return -EINVAL;
+		}
+		if (mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_CM) {
+			mlx4_ib_warn(ibdev, "RoCE mgmt class is not CM\n");
+			return -EINVAL;
+		}
+		if (mlx4_get_slave_from_roce_gid(dev->dev, port, grh->dgid.raw, &slave)) {
+			mlx4_ib_warn(ibdev, "failed matching grh\n");
+			return -ENOENT;
+		}
+		if (slave >= dev->dev->caps.sqp_demux) {
+			mlx4_ib_warn(ibdev, "slave id: %d is bigger than allowed:%d\n",
+				     slave, dev->dev->caps.sqp_demux);
+			return -ENOENT;
+		}
+
+		if (mlx4_ib_demux_cm_handler(ibdev, port, NULL, mad))
+			return 0;
+
+		err = mlx4_ib_send_to_slave(dev, slave, port, wc->qp->qp_type, wc, grh, mad);
+		if (err)
+			pr_debug("failed sending to slave %d via tunnel qp (%d)\n",
+				 slave, err);
+		return 0;
+	}
 
 	/* Initially assume that this mad is for us */
 	slave = mlx4_master_func_num(dev->dev);
@@ -1260,12 +1302,8 @@ static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc
 	memcpy(&ah.av, &tunnel->hdr.av, sizeof (struct mlx4_av));
 	ah.ibah.device = ctx->ib_dev;
 	mlx4_ib_query_ah(&ah.ibah, &ah_attr);
-	if ((ah_attr.ah_flags & IB_AH_GRH) &&
-	    (ah_attr.grh.sgid_index != slave)) {
-		mlx4_ib_warn(ctx->ib_dev, "slave:%d accessed invalid sgid_index:%d\n",
-			     slave, ah_attr.grh.sgid_index);
-		return;
-	}
+	if (ah_attr.ah_flags & IB_AH_GRH)
+		ah_attr.grh.sgid_index = slave;
 
 	mlx4_ib_send_to_wire(dev, slave, ctx->port,
 			     is_proxy_qp0(dev, wc->src_qp, slave) ?
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index d8f4d1fe8494..c6ef2e7e3045 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -1842,9 +1842,9 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
 {
 	struct ib_device *ib_dev = sqp->qp.ibqp.device;
 	struct mlx4_wqe_mlx_seg *mlx = wqe;
+	struct mlx4_wqe_ctrl_seg *ctrl = wqe;
 	struct mlx4_wqe_inline_seg *inl = wqe + sizeof *mlx;
 	struct mlx4_ib_ah *ah = to_mah(wr->wr.ud.ah);
-	struct net_device *ndev;
 	union ib_gid sgid;
 	u16 pkey;
 	int send_size;
@@ -1868,12 +1868,11 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
 			/* When multi-function is enabled, the ib_core gid
 			 * indexes don't necessarily match the hw ones, so
 			 * we must use our own cache */
-			sgid.global.subnet_prefix =
-				to_mdev(ib_dev)->sriov.demux[sqp->qp.port - 1].
-				subnet_prefix;
-			sgid.global.interface_id =
-				to_mdev(ib_dev)->sriov.demux[sqp->qp.port - 1].
-				guid_cache[ah->av.ib.gid_index];
+			err = mlx4_get_roce_gid_from_slave(to_mdev(ib_dev)->dev,
+							   be32_to_cpu(ah->av.ib.port_pd) >> 24,
+							   ah->av.ib.gid_index, &sgid.raw[0]);
+			if (err)
+				return err;
 		} else  {
 			err = ib_get_cached_gid(ib_dev,
 						be32_to_cpu(ah->av.ib.port_pd) >> 24,
@@ -1902,6 +1901,9 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
 		sqp->ud_header.grh.flow_label    =
 			ah->av.ib.sl_tclass_flowlabel & cpu_to_be32(0xfffff);
 		sqp->ud_header.grh.hop_limit     = ah->av.ib.hop_limit;
+		if (is_eth)
+			memcpy(sqp->ud_header.grh.source_gid.raw, sgid.raw, 16);
+		else {
 		if (mlx4_is_mfunc(to_mdev(ib_dev)->dev)) {
 			/* When multi-function is enabled, the ib_core gid
 			 * indexes don't necessarily match the hw ones, so
@@ -1917,6 +1919,7 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
 					  be32_to_cpu(ah->av.ib.port_pd) >> 24,
 					  ah->av.ib.gid_index,
 					  &sqp->ud_header.grh.source_gid);
+		}
 		memcpy(sqp->ud_header.grh.destination_gid.raw,
 		       ah->av.ib.dgid, 16);
 	}
@@ -1948,17 +1951,19 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
 	}
 
 	if (is_eth) {
-		u8 *smac;
+		u8 smac[6];
+		struct in6_addr in6;
+
 		u16 pcp = (be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 29) << 13;
 
 		mlx->sched_prio = cpu_to_be16(pcp);
 
 		memcpy(sqp->ud_header.eth.dmac_h, ah->av.eth.mac, 6);
 		/* FIXME: cache smac value? */
-		ndev = to_mdev(sqp->qp.ibqp.device)->iboe.netdevs[sqp->qp.port - 1];
-		if (!ndev)
-			return -ENODEV;
-		smac = ndev->dev_addr;
+		memcpy(&ctrl->srcrb_flags16[0], ah->av.eth.mac, 2);
+		memcpy(&ctrl->imm, ah->av.eth.mac + 2, 4);
+		memcpy(&in6, sgid.raw, sizeof(in6));
+		rdma_get_ll_mac(&in6, smac);
 		memcpy(sqp->ud_header.eth.smac_h, smac, 6);
 		if (!memcmp(sqp->ud_header.eth.smac_h, sqp->ud_header.eth.dmac_h, 6))
 			mlx->flags |= cpu_to_be32(MLX4_WQE_CTRL_FORCE_LOOPBACK);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 7aec6c833973..da829f4ef938 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -788,6 +788,10 @@ enum {
 	MLX4_USE_RR	= 1,
 };
 
+struct mlx4_roce_gid_entry {
+	u8 raw[16];
+};
+
 struct mlx4_priv {
 	struct mlx4_dev		dev;
 
@@ -834,6 +838,7 @@ struct mlx4_priv {
 	int			fs_hash_mode;
 	u8 virt2phys_pkey[MLX4_MFUNC_MAX][MLX4_MAX_PORTS][MLX4_MAX_PORT_PKEYS];
 	__be64			slave_node_guids[MLX4_MFUNC_MAX];
+	struct mlx4_roce_gid_entry roce_gids[MLX4_MAX_PORTS][MLX4_ROCE_MAX_GIDS];
 
 	atomic_t		opreq_count;
 	struct work_struct	opreq_task;
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index a58bcbf1b806..9c063d6122b3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -927,3 +927,37 @@ void mlx4_set_stats_bitmap(struct mlx4_dev *dev, u64 *stats_bitmap)
 		*stats_bitmap |= MLX4_STATS_ERROR_COUNTERS_MASK;
 }
 EXPORT_SYMBOL(mlx4_set_stats_bitmap);
+
+int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid, int *slave_id)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int i, found_ix = -1;
+
+	if (!mlx4_is_mfunc(dev))
+		return -EINVAL;
+
+	for (i = 0; i < MLX4_ROCE_MAX_GIDS; i++) {
+		if (!memcmp(priv->roce_gids[port - 1][i].raw, gid, 16)) {
+			found_ix = i;
+			break;
+		}
+	}
+
+	if (found_ix >= 0)
+		*slave_id = found_ix;
+
+	return (found_ix >= 0) ? 0 : -EINVAL;
+}
+EXPORT_SYMBOL(mlx4_get_slave_from_roce_gid);
+
+int mlx4_get_roce_gid_from_slave(struct mlx4_dev *dev, int port, int slave_id, u8 *gid)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	if (!mlx4_is_master(dev))
+		return -EINVAL;
+
+	memcpy(gid, priv->roce_gids[port - 1][slave_id].raw, 16);
+	return 0;
+}
+EXPORT_SYMBOL(mlx4_get_roce_gid_from_slave);
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 5edd2c68274d..fbe6cda00ba7 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -48,6 +48,8 @@
 #define MSIX_LEGACY_SZ		4
 #define MIN_MSIX_P_PORT		5
 
+#define MLX4_ROCE_MAX_GIDS	128
+
 enum {
 	MLX4_FLAG_MSI_X		= 1 << 0,
 	MLX4_FLAG_OLD_PORT_CMDS	= 1 << 1,
@@ -1182,6 +1184,8 @@ int set_and_calc_slave_port_state(struct mlx4_dev *dev, int slave, u8 port, int
 
 void mlx4_put_slave_node_guid(struct mlx4_dev *dev, int slave, __be64 guid);
 __be64 mlx4_get_slave_node_guid(struct mlx4_dev *dev, int slave);
+int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid, int *slave_id);
+int mlx4_get_roce_gid_from_slave(struct mlx4_dev *dev, int port, int slave_id, u8 *gid);
 
 int mlx4_FLOW_STEERING_IB_UC_QP_RANGE(struct mlx4_dev *dev, u32 min_range_qpn,
 				      u32 max_range_qpn);
-- 
cgit v1.2.3


From 9cd593529c8652785bc9962acc79b6b176741f99 Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Wed, 12 Mar 2014 12:00:38 +0200
Subject: mlx4_core: For RoCE, allow slaves to set the GID entry at that
 slave's index

For IB transport, the host determines the slave GIDs. For ETH (RoCE),
however, the slave's GID is determined by the IP address that the slave
itself assigns to the ETH device used by RoCE.

In this case, the slave must be able to write its GIDs to the HCA gid table
(at the GID indices that slave "owns").

This commit adds processing for the SET_PORT_GID_TABLE opcode modifier
for the SET_PORT command wrapper (so that slaves may modify their GIDS
for RoCE).

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/port.c | 33 ++++++++++++++++++++++++++++---
 include/linux/mlx4/device.h               |  7 +++++--
 2 files changed, 35 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 9c063d6122b3..591740b06043 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -505,6 +505,7 @@ int mlx4_get_port_ib_caps(struct mlx4_dev *dev, u8 port, __be32 *caps)
 	mlx4_free_cmd_mailbox(dev, outmailbox);
 	return err;
 }
+static struct mlx4_roce_gid_entry zgid_entry;
 
 static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
 				u8 op_mod, struct mlx4_cmd_mailbox *inbox)
@@ -515,6 +516,7 @@ static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
 	struct mlx4_slave_state *slave_st = &master->slave_state[slave];
 	struct mlx4_set_port_rqp_calc_context *qpn_context;
 	struct mlx4_set_port_general_context *gen_context;
+	struct mlx4_roce_gid_entry *gid_entry;
 	int reset_qkey_viols;
 	int port;
 	int is_eth;
@@ -535,7 +537,8 @@ static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
 	/* Slaves cannot perform SET_PORT operations except changing MTU */
 	if (is_eth) {
 		if (slave != dev->caps.function &&
-		    in_modifier != MLX4_SET_PORT_GENERAL) {
+		    in_modifier != MLX4_SET_PORT_GENERAL &&
+		    in_modifier != MLX4_SET_PORT_GID_TABLE) {
 			mlx4_warn(dev, "denying SET_PORT for slave:%d\n",
 					slave);
 			return -EINVAL;
@@ -581,6 +584,28 @@ static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
 
 			gen_context->mtu = cpu_to_be16(master->max_mtu[port]);
 			break;
+		case MLX4_SET_PORT_GID_TABLE:
+			gid_entry = (struct mlx4_roce_gid_entry *)(inbox->buf);
+			/* check that do not have duplicates */
+			if (memcmp(gid_entry->raw, zgid_entry.raw, 16)) {
+				for (i = 0; i < MLX4_ROCE_MAX_GIDS; i++) {
+					if (slave != i &&
+					    !memcmp(gid_entry->raw, priv->roce_gids[port - 1][i].raw, 16)) {
+						mlx4_warn(dev, "requested gid entry for slave:%d "
+							  "is a duplicate of slave %d\n",
+							  slave, i);
+						return -EEXIST;
+					}
+				}
+			}
+			/* insert slave GID at proper index */
+			memcpy(priv->roce_gids[port - 1][slave].raw, gid_entry->raw, 16);
+			/* rewrite roce port gids table to FW */
+			for (i = 0; i < MLX4_ROCE_MAX_GIDS; i++) {
+				memcpy(gid_entry->raw, priv->roce_gids[port - 1][i].raw, 16);
+				gid_entry++;
+			}
+			break;
 		}
 		return mlx4_cmd(dev, inbox->dma, in_mod, op_mod,
 				MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B,
@@ -928,7 +953,8 @@ void mlx4_set_stats_bitmap(struct mlx4_dev *dev, u64 *stats_bitmap)
 }
 EXPORT_SYMBOL(mlx4_set_stats_bitmap);
 
-int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid, int *slave_id)
+int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid,
+				 int *slave_id)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int i, found_ix = -1;
@@ -950,7 +976,8 @@ int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid, int *s
 }
 EXPORT_SYMBOL(mlx4_get_slave_from_roce_gid);
 
-int mlx4_get_roce_gid_from_slave(struct mlx4_dev *dev, int port, int slave_id, u8 *gid)
+int mlx4_get_roce_gid_from_slave(struct mlx4_dev *dev, int port, int slave_id,
+				 u8 *gid)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index fbe6cda00ba7..e4853650679d 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1184,8 +1184,11 @@ int set_and_calc_slave_port_state(struct mlx4_dev *dev, int slave, u8 port, int
 
 void mlx4_put_slave_node_guid(struct mlx4_dev *dev, int slave, __be64 guid);
 __be64 mlx4_get_slave_node_guid(struct mlx4_dev *dev, int slave);
-int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid, int *slave_id);
-int mlx4_get_roce_gid_from_slave(struct mlx4_dev *dev, int port, int slave_id, u8 *gid);
+
+int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid,
+				 int *slave_id);
+int mlx4_get_roce_gid_from_slave(struct mlx4_dev *dev, int port, int slave_id,
+				 u8 *gid);
 
 int mlx4_FLOW_STEERING_IB_UC_QP_RANGE(struct mlx4_dev *dev, u32 min_range_qpn,
 				      u32 max_range_qpn);
-- 
cgit v1.2.3


From b6ffaeffaea4d92f05f5ba1ef54df407cb7c8517 Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Wed, 12 Mar 2014 12:00:39 +0200
Subject: mlx4: In RoCE allow guests to have multiple GIDS

The GIDs are statically distributed, as follows:
PF: gets 16 GIDs
VFs:  Remaining GIDS are divided evenly between VFs activated by the driver.
      If the division is not even, lower-numbered VFs get an extra GID.

For an IB interface, the number of gids per guest remains as before: one gid per guest.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/mad.c                   |  34 +++++-
 drivers/net/ethernet/mellanox/mlx4/fw.c            |   5 +-
 drivers/net/ethernet/mellanox/mlx4/main.c          |   6 +-
 drivers/net/ethernet/mellanox/mlx4/mlx4.h          |   3 +
 drivers/net/ethernet/mellanox/mlx4/port.c          | 117 +++++++++++++++++----
 .../net/ethernet/mellanox/mlx4/resource_tracker.c  |  64 ++++++++---
 include/linux/mlx4/device.h                        |   1 +
 7 files changed, 192 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index c2e9879a5a34..c5bca0f0da4a 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -511,9 +511,7 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
 	memset(&attr, 0, sizeof attr);
 	attr.port_num = port;
 	if (is_eth) {
-		ret = mlx4_get_roce_gid_from_slave(dev->dev, port, slave, attr.grh.dgid.raw);
-		if (ret)
-			return ret;
+		memcpy(&attr.grh.dgid.raw[0], &grh->dgid.raw[0], 16);
 		attr.ah_flags = IB_AH_GRH;
 	}
 	ah = ib_create_ah(tun_ctx->pd, &attr);
@@ -1216,6 +1214,34 @@ out:
 	return ret;
 }
 
+static int get_slave_base_gid_ix(struct mlx4_ib_dev *dev, int slave, int port)
+{
+	int gids;
+	int vfs;
+
+	if (rdma_port_get_link_layer(&dev->ib_dev, port) == IB_LINK_LAYER_INFINIBAND)
+		return slave;
+
+	gids = MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS;
+	vfs = dev->dev->num_vfs;
+
+	if (slave == 0)
+		return 0;
+	if (slave <= gids % vfs)
+		return MLX4_ROCE_PF_GIDS + ((gids / vfs) + 1) * (slave - 1);
+
+	return MLX4_ROCE_PF_GIDS + (gids % vfs) + ((gids / vfs) * (slave - 1));
+}
+
+static void fill_in_real_sgid_index(struct mlx4_ib_dev *dev, int slave, int port,
+				    struct ib_ah_attr *ah_attr)
+{
+	if (rdma_port_get_link_layer(&dev->ib_dev, port) == IB_LINK_LAYER_INFINIBAND)
+		ah_attr->grh.sgid_index = slave;
+	else
+		ah_attr->grh.sgid_index += get_slave_base_gid_ix(dev, slave, port);
+}
+
 static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc *wc)
 {
 	struct mlx4_ib_dev *dev = to_mdev(ctx->ib_dev);
@@ -1303,7 +1329,7 @@ static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc
 	ah.ibah.device = ctx->ib_dev;
 	mlx4_ib_query_ah(&ah.ibah, &ah_attr);
 	if (ah_attr.ah_flags & IB_AH_GRH)
-		ah_attr.grh.sgid_index = slave;
+		fill_in_real_sgid_index(dev, slave, ctx->port, &ah_attr);
 
 	mlx4_ib_send_to_wire(dev, slave, ctx->port,
 			     is_proxy_qp0(dev, wc->src_qp, slave) ?
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 9cdf452140da..6e1ee2170a39 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -934,7 +934,10 @@ int mlx4_QUERY_PORT_wrapper(struct mlx4_dev *dev, int slave,
 		MLX4_PUT(outbox->buf, port_type,
 			 QUERY_PORT_SUPPORTED_TYPE_OFFSET);
 
-		short_field = 1; /* slave max gids */
+		if (dev->caps.port_type[vhcr->in_modifier] == MLX4_PORT_TYPE_ETH)
+			short_field = mlx4_get_slave_num_gids(dev, slave);
+		else
+			short_field = 1; /* slave max gids */
 		MLX4_PUT(outbox->buf, short_field,
 			 QUERY_PORT_CUR_MAX_GID_OFFSET);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 979ea4364efb..4c441aa83016 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -1462,7 +1462,11 @@ static void mlx4_parav_master_pf_caps(struct mlx4_dev *dev)
 	int i;
 
 	for (i = 1; i <= dev->caps.num_ports; i++) {
-		dev->caps.gid_table_len[i] = 1;
+		if (dev->caps.port_type[i] == MLX4_PORT_TYPE_ETH)
+			dev->caps.gid_table_len[i] =
+				mlx4_get_slave_num_gids(dev, 0);
+		else
+			dev->caps.gid_table_len[i] = 1;
 		dev->caps.pkey_table_len[i] =
 			dev->phys_caps.pkey_phys_table_len[i] - 1;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index da829f4ef938..6ba38c98c492 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -1287,4 +1287,7 @@ void mlx4_vf_immed_vlan_work_handler(struct work_struct *_work);
 
 void mlx4_init_quotas(struct mlx4_dev *dev);
 
+int mlx4_get_slave_num_gids(struct mlx4_dev *dev, int slave);
+int mlx4_get_base_gid_ix(struct mlx4_dev *dev, int slave);
+
 #endif /* MLX4_H */
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 591740b06043..ece328166e94 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -507,6 +507,31 @@ int mlx4_get_port_ib_caps(struct mlx4_dev *dev, u8 port, __be32 *caps)
 }
 static struct mlx4_roce_gid_entry zgid_entry;
 
+int mlx4_get_slave_num_gids(struct mlx4_dev *dev, int slave)
+{
+	if (slave == 0)
+		return MLX4_ROCE_PF_GIDS;
+	if (slave <= ((MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS) % dev->num_vfs))
+		return ((MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS) / dev->num_vfs) + 1;
+	return (MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS) / dev->num_vfs;
+}
+
+int mlx4_get_base_gid_ix(struct mlx4_dev *dev, int slave)
+{
+	int gids;
+	int vfs;
+
+	gids = MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS;
+	vfs = dev->num_vfs;
+
+	if (slave == 0)
+		return 0;
+	if (slave <= gids % vfs)
+		return MLX4_ROCE_PF_GIDS + ((gids / vfs) + 1) * (slave - 1);
+
+	return MLX4_ROCE_PF_GIDS + (gids % vfs) + ((gids / vfs) * (slave - 1));
+}
+
 static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
 				u8 op_mod, struct mlx4_cmd_mailbox *inbox)
 {
@@ -516,15 +541,18 @@ static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
 	struct mlx4_slave_state *slave_st = &master->slave_state[slave];
 	struct mlx4_set_port_rqp_calc_context *qpn_context;
 	struct mlx4_set_port_general_context *gen_context;
-	struct mlx4_roce_gid_entry *gid_entry;
+	struct mlx4_roce_gid_entry *gid_entry_tbl, *gid_entry_mbox, *gid_entry_mb1;
 	int reset_qkey_viols;
 	int port;
 	int is_eth;
+	int num_gids;
+	int base;
 	u32 in_modifier;
 	u32 promisc;
 	u16 mtu, prev_mtu;
 	int err;
-	int i;
+	int i, j;
+	int offset;
 	__be32 agg_cap_mask;
 	__be32 slave_cap_mask;
 	__be32 new_cap_mask;
@@ -585,26 +613,65 @@ static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
 			gen_context->mtu = cpu_to_be16(master->max_mtu[port]);
 			break;
 		case MLX4_SET_PORT_GID_TABLE:
-			gid_entry = (struct mlx4_roce_gid_entry *)(inbox->buf);
-			/* check that do not have duplicates */
-			if (memcmp(gid_entry->raw, zgid_entry.raw, 16)) {
-				for (i = 0; i < MLX4_ROCE_MAX_GIDS; i++) {
-					if (slave != i &&
-					    !memcmp(gid_entry->raw, priv->roce_gids[port - 1][i].raw, 16)) {
-						mlx4_warn(dev, "requested gid entry for slave:%d "
-							  "is a duplicate of slave %d\n",
-							  slave, i);
-						return -EEXIST;
+			/* change to MULTIPLE entries: number of guest's gids
+			 * need a FOR-loop here over number of gids the guest has.
+			 * 1. Check no duplicates in gids passed by slave
+			 */
+			num_gids = mlx4_get_slave_num_gids(dev, slave);
+			base = mlx4_get_base_gid_ix(dev, slave);
+			gid_entry_mbox = (struct mlx4_roce_gid_entry *)(inbox->buf);
+			for (i = 0; i < num_gids; gid_entry_mbox++, i++) {
+				if (!memcmp(gid_entry_mbox->raw, zgid_entry.raw,
+					    sizeof(zgid_entry)))
+					continue;
+				gid_entry_mb1 = gid_entry_mbox + 1;
+				for (j = i + 1; j < num_gids; gid_entry_mb1++, j++) {
+					if (!memcmp(gid_entry_mb1->raw,
+						    zgid_entry.raw, sizeof(zgid_entry)))
+						continue;
+					if (!memcmp(gid_entry_mb1->raw, gid_entry_mbox->raw,
+						    sizeof(gid_entry_mbox->raw))) {
+						/* found duplicate */
+						return -EINVAL;
 					}
 				}
 			}
-			/* insert slave GID at proper index */
-			memcpy(priv->roce_gids[port - 1][slave].raw, gid_entry->raw, 16);
-			/* rewrite roce port gids table to FW */
+
+			/* 2. Check that do not have duplicates in OTHER
+			 *    entries in the port GID table
+			 */
 			for (i = 0; i < MLX4_ROCE_MAX_GIDS; i++) {
-				memcpy(gid_entry->raw, priv->roce_gids[port - 1][i].raw, 16);
-				gid_entry++;
+				if (i >= base && i < base + num_gids)
+					continue; /* don't compare to slave's current gids */
+				gid_entry_tbl = &priv->roce_gids[port - 1][i];
+				if (!memcmp(gid_entry_tbl->raw, zgid_entry.raw, sizeof(zgid_entry)))
+					continue;
+				gid_entry_mbox = (struct mlx4_roce_gid_entry *)(inbox->buf);
+				for (j = 0; j < num_gids; gid_entry_mbox++, j++) {
+					if (!memcmp(gid_entry_mbox->raw, zgid_entry.raw,
+						    sizeof(zgid_entry)))
+						continue;
+					if (!memcmp(gid_entry_mbox->raw, gid_entry_tbl->raw,
+						    sizeof(gid_entry_tbl->raw))) {
+						/* found duplicate */
+						mlx4_warn(dev, "requested gid entry for slave:%d "
+							  "is a duplicate of gid at index %d\n",
+							  slave, i);
+						return -EINVAL;
+					}
+				}
 			}
+
+			/* insert slave GIDs with memcpy, starting at slave's base index */
+			gid_entry_mbox = (struct mlx4_roce_gid_entry *)(inbox->buf);
+			for (i = 0, offset = base; i < num_gids; gid_entry_mbox++, offset++, i++)
+				memcpy(priv->roce_gids[port - 1][offset].raw, gid_entry_mbox->raw, 16);
+
+			/* Now, copy roce port gids table to current mailbox for passing to FW */
+			gid_entry_mbox = (struct mlx4_roce_gid_entry *)(inbox->buf);
+			for (i = 0; i < MLX4_ROCE_MAX_GIDS; gid_entry_mbox++, i++)
+				memcpy(gid_entry_mbox->raw, priv->roce_gids[port - 1][i].raw, 16);
+
 			break;
 		}
 		return mlx4_cmd(dev, inbox->dma, in_mod, op_mod,
@@ -958,6 +1025,7 @@ int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid,
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int i, found_ix = -1;
+	int vf_gids = MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS;
 
 	if (!mlx4_is_mfunc(dev))
 		return -EINVAL;
@@ -969,8 +1037,19 @@ int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid,
 		}
 	}
 
-	if (found_ix >= 0)
-		*slave_id = found_ix;
+	if (found_ix >= 0) {
+		if (found_ix < MLX4_ROCE_PF_GIDS)
+			*slave_id = 0;
+		else if (found_ix < MLX4_ROCE_PF_GIDS + (vf_gids % dev->num_vfs) *
+			 (vf_gids / dev->num_vfs + 1))
+			*slave_id = ((found_ix - MLX4_ROCE_PF_GIDS) /
+				     (vf_gids / dev->num_vfs + 1)) + 1;
+		else
+			*slave_id =
+			((found_ix - MLX4_ROCE_PF_GIDS -
+			  ((vf_gids % dev->num_vfs) * ((vf_gids / dev->num_vfs + 1)))) /
+			 (vf_gids / dev->num_vfs)) + vf_gids % dev->num_vfs + 1;
+	}
 
 	return (found_ix >= 0) ? 0 : -EINVAL;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 57428a0cb9dd..1c3634eab5e1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -219,6 +219,11 @@ struct res_fs_rule {
 	int			qpn;
 };
 
+static int mlx4_is_eth(struct mlx4_dev *dev, int port)
+{
+	return dev->caps.port_mask[port] == MLX4_PORT_TYPE_IB ? 0 : 1;
+}
+
 static void *res_tracker_lookup(struct rb_root *root, u64 res_id)
 {
 	struct rb_node *node = root->rb_node;
@@ -600,15 +605,34 @@ static void update_gid(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *inbox,
 	struct mlx4_qp_context	*qp_ctx = inbox->buf + 8;
 	enum mlx4_qp_optpar	optpar = be32_to_cpu(*(__be32 *) inbox->buf);
 	u32			ts = (be32_to_cpu(qp_ctx->flags) >> 16) & 0xff;
+	int port;
 
-	if (MLX4_QP_ST_UD == ts)
-		qp_ctx->pri_path.mgid_index = 0x80 | slave;
-
-	if (MLX4_QP_ST_RC == ts || MLX4_QP_ST_UC == ts) {
-		if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH)
-			qp_ctx->pri_path.mgid_index = slave & 0x7F;
-		if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH)
-			qp_ctx->alt_path.mgid_index = slave & 0x7F;
+	if (MLX4_QP_ST_UD == ts) {
+		port = (qp_ctx->pri_path.sched_queue >> 6 & 1) + 1;
+		if (mlx4_is_eth(dev, port))
+			qp_ctx->pri_path.mgid_index = mlx4_get_base_gid_ix(dev, slave) | 0x80;
+		else
+			qp_ctx->pri_path.mgid_index = slave | 0x80;
+
+	} else if (MLX4_QP_ST_RC == ts || MLX4_QP_ST_XRC == ts || MLX4_QP_ST_UC == ts) {
+		if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH) {
+			port = (qp_ctx->pri_path.sched_queue >> 6 & 1) + 1;
+			if (mlx4_is_eth(dev, port)) {
+				qp_ctx->pri_path.mgid_index += mlx4_get_base_gid_ix(dev, slave);
+				qp_ctx->pri_path.mgid_index &= 0x7f;
+			} else {
+				qp_ctx->pri_path.mgid_index = slave & 0x7F;
+			}
+		}
+		if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH) {
+			port = (qp_ctx->alt_path.sched_queue >> 6 & 1) + 1;
+			if (mlx4_is_eth(dev, port)) {
+				qp_ctx->alt_path.mgid_index += mlx4_get_base_gid_ix(dev, slave);
+				qp_ctx->alt_path.mgid_index &= 0x7f;
+			} else {
+				qp_ctx->alt_path.mgid_index = slave & 0x7F;
+			}
+		}
 	}
 }
 
@@ -2734,6 +2758,8 @@ static int verify_qp_parameters(struct mlx4_dev *dev,
 	u32			qp_type;
 	struct mlx4_qp_context	*qp_ctx;
 	enum mlx4_qp_optpar	optpar;
+	int port;
+	int num_gids;
 
 	qp_ctx  = inbox->buf + 8;
 	qp_type	= (be32_to_cpu(qp_ctx->flags) >> 16) & 0xff;
@@ -2741,6 +2767,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev,
 
 	switch (qp_type) {
 	case MLX4_QP_ST_RC:
+	case MLX4_QP_ST_XRC:
 	case MLX4_QP_ST_UC:
 		switch (transition) {
 		case QP_TRANS_INIT2RTR:
@@ -2749,13 +2776,24 @@ static int verify_qp_parameters(struct mlx4_dev *dev,
 		case QP_TRANS_SQD2SQD:
 		case QP_TRANS_SQD2RTS:
 			if (slave != mlx4_master_func_num(dev))
-				/* slaves have only gid index 0 */
-				if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH)
-					if (qp_ctx->pri_path.mgid_index)
+				if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH) {
+					port = (qp_ctx->pri_path.sched_queue >> 6 & 1) + 1;
+					if (dev->caps.port_mask[port] != MLX4_PORT_TYPE_IB)
+						num_gids = mlx4_get_slave_num_gids(dev, slave);
+					else
+						num_gids = 1;
+					if (qp_ctx->pri_path.mgid_index >= num_gids)
 						return -EINVAL;
-				if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH)
-					if (qp_ctx->alt_path.mgid_index)
+				}
+				if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH) {
+					port = (qp_ctx->alt_path.sched_queue >> 6 & 1) + 1;
+					if (dev->caps.port_mask[port] != MLX4_PORT_TYPE_IB)
+						num_gids = mlx4_get_slave_num_gids(dev, slave);
+					else
+						num_gids = 1;
+					if (qp_ctx->alt_path.mgid_index >= num_gids)
 						return -EINVAL;
+				}
 			break;
 		default:
 			break;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index e4853650679d..86e02e5c2c77 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -49,6 +49,7 @@
 #define MIN_MSIX_P_PORT		5
 
 #define MLX4_ROCE_MAX_GIDS	128
+#define MLX4_ROCE_PF_GIDS	16
 
 enum {
 	MLX4_FLAG_MSI_X		= 1 << 0,
-- 
cgit v1.2.3


From 5ea8bbfc49291b7e23161fe4de0bf3e4a4e34b18 Mon Sep 17 00:00:00 2001
From: Jack Morgenstein <jackm@dev.mellanox.co.il>
Date: Wed, 12 Mar 2014 12:00:41 +0200
Subject: mlx4: Implement IP based gids support for RoCE/SRIOV

Since there is no connection between the MAC/VLAN and the GID
when using IP-based addressing, the proxy QP1 (running on the
slave) must pass the source-mac, destination-mac, and vlan_id
information separately from the GID. Additionally, the Host
must pass the remote source-mac and vlan_id back to the slave,

This is achieved as follows:
Outgoing MADs:
    1. Source MAC: obtained from the CQ completion structure
       (struct ib_wc, smac field).
    2. Destination MAC: obtained from the tunnel header
    3. vlan_id: obtained from the tunnel header.
Incoming MADs
    1. The source (i.e., remote) MAC and vlan_id are passed in
       the tunnel header to the proxy QP1.

VST mode support:
     For outgoing MADs,  the vlan_id obtained from the header is
        discarded, and the vlan_id specified by the Hypervisor is used
        instead.
     For incoming MADs, the incoming vlan_id (in the wc) is discarded, and the
        "invalid" vlan (0xffff)  is substituted when forwarding to the slave.

Signed-off-by: Moni Shoua <monis@mellanox.co.il>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/cq.c          | 42 +++++++++++++++++++----------
 drivers/infiniband/hw/mlx4/mad.c         | 45 ++++++++++++++++++++++++++++----
 drivers/infiniband/hw/mlx4/mcg.c         |  5 ++--
 drivers/infiniband/hw/mlx4/mlx4_ib.h     |  5 +++-
 drivers/infiniband/hw/mlx4/qp.c          | 11 ++++++--
 drivers/net/ethernet/mellanox/mlx4/cmd.c | 24 +++++++++++++++++
 include/linux/mlx4/cmd.h                 |  7 +++++
 include/linux/mlx4/device.h              |  3 ++-
 8 files changed, 117 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index cc40f08ca8f1..5f640814cc81 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -564,7 +564,7 @@ static int mlx4_ib_ipoib_csum_ok(__be16 status, __be16 checksum)
 }
 
 static int use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct ib_wc *wc,
-			   unsigned tail, struct mlx4_cqe *cqe)
+			   unsigned tail, struct mlx4_cqe *cqe, int is_eth)
 {
 	struct mlx4_ib_proxy_sqp_hdr *hdr;
 
@@ -574,12 +574,20 @@ static int use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct
 				   DMA_FROM_DEVICE);
 	hdr = (struct mlx4_ib_proxy_sqp_hdr *) (qp->sqp_proxy_rcv[tail].addr);
 	wc->pkey_index	= be16_to_cpu(hdr->tun.pkey_index);
-	wc->slid	= be16_to_cpu(hdr->tun.slid_mac_47_32);
-	wc->sl		= (u8) (be16_to_cpu(hdr->tun.sl_vid) >> 12);
 	wc->src_qp	= be32_to_cpu(hdr->tun.flags_src_qp) & 0xFFFFFF;
 	wc->wc_flags   |= (hdr->tun.g_ml_path & 0x80) ? (IB_WC_GRH) : 0;
 	wc->dlid_path_bits = 0;
 
+	if (is_eth) {
+		wc->vlan_id = be16_to_cpu(hdr->tun.sl_vid);
+		memcpy(&(wc->smac[0]), (char *)&hdr->tun.mac_31_0, 4);
+		memcpy(&(wc->smac[4]), (char *)&hdr->tun.slid_mac_47_32, 2);
+		wc->wc_flags |= (IB_WC_WITH_VLAN | IB_WC_WITH_SMAC);
+	} else {
+		wc->slid        = be16_to_cpu(hdr->tun.slid_mac_47_32);
+		wc->sl          = (u8) (be16_to_cpu(hdr->tun.sl_vid) >> 12);
+	}
+
 	return 0;
 }
 
@@ -594,6 +602,7 @@ static int mlx4_ib_poll_one(struct mlx4_ib_cq *cq,
 	struct mlx4_srq *msrq = NULL;
 	int is_send;
 	int is_error;
+	int is_eth;
 	u32 g_mlpath_rqpn;
 	u16 wqe_ctr;
 	unsigned tail = 0;
@@ -778,11 +787,15 @@ repoll:
 			break;
 		}
 
+		is_eth = (rdma_port_get_link_layer(wc->qp->device,
+						  (*cur_qp)->port) ==
+			  IB_LINK_LAYER_ETHERNET);
 		if (mlx4_is_mfunc(to_mdev(cq->ibcq.device)->dev)) {
 			if ((*cur_qp)->mlx4_ib_qp_type &
 			    (MLX4_IB_QPT_PROXY_SMI_OWNER |
 			     MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI))
-				return use_tunnel_data(*cur_qp, cq, wc, tail, cqe);
+				return use_tunnel_data(*cur_qp, cq, wc, tail,
+						       cqe, is_eth);
 		}
 
 		wc->slid	   = be16_to_cpu(cqe->rlid);
@@ -793,20 +806,21 @@ repoll:
 		wc->pkey_index     = be32_to_cpu(cqe->immed_rss_invalid) & 0x7f;
 		wc->wc_flags	  |= mlx4_ib_ipoib_csum_ok(cqe->status,
 					cqe->checksum) ? IB_WC_IP_CSUM_OK : 0;
-		if (rdma_port_get_link_layer(wc->qp->device,
-				(*cur_qp)->port) == IB_LINK_LAYER_ETHERNET)
+		if (is_eth) {
 			wc->sl  = be16_to_cpu(cqe->sl_vid) >> 13;
-		else
-			wc->sl  = be16_to_cpu(cqe->sl_vid) >> 12;
-		if (be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_VLAN_PRESENT_MASK) {
-			wc->vlan_id = be16_to_cpu(cqe->sl_vid) &
-				MLX4_CQE_VID_MASK;
+			if (be32_to_cpu(cqe->vlan_my_qpn) &
+					MLX4_CQE_VLAN_PRESENT_MASK) {
+				wc->vlan_id = be16_to_cpu(cqe->sl_vid) &
+					MLX4_CQE_VID_MASK;
+			} else {
+				wc->vlan_id = 0xffff;
+			}
+			memcpy(wc->smac, cqe->smac, ETH_ALEN);
+			wc->wc_flags |= (IB_WC_WITH_VLAN | IB_WC_WITH_SMAC);
 		} else {
+			wc->sl  = be16_to_cpu(cqe->sl_vid) >> 12;
 			wc->vlan_id = 0xffff;
 		}
-		wc->wc_flags |= IB_WC_WITH_VLAN;
-		memcpy(wc->smac, cqe->smac, ETH_ALEN);
-		wc->wc_flags |= IB_WC_WITH_SMAC;
 	}
 
 	return 0;
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index c5bca0f0da4a..2c572aed3f6f 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -545,11 +545,36 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
 
 	/* adjust tunnel data */
 	tun_mad->hdr.pkey_index = cpu_to_be16(tun_pkey_ix);
-	tun_mad->hdr.sl_vid = cpu_to_be16(((u16)(wc->sl)) << 12);
-	tun_mad->hdr.slid_mac_47_32 = cpu_to_be16(wc->slid);
 	tun_mad->hdr.flags_src_qp = cpu_to_be32(wc->src_qp & 0xFFFFFF);
 	tun_mad->hdr.g_ml_path = (grh && (wc->wc_flags & IB_WC_GRH)) ? 0x80 : 0;
 
+	if (is_eth) {
+		u16 vlan = 0;
+		if (mlx4_get_slave_default_vlan(dev->dev, port, slave, &vlan,
+						NULL)) {
+			/* VST mode */
+			if (vlan != wc->vlan_id)
+				/* Packet vlan is not the VST-assigned vlan.
+				 * Drop the packet.
+				 */
+				goto out;
+			 else
+				/* Remove the vlan tag before forwarding
+				 * the packet to the VF.
+				 */
+				vlan = 0xffff;
+		} else {
+			vlan = wc->vlan_id;
+		}
+
+		tun_mad->hdr.sl_vid = cpu_to_be16(vlan);
+		memcpy((char *)&tun_mad->hdr.mac_31_0, &(wc->smac[0]), 4);
+		memcpy((char *)&tun_mad->hdr.slid_mac_47_32, &(wc->smac[4]), 2);
+	} else {
+		tun_mad->hdr.sl_vid = cpu_to_be16(((u16)(wc->sl)) << 12);
+		tun_mad->hdr.slid_mac_47_32 = cpu_to_be16(wc->slid);
+	}
+
 	ib_dma_sync_single_for_device(&dev->ib_dev,
 				      tun_qp->tx_ring[tun_tx_ix].buf.map,
 				      sizeof (struct mlx4_rcv_tunnel_mad),
@@ -1116,8 +1141,9 @@ static int is_proxy_qp0(struct mlx4_ib_dev *dev, int qpn, int slave)
 
 
 int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port,
-			 enum ib_qp_type dest_qpt, u16 pkey_index, u32 remote_qpn,
-			 u32 qkey, struct ib_ah_attr *attr, struct ib_mad *mad)
+			 enum ib_qp_type dest_qpt, u16 pkey_index,
+			 u32 remote_qpn, u32 qkey, struct ib_ah_attr *attr,
+			 u8 *s_mac, struct ib_mad *mad)
 {
 	struct ib_sge list;
 	struct ib_send_wr wr, *bad_wr;
@@ -1206,6 +1232,9 @@ int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port,
 	wr.num_sge = 1;
 	wr.opcode = IB_WR_SEND;
 	wr.send_flags = IB_SEND_SIGNALED;
+	if (s_mac)
+		memcpy(to_mah(ah)->av.eth.s_mac, s_mac, 6);
+
 
 	ret = ib_post_send(send_qp, &wr, &bad_wr);
 out:
@@ -1331,13 +1360,19 @@ static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc
 	if (ah_attr.ah_flags & IB_AH_GRH)
 		fill_in_real_sgid_index(dev, slave, ctx->port, &ah_attr);
 
+	memcpy(ah_attr.dmac, tunnel->hdr.mac, 6);
+	ah_attr.vlan_id = be16_to_cpu(tunnel->hdr.vlan);
+	/* if slave have default vlan use it */
+	mlx4_get_slave_default_vlan(dev->dev, ctx->port, slave,
+				    &ah_attr.vlan_id, &ah_attr.sl);
+
 	mlx4_ib_send_to_wire(dev, slave, ctx->port,
 			     is_proxy_qp0(dev, wc->src_qp, slave) ?
 			     IB_QPT_SMI : IB_QPT_GSI,
 			     be16_to_cpu(tunnel->hdr.pkey_index),
 			     be32_to_cpu(tunnel->hdr.remote_qpn),
 			     be32_to_cpu(tunnel->hdr.qkey),
-			     &ah_attr, &tunnel->mad);
+			     &ah_attr, wc->smac, &tunnel->mad);
 }
 
 static int mlx4_ib_alloc_pv_bufs(struct mlx4_ib_demux_pv_ctx *ctx,
diff --git a/drivers/infiniband/hw/mlx4/mcg.c b/drivers/infiniband/hw/mlx4/mcg.c
index 25b2cdff00f8..ed327e6c8fdc 100644
--- a/drivers/infiniband/hw/mlx4/mcg.c
+++ b/drivers/infiniband/hw/mlx4/mcg.c
@@ -215,8 +215,9 @@ static int send_mad_to_wire(struct mlx4_ib_demux_ctx *ctx, struct ib_mad *mad)
 	}
 	mlx4_ib_query_ah(dev->sm_ah[ctx->port - 1], &ah_attr);
 	spin_unlock(&dev->sm_lock);
-	return mlx4_ib_send_to_wire(dev, mlx4_master_func_num(dev->dev), ctx->port,
-				    IB_QPT_GSI, 0, 1, IB_QP1_QKEY, &ah_attr, mad);
+	return mlx4_ib_send_to_wire(dev, mlx4_master_func_num(dev->dev),
+				    ctx->port, IB_QPT_GSI, 0, 1, IB_QP1_QKEY,
+				    &ah_attr, NULL, mad);
 }
 
 static int send_mad_to_slave(int slave, struct mlx4_ib_demux_ctx *ctx,
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index febc8f9bc59a..f589522fddfd 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -737,9 +737,12 @@ void mlx4_ib_tunnels_update_work(struct work_struct *work);
 int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
 			  enum ib_qp_type qpt, struct ib_wc *wc,
 			  struct ib_grh *grh, struct ib_mad *mad);
+
 int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port,
 			 enum ib_qp_type dest_qpt, u16 pkey_index, u32 remote_qpn,
-			 u32 qkey, struct ib_ah_attr *attr, struct ib_mad *mad);
+			 u32 qkey, struct ib_ah_attr *attr, u8 *s_mac,
+			 struct ib_mad *mad);
+
 __be64 mlx4_ib_get_new_demux_tid(struct mlx4_ib_demux_ctx *ctx);
 
 int mlx4_ib_demux_cm_handler(struct ib_device *ibdev, int port, int *slave,
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 11332f074023..aadf7f82e1f3 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -2152,7 +2152,7 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
 	}
 
 	if (is_eth) {
-		u8 smac[6];
+		u8 *smac;
 		struct in6_addr in6;
 
 		u16 pcp = (be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 29) << 13;
@@ -2164,7 +2164,12 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
 		memcpy(&ctrl->srcrb_flags16[0], ah->av.eth.mac, 2);
 		memcpy(&ctrl->imm, ah->av.eth.mac + 2, 4);
 		memcpy(&in6, sgid.raw, sizeof(in6));
-		rdma_get_ll_mac(&in6, smac);
+
+		if (!mlx4_is_mfunc(to_mdev(ib_dev)->dev))
+			smac = to_mdev(sqp->qp.ibqp.device)->
+				iboe.netdevs[sqp->qp.port - 1]->dev_addr;
+		else	/* use the src mac of the tunnel */
+			smac = ah->av.eth.s_mac;
 		memcpy(sqp->ud_header.eth.smac_h, smac, 6);
 		if (!memcmp(sqp->ud_header.eth.smac_h, sqp->ud_header.eth.dmac_h, 6))
 			mlx->flags |= cpu_to_be32(MLX4_WQE_CTRL_FORCE_LOOPBACK);
@@ -2396,6 +2401,8 @@ static void build_tunnel_header(struct ib_send_wr *wr, void *wqe, unsigned *mlx_
 	hdr.remote_qpn = cpu_to_be32(wr->wr.ud.remote_qpn);
 	hdr.pkey_index = cpu_to_be16(wr->wr.ud.pkey_index);
 	hdr.qkey = cpu_to_be32(wr->wr.ud.remote_qkey);
+	memcpy(hdr.mac, ah->av.eth.mac, 6);
+	hdr.vlan = ah->av.eth.vlan;
 
 	spc = MLX4_INLINE_ALIGN -
 		((unsigned long) (inl + 1) & (MLX4_INLINE_ALIGN - 1));
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 0d02fba94536..2b0b45ece14b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2289,6 +2289,30 @@ int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos)
 }
 EXPORT_SYMBOL_GPL(mlx4_set_vf_vlan);
 
+ /* mlx4_get_slave_default_vlan -
+ * return true if VST ( default vlan)
+ * if VST, will return vlan & qos (if not NULL)
+ */
+bool mlx4_get_slave_default_vlan(struct mlx4_dev *dev, int port, int slave,
+				 u16 *vlan, u8 *qos)
+{
+	struct mlx4_vport_oper_state *vp_oper;
+	struct mlx4_priv *priv;
+
+	priv = mlx4_priv(dev);
+	vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
+
+	if (MLX4_VGT != vp_oper->state.default_vlan) {
+		if (vlan)
+			*vlan = vp_oper->state.default_vlan;
+		if (qos)
+			*qos = vp_oper->state.default_qos;
+		return true;
+	}
+	return false;
+}
+EXPORT_SYMBOL_GPL(mlx4_get_slave_default_vlan);
+
 int mlx4_set_vf_spoofchk(struct mlx4_dev *dev, int port, int vf, bool setting)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h
index 79a347238168..009985628257 100644
--- a/include/linux/mlx4/cmd.h
+++ b/include/linux/mlx4/cmd.h
@@ -240,6 +240,13 @@ int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos);
 int mlx4_set_vf_spoofchk(struct mlx4_dev *dev, int port, int vf, bool setting);
 int mlx4_get_vf_config(struct mlx4_dev *dev, int port, int vf, struct ifla_vf_info *ivf);
 int mlx4_set_vf_link_state(struct mlx4_dev *dev, int port, int vf, int link_state);
+/*
+ * mlx4_get_slave_default_vlan -
+ * return true if VST ( default vlan)
+ * if VST, will return vlan & qos (if not NULL)
+ */
+bool mlx4_get_slave_default_vlan(struct mlx4_dev *dev, int port, int slave,
+				 u16 *vlan, u8 *qos);
 
 #define MLX4_COMM_GET_IF_REV(cmd_chan_ver) (u8)((cmd_chan_ver) >> 8)
 
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 86e02e5c2c77..f211b51dc726 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -632,7 +632,8 @@ struct mlx4_eth_av {
 	u8		hop_limit;
 	__be32		sl_tclass_flowlabel;
 	u8		dgid[16];
-	u32		reserved4[2];
+	u8		s_mac[6];
+	u8		reserved4[2];
 	__be16		vlan;
 	u8		mac[ETH_ALEN];
 };
-- 
cgit v1.2.3


From 21bdd17b21b45ea48e06e23918d681afbe0622e9 Mon Sep 17 00:00:00 2001
From: Tom Gundersen <teg@jklm.no>
Date: Mon, 3 Feb 2014 11:14:13 +1030
Subject: module: allow multiple calls to MODULE_DEVICE_TABLE() per module

Commit 78551277e4df5: "Input: i8042 - add PNP modaliases" had a bug, where the
second call to MODULE_DEVICE_TABLE() overrode the first resulting in not all
the modaliases being exposed.

This fixes the problem by including the name of the device_id table in the
__mod_*_device_table alias, allowing us to export several device_id tables
per module.

Suggested-by: Kay Sievers <kay@vrfy.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Tom Gundersen <teg@jklm.no>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/module.h   |  2 +-
 scripts/mod/file2alias.c | 14 +++++++++-----
 2 files changed, 10 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/module.h b/include/linux/module.h
index eaf60ff9ba94..ad18f6006f86 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -142,7 +142,7 @@ extern const struct gtype##_id __mod_##gtype##_table		\
 #define MODULE_DESCRIPTION(_description) MODULE_INFO(description, _description)
 
 #define MODULE_DEVICE_TABLE(type, name)		\
-  MODULE_GENERIC_TABLE(type##_device, name)
+  MODULE_GENERIC_TABLE(type##__##name##_device, name)
 
 /* Version of form [<epoch>:]<version>[-<extra-version>].
  * Or for CVS/RCS ID version, everything but the number is stripped.
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index 25e5cb0aaef6..ce164044f0cc 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -42,7 +42,7 @@ typedef unsigned char	__u8;
 
 /* This array collects all instances that use the generic do_table */
 struct devtable {
-	const char *device_id; /* name of table, __mod_<name>_device_table. */
+	const char *device_id; /* name of table, __mod_<name>__*_device_table. */
 	unsigned long id_size;
 	void *function;
 };
@@ -146,7 +146,8 @@ static void device_id_check(const char *modname, const char *device_id,
 
 	if (size % id_size || size < id_size) {
 		fatal("%s: sizeof(struct %s_device_id)=%lu is not a modulo "
-		      "of the size of section __mod_%s_device_table=%lu.\n"
+		      "of the size of "
+		      "section __mod_%s__<identifier>_device_table=%lu.\n"
 		      "Fix definition of struct %s_device_id "
 		      "in mod_devicetable.h\n",
 		      modname, device_id, id_size, device_id, size, device_id);
@@ -1206,7 +1207,7 @@ void handle_moddevtable(struct module *mod, struct elf_info *info,
 {
 	void *symval;
 	char *zeros = NULL;
-	const char *name;
+	const char *name, *identifier;
 	unsigned int namelen;
 
 	/* We're looking for a section relative symbol */
@@ -1217,7 +1218,7 @@ void handle_moddevtable(struct module *mod, struct elf_info *info,
 	if (ELF_ST_TYPE(sym->st_info) != STT_OBJECT)
 		return;
 
-	/* All our symbols are of form <prefix>__mod_XXX_device_table. */
+	/* All our symbols are of form <prefix>__mod_<name>__<identifier>_device_table. */
 	name = strstr(symname, "__mod_");
 	if (!name)
 		return;
@@ -1227,7 +1228,10 @@ void handle_moddevtable(struct module *mod, struct elf_info *info,
 		return;
 	if (strcmp(name + namelen - strlen("_device_table"), "_device_table"))
 		return;
-	namelen -= strlen("_device_table");
+	identifier = strstr(name, "__");
+	if (!identifier)
+		return;
+	namelen = identifier - name;
 
 	/* Handle all-NULL symbols allocated into .bss */
 	if (info->sechdrs[get_secindex(info, sym)].sh_type & SHT_NOBITS) {
-- 
cgit v1.2.3


From cff26a51da5d206d3baf871e75778da44710219d Mon Sep 17 00:00:00 2001
From: Rusty Russell <rusty@rustcorp.com.au>
Date: Mon, 3 Feb 2014 11:15:13 +1030
Subject: module: remove MODULE_GENERIC_TABLE

MODULE_DEVICE_TABLE() calles MODULE_GENERIC_TABLE(); make it do the
work directly.  This also removes a wart introduced in the last patch,
where the alias is defined to be an unknown struct type "struct
type##__##name##_device_id" instead of "struct type##_device_id" (it's
an extern so GCC doesn't care, but it's wrong).

The other user of MODULE_GENERIC_TABLE (ISAPNP_CARD_TABLE) is unused,
so delete it.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/isapnp.h |  4 ----
 include/linux/module.h | 19 ++++++++-----------
 2 files changed, 8 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/isapnp.h b/include/linux/isapnp.h
index e2d28b026a8c..3c77bf9b1efd 100644
--- a/include/linux/isapnp.h
+++ b/include/linux/isapnp.h
@@ -56,10 +56,6 @@
 #define ISAPNP_DEVICE_ID(_va, _vb, _vc, _function) \
 		{ .vendor = ISAPNP_VENDOR(_va, _vb, _vc), .function = ISAPNP_FUNCTION(_function) }
 
-/* export used IDs outside module */
-#define ISAPNP_CARD_TABLE(name) \
-		MODULE_GENERIC_TABLE(isapnp_card, name)
-
 struct isapnp_card_id {
 	unsigned long driver_data;	/* data private to the driver */
 	unsigned short card_vendor, card_device;
diff --git a/include/linux/module.h b/include/linux/module.h
index ad18f6006f86..5686b37e11d6 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -82,15 +82,6 @@ void sort_extable(struct exception_table_entry *start,
 void sort_main_extable(void);
 void trim_init_extable(struct module *m);
 
-#ifdef MODULE
-#define MODULE_GENERIC_TABLE(gtype, name)			\
-extern const struct gtype##_id __mod_##gtype##_table		\
-  __attribute__ ((unused, alias(__stringify(name))))
-
-#else  /* !MODULE */
-#define MODULE_GENERIC_TABLE(gtype, name)
-#endif
-
 /* Generic info of form tag = "info" */
 #define MODULE_INFO(tag, info) __MODULE_INFO(tag, tag, info)
 
@@ -141,8 +132,14 @@ extern const struct gtype##_id __mod_##gtype##_table		\
 /* What your module does. */
 #define MODULE_DESCRIPTION(_description) MODULE_INFO(description, _description)
 
-#define MODULE_DEVICE_TABLE(type, name)		\
-  MODULE_GENERIC_TABLE(type##__##name##_device, name)
+#ifdef MODULE
+/* Creates an alias so file2alias.c can find device table. */
+#define MODULE_DEVICE_TABLE(type, name)					\
+  extern const struct type##_device_id __mod_##type##__##name##_device_table \
+  __attribute__ ((unused, alias(__stringify(name))))
+#else  /* !MODULE */
+#define MODULE_DEVICE_TABLE(type, name)
+#endif
 
 /* Version of form [<epoch>:]<version>[-<extra-version>].
  * Or for CVS/RCS ID version, everything but the number is stripped.
-- 
cgit v1.2.3


From 66cc69e34e86a231fbe68d8918c6119e3b7549a3 Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Date: Thu, 13 Mar 2014 12:11:30 +1030
Subject: Fix: module signature vs tracepoints: add new TAINT_UNSIGNED_MODULE

Users have reported being unable to trace non-signed modules loaded
within a kernel supporting module signature.

This is caused by tracepoint.c:tracepoint_module_coming() refusing to
take into account tracepoints sitting within force-loaded modules
(TAINT_FORCED_MODULE). The reason for this check, in the first place, is
that a force-loaded module may have a struct module incompatible with
the layout expected by the kernel, and can thus cause a kernel crash
upon forced load of that module on a kernel with CONFIG_TRACEPOINTS=y.

Tracepoints, however, specifically accept TAINT_OOT_MODULE and
TAINT_CRAP, since those modules do not lead to the "very likely system
crash" issue cited above for force-loaded modules.

With kernels having CONFIG_MODULE_SIG=y (signed modules), a non-signed
module is tainted re-using the TAINT_FORCED_MODULE taint flag.
Unfortunately, this means that Tracepoints treat that module as a
force-loaded module, and thus silently refuse to consider any tracepoint
within this module.

Since an unsigned module does not fit within the "very likely system
crash" category of tainting, add a new TAINT_UNSIGNED_MODULE taint flag
to specifically address this taint behavior, and accept those modules
within Tracepoints. We use the letter 'X' as a taint flag character for
a module being loaded that doesn't know how to sign its name (proposed
by Steven Rostedt).

Also add the missing 'O' entry to trace event show_module_flags() list
for the sake of completeness.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
NAKed-by: Ingo Molnar <mingo@redhat.com>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: David Howells <dhowells@redhat.com>
CC: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 Documentation/ABI/testing/sysfs-module | 1 +
 Documentation/module-signing.txt       | 3 ++-
 Documentation/oops-tracing.txt         | 3 +++
 Documentation/sysctl/kernel.txt        | 2 ++
 include/linux/kernel.h                 | 1 +
 include/trace/events/module.h          | 4 +++-
 kernel/module.c                        | 4 +++-
 kernel/panic.c                         | 2 ++
 kernel/tracepoint.c                    | 5 +++--
 9 files changed, 20 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-module b/Documentation/ABI/testing/sysfs-module
index 47064c2b1f79..b9a29cdbaccb 100644
--- a/Documentation/ABI/testing/sysfs-module
+++ b/Documentation/ABI/testing/sysfs-module
@@ -49,3 +49,4 @@ Description:	Module taint flags:
 			O - out-of-tree module
 			F - force-loaded module
 			C - staging driver module
+			X - unsigned module
diff --git a/Documentation/module-signing.txt b/Documentation/module-signing.txt
index 2b40e04d3c49..b6af42e4d790 100644
--- a/Documentation/module-signing.txt
+++ b/Documentation/module-signing.txt
@@ -53,7 +53,8 @@ This has a number of options available:
 
      If this is off (ie. "permissive"), then modules for which the key is not
      available and modules that are unsigned are permitted, but the kernel will
-     be marked as being tainted.
+     be marked as being tainted, and the concerned modules will be marked as
+     tainted, shown with the character 'X'.
 
      If this is on (ie. "restrictive"), only modules that have a valid
      signature that can be verified by a public key in the kernel's possession
diff --git a/Documentation/oops-tracing.txt b/Documentation/oops-tracing.txt
index 13032c0140d4..879abe289523 100644
--- a/Documentation/oops-tracing.txt
+++ b/Documentation/oops-tracing.txt
@@ -265,6 +265,9 @@ characters, each representing a particular tainted value.
 
  13: 'O' if an externally-built ("out-of-tree") module has been loaded.
 
+ 14: 'X' if an unsigned module has been loaded in a kernel supporting
+     module signature.
+
 The primary reason for the 'Tainted: ' string is to tell kernel
 debuggers if this is a clean kernel or if anything unusual has
 occurred.  Tainting is permanent: even if an offending module is
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index e55124e7c40c..8ebe1c047004 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -792,6 +792,8 @@ can be ORed together:
 1024 - A module from drivers/staging was loaded.
 2048 - The system is working around a severe firmware bug.
 4096 - An out-of-tree module has been loaded.
+8192 - An unsigned module has been loaded in a kernel supporting module
+       signature.
 
 ==============================================================
 
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 196d1ea86df0..471090093c67 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -469,6 +469,7 @@ extern enum system_states {
 #define TAINT_CRAP			10
 #define TAINT_FIRMWARE_WORKAROUND	11
 #define TAINT_OOT_MODULE		12
+#define TAINT_UNSIGNED_MODULE		13
 
 extern const char hex_asc[];
 #define hex_asc_lo(x)	hex_asc[((x) & 0x0f)]
diff --git a/include/trace/events/module.h b/include/trace/events/module.h
index 161932737416..11fd51b413de 100644
--- a/include/trace/events/module.h
+++ b/include/trace/events/module.h
@@ -22,8 +22,10 @@ struct module;
 
 #define show_module_flags(flags) __print_flags(flags, "",	\
 	{ (1UL << TAINT_PROPRIETARY_MODULE),	"P" },		\
+	{ (1UL << TAINT_OOT_MODULE),		"O" },		\
 	{ (1UL << TAINT_FORCED_MODULE),		"F" },		\
-	{ (1UL << TAINT_CRAP),			"C" })
+	{ (1UL << TAINT_CRAP),			"C" },		\
+	{ (1UL << TAINT_UNSIGNED_MODULE),	"X" })
 
 TRACE_EVENT(module_load,
 
diff --git a/kernel/module.c b/kernel/module.c
index efa1e6031950..c1acb0c5b637 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1013,6 +1013,8 @@ static size_t module_flags_taint(struct module *mod, char *buf)
 		buf[l++] = 'F';
 	if (mod->taints & (1 << TAINT_CRAP))
 		buf[l++] = 'C';
+	if (mod->taints & (1 << TAINT_UNSIGNED_MODULE))
+		buf[l++] = 'X';
 	/*
 	 * TAINT_FORCED_RMMOD: could be added.
 	 * TAINT_UNSAFE_SMP, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't
@@ -3214,7 +3216,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
 		pr_notice_once("%s: module verification failed: signature "
 			       "and/or  required key missing - tainting "
 			       "kernel\n", mod->name);
-		add_taint_module(mod, TAINT_FORCED_MODULE, LOCKDEP_STILL_OK);
+		add_taint_module(mod, TAINT_UNSIGNED_MODULE, LOCKDEP_STILL_OK);
 	}
 #endif
 
diff --git a/kernel/panic.c b/kernel/panic.c
index 6d6300375090..0e25fe10871e 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -210,6 +210,7 @@ static const struct tnt tnts[] = {
 	{ TAINT_CRAP,			'C', ' ' },
 	{ TAINT_FIRMWARE_WORKAROUND,	'I', ' ' },
 	{ TAINT_OOT_MODULE,		'O', ' ' },
+	{ TAINT_UNSIGNED_MODULE,	'X', ' ' },
 };
 
 /**
@@ -228,6 +229,7 @@ static const struct tnt tnts[] = {
  *  'C' - modules from drivers/staging are loaded.
  *  'I' - Working around severe firmware bug.
  *  'O' - Out-of-tree module has been loaded.
+ *  'X' - Unsigned module has been loaded.
  *
  *	The string is overwritten by the next call to print_tainted().
  */
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 031cc5655a51..3cdbed1fbdc7 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -633,7 +633,8 @@ EXPORT_SYMBOL_GPL(tracepoint_iter_reset);
 #ifdef CONFIG_MODULES
 bool trace_module_has_bad_taint(struct module *mod)
 {
-	return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP));
+	return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP) |
+			       (1 << TAINT_UNSIGNED_MODULE));
 }
 
 static int tracepoint_module_coming(struct module *mod)
@@ -644,7 +645,7 @@ static int tracepoint_module_coming(struct module *mod)
 	/*
 	 * We skip modules that taint the kernel, especially those with different
 	 * module headers (for forced load), to make sure we don't cause a crash.
-	 * Staging and out-of-tree GPL modules are fine.
+	 * Staging, out-of-tree, and unsigned GPL modules are fine.
 	 */
 	if (trace_module_has_bad_taint(mod))
 		return 0;
-- 
cgit v1.2.3


From 2d123f463669cb7b84b56aa00e073ce07fe7aff2 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed, 22 Jan 2014 18:26:16 +0100
Subject: drm/docs: Include hdmi infoframe helper reference

Thierry created such nice kerneldocs, it's a shame we've left them
lingering!

For the fun of it also add a bit of kerneldoc to the header so that we
can also include that. Just in case someone adds kerneldoc in there.

Cc: Thierry Reding <thierry.reding@gmail.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 Documentation/DocBook/drm.tmpl | 11 +++++++++++
 include/linux/hdmi.h           | 12 ++++++++++++
 2 files changed, 23 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
index 0a9407ae4025..0e0390ece122 100644
--- a/Documentation/DocBook/drm.tmpl
+++ b/Documentation/DocBook/drm.tmpl
@@ -2219,6 +2219,17 @@ void intel_crt_init(struct drm_device *dev)
 !Iinclude/drm/drm_flip_work.h
 !Edrivers/gpu/drm/drm_flip_work.c
     </sect2>
+    <sect2>
+      <title>HDMI Infoframes Helper Reference</title>
+      <para>
+	Strictly speaking this is not a DRM helper library but generally useable
+	by any driver interfacing with HDMI outputs like v4l or alsa drivers.
+	But it nicely fits into the overall topic of mode setting helper
+	libraries and hence is also included here.
+      </para>
+!Iinclude/linux/hdmi.h
+!Edrivers/video/hdmi.c
+    </sect2>
   </sect1>
 
   <!-- Internals: kms properties -->
diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h
index 9231be9e90a2..11c0182a153b 100644
--- a/include/linux/hdmi.h
+++ b/include/linux/hdmi.h
@@ -262,6 +262,18 @@ union hdmi_vendor_any_infoframe {
 	struct hdmi_vendor_infoframe hdmi;
 };
 
+/**
+ * union hdmi_infoframe - overall union of all abstract infoframe representations
+ * @any: generic infoframe
+ * @avi: avi infoframe
+ * @spd: spd infoframe
+ * @vendor: union of all vendor infoframes
+ * @audio: audio infoframe
+ *
+ * This is used by the generic pack function. This works since all infoframes
+ * have the same header which also indicates which type of infoframe should be
+ * packed.
+ */
 union hdmi_infoframe {
 	struct hdmi_any_infoframe any;
 	struct hdmi_avi_infoframe avi;
-- 
cgit v1.2.3


From 89f8b33ca1ea881d1d84542282cb85d07d02e78d Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@fb.com>
Date: Thu, 13 Mar 2014 09:38:42 -0600
Subject: block: remove old blk_iopoll_enabled variable

This was a debugging measure to toggle enabled/disabled
when testing. But for real production setups, it's not
safe to toggle this setting without either reloading
drivers of quiescing IO first. Neither of which the toggle
enforces.

Additionally, it makes drivers deal with the conditional
state.

Remove it completely. It's up to the driver whether iopoll
is enabled or not.

Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-iopoll.c              |   3 -
 drivers/scsi/be2iscsi/be_main.c | 206 ++++++++++++----------------------------
 drivers/scsi/ipr.c              |  15 +--
 include/linux/blk-iopoll.h      |   2 -
 kernel/sysctl.c                 |  12 ---
 5 files changed, 68 insertions(+), 170 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-iopoll.c b/block/blk-iopoll.c
index 1855bf51edb0..c11d24e379e2 100644
--- a/block/blk-iopoll.c
+++ b/block/blk-iopoll.c
@@ -14,9 +14,6 @@
 
 #include "blk.h"
 
-int blk_iopoll_enabled = 1;
-EXPORT_SYMBOL(blk_iopoll_enabled);
-
 static unsigned int blk_iopoll_budget __read_mostly = 256;
 
 static DEFINE_PER_CPU(struct list_head, blk_cpu_iopoll);
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index 1f375051483a..a929c3c9aedc 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -873,7 +873,6 @@ static irqreturn_t be_isr_msix(int irq, void *dev_id)
 	struct be_queue_info *cq;
 	unsigned int num_eq_processed;
 	struct be_eq_obj *pbe_eq;
-	unsigned long flags;
 
 	pbe_eq = dev_id;
 	eq = &pbe_eq->q;
@@ -882,31 +881,15 @@ static irqreturn_t be_isr_msix(int irq, void *dev_id)
 
 	phba = pbe_eq->phba;
 	num_eq_processed = 0;
-	if (blk_iopoll_enabled) {
-		while (eqe->dw[offsetof(struct amap_eq_entry, valid) / 32]
-					& EQE_VALID_MASK) {
-			if (!blk_iopoll_sched_prep(&pbe_eq->iopoll))
-				blk_iopoll_sched(&pbe_eq->iopoll);
-
-			AMAP_SET_BITS(struct amap_eq_entry, valid, eqe, 0);
-			queue_tail_inc(eq);
-			eqe = queue_tail_node(eq);
-			num_eq_processed++;
-		}
-	} else {
-		while (eqe->dw[offsetof(struct amap_eq_entry, valid) / 32]
-						& EQE_VALID_MASK) {
-			spin_lock_irqsave(&phba->isr_lock, flags);
-			pbe_eq->todo_cq = true;
-			spin_unlock_irqrestore(&phba->isr_lock, flags);
-			AMAP_SET_BITS(struct amap_eq_entry, valid, eqe, 0);
-			queue_tail_inc(eq);
-			eqe = queue_tail_node(eq);
-			num_eq_processed++;
-		}
+	while (eqe->dw[offsetof(struct amap_eq_entry, valid) / 32]
+				& EQE_VALID_MASK) {
+		if (!blk_iopoll_sched_prep(&pbe_eq->iopoll))
+			blk_iopoll_sched(&pbe_eq->iopoll);
 
-		if (pbe_eq->todo_cq)
-			queue_work(phba->wq, &pbe_eq->work_cqs);
+		AMAP_SET_BITS(struct amap_eq_entry, valid, eqe, 0);
+		queue_tail_inc(eq);
+		eqe = queue_tail_node(eq);
+		num_eq_processed++;
 	}
 
 	if (num_eq_processed)
@@ -927,7 +910,6 @@ static irqreturn_t be_isr(int irq, void *dev_id)
 	struct hwi_context_memory *phwi_context;
 	struct be_eq_entry *eqe = NULL;
 	struct be_queue_info *eq;
-	struct be_queue_info *cq;
 	struct be_queue_info *mcc;
 	unsigned long flags, index;
 	unsigned int num_mcceq_processed, num_ioeq_processed;
@@ -953,72 +935,40 @@ static irqreturn_t be_isr(int irq, void *dev_id)
 
 	num_ioeq_processed = 0;
 	num_mcceq_processed = 0;
-	if (blk_iopoll_enabled) {
-		while (eqe->dw[offsetof(struct amap_eq_entry, valid) / 32]
-					& EQE_VALID_MASK) {
-			if (((eqe->dw[offsetof(struct amap_eq_entry,
-			     resource_id) / 32] &
-			     EQE_RESID_MASK) >> 16) == mcc->id) {
-				spin_lock_irqsave(&phba->isr_lock, flags);
-				pbe_eq->todo_mcc_cq = true;
-				spin_unlock_irqrestore(&phba->isr_lock, flags);
-				num_mcceq_processed++;
-			} else {
-				if (!blk_iopoll_sched_prep(&pbe_eq->iopoll))
-					blk_iopoll_sched(&pbe_eq->iopoll);
-				num_ioeq_processed++;
-			}
-			AMAP_SET_BITS(struct amap_eq_entry, valid, eqe, 0);
-			queue_tail_inc(eq);
-			eqe = queue_tail_node(eq);
-		}
-		if (num_ioeq_processed || num_mcceq_processed) {
-			if (pbe_eq->todo_mcc_cq)
-				queue_work(phba->wq, &pbe_eq->work_cqs);
-
-			if ((num_mcceq_processed) && (!num_ioeq_processed))
-				hwi_ring_eq_db(phba, eq->id, 0,
-					      (num_ioeq_processed +
-					       num_mcceq_processed) , 1, 1);
-			else
-				hwi_ring_eq_db(phba, eq->id, 0,
-					       (num_ioeq_processed +
-						num_mcceq_processed), 0, 1);
-
-			return IRQ_HANDLED;
-		} else
-			return IRQ_NONE;
-	} else {
-		cq = &phwi_context->be_cq[0];
-		while (eqe->dw[offsetof(struct amap_eq_entry, valid) / 32]
-						& EQE_VALID_MASK) {
-
-			if (((eqe->dw[offsetof(struct amap_eq_entry,
-			     resource_id) / 32] &
-			     EQE_RESID_MASK) >> 16) != cq->id) {
-				spin_lock_irqsave(&phba->isr_lock, flags);
-				pbe_eq->todo_mcc_cq = true;
-				spin_unlock_irqrestore(&phba->isr_lock, flags);
-			} else {
-				spin_lock_irqsave(&phba->isr_lock, flags);
-				pbe_eq->todo_cq = true;
-				spin_unlock_irqrestore(&phba->isr_lock, flags);
-			}
-			AMAP_SET_BITS(struct amap_eq_entry, valid, eqe, 0);
-			queue_tail_inc(eq);
-			eqe = queue_tail_node(eq);
+	while (eqe->dw[offsetof(struct amap_eq_entry, valid) / 32]
+				& EQE_VALID_MASK) {
+		if (((eqe->dw[offsetof(struct amap_eq_entry,
+		     resource_id) / 32] &
+		     EQE_RESID_MASK) >> 16) == mcc->id) {
+			spin_lock_irqsave(&phba->isr_lock, flags);
+			pbe_eq->todo_mcc_cq = true;
+			spin_unlock_irqrestore(&phba->isr_lock, flags);
+			num_mcceq_processed++;
+		} else {
+			if (!blk_iopoll_sched_prep(&pbe_eq->iopoll))
+				blk_iopoll_sched(&pbe_eq->iopoll);
 			num_ioeq_processed++;
 		}
-		if (pbe_eq->todo_cq || pbe_eq->todo_mcc_cq)
+		AMAP_SET_BITS(struct amap_eq_entry, valid, eqe, 0);
+		queue_tail_inc(eq);
+		eqe = queue_tail_node(eq);
+	}
+	if (num_ioeq_processed || num_mcceq_processed) {
+		if (pbe_eq->todo_mcc_cq)
 			queue_work(phba->wq, &pbe_eq->work_cqs);
 
-		if (num_ioeq_processed) {
+		if ((num_mcceq_processed) && (!num_ioeq_processed))
 			hwi_ring_eq_db(phba, eq->id, 0,
-				       num_ioeq_processed, 1, 1);
-			return IRQ_HANDLED;
-		} else
-			return IRQ_NONE;
-	}
+				      (num_ioeq_processed +
+				       num_mcceq_processed) , 1, 1);
+		else
+			hwi_ring_eq_db(phba, eq->id, 0,
+				       (num_ioeq_processed +
+					num_mcceq_processed), 0, 1);
+
+		return IRQ_HANDLED;
+	} else
+		return IRQ_NONE;
 }
 
 static int beiscsi_init_irqs(struct beiscsi_hba *phba)
@@ -5216,11 +5166,10 @@ static void beiscsi_quiesce(struct beiscsi_hba *phba,
 		}
 	pci_disable_msix(phba->pcidev);
 
-	if (blk_iopoll_enabled)
-		for (i = 0; i < phba->num_cpus; i++) {
-			pbe_eq = &phwi_context->be_eq[i];
-			blk_iopoll_disable(&pbe_eq->iopoll);
-		}
+	for (i = 0; i < phba->num_cpus; i++) {
+		pbe_eq = &phwi_context->be_eq[i];
+		blk_iopoll_disable(&pbe_eq->iopoll);
+	}
 
 	if (unload_state == BEISCSI_CLEAN_UNLOAD) {
 		destroy_workqueue(phba->wq);
@@ -5429,32 +5378,18 @@ static void beiscsi_eeh_resume(struct pci_dev *pdev)
 	phwi_ctrlr = phba->phwi_ctrlr;
 	phwi_context = phwi_ctrlr->phwi_ctxt;
 
-	if (blk_iopoll_enabled) {
-		for (i = 0; i < phba->num_cpus; i++) {
-			pbe_eq = &phwi_context->be_eq[i];
-			blk_iopoll_init(&pbe_eq->iopoll, be_iopoll_budget,
-					be_iopoll);
-			blk_iopoll_enable(&pbe_eq->iopoll);
-		}
-
-		i = (phba->msix_enabled) ? i : 0;
-		/* Work item for MCC handling */
+	for (i = 0; i < phba->num_cpus; i++) {
 		pbe_eq = &phwi_context->be_eq[i];
-		INIT_WORK(&pbe_eq->work_cqs, beiscsi_process_all_cqs);
-	} else {
-		if (phba->msix_enabled) {
-			for (i = 0; i <= phba->num_cpus; i++) {
-				pbe_eq = &phwi_context->be_eq[i];
-				INIT_WORK(&pbe_eq->work_cqs,
-					  beiscsi_process_all_cqs);
-			}
-		} else {
-			pbe_eq = &phwi_context->be_eq[0];
-			INIT_WORK(&pbe_eq->work_cqs,
-				  beiscsi_process_all_cqs);
-		}
+		blk_iopoll_init(&pbe_eq->iopoll, be_iopoll_budget,
+				be_iopoll);
+		blk_iopoll_enable(&pbe_eq->iopoll);
 	}
 
+	i = (phba->msix_enabled) ? i : 0;
+	/* Work item for MCC handling */
+	pbe_eq = &phwi_context->be_eq[i];
+	INIT_WORK(&pbe_eq->work_cqs, beiscsi_process_all_cqs);
+
 	ret = beiscsi_init_irqs(phba);
 	if (ret < 0) {
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
@@ -5614,32 +5549,18 @@ static int beiscsi_dev_probe(struct pci_dev *pcidev,
 	phwi_ctrlr = phba->phwi_ctrlr;
 	phwi_context = phwi_ctrlr->phwi_ctxt;
 
-	if (blk_iopoll_enabled) {
-		for (i = 0; i < phba->num_cpus; i++) {
-			pbe_eq = &phwi_context->be_eq[i];
-			blk_iopoll_init(&pbe_eq->iopoll, be_iopoll_budget,
-					be_iopoll);
-			blk_iopoll_enable(&pbe_eq->iopoll);
-		}
-
-		i = (phba->msix_enabled) ? i : 0;
-		/* Work item for MCC handling */
+	for (i = 0; i < phba->num_cpus; i++) {
 		pbe_eq = &phwi_context->be_eq[i];
-		INIT_WORK(&pbe_eq->work_cqs, beiscsi_process_all_cqs);
-	} else {
-		if (phba->msix_enabled) {
-			for (i = 0; i <= phba->num_cpus; i++) {
-				pbe_eq = &phwi_context->be_eq[i];
-				INIT_WORK(&pbe_eq->work_cqs,
-					  beiscsi_process_all_cqs);
-			}
-		} else {
-				pbe_eq = &phwi_context->be_eq[0];
-				INIT_WORK(&pbe_eq->work_cqs,
-					  beiscsi_process_all_cqs);
-			}
+		blk_iopoll_init(&pbe_eq->iopoll, be_iopoll_budget,
+				be_iopoll);
+		blk_iopoll_enable(&pbe_eq->iopoll);
 	}
 
+	i = (phba->msix_enabled) ? i : 0;
+	/* Work item for MCC handling */
+	pbe_eq = &phwi_context->be_eq[i];
+	INIT_WORK(&pbe_eq->work_cqs, beiscsi_process_all_cqs);
+
 	ret = beiscsi_init_irqs(phba);
 	if (ret < 0) {
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
@@ -5668,11 +5589,10 @@ static int beiscsi_dev_probe(struct pci_dev *pcidev,
 
 free_blkenbld:
 	destroy_workqueue(phba->wq);
-	if (blk_iopoll_enabled)
-		for (i = 0; i < phba->num_cpus; i++) {
-			pbe_eq = &phwi_context->be_eq[i];
-			blk_iopoll_disable(&pbe_eq->iopoll);
-		}
+	for (i = 0; i < phba->num_cpus; i++) {
+		pbe_eq = &phwi_context->be_eq[i];
+		blk_iopoll_disable(&pbe_eq->iopoll);
+	}
 free_twq:
 	beiscsi_clean_port(phba);
 	beiscsi_free_mem(phba);
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 3f5b56a99892..69470f5c0ac9 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -3630,16 +3630,14 @@ static ssize_t ipr_store_iopoll_weight(struct device *dev,
 		return strlen(buf);
 	}
 
-	if (blk_iopoll_enabled && ioa_cfg->iopoll_weight &&
-			ioa_cfg->sis64 && ioa_cfg->nvectors > 1) {
+	if (ioa_cfg->iopoll_weight && ioa_cfg->sis64 && ioa_cfg->nvectors > 1) {
 		for (i = 1; i < ioa_cfg->hrrq_num; i++)
 			blk_iopoll_disable(&ioa_cfg->hrrq[i].iopoll);
 	}
 
 	spin_lock_irqsave(shost->host_lock, lock_flags);
 	ioa_cfg->iopoll_weight = user_iopoll_weight;
-	if (blk_iopoll_enabled && ioa_cfg->iopoll_weight &&
-			ioa_cfg->sis64 && ioa_cfg->nvectors > 1) {
+	if (ioa_cfg->iopoll_weight && ioa_cfg->sis64 && ioa_cfg->nvectors > 1) {
 		for (i = 1; i < ioa_cfg->hrrq_num; i++) {
 			blk_iopoll_init(&ioa_cfg->hrrq[i].iopoll,
 					ioa_cfg->iopoll_weight, ipr_iopoll);
@@ -5484,8 +5482,7 @@ static irqreturn_t ipr_isr_mhrrq(int irq, void *devp)
 		return IRQ_NONE;
 	}
 
-	if (blk_iopoll_enabled && ioa_cfg->iopoll_weight &&
-			ioa_cfg->sis64 && ioa_cfg->nvectors > 1) {
+	if (ioa_cfg->iopoll_weight && ioa_cfg->sis64 && ioa_cfg->nvectors > 1) {
 		if ((be32_to_cpu(*hrrq->hrrq_curr) & IPR_HRRQ_TOGGLE_BIT) ==
 		       hrrq->toggle_bit) {
 			if (!blk_iopoll_sched_prep(&hrrq->iopoll))
@@ -9859,8 +9856,7 @@ static int ipr_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id)
 	ioa_cfg->host->max_channel = IPR_VSET_BUS;
 	ioa_cfg->iopoll_weight = ioa_cfg->chip_cfg->iopoll_weight;
 
-	if (blk_iopoll_enabled && ioa_cfg->iopoll_weight &&
-			ioa_cfg->sis64 && ioa_cfg->nvectors > 1) {
+	if (ioa_cfg->iopoll_weight && ioa_cfg->sis64 && ioa_cfg->nvectors > 1) {
 		for (i = 1; i < ioa_cfg->hrrq_num; i++) {
 			blk_iopoll_init(&ioa_cfg->hrrq[i].iopoll,
 					ioa_cfg->iopoll_weight, ipr_iopoll);
@@ -9889,8 +9885,7 @@ static void ipr_shutdown(struct pci_dev *pdev)
 	int i;
 
 	spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
-	if (blk_iopoll_enabled && ioa_cfg->iopoll_weight &&
-			ioa_cfg->sis64 && ioa_cfg->nvectors > 1) {
+	if (ioa_cfg->iopoll_weight && ioa_cfg->sis64 && ioa_cfg->nvectors > 1) {
 		ioa_cfg->iopoll_weight = 0;
 		for (i = 1; i < ioa_cfg->hrrq_num; i++)
 			blk_iopoll_disable(&ioa_cfg->hrrq[i].iopoll);
diff --git a/include/linux/blk-iopoll.h b/include/linux/blk-iopoll.h
index 308734d3d4a2..77ae77c0b704 100644
--- a/include/linux/blk-iopoll.h
+++ b/include/linux/blk-iopoll.h
@@ -43,6 +43,4 @@ extern void __blk_iopoll_complete(struct blk_iopoll *);
 extern void blk_iopoll_enable(struct blk_iopoll *);
 extern void blk_iopoll_disable(struct blk_iopoll *);
 
-extern int blk_iopoll_enabled;
-
 #endif
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 49e13e1f8fe6..ef0bf04e8649 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -112,9 +112,6 @@ extern int sysctl_nr_open_min, sysctl_nr_open_max;
 #ifndef CONFIG_MMU
 extern int sysctl_nr_trim_pages;
 #endif
-#ifdef CONFIG_BLOCK
-extern int blk_iopoll_enabled;
-#endif
 
 /* Constants used for minimum and  maximum */
 #ifdef CONFIG_LOCKUP_DETECTOR
@@ -1093,15 +1090,6 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-#endif
-#ifdef CONFIG_BLOCK
-	{
-		.procname	= "blk_iopoll",
-		.data		= &blk_iopoll_enabled,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 #endif
 	{ }
 };
-- 
cgit v1.2.3


From e534a9352237e84263cecedff283387b144b3ed8 Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Date: Sat, 8 Mar 2014 22:52:42 -0500
Subject: HID: sony: do not rely on hid_output_raw_report

hid_out_raw_report is going to be obsoleted as it is not part of the
unified HID low level transport documentation
(Documentation/hid/hid-transport.txt)

To do so, we need to introduce two new quirks:
* HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP: this quirks prevents the
  transport driver to use the interrupt channel to send output report
  (and thus force to use HID_REQ_SET_REPORT command)
* HID_QUIRK_SKIP_OUTPUT_REPORT_ID: this one forces usbhid to not
  include the report ID in the buffer it sends to the device through
  HID_REQ_SET_REPORT in case of an output report

This also fixes a regression introduced in commit 3a75b24949a8
(HID: hidraw: replace hid_output_raw_report() calls by appropriates ones).
The hidraw API was not able to communicate with the PS3 SixAxis
controllers in USB mode.

Reviewed-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Tested-by: Antonio Ospite <ao2@ao2.it>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/hid-sony.c        | 60 ++++++++++---------------------------------
 drivers/hid/hidraw.c          |  3 ++-
 drivers/hid/usbhid/hid-core.c |  7 ++++-
 include/linux/hid.h           |  2 ++
 4 files changed, 24 insertions(+), 48 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index b5fe65e70dc4..4884bb567bf8 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -29,7 +29,6 @@
 #include <linux/hid.h>
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <linux/usb.h>
 #include <linux/leds.h>
 #include <linux/power_supply.h>
 #include <linux/spinlock.h>
@@ -1006,45 +1005,6 @@ static int sony_mapping(struct hid_device *hdev, struct hid_input *hi,
 	return 0;
 }
 
-/*
- * The Sony Sixaxis does not handle HID Output Reports on the Interrupt EP
- * like it should according to usbhid/hid-core.c::usbhid_output_raw_report()
- * so we need to override that forcing HID Output Reports on the Control EP.
- *
- * There is also another issue about HID Output Reports via USB, the Sixaxis
- * does not want the report_id as part of the data packet, so we have to
- * discard buf[0] when sending the actual control message, even for numbered
- * reports, humpf!
- */
-static int sixaxis_usb_output_raw_report(struct hid_device *hid, __u8 *buf,
-		size_t count, unsigned char report_type)
-{
-	struct usb_interface *intf = to_usb_interface(hid->dev.parent);
-	struct usb_device *dev = interface_to_usbdev(intf);
-	struct usb_host_interface *interface = intf->cur_altsetting;
-	int report_id = buf[0];
-	int ret;
-
-	if (report_type == HID_OUTPUT_REPORT) {
-		/* Don't send the Report ID */
-		buf++;
-		count--;
-	}
-
-	ret = usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
-		HID_REQ_SET_REPORT,
-		USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE,
-		((report_type + 1) << 8) | report_id,
-		interface->desc.bInterfaceNumber, buf, count,
-		USB_CTRL_SET_TIMEOUT);
-
-	/* Count also the Report ID, in case of an Output report. */
-	if (ret > 0 && report_type == HID_OUTPUT_REPORT)
-		ret++;
-
-	return ret;
-}
-
 /*
  * Sending HID_REQ_GET_REPORT changes the operation mode of the ps3 controller
  * to "operational".  Without this, the ps3 controller will not report any
@@ -1305,11 +1265,8 @@ static void sixaxis_state_worker(struct work_struct *work)
 	buf[10] |= sc->led_state[2] << 3;
 	buf[10] |= sc->led_state[3] << 4;
 
-	if (sc->quirks & SIXAXIS_CONTROLLER_USB)
-		hid_output_raw_report(sc->hdev, buf, sizeof(buf), HID_OUTPUT_REPORT);
-	else
-		hid_hw_raw_request(sc->hdev, 0x01, buf, sizeof(buf),
-				HID_OUTPUT_REPORT, HID_REQ_SET_REPORT);
+	hid_hw_raw_request(sc->hdev, 0x01, buf, sizeof(buf), HID_OUTPUT_REPORT,
+			HID_REQ_SET_REPORT);
 }
 
 static void dualshock4_state_worker(struct work_struct *work)
@@ -1659,7 +1616,18 @@ static int sony_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	}
 
 	if (sc->quirks & SIXAXIS_CONTROLLER_USB) {
-		hdev->hid_output_raw_report = sixaxis_usb_output_raw_report;
+		/*
+		 * The Sony Sixaxis does not handle HID Output Reports on the
+		 * Interrupt EP like it could, so we need to force HID Output
+		 * Reports to use HID_REQ_SET_REPORT on the Control EP.
+		 *
+		 * There is also another issue about HID Output Reports via USB,
+		 * the Sixaxis does not want the report_id as part of the data
+		 * packet, so we have to discard buf[0] when sending the actual
+		 * control message, even for numbered reports, humpf!
+		 */
+		hdev->quirks |= HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP;
+		hdev->quirks |= HID_QUIRK_SKIP_OUTPUT_REPORT_ID;
 		ret = sixaxis_set_operational_usb(hdev);
 		sc->worker_initialized = 1;
 		INIT_WORK(&sc->state_worker, sixaxis_state_worker);
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index 2cc484c0017b..ffa648ce002e 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -149,7 +149,8 @@ static ssize_t hidraw_send_report(struct file *file, const char __user *buffer,
 		goto out_free;
 	}
 
-	if (report_type == HID_OUTPUT_REPORT) {
+	if ((report_type == HID_OUTPUT_REPORT) &&
+	    !(dev->quirks & HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP)) {
 		ret = hid_hw_output_report(dev, buf, count);
 		/*
 		 * compatibility with old implementation of USB-HID and I2C-HID:
diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index 0d1d87533f48..3bc7cad48fe0 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -894,7 +894,12 @@ static int usbhid_set_raw_report(struct hid_device *hid, unsigned int reportnum,
 	int ret, skipped_report_id = 0;
 
 	/* Byte 0 is the report number. Report data starts at byte 1.*/
-	buf[0] = reportnum;
+	if ((rtype == HID_OUTPUT_REPORT) &&
+	    (hid->quirks & HID_QUIRK_SKIP_OUTPUT_REPORT_ID))
+		buf[0] = 0;
+	else
+		buf[0] = reportnum;
+
 	if (buf[0] == 0x0) {
 		/* Don't send the Report ID */
 		buf++;
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 5eb282e0dff7..3fe444f4a36f 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -287,6 +287,8 @@ struct hid_item {
 #define HID_QUIRK_NO_EMPTY_INPUT		0x00000100
 #define HID_QUIRK_NO_INIT_INPUT_REPORTS		0x00000200
 #define HID_QUIRK_SKIP_OUTPUT_REPORTS		0x00010000
+#define HID_QUIRK_SKIP_OUTPUT_REPORT_ID		0x00020000
+#define HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP	0x00040000
 #define HID_QUIRK_FULLSPEED_INTERVAL		0x10000000
 #define HID_QUIRK_NO_INIT_REPORTS		0x20000000
 #define HID_QUIRK_NO_IGNORE			0x40000000
-- 
cgit v1.2.3


From 6fd182028c43baf1c7d017d52b0134ecadbdc447 Mon Sep 17 00:00:00 2001
From: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Date: Sat, 8 Mar 2014 22:52:43 -0500
Subject: HID: remove hid_output_raw_report transport implementations

Nobody calls hid_output_raw_report anymore, and nobody should.
We can now remove the various implementation in the different
transport drivers and the declarations.

Reviewed-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 drivers/hid/i2c-hid/i2c-hid.c | 14 --------------
 drivers/hid/uhid.c            |  1 -
 drivers/hid/usbhid/hid-core.c | 12 ------------
 include/linux/hid.h           | 19 -------------------
 net/bluetooth/hidp/core.c     | 14 --------------
 5 files changed, 60 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index 1a955317d05f..2de2b8e22462 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -587,19 +587,6 @@ static int i2c_hid_output_raw_report(struct hid_device *hid, __u8 *buf,
 	return ret;
 }
 
-static int __i2c_hid_output_raw_report(struct hid_device *hid, __u8 *buf,
-		size_t count, unsigned char report_type)
-{
-	struct i2c_client *client = hid->driver_data;
-	struct i2c_hid *ihid = i2c_get_clientdata(client);
-	bool data = true; /* SET_REPORT */
-
-	if (report_type == HID_OUTPUT_REPORT)
-		data = le16_to_cpu(ihid->hdesc.wMaxOutputLength) == 0;
-
-	return i2c_hid_output_raw_report(hid, buf, count, report_type, data);
-}
-
 static int i2c_hid_output_report(struct hid_device *hid, __u8 *buf,
 		size_t count)
 {
@@ -1025,7 +1012,6 @@ static int i2c_hid_probe(struct i2c_client *client,
 
 	hid->driver_data = client;
 	hid->ll_driver = &i2c_hid_ll_driver;
-	hid->hid_output_raw_report = __i2c_hid_output_raw_report;
 	hid->dev.parent = &client->dev;
 	ACPI_COMPANION_SET(&hid->dev, ACPI_COMPANION(&client->dev));
 	hid->bus = BUS_I2C;
diff --git a/drivers/hid/uhid.c b/drivers/hid/uhid.c
index 60acee422fdc..7ed79be2686a 100644
--- a/drivers/hid/uhid.c
+++ b/drivers/hid/uhid.c
@@ -400,7 +400,6 @@ static int uhid_dev_create(struct uhid_device *uhid,
 	hid->uniq[63] = 0;
 
 	hid->ll_driver = &uhid_hid_driver;
-	hid->hid_output_raw_report = uhid_hid_output_raw;
 	hid->bus = ev->u.create.bus;
 	hid->vendor = ev->u.create.vendor;
 	hid->product = ev->u.create.product;
diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index 3bc7cad48fe0..7b88f4cb9902 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -950,17 +950,6 @@ static int usbhid_output_report(struct hid_device *hid, __u8 *buf, size_t count)
 	return ret;
 }
 
-static int usbhid_output_raw_report(struct hid_device *hid, __u8 *buf,
-		size_t count, unsigned char report_type)
-{
-	struct usbhid_device *usbhid = hid->driver_data;
-
-	if (usbhid->urbout && report_type != HID_FEATURE_REPORT)
-		return usbhid_output_report(hid, buf, count);
-
-	return usbhid_set_raw_report(hid, buf[0], buf, count, report_type);
-}
-
 static void usbhid_restart_queues(struct usbhid_device *usbhid)
 {
 	if (usbhid->urbout && !test_bit(HID_OUT_RUNNING, &usbhid->iofl))
@@ -1294,7 +1283,6 @@ static int usbhid_probe(struct usb_interface *intf, const struct usb_device_id *
 
 	usb_set_intfdata(intf, hid);
 	hid->ll_driver = &usb_hid_driver;
-	hid->hid_output_raw_report = usbhid_output_raw_report;
 	hid->ff_init = hid_pidff_init;
 #ifdef CONFIG_USB_HIDDEV
 	hid->hiddev_connect = hiddev_connect;
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 3fe444f4a36f..01a90b8d53bb 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -510,9 +510,6 @@ struct hid_device {							/* device report descriptor */
 				  struct hid_usage *, __s32);
 	void (*hiddev_report_event) (struct hid_device *, struct hid_report *);
 
-	/* handler for raw output data, used by hidraw */
-	int (*hid_output_raw_report) (struct hid_device *, __u8 *, size_t, unsigned char);
-
 	/* debugging support via debugfs */
 	unsigned short debug;
 	struct dentry *debug_dir;
@@ -1019,22 +1016,6 @@ static inline int hid_hw_output_report(struct hid_device *hdev, __u8 *buf,
 	return -ENOSYS;
 }
 
-/**
- * hid_output_raw_report - send an output or a feature report to the device
- *
- * @hdev: hid device
- * @buf: raw data to transfer
- * @len: length of buf
- * @report_type: HID_FEATURE_REPORT or HID_OUTPUT_REPORT
- *
- * @return: count of data transfered, negative if error
- */
-static inline int hid_output_raw_report(struct hid_device *hdev, __u8 *buf,
-					size_t len, unsigned char report_type)
-{
-	return hdev->hid_output_raw_report(hdev, buf, len, report_type);
-}
-
 /**
  * hid_hw_idle - send idle request to device
  *
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 98e4840935e2..514ddb5aef96 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -382,18 +382,6 @@ static int hidp_output_report(struct hid_device *hid, __u8 *data, size_t count)
 				      data, count);
 }
 
-static int hidp_output_raw_report(struct hid_device *hid, unsigned char *data,
-		size_t count, unsigned char report_type)
-{
-	if (report_type == HID_OUTPUT_REPORT) {
-		return hidp_output_report(hid, data, count);
-	} else if (report_type != HID_FEATURE_REPORT) {
-		return -EINVAL;
-	}
-
-	return hidp_set_raw_report(hid, data[0], data, count, report_type);
-}
-
 static int hidp_raw_request(struct hid_device *hid, unsigned char reportnum,
 			    __u8 *buf, size_t len, unsigned char rtype,
 			    int reqtype)
@@ -776,8 +764,6 @@ static int hidp_setup_hid(struct hidp_session *session,
 	hid->dev.parent = &session->conn->hcon->dev;
 	hid->ll_driver = &hidp_hid_driver;
 
-	hid->hid_output_raw_report = hidp_output_raw_report;
-
 	/* True if device is blacklisted in drivers/hid/hid-core.c */
 	if (hid_ignore(hid)) {
 		hid_destroy_device(session->hid);
-- 
cgit v1.2.3


From 95363efde193079541cb379eb47140e9c4d355d5 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@fb.com>
Date: Fri, 14 Mar 2014 10:43:15 -0600
Subject: blk-mq: allow blk_mq_init_commands() to return failure

If drivers do dynamic allocation in the hardware command init
path, then we need to be able to handle and return failures.

And if they do allocations or mappings in the init command path,
then we need a cleanup function to free up that space at exit
time. So add blk_mq_free_commands() as the cleanup function.

This is required for the mtip32xx driver conversion to blk-mq.

Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq.c             | 52 +++++++++++++++++++++++++++++++++++++++-------
 drivers/block/virtio_blk.c |  3 ++-
 include/linux/blk-mq.h     |  3 ++-
 3 files changed, 49 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 01d8735db8d3..92284af4e0df 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1058,8 +1058,46 @@ static void blk_mq_hctx_notify(void *data, unsigned long action,
 	blk_mq_put_ctx(ctx);
 }
 
-static void blk_mq_init_hw_commands(struct blk_mq_hw_ctx *hctx,
-				    void (*init)(void *, struct blk_mq_hw_ctx *,
+static int blk_mq_init_hw_commands(struct blk_mq_hw_ctx *hctx,
+				   int (*init)(void *, struct blk_mq_hw_ctx *,
+					struct request *, unsigned int),
+				   void *data)
+{
+	unsigned int i;
+	int ret = 0;
+
+	for (i = 0; i < hctx->queue_depth; i++) {
+		struct request *rq = hctx->rqs[i];
+
+		ret = init(data, hctx, rq, i);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+int blk_mq_init_commands(struct request_queue *q,
+			 int (*init)(void *, struct blk_mq_hw_ctx *,
+					struct request *, unsigned int),
+			 void *data)
+{
+	struct blk_mq_hw_ctx *hctx;
+	unsigned int i;
+	int ret = 0;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		ret = blk_mq_init_hw_commands(hctx, init, data);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(blk_mq_init_commands);
+
+static void blk_mq_free_hw_commands(struct blk_mq_hw_ctx *hctx,
+				    void (*free)(void *, struct blk_mq_hw_ctx *,
 					struct request *, unsigned int),
 				    void *data)
 {
@@ -1068,12 +1106,12 @@ static void blk_mq_init_hw_commands(struct blk_mq_hw_ctx *hctx,
 	for (i = 0; i < hctx->queue_depth; i++) {
 		struct request *rq = hctx->rqs[i];
 
-		init(data, hctx, rq, i);
+		free(data, hctx, rq, i);
 	}
 }
 
-void blk_mq_init_commands(struct request_queue *q,
-			  void (*init)(void *, struct blk_mq_hw_ctx *,
+void blk_mq_free_commands(struct request_queue *q,
+			  void (*free)(void *, struct blk_mq_hw_ctx *,
 					struct request *, unsigned int),
 			  void *data)
 {
@@ -1081,9 +1119,9 @@ void blk_mq_init_commands(struct request_queue *q,
 	unsigned int i;
 
 	queue_for_each_hw_ctx(q, hctx, i)
-		blk_mq_init_hw_commands(hctx, init, data);
+		blk_mq_free_hw_commands(hctx, free, data);
 }
-EXPORT_SYMBOL(blk_mq_init_commands);
+EXPORT_SYMBOL(blk_mq_free_commands);
 
 static void blk_mq_free_rq_map(struct blk_mq_hw_ctx *hctx)
 {
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index b1cb3f4c4db4..0eace43cea11 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -490,13 +490,14 @@ static struct blk_mq_reg virtio_mq_reg = {
 	.flags		= BLK_MQ_F_SHOULD_MERGE,
 };
 
-static void virtblk_init_vbr(void *data, struct blk_mq_hw_ctx *hctx,
+static int virtblk_init_vbr(void *data, struct blk_mq_hw_ctx *hctx,
 			     struct request *rq, unsigned int nr)
 {
 	struct virtio_blk *vblk = data;
 	struct virtblk_req *vbr = rq->special;
 
 	sg_init_table(vbr->sg, vblk->sg_elems);
+	return 0;
 }
 
 static int virtblk_probe(struct virtio_device *vdev)
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 18ba8a627f46..33ff10ebcabb 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -117,7 +117,8 @@ enum {
 struct request_queue *blk_mq_init_queue(struct blk_mq_reg *, void *);
 int blk_mq_register_disk(struct gendisk *);
 void blk_mq_unregister_disk(struct gendisk *);
-void blk_mq_init_commands(struct request_queue *, void (*init)(void *data, struct blk_mq_hw_ctx *, struct request *, unsigned int), void *data);
+int blk_mq_init_commands(struct request_queue *, int (*init)(void *data, struct blk_mq_hw_ctx *, struct request *, unsigned int), void *data);
+void blk_mq_free_commands(struct request_queue *, void (*free)(void *data, struct blk_mq_hw_ctx *, struct request *, unsigned int), void *data);
 
 void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
 
-- 
cgit v1.2.3


From 57a7744e09867ebcfa0ccf1d6d529caa7728d552 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Thu, 13 Mar 2014 21:26:42 -0700
Subject: net: Replace u64_stats_fetch_begin_bh to u64_stats_fetch_begin_irq

Replace the bh safe variant with the hard irq safe variant.

We need a hard irq safe variant to deal with netpoll transmitting
packets from hard irq context, and we need it in most if not all of
the places using the bh safe variant.

Except on 32bit uni-processor the code is exactly the same so don't
bother with a bh variant, just have a hard irq safe variant that
everyone can use.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 block/blk-cgroup.h                                |  8 ++++----
 drivers/net/dummy.c                               |  4 ++--
 drivers/net/ethernet/broadcom/b44.c               |  8 ++++----
 drivers/net/ethernet/emulex/benet/be_ethtool.c    | 12 ++++++------
 drivers/net/ethernet/emulex/benet/be_main.c       | 16 ++++++++--------
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c    |  8 ++++----
 drivers/net/ethernet/intel/i40e/i40e_main.c       | 16 ++++++++--------
 drivers/net/ethernet/intel/igb/igb_ethtool.c      | 12 ++++++------
 drivers/net/ethernet/intel/igb/igb_main.c         |  8 ++++----
 drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c  |  8 ++++----
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c     |  8 ++++----
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c |  8 ++++----
 drivers/net/ethernet/marvell/mvneta.c             |  4 ++--
 drivers/net/ethernet/marvell/sky2.c               |  8 ++++----
 drivers/net/ethernet/neterion/vxge/vxge-main.c    |  8 ++++----
 drivers/net/ethernet/nvidia/forcedeth.c           |  8 ++++----
 drivers/net/ethernet/realtek/8139too.c            |  8 ++++----
 drivers/net/ethernet/realtek/r8169.c              |  8 ++++----
 drivers/net/ethernet/tile/tilepro.c               |  4 ++--
 drivers/net/ethernet/via/via-rhine.c              |  8 ++++----
 drivers/net/ifb.c                                 |  8 ++++----
 drivers/net/loopback.c                            |  4 ++--
 drivers/net/macvlan.c                             |  4 ++--
 drivers/net/nlmon.c                               |  4 ++--
 drivers/net/team/team.c                           |  4 ++--
 drivers/net/team/team_mode_loadbalance.c          |  4 ++--
 drivers/net/veth.c                                |  4 ++--
 drivers/net/virtio_net.c                          |  8 ++++----
 drivers/net/xen-netfront.c                        |  4 ++--
 include/linux/u64_stats_sync.h                    | 16 ++++++++--------
 net/8021q/vlan_dev.c                              |  4 ++--
 net/bridge/br_device.c                            |  4 ++--
 net/ipv4/af_inet.c                                |  4 ++--
 net/ipv4/ip_tunnel_core.c                         |  4 ++--
 net/ipv6/ip6_tunnel.c                             |  4 ++--
 net/netfilter/ipvs/ip_vs_ctl.c                    |  4 ++--
 net/openvswitch/datapath.c                        |  4 ++--
 net/openvswitch/vport.c                           |  4 ++--
 38 files changed, 132 insertions(+), 132 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 86154eab9523..604f6d99ab92 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -435,9 +435,9 @@ static inline uint64_t blkg_stat_read(struct blkg_stat *stat)
 	uint64_t v;
 
 	do {
-		start = u64_stats_fetch_begin_bh(&stat->syncp);
+		start = u64_stats_fetch_begin_irq(&stat->syncp);
 		v = stat->cnt;
-	} while (u64_stats_fetch_retry_bh(&stat->syncp, start));
+	} while (u64_stats_fetch_retry_irq(&stat->syncp, start));
 
 	return v;
 }
@@ -508,9 +508,9 @@ static inline struct blkg_rwstat blkg_rwstat_read(struct blkg_rwstat *rwstat)
 	struct blkg_rwstat tmp;
 
 	do {
-		start = u64_stats_fetch_begin_bh(&rwstat->syncp);
+		start = u64_stats_fetch_begin_irq(&rwstat->syncp);
 		tmp = *rwstat;
-	} while (u64_stats_fetch_retry_bh(&rwstat->syncp, start));
+	} while (u64_stats_fetch_retry_irq(&rwstat->syncp, start));
 
 	return tmp;
 }
diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index 1656317c96f8..0932ffbf381b 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -63,10 +63,10 @@ static struct rtnl_link_stats64 *dummy_get_stats64(struct net_device *dev,
 
 		dstats = per_cpu_ptr(dev->dstats, i);
 		do {
-			start = u64_stats_fetch_begin_bh(&dstats->syncp);
+			start = u64_stats_fetch_begin_irq(&dstats->syncp);
 			tbytes = dstats->tx_bytes;
 			tpackets = dstats->tx_packets;
-		} while (u64_stats_fetch_retry_bh(&dstats->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&dstats->syncp, start));
 		stats->tx_bytes += tbytes;
 		stats->tx_packets += tpackets;
 	}
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index 8a7bf7dad898..05ba62589017 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -1685,7 +1685,7 @@ static struct rtnl_link_stats64 *b44_get_stats64(struct net_device *dev,
 	unsigned int start;
 
 	do {
-		start = u64_stats_fetch_begin_bh(&hwstat->syncp);
+		start = u64_stats_fetch_begin_irq(&hwstat->syncp);
 
 		/* Convert HW stats into rtnl_link_stats64 stats. */
 		nstat->rx_packets = hwstat->rx_pkts;
@@ -1719,7 +1719,7 @@ static struct rtnl_link_stats64 *b44_get_stats64(struct net_device *dev,
 		/* Carrier lost counter seems to be broken for some devices */
 		nstat->tx_carrier_errors = hwstat->tx_carrier_lost;
 #endif
-	} while (u64_stats_fetch_retry_bh(&hwstat->syncp, start));
+	} while (u64_stats_fetch_retry_irq(&hwstat->syncp, start));
 
 	return nstat;
 }
@@ -2073,12 +2073,12 @@ static void b44_get_ethtool_stats(struct net_device *dev,
 	do {
 		data_src = &hwstat->tx_good_octets;
 		data_dst = data;
-		start = u64_stats_fetch_begin_bh(&hwstat->syncp);
+		start = u64_stats_fetch_begin_irq(&hwstat->syncp);
 
 		for (i = 0; i < ARRAY_SIZE(b44_gstrings); i++)
 			*data_dst++ = *data_src++;
 
-	} while (u64_stats_fetch_retry_bh(&hwstat->syncp, start));
+	} while (u64_stats_fetch_retry_irq(&hwstat->syncp, start));
 }
 
 static void b44_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index 66759b6ce373..15ba96cba65d 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -357,10 +357,10 @@ be_get_ethtool_stats(struct net_device *netdev,
 		struct be_rx_stats *stats = rx_stats(rxo);
 
 		do {
-			start = u64_stats_fetch_begin_bh(&stats->sync);
+			start = u64_stats_fetch_begin_irq(&stats->sync);
 			data[base] = stats->rx_bytes;
 			data[base + 1] = stats->rx_pkts;
-		} while (u64_stats_fetch_retry_bh(&stats->sync, start));
+		} while (u64_stats_fetch_retry_irq(&stats->sync, start));
 
 		for (i = 2; i < ETHTOOL_RXSTATS_NUM; i++) {
 			p = (u8 *)stats + et_rx_stats[i].offset;
@@ -373,19 +373,19 @@ be_get_ethtool_stats(struct net_device *netdev,
 		struct be_tx_stats *stats = tx_stats(txo);
 
 		do {
-			start = u64_stats_fetch_begin_bh(&stats->sync_compl);
+			start = u64_stats_fetch_begin_irq(&stats->sync_compl);
 			data[base] = stats->tx_compl;
-		} while (u64_stats_fetch_retry_bh(&stats->sync_compl, start));
+		} while (u64_stats_fetch_retry_irq(&stats->sync_compl, start));
 
 		do {
-			start = u64_stats_fetch_begin_bh(&stats->sync);
+			start = u64_stats_fetch_begin_irq(&stats->sync);
 			for (i = 1; i < ETHTOOL_TXSTATS_NUM; i++) {
 				p = (u8 *)stats + et_tx_stats[i].offset;
 				data[base + i] =
 					(et_tx_stats[i].size == sizeof(u64)) ?
 						*(u64 *)p : *(u32 *)p;
 			}
-		} while (u64_stats_fetch_retry_bh(&stats->sync, start));
+		} while (u64_stats_fetch_retry_irq(&stats->sync, start));
 		base += ETHTOOL_TXSTATS_NUM;
 	}
 }
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 239273b7b881..a61f967f9ca1 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -591,10 +591,10 @@ static struct rtnl_link_stats64 *be_get_stats64(struct net_device *netdev,
 	for_all_rx_queues(adapter, rxo, i) {
 		const struct be_rx_stats *rx_stats = rx_stats(rxo);
 		do {
-			start = u64_stats_fetch_begin_bh(&rx_stats->sync);
+			start = u64_stats_fetch_begin_irq(&rx_stats->sync);
 			pkts = rx_stats(rxo)->rx_pkts;
 			bytes = rx_stats(rxo)->rx_bytes;
-		} while (u64_stats_fetch_retry_bh(&rx_stats->sync, start));
+		} while (u64_stats_fetch_retry_irq(&rx_stats->sync, start));
 		stats->rx_packets += pkts;
 		stats->rx_bytes += bytes;
 		stats->multicast += rx_stats(rxo)->rx_mcast_pkts;
@@ -605,10 +605,10 @@ static struct rtnl_link_stats64 *be_get_stats64(struct net_device *netdev,
 	for_all_tx_queues(adapter, txo, i) {
 		const struct be_tx_stats *tx_stats = tx_stats(txo);
 		do {
-			start = u64_stats_fetch_begin_bh(&tx_stats->sync);
+			start = u64_stats_fetch_begin_irq(&tx_stats->sync);
 			pkts = tx_stats(txo)->tx_pkts;
 			bytes = tx_stats(txo)->tx_bytes;
-		} while (u64_stats_fetch_retry_bh(&tx_stats->sync, start));
+		} while (u64_stats_fetch_retry_irq(&tx_stats->sync, start));
 		stats->tx_packets += pkts;
 		stats->tx_bytes += bytes;
 	}
@@ -1408,15 +1408,15 @@ static void be_eqd_update(struct be_adapter *adapter)
 
 		rxo = &adapter->rx_obj[eqo->idx];
 		do {
-			start = u64_stats_fetch_begin_bh(&rxo->stats.sync);
+			start = u64_stats_fetch_begin_irq(&rxo->stats.sync);
 			rx_pkts = rxo->stats.rx_pkts;
-		} while (u64_stats_fetch_retry_bh(&rxo->stats.sync, start));
+		} while (u64_stats_fetch_retry_irq(&rxo->stats.sync, start));
 
 		txo = &adapter->tx_obj[eqo->idx];
 		do {
-			start = u64_stats_fetch_begin_bh(&txo->stats.sync);
+			start = u64_stats_fetch_begin_irq(&txo->stats.sync);
 			tx_pkts = txo->stats.tx_reqs;
-		} while (u64_stats_fetch_retry_bh(&txo->stats.sync, start));
+		} while (u64_stats_fetch_retry_irq(&txo->stats.sync, start));
 
 
 		/* Skip, if wrapped around or first calculation */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 8ee224fdc1d1..6049e63a826d 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -653,18 +653,18 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 
 		/* process Tx ring statistics */
 		do {
-			start = u64_stats_fetch_begin_bh(&tx_ring->syncp);
+			start = u64_stats_fetch_begin_irq(&tx_ring->syncp);
 			data[i] = tx_ring->stats.packets;
 			data[i + 1] = tx_ring->stats.bytes;
-		} while (u64_stats_fetch_retry_bh(&tx_ring->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&tx_ring->syncp, start));
 
 		/* Rx ring is the 2nd half of the queue pair */
 		rx_ring = &tx_ring[1];
 		do {
-			start = u64_stats_fetch_begin_bh(&rx_ring->syncp);
+			start = u64_stats_fetch_begin_irq(&rx_ring->syncp);
 			data[i + 2] = rx_ring->stats.packets;
 			data[i + 3] = rx_ring->stats.bytes;
-		} while (u64_stats_fetch_retry_bh(&rx_ring->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&rx_ring->syncp, start));
 	}
 	rcu_read_unlock();
 	if (vsi == pf->vsi[pf->lan_vsi]) {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 7379e5a9126b..c66a11e31e6f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -376,20 +376,20 @@ static struct rtnl_link_stats64 *i40e_get_netdev_stats_struct(
 			continue;
 
 		do {
-			start = u64_stats_fetch_begin_bh(&tx_ring->syncp);
+			start = u64_stats_fetch_begin_irq(&tx_ring->syncp);
 			packets = tx_ring->stats.packets;
 			bytes   = tx_ring->stats.bytes;
-		} while (u64_stats_fetch_retry_bh(&tx_ring->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&tx_ring->syncp, start));
 
 		stats->tx_packets += packets;
 		stats->tx_bytes   += bytes;
 		rx_ring = &tx_ring[1];
 
 		do {
-			start = u64_stats_fetch_begin_bh(&rx_ring->syncp);
+			start = u64_stats_fetch_begin_irq(&rx_ring->syncp);
 			packets = rx_ring->stats.packets;
 			bytes   = rx_ring->stats.bytes;
-		} while (u64_stats_fetch_retry_bh(&rx_ring->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&rx_ring->syncp, start));
 
 		stats->rx_packets += packets;
 		stats->rx_bytes   += bytes;
@@ -770,10 +770,10 @@ void i40e_update_stats(struct i40e_vsi *vsi)
 		p = ACCESS_ONCE(vsi->tx_rings[q]);
 
 		do {
-			start = u64_stats_fetch_begin_bh(&p->syncp);
+			start = u64_stats_fetch_begin_irq(&p->syncp);
 			packets = p->stats.packets;
 			bytes = p->stats.bytes;
-		} while (u64_stats_fetch_retry_bh(&p->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&p->syncp, start));
 		tx_b += bytes;
 		tx_p += packets;
 		tx_restart += p->tx_stats.restart_queue;
@@ -782,10 +782,10 @@ void i40e_update_stats(struct i40e_vsi *vsi)
 		/* Rx queue is part of the same block as Tx queue */
 		p = &p[1];
 		do {
-			start = u64_stats_fetch_begin_bh(&p->syncp);
+			start = u64_stats_fetch_begin_irq(&p->syncp);
 			packets = p->stats.packets;
 			bytes = p->stats.bytes;
-		} while (u64_stats_fetch_retry_bh(&p->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&p->syncp, start));
 		rx_b += bytes;
 		rx_p += packets;
 		rx_buf += p->rx_stats.alloc_buff_failed;
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 170e4dbddc11..e35bc1faa452 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -2273,15 +2273,15 @@ static void igb_get_ethtool_stats(struct net_device *netdev,
 
 		ring = adapter->tx_ring[j];
 		do {
-			start = u64_stats_fetch_begin_bh(&ring->tx_syncp);
+			start = u64_stats_fetch_begin_irq(&ring->tx_syncp);
 			data[i]   = ring->tx_stats.packets;
 			data[i+1] = ring->tx_stats.bytes;
 			data[i+2] = ring->tx_stats.restart_queue;
-		} while (u64_stats_fetch_retry_bh(&ring->tx_syncp, start));
+		} while (u64_stats_fetch_retry_irq(&ring->tx_syncp, start));
 		do {
-			start = u64_stats_fetch_begin_bh(&ring->tx_syncp2);
+			start = u64_stats_fetch_begin_irq(&ring->tx_syncp2);
 			restart2  = ring->tx_stats.restart_queue2;
-		} while (u64_stats_fetch_retry_bh(&ring->tx_syncp2, start));
+		} while (u64_stats_fetch_retry_irq(&ring->tx_syncp2, start));
 		data[i+2] += restart2;
 
 		i += IGB_TX_QUEUE_STATS_LEN;
@@ -2289,13 +2289,13 @@ static void igb_get_ethtool_stats(struct net_device *netdev,
 	for (j = 0; j < adapter->num_rx_queues; j++) {
 		ring = adapter->rx_ring[j];
 		do {
-			start = u64_stats_fetch_begin_bh(&ring->rx_syncp);
+			start = u64_stats_fetch_begin_irq(&ring->rx_syncp);
 			data[i]   = ring->rx_stats.packets;
 			data[i+1] = ring->rx_stats.bytes;
 			data[i+2] = ring->rx_stats.drops;
 			data[i+3] = ring->rx_stats.csum_err;
 			data[i+4] = ring->rx_stats.alloc_failed;
-		} while (u64_stats_fetch_retry_bh(&ring->rx_syncp, start));
+		} while (u64_stats_fetch_retry_irq(&ring->rx_syncp, start));
 		i += IGB_RX_QUEUE_STATS_LEN;
 	}
 	spin_unlock(&adapter->stats64_lock);
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index ea8b9c41cf9f..f81d87cfcc8d 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -5168,10 +5168,10 @@ void igb_update_stats(struct igb_adapter *adapter,
 		}
 
 		do {
-			start = u64_stats_fetch_begin_bh(&ring->rx_syncp);
+			start = u64_stats_fetch_begin_irq(&ring->rx_syncp);
 			_bytes = ring->rx_stats.bytes;
 			_packets = ring->rx_stats.packets;
-		} while (u64_stats_fetch_retry_bh(&ring->rx_syncp, start));
+		} while (u64_stats_fetch_retry_irq(&ring->rx_syncp, start));
 		bytes += _bytes;
 		packets += _packets;
 	}
@@ -5184,10 +5184,10 @@ void igb_update_stats(struct igb_adapter *adapter,
 	for (i = 0; i < adapter->num_tx_queues; i++) {
 		struct igb_ring *ring = adapter->tx_ring[i];
 		do {
-			start = u64_stats_fetch_begin_bh(&ring->tx_syncp);
+			start = u64_stats_fetch_begin_irq(&ring->tx_syncp);
 			_bytes = ring->tx_stats.bytes;
 			_packets = ring->tx_stats.packets;
-		} while (u64_stats_fetch_retry_bh(&ring->tx_syncp, start));
+		} while (u64_stats_fetch_retry_irq(&ring->tx_syncp, start));
 		bytes += _bytes;
 		packets += _packets;
 	}
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 24dd6f0233f3..6c55c14d082a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -1128,10 +1128,10 @@ static void ixgbe_get_ethtool_stats(struct net_device *netdev,
 		}
 
 		do {
-			start = u64_stats_fetch_begin_bh(&ring->syncp);
+			start = u64_stats_fetch_begin_irq(&ring->syncp);
 			data[i]   = ring->stats.packets;
 			data[i+1] = ring->stats.bytes;
-		} while (u64_stats_fetch_retry_bh(&ring->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
 		i += 2;
 #ifdef BP_EXTENDED_STATS
 		data[i] = ring->stats.yields;
@@ -1156,10 +1156,10 @@ static void ixgbe_get_ethtool_stats(struct net_device *netdev,
 		}
 
 		do {
-			start = u64_stats_fetch_begin_bh(&ring->syncp);
+			start = u64_stats_fetch_begin_irq(&ring->syncp);
 			data[i]   = ring->stats.packets;
 			data[i+1] = ring->stats.bytes;
-		} while (u64_stats_fetch_retry_bh(&ring->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
 		i += 2;
 #ifdef BP_EXTENDED_STATS
 		data[i] = ring->stats.yields;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 851c41377b47..5d314fe873bb 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -7293,10 +7293,10 @@ static struct rtnl_link_stats64 *ixgbe_get_stats64(struct net_device *netdev,
 
 		if (ring) {
 			do {
-				start = u64_stats_fetch_begin_bh(&ring->syncp);
+				start = u64_stats_fetch_begin_irq(&ring->syncp);
 				packets = ring->stats.packets;
 				bytes   = ring->stats.bytes;
-			} while (u64_stats_fetch_retry_bh(&ring->syncp, start));
+			} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
 			stats->rx_packets += packets;
 			stats->rx_bytes   += bytes;
 		}
@@ -7309,10 +7309,10 @@ static struct rtnl_link_stats64 *ixgbe_get_stats64(struct net_device *netdev,
 
 		if (ring) {
 			do {
-				start = u64_stats_fetch_begin_bh(&ring->syncp);
+				start = u64_stats_fetch_begin_irq(&ring->syncp);
 				packets = ring->stats.packets;
 				bytes   = ring->stats.bytes;
-			} while (u64_stats_fetch_retry_bh(&ring->syncp, start));
+			} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
 			stats->tx_packets += packets;
 			stats->tx_bytes   += bytes;
 		}
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 475341d0ce7e..8581079791fe 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -3337,10 +3337,10 @@ static struct rtnl_link_stats64 *ixgbevf_get_stats(struct net_device *netdev,
 	for (i = 0; i < adapter->num_rx_queues; i++) {
 		ring = adapter->rx_ring[i];
 		do {
-			start = u64_stats_fetch_begin_bh(&ring->syncp);
+			start = u64_stats_fetch_begin_irq(&ring->syncp);
 			bytes = ring->stats.bytes;
 			packets = ring->stats.packets;
-		} while (u64_stats_fetch_retry_bh(&ring->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
 		stats->rx_bytes += bytes;
 		stats->rx_packets += packets;
 	}
@@ -3348,10 +3348,10 @@ static struct rtnl_link_stats64 *ixgbevf_get_stats(struct net_device *netdev,
 	for (i = 0; i < adapter->num_tx_queues; i++) {
 		ring = adapter->tx_ring[i];
 		do {
-			start = u64_stats_fetch_begin_bh(&ring->syncp);
+			start = u64_stats_fetch_begin_irq(&ring->syncp);
 			bytes = ring->stats.bytes;
 			packets = ring->stats.packets;
-		} while (u64_stats_fetch_retry_bh(&ring->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
 		stats->tx_bytes += bytes;
 		stats->tx_packets += packets;
 	}
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 12c6a66e54d1..f3afcbdbb725 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -508,12 +508,12 @@ struct rtnl_link_stats64 *mvneta_get_stats64(struct net_device *dev,
 
 		cpu_stats = per_cpu_ptr(pp->stats, cpu);
 		do {
-			start = u64_stats_fetch_begin_bh(&cpu_stats->syncp);
+			start = u64_stats_fetch_begin_irq(&cpu_stats->syncp);
 			rx_packets = cpu_stats->rx_packets;
 			rx_bytes   = cpu_stats->rx_bytes;
 			tx_packets = cpu_stats->tx_packets;
 			tx_bytes   = cpu_stats->tx_bytes;
-		} while (u64_stats_fetch_retry_bh(&cpu_stats->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start));
 
 		stats->rx_packets += rx_packets;
 		stats->rx_bytes   += rx_bytes;
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 2434611d1b4e..5a5b23741179 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -3908,19 +3908,19 @@ static struct rtnl_link_stats64 *sky2_get_stats(struct net_device *dev,
 	u64 _bytes, _packets;
 
 	do {
-		start = u64_stats_fetch_begin_bh(&sky2->rx_stats.syncp);
+		start = u64_stats_fetch_begin_irq(&sky2->rx_stats.syncp);
 		_bytes = sky2->rx_stats.bytes;
 		_packets = sky2->rx_stats.packets;
-	} while (u64_stats_fetch_retry_bh(&sky2->rx_stats.syncp, start));
+	} while (u64_stats_fetch_retry_irq(&sky2->rx_stats.syncp, start));
 
 	stats->rx_packets = _packets;
 	stats->rx_bytes = _bytes;
 
 	do {
-		start = u64_stats_fetch_begin_bh(&sky2->tx_stats.syncp);
+		start = u64_stats_fetch_begin_irq(&sky2->tx_stats.syncp);
 		_bytes = sky2->tx_stats.bytes;
 		_packets = sky2->tx_stats.packets;
-	} while (u64_stats_fetch_retry_bh(&sky2->tx_stats.syncp, start));
+	} while (u64_stats_fetch_retry_irq(&sky2->tx_stats.syncp, start));
 
 	stats->tx_packets = _packets;
 	stats->tx_bytes = _bytes;
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c
index c83cedd26dec..c5bb1ace4a74 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-main.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c
@@ -3134,12 +3134,12 @@ vxge_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *net_stats)
 		u64 packets, bytes, multicast;
 
 		do {
-			start = u64_stats_fetch_begin_bh(&rxstats->syncp);
+			start = u64_stats_fetch_begin_irq(&rxstats->syncp);
 
 			packets   = rxstats->rx_frms;
 			multicast = rxstats->rx_mcast;
 			bytes     = rxstats->rx_bytes;
-		} while (u64_stats_fetch_retry_bh(&rxstats->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&rxstats->syncp, start));
 
 		net_stats->rx_packets += packets;
 		net_stats->rx_bytes += bytes;
@@ -3149,11 +3149,11 @@ vxge_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *net_stats)
 		net_stats->rx_dropped += rxstats->rx_dropped;
 
 		do {
-			start = u64_stats_fetch_begin_bh(&txstats->syncp);
+			start = u64_stats_fetch_begin_irq(&txstats->syncp);
 
 			packets = txstats->tx_frms;
 			bytes   = txstats->tx_bytes;
-		} while (u64_stats_fetch_retry_bh(&txstats->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&txstats->syncp, start));
 
 		net_stats->tx_packets += packets;
 		net_stats->tx_bytes += bytes;
diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c
index bad3c057ee8a..811be0bccd14 100644
--- a/drivers/net/ethernet/nvidia/forcedeth.c
+++ b/drivers/net/ethernet/nvidia/forcedeth.c
@@ -1753,19 +1753,19 @@ nv_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *storage)
 
 	/* software stats */
 	do {
-		syncp_start = u64_stats_fetch_begin_bh(&np->swstats_rx_syncp);
+		syncp_start = u64_stats_fetch_begin_irq(&np->swstats_rx_syncp);
 		storage->rx_packets       = np->stat_rx_packets;
 		storage->rx_bytes         = np->stat_rx_bytes;
 		storage->rx_dropped       = np->stat_rx_dropped;
 		storage->rx_missed_errors = np->stat_rx_missed_errors;
-	} while (u64_stats_fetch_retry_bh(&np->swstats_rx_syncp, syncp_start));
+	} while (u64_stats_fetch_retry_irq(&np->swstats_rx_syncp, syncp_start));
 
 	do {
-		syncp_start = u64_stats_fetch_begin_bh(&np->swstats_tx_syncp);
+		syncp_start = u64_stats_fetch_begin_irq(&np->swstats_tx_syncp);
 		storage->tx_packets = np->stat_tx_packets;
 		storage->tx_bytes   = np->stat_tx_bytes;
 		storage->tx_dropped = np->stat_tx_dropped;
-	} while (u64_stats_fetch_retry_bh(&np->swstats_tx_syncp, syncp_start));
+	} while (u64_stats_fetch_retry_irq(&np->swstats_tx_syncp, syncp_start));
 
 	/* If the nic supports hw counters then retrieve latest values */
 	if (np->driver_data & DEV_HAS_STATISTICS_V123) {
diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index 8cb2f357026e..2e5df148af4c 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -2522,16 +2522,16 @@ rtl8139_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	netdev_stats_to_stats64(stats, &dev->stats);
 
 	do {
-		start = u64_stats_fetch_begin_bh(&tp->rx_stats.syncp);
+		start = u64_stats_fetch_begin_irq(&tp->rx_stats.syncp);
 		stats->rx_packets = tp->rx_stats.packets;
 		stats->rx_bytes = tp->rx_stats.bytes;
-	} while (u64_stats_fetch_retry_bh(&tp->rx_stats.syncp, start));
+	} while (u64_stats_fetch_retry_irq(&tp->rx_stats.syncp, start));
 
 	do {
-		start = u64_stats_fetch_begin_bh(&tp->tx_stats.syncp);
+		start = u64_stats_fetch_begin_irq(&tp->tx_stats.syncp);
 		stats->tx_packets = tp->tx_stats.packets;
 		stats->tx_bytes = tp->tx_stats.bytes;
-	} while (u64_stats_fetch_retry_bh(&tp->tx_stats.syncp, start));
+	} while (u64_stats_fetch_retry_irq(&tp->tx_stats.syncp, start));
 
 	return stats;
 }
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 90c14d16f261..aa1c079f231d 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -6590,17 +6590,17 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 		rtl8169_rx_missed(dev, ioaddr);
 
 	do {
-		start = u64_stats_fetch_begin_bh(&tp->rx_stats.syncp);
+		start = u64_stats_fetch_begin_irq(&tp->rx_stats.syncp);
 		stats->rx_packets = tp->rx_stats.packets;
 		stats->rx_bytes	= tp->rx_stats.bytes;
-	} while (u64_stats_fetch_retry_bh(&tp->rx_stats.syncp, start));
+	} while (u64_stats_fetch_retry_irq(&tp->rx_stats.syncp, start));
 
 
 	do {
-		start = u64_stats_fetch_begin_bh(&tp->tx_stats.syncp);
+		start = u64_stats_fetch_begin_irq(&tp->tx_stats.syncp);
 		stats->tx_packets = tp->tx_stats.packets;
 		stats->tx_bytes	= tp->tx_stats.bytes;
-	} while (u64_stats_fetch_retry_bh(&tp->tx_stats.syncp, start));
+	} while (u64_stats_fetch_retry_irq(&tp->tx_stats.syncp, start));
 
 	stats->rx_dropped	= dev->stats.rx_dropped;
 	stats->tx_dropped	= dev->stats.tx_dropped;
diff --git a/drivers/net/ethernet/tile/tilepro.c b/drivers/net/ethernet/tile/tilepro.c
index edb2e12a0fe2..7e33973487ee 100644
--- a/drivers/net/ethernet/tile/tilepro.c
+++ b/drivers/net/ethernet/tile/tilepro.c
@@ -2068,14 +2068,14 @@ static struct rtnl_link_stats64 *tile_net_get_stats64(struct net_device *dev,
 		cpu_stats = &priv->cpu[i]->stats;
 
 		do {
-			start = u64_stats_fetch_begin_bh(&cpu_stats->syncp);
+			start = u64_stats_fetch_begin_irq(&cpu_stats->syncp);
 			trx_packets = cpu_stats->rx_packets;
 			ttx_packets = cpu_stats->tx_packets;
 			trx_bytes   = cpu_stats->rx_bytes;
 			ttx_bytes   = cpu_stats->tx_bytes;
 			trx_errors  = cpu_stats->rx_errors;
 			trx_dropped = cpu_stats->rx_dropped;
-		} while (u64_stats_fetch_retry_bh(&cpu_stats->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start));
 
 		rx_packets += trx_packets;
 		tx_packets += ttx_packets;
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index ef312bc6b865..5bc1a2d02dc1 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -2070,16 +2070,16 @@ rhine_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	netdev_stats_to_stats64(stats, &dev->stats);
 
 	do {
-		start = u64_stats_fetch_begin_bh(&rp->rx_stats.syncp);
+		start = u64_stats_fetch_begin_irq(&rp->rx_stats.syncp);
 		stats->rx_packets = rp->rx_stats.packets;
 		stats->rx_bytes = rp->rx_stats.bytes;
-	} while (u64_stats_fetch_retry_bh(&rp->rx_stats.syncp, start));
+	} while (u64_stats_fetch_retry_irq(&rp->rx_stats.syncp, start));
 
 	do {
-		start = u64_stats_fetch_begin_bh(&rp->tx_stats.syncp);
+		start = u64_stats_fetch_begin_irq(&rp->tx_stats.syncp);
 		stats->tx_packets = rp->tx_stats.packets;
 		stats->tx_bytes = rp->tx_stats.bytes;
-	} while (u64_stats_fetch_retry_bh(&rp->tx_stats.syncp, start));
+	} while (u64_stats_fetch_retry_irq(&rp->tx_stats.syncp, start));
 
 	return stats;
 }
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index c14d39bf32d0..1da36764b1a4 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -136,18 +136,18 @@ static struct rtnl_link_stats64 *ifb_stats64(struct net_device *dev,
 	unsigned int start;
 
 	do {
-		start = u64_stats_fetch_begin_bh(&dp->rsync);
+		start = u64_stats_fetch_begin_irq(&dp->rsync);
 		stats->rx_packets = dp->rx_packets;
 		stats->rx_bytes = dp->rx_bytes;
-	} while (u64_stats_fetch_retry_bh(&dp->rsync, start));
+	} while (u64_stats_fetch_retry_irq(&dp->rsync, start));
 
 	do {
-		start = u64_stats_fetch_begin_bh(&dp->tsync);
+		start = u64_stats_fetch_begin_irq(&dp->tsync);
 
 		stats->tx_packets = dp->tx_packets;
 		stats->tx_bytes = dp->tx_bytes;
 
-	} while (u64_stats_fetch_retry_bh(&dp->tsync, start));
+	} while (u64_stats_fetch_retry_irq(&dp->tsync, start));
 
 	stats->rx_dropped = dev->stats.rx_dropped;
 	stats->tx_dropped = dev->stats.tx_dropped;
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index 282effee7e1c..bb96409f8c05 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -111,10 +111,10 @@ static struct rtnl_link_stats64 *loopback_get_stats64(struct net_device *dev,
 
 		lb_stats = per_cpu_ptr(dev->lstats, i);
 		do {
-			start = u64_stats_fetch_begin_bh(&lb_stats->syncp);
+			start = u64_stats_fetch_begin_irq(&lb_stats->syncp);
 			tbytes = lb_stats->bytes;
 			tpackets = lb_stats->packets;
-		} while (u64_stats_fetch_retry_bh(&lb_stats->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&lb_stats->syncp, start));
 		bytes   += tbytes;
 		packets += tpackets;
 	}
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index c683ac2c8c94..753a8c23d15d 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -582,13 +582,13 @@ static struct rtnl_link_stats64 *macvlan_dev_get_stats64(struct net_device *dev,
 		for_each_possible_cpu(i) {
 			p = per_cpu_ptr(vlan->pcpu_stats, i);
 			do {
-				start = u64_stats_fetch_begin_bh(&p->syncp);
+				start = u64_stats_fetch_begin_irq(&p->syncp);
 				rx_packets	= p->rx_packets;
 				rx_bytes	= p->rx_bytes;
 				rx_multicast	= p->rx_multicast;
 				tx_packets	= p->tx_packets;
 				tx_bytes	= p->tx_bytes;
-			} while (u64_stats_fetch_retry_bh(&p->syncp, start));
+			} while (u64_stats_fetch_retry_irq(&p->syncp, start));
 
 			stats->rx_packets	+= rx_packets;
 			stats->rx_bytes		+= rx_bytes;
diff --git a/drivers/net/nlmon.c b/drivers/net/nlmon.c
index 14ce7de6a933..6929b03ec638 100644
--- a/drivers/net/nlmon.c
+++ b/drivers/net/nlmon.c
@@ -90,10 +90,10 @@ nlmon_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 		nl_stats = per_cpu_ptr(dev->lstats, i);
 
 		do {
-			start = u64_stats_fetch_begin_bh(&nl_stats->syncp);
+			start = u64_stats_fetch_begin_irq(&nl_stats->syncp);
 			tbytes = nl_stats->bytes;
 			tpackets = nl_stats->packets;
-		} while (u64_stats_fetch_retry_bh(&nl_stats->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&nl_stats->syncp, start));
 
 		packets += tpackets;
 		bytes += tbytes;
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index aea92f02401b..2b1a1d61072c 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1761,13 +1761,13 @@ team_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	for_each_possible_cpu(i) {
 		p = per_cpu_ptr(team->pcpu_stats, i);
 		do {
-			start = u64_stats_fetch_begin_bh(&p->syncp);
+			start = u64_stats_fetch_begin_irq(&p->syncp);
 			rx_packets	= p->rx_packets;
 			rx_bytes	= p->rx_bytes;
 			rx_multicast	= p->rx_multicast;
 			tx_packets	= p->tx_packets;
 			tx_bytes	= p->tx_bytes;
-		} while (u64_stats_fetch_retry_bh(&p->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&p->syncp, start));
 
 		stats->rx_packets	+= rx_packets;
 		stats->rx_bytes		+= rx_bytes;
diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c
index d671fc3ac5ac..dbde3412ee5e 100644
--- a/drivers/net/team/team_mode_loadbalance.c
+++ b/drivers/net/team/team_mode_loadbalance.c
@@ -432,9 +432,9 @@ static void __lb_one_cpu_stats_add(struct lb_stats *acc_stats,
 	struct lb_stats tmp;
 
 	do {
-		start = u64_stats_fetch_begin_bh(syncp);
+		start = u64_stats_fetch_begin_irq(syncp);
 		tmp.tx_bytes = cpu_stats->tx_bytes;
-	} while (u64_stats_fetch_retry_bh(syncp, start));
+	} while (u64_stats_fetch_retry_irq(syncp, start));
 	acc_stats->tx_bytes += tmp.tx_bytes;
 }
 
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 3aca92e80e1e..e1c77d4b80e4 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -156,10 +156,10 @@ static u64 veth_stats_one(struct pcpu_vstats *result, struct net_device *dev)
 		unsigned int start;
 
 		do {
-			start = u64_stats_fetch_begin_bh(&stats->syncp);
+			start = u64_stats_fetch_begin_irq(&stats->syncp);
 			packets = stats->packets;
 			bytes = stats->bytes;
-		} while (u64_stats_fetch_retry_bh(&stats->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
 		result->packets += packets;
 		result->bytes += bytes;
 	}
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 5632a99cbbd2..80d84c446962 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1000,16 +1000,16 @@ static struct rtnl_link_stats64 *virtnet_stats(struct net_device *dev,
 		u64 tpackets, tbytes, rpackets, rbytes;
 
 		do {
-			start = u64_stats_fetch_begin_bh(&stats->tx_syncp);
+			start = u64_stats_fetch_begin_irq(&stats->tx_syncp);
 			tpackets = stats->tx_packets;
 			tbytes   = stats->tx_bytes;
-		} while (u64_stats_fetch_retry_bh(&stats->tx_syncp, start));
+		} while (u64_stats_fetch_retry_irq(&stats->tx_syncp, start));
 
 		do {
-			start = u64_stats_fetch_begin_bh(&stats->rx_syncp);
+			start = u64_stats_fetch_begin_irq(&stats->rx_syncp);
 			rpackets = stats->rx_packets;
 			rbytes   = stats->rx_bytes;
-		} while (u64_stats_fetch_retry_bh(&stats->rx_syncp, start));
+		} while (u64_stats_fetch_retry_irq(&stats->rx_syncp, start));
 
 		tot->rx_packets += rpackets;
 		tot->tx_packets += tpackets;
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index a38f03ded5a4..49f3b3dbbed8 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1060,13 +1060,13 @@ static struct rtnl_link_stats64 *xennet_get_stats64(struct net_device *dev,
 		unsigned int start;
 
 		do {
-			start = u64_stats_fetch_begin_bh(&stats->syncp);
+			start = u64_stats_fetch_begin_irq(&stats->syncp);
 
 			rx_packets = stats->rx_packets;
 			tx_packets = stats->tx_packets;
 			rx_bytes = stats->rx_bytes;
 			tx_bytes = stats->tx_bytes;
-		} while (u64_stats_fetch_retry_bh(&stats->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
 
 		tot->rx_packets += rx_packets;
 		tot->tx_packets += tx_packets;
diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h
index 7bfabd20204c..4b4439e75f45 100644
--- a/include/linux/u64_stats_sync.h
+++ b/include/linux/u64_stats_sync.h
@@ -27,8 +27,8 @@
  *    (On UP, there is no seqcount_t protection, a reader allowing interrupts could
  *     read partial values)
  *
- * 7) For softirq uses, readers can use u64_stats_fetch_begin_bh() and
- *    u64_stats_fetch_retry_bh() helpers
+ * 7) For irq and softirq uses, readers can use u64_stats_fetch_begin_irq() and
+ *    u64_stats_fetch_retry_irq() helpers
  *
  * Usage :
  *
@@ -114,31 +114,31 @@ static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp,
 }
 
 /*
- * In case softirq handlers can update u64 counters, readers can use following helpers
+ * In case irq handlers can update u64 counters, readers can use following helpers
  * - SMP 32bit arches use seqcount protection, irq safe.
- * - UP 32bit must disable BH.
+ * - UP 32bit must disable irqs.
  * - 64bit have no problem atomically reading u64 values, irq safe.
  */
-static inline unsigned int u64_stats_fetch_begin_bh(const struct u64_stats_sync *syncp)
+static inline unsigned int u64_stats_fetch_begin_irq(const struct u64_stats_sync *syncp)
 {
 #if BITS_PER_LONG==32 && defined(CONFIG_SMP)
 	return read_seqcount_begin(&syncp->seq);
 #else
 #if BITS_PER_LONG==32
-	local_bh_disable();
+	local_irq_disable();
 #endif
 	return 0;
 #endif
 }
 
-static inline bool u64_stats_fetch_retry_bh(const struct u64_stats_sync *syncp,
+static inline bool u64_stats_fetch_retry_irq(const struct u64_stats_sync *syncp,
 					 unsigned int start)
 {
 #if BITS_PER_LONG==32 && defined(CONFIG_SMP)
 	return read_seqcount_retry(&syncp->seq, start);
 #else
 #if BITS_PER_LONG==32
-	local_bh_enable();
+	local_irq_enable();
 #endif
 	return false;
 #endif
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index b38e715b1cd4..4f3e9073cb49 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -678,13 +678,13 @@ static struct rtnl_link_stats64 *vlan_dev_get_stats64(struct net_device *dev, st
 
 			p = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i);
 			do {
-				start = u64_stats_fetch_begin_bh(&p->syncp);
+				start = u64_stats_fetch_begin_irq(&p->syncp);
 				rxpackets	= p->rx_packets;
 				rxbytes		= p->rx_bytes;
 				rxmulticast	= p->rx_multicast;
 				txpackets	= p->tx_packets;
 				txbytes		= p->tx_bytes;
-			} while (u64_stats_fetch_retry_bh(&p->syncp, start));
+			} while (u64_stats_fetch_retry_irq(&p->syncp, start));
 
 			stats->rx_packets	+= rxpackets;
 			stats->rx_bytes		+= rxbytes;
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index b063050b63e2..f2a08477e0f5 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -136,9 +136,9 @@ static struct rtnl_link_stats64 *br_get_stats64(struct net_device *dev,
 		const struct pcpu_sw_netstats *bstats
 			= per_cpu_ptr(br->stats, cpu);
 		do {
-			start = u64_stats_fetch_begin_bh(&bstats->syncp);
+			start = u64_stats_fetch_begin_irq(&bstats->syncp);
 			memcpy(&tmp, bstats, sizeof(tmp));
-		} while (u64_stats_fetch_retry_bh(&bstats->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&bstats->syncp, start));
 		sum.tx_bytes   += tmp.tx_bytes;
 		sum.tx_packets += tmp.tx_packets;
 		sum.rx_bytes   += tmp.rx_bytes;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 19ab78aca547..8c54870db792 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1505,9 +1505,9 @@ u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_offset)
 		bhptr = per_cpu_ptr(mib[0], cpu);
 		syncp = (struct u64_stats_sync *)(bhptr + syncp_offset);
 		do {
-			start = u64_stats_fetch_begin_bh(syncp);
+			start = u64_stats_fetch_begin_irq(syncp);
 			v = *(((u64 *) bhptr) + offt);
-		} while (u64_stats_fetch_retry_bh(syncp, start));
+		} while (u64_stats_fetch_retry_irq(syncp, start));
 
 		res += v;
 	}
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 6f847dd56dbc..b86f0a37fa7c 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -161,12 +161,12 @@ struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
 		unsigned int start;
 
 		do {
-			start = u64_stats_fetch_begin_bh(&tstats->syncp);
+			start = u64_stats_fetch_begin_irq(&tstats->syncp);
 			rx_packets = tstats->rx_packets;
 			tx_packets = tstats->tx_packets;
 			rx_bytes = tstats->rx_bytes;
 			tx_bytes = tstats->tx_bytes;
-		} while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&tstats->syncp, start));
 
 		tot->rx_packets += rx_packets;
 		tot->tx_packets += tx_packets;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 8ad59f4811df..e1df691d78be 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -108,12 +108,12 @@ static struct net_device_stats *ip6_get_stats(struct net_device *dev)
 						   per_cpu_ptr(dev->tstats, i);
 
 		do {
-			start = u64_stats_fetch_begin_bh(&tstats->syncp);
+			start = u64_stats_fetch_begin_irq(&tstats->syncp);
 			tmp.rx_packets = tstats->rx_packets;
 			tmp.rx_bytes = tstats->rx_bytes;
 			tmp.tx_packets = tstats->tx_packets;
 			tmp.tx_bytes =  tstats->tx_bytes;
-		} while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&tstats->syncp, start));
 
 		sum.rx_packets += tmp.rx_packets;
 		sum.rx_bytes   += tmp.rx_bytes;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 35be035ee0ce..d6d75841352a 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2177,10 +2177,10 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
 		__u64 inbytes, outbytes;
 
 		do {
-			start = u64_stats_fetch_begin_bh(&u->syncp);
+			start = u64_stats_fetch_begin_irq(&u->syncp);
 			inbytes = u->ustats.inbytes;
 			outbytes = u->ustats.outbytes;
-		} while (u64_stats_fetch_retry_bh(&u->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&u->syncp, start));
 
 		seq_printf(seq, "%3X %8X %8X %8X %16LX %16LX\n",
 			   i, u->ustats.conns, u->ustats.inpkts,
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 36f8872cb072..c53fe0c9697c 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -606,9 +606,9 @@ static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats,
 		percpu_stats = per_cpu_ptr(dp->stats_percpu, i);
 
 		do {
-			start = u64_stats_fetch_begin_bh(&percpu_stats->syncp);
+			start = u64_stats_fetch_begin_irq(&percpu_stats->syncp);
 			local_stats = *percpu_stats;
-		} while (u64_stats_fetch_retry_bh(&percpu_stats->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start));
 
 		stats->n_hit += local_stats.n_hit;
 		stats->n_missed += local_stats.n_missed;
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 3b4db3220456..42c0f4a0b78c 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -277,9 +277,9 @@ void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats)
 		percpu_stats = per_cpu_ptr(vport->percpu_stats, i);
 
 		do {
-			start = u64_stats_fetch_begin_bh(&percpu_stats->syncp);
+			start = u64_stats_fetch_begin_irq(&percpu_stats->syncp);
 			local_stats = *percpu_stats;
-		} while (u64_stats_fetch_retry_bh(&percpu_stats->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start));
 
 		stats->rx_bytes		+= local_stats.rx_bytes;
 		stats->rx_packets	+= local_stats.rx_packets;
-- 
cgit v1.2.3


From 4b409c50343f41596f76006460cb5adc4d25824e Mon Sep 17 00:00:00 2001
From: "Stephen M. Cameron" <scameron@beardog.cce.hp.com>
Date: Tue, 18 Feb 2014 13:57:57 -0600
Subject: [SCSI] hpsa: add HP/3PAR vendor id to pci_ids.h

Signed-off-by: Stephen M. Cameron <scameron@beardog.cce.hp.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
---
 include/linux/pci_ids.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 97fbecdd7a40..0154d9b1b96c 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -726,6 +726,7 @@
 #define PCI_DEVICE_ID_SI_7018		0x7018
 
 #define PCI_VENDOR_ID_HP		0x103c
+#define PCI_VENDOR_ID_HP_3PAR		0x1590
 #define PCI_DEVICE_ID_HP_VISUALIZE_EG	0x1005
 #define PCI_DEVICE_ID_HP_VISUALIZE_FX6	0x1006
 #define PCI_DEVICE_ID_HP_VISUALIZE_FX4	0x1008
-- 
cgit v1.2.3


From 0283f9a529c81e64bafea80d6d3e056d1c3f656d Mon Sep 17 00:00:00 2001
From: Mark Charlebois <charlebm@gmail.com>
Date: Mon, 17 Mar 2014 13:18:26 +1030
Subject: module: LLVMLinux: Remove unused function warning from __param_check
 macro

This code makes a compile time type check that is optimized away. Clang
complains that it generates an unused function:

linux/kernel/panic.c:471:1: warning: unused function '__check_panic'
      [-Wunused-function]
core_param(panic, panic_timeout, int, 0644);
^
linux/moduleparam.h:283:2: note: expanded from macro
      'core_param'
        param_check_##type(name, &(var));                               \
        ^
<scratch space>:87:1: note: expanded from here
param_check_int
^
linux/moduleparam.h:369:34: note: expanded from macro
      'param_check_int'
#define param_check_int(name, p) __param_check(name, p, int)
                                 ^
linux/moduleparam.h:349:22: note: expanded from macro
      '__param_check'
        static inline type *__check_##name(void) { return(p); }
                            ^
<scratch space>:88:1: note: expanded from here
__check_panic

GCC won't complain for a static inline function but would if it was just
a static function.

Adding the unused attribute to the function declaration removes the warning.
Per request from Rusty Russell it is marked as __always_unused as the code
is meant to be optimized away.

This code works for both GCC and clang.

Signed-off-by: Mark Charlebois <charlebm@gmail.com>
Signed-off-by: Behan Webster <behanw@converseincode.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/moduleparam.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index c3eb102a9cc8..175f6995d1af 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -346,7 +346,7 @@ static inline void destroy_params(const struct kernel_param *params,
 /* The macros to do compile-time type checking stolen from Jakub
    Jelinek, who IIRC came up with this idea for the 2.4 module init code. */
 #define __param_check(name, p, type) \
-	static inline type *__check_##name(void) { return(p); }
+	static inline type __always_unused *__check_##name(void) { return(p); }
 
 extern struct kernel_param_ops param_ops_byte;
 extern int param_set_byte(const char *val, const struct kernel_param *kp);
-- 
cgit v1.2.3


From 740a221ef0e579dc7c675cf6b90f5313509788f7 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Mon, 10 Mar 2014 15:02:41 +0200
Subject: mmc: slot-gpio: Add GPIO descriptor based CD GPIO API

Add functions to request a CD GPIO using the GPIO descriptor API.
Note that the new request function is paired with mmc_gpiod_free_cd()
not mmc_gpio_free_cd().  Note also that it must be called prior to
mmc_add_host() otherwise the caller must also call
mmc_gpiod_request_cd_irq().

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Chris Ball <chris@printf.net>
---
 drivers/mmc/core/core.c       |  4 +++
 drivers/mmc/core/slot-gpio.c  | 81 ++++++++++++++++++++++++++++++++++++++++++-
 include/linux/mmc/slot-gpio.h |  6 ++++
 3 files changed, 90 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index dc7a5fb81a5c..acbc3f2aaaf9 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -34,6 +34,7 @@
 #include <linux/mmc/host.h>
 #include <linux/mmc/mmc.h>
 #include <linux/mmc/sd.h>
+#include <linux/mmc/slot-gpio.h>
 
 #include "core.h"
 #include "bus.h"
@@ -2471,6 +2472,7 @@ void mmc_start_host(struct mmc_host *host)
 		mmc_power_off(host);
 	else
 		mmc_power_up(host, host->ocr_avail);
+	mmc_gpiod_request_cd_irq(host);
 	_mmc_detect_change(host, 0, false);
 }
 
@@ -2482,6 +2484,8 @@ void mmc_stop_host(struct mmc_host *host)
 	host->removed = 1;
 	spin_unlock_irqrestore(&host->lock, flags);
 #endif
+	if (host->slot.cd_irq >= 0)
+		disable_irq(host->slot.cd_irq);
 
 	host->rescan_disable = 1;
 	cancel_delayed_work_sync(&host->detect);
diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c
index 47fa07e3604d..f7650b899e3d 100644
--- a/drivers/mmc/core/slot-gpio.c
+++ b/drivers/mmc/core/slot-gpio.c
@@ -139,7 +139,7 @@ int mmc_gpio_request_ro(struct mmc_host *host, unsigned int gpio)
 }
 EXPORT_SYMBOL(mmc_gpio_request_ro);
 
-static void mmc_gpiod_request_cd_irq(struct mmc_host *host)
+void mmc_gpiod_request_cd_irq(struct mmc_host *host)
 {
 	struct mmc_gpio *ctx = host->slot.handler_priv;
 	int ret, irq;
@@ -171,6 +171,7 @@ static void mmc_gpiod_request_cd_irq(struct mmc_host *host)
 	if (irq < 0)
 		host->caps |= MMC_CAP_NEEDS_POLL;
 }
+EXPORT_SYMBOL(mmc_gpiod_request_cd_irq);
 
 /**
  * mmc_gpio_request_cd - request a gpio for card-detection
@@ -276,3 +277,81 @@ void mmc_gpio_free_cd(struct mmc_host *host)
 	devm_gpio_free(&host->class_dev, gpio);
 }
 EXPORT_SYMBOL(mmc_gpio_free_cd);
+
+/**
+ * mmc_gpiod_request_cd - request a gpio descriptor for card-detection
+ * @host: mmc host
+ * @con_id: function within the GPIO consumer
+ * @idx: index of the GPIO to obtain in the consumer
+ * @override_active_level: ignore %GPIO_ACTIVE_LOW flag
+ * @debounce: debounce time in microseconds
+ *
+ * Use this function in place of mmc_gpio_request_cd() to use the GPIO
+ * descriptor API.  Note that it is paired with mmc_gpiod_free_cd() not
+ * mmc_gpio_free_cd().  Note also that it must be called prior to mmc_add_host()
+ * otherwise the caller must also call mmc_gpiod_request_cd_irq().
+ *
+ * Returns zero on success, else an error.
+ */
+int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id,
+			 unsigned int idx, bool override_active_level,
+			 unsigned int debounce)
+{
+	struct mmc_gpio *ctx;
+	struct gpio_desc *desc;
+	int ret;
+
+	ret = mmc_gpio_alloc(host);
+	if (ret < 0)
+		return ret;
+
+	ctx = host->slot.handler_priv;
+
+	if (!con_id)
+		con_id = ctx->cd_label;
+
+	desc = devm_gpiod_get_index(host->parent, con_id, idx);
+	if (IS_ERR(desc))
+		return PTR_ERR(desc);
+
+	ret = gpiod_direction_input(desc);
+	if (ret < 0)
+		return ret;
+
+	if (debounce) {
+		ret = gpiod_set_debounce(desc, debounce);
+		if (ret < 0)
+			return ret;
+	}
+
+	ctx->override_cd_active_level = override_active_level;
+	ctx->cd_gpio = desc;
+
+	return 0;
+}
+EXPORT_SYMBOL(mmc_gpiod_request_cd);
+
+/**
+ * mmc_gpiod_free_cd - free the card-detection gpio descriptor
+ * @host: mmc host
+ *
+ * It's provided only for cases that client drivers need to manually free
+ * up the card-detection gpio requested by mmc_gpiod_request_cd().
+ */
+void mmc_gpiod_free_cd(struct mmc_host *host)
+{
+	struct mmc_gpio *ctx = host->slot.handler_priv;
+
+	if (!ctx || !ctx->cd_gpio)
+		return;
+
+	if (host->slot.cd_irq >= 0) {
+		devm_free_irq(&host->class_dev, host->slot.cd_irq, host);
+		host->slot.cd_irq = -EINVAL;
+	}
+
+	devm_gpiod_put(&host->class_dev, ctx->cd_gpio);
+
+	ctx->cd_gpio = NULL;
+}
+EXPORT_SYMBOL(mmc_gpiod_free_cd);
diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h
index b0c73e4cacea..d2433381e828 100644
--- a/include/linux/mmc/slot-gpio.h
+++ b/include/linux/mmc/slot-gpio.h
@@ -22,4 +22,10 @@ int mmc_gpio_request_cd(struct mmc_host *host, unsigned int gpio,
 			unsigned int debounce);
 void mmc_gpio_free_cd(struct mmc_host *host);
 
+int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id,
+			 unsigned int idx, bool override_active_level,
+			 unsigned int debounce);
+void mmc_gpiod_free_cd(struct mmc_host *host);
+void mmc_gpiod_request_cd_irq(struct mmc_host *host);
+
 #endif
-- 
cgit v1.2.3


From a797ca1eadeef7f4fdba2ab5d143d56cc3ec5da3 Mon Sep 17 00:00:00 2001
From: Franky Lin <frankyl@broadcom.com>
Date: Sat, 15 Mar 2014 17:18:17 +0100
Subject: brcmfmac: add BCM4354 SDIO interface support

BCM4354 is an a/b/g/n/ac 2x2 WiFi chip. This patch adds support for it through
SDIO interface.

Reviewed-by: Pieter-Paul Giesberts <pieterpg@broadcom.com>
Reviewed-by: Arend Van Spriel <arend@broadcom.com>
Signed-off-by: Franky Lin <frankyl@broadcom.com>
Signed-off-by: Arend van Spriel <arend@broadcom.com>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c     | 1 +
 drivers/net/wireless/brcm80211/brcmfmac/chip.c       | 5 +++++
 drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c   | 7 ++++++-
 drivers/net/wireless/brcm80211/include/brcm_hw_ids.h | 1 +
 include/linux/mmc/sdio_ids.h                         | 1 +
 5 files changed, 14 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c
index d737cf78469a..6e8718bf6920 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c
@@ -988,6 +988,7 @@ static const struct sdio_device_id brcmf_sdmmc_ids[] = {
 	{SDIO_DEVICE(SDIO_VENDOR_ID_BROADCOM, SDIO_DEVICE_ID_BROADCOM_43362)},
 	{SDIO_DEVICE(SDIO_VENDOR_ID_BROADCOM,
 		     SDIO_DEVICE_ID_BROADCOM_4335_4339)},
+	{SDIO_DEVICE(SDIO_VENDOR_ID_BROADCOM, SDIO_DEVICE_ID_BROADCOM_4354)},
 	{ /* end: all zeroes */ },
 };
 MODULE_DEVICE_TABLE(sdio, brcmf_sdmmc_ids);
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/chip.c b/drivers/net/wireless/brcm80211/brcmfmac/chip.c
index a07b95ef9e70..df130ef53d1c 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/chip.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/chip.c
@@ -504,6 +504,7 @@ static void brcmf_chip_get_raminfo(struct brcmf_chip_priv *ci)
 		ci->pub.ramsize = 0x3c000;
 		break;
 	case BCM4339_CHIP_ID:
+	case BCM4354_CHIP_ID:
 		ci->pub.ramsize = 0xc0000;
 		ci->pub.rambase = 0x180000;
 		break;
@@ -1006,6 +1007,10 @@ bool brcmf_chip_sr_capable(struct brcmf_chip *pub)
 	chip = container_of(pub, struct brcmf_chip_priv, pub);
 
 	switch (pub->chip) {
+	case BCM4354_CHIP_ID:
+		/* explicitly check SR engine enable bit */
+		pmu_cc3_mask = BIT(2);
+		/* fall-through */
 	case BCM43241_CHIP_ID:
 	case BCM4335_CHIP_ID:
 	case BCM4339_CHIP_ID:
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c b/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c
index a111b6fbbeba..4aa8678590d5 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/dhd_sdio.c
@@ -578,6 +578,8 @@ static const struct sdiod_drive_str sdiod_drvstr_tab2_3v3[] = {
 #define BCM43362_NVRAM_NAME		"brcm/brcmfmac43362-sdio.txt"
 #define BCM4339_FIRMWARE_NAME		"brcm/brcmfmac4339-sdio.bin"
 #define BCM4339_NVRAM_NAME		"brcm/brcmfmac4339-sdio.txt"
+#define BCM4354_FIRMWARE_NAME		"brcm/brcmfmac4354-sdio.bin"
+#define BCM4354_NVRAM_NAME		"brcm/brcmfmac4354-sdio.txt"
 
 MODULE_FIRMWARE(BCM43143_FIRMWARE_NAME);
 MODULE_FIRMWARE(BCM43143_NVRAM_NAME);
@@ -597,6 +599,8 @@ MODULE_FIRMWARE(BCM43362_FIRMWARE_NAME);
 MODULE_FIRMWARE(BCM43362_NVRAM_NAME);
 MODULE_FIRMWARE(BCM4339_FIRMWARE_NAME);
 MODULE_FIRMWARE(BCM4339_NVRAM_NAME);
+MODULE_FIRMWARE(BCM4354_FIRMWARE_NAME);
+MODULE_FIRMWARE(BCM4354_NVRAM_NAME);
 
 struct brcmf_firmware_names {
 	u32 chipid;
@@ -622,7 +626,8 @@ static const struct brcmf_firmware_names brcmf_fwname_data[] = {
 	{ BCM4334_CHIP_ID, 0xFFFFFFFF, BRCMF_FIRMWARE_NVRAM(BCM4334) },
 	{ BCM4335_CHIP_ID, 0xFFFFFFFF, BRCMF_FIRMWARE_NVRAM(BCM4335) },
 	{ BCM43362_CHIP_ID, 0xFFFFFFFE, BRCMF_FIRMWARE_NVRAM(BCM43362) },
-	{ BCM4339_CHIP_ID, 0xFFFFFFFF, BRCMF_FIRMWARE_NVRAM(BCM4339) }
+	{ BCM4339_CHIP_ID, 0xFFFFFFFF, BRCMF_FIRMWARE_NVRAM(BCM4339) },
+	{ BCM4354_CHIP_ID, 0xFFFFFFFF, BRCMF_FIRMWARE_NVRAM(BCM4354) }
 };
 
 
diff --git a/drivers/net/wireless/brcm80211/include/brcm_hw_ids.h b/drivers/net/wireless/brcm80211/include/brcm_hw_ids.h
index 6fa5d4863782..d816270db3be 100644
--- a/drivers/net/wireless/brcm80211/include/brcm_hw_ids.h
+++ b/drivers/net/wireless/brcm80211/include/brcm_hw_ids.h
@@ -43,5 +43,6 @@
 #define BCM4335_CHIP_ID		0x4335
 #define BCM43362_CHIP_ID	43362
 #define BCM4339_CHIP_ID		0x4339
+#define BCM4354_CHIP_ID		0x4354
 
 #endif				/* _BRCM_HW_IDS_H_ */
diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h
index d8836623f36a..0f01fe065424 100644
--- a/include/linux/mmc/sdio_ids.h
+++ b/include/linux/mmc/sdio_ids.h
@@ -31,6 +31,7 @@
 #define SDIO_DEVICE_ID_BROADCOM_4334		0x4334
 #define SDIO_DEVICE_ID_BROADCOM_4335_4339	0x4335
 #define SDIO_DEVICE_ID_BROADCOM_43362		43362
+#define SDIO_DEVICE_ID_BROADCOM_4354		0x4354
 
 #define SDIO_VENDOR_ID_INTEL			0x0089
 #define SDIO_DEVICE_ID_INTEL_IWMC3200WIMAX	0x1402
-- 
cgit v1.2.3


From 96f9d8c0740264c5e2975361389ff2c21f2c5a4d Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@redhat.com>
Date: Mon, 17 Mar 2014 07:06:54 -0400
Subject: nfs: abstract out code needed to complete a sillyrename

The async rename code is currently "polluted" with some parts that are
really just for sillyrenames. Add a new "complete" operation vector to
the nfs_renamedata to separate out the stuff that just needs to be done
for a sillyrename.

Signed-off-by: Jeff Layton <jlayton@redhat.com>
Tested-by: Anna Schumaker <Anna.Schumaker@netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/nfs/unlink.c         | 22 ++++++++++++++++++----
 include/linux/nfs_xdr.h |  1 +
 2 files changed, 19 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 11d78944de79..3e6798c9ba1f 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -353,8 +353,8 @@ static void nfs_async_rename_done(struct rpc_task *task, void *calldata)
 		return;
 	}
 
-	if (task->tk_status != 0)
-		nfs_cancel_async_unlink(old_dentry);
+	if (data->complete)
+		data->complete(task, data);
 }
 
 /**
@@ -401,7 +401,8 @@ static const struct rpc_call_ops nfs_rename_ops = {
  */
 static struct rpc_task *
 nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
-		 struct dentry *old_dentry, struct dentry *new_dentry)
+		 struct dentry *old_dentry, struct dentry *new_dentry,
+		 void (*complete)(struct rpc_task *, struct nfs_renamedata *))
 {
 	struct nfs_renamedata *data;
 	struct rpc_message msg = { };
@@ -438,6 +439,7 @@ nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
 	data->new_dentry = dget(new_dentry);
 	nfs_fattr_init(&data->old_fattr);
 	nfs_fattr_init(&data->new_fattr);
+	data->complete = complete;
 
 	/* set up nfs_renameargs */
 	data->args.old_dir = NFS_FH(old_dir);
@@ -456,6 +458,17 @@ nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
 	return rpc_run_task(&task_setup_data);
 }
 
+/*
+ * Perform tasks needed when a sillyrename is done such as cancelling the
+ * queued async unlink if it failed.
+ */
+static void
+nfs_complete_sillyrename(struct rpc_task *task, struct nfs_renamedata *data)
+{
+	if (task->tk_status != 0)
+		nfs_cancel_async_unlink(data->old_dentry);
+}
+
 #define SILLYNAME_PREFIX ".nfs"
 #define SILLYNAME_PREFIX_LEN ((unsigned)sizeof(SILLYNAME_PREFIX) - 1)
 #define SILLYNAME_FILEID_LEN ((unsigned)sizeof(u64) << 1)
@@ -548,7 +561,8 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry)
 	}
 
 	/* run the rename task, undo unlink if it fails */
-	task = nfs_async_rename(dir, dir, dentry, sdentry);
+	task = nfs_async_rename(dir, dir, dentry, sdentry,
+					nfs_complete_sillyrename);
 	if (IS_ERR(task)) {
 		error = -EBUSY;
 		nfs_cancel_async_unlink(dentry);
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index b2fb167b2e6d..0534184b65ce 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1397,6 +1397,7 @@ struct nfs_renamedata {
 	struct inode		*new_dir;
 	struct dentry		*new_dentry;
 	struct nfs_fattr	new_fattr;
+	void (*complete)(struct rpc_task *, struct nfs_renamedata *);
 };
 
 struct nfs_access_entry;
-- 
cgit v1.2.3


From 0e862a405185b28e775eeeae6b04bfa39724b1ad Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@redhat.com>
Date: Mon, 17 Mar 2014 07:06:55 -0400
Subject: nfs: make nfs_async_rename non-static

...and move the prototype for nfs_sillyrename to internal.h.

Signed-off-by: Jeff Layton <jlayton@redhat.com>
Tested-by: Anna Schumaker <Anna.Schumaker@netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/nfs/internal.h      | 7 +++++++
 fs/nfs/unlink.c        | 2 +-
 include/linux/nfs_fs.h | 1 -
 3 files changed, 8 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 7f7c476d0c2c..2a81cdb93ec0 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -474,6 +474,13 @@ extern int nfs_migrate_page(struct address_space *,
 #define nfs_migrate_page NULL
 #endif
 
+/* unlink.c */
+extern struct rpc_task *
+nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
+		 struct dentry *old_dentry, struct dentry *new_dentry,
+		 void (*complete)(struct rpc_task *, struct nfs_renamedata *));
+extern int nfs_sillyrename(struct inode *dir, struct dentry *dentry);
+
 /* direct.c */
 void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo,
 			      struct nfs_direct_req *dreq);
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 3e6798c9ba1f..818ded7b7b74 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -399,7 +399,7 @@ static const struct rpc_call_ops nfs_rename_ops = {
  *
  * It's expected that valid references to the dentries and inodes are held
  */
-static struct rpc_task *
+struct rpc_task *
 nfs_async_rename(struct inode *old_dir, struct inode *new_dir,
 		 struct dentry *old_dentry, struct dentry *new_dentry,
 		 void (*complete)(struct rpc_task *, struct nfs_renamedata *))
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index f55a90bed0b4..fa6918b0f829 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -511,7 +511,6 @@ extern void nfs_complete_unlink(struct dentry *dentry, struct inode *);
 extern void nfs_wait_on_sillyrename(struct dentry *dentry);
 extern void nfs_block_sillyrename(struct dentry *dentry);
 extern void nfs_unblock_sillyrename(struct dentry *dentry);
-extern int  nfs_sillyrename(struct inode *dir, struct dentry *dentry);
 
 /*
  * linux/fs/nfs/write.c
-- 
cgit v1.2.3


From 33912be816d96e204ed7a93690552daa39c08ea9 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@redhat.com>
Date: Mon, 17 Mar 2014 07:06:57 -0400
Subject: nfs: remove synchronous rename code

Now that nfs_rename uses the async infrastructure, we can remove this.

Signed-off-by: Jeff Layton <jlayton@redhat.com>
Tested-by: Anna Schumaker <Anna.Schumaker@netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
 fs/nfs/nfs3proc.c       | 36 ------------------------------------
 fs/nfs/nfs4proc.c       | 44 --------------------------------------------
 fs/nfs/proc.c           | 25 -------------------------
 include/linux/nfs_xdr.h |  2 --
 4 files changed, 107 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index aa9bc973f36a..251e6253fc36 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -477,41 +477,6 @@ nfs3_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
 	return 1;
 }
 
-static int
-nfs3_proc_rename(struct inode *old_dir, struct qstr *old_name,
-		 struct inode *new_dir, struct qstr *new_name)
-{
-	struct nfs_renameargs	arg = {
-		.old_dir	= NFS_FH(old_dir),
-		.old_name	= old_name,
-		.new_dir	= NFS_FH(new_dir),
-		.new_name	= new_name,
-	};
-	struct nfs_renameres res;
-	struct rpc_message msg = {
-		.rpc_proc	= &nfs3_procedures[NFS3PROC_RENAME],
-		.rpc_argp	= &arg,
-		.rpc_resp	= &res,
-	};
-	int status = -ENOMEM;
-
-	dprintk("NFS call  rename %s -> %s\n", old_name->name, new_name->name);
-
-	res.old_fattr = nfs_alloc_fattr();
-	res.new_fattr = nfs_alloc_fattr();
-	if (res.old_fattr == NULL || res.new_fattr == NULL)
-		goto out;
-
-	status = rpc_call_sync(NFS_CLIENT(old_dir), &msg, 0);
-	nfs_post_op_update_inode(old_dir, res.old_fattr);
-	nfs_post_op_update_inode(new_dir, res.new_fattr);
-out:
-	nfs_free_fattr(res.old_fattr);
-	nfs_free_fattr(res.new_fattr);
-	dprintk("NFS reply rename: %d\n", status);
-	return status;
-}
-
 static int
 nfs3_proc_link(struct inode *inode, struct inode *dir, struct qstr *name)
 {
@@ -967,7 +932,6 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.unlink_setup	= nfs3_proc_unlink_setup,
 	.unlink_rpc_prepare = nfs3_proc_unlink_rpc_prepare,
 	.unlink_done	= nfs3_proc_unlink_done,
-	.rename		= nfs3_proc_rename,
 	.rename_setup	= nfs3_proc_rename_setup,
 	.rename_rpc_prepare = nfs3_proc_rename_rpc_prepare,
 	.rename_done	= nfs3_proc_rename_done,
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 2427ef4c4d63..013b97afb371 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3544,49 +3544,6 @@ static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
 	return 1;
 }
 
-static int _nfs4_proc_rename(struct inode *old_dir, struct qstr *old_name,
-		struct inode *new_dir, struct qstr *new_name)
-{
-	struct nfs_server *server = NFS_SERVER(old_dir);
-	struct nfs_renameargs arg = {
-		.old_dir = NFS_FH(old_dir),
-		.new_dir = NFS_FH(new_dir),
-		.old_name = old_name,
-		.new_name = new_name,
-	};
-	struct nfs_renameres res = {
-		.server = server,
-	};
-	struct rpc_message msg = {
-		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENAME],
-		.rpc_argp = &arg,
-		.rpc_resp = &res,
-	};
-	int status = -ENOMEM;
-
-	status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
-	if (!status) {
-		update_changeattr(old_dir, &res.old_cinfo);
-		update_changeattr(new_dir, &res.new_cinfo);
-	}
-	return status;
-}
-
-static int nfs4_proc_rename(struct inode *old_dir, struct qstr *old_name,
-		struct inode *new_dir, struct qstr *new_name)
-{
-	struct nfs4_exception exception = { };
-	int err;
-	do {
-		err = _nfs4_proc_rename(old_dir, old_name,
-					new_dir, new_name);
-		trace_nfs4_rename(old_dir, old_name, new_dir, new_name, err);
-		err = nfs4_handle_exception(NFS_SERVER(old_dir), err,
-				&exception);
-	} while (exception.retry);
-	return err;
-}
-
 static int _nfs4_proc_link(struct inode *inode, struct inode *dir, struct qstr *name)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
@@ -8444,7 +8401,6 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.unlink_setup	= nfs4_proc_unlink_setup,
 	.unlink_rpc_prepare = nfs4_proc_unlink_rpc_prepare,
 	.unlink_done	= nfs4_proc_unlink_done,
-	.rename		= nfs4_proc_rename,
 	.rename_setup	= nfs4_proc_rename_setup,
 	.rename_rpc_prepare = nfs4_proc_rename_rpc_prepare,
 	.rename_done	= nfs4_proc_rename_done,
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index fddbba2d9eff..e55ce9e8b034 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -356,30 +356,6 @@ nfs_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
 	return 1;
 }
 
-static int
-nfs_proc_rename(struct inode *old_dir, struct qstr *old_name,
-		struct inode *new_dir, struct qstr *new_name)
-{
-	struct nfs_renameargs	arg = {
-		.old_dir	= NFS_FH(old_dir),
-		.old_name	= old_name,
-		.new_dir	= NFS_FH(new_dir),
-		.new_name	= new_name,
-	};
-	struct rpc_message msg = {
-		.rpc_proc	= &nfs_procedures[NFSPROC_RENAME],
-		.rpc_argp	= &arg,
-	};
-	int			status;
-
-	dprintk("NFS call  rename %s -> %s\n", old_name->name, new_name->name);
-	status = rpc_call_sync(NFS_CLIENT(old_dir), &msg, 0);
-	nfs_mark_for_revalidate(old_dir);
-	nfs_mark_for_revalidate(new_dir);
-	dprintk("NFS reply rename: %d\n", status);
-	return status;
-}
-
 static int
 nfs_proc_link(struct inode *inode, struct inode *dir, struct qstr *name)
 {
@@ -745,7 +721,6 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
 	.unlink_setup	= nfs_proc_unlink_setup,
 	.unlink_rpc_prepare = nfs_proc_unlink_rpc_prepare,
 	.unlink_done	= nfs_proc_unlink_done,
-	.rename		= nfs_proc_rename,
 	.rename_setup	= nfs_proc_rename_setup,
 	.rename_rpc_prepare = nfs_proc_rename_rpc_prepare,
 	.rename_done	= nfs_proc_rename_done,
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 0534184b65ce..ad88a0a30a18 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1440,8 +1440,6 @@ struct nfs_rpc_ops {
 	void	(*unlink_setup)  (struct rpc_message *, struct inode *dir);
 	void	(*unlink_rpc_prepare) (struct rpc_task *, struct nfs_unlinkdata *);
 	int	(*unlink_done) (struct rpc_task *, struct inode *);
-	int	(*rename)  (struct inode *, struct qstr *,
-			    struct inode *, struct qstr *);
 	void	(*rename_setup)  (struct rpc_message *msg, struct inode *dir);
 	void	(*rename_rpc_prepare)(struct rpc_task *task, struct nfs_renamedata *);
 	int	(*rename_done) (struct rpc_task *task, struct inode *old_dir, struct inode *new_dir);
-- 
cgit v1.2.3


From ff6076314339e079806d9d2f3de9c9b768e94db1 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 14 Mar 2014 20:47:49 -0700
Subject: netpoll: Add netpoll_rx_processing

Add a helper netpoll_rx_processing that reports when netpoll has
receive side processing to perform.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netpoll.h | 18 ++++++++++++++----
 net/core/netpoll.c      |  4 ++--
 2 files changed, 16 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index fbfdb9d8d3a7..479d15c97770 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -82,14 +82,24 @@ static inline void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb)
 	local_irq_restore(flags);
 }
 
-
+#ifdef CONFIG_NETPOLL_TRAP
+static inline bool netpoll_rx_processing(struct netpoll_info *npinfo)
+{
+	return !list_empty(&npinfo->rx_np);
+}
+#else
+static inline bool netpoll_rx_processing(struct netpoll_info *npinfo)
+{
+	return false;
+}
+#endif
 
 #ifdef CONFIG_NETPOLL
 static inline bool netpoll_rx_on(struct sk_buff *skb)
 {
 	struct netpoll_info *npinfo = rcu_dereference_bh(skb->dev->npinfo);
 
-	return npinfo && (!list_empty(&npinfo->rx_np) || npinfo->rx_flags);
+	return npinfo && (netpoll_rx_processing(npinfo) || npinfo->rx_flags);
 }
 
 static inline bool netpoll_rx(struct sk_buff *skb)
@@ -105,8 +115,8 @@ static inline bool netpoll_rx(struct sk_buff *skb)
 
 	npinfo = rcu_dereference_bh(skb->dev->npinfo);
 	spin_lock(&npinfo->rx_lock);
-	/* check rx_flags again with the lock held */
-	if (npinfo->rx_flags && __netpoll_rx(skb, npinfo))
+	/* check rx_processing again with the lock held */
+	if (netpoll_rx_processing(npinfo) && __netpoll_rx(skb, npinfo))
 		ret = true;
 	spin_unlock(&npinfo->rx_lock);
 
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 2ad330e02967..ef83a2530e98 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -538,7 +538,7 @@ static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo
 	int hlen, tlen;
 	int hits = 0, proto;
 
-	if (list_empty(&npinfo->rx_np))
+	if (!netpoll_rx_processing(npinfo))
 		return;
 
 	/* Before checking the packet, we do some early
@@ -770,7 +770,7 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
 	struct netpoll *np, *tmp;
 	uint16_t source;
 
-	if (list_empty(&npinfo->rx_np))
+	if (!netpoll_rx_processing(npinfo))
 		goto out;
 
 	if (skb->dev->type != ARPHRD_ETHER)
-- 
cgit v1.2.3


From b6bacd550c33124ea76291bd84ac42c8d30767eb Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 14 Mar 2014 20:48:28 -0700
Subject: netpoll: Don't drop all received packets.

Change the strategy of netpoll from dropping all packets received
during netpoll_poll_dev to calling napi poll with a budget of 0
(to avoid processing drivers rx queue), and to ignore packets received
with netif_rx (those will safely be placed on the backlog queue).

All of the netpoll supporting drivers have been reviewed to ensure
either thay use netif_rx or that a budget of 0 is supported by their
napi poll routine and that a budget of 0 will not process the drivers
rx queues.

Not dropping packets makes NETPOLL_RX_DROP unnecesary so it is removed.

npinfo->rx_flags is removed  as rx_flags with just the NETPOLL_RX_ENABLED
flag becomes just a redundant mirror of list_empty(&npinfo->rx_np).

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netpoll.h |  3 +--
 net/core/netpoll.c      | 17 ++++++-----------
 2 files changed, 7 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index 479d15c97770..154f9776056c 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -39,7 +39,6 @@ struct netpoll {
 struct netpoll_info {
 	atomic_t refcnt;
 
-	unsigned long rx_flags;
 	spinlock_t rx_lock;
 	struct semaphore dev_lock;
 	struct list_head rx_np; /* netpolls that registered an rx_skb_hook */
@@ -99,7 +98,7 @@ static inline bool netpoll_rx_on(struct sk_buff *skb)
 {
 	struct netpoll_info *npinfo = rcu_dereference_bh(skb->dev->npinfo);
 
-	return npinfo && (netpoll_rx_processing(npinfo) || npinfo->rx_flags);
+	return npinfo && netpoll_rx_processing(npinfo);
 }
 
 static inline bool netpoll_rx(struct sk_buff *skb)
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index ef83a2530e98..793dc04d2f19 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -51,8 +51,6 @@ static atomic_t trapped;
 DEFINE_STATIC_SRCU(netpoll_srcu);
 
 #define USEC_PER_POLL	50
-#define NETPOLL_RX_ENABLED  1
-#define NETPOLL_RX_DROP     2
 
 #define MAX_SKB_SIZE							\
 	(sizeof(struct ethhdr) +					\
@@ -193,7 +191,8 @@ static void netpoll_poll_dev(struct net_device *dev)
 {
 	const struct net_device_ops *ops;
 	struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo);
-	int budget = 16;
+	bool rx_processing = netpoll_rx_processing(ni);
+	int budget = rx_processing? 16 : 0;
 
 	/* Don't do any rx activity if the dev_lock mutex is held
 	 * the dev_open/close paths use this to block netpoll activity
@@ -207,8 +206,8 @@ static void netpoll_poll_dev(struct net_device *dev)
 		return;
 	}
 
-	ni->rx_flags |= NETPOLL_RX_DROP;
-	atomic_inc(&trapped);
+	if (rx_processing)
+		atomic_inc(&trapped);
 
 	ops = dev->netdev_ops;
 	if (!ops->ndo_poll_controller) {
@@ -221,8 +220,8 @@ static void netpoll_poll_dev(struct net_device *dev)
 
 	poll_napi(dev, budget);
 
-	atomic_dec(&trapped);
-	ni->rx_flags &= ~NETPOLL_RX_DROP;
+	if (rx_processing)
+		atomic_dec(&trapped);
 
 	up(&ni->dev_lock);
 
@@ -1050,7 +1049,6 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
 			goto out;
 		}
 
-		npinfo->rx_flags = 0;
 		INIT_LIST_HEAD(&npinfo->rx_np);
 
 		spin_lock_init(&npinfo->rx_lock);
@@ -1076,7 +1074,6 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
 
 	if (np->rx_skb_hook) {
 		spin_lock_irqsave(&npinfo->rx_lock, flags);
-		npinfo->rx_flags |= NETPOLL_RX_ENABLED;
 		list_add_tail(&np->rx, &npinfo->rx_np);
 		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
 	}
@@ -1258,8 +1255,6 @@ void __netpoll_cleanup(struct netpoll *np)
 	if (!list_empty(&npinfo->rx_np)) {
 		spin_lock_irqsave(&npinfo->rx_lock, flags);
 		list_del(&np->rx);
-		if (list_empty(&npinfo->rx_np))
-			npinfo->rx_flags &= ~NETPOLL_RX_ENABLED;
 		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
 	}
 
-- 
cgit v1.2.3


From ad8d475244b4112a0f5331e78d043d3a4c9eb37e Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 14 Mar 2014 20:49:43 -0700
Subject: netpoll: Move netpoll_trap under CONFIG_NETPOLL_TRAP

Now that we no longer need to receive packets to safely drain the
network drivers receive queue move netpoll_trap and netpoll_set_trap
under CONFIG_NETPOLL_TRAP

Making netpoll_trap and netpoll_set_trap noop inline functions
when CONFIG_NETPOLL_TRAP is not set.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netpoll.h | 11 +++++++++--
 net/core/netpoll.c      | 14 +++++++++-----
 2 files changed, 18 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index 154f9776056c..ab9aaaff8d04 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -65,8 +65,6 @@ void netpoll_print_options(struct netpoll *np);
 int netpoll_parse_options(struct netpoll *np, char *opt);
 int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp);
 int netpoll_setup(struct netpoll *np);
-int netpoll_trap(void);
-void netpoll_set_trap(int trap);
 void __netpoll_cleanup(struct netpoll *np);
 void __netpoll_free_async(struct netpoll *np);
 void netpoll_cleanup(struct netpoll *np);
@@ -82,11 +80,20 @@ static inline void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb)
 }
 
 #ifdef CONFIG_NETPOLL_TRAP
+int netpoll_trap(void);
+void netpoll_set_trap(int trap);
 static inline bool netpoll_rx_processing(struct netpoll_info *npinfo)
 {
 	return !list_empty(&npinfo->rx_np);
 }
 #else
+static inline int netpoll_trap(void)
+{
+	return 0;
+}
+static inline void netpoll_set_trap(int trap)
+{
+}
 static inline bool netpoll_rx_processing(struct netpoll_info *npinfo)
 {
 	return false;
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 793dc04d2f19..0e45835f1737 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -46,7 +46,9 @@
 
 static struct sk_buff_head skb_pool;
 
+#ifdef CONFIG_NETPOLL_TRAP
 static atomic_t trapped;
+#endif
 
 DEFINE_STATIC_SRCU(netpoll_srcu);
 
@@ -207,7 +209,7 @@ static void netpoll_poll_dev(struct net_device *dev)
 	}
 
 	if (rx_processing)
-		atomic_inc(&trapped);
+		netpoll_set_trap(1);
 
 	ops = dev->netdev_ops;
 	if (!ops->ndo_poll_controller) {
@@ -221,7 +223,7 @@ static void netpoll_poll_dev(struct net_device *dev)
 	poll_napi(dev, budget);
 
 	if (rx_processing)
-		atomic_dec(&trapped);
+		netpoll_set_trap(0);
 
 	up(&ni->dev_lock);
 
@@ -776,10 +778,10 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
 		goto out;
 
 	/* check if netpoll clients need ARP */
-	if (skb->protocol == htons(ETH_P_ARP) && atomic_read(&trapped)) {
+	if (skb->protocol == htons(ETH_P_ARP) && netpoll_trap()) {
 		skb_queue_tail(&npinfo->neigh_tx, skb);
 		return 1;
-	} else if (pkt_is_ns(skb) && atomic_read(&trapped)) {
+	} else if (pkt_is_ns(skb) && netpoll_trap()) {
 		skb_queue_tail(&npinfo->neigh_tx, skb);
 		return 1;
 	}
@@ -896,7 +898,7 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
 	return 1;
 
 out:
-	if (atomic_read(&trapped)) {
+	if (netpoll_trap()) {
 		kfree_skb(skb);
 		return 1;
 	}
@@ -1302,6 +1304,7 @@ out:
 }
 EXPORT_SYMBOL(netpoll_cleanup);
 
+#ifdef CONFIG_NETPOLL_TRAP
 int netpoll_trap(void)
 {
 	return atomic_read(&trapped);
@@ -1316,3 +1319,4 @@ void netpoll_set_trap(int trap)
 		atomic_dec(&trapped);
 }
 EXPORT_SYMBOL(netpoll_set_trap);
+#endif /* CONFIG_NETPOLL_TRAP */
-- 
cgit v1.2.3


From e1bd4d3d7dd2a4a0e731ffe07c439927c23f16ea Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 14 Mar 2014 20:50:58 -0700
Subject: netpoll: Move all receive processing under CONFIG_NETPOLL_TRAP

Make rx_skb_hook, and rx in struct netpoll depend on
CONFIG_NETPOLL_TRAP Make rx_lock, rx_np, and neigh_tx in struct
netpoll_info depend on CONFIG_NETPOLL_TRAP

Make the functions netpoll_rx_on, netpoll_rx, and netpoll_receive_skb
no-ops when CONFIG_NETPOLL_TRAP is not set.

Only build netpoll_neigh_reply, checksum_udp service_neigh_queue,
pkt_is_ns, and __netpoll_rx when CONFIG_NETPOLL_TRAP is defined.

Add helper functions netpoll_trap_setup, netpoll_trap_setup_info,
netpoll_trap_cleanup, and netpoll_trap_cleanup_info that initialize
and cleanup the struct netpoll and struct netpoll_info receive
specific fields when CONFIG_NETPOLL_TRAP is enabled and do nothing
otherwise.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netpoll.h | 73 ++++++++++++++++++++++++--------------------
 net/core/netpoll.c      | 81 ++++++++++++++++++++++++++++++++++++++-----------
 2 files changed, 104 insertions(+), 50 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index ab9aaaff8d04..a0632af88d8b 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -24,32 +24,38 @@ struct netpoll {
 	struct net_device *dev;
 	char dev_name[IFNAMSIZ];
 	const char *name;
-	void (*rx_skb_hook)(struct netpoll *np, int source, struct sk_buff *skb,
-			    int offset, int len);
 
 	union inet_addr local_ip, remote_ip;
 	bool ipv6;
 	u16 local_port, remote_port;
 	u8 remote_mac[ETH_ALEN];
 
-	struct list_head rx; /* rx_np list element */
 	struct work_struct cleanup_work;
+
+#ifdef CONFIG_NETPOLL_TRAP
+	void (*rx_skb_hook)(struct netpoll *np, int source, struct sk_buff *skb,
+			    int offset, int len);
+	struct list_head rx; /* rx_np list element */
+#endif
 };
 
 struct netpoll_info {
 	atomic_t refcnt;
 
-	spinlock_t rx_lock;
 	struct semaphore dev_lock;
-	struct list_head rx_np; /* netpolls that registered an rx_skb_hook */
 
-	struct sk_buff_head neigh_tx; /* list of neigh requests to reply to */
 	struct sk_buff_head txq;
 
 	struct delayed_work tx_work;
 
 	struct netpoll *netpoll;
 	struct rcu_head rcu;
+
+#ifdef CONFIG_NETPOLL_TRAP
+	spinlock_t rx_lock;
+	struct list_head rx_np; /* netpolls that registered an rx_skb_hook */
+	struct sk_buff_head neigh_tx; /* list of neigh requests to reply to */
+#endif
 };
 
 #ifdef CONFIG_NETPOLL
@@ -68,7 +74,6 @@ int netpoll_setup(struct netpoll *np);
 void __netpoll_cleanup(struct netpoll *np);
 void __netpoll_free_async(struct netpoll *np);
 void netpoll_cleanup(struct netpoll *np);
-int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo);
 void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 			     struct net_device *dev);
 static inline void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb)
@@ -82,25 +87,12 @@ static inline void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb)
 #ifdef CONFIG_NETPOLL_TRAP
 int netpoll_trap(void);
 void netpoll_set_trap(int trap);
+int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo);
 static inline bool netpoll_rx_processing(struct netpoll_info *npinfo)
 {
 	return !list_empty(&npinfo->rx_np);
 }
-#else
-static inline int netpoll_trap(void)
-{
-	return 0;
-}
-static inline void netpoll_set_trap(int trap)
-{
-}
-static inline bool netpoll_rx_processing(struct netpoll_info *npinfo)
-{
-	return false;
-}
-#endif
 
-#ifdef CONFIG_NETPOLL
 static inline bool netpoll_rx_on(struct sk_buff *skb)
 {
 	struct netpoll_info *npinfo = rcu_dereference_bh(skb->dev->npinfo);
@@ -138,6 +130,33 @@ static inline int netpoll_receive_skb(struct sk_buff *skb)
 	return 0;
 }
 
+#else
+static inline int netpoll_trap(void)
+{
+	return 0;
+}
+static inline void netpoll_set_trap(int trap)
+{
+}
+static inline bool netpoll_rx_processing(struct netpoll_info *npinfo)
+{
+	return false;
+}
+static inline bool netpoll_rx(struct sk_buff *skb)
+{
+	return false;
+}
+static inline bool netpoll_rx_on(struct sk_buff *skb)
+{
+	return false;
+}
+static inline int netpoll_receive_skb(struct sk_buff *skb)
+{
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_NETPOLL
 static inline void *netpoll_poll_lock(struct napi_struct *napi)
 {
 	struct net_device *dev = napi->dev;
@@ -166,18 +185,6 @@ static inline bool netpoll_tx_running(struct net_device *dev)
 }
 
 #else
-static inline bool netpoll_rx(struct sk_buff *skb)
-{
-	return false;
-}
-static inline bool netpoll_rx_on(struct sk_buff *skb)
-{
-	return false;
-}
-static inline int netpoll_receive_skb(struct sk_buff *skb)
-{
-	return 0;
-}
 static inline void *netpoll_poll_lock(struct napi_struct *napi)
 {
 	return NULL;
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index b69bb3f1ba3f..eed8b1d2d302 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -48,6 +48,7 @@ static struct sk_buff_head skb_pool;
 
 #ifdef CONFIG_NETPOLL_TRAP
 static atomic_t trapped;
+static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo);
 #endif
 
 DEFINE_STATIC_SRCU(netpoll_srcu);
@@ -61,7 +62,6 @@ DEFINE_STATIC_SRCU(netpoll_srcu);
 	 MAX_UDP_CHUNK)
 
 static void zap_completion_queue(void);
-static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo);
 static void netpoll_async_cleanup(struct work_struct *work);
 
 static unsigned int carrier_timeout = 4;
@@ -109,6 +109,7 @@ static void queue_process(struct work_struct *work)
 	}
 }
 
+#ifdef CONFIG_NETPOLL_TRAP
 static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh,
 			    unsigned short ulen, __be32 saddr, __be32 daddr)
 {
@@ -127,6 +128,7 @@ static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh,
 
 	return __skb_checksum_complete(skb);
 }
+#endif /* CONFIG_NETPOLL_TRAP */
 
 /*
  * Check whether delayed processing was scheduled for our NIC. If so,
@@ -179,6 +181,7 @@ static void poll_napi(struct net_device *dev, int budget)
 	}
 }
 
+#ifdef CONFIG_NETPOLL_TRAP
 static void service_neigh_queue(struct net_device *dev,
 				struct netpoll_info *npi)
 {
@@ -197,6 +200,12 @@ static void service_neigh_queue(struct net_device *dev,
 	while ((skb = skb_dequeue(&npi->neigh_tx)))
 		netpoll_neigh_reply(skb, npi);
 }
+#else /* !CONFIG_NETPOLL_TRAP */
+static inline void service_neigh_queue(struct net_device *dev,
+				struct netpoll_info *npi)
+{
+}
+#endif /* CONFIG_NETPOLL_TRAP */
 
 static void netpoll_poll_dev(struct net_device *dev)
 {
@@ -522,6 +531,7 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
 }
 EXPORT_SYMBOL(netpoll_send_udp);
 
+#ifdef CONFIG_NETPOLL_TRAP
 static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo)
 {
 	int size, type = ARPOP_REPLY;
@@ -900,6 +910,55 @@ out:
 	return 0;
 }
 
+static void netpoll_trap_setup_info(struct netpoll_info *npinfo)
+{
+	INIT_LIST_HEAD(&npinfo->rx_np);
+	spin_lock_init(&npinfo->rx_lock);
+	skb_queue_head_init(&npinfo->neigh_tx);
+}
+
+static void netpoll_trap_cleanup_info(struct netpoll_info *npinfo)
+{
+	skb_queue_purge(&npinfo->neigh_tx);
+}
+
+static void netpoll_trap_setup(struct netpoll *np, struct netpoll_info *npinfo)
+{
+	unsigned long flags;
+	if (np->rx_skb_hook) {
+		spin_lock_irqsave(&npinfo->rx_lock, flags);
+		list_add_tail(&np->rx, &npinfo->rx_np);
+		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
+	}
+}
+
+static void netpoll_trap_cleanup(struct netpoll *np, struct netpoll_info *npinfo)
+{
+	unsigned long flags;
+	if (!list_empty(&npinfo->rx_np)) {
+		spin_lock_irqsave(&npinfo->rx_lock, flags);
+		list_del(&np->rx);
+		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
+	}
+}
+
+#else /* !CONFIG_NETPOLL_TRAP */
+static inline void netpoll_trap_setup_info(struct netpoll_info *npinfo)
+{
+}
+static inline void netpoll_trap_cleanup_info(struct netpoll_info *npinfo)
+{
+}
+static inline
+void netpoll_trap_setup(struct netpoll *np, struct netpoll_info *npinfo)
+{
+}
+static inline
+void netpoll_trap_cleanup(struct netpoll *np, struct netpoll_info *npinfo)
+{
+}
+#endif /* CONFIG_NETPOLL_TRAP */
+
 void netpoll_print_options(struct netpoll *np)
 {
 	np_info(np, "local port %d\n", np->local_port);
@@ -1023,7 +1082,6 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
 {
 	struct netpoll_info *npinfo;
 	const struct net_device_ops *ops;
-	unsigned long flags;
 	int err;
 
 	np->dev = ndev;
@@ -1045,11 +1103,9 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
 			goto out;
 		}
 
-		INIT_LIST_HEAD(&npinfo->rx_np);
+		netpoll_trap_setup_info(npinfo);
 
-		spin_lock_init(&npinfo->rx_lock);
 		sema_init(&npinfo->dev_lock, 1);
-		skb_queue_head_init(&npinfo->neigh_tx);
 		skb_queue_head_init(&npinfo->txq);
 		INIT_DELAYED_WORK(&npinfo->tx_work, queue_process);
 
@@ -1068,11 +1124,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
 
 	npinfo->netpoll = np;
 
-	if (np->rx_skb_hook) {
-		spin_lock_irqsave(&npinfo->rx_lock, flags);
-		list_add_tail(&np->rx, &npinfo->rx_np);
-		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
-	}
+	netpoll_trap_setup(np, npinfo);
 
 	/* last thing to do is link it to the net device structure */
 	rcu_assign_pointer(ndev->npinfo, npinfo);
@@ -1222,7 +1274,7 @@ static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head)
 	struct netpoll_info *npinfo =
 			container_of(rcu_head, struct netpoll_info, rcu);
 
-	skb_queue_purge(&npinfo->neigh_tx);
+	netpoll_trap_cleanup_info(npinfo);
 	skb_queue_purge(&npinfo->txq);
 
 	/* we can't call cancel_delayed_work_sync here, as we are in softirq */
@@ -1238,7 +1290,6 @@ static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head)
 void __netpoll_cleanup(struct netpoll *np)
 {
 	struct netpoll_info *npinfo;
-	unsigned long flags;
 
 	/* rtnl_dereference would be preferable here but
 	 * rcu_cleanup_netpoll path can put us in here safely without
@@ -1248,11 +1299,7 @@ void __netpoll_cleanup(struct netpoll *np)
 	if (!npinfo)
 		return;
 
-	if (!list_empty(&npinfo->rx_np)) {
-		spin_lock_irqsave(&npinfo->rx_lock, flags);
-		list_del(&np->rx);
-		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
-	}
+	netpoll_trap_cleanup(np, npinfo);
 
 	synchronize_srcu(&netpoll_srcu);
 
-- 
cgit v1.2.3


From 9c62a68d13119a1ca9718381d97b0cb415ff4e9d Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 14 Mar 2014 20:51:52 -0700
Subject: netpoll: Remove dead packet receive code (CONFIG_NETPOLL_TRAP)

The netpoll packet receive code only becomes active if the netpoll
rx_skb_hook is implemented, and there is not a single implementation
of the netpoll rx_skb_hook in the kernel.

All of the out of tree implementations I have found all call
netpoll_poll which was removed from the kernel in 2011, so this
change should not add any additional breakage.

There are problems with the netpoll packet receive code.  __netpoll_rx
does not call dev_kfree_skb_irq or dev_kfree_skb_any in hard irq
context.  netpoll_neigh_reply leaks every skb it receives.  Reception
of packets does not work successfully on stacked devices (aka bonding,
team, bridge, and vlans).

Given that the netpoll packet receive code is buggy, there are no
out of tree users that will be merged soon, and the code has
not been used for in tree for a decade let's just remove it.

Reverting this commit can server as a starting point for anyone
who wants to resurrect netpoll packet reception support.

Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/Kconfig       |   5 -
 include/linux/netdevice.h |  17 --
 include/linux/netpoll.h   |  84 --------
 net/core/dev.c            |  11 +-
 net/core/netpoll.c        | 520 +---------------------------------------------
 5 files changed, 2 insertions(+), 635 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 494b888a6568..89402c3b64f8 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -177,11 +177,6 @@ config NETCONSOLE_DYNAMIC
 config NETPOLL
 	def_bool NETCONSOLE
 
-config NETPOLL_TRAP
-	bool "Netpoll traffic trapping"
-	default n
-	depends on NETPOLL
-
 config NET_POLL_CONTROLLER
 	def_bool NETPOLL
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b8d8c805fd75..4b6d12c7b803 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1979,9 +1979,6 @@ struct net_device *__dev_get_by_index(struct net *net, int ifindex);
 struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
 int netdev_get_name(struct net *net, char *name, int ifindex);
 int dev_restart(struct net_device *dev);
-#ifdef CONFIG_NETPOLL_TRAP
-int netpoll_trap(void);
-#endif
 int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb);
 
 static inline unsigned int skb_gro_offset(const struct sk_buff *skb)
@@ -2186,12 +2183,6 @@ static inline void netif_tx_start_all_queues(struct net_device *dev)
 
 static inline void netif_tx_wake_queue(struct netdev_queue *dev_queue)
 {
-#ifdef CONFIG_NETPOLL_TRAP
-	if (netpoll_trap()) {
-		netif_tx_start_queue(dev_queue);
-		return;
-	}
-#endif
 	if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state))
 		__netif_schedule(dev_queue->qdisc);
 }
@@ -2435,10 +2426,6 @@ static inline void netif_start_subqueue(struct net_device *dev, u16 queue_index)
 static inline void netif_stop_subqueue(struct net_device *dev, u16 queue_index)
 {
 	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
-#ifdef CONFIG_NETPOLL_TRAP
-	if (netpoll_trap())
-		return;
-#endif
 	netif_tx_stop_queue(txq);
 }
 
@@ -2473,10 +2460,6 @@ static inline bool netif_subqueue_stopped(const struct net_device *dev,
 static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index)
 {
 	struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
-#ifdef CONFIG_NETPOLL_TRAP
-	if (netpoll_trap())
-		return;
-#endif
 	if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &txq->state))
 		__netif_schedule(txq->qdisc);
 }
diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index a0632af88d8b..1b475a5a7239 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -31,12 +31,6 @@ struct netpoll {
 	u8 remote_mac[ETH_ALEN];
 
 	struct work_struct cleanup_work;
-
-#ifdef CONFIG_NETPOLL_TRAP
-	void (*rx_skb_hook)(struct netpoll *np, int source, struct sk_buff *skb,
-			    int offset, int len);
-	struct list_head rx; /* rx_np list element */
-#endif
 };
 
 struct netpoll_info {
@@ -50,12 +44,6 @@ struct netpoll_info {
 
 	struct netpoll *netpoll;
 	struct rcu_head rcu;
-
-#ifdef CONFIG_NETPOLL_TRAP
-	spinlock_t rx_lock;
-	struct list_head rx_np; /* netpolls that registered an rx_skb_hook */
-	struct sk_buff_head neigh_tx; /* list of neigh requests to reply to */
-#endif
 };
 
 #ifdef CONFIG_NETPOLL
@@ -84,78 +72,6 @@ static inline void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb)
 	local_irq_restore(flags);
 }
 
-#ifdef CONFIG_NETPOLL_TRAP
-int netpoll_trap(void);
-void netpoll_set_trap(int trap);
-int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo);
-static inline bool netpoll_rx_processing(struct netpoll_info *npinfo)
-{
-	return !list_empty(&npinfo->rx_np);
-}
-
-static inline bool netpoll_rx_on(struct sk_buff *skb)
-{
-	struct netpoll_info *npinfo = rcu_dereference_bh(skb->dev->npinfo);
-
-	return npinfo && netpoll_rx_processing(npinfo);
-}
-
-static inline bool netpoll_rx(struct sk_buff *skb)
-{
-	struct netpoll_info *npinfo;
-	unsigned long flags;
-	bool ret = false;
-
-	local_irq_save(flags);
-
-	if (!netpoll_rx_on(skb))
-		goto out;
-
-	npinfo = rcu_dereference_bh(skb->dev->npinfo);
-	spin_lock(&npinfo->rx_lock);
-	/* check rx_processing again with the lock held */
-	if (netpoll_rx_processing(npinfo) && __netpoll_rx(skb, npinfo))
-		ret = true;
-	spin_unlock(&npinfo->rx_lock);
-
-out:
-	local_irq_restore(flags);
-	return ret;
-}
-
-static inline int netpoll_receive_skb(struct sk_buff *skb)
-{
-	if (!list_empty(&skb->dev->napi_list))
-		return netpoll_rx(skb);
-	return 0;
-}
-
-#else
-static inline int netpoll_trap(void)
-{
-	return 0;
-}
-static inline void netpoll_set_trap(int trap)
-{
-}
-static inline bool netpoll_rx_processing(struct netpoll_info *npinfo)
-{
-	return false;
-}
-static inline bool netpoll_rx(struct sk_buff *skb)
-{
-	return false;
-}
-static inline bool netpoll_rx_on(struct sk_buff *skb)
-{
-	return false;
-}
-static inline int netpoll_receive_skb(struct sk_buff *skb)
-{
-	return 0;
-}
-#endif
-
 #ifdef CONFIG_NETPOLL
 static inline void *netpoll_poll_lock(struct napi_struct *napi)
 {
diff --git a/net/core/dev.c b/net/core/dev.c
index 587f9fb85d73..55f8e64c03a2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3231,10 +3231,6 @@ static int netif_rx_internal(struct sk_buff *skb)
 {
 	int ret;
 
-	/* if netpoll wants it, pretend we never saw it */
-	if (netpoll_rx(skb))
-		return NET_RX_DROP;
-
 	net_timestamp_check(netdev_tstamp_prequeue, skb);
 
 	trace_netif_rx(skb);
@@ -3520,10 +3516,6 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)
 
 	trace_netif_receive_skb(skb);
 
-	/* if we've gotten here through NAPI, check netpoll */
-	if (netpoll_receive_skb(skb))
-		goto out;
-
 	orig_dev = skb->dev;
 
 	skb_reset_network_header(skb);
@@ -3650,7 +3642,6 @@ drop:
 
 unlock:
 	rcu_read_unlock();
-out:
 	return ret;
 }
 
@@ -3875,7 +3866,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	int same_flow;
 	enum gro_result ret;
 
-	if (!(skb->dev->features & NETIF_F_GRO) || netpoll_rx_on(skb))
+	if (!(skb->dev->features & NETIF_F_GRO))
 		goto normal;
 
 	if (skb_is_gso(skb) || skb_has_frag_list(skb))
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index eed8b1d2d302..7291dde93469 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -46,11 +46,6 @@
 
 static struct sk_buff_head skb_pool;
 
-#ifdef CONFIG_NETPOLL_TRAP
-static atomic_t trapped;
-static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo);
-#endif
-
 DEFINE_STATIC_SRCU(netpoll_srcu);
 
 #define USEC_PER_POLL	50
@@ -109,27 +104,6 @@ static void queue_process(struct work_struct *work)
 	}
 }
 
-#ifdef CONFIG_NETPOLL_TRAP
-static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh,
-			    unsigned short ulen, __be32 saddr, __be32 daddr)
-{
-	__wsum psum;
-
-	if (uh->check == 0 || skb_csum_unnecessary(skb))
-		return 0;
-
-	psum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0);
-
-	if (skb->ip_summed == CHECKSUM_COMPLETE &&
-	    !csum_fold(csum_add(psum, skb->csum)))
-		return 0;
-
-	skb->csum = psum;
-
-	return __skb_checksum_complete(skb);
-}
-#endif /* CONFIG_NETPOLL_TRAP */
-
 /*
  * Check whether delayed processing was scheduled for our NIC. If so,
  * we attempt to grab the poll lock and use ->poll() to pump the card.
@@ -140,11 +114,6 @@ static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh,
  * trylock here and interrupts are already disabled in the softirq
  * case. Further, we test the poll_owner to avoid recursion on UP
  * systems where the lock doesn't exist.
- *
- * In cases where there is bi-directional communications, reading only
- * one message at a time can lead to packets being dropped by the
- * network adapter, forcing superfluous retries and possibly timeouts.
- * Thus, we set our budget to greater than 1.
  */
 static int poll_one_napi(struct napi_struct *napi, int budget)
 {
@@ -181,38 +150,11 @@ static void poll_napi(struct net_device *dev, int budget)
 	}
 }
 
-#ifdef CONFIG_NETPOLL_TRAP
-static void service_neigh_queue(struct net_device *dev,
-				struct netpoll_info *npi)
-{
-	struct sk_buff *skb;
-	if (dev->flags & IFF_SLAVE) {
-		struct net_device *bond_dev;
-		struct netpoll_info *bond_ni;
-
-		bond_dev = netdev_master_upper_dev_get_rcu(dev);
-		bond_ni = rcu_dereference_bh(bond_dev->npinfo);
-		while ((skb = skb_dequeue(&npi->neigh_tx))) {
-			skb->dev = bond_dev;
-			skb_queue_tail(&bond_ni->neigh_tx, skb);
-		}
-	}
-	while ((skb = skb_dequeue(&npi->neigh_tx)))
-		netpoll_neigh_reply(skb, npi);
-}
-#else /* !CONFIG_NETPOLL_TRAP */
-static inline void service_neigh_queue(struct net_device *dev,
-				struct netpoll_info *npi)
-{
-}
-#endif /* CONFIG_NETPOLL_TRAP */
-
 static void netpoll_poll_dev(struct net_device *dev)
 {
 	const struct net_device_ops *ops;
 	struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo);
-	bool rx_processing = netpoll_rx_processing(ni);
-	int budget = rx_processing? 16 : 0;
+	int budget = 0;
 
 	/* Don't do any rx activity if the dev_lock mutex is held
 	 * the dev_open/close paths use this to block netpoll activity
@@ -226,9 +168,6 @@ static void netpoll_poll_dev(struct net_device *dev)
 		return;
 	}
 
-	if (rx_processing)
-		netpoll_set_trap(1);
-
 	ops = dev->netdev_ops;
 	if (!ops->ndo_poll_controller) {
 		up(&ni->dev_lock);
@@ -240,13 +179,8 @@ static void netpoll_poll_dev(struct net_device *dev)
 
 	poll_napi(dev, budget);
 
-	if (rx_processing)
-		netpoll_set_trap(0);
-
 	up(&ni->dev_lock);
 
-	service_neigh_queue(dev, ni);
-
 	zap_completion_queue();
 }
 
@@ -531,434 +465,6 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
 }
 EXPORT_SYMBOL(netpoll_send_udp);
 
-#ifdef CONFIG_NETPOLL_TRAP
-static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo)
-{
-	int size, type = ARPOP_REPLY;
-	__be32 sip, tip;
-	unsigned char *sha;
-	struct sk_buff *send_skb;
-	struct netpoll *np, *tmp;
-	unsigned long flags;
-	int hlen, tlen;
-	int hits = 0, proto;
-
-	if (!netpoll_rx_processing(npinfo))
-		return;
-
-	/* Before checking the packet, we do some early
-	   inspection whether this is interesting at all */
-	spin_lock_irqsave(&npinfo->rx_lock, flags);
-	list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
-		if (np->dev == skb->dev)
-			hits++;
-	}
-	spin_unlock_irqrestore(&npinfo->rx_lock, flags);
-
-	/* No netpoll struct is using this dev */
-	if (!hits)
-		return;
-
-	proto = ntohs(eth_hdr(skb)->h_proto);
-	if (proto == ETH_P_ARP) {
-		struct arphdr *arp;
-		unsigned char *arp_ptr;
-		/* No arp on this interface */
-		if (skb->dev->flags & IFF_NOARP)
-			return;
-
-		if (!pskb_may_pull(skb, arp_hdr_len(skb->dev)))
-			return;
-
-		skb_reset_network_header(skb);
-		skb_reset_transport_header(skb);
-		arp = arp_hdr(skb);
-
-		if ((arp->ar_hrd != htons(ARPHRD_ETHER) &&
-		     arp->ar_hrd != htons(ARPHRD_IEEE802)) ||
-		    arp->ar_pro != htons(ETH_P_IP) ||
-		    arp->ar_op != htons(ARPOP_REQUEST))
-			return;
-
-		arp_ptr = (unsigned char *)(arp+1);
-		/* save the location of the src hw addr */
-		sha = arp_ptr;
-		arp_ptr += skb->dev->addr_len;
-		memcpy(&sip, arp_ptr, 4);
-		arp_ptr += 4;
-		/* If we actually cared about dst hw addr,
-		   it would get copied here */
-		arp_ptr += skb->dev->addr_len;
-		memcpy(&tip, arp_ptr, 4);
-
-		/* Should we ignore arp? */
-		if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip))
-			return;
-
-		size = arp_hdr_len(skb->dev);
-
-		spin_lock_irqsave(&npinfo->rx_lock, flags);
-		list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
-			if (tip != np->local_ip.ip)
-				continue;
-
-			hlen = LL_RESERVED_SPACE(np->dev);
-			tlen = np->dev->needed_tailroom;
-			send_skb = find_skb(np, size + hlen + tlen, hlen);
-			if (!send_skb)
-				continue;
-
-			skb_reset_network_header(send_skb);
-			arp = (struct arphdr *) skb_put(send_skb, size);
-			send_skb->dev = skb->dev;
-			send_skb->protocol = htons(ETH_P_ARP);
-
-			/* Fill the device header for the ARP frame */
-			if (dev_hard_header(send_skb, skb->dev, ETH_P_ARP,
-					    sha, np->dev->dev_addr,
-					    send_skb->len) < 0) {
-				kfree_skb(send_skb);
-				continue;
-			}
-
-			/*
-			 * Fill out the arp protocol part.
-			 *
-			 * we only support ethernet device type,
-			 * which (according to RFC 1390) should
-			 * always equal 1 (Ethernet).
-			 */
-
-			arp->ar_hrd = htons(np->dev->type);
-			arp->ar_pro = htons(ETH_P_IP);
-			arp->ar_hln = np->dev->addr_len;
-			arp->ar_pln = 4;
-			arp->ar_op = htons(type);
-
-			arp_ptr = (unsigned char *)(arp + 1);
-			memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len);
-			arp_ptr += np->dev->addr_len;
-			memcpy(arp_ptr, &tip, 4);
-			arp_ptr += 4;
-			memcpy(arp_ptr, sha, np->dev->addr_len);
-			arp_ptr += np->dev->addr_len;
-			memcpy(arp_ptr, &sip, 4);
-
-			netpoll_send_skb(np, send_skb);
-
-			/* If there are several rx_skb_hooks for the same
-			 * address we're fine by sending a single reply
-			 */
-			break;
-		}
-		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
-	} else if( proto == ETH_P_IPV6) {
-#if IS_ENABLED(CONFIG_IPV6)
-		struct nd_msg *msg;
-		u8 *lladdr = NULL;
-		struct ipv6hdr *hdr;
-		struct icmp6hdr *icmp6h;
-		const struct in6_addr *saddr;
-		const struct in6_addr *daddr;
-		struct inet6_dev *in6_dev = NULL;
-		struct in6_addr *target;
-
-		in6_dev = in6_dev_get(skb->dev);
-		if (!in6_dev || !in6_dev->cnf.accept_ra)
-			return;
-
-		if (!pskb_may_pull(skb, skb->len))
-			return;
-
-		msg = (struct nd_msg *)skb_transport_header(skb);
-
-		__skb_push(skb, skb->data - skb_transport_header(skb));
-
-		if (ipv6_hdr(skb)->hop_limit != 255)
-			return;
-		if (msg->icmph.icmp6_code != 0)
-			return;
-		if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
-			return;
-
-		saddr = &ipv6_hdr(skb)->saddr;
-		daddr = &ipv6_hdr(skb)->daddr;
-
-		size = sizeof(struct icmp6hdr) + sizeof(struct in6_addr);
-
-		spin_lock_irqsave(&npinfo->rx_lock, flags);
-		list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
-			if (!ipv6_addr_equal(daddr, &np->local_ip.in6))
-				continue;
-
-			hlen = LL_RESERVED_SPACE(np->dev);
-			tlen = np->dev->needed_tailroom;
-			send_skb = find_skb(np, size + hlen + tlen, hlen);
-			if (!send_skb)
-				continue;
-
-			send_skb->protocol = htons(ETH_P_IPV6);
-			send_skb->dev = skb->dev;
-
-			skb_reset_network_header(send_skb);
-			hdr = (struct ipv6hdr *) skb_put(send_skb, sizeof(struct ipv6hdr));
-			*(__be32*)hdr = htonl(0x60000000);
-			hdr->payload_len = htons(size);
-			hdr->nexthdr = IPPROTO_ICMPV6;
-			hdr->hop_limit = 255;
-			hdr->saddr = *saddr;
-			hdr->daddr = *daddr;
-
-			icmp6h = (struct icmp6hdr *) skb_put(send_skb, sizeof(struct icmp6hdr));
-			icmp6h->icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT;
-			icmp6h->icmp6_router = 0;
-			icmp6h->icmp6_solicited = 1;
-
-			target = (struct in6_addr *) skb_put(send_skb, sizeof(struct in6_addr));
-			*target = msg->target;
-			icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, size,
-							      IPPROTO_ICMPV6,
-							      csum_partial(icmp6h,
-									   size, 0));
-
-			if (dev_hard_header(send_skb, skb->dev, ETH_P_IPV6,
-					    lladdr, np->dev->dev_addr,
-					    send_skb->len) < 0) {
-				kfree_skb(send_skb);
-				continue;
-			}
-
-			netpoll_send_skb(np, send_skb);
-
-			/* If there are several rx_skb_hooks for the same
-			 * address, we're fine by sending a single reply
-			 */
-			break;
-		}
-		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
-#endif
-	}
-}
-
-static bool pkt_is_ns(struct sk_buff *skb)
-{
-	struct nd_msg *msg;
-	struct ipv6hdr *hdr;
-
-	if (skb->protocol != htons(ETH_P_ARP))
-		return false;
-	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)))
-		return false;
-
-	msg = (struct nd_msg *)skb_transport_header(skb);
-	__skb_push(skb, skb->data - skb_transport_header(skb));
-	hdr = ipv6_hdr(skb);
-
-	if (hdr->nexthdr != IPPROTO_ICMPV6)
-		return false;
-	if (hdr->hop_limit != 255)
-		return false;
-	if (msg->icmph.icmp6_code != 0)
-		return false;
-	if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION)
-		return false;
-
-	return true;
-}
-
-int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo)
-{
-	int proto, len, ulen, data_len;
-	int hits = 0, offset;
-	const struct iphdr *iph;
-	struct udphdr *uh;
-	struct netpoll *np, *tmp;
-	uint16_t source;
-
-	if (!netpoll_rx_processing(npinfo))
-		goto out;
-
-	if (skb->dev->type != ARPHRD_ETHER)
-		goto out;
-
-	/* check if netpoll clients need ARP */
-	if (skb->protocol == htons(ETH_P_ARP) && netpoll_trap()) {
-		skb_queue_tail(&npinfo->neigh_tx, skb);
-		return 1;
-	} else if (pkt_is_ns(skb) && netpoll_trap()) {
-		skb_queue_tail(&npinfo->neigh_tx, skb);
-		return 1;
-	}
-
-	if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
-		skb = vlan_untag(skb);
-		if (unlikely(!skb))
-			goto out;
-	}
-
-	proto = ntohs(eth_hdr(skb)->h_proto);
-	if (proto != ETH_P_IP && proto != ETH_P_IPV6)
-		goto out;
-	if (skb->pkt_type == PACKET_OTHERHOST)
-		goto out;
-	if (skb_shared(skb))
-		goto out;
-
-	if (proto == ETH_P_IP) {
-		if (!pskb_may_pull(skb, sizeof(struct iphdr)))
-			goto out;
-		iph = (struct iphdr *)skb->data;
-		if (iph->ihl < 5 || iph->version != 4)
-			goto out;
-		if (!pskb_may_pull(skb, iph->ihl*4))
-			goto out;
-		iph = (struct iphdr *)skb->data;
-		if (ip_fast_csum((u8 *)iph, iph->ihl) != 0)
-			goto out;
-
-		len = ntohs(iph->tot_len);
-		if (skb->len < len || len < iph->ihl*4)
-			goto out;
-
-		/*
-		 * Our transport medium may have padded the buffer out.
-		 * Now We trim to the true length of the frame.
-		 */
-		if (pskb_trim_rcsum(skb, len))
-			goto out;
-
-		iph = (struct iphdr *)skb->data;
-		if (iph->protocol != IPPROTO_UDP)
-			goto out;
-
-		len -= iph->ihl*4;
-		uh = (struct udphdr *)(((char *)iph) + iph->ihl*4);
-		offset = (unsigned char *)(uh + 1) - skb->data;
-		ulen = ntohs(uh->len);
-		data_len = skb->len - offset;
-		source = ntohs(uh->source);
-
-		if (ulen != len)
-			goto out;
-		if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr))
-			goto out;
-		list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
-			if (np->local_ip.ip && np->local_ip.ip != iph->daddr)
-				continue;
-			if (np->remote_ip.ip && np->remote_ip.ip != iph->saddr)
-				continue;
-			if (np->local_port && np->local_port != ntohs(uh->dest))
-				continue;
-
-			np->rx_skb_hook(np, source, skb, offset, data_len);
-			hits++;
-		}
-	} else {
-#if IS_ENABLED(CONFIG_IPV6)
-		const struct ipv6hdr *ip6h;
-
-		if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
-			goto out;
-		ip6h = (struct ipv6hdr *)skb->data;
-		if (ip6h->version != 6)
-			goto out;
-		len = ntohs(ip6h->payload_len);
-		if (!len)
-			goto out;
-		if (len + sizeof(struct ipv6hdr) > skb->len)
-			goto out;
-		if (pskb_trim_rcsum(skb, len + sizeof(struct ipv6hdr)))
-			goto out;
-		ip6h = ipv6_hdr(skb);
-		if (!pskb_may_pull(skb, sizeof(struct udphdr)))
-			goto out;
-		uh = udp_hdr(skb);
-		offset = (unsigned char *)(uh + 1) - skb->data;
-		ulen = ntohs(uh->len);
-		data_len = skb->len - offset;
-		source = ntohs(uh->source);
-		if (ulen != skb->len)
-			goto out;
-		if (udp6_csum_init(skb, uh, IPPROTO_UDP))
-			goto out;
-		list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) {
-			if (!ipv6_addr_equal(&np->local_ip.in6, &ip6h->daddr))
-				continue;
-			if (!ipv6_addr_equal(&np->remote_ip.in6, &ip6h->saddr))
-				continue;
-			if (np->local_port && np->local_port != ntohs(uh->dest))
-				continue;
-
-			np->rx_skb_hook(np, source, skb, offset, data_len);
-			hits++;
-		}
-#endif
-	}
-
-	if (!hits)
-		goto out;
-
-	kfree_skb(skb);
-	return 1;
-
-out:
-	if (netpoll_trap()) {
-		kfree_skb(skb);
-		return 1;
-	}
-
-	return 0;
-}
-
-static void netpoll_trap_setup_info(struct netpoll_info *npinfo)
-{
-	INIT_LIST_HEAD(&npinfo->rx_np);
-	spin_lock_init(&npinfo->rx_lock);
-	skb_queue_head_init(&npinfo->neigh_tx);
-}
-
-static void netpoll_trap_cleanup_info(struct netpoll_info *npinfo)
-{
-	skb_queue_purge(&npinfo->neigh_tx);
-}
-
-static void netpoll_trap_setup(struct netpoll *np, struct netpoll_info *npinfo)
-{
-	unsigned long flags;
-	if (np->rx_skb_hook) {
-		spin_lock_irqsave(&npinfo->rx_lock, flags);
-		list_add_tail(&np->rx, &npinfo->rx_np);
-		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
-	}
-}
-
-static void netpoll_trap_cleanup(struct netpoll *np, struct netpoll_info *npinfo)
-{
-	unsigned long flags;
-	if (!list_empty(&npinfo->rx_np)) {
-		spin_lock_irqsave(&npinfo->rx_lock, flags);
-		list_del(&np->rx);
-		spin_unlock_irqrestore(&npinfo->rx_lock, flags);
-	}
-}
-
-#else /* !CONFIG_NETPOLL_TRAP */
-static inline void netpoll_trap_setup_info(struct netpoll_info *npinfo)
-{
-}
-static inline void netpoll_trap_cleanup_info(struct netpoll_info *npinfo)
-{
-}
-static inline
-void netpoll_trap_setup(struct netpoll *np, struct netpoll_info *npinfo)
-{
-}
-static inline
-void netpoll_trap_cleanup(struct netpoll *np, struct netpoll_info *npinfo)
-{
-}
-#endif /* CONFIG_NETPOLL_TRAP */
-
 void netpoll_print_options(struct netpoll *np)
 {
 	np_info(np, "local port %d\n", np->local_port);
@@ -1103,8 +609,6 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
 			goto out;
 		}
 
-		netpoll_trap_setup_info(npinfo);
-
 		sema_init(&npinfo->dev_lock, 1);
 		skb_queue_head_init(&npinfo->txq);
 		INIT_DELAYED_WORK(&npinfo->tx_work, queue_process);
@@ -1124,8 +628,6 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
 
 	npinfo->netpoll = np;
 
-	netpoll_trap_setup(np, npinfo);
-
 	/* last thing to do is link it to the net device structure */
 	rcu_assign_pointer(ndev->npinfo, npinfo);
 
@@ -1274,7 +776,6 @@ static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head)
 	struct netpoll_info *npinfo =
 			container_of(rcu_head, struct netpoll_info, rcu);
 
-	netpoll_trap_cleanup_info(npinfo);
 	skb_queue_purge(&npinfo->txq);
 
 	/* we can't call cancel_delayed_work_sync here, as we are in softirq */
@@ -1299,8 +800,6 @@ void __netpoll_cleanup(struct netpoll *np)
 	if (!npinfo)
 		return;
 
-	netpoll_trap_cleanup(np, npinfo);
-
 	synchronize_srcu(&netpoll_srcu);
 
 	if (atomic_dec_and_test(&npinfo->refcnt)) {
@@ -1344,20 +843,3 @@ out:
 	rtnl_unlock();
 }
 EXPORT_SYMBOL(netpoll_cleanup);
-
-#ifdef CONFIG_NETPOLL_TRAP
-int netpoll_trap(void)
-{
-	return atomic_read(&trapped);
-}
-EXPORT_SYMBOL(netpoll_trap);
-
-void netpoll_set_trap(int trap)
-{
-	if (trap)
-		atomic_inc(&trapped);
-	else
-		atomic_dec(&trapped);
-}
-EXPORT_SYMBOL(netpoll_set_trap);
-#endif /* CONFIG_NETPOLL_TRAP */
-- 
cgit v1.2.3


From 26de4f1b2fb45e53a9e8f4f913b9cdf6c294070b Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@linux-m68k.org>
Date: Tue, 11 Mar 2014 11:11:19 +0100
Subject: serial: sh-sci: Add more register documentation

Signed-off-by: Geert Uytterhoeven <geert+renesas@linux-m68k.org>
Acked-by: Simon Horman <horms@verge.net.au>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/tty/serial/sh-sci.c | 28 +++++++-------
 include/linux/serial_sci.h  | 93 ++++++++++++++++++++++++++++-----------------
 2 files changed, 73 insertions(+), 48 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index c93154f690a6..22a508a638b9 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -911,7 +911,7 @@ static irqreturn_t sci_rx_interrupt(int irq, void *ptr)
 		/* Disable future Rx interrupts */
 		if (port->type == PORT_SCIFA || port->type == PORT_SCIFB) {
 			disable_irq_nosync(irq);
-			scr |= 0x4000;
+			scr |= SCSCR_RDRQE;
 		} else {
 			scr &= ~SCSCR_RIE;
 		}
@@ -1200,7 +1200,9 @@ static void sci_set_mctrl(struct uart_port *port, unsigned int mctrl)
 		 */
 		reg = sci_getreg(port, SCFCR);
 		if (reg->size)
-			serial_port_out(port, SCFCR, serial_port_in(port, SCFCR) | 1);
+			serial_port_out(port, SCFCR,
+					serial_port_in(port, SCFCR) |
+					SCFCR_LOOP);
 	}
 }
 
@@ -1496,9 +1498,9 @@ static void sci_start_tx(struct uart_port *port)
 	if (port->type == PORT_SCIFA || port->type == PORT_SCIFB) {
 		u16 new, scr = serial_port_in(port, SCSCR);
 		if (s->chan_tx)
-			new = scr | 0x8000;
+			new = scr | SCSCR_TDRQE;
 		else
-			new = scr & ~0x8000;
+			new = scr & ~SCSCR_TDRQE;
 		if (new != scr)
 			serial_port_out(port, SCSCR, new);
 	}
@@ -1525,7 +1527,7 @@ static void sci_stop_tx(struct uart_port *port)
 	ctrl = serial_port_in(port, SCSCR);
 
 	if (port->type == PORT_SCIFA || port->type == PORT_SCIFB)
-		ctrl &= ~0x8000;
+		ctrl &= ~SCSCR_TDRQE;
 
 	ctrl &= ~SCSCR_TIE;
 
@@ -1539,7 +1541,7 @@ static void sci_start_rx(struct uart_port *port)
 	ctrl = serial_port_in(port, SCSCR) | port_rx_irq_mask(port);
 
 	if (port->type == PORT_SCIFA || port->type == PORT_SCIFB)
-		ctrl &= ~0x4000;
+		ctrl &= ~SCSCR_RDRQE;
 
 	serial_port_out(port, SCSCR, ctrl);
 }
@@ -1551,7 +1553,7 @@ static void sci_stop_rx(struct uart_port *port)
 	ctrl = serial_port_in(port, SCSCR);
 
 	if (port->type == PORT_SCIFA || port->type == PORT_SCIFB)
-		ctrl &= ~0x4000;
+		ctrl &= ~SCSCR_RDRQE;
 
 	ctrl &= ~port_rx_irq_mask(port);
 
@@ -1614,7 +1616,7 @@ static void rx_timer_fn(unsigned long arg)
 	u16 scr = serial_port_in(port, SCSCR);
 
 	if (port->type == PORT_SCIFA || port->type == PORT_SCIFB) {
-		scr &= ~0x4000;
+		scr &= ~SCSCR_RDRQE;
 		enable_irq(s->irqs[SCIx_RXI_IRQ]);
 	}
 	serial_port_out(port, SCSCR, scr | SCSCR_RIE);
@@ -1871,13 +1873,13 @@ static void sci_set_termios(struct uart_port *port, struct ktermios *termios,
 	smr_val = serial_port_in(port, SCSMR) & 3;
 
 	if ((termios->c_cflag & CSIZE) == CS7)
-		smr_val |= 0x40;
+		smr_val |= SCSMR_CHR;
 	if (termios->c_cflag & PARENB)
-		smr_val |= 0x20;
+		smr_val |= SCSMR_PE;
 	if (termios->c_cflag & PARODD)
-		smr_val |= 0x30;
+		smr_val |= SCSMR_PE | SCSMR_ODD;
 	if (termios->c_cflag & CSTOPB)
-		smr_val |= 0x08;
+		smr_val |= SCSMR_STOP;
 
 	uart_update_timeout(port, termios->c_cflag, baud);
 
@@ -1885,7 +1887,7 @@ static void sci_set_termios(struct uart_port *port, struct ktermios *termios,
 		__func__, smr_val, cks, t, s->cfg->scscr);
 
 	if (t >= 0) {
-		serial_port_out(port, SCSMR, (smr_val & ~3) | cks);
+		serial_port_out(port, SCSMR, (smr_val & ~SCSMR_CKS) | cks);
 		serial_port_out(port, SCBRR, t);
 		reg = sci_getreg(port, HSSRR);
 		if (reg->size)
diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h
index 22b3640c9424..6c5e3bb282b0 100644
--- a/include/linux/serial_sci.h
+++ b/include/linux/serial_sci.h
@@ -10,45 +10,59 @@
 
 #define SCIx_NOT_SUPPORTED	(-1)
 
-#define SCSCR_TIE	(1 << 7)
-#define SCSCR_RIE	(1 << 6)
-#define SCSCR_TE	(1 << 5)
-#define SCSCR_RE	(1 << 4)
-#define SCSCR_REIE	(1 << 3)	/* not supported by all parts */
-#define SCSCR_TOIE	(1 << 2)	/* not supported by all parts */
-#define SCSCR_CKE1	(1 << 1)
-#define SCSCR_CKE0	(1 << 0)
-
-/* SCxSR SCI */
-#define SCI_TDRE  0x80
-#define SCI_RDRF  0x40
-#define SCI_ORER  0x20
-#define SCI_FER   0x10
-#define SCI_PER   0x08
-#define SCI_TEND  0x04
+/* SCSMR (Serial Mode Register) */
+#define SCSMR_CHR	(1 << 6)	/* 7-bit Character Length */
+#define SCSMR_PE	(1 << 5)	/* Parity Enable */
+#define SCSMR_ODD	(1 << 4)	/* Odd Parity */
+#define SCSMR_STOP	(1 << 3)	/* Stop Bit Length */
+#define SCSMR_CKS	0x0003		/* Clock Select */
+
+/* Serial Control Register (@ = not supported by all parts) */
+#define SCSCR_TIE	(1 << 7)	/* Transmit Interrupt Enable */
+#define SCSCR_RIE	(1 << 6)	/* Receive Interrupt Enable */
+#define SCSCR_TE	(1 << 5)	/* Transmit Enable */
+#define SCSCR_RE	(1 << 4)	/* Receive Enable */
+#define SCSCR_REIE	(1 << 3)	/* Receive Error Interrupt Enable @ */
+#define SCSCR_TOIE	(1 << 2)	/* Timeout Interrupt Enable @ */
+#define SCSCR_CKE1	(1 << 1)	/* Clock Enable 1 */
+#define SCSCR_CKE0	(1 << 0)	/* Clock Enable 0 */
+/* SCIFA/SCIFB only */
+#define SCSCR_TDRQE	(1 << 15)	/* Tx Data Transfer Request Enable */
+#define SCSCR_RDRQE	(1 << 14)	/* Rx Data Transfer Request Enable */
+
+/* SCxSR (Serial Status Register) on SCI */
+#define SCI_TDRE  0x80			/* Transmit Data Register Empty */
+#define SCI_RDRF  0x40			/* Receive Data Register Full */
+#define SCI_ORER  0x20			/* Overrun Error */
+#define SCI_FER   0x10			/* Framing Error */
+#define SCI_PER   0x08			/* Parity Error */
+#define SCI_TEND  0x04			/* Transmit End */
 
 #define SCI_DEFAULT_ERROR_MASK (SCI_PER | SCI_FER)
 
-/* SCxSR SCIF, HSCIF */
-#define SCIF_ER    0x0080
-#define SCIF_TEND  0x0040
-#define SCIF_TDFE  0x0020
-#define SCIF_BRK   0x0010
-#define SCIF_FER   0x0008
-#define SCIF_PER   0x0004
-#define SCIF_RDF   0x0002
-#define SCIF_DR    0x0001
+/* SCxSR (Serial Status Register) on SCIF, HSCIF */
+#define SCIF_ER    0x0080		/* Receive Error */
+#define SCIF_TEND  0x0040		/* Transmission End */
+#define SCIF_TDFE  0x0020		/* Transmit FIFO Data Empty */
+#define SCIF_BRK   0x0010		/* Break Detect */
+#define SCIF_FER   0x0008		/* Framing Error */
+#define SCIF_PER   0x0004		/* Parity Error */
+#define SCIF_RDF   0x0002		/* Receive FIFO Data Full */
+#define SCIF_DR    0x0001		/* Receive Data Ready */
 
 #define SCIF_DEFAULT_ERROR_MASK (SCIF_PER | SCIF_FER | SCIF_ER | SCIF_BRK)
 
-/* SCSPTR, optional */
-#define SCSPTR_RTSIO	(1 << 7)
-#define SCSPTR_CTSIO	(1 << 5)
-#define SCSPTR_SPB2IO	(1 << 1)
-#define SCSPTR_SPB2DT	(1 << 0)
+/* SCFCR (FIFO Control Register) */
+#define SCFCR_LOOP	(1 << 0)	/* Loopback Test */
+
+/* SCSPTR (Serial Port Register), optional */
+#define SCSPTR_RTSIO	(1 << 7)	/* Serial Port RTS Pin Input/Output */
+#define SCSPTR_CTSIO	(1 << 5)	/* Serial Port CTS Pin Input/Output */
+#define SCSPTR_SPB2IO	(1 << 1)	/* Serial Port Break Input/Output */
+#define SCSPTR_SPB2DT	(1 << 0)	/* Serial Port Break Data */
 
 /* HSSRR HSCIF */
-#define HSCIF_SRE	0x8000
+#define HSCIF_SRE	0x8000		/* Sampling Rate Register Enable */
 
 enum {
 	SCIx_PROBE_REGTYPE,
@@ -73,10 +87,19 @@ enum {
  * Not all registers will exist on all parts.
  */
 enum {
-	SCSMR, SCBRR, SCSCR, SCxSR,
-	SCFCR, SCFDR, SCxTDR, SCxRDR,
-	SCLSR, SCTFDR, SCRFDR, SCSPTR,
-	HSSRR,
+	SCSMR,				/* Serial Mode Register */
+	SCBRR,				/* Bit Rate Register */
+	SCSCR,				/* Serial Control Register */
+	SCxSR,				/* Serial Status Register */
+	SCFCR,				/* FIFO Control Register */
+	SCFDR,				/* FIFO Data Count Register */
+	SCxTDR,				/* Transmit (FIFO) Data Register */
+	SCxRDR,				/* Receive (FIFO) Data Register */
+	SCLSR,				/* Line Status Register */
+	SCTFDR,				/* Transmit FIFO Data Count Register */
+	SCRFDR,				/* Receive FIFO Data Count Register */
+	SCSPTR,				/* Serial Port Register */
+	HSSRR,				/* Sampling Rate Register */
 
 	SCIx_NR_REGS,
 };
-- 
cgit v1.2.3


From 99be0245c8869cbd7b9c0ab3f093f41c60362f91 Mon Sep 17 00:00:00 2001
From: Sebastian Reichel <sre@debian.org>
Date: Sun, 16 Mar 2014 02:43:27 +0100
Subject: mfd: twl4030-madc: Cleanup driver

Some style fixes in twl4030-madc driver.

Reported-by: Jonathan Cameron <jic23@kernel.org>
Reported-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Sebastian Reichel <sre@debian.org>
Acked-by: Jonathan Cameron <jic23@kernel.org>
Tested-by: Marek Belisko <marek@goldelico.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/twl4030-madc.c       | 145 +++++++++++++++++++--------------------
 include/linux/i2c/twl4030-madc.h |   2 +-
 2 files changed, 73 insertions(+), 74 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mfd/twl4030-madc.c b/drivers/mfd/twl4030-madc.c
index 93ef91229cd3..98b9c9874d26 100644
--- a/drivers/mfd/twl4030-madc.c
+++ b/drivers/mfd/twl4030-madc.c
@@ -49,22 +49,22 @@
 
 #include <linux/iio/iio.h>
 
-/*
+/**
  * struct twl4030_madc_data - a container for madc info
- * @dev - pointer to device structure for madc
- * @lock - mutex protecting this data structure
- * @requests - Array of request struct corresponding to SW1, SW2 and RT
- * @use_second_irq - IRQ selection (main or co-processor)
- * @imr - Interrupt mask register of MADC
- * @isr - Interrupt status register of MADC
+ * @dev:		Pointer to device structure for madc
+ * @lock:		Mutex protecting this data structure
+ * @requests:		Array of request struct corresponding to SW1, SW2 and RT
+ * @use_second_irq:	IRQ selection (main or co-processor)
+ * @imr:		Interrupt mask register of MADC
+ * @isr:		Interrupt status register of MADC
  */
 struct twl4030_madc_data {
 	struct device *dev;
 	struct mutex lock;	/* mutex protecting this data structure */
 	struct twl4030_madc_request requests[TWL4030_MADC_NUM_METHODS];
 	bool use_second_irq;
-	int imr;
-	int isr;
+	u8 imr;
+	u8 isr;
 };
 
 static int twl4030_madc_read(struct iio_dev *iio_dev,
@@ -155,17 +155,16 @@ twl4030_divider_ratios[16] = {
 };
 
 
-/*
- * Conversion table from -3 to 55 degree Celcius
- */
-static int therm_tbl[] = {
-30800,	29500,	28300,	27100,
-26000,	24900,	23900,	22900,	22000,	21100,	20300,	19400,	18700,	17900,
-17200,	16500,	15900,	15300,	14700,	14100,	13600,	13100,	12600,	12100,
-11600,	11200,	10800,	10400,	10000,	9630,	9280,	8950,	8620,	8310,
-8020,	7730,	7460,	7200,	6950,	6710,	6470,	6250,	6040,	5830,
-5640,	5450,	5260,	5090,	4920,	4760,	4600,	4450,	4310,	4170,
-4040,	3910,	3790,	3670,	3550
+/* Conversion table from -3 to 55 degrees Celcius */
+static int twl4030_therm_tbl[] = {
+	30800,	29500,	28300,	27100,
+	26000,	24900,	23900,	22900,	22000,	21100,	20300,	19400,	18700,
+	17900,	17200,	16500,	15900,	15300,	14700,	14100,	13600,	13100,
+	12600,	12100,	11600,	11200,	10800,	10400,	10000,	9630,	9280,
+	8950,	8620,	8310,	8020,	7730,	7460,	7200,	6950,	6710,
+	6470,	6250,	6040,	5830,	5640,	5450,	5260,	5090,	4920,
+	4760,	4600,	4450,	4310,	4170,	4040,	3910,	3790,	3670,
+	3550
 };
 
 /*
@@ -197,11 +196,12 @@ const struct twl4030_madc_conversion_method twl4030_conversion_methods[] = {
 			      },
 };
 
-/*
- * Function to read a particular channel value.
- * @madc - pointer to struct twl4030_madc_data
- * @reg - lsb of ADC Channel
- * If the i2c read fails it returns an error else returns 0.
+/**
+ * twl4030_madc_channel_raw_read() - Function to read a particular channel value
+ * @madc:	pointer to struct twl4030_madc_data
+ * @reg:	lsb of ADC Channel
+ *
+ * Return: 0 on success, an error code otherwise.
  */
 static int twl4030_madc_channel_raw_read(struct twl4030_madc_data *madc, u8 reg)
 {
@@ -227,7 +227,7 @@ static int twl4030_madc_channel_raw_read(struct twl4030_madc_data *madc, u8 reg)
 }
 
 /*
- * Return battery temperature
+ * Return battery temperature in degrees Celsius
  * Or < 0 on failure.
  */
 static int twl4030battery_temperature(int raw_volt)
@@ -236,18 +236,18 @@ static int twl4030battery_temperature(int raw_volt)
 	int temp, curr, volt, res, ret;
 
 	volt = (raw_volt * TEMP_STEP_SIZE) / TEMP_PSR_R;
-	/* Getting and calculating the supply current in micro ampers */
+	/* Getting and calculating the supply current in micro amperes */
 	ret = twl_i2c_read_u8(TWL_MODULE_MAIN_CHARGE, &val,
 		REG_BCICTL2);
 	if (ret < 0)
 		return ret;
+
 	curr = ((val & TWL4030_BCI_ITHEN) + 1) * 10;
 	/* Getting and calculating the thermistor resistance in ohms */
 	res = volt * 1000 / curr;
 	/* calculating temperature */
 	for (temp = 58; temp >= 0; temp--) {
-		int actual = therm_tbl[temp];
-
+		int actual = twl4030_therm_tbl[temp];
 		if ((actual - res) >= 0)
 			break;
 	}
@@ -269,11 +269,12 @@ static int twl4030battery_current(int raw_volt)
 	else /* slope of 0.88 mV/mA */
 		return (raw_volt * CURR_STEP_SIZE) / CURR_PSR_R2;
 }
+
 /*
  * Function to read channel values
  * @madc - pointer to twl4030_madc_data struct
  * @reg_base - Base address of the first channel
- * @Channels - 16 bit bitmap. If the bit is set, channel value is read
+ * @Channels - 16 bit bitmap. If the bit is set, channel's value is read
  * @buf - The channel values are stored here. if read fails error
  * @raw - Return raw values without conversion
  * value is stored
@@ -284,17 +285,17 @@ static int twl4030_madc_read_channels(struct twl4030_madc_data *madc,
 				      long channels, int *buf,
 				      bool raw)
 {
-	int count = 0, count_req = 0, i;
+	int count = 0;
+	int i;
 	u8 reg;
 
 	for_each_set_bit(i, &channels, TWL4030_MADC_MAX_CHANNELS) {
-		reg = reg_base + 2 * i;
+		reg = reg_base + (2 * i);
 		buf[i] = twl4030_madc_channel_raw_read(madc, reg);
 		if (buf[i] < 0) {
-			dev_err(madc->dev,
-				"Unable to read register 0x%X\n", reg);
-			count_req++;
-			continue;
+			dev_err(madc->dev, "Unable to read register 0x%X\n",
+				reg);
+			return buf[i];
 		}
 		if (raw) {
 			count++;
@@ -305,7 +306,7 @@ static int twl4030_madc_read_channels(struct twl4030_madc_data *madc,
 			buf[i] = twl4030battery_current(buf[i]);
 			if (buf[i] < 0) {
 				dev_err(madc->dev, "err reading current\n");
-				count_req++;
+				return buf[i];
 			} else {
 				count++;
 				buf[i] = buf[i] - 750;
@@ -315,7 +316,7 @@ static int twl4030_madc_read_channels(struct twl4030_madc_data *madc,
 			buf[i] = twl4030battery_temperature(buf[i]);
 			if (buf[i] < 0) {
 				dev_err(madc->dev, "err reading temperature\n");
-				count_req++;
+				return buf[i];
 			} else {
 				buf[i] -= 3;
 				count++;
@@ -336,8 +337,6 @@ static int twl4030_madc_read_channels(struct twl4030_madc_data *madc,
 				twl4030_divider_ratios[i].numerator);
 		}
 	}
-	if (count_req)
-		dev_err(madc->dev, "%d channel conversion failed\n", count_req);
 
 	return count;
 }
@@ -361,13 +360,13 @@ static int twl4030_madc_enable_irq(struct twl4030_madc_data *madc, u8 id)
 			madc->imr);
 		return ret;
 	}
+
 	val &= ~(1 << id);
 	ret = twl_i2c_write_u8(TWL4030_MODULE_MADC, val, madc->imr);
 	if (ret) {
 		dev_err(madc->dev,
 			"unable to write imr register 0x%X\n", madc->imr);
 		return ret;
-
 	}
 
 	return 0;
@@ -430,7 +429,7 @@ static irqreturn_t twl4030_madc_threaded_irq_handler(int irq, void *_madc)
 			continue;
 		ret = twl4030_madc_disable_irq(madc, i);
 		if (ret < 0)
-			dev_dbg(madc->dev, "Disable interrupt failed%d\n", i);
+			dev_dbg(madc->dev, "Disable interrupt failed %d\n", i);
 		madc->requests[i].result_pending = 1;
 	}
 	for (i = 0; i < TWL4030_MADC_NUM_METHODS; i++) {
@@ -512,21 +511,17 @@ static int twl4030_madc_start_conversion(struct twl4030_madc_data *madc,
 {
 	const struct twl4030_madc_conversion_method *method;
 	int ret = 0;
+
+	if (conv_method != TWL4030_MADC_SW1 && conv_method != TWL4030_MADC_SW2)
+		return -ENOTSUPP;
+
 	method = &twl4030_conversion_methods[conv_method];
-	switch (conv_method) {
-	case TWL4030_MADC_SW1:
-	case TWL4030_MADC_SW2:
-		ret = twl_i2c_write_u8(TWL4030_MODULE_MADC,
-				       TWL4030_MADC_SW_START, method->ctrl);
-		if (ret) {
-			dev_err(madc->dev,
-				"unable to write ctrl register 0x%X\n",
-				method->ctrl);
-			return ret;
-		}
-		break;
-	default:
-		break;
+	ret = twl_i2c_write_u8(TWL4030_MODULE_MADC, TWL4030_MADC_SW_START,
+			       method->ctrl);
+	if (ret) {
+		dev_err(madc->dev, "unable to write ctrl register 0x%X\n",
+			method->ctrl);
+		return ret;
 	}
 
 	return 0;
@@ -623,8 +618,8 @@ int twl4030_madc_conversion(struct twl4030_madc_request *req)
 				       ch_lsb, method->avg);
 		if (ret) {
 			dev_err(twl4030_madc->dev,
-				"unable to write sel reg 0x%X\n",
-				method->sel + 1);
+				"unable to write avg reg 0x%X\n",
+				method->avg);
 			goto out;
 		}
 	}
@@ -665,10 +660,6 @@ out:
 }
 EXPORT_SYMBOL_GPL(twl4030_madc_conversion);
 
-/*
- * Return channel value
- * Or < 0 on failure.
- */
 int twl4030_get_madc_conversion(int channel_no)
 {
 	struct twl4030_madc_request req;
@@ -689,20 +680,25 @@ int twl4030_get_madc_conversion(int channel_no)
 }
 EXPORT_SYMBOL_GPL(twl4030_get_madc_conversion);
 
-/*
+/**
+ * twl4030_madc_set_current_generator() - setup bias current
+ *
+ * @madc:	pointer to twl4030_madc_data struct
+ * @chan:	can be one of the two values:
+ *		TWL4030_BCI_ITHEN
+ *		Enables bias current for main battery type reading
+ *		TWL4030_BCI_TYPEN
+ *		Enables bias current for main battery temperature sensing
+ * @on:		enable or disable chan.
+ *
  * Function to enable or disable bias current for
  * main battery type reading or temperature sensing
- * @madc - pointer to twl4030_madc_data struct
- * @chan - can be one of the two values
- * TWL4030_BCI_ITHEN - Enables bias current for main battery type reading
- * TWL4030_BCI_TYPEN - Enables bias current for main battery temperature
- * sensing
- * @on - enable or disable chan.
  */
 static int twl4030_madc_set_current_generator(struct twl4030_madc_data *madc,
 					      int chan, int on)
 {
 	int ret;
+	int regmask;
 	u8 regval;
 
 	ret = twl_i2c_read_u8(TWL_MODULE_MAIN_CHARGE,
@@ -712,10 +708,13 @@ static int twl4030_madc_set_current_generator(struct twl4030_madc_data *madc,
 			TWL4030_BCI_BCICTL1);
 		return ret;
 	}
+
+	regmask = chan ? TWL4030_BCI_ITHEN : TWL4030_BCI_TYPEN;
 	if (on)
-		regval |= chan ? TWL4030_BCI_ITHEN : TWL4030_BCI_TYPEN;
+		regval |= regmask;
 	else
-		regval &= chan ? ~TWL4030_BCI_ITHEN : ~TWL4030_BCI_TYPEN;
+		regval &= ~regmask;
+
 	ret = twl_i2c_write_u8(TWL_MODULE_MAIN_CHARGE,
 			       regval, TWL4030_BCI_BCICTL1);
 	if (ret) {
@@ -730,7 +729,7 @@ static int twl4030_madc_set_current_generator(struct twl4030_madc_data *madc,
 /*
  * Function that sets MADC software power on bit to enable MADC
  * @madc - pointer to twl4030_madc_data struct
- * @on - Enable or disable MADC software powen on bit.
+ * @on - Enable or disable MADC software power on bit.
  * returns error if i2c read/write fails else 0
  */
 static int twl4030_madc_set_power(struct twl4030_madc_data *madc, int on)
@@ -909,7 +908,7 @@ static struct platform_driver twl4030_madc_driver = {
 		   .name = "twl4030_madc",
 		   .owner = THIS_MODULE,
 		   .of_match_table = of_match_ptr(twl_madc_of_match),
-		   },
+	},
 };
 
 module_platform_driver(twl4030_madc_driver);
diff --git a/include/linux/i2c/twl4030-madc.h b/include/linux/i2c/twl4030-madc.h
index 01f595107048..1c0134dd3271 100644
--- a/include/linux/i2c/twl4030-madc.h
+++ b/include/linux/i2c/twl4030-madc.h
@@ -44,7 +44,7 @@ struct twl4030_madc_conversion_method {
 
 struct twl4030_madc_request {
 	unsigned long channels;
-	u16 do_avg;
+	bool do_avg;
 	u16 method;
 	u16 type;
 	bool active;
-- 
cgit v1.2.3


From 204dfd63a07ec4785fc786ff3511d85eb1346b7b Mon Sep 17 00:00:00 2001
From: Sebastian Reichel <sre@debian.org>
Date: Sun, 16 Mar 2014 02:43:28 +0100
Subject: mfd: twl-core: Add twl_i2c_read/write_u16

Add a simple twl_i2c_read/write_u16 wrapper over
the twl_i2c_read/write, which is similar to the
twl_i2c_read/write_u8 wrapper.

Signed-off-by: Sebastian Reichel <sre@debian.org>
Acked-by: Jonathan Cameron <jic23@kernel.org>
Tested-by: Marek Belisko <marek@goldelico.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/i2c/twl.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/i2c/twl.h b/include/linux/i2c/twl.h
index ade1c06d4ceb..d2b16704624c 100644
--- a/include/linux/i2c/twl.h
+++ b/include/linux/i2c/twl.h
@@ -195,6 +195,18 @@ static inline int twl_i2c_read_u8(u8 mod_no, u8 *val, u8 reg) {
 	return twl_i2c_read(mod_no, val, reg, 1);
 }
 
+static inline int twl_i2c_write_u16(u8 mod_no, u16 val, u8 reg) {
+	val = cpu_to_le16(val);
+	return twl_i2c_write(mod_no, (u8*) &val, reg, 2);
+}
+
+static inline int twl_i2c_read_u16(u8 mod_no, u16 *val, u8 reg) {
+	int ret;
+	ret = twl_i2c_read(mod_no, (u8*) val, reg, 2);
+	*val = le16_to_cpu(*val);
+	return ret;
+}
+
 int twl_get_type(void);
 int twl_get_version(void);
 int twl_get_hfclk_rate(void);
-- 
cgit v1.2.3


From b07e2b70b9a1ff9f59af66fd0085c1c52178f440 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Date: Fri, 28 Feb 2014 11:41:41 +0100
Subject: mfd: sec-core: Add maximum RTC register for regmap config

Add maximum register to the regmap used by rtc-s5m driver.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/sec-core.c          | 2 ++
 include/linux/mfd/samsung/rtc.h | 2 ++
 2 files changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/mfd/sec-core.c b/drivers/mfd/sec-core.c
index 714e2135210e..306b3a282c29 100644
--- a/drivers/mfd/sec-core.c
+++ b/drivers/mfd/sec-core.c
@@ -141,6 +141,8 @@ static const struct regmap_config s5m8767_regmap_config = {
 static const struct regmap_config sec_rtc_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
+
+	.max_register = SEC_RTC_REG_MAX,
 };
 
 #ifdef CONFIG_OF
diff --git a/include/linux/mfd/samsung/rtc.h b/include/linux/mfd/samsung/rtc.h
index 94b7cd6d8891..4627f59ebd84 100644
--- a/include/linux/mfd/samsung/rtc.h
+++ b/include/linux/mfd/samsung/rtc.h
@@ -43,6 +43,8 @@ enum sec_rtc_reg {
 	SEC_RTC_STATUS,
 	SEC_WTSR_SMPL_CNTL,
 	SEC_RTC_UDR_CON,
+
+	SEC_RTC_REG_MAX,
 };
 
 #define RTC_I2C_ADDR		(0x0C >> 1)
-- 
cgit v1.2.3


From 677620952a0fd1b1618bed57c1ebd94bf3c710f3 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Date: Fri, 28 Feb 2014 11:41:43 +0100
Subject: mfd: sec-irq: Use consistent S2MPS11 RTC alarm interrupt indexes

The S2MPS11 RTC has two alarms: alarm0 and alarm1 (corresponding
interrupts are named similarly). Use consistent names for interrupts to
limit possible errors.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/sec-irq.c           | 8 ++++----
 include/linux/mfd/samsung/irq.h | 4 ++--
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mfd/sec-irq.c b/drivers/mfd/sec-irq.c
index 4de494f51d40..e403c293b437 100644
--- a/drivers/mfd/sec-irq.c
+++ b/drivers/mfd/sec-irq.c
@@ -59,13 +59,13 @@ static const struct regmap_irq s2mps11_irqs[] = {
 		.reg_offset = 1,
 		.mask = S2MPS11_IRQ_RTC60S_MASK,
 	},
-	[S2MPS11_IRQ_RTCA1] = {
+	[S2MPS11_IRQ_RTCA0] = {
 		.reg_offset = 1,
-		.mask = S2MPS11_IRQ_RTCA1_MASK,
+		.mask = S2MPS11_IRQ_RTCA0_MASK,
 	},
-	[S2MPS11_IRQ_RTCA2] = {
+	[S2MPS11_IRQ_RTCA1] = {
 		.reg_offset = 1,
-		.mask = S2MPS11_IRQ_RTCA2_MASK,
+		.mask = S2MPS11_IRQ_RTCA1_MASK,
 	},
 	[S2MPS11_IRQ_SMPL] = {
 		.reg_offset = 1,
diff --git a/include/linux/mfd/samsung/irq.h b/include/linux/mfd/samsung/irq.h
index d43b4f9e7fb2..abe1a6aae3b7 100644
--- a/include/linux/mfd/samsung/irq.h
+++ b/include/linux/mfd/samsung/irq.h
@@ -24,8 +24,8 @@ enum s2mps11_irq {
 	S2MPS11_IRQ_MRB,
 
 	S2MPS11_IRQ_RTC60S,
+	S2MPS11_IRQ_RTCA0,
 	S2MPS11_IRQ_RTCA1,
-	S2MPS11_IRQ_RTCA2,
 	S2MPS11_IRQ_SMPL,
 	S2MPS11_IRQ_RTC1S,
 	S2MPS11_IRQ_WTSR,
@@ -47,7 +47,7 @@ enum s2mps11_irq {
 
 #define S2MPS11_IRQ_RTC60S_MASK		(1 << 0)
 #define S2MPS11_IRQ_RTCA1_MASK		(1 << 1)
-#define S2MPS11_IRQ_RTCA2_MASK		(1 << 2)
+#define S2MPS11_IRQ_RTCA0_MASK		(1 << 2)
 #define S2MPS11_IRQ_SMPL_MASK		(1 << 3)
 #define S2MPS11_IRQ_RTC1S_MASK		(1 << 4)
 #define S2MPS11_IRQ_WTSR_MASK		(1 << 5)
-- 
cgit v1.2.3


From dc6919663f7a02d02cc08d605a1f68d6cefe0042 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Date: Fri, 28 Feb 2014 11:41:44 +0100
Subject: mfd: sec: Add support for S2MPS14

Add support for S2MPS14 PMIC device to the MFD sec-core driver.
The S2MPS14 is similar to S2MPS11 but it has fewer regulators, two
clocks instead of three and a little different registers layout.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/sec-core.c              |  48 ++++++++++--
 drivers/mfd/sec-irq.c               |  89 ++++++++++++++++++++-
 include/linux/mfd/samsung/core.h    |   1 +
 include/linux/mfd/samsung/irq.h     |  27 +++++++
 include/linux/mfd/samsung/rtc.h     |  55 +++++++++++--
 include/linux/mfd/samsung/s2mps14.h | 152 ++++++++++++++++++++++++++++++++++++
 6 files changed, 360 insertions(+), 12 deletions(-)
 create mode 100644 include/linux/mfd/samsung/s2mps14.h

(limited to 'include/linux')

diff --git a/drivers/mfd/sec-core.c b/drivers/mfd/sec-core.c
index 9623899e6f7c..a4df76c160f8 100644
--- a/drivers/mfd/sec-core.c
+++ b/drivers/mfd/sec-core.c
@@ -27,6 +27,7 @@
 #include <linux/mfd/samsung/irq.h>
 #include <linux/mfd/samsung/rtc.h>
 #include <linux/mfd/samsung/s2mps11.h>
+#include <linux/mfd/samsung/s2mps14.h>
 #include <linux/mfd/samsung/s5m8763.h>
 #include <linux/mfd/samsung/s5m8767.h>
 #include <linux/regmap.h>
@@ -69,6 +70,16 @@ static const struct mfd_cell s2mps11_devs[] = {
 	}
 };
 
+static const struct mfd_cell s2mps14_devs[] = {
+	{
+		.name = "s2mps14-pmic",
+	}, {
+		.name = "s2mps14-rtc",
+	}, {
+		.name = "s2mps14-clk",
+	}
+};
+
 #ifdef CONFIG_OF
 static struct of_device_id sec_dt_match[] = {
 	{	.compatible = "samsung,s5m8767-pmic",
@@ -77,6 +88,9 @@ static struct of_device_id sec_dt_match[] = {
 	{	.compatible = "samsung,s2mps11-pmic",
 		.data = (void *)S2MPS11X,
 	},
+	{	.compatible = "samsung,s2mps14-pmic",
+		.data = (void *)S2MPS14X,
+	},
 	{},
 };
 #endif
@@ -120,6 +134,15 @@ static const struct regmap_config s2mps11_regmap_config = {
 	.cache_type = REGCACHE_FLAT,
 };
 
+static const struct regmap_config s2mps14_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = S2MPS14_REG_LDODSCH3,
+	.volatile_reg = s2mps11_volatile,
+	.cache_type = REGCACHE_FLAT,
+};
+
 static const struct regmap_config s5m8763_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
@@ -138,13 +161,20 @@ static const struct regmap_config s5m8767_regmap_config = {
 	.cache_type = REGCACHE_FLAT,
 };
 
-static const struct regmap_config sec_rtc_regmap_config = {
+static const struct regmap_config s5m_rtc_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
 
 	.max_register = SEC_RTC_REG_MAX,
 };
 
+static const struct regmap_config s2mps14_rtc_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = S2MPS_RTC_REG_MAX,
+};
+
 #ifdef CONFIG_OF
 /*
  * Only the common platform data elements for s5m8767 are parsed here from the
@@ -239,19 +269,23 @@ static int sec_pmic_probe(struct i2c_client *i2c,
 		 * However we must pass something to devm_regmap_init_i2c()
 		 * so use S5M-like regmap config even though it wouldn't work.
 		 */
-		regmap_rtc = &sec_rtc_regmap_config;
+		regmap_rtc = &s5m_rtc_regmap_config;
+		break;
+	case S2MPS14X:
+		regmap = &s2mps14_regmap_config;
+		regmap_rtc = &s2mps14_rtc_regmap_config;
 		break;
 	case S5M8763X:
 		regmap = &s5m8763_regmap_config;
-		regmap_rtc = &sec_rtc_regmap_config;
+		regmap_rtc = &s5m_rtc_regmap_config;
 		break;
 	case S5M8767X:
 		regmap = &s5m8767_regmap_config;
-		regmap_rtc = &sec_rtc_regmap_config;
+		regmap_rtc = &s5m_rtc_regmap_config;
 		break;
 	default:
 		regmap = &sec_regmap_config;
-		regmap_rtc = &sec_rtc_regmap_config;
+		regmap_rtc = &s5m_rtc_regmap_config;
 		break;
 	}
 
@@ -298,6 +332,10 @@ static int sec_pmic_probe(struct i2c_client *i2c,
 		ret = mfd_add_devices(sec_pmic->dev, -1, s2mps11_devs,
 				      ARRAY_SIZE(s2mps11_devs), NULL, 0, NULL);
 		break;
+	case S2MPS14X:
+		ret = mfd_add_devices(sec_pmic->dev, -1, s2mps14_devs,
+				      ARRAY_SIZE(s2mps14_devs), NULL, 0, NULL);
+		break;
 	default:
 		/* If this happens the probe function is problem */
 		BUG();
diff --git a/drivers/mfd/sec-irq.c b/drivers/mfd/sec-irq.c
index e403c293b437..64e7913aadc6 100644
--- a/drivers/mfd/sec-irq.c
+++ b/drivers/mfd/sec-irq.c
@@ -1,7 +1,7 @@
 /*
  * sec-irq.c
  *
- * Copyright (c) 2011 Samsung Electronics Co., Ltd
+ * Copyright (c) 2011-2014 Samsung Electronics Co., Ltd
  *              http://www.samsung.com
  *
  *  This program is free software; you can redistribute  it and/or modify it
@@ -19,6 +19,7 @@
 #include <linux/mfd/samsung/core.h>
 #include <linux/mfd/samsung/irq.h>
 #include <linux/mfd/samsung/s2mps11.h>
+#include <linux/mfd/samsung/s2mps14.h>
 #include <linux/mfd/samsung/s5m8763.h>
 #include <linux/mfd/samsung/s5m8767.h>
 
@@ -89,6 +90,76 @@ static const struct regmap_irq s2mps11_irqs[] = {
 	},
 };
 
+static const struct regmap_irq s2mps14_irqs[] = {
+	[S2MPS14_IRQ_PWRONF] = {
+		.reg_offset = 0,
+		.mask = S2MPS11_IRQ_PWRONF_MASK,
+	},
+	[S2MPS14_IRQ_PWRONR] = {
+		.reg_offset = 0,
+		.mask = S2MPS11_IRQ_PWRONR_MASK,
+	},
+	[S2MPS14_IRQ_JIGONBF] = {
+		.reg_offset = 0,
+		.mask = S2MPS11_IRQ_JIGONBF_MASK,
+	},
+	[S2MPS14_IRQ_JIGONBR] = {
+		.reg_offset = 0,
+		.mask = S2MPS11_IRQ_JIGONBR_MASK,
+	},
+	[S2MPS14_IRQ_ACOKBF] = {
+		.reg_offset = 0,
+		.mask = S2MPS11_IRQ_ACOKBF_MASK,
+	},
+	[S2MPS14_IRQ_ACOKBR] = {
+		.reg_offset = 0,
+		.mask = S2MPS11_IRQ_ACOKBR_MASK,
+	},
+	[S2MPS14_IRQ_PWRON1S] = {
+		.reg_offset = 0,
+		.mask = S2MPS11_IRQ_PWRON1S_MASK,
+	},
+	[S2MPS14_IRQ_MRB] = {
+		.reg_offset = 0,
+		.mask = S2MPS11_IRQ_MRB_MASK,
+	},
+	[S2MPS14_IRQ_RTC60S] = {
+		.reg_offset = 1,
+		.mask = S2MPS11_IRQ_RTC60S_MASK,
+	},
+	[S2MPS14_IRQ_RTCA1] = {
+		.reg_offset = 1,
+		.mask = S2MPS11_IRQ_RTCA1_MASK,
+	},
+	[S2MPS14_IRQ_RTCA0] = {
+		.reg_offset = 1,
+		.mask = S2MPS11_IRQ_RTCA0_MASK,
+	},
+	[S2MPS14_IRQ_SMPL] = {
+		.reg_offset = 1,
+		.mask = S2MPS11_IRQ_SMPL_MASK,
+	},
+	[S2MPS14_IRQ_RTC1S] = {
+		.reg_offset = 1,
+		.mask = S2MPS11_IRQ_RTC1S_MASK,
+	},
+	[S2MPS14_IRQ_WTSR] = {
+		.reg_offset = 1,
+		.mask = S2MPS11_IRQ_WTSR_MASK,
+	},
+	[S2MPS14_IRQ_INT120C] = {
+		.reg_offset = 2,
+		.mask = S2MPS11_IRQ_INT120C_MASK,
+	},
+	[S2MPS14_IRQ_INT140C] = {
+		.reg_offset = 2,
+		.mask = S2MPS11_IRQ_INT140C_MASK,
+	},
+	[S2MPS14_IRQ_TSD] = {
+		.reg_offset = 2,
+		.mask = S2MPS14_IRQ_TSD_MASK,
+	},
+};
 
 static const struct regmap_irq s5m8767_irqs[] = {
 	[S5M8767_IRQ_PWRR] = {
@@ -246,6 +317,16 @@ static const struct regmap_irq_chip s2mps11_irq_chip = {
 	.ack_base = S2MPS11_REG_INT1,
 };
 
+static const struct regmap_irq_chip s2mps14_irq_chip = {
+	.name = "s2mps14",
+	.irqs = s2mps14_irqs,
+	.num_irqs = ARRAY_SIZE(s2mps14_irqs),
+	.num_regs = 3,
+	.status_base = S2MPS14_REG_INT1,
+	.mask_base = S2MPS14_REG_INT1M,
+	.ack_base = S2MPS14_REG_INT1,
+};
+
 static const struct regmap_irq_chip s5m8767_irq_chip = {
 	.name = "s5m8767",
 	.irqs = s5m8767_irqs,
@@ -297,6 +378,12 @@ int sec_irq_init(struct sec_pmic_dev *sec_pmic)
 				  sec_pmic->irq_base, &s2mps11_irq_chip,
 				  &sec_pmic->irq_data);
 		break;
+	case S2MPS14X:
+		ret = regmap_add_irq_chip(sec_pmic->regmap_pmic, sec_pmic->irq,
+				  IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
+				  sec_pmic->irq_base, &s2mps14_irq_chip,
+				  &sec_pmic->irq_data);
+		break;
 	default:
 		dev_err(sec_pmic->dev, "Unknown device type %d\n",
 			sec_pmic->device_type);
diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h
index 41c9bde410c5..8e9bbb1083d4 100644
--- a/include/linux/mfd/samsung/core.h
+++ b/include/linux/mfd/samsung/core.h
@@ -19,6 +19,7 @@ enum sec_device_type {
 	S5M8763X,
 	S5M8767X,
 	S2MPS11X,
+	S2MPS14X,
 };
 
 /**
diff --git a/include/linux/mfd/samsung/irq.h b/include/linux/mfd/samsung/irq.h
index abe1a6aae3b7..0065f6f1daf4 100644
--- a/include/linux/mfd/samsung/irq.h
+++ b/include/linux/mfd/samsung/irq.h
@@ -55,6 +55,33 @@ enum s2mps11_irq {
 #define S2MPS11_IRQ_INT120C_MASK	(1 << 0)
 #define S2MPS11_IRQ_INT140C_MASK	(1 << 1)
 
+enum s2mps14_irq {
+	S2MPS14_IRQ_PWRONF,
+	S2MPS14_IRQ_PWRONR,
+	S2MPS14_IRQ_JIGONBF,
+	S2MPS14_IRQ_JIGONBR,
+	S2MPS14_IRQ_ACOKBF,
+	S2MPS14_IRQ_ACOKBR,
+	S2MPS14_IRQ_PWRON1S,
+	S2MPS14_IRQ_MRB,
+
+	S2MPS14_IRQ_RTC60S,
+	S2MPS14_IRQ_RTCA1,
+	S2MPS14_IRQ_RTCA0,
+	S2MPS14_IRQ_SMPL,
+	S2MPS14_IRQ_RTC1S,
+	S2MPS14_IRQ_WTSR,
+
+	S2MPS14_IRQ_INT120C,
+	S2MPS14_IRQ_INT140C,
+	S2MPS14_IRQ_TSD,
+
+	S2MPS14_IRQ_NR,
+};
+
+/* Masks for interrupts are the same as in s2mps11 */
+#define S2MPS14_IRQ_TSD_MASK		(1 << 2)
+
 enum s5m8767_irq {
 	S5M8767_IRQ_PWRR,
 	S5M8767_IRQ_PWRF,
diff --git a/include/linux/mfd/samsung/rtc.h b/include/linux/mfd/samsung/rtc.h
index 4627f59ebd84..3e02b768d537 100644
--- a/include/linux/mfd/samsung/rtc.h
+++ b/include/linux/mfd/samsung/rtc.h
@@ -1,12 +1,17 @@
-/*  rtc.h
+/* rtc.h
  *
- * Copyright (c) 2011 Samsung Electronics Co., Ltd
+ * Copyright (c) 2011-2014 Samsung Electronics Co., Ltd
  *              http://www.samsung.com
  *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
  *
  */
 
@@ -47,6 +52,37 @@ enum sec_rtc_reg {
 	SEC_RTC_REG_MAX,
 };
 
+enum s2mps_rtc_reg {
+	S2MPS_RTC_CTRL,
+	S2MPS_WTSR_SMPL_CNTL,
+	S2MPS_RTC_UDR_CON,
+	S2MPS_RSVD,
+	S2MPS_RTC_SEC,
+	S2MPS_RTC_MIN,
+	S2MPS_RTC_HOUR,
+	S2MPS_RTC_WEEKDAY,
+	S2MPS_RTC_DATE,
+	S2MPS_RTC_MONTH,
+	S2MPS_RTC_YEAR,
+	S2MPS_ALARM0_SEC,
+	S2MPS_ALARM0_MIN,
+	S2MPS_ALARM0_HOUR,
+	S2MPS_ALARM0_WEEKDAY,
+	S2MPS_ALARM0_DATE,
+	S2MPS_ALARM0_MONTH,
+	S2MPS_ALARM0_YEAR,
+	S2MPS_ALARM1_SEC,
+	S2MPS_ALARM1_MIN,
+	S2MPS_ALARM1_HOUR,
+	S2MPS_ALARM1_WEEKDAY,
+	S2MPS_ALARM1_DATE,
+	S2MPS_ALARM1_MONTH,
+	S2MPS_ALARM1_YEAR,
+	S2MPS_OFFSRC,
+
+	S2MPS_RTC_REG_MAX,
+};
+
 #define RTC_I2C_ADDR		(0x0C >> 1)
 
 #define HOUR_12			(1 << 7)
@@ -56,6 +92,9 @@ enum sec_rtc_reg {
 #define ALARM1_STATUS		(1 << 2)
 #define UPDATE_AD		(1 << 0)
 
+#define S2MPS_ALARM0_STATUS	(1 << 2)
+#define S2MPS_ALARM1_STATUS	(1 << 1)
+
 /* RTC Control Register */
 #define BCD_EN_SHIFT		0
 #define BCD_EN_MASK		(1 << BCD_EN_SHIFT)
@@ -64,6 +103,10 @@ enum sec_rtc_reg {
 /* RTC Update Register1 */
 #define RTC_UDR_SHIFT		0
 #define RTC_UDR_MASK		(1 << RTC_UDR_SHIFT)
+#define S2MPS_RTC_WUDR_SHIFT	4
+#define S2MPS_RTC_WUDR_MASK	(1 << S2MPS_RTC_WUDR_SHIFT)
+#define S2MPS_RTC_RUDR_SHIFT	0
+#define S2MPS_RTC_RUDR_MASK	(1 << S2MPS_RTC_RUDR_SHIFT)
 #define RTC_TCON_SHIFT		1
 #define RTC_TCON_MASK		(1 << RTC_TCON_SHIFT)
 #define RTC_TIME_EN_SHIFT	3
diff --git a/include/linux/mfd/samsung/s2mps14.h b/include/linux/mfd/samsung/s2mps14.h
new file mode 100644
index 000000000000..ec1e0857ddde
--- /dev/null
+++ b/include/linux/mfd/samsung/s2mps14.h
@@ -0,0 +1,152 @@
+/*
+ * s2mps14.h
+ *
+ * Copyright (c) 2014 Samsung Electronics Co., Ltd
+ *              http://www.samsung.com
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __LINUX_MFD_S2MPS14_H
+#define __LINUX_MFD_S2MPS14_H
+
+/* S2MPS14 registers */
+enum s2mps14_reg {
+	S2MPS14_REG_ID,
+	S2MPS14_REG_INT1,
+	S2MPS14_REG_INT2,
+	S2MPS14_REG_INT3,
+	S2MPS14_REG_INT1M,
+	S2MPS14_REG_INT2M,
+	S2MPS14_REG_INT3M,
+	S2MPS14_REG_ST1,
+	S2MPS14_REG_ST2,
+	S2MPS14_REG_PWRONSRC,
+	S2MPS14_REG_OFFSRC,
+	S2MPS14_REG_BU_CHG,
+	S2MPS14_REG_RTCCTRL,
+	S2MPS14_REG_CTRL1,
+	S2MPS14_REG_CTRL2,
+	S2MPS14_REG_RSVD1,
+	S2MPS14_REG_RSVD2,
+	S2MPS14_REG_RSVD3,
+	S2MPS14_REG_RSVD4,
+	S2MPS14_REG_RSVD5,
+	S2MPS14_REG_RSVD6,
+	S2MPS14_REG_CTRL3,
+	S2MPS14_REG_RSVD7,
+	S2MPS14_REG_RSVD8,
+	S2MPS14_REG_WRSTBI,
+	S2MPS14_REG_B1CTRL1,
+	S2MPS14_REG_B1CTRL2,
+	S2MPS14_REG_B2CTRL1,
+	S2MPS14_REG_B2CTRL2,
+	S2MPS14_REG_B3CTRL1,
+	S2MPS14_REG_B3CTRL2,
+	S2MPS14_REG_B4CTRL1,
+	S2MPS14_REG_B4CTRL2,
+	S2MPS14_REG_B5CTRL1,
+	S2MPS14_REG_B5CTRL2,
+	S2MPS14_REG_L1CTRL,
+	S2MPS14_REG_L2CTRL,
+	S2MPS14_REG_L3CTRL,
+	S2MPS14_REG_L4CTRL,
+	S2MPS14_REG_L5CTRL,
+	S2MPS14_REG_L6CTRL,
+	S2MPS14_REG_L7CTRL,
+	S2MPS14_REG_L8CTRL,
+	S2MPS14_REG_L9CTRL,
+	S2MPS14_REG_L10CTRL,
+	S2MPS14_REG_L11CTRL,
+	S2MPS14_REG_L12CTRL,
+	S2MPS14_REG_L13CTRL,
+	S2MPS14_REG_L14CTRL,
+	S2MPS14_REG_L15CTRL,
+	S2MPS14_REG_L16CTRL,
+	S2MPS14_REG_L17CTRL,
+	S2MPS14_REG_L18CTRL,
+	S2MPS14_REG_L19CTRL,
+	S2MPS14_REG_L20CTRL,
+	S2MPS14_REG_L21CTRL,
+	S2MPS14_REG_L22CTRL,
+	S2MPS14_REG_L23CTRL,
+	S2MPS14_REG_L24CTRL,
+	S2MPS14_REG_L25CTRL,
+	S2MPS14_REG_LDODSCH1,
+	S2MPS14_REG_LDODSCH2,
+	S2MPS14_REG_LDODSCH3,
+};
+
+/* S2MPS14 regulator ids */
+enum s2mps14_regulators {
+	S2MPS14_LDO1,
+	S2MPS14_LDO2,
+	S2MPS14_LDO3,
+	S2MPS14_LDO4,
+	S2MPS14_LDO5,
+	S2MPS14_LDO6,
+	S2MPS14_LDO7,
+	S2MPS14_LDO8,
+	S2MPS14_LDO9,
+	S2MPS14_LDO10,
+	S2MPS14_LDO11,
+	S2MPS14_LDO12,
+	S2MPS14_LDO13,
+	S2MPS14_LDO14,
+	S2MPS14_LDO15,
+	S2MPS14_LDO16,
+	S2MPS14_LDO17,
+	S2MPS14_LDO18,
+	S2MPS14_LDO19,
+	S2MPS14_LDO20,
+	S2MPS14_LDO21,
+	S2MPS14_LDO22,
+	S2MPS14_LDO23,
+	S2MPS14_LDO24,
+	S2MPS14_LDO25,
+	S2MPS14_BUCK1,
+	S2MPS14_BUCK2,
+	S2MPS14_BUCK3,
+	S2MPS14_BUCK4,
+	S2MPS14_BUCK5,
+
+	S2MPS14_REGULATOR_MAX,
+};
+
+/* Regulator constraints for BUCKx */
+#define S2MPS14_BUCK1235_MIN_600MV	600000
+#define S2MPS14_BUCK4_MIN_1400MV	1400000
+#define S2MPS14_BUCK1235_STEP_6_25MV	6250
+#define S2MPS14_BUCK4_STEP_12_5MV	12500
+#define S2MPS14_BUCK1235_START_SEL	0x20
+#define S2MPS14_BUCK4_START_SEL		0x40
+/*
+ * Default ramp delay in uv/us. Datasheet says that ramp delay can be
+ * controlled however it does not specify which register is used for that.
+ * Let's assume that default value will be set.
+ */
+#define S2MPS14_BUCK_RAMP_DELAY		12500
+
+/* Regulator constraints for different types of LDOx */
+#define S2MPS14_LDO_MIN_800MV		800000
+#define S2MPS14_LDO_MIN_1800MV		1800000
+#define S2MPS14_LDO_STEP_12_5MV		12500
+#define S2MPS14_LDO_STEP_25MV		25000
+
+#define S2MPS14_LDO_VSEL_MASK		0x3F
+#define S2MPS14_BUCK_VSEL_MASK		0xFF
+#define S2MPS14_ENABLE_MASK		(0x03 << S2MPS14_ENABLE_SHIFT)
+#define S2MPS14_ENABLE_SHIFT		6
+#define S2MPS14_LDO_N_VOLTAGES		(S2MPS14_LDO_VSEL_MASK + 1)
+#define S2MPS14_BUCK_N_VOLTAGES		(S2MPS14_BUCK_VSEL_MASK + 1)
+
+#endif /*  __LINUX_MFD_S2MPS14_H */
-- 
cgit v1.2.3


From 8f695de515b9e08e30c5b7fae48c0672c8361c51 Mon Sep 17 00:00:00 2001
From: Pankaj Dubey <pankaj.dubey@samsung.com>
Date: Thu, 13 Mar 2014 11:14:07 +0900
Subject: mfd: sec-core: Silence compiler warning

When used 64bit compiler GCC warns as
drivers/mfd/sec-core.c:199:10: warning:
cast from pointer to integer of different size [-Wpointer-to-int-cast]

Signed-off-by: Pankaj Dubey <pankaj.dubey@samsung.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/sec-core.c           | 6 +++---
 include/linux/mfd/samsung/core.h | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mfd/sec-core.c b/drivers/mfd/sec-core.c
index d163c66edebb..3fc3ebdd7b8a 100644
--- a/drivers/mfd/sec-core.c
+++ b/drivers/mfd/sec-core.c
@@ -212,17 +212,17 @@ static struct sec_platform_data *sec_pmic_i2c_parse_dt_pdata(
 }
 #endif
 
-static inline int sec_i2c_get_driver_data(struct i2c_client *i2c,
+static inline unsigned long sec_i2c_get_driver_data(struct i2c_client *i2c,
 						const struct i2c_device_id *id)
 {
 #ifdef CONFIG_OF
 	if (i2c->dev.of_node) {
 		const struct of_device_id *match;
 		match = of_match_node(sec_dt_match, i2c->dev.of_node);
-		return (int)match->data;
+		return (unsigned long)match->data;
 	}
 #endif
-	return (int)id->driver_data;
+	return id->driver_data;
 }
 
 static int sec_pmic_probe(struct i2c_client *i2c,
diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h
index 8e9bbb1083d4..5073d81660e7 100644
--- a/include/linux/mfd/samsung/core.h
+++ b/include/linux/mfd/samsung/core.h
@@ -51,7 +51,7 @@ struct sec_pmic_dev {
 	struct regmap_irq_chip_data *irq_data;
 
 	int ono;
-	int type;
+	unsigned long type;
 	bool wakeup;
 	bool wtsr_smpl;
 };
-- 
cgit v1.2.3


From ce24991e1e4d7bee05bcc0e156b0b1c2ef791dd3 Mon Sep 17 00:00:00 2001
From: Sachin Kamat <sachin.kamat@linaro.org>
Date: Fri, 14 Mar 2014 17:21:57 +0530
Subject: mfd: Add support for S2MPA01 device

Add the necessary entries required for S2MPA01 multi-function
device. While at it also convert whitespaces to tabs in core.h.

Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/sec-core.c              |  49 ++++++++-
 include/linux/mfd/samsung/core.h    |  16 ++-
 include/linux/mfd/samsung/irq.h     |  50 ++++++++++
 include/linux/mfd/samsung/s2mpa01.h | 192 ++++++++++++++++++++++++++++++++++++
 4 files changed, 297 insertions(+), 10 deletions(-)
 create mode 100644 include/linux/mfd/samsung/s2mpa01.h

(limited to 'include/linux')

diff --git a/drivers/mfd/sec-core.c b/drivers/mfd/sec-core.c
index 3fc3ebdd7b8a..281a82747275 100644
--- a/drivers/mfd/sec-core.c
+++ b/drivers/mfd/sec-core.c
@@ -26,6 +26,7 @@
 #include <linux/mfd/samsung/core.h>
 #include <linux/mfd/samsung/irq.h>
 #include <linux/mfd/samsung/rtc.h>
+#include <linux/mfd/samsung/s2mpa01.h>
 #include <linux/mfd/samsung/s2mps11.h>
 #include <linux/mfd/samsung/s2mps14.h>
 #include <linux/mfd/samsung/s5m8763.h>
@@ -80,21 +81,43 @@ static const struct mfd_cell s2mps14_devs[] = {
 	}
 };
 
+static const struct mfd_cell s2mpa01_devs[] = {
+	{
+		.name = "s2mpa01-pmic",
+	},
+};
+
 #ifdef CONFIG_OF
 static struct of_device_id sec_dt_match[] = {
 	{	.compatible = "samsung,s5m8767-pmic",
 		.data = (void *)S5M8767X,
-	},
-	{	.compatible = "samsung,s2mps11-pmic",
+	}, {
+		.compatible = "samsung,s2mps11-pmic",
 		.data = (void *)S2MPS11X,
-	},
-	{	.compatible = "samsung,s2mps14-pmic",
+	}, {
+		.compatible = "samsung,s2mps14-pmic",
 		.data = (void *)S2MPS14X,
+	}, {
+		.compatible = "samsung,s2mpa01-pmic",
+		.data = (void *)S2MPA01,
+	}, {
+		/* Sentinel */
 	},
-	{},
 };
 #endif
 
+static bool s2mpa01_volatile(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case S2MPA01_REG_INT1M:
+	case S2MPA01_REG_INT2M:
+	case S2MPA01_REG_INT3M:
+		return false;
+	default:
+		return true;
+	}
+}
+
 static bool s2mps11_volatile(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
@@ -125,6 +148,15 @@ static const struct regmap_config sec_regmap_config = {
 	.val_bits = 8,
 };
 
+static const struct regmap_config s2mpa01_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+
+	.max_register = S2MPA01_REG_LDO_OVCB4,
+	.volatile_reg = s2mpa01_volatile,
+	.cache_type = REGCACHE_FLAT,
+};
+
 static const struct regmap_config s2mps11_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
@@ -261,6 +293,9 @@ static int sec_pmic_probe(struct i2c_client *i2c,
 	}
 
 	switch (sec_pmic->device_type) {
+	case S2MPA01:
+		regmap = &s2mpa01_regmap_config;
+		break;
 	case S2MPS11X:
 		regmap = &s2mps11_regmap_config;
 		/*
@@ -332,6 +367,10 @@ static int sec_pmic_probe(struct i2c_client *i2c,
 		ret = mfd_add_devices(sec_pmic->dev, -1, s5m8767_devs,
 				      ARRAY_SIZE(s5m8767_devs), NULL, 0, NULL);
 		break;
+	case S2MPA01:
+		ret = mfd_add_devices(sec_pmic->dev, -1, s2mpa01_devs,
+				      ARRAY_SIZE(s2mpa01_devs), NULL, 0, NULL);
+		break;
 	case S2MPS11X:
 		ret = mfd_add_devices(sec_pmic->dev, -1, s2mps11_devs,
 				      ARRAY_SIZE(s2mps11_devs), NULL, 0, NULL);
diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h
index 5073d81660e7..900bc9e1888b 100644
--- a/include/linux/mfd/samsung/core.h
+++ b/include/linux/mfd/samsung/core.h
@@ -18,6 +18,7 @@ enum sec_device_type {
 	S5M8751X,
 	S5M8763X,
 	S5M8767X,
+	S2MPA01,
 	S2MPS11X,
 	S2MPS14X,
 };
@@ -93,7 +94,7 @@ struct sec_platform_data {
 	int				buck3_default_idx;
 	int				buck4_default_idx;
 
-	int                             buck_ramp_delay;
+	int				buck_ramp_delay;
 
 	int				buck2_ramp_delay;
 	int				buck34_ramp_delay;
@@ -101,10 +102,15 @@ struct sec_platform_data {
 	int				buck16_ramp_delay;
 	int				buck7810_ramp_delay;
 	int				buck9_ramp_delay;
-
-	bool                            buck2_ramp_enable;
-	bool                            buck3_ramp_enable;
-	bool                            buck4_ramp_enable;
+	int				buck24_ramp_delay;
+	int				buck3_ramp_delay;
+	int				buck7_ramp_delay;
+	int				buck8910_ramp_delay;
+
+	bool				buck1_ramp_enable;
+	bool				buck2_ramp_enable;
+	bool				buck3_ramp_enable;
+	bool				buck4_ramp_enable;
 	bool				buck6_ramp_enable;
 
 	int				buck2_init;
diff --git a/include/linux/mfd/samsung/irq.h b/include/linux/mfd/samsung/irq.h
index 0065f6f1daf4..1224f447356b 100644
--- a/include/linux/mfd/samsung/irq.h
+++ b/include/linux/mfd/samsung/irq.h
@@ -13,6 +13,56 @@
 #ifndef __LINUX_MFD_SEC_IRQ_H
 #define __LINUX_MFD_SEC_IRQ_H
 
+enum s2mpa01_irq {
+	S2MPA01_IRQ_PWRONF,
+	S2MPA01_IRQ_PWRONR,
+	S2MPA01_IRQ_JIGONBF,
+	S2MPA01_IRQ_JIGONBR,
+	S2MPA01_IRQ_ACOKBF,
+	S2MPA01_IRQ_ACOKBR,
+	S2MPA01_IRQ_PWRON1S,
+	S2MPA01_IRQ_MRB,
+
+	S2MPA01_IRQ_RTC60S,
+	S2MPA01_IRQ_RTCA1,
+	S2MPA01_IRQ_RTCA0,
+	S2MPA01_IRQ_SMPL,
+	S2MPA01_IRQ_RTC1S,
+	S2MPA01_IRQ_WTSR,
+
+	S2MPA01_IRQ_INT120C,
+	S2MPA01_IRQ_INT140C,
+	S2MPA01_IRQ_LDO3_TSD,
+	S2MPA01_IRQ_B16_TSD,
+	S2MPA01_IRQ_B24_TSD,
+	S2MPA01_IRQ_B35_TSD,
+
+	S2MPA01_IRQ_NR,
+};
+
+#define S2MPA01_IRQ_PWRONF_MASK		(1 << 0)
+#define S2MPA01_IRQ_PWRONR_MASK		(1 << 1)
+#define S2MPA01_IRQ_JIGONBF_MASK	(1 << 2)
+#define S2MPA01_IRQ_JIGONBR_MASK	(1 << 3)
+#define S2MPA01_IRQ_ACOKBF_MASK		(1 << 4)
+#define S2MPA01_IRQ_ACOKBR_MASK		(1 << 5)
+#define S2MPA01_IRQ_PWRON1S_MASK	(1 << 6)
+#define S2MPA01_IRQ_MRB_MASK		(1 << 7)
+
+#define S2MPA01_IRQ_RTC60S_MASK		(1 << 0)
+#define S2MPA01_IRQ_RTCA1_MASK		(1 << 1)
+#define S2MPA01_IRQ_RTCA0_MASK		(1 << 2)
+#define S2MPA01_IRQ_SMPL_MASK		(1 << 3)
+#define S2MPA01_IRQ_RTC1S_MASK		(1 << 4)
+#define S2MPA01_IRQ_WTSR_MASK		(1 << 5)
+
+#define S2MPA01_IRQ_INT120C_MASK	(1 << 0)
+#define S2MPA01_IRQ_INT140C_MASK	(1 << 1)
+#define S2MPA01_IRQ_LDO3_TSD_MASK	(1 << 2)
+#define S2MPA01_IRQ_B16_TSD_MASK	(1 << 3)
+#define S2MPA01_IRQ_B24_TSD_MASK	(1 << 4)
+#define S2MPA01_IRQ_B35_TSD_MASK	(1 << 5)
+
 enum s2mps11_irq {
 	S2MPS11_IRQ_PWRONF,
 	S2MPS11_IRQ_PWRONR,
diff --git a/include/linux/mfd/samsung/s2mpa01.h b/include/linux/mfd/samsung/s2mpa01.h
new file mode 100644
index 000000000000..fbc63bc0d6a2
--- /dev/null
+++ b/include/linux/mfd/samsung/s2mpa01.h
@@ -0,0 +1,192 @@
+/*
+ * Copyright (c) 2013 Samsung Electronics Co., Ltd
+ *		http://www.samsung.com
+ *
+ *  This program is free software; you can redistribute  it and/or modify it
+ *  under  the terms of  the GNU General  Public License as published by the
+ *  Free Software Foundation;  either version 2 of the  License, or (at your
+ *  option) any later version.
+ *
+ */
+
+#ifndef __LINUX_MFD_S2MPA01_H
+#define __LINUX_MFD_S2MPA01_H
+
+/* S2MPA01 registers */
+enum s2mpa01_reg {
+	S2MPA01_REG_ID,
+	S2MPA01_REG_INT1,
+	S2MPA01_REG_INT2,
+	S2MPA01_REG_INT3,
+	S2MPA01_REG_INT1M,
+	S2MPA01_REG_INT2M,
+	S2MPA01_REG_INT3M,
+	S2MPA01_REG_ST1,
+	S2MPA01_REG_ST2,
+	S2MPA01_REG_PWRONSRC,
+	S2MPA01_REG_OFFSRC,
+	S2MPA01_REG_RTC_BUF,
+	S2MPA01_REG_CTRL1,
+	S2MPA01_REG_ETC_TEST,
+	S2MPA01_REG_RSVD1,
+	S2MPA01_REG_BU_CHG,
+	S2MPA01_REG_RAMP1,
+	S2MPA01_REG_RAMP2,
+	S2MPA01_REG_LDO_DSCH1,
+	S2MPA01_REG_LDO_DSCH2,
+	S2MPA01_REG_LDO_DSCH3,
+	S2MPA01_REG_LDO_DSCH4,
+	S2MPA01_REG_OTP_ADRL,
+	S2MPA01_REG_OTP_ADRH,
+	S2MPA01_REG_OTP_DATA,
+	S2MPA01_REG_MON1SEL,
+	S2MPA01_REG_MON2SEL,
+	S2MPA01_REG_LEE,
+	S2MPA01_REG_RSVD2,
+	S2MPA01_REG_RSVD3,
+	S2MPA01_REG_RSVD4,
+	S2MPA01_REG_RSVD5,
+	S2MPA01_REG_RSVD6,
+	S2MPA01_REG_TOP_RSVD,
+	S2MPA01_REG_DVS_SEL,
+	S2MPA01_REG_DVS_PTR,
+	S2MPA01_REG_DVS_DATA,
+	S2MPA01_REG_RSVD_NO,
+	S2MPA01_REG_UVLO,
+	S2MPA01_REG_LEE_NO,
+	S2MPA01_REG_B1CTRL1,
+	S2MPA01_REG_B1CTRL2,
+	S2MPA01_REG_B2CTRL1,
+	S2MPA01_REG_B2CTRL2,
+	S2MPA01_REG_B3CTRL1,
+	S2MPA01_REG_B3CTRL2,
+	S2MPA01_REG_B4CTRL1,
+	S2MPA01_REG_B4CTRL2,
+	S2MPA01_REG_B5CTRL1,
+	S2MPA01_REG_B5CTRL2,
+	S2MPA01_REG_B5CTRL3,
+	S2MPA01_REG_B5CTRL4,
+	S2MPA01_REG_B5CTRL5,
+	S2MPA01_REG_B5CTRL6,
+	S2MPA01_REG_B6CTRL1,
+	S2MPA01_REG_B6CTRL2,
+	S2MPA01_REG_B7CTRL1,
+	S2MPA01_REG_B7CTRL2,
+	S2MPA01_REG_B8CTRL1,
+	S2MPA01_REG_B8CTRL2,
+	S2MPA01_REG_B9CTRL1,
+	S2MPA01_REG_B9CTRL2,
+	S2MPA01_REG_B10CTRL1,
+	S2MPA01_REG_B10CTRL2,
+	S2MPA01_REG_L1CTRL,
+	S2MPA01_REG_L2CTRL,
+	S2MPA01_REG_L3CTRL,
+	S2MPA01_REG_L4CTRL,
+	S2MPA01_REG_L5CTRL,
+	S2MPA01_REG_L6CTRL,
+	S2MPA01_REG_L7CTRL,
+	S2MPA01_REG_L8CTRL,
+	S2MPA01_REG_L9CTRL,
+	S2MPA01_REG_L10CTRL,
+	S2MPA01_REG_L11CTRL,
+	S2MPA01_REG_L12CTRL,
+	S2MPA01_REG_L13CTRL,
+	S2MPA01_REG_L14CTRL,
+	S2MPA01_REG_L15CTRL,
+	S2MPA01_REG_L16CTRL,
+	S2MPA01_REG_L17CTRL,
+	S2MPA01_REG_L18CTRL,
+	S2MPA01_REG_L19CTRL,
+	S2MPA01_REG_L20CTRL,
+	S2MPA01_REG_L21CTRL,
+	S2MPA01_REG_L22CTRL,
+	S2MPA01_REG_L23CTRL,
+	S2MPA01_REG_L24CTRL,
+	S2MPA01_REG_L25CTRL,
+	S2MPA01_REG_L26CTRL,
+
+	S2MPA01_REG_LDO_OVCB1,
+	S2MPA01_REG_LDO_OVCB2,
+	S2MPA01_REG_LDO_OVCB3,
+	S2MPA01_REG_LDO_OVCB4,
+
+};
+
+/* S2MPA01 regulator ids */
+enum s2mpa01_regulators {
+	S2MPA01_LDO1,
+	S2MPA01_LDO2,
+	S2MPA01_LDO3,
+	S2MPA01_LDO4,
+	S2MPA01_LDO5,
+	S2MPA01_LDO6,
+	S2MPA01_LDO7,
+	S2MPA01_LDO8,
+	S2MPA01_LDO9,
+	S2MPA01_LDO10,
+	S2MPA01_LDO11,
+	S2MPA01_LDO12,
+	S2MPA01_LDO13,
+	S2MPA01_LDO14,
+	S2MPA01_LDO15,
+	S2MPA01_LDO16,
+	S2MPA01_LDO17,
+	S2MPA01_LDO18,
+	S2MPA01_LDO19,
+	S2MPA01_LDO20,
+	S2MPA01_LDO21,
+	S2MPA01_LDO22,
+	S2MPA01_LDO23,
+	S2MPA01_LDO24,
+	S2MPA01_LDO25,
+	S2MPA01_LDO26,
+
+	S2MPA01_BUCK1,
+	S2MPA01_BUCK2,
+	S2MPA01_BUCK3,
+	S2MPA01_BUCK4,
+	S2MPA01_BUCK5,
+	S2MPA01_BUCK6,
+	S2MPA01_BUCK7,
+	S2MPA01_BUCK8,
+	S2MPA01_BUCK9,
+	S2MPA01_BUCK10,
+
+	S2MPA01_REGULATOR_MAX,
+};
+
+#define S2MPA01_BUCK_MIN1	600000
+#define S2MPA01_BUCK_MIN2	800000
+#define S2MPA01_BUCK_MIN3	1000000
+#define S2MPA01_BUCK_MIN4	1500000
+#define S2MPA01_LDO_MIN		800000
+
+#define S2MPA01_BUCK_STEP1	6250
+#define S2MPA01_BUCK_STEP2	12500
+
+#define S2MPA01_LDO_STEP1	50000
+#define S2MPA01_LDO_STEP2	25000
+
+#define S2MPA01_LDO_VSEL_MASK	0x3F
+#define S2MPA01_BUCK_VSEL_MASK	0xFF
+#define S2MPA01_ENABLE_MASK	(0x03 << S2MPA01_ENABLE_SHIFT)
+#define S2MPA01_ENABLE_SHIFT	0x06
+#define S2MPA01_LDO_N_VOLTAGES	(S2MPA01_LDO_VSEL_MASK + 1)
+#define S2MPA01_BUCK_N_VOLTAGES (S2MPA01_BUCK_VSEL_MASK + 1)
+
+#define S2MPA01_RAMP_DELAY	12500	/* uV/us */
+
+#define S2MPA01_BUCK16_RAMP_SHIFT	4
+#define S2MPA01_BUCK24_RAMP_SHIFT	6
+#define S2MPA01_BUCK3_RAMP_SHIFT	4
+#define S2MPA01_BUCK5_RAMP_SHIFT	6
+#define S2MPA01_BUCK7_RAMP_SHIFT	2
+#define S2MPA01_BUCK8910_RAMP_SHIFT	0
+
+#define S2MPA01_BUCK1_RAMP_EN_SHIFT	3
+#define S2MPA01_BUCK2_RAMP_EN_SHIFT	2
+#define S2MPA01_BUCK3_RAMP_EN_SHIFT	1
+#define S2MPA01_BUCK4_RAMP_EN_SHIFT	0
+#define S2MPA01_PMIC_EN_SHIFT	6
+
+#endif /*__LINUX_MFD_S2MPA01_H */
-- 
cgit v1.2.3


From 3935ed6a3a533c1736e3ca65bff72afd1773be27 Mon Sep 17 00:00:00 2001
From: Stefani Seibold <stefani@seibold.net>
Date: Mon, 17 Mar 2014 23:22:02 +0100
Subject: mm: Add new func _install_special_mapping() to mmap.c

The _install_special_mapping() is the new base function for
install_special_mapping(). This function will return a pointer of the
created VMA or a error code in an ERR_PTR()

This new function will be needed by the for the vdso 32 bit support to map the
additonal vvar and hpet pages into the 32 bit address space. This will be done
with io_remap_pfn_range() and remap_pfn_range, which requieres a vm_area_struct.

Reviewed-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Stefani Seibold <stefani@seibold.net>
Link: http://lkml.kernel.org/r/1395094933-14252-3-git-send-email-stefani@seibold.net
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 include/linux/mm.h |  3 +++
 mm/mmap.c          | 20 ++++++++++++++++----
 2 files changed, 19 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index c1b7414c7bef..6c7fedf5db2b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1750,6 +1750,9 @@ extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
 extern struct file *get_mm_exe_file(struct mm_struct *mm);
 
 extern int may_expand_vm(struct mm_struct *mm, unsigned long npages);
+extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm,
+				   unsigned long addr, unsigned long len,
+				   unsigned long flags, struct page **pages);
 extern int install_special_mapping(struct mm_struct *mm,
 				   unsigned long addr, unsigned long len,
 				   unsigned long flags, struct page **pages);
diff --git a/mm/mmap.c b/mm/mmap.c
index 20ff0c33274c..81ba54ff96c7 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2918,7 +2918,7 @@ static const struct vm_operations_struct special_mapping_vmops = {
  * The array pointer and the pages it points to are assumed to stay alive
  * for as long as this mapping might exist.
  */
-int install_special_mapping(struct mm_struct *mm,
+struct vm_area_struct *_install_special_mapping(struct mm_struct *mm,
 			    unsigned long addr, unsigned long len,
 			    unsigned long vm_flags, struct page **pages)
 {
@@ -2927,7 +2927,7 @@ int install_special_mapping(struct mm_struct *mm,
 
 	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
 	if (unlikely(vma == NULL))
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	INIT_LIST_HEAD(&vma->anon_vma_chain);
 	vma->vm_mm = mm;
@@ -2948,11 +2948,23 @@ int install_special_mapping(struct mm_struct *mm,
 
 	perf_event_mmap(vma);
 
-	return 0;
+	return vma;
 
 out:
 	kmem_cache_free(vm_area_cachep, vma);
-	return ret;
+	return ERR_PTR(ret);
+}
+
+int install_special_mapping(struct mm_struct *mm,
+			    unsigned long addr, unsigned long len,
+			    unsigned long vm_flags, struct page **pages)
+{
+	struct vm_area_struct *vma = _install_special_mapping(mm,
+			    addr, len, vm_flags, pages);
+
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
+	return 0;
 }
 
 static DEFINE_MUTEX(mm_all_locks_mutex);
-- 
cgit v1.2.3


From 6fe50a28ba6e5fafb4a549dea666dd15297dd8bd Mon Sep 17 00:00:00 2001
From: "David A. Long" <dave.long@linaro.org>
Date: Mon, 3 Feb 2014 14:25:49 -0500
Subject: uprobes: allow ignoring of probe hits

Allow arches to decided to ignore a probe hit.  ARM will use this to
only call handlers if the conditions to execute a conditionally executed
instruction are satisfied.

Signed-off-by: David A. Long <dave.long@linaro.org>
Acked-by: Oleg Nesterov <oleg@redhat.com>
---
 include/linux/uprobes.h | 1 +
 kernel/events/uprobes.c | 9 +++++++++
 2 files changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index e32251e00e62..edff2b97b864 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -126,6 +126,7 @@ extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk);
 extern int  arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data);
 extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs);
 extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs);
+extern bool __weak arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs);
 #else /* !CONFIG_UPROBES */
 struct uprobes_state {
 };
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 307d87c0991a..04709b66369d 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1804,6 +1804,11 @@ static bool handle_trampoline(struct pt_regs *regs)
 	return true;
 }
 
+bool __weak arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs)
+{
+	return false;
+}
+
 /*
  * Run handler and ask thread to singlestep.
  * Ensure all non-fatal signals cannot interrupt thread while it singlesteps.
@@ -1858,7 +1863,11 @@ static void handle_swbp(struct pt_regs *regs)
 	if (!get_utask())
 		goto out;
 
+	if (arch_uprobe_ignore(&uprobe->arch, regs))
+		goto out;
+
 	handler_chain(uprobe, regs);
+
 	if (can_skip_sstep(uprobe, regs))
 		goto out;
 
-- 
cgit v1.2.3


From 3e037e5211252902a188a6a11aecd247409d0229 Mon Sep 17 00:00:00 2001
From: T Makphaibulchoke <tmac@hp.com>
Date: Tue, 18 Mar 2014 19:19:41 -0400
Subject: fs/mbcache.c: change block and index hash chain to hlist_bl_node

This patch changes each mb_cache's both block and index hash chains to
use a hlist_bl_node, which contains a built-in lock.  This is the
first step in decoupling of locks serializing accesses to mb_cache
global data and each mb_cache_entry local data.

Signed-off-by: T. Makphaibulchoke <tmac@hp.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/mbcache.c            | 117 ++++++++++++++++++++++++++++++++----------------
 include/linux/mbcache.h |  12 ++---
 2 files changed, 85 insertions(+), 44 deletions(-)

(limited to 'include/linux')

diff --git a/fs/mbcache.c b/fs/mbcache.c
index e519e45bf673..55db0daaca74 100644
--- a/fs/mbcache.c
+++ b/fs/mbcache.c
@@ -34,9 +34,9 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
-#include <linux/init.h>
+#include <linux/list_bl.h>
 #include <linux/mbcache.h>
-
+#include <linux/init.h>
 
 #ifdef MB_CACHE_DEBUG
 # define mb_debug(f...) do { \
@@ -87,21 +87,38 @@ static LIST_HEAD(mb_cache_lru_list);
 static DEFINE_SPINLOCK(mb_cache_spinlock);
 
 static inline int
-__mb_cache_entry_is_hashed(struct mb_cache_entry *ce)
+__mb_cache_entry_is_block_hashed(struct mb_cache_entry *ce)
 {
-	return !list_empty(&ce->e_block_list);
+	return !hlist_bl_unhashed(&ce->e_block_list);
 }
 
 
-static void
-__mb_cache_entry_unhash(struct mb_cache_entry *ce)
+static inline void
+__mb_cache_entry_unhash_block(struct mb_cache_entry *ce)
 {
-	if (__mb_cache_entry_is_hashed(ce)) {
-		list_del_init(&ce->e_block_list);
-		list_del(&ce->e_index.o_list);
-	}
+	if (__mb_cache_entry_is_block_hashed(ce))
+		hlist_bl_del_init(&ce->e_block_list);
+}
+
+static inline int
+__mb_cache_entry_is_index_hashed(struct mb_cache_entry *ce)
+{
+	return !hlist_bl_unhashed(&ce->e_index.o_list);
 }
 
+static inline void
+__mb_cache_entry_unhash_index(struct mb_cache_entry *ce)
+{
+	if (__mb_cache_entry_is_index_hashed(ce))
+		hlist_bl_del_init(&ce->e_index.o_list);
+}
+
+static inline void
+__mb_cache_entry_unhash(struct mb_cache_entry *ce)
+{
+	__mb_cache_entry_unhash_index(ce);
+	__mb_cache_entry_unhash_block(ce);
+}
 
 static void
 __mb_cache_entry_forget(struct mb_cache_entry *ce, gfp_t gfp_mask)
@@ -125,7 +142,7 @@ __mb_cache_entry_release_unlock(struct mb_cache_entry *ce)
 		ce->e_used -= MB_CACHE_WRITER;
 	ce->e_used--;
 	if (!(ce->e_used || ce->e_queued)) {
-		if (!__mb_cache_entry_is_hashed(ce))
+		if (!__mb_cache_entry_is_block_hashed(ce))
 			goto forget;
 		mb_assert(list_empty(&ce->e_lru_list));
 		list_add_tail(&ce->e_lru_list, &mb_cache_lru_list);
@@ -221,18 +238,18 @@ mb_cache_create(const char *name, int bucket_bits)
 	cache->c_name = name;
 	atomic_set(&cache->c_entry_count, 0);
 	cache->c_bucket_bits = bucket_bits;
-	cache->c_block_hash = kmalloc(bucket_count * sizeof(struct list_head),
-	                              GFP_KERNEL);
+	cache->c_block_hash = kmalloc(bucket_count *
+		sizeof(struct hlist_bl_head), GFP_KERNEL);
 	if (!cache->c_block_hash)
 		goto fail;
 	for (n=0; n<bucket_count; n++)
-		INIT_LIST_HEAD(&cache->c_block_hash[n]);
-	cache->c_index_hash = kmalloc(bucket_count * sizeof(struct list_head),
-				      GFP_KERNEL);
+		INIT_HLIST_BL_HEAD(&cache->c_block_hash[n]);
+	cache->c_index_hash = kmalloc(bucket_count *
+		sizeof(struct hlist_bl_head), GFP_KERNEL);
 	if (!cache->c_index_hash)
 		goto fail;
 	for (n=0; n<bucket_count; n++)
-		INIT_LIST_HEAD(&cache->c_index_hash[n]);
+		INIT_HLIST_BL_HEAD(&cache->c_index_hash[n]);
 	cache->c_entry_cache = kmem_cache_create(name,
 		sizeof(struct mb_cache_entry), 0,
 		SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL);
@@ -364,10 +381,13 @@ mb_cache_entry_alloc(struct mb_cache *cache, gfp_t gfp_flags)
 			return NULL;
 		atomic_inc(&cache->c_entry_count);
 		INIT_LIST_HEAD(&ce->e_lru_list);
-		INIT_LIST_HEAD(&ce->e_block_list);
+		INIT_HLIST_BL_NODE(&ce->e_block_list);
+		INIT_HLIST_BL_NODE(&ce->e_index.o_list);
 		ce->e_cache = cache;
 		ce->e_queued = 0;
 	}
+	ce->e_block_hash_p = &cache->c_block_hash[0];
+	ce->e_index_hash_p = &cache->c_index_hash[0];
 	ce->e_used = 1 + MB_CACHE_WRITER;
 	return ce;
 }
@@ -393,25 +413,32 @@ mb_cache_entry_insert(struct mb_cache_entry *ce, struct block_device *bdev,
 {
 	struct mb_cache *cache = ce->e_cache;
 	unsigned int bucket;
-	struct list_head *l;
+	struct hlist_bl_node *l;
 	int error = -EBUSY;
+	struct hlist_bl_head *block_hash_p;
+	struct hlist_bl_head *index_hash_p;
+	struct mb_cache_entry *lce;
 
+	mb_assert(ce);
 	bucket = hash_long((unsigned long)bdev + (block & 0xffffffff), 
 			   cache->c_bucket_bits);
+	block_hash_p = &cache->c_block_hash[bucket];
 	spin_lock(&mb_cache_spinlock);
-	list_for_each_prev(l, &cache->c_block_hash[bucket]) {
-		struct mb_cache_entry *ce =
-			list_entry(l, struct mb_cache_entry, e_block_list);
-		if (ce->e_bdev == bdev && ce->e_block == block)
+	hlist_bl_for_each_entry(lce, l, block_hash_p, e_block_list) {
+		if (lce->e_bdev == bdev && lce->e_block == block)
 			goto out;
 	}
+	mb_assert(!__mb_cache_entry_is_block_hashed(ce));
 	__mb_cache_entry_unhash(ce);
 	ce->e_bdev = bdev;
 	ce->e_block = block;
-	list_add(&ce->e_block_list, &cache->c_block_hash[bucket]);
+	ce->e_block_hash_p = block_hash_p;
 	ce->e_index.o_key = key;
 	bucket = hash_long(key, cache->c_bucket_bits);
-	list_add(&ce->e_index.o_list, &cache->c_index_hash[bucket]);
+	index_hash_p = &cache->c_index_hash[bucket];
+	ce->e_index_hash_p = index_hash_p;
+	hlist_bl_add_head(&ce->e_index.o_list, index_hash_p);
+	hlist_bl_add_head(&ce->e_block_list, block_hash_p);
 	error = 0;
 out:
 	spin_unlock(&mb_cache_spinlock);
@@ -463,14 +490,16 @@ mb_cache_entry_get(struct mb_cache *cache, struct block_device *bdev,
 		   sector_t block)
 {
 	unsigned int bucket;
-	struct list_head *l;
+	struct hlist_bl_node *l;
 	struct mb_cache_entry *ce;
+	struct hlist_bl_head *block_hash_p;
 
 	bucket = hash_long((unsigned long)bdev + (block & 0xffffffff),
 			   cache->c_bucket_bits);
+	block_hash_p = &cache->c_block_hash[bucket];
 	spin_lock(&mb_cache_spinlock);
-	list_for_each(l, &cache->c_block_hash[bucket]) {
-		ce = list_entry(l, struct mb_cache_entry, e_block_list);
+	hlist_bl_for_each_entry(ce, l, block_hash_p, e_block_list) {
+		mb_assert(ce->e_block_hash_p == block_hash_p);
 		if (ce->e_bdev == bdev && ce->e_block == block) {
 			DEFINE_WAIT(wait);
 
@@ -489,7 +518,7 @@ mb_cache_entry_get(struct mb_cache *cache, struct block_device *bdev,
 			finish_wait(&mb_cache_queue, &wait);
 			ce->e_used += 1 + MB_CACHE_WRITER;
 
-			if (!__mb_cache_entry_is_hashed(ce)) {
+			if (!__mb_cache_entry_is_block_hashed(ce)) {
 				__mb_cache_entry_release_unlock(ce);
 				return NULL;
 			}
@@ -506,12 +535,14 @@ cleanup:
 #if !defined(MB_CACHE_INDEXES_COUNT) || (MB_CACHE_INDEXES_COUNT > 0)
 
 static struct mb_cache_entry *
-__mb_cache_entry_find(struct list_head *l, struct list_head *head,
+__mb_cache_entry_find(struct hlist_bl_node *l, struct hlist_bl_head *head,
 		      struct block_device *bdev, unsigned int key)
 {
-	while (l != head) {
+	while (l != NULL) {
 		struct mb_cache_entry *ce =
-			list_entry(l, struct mb_cache_entry, e_index.o_list);
+			hlist_bl_entry(l, struct mb_cache_entry,
+				e_index.o_list);
+		mb_assert(ce->e_index_hash_p == head);
 		if (ce->e_bdev == bdev && ce->e_index.o_key == key) {
 			DEFINE_WAIT(wait);
 
@@ -532,7 +563,7 @@ __mb_cache_entry_find(struct list_head *l, struct list_head *head,
 			}
 			finish_wait(&mb_cache_queue, &wait);
 
-			if (!__mb_cache_entry_is_hashed(ce)) {
+			if (!__mb_cache_entry_is_block_hashed(ce)) {
 				__mb_cache_entry_release_unlock(ce);
 				spin_lock(&mb_cache_spinlock);
 				return ERR_PTR(-EAGAIN);
@@ -562,12 +593,16 @@ mb_cache_entry_find_first(struct mb_cache *cache, struct block_device *bdev,
 			  unsigned int key)
 {
 	unsigned int bucket = hash_long(key, cache->c_bucket_bits);
-	struct list_head *l;
-	struct mb_cache_entry *ce;
+	struct hlist_bl_node *l;
+	struct mb_cache_entry *ce = NULL;
+	struct hlist_bl_head *index_hash_p;
 
+	index_hash_p = &cache->c_index_hash[bucket];
 	spin_lock(&mb_cache_spinlock);
-	l = cache->c_index_hash[bucket].next;
-	ce = __mb_cache_entry_find(l, &cache->c_index_hash[bucket], bdev, key);
+	if (!hlist_bl_empty(index_hash_p)) {
+		l = hlist_bl_first(index_hash_p);
+		ce = __mb_cache_entry_find(l, index_hash_p, bdev, key);
+	}
 	spin_unlock(&mb_cache_spinlock);
 	return ce;
 }
@@ -597,12 +632,16 @@ mb_cache_entry_find_next(struct mb_cache_entry *prev,
 {
 	struct mb_cache *cache = prev->e_cache;
 	unsigned int bucket = hash_long(key, cache->c_bucket_bits);
-	struct list_head *l;
+	struct hlist_bl_node *l;
 	struct mb_cache_entry *ce;
+	struct hlist_bl_head *index_hash_p;
 
+	index_hash_p = &cache->c_index_hash[bucket];
+	mb_assert(prev->e_index_hash_p == index_hash_p);
 	spin_lock(&mb_cache_spinlock);
+	mb_assert(!hlist_bl_empty(index_hash_p));
 	l = prev->e_index.o_list.next;
-	ce = __mb_cache_entry_find(l, &cache->c_index_hash[bucket], bdev, key);
+	ce = __mb_cache_entry_find(l, index_hash_p, bdev, key);
 	__mb_cache_entry_release_unlock(prev);
 	return ce;
 }
diff --git a/include/linux/mbcache.h b/include/linux/mbcache.h
index 5525d370701d..6a392e7a723a 100644
--- a/include/linux/mbcache.h
+++ b/include/linux/mbcache.h
@@ -3,19 +3,21 @@
 
   (C) 2001 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
 */
-
 struct mb_cache_entry {
 	struct list_head		e_lru_list;
 	struct mb_cache			*e_cache;
 	unsigned short			e_used;
 	unsigned short			e_queued;
+	atomic_t			e_refcnt;
 	struct block_device		*e_bdev;
 	sector_t			e_block;
-	struct list_head		e_block_list;
+	struct hlist_bl_node		e_block_list;
 	struct {
-		struct list_head	o_list;
+		struct hlist_bl_node	o_list;
 		unsigned int		o_key;
 	} e_index;
+	struct hlist_bl_head		*e_block_hash_p;
+	struct hlist_bl_head		*e_index_hash_p;
 };
 
 struct mb_cache {
@@ -25,8 +27,8 @@ struct mb_cache {
 	int				c_max_entries;
 	int				c_bucket_bits;
 	struct kmem_cache		*c_entry_cache;
-	struct list_head		*c_block_hash;
-	struct list_head		*c_index_hash;
+	struct hlist_bl_head		*c_block_hash;
+	struct hlist_bl_head		*c_index_hash;
 };
 
 /* Functions on caches */
-- 
cgit v1.2.3


From 1ad94ffef22c0a6e2ee6ba90a800c32fd29ffa1f Mon Sep 17 00:00:00 2001
From: Chanwoo Choi <cw00.choi@samsung.com>
Date: Tue, 18 Mar 2014 19:55:46 +0900
Subject: extcon: Move OF helper function to extcon core and change function
 name

This patch move simply OF helper function to extcon core and change function
name as following:
- of_extcon_get_extcon_dev() -> extcon_get_edev_by_phandle()

Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
Acked-by: Felipe Balbi <balbi@ti.com>
---
 drivers/extcon/Kconfig           |  4 ---
 drivers/extcon/Makefile          |  2 --
 drivers/extcon/extcon-class.c    | 42 ++++++++++++++++++++++++++++++
 drivers/extcon/of_extcon.c       | 56 ----------------------------------------
 drivers/usb/dwc3/dwc3-omap.c     |  3 +--
 include/linux/extcon.h           | 12 +++++++++
 include/linux/extcon/of_extcon.h | 31 ----------------------
 7 files changed, 55 insertions(+), 95 deletions(-)
 delete mode 100644 drivers/extcon/of_extcon.c
 delete mode 100644 include/linux/extcon/of_extcon.h

(limited to 'include/linux')

diff --git a/drivers/extcon/Kconfig b/drivers/extcon/Kconfig
index bdb5a00f1dfa..be56e8ac95e6 100644
--- a/drivers/extcon/Kconfig
+++ b/drivers/extcon/Kconfig
@@ -14,10 +14,6 @@ if EXTCON
 
 comment "Extcon Device Drivers"
 
-config OF_EXTCON
-	def_tristate y
-	depends on OF
-
 config EXTCON_GPIO
 	tristate "GPIO extcon support"
 	depends on GPIOLIB
diff --git a/drivers/extcon/Makefile b/drivers/extcon/Makefile
index 43eccc0e3448..bf7861ec0906 100644
--- a/drivers/extcon/Makefile
+++ b/drivers/extcon/Makefile
@@ -2,8 +2,6 @@
 # Makefile for external connector class (extcon) devices
 #
 
-obj-$(CONFIG_OF_EXTCON)		+= of_extcon.o
-
 obj-$(CONFIG_EXTCON)		+= extcon-class.o
 obj-$(CONFIG_EXTCON_GPIO)	+= extcon-gpio.o
 obj-$(CONFIG_EXTCON_ADC_JACK)	+= extcon-adc-jack.o
diff --git a/drivers/extcon/extcon-class.c b/drivers/extcon/extcon-class.c
index 76322330cbd7..7ab21aa6eaa1 100644
--- a/drivers/extcon/extcon-class.c
+++ b/drivers/extcon/extcon-class.c
@@ -31,6 +31,7 @@
 #include <linux/extcon.h>
 #include <linux/slab.h>
 #include <linux/sysfs.h>
+#include <linux/of.h>
 
 /*
  * extcon_cable_name suggests the standard cable names for commonly used
@@ -818,6 +819,47 @@ void extcon_dev_unregister(struct extcon_dev *edev)
 }
 EXPORT_SYMBOL_GPL(extcon_dev_unregister);
 
+#ifdef CONFIG_OF
+/*
+ * extcon_get_edev_by_phandle - Get the extcon device from devicetree
+ * @dev - instance to the given device
+ * @index - index into list of extcon_dev
+ *
+ * return the instance of extcon device
+ */
+struct extcon_dev *extcon_get_edev_by_phandle(struct device *dev, int index)
+{
+	struct device_node *node;
+	struct extcon_dev *edev;
+
+	if (!dev->of_node) {
+		dev_err(dev, "device does not have a device node entry\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	node = of_parse_phandle(dev->of_node, "extcon", index);
+	if (!node) {
+		dev_err(dev, "failed to get phandle in %s node\n",
+			dev->of_node->full_name);
+		return ERR_PTR(-ENODEV);
+	}
+
+	edev = extcon_get_extcon_dev(node->name);
+	if (!edev) {
+		dev_err(dev, "unable to get extcon device : %s\n", node->name);
+		return ERR_PTR(-ENODEV);
+	}
+
+	return edev;
+}
+#else
+struct extcon_dev *extcon_get_edev_by_phandle(struct device *dev, int index)
+{
+	return ERR_PTR(-ENOSYS);
+}
+#endif /* CONFIG_OF */
+EXPORT_SYMBOL_GPL(extcon_get_edev_by_phandle);
+
 static int __init extcon_class_init(void)
 {
 	return create_extcon_class();
diff --git a/drivers/extcon/of_extcon.c b/drivers/extcon/of_extcon.c
deleted file mode 100644
index 0a29f822cf77..000000000000
--- a/drivers/extcon/of_extcon.c
+++ /dev/null
@@ -1,56 +0,0 @@
-/*
- * OF helpers for External connector (extcon) framework
- *
- * Copyright (C) 2013 Texas Instruments, Inc.
- * Kishon Vijay Abraham I <kishon@ti.com>
- *
- * Copyright (C) 2013 Samsung Electronics
- * Chanwoo Choi <cw00.choi@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/err.h>
-#include <linux/extcon.h>
-#include <linux/of.h>
-#include <linux/of_platform.h>
-#include <linux/extcon/of_extcon.h>
-
-/*
- * of_extcon_get_extcon_dev - Get the name of extcon device from devicetree
- * @dev - instance to the given device
- * @index - index into list of extcon_dev
- *
- * return the instance of extcon device
- */
-struct extcon_dev *of_extcon_get_extcon_dev(struct device *dev, int index)
-{
-	struct device_node *node;
-	struct extcon_dev *edev;
-
-	if (!dev->of_node) {
-		dev_dbg(dev, "device does not have a device node entry\n");
-		return ERR_PTR(-EINVAL);
-	}
-
-	node = of_parse_phandle(dev->of_node, "extcon", index);
-	if (!node) {
-		dev_dbg(dev, "failed to get phandle in %s node\n",
-			dev->of_node->full_name);
-		return ERR_PTR(-ENODEV);
-	}
-
-	edev = extcon_get_extcon_dev(node->name);
-	if (!edev) {
-		dev_dbg(dev, "unable to get extcon device : %s\n", node->name);
-		return ERR_PTR(-ENODEV);
-	}
-
-	return edev;
-}
-EXPORT_SYMBOL_GPL(of_extcon_get_extcon_dev);
diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c
index b269dbd47fc4..b1d7ee6e40b7 100644
--- a/drivers/usb/dwc3/dwc3-omap.c
+++ b/drivers/usb/dwc3/dwc3-omap.c
@@ -29,7 +29,6 @@
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/extcon.h>
-#include <linux/extcon/of_extcon.h>
 #include <linux/regulator/consumer.h>
 
 #include <linux/usb/otg.h>
@@ -522,7 +521,7 @@ static int dwc3_omap_probe(struct platform_device *pdev)
 	dwc3_omap_enable_irqs(omap);
 
 	if (of_property_read_bool(node, "extcon")) {
-		edev = of_extcon_get_extcon_dev(dev, 0);
+		edev = extcon_get_edev_by_phandle(dev, 0);
 		if (IS_ERR(edev)) {
 			dev_vdbg(dev, "couldn't get extcon device\n");
 			ret = -EPROBE_DEFER;
diff --git a/include/linux/extcon.h b/include/linux/extcon.h
index 21c59af1150b..f488145bb2d4 100644
--- a/include/linux/extcon.h
+++ b/include/linux/extcon.h
@@ -240,6 +240,12 @@ extern int extcon_register_notifier(struct extcon_dev *edev,
 				    struct notifier_block *nb);
 extern int extcon_unregister_notifier(struct extcon_dev *edev,
 				      struct notifier_block *nb);
+
+/*
+ * Following API get the extcon device from devicetree.
+ * This function use phandle of devicetree to get extcon device directly.
+ */
+extern struct extcon_dev *extcon_get_edev_by_phandle(struct device *dev, int index);
 #else /* CONFIG_EXTCON */
 static inline int extcon_dev_register(struct extcon_dev *edev)
 {
@@ -324,5 +330,11 @@ static inline int extcon_unregister_interest(struct extcon_specific_cable_nb
 {
 	return 0;
 }
+
+static inline struct extcon_dev *extcon_get_edev_by_phandle(struct device *dev,
+							    int index)
+{
+	return ERR_PTR(-ENODEV);
+}
 #endif /* CONFIG_EXTCON */
 #endif /* __LINUX_EXTCON_H__ */
diff --git a/include/linux/extcon/of_extcon.h b/include/linux/extcon/of_extcon.h
deleted file mode 100644
index 0ebfeff1b55d..000000000000
--- a/include/linux/extcon/of_extcon.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * OF helpers for External connector (extcon) framework
- *
- * Copyright (C) 2013 Texas Instruments, Inc.
- * Kishon Vijay Abraham I <kishon@ti.com>
- *
- * Copyright (C) 2013 Samsung Electronics
- * Chanwoo Choi <cw00.choi@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#ifndef __LINUX_OF_EXTCON_H
-#define __LINUX_OF_EXTCON_H
-
-#include <linux/err.h>
-
-#if IS_ENABLED(CONFIG_OF_EXTCON)
-extern struct extcon_dev
-	*of_extcon_get_extcon_dev(struct device *dev, int index);
-#else
-static inline struct extcon_dev
-	*of_extcon_get_extcon_dev(struct device *dev, int index)
-{
-	return ERR_PTR(-ENOSYS);
-}
-#endif /* CONFIG_OF_EXTCON */
-#endif /* __LINUX_OF_EXTCON_H */
-- 
cgit v1.2.3


From 5e98fc8feaa869aa6ca5c73830f0855133eb461e Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Date: Tue, 28 Jan 2014 13:18:26 +0100
Subject: mfd: max14577: Remove unused enum max14577_irq_source

Remove unused symbol: enum max14577_irq_source.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/max14577-private.h | 8 --------
 1 file changed, 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mfd/max14577-private.h b/include/linux/mfd/max14577-private.h
index a3d0185196d3..c9b332fb0d5d 100644
--- a/include/linux/mfd/max14577-private.h
+++ b/include/linux/mfd/max14577-private.h
@@ -248,14 +248,6 @@ enum max14577_charger_reg {
 /* MAX14577 regulator SFOUT LDO voltage, fixed, uV */
 #define MAX14577_REGULATOR_SAFEOUT_VOLTAGE		4900000
 
-enum max14577_irq_source {
-	MAX14577_IRQ_INT1 = 0,
-	MAX14577_IRQ_INT2,
-	MAX14577_IRQ_INT3,
-
-	MAX14577_IRQ_REGS_NUM,
-};
-
 enum max14577_irq {
 	/* INT1 */
 	MAX14577_IRQ_INT1_ADC,
-- 
cgit v1.2.3


From ec2b26724f81d58008626228686f47ca3337e7ed Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Date: Tue, 28 Jan 2014 13:18:27 +0100
Subject: mfd: max14577: Remove not needed header inclusion

Remove not needed max14577-private.h header inclusion in the main driver
header. Remove obvious comment.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/max14577.h | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mfd/max14577.h b/include/linux/mfd/max14577.h
index 247b021dfaaf..736d39c3ec0d 100644
--- a/include/linux/mfd/max14577.h
+++ b/include/linux/mfd/max14577.h
@@ -25,13 +25,8 @@
 #ifndef __MAX14577_H__
 #define __MAX14577_H__
 
-#include <linux/mfd/max14577-private.h>
 #include <linux/regulator/consumer.h>
 
-/*
- * MAX14577 Regulator
- */
-
 /* MAX14577 regulator IDs */
 enum max14577_regulators {
 	MAX14577_SAFEOUT = 0,
-- 
cgit v1.2.3


From 8dbb947af37159d3df202d3cdbbae5fb896c462a Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Date: Wed, 22 Jan 2014 13:04:23 +0000
Subject: mfd: wm5102: Make additional DSP registers available to the user

Expose some DSP registers which are useful for DSP users to be able to
access whilst debugging their firmware.

Signed-off-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/wm5102-tables.c           | 34 ++++++++++++++++++++++++++++++++++
 include/linux/mfd/arizona/registers.h | 17 +++++++++++++++++
 2 files changed, 51 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/mfd/wm5102-tables.c b/drivers/mfd/wm5102-tables.c
index f9b1e9666013..187ee86cbbe6 100644
--- a/drivers/mfd/wm5102-tables.c
+++ b/drivers/mfd/wm5102-tables.c
@@ -1853,6 +1853,23 @@ static bool wm5102_readable_register(struct device *dev, unsigned int reg)
 	case ARIZONA_DSP1_STATUS_1:
 	case ARIZONA_DSP1_STATUS_2:
 	case ARIZONA_DSP1_STATUS_3:
+	case ARIZONA_DSP1_WDMA_BUFFER_1:
+	case ARIZONA_DSP1_WDMA_BUFFER_2:
+	case ARIZONA_DSP1_WDMA_BUFFER_3:
+	case ARIZONA_DSP1_WDMA_BUFFER_4:
+	case ARIZONA_DSP1_WDMA_BUFFER_5:
+	case ARIZONA_DSP1_WDMA_BUFFER_6:
+	case ARIZONA_DSP1_WDMA_BUFFER_7:
+	case ARIZONA_DSP1_WDMA_BUFFER_8:
+	case ARIZONA_DSP1_RDMA_BUFFER_1:
+	case ARIZONA_DSP1_RDMA_BUFFER_2:
+	case ARIZONA_DSP1_RDMA_BUFFER_3:
+	case ARIZONA_DSP1_RDMA_BUFFER_4:
+	case ARIZONA_DSP1_RDMA_BUFFER_5:
+	case ARIZONA_DSP1_RDMA_BUFFER_6:
+	case ARIZONA_DSP1_WDMA_CONFIG_1:
+	case ARIZONA_DSP1_WDMA_CONFIG_2:
+	case ARIZONA_DSP1_RDMA_CONFIG_1:
 	case ARIZONA_DSP1_SCRATCH_0:
 	case ARIZONA_DSP1_SCRATCH_1:
 	case ARIZONA_DSP1_SCRATCH_2:
@@ -1911,6 +1928,23 @@ static bool wm5102_volatile_register(struct device *dev, unsigned int reg)
 	case ARIZONA_DSP1_STATUS_1:
 	case ARIZONA_DSP1_STATUS_2:
 	case ARIZONA_DSP1_STATUS_3:
+	case ARIZONA_DSP1_WDMA_BUFFER_1:
+	case ARIZONA_DSP1_WDMA_BUFFER_2:
+	case ARIZONA_DSP1_WDMA_BUFFER_3:
+	case ARIZONA_DSP1_WDMA_BUFFER_4:
+	case ARIZONA_DSP1_WDMA_BUFFER_5:
+	case ARIZONA_DSP1_WDMA_BUFFER_6:
+	case ARIZONA_DSP1_WDMA_BUFFER_7:
+	case ARIZONA_DSP1_WDMA_BUFFER_8:
+	case ARIZONA_DSP1_RDMA_BUFFER_1:
+	case ARIZONA_DSP1_RDMA_BUFFER_2:
+	case ARIZONA_DSP1_RDMA_BUFFER_3:
+	case ARIZONA_DSP1_RDMA_BUFFER_4:
+	case ARIZONA_DSP1_RDMA_BUFFER_5:
+	case ARIZONA_DSP1_RDMA_BUFFER_6:
+	case ARIZONA_DSP1_WDMA_CONFIG_1:
+	case ARIZONA_DSP1_WDMA_CONFIG_2:
+	case ARIZONA_DSP1_RDMA_CONFIG_1:
 	case ARIZONA_DSP1_SCRATCH_0:
 	case ARIZONA_DSP1_SCRATCH_1:
 	case ARIZONA_DSP1_SCRATCH_2:
diff --git a/include/linux/mfd/arizona/registers.h b/include/linux/mfd/arizona/registers.h
index fdf3aa376eb2..6a3b16993c1a 100644
--- a/include/linux/mfd/arizona/registers.h
+++ b/include/linux/mfd/arizona/registers.h
@@ -1034,6 +1034,23 @@
 #define ARIZONA_DSP1_STATUS_1                    0x1104
 #define ARIZONA_DSP1_STATUS_2                    0x1105
 #define ARIZONA_DSP1_STATUS_3                    0x1106
+#define ARIZONA_DSP1_WDMA_BUFFER_1               0x1110
+#define ARIZONA_DSP1_WDMA_BUFFER_2               0x1111
+#define ARIZONA_DSP1_WDMA_BUFFER_3               0x1112
+#define ARIZONA_DSP1_WDMA_BUFFER_4               0x1113
+#define ARIZONA_DSP1_WDMA_BUFFER_5               0x1114
+#define ARIZONA_DSP1_WDMA_BUFFER_6               0x1115
+#define ARIZONA_DSP1_WDMA_BUFFER_7               0x1116
+#define ARIZONA_DSP1_WDMA_BUFFER_8               0x1117
+#define ARIZONA_DSP1_RDMA_BUFFER_1               0x1120
+#define ARIZONA_DSP1_RDMA_BUFFER_2               0x1121
+#define ARIZONA_DSP1_RDMA_BUFFER_3               0x1122
+#define ARIZONA_DSP1_RDMA_BUFFER_4               0x1123
+#define ARIZONA_DSP1_RDMA_BUFFER_5               0x1124
+#define ARIZONA_DSP1_RDMA_BUFFER_6               0x1125
+#define ARIZONA_DSP1_WDMA_CONFIG_1               0x1130
+#define ARIZONA_DSP1_WDMA_CONFIG_2               0x1131
+#define ARIZONA_DSP1_RDMA_CONFIG_1               0x1134
 #define ARIZONA_DSP1_SCRATCH_0                   0x1140
 #define ARIZONA_DSP1_SCRATCH_1                   0x1141
 #define ARIZONA_DSP1_SCRATCH_2                   0x1142
-- 
cgit v1.2.3


From 47ec66a17cca571eb7038b7835dff7cbd5851b90 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Date: Wed, 22 Jan 2014 13:04:24 +0000
Subject: mfd: wm5110: Make additional DSP registers available to the user

Expose some DSP registers which are useful for DSP users to be able to
access whilst debugging their firmware.

Signed-off-by: Charles Keepax <ckeepax@opensource.wolfsonmicro.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/wm5110-tables.c           | 168 ++++++++++++++++++++++++++++++++++
 include/linux/mfd/arizona/registers.h |  67 ++++++++++++++
 2 files changed, 235 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/mfd/wm5110-tables.c b/drivers/mfd/wm5110-tables.c
index 11632f135e8c..ca9968525017 100644
--- a/drivers/mfd/wm5110-tables.c
+++ b/drivers/mfd/wm5110-tables.c
@@ -2461,6 +2461,27 @@ static bool wm5110_readable_register(struct device *dev, unsigned int reg)
 	case ARIZONA_DSP1_STATUS_1:
 	case ARIZONA_DSP1_STATUS_2:
 	case ARIZONA_DSP1_STATUS_3:
+	case ARIZONA_DSP1_STATUS_4:
+	case ARIZONA_DSP1_WDMA_BUFFER_1:
+	case ARIZONA_DSP1_WDMA_BUFFER_2:
+	case ARIZONA_DSP1_WDMA_BUFFER_3:
+	case ARIZONA_DSP1_WDMA_BUFFER_4:
+	case ARIZONA_DSP1_WDMA_BUFFER_5:
+	case ARIZONA_DSP1_WDMA_BUFFER_6:
+	case ARIZONA_DSP1_WDMA_BUFFER_7:
+	case ARIZONA_DSP1_WDMA_BUFFER_8:
+	case ARIZONA_DSP1_RDMA_BUFFER_1:
+	case ARIZONA_DSP1_RDMA_BUFFER_2:
+	case ARIZONA_DSP1_RDMA_BUFFER_3:
+	case ARIZONA_DSP1_RDMA_BUFFER_4:
+	case ARIZONA_DSP1_RDMA_BUFFER_5:
+	case ARIZONA_DSP1_RDMA_BUFFER_6:
+	case ARIZONA_DSP1_WDMA_CONFIG_1:
+	case ARIZONA_DSP1_WDMA_CONFIG_2:
+	case ARIZONA_DSP1_WDMA_OFFSET_1:
+	case ARIZONA_DSP1_RDMA_CONFIG_1:
+	case ARIZONA_DSP1_RDMA_OFFSET_1:
+	case ARIZONA_DSP1_EXTERNAL_START_SELECT_1:
 	case ARIZONA_DSP1_SCRATCH_0:
 	case ARIZONA_DSP1_SCRATCH_1:
 	case ARIZONA_DSP1_SCRATCH_2:
@@ -2470,6 +2491,27 @@ static bool wm5110_readable_register(struct device *dev, unsigned int reg)
 	case ARIZONA_DSP2_STATUS_1:
 	case ARIZONA_DSP2_STATUS_2:
 	case ARIZONA_DSP2_STATUS_3:
+	case ARIZONA_DSP2_STATUS_4:
+	case ARIZONA_DSP2_WDMA_BUFFER_1:
+	case ARIZONA_DSP2_WDMA_BUFFER_2:
+	case ARIZONA_DSP2_WDMA_BUFFER_3:
+	case ARIZONA_DSP2_WDMA_BUFFER_4:
+	case ARIZONA_DSP2_WDMA_BUFFER_5:
+	case ARIZONA_DSP2_WDMA_BUFFER_6:
+	case ARIZONA_DSP2_WDMA_BUFFER_7:
+	case ARIZONA_DSP2_WDMA_BUFFER_8:
+	case ARIZONA_DSP2_RDMA_BUFFER_1:
+	case ARIZONA_DSP2_RDMA_BUFFER_2:
+	case ARIZONA_DSP2_RDMA_BUFFER_3:
+	case ARIZONA_DSP2_RDMA_BUFFER_4:
+	case ARIZONA_DSP2_RDMA_BUFFER_5:
+	case ARIZONA_DSP2_RDMA_BUFFER_6:
+	case ARIZONA_DSP2_WDMA_CONFIG_1:
+	case ARIZONA_DSP2_WDMA_CONFIG_2:
+	case ARIZONA_DSP2_WDMA_OFFSET_1:
+	case ARIZONA_DSP2_RDMA_CONFIG_1:
+	case ARIZONA_DSP2_RDMA_OFFSET_1:
+	case ARIZONA_DSP2_EXTERNAL_START_SELECT_1:
 	case ARIZONA_DSP2_SCRATCH_0:
 	case ARIZONA_DSP2_SCRATCH_1:
 	case ARIZONA_DSP2_SCRATCH_2:
@@ -2479,6 +2521,27 @@ static bool wm5110_readable_register(struct device *dev, unsigned int reg)
 	case ARIZONA_DSP3_STATUS_1:
 	case ARIZONA_DSP3_STATUS_2:
 	case ARIZONA_DSP3_STATUS_3:
+	case ARIZONA_DSP3_STATUS_4:
+	case ARIZONA_DSP3_WDMA_BUFFER_1:
+	case ARIZONA_DSP3_WDMA_BUFFER_2:
+	case ARIZONA_DSP3_WDMA_BUFFER_3:
+	case ARIZONA_DSP3_WDMA_BUFFER_4:
+	case ARIZONA_DSP3_WDMA_BUFFER_5:
+	case ARIZONA_DSP3_WDMA_BUFFER_6:
+	case ARIZONA_DSP3_WDMA_BUFFER_7:
+	case ARIZONA_DSP3_WDMA_BUFFER_8:
+	case ARIZONA_DSP3_RDMA_BUFFER_1:
+	case ARIZONA_DSP3_RDMA_BUFFER_2:
+	case ARIZONA_DSP3_RDMA_BUFFER_3:
+	case ARIZONA_DSP3_RDMA_BUFFER_4:
+	case ARIZONA_DSP3_RDMA_BUFFER_5:
+	case ARIZONA_DSP3_RDMA_BUFFER_6:
+	case ARIZONA_DSP3_WDMA_CONFIG_1:
+	case ARIZONA_DSP3_WDMA_CONFIG_2:
+	case ARIZONA_DSP3_WDMA_OFFSET_1:
+	case ARIZONA_DSP3_RDMA_CONFIG_1:
+	case ARIZONA_DSP3_RDMA_OFFSET_1:
+	case ARIZONA_DSP3_EXTERNAL_START_SELECT_1:
 	case ARIZONA_DSP3_SCRATCH_0:
 	case ARIZONA_DSP3_SCRATCH_1:
 	case ARIZONA_DSP3_SCRATCH_2:
@@ -2488,6 +2551,27 @@ static bool wm5110_readable_register(struct device *dev, unsigned int reg)
 	case ARIZONA_DSP4_STATUS_1:
 	case ARIZONA_DSP4_STATUS_2:
 	case ARIZONA_DSP4_STATUS_3:
+	case ARIZONA_DSP4_STATUS_4:
+	case ARIZONA_DSP4_WDMA_BUFFER_1:
+	case ARIZONA_DSP4_WDMA_BUFFER_2:
+	case ARIZONA_DSP4_WDMA_BUFFER_3:
+	case ARIZONA_DSP4_WDMA_BUFFER_4:
+	case ARIZONA_DSP4_WDMA_BUFFER_5:
+	case ARIZONA_DSP4_WDMA_BUFFER_6:
+	case ARIZONA_DSP4_WDMA_BUFFER_7:
+	case ARIZONA_DSP4_WDMA_BUFFER_8:
+	case ARIZONA_DSP4_RDMA_BUFFER_1:
+	case ARIZONA_DSP4_RDMA_BUFFER_2:
+	case ARIZONA_DSP4_RDMA_BUFFER_3:
+	case ARIZONA_DSP4_RDMA_BUFFER_4:
+	case ARIZONA_DSP4_RDMA_BUFFER_5:
+	case ARIZONA_DSP4_RDMA_BUFFER_6:
+	case ARIZONA_DSP4_WDMA_CONFIG_1:
+	case ARIZONA_DSP4_WDMA_CONFIG_2:
+	case ARIZONA_DSP4_WDMA_OFFSET_1:
+	case ARIZONA_DSP4_RDMA_CONFIG_1:
+	case ARIZONA_DSP4_RDMA_OFFSET_1:
+	case ARIZONA_DSP4_EXTERNAL_START_SELECT_1:
 	case ARIZONA_DSP4_SCRATCH_0:
 	case ARIZONA_DSP4_SCRATCH_1:
 	case ARIZONA_DSP4_SCRATCH_2:
@@ -2543,6 +2627,27 @@ static bool wm5110_volatile_register(struct device *dev, unsigned int reg)
 	case ARIZONA_DSP1_STATUS_1:
 	case ARIZONA_DSP1_STATUS_2:
 	case ARIZONA_DSP1_STATUS_3:
+	case ARIZONA_DSP1_STATUS_4:
+	case ARIZONA_DSP1_WDMA_BUFFER_1:
+	case ARIZONA_DSP1_WDMA_BUFFER_2:
+	case ARIZONA_DSP1_WDMA_BUFFER_3:
+	case ARIZONA_DSP1_WDMA_BUFFER_4:
+	case ARIZONA_DSP1_WDMA_BUFFER_5:
+	case ARIZONA_DSP1_WDMA_BUFFER_6:
+	case ARIZONA_DSP1_WDMA_BUFFER_7:
+	case ARIZONA_DSP1_WDMA_BUFFER_8:
+	case ARIZONA_DSP1_RDMA_BUFFER_1:
+	case ARIZONA_DSP1_RDMA_BUFFER_2:
+	case ARIZONA_DSP1_RDMA_BUFFER_3:
+	case ARIZONA_DSP1_RDMA_BUFFER_4:
+	case ARIZONA_DSP1_RDMA_BUFFER_5:
+	case ARIZONA_DSP1_RDMA_BUFFER_6:
+	case ARIZONA_DSP1_WDMA_CONFIG_1:
+	case ARIZONA_DSP1_WDMA_CONFIG_2:
+	case ARIZONA_DSP1_WDMA_OFFSET_1:
+	case ARIZONA_DSP1_RDMA_CONFIG_1:
+	case ARIZONA_DSP1_RDMA_OFFSET_1:
+	case ARIZONA_DSP1_EXTERNAL_START_SELECT_1:
 	case ARIZONA_DSP1_SCRATCH_0:
 	case ARIZONA_DSP1_SCRATCH_1:
 	case ARIZONA_DSP1_SCRATCH_2:
@@ -2550,6 +2655,27 @@ static bool wm5110_volatile_register(struct device *dev, unsigned int reg)
 	case ARIZONA_DSP2_STATUS_1:
 	case ARIZONA_DSP2_STATUS_2:
 	case ARIZONA_DSP2_STATUS_3:
+	case ARIZONA_DSP2_STATUS_4:
+	case ARIZONA_DSP2_WDMA_BUFFER_1:
+	case ARIZONA_DSP2_WDMA_BUFFER_2:
+	case ARIZONA_DSP2_WDMA_BUFFER_3:
+	case ARIZONA_DSP2_WDMA_BUFFER_4:
+	case ARIZONA_DSP2_WDMA_BUFFER_5:
+	case ARIZONA_DSP2_WDMA_BUFFER_6:
+	case ARIZONA_DSP2_WDMA_BUFFER_7:
+	case ARIZONA_DSP2_WDMA_BUFFER_8:
+	case ARIZONA_DSP2_RDMA_BUFFER_1:
+	case ARIZONA_DSP2_RDMA_BUFFER_2:
+	case ARIZONA_DSP2_RDMA_BUFFER_3:
+	case ARIZONA_DSP2_RDMA_BUFFER_4:
+	case ARIZONA_DSP2_RDMA_BUFFER_5:
+	case ARIZONA_DSP2_RDMA_BUFFER_6:
+	case ARIZONA_DSP2_WDMA_CONFIG_1:
+	case ARIZONA_DSP2_WDMA_CONFIG_2:
+	case ARIZONA_DSP2_WDMA_OFFSET_1:
+	case ARIZONA_DSP2_RDMA_CONFIG_1:
+	case ARIZONA_DSP2_RDMA_OFFSET_1:
+	case ARIZONA_DSP2_EXTERNAL_START_SELECT_1:
 	case ARIZONA_DSP2_SCRATCH_0:
 	case ARIZONA_DSP2_SCRATCH_1:
 	case ARIZONA_DSP2_SCRATCH_2:
@@ -2557,6 +2683,27 @@ static bool wm5110_volatile_register(struct device *dev, unsigned int reg)
 	case ARIZONA_DSP3_STATUS_1:
 	case ARIZONA_DSP3_STATUS_2:
 	case ARIZONA_DSP3_STATUS_3:
+	case ARIZONA_DSP3_STATUS_4:
+	case ARIZONA_DSP3_WDMA_BUFFER_1:
+	case ARIZONA_DSP3_WDMA_BUFFER_2:
+	case ARIZONA_DSP3_WDMA_BUFFER_3:
+	case ARIZONA_DSP3_WDMA_BUFFER_4:
+	case ARIZONA_DSP3_WDMA_BUFFER_5:
+	case ARIZONA_DSP3_WDMA_BUFFER_6:
+	case ARIZONA_DSP3_WDMA_BUFFER_7:
+	case ARIZONA_DSP3_WDMA_BUFFER_8:
+	case ARIZONA_DSP3_RDMA_BUFFER_1:
+	case ARIZONA_DSP3_RDMA_BUFFER_2:
+	case ARIZONA_DSP3_RDMA_BUFFER_3:
+	case ARIZONA_DSP3_RDMA_BUFFER_4:
+	case ARIZONA_DSP3_RDMA_BUFFER_5:
+	case ARIZONA_DSP3_RDMA_BUFFER_6:
+	case ARIZONA_DSP3_WDMA_CONFIG_1:
+	case ARIZONA_DSP3_WDMA_CONFIG_2:
+	case ARIZONA_DSP3_WDMA_OFFSET_1:
+	case ARIZONA_DSP3_RDMA_CONFIG_1:
+	case ARIZONA_DSP3_RDMA_OFFSET_1:
+	case ARIZONA_DSP3_EXTERNAL_START_SELECT_1:
 	case ARIZONA_DSP3_SCRATCH_0:
 	case ARIZONA_DSP3_SCRATCH_1:
 	case ARIZONA_DSP3_SCRATCH_2:
@@ -2564,6 +2711,27 @@ static bool wm5110_volatile_register(struct device *dev, unsigned int reg)
 	case ARIZONA_DSP4_STATUS_1:
 	case ARIZONA_DSP4_STATUS_2:
 	case ARIZONA_DSP4_STATUS_3:
+	case ARIZONA_DSP4_STATUS_4:
+	case ARIZONA_DSP4_WDMA_BUFFER_1:
+	case ARIZONA_DSP4_WDMA_BUFFER_2:
+	case ARIZONA_DSP4_WDMA_BUFFER_3:
+	case ARIZONA_DSP4_WDMA_BUFFER_4:
+	case ARIZONA_DSP4_WDMA_BUFFER_5:
+	case ARIZONA_DSP4_WDMA_BUFFER_6:
+	case ARIZONA_DSP4_WDMA_BUFFER_7:
+	case ARIZONA_DSP4_WDMA_BUFFER_8:
+	case ARIZONA_DSP4_RDMA_BUFFER_1:
+	case ARIZONA_DSP4_RDMA_BUFFER_2:
+	case ARIZONA_DSP4_RDMA_BUFFER_3:
+	case ARIZONA_DSP4_RDMA_BUFFER_4:
+	case ARIZONA_DSP4_RDMA_BUFFER_5:
+	case ARIZONA_DSP4_RDMA_BUFFER_6:
+	case ARIZONA_DSP4_WDMA_CONFIG_1:
+	case ARIZONA_DSP4_WDMA_CONFIG_2:
+	case ARIZONA_DSP4_WDMA_OFFSET_1:
+	case ARIZONA_DSP4_RDMA_CONFIG_1:
+	case ARIZONA_DSP4_RDMA_OFFSET_1:
+	case ARIZONA_DSP4_EXTERNAL_START_SELECT_1:
 	case ARIZONA_DSP4_SCRATCH_0:
 	case ARIZONA_DSP4_SCRATCH_1:
 	case ARIZONA_DSP4_SCRATCH_2:
diff --git a/include/linux/mfd/arizona/registers.h b/include/linux/mfd/arizona/registers.h
index 6a3b16993c1a..90d57aec34e7 100644
--- a/include/linux/mfd/arizona/registers.h
+++ b/include/linux/mfd/arizona/registers.h
@@ -1034,6 +1034,7 @@
 #define ARIZONA_DSP1_STATUS_1                    0x1104
 #define ARIZONA_DSP1_STATUS_2                    0x1105
 #define ARIZONA_DSP1_STATUS_3                    0x1106
+#define ARIZONA_DSP1_STATUS_4                    0x1107
 #define ARIZONA_DSP1_WDMA_BUFFER_1               0x1110
 #define ARIZONA_DSP1_WDMA_BUFFER_2               0x1111
 #define ARIZONA_DSP1_WDMA_BUFFER_3               0x1112
@@ -1050,7 +1051,10 @@
 #define ARIZONA_DSP1_RDMA_BUFFER_6               0x1125
 #define ARIZONA_DSP1_WDMA_CONFIG_1               0x1130
 #define ARIZONA_DSP1_WDMA_CONFIG_2               0x1131
+#define ARIZONA_DSP1_WDMA_OFFSET_1               0x1132
 #define ARIZONA_DSP1_RDMA_CONFIG_1               0x1134
+#define ARIZONA_DSP1_RDMA_OFFSET_1               0x1135
+#define ARIZONA_DSP1_EXTERNAL_START_SELECT_1     0x1138
 #define ARIZONA_DSP1_SCRATCH_0                   0x1140
 #define ARIZONA_DSP1_SCRATCH_1                   0x1141
 #define ARIZONA_DSP1_SCRATCH_2                   0x1142
@@ -1060,6 +1064,27 @@
 #define ARIZONA_DSP2_STATUS_1                    0x1204
 #define ARIZONA_DSP2_STATUS_2                    0x1205
 #define ARIZONA_DSP2_STATUS_3                    0x1206
+#define ARIZONA_DSP2_STATUS_4                    0x1207
+#define ARIZONA_DSP2_WDMA_BUFFER_1               0x1210
+#define ARIZONA_DSP2_WDMA_BUFFER_2               0x1211
+#define ARIZONA_DSP2_WDMA_BUFFER_3               0x1212
+#define ARIZONA_DSP2_WDMA_BUFFER_4               0x1213
+#define ARIZONA_DSP2_WDMA_BUFFER_5               0x1214
+#define ARIZONA_DSP2_WDMA_BUFFER_6               0x1215
+#define ARIZONA_DSP2_WDMA_BUFFER_7               0x1216
+#define ARIZONA_DSP2_WDMA_BUFFER_8               0x1217
+#define ARIZONA_DSP2_RDMA_BUFFER_1               0x1220
+#define ARIZONA_DSP2_RDMA_BUFFER_2               0x1221
+#define ARIZONA_DSP2_RDMA_BUFFER_3               0x1222
+#define ARIZONA_DSP2_RDMA_BUFFER_4               0x1223
+#define ARIZONA_DSP2_RDMA_BUFFER_5               0x1224
+#define ARIZONA_DSP2_RDMA_BUFFER_6               0x1225
+#define ARIZONA_DSP2_WDMA_CONFIG_1               0x1230
+#define ARIZONA_DSP2_WDMA_CONFIG_2               0x1231
+#define ARIZONA_DSP2_WDMA_OFFSET_1               0x1232
+#define ARIZONA_DSP2_RDMA_CONFIG_1               0x1234
+#define ARIZONA_DSP2_RDMA_OFFSET_1               0x1235
+#define ARIZONA_DSP2_EXTERNAL_START_SELECT_1     0x1238
 #define ARIZONA_DSP2_SCRATCH_0                   0x1240
 #define ARIZONA_DSP2_SCRATCH_1                   0x1241
 #define ARIZONA_DSP2_SCRATCH_2                   0x1242
@@ -1069,6 +1094,27 @@
 #define ARIZONA_DSP3_STATUS_1                    0x1304
 #define ARIZONA_DSP3_STATUS_2                    0x1305
 #define ARIZONA_DSP3_STATUS_3                    0x1306
+#define ARIZONA_DSP3_STATUS_4                    0x1307
+#define ARIZONA_DSP3_WDMA_BUFFER_1               0x1310
+#define ARIZONA_DSP3_WDMA_BUFFER_2               0x1311
+#define ARIZONA_DSP3_WDMA_BUFFER_3               0x1312
+#define ARIZONA_DSP3_WDMA_BUFFER_4               0x1313
+#define ARIZONA_DSP3_WDMA_BUFFER_5               0x1314
+#define ARIZONA_DSP3_WDMA_BUFFER_6               0x1315
+#define ARIZONA_DSP3_WDMA_BUFFER_7               0x1316
+#define ARIZONA_DSP3_WDMA_BUFFER_8               0x1317
+#define ARIZONA_DSP3_RDMA_BUFFER_1               0x1320
+#define ARIZONA_DSP3_RDMA_BUFFER_2               0x1321
+#define ARIZONA_DSP3_RDMA_BUFFER_3               0x1322
+#define ARIZONA_DSP3_RDMA_BUFFER_4               0x1323
+#define ARIZONA_DSP3_RDMA_BUFFER_5               0x1324
+#define ARIZONA_DSP3_RDMA_BUFFER_6               0x1325
+#define ARIZONA_DSP3_WDMA_CONFIG_1               0x1330
+#define ARIZONA_DSP3_WDMA_CONFIG_2               0x1331
+#define ARIZONA_DSP3_WDMA_OFFSET_1               0x1332
+#define ARIZONA_DSP3_RDMA_CONFIG_1               0x1334
+#define ARIZONA_DSP3_RDMA_OFFSET_1               0x1335
+#define ARIZONA_DSP3_EXTERNAL_START_SELECT_1     0x1338
 #define ARIZONA_DSP3_SCRATCH_0                   0x1340
 #define ARIZONA_DSP3_SCRATCH_1                   0x1341
 #define ARIZONA_DSP3_SCRATCH_2                   0x1342
@@ -1078,6 +1124,27 @@
 #define ARIZONA_DSP4_STATUS_1                    0x1404
 #define ARIZONA_DSP4_STATUS_2                    0x1405
 #define ARIZONA_DSP4_STATUS_3                    0x1406
+#define ARIZONA_DSP4_STATUS_4                    0x1407
+#define ARIZONA_DSP4_WDMA_BUFFER_1               0x1410
+#define ARIZONA_DSP4_WDMA_BUFFER_2               0x1411
+#define ARIZONA_DSP4_WDMA_BUFFER_3               0x1412
+#define ARIZONA_DSP4_WDMA_BUFFER_4               0x1413
+#define ARIZONA_DSP4_WDMA_BUFFER_5               0x1414
+#define ARIZONA_DSP4_WDMA_BUFFER_6               0x1415
+#define ARIZONA_DSP4_WDMA_BUFFER_7               0x1416
+#define ARIZONA_DSP4_WDMA_BUFFER_8               0x1417
+#define ARIZONA_DSP4_RDMA_BUFFER_1               0x1420
+#define ARIZONA_DSP4_RDMA_BUFFER_2               0x1421
+#define ARIZONA_DSP4_RDMA_BUFFER_3               0x1422
+#define ARIZONA_DSP4_RDMA_BUFFER_4               0x1423
+#define ARIZONA_DSP4_RDMA_BUFFER_5               0x1424
+#define ARIZONA_DSP4_RDMA_BUFFER_6               0x1425
+#define ARIZONA_DSP4_WDMA_CONFIG_1               0x1430
+#define ARIZONA_DSP4_WDMA_CONFIG_2               0x1431
+#define ARIZONA_DSP4_WDMA_OFFSET_1               0x1432
+#define ARIZONA_DSP4_RDMA_CONFIG_1               0x1434
+#define ARIZONA_DSP4_RDMA_OFFSET_1               0x1435
+#define ARIZONA_DSP4_EXTERNAL_START_SELECT_1     0x1438
 #define ARIZONA_DSP4_SCRATCH_0                   0x1440
 #define ARIZONA_DSP4_SCRATCH_1                   0x1441
 #define ARIZONA_DSP4_SCRATCH_2                   0x1442
-- 
cgit v1.2.3


From 44b4dc616365d7897808555d415099330e3af9df Mon Sep 17 00:00:00 2001
From: Keerthy <j-keerthy@ti.com>
Date: Thu, 6 Feb 2014 11:20:12 +0530
Subject: mfd: tps65218: Add driver for the TPS65218 PMIC

The TPS65218 chip is a power management IC for Portable Navigation Systems
and Tablet Computing devices. It contains the following components:

 - Regulators.
 - Over Temperature warning and Shut down.

This patch adds support for tps65218 mfd device. At this time only
the regulator functionality is made available.

Signed-off-by: Keerthy <j-keerthy@ti.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/Kconfig          |  15 +++
 drivers/mfd/Makefile         |   1 +
 drivers/mfd/tps65218.c       | 282 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/tps65218.h | 284 +++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 582 insertions(+)
 create mode 100644 drivers/mfd/tps65218.c
 create mode 100644 include/linux/mfd/tps65218.h

(limited to 'include/linux')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 30fbacfe8b3b..3e2d698ac432 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -853,6 +853,21 @@ config MFD_TPS65217
 	  This driver can also be built as a module.  If so, the module
 	  will be called tps65217.
 
+config MFD_TPS65218
+	tristate "TI TPS65218 Power Management chips"
+	depends on I2C
+	select MFD_CORE
+	select REGMAP_I2C
+	help
+	  If you say yes here you get support for the TPS65218 series of
+	  Power Management chips.
+	  These include voltage regulators, gpio and other features
+	  that are often used in portable devices. Only regulator
+	  component is currently supported.
+
+	  This driver can also be built as a module.  If so, the module
+	  will be called tps65218.
+
 config MFD_TPS6586X
 	bool "TI TPS6586x Power Management chips"
 	depends on I2C=y
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index c8eb0bcf4da0..5e5cfbd1b8da 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -62,6 +62,7 @@ obj-$(CONFIG_TPS6105X)		+= tps6105x.o
 obj-$(CONFIG_TPS65010)		+= tps65010.o
 obj-$(CONFIG_TPS6507X)		+= tps6507x.o
 obj-$(CONFIG_MFD_TPS65217)	+= tps65217.o
+obj-$(CONFIG_MFD_TPS65218)	+= tps65218.o
 obj-$(CONFIG_MFD_TPS65910)	+= tps65910.o
 tps65912-objs                   := tps65912-core.o tps65912-irq.o
 obj-$(CONFIG_MFD_TPS65912)	+= tps65912.o
diff --git a/drivers/mfd/tps65218.c b/drivers/mfd/tps65218.c
new file mode 100644
index 000000000000..a74bfb59f18f
--- /dev/null
+++ b/drivers/mfd/tps65218.c
@@ -0,0 +1,282 @@
+/*
+ * Driver for TPS65218 Integrated power management chipsets
+ *
+ * Copyright (C) 2014 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether expressed or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License version 2 for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/init.h>
+#include <linux/i2c.h>
+#include <linux/slab.h>
+#include <linux/regmap.h>
+#include <linux/err.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/mutex.h>
+
+#include <linux/mfd/core.h>
+#include <linux/mfd/tps65218.h>
+
+#define TPS65218_PASSWORD_REGS_UNLOCK   0x7D
+
+/**
+ * tps65218_reg_read: Read a single tps65218 register.
+ *
+ * @tps: Device to read from.
+ * @reg: Register to read.
+ * @val: Contians the value
+ */
+int tps65218_reg_read(struct tps65218 *tps, unsigned int reg,
+			unsigned int *val)
+{
+	return regmap_read(tps->regmap, reg, val);
+}
+EXPORT_SYMBOL_GPL(tps65218_reg_read);
+
+/**
+ * tps65218_reg_write: Write a single tps65218 register.
+ *
+ * @tps65218: Device to write to.
+ * @reg: Register to write to.
+ * @val: Value to write.
+ * @level: Password protected level
+ */
+int tps65218_reg_write(struct tps65218 *tps, unsigned int reg,
+			unsigned int val, unsigned int level)
+{
+	int ret;
+	unsigned int xor_reg_val;
+
+	switch (level) {
+	case TPS65218_PROTECT_NONE:
+		return regmap_write(tps->regmap, reg, val);
+	case TPS65218_PROTECT_L1:
+		xor_reg_val = reg ^ TPS65218_PASSWORD_REGS_UNLOCK;
+		ret = regmap_write(tps->regmap, TPS65218_REG_PASSWORD,
+							xor_reg_val);
+		if (ret < 0)
+			return ret;
+
+		return regmap_write(tps->regmap, reg, val);
+	default:
+		return -EINVAL;
+	}
+}
+EXPORT_SYMBOL_GPL(tps65218_reg_write);
+
+/**
+ * tps65218_update_bits: Modify bits w.r.t mask, val and level.
+ *
+ * @tps65218: Device to write to.
+ * @reg: Register to read-write to.
+ * @mask: Mask.
+ * @val: Value to write.
+ * @level: Password protected level
+ */
+static int tps65218_update_bits(struct tps65218 *tps, unsigned int reg,
+		unsigned int mask, unsigned int val, unsigned int level)
+{
+	int ret;
+	unsigned int data;
+
+	ret = tps65218_reg_read(tps, reg, &data);
+	if (ret) {
+		dev_err(tps->dev, "Read from reg 0x%x failed\n", reg);
+		return ret;
+	}
+
+	data &= ~mask;
+	data |= val & mask;
+
+	mutex_lock(&tps->tps_lock);
+	ret = tps65218_reg_write(tps, reg, data, level);
+	if (ret)
+		dev_err(tps->dev, "Write for reg 0x%x failed\n", reg);
+	mutex_unlock(&tps->tps_lock);
+
+	return ret;
+}
+
+int tps65218_set_bits(struct tps65218 *tps, unsigned int reg,
+		unsigned int mask, unsigned int val, unsigned int level)
+{
+	return tps65218_update_bits(tps, reg, mask, val, level);
+}
+EXPORT_SYMBOL_GPL(tps65218_set_bits);
+
+int tps65218_clear_bits(struct tps65218 *tps, unsigned int reg,
+		unsigned int mask, unsigned int level)
+{
+	return tps65218_update_bits(tps, reg, mask, 0, level);
+}
+EXPORT_SYMBOL_GPL(tps65218_clear_bits);
+
+static struct regmap_config tps65218_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.cache_type = REGCACHE_RBTREE,
+};
+
+static const struct regmap_irq tps65218_irqs[] = {
+	/* INT1 IRQs */
+	[TPS65218_PRGC_IRQ] = {
+		.mask = TPS65218_INT1_PRGC,
+	},
+	[TPS65218_CC_AQC_IRQ] = {
+		.mask = TPS65218_INT1_CC_AQC,
+	},
+	[TPS65218_HOT_IRQ] = {
+		.mask = TPS65218_INT1_HOT,
+	},
+	[TPS65218_PB_IRQ] = {
+		.mask = TPS65218_INT1_PB,
+	},
+	[TPS65218_AC_IRQ] = {
+		.mask = TPS65218_INT1_AC,
+	},
+	[TPS65218_VPRG_IRQ] = {
+		.mask = TPS65218_INT1_VPRG,
+	},
+	[TPS65218_INVALID1_IRQ] = {
+	},
+	[TPS65218_INVALID2_IRQ] = {
+	},
+	/* INT2 IRQs*/
+	[TPS65218_LS1_I_IRQ] = {
+		.mask = TPS65218_INT2_LS1_I,
+		.reg_offset = 1,
+	},
+	[TPS65218_LS2_I_IRQ] = {
+		.mask = TPS65218_INT2_LS2_I,
+		.reg_offset = 1,
+	},
+	[TPS65218_LS3_I_IRQ] = {
+		.mask = TPS65218_INT2_LS3_I,
+		.reg_offset = 1,
+	},
+	[TPS65218_LS1_F_IRQ] = {
+		.mask = TPS65218_INT2_LS1_F,
+		.reg_offset = 1,
+	},
+	[TPS65218_LS2_F_IRQ] = {
+		.mask = TPS65218_INT2_LS2_F,
+		.reg_offset = 1,
+	},
+	[TPS65218_LS3_F_IRQ] = {
+		.mask = TPS65218_INT2_LS3_F,
+		.reg_offset = 1,
+	},
+	[TPS65218_INVALID3_IRQ] = {
+	},
+	[TPS65218_INVALID4_IRQ] = {
+	},
+};
+
+static struct regmap_irq_chip tps65218_irq_chip = {
+	.name = "tps65218",
+	.irqs = tps65218_irqs,
+	.num_irqs = ARRAY_SIZE(tps65218_irqs),
+
+	.num_regs = 2,
+	.mask_base = TPS65218_REG_INT_MASK1,
+};
+
+static const struct of_device_id of_tps65218_match_table[] = {
+	{ .compatible = "ti,tps65218", },
+};
+
+static int tps65218_probe(struct i2c_client *client,
+				const struct i2c_device_id *ids)
+{
+	struct tps65218 *tps;
+	const struct of_device_id *match;
+	int ret;
+
+	match = of_match_device(of_tps65218_match_table, &client->dev);
+	if (!match) {
+		dev_err(&client->dev,
+			"Failed to find matching dt id\n");
+		return -EINVAL;
+	}
+
+	tps = devm_kzalloc(&client->dev, sizeof(*tps), GFP_KERNEL);
+	if (!tps)
+		return -ENOMEM;
+
+	i2c_set_clientdata(client, tps);
+	tps->dev = &client->dev;
+	tps->irq = client->irq;
+	tps->regmap = devm_regmap_init_i2c(client, &tps65218_regmap_config);
+	if (IS_ERR(tps->regmap)) {
+		ret = PTR_ERR(tps->regmap);
+		dev_err(tps->dev, "Failed to allocate register map: %d\n",
+			ret);
+		return ret;
+	}
+
+	mutex_init(&tps->tps_lock);
+
+	ret = regmap_add_irq_chip(tps->regmap, tps->irq,
+			IRQF_ONESHOT, 0, &tps65218_irq_chip,
+			&tps->irq_data);
+	if (ret < 0)
+		return ret;
+
+	ret = of_platform_populate(client->dev.of_node, NULL, NULL,
+				   &client->dev);
+	if (ret < 0)
+		goto err_irq;
+
+	return 0;
+
+err_irq:
+	regmap_del_irq_chip(tps->irq, tps->irq_data);
+
+	return ret;
+}
+
+static int tps65218_remove(struct i2c_client *client)
+{
+	struct tps65218 *tps = i2c_get_clientdata(client);
+
+	regmap_del_irq_chip(tps->irq, tps->irq_data);
+
+	return 0;
+}
+
+static const struct i2c_device_id tps65218_id_table[] = {
+	{ "tps65218", TPS65218 },
+	{ },
+};
+MODULE_DEVICE_TABLE(i2c, tps65218_id_table);
+
+static struct i2c_driver tps65218_driver = {
+	.driver		= {
+		.name	= "tps65218",
+		.owner	= THIS_MODULE,
+		.of_match_table = of_tps65218_match_table,
+	},
+	.probe		= tps65218_probe,
+	.remove		= tps65218_remove,
+	.id_table       = tps65218_id_table,
+};
+
+module_i2c_driver(tps65218_driver);
+
+MODULE_AUTHOR("J Keerthy <j-keerthy@ti.com>");
+MODULE_DESCRIPTION("TPS65218 chip family multi-function driver");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/mfd/tps65218.h b/include/linux/mfd/tps65218.h
new file mode 100644
index 000000000000..d2e357df5a0e
--- /dev/null
+++ b/include/linux/mfd/tps65218.h
@@ -0,0 +1,284 @@
+/*
+ * linux/mfd/tps65218.h
+ *
+ * Functions to access TPS65219 power management chip.
+ *
+ * Copyright (C) 2014 Texas Instruments Incorporated - http://www.ti.com/
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether expressed or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License version 2 for more details.
+ */
+
+#ifndef __LINUX_MFD_TPS65218_H
+#define __LINUX_MFD_TPS65218_H
+
+#include <linux/i2c.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+#include <linux/bitops.h>
+
+/* TPS chip id list */
+#define TPS65218			0xF0
+
+/* I2C ID for TPS65218 part */
+#define TPS65218_I2C_ID			0x24
+
+/* All register addresses */
+#define TPS65218_REG_CHIPID		0x00
+#define TPS65218_REG_INT1		0x01
+#define TPS65218_REG_INT2		0x02
+#define TPS65218_REG_INT_MASK1		0x03
+#define TPS65218_REG_INT_MASK2		0x04
+#define TPS65218_REG_STATUS		0x05
+#define TPS65218_REG_CONTROL		0x06
+#define TPS65218_REG_FLAG		0x07
+
+#define TPS65218_REG_PASSWORD		0x10
+#define TPS65218_REG_ENABLE1		0x11
+#define TPS65218_REG_ENABLE2		0x12
+#define TPS65218_REG_CONFIG1		0x13
+#define TPS65218_REG_CONFIG2		0x14
+#define TPS65218_REG_CONFIG3		0x15
+#define TPS65218_REG_CONTROL_DCDC1	0x16
+#define TPS65218_REG_CONTROL_DCDC2	0x17
+#define TPS65218_REG_CONTROL_DCDC3	0x18
+#define TPS65218_REG_CONTROL_DCDC4	0x19
+#define TPS65218_REG_CONTRL_SLEW_RATE	0x1A
+#define TPS65218_REG_CONTROL_LDO1	0x1B
+#define TPS65218_REG_SEQ1		0x20
+#define TPS65218_REG_SEQ2		0x21
+#define TPS65218_REG_SEQ3		0x22
+#define TPS65218_REG_SEQ4		0x23
+#define TPS65218_REG_SEQ5		0x24
+#define TPS65218_REG_SEQ6		0x25
+#define TPS65218_REG_SEQ7		0x26
+
+/* Register field definitions */
+#define TPS65218_CHIPID_CHIP_MASK	0xF8
+#define TPS65218_CHIPID_REV_MASK	0x07
+
+#define TPS65218_INT1_VPRG		BIT(5)
+#define TPS65218_INT1_AC		BIT(4)
+#define TPS65218_INT1_PB		BIT(3)
+#define TPS65218_INT1_HOT		BIT(2)
+#define TPS65218_INT1_CC_AQC		BIT(1)
+#define TPS65218_INT1_PRGC		BIT(0)
+
+#define TPS65218_INT2_LS3_F		BIT(5)
+#define TPS65218_INT2_LS2_F		BIT(4)
+#define TPS65218_INT2_LS1_F		BIT(3)
+#define TPS65218_INT2_LS3_I		BIT(2)
+#define TPS65218_INT2_LS2_I		BIT(1)
+#define TPS65218_INT2_LS1_I		BIT(0)
+
+#define TPS65218_INT_MASK1_VPRG		BIT(5)
+#define TPS65218_INT_MASK1_AC		BIT(4)
+#define TPS65218_INT_MASK1_PB		BIT(3)
+#define TPS65218_INT_MASK1_HOT		BIT(2)
+#define TPS65218_INT_MASK1_CC_AQC	BIT(1)
+#define TPS65218_INT_MASK1_PRGC		BIT(0)
+
+#define TPS65218_INT_MASK2_LS3_F	BIT(5)
+#define TPS65218_INT_MASK2_LS2_F	BIT(4)
+#define TPS65218_INT_MASK2_LS1_F	BIT(3)
+#define TPS65218_INT_MASK2_LS3_I	BIT(2)
+#define TPS65218_INT_MASK2_LS2_I	BIT(1)
+#define TPS65218_INT_MASK2_LS1_I	BIT(0)
+
+#define TPS65218_STATUS_FSEAL		BIT(7)
+#define TPS65218_STATUS_EE		BIT(6)
+#define TPS65218_STATUS_AC_STATE	BIT(5)
+#define TPS65218_STATUS_PB_STATE	BIT(4)
+#define TPS65218_STATUS_STATE_MASK	0xC
+#define TPS65218_STATUS_CC_STAT		0x3
+
+#define TPS65218_CONTROL_OFFNPFO	BIT(1)
+#define TPS65218_CONTROL_CC_AQ	BIT(0)
+
+#define TPS65218_FLAG_GPO3_FLG		BIT(7)
+#define TPS65218_FLAG_GPO2_FLG		BIT(6)
+#define TPS65218_FLAG_GPO1_FLG		BIT(5)
+#define TPS65218_FLAG_LDO1_FLG		BIT(4)
+#define TPS65218_FLAG_DC4_FLG		BIT(3)
+#define TPS65218_FLAG_DC3_FLG		BIT(2)
+#define TPS65218_FLAG_DC2_FLG		BIT(1)
+#define TPS65218_FLAG_DC1_FLG		BIT(0)
+
+#define TPS65218_ENABLE1_DC6_EN		BIT(5)
+#define TPS65218_ENABLE1_DC5_EN		BIT(4)
+#define TPS65218_ENABLE1_DC4_EN		BIT(3)
+#define TPS65218_ENABLE1_DC3_EN		BIT(2)
+#define TPS65218_ENABLE1_DC2_EN		BIT(1)
+#define TPS65218_ENABLE1_DC1_EN		BIT(0)
+
+#define TPS65218_ENABLE2_GPIO3		BIT(6)
+#define TPS65218_ENABLE2_GPIO2		BIT(5)
+#define TPS65218_ENABLE2_GPIO1		BIT(4)
+#define TPS65218_ENABLE2_LS3_EN		BIT(3)
+#define TPS65218_ENABLE2_LS2_EN		BIT(2)
+#define TPS65218_ENABLE2_LS1_EN		BIT(1)
+#define TPS65218_ENABLE2_LDO1_EN	BIT(0)
+
+
+#define TPS65218_CONFIG1_TRST		BIT(7)
+#define TPS65218_CONFIG1_GPO2_BUF	BIT(6)
+#define TPS65218_CONFIG1_IO1_SEL	BIT(5)
+#define TPS65218_CONFIG1_PGDLY_MASK	0x18
+#define TPS65218_CONFIG1_STRICT		BIT(2)
+#define TPS65218_CONFIG1_UVLO_MASK	0x3
+
+#define TPS65218_CONFIG2_DC12_RST	BIT(7)
+#define TPS65218_CONFIG2_UVLOHYS	BIT(6)
+#define TPS65218_CONFIG2_LS3ILIM_MASK	0xC
+#define TPS65218_CONFIG2_LS2ILIM_MASK	0x3
+
+#define TPS65218_CONFIG3_LS3NPFO	BIT(5)
+#define TPS65218_CONFIG3_LS2NPFO	BIT(4)
+#define TPS65218_CONFIG3_LS1NPFO	BIT(3)
+#define TPS65218_CONFIG3_LS3DCHRG	BIT(2)
+#define TPS65218_CONFIG3_LS2DCHRG	BIT(1)
+#define TPS65218_CONFIG3_LS1DCHRG	BIT(0)
+
+#define TPS65218_CONTROL_DCDC1_PFM	BIT(7)
+#define TPS65218_CONTROL_DCDC1_MASK	0x7F
+
+#define TPS65218_CONTROL_DCDC2_PFM	BIT(7)
+#define TPS65218_CONTROL_DCDC2_MASK	0x3F
+
+#define TPS65218_CONTROL_DCDC3_PFM	BIT(7)
+#define TPS65218_CONTROL_DCDC3_MASK	0x3F
+
+#define TPS65218_CONTROL_DCDC4_PFM	BIT(7)
+#define TPS65218_CONTROL_DCDC4_MASK	0x3F
+
+#define TPS65218_SLEW_RATE_GO		BIT(7)
+#define TPS65218_SLEW_RATE_GODSBL	BIT(6)
+#define TPS65218_SLEW_RATE_SLEW_MASK	0x7
+
+#define TPS65218_CONTROL_LDO1_MASK	0x3F
+
+#define TPS65218_SEQ1_DLY8		BIT(7)
+#define TPS65218_SEQ1_DLY7		BIT(6)
+#define TPS65218_SEQ1_DLY6		BIT(5)
+#define TPS65218_SEQ1_DLY5		BIT(4)
+#define TPS65218_SEQ1_DLY4		BIT(3)
+#define TPS65218_SEQ1_DLY3		BIT(2)
+#define TPS65218_SEQ1_DLY2		BIT(1)
+#define TPS65218_SEQ1_DLY1		BIT(0)
+
+#define TPS65218_SEQ2_DLYFCTR		BIT(7)
+#define TPS65218_SEQ2_DLY9		BIT(0)
+
+#define TPS65218_SEQ3_DC2_SEQ_MASK	0xF0
+#define TPS65218_SEQ3_DC1_SEQ_MASK	0xF
+
+#define TPS65218_SEQ4_DC4_SEQ_MASK	0xF0
+#define TPS65218_SEQ4_DC3_SEQ_MASK	0xF
+
+#define TPS65218_SEQ5_DC6_SEQ_MASK	0xF0
+#define TPS65218_SEQ5_DC5_SEQ_MASK	0xF
+
+#define TPS65218_SEQ6_LS1_SEQ_MASK	0xF0
+#define TPS65218_SEQ6_LDO1_SEQ_MASK	0xF
+
+#define TPS65218_SEQ7_GPO3_SEQ_MASK	0xF0
+#define TPS65218_SEQ7_GPO1_SEQ_MASK	0xF
+#define TPS65218_PROTECT_NONE		0
+#define TPS65218_PROTECT_L1		1
+
+enum tps65218_regulator_id {
+	/* DCDC's */
+	TPS65218_DCDC_1,
+	TPS65218_DCDC_2,
+	TPS65218_DCDC_3,
+	TPS65218_DCDC_4,
+	TPS65218_DCDC_5,
+	TPS65218_DCDC_6,
+	/* LDOs */
+	TPS65218_LDO_1,
+};
+
+#define TPS65218_MAX_REG_ID		TPS65218_LDO_1
+
+/* Number of step-down converters available */
+#define TPS65218_NUM_DCDC		6
+/* Number of LDO voltage regulators available */
+#define TPS65218_NUM_LDO		1
+/* Number of total regulators available */
+#define TPS65218_NUM_REGULATOR		(TPS65218_NUM_DCDC + TPS65218_NUM_LDO)
+
+/* Define the TPS65218 IRQ numbers */
+enum tps65218_irqs {
+	/* INT1 registers */
+	TPS65218_PRGC_IRQ,
+	TPS65218_CC_AQC_IRQ,
+	TPS65218_HOT_IRQ,
+	TPS65218_PB_IRQ,
+	TPS65218_AC_IRQ,
+	TPS65218_VPRG_IRQ,
+	TPS65218_INVALID1_IRQ,
+	TPS65218_INVALID2_IRQ,
+	/* INT2 registers */
+	TPS65218_LS1_I_IRQ,
+	TPS65218_LS2_I_IRQ,
+	TPS65218_LS3_I_IRQ,
+	TPS65218_LS1_F_IRQ,
+	TPS65218_LS2_F_IRQ,
+	TPS65218_LS3_F_IRQ,
+	TPS65218_INVALID3_IRQ,
+	TPS65218_INVALID4_IRQ,
+};
+
+/**
+ * struct tps_info - packages regulator constraints
+ * @id:			Id of the regulator
+ * @name:		Voltage regulator name
+ * @min_uV:		minimum micro volts
+ * @max_uV:		minimum micro volts
+ *
+ * This data is used to check the regualtor voltage limits while setting.
+ */
+struct tps_info {
+	int id;
+	const char *name;
+	int min_uV;
+	int max_uV;
+};
+
+/**
+ * struct tps65218 - tps65218 sub-driver chip access routines
+ *
+ * Device data may be used to access the TPS65218 chip
+ */
+
+struct tps65218 {
+	struct device *dev;
+	unsigned int id;
+
+	struct mutex tps_lock;		/* lock guarding the data structure */
+	/* IRQ Data */
+	int irq;
+	u32 irq_mask;
+	struct regmap_irq_chip_data *irq_data;
+	struct regulator_desc desc[TPS65218_NUM_REGULATOR];
+	struct regulator_dev *rdev[TPS65218_NUM_REGULATOR];
+	struct tps_info *info[TPS65218_NUM_REGULATOR];
+	struct regmap *regmap;
+};
+
+int tps65218_reg_read(struct tps65218 *tps, unsigned int reg,
+					unsigned int *val);
+int tps65218_reg_write(struct tps65218 *tps, unsigned int reg,
+			unsigned int val, unsigned int level);
+int tps65218_set_bits(struct tps65218 *tps, unsigned int reg,
+		unsigned int mask, unsigned int val, unsigned int level);
+int tps65218_clear_bits(struct tps65218 *tps, unsigned int reg,
+		unsigned int mask, unsigned int level);
+
+#endif /*  __LINUX_MFD_TPS65218_H */
-- 
cgit v1.2.3


From 730876be256603b4ee7225a125467d97a7ce9060 Mon Sep 17 00:00:00 2001
From: Roger Tseng <rogerable@realtek.com>
Date: Wed, 12 Feb 2014 18:00:36 +0800
Subject: mfd: Add realtek USB card reader driver

Realtek USB card reader provides a channel to transfer command or data to flash
memory cards. This driver exports host instances for mmc and memstick subsystems
and handles basic works.

Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Roger Tseng <rogerable@realtek.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/Kconfig          |  10 +
 drivers/mfd/Makefile         |   1 +
 drivers/mfd/rtsx_usb.c       | 760 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/rtsx_usb.h | 628 +++++++++++++++++++++++++++++++++++
 4 files changed, 1399 insertions(+)
 create mode 100644 drivers/mfd/rtsx_usb.c
 create mode 100644 include/linux/mfd/rtsx_usb.h

(limited to 'include/linux')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 91fea6164bce..09fb5706208f 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -516,6 +516,16 @@ config MFD_RTSX_PCI
 	  types of memory cards, such as Memory Stick, Memory Stick Pro,
 	  Secure Digital and MultiMediaCard.
 
+config MFD_RTSX_USB
+	tristate "Realtek USB card reader"
+	depends on USB
+	select MFD_CORE
+	help
+	  Select this option to get support for Realtek USB 2.0 card readers
+	  including RTS5129, RTS5139, RTS5179 and RTS5170.
+	  Realtek card reader supports access to many types of memory cards,
+	  such as Memory Stick Pro, Secure Digital and MultiMediaCard.
+
 config MFD_RC5T583
 	bool "Ricoh RC5T583 Power Management system device"
 	depends on I2C=y
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 5e5cfbd1b8da..377bd519884c 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -14,6 +14,7 @@ obj-$(CONFIG_MFD_CROS_EC_SPI)	+= cros_ec_spi.o
 
 rtsx_pci-objs			:= rtsx_pcr.o rts5209.o rts5229.o rtl8411.o rts5227.o rts5249.o
 obj-$(CONFIG_MFD_RTSX_PCI)	+= rtsx_pci.o
+obj-$(CONFIG_MFD_RTSX_USB)	+= rtsx_usb.o
 
 obj-$(CONFIG_HTC_EGPIO)		+= htc-egpio.o
 obj-$(CONFIG_HTC_PASIC3)	+= htc-pasic3.o
diff --git a/drivers/mfd/rtsx_usb.c b/drivers/mfd/rtsx_usb.c
new file mode 100644
index 000000000000..b53b9d46cc45
--- /dev/null
+++ b/drivers/mfd/rtsx_usb.c
@@ -0,0 +1,760 @@
+/* Driver for Realtek USB card reader
+ *
+ * Copyright(c) 2009-2013 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * Author:
+ *   Roger Tseng <rogerable@realtek.com>
+ */
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/usb.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/rtsx_usb.h>
+
+static int polling_pipe = 1;
+module_param(polling_pipe, int, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(polling_pipe, "polling pipe (0: ctl, 1: bulk)");
+
+static struct mfd_cell rtsx_usb_cells[] = {
+	[RTSX_USB_SD_CARD] = {
+		.name = "rtsx_usb_sdmmc",
+		.pdata_size = 0,
+	},
+	[RTSX_USB_MS_CARD] = {
+		.name = "rtsx_usb_ms",
+		.pdata_size = 0,
+	},
+};
+
+static void rtsx_usb_sg_timed_out(unsigned long data)
+{
+	struct rtsx_ucr *ucr = (struct rtsx_ucr *)data;
+
+	dev_dbg(&ucr->pusb_intf->dev, "%s: sg transfer timed out", __func__);
+	usb_sg_cancel(&ucr->current_sg);
+
+	/* we know the cancellation is caused by time-out */
+	ucr->current_sg.status = -ETIMEDOUT;
+}
+
+static int rtsx_usb_bulk_transfer_sglist(struct rtsx_ucr *ucr,
+		unsigned int pipe, struct scatterlist *sg, int num_sg,
+		unsigned int length, unsigned int *act_len, int timeout)
+{
+	int ret;
+
+	dev_dbg(&ucr->pusb_intf->dev, "%s: xfer %u bytes, %d entries\n",
+			__func__, length, num_sg);
+	ret = usb_sg_init(&ucr->current_sg, ucr->pusb_dev, pipe, 0,
+			sg, num_sg, length, GFP_NOIO);
+	if (ret)
+		return ret;
+
+	ucr->sg_timer.expires = jiffies + msecs_to_jiffies(timeout);
+	add_timer(&ucr->sg_timer);
+	usb_sg_wait(&ucr->current_sg);
+	del_timer(&ucr->sg_timer);
+
+	if (act_len)
+		*act_len = ucr->current_sg.bytes;
+
+	return ucr->current_sg.status;
+}
+
+int rtsx_usb_transfer_data(struct rtsx_ucr *ucr, unsigned int pipe,
+			      void *buf, unsigned int len, int num_sg,
+			      unsigned int *act_len, int timeout)
+{
+	if (timeout < 600)
+		timeout = 600;
+
+	if (num_sg)
+		return rtsx_usb_bulk_transfer_sglist(ucr, pipe,
+				(struct scatterlist *)buf, num_sg, len, act_len,
+				timeout);
+	else
+		return usb_bulk_msg(ucr->pusb_dev, pipe, buf, len, act_len,
+				timeout);
+}
+EXPORT_SYMBOL_GPL(rtsx_usb_transfer_data);
+
+static inline void rtsx_usb_seq_cmd_hdr(struct rtsx_ucr *ucr,
+		u16 addr, u16 len, u8 seq_type)
+{
+	rtsx_usb_cmd_hdr_tag(ucr);
+
+	ucr->cmd_buf[PACKET_TYPE] = seq_type;
+	ucr->cmd_buf[5] = (u8)(len >> 8);
+	ucr->cmd_buf[6] = (u8)len;
+	ucr->cmd_buf[8] = (u8)(addr >> 8);
+	ucr->cmd_buf[9] = (u8)addr;
+
+	if (seq_type == SEQ_WRITE)
+		ucr->cmd_buf[STAGE_FLAG] = 0;
+	else
+		ucr->cmd_buf[STAGE_FLAG] = STAGE_R;
+}
+
+static int rtsx_usb_seq_write_register(struct rtsx_ucr *ucr,
+		u16 addr, u16 len, u8 *data)
+{
+	u16 cmd_len = ALIGN(SEQ_WRITE_DATA_OFFSET + len, 4);
+
+	if (!data)
+		return -EINVAL;
+
+	if (cmd_len > IOBUF_SIZE)
+		return -EINVAL;
+
+	rtsx_usb_seq_cmd_hdr(ucr, addr, len, SEQ_WRITE);
+	memcpy(ucr->cmd_buf + SEQ_WRITE_DATA_OFFSET, data, len);
+
+	return rtsx_usb_transfer_data(ucr,
+			usb_sndbulkpipe(ucr->pusb_dev, EP_BULK_OUT),
+			ucr->cmd_buf, cmd_len, 0, NULL, 100);
+}
+
+static int rtsx_usb_seq_read_register(struct rtsx_ucr *ucr,
+		u16 addr, u16 len, u8 *data)
+{
+	int i, ret;
+	u16 rsp_len = round_down(len, 4);
+	u16 res_len = len - rsp_len;
+
+	if (!data)
+		return -EINVAL;
+
+	/* 4-byte aligned part */
+	if (rsp_len) {
+		rtsx_usb_seq_cmd_hdr(ucr, addr, len, SEQ_READ);
+		ret = rtsx_usb_transfer_data(ucr,
+				usb_sndbulkpipe(ucr->pusb_dev, EP_BULK_OUT),
+				ucr->cmd_buf, 12, 0, NULL, 100);
+		if (ret)
+			return ret;
+
+		ret = rtsx_usb_transfer_data(ucr,
+				usb_rcvbulkpipe(ucr->pusb_dev, EP_BULK_IN),
+				data, rsp_len, 0, NULL, 100);
+		if (ret)
+			return ret;
+	}
+
+	/* unaligned part */
+	for (i = 0; i < res_len; i++) {
+		ret = rtsx_usb_read_register(ucr, addr + rsp_len + i,
+				data + rsp_len + i);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+int rtsx_usb_read_ppbuf(struct rtsx_ucr *ucr, u8 *buf, int buf_len)
+{
+	return rtsx_usb_seq_read_register(ucr, PPBUF_BASE2, (u16)buf_len, buf);
+}
+EXPORT_SYMBOL_GPL(rtsx_usb_read_ppbuf);
+
+int rtsx_usb_write_ppbuf(struct rtsx_ucr *ucr, u8 *buf, int buf_len)
+{
+	return rtsx_usb_seq_write_register(ucr, PPBUF_BASE2, (u16)buf_len, buf);
+}
+EXPORT_SYMBOL_GPL(rtsx_usb_write_ppbuf);
+
+int rtsx_usb_ep0_write_register(struct rtsx_ucr *ucr, u16 addr,
+		u8 mask, u8 data)
+{
+	u16 value, index;
+
+	addr |= EP0_WRITE_REG_CMD << EP0_OP_SHIFT;
+	value = swab16(addr);
+	index = mask | data << 8;
+
+	return usb_control_msg(ucr->pusb_dev,
+			usb_sndctrlpipe(ucr->pusb_dev, 0), RTSX_USB_REQ_REG_OP,
+			USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
+			value, index, NULL, 0, 100);
+}
+EXPORT_SYMBOL_GPL(rtsx_usb_ep0_write_register);
+
+int rtsx_usb_ep0_read_register(struct rtsx_ucr *ucr, u16 addr, u8 *data)
+{
+	u16 value;
+
+	if (!data)
+		return -EINVAL;
+	*data = 0;
+
+	addr |= EP0_READ_REG_CMD << EP0_OP_SHIFT;
+	value = swab16(addr);
+
+	return usb_control_msg(ucr->pusb_dev,
+			usb_rcvctrlpipe(ucr->pusb_dev, 0), RTSX_USB_REQ_REG_OP,
+			USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
+			value, 0, data, 1, 100);
+}
+EXPORT_SYMBOL_GPL(rtsx_usb_ep0_read_register);
+
+void rtsx_usb_add_cmd(struct rtsx_ucr *ucr, u8 cmd_type, u16 reg_addr,
+		u8 mask, u8 data)
+{
+	int i;
+
+	if (ucr->cmd_idx < (IOBUF_SIZE - CMD_OFFSET) / 4) {
+		i = CMD_OFFSET + ucr->cmd_idx * 4;
+
+		ucr->cmd_buf[i++] = ((cmd_type & 0x03) << 6) |
+			(u8)((reg_addr >> 8) & 0x3F);
+		ucr->cmd_buf[i++] = (u8)reg_addr;
+		ucr->cmd_buf[i++] = mask;
+		ucr->cmd_buf[i++] = data;
+
+		ucr->cmd_idx++;
+	}
+}
+EXPORT_SYMBOL_GPL(rtsx_usb_add_cmd);
+
+int rtsx_usb_send_cmd(struct rtsx_ucr *ucr, u8 flag, int timeout)
+{
+	int ret;
+
+	ucr->cmd_buf[CNT_H] = (u8)(ucr->cmd_idx >> 8);
+	ucr->cmd_buf[CNT_L] = (u8)(ucr->cmd_idx);
+	ucr->cmd_buf[STAGE_FLAG] = flag;
+
+	ret = rtsx_usb_transfer_data(ucr,
+			usb_sndbulkpipe(ucr->pusb_dev, EP_BULK_OUT),
+			ucr->cmd_buf, ucr->cmd_idx * 4 + CMD_OFFSET,
+			0, NULL, timeout);
+	if (ret) {
+		rtsx_usb_clear_fsm_err(ucr);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_usb_send_cmd);
+
+int rtsx_usb_get_rsp(struct rtsx_ucr *ucr, int rsp_len, int timeout)
+{
+	if (rsp_len <= 0)
+		return -EINVAL;
+
+	rsp_len = ALIGN(rsp_len, 4);
+
+	return rtsx_usb_transfer_data(ucr,
+			usb_rcvbulkpipe(ucr->pusb_dev, EP_BULK_IN),
+			ucr->rsp_buf, rsp_len, 0, NULL, timeout);
+}
+EXPORT_SYMBOL_GPL(rtsx_usb_get_rsp);
+
+static int rtsx_usb_get_status_with_bulk(struct rtsx_ucr *ucr, u16 *status)
+{
+	int ret;
+
+	rtsx_usb_init_cmd(ucr);
+	rtsx_usb_add_cmd(ucr, READ_REG_CMD, CARD_EXIST, 0x00, 0x00);
+	rtsx_usb_add_cmd(ucr, READ_REG_CMD, OCPSTAT, 0x00, 0x00);
+	ret = rtsx_usb_send_cmd(ucr, MODE_CR, 100);
+	if (ret)
+		return ret;
+
+	ret = rtsx_usb_get_rsp(ucr, 2, 100);
+	if (ret)
+		return ret;
+
+	*status = ((ucr->rsp_buf[0] >> 2) & 0x0f) |
+		  ((ucr->rsp_buf[1] & 0x03) << 4);
+
+	return 0;
+}
+
+int rtsx_usb_get_card_status(struct rtsx_ucr *ucr, u16 *status)
+{
+	int ret;
+
+	if (!status)
+		return -EINVAL;
+
+	if (polling_pipe == 0)
+		ret = usb_control_msg(ucr->pusb_dev,
+				usb_rcvctrlpipe(ucr->pusb_dev, 0),
+				RTSX_USB_REQ_POLL,
+				USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
+				0, 0, status, 2, 100);
+	else
+		ret = rtsx_usb_get_status_with_bulk(ucr, status);
+
+	/* usb_control_msg may return positive when success */
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_usb_get_card_status);
+
+static int rtsx_usb_write_phy_register(struct rtsx_ucr *ucr, u8 addr, u8 val)
+{
+	dev_dbg(&ucr->pusb_intf->dev, "Write 0x%x to phy register 0x%x\n",
+			val, addr);
+
+	rtsx_usb_init_cmd(ucr);
+
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, HS_VSTAIN, 0xFF, val);
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, HS_VCONTROL, 0xFF, addr & 0x0F);
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, HS_VLOADM, 0xFF, 0x00);
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, HS_VLOADM, 0xFF, 0x00);
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, HS_VLOADM, 0xFF, 0x01);
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, HS_VCONTROL,
+			0xFF, (addr >> 4) & 0x0F);
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, HS_VLOADM, 0xFF, 0x00);
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, HS_VLOADM, 0xFF, 0x00);
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, HS_VLOADM, 0xFF, 0x01);
+
+	return rtsx_usb_send_cmd(ucr, MODE_C, 100);
+}
+
+int rtsx_usb_write_register(struct rtsx_ucr *ucr, u16 addr, u8 mask, u8 data)
+{
+	rtsx_usb_init_cmd(ucr);
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, addr, mask, data);
+	return rtsx_usb_send_cmd(ucr, MODE_C, 100);
+}
+EXPORT_SYMBOL_GPL(rtsx_usb_write_register);
+
+int rtsx_usb_read_register(struct rtsx_ucr *ucr, u16 addr, u8 *data)
+{
+	int ret;
+
+	if (data != NULL)
+		*data = 0;
+
+	rtsx_usb_init_cmd(ucr);
+	rtsx_usb_add_cmd(ucr, READ_REG_CMD, addr, 0, 0);
+	ret = rtsx_usb_send_cmd(ucr, MODE_CR, 100);
+	if (ret)
+		return ret;
+
+	ret = rtsx_usb_get_rsp(ucr, 1, 100);
+	if (ret)
+		return ret;
+
+	if (data != NULL)
+		*data = ucr->rsp_buf[0];
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_usb_read_register);
+
+static inline u8 double_ssc_depth(u8 depth)
+{
+	return (depth > 1) ? (depth - 1) : depth;
+}
+
+static u8 revise_ssc_depth(u8 ssc_depth, u8 div)
+{
+	if (div > CLK_DIV_1) {
+		if (ssc_depth > div - 1)
+			ssc_depth -= (div - 1);
+		else
+			ssc_depth = SSC_DEPTH_2M;
+	}
+
+	return ssc_depth;
+}
+
+int rtsx_usb_switch_clock(struct rtsx_ucr *ucr, unsigned int card_clock,
+		u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk)
+{
+	int ret;
+	u8 n, clk_divider, mcu_cnt, div;
+
+	if (!card_clock) {
+		ucr->cur_clk = 0;
+		return 0;
+	}
+
+	if (initial_mode) {
+		/* We use 250k(around) here, in initial stage */
+		clk_divider = SD_CLK_DIVIDE_128;
+		card_clock = 30000000;
+	} else {
+		clk_divider = SD_CLK_DIVIDE_0;
+	}
+
+	ret = rtsx_usb_write_register(ucr, SD_CFG1,
+			SD_CLK_DIVIDE_MASK, clk_divider);
+	if (ret < 0)
+		return ret;
+
+	card_clock /= 1000000;
+	dev_dbg(&ucr->pusb_intf->dev,
+			"Switch card clock to %dMHz\n", card_clock);
+
+	if (!initial_mode && double_clk)
+		card_clock *= 2;
+	dev_dbg(&ucr->pusb_intf->dev,
+			"Internal SSC clock: %dMHz (cur_clk = %d)\n",
+			card_clock, ucr->cur_clk);
+
+	if (card_clock == ucr->cur_clk)
+		return 0;
+
+	/* Converting clock value into internal settings: n and div */
+	n = card_clock - 2;
+	if ((card_clock <= 2) || (n > MAX_DIV_N))
+		return -EINVAL;
+
+	mcu_cnt = 60/card_clock + 3;
+	if (mcu_cnt > 15)
+		mcu_cnt = 15;
+
+	/* Make sure that the SSC clock div_n is not less than MIN_DIV_N */
+
+	div = CLK_DIV_1;
+	while (n < MIN_DIV_N && div < CLK_DIV_4) {
+		n = (n + 2) * 2 - 2;
+		div++;
+	}
+	dev_dbg(&ucr->pusb_intf->dev, "n = %d, div = %d\n", n, div);
+
+	if (double_clk)
+		ssc_depth = double_ssc_depth(ssc_depth);
+
+	ssc_depth = revise_ssc_depth(ssc_depth, div);
+	dev_dbg(&ucr->pusb_intf->dev, "ssc_depth = %d\n", ssc_depth);
+
+	rtsx_usb_init_cmd(ucr);
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, CLK_DIV, CLK_CHANGE, CLK_CHANGE);
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, CLK_DIV,
+			0x3F, (div << 4) | mcu_cnt);
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, 0);
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, SSC_CTL2,
+			SSC_DEPTH_MASK, ssc_depth);
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, SSC_DIV_N_0, 0xFF, n);
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, SSC_CTL1, SSC_RSTB, SSC_RSTB);
+	if (vpclk) {
+		rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, SD_VPCLK0_CTL,
+				PHASE_NOT_RESET, 0);
+		rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, SD_VPCLK0_CTL,
+				PHASE_NOT_RESET, PHASE_NOT_RESET);
+	}
+
+	ret = rtsx_usb_send_cmd(ucr, MODE_C, 2000);
+	if (ret < 0)
+		return ret;
+
+	ret = rtsx_usb_write_register(ucr, SSC_CTL1, 0xff,
+			SSC_RSTB | SSC_8X_EN | SSC_SEL_4M);
+	if (ret < 0)
+		return ret;
+
+	/* Wait SSC clock stable */
+	usleep_range(100, 1000);
+
+	ret = rtsx_usb_write_register(ucr, CLK_DIV, CLK_CHANGE, 0);
+	if (ret < 0)
+		return ret;
+
+	ucr->cur_clk = card_clock;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_usb_switch_clock);
+
+int rtsx_usb_card_exclusive_check(struct rtsx_ucr *ucr, int card)
+{
+	int ret;
+	u16 val;
+	u16 cd_mask[] = {
+		[RTSX_USB_SD_CARD] = (CD_MASK & ~SD_CD),
+		[RTSX_USB_MS_CARD] = (CD_MASK & ~MS_CD)
+	};
+
+	ret = rtsx_usb_get_card_status(ucr, &val);
+	/*
+	 * If get status fails, return 0 (ok) for the exclusive check
+	 * and let the flow fail at somewhere else.
+	 */
+	if (ret)
+		return 0;
+
+	if (val & cd_mask[card])
+		return -EIO;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtsx_usb_card_exclusive_check);
+
+static int rtsx_usb_reset_chip(struct rtsx_ucr *ucr)
+{
+	int ret;
+	u8 val;
+
+	rtsx_usb_init_cmd(ucr);
+
+	if (CHECK_PKG(ucr, LQFP48)) {
+		rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, CARD_PWR_CTL,
+				LDO3318_PWR_MASK, LDO_SUSPEND);
+		rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, CARD_PWR_CTL,
+				FORCE_LDO_POWERB, FORCE_LDO_POWERB);
+		rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, CARD_PULL_CTL1,
+				0x30, 0x10);
+		rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, CARD_PULL_CTL5,
+				0x03, 0x01);
+		rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, CARD_PULL_CTL6,
+				0x0C, 0x04);
+	}
+
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, SYS_DUMMY0, NYET_MSAK, NYET_EN);
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, CD_DEGLITCH_WIDTH, 0xFF, 0x08);
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD,
+			CD_DEGLITCH_EN, XD_CD_DEGLITCH_EN, 0x0);
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, SD30_DRIVE_SEL,
+			SD30_DRIVE_MASK, DRIVER_TYPE_D);
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD,
+			CARD_DRIVE_SEL, SD20_DRIVE_MASK, 0x0);
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, LDO_POWER_CFG, 0xE0, 0x0);
+
+	if (ucr->is_rts5179)
+		rtsx_usb_add_cmd(ucr, WRITE_REG_CMD,
+				CARD_PULL_CTL5, 0x03, 0x01);
+
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, CARD_DMA1_CTL,
+		       EXTEND_DMA1_ASYNC_SIGNAL, EXTEND_DMA1_ASYNC_SIGNAL);
+	rtsx_usb_add_cmd(ucr, WRITE_REG_CMD, CARD_INT_PEND,
+			XD_INT | MS_INT | SD_INT,
+			XD_INT | MS_INT | SD_INT);
+
+	ret = rtsx_usb_send_cmd(ucr, MODE_C, 100);
+	if (ret)
+		return ret;
+
+	/* config non-crystal mode */
+	rtsx_usb_read_register(ucr, CFG_MODE, &val);
+	if ((val & XTAL_FREE) || ((val & CLK_MODE_MASK) == CLK_MODE_NON_XTAL)) {
+		ret = rtsx_usb_write_phy_register(ucr, 0xC2, 0x7C);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int rtsx_usb_init_chip(struct rtsx_ucr *ucr)
+{
+	int ret;
+	u8 val;
+
+	rtsx_usb_clear_fsm_err(ucr);
+
+	/* power on SSC */
+	ret = rtsx_usb_write_register(ucr,
+			FPDCTL, SSC_POWER_MASK, SSC_POWER_ON);
+	if (ret)
+		return ret;
+
+	usleep_range(100, 1000);
+	ret = rtsx_usb_write_register(ucr, CLK_DIV, CLK_CHANGE, 0x00);
+	if (ret)
+		return ret;
+
+	/* determine IC version */
+	ret = rtsx_usb_read_register(ucr, HW_VERSION, &val);
+	if (ret)
+		return ret;
+
+	ucr->ic_version = val & HW_VER_MASK;
+
+	/* determine package */
+	ret = rtsx_usb_read_register(ucr, CARD_SHARE_MODE, &val);
+	if (ret)
+		return ret;
+
+	if (val & CARD_SHARE_LQFP_SEL) {
+		ucr->package = LQFP48;
+		dev_dbg(&ucr->pusb_intf->dev, "Package: LQFP48\n");
+	} else {
+		ucr->package = QFN24;
+		dev_dbg(&ucr->pusb_intf->dev, "Package: QFN24\n");
+	}
+
+	/* determine IC variations */
+	rtsx_usb_read_register(ucr, CFG_MODE_1, &val);
+	if (val & RTS5179) {
+		ucr->is_rts5179 = true;
+		dev_dbg(&ucr->pusb_intf->dev, "Device is rts5179\n");
+	} else {
+		ucr->is_rts5179 = false;
+	}
+
+	return rtsx_usb_reset_chip(ucr);
+}
+
+static int rtsx_usb_probe(struct usb_interface *intf,
+			 const struct usb_device_id *id)
+{
+	struct usb_device *usb_dev = interface_to_usbdev(intf);
+	struct rtsx_ucr *ucr;
+	int ret;
+
+	dev_dbg(&intf->dev,
+		": Realtek USB Card Reader found at bus %03d address %03d\n",
+		 usb_dev->bus->busnum, usb_dev->devnum);
+
+	ucr = devm_kzalloc(&intf->dev, sizeof(*ucr), GFP_KERNEL);
+	if (!ucr)
+		return -ENOMEM;
+
+	ucr->pusb_dev = usb_dev;
+
+	ucr->iobuf = usb_alloc_coherent(ucr->pusb_dev, IOBUF_SIZE,
+			GFP_KERNEL, &ucr->iobuf_dma);
+	if (!ucr->iobuf)
+		return -ENOMEM;
+
+	usb_set_intfdata(intf, ucr);
+
+	ucr->vendor_id = id->idVendor;
+	ucr->product_id = id->idProduct;
+	ucr->cmd_buf = ucr->rsp_buf = ucr->iobuf;
+
+	mutex_init(&ucr->dev_mutex);
+
+	ucr->pusb_intf = intf;
+
+	/* initialize */
+	ret = rtsx_usb_init_chip(ucr);
+	if (ret)
+		goto out_init_fail;
+
+	ret = mfd_add_devices(&intf->dev, usb_dev->devnum, rtsx_usb_cells,
+			ARRAY_SIZE(rtsx_usb_cells), NULL, 0, NULL);
+	if (ret)
+		goto out_init_fail;
+
+	/* initialize USB SG transfer timer */
+	init_timer(&ucr->sg_timer);
+	setup_timer(&ucr->sg_timer, rtsx_usb_sg_timed_out, (unsigned long) ucr);
+#ifdef CONFIG_PM
+	intf->needs_remote_wakeup = 1;
+	usb_enable_autosuspend(usb_dev);
+#endif
+
+	return 0;
+
+out_init_fail:
+	usb_free_coherent(ucr->pusb_dev, IOBUF_SIZE, ucr->iobuf,
+			ucr->iobuf_dma);
+	return ret;
+}
+
+static void rtsx_usb_disconnect(struct usb_interface *intf)
+{
+	struct rtsx_ucr *ucr = (struct rtsx_ucr *)usb_get_intfdata(intf);
+
+	dev_dbg(&intf->dev, "%s called\n", __func__);
+
+	mfd_remove_devices(&intf->dev);
+
+	usb_set_intfdata(ucr->pusb_intf, NULL);
+	usb_free_coherent(ucr->pusb_dev, IOBUF_SIZE, ucr->iobuf,
+			ucr->iobuf_dma);
+}
+
+#ifdef CONFIG_PM
+static int rtsx_usb_suspend(struct usb_interface *intf, pm_message_t message)
+{
+	struct rtsx_ucr *ucr =
+		(struct rtsx_ucr *)usb_get_intfdata(intf);
+
+	dev_dbg(&intf->dev, "%s called with pm message 0x%04u\n",
+			__func__, message.event);
+
+	mutex_lock(&ucr->dev_mutex);
+	rtsx_usb_turn_off_led(ucr);
+	mutex_unlock(&ucr->dev_mutex);
+	return 0;
+}
+
+static int rtsx_usb_resume(struct usb_interface *intf)
+{
+	return 0;
+}
+
+static int rtsx_usb_reset_resume(struct usb_interface *intf)
+{
+	struct rtsx_ucr *ucr =
+		(struct rtsx_ucr *)usb_get_intfdata(intf);
+
+	rtsx_usb_reset_chip(ucr);
+	return 0;
+}
+
+#else /* CONFIG_PM */
+
+#define rtsx_usb_suspend NULL
+#define rtsx_usb_resume NULL
+#define rtsx_usb_reset_resume NULL
+
+#endif /* CONFIG_PM */
+
+
+static int rtsx_usb_pre_reset(struct usb_interface *intf)
+{
+	struct rtsx_ucr *ucr = (struct rtsx_ucr *)usb_get_intfdata(intf);
+
+	mutex_lock(&ucr->dev_mutex);
+	return 0;
+}
+
+static int rtsx_usb_post_reset(struct usb_interface *intf)
+{
+	struct rtsx_ucr *ucr = (struct rtsx_ucr *)usb_get_intfdata(intf);
+
+	mutex_unlock(&ucr->dev_mutex);
+	return 0;
+}
+
+static struct usb_device_id rtsx_usb_usb_ids[] = {
+	{ USB_DEVICE(0x0BDA, 0x0129) },
+	{ USB_DEVICE(0x0BDA, 0x0139) },
+	{ USB_DEVICE(0x0BDA, 0x0140) },
+	{ }
+};
+
+static struct usb_driver rtsx_usb_driver = {
+	.name			= "rtsx_usb",
+	.probe			= rtsx_usb_probe,
+	.disconnect		= rtsx_usb_disconnect,
+	.suspend		= rtsx_usb_suspend,
+	.resume			= rtsx_usb_resume,
+	.reset_resume		= rtsx_usb_reset_resume,
+	.pre_reset		= rtsx_usb_pre_reset,
+	.post_reset		= rtsx_usb_post_reset,
+	.id_table		= rtsx_usb_usb_ids,
+	.supports_autosuspend	= 1,
+	.soft_unbind		= 1,
+};
+
+module_usb_driver(rtsx_usb_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Roger Tseng <rogerable@realtek.com>");
+MODULE_DESCRIPTION("Realtek USB Card Reader Driver");
diff --git a/include/linux/mfd/rtsx_usb.h b/include/linux/mfd/rtsx_usb.h
new file mode 100644
index 000000000000..c446e4fd6b5c
--- /dev/null
+++ b/include/linux/mfd/rtsx_usb.h
@@ -0,0 +1,628 @@
+/* Driver for Realtek RTS5139 USB card reader
+ *
+ * Copyright(c) 2009-2013 Realtek Semiconductor Corp. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ * Author:
+ *   Roger Tseng <rogerable@realtek.com>
+ */
+
+#ifndef __RTSX_USB_H
+#define __RTSX_USB_H
+
+#include <linux/usb.h>
+
+/* related module names */
+#define RTSX_USB_SD_CARD	0
+#define RTSX_USB_MS_CARD	1
+
+/* endpoint numbers */
+#define EP_BULK_OUT		1
+#define EP_BULK_IN		2
+#define EP_INTR_IN		3
+
+/* USB vendor requests */
+#define RTSX_USB_REQ_REG_OP	0x00
+#define RTSX_USB_REQ_POLL	0x02
+
+/* miscellaneous parameters */
+#define MIN_DIV_N		60
+#define MAX_DIV_N		120
+
+#define MAX_PHASE		15
+#define RX_TUNING_CNT		3
+
+#define QFN24			0
+#define LQFP48			1
+#define CHECK_PKG(ucr, pkg)	((ucr)->package == (pkg))
+
+/* data structures */
+struct rtsx_ucr {
+	u16			vendor_id;
+	u16			product_id;
+
+	int			package;
+	u8			ic_version;
+	bool			is_rts5179;
+
+	unsigned int		cur_clk;
+
+	u8			*cmd_buf;
+	unsigned int		cmd_idx;
+	u8			*rsp_buf;
+
+	struct usb_device	*pusb_dev;
+	struct usb_interface	*pusb_intf;
+	struct usb_sg_request	current_sg;
+	unsigned char		*iobuf;
+	dma_addr_t		iobuf_dma;
+
+	struct timer_list	sg_timer;
+	struct mutex		dev_mutex;
+};
+
+/* buffer size */
+#define IOBUF_SIZE		1024
+
+/* prototypes of exported functions */
+extern int rtsx_usb_get_card_status(struct rtsx_ucr *ucr, u16 *status);
+
+extern int rtsx_usb_read_register(struct rtsx_ucr *ucr, u16 addr, u8 *data);
+extern int rtsx_usb_write_register(struct rtsx_ucr *ucr, u16 addr, u8 mask,
+		u8 data);
+
+extern int rtsx_usb_ep0_write_register(struct rtsx_ucr *ucr, u16 addr, u8 mask,
+		u8 data);
+extern int rtsx_usb_ep0_read_register(struct rtsx_ucr *ucr, u16 addr,
+		u8 *data);
+
+extern void rtsx_usb_add_cmd(struct rtsx_ucr *ucr, u8 cmd_type,
+		u16 reg_addr, u8 mask, u8 data);
+extern int rtsx_usb_send_cmd(struct rtsx_ucr *ucr, u8 flag, int timeout);
+extern int rtsx_usb_get_rsp(struct rtsx_ucr *ucr, int rsp_len, int timeout);
+extern int rtsx_usb_transfer_data(struct rtsx_ucr *ucr, unsigned int pipe,
+			      void *buf, unsigned int len, int use_sg,
+			      unsigned int *act_len, int timeout);
+
+extern int rtsx_usb_read_ppbuf(struct rtsx_ucr *ucr, u8 *buf, int buf_len);
+extern int rtsx_usb_write_ppbuf(struct rtsx_ucr *ucr, u8 *buf, int buf_len);
+extern int rtsx_usb_switch_clock(struct rtsx_ucr *ucr, unsigned int card_clock,
+		u8 ssc_depth, bool initial_mode, bool double_clk, bool vpclk);
+extern int rtsx_usb_card_exclusive_check(struct rtsx_ucr *ucr, int card);
+
+/* card status */
+#define SD_CD		0x01
+#define MS_CD		0x02
+#define XD_CD		0x04
+#define CD_MASK		(SD_CD | MS_CD | XD_CD)
+#define SD_WP		0x08
+
+/* reader command field offset & parameters */
+#define READ_REG_CMD		0
+#define WRITE_REG_CMD		1
+#define CHECK_REG_CMD		2
+
+#define PACKET_TYPE		4
+#define CNT_H			5
+#define CNT_L			6
+#define STAGE_FLAG		7
+#define CMD_OFFSET		8
+#define SEQ_WRITE_DATA_OFFSET	12
+
+#define BATCH_CMD		0
+#define SEQ_READ		1
+#define SEQ_WRITE		2
+
+#define STAGE_R			0x01
+#define STAGE_DI		0x02
+#define STAGE_DO		0x04
+#define STAGE_MS_STATUS		0x08
+#define STAGE_XD_STATUS		0x10
+#define MODE_C			0x00
+#define MODE_CR			(STAGE_R)
+#define MODE_CDIR		(STAGE_R | STAGE_DI)
+#define MODE_CDOR		(STAGE_R | STAGE_DO)
+
+#define EP0_OP_SHIFT		14
+#define EP0_READ_REG_CMD	2
+#define EP0_WRITE_REG_CMD	3
+
+#define rtsx_usb_cmd_hdr_tag(ucr)		\
+	do {					\
+		ucr->cmd_buf[0] = 'R';		\
+		ucr->cmd_buf[1] = 'T';		\
+		ucr->cmd_buf[2] = 'C';		\
+		ucr->cmd_buf[3] = 'R';		\
+	} while (0)
+
+static inline void rtsx_usb_init_cmd(struct rtsx_ucr *ucr)
+{
+	rtsx_usb_cmd_hdr_tag(ucr);
+	ucr->cmd_idx = 0;
+	ucr->cmd_buf[PACKET_TYPE] = BATCH_CMD;
+}
+
+/* internal register address */
+#define FPDCTL				0xFC00
+#define SSC_DIV_N_0			0xFC07
+#define SSC_CTL1			0xFC09
+#define SSC_CTL2			0xFC0A
+#define CFG_MODE			0xFC0E
+#define CFG_MODE_1			0xFC0F
+#define RCCTL				0xFC14
+#define SOF_WDOG			0xFC28
+#define SYS_DUMMY0			0xFC30
+
+#define MS_BLKEND			0xFD30
+#define MS_READ_START			0xFD31
+#define MS_READ_COUNT			0xFD32
+#define MS_WRITE_START			0xFD33
+#define MS_WRITE_COUNT			0xFD34
+#define MS_COMMAND			0xFD35
+#define MS_OLD_BLOCK_0			0xFD36
+#define MS_OLD_BLOCK_1			0xFD37
+#define MS_NEW_BLOCK_0			0xFD38
+#define MS_NEW_BLOCK_1			0xFD39
+#define MS_LOG_BLOCK_0			0xFD3A
+#define MS_LOG_BLOCK_1			0xFD3B
+#define MS_BUS_WIDTH			0xFD3C
+#define MS_PAGE_START			0xFD3D
+#define MS_PAGE_LENGTH			0xFD3E
+#define MS_CFG				0xFD40
+#define MS_TPC				0xFD41
+#define MS_TRANS_CFG			0xFD42
+#define MS_TRANSFER			0xFD43
+#define MS_INT_REG			0xFD44
+#define MS_BYTE_CNT			0xFD45
+#define MS_SECTOR_CNT_L			0xFD46
+#define MS_SECTOR_CNT_H			0xFD47
+#define MS_DBUS_H			0xFD48
+
+#define CARD_DMA1_CTL			0xFD5C
+#define CARD_PULL_CTL1			0xFD60
+#define CARD_PULL_CTL2			0xFD61
+#define CARD_PULL_CTL3			0xFD62
+#define CARD_PULL_CTL4			0xFD63
+#define CARD_PULL_CTL5			0xFD64
+#define CARD_PULL_CTL6			0xFD65
+#define CARD_EXIST			0xFD6F
+#define CARD_INT_PEND			0xFD71
+
+#define LDO_POWER_CFG			0xFD7B
+
+#define SD_CFG1				0xFDA0
+#define SD_CFG2				0xFDA1
+#define SD_CFG3				0xFDA2
+#define SD_STAT1			0xFDA3
+#define SD_STAT2			0xFDA4
+#define SD_BUS_STAT			0xFDA5
+#define SD_PAD_CTL			0xFDA6
+#define SD_SAMPLE_POINT_CTL		0xFDA7
+#define SD_PUSH_POINT_CTL		0xFDA8
+#define SD_CMD0				0xFDA9
+#define SD_CMD1				0xFDAA
+#define SD_CMD2				0xFDAB
+#define SD_CMD3				0xFDAC
+#define SD_CMD4				0xFDAD
+#define SD_CMD5				0xFDAE
+#define SD_BYTE_CNT_L			0xFDAF
+#define SD_BYTE_CNT_H			0xFDB0
+#define SD_BLOCK_CNT_L			0xFDB1
+#define SD_BLOCK_CNT_H			0xFDB2
+#define SD_TRANSFER			0xFDB3
+#define SD_CMD_STATE			0xFDB5
+#define SD_DATA_STATE			0xFDB6
+#define SD_VPCLK0_CTL			0xFC2A
+#define SD_VPCLK1_CTL			0xFC2B
+#define SD_DCMPS0_CTL			0xFC2C
+#define SD_DCMPS1_CTL			0xFC2D
+
+#define CARD_DMA1_CTL			0xFD5C
+
+#define HW_VERSION			0xFC01
+
+#define SSC_CLK_FPGA_SEL		0xFC02
+#define CLK_DIV				0xFC03
+#define SFSM_ED				0xFC04
+
+#define CD_DEGLITCH_WIDTH		0xFC20
+#define CD_DEGLITCH_EN			0xFC21
+#define AUTO_DELINK_EN			0xFC23
+
+#define FPGA_PULL_CTL			0xFC1D
+#define CARD_CLK_SOURCE			0xFC2E
+
+#define CARD_SHARE_MODE			0xFD51
+#define CARD_DRIVE_SEL			0xFD52
+#define CARD_STOP			0xFD53
+#define CARD_OE				0xFD54
+#define CARD_AUTO_BLINK			0xFD55
+#define CARD_GPIO			0xFD56
+#define SD30_DRIVE_SEL			0xFD57
+
+#define CARD_DATA_SOURCE		0xFD5D
+#define CARD_SELECT			0xFD5E
+
+#define CARD_CLK_EN			0xFD79
+#define CARD_PWR_CTL			0xFD7A
+
+#define OCPCTL				0xFD80
+#define OCPPARA1			0xFD81
+#define OCPPARA2			0xFD82
+#define OCPSTAT				0xFD83
+
+#define HS_USB_STAT			0xFE01
+#define HS_VCONTROL			0xFE26
+#define HS_VSTAIN			0xFE27
+#define HS_VLOADM			0xFE28
+#define HS_VSTAOUT			0xFE29
+
+#define MC_IRQ				0xFF00
+#define MC_IRQEN			0xFF01
+#define MC_FIFO_CTL			0xFF02
+#define MC_FIFO_BC0			0xFF03
+#define MC_FIFO_BC1			0xFF04
+#define MC_FIFO_STAT			0xFF05
+#define MC_FIFO_MODE			0xFF06
+#define MC_FIFO_RD_PTR0			0xFF07
+#define MC_FIFO_RD_PTR1			0xFF08
+#define MC_DMA_CTL			0xFF10
+#define MC_DMA_TC0			0xFF11
+#define MC_DMA_TC1			0xFF12
+#define MC_DMA_TC2			0xFF13
+#define MC_DMA_TC3			0xFF14
+#define MC_DMA_RST			0xFF15
+
+#define RBUF_SIZE_MASK			0xFBFF
+#define RBUF_BASE			0xF000
+#define PPBUF_BASE1			0xF800
+#define PPBUF_BASE2			0xFA00
+
+/* internal register value macros */
+#define POWER_OFF			0x03
+#define PARTIAL_POWER_ON		0x02
+#define POWER_ON			0x00
+#define POWER_MASK			0x03
+#define LDO3318_PWR_MASK		0x0C
+#define LDO_ON				0x00
+#define LDO_SUSPEND			0x08
+#define LDO_OFF				0x0C
+#define DV3318_AUTO_PWR_OFF		0x10
+#define FORCE_LDO_POWERB		0x60
+
+/* LDO_POWER_CFG */
+#define TUNE_SD18_MASK			0x1C
+#define TUNE_SD18_1V7			0x00
+#define TUNE_SD18_1V8			(0x01 << 2)
+#define TUNE_SD18_1V9			(0x02 << 2)
+#define TUNE_SD18_2V0			(0x03 << 2)
+#define TUNE_SD18_2V7			(0x04 << 2)
+#define TUNE_SD18_2V8			(0x05 << 2)
+#define TUNE_SD18_2V9			(0x06 << 2)
+#define TUNE_SD18_3V3			(0x07 << 2)
+
+/* CLK_DIV */
+#define CLK_CHANGE			0x80
+#define CLK_DIV_1			0x00
+#define CLK_DIV_2			0x01
+#define CLK_DIV_4			0x02
+#define CLK_DIV_8			0x03
+
+#define SSC_POWER_MASK			0x01
+#define SSC_POWER_DOWN			0x01
+#define SSC_POWER_ON			0x00
+
+#define FPGA_VER			0x80
+#define HW_VER_MASK			0x0F
+
+#define EXTEND_DMA1_ASYNC_SIGNAL	0x02
+
+/* CFG_MODE*/
+#define XTAL_FREE			0x80
+#define CLK_MODE_MASK			0x03
+#define CLK_MODE_12M_XTAL		0x00
+#define CLK_MODE_NON_XTAL		0x01
+#define CLK_MODE_24M_OSC		0x02
+#define CLK_MODE_48M_OSC		0x03
+
+/* CFG_MODE_1*/
+#define RTS5179				0x02
+
+#define NYET_EN				0x01
+#define NYET_MSAK			0x01
+
+#define SD30_DRIVE_MASK			0x07
+#define SD20_DRIVE_MASK			0x03
+
+#define DISABLE_SD_CD			0x08
+#define DISABLE_MS_CD			0x10
+#define DISABLE_XD_CD			0x20
+#define SD_CD_DEGLITCH_EN		0x01
+#define MS_CD_DEGLITCH_EN		0x02
+#define XD_CD_DEGLITCH_EN		0x04
+
+#define	CARD_SHARE_LQFP48		0x04
+#define	CARD_SHARE_QFN24		0x00
+#define CARD_SHARE_LQFP_SEL		0x04
+#define	CARD_SHARE_XD			0x00
+#define	CARD_SHARE_SD			0x01
+#define	CARD_SHARE_MS			0x02
+#define CARD_SHARE_MASK			0x03
+
+
+/* SD30_DRIVE_SEL */
+#define DRIVER_TYPE_A			0x05
+#define DRIVER_TYPE_B			0x03
+#define DRIVER_TYPE_C			0x02
+#define DRIVER_TYPE_D			0x01
+
+/* SD_BUS_STAT */
+#define	SD_CLK_TOGGLE_EN		0x80
+#define	SD_CLK_FORCE_STOP	        0x40
+#define	SD_DAT3_STATUS		        0x10
+#define	SD_DAT2_STATUS		        0x08
+#define	SD_DAT1_STATUS		        0x04
+#define	SD_DAT0_STATUS		        0x02
+#define	SD_CMD_STATUS			0x01
+
+/* SD_PAD_CTL */
+#define	SD_IO_USING_1V8		        0x80
+#define	SD_IO_USING_3V3		        0x7F
+#define	TYPE_A_DRIVING		        0x00
+#define	TYPE_B_DRIVING			0x01
+#define	TYPE_C_DRIVING			0x02
+#define	TYPE_D_DRIVING		        0x03
+
+/* CARD_CLK_EN */
+#define SD_CLK_EN			0x04
+#define MS_CLK_EN			0x08
+
+/* CARD_SELECT */
+#define SD_MOD_SEL			2
+#define MS_MOD_SEL			3
+
+/* CARD_SHARE_MODE */
+#define	CARD_SHARE_LQFP48		0x04
+#define	CARD_SHARE_QFN24		0x00
+#define CARD_SHARE_LQFP_SEL		0x04
+#define	CARD_SHARE_XD			0x00
+#define	CARD_SHARE_SD			0x01
+#define	CARD_SHARE_MS			0x02
+#define CARD_SHARE_MASK			0x03
+
+/* SSC_CTL1 */
+#define SSC_RSTB			0x80
+#define SSC_8X_EN			0x40
+#define SSC_FIX_FRAC			0x20
+#define SSC_SEL_1M			0x00
+#define SSC_SEL_2M			0x08
+#define SSC_SEL_4M			0x10
+#define SSC_SEL_8M			0x18
+
+/* SSC_CTL2 */
+#define SSC_DEPTH_MASK			0x03
+#define SSC_DEPTH_DISALBE		0x00
+#define SSC_DEPTH_2M			0x01
+#define SSC_DEPTH_1M			0x02
+#define SSC_DEPTH_512K			0x03
+
+/* SD_VPCLK0_CTL */
+#define PHASE_CHANGE			0x80
+#define PHASE_NOT_RESET			0x40
+
+/* SD_TRANSFER */
+#define	SD_TRANSFER_START		0x80
+#define	SD_TRANSFER_END			0x40
+#define SD_STAT_IDLE			0x20
+#define	SD_TRANSFER_ERR			0x10
+#define	SD_TM_NORMAL_WRITE		0x00
+#define	SD_TM_AUTO_WRITE_3		0x01
+#define	SD_TM_AUTO_WRITE_4		0x02
+#define	SD_TM_AUTO_READ_3		0x05
+#define	SD_TM_AUTO_READ_4		0x06
+#define	SD_TM_CMD_RSP			0x08
+#define	SD_TM_AUTO_WRITE_1		0x09
+#define	SD_TM_AUTO_WRITE_2		0x0A
+#define	SD_TM_NORMAL_READ		0x0C
+#define	SD_TM_AUTO_READ_1		0x0D
+#define	SD_TM_AUTO_READ_2		0x0E
+#define	SD_TM_AUTO_TUNING		0x0F
+
+/* SD_CFG1 */
+#define SD_CLK_DIVIDE_0			0x00
+#define	SD_CLK_DIVIDE_256		0xC0
+#define	SD_CLK_DIVIDE_128		0x80
+#define SD_CLK_DIVIDE_MASK		0xC0
+#define	SD_BUS_WIDTH_1BIT		0x00
+#define	SD_BUS_WIDTH_4BIT		0x01
+#define	SD_BUS_WIDTH_8BIT		0x02
+#define	SD_ASYNC_FIFO_RST		0x10
+#define	SD_20_MODE			0x00
+#define	SD_DDR_MODE			0x04
+#define	SD_30_MODE			0x08
+
+/* SD_CFG2 */
+#define	SD_CALCULATE_CRC7		0x00
+#define	SD_NO_CALCULATE_CRC7		0x80
+#define	SD_CHECK_CRC16			0x00
+#define	SD_NO_CHECK_CRC16		0x40
+#define SD_WAIT_CRC_TO_EN		0x20
+#define	SD_WAIT_BUSY_END		0x08
+#define	SD_NO_WAIT_BUSY_END		0x00
+#define	SD_CHECK_CRC7			0x00
+#define	SD_NO_CHECK_CRC7		0x04
+#define	SD_RSP_LEN_0			0x00
+#define	SD_RSP_LEN_6			0x01
+#define	SD_RSP_LEN_17			0x02
+#define	SD_RSP_TYPE_R0			0x04
+#define	SD_RSP_TYPE_R1			0x01
+#define	SD_RSP_TYPE_R1b			0x09
+#define	SD_RSP_TYPE_R2			0x02
+#define	SD_RSP_TYPE_R3			0x05
+#define	SD_RSP_TYPE_R4			0x05
+#define	SD_RSP_TYPE_R5			0x01
+#define	SD_RSP_TYPE_R6			0x01
+#define	SD_RSP_TYPE_R7			0x01
+
+/* SD_STAT1 */
+#define	SD_CRC7_ERR			0x80
+#define	SD_CRC16_ERR			0x40
+#define	SD_CRC_WRITE_ERR		0x20
+#define	SD_CRC_WRITE_ERR_MASK		0x1C
+#define	GET_CRC_TIME_OUT		0x02
+#define	SD_TUNING_COMPARE_ERR		0x01
+
+/* SD_DATA_STATE */
+#define SD_DATA_IDLE			0x80
+
+/* CARD_DATA_SOURCE */
+#define PINGPONG_BUFFER			0x01
+#define RING_BUFFER			0x00
+
+/* CARD_OE */
+#define SD_OUTPUT_EN			0x04
+#define MS_OUTPUT_EN			0x08
+
+/* CARD_STOP */
+#define SD_STOP				0x04
+#define MS_STOP				0x08
+#define SD_CLR_ERR			0x40
+#define MS_CLR_ERR			0x80
+
+/* CARD_CLK_SOURCE */
+#define CRC_FIX_CLK			(0x00 << 0)
+#define CRC_VAR_CLK0			(0x01 << 0)
+#define CRC_VAR_CLK1			(0x02 << 0)
+#define SD30_FIX_CLK			(0x00 << 2)
+#define SD30_VAR_CLK0			(0x01 << 2)
+#define SD30_VAR_CLK1			(0x02 << 2)
+#define SAMPLE_FIX_CLK			(0x00 << 4)
+#define SAMPLE_VAR_CLK0			(0x01 << 4)
+#define SAMPLE_VAR_CLK1			(0x02 << 4)
+
+/* SD_SAMPLE_POINT_CTL */
+#define	DDR_FIX_RX_DAT			0x00
+#define	DDR_VAR_RX_DAT			0x80
+#define	DDR_FIX_RX_DAT_EDGE		0x00
+#define	DDR_FIX_RX_DAT_14_DELAY		0x40
+#define	DDR_FIX_RX_CMD			0x00
+#define	DDR_VAR_RX_CMD			0x20
+#define	DDR_FIX_RX_CMD_POS_EDGE		0x00
+#define	DDR_FIX_RX_CMD_14_DELAY		0x10
+#define	SD20_RX_POS_EDGE		0x00
+#define	SD20_RX_14_DELAY		0x08
+#define SD20_RX_SEL_MASK		0x08
+
+/* SD_PUSH_POINT_CTL */
+#define	DDR_FIX_TX_CMD_DAT		0x00
+#define	DDR_VAR_TX_CMD_DAT		0x80
+#define	DDR_FIX_TX_DAT_14_TSU		0x00
+#define	DDR_FIX_TX_DAT_12_TSU		0x40
+#define	DDR_FIX_TX_CMD_NEG_EDGE		0x00
+#define	DDR_FIX_TX_CMD_14_AHEAD		0x20
+#define	SD20_TX_NEG_EDGE		0x00
+#define	SD20_TX_14_AHEAD		0x10
+#define SD20_TX_SEL_MASK		0x10
+#define	DDR_VAR_SDCLK_POL_SWAP		0x01
+
+/* MS_CFG */
+#define	SAMPLE_TIME_RISING		0x00
+#define	SAMPLE_TIME_FALLING		0x80
+#define	PUSH_TIME_DEFAULT		0x00
+#define	PUSH_TIME_ODD			0x40
+#define	NO_EXTEND_TOGGLE		0x00
+#define	EXTEND_TOGGLE_CHK		0x20
+#define	MS_BUS_WIDTH_1			0x00
+#define	MS_BUS_WIDTH_4			0x10
+#define	MS_BUS_WIDTH_8			0x18
+#define	MS_2K_SECTOR_MODE		0x04
+#define	MS_512_SECTOR_MODE		0x00
+#define	MS_TOGGLE_TIMEOUT_EN		0x00
+#define	MS_TOGGLE_TIMEOUT_DISEN		0x01
+#define MS_NO_CHECK_INT			0x02
+
+/* MS_TRANS_CFG */
+#define	WAIT_INT			0x80
+#define	NO_WAIT_INT			0x00
+#define	NO_AUTO_READ_INT_REG		0x00
+#define	AUTO_READ_INT_REG		0x40
+#define	MS_CRC16_ERR			0x20
+#define	MS_RDY_TIMEOUT			0x10
+#define	MS_INT_CMDNK			0x08
+#define	MS_INT_BREQ			0x04
+#define	MS_INT_ERR			0x02
+#define	MS_INT_CED			0x01
+
+/* MS_TRANSFER */
+#define	MS_TRANSFER_START		0x80
+#define	MS_TRANSFER_END			0x40
+#define	MS_TRANSFER_ERR			0x20
+#define	MS_BS_STATE			0x10
+#define	MS_TM_READ_BYTES		0x00
+#define	MS_TM_NORMAL_READ		0x01
+#define	MS_TM_WRITE_BYTES		0x04
+#define	MS_TM_NORMAL_WRITE		0x05
+#define	MS_TM_AUTO_READ			0x08
+#define	MS_TM_AUTO_WRITE		0x0C
+#define MS_TM_SET_CMD			0x06
+#define MS_TM_COPY_PAGE			0x07
+#define MS_TM_MULTI_READ		0x02
+#define MS_TM_MULTI_WRITE		0x03
+
+/* MC_FIFO_CTL */
+#define FIFO_FLUSH			0x01
+
+/* MC_DMA_RST */
+#define DMA_RESET  0x01
+
+/* MC_DMA_CTL */
+#define DMA_TC_EQ_0			0x80
+#define DMA_DIR_TO_CARD			0x00
+#define DMA_DIR_FROM_CARD		0x02
+#define DMA_EN				0x01
+#define DMA_128				(0 << 2)
+#define DMA_256				(1 << 2)
+#define DMA_512				(2 << 2)
+#define DMA_1024			(3 << 2)
+#define DMA_PACK_SIZE_MASK		0x0C
+
+/* CARD_INT_PEND */
+#define XD_INT				0x10
+#define MS_INT				0x08
+#define SD_INT				0x04
+
+/* LED operations*/
+static inline int rtsx_usb_turn_on_led(struct rtsx_ucr *ucr)
+{
+	return  rtsx_usb_ep0_write_register(ucr, CARD_GPIO, 0x03, 0x02);
+}
+
+static inline int rtsx_usb_turn_off_led(struct rtsx_ucr *ucr)
+{
+	return rtsx_usb_ep0_write_register(ucr, CARD_GPIO, 0x03, 0x03);
+}
+
+/* HW error clearing */
+static inline void rtsx_usb_clear_fsm_err(struct rtsx_ucr *ucr)
+{
+	rtsx_usb_ep0_write_register(ucr, SFSM_ED, 0xf8, 0xf8);
+}
+
+static inline void rtsx_usb_clear_dma_err(struct rtsx_ucr *ucr)
+{
+	rtsx_usb_ep0_write_register(ucr, MC_FIFO_CTL,
+			FIFO_FLUSH, FIFO_FLUSH);
+	rtsx_usb_ep0_write_register(ucr, MC_DMA_RST, DMA_RESET, DMA_RESET);
+}
+#endif /* __RTS51139_H */
-- 
cgit v1.2.3


From c1d12c784c49980e4cbe57b7e6cc14b406449099 Mon Sep 17 00:00:00 2001
From: "Opensource [Steve Twiss]" <stwiss.opensource@diasemi.com>
Date: Fri, 14 Feb 2014 14:08:11 +0000
Subject: mfd: da9063: Add support for production silicon variant code

Add the correct silicon variant code ID (0x5) to the driver. This
new code is the 'production' variant code ID for DA9063.

This patch will remove the older variant code ID which matches the
pre-production silicon ID (0x3) for the DA9063 chip.

There is also some small amount of correction done in this patch:
it splits the revision code and correctly names it according to
the hardware specification and moves the dev_info() call before
the variant ID test.

Signed-off-by: Opensource [Steve Twiss] <stwiss.opensource@diasemi.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/da9063-core.c       | 25 ++++++++++++++-----------
 include/linux/mfd/da9063/core.h |  6 +++++-
 2 files changed, 19 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mfd/da9063-core.c b/drivers/mfd/da9063-core.c
index 26937cd01071..e70ae315abc7 100644
--- a/drivers/mfd/da9063-core.c
+++ b/drivers/mfd/da9063-core.c
@@ -110,7 +110,7 @@ static const struct mfd_cell da9063_devs[] = {
 int da9063_device_init(struct da9063 *da9063, unsigned int irq)
 {
 	struct da9063_pdata *pdata = da9063->dev->platform_data;
-	int model, revision;
+	int model, variant_id, variant_code;
 	int ret;
 
 	if (pdata) {
@@ -141,23 +141,26 @@ int da9063_device_init(struct da9063 *da9063, unsigned int irq)
 		return -ENODEV;
 	}
 
-	ret = regmap_read(da9063->regmap, DA9063_REG_CHIP_VARIANT, &revision);
+	ret = regmap_read(da9063->regmap, DA9063_REG_CHIP_VARIANT, &variant_id);
 	if (ret < 0) {
-		dev_err(da9063->dev, "Cannot read chip revision id.\n");
+		dev_err(da9063->dev, "Cannot read chip variant id.\n");
 		return -EIO;
 	}
-	revision >>= DA9063_CHIP_VARIANT_SHIFT;
-	if (revision != 3) {
-		dev_err(da9063->dev, "Unknown chip revision: %d\n", revision);
+
+	variant_code = variant_id >> DA9063_CHIP_VARIANT_SHIFT;
+
+	dev_info(da9063->dev,
+		 "Device detected (chip-ID: 0x%02X, var-ID: 0x%02X)\n",
+		 model, variant_id);
+
+	if (variant_code != PMIC_DA9063_BB) {
+		dev_err(da9063->dev, "Unknown chip variant code: 0x%02X\n",
+				variant_code);
 		return -ENODEV;
 	}
 
 	da9063->model = model;
-	da9063->revision = revision;
-
-	dev_info(da9063->dev,
-		 "Device detected (model-ID: 0x%02X  rev-ID: 0x%02X)\n",
-		 model, revision);
+	da9063->variant_code = variant_code;
 
 	ret = da9063_irq_init(da9063);
 	if (ret) {
diff --git a/include/linux/mfd/da9063/core.h b/include/linux/mfd/da9063/core.h
index 2d2a0af675fd..00a9aac5d1e8 100644
--- a/include/linux/mfd/da9063/core.h
+++ b/include/linux/mfd/da9063/core.h
@@ -33,6 +33,10 @@ enum da9063_models {
 	PMIC_DA9063 = 0x61,
 };
 
+enum da9063_variant_codes {
+	PMIC_DA9063_BB = 0x5
+};
+
 /* Interrupts */
 enum da9063_irqs {
 	DA9063_IRQ_ONKEY = 0,
@@ -72,7 +76,7 @@ struct da9063 {
 	/* Device */
 	struct device	*dev;
 	unsigned short	model;
-	unsigned short	revision;
+	unsigned char	variant_code;
 	unsigned int	flags;
 
 	/* Control interface */
-- 
cgit v1.2.3


From 6cec365e3eba3dd8c864056d8d3fd9e73ab8dd7a Mon Sep 17 00:00:00 2001
From: Vincent Donnefort <vdonnefort@gmail.com>
Date: Fri, 14 Feb 2014 15:01:53 +0100
Subject: mfd: lpc_ich: Convert ICH GPIOs IDs to enum

All those IDs are arbitrary and so can be encapsulated into an enumeration.

Signed-off-by: Vincent Donnefort <vdonnefort@gmail.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/lpc_ich.h | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mfd/lpc_ich.h b/include/linux/mfd/lpc_ich.h
index 3e1df644c407..293b06209b9c 100644
--- a/include/linux/mfd/lpc_ich.h
+++ b/include/linux/mfd/lpc_ich.h
@@ -31,13 +31,15 @@
 #define ICH_RES_GPE0	1
 
 /* GPIO compatibility */
-#define ICH_I3100_GPIO		0x401
-#define ICH_V5_GPIO		0x501
-#define ICH_V6_GPIO		0x601
-#define ICH_V7_GPIO		0x701
-#define ICH_V9_GPIO		0x801
-#define ICH_V10CORP_GPIO	0xa01
-#define ICH_V10CONS_GPIO	0xa11
+enum {
+	ICH_I3100_GPIO,
+	ICH_V5_GPIO,
+	ICH_V6_GPIO,
+	ICH_V7_GPIO,
+	ICH_V9_GPIO,
+	ICH_V10CORP_GPIO,
+	ICH_V10CONS_GPIO,
+};
 
 struct lpc_ich_info {
 	char name[32];
-- 
cgit v1.2.3


From facd9939403cb5769190054a600474399e776e3a Mon Sep 17 00:00:00 2001
From: Vincent Donnefort <vdonnefort@gmail.com>
Date: Fri, 14 Feb 2014 15:01:54 +0100
Subject: mfd: lpc_ich: Add support for Intel Avoton GPIOs

Signed-off-by: Vincent Donnefort <vdonnefort@gmail.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/lpc_ich.c       | 1 +
 include/linux/mfd/lpc_ich.h | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/mfd/lpc_ich.c b/drivers/mfd/lpc_ich.c
index 010c1b490478..17eff0925ac1 100644
--- a/drivers/mfd/lpc_ich.c
+++ b/drivers/mfd/lpc_ich.c
@@ -499,6 +499,7 @@ static struct lpc_ich_info lpc_chipset_info[] = {
 	[LPC_AVN] = {
 		.name = "Avoton SoC",
 		.iTCO_version = 1,
+		.gpio_version = AVOTON_GPIO,
 	},
 	[LPC_COLETO] = {
 		.name = "Coleto Creek",
diff --git a/include/linux/mfd/lpc_ich.h b/include/linux/mfd/lpc_ich.h
index 293b06209b9c..b2364dd026a6 100644
--- a/include/linux/mfd/lpc_ich.h
+++ b/include/linux/mfd/lpc_ich.h
@@ -39,6 +39,7 @@ enum {
 	ICH_V9_GPIO,
 	ICH_V10CORP_GPIO,
 	ICH_V10CONS_GPIO,
+	AVOTON_GPIO,
 };
 
 struct lpc_ich_info {
-- 
cgit v1.2.3


From 16263f2879afecb7772f4bae238bca66352ecffe Mon Sep 17 00:00:00 2001
From: "Opensource [Anthony Olech]" <anthony.olech.opensource@diasemi.com>
Date: Wed, 19 Feb 2014 16:32:46 +0000
Subject: mfd: da9052: Extend support to a new chip

Add the hash define for the new variant of the DA9053 PMIC called BC.

Signed-off-by: Anthony Olech <anthony.olech.opensource@diasemi.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/da9052/da9052.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/mfd/da9052/da9052.h b/include/linux/mfd/da9052/da9052.h
index 21e21b81cc75..bba65f51a0b5 100644
--- a/include/linux/mfd/da9052/da9052.h
+++ b/include/linux/mfd/da9052/da9052.h
@@ -83,6 +83,7 @@ enum da9052_chip_id {
 	DA9053_AA,
 	DA9053_BA,
 	DA9053_BB,
+	DA9053_BC,
 };
 
 struct da9052_pdata;
-- 
cgit v1.2.3


From bc866fc7a8c4322de40b694ffcfcdda50ab82f35 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@codeaurora.org>
Date: Wed, 26 Feb 2014 10:59:19 -0800
Subject: mfd: pm8xxx: Move pm8xxx-irq.c contents into only driver that uses it

The pm8xxx-irq.c code is practically mandatory given that the
pm8921-core driver will WARN about it missing and the Kconfig
marks it as default y when a PM8xxx chips is enabled. The only
reason the file was split out was because we planned to support
other pm8xxx chips with different pm8xxx-core.c files. Now that
we have DT on ARM this isn't necessary because we should be able
to support all the ssbi based PM8xxx chips in one driver and one
file with no data bloat. Let's move this code into the only
driver that uses it right now (pm8921) so that it's always compiled when
needed. In the future we can rename pm8921-core.c to something
more generic.

Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/Kconfig            |  10 --
 drivers/mfd/Makefile           |   1 -
 drivers/mfd/pm8921-core.c      | 348 ++++++++++++++++++++++++++++++++++++++
 drivers/mfd/pm8xxx-irq.c       | 371 -----------------------------------------
 include/linux/mfd/pm8xxx/irq.h |  23 ---
 5 files changed, 348 insertions(+), 405 deletions(-)
 delete mode 100644 drivers/mfd/pm8xxx-irq.c

(limited to 'include/linux')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index d93d1183991b..001668d8895f 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -492,16 +492,6 @@ config MFD_PM8921_CORE
 	  Say M here if you want to include support for PM8921 chip as a module.
 	  This will build a module called "pm8921-core".
 
-config MFD_PM8XXX_IRQ
-	bool "Qualcomm PM8xxx IRQ features"
-	depends on MFD_PM8XXX
-	default y if MFD_PM8XXX
-	help
-	  This is the IRQ driver for Qualcomm PM 8xxx PMIC chips.
-
-	  This is required to use certain other PM 8xxx features, such as GPIO
-	  and MPP.
-
 config MFD_RDC321X
 	tristate "RDC R-321x southbridge"
 	select MFD_CORE
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 377bd519884c..89a7951503ca 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -151,7 +151,6 @@ obj-$(CONFIG_MFD_SI476X_CORE)	+= si476x-core.o
 obj-$(CONFIG_MFD_CS5535)	+= cs5535-mfd.o
 obj-$(CONFIG_MFD_OMAP_USB_HOST)	+= omap-usb-host.o omap-usb-tll.o
 obj-$(CONFIG_MFD_PM8921_CORE) 	+= pm8921-core.o ssbi.o
-obj-$(CONFIG_MFD_PM8XXX_IRQ) 	+= pm8xxx-irq.o
 obj-$(CONFIG_TPS65911_COMPARATOR)	+= tps65911-comparator.o
 obj-$(CONFIG_MFD_TPS65090)	+= tps65090.o
 obj-$(CONFIG_MFD_AAT2870_CORE)	+= aat2870-core.o
diff --git a/drivers/mfd/pm8921-core.c b/drivers/mfd/pm8921-core.c
index 484fe66e6c88..50e0a9b69b9d 100644
--- a/drivers/mfd/pm8921-core.c
+++ b/drivers/mfd/pm8921-core.c
@@ -14,6 +14,8 @@
 #define pr_fmt(fmt) "%s: " fmt, __func__
 
 #include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
@@ -22,15 +24,361 @@
 #include <linux/mfd/core.h>
 #include <linux/mfd/pm8xxx/pm8921.h>
 #include <linux/mfd/pm8xxx/core.h>
+#include <linux/mfd/pm8xxx/irq.h>
+
+#define	SSBI_REG_ADDR_IRQ_BASE		0x1BB
+
+#define	SSBI_REG_ADDR_IRQ_ROOT		(SSBI_REG_ADDR_IRQ_BASE + 0)
+#define	SSBI_REG_ADDR_IRQ_M_STATUS1	(SSBI_REG_ADDR_IRQ_BASE + 1)
+#define	SSBI_REG_ADDR_IRQ_M_STATUS2	(SSBI_REG_ADDR_IRQ_BASE + 2)
+#define	SSBI_REG_ADDR_IRQ_M_STATUS3	(SSBI_REG_ADDR_IRQ_BASE + 3)
+#define	SSBI_REG_ADDR_IRQ_M_STATUS4	(SSBI_REG_ADDR_IRQ_BASE + 4)
+#define	SSBI_REG_ADDR_IRQ_BLK_SEL	(SSBI_REG_ADDR_IRQ_BASE + 5)
+#define	SSBI_REG_ADDR_IRQ_IT_STATUS	(SSBI_REG_ADDR_IRQ_BASE + 6)
+#define	SSBI_REG_ADDR_IRQ_CONFIG	(SSBI_REG_ADDR_IRQ_BASE + 7)
+#define	SSBI_REG_ADDR_IRQ_RT_STATUS	(SSBI_REG_ADDR_IRQ_BASE + 8)
+
+#define	PM_IRQF_LVL_SEL			0x01	/* level select */
+#define	PM_IRQF_MASK_FE			0x02	/* mask falling edge */
+#define	PM_IRQF_MASK_RE			0x04	/* mask rising edge */
+#define	PM_IRQF_CLR			0x08	/* clear interrupt */
+#define	PM_IRQF_BITS_MASK		0x70
+#define	PM_IRQF_BITS_SHIFT		4
+#define	PM_IRQF_WRITE			0x80
+
+#define	PM_IRQF_MASK_ALL		(PM_IRQF_MASK_FE | \
+					PM_IRQF_MASK_RE)
 
 #define REG_HWREV		0x002  /* PMIC4 revision */
 #define REG_HWREV_2		0x0E8  /* PMIC4 revision 2 */
 
+struct pm_irq_chip {
+	struct device		*dev;
+	spinlock_t		pm_irq_lock;
+	unsigned int		devirq;
+	unsigned int		irq_base;
+	unsigned int		num_irqs;
+	unsigned int		num_blocks;
+	unsigned int		num_masters;
+	u8			config[0];
+};
+
 struct pm8921 {
 	struct device			*dev;
 	struct pm_irq_chip		*irq_chip;
 };
 
+static int pm8xxx_read_root_irq(const struct pm_irq_chip *chip, u8 *rp)
+{
+	return pm8xxx_readb(chip->dev, SSBI_REG_ADDR_IRQ_ROOT, rp);
+}
+
+static int pm8xxx_read_master_irq(const struct pm_irq_chip *chip, u8 m, u8 *bp)
+{
+	return pm8xxx_readb(chip->dev,
+			SSBI_REG_ADDR_IRQ_M_STATUS1 + m, bp);
+}
+
+static int pm8xxx_read_block_irq(struct pm_irq_chip *chip, u8 bp, u8 *ip)
+{
+	int	rc;
+
+	spin_lock(&chip->pm_irq_lock);
+	rc = pm8xxx_writeb(chip->dev, SSBI_REG_ADDR_IRQ_BLK_SEL, bp);
+	if (rc) {
+		pr_err("Failed Selecting Block %d rc=%d\n", bp, rc);
+		goto bail;
+	}
+
+	rc = pm8xxx_readb(chip->dev, SSBI_REG_ADDR_IRQ_IT_STATUS, ip);
+	if (rc)
+		pr_err("Failed Reading Status rc=%d\n", rc);
+bail:
+	spin_unlock(&chip->pm_irq_lock);
+	return rc;
+}
+
+static int pm8xxx_config_irq(struct pm_irq_chip *chip, u8 bp, u8 cp)
+{
+	int	rc;
+
+	spin_lock(&chip->pm_irq_lock);
+	rc = pm8xxx_writeb(chip->dev, SSBI_REG_ADDR_IRQ_BLK_SEL, bp);
+	if (rc) {
+		pr_err("Failed Selecting Block %d rc=%d\n", bp, rc);
+		goto bail;
+	}
+
+	cp |= PM_IRQF_WRITE;
+	rc = pm8xxx_writeb(chip->dev, SSBI_REG_ADDR_IRQ_CONFIG, cp);
+	if (rc)
+		pr_err("Failed Configuring IRQ rc=%d\n", rc);
+bail:
+	spin_unlock(&chip->pm_irq_lock);
+	return rc;
+}
+
+static int pm8xxx_irq_block_handler(struct pm_irq_chip *chip, int block)
+{
+	int pmirq, irq, i, ret = 0;
+	u8 bits;
+
+	ret = pm8xxx_read_block_irq(chip, block, &bits);
+	if (ret) {
+		pr_err("Failed reading %d block ret=%d", block, ret);
+		return ret;
+	}
+	if (!bits) {
+		pr_err("block bit set in master but no irqs: %d", block);
+		return 0;
+	}
+
+	/* Check IRQ bits */
+	for (i = 0; i < 8; i++) {
+		if (bits & (1 << i)) {
+			pmirq = block * 8 + i;
+			irq = pmirq + chip->irq_base;
+			generic_handle_irq(irq);
+		}
+	}
+	return 0;
+}
+
+static int pm8xxx_irq_master_handler(struct pm_irq_chip *chip, int master)
+{
+	u8 blockbits;
+	int block_number, i, ret = 0;
+
+	ret = pm8xxx_read_master_irq(chip, master, &blockbits);
+	if (ret) {
+		pr_err("Failed to read master %d ret=%d\n", master, ret);
+		return ret;
+	}
+	if (!blockbits) {
+		pr_err("master bit set in root but no blocks: %d", master);
+		return 0;
+	}
+
+	for (i = 0; i < 8; i++)
+		if (blockbits & (1 << i)) {
+			block_number = master * 8 + i;	/* block # */
+			ret |= pm8xxx_irq_block_handler(chip, block_number);
+		}
+	return ret;
+}
+
+static void pm8xxx_irq_handler(unsigned int irq, struct irq_desc *desc)
+{
+	struct pm_irq_chip *chip = irq_desc_get_handler_data(desc);
+	struct irq_chip *irq_chip = irq_desc_get_chip(desc);
+	u8	root;
+	int	i, ret, masters = 0;
+
+	ret = pm8xxx_read_root_irq(chip, &root);
+	if (ret) {
+		pr_err("Can't read root status ret=%d\n", ret);
+		return;
+	}
+
+	/* on pm8xxx series masters start from bit 1 of the root */
+	masters = root >> 1;
+
+	/* Read allowed masters for blocks. */
+	for (i = 0; i < chip->num_masters; i++)
+		if (masters & (1 << i))
+			pm8xxx_irq_master_handler(chip, i);
+
+	irq_chip->irq_ack(&desc->irq_data);
+}
+
+static void pm8xxx_irq_mask_ack(struct irq_data *d)
+{
+	struct pm_irq_chip *chip = irq_data_get_irq_chip_data(d);
+	unsigned int pmirq = d->irq - chip->irq_base;
+	int	master, irq_bit;
+	u8	block, config;
+
+	block = pmirq / 8;
+	master = block / 8;
+	irq_bit = pmirq % 8;
+
+	config = chip->config[pmirq] | PM_IRQF_MASK_ALL | PM_IRQF_CLR;
+	pm8xxx_config_irq(chip, block, config);
+}
+
+static void pm8xxx_irq_unmask(struct irq_data *d)
+{
+	struct pm_irq_chip *chip = irq_data_get_irq_chip_data(d);
+	unsigned int pmirq = d->irq - chip->irq_base;
+	int	master, irq_bit;
+	u8	block, config;
+
+	block = pmirq / 8;
+	master = block / 8;
+	irq_bit = pmirq % 8;
+
+	config = chip->config[pmirq];
+	pm8xxx_config_irq(chip, block, config);
+}
+
+static int pm8xxx_irq_set_type(struct irq_data *d, unsigned int flow_type)
+{
+	struct pm_irq_chip *chip = irq_data_get_irq_chip_data(d);
+	unsigned int pmirq = d->irq - chip->irq_base;
+	int master, irq_bit;
+	u8 block, config;
+
+	block = pmirq / 8;
+	master = block / 8;
+	irq_bit  = pmirq % 8;
+
+	chip->config[pmirq] = (irq_bit << PM_IRQF_BITS_SHIFT)
+							| PM_IRQF_MASK_ALL;
+	if (flow_type & (IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING)) {
+		if (flow_type & IRQF_TRIGGER_RISING)
+			chip->config[pmirq] &= ~PM_IRQF_MASK_RE;
+		if (flow_type & IRQF_TRIGGER_FALLING)
+			chip->config[pmirq] &= ~PM_IRQF_MASK_FE;
+	} else {
+		chip->config[pmirq] |= PM_IRQF_LVL_SEL;
+
+		if (flow_type & IRQF_TRIGGER_HIGH)
+			chip->config[pmirq] &= ~PM_IRQF_MASK_RE;
+		else
+			chip->config[pmirq] &= ~PM_IRQF_MASK_FE;
+	}
+
+	config = chip->config[pmirq] | PM_IRQF_CLR;
+	return pm8xxx_config_irq(chip, block, config);
+}
+
+static int pm8xxx_irq_set_wake(struct irq_data *d, unsigned int on)
+{
+	return 0;
+}
+
+static struct irq_chip pm8xxx_irq_chip = {
+	.name		= "pm8xxx",
+	.irq_mask_ack	= pm8xxx_irq_mask_ack,
+	.irq_unmask	= pm8xxx_irq_unmask,
+	.irq_set_type	= pm8xxx_irq_set_type,
+	.irq_set_wake	= pm8xxx_irq_set_wake,
+	.flags		= IRQCHIP_MASK_ON_SUSPEND,
+};
+
+/**
+ * pm8xxx_get_irq_stat - get the status of the irq line
+ * @chip: pointer to identify a pmic irq controller
+ * @irq: the irq number
+ *
+ * The pm8xxx gpio and mpp rely on the interrupt block to read
+ * the values on their pins. This function is to facilitate reading
+ * the status of a gpio or an mpp line. The caller has to convert the
+ * gpio number to irq number.
+ *
+ * RETURNS:
+ * an int indicating the value read on that line
+ */
+static int pm8xxx_get_irq_stat(struct pm_irq_chip *chip, int irq)
+{
+	int pmirq, rc;
+	u8  block, bits, bit;
+	unsigned long flags;
+
+	if (chip == NULL || irq < chip->irq_base ||
+			irq >= chip->irq_base + chip->num_irqs)
+		return -EINVAL;
+
+	pmirq = irq - chip->irq_base;
+
+	block = pmirq / 8;
+	bit = pmirq % 8;
+
+	spin_lock_irqsave(&chip->pm_irq_lock, flags);
+
+	rc = pm8xxx_writeb(chip->dev, SSBI_REG_ADDR_IRQ_BLK_SEL, block);
+	if (rc) {
+		pr_err("Failed Selecting block irq=%d pmirq=%d blk=%d rc=%d\n",
+			irq, pmirq, block, rc);
+		goto bail_out;
+	}
+
+	rc = pm8xxx_readb(chip->dev, SSBI_REG_ADDR_IRQ_RT_STATUS, &bits);
+	if (rc) {
+		pr_err("Failed Configuring irq=%d pmirq=%d blk=%d rc=%d\n",
+			irq, pmirq, block, rc);
+		goto bail_out;
+	}
+
+	rc = (bits & (1 << bit)) ? 1 : 0;
+
+bail_out:
+	spin_unlock_irqrestore(&chip->pm_irq_lock, flags);
+
+	return rc;
+}
+
+static struct pm_irq_chip *pm8xxx_irq_init(struct device *dev,
+				const struct pm8xxx_irq_platform_data *pdata)
+{
+	struct pm_irq_chip  *chip;
+	int devirq, rc;
+	unsigned int pmirq;
+
+	if (!pdata) {
+		pr_err("No platform data\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	devirq = pdata->devirq;
+	if (devirq < 0) {
+		pr_err("missing devirq\n");
+		rc = devirq;
+		return ERR_PTR(-EINVAL);
+	}
+
+	chip = kzalloc(sizeof(struct pm_irq_chip)
+			+ sizeof(u8) * pdata->irq_cdata.nirqs, GFP_KERNEL);
+	if (!chip) {
+		pr_err("Cannot alloc pm_irq_chip struct\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	chip->dev = dev;
+	chip->devirq = devirq;
+	chip->irq_base = pdata->irq_base;
+	chip->num_irqs = pdata->irq_cdata.nirqs;
+	chip->num_blocks = DIV_ROUND_UP(chip->num_irqs, 8);
+	chip->num_masters = DIV_ROUND_UP(chip->num_blocks, 8);
+	spin_lock_init(&chip->pm_irq_lock);
+
+	for (pmirq = 0; pmirq < chip->num_irqs; pmirq++) {
+		irq_set_chip_and_handler(chip->irq_base + pmirq,
+				&pm8xxx_irq_chip,
+				handle_level_irq);
+		irq_set_chip_data(chip->irq_base + pmirq, chip);
+#ifdef CONFIG_ARM
+		set_irq_flags(chip->irq_base + pmirq, IRQF_VALID);
+#else
+		irq_set_noprobe(chip->irq_base + pmirq);
+#endif
+	}
+
+	irq_set_irq_type(devirq, pdata->irq_trigger_flag);
+	irq_set_handler_data(devirq, chip);
+	irq_set_chained_handler(devirq, pm8xxx_irq_handler);
+	set_irq_wake(devirq, 1);
+
+	return chip;
+}
+
+static int pm8xxx_irq_exit(struct pm_irq_chip *chip)
+{
+	irq_set_chained_handler(chip->devirq, NULL);
+	kfree(chip);
+	return 0;
+}
+
 static int pm8921_readb(const struct device *dev, u16 addr, u8 *val)
 {
 	const struct pm8xxx_drvdata *pm8921_drvdata = dev_get_drvdata(dev);
diff --git a/drivers/mfd/pm8xxx-irq.c b/drivers/mfd/pm8xxx-irq.c
deleted file mode 100644
index 1360e20adf11..000000000000
--- a/drivers/mfd/pm8xxx-irq.c
+++ /dev/null
@@ -1,371 +0,0 @@
-/*
- * Copyright (c) 2011, Code Aurora Forum. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#define pr_fmt(fmt)	"%s: " fmt, __func__
-
-#include <linux/err.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/kernel.h>
-#include <linux/mfd/pm8xxx/core.h>
-#include <linux/mfd/pm8xxx/irq.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-
-/* PMIC8xxx IRQ */
-
-#define	SSBI_REG_ADDR_IRQ_BASE		0x1BB
-
-#define	SSBI_REG_ADDR_IRQ_ROOT		(SSBI_REG_ADDR_IRQ_BASE + 0)
-#define	SSBI_REG_ADDR_IRQ_M_STATUS1	(SSBI_REG_ADDR_IRQ_BASE + 1)
-#define	SSBI_REG_ADDR_IRQ_M_STATUS2	(SSBI_REG_ADDR_IRQ_BASE + 2)
-#define	SSBI_REG_ADDR_IRQ_M_STATUS3	(SSBI_REG_ADDR_IRQ_BASE + 3)
-#define	SSBI_REG_ADDR_IRQ_M_STATUS4	(SSBI_REG_ADDR_IRQ_BASE + 4)
-#define	SSBI_REG_ADDR_IRQ_BLK_SEL	(SSBI_REG_ADDR_IRQ_BASE + 5)
-#define	SSBI_REG_ADDR_IRQ_IT_STATUS	(SSBI_REG_ADDR_IRQ_BASE + 6)
-#define	SSBI_REG_ADDR_IRQ_CONFIG	(SSBI_REG_ADDR_IRQ_BASE + 7)
-#define	SSBI_REG_ADDR_IRQ_RT_STATUS	(SSBI_REG_ADDR_IRQ_BASE + 8)
-
-#define	PM_IRQF_LVL_SEL			0x01	/* level select */
-#define	PM_IRQF_MASK_FE			0x02	/* mask falling edge */
-#define	PM_IRQF_MASK_RE			0x04	/* mask rising edge */
-#define	PM_IRQF_CLR			0x08	/* clear interrupt */
-#define	PM_IRQF_BITS_MASK		0x70
-#define	PM_IRQF_BITS_SHIFT		4
-#define	PM_IRQF_WRITE			0x80
-
-#define	PM_IRQF_MASK_ALL		(PM_IRQF_MASK_FE | \
-					PM_IRQF_MASK_RE)
-
-struct pm_irq_chip {
-	struct device		*dev;
-	spinlock_t		pm_irq_lock;
-	unsigned int		devirq;
-	unsigned int		irq_base;
-	unsigned int		num_irqs;
-	unsigned int		num_blocks;
-	unsigned int		num_masters;
-	u8			config[0];
-};
-
-static int pm8xxx_read_root_irq(const struct pm_irq_chip *chip, u8 *rp)
-{
-	return pm8xxx_readb(chip->dev, SSBI_REG_ADDR_IRQ_ROOT, rp);
-}
-
-static int pm8xxx_read_master_irq(const struct pm_irq_chip *chip, u8 m, u8 *bp)
-{
-	return pm8xxx_readb(chip->dev,
-			SSBI_REG_ADDR_IRQ_M_STATUS1 + m, bp);
-}
-
-static int pm8xxx_read_block_irq(struct pm_irq_chip *chip, u8 bp, u8 *ip)
-{
-	int	rc;
-
-	spin_lock(&chip->pm_irq_lock);
-	rc = pm8xxx_writeb(chip->dev, SSBI_REG_ADDR_IRQ_BLK_SEL, bp);
-	if (rc) {
-		pr_err("Failed Selecting Block %d rc=%d\n", bp, rc);
-		goto bail;
-	}
-
-	rc = pm8xxx_readb(chip->dev, SSBI_REG_ADDR_IRQ_IT_STATUS, ip);
-	if (rc)
-		pr_err("Failed Reading Status rc=%d\n", rc);
-bail:
-	spin_unlock(&chip->pm_irq_lock);
-	return rc;
-}
-
-static int pm8xxx_config_irq(struct pm_irq_chip *chip, u8 bp, u8 cp)
-{
-	int	rc;
-
-	spin_lock(&chip->pm_irq_lock);
-	rc = pm8xxx_writeb(chip->dev, SSBI_REG_ADDR_IRQ_BLK_SEL, bp);
-	if (rc) {
-		pr_err("Failed Selecting Block %d rc=%d\n", bp, rc);
-		goto bail;
-	}
-
-	cp |= PM_IRQF_WRITE;
-	rc = pm8xxx_writeb(chip->dev, SSBI_REG_ADDR_IRQ_CONFIG, cp);
-	if (rc)
-		pr_err("Failed Configuring IRQ rc=%d\n", rc);
-bail:
-	spin_unlock(&chip->pm_irq_lock);
-	return rc;
-}
-
-static int pm8xxx_irq_block_handler(struct pm_irq_chip *chip, int block)
-{
-	int pmirq, irq, i, ret = 0;
-	u8 bits;
-
-	ret = pm8xxx_read_block_irq(chip, block, &bits);
-	if (ret) {
-		pr_err("Failed reading %d block ret=%d", block, ret);
-		return ret;
-	}
-	if (!bits) {
-		pr_err("block bit set in master but no irqs: %d", block);
-		return 0;
-	}
-
-	/* Check IRQ bits */
-	for (i = 0; i < 8; i++) {
-		if (bits & (1 << i)) {
-			pmirq = block * 8 + i;
-			irq = pmirq + chip->irq_base;
-			generic_handle_irq(irq);
-		}
-	}
-	return 0;
-}
-
-static int pm8xxx_irq_master_handler(struct pm_irq_chip *chip, int master)
-{
-	u8 blockbits;
-	int block_number, i, ret = 0;
-
-	ret = pm8xxx_read_master_irq(chip, master, &blockbits);
-	if (ret) {
-		pr_err("Failed to read master %d ret=%d\n", master, ret);
-		return ret;
-	}
-	if (!blockbits) {
-		pr_err("master bit set in root but no blocks: %d", master);
-		return 0;
-	}
-
-	for (i = 0; i < 8; i++)
-		if (blockbits & (1 << i)) {
-			block_number = master * 8 + i;	/* block # */
-			ret |= pm8xxx_irq_block_handler(chip, block_number);
-		}
-	return ret;
-}
-
-static void pm8xxx_irq_handler(unsigned int irq, struct irq_desc *desc)
-{
-	struct pm_irq_chip *chip = irq_desc_get_handler_data(desc);
-	struct irq_chip *irq_chip = irq_desc_get_chip(desc);
-	u8	root;
-	int	i, ret, masters = 0;
-
-	ret = pm8xxx_read_root_irq(chip, &root);
-	if (ret) {
-		pr_err("Can't read root status ret=%d\n", ret);
-		return;
-	}
-
-	/* on pm8xxx series masters start from bit 1 of the root */
-	masters = root >> 1;
-
-	/* Read allowed masters for blocks. */
-	for (i = 0; i < chip->num_masters; i++)
-		if (masters & (1 << i))
-			pm8xxx_irq_master_handler(chip, i);
-
-	irq_chip->irq_ack(&desc->irq_data);
-}
-
-static void pm8xxx_irq_mask_ack(struct irq_data *d)
-{
-	struct pm_irq_chip *chip = irq_data_get_irq_chip_data(d);
-	unsigned int pmirq = d->irq - chip->irq_base;
-	int	master, irq_bit;
-	u8	block, config;
-
-	block = pmirq / 8;
-	master = block / 8;
-	irq_bit = pmirq % 8;
-
-	config = chip->config[pmirq] | PM_IRQF_MASK_ALL | PM_IRQF_CLR;
-	pm8xxx_config_irq(chip, block, config);
-}
-
-static void pm8xxx_irq_unmask(struct irq_data *d)
-{
-	struct pm_irq_chip *chip = irq_data_get_irq_chip_data(d);
-	unsigned int pmirq = d->irq - chip->irq_base;
-	int	master, irq_bit;
-	u8	block, config;
-
-	block = pmirq / 8;
-	master = block / 8;
-	irq_bit = pmirq % 8;
-
-	config = chip->config[pmirq];
-	pm8xxx_config_irq(chip, block, config);
-}
-
-static int pm8xxx_irq_set_type(struct irq_data *d, unsigned int flow_type)
-{
-	struct pm_irq_chip *chip = irq_data_get_irq_chip_data(d);
-	unsigned int pmirq = d->irq - chip->irq_base;
-	int master, irq_bit;
-	u8 block, config;
-
-	block = pmirq / 8;
-	master = block / 8;
-	irq_bit  = pmirq % 8;
-
-	chip->config[pmirq] = (irq_bit << PM_IRQF_BITS_SHIFT)
-							| PM_IRQF_MASK_ALL;
-	if (flow_type & (IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING)) {
-		if (flow_type & IRQF_TRIGGER_RISING)
-			chip->config[pmirq] &= ~PM_IRQF_MASK_RE;
-		if (flow_type & IRQF_TRIGGER_FALLING)
-			chip->config[pmirq] &= ~PM_IRQF_MASK_FE;
-	} else {
-		chip->config[pmirq] |= PM_IRQF_LVL_SEL;
-
-		if (flow_type & IRQF_TRIGGER_HIGH)
-			chip->config[pmirq] &= ~PM_IRQF_MASK_RE;
-		else
-			chip->config[pmirq] &= ~PM_IRQF_MASK_FE;
-	}
-
-	config = chip->config[pmirq] | PM_IRQF_CLR;
-	return pm8xxx_config_irq(chip, block, config);
-}
-
-static int pm8xxx_irq_set_wake(struct irq_data *d, unsigned int on)
-{
-	return 0;
-}
-
-static struct irq_chip pm8xxx_irq_chip = {
-	.name		= "pm8xxx",
-	.irq_mask_ack	= pm8xxx_irq_mask_ack,
-	.irq_unmask	= pm8xxx_irq_unmask,
-	.irq_set_type	= pm8xxx_irq_set_type,
-	.irq_set_wake	= pm8xxx_irq_set_wake,
-	.flags		= IRQCHIP_MASK_ON_SUSPEND,
-};
-
-/**
- * pm8xxx_get_irq_stat - get the status of the irq line
- * @chip: pointer to identify a pmic irq controller
- * @irq: the irq number
- *
- * The pm8xxx gpio and mpp rely on the interrupt block to read
- * the values on their pins. This function is to facilitate reading
- * the status of a gpio or an mpp line. The caller has to convert the
- * gpio number to irq number.
- *
- * RETURNS:
- * an int indicating the value read on that line
- */
-int pm8xxx_get_irq_stat(struct pm_irq_chip *chip, int irq)
-{
-	int pmirq, rc;
-	u8  block, bits, bit;
-	unsigned long flags;
-
-	if (chip == NULL || irq < chip->irq_base ||
-			irq >= chip->irq_base + chip->num_irqs)
-		return -EINVAL;
-
-	pmirq = irq - chip->irq_base;
-
-	block = pmirq / 8;
-	bit = pmirq % 8;
-
-	spin_lock_irqsave(&chip->pm_irq_lock, flags);
-
-	rc = pm8xxx_writeb(chip->dev, SSBI_REG_ADDR_IRQ_BLK_SEL, block);
-	if (rc) {
-		pr_err("Failed Selecting block irq=%d pmirq=%d blk=%d rc=%d\n",
-			irq, pmirq, block, rc);
-		goto bail_out;
-	}
-
-	rc = pm8xxx_readb(chip->dev, SSBI_REG_ADDR_IRQ_RT_STATUS, &bits);
-	if (rc) {
-		pr_err("Failed Configuring irq=%d pmirq=%d blk=%d rc=%d\n",
-			irq, pmirq, block, rc);
-		goto bail_out;
-	}
-
-	rc = (bits & (1 << bit)) ? 1 : 0;
-
-bail_out:
-	spin_unlock_irqrestore(&chip->pm_irq_lock, flags);
-
-	return rc;
-}
-EXPORT_SYMBOL_GPL(pm8xxx_get_irq_stat);
-
-struct pm_irq_chip *  pm8xxx_irq_init(struct device *dev,
-				const struct pm8xxx_irq_platform_data *pdata)
-{
-	struct pm_irq_chip  *chip;
-	int devirq, rc;
-	unsigned int pmirq;
-
-	if (!pdata) {
-		pr_err("No platform data\n");
-		return ERR_PTR(-EINVAL);
-	}
-
-	devirq = pdata->devirq;
-	if (devirq < 0) {
-		pr_err("missing devirq\n");
-		rc = devirq;
-		return ERR_PTR(-EINVAL);
-	}
-
-	chip = kzalloc(sizeof(struct pm_irq_chip)
-			+ sizeof(u8) * pdata->irq_cdata.nirqs, GFP_KERNEL);
-	if (!chip) {
-		pr_err("Cannot alloc pm_irq_chip struct\n");
-		return ERR_PTR(-EINVAL);
-	}
-
-	chip->dev = dev;
-	chip->devirq = devirq;
-	chip->irq_base = pdata->irq_base;
-	chip->num_irqs = pdata->irq_cdata.nirqs;
-	chip->num_blocks = DIV_ROUND_UP(chip->num_irqs, 8);
-	chip->num_masters = DIV_ROUND_UP(chip->num_blocks, 8);
-	spin_lock_init(&chip->pm_irq_lock);
-
-	for (pmirq = 0; pmirq < chip->num_irqs; pmirq++) {
-		irq_set_chip_and_handler(chip->irq_base + pmirq,
-				&pm8xxx_irq_chip,
-				handle_level_irq);
-		irq_set_chip_data(chip->irq_base + pmirq, chip);
-#ifdef CONFIG_ARM
-		set_irq_flags(chip->irq_base + pmirq, IRQF_VALID);
-#else
-		irq_set_noprobe(chip->irq_base + pmirq);
-#endif
-	}
-
-	irq_set_irq_type(devirq, pdata->irq_trigger_flag);
-	irq_set_handler_data(devirq, chip);
-	irq_set_chained_handler(devirq, pm8xxx_irq_handler);
-	set_irq_wake(devirq, 1);
-
-	return chip;
-}
-
-int pm8xxx_irq_exit(struct pm_irq_chip *chip)
-{
-	irq_set_chained_handler(chip->devirq, NULL);
-	kfree(chip);
-	return 0;
-}
diff --git a/include/linux/mfd/pm8xxx/irq.h b/include/linux/mfd/pm8xxx/irq.h
index f83d6b43ecbb..1a11b02383f0 100644
--- a/include/linux/mfd/pm8xxx/irq.h
+++ b/include/linux/mfd/pm8xxx/irq.h
@@ -33,27 +33,4 @@ struct pm8xxx_irq_platform_data {
 	int				irq_trigger_flag;
 };
 
-struct pm_irq_chip;
-
-#ifdef CONFIG_MFD_PM8XXX_IRQ
-int pm8xxx_get_irq_stat(struct pm_irq_chip *chip, int irq);
-struct pm_irq_chip *pm8xxx_irq_init(struct device *dev,
-				const struct pm8xxx_irq_platform_data *pdata);
-int pm8xxx_irq_exit(struct pm_irq_chip *chip);
-#else
-static inline int pm8xxx_get_irq_stat(struct pm_irq_chip *chip, int irq)
-{
-	return -ENXIO;
-}
-static inline struct pm_irq_chip *pm8xxx_irq_init(
-				const struct device *dev,
-				const struct pm8xxx_irq_platform_data *pdata)
-{
-	return ERR_PTR(-ENXIO);
-}
-static inline int pm8xxx_irq_exit(struct pm_irq_chip *chip)
-{
-	return -ENXIO;
-}
-#endif /* CONFIG_MFD_PM8XXX_IRQ */
 #endif /* __MFD_PM8XXX_IRQ_H */
-- 
cgit v1.2.3


From dc1a95ccaa1158948bbc6648d6dadc534a30ed92 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@codeaurora.org>
Date: Wed, 26 Feb 2014 10:59:21 -0800
Subject: mfd: pm8921: Migrate to irqdomains

Convert this driver to use irqdomains so that the PMIC's child
devices can be converted to devicetree.

Acked-by: Lee Jones <lee.jones@linaro.org>
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
---
 drivers/mfd/Kconfig               |   1 +
 drivers/mfd/pm8921-core.c         | 198 +++++++++++++++-----------------------
 include/linux/mfd/pm8xxx/irq.h    |  36 -------
 include/linux/mfd/pm8xxx/pm8921.h |  30 ------
 4 files changed, 76 insertions(+), 189 deletions(-)
 delete mode 100644 include/linux/mfd/pm8xxx/irq.h
 delete mode 100644 include/linux/mfd/pm8xxx/pm8921.h

(limited to 'include/linux')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 650c90f814ff..833d2c884437 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -479,6 +479,7 @@ config MFD_PM8XXX
 config MFD_PM8921_CORE
 	tristate "Qualcomm PM8921 PMIC chip"
 	depends on (ARCH_MSM || HEXAGON)
+	select IRQ_DOMAIN
 	select MFD_CORE
 	select MFD_PM8XXX
 	help
diff --git a/drivers/mfd/pm8921-core.c b/drivers/mfd/pm8921-core.c
index 9ddc31f7a71d..c25e7dae150b 100644
--- a/drivers/mfd/pm8921-core.c
+++ b/drivers/mfd/pm8921-core.c
@@ -17,15 +17,15 @@
 #include <linux/interrupt.h>
 #include <linux/irqchip/chained_irq.h>
 #include <linux/irq.h>
+#include <linux/irqdomain.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/ssbi.h>
+#include <linux/of_platform.h>
 #include <linux/mfd/core.h>
-#include <linux/mfd/pm8xxx/pm8921.h>
 #include <linux/mfd/pm8xxx/core.h>
-#include <linux/mfd/pm8xxx/irq.h>
 
 #define	SSBI_REG_ADDR_IRQ_BASE		0x1BB
 
@@ -53,11 +53,12 @@
 #define REG_HWREV		0x002  /* PMIC4 revision */
 #define REG_HWREV_2		0x0E8  /* PMIC4 revision 2 */
 
+#define PM8921_NR_IRQS		256
+
 struct pm_irq_chip {
 	struct device		*dev;
 	spinlock_t		pm_irq_lock;
-	unsigned int		devirq;
-	unsigned int		irq_base;
+	struct irq_domain	*irqdomain;
 	unsigned int		num_irqs;
 	unsigned int		num_blocks;
 	unsigned int		num_masters;
@@ -138,7 +139,7 @@ static int pm8xxx_irq_block_handler(struct pm_irq_chip *chip, int block)
 	for (i = 0; i < 8; i++) {
 		if (bits & (1 << i)) {
 			pmirq = block * 8 + i;
-			irq = pmirq + chip->irq_base;
+			irq = irq_find_mapping(chip->irqdomain, pmirq);
 			generic_handle_irq(irq);
 		}
 	}
@@ -197,12 +198,11 @@ static void pm8xxx_irq_handler(unsigned int irq, struct irq_desc *desc)
 static void pm8xxx_irq_mask_ack(struct irq_data *d)
 {
 	struct pm_irq_chip *chip = irq_data_get_irq_chip_data(d);
-	unsigned int pmirq = d->irq - chip->irq_base;
-	int	master, irq_bit;
+	unsigned int pmirq = irqd_to_hwirq(d);
+	int	irq_bit;
 	u8	block, config;
 
 	block = pmirq / 8;
-	master = block / 8;
 	irq_bit = pmirq % 8;
 
 	config = chip->config[pmirq] | PM_IRQF_MASK_ALL | PM_IRQF_CLR;
@@ -212,12 +212,11 @@ static void pm8xxx_irq_mask_ack(struct irq_data *d)
 static void pm8xxx_irq_unmask(struct irq_data *d)
 {
 	struct pm_irq_chip *chip = irq_data_get_irq_chip_data(d);
-	unsigned int pmirq = d->irq - chip->irq_base;
-	int	master, irq_bit;
+	unsigned int pmirq = irqd_to_hwirq(d);
+	int	irq_bit;
 	u8	block, config;
 
 	block = pmirq / 8;
-	master = block / 8;
 	irq_bit = pmirq % 8;
 
 	config = chip->config[pmirq];
@@ -227,12 +226,11 @@ static void pm8xxx_irq_unmask(struct irq_data *d)
 static int pm8xxx_irq_set_type(struct irq_data *d, unsigned int flow_type)
 {
 	struct pm_irq_chip *chip = irq_data_get_irq_chip_data(d);
-	unsigned int pmirq = d->irq - chip->irq_base;
-	int master, irq_bit;
+	unsigned int pmirq = irqd_to_hwirq(d);
+	int irq_bit;
 	u8 block, config;
 
 	block = pmirq / 8;
-	master = block / 8;
 	irq_bit  = pmirq % 8;
 
 	chip->config[pmirq] = (irq_bit << PM_IRQF_BITS_SHIFT)
@@ -287,12 +285,9 @@ static int pm8xxx_get_irq_stat(struct pm_irq_chip *chip, int irq)
 	int pmirq, rc;
 	u8  block, bits, bit;
 	unsigned long flags;
+	struct irq_data *irq_data = irq_get_irq_data(irq);
 
-	if (chip == NULL || irq < chip->irq_base ||
-			irq >= chip->irq_base + chip->num_irqs)
-		return -EINVAL;
-
-	pmirq = irq - chip->irq_base;
+	pmirq = irq_data->hwirq;
 
 	block = pmirq / 8;
 	bit = pmirq % 8;
@@ -321,67 +316,29 @@ bail_out:
 	return rc;
 }
 
-static struct pm_irq_chip *pm8xxx_irq_init(struct device *dev,
-				const struct pm8xxx_irq_platform_data *pdata)
-{
-	struct pm_irq_chip  *chip;
-	int devirq, rc;
-	unsigned int pmirq;
-
-	if (!pdata) {
-		pr_err("No platform data\n");
-		return ERR_PTR(-EINVAL);
-	}
+static struct lock_class_key pm8xxx_irq_lock_class;
 
-	devirq = pdata->devirq;
-	if (devirq < 0) {
-		pr_err("missing devirq\n");
-		rc = devirq;
-		return ERR_PTR(-EINVAL);
-	}
-
-	chip = kzalloc(sizeof(struct pm_irq_chip)
-			+ sizeof(u8) * pdata->irq_cdata.nirqs, GFP_KERNEL);
-	if (!chip) {
-		pr_err("Cannot alloc pm_irq_chip struct\n");
-		return ERR_PTR(-EINVAL);
-	}
-
-	chip->dev = dev;
-	chip->devirq = devirq;
-	chip->irq_base = pdata->irq_base;
-	chip->num_irqs = pdata->irq_cdata.nirqs;
-	chip->num_blocks = DIV_ROUND_UP(chip->num_irqs, 8);
-	chip->num_masters = DIV_ROUND_UP(chip->num_blocks, 8);
-	spin_lock_init(&chip->pm_irq_lock);
+static int pm8xxx_irq_domain_map(struct irq_domain *d, unsigned int irq,
+				   irq_hw_number_t hwirq)
+{
+	struct pm_irq_chip *chip = d->host_data;
 
-	for (pmirq = 0; pmirq < chip->num_irqs; pmirq++) {
-		irq_set_chip_and_handler(chip->irq_base + pmirq,
-				&pm8xxx_irq_chip,
-				handle_level_irq);
-		irq_set_chip_data(chip->irq_base + pmirq, chip);
+	irq_set_lockdep_class(irq, &pm8xxx_irq_lock_class);
+	irq_set_chip_and_handler(irq, &pm8xxx_irq_chip, handle_level_irq);
+	irq_set_chip_data(irq, chip);
 #ifdef CONFIG_ARM
-		set_irq_flags(chip->irq_base + pmirq, IRQF_VALID);
+	set_irq_flags(irq, IRQF_VALID);
 #else
-		irq_set_noprobe(chip->irq_base + pmirq);
+	irq_set_noprobe(irq);
 #endif
-	}
-
-	irq_set_irq_type(devirq, pdata->irq_trigger_flag);
-	irq_set_handler_data(devirq, chip);
-	irq_set_chained_handler(devirq, pm8xxx_irq_handler);
-	irq_set_irq_wake(devirq, 1);
-
-	return chip;
-}
-
-static int pm8xxx_irq_exit(struct pm_irq_chip *chip)
-{
-	irq_set_chained_handler(chip->devirq, NULL);
-	kfree(chip);
 	return 0;
 }
 
+static const struct irq_domain_ops pm8xxx_irq_domain_ops = {
+	.xlate = irq_domain_xlate_twocell,
+	.map = pm8xxx_irq_domain_map,
+};
+
 static int pm8921_readb(const struct device *dev, u16 addr, u8 *val)
 {
 	const struct pm8xxx_drvdata *pm8921_drvdata = dev_get_drvdata(dev);
@@ -432,42 +389,19 @@ static struct pm8xxx_drvdata pm8921_drvdata = {
 	.pmic_read_irq_stat	= pm8921_read_irq_stat,
 };
 
-static int pm8921_add_subdevices(const struct pm8921_platform_data
-					   *pdata,
-					   struct pm8921 *pmic,
-					   u32 rev)
-{
-	int ret = 0, irq_base = 0;
-	struct pm_irq_chip *irq_chip;
-
-	if (pdata->irq_pdata) {
-		pdata->irq_pdata->irq_cdata.nirqs = PM8921_NR_IRQS;
-		pdata->irq_pdata->irq_cdata.rev = rev;
-		irq_base = pdata->irq_pdata->irq_base;
-		irq_chip = pm8xxx_irq_init(pmic->dev, pdata->irq_pdata);
-
-		if (IS_ERR(irq_chip)) {
-			pr_err("Failed to init interrupts ret=%ld\n",
-					PTR_ERR(irq_chip));
-			return PTR_ERR(irq_chip);
-		}
-		pmic->irq_chip = irq_chip;
-	}
-	return ret;
-}
-
 static int pm8921_probe(struct platform_device *pdev)
 {
-	const struct pm8921_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	struct pm8921 *pmic;
 	int rc;
 	u8 val;
+	unsigned int irq;
 	u32 rev;
+	struct pm_irq_chip *chip;
+	unsigned int nirqs = PM8921_NR_IRQS;
 
-	if (!pdata) {
-		pr_err("missing platform data\n");
-		return -EINVAL;
-	}
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
 
 	pmic = devm_kzalloc(&pdev->dev, sizeof(struct pm8921), GFP_KERNEL);
 	if (!pmic) {
@@ -498,37 +432,55 @@ static int pm8921_probe(struct platform_device *pdev)
 	pm8921_drvdata.pm_chip_data = pmic;
 	platform_set_drvdata(pdev, &pm8921_drvdata);
 
-	rc = pm8921_add_subdevices(pdata, pmic, rev);
+	chip = devm_kzalloc(&pdev->dev, sizeof(*chip) +
+					sizeof(chip->config[0]) * nirqs,
+					GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	pmic->irq_chip = chip;
+	chip->dev = &pdev->dev;
+	chip->num_irqs = nirqs;
+	chip->num_blocks = DIV_ROUND_UP(chip->num_irqs, 8);
+	chip->num_masters = DIV_ROUND_UP(chip->num_blocks, 8);
+	spin_lock_init(&chip->pm_irq_lock);
+
+	chip->irqdomain = irq_domain_add_linear(pdev->dev.of_node, nirqs,
+						&pm8xxx_irq_domain_ops,
+						chip);
+	if (!chip->irqdomain)
+		return -ENODEV;
+
+	irq_set_handler_data(irq, chip);
+	irq_set_chained_handler(irq, pm8xxx_irq_handler);
+	irq_set_irq_wake(irq, 1);
+
+	rc = of_platform_populate(pdev->dev.of_node, NULL, NULL, &pdev->dev);
 	if (rc) {
-		pr_err("Cannot add subdevices rc=%d\n", rc);
-		goto err;
+		irq_set_chained_handler(irq, NULL);
+		irq_set_handler_data(irq, NULL);
+		irq_domain_remove(chip->irqdomain);
 	}
 
-	/* gpio might not work if no irq device is found */
-	WARN_ON(pmic->irq_chip == NULL);
+	return rc;
+}
 
+static int pm8921_remove_child(struct device *dev, void *unused)
+{
+	platform_device_unregister(to_platform_device(dev));
 	return 0;
-
-err:
-	mfd_remove_devices(pmic->dev);
-	return rc;
 }
 
 static int pm8921_remove(struct platform_device *pdev)
 {
-	struct pm8xxx_drvdata *drvdata;
-	struct pm8921 *pmic = NULL;
-
-	drvdata = platform_get_drvdata(pdev);
-	if (drvdata)
-		pmic = drvdata->pm_chip_data;
-	if (pmic) {
-		mfd_remove_devices(pmic->dev);
-		if (pmic->irq_chip) {
-			pm8xxx_irq_exit(pmic->irq_chip);
-			pmic->irq_chip = NULL;
-		}
-	}
+	int irq = platform_get_irq(pdev, 0);
+	struct pm8921 *pmic = pm8921_drvdata.pm_chip_data;
+	struct pm_irq_chip *chip = pmic->irq_chip;
+
+	device_for_each_child(&pdev->dev, NULL, pm8921_remove_child);
+	irq_set_chained_handler(irq, NULL);
+	irq_set_handler_data(irq, NULL);
+	irq_domain_remove(chip->irqdomain);
 
 	return 0;
 }
diff --git a/include/linux/mfd/pm8xxx/irq.h b/include/linux/mfd/pm8xxx/irq.h
deleted file mode 100644
index 1a11b02383f0..000000000000
--- a/include/linux/mfd/pm8xxx/irq.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/*
- * Copyright (c) 2011, Code Aurora Forum. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-/*
- * Qualcomm PMIC irq 8xxx driver header file
- *
- */
-
-#ifndef __MFD_PM8XXX_IRQ_H
-#define __MFD_PM8XXX_IRQ_H
-
-#include <linux/errno.h>
-#include <linux/err.h>
-
-struct pm8xxx_irq_core_data {
-	u32		rev;
-	int		nirqs;
-};
-
-struct pm8xxx_irq_platform_data {
-	int				irq_base;
-	struct pm8xxx_irq_core_data	irq_cdata;
-	int				devirq;
-	int				irq_trigger_flag;
-};
-
-#endif /* __MFD_PM8XXX_IRQ_H */
diff --git a/include/linux/mfd/pm8xxx/pm8921.h b/include/linux/mfd/pm8xxx/pm8921.h
deleted file mode 100644
index 00fa3de7659d..000000000000
--- a/include/linux/mfd/pm8xxx/pm8921.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * Copyright (c) 2011, Code Aurora Forum. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-/*
- * Qualcomm PMIC 8921 driver header file
- *
- */
-
-#ifndef __MFD_PM8921_H
-#define __MFD_PM8921_H
-
-#include <linux/mfd/pm8xxx/irq.h>
-
-#define PM8921_NR_IRQS		256
-
-struct pm8921_platform_data {
-	int					irq_base;
-	struct pm8xxx_irq_platform_data		*irq_pdata;
-};
-
-#endif
-- 
cgit v1.2.3


From 559c04f6f116075a1ebead411666c7ab47dcc7fe Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@codeaurora.org>
Date: Wed, 26 Feb 2014 10:59:22 -0800
Subject: mfd: ssbi: Add regmap read/write helpers

Add read and write helper functions that the pm8921-core driver
can use to read and write ssbi registers via a "no-bus" regmap.

Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/ssbi.h | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ssbi.h b/include/linux/ssbi.h
index bcbb642a7641..087b08a4d333 100644
--- a/include/linux/ssbi.h
+++ b/include/linux/ssbi.h
@@ -20,4 +20,24 @@
 int ssbi_write(struct device *dev, u16 addr, const u8 *buf, int len);
 int ssbi_read(struct device *dev, u16 addr, u8 *buf, int len);
 
+static inline int
+ssbi_reg_read(void *context, unsigned int reg, unsigned int *val)
+{
+	int ret;
+	u8 v;
+
+	ret = ssbi_read(context, reg, &v, 1);
+	if (!ret)
+		*val = v;
+
+	return ret;
+}
+
+static inline int
+ssbi_reg_write(void *context, unsigned int reg, unsigned int val)
+{
+	u8 v = val;
+	return ssbi_write(context, reg, &v, 1);
+}
+
 #endif
-- 
cgit v1.2.3


From 9fc2b9ca99428b54e6bbfd2d7bf0ccc1c594f1f5 Mon Sep 17 00:00:00 2001
From: "Opensource [Steve Twiss]" <stwiss.opensource@diasemi.com>
Date: Thu, 6 Mar 2014 16:40:02 +0000
Subject: mfd: da9063: Upgrade of register definitions to support production
 silicon

This patch updates the register definitions for DA9063 to support the
production silicon variant code ID (0x5). These changes are not backwards
compatible with the previous register definitions and can only be used
with the production variant of DA9063.

Signed-off-by: Opensource [Steve Twiss] <stwiss.opensource@diasemi.com>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 include/linux/mfd/da9063/registers.h | 120 ++++++++++++++++++-----------------
 1 file changed, 62 insertions(+), 58 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mfd/da9063/registers.h b/include/linux/mfd/da9063/registers.h
index 5834813fb5f3..09a85c699da1 100644
--- a/include/linux/mfd/da9063/registers.h
+++ b/include/linux/mfd/da9063/registers.h
@@ -17,11 +17,7 @@
 #define	_DA9063_REG_H
 
 #define DA9063_I2C_PAGE_SEL_SHIFT	1
-
 #define	DA9063_EVENT_REG_NUM		4
-#define	DA9210_EVENT_REG_NUM		2
-#define	DA9063_EXT_EVENT_REG_NUM	(DA9063_EVENT_REG_NUM + \
-						DA9210_EVENT_REG_NUM)
 
 /* Page selection I2C or SPI always in the begining of any page. */
 /* Page 0 : I2C access 0x000 - 0x0FF	SPI access 0x000 - 0x07F */
@@ -61,9 +57,9 @@
 #define	DA9063_REG_GPIO_10_11		0x1A
 #define	DA9063_REG_GPIO_12_13		0x1B
 #define	DA9063_REG_GPIO_14_15		0x1C
-#define	DA9063_REG_GPIO_MODE_0_7	0x1D
-#define	DA9063_REG_GPIO_MODE_8_15	0x1E
-#define	DA9063_REG_GPIO_SWITCH_CONT	0x1F
+#define	DA9063_REG_GPIO_MODE0_7		0x1D
+#define	DA9063_REG_GPIO_MODE8_15	0x1E
+#define	DA9063_REG_SWITCH_CONT		0x1F
 
 /* Regulator Control Registers */
 #define	DA9063_REG_BCORE2_CONT		0x20
@@ -83,7 +79,7 @@
 #define	DA9063_REG_LDO9_CONT		0x2E
 #define	DA9063_REG_LDO10_CONT		0x2F
 #define	DA9063_REG_LDO11_CONT		0x30
-#define	DA9063_REG_VIB			0x31
+#define	DA9063_REG_SUPPLIES		0x31
 #define	DA9063_REG_DVC_1		0x32
 #define	DA9063_REG_DVC_2		0x33
 
@@ -97,9 +93,9 @@
 #define	DA9063_REG_ADCIN1_RES		0x3A
 #define	DA9063_REG_ADCIN2_RES		0x3B
 #define	DA9063_REG_ADCIN3_RES		0x3C
-#define	DA9063_REG_MON1_RES		0x3D
-#define	DA9063_REG_MON2_RES		0x3E
-#define	DA9063_REG_MON3_RES		0x3F
+#define	DA9063_REG_MON_A8_RES		0x3D
+#define	DA9063_REG_MON_A9_RES		0x3E
+#define	DA9063_REG_MON_A10_RES		0x3F
 
 /* RTC Calendar and Alarm Registers */
 #define	DA9063_REG_COUNT_S		0x40
@@ -108,15 +104,16 @@
 #define	DA9063_REG_COUNT_D		0x43
 #define	DA9063_REG_COUNT_MO		0x44
 #define	DA9063_REG_COUNT_Y		0x45
-#define	DA9063_REG_ALARM_MI		0x46
-#define	DA9063_REG_ALARM_H		0x47
-#define	DA9063_REG_ALARM_D		0x48
-#define	DA9063_REG_ALARM_MO		0x49
-#define	DA9063_REG_ALARM_Y		0x4A
-#define	DA9063_REG_SECOND_A		0x4B
-#define	DA9063_REG_SECOND_B		0x4C
-#define	DA9063_REG_SECOND_C		0x4D
-#define	DA9063_REG_SECOND_D		0x4E
+#define	DA9063_REG_ALARM_S		0x46
+#define	DA9063_REG_ALARM_MI		0x47
+#define	DA9063_REG_ALARM_H		0x48
+#define	DA9063_REG_ALARM_D		0x49
+#define	DA9063_REG_ALARM_MO		0x4A
+#define	DA9063_REG_ALARM_Y		0x4B
+#define	DA9063_REG_SECOND_A		0x4C
+#define	DA9063_REG_SECOND_B		0x4D
+#define	DA9063_REG_SECOND_C		0x4E
+#define	DA9063_REG_SECOND_D		0x4F
 
 /* Sequencer Control Registers */
 #define	DA9063_REG_SEQ			0x81
@@ -226,35 +223,37 @@
 #define	DA9063_REG_CONFIG_J		0x10F
 #define	DA9063_REG_CONFIG_K		0x110
 #define	DA9063_REG_CONFIG_L		0x111
-#define	DA9063_REG_MON_REG_1		0x112
-#define	DA9063_REG_MON_REG_2		0x113
-#define	DA9063_REG_MON_REG_3		0x114
-#define	DA9063_REG_MON_REG_4		0x115
-#define	DA9063_REG_MON_REG_5		0x116
-#define	DA9063_REG_MON_REG_6		0x117
-#define	DA9063_REG_TRIM_CLDR		0x118
-
+#define	DA9063_REG_CONFIG_M		0x112
+#define	DA9063_REG_CONFIG_N		0x113
+
+#define	DA9063_REG_MON_REG_1		0x114
+#define	DA9063_REG_MON_REG_2		0x115
+#define	DA9063_REG_MON_REG_3		0x116
+#define	DA9063_REG_MON_REG_4		0x117
+#define	DA9063_REG_MON_REG_5		0x11E
+#define	DA9063_REG_MON_REG_6		0x11F
+#define	DA9063_REG_TRIM_CLDR		0x120
 /* General Purpose Registers */
-#define	DA9063_REG_GP_ID_0		0x119
-#define	DA9063_REG_GP_ID_1		0x11A
-#define	DA9063_REG_GP_ID_2		0x11B
-#define	DA9063_REG_GP_ID_3		0x11C
-#define	DA9063_REG_GP_ID_4		0x11D
-#define	DA9063_REG_GP_ID_5		0x11E
-#define	DA9063_REG_GP_ID_6		0x11F
-#define	DA9063_REG_GP_ID_7		0x120
-#define	DA9063_REG_GP_ID_8		0x121
-#define	DA9063_REG_GP_ID_9		0x122
-#define	DA9063_REG_GP_ID_10		0x123
-#define	DA9063_REG_GP_ID_11		0x124
-#define	DA9063_REG_GP_ID_12		0x125
-#define	DA9063_REG_GP_ID_13		0x126
-#define	DA9063_REG_GP_ID_14		0x127
-#define	DA9063_REG_GP_ID_15		0x128
-#define	DA9063_REG_GP_ID_16		0x129
-#define	DA9063_REG_GP_ID_17		0x12A
-#define	DA9063_REG_GP_ID_18		0x12B
-#define	DA9063_REG_GP_ID_19		0x12C
+#define	DA9063_REG_GP_ID_0		0x121
+#define	DA9063_REG_GP_ID_1		0x122
+#define	DA9063_REG_GP_ID_2		0x123
+#define	DA9063_REG_GP_ID_3		0x124
+#define	DA9063_REG_GP_ID_4		0x125
+#define	DA9063_REG_GP_ID_5		0x126
+#define	DA9063_REG_GP_ID_6		0x127
+#define	DA9063_REG_GP_ID_7		0x128
+#define	DA9063_REG_GP_ID_8		0x129
+#define	DA9063_REG_GP_ID_9		0x12A
+#define	DA9063_REG_GP_ID_10		0x12B
+#define	DA9063_REG_GP_ID_11		0x12C
+#define	DA9063_REG_GP_ID_12		0x12D
+#define	DA9063_REG_GP_ID_13		0x12E
+#define	DA9063_REG_GP_ID_14		0x12F
+#define	DA9063_REG_GP_ID_15		0x130
+#define	DA9063_REG_GP_ID_16		0x131
+#define	DA9063_REG_GP_ID_17		0x132
+#define	DA9063_REG_GP_ID_18		0x133
+#define	DA9063_REG_GP_ID_19		0x134
 
 /* Chip ID and variant */
 #define	DA9063_REG_CHIP_ID		0x181
@@ -405,8 +404,10 @@
 /* DA9063_REG_CONTROL_B (addr=0x0F) */
 #define	DA9063_CHG_SEL				0x01
 #define	DA9063_WATCHDOG_PD			0x02
+#define	DA9063_RESET_BLINKING			0x04
 #define	DA9063_NRES_MODE			0x08
 #define	DA9063_NONKEY_LOCK			0x10
+#define	DA9063_BUCK_SLOWSTART			0x80
 
 /* DA9063_REG_CONTROL_C (addr=0x10) */
 #define	DA9063_DEBOUNCING_MASK			0x07
@@ -466,6 +467,7 @@
 #define	DA9063_GPADC_PAUSE			0x02
 #define	DA9063_PMIF_DIS				0x04
 #define	DA9063_HS2WIRE_DIS			0x08
+#define	DA9063_CLDR_PAUSE			0x10
 #define	DA9063_BBAT_DIS				0x20
 #define	DA9063_OUT_32K_PAUSE			0x40
 #define	DA9063_PMCONT_DIS			0x80
@@ -660,7 +662,7 @@
 #define		DA9063_GPIO15_TYPE_GPO		0x04
 #define	DA9063_GPIO15_NO_WAKEUP			0x80
 
-/* DA9063_REG_GPIO_MODE_0_7 (addr=0x1D) */
+/* DA9063_REG_GPIO_MODE0_7 (addr=0x1D) */
 #define	DA9063_GPIO0_MODE			0x01
 #define	DA9063_GPIO1_MODE			0x02
 #define	DA9063_GPIO2_MODE			0x04
@@ -670,7 +672,7 @@
 #define	DA9063_GPIO6_MODE			0x40
 #define	DA9063_GPIO7_MODE			0x80
 
-/* DA9063_REG_GPIO_MODE_8_15 (addr=0x1E) */
+/* DA9063_REG_GPIO_MODE8_15 (addr=0x1E) */
 #define	DA9063_GPIO8_MODE			0x01
 #define	DA9063_GPIO9_MODE			0x02
 #define	DA9063_GPIO10_MODE			0x04
@@ -702,12 +704,12 @@
 #define		DA9063_SWITCH_SR_5MV		0x10
 #define		DA9063_SWITCH_SR_10MV		0x20
 #define		DA9063_SWITCH_SR_50MV		0x30
-#define	DA9063_SWITCH_SR_DIS			0x40
+#define	DA9063_CORE_SW_INTERNAL			0x40
 #define	DA9063_CP_EN_MODE			0x80
 
 /* DA9063_REGL_Bxxxx_CONT common bits (addr=0x20-0x25) */
 #define	DA9063_BUCK_EN				0x01
-#define DA9063_BUCK_GPI_MASK			0x06
+#define	DA9063_BUCK_GPI_MASK			0x06
 #define		DA9063_BUCK_GPI_OFF		0x00
 #define		DA9063_BUCK_GPI_GPIO1		0x02
 #define		DA9063_BUCK_GPI_GPIO2		0x04
@@ -841,25 +843,27 @@
 #define DA9063_COUNT_YEAR_MASK			0x3F
 #define DA9063_MONITOR				0x40
 
-/* DA9063_REG_ALARM_MI (addr=0x46) */
+/* DA9063_REG_ALARM_S (addr=0x46) */
+#define DA9063_ALARM_S_MASK			0x3F
 #define DA9063_ALARM_STATUS_ALARM		0x80
 #define DA9063_ALARM_STATUS_TICK		0x40
+/* DA9063_REG_ALARM_MI (addr=0x47) */
 #define DA9063_ALARM_MIN_MASK			0x3F
 
-/* DA9063_REG_ALARM_H (addr=0x47) */
+/* DA9063_REG_ALARM_H (addr=0x48) */
 #define DA9063_ALARM_HOUR_MASK			0x1F
 
-/* DA9063_REG_ALARM_D (addr=0x48) */
+/* DA9063_REG_ALARM_D (addr=0x49) */
 #define DA9063_ALARM_DAY_MASK			0x1F
 
-/* DA9063_REG_ALARM_MO (addr=0x49) */
+/* DA9063_REG_ALARM_MO (addr=0x4A) */
 #define DA9063_TICK_WAKE			0x20
 #define DA9063_TICK_TYPE			0x10
 #define		DA9063_TICK_TYPE_SEC		0x00
 #define		DA9063_TICK_TYPE_MIN		0x10
 #define DA9063_ALARM_MONTH_MASK			0x0F
 
-/* DA9063_REG_ALARM_Y (addr=0x4A) */
+/* DA9063_REG_ALARM_Y (addr=0x4B) */
 #define DA9063_TICK_ON				0x80
 #define DA9063_ALARM_ON				0x40
 #define DA9063_ALARM_YEAR_MASK			0x3F
@@ -906,7 +910,7 @@
 
 /* DA9063_REG_Bxxxx_CFG common bits (addr=0x9D-0xA2) */
 #define DA9063_BUCK_FB_MASK			0x07
-#define DA9063_BUCK_PD_DIS_SHIFT		5
+#define DA9063_BUCK_PD_DIS_MASK		0x20
 #define DA9063_BUCK_MODE_MASK			0xC0
 #define		DA9063_BUCK_MODE_MANUAL		0x00
 #define		DA9063_BUCK_MODE_SLEEP		0x40
-- 
cgit v1.2.3


From 037b60f2ca9403d02cbee60ad0a10f3806f9dc4b Mon Sep 17 00:00:00 2001
From: Matt Porter <mporter@linaro.org>
Date: Tue, 11 Mar 2014 19:33:54 -0400
Subject: mfd: Add bcm590xx pmu driver

Add a driver for the BCM590xx PMU multi-function devices. The driver
initially supports regmap initialization and instantiation of the
voltage regulator device function of the PMU.

Signed-off-by: Matt Porter <mporter@linaro.org>
Reviewed-by: Tim Kryger <tim.kryger@linaro.org>
Reviewed-by: Markus Mayer <markus.mayer@linaro.org>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/Kconfig          |  8 ++++
 drivers/mfd/Makefile         |  1 +
 drivers/mfd/bcm590xx.c       | 93 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/bcm590xx.h | 31 +++++++++++++++
 4 files changed, 133 insertions(+)
 create mode 100644 drivers/mfd/bcm590xx.c
 create mode 100644 include/linux/mfd/bcm590xx.h

(limited to 'include/linux')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index d22ca0fc873f..7587c9e1a519 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -59,6 +59,14 @@ config MFD_AAT2870_CORE
 	  additional drivers must be enabled in order to use the
 	  functionality of the device.
 
+config MFD_BCM590XX
+	tristate "Broadcom BCM590xx PMUs"
+	select MFD_CORE
+	select REGMAP_I2C
+	depends on I2C
+	help
+	  Support for the BCM590xx PMUs from Broadcom
+
 config MFD_CROS_EC
 	tristate "ChromeOS Embedded Controller"
 	select MFD_CORE
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 89a7951503ca..23835dfa615c 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -8,6 +8,7 @@ obj-$(CONFIG_MFD_88PM800)	+= 88pm800.o 88pm80x.o
 obj-$(CONFIG_MFD_88PM805)	+= 88pm805.o 88pm80x.o
 obj-$(CONFIG_MFD_SM501)		+= sm501.o
 obj-$(CONFIG_MFD_ASIC3)		+= asic3.o tmio_core.o
+obj-$(CONFIG_MFD_BCM590XX)	+= bcm590xx.o
 obj-$(CONFIG_MFD_CROS_EC)	+= cros_ec.o
 obj-$(CONFIG_MFD_CROS_EC_I2C)	+= cros_ec_i2c.o
 obj-$(CONFIG_MFD_CROS_EC_SPI)	+= cros_ec_spi.o
diff --git a/drivers/mfd/bcm590xx.c b/drivers/mfd/bcm590xx.c
new file mode 100644
index 000000000000..926a57e4d533
--- /dev/null
+++ b/drivers/mfd/bcm590xx.c
@@ -0,0 +1,93 @@
+/*
+ * Broadcom BCM590xx PMU
+ *
+ * Copyright 2014 Linaro Limited
+ * Author: Matt Porter <mporter@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under  the terms of the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/mfd/bcm590xx.h>
+#include <linux/mfd/core.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+static const struct mfd_cell bcm590xx_devs[] = {
+	{
+		.name = "bcm590xx-vregs",
+	},
+};
+
+static const struct regmap_config bcm590xx_regmap_config = {
+	.reg_bits	= 8,
+	.val_bits	= 8,
+	.max_register	= BCM590XX_MAX_REGISTER,
+	.cache_type	= REGCACHE_RBTREE,
+};
+
+static int bcm590xx_i2c_probe(struct i2c_client *i2c,
+			      const struct i2c_device_id *id)
+{
+	struct bcm590xx *bcm590xx;
+	int ret;
+
+	bcm590xx = devm_kzalloc(&i2c->dev, sizeof(*bcm590xx), GFP_KERNEL);
+	if (!bcm590xx)
+		return -ENOMEM;
+
+	i2c_set_clientdata(i2c, bcm590xx);
+	bcm590xx->dev = &i2c->dev;
+	bcm590xx->i2c_client = i2c;
+
+	bcm590xx->regmap = devm_regmap_init_i2c(i2c, &bcm590xx_regmap_config);
+	if (IS_ERR(bcm590xx->regmap)) {
+		ret = PTR_ERR(bcm590xx->regmap);
+		dev_err(&i2c->dev, "regmap initialization failed: %d\n", ret);
+		return ret;
+	}
+
+	ret = mfd_add_devices(&i2c->dev, -1, bcm590xx_devs,
+			      ARRAY_SIZE(bcm590xx_devs), NULL, 0, NULL);
+	if (ret < 0)
+		dev_err(&i2c->dev, "failed to add sub-devices: %d\n", ret);
+
+	return ret;
+}
+
+static const struct of_device_id bcm590xx_of_match[] = {
+	{ .compatible = "brcm,bcm59056" },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, bcm590xx_of_match);
+
+static const struct i2c_device_id bcm590xx_i2c_id[] = {
+	{ "bcm59056" },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, bcm590xx_i2c_id);
+
+static struct i2c_driver bcm590xx_i2c_driver = {
+	.driver = {
+		   .name = "bcm590xx",
+		   .owner = THIS_MODULE,
+		   .of_match_table = of_match_ptr(bcm590xx_of_match),
+	},
+	.probe = bcm590xx_i2c_probe,
+	.id_table = bcm590xx_i2c_id,
+};
+module_i2c_driver(bcm590xx_i2c_driver);
+
+MODULE_AUTHOR("Matt Porter <mporter@linaro.org>");
+MODULE_DESCRIPTION("BCM590xx multi-function driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:bcm590xx");
diff --git a/include/linux/mfd/bcm590xx.h b/include/linux/mfd/bcm590xx.h
new file mode 100644
index 000000000000..434df2d4e587
--- /dev/null
+++ b/include/linux/mfd/bcm590xx.h
@@ -0,0 +1,31 @@
+/*
+ * Broadcom BCM590xx PMU
+ *
+ * Copyright 2014 Linaro Limited
+ * Author: Matt Porter <mporter@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under  the terms of the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ */
+
+#ifndef __LINUX_MFD_BCM590XX_H
+#define __LINUX_MFD_BCM590XX_H
+
+#include <linux/device.h>
+#include <linux/i2c.h>
+#include <linux/regmap.h>
+
+/* max register address */
+#define BCM590XX_MAX_REGISTER	0xe7
+
+struct bcm590xx {
+	struct device *dev;
+	struct i2c_client *i2c_client;
+	struct regmap *regmap;
+	unsigned int id;
+};
+
+#endif /*  __LINUX_MFD_BCM590XX_H */
-- 
cgit v1.2.3


From eb71d4dec4a5e010e34b9d7afdb5af41884c388e Mon Sep 17 00:00:00 2001
From: Peter Tyser <ptyser@xes-inc.com>
Date: Mon, 10 Mar 2014 16:34:54 -0500
Subject: mfd: lpc_ich: Add support for iTCO v3

Some newer Atom CPUs, eg Avoton and Bay Trail, use slightly different
register layouts for the iTCO than the current v1 and v2 iTCO.
Differences from previous iTCO versions include:
- The ACPI space is enabled in the "ACPI base address" register instead
  of the "ACPI control register"

- The "no reboot" functionality is set in the "Power Management
  Configuration" register instead of the "General Control and Status"
  (GCS) register or PCI configuration space.

- The "ACPI Control Register" is not present on v3.  The "Power
  Management Configuration Base Address" register resides at the same
  address is Avoton/Bay Trail.

To differentiate these newer chipsets create a new v3 iTCO version and
update the MFD driver to support them.

Signed-off-by: Peter Tyser <ptyser@xes-inc.com>
Tested-by: Rajat Jain <rajatjain@juniper.net>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Lee Jones <lee.jones@linaro.org>
---
 drivers/mfd/lpc_ich.c       | 81 +++++++++++++++++++++++++++++++++++++--------
 include/linux/mfd/lpc_ich.h |  8 ++---
 2 files changed, 71 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mfd/lpc_ich.c b/drivers/mfd/lpc_ich.c
index b24bae2bcdea..c0683370abbf 100644
--- a/drivers/mfd/lpc_ich.c
+++ b/drivers/mfd/lpc_ich.c
@@ -71,9 +71,11 @@
 #define ACPIBASE_GPE_END	0x2f
 #define ACPIBASE_SMI_OFF	0x30
 #define ACPIBASE_SMI_END	0x33
+#define ACPIBASE_PMC_OFF	0x08
+#define ACPIBASE_PMC_END	0x0c
 #define ACPIBASE_TCO_OFF	0x60
 #define ACPIBASE_TCO_END	0x7f
-#define ACPICTRL		0x44
+#define ACPICTRL_PMCBASE	0x44
 
 #define ACPIBASE_GCS_OFF	0x3410
 #define ACPIBASE_GCS_END	0x3414
@@ -93,11 +95,12 @@ struct lpc_ich_priv {
 	int chipset;
 
 	int abase;		/* ACPI base */
-	int actrl;		/* ACPI control or PMC base */
+	int actrl_pbase;	/* ACPI control or PMC base */
 	int gbase;		/* GPIO base */
 	int gctrl;		/* GPIO control */
 
-	int actrl_save;		/* Cached ACPI control base value */
+	int abase_save;		/* Cached ACPI base value */
+	int actrl_pbase_save;		/* Cached ACPI control or PMC base value */
 	int gctrl_save;		/* Cached GPIO control value */
 };
 
@@ -110,7 +113,7 @@ static struct resource wdt_ich_res[] = {
 	{
 		.flags = IORESOURCE_IO,
 	},
-	/* GCS */
+	/* GCS or PMC */
 	{
 		.flags = IORESOURCE_MEM,
 	},
@@ -742,9 +745,15 @@ static void lpc_ich_restore_config_space(struct pci_dev *dev)
 {
 	struct lpc_ich_priv *priv = pci_get_drvdata(dev);
 
-	if (priv->actrl_save >= 0) {
-		pci_write_config_byte(dev, priv->actrl, priv->actrl_save);
-		priv->actrl_save = -1;
+	if (priv->abase_save >= 0) {
+		pci_write_config_byte(dev, priv->abase, priv->abase_save);
+		priv->abase_save = -1;
+	}
+
+	if (priv->actrl_pbase_save >= 0) {
+		pci_write_config_byte(dev, priv->actrl_pbase,
+			priv->actrl_pbase_save);
+		priv->actrl_pbase_save = -1;
 	}
 
 	if (priv->gctrl_save >= 0) {
@@ -758,9 +767,26 @@ static void lpc_ich_enable_acpi_space(struct pci_dev *dev)
 	struct lpc_ich_priv *priv = pci_get_drvdata(dev);
 	u8 reg_save;
 
-	pci_read_config_byte(dev, priv->actrl, &reg_save);
-	pci_write_config_byte(dev, priv->actrl, reg_save | 0x80);
-	priv->actrl_save = reg_save;
+	switch (lpc_chipset_info[priv->chipset].iTCO_version) {
+	case 3:
+		/*
+		 * Some chipsets (eg Avoton) enable the ACPI space in the
+		 * ACPI BASE register.
+		 */
+		pci_read_config_byte(dev, priv->abase, &reg_save);
+		pci_write_config_byte(dev, priv->abase, reg_save | 0x2);
+		priv->abase_save = reg_save;
+		break;
+	default:
+		/*
+		 * Most chipsets enable the ACPI space in the ACPI control
+		 * register.
+		 */
+		pci_read_config_byte(dev, priv->actrl_pbase, &reg_save);
+		pci_write_config_byte(dev, priv->actrl_pbase, reg_save | 0x80);
+		priv->actrl_pbase_save = reg_save;
+		break;
+	}
 }
 
 static void lpc_ich_enable_gpio_space(struct pci_dev *dev)
@@ -773,6 +799,17 @@ static void lpc_ich_enable_gpio_space(struct pci_dev *dev)
 	priv->gctrl_save = reg_save;
 }
 
+static void lpc_ich_enable_pmc_space(struct pci_dev *dev)
+{
+	struct lpc_ich_priv *priv = pci_get_drvdata(dev);
+	u8 reg_save;
+
+	pci_read_config_byte(dev, priv->actrl_pbase, &reg_save);
+	pci_write_config_byte(dev, priv->actrl_pbase, reg_save | 0x2);
+
+	priv->actrl_pbase_save = reg_save;
+}
+
 static void lpc_ich_finalize_cell(struct pci_dev *dev, struct mfd_cell *cell)
 {
 	struct lpc_ich_priv *priv = pci_get_drvdata(dev);
@@ -910,14 +947,20 @@ static int lpc_ich_init_wdt(struct pci_dev *dev)
 	lpc_ich_enable_acpi_space(dev);
 
 	/*
+	 * iTCO v2:
 	 * Get the Memory-Mapped GCS register. To get access to it
 	 * we have to read RCBA from PCI Config space 0xf0 and use
 	 * it as base. GCS = RCBA + ICH6_GCS(0x3410).
+	 *
+	 * iTCO v3:
+	 * Get the Power Management Configuration register.  To get access
+	 * to it we have to read the PMC BASE from config space and address
+	 * the register at offset 0x8.
 	 */
 	if (lpc_chipset_info[priv->chipset].iTCO_version == 1) {
 		/* Don't register iomem for TCO ver 1 */
 		lpc_ich_cells[LPC_WDT].num_resources--;
-	} else {
+	} else if (lpc_chipset_info[priv->chipset].iTCO_version == 2) {
 		pci_read_config_dword(dev, RCBABASE, &base_addr_cfg);
 		base_addr = base_addr_cfg & 0xffffc000;
 		if (!(base_addr_cfg & 1)) {
@@ -926,9 +969,17 @@ static int lpc_ich_init_wdt(struct pci_dev *dev)
 			ret = -ENODEV;
 			goto wdt_done;
 		}
-		res = wdt_mem_res(ICH_RES_MEM_GCS);
+		res = wdt_mem_res(ICH_RES_MEM_GCS_PMC);
 		res->start = base_addr + ACPIBASE_GCS_OFF;
 		res->end = base_addr + ACPIBASE_GCS_END;
+	} else if (lpc_chipset_info[priv->chipset].iTCO_version == 3) {
+		lpc_ich_enable_pmc_space(dev);
+		pci_read_config_dword(dev, ACPICTRL_PMCBASE, &base_addr_cfg);
+		base_addr = base_addr_cfg & 0xfffffe00;
+
+		res = wdt_mem_res(ICH_RES_MEM_GCS_PMC);
+		res->start = base_addr + ACPIBASE_PMC_OFF;
+		res->end = base_addr + ACPIBASE_PMC_END;
 	}
 
 	lpc_ich_finalize_cell(dev, &lpc_ich_cells[LPC_WDT]);
@@ -953,9 +1004,11 @@ static int lpc_ich_probe(struct pci_dev *dev,
 
 	priv->chipset = id->driver_data;
 
-	priv->actrl_save = -1;
+	priv->actrl_pbase_save = -1;
+	priv->abase_save = -1;
+
 	priv->abase = ACPIBASE;
-	priv->actrl = ACPICTRL;
+	priv->actrl_pbase = ACPICTRL_PMCBASE;
 
 	priv->gctrl_save = -1;
 	if (priv->chipset <= LPC_ICH5) {
diff --git a/include/linux/mfd/lpc_ich.h b/include/linux/mfd/lpc_ich.h
index b2364dd026a6..8feac782fa83 100644
--- a/include/linux/mfd/lpc_ich.h
+++ b/include/linux/mfd/lpc_ich.h
@@ -21,10 +21,10 @@
 #define LPC_ICH_H
 
 /* Watchdog resources */
-#define ICH_RES_IO_TCO	0
-#define ICH_RES_IO_SMI	1
-#define ICH_RES_MEM_OFF	2
-#define ICH_RES_MEM_GCS	0
+#define ICH_RES_IO_TCO		0
+#define ICH_RES_IO_SMI		1
+#define ICH_RES_MEM_OFF		2
+#define ICH_RES_MEM_GCS_PMC	0
 
 /* GPIO resources */
 #define ICH_RES_GPIO	0
-- 
cgit v1.2.3


From 05be09bb5ec8d12051515087a1983745dc93d906 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Date: Fri, 7 Mar 2014 11:10:51 +0100
Subject: regulator: s2mps11: Add set_suspend_disable for S2MPS14

S2MPS14 regulators support suspend mode where their status is controlled
by PWREN coming from SoC. This patch implements the set_suspend_disable
for S2MPS14 regulators.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/regulator/s2mps11.c         | 51 ++++++++++++++++++++++++++++++++++++-
 include/linux/mfd/samsung/s2mps14.h |  2 ++
 2 files changed, 52 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c
index 65697b1a26c0..cdd8d4066121 100644
--- a/drivers/regulator/s2mps11.c
+++ b/drivers/regulator/s2mps11.c
@@ -39,6 +39,11 @@ struct s2mps11_info {
 	int ramp_delay16;
 	int ramp_delay7810;
 	int ramp_delay9;
+	/*
+	 * One bit for each S2MPS14 regulator whether the suspend mode
+	 * was enabled.
+	 */
+	unsigned int s2mps14_suspend_state:30;
 };
 
 static int get_ramp_delay(int ramp_delay)
@@ -399,15 +404,59 @@ static const struct regulator_desc s2mps11_regulators[] = {
 	regulator_desc_s2mps11_buck10,
 };
 
+static int s2mps14_regulator_enable(struct regulator_dev *rdev)
+{
+	struct s2mps11_info *s2mps11 = rdev_get_drvdata(rdev);
+	unsigned int val;
+
+	if (s2mps11->s2mps14_suspend_state & (1 << rdev_get_id(rdev)))
+		val = S2MPS14_ENABLE_SUSPEND;
+	else
+		val = rdev->desc->enable_mask;
+
+	return regmap_update_bits(rdev->regmap, rdev->desc->enable_reg,
+			rdev->desc->enable_mask, val);
+}
+
+static int s2mps14_regulator_set_suspend_disable(struct regulator_dev *rdev)
+{
+	int ret;
+	unsigned int val;
+	struct s2mps11_info *s2mps11 = rdev_get_drvdata(rdev);
+
+	/* LDO3 should be always on and does not support suspend mode */
+	if (rdev_get_id(rdev) == S2MPS14_LDO3)
+		return 0;
+
+	ret = regmap_read(rdev->regmap, rdev->desc->enable_reg, &val);
+	if (ret < 0)
+		return ret;
+
+	s2mps11->s2mps14_suspend_state |= (1 << rdev_get_id(rdev));
+	/*
+	 * Don't enable suspend mode if regulator is already disabled because
+	 * this would effectively for a short time turn on the regulator after
+	 * resuming.
+	 * However we still want to toggle the suspend_state bit for regulator
+	 * in case if it got enabled before suspending the system.
+	 */
+	if (!(val & rdev->desc->enable_mask))
+		return 0;
+
+	return regmap_update_bits(rdev->regmap, rdev->desc->enable_reg,
+			rdev->desc->enable_mask, S2MPS14_ENABLE_SUSPEND);
+}
+
 static struct regulator_ops s2mps14_reg_ops = {
 	.list_voltage		= regulator_list_voltage_linear,
 	.map_voltage		= regulator_map_voltage_linear,
 	.is_enabled		= regulator_is_enabled_regmap,
-	.enable			= regulator_enable_regmap,
+	.enable			= s2mps14_regulator_enable,
 	.disable		= regulator_disable_regmap,
 	.get_voltage_sel	= regulator_get_voltage_sel_regmap,
 	.set_voltage_sel	= regulator_set_voltage_sel_regmap,
 	.set_voltage_time_sel	= regulator_set_voltage_time_sel,
+	.set_suspend_disable	= s2mps14_regulator_set_suspend_disable,
 };
 
 #define regulator_desc_s2mps14_ldo1(num) {		\
diff --git a/include/linux/mfd/samsung/s2mps14.h b/include/linux/mfd/samsung/s2mps14.h
index ec1e0857ddde..4b449b8ac548 100644
--- a/include/linux/mfd/samsung/s2mps14.h
+++ b/include/linux/mfd/samsung/s2mps14.h
@@ -146,6 +146,8 @@ enum s2mps14_regulators {
 #define S2MPS14_BUCK_VSEL_MASK		0xFF
 #define S2MPS14_ENABLE_MASK		(0x03 << S2MPS14_ENABLE_SHIFT)
 #define S2MPS14_ENABLE_SHIFT		6
+/* On/Off controlled by PWREN */
+#define S2MPS14_ENABLE_SUSPEND		(0x01 << S2MPS14_ENABLE_SHIFT)
 #define S2MPS14_LDO_N_VOLTAGES		(S2MPS14_LDO_VSEL_MASK + 1)
 #define S2MPS14_BUCK_N_VOLTAGES		(S2MPS14_BUCK_VSEL_MASK + 1)
 
-- 
cgit v1.2.3


From 0b443ead714f0cba797a7f2476dd756f22b5421e Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Wed, 19 Mar 2014 11:24:58 +0530
Subject: cpufreq: remove unused notifier: CPUFREQ_{SUSPENDCHANGE|RESUMECHANGE}

Two cpufreq notifiers CPUFREQ_RESUMECHANGE and CPUFREQ_SUSPENDCHANGE have
not been used for some time, so remove them to clean up code a bit.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
[rjw: Changelog]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/cpu-freq/core.txt       | 4 ----
 arch/arm/kernel/smp.c                 | 3 +--
 arch/arm/kernel/smp_twd.c             | 2 +-
 arch/arm/mach-pxa/viper.c             | 3 ---
 arch/powerpc/oprofile/op_model_cell.c | 3 +--
 arch/sparc/kernel/time_64.c           | 3 +--
 arch/x86/kernel/tsc.c                 | 3 +--
 drivers/cpufreq/cpufreq.c             | 3 +--
 drivers/pcmcia/sa11xx_base.c          | 3 ---
 drivers/tty/serial/sh-sci.c           | 3 +--
 include/linux/cpufreq.h               | 2 --
 11 files changed, 7 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/cpu-freq/core.txt b/Documentation/cpu-freq/core.txt
index ce0666e51036..0060d76b445f 100644
--- a/Documentation/cpu-freq/core.txt
+++ b/Documentation/cpu-freq/core.txt
@@ -92,7 +92,3 @@ values:
 cpu	- number of the affected CPU
 old	- old frequency
 new	- new frequency
-
-If the cpufreq core detects the frequency has changed while the system
-was suspended, these notifiers are called with CPUFREQ_RESUMECHANGE as
-second argument.
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index b7b4c86e338b..7c4fada440f0 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -674,8 +674,7 @@ static int cpufreq_callback(struct notifier_block *nb,
 	}
 
 	if ((val == CPUFREQ_PRECHANGE  && freq->old < freq->new) ||
-	    (val == CPUFREQ_POSTCHANGE && freq->old > freq->new) ||
-	    (val == CPUFREQ_RESUMECHANGE || val == CPUFREQ_SUSPENDCHANGE)) {
+	    (val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) {
 		loops_per_jiffy = cpufreq_scale(global_l_p_j_ref,
 						global_l_p_j_ref_freq,
 						freq->new);
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index 6591e26fc13f..dfc32130bc44 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -166,7 +166,7 @@ static int twd_cpufreq_transition(struct notifier_block *nb,
 	 * frequency.  The timer is local to a cpu, so cross-call to the
 	 * changing cpu.
 	 */
-	if (state == CPUFREQ_POSTCHANGE || state == CPUFREQ_RESUMECHANGE)
+	if (state == CPUFREQ_POSTCHANGE)
 		smp_call_function_single(freqs->cpu, twd_update_frequency,
 			NULL, 1);
 
diff --git a/arch/arm/mach-pxa/viper.c b/arch/arm/mach-pxa/viper.c
index 29905b127ad9..41f27f667ca8 100644
--- a/arch/arm/mach-pxa/viper.c
+++ b/arch/arm/mach-pxa/viper.c
@@ -885,9 +885,6 @@ static int viper_cpufreq_notifier(struct notifier_block *nb,
 			viper_set_core_cpu_voltage(freq->new, 0);
 		}
 		break;
-	case CPUFREQ_RESUMECHANGE:
-		viper_set_core_cpu_voltage(freq->new, 0);
-		break;
 	default:
 		/* ignore */
 		break;
diff --git a/arch/powerpc/oprofile/op_model_cell.c b/arch/powerpc/oprofile/op_model_cell.c
index 1f0ebdeea5f7..863d89386f60 100644
--- a/arch/powerpc/oprofile/op_model_cell.c
+++ b/arch/powerpc/oprofile/op_model_cell.c
@@ -1121,8 +1121,7 @@ oprof_cpufreq_notify(struct notifier_block *nb, unsigned long val, void *data)
 	int ret = 0;
 	struct cpufreq_freqs *frq = data;
 	if ((val == CPUFREQ_PRECHANGE && frq->old < frq->new) ||
-	    (val == CPUFREQ_POSTCHANGE && frq->old > frq->new) ||
-	    (val == CPUFREQ_RESUMECHANGE || val == CPUFREQ_SUSPENDCHANGE))
+	    (val == CPUFREQ_POSTCHANGE && frq->old > frq->new))
 		set_spu_profiling_frequency(frq->new, spu_cycle_reset);
 	return ret;
 }
diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c
index c3d82b5f54ca..b397e053b872 100644
--- a/arch/sparc/kernel/time_64.c
+++ b/arch/sparc/kernel/time_64.c
@@ -659,8 +659,7 @@ static int sparc64_cpufreq_notifier(struct notifier_block *nb, unsigned long val
 		ft->clock_tick_ref = cpu_data(cpu).clock_tick;
 	}
 	if ((val == CPUFREQ_PRECHANGE  && freq->old < freq->new) ||
-	    (val == CPUFREQ_POSTCHANGE && freq->old > freq->new) ||
-	    (val == CPUFREQ_RESUMECHANGE)) {
+	    (val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) {
 		cpu_data(cpu).clock_tick =
 			cpufreq_scale(ft->clock_tick_ref,
 				      ft->ref_freq,
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index cfbe99f88830..7a9296ab8834 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -914,8 +914,7 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 		tsc_khz_ref = tsc_khz;
 	}
 	if ((val == CPUFREQ_PRECHANGE  && freq->old < freq->new) ||
-			(val == CPUFREQ_POSTCHANGE && freq->old > freq->new) ||
-			(val == CPUFREQ_RESUMECHANGE)) {
+			(val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) {
 		*lpj = cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new);
 
 		tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new);
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 24cd6ff9bb0b..e3aa9deb40d9 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -264,8 +264,7 @@ static void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci)
 		pr_debug("saving %lu as reference value for loops_per_jiffy; freq is %u kHz\n",
 			 l_p_j_ref, l_p_j_ref_freq);
 	}
-	if ((val == CPUFREQ_POSTCHANGE && ci->old != ci->new) ||
-	    (val == CPUFREQ_RESUMECHANGE || val == CPUFREQ_SUSPENDCHANGE)) {
+	if (val == CPUFREQ_POSTCHANGE && ci->old != ci->new) {
 		loops_per_jiffy = cpufreq_scale(l_p_j_ref, l_p_j_ref_freq,
 								ci->new);
 		pr_debug("scaling loops_per_jiffy to %lu for frequency %u kHz\n",
diff --git a/drivers/pcmcia/sa11xx_base.c b/drivers/pcmcia/sa11xx_base.c
index 6eecd7cddf57..54d3089d157b 100644
--- a/drivers/pcmcia/sa11xx_base.c
+++ b/drivers/pcmcia/sa11xx_base.c
@@ -125,9 +125,6 @@ sa1100_pcmcia_frequency_change(struct soc_pcmcia_socket *skt,
 		if (freqs->new < freqs->old)
 			sa1100_pcmcia_set_mecr(skt, freqs->new);
 		break;
-	case CPUFREQ_RESUMECHANGE:
-		sa1100_pcmcia_set_mecr(skt, freqs->new);
-		break;
 	}
 
 	return 0;
diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index be33d2b0613b..7e0b62602632 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -1041,8 +1041,7 @@ static int sci_notifier(struct notifier_block *self,
 
 	sci_port = container_of(self, struct sci_port, freq_transition);
 
-	if ((phase == CPUFREQ_POSTCHANGE) ||
-	    (phase == CPUFREQ_RESUMECHANGE)) {
+	if (phase == CPUFREQ_POSTCHANGE) {
 		struct uart_port *port = &sci_port->port;
 
 		spin_lock_irqsave(&port->lock, flags);
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 31c431e150a7..70929bcf1a9d 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -318,8 +318,6 @@ static inline void cpufreq_resume(void) {}
 /* Transition notifiers */
 #define CPUFREQ_PRECHANGE		(0)
 #define CPUFREQ_POSTCHANGE		(1)
-#define CPUFREQ_RESUMECHANGE		(8)
-#define CPUFREQ_SUSPENDCHANGE		(9)
 
 /* Policy Notifiers  */
 #define CPUFREQ_ADJUST			(0)
-- 
cgit v1.2.3


From fdce6bf8c5b6968eb9b96ecc5fe400514a604902 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 19 Mar 2014 10:23:54 -0400
Subject: cgroup: remove NULL checks from [pr_cont_]cgroup_{name|path}()

The dummy hierarchy is now a fully functional one and dummy_top has a
kernfs_node associated with it.  Drop the NULL checks in
[pr_cont_]cont_{name|path}() which are no longer necessary.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h | 24 ++++--------------------
 1 file changed, 4 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index acbb9a4cb6e9..9f4f253f0e47 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -508,39 +508,23 @@ struct cgroup_subsys_state *seq_css(struct seq_file *seq);
 
 static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen)
 {
-	/* dummy_top doesn't have a kn associated */
-	if (cgrp->kn)
-		return kernfs_name(cgrp->kn, buf, buflen);
-	else
-		return strlcpy(buf, "/", buflen);
+	return kernfs_name(cgrp->kn, buf, buflen);
 }
 
 static inline char * __must_check cgroup_path(struct cgroup *cgrp, char *buf,
 					      size_t buflen)
 {
-	/* dummy_top doesn't have a kn associated */
-	if (cgrp->kn)
-		return kernfs_path(cgrp->kn, buf, buflen);
-	strlcpy(buf, "/", buflen);
-	return (buflen <= 2) ? NULL : buf;
+	return kernfs_path(cgrp->kn, buf, buflen);
 }
 
 static inline void pr_cont_cgroup_name(struct cgroup *cgrp)
 {
-	/* dummy_top doesn't have a kn associated */
-	if (cgrp->kn)
-		pr_cont_kernfs_name(cgrp->kn);
-	else
-		pr_cont("/");
+	pr_cont_kernfs_name(cgrp->kn);
 }
 
 static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
 {
-	/* dummy_top doesn't have a kn associated */
-	if (cgrp->kn)
-		pr_cont_kernfs_path(cgrp->kn);
-	else
-		pr_cont("/");
+	pr_cont_kernfs_path(cgrp->kn);
 }
 
 char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen);
-- 
cgit v1.2.3


From 944196278d3dea0cece1636de417b56897d9a108 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 19 Mar 2014 10:23:54 -0400
Subject: cgroup: move ->subsys_mask from cgroupfs_root to cgroup

cgroupfs_root->subsys_mask represents the controllers attached to the
hierarchy.  This patch moves the field to cgroup.  Subsystem
initialization and rebinding updates the top cgroup's subsys_mask.
For !root cgroups, the subsys_mask bits are set from create_css() and
cleared from kill_css(), which effectively means that all cgroups will
have the same subsys_mask as the top cgroup.

While this doesn't make any difference now, this will help
implementation of the default unified hierarchy where !root cgroups
may have subsets of the top_cgroup's subsys_mask.

While at it, __kill_css() is split out of kill_css().  The former
doesn't care about the subsys_mask while the latter becomes noop if
the controller is already killed and clears the matching bit if not
before proceeding to killing the css.  This will be used later by the
default unified hierarchy implementation.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h |  6 ++---
 kernel/cgroup.c        | 61 ++++++++++++++++++++++++++++++++------------------
 2 files changed, 42 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 9f4f253f0e47..3752a0182c94 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -173,6 +173,9 @@ struct cgroup {
 	 */
 	u64 serial_nr;
 
+	/* The bitmask of subsystems attached to this cgroup */
+	unsigned long subsys_mask;
+
 	/* Private pointers for each registered subsystem */
 	struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT];
 
@@ -276,9 +279,6 @@ enum {
 struct cgroupfs_root {
 	struct kernfs_root *kf_root;
 
-	/* The bitmask of subsystems attached to this hierarchy */
-	unsigned long subsys_mask;
-
 	/* Unique id for this hierarchy. */
 	int hierarchy_id;
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index b632981bd9c7..807f88dbda51 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -526,7 +526,7 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset,
 	 * won't change, so no need for locking.
 	 */
 	for_each_subsys(ss, i) {
-		if (root->subsys_mask & (1UL << i)) {
+		if (root->top_cgroup.subsys_mask & (1UL << i)) {
 			/* Subsystem is in this hierarchy. So we want
 			 * the subsystem state from the new
 			 * cgroup */
@@ -739,7 +739,7 @@ static void cgroup_destroy_root(struct cgroupfs_root *root)
 	BUG_ON(!list_empty(&cgrp->children));
 
 	/* Rebind all subsystems back to the default hierarchy */
-	rebind_subsystems(&cgroup_dummy_root, root->subsys_mask);
+	rebind_subsystems(&cgroup_dummy_root, cgrp->subsys_mask);
 
 	/*
 	 * Release all the links from cset_links to this hierarchy's
@@ -1038,8 +1038,8 @@ static int rebind_subsystems(struct cgroupfs_root *dst_root,
 		ss->root = dst_root;
 		css->cgroup = dst_top;
 
-		src_root->subsys_mask &= ~(1 << ssid);
-		dst_root->subsys_mask |= 1 << ssid;
+		src_top->subsys_mask &= ~(1 << ssid);
+		dst_top->subsys_mask |= 1 << ssid;
 
 		if (ss->bind)
 			ss->bind(css);
@@ -1058,7 +1058,7 @@ static int cgroup_show_options(struct seq_file *seq,
 	int ssid;
 
 	for_each_subsys(ss, ssid)
-		if (root->subsys_mask & (1 << ssid))
+		if (root->top_cgroup.subsys_mask & (1 << ssid))
 			seq_printf(seq, ",%s", ss->name);
 	if (root->flags & CGRP_ROOT_SANE_BEHAVIOR)
 		seq_puts(seq, ",sane_behavior");
@@ -1262,12 +1262,12 @@ static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
 	if (ret)
 		goto out_unlock;
 
-	if (opts.subsys_mask != root->subsys_mask || opts.release_agent)
+	if (opts.subsys_mask != root->top_cgroup.subsys_mask || opts.release_agent)
 		pr_warning("cgroup: option changes via remount are deprecated (pid=%d comm=%s)\n",
 			   task_tgid_nr(current), current->comm);
 
-	added_mask = opts.subsys_mask & ~root->subsys_mask;
-	removed_mask = root->subsys_mask & ~opts.subsys_mask;
+	added_mask = opts.subsys_mask & ~root->top_cgroup.subsys_mask;
+	removed_mask = root->top_cgroup.subsys_mask & ~opts.subsys_mask;
 
 	/* Don't allow flags or name to change at remount */
 	if (((opts.flags ^ root->flags) & CGRP_ROOT_OPTION_MASK) ||
@@ -1515,7 +1515,7 @@ retry:
 		 * subsystems) then they must match.
 		 */
 		if ((opts.subsys_mask || opts.none) &&
-		    (opts.subsys_mask != root->subsys_mask)) {
+		    (opts.subsys_mask != root->top_cgroup.subsys_mask)) {
 			if (!name_match)
 				continue;
 			ret = -EBUSY;
@@ -3594,6 +3594,8 @@ static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss)
 	cgroup_get(cgrp);
 	css_get(css->parent);
 
+	cgrp->subsys_mask |= 1 << ss->id;
+
 	if (ss->broken_hierarchy && !ss->warned_broken_hierarchy &&
 	    parent->parent) {
 		pr_warning("cgroup: %s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n",
@@ -3700,7 +3702,7 @@ static long cgroup_create(struct cgroup *parent, const char *name,
 
 	/* let's create and online css's */
 	for_each_subsys(ss, ssid) {
-		if (root->subsys_mask & (1 << ssid)) {
+		if (root->top_cgroup.subsys_mask & (1 << ssid)) {
 			err = create_css(cgrp, ss);
 			if (err)
 				goto err_destroy;
@@ -3788,17 +3790,10 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
 	queue_work(cgroup_destroy_wq, &css->destroy_work);
 }
 
-/**
- * kill_css - destroy a css
- * @css: css to destroy
- *
- * This function initiates destruction of @css by removing cgroup interface
- * files and putting its base reference.  ->css_offline() will be invoked
- * asynchronously once css_tryget() is guaranteed to fail and when the
- * reference count reaches zero, @css will be released.
- */
-static void kill_css(struct cgroup_subsys_state *css)
+static void __kill_css(struct cgroup_subsys_state *css)
 {
+	lockdep_assert_held(&cgroup_tree_mutex);
+
 	/*
 	 * This must happen before css is disassociated with its cgroup.
 	 * See seq_css() for details.
@@ -3824,6 +3819,28 @@ static void kill_css(struct cgroup_subsys_state *css)
 	percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn);
 }
 
+/**
+ * kill_css - destroy a css
+ * @css: css to destroy
+ *
+ * This function initiates destruction of @css by removing cgroup interface
+ * files and putting its base reference.  ->css_offline() will be invoked
+ * asynchronously once css_tryget() is guaranteed to fail and when the
+ * reference count reaches zero, @css will be released.
+ */
+static void kill_css(struct cgroup_subsys_state *css)
+{
+	struct cgroup *cgrp = css->cgroup;
+
+	lockdep_assert_held(&cgroup_tree_mutex);
+
+	/* if already killed, noop */
+	if (cgrp->subsys_mask & (1 << css->ss->id)) {
+		cgrp->subsys_mask &= ~(1 << css->ss->id);
+		__kill_css(css);
+	}
+}
+
 /**
  * cgroup_destroy_locked - the first stage of cgroup destruction
  * @cgrp: cgroup to be destroyed
@@ -4036,7 +4053,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 
 	BUG_ON(online_css(css));
 
-	cgroup_dummy_root.subsys_mask |= 1 << ss->id;
+	cgroup_dummy_root.top_cgroup.subsys_mask |= 1 << ss->id;
 
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&cgroup_tree_mutex);
@@ -4192,7 +4209,7 @@ int proc_cgroup_show(struct seq_file *m, void *v)
 
 		seq_printf(m, "%d:", root->hierarchy_id);
 		for_each_subsys(ss, ssid)
-			if (root->subsys_mask & (1 << ssid))
+			if (root->top_cgroup.subsys_mask & (1 << ssid))
 				seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
 		if (strlen(root->name))
 			seq_printf(m, "%sname=%s", count ? "," : "",
-- 
cgit v1.2.3


From 3dd06ffa9df99aa88f4e01eaa0c9d3cb362430b0 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 19 Mar 2014 10:23:54 -0400
Subject: cgroup: rename cgroup_dummy_root and related names

The dummy root will be repurposed to serve as the default unified
hierarchy.  Let's rename things in preparation.

* s/cgroup_dummy_root/cgrp_dfl_root/
* s/cgroupfs_root/cgroup_root/ as we don't do fs part directly anymore
* s/cgroup_root->top_cgroup/cgroup_root->cgrp/ for brevity

This is pure rename.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h |  14 ++---
 kernel/cgroup.c        | 168 ++++++++++++++++++++++++-------------------------
 2 files changed, 88 insertions(+), 94 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 3752a0182c94..77294fc66603 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -24,7 +24,7 @@
 
 #ifdef CONFIG_CGROUPS
 
-struct cgroupfs_root;
+struct cgroup_root;
 struct cgroup_subsys;
 struct inode;
 struct cgroup;
@@ -179,7 +179,7 @@ struct cgroup {
 	/* Private pointers for each registered subsystem */
 	struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT];
 
-	struct cgroupfs_root *root;
+	struct cgroup_root *root;
 
 	/*
 	 * List of cgrp_cset_links pointing at css_sets with tasks in this
@@ -211,7 +211,7 @@ struct cgroup {
 
 #define MAX_CGROUP_ROOT_NAMELEN 64
 
-/* cgroupfs_root->flags */
+/* cgroup_root->flags */
 enum {
 	/*
 	 * Unfortunately, cgroup core and various controllers are riddled
@@ -272,18 +272,18 @@ enum {
 };
 
 /*
- * A cgroupfs_root represents the root of a cgroup hierarchy, and may be
+ * A cgroup_root represents the root of a cgroup hierarchy, and may be
  * associated with a kernfs_root to form an active hierarchy.  This is
  * internal to cgroup core.  Don't access directly from controllers.
  */
-struct cgroupfs_root {
+struct cgroup_root {
 	struct kernfs_root *kf_root;
 
 	/* Unique id for this hierarchy. */
 	int hierarchy_id;
 
 	/* The root cgroup.  Root is destroyed on its release. */
-	struct cgroup top_cgroup;
+	struct cgroup cgrp;
 
 	/* Number of cgroups in the hierarchy, used only for /proc/cgroups */
 	atomic_t nr_cgrps;
@@ -598,7 +598,7 @@ struct cgroup_subsys {
 	const char *name;
 
 	/* link to parent, protected by cgroup_lock() */
-	struct cgroupfs_root *root;
+	struct cgroup_root *root;
 
 	/*
 	 * List of cftypes.  Each entry is the first entry of an array
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 807f88dbda51..60ea16058c42 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -138,14 +138,11 @@ static const char *cgroup_subsys_name[] = {
 #undef SUBSYS
 
 /*
- * The dummy hierarchy, reserved for the subsystems that are otherwise
+ * The default hierarchy, reserved for the subsystems that are otherwise
  * unattached - it never has more than a single cgroup, and all tasks are
  * part of that cgroup.
  */
-static struct cgroupfs_root cgroup_dummy_root;
-
-/* dummy_top is a shorthand for the dummy hierarchy's top cgroup */
-static struct cgroup * const cgroup_dummy_top = &cgroup_dummy_root.top_cgroup;
+static struct cgroup_root cgrp_dfl_root;
 
 /* The list of hierarchy roots */
 
@@ -175,7 +172,7 @@ static int need_forkexit_callback __read_mostly;
 static struct cftype cgroup_base_files[];
 
 static void cgroup_put(struct cgroup *cgrp);
-static int rebind_subsystems(struct cgroupfs_root *dst_root,
+static int rebind_subsystems(struct cgroup_root *dst_root,
 			     unsigned long ss_mask);
 static void cgroup_destroy_css_killed(struct cgroup *cgrp);
 static int cgroup_destroy_locked(struct cgroup *cgrp);
@@ -514,7 +511,7 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset,
 					struct cgroup *cgrp,
 					struct cgroup_subsys_state *template[])
 {
-	struct cgroupfs_root *root = cgrp->root;
+	struct cgroup_root *root = cgrp->root;
 	struct cgroup_subsys *ss;
 	struct css_set *cset;
 	unsigned long key;
@@ -526,7 +523,7 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset,
 	 * won't change, so no need for locking.
 	 */
 	for_each_subsys(ss, i) {
-		if (root->top_cgroup.subsys_mask & (1UL << i)) {
+		if (root->cgrp.subsys_mask & (1UL << i)) {
 			/* Subsystem is in this hierarchy. So we want
 			 * the subsystem state from the new
 			 * cgroup */
@@ -685,14 +682,14 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 	return cset;
 }
 
-static struct cgroupfs_root *cgroup_root_from_kf(struct kernfs_root *kf_root)
+static struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root)
 {
-	struct cgroup *top_cgrp = kf_root->kn->priv;
+	struct cgroup *root_cgrp = kf_root->kn->priv;
 
-	return top_cgrp->root;
+	return root_cgrp->root;
 }
 
-static int cgroup_init_root_id(struct cgroupfs_root *root)
+static int cgroup_init_root_id(struct cgroup_root *root)
 {
 	int id;
 
@@ -706,7 +703,7 @@ static int cgroup_init_root_id(struct cgroupfs_root *root)
 	return 0;
 }
 
-static void cgroup_exit_root_id(struct cgroupfs_root *root)
+static void cgroup_exit_root_id(struct cgroup_root *root)
 {
 	lockdep_assert_held(&cgroup_mutex);
 
@@ -716,7 +713,7 @@ static void cgroup_exit_root_id(struct cgroupfs_root *root)
 	}
 }
 
-static void cgroup_free_root(struct cgroupfs_root *root)
+static void cgroup_free_root(struct cgroup_root *root)
 {
 	if (root) {
 		/* hierarhcy ID shoulid already have been released */
@@ -727,9 +724,9 @@ static void cgroup_free_root(struct cgroupfs_root *root)
 	}
 }
 
-static void cgroup_destroy_root(struct cgroupfs_root *root)
+static void cgroup_destroy_root(struct cgroup_root *root)
 {
-	struct cgroup *cgrp = &root->top_cgroup;
+	struct cgroup *cgrp = &root->cgrp;
 	struct cgrp_cset_link *link, *tmp_link;
 
 	mutex_lock(&cgroup_tree_mutex);
@@ -739,7 +736,7 @@ static void cgroup_destroy_root(struct cgroupfs_root *root)
 	BUG_ON(!list_empty(&cgrp->children));
 
 	/* Rebind all subsystems back to the default hierarchy */
-	rebind_subsystems(&cgroup_dummy_root, cgrp->subsys_mask);
+	rebind_subsystems(&cgrp_dfl_root, cgrp->subsys_mask);
 
 	/*
 	 * Release all the links from cset_links to this hierarchy's
@@ -770,7 +767,7 @@ static void cgroup_destroy_root(struct cgroupfs_root *root)
 
 /* look up cgroup associated with given css_set on the specified hierarchy */
 static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
-					    struct cgroupfs_root *root)
+					    struct cgroup_root *root)
 {
 	struct cgroup *res = NULL;
 
@@ -778,7 +775,7 @@ static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
 	lockdep_assert_held(&css_set_rwsem);
 
 	if (cset == &init_css_set) {
-		res = &root->top_cgroup;
+		res = &root->cgrp;
 	} else {
 		struct cgrp_cset_link *link;
 
@@ -801,7 +798,7 @@ static struct cgroup *cset_cgroup_from_root(struct css_set *cset,
  * called with cgroup_mutex and css_set_rwsem held.
  */
 static struct cgroup *task_cgroup_from_root(struct task_struct *task,
-					    struct cgroupfs_root *root)
+					    struct cgroup_root *root)
 {
 	/*
 	 * No need to lock the task - since we hold cgroup_mutex the
@@ -837,9 +834,9 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task,
  * A cgroup can only be deleted if both its 'count' of using tasks
  * is zero, and its list of 'children' cgroups is empty.  Since all
  * tasks in the system use _some_ cgroup, and since there is always at
- * least one task in the system (init, pid == 1), therefore, top_cgroup
+ * least one task in the system (init, pid == 1), therefore, root cgroup
  * always has either children cgroups and/or using tasks.  So we don't
- * need a special hack to ensure that top_cgroup cannot be deleted.
+ * need a special hack to ensure that root cgroup cannot be deleted.
  *
  * P.S.  One more locking exception.  RCU is used to guard the
  * update of a tasks cgroup pointer by cgroup_attach_task()
@@ -905,7 +902,7 @@ static void cgroup_free_fn(struct work_struct *work)
 		kfree(cgrp);
 	} else {
 		/*
-		 * This is top cgroup's refcnt reaching zero, which
+		 * This is root cgroup's refcnt reaching zero, which
 		 * indicates that the root should be released.
 		 */
 		cgroup_destroy_root(cgrp->root);
@@ -976,10 +973,9 @@ static void cgroup_clear_dir(struct cgroup *cgrp, unsigned long subsys_mask)
 	}
 }
 
-static int rebind_subsystems(struct cgroupfs_root *dst_root,
+static int rebind_subsystems(struct cgroup_root *dst_root,
 			     unsigned long ss_mask)
 {
-	struct cgroup *dst_top = &dst_root->top_cgroup;
 	struct cgroup_subsys *ss;
 	int ssid, ret;
 
@@ -991,20 +987,20 @@ static int rebind_subsystems(struct cgroupfs_root *dst_root,
 			continue;
 
 		/* if @ss is on the dummy_root, we can always move it */
-		if (ss->root == &cgroup_dummy_root)
+		if (ss->root == &cgrp_dfl_root)
 			continue;
 
 		/* if @ss has non-root cgroups attached to it, can't move */
-		if (!list_empty(&ss->root->top_cgroup.children))
+		if (!list_empty(&ss->root->cgrp.children))
 			return -EBUSY;
 
 		/* can't move between two non-dummy roots either */
-		if (dst_root != &cgroup_dummy_root)
+		if (dst_root != &cgrp_dfl_root)
 			return -EBUSY;
 	}
 
-	if (dst_root != &cgroup_dummy_root) {
-		ret = cgroup_populate_dir(dst_top, ss_mask);
+	if (dst_root != &cgrp_dfl_root) {
+		ret = cgroup_populate_dir(&dst_root->cgrp, ss_mask);
 		if (ret)
 			return ret;
 	}
@@ -1015,50 +1011,48 @@ static int rebind_subsystems(struct cgroupfs_root *dst_root,
 	 */
 	mutex_unlock(&cgroup_mutex);
 	for_each_subsys(ss, ssid)
-		if ((ss_mask & (1 << ssid)) && ss->root != &cgroup_dummy_root)
-			cgroup_clear_dir(&ss->root->top_cgroup, 1 << ssid);
+		if ((ss_mask & (1 << ssid)) && ss->root != &cgrp_dfl_root)
+			cgroup_clear_dir(&ss->root->cgrp, 1 << ssid);
 	mutex_lock(&cgroup_mutex);
 
 	for_each_subsys(ss, ssid) {
-		struct cgroupfs_root *src_root;
-		struct cgroup *src_top;
+		struct cgroup_root *src_root;
 		struct cgroup_subsys_state *css;
 
 		if (!(ss_mask & (1 << ssid)))
 			continue;
 
 		src_root = ss->root;
-		src_top = &src_root->top_cgroup;
-		css = cgroup_css(src_top, ss);
+		css = cgroup_css(&src_root->cgrp, ss);
 
-		WARN_ON(!css || cgroup_css(dst_top, ss));
+		WARN_ON(!css || cgroup_css(&dst_root->cgrp, ss));
 
-		RCU_INIT_POINTER(src_top->subsys[ssid], NULL);
-		rcu_assign_pointer(dst_top->subsys[ssid], css);
+		RCU_INIT_POINTER(src_root->cgrp.subsys[ssid], NULL);
+		rcu_assign_pointer(dst_root->cgrp.subsys[ssid], css);
 		ss->root = dst_root;
-		css->cgroup = dst_top;
+		css->cgroup = &dst_root->cgrp;
 
-		src_top->subsys_mask &= ~(1 << ssid);
-		dst_top->subsys_mask |= 1 << ssid;
+		src_root->cgrp.subsys_mask &= ~(1 << ssid);
+		dst_root->cgrp.subsys_mask |= 1 << ssid;
 
 		if (ss->bind)
 			ss->bind(css);
 	}
 
-	if (dst_root != &cgroup_dummy_root)
-		kernfs_activate(dst_top->kn);
+	if (dst_root != &cgrp_dfl_root)
+		kernfs_activate(dst_root->cgrp.kn);
 	return 0;
 }
 
 static int cgroup_show_options(struct seq_file *seq,
 			       struct kernfs_root *kf_root)
 {
-	struct cgroupfs_root *root = cgroup_root_from_kf(kf_root);
+	struct cgroup_root *root = cgroup_root_from_kf(kf_root);
 	struct cgroup_subsys *ss;
 	int ssid;
 
 	for_each_subsys(ss, ssid)
-		if (root->top_cgroup.subsys_mask & (1 << ssid))
+		if (root->cgrp.subsys_mask & (1 << ssid))
 			seq_printf(seq, ",%s", ss->name);
 	if (root->flags & CGRP_ROOT_SANE_BEHAVIOR)
 		seq_puts(seq, ",sane_behavior");
@@ -1072,7 +1066,7 @@ static int cgroup_show_options(struct seq_file *seq,
 		seq_printf(seq, ",release_agent=%s", root->release_agent_path);
 	spin_unlock(&release_agent_path_lock);
 
-	if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->top_cgroup.flags))
+	if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags))
 		seq_puts(seq, ",clone_children");
 	if (strlen(root->name))
 		seq_printf(seq, ",name=%s", root->name);
@@ -1245,7 +1239,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
 {
 	int ret = 0;
-	struct cgroupfs_root *root = cgroup_root_from_kf(kf_root);
+	struct cgroup_root *root = cgroup_root_from_kf(kf_root);
 	struct cgroup_sb_opts opts;
 	unsigned long added_mask, removed_mask;
 
@@ -1262,12 +1256,12 @@ static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
 	if (ret)
 		goto out_unlock;
 
-	if (opts.subsys_mask != root->top_cgroup.subsys_mask || opts.release_agent)
+	if (opts.subsys_mask != root->cgrp.subsys_mask || opts.release_agent)
 		pr_warning("cgroup: option changes via remount are deprecated (pid=%d comm=%s)\n",
 			   task_tgid_nr(current), current->comm);
 
-	added_mask = opts.subsys_mask & ~root->top_cgroup.subsys_mask;
-	removed_mask = root->top_cgroup.subsys_mask & ~opts.subsys_mask;
+	added_mask = opts.subsys_mask & ~root->cgrp.subsys_mask;
+	removed_mask = root->cgrp.subsys_mask & ~opts.subsys_mask;
 
 	/* Don't allow flags or name to change at remount */
 	if (((opts.flags ^ root->flags) & CGRP_ROOT_OPTION_MASK) ||
@@ -1280,7 +1274,7 @@ static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
 	}
 
 	/* remounting is not allowed for populated hierarchies */
-	if (!list_empty(&root->top_cgroup.children)) {
+	if (!list_empty(&root->cgrp.children)) {
 		ret = -EBUSY;
 		goto out_unlock;
 	}
@@ -1289,7 +1283,7 @@ static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data)
 	if (ret)
 		goto out_unlock;
 
-	rebind_subsystems(&cgroup_dummy_root, removed_mask);
+	rebind_subsystems(&cgrp_dfl_root, removed_mask);
 
 	if (opts.release_agent) {
 		spin_lock(&release_agent_path_lock);
@@ -1368,10 +1362,10 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 	cgrp->dummy_css.cgroup = cgrp;
 }
 
-static void init_cgroup_root(struct cgroupfs_root *root,
+static void init_cgroup_root(struct cgroup_root *root,
 			     struct cgroup_sb_opts *opts)
 {
-	struct cgroup *cgrp = &root->top_cgroup;
+	struct cgroup *cgrp = &root->cgrp;
 
 	INIT_LIST_HEAD(&root->root_list);
 	atomic_set(&root->nr_cgrps, 1);
@@ -1385,13 +1379,13 @@ static void init_cgroup_root(struct cgroupfs_root *root,
 	if (opts->name)
 		strcpy(root->name, opts->name);
 	if (opts->cpuset_clone_children)
-		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->top_cgroup.flags);
+		set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags);
 }
 
-static int cgroup_setup_root(struct cgroupfs_root *root, unsigned long ss_mask)
+static int cgroup_setup_root(struct cgroup_root *root, unsigned long ss_mask)
 {
 	LIST_HEAD(tmp_links);
-	struct cgroup *root_cgrp = &root->top_cgroup;
+	struct cgroup *root_cgrp = &root->cgrp;
 	struct css_set *cset;
 	int i, ret;
 
@@ -1443,7 +1437,7 @@ static int cgroup_setup_root(struct cgroupfs_root *root, unsigned long ss_mask)
 	cgroup_root_count++;
 
 	/*
-	 * Link the top cgroup in this hierarchy into all the css_set
+	 * Link the root cgroup in this hierarchy into all the css_set
 	 * objects.
 	 */
 	down_write(&css_set_rwsem);
@@ -1472,7 +1466,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 			 int flags, const char *unused_dev_name,
 			 void *data)
 {
-	struct cgroupfs_root *root;
+	struct cgroup_root *root;
 	struct cgroup_sb_opts opts;
 	struct dentry *dentry;
 	int ret;
@@ -1496,7 +1490,7 @@ retry:
 	for_each_root(root) {
 		bool name_match = false;
 
-		if (root == &cgroup_dummy_root)
+		if (root == &cgrp_dfl_root)
 			continue;
 
 		/*
@@ -1515,7 +1509,7 @@ retry:
 		 * subsystems) then they must match.
 		 */
 		if ((opts.subsys_mask || opts.none) &&
-		    (opts.subsys_mask != root->top_cgroup.subsys_mask)) {
+		    (opts.subsys_mask != root->cgrp.subsys_mask)) {
 			if (!name_match)
 				continue;
 			ret = -EBUSY;
@@ -1533,13 +1527,13 @@ retry:
 		}
 
 		/*
-		 * A root's lifetime is governed by its top cgroup.  Zero
+		 * A root's lifetime is governed by its root cgroup.  Zero
 		 * ref indicate that the root is being destroyed.  Wait for
 		 * destruction to complete so that the subsystems are free.
 		 * We can use wait_queue for the wait but this path is
 		 * super cold.  Let's just sleep for a bit and retry.
 		 */
-		if (!atomic_inc_not_zero(&root->top_cgroup.refcnt)) {
+		if (!atomic_inc_not_zero(&root->cgrp.refcnt)) {
 			mutex_unlock(&cgroup_mutex);
 			mutex_unlock(&cgroup_tree_mutex);
 			kfree(opts.release_agent);
@@ -1586,16 +1580,16 @@ out_unlock:
 
 	dentry = kernfs_mount(fs_type, flags, root->kf_root);
 	if (IS_ERR(dentry))
-		cgroup_put(&root->top_cgroup);
+		cgroup_put(&root->cgrp);
 	return dentry;
 }
 
 static void cgroup_kill_sb(struct super_block *sb)
 {
 	struct kernfs_root *kf_root = kernfs_root_from_sb(sb);
-	struct cgroupfs_root *root = cgroup_root_from_kf(kf_root);
+	struct cgroup_root *root = cgroup_root_from_kf(kf_root);
 
-	cgroup_put(&root->top_cgroup);
+	cgroup_put(&root->cgrp);
 	kernfs_kill_sb(sb);
 }
 
@@ -1622,7 +1616,7 @@ static struct kobject *cgroup_kobj;
  */
 char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen)
 {
-	struct cgroupfs_root *root;
+	struct cgroup_root *root;
 	struct cgroup *cgrp;
 	int hierarchy_id = 1;
 	char *path = NULL;
@@ -2112,14 +2106,14 @@ out_unlock_cgroup:
  */
 int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk)
 {
-	struct cgroupfs_root *root;
+	struct cgroup_root *root;
 	int retval = 0;
 
 	mutex_lock(&cgroup_mutex);
 	for_each_root(root) {
 		struct cgroup *from_cgrp;
 
-		if (root == &cgroup_dummy_root)
+		if (root == &cgrp_dfl_root)
 			continue;
 
 		down_read(&css_set_rwsem);
@@ -2151,7 +2145,7 @@ static int cgroup_procs_write(struct cgroup_subsys_state *css,
 static int cgroup_release_agent_write(struct cgroup_subsys_state *css,
 				      struct cftype *cft, const char *buffer)
 {
-	struct cgroupfs_root *root = css->cgroup->root;
+	struct cgroup_root *root = css->cgroup->root;
 
 	BUILD_BUG_ON(sizeof(root->release_agent_path) < PATH_MAX);
 	if (!cgroup_lock_live_group(css->cgroup))
@@ -2362,14 +2356,14 @@ static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add)
 {
 	LIST_HEAD(pending);
 	struct cgroup_subsys *ss = cfts[0].ss;
-	struct cgroup *root = &ss->root->top_cgroup;
+	struct cgroup *root = &ss->root->cgrp;
 	struct cgroup_subsys_state *css;
 	int ret = 0;
 
 	lockdep_assert_held(&cgroup_tree_mutex);
 
 	/* don't bother if @ss isn't attached */
-	if (ss->root == &cgroup_dummy_root)
+	if (ss->root == &cgrp_dfl_root)
 		return 0;
 
 	/* add/rm files for all cgroups created before */
@@ -3623,7 +3617,7 @@ static long cgroup_create(struct cgroup *parent, const char *name,
 			  umode_t mode)
 {
 	struct cgroup *cgrp;
-	struct cgroupfs_root *root = parent->root;
+	struct cgroup_root *root = parent->root;
 	int ssid, err;
 	struct cgroup_subsys *ss;
 	struct kernfs_node *kn;
@@ -3702,7 +3696,7 @@ static long cgroup_create(struct cgroup *parent, const char *name,
 
 	/* let's create and online css's */
 	for_each_subsys(ss, ssid) {
-		if (root->top_cgroup.subsys_mask & (1 << ssid)) {
+		if (root->cgrp.subsys_mask & (1 << ssid)) {
 			err = create_css(cgrp, ss);
 			if (err)
 				goto err_destroy;
@@ -4031,17 +4025,17 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 
 	INIT_LIST_HEAD(&ss->cfts);
 
-	/* Create the top cgroup state for this subsystem */
-	ss->root = &cgroup_dummy_root;
-	css = ss->css_alloc(cgroup_css(cgroup_dummy_top, ss));
+	/* Create the root cgroup state for this subsystem */
+	ss->root = &cgrp_dfl_root;
+	css = ss->css_alloc(cgroup_css(&cgrp_dfl_root.cgrp, ss));
 	/* We don't handle early failures gracefully */
 	BUG_ON(IS_ERR(css));
-	init_css(css, ss, cgroup_dummy_top);
+	init_css(css, ss, &cgrp_dfl_root.cgrp);
 
 	/* Update the init_css_set to contain a subsys
 	 * pointer to this state - since the subsystem is
 	 * newly registered, all tasks and hence the
-	 * init_css_set is in the subsystem's top cgroup. */
+	 * init_css_set is in the subsystem's root cgroup. */
 	init_css_set.subsys[ss->id] = css;
 
 	need_forkexit_callback |= ss->fork || ss->exit;
@@ -4053,7 +4047,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 
 	BUG_ON(online_css(css));
 
-	cgroup_dummy_root.top_cgroup.subsys_mask |= 1 << ss->id;
+	cgrp_dfl_root.cgrp.subsys_mask |= 1 << ss->id;
 
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&cgroup_tree_mutex);
@@ -4071,7 +4065,7 @@ int __init cgroup_init_early(void)
 	struct cgroup_subsys *ss;
 	int i;
 
-	init_cgroup_root(&cgroup_dummy_root, &opts);
+	init_cgroup_root(&cgrp_dfl_root, &opts);
 	RCU_INIT_POINTER(init_task.cgroups, &init_css_set);
 
 	for_each_subsys(ss, i) {
@@ -4112,7 +4106,7 @@ int __init cgroup_init(void)
 	key = css_set_hash(init_css_set.subsys);
 	hash_add(css_set_table, &init_css_set.hlist, key);
 
-	BUG_ON(cgroup_setup_root(&cgroup_dummy_root, 0));
+	BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0));
 
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&cgroup_tree_mutex);
@@ -4181,7 +4175,7 @@ int proc_cgroup_show(struct seq_file *m, void *v)
 	struct task_struct *tsk;
 	char *buf, *path;
 	int retval;
-	struct cgroupfs_root *root;
+	struct cgroup_root *root;
 
 	retval = -ENOMEM;
 	buf = kmalloc(PATH_MAX, GFP_KERNEL);
@@ -4204,12 +4198,12 @@ int proc_cgroup_show(struct seq_file *m, void *v)
 		struct cgroup *cgrp;
 		int ssid, count = 0;
 
-		if (root == &cgroup_dummy_root)
+		if (root == &cgrp_dfl_root)
 			continue;
 
 		seq_printf(m, "%d:", root->hierarchy_id);
 		for_each_subsys(ss, ssid)
-			if (root->top_cgroup.subsys_mask & (1 << ssid))
+			if (root->cgrp.subsys_mask & (1 << ssid))
 				seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
 		if (strlen(root->name))
 			seq_printf(m, "%sname=%s", count ? "," : "",
@@ -4639,7 +4633,7 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
 		struct cgroup *c = link->cgrp;
 		const char *name = "?";
 
-		if (c != cgroup_dummy_top) {
+		if (c != &cgrp_dfl_root.cgrp) {
 			cgroup_name(c, name_buf, NAME_MAX + 1);
 			name = name_buf;
 		}
-- 
cgit v1.2.3


From 4d3bb511b5f9980fc3e9ae5939ebc475b231d3fc Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 19 Mar 2014 10:23:54 -0400
Subject: cgroup: drop const from @buffer of cftype->write_string()

cftype->write_string() just passes on the writeable buffer from kernfs
and there's no reason to add const restriction on the buffer.  The
only thing const achieves is unnecessarily complicating parsing of the
buffer.  Drop const from @buffer.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Daniel Borkmann <dborkman@redhat.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
---
 block/blk-throttle.c      | 4 ++--
 block/cfq-iosched.c       | 4 ++--
 include/linux/cgroup.h    | 2 +-
 kernel/cgroup.c           | 2 +-
 kernel/cgroup_freezer.c   | 2 +-
 kernel/cpuset.c           | 2 +-
 mm/hugetlb_cgroup.c       | 2 +-
 mm/memcontrol.c           | 4 ++--
 net/core/netprio_cgroup.c | 2 +-
 net/ipv4/tcp_memcontrol.c | 2 +-
 security/device_cgroup.c  | 4 ++--
 11 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 861c363e4129..033745cd7fba 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -1408,13 +1408,13 @@ static int tg_set_conf(struct cgroup_subsys_state *css, struct cftype *cft,
 }
 
 static int tg_set_conf_u64(struct cgroup_subsys_state *css, struct cftype *cft,
-			   const char *buf)
+			   char *buf)
 {
 	return tg_set_conf(css, cft, buf, true);
 }
 
 static int tg_set_conf_uint(struct cgroup_subsys_state *css, struct cftype *cft,
-			    const char *buf)
+			    char *buf)
 {
 	return tg_set_conf(css, cft, buf, false);
 }
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 461187943392..f5de45b6af36 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1701,13 +1701,13 @@ static int __cfqg_set_weight_device(struct cgroup_subsys_state *css,
 }
 
 static int cfqg_set_weight_device(struct cgroup_subsys_state *css,
-				  struct cftype *cft, const char *buf)
+				  struct cftype *cft, char *buf)
 {
 	return __cfqg_set_weight_device(css, cft, buf, false);
 }
 
 static int cfqg_set_leaf_weight_device(struct cgroup_subsys_state *css,
-				       struct cftype *cft, const char *buf)
+				       struct cftype *cft, char *buf)
 {
 	return __cfqg_set_weight_device(css, cft, buf, true);
 }
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 77294fc66603..79993ac066c5 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -454,7 +454,7 @@ struct cftype {
 	 * Returns 0 or -ve error code.
 	 */
 	int (*write_string)(struct cgroup_subsys_state *css, struct cftype *cft,
-			    const char *buffer);
+			    char *buffer);
 	/*
 	 * trigger() callback can be used to get some kick from the
 	 * userspace, when the actual string written is not important
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 60ea16058c42..f5754910e80b 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2143,7 +2143,7 @@ static int cgroup_procs_write(struct cgroup_subsys_state *css,
 }
 
 static int cgroup_release_agent_write(struct cgroup_subsys_state *css,
-				      struct cftype *cft, const char *buffer)
+				      struct cftype *cft, char *buffer)
 {
 	struct cgroup_root *root = css->cgroup->root;
 
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index 2ea98b216bff..2bc4a2256444 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -442,7 +442,7 @@ static void freezer_change_state(struct freezer *freezer, bool freeze)
 }
 
 static int freezer_write(struct cgroup_subsys_state *css, struct cftype *cft,
-			 const char *buffer)
+			 char *buffer)
 {
 	bool freeze;
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 8d5324583aa4..efbf9baf77ec 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1610,7 +1610,7 @@ out_unlock:
  * Common handling for a write to a "cpus" or "mems" file.
  */
 static int cpuset_write_resmask(struct cgroup_subsys_state *css,
-				struct cftype *cft, const char *buf)
+				struct cftype *cft, char *buf)
 {
 	struct cpuset *cs = css_cs(css);
 	struct cpuset *trialcs;
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index b135853e68f3..595d7fd795e1 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -254,7 +254,7 @@ static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css,
 }
 
 static int hugetlb_cgroup_write(struct cgroup_subsys_state *css,
-				struct cftype *cft, const char *buffer)
+				struct cftype *cft, char *buffer)
 {
 	int idx, name, ret;
 	unsigned long long val;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d9c6ac1532e6..96f94a9f2faf 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5242,7 +5242,7 @@ static int memcg_update_kmem_limit(struct mem_cgroup *memcg,
  * RES_LIMIT.
  */
 static int mem_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft,
-			    const char *buffer)
+			    char *buffer)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	enum res_type type;
@@ -6063,7 +6063,7 @@ static void memcg_event_ptable_queue_proc(struct file *file,
  * Interpretation of args is defined by control file implementation.
  */
 static int memcg_write_event_control(struct cgroup_subsys_state *css,
-				     struct cftype *cft, const char *buffer)
+				     struct cftype *cft, char *buffer)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	struct mem_cgroup_event *event;
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index f9f3a40d3350..3825f669147b 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -186,7 +186,7 @@ static int read_priomap(struct seq_file *sf, void *v)
 }
 
 static int write_priomap(struct cgroup_subsys_state *css, struct cftype *cft,
-			 const char *buffer)
+			 char *buffer)
 {
 	char devname[IFNAMSIZ + 1];
 	struct net_device *dev;
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 20a0aca9131e..d4f015ad6c84 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -103,7 +103,7 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 }
 
 static int tcp_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft,
-			    const char *buffer)
+			    char *buffer)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	unsigned long long val;
diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index 7f88bcde7c61..8365909f5f8c 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -496,7 +496,7 @@ static inline bool has_children(struct dev_cgroup *devcgroup)
  * parent cgroup has the access you're asking for.
  */
 static int devcgroup_update_access(struct dev_cgroup *devcgroup,
-				   int filetype, const char *buffer)
+				   int filetype, char *buffer)
 {
 	const char *b;
 	char temp[12];		/* 11 + 1 characters needed for a u32 */
@@ -652,7 +652,7 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup,
 }
 
 static int devcgroup_access_write(struct cgroup_subsys_state *css,
-				  struct cftype *cft, const char *buffer)
+				  struct cftype *cft, char *buffer)
 {
 	int retval;
 
-- 
cgit v1.2.3


From a2dd424750807f83632a2a70293961086fd8f870 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 19 Mar 2014 10:23:55 -0400
Subject: cgroup: make cgrp_dfl_root mountable

cgrp_dfl_root will be used as the default unified hierarchy.  This
patch makes cgrp_dfl_root mountable by making the following changes.

* cgroup_init_early() now initializes cgrp_dfl_root w/
  CGRP_ROOT_SANE_BEHAVIOR.  The default hierarchy is always sane.

* parse_cgroupfs_options() and cgroup_mount() are updated such that
  cgrp_dfl_root is mounted if sane_behavior is specified w/o any
  subsystems.

* rebind_subsystems() now populates the root directory of
  cgrp_dfl_root.  Note that the function still guarantees success of
  rebinding subsystems to cgrp_dfl_root.  If populating fails while
  rebinding to cgrp_dfl_root, it whines but ignores the error.

* For backward compatibility, the default hierarchy shows up in
  /proc/$PID/cgroup only after it's explicitly mounted so that
  userland which doesn't make use of it doesn't see any change.

* "current_css_set_cg_links" file of debug cgroup now treats the
  default hierarchy the same as other hierarchies.  This is visible to
  userland.  Given that it's for debug controller, this should be
  fine.

* While at it, implement cgroup_on_dfl() which tests whether a give
  cgroup is on the default hierarchy or not.

The above changes make cgrp_dfl_root mostly equivalent to other
controllers but the actual unified hierarchy behaviors are not
implemented yet.  Let's plug child cgroup creation in cgrp_dfl_root
from create_cgroup() for now.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h | 10 ++++++
 kernel/cgroup.c        | 94 ++++++++++++++++++++++++++++++++------------------
 2 files changed, 71 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 79993ac066c5..7e9fa505b7bb 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -250,6 +250,9 @@ enum {
 	 *
 	 * - "cgroup.clone_children" is removed.
 	 *
+	 * - If mount is requested with sane_behavior but without any
+	 *   subsystem, the default unified hierarchy is mounted.
+	 *
 	 * - cpuset: tasks will be kept in empty cpusets when hotplug happens
 	 *   and take masks of ancestors with non-empty cpus/mems, instead of
 	 *   being moved to an ancestor.
@@ -468,6 +471,13 @@ struct cftype {
 #endif
 };
 
+extern struct cgroup_root cgrp_dfl_root;
+
+static inline bool cgroup_on_dfl(const struct cgroup *cgrp)
+{
+	return cgrp->root == &cgrp_dfl_root;
+}
+
 /*
  * See the comment above CGRP_ROOT_SANE_BEHAVIOR for details.  This
  * function can be called as long as @cgrp is accessible.
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index f5754910e80b..69b4939e9f6d 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -142,7 +142,13 @@ static const char *cgroup_subsys_name[] = {
  * unattached - it never has more than a single cgroup, and all tasks are
  * part of that cgroup.
  */
-static struct cgroup_root cgrp_dfl_root;
+struct cgroup_root cgrp_dfl_root;
+
+/*
+ * The default hierarchy always exists but is hidden until mounted for the
+ * first time.  This is for backward compatibility.
+ */
+static bool cgrp_dfl_root_visible;
 
 /* The list of hierarchy roots */
 
@@ -999,10 +1005,22 @@ static int rebind_subsystems(struct cgroup_root *dst_root,
 			return -EBUSY;
 	}
 
-	if (dst_root != &cgrp_dfl_root) {
-		ret = cgroup_populate_dir(&dst_root->cgrp, ss_mask);
-		if (ret)
+	ret = cgroup_populate_dir(&dst_root->cgrp, ss_mask);
+	if (ret) {
+		if (dst_root != &cgrp_dfl_root)
 			return ret;
+
+		/*
+		 * Rebinding back to the default root is not allowed to
+		 * fail.  Using both default and non-default roots should
+		 * be rare.  Moving subsystems back and forth even more so.
+		 * Just warn about it and continue.
+		 */
+		if (cgrp_dfl_root_visible) {
+			pr_warning("cgroup: failed to create files (%d) while rebinding 0x%lx to default root\n",
+				   ret, ss_mask);
+			pr_warning("cgroup: you may retry by moving them to a different hierarchy and unbinding\n");
+		}
 	}
 
 	/*
@@ -1011,7 +1029,7 @@ static int rebind_subsystems(struct cgroup_root *dst_root,
 	 */
 	mutex_unlock(&cgroup_mutex);
 	for_each_subsys(ss, ssid)
-		if ((ss_mask & (1 << ssid)) && ss->root != &cgrp_dfl_root)
+		if (ss_mask & (1 << ssid))
 			cgroup_clear_dir(&ss->root->cgrp, 1 << ssid);
 	mutex_lock(&cgroup_mutex);
 
@@ -1039,8 +1057,7 @@ static int rebind_subsystems(struct cgroup_root *dst_root,
 			ss->bind(css);
 	}
 
-	if (dst_root != &cgrp_dfl_root)
-		kernfs_activate(dst_root->cgrp.kn);
+	kernfs_activate(dst_root->cgrp.kn);
 	return 0;
 }
 
@@ -1190,16 +1207,6 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 			return -ENOENT;
 	}
 
-	/*
-	 * If the 'all' option was specified select all the subsystems,
-	 * otherwise if 'none', 'name=' and a subsystem name options
-	 * were not specified, let's default to 'all'
-	 */
-	if (all_ss || (!one_ss && !opts->none && !opts->name))
-		for_each_subsys(ss, i)
-			if (!ss->disabled)
-				set_bit(i, &opts->subsys_mask);
-
 	/* Consistency checks */
 
 	if (opts->flags & CGRP_ROOT_SANE_BEHAVIOR) {
@@ -1211,6 +1218,23 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 			pr_err("cgroup: sane_behavior: noprefix, xattr, clone_children, release_agent and name are not allowed\n");
 			return -EINVAL;
 		}
+	} else {
+		/*
+		 * If the 'all' option was specified select all the
+		 * subsystems, otherwise if 'none', 'name=' and a subsystem
+		 * name options were not specified, let's default to 'all'
+		 */
+		if (all_ss || (!one_ss && !opts->none && !opts->name))
+			for_each_subsys(ss, i)
+				if (!ss->disabled)
+					set_bit(i, &opts->subsys_mask);
+
+		/*
+		 * We either have to specify by name or by subsystems. (So
+		 * all empty hierarchies must have a name).
+		 */
+		if (!opts->subsys_mask && !opts->name)
+			return -EINVAL;
 	}
 
 	/*
@@ -1226,13 +1250,6 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 	if (opts->subsys_mask && opts->none)
 		return -EINVAL;
 
-	/*
-	 * We either have to specify by name or by subsystems. (So all
-	 * empty hierarchies must have a name).
-	 */
-	if (!opts->subsys_mask && !opts->name)
-		return -EINVAL;
-
 	return 0;
 }
 
@@ -1487,6 +1504,14 @@ retry:
 		goto out_unlock;
 
 	/* look for a matching existing root */
+	if (!opts.subsys_mask && !opts.none && !opts.name) {
+		cgrp_dfl_root_visible = true;
+		root = &cgrp_dfl_root;
+		cgroup_get(&root->cgrp);
+		ret = 0;
+		goto out_unlock;
+	}
+
 	for_each_root(root) {
 		bool name_match = false;
 
@@ -3622,6 +3647,13 @@ static long cgroup_create(struct cgroup *parent, const char *name,
 	struct cgroup_subsys *ss;
 	struct kernfs_node *kn;
 
+	/*
+	 * XXX: The default hierarchy isn't fully implemented yet.  Block
+	 * !root cgroup creation on it for now.
+	 */
+	if (root == &cgrp_dfl_root)
+		return -EINVAL;
+
 	/* allocate the cgroup and its ID, 0 is reserved for the root */
 	cgrp = kzalloc(sizeof(*cgrp), GFP_KERNEL);
 	if (!cgrp)
@@ -4061,7 +4093,8 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
  */
 int __init cgroup_init_early(void)
 {
-	static struct cgroup_sb_opts __initdata opts = { };
+	static struct cgroup_sb_opts __initdata opts =
+		{ .flags = CGRP_ROOT_SANE_BEHAVIOR };
 	struct cgroup_subsys *ss;
 	int i;
 
@@ -4198,7 +4231,7 @@ int proc_cgroup_show(struct seq_file *m, void *v)
 		struct cgroup *cgrp;
 		int ssid, count = 0;
 
-		if (root == &cgrp_dfl_root)
+		if (root == &cgrp_dfl_root && !cgrp_dfl_root_visible)
 			continue;
 
 		seq_printf(m, "%d:", root->hierarchy_id);
@@ -4631,15 +4664,10 @@ static int current_css_set_cg_links_read(struct seq_file *seq, void *v)
 	cset = rcu_dereference(current->cgroups);
 	list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
 		struct cgroup *c = link->cgrp;
-		const char *name = "?";
-
-		if (c != &cgrp_dfl_root.cgrp) {
-			cgroup_name(c, name_buf, NAME_MAX + 1);
-			name = name_buf;
-		}
 
+		cgroup_name(c, name_buf, NAME_MAX + 1);
 		seq_printf(seq, "Root %d group %s\n",
-			   c->root->hierarchy_id, name);
+			   c->root->hierarchy_id, name_buf);
 	}
 	rcu_read_unlock();
 	up_read(&css_set_rwsem);
-- 
cgit v1.2.3


From 8cbbf2c972c4444cad36f61cd571714c39b8cf04 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 19 Mar 2014 10:23:55 -0400
Subject: cgroup: implement CFTYPE_ONLY_ON_DFL

This cftype flag makes the file only appear on the default hierarchy.
This will later be used for cgroup.controllers file.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/cgroup.h | 1 +
 kernel/cgroup.c        | 2 ++
 2 files changed, 3 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 7e9fa505b7bb..43d1ed30bae3 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -384,6 +384,7 @@ enum {
 	CFTYPE_NOT_ON_ROOT	= (1 << 1),	/* don't create on root cgrp */
 	CFTYPE_INSANE		= (1 << 2),	/* don't create if sane_behavior */
 	CFTYPE_NO_PREFIX	= (1 << 3),	/* (DON'T USE FOR NEW FILES) no subsys prefix */
+	CFTYPE_ONLY_ON_DFL	= (1 << 4),	/* only on default hierarchy */
 };
 
 #define MAX_CFTYPE_NAME		64
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 69b4939e9f6d..37b6d534b0ca 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2356,6 +2356,8 @@ static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
 
 	for (cft = cfts; cft->name[0] != '\0'; cft++) {
 		/* does cft->flags tell us to skip this file on @cgrp? */
+		if ((cft->flags & CFTYPE_ONLY_ON_DFL) && !cgroup_on_dfl(cgrp))
+			continue;
 		if ((cft->flags & CFTYPE_INSANE) && cgroup_sane_behavior(cgrp))
 			continue;
 		if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgrp->parent)
-- 
cgit v1.2.3


From 0829f6d1f69e4f2fae4062987ae6531a9af1a2e3 Mon Sep 17 00:00:00 2001
From: Pantelis Antoniou <panto@antoniou-consulting.com>
Date: Fri, 13 Dec 2013 20:08:59 +0200
Subject: of: device_node kobject lifecycle fixes

After the move to having device nodes be proper kobjects the lifecycle
of the node needs to be controlled better.

At first convert of_add_node() in the unflattened functions to
of_init_node() which initializes the kobject so that of_node_get/put
work correctly even before of_init is called.

Afterwards introduce of_node_is_initialized & of_node_is_attached that
query the underlying kobject about the state (attached means kobj
is visible in sysfs)

Using that make sure the lifecycle of the tree is correct at all
times.

Signed-off-by: Pantelis Antoniou <panto@antoniou-consulting.com>
[grant.likely: moved of_node_init() calls, fixed up locking, and
               dropped __of_populate() hunks]
Signed-off-by: Grant Likely <grant.likely@linaro.org>
---
 drivers/of/base.c  | 35 ++++++++++++++++++++++++++---------
 drivers/of/fdt.c   |  3 +--
 drivers/of/pdt.c   |  3 +--
 include/linux/of.h | 19 +++++++++++++++++++
 4 files changed, 47 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/of/base.c b/drivers/of/base.c
index ed3e70b84957..418a4ff9d97c 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -246,10 +246,19 @@ static int __of_node_add(struct device_node *np)
 int of_node_add(struct device_node *np)
 {
 	int rc = 0;
-	kobject_init(&np->kobj, &of_node_ktype);
+
+	BUG_ON(!of_node_is_initialized(np));
+
+	/*
+	 * Grab the mutex here so that in a race condition between of_init() and
+	 * of_node_add(), node addition will still be consistent.
+	 */
 	mutex_lock(&of_aliases_mutex);
 	if (of_kset)
 		rc = __of_node_add(np);
+	else
+		/* This scenario may be perfectly valid, but report it anyway */
+		pr_info("of_node_add(%s) before of_init()\n", np->full_name);
 	mutex_unlock(&of_aliases_mutex);
 	return rc;
 }
@@ -259,10 +268,17 @@ static void of_node_remove(struct device_node *np)
 {
 	struct property *pp;
 
-	for_each_property_of_node(np, pp)
-		sysfs_remove_bin_file(&np->kobj, &pp->attr);
+	BUG_ON(!of_node_is_initialized(np));
+
+	/* only remove properties if on sysfs */
+	if (of_node_is_attached(np)) {
+		for_each_property_of_node(np, pp)
+			sysfs_remove_bin_file(&np->kobj, &pp->attr);
+		kobject_del(&np->kobj);
+	}
 
-	kobject_del(&np->kobj);
+	/* finally remove the kobj_init ref */
+	of_node_put(np);
 }
 #endif
 
@@ -1631,6 +1647,10 @@ static int of_property_notify(int action, struct device_node *np,
 {
 	struct of_prop_reconfig pr;
 
+	/* only call notifiers if the node is attached */
+	if (!of_node_is_attached(np))
+		return 0;
+
 	pr.dn = np;
 	pr.prop = prop;
 	return of_reconfig_notify(action, &pr);
@@ -1682,11 +1702,8 @@ int of_add_property(struct device_node *np, struct property *prop)
 	if (rc)
 		return rc;
 
-	/* at early boot, bail hear and defer setup to of_init() */
-	if (!of_kset)
-		return 0;
-
-	__of_add_property_sysfs(np, prop);
+	if (of_node_is_attached(np))
+		__of_add_property_sysfs(np, prop);
 
 	return rc;
 }
diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 96ad1ab7f9d6..70ccc36513e7 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -202,6 +202,7 @@ static void * unflatten_dt_node(struct boot_param_header *blob,
 				__alignof__(struct device_node));
 	if (allnextpp) {
 		char *fn;
+		of_node_init(np);
 		np->full_name = fn = ((char *)np) + sizeof(*np);
 		if (new_format) {
 			/* rebuild full path for new format */
@@ -326,8 +327,6 @@ static void * unflatten_dt_node(struct boot_param_header *blob,
 			np->name = "<NULL>";
 		if (!np->type)
 			np->type = "<NULL>";
-
-		of_node_add(np);
 	}
 	while (tag == OF_DT_BEGIN_NODE || tag == OF_DT_NOP) {
 		if (tag == OF_DT_NOP)
diff --git a/drivers/of/pdt.c b/drivers/of/pdt.c
index e64fa3d3da5f..36b4035881b0 100644
--- a/drivers/of/pdt.c
+++ b/drivers/of/pdt.c
@@ -176,6 +176,7 @@ static struct device_node * __init of_pdt_create_node(phandle node,
 		return NULL;
 
 	dp = prom_early_alloc(sizeof(*dp));
+	of_node_init(dp);
 	of_pdt_incr_unique_id(dp);
 	dp->parent = parent;
 
@@ -213,7 +214,6 @@ static struct device_node * __init of_pdt_build_tree(struct device_node *parent,
 		*nextp = &dp->allnext;
 
 		dp->full_name = of_pdt_build_full_name(dp);
-		of_node_add(dp);
 
 		dp->child = of_pdt_build_tree(dp,
 				of_pdt_prom_ops->getchild(node), nextp);
@@ -244,7 +244,6 @@ void __init of_pdt_build_devicetree(phandle root_node, struct of_pdt_ops *ops)
 	of_allnodes->path_component_name = "";
 #endif
 	of_allnodes->full_name = "/";
-	of_node_add(of_allnodes);
 
 	nextp = &of_allnodes->allnext;
 	of_allnodes->child = of_pdt_build_tree(of_allnodes,
diff --git a/include/linux/of.h b/include/linux/of.h
index 257994a420f3..a8b9dad90c64 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -76,6 +76,25 @@ struct of_phandle_args {
 
 extern int of_node_add(struct device_node *node);
 
+/* initialize a node */
+extern struct kobj_type of_node_ktype;
+static inline void of_node_init(struct device_node *node)
+{
+	kobject_init(&node->kobj, &of_node_ktype);
+}
+
+/* true when node is initialized */
+static inline int of_node_is_initialized(struct device_node *node)
+{
+	return node && node->kobj.state_initialized;
+}
+
+/* true when node is attached (i.e. present on sysfs) */
+static inline int of_node_is_attached(struct device_node *node)
+{
+	return node && node->kobj.state_in_sysfs;
+}
+
 #ifdef CONFIG_OF_DYNAMIC
 extern struct device_node *of_node_get(struct device_node *node);
 extern void of_node_put(struct device_node *node);
-- 
cgit v1.2.3


From aa475b0ef34a8230b8cc3a298bf67c668540d689 Mon Sep 17 00:00:00 2001
From: Vladimir Kondratiev <qca_vkondrat@qca.qualcomm.com>
Date: Wed, 19 Mar 2014 13:14:40 +0200
Subject: wireless: max MSDU size for DMG networks

In the 802.11ad, aka DMG (Dynamic Multi-Gigabit), aka 60Ghz
spec, maximum MSDU size extended to 7920 bytes.
add #define for this.

Signed-off-by: Vladimir Kondratiev <qca_vkondrat@qca.qualcomm.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 5f349355ee54..cde7ede8e554 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -154,6 +154,10 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2)
    802.11e clarifies the figure in section 7.1.2. The frame body is
    up to 2304 octets long (maximum MSDU size) plus any crypt overhead. */
 #define IEEE80211_MAX_DATA_LEN		2304
+/* 802.11ad extends maximum MSDU size for DMG (freq > 40Ghz) networks
+ * to 7920 bytes, see 8.2.3 General frame format
+ */
+#define IEEE80211_MAX_DATA_LEN_DMG	7920
 /* 30 byte 4 addr hdr, 2 byte QoS, 2304 byte MSDU, 12 byte crypt, 4 byte FCS */
 #define IEEE80211_MAX_FRAME_LEN		2352
 
-- 
cgit v1.2.3


From 664c28480c90fb8541bcdd1d4b349e9436165ec7 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Fri, 7 Mar 2014 13:51:12 -0700
Subject: PCI: Change pci_bus_alloc_resource() type_mask to unsigned long

The pci_bus_alloc_resource() "type_mask" parameter is used to compare with
the "flags" member of a struct resource, so it should be the same type,
namely "unsigned long".

No functional change because all current IORESOURCE_* flags fit in 32 bits.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/bus.c   | 4 ++--
 include/linux/pci.h | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index e3bdc88668ec..fb8aed307c28 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -132,7 +132,7 @@ static void pci_clip_resource_to_region(struct pci_bus *bus,
 
 static int pci_bus_alloc_from_region(struct pci_bus *bus, struct resource *res,
 		resource_size_t size, resource_size_t align,
-		resource_size_t min, unsigned int type_mask,
+		resource_size_t min, unsigned long type_mask,
 		resource_size_t (*alignf)(void *,
 					  const struct resource *,
 					  resource_size_t,
@@ -200,7 +200,7 @@ static int pci_bus_alloc_from_region(struct pci_bus *bus, struct resource *res,
  */
 int pci_bus_alloc_resource(struct pci_bus *bus, struct resource *res,
 		resource_size_t size, resource_size_t align,
-		resource_size_t min, unsigned int type_mask,
+		resource_size_t min, unsigned long type_mask,
 		resource_size_t (*alignf)(void *,
 					  const struct resource *,
 					  resource_size_t,
diff --git a/include/linux/pci.h b/include/linux/pci.h
index fb57c892b214..60ebc17fe909 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1066,7 +1066,7 @@ void pci_bus_remove_resources(struct pci_bus *bus);
 int __must_check pci_bus_alloc_resource(struct pci_bus *bus,
 			struct resource *res, resource_size_t size,
 			resource_size_t align, resource_size_t min,
-			unsigned int type_mask,
+			unsigned long type_mask,
 			resource_size_t (*alignf)(void *,
 						  const struct resource *,
 						  resource_size_t,
-- 
cgit v1.2.3


From 5d12f905cc50c0810628d0deedd478ec2db48659 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@fb.com>
Date: Wed, 19 Mar 2014 15:25:02 -0600
Subject: blk-mq: fix wrong usage of hctx->state vs hctx->flags

BLK_MQ_F_* flags are for hctx->flags, and are non-atomic and
set at registration time. BLK_MQ_S_* flags are dynamic and
atomic, and are accessed through hctx->state.

Some of the BLK_MQ_S_STOPPED uses were wrong. Additionally,
the header file should not use a bit shift for the _S_ flags,
as they are done through the set/test_bit functions.

Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-mq.c         | 6 +++---
 include/linux/blk-mq.h | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 92284af4e0df..ed216f27e3b8 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -547,7 +547,7 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 	LIST_HEAD(rq_list);
 	int bit, queued;
 
-	if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->flags)))
+	if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
 		return;
 
 	hctx->run++;
@@ -636,7 +636,7 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 
 void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 {
-	if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->flags)))
+	if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
 		return;
 
 	if (!async)
@@ -656,7 +656,7 @@ void blk_mq_run_queues(struct request_queue *q, bool async)
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if ((!blk_mq_hctx_has_pending(hctx) &&
 		    list_empty_careful(&hctx->dispatch)) ||
-		    test_bit(BLK_MQ_S_STOPPED, &hctx->flags))
+		    test_bit(BLK_MQ_S_STOPPED, &hctx->state))
 			continue;
 
 		blk_mq_run_hw_queue(hctx, async);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 33ff10ebcabb..bb68b03741be 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -109,7 +109,7 @@ enum {
 	BLK_MQ_F_SHOULD_SORT	= 1 << 1,
 	BLK_MQ_F_SHOULD_IPI	= 1 << 2,
 
-	BLK_MQ_S_STOPPED	= 1 << 0,
+	BLK_MQ_S_STOPPED	= 0,
 
 	BLK_MQ_MAX_DEPTH	= 2048,
 };
-- 
cgit v1.2.3


From f167a64e9d67ebd03d304e369c12011cf2bffaf5 Mon Sep 17 00:00:00 2001
From: Jean Delvare <jdelvare@suse.de>
Date: Mon, 17 Mar 2014 15:49:10 +0100
Subject: video / output: Drop display output class support

It was only ever used by the ACPI video driver, and that only use case
vanished over 3 years ago (see commit 677bd810, "ACPI video: remove
output switching control".) So this is dead code and I guess we can
remove it now.

Signed-off-by: Jean Delvare <jdelvare@suse.de>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/video/Kconfig        |   6 --
 drivers/video/Makefile       |   2 -
 drivers/video/output.c       | 133 -------------------------------------------
 include/linux/video_output.h |  57 -------------------
 4 files changed, 198 deletions(-)
 delete mode 100644 drivers/video/output.c
 delete mode 100644 include/linux/video_output.h

(limited to 'include/linux')

diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
index dade5b7699bc..97a8f3a12a7b 100644
--- a/drivers/video/Kconfig
+++ b/drivers/video/Kconfig
@@ -27,12 +27,6 @@ config VGASTATE
        tristate
        default n
 
-config VIDEO_OUTPUT_CONTROL
-	tristate "Lowlevel video output switch controls"
-	help
-	  This framework adds support for low-level control of the video 
-	  output switch.
-
 config VIDEOMODE_HELPERS
 	bool
 
diff --git a/drivers/video/Makefile b/drivers/video/Makefile
index ae17ddf49a00..08d6a4ab3ace 100644
--- a/drivers/video/Makefile
+++ b/drivers/video/Makefile
@@ -172,8 +172,6 @@ obj-$(CONFIG_FB_SIMPLE)           += simplefb.o
 # the test framebuffer is last
 obj-$(CONFIG_FB_VIRTUAL)          += vfb.o
 
-#video output switch sysfs driver
-obj-$(CONFIG_VIDEO_OUTPUT_CONTROL) += output.o
 obj-$(CONFIG_VIDEOMODE_HELPERS) += display_timing.o videomode.o
 ifeq ($(CONFIG_OF),y)
 obj-$(CONFIG_VIDEOMODE_HELPERS) += of_display_timing.o of_videomode.o
diff --git a/drivers/video/output.c b/drivers/video/output.c
deleted file mode 100644
index 1446c49fe6af..000000000000
--- a/drivers/video/output.c
+++ /dev/null
@@ -1,133 +0,0 @@
-/*
- *  output.c - Display Output Switch driver
- *
- *  Copyright (C) 2006 Luming Yu <luming.yu@intel.com>
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or (at
- *  your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful, but
- *  WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- *  General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- */
-#include <linux/module.h>
-#include <linux/video_output.h>
-#include <linux/slab.h>
-#include <linux/err.h>
-#include <linux/ctype.h>
-
-
-MODULE_DESCRIPTION("Display Output Switcher Lowlevel Control Abstraction");
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Luming Yu <luming.yu@intel.com>");
-
-static ssize_t state_show(struct device *dev, struct device_attribute *attr,
-			  char *buf)
-{
-	ssize_t ret_size = 0;
-	struct output_device *od = to_output_device(dev);
-	if (od->props)
-		ret_size = sprintf(buf,"%.8x\n",od->props->get_status(od));
-	return ret_size;
-}
-
-static ssize_t state_store(struct device *dev, struct device_attribute *attr,
-			   const char *buf,size_t count)
-{
-	char *endp;
-	struct output_device *od = to_output_device(dev);
-	int request_state = simple_strtoul(buf,&endp,0);
-	size_t size = endp - buf;
-
-	if (isspace(*endp))
-		size++;
-	if (size != count)
-		return -EINVAL;
-
-	if (od->props) {
-		od->request_state = request_state;
-		od->props->set_state(od);
-	}
-	return count;
-}
-static DEVICE_ATTR_RW(state);
-
-static void video_output_release(struct device *dev)
-{
-	struct output_device *od = to_output_device(dev);
-	kfree(od);
-}
-
-static struct attribute *video_output_attrs[] = {
-	&dev_attr_state.attr,
-	NULL,
-};
-ATTRIBUTE_GROUPS(video_output);
-
-static struct class video_output_class = {
-	.name = "video_output",
-	.dev_release = video_output_release,
-	.dev_groups = video_output_groups,
-};
-
-struct output_device *video_output_register(const char *name,
-	struct device *dev,
-	void *devdata,
-	struct output_properties *op)
-{
-	struct output_device *new_dev;
-	int ret_code = 0;
-
-	new_dev = kzalloc(sizeof(struct output_device),GFP_KERNEL);
-	if (!new_dev) {
-		ret_code = -ENOMEM;
-		goto error_return;
-	}
-	new_dev->props = op;
-	new_dev->dev.class = &video_output_class;
-	new_dev->dev.parent = dev;
-	dev_set_name(&new_dev->dev, "%s", name);
-	dev_set_drvdata(&new_dev->dev, devdata);
-	ret_code = device_register(&new_dev->dev);
-	if (ret_code) {
-		kfree(new_dev);
-		goto error_return;
-	}
-	return new_dev;
-
-error_return:
-	return ERR_PTR(ret_code);
-}
-EXPORT_SYMBOL(video_output_register);
-
-void video_output_unregister(struct output_device *dev)
-{
-	if (!dev)
-		return;
-	device_unregister(&dev->dev);
-}
-EXPORT_SYMBOL(video_output_unregister);
-
-static void __exit video_output_class_exit(void)
-{
-	class_unregister(&video_output_class);
-}
-
-static int __init video_output_class_init(void)
-{
-	return class_register(&video_output_class);
-}
-
-postcore_initcall(video_output_class_init);
-module_exit(video_output_class_exit);
diff --git a/include/linux/video_output.h b/include/linux/video_output.h
deleted file mode 100644
index ed5cdeb3604d..000000000000
--- a/include/linux/video_output.h
+++ /dev/null
@@ -1,57 +0,0 @@
-/*
- *
- *  Copyright (C) 2006 Luming Yu <luming.yu@intel.com>
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or (at
- *  your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful, but
- *  WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- *  General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- */
-#ifndef _LINUX_VIDEO_OUTPUT_H
-#define _LINUX_VIDEO_OUTPUT_H
-#include <linux/device.h>
-#include <linux/err.h>
-struct output_device;
-struct output_properties {
-	int (*set_state)(struct output_device *);
-	int (*get_status)(struct output_device *);
-};
-struct output_device {
-	int request_state;
-	struct output_properties *props;
-	struct device dev;
-};
-#define to_output_device(obj) container_of(obj, struct output_device, dev)
-#if	defined(CONFIG_VIDEO_OUTPUT_CONTROL) || defined(CONFIG_VIDEO_OUTPUT_CONTROL_MODULE)
-struct output_device *video_output_register(const char *name,
-	struct device *dev,
-	void *devdata,
-	struct output_properties *op);
-void video_output_unregister(struct output_device *dev);
-#else
-static struct output_device *video_output_register(const char *name,
-        struct device *dev,
-        void *devdata,
-        struct output_properties *op)
-{
-	return ERR_PTR(-ENODEV);
-}
-static void video_output_unregister(struct output_device *dev)
-{
-	return;
-}
-#endif
-#endif
-- 
cgit v1.2.3


From d20f78d252778e0fae8f8256e602bd682eb2185c Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin" <hpa@linux.intel.com>
Date: Mon, 17 Mar 2014 16:36:27 -0700
Subject: x86, random: Enable the RDSEED instruction

Upcoming Intel silicon adds a new RDSEED instruction, which is similar
to RDRAND but provides a stronger guarantee: unlike RDRAND, RDSEED
will always reseed the PRNG from the true random number source between
each read.  Thus, the output of RDSEED is guaranteed to be 100%
entropic, unlike RDRAND which is only architecturally guaranteed to be
1/512 entropic (although in practice is much more.)

The RDSEED instruction takes the same time to execute as RDRAND, but
RDSEED unlike RDRAND can legitimately return failure (CF=0) due to
entropy exhaustion if too many threads on too many cores are hammering
the RDSEED instruction at the same time.  Therefore, we have to be
more conservative and only use it in places where we can tolerate
failures.

This patch introduces the primitives arch_get_random_seed_{int,long}()
but does not use it yet.

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 arch/powerpc/include/asm/archrandom.h |  9 ++++++++
 arch/x86/include/asm/archrandom.h     | 39 ++++++++++++++++++++++++++++++++++-
 include/linux/random.h                |  8 +++++++
 3 files changed, 55 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/arch/powerpc/include/asm/archrandom.h b/arch/powerpc/include/asm/archrandom.h
index d853d163ba47..801beba4e64b 100644
--- a/arch/powerpc/include/asm/archrandom.h
+++ b/arch/powerpc/include/asm/archrandom.h
@@ -27,6 +27,15 @@ static inline int arch_get_random_int(unsigned int *v)
 
 int powernv_get_random_long(unsigned long *v);
 
+static inline int arch_get_random_seed_long(unsigned long *v)
+{
+	return 0;
+}
+static inline int arch_get_random_seed_int(unsigned int *v)
+{
+	return 0;
+}
+
 #endif /* CONFIG_ARCH_RANDOM */
 
 #endif /* _ASM_POWERPC_ARCHRANDOM_H */
diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h
index e6a92455740e..6ad7f6d3f97f 100644
--- a/arch/x86/include/asm/archrandom.h
+++ b/arch/x86/include/asm/archrandom.h
@@ -1,7 +1,7 @@
 /*
  * This file is part of the Linux kernel.
  *
- * Copyright (c) 2011, Intel Corporation
+ * Copyright (c) 2011-2014, Intel Corporation
  * Authors: Fenghua Yu <fenghua.yu@intel.com>,
  *          H. Peter Anvin <hpa@linux.intel.com>
  *
@@ -31,10 +31,13 @@
 #define RDRAND_RETRY_LOOPS	10
 
 #define RDRAND_INT	".byte 0x0f,0xc7,0xf0"
+#define RDSEED_INT	".byte 0x0f,0xc7,0xf8"
 #ifdef CONFIG_X86_64
 # define RDRAND_LONG	".byte 0x48,0x0f,0xc7,0xf0"
+# define RDSEED_LONG	".byte 0x48,0x0f,0xc7,0xf8"
 #else
 # define RDRAND_LONG	RDRAND_INT
+# define RDSEED_LONG	RDSEED_INT
 #endif
 
 #ifdef CONFIG_ARCH_RANDOM
@@ -53,6 +56,16 @@ static inline int rdrand_long(unsigned long *v)
 	return ok;
 }
 
+/* A single attempt at RDSEED */
+static inline bool rdseed_long(unsigned long *v)
+{
+	unsigned char ok;
+	asm volatile(RDSEED_LONG "\n\t"
+		     "setc %0"
+		     : "=qm" (ok), "=a" (*v));
+	return ok;
+}
+
 #define GET_RANDOM(name, type, rdrand, nop)			\
 static inline int name(type *v)					\
 {								\
@@ -70,16 +83,35 @@ static inline int name(type *v)					\
 	return ok;						\
 }
 
+#define GET_SEED(name, type, rdseed, nop)			\
+static inline int name(type *v)					\
+{								\
+	unsigned char ok;					\
+	alternative_io("movb $0, %0\n\t"			\
+		       nop,					\
+		       rdseed "\n\t"				\
+		       "setc %0",				\
+		       X86_FEATURE_RDSEED,                      \
+		       ASM_OUTPUT2("=q" (ok), "=a" (*v)));	\
+	return ok;						\
+}
+
 #ifdef CONFIG_X86_64
 
 GET_RANDOM(arch_get_random_long, unsigned long, RDRAND_LONG, ASM_NOP5);
 GET_RANDOM(arch_get_random_int, unsigned int, RDRAND_INT, ASM_NOP4);
 
+GET_SEED(arch_get_random_seed_long, unsigned long, RDSEED_LONG, ASM_NOP5);
+GET_SEED(arch_get_random_seed_int, unsigned int, RDSEED_INT, ASM_NOP4);
+
 #else
 
 GET_RANDOM(arch_get_random_long, unsigned long, RDRAND_LONG, ASM_NOP3);
 GET_RANDOM(arch_get_random_int, unsigned int, RDRAND_INT, ASM_NOP3);
 
+GET_SEED(arch_get_random_seed_long, unsigned long, RDSEED_LONG, ASM_NOP4);
+GET_SEED(arch_get_random_seed_int, unsigned int, RDSEED_INT, ASM_NOP4);
+
 #endif /* CONFIG_X86_64 */
 
 #else
@@ -89,6 +121,11 @@ static inline int rdrand_long(unsigned long *v)
 	return 0;
 }
 
+static inline bool rdseed_long(unsigned long *v)
+{
+	return 0;
+}
+
 #endif  /* CONFIG_ARCH_RANDOM */
 
 extern void x86_init_rdrand(struct cpuinfo_x86 *c);
diff --git a/include/linux/random.h b/include/linux/random.h
index 1cfce0e24dbd..c2f08131050d 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -88,6 +88,14 @@ static inline int arch_get_random_int(unsigned int *v)
 {
 	return 0;
 }
+static inline int arch_get_random_seed_long(unsigned long *v)
+{
+	return 0;
+}
+static inline int arch_get_random_seed_int(unsigned int *v)
+{
+	return 0;
+}
 #endif
 
 /* Pseudo random number generator from numerical recipes. */
-- 
cgit v1.2.3


From 7b878d4b48c4e04b936918bb83836a107ba453b3 Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin" <hpa@linux.intel.com>
Date: Mon, 17 Mar 2014 16:36:30 -0700
Subject: random: Add arch_has_random[_seed]()

Add predicate functions for having arch_get_random[_seed]*().  The
only current use is to avoid the loop in arch_random_refill() when
arch_get_random_seed_long() is unavailable.

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 arch/powerpc/include/asm/archrandom.h | 9 +++++++++
 arch/x86/include/asm/archrandom.h     | 3 +++
 drivers/char/random.c                 | 3 +++
 include/linux/random.h                | 8 ++++++++
 4 files changed, 23 insertions(+)

(limited to 'include/linux')

diff --git a/arch/powerpc/include/asm/archrandom.h b/arch/powerpc/include/asm/archrandom.h
index 801beba4e64b..bde531103638 100644
--- a/arch/powerpc/include/asm/archrandom.h
+++ b/arch/powerpc/include/asm/archrandom.h
@@ -25,6 +25,11 @@ static inline int arch_get_random_int(unsigned int *v)
 	return rc;
 }
 
+static inline int arch_has_random(void)
+{
+	return !!ppc_md.get_random_long;
+}
+
 int powernv_get_random_long(unsigned long *v);
 
 static inline int arch_get_random_seed_long(unsigned long *v)
@@ -35,6 +40,10 @@ static inline int arch_get_random_seed_int(unsigned int *v)
 {
 	return 0;
 }
+static inline int arch_has_random_seed(void)
+{
+	return 0;
+}
 
 #endif /* CONFIG_ARCH_RANDOM */
 
diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h
index 6ad7f6d3f97f..69f1366f1aa3 100644
--- a/arch/x86/include/asm/archrandom.h
+++ b/arch/x86/include/asm/archrandom.h
@@ -114,6 +114,9 @@ GET_SEED(arch_get_random_seed_int, unsigned int, RDSEED_INT, ASM_NOP4);
 
 #endif /* CONFIG_X86_64 */
 
+#define arch_has_random()	static_cpu_has(X86_FEATURE_RDRAND)
+#define arch_has_random_seed()	static_cpu_has(X86_FEATURE_RDSEED)
+
 #else
 
 static inline int rdrand_long(unsigned long *v)
diff --git a/drivers/char/random.c b/drivers/char/random.c
index c35cee268e13..6b75713d953a 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1307,6 +1307,9 @@ static int arch_random_refill(void)
 	unsigned int i;
 	unsigned long buf[nlongs];
 
+	if (!arch_has_random_seed())
+		return 0;
+
 	for (i = 0; i < nlongs; i++) {
 		if (arch_get_random_seed_long(&buf[n]))
 			n++;
diff --git a/include/linux/random.h b/include/linux/random.h
index c2f08131050d..57fbbffd77a0 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -88,6 +88,10 @@ static inline int arch_get_random_int(unsigned int *v)
 {
 	return 0;
 }
+static inline int arch_has_random(void)
+{
+	return 0;
+}
 static inline int arch_get_random_seed_long(unsigned long *v)
 {
 	return 0;
@@ -96,6 +100,10 @@ static inline int arch_get_random_seed_int(unsigned int *v)
 {
 	return 0;
 }
+static inline int arch_has_random_seed(void)
+{
+	return 0;
+}
 #endif
 
 /* Pseudo random number generator from numerical recipes. */
-- 
cgit v1.2.3


From 651665dbfdfca3201966c72edefdb0391160bea9 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@linux-m68k.org>
Date: Mon, 17 Mar 2014 21:26:11 +0100
Subject: PM / Runtime: Update runtime_idle() documentation for return value
 meaning

As of commit 45f0a85c8258 ('PM / Runtime: Rework the "runtime idle"
helper routine'), the return value of ->runtime_idle() is no longer
ignored by the PM core, but used to decide whether to suspend the
device or not.

Update the documentation to match the code.

Signed-off-by: Geert Uytterhoeven <geert+renesas@linux-m68k.org>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pm.h b/include/linux/pm.h
index 8c6583a53a06..0298b5e5de01 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -264,9 +264,9 @@ typedef struct pm_message {
  *	registers, so that it is fully operational.
  *
  * @runtime_idle: Device appears to be inactive and it might be put into a
- *	low-power state if all of the necessary conditions are satisfied.  Check
- *	these conditions and handle the device as appropriate, possibly queueing
- *	a suspend request for it.  The return value is ignored by the PM core.
+ *	low-power state if all of the necessary conditions are satisfied.
+ *	Check these conditions, and return 0 if it's appropriate to let the PM
+ *	core queue a suspend request for the device.
  *
  * Refer to Documentation/power/runtime_pm.txt for more information about the
  * role of the above callbacks in device runtime power management.
-- 
cgit v1.2.3


From 367dc4aa932bfb33a3189064d33f7890a8ec1ca8 Mon Sep 17 00:00:00 2001
From: Dirk Brandewie <dirk.j.brandewie@intel.com>
Date: Wed, 19 Mar 2014 08:45:53 -0700
Subject: cpufreq: Add stop CPU callback to cpufreq_driver interface

This callback allows the driver to do clean up before the CPU is
completely down and its state cannot be modified.  This is used
by the intel_pstate driver to reduce the requested P state prior to
the core going away.  This is required because the requested P state
of the offline core is used to select the package P state. This
effectively sets the floor package P state to the requested P state on
the offline core.

Signed-off-by: Dirk Brandewie <dirk.j.brandewie@intel.com>
[rjw: Minor modifications]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/cpu-freq/cpu-drivers.txt | 8 +++++++-
 drivers/cpufreq/cpufreq.c              | 2 ++
 include/linux/cpufreq.h                | 1 +
 3 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/Documentation/cpu-freq/cpu-drivers.txt b/Documentation/cpu-freq/cpu-drivers.txt
index 8b1a4451422e..48da5fdcb9f1 100644
--- a/Documentation/cpu-freq/cpu-drivers.txt
+++ b/Documentation/cpu-freq/cpu-drivers.txt
@@ -61,7 +61,13 @@ target_index		-	See below on the differences.
 
 And optionally
 
-cpufreq_driver.exit -		A pointer to a per-CPU cleanup function.
+cpufreq_driver.exit -		A pointer to a per-CPU cleanup
+				function called during CPU_POST_DEAD
+				phase of cpu hotplug process.
+
+cpufreq_driver.stop_cpu -	A pointer to a per-CPU stop function
+				called during CPU_DOWN_PREPARE phase of
+				cpu hotplug process.
 
 cpufreq_driver.resume -		A pointer to a per-CPU resume function
 				which is called with interrupts disabled
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 3c56c4759aa1..3aa7a7a226b3 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1337,6 +1337,8 @@ static int __cpufreq_remove_dev_prepare(struct device *dev,
 				pr_debug("%s: policy Kobject moved to cpu: %d from: %d\n",
 					 __func__, new_cpu, cpu);
 		}
+	} else if (cpufreq_driver->stop_cpu && cpufreq_driver->setpolicy) {
+		cpufreq_driver->stop_cpu(policy);
 	}
 
 	return 0;
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 70929bcf1a9d..2d2e62c8666a 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -227,6 +227,7 @@ struct cpufreq_driver {
 	int	(*bios_limit)	(int cpu, unsigned int *limit);
 
 	int	(*exit)		(struct cpufreq_policy *policy);
+	void	(*stop_cpu)	(struct cpufreq_policy *policy);
 	int	(*suspend)	(struct cpufreq_policy *policy);
 	int	(*resume)	(struct cpufreq_policy *policy);
 	struct freq_attr	**attr;
-- 
cgit v1.2.3


From 33fe0ad946bbb0a2f04f551fce68a74d8821f32e Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@linux-m68k.org>
Date: Mon, 17 Mar 2014 21:26:10 +0100
Subject: PM / sleep: Correct whitespace errors in <linux/pm.h>

rjw> Why exactly are they errors?
Geert> checkpatch.pl says: "WARNING: please, no space before tabs",
       Vim (with "let c_space_errors=1") shows them in red.

Signed-off-by: Geert Uytterhoeven <geert+renesas@linux-m68k.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm.h | 32 ++++++++++++++++----------------
 1 file changed, 16 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pm.h b/include/linux/pm.h
index 6fffbcd7bc37..f902ad83986e 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -379,7 +379,7 @@ const struct dev_pm_ops name = { \
  *
  * ON		No transition.
  *
- * FREEZE 	System is going to hibernate, call ->prepare() and ->freeze()
+ * FREEZE	System is going to hibernate, call ->prepare() and ->freeze()
  *		for all devices.
  *
  * SUSPEND	System is going to suspend, call ->prepare() and ->suspend()
@@ -423,7 +423,7 @@ const struct dev_pm_ops name = { \
 
 #define PM_EVENT_INVALID	(-1)
 #define PM_EVENT_ON		0x0000
-#define PM_EVENT_FREEZE 	0x0001
+#define PM_EVENT_FREEZE		0x0001
 #define PM_EVENT_SUSPEND	0x0002
 #define PM_EVENT_HIBERNATE	0x0004
 #define PM_EVENT_QUIESCE	0x0008
@@ -614,11 +614,11 @@ struct dev_pm_domain {
  * message is implicit:
  *
  * ON		Driver starts working again, responding to hardware events
- * 		and software requests.  The hardware may have gone through
- * 		a power-off reset, or it may have maintained state from the
- * 		previous suspend() which the driver will rely on while
- * 		resuming.  On most platforms, there are no restrictions on
- * 		availability of resources like clocks during resume().
+ *		and software requests.  The hardware may have gone through
+ *		a power-off reset, or it may have maintained state from the
+ *		previous suspend() which the driver will rely on while
+ *		resuming.  On most platforms, there are no restrictions on
+ *		availability of resources like clocks during resume().
  *
  * Other transitions are triggered by messages sent using suspend().  All
  * these transitions quiesce the driver, so that I/O queues are inactive.
@@ -628,21 +628,21 @@ struct dev_pm_domain {
  * differ according to the message:
  *
  * SUSPEND	Quiesce, enter a low power device state appropriate for
- * 		the upcoming system state (such as PCI_D3hot), and enable
- * 		wakeup events as appropriate.
+ *		the upcoming system state (such as PCI_D3hot), and enable
+ *		wakeup events as appropriate.
  *
  * HIBERNATE	Enter a low power device state appropriate for the hibernation
- * 		state (eg. ACPI S4) and enable wakeup events as appropriate.
+ *		state (eg. ACPI S4) and enable wakeup events as appropriate.
  *
  * FREEZE	Quiesce operations so that a consistent image can be saved;
- * 		but do NOT otherwise enter a low power device state, and do
- * 		NOT emit system wakeup events.
+ *		but do NOT otherwise enter a low power device state, and do
+ *		NOT emit system wakeup events.
  *
  * PRETHAW	Quiesce as if for FREEZE; additionally, prepare for restoring
- * 		the system from a snapshot taken after an earlier FREEZE.
- * 		Some drivers will need to reset their hardware state instead
- * 		of preserving it, to ensure that it's never mistaken for the
- * 		state which that earlier snapshot had set up.
+ *		the system from a snapshot taken after an earlier FREEZE.
+ *		Some drivers will need to reset their hardware state instead
+ *		of preserving it, to ensure that it's never mistaken for the
+ *		state which that earlier snapshot had set up.
  *
  * A minimally power-aware driver treats all messages as SUSPEND, fully
  * reinitializes its device during resume() -- whether or not it was reset
-- 
cgit v1.2.3


From 93ae4f978ca7f26d17df915ac7afc919c1dd0353 Mon Sep 17 00:00:00 2001
From: "Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com>
Date: Tue, 11 Mar 2014 02:04:14 +0530
Subject: CPU hotplug: Provide lockless versions of callback registration
 functions

The following method of CPU hotplug callback registration is not safe
due to the possibility of an ABBA deadlock involving the cpu_add_remove_lock
and the cpu_hotplug.lock.

	get_online_cpus();

	for_each_online_cpu(cpu)
		init_cpu(cpu);

	register_cpu_notifier(&foobar_cpu_notifier);

	put_online_cpus();

The deadlock is shown below:

          CPU 0                                         CPU 1
          -----                                         -----

   Acquire cpu_hotplug.lock
   [via get_online_cpus()]

                                              CPU online/offline operation
                                              takes cpu_add_remove_lock
                                              [via cpu_maps_update_begin()]

   Try to acquire
   cpu_add_remove_lock
   [via register_cpu_notifier()]

                                              CPU online/offline operation
                                              tries to acquire cpu_hotplug.lock
                                              [via cpu_hotplug_begin()]

                            *** DEADLOCK! ***

The problem here is that callback registration takes the locks in one order
whereas the CPU hotplug operations take the same locks in the opposite order.
To avoid this issue and to provide a race-free method to register CPU hotplug
callbacks (along with initialization of already online CPUs), introduce new
variants of the callback registration APIs that simply register the callbacks
without holding the cpu_add_remove_lock during the registration. That way,
we can avoid the ABBA scenario. However, we will need to hold the
cpu_add_remove_lock throughout the entire critical section, to protect updates
to the callback/notifier chain.

This can be achieved by writing the callback registration code as follows:

	cpu_maps_update_begin(); [ or cpu_notifier_register_begin(); see below ]

	for_each_online_cpu(cpu)
		init_cpu(cpu);

	/* This doesn't take the cpu_add_remove_lock */
	__register_cpu_notifier(&foobar_cpu_notifier);

	cpu_maps_update_done();  [ or cpu_notifier_register_done(); see below ]

Note that we can't use get_online_cpus() here instead of cpu_maps_update_begin()
because the cpu_hotplug.lock is dropped during the invocation of CPU_POST_DEAD
notifiers, and hence get_online_cpus() cannot provide the necessary
synchronization to protect the callback/notifier chains against concurrent
reads and writes. On the other hand, since the cpu_add_remove_lock protects
the entire hotplug operation (including CPU_POST_DEAD), we can use
cpu_maps_update_begin/done() to guarantee proper synchronization.

Also, since cpu_maps_update_begin/done() is like a super-set of
get/put_online_cpus(), the former naturally protects the critical sections
from concurrent hotplug operations.

Since the names cpu_maps_update_begin/done() don't make much sense in CPU
hotplug callback registration scenarios, we'll introduce new APIs named
cpu_notifier_register_begin/done() and map them to cpu_maps_update_begin/done().

In summary, introduce the lockless variants of un/register_cpu_notifier() and
also export the cpu_notifier_register_begin/done() APIs for use by modules.
This way, we provide a race-free way to register hotplug callbacks as well as
perform initialization for the CPUs that are already online.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Toshi Kani <toshi.kani@hp.com>
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/cpu.h | 47 +++++++++++++++++++++++++++++++++++++++++++++++
 kernel/cpu.c        | 21 +++++++++++++++++++--
 2 files changed, 66 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 03e235ad1bba..488d6ebcf6a1 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -122,26 +122,46 @@ enum {
 		{ .notifier_call = fn, .priority = pri };	\
 	register_cpu_notifier(&fn##_nb);			\
 }
+
+#define __cpu_notifier(fn, pri) {				\
+	static struct notifier_block fn##_nb =			\
+		{ .notifier_call = fn, .priority = pri };	\
+	__register_cpu_notifier(&fn##_nb);			\
+}
 #else /* #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */
 #define cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
+#define __cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
 #endif /* #else #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) */
+
 #ifdef CONFIG_HOTPLUG_CPU
 extern int register_cpu_notifier(struct notifier_block *nb);
+extern int __register_cpu_notifier(struct notifier_block *nb);
 extern void unregister_cpu_notifier(struct notifier_block *nb);
+extern void __unregister_cpu_notifier(struct notifier_block *nb);
 #else
 
 #ifndef MODULE
 extern int register_cpu_notifier(struct notifier_block *nb);
+extern int __register_cpu_notifier(struct notifier_block *nb);
 #else
 static inline int register_cpu_notifier(struct notifier_block *nb)
 {
 	return 0;
 }
+
+static inline int __register_cpu_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
 #endif
 
 static inline void unregister_cpu_notifier(struct notifier_block *nb)
 {
 }
+
+static inline void __unregister_cpu_notifier(struct notifier_block *nb)
+{
+}
 #endif
 
 int cpu_up(unsigned int cpu);
@@ -149,19 +169,32 @@ void notify_cpu_starting(unsigned int cpu);
 extern void cpu_maps_update_begin(void);
 extern void cpu_maps_update_done(void);
 
+#define cpu_notifier_register_begin	cpu_maps_update_begin
+#define cpu_notifier_register_done	cpu_maps_update_done
+
 #else	/* CONFIG_SMP */
 
 #define cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
+#define __cpu_notifier(fn, pri)	do { (void)(fn); } while (0)
 
 static inline int register_cpu_notifier(struct notifier_block *nb)
 {
 	return 0;
 }
 
+static inline int __register_cpu_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
 static inline void unregister_cpu_notifier(struct notifier_block *nb)
 {
 }
 
+static inline void __unregister_cpu_notifier(struct notifier_block *nb)
+{
+}
+
 static inline void cpu_maps_update_begin(void)
 {
 }
@@ -170,6 +203,14 @@ static inline void cpu_maps_update_done(void)
 {
 }
 
+static inline void cpu_notifier_register_begin(void)
+{
+}
+
+static inline void cpu_notifier_register_done(void)
+{
+}
+
 #endif /* CONFIG_SMP */
 extern struct bus_type cpu_subsys;
 
@@ -183,8 +224,11 @@ extern void put_online_cpus(void);
 extern void cpu_hotplug_disable(void);
 extern void cpu_hotplug_enable(void);
 #define hotcpu_notifier(fn, pri)	cpu_notifier(fn, pri)
+#define __hotcpu_notifier(fn, pri)	__cpu_notifier(fn, pri)
 #define register_hotcpu_notifier(nb)	register_cpu_notifier(nb)
+#define __register_hotcpu_notifier(nb)	__register_cpu_notifier(nb)
 #define unregister_hotcpu_notifier(nb)	unregister_cpu_notifier(nb)
+#define __unregister_hotcpu_notifier(nb)	__unregister_cpu_notifier(nb)
 void clear_tasks_mm_cpumask(int cpu);
 int cpu_down(unsigned int cpu);
 
@@ -197,9 +241,12 @@ static inline void cpu_hotplug_done(void) {}
 #define cpu_hotplug_disable()	do { } while (0)
 #define cpu_hotplug_enable()	do { } while (0)
 #define hotcpu_notifier(fn, pri)	do { (void)(fn); } while (0)
+#define __hotcpu_notifier(fn, pri)	do { (void)(fn); } while (0)
 /* These aren't inline functions due to a GCC bug. */
 #define register_hotcpu_notifier(nb)	({ (void)(nb); 0; })
+#define __register_hotcpu_notifier(nb)	({ (void)(nb); 0; })
 #define unregister_hotcpu_notifier(nb)	({ (void)(nb); })
+#define __unregister_hotcpu_notifier(nb)	({ (void)(nb); })
 #endif		/* CONFIG_HOTPLUG_CPU */
 
 #ifdef CONFIG_PM_SLEEP_SMP
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 33caf5e97701..a9e710eef0e2 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -28,18 +28,23 @@
 static DEFINE_MUTEX(cpu_add_remove_lock);
 
 /*
- * The following two API's must be used when attempting
- * to serialize the updates to cpu_online_mask, cpu_present_mask.
+ * The following two APIs (cpu_maps_update_begin/done) must be used when
+ * attempting to serialize the updates to cpu_online_mask & cpu_present_mask.
+ * The APIs cpu_notifier_register_begin/done() must be used to protect CPU
+ * hotplug callback (un)registration performed using __register_cpu_notifier()
+ * or __unregister_cpu_notifier().
  */
 void cpu_maps_update_begin(void)
 {
 	mutex_lock(&cpu_add_remove_lock);
 }
+EXPORT_SYMBOL(cpu_notifier_register_begin);
 
 void cpu_maps_update_done(void)
 {
 	mutex_unlock(&cpu_add_remove_lock);
 }
+EXPORT_SYMBOL(cpu_notifier_register_done);
 
 static RAW_NOTIFIER_HEAD(cpu_chain);
 
@@ -183,6 +188,11 @@ int __ref register_cpu_notifier(struct notifier_block *nb)
 	return ret;
 }
 
+int __ref __register_cpu_notifier(struct notifier_block *nb)
+{
+	return raw_notifier_chain_register(&cpu_chain, nb);
+}
+
 static int __cpu_notify(unsigned long val, void *v, int nr_to_call,
 			int *nr_calls)
 {
@@ -206,6 +216,7 @@ static void cpu_notify_nofail(unsigned long val, void *v)
 	BUG_ON(cpu_notify(val, v));
 }
 EXPORT_SYMBOL(register_cpu_notifier);
+EXPORT_SYMBOL(__register_cpu_notifier);
 
 void __ref unregister_cpu_notifier(struct notifier_block *nb)
 {
@@ -215,6 +226,12 @@ void __ref unregister_cpu_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL(unregister_cpu_notifier);
 
+void __ref __unregister_cpu_notifier(struct notifier_block *nb)
+{
+	raw_notifier_chain_unregister(&cpu_chain, nb);
+}
+EXPORT_SYMBOL(__unregister_cpu_notifier);
+
 /**
  * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
  * @cpu: a CPU id
-- 
cgit v1.2.3


From f0bdb5e0c72b7347c867da539367138ad95c6b24 Mon Sep 17 00:00:00 2001
From: "Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com>
Date: Tue, 11 Mar 2014 02:04:39 +0530
Subject: CPU hotplug, perf: Fix CPU hotplug callback registration

Subsystems that want to register CPU hotplug callbacks, as well as perform
initialization for the CPUs that are already online, often do it as shown
below:

	get_online_cpus();

	for_each_online_cpu(cpu)
		init_cpu(cpu);

	register_cpu_notifier(&foobar_cpu_notifier);

	put_online_cpus();

This is wrong, since it is prone to ABBA deadlocks involving the
cpu_add_remove_lock and the cpu_hotplug.lock (when running concurrently
with CPU hotplug operations).

Instead, the correct and race-free way of performing the callback
registration is:

	cpu_notifier_register_begin();

	for_each_online_cpu(cpu)
		init_cpu(cpu);

	/* Note the use of the double underscored version of the API */
	__register_cpu_notifier(&foobar_cpu_notifier);

	cpu_notifier_register_done();

Fix the perf subsystem's hotplug notifier by using this latter form of
callback registration.

Also provide a bare-bones version of perf_cpu_notifier() that doesn't
invoke the notifiers for the already online CPUs. This would be useful
for subsystems that need to perform a different set of initialization
for the already online CPUs, or don't need the initialization altogether.

Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/perf_event.h | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e56b07f5c9b6..3356abcfff18 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -835,6 +835,8 @@ do {									\
 		{ .notifier_call = fn, .priority = CPU_PRI_PERF };	\
 	unsigned long cpu = smp_processor_id();				\
 	unsigned long flags;						\
+									\
+	cpu_notifier_register_begin();					\
 	fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE,			\
 		(void *)(unsigned long)cpu);				\
 	local_irq_save(flags);						\
@@ -843,9 +845,21 @@ do {									\
 	local_irq_restore(flags);					\
 	fn(&fn##_nb, (unsigned long)CPU_ONLINE,				\
 		(void *)(unsigned long)cpu);				\
-	register_cpu_notifier(&fn##_nb);				\
+	__register_cpu_notifier(&fn##_nb);				\
+	cpu_notifier_register_done();					\
 } while (0)
 
+/*
+ * Bare-bones version of perf_cpu_notifier(), which doesn't invoke the
+ * callback for already online CPUs.
+ */
+#define __perf_cpu_notifier(fn)						\
+do {									\
+	static struct notifier_block fn##_nb =				\
+		{ .notifier_call = fn, .priority = CPU_PRI_PERF };	\
+									\
+	__register_cpu_notifier(&fn##_nb);				\
+} while (0)
 
 struct perf_pmu_events_attr {
 	struct device_attribute attr;
-- 
cgit v1.2.3


From 099dd235113700bbb476e572cd191ddb77b9af46 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 28 Feb 2014 20:36:55 -0800
Subject: audit: Send replies in the proper network namespace.

In perverse cases of file descriptor passing the current network
namespace of a process and the network namespace of a socket used by
that socket may differ.  Therefore use the network namespace of the
appropiate socket to ensure replies always go to the appropiate
socket.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 include/linux/audit.h |  3 ++-
 kernel/audit.c        | 21 ++++++++++-----------
 kernel/auditfilter.c  |  7 +++++--
 3 files changed, 17 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index aa865a9a4c4f..ec1464df4c60 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -43,6 +43,7 @@ struct mq_attr;
 struct mqstat;
 struct audit_watch;
 struct audit_tree;
+struct sk_buff;
 
 struct audit_krule {
 	int			vers_ops;
@@ -463,7 +464,7 @@ extern int audit_filter_user(int type);
 extern int audit_filter_type(int type);
 extern int audit_rule_change(int type, __u32 portid, int seq,
 				void *data, size_t datasz);
-extern int audit_list_rules_send(__u32 portid, int seq);
+extern int audit_list_rules_send(struct sk_buff *request_skb, int seq);
 
 extern u32 audit_enabled;
 #else /* CONFIG_AUDIT */
diff --git a/kernel/audit.c b/kernel/audit.c
index 71fb41f393d7..7b44bd47759c 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -570,9 +570,11 @@ static int audit_send_reply_thread(void *arg)
  * Allocates an skb, builds the netlink message, and sends it to the port id.
  * No failure notifications.
  */
-static void audit_send_reply(__u32 portid, int seq, int type, int done,
+static void audit_send_reply(struct sk_buff *request_skb, int seq, int type, int done,
 			     int multi, const void *payload, int size)
 {
+	u32 portid = NETLINK_CB(request_skb).portid;
+	struct net *net = sock_net(NETLINK_CB(request_skb).sk);
 	struct sk_buff *skb;
 	struct task_struct *tsk;
 	struct audit_reply *reply = kmalloc(sizeof(struct audit_reply),
@@ -585,7 +587,7 @@ static void audit_send_reply(__u32 portid, int seq, int type, int done,
 	if (!skb)
 		goto out;
 
-	reply->net = get_net(current->nsproxy->net_ns);
+	reply->net = get_net(net);
 	reply->portid = portid;
 	reply->skb = skb;
 
@@ -675,8 +677,7 @@ static int audit_get_feature(struct sk_buff *skb)
 
 	seq = nlmsg_hdr(skb)->nlmsg_seq;
 
-	audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0,
-			 &af, sizeof(af));
+	audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &af, sizeof(af));
 
 	return 0;
 }
@@ -796,8 +797,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		s.backlog		= skb_queue_len(&audit_skb_queue);
 		s.version		= AUDIT_VERSION_LATEST;
 		s.backlog_wait_time	= audit_backlog_wait_time;
-		audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0,
-				 &s, sizeof(s));
+		audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &s, sizeof(s));
 		break;
 	}
 	case AUDIT_SET: {
@@ -907,7 +907,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 					   seq, data, nlmsg_len(nlh));
 		break;
 	case AUDIT_LIST_RULES:
-		err = audit_list_rules_send(NETLINK_CB(skb).portid, seq);
+		err = audit_list_rules_send(skb, seq);
 		break;
 	case AUDIT_TRIM:
 		audit_trim_trees();
@@ -972,8 +972,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 			memcpy(sig_data->ctx, ctx, len);
 			security_release_secctx(ctx, len);
 		}
-		audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_SIGNAL_INFO,
-				0, 0, sig_data, sizeof(*sig_data) + len);
+		audit_send_reply(skb, seq, AUDIT_SIGNAL_INFO, 0, 0,
+				 sig_data, sizeof(*sig_data) + len);
 		kfree(sig_data);
 		break;
 	case AUDIT_TTY_GET: {
@@ -985,8 +985,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		s.log_passwd = tsk->signal->audit_tty_log_passwd;
 		spin_unlock(&tsk->sighand->siglock);
 
-		audit_send_reply(NETLINK_CB(skb).portid, seq,
-				 AUDIT_TTY_GET, 0, 0, &s, sizeof(s));
+		audit_send_reply(skb, seq, AUDIT_TTY_GET, 0, 0, &s, sizeof(s));
 		break;
 	}
 	case AUDIT_TTY_SET: {
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index a0d470131fd0..549bbb6e6597 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -32,6 +32,7 @@
 #include <linux/slab.h>
 #include <linux/security.h>
 #include <net/net_namespace.h>
+#include <net/sock.h>
 #include "audit.h"
 
 /*
@@ -1071,8 +1072,10 @@ int audit_rule_change(int type, __u32 portid, int seq, void *data,
  * @portid: target portid for netlink audit messages
  * @seq: netlink audit message sequence (serial) number
  */
-int audit_list_rules_send(__u32 portid, int seq)
+int audit_list_rules_send(struct sk_buff *request_skb, int seq)
 {
+	u32 portid = NETLINK_CB(request_skb).portid;
+	struct net *net = sock_net(NETLINK_CB(request_skb).sk);
 	struct task_struct *tsk;
 	struct audit_netlink_list *dest;
 	int err = 0;
@@ -1086,7 +1089,7 @@ int audit_list_rules_send(__u32 portid, int seq)
 	dest = kmalloc(sizeof(struct audit_netlink_list), GFP_KERNEL);
 	if (!dest)
 		return -ENOMEM;
-	dest->net = get_net(current->nsproxy->net_ns);
+	dest->net = get_net(net);
 	dest->portid = portid;
 	skb_queue_head_init(&dest->q);
 
-- 
cgit v1.2.3


From 4b58841149dcaa500ceba1d5378ae70622fe4899 Mon Sep 17 00:00:00 2001
From: AKASHI Takahiro <takahiro.akashi@linaro.org>
Date: Sat, 15 Mar 2014 14:48:00 +0900
Subject: audit: Add generic compat syscall support

lib/audit.c provides a generic function for auditing system calls.
This patch extends it for compat syscall support on bi-architectures
(32/64-bit) by adding lib/compat_audit.c.
What is required to support this feature are:
 * add asm/unistd32.h for compat system call names
 * select CONFIG_AUDIT_ARCH_COMPAT_GENERIC

Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Acked-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 include/linux/audit.h      |  8 ++++++++
 include/uapi/linux/audit.h |  6 ++++++
 lib/Kconfig                |  9 +++++++++
 lib/Makefile               |  1 +
 lib/audit.c                | 15 +++++++++++++-
 lib/compat_audit.c         | 50 ++++++++++++++++++++++++++++++++++++++++++++++
 6 files changed, 88 insertions(+), 1 deletion(-)
 create mode 100644 lib/compat_audit.c

(limited to 'include/linux')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index ec1464df4c60..4b2983e25ce0 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -79,6 +79,14 @@ extern int is_audit_feature_set(int which);
 extern int __init audit_register_class(int class, unsigned *list);
 extern int audit_classify_syscall(int abi, unsigned syscall);
 extern int audit_classify_arch(int arch);
+/* only for compat system calls */
+extern unsigned compat_write_class[];
+extern unsigned compat_read_class[];
+extern unsigned compat_dir_class[];
+extern unsigned compat_chattr_class[];
+extern unsigned compat_signal_class[];
+
+extern int __weak audit_classify_compat_syscall(int abi, unsigned syscall);
 
 /* audit_names->type values */
 #define	AUDIT_TYPE_UNKNOWN	0	/* we don't know yet */
diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index 4315ee99b967..9af01d77dc44 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -362,6 +362,12 @@ enum {
 #define AUDIT_ARCH_SPARC64	(EM_SPARCV9|__AUDIT_ARCH_64BIT)
 #define AUDIT_ARCH_X86_64	(EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
 
+#ifdef CONFIG_COMPAT
+#define audit_is_compat(arch)	(!((arch) & __AUDIT_ARCH_64BIT))
+#else
+#define audit_is_compat(arch)	false
+#endif
+
 #define AUDIT_PERM_EXEC		1
 #define AUDIT_PERM_WRITE	2
 #define AUDIT_PERM_READ		4
diff --git a/lib/Kconfig b/lib/Kconfig
index 991c98bc4a3f..1e80cb3c77a9 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -182,6 +182,15 @@ config AUDIT_GENERIC
 	depends on AUDIT && !AUDIT_ARCH
 	default y
 
+config AUDIT_ARCH_COMPAT_GENERIC
+	bool
+	default n
+
+config AUDIT_COMPAT_GENERIC
+	bool
+	depends on AUDIT_GENERIC && AUDIT_ARCH_COMPAT_GENERIC && COMPAT
+	default y
+
 config RANDOM32_SELFTEST
 	bool "PRNG perform self test on init"
 	default n
diff --git a/lib/Makefile b/lib/Makefile
index a459c31e8c6b..972552b39cf5 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -93,6 +93,7 @@ obj-$(CONFIG_TEXTSEARCH_BM) += ts_bm.o
 obj-$(CONFIG_TEXTSEARCH_FSM) += ts_fsm.o
 obj-$(CONFIG_SMP) += percpu_counter.o
 obj-$(CONFIG_AUDIT_GENERIC) += audit.o
+obj-$(CONFIG_AUDIT_COMPAT_GENERIC) += compat_audit.o
 
 obj-$(CONFIG_SWIOTLB) += swiotlb.o
 obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o
diff --git a/lib/audit.c b/lib/audit.c
index 76bbed4a20e5..1d726a22565b 100644
--- a/lib/audit.c
+++ b/lib/audit.c
@@ -30,11 +30,17 @@ static unsigned signal_class[] = {
 
 int audit_classify_arch(int arch)
 {
-	return 0;
+	if (audit_is_compat(arch))
+		return 1;
+	else
+		return 0;
 }
 
 int audit_classify_syscall(int abi, unsigned syscall)
 {
+	if (audit_is_compat(abi))
+		return audit_classify_compat_syscall(abi, syscall);
+
 	switch(syscall) {
 #ifdef __NR_open
 	case __NR_open:
@@ -57,6 +63,13 @@ int audit_classify_syscall(int abi, unsigned syscall)
 
 static int __init audit_classes_init(void)
 {
+#ifdef CONFIG_AUDIT_COMPAT_GENERIC
+	audit_register_class(AUDIT_CLASS_WRITE_32, compat_write_class);
+	audit_register_class(AUDIT_CLASS_READ_32, compat_read_class);
+	audit_register_class(AUDIT_CLASS_DIR_WRITE_32, compat_dir_class);
+	audit_register_class(AUDIT_CLASS_CHATTR_32, compat_chattr_class);
+	audit_register_class(AUDIT_CLASS_SIGNAL_32, compat_signal_class);
+#endif
 	audit_register_class(AUDIT_CLASS_WRITE, write_class);
 	audit_register_class(AUDIT_CLASS_READ, read_class);
 	audit_register_class(AUDIT_CLASS_DIR_WRITE, dir_class);
diff --git a/lib/compat_audit.c b/lib/compat_audit.c
new file mode 100644
index 000000000000..873f75b640ab
--- /dev/null
+++ b/lib/compat_audit.c
@@ -0,0 +1,50 @@
+#include <linux/init.h>
+#include <linux/types.h>
+#include <asm/unistd32.h>
+
+unsigned compat_dir_class[] = {
+#include <asm-generic/audit_dir_write.h>
+~0U
+};
+
+unsigned compat_read_class[] = {
+#include <asm-generic/audit_read.h>
+~0U
+};
+
+unsigned compat_write_class[] = {
+#include <asm-generic/audit_write.h>
+~0U
+};
+
+unsigned compat_chattr_class[] = {
+#include <asm-generic/audit_change_attr.h>
+~0U
+};
+
+unsigned compat_signal_class[] = {
+#include <asm-generic/audit_signal.h>
+~0U
+};
+
+int audit_classify_compat_syscall(int abi, unsigned syscall)
+{
+	switch (syscall) {
+#ifdef __NR_open
+	case __NR_open:
+		return 2;
+#endif
+#ifdef __NR_openat
+	case __NR_openat:
+		return 3;
+#endif
+#ifdef __NR_socketcall
+	case __NR_socketcall:
+		return 4;
+#endif
+	case __NR_execve:
+		return 5;
+	default:
+		return 1;
+	}
+}
-- 
cgit v1.2.3


From ad36d28293936b03d6b7996e9d6aadfd73c0eb08 Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Thu, 15 Aug 2013 18:05:12 -0400
Subject: pid: get pid_t ppid of task in init_pid_ns

Added the functions task_ppid_nr_ns() and task_ppid_nr() to abstract the lookup
of the PPID (real_parent's pid_t) of a process, including rcu locking, in the
arbitrary and init_pid_ns.
This provides an alternative to sys_getppid(), which is relative to the child
process' pid namespace.

(informed by ebiederman's 6c621b7e)
Cc: stable@vger.kernel.org
Cc: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
---
 include/linux/sched.h | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 53f97eb8dbc7..116e301fb13f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1561,6 +1561,24 @@ static inline pid_t task_tgid_vnr(struct task_struct *tsk)
 }
 
 
+static int pid_alive(const struct task_struct *p);
+static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
+{
+	pid_t pid = 0;
+
+	rcu_read_lock();
+	if (pid_alive(tsk))
+		pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns);
+	rcu_read_unlock();
+
+	return pid;
+}
+
+static inline pid_t task_ppid_nr(const struct task_struct *tsk)
+{
+	return task_ppid_nr_ns(tsk, &init_pid_ns);
+}
+
 static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk,
 					struct pid_namespace *ns)
 {
@@ -1600,7 +1618,7 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk)
  *
  * Return: 1 if the process is alive. 0 otherwise.
  */
-static inline int pid_alive(struct task_struct *p)
+static inline int pid_alive(const struct task_struct *p)
 {
 	return p->pids[PIDTYPE_PID].pid != NULL;
 }
-- 
cgit v1.2.3


From 80e0b6e8a001361316a2d62b748fe677ec46b860 Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Sun, 16 Mar 2014 14:00:19 -0400
Subject: sched: declare pid_alive as inline

We accidentally declared pid_alive without any extern/inline connotation.
Some platforms were fine with this, some like ia64 and mips were very angry.
If the function is inline, the prototype should be inline!

on ia64:
include/linux/sched.h:1718: warning: 'pid_alive' declared inline after
being called

Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 include/linux/sched.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 116e301fb13f..0f72548732f1 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1561,7 +1561,7 @@ static inline pid_t task_tgid_vnr(struct task_struct *tsk)
 }
 
 
-static int pid_alive(const struct task_struct *p);
+static inline int pid_alive(const struct task_struct *p);
 static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
 {
 	pid_t pid = 0;
-- 
cgit v1.2.3


From cf559ab94e058df65c841b4afc8d5346fdda19b3 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@linaro.org>
Date: Fri, 21 Mar 2014 02:55:11 +0900
Subject: serial: s3c: Fix build of header without serial_core.h preinclusion

serial_s3c.h uses upf_t which is defined in serial_core.h but does not
include that itself meaning that users which include serial_s3c.h by
itself don't build.

Signed-off-by: Mark Brown <broonie@linaro.org>
[t.figa: Moved inclusion under #ifndef __ASSEMBLY__ to fix mach-exynos]
Signed-off-by: Tomasz Figa <t.figa@samsung.com>
Signed-off-by: Kukjin Kim <kgene.kim@samsung.com>
---
 include/linux/serial_s3c.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/serial_s3c.h b/include/linux/serial_s3c.h
index 907d9d1d56cf..e6fc9567690b 100644
--- a/include/linux/serial_s3c.h
+++ b/include/linux/serial_s3c.h
@@ -233,6 +233,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/serial_core.h>
+
 /* configuration structure for per-machine configurations for the
  * serial port
  *
-- 
cgit v1.2.3


From 1ab95d37bcc3ff2d69e3871e4f056bab7aed0b85 Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Wed, 19 Mar 2014 18:11:50 +0200
Subject: net/mlx4: Add data structures to support N-Ports per VF

Adds the required data structures to support VFs with N (1 or 2)
ports instead of always using the number of physical ports.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/main.c | 109 +++++++++++++++++++++++-------
 include/linux/mlx4/device.h               |   7 ++
 2 files changed, 92 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index abd0b1d277aa..e1a55857af71 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2193,6 +2193,10 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 	struct mlx4_dev *dev;
 	int err;
 	int port;
+	int nvfs[MLX4_MAX_PORTS + 1], prb_vf[MLX4_MAX_PORTS + 1];
+	unsigned total_vfs = 0;
+	int sriov_initialized = 0;
+	unsigned int i;
 
 	pr_info(DRV_NAME ": Initializing %s\n", pci_name(pdev));
 
@@ -2207,17 +2211,39 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 	 * per port, we must limit the number of VFs to 63 (since their are
 	 * 128 MACs)
 	 */
-	if (num_vfs >= MLX4_MAX_NUM_VF) {
+	for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]);
+	     total_vfs += nvfs[i], i++) {
+		nvfs[i] = i == MLX4_MAX_PORTS ? num_vfs : 0;
+		if (nvfs[i] < 0) {
+			dev_err(&pdev->dev, "num_vfs module parameter cannot be negative\n");
+			return -EINVAL;
+		}
+	}
+	for (i = 0; i < sizeof(prb_vf)/sizeof(prb_vf[0]); i++) {
+		prb_vf[i] = i == MLX4_MAX_PORTS ? probe_vf : 0;
+		if (prb_vf[i] < 0 || prb_vf[i] > nvfs[i]) {
+			dev_err(&pdev->dev, "probe_vf module parameter cannot be negative or greater than num_vfs\n");
+			return -EINVAL;
+		}
+	}
+	if (total_vfs >= MLX4_MAX_NUM_VF) {
 		dev_err(&pdev->dev,
 			"Requested more VF's (%d) than allowed (%d)\n",
-			num_vfs, MLX4_MAX_NUM_VF - 1);
+			total_vfs, MLX4_MAX_NUM_VF - 1);
 		return -EINVAL;
 	}
 
-	if (num_vfs < 0) {
-		pr_err("num_vfs module parameter cannot be negative\n");
-		return -EINVAL;
+	for (i = 0; i < MLX4_MAX_PORTS; i++) {
+		if (nvfs[i] + nvfs[2] >= MLX4_MAX_NUM_VF_P_PORT) {
+			dev_err(&pdev->dev,
+				"Requested more VF's (%d) for port (%d) than allowed (%d)\n",
+				nvfs[i] + nvfs[2], i + 1,
+				MLX4_MAX_NUM_VF_P_PORT - 1);
+			return -EINVAL;
+		}
 	}
+
+
 	/*
 	 * Check for BARs.
 	 */
@@ -2292,11 +2318,23 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 	if (pci_dev_data & MLX4_PCI_DEV_IS_VF) {
 		/* When acting as pf, we normally skip vfs unless explicitly
 		 * requested to probe them. */
-		if (num_vfs && extended_func_num(pdev) > probe_vf) {
-			mlx4_warn(dev, "Skipping virtual function:%d\n",
-						extended_func_num(pdev));
-			err = -ENODEV;
-			goto err_free_dev;
+		if (total_vfs) {
+			unsigned vfs_offset = 0;
+			for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]) &&
+			     vfs_offset + nvfs[i] < extended_func_num(pdev);
+			     vfs_offset += nvfs[i], i++)
+				;
+			if (i == sizeof(nvfs)/sizeof(nvfs[0])) {
+				err = -ENODEV;
+				goto err_free_dev;
+			}
+			if ((extended_func_num(pdev) - vfs_offset)
+			    > prb_vf[i]) {
+				mlx4_warn(dev, "Skipping virtual function:%d\n",
+					  extended_func_num(pdev));
+				err = -ENODEV;
+				goto err_free_dev;
+			}
 		}
 		mlx4_warn(dev, "Detected virtual function - running in slave mode\n");
 		dev->flags |= MLX4_FLAG_SLAVE;
@@ -2316,22 +2354,30 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 			}
 		}
 
-		if (num_vfs) {
-			mlx4_warn(dev, "Enabling SR-IOV with %d VFs\n", num_vfs);
-
-			atomic_inc(&pf_loading);
-			err = pci_enable_sriov(pdev, num_vfs);
-			atomic_dec(&pf_loading);
-
-			if (err) {
-				mlx4_err(dev, "Failed to enable SR-IOV, continuing without SR-IOV (err = %d).\n",
-					 err);
+		if (total_vfs) {
+			mlx4_warn(dev, "Enabling SR-IOV with %d VFs\n",
+				  total_vfs);
+			dev->dev_vfs = kzalloc(
+					total_vfs * sizeof(*dev->dev_vfs),
+					GFP_KERNEL);
+			if (NULL == dev->dev_vfs) {
+				mlx4_err(dev, "Failed to allocate memory for VFs\n");
 				err = 0;
 			} else {
-				mlx4_warn(dev, "Running in master mode\n");
-				dev->flags |= MLX4_FLAG_SRIOV |
-					      MLX4_FLAG_MASTER;
-				dev->num_vfs = num_vfs;
+				atomic_inc(&pf_loading);
+				err = pci_enable_sriov(pdev, total_vfs);
+				atomic_dec(&pf_loading);
+				if (err) {
+					mlx4_err(dev, "Failed to enable SR-IOV, continuing without SR-IOV (err = %d).\n",
+						 err);
+					err = 0;
+				} else {
+					mlx4_warn(dev, "Running in master mode\n");
+					dev->flags |= MLX4_FLAG_SRIOV |
+						      MLX4_FLAG_MASTER;
+					dev->num_vfs = total_vfs;
+					sriov_initialized = 1;
+				}
 			}
 		}
 
@@ -2396,12 +2442,24 @@ slave_start:
 	/* In master functions, the communication channel must be initialized
 	 * after obtaining its address from fw */
 	if (mlx4_is_master(dev)) {
+		unsigned sum = 0;
 		err = mlx4_multi_func_init(dev);
 		if (err) {
 			mlx4_err(dev, "Failed to init master mfunc"
 				 "interface, aborting.\n");
 			goto err_close;
 		}
+		if (sriov_initialized) {
+			for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]); i++) {
+				unsigned j;
+				for (j = 0; j < nvfs[i]; ++sum, ++j) {
+					dev->dev_vfs[sum].min_port =
+						i < 2 ? i + 1 : 1;
+					dev->dev_vfs[sum].n_ports = i < 2 ? 1 :
+						dev->caps.num_ports;
+				}
+			}
+		}
 	}
 
 	err = mlx4_alloc_eq_table(dev);
@@ -2509,6 +2567,8 @@ err_rel_own:
 	if (!mlx4_is_slave(dev))
 		mlx4_free_ownership(dev);
 
+	kfree(priv->dev.dev_vfs);
+
 err_free_dev:
 	kfree(priv);
 
@@ -2595,6 +2655,7 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 		kfree(dev->caps.qp0_proxy);
 		kfree(dev->caps.qp1_tunnel);
 		kfree(dev->caps.qp1_proxy);
+		kfree(dev->dev_vfs);
 
 		kfree(priv);
 		pci_release_regions(pdev);
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index f211b51dc726..b3044f32aef1 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -84,6 +84,7 @@ enum {
 enum {
 	MLX4_MAX_NUM_PF		= 16,
 	MLX4_MAX_NUM_VF		= 64,
+	MLX4_MAX_NUM_VF_P_PORT  = 64,
 	MLX4_MFUNC_MAX		= 80,
 	MLX4_MAX_EQ_NUM		= 1024,
 	MLX4_MFUNC_EQ_NUM	= 4,
@@ -664,6 +665,11 @@ struct mlx4_quotas {
 	int xrcd;
 };
 
+struct mlx4_vf_dev {
+	u8			min_port;
+	u8			n_ports;
+};
+
 struct mlx4_dev {
 	struct pci_dev	       *pdev;
 	unsigned long		flags;
@@ -679,6 +685,7 @@ struct mlx4_dev {
 	int			oper_log_mgm_entry_size;
 	u64			regid_promisc_array[MLX4_MAX_PORTS + 1];
 	u64			regid_allmulti_array[MLX4_MAX_PORTS + 1];
+	struct mlx4_vf_dev     *dev_vfs;
 };
 
 struct mlx4_eqe {
-- 
cgit v1.2.3


From f74462acf8f390528c8b7937f227c6c90d017f3b Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Wed, 19 Mar 2014 18:11:51 +0200
Subject: net/mlx4: Add utils for N-Port VFs

This patch adds the following utils:
1. Convert slave_id -> VF
2. Get the active ports by slave_id
3. Convert slave's port to real port
4. Get the slave's port from real port
5. Get all slaves that uses the i'th real port
6. Get all slaves that uses the i'th real port exclusively

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/cmd.c  | 106 ++++++++++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx4/mlx4.h |   2 +
 include/linux/mlx4/device.h               |  27 ++++++++
 3 files changed, 135 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 2b0b45ece14b..59a1b2703281 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2234,6 +2234,112 @@ static int mlx4_get_slave_indx(struct mlx4_dev *dev, int vf)
 	return vf+1;
 }
 
+int mlx4_get_vf_indx(struct mlx4_dev *dev, int slave)
+{
+	if (slave < 1 || slave > dev->num_vfs) {
+		mlx4_err(dev,
+			 "Bad slave number:%d (number of activated slaves: %lu)\n",
+			 slave, dev->num_slaves);
+		return -EINVAL;
+	}
+	return slave - 1;
+}
+
+struct mlx4_active_ports mlx4_get_active_ports(struct mlx4_dev *dev, int slave)
+{
+	struct mlx4_active_ports actv_ports;
+	int vf;
+
+	bitmap_zero(actv_ports.ports, MLX4_MAX_PORTS);
+
+	if (slave == 0) {
+		bitmap_fill(actv_ports.ports, dev->caps.num_ports);
+		return actv_ports;
+	}
+
+	vf = mlx4_get_vf_indx(dev, slave);
+	if (vf < 0)
+		return actv_ports;
+
+	bitmap_set(actv_ports.ports, dev->dev_vfs[vf].min_port - 1,
+		   min((int)dev->dev_vfs[mlx4_get_vf_indx(dev, slave)].n_ports,
+		   dev->caps.num_ports));
+
+	return actv_ports;
+}
+EXPORT_SYMBOL_GPL(mlx4_get_active_ports);
+
+int mlx4_slave_convert_port(struct mlx4_dev *dev, int slave, int port)
+{
+	unsigned n;
+	struct mlx4_active_ports actv_ports = mlx4_get_active_ports(dev, slave);
+	unsigned m = bitmap_weight(actv_ports.ports, dev->caps.num_ports);
+
+	if (port <= 0 || port > m)
+		return -EINVAL;
+
+	n = find_first_bit(actv_ports.ports, dev->caps.num_ports);
+	if (port <= n)
+		port = n + 1;
+
+	return port;
+}
+EXPORT_SYMBOL_GPL(mlx4_slave_convert_port);
+
+int mlx4_phys_to_slave_port(struct mlx4_dev *dev, int slave, int port)
+{
+	struct mlx4_active_ports actv_ports = mlx4_get_active_ports(dev, slave);
+	if (test_bit(port - 1, actv_ports.ports))
+		return port -
+			find_first_bit(actv_ports.ports, dev->caps.num_ports);
+
+	return -1;
+}
+EXPORT_SYMBOL_GPL(mlx4_phys_to_slave_port);
+
+struct mlx4_slaves_pport mlx4_phys_to_slaves_pport(struct mlx4_dev *dev,
+						   int port)
+{
+	unsigned i;
+	struct mlx4_slaves_pport slaves_pport;
+
+	bitmap_zero(slaves_pport.slaves, MLX4_MFUNC_MAX);
+
+	if (port <= 0 || port > dev->caps.num_ports)
+		return slaves_pport;
+
+	for (i = 0; i < dev->num_vfs + 1; i++) {
+		struct mlx4_active_ports actv_ports =
+			mlx4_get_active_ports(dev, i);
+		if (test_bit(port - 1, actv_ports.ports))
+			set_bit(i, slaves_pport.slaves);
+	}
+
+	return slaves_pport;
+}
+EXPORT_SYMBOL_GPL(mlx4_phys_to_slaves_pport);
+
+struct mlx4_slaves_pport mlx4_phys_to_slaves_pport_actv(
+		struct mlx4_dev *dev,
+		const struct mlx4_active_ports *crit_ports)
+{
+	unsigned i;
+	struct mlx4_slaves_pport slaves_pport;
+
+	bitmap_zero(slaves_pport.slaves, MLX4_MFUNC_MAX);
+
+	for (i = 0; i < dev->num_vfs + 1; i++) {
+		struct mlx4_active_ports actv_ports =
+			mlx4_get_active_ports(dev, i);
+		if (bitmap_equal(crit_ports->ports, actv_ports.ports,
+				 dev->caps.num_ports))
+			set_bit(i, slaves_pport.slaves);
+	}
+
+	return slaves_pport;
+}
+EXPORT_SYMBOL_GPL(mlx4_phys_to_slaves_pport_actv);
+
 int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 6ba38c98c492..fe8715e35afa 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -1289,5 +1289,7 @@ void mlx4_init_quotas(struct mlx4_dev *dev);
 
 int mlx4_get_slave_num_gids(struct mlx4_dev *dev, int slave);
 int mlx4_get_base_gid_ix(struct mlx4_dev *dev, int slave);
+/* Returns the VF index of slave */
+int mlx4_get_vf_indx(struct mlx4_dev *dev, int slave);
 
 #endif /* MLX4_H */
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index b3044f32aef1..122c7cabaee7 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1204,4 +1204,31 @@ int mlx4_FLOW_STEERING_IB_UC_QP_RANGE(struct mlx4_dev *dev, u32 min_range_qpn,
 
 cycle_t mlx4_read_clock(struct mlx4_dev *dev);
 
+struct mlx4_active_ports {
+	DECLARE_BITMAP(ports, MLX4_MAX_PORTS);
+};
+/* Returns a bitmap of the physical ports which are assigned to slave */
+struct mlx4_active_ports mlx4_get_active_ports(struct mlx4_dev *dev, int slave);
+
+/* Returns the physical port that represents the virtual port of the slave, */
+/* or a value < 0 in case of an error. If a slave has 2 ports, the identity */
+/* mapping is returned.							    */
+int mlx4_slave_convert_port(struct mlx4_dev *dev, int slave, int port);
+
+struct mlx4_slaves_pport {
+	DECLARE_BITMAP(slaves, MLX4_MFUNC_MAX);
+};
+/* Returns a bitmap of all slaves that are assigned to port. */
+struct mlx4_slaves_pport mlx4_phys_to_slaves_pport(struct mlx4_dev *dev,
+						   int port);
+
+/* Returns a bitmap of all slaves that are assigned exactly to all the */
+/* the ports that are set in crit_ports.			       */
+struct mlx4_slaves_pport mlx4_phys_to_slaves_pport_actv(
+		struct mlx4_dev *dev,
+		const struct mlx4_active_ports *crit_ports);
+
+/* Returns the slave's virtual port that represents the physical port. */
+int mlx4_phys_to_slave_port(struct mlx4_dev *dev, int slave, int port);
+
 #endif /* MLX4_DEVICE_H */
-- 
cgit v1.2.3


From 449fc48866f7d84b0d9a19201de18a4dd4d3488c Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Wed, 19 Mar 2014 18:11:52 +0200
Subject: net/mlx4: Adapt code for N-Port VF

Adds support for N-Port VFs, this includes:
1. Adding support in the wrapped FW command
	In wrapped commands, we need to verify and convert
	the slave's port into the real physical port.
	Furthermore, when sending the response back to the slave,
	a reverse conversion should be made.
2. Adjusting sqpn for QP1 para-virtualization
	The slave assumes that sqpn is used for QP1 communication.
	If the slave is assigned to a port != (first port), we need
	to adjust the sqpn that will direct its QP1 packets into the
	correct endpoint.
3. Adjusting gid[5] to modify the port for raw ethernet
	In B0 steering, gid[5] contains the port. It needs
	to be adjusted into the physical port.
4. Adjusting number of ports in the query / ports caps in the FW commands
	When a slave queries the hardware, it needs to view only
	the physical ports it's assigned to.
5. Adjusting the sched_qp according to the port number
	The QP port is encoded in the sched_qp, thus in modify_qp we need
	to encode the correct port in sched_qp.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/mad.c                   |  29 ++--
 drivers/infiniband/hw/mlx4/main.c                  |  15 +-
 drivers/infiniband/hw/mlx4/sysfs.c                 |   5 +
 drivers/net/ethernet/mellanox/mlx4/cmd.c           |  23 ++-
 drivers/net/ethernet/mellanox/mlx4/eq.c            |  48 +++++--
 drivers/net/ethernet/mellanox/mlx4/fw.c            |  62 +++++++-
 drivers/net/ethernet/mellanox/mlx4/main.c          |   4 +-
 drivers/net/ethernet/mellanox/mlx4/mcg.c           |   5 +-
 drivers/net/ethernet/mellanox/mlx4/mlx4.h          |   3 +-
 drivers/net/ethernet/mellanox/mlx4/port.c          | 158 ++++++++++++++++++---
 .../net/ethernet/mellanox/mlx4/resource_tracker.c  | 143 ++++++++++++++++---
 include/linux/mlx4/device.h                        |   1 +
 12 files changed, 417 insertions(+), 79 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 2c572aed3f6f..fd36ec672632 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -1245,21 +1245,9 @@ out:
 
 static int get_slave_base_gid_ix(struct mlx4_ib_dev *dev, int slave, int port)
 {
-	int gids;
-	int vfs;
-
 	if (rdma_port_get_link_layer(&dev->ib_dev, port) == IB_LINK_LAYER_INFINIBAND)
 		return slave;
-
-	gids = MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS;
-	vfs = dev->dev->num_vfs;
-
-	if (slave == 0)
-		return 0;
-	if (slave <= gids % vfs)
-		return MLX4_ROCE_PF_GIDS + ((gids / vfs) + 1) * (slave - 1);
-
-	return MLX4_ROCE_PF_GIDS + (gids % vfs) + ((gids / vfs) * (slave - 1));
+	return mlx4_get_base_gid_ix(dev->dev, slave, port);
 }
 
 static void fill_in_real_sgid_index(struct mlx4_ib_dev *dev, int slave, int port,
@@ -1281,6 +1269,7 @@ static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc
 	struct ib_ah_attr ah_attr;
 	u8 *slave_id;
 	int slave;
+	int port;
 
 	/* Get slave that sent this packet */
 	if (wc->src_qp < dev->dev->phys_caps.base_proxy_sqpn ||
@@ -1360,6 +1349,10 @@ static void mlx4_ib_multiplex_mad(struct mlx4_ib_demux_pv_ctx *ctx, struct ib_wc
 	if (ah_attr.ah_flags & IB_AH_GRH)
 		fill_in_real_sgid_index(dev, slave, ctx->port, &ah_attr);
 
+	port = mlx4_slave_convert_port(dev->dev, slave, ah_attr.port_num);
+	if (port < 0)
+		return;
+	ah_attr.port_num = port;
 	memcpy(ah_attr.dmac, tunnel->hdr.mac, 6);
 	ah_attr.vlan_id = be16_to_cpu(tunnel->hdr.vlan);
 	/* if slave have default vlan use it */
@@ -1949,7 +1942,15 @@ static int mlx4_ib_alloc_demux_ctx(struct mlx4_ib_dev *dev,
 	ctx->port = port;
 	ctx->ib_dev = &dev->ib_dev;
 
-	for (i = 0; i < dev->dev->caps.sqp_demux; i++) {
+	for (i = 0;
+	     i < min(dev->dev->caps.sqp_demux, (u16)(dev->dev->num_vfs + 1));
+	     i++) {
+		struct mlx4_active_ports actv_ports =
+			mlx4_get_active_ports(dev->dev, i);
+
+		if (!test_bit(port - 1, actv_ports.ports))
+			continue;
+
 		ret = alloc_pv_object(dev, i, port, &ctx->tun[i]);
 		if (ret) {
 			ret = -ENOMEM;
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 2ff428b17088..6cb85467dde7 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -2323,17 +2323,24 @@ static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init)
 	struct mlx4_dev *dev = ibdev->dev;
 	int i;
 	unsigned long flags;
+	struct mlx4_active_ports actv_ports;
+	unsigned int ports;
+	unsigned int first_port;
 
 	if (!mlx4_is_master(dev))
 		return;
 
-	dm = kcalloc(dev->caps.num_ports, sizeof *dm, GFP_ATOMIC);
+	actv_ports = mlx4_get_active_ports(dev, slave);
+	ports = bitmap_weight(actv_ports.ports, dev->caps.num_ports);
+	first_port = find_first_bit(actv_ports.ports, dev->caps.num_ports);
+
+	dm = kcalloc(ports, sizeof(*dm), GFP_ATOMIC);
 	if (!dm) {
 		pr_err("failed to allocate memory for tunneling qp update\n");
 		goto out;
 	}
 
-	for (i = 0; i < dev->caps.num_ports; i++) {
+	for (i = 0; i < ports; i++) {
 		dm[i] = kmalloc(sizeof (struct mlx4_ib_demux_work), GFP_ATOMIC);
 		if (!dm[i]) {
 			pr_err("failed to allocate memory for tunneling qp update work struct\n");
@@ -2345,9 +2352,9 @@ static void do_slave_init(struct mlx4_ib_dev *ibdev, int slave, int do_init)
 		}
 	}
 	/* initialize or tear down tunnel QPs for the slave */
-	for (i = 0; i < dev->caps.num_ports; i++) {
+	for (i = 0; i < ports; i++) {
 		INIT_WORK(&dm[i]->work, mlx4_ib_tunnels_update_work);
-		dm[i]->port = i + 1;
+		dm[i]->port = first_port + i + 1;
 		dm[i]->slave = slave;
 		dm[i]->do_init = do_init;
 		dm[i]->dev = ibdev;
diff --git a/drivers/infiniband/hw/mlx4/sysfs.c b/drivers/infiniband/hw/mlx4/sysfs.c
index db2ea31df832..5a38e43eca65 100644
--- a/drivers/infiniband/hw/mlx4/sysfs.c
+++ b/drivers/infiniband/hw/mlx4/sysfs.c
@@ -627,6 +627,7 @@ static int register_one_pkey_tree(struct mlx4_ib_dev *dev, int slave)
 	int port;
 	struct kobject *p, *t;
 	struct mlx4_port *mport;
+	struct mlx4_active_ports actv_ports;
 
 	get_name(dev, name, slave, sizeof name);
 
@@ -649,7 +650,11 @@ static int register_one_pkey_tree(struct mlx4_ib_dev *dev, int slave)
 		goto err_ports;
 	}
 
+	actv_ports = mlx4_get_active_ports(dev->dev, slave);
+
 	for (port = 1; port <= dev->dev->caps.num_ports; ++port) {
+		if (!test_bit(port - 1, actv_ports.ports))
+			continue;
 		err = add_port(dev, port, slave);
 		if (err)
 			goto err_add;
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 59a1b2703281..516c1dd4963b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -1643,8 +1643,16 @@ static int mlx4_master_activate_admin_state(struct mlx4_priv *priv, int slave)
 	int port, err;
 	struct mlx4_vport_state *vp_admin;
 	struct mlx4_vport_oper_state *vp_oper;
-
-	for (port = 1; port <= MLX4_MAX_PORTS; port++) {
+	struct mlx4_active_ports actv_ports = mlx4_get_active_ports(
+			&priv->dev, slave);
+	int min_port = find_first_bit(actv_ports.ports,
+				      priv->dev.caps.num_ports) + 1;
+	int max_port = min_port - 1 +
+		bitmap_weight(actv_ports.ports, priv->dev.caps.num_ports);
+
+	for (port = min_port; port <= max_port; port++) {
+		if (!test_bit(port - 1, actv_ports.ports))
+			continue;
 		vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
 		vp_admin = &priv->mfunc.master.vf_admin[slave].vport[port];
 		vp_oper->state = *vp_admin;
@@ -1685,8 +1693,17 @@ static void mlx4_master_deactivate_admin_state(struct mlx4_priv *priv, int slave
 {
 	int port;
 	struct mlx4_vport_oper_state *vp_oper;
+	struct mlx4_active_ports actv_ports = mlx4_get_active_ports(
+			&priv->dev, slave);
+	int min_port = find_first_bit(actv_ports.ports,
+				      priv->dev.caps.num_ports) + 1;
+	int max_port = min_port - 1 +
+		bitmap_weight(actv_ports.ports, priv->dev.caps.num_ports);
+
 
-	for (port = 1; port <= MLX4_MAX_PORTS; port++) {
+	for (port = min_port; port <= max_port; port++) {
+		if (!test_bit(port - 1, actv_ports.ports))
+			continue;
 		vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
 		if (NO_INDX != vp_oper->vlan_idx) {
 			__mlx4_unregister_vlan(&priv->dev,
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 8992b38578d5..d501a2b0fb79 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -271,7 +271,10 @@ enum slave_port_state mlx4_get_slave_port_state(struct mlx4_dev *dev, int slave,
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_slave_state *s_state = priv->mfunc.master.slave_state;
-	if (slave >= dev->num_slaves || port > MLX4_MAX_PORTS) {
+	struct mlx4_active_ports actv_ports = mlx4_get_active_ports(dev, slave);
+
+	if (slave >= dev->num_slaves || port > dev->caps.num_ports ||
+	    port <= 0 || !test_bit(port - 1, actv_ports.ports)) {
 		pr_err("%s: Error: asking for slave:%d, port:%d\n",
 		       __func__, slave, port);
 		return SLAVE_PORT_DOWN;
@@ -285,8 +288,10 @@ static int mlx4_set_slave_port_state(struct mlx4_dev *dev, int slave, u8 port,
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_slave_state *s_state = priv->mfunc.master.slave_state;
+	struct mlx4_active_ports actv_ports = mlx4_get_active_ports(dev, slave);
 
-	if (slave >= dev->num_slaves || port > MLX4_MAX_PORTS || port == 0) {
+	if (slave >= dev->num_slaves || port > dev->caps.num_ports ||
+	    port <= 0 || !test_bit(port - 1, actv_ports.ports)) {
 		pr_err("%s: Error: asking for slave:%d, port:%d\n",
 		       __func__, slave, port);
 		return -1;
@@ -300,9 +305,13 @@ static void set_all_slave_state(struct mlx4_dev *dev, u8 port, int event)
 {
 	int i;
 	enum slave_port_gen_event gen_event;
+	struct mlx4_slaves_pport slaves_pport = mlx4_phys_to_slaves_pport(dev,
+									  port);
 
-	for (i = 0; i < dev->num_slaves; i++)
-		set_and_calc_slave_port_state(dev, i, port, event, &gen_event);
+	for (i = 0; i < dev->num_vfs + 1; i++)
+		if (test_bit(i, slaves_pport.slaves))
+			set_and_calc_slave_port_state(dev, i, port,
+						      event, &gen_event);
 }
 /**************************************************************************
 	The function get as input the new event to that port,
@@ -321,12 +330,14 @@ int set_and_calc_slave_port_state(struct mlx4_dev *dev, int slave,
 	struct mlx4_slave_state *ctx = NULL;
 	unsigned long flags;
 	int ret = -1;
+	struct mlx4_active_ports actv_ports = mlx4_get_active_ports(dev, slave);
 	enum slave_port_state cur_state =
 		mlx4_get_slave_port_state(dev, slave, port);
 
 	*gen_event = SLAVE_PORT_GEN_EVENT_NONE;
 
-	if (slave >= dev->num_slaves || port > MLX4_MAX_PORTS || port == 0) {
+	if (slave >= dev->num_slaves || port > dev->caps.num_ports ||
+	    port <= 0 || !test_bit(port - 1, actv_ports.ports)) {
 		pr_err("%s: Error: asking for slave:%d, port:%d\n",
 		       __func__, slave, port);
 		return ret;
@@ -542,15 +553,19 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 				       be64_to_cpu(eqe->event.cmd.out_param));
 			break;
 
-		case MLX4_EVENT_TYPE_PORT_CHANGE:
+		case MLX4_EVENT_TYPE_PORT_CHANGE: {
+			struct mlx4_slaves_pport slaves_port;
 			port = be32_to_cpu(eqe->event.port_change.port) >> 28;
+			slaves_port = mlx4_phys_to_slaves_pport(dev, port);
 			if (eqe->subtype == MLX4_PORT_CHANGE_SUBTYPE_DOWN) {
 				mlx4_dispatch_event(dev, MLX4_DEV_EVENT_PORT_DOWN,
 						    port);
 				mlx4_priv(dev)->sense.do_sense_port[port] = 1;
 				if (!mlx4_is_master(dev))
 					break;
-				for (i = 0; i < dev->num_slaves; i++) {
+				for (i = 0; i < dev->num_vfs + 1; i++) {
+					if (!test_bit(i, slaves_port.slaves))
+						continue;
 					if (dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH) {
 						if (i == mlx4_master_func_num(dev))
 							continue;
@@ -558,8 +573,13 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 							 " to slave: %d, port:%d\n",
 							 __func__, i, port);
 						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
-						if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state)
+						if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) {
+							eqe->event.port_change.port =
+								cpu_to_be32(
+								(be32_to_cpu(eqe->event.port_change.port) & 0xFFFFFFF)
+								| (mlx4_phys_to_slave_port(dev, i, port) << 28));
 							mlx4_slave_event(dev, i, eqe);
+						}
 					} else {  /* IB port */
 						set_and_calc_slave_port_state(dev, i, port,
 									      MLX4_PORT_STATE_DEV_EVENT_PORT_DOWN,
@@ -580,12 +600,19 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 				if (!mlx4_is_master(dev))
 					break;
 				if (dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH)
-					for (i = 0; i < dev->num_slaves; i++) {
+					for (i = 0; i < dev->num_vfs + 1; i++) {
+						if (!test_bit(i, slaves_port.slaves))
+							continue;
 						if (i == mlx4_master_func_num(dev))
 							continue;
 						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
-						if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state)
+						if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) {
+							eqe->event.port_change.port =
+								cpu_to_be32(
+								(be32_to_cpu(eqe->event.port_change.port) & 0xFFFFFFF)
+								| (mlx4_phys_to_slave_port(dev, i, port) << 28));
 							mlx4_slave_event(dev, i, eqe);
+						}
 					}
 				else /* IB port */
 					/* port-up event will be sent to a slave when the
@@ -594,6 +621,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 					set_all_slave_state(dev, port, MLX4_DEV_EVENT_PORT_UP);
 			}
 			break;
+		}
 
 		case MLX4_EVENT_TYPE_CQ_ERROR:
 			mlx4_warn(dev, "CQ %s on CQN %06x\n",
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index d0d8dd832557..6bd33e2fc17c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -225,13 +225,25 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 #define QUERY_FUNC_CAP_FLAGS0_FORCE_PHY_WQE_GID 0x80
 
 	if (vhcr->op_modifier == 1) {
+		struct mlx4_active_ports actv_ports =
+			mlx4_get_active_ports(dev, slave);
+		int converted_port = mlx4_slave_convert_port(
+				dev, slave, vhcr->in_modifier);
+
+		if (converted_port < 0)
+			return -EINVAL;
+
+		vhcr->in_modifier = converted_port;
 		/* Set nic_info bit to mark new fields support */
 		field  = QUERY_FUNC_CAP_FLAGS1_NIC_INFO;
 		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_FLAGS1_OFFSET);
 
-		field = vhcr->in_modifier; /* phys-port = logical-port */
+		/* phys-port = logical-port */
+		field = vhcr->in_modifier -
+			find_first_bit(actv_ports.ports, dev->caps.num_ports);
 		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_PHYS_PORT_OFFSET);
 
+		field = vhcr->in_modifier;
 		/* size is now the QP number */
 		size = dev->phys_caps.base_tunnel_sqpn + 8 * slave + field - 1;
 		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_QP0_TUNNEL);
@@ -249,12 +261,16 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 			 QUERY_FUNC_CAP_PHYS_PORT_ID);
 
 	} else if (vhcr->op_modifier == 0) {
+		struct mlx4_active_ports actv_ports =
+			mlx4_get_active_ports(dev, slave);
 		/* enable rdma and ethernet interfaces, and new quota locations */
 		field = (QUERY_FUNC_CAP_FLAG_ETH | QUERY_FUNC_CAP_FLAG_RDMA |
 			 QUERY_FUNC_CAP_FLAG_QUOTAS);
 		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_FLAGS_OFFSET);
 
-		field = dev->caps.num_ports;
+		field = min(
+			bitmap_weight(actv_ports.ports, dev->caps.num_ports),
+			dev->caps.num_ports);
 		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_NUM_PORTS_OFFSET);
 
 		size = dev->caps.function_caps; /* set PF behaviours */
@@ -840,6 +856,10 @@ int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave,
 	int	err = 0;
 	u8	field;
 	u32	bmme_flags;
+	int	real_port;
+	int	slave_port;
+	int	first_port;
+	struct mlx4_active_ports actv_ports;
 
 	err = mlx4_cmd_box(dev, 0, outbox->dma, 0, 0, MLX4_CMD_QUERY_DEV_CAP,
 			   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
@@ -852,8 +872,26 @@ int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave,
 	MLX4_GET(flags, outbox->buf, QUERY_DEV_CAP_EXT_FLAGS_OFFSET);
 	flags |= MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV;
 	flags &= ~MLX4_DEV_CAP_FLAG_MEM_WINDOW;
+	actv_ports = mlx4_get_active_ports(dev, slave);
+	first_port = find_first_bit(actv_ports.ports, dev->caps.num_ports);
+	for (slave_port = 0, real_port = first_port;
+	     real_port < first_port +
+	     bitmap_weight(actv_ports.ports, dev->caps.num_ports);
+	     ++real_port, ++slave_port) {
+		if (flags & (MLX4_DEV_CAP_FLAG_WOL_PORT1 << real_port))
+			flags |= MLX4_DEV_CAP_FLAG_WOL_PORT1 << slave_port;
+		else
+			flags &= ~(MLX4_DEV_CAP_FLAG_WOL_PORT1 << slave_port);
+	}
+	for (; slave_port < dev->caps.num_ports; ++slave_port)
+		flags &= ~(MLX4_DEV_CAP_FLAG_WOL_PORT1 << slave_port);
 	MLX4_PUT(outbox->buf, flags, QUERY_DEV_CAP_EXT_FLAGS_OFFSET);
 
+	MLX4_GET(field, outbox->buf, QUERY_DEV_CAP_VL_PORT_OFFSET);
+	field &= ~0x0F;
+	field |= bitmap_weight(actv_ports.ports, dev->caps.num_ports) & 0x0F;
+	MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_VL_PORT_OFFSET);
+
 	/* For guests, disable timestamp */
 	MLX4_GET(field, outbox->buf, QUERY_DEV_CAP_CQ_TS_SUPPORT_OFFSET);
 	field &= 0x7f;
@@ -903,12 +941,20 @@ int mlx4_QUERY_PORT_wrapper(struct mlx4_dev *dev, int slave,
 	u16 short_field;
 	int err;
 	int admin_link_state;
+	int port = mlx4_slave_convert_port(dev, slave,
+					   vhcr->in_modifier & 0xFF);
 
 #define MLX4_VF_PORT_NO_LINK_SENSE_MASK	0xE0
 #define MLX4_PORT_LINK_UP_MASK		0x80
 #define QUERY_PORT_CUR_MAX_PKEY_OFFSET	0x0c
 #define QUERY_PORT_CUR_MAX_GID_OFFSET	0x0e
 
+	if (port < 0)
+		return -EINVAL;
+
+	vhcr->in_modifier = (vhcr->in_modifier & ~0xFF) |
+			    (port & 0xFF);
+
 	err = mlx4_cmd_box(dev, 0, outbox->dma, vhcr->in_modifier, 0,
 			   MLX4_CMD_QUERY_PORT, MLX4_CMD_TIME_CLASS_B,
 			   MLX4_CMD_NATIVE);
@@ -936,7 +982,7 @@ int mlx4_QUERY_PORT_wrapper(struct mlx4_dev *dev, int slave,
 			 QUERY_PORT_SUPPORTED_TYPE_OFFSET);
 
 		if (dev->caps.port_type[vhcr->in_modifier] == MLX4_PORT_TYPE_ETH)
-			short_field = mlx4_get_slave_num_gids(dev, slave);
+			short_field = mlx4_get_slave_num_gids(dev, slave, port);
 		else
 			short_field = 1; /* slave max gids */
 		MLX4_PUT(outbox->buf, short_field,
@@ -1588,9 +1634,12 @@ int mlx4_INIT_PORT_wrapper(struct mlx4_dev *dev, int slave,
 			   struct mlx4_cmd_info *cmd)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
-	int port = vhcr->in_modifier;
+	int port = mlx4_slave_convert_port(dev, slave, vhcr->in_modifier);
 	int err;
 
+	if (port < 0)
+		return -EINVAL;
+
 	if (priv->mfunc.master.slave_state[slave].init_port_mask & (1 << port))
 		return 0;
 
@@ -1680,9 +1729,12 @@ int mlx4_CLOSE_PORT_wrapper(struct mlx4_dev *dev, int slave,
 			    struct mlx4_cmd_info *cmd)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
-	int port = vhcr->in_modifier;
+	int port = mlx4_slave_convert_port(dev, slave, vhcr->in_modifier);
 	int err;
 
+	if (port < 0)
+		return -EINVAL;
+
 	if (!(priv->mfunc.master.slave_state[slave].init_port_mask &
 	    (1 << port)))
 		return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index e1a55857af71..472925428de7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -1471,7 +1471,7 @@ static void mlx4_parav_master_pf_caps(struct mlx4_dev *dev)
 	for (i = 1; i <= dev->caps.num_ports; i++) {
 		if (dev->caps.port_type[i] == MLX4_PORT_TYPE_ETH)
 			dev->caps.gid_table_len[i] =
-				mlx4_get_slave_num_gids(dev, 0);
+				mlx4_get_slave_num_gids(dev, 0, i);
 		else
 			dev->caps.gid_table_len[i] = 1;
 		dev->caps.pkey_table_len[i] =
@@ -1498,7 +1498,7 @@ static void choose_steering_mode(struct mlx4_dev *dev,
 	if (mlx4_log_num_mgm_entry_size == -1 &&
 	    dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_FS_EN &&
 	    (!mlx4_is_mfunc(dev) ||
-	     (dev_cap->fs_max_num_qp_per_entry >= (num_vfs + 1))) &&
+	     (dev_cap->fs_max_num_qp_per_entry >= (dev->num_vfs + 1))) &&
 	    choose_log_fs_mgm_entry_size(dev_cap->fs_max_num_qp_per_entry) >=
 		MLX4_MIN_MGM_LOG_ENTRY_SIZE) {
 		dev->oper_log_mgm_entry_size =
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index db7dc0b6667d..80ccb4edf825 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -1387,9 +1387,12 @@ int mlx4_PROMISC_wrapper(struct mlx4_dev *dev, int slave,
 			 struct mlx4_cmd_info *cmd)
 {
 	u32 qpn = (u32) vhcr->in_param & 0xffffffff;
-	u8 port = vhcr->in_param >> 62;
+	int port = mlx4_slave_convert_port(dev, slave, vhcr->in_param >> 62);
 	enum mlx4_steer_type steer = vhcr->in_modifier;
 
+	if (port < 0)
+		return -EINVAL;
+
 	/* Promiscuous unicast is not allowed in mfunc */
 	if (mlx4_is_mfunc(dev) && steer == MLX4_UC_STEER)
 		return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index fe8715e35afa..9fca6c150de3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -1287,8 +1287,7 @@ void mlx4_vf_immed_vlan_work_handler(struct work_struct *_work);
 
 void mlx4_init_quotas(struct mlx4_dev *dev);
 
-int mlx4_get_slave_num_gids(struct mlx4_dev *dev, int slave);
-int mlx4_get_base_gid_ix(struct mlx4_dev *dev, int slave);
+int mlx4_get_slave_num_gids(struct mlx4_dev *dev, int slave, int port);
 /* Returns the VF index of slave */
 int mlx4_get_vf_indx(struct mlx4_dev *dev, int slave);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index ece328166e94..2705b9ab9463 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -507,30 +507,82 @@ int mlx4_get_port_ib_caps(struct mlx4_dev *dev, u8 port, __be32 *caps)
 }
 static struct mlx4_roce_gid_entry zgid_entry;
 
-int mlx4_get_slave_num_gids(struct mlx4_dev *dev, int slave)
+int mlx4_get_slave_num_gids(struct mlx4_dev *dev, int slave, int port)
 {
+	int vfs;
+	int slave_gid = slave;
+	unsigned i;
+	struct mlx4_slaves_pport slaves_pport;
+	struct mlx4_active_ports actv_ports;
+	unsigned max_port_p_one;
+
 	if (slave == 0)
 		return MLX4_ROCE_PF_GIDS;
-	if (slave <= ((MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS) % dev->num_vfs))
-		return ((MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS) / dev->num_vfs) + 1;
-	return (MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS) / dev->num_vfs;
+
+	/* Slave is a VF */
+	slaves_pport = mlx4_phys_to_slaves_pport(dev, port);
+	actv_ports = mlx4_get_active_ports(dev, slave);
+	max_port_p_one = find_first_bit(actv_ports.ports, dev->caps.num_ports) +
+		bitmap_weight(actv_ports.ports, dev->caps.num_ports) + 1;
+
+	for (i = 1; i < max_port_p_one; i++) {
+		struct mlx4_active_ports exclusive_ports;
+		struct mlx4_slaves_pport slaves_pport_actv;
+		bitmap_zero(exclusive_ports.ports, dev->caps.num_ports);
+		set_bit(i - 1, exclusive_ports.ports);
+		if (i == port)
+			continue;
+		slaves_pport_actv = mlx4_phys_to_slaves_pport_actv(
+				    dev, &exclusive_ports);
+		slave_gid -= bitmap_weight(slaves_pport_actv.slaves,
+					   dev->num_vfs + 1);
+	}
+	vfs = bitmap_weight(slaves_pport.slaves, dev->num_vfs + 1) - 1;
+	if (slave_gid <= ((MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS) % vfs))
+		return ((MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS) / vfs) + 1;
+	return (MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS) / vfs;
 }
 
-int mlx4_get_base_gid_ix(struct mlx4_dev *dev, int slave)
+int mlx4_get_base_gid_ix(struct mlx4_dev *dev, int slave, int port)
 {
 	int gids;
+	unsigned i;
+	int slave_gid = slave;
 	int vfs;
 
-	gids = MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS;
-	vfs = dev->num_vfs;
+	struct mlx4_slaves_pport slaves_pport;
+	struct mlx4_active_ports actv_ports;
+	unsigned max_port_p_one;
 
 	if (slave == 0)
 		return 0;
-	if (slave <= gids % vfs)
-		return MLX4_ROCE_PF_GIDS + ((gids / vfs) + 1) * (slave - 1);
 
-	return MLX4_ROCE_PF_GIDS + (gids % vfs) + ((gids / vfs) * (slave - 1));
+	slaves_pport = mlx4_phys_to_slaves_pport(dev, port);
+	actv_ports = mlx4_get_active_ports(dev, slave);
+	max_port_p_one = find_first_bit(actv_ports.ports, dev->caps.num_ports) +
+		bitmap_weight(actv_ports.ports, dev->caps.num_ports) + 1;
+
+	for (i = 1; i < max_port_p_one; i++) {
+		struct mlx4_active_ports exclusive_ports;
+		struct mlx4_slaves_pport slaves_pport_actv;
+		bitmap_zero(exclusive_ports.ports, dev->caps.num_ports);
+		set_bit(i - 1, exclusive_ports.ports);
+		if (i == port)
+			continue;
+		slaves_pport_actv = mlx4_phys_to_slaves_pport_actv(
+				    dev, &exclusive_ports);
+		slave_gid -= bitmap_weight(slaves_pport_actv.slaves,
+					   dev->num_vfs + 1);
+	}
+	gids = MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS;
+	vfs = bitmap_weight(slaves_pport.slaves, dev->num_vfs + 1) - 1;
+	if (slave_gid <= gids % vfs)
+		return MLX4_ROCE_PF_GIDS + ((gids / vfs) + 1) * (slave_gid - 1);
+
+	return MLX4_ROCE_PF_GIDS + (gids % vfs) +
+		((gids / vfs) * (slave_gid - 1));
 }
+EXPORT_SYMBOL_GPL(mlx4_get_base_gid_ix);
 
 static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
 				u8 op_mod, struct mlx4_cmd_mailbox *inbox)
@@ -617,8 +669,8 @@ static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
 			 * need a FOR-loop here over number of gids the guest has.
 			 * 1. Check no duplicates in gids passed by slave
 			 */
-			num_gids = mlx4_get_slave_num_gids(dev, slave);
-			base = mlx4_get_base_gid_ix(dev, slave);
+			num_gids = mlx4_get_slave_num_gids(dev, slave, port);
+			base = mlx4_get_base_gid_ix(dev, slave, port);
 			gid_entry_mbox = (struct mlx4_roce_gid_entry *)(inbox->buf);
 			for (i = 0; i < num_gids; gid_entry_mbox++, i++) {
 				if (!memcmp(gid_entry_mbox->raw, zgid_entry.raw,
@@ -738,6 +790,15 @@ int mlx4_SET_PORT_wrapper(struct mlx4_dev *dev, int slave,
 			  struct mlx4_cmd_mailbox *outbox,
 			  struct mlx4_cmd_info *cmd)
 {
+	int port = mlx4_slave_convert_port(
+			dev, slave, vhcr->in_modifier & 0xFF);
+
+	if (port < 0)
+		return -EINVAL;
+
+	vhcr->in_modifier = (vhcr->in_modifier & ~0xFF) |
+			    (port & 0xFF);
+
 	return mlx4_common_set_port(dev, slave, vhcr->in_modifier,
 				    vhcr->op_modifier, inbox);
 }
@@ -1026,10 +1087,16 @@ int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid,
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int i, found_ix = -1;
 	int vf_gids = MLX4_ROCE_MAX_GIDS - MLX4_ROCE_PF_GIDS;
+	struct mlx4_slaves_pport slaves_pport;
+	unsigned num_vfs;
+	int slave_gid;
 
 	if (!mlx4_is_mfunc(dev))
 		return -EINVAL;
 
+	slaves_pport = mlx4_phys_to_slaves_pport(dev, port);
+	num_vfs = bitmap_weight(slaves_pport.slaves, dev->num_vfs + 1) - 1;
+
 	for (i = 0; i < MLX4_ROCE_MAX_GIDS; i++) {
 		if (!memcmp(priv->roce_gids[port - 1][i].raw, gid, 16)) {
 			found_ix = i;
@@ -1039,16 +1106,67 @@ int mlx4_get_slave_from_roce_gid(struct mlx4_dev *dev, int port, u8 *gid,
 
 	if (found_ix >= 0) {
 		if (found_ix < MLX4_ROCE_PF_GIDS)
-			*slave_id = 0;
-		else if (found_ix < MLX4_ROCE_PF_GIDS + (vf_gids % dev->num_vfs) *
-			 (vf_gids / dev->num_vfs + 1))
-			*slave_id = ((found_ix - MLX4_ROCE_PF_GIDS) /
-				     (vf_gids / dev->num_vfs + 1)) + 1;
+			slave_gid = 0;
+		else if (found_ix < MLX4_ROCE_PF_GIDS + (vf_gids % num_vfs) *
+			 (vf_gids / num_vfs + 1))
+			slave_gid = ((found_ix - MLX4_ROCE_PF_GIDS) /
+				     (vf_gids / num_vfs + 1)) + 1;
 		else
-			*slave_id =
+			slave_gid =
 			((found_ix - MLX4_ROCE_PF_GIDS -
-			  ((vf_gids % dev->num_vfs) * ((vf_gids / dev->num_vfs + 1)))) /
-			 (vf_gids / dev->num_vfs)) + vf_gids % dev->num_vfs + 1;
+			  ((vf_gids % num_vfs) * ((vf_gids / num_vfs + 1)))) /
+			 (vf_gids / num_vfs)) + vf_gids % num_vfs + 1;
+
+		if (slave_gid) {
+			struct mlx4_active_ports exclusive_ports;
+			struct mlx4_active_ports actv_ports;
+			struct mlx4_slaves_pport slaves_pport_actv;
+			unsigned max_port_p_one;
+			int num_slaves_before = 1;
+
+			for (i = 1; i < port; i++) {
+				bitmap_zero(exclusive_ports.ports, dev->caps.num_ports);
+				set_bit(i, exclusive_ports.ports);
+				slaves_pport_actv =
+					mlx4_phys_to_slaves_pport_actv(
+							dev, &exclusive_ports);
+				num_slaves_before += bitmap_weight(
+						slaves_pport_actv.slaves,
+						dev->num_vfs + 1);
+			}
+
+			if (slave_gid < num_slaves_before) {
+				bitmap_zero(exclusive_ports.ports, dev->caps.num_ports);
+				set_bit(port - 1, exclusive_ports.ports);
+				slaves_pport_actv =
+					mlx4_phys_to_slaves_pport_actv(
+							dev, &exclusive_ports);
+				slave_gid += bitmap_weight(
+						slaves_pport_actv.slaves,
+						dev->num_vfs + 1) -
+						num_slaves_before;
+			}
+			actv_ports = mlx4_get_active_ports(dev, slave_gid);
+			max_port_p_one = find_first_bit(
+				actv_ports.ports, dev->caps.num_ports) +
+				bitmap_weight(actv_ports.ports,
+					      dev->caps.num_ports) + 1;
+
+			for (i = 1; i < max_port_p_one; i++) {
+				if (i == port)
+					continue;
+				bitmap_zero(exclusive_ports.ports,
+					    dev->caps.num_ports);
+				set_bit(i - 1, exclusive_ports.ports);
+				slaves_pport_actv =
+					mlx4_phys_to_slaves_pport_actv(
+						dev, &exclusive_ports);
+				slave_gid += bitmap_weight(
+						slaves_pport_actv.slaves,
+						dev->num_vfs + 1);
+			}
+		}
+		*slave_id = slave_gid;
 	}
 
 	return (found_ix >= 0) ? 0 : -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 74e490d70184..2a33513a0e31 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -468,6 +468,8 @@ int mlx4_init_resource_tracker(struct mlx4_dev *dev)
 
 		spin_lock_init(&res_alloc->alloc_lock);
 		for (t = 0; t < dev->num_vfs + 1; t++) {
+			struct mlx4_active_ports actv_ports =
+				mlx4_get_active_ports(dev, t);
 			switch (i) {
 			case RES_QP:
 				initialize_res_quotas(dev, res_alloc, RES_QP,
@@ -497,10 +499,27 @@ int mlx4_init_resource_tracker(struct mlx4_dev *dev)
 				break;
 			case RES_MAC:
 				if (t == mlx4_master_func_num(dev)) {
-					res_alloc->quota[t] = MLX4_MAX_MAC_NUM;
+					int max_vfs_pport = 0;
+					/* Calculate the max vfs per port for */
+					/* both ports.			      */
+					for (j = 0; j < dev->caps.num_ports;
+					     j++) {
+						struct mlx4_slaves_pport slaves_pport =
+							mlx4_phys_to_slaves_pport(dev, j + 1);
+						unsigned current_slaves =
+							bitmap_weight(slaves_pport.slaves,
+								      dev->caps.num_ports) - 1;
+						if (max_vfs_pport < current_slaves)
+							max_vfs_pport =
+								current_slaves;
+					}
+					res_alloc->quota[t] =
+						MLX4_MAX_MAC_NUM -
+						2 * max_vfs_pport;
 					res_alloc->guaranteed[t] = 2;
 					for (j = 0; j < MLX4_MAX_PORTS; j++)
-						res_alloc->res_port_free[j] = MLX4_MAX_MAC_NUM;
+						res_alloc->res_port_free[j] =
+							MLX4_MAX_MAC_NUM;
 				} else {
 					res_alloc->quota[t] = MLX4_MAX_MAC_NUM;
 					res_alloc->guaranteed[t] = 2;
@@ -528,9 +547,10 @@ int mlx4_init_resource_tracker(struct mlx4_dev *dev)
 				break;
 			}
 			if (i == RES_MAC || i == RES_VLAN) {
-				for (j = 0; j < MLX4_MAX_PORTS; j++)
-					res_alloc->res_port_rsvd[j] +=
-						res_alloc->guaranteed[t];
+				for (j = 0; j < dev->caps.num_ports; j++)
+					if (test_bit(j, actv_ports.ports))
+						res_alloc->res_port_rsvd[j] +=
+							res_alloc->guaranteed[t];
 			} else {
 				res_alloc->res_reserved += res_alloc->guaranteed[t];
 			}
@@ -612,7 +632,8 @@ static void update_gid(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *inbox,
 	if (MLX4_QP_ST_UD == ts) {
 		port = (qp_ctx->pri_path.sched_queue >> 6 & 1) + 1;
 		if (mlx4_is_eth(dev, port))
-			qp_ctx->pri_path.mgid_index = mlx4_get_base_gid_ix(dev, slave) | 0x80;
+			qp_ctx->pri_path.mgid_index =
+				mlx4_get_base_gid_ix(dev, slave, port) | 0x80;
 		else
 			qp_ctx->pri_path.mgid_index = slave | 0x80;
 
@@ -620,7 +641,8 @@ static void update_gid(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *inbox,
 		if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH) {
 			port = (qp_ctx->pri_path.sched_queue >> 6 & 1) + 1;
 			if (mlx4_is_eth(dev, port)) {
-				qp_ctx->pri_path.mgid_index += mlx4_get_base_gid_ix(dev, slave);
+				qp_ctx->pri_path.mgid_index +=
+					mlx4_get_base_gid_ix(dev, slave, port);
 				qp_ctx->pri_path.mgid_index &= 0x7f;
 			} else {
 				qp_ctx->pri_path.mgid_index = slave & 0x7F;
@@ -629,7 +651,8 @@ static void update_gid(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *inbox,
 		if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH) {
 			port = (qp_ctx->alt_path.sched_queue >> 6 & 1) + 1;
 			if (mlx4_is_eth(dev, port)) {
-				qp_ctx->alt_path.mgid_index += mlx4_get_base_gid_ix(dev, slave);
+				qp_ctx->alt_path.mgid_index +=
+					mlx4_get_base_gid_ix(dev, slave, port);
 				qp_ctx->alt_path.mgid_index &= 0x7f;
 			} else {
 				qp_ctx->alt_path.mgid_index = slave & 0x7F;
@@ -1780,6 +1803,11 @@ static int mac_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
 		return err;
 
 	port = !in_port ? get_param_l(out_param) : in_port;
+	port = mlx4_slave_convert_port(
+			dev, slave, port);
+
+	if (port < 0)
+		return -EINVAL;
 	mac = in_param;
 
 	err = __mlx4_register_mac(dev, port, mac);
@@ -1887,6 +1915,11 @@ static int vlan_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
 	if (!port || op != RES_OP_RESERVE_AND_MAP)
 		return -EINVAL;
 
+	port = mlx4_slave_convert_port(
+			dev, slave, port);
+
+	if (port < 0)
+		return -EINVAL;
 	/* upstream kernels had NOP for reg/unreg vlan. Continue this. */
 	if (!in_port && port > 0 && port <= dev->caps.num_ports) {
 		slave_state[slave].old_vlan_api = true;
@@ -2184,6 +2217,11 @@ static int mac_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
 	switch (op) {
 	case RES_OP_RESERVE_AND_MAP:
 		port = !in_port ? get_param_l(out_param) : in_port;
+		port = mlx4_slave_convert_port(
+				dev, slave, port);
+
+		if (port < 0)
+			return -EINVAL;
 		mac_del_from_slave(dev, slave, in_param, port);
 		__mlx4_unregister_mac(dev, port, in_param);
 		break;
@@ -2203,6 +2241,11 @@ static int vlan_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
 	struct mlx4_slave_state *slave_state = priv->mfunc.master.slave_state;
 	int err = 0;
 
+	port = mlx4_slave_convert_port(
+			dev, slave, port);
+
+	if (port < 0)
+		return -EINVAL;
 	switch (op) {
 	case RES_OP_RESERVE_AND_MAP:
 		if (slave_state[slave].old_vlan_api)
@@ -2811,7 +2854,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev,
 				if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH) {
 					port = (qp_ctx->pri_path.sched_queue >> 6 & 1) + 1;
 					if (dev->caps.port_mask[port] != MLX4_PORT_TYPE_IB)
-						num_gids = mlx4_get_slave_num_gids(dev, slave);
+						num_gids = mlx4_get_slave_num_gids(dev, slave, port);
 					else
 						num_gids = 1;
 					if (qp_ctx->pri_path.mgid_index >= num_gids)
@@ -2820,7 +2863,7 @@ static int verify_qp_parameters(struct mlx4_dev *dev,
 				if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH) {
 					port = (qp_ctx->alt_path.sched_queue >> 6 & 1) + 1;
 					if (dev->caps.port_mask[port] != MLX4_PORT_TYPE_IB)
-						num_gids = mlx4_get_slave_num_gids(dev, slave);
+						num_gids = mlx4_get_slave_num_gids(dev, slave, port);
 					else
 						num_gids = 1;
 					if (qp_ctx->alt_path.mgid_index >= num_gids)
@@ -3338,6 +3381,39 @@ int mlx4_INIT2INIT_QP_wrapper(struct mlx4_dev *dev, int slave,
 	return mlx4_GEN_QP_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
 }
 
+static int adjust_qp_sched_queue(struct mlx4_dev *dev, int slave,
+				  struct mlx4_qp_context *qpc,
+				  struct mlx4_cmd_mailbox *inbox)
+{
+	enum mlx4_qp_optpar optpar = be32_to_cpu(*(__be32 *)inbox->buf);
+	u8 pri_sched_queue;
+	int port = mlx4_slave_convert_port(
+		   dev, slave, (qpc->pri_path.sched_queue >> 6 & 1) + 1) - 1;
+
+	if (port < 0)
+		return -EINVAL;
+
+	pri_sched_queue = (qpc->pri_path.sched_queue & ~(1 << 6)) |
+			  ((port & 1) << 6);
+
+	if (optpar & MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH ||
+	    mlx4_is_eth(dev, port + 1)) {
+		qpc->pri_path.sched_queue = pri_sched_queue;
+	}
+
+	if (optpar & MLX4_QP_OPTPAR_ALT_ADDR_PATH) {
+		port = mlx4_slave_convert_port(
+				dev, slave, (qpc->alt_path.sched_queue >> 6 & 1)
+				+ 1) - 1;
+		if (port < 0)
+			return -EINVAL;
+		qpc->alt_path.sched_queue =
+			(qpc->alt_path.sched_queue & ~(1 << 6)) |
+			(port & 1) << 6;
+	}
+	return 0;
+}
+
 static int roce_verify_mac(struct mlx4_dev *dev, int slave,
 				struct mlx4_qp_context *qpc,
 				struct mlx4_cmd_mailbox *inbox)
@@ -3375,6 +3451,9 @@ int mlx4_INIT2RTR_QP_wrapper(struct mlx4_dev *dev, int slave,
 	u8 orig_vlan_index = qpc->pri_path.vlan_index;
 	u8 orig_feup = qpc->pri_path.feup;
 
+	err = adjust_qp_sched_queue(dev, slave, qpc, inbox);
+	if (err)
+		return err;
 	err = verify_qp_parameters(dev, inbox, QP_TRANS_INIT2RTR, slave);
 	if (err)
 		return err;
@@ -3426,6 +3505,9 @@ int mlx4_RTR2RTS_QP_wrapper(struct mlx4_dev *dev, int slave,
 	int err;
 	struct mlx4_qp_context *context = inbox->buf + 8;
 
+	err = adjust_qp_sched_queue(dev, slave, context, inbox);
+	if (err)
+		return err;
 	err = verify_qp_parameters(dev, inbox, QP_TRANS_RTR2RTS, slave);
 	if (err)
 		return err;
@@ -3445,6 +3527,9 @@ int mlx4_RTS2RTS_QP_wrapper(struct mlx4_dev *dev, int slave,
 	int err;
 	struct mlx4_qp_context *context = inbox->buf + 8;
 
+	err = adjust_qp_sched_queue(dev, slave, context, inbox);
+	if (err)
+		return err;
 	err = verify_qp_parameters(dev, inbox, QP_TRANS_RTS2RTS, slave);
 	if (err)
 		return err;
@@ -3463,6 +3548,9 @@ int mlx4_SQERR2RTS_QP_wrapper(struct mlx4_dev *dev, int slave,
 			      struct mlx4_cmd_info *cmd)
 {
 	struct mlx4_qp_context *context = inbox->buf + 8;
+	int err = adjust_qp_sched_queue(dev, slave, context, inbox);
+	if (err)
+		return err;
 	adjust_proxy_tun_qkey(dev, vhcr, context);
 	return mlx4_GEN_QP_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
 }
@@ -3476,6 +3564,9 @@ int mlx4_SQD2SQD_QP_wrapper(struct mlx4_dev *dev, int slave,
 	int err;
 	struct mlx4_qp_context *context = inbox->buf + 8;
 
+	err = adjust_qp_sched_queue(dev, slave, context, inbox);
+	if (err)
+		return err;
 	err = verify_qp_parameters(dev, inbox, QP_TRANS_SQD2SQD, slave);
 	if (err)
 		return err;
@@ -3495,6 +3586,9 @@ int mlx4_SQD2RTS_QP_wrapper(struct mlx4_dev *dev, int slave,
 	int err;
 	struct mlx4_qp_context *context = inbox->buf + 8;
 
+	err = adjust_qp_sched_queue(dev, slave, context, inbox);
+	if (err)
+		return err;
 	err = verify_qp_parameters(dev, inbox, QP_TRANS_SQD2RTS, slave);
 	if (err)
 		return err;
@@ -3598,16 +3692,26 @@ static int rem_mcg_res(struct mlx4_dev *dev, int slave, struct res_qp *rqp,
 	return err;
 }
 
-static int qp_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
-		     int block_loopback, enum mlx4_protocol prot,
+static int qp_attach(struct mlx4_dev *dev, int slave, struct mlx4_qp *qp,
+		     u8 gid[16], int block_loopback, enum mlx4_protocol prot,
 		     enum mlx4_steer_type type, u64 *reg_id)
 {
 	switch (dev->caps.steering_mode) {
-	case MLX4_STEERING_MODE_DEVICE_MANAGED:
-		return mlx4_trans_to_dmfs_attach(dev, qp, gid, gid[5],
+	case MLX4_STEERING_MODE_DEVICE_MANAGED: {
+		int port = mlx4_slave_convert_port(dev, slave, gid[5]);
+		if (port < 0)
+			return port;
+		return mlx4_trans_to_dmfs_attach(dev, qp, gid, port,
 						block_loopback, prot,
 						reg_id);
+	}
 	case MLX4_STEERING_MODE_B0:
+		if (prot == MLX4_PROT_ETH) {
+			int port = mlx4_slave_convert_port(dev, slave, gid[5]);
+			if (port < 0)
+				return port;
+			gid[5] = port;
+		}
 		return mlx4_qp_attach_common(dev, qp, gid,
 					    block_loopback, prot, type);
 	default:
@@ -3615,9 +3719,9 @@ static int qp_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	}
 }
 
-static int qp_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
-		     enum mlx4_protocol prot, enum mlx4_steer_type type,
-		     u64 reg_id)
+static int qp_detach(struct mlx4_dev *dev, struct mlx4_qp *qp,
+		     u8 gid[16], enum mlx4_protocol prot,
+		     enum mlx4_steer_type type, u64 reg_id)
 {
 	switch (dev->caps.steering_mode) {
 	case MLX4_STEERING_MODE_DEVICE_MANAGED:
@@ -3654,7 +3758,7 @@ int mlx4_QP_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
 
 	qp.qpn = qpn;
 	if (attach) {
-		err = qp_attach(dev, &qp, gid, block_loopback, prot,
+		err = qp_attach(dev, slave, &qp, gid, block_loopback, prot,
 				type, &reg_id);
 		if (err) {
 			pr_err("Fail to attach rule to qp 0x%x\n", qpn);
@@ -3790,6 +3894,9 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
 		return -EOPNOTSUPP;
 
 	ctrl = (struct mlx4_net_trans_rule_hw_ctrl *)inbox->buf;
+	ctrl->port = mlx4_slave_convert_port(dev, slave, ctrl->port);
+	if (ctrl->port <= 0)
+		return -EINVAL;
 	qpn = be32_to_cpu(ctrl->qpn) & 0xffffff;
 	err = get_res(dev, slave, qpn, RES_QP, &rqp);
 	if (err) {
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 122c7cabaee7..6b3998396b99 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1231,4 +1231,5 @@ struct mlx4_slaves_pport mlx4_phys_to_slaves_pport_actv(
 /* Returns the slave's virtual port that represents the physical port. */
 int mlx4_phys_to_slave_port(struct mlx4_dev *dev, int slave, int port);
 
+int mlx4_get_base_gid_ix(struct mlx4_dev *dev, int slave, int port);
 #endif /* MLX4_DEVICE_H */
-- 
cgit v1.2.3


From 259fef033ffe4e70bf7f358c53400a09f1b5384e Mon Sep 17 00:00:00 2001
From: Ben Chan <benchan@chromium.org>
Date: Wed, 19 Mar 2014 14:00:06 -0700
Subject: net: cdc_ncm: respect operator preferred MTU reported by MBIM

According to "Universal Serial Bus Communications Class Subclass
Specification for Mobile Broadband Interface Model, Revision 1.0,
Errata-1" published by USB-IF, the wMTU field of the MBIM extended
functional descriptor indicates the operator preferred MTU for IP data
streams.

This patch modifies cdc_ncm_setup to ensure that the MTU value set on
the usbnet device does not exceed the operator preferred MTU indicated
by wMTU if the MBIM device exposes a MBIM extended functional
descriptor.

Signed-off-by: Ben Chan <benchan@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_ncm.c   | 17 +++++++++++++++++
 include/linux/usb/cdc_ncm.h |  1 +
 2 files changed, 18 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index dbff290ed0e4..e8711a8cfa01 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -74,6 +74,7 @@ static int cdc_ncm_setup(struct usbnet *dev)
 	u8 iface_no;
 	int err;
 	int eth_hlen;
+	u16 mbim_mtu;
 	u16 ntb_fmt_supported;
 	__le16 max_datagram_size;
 
@@ -261,6 +262,14 @@ out:
 	/* set MTU to max supported by the device if necessary */
 	if (dev->net->mtu > ctx->max_datagram_size - eth_hlen)
 		dev->net->mtu = ctx->max_datagram_size - eth_hlen;
+
+	/* do not exceed operater preferred MTU */
+	if (ctx->mbim_extended_desc) {
+		mbim_mtu = le16_to_cpu(ctx->mbim_extended_desc->wMTU);
+		if (mbim_mtu != 0 && mbim_mtu < dev->net->mtu)
+			dev->net->mtu = mbim_mtu;
+	}
+
 	return 0;
 }
 
@@ -399,6 +408,14 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 			ctx->mbim_desc = (const struct usb_cdc_mbim_desc *)buf;
 			break;
 
+		case USB_CDC_MBIM_EXTENDED_TYPE:
+			if (buf[0] < sizeof(*(ctx->mbim_extended_desc)))
+				break;
+
+			ctx->mbim_extended_desc =
+				(const struct usb_cdc_mbim_extended_desc *)buf;
+			break;
+
 		default:
 			break;
 		}
diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index c3fa80745996..bdf05fb36729 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -93,6 +93,7 @@ struct cdc_ncm_ctx {
 
 	const struct usb_cdc_ncm_desc *func_desc;
 	const struct usb_cdc_mbim_desc *mbim_desc;
+	const struct usb_cdc_mbim_extended_desc *mbim_extended_desc;
 	const struct usb_cdc_ether_desc *ether_desc;
 
 	struct usb_interface *control;
-- 
cgit v1.2.3


From 84223598778ba08041f4297fda485df83414d57e Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cornelia.huck@de.ibm.com>
Date: Mon, 15 Jul 2013 13:36:01 +0200
Subject: KVM: s390: irq routing for adapter interrupts.

Introduce a new interrupt class for s390 adapter interrupts and enable
irqfds for s390.

This is depending on a new s390 specific vm capability, KVM_CAP_S390_IRQCHIP,
that needs to be enabled by userspace.

Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
---
 Documentation/virtual/kvm/api.txt |  21 +++++--
 arch/s390/include/asm/kvm_host.h  |   9 +++
 arch/s390/kvm/Kconfig             |   2 +
 arch/s390/kvm/Makefile            |   2 +-
 arch/s390/kvm/interrupt.c         | 121 ++++++++++++++++++++++++++++++++++++++
 arch/s390/kvm/irq.h               |  22 +++++++
 arch/s390/kvm/kvm-s390.c          |  17 ++++++
 include/linux/kvm_host.h          |   9 +++
 include/uapi/linux/kvm.h          |  11 ++++
 9 files changed, 209 insertions(+), 5 deletions(-)
 create mode 100644 arch/s390/kvm/irq.h

(limited to 'include/linux')

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index faf6fe9772c7..2cb1640a90ad 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -586,8 +586,8 @@ struct kvm_fpu {
 
 4.24 KVM_CREATE_IRQCHIP
 
-Capability: KVM_CAP_IRQCHIP
-Architectures: x86, ia64, ARM, arm64
+Capability: KVM_CAP_IRQCHIP, KVM_CAP_S390_IRQCHIP (s390)
+Architectures: x86, ia64, ARM, arm64, s390
 Type: vm ioctl
 Parameters: none
 Returns: 0 on success, -1 on error
@@ -596,7 +596,10 @@ Creates an interrupt controller model in the kernel.  On x86, creates a virtual
 ioapic, a virtual PIC (two PICs, nested), and sets up future vcpus to have a
 local APIC.  IRQ routing for GSIs 0-15 is set to both PIC and IOAPIC; GSI 16-23
 only go to the IOAPIC.  On ia64, a IOSAPIC is created. On ARM/arm64, a GIC is
-created.
+created. On s390, a dummy irq routing table is created.
+
+Note that on s390 the KVM_CAP_S390_IRQCHIP vm capability needs to be enabled
+before KVM_CREATE_IRQCHIP can be used.
 
 
 4.25 KVM_IRQ_LINE
@@ -1336,7 +1339,7 @@ KVM_ASSIGN_DEV_IRQ. Partial deassignment of host or guest IRQ is allowed.
 4.52 KVM_SET_GSI_ROUTING
 
 Capability: KVM_CAP_IRQ_ROUTING
-Architectures: x86 ia64
+Architectures: x86 ia64 s390
 Type: vm ioctl
 Parameters: struct kvm_irq_routing (in)
 Returns: 0 on success, -1 on error
@@ -1359,6 +1362,7 @@ struct kvm_irq_routing_entry {
 	union {
 		struct kvm_irq_routing_irqchip irqchip;
 		struct kvm_irq_routing_msi msi;
+		struct kvm_irq_routing_s390_adapter adapter;
 		__u32 pad[8];
 	} u;
 };
@@ -1366,6 +1370,7 @@ struct kvm_irq_routing_entry {
 /* gsi routing entry types */
 #define KVM_IRQ_ROUTING_IRQCHIP 1
 #define KVM_IRQ_ROUTING_MSI 2
+#define KVM_IRQ_ROUTING_S390_ADAPTER 3
 
 No flags are specified so far, the corresponding field must be set to zero.
 
@@ -1381,6 +1386,14 @@ struct kvm_irq_routing_msi {
 	__u32 pad;
 };
 
+struct kvm_irq_routing_s390_adapter {
+	__u64 ind_addr;
+	__u64 summary_addr;
+	__u64 ind_offset;
+	__u32 summary_offset;
+	__u32 adapter_id;
+};
+
 
 4.53 KVM_ASSIGN_SET_MSIX_NR
 
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 0d5235262707..dd3933754d23 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -24,6 +24,14 @@
 #define KVM_MAX_VCPUS 64
 #define KVM_USER_MEM_SLOTS 32
 
+/*
+ * These seem to be used for allocating ->chip in the routing table,
+ * which we don't use. 4096 is an out-of-thin-air value. If we need
+ * to look at ->chip later on, we'll need to revisit this.
+ */
+#define KVM_NR_IRQCHIPS 1
+#define KVM_IRQCHIP_NUM_PINS 4096
+
 struct sca_entry {
 	atomic_t scn;
 	__u32	reserved;
@@ -274,6 +282,7 @@ struct kvm_arch{
 	struct kvm_device *flic;
 	struct gmap *gmap;
 	int css_support;
+	int use_irqchip;
 	struct s390_io_adapter *adapters[MAX_S390_IO_ADAPTERS];
 };
 
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index c8bacbcd2e5b..10d529ac9821 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -25,6 +25,8 @@ config KVM
 	select HAVE_KVM_EVENTFD
 	select KVM_ASYNC_PF
 	select KVM_ASYNC_PF_SYNC
+	select HAVE_KVM_IRQCHIP
+	select HAVE_KVM_IRQ_ROUTING
 	---help---
 	  Support hosting paravirtualized guest machines using the SIE
 	  virtualization capability on the mainframe. This should work
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
index a47d2c355f68..d3adb37e93a4 100644
--- a/arch/s390/kvm/Makefile
+++ b/arch/s390/kvm/Makefile
@@ -7,7 +7,7 @@
 # as published by the Free Software Foundation.
 
 KVM := ../../../virt/kvm
-common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o  $(KVM)/async_pf.o
+common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o  $(KVM)/async_pf.o $(KVM)/irqchip.o
 
 ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
 
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 7ecef5a18e25..2e2814eceb85 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -13,6 +13,7 @@
 #include <linux/interrupt.h>
 #include <linux/kvm_host.h>
 #include <linux/hrtimer.h>
+#include <linux/mmu_context.h>
 #include <linux/signal.h>
 #include <linux/slab.h>
 #include <asm/asm-offsets.h>
@@ -1284,3 +1285,123 @@ struct kvm_device_ops kvm_flic_ops = {
 	.create = flic_create,
 	.destroy = flic_destroy,
 };
+
+static unsigned long get_ind_bit(__u64 addr, unsigned long bit_nr, bool swap)
+{
+	unsigned long bit;
+
+	bit = bit_nr + (addr % PAGE_SIZE) * 8;
+
+	return swap ? (bit ^ (BITS_PER_LONG - 1)) : bit;
+}
+
+static struct s390_map_info *get_map_info(struct s390_io_adapter *adapter,
+					  u64 addr)
+{
+	struct s390_map_info *map;
+
+	if (!adapter)
+		return NULL;
+
+	list_for_each_entry(map, &adapter->maps, list) {
+		if (map->guest_addr == addr)
+			return map;
+	}
+	return NULL;
+}
+
+static int adapter_indicators_set(struct kvm *kvm,
+				  struct s390_io_adapter *adapter,
+				  struct kvm_s390_adapter_int *adapter_int)
+{
+	unsigned long bit;
+	int summary_set, idx;
+	struct s390_map_info *info;
+	void *map;
+
+	info = get_map_info(adapter, adapter_int->ind_addr);
+	if (!info)
+		return -1;
+	map = page_address(info->page);
+	bit = get_ind_bit(info->addr, adapter_int->ind_offset, adapter->swap);
+	set_bit(bit, map);
+	idx = srcu_read_lock(&kvm->srcu);
+	mark_page_dirty(kvm, info->guest_addr >> PAGE_SHIFT);
+	set_page_dirty_lock(info->page);
+	info = get_map_info(adapter, adapter_int->summary_addr);
+	if (!info) {
+		srcu_read_unlock(&kvm->srcu, idx);
+		return -1;
+	}
+	map = page_address(info->page);
+	bit = get_ind_bit(info->addr, adapter_int->summary_offset,
+			  adapter->swap);
+	summary_set = test_and_set_bit(bit, map);
+	mark_page_dirty(kvm, info->guest_addr >> PAGE_SHIFT);
+	set_page_dirty_lock(info->page);
+	srcu_read_unlock(&kvm->srcu, idx);
+	return summary_set ? 0 : 1;
+}
+
+/*
+ * < 0 - not injected due to error
+ * = 0 - coalesced, summary indicator already active
+ * > 0 - injected interrupt
+ */
+static int set_adapter_int(struct kvm_kernel_irq_routing_entry *e,
+			   struct kvm *kvm, int irq_source_id, int level,
+			   bool line_status)
+{
+	int ret;
+	struct s390_io_adapter *adapter;
+
+	/* We're only interested in the 0->1 transition. */
+	if (!level)
+		return 0;
+	adapter = get_io_adapter(kvm, e->adapter.adapter_id);
+	if (!adapter)
+		return -1;
+	down_read(&adapter->maps_lock);
+	ret = adapter_indicators_set(kvm, adapter, &e->adapter);
+	up_read(&adapter->maps_lock);
+	if ((ret > 0) && !adapter->masked) {
+		struct kvm_s390_interrupt s390int = {
+			.type = KVM_S390_INT_IO(1, 0, 0, 0),
+			.parm = 0,
+			.parm64 = (adapter->isc << 27) | 0x80000000,
+		};
+		ret = kvm_s390_inject_vm(kvm, &s390int);
+		if (ret == 0)
+			ret = 1;
+	}
+	return ret;
+}
+
+int kvm_set_routing_entry(struct kvm_irq_routing_table *rt,
+			  struct kvm_kernel_irq_routing_entry *e,
+			  const struct kvm_irq_routing_entry *ue)
+{
+	int ret;
+
+	switch (ue->type) {
+	case KVM_IRQ_ROUTING_S390_ADAPTER:
+		e->set = set_adapter_int;
+		e->adapter.summary_addr = ue->u.adapter.summary_addr;
+		e->adapter.ind_addr = ue->u.adapter.ind_addr;
+		e->adapter.summary_offset = ue->u.adapter.summary_offset;
+		e->adapter.ind_offset = ue->u.adapter.ind_offset;
+		e->adapter.adapter_id = ue->u.adapter.adapter_id;
+		ret = 0;
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm,
+		int irq_source_id, int level, bool line_status)
+{
+	return -EINVAL;
+}
diff --git a/arch/s390/kvm/irq.h b/arch/s390/kvm/irq.h
new file mode 100644
index 000000000000..d98e4159643d
--- /dev/null
+++ b/arch/s390/kvm/irq.h
@@ -0,0 +1,22 @@
+/*
+ * s390 irqchip routines
+ *
+ * Copyright IBM Corp. 2014
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
+ */
+#ifndef __KVM_IRQ_H
+#define __KVM_IRQ_H
+
+#include <linux/kvm_host.h>
+
+static inline int irqchip_in_kernel(struct kvm *kvm)
+{
+	return 1;
+}
+
+#endif
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 2e6fbb0b4f68..ce5b659ec531 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -196,6 +196,10 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		return -EINVAL;
 
 	switch (cap->cap) {
+	case KVM_CAP_S390_IRQCHIP:
+		kvm->arch.use_irqchip = 1;
+		r = 0;
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -228,6 +232,18 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = kvm_vm_ioctl_enable_cap(kvm, &cap);
 		break;
 	}
+	case KVM_CREATE_IRQCHIP: {
+		struct kvm_irq_routing_entry routing;
+
+		r = -EINVAL;
+		if (kvm->arch.use_irqchip) {
+			/* Set up dummy routing. */
+			memset(&routing, 0, sizeof(routing));
+			kvm_set_irq_routing(kvm, &routing, 0, 0);
+			r = 0;
+		}
+		break;
+	}
 	default:
 		r = -ENOTTY;
 	}
@@ -284,6 +300,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	}
 
 	kvm->arch.css_support = 0;
+	kvm->arch.use_irqchip = 0;
 
 	return 0;
 out_nogmap:
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 9816b68b085f..da7510b4c6ad 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -297,6 +297,14 @@ static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memsl
 	return ALIGN(memslot->npages, BITS_PER_LONG) / 8;
 }
 
+struct kvm_s390_adapter_int {
+	u64 ind_addr;
+	u64 summary_addr;
+	u64 ind_offset;
+	u32 summary_offset;
+	u32 adapter_id;
+};
+
 struct kvm_kernel_irq_routing_entry {
 	u32 gsi;
 	u32 type;
@@ -309,6 +317,7 @@ struct kvm_kernel_irq_routing_entry {
 			unsigned pin;
 		} irqchip;
 		struct msi_msg msi;
+		struct kvm_s390_adapter_int adapter;
 	};
 	struct hlist_node link;
 };
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 46ea1b470c76..a8f4ee5d2e82 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -742,6 +742,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_HYPERV_TIME 96
 #define KVM_CAP_IOAPIC_POLARITY_IGNORED 97
 #define KVM_CAP_ENABLE_CAP_VM 98
+#define KVM_CAP_S390_IRQCHIP 99
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -757,9 +758,18 @@ struct kvm_irq_routing_msi {
 	__u32 pad;
 };
 
+struct kvm_irq_routing_s390_adapter {
+	__u64 ind_addr;
+	__u64 summary_addr;
+	__u64 ind_offset;
+	__u32 summary_offset;
+	__u32 adapter_id;
+};
+
 /* gsi routing entry types */
 #define KVM_IRQ_ROUTING_IRQCHIP 1
 #define KVM_IRQ_ROUTING_MSI 2
+#define KVM_IRQ_ROUTING_S390_ADAPTER 3
 
 struct kvm_irq_routing_entry {
 	__u32 gsi;
@@ -769,6 +779,7 @@ struct kvm_irq_routing_entry {
 	union {
 		struct kvm_irq_routing_irqchip irqchip;
 		struct kvm_irq_routing_msi msi;
+		struct kvm_irq_routing_s390_adapter adapter;
 		__u32 pad[8];
 	} u;
 };
-- 
cgit v1.2.3


From f3f710bc64e121c10c67ce58c893d3bc8c72abe4 Mon Sep 17 00:00:00 2001
From: Cornelia Huck <cornelia.huck@de.ibm.com>
Date: Tue, 25 Feb 2014 12:48:01 +0100
Subject: KVM: Bump KVM_MAX_IRQ_ROUTES for s390

The maximum number for irq routes is currently 1024, which is a bit on
the small size for s390: We support up to 4 x 64k virtual devices with
up to 64 queues, and we need one route for each of the queues if we want
to operate it via irqfd.

Let's bump this to 4k on s390 for now, as this at least covers the saner
setups.

We need to find a more general solution, though, as we can't just grow
the routing table indefinitly.

Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
---
 include/linux/kvm_host.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index da7510b4c6ad..7d21cf9f4380 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -922,7 +922,11 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq)
 
 #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
 
+#ifdef CONFIG_S390
+#define KVM_MAX_IRQ_ROUTES 4096 //FIXME: we can have more than that...
+#else
 #define KVM_MAX_IRQ_ROUTES 1024
+#endif
 
 int kvm_setup_default_irq_routing(struct kvm *kvm);
 int kvm_set_irq_routing(struct kvm *kvm,
-- 
cgit v1.2.3


From eeabc850b79336575da7be3dbe186a2da4de8293 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@infradead.org>
Date: Fri, 21 Mar 2014 08:57:37 -0600
Subject: blk-mq: merge blk_mq_insert_request and blk_mq_run_request

It's almost identical to blk_mq_insert_request, so fold the two into one
slightly more generic function by making the flush special case a bit
smarted.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-exec.c       |  2 +-
 block/blk-flush.c      |  4 ++--
 block/blk-mq.c         | 53 ++++++++++----------------------------------------
 block/blk-mq.h         |  1 -
 include/linux/blk-mq.h |  3 +--
 5 files changed, 14 insertions(+), 49 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-exec.c b/block/blk-exec.c
index c68613bb4c79..dbf4502b1d67 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -65,7 +65,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	 * be resued after dying flag is set
 	 */
 	if (q->mq_ops) {
-		blk_mq_insert_request(q, rq, at_head, true);
+		blk_mq_insert_request(rq, at_head, true, false);
 		return;
 	}
 
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 66e2b697f5db..f598f794c3c6 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -137,7 +137,7 @@ static void mq_flush_run(struct work_struct *work)
 	rq = container_of(work, struct request, mq_flush_work);
 
 	memset(&rq->csd, 0, sizeof(rq->csd));
-	blk_mq_run_request(rq, true, false);
+	blk_mq_insert_request(rq, false, true, false);
 }
 
 static bool blk_flush_queue_rq(struct request *rq)
@@ -411,7 +411,7 @@ void blk_insert_flush(struct request *rq)
 	if ((policy & REQ_FSEQ_DATA) &&
 	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
 		if (q->mq_ops) {
-			blk_mq_run_request(rq, false, true);
+			blk_mq_insert_request(rq, false, false, true);
 		} else
 			list_add_tail(&rq->queuelist, &q->queue_head);
 		return;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index a56e77383738..81ff7879bac8 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -724,61 +724,28 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
 	blk_mq_add_timer(rq);
 }
 
-void blk_mq_insert_request(struct request_queue *q, struct request *rq,
-			   bool at_head, bool run_queue)
+void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
+		bool async)
 {
+	struct request_queue *q = rq->q;
 	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx, *current_ctx;
+	struct blk_mq_ctx *ctx = rq->mq_ctx, *current_ctx;
+
+	current_ctx = blk_mq_get_ctx(q);
+	if (!cpu_online(ctx->cpu))
+		rq->mq_ctx = ctx = current_ctx;
 
-	ctx = rq->mq_ctx;
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
-	if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
+	if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA) &&
+	    !(rq->cmd_flags & (REQ_FLUSH_SEQ))) {
 		blk_insert_flush(rq);
 	} else {
-		current_ctx = blk_mq_get_ctx(q);
-
-		if (!cpu_online(ctx->cpu)) {
-			ctx = current_ctx;
-			hctx = q->mq_ops->map_queue(q, ctx->cpu);
-			rq->mq_ctx = ctx;
-		}
 		spin_lock(&ctx->lock);
 		__blk_mq_insert_request(hctx, rq, at_head);
 		spin_unlock(&ctx->lock);
-
-		blk_mq_put_ctx(current_ctx);
 	}
 
-	if (run_queue)
-		__blk_mq_run_hw_queue(hctx);
-}
-EXPORT_SYMBOL(blk_mq_insert_request);
-
-/*
- * This is a special version of blk_mq_insert_request to bypass FLUSH request
- * check. Should only be used internally.
- */
-void blk_mq_run_request(struct request *rq, bool run_queue, bool async)
-{
-	struct request_queue *q = rq->q;
-	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx, *current_ctx;
-
-	current_ctx = blk_mq_get_ctx(q);
-
-	ctx = rq->mq_ctx;
-	if (!cpu_online(ctx->cpu)) {
-		ctx = current_ctx;
-		rq->mq_ctx = ctx;
-	}
-	hctx = q->mq_ops->map_queue(q, ctx->cpu);
-
-	/* ctx->cpu might be offline */
-	spin_lock(&ctx->lock);
-	__blk_mq_insert_request(hctx, rq, false);
-	spin_unlock(&ctx->lock);
-
 	blk_mq_put_ctx(current_ctx);
 
 	if (run_queue)
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 361f9343dab1..ebbe6bac9d61 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -23,7 +23,6 @@ struct blk_mq_ctx {
 };
 
 void __blk_mq_complete_request(struct request *rq);
-void blk_mq_run_request(struct request *rq, bool run_queue, bool async);
 void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
 void blk_mq_init_flush(struct request_queue *q);
 void blk_mq_drain_queue(struct request_queue *q);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index bb68b03741be..349c730a579e 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -122,8 +122,7 @@ void blk_mq_free_commands(struct request_queue *, void (*free)(void *data, struc
 
 void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
 
-void blk_mq_insert_request(struct request_queue *, struct request *,
-		bool, bool);
+void blk_mq_insert_request(struct request *, bool, bool, bool);
 void blk_mq_run_queues(struct request_queue *q, bool async);
 void blk_mq_free_request(struct request *rq);
 bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
-- 
cgit v1.2.3


From bc4c426ee2431d1f717004d3bbaacbd819b544fd Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Fri, 21 Mar 2014 08:23:38 -0400
Subject: Revert "tracing: Move event storage for array from macro to
 standalone function"

I originally wrote commit 35bb4399bd0e to shrink the size of the overhead of
tracepoints by several kilobytes. Later, I received a patch from Vaibhav
Nagarnaik that fixed a bug in the same code that this commit touches. Not
only did it fix a bug, it also removed code and shrunk the size of the
overhead of trace events even more than this commit did.

Since this commit is scheduled for 3.15 and Vaibhav's patch is already in
mainline, I need to revert this patch in order to keep it from conflicting
with Vaibhav's patch. Not to mention, Vaibhav's patch makes this patch
obsolete.

Link: http://lkml.kernel.org/r/20140320225637.0226041b@gandalf.local.home

Cc: Vaibhav Nagarnaik <vnagarnaik@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace_event.h |  8 ++++++++
 include/trace/ftrace.h       | 12 ++++++++----
 kernel/trace/trace_events.c  |  6 ++++++
 kernel/trace/trace_export.c  | 12 ++++++++----
 kernel/trace/trace_output.c  | 21 ---------------------
 5 files changed, 30 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 9d3fe0658398..cdc975929d15 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -221,6 +221,10 @@ void *ftrace_event_buffer_reserve(struct ftrace_event_buffer *fbuffer,
 
 void ftrace_event_buffer_commit(struct ftrace_event_buffer *fbuffer);
 
+int ftrace_event_define_field(struct ftrace_event_call *call,
+			      char *type, int len, char *item, int offset,
+			      int field_size, int sign, int filter);
+
 enum {
 	TRACE_EVENT_FL_FILTERED_BIT,
 	TRACE_EVENT_FL_CAP_ANY_BIT,
@@ -519,6 +523,10 @@ enum {
 	FILTER_TRACE_FN,
 };
 
+#define EVENT_STORAGE_SIZE 128
+extern struct mutex event_storage_mutex;
+extern char event_storage[EVENT_STORAGE_SIZE];
+
 extern int trace_event_raw_init(struct ftrace_event_call *call);
 extern int trace_define_field(struct ftrace_event_call *call, const char *type,
 			      const char *name, int offset, int size,
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index e15ae4010d51..d1d91875faa5 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -302,11 +302,15 @@ static struct trace_event_functions ftrace_event_type_funcs_##call = {	\
 #undef __array
 #define __array(type, item, len)					\
 	do {								\
+		mutex_lock(&event_storage_mutex);			\
 		BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);			\
-		ret = ftrace_event_define_field(event_call, #type, len,	\
-				#item, offsetof(typeof(field), item),   \
-				sizeof(field.item),			\
-			 	is_signed_type(type), FILTER_OTHER); \
+		snprintf(event_storage, sizeof(event_storage),		\
+			 "%s[%d]", #type, len);				\
+		ret = trace_define_field(event_call, event_storage, #item, \
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item),			\
+				 is_signed_type(type), FILTER_OTHER);	\
+		mutex_unlock(&event_storage_mutex);			\
 		if (ret)						\
 			return ret;					\
 	} while (0);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index b8f73b333a3c..2f7b8e31e3a4 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -27,6 +27,12 @@
 
 DEFINE_MUTEX(event_mutex);
 
+DEFINE_MUTEX(event_storage_mutex);
+EXPORT_SYMBOL_GPL(event_storage_mutex);
+
+char event_storage[EVENT_STORAGE_SIZE];
+EXPORT_SYMBOL_GPL(event_storage);
+
 LIST_HEAD(ftrace_events);
 static LIST_HEAD(ftrace_common_fields);
 
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 39c746c5ae73..7c3e3e72e2b6 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -96,10 +96,14 @@ static void __always_unused ____ftrace_check_##name(void)		\
 #define __array(type, item, len)					\
 	do {								\
 		BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);			\
-		ret = ftrace_event_define_field(event_call, #type, len,	\
-				#item, offsetof(typeof(field), item),   \
-				sizeof(field.item),			\
-			 	is_signed_type(type), filter_type);	\
+		mutex_lock(&event_storage_mutex);			\
+		snprintf(event_storage, sizeof(event_storage),		\
+			 "%s[%d]", #type, len);				\
+		ret = trace_define_field(event_call, event_storage, #item, \
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item),			\
+				 is_signed_type(type), filter_type);	\
+		mutex_unlock(&event_storage_mutex);			\
 		if (ret)						\
 			return ret;					\
 	} while (0);
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index ee8d74840b88..ca0e79e2abaa 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -20,10 +20,6 @@ static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
 
 static int next_event_type = __TRACE_LAST_TYPE + 1;
 
-#define EVENT_STORAGE_SIZE 128
-static DEFINE_MUTEX(event_storage_mutex);
-static char event_storage[EVENT_STORAGE_SIZE];
-
 int trace_print_seq(struct seq_file *m, struct trace_seq *s)
 {
 	int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
@@ -474,23 +470,6 @@ int ftrace_output_call(struct trace_iterator *iter, char *name, char *fmt, ...)
 }
 EXPORT_SYMBOL_GPL(ftrace_output_call);
 
-int ftrace_event_define_field(struct ftrace_event_call *call,
-			      char *type, int len, char *item, int offset,
-			      int field_size, int sign, int filter)
-{
-	int ret;
-
-	mutex_lock(&event_storage_mutex);
-	snprintf(event_storage, sizeof(event_storage),
-		 "%s[%d]", type, len);
-	ret = trace_define_field(call, event_storage, item, offset,
-				 field_size, sign, filter);
-	mutex_unlock(&event_storage_mutex);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(ftrace_event_define_field);
-
 #ifdef CONFIG_KRETPROBES
 static inline const char *kretprobed(const char *name)
 {
-- 
cgit v1.2.3


From 1ced9a5b07ccf41704ca347778a154944598c665 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 18 Feb 2014 16:33:07 +0100
Subject: ARM: pxa: fix pxa_ssp_* declarations

The functions declared in include/linux/pxa2xx_ssp.h are
defined in plat-pxa/ssp.c, which can also be built for
PLAT_MMP, but may be disabled there. This can lead to
both unresolved symbols at link time and to duplicate
symbols at compile time for random configurations.

Changing the #ifdef in the header file to match the
Kconfig symbol that decides if the file is built solves
both problems.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Eric Miao <eric.y.miao@gmail.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Haojian Zhuang <haojian.zhuang@gmail.com>
Cc: Daniel Mack <zonque@gmail.com>
---
 include/linux/pxa2xx_ssp.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h
index 49444203328a..f2b405116166 100644
--- a/include/linux/pxa2xx_ssp.h
+++ b/include/linux/pxa2xx_ssp.h
@@ -219,7 +219,7 @@ static inline u32 pxa_ssp_read_reg(struct ssp_device *dev, u32 reg)
 	return __raw_readl(dev->mmio_base + reg);
 }
 
-#ifdef CONFIG_ARCH_PXA
+#if IS_ENABLED(CONFIG_PXA_SSP)
 struct ssp_device *pxa_ssp_request(int port, const char *label);
 void pxa_ssp_free(struct ssp_device *);
 struct ssp_device *pxa_ssp_request_of(const struct device_node *of_node,
-- 
cgit v1.2.3


From 0dea6d52638b2693b18cd2ed8938b236e0789ddb Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Date: Fri, 21 Mar 2014 01:19:01 -0400
Subject: tracepoint: Remove unused API functions

After the following commit:

commit b75ef8b44b1cb95f5a26484b0e2fe37a63b12b44
Author: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Date:   Wed Aug 10 15:18:39 2011 -0400

    Tracepoint: Dissociate from module mutex

The following functions became unnecessary:

- tracepoint_probe_register_noupdate,
- tracepoint_probe_unregister_noupdate,
- tracepoint_probe_update_all.

In fact, none of the in-kernel tracers, nor LTTng, nor SystemTAP use
them. Remove those.

Moreover, the functions:

- tracepoint_iter_start,
- tracepoint_iter_next,
- tracepoint_iter_stop,
- tracepoint_iter_reset.

are unused by in-kernel tracers, LTTng and SystemTAP. Remove those too.

Link: http://lkml.kernel.org/r/1395379142-2118-2-git-send-email-mathieu.desnoyers@efficios.com

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/tracepoint.h |  18 ----
 kernel/tracepoint.c        | 222 +--------------------------------------------
 2 files changed, 5 insertions(+), 235 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index accc497f8d72..a3b2837d8dd1 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -48,12 +48,6 @@ extern int tracepoint_probe_register(const char *name, void *probe, void *data);
 extern int
 tracepoint_probe_unregister(const char *name, void *probe, void *data);
 
-extern int tracepoint_probe_register_noupdate(const char *name, void *probe,
-					      void *data);
-extern int tracepoint_probe_unregister_noupdate(const char *name, void *probe,
-						void *data);
-extern void tracepoint_probe_update_all(void);
-
 #ifdef CONFIG_MODULES
 struct tp_module {
 	struct list_head list;
@@ -62,18 +56,6 @@ struct tp_module {
 };
 #endif /* CONFIG_MODULES */
 
-struct tracepoint_iter {
-#ifdef CONFIG_MODULES
-	struct tp_module *module;
-#endif /* CONFIG_MODULES */
-	struct tracepoint * const *tracepoint;
-};
-
-extern void tracepoint_iter_start(struct tracepoint_iter *iter);
-extern void tracepoint_iter_next(struct tracepoint_iter *iter);
-extern void tracepoint_iter_stop(struct tracepoint_iter *iter);
-extern void tracepoint_iter_reset(struct tracepoint_iter *iter);
-
 /*
  * tracepoint_synchronize_unregister must be called between the last tracepoint
  * probe unregistration and the end of module exit to make sure there is no
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index e2a58a22b0f4..65d9f9459a75 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -67,10 +67,7 @@ struct tracepoint_entry {
 };
 
 struct tp_probes {
-	union {
-		struct rcu_head rcu;
-		struct list_head list;
-	} u;
+	struct rcu_head rcu;
 	struct tracepoint_func probes[0];
 };
 
@@ -83,7 +80,7 @@ static inline void *allocate_probes(int count)
 
 static void rcu_free_old_probes(struct rcu_head *head)
 {
-	kfree(container_of(head, struct tp_probes, u.rcu));
+	kfree(container_of(head, struct tp_probes, rcu));
 }
 
 static inline void release_probes(struct tracepoint_func *old)
@@ -91,7 +88,7 @@ static inline void release_probes(struct tracepoint_func *old)
 	if (old) {
 		struct tp_probes *tp_probes = container_of(old,
 			struct tp_probes, probes[0]);
-		call_rcu_sched(&tp_probes->u.rcu, rcu_free_old_probes);
+		call_rcu_sched(&tp_probes->rcu, rcu_free_old_probes);
 	}
 }
 
@@ -459,204 +456,11 @@ int tracepoint_probe_unregister(const char *name, void *probe, void *data)
 }
 EXPORT_SYMBOL_GPL(tracepoint_probe_unregister);
 
-static LIST_HEAD(old_probes);
-static int need_update;
-
-static void tracepoint_add_old_probes(void *old)
-{
-	need_update = 1;
-	if (old) {
-		struct tp_probes *tp_probes = container_of(old,
-			struct tp_probes, probes[0]);
-		list_add(&tp_probes->u.list, &old_probes);
-	}
-}
-
-/**
- * tracepoint_probe_register_noupdate -  register a probe but not connect
- * @name: tracepoint name
- * @probe: probe handler
- * @data: probe private data
- *
- * caller must call tracepoint_probe_update_all()
- */
-int tracepoint_probe_register_noupdate(const char *name, void *probe,
-				       void *data)
-{
-	struct tracepoint_func *old;
-
-	mutex_lock(&tracepoints_mutex);
-	old = tracepoint_add_probe(name, probe, data);
-	if (IS_ERR(old)) {
-		mutex_unlock(&tracepoints_mutex);
-		return PTR_ERR(old);
-	}
-	tracepoint_add_old_probes(old);
-	mutex_unlock(&tracepoints_mutex);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(tracepoint_probe_register_noupdate);
-
-/**
- * tracepoint_probe_unregister_noupdate -  remove a probe but not disconnect
- * @name: tracepoint name
- * @probe: probe function pointer
- * @data: probe private data
- *
- * caller must call tracepoint_probe_update_all()
- */
-int tracepoint_probe_unregister_noupdate(const char *name, void *probe,
-					 void *data)
-{
-	struct tracepoint_func *old;
-
-	mutex_lock(&tracepoints_mutex);
-	old = tracepoint_remove_probe(name, probe, data);
-	if (IS_ERR(old)) {
-		mutex_unlock(&tracepoints_mutex);
-		return PTR_ERR(old);
-	}
-	tracepoint_add_old_probes(old);
-	mutex_unlock(&tracepoints_mutex);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(tracepoint_probe_unregister_noupdate);
-
-/**
- * tracepoint_probe_update_all -  update tracepoints
- */
-void tracepoint_probe_update_all(void)
-{
-	LIST_HEAD(release_probes);
-	struct tp_probes *pos, *next;
-
-	mutex_lock(&tracepoints_mutex);
-	if (!need_update) {
-		mutex_unlock(&tracepoints_mutex);
-		return;
-	}
-	if (!list_empty(&old_probes))
-		list_replace_init(&old_probes, &release_probes);
-	need_update = 0;
-	tracepoint_update_probes();
-	mutex_unlock(&tracepoints_mutex);
-	list_for_each_entry_safe(pos, next, &release_probes, u.list) {
-		list_del(&pos->u.list);
-		call_rcu_sched(&pos->u.rcu, rcu_free_old_probes);
-	}
-}
-EXPORT_SYMBOL_GPL(tracepoint_probe_update_all);
-
-/**
- * tracepoint_get_iter_range - Get a next tracepoint iterator given a range.
- * @tracepoint: current tracepoints (in), next tracepoint (out)
- * @begin: beginning of the range
- * @end: end of the range
- *
- * Returns whether a next tracepoint has been found (1) or not (0).
- * Will return the first tracepoint in the range if the input tracepoint is
- * NULL.
- */
-static int tracepoint_get_iter_range(struct tracepoint * const **tracepoint,
-	struct tracepoint * const *begin, struct tracepoint * const *end)
-{
-	if (!*tracepoint && begin != end) {
-		*tracepoint = begin;
-		return 1;
-	}
-	if (*tracepoint >= begin && *tracepoint < end)
-		return 1;
-	return 0;
-}
-
-#ifdef CONFIG_MODULES
-static void tracepoint_get_iter(struct tracepoint_iter *iter)
-{
-	int found = 0;
-	struct tp_module *iter_mod;
-
-	/* Core kernel tracepoints */
-	if (!iter->module) {
-		found = tracepoint_get_iter_range(&iter->tracepoint,
-				__start___tracepoints_ptrs,
-				__stop___tracepoints_ptrs);
-		if (found)
-			goto end;
-	}
-	/* Tracepoints in modules */
-	mutex_lock(&tracepoints_mutex);
-	list_for_each_entry(iter_mod, &tracepoint_module_list, list) {
-		/*
-		 * Sorted module list
-		 */
-		if (iter_mod < iter->module)
-			continue;
-		else if (iter_mod > iter->module)
-			iter->tracepoint = NULL;
-		found = tracepoint_get_iter_range(&iter->tracepoint,
-			iter_mod->tracepoints_ptrs,
-			iter_mod->tracepoints_ptrs
-				+ iter_mod->num_tracepoints);
-		if (found) {
-			iter->module = iter_mod;
-			break;
-		}
-	}
-	mutex_unlock(&tracepoints_mutex);
-end:
-	if (!found)
-		tracepoint_iter_reset(iter);
-}
-#else /* CONFIG_MODULES */
-static void tracepoint_get_iter(struct tracepoint_iter *iter)
-{
-	int found = 0;
-
-	/* Core kernel tracepoints */
-	found = tracepoint_get_iter_range(&iter->tracepoint,
-			__start___tracepoints_ptrs,
-			__stop___tracepoints_ptrs);
-	if (!found)
-		tracepoint_iter_reset(iter);
-}
-#endif /* CONFIG_MODULES */
-
-void tracepoint_iter_start(struct tracepoint_iter *iter)
-{
-	tracepoint_get_iter(iter);
-}
-EXPORT_SYMBOL_GPL(tracepoint_iter_start);
-
-void tracepoint_iter_next(struct tracepoint_iter *iter)
-{
-	iter->tracepoint++;
-	/*
-	 * iter->tracepoint may be invalid because we blindly incremented it.
-	 * Make sure it is valid by marshalling on the tracepoints, getting the
-	 * tracepoints from following modules if necessary.
-	 */
-	tracepoint_get_iter(iter);
-}
-EXPORT_SYMBOL_GPL(tracepoint_iter_next);
-
-void tracepoint_iter_stop(struct tracepoint_iter *iter)
-{
-}
-EXPORT_SYMBOL_GPL(tracepoint_iter_stop);
-
-void tracepoint_iter_reset(struct tracepoint_iter *iter)
-{
-#ifdef CONFIG_MODULES
-	iter->module = NULL;
-#endif /* CONFIG_MODULES */
-	iter->tracepoint = NULL;
-}
-EXPORT_SYMBOL_GPL(tracepoint_iter_reset);
 
 #ifdef CONFIG_MODULES
 static int tracepoint_module_coming(struct module *mod)
 {
-	struct tp_module *tp_mod, *iter;
+	struct tp_module *tp_mod;
 	int ret = 0;
 
 	if (!mod->num_tracepoints)
@@ -677,23 +481,7 @@ static int tracepoint_module_coming(struct module *mod)
 	}
 	tp_mod->num_tracepoints = mod->num_tracepoints;
 	tp_mod->tracepoints_ptrs = mod->tracepoints_ptrs;
-
-	/*
-	 * tracepoint_module_list is kept sorted by struct module pointer
-	 * address for iteration on tracepoints from a seq_file that can release
-	 * the mutex between calls.
-	 */
-	list_for_each_entry_reverse(iter, &tracepoint_module_list, list) {
-		BUG_ON(iter == tp_mod);	/* Should never be in the list twice */
-		if (iter < tp_mod) {
-			/* We belong to the location right after iter. */
-			list_add(&tp_mod->list, &iter->list);
-			goto module_added;
-		}
-	}
-	/* We belong to the beginning of the list */
-	list_add(&tp_mod->list, &tracepoint_module_list);
-module_added:
+	list_add_tail(&tp_mod->list, &tracepoint_module_list);
 	tracepoint_update_probe_range(mod->tracepoints_ptrs,
 		mod->tracepoints_ptrs + mod->num_tracepoints);
 end:
-- 
cgit v1.2.3


From 6092315dfdec5185881605d15a0e200d6e90eb66 Mon Sep 17 00:00:00 2001
From: Richard Cochran <richardcochran@gmail.com>
Date: Thu, 20 Mar 2014 22:21:52 +0100
Subject: ptp: introduce programmable pins.

This patch adds a pair of new ioctls to the PTP Hardware Clock device
interface. Using the ioctls, user space programs can query each pin to
find out its current function and also reprogram a different function
if desired.

Signed-off-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_chardev.c        | 128 ++++++++++++++++++++++++++++++++++++++-
 drivers/ptp/ptp_clock.c          |  23 +++++++
 drivers/ptp/ptp_private.h        |   5 ++
 include/linux/ptp_clock_kernel.h |  33 ++++++++++
 include/uapi/linux/ptp_clock.h   |  39 +++++++++++-
 5 files changed, 226 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index 34a0c607318e..419056d7887e 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -25,6 +25,96 @@
 
 #include "ptp_private.h"
 
+static int ptp_disable_pinfunc(struct ptp_clock_info *ops,
+			       enum ptp_pin_function func, unsigned int chan)
+{
+	struct ptp_clock_request rq;
+	int err = 0;
+
+	memset(&rq, 0, sizeof(rq));
+
+	switch (func) {
+	case PTP_PF_NONE:
+		break;
+	case PTP_PF_EXTTS:
+		rq.type = PTP_CLK_REQ_EXTTS;
+		rq.extts.index = chan;
+		err = ops->enable(ops, &rq, 0);
+		break;
+	case PTP_PF_PEROUT:
+		rq.type = PTP_CLK_REQ_PEROUT;
+		rq.perout.index = chan;
+		err = ops->enable(ops, &rq, 0);
+		break;
+	case PTP_PF_PHYSYNC:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return err;
+}
+
+int ptp_set_pinfunc(struct ptp_clock *ptp, unsigned int pin,
+		    enum ptp_pin_function func, unsigned int chan)
+{
+	struct ptp_clock_info *info = ptp->info;
+	struct ptp_pin_desc *pin1 = NULL, *pin2 = &info->pin_config[pin];
+	unsigned int i;
+
+	/* Check to see if any other pin previously had this function. */
+	for (i = 0; i < info->n_pins; i++) {
+		if (info->pin_config[i].func == func &&
+		    info->pin_config[i].chan == chan) {
+			pin1 = &info->pin_config[i];
+			break;
+		}
+	}
+	if (pin1 && i == pin)
+		return 0;
+
+	/* Check the desired function and channel. */
+	switch (func) {
+	case PTP_PF_NONE:
+		break;
+	case PTP_PF_EXTTS:
+		if (chan >= info->n_ext_ts)
+			return -EINVAL;
+		break;
+	case PTP_PF_PEROUT:
+		if (chan >= info->n_per_out)
+			return -EINVAL;
+		break;
+	case PTP_PF_PHYSYNC:
+		pr_err("sorry, cannot reassign the calibration pin\n");
+		return -EINVAL;
+	default:
+		return -EINVAL;
+	}
+
+	if (pin2->func == PTP_PF_PHYSYNC) {
+		pr_err("sorry, cannot reprogram the calibration pin\n");
+		return -EINVAL;
+	}
+
+	if (info->verify(info, pin, func, chan)) {
+		pr_err("driver cannot use function %u on pin %u\n", func, chan);
+		return -EOPNOTSUPP;
+	}
+
+	/* Disable whatever function was previously assigned. */
+	if (pin1) {
+		ptp_disable_pinfunc(info, func, chan);
+		pin1->func = PTP_PF_NONE;
+		pin1->chan = 0;
+	}
+	ptp_disable_pinfunc(info, pin2->func, pin2->chan);
+	pin2->func = func;
+	pin2->chan = chan;
+
+	return 0;
+}
+
 int ptp_open(struct posix_clock *pc, fmode_t fmode)
 {
 	return 0;
@@ -35,12 +125,13 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 	struct ptp_clock_caps caps;
 	struct ptp_clock_request req;
 	struct ptp_sys_offset *sysoff = NULL;
+	struct ptp_pin_desc pd;
 	struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
 	struct ptp_clock_info *ops = ptp->info;
 	struct ptp_clock_time *pct;
 	struct timespec ts;
 	int enable, err = 0;
-	unsigned int i;
+	unsigned int i, pin_index;
 
 	switch (cmd) {
 
@@ -51,6 +142,7 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 		caps.n_ext_ts = ptp->info->n_ext_ts;
 		caps.n_per_out = ptp->info->n_per_out;
 		caps.pps = ptp->info->pps;
+		caps.n_pins = ptp->info->n_pins;
 		if (copy_to_user((void __user *)arg, &caps, sizeof(caps)))
 			err = -EFAULT;
 		break;
@@ -126,6 +218,40 @@ long ptp_ioctl(struct posix_clock *pc, unsigned int cmd, unsigned long arg)
 			err = -EFAULT;
 		break;
 
+	case PTP_PIN_GETFUNC:
+		if (copy_from_user(&pd, (void __user *)arg, sizeof(pd))) {
+			err = -EFAULT;
+			break;
+		}
+		pin_index = pd.index;
+		if (pin_index >= ops->n_pins) {
+			err = -EINVAL;
+			break;
+		}
+		if (mutex_lock_interruptible(&ptp->pincfg_mux))
+			return -ERESTARTSYS;
+		pd = ops->pin_config[pin_index];
+		mutex_unlock(&ptp->pincfg_mux);
+		if (!err && copy_to_user((void __user *)arg, &pd, sizeof(pd)))
+			err = -EFAULT;
+		break;
+
+	case PTP_PIN_SETFUNC:
+		if (copy_from_user(&pd, (void __user *)arg, sizeof(pd))) {
+			err = -EFAULT;
+			break;
+		}
+		pin_index = pd.index;
+		if (pin_index >= ops->n_pins) {
+			err = -EINVAL;
+			break;
+		}
+		if (mutex_lock_interruptible(&ptp->pincfg_mux))
+			return -ERESTARTSYS;
+		err = ptp_set_pinfunc(ptp, pin_index, pd.func, pd.chan);
+		mutex_unlock(&ptp->pincfg_mux);
+		break;
+
 	default:
 		err = -ENOTTY;
 		break;
diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index a8319b266643..e25d2bc898e5 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -169,6 +169,7 @@ static void delete_ptp_clock(struct posix_clock *pc)
 	struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
 
 	mutex_destroy(&ptp->tsevq_mux);
+	mutex_destroy(&ptp->pincfg_mux);
 	ida_simple_remove(&ptp_clocks_map, ptp->index);
 	kfree(ptp);
 }
@@ -203,6 +204,7 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
 	ptp->index = index;
 	spin_lock_init(&ptp->tsevq.lock);
 	mutex_init(&ptp->tsevq_mux);
+	mutex_init(&ptp->pincfg_mux);
 	init_waitqueue_head(&ptp->tsev_wq);
 
 	/* Create a new device in our class. */
@@ -249,6 +251,7 @@ no_sysfs:
 	device_destroy(ptp_class, ptp->devid);
 no_device:
 	mutex_destroy(&ptp->tsevq_mux);
+	mutex_destroy(&ptp->pincfg_mux);
 no_slot:
 	kfree(ptp);
 no_memory:
@@ -305,6 +308,26 @@ int ptp_clock_index(struct ptp_clock *ptp)
 }
 EXPORT_SYMBOL(ptp_clock_index);
 
+int ptp_find_pin(struct ptp_clock *ptp,
+		 enum ptp_pin_function func, unsigned int chan)
+{
+	struct ptp_pin_desc *pin = NULL;
+	int i;
+
+	mutex_lock(&ptp->pincfg_mux);
+	for (i = 0; i < ptp->info->n_pins; i++) {
+		if (ptp->info->pin_config[i].func == func &&
+		    ptp->info->pin_config[i].chan == chan) {
+			pin = &ptp->info->pin_config[i];
+			break;
+		}
+	}
+	mutex_unlock(&ptp->pincfg_mux);
+
+	return pin ? i : -1;
+}
+EXPORT_SYMBOL(ptp_find_pin);
+
 /* module operations */
 
 static void __exit ptp_exit(void)
diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h
index df03f2e30ad9..b114a84c63c7 100644
--- a/drivers/ptp/ptp_private.h
+++ b/drivers/ptp/ptp_private.h
@@ -48,6 +48,7 @@ struct ptp_clock {
 	long dialed_frequency; /* remembers the frequency adjustment */
 	struct timestamp_event_queue tsevq; /* simple fifo for time stamps */
 	struct mutex tsevq_mux; /* one process at a time reading the fifo */
+	struct mutex pincfg_mux; /* protect concurrent info->pin_config access */
 	wait_queue_head_t tsev_wq;
 	int defunct; /* tells readers to go away when clock is being removed */
 };
@@ -69,6 +70,10 @@ static inline int queue_cnt(struct timestamp_event_queue *q)
  * see ptp_chardev.c
  */
 
+/* caller must hold pincfg_mux */
+int ptp_set_pinfunc(struct ptp_clock *ptp, unsigned int pin,
+		    enum ptp_pin_function func, unsigned int chan);
+
 long ptp_ioctl(struct posix_clock *pc,
 	       unsigned int cmd, unsigned long arg);
 
diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h
index 38a993508327..0d8ff3fb84ba 100644
--- a/include/linux/ptp_clock_kernel.h
+++ b/include/linux/ptp_clock_kernel.h
@@ -49,7 +49,11 @@ struct ptp_clock_request {
  * @n_alarm:   The number of programmable alarms.
  * @n_ext_ts:  The number of external time stamp channels.
  * @n_per_out: The number of programmable periodic signals.
+ * @n_pins:    The number of programmable pins.
  * @pps:       Indicates whether the clock supports a PPS callback.
+ * @pin_config: Array of length 'n_pins'. If the number of
+ *              programmable pins is nonzero, then drivers must
+ *              allocate and initialize this array.
  *
  * clock operations
  *
@@ -70,6 +74,18 @@ struct ptp_clock_request {
  *            parameter request: Desired resource to enable or disable.
  *            parameter on: Caller passes one to enable or zero to disable.
  *
+ * @verify:   Confirm that a pin can perform a given function. The PTP
+ *            Hardware Clock subsystem maintains the 'pin_config'
+ *            array on behalf of the drivers, but the PHC subsystem
+ *            assumes that every pin can perform every function. This
+ *            hook gives drivers a way of telling the core about
+ *            limitations on specific pins. This function must return
+ *            zero if the function can be assigned to this pin, and
+ *            nonzero otherwise.
+ *            parameter pin: index of the pin in question.
+ *            parameter func: the desired function to use.
+ *            parameter chan: the function channel index to use.
+ *
  * Drivers should embed their ptp_clock_info within a private
  * structure, obtaining a reference to it using container_of().
  *
@@ -83,13 +99,17 @@ struct ptp_clock_info {
 	int n_alarm;
 	int n_ext_ts;
 	int n_per_out;
+	int n_pins;
 	int pps;
+	struct ptp_pin_desc *pin_config;
 	int (*adjfreq)(struct ptp_clock_info *ptp, s32 delta);
 	int (*adjtime)(struct ptp_clock_info *ptp, s64 delta);
 	int (*gettime)(struct ptp_clock_info *ptp, struct timespec *ts);
 	int (*settime)(struct ptp_clock_info *ptp, const struct timespec *ts);
 	int (*enable)(struct ptp_clock_info *ptp,
 		      struct ptp_clock_request *request, int on);
+	int (*verify)(struct ptp_clock_info *ptp, unsigned int pin,
+		      enum ptp_pin_function func, unsigned int chan);
 };
 
 struct ptp_clock;
@@ -156,4 +176,17 @@ extern void ptp_clock_event(struct ptp_clock *ptp,
 
 extern int ptp_clock_index(struct ptp_clock *ptp);
 
+/**
+ * ptp_find_pin() - obtain the pin index of a given auxiliary function
+ *
+ * @ptp:    The clock obtained from ptp_clock_register().
+ * @func:   One of the ptp_pin_function enumerated values.
+ * @chan:   The particular functional channel to find.
+ * Return:  Pin index in the range of zero to ptp_clock_caps.n_pins - 1,
+ *          or -1 if the auxiliary function cannot be found.
+ */
+
+int ptp_find_pin(struct ptp_clock *ptp,
+		 enum ptp_pin_function func, unsigned int chan);
+
 #endif
diff --git a/include/uapi/linux/ptp_clock.h b/include/uapi/linux/ptp_clock.h
index b65c834f83e9..f0b7bfe5da92 100644
--- a/include/uapi/linux/ptp_clock.h
+++ b/include/uapi/linux/ptp_clock.h
@@ -50,7 +50,8 @@ struct ptp_clock_caps {
 	int n_ext_ts;  /* Number of external time stamp channels. */
 	int n_per_out; /* Number of programmable periodic signals. */
 	int pps;       /* Whether the clock supports a PPS callback. */
-	int rsv[15];   /* Reserved for future use. */
+	int n_pins;    /* Number of input/output pins. */
+	int rsv[14];   /* Reserved for future use. */
 };
 
 struct ptp_extts_request {
@@ -80,6 +81,40 @@ struct ptp_sys_offset {
 	struct ptp_clock_time ts[2 * PTP_MAX_SAMPLES + 1];
 };
 
+enum ptp_pin_function {
+	PTP_PF_NONE,
+	PTP_PF_EXTTS,
+	PTP_PF_PEROUT,
+	PTP_PF_PHYSYNC,
+};
+
+struct ptp_pin_desc {
+	/*
+	 * Hardware specific human readable pin name. This field is
+	 * set by the kernel during the PTP_PIN_GETFUNC ioctl and is
+	 * ignored for the PTP_PIN_SETFUNC ioctl.
+	 */
+	char name[64];
+	/*
+	 * Pin index in the range of zero to ptp_clock_caps.n_pins - 1.
+	 */
+	unsigned int index;
+	/*
+	 * Which of the PTP_PF_xxx functions to use on this pin.
+	 */
+	unsigned int func;
+	/*
+	 * The specific channel to use for this function.
+	 * This corresponds to the 'index' field of the
+	 * PTP_EXTTS_REQUEST and PTP_PEROUT_REQUEST ioctls.
+	 */
+	unsigned int chan;
+	/*
+	 * Reserved for future use.
+	 */
+	unsigned int rsv[5];
+};
+
 #define PTP_CLK_MAGIC '='
 
 #define PTP_CLOCK_GETCAPS  _IOR(PTP_CLK_MAGIC, 1, struct ptp_clock_caps)
@@ -87,6 +122,8 @@ struct ptp_sys_offset {
 #define PTP_PEROUT_REQUEST _IOW(PTP_CLK_MAGIC, 3, struct ptp_perout_request)
 #define PTP_ENABLE_PPS     _IOW(PTP_CLK_MAGIC, 4, int)
 #define PTP_SYS_OFFSET     _IOW(PTP_CLK_MAGIC, 5, struct ptp_sys_offset)
+#define PTP_PIN_GETFUNC    _IOWR(PTP_CLK_MAGIC, 6, struct ptp_pin_desc)
+#define PTP_PIN_SETFUNC    _IOW(PTP_CLK_MAGIC, 7, struct ptp_pin_desc)
 
 struct ptp_extts_event {
 	struct ptp_clock_time t; /* Time event occured. */
-- 
cgit v1.2.3


From 58f86cc89c3372d3e61d5b71e5513ec5a0b02848 Mon Sep 17 00:00:00 2001
From: Rusty Russell <rusty@rustcorp.com.au>
Date: Mon, 24 Mar 2014 12:00:34 +1030
Subject: VERIFY_OCTAL_PERMISSIONS: stricter checking for sysfs perms.

Summary of http://lkml.org/lkml/2014/3/14/363 :

  Ted: module_param(queue_depth, int, 444)
  Joe: 0444!
  Rusty: User perms >= group perms >= other perms?
  Joe: CLASS_ATTR, DEVICE_ATTR, SENSOR_ATTR and SENSOR_ATTR_2?

Side effect of stricter permissions means removing the unnecessary
S_IFREG from several callers.

Note that the BUILD_BUG_ON_ZERO((perm) & 2) test was removed: a fair
number of drivers fail this test, so that will be the debate for a
future patch.

Suggested-by: Joe Perches <joe@perches.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com> for drivers/pci/slot.c
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 drivers/pci/slot.c          | 6 +++---
 fs/fuse/cuse.c              | 4 ++--
 fs/ocfs2/cluster/sys.c      | 2 +-
 fs/ocfs2/stackglue.c        | 8 ++++----
 include/linux/kernel.h      | 8 ++++++++
 include/linux/moduleparam.h | 8 +++-----
 include/linux/sysfs.h       | 3 ++-
 7 files changed, 23 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c
index 7dd62fa9d0bd..396c200b9ddb 100644
--- a/drivers/pci/slot.c
+++ b/drivers/pci/slot.c
@@ -116,11 +116,11 @@ static void pci_slot_release(struct kobject *kobj)
 }
 
 static struct pci_slot_attribute pci_slot_attr_address =
-	__ATTR(address, (S_IFREG | S_IRUGO), address_read_file, NULL);
+	__ATTR(address, S_IRUGO, address_read_file, NULL);
 static struct pci_slot_attribute pci_slot_attr_max_speed =
-	__ATTR(max_bus_speed, (S_IFREG | S_IRUGO), max_speed_read_file, NULL);
+	__ATTR(max_bus_speed, S_IRUGO, max_speed_read_file, NULL);
 static struct pci_slot_attribute pci_slot_attr_cur_speed =
-	__ATTR(cur_bus_speed, (S_IFREG | S_IRUGO), cur_speed_read_file, NULL);
+	__ATTR(cur_bus_speed, S_IRUGO, cur_speed_read_file, NULL);
 
 static struct attribute *pci_slot_default_attrs[] = {
 	&pci_slot_attr_address.attr,
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index b96a49b37d66..77cf5eeeabd1 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -568,7 +568,7 @@ static ssize_t cuse_class_waiting_show(struct device *dev,
 
 	return sprintf(buf, "%d\n", atomic_read(&cc->fc.num_waiting));
 }
-static DEVICE_ATTR(waiting, S_IFREG | 0400, cuse_class_waiting_show, NULL);
+static DEVICE_ATTR(waiting, 0400, cuse_class_waiting_show, NULL);
 
 static ssize_t cuse_class_abort_store(struct device *dev,
 				      struct device_attribute *attr,
@@ -579,7 +579,7 @@ static ssize_t cuse_class_abort_store(struct device *dev,
 	fuse_abort_conn(&cc->fc);
 	return count;
 }
-static DEVICE_ATTR(abort, S_IFREG | 0200, NULL, cuse_class_abort_store);
+static DEVICE_ATTR(abort, 0200, NULL, cuse_class_abort_store);
 
 static struct attribute *cuse_class_dev_attrs[] = {
 	&dev_attr_waiting.attr,
diff --git a/fs/ocfs2/cluster/sys.c b/fs/ocfs2/cluster/sys.c
index a4b07730b2e1..b7f57271d49c 100644
--- a/fs/ocfs2/cluster/sys.c
+++ b/fs/ocfs2/cluster/sys.c
@@ -41,7 +41,7 @@ static ssize_t version_show(struct kobject *kobj, struct kobj_attribute *attr,
 	return snprintf(buf, PAGE_SIZE, "%u\n", O2NM_API_VERSION);
 }
 static struct kobj_attribute attr_version =
-	__ATTR(interface_revision, S_IFREG | S_IRUGO, version_show, NULL);
+	__ATTR(interface_revision, S_IRUGO, version_show, NULL);
 
 static struct attribute *o2cb_attrs[] = {
 	&attr_version.attr,
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 1324e6600e57..25e9f7b5bad3 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -494,7 +494,7 @@ static ssize_t ocfs2_max_locking_protocol_show(struct kobject *kobj,
 }
 
 static struct kobj_attribute ocfs2_attr_max_locking_protocol =
-	__ATTR(max_locking_protocol, S_IFREG | S_IRUGO,
+	__ATTR(max_locking_protocol, S_IRUGO,
 	       ocfs2_max_locking_protocol_show, NULL);
 
 static ssize_t ocfs2_loaded_cluster_plugins_show(struct kobject *kobj,
@@ -526,7 +526,7 @@ static ssize_t ocfs2_loaded_cluster_plugins_show(struct kobject *kobj,
 }
 
 static struct kobj_attribute ocfs2_attr_loaded_cluster_plugins =
-	__ATTR(loaded_cluster_plugins, S_IFREG | S_IRUGO,
+	__ATTR(loaded_cluster_plugins, S_IRUGO,
 	       ocfs2_loaded_cluster_plugins_show, NULL);
 
 static ssize_t ocfs2_active_cluster_plugin_show(struct kobject *kobj,
@@ -548,7 +548,7 @@ static ssize_t ocfs2_active_cluster_plugin_show(struct kobject *kobj,
 }
 
 static struct kobj_attribute ocfs2_attr_active_cluster_plugin =
-	__ATTR(active_cluster_plugin, S_IFREG | S_IRUGO,
+	__ATTR(active_cluster_plugin, S_IRUGO,
 	       ocfs2_active_cluster_plugin_show, NULL);
 
 static ssize_t ocfs2_cluster_stack_show(struct kobject *kobj,
@@ -597,7 +597,7 @@ static ssize_t ocfs2_cluster_stack_store(struct kobject *kobj,
 
 
 static struct kobj_attribute ocfs2_attr_cluster_stack =
-	__ATTR(cluster_stack, S_IFREG | S_IRUGO | S_IWUSR,
+	__ATTR(cluster_stack, S_IRUGO | S_IWUSR,
 	       ocfs2_cluster_stack_show,
 	       ocfs2_cluster_stack_store);
 
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 471090093c67..4679eddc110a 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -842,4 +842,12 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
 # define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD
 #endif
 
+/* Permissions on a sysfs file: you didn't miss the 0 prefix did you? */
+#define VERIFY_OCTAL_PERMISSIONS(perms)					\
+	(BUILD_BUG_ON_ZERO((perms) < 0) +				\
+	 BUILD_BUG_ON_ZERO((perms) > 0777) +				\
+	 /* User perms >= group perms >= other perms */			\
+	 BUILD_BUG_ON_ZERO(((perms) >> 6) < (((perms) >> 3) & 7)) +	\
+	 BUILD_BUG_ON_ZERO((((perms) >> 3) & 7) < ((perms) & 7)) +	\
+	 (perms))
 #endif
diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 175f6995d1af..204a67743804 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -186,14 +186,12 @@ struct kparam_array
    parameters. */
 #define __module_param_call(prefix, name, ops, arg, perm, level)	\
 	/* Default value instead of permissions? */			\
-	static int __param_perm_check_##name __attribute__((unused)) =	\
-	BUILD_BUG_ON_ZERO((perm) < 0 || (perm) > 0777 || ((perm) & 2))	\
-	+ BUILD_BUG_ON_ZERO(sizeof(""prefix) > MAX_PARAM_PREFIX_LEN);	\
-	static const char __param_str_##name[] = prefix #name;		\
+	static const char __param_str_##name[] = prefix #name; \
 	static struct kernel_param __moduleparam_const __param_##name	\
 	__used								\
     __attribute__ ((unused,__section__ ("__param"),aligned(sizeof(void *)))) \
-	= { __param_str_##name, ops, perm, level, { arg } }
+	= { __param_str_##name, ops, VERIFY_OCTAL_PERMISSIONS(perm),	\
+	    level, { arg } }
 
 /* Obsolete - use module_param_cb() */
 #define module_param_call(name, set, get, arg, perm)			\
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index 30b2ebee6439..f517e6e488c8 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -71,7 +71,8 @@ struct attribute_group {
  */
 
 #define __ATTR(_name, _mode, _show, _store) {				\
-	.attr = {.name = __stringify(_name), .mode = _mode },		\
+	.attr = {.name = __stringify(_name),				\
+		 .mode = VERIFY_OCTAL_PERMISSIONS(_mode) },		\
 	.show	= _show,						\
 	.store	= _store,						\
 }
-- 
cgit v1.2.3


From 5a92e700af2e5e0e6404988d6a7f2ed3dad3f46f Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Fri, 21 Feb 2014 14:13:44 -0700
Subject: NVMe: RCU protected access to io queues

This adds rcu protected access to nvme_queue to fix a race between a
surprise removal freeing the queue and a thread with open reference on
a NVMe block device using that queue.

The queues do not need to be rcu protected during the initialization or
shutdown parts, so I've added a helper function for raw deferencing
to get around the sparse errors.

There is still a hole in the IOCTL path for the same problem, which is
fixed in a subsequent patch.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
---
 drivers/block/nvme-core.c | 91 +++++++++++++++++++++++------------------------
 include/linux/nvme.h      |  2 +-
 2 files changed, 46 insertions(+), 47 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index f565212a9e32..b66ab1db4629 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -74,6 +74,7 @@ struct async_cmd_info {
  * commands and one for I/O commands).
  */
 struct nvme_queue {
+	struct rcu_head r_head;
 	struct device *q_dmadev;
 	struct nvme_dev *dev;
 	char irqname[24];	/* nvme4294967295-65535\0 */
@@ -262,14 +263,21 @@ static void *cancel_cmdid(struct nvme_queue *nvmeq, int cmdid,
 	return ctx;
 }
 
-struct nvme_queue *get_nvmeq(struct nvme_dev *dev)
+static struct nvme_queue *raw_nvmeq(struct nvme_dev *dev, int qid)
 {
-	return dev->queues[get_cpu() + 1];
+	return rcu_dereference_raw(dev->queues[qid]);
 }
 
-void put_nvmeq(struct nvme_queue *nvmeq)
+struct nvme_queue *get_nvmeq(struct nvme_dev *dev) __acquires(RCU)
+{
+	rcu_read_lock();
+	return rcu_dereference(dev->queues[get_cpu() + 1]);
+}
+
+void put_nvmeq(struct nvme_queue *nvmeq) __releases(RCU)
 {
 	put_cpu();
+	rcu_read_unlock();
 }
 
 /**
@@ -852,13 +860,14 @@ static int nvme_submit_async_cmd(struct nvme_queue *nvmeq,
 int nvme_submit_admin_cmd(struct nvme_dev *dev, struct nvme_command *cmd,
 								u32 *result)
 {
-	return nvme_submit_sync_cmd(dev->queues[0], cmd, result, ADMIN_TIMEOUT);
+	return nvme_submit_sync_cmd(raw_nvmeq(dev, 0), cmd, result,
+								ADMIN_TIMEOUT);
 }
 
 static int nvme_submit_admin_cmd_async(struct nvme_dev *dev,
 		struct nvme_command *cmd, struct async_cmd_info *cmdinfo)
 {
-	return nvme_submit_async_cmd(dev->queues[0], cmd, cmdinfo,
+	return nvme_submit_async_cmd(raw_nvmeq(dev, 0), cmd, cmdinfo,
 								ADMIN_TIMEOUT);
 }
 
@@ -985,6 +994,7 @@ static void nvme_abort_cmd(int cmdid, struct nvme_queue *nvmeq)
 	struct nvme_command cmd;
 	struct nvme_dev *dev = nvmeq->dev;
 	struct nvme_cmd_info *info = nvme_cmd_info(nvmeq);
+	struct nvme_queue *adminq;
 
 	if (!nvmeq->qid || info[cmdid].aborted) {
 		if (work_busy(&dev->reset_work))
@@ -1001,7 +1011,8 @@ static void nvme_abort_cmd(int cmdid, struct nvme_queue *nvmeq)
 	if (!dev->abort_limit)
 		return;
 
-	a_cmdid = alloc_cmdid(dev->queues[0], CMD_CTX_ABORT, special_completion,
+	adminq = rcu_dereference(dev->queues[0]);
+	a_cmdid = alloc_cmdid(adminq, CMD_CTX_ABORT, special_completion,
 								ADMIN_TIMEOUT);
 	if (a_cmdid < 0)
 		return;
@@ -1018,7 +1029,7 @@ static void nvme_abort_cmd(int cmdid, struct nvme_queue *nvmeq)
 
 	dev_warn(nvmeq->q_dmadev, "Aborting I/O %d QID %d\n", cmdid,
 							nvmeq->qid);
-	nvme_submit_cmd(dev->queues[0], &cmd);
+	nvme_submit_cmd(adminq, &cmd);
 }
 
 /**
@@ -1055,8 +1066,10 @@ static void nvme_cancel_ios(struct nvme_queue *nvmeq, bool timeout)
 	}
 }
 
-static void nvme_free_queue(struct nvme_queue *nvmeq)
+static void nvme_free_queue(struct rcu_head *r)
 {
+	struct nvme_queue *nvmeq = container_of(r, struct nvme_queue, r_head);
+
 	spin_lock_irq(&nvmeq->q_lock);
 	while (bio_list_peek(&nvmeq->sq_cong)) {
 		struct bio *bio = bio_list_pop(&nvmeq->sq_cong);
@@ -1075,10 +1088,13 @@ static void nvme_free_queues(struct nvme_dev *dev, int lowest)
 {
 	int i;
 
+	for (i = num_possible_cpus(); i > dev->queue_count - 1; i--)
+		rcu_assign_pointer(dev->queues[i], NULL);
 	for (i = dev->queue_count - 1; i >= lowest; i--) {
-		nvme_free_queue(dev->queues[i]);
+		struct nvme_queue *nvmeq = raw_nvmeq(dev, i);
+		rcu_assign_pointer(dev->queues[i], NULL);
+		call_rcu(&nvmeq->r_head, nvme_free_queue);
 		dev->queue_count--;
-		dev->queues[i] = NULL;
 	}
 }
 
@@ -1116,7 +1132,7 @@ static void nvme_clear_queue(struct nvme_queue *nvmeq)
 
 static void nvme_disable_queue(struct nvme_dev *dev, int qid)
 {
-	struct nvme_queue *nvmeq = dev->queues[qid];
+	struct nvme_queue *nvmeq = raw_nvmeq(dev, qid);
 
 	if (!nvmeq)
 		return;
@@ -1168,6 +1184,7 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 	nvmeq->qid = qid;
 	nvmeq->q_suspended = 1;
 	dev->queue_count++;
+	rcu_assign_pointer(dev->queues[qid], nvmeq);
 
 	return nvmeq;
 
@@ -1311,12 +1328,11 @@ static int nvme_configure_admin_queue(struct nvme_dev *dev)
 	if (result < 0)
 		return result;
 
-	nvmeq = dev->queues[0];
+	nvmeq = raw_nvmeq(dev, 0);
 	if (!nvmeq) {
 		nvmeq = nvme_alloc_queue(dev, 0, 64, 0);
 		if (!nvmeq)
 			return -ENOMEM;
-		dev->queues[0] = nvmeq;
 	}
 
 	aqa = nvmeq->q_depth - 1;
@@ -1581,8 +1597,8 @@ static int nvme_user_admin_cmd(struct nvme_dev *dev,
 	if (length != cmd.data_len)
 		status = -ENOMEM;
 	else
-		status = nvme_submit_sync_cmd(dev->queues[0], &c, &cmd.result,
-								timeout);
+		status = nvme_submit_sync_cmd(raw_nvmeq(dev, 0), &c,
+							&cmd.result, timeout);
 
 	if (cmd.data_len) {
 		nvme_unmap_user_pages(dev, cmd.opcode & 1, iod);
@@ -1701,8 +1717,10 @@ static int nvme_kthread(void *data)
 				queue_work(nvme_workq, &dev->reset_work);
 				continue;
 			}
+			rcu_read_lock();
 			for (i = 0; i < dev->queue_count; i++) {
-				struct nvme_queue *nvmeq = dev->queues[i];
+				struct nvme_queue *nvmeq =
+						rcu_dereference(dev->queues[i]);
 				if (!nvmeq)
 					continue;
 				spin_lock_irq(&nvmeq->q_lock);
@@ -1714,6 +1732,7 @@ static int nvme_kthread(void *data)
  unlock:
 				spin_unlock_irq(&nvmeq->q_lock);
 			}
+			rcu_read_unlock();
 		}
 		spin_unlock(&dev_list_lock);
 		schedule_timeout(round_jiffies_relative(HZ));
@@ -1808,7 +1827,7 @@ static size_t db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues)
 
 static int nvme_setup_io_queues(struct nvme_dev *dev)
 {
-	struct nvme_queue *adminq = dev->queues[0];
+	struct nvme_queue *adminq = raw_nvmeq(dev, 0);
 	struct pci_dev *pdev = dev->pci_dev;
 	int result, cpu, i, vecs, nr_io_queues, size, q_depth;
 
@@ -1831,7 +1850,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 			size = db_bar_size(dev, nr_io_queues);
 		} while (1);
 		dev->dbs = ((void __iomem *)dev->bar) + 4096;
-		dev->queues[0]->q_db = dev->dbs;
+		adminq->q_db = dev->dbs;
 	}
 
 	/* Deregister the admin queue's interrupt */
@@ -1880,19 +1899,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	}
 
 	/* Free previously allocated queues that are no longer usable */
-	spin_lock(&dev_list_lock);
-	for (i = dev->queue_count - 1; i > nr_io_queues; i--) {
-		struct nvme_queue *nvmeq = dev->queues[i];
-
-		spin_lock_irq(&nvmeq->q_lock);
-		nvme_cancel_ios(nvmeq, false);
-		spin_unlock_irq(&nvmeq->q_lock);
-
-		nvme_free_queue(nvmeq);
-		dev->queue_count--;
-		dev->queues[i] = NULL;
-	}
-	spin_unlock(&dev_list_lock);
+	nvme_free_queues(dev, nr_io_queues);
 
 	cpu = cpumask_first(cpu_online_mask);
 	for (i = 0; i < nr_io_queues; i++) {
@@ -1903,8 +1910,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	q_depth = min_t(int, NVME_CAP_MQES(readq(&dev->bar->cap)) + 1,
 								NVME_Q_DEPTH);
 	for (i = dev->queue_count - 1; i < nr_io_queues; i++) {
-		dev->queues[i + 1] = nvme_alloc_queue(dev, i + 1, q_depth, i);
-		if (!dev->queues[i + 1]) {
+		if (!nvme_alloc_queue(dev, i + 1, q_depth, i)) {
 			result = -ENOMEM;
 			goto free_queues;
 		}
@@ -1912,11 +1918,11 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 
 	for (; i < num_possible_cpus(); i++) {
 		int target = i % rounddown_pow_of_two(dev->queue_count - 1);
-		dev->queues[i + 1] = dev->queues[target + 1];
+		rcu_assign_pointer(dev->queues[i + 1], dev->queues[target + 1]);
 	}
 
 	for (i = 1; i < dev->queue_count; i++) {
-		result = nvme_create_queue(dev->queues[i], i);
+		result = nvme_create_queue(raw_nvmeq(dev, i), i);
 		if (result) {
 			for (--i; i > 0; i--)
 				nvme_disable_queue(dev, i);
@@ -2180,7 +2186,7 @@ static void nvme_disable_io_queues(struct nvme_dev *dev)
 	atomic_set(&dq.refcount, 0);
 	dq.worker = &worker;
 	for (i = dev->queue_count - 1; i > 0; i--) {
-		struct nvme_queue *nvmeq = dev->queues[i];
+		struct nvme_queue *nvmeq = raw_nvmeq(dev, i);
 
 		if (nvme_suspend_queue(nvmeq))
 			continue;
@@ -2205,7 +2211,7 @@ static void nvme_dev_shutdown(struct nvme_dev *dev)
 
 	if (!dev->bar || (dev->bar && readl(&dev->bar->csts) == -1)) {
 		for (i = dev->queue_count - 1; i >= 0; i--) {
-			struct nvme_queue *nvmeq = dev->queues[i];
+			struct nvme_queue *nvmeq = raw_nvmeq(dev, i);
 			nvme_suspend_queue(nvmeq);
 			nvme_clear_queue(nvmeq);
 		}
@@ -2383,18 +2389,10 @@ static int nvme_remove_dead_ctrl(void *arg)
 
 static void nvme_remove_disks(struct work_struct *ws)
 {
-	int i;
 	struct nvme_dev *dev = container_of(ws, struct nvme_dev, reset_work);
 
 	nvme_dev_remove(dev);
-	spin_lock(&dev_list_lock);
-	for (i = dev->queue_count - 1; i > 0; i--) {
-		BUG_ON(!dev->queues[i] || !dev->queues[i]->q_suspended);
-		nvme_free_queue(dev->queues[i]);
-		dev->queue_count--;
-		dev->queues[i] = NULL;
-	}
-	spin_unlock(&dev_list_lock);
+	nvme_free_queues(dev, 1);
 }
 
 static int nvme_dev_resume(struct nvme_dev *dev)
@@ -2526,6 +2524,7 @@ static void nvme_remove(struct pci_dev *pdev)
 	nvme_dev_remove(dev);
 	nvme_dev_shutdown(dev);
 	nvme_free_queues(dev, 0);
+	rcu_barrier();
 	nvme_release_instance(dev);
 	nvme_release_prp_pools(dev);
 	kref_put(&dev->kref, nvme_free_dev);
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 69ae03f6eb15..98d367b06f9c 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -73,7 +73,7 @@ enum {
  */
 struct nvme_dev {
 	struct list_head node;
-	struct nvme_queue **queues;
+	struct nvme_queue __rcu **queues;
 	u32 __iomem *dbs;
 	struct pci_dev *pci_dev;
 	struct dma_pool *prp_page_pool;
-- 
cgit v1.2.3


From 4f5099af4f3d5f999d8ab7784472d93e810e3912 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Mon, 3 Mar 2014 16:39:13 -0700
Subject: NVMe: IOCTL path RCU protect queue access

This adds rcu protected access to a queue in the nvme IOCTL path
to fix potential races between a surprise removal and queue usage in
nvme_submit_sync_cmd. The fix holds the rcu_read_lock() here to prevent
the nvme_queue from freeing while this path is executing so it can't
sleep, and so this path will no longer wait for a available command
id should they all be in use at the time a passthrough IOCTL request
is received.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
---
 drivers/block/nvme-core.c | 82 +++++++++++++++++++++++++++++++----------------
 drivers/block/nvme-scsi.c | 31 +++---------------
 include/linux/nvme.h      |  5 +--
 3 files changed, 60 insertions(+), 58 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index b66ab1db4629..04664cadadfa 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -268,18 +268,30 @@ static struct nvme_queue *raw_nvmeq(struct nvme_dev *dev, int qid)
 	return rcu_dereference_raw(dev->queues[qid]);
 }
 
-struct nvme_queue *get_nvmeq(struct nvme_dev *dev) __acquires(RCU)
+static struct nvme_queue *get_nvmeq(struct nvme_dev *dev) __acquires(RCU)
 {
 	rcu_read_lock();
 	return rcu_dereference(dev->queues[get_cpu() + 1]);
 }
 
-void put_nvmeq(struct nvme_queue *nvmeq) __releases(RCU)
+static void put_nvmeq(struct nvme_queue *nvmeq) __releases(RCU)
 {
 	put_cpu();
 	rcu_read_unlock();
 }
 
+static struct nvme_queue *lock_nvmeq(struct nvme_dev *dev, int q_idx)
+							__acquires(RCU)
+{
+	rcu_read_lock();
+	return rcu_dereference(dev->queues[q_idx]);
+}
+
+static void unlock_nvmeq(struct nvme_queue *nvmeq) __releases(RCU)
+{
+	rcu_read_unlock();
+}
+
 /**
  * nvme_submit_cmd() - Copy a command into a queue and ring the doorbell
  * @nvmeq: The queue to use
@@ -292,6 +304,10 @@ static int nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
 	unsigned long flags;
 	u16 tail;
 	spin_lock_irqsave(&nvmeq->q_lock, flags);
+	if (nvmeq->q_suspended) {
+		spin_unlock_irqrestore(&nvmeq->q_lock, flags);
+		return -EBUSY;
+	}
 	tail = nvmeq->sq_tail;
 	memcpy(&nvmeq->sq_cmds[tail], cmd, sizeof(*cmd));
 	if (++tail == nvmeq->q_depth)
@@ -812,27 +828,46 @@ static void sync_completion(struct nvme_dev *dev, void *ctx,
  * Returns 0 on success.  If the result is negative, it's a Linux error code;
  * if the result is positive, it's an NVM Express status code
  */
-int nvme_submit_sync_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd,
+static int nvme_submit_sync_cmd(struct nvme_dev *dev, int q_idx,
+						struct nvme_command *cmd,
 						u32 *result, unsigned timeout)
 {
-	int cmdid;
+	int cmdid, ret;
 	struct sync_cmd_info cmdinfo;
+	struct nvme_queue *nvmeq;
+
+	nvmeq = lock_nvmeq(dev, q_idx);
+	if (!nvmeq) {
+		unlock_nvmeq(nvmeq);
+		return -ENODEV;
+	}
 
 	cmdinfo.task = current;
 	cmdinfo.status = -EINTR;
 
-	cmdid = alloc_cmdid_killable(nvmeq, &cmdinfo, sync_completion,
-								timeout);
-	if (cmdid < 0)
+	cmdid = alloc_cmdid(nvmeq, &cmdinfo, sync_completion, timeout);
+	if (cmdid < 0) {
+		unlock_nvmeq(nvmeq);
 		return cmdid;
+	}
 	cmd->common.command_id = cmdid;
 
 	set_current_state(TASK_KILLABLE);
-	nvme_submit_cmd(nvmeq, cmd);
+	ret = nvme_submit_cmd(nvmeq, cmd);
+	if (ret) {
+		free_cmdid(nvmeq, cmdid, NULL);
+		unlock_nvmeq(nvmeq);
+		set_current_state(TASK_RUNNING);
+		return ret;
+	}
+	unlock_nvmeq(nvmeq);
 	schedule_timeout(timeout);
 
 	if (cmdinfo.status == -EINTR) {
-		nvme_abort_command(nvmeq, cmdid);
+		nvmeq = lock_nvmeq(dev, q_idx);
+		if (nvmeq)
+			nvme_abort_command(nvmeq, cmdid);
+		unlock_nvmeq(nvmeq);
 		return -EINTR;
 	}
 
@@ -853,15 +888,20 @@ static int nvme_submit_async_cmd(struct nvme_queue *nvmeq,
 		return cmdid;
 	cmdinfo->status = -EINTR;
 	cmd->common.command_id = cmdid;
-	nvme_submit_cmd(nvmeq, cmd);
-	return 0;
+	return nvme_submit_cmd(nvmeq, cmd);
 }
 
 int nvme_submit_admin_cmd(struct nvme_dev *dev, struct nvme_command *cmd,
 								u32 *result)
 {
-	return nvme_submit_sync_cmd(raw_nvmeq(dev, 0), cmd, result,
-								ADMIN_TIMEOUT);
+	return nvme_submit_sync_cmd(dev, 0, cmd, result, ADMIN_TIMEOUT);
+}
+
+int nvme_submit_io_cmd(struct nvme_dev *dev, struct nvme_command *cmd,
+								u32 *result)
+{
+	return nvme_submit_sync_cmd(dev, smp_processor_id() + 1, cmd, result,
+							NVME_IO_TIMEOUT);
 }
 
 static int nvme_submit_admin_cmd_async(struct nvme_dev *dev,
@@ -1434,7 +1474,6 @@ void nvme_unmap_user_pages(struct nvme_dev *dev, int write,
 static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 {
 	struct nvme_dev *dev = ns->dev;
-	struct nvme_queue *nvmeq;
 	struct nvme_user_io io;
 	struct nvme_command c;
 	unsigned length, meta_len;
@@ -1510,20 +1549,10 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 
 	length = nvme_setup_prps(dev, &c.common, iod, length, GFP_KERNEL);
 
-	nvmeq = get_nvmeq(dev);
-	/*
-	 * Since nvme_submit_sync_cmd sleeps, we can't keep preemption
-	 * disabled.  We may be preempted at any point, and be rescheduled
-	 * to a different CPU.  That will cause cacheline bouncing, but no
-	 * additional races since q_lock already protects against other CPUs.
-	 */
-	put_nvmeq(nvmeq);
 	if (length != (io.nblocks + 1) << ns->lba_shift)
 		status = -ENOMEM;
-	else if (!nvmeq || nvmeq->q_suspended)
-		status = -EBUSY;
 	else
-		status = nvme_submit_sync_cmd(nvmeq, &c, NULL, NVME_IO_TIMEOUT);
+		status = nvme_submit_io_cmd(dev, &c, NULL);
 
 	if (meta_len) {
 		if (status == NVME_SC_SUCCESS && !(io.opcode & 1)) {
@@ -1597,8 +1626,7 @@ static int nvme_user_admin_cmd(struct nvme_dev *dev,
 	if (length != cmd.data_len)
 		status = -ENOMEM;
 	else
-		status = nvme_submit_sync_cmd(raw_nvmeq(dev, 0), &c,
-							&cmd.result, timeout);
+		status = nvme_submit_sync_cmd(dev, 0, &c, &cmd.result, timeout);
 
 	if (cmd.data_len) {
 		nvme_unmap_user_pages(dev, cmd.opcode & 1, iod);
diff --git a/drivers/block/nvme-scsi.c b/drivers/block/nvme-scsi.c
index 4a0ceb64e269..e157e85bb5d7 100644
--- a/drivers/block/nvme-scsi.c
+++ b/drivers/block/nvme-scsi.c
@@ -2033,7 +2033,6 @@ static int nvme_trans_do_nvme_io(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	int res = SNTI_TRANSLATION_SUCCESS;
 	int nvme_sc;
 	struct nvme_dev *dev = ns->dev;
-	struct nvme_queue *nvmeq;
 	u32 num_cmds;
 	struct nvme_iod *iod;
 	u64 unit_len;
@@ -2106,18 +2105,7 @@ static int nvme_trans_do_nvme_io(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 
 		nvme_offset += unit_num_blocks;
 
-		nvmeq = get_nvmeq(dev);
-		/*
-		 * Since nvme_submit_sync_cmd sleeps, we can't keep
-		 * preemption disabled.  We may be preempted at any
-		 * point, and be rescheduled to a different CPU.  That
-		 * will cause cacheline bouncing, but no additional
-		 * races since q_lock already protects against other
-		 * CPUs.
-		 */
-		put_nvmeq(nvmeq);
-		nvme_sc = nvme_submit_sync_cmd(nvmeq, &c, NULL,
-						NVME_IO_TIMEOUT);
+		nvme_sc = nvme_submit_io_cmd(dev, &c, NULL);
 		if (nvme_sc != NVME_SC_SUCCESS) {
 			nvme_unmap_user_pages(dev,
 				(is_write) ? DMA_TO_DEVICE : DMA_FROM_DEVICE,
@@ -2644,7 +2632,6 @@ static int nvme_trans_start_stop(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 {
 	int res = SNTI_TRANSLATION_SUCCESS;
 	int nvme_sc;
-	struct nvme_queue *nvmeq;
 	struct nvme_command c;
 	u8 immed, pcmod, pc, no_flush, start;
 
@@ -2671,10 +2658,7 @@ static int nvme_trans_start_stop(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 			c.common.opcode = nvme_cmd_flush;
 			c.common.nsid = cpu_to_le32(ns->ns_id);
 
-			nvmeq = get_nvmeq(ns->dev);
-			put_nvmeq(nvmeq);
-			nvme_sc = nvme_submit_sync_cmd(nvmeq, &c, NULL, NVME_IO_TIMEOUT);
-
+			nvme_sc = nvme_submit_io_cmd(ns->dev, &c, NULL);
 			res = nvme_trans_status_code(hdr, nvme_sc);
 			if (res)
 				goto out;
@@ -2697,15 +2681,12 @@ static int nvme_trans_synchronize_cache(struct nvme_ns *ns,
 	int res = SNTI_TRANSLATION_SUCCESS;
 	int nvme_sc;
 	struct nvme_command c;
-	struct nvme_queue *nvmeq;
 
 	memset(&c, 0, sizeof(c));
 	c.common.opcode = nvme_cmd_flush;
 	c.common.nsid = cpu_to_le32(ns->ns_id);
 
-	nvmeq = get_nvmeq(ns->dev);
-	put_nvmeq(nvmeq);
-	nvme_sc = nvme_submit_sync_cmd(nvmeq, &c, NULL, NVME_IO_TIMEOUT);
+	nvme_sc = nvme_submit_io_cmd(ns->dev, &c, NULL);
 
 	res = nvme_trans_status_code(hdr, nvme_sc);
 	if (res)
@@ -2872,7 +2853,6 @@ static int nvme_trans_unmap(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	struct nvme_dev *dev = ns->dev;
 	struct scsi_unmap_parm_list *plist;
 	struct nvme_dsm_range *range;
-	struct nvme_queue *nvmeq;
 	struct nvme_command c;
 	int i, nvme_sc, res = -ENOMEM;
 	u16 ndesc, list_len;
@@ -2914,10 +2894,7 @@ static int nvme_trans_unmap(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 	c.dsm.nr = cpu_to_le32(ndesc - 1);
 	c.dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
 
-	nvmeq = get_nvmeq(dev);
-	put_nvmeq(nvmeq);
-
-	nvme_sc = nvme_submit_sync_cmd(nvmeq, &c, NULL, NVME_IO_TIMEOUT);
+	nvme_sc = nvme_submit_io_cmd(dev, &c, NULL);
 	res = nvme_trans_status_code(hdr, nvme_sc);
 
 	dma_free_coherent(&dev->pci_dev->dev, ndesc * sizeof(*range),
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 98d367b06f9c..7c3f85bc10f1 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -151,10 +151,7 @@ struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write,
 				unsigned long addr, unsigned length);
 void nvme_unmap_user_pages(struct nvme_dev *dev, int write,
 			struct nvme_iod *iod);
-struct nvme_queue *get_nvmeq(struct nvme_dev *dev);
-void put_nvmeq(struct nvme_queue *nvmeq);
-int nvme_submit_sync_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd,
-						u32 *result, unsigned timeout);
+int nvme_submit_io_cmd(struct nvme_dev *, struct nvme_command *, u32 *);
 int nvme_submit_flush_data(struct nvme_queue *nvmeq, struct nvme_ns *ns);
 int nvme_submit_admin_cmd(struct nvme_dev *, struct nvme_command *,
 							u32 *result);
-- 
cgit v1.2.3


From 832bd858674023b2415c7585db3beba345ef807f Mon Sep 17 00:00:00 2001
From: David Woodhouse <David.Woodhouse@intel.com>
Date: Fri, 7 Mar 2014 15:08:36 +0000
Subject: iommu/vt-d: Change scope lists to struct device, bus, devfn

It's not only for PCI devices any more, and the scope information for an
ACPI device provides the bus and devfn so that has to be stored here too.

It is the device pointer itself which needs to be protected with RCU,
so the __rcu annotation follows it into the definition of struct
dmar_dev_scope, since we're no longer just passing arrays of device
pointers around.

Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
---
 drivers/iommu/dmar.c        | 41 ++++++++++++++++++++++-------------------
 drivers/iommu/intel-iommu.c | 43 +++++++++++++++++++++++++------------------
 include/linux/dmar.h        | 18 ++++++++++++------
 3 files changed, 59 insertions(+), 43 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 4c6297d1b421..c1e2e0c82e69 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -97,17 +97,17 @@ void *dmar_alloc_dev_scope(void *start, void *end, int *cnt)
 	if (*cnt == 0)
 		return NULL;
 
-	return kcalloc(*cnt, sizeof(struct pci_dev *), GFP_KERNEL);
+	return kcalloc(*cnt, sizeof(struct dmar_dev_scope), GFP_KERNEL);
 }
 
-void dmar_free_dev_scope(struct pci_dev __rcu ***devices, int *cnt)
+void dmar_free_dev_scope(struct dmar_dev_scope **devices, int *cnt)
 {
 	int i;
-	struct pci_dev *tmp_dev;
+	struct device *tmp_dev;
 
 	if (*devices && *cnt) {
 		for_each_active_dev_scope(*devices, *cnt, i, tmp_dev)
-			pci_dev_put(tmp_dev);
+			put_device(tmp_dev);
 		kfree(*devices);
 	}
 
@@ -191,10 +191,11 @@ static bool dmar_match_pci_path(struct dmar_pci_notify_info *info, int bus,
 /* Return: > 0 if match found, 0 if no match found, < 0 if error happens */
 int dmar_insert_dev_scope(struct dmar_pci_notify_info *info,
 			  void *start, void*end, u16 segment,
-			  struct pci_dev __rcu **devices, int devices_cnt)
+			  struct dmar_dev_scope *devices,
+			  int devices_cnt)
 {
 	int i, level;
-	struct pci_dev *tmp, *dev = info->dev;
+	struct device *tmp, *dev = &info->dev->dev;
 	struct acpi_dmar_device_scope *scope;
 	struct acpi_dmar_pci_path *path;
 
@@ -213,16 +214,18 @@ int dmar_insert_dev_scope(struct dmar_pci_notify_info *info,
 			continue;
 
 		if ((scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT) ^
-		    (dev->hdr_type == PCI_HEADER_TYPE_NORMAL)) {
+		    (info->dev->hdr_type == PCI_HEADER_TYPE_NORMAL)) {
 			pr_warn("Device scope type does not match for %s\n",
-				pci_name(dev));
+				pci_name(info->dev));
 			return -EINVAL;
 		}
 
 		for_each_dev_scope(devices, devices_cnt, i, tmp)
 			if (tmp == NULL) {
-				rcu_assign_pointer(devices[i],
-						   pci_dev_get(dev));
+				devices[i].bus = info->dev->bus->number;
+				devices[i].devfn = info->dev->devfn;
+				rcu_assign_pointer(devices[i].dev,
+						   get_device(dev));
 				return 1;
 			}
 		BUG_ON(i >= devices_cnt);
@@ -232,19 +235,19 @@ int dmar_insert_dev_scope(struct dmar_pci_notify_info *info,
 }
 
 int dmar_remove_dev_scope(struct dmar_pci_notify_info *info, u16 segment,
-			  struct pci_dev __rcu **devices, int count)
+			  struct dmar_dev_scope *devices, int count)
 {
 	int index;
-	struct pci_dev *tmp;
+	struct device *tmp;
 
 	if (info->seg != segment)
 		return 0;
 
 	for_each_active_dev_scope(devices, count, index, tmp)
-		if (tmp == info->dev) {
-			rcu_assign_pointer(devices[index], NULL);
+		if (tmp == &info->dev->dev) {
+			rcu_assign_pointer(devices[index].dev, NULL);
 			synchronize_rcu();
-			pci_dev_put(tmp);
+			put_device(tmp);
 			return 1;
 		}
 
@@ -562,15 +565,15 @@ parse_dmar_table(void)
 	return ret;
 }
 
-static int dmar_pci_device_match(struct pci_dev __rcu *devices[], int cnt,
-			  struct pci_dev *dev)
+static int dmar_pci_device_match(struct dmar_dev_scope devices[],
+				 int cnt, struct pci_dev *dev)
 {
 	int index;
-	struct pci_dev *tmp;
+	struct device *tmp;
 
 	while (dev) {
 		for_each_active_dev_scope(devices, cnt, index, tmp)
-			if (dev == tmp)
+			if (dev_is_pci(tmp) && dev == to_pci_dev(tmp))
 				return 1;
 
 		/* Check our parent */
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 1599cb1e041c..ace088eebb45 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -382,14 +382,14 @@ struct dmar_rmrr_unit {
 	struct acpi_dmar_header *hdr;	/* ACPI header		*/
 	u64	base_address;		/* reserved base address*/
 	u64	end_address;		/* reserved end address */
-	struct pci_dev __rcu **devices;	/* target devices */
+	struct dmar_dev_scope *devices;	/* target devices */
 	int	devices_cnt;		/* target device count */
 };
 
 struct dmar_atsr_unit {
 	struct list_head list;		/* list of ATSR units */
 	struct acpi_dmar_header *hdr;	/* ACPI header */
-	struct pci_dev __rcu **devices;	/* target devices */
+	struct dmar_dev_scope *devices;	/* target devices */
 	int devices_cnt;		/* target device count */
 	u8 include_all:1;		/* include all ports */
 };
@@ -669,7 +669,8 @@ static struct intel_iommu *device_to_iommu(int segment, u8 bus, u8 devfn)
 {
 	struct dmar_drhd_unit *drhd = NULL;
 	struct intel_iommu *iommu;
-	struct pci_dev *dev;
+	struct device *dev;
+	struct pci_dev *pdev;
 	int i;
 
 	rcu_read_lock();
@@ -679,11 +680,14 @@ static struct intel_iommu *device_to_iommu(int segment, u8 bus, u8 devfn)
 
 		for_each_active_dev_scope(drhd->devices,
 					  drhd->devices_cnt, i, dev) {
-			if (dev->bus->number == bus && dev->devfn == devfn)
+			if (!dev_is_pci(dev))
+				continue;
+			pdev = to_pci_dev(dev);
+			if (pdev->bus->number == bus && pdev->devfn == devfn)
 				goto out;
-			if (dev->subordinate &&
-			    dev->subordinate->number <= bus &&
-			    dev->subordinate->busn_res.end >= bus)
+			if (pdev->subordinate &&
+			    pdev->subordinate->number <= bus &&
+			    pdev->subordinate->busn_res.end >= bus)
 				goto out;
 		}
 
@@ -2479,7 +2483,7 @@ static int domain_add_dev_info(struct dmar_domain *domain,
 static bool device_has_rmrr(struct pci_dev *dev)
 {
 	struct dmar_rmrr_unit *rmrr;
-	struct pci_dev *tmp;
+	struct device *tmp;
 	int i;
 
 	rcu_read_lock();
@@ -2490,7 +2494,7 @@ static bool device_has_rmrr(struct pci_dev *dev)
 		 */
 		for_each_active_dev_scope(rmrr->devices,
 					  rmrr->devices_cnt, i, tmp)
-			if (tmp == dev) {
+			if (tmp == &dev->dev) {
 				rcu_read_unlock();
 				return true;
 			}
@@ -2602,7 +2606,7 @@ static int __init init_dmars(void)
 {
 	struct dmar_drhd_unit *drhd;
 	struct dmar_rmrr_unit *rmrr;
-	struct pci_dev *pdev;
+	struct device *dev;
 	struct intel_iommu *iommu;
 	int i, ret;
 
@@ -2746,8 +2750,10 @@ static int __init init_dmars(void)
 	for_each_rmrr_units(rmrr) {
 		/* some BIOS lists non-exist devices in DMAR table. */
 		for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt,
-					  i, pdev) {
-			ret = iommu_prepare_rmrr_dev(rmrr, pdev);
+					  i, dev) {
+			if (!dev_is_pci(dev))
+				continue;
+			ret = iommu_prepare_rmrr_dev(rmrr, to_pci_dev(dev));
 			if (ret)
 				printk(KERN_ERR
 				       "IOMMU: mapping reserved region failed\n");
@@ -3434,7 +3440,7 @@ DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_SNB, quir
 static void __init init_no_remapping_devices(void)
 {
 	struct dmar_drhd_unit *drhd;
-	struct pci_dev *dev;
+	struct device *dev;
 	int i;
 
 	for_each_drhd_unit(drhd) {
@@ -3442,7 +3448,7 @@ static void __init init_no_remapping_devices(void)
 			for_each_active_dev_scope(drhd->devices,
 						  drhd->devices_cnt, i, dev)
 				break;
-			/* ignore DMAR unit if no pci devices exist */
+			/* ignore DMAR unit if no devices exist */
 			if (i == drhd->devices_cnt)
 				drhd->ignored = 1;
 		}
@@ -3454,7 +3460,7 @@ static void __init init_no_remapping_devices(void)
 
 		for_each_active_dev_scope(drhd->devices,
 					  drhd->devices_cnt, i, dev)
-			if (!IS_GFX_DEVICE(dev))
+			if (!dev_is_pci(dev) || !IS_GFX_DEVICE(to_pci_dev(dev)))
 				break;
 		if (i < drhd->devices_cnt)
 			continue;
@@ -3467,7 +3473,7 @@ static void __init init_no_remapping_devices(void)
 			drhd->ignored = 1;
 			for_each_active_dev_scope(drhd->devices,
 						  drhd->devices_cnt, i, dev)
-				dev->dev.archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO;
+				dev->archdata.iommu = DUMMY_DEVICE_DOMAIN_INFO;
 		}
 	}
 }
@@ -3691,7 +3697,8 @@ int dmar_find_matched_atsr_unit(struct pci_dev *dev)
 {
 	int i, ret = 1;
 	struct pci_bus *bus;
-	struct pci_dev *bridge = NULL, *tmp;
+	struct pci_dev *bridge = NULL;
+	struct device *tmp;
 	struct acpi_dmar_atsr *atsr;
 	struct dmar_atsr_unit *atsru;
 
@@ -3714,7 +3721,7 @@ int dmar_find_matched_atsr_unit(struct pci_dev *dev)
 			continue;
 
 		for_each_dev_scope(atsru->devices, atsru->devices_cnt, i, tmp)
-			if (tmp == bridge)
+			if (tmp == &bridge->dev)
 				goto out;
 
 		if (atsru->include_all)
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 0a92e4d978bc..23c8db129560 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -36,13 +36,19 @@ struct acpi_dmar_header;
 
 struct intel_iommu;
 
+struct dmar_dev_scope {
+	struct device __rcu *dev;
+	u8 bus;
+	u8 devfn;
+};
+
 #ifdef CONFIG_DMAR_TABLE
 extern struct acpi_table_header *dmar_tbl;
 struct dmar_drhd_unit {
 	struct list_head list;		/* list of drhd units	*/
 	struct  acpi_dmar_header *hdr;	/* ACPI header		*/
 	u64	reg_base_addr;		/* register base address*/
-	struct	pci_dev __rcu **devices;/* target device array	*/
+	struct	dmar_dev_scope *devices;/* target device array	*/
 	int	devices_cnt;		/* target device count	*/
 	u16	segment;		/* PCI domain		*/
 	u8	ignored:1; 		/* ignore drhd		*/
@@ -86,7 +92,7 @@ static inline bool dmar_rcu_check(void)
 #define	dmar_rcu_dereference(p)	rcu_dereference_check((p), dmar_rcu_check())
 
 #define	for_each_dev_scope(a, c, p, d)	\
-	for ((p) = 0; ((d) = (p) < (c) ? dmar_rcu_dereference((a)[(p)]) : \
+	for ((p) = 0; ((d) = (p) < (c) ? dmar_rcu_dereference((a)[(p)].dev) : \
 			NULL, (p) < (c)); (p)++)
 
 #define	for_each_active_dev_scope(a, c, p, d)	\
@@ -95,15 +101,15 @@ static inline bool dmar_rcu_check(void)
 extern int dmar_table_init(void);
 extern int dmar_dev_scope_init(void);
 extern int dmar_parse_dev_scope(void *start, void *end, int *cnt,
-				struct pci_dev ***devices, u16 segment);
+				struct dmar_dev_scope **devices, u16 segment);
 extern void *dmar_alloc_dev_scope(void *start, void *end, int *cnt);
-extern void dmar_free_dev_scope(struct pci_dev __rcu ***devices, int *cnt);
+extern void dmar_free_dev_scope(struct dmar_dev_scope **devices, int *cnt);
 extern int dmar_insert_dev_scope(struct dmar_pci_notify_info *info,
 				 void *start, void*end, u16 segment,
-				 struct pci_dev __rcu **devices,
+				 struct dmar_dev_scope *devices,
 				 int devices_cnt);
 extern int dmar_remove_dev_scope(struct dmar_pci_notify_info *info,
-				 u16 segment, struct pci_dev __rcu **devices,
+				 u16 segment, struct dmar_dev_scope *devices,
 				 int count);
 /* Intel IOMMU detection */
 extern int detect_intel_iommu(void);
-- 
cgit v1.2.3


From 67ccac41fafda88492620f4c0a30d4ccb2eb7767 Mon Sep 17 00:00:00 2001
From: David Woodhouse <David.Woodhouse@intel.com>
Date: Sun, 9 Mar 2014 13:49:45 -0700
Subject: iommu/vt-d: Store PCI segment number in struct intel_iommu

Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
---
 drivers/iommu/dmar.c        | 1 +
 include/linux/intel-iommu.h | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 7ea086f61073..56e1c79dc77f 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -952,6 +952,7 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 	}
 	iommu->agaw = agaw;
 	iommu->msagaw = msagaw;
+	iommu->segment = drhd->segment;
 
 	iommu->node = -1;
 
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 2c4bed593b32..0a2da5188217 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -319,6 +319,7 @@ struct intel_iommu {
 	int		agaw; /* agaw of this iommu */
 	int		msagaw; /* max sagaw of this iommu */
 	unsigned int 	irq;
+	u16		segment;     /* PCI segment# */
 	unsigned char 	name[13];    /* Device Name */
 
 #ifdef CONFIG_INTEL_IOMMU
-- 
cgit v1.2.3


From 356750e35e86485c464704c0a32c1d8dc77590d7 Mon Sep 17 00:00:00 2001
From: Eric Paris <eparis@redhat.com>
Date: Mon, 24 Mar 2014 12:13:48 -0400
Subject: audit: define audit_is_compat in kernel internal header

We were exposing a function based on kernel config options to userspace.
This is wrong.  Move it to the audit internal header.

Suggested-by: Chris Metcalf <cmetcalf@tilera.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 include/linux/audit.h      | 6 ++++++
 include/uapi/linux/audit.h | 6 ------
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 4b2983e25ce0..611a59a56f1a 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -102,6 +102,12 @@ struct filename;
 
 extern void audit_log_session_info(struct audit_buffer *ab);
 
+#ifdef CONFIG_COMPAT
+#define audit_is_compat(arch)  (!((arch) & __AUDIT_ARCH_64BIT))
+#else
+#define audit_is_compat(arch)  false
+#endif
+
 #ifdef CONFIG_AUDITSYSCALL
 /* These are defined in auditsc.c */
 				/* Public API */
diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index 9af01d77dc44..4315ee99b967 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -362,12 +362,6 @@ enum {
 #define AUDIT_ARCH_SPARC64	(EM_SPARCV9|__AUDIT_ARCH_64BIT)
 #define AUDIT_ARCH_X86_64	(EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
 
-#ifdef CONFIG_COMPAT
-#define audit_is_compat(arch)	(!((arch) & __AUDIT_ARCH_64BIT))
-#else
-#define audit_is_compat(arch)	false
-#endif
-
 #define AUDIT_PERM_EXEC		1
 #define AUDIT_PERM_WRITE	2
 #define AUDIT_PERM_READ		4
-- 
cgit v1.2.3


From 5f16f3225b06242a9ee876f07c1c9b6ed36a22b6 Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Mon, 24 Mar 2014 14:43:12 -0400
Subject: ext4: atomically set inode->i_flags in ext4_set_inode_flags()

Use cmpxchg() to atomically set i_flags instead of clearing out the
S_IMMUTABLE, S_APPEND, etc. flags and then setting them from the
EXT4_IMMUTABLE_FL, EXT4_APPEND_FL flags, since this opens up a race
where an immutable file has the immutable flag cleared for a brief
window of time.

Reported-by: John Sullivan <jsrhbz@kanargh.force9.co.uk>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Cc: stable@kernel.org
---
 fs/ext4/inode.c    | 14 ++++++++------
 fs/inode.c         | 31 +++++++++++++++++++++++++++++++
 include/linux/fs.h |  3 +++
 3 files changed, 42 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index b5e182acf9b9..df067c3c6c93 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3938,18 +3938,20 @@ int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
 void ext4_set_inode_flags(struct inode *inode)
 {
 	unsigned int flags = EXT4_I(inode)->i_flags;
+	unsigned int new_fl = 0;
 
-	inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
 	if (flags & EXT4_SYNC_FL)
-		inode->i_flags |= S_SYNC;
+		new_fl |= S_SYNC;
 	if (flags & EXT4_APPEND_FL)
-		inode->i_flags |= S_APPEND;
+		new_fl |= S_APPEND;
 	if (flags & EXT4_IMMUTABLE_FL)
-		inode->i_flags |= S_IMMUTABLE;
+		new_fl |= S_IMMUTABLE;
 	if (flags & EXT4_NOATIME_FL)
-		inode->i_flags |= S_NOATIME;
+		new_fl |= S_NOATIME;
 	if (flags & EXT4_DIRSYNC_FL)
-		inode->i_flags |= S_DIRSYNC;
+		new_fl |= S_DIRSYNC;
+	inode_set_flags(inode, new_fl,
+			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
 }
 
 /* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
diff --git a/fs/inode.c b/fs/inode.c
index 4bcdad3c9361..26f95ceb6250 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1899,3 +1899,34 @@ void inode_dio_done(struct inode *inode)
 		wake_up_bit(&inode->i_state, __I_DIO_WAKEUP);
 }
 EXPORT_SYMBOL(inode_dio_done);
+
+/*
+ * inode_set_flags - atomically set some inode flags
+ *
+ * Note: the caller should be holding i_mutex, or else be sure that
+ * they have exclusive access to the inode structure (i.e., while the
+ * inode is being instantiated).  The reason for the cmpxchg() loop
+ * --- which wouldn't be necessary if all code paths which modify
+ * i_flags actually followed this rule, is that there is at least one
+ * code path which doesn't today --- for example,
+ * __generic_file_aio_write() calls file_remove_suid() without holding
+ * i_mutex --- so we use cmpxchg() out of an abundance of caution.
+ *
+ * In the long run, i_mutex is overkill, and we should probably look
+ * at using the i_lock spinlock to protect i_flags, and then make sure
+ * it is so documented in include/linux/fs.h and that all code follows
+ * the locking convention!!
+ */
+void inode_set_flags(struct inode *inode, unsigned int flags,
+		     unsigned int mask)
+{
+	unsigned int old_flags, new_flags;
+
+	WARN_ON_ONCE(flags & ~mask);
+	do {
+		old_flags = ACCESS_ONCE(inode->i_flags);
+		new_flags = (old_flags & ~mask) | flags;
+	} while (unlikely(cmpxchg(&inode->i_flags, old_flags,
+				  new_flags) != old_flags));
+}
+EXPORT_SYMBOL(inode_set_flags);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 60829565e552..5d1f6fa8daed 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2556,6 +2556,9 @@ static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
 void inode_dio_wait(struct inode *inode);
 void inode_dio_done(struct inode *inode);
 
+extern void inode_set_flags(struct inode *inode, unsigned int flags,
+			    unsigned int mask);
+
 extern const struct file_operations generic_ro_fops;
 
 #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m))
-- 
cgit v1.2.3


From c646cbf10fb3347ecda290dfce96b813a423ca07 Mon Sep 17 00:00:00 2001
From: Alex Elder <elder@linaro.org>
Date: Fri, 21 Mar 2014 06:43:56 -0500
Subject: clk: support hardware-specific debugfs entries

Add a new clk_ops->debug_init method to allow a clock hardware
driver to populate the clock's debugfs directory with entries
beyond those common for every clock.

Signed-off-by: Alex Elder <elder@linaro.org>
Signed-off-by: Mike Turquette <mturquette@linaro.org>
---
 drivers/clk/clk.c            | 4 ++++
 include/linux/clk-provider.h | 8 ++++++++
 2 files changed, 12 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index fb3c40b4fbe2..1fbcb2b107e7 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -277,6 +277,10 @@ static int clk_debug_create_one(struct clk *clk, struct dentry *pdentry)
 	if (!d)
 		goto err_out;
 
+	if (clk->ops->debug_init)
+		if (clk->ops->debug_init(clk->hw, clk->dentry))
+			goto err_out;
+
 	ret = 0;
 	goto out;
 
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 939533da93a7..511917416fb0 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -32,6 +32,7 @@
 #define CLK_GET_ACCURACY_NOCACHE BIT(8) /* do not use the cached clk accuracy */
 
 struct clk_hw;
+struct dentry;
 
 /**
  * struct clk_ops -  Callback operations for hardware clocks; these are to
@@ -127,6 +128,12 @@ struct clk_hw;
  *		separately via calls to .set_parent and .set_rate.
  *		Returns 0 on success, -EERROR otherwise.
  *
+ * @debug_init:	Set up type-specific debugfs entries for this clock.  This
+ *		is called once, after the debugfs directory entry for this
+ *		clock has been created.  The dentry pointer representing that
+ *		directory is provided as an argument.  Called with
+ *		prepare_lock held.  Returns 0 on success, -EERROR otherwise.
+ *
  *
  * The clk_enable/clk_disable and clk_prepare/clk_unprepare pairs allow
  * implementations to split any work between atomic (enable) and sleepable
@@ -165,6 +172,7 @@ struct clk_ops {
 	unsigned long	(*recalc_accuracy)(struct clk_hw *hw,
 					   unsigned long parent_accuracy);
 	void		(*init)(struct clk_hw *hw);
+	int		(*debug_init)(struct clk_hw *hw, struct dentry *dentry);
 };
 
 /**
-- 
cgit v1.2.3


From fb7c03dfc48eb81bda368561f4ca162749d127c9 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Thu, 20 Mar 2014 19:50:33 -0700
Subject: if_vlan: Call dev_kfree_skb_any instead of kfree_skb.

Replace kfree_skb with dev_kfree_skb_any in vlan_insert_tag as
vlan_insert_tag can be called from hard irq context (netpoll)
and from other contexts.

dev_kfree_skb_any is used as vlan_insert_tag only frees the skb if the
skb can not be modified to insert a tag, in which case vlan_insert_tag
drops the skb.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 include/linux/if_vlan.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index bbedfb56bd66..d3d2306f00bf 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -288,7 +288,7 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb,
 	struct vlan_ethhdr *veth;
 
 	if (skb_cow_head(skb, VLAN_HLEN) < 0) {
-		kfree_skb(skb);
+		dev_kfree_skb_any(skb);
 		return NULL;
 	}
 	veth = (struct vlan_ethhdr *)skb_push(skb, VLAN_HLEN);
-- 
cgit v1.2.3


From 72099304eeb316c4b00df3ae83efe4375729bd78 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 25 Mar 2014 20:54:57 -0700
Subject: Revert "sysfs, driver-core: remove unused
 {sysfs|device}_schedule_callback_owner()"

This reverts commit d1ba277e79889085a2faec3b68b91ce89c63f888.

As reported by Stephen, this patch breaks linux-next as a ppc patch
suddenly (after 2 years) started using this old api call.  So revert it
for now, it will go away in 3.15-rc2 when we can change the PPC call to
the new api.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Tejun Heo <tj@kernel.org>
Cc: Stewart Smith <stewart@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c    | 33 ++++++++++++++++++
 fs/sysfs/file.c        | 92 ++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/device.h | 11 +++++-
 include/linux/sysfs.h  |  9 +++++
 4 files changed, 144 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 20da3ad1696b..0dd65281cc65 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -614,6 +614,39 @@ void device_remove_bin_file(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(device_remove_bin_file);
 
+/**
+ * device_schedule_callback_owner - helper to schedule a callback for a device
+ * @dev: device.
+ * @func: callback function to invoke later.
+ * @owner: module owning the callback routine
+ *
+ * Attribute methods must not unregister themselves or their parent device
+ * (which would amount to the same thing).  Attempts to do so will deadlock,
+ * since unregistration is mutually exclusive with driver callbacks.
+ *
+ * Instead methods can call this routine, which will attempt to allocate
+ * and schedule a workqueue request to call back @func with @dev as its
+ * argument in the workqueue's process context.  @dev will be pinned until
+ * @func returns.
+ *
+ * This routine is usually called via the inline device_schedule_callback(),
+ * which automatically sets @owner to THIS_MODULE.
+ *
+ * Returns 0 if the request was submitted, -ENOMEM if storage could not
+ * be allocated, -ENODEV if a reference to @owner isn't available.
+ *
+ * NOTE: This routine won't work if CONFIG_SYSFS isn't set!  It uses an
+ * underlying sysfs routine (since it is intended for use by attribute
+ * methods), and if sysfs isn't available you'll get nothing but -ENOSYS.
+ */
+int device_schedule_callback_owner(struct device *dev,
+		void (*func)(struct device *), struct module *owner)
+{
+	return sysfs_schedule_callback(&dev->kobj,
+			(void (*)(void *)) func, dev, owner);
+}
+EXPORT_SYMBOL_GPL(device_schedule_callback_owner);
+
 static void klist_children_get(struct klist_node *n)
 {
 	struct device_private *p = to_device_private_parent(n);
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 28cc1acd5439..1b8b91b67fdb 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -453,3 +453,95 @@ void sysfs_remove_bin_file(struct kobject *kobj,
 	kernfs_remove_by_name(kobj->sd, attr->attr.name);
 }
 EXPORT_SYMBOL_GPL(sysfs_remove_bin_file);
+
+struct sysfs_schedule_callback_struct {
+	struct list_head	workq_list;
+	struct kobject		*kobj;
+	void			(*func)(void *);
+	void			*data;
+	struct module		*owner;
+	struct work_struct	work;
+};
+
+static struct workqueue_struct *sysfs_workqueue;
+static DEFINE_MUTEX(sysfs_workq_mutex);
+static LIST_HEAD(sysfs_workq);
+static void sysfs_schedule_callback_work(struct work_struct *work)
+{
+	struct sysfs_schedule_callback_struct *ss = container_of(work,
+			struct sysfs_schedule_callback_struct, work);
+
+	(ss->func)(ss->data);
+	kobject_put(ss->kobj);
+	module_put(ss->owner);
+	mutex_lock(&sysfs_workq_mutex);
+	list_del(&ss->workq_list);
+	mutex_unlock(&sysfs_workq_mutex);
+	kfree(ss);
+}
+
+/**
+ * sysfs_schedule_callback - helper to schedule a callback for a kobject
+ * @kobj: object we're acting for.
+ * @func: callback function to invoke later.
+ * @data: argument to pass to @func.
+ * @owner: module owning the callback code
+ *
+ * sysfs attribute methods must not unregister themselves or their parent
+ * kobject (which would amount to the same thing).  Attempts to do so will
+ * deadlock, since unregistration is mutually exclusive with driver
+ * callbacks.
+ *
+ * Instead methods can call this routine, which will attempt to allocate
+ * and schedule a workqueue request to call back @func with @data as its
+ * argument in the workqueue's process context.  @kobj will be pinned
+ * until @func returns.
+ *
+ * Returns 0 if the request was submitted, -ENOMEM if storage could not
+ * be allocated, -ENODEV if a reference to @owner isn't available,
+ * -EAGAIN if a callback has already been scheduled for @kobj.
+ */
+int sysfs_schedule_callback(struct kobject *kobj, void (*func)(void *),
+		void *data, struct module *owner)
+{
+	struct sysfs_schedule_callback_struct *ss, *tmp;
+
+	if (!try_module_get(owner))
+		return -ENODEV;
+
+	mutex_lock(&sysfs_workq_mutex);
+	list_for_each_entry_safe(ss, tmp, &sysfs_workq, workq_list)
+		if (ss->kobj == kobj) {
+			module_put(owner);
+			mutex_unlock(&sysfs_workq_mutex);
+			return -EAGAIN;
+		}
+	mutex_unlock(&sysfs_workq_mutex);
+
+	if (sysfs_workqueue == NULL) {
+		sysfs_workqueue = create_singlethread_workqueue("sysfsd");
+		if (sysfs_workqueue == NULL) {
+			module_put(owner);
+			return -ENOMEM;
+		}
+	}
+
+	ss = kmalloc(sizeof(*ss), GFP_KERNEL);
+	if (!ss) {
+		module_put(owner);
+		return -ENOMEM;
+	}
+	kobject_get(kobj);
+	ss->kobj = kobj;
+	ss->func = func;
+	ss->data = data;
+	ss->owner = owner;
+	INIT_WORK(&ss->work, sysfs_schedule_callback_work);
+	INIT_LIST_HEAD(&ss->workq_list);
+	mutex_lock(&sysfs_workq_mutex);
+	list_add_tail(&ss->workq_list, &sysfs_workq);
+	mutex_unlock(&sysfs_workq_mutex);
+	queue_work(sysfs_workqueue, &ss->work);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(sysfs_schedule_callback);
diff --git a/include/linux/device.h b/include/linux/device.h
index fb1ba13f7665..1ff3f1697513 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -566,6 +566,12 @@ extern int __must_check device_create_bin_file(struct device *dev,
 					const struct bin_attribute *attr);
 extern void device_remove_bin_file(struct device *dev,
 				   const struct bin_attribute *attr);
+extern int device_schedule_callback_owner(struct device *dev,
+		void (*func)(struct device *dev), struct module *owner);
+
+/* This is a macro to avoid include problems with THIS_MODULE */
+#define device_schedule_callback(dev, func)			\
+	device_schedule_callback_owner(dev, func, THIS_MODULE)
 
 /* device resource management */
 typedef void (*dr_release_t)(struct device *dev, void *res);
@@ -925,7 +931,10 @@ extern int device_online(struct device *dev);
 extern struct device *__root_device_register(const char *name,
 					     struct module *owner);
 
-/* This is a macro to avoid include problems with THIS_MODULE */
+/*
+ * This is a macro to avoid include problems with THIS_MODULE,
+ * just as per what is done for device_schedule_callback() above.
+ */
 #define root_device_register(name) \
 	__root_device_register(name, THIS_MODULE)
 
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index fdaa0c6fc7a2..e0bf210ddffd 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -178,6 +178,9 @@ struct sysfs_ops {
 
 #ifdef CONFIG_SYSFS
 
+int sysfs_schedule_callback(struct kobject *kobj, void (*func)(void *),
+			    void *data, struct module *owner);
+
 int __must_check sysfs_create_dir_ns(struct kobject *kobj, const void *ns);
 void sysfs_remove_dir(struct kobject *kobj);
 int __must_check sysfs_rename_dir_ns(struct kobject *kobj, const char *new_name,
@@ -251,6 +254,12 @@ static inline void sysfs_enable_ns(struct kernfs_node *kn)
 
 #else /* CONFIG_SYSFS */
 
+static inline int sysfs_schedule_callback(struct kobject *kobj,
+		void (*func)(void *), void *data, struct module *owner)
+{
+	return -ENOSYS;
+}
+
 static inline int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
 {
 	return 0;
-- 
cgit v1.2.3


From 3f4eb14bdbe148fcc3a8e02f506ccc9b8c955ad4 Mon Sep 17 00:00:00 2001
From: Pekon Gupta <pekon@ti.com>
Date: Thu, 20 Mar 2014 18:48:34 +0530
Subject: mtd: devices: elm: check for hardware engine's design constraints

ELM hardware engine is used by BCH ecc-schemes for detecting and locating ECC
errors. This patch adds the following checks for ELM hardware engine:

 - ELM internal buffers are of 1K,
   so it cannot process data with ecc-step-size > 1K.

 - ELM engine can execute upto maximum of 8 threads in parallel,
   so in *page-mode* (when complete page is processed in single iteration),
   ELM cannot support ecc-steps > 8.

Signed-off-by: Pekon Gupta <pekon@ti.com>
Reviewed-by: Ezequiel Garcia <ezequiel.garcia@free-electrons.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 drivers/mtd/devices/elm.c         | 13 ++++++++++++-
 drivers/mtd/nand/omap2.c          |  9 ++++++---
 include/linux/platform_data/elm.h |  3 ++-
 3 files changed, 20 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/devices/elm.c b/drivers/mtd/devices/elm.c
index f160d2c6cd59..c51752ad072e 100644
--- a/drivers/mtd/devices/elm.c
+++ b/drivers/mtd/devices/elm.c
@@ -103,7 +103,8 @@ static u32 elm_read_reg(struct elm_info *info, int offset)
  * @dev:	ELM device
  * @bch_type:	Type of BCH ecc
  */
-int elm_config(struct device *dev, enum bch_ecc bch_type)
+int elm_config(struct device *dev, enum bch_ecc bch_type,
+	int ecc_steps, int ecc_step_size, int ecc_syndrome_size)
 {
 	u32 reg_val;
 	struct elm_info *info = dev_get_drvdata(dev);
@@ -112,6 +113,16 @@ int elm_config(struct device *dev, enum bch_ecc bch_type)
 		dev_err(dev, "Unable to configure elm - device not probed?\n");
 		return -ENODEV;
 	}
+	/* ELM cannot detect ECC errors for chunks > 1KB */
+	if (ecc_step_size > ((ELM_ECC_SIZE + 1) / 2)) {
+		dev_err(dev, "unsupported config ecc-size=%d\n", ecc_step_size);
+		return -EINVAL;
+	}
+	/* ELM support 8 error syndrome process */
+	if (ecc_steps > ERROR_VECTOR_MAX) {
+		dev_err(dev, "unsupported config ecc-step=%d\n", ecc_steps);
+		return -EINVAL;
+	}
 
 	reg_val = (bch_type & ECC_BCH_LEVEL_MASK) | (ELM_ECC_SIZE << 16);
 	elm_write_reg(info, ELM_LOCATION_CONFIG, reg_val);
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index ab9c472456d9..6f9b339aed74 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -1540,6 +1540,8 @@ static int is_elm_present(struct omap_nand_info *info,
 			struct device_node *elm_node, enum bch_ecc bch_type)
 {
 	struct platform_device *pdev;
+	struct nand_ecc_ctrl *ecc = &info->nand.ecc;
+	int err;
 	/* check whether elm-id is passed via DT */
 	if (!elm_node) {
 		pr_err("nand: error: ELM DT node not found\n");
@@ -1553,9 +1555,10 @@ static int is_elm_present(struct omap_nand_info *info,
 	}
 	/* ELM module available, now configure it */
 	info->elm_dev = &pdev->dev;
-	if (elm_config(info->elm_dev, bch_type))
-		return -ENODEV;
-	return 0;
+	err = elm_config(info->elm_dev, bch_type,
+		(info->mtd.writesize / ecc->size), ecc->size, ecc->bytes);
+
+	return err;
 }
 #endif /* CONFIG_MTD_NAND_ECC_BCH */
 
diff --git a/include/linux/platform_data/elm.h b/include/linux/platform_data/elm.h
index bf0a83b7ed9d..6e37156b0902 100644
--- a/include/linux/platform_data/elm.h
+++ b/include/linux/platform_data/elm.h
@@ -50,5 +50,6 @@ struct elm_errorvec {
 
 void elm_decode_bch_error_page(struct device *dev, u8 *ecc_calc,
 		struct elm_errorvec *err_vec);
-int elm_config(struct device *dev, enum bch_ecc bch_type);
+int elm_config(struct device *dev, enum bch_ecc bch_type,
+	int ecc_steps, int ecc_step_size, int ecc_syndrome_size);
 #endif /* __ELM_H */
-- 
cgit v1.2.3


From ea0760244d235688b5fae4e5cdd9412c1fb1c2fe Mon Sep 17 00:00:00 2001
From: Pekon Gupta <pekon@ti.com>
Date: Thu, 20 Mar 2014 18:48:35 +0530
Subject: mtd: devices: elm: clean elm_load_syndrome

This patch refactors elm_load_syndrome() to make it scalable for newer
ECC schemes by removing scheme specific macros (like ECC_BYTES*xx),
and instead using ECC control information passed during elm_config.

Signed-off-by: Pekon Gupta <pekon@ti.com>
Reviewed-by: Ezequiel Garcia <ezequiel.garcia@free-electrons.com>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 drivers/mtd/devices/elm.c         | 18 +++++++++++-------
 include/linux/platform_data/elm.h |  7 -------
 2 files changed, 11 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/devices/elm.c b/drivers/mtd/devices/elm.c
index c51752ad072e..4fbfaf65fabd 100644
--- a/drivers/mtd/devices/elm.c
+++ b/drivers/mtd/devices/elm.c
@@ -84,6 +84,7 @@ struct elm_info {
 	struct list_head list;
 	enum bch_ecc bch_type;
 	struct elm_registers elm_regs;
+	int ecc_syndrome_size;
 };
 
 static LIST_HEAD(elm_devices);
@@ -126,7 +127,8 @@ int elm_config(struct device *dev, enum bch_ecc bch_type,
 
 	reg_val = (bch_type & ECC_BCH_LEVEL_MASK) | (ELM_ECC_SIZE << 16);
 	elm_write_reg(info, ELM_LOCATION_CONFIG, reg_val);
-	info->bch_type = bch_type;
+	info->bch_type		= bch_type;
+	info->ecc_syndrome_size	= ecc_syndrome_size;
 
 	return 0;
 }
@@ -175,10 +177,8 @@ static void elm_load_syndrome(struct elm_info *info,
 			elm_configure_page_mode(info, i, true);
 			offset = ELM_SYNDROME_FRAGMENT_0 +
 				SYNDROME_FRAGMENT_REG_SIZE * i;
-
-			/* BCH8 */
-			if (info->bch_type) {
-
+			switch (info->bch_type) {
+			case BCH8_ECC:
 				/* syndrome fragment 0 = ecc[9-12B] */
 				val = cpu_to_be32(*(u32 *) &ecc[9]);
 				elm_write_reg(info, offset, val);
@@ -197,7 +197,8 @@ static void elm_load_syndrome(struct elm_info *info,
 				offset += 4;
 				val = ecc[0];
 				elm_write_reg(info, offset, val);
-			} else {
+				break;
+			case BCH4_ECC:
 				/* syndrome fragment 0 = ecc[20-52b] bits */
 				val = (cpu_to_be32(*(u32 *) &ecc[3]) >> 4) |
 					((ecc[2] & 0xf) << 28);
@@ -207,11 +208,14 @@ static void elm_load_syndrome(struct elm_info *info,
 				offset += 4;
 				val = cpu_to_be32(*(u32 *) &ecc[0]) >> 12;
 				elm_write_reg(info, offset, val);
+				break;
+			default:
+				pr_err("invalid config bch_type\n");
 			}
 		}
 
 		/* Update ecc pointer with ecc byte size */
-		ecc += info->bch_type ? BCH8_SIZE : BCH4_SIZE;
+		ecc += info->ecc_syndrome_size;
 	}
 }
 
diff --git a/include/linux/platform_data/elm.h b/include/linux/platform_data/elm.h
index 6e37156b0902..4edb40676b3f 100644
--- a/include/linux/platform_data/elm.h
+++ b/include/linux/platform_data/elm.h
@@ -26,13 +26,6 @@ enum bch_ecc {
 /* ELM support 8 error syndrome process */
 #define ERROR_VECTOR_MAX		8
 
-#define BCH8_ECC_OOB_BYTES		13
-#define BCH4_ECC_OOB_BYTES		7
-/* RBL requires 14 byte even though BCH8 uses only 13 byte */
-#define BCH8_SIZE			(BCH8_ECC_OOB_BYTES + 1)
-/* Uses 1 extra byte to handle erased pages */
-#define BCH4_SIZE			(BCH4_ECC_OOB_BYTES + 1)
-
 /**
  * struct elm_errorvec - error vector for elm
  * @error_reported:		set true for vectors error is reported
-- 
cgit v1.2.3


From e34fcb07a6d57411de6e15a47724fbe92c5caa42 Mon Sep 17 00:00:00 2001
From: David Mosberger <davidm@egauge.net>
Date: Fri, 21 Mar 2014 16:05:10 -0600
Subject: mtd: nand: fix GET/SET_FEATURES address on 16-bit devices

GET_FEATURES and SET_FEATURES also need byte-addressing on 16-bit devices.

Signed-off-by: David Mosberger <davidm@egauge.net>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
---
 include/linux/mtd/nand.h | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 0747fef2bfc6..450d61ec7f06 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -925,7 +925,16 @@ static inline bool nand_is_slc(struct nand_chip *chip)
  */
 static inline int nand_opcode_8bits(unsigned int command)
 {
-	return command == NAND_CMD_READID || command == NAND_CMD_PARAM;
+	switch (command) {
+	case NAND_CMD_READID:
+	case NAND_CMD_PARAM:
+	case NAND_CMD_GET_FEATURES:
+	case NAND_CMD_SET_FEATURES:
+		return 1;
+	default:
+		break;
+	}
+	return 0;
 }
 
 /* return the supported JEDEC features. */
-- 
cgit v1.2.3


From 1425052097b53de841e064dc190a9009480c208c Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Tue, 25 Mar 2014 10:40:18 +0100
Subject: gpio: add IRQ chip helpers in gpiolib

This provides a function gpiochip_irqchip_add() to set
up an irqchip for a GPIO controller, and a function
gpiochip_set_chained_irqchip() to chain it to a parent
irqchip.

Most GPIOs are of the type where a number of lines form
a cascaded interrupt controller chained onto
the primary system interrupt controller (or further down the
chain) so let's add this helper and factor the code to
request the lines to be used as IRQs, the .to_irq() function
and the irqdomain into the core as well.

Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/Kconfig        |   3 +
 drivers/gpio/gpiolib.c      | 188 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/gpio/driver.h |  29 +++++++
 3 files changed, 220 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 2e461e459d88..51c782532687 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -55,6 +55,9 @@ config GPIO_ACPI
 	def_bool y
 	depends on ACPI
 
+config GPIOLIB_IRQCHIP
+	bool
+
 config DEBUG_GPIO
 	bool "Debug GPIO calls"
 	depends on DEBUG_KERNEL
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 584d2b465f84..f41cb4f3d715 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1254,6 +1254,9 @@ fail:
 }
 EXPORT_SYMBOL_GPL(gpiochip_add);
 
+/* Forward-declaration */
+static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip);
+
 /**
  * gpiochip_remove() - unregister a gpio_chip
  * @chip: the chip to unregister
@@ -1270,6 +1273,7 @@ int gpiochip_remove(struct gpio_chip *chip)
 
 	spin_lock_irqsave(&gpio_lock, flags);
 
+	gpiochip_irqchip_remove(chip);
 	gpiochip_remove_pin_ranges(chip);
 	of_gpiochip_remove(chip);
 
@@ -1339,6 +1343,190 @@ static struct gpio_chip *find_chip_by_name(const char *name)
 	return gpiochip_find((void *)name, gpiochip_match_name);
 }
 
+#ifdef CONFIG_GPIOLIB_IRQCHIP
+
+/*
+ * The following is irqchip helper code for gpiochips.
+ */
+
+/**
+ * gpiochip_add_chained_irqchip() - adds a chained irqchip to a gpiochip
+ * @gpiochip: the gpiochip to add the irqchip to
+ * @irqchip: the irqchip to add to the gpiochip
+ * @parent_irq: the irq number corresponding to the parent IRQ for this
+ * chained irqchip
+ * @parent_handler: the parent interrupt handler for the accumulated IRQ
+ * coming out of the gpiochip
+ */
+void gpiochip_set_chained_irqchip(struct gpio_chip *gpiochip,
+				  struct irq_chip *irqchip,
+				  int parent_irq,
+				  irq_flow_handler_t parent_handler)
+{
+	irq_set_chained_handler(parent_irq, parent_handler);
+	/*
+	 * The parent irqchip is already using the chip_data for this
+	 * irqchip, so our callbacks simply use the handler_data.
+	 */
+	irq_set_handler_data(parent_irq, gpiochip);
+}
+EXPORT_SYMBOL_GPL(gpiochip_set_chained_irqchip);
+
+/**
+ * gpiochip_irq_map() - maps an IRQ into a GPIO irqchip
+ * @d: the irqdomain used by this irqchip
+ * @irq: the global irq number used by this GPIO irqchip irq
+ * @hwirq: the local IRQ/GPIO line offset on this gpiochip
+ *
+ * This function will set up the mapping for a certain IRQ line on a
+ * gpiochip by assigning the gpiochip as chip data, and using the irqchip
+ * stored inside the gpiochip.
+ */
+static int gpiochip_irq_map(struct irq_domain *d, unsigned int irq,
+			    irq_hw_number_t hwirq)
+{
+	struct gpio_chip *chip = d->host_data;
+
+	irq_set_chip_and_handler(irq, chip->irqchip, chip->irq_handler);
+	irq_set_chip_data(irq, chip);
+#ifdef CONFIG_ARM
+	set_irq_flags(irq, IRQF_VALID);
+#else
+	irq_set_noprobe(irq);
+#endif
+	irq_set_irq_type(irq, chip->irq_default_type);
+
+	return 0;
+}
+
+static const struct irq_domain_ops gpiochip_domain_ops = {
+	.map	= gpiochip_irq_map,
+	/* Virtually all GPIO irqchips are twocell:ed */
+	.xlate	= irq_domain_xlate_twocell,
+};
+
+static int gpiochip_irq_reqres(struct irq_data *d)
+{
+	struct gpio_chip *chip = irq_data_get_irq_chip_data(d);
+
+	if (gpio_lock_as_irq(chip, d->hwirq)) {
+		chip_err(chip,
+			"unable to lock HW IRQ %lu for IRQ\n",
+			d->hwirq);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void gpiochip_irq_relres(struct irq_data *d)
+{
+	struct gpio_chip *chip = irq_data_get_irq_chip_data(d);
+
+	gpio_unlock_as_irq(chip, d->hwirq);
+}
+
+static int gpiochip_to_irq(struct gpio_chip *chip, unsigned offset)
+{
+	return irq_find_mapping(chip->irqdomain, offset);
+}
+
+/**
+ * gpiochip_irqchip_remove() - removes an irqchip added to a gpiochip
+ * @gpiochip: the gpiochip to remove the irqchip from
+ *
+ * This is called only from gpiochip_remove()
+ */
+static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip)
+{
+	if (gpiochip->irqdomain)
+		irq_domain_remove(gpiochip->irqdomain);
+
+	if (gpiochip->irqchip) {
+		gpiochip->irqchip->irq_request_resources = NULL;
+		gpiochip->irqchip->irq_release_resources = NULL;
+		gpiochip->irqchip = NULL;
+	}
+}
+
+/**
+ * gpiochip_irqchip_add() - adds an irqchip to a gpiochip
+ * @gpiochip: the gpiochip to add the irqchip to
+ * @irqchip: the irqchip to add to the gpiochip
+ * @first_irq: if not dynamically assigned, the base (first) IRQ to
+ * allocate gpiochip irqs from
+ * @handler: the irq handler to use (often a predefined irq core function)
+ * @type: the default type for IRQs on this irqchip
+ *
+ * This function closely associates a certain irqchip with a certain
+ * gpiochip, providing an irq domain to translate the local IRQs to
+ * global irqs in the gpiolib core, and making sure that the gpiochip
+ * is passed as chip data to all related functions. Driver callbacks
+ * need to use container_of() to get their local state containers back
+ * from the gpiochip passed as chip data. An irqdomain will be stored
+ * in the gpiochip that shall be used by the driver to handle IRQ number
+ * translation. The gpiochip will need to be initialized and registered
+ * before calling this function.
+ *
+ * This function will handle two cell:ed simple IRQs. Everything else
+ * need to be open coded.
+ */
+int gpiochip_irqchip_add(struct gpio_chip *gpiochip,
+			 struct irq_chip *irqchip,
+			 unsigned int first_irq,
+			 irq_flow_handler_t handler,
+			 unsigned int type)
+{
+	struct device_node *of_node;
+	unsigned int offset;
+
+	if (!gpiochip || !irqchip)
+		return -EINVAL;
+
+	if (!gpiochip->dev) {
+		pr_err("missing gpiochip .dev parent pointer\n");
+		return -EINVAL;
+	}
+	of_node = gpiochip->dev->of_node;
+#ifdef CONFIG_OF_GPIO
+	/*
+	 * If the gpiochip has an assigned OF node this takes precendence
+	 * FIXME: get rid of this and use gpiochip->dev->of_node everywhere
+	 */
+	if (gpiochip->of_node)
+		of_node = gpiochip->of_node;
+#endif
+	gpiochip->irqchip = irqchip;
+	gpiochip->irq_handler = handler;
+	gpiochip->irq_default_type = type;
+	gpiochip->to_irq = gpiochip_to_irq;
+	gpiochip->irqdomain = irq_domain_add_simple(of_node,
+					gpiochip->ngpio, first_irq,
+					&gpiochip_domain_ops, gpiochip);
+	if (!gpiochip->irqdomain) {
+		gpiochip->irqchip = NULL;
+		return -EINVAL;
+	}
+	irqchip->irq_request_resources = gpiochip_irq_reqres;
+	irqchip->irq_release_resources = gpiochip_irq_relres;
+
+	/*
+	 * Prepare the mapping since the irqchip shall be orthogonal to
+	 * any gpiochip calls. If the first_irq was zero, this is
+	 * necessary to allocate descriptors for all IRQs.
+	 */
+	for (offset = 0; offset < gpiochip->ngpio; offset++)
+		irq_create_mapping(gpiochip->irqdomain, offset);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(gpiochip_irqchip_add);
+
+#else /* CONFIG_GPIOLIB_IRQCHIP */
+
+static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip) {}
+
+#endif /* CONFIG_GPIOLIB_IRQCHIP */
+
 #ifdef CONFIG_PINCTRL
 
 /**
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 9fe283642253..c1c5c2368fc8 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -3,6 +3,9 @@
 
 #include <linux/types.h>
 #include <linux/module.h>
+#include <linux/irq.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
 
 struct device;
 struct gpio_desc;
@@ -97,6 +100,17 @@ struct gpio_chip {
 	bool			can_sleep;
 	bool			exported;
 
+#ifdef CONFIG_GPIOLIB_IRQCHIP
+	/*
+	 * With CONFIG_GPIO_IRQCHIP we get an irqchip inside the gpiolib
+	 * to handle IRQs for most practical cases.
+	 */
+	struct irq_chip		*irqchip;
+	struct irq_domain	*irqdomain;
+	irq_flow_handler_t	irq_handler;
+	unsigned int		irq_default_type;
+#endif
+
 #if defined(CONFIG_OF_GPIO)
 	/*
 	 * If CONFIG_OF is enabled, then all GPIO controllers described in the
@@ -190,6 +204,21 @@ struct gpiod_lookup_table {
 
 void gpiod_add_lookup_table(struct gpiod_lookup_table *table);
 
+#ifdef CONFIG_GPIOLIB_IRQCHIP
+
+void gpiochip_set_chained_irqchip(struct gpio_chip *gpiochip,
+		struct irq_chip *irqchip,
+		int parent_irq,
+		irq_flow_handler_t parent_handler);
+
+int gpiochip_irqchip_add(struct gpio_chip *gpiochip,
+		struct irq_chip *irqchip,
+		unsigned int first_irq,
+		irq_flow_handler_t handler,
+		unsigned int type);
+
+#endif /* CONFIG_GPIO_IRQCHIP */
+
 #else /* CONFIG_GPIOLIB */
 
 static inline struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc)
-- 
cgit v1.2.3


From 12478cf0c55e5969f740bb38a24b1a0104ae18d8 Mon Sep 17 00:00:00 2001
From: "Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com>
Date: Mon, 24 Mar 2014 13:35:44 +0530
Subject: cpufreq: Make sure frequency transitions are serialized

Whenever we change the frequency of a CPU, we call the PRECHANGE and POSTCHANGE
notifiers. They must be serialized, i.e. PRECHANGE and POSTCHANGE notifiers
should strictly alternate, thereby preventing two different sets of PRECHANGE or
POSTCHANGE notifiers from interleaving arbitrarily.

The following examples illustrate why this is important:

Scenario 1:
-----------
A thread reading the value of cpuinfo_cur_freq, will call
__cpufreq_cpu_get()->cpufreq_out_of_sync()->cpufreq_notify_transition()

The ondemand governor can decide to change the frequency of the CPU at the same
time and hence it can end up sending the notifications via ->target().

If the notifiers are not serialized, the following sequence can occur:
- PRECHANGE Notification for freq A (from cpuinfo_cur_freq)
- PRECHANGE Notification for freq B (from target())
- Freq changed by target() to B
- POSTCHANGE Notification for freq B
- POSTCHANGE Notification for freq A

We can see from the above that the last POSTCHANGE Notification happens for freq
A but the hardware is set to run at freq B.

Where would we break then?: adjust_jiffies() in cpufreq.c & cpufreq_callback()
in arch/arm/kernel/smp.c (which also adjusts the jiffies). All the
loops_per_jiffy calculations will get messed up.

Scenario 2:
-----------
The governor calls __cpufreq_driver_target() to change the frequency. At the
same time, if we change scaling_{min|max}_freq from sysfs, it will end up
calling the governor's CPUFREQ_GOV_LIMITS notification, which will also call
__cpufreq_driver_target(). And hence we end up issuing concurrent calls to
->target().

Typically, platforms have the following logic in their ->target() routines:
(Eg: cpufreq-cpu0, omap, exynos, etc)

A. If new freq is more than old: Increase voltage
B. Change freq
C. If new freq is less than old: decrease voltage

Now, if the two concurrent calls to ->target() are X and Y, where X is trying to
increase the freq and Y is trying to decrease it, we get the following race
condition:

X.A: voltage gets increased for larger freq
Y.A: nothing happens
Y.B: freq gets decreased
Y.C: voltage gets decreased
X.B: freq gets increased
X.C: nothing happens

Thus we can end up setting a freq which is not supported by the voltage we have
set. That will probably make the clock to the CPU unstable and the system might
not work properly anymore.

This patch introduces a set of synchronization primitives to serialize frequency
transitions, which are to be used as shown below:

cpufreq_freq_transition_begin();

//Perform the frequency change

cpufreq_freq_transition_end();

The _begin() call sends the PRECHANGE notification whereas the _end() call sends
the POSTCHANGE notification. Also, all the necessary synchronization is handled
within these calls. In particular, even drivers which set the ASYNC_NOTIFICATION
flag can also use these APIs for performing frequency transitions (ie., you can
call _begin() from one task, and call the corresponding _end() from a different
task).

The actual synchronization underneath is not that complicated:

The key challenge is to allow drivers to begin the transition from one thread
and end it in a completely different thread (this is to enable drivers that do
asynchronous POSTCHANGE notification from bottom-halves, to also use the same
interface).

To achieve this, a 'transition_ongoing' flag, a 'transition_lock' spinlock and a
wait-queue are added per-policy. The flag and the wait-queue are used in
conjunction to create an "uninterrupted flow" from _begin() to _end(). The
spinlock is used to ensure that only one such "flow" is in flight at any given
time. Put together, this provides us all the necessary synchronization.

Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cpufreq.c | 37 +++++++++++++++++++++++++++++++++++++
 include/linux/cpufreq.h   | 10 ++++++++++
 2 files changed, 47 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index d8d6bc9d1815..d57806a85def 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -353,6 +353,41 @@ void cpufreq_notify_post_transition(struct cpufreq_policy *policy,
 }
 EXPORT_SYMBOL_GPL(cpufreq_notify_post_transition);
 
+void cpufreq_freq_transition_begin(struct cpufreq_policy *policy,
+		struct cpufreq_freqs *freqs)
+{
+wait:
+	wait_event(policy->transition_wait, !policy->transition_ongoing);
+
+	spin_lock(&policy->transition_lock);
+
+	if (unlikely(policy->transition_ongoing)) {
+		spin_unlock(&policy->transition_lock);
+		goto wait;
+	}
+
+	policy->transition_ongoing = true;
+
+	spin_unlock(&policy->transition_lock);
+
+	cpufreq_notify_transition(policy, freqs, CPUFREQ_PRECHANGE);
+}
+EXPORT_SYMBOL_GPL(cpufreq_freq_transition_begin);
+
+void cpufreq_freq_transition_end(struct cpufreq_policy *policy,
+		struct cpufreq_freqs *freqs, int transition_failed)
+{
+	if (unlikely(WARN_ON(!policy->transition_ongoing)))
+		return;
+
+	cpufreq_notify_post_transition(policy, freqs, transition_failed);
+
+	policy->transition_ongoing = false;
+
+	wake_up(&policy->transition_wait);
+}
+EXPORT_SYMBOL_GPL(cpufreq_freq_transition_end);
+
 
 /*********************************************************************
  *                          SYSFS INTERFACE                          *
@@ -985,6 +1020,8 @@ static struct cpufreq_policy *cpufreq_policy_alloc(void)
 
 	INIT_LIST_HEAD(&policy->policy_list);
 	init_rwsem(&policy->rwsem);
+	spin_lock_init(&policy->transition_lock);
+	init_waitqueue_head(&policy->transition_wait);
 
 	return policy;
 
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 2d2e62c8666a..e33760268a86 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -16,6 +16,7 @@
 #include <linux/completion.h>
 #include <linux/kobject.h>
 #include <linux/notifier.h>
+#include <linux/spinlock.h>
 #include <linux/sysfs.h>
 
 /*********************************************************************
@@ -104,6 +105,11 @@ struct cpufreq_policy {
 	 *     __cpufreq_governor(data, CPUFREQ_GOV_POLICY_EXIT);
 	 */
 	struct rw_semaphore	rwsem;
+
+	/* Synchronization for frequency transitions */
+	bool			transition_ongoing; /* Tracks transition status */
+	spinlock_t		transition_lock;
+	wait_queue_head_t	transition_wait;
 };
 
 /* Only for ACPI */
@@ -337,6 +343,10 @@ void cpufreq_notify_transition(struct cpufreq_policy *policy,
 		struct cpufreq_freqs *freqs, unsigned int state);
 void cpufreq_notify_post_transition(struct cpufreq_policy *policy,
 		struct cpufreq_freqs *freqs, int transition_failed);
+void cpufreq_freq_transition_begin(struct cpufreq_policy *policy,
+		struct cpufreq_freqs *freqs);
+void cpufreq_freq_transition_end(struct cpufreq_policy *policy,
+		struct cpufreq_freqs *freqs, int transition_failed);
 
 #else /* CONFIG_CPU_FREQ */
 static inline int cpufreq_register_notifier(struct notifier_block *nb,
-- 
cgit v1.2.3


From 236a98005274d8011136aee4aef52241588a9712 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Mon, 24 Mar 2014 13:35:46 +0530
Subject: cpufreq: Make cpufreq_notify_transition &
 cpufreq_notify_post_transition static

cpufreq_notify_transition() and cpufreq_notify_post_transition() shouldn't be
called directly by cpufreq drivers anymore and so these should be marked static.

Reviewed-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cpufreq.c | 6 ++----
 include/linux/cpufreq.h   | 4 ----
 2 files changed, 2 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index eb562d043412..abda6609d3e7 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -331,16 +331,15 @@ static void __cpufreq_notify_transition(struct cpufreq_policy *policy,
  * function. It is called twice on all CPU frequency changes that have
  * external effects.
  */
-void cpufreq_notify_transition(struct cpufreq_policy *policy,
+static void cpufreq_notify_transition(struct cpufreq_policy *policy,
 		struct cpufreq_freqs *freqs, unsigned int state)
 {
 	for_each_cpu(freqs->cpu, policy->cpus)
 		__cpufreq_notify_transition(policy, freqs, state);
 }
-EXPORT_SYMBOL_GPL(cpufreq_notify_transition);
 
 /* Do post notifications when there are chances that transition has failed */
-void cpufreq_notify_post_transition(struct cpufreq_policy *policy,
+static void cpufreq_notify_post_transition(struct cpufreq_policy *policy,
 		struct cpufreq_freqs *freqs, int transition_failed)
 {
 	cpufreq_notify_transition(policy, freqs, CPUFREQ_POSTCHANGE);
@@ -351,7 +350,6 @@ void cpufreq_notify_post_transition(struct cpufreq_policy *policy,
 	cpufreq_notify_transition(policy, freqs, CPUFREQ_PRECHANGE);
 	cpufreq_notify_transition(policy, freqs, CPUFREQ_POSTCHANGE);
 }
-EXPORT_SYMBOL_GPL(cpufreq_notify_post_transition);
 
 void cpufreq_freq_transition_begin(struct cpufreq_policy *policy,
 		struct cpufreq_freqs *freqs)
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index e33760268a86..c48e595f623e 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -339,10 +339,6 @@ static inline void cpufreq_resume(void) {}
 int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list);
 int cpufreq_unregister_notifier(struct notifier_block *nb, unsigned int list);
 
-void cpufreq_notify_transition(struct cpufreq_policy *policy,
-		struct cpufreq_freqs *freqs, unsigned int state);
-void cpufreq_notify_post_transition(struct cpufreq_policy *policy,
-		struct cpufreq_freqs *freqs, int transition_failed);
 void cpufreq_freq_transition_begin(struct cpufreq_policy *policy,
 		struct cpufreq_freqs *freqs);
 void cpufreq_freq_transition_end(struct cpufreq_policy *policy,
-- 
cgit v1.2.3


From 61b905da33ae25edb6b9d2a5de21e34c3a77efe3 Mon Sep 17 00:00:00 2001
From: Tom Herbert <therbert@google.com>
Date: Mon, 24 Mar 2014 15:34:47 -0700
Subject: net: Rename skb->rxhash to skb->hash

The packet hash can be considered a property of the packet, not just
on RX path.

This patch changes name of rxhash and l4_rxhash skbuff fields to be
hash and l4_hash respectively. This includes changing uses of the
field in the code which don't call the access functions.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Mahesh Bandewar <maheshb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm/net/bpf_jit_32.c       |  4 ++--
 arch/powerpc/net/bpf_jit_comp.c |  4 ++--
 arch/s390/net/bpf_jit_comp.c    |  8 ++++----
 arch/sparc/net/bpf_jit_comp.c   |  2 +-
 arch/x86/net/bpf_jit_comp.c     |  8 ++++----
 include/linux/skbuff.h          | 28 ++++++++++++++--------------
 include/net/sock.h              |  4 ++--
 include/trace/events/net.h      | 12 ++++++------
 net/core/dev.c                  | 13 +++++++------
 net/core/filter.c               |  2 +-
 net/core/flow_dissector.c       | 10 +++++-----
 net/packet/af_packet.c          |  3 +--
 12 files changed, 49 insertions(+), 49 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 271b5e971568..7ddb9c83cdfc 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -825,8 +825,8 @@ b_epilogue:
 			break;
 		case BPF_S_ANC_RXHASH:
 			ctx->seen |= SEEN_SKB;
-			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4);
-			off = offsetof(struct sk_buff, rxhash);
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
+			off = offsetof(struct sk_buff, hash);
 			emit(ARM_LDR_I(r_A, r_skb, off), ctx);
 			break;
 		case BPF_S_ANC_VLAN_TAG:
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 555034f8505e..4afad6c17d50 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -390,9 +390,9 @@ static int bpf_jit_build_body(struct sk_filter *fp, u32 *image,
 							  mark));
 			break;
 		case BPF_S_ANC_RXHASH:
-			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4);
+			BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
 			PPC_LWZ_OFFS(r_A, r_skb, offsetof(struct sk_buff,
-							  rxhash));
+							  hash));
 			break;
 		case BPF_S_ANC_VLAN_TAG:
 		case BPF_S_ANC_VLAN_TAG_PRESENT:
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 708d60e40066..153f8f2cfd56 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -737,10 +737,10 @@ call_fn:	/* lg %r1,<d(function)>(%r13) */
 		/* icm	%r5,3,<d(type)>(%r1) */
 		EMIT4_DISP(0xbf531000, offsetof(struct net_device, type));
 		break;
-	case BPF_S_ANC_RXHASH: /* A = skb->rxhash */
-		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4);
-		/* l %r5,<d(rxhash)>(%r2) */
-		EMIT4_DISP(0x58502000, offsetof(struct sk_buff, rxhash));
+	case BPF_S_ANC_RXHASH: /* A = skb->hash */
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
+		/* l %r5,<d(hash)>(%r2) */
+		EMIT4_DISP(0x58502000, offsetof(struct sk_buff, hash));
 		break;
 	case BPF_S_ANC_VLAN_TAG:
 	case BPF_S_ANC_VLAN_TAG_PRESENT:
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index 01fe9946d388..d96d2a7c78ee 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -618,7 +618,7 @@ void bpf_jit_compile(struct sk_filter *fp)
 				emit_load16(r_A, struct net_device, type, r_A);
 				break;
 			case BPF_S_ANC_RXHASH:
-				emit_skb_load32(rxhash, r_A);
+				emit_skb_load32(hash, r_A);
 				break;
 			case BPF_S_ANC_VLAN_TAG:
 			case BPF_S_ANC_VLAN_TAG_PRESENT:
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 4ed75dd81d05..293c57b74edc 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -553,13 +553,13 @@ void bpf_jit_compile(struct sk_filter *fp)
 				}
 				break;
 			case BPF_S_ANC_RXHASH:
-				BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, rxhash) != 4);
-				if (is_imm8(offsetof(struct sk_buff, rxhash))) {
+				BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
+				if (is_imm8(offsetof(struct sk_buff, hash))) {
 					/* mov off8(%rdi),%eax */
-					EMIT3(0x8b, 0x47, offsetof(struct sk_buff, rxhash));
+					EMIT3(0x8b, 0x47, offsetof(struct sk_buff, hash));
 				} else {
 					EMIT2(0x8b, 0x87);
-					EMIT(offsetof(struct sk_buff, rxhash), 4);
+					EMIT(offsetof(struct sk_buff, hash), 4);
 				}
 				break;
 			case BPF_S_ANC_QUEUE:
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 03db95ab8a8c..aa2c22cb8158 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -444,11 +444,11 @@ static inline u32 skb_mstamp_us_delta(const struct skb_mstamp *t1,
  *	@skb_iif: ifindex of device we arrived on
  *	@tc_index: Traffic control index
  *	@tc_verd: traffic control verdict
- *	@rxhash: the packet hash computed on receive
+ *	@hash: the packet hash
  *	@queue_mapping: Queue mapping for multiqueue devices
  *	@ndisc_nodetype: router type (from link layer)
  *	@ooo_okay: allow the mapping of a socket to a queue to be changed
- *	@l4_rxhash: indicate rxhash is a canonical 4-tuple hash over transport
+ *	@l4_hash: indicate hash is a canonical 4-tuple hash over transport
  *		ports.
  *	@wifi_acked_valid: wifi_acked was set
  *	@wifi_acked: whether frame was acked on wifi or not
@@ -537,7 +537,7 @@ struct sk_buff {
 
 	int			skb_iif;
 
-	__u32			rxhash;
+	__u32			hash;
 
 	__be16			vlan_proto;
 	__u16			vlan_tci;
@@ -556,7 +556,7 @@ struct sk_buff {
 #endif
 	__u8			pfmemalloc:1;
 	__u8			ooo_okay:1;
-	__u8			l4_rxhash:1;
+	__u8			l4_hash:1;
 	__u8			wifi_acked_valid:1;
 	__u8			wifi_acked:1;
 	__u8			no_fcs:1;
@@ -815,40 +815,40 @@ enum pkt_hash_types {
 static inline void
 skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type)
 {
-	skb->l4_rxhash = (type == PKT_HASH_TYPE_L4);
-	skb->rxhash = hash;
+	skb->l4_hash = (type == PKT_HASH_TYPE_L4);
+	skb->hash = hash;
 }
 
 void __skb_get_hash(struct sk_buff *skb);
 static inline __u32 skb_get_hash(struct sk_buff *skb)
 {
-	if (!skb->l4_rxhash)
+	if (!skb->l4_hash)
 		__skb_get_hash(skb);
 
-	return skb->rxhash;
+	return skb->hash;
 }
 
 static inline __u32 skb_get_hash_raw(const struct sk_buff *skb)
 {
-	return skb->rxhash;
+	return skb->hash;
 }
 
 static inline void skb_clear_hash(struct sk_buff *skb)
 {
-	skb->rxhash = 0;
-	skb->l4_rxhash = 0;
+	skb->hash = 0;
+	skb->l4_hash = 0;
 }
 
 static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb)
 {
-	if (!skb->l4_rxhash)
+	if (!skb->l4_hash)
 		skb_clear_hash(skb);
 }
 
 static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from)
 {
-	to->rxhash = from->rxhash;
-	to->l4_rxhash = from->l4_rxhash;
+	to->hash = from->hash;
+	to->l4_hash = from->l4_hash;
 };
 
 #ifdef NET_SKBUFF_DATA_USES_OFFSET
diff --git a/include/net/sock.h b/include/net/sock.h
index 625e65b12366..8d7c431a0660 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -862,9 +862,9 @@ static inline void sock_rps_save_rxhash(struct sock *sk,
 					const struct sk_buff *skb)
 {
 #ifdef CONFIG_RPS
-	if (unlikely(sk->sk_rxhash != skb->rxhash)) {
+	if (unlikely(sk->sk_rxhash != skb->hash)) {
 		sock_rps_reset_flow(sk);
-		sk->sk_rxhash = skb->rxhash;
+		sk->sk_rxhash = skb->hash;
 	}
 #endif
 }
diff --git a/include/trace/events/net.h b/include/trace/events/net.h
index a34f27b2e394..1de256b35807 100644
--- a/include/trace/events/net.h
+++ b/include/trace/events/net.h
@@ -153,8 +153,8 @@ DECLARE_EVENT_CLASS(net_dev_rx_verbose_template,
 		__field(	u16,			vlan_tci	)
 		__field(	u16,			protocol	)
 		__field(	u8,			ip_summed	)
-		__field(	u32,			rxhash		)
-		__field(	bool,			l4_rxhash	)
+		__field(	u32,			hash		)
+		__field(	bool,			l4_hash		)
 		__field(	unsigned int,		len		)
 		__field(	unsigned int,		data_len	)
 		__field(	unsigned int,		truesize	)
@@ -179,8 +179,8 @@ DECLARE_EVENT_CLASS(net_dev_rx_verbose_template,
 		__entry->vlan_tci = vlan_tx_tag_get(skb);
 		__entry->protocol = ntohs(skb->protocol);
 		__entry->ip_summed = skb->ip_summed;
-		__entry->rxhash = skb->rxhash;
-		__entry->l4_rxhash = skb->l4_rxhash;
+		__entry->hash = skb->hash;
+		__entry->l4_hash = skb->l4_hash;
 		__entry->len = skb->len;
 		__entry->data_len = skb->data_len;
 		__entry->truesize = skb->truesize;
@@ -191,11 +191,11 @@ DECLARE_EVENT_CLASS(net_dev_rx_verbose_template,
 		__entry->gso_type = skb_shinfo(skb)->gso_type;
 	),
 
-	TP_printk("dev=%s napi_id=%#x queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d rxhash=0x%08x l4_rxhash=%d len=%u data_len=%u truesize=%u mac_header_valid=%d mac_header=%d nr_frags=%d gso_size=%d gso_type=%#x",
+	TP_printk("dev=%s napi_id=%#x queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d hash=0x%08x l4_hash=%d len=%u data_len=%u truesize=%u mac_header_valid=%d mac_header=%d nr_frags=%d gso_size=%d gso_type=%#x",
 		  __get_str(name), __entry->napi_id, __entry->queue_mapping,
 		  __entry->skbaddr, __entry->vlan_tagged, __entry->vlan_proto,
 		  __entry->vlan_tci, __entry->protocol, __entry->ip_summed,
-		  __entry->rxhash, __entry->l4_rxhash, __entry->len,
+		  __entry->hash, __entry->l4_hash, __entry->len,
 		  __entry->data_len, __entry->truesize,
 		  __entry->mac_header_valid, __entry->mac_header,
 		  __entry->nr_frags, __entry->gso_size, __entry->gso_type)
diff --git a/net/core/dev.c b/net/core/dev.c
index 55f8e64c03a2..48dd323d5918 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2952,7 +2952,7 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		flow_table = rcu_dereference(rxqueue->rps_flow_table);
 		if (!flow_table)
 			goto out;
-		flow_id = skb->rxhash & flow_table->mask;
+		flow_id = skb_get_hash(skb) & flow_table->mask;
 		rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb,
 							rxq_index, flow_id);
 		if (rc < 0)
@@ -2986,6 +2986,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	struct rps_sock_flow_table *sock_flow_table;
 	int cpu = -1;
 	u16 tcpu;
+	u32 hash;
 
 	if (skb_rx_queue_recorded(skb)) {
 		u16 index = skb_get_rx_queue(skb);
@@ -3014,7 +3015,8 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	}
 
 	skb_reset_network_header(skb);
-	if (!skb_get_hash(skb))
+	hash = skb_get_hash(skb);
+	if (!hash)
 		goto done;
 
 	flow_table = rcu_dereference(rxqueue->rps_flow_table);
@@ -3023,11 +3025,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		u16 next_cpu;
 		struct rps_dev_flow *rflow;
 
-		rflow = &flow_table->flows[skb->rxhash & flow_table->mask];
+		rflow = &flow_table->flows[hash & flow_table->mask];
 		tcpu = rflow->cpu;
 
-		next_cpu = sock_flow_table->ents[skb->rxhash &
-		    sock_flow_table->mask];
+		next_cpu = sock_flow_table->ents[hash & sock_flow_table->mask];
 
 		/*
 		 * If the desired CPU (where last recvmsg was done) is
@@ -3056,7 +3057,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	}
 
 	if (map) {
-		tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32];
+		tcpu = map->cpus[((u64) hash * map->len) >> 32];
 
 		if (cpu_online(tcpu)) {
 			cpu = tcpu;
diff --git a/net/core/filter.c b/net/core/filter.c
index ad30d626a5bd..65b75966e206 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -336,7 +336,7 @@ load_b:
 			A = skb->dev->type;
 			continue;
 		case BPF_S_ANC_RXHASH:
-			A = skb->rxhash;
+			A = skb->hash;
 			continue;
 		case BPF_S_ANC_CPU:
 			A = raw_smp_processor_id();
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 80201bf69d59..107ed12a5323 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -203,8 +203,8 @@ static __always_inline u32 __flow_hash_1word(u32 a)
 
 /*
  * __skb_get_hash: calculate a flow hash based on src/dst addresses
- * and src/dst port numbers.  Sets rxhash in skb to non-zero hash value
- * on success, zero indicates no valid hash.  Also, sets l4_rxhash in skb
+ * and src/dst port numbers.  Sets hash in skb to non-zero hash value
+ * on success, zero indicates no valid hash.  Also, sets l4_hash in skb
  * if hash is a canonical 4-tuple hash over transport ports.
  */
 void __skb_get_hash(struct sk_buff *skb)
@@ -216,7 +216,7 @@ void __skb_get_hash(struct sk_buff *skb)
 		return;
 
 	if (keys.ports)
-		skb->l4_rxhash = 1;
+		skb->l4_hash = 1;
 
 	/* get a consistent hash (same value on both flow directions) */
 	if (((__force u32)keys.dst < (__force u32)keys.src) ||
@@ -232,7 +232,7 @@ void __skb_get_hash(struct sk_buff *skb)
 	if (!hash)
 		hash = 1;
 
-	skb->rxhash = hash;
+	skb->hash = hash;
 }
 EXPORT_SYMBOL(__skb_get_hash);
 
@@ -344,7 +344,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
 					hash = skb->sk->sk_hash;
 				else
 					hash = (__force u16) skb->protocol ^
-					    skb->rxhash;
+					    skb->hash;
 				hash = __flow_hash_1word(hash);
 				queue_index = map->queues[
 				    ((u64)hash * map->len) >> 32];
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 292304404fda..097a354ec8cd 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1277,7 +1277,7 @@ static unsigned int fanout_demux_hash(struct packet_fanout *f,
 				      struct sk_buff *skb,
 				      unsigned int num)
 {
-	return reciprocal_scale(skb->rxhash, num);
+	return reciprocal_scale(skb_get_hash(skb), num);
 }
 
 static unsigned int fanout_demux_lb(struct packet_fanout *f,
@@ -1362,7 +1362,6 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 			if (!skb)
 				return 0;
 		}
-		skb_get_hash(skb);
 		idx = fanout_demux_hash(f, skb, num);
 		break;
 	case PACKET_FANOUT_LB:
-- 
cgit v1.2.3


From 71e415e44c1f9b7a4f05dac4f8038575dbef0c6f Mon Sep 17 00:00:00 2001
From: dingtianhong <dingtianhong@huawei.com>
Date: Tue, 25 Mar 2014 17:44:42 +0800
Subject: vlan: make a new function vlan_dev_vlan_proto() and export

The vlan support 2 proto: 802.1q and 802.1ad, so make a new function
called vlan_dev_vlan_proto() which could return the vlan proto for
input dev.

Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_vlan.h | 7 +++++++
 net/8021q/vlan_core.c   | 6 ++++++
 2 files changed, 13 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index d3d2306f00bf..13bbbde00e68 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -110,6 +110,7 @@ extern struct net_device *__vlan_find_dev_deep(struct net_device *real_dev,
 					       __be16 vlan_proto, u16 vlan_id);
 extern struct net_device *vlan_dev_real_dev(const struct net_device *dev);
 extern u16 vlan_dev_vlan_id(const struct net_device *dev);
+extern __be16 vlan_dev_vlan_proto(const struct net_device *dev);
 
 /**
  *	struct vlan_priority_tci_mapping - vlan egress priority mappings
@@ -216,6 +217,12 @@ static inline u16 vlan_dev_vlan_id(const struct net_device *dev)
 	return 0;
 }
 
+static inline __be16 vlan_dev_vlan_proto(const struct net_device *dev)
+{
+	BUG();
+	return 0;
+}
+
 static inline u16 vlan_dev_get_egress_qos_mask(struct net_device *dev,
 					       u32 skprio)
 {
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 35b3c192d7b9..3c32bd257b73 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -106,6 +106,12 @@ u16 vlan_dev_vlan_id(const struct net_device *dev)
 }
 EXPORT_SYMBOL(vlan_dev_vlan_id);
 
+__be16 vlan_dev_vlan_proto(const struct net_device *dev)
+{
+	return vlan_dev_priv(dev)->vlan_proto;
+}
+EXPORT_SYMBOL(vlan_dev_vlan_proto);
+
 static struct sk_buff *vlan_reorder_header(struct sk_buff *skb)
 {
 	if (skb_cow(skb, skb_headroom(skb)) < 0)
-- 
cgit v1.2.3


From 1edb9ca69e8a7988900fc0283e10550b5592164d Mon Sep 17 00:00:00 2001
From: Siva Reddy <siva.kallam@samsung.com>
Date: Tue, 25 Mar 2014 12:10:54 -0700
Subject: net: sxgbe: add basic framework for Samsung 10Gb ethernet driver

This patch adds support for Samsung 10Gb ethernet driver(sxgbe).

- sxgbe core initialization
- Tx and Rx support
- MDIO support
- ISRs for Tx and Rx
- ifconfig support to driver

Signed-off-by: Siva Reddy Kallam <siva.kallam@samsung.com>
Signed-off-by: Vipul Pandya <vipul.pandya@samsung.com>
Signed-off-by: Girish K S <ks.giri@samsung.com>
Neatening-by: Joe Perches <joe@perches.com>
Signed-off-by: Byungho An <bh74.an@samsung.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/Kconfig                       |    1 +
 drivers/net/ethernet/Makefile                      |    1 +
 drivers/net/ethernet/samsung/Kconfig               |   16 +
 drivers/net/ethernet/samsung/Makefile              |    5 +
 drivers/net/ethernet/samsung/sxgbe/Kconfig         |    9 +
 drivers/net/ethernet/samsung/sxgbe/Makefile        |    4 +
 drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h  |  462 +++++
 drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c    |  158 ++
 drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.c    |  515 +++++
 drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.h    |  298 +++
 drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.c     |  372 ++++
 drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.h     |   48 +
 drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c |   44 +
 drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c    | 2052 ++++++++++++++++++++
 drivers/net/ethernet/samsung/sxgbe/sxgbe_mdio.c    |  251 +++
 drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.c     |  254 +++
 drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.h     |  104 +
 .../net/ethernet/samsung/sxgbe/sxgbe_platform.c    |  253 +++
 drivers/net/ethernet/samsung/sxgbe/sxgbe_reg.h     |  477 +++++
 drivers/net/ethernet/samsung/sxgbe/sxgbe_xpcs.c    |   91 +
 drivers/net/ethernet/samsung/sxgbe/sxgbe_xpcs.h    |   38 +
 include/linux/sxgbe_platform.h                     |   54 +
 22 files changed, 5507 insertions(+)
 create mode 100644 drivers/net/ethernet/samsung/Kconfig
 create mode 100644 drivers/net/ethernet/samsung/Makefile
 create mode 100644 drivers/net/ethernet/samsung/sxgbe/Kconfig
 create mode 100644 drivers/net/ethernet/samsung/sxgbe/Makefile
 create mode 100644 drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h
 create mode 100644 drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c
 create mode 100644 drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.c
 create mode 100644 drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.h
 create mode 100644 drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.c
 create mode 100644 drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.h
 create mode 100644 drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
 create mode 100644 drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
 create mode 100644 drivers/net/ethernet/samsung/sxgbe/sxgbe_mdio.c
 create mode 100644 drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.c
 create mode 100644 drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.h
 create mode 100644 drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c
 create mode 100644 drivers/net/ethernet/samsung/sxgbe/sxgbe_reg.h
 create mode 100644 drivers/net/ethernet/samsung/sxgbe/sxgbe_xpcs.c
 create mode 100644 drivers/net/ethernet/samsung/sxgbe/sxgbe_xpcs.h
 create mode 100644 include/linux/sxgbe_platform.h

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index 39484b534f5e..39b26fe28d10 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -150,6 +150,7 @@ config S6GMAC
 	  To compile this driver as a module, choose M here. The module
 	  will be called s6gmac.
 
+source "drivers/net/ethernet/samsung/Kconfig"
 source "drivers/net/ethernet/seeq/Kconfig"
 source "drivers/net/ethernet/silan/Kconfig"
 source "drivers/net/ethernet/sis/Kconfig"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index adf61af507f7..545d0b3b9cb4 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -61,6 +61,7 @@ obj-$(CONFIG_NET_VENDOR_REALTEK) += realtek/
 obj-$(CONFIG_SH_ETH) += renesas/
 obj-$(CONFIG_NET_VENDOR_RDC) += rdc/
 obj-$(CONFIG_S6GMAC) += s6gmac.o
+obj-$(CONFIG_NET_VENDOR_SAMSUNG) += samsung/
 obj-$(CONFIG_NET_VENDOR_SEEQ) += seeq/
 obj-$(CONFIG_NET_VENDOR_SILAN) += silan/
 obj-$(CONFIG_NET_VENDOR_SIS) += sis/
diff --git a/drivers/net/ethernet/samsung/Kconfig b/drivers/net/ethernet/samsung/Kconfig
new file mode 100644
index 000000000000..7902341f2623
--- /dev/null
+++ b/drivers/net/ethernet/samsung/Kconfig
@@ -0,0 +1,16 @@
+#
+# Samsung Ethernet device configuration
+#
+
+config NET_VENDOR_SAMSUNG
+	bool "Samsung Ethernet device"
+	default y
+	---help---
+	  This is the driver for the SXGBE 10G Ethernet IP block found on Samsung
+	  platforms.
+
+if NET_VENDOR_SAMSUNG
+
+source "drivers/net/ethernet/samsung/sxgbe/Kconfig"
+
+endif # NET_VENDOR_SAMSUNG
diff --git a/drivers/net/ethernet/samsung/Makefile b/drivers/net/ethernet/samsung/Makefile
new file mode 100644
index 000000000000..1773c29b8d76
--- /dev/null
+++ b/drivers/net/ethernet/samsung/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the Samsung Ethernet device drivers.
+#
+
+obj-$(CONFIG_SXGBE_ETH) += sxgbe/
diff --git a/drivers/net/ethernet/samsung/sxgbe/Kconfig b/drivers/net/ethernet/samsung/sxgbe/Kconfig
new file mode 100644
index 000000000000..d79288c51d0a
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/Kconfig
@@ -0,0 +1,9 @@
+config SXGBE_ETH
+	tristate "Samsung 10G/2.5G/1G SXGBE Ethernet driver"
+	depends on HAS_IOMEM && HAS_DMA
+	select PHYLIB
+	select CRC32
+	select PTP_1588_CLOCK
+	---help---
+	  This is the driver for the SXGBE 10G Ethernet IP block found on Samsung
+	  platforms.
diff --git a/drivers/net/ethernet/samsung/sxgbe/Makefile b/drivers/net/ethernet/samsung/sxgbe/Makefile
new file mode 100644
index 000000000000..dcc80b9d4370
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/Makefile
@@ -0,0 +1,4 @@
+obj-$(CONFIG_SXGBE_ETH) += samsung-sxgbe.o
+samsung-sxgbe-objs:= sxgbe_platform.o sxgbe_main.o sxgbe_desc.o \
+		sxgbe_dma.o sxgbe_core.o sxgbe_mtl.o  sxgbe_mdio.o \
+		sxgbe_ethtool.o sxgbe_xpcs.o $(samsung-sxgbe-y)
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h
new file mode 100644
index 000000000000..c7803f199967
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h
@@ -0,0 +1,462 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __SXGBE_COMMON_H__
+#define __SXGBE_COMMON_H__
+
+/* forward references */
+struct sxgbe_desc_ops;
+struct sxgbe_dma_ops;
+struct sxgbe_mtl_ops;
+
+#define SXGBE_RESOURCE_NAME	"sam_sxgbeeth"
+#define DRV_MODULE_VERSION	"November_2013"
+
+/* MAX HW feature words */
+#define SXGBE_HW_WORDS 3
+
+#define SXGBE_RX_COE_NONE	0
+
+/* CSR Frequency Access Defines*/
+#define SXGBE_CSR_F_150M	150000000
+#define SXGBE_CSR_F_250M	250000000
+#define SXGBE_CSR_F_300M	300000000
+#define SXGBE_CSR_F_350M	350000000
+#define SXGBE_CSR_F_400M	400000000
+#define SXGBE_CSR_F_500M	500000000
+
+/* pause time */
+#define SXGBE_PAUSE_TIME 0x200
+
+/* tx queues */
+#define SXGBE_TX_QUEUES   8
+#define SXGBE_RX_QUEUES   16
+
+/* Calculated based how much time does it take to fill 256KB Rx memory
+ * at 10Gb speed at 156MHz clock rate and considered little less then
+ * the actual value.
+ */
+#define SXGBE_MAX_DMA_RIWT	0x70
+#define SXGBE_MIN_DMA_RIWT	0x01
+
+/* Tx coalesce parameters */
+#define SXGBE_COAL_TX_TIMER	40000
+#define SXGBE_MAX_COAL_TX_TICK	100000
+#define SXGBE_TX_MAX_FRAMES	512
+#define SXGBE_TX_FRAMES	128
+
+/* SXGBE TX FIFO is 8K, Rx FIFO is 16K */
+#define BUF_SIZE_16KiB 16384
+#define BUF_SIZE_8KiB 8192
+#define BUF_SIZE_4KiB 4096
+#define BUF_SIZE_2KiB 2048
+
+#define SXGBE_DEFAULT_LIT_LS	0x3E8
+#define SXGBE_DEFAULT_TWT_LS	0x0
+
+/* Flow Control defines */
+#define SXGBE_FLOW_OFF		0
+#define SXGBE_FLOW_RX		1
+#define SXGBE_FLOW_TX		2
+#define SXGBE_FLOW_AUTO		(SXGBE_FLOW_TX | SXGBE_FLOW_RX)
+
+#define SF_DMA_MODE 1		/* DMA STORE-AND-FORWARD Operation Mode */
+
+/* errors */
+#define RX_GMII_ERR		0x01
+#define RX_WATCHDOG_ERR		0x02
+#define RX_CRC_ERR		0x03
+#define RX_GAINT_ERR		0x04
+#define RX_IP_HDR_ERR		0x05
+#define RX_PAYLOAD_ERR		0x06
+#define RX_OVERFLOW_ERR		0x07
+
+/* pkt type */
+#define RX_LEN_PKT		0x00
+#define RX_MACCTL_PKT		0x01
+#define RX_DCBCTL_PKT		0x02
+#define RX_ARP_PKT		0x03
+#define RX_OAM_PKT		0x04
+#define RX_UNTAG_PKT		0x05
+#define RX_OTHER_PKT		0x07
+#define RX_SVLAN_PKT		0x08
+#define RX_CVLAN_PKT		0x09
+#define RX_DVLAN_OCVLAN_ICVLAN_PKT		0x0A
+#define RX_DVLAN_OSVLAN_ISVLAN_PKT		0x0B
+#define RX_DVLAN_OSVLAN_ICVLAN_PKT		0x0C
+#define RX_DVLAN_OCVLAN_ISVLAN_PKT		0x0D
+
+#define RX_NOT_IP_PKT		0x00
+#define RX_IPV4_TCP_PKT		0x01
+#define RX_IPV4_UDP_PKT		0x02
+#define RX_IPV4_ICMP_PKT	0x03
+#define RX_IPV4_UNKNOWN_PKT	0x07
+#define RX_IPV6_TCP_PKT		0x09
+#define RX_IPV6_UDP_PKT		0x0A
+#define RX_IPV6_ICMP_PKT	0x0B
+#define RX_IPV6_UNKNOWN_PKT	0x0F
+
+#define RX_NO_PTP		0x00
+#define RX_PTP_SYNC		0x01
+#define RX_PTP_FOLLOW_UP	0x02
+#define RX_PTP_DELAY_REQ	0x03
+#define RX_PTP_DELAY_RESP	0x04
+#define RX_PTP_PDELAY_REQ	0x05
+#define RX_PTP_PDELAY_RESP	0x06
+#define RX_PTP_PDELAY_FOLLOW_UP	0x07
+#define RX_PTP_ANNOUNCE		0x08
+#define RX_PTP_MGMT		0x09
+#define RX_PTP_SIGNAL		0x0A
+#define RX_PTP_RESV_MSG		0x0F
+
+enum dma_irq_status {
+	tx_hard_error	= BIT(0),
+	tx_bump_tc	= BIT(1),
+	handle_tx	= BIT(2),
+	rx_hard_error	= BIT(3),
+	rx_bump_tc	= BIT(4),
+	handle_rx	= BIT(5),
+};
+
+#define NETIF_F_HW_VLAN_ALL     (NETIF_F_HW_VLAN_CTAG_RX |	\
+				 NETIF_F_HW_VLAN_STAG_RX |	\
+				 NETIF_F_HW_VLAN_CTAG_TX |	\
+				 NETIF_F_HW_VLAN_STAG_TX |	\
+				 NETIF_F_HW_VLAN_CTAG_FILTER |	\
+				 NETIF_F_HW_VLAN_STAG_FILTER)
+
+/* MMC control defines */
+#define SXGBE_MMC_CTRL_CNT_FRZ  0x00000008
+
+/* SXGBE HW ADDR regs */
+#define SXGBE_ADDR_HIGH(reg)    (((reg > 15) ? 0x00000800 : 0x00000040) + \
+				 (reg * 8))
+#define SXGBE_ADDR_LOW(reg)     (((reg > 15) ? 0x00000804 : 0x00000044) + \
+				 (reg * 8))
+#define SXGBE_MAX_PERFECT_ADDRESSES 32 /* Maximum unicast perfect filtering */
+#define SXGBE_FRAME_FILTER       0x00000004      /* Frame Filter */
+
+/* SXGBE Frame Filter defines */
+#define SXGBE_FRAME_FILTER_PR    0x00000001      /* Promiscuous Mode */
+#define SXGBE_FRAME_FILTER_HUC   0x00000002      /* Hash Unicast */
+#define SXGBE_FRAME_FILTER_HMC   0x00000004      /* Hash Multicast */
+#define SXGBE_FRAME_FILTER_DAIF  0x00000008      /* DA Inverse Filtering */
+#define SXGBE_FRAME_FILTER_PM    0x00000010      /* Pass all multicast */
+#define SXGBE_FRAME_FILTER_DBF   0x00000020      /* Disable Broadcast frames */
+#define SXGBE_FRAME_FILTER_SAIF  0x00000100      /* Inverse Filtering */
+#define SXGBE_FRAME_FILTER_SAF   0x00000200      /* Source Address Filter */
+#define SXGBE_FRAME_FILTER_HPF   0x00000400      /* Hash or perfect Filter */
+#define SXGBE_FRAME_FILTER_RA    0x80000000      /* Receive all mode */
+
+#define SXGBE_HASH_TABLE_SIZE    64
+#define SXGBE_HASH_HIGH          0x00000008      /* Multicast Hash Table High */
+#define SXGBE_HASH_LOW           0x0000000c      /* Multicast Hash Table Low */
+
+#define SXGBE_HI_REG_AE          0x80000000
+
+/* Minimum and maximum MTU */
+#define MIN_MTU         68
+#define MAX_MTU         9000
+
+#define SXGBE_FOR_EACH_QUEUE(max_queues, queue_num)			\
+	for (queue_num = 0; queue_num < max_queues; queue_num++)
+
+/* sxgbe statistics counters */
+struct sxgbe_extra_stats {
+	/* TX/RX IRQ events */
+	unsigned long tx_underflow_irq;
+	unsigned long tx_process_stopped_irq;
+	unsigned long tx_ctxt_desc_err;
+	unsigned long tx_threshold;
+	unsigned long rx_threshold;
+	unsigned long tx_pkt_n;
+	unsigned long rx_pkt_n;
+	unsigned long normal_irq_n;
+	unsigned long tx_normal_irq_n;
+	unsigned long rx_normal_irq_n;
+	unsigned long napi_poll;
+	unsigned long tx_clean;
+	unsigned long tx_reset_ic_bit;
+	unsigned long rx_process_stopped_irq;
+	unsigned long rx_underflow_irq;
+
+	/* Bus access errors */
+	unsigned long fatal_bus_error_irq;
+	unsigned long tx_read_transfer_err;
+	unsigned long tx_write_transfer_err;
+	unsigned long tx_desc_access_err;
+	unsigned long tx_buffer_access_err;
+	unsigned long tx_data_transfer_err;
+	unsigned long rx_read_transfer_err;
+	unsigned long rx_write_transfer_err;
+	unsigned long rx_desc_access_err;
+	unsigned long rx_buffer_access_err;
+	unsigned long rx_data_transfer_err;
+
+	/* RX specific */
+	/* L2 error */
+	unsigned long rx_code_gmii_err;
+	unsigned long rx_watchdog_err;
+	unsigned long rx_crc_err;
+	unsigned long rx_gaint_pkt_err;
+	unsigned long ip_hdr_err;
+	unsigned long ip_payload_err;
+	unsigned long overflow_error;
+
+	/* L2 Pkt type */
+	unsigned long len_pkt;
+	unsigned long mac_ctl_pkt;
+	unsigned long dcb_ctl_pkt;
+	unsigned long arp_pkt;
+	unsigned long oam_pkt;
+	unsigned long untag_okt;
+	unsigned long other_pkt;
+	unsigned long svlan_tag_pkt;
+	unsigned long cvlan_tag_pkt;
+	unsigned long dvlan_ocvlan_icvlan_pkt;
+	unsigned long dvlan_osvlan_isvlan_pkt;
+	unsigned long dvlan_osvlan_icvlan_pkt;
+	unsigned long dvan_ocvlan_icvlan_pkt;
+
+	/* L3/L4 Pkt type */
+	unsigned long not_ip_pkt;
+	unsigned long ip4_tcp_pkt;
+	unsigned long ip4_udp_pkt;
+	unsigned long ip4_icmp_pkt;
+	unsigned long ip4_unknown_pkt;
+	unsigned long ip6_tcp_pkt;
+	unsigned long ip6_udp_pkt;
+	unsigned long ip6_icmp_pkt;
+	unsigned long ip6_unknown_pkt;
+
+	/* Filter specific */
+	unsigned long vlan_filter_match;
+	unsigned long sa_filter_fail;
+	unsigned long da_filter_fail;
+	unsigned long hash_filter_pass;
+	unsigned long l3_filter_match;
+	unsigned long l4_filter_match;
+
+	/* RX context specific */
+	unsigned long timestamp_dropped;
+	unsigned long rx_msg_type_no_ptp;
+	unsigned long rx_ptp_type_sync;
+	unsigned long rx_ptp_type_follow_up;
+	unsigned long rx_ptp_type_delay_req;
+	unsigned long rx_ptp_type_delay_resp;
+	unsigned long rx_ptp_type_pdelay_req;
+	unsigned long rx_ptp_type_pdelay_resp;
+	unsigned long rx_ptp_type_pdelay_follow_up;
+	unsigned long rx_ptp_announce;
+	unsigned long rx_ptp_mgmt;
+	unsigned long rx_ptp_signal;
+	unsigned long rx_ptp_resv_msg_type;
+};
+
+struct mac_link {
+	int port;
+	int duplex;
+	int speed;
+};
+
+struct mii_regs {
+	unsigned int addr;	/* MII Address */
+	unsigned int data;	/* MII Data */
+};
+
+struct sxgbe_core_ops {
+	/* MAC core initialization */
+	void (*core_init)(void __iomem *ioaddr);
+	/* Dump MAC registers */
+	void (*dump_regs)(void __iomem *ioaddr);
+	/* Handle extra events on specific interrupts hw dependent */
+	int (*host_irq_status)(void __iomem *ioaddr,
+			       struct sxgbe_extra_stats *x);
+	/* Set power management mode (e.g. magic frame) */
+	void (*pmt)(void __iomem *ioaddr, unsigned long mode);
+	/* Set/Get Unicast MAC addresses */
+	void (*set_umac_addr)(void __iomem *ioaddr, unsigned char *addr,
+			      unsigned int reg_n);
+	void (*get_umac_addr)(void __iomem *ioaddr, unsigned char *addr,
+			      unsigned int reg_n);
+	void (*enable_rx)(void __iomem *ioaddr, bool enable);
+	void (*enable_tx)(void __iomem *ioaddr, bool enable);
+
+	/* controller version specific operations */
+	int (*get_controller_version)(void __iomem *ioaddr);
+
+	/* If supported then get the optional core features */
+	unsigned int (*get_hw_feature)(void __iomem *ioaddr,
+				       unsigned char feature_index);
+	/* adjust SXGBE speed */
+	void (*set_speed)(void __iomem *ioaddr, unsigned char speed);
+};
+
+const struct sxgbe_core_ops *sxgbe_get_core_ops(void);
+
+struct sxgbe_ops {
+	const struct sxgbe_core_ops *mac;
+	const struct sxgbe_desc_ops *desc;
+	const struct sxgbe_dma_ops *dma;
+	const struct sxgbe_mtl_ops *mtl;
+	struct mii_regs mii;	/* MII register Addresses */
+	struct mac_link link;
+	unsigned int ctrl_uid;
+	unsigned int ctrl_id;
+};
+
+/* SXGBE private data structures */
+struct sxgbe_tx_queue {
+	unsigned int irq_no;
+	struct sxgbe_priv_data *priv_ptr;
+	struct sxgbe_tx_norm_desc *dma_tx;
+	dma_addr_t dma_tx_phy;
+	dma_addr_t *tx_skbuff_dma;
+	struct sk_buff **tx_skbuff;
+	struct timer_list txtimer;
+	spinlock_t tx_lock;	/* lock for tx queues */
+	unsigned int cur_tx;
+	unsigned int dirty_tx;
+	u32 tx_count_frames;
+	u32 tx_coal_frames;
+	u32 tx_coal_timer;
+	int hwts_tx_en;
+	u8 queue_no;
+};
+
+struct sxgbe_rx_queue {
+	struct sxgbe_priv_data *priv_ptr;
+	struct sxgbe_rx_norm_desc *dma_rx;
+	struct sk_buff **rx_skbuff;
+	unsigned int cur_rx;
+	unsigned int dirty_rx;
+	unsigned int irq_no;
+	u32 rx_riwt;
+	dma_addr_t *rx_skbuff_dma;
+	dma_addr_t dma_rx_phy;
+	u8 queue_no;
+};
+
+/* SXGBE HW capabilities */
+struct sxgbe_hw_features {
+	/****** CAP [0] *******/
+	unsigned int pmt_remote_wake_up;
+	unsigned int pmt_magic_frame;
+	/* IEEE 1588-2008 */
+	unsigned int atime_stamp;
+
+	unsigned int tx_csum_offload;
+	unsigned int rx_csum_offload;
+	unsigned int multi_macaddr;
+	unsigned int tstamp_srcselect;
+	unsigned int sa_vlan_insert;
+
+	/****** CAP [1] *******/
+	unsigned int rxfifo_size;
+	unsigned int txfifo_size;
+	unsigned int atstmap_hword;
+	unsigned int dcb_enable;
+	unsigned int splithead_enable;
+	unsigned int tcpseg_offload;
+	unsigned int debug_mem;
+	unsigned int rss_enable;
+	unsigned int hash_tsize;
+	unsigned int l3l4_filer_size;
+
+	/* This value is in bytes and
+	 * as mentioned in HW features
+	 * of SXGBE data book
+	 */
+	unsigned int rx_mtl_qsize;
+	unsigned int tx_mtl_qsize;
+
+	/****** CAP [2] *******/
+	/* TX and RX number of channels */
+	unsigned int rx_mtl_queues;
+	unsigned int tx_mtl_queues;
+	unsigned int rx_dma_channels;
+	unsigned int tx_dma_channels;
+	unsigned int pps_output_count;
+	unsigned int aux_input_count;
+};
+
+struct sxgbe_priv_data {
+	/* DMA descriptos */
+	struct sxgbe_tx_queue *txq[SXGBE_TX_QUEUES];
+	struct sxgbe_rx_queue *rxq[SXGBE_RX_QUEUES];
+	u8 cur_rx_qnum;
+
+	unsigned int dma_tx_size;
+	unsigned int dma_rx_size;
+	unsigned int dma_buf_sz;
+	u32 rx_riwt;
+
+	struct napi_struct napi;
+
+	void __iomem *ioaddr;
+	struct net_device *dev;
+	struct device *device;
+	struct sxgbe_ops *hw;	/* sxgbe specific ops */
+	int no_csum_insertion;
+	int irq;
+	spinlock_t stats_lock;	/* lock for tx/rx statatics */
+
+	struct phy_device *phydev;
+	int oldlink;
+	int speed;
+	int oldduplex;
+	struct mii_bus *mii;
+	int mii_irq[PHY_MAX_ADDR];
+	u8 rx_pause;
+	u8 tx_pause;
+
+	struct sxgbe_extra_stats xstats;
+	struct sxgbe_plat_data *plat;
+	struct sxgbe_hw_features hw_cap;
+
+	u32 msg_enable;
+
+	struct clk *sxgbe_clk;
+	int clk_csr;
+	unsigned int mode;
+	unsigned int default_addend;
+
+	/* advanced time stamp support */
+	u32 adv_ts;
+	int use_riwt;
+
+	/* tc control */
+	int tx_tc;
+	int rx_tc;
+};
+
+/* Function prototypes */
+struct sxgbe_priv_data *sxgbe_drv_probe(struct device *device,
+					struct sxgbe_plat_data *plat_dat,
+					void __iomem *addr);
+int sxgbe_drv_remove(struct net_device *ndev);
+void sxgbe_set_ethtool_ops(struct net_device *netdev);
+int sxgbe_mdio_unregister(struct net_device *ndev);
+int sxgbe_mdio_register(struct net_device *ndev);
+int sxgbe_register_platform(void);
+void sxgbe_unregister_platform(void);
+
+#ifdef CONFIG_PM
+int sxgbe_suspend(struct net_device *ndev);
+int sxgbe_resume(struct net_device *ndev);
+int sxgbe_freeze(struct net_device *ndev);
+int sxgbe_restore(struct net_device *ndev);
+#endif /* CONFIG_PM */
+
+const struct sxgbe_mtl_ops *sxgbe_get_mtl_ops(void);
+
+#endif /* __SXGBE_COMMON_H__ */
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c
new file mode 100644
index 000000000000..4ad31bbc42c9
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c
@@ -0,0 +1,158 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/export.h>
+#include <linux/io.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+
+#include "sxgbe_common.h"
+#include "sxgbe_reg.h"
+
+/* MAC core initialization */
+static void sxgbe_core_init(void __iomem *ioaddr)
+{
+	u32 regval;
+
+	/* TX configuration */
+	regval = readl(ioaddr + SXGBE_CORE_TX_CONFIG_REG);
+	/* Other configurable parameters IFP, IPG, ISR, ISM
+	 * needs to be set if needed
+	 */
+	regval |= SXGBE_TX_JABBER_DISABLE;
+	writel(regval, ioaddr + SXGBE_CORE_TX_CONFIG_REG);
+
+	/* RX configuration */
+	regval = readl(ioaddr + SXGBE_CORE_RX_CONFIG_REG);
+	/* Other configurable parameters CST, SPEN, USP, GPSLCE
+	 * WD, LM, S2KP, HDSMS, GPSL, ELEN, ARPEN needs to be
+	 * set if needed
+	 */
+	regval |= SXGBE_RX_JUMBPKT_ENABLE | SXGBE_RX_ACS_ENABLE;
+	writel(regval, ioaddr + SXGBE_CORE_RX_CONFIG_REG);
+}
+
+/* Dump MAC registers */
+static void sxgbe_core_dump_regs(void __iomem *ioaddr)
+{
+}
+
+/* Handle extra events on specific interrupts hw dependent */
+static int sxgbe_core_host_irq_status(void __iomem *ioaddr,
+				      struct sxgbe_extra_stats *x)
+{
+	return 0;
+}
+
+/* Set power management mode (e.g. magic frame) */
+static void sxgbe_core_pmt(void __iomem *ioaddr, unsigned long mode)
+{
+}
+
+/* Set/Get Unicast MAC addresses */
+static void sxgbe_core_set_umac_addr(void __iomem *ioaddr, unsigned char *addr,
+				     unsigned int reg_n)
+{
+	u32 high_word, low_word;
+
+	high_word = (addr[5] << 8) || (addr[4]);
+	low_word = ((addr[3] << 24) || (addr[2] << 16) ||
+		    (addr[1] << 8) || (addr[0]));
+	writel(high_word, ioaddr + SXGBE_CORE_ADD_HIGHOFFSET(reg_n));
+	writel(low_word, ioaddr + SXGBE_CORE_ADD_LOWOFFSET(reg_n));
+}
+
+static void sxgbe_core_get_umac_addr(void __iomem *ioaddr, unsigned char *addr,
+				     unsigned int reg_n)
+{
+	u32 high_word, low_word;
+
+	high_word = readl(ioaddr + SXGBE_CORE_ADD_HIGHOFFSET(reg_n));
+	low_word = readl(ioaddr + SXGBE_CORE_ADD_LOWOFFSET(reg_n));
+
+	/* extract and assign address */
+	addr[5] = (high_word & 0x0000FF00) >> 8;
+	addr[4] = (high_word & 0x000000FF);
+	addr[3] = (low_word & 0xFF000000) >> 24;
+	addr[2] = (low_word & 0x00FF0000) >> 16;
+	addr[1] = (low_word & 0x0000FF00) >> 8;
+	addr[0] = (low_word & 0x000000FF);
+}
+
+static void sxgbe_enable_tx(void __iomem *ioaddr, bool enable)
+{
+	u32 tx_config;
+
+	tx_config = readl(ioaddr + SXGBE_CORE_TX_CONFIG_REG);
+	tx_config &= ~SXGBE_TX_ENABLE;
+
+	if (enable)
+		tx_config |= SXGBE_TX_ENABLE;
+	writel(tx_config, ioaddr + SXGBE_CORE_TX_CONFIG_REG);
+}
+
+static void sxgbe_enable_rx(void __iomem *ioaddr, bool enable)
+{
+	u32 rx_config;
+
+	rx_config = readl(ioaddr + SXGBE_CORE_RX_CONFIG_REG);
+	rx_config &= ~SXGBE_RX_ENABLE;
+
+	if (enable)
+		rx_config |= SXGBE_RX_ENABLE;
+	writel(rx_config, ioaddr + SXGBE_CORE_RX_CONFIG_REG);
+}
+
+static int sxgbe_get_controller_version(void __iomem *ioaddr)
+{
+	return readl(ioaddr + SXGBE_CORE_VERSION_REG);
+}
+
+/* If supported then get the optional core features */
+static unsigned int sxgbe_get_hw_feature(void __iomem *ioaddr,
+					 unsigned char feature_index)
+{
+	return readl(ioaddr + (SXGBE_CORE_HW_FEA_REG(feature_index)));
+}
+
+static void sxgbe_core_set_speed(void __iomem *ioaddr, unsigned char speed)
+{
+	u32 tx_cfg = readl(ioaddr + SXGBE_CORE_TX_CONFIG_REG);
+
+	/* clear the speed bits */
+	tx_cfg &= ~0x60000000;
+	tx_cfg |= (speed << SXGBE_SPEED_LSHIFT);
+
+	/* set the speed */
+	writel(tx_cfg, ioaddr + SXGBE_CORE_TX_CONFIG_REG);
+}
+
+const struct sxgbe_core_ops core_ops = {
+	.core_init		= sxgbe_core_init,
+	.dump_regs		= sxgbe_core_dump_regs,
+	.host_irq_status	= sxgbe_core_host_irq_status,
+	.pmt			= sxgbe_core_pmt,
+	.set_umac_addr		= sxgbe_core_set_umac_addr,
+	.get_umac_addr		= sxgbe_core_get_umac_addr,
+	.enable_rx		= sxgbe_enable_rx,
+	.enable_tx		= sxgbe_enable_tx,
+	.get_controller_version	= sxgbe_get_controller_version,
+	.get_hw_feature		= sxgbe_get_hw_feature,
+	.set_speed		= sxgbe_core_set_speed,
+};
+
+const struct sxgbe_core_ops *sxgbe_get_core_ops(void)
+{
+	return &core_ops;
+}
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.c
new file mode 100644
index 000000000000..7cb5520475b7
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.c
@@ -0,0 +1,515 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/bitops.h>
+#include <linux/export.h>
+#include <linux/io.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+
+#include "sxgbe_common.h"
+#include "sxgbe_dma.h"
+#include "sxgbe_desc.h"
+
+/* DMA TX descriptor ring initialization */
+static void sxgbe_init_tx_desc(struct sxgbe_tx_norm_desc *p)
+{
+	p->tdes23.tx_rd_des23.own_bit = 0;
+}
+
+static void sxgbe_tx_desc_enable_tse(struct sxgbe_tx_norm_desc *p, u8 is_tse,
+				     u32 total_hdr_len, u32 tcp_hdr_len,
+				     u32 tcp_payload_len)
+{
+	p->tdes23.tx_rd_des23.tse_bit = is_tse;
+	p->tdes23.tx_rd_des23.buf1_size = total_hdr_len;
+	p->tdes23.tx_rd_des23.tcp_hdr_len = tcp_hdr_len / 4;
+	p->tdes23.tx_rd_des23.tx_pkt_len.tcp_payload_len  = tcp_payload_len;
+}
+
+/* Assign buffer lengths for descriptor */
+static void sxgbe_prepare_tx_desc(struct sxgbe_tx_norm_desc *p, u8 is_fd,
+				  int buf1_len, int pkt_len, int cksum)
+{
+	p->tdes23.tx_rd_des23.first_desc = is_fd;
+	p->tdes23.tx_rd_des23.buf1_size = buf1_len;
+
+	p->tdes23.tx_rd_des23.tx_pkt_len.cksum_pktlen.total_pkt_len = pkt_len;
+
+	if (cksum)
+		p->tdes23.tx_rd_des23.tx_pkt_len.cksum_pktlen.cksum_ctl = cic_full;
+}
+
+/* Set VLAN control information */
+static void sxgbe_tx_vlanctl_desc(struct sxgbe_tx_norm_desc *p, int vlan_ctl)
+{
+	p->tdes23.tx_rd_des23.vlan_tag_ctl = vlan_ctl;
+}
+
+/* Set the owner of Normal descriptor */
+static void sxgbe_set_tx_owner(struct sxgbe_tx_norm_desc *p)
+{
+	p->tdes23.tx_rd_des23.own_bit = 1;
+}
+
+/* Get the owner of Normal descriptor */
+static int sxgbe_get_tx_owner(struct sxgbe_tx_norm_desc *p)
+{
+	return p->tdes23.tx_rd_des23.own_bit;
+}
+
+/* Invoked by the xmit function to close the tx descriptor */
+static void sxgbe_close_tx_desc(struct sxgbe_tx_norm_desc *p)
+{
+	p->tdes23.tx_rd_des23.last_desc = 1;
+	p->tdes23.tx_rd_des23.int_on_com = 1;
+}
+
+/* Clean the tx descriptor as soon as the tx irq is received */
+static void sxgbe_release_tx_desc(struct sxgbe_tx_norm_desc *p)
+{
+	memset(p, 0, sizeof(*p));
+}
+
+/* Clear interrupt on tx frame completion. When this bit is
+ * set an interrupt happens as soon as the frame is transmitted
+ */
+static void sxgbe_clear_tx_ic(struct sxgbe_tx_norm_desc *p)
+{
+	p->tdes23.tx_rd_des23.int_on_com = 0;
+}
+
+/* Last tx segment reports the transmit status */
+static int sxgbe_get_tx_ls(struct sxgbe_tx_norm_desc *p)
+{
+	return p->tdes23.tx_rd_des23.last_desc;
+}
+
+/* Get the buffer size from the descriptor */
+static int sxgbe_get_tx_len(struct sxgbe_tx_norm_desc *p)
+{
+	return p->tdes23.tx_rd_des23.buf1_size;
+}
+
+/* Set tx timestamp enable bit */
+static void sxgbe_tx_enable_tstamp(struct sxgbe_tx_norm_desc *p)
+{
+	p->tdes23.tx_rd_des23.timestmp_enable = 1;
+}
+
+/* get tx timestamp status */
+static int sxgbe_get_tx_timestamp_status(struct sxgbe_tx_norm_desc *p)
+{
+	return p->tdes23.tx_rd_des23.timestmp_enable;
+}
+
+/* TX Context Descripto Specific */
+static void sxgbe_tx_ctxt_desc_set_ctxt(struct sxgbe_tx_ctxt_desc *p)
+{
+	p->ctxt_bit = 1;
+}
+
+/* Set the owner of TX context descriptor */
+static void sxgbe_tx_ctxt_desc_set_owner(struct sxgbe_tx_ctxt_desc *p)
+{
+	p->own_bit = 1;
+}
+
+/* Get the owner of TX context descriptor */
+static int sxgbe_tx_ctxt_desc_get_owner(struct sxgbe_tx_ctxt_desc *p)
+{
+	return p->own_bit;
+}
+
+/* Set TX mss in TX context Descriptor */
+static void sxgbe_tx_ctxt_desc_set_mss(struct sxgbe_tx_ctxt_desc *p, int mss)
+{
+	p->maxseg_size = mss;
+}
+
+/* Get TX mss from TX context Descriptor */
+static int sxgbe_tx_ctxt_desc_get_mss(struct sxgbe_tx_ctxt_desc *p)
+{
+	return p->maxseg_size;
+}
+
+/* Set TX tcmssv in TX context Descriptor */
+static void sxgbe_tx_ctxt_desc_set_tcmssv(struct sxgbe_tx_ctxt_desc *p)
+{
+	p->tcmssv = 1;
+}
+
+/* Reset TX ostc in TX context Descriptor */
+static void sxgbe_tx_ctxt_desc_reset_ostc(struct sxgbe_tx_ctxt_desc *p)
+{
+	p->ostc = 0;
+}
+
+/* Set IVLAN information */
+static void sxgbe_tx_ctxt_desc_set_ivlantag(struct sxgbe_tx_ctxt_desc *p,
+					    int is_ivlanvalid, int ivlan_tag,
+					    int ivlan_ctl)
+{
+	if (is_ivlanvalid) {
+		p->ivlan_tag_valid = is_ivlanvalid;
+		p->ivlan_tag = ivlan_tag;
+		p->ivlan_tag_ctl = ivlan_ctl;
+	}
+}
+
+/* Return IVLAN Tag */
+static int sxgbe_tx_ctxt_desc_get_ivlantag(struct sxgbe_tx_ctxt_desc *p)
+{
+	return p->ivlan_tag;
+}
+
+/* Set VLAN Tag */
+static void sxgbe_tx_ctxt_desc_set_vlantag(struct sxgbe_tx_ctxt_desc *p,
+					   int is_vlanvalid, int vlan_tag)
+{
+	if (is_vlanvalid) {
+		p->vltag_valid = is_vlanvalid;
+		p->vlan_tag = vlan_tag;
+	}
+}
+
+/* Return VLAN Tag */
+static int sxgbe_tx_ctxt_desc_get_vlantag(struct sxgbe_tx_ctxt_desc *p)
+{
+	return p->vlan_tag;
+}
+
+/* Set Time stamp */
+static void sxgbe_tx_ctxt_desc_set_tstamp(struct sxgbe_tx_ctxt_desc *p,
+					  u8 ostc_enable, u64 tstamp)
+{
+	if (ostc_enable) {
+		p->ostc = ostc_enable;
+		p->tstamp_lo = (u32) tstamp;
+		p->tstamp_hi = (u32) (tstamp>>32);
+	}
+}
+/* Close TX context descriptor */
+static void sxgbe_tx_ctxt_desc_close(struct sxgbe_tx_ctxt_desc *p)
+{
+	p->own_bit = 1;
+}
+
+/* WB status of context descriptor */
+static int sxgbe_tx_ctxt_desc_get_cde(struct sxgbe_tx_ctxt_desc *p)
+{
+	return p->ctxt_desc_err;
+}
+
+/* DMA RX descriptor ring initialization */
+static void sxgbe_init_rx_desc(struct sxgbe_rx_norm_desc *p, int disable_rx_ic,
+			       int mode, int end)
+{
+	p->rdes23.rx_rd_des23.own_bit = 1;
+	if (disable_rx_ic)
+		p->rdes23.rx_rd_des23.int_on_com = disable_rx_ic;
+}
+
+/* Get RX own bit */
+static int sxgbe_get_rx_owner(struct sxgbe_rx_norm_desc *p)
+{
+	return p->rdes23.rx_rd_des23.own_bit;
+}
+
+/* Set RX own bit */
+static void sxgbe_set_rx_owner(struct sxgbe_rx_norm_desc *p)
+{
+	p->rdes23.rx_rd_des23.own_bit = 1;
+}
+
+/* Get the receive frame size */
+static int sxgbe_get_rx_frame_len(struct sxgbe_rx_norm_desc *p)
+{
+	return p->rdes23.rx_wb_des23.pkt_len;
+}
+
+/* Return first Descriptor status */
+static int sxgbe_get_rx_fd_status(struct sxgbe_rx_norm_desc *p)
+{
+	return p->rdes23.rx_wb_des23.first_desc;
+}
+
+/* Return Last Descriptor status */
+static int sxgbe_get_rx_ld_status(struct sxgbe_rx_norm_desc *p)
+{
+	return p->rdes23.rx_wb_des23.last_desc;
+}
+
+
+/* Return the RX status looking at the WB fields */
+static int sxgbe_rx_wbstatus(struct sxgbe_rx_norm_desc *p,
+			     struct sxgbe_extra_stats *x, int *checksum)
+{
+	int status = 0;
+
+	*checksum = CHECKSUM_UNNECESSARY;
+	if (p->rdes23.rx_wb_des23.err_summary) {
+		switch (p->rdes23.rx_wb_des23.err_l2_type) {
+		case RX_GMII_ERR:
+			status = -EINVAL;
+			x->rx_code_gmii_err++;
+			break;
+		case RX_WATCHDOG_ERR:
+			status = -EINVAL;
+			x->rx_watchdog_err++;
+			break;
+		case RX_CRC_ERR:
+			status = -EINVAL;
+			x->rx_crc_err++;
+			break;
+		case RX_GAINT_ERR:
+			status = -EINVAL;
+			x->rx_gaint_pkt_err++;
+			break;
+		case RX_IP_HDR_ERR:
+			*checksum = CHECKSUM_NONE;
+			x->ip_hdr_err++;
+			break;
+		case RX_PAYLOAD_ERR:
+			*checksum = CHECKSUM_NONE;
+			x->ip_payload_err++;
+			break;
+		case RX_OVERFLOW_ERR:
+			status = -EINVAL;
+			x->overflow_error++;
+			break;
+		default:
+			pr_err("Invalid Error type\n");
+			break;
+		}
+	} else {
+		switch (p->rdes23.rx_wb_des23.err_l2_type) {
+		case RX_LEN_PKT:
+			x->len_pkt++;
+			break;
+		case RX_MACCTL_PKT:
+			x->mac_ctl_pkt++;
+			break;
+		case RX_DCBCTL_PKT:
+			x->dcb_ctl_pkt++;
+			break;
+		case RX_ARP_PKT:
+			x->arp_pkt++;
+			break;
+		case RX_OAM_PKT:
+			x->oam_pkt++;
+			break;
+		case RX_UNTAG_PKT:
+			x->untag_okt++;
+			break;
+		case RX_OTHER_PKT:
+			x->other_pkt++;
+			break;
+		case RX_SVLAN_PKT:
+			x->svlan_tag_pkt++;
+			break;
+		case RX_CVLAN_PKT:
+			x->cvlan_tag_pkt++;
+			break;
+		case RX_DVLAN_OCVLAN_ICVLAN_PKT:
+			x->dvlan_ocvlan_icvlan_pkt++;
+			break;
+		case RX_DVLAN_OSVLAN_ISVLAN_PKT:
+			x->dvlan_osvlan_isvlan_pkt++;
+			break;
+		case RX_DVLAN_OSVLAN_ICVLAN_PKT:
+			x->dvlan_osvlan_icvlan_pkt++;
+			break;
+		case RX_DVLAN_OCVLAN_ISVLAN_PKT:
+			x->dvlan_ocvlan_icvlan_pkt++;
+			break;
+		default:
+			pr_err("Invalid L2 Packet type\n");
+			break;
+		}
+	}
+
+	/* L3/L4 Pkt type */
+	switch (p->rdes23.rx_wb_des23.layer34_pkt_type) {
+	case RX_NOT_IP_PKT:
+		x->not_ip_pkt++;
+		break;
+	case RX_IPV4_TCP_PKT:
+		x->ip4_tcp_pkt++;
+		break;
+	case RX_IPV4_UDP_PKT:
+		x->ip4_udp_pkt++;
+		break;
+	case RX_IPV4_ICMP_PKT:
+		x->ip4_icmp_pkt++;
+		break;
+	case RX_IPV4_UNKNOWN_PKT:
+		x->ip4_unknown_pkt++;
+		break;
+	case RX_IPV6_TCP_PKT:
+		x->ip6_tcp_pkt++;
+		break;
+	case RX_IPV6_UDP_PKT:
+		x->ip6_udp_pkt++;
+		break;
+	case RX_IPV6_ICMP_PKT:
+		x->ip6_icmp_pkt++;
+		break;
+	case RX_IPV6_UNKNOWN_PKT:
+		x->ip6_unknown_pkt++;
+		break;
+	default:
+		pr_err("Invalid L3/L4 Packet type\n");
+		break;
+	}
+
+	/* Filter */
+	if (p->rdes23.rx_wb_des23.vlan_filter_match)
+		x->vlan_filter_match++;
+
+	if (p->rdes23.rx_wb_des23.sa_filter_fail) {
+		status = -EINVAL;
+		x->sa_filter_fail++;
+	}
+	if (p->rdes23.rx_wb_des23.da_filter_fail) {
+		status = -EINVAL;
+		x->da_filter_fail++;
+	}
+	if (p->rdes23.rx_wb_des23.hash_filter_pass)
+		x->hash_filter_pass++;
+
+	if (p->rdes23.rx_wb_des23.l3_filter_match)
+		x->l3_filter_match++;
+
+	if (p->rdes23.rx_wb_des23.l4_filter_match)
+		x->l4_filter_match++;
+
+	return status;
+}
+
+/* Get own bit of context descriptor */
+static int sxgbe_get_rx_ctxt_owner(struct sxgbe_rx_ctxt_desc *p)
+{
+	return p->own_bit;
+}
+
+/* Set own bit for context descriptor */
+static void sxgbe_set_ctxt_rx_owner(struct sxgbe_rx_ctxt_desc *p)
+{
+	p->own_bit = 1;
+}
+
+
+/* Return the reception status looking at Context control information */
+static void sxgbe_rx_ctxt_wbstatus(struct sxgbe_rx_ctxt_desc *p,
+				   struct sxgbe_extra_stats *x)
+{
+	if (p->tstamp_dropped)
+		x->timestamp_dropped++;
+
+	/* ptp */
+	if (p->ptp_msgtype == RX_NO_PTP)
+		x->rx_msg_type_no_ptp++;
+	else if (p->ptp_msgtype == RX_PTP_SYNC)
+		x->rx_ptp_type_sync++;
+	else if (p->ptp_msgtype == RX_PTP_FOLLOW_UP)
+		x->rx_ptp_type_follow_up++;
+	else if (p->ptp_msgtype == RX_PTP_DELAY_REQ)
+		x->rx_ptp_type_delay_req++;
+	else if (p->ptp_msgtype == RX_PTP_DELAY_RESP)
+		x->rx_ptp_type_delay_resp++;
+	else if (p->ptp_msgtype == RX_PTP_PDELAY_REQ)
+		x->rx_ptp_type_pdelay_req++;
+	else if (p->ptp_msgtype == RX_PTP_PDELAY_RESP)
+		x->rx_ptp_type_pdelay_resp++;
+	else if (p->ptp_msgtype == RX_PTP_PDELAY_FOLLOW_UP)
+		x->rx_ptp_type_pdelay_follow_up++;
+	else if (p->ptp_msgtype == RX_PTP_ANNOUNCE)
+		x->rx_ptp_announce++;
+	else if (p->ptp_msgtype == RX_PTP_MGMT)
+		x->rx_ptp_mgmt++;
+	else if (p->ptp_msgtype == RX_PTP_SIGNAL)
+		x->rx_ptp_signal++;
+	else if (p->ptp_msgtype == RX_PTP_RESV_MSG)
+		x->rx_ptp_resv_msg_type++;
+}
+
+/* Get rx timestamp status */
+static int sxgbe_get_rx_ctxt_tstamp_status(struct sxgbe_rx_ctxt_desc *p)
+{
+	if ((p->tstamp_hi == 0xffffffff) && (p->tstamp_lo == 0xffffffff)) {
+		pr_err("Time stamp corrupted\n");
+		return 0;
+	}
+
+	return p->tstamp_available;
+}
+
+
+static u64 sxgbe_get_rx_timestamp(struct sxgbe_rx_ctxt_desc *p)
+{
+	u64 ns;
+
+	ns = p->tstamp_lo;
+	ns |= ((u64)p->tstamp_hi) << 32;
+
+	return ns;
+}
+
+static const struct sxgbe_desc_ops desc_ops = {
+	.init_tx_desc			= sxgbe_init_tx_desc,
+	.tx_desc_enable_tse		= sxgbe_tx_desc_enable_tse,
+	.prepare_tx_desc		= sxgbe_prepare_tx_desc,
+	.tx_vlanctl_desc		= sxgbe_tx_vlanctl_desc,
+	.set_tx_owner			= sxgbe_set_tx_owner,
+	.get_tx_owner			= sxgbe_get_tx_owner,
+	.close_tx_desc			= sxgbe_close_tx_desc,
+	.release_tx_desc		= sxgbe_release_tx_desc,
+	.clear_tx_ic			= sxgbe_clear_tx_ic,
+	.get_tx_ls			= sxgbe_get_tx_ls,
+	.get_tx_len			= sxgbe_get_tx_len,
+	.tx_enable_tstamp		= sxgbe_tx_enable_tstamp,
+	.get_tx_timestamp_status	= sxgbe_get_tx_timestamp_status,
+	.tx_ctxt_desc_set_ctxt		= sxgbe_tx_ctxt_desc_set_ctxt,
+	.tx_ctxt_desc_set_owner		= sxgbe_tx_ctxt_desc_set_owner,
+	.get_tx_ctxt_owner		= sxgbe_tx_ctxt_desc_get_owner,
+	.tx_ctxt_desc_set_mss		= sxgbe_tx_ctxt_desc_set_mss,
+	.tx_ctxt_desc_get_mss		= sxgbe_tx_ctxt_desc_get_mss,
+	.tx_ctxt_desc_set_tcmssv	= sxgbe_tx_ctxt_desc_set_tcmssv,
+	.tx_ctxt_desc_reset_ostc	= sxgbe_tx_ctxt_desc_reset_ostc,
+	.tx_ctxt_desc_set_ivlantag	= sxgbe_tx_ctxt_desc_set_ivlantag,
+	.tx_ctxt_desc_get_ivlantag	= sxgbe_tx_ctxt_desc_get_ivlantag,
+	.tx_ctxt_desc_set_vlantag	= sxgbe_tx_ctxt_desc_set_vlantag,
+	.tx_ctxt_desc_get_vlantag	= sxgbe_tx_ctxt_desc_get_vlantag,
+	.tx_ctxt_set_tstamp		= sxgbe_tx_ctxt_desc_set_tstamp,
+	.close_tx_ctxt_desc		= sxgbe_tx_ctxt_desc_close,
+	.get_tx_ctxt_cde		= sxgbe_tx_ctxt_desc_get_cde,
+	.init_rx_desc			= sxgbe_init_rx_desc,
+	.get_rx_owner			= sxgbe_get_rx_owner,
+	.set_rx_owner			= sxgbe_set_rx_owner,
+	.get_rx_frame_len		= sxgbe_get_rx_frame_len,
+	.get_rx_fd_status		= sxgbe_get_rx_fd_status,
+	.get_rx_ld_status		= sxgbe_get_rx_ld_status,
+	.rx_wbstatus			= sxgbe_rx_wbstatus,
+	.get_rx_ctxt_owner		= sxgbe_get_rx_ctxt_owner,
+	.set_rx_ctxt_owner		= sxgbe_set_ctxt_rx_owner,
+	.rx_ctxt_wbstatus		= sxgbe_rx_ctxt_wbstatus,
+	.get_rx_ctxt_tstamp_status	= sxgbe_get_rx_ctxt_tstamp_status,
+	.get_timestamp			= sxgbe_get_rx_timestamp,
+};
+
+const struct sxgbe_desc_ops *sxgbe_get_desc_ops(void)
+{
+	return &desc_ops;
+}
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.h
new file mode 100644
index 000000000000..2caef1ae1ac5
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_desc.h
@@ -0,0 +1,298 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __SXGBE_DESC_H__
+#define __SXGBE_DESC_H__
+
+#define SXGBE_DESC_SIZE_BYTES	16
+
+/* forward declaration */
+struct sxgbe_extra_stats;
+
+/* Transmit checksum insertion control */
+enum tdes_csum_insertion {
+	cic_disabled		= 0,	/* Checksum Insertion Control */
+	cic_only_ip		= 1,	/* Only IP header */
+	/* IP header but pseudoheader is not calculated */
+	cic_no_pseudoheader	= 2,
+	cic_full		= 3,	/* IP header and pseudoheader */
+};
+
+struct sxgbe_tx_norm_desc {
+	u64 tdes01; /* buf1 address */
+	union {
+		/* TX Read-Format Desc 2,3 */
+		struct {
+			/* TDES2 */
+			u32 buf1_size:14;
+			u32 vlan_tag_ctl:2;
+			u32 buf2_size:14;
+			u32 timestmp_enable:1;
+			u32 int_on_com:1;
+			/* TDES3 */
+			union {
+				u32 tcp_payload_len:18;
+				struct {
+					u32 total_pkt_len:15;
+					u32 reserved1:1;
+					u32 cksum_ctl:2;
+				} cksum_pktlen;
+			} tx_pkt_len;
+
+			u32 tse_bit:1;
+			u32 tcp_hdr_len:4;
+			u32 sa_insert_ctl:3;
+			u32 crc_pad_ctl:2;
+			u32 last_desc:1;
+			u32 first_desc:1;
+			u32 ctxt_bit:1;
+			u32 own_bit:1;
+		} tx_rd_des23;
+
+		/* tx write back Desc 2,3 */
+		struct {
+			/* WB TES2 */
+			u32 reserved1;
+			/* WB TES3 */
+			u32 reserved2:31;
+			u32 own_bit:1;
+		} tx_wb_des23;
+	} tdes23;
+};
+
+struct sxgbe_rx_norm_desc {
+	union {
+		u32 rdes0; /* buf1 address */
+		struct {
+			u32 out_vlan_tag:16;
+			u32 in_vlan_tag:16;
+		} wb_rx_des0;
+	} rd_wb_des0;
+
+	union {
+		u32 rdes1;	/* buf2 address or buf1[63:32] */
+		u32 rss_hash;	/* Write-back RX */
+	} rd_wb_des1;
+
+	union {
+		/* RX Read format Desc 2,3 */
+		struct{
+			/* RDES2 */
+			u32 buf2_addr;
+			/* RDES3 */
+			u32 buf2_hi_addr:30;
+			u32 int_on_com:1;
+			u32 own_bit:1;
+		} rx_rd_des23;
+
+		/* RX write back */
+		struct{
+			/* WB RDES2 */
+			u32 hdr_len:10;
+			u32 rdes2_reserved:2;
+			u32 elrd_val:1;
+			u32 iovt_sel:1;
+			u32 res_pkt:1;
+			u32 vlan_filter_match:1;
+			u32 sa_filter_fail:1;
+			u32 da_filter_fail:1;
+			u32 hash_filter_pass:1;
+			u32 macaddr_filter_match:8;
+			u32 l3_filter_match:1;
+			u32 l4_filter_match:1;
+			u32 l34_filter_num:3;
+
+			/* WB RDES3 */
+			u32 pkt_len:14;
+			u32 rdes3_reserved:1;
+			u32 err_summary:15;
+			u32 err_l2_type:4;
+			u32 layer34_pkt_type:4;
+			u32 no_coagulation_pkt:1;
+			u32 in_seq_pkt:1;
+			u32 rss_valid:1;
+			u32 context_des_avail:1;
+			u32 last_desc:1;
+			u32 first_desc:1;
+			u32 recv_context_desc:1;
+			u32 own_bit:1;
+		} rx_wb_des23;
+	} rdes23;
+};
+
+/* Context descriptor structure */
+struct sxgbe_tx_ctxt_desc {
+	u32 tstamp_lo;
+	u32 tstamp_hi;
+	u32 maxseg_size:15;
+	u32 reserved1:1;
+	u32 ivlan_tag:16;
+	u32 vlan_tag:16;
+	u32 vltag_valid:1;
+	u32 ivlan_tag_valid:1;
+	u32 ivlan_tag_ctl:2;
+	u32 reserved2:3;
+	u32 ctxt_desc_err:1;
+	u32 reserved3:2;
+	u32 ostc:1;
+	u32 tcmssv:1;
+	u32 reserved4:2;
+	u32 ctxt_bit:1;
+	u32 own_bit:1;
+};
+
+struct sxgbe_rx_ctxt_desc {
+	u32 tstamp_lo;
+	u32 tstamp_hi;
+	u32 reserved1;
+	u32 ptp_msgtype:4;
+	u32 tstamp_available:1;
+	u32 ptp_rsp_err:1;
+	u32 tstamp_dropped:1;
+	u32 reserved2:23;
+	u32 rx_ctxt_desc:1;
+	u32 own_bit:1;
+};
+
+struct sxgbe_desc_ops {
+	/* DMA TX descriptor ring initialization */
+	void (*init_tx_desc)(struct sxgbe_tx_norm_desc *p);
+
+	/* Invoked by the xmit function to prepare the tx descriptor */
+	void (*tx_desc_enable_tse)(struct sxgbe_tx_norm_desc *p, u8 is_tse,
+				   u32 total_hdr_len, u32 payload_len,
+				   u32 tcp_payload_len);
+
+	/* Assign buffer lengths for descriptor */
+	void (*prepare_tx_desc)(struct sxgbe_tx_norm_desc *p, u8 is_fd,
+				int buf1_len, int pkt_len, int cksum);
+
+	/* Set VLAN control information */
+	void (*tx_vlanctl_desc)(struct sxgbe_tx_norm_desc *p, int vlan_ctl);
+
+	/* Set the owner of the descriptor */
+	void (*set_tx_owner)(struct sxgbe_tx_norm_desc *p);
+
+	/* Get the owner of the descriptor */
+	int (*get_tx_owner)(struct sxgbe_tx_norm_desc *p);
+
+	/* Invoked by the xmit function to close the tx descriptor */
+	void (*close_tx_desc)(struct sxgbe_tx_norm_desc *p);
+
+	/* Clean the tx descriptor as soon as the tx irq is received */
+	void (*release_tx_desc)(struct sxgbe_tx_norm_desc *p);
+
+	/* Clear interrupt on tx frame completion. When this bit is
+	 * set an interrupt happens as soon as the frame is transmitted
+	 */
+	void (*clear_tx_ic)(struct sxgbe_tx_norm_desc *p);
+
+	/* Last tx segment reports the transmit status */
+	int (*get_tx_ls)(struct sxgbe_tx_norm_desc *p);
+
+	/* Get the buffer size from the descriptor */
+	int (*get_tx_len)(struct sxgbe_tx_norm_desc *p);
+
+	/* Set tx timestamp enable bit */
+	void (*tx_enable_tstamp)(struct sxgbe_tx_norm_desc *p);
+
+	/* get tx timestamp status */
+	int (*get_tx_timestamp_status)(struct sxgbe_tx_norm_desc *p);
+
+	/* TX Context Descripto Specific */
+	void (*tx_ctxt_desc_set_ctxt)(struct sxgbe_tx_ctxt_desc *p);
+
+	/* Set the owner of the TX context descriptor */
+	void (*tx_ctxt_desc_set_owner)(struct sxgbe_tx_ctxt_desc *p);
+
+	/* Get the owner of the TX context descriptor */
+	int (*get_tx_ctxt_owner)(struct sxgbe_tx_ctxt_desc *p);
+
+	/* Set TX mss */
+	void (*tx_ctxt_desc_set_mss)(struct sxgbe_tx_ctxt_desc *p, int mss);
+
+	/* Set TX mss */
+	int (*tx_ctxt_desc_get_mss)(struct sxgbe_tx_ctxt_desc *p);
+
+	/* Set TX tcmssv */
+	void (*tx_ctxt_desc_set_tcmssv)(struct sxgbe_tx_ctxt_desc *p);
+
+	/* Reset TX ostc */
+	void (*tx_ctxt_desc_reset_ostc)(struct sxgbe_tx_ctxt_desc *p);
+
+	/* Set IVLAN information */
+	void (*tx_ctxt_desc_set_ivlantag)(struct sxgbe_tx_ctxt_desc *p,
+					  int is_ivlanvalid, int ivlan_tag,
+					  int ivlan_ctl);
+
+	/* Return IVLAN Tag */
+	int (*tx_ctxt_desc_get_ivlantag)(struct sxgbe_tx_ctxt_desc *p);
+
+	/* Set VLAN Tag */
+	void (*tx_ctxt_desc_set_vlantag)(struct sxgbe_tx_ctxt_desc *p,
+					 int is_vlanvalid, int vlan_tag);
+
+	/* Return VLAN Tag */
+	int (*tx_ctxt_desc_get_vlantag)(struct sxgbe_tx_ctxt_desc *p);
+
+	/* Set Time stamp */
+	void (*tx_ctxt_set_tstamp)(struct sxgbe_tx_ctxt_desc *p,
+				   u8 ostc_enable, u64 tstamp);
+
+	/* Close TX context descriptor */
+	void (*close_tx_ctxt_desc)(struct sxgbe_tx_ctxt_desc *p);
+
+	/* WB status of context descriptor */
+	int (*get_tx_ctxt_cde)(struct sxgbe_tx_ctxt_desc *p);
+
+	/* DMA RX descriptor ring initialization */
+	void (*init_rx_desc)(struct sxgbe_rx_norm_desc *p, int disable_rx_ic,
+			     int mode, int end);
+
+	/* Get own bit */
+	int (*get_rx_owner)(struct sxgbe_rx_norm_desc *p);
+
+	/* Set own bit */
+	void (*set_rx_owner)(struct sxgbe_rx_norm_desc *p);
+
+	/* Get the receive frame size */
+	int (*get_rx_frame_len)(struct sxgbe_rx_norm_desc *p);
+
+	/* Return first Descriptor status */
+	int (*get_rx_fd_status)(struct sxgbe_rx_norm_desc *p);
+
+	/* Return first Descriptor status */
+	int (*get_rx_ld_status)(struct sxgbe_rx_norm_desc *p);
+
+	/* Return the reception status looking at the RDES1 */
+	int (*rx_wbstatus)(struct sxgbe_rx_norm_desc *p,
+			   struct sxgbe_extra_stats *x, int *checksum);
+
+	/* Get own bit */
+	int (*get_rx_ctxt_owner)(struct sxgbe_rx_ctxt_desc *p);
+
+	/* Set own bit */
+	void (*set_rx_ctxt_owner)(struct sxgbe_rx_ctxt_desc *p);
+
+	/* Return the reception status looking at Context control information */
+	void (*rx_ctxt_wbstatus)(struct sxgbe_rx_ctxt_desc *p,
+				 struct sxgbe_extra_stats *x);
+
+	/* Get rx timestamp status */
+	int (*get_rx_ctxt_tstamp_status)(struct sxgbe_rx_ctxt_desc *p);
+
+	/* Get timestamp value for rx, need to check this */
+	u64 (*get_timestamp)(struct sxgbe_rx_ctxt_desc *p);
+};
+
+const struct sxgbe_desc_ops *sxgbe_get_desc_ops(void);
+
+#endif /* __SXGBE_DESC_H__ */
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.c
new file mode 100644
index 000000000000..59d2d3976277
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.c
@@ -0,0 +1,372 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/io.h>
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/io.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+
+#include "sxgbe_common.h"
+#include "sxgbe_dma.h"
+#include "sxgbe_reg.h"
+#include "sxgbe_desc.h"
+
+/* DMA core initialization */
+static int sxgbe_dma_init(void __iomem *ioaddr, int fix_burst, int burst_map)
+{
+	int retry_count = 10;
+	u32 reg_val;
+
+	/* reset the DMA */
+	writel(SXGBE_DMA_SOFT_RESET, ioaddr + SXGBE_DMA_MODE_REG);
+	while (retry_count--) {
+		if (!(readl(ioaddr + SXGBE_DMA_MODE_REG) &
+		      SXGBE_DMA_SOFT_RESET))
+			break;
+		mdelay(10);
+	}
+
+	if (retry_count < 0)
+		return -EBUSY;
+
+	reg_val = readl(ioaddr + SXGBE_DMA_SYSBUS_MODE_REG);
+
+	/* if fix_burst = 0, Set UNDEF = 1 of DMA_Sys_Mode Register.
+	 * if fix_burst = 1, Set UNDEF = 0 of DMA_Sys_Mode Register.
+	 * burst_map is bitmap for  BLEN[4, 8, 16, 32, 64, 128 and 256].
+	 * Set burst_map irrespective of fix_burst value.
+	 */
+	if (!fix_burst)
+		reg_val |= SXGBE_DMA_AXI_UNDEF_BURST;
+
+	/* write burst len map */
+	reg_val |= (burst_map << SXGBE_DMA_BLENMAP_LSHIFT);
+
+	writel(reg_val,	ioaddr + SXGBE_DMA_SYSBUS_MODE_REG);
+
+	return 0;
+}
+
+static void sxgbe_dma_channel_init(void __iomem *ioaddr, int cha_num,
+				   int fix_burst, int pbl, dma_addr_t dma_tx,
+				   dma_addr_t dma_rx, int t_rsize, int r_rsize)
+{
+	u32 reg_val;
+	dma_addr_t dma_addr;
+
+	reg_val = readl(ioaddr + SXGBE_DMA_CHA_CTL_REG(cha_num));
+	/* set the pbl */
+	if (fix_burst) {
+		reg_val |= SXGBE_DMA_PBL_X8MODE;
+		writel(reg_val, ioaddr + SXGBE_DMA_CHA_CTL_REG(cha_num));
+		/* program the TX pbl */
+		reg_val = readl(ioaddr + SXGBE_DMA_CHA_TXCTL_REG(cha_num));
+		reg_val |= (pbl << SXGBE_DMA_TXPBL_LSHIFT);
+		writel(reg_val, ioaddr + SXGBE_DMA_CHA_TXCTL_REG(cha_num));
+		/* program the RX pbl */
+		reg_val = readl(ioaddr + SXGBE_DMA_CHA_RXCTL_REG(cha_num));
+		reg_val |= (pbl << SXGBE_DMA_RXPBL_LSHIFT);
+		writel(reg_val, ioaddr + SXGBE_DMA_CHA_RXCTL_REG(cha_num));
+	}
+
+	/* program desc registers */
+	writel(upper_32_bits(dma_tx),
+	       ioaddr + SXGBE_DMA_CHA_TXDESC_HADD_REG(cha_num));
+	writel(lower_32_bits(dma_tx),
+	       ioaddr + SXGBE_DMA_CHA_TXDESC_LADD_REG(cha_num));
+
+	writel(upper_32_bits(dma_rx),
+	       ioaddr + SXGBE_DMA_CHA_RXDESC_HADD_REG(cha_num));
+	writel(lower_32_bits(dma_rx),
+	       ioaddr + SXGBE_DMA_CHA_RXDESC_LADD_REG(cha_num));
+
+	/* program tail pointers */
+	/* assumption: upper 32 bits are constant and
+	 * same as TX/RX desc list
+	 */
+	dma_addr = dma_tx + ((t_rsize - 1) * SXGBE_DESC_SIZE_BYTES);
+	writel(lower_32_bits(dma_addr),
+	       ioaddr + SXGBE_DMA_CHA_TXDESC_TAILPTR_REG(cha_num));
+
+	dma_addr = dma_rx + ((r_rsize - 1) * SXGBE_DESC_SIZE_BYTES);
+	writel(lower_32_bits(dma_addr),
+	       ioaddr + SXGBE_DMA_CHA_RXDESC_LADD_REG(cha_num));
+	/* program the ring sizes */
+	writel(t_rsize - 1, ioaddr + SXGBE_DMA_CHA_TXDESC_RINGLEN_REG(cha_num));
+	writel(r_rsize - 1, ioaddr + SXGBE_DMA_CHA_RXDESC_RINGLEN_REG(cha_num));
+
+	/* Enable TX/RX interrupts */
+	writel(SXGBE_DMA_ENA_INT,
+	       ioaddr + SXGBE_DMA_CHA_INT_ENABLE_REG(cha_num));
+}
+
+static void sxgbe_enable_dma_transmission(void __iomem *ioaddr, int cha_num)
+{
+	u32 tx_config;
+
+	tx_config = readl(ioaddr + SXGBE_DMA_CHA_TXCTL_REG(cha_num));
+	tx_config |= SXGBE_TX_START_DMA;
+	writel(tx_config, ioaddr + SXGBE_DMA_CHA_TXCTL_REG(cha_num));
+}
+
+static void sxgbe_enable_dma_irq(void __iomem *ioaddr, int dma_cnum)
+{
+	/* Enable TX/RX interrupts */
+	writel(SXGBE_DMA_ENA_INT,
+	       ioaddr + SXGBE_DMA_CHA_INT_ENABLE_REG(dma_cnum));
+}
+
+static void sxgbe_disable_dma_irq(void __iomem *ioaddr, int dma_cnum)
+{
+	/* Disable TX/RX interrupts */
+	writel(0, ioaddr + SXGBE_DMA_CHA_INT_ENABLE_REG(dma_cnum));
+}
+
+static void sxgbe_dma_start_tx(void __iomem *ioaddr, int tchannels)
+{
+	int cnum;
+	u32 tx_ctl_reg;
+
+	for (cnum = 0; cnum < tchannels; cnum++) {
+		tx_ctl_reg = readl(ioaddr + SXGBE_DMA_CHA_TXCTL_REG(cnum));
+		tx_ctl_reg |= SXGBE_TX_ENABLE;
+		writel(tx_ctl_reg,
+		       ioaddr + SXGBE_DMA_CHA_TXCTL_REG(cnum));
+	}
+}
+
+static void sxgbe_dma_start_tx_queue(void __iomem *ioaddr, int dma_cnum)
+{
+	u32 tx_ctl_reg;
+
+	tx_ctl_reg = readl(ioaddr + SXGBE_DMA_CHA_TXCTL_REG(dma_cnum));
+	tx_ctl_reg |= SXGBE_TX_ENABLE;
+	writel(tx_ctl_reg, ioaddr + SXGBE_DMA_CHA_TXCTL_REG(dma_cnum));
+}
+
+static void sxgbe_dma_stop_tx_queue(void __iomem *ioaddr, int dma_cnum)
+{
+	u32 tx_ctl_reg;
+
+	tx_ctl_reg = readl(ioaddr + SXGBE_DMA_CHA_TXCTL_REG(dma_cnum));
+	tx_ctl_reg &= ~(SXGBE_TX_ENABLE);
+	writel(tx_ctl_reg, ioaddr + SXGBE_DMA_CHA_TXCTL_REG(dma_cnum));
+}
+
+static void sxgbe_dma_stop_tx(void __iomem *ioaddr, int tchannels)
+{
+	int cnum;
+	u32 tx_ctl_reg;
+
+	for (cnum = 0; cnum < tchannels; cnum++) {
+		tx_ctl_reg = readl(ioaddr + SXGBE_DMA_CHA_TXCTL_REG(cnum));
+		tx_ctl_reg &= ~(SXGBE_TX_ENABLE);
+		writel(tx_ctl_reg, ioaddr + SXGBE_DMA_CHA_TXCTL_REG(cnum));
+	}
+}
+
+static void sxgbe_dma_start_rx(void __iomem *ioaddr, int rchannels)
+{
+	int cnum;
+	u32 rx_ctl_reg;
+
+	for (cnum = 0; cnum < rchannels; cnum++) {
+		rx_ctl_reg = readl(ioaddr + SXGBE_DMA_CHA_RXCTL_REG(cnum));
+		rx_ctl_reg |= SXGBE_RX_ENABLE;
+		writel(rx_ctl_reg,
+		       ioaddr + SXGBE_DMA_CHA_RXCTL_REG(cnum));
+	}
+}
+
+static void sxgbe_dma_stop_rx(void __iomem *ioaddr, int rchannels)
+{
+	int cnum;
+	u32 rx_ctl_reg;
+
+	for (cnum = 0; cnum < rchannels; cnum++) {
+		rx_ctl_reg = readl(ioaddr + SXGBE_DMA_CHA_RXCTL_REG(cnum));
+		rx_ctl_reg &= ~(SXGBE_RX_ENABLE);
+		writel(rx_ctl_reg, ioaddr + SXGBE_DMA_CHA_RXCTL_REG(cnum));
+	}
+}
+
+static int sxgbe_tx_dma_int_status(void __iomem *ioaddr, int channel_no,
+				   struct sxgbe_extra_stats *x)
+{
+	u32 int_status = readl(ioaddr + SXGBE_DMA_CHA_STATUS_REG(channel_no));
+	u32 clear_val = 0;
+	u32 ret_val = 0;
+
+	/* TX Normal Interrupt Summary */
+	if (likely(int_status & SXGBE_DMA_INT_STATUS_NIS)) {
+		x->normal_irq_n++;
+		if (int_status & SXGBE_DMA_INT_STATUS_TI) {
+			ret_val |= handle_tx;
+			x->tx_normal_irq_n++;
+			clear_val |= SXGBE_DMA_INT_STATUS_TI;
+		}
+
+		if (int_status & SXGBE_DMA_INT_STATUS_TBU) {
+			x->tx_underflow_irq++;
+			ret_val |= tx_bump_tc;
+			clear_val |= SXGBE_DMA_INT_STATUS_TBU;
+		}
+	} else if (unlikely(int_status & SXGBE_DMA_INT_STATUS_AIS)) {
+		/* TX Abnormal Interrupt Summary */
+		if (int_status & SXGBE_DMA_INT_STATUS_TPS) {
+			ret_val |= tx_hard_error;
+			clear_val |= SXGBE_DMA_INT_STATUS_TPS;
+			x->tx_process_stopped_irq++;
+		}
+
+		if (int_status & SXGBE_DMA_INT_STATUS_FBE) {
+			ret_val |= tx_hard_error;
+			x->fatal_bus_error_irq++;
+
+			/* Assumption: FBE bit is the combination of
+			 * all the bus access erros and cleared when
+			 * the respective error bits cleared
+			 */
+
+			/* check for actual cause */
+			if (int_status & SXGBE_DMA_INT_STATUS_TEB0) {
+				x->tx_read_transfer_err++;
+				clear_val |= SXGBE_DMA_INT_STATUS_TEB0;
+			} else {
+				x->tx_write_transfer_err++;
+			}
+
+			if (int_status & SXGBE_DMA_INT_STATUS_TEB1) {
+				x->tx_desc_access_err++;
+				clear_val |= SXGBE_DMA_INT_STATUS_TEB1;
+			} else {
+				x->tx_buffer_access_err++;
+			}
+
+			if (int_status & SXGBE_DMA_INT_STATUS_TEB2) {
+				x->tx_data_transfer_err++;
+				clear_val |= SXGBE_DMA_INT_STATUS_TEB2;
+			}
+		}
+
+		/* context descriptor error */
+		if (int_status & SXGBE_DMA_INT_STATUS_CTXTERR) {
+			x->tx_ctxt_desc_err++;
+			clear_val |= SXGBE_DMA_INT_STATUS_CTXTERR;
+		}
+	}
+
+	/* clear the served bits */
+	writel(clear_val, ioaddr + SXGBE_DMA_CHA_STATUS_REG(channel_no));
+
+	return ret_val;
+}
+
+static int sxgbe_rx_dma_int_status(void __iomem *ioaddr, int channel_no,
+				   struct sxgbe_extra_stats *x)
+{
+	u32 int_status = readl(ioaddr + SXGBE_DMA_CHA_STATUS_REG(channel_no));
+	u32 clear_val = 0;
+	u32 ret_val = 0;
+
+	/* RX Normal Interrupt Summary */
+	if (likely(int_status & SXGBE_DMA_INT_STATUS_NIS)) {
+		x->normal_irq_n++;
+		if (int_status & SXGBE_DMA_INT_STATUS_RI) {
+			ret_val |= handle_rx;
+			x->rx_normal_irq_n++;
+			clear_val |= SXGBE_DMA_INT_STATUS_RI;
+		}
+	} else if (unlikely(int_status & SXGBE_DMA_INT_STATUS_AIS)) {
+		/* RX Abnormal Interrupt Summary */
+		if (int_status & SXGBE_DMA_INT_STATUS_RBU) {
+			ret_val |= rx_bump_tc;
+			clear_val |= SXGBE_DMA_INT_STATUS_RBU;
+			x->rx_underflow_irq++;
+		}
+
+		if (int_status & SXGBE_DMA_INT_STATUS_RPS) {
+			ret_val |= rx_hard_error;
+			clear_val |= SXGBE_DMA_INT_STATUS_RPS;
+			x->rx_process_stopped_irq++;
+		}
+
+		if (int_status & SXGBE_DMA_INT_STATUS_FBE) {
+			ret_val |= rx_hard_error;
+			x->fatal_bus_error_irq++;
+
+			/* Assumption: FBE bit is the combination of
+			 * all the bus access erros and cleared when
+			 * the respective error bits cleared
+			 */
+
+			/* check for actual cause */
+			if (int_status & SXGBE_DMA_INT_STATUS_REB0) {
+				x->rx_read_transfer_err++;
+				clear_val |= SXGBE_DMA_INT_STATUS_REB0;
+			} else {
+				x->rx_write_transfer_err++;
+			}
+
+			if (int_status & SXGBE_DMA_INT_STATUS_REB1) {
+				x->rx_desc_access_err++;
+				clear_val |= SXGBE_DMA_INT_STATUS_REB1;
+			} else {
+				x->rx_buffer_access_err++;
+			}
+
+			if (int_status & SXGBE_DMA_INT_STATUS_REB2) {
+				x->rx_data_transfer_err++;
+				clear_val |= SXGBE_DMA_INT_STATUS_REB2;
+			}
+		}
+	}
+
+	/* clear the served bits */
+	writel(clear_val, ioaddr + SXGBE_DMA_CHA_STATUS_REG(channel_no));
+
+	return ret_val;
+}
+
+/* Program the HW RX Watchdog */
+static void sxgbe_dma_rx_watchdog(void __iomem *ioaddr, u32 riwt)
+{
+	u32 que_num;
+
+	SXGBE_FOR_EACH_QUEUE(SXGBE_RX_QUEUES, que_num) {
+		writel(riwt,
+		       ioaddr + SXGBE_DMA_CHA_INT_RXWATCHTMR_REG(que_num));
+	}
+}
+
+static const struct sxgbe_dma_ops sxgbe_dma_ops = {
+	.init				= sxgbe_dma_init,
+	.cha_init			= sxgbe_dma_channel_init,
+	.enable_dma_transmission	= sxgbe_enable_dma_transmission,
+	.enable_dma_irq			= sxgbe_enable_dma_irq,
+	.disable_dma_irq		= sxgbe_disable_dma_irq,
+	.start_tx			= sxgbe_dma_start_tx,
+	.start_tx_queue			= sxgbe_dma_start_tx_queue,
+	.stop_tx			= sxgbe_dma_stop_tx,
+	.stop_tx_queue			= sxgbe_dma_stop_tx_queue,
+	.start_rx			= sxgbe_dma_start_rx,
+	.stop_rx			= sxgbe_dma_stop_rx,
+	.tx_dma_int_status		= sxgbe_tx_dma_int_status,
+	.rx_dma_int_status		= sxgbe_rx_dma_int_status,
+	.rx_watchdog			= sxgbe_dma_rx_watchdog,
+};
+
+const struct sxgbe_dma_ops *sxgbe_get_dma_ops(void)
+{
+	return &sxgbe_dma_ops;
+}
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.h
new file mode 100644
index 000000000000..bbf167efb60c
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_dma.h
@@ -0,0 +1,48 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __SXGBE_DMA_H__
+#define __SXGBE_DMA_H__
+
+/* forward declaration */
+struct sxgbe_extra_stats;
+
+#define SXGBE_DMA_BLENMAP_LSHIFT	1
+#define SXGBE_DMA_TXPBL_LSHIFT		16
+#define SXGBE_DMA_RXPBL_LSHIFT		16
+#define DEFAULT_DMA_PBL			8
+
+struct sxgbe_dma_ops {
+	/* DMA core initialization */
+	int (*init)(void __iomem *ioaddr, int fix_burst, int burst_map);
+	void (*cha_init)(void __iomem *ioaddr, int cha_num, int fix_burst,
+			 int pbl, dma_addr_t dma_tx, dma_addr_t dma_rx,
+			 int t_rzie, int r_rsize);
+	void (*enable_dma_transmission)(void __iomem *ioaddr, int dma_cnum);
+	void (*enable_dma_irq)(void __iomem *ioaddr, int dma_cnum);
+	void (*disable_dma_irq)(void __iomem *ioaddr, int dma_cnum);
+	void (*start_tx)(void __iomem *ioaddr, int tchannels);
+	void (*start_tx_queue)(void __iomem *ioaddr, int dma_cnum);
+	void (*stop_tx)(void __iomem *ioaddr, int tchannels);
+	void (*stop_tx_queue)(void __iomem *ioaddr, int dma_cnum);
+	void (*start_rx)(void __iomem *ioaddr, int rchannels);
+	void (*stop_rx)(void __iomem *ioaddr, int rchannels);
+	int (*tx_dma_int_status)(void __iomem *ioaddr, int channel_no,
+				 struct sxgbe_extra_stats *x);
+	int (*rx_dma_int_status)(void __iomem *ioaddr, int channel_no,
+				 struct sxgbe_extra_stats *x);
+	/* Program the HW RX Watchdog */
+	void (*rx_watchdog)(void __iomem *ioaddr, u32 riwt);
+};
+
+const struct sxgbe_dma_ops *sxgbe_get_dma_ops(void);
+
+#endif /* __SXGBE_CORE_H__ */
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
new file mode 100644
index 000000000000..1dce2b2e045b
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
@@ -0,0 +1,44 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+
+#include "sxgbe_common.h"
+
+struct sxgbe_stats {
+	char stat_string[ETH_GSTRING_LEN];
+	int sizeof_stat;
+	int stat_offset;
+};
+
+#define SXGBE_STAT(m)						\
+{								\
+	#m,							\
+	FIELD_SIZEOF(struct sxgbe_extra_stats, m),		\
+	offsetof(struct sxgbe_priv_data, xstats.m)		\
+}
+
+static const struct sxgbe_stats sxgbe_gstrings_stats[] = {
+};
+#define SXGBE_STATS_LEN ARRAY_SIZE(sxgbe_gstrings_stats)
+
+static const struct ethtool_ops sxgbe_ethtool_ops = {
+};
+
+void sxgbe_set_ethtool_ops(struct net_device *netdev)
+{
+	SET_ETHTOOL_OPS(netdev, &sxgbe_ethtool_ops);
+}
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
new file mode 100644
index 000000000000..75ba57cfe7c0
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
@@ -0,0 +1,2052 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/clk.h>
+#include <linux/crc32.h>
+#include <linux/dma-mapping.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/if.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/ip.h>
+#include <linux/kernel.h>
+#include <linux/mii.h>
+#include <linux/module.h>
+#include <linux/net_tstamp.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+#include <linux/platform_device.h>
+#include <linux/prefetch.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/tcp.h>
+#include <linux/sxgbe_platform.h>
+
+#include "sxgbe_common.h"
+#include "sxgbe_desc.h"
+#include "sxgbe_dma.h"
+#include "sxgbe_mtl.h"
+#include "sxgbe_reg.h"
+
+#define SXGBE_ALIGN(x)	L1_CACHE_ALIGN(x)
+#define JUMBO_LEN	9000
+
+/* Module parameters */
+#define TX_TIMEO	5000
+#define DMA_TX_SIZE	512
+#define DMA_RX_SIZE	1024
+#define TC_DEFAULT	64
+#define DMA_BUFFER_SIZE	BUF_SIZE_2KiB
+/* The default timer value as per the sxgbe specification 1 sec(1000 ms) */
+#define SXGBE_DEFAULT_LPI_TIMER	1000
+
+static int debug = -1;
+
+module_param(debug, int, S_IRUGO | S_IWUSR);
+static const u32 default_msg_level = (NETIF_MSG_DRV | NETIF_MSG_PROBE |
+				      NETIF_MSG_LINK | NETIF_MSG_IFUP |
+				      NETIF_MSG_IFDOWN | NETIF_MSG_TIMER);
+
+static irqreturn_t sxgbe_common_interrupt(int irq, void *dev_id);
+static irqreturn_t sxgbe_tx_interrupt(int irq, void *dev_id);
+static irqreturn_t sxgbe_rx_interrupt(int irq, void *dev_id);
+
+#define SXGBE_COAL_TIMER(x) (jiffies + usecs_to_jiffies(x))
+
+/**
+ * sxgbe_clk_csr_set - dynamically set the MDC clock
+ * @priv: driver private structure
+ * Description: this is to dynamically set the MDC clock according to the csr
+ * clock input.
+ */
+static void sxgbe_clk_csr_set(struct sxgbe_priv_data *priv)
+{
+	u32 clk_rate = clk_get_rate(priv->sxgbe_clk);
+
+	/* assign the proper divider, this will be used during
+	 * mdio communication
+	 */
+	if (clk_rate < SXGBE_CSR_F_150M)
+		priv->clk_csr = SXGBE_CSR_100_150M;
+	else if (clk_rate <= SXGBE_CSR_F_250M)
+		priv->clk_csr = SXGBE_CSR_150_250M;
+	else if (clk_rate <= SXGBE_CSR_F_300M)
+		priv->clk_csr = SXGBE_CSR_250_300M;
+	else if (clk_rate <= SXGBE_CSR_F_350M)
+		priv->clk_csr = SXGBE_CSR_300_350M;
+	else if (clk_rate <= SXGBE_CSR_F_400M)
+		priv->clk_csr = SXGBE_CSR_350_400M;
+	else if (clk_rate <= SXGBE_CSR_F_500M)
+		priv->clk_csr = SXGBE_CSR_400_500M;
+}
+
+/* minimum number of free TX descriptors required to wake up TX process */
+#define SXGBE_TX_THRESH(x)	(x->dma_tx_size/4)
+
+static inline u32 sxgbe_tx_avail(struct sxgbe_tx_queue *queue, int tx_qsize)
+{
+	return queue->dirty_tx + tx_qsize - queue->cur_tx - 1;
+}
+
+/**
+ * sxgbe_adjust_link
+ * @dev: net device structure
+ * Description: it adjusts the link parameters.
+ */
+static void sxgbe_adjust_link(struct net_device *dev)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+	struct phy_device *phydev = priv->phydev;
+	u8 new_state = 0;
+	u8 speed = 0xff;
+
+	if (!phydev)
+		return;
+
+	/* SXGBE is not supporting auto-negotiation and
+	 * half duplex mode. so, not handling duplex change
+	 * in this function. only handling speed and link status
+	 */
+	if (phydev->link) {
+		if (phydev->speed != priv->speed) {
+			new_state = 1;
+			switch (phydev->speed) {
+			case SPEED_10000:
+				speed = SXGBE_SPEED_10G;
+				break;
+			case SPEED_2500:
+				speed = SXGBE_SPEED_2_5G;
+				break;
+			case SPEED_1000:
+				speed = SXGBE_SPEED_1G;
+				break;
+			default:
+				netif_err(priv, link, dev,
+					  "Speed (%d) not supported\n",
+					  phydev->speed);
+			}
+
+			priv->speed = phydev->speed;
+			priv->hw->mac->set_speed(priv->ioaddr, speed);
+		}
+
+		if (!priv->oldlink) {
+			new_state = 1;
+			priv->oldlink = 1;
+		}
+	} else if (priv->oldlink) {
+		new_state = 1;
+		priv->oldlink = 0;
+		priv->speed = SPEED_UNKNOWN;
+	}
+
+	if (new_state & netif_msg_link(priv))
+		phy_print_status(phydev);
+}
+
+/**
+ * sxgbe_init_phy - PHY initialization
+ * @dev: net device structure
+ * Description: it initializes the driver's PHY state, and attaches the PHY
+ * to the mac driver.
+ *  Return value:
+ *  0 on success
+ */
+static int sxgbe_init_phy(struct net_device *ndev)
+{
+	char phy_id_fmt[MII_BUS_ID_SIZE + 3];
+	char bus_id[MII_BUS_ID_SIZE];
+	struct phy_device *phydev;
+	struct sxgbe_priv_data *priv = netdev_priv(ndev);
+	int phy_iface = priv->plat->interface;
+
+	/* assign default link status */
+	priv->oldlink = 0;
+	priv->speed = SPEED_UNKNOWN;
+	priv->oldduplex = DUPLEX_UNKNOWN;
+
+	if (priv->plat->phy_bus_name)
+		snprintf(bus_id, MII_BUS_ID_SIZE, "%s-%x",
+			 priv->plat->phy_bus_name, priv->plat->bus_id);
+	else
+		snprintf(bus_id, MII_BUS_ID_SIZE, "sxgbe-%x",
+			 priv->plat->bus_id);
+
+	snprintf(phy_id_fmt, MII_BUS_ID_SIZE + 3, PHY_ID_FMT, bus_id,
+		 priv->plat->phy_addr);
+	netdev_dbg(ndev, "%s: trying to attach to %s\n", __func__, phy_id_fmt);
+
+	phydev = phy_connect(ndev, phy_id_fmt, &sxgbe_adjust_link, phy_iface);
+
+	if (IS_ERR(phydev)) {
+		netdev_err(ndev, "Could not attach to PHY\n");
+		return PTR_ERR(phydev);
+	}
+
+	/* Stop Advertising 1000BASE Capability if interface is not GMII */
+	if ((phy_iface == PHY_INTERFACE_MODE_MII) ||
+	    (phy_iface == PHY_INTERFACE_MODE_RMII))
+		phydev->advertising &= ~(SUPPORTED_1000baseT_Half |
+					 SUPPORTED_1000baseT_Full);
+	if (phydev->phy_id == 0) {
+		phy_disconnect(phydev);
+		return -ENODEV;
+	}
+
+	netdev_dbg(ndev, "%s: attached to PHY (UID 0x%x) Link = %d\n",
+		   __func__, phydev->phy_id, phydev->link);
+
+	/* save phy device in private structure */
+	priv->phydev = phydev;
+
+	return 0;
+}
+
+/**
+ * sxgbe_clear_descriptors: clear descriptors
+ * @priv: driver private structure
+ * Description: this function is called to clear the tx and rx descriptors
+ * in case of both basic and extended descriptors are used.
+ */
+static void sxgbe_clear_descriptors(struct sxgbe_priv_data *priv)
+{
+	int i, j;
+	unsigned int txsize = priv->dma_tx_size;
+	unsigned int rxsize = priv->dma_rx_size;
+
+	/* Clear the Rx/Tx descriptors */
+	for (j = 0; j < SXGBE_RX_QUEUES; j++) {
+		for (i = 0; i < rxsize; i++)
+			priv->hw->desc->init_rx_desc(&priv->rxq[j]->dma_rx[i],
+						     priv->use_riwt, priv->mode,
+						     (i == rxsize - 1));
+	}
+
+	for (j = 0; j < SXGBE_TX_QUEUES; j++) {
+		for (i = 0; i < txsize; i++)
+			priv->hw->desc->init_tx_desc(&priv->txq[j]->dma_tx[i]);
+	}
+}
+
+static int sxgbe_init_rx_buffers(struct net_device *dev,
+				 struct sxgbe_rx_norm_desc *p, int i,
+				 unsigned int dma_buf_sz,
+				 struct sxgbe_rx_queue *rx_ring)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+	struct sk_buff *skb;
+
+	skb = __netdev_alloc_skb_ip_align(dev, dma_buf_sz, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	rx_ring->rx_skbuff[i] = skb;
+	rx_ring->rx_skbuff_dma[i] = dma_map_single(priv->device, skb->data,
+						   dma_buf_sz, DMA_FROM_DEVICE);
+
+	if (dma_mapping_error(priv->device, rx_ring->rx_skbuff_dma[i])) {
+		netdev_err(dev, "%s: DMA mapping error\n", __func__);
+		dev_kfree_skb_any(skb);
+		return -EINVAL;
+	}
+
+	p->rdes23.rx_rd_des23.buf2_addr = rx_ring->rx_skbuff_dma[i];
+
+	return 0;
+}
+/**
+ * init_tx_ring - init the TX descriptor ring
+ * @dev: net device structure
+ * @tx_ring: ring to be intialised
+ * @tx_rsize: ring size
+ * Description:  this function initializes the DMA TX descriptor
+ */
+static int init_tx_ring(struct device *dev, u8 queue_no,
+			struct sxgbe_tx_queue *tx_ring,	int tx_rsize)
+{
+	/* TX ring is not allcoated */
+	if (!tx_ring) {
+		dev_err(dev, "No memory for TX queue of SXGBE\n");
+		return -ENOMEM;
+	}
+
+	/* allocate memory for TX descriptors */
+	tx_ring->dma_tx = dma_zalloc_coherent(dev,
+					      tx_rsize * sizeof(struct sxgbe_tx_norm_desc),
+					      &tx_ring->dma_tx_phy, GFP_KERNEL);
+	if (!tx_ring->dma_tx)
+		return -ENOMEM;
+
+	/* allocate memory for TX skbuff array */
+	tx_ring->tx_skbuff_dma = devm_kcalloc(dev, tx_rsize,
+					      sizeof(dma_addr_t), GFP_KERNEL);
+	if (!tx_ring->tx_skbuff_dma)
+		goto dmamem_err;
+
+	tx_ring->tx_skbuff = devm_kcalloc(dev, tx_rsize,
+					  sizeof(struct sk_buff *), GFP_KERNEL);
+
+	if (!tx_ring->tx_skbuff)
+		goto dmamem_err;
+
+	/* assign queue number */
+	tx_ring->queue_no = queue_no;
+
+	/* initalise counters */
+	tx_ring->dirty_tx = 0;
+	tx_ring->cur_tx = 0;
+
+	/* initalise TX queue lock */
+	spin_lock_init(&tx_ring->tx_lock);
+
+	return 0;
+
+dmamem_err:
+	dma_free_coherent(dev, tx_rsize * sizeof(struct sxgbe_tx_norm_desc),
+			  tx_ring->dma_tx, tx_ring->dma_tx_phy);
+	return -ENOMEM;
+}
+
+/**
+ * free_rx_ring - free the RX descriptor ring
+ * @dev: net device structure
+ * @rx_ring: ring to be intialised
+ * @rx_rsize: ring size
+ * Description:  this function initializes the DMA RX descriptor
+ */
+void free_rx_ring(struct device *dev, struct sxgbe_rx_queue *rx_ring,
+		  int rx_rsize)
+{
+	dma_free_coherent(dev, rx_rsize * sizeof(struct sxgbe_rx_norm_desc),
+			  rx_ring->dma_rx, rx_ring->dma_rx_phy);
+	kfree(rx_ring->rx_skbuff_dma);
+	kfree(rx_ring->rx_skbuff);
+}
+
+/**
+ * init_rx_ring - init the RX descriptor ring
+ * @dev: net device structure
+ * @rx_ring: ring to be intialised
+ * @rx_rsize: ring size
+ * Description:  this function initializes the DMA RX descriptor
+ */
+static int init_rx_ring(struct net_device *dev, u8 queue_no,
+			struct sxgbe_rx_queue *rx_ring,	int rx_rsize)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+	int desc_index;
+	unsigned int bfsize = 0;
+	unsigned int ret = 0;
+
+	/* Set the max buffer size according to the MTU. */
+	bfsize = ALIGN(dev->mtu + ETH_HLEN + ETH_FCS_LEN + NET_IP_ALIGN, 8);
+
+	netif_dbg(priv, probe, dev, "%s: bfsize %d\n", __func__, bfsize);
+
+	/* RX ring is not allcoated */
+	if (rx_ring == NULL) {
+		netdev_err(dev, "No memory for RX queue\n");
+		goto error;
+	}
+
+	/* assign queue number */
+	rx_ring->queue_no = queue_no;
+
+	/* allocate memory for RX descriptors */
+	rx_ring->dma_rx = dma_zalloc_coherent(priv->device,
+					      rx_rsize * sizeof(struct sxgbe_rx_norm_desc),
+					      &rx_ring->dma_rx_phy, GFP_KERNEL);
+
+	if (rx_ring->dma_rx == NULL)
+		goto error;
+
+	/* allocate memory for RX skbuff array */
+	rx_ring->rx_skbuff_dma = kmalloc_array(rx_rsize,
+					       sizeof(dma_addr_t), GFP_KERNEL);
+	if (rx_ring->rx_skbuff_dma == NULL)
+		goto dmamem_err;
+
+	rx_ring->rx_skbuff = kmalloc_array(rx_rsize,
+					   sizeof(struct sk_buff *), GFP_KERNEL);
+	if (rx_ring->rx_skbuff == NULL)
+		goto rxbuff_err;
+
+	/* initialise the buffers */
+	for (desc_index = 0; desc_index < rx_rsize; desc_index++) {
+		struct sxgbe_rx_norm_desc *p;
+		p = rx_ring->dma_rx + desc_index;
+		ret = sxgbe_init_rx_buffers(dev, p, desc_index,
+					    bfsize, rx_ring);
+		if (ret)
+			goto err_init_rx_buffers;
+	}
+
+	/* initalise counters */
+	rx_ring->cur_rx = 0;
+	rx_ring->dirty_rx = (unsigned int)(desc_index - rx_rsize);
+	priv->dma_buf_sz = bfsize;
+
+	return 0;
+
+err_init_rx_buffers:
+	while (--desc_index >= 0)
+		free_rx_ring(priv->device, rx_ring, desc_index);
+	kfree(rx_ring->rx_skbuff);
+rxbuff_err:
+	kfree(rx_ring->rx_skbuff_dma);
+dmamem_err:
+	dma_free_coherent(priv->device,
+			  rx_rsize * sizeof(struct sxgbe_rx_norm_desc),
+			  rx_ring->dma_rx, rx_ring->dma_rx_phy);
+error:
+	return -ENOMEM;
+}
+/**
+ * free_tx_ring - free the TX descriptor ring
+ * @dev: net device structure
+ * @tx_ring: ring to be intialised
+ * @tx_rsize: ring size
+ * Description:  this function initializes the DMA TX descriptor
+ */
+void free_tx_ring(struct device *dev, struct sxgbe_tx_queue *tx_ring,
+		  int tx_rsize)
+{
+	dma_free_coherent(dev, tx_rsize * sizeof(struct sxgbe_tx_norm_desc),
+			  tx_ring->dma_tx, tx_ring->dma_tx_phy);
+}
+
+/**
+ * init_dma_desc_rings - init the RX/TX descriptor rings
+ * @dev: net device structure
+ * Description:  this function initializes the DMA RX/TX descriptors
+ * and allocates the socket buffers. It suppors the chained and ring
+ * modes.
+ */
+static int init_dma_desc_rings(struct net_device *netd)
+{
+	int queue_num, ret;
+	struct sxgbe_priv_data *priv = netdev_priv(netd);
+	int tx_rsize = priv->dma_tx_size;
+	int rx_rsize = priv->dma_rx_size;
+
+	/* Allocate memory for queue structures and TX descs */
+	SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num) {
+		ret = init_tx_ring(priv->device, queue_num,
+				   priv->txq[queue_num], tx_rsize);
+		if (ret) {
+			dev_err(&netd->dev, "TX DMA ring allocation failed!\n");
+			goto txalloc_err;
+		}
+
+		/* save private pointer in each ring this
+		 * pointer is needed during cleaing TX queue
+		 */
+		priv->txq[queue_num]->priv_ptr = priv;
+	}
+
+	/* Allocate memory for queue structures and RX descs */
+	SXGBE_FOR_EACH_QUEUE(SXGBE_RX_QUEUES, queue_num) {
+		ret = init_rx_ring(netd, queue_num,
+				   priv->rxq[queue_num], rx_rsize);
+		if (ret) {
+			netdev_err(netd, "RX DMA ring allocation failed!!\n");
+			goto rxalloc_err;
+		}
+
+		/* save private pointer in each ring this
+		 * pointer is needed during cleaing TX queue
+		 */
+		priv->rxq[queue_num]->priv_ptr = priv;
+	}
+
+	sxgbe_clear_descriptors(priv);
+
+	return 0;
+
+txalloc_err:
+	while (queue_num--)
+		free_tx_ring(priv->device, priv->txq[queue_num], tx_rsize);
+	return ret;
+
+rxalloc_err:
+	while (queue_num--)
+		free_rx_ring(priv->device, priv->rxq[queue_num], rx_rsize);
+	return ret;
+}
+
+static void tx_free_ring_skbufs(struct sxgbe_tx_queue *txqueue)
+{
+	int dma_desc;
+	struct sxgbe_priv_data *priv = txqueue->priv_ptr;
+	int tx_rsize = priv->dma_tx_size;
+
+	for (dma_desc = 0; dma_desc < tx_rsize; dma_desc++) {
+		struct sxgbe_tx_norm_desc *tdesc = txqueue->dma_tx + dma_desc;
+
+		if (txqueue->tx_skbuff_dma[dma_desc])
+			dma_unmap_single(priv->device,
+					 txqueue->tx_skbuff_dma[dma_desc],
+					 priv->hw->desc->get_tx_len(tdesc),
+					 DMA_TO_DEVICE);
+
+		dev_kfree_skb_any(txqueue->tx_skbuff[dma_desc]);
+		txqueue->tx_skbuff[dma_desc] = NULL;
+		txqueue->tx_skbuff_dma[dma_desc] = 0;
+	}
+}
+
+
+static void dma_free_tx_skbufs(struct sxgbe_priv_data *priv)
+{
+	int queue_num;
+
+	SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num) {
+		struct sxgbe_tx_queue *tqueue = priv->txq[queue_num];
+		tx_free_ring_skbufs(tqueue);
+	}
+}
+
+static void free_dma_desc_resources(struct sxgbe_priv_data *priv)
+{
+	int queue_num;
+	int tx_rsize = priv->dma_tx_size;
+	int rx_rsize = priv->dma_rx_size;
+
+	/* Release the DMA TX buffers */
+	dma_free_tx_skbufs(priv);
+
+	/* Release the TX ring memory also */
+	SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num) {
+		free_tx_ring(priv->device, priv->txq[queue_num], tx_rsize);
+	}
+
+	/* Release the RX ring memory also */
+	SXGBE_FOR_EACH_QUEUE(SXGBE_RX_QUEUES, queue_num) {
+		free_rx_ring(priv->device, priv->rxq[queue_num], rx_rsize);
+	}
+}
+
+static int txring_mem_alloc(struct sxgbe_priv_data *priv)
+{
+	int queue_num;
+
+	SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num) {
+		priv->txq[queue_num] = devm_kmalloc(priv->device,
+						    sizeof(struct sxgbe_tx_queue), GFP_KERNEL);
+		if (!priv->txq[queue_num])
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int rxring_mem_alloc(struct sxgbe_priv_data *priv)
+{
+	int queue_num;
+
+	SXGBE_FOR_EACH_QUEUE(SXGBE_RX_QUEUES, queue_num) {
+		priv->rxq[queue_num] = devm_kmalloc(priv->device,
+						    sizeof(struct sxgbe_rx_queue), GFP_KERNEL);
+		if (!priv->rxq[queue_num])
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+/**
+ *  sxgbe_mtl_operation_mode - HW MTL operation mode
+ *  @priv: driver private structure
+ *  Description: it sets the MTL operation mode: tx/rx MTL thresholds
+ *  or Store-And-Forward capability.
+ */
+static void sxgbe_mtl_operation_mode(struct sxgbe_priv_data *priv)
+{
+	int queue_num;
+
+	/* TX/RX threshold control */
+	if (likely(priv->plat->force_sf_dma_mode)) {
+		/* set TC mode for TX QUEUES */
+		SXGBE_FOR_EACH_QUEUE(priv->hw_cap.tx_mtl_queues, queue_num)
+			priv->hw->mtl->set_tx_mtl_mode(priv->ioaddr, queue_num,
+						       SXGBE_MTL_SFMODE);
+		priv->tx_tc = SXGBE_MTL_SFMODE;
+
+		/* set TC mode for RX QUEUES */
+		SXGBE_FOR_EACH_QUEUE(priv->hw_cap.rx_mtl_queues, queue_num)
+			priv->hw->mtl->set_rx_mtl_mode(priv->ioaddr, queue_num,
+						       SXGBE_MTL_SFMODE);
+		priv->rx_tc = SXGBE_MTL_SFMODE;
+	} else if (unlikely(priv->plat->force_thresh_dma_mode)) {
+		/* set TC mode for TX QUEUES */
+		SXGBE_FOR_EACH_QUEUE(priv->hw_cap.tx_mtl_queues, queue_num)
+			priv->hw->mtl->set_tx_mtl_mode(priv->ioaddr, queue_num,
+						       priv->tx_tc);
+		/* set TC mode for RX QUEUES */
+		SXGBE_FOR_EACH_QUEUE(priv->hw_cap.rx_mtl_queues, queue_num)
+			priv->hw->mtl->set_rx_mtl_mode(priv->ioaddr, queue_num,
+						       priv->rx_tc);
+	} else {
+		pr_err("ERROR: %s: Invalid TX threshold mode\n", __func__);
+	}
+}
+
+/**
+ * sxgbe_tx_queue_clean:
+ * @priv: driver private structure
+ * Description: it reclaims resources after transmission completes.
+ */
+static void sxgbe_tx_queue_clean(struct sxgbe_tx_queue *tqueue)
+{
+	struct sxgbe_priv_data *priv = tqueue->priv_ptr;
+	unsigned int tx_rsize = priv->dma_tx_size;
+	struct netdev_queue *dev_txq;
+	u8 queue_no = tqueue->queue_no;
+
+	dev_txq = netdev_get_tx_queue(priv->dev, queue_no);
+
+	spin_lock(&tqueue->tx_lock);
+
+	priv->xstats.tx_clean++;
+	while (tqueue->dirty_tx != tqueue->cur_tx) {
+		unsigned int entry = tqueue->dirty_tx % tx_rsize;
+		struct sk_buff *skb = tqueue->tx_skbuff[entry];
+		struct sxgbe_tx_norm_desc *p;
+
+		p = tqueue->dma_tx + entry;
+
+		/* Check if the descriptor is owned by the DMA. */
+		if (priv->hw->desc->get_tx_owner(p))
+			break;
+
+		if (netif_msg_tx_done(priv))
+			pr_debug("%s: curr %d, dirty %d\n",
+				 __func__, tqueue->cur_tx, tqueue->dirty_tx);
+
+		if (likely(tqueue->tx_skbuff_dma[entry])) {
+			dma_unmap_single(priv->device,
+					 tqueue->tx_skbuff_dma[entry],
+					 priv->hw->desc->get_tx_len(p),
+					 DMA_TO_DEVICE);
+			tqueue->tx_skbuff_dma[entry] = 0;
+		}
+
+		if (likely(skb)) {
+			dev_kfree_skb(skb);
+			tqueue->tx_skbuff[entry] = NULL;
+		}
+
+		priv->hw->desc->release_tx_desc(p);
+
+		tqueue->dirty_tx++;
+	}
+
+	/* wake up queue */
+	if (unlikely(netif_tx_queue_stopped(dev_txq) &&
+		     sxgbe_tx_avail(tqueue, tx_rsize) > SXGBE_TX_THRESH(priv))) {
+		netif_tx_lock(priv->dev);
+		if (netif_tx_queue_stopped(dev_txq) &&
+		    sxgbe_tx_avail(tqueue, tx_rsize) > SXGBE_TX_THRESH(priv)) {
+			if (netif_msg_tx_done(priv))
+				pr_debug("%s: restart transmit\n", __func__);
+			netif_tx_wake_queue(dev_txq);
+		}
+		netif_tx_unlock(priv->dev);
+	}
+
+	spin_unlock(&tqueue->tx_lock);
+}
+
+/**
+ * sxgbe_tx_clean:
+ * @priv: driver private structure
+ * Description: it reclaims resources after transmission completes.
+ */
+static void sxgbe_tx_all_clean(struct sxgbe_priv_data *priv)
+{
+	u8 queue_num;
+
+	SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num) {
+		struct sxgbe_tx_queue *tqueue = priv->txq[queue_num];
+
+		sxgbe_tx_queue_clean(tqueue);
+	}
+}
+
+/**
+ * sxgbe_restart_tx_queue: irq tx error mng function
+ * @priv: driver private structure
+ * Description: it cleans the descriptors and restarts the transmission
+ * in case of errors.
+ */
+static void sxgbe_restart_tx_queue(struct sxgbe_priv_data *priv, int queue_num)
+{
+	struct sxgbe_tx_queue *tx_ring = priv->txq[queue_num];
+	struct netdev_queue *dev_txq = netdev_get_tx_queue(priv->dev,
+							   queue_num);
+
+	/* stop the queue */
+	netif_tx_stop_queue(dev_txq);
+
+	/* stop the tx dma */
+	priv->hw->dma->stop_tx_queue(priv->ioaddr, queue_num);
+
+	/* free the skbuffs of the ring */
+	tx_free_ring_skbufs(tx_ring);
+
+	/* initalise counters */
+	tx_ring->cur_tx = 0;
+	tx_ring->dirty_tx = 0;
+
+	/* start the tx dma */
+	priv->hw->dma->start_tx_queue(priv->ioaddr, queue_num);
+
+	priv->dev->stats.tx_errors++;
+
+	/* wakeup the queue */
+	netif_tx_wake_queue(dev_txq);
+}
+
+/**
+ * sxgbe_reset_all_tx_queues: irq tx error mng function
+ * @priv: driver private structure
+ * Description: it cleans all the descriptors and
+ * restarts the transmission on all queues in case of errors.
+ */
+static void sxgbe_reset_all_tx_queues(struct sxgbe_priv_data *priv)
+{
+	int queue_num;
+
+	/* On TX timeout of net device, resetting of all queues
+	 * may not be proper way, revisit this later if needed
+	 */
+	SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num)
+		sxgbe_restart_tx_queue(priv, queue_num);
+}
+
+/**
+ * sxgbe_get_hw_features: get XMAC capabilities from the HW cap. register.
+ * @priv: driver private structure
+ * Description:
+ *  new GMAC chip generations have a new register to indicate the
+ *  presence of the optional feature/functions.
+ *  This can be also used to override the value passed through the
+ *  platform and necessary for old MAC10/100 and GMAC chips.
+ */
+static int sxgbe_get_hw_features(struct sxgbe_priv_data * const priv)
+{
+	int rval = 0;
+	struct sxgbe_hw_features *features = &priv->hw_cap;
+
+	/* Read First Capability Register CAP[0] */
+	rval = priv->hw->mac->get_hw_feature(priv->ioaddr, 0);
+	if (rval) {
+		features->pmt_remote_wake_up =
+			SXGBE_HW_FEAT_PMT_TEMOTE_WOP(rval);
+		features->pmt_magic_frame = SXGBE_HW_FEAT_PMT_MAGIC_PKT(rval);
+		features->atime_stamp = SXGBE_HW_FEAT_IEEE1500_2008(rval);
+		features->tx_csum_offload =
+			SXGBE_HW_FEAT_TX_CSUM_OFFLOAD(rval);
+		features->rx_csum_offload =
+			SXGBE_HW_FEAT_RX_CSUM_OFFLOAD(rval);
+		features->multi_macaddr = SXGBE_HW_FEAT_MACADDR_COUNT(rval);
+		features->tstamp_srcselect = SXGBE_HW_FEAT_TSTMAP_SRC(rval);
+		features->sa_vlan_insert = SXGBE_HW_FEAT_SRCADDR_VLAN(rval);
+	}
+
+	/* Read First Capability Register CAP[1] */
+	rval = priv->hw->mac->get_hw_feature(priv->ioaddr, 1);
+	if (rval) {
+		features->rxfifo_size = SXGBE_HW_FEAT_RX_FIFO_SIZE(rval);
+		features->txfifo_size = SXGBE_HW_FEAT_TX_FIFO_SIZE(rval);
+		features->atstmap_hword = SXGBE_HW_FEAT_TX_FIFO_SIZE(rval);
+		features->dcb_enable = SXGBE_HW_FEAT_DCB(rval);
+		features->splithead_enable = SXGBE_HW_FEAT_SPLIT_HDR(rval);
+		features->tcpseg_offload = SXGBE_HW_FEAT_TSO(rval);
+		features->debug_mem = SXGBE_HW_FEAT_DEBUG_MEM_IFACE(rval);
+		features->rss_enable = SXGBE_HW_FEAT_RSS(rval);
+		features->hash_tsize = SXGBE_HW_FEAT_HASH_TABLE_SIZE(rval);
+		features->l3l4_filer_size = SXGBE_HW_FEAT_L3L4_FILTER_NUM(rval);
+	}
+
+	/* Read First Capability Register CAP[2] */
+	rval = priv->hw->mac->get_hw_feature(priv->ioaddr, 2);
+	if (rval) {
+		features->rx_mtl_queues = SXGBE_HW_FEAT_RX_MTL_QUEUES(rval);
+		features->tx_mtl_queues = SXGBE_HW_FEAT_TX_MTL_QUEUES(rval);
+		features->rx_dma_channels = SXGBE_HW_FEAT_RX_DMA_CHANNELS(rval);
+		features->tx_dma_channels = SXGBE_HW_FEAT_TX_DMA_CHANNELS(rval);
+		features->pps_output_count = SXGBE_HW_FEAT_PPS_OUTPUTS(rval);
+		features->aux_input_count = SXGBE_HW_FEAT_AUX_SNAPSHOTS(rval);
+	}
+
+	return rval;
+}
+
+/**
+ * sxgbe_check_ether_addr: check if the MAC addr is valid
+ * @priv: driver private structure
+ * Description:
+ * it is to verify if the MAC address is valid, in case of failures it
+ * generates a random MAC address
+ */
+static void sxgbe_check_ether_addr(struct sxgbe_priv_data *priv)
+{
+	if (!is_valid_ether_addr(priv->dev->dev_addr)) {
+		priv->hw->mac->get_umac_addr((void __iomem *)
+					     priv->ioaddr,
+					     priv->dev->dev_addr, 0);
+		if (!is_valid_ether_addr(priv->dev->dev_addr))
+			eth_hw_addr_random(priv->dev);
+	}
+	dev_info(priv->device, "device MAC address %pM\n",
+		 priv->dev->dev_addr);
+}
+
+/**
+ * sxgbe_init_dma_engine: DMA init.
+ * @priv: driver private structure
+ * Description:
+ * It inits the DMA invoking the specific SXGBE callback.
+ * Some DMA parameters can be passed from the platform;
+ * in case of these are not passed a default is kept for the MAC or GMAC.
+ */
+static int sxgbe_init_dma_engine(struct sxgbe_priv_data *priv)
+{
+	int pbl = DEFAULT_DMA_PBL, fixed_burst = 0, burst_map = 0;
+	int queue_num;
+
+	if (priv->plat->dma_cfg) {
+		pbl = priv->plat->dma_cfg->pbl;
+		fixed_burst = priv->plat->dma_cfg->fixed_burst;
+		burst_map = priv->plat->dma_cfg->burst_map;
+	}
+
+	SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num)
+		priv->hw->dma->cha_init(priv->ioaddr, queue_num,
+					fixed_burst, pbl,
+					(priv->txq[queue_num])->dma_tx_phy,
+					(priv->rxq[queue_num])->dma_rx_phy,
+					priv->dma_tx_size, priv->dma_rx_size);
+
+	return priv->hw->dma->init(priv->ioaddr, fixed_burst, burst_map);
+}
+
+/**
+ * sxgbe_init_mtl_engine: MTL init.
+ * @priv: driver private structure
+ * Description:
+ * It inits the MTL invoking the specific SXGBE callback.
+ */
+static void sxgbe_init_mtl_engine(struct sxgbe_priv_data *priv)
+{
+	int queue_num;
+
+	SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num) {
+		priv->hw->mtl->mtl_set_txfifosize(priv->ioaddr, queue_num,
+						  priv->hw_cap.tx_mtl_qsize);
+		priv->hw->mtl->mtl_enable_txqueue(priv->ioaddr, queue_num);
+	}
+}
+
+/**
+ * sxgbe_disable_mtl_engine: MTL disable.
+ * @priv: driver private structure
+ * Description:
+ * It disables the MTL queues by invoking the specific SXGBE callback.
+ */
+static void sxgbe_disable_mtl_engine(struct sxgbe_priv_data *priv)
+{
+	int queue_num;
+
+	SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num)
+		priv->hw->mtl->mtl_disable_txqueue(priv->ioaddr, queue_num);
+}
+
+
+/**
+ * sxgbe_tx_timer: mitigation sw timer for tx.
+ * @data: data pointer
+ * Description:
+ * This is the timer handler to directly invoke the sxgbe_tx_clean.
+ */
+static void sxgbe_tx_timer(unsigned long data)
+{
+	struct sxgbe_tx_queue *p = (struct sxgbe_tx_queue *)data;
+	sxgbe_tx_queue_clean(p);
+}
+
+/**
+ * sxgbe_init_tx_coalesce: init tx mitigation options.
+ * @priv: driver private structure
+ * Description:
+ * This inits the transmit coalesce parameters: i.e. timer rate,
+ * timer handler and default threshold used for enabling the
+ * interrupt on completion bit.
+ */
+static void sxgbe_tx_init_coalesce(struct sxgbe_priv_data *priv)
+{
+	u8 queue_num;
+
+	SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num) {
+		struct sxgbe_tx_queue *p = priv->txq[queue_num];
+		p->tx_coal_frames =  SXGBE_TX_FRAMES;
+		p->tx_coal_timer = SXGBE_COAL_TX_TIMER;
+		init_timer(&p->txtimer);
+		p->txtimer.expires = SXGBE_COAL_TIMER(p->tx_coal_timer);
+		p->txtimer.data = (unsigned long)&priv->txq[queue_num];
+		p->txtimer.function = sxgbe_tx_timer;
+		add_timer(&p->txtimer);
+	}
+}
+
+static void sxgbe_tx_del_timer(struct sxgbe_priv_data *priv)
+{
+	u8 queue_num;
+
+	SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num) {
+		struct sxgbe_tx_queue *p = priv->txq[queue_num];
+		del_timer_sync(&p->txtimer);
+	}
+}
+
+/**
+ *  sxgbe_open - open entry point of the driver
+ *  @dev : pointer to the device structure.
+ *  Description:
+ *  This function is the open entry point of the driver.
+ *  Return value:
+ *  0 on success and an appropriate (-)ve integer as defined in errno.h
+ *  file on failure.
+ */
+static int sxgbe_open(struct net_device *dev)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+	int ret, queue_num;
+
+	clk_prepare_enable(priv->sxgbe_clk);
+
+	sxgbe_check_ether_addr(priv);
+
+	/* Init the phy */
+	ret = sxgbe_init_phy(dev);
+	if (ret) {
+		netdev_err(dev, "%s: Cannot attach to PHY (error: %d)\n",
+			   __func__, ret);
+		goto phy_error;
+	}
+
+	/* Create and initialize the TX/RX descriptors chains. */
+	priv->dma_tx_size = SXGBE_ALIGN(DMA_TX_SIZE);
+	priv->dma_rx_size = SXGBE_ALIGN(DMA_RX_SIZE);
+	priv->dma_buf_sz = SXGBE_ALIGN(DMA_BUFFER_SIZE);
+	priv->tx_tc = TC_DEFAULT;
+	priv->rx_tc = TC_DEFAULT;
+	init_dma_desc_rings(dev);
+
+	/* DMA initialization and SW reset */
+	ret = sxgbe_init_dma_engine(priv);
+	if (ret < 0) {
+		netdev_err(dev, "%s: DMA initialization failed\n", __func__);
+		goto init_error;
+	}
+
+	/*  MTL initialization */
+	sxgbe_init_mtl_engine(priv);
+
+	/* Copy the MAC addr into the HW  */
+	priv->hw->mac->set_umac_addr(priv->ioaddr, dev->dev_addr, 0);
+
+	/* Initialize the MAC Core */
+	priv->hw->mac->core_init(priv->ioaddr);
+
+	/* Request the IRQ lines */
+	ret = devm_request_irq(priv->device, priv->irq, sxgbe_common_interrupt,
+			       IRQF_SHARED, dev->name, dev);
+	if (unlikely(ret < 0)) {
+		netdev_err(dev, "%s: ERROR: allocating the IRQ %d (error: %d)\n",
+			   __func__, priv->irq, ret);
+		goto init_error;
+	}
+
+	/* Request TX DMA irq lines */
+	SXGBE_FOR_EACH_QUEUE(SXGBE_TX_QUEUES, queue_num) {
+		ret = devm_request_irq(priv->device,
+				       (priv->txq[queue_num])->irq_no,
+				       sxgbe_tx_interrupt, 0,
+				       dev->name, priv->txq[queue_num]);
+		if (unlikely(ret < 0)) {
+			netdev_err(dev, "%s: ERROR: allocating TX IRQ %d (error: %d)\n",
+				   __func__, priv->irq, ret);
+			goto init_error;
+		}
+	}
+
+	/* Request RX DMA irq lines */
+	SXGBE_FOR_EACH_QUEUE(SXGBE_RX_QUEUES, queue_num) {
+		ret = devm_request_irq(priv->device,
+				       (priv->rxq[queue_num])->irq_no,
+				       sxgbe_rx_interrupt, 0,
+				       dev->name, priv->rxq[queue_num]);
+		if (unlikely(ret < 0)) {
+			netdev_err(dev, "%s: ERROR: allocating TX IRQ %d (error: %d)\n",
+				   __func__, priv->irq, ret);
+			goto init_error;
+		}
+	}
+
+	/* Enable the MAC Rx/Tx */
+	priv->hw->mac->enable_tx(priv->ioaddr, true);
+	priv->hw->mac->enable_rx(priv->ioaddr, true);
+
+	/* Set the HW DMA mode and the COE */
+	sxgbe_mtl_operation_mode(priv);
+
+	/* Extra statistics */
+	memset(&priv->xstats, 0, sizeof(struct sxgbe_extra_stats));
+
+	priv->xstats.tx_threshold = priv->tx_tc;
+	priv->xstats.rx_threshold = priv->rx_tc;
+
+	/* Start the ball rolling... */
+	netdev_dbg(dev, "DMA RX/TX processes started...\n");
+	priv->hw->dma->start_tx(priv->ioaddr, SXGBE_TX_QUEUES);
+	priv->hw->dma->start_rx(priv->ioaddr, SXGBE_RX_QUEUES);
+
+	if (priv->phydev)
+		phy_start(priv->phydev);
+
+	/* initalise TX coalesce parameters */
+	sxgbe_tx_init_coalesce(priv);
+
+	if ((priv->use_riwt) && (priv->hw->dma->rx_watchdog)) {
+		priv->rx_riwt = SXGBE_MAX_DMA_RIWT;
+		priv->hw->dma->rx_watchdog(priv->ioaddr, SXGBE_MAX_DMA_RIWT);
+	}
+
+	napi_enable(&priv->napi);
+	netif_start_queue(dev);
+
+	return 0;
+
+init_error:
+	free_dma_desc_resources(priv);
+	if (priv->phydev)
+		phy_disconnect(priv->phydev);
+phy_error:
+	clk_disable_unprepare(priv->sxgbe_clk);
+
+	return ret;
+}
+
+/**
+ *  sxgbe_release - close entry point of the driver
+ *  @dev : device pointer.
+ *  Description:
+ *  This is the stop entry point of the driver.
+ */
+static int sxgbe_release(struct net_device *dev)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+
+	/* Stop and disconnect the PHY */
+	if (priv->phydev) {
+		phy_stop(priv->phydev);
+		phy_disconnect(priv->phydev);
+		priv->phydev = NULL;
+	}
+
+	netif_tx_stop_all_queues(dev);
+
+	napi_disable(&priv->napi);
+
+	/* delete TX timers */
+	sxgbe_tx_del_timer(priv);
+
+	/* Stop TX/RX DMA and clear the descriptors */
+	priv->hw->dma->stop_tx(priv->ioaddr, SXGBE_TX_QUEUES);
+	priv->hw->dma->stop_rx(priv->ioaddr, SXGBE_RX_QUEUES);
+
+	/* disable MTL queue */
+	sxgbe_disable_mtl_engine(priv);
+
+	/* Release and free the Rx/Tx resources */
+	free_dma_desc_resources(priv);
+
+	/* Disable the MAC Rx/Tx */
+	priv->hw->mac->enable_tx(priv->ioaddr, false);
+	priv->hw->mac->enable_rx(priv->ioaddr, false);
+
+	clk_disable_unprepare(priv->sxgbe_clk);
+
+	return 0;
+}
+
+/**
+ *  sxgbe_xmit: Tx entry point of the driver
+ *  @skb : the socket buffer
+ *  @dev : device pointer
+ *  Description : this is the tx entry point of the driver.
+ *  It programs the chain or the ring and supports oversized frames
+ *  and SG feature.
+ */
+static netdev_tx_t sxgbe_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	unsigned int entry, frag_num;
+	struct netdev_queue *dev_txq;
+	unsigned txq_index = skb_get_queue_mapping(skb);
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+	unsigned int tx_rsize = priv->dma_tx_size;
+	struct sxgbe_tx_queue *tqueue = priv->txq[txq_index];
+	struct sxgbe_tx_norm_desc *tx_desc, *first_desc;
+	int nr_frags = skb_shinfo(skb)->nr_frags;
+	int no_pagedlen = skb_headlen(skb);
+	int is_jumbo = 0;
+
+	/* get the TX queue handle */
+	dev_txq = netdev_get_tx_queue(dev, txq_index);
+
+	/* get the spinlock */
+	spin_lock(&tqueue->tx_lock);
+
+	if (unlikely(sxgbe_tx_avail(tqueue, tx_rsize) < nr_frags + 1)) {
+		if (!netif_tx_queue_stopped(dev_txq)) {
+			netif_tx_stop_queue(dev_txq);
+			netdev_err(dev, "%s: Tx Ring is full when %d queue is awake\n",
+				   __func__, txq_index);
+		}
+		/* release the spin lock in case of BUSY */
+		spin_unlock(&tqueue->tx_lock);
+		return NETDEV_TX_BUSY;
+	}
+
+	entry = tqueue->cur_tx % tx_rsize;
+	tx_desc = tqueue->dma_tx + entry;
+
+	first_desc = tx_desc;
+
+	/* save the skb address */
+	tqueue->tx_skbuff[entry] = skb;
+
+	if (!is_jumbo) {
+		tx_desc->tdes01 = dma_map_single(priv->device, skb->data,
+						   no_pagedlen, DMA_TO_DEVICE);
+		if (dma_mapping_error(priv->device, tx_desc->tdes01))
+			pr_err("%s: TX dma mapping failed!!\n", __func__);
+
+		priv->hw->desc->prepare_tx_desc(tx_desc, 1, no_pagedlen,
+						no_pagedlen, 0);
+	}
+
+	for (frag_num = 0; frag_num < nr_frags; frag_num++) {
+		const skb_frag_t *frag = &skb_shinfo(skb)->frags[frag_num];
+		int len = skb_frag_size(frag);
+
+		entry = (++tqueue->cur_tx) % tx_rsize;
+		tx_desc = tqueue->dma_tx + entry;
+		tx_desc->tdes01 = skb_frag_dma_map(priv->device, frag, 0, len,
+						   DMA_TO_DEVICE);
+
+		tqueue->tx_skbuff_dma[entry] = tx_desc->tdes01;
+		tqueue->tx_skbuff[entry] = NULL;
+
+		/* prepare the descriptor */
+		priv->hw->desc->prepare_tx_desc(tx_desc, 0, len,
+						len, 0);
+		/* memory barrier to flush descriptor */
+		wmb();
+
+		/* set the owner */
+		priv->hw->desc->set_tx_owner(tx_desc);
+	}
+
+	/* close the descriptors */
+	priv->hw->desc->close_tx_desc(tx_desc);
+
+	/* memory barrier to flush descriptor */
+	wmb();
+
+	tqueue->tx_count_frames += nr_frags + 1;
+	if (tqueue->tx_count_frames > tqueue->tx_coal_frames) {
+		priv->hw->desc->clear_tx_ic(tx_desc);
+		priv->xstats.tx_reset_ic_bit++;
+		mod_timer(&tqueue->txtimer,
+			  SXGBE_COAL_TIMER(tqueue->tx_coal_timer));
+	} else {
+		tqueue->tx_count_frames = 0;
+	}
+
+	/* set owner for first desc */
+	priv->hw->desc->set_tx_owner(first_desc);
+
+	/* memory barrier to flush descriptor */
+	wmb();
+
+	tqueue->cur_tx++;
+
+	/* display current ring */
+	netif_dbg(priv, pktdata, dev, "%s: curr %d dirty=%d entry=%d, first=%p, nfrags=%d\n",
+		  __func__, tqueue->cur_tx % tx_rsize,
+		  tqueue->dirty_tx % tx_rsize, entry,
+		  first_desc, nr_frags);
+
+	if (unlikely(sxgbe_tx_avail(tqueue, tx_rsize) <= (MAX_SKB_FRAGS + 1))) {
+		netif_dbg(priv, hw, dev, "%s: stop transmitted packets\n",
+			  __func__);
+		netif_tx_stop_queue(dev_txq);
+	}
+
+	dev->stats.tx_bytes += skb->len;
+
+	if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+		     tqueue->hwts_tx_en)) {
+		/* declare that device is doing timestamping */
+		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+		priv->hw->desc->tx_enable_tstamp(first_desc);
+	}
+
+	if (!tqueue->hwts_tx_en)
+		skb_tx_timestamp(skb);
+
+	priv->hw->dma->enable_dma_transmission(priv->ioaddr, txq_index);
+
+	spin_unlock(&tqueue->tx_lock);
+
+	return NETDEV_TX_OK;
+}
+
+/**
+ * sxgbe_rx_refill: refill used skb preallocated buffers
+ * @priv: driver private structure
+ * Description : this is to reallocate the skb for the reception process
+ * that is based on zero-copy.
+ */
+static void sxgbe_rx_refill(struct sxgbe_priv_data *priv)
+{
+	unsigned int rxsize = priv->dma_rx_size;
+	int bfsize = priv->dma_buf_sz;
+	u8 qnum = priv->cur_rx_qnum;
+
+	for (; priv->rxq[qnum]->cur_rx - priv->rxq[qnum]->dirty_rx > 0;
+	     priv->rxq[qnum]->dirty_rx++) {
+		unsigned int entry = priv->rxq[qnum]->dirty_rx % rxsize;
+		struct sxgbe_rx_norm_desc *p;
+
+		p = priv->rxq[qnum]->dma_rx + entry;
+
+		if (likely(priv->rxq[qnum]->rx_skbuff[entry] == NULL)) {
+			struct sk_buff *skb;
+
+			skb = netdev_alloc_skb_ip_align(priv->dev, bfsize);
+
+			if (unlikely(skb == NULL))
+				break;
+
+			priv->rxq[qnum]->rx_skbuff[entry] = skb;
+			priv->rxq[qnum]->rx_skbuff_dma[entry] =
+				dma_map_single(priv->device, skb->data, bfsize,
+					       DMA_FROM_DEVICE);
+
+			p->rdes23.rx_rd_des23.buf2_addr =
+				priv->rxq[qnum]->rx_skbuff_dma[entry];
+		}
+
+		/* Added memory barrier for RX descriptor modification */
+		wmb();
+		priv->hw->desc->set_rx_owner(p);
+		/* Added memory barrier for RX descriptor modification */
+		wmb();
+	}
+}
+
+/**
+ * sxgbe_rx: receive the frames from the remote host
+ * @priv: driver private structure
+ * @limit: napi bugget.
+ * Description :  this the function called by the napi poll method.
+ * It gets all the frames inside the ring.
+ */
+static int sxgbe_rx(struct sxgbe_priv_data *priv, int limit)
+{
+	u8 qnum = priv->cur_rx_qnum;
+	unsigned int rxsize = priv->dma_rx_size;
+	unsigned int entry = priv->rxq[qnum]->cur_rx;
+	unsigned int next_entry = 0;
+	unsigned int count = 0;
+
+	while (count < limit) {
+		struct sxgbe_rx_norm_desc *p;
+		struct sk_buff *skb;
+		int frame_len;
+
+		p = priv->rxq[qnum]->dma_rx + entry;
+
+		if (priv->hw->desc->get_rx_owner(p))
+			break;
+
+		count++;
+
+		next_entry = (++priv->rxq[qnum]->cur_rx) % rxsize;
+		prefetch(priv->rxq[qnum]->dma_rx + next_entry);
+
+		/*TO DO read the status of the incoming frame */
+
+		skb = priv->rxq[qnum]->rx_skbuff[entry];
+
+		if (unlikely(!skb))
+			netdev_err(priv->dev, "rx descriptor is not consistent\n");
+
+		prefetch(skb->data - NET_IP_ALIGN);
+		priv->rxq[qnum]->rx_skbuff[entry] = NULL;
+
+		frame_len = priv->hw->desc->get_rx_frame_len(p);
+
+		skb_put(skb, frame_len);
+
+		netif_receive_skb(skb);
+
+		entry = next_entry;
+	}
+
+	sxgbe_rx_refill(priv);
+
+	return count;
+}
+
+/**
+ *  sxgbe_poll - sxgbe poll method (NAPI)
+ *  @napi : pointer to the napi structure.
+ *  @budget : maximum number of packets that the current CPU can receive from
+ *	      all interfaces.
+ *  Description :
+ *  To look at the incoming frames and clear the tx resources.
+ */
+static int sxgbe_poll(struct napi_struct *napi, int budget)
+{
+	struct sxgbe_priv_data *priv = container_of(napi,
+						    struct sxgbe_priv_data, napi);
+	int work_done = 0;
+	u8 qnum = priv->cur_rx_qnum;
+
+	priv->xstats.napi_poll++;
+	/* first, clean the tx queues */
+	sxgbe_tx_all_clean(priv);
+
+	work_done = sxgbe_rx(priv, budget);
+	if (work_done < budget) {
+		napi_complete(napi);
+		priv->hw->dma->enable_dma_irq(priv->ioaddr, qnum);
+	}
+
+	return work_done;
+}
+
+/**
+ *  sxgbe_tx_timeout
+ *  @dev : Pointer to net device structure
+ *  Description: this function is called when a packet transmission fails to
+ *   complete within a reasonable time. The driver will mark the error in the
+ *   netdev structure and arrange for the device to be reset to a sane state
+ *   in order to transmit a new packet.
+ */
+static void sxgbe_tx_timeout(struct net_device *dev)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+
+	sxgbe_reset_all_tx_queues(priv);
+}
+
+/**
+ *  sxgbe_common_interrupt - main ISR
+ *  @irq: interrupt number.
+ *  @dev_id: to pass the net device pointer.
+ *  Description: this is the main driver interrupt service routine.
+ *  It calls the DMA ISR and also the core ISR to manage PMT, MMC, LPI
+ *  interrupts.
+ */
+static irqreturn_t sxgbe_common_interrupt(int irq, void *dev_id)
+{
+	return IRQ_HANDLED;
+}
+
+/**
+ *  sxgbe_tx_interrupt - TX DMA ISR
+ *  @irq: interrupt number.
+ *  @dev_id: to pass the net device pointer.
+ *  Description: this is the tx dma interrupt service routine.
+ */
+static irqreturn_t sxgbe_tx_interrupt(int irq, void *dev_id)
+{
+	int status;
+	struct sxgbe_tx_queue *txq = (struct sxgbe_tx_queue *)dev_id;
+	struct sxgbe_priv_data *priv = txq->priv_ptr;
+
+	/* get the channel status */
+	status = priv->hw->dma->tx_dma_int_status(priv->ioaddr, txq->queue_no,
+						  &priv->xstats);
+	/* check for normal path */
+	if (likely((status & handle_tx)))
+		napi_schedule(&priv->napi);
+
+	/* check for unrecoverable error */
+	if (unlikely((status & tx_hard_error)))
+		sxgbe_restart_tx_queue(priv, txq->queue_no);
+
+	/* check for TC configuration change */
+	if (unlikely((status & tx_bump_tc) &&
+		     (priv->tx_tc != SXGBE_MTL_SFMODE) &&
+		     (priv->tx_tc < 512))) {
+		/* step of TX TC is 32 till 128, otherwise 64 */
+		priv->tx_tc += (priv->tx_tc < 128) ? 32 : 64;
+		priv->hw->mtl->set_tx_mtl_mode(priv->ioaddr,
+					       txq->queue_no, priv->tx_tc);
+		priv->xstats.tx_threshold = priv->tx_tc;
+	}
+
+	return IRQ_HANDLED;
+}
+
+/**
+ *  sxgbe_rx_interrupt - RX DMA ISR
+ *  @irq: interrupt number.
+ *  @dev_id: to pass the net device pointer.
+ *  Description: this is the rx dma interrupt service routine.
+ */
+static irqreturn_t sxgbe_rx_interrupt(int irq, void *dev_id)
+{
+	int status;
+	struct sxgbe_rx_queue *rxq = (struct sxgbe_rx_queue *)dev_id;
+	struct sxgbe_priv_data *priv = rxq->priv_ptr;
+
+	/* get the channel status */
+	status = priv->hw->dma->rx_dma_int_status(priv->ioaddr, rxq->queue_no,
+						  &priv->xstats);
+
+	if (likely((status & handle_rx) && (napi_schedule_prep(&priv->napi)))) {
+		priv->hw->dma->disable_dma_irq(priv->ioaddr, rxq->queue_no);
+		__napi_schedule(&priv->napi);
+	}
+
+	/* check for TC configuration change */
+	if (unlikely((status & rx_bump_tc) &&
+		     (priv->rx_tc != SXGBE_MTL_SFMODE) &&
+		     (priv->rx_tc < 128))) {
+		/* step of TC is 32 */
+		priv->rx_tc += 32;
+		priv->hw->mtl->set_rx_mtl_mode(priv->ioaddr,
+					       rxq->queue_no, priv->rx_tc);
+		priv->xstats.rx_threshold = priv->rx_tc;
+	}
+
+	return IRQ_HANDLED;
+}
+
+static inline u64 sxgbe_get_stat64(void __iomem *ioaddr, int reg_lo, int reg_hi)
+{
+	u64 val = readl(ioaddr + reg_lo);
+
+	val |= ((u64)readl(ioaddr + reg_hi)) << 32;
+
+	return val;
+}
+
+
+/*  sxgbe_get_stats64 - entry point to see statistical information of device
+ *  @dev : device pointer.
+ *  @stats : pointer to hold all the statistical information of device.
+ *  Description:
+ *  This function is a driver entry point whenever ifconfig command gets
+ *  executed to see device statistics. Statistics are number of
+ *  bytes sent or received, errors occured etc.
+ *  Return value:
+ *  This function returns various statistical information of device.
+ */
+static struct rtnl_link_stats64 *sxgbe_get_stats64(struct net_device *dev,
+						   struct rtnl_link_stats64 *stats)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+	void __iomem *ioaddr = priv->ioaddr;
+	u64 count;
+
+	spin_lock(&priv->stats_lock);
+	/* Freeze the counter registers before reading value otherwise it may
+	 * get updated by hardware while we are reading them
+	 */
+	writel(SXGBE_MMC_CTRL_CNT_FRZ, ioaddr + SXGBE_MMC_CTL_REG);
+
+	stats->rx_bytes = sxgbe_get_stat64(ioaddr,
+					   SXGBE_MMC_RXOCTETLO_GCNT_REG,
+					   SXGBE_MMC_RXOCTETHI_GCNT_REG);
+
+	stats->rx_packets = sxgbe_get_stat64(ioaddr,
+					     SXGBE_MMC_RXFRAMELO_GBCNT_REG,
+					     SXGBE_MMC_RXFRAMEHI_GBCNT_REG);
+
+	stats->multicast = sxgbe_get_stat64(ioaddr,
+					    SXGBE_MMC_RXMULTILO_GCNT_REG,
+					    SXGBE_MMC_RXMULTIHI_GCNT_REG);
+
+	stats->rx_crc_errors = sxgbe_get_stat64(ioaddr,
+						SXGBE_MMC_RXCRCERRLO_REG,
+						SXGBE_MMC_RXCRCERRHI_REG);
+
+	stats->rx_length_errors = sxgbe_get_stat64(ioaddr,
+						  SXGBE_MMC_RXLENERRLO_REG,
+						  SXGBE_MMC_RXLENERRHI_REG);
+
+	stats->rx_missed_errors = sxgbe_get_stat64(ioaddr,
+						   SXGBE_MMC_RXFIFOOVERFLOWLO_GBCNT_REG,
+						   SXGBE_MMC_RXFIFOOVERFLOWHI_GBCNT_REG);
+
+	stats->tx_bytes = sxgbe_get_stat64(ioaddr,
+					   SXGBE_MMC_TXOCTETLO_GCNT_REG,
+					   SXGBE_MMC_TXOCTETHI_GCNT_REG);
+
+	count = sxgbe_get_stat64(ioaddr, SXGBE_MMC_TXFRAMELO_GBCNT_REG,
+				 SXGBE_MMC_TXFRAMEHI_GBCNT_REG);
+
+	stats->tx_errors = sxgbe_get_stat64(ioaddr, SXGBE_MMC_TXFRAMELO_GCNT_REG,
+					    SXGBE_MMC_TXFRAMEHI_GCNT_REG);
+	stats->tx_errors = count - stats->tx_errors;
+	stats->tx_packets = count;
+	stats->tx_fifo_errors = sxgbe_get_stat64(ioaddr, SXGBE_MMC_TXUFLWLO_GBCNT_REG,
+						 SXGBE_MMC_TXUFLWHI_GBCNT_REG);
+	writel(0, ioaddr + SXGBE_MMC_CTL_REG);
+	spin_unlock(&priv->stats_lock);
+
+	return stats;
+}
+
+/*  sxgbe_set_features - entry point to set offload features of the device.
+ *  @dev : device pointer.
+ *  @features : features which are required to be set.
+ *  Description:
+ *  This function is a driver entry point and called by Linux kernel whenever
+ *  any device features are set or reset by user.
+ *  Return value:
+ *  This function returns 0 after setting or resetting device features.
+ */
+static int sxgbe_set_features(struct net_device *dev,
+			      netdev_features_t features)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+	netdev_features_t changed = dev->features ^ features;
+	u32 ctrl;
+
+	if (changed & NETIF_F_RXCSUM) {
+		ctrl = readl(priv->ioaddr + SXGBE_CORE_RX_CONFIG_REG);
+		if (features & NETIF_F_RXCSUM)
+			ctrl |= SXGBE_RX_CSUMOFFLOAD_ENABLE;
+		else
+			ctrl &= ~SXGBE_RX_CSUMOFFLOAD_ENABLE;
+		writel(ctrl, priv->ioaddr + SXGBE_CORE_RX_CONFIG_REG);
+	}
+
+	return 0;
+}
+
+/*  sxgbe_change_mtu - entry point to change MTU size for the device.
+ *  @dev : device pointer.
+ *  @new_mtu : the new MTU size for the device.
+ *  Description: the Maximum Transfer Unit (MTU) is used by the network layer
+ *  to drive packet transmission. Ethernet has an MTU of 1500 octets
+ *  (ETH_DATA_LEN). This value can be changed with ifconfig.
+ *  Return value:
+ *  0 on success and an appropriate (-)ve integer as defined in errno.h
+ *  file on failure.
+ */
+static int sxgbe_change_mtu(struct net_device *dev, int new_mtu)
+{
+	/* RFC 791, page 25, "Every internet module must be able to forward
+	 * a datagram of 68 octets without further fragmentation."
+	 */
+	if (new_mtu < MIN_MTU || (new_mtu > MAX_MTU)) {
+		netdev_err(dev, "invalid MTU, MTU should be in between %d and %d\n",
+			   MIN_MTU, MAX_MTU);
+		return -EINVAL;
+	}
+
+	/* Return if the buffer sizes will not change */
+	if (dev->mtu == new_mtu)
+		return 0;
+
+	dev->mtu = new_mtu;
+
+	if (!netif_running(dev))
+		return 0;
+
+	/* Recevice ring buffer size is needed to be set based on MTU. If MTU is
+	 * changed then reinitilisation of the receive ring buffers need to be
+	 * done. Hence bring interface down and bring interface back up
+	 */
+	sxgbe_release(dev);
+	return sxgbe_open(dev);
+}
+
+static void sxgbe_set_umac_addr(void __iomem *ioaddr, unsigned char *addr,
+				unsigned int reg_n)
+{
+	unsigned long data;
+
+	data = (addr[5] << 8) | addr[4];
+	/* For MAC Addr registers se have to set the Address Enable (AE)
+	 * bit that has no effect on the High Reg 0 where the bit 31 (MO)
+	 * is RO.
+	 */
+	writel(data | SXGBE_HI_REG_AE, ioaddr + SXGBE_ADDR_HIGH(reg_n));
+	data = (addr[3] << 24) | (addr[2] << 16) | (addr[1] << 8) | addr[0];
+	writel(data, ioaddr + SXGBE_ADDR_LOW(reg_n));
+}
+
+/**
+ * sxgbe_set_rx_mode - entry point for setting different receive mode of
+ * a device. unicast, multicast addressing
+ * @dev : pointer to the device structure
+ * Description:
+ * This function is a driver entry point which gets called by the kernel
+ * whenever different receive mode like unicast, multicast and promiscuous
+ * must be enabled/disabled.
+ * Return value:
+ * void.
+ */
+static void sxgbe_set_rx_mode(struct net_device *dev)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+	void __iomem *ioaddr = (void __iomem *)priv->ioaddr;
+	unsigned int value = 0;
+	u32 mc_filter[2];
+	struct netdev_hw_addr *ha;
+	int reg = 1;
+
+	netdev_dbg(dev, "%s: # mcasts %d, # unicast %d\n",
+		   __func__, netdev_mc_count(dev), netdev_uc_count(dev));
+
+	if (dev->flags & IFF_PROMISC) {
+		value = SXGBE_FRAME_FILTER_PR;
+
+	} else if ((netdev_mc_count(dev) > SXGBE_HASH_TABLE_SIZE) ||
+		   (dev->flags & IFF_ALLMULTI)) {
+		value = SXGBE_FRAME_FILTER_PM;	/* pass all multi */
+		writel(0xffffffff, ioaddr + SXGBE_HASH_HIGH);
+		writel(0xffffffff, ioaddr + SXGBE_HASH_LOW);
+
+	} else if (!netdev_mc_empty(dev)) {
+		/* Hash filter for multicast */
+		value = SXGBE_FRAME_FILTER_HMC;
+
+		memset(mc_filter, 0, sizeof(mc_filter));
+		netdev_for_each_mc_addr(ha, dev) {
+			/* The upper 6 bits of the calculated CRC are used to
+			 * index the contens of the hash table
+			 */
+			int bit_nr = bitrev32(~crc32_le(~0, ha->addr, 6)) >> 26;
+
+			/* The most significant bit determines the register to
+			 * use (H/L) while the other 5 bits determine the bit
+			 * within the register.
+			 */
+			mc_filter[bit_nr >> 5] |= 1 << (bit_nr & 31);
+		}
+		writel(mc_filter[0], ioaddr + SXGBE_HASH_LOW);
+		writel(mc_filter[1], ioaddr + SXGBE_HASH_HIGH);
+	}
+
+	/* Handle multiple unicast addresses (perfect filtering) */
+	if (netdev_uc_count(dev) > SXGBE_MAX_PERFECT_ADDRESSES)
+		/* Switch to promiscuous mode if more than 16 addrs
+		 * are required
+		 */
+		value |= SXGBE_FRAME_FILTER_PR;
+	else {
+		netdev_for_each_uc_addr(ha, dev) {
+			sxgbe_set_umac_addr(ioaddr, ha->addr, reg);
+			reg++;
+		}
+	}
+#ifdef FRAME_FILTER_DEBUG
+	/* Enable Receive all mode (to debug filtering_fail errors) */
+	value |= SXGBE_FRAME_FILTER_RA;
+#endif
+	writel(value, ioaddr + SXGBE_FRAME_FILTER);
+
+	netdev_dbg(dev, "Filter: 0x%08x\n\tHash: HI 0x%08x, LO 0x%08x\n",
+		   readl(ioaddr + SXGBE_FRAME_FILTER),
+		   readl(ioaddr + SXGBE_HASH_HIGH),
+		   readl(ioaddr + SXGBE_HASH_LOW));
+}
+
+/**
+ * sxgbe_config - entry point for changing configuration mode passed on by
+ * ifconfig
+ * @dev : pointer to the device structure
+ * @map : pointer to the device mapping structure
+ * Description:
+ * This function is a driver entry point which gets called by the kernel
+ * whenever some device configuration is changed.
+ * Return value:
+ * This function returns 0 if success and appropriate error otherwise.
+ */
+static int sxgbe_config(struct net_device *dev, struct ifmap *map)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+
+	/* Can't act on a running interface */
+	if (dev->flags & IFF_UP)
+		return -EBUSY;
+
+	/* Don't allow changing the I/O address */
+	if (map->base_addr != (unsigned long)priv->ioaddr) {
+		netdev_warn(dev, "can't change I/O address\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* Don't allow changing the IRQ */
+	if (map->irq != priv->irq) {
+		netdev_warn(dev, "not change IRQ number %d\n", priv->irq);
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+/**
+ * sxgbe_poll_controller - entry point for polling receive by device
+ * @dev : pointer to the device structure
+ * Description:
+ * This function is used by NETCONSOLE and other diagnostic tools
+ * to allow network I/O with interrupts disabled.
+ * Return value:
+ * Void.
+ */
+static void sxgbe_poll_controller(struct net_device *dev)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+
+	disable_irq(priv->irq);
+	sxgbe_rx_interrupt(priv->irq, dev);
+	enable_irq(priv->irq);
+}
+#endif
+
+/*  sxgbe_ioctl - Entry point for the Ioctl
+ *  @dev: Device pointer.
+ *  @rq: An IOCTL specefic structure, that can contain a pointer to
+ *  a proprietary structure used to pass information to the driver.
+ *  @cmd: IOCTL command
+ *  Description:
+ *  Currently it supports the phy_mii_ioctl(...) and HW time stamping.
+ */
+static int sxgbe_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(dev);
+	int ret = -EOPNOTSUPP;
+
+	if (!netif_running(dev))
+		return -EINVAL;
+
+	switch (cmd) {
+	case SIOCGMIIPHY:
+	case SIOCGMIIREG:
+	case SIOCSMIIREG:
+		if (!priv->phydev)
+			return -EINVAL;
+		ret = phy_mii_ioctl(priv->phydev, rq, cmd);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static const struct net_device_ops sxgbe_netdev_ops = {
+	.ndo_open		= sxgbe_open,
+	.ndo_start_xmit		= sxgbe_xmit,
+	.ndo_stop		= sxgbe_release,
+	.ndo_get_stats64	= sxgbe_get_stats64,
+	.ndo_change_mtu		= sxgbe_change_mtu,
+	.ndo_set_features	= sxgbe_set_features,
+	.ndo_set_rx_mode	= sxgbe_set_rx_mode,
+	.ndo_tx_timeout		= sxgbe_tx_timeout,
+	.ndo_do_ioctl		= sxgbe_ioctl,
+	.ndo_set_config		= sxgbe_config,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= sxgbe_poll_controller,
+#endif
+	.ndo_set_mac_address	= eth_mac_addr,
+};
+
+/* Get the hardware ops */
+void sxgbe_get_ops(struct sxgbe_ops * const ops_ptr)
+{
+	ops_ptr->mac		= sxgbe_get_core_ops();
+	ops_ptr->desc		= sxgbe_get_desc_ops();
+	ops_ptr->dma		= sxgbe_get_dma_ops();
+	ops_ptr->mtl		= sxgbe_get_mtl_ops();
+
+	/* set the MDIO communication Address/Data regisers */
+	ops_ptr->mii.addr	= SXGBE_MDIO_SCMD_ADD_REG;
+	ops_ptr->mii.data	= SXGBE_MDIO_SCMD_DATA_REG;
+
+	/* Assigning the default link settings
+	 * no SXGBE defined default values to be set in registers,
+	 * so assigning as 0 for port and duplex
+	 */
+	ops_ptr->link.port	= 0;
+	ops_ptr->link.duplex	= 0;
+	ops_ptr->link.speed	= SXGBE_SPEED_10G;
+}
+
+/**
+ *  sxgbe_hw_init - Init the GMAC device
+ *  @priv: driver private structure
+ *  Description: this function checks the HW capability
+ *  (if supported) and sets the driver's features.
+ */
+static void sxgbe_hw_init(struct sxgbe_priv_data * const priv)
+{
+	u32 ctrl_ids;
+
+	priv->hw = kmalloc(sizeof(*priv->hw), GFP_KERNEL);
+
+	/* get the hardware ops */
+	sxgbe_get_ops(priv->hw);
+
+	/* get the controller id */
+	ctrl_ids = priv->hw->mac->get_controller_version(priv->ioaddr);
+	priv->hw->ctrl_uid = (ctrl_ids & 0x00ff0000) >> 16;
+	priv->hw->ctrl_id = (ctrl_ids & 0x000000ff);
+	pr_info("user ID: 0x%x, Controller ID: 0x%x\n",
+		priv->hw->ctrl_uid, priv->hw->ctrl_id);
+
+	/* get the H/W features */
+	if (!sxgbe_get_hw_features(priv))
+		pr_info("Hardware features not found\n");
+
+	if (priv->hw_cap.tx_csum_offload)
+		pr_info("TX Checksum offload supported\n");
+
+	if (priv->hw_cap.rx_csum_offload)
+		pr_info("RX Checksum offload supported\n");
+}
+
+/**
+ * sxgbe_drv_probe
+ * @device: device pointer
+ * @plat_dat: platform data pointer
+ * @addr: iobase memory address
+ * Description: this is the main probe function used to
+ * call the alloc_etherdev, allocate the priv structure.
+ */
+struct sxgbe_priv_data *sxgbe_drv_probe(struct device *device,
+					struct sxgbe_plat_data *plat_dat,
+					void __iomem *addr)
+{
+	struct sxgbe_priv_data *priv;
+	struct net_device *ndev;
+	int ret;
+
+	ndev = alloc_etherdev_mqs(sizeof(struct sxgbe_priv_data),
+				  SXGBE_TX_QUEUES, SXGBE_RX_QUEUES);
+	if (!ndev)
+		return NULL;
+
+	SET_NETDEV_DEV(ndev, device);
+
+	priv = netdev_priv(ndev);
+	priv->device = device;
+	priv->dev = ndev;
+
+	sxgbe_set_ethtool_ops(ndev);
+	priv->plat = plat_dat;
+	priv->ioaddr = addr;
+
+	/* Init MAC and get the capabilities */
+	sxgbe_hw_init(priv);
+
+	/* allocate memory resources for Descriptor rings */
+	ret = txring_mem_alloc(priv);
+	if (ret)
+		goto error_free_netdev;
+
+	ret = rxring_mem_alloc(priv);
+	if (ret)
+		goto error_free_netdev;
+
+	ndev->netdev_ops = &sxgbe_netdev_ops;
+
+	ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM;
+	ndev->features |= ndev->hw_features | NETIF_F_HIGHDMA;
+	ndev->watchdog_timeo = msecs_to_jiffies(TX_TIMEO);
+
+	/* assign filtering support */
+	ndev->priv_flags |= IFF_UNICAST_FLT;
+
+	priv->msg_enable = netif_msg_init(debug, default_msg_level);
+
+	/* Rx Watchdog is available, enable depend on platform data */
+	if (!priv->plat->riwt_off) {
+		priv->use_riwt = 1;
+		pr_info("Enable RX Mitigation via HW Watchdog Timer\n");
+	}
+
+	netif_napi_add(ndev, &priv->napi, sxgbe_poll, 64);
+
+	spin_lock_init(&priv->stats_lock);
+
+	priv->sxgbe_clk = clk_get(priv->device, SXGBE_RESOURCE_NAME);
+	if (IS_ERR(priv->sxgbe_clk)) {
+		netdev_warn(ndev, "%s: warning: cannot get CSR clock\n",
+			    __func__);
+		goto error_clk_get;
+	}
+
+	/* If a specific clk_csr value is passed from the platform
+	 * this means that the CSR Clock Range selection cannot be
+	 * changed at run-time and it is fixed. Viceversa the driver'll try to
+	 * set the MDC clock dynamically according to the csr actual
+	 * clock input.
+	 */
+	if (!priv->plat->clk_csr)
+		sxgbe_clk_csr_set(priv);
+	else
+		priv->clk_csr = priv->plat->clk_csr;
+
+	/* MDIO bus Registration */
+	ret = sxgbe_mdio_register(ndev);
+	if (ret < 0) {
+		netdev_dbg(ndev, "%s: MDIO bus (id: %d) registration failed\n",
+			   __func__, priv->plat->bus_id);
+		goto error_mdio_register;
+	}
+
+	ret = register_netdev(ndev);
+	if (ret) {
+		pr_err("%s: ERROR %i registering the device\n", __func__, ret);
+		goto error_netdev_register;
+	}
+
+	sxgbe_check_ether_addr(priv);
+
+	return priv;
+
+error_mdio_register:
+	clk_put(priv->sxgbe_clk);
+error_clk_get:
+error_netdev_register:
+	netif_napi_del(&priv->napi);
+error_free_netdev:
+	free_netdev(ndev);
+
+	return NULL;
+}
+
+/**
+ * sxgbe_drv_remove
+ * @ndev: net device pointer
+ * Description: this function resets the TX/RX processes, disables the MAC RX/TX
+ * changes the link status, releases the DMA descriptor rings.
+ */
+int sxgbe_drv_remove(struct net_device *ndev)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(ndev);
+
+	netdev_info(ndev, "%s: removing driver\n", __func__);
+
+	priv->hw->dma->stop_rx(priv->ioaddr, SXGBE_RX_QUEUES);
+	priv->hw->dma->stop_tx(priv->ioaddr, SXGBE_TX_QUEUES);
+
+	priv->hw->mac->enable_tx(priv->ioaddr, false);
+	priv->hw->mac->enable_rx(priv->ioaddr, false);
+
+	netif_napi_del(&priv->napi);
+
+	sxgbe_mdio_unregister(ndev);
+
+	unregister_netdev(ndev);
+
+	free_netdev(ndev);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+int sxgbe_suspend(struct net_device *ndev)
+{
+	return 0;
+}
+
+int sxgbe_resume(struct net_device *ndev)
+{
+	return 0;
+}
+
+int sxgbe_freeze(struct net_device *ndev)
+{
+	return -ENOSYS;
+}
+
+int sxgbe_restore(struct net_device *ndev)
+{
+	return -ENOSYS;
+}
+#endif /* CONFIG_PM */
+
+/* Driver is configured as Platform driver */
+static int __init sxgbe_init(void)
+{
+	int ret;
+
+	ret = sxgbe_register_platform();
+	if (ret)
+		goto err;
+	return 0;
+err:
+	pr_err("driver registration failed\n");
+	return ret;
+}
+
+static void __exit sxgbe_exit(void)
+{
+	sxgbe_unregister_platform();
+}
+
+module_init(sxgbe_init);
+module_exit(sxgbe_exit);
+
+#ifndef MODULE
+static int __init sxgbe_cmdline_opt(char *str)
+{
+	return 0;
+}
+
+__setup("sxgbeeth=", sxgbe_cmdline_opt);
+#endif /* MODULE */
+
+
+
+MODULE_DESCRIPTION("SAMSUNG 10G/2.5G/1G Ethernet PLATFORM driver");
+
+MODULE_PARM_DESC(debug, "Message Level (-1: default, 0: no output, 16: all)");
+
+MODULE_AUTHOR("Siva Reddy Kallam <siva.kallam@samsung.com>");
+MODULE_AUTHOR("ByungHo An <bh74.an@samsung.com>");
+MODULE_AUTHOR("Girish K S <ks.giri@samsung.com>");
+MODULE_AUTHOR("Vipul Pandya <vipul.pandya@samsung.com>");
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_mdio.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_mdio.c
new file mode 100644
index 000000000000..b0eb0a2c52ca
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_mdio.c
@@ -0,0 +1,251 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/io.h>
+#include <linux/mii.h>
+#include <linux/netdevice.h>
+#include <linux/platform_device.h>
+#include <linux/phy.h>
+#include <linux/slab.h>
+#include <linux/sxgbe_platform.h>
+
+#include "sxgbe_common.h"
+#include "sxgbe_reg.h"
+
+#define SXGBE_SMA_WRITE_CMD	0x01 /* write command */
+#define SXGBE_SMA_PREAD_CMD	0x02 /* post read  increament address */
+#define SXGBE_SMA_READ_CMD	0x03 /* read command */
+#define SXGBE_SMA_SKIP_ADDRFRM	0x00040000 /* skip the address frame */
+#define SXGBE_MII_BUSY		0x00800000 /* mii busy */
+
+static int sxgbe_mdio_busy_wait(void __iomem *ioaddr, unsigned int mii_data)
+{
+	unsigned long fin_time = jiffies + 3 * HZ; /* 3 seconds */
+
+	while (!time_after(jiffies, fin_time)) {
+		if (!(readl(ioaddr + mii_data) & SXGBE_MII_BUSY))
+			return 0;
+		cpu_relax();
+	}
+
+	return -EBUSY;
+}
+
+static void sxgbe_mdio_ctrl_data(struct sxgbe_priv_data *sp, u32 cmd,
+				 u16 phydata)
+{
+	u32 reg = phydata;
+
+	reg |= (cmd << 16) | SXGBE_SMA_SKIP_ADDRFRM |
+	       ((sp->clk_csr & 0x7) << 19) | SXGBE_MII_BUSY;
+	writel(reg, sp->ioaddr + sp->hw->mii.data);
+}
+
+static void sxgbe_mdio_c45(struct sxgbe_priv_data *sp, u32 cmd, int phyaddr,
+			   int phyreg, u16 phydata)
+{
+	u32 reg;
+
+	/* set mdio address register */
+	reg = ((phyreg >> 16) & 0x1f) << 21;
+	reg |= (phyaddr << 16) | (phyreg & 0xffff);
+	writel(reg, sp->ioaddr + sp->hw->mii.addr);
+
+	sxgbe_mdio_ctrl_data(sp, cmd, phydata);
+}
+
+static void sxgbe_mdio_c22(struct sxgbe_priv_data *sp, u32 cmd, int phyaddr,
+			   int phyreg, u16 phydata)
+{
+	u32 reg;
+
+	writel(1 << phyaddr, sp->ioaddr + SXGBE_MDIO_CLAUSE22_PORT_REG);
+
+	/* set mdio address register */
+	reg = (phyaddr << 16) | (phyreg & 0x1f);
+	writel(reg, sp->ioaddr + sp->hw->mii.addr);
+
+	sxgbe_mdio_ctrl_data(sp, cmd, phydata);
+}
+
+static int sxgbe_mdio_access(struct sxgbe_priv_data *sp, u32 cmd, int phyaddr,
+			     int phyreg, u16 phydata)
+{
+	const struct mii_regs *mii = &sp->hw->mii;
+	int rc;
+
+	rc = sxgbe_mdio_busy_wait(sp->ioaddr, mii->data);
+	if (rc < 0)
+		return rc;
+
+	if (phyreg & MII_ADDR_C45) {
+		sxgbe_mdio_c45(sp, cmd, phyaddr, phyreg, phydata);
+	} else {
+		 /* Ports 0-3 only support C22. */
+		if (phyaddr >= 4)
+			return -ENODEV;
+
+		sxgbe_mdio_c22(sp, cmd, phyaddr, phyreg, phydata);
+	}
+
+	return sxgbe_mdio_busy_wait(sp->ioaddr, mii->data);
+}
+
+/**
+ * sxgbe_mdio_read
+ * @bus: points to the mii_bus structure
+ * @phyaddr: address of phy port
+ * @phyreg: address of register with in phy register
+ * Description: this function used for C45 and C22 MDIO Read
+ */
+static int sxgbe_mdio_read(struct mii_bus *bus, int phyaddr, int phyreg)
+{
+	struct net_device *ndev = bus->priv;
+	struct sxgbe_priv_data *priv = netdev_priv(ndev);
+	int rc;
+
+	rc = sxgbe_mdio_access(priv, SXGBE_SMA_READ_CMD, phyaddr, phyreg, 0);
+	if (rc < 0)
+		return rc;
+
+	return readl(priv->ioaddr + priv->hw->mii.data) & 0xffff;
+}
+
+/**
+ * sxgbe_mdio_write
+ * @bus: points to the mii_bus structure
+ * @phyaddr: address of phy port
+ * @phyreg: address of phy registers
+ * @phydata: data to be written into phy register
+ * Description: this function is used for C45 and C22 MDIO write
+ */
+static int sxgbe_mdio_write(struct mii_bus *bus, int phyaddr, int phyreg,
+			     u16 phydata)
+{
+	struct net_device *ndev = bus->priv;
+	struct sxgbe_priv_data *priv = netdev_priv(ndev);
+
+	return sxgbe_mdio_access(priv, SXGBE_SMA_WRITE_CMD, phyaddr, phyreg,
+				 phydata);
+}
+
+int sxgbe_mdio_register(struct net_device *ndev)
+{
+	struct mii_bus *mdio_bus;
+	struct sxgbe_priv_data *priv = netdev_priv(ndev);
+	struct sxgbe_mdio_bus_data *mdio_data = priv->plat->mdio_bus_data;
+	int err, phy_addr;
+	int *irqlist;
+	bool act;
+
+	/* allocate the new mdio bus */
+	mdio_bus = mdiobus_alloc();
+	if (!mdio_bus) {
+		netdev_err(ndev, "%s: mii bus allocation failed\n", __func__);
+		return -ENOMEM;
+	}
+
+	if (mdio_data->irqs)
+		irqlist = mdio_data->irqs;
+	else
+		irqlist = priv->mii_irq;
+
+	/* assign mii bus fields */
+	mdio_bus->name = "samsxgbe";
+	mdio_bus->read = &sxgbe_mdio_read;
+	mdio_bus->write = &sxgbe_mdio_write;
+	snprintf(mdio_bus->id, MII_BUS_ID_SIZE, "%s-%x",
+		 mdio_bus->name, priv->plat->bus_id);
+	mdio_bus->priv = ndev;
+	mdio_bus->phy_mask = mdio_data->phy_mask;
+	mdio_bus->parent = priv->device;
+
+	/* register with kernel subsystem */
+	err = mdiobus_register(mdio_bus);
+	if (err != 0) {
+		netdev_err(ndev, "mdiobus register failed\n");
+		goto mdiobus_err;
+	}
+
+	for (phy_addr = 0; phy_addr < PHY_MAX_ADDR; phy_addr++) {
+		struct phy_device *phy = mdio_bus->phy_map[phy_addr];
+
+		if (phy) {
+			char irq_num[4];
+			char *irq_str;
+			/* If an IRQ was provided to be assigned after
+			 * the bus probe, do it here.
+			 */
+			if ((mdio_data->irqs == NULL) &&
+			    (mdio_data->probed_phy_irq > 0)) {
+				irqlist[phy_addr] = mdio_data->probed_phy_irq;
+				phy->irq = mdio_data->probed_phy_irq;
+			}
+
+			/* If we're  going to bind the MAC to this PHY bus,
+			 * and no PHY number was provided to the MAC,
+			 * use the one probed here.
+			 */
+			if (priv->plat->phy_addr == -1)
+				priv->plat->phy_addr = phy_addr;
+
+			act = (priv->plat->phy_addr == phy_addr);
+			switch (phy->irq) {
+			case PHY_POLL:
+				irq_str = "POLL";
+				break;
+			case PHY_IGNORE_INTERRUPT:
+				irq_str = "IGNORE";
+				break;
+			default:
+				sprintf(irq_num, "%d", phy->irq);
+				irq_str = irq_num;
+				break;
+			}
+			netdev_info(ndev, "PHY ID %08x at %d IRQ %s (%s)%s\n",
+				    phy->phy_id, phy_addr, irq_str,
+				    dev_name(&phy->dev), act ? " active" : "");
+		}
+	}
+
+	if (!err) {
+		netdev_err(ndev, "PHY not found\n");
+		mdiobus_unregister(mdio_bus);
+		mdiobus_free(mdio_bus);
+		goto mdiobus_err;
+	}
+
+	priv->mii = mdio_bus;
+
+	return 0;
+
+mdiobus_err:
+	mdiobus_free(mdio_bus);
+	return err;
+}
+
+int sxgbe_mdio_unregister(struct net_device *ndev)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(ndev);
+
+	if (!priv->mii)
+		return 0;
+
+	mdiobus_unregister(priv->mii);
+	priv->mii->priv = NULL;
+	mdiobus_free(priv->mii);
+	priv->mii = NULL;
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.c
new file mode 100644
index 000000000000..324681c2bb74
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.c
@@ -0,0 +1,254 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/io.h>
+#include <linux/errno.h>
+#include <linux/export.h>
+#include <linux/jiffies.h>
+
+#include "sxgbe_mtl.h"
+#include "sxgbe_reg.h"
+
+static void sxgbe_mtl_init(void __iomem *ioaddr, unsigned int etsalg,
+			   unsigned int raa)
+{
+	u32 reg_val;
+
+	reg_val = readl(ioaddr + SXGBE_MTL_OP_MODE_REG);
+	reg_val &= ETS_RST;
+
+	/* ETS Algorith */
+	switch (etsalg & SXGBE_MTL_OPMODE_ESTMASK) {
+	case ETS_WRR:
+		reg_val &= ETS_WRR;
+		break;
+	case ETS_WFQ:
+		reg_val |= ETS_WFQ;
+		break;
+	case ETS_DWRR:
+		reg_val |= ETS_DWRR;
+		break;
+	}
+	writel(reg_val, ioaddr + SXGBE_MTL_OP_MODE_REG);
+
+	switch (raa & SXGBE_MTL_OPMODE_RAAMASK) {
+	case RAA_SP:
+		reg_val &= RAA_SP;
+		break;
+	case RAA_WSP:
+		reg_val |= RAA_WSP;
+		break;
+	}
+	writel(reg_val, ioaddr + SXGBE_MTL_OP_MODE_REG);
+}
+
+/* For Dynamic DMA channel mapping for Rx queue */
+static void sxgbe_mtl_dma_dm_rxqueue(void __iomem *ioaddr)
+{
+	writel(RX_QUEUE_DYNAMIC, ioaddr + SXGBE_MTL_RXQ_DMAMAP0_REG);
+	writel(RX_QUEUE_DYNAMIC, ioaddr + SXGBE_MTL_RXQ_DMAMAP1_REG);
+	writel(RX_QUEUE_DYNAMIC, ioaddr + SXGBE_MTL_RXQ_DMAMAP2_REG);
+}
+
+static void sxgbe_mtl_set_txfifosize(void __iomem *ioaddr, int queue_num,
+				     int queue_fifo)
+{
+	u32 fifo_bits, reg_val;
+
+	/* 0 means 256 bytes */
+	fifo_bits = (queue_fifo / SXGBE_MTL_TX_FIFO_DIV) - 1;
+	reg_val = readl(ioaddr + SXGBE_MTL_TXQ_OPMODE_REG(queue_num));
+	reg_val |= (fifo_bits << SXGBE_MTL_FIFO_LSHIFT);
+	writel(reg_val, ioaddr + SXGBE_MTL_TXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_mtl_set_rxfifosize(void __iomem *ioaddr, int queue_num,
+				     int queue_fifo)
+{
+	u32 fifo_bits, reg_val;
+
+	/* 0 means 256 bytes */
+	fifo_bits = (queue_fifo / SXGBE_MTL_RX_FIFO_DIV)-1;
+	reg_val = readl(ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+	reg_val |= (fifo_bits << SXGBE_MTL_FIFO_LSHIFT);
+	writel(reg_val, ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_mtl_enable_txqueue(void __iomem *ioaddr, int queue_num)
+{
+	u32 reg_val;
+
+	reg_val = readl(ioaddr + SXGBE_MTL_TXQ_OPMODE_REG(queue_num));
+	reg_val |= SXGBE_MTL_ENABLE_QUEUE;
+	writel(reg_val, ioaddr + SXGBE_MTL_TXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_mtl_disable_txqueue(void __iomem *ioaddr, int queue_num)
+{
+	u32 reg_val;
+
+	reg_val = readl(ioaddr + SXGBE_MTL_TXQ_OPMODE_REG(queue_num));
+	reg_val &= ~SXGBE_MTL_ENABLE_QUEUE;
+	writel(reg_val, ioaddr + SXGBE_MTL_TXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_mtl_fc_active(void __iomem *ioaddr, int queue_num,
+				int threshold)
+{
+	u32 reg_val;
+
+	reg_val = readl(ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+	reg_val &= ~(SXGBE_MTL_FCMASK << RX_FC_ACTIVE);
+	reg_val |= (threshold << RX_FC_ACTIVE);
+
+	writel(reg_val, ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_mtl_fc_enable(void __iomem *ioaddr, int queue_num)
+{
+	u32 reg_val;
+
+	reg_val = readl(ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+	reg_val |= SXGBE_MTL_ENABLE_FC;
+	writel(reg_val, ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_mtl_fc_deactive(void __iomem *ioaddr, int queue_num,
+				  int threshold)
+{
+	u32 reg_val;
+
+	reg_val = readl(ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+	reg_val &= ~(SXGBE_MTL_FCMASK << RX_FC_DEACTIVE);
+	reg_val |= (threshold << RX_FC_DEACTIVE);
+
+	writel(reg_val, ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_mtl_fep_enable(void __iomem *ioaddr, int queue_num)
+{
+	u32 reg_val;
+
+	reg_val = readl(ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+	reg_val |= SXGBE_MTL_RXQ_OP_FEP;
+
+	writel(reg_val, ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_mtl_fep_disable(void __iomem *ioaddr, int queue_num)
+{
+	u32 reg_val;
+
+	reg_val = readl(ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+	reg_val &= ~(SXGBE_MTL_RXQ_OP_FEP);
+
+	writel(reg_val, ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_mtl_fup_enable(void __iomem *ioaddr, int queue_num)
+{
+	u32 reg_val;
+
+	reg_val = readl(ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+	reg_val |= SXGBE_MTL_RXQ_OP_FUP;
+
+	writel(reg_val, ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_mtl_fup_disable(void __iomem *ioaddr, int queue_num)
+{
+	u32 reg_val;
+
+	reg_val = readl(ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+	reg_val &= ~(SXGBE_MTL_RXQ_OP_FUP);
+
+	writel(reg_val, ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+}
+
+
+static void sxgbe_set_tx_mtl_mode(void __iomem *ioaddr, int queue_num,
+				  int tx_mode)
+{
+	u32 reg_val;
+
+	reg_val = readl(ioaddr + SXGBE_MTL_TXQ_OPMODE_REG(queue_num));
+	/* TX specific MTL mode settings */
+	if (tx_mode == SXGBE_MTL_SFMODE) {
+		reg_val |= SXGBE_MTL_SFMODE;
+	} else {
+		/* set the TTC values */
+		if (tx_mode <= 64)
+			reg_val |= MTL_CONTROL_TTC_64;
+		else if (tx_mode <= 96)
+			reg_val |= MTL_CONTROL_TTC_96;
+		else if (tx_mode <= 128)
+			reg_val |= MTL_CONTROL_TTC_128;
+		else if (tx_mode <= 192)
+			reg_val |= MTL_CONTROL_TTC_192;
+		else if (tx_mode <= 256)
+			reg_val |= MTL_CONTROL_TTC_256;
+		else if (tx_mode <= 384)
+			reg_val |= MTL_CONTROL_TTC_384;
+		else
+			reg_val |= MTL_CONTROL_TTC_512;
+	}
+
+	/* write into TXQ operation register */
+	writel(reg_val, ioaddr + SXGBE_MTL_TXQ_OPMODE_REG(queue_num));
+}
+
+static void sxgbe_set_rx_mtl_mode(void __iomem *ioaddr, int queue_num,
+				  int rx_mode)
+{
+	u32 reg_val;
+
+	reg_val = readl(ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+	/* RX specific MTL mode settings */
+	if (rx_mode == SXGBE_RX_MTL_SFMODE) {
+		reg_val |= SXGBE_RX_MTL_SFMODE;
+	} else {
+		if (rx_mode <= 64)
+			reg_val |= MTL_CONTROL_RTC_64;
+		else if (rx_mode <= 96)
+			reg_val |= MTL_CONTROL_RTC_96;
+		else if (rx_mode <= 128)
+			reg_val |= MTL_CONTROL_RTC_128;
+	}
+
+	/* write into RXQ operation register */
+	writel(reg_val, ioaddr + SXGBE_MTL_RXQ_OPMODE_REG(queue_num));
+}
+
+static const struct sxgbe_mtl_ops mtl_ops = {
+	.mtl_set_txfifosize		= sxgbe_mtl_set_txfifosize,
+	.mtl_set_rxfifosize		= sxgbe_mtl_set_rxfifosize,
+	.mtl_enable_txqueue		= sxgbe_mtl_enable_txqueue,
+	.mtl_disable_txqueue		= sxgbe_mtl_disable_txqueue,
+	.mtl_dynamic_dma_rxqueue	= sxgbe_mtl_dma_dm_rxqueue,
+	.set_tx_mtl_mode		= sxgbe_set_tx_mtl_mode,
+	.set_rx_mtl_mode		= sxgbe_set_rx_mtl_mode,
+	.mtl_init			= sxgbe_mtl_init,
+	.mtl_fc_active			= sxgbe_mtl_fc_active,
+	.mtl_fc_deactive		= sxgbe_mtl_fc_deactive,
+	.mtl_fc_enable			= sxgbe_mtl_fc_enable,
+	.mtl_fep_enable			= sxgbe_mtl_fep_enable,
+	.mtl_fep_disable		= sxgbe_mtl_fep_disable,
+	.mtl_fup_enable			= sxgbe_mtl_fup_enable,
+	.mtl_fup_disable		= sxgbe_mtl_fup_disable
+};
+
+const struct sxgbe_mtl_ops *sxgbe_get_mtl_ops(void)
+{
+	return &mtl_ops;
+}
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.h
new file mode 100644
index 000000000000..7e4810c4137e
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_mtl.h
@@ -0,0 +1,104 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __SXGBE_MTL_H__
+#define __SXGBE_MTL_H__
+
+#define SXGBE_MTL_OPMODE_ESTMASK	0x3
+#define SXGBE_MTL_OPMODE_RAAMASK	0x1
+#define SXGBE_MTL_FCMASK		0x7
+#define SXGBE_MTL_TX_FIFO_DIV		256
+#define SXGBE_MTL_RX_FIFO_DIV		256
+
+#define SXGBE_MTL_RXQ_OP_FEP		BIT(4)
+#define SXGBE_MTL_RXQ_OP_FUP		BIT(3)
+#define SXGBE_MTL_ENABLE_FC		0x80
+
+#define ETS_WRR				0xFFFFFF9F
+#define ETS_RST				0xFFFFFF9F
+#define ETS_WFQ				0x00000020
+#define ETS_DWRR			0x00000040
+#define RAA_SP				0xFFFFFFFB
+#define RAA_WSP				0x00000004
+
+#define RX_QUEUE_DYNAMIC		0x80808080
+#define RX_FC_ACTIVE			8
+#define RX_FC_DEACTIVE			13
+
+enum ttc_control {
+	MTL_CONTROL_TTC_64 = 0x00000000,
+	MTL_CONTROL_TTC_96 = 0x00000020,
+	MTL_CONTROL_TTC_128 = 0x00000030,
+	MTL_CONTROL_TTC_192 = 0x00000040,
+	MTL_CONTROL_TTC_256 = 0x00000050,
+	MTL_CONTROL_TTC_384 = 0x00000060,
+	MTL_CONTROL_TTC_512 = 0x00000070,
+};
+
+enum rtc_control {
+	MTL_CONTROL_RTC_64 = 0x00000000,
+	MTL_CONTROL_RTC_96 = 0x00000002,
+	MTL_CONTROL_RTC_128 = 0x00000003,
+};
+
+enum flow_control_th {
+	MTL_FC_FULL_1K = 0x00000000,
+	MTL_FC_FULL_2K = 0x00000001,
+	MTL_FC_FULL_4K = 0x00000002,
+	MTL_FC_FULL_5K = 0x00000003,
+	MTL_FC_FULL_6K = 0x00000004,
+	MTL_FC_FULL_8K = 0x00000005,
+	MTL_FC_FULL_16K = 0x00000006,
+	MTL_FC_FULL_24K = 0x00000007,
+};
+
+struct sxgbe_mtl_ops {
+	void (*mtl_init)(void __iomem *ioaddr, unsigned int etsalg,
+			 unsigned int raa);
+
+	void (*mtl_set_txfifosize)(void __iomem *ioaddr, int queue_num,
+				   int mtl_fifo);
+
+	void (*mtl_set_rxfifosize)(void __iomem *ioaddr, int queue_num,
+				   int queue_fifo);
+
+	void (*mtl_enable_txqueue)(void __iomem *ioaddr, int queue_num);
+
+	void (*mtl_disable_txqueue)(void __iomem *ioaddr, int queue_num);
+
+	void (*set_tx_mtl_mode)(void __iomem *ioaddr, int queue_num,
+				int tx_mode);
+
+	void (*set_rx_mtl_mode)(void __iomem *ioaddr, int queue_num,
+				int rx_mode);
+
+	void (*mtl_dynamic_dma_rxqueue)(void __iomem *ioaddr);
+
+	void (*mtl_fc_active)(void __iomem *ioaddr, int queue_num,
+			      int threshold);
+
+	void (*mtl_fc_deactive)(void __iomem *ioaddr, int queue_num,
+				int threshold);
+
+	void (*mtl_fc_enable)(void __iomem *ioaddr, int queue_num);
+
+	void (*mtl_fep_enable)(void __iomem *ioaddr, int queue_num);
+
+	void (*mtl_fep_disable)(void __iomem *ioaddr, int queue_num);
+
+	void (*mtl_fup_enable)(void __iomem *ioaddr, int queue_num);
+
+	void (*mtl_fup_disable)(void __iomem *ioaddr, int queue_num);
+};
+
+const struct sxgbe_mtl_ops *sxgbe_get_mtl_ops(void);
+
+#endif /* __SXGBE_MTL_H__ */
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c
new file mode 100644
index 000000000000..f5a9de710052
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c
@@ -0,0 +1,253 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/etherdevice.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_net.h>
+#include <linux/phy.h>
+#include <linux/platform_device.h>
+#include <linux/sxgbe_platform.h>
+
+#include "sxgbe_common.h"
+#include "sxgbe_reg.h"
+
+#ifdef CONFIG_OF
+static int sxgbe_probe_config_dt(struct platform_device *pdev,
+				 struct sxgbe_plat_data *plat,
+				 const char **mac)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct sxgbe_dma_cfg *dma_cfg;
+
+	if (!np)
+		return -ENODEV;
+
+	*mac = of_get_mac_address(np);
+	plat->interface = of_get_phy_mode(np);
+
+	plat->bus_id = of_alias_get_id(np, "ethernet");
+	if (plat->bus_id < 0)
+		plat->bus_id = 0;
+
+	plat->mdio_bus_data = devm_kzalloc(&pdev->dev,
+					   sizeof(*plat->mdio_bus_data),
+					   GFP_KERNEL);
+
+	dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*dma_cfg), GFP_KERNEL);
+	if (!dma_cfg)
+		return -ENOMEM;
+
+	plat->dma_cfg = dma_cfg;
+	of_property_read_u32(np, "samsung,pbl", &dma_cfg->pbl);
+	if (of_property_read_u32(np, "samsung,burst-map", &dma_cfg->burst_map) == 0)
+		dma_cfg->fixed_burst = true;
+
+	return 0;
+}
+#else
+static int sxgbe_probe_config_dt(struct platform_device *pdev,
+				 struct sxgbe_plat_data *plat,
+				 const char **mac)
+{
+	return -ENOSYS;
+}
+#endif /* CONFIG_OF */
+
+/**
+ * sxgbe_platform_probe
+ * @pdev: platform device pointer
+ * Description: platform_device probe function. It allocates
+ * the necessary resources and invokes the main to init
+ * the net device, register the mdio bus etc.
+ */
+static int sxgbe_platform_probe(struct platform_device *pdev)
+{
+	int ret;
+	int i, chan;
+	struct resource *res;
+	struct device *dev = &pdev->dev;
+	void __iomem *addr;
+	struct sxgbe_priv_data *priv = NULL;
+	struct sxgbe_plat_data *plat_dat = NULL;
+	const char *mac = NULL;
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct device_node *node = dev->of_node;
+
+	/* Get memory resource */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		goto err_out;
+
+	addr = devm_ioremap_resource(dev, res);
+	if (IS_ERR(addr))
+		return PTR_ERR(addr);
+
+	if (pdev->dev.of_node) {
+		plat_dat = devm_kzalloc(&pdev->dev,
+					sizeof(struct sxgbe_plat_data),
+					GFP_KERNEL);
+		if (!plat_dat)
+			return  -ENOMEM;
+
+		ret = sxgbe_probe_config_dt(pdev, plat_dat, &mac);
+		if (ret) {
+			pr_err("%s: main dt probe failed\n", __func__);
+			return ret;
+		}
+	}
+
+	/* Get MAC address if available (DT) */
+	if (mac)
+		ether_addr_copy(priv->dev->dev_addr, mac);
+
+	priv = sxgbe_drv_probe(&(pdev->dev), plat_dat, addr);
+	if (!priv) {
+		pr_err("%s: main driver probe failed\n", __func__);
+		goto err_out;
+	}
+
+	/* Get the SXGBE common INT information */
+	priv->irq  = irq_of_parse_and_map(node, 0);
+	if (priv->irq <= 0) {
+		dev_err(dev, "sxgbe common irq parsing failed\n");
+		goto err_drv_remove;
+	}
+
+	/* Get the TX/RX IRQ numbers */
+	for (i = 0, chan = 1; i < SXGBE_TX_QUEUES; i++) {
+		priv->txq[i]->irq_no = irq_of_parse_and_map(node, chan++);
+		if (priv->txq[i]->irq_no <= 0) {
+			dev_err(dev, "sxgbe tx irq parsing failed\n");
+			goto err_tx_irq_unmap;
+		}
+	}
+
+	for (i = 0; i < SXGBE_RX_QUEUES; i++) {
+		priv->rxq[i]->irq_no = irq_of_parse_and_map(node, chan++);
+		if (priv->rxq[i]->irq_no <= 0) {
+			dev_err(dev, "sxgbe rx irq parsing failed\n");
+			goto err_rx_irq_unmap;
+		}
+	}
+
+	platform_set_drvdata(pdev, priv->dev);
+
+	pr_debug("platform driver registration completed\n");
+
+	return 0;
+
+err_rx_irq_unmap:
+	while (--i)
+		irq_dispose_mapping(priv->rxq[i]->irq_no);
+	i = SXGBE_TX_QUEUES;
+err_tx_irq_unmap:
+	while (--i)
+		irq_dispose_mapping(priv->txq[i]->irq_no);
+	irq_dispose_mapping(priv->irq);
+err_drv_remove:
+	sxgbe_drv_remove(ndev);
+err_out:
+	return -ENODEV;
+}
+
+/**
+ * sxgbe_platform_remove
+ * @pdev: platform device pointer
+ * Description: this function calls the main to free the net resources
+ * and calls the platforms hook and release the resources (e.g. mem).
+ */
+static int sxgbe_platform_remove(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	int ret = sxgbe_drv_remove(ndev);
+
+	return ret;
+}
+
+#ifdef CONFIG_PM
+static int sxgbe_platform_suspend(struct device *dev)
+{
+	struct net_device *ndev = dev_get_drvdata(dev);
+
+	return sxgbe_suspend(ndev);
+}
+
+static int sxgbe_platform_resume(struct device *dev)
+{
+	struct net_device *ndev = dev_get_drvdata(dev);
+
+	return sxgbe_resume(ndev);
+}
+
+int sxgbe_platform_freeze(struct device *dev)
+{
+	struct net_device *ndev = dev_get_drvdata(dev);
+
+	return sxgbe_freeze(ndev);
+}
+
+int sxgbe_platform_restore(struct device *dev)
+{
+	struct net_device *ndev = dev_get_drvdata(dev);
+
+	return sxgbe_restore(ndev);
+}
+
+static const struct dev_pm_ops sxgbe_platform_pm_ops = {
+	.suspend	= sxgbe_platform_suspend,
+	.resume		= sxgbe_platform_resume,
+	.freeze		= sxgbe_platform_freeze,
+	.thaw		= sxgbe_platform_restore,
+	.restore	= sxgbe_platform_restore,
+};
+#else
+static const struct dev_pm_ops sxgbe_platform_pm_ops;
+#endif /* CONFIG_PM */
+
+static const struct of_device_id sxgbe_dt_ids[] = {
+	{ .compatible = "samsung,sxgbe-v2.0a"},
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, sxgbe_dt_ids);
+
+struct platform_driver sxgbe_platform_driver = {
+	.probe	= sxgbe_platform_probe,
+	.remove	= sxgbe_platform_remove,
+	.driver	= {
+		.name		= SXGBE_RESOURCE_NAME,
+		.owner		= THIS_MODULE,
+		.pm		= &sxgbe_platform_pm_ops,
+		.of_match_table	= of_match_ptr(sxgbe_dt_ids),
+	},
+};
+
+int sxgbe_register_platform(void)
+{
+	int err;
+
+	err = platform_driver_register(&sxgbe_platform_driver);
+	if (err)
+		pr_err("failed to register the platform driver\n");
+
+	return err;
+}
+
+void sxgbe_unregister_platform(void)
+{
+	platform_driver_unregister(&sxgbe_platform_driver);
+}
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_reg.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_reg.h
new file mode 100644
index 000000000000..d1cd9ac1b062
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_reg.h
@@ -0,0 +1,477 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __SXGBE_REGMAP_H__
+#define __SXGBE_REGMAP_H__
+
+/* SXGBE MAC Registers */
+#define SXGBE_CORE_TX_CONFIG_REG	0x0000
+#define SXGBE_CORE_RX_CONFIG_REG	0x0004
+#define SXGBE_CORE_PKT_FILTER_REG	0x0008
+#define SXGBE_CORE_WATCHDOG_TIMEOUT_REG 0x000C
+#define SXGBE_CORE_HASH_TABLE_REG0	0x0010
+#define SXGBE_CORE_HASH_TABLE_REG1	0x0014
+#define SXGBE_CORE_HASH_TABLE_REG2	0x0018
+#define SXGBE_CORE_HASH_TABLE_REG3	0x001C
+#define SXGBE_CORE_HASH_TABLE_REG4	0x0020
+#define SXGBE_CORE_HASH_TABLE_REG5	0x0024
+#define SXGBE_CORE_HASH_TABLE_REG6	0x0028
+#define SXGBE_CORE_HASH_TABLE_REG7	0x002C
+/* VLAN Specific Registers */
+#define SXGBE_CORE_VLAN_TAG_REG		0x0050
+#define SXGBE_CORE_VLAN_HASHTAB_REG	0x0058
+#define SXGBE_CORE_VLAN_INSCTL_REG	0x0060
+#define SXGBE_CORE_VLAN_INNERCTL_REG	0x0064
+#define SXGBE_CORE_RX_ETHTYPE_MATCH_REG 0x006C
+
+/* Flow Contol Registers */
+#define SXGBE_CORE_TX_Q0_FLOWCTL_REG	0x0070
+#define SXGBE_CORE_TX_Q1_FLOWCTL_REG	0x0074
+#define SXGBE_CORE_TX_Q2_FLOWCTL_REG	0x0078
+#define SXGBE_CORE_TX_Q3_FLOWCTL_REG	0x007C
+#define SXGBE_CORE_TX_Q4_FLOWCTL_REG	0x0080
+#define SXGBE_CORE_TX_Q5_FLOWCTL_REG	0x0084
+#define SXGBE_CORE_TX_Q6_FLOWCTL_REG	0x0088
+#define SXGBE_CORE_TX_Q7_FLOWCTL_REG	0x008C
+#define SXGBE_CORE_RX_FLOWCTL_REG	0x0090
+#define SXGBE_CORE_RX_CTL0_REG		0x00A0
+#define SXGBE_CORE_RX_CTL1_REG		0x00A4
+#define SXGBE_CORE_RX_CTL2_REG		0x00A8
+#define SXGBE_CORE_RX_CTL3_REG		0x00AC
+
+/* Interrupt Registers */
+#define SXGBE_CORE_INT_STATUS_REG	0x00B0
+#define SXGBE_CORE_INT_ENABLE_REG	0x00B4
+#define SXGBE_CORE_RXTX_ERR_STATUS_REG	0x00B8
+#define SXGBE_CORE_PMT_CTL_STATUS_REG	0x00C0
+#define SXGBE_CORE_RWK_PKT_FILTER_REG	0x00C4
+#define SXGBE_CORE_VERSION_REG		0x0110
+#define SXGBE_CORE_DEBUG_REG		0x0114
+#define SXGBE_CORE_HW_FEA_REG(index)	(0x011C + index * 4)
+
+/* SMA(MDIO) module registers */
+#define SXGBE_MDIO_SCMD_ADD_REG		0x0200
+#define SXGBE_MDIO_SCMD_DATA_REG	0x0204
+#define SXGBE_MDIO_CCMD_WADD_REG	0x0208
+#define SXGBE_MDIO_CCMD_WDATA_REG	0x020C
+#define SXGBE_MDIO_CSCAN_PORT_REG	0x0210
+#define SXGBE_MDIO_INT_STATUS_REG	0x0214
+#define SXGBE_MDIO_INT_ENABLE_REG	0x0218
+#define SXGBE_MDIO_PORT_CONDCON_REG	0x021C
+#define SXGBE_MDIO_CLAUSE22_PORT_REG	0x0220
+
+/* port specific, addr = 0-3 */
+#define SXGBE_MDIO_DEV_BASE_REG		0x0230
+#define SXGBE_MDIO_PORT_DEV_REG(addr)			\
+	(SXGBE_MDIO_DEV_BASE_REG + (0x10 * addr) + 0x0)
+#define SXGBE_MDIO_PORT_LSTATUS_REG(addr)		\
+	(SXGBE_MDIO_DEV_BASE_REG + (0x10 * addr) + 0x4)
+#define SXGBE_MDIO_PORT_ALIVE_REG(addr)			\
+	(SXGBE_MDIO_DEV_BASE_REG + (0x10 * addr) + 0x8)
+
+#define SXGBE_CORE_GPIO_CTL_REG		0x0278
+#define SXGBE_CORE_GPIO_STATUS_REG	0x027C
+
+/* Address registers for filtering */
+#define SXGBE_CORE_ADD_BASE_REG		0x0300
+
+/* addr = 0-31 */
+#define SXGBE_CORE_ADD_HIGHOFFSET(addr)			\
+	(SXGBE_CORE_ADD_BASE_REG + (0x8 * addr) + 0x0)
+#define SXGBE_CORE_ADD_LOWOFFSET(addr)			\
+	(SXGBE_CORE_ADD_BASE_REG + (0x8 * addr) + 0x4)
+
+/* SXGBE MMC registers */
+#define SXGBE_MMC_CTL_REG		0x0800
+#define SXGBE_MMC_RXINT_STATUS_REG	0x0804
+#define SXGBE_MMC_TXINT_STATUS_REG	0x0808
+#define SXGBE_MMC_RXINT_ENABLE_REG	0x080C
+#define SXGBE_MMC_TXINT_ENABLE_REG	0x0810
+
+/* TX specific counters */
+#define SXGBE_MMC_TXOCTETHI_GBCNT_REG	0x0814
+#define SXGBE_MMC_TXOCTETLO_GBCNT_REG	0x0818
+#define SXGBE_MMC_TXFRAMELO_GBCNT_REG	0x081C
+#define SXGBE_MMC_TXFRAMEHI_GBCNT_REG	0x0820
+#define SXGBE_MMC_TXBROADLO_GCNT_REG	0x0824
+#define SXGBE_MMC_TXBROADHI_GCNT_REG	0x0828
+#define SXGBE_MMC_TXMULTILO_GCNT_REG	0x082C
+#define SXGBE_MMC_TXMULTIHI_GCNT_REG	0x0830
+#define SXGBE_MMC_TX64LO_GBCNT_REG	0x0834
+#define SXGBE_MMC_TX64HI_GBCNT_REG	0x0838
+#define SXGBE_MMC_TX65TO127LO_GBCNT_REG		0x083C
+#define SXGBE_MMC_TX65TO127HI_GBCNT_REG		0x0840
+#define SXGBE_MMC_TX128TO255LO_GBCNT_REG	0x0844
+#define SXGBE_MMC_TX128TO255HI_GBCNT_REG	0x0848
+#define SXGBE_MMC_TX256TO511LO_GBCNT_REG	0x084C
+#define SXGBE_MMC_TX256TO511HI_GBCNT_REG	0x0850
+#define SXGBE_MMC_TX512TO1023LO_GBCNT_REG	0x0854
+#define SXGBE_MMC_TX512TO1023HI_GBCNT_REG	0x0858
+#define SXGBE_MMC_TX1023TOMAXLO_GBCNT_REG	0x085C
+#define SXGBE_MMC_TX1023TOMAXHI_GBCNT_REG	0x0860
+#define SXGBE_MMC_TXUNICASTLO_GBCNT_REG		0x0864
+#define SXGBE_MMC_TXUNICASTHI_GBCNT_REG		0x0868
+#define SXGBE_MMC_TXMULTILO_GBCNT_REG		0x086C
+#define SXGBE_MMC_TXMULTIHI_GBCNT_REG		0x0870
+#define SXGBE_MMC_TXBROADLO_GBCNT_REG		0x0874
+#define SXGBE_MMC_TXBROADHI_GBCNT_REG		0x0878
+#define SXGBE_MMC_TXUFLWLO_GBCNT_REG		0x087C
+#define SXGBE_MMC_TXUFLWHI_GBCNT_REG		0x0880
+#define SXGBE_MMC_TXOCTETLO_GCNT_REG	0x0884
+#define SXGBE_MMC_TXOCTETHI_GCNT_REG	0x0888
+#define SXGBE_MMC_TXFRAMELO_GCNT_REG	0x088C
+#define SXGBE_MMC_TXFRAMEHI_GCNT_REG	0x0890
+#define SXGBE_MMC_TXPAUSELO_CNT_REG	0x0894
+#define SXGBE_MMC_TXPAUSEHI_CNT_REG	0x0898
+#define SXGBE_MMC_TXVLANLO_GCNT_REG	0x089C
+#define SXGBE_MMC_TXVLANHI_GCNT_REG	0x08A0
+
+/* RX specific counters */
+#define SXGBE_MMC_RXFRAMELO_GBCNT_REG	0x0900
+#define SXGBE_MMC_RXFRAMEHI_GBCNT_REG	0x0904
+#define SXGBE_MMC_RXOCTETLO_GBCNT_REG	0x0908
+#define SXGBE_MMC_RXOCTETHI_GBCNT_REG	0x090C
+#define SXGBE_MMC_RXOCTETLO_GCNT_REG	0x0910
+#define SXGBE_MMC_RXOCTETHI_GCNT_REG	0x0914
+#define SXGBE_MMC_RXBROADLO_GCNT_REG	0x0918
+#define SXGBE_MMC_RXBROADHI_GCNT_REG	0x091C
+#define SXGBE_MMC_RXMULTILO_GCNT_REG	0x0920
+#define SXGBE_MMC_RXMULTIHI_GCNT_REG	0x0924
+#define SXGBE_MMC_RXCRCERRLO_REG	0x0928
+#define SXGBE_MMC_RXCRCERRHI_REG	0x092C
+#define SXGBE_MMC_RXSHORT64BFRAME_ERR_REG	0x0930
+#define SXGBE_MMC_RXJABBERERR_REG		0x0934
+#define SXGBE_MMC_RXSHORT64BFRAME_COR_REG	0x0938
+#define SXGBE_MMC_RXOVERMAXFRAME_COR_REG	0x093C
+#define SXGBE_MMC_RX64LO_GBCNT_REG		0x0940
+#define SXGBE_MMC_RX64HI_GBCNT_REG		0x0944
+#define SXGBE_MMC_RX65TO127LO_GBCNT_REG		0x0948
+#define SXGBE_MMC_RX65TO127HI_GBCNT_REG		0x094C
+#define SXGBE_MMC_RX128TO255LO_GBCNT_REG	0x0950
+#define SXGBE_MMC_RX128TO255HI_GBCNT_REG	0x0954
+#define SXGBE_MMC_RX256TO511LO_GBCNT_REG	0x0958
+#define SXGBE_MMC_RX256TO511HI_GBCNT_REG	0x095C
+#define SXGBE_MMC_RX512TO1023LO_GBCNT_REG	0x0960
+#define SXGBE_MMC_RX512TO1023HI_GBCNT_REG	0x0964
+#define SXGBE_MMC_RX1023TOMAXLO_GBCNT_REG	0x0968
+#define SXGBE_MMC_RX1023TOMAXHI_GBCNT_REG	0x096C
+#define SXGBE_MMC_RXUNICASTLO_GCNT_REG		0x0970
+#define SXGBE_MMC_RXUNICASTHI_GCNT_REG		0x0974
+#define SXGBE_MMC_RXLENERRLO_REG		0x0978
+#define SXGBE_MMC_RXLENERRHI_REG		0x097C
+#define SXGBE_MMC_RXOUTOFRANGETYPELO_REG	0x0980
+#define SXGBE_MMC_RXOUTOFRANGETYPEHI_REG	0x0984
+#define SXGBE_MMC_RXPAUSELO_CNT_REG		0x0988
+#define SXGBE_MMC_RXPAUSEHI_CNT_REG		0x098C
+#define SXGBE_MMC_RXFIFOOVERFLOWLO_GBCNT_REG	0x0990
+#define SXGBE_MMC_RXFIFOOVERFLOWHI_GBCNT_REG	0x0994
+#define SXGBE_MMC_RXVLANLO_GBCNT_REG		0x0998
+#define SXGBE_MMC_RXVLANHI_GBCNT_REG		0x099C
+#define SXGBE_MMC_RXWATCHDOG_ERR_REG		0x09A0
+
+/* L3/L4 function registers */
+#define SXGBE_CORE_L34_ADDCTL_REG	0x0C00
+#define SXGBE_CORE_L34_ADDCTL_REG	0x0C00
+#define SXGBE_CORE_L34_DATA_REG		0x0C04
+
+/* ARP registers */
+#define SXGBE_CORE_ARP_ADD_REG		0x0C10
+
+/* RSS registers */
+#define SXGBE_CORE_RSS_CTL_REG		0x0C80
+#define SXGBE_CORE_RSS_ADD_REG		0x0C88
+#define SXGBE_CORE_RSS_DATA_REG		0x0C8C
+
+/* IEEE 1588 registers */
+#define SXGBE_CORE_TSTAMP_CTL_REG	0x0D00
+#define SXGBE_CORE_SUBSEC_INC_REG	0x0D04
+#define SXGBE_CORE_SYSTIME_SEC_REG	0x0D0C
+#define SXGBE_CORE_SYSTIME_NSEC_REG	0x0D10
+#define SXGBE_CORE_SYSTIME_SECUP_REG	0x0D14
+#define SXGBE_CORE_TSTAMP_ADD_REG	0x0D18
+#define SXGBE_CORE_SYSTIME_HWORD_REG	0x0D1C
+#define SXGBE_CORE_TSTAMP_STATUS_REG	0x0D20
+#define SXGBE_CORE_TXTIME_STATUSNSEC_REG 0x0D30
+#define SXGBE_CORE_TXTIME_STATUSSEC_REG	0x0D34
+
+/* Auxiliary registers */
+#define SXGBE_CORE_AUX_CTL_REG			 0x0D40
+#define SXGBE_CORE_AUX_TSTAMP_NSEC_REG		 0x0D48
+#define SXGBE_CORE_AUX_TSTAMP_SEC_REG		 0x0D4C
+#define SXGBE_CORE_AUX_TSTAMP_INGCOR_REG	 0x0D50
+#define SXGBE_CORE_AUX_TSTAMP_ENGCOR_REG	 0x0D54
+#define SXGBE_CORE_AUX_TSTAMP_INGCOR_NSEC_REG	 0x0D58
+#define SXGBE_CORE_AUX_TSTAMP_INGCOR_SUBNSEC_REG 0x0D5C
+#define SXGBE_CORE_AUX_TSTAMP_ENGCOR_NSEC_REG	 0x0D60
+#define SXGBE_CORE_AUX_TSTAMP_ENGCOR_SUBNSEC_REG 0x0D64
+
+/* PPS registers */
+#define SXGBE_CORE_PPS_CTL_REG		0x0D70
+#define SXGBE_CORE_PPS_BASE			0x0D80
+
+/* addr = 0 - 3 */
+#define SXGBE_CORE_PPS_TTIME_SEC_REG(addr)		\
+	(SXGBE_CORE_PPS_BASE + (0x10 * addr) + 0x0)
+#define SXGBE_CORE_PPS_TTIME_NSEC_REG(addr)		\
+	(SXGBE_CORE_PPS_BASE + (0x10 * addr) + 0x4)
+#define SXGBE_CORE_PPS_INTERVAL_REG(addr)		\
+	(SXGBE_CORE_PPS_BASE + (0x10 * addr) + 0x8)
+#define SXGBE_CORE_PPS_WIDTH_REG(addr)			\
+	(SXGBE_CORE_PPS_BASE + (0x10 * addr) + 0xC)
+#define SXGBE_CORE_PTO_CTL_REG		0x0DC0
+#define SXGBE_CORE_SRCPORT_ITY0_REG	0x0DC4
+#define SXGBE_CORE_SRCPORT_ITY1_REG	0x0DC8
+#define SXGBE_CORE_SRCPORT_ITY2_REG	0x0DCC
+#define SXGBE_CORE_LOGMSG_LEVEL_REG	0x0DD0
+
+/* SXGBE MTL Registers */
+#define SXGBE_MTL_BASE_REG		0x1000
+#define SXGBE_MTL_OP_MODE_REG		(SXGBE_MTL_BASE_REG + 0x0000)
+#define SXGBE_MTL_DEBUG_CTL_REG		(SXGBE_MTL_BASE_REG + 0x0008)
+#define SXGBE_MTL_DEBUG_STATUS_REG	(SXGBE_MTL_BASE_REG + 0x000C)
+#define SXGBE_MTL_FIFO_DEBUGDATA_REG	(SXGBE_MTL_BASE_REG + 0x0010)
+#define SXGBE_MTL_INT_STATUS_REG	(SXGBE_MTL_BASE_REG + 0x0020)
+#define SXGBE_MTL_RXQ_DMAMAP0_REG	(SXGBE_MTL_BASE_REG + 0x0030)
+#define SXGBE_MTL_RXQ_DMAMAP1_REG	(SXGBE_MTL_BASE_REG + 0x0034)
+#define SXGBE_MTL_RXQ_DMAMAP2_REG	(SXGBE_MTL_BASE_REG + 0x0038)
+#define SXGBE_MTL_TX_PRTYMAP0_REG	(SXGBE_MTL_BASE_REG + 0x0040)
+#define SXGBE_MTL_TX_PRTYMAP1_REG	(SXGBE_MTL_BASE_REG + 0x0044)
+
+/* TC/Queue registers, qnum=0-15 */
+#define SXGBE_MTL_TC_TXBASE_REG		(SXGBE_MTL_BASE_REG + 0x0100)
+#define SXGBE_MTL_TXQ_OPMODE_REG(qnum)				\
+	(SXGBE_MTL_TC_TXBASE_REG + (qnum * 0x80) + 0x00)
+#define SXGBE_MTL_SFMODE		BIT(1)
+#define SXGBE_MTL_FIFO_LSHIFT		16
+#define SXGBE_MTL_ENABLE_QUEUE		0x00000008
+#define SXGBE_MTL_TXQ_UNDERFLOW_REG(qnum)			\
+	(SXGBE_MTL_TC_TXBASE_REG + (qnum * 0x80) + 0x04)
+#define SXGBE_MTL_TXQ_DEBUG_REG(qnum)				\
+	(SXGBE_MTL_TC_TXBASE_REG + (qnum * 0x80) + 0x08)
+#define SXGBE_MTL_TXQ_ETSCTL_REG(qnum)				\
+	(SXGBE_MTL_TC_TXBASE_REG + (qnum * 0x80) + 0x10)
+#define SXGBE_MTL_TXQ_ETSSTATUS_REG(qnum)			\
+	(SXGBE_MTL_TC_TXBASE_REG + (qnum * 0x80) + 0x14)
+#define SXGBE_MTL_TXQ_QUANTWEIGHT_REG(qnum)			\
+	(SXGBE_MTL_TC_TXBASE_REG + (qnum * 0x80) + 0x18)
+
+#define SXGBE_MTL_TC_RXBASE_REG		0x1140
+#define SXGBE_RX_MTL_SFMODE		BIT(5)
+#define SXGBE_MTL_RXQ_OPMODE_REG(qnum)				\
+	(SXGBE_MTL_TC_RXBASE_REG + (qnum * 0x80) + 0x00)
+#define SXGBE_MTL_RXQ_MISPKTOVERFLOW_REG(qnum)			\
+	(SXGBE_MTL_TC_RXBASE_REG + (qnum * 0x80) + 0x04)
+#define SXGBE_MTL_RXQ_DEBUG_REG(qnum)				\
+	(SXGBE_MTL_TC_RXBASE_REG + (qnum * 0x80) + 0x08)
+#define SXGBE_MTL_RXQ_CTL_REG(qnum)				\
+	(SXGBE_MTL_TC_RXBASE_REG + (qnum * 0x80) + 0x0C)
+#define SXGBE_MTL_RXQ_INTENABLE_REG(qnum)			\
+	(SXGBE_MTL_TC_RXBASE_REG + (qnum * 0x80) + 0x30)
+#define SXGBE_MTL_RXQ_INTSTATUS_REG(qnum)			\
+	(SXGBE_MTL_TC_RXBASE_REG + (qnum * 0x80) + 0x34)
+
+/* SXGBE DMA Registers */
+#define SXGBE_DMA_BASE_REG		0x3000
+#define SXGBE_DMA_MODE_REG		(SXGBE_DMA_BASE_REG + 0x0000)
+#define SXGBE_DMA_SOFT_RESET		BIT(0)
+#define SXGBE_DMA_SYSBUS_MODE_REG	(SXGBE_DMA_BASE_REG + 0x0004)
+#define SXGBE_DMA_AXI_UNDEF_BURST	BIT(0)
+#define SXGBE_DMA_ENHACE_ADDR_MODE	BIT(11)
+#define SXGBE_DMA_INT_STATUS_REG	(SXGBE_DMA_BASE_REG + 0x0008)
+#define SXGBE_DMA_AXI_ARCACHECTL_REG	(SXGBE_DMA_BASE_REG + 0x0010)
+#define SXGBE_DMA_AXI_AWCACHECTL_REG	(SXGBE_DMA_BASE_REG + 0x0018)
+#define SXGBE_DMA_DEBUG_STATUS0_REG	(SXGBE_DMA_BASE_REG + 0x0020)
+#define SXGBE_DMA_DEBUG_STATUS1_REG	(SXGBE_DMA_BASE_REG + 0x0024)
+#define SXGBE_DMA_DEBUG_STATUS2_REG	(SXGBE_DMA_BASE_REG + 0x0028)
+#define SXGBE_DMA_DEBUG_STATUS3_REG	(SXGBE_DMA_BASE_REG + 0x002C)
+#define SXGBE_DMA_DEBUG_STATUS4_REG	(SXGBE_DMA_BASE_REG + 0x0030)
+#define SXGBE_DMA_DEBUG_STATUS5_REG	(SXGBE_DMA_BASE_REG + 0x0034)
+
+/* Channel Registers, cha_num = 0-15 */
+#define SXGBE_DMA_CHA_BASE_REG			\
+	(SXGBE_DMA_BASE_REG + 0x0100)
+#define SXGBE_DMA_CHA_CTL_REG(cha_num)				\
+	(SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x00)
+#define SXGBE_DMA_PBL_X8MODE			BIT(16)
+#define SXGBE_DMA_CHA_TXCTL_TSE_ENABLE		BIT(12)
+#define SXGBE_DMA_CHA_TXCTL_REG(cha_num)			\
+	(SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x04)
+#define SXGBE_DMA_CHA_RXCTL_REG(cha_num)			\
+	(SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x08)
+#define SXGBE_DMA_CHA_TXDESC_HADD_REG(cha_num)			\
+	(SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x10)
+#define SXGBE_DMA_CHA_TXDESC_LADD_REG(cha_num)			\
+	(SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x14)
+#define SXGBE_DMA_CHA_RXDESC_HADD_REG(cha_num)			\
+	(SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x18)
+#define SXGBE_DMA_CHA_RXDESC_LADD_REG(cha_num)			\
+	(SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x1C)
+#define SXGBE_DMA_CHA_TXDESC_TAILPTR_REG(cha_num)		\
+	(SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x24)
+#define SXGBE_DMA_CHA_RXDESC_TAILPTR_REG(cha_num)		\
+	(SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x2C)
+#define SXGBE_DMA_CHA_TXDESC_RINGLEN_REG(cha_num)		\
+	(SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x30)
+#define SXGBE_DMA_CHA_RXDESC_RINGLEN_REG(cha_num)		\
+	(SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x34)
+#define SXGBE_DMA_CHA_INT_ENABLE_REG(cha_num)			\
+	(SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x38)
+#define SXGBE_DMA_CHA_INT_RXWATCHTMR_REG(cha_num)		\
+	(SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x3C)
+#define SXGBE_DMA_CHA_TXDESC_CURADDLO_REG(cha_num)		\
+	(SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x44)
+#define SXGBE_DMA_CHA_RXDESC_CURADDLO_REG(cha_num)		\
+	(SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x4C)
+#define SXGBE_DMA_CHA_CURTXBUF_ADDHI_REG(cha_num)		\
+	(SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x50)
+#define SXGBE_DMA_CHA_CURTXBUF_ADDLO_REG(cha_num)		\
+	(SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x54)
+#define SXGBE_DMA_CHA_CURRXBUF_ADDHI_REG(cha_num)		\
+	(SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x58)
+#define SXGBE_DMA_CHA_CURRXBUF_ADDLO_REG(cha_num)		\
+	(SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x5C)
+#define SXGBE_DMA_CHA_STATUS_REG(cha_num)			\
+	(SXGBE_DMA_CHA_BASE_REG + (cha_num * 0x80) + 0x60)
+
+/* TX DMA control register specific */
+#define SXGBE_TX_START_DMA	BIT(0)
+
+/* sxgbe tx configuration register bitfields */
+#define SXGBE_SPEED_10G		0x0
+#define SXGBE_SPEED_2_5G	0x1
+#define SXGBE_SPEED_1G		0x2
+#define SXGBE_SPEED_LSHIFT	29
+
+#define SXGBE_TX_ENABLE		BIT(0)
+#define SXGBE_TX_DISDIC_ALGO	BIT(1)
+#define SXGBE_TX_JABBER_DISABLE	BIT(16)
+
+/* sxgbe rx configuration register bitfields */
+#define SXGBE_RX_ENABLE		BIT(0)
+#define SXGBE_RX_ACS_ENABLE		BIT(1)
+#define SXGBE_RX_WATCHDOG_DISABLE	BIT(7)
+#define SXGBE_RX_JUMBPKT_ENABLE		BIT(8)
+#define SXGBE_RX_CSUMOFFLOAD_ENABLE	BIT(9)
+#define SXGBE_RX_LOOPBACK_ENABLE	BIT(10)
+#define SXGBE_RX_ARPOFFLOAD_ENABLE	BIT(31)
+
+/* sxgbe vlan Tag Register bitfields */
+#define SXGBE_VLAN_SVLAN_ENABLE		BIT(18)
+#define SXGBE_VLAN_DOUBLEVLAN_ENABLE	BIT(26)
+#define SXGBE_VLAN_INNERVLAN_ENABLE	BIT(27)
+
+/* XMAC VLAN Tag Inclusion Register(0x0060) bitfields
+ * Below fields same for  Inner VLAN Tag Inclusion
+ * Register(0x0064) register
+ */
+enum vlan_tag_ctl_tx {
+	VLAN_TAG_TX_NOP,
+	VLAN_TAG_TX_DEL,
+	VLAN_TAG_TX_INSERT,
+	VLAN_TAG_TX_REPLACE
+};
+#define SXGBE_VLAN_PRTY_CTL	BIT(18)
+#define SXGBE_VLAN_CSVL_CTL	BIT(19)
+
+/* SXGBE TX Q Flow Control Register bitfields */
+#define SXGBE_TX_FLOW_CTL_FCB	BIT(0)
+#define SXGBE_TX_FLOW_CTL_TFB	BIT(1)
+
+/* SXGBE RX Q Flow Control Register bitfields */
+#define SXGBE_RX_FLOW_CTL_ENABLE	BIT(0)
+#define SXGBE_RX_UNICAST_DETECT		BIT(1)
+#define SXGBE_RX_PRTYFLOW_CTL_ENABLE	BIT(8)
+
+/* sxgbe rx Q control0 register bitfields */
+#define SXGBE_RX_Q_ENABLE	0x2
+
+/* SXGBE hardware features bitfield specific */
+/* Capability Register 0 */
+#define SXGBE_HW_FEAT_GMII(cap)			((cap & 0x00000002) >> 1)
+#define SXGBE_HW_FEAT_VLAN_HASH_FILTER(cap)	((cap & 0x00000010) >> 4)
+#define SXGBE_HW_FEAT_SMA(cap)			((cap & 0x00000020) >> 5)
+#define SXGBE_HW_FEAT_PMT_TEMOTE_WOP(cap)	((cap & 0x00000040) >> 6)
+#define SXGBE_HW_FEAT_PMT_MAGIC_PKT(cap)	((cap & 0x00000080) >> 7)
+#define SXGBE_HW_FEAT_RMON(cap)			((cap & 0x00000100) >> 8)
+#define SXGBE_HW_FEAT_ARP_OFFLOAD(cap)		((cap & 0x00000200) >> 9)
+#define SXGBE_HW_FEAT_IEEE1500_2008(cap)	((cap & 0x00001000) >> 12)
+#define SXGBE_HW_FEAT_EEE(cap)			((cap & 0x00002000) >> 13)
+#define SXGBE_HW_FEAT_TX_CSUM_OFFLOAD(cap)	((cap & 0x00004000) >> 14)
+#define SXGBE_HW_FEAT_RX_CSUM_OFFLOAD(cap)	((cap & 0x00010000) >> 16)
+#define SXGBE_HW_FEAT_MACADDR_COUNT(cap)	((cap & 0x007C0000) >> 18)
+#define SXGBE_HW_FEAT_TSTMAP_SRC(cap)		((cap & 0x06000000) >> 25)
+#define SXGBE_HW_FEAT_SRCADDR_VLAN(cap)		((cap & 0x08000000) >> 27)
+
+/* Capability Register 1 */
+#define SXGBE_HW_FEAT_RX_FIFO_SIZE(cap)		((cap & 0x0000001F))
+#define SXGBE_HW_FEAT_TX_FIFO_SIZE(cap)		((cap & 0x000007C0) >> 6)
+#define SXGBE_HW_FEAT_IEEE1588_HWORD(cap)	((cap & 0x00002000) >> 13)
+#define SXGBE_HW_FEAT_DCB(cap)			((cap & 0x00010000) >> 16)
+#define SXGBE_HW_FEAT_SPLIT_HDR(cap)		((cap & 0x00020000) >> 17)
+#define SXGBE_HW_FEAT_TSO(cap)			((cap & 0x00040000) >> 18)
+#define SXGBE_HW_FEAT_DEBUG_MEM_IFACE(cap)	((cap & 0x00080000) >> 19)
+#define SXGBE_HW_FEAT_RSS(cap)			((cap & 0x00100000) >> 20)
+#define SXGBE_HW_FEAT_HASH_TABLE_SIZE(cap)	((cap & 0x03000000) >> 24)
+#define SXGBE_HW_FEAT_L3L4_FILTER_NUM(cap)	((cap & 0x78000000) >> 27)
+
+/* Capability Register 2 */
+#define SXGBE_HW_FEAT_RX_MTL_QUEUES(cap)	((cap & 0x0000000F))
+#define SXGBE_HW_FEAT_TX_MTL_QUEUES(cap)	((cap & 0x000003C0) >> 6)
+#define SXGBE_HW_FEAT_RX_DMA_CHANNELS(cap)	((cap & 0x0000F000) >> 12)
+#define SXGBE_HW_FEAT_TX_DMA_CHANNELS(cap)	((cap & 0x003C0000) >> 18)
+#define SXGBE_HW_FEAT_PPS_OUTPUTS(cap)		((cap & 0x07000000) >> 24)
+#define SXGBE_HW_FEAT_AUX_SNAPSHOTS(cap)	((cap & 0x70000000) >> 28)
+
+/* DMAchannel interrupt enable specific */
+/* DMA Normal interrupt */
+#define SXGBE_DMA_INT_ENA_NIE	BIT(16)	/* Normal Summary */
+#define SXGBE_DMA_INT_ENA_TIE	BIT(0)	/* Transmit Interrupt */
+#define SXGBE_DMA_INT_ENA_TUE	BIT(2)	/* Transmit Buffer Unavailable */
+#define SXGBE_DMA_INT_ENA_RIE	BIT(6)	/* Receive Interrupt */
+
+#define SXGBE_DMA_INT_NORMAL					\
+	(SXGBE_DMA_INT_ENA_NIE | SXGBE_DMA_INT_ENA_RIE |	\
+	 SXGBE_DMA_INT_ENA_TIE | SXGBE_DMA_INT_ENA_TUE)
+
+/* DMA Abnormal interrupt */
+#define SXGBE_DMA_INT_ENA_AIE	BIT(15)	/* Abnormal Summary */
+#define SXGBE_DMA_INT_ENA_TSE	BIT(1)	/* Transmit Stopped */
+#define SXGBE_DMA_INT_ENA_RUE	BIT(7)	/* Receive Buffer Unavailable */
+#define SXGBE_DMA_INT_ENA_RSE	BIT(8)	/* Receive Stopped */
+#define SXGBE_DMA_INT_ENA_FBE	BIT(12)	/* Fatal Bus Error */
+#define SXGBE_DMA_INT_ENA_CDEE	BIT(13)	/* Context Descriptor Error */
+
+#define SXGBE_DMA_INT_ABNORMAL					\
+	(SXGBE_DMA_INT_ENA_AIE | SXGBE_DMA_INT_ENA_TSE |	\
+	 SXGBE_DMA_INT_ENA_RUE | SXGBE_DMA_INT_ENA_RSE |	\
+	 SXGBE_DMA_INT_ENA_FBE | SXGBE_DMA_INT_ENA_CDEE)
+
+#define SXGBE_DMA_ENA_INT	(SXGBE_DMA_INT_NORMAL | SXGBE_DMA_INT_ABNORMAL)
+
+/* DMA channel interrupt status specific */
+#define	SXGBE_DMA_INT_STATUS_REB2	BIT(21)
+#define	SXGBE_DMA_INT_STATUS_REB1	BIT(20)
+#define	SXGBE_DMA_INT_STATUS_REB0	BIT(19)
+#define	SXGBE_DMA_INT_STATUS_TEB2	BIT(18)
+#define	SXGBE_DMA_INT_STATUS_TEB1	BIT(17)
+#define	SXGBE_DMA_INT_STATUS_TEB0	BIT(16)
+#define	SXGBE_DMA_INT_STATUS_NIS	BIT(15)
+#define SXGBE_DMA_INT_STATUS_AIS	BIT(14)
+#define SXGBE_DMA_INT_STATUS_CTXTERR	BIT(13)
+#define SXGBE_DMA_INT_STATUS_FBE	BIT(12)
+#define SXGBE_DMA_INT_STATUS_RPS	BIT(8)
+#define SXGBE_DMA_INT_STATUS_RBU	BIT(7)
+#define SXGBE_DMA_INT_STATUS_RI		BIT(6)
+#define SXGBE_DMA_INT_STATUS_TBU	BIT(2)
+#define SXGBE_DMA_INT_STATUS_TPS	BIT(1)
+#define SXGBE_DMA_INT_STATUS_TI		BIT(0)
+
+#endif /* __SXGBE_REGMAP_H__ */
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_xpcs.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_xpcs.c
new file mode 100644
index 000000000000..51c32194ba88
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_xpcs.c
@@ -0,0 +1,91 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+#include "sxgbe_common.h"
+#include "sxgbe_xpcs.h"
+
+static int sxgbe_xpcs_read(struct net_device *ndev, unsigned int reg)
+{
+	u32 value;
+	struct sxgbe_priv_data *priv = netdev_priv(ndev);
+
+	value = readl(priv->ioaddr + XPCS_OFFSET + reg);
+
+	return value;
+}
+
+static int sxgbe_xpcs_write(struct net_device *ndev, int reg, int data)
+{
+	struct sxgbe_priv_data *priv = netdev_priv(ndev);
+
+	writel(data, priv->ioaddr + XPCS_OFFSET + reg);
+
+	return 0;
+}
+
+int sxgbe_xpcs_init(struct net_device *ndev)
+{
+	u32 value;
+
+	value = sxgbe_xpcs_read(ndev, SR_PCS_MMD_CONTROL1);
+	/* 10G XAUI mode */
+	sxgbe_xpcs_write(ndev, SR_PCS_CONTROL2, XPCS_TYPE_SEL_X);
+	sxgbe_xpcs_write(ndev, VR_PCS_MMD_XAUI_MODE_CONTROL, XPCS_XAUI_MODE);
+	sxgbe_xpcs_write(ndev, VR_PCS_MMD_XAUI_MODE_CONTROL, value | BIT(13));
+	sxgbe_xpcs_write(ndev, SR_PCS_MMD_CONTROL1, value | BIT(11));
+
+	do {
+		value = sxgbe_xpcs_read(ndev, VR_PCS_MMD_DIGITAL_STATUS);
+	} while ((value & XPCS_QSEQ_STATE_MPLLOFF) == XPCS_QSEQ_STATE_STABLE);
+
+	value = sxgbe_xpcs_read(ndev, SR_PCS_MMD_CONTROL1);
+	sxgbe_xpcs_write(ndev, SR_PCS_MMD_CONTROL1, value & ~BIT(11));
+
+	do {
+		value = sxgbe_xpcs_read(ndev, VR_PCS_MMD_DIGITAL_STATUS);
+	} while ((value & XPCS_QSEQ_STATE_MPLLOFF) != XPCS_QSEQ_STATE_STABLE);
+
+	return 0;
+}
+
+int sxgbe_xpcs_init_1G(struct net_device *ndev)
+{
+	int value;
+
+	/* 10GBASE-X PCS (1G) mode */
+	sxgbe_xpcs_write(ndev, SR_PCS_CONTROL2, XPCS_TYPE_SEL_X);
+	sxgbe_xpcs_write(ndev, VR_PCS_MMD_XAUI_MODE_CONTROL, XPCS_XAUI_MODE);
+	value = sxgbe_xpcs_read(ndev, SR_PCS_MMD_CONTROL1);
+	sxgbe_xpcs_write(ndev, SR_PCS_MMD_CONTROL1, value & ~BIT(13));
+
+	value = sxgbe_xpcs_read(ndev, SR_MII_MMD_CONTROL);
+	sxgbe_xpcs_write(ndev, SR_MII_MMD_CONTROL, value | BIT(6));
+	sxgbe_xpcs_write(ndev, SR_MII_MMD_CONTROL, value & ~BIT(13));
+	value = sxgbe_xpcs_read(ndev, SR_PCS_MMD_CONTROL1);
+	sxgbe_xpcs_write(ndev, SR_PCS_MMD_CONTROL1, value | BIT(11));
+
+	do {
+		value = sxgbe_xpcs_read(ndev, VR_PCS_MMD_DIGITAL_STATUS);
+	} while ((value & XPCS_QSEQ_STATE_MPLLOFF) != XPCS_QSEQ_STATE_STABLE);
+
+	value = sxgbe_xpcs_read(ndev, SR_PCS_MMD_CONTROL1);
+	sxgbe_xpcs_write(ndev, SR_PCS_MMD_CONTROL1, value & ~BIT(11));
+
+	/* Auto Negotiation cluase 37 enable */
+	value = sxgbe_xpcs_read(ndev, SR_MII_MMD_CONTROL);
+	sxgbe_xpcs_write(ndev, SR_MII_MMD_CONTROL, value | BIT(12));
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_xpcs.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_xpcs.h
new file mode 100644
index 000000000000..6b26a50724d3
--- /dev/null
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_xpcs.h
@@ -0,0 +1,38 @@
+/* 10G controller driver for Samsung SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Author: Byungho An <bh74.an@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __SXGBE_XPCS_H__
+#define __SXGBE_XPCS_H__
+
+/* XPCS Registers */
+#define XPCS_OFFSET			0x1A060000
+#define SR_PCS_MMD_CONTROL1		0x030000
+#define SR_PCS_CONTROL2			0x030007
+#define VR_PCS_MMD_XAUI_MODE_CONTROL	0x038004
+#define VR_PCS_MMD_DIGITAL_STATUS	0x038010
+#define SR_MII_MMD_CONTROL		0x1F0000
+#define SR_MII_MMD_AN_ADV		0x1F0004
+#define SR_MII_MMD_AN_LINK_PARTNER_BA	0x1F0005
+#define VR_MII_MMD_AN_CONTROL		0x1F8001
+#define VR_MII_MMD_AN_INT_STATUS	0x1F8002
+
+#define XPCS_QSEQ_STATE_STABLE		0x10
+#define XPCS_QSEQ_STATE_MPLLOFF		0x1c
+#define XPCS_TYPE_SEL_R			0x00
+#define XPCS_TYPE_SEL_X			0x01
+#define XPCS_TYPE_SEL_W			0x02
+#define XPCS_XAUI_MODE			0x00
+#define XPCS_RXAUI_MODE			0x01
+
+int sxgbe_xpcs_init(struct net_device *ndev);
+int sxgbe_xpcs_init_1G(struct net_device *ndev);
+
+#endif /* __SXGBE_XPCS_H__ */
diff --git a/include/linux/sxgbe_platform.h b/include/linux/sxgbe_platform.h
new file mode 100644
index 000000000000..a62442cf0037
--- /dev/null
+++ b/include/linux/sxgbe_platform.h
@@ -0,0 +1,54 @@
+/*
+ * 10G controller driver for Samsung EXYNOS SoCs
+ *
+ * Copyright (C) 2013 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __SXGBE_PLATFORM_H__
+#define __SXGBE_PLATFORM_H__
+
+/* MDC Clock Selection define*/
+#define SXGBE_CSR_100_150M	0x0	/* MDC = clk_scr_i/62 */
+#define SXGBE_CSR_150_250M	0x1	/* MDC = clk_scr_i/102 */
+#define SXGBE_CSR_250_300M	0x2	/* MDC = clk_scr_i/122 */
+#define SXGBE_CSR_300_350M	0x3	/* MDC = clk_scr_i/142 */
+#define SXGBE_CSR_350_400M	0x4	/* MDC = clk_scr_i/162 */
+#define SXGBE_CSR_400_500M	0x5	/* MDC = clk_scr_i/202 */
+
+/* Platfrom data for platform device structure's
+ * platform_data field
+ */
+struct sxgbe_mdio_bus_data {
+	unsigned int phy_mask;
+	int *irqs;
+	int probed_phy_irq;
+};
+
+struct sxgbe_dma_cfg {
+	int pbl;
+	int fixed_burst;
+	int burst_map;
+	int adv_addr_mode;
+};
+
+struct sxgbe_plat_data {
+	char *phy_bus_name;
+	int bus_id;
+	int phy_addr;
+	int interface;
+	struct sxgbe_mdio_bus_data *mdio_bus_data;
+	struct sxgbe_dma_cfg *dma_cfg;
+	int clk_csr;
+	int pmt;
+	int force_sf_dma_mode;
+	int force_thresh_dma_mode;
+	int riwt_off;
+};
+
+#endif /* __SXGBE_PLATFORM_H__ */
-- 
cgit v1.2.3


From d70ab4fb723cf7acfa656cb2ad1e75be7ed94bef Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Mon, 3 Mar 2014 17:43:31 -0500
Subject: dm: remove dm_get_mapinfo

Remove dm_get_mapinfo() because no target uses it.  Targets can allocate
per-bio data using ti->per_bio_data_size, this is much more flexible
than union map_info.

Leave union map_info only for the request-based multipath target's use.
Also delete the unused "unsigned long long ll" field of union map_info.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
---
 drivers/md/dm.c               | 10 ----------
 include/linux/device-mapper.h |  3 ---
 2 files changed, 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 8c53b09b9a2c..ef5750d21235 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -94,13 +94,6 @@ struct dm_rq_clone_bio_info {
 	struct bio clone;
 };
 
-union map_info *dm_get_mapinfo(struct bio *bio)
-{
-	if (bio && bio->bi_private)
-		return &((struct dm_target_io *)bio->bi_private)->info;
-	return NULL;
-}
-
 union map_info *dm_get_rq_mapinfo(struct request *rq)
 {
 	if (rq && rq->end_io_data)
@@ -1195,7 +1188,6 @@ static struct dm_target_io *alloc_tio(struct clone_info *ci,
 
 	tio->io = ci->io;
 	tio->ti = ti;
-	memset(&tio->info, 0, sizeof(tio->info));
 	tio->target_bio_nr = target_bio_nr;
 
 	return tio;
@@ -2873,8 +2865,6 @@ static const struct block_device_operations dm_blk_dops = {
 	.owner = THIS_MODULE
 };
 
-EXPORT_SYMBOL(dm_get_mapinfo);
-
 /*
  * module hooks
  */
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index ed419c62dde1..5eeeab470cfd 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -23,7 +23,6 @@ typedef enum { STATUSTYPE_INFO, STATUSTYPE_TABLE } status_type_t;
 
 union map_info {
 	void *ptr;
-	unsigned long long ll;
 };
 
 /*
@@ -291,7 +290,6 @@ struct dm_target_callbacks {
 struct dm_target_io {
 	struct dm_io *io;
 	struct dm_target *ti;
-	union map_info info;
 	unsigned target_bio_nr;
 	struct bio clone;
 };
@@ -403,7 +401,6 @@ int dm_copy_name_and_uuid(struct mapped_device *md, char *name, char *uuid);
 struct gendisk *dm_disk(struct mapped_device *md);
 int dm_suspended(struct dm_target *ti);
 int dm_noflush_suspending(struct dm_target *ti);
-union map_info *dm_get_mapinfo(struct bio *bio);
 union map_info *dm_get_rq_mapinfo(struct request *rq);
 
 struct queue_limits *dm_get_queue_limits(struct mapped_device *md);
-- 
cgit v1.2.3


From 9974fa2c6a7d470ca3c201fe7dbac64bf4dd8d2a Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@redhat.com>
Date: Fri, 28 Feb 2014 15:33:43 +0100
Subject: dm table: add dm_table_run_md_queue_async

Introduce dm_table_run_md_queue_async() to run the request_queue of the
mapped_device associated with a request-based DM table.

Also add dm_md_get_queue() wrapper to extract the request_queue from a
mapped_device.

Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
---
 drivers/md/dm-table.c         | 19 +++++++++++++++++++
 drivers/md/dm.c               |  5 +++++
 drivers/md/dm.h               |  1 +
 include/linux/device-mapper.h |  5 +++++
 4 files changed, 30 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 2ae35b2f80fd..50601ec7017a 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1618,6 +1618,25 @@ struct mapped_device *dm_table_get_md(struct dm_table *t)
 }
 EXPORT_SYMBOL(dm_table_get_md);
 
+void dm_table_run_md_queue_async(struct dm_table *t)
+{
+	struct mapped_device *md;
+	struct request_queue *queue;
+	unsigned long flags;
+
+	if (!dm_table_request_based(t))
+		return;
+
+	md = dm_table_get_md(t);
+	queue = dm_get_md_queue(md);
+	if (queue) {
+		spin_lock_irqsave(queue->queue_lock, flags);
+		blk_run_queue_async(queue);
+		spin_unlock_irqrestore(queue->queue_lock, flags);
+	}
+}
+EXPORT_SYMBOL(dm_table_run_md_queue_async);
+
 static int device_discard_capable(struct dm_target *ti, struct dm_dev *dev,
 				  sector_t start, sector_t len, void *data)
 {
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 6382213dbd88..455e64916498 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -468,6 +468,11 @@ sector_t dm_get_size(struct mapped_device *md)
 	return get_capacity(md->disk);
 }
 
+struct request_queue *dm_get_md_queue(struct mapped_device *md)
+{
+	return md->queue;
+}
+
 struct dm_stats *dm_get_stats(struct mapped_device *md)
 {
 	return &md->stats;
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 88cc58c5871a..ed76126aac54 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -188,6 +188,7 @@ int dm_lock_for_deletion(struct mapped_device *md, bool mark_deferred, bool only
 int dm_cancel_deferred_remove(struct mapped_device *md);
 int dm_request_based(struct mapped_device *md);
 sector_t dm_get_size(struct mapped_device *md);
+struct request_queue *dm_get_md_queue(struct mapped_device *md);
 struct dm_stats *dm_get_stats(struct mapped_device *md);
 
 int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action,
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 5eeeab470cfd..63da56ed9796 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -462,6 +462,11 @@ struct mapped_device *dm_table_get_md(struct dm_table *t);
  */
 void dm_table_event(struct dm_table *t);
 
+/*
+ * Run the queue for request-based targets.
+ */
+void dm_table_run_md_queue_async(struct dm_table *t);
+
 /*
  * The device must be suspended before calling this method.
  * Returns the previous table, which the caller must destroy.
-- 
cgit v1.2.3


From c3626fdea044cc97bfc035ebb048f7619acb6736 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Fri, 28 Mar 2014 20:42:01 +0100
Subject: gpio: unmap gpio irqs properly

When using the irqchip helper inside the gpiolib, make sure
the IRQs are unmapped/disposed before the irqdomain is removed
as part of removing the gpiochip.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.c      | 33 +++++++++++++++++++++++++++++----
 include/linux/gpio/driver.h |  1 +
 2 files changed, 30 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index f41cb4f3d715..761013f8b82f 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1399,8 +1399,18 @@ static int gpiochip_irq_map(struct irq_domain *d, unsigned int irq,
 	return 0;
 }
 
+static void gpiochip_irq_unmap(struct irq_domain *d, unsigned int irq)
+{
+#ifdef CONFIG_ARM
+	set_irq_flags(irq, 0);
+#endif
+	irq_set_chip_and_handler(irq, NULL, NULL);
+	irq_set_chip_data(irq, NULL);
+}
+
 static const struct irq_domain_ops gpiochip_domain_ops = {
 	.map	= gpiochip_irq_map,
+	.unmap	= gpiochip_irq_unmap,
 	/* Virtually all GPIO irqchips are twocell:ed */
 	.xlate	= irq_domain_xlate_twocell,
 };
@@ -1438,8 +1448,14 @@ static int gpiochip_to_irq(struct gpio_chip *chip, unsigned offset)
  */
 static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip)
 {
-	if (gpiochip->irqdomain)
+	unsigned int offset;
+
+	/* Remove all IRQ mappings and delete the domain */
+	if (gpiochip->irqdomain) {
+		for (offset = 0; offset < gpiochip->ngpio; offset++)
+			irq_dispose_mapping(gpiochip->irq_base + offset);
 		irq_domain_remove(gpiochip->irqdomain);
+	}
 
 	if (gpiochip->irqchip) {
 		gpiochip->irqchip->irq_request_resources = NULL;
@@ -1467,7 +1483,8 @@ static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip)
  * translation. The gpiochip will need to be initialized and registered
  * before calling this function.
  *
- * This function will handle two cell:ed simple IRQs. Everything else
+ * This function will handle two cell:ed simple IRQs and assumes all
+ * the pins on the gpiochip can generate a unique IRQ. Everything else
  * need to be open coded.
  */
 int gpiochip_irqchip_add(struct gpio_chip *gpiochip,
@@ -1478,6 +1495,7 @@ int gpiochip_irqchip_add(struct gpio_chip *gpiochip,
 {
 	struct device_node *of_node;
 	unsigned int offset;
+	unsigned irq_base = 0;
 
 	if (!gpiochip || !irqchip)
 		return -EINVAL;
@@ -1514,8 +1532,15 @@ int gpiochip_irqchip_add(struct gpio_chip *gpiochip,
 	 * any gpiochip calls. If the first_irq was zero, this is
 	 * necessary to allocate descriptors for all IRQs.
 	 */
-	for (offset = 0; offset < gpiochip->ngpio; offset++)
-		irq_create_mapping(gpiochip->irqdomain, offset);
+	for (offset = 0; offset < gpiochip->ngpio; offset++) {
+		irq_base = irq_create_mapping(gpiochip->irqdomain, offset);
+		if (offset == 0)
+			/*
+			 * Store the base into the gpiochip to be used when
+			 * unmapping the irqs.
+			 */
+			gpiochip->irq_base = irq_base;
+	}
 
 	return 0;
 }
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index c1c5c2368fc8..1827b43966d9 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -107,6 +107,7 @@ struct gpio_chip {
 	 */
 	struct irq_chip		*irqchip;
 	struct irq_domain	*irqdomain;
+	unsigned int		irq_base;
 	irq_flow_handler_t	irq_handler;
 	unsigned int		irq_default_type;
 #endif
-- 
cgit v1.2.3


From d18f141a1a7cfa5ffad8433e43062b05a8d1b82a Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Thu, 27 Mar 2014 14:02:03 +0200
Subject: mlx4: Add support for CONFIG_DEV command

Introduce the CONFIG_DEV firmware command which we will use to
configure the UDP port assumed by the firmware for the VXLAN offloads.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/cmd.c |  9 +++++++
 drivers/net/ethernet/mellanox/mlx4/fw.c  | 40 ++++++++++++++++++++++++++++++++
 include/linux/mlx4/cmd.h                 |  1 +
 include/linux/mlx4/device.h              |  2 ++
 4 files changed, 52 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 2fd61b60a5c5..78099eab7673 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -954,6 +954,15 @@ static struct mlx4_cmd_info cmd_info[] = {
 		.verify = NULL,
 		.wrapper = NULL
 	},
+	{
+		.opcode = MLX4_CMD_CONFIG_DEV,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_CMD_EPERM_wrapper
+	},
 	{
 		.opcode = MLX4_CMD_ALLOC_RES,
 		.has_inbox = false,
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 6bd33e2fc17c..d16a4d118903 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -1779,6 +1779,46 @@ int mlx4_CLOSE_HCA(struct mlx4_dev *dev, int panic)
 			MLX4_CMD_NATIVE);
 }
 
+struct mlx4_config_dev {
+	__be32	update_flags;
+	__be32	rsdv1[3];
+	__be16	vxlan_udp_dport;
+	__be16	rsvd2;
+};
+
+#define MLX4_VXLAN_UDP_DPORT (1 << 0)
+
+static int mlx4_CONFIG_DEV(struct mlx4_dev *dev, struct mlx4_config_dev *config_dev)
+{
+	int err;
+	struct mlx4_cmd_mailbox *mailbox;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return PTR_ERR(mailbox);
+
+	memcpy(mailbox->buf, config_dev, sizeof(*config_dev));
+
+	err = mlx4_cmd(dev, mailbox->dma, 0, 0, MLX4_CMD_CONFIG_DEV,
+		       MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
+
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return err;
+}
+
+int mlx4_config_vxlan_port(struct mlx4_dev *dev, __be16 udp_port)
+{
+	struct mlx4_config_dev config_dev;
+
+	memset(&config_dev, 0, sizeof(config_dev));
+	config_dev.update_flags    = cpu_to_be32(MLX4_VXLAN_UDP_DPORT);
+	config_dev.vxlan_udp_dport = udp_port;
+
+	return mlx4_CONFIG_DEV(dev, &config_dev);
+}
+EXPORT_SYMBOL_GPL(mlx4_config_vxlan_port);
+
+
 int mlx4_SET_ICM_SIZE(struct mlx4_dev *dev, u64 icm_size, u64 *aux_pages)
 {
 	int ret = mlx4_cmd_imm(dev, icm_size, aux_pages, 0, 0,
diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h
index 009985628257..c8450366c130 100644
--- a/include/linux/mlx4/cmd.h
+++ b/include/linux/mlx4/cmd.h
@@ -125,6 +125,7 @@ enum {
 	/* miscellaneous commands */
 	MLX4_CMD_DIAG_RPRT	 = 0x30,
 	MLX4_CMD_NOP		 = 0x31,
+	MLX4_CMD_CONFIG_DEV	 = 0x3a,
 	MLX4_CMD_ACCESS_MEM	 = 0x2e,
 	MLX4_CMD_SET_VEP	 = 0x52,
 
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 6b3998396b99..d986c975616f 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1232,4 +1232,6 @@ struct mlx4_slaves_pport mlx4_phys_to_slaves_pport_actv(
 int mlx4_phys_to_slave_port(struct mlx4_dev *dev, int slave, int port);
 
 int mlx4_get_base_gid_ix(struct mlx4_dev *dev, int slave, int port);
+
+int mlx4_config_vxlan_port(struct mlx4_dev *dev, __be16 udp_port);
 #endif /* MLX4_DEVICE_H */
-- 
cgit v1.2.3


From 1b136de120dda625109f2afe1e3d04e256be9ec1 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Thu, 27 Mar 2014 14:02:04 +0200
Subject: net/mlx4: Implement vxlan ndo calls

Add implementation for the add/del vxlan port ndo calls, using the
CONFIG_DEV firmware command.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 86 +++++++++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h   |  3 +
 drivers/net/ethernet/mellanox/mlx4/port.c      |  5 +-
 include/linux/mlx4/device.h                    |  2 +-
 4 files changed, 91 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index fa5ee719e04b..82d7eb5b79cc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -39,6 +39,7 @@
 #include <linux/hash.h>
 #include <net/ip.h>
 #include <net/busy_poll.h>
+#include <net/vxlan.h>
 
 #include <linux/mlx4/driver.h>
 #include <linux/mlx4/device.h>
@@ -1665,7 +1666,7 @@ int mlx4_en_start_port(struct net_device *dev)
 	}
 
 	if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) {
-		err = mlx4_SET_PORT_VXLAN(mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC);
+		err = mlx4_SET_PORT_VXLAN(mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC, 1);
 		if (err) {
 			en_err(priv, "Failed setting port L2 tunnel configuration, err %d\n",
 			       err);
@@ -1697,6 +1698,8 @@ int mlx4_en_start_port(struct net_device *dev)
 
 	mlx4_set_stats_bitmap(mdev->dev, &priv->stats_bitmap);
 
+	if (priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS)
+		vxlan_get_rx_port(dev);
 	priv->port_up = true;
 	netif_tx_start_all_queues(dev);
 	netif_device_attach(dev);
@@ -2264,6 +2267,81 @@ static int mlx4_en_get_phys_port_id(struct net_device *dev,
 	return 0;
 }
 
+static void mlx4_en_add_vxlan_offloads(struct work_struct *work)
+{
+	int ret;
+	struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv,
+						 vxlan_add_task);
+
+	ret = mlx4_config_vxlan_port(priv->mdev->dev, priv->vxlan_port);
+	if (ret)
+		goto out;
+
+	ret = mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port,
+				  VXLAN_STEER_BY_OUTER_MAC, 1);
+out:
+	if (ret)
+		en_err(priv, "failed setting L2 tunnel configuration ret %d\n", ret);
+}
+
+static void mlx4_en_del_vxlan_offloads(struct work_struct *work)
+{
+	int ret;
+	struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv,
+						 vxlan_del_task);
+
+	ret = mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port,
+				  VXLAN_STEER_BY_OUTER_MAC, 0);
+	if (ret)
+		en_err(priv, "failed setting L2 tunnel configuration ret %d\n", ret);
+
+	priv->vxlan_port = 0;
+}
+
+static void mlx4_en_add_vxlan_port(struct  net_device *dev,
+				   sa_family_t sa_family, __be16 port)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	__be16 current_port;
+
+	if (!(priv->mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS))
+		return;
+
+	if (sa_family == AF_INET6)
+		return;
+
+	current_port = priv->vxlan_port;
+	if (current_port && current_port != port) {
+		en_warn(priv, "vxlan port %d configured, can't add port %d\n",
+			ntohs(current_port), ntohs(port));
+		return;
+	}
+
+	priv->vxlan_port = port;
+	queue_work(priv->mdev->workqueue, &priv->vxlan_add_task);
+}
+
+static void mlx4_en_del_vxlan_port(struct  net_device *dev,
+				   sa_family_t sa_family, __be16 port)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	__be16 current_port;
+
+	if (priv->mdev->dev->caps.tunnel_offload_mode != MLX4_TUNNEL_OFFLOAD_MODE_VXLAN)
+		return;
+
+	if (sa_family == AF_INET6)
+		return;
+
+	current_port = priv->vxlan_port;
+	if (current_port != port) {
+		en_dbg(DRV, priv, "vxlan port %d isn't configured, ignoring\n", ntohs(port));
+		return;
+	}
+
+	queue_work(priv->mdev->workqueue, &priv->vxlan_del_task);
+}
+
 static const struct net_device_ops mlx4_netdev_ops = {
 	.ndo_open		= mlx4_en_open,
 	.ndo_stop		= mlx4_en_close,
@@ -2290,6 +2368,8 @@ static const struct net_device_ops mlx4_netdev_ops = {
 	.ndo_busy_poll		= mlx4_en_low_latency_recv,
 #endif
 	.ndo_get_phys_port_id	= mlx4_en_get_phys_port_id,
+	.ndo_add_vxlan_port	= mlx4_en_add_vxlan_port,
+	.ndo_del_vxlan_port	= mlx4_en_del_vxlan_port,
 };
 
 static const struct net_device_ops mlx4_netdev_ops_master = {
@@ -2381,6 +2461,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	INIT_WORK(&priv->linkstate_task, mlx4_en_linkstate);
 	INIT_DELAYED_WORK(&priv->stats_task, mlx4_en_do_get_stats);
 	INIT_DELAYED_WORK(&priv->service_task, mlx4_en_service_task);
+	INIT_WORK(&priv->vxlan_add_task, mlx4_en_add_vxlan_offloads);
+	INIT_WORK(&priv->vxlan_del_task, mlx4_en_del_vxlan_offloads);
 #ifdef CONFIG_MLX4_EN_DCB
 	if (!mlx4_is_slave(priv->mdev->dev)) {
 		if (mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_SET_ETH_SCHED) {
@@ -2514,7 +2596,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	}
 
 	if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) {
-		err = mlx4_SET_PORT_VXLAN(mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC);
+		err = mlx4_SET_PORT_VXLAN(mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC, 1);
 		if (err) {
 			en_err(priv, "Failed setting port L2 tunnel configuration, err %d\n",
 			       err);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 69e1f36858e0..36fc2a2b24c3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -559,6 +559,8 @@ struct mlx4_en_priv {
 	struct work_struct linkstate_task;
 	struct delayed_work stats_task;
 	struct delayed_work service_task;
+	struct work_struct vxlan_add_task;
+	struct work_struct vxlan_del_task;
 	struct mlx4_en_perf_stats pstats;
 	struct mlx4_en_pkt_stats pkstats;
 	struct mlx4_en_port_stats port_stats;
@@ -585,6 +587,7 @@ struct mlx4_en_priv {
 	struct hlist_head filter_hash[1 << MLX4_EN_FILTER_HASH_SHIFT];
 #endif
 	u64 tunnel_reg_id;
+	__be16 vxlan_port;
 };
 
 enum mlx4_en_wol {
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 2705b9ab9463..cfcad26ed40f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -988,7 +988,7 @@ struct mlx4_set_port_vxlan_context {
 	u8	steering;
 };
 
-int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering)
+int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering, int enable)
 {
 	int err;
 	u32 in_mod;
@@ -1002,7 +1002,8 @@ int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering)
 	memset(context, 0, sizeof(*context));
 
 	context->modify_flags = VXLAN_ENABLE_MODIFY | VXLAN_STEERING_MODIFY;
-	context->enable_flags = VXLAN_ENABLE;
+	if (enable)
+		context->enable_flags = VXLAN_ENABLE;
 	context->steering  = steering;
 
 	in_mod = MLX4_SET_PORT_VXLAN << 8 | port;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index d986c975616f..ba87bd21295a 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1142,7 +1142,7 @@ int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn,
 int mlx4_SET_PORT_PRIO2TC(struct mlx4_dev *dev, u8 port, u8 *prio2tc);
 int mlx4_SET_PORT_SCHEDULER(struct mlx4_dev *dev, u8 port, u8 *tc_tx_bw,
 		u8 *pg, u16 *ratelimit);
-int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering);
+int mlx4_SET_PORT_VXLAN(struct mlx4_dev *dev, u8 port, u8 steering, int enable);
 int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx);
 int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx);
 int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
-- 
cgit v1.2.3


From 015f0688f57ca4d499047d335b8052a733e17a4d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 27 Mar 2014 08:45:56 -0700
Subject: net: net: add a core netdev->tx_dropped counter

Dropping packets in __dev_queue_xmit() when transmit queue
is stopped (NIC TX ring buffer full or BQL limit reached) currently
outputs a syslog message.

It would be better to get a precise count of such events available in
netdevice stats so that monitoring tools can have a clue.

This extends the work done in caf586e5f23ce
("net: add a core netdev->rx_dropped counter")

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 7 ++++---
 net/core/dev.c            | 2 ++
 2 files changed, 6 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4b6d12c7b803..159c7e7945f8 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1311,9 +1311,10 @@ struct net_device {
 	int			iflink;
 
 	struct net_device_stats	stats;
-	atomic_long_t		rx_dropped; /* dropped packets by core network
-					     * Do not use this in drivers.
-					     */
+
+	/* dropped packets by core network, Do not use this in drivers */
+	atomic_long_t		rx_dropped;
+	atomic_long_t		tx_dropped;
 
 #ifdef CONFIG_WIRELESS_EXT
 	/* List of functions to handle Wireless Extensions (instead of ioctl).
diff --git a/net/core/dev.c b/net/core/dev.c
index 48dd323d5918..98ba581b89f0 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2880,6 +2880,7 @@ recursion_alert:
 	rc = -ENETDOWN;
 	rcu_read_unlock_bh();
 
+	atomic_long_inc(&dev->tx_dropped);
 	kfree_skb(skb);
 	return rc;
 out:
@@ -6238,6 +6239,7 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
 		netdev_stats_to_stats64(storage, &dev->stats);
 	}
 	storage->rx_dropped += atomic_long_read(&dev->rx_dropped);
+	storage->tx_dropped += atomic_long_read(&dev->tx_dropped);
 	return storage;
 }
 EXPORT_SYMBOL(dev_get_stats);
-- 
cgit v1.2.3


From d9721ae1493725bb14dcd1a3c19bbb5795e4a42f Mon Sep 17 00:00:00 2001
From: Axel Lin <axel.lin@ingics.com>
Date: Sat, 29 Mar 2014 18:50:12 +0800
Subject: spi: bitbang: Make spi_bitbang_stop() return void

spi_bitbang_stop() never fails, so make it return void.

Signed-off-by: Axel Lin <axel.lin@ingics.com>
Signed-off-by: Mark Brown <broonie@linaro.org>
---
 drivers/spi/spi-bitbang.c       | 4 +---
 drivers/spi/spi-butterfly.c     | 3 +--
 drivers/spi/spi-gpio.c          | 5 ++---
 drivers/spi/spi-omap-uwire.c    | 5 ++---
 include/linux/spi/spi_bitbang.h | 2 +-
 5 files changed, 7 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c
index bd222f6b677d..67aead248753 100644
--- a/drivers/spi/spi-bitbang.c
+++ b/drivers/spi/spi-bitbang.c
@@ -467,11 +467,9 @@ EXPORT_SYMBOL_GPL(spi_bitbang_start);
 /**
  * spi_bitbang_stop - stops the task providing spi communication
  */
-int spi_bitbang_stop(struct spi_bitbang *bitbang)
+void spi_bitbang_stop(struct spi_bitbang *bitbang)
 {
 	spi_unregister_master(bitbang->master);
-
-	return 0;
 }
 EXPORT_SYMBOL_GPL(spi_bitbang_stop);
 
diff --git a/drivers/spi/spi-butterfly.c b/drivers/spi/spi-butterfly.c
index 8081f96bd1d5..ee4f91ccd8fd 100644
--- a/drivers/spi/spi-butterfly.c
+++ b/drivers/spi/spi-butterfly.c
@@ -309,7 +309,6 @@ done:
 static void butterfly_detach(struct parport *p)
 {
 	struct butterfly	*pp;
-	int			status;
 
 	/* FIXME this global is ugly ... but, how to quickly get from
 	 * the parport to the "struct butterfly" associated with it?
@@ -321,7 +320,7 @@ static void butterfly_detach(struct parport *p)
 	butterfly = NULL;
 
 	/* stop() unregisters child devices too */
-	status = spi_bitbang_stop(&pp->bitbang);
+	spi_bitbang_stop(&pp->bitbang);
 
 	/* turn off VCC */
 	parport_write_data(pp->port, 0);
diff --git a/drivers/spi/spi-gpio.c b/drivers/spi/spi-gpio.c
index 7beeb29472ac..b189b958432b 100644
--- a/drivers/spi/spi-gpio.c
+++ b/drivers/spi/spi-gpio.c
@@ -503,13 +503,12 @@ static int spi_gpio_remove(struct platform_device *pdev)
 {
 	struct spi_gpio			*spi_gpio;
 	struct spi_gpio_platform_data	*pdata;
-	int				status;
 
 	spi_gpio = platform_get_drvdata(pdev);
 	pdata = dev_get_platdata(&pdev->dev);
 
 	/* stop() unregisters child devices too */
-	status = spi_bitbang_stop(&spi_gpio->bitbang);
+	spi_bitbang_stop(&spi_gpio->bitbang);
 
 	if (SPI_MISO_GPIO != SPI_GPIO_NO_MISO)
 		gpio_free(SPI_MISO_GPIO);
@@ -518,7 +517,7 @@ static int spi_gpio_remove(struct platform_device *pdev)
 	gpio_free(SPI_SCK_GPIO);
 	spi_master_put(spi_gpio->bitbang.master);
 
-	return status;
+	return 0;
 }
 
 MODULE_ALIAS("platform:" DRIVER_NAME);
diff --git a/drivers/spi/spi-omap-uwire.c b/drivers/spi/spi-omap-uwire.c
index 9313fd3b413d..a4d7bb557792 100644
--- a/drivers/spi/spi-omap-uwire.c
+++ b/drivers/spi/spi-omap-uwire.c
@@ -539,14 +539,13 @@ static int uwire_probe(struct platform_device *pdev)
 static int uwire_remove(struct platform_device *pdev)
 {
 	struct uwire_spi	*uwire = platform_get_drvdata(pdev);
-	int			status;
 
 	// FIXME remove all child devices, somewhere ...
 
-	status = spi_bitbang_stop(&uwire->bitbang);
+	spi_bitbang_stop(&uwire->bitbang);
 	uwire_off(uwire);
 	iounmap(uwire_base);
-	return status;
+	return 0;
 }
 
 /* work with hotplug and coldplug */
diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h
index daebaba886aa..85578d4be034 100644
--- a/include/linux/spi/spi_bitbang.h
+++ b/include/linux/spi/spi_bitbang.h
@@ -42,6 +42,6 @@ extern int spi_bitbang_setup_transfer(struct spi_device *spi,
 
 /* start or stop queue processing */
 extern int spi_bitbang_start(struct spi_bitbang *spi);
-extern int spi_bitbang_stop(struct spi_bitbang *spi);
+extern void spi_bitbang_stop(struct spi_bitbang *spi);
 
 #endif	/* __SPI_BITBANG_H */
-- 
cgit v1.2.3


From 1ec41830e087cda1f62dda4182c2b62811eb0ffc Mon Sep 17 00:00:00 2001
From: Li Zefan <lizefan@huawei.com>
Date: Fri, 28 Mar 2014 15:22:19 +0800
Subject: cgroup: remove useless argument from cgroup_exit()

Signed-off-by: Li Zefan <lizefan@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cgroup.h | 4 ++--
 kernel/cgroup.c        | 5 ++---
 kernel/exit.c          | 2 +-
 3 files changed, 5 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 43d1ed30bae3..c2515851c1aa 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -33,7 +33,7 @@ extern int cgroup_init_early(void);
 extern int cgroup_init(void);
 extern void cgroup_fork(struct task_struct *p);
 extern void cgroup_post_fork(struct task_struct *p);
-extern void cgroup_exit(struct task_struct *p, int run_callbacks);
+extern void cgroup_exit(struct task_struct *p);
 extern int cgroupstats_build(struct cgroupstats *stats,
 				struct dentry *dentry);
 
@@ -843,7 +843,7 @@ static inline int cgroup_init_early(void) { return 0; }
 static inline int cgroup_init(void) { return 0; }
 static inline void cgroup_fork(struct task_struct *p) {}
 static inline void cgroup_post_fork(struct task_struct *p) {}
-static inline void cgroup_exit(struct task_struct *p, int callbacks) {}
+static inline void cgroup_exit(struct task_struct *p) {}
 
 static inline int cgroupstats_build(struct cgroupstats *stats,
 					struct dentry *dentry)
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 60fd6f1f6d4e..f7f94322d312 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4416,7 +4416,6 @@ void cgroup_post_fork(struct task_struct *child)
 /**
  * cgroup_exit - detach cgroup from exiting task
  * @tsk: pointer to task_struct of exiting process
- * @run_callback: run exit callbacks?
  *
  * Description: Detach cgroup from @tsk and release it.
  *
@@ -4433,7 +4432,7 @@ void cgroup_post_fork(struct task_struct *child)
  * init_css_set refcnting.  init_css_set never goes away and we can't race
  * with migration path - PF_EXITING is visible to migration path.
  */
-void cgroup_exit(struct task_struct *tsk, int run_callbacks)
+void cgroup_exit(struct task_struct *tsk)
 {
 	struct cgroup_subsys *ss;
 	struct css_set *cset;
@@ -4455,7 +4454,7 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
 	cset = task_css_set(tsk);
 	RCU_INIT_POINTER(tsk->cgroups, &init_css_set);
 
-	if (run_callbacks && need_forkexit_callback) {
+	if (need_forkexit_callback) {
 		/* see cgroup_post_fork() for details */
 		for_each_subsys(ss, i) {
 			if (ss->exit) {
diff --git a/kernel/exit.c b/kernel/exit.c
index 1e77fc645317..6480d1c85d7a 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -797,7 +797,7 @@ void do_exit(long code)
 	 */
 	perf_event_exit_task(tsk);
 
-	cgroup_exit(tsk, 1);
+	cgroup_exit(tsk);
 
 	if (group_dead)
 		disassociate_ctty(1);
-- 
cgit v1.2.3


From e43a34e3ec5d1b14a11c3220f5a12aa797d73cd1 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 10 Mar 2014 18:11:50 -0700
Subject: shdma: add R-Car Audio DMAC peri peri driver

Add support Audio DMAC peri peri driver
for Renesas R-Car Gen2 SoC, using 'shdma-base'
DMA driver framework.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
[fixed checkpatch error]
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 drivers/dma/sh/Kconfig                         |   6 +
 drivers/dma/sh/Makefile                        |   1 +
 drivers/dma/sh/rcar-audmapp.c                  | 320 +++++++++++++++++++++++++
 include/linux/platform_data/dma-rcar-audmapp.h |  34 +++
 4 files changed, 361 insertions(+)
 create mode 100644 drivers/dma/sh/rcar-audmapp.c
 create mode 100644 include/linux/platform_data/dma-rcar-audmapp.h

(limited to 'include/linux')

diff --git a/drivers/dma/sh/Kconfig b/drivers/dma/sh/Kconfig
index dadd9e010c0b..b4c813831006 100644
--- a/drivers/dma/sh/Kconfig
+++ b/drivers/dma/sh/Kconfig
@@ -29,6 +29,12 @@ config RCAR_HPB_DMAE
 	help
 	  Enable support for the Renesas R-Car series DMA controllers.
 
+config RCAR_AUDMAC_PP
+	tristate "Renesas R-Car Audio DMAC Peripheral Peripheral support"
+	depends on SH_DMAE_BASE
+	help
+	  Enable support for the Renesas R-Car Audio DMAC Peripheral Peripheral controllers.
+
 config SHDMA_R8A73A4
 	def_bool y
 	depends on ARCH_R8A73A4 && SH_DMAE != n
diff --git a/drivers/dma/sh/Makefile b/drivers/dma/sh/Makefile
index e856af23b789..1ce88b28cfc6 100644
--- a/drivers/dma/sh/Makefile
+++ b/drivers/dma/sh/Makefile
@@ -7,3 +7,4 @@ endif
 shdma-objs := $(shdma-y)
 obj-$(CONFIG_SUDMAC) += sudmac.o
 obj-$(CONFIG_RCAR_HPB_DMAE) += rcar-hpbdma.o
+obj-$(CONFIG_RCAR_AUDMAC_PP) += rcar-audmapp.o
diff --git a/drivers/dma/sh/rcar-audmapp.c b/drivers/dma/sh/rcar-audmapp.c
new file mode 100644
index 000000000000..2de77289a2e9
--- /dev/null
+++ b/drivers/dma/sh/rcar-audmapp.c
@@ -0,0 +1,320 @@
+/*
+ * This is for Renesas R-Car Audio-DMAC-peri-peri.
+ *
+ * Copyright (C) 2014 Renesas Electronics Corporation
+ * Copyright (C) 2014 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+ *
+ * based on the drivers/dma/sh/shdma.c
+ *
+ * Copyright (C) 2011-2012 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+ * Copyright (C) 2009 Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com>
+ * Copyright (C) 2009 Renesas Solutions, Inc. All rights reserved.
+ * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/dmaengine.h>
+#include <linux/platform_data/dma-rcar-audmapp.h>
+#include <linux/platform_device.h>
+#include <linux/shdma-base.h>
+
+/*
+ * DMA register
+ */
+#define PDMASAR		0x00
+#define PDMADAR		0x04
+#define PDMACHCR	0x0c
+
+/* PDMACHCR */
+#define PDMACHCR_DE		(1 << 0)
+
+#define AUDMAPP_MAX_CHANNELS	29
+
+/* Default MEMCPY transfer size = 2^2 = 4 bytes */
+#define LOG2_DEFAULT_XFER_SIZE	2
+#define AUDMAPP_SLAVE_NUMBER	256
+#define AUDMAPP_LEN_MAX		(16 * 1024 * 1024)
+
+struct audmapp_chan {
+	struct shdma_chan shdma_chan;
+	struct audmapp_slave_config *config;
+	void __iomem *base;
+};
+
+struct audmapp_device {
+	struct shdma_dev shdma_dev;
+	struct audmapp_pdata *pdata;
+	struct device *dev;
+	void __iomem *chan_reg;
+};
+
+#define to_chan(chan) container_of(chan, struct audmapp_chan, shdma_chan)
+#define to_dev(chan) container_of(chan->shdma_chan.dma_chan.device,	\
+				  struct audmapp_device, shdma_dev.dma_dev)
+
+static void audmapp_write(struct audmapp_chan *auchan, u32 data, u32 reg)
+{
+	struct audmapp_device *audev = to_dev(auchan);
+	struct device *dev = audev->dev;
+
+	dev_dbg(dev, "w %p : %08x\n", auchan->base + reg, data);
+
+	iowrite32(data, auchan->base + reg);
+}
+
+static u32 audmapp_read(struct audmapp_chan *auchan, u32 reg)
+{
+	return ioread32(auchan->base + reg);
+}
+
+static void audmapp_halt(struct shdma_chan *schan)
+{
+	struct audmapp_chan *auchan = to_chan(schan);
+	int i;
+
+	audmapp_write(auchan, 0, PDMACHCR);
+
+	for (i = 0; i < 1024; i++) {
+		if (0 == audmapp_read(auchan, PDMACHCR))
+			return;
+		udelay(1);
+	}
+}
+
+static void audmapp_start_xfer(struct shdma_chan *schan,
+			       struct shdma_desc *sdecs)
+{
+	struct audmapp_chan *auchan = to_chan(schan);
+	struct audmapp_device *audev = to_dev(auchan);
+	struct audmapp_slave_config *cfg = auchan->config;
+	struct device *dev = audev->dev;
+	u32 chcr = cfg->chcr | PDMACHCR_DE;
+
+	dev_dbg(dev, "src/dst/chcr = %pad/%pad/%x\n",
+		&cfg->src, &cfg->dst, cfg->chcr);
+
+	audmapp_write(auchan, cfg->src,	PDMASAR);
+	audmapp_write(auchan, cfg->dst,	PDMADAR);
+	audmapp_write(auchan, chcr,	PDMACHCR);
+}
+
+static struct audmapp_slave_config *
+audmapp_find_slave(struct audmapp_chan *auchan, int slave_id)
+{
+	struct audmapp_device *audev = to_dev(auchan);
+	struct audmapp_pdata *pdata = audev->pdata;
+	struct audmapp_slave_config *cfg;
+	int i;
+
+	if (slave_id >= AUDMAPP_SLAVE_NUMBER)
+		return NULL;
+
+	for (i = 0, cfg = pdata->slave; i < pdata->slave_num; i++, cfg++)
+		if (cfg->slave_id == slave_id)
+			return cfg;
+
+	return NULL;
+}
+
+static int audmapp_set_slave(struct shdma_chan *schan, int slave_id,
+			     dma_addr_t slave_addr, bool try)
+{
+	struct audmapp_chan *auchan = to_chan(schan);
+	struct audmapp_slave_config *cfg =
+		audmapp_find_slave(auchan, slave_id);
+
+	if (!cfg)
+		return -ENODEV;
+	if (try)
+		return 0;
+
+	auchan->config	= cfg;
+
+	return 0;
+}
+
+static int audmapp_desc_setup(struct shdma_chan *schan,
+			      struct shdma_desc *sdecs,
+			      dma_addr_t src, dma_addr_t dst, size_t *len)
+{
+	struct audmapp_chan *auchan = to_chan(schan);
+	struct audmapp_slave_config *cfg = auchan->config;
+
+	if (!cfg)
+		return -ENODEV;
+
+	if (*len > (size_t)AUDMAPP_LEN_MAX)
+		*len = (size_t)AUDMAPP_LEN_MAX;
+
+	return 0;
+}
+
+static void audmapp_setup_xfer(struct shdma_chan *schan,
+			       int slave_id)
+{
+}
+
+static dma_addr_t audmapp_slave_addr(struct shdma_chan *schan)
+{
+	return 0; /* always fixed address */
+}
+
+static bool audmapp_channel_busy(struct shdma_chan *schan)
+{
+	struct audmapp_chan *auchan = to_chan(schan);
+	u32 chcr = audmapp_read(auchan, PDMACHCR);
+
+	return chcr & ~PDMACHCR_DE;
+}
+
+static bool audmapp_desc_completed(struct shdma_chan *schan,
+				   struct shdma_desc *sdesc)
+{
+	return true;
+}
+
+static struct shdma_desc *audmapp_embedded_desc(void *buf, int i)
+{
+	return &((struct shdma_desc *)buf)[i];
+}
+
+static const struct shdma_ops audmapp_shdma_ops = {
+	.halt_channel	= audmapp_halt,
+	.desc_setup	= audmapp_desc_setup,
+	.set_slave	= audmapp_set_slave,
+	.start_xfer	= audmapp_start_xfer,
+	.embedded_desc	= audmapp_embedded_desc,
+	.setup_xfer	= audmapp_setup_xfer,
+	.slave_addr	= audmapp_slave_addr,
+	.channel_busy	= audmapp_channel_busy,
+	.desc_completed	= audmapp_desc_completed,
+};
+
+static int audmapp_chan_probe(struct platform_device *pdev,
+			      struct audmapp_device *audev, int id)
+{
+	struct shdma_dev *sdev = &audev->shdma_dev;
+	struct audmapp_chan *auchan;
+	struct shdma_chan *schan;
+	struct device *dev = audev->dev;
+
+	auchan = devm_kzalloc(dev, sizeof(*auchan), GFP_KERNEL);
+	if (!auchan)
+		return -ENOMEM;
+
+	schan = &auchan->shdma_chan;
+	schan->max_xfer_len = AUDMAPP_LEN_MAX;
+
+	shdma_chan_probe(sdev, schan, id);
+
+	auchan->base = audev->chan_reg + 0x20 + (0x10 * id);
+	dev_dbg(dev, "%02d : %p / %p", id, auchan->base, audev->chan_reg);
+
+	return 0;
+}
+
+static void audmapp_chan_remove(struct audmapp_device *audev)
+{
+	struct dma_device *dma_dev = &audev->shdma_dev.dma_dev;
+	struct shdma_chan *schan;
+	int i;
+
+	shdma_for_each_chan(schan, &audev->shdma_dev, i) {
+		BUG_ON(!schan);
+		shdma_chan_remove(schan);
+	}
+	dma_dev->chancnt = 0;
+}
+
+static int audmapp_probe(struct platform_device *pdev)
+{
+	struct audmapp_pdata *pdata = pdev->dev.platform_data;
+	struct audmapp_device *audev;
+	struct shdma_dev *sdev;
+	struct dma_device *dma_dev;
+	struct resource *res;
+	int err, i;
+
+	if (!pdata)
+		return -ENODEV;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+	audev = devm_kzalloc(&pdev->dev, sizeof(*audev), GFP_KERNEL);
+	if (!audev)
+		return -ENOMEM;
+
+	audev->dev	= &pdev->dev;
+	audev->pdata	= pdata;
+	audev->chan_reg	= devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(audev->chan_reg))
+		return PTR_ERR(audev->chan_reg);
+
+	sdev		= &audev->shdma_dev;
+	sdev->ops	= &audmapp_shdma_ops;
+	sdev->desc_size	= sizeof(struct shdma_desc);
+
+	dma_dev			= &sdev->dma_dev;
+	dma_dev->copy_align	= LOG2_DEFAULT_XFER_SIZE;
+	dma_cap_set(DMA_SLAVE, dma_dev->cap_mask);
+
+	err = shdma_init(&pdev->dev, sdev, AUDMAPP_MAX_CHANNELS);
+	if (err < 0)
+		return err;
+
+	platform_set_drvdata(pdev, audev);
+
+	/* Create DMA Channel */
+	for (i = 0; i < AUDMAPP_MAX_CHANNELS; i++) {
+		err = audmapp_chan_probe(pdev, audev, i);
+		if (err)
+			goto chan_probe_err;
+	}
+
+	err = dma_async_device_register(dma_dev);
+	if (err < 0)
+		goto chan_probe_err;
+
+	return err;
+
+chan_probe_err:
+	audmapp_chan_remove(audev);
+	shdma_cleanup(sdev);
+
+	return err;
+}
+
+static int audmapp_remove(struct platform_device *pdev)
+{
+	struct audmapp_device *audev = platform_get_drvdata(pdev);
+	struct dma_device *dma_dev = &audev->shdma_dev.dma_dev;
+
+	dma_async_device_unregister(dma_dev);
+
+	audmapp_chan_remove(audev);
+	shdma_cleanup(&audev->shdma_dev);
+
+	return 0;
+}
+
+static struct platform_driver audmapp_driver = {
+	.probe		= audmapp_probe,
+	.remove		= audmapp_remove,
+	.driver		= {
+		.owner	= THIS_MODULE,
+		.name	= "rcar-audmapp-engine",
+	},
+};
+module_platform_driver(audmapp_driver);
+
+MODULE_AUTHOR("Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>");
+MODULE_DESCRIPTION("Renesas R-Car Audio DMAC peri-peri driver");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/platform_data/dma-rcar-audmapp.h b/include/linux/platform_data/dma-rcar-audmapp.h
new file mode 100644
index 000000000000..471fffebbeb4
--- /dev/null
+++ b/include/linux/platform_data/dma-rcar-audmapp.h
@@ -0,0 +1,34 @@
+/*
+ * This is for Renesas R-Car Audio-DMAC-peri-peri.
+ *
+ * Copyright (C) 2014 Renesas Electronics Corporation
+ * Copyright (C) 2014 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+ *
+ * This file is based on the include/linux/sh_dma.h
+ *
+ * Header for the new SH dmaengine driver
+ *
+ * Copyright (C) 2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef SH_AUDMAPP_H
+#define SH_AUDMAPP_H
+
+#include <linux/dmaengine.h>
+
+struct audmapp_slave_config {
+	int		slave_id;
+	dma_addr_t	src;
+	dma_addr_t	dst;
+	u32		chcr;
+};
+
+struct audmapp_pdata {
+	struct audmapp_slave_config *slave;
+	int slave_num;
+};
+
+#endif /* SH_AUDMAPP_H */
-- 
cgit v1.2.3


From a8779ec1c5e60548b7b661a8d74a8cecf7775690 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Thu, 27 Mar 2014 15:36:38 -0700
Subject: netpoll: Remove gfp parameter from __netpoll_setup

The gfp parameter was added in:
commit 47be03a28cc6c80e3aa2b3e8ed6d960ff0c5c0af
Author: Amerigo Wang <amwang@redhat.com>
Date:   Fri Aug 10 01:24:37 2012 +0000

    netpoll: use GFP_ATOMIC in slave_enable_netpoll() and __netpoll_setup()

    slave_enable_netpoll() and __netpoll_setup() may be called
    with read_lock() held, so should use GFP_ATOMIC to allocate
    memory. Eric suggested to pass gfp flags to __netpoll_setup().

    Cc: Eric Dumazet <eric.dumazet@gmail.com>
    Cc: "David S. Miller" <davem@davemloft.net>
    Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
    Signed-off-by: Eric Dumazet <edumazet@google.com>
    Signed-off-by: Cong Wang <amwang@redhat.com>
    Signed-off-by: David S. Miller <davem@davemloft.net>

The reason for the gfp parameter was removed in:
commit c4cdef9b7183159c23c7302aaf270d64c549f557
Author: dingtianhong <dingtianhong@huawei.com>
Date:   Tue Jul 23 15:25:27 2013 +0800

    bonding: don't call slave_xxx_netpoll under spinlocks

    The slave_xxx_netpoll will call synchronize_rcu_bh(),
    so the function may schedule and sleep, it should't be
    called under spinlocks.

    bond_netpoll_setup() and bond_netpoll_cleanup() are always
    protected by rtnl lock, it is no need to take the read lock,
    as the slave list couldn't be changed outside rtnl lock.

    Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
    Cc: Jay Vosburgh <fubar@us.ibm.com>
    Cc: Andy Gospodarek <andy@greyhouse.net>
    Signed-off-by: David S. Miller <davem@davemloft.net>

Nothing else that calls __netpoll_setup or ndo_netpoll_setup
requires a gfp paramter, so remove the gfp parameter from both
of these functions making the code clearer.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c |  6 +++---
 drivers/net/team/team.c         | 16 +++++++---------
 include/linux/netdevice.h       |  3 +--
 include/linux/netpoll.h         |  2 +-
 net/8021q/vlan_dev.c            |  7 +++----
 net/bridge/br_device.c          | 15 +++++++--------
 net/bridge/br_if.c              |  2 +-
 net/bridge/br_private.h         |  4 ++--
 net/core/netpoll.c              |  8 ++++----
 9 files changed, 29 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 5be34b72a048..95a6ca7d9e51 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -922,12 +922,12 @@ static inline int slave_enable_netpoll(struct slave *slave)
 	struct netpoll *np;
 	int err = 0;
 
-	np = kzalloc(sizeof(*np), GFP_ATOMIC);
+	np = kzalloc(sizeof(*np), GFP_KERNEL);
 	err = -ENOMEM;
 	if (!np)
 		goto out;
 
-	err = __netpoll_setup(np, slave->dev, GFP_ATOMIC);
+	err = __netpoll_setup(np, slave->dev);
 	if (err) {
 		kfree(np);
 		goto out;
@@ -962,7 +962,7 @@ static void bond_netpoll_cleanup(struct net_device *bond_dev)
 			slave_disable_netpoll(slave);
 }
 
-static int bond_netpoll_setup(struct net_device *dev, struct netpoll_info *ni, gfp_t gfp)
+static int bond_netpoll_setup(struct net_device *dev, struct netpoll_info *ni)
 {
 	struct bonding *bond = netdev_priv(dev);
 	struct list_head *iter;
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 2b1a1d61072c..33008c1d1d67 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1031,8 +1031,7 @@ static void team_port_leave(struct team *team, struct team_port *port)
 }
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
-static int team_port_enable_netpoll(struct team *team, struct team_port *port,
-				    gfp_t gfp)
+static int team_port_enable_netpoll(struct team *team, struct team_port *port)
 {
 	struct netpoll *np;
 	int err;
@@ -1040,11 +1039,11 @@ static int team_port_enable_netpoll(struct team *team, struct team_port *port,
 	if (!team->dev->npinfo)
 		return 0;
 
-	np = kzalloc(sizeof(*np), gfp);
+	np = kzalloc(sizeof(*np), GFP_KERNEL);
 	if (!np)
 		return -ENOMEM;
 
-	err = __netpoll_setup(np, port->dev, gfp);
+	err = __netpoll_setup(np, port->dev);
 	if (err) {
 		kfree(np);
 		return err;
@@ -1067,8 +1066,7 @@ static void team_port_disable_netpoll(struct team_port *port)
 	kfree(np);
 }
 #else
-static int team_port_enable_netpoll(struct team *team, struct team_port *port,
-				    gfp_t gfp)
+static int team_port_enable_netpoll(struct team *team, struct team_port *port)
 {
 	return 0;
 }
@@ -1156,7 +1154,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev)
 		goto err_vids_add;
 	}
 
-	err = team_port_enable_netpoll(team, port, GFP_KERNEL);
+	err = team_port_enable_netpoll(team, port);
 	if (err) {
 		netdev_err(dev, "Failed to enable netpoll on device %s\n",
 			   portname);
@@ -1850,7 +1848,7 @@ static void team_netpoll_cleanup(struct net_device *dev)
 }
 
 static int team_netpoll_setup(struct net_device *dev,
-			      struct netpoll_info *npifo, gfp_t gfp)
+			      struct netpoll_info *npifo)
 {
 	struct team *team = netdev_priv(dev);
 	struct team_port *port;
@@ -1858,7 +1856,7 @@ static int team_netpoll_setup(struct net_device *dev,
 
 	mutex_lock(&team->lock);
 	list_for_each_entry(port, &team->port_list, list) {
-		err = team_port_enable_netpoll(team, port, gfp);
+		err = team_port_enable_netpoll(team, port);
 		if (err) {
 			__team_netpoll_cleanup(team);
 			break;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 159c7e7945f8..0d8c8718980a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1037,8 +1037,7 @@ struct net_device_ops {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	void                    (*ndo_poll_controller)(struct net_device *dev);
 	int			(*ndo_netpoll_setup)(struct net_device *dev,
-						     struct netpoll_info *info,
-						     gfp_t gfp);
+						     struct netpoll_info *info);
 	void			(*ndo_netpoll_cleanup)(struct net_device *dev);
 #endif
 #ifdef CONFIG_NET_RX_BUSY_POLL
diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index 1b475a5a7239..893b9e66060e 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -57,7 +57,7 @@ static inline void netpoll_rx_enable(struct net_device *dev) { return; }
 void netpoll_send_udp(struct netpoll *np, const char *msg, int len);
 void netpoll_print_options(struct netpoll *np);
 int netpoll_parse_options(struct netpoll *np, char *opt);
-int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp);
+int __netpoll_setup(struct netpoll *np, struct net_device *ndev);
 int netpoll_setup(struct netpoll *np);
 void __netpoll_cleanup(struct netpoll *np);
 void __netpoll_free_async(struct netpoll *np);
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 4f3e9073cb49..a78bebeca4d9 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -707,20 +707,19 @@ static void vlan_dev_poll_controller(struct net_device *dev)
 	return;
 }
 
-static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo,
-				  gfp_t gfp)
+static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo)
 {
 	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	struct net_device *real_dev = vlan->real_dev;
 	struct netpoll *netpoll;
 	int err = 0;
 
-	netpoll = kzalloc(sizeof(*netpoll), gfp);
+	netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL);
 	err = -ENOMEM;
 	if (!netpoll)
 		goto out;
 
-	err = __netpoll_setup(netpoll, real_dev, gfp);
+	err = __netpoll_setup(netpoll, real_dev);
 	if (err) {
 		kfree(netpoll);
 		goto out;
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index f2a08477e0f5..0dd01a05bd59 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -218,16 +218,16 @@ static void br_netpoll_cleanup(struct net_device *dev)
 		br_netpoll_disable(p);
 }
 
-static int __br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp)
+static int __br_netpoll_enable(struct net_bridge_port *p)
 {
 	struct netpoll *np;
 	int err;
 
-	np = kzalloc(sizeof(*p->np), gfp);
+	np = kzalloc(sizeof(*p->np), GFP_KERNEL);
 	if (!np)
 		return -ENOMEM;
 
-	err = __netpoll_setup(np, p->dev, gfp);
+	err = __netpoll_setup(np, p->dev);
 	if (err) {
 		kfree(np);
 		return err;
@@ -237,16 +237,15 @@ static int __br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp)
 	return err;
 }
 
-int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp)
+int br_netpoll_enable(struct net_bridge_port *p)
 {
 	if (!p->br->dev->npinfo)
 		return 0;
 
-	return __br_netpoll_enable(p, gfp);
+	return __br_netpoll_enable(p);
 }
 
-static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni,
-			    gfp_t gfp)
+static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni)
 {
 	struct net_bridge *br = netdev_priv(dev);
 	struct net_bridge_port *p;
@@ -255,7 +254,7 @@ static int br_netpoll_setup(struct net_device *dev, struct netpoll_info *ni,
 	list_for_each_entry(p, &br->port_list, list) {
 		if (!p->dev)
 			continue;
-		err = __br_netpoll_enable(p, gfp);
+		err = __br_netpoll_enable(p);
 		if (err)
 			goto fail;
 	}
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 54d207d3a31c..5262b8617eb9 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -366,7 +366,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
 	if (err)
 		goto err2;
 
-	err = br_netpoll_enable(p, GFP_KERNEL);
+	err = br_netpoll_enable(p);
 	if (err)
 		goto err3;
 
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index e1ca1dc916a4..06811d79f89f 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -349,7 +349,7 @@ static inline void br_netpoll_send_skb(const struct net_bridge_port *p,
 		netpoll_send_skb(np, skb);
 }
 
-int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp);
+int br_netpoll_enable(struct net_bridge_port *p);
 void br_netpoll_disable(struct net_bridge_port *p);
 #else
 static inline void br_netpoll_send_skb(const struct net_bridge_port *p,
@@ -357,7 +357,7 @@ static inline void br_netpoll_send_skb(const struct net_bridge_port *p,
 {
 }
 
-static inline int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp)
+static inline int br_netpoll_enable(struct net_bridge_port *p)
 {
 	return 0;
 }
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 41c4e9ce1141..2c6379da295c 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -584,7 +584,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
 }
 EXPORT_SYMBOL(netpoll_parse_options);
 
-int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
+int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
 {
 	struct netpoll_info *npinfo;
 	const struct net_device_ops *ops;
@@ -603,7 +603,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
 	}
 
 	if (!ndev->npinfo) {
-		npinfo = kmalloc(sizeof(*npinfo), gfp);
+		npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL);
 		if (!npinfo) {
 			err = -ENOMEM;
 			goto out;
@@ -617,7 +617,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp)
 
 		ops = np->dev->netdev_ops;
 		if (ops->ndo_netpoll_setup) {
-			err = ops->ndo_netpoll_setup(ndev, npinfo, gfp);
+			err = ops->ndo_netpoll_setup(ndev, npinfo);
 			if (err)
 				goto free_npinfo;
 		}
@@ -749,7 +749,7 @@ int netpoll_setup(struct netpoll *np)
 	/* fill up the skb queue */
 	refill_skbs();
 
-	err = __netpoll_setup(np, ndev, GFP_KERNEL);
+	err = __netpoll_setup(np, ndev);
 	if (err)
 		goto put;
 
-- 
cgit v1.2.3


From 66b5552fc2dfbaa6445b1bdadd10c9305ce261bd Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Thu, 27 Mar 2014 15:39:03 -0700
Subject: netpoll: Rename netpoll_rx_enable/disable to
 netpoll_poll_disable/enable

The netpoll_rx_enable and netpoll_rx_disable functions have always
controlled polling the network drivers transmit and receive queues.

Rename them to netpoll_poll_enable and netpoll_poll_disable to make
their functionality clear.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netpoll.h | 8 ++++----
 net/core/dev.c          | 8 ++++----
 net/core/netpoll.c      | 8 ++++----
 3 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index 893b9e66060e..b25ee9ffdbe6 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -47,11 +47,11 @@ struct netpoll_info {
 };
 
 #ifdef CONFIG_NETPOLL
-extern void netpoll_rx_disable(struct net_device *dev);
-extern void netpoll_rx_enable(struct net_device *dev);
+extern void netpoll_poll_disable(struct net_device *dev);
+extern void netpoll_poll_enable(struct net_device *dev);
 #else
-static inline void netpoll_rx_disable(struct net_device *dev) { return; }
-static inline void netpoll_rx_enable(struct net_device *dev) { return; }
+static inline void netpoll_poll_disable(struct net_device *dev) { return; }
+static inline void netpoll_poll_enable(struct net_device *dev) { return; }
 #endif
 
 void netpoll_send_udp(struct netpoll *np, const char *msg, int len);
diff --git a/net/core/dev.c b/net/core/dev.c
index 8d55fe780e3f..778b2036a9e7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1245,7 +1245,7 @@ static int __dev_open(struct net_device *dev)
 	 * If we don't do this there is a chance ndo_poll_controller
 	 * or ndo_poll may be running while we open the device
 	 */
-	netpoll_rx_disable(dev);
+	netpoll_poll_disable(dev);
 
 	ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev);
 	ret = notifier_to_errno(ret);
@@ -1260,7 +1260,7 @@ static int __dev_open(struct net_device *dev)
 	if (!ret && ops->ndo_open)
 		ret = ops->ndo_open(dev);
 
-	netpoll_rx_enable(dev);
+	netpoll_poll_enable(dev);
 
 	if (ret)
 		clear_bit(__LINK_STATE_START, &dev->state);
@@ -1314,7 +1314,7 @@ static int __dev_close_many(struct list_head *head)
 
 	list_for_each_entry(dev, head, close_list) {
 		/* Temporarily disable netpoll until the interface is down */
-		netpoll_rx_disable(dev);
+		netpoll_poll_disable(dev);
 
 		call_netdevice_notifiers(NETDEV_GOING_DOWN, dev);
 
@@ -1346,7 +1346,7 @@ static int __dev_close_many(struct list_head *head)
 
 		dev->flags &= ~IFF_UP;
 		net_dmaengine_put();
-		netpoll_rx_enable(dev);
+		netpoll_poll_enable(dev);
 	}
 
 	return 0;
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index e2492d176ae7..9fd88875faff 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -214,7 +214,7 @@ static void netpoll_poll_dev(struct net_device *dev)
 	zap_completion_queue();
 }
 
-void netpoll_rx_disable(struct net_device *dev)
+void netpoll_poll_disable(struct net_device *dev)
 {
 	struct netpoll_info *ni;
 	int idx;
@@ -225,9 +225,9 @@ void netpoll_rx_disable(struct net_device *dev)
 		down(&ni->dev_lock);
 	srcu_read_unlock(&netpoll_srcu, idx);
 }
-EXPORT_SYMBOL(netpoll_rx_disable);
+EXPORT_SYMBOL(netpoll_poll_disable);
 
-void netpoll_rx_enable(struct net_device *dev)
+void netpoll_poll_enable(struct net_device *dev)
 {
 	struct netpoll_info *ni;
 	rcu_read_lock();
@@ -236,7 +236,7 @@ void netpoll_rx_enable(struct net_device *dev)
 		up(&ni->dev_lock);
 	rcu_read_unlock();
 }
-EXPORT_SYMBOL(netpoll_rx_enable);
+EXPORT_SYMBOL(netpoll_poll_enable);
 
 static void refill_skbs(void)
 {
-- 
cgit v1.2.3


From 5efeac44cfca62f66a1b2919fc8ec7f7c726d15b Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Thu, 27 Mar 2014 15:42:20 -0700
Subject: netpoll: Respect NETIF_F_LLTX

Stop taking the transmit lock when a network device has specified
NETIF_F_LLTX.

If no locks needed to trasnmit a packet this is the ideal scenario for
netpoll as all packets can be trasnmitted immediately.

Even if some locks are needed in ndo_start_xmit skipping any unnecessary
serialization is desirable for netpoll as it makes it more likely a
debugging packet may be trasnmitted immediately instead of being
deferred until later.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  5 +++++
 net/core/netpoll.c        | 10 +++++-----
 2 files changed, 10 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 0d8c8718980a..4cd5e9e13c87 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2909,6 +2909,11 @@ static inline void netif_tx_unlock_bh(struct net_device *dev)
 	}						\
 }
 
+#define HARD_TX_TRYLOCK(dev, txq)			\
+	(((dev->features & NETIF_F_LLTX) == 0) ?	\
+		__netif_tx_trylock(txq) :		\
+		true )
+
 #define HARD_TX_UNLOCK(dev, txq) {			\
 	if ((dev->features & NETIF_F_LLTX) == 0) {	\
 		__netif_tx_unlock(txq);			\
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index d44af2306f23..ed7740f7a94d 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -119,17 +119,17 @@ static void queue_process(struct work_struct *work)
 		txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
 
 		local_irq_save(flags);
-		__netif_tx_lock(txq, smp_processor_id());
+		HARD_TX_LOCK(dev, txq, smp_processor_id());
 		if (netif_xmit_frozen_or_stopped(txq) ||
 		    netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) {
 			skb_queue_head(&npinfo->txq, skb);
-			__netif_tx_unlock(txq);
+			HARD_TX_UNLOCK(dev, txq);
 			local_irq_restore(flags);
 
 			schedule_delayed_work(&npinfo->tx_work, HZ/10);
 			return;
 		}
-		__netif_tx_unlock(txq);
+		HARD_TX_UNLOCK(dev, txq);
 		local_irq_restore(flags);
 	}
 }
@@ -345,11 +345,11 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 		/* try until next clock tick */
 		for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
 		     tries > 0; --tries) {
-			if (__netif_tx_trylock(txq)) {
+			if (HARD_TX_TRYLOCK(dev, txq)) {
 				if (!netif_xmit_stopped(txq))
 					status = netpoll_start_xmit(skb, dev, txq);
 
-				__netif_tx_unlock(txq);
+				HARD_TX_UNLOCK(dev, txq);
 
 				if (status == NETDEV_TX_OK)
 					break;
-- 
cgit v1.2.3


From 83ddfebdd21da669918d7f9854fd592858625f4b Mon Sep 17 00:00:00 2001
From: Kinglong Mee <kinglongmee@gmail.com>
Date: Mon, 24 Mar 2014 11:58:59 +0800
Subject: SUNRPC: New helper for creating client with rpc_xprt

Signed-off-by: Kinglong Mee <kinglongmee@gmail.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 include/linux/sunrpc/clnt.h |  2 ++
 net/sunrpc/clnt.c           | 58 ++++++++++++++++++++++++++-------------------
 2 files changed, 35 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 8af2804bab16..70736b98c721 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -130,6 +130,8 @@ struct rpc_create_args {
 #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT	(1UL << 9)
 
 struct rpc_clnt *rpc_create(struct rpc_create_args *args);
+struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
+					struct rpc_xprt *xprt);
 struct rpc_clnt	*rpc_bind_new_program(struct rpc_clnt *,
 				const struct rpc_program *, u32);
 void rpc_task_reset_client(struct rpc_task *task, struct rpc_clnt *clnt);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 0edada973434..3c9a0f02374d 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -438,6 +438,38 @@ out_no_rpciod:
 	return ERR_PTR(err);
 }
 
+struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args,
+					struct rpc_xprt *xprt)
+{
+	struct rpc_clnt *clnt = NULL;
+
+	clnt = rpc_new_client(args, xprt, NULL);
+	if (IS_ERR(clnt))
+		return clnt;
+
+	if (!(args->flags & RPC_CLNT_CREATE_NOPING)) {
+		int err = rpc_ping(clnt);
+		if (err != 0) {
+			rpc_shutdown_client(clnt);
+			return ERR_PTR(err);
+		}
+	}
+
+	clnt->cl_softrtry = 1;
+	if (args->flags & RPC_CLNT_CREATE_HARDRTRY)
+		clnt->cl_softrtry = 0;
+
+	if (args->flags & RPC_CLNT_CREATE_AUTOBIND)
+		clnt->cl_autobind = 1;
+	if (args->flags & RPC_CLNT_CREATE_DISCRTRY)
+		clnt->cl_discrtry = 1;
+	if (!(args->flags & RPC_CLNT_CREATE_QUIET))
+		clnt->cl_chatty = 1;
+
+	return clnt;
+}
+EXPORT_SYMBOL_GPL(rpc_create_xprt);
+
 /**
  * rpc_create - create an RPC client and transport with one call
  * @args: rpc_clnt create argument structure
@@ -451,7 +483,6 @@ out_no_rpciod:
 struct rpc_clnt *rpc_create(struct rpc_create_args *args)
 {
 	struct rpc_xprt *xprt;
-	struct rpc_clnt *clnt;
 	struct xprt_create xprtargs = {
 		.net = args->net,
 		.ident = args->protocol,
@@ -515,30 +546,7 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args)
 	if (args->flags & RPC_CLNT_CREATE_NONPRIVPORT)
 		xprt->resvport = 0;
 
-	clnt = rpc_new_client(args, xprt, NULL);
-	if (IS_ERR(clnt))
-		return clnt;
-
-	if (!(args->flags & RPC_CLNT_CREATE_NOPING)) {
-		int err = rpc_ping(clnt);
-		if (err != 0) {
-			rpc_shutdown_client(clnt);
-			return ERR_PTR(err);
-		}
-	}
-
-	clnt->cl_softrtry = 1;
-	if (args->flags & RPC_CLNT_CREATE_HARDRTRY)
-		clnt->cl_softrtry = 0;
-
-	if (args->flags & RPC_CLNT_CREATE_AUTOBIND)
-		clnt->cl_autobind = 1;
-	if (args->flags & RPC_CLNT_CREATE_DISCRTRY)
-		clnt->cl_discrtry = 1;
-	if (!(args->flags & RPC_CLNT_CREATE_QUIET))
-		clnt->cl_chatty = 1;
-
-	return clnt;
+	return rpc_create_xprt(args, xprt);
 }
 EXPORT_SYMBOL_GPL(rpc_create);
 
-- 
cgit v1.2.3


From d531c008d7d9713456abe3d265fc577bba2e1cef Mon Sep 17 00:00:00 2001
From: Kinglong Mee <kinglongmee@gmail.com>
Date: Mon, 24 Mar 2014 11:59:46 +0800
Subject: NFSD/SUNRPC: Check rpc_xprt out of xs_setup_bc_tcp

Besides checking rpc_xprt out of xs_setup_bc_tcp,
increase it's reference (it's important).

Signed-off-by: Kinglong Mee <kinglongmee@gmail.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfs4callback.c      | 19 ++++++++++++++++++-
 include/linux/sunrpc/xprt.h | 13 ++++++++++++-
 net/sunrpc/xprt.c           | 12 ------------
 net/sunrpc/xprtsock.c       |  9 ---------
 4 files changed, 30 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 7f05cd140de3..39c8ef875f91 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -32,6 +32,7 @@
  */
 
 #include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/xprt.h>
 #include <linux/sunrpc/svc_xprt.h>
 #include <linux/slab.h>
 #include "nfsd.h"
@@ -635,6 +636,22 @@ static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc
 	}
 }
 
+static struct rpc_clnt *create_backchannel_client(struct rpc_create_args *args)
+{
+	struct rpc_xprt *xprt;
+
+	if (args->protocol != XPRT_TRANSPORT_BC_TCP)
+		return rpc_create(args);
+
+	xprt = args->bc_xprt->xpt_bc_xprt;
+	if (xprt) {
+		xprt_get(xprt);
+		return rpc_create_xprt(args, xprt);
+	}
+
+	return rpc_create(args);
+}
+
 static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn, struct nfsd4_session *ses)
 {
 	struct rpc_timeout	timeparms = {
@@ -674,7 +691,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
 		args.authflavor = ses->se_cb_sec.flavor;
 	}
 	/* Create RPC client */
-	client = rpc_create(&args);
+	client = create_backchannel_client(&args);
 	if (IS_ERR(client)) {
 		dprintk("NFSD: couldn't create callback client: %ld\n",
 			PTR_ERR(client));
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 8097b9df6773..3e5efb2b236e 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -295,13 +295,24 @@ int			xprt_adjust_timeout(struct rpc_rqst *req);
 void			xprt_release_xprt(struct rpc_xprt *xprt, struct rpc_task *task);
 void			xprt_release_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task);
 void			xprt_release(struct rpc_task *task);
-struct rpc_xprt *	xprt_get(struct rpc_xprt *xprt);
 void			xprt_put(struct rpc_xprt *xprt);
 struct rpc_xprt *	xprt_alloc(struct net *net, size_t size,
 				unsigned int num_prealloc,
 				unsigned int max_req);
 void			xprt_free(struct rpc_xprt *);
 
+/**
+ * xprt_get - return a reference to an RPC transport.
+ * @xprt: pointer to the transport
+ *
+ */
+static inline struct rpc_xprt *xprt_get(struct rpc_xprt *xprt)
+{
+	if (atomic_inc_not_zero(&xprt->count))
+		return xprt;
+	return NULL;
+}
+
 static inline __be32 *xprt_skip_transport_header(struct rpc_xprt *xprt, __be32 *p)
 {
 	return p + xprt->tsh_size;
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 7d4df99f761f..d173f79947c6 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1383,15 +1383,3 @@ void xprt_put(struct rpc_xprt *xprt)
 	if (atomic_dec_and_test(&xprt->count))
 		xprt_destroy(xprt);
 }
-
-/**
- * xprt_get - return a reference to an RPC transport.
- * @xprt: pointer to the transport
- *
- */
-struct rpc_xprt *xprt_get(struct rpc_xprt *xprt)
-{
-	if (atomic_inc_not_zero(&xprt->count))
-		return xprt;
-	return NULL;
-}
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 63ae657f255b..1335239217cd 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2923,15 +2923,6 @@ static struct rpc_xprt *xs_setup_bc_tcp(struct xprt_create *args)
 	struct svc_sock *bc_sock;
 	struct rpc_xprt *ret;
 
-	if (args->bc_xprt->xpt_bc_xprt) {
-		/*
-		 * This server connection already has a backchannel
-		 * transport; we can't create a new one, as we wouldn't
-		 * be able to match replies based on xid any more.  So,
-		 * reuse the already-existing one:
-		 */
-		 return args->bc_xprt->xpt_bc_xprt;
-	}
 	xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries,
 			xprt_tcp_slot_table_entries);
 	if (IS_ERR(xprt))
-- 
cgit v1.2.3


From 86ea5e6b793d45fa7d2aa504ac3aefc813f0fd55 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@codeaurora.org>
Date: Sat, 29 Mar 2014 12:35:35 -0700
Subject: Input: pmic8xxx-keypad - migrate to DT

The driver is only supported on DT enabled platforms. Convert the
driver to DT so that it can probe properly.

Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../bindings/input/qcom,pm8xxx-keypad.txt          |  89 ++++++++++++
 drivers/input/keyboard/pmic8xxx-keypad.c           | 150 ++++++++++++---------
 include/linux/input/pmic8xxx-keypad.h              |  52 -------
 3 files changed, 175 insertions(+), 116 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/input/qcom,pm8xxx-keypad.txt
 delete mode 100644 include/linux/input/pmic8xxx-keypad.h

(limited to 'include/linux')

diff --git a/Documentation/devicetree/bindings/input/qcom,pm8xxx-keypad.txt b/Documentation/devicetree/bindings/input/qcom,pm8xxx-keypad.txt
new file mode 100644
index 000000000000..7d8cb92831d7
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/qcom,pm8xxx-keypad.txt
@@ -0,0 +1,89 @@
+Qualcomm PM8xxx PMIC Keypad
+
+PROPERTIES
+
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: must be one of:
+		    "qcom,pm8058-keypad"
+		    "qcom,pm8921-keypad"
+
+- reg:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: address of keypad control register
+
+- interrupts:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: the first interrupt specifies the key sense interrupt
+		    and the second interrupt specifies the key stuck interrupt.
+		    The format of the specifier is defined by the binding
+		    document describing the node's interrupt parent.
+
+- linux,keymap:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: the linux keymap. More information can be found in
+		    input/matrix-keymap.txt.
+
+- linux,keypad-no-autorepeat:
+	Usage: optional
+	Value type: <bool>
+	Definition: don't enable autorepeat feature.
+
+- linux,keypad-wakeup:
+	Usage: optional
+	Value type: <bool>
+	Definition: use any event on keypad as wakeup event.
+
+- keypad,num-rows:
+	Usage: required
+	Value type: <u32>
+	Definition: number of rows in the keymap. More information can be found
+		    in input/matrix-keymap.txt.
+
+- keypad,num-columns:
+	Usage: required
+	Value type: <u32>
+	Definition: number of columns in the keymap. More information can be
+		    found in input/matrix-keymap.txt.
+
+- debounce:
+	Usage: optional
+	Value type: <u32>
+	Definition: time in microseconds that key must be pressed or release
+		    for key sense interrupt to trigger.
+
+- scan-delay:
+	Usage: optional
+	Value type: <u32>
+	Definition: time in microseconds to pause between successive scans
+		    of the matrix array.
+
+- row-hold:
+	Usage: optional
+	Value type: <u32>
+	Definition: time in nanoseconds to pause between scans of each row in
+		    the matrix array.
+
+EXAMPLE
+
+	keypad@148 {
+		compatible = "qcom,pm8921-keypad";
+		reg = <0x148>;
+		interrupt-parent = <&pmicintc>;
+		interrupts = <74 1>, <75 1>;
+		linux,keymap = <
+			MATRIX_KEY(0, 0, KEY_VOLUMEUP)
+			MATRIX_KEY(0, 1, KEY_VOLUMEDOWN)
+			MATRIX_KEY(0, 2, KEY_CAMERA_FOCUS)
+			MATRIX_KEY(0, 3, KEY_CAMERA)
+			>;
+		keypad,num-rows = <1>;
+		keypad,num-columns = <5>;
+		debounce = <15>;
+		scan-delay = <32>;
+		row-hold = <91500>;
+	};
diff --git a/drivers/input/keyboard/pmic8xxx-keypad.c b/drivers/input/keyboard/pmic8xxx-keypad.c
index 0efd11e16b7e..80c6b0ef3fc8 100644
--- a/drivers/input/keyboard/pmic8xxx-keypad.c
+++ b/drivers/input/keyboard/pmic8xxx-keypad.c
@@ -20,8 +20,8 @@
 #include <linux/delay.h>
 #include <linux/mutex.h>
 #include <linux/regmap.h>
-
-#include <linux/input/pmic8xxx-keypad.h>
+#include <linux/of.h>
+#include <linux/input/matrix_keypad.h>
 
 #define PM8XXX_MAX_ROWS		18
 #define PM8XXX_MAX_COLS		8
@@ -84,7 +84,8 @@
 
 /**
  * struct pmic8xxx_kp - internal keypad data structure
- * @pdata - keypad platform data pointer
+ * @num_cols - number of columns of keypad
+ * @num_rows - number of row of keypad
  * @input - input device pointer for keypad
  * @regmap - regmap handle
  * @key_sense_irq - key press/release irq number
@@ -96,7 +97,8 @@
  * @ctrl_reg - control register value
  */
 struct pmic8xxx_kp {
-	const struct pm8xxx_keypad_platform_data *pdata;
+	unsigned int num_rows;
+	unsigned int num_cols;
 	struct input_dev *input;
 	struct regmap *regmap;
 	int key_sense_irq;
@@ -115,9 +117,9 @@ static u8 pmic8xxx_col_state(struct pmic8xxx_kp *kp, u8 col)
 {
 	/* all keys pressed on that particular row? */
 	if (col == 0x00)
-		return 1 << kp->pdata->num_cols;
+		return 1 << kp->num_cols;
 	else
-		return col & ((1 << kp->pdata->num_cols) - 1);
+		return col & ((1 << kp->num_cols) - 1);
 }
 
 /*
@@ -180,10 +182,10 @@ static int pmic8xxx_kp_read_matrix(struct pmic8xxx_kp *kp, u16 *new_state,
 	int rc, read_rows;
 	unsigned int scan_val;
 
-	if (kp->pdata->num_rows < PM8XXX_MIN_ROWS)
+	if (kp->num_rows < PM8XXX_MIN_ROWS)
 		read_rows = PM8XXX_MIN_ROWS;
 	else
-		read_rows = kp->pdata->num_rows;
+		read_rows = kp->num_rows;
 
 	pmic8xxx_chk_sync_read(kp);
 
@@ -227,13 +229,13 @@ static void __pmic8xxx_kp_scan_matrix(struct pmic8xxx_kp *kp, u16 *new_state,
 {
 	int row, col, code;
 
-	for (row = 0; row < kp->pdata->num_rows; row++) {
+	for (row = 0; row < kp->num_rows; row++) {
 		int bits_changed = new_state[row] ^ old_state[row];
 
 		if (!bits_changed)
 			continue;
 
-		for (col = 0; col < kp->pdata->num_cols; col++) {
+		for (col = 0; col < kp->num_cols; col++) {
 			if (!(bits_changed & (1 << col)))
 				continue;
 
@@ -259,9 +261,9 @@ static bool pmic8xxx_detect_ghost_keys(struct pmic8xxx_kp *kp, u16 *new_state)
 	u16 check, row_state;
 
 	check = 0;
-	for (row = 0; row < kp->pdata->num_rows; row++) {
+	for (row = 0; row < kp->num_rows; row++) {
 		row_state = (~new_state[row]) &
-				 ((1 << kp->pdata->num_cols) - 1);
+				 ((1 << kp->num_cols) - 1);
 
 		if (hweight16(row_state) > 1) {
 			if (found_first == -1)
@@ -369,8 +371,13 @@ static irqreturn_t pmic8xxx_kp_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int pmic8xxx_kpd_init(struct pmic8xxx_kp *kp)
+static int pmic8xxx_kpd_init(struct pmic8xxx_kp *kp,
+			     struct platform_device *pdev)
 {
+	const struct device_node *of_node = pdev->dev.of_node;
+	unsigned int scan_delay_ms;
+	unsigned int row_hold_ns;
+	unsigned int debounce_ms;
 	int bits, rc, cycles;
 	u8 scan_val = 0, ctrl_val = 0;
 	static const u8 row_bits[] = {
@@ -378,18 +385,18 @@ static int pmic8xxx_kpd_init(struct pmic8xxx_kp *kp)
 	};
 
 	/* Find column bits */
-	if (kp->pdata->num_cols < KEYP_CTRL_SCAN_COLS_MIN)
+	if (kp->num_cols < KEYP_CTRL_SCAN_COLS_MIN)
 		bits = 0;
 	else
-		bits = kp->pdata->num_cols - KEYP_CTRL_SCAN_COLS_MIN;
+		bits = kp->num_cols - KEYP_CTRL_SCAN_COLS_MIN;
 	ctrl_val = (bits & KEYP_CTRL_SCAN_COLS_BITS) <<
 		KEYP_CTRL_SCAN_COLS_SHIFT;
 
 	/* Find row bits */
-	if (kp->pdata->num_rows < KEYP_CTRL_SCAN_ROWS_MIN)
+	if (kp->num_rows < KEYP_CTRL_SCAN_ROWS_MIN)
 		bits = 0;
 	else
-		bits = row_bits[kp->pdata->num_rows - KEYP_CTRL_SCAN_ROWS_MIN];
+		bits = row_bits[kp->num_rows - KEYP_CTRL_SCAN_ROWS_MIN];
 
 	ctrl_val |= (bits << KEYP_CTRL_SCAN_ROWS_SHIFT);
 
@@ -399,15 +406,44 @@ static int pmic8xxx_kpd_init(struct pmic8xxx_kp *kp)
 		return rc;
 	}
 
-	bits = (kp->pdata->debounce_ms / 5) - 1;
+	if (of_property_read_u32(of_node, "scan-delay", &scan_delay_ms))
+		scan_delay_ms = MIN_SCAN_DELAY;
+
+	if (scan_delay_ms > MAX_SCAN_DELAY || scan_delay_ms < MIN_SCAN_DELAY ||
+	    !is_power_of_2(scan_delay_ms)) {
+		dev_err(&pdev->dev, "invalid keypad scan time supplied\n");
+		return -EINVAL;
+	}
+
+	if (of_property_read_u32(of_node, "row-hold", &row_hold_ns))
+		row_hold_ns = MIN_ROW_HOLD_DELAY;
+
+	if (row_hold_ns > MAX_ROW_HOLD_DELAY ||
+	    row_hold_ns < MIN_ROW_HOLD_DELAY ||
+	    ((row_hold_ns % MIN_ROW_HOLD_DELAY) != 0)) {
+		dev_err(&pdev->dev, "invalid keypad row hold time supplied\n");
+		return -EINVAL;
+	}
+
+	if (of_property_read_u32(of_node, "debounce", &debounce_ms))
+		debounce_ms = MIN_DEBOUNCE_TIME;
+
+	if (((debounce_ms % 5) != 0) ||
+	    debounce_ms > MAX_DEBOUNCE_TIME ||
+	    debounce_ms < MIN_DEBOUNCE_TIME) {
+		dev_err(&pdev->dev, "invalid debounce time supplied\n");
+		return -EINVAL;
+	}
+
+	bits = (debounce_ms / 5) - 1;
 
 	scan_val |= (bits << KEYP_SCAN_DBOUNCE_SHIFT);
 
-	bits = fls(kp->pdata->scan_delay_ms) - 1;
+	bits = fls(scan_delay_ms) - 1;
 	scan_val |= (bits << KEYP_SCAN_PAUSE_SHIFT);
 
 	/* Row hold time is a multiple of 32KHz cycles. */
-	cycles = (kp->pdata->row_hold_ns * KEYP_CLOCK_FREQ) / NSEC_PER_SEC;
+	cycles = (row_hold_ns * KEYP_CLOCK_FREQ) / NSEC_PER_SEC;
 
 	scan_val |= (cycles << KEYP_SCAN_ROW_HOLD_SHIFT);
 
@@ -471,50 +507,27 @@ static void pmic8xxx_kp_close(struct input_dev *dev)
  */
 static int pmic8xxx_kp_probe(struct platform_device *pdev)
 {
-	const struct pm8xxx_keypad_platform_data *pdata =
-					dev_get_platdata(&pdev->dev);
-	const struct matrix_keymap_data *keymap_data;
+	unsigned int rows, cols;
+	bool repeat;
+	bool wakeup;
 	struct pmic8xxx_kp *kp;
 	int rc;
 	unsigned int ctrl_val;
 
-	if (!pdata || !pdata->num_cols || !pdata->num_rows ||
-		pdata->num_cols > PM8XXX_MAX_COLS ||
-		pdata->num_rows > PM8XXX_MAX_ROWS ||
-		pdata->num_cols < PM8XXX_MIN_COLS) {
-		dev_err(&pdev->dev, "invalid platform data\n");
-		return -EINVAL;
-	}
-
-	if (!pdata->scan_delay_ms ||
-		pdata->scan_delay_ms > MAX_SCAN_DELAY ||
-		pdata->scan_delay_ms < MIN_SCAN_DELAY ||
-		!is_power_of_2(pdata->scan_delay_ms)) {
-		dev_err(&pdev->dev, "invalid keypad scan time supplied\n");
-		return -EINVAL;
-	}
-
-	if (!pdata->row_hold_ns ||
-		pdata->row_hold_ns > MAX_ROW_HOLD_DELAY ||
-		pdata->row_hold_ns < MIN_ROW_HOLD_DELAY ||
-		((pdata->row_hold_ns % MIN_ROW_HOLD_DELAY) != 0)) {
-		dev_err(&pdev->dev, "invalid keypad row hold time supplied\n");
-		return -EINVAL;
-	}
+	rc = matrix_keypad_parse_of_params(&pdev->dev, &rows, &cols);
+	if (rc)
+		return rc;
 
-	if (!pdata->debounce_ms ||
-		((pdata->debounce_ms % 5) != 0) ||
-		pdata->debounce_ms > MAX_DEBOUNCE_TIME ||
-		pdata->debounce_ms < MIN_DEBOUNCE_TIME) {
-		dev_err(&pdev->dev, "invalid debounce time supplied\n");
+	if (cols > PM8XXX_MAX_COLS || rows > PM8XXX_MAX_ROWS ||
+	    cols < PM8XXX_MIN_COLS) {
+		dev_err(&pdev->dev, "invalid platform data\n");
 		return -EINVAL;
 	}
 
-	keymap_data = pdata->keymap_data;
-	if (!keymap_data) {
-		dev_err(&pdev->dev, "no keymap data supplied\n");
-		return -EINVAL;
-	}
+	repeat = !of_property_read_bool(pdev->dev.of_node,
+					"linux,input-no-autorepeat");
+	wakeup = of_property_read_bool(pdev->dev.of_node,
+					"linux,keypad-wakeup");
 
 	kp = devm_kzalloc(&pdev->dev, sizeof(*kp), GFP_KERNEL);
 	if (!kp)
@@ -526,7 +539,8 @@ static int pmic8xxx_kp_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, kp);
 
-	kp->pdata	= pdata;
+	kp->num_rows	= rows;
+	kp->num_cols	= cols;
 	kp->dev		= &pdev->dev;
 
 	kp->input = devm_input_allocate_device(&pdev->dev);
@@ -547,8 +561,8 @@ static int pmic8xxx_kp_probe(struct platform_device *pdev)
 		return kp->key_stuck_irq;
 	}
 
-	kp->input->name = pdata->input_name ? : "PMIC8XXX keypad";
-	kp->input->phys = pdata->input_phys_device ? : "pmic8xxx_keypad/input0";
+	kp->input->name = "PMIC8XXX keypad";
+	kp->input->phys = "pmic8xxx_keypad/input0";
 
 	kp->input->id.bustype	= BUS_I2C;
 	kp->input->id.version	= 0x0001;
@@ -558,7 +572,7 @@ static int pmic8xxx_kp_probe(struct platform_device *pdev)
 	kp->input->open		= pmic8xxx_kp_open;
 	kp->input->close	= pmic8xxx_kp_close;
 
-	rc = matrix_keypad_build_keymap(keymap_data, NULL,
+	rc = matrix_keypad_build_keymap(NULL, NULL,
 					PM8XXX_MAX_ROWS, PM8XXX_MAX_COLS,
 					kp->keycodes, kp->input);
 	if (rc) {
@@ -566,7 +580,7 @@ static int pmic8xxx_kp_probe(struct platform_device *pdev)
 		return rc;
 	}
 
-	if (pdata->rep)
+	if (repeat)
 		__set_bit(EV_REP, kp->input->evbit);
 	input_set_capability(kp->input, EV_MSC, MSC_SCAN);
 
@@ -576,7 +590,7 @@ static int pmic8xxx_kp_probe(struct platform_device *pdev)
 	memset(kp->keystate, 0xff, sizeof(kp->keystate));
 	memset(kp->stuckstate, 0xff, sizeof(kp->stuckstate));
 
-	rc = pmic8xxx_kpd_init(kp);
+	rc = pmic8xxx_kpd_init(kp, pdev);
 	if (rc < 0) {
 		dev_err(&pdev->dev, "unable to initialize keypad controller\n");
 		return rc;
@@ -612,7 +626,7 @@ static int pmic8xxx_kp_probe(struct platform_device *pdev)
 		return rc;
 	}
 
-	device_init_wakeup(&pdev->dev, pdata->wakeup);
+	device_init_wakeup(&pdev->dev, wakeup);
 
 	return 0;
 }
@@ -662,12 +676,20 @@ static int pmic8xxx_kp_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(pm8xxx_kp_pm_ops,
 			 pmic8xxx_kp_suspend, pmic8xxx_kp_resume);
 
+static const struct of_device_id pm8xxx_match_table[] = {
+	{ .compatible = "qcom,pm8058-keypad" },
+	{ .compatible = "qcom,pm8921-keypad" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, pm8xxx_match_table);
+
 static struct platform_driver pmic8xxx_kp_driver = {
 	.probe		= pmic8xxx_kp_probe,
 	.driver		= {
-		.name = PM8XXX_KEYPAD_DEV_NAME,
+		.name = "pm8xxx-keypad",
 		.owner = THIS_MODULE,
 		.pm = &pm8xxx_kp_pm_ops,
+		.of_match_table = pm8xxx_match_table,
 	},
 };
 module_platform_driver(pmic8xxx_kp_driver);
diff --git a/include/linux/input/pmic8xxx-keypad.h b/include/linux/input/pmic8xxx-keypad.h
deleted file mode 100644
index 5f1e2f9ad959..000000000000
--- a/include/linux/input/pmic8xxx-keypad.h
+++ /dev/null
@@ -1,52 +0,0 @@
-/* Copyright (c) 2011, Code Aurora Forum. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#ifndef __PMIC8XXX_KEYPAD_H__
-#define __PMIC8XXX_KEYPAD_H__
-
-#include <linux/input/matrix_keypad.h>
-
-#define PM8XXX_KEYPAD_DEV_NAME     "pm8xxx-keypad"
-
-/**
- * struct pm8xxx_keypad_platform_data - platform data for keypad
- * @keymap_data - matrix keymap data
- * @input_name - input device name
- * @input_phys_device - input device name
- * @num_cols - number of columns of keypad
- * @num_rows - number of row of keypad
- * @debounce_ms - debounce period in milliseconds
- * @scan_delay_ms - scan delay in milliseconds
- * @row_hold_ns - row hold period in nanoseconds
- * @wakeup - configure keypad as wakeup
- * @rep - enable or disable key repeat bit
- */
-struct pm8xxx_keypad_platform_data {
-	const struct matrix_keymap_data *keymap_data;
-
-	const char *input_name;
-	const char *input_phys_device;
-
-	unsigned int num_cols;
-	unsigned int num_rows;
-	unsigned int rows_gpio_start;
-	unsigned int cols_gpio_start;
-
-	unsigned int debounce_ms;
-	unsigned int scan_delay_ms;
-	unsigned int row_hold_ns;
-
-	bool wakeup;
-	bool rep;
-};
-
-#endif /*__PMIC8XXX_KEYPAD_H__ */
-- 
cgit v1.2.3


From 57918dfadf717acf7d0488d5970c56a282d0aad1 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@codeaurora.org>
Date: Sat, 29 Mar 2014 12:39:38 -0700
Subject: Input: pmic8xxx-pwrkey - migrate to DT

The driver is only supported on DT enabled platforms. Convert the
driver to DT so that it can probe properly.

Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../bindings/input/qcom,pm8xxx-pwrkey.txt          | 46 ++++++++++++++++++++++
 drivers/input/misc/pmic8xxx-pwrkey.c               | 33 ++++++++++------
 include/linux/input/pmic8xxx-pwrkey.h              | 31 ---------------
 3 files changed, 66 insertions(+), 44 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/input/qcom,pm8xxx-pwrkey.txt
 delete mode 100644 include/linux/input/pmic8xxx-pwrkey.h

(limited to 'include/linux')

diff --git a/Documentation/devicetree/bindings/input/qcom,pm8xxx-pwrkey.txt b/Documentation/devicetree/bindings/input/qcom,pm8xxx-pwrkey.txt
new file mode 100644
index 000000000000..588536cc96ed
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/qcom,pm8xxx-pwrkey.txt
@@ -0,0 +1,46 @@
+Qualcomm PM8xxx PMIC Power Key
+
+PROPERTIES
+
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: must be one of:
+		    "qcom,pm8058-pwrkey"
+		    "qcom,pm8921-pwrkey"
+
+- reg:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: address of power key control register
+
+- interrupts:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: the first interrupt specifies the key release interrupt
+		    and the second interrupt specifies the key press interrupt.
+		    The format of the specifier is defined by the binding
+		    document describing the node's interrupt parent.
+
+- debounce:
+	Usage: optional
+	Value type: <u32>
+	Definition: time in microseconds that key must be pressed or release
+		    for state change interrupt to trigger.
+
+- pull-up:
+	Usage: optional
+	Value type: <empty>
+	Definition: presence of this property indicates that the KPDPWR_N pin
+		    should be configured for pull up.
+
+EXAMPLE
+
+	pwrkey@1c {
+		compatible = "qcom,pm8921-pwrkey";
+		reg = <0x1c>;
+		interrupt-parent = <&pmicintc>;
+		interrupts = <50 1>, <51 1>;
+		debounce = <15625>;
+		pull-up;
+	};
diff --git a/drivers/input/misc/pmic8xxx-pwrkey.c b/drivers/input/misc/pmic8xxx-pwrkey.c
index 0e1a05f95858..1cb8fda7a166 100644
--- a/drivers/input/misc/pmic8xxx-pwrkey.c
+++ b/drivers/input/misc/pmic8xxx-pwrkey.c
@@ -19,8 +19,7 @@
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <linux/log2.h>
-
-#include <linux/input/pmic8xxx-pwrkey.h>
+#include <linux/of.h>
 
 #define PON_CNTL_1 0x1C
 #define PON_CNTL_PULL_UP BIT(7)
@@ -89,15 +88,15 @@ static int pmic8xxx_pwrkey_probe(struct platform_device *pdev)
 	unsigned int pon_cntl;
 	struct regmap *regmap;
 	struct pmic8xxx_pwrkey *pwrkey;
-	const struct pm8xxx_pwrkey_platform_data *pdata =
-					dev_get_platdata(&pdev->dev);
+	u32 kpd_delay;
+	bool pull_up;
 
-	if (!pdata) {
-		dev_err(&pdev->dev, "power key platform data not supplied\n");
-		return -EINVAL;
-	}
+	if (of_property_read_u32(pdev->dev.of_node, "debounce", &kpd_delay))
+		kpd_delay = 0;
 
-	if (pdata->kpd_trigger_delay_us > 62500) {
+	pull_up = of_property_read_bool(pdev->dev.of_node, "pull-up");
+
+	if (kpd_delay > 62500) {
 		dev_err(&pdev->dev, "invalid power key trigger delay\n");
 		return -EINVAL;
 	}
@@ -125,7 +124,7 @@ static int pmic8xxx_pwrkey_probe(struct platform_device *pdev)
 	pwr->name = "pmic8xxx_pwrkey";
 	pwr->phys = "pmic8xxx_pwrkey/input0";
 
-	delay = (pdata->kpd_trigger_delay_us << 10) / USEC_PER_SEC;
+	delay = (kpd_delay << 10) / USEC_PER_SEC;
 	delay = 1 + ilog2(delay);
 
 	err = regmap_read(regmap, PON_CNTL_1, &pon_cntl);
@@ -136,7 +135,7 @@ static int pmic8xxx_pwrkey_probe(struct platform_device *pdev)
 
 	pon_cntl &= ~PON_CNTL_TRIG_DELAY_MASK;
 	pon_cntl |= (delay & PON_CNTL_TRIG_DELAY_MASK);
-	if (pdata->pull_up)
+	if (pull_up)
 		pon_cntl |= PON_CNTL_PULL_UP;
 	else
 		pon_cntl &= ~PON_CNTL_PULL_UP;
@@ -172,7 +171,7 @@ static int pmic8xxx_pwrkey_probe(struct platform_device *pdev)
 	}
 
 	platform_set_drvdata(pdev, pwrkey);
-	device_init_wakeup(&pdev->dev, pdata->wakeup);
+	device_init_wakeup(&pdev->dev, 1);
 
 	return 0;
 }
@@ -184,13 +183,21 @@ static int pmic8xxx_pwrkey_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id pm8xxx_pwr_key_id_table[] = {
+	{ .compatible = "qcom,pm8058-pwrkey" },
+	{ .compatible = "qcom,pm8921-pwrkey" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, pm8xxx_pwr_key_id_table);
+
 static struct platform_driver pmic8xxx_pwrkey_driver = {
 	.probe		= pmic8xxx_pwrkey_probe,
 	.remove		= pmic8xxx_pwrkey_remove,
 	.driver		= {
-		.name	= PM8XXX_PWRKEY_DEV_NAME,
+		.name	= "pm8xxx-pwrkey",
 		.owner	= THIS_MODULE,
 		.pm	= &pm8xxx_pwr_key_pm_ops,
+		.of_match_table = pm8xxx_pwr_key_id_table,
 	},
 };
 module_platform_driver(pmic8xxx_pwrkey_driver);
diff --git a/include/linux/input/pmic8xxx-pwrkey.h b/include/linux/input/pmic8xxx-pwrkey.h
deleted file mode 100644
index 6d2974e57109..000000000000
--- a/include/linux/input/pmic8xxx-pwrkey.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/* Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#ifndef __PMIC8XXX_PWRKEY_H__
-#define __PMIC8XXX_PWRKEY_H__
-
-#define PM8XXX_PWRKEY_DEV_NAME "pm8xxx-pwrkey"
-
-/**
- * struct pm8xxx_pwrkey_platform_data - platform data for pwrkey driver
- * @pull up:  power on register control for pull up/down configuration
- * @kpd_trigger_delay_us: time delay for power key state change interrupt
- *                  trigger.
- * @wakeup: configure power key as wakeup source
- */
-struct pm8xxx_pwrkey_platform_data  {
-	bool pull_up;
-	u32  kpd_trigger_delay_us;
-	u32  wakeup;
-};
-
-#endif /* __PMIC8XXX_PWRKEY_H__ */
-- 
cgit v1.2.3


From f8bbbfc3b97f4c7a6c7c23185e520b22bfc3a21d Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Fri, 28 Mar 2014 18:58:18 +0100
Subject: net: filter: add jited flag to indicate jit compiled filters

This patch adds a jited flag into sk_filter struct in order to indicate
whether a filter is currently jited or not. The size of sk_filter is
not being expanded as the 32 bit 'len' member allows upper bits to be
reused since a filter can currently only grow as large as BPF_MAXINSNS.

Therefore, there's enough room also for other in future needed flags to
reuse 'len' field if necessary. The jited flag also allows for having
alternative interpreter functions running as currently, we can only
detect jit compiled filters by testing fp->bpf_func to not equal the
address of sk_run_filter().

Joint work with Alexei Starovoitov.

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm/net/bpf_jit_32.c       | 3 ++-
 arch/powerpc/net/bpf_jit_comp.c | 3 ++-
 arch/s390/net/bpf_jit_comp.c    | 5 ++++-
 arch/sparc/net/bpf_jit_comp.c   | 3 ++-
 arch/x86/net/bpf_jit_comp.c     | 3 ++-
 include/linux/filter.h          | 3 ++-
 net/core/filter.c               | 1 +
 7 files changed, 15 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 7ddb9c83cdfc..6f879c319a9d 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -925,6 +925,7 @@ void bpf_jit_compile(struct sk_filter *fp)
 		bpf_jit_dump(fp->len, alloc_size, 2, ctx.target);
 
 	fp->bpf_func = (void *)ctx.target;
+	fp->jited = 1;
 out:
 	kfree(ctx.offsets);
 	return;
@@ -932,7 +933,7 @@ out:
 
 void bpf_jit_free(struct sk_filter *fp)
 {
-	if (fp->bpf_func != sk_run_filter)
+	if (fp->jited)
 		module_free(NULL, fp->bpf_func);
 	kfree(fp);
 }
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 4afad6c17d50..808ce1cae21a 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -689,6 +689,7 @@ void bpf_jit_compile(struct sk_filter *fp)
 		((u64 *)image)[0] = (u64)code_base;
 		((u64 *)image)[1] = local_paca->kernel_toc;
 		fp->bpf_func = (void *)image;
+		fp->jited = 1;
 	}
 out:
 	kfree(addrs);
@@ -697,7 +698,7 @@ out:
 
 void bpf_jit_free(struct sk_filter *fp)
 {
-	if (fp->bpf_func != sk_run_filter)
+	if (fp->jited)
 		module_free(NULL, fp->bpf_func);
 	kfree(fp);
 }
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 153f8f2cfd56..9c36dc398f90 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -877,6 +877,7 @@ void bpf_jit_compile(struct sk_filter *fp)
 	if (jit.start) {
 		set_memory_ro((unsigned long)header, header->pages);
 		fp->bpf_func = (void *) jit.start;
+		fp->jited = 1;
 	}
 out:
 	kfree(addrs);
@@ -887,10 +888,12 @@ void bpf_jit_free(struct sk_filter *fp)
 	unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK;
 	struct bpf_binary_header *header = (void *)addr;
 
-	if (fp->bpf_func == sk_run_filter)
+	if (!fp->jited)
 		goto free_filter;
+
 	set_memory_rw(addr, header->pages);
 	module_free(NULL, header);
+
 free_filter:
 	kfree(fp);
 }
diff --git a/arch/sparc/net/bpf_jit_comp.c b/arch/sparc/net/bpf_jit_comp.c
index d96d2a7c78ee..a82c6b2a9780 100644
--- a/arch/sparc/net/bpf_jit_comp.c
+++ b/arch/sparc/net/bpf_jit_comp.c
@@ -809,6 +809,7 @@ cond_branch:			f_offset = addrs[i + filter[i].jf];
 	if (image) {
 		bpf_flush_icache(image, image + proglen);
 		fp->bpf_func = (void *)image;
+		fp->jited = 1;
 	}
 out:
 	kfree(addrs);
@@ -817,7 +818,7 @@ out:
 
 void bpf_jit_free(struct sk_filter *fp)
 {
-	if (fp->bpf_func != sk_run_filter)
+	if (fp->jited)
 		module_free(NULL, fp->bpf_func);
 	kfree(fp);
 }
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 293c57b74edc..dc017735bb91 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -772,6 +772,7 @@ cond_branch:			f_offset = addrs[i + filter[i].jf] - addrs[i];
 		bpf_flush_icache(header, image + proglen);
 		set_memory_ro((unsigned long)header, header->pages);
 		fp->bpf_func = (void *)image;
+		fp->jited = 1;
 	}
 out:
 	kfree(addrs);
@@ -791,7 +792,7 @@ static void bpf_jit_free_deferred(struct work_struct *work)
 
 void bpf_jit_free(struct sk_filter *fp)
 {
-	if (fp->bpf_func != sk_run_filter) {
+	if (fp->jited) {
 		INIT_WORK(&fp->work, bpf_jit_free_deferred);
 		schedule_work(&fp->work);
 	} else {
diff --git a/include/linux/filter.h b/include/linux/filter.h
index e568c8ef896b..e65e23087367 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -25,7 +25,8 @@ struct sock;
 struct sk_filter
 {
 	atomic_t		refcnt;
-	unsigned int         	len;	/* Number of filter blocks */
+	u32			jited:1,	/* Is our filter JIT'ed? */
+				len:31;		/* Number of filter blocks */
 	struct rcu_head		rcu;
 	unsigned int		(*bpf_func)(const struct sk_buff *skb,
 					    const struct sock_filter *filter);
diff --git a/net/core/filter.c b/net/core/filter.c
index 65b75966e206..bb3c76458ca9 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -646,6 +646,7 @@ static int __sk_prepare_filter(struct sk_filter *fp)
 	int err;
 
 	fp->bpf_func = sk_run_filter;
+	fp->jited = 0;
 
 	err = sk_chk_filter(fp->insns, fp->len);
 	if (err)
-- 
cgit v1.2.3


From a3ea269b8bcdbb0c5fa2fd449a436e7987446975 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Fri, 28 Mar 2014 18:58:19 +0100
Subject: net: filter: keep original BPF program around

In order to open up the possibility to internally transform a BPF program
into an alternative and possibly non-trivial reversible representation, we
need to keep the original BPF program around, so that it can be passed back
to user space w/o the need of a complex decoder.

The reason for that use case resides in commit a8fc92778080 ("sk-filter:
Add ability to get socket filter program (v2)"), that is, the ability
to retrieve the currently attached BPF filter from a given socket used
mainly by the checkpoint-restore project, for example.

Therefore, we add two helpers sk_{store,release}_orig_filter for taking
care of that. In the sk_unattached_filter_create() case, there's no such
possibility/requirement to retrieve a loaded BPF program. Therefore, we
can spare us the work in that case.

This approach will simplify and slightly speed up both, sk_get_filter()
and sock_diag_put_filterinfo() handlers as we won't need to successively
decode filters anymore through sk_decode_filter(). As we still need
sk_decode_filter() later on, we're keeping it around.

Joint work with Alexei Starovoitov.

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/filter.h | 15 +++++++--
 net/core/filter.c      | 86 ++++++++++++++++++++++++++++++++++++++++----------
 net/core/sock_diag.c   | 23 ++++++--------
 3 files changed, 93 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index e65e23087367..93a9792e27bc 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -19,14 +19,19 @@ struct compat_sock_fprog {
 };
 #endif
 
+struct sock_fprog_kern {
+	u16			len;
+	struct sock_filter	*filter;
+};
+
 struct sk_buff;
 struct sock;
 
-struct sk_filter
-{
+struct sk_filter {
 	atomic_t		refcnt;
 	u32			jited:1,	/* Is our filter JIT'ed? */
 				len:31;		/* Number of filter blocks */
+	struct sock_fprog_kern	*orig_prog;	/* Original BPF program */
 	struct rcu_head		rcu;
 	unsigned int		(*bpf_func)(const struct sk_buff *skb,
 					    const struct sock_filter *filter);
@@ -42,14 +47,20 @@ static inline unsigned int sk_filter_size(unsigned int proglen)
 		   offsetof(struct sk_filter, insns[proglen]));
 }
 
+#define sk_filter_proglen(fprog)			\
+		(fprog->len * sizeof(fprog->filter[0]))
+
 extern int sk_filter(struct sock *sk, struct sk_buff *skb);
 extern unsigned int sk_run_filter(const struct sk_buff *skb,
 				  const struct sock_filter *filter);
+
 extern int sk_unattached_filter_create(struct sk_filter **pfp,
 				       struct sock_fprog *fprog);
 extern void sk_unattached_filter_destroy(struct sk_filter *fp);
+
 extern int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
 extern int sk_detach_filter(struct sock *sk);
+
 extern int sk_chk_filter(struct sock_filter *filter, unsigned int flen);
 extern int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned len);
 extern void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to);
diff --git a/net/core/filter.c b/net/core/filter.c
index bb3c76458ca9..9730e7fe4770 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -629,6 +629,37 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen)
 }
 EXPORT_SYMBOL(sk_chk_filter);
 
+static int sk_store_orig_filter(struct sk_filter *fp,
+				const struct sock_fprog *fprog)
+{
+	unsigned int fsize = sk_filter_proglen(fprog);
+	struct sock_fprog_kern *fkprog;
+
+	fp->orig_prog = kmalloc(sizeof(*fkprog), GFP_KERNEL);
+	if (!fp->orig_prog)
+		return -ENOMEM;
+
+	fkprog = fp->orig_prog;
+	fkprog->len = fprog->len;
+	fkprog->filter = kmemdup(fp->insns, fsize, GFP_KERNEL);
+	if (!fkprog->filter) {
+		kfree(fp->orig_prog);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void sk_release_orig_filter(struct sk_filter *fp)
+{
+	struct sock_fprog_kern *fprog = fp->orig_prog;
+
+	if (fprog) {
+		kfree(fprog->filter);
+		kfree(fprog);
+	}
+}
+
 /**
  * 	sk_filter_release_rcu - Release a socket filter by rcu_head
  *	@rcu: rcu_head that contains the sk_filter to free
@@ -637,6 +668,7 @@ void sk_filter_release_rcu(struct rcu_head *rcu)
 {
 	struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu);
 
+	sk_release_orig_filter(fp);
 	bpf_jit_free(fp);
 }
 EXPORT_SYMBOL(sk_filter_release_rcu);
@@ -669,8 +701,8 @@ static int __sk_prepare_filter(struct sk_filter *fp)
 int sk_unattached_filter_create(struct sk_filter **pfp,
 				struct sock_fprog *fprog)
 {
+	unsigned int fsize = sk_filter_proglen(fprog);
 	struct sk_filter *fp;
-	unsigned int fsize = sizeof(struct sock_filter) * fprog->len;
 	int err;
 
 	/* Make sure new filter is there and in the right amounts. */
@@ -680,10 +712,16 @@ int sk_unattached_filter_create(struct sk_filter **pfp,
 	fp = kmalloc(sk_filter_size(fprog->len), GFP_KERNEL);
 	if (!fp)
 		return -ENOMEM;
+
 	memcpy(fp->insns, fprog->filter, fsize);
 
 	atomic_set(&fp->refcnt, 1);
 	fp->len = fprog->len;
+	/* Since unattached filters are not copied back to user
+	 * space through sk_get_filter(), we do not need to hold
+	 * a copy here, and can spare us the work.
+	 */
+	fp->orig_prog = NULL;
 
 	err = __sk_prepare_filter(fp);
 	if (err)
@@ -716,7 +754,7 @@ EXPORT_SYMBOL_GPL(sk_unattached_filter_destroy);
 int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 {
 	struct sk_filter *fp, *old_fp;
-	unsigned int fsize = sizeof(struct sock_filter) * fprog->len;
+	unsigned int fsize = sk_filter_proglen(fprog);
 	unsigned int sk_fsize = sk_filter_size(fprog->len);
 	int err;
 
@@ -730,6 +768,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 	fp = sock_kmalloc(sk, sk_fsize, GFP_KERNEL);
 	if (!fp)
 		return -ENOMEM;
+
 	if (copy_from_user(fp->insns, fprog->filter, fsize)) {
 		sock_kfree_s(sk, fp, sk_fsize);
 		return -EFAULT;
@@ -738,6 +777,12 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 	atomic_set(&fp->refcnt, 1);
 	fp->len = fprog->len;
 
+	err = sk_store_orig_filter(fp, fprog);
+	if (err) {
+		sk_filter_uncharge(sk, fp);
+		return -ENOMEM;
+	}
+
 	err = __sk_prepare_filter(fp);
 	if (err) {
 		sk_filter_uncharge(sk, fp);
@@ -750,6 +795,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 
 	if (old_fp)
 		sk_filter_uncharge(sk, old_fp);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(sk_attach_filter);
@@ -769,6 +815,7 @@ int sk_detach_filter(struct sock *sk)
 		sk_filter_uncharge(sk, filter);
 		ret = 0;
 	}
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(sk_detach_filter);
@@ -851,34 +898,41 @@ void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to)
 	to->k = filt->k;
 }
 
-int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, unsigned int len)
+int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf,
+		  unsigned int len)
 {
+	struct sock_fprog_kern *fprog;
 	struct sk_filter *filter;
-	int i, ret;
+	int ret = 0;
 
 	lock_sock(sk);
 	filter = rcu_dereference_protected(sk->sk_filter,
-			sock_owned_by_user(sk));
-	ret = 0;
+					   sock_owned_by_user(sk));
 	if (!filter)
 		goto out;
-	ret = filter->len;
+
+	/* We're copying the filter that has been originally attached,
+	 * so no conversion/decode needed anymore.
+	 */
+	fprog = filter->orig_prog;
+
+	ret = fprog->len;
 	if (!len)
+		/* User space only enquires number of filter blocks. */
 		goto out;
+
 	ret = -EINVAL;
-	if (len < filter->len)
+	if (len < fprog->len)
 		goto out;
 
 	ret = -EFAULT;
-	for (i = 0; i < filter->len; i++) {
-		struct sock_filter fb;
-
-		sk_decode_filter(&filter->insns[i], &fb);
-		if (copy_to_user(&ubuf[i], &fb, sizeof(fb)))
-			goto out;
-	}
+	if (copy_to_user(ubuf, fprog->filter, sk_filter_proglen(fprog)))
+		goto out;
 
-	ret = filter->len;
+	/* Instead of bytes, the API requests to return the number
+	 * of filter blocks.
+	 */
+	ret = fprog->len;
 out:
 	release_sock(sk);
 	return ret;
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index a0e9cf6379de..d7af18859322 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -52,9 +52,10 @@ EXPORT_SYMBOL_GPL(sock_diag_put_meminfo);
 int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk,
 			     struct sk_buff *skb, int attrtype)
 {
-	struct nlattr *attr;
+	struct sock_fprog_kern *fprog;
 	struct sk_filter *filter;
-	unsigned int len;
+	struct nlattr *attr;
+	unsigned int flen;
 	int err = 0;
 
 	if (!ns_capable(user_ns, CAP_NET_ADMIN)) {
@@ -63,24 +64,20 @@ int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk,
 	}
 
 	rcu_read_lock();
-
 	filter = rcu_dereference(sk->sk_filter);
-	len = filter ? filter->len * sizeof(struct sock_filter) : 0;
+	if (!filter)
+		goto out;
 
-	attr = nla_reserve(skb, attrtype, len);
+	fprog = filter->orig_prog;
+	flen = sk_filter_proglen(fprog);
+
+	attr = nla_reserve(skb, attrtype, flen);
 	if (attr == NULL) {
 		err = -EMSGSIZE;
 		goto out;
 	}
 
-	if (filter) {
-		struct sock_filter *fb = (struct sock_filter *)nla_data(attr);
-		int i;
-
-		for (i = 0; i < filter->len; i++, fb++)
-			sk_decode_filter(&filter->insns[i], fb);
-	}
-
+	memcpy(nla_data(attr), fprog->filter, flen);
 out:
 	rcu_read_unlock();
 	return err;
-- 
cgit v1.2.3


From fbc907f0b1386c02e00516aa78a0fa6b0454fd0b Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Fri, 28 Mar 2014 18:58:20 +0100
Subject: net: filter: move filter accounting to filter core

This patch basically does two things, i) removes the extern keyword
from the include/linux/filter.h file to be more consistent with the
rest of Joe's changes, and ii) moves filter accounting into the filter
core framework.

Filter accounting mainly done through sk_filter_{un,}charge() take
care of the case when sockets are being cloned through sk_clone_lock()
so that removal of the filter on one socket won't result in eviction
as it's still referenced by the other.

These functions actually belong to net/core/filter.c and not
include/net/sock.h as we want to keep all that in a central place.
It's also not in fast-path so uninlining them is fine and even allows
us to get rd of sk_filter_release_rcu()'s EXPORT_SYMBOL and a forward
declaration.

Joint work with Alexei Starovoitov.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/filter.h | 30 +++++++++++++++++-------------
 include/net/sock.h     | 27 ---------------------------
 net/core/filter.c      | 27 +++++++++++++++++++++++++--
 3 files changed, 42 insertions(+), 42 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 93a9792e27bc..9bde3ed19fe6 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -50,28 +50,32 @@ static inline unsigned int sk_filter_size(unsigned int proglen)
 #define sk_filter_proglen(fprog)			\
 		(fprog->len * sizeof(fprog->filter[0]))
 
-extern int sk_filter(struct sock *sk, struct sk_buff *skb);
-extern unsigned int sk_run_filter(const struct sk_buff *skb,
-				  const struct sock_filter *filter);
+int sk_filter(struct sock *sk, struct sk_buff *skb);
+unsigned int sk_run_filter(const struct sk_buff *skb,
+			   const struct sock_filter *filter);
 
-extern int sk_unattached_filter_create(struct sk_filter **pfp,
-				       struct sock_fprog *fprog);
-extern void sk_unattached_filter_destroy(struct sk_filter *fp);
+int sk_unattached_filter_create(struct sk_filter **pfp,
+				struct sock_fprog *fprog);
+void sk_unattached_filter_destroy(struct sk_filter *fp);
 
-extern int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
-extern int sk_detach_filter(struct sock *sk);
+int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
+int sk_detach_filter(struct sock *sk);
 
-extern int sk_chk_filter(struct sock_filter *filter, unsigned int flen);
-extern int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned len);
-extern void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to);
+int sk_chk_filter(struct sock_filter *filter, unsigned int flen);
+int sk_get_filter(struct sock *sk, struct sock_filter __user *filter,
+		  unsigned int len);
+void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to);
+
+void sk_filter_charge(struct sock *sk, struct sk_filter *fp);
+void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp);
 
 #ifdef CONFIG_BPF_JIT
 #include <stdarg.h>
 #include <linux/linkage.h>
 #include <linux/printk.h>
 
-extern void bpf_jit_compile(struct sk_filter *fp);
-extern void bpf_jit_free(struct sk_filter *fp);
+void bpf_jit_compile(struct sk_filter *fp);
+void bpf_jit_free(struct sk_filter *fp);
 
 static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen,
 				u32 pass, void *image)
diff --git a/include/net/sock.h b/include/net/sock.h
index 8d7c431a0660..06a5668f05c9 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1621,33 +1621,6 @@ void sk_common_release(struct sock *sk);
 /* Initialise core socket variables */
 void sock_init_data(struct socket *sock, struct sock *sk);
 
-void sk_filter_release_rcu(struct rcu_head *rcu);
-
-/**
- *	sk_filter_release - release a socket filter
- *	@fp: filter to remove
- *
- *	Remove a filter from a socket and release its resources.
- */
-
-static inline void sk_filter_release(struct sk_filter *fp)
-{
-	if (atomic_dec_and_test(&fp->refcnt))
-		call_rcu(&fp->rcu, sk_filter_release_rcu);
-}
-
-static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
-{
-	atomic_sub(sk_filter_size(fp->len), &sk->sk_omem_alloc);
-	sk_filter_release(fp);
-}
-
-static inline void sk_filter_charge(struct sock *sk, struct sk_filter *fp)
-{
-	atomic_inc(&fp->refcnt);
-	atomic_add(sk_filter_size(fp->len), &sk->sk_omem_alloc);
-}
-
 /*
  * Socket reference counting postulates.
  *
diff --git a/net/core/filter.c b/net/core/filter.c
index 9730e7fe4770..5b3427aaeca5 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -664,14 +664,37 @@ static void sk_release_orig_filter(struct sk_filter *fp)
  * 	sk_filter_release_rcu - Release a socket filter by rcu_head
  *	@rcu: rcu_head that contains the sk_filter to free
  */
-void sk_filter_release_rcu(struct rcu_head *rcu)
+static void sk_filter_release_rcu(struct rcu_head *rcu)
 {
 	struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu);
 
 	sk_release_orig_filter(fp);
 	bpf_jit_free(fp);
 }
-EXPORT_SYMBOL(sk_filter_release_rcu);
+
+/**
+ *	sk_filter_release - release a socket filter
+ *	@fp: filter to remove
+ *
+ *	Remove a filter from a socket and release its resources.
+ */
+static void sk_filter_release(struct sk_filter *fp)
+{
+	if (atomic_dec_and_test(&fp->refcnt))
+		call_rcu(&fp->rcu, sk_filter_release_rcu);
+}
+
+void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
+{
+	atomic_sub(sk_filter_size(fp->len), &sk->sk_omem_alloc);
+	sk_filter_release(fp);
+}
+
+void sk_filter_charge(struct sock *sk, struct sk_filter *fp)
+{
+	atomic_inc(&fp->refcnt);
+	atomic_add(sk_filter_size(fp->len), &sk->sk_omem_alloc);
+}
 
 static int __sk_prepare_filter(struct sk_filter *fp)
 {
-- 
cgit v1.2.3


From e62d2df084e2849edffb206559725fa81bb569a8 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Fri, 28 Mar 2014 18:58:21 +0100
Subject: net: ptp: use sk_unattached_filter_create() for BPF

This patch migrates an open-coded sk_run_filter() implementation with
proper use of the BPF API, that is, sk_unattached_filter_create(). This
migration is needed, as we will be internally transforming the filter
to a different representation, and therefore needs to be decoupled.

It is okay to do so as skb_timestamping_init() is called during
initialization of the network stack in core initcall via sock_init().
This would effectively also allow for PTP filters to be jit compiled if
bpf_jit_enable is set.

For better readability, there are also some newlines introduced, also
ptp_classify.h is only in kernel space.

Joint work with Alexei Starovoitov.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Richard Cochran <richard.cochran@omicron.at>
Cc: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/ptp_classify.h |  4 ----
 net/core/timestamping.c      | 21 ++++++++++++++-------
 2 files changed, 14 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h
index 1dc420ba213a..3decfa4d3732 100644
--- a/include/linux/ptp_classify.h
+++ b/include/linux/ptp_classify.h
@@ -27,11 +27,7 @@
 #include <linux/if_vlan.h>
 #include <linux/ip.h>
 #include <linux/filter.h>
-#ifdef __KERNEL__
 #include <linux/in.h>
-#else
-#include <netinet/in.h>
-#endif
 
 #define PTP_CLASS_NONE  0x00 /* not a PTP event message */
 #define PTP_CLASS_V1    0x01 /* protocol version 1 */
diff --git a/net/core/timestamping.c b/net/core/timestamping.c
index 661b5a40ec10..e43d56acf803 100644
--- a/net/core/timestamping.c
+++ b/net/core/timestamping.c
@@ -23,16 +23,13 @@
 #include <linux/skbuff.h>
 #include <linux/export.h>
 
-static struct sock_filter ptp_filter[] = {
-	PTP_FILTER
-};
+static struct sk_filter *ptp_insns __read_mostly;
 
 static unsigned int classify(const struct sk_buff *skb)
 {
-	if (likely(skb->dev &&
-		   skb->dev->phydev &&
+	if (likely(skb->dev && skb->dev->phydev &&
 		   skb->dev->phydev->drv))
-		return sk_run_filter(skb, ptp_filter);
+		return SK_RUN_FILTER(ptp_insns, skb);
 	else
 		return PTP_CLASS_NONE;
 }
@@ -60,11 +57,13 @@ void skb_clone_tx_timestamp(struct sk_buff *skb)
 		if (likely(phydev->drv->txtstamp)) {
 			if (!atomic_inc_not_zero(&sk->sk_refcnt))
 				return;
+
 			clone = skb_clone(skb, GFP_ATOMIC);
 			if (!clone) {
 				sock_put(sk);
 				return;
 			}
+
 			clone->sk = sk;
 			phydev->drv->txtstamp(phydev, clone, type);
 		}
@@ -89,12 +88,15 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
 	}
 
 	*skb_hwtstamps(skb) = *hwtstamps;
+
 	serr = SKB_EXT_ERR(skb);
 	memset(serr, 0, sizeof(*serr));
 	serr->ee.ee_errno = ENOMSG;
 	serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
 	skb->sk = NULL;
+
 	err = sock_queue_err_skb(sk, skb);
+
 	sock_put(sk);
 	if (err)
 		kfree_skb(skb);
@@ -135,5 +137,10 @@ EXPORT_SYMBOL_GPL(skb_defer_rx_timestamp);
 
 void __init skb_timestamping_init(void)
 {
-	BUG_ON(sk_chk_filter(ptp_filter, ARRAY_SIZE(ptp_filter)));
+	static struct sock_filter ptp_filter[] = { PTP_FILTER };
+	struct sock_fprog ptp_prog = {
+		.len = ARRAY_SIZE(ptp_filter), .filter = ptp_filter,
+	};
+
+	BUG_ON(sk_unattached_filter_create(&ptp_insns, &ptp_prog));
 }
-- 
cgit v1.2.3


From 164d8c6665213c931645578310256da7b1259331 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Fri, 28 Mar 2014 18:58:22 +0100
Subject: net: ptp: do not reimplement PTP/BPF classifier

There are currently pch_gbe, cpts, and ixp4xx_eth drivers that open-code
and reimplement a BPF classifier for the PTP protocol. Since all of them
effectively do the very same thing and load the very same PTP/BPF filter,
we can just consolidate that code by introducing ptp_classify_raw() in
the time-stamping core framework which can be used in drivers.

As drivers get initialized after bootstrapping the core networking
subsystem, they can make use of ptp_insns wrapped through
ptp_classify_raw(), which allows to simplify and remove PTP classifier
setup code in drivers.

Joint work with Alexei Starovoitov.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Richard Cochran <richard.cochran@omicron.at>
Cc: Jiri Benc <jbenc@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c | 11 +----------
 drivers/net/ethernet/ti/cpts.c                       | 10 +---------
 drivers/net/ethernet/xscale/ixp4xx_eth.c             | 11 +----------
 include/linux/ptp_classify.h                         | 10 ++--------
 net/core/timestamping.c                              |  8 +++++++-
 5 files changed, 12 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 464e91058c81..73e66838cfef 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -120,10 +120,6 @@ static void pch_gbe_mdio_write(struct net_device *netdev, int addr, int reg,
 			       int data);
 static void pch_gbe_set_multi(struct net_device *netdev);
 
-static struct sock_filter ptp_filter[] = {
-	PTP_FILTER
-};
-
 static int pch_ptp_match(struct sk_buff *skb, u16 uid_hi, u32 uid_lo, u16 seqid)
 {
 	u8 *data = skb->data;
@@ -131,7 +127,7 @@ static int pch_ptp_match(struct sk_buff *skb, u16 uid_hi, u32 uid_lo, u16 seqid)
 	u16 *hi, *id;
 	u32 lo;
 
-	if (sk_run_filter(skb, ptp_filter) == PTP_CLASS_NONE)
+	if (ptp_classify_raw(skb) == PTP_CLASS_NONE)
 		return 0;
 
 	offset = ETH_HLEN + IPV4_HLEN(data) + UDP_HLEN;
@@ -2635,11 +2631,6 @@ static int pch_gbe_probe(struct pci_dev *pdev,
 
 	adapter->ptp_pdev = pci_get_bus_and_slot(adapter->pdev->bus->number,
 					       PCI_DEVFN(12, 4));
-	if (ptp_filter_init(ptp_filter, ARRAY_SIZE(ptp_filter))) {
-		dev_err(&pdev->dev, "Bad ptp filter\n");
-		ret = -EINVAL;
-		goto err_free_netdev;
-	}
 
 	netdev->netdev_ops = &pch_gbe_netdev_ops;
 	netdev->watchdog_timeo = PCH_GBE_WATCHDOG_PERIOD;
diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index 372cb192c5aa..a3bbf59eaafd 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -31,10 +31,6 @@
 
 #ifdef CONFIG_TI_CPTS
 
-static struct sock_filter ptp_filter[] = {
-	PTP_FILTER
-};
-
 #define cpts_read32(c, r)	__raw_readl(&c->reg->r)
 #define cpts_write32(c, v, r)	__raw_writel(v, &c->reg->r)
 
@@ -301,7 +297,7 @@ static u64 cpts_find_ts(struct cpts *cpts, struct sk_buff *skb, int ev_type)
 	u64 ns = 0;
 	struct cpts_event *event;
 	struct list_head *this, *next;
-	unsigned int class = sk_run_filter(skb, ptp_filter);
+	unsigned int class = ptp_classify_raw(skb);
 	unsigned long flags;
 	u16 seqid;
 	u8 mtype;
@@ -372,10 +368,6 @@ int cpts_register(struct device *dev, struct cpts *cpts,
 	int err, i;
 	unsigned long flags;
 
-	if (ptp_filter_init(ptp_filter, ARRAY_SIZE(ptp_filter))) {
-		pr_err("cpts: bad ptp filter\n");
-		return -EINVAL;
-	}
 	cpts->info = cpts_info;
 	cpts->clock = ptp_clock_register(&cpts->info, dev);
 	if (IS_ERR(cpts->clock)) {
diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c
index 25283f17d82f..f7e0f0f7c2e2 100644
--- a/drivers/net/ethernet/xscale/ixp4xx_eth.c
+++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c
@@ -256,10 +256,6 @@ static int ports_open;
 static struct port *npe_port_tab[MAX_NPES];
 static struct dma_pool *dma_pool;
 
-static struct sock_filter ptp_filter[] = {
-	PTP_FILTER
-};
-
 static int ixp_ptp_match(struct sk_buff *skb, u16 uid_hi, u32 uid_lo, u16 seqid)
 {
 	u8 *data = skb->data;
@@ -267,7 +263,7 @@ static int ixp_ptp_match(struct sk_buff *skb, u16 uid_hi, u32 uid_lo, u16 seqid)
 	u16 *hi, *id;
 	u32 lo;
 
-	if (sk_run_filter(skb, ptp_filter) != PTP_CLASS_V1_IPV4)
+	if (ptp_classify_raw(skb) != PTP_CLASS_V1_IPV4)
 		return 0;
 
 	offset = ETH_HLEN + IPV4_HLEN(data) + UDP_HLEN;
@@ -1413,11 +1409,6 @@ static int eth_init_one(struct platform_device *pdev)
 	char phy_id[MII_BUS_ID_SIZE + 3];
 	int err;
 
-	if (ptp_filter_init(ptp_filter, ARRAY_SIZE(ptp_filter))) {
-		pr_err("ixp4xx_eth: bad ptp filter\n");
-		return -EINVAL;
-	}
-
 	if (!(dev = alloc_etherdev(sizeof(struct port))))
 		return -ENOMEM;
 
diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h
index 3decfa4d3732..6d3b0a2ef9ce 100644
--- a/include/linux/ptp_classify.h
+++ b/include/linux/ptp_classify.h
@@ -80,14 +80,6 @@
 #define OP_RETA	(BPF_RET | BPF_A)
 #define OP_RETK	(BPF_RET | BPF_K)
 
-static inline int ptp_filter_init(struct sock_filter *f, int len)
-{
-	if (OP_LDH == f[0].code)
-		return sk_chk_filter(f, len);
-	else
-		return 0;
-}
-
 #define PTP_FILTER \
 	{OP_LDH,	0,   0, OFF_ETYPE		}, /*              */ \
 	{OP_JEQ,	0,  12, ETH_P_IP		}, /* f goto L20   */ \
@@ -133,4 +125,6 @@ static inline int ptp_filter_init(struct sock_filter *f, int len)
 	{OP_RETA,	0,   0, 0			}, /*              */ \
 /*L6x*/	{OP_RETK,	0,   0, PTP_CLASS_NONE		},
 
+unsigned int ptp_classify_raw(const struct sk_buff *skb);
+
 #endif
diff --git a/net/core/timestamping.c b/net/core/timestamping.c
index e43d56acf803..9ff26b3cc021 100644
--- a/net/core/timestamping.c
+++ b/net/core/timestamping.c
@@ -25,11 +25,17 @@
 
 static struct sk_filter *ptp_insns __read_mostly;
 
+unsigned int ptp_classify_raw(const struct sk_buff *skb)
+{
+	return SK_RUN_FILTER(ptp_insns, skb);
+}
+EXPORT_SYMBOL_GPL(ptp_classify_raw);
+
 static unsigned int classify(const struct sk_buff *skb)
 {
 	if (likely(skb->dev && skb->dev->phydev &&
 		   skb->dev->phydev->drv))
-		return SK_RUN_FILTER(ptp_insns, skb);
+		return ptp_classify_raw(skb);
 	else
 		return PTP_CLASS_NONE;
 }
-- 
cgit v1.2.3


From 77e0114ae9ae08685c503772a57af21d299c6701 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Fri, 28 Mar 2014 18:58:24 +0100
Subject: net: isdn: use sk_unattached_filter api

Similarly as in ppp, we need to migrate the ISDN/PPP code to make use
of the sk_unattached_filter api in order to decouple having direct
filter structure access. By using sk_unattached_filter_{create,destroy},
we can allow for the possibility to jit compile filters for faster
filter verdicts as well.

Joint work with Alexei Starovoitov.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Karsten Keil <isdn@linux-pingi.de>
Cc: isdn4linux@listserv.isdn4linux.de
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/i4l/isdn_ppp.c | 61 ++++++++++++++++++++++++++++++---------------
 include/linux/isdn_ppp.h    |  5 ++--
 2 files changed, 43 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/isdn/i4l/isdn_ppp.c b/drivers/isdn/i4l/isdn_ppp.c
index 38ceac5053a0..a5da511e3c9a 100644
--- a/drivers/isdn/i4l/isdn_ppp.c
+++ b/drivers/isdn/i4l/isdn_ppp.c
@@ -378,10 +378,15 @@ isdn_ppp_release(int min, struct file *file)
 	is->slcomp = NULL;
 #endif
 #ifdef CONFIG_IPPP_FILTER
-	kfree(is->pass_filter);
-	is->pass_filter = NULL;
-	kfree(is->active_filter);
-	is->active_filter = NULL;
+	if (is->pass_filter) {
+		sk_unattached_filter_destroy(is->pass_filter);
+		is->pass_filter = NULL;
+	}
+
+	if (is->active_filter) {
+		sk_unattached_filter_destroy(is->active_filter);
+		is->active_filter = NULL;
+	}
 #endif
 
 /* TODO: if this was the previous master: link the stuff to the new master */
@@ -629,25 +634,41 @@ isdn_ppp_ioctl(int min, struct file *file, unsigned int cmd, unsigned long arg)
 #ifdef CONFIG_IPPP_FILTER
 	case PPPIOCSPASS:
 	{
+		struct sock_fprog fprog;
 		struct sock_filter *code;
-		int len = get_filter(argp, &code);
+		int err, len = get_filter(argp, &code);
+
 		if (len < 0)
 			return len;
-		kfree(is->pass_filter);
-		is->pass_filter = code;
-		is->pass_len = len;
-		break;
+
+		fprog.len = len;
+		fprog.filter = code;
+
+		if (is->pass_filter)
+			sk_unattached_filter_destroy(is->pass_filter);
+		err = sk_unattached_filter_create(&is->pass_filter, &fprog);
+		kfree(code);
+
+		return err;
 	}
 	case PPPIOCSACTIVE:
 	{
+		struct sock_fprog fprog;
 		struct sock_filter *code;
-		int len = get_filter(argp, &code);
+		int err, len = get_filter(argp, &code);
+
 		if (len < 0)
 			return len;
-		kfree(is->active_filter);
-		is->active_filter = code;
-		is->active_len = len;
-		break;
+
+		fprog.len = len;
+		fprog.filter = code;
+
+		if (is->active_filter)
+			sk_unattached_filter_destroy(is->active_filter);
+		err = sk_unattached_filter_create(&is->active_filter, &fprog);
+		kfree(code);
+
+		return err;
 	}
 #endif /* CONFIG_IPPP_FILTER */
 	default:
@@ -1147,14 +1168,14 @@ isdn_ppp_push_higher(isdn_net_dev *net_dev, isdn_net_local *lp, struct sk_buff *
 	}
 
 	if (is->pass_filter
-	    && sk_run_filter(skb, is->pass_filter) == 0) {
+	    && SK_RUN_FILTER(is->pass_filter, skb) == 0) {
 		if (is->debug & 0x2)
 			printk(KERN_DEBUG "IPPP: inbound frame filtered.\n");
 		kfree_skb(skb);
 		return;
 	}
 	if (!(is->active_filter
-	      && sk_run_filter(skb, is->active_filter) == 0)) {
+	      && SK_RUN_FILTER(is->active_filter, skb) == 0)) {
 		if (is->debug & 0x2)
 			printk(KERN_DEBUG "IPPP: link-active filter: resetting huptimer.\n");
 		lp->huptimer = 0;
@@ -1293,14 +1314,14 @@ isdn_ppp_xmit(struct sk_buff *skb, struct net_device *netdev)
 	}
 
 	if (ipt->pass_filter
-	    && sk_run_filter(skb, ipt->pass_filter) == 0) {
+	    && SK_RUN_FILTER(ipt->pass_filter, skb) == 0) {
 		if (ipt->debug & 0x4)
 			printk(KERN_DEBUG "IPPP: outbound frame filtered.\n");
 		kfree_skb(skb);
 		goto unlock;
 	}
 	if (!(ipt->active_filter
-	      && sk_run_filter(skb, ipt->active_filter) == 0)) {
+	      && SK_RUN_FILTER(ipt->active_filter, skb) == 0)) {
 		if (ipt->debug & 0x4)
 			printk(KERN_DEBUG "IPPP: link-active filter: resetting huptimer.\n");
 		lp->huptimer = 0;
@@ -1490,9 +1511,9 @@ int isdn_ppp_autodial_filter(struct sk_buff *skb, isdn_net_local *lp)
 	}
 
 	drop |= is->pass_filter
-		&& sk_run_filter(skb, is->pass_filter) == 0;
+		&& SK_RUN_FILTER(is->pass_filter, skb) == 0;
 	drop |= is->active_filter
-		&& sk_run_filter(skb, is->active_filter) == 0;
+		&& SK_RUN_FILTER(is->active_filter, skb) == 0;
 
 	skb_push(skb, IPPP_MAX_HEADER - 4);
 	return drop;
diff --git a/include/linux/isdn_ppp.h b/include/linux/isdn_ppp.h
index d5f62bc5f4be..8e10f57f109f 100644
--- a/include/linux/isdn_ppp.h
+++ b/include/linux/isdn_ppp.h
@@ -180,9 +180,8 @@ struct ippp_struct {
   struct slcompress *slcomp;
 #endif
 #ifdef CONFIG_IPPP_FILTER
-  struct sock_filter *pass_filter;	/* filter for packets to pass */
-  struct sock_filter *active_filter;	/* filter for pkts to reset idle */
-  unsigned pass_len, active_len;
+  struct sk_filter *pass_filter;   /* filter for packets to pass */
+  struct sk_filter *active_filter; /* filter for pkts to reset idle */
 #endif
   unsigned long debug;
   struct isdn_ppp_compressor *compressor,*decompressor;
-- 
cgit v1.2.3


From bd4cf0ed331a275e9bf5a49e6d0fd55dffc551b8 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@plumgrid.com>
Date: Fri, 28 Mar 2014 18:58:25 +0100
Subject: net: filter: rework/optimize internal BPF interpreter's instruction
 set

This patch replaces/reworks the kernel-internal BPF interpreter with
an optimized BPF instruction set format that is modelled closer to
mimic native instruction sets and is designed to be JITed with one to
one mapping. Thus, the new interpreter is noticeably faster than the
current implementation of sk_run_filter(); mainly for two reasons:

1. Fall-through jumps:

  BPF jump instructions are forced to go either 'true' or 'false'
  branch which causes branch-miss penalty. The new BPF jump
  instructions have only one branch and fall-through otherwise,
  which fits the CPU branch predictor logic better. `perf stat`
  shows drastic difference for branch-misses between the old and
  new code.

2. Jump-threaded implementation of interpreter vs switch
   statement:

  Instead of single table-jump at the top of 'switch' statement,
  gcc will now generate multiple table-jump instructions, which
  helps CPU branch predictor logic.

Note that the verification of filters is still being done through
sk_chk_filter() in classical BPF format, so filters from user- or
kernel space are verified in the same way as we do now, and same
restrictions/constraints hold as well.

We reuse current BPF JIT compilers in a way that this upgrade would
even be fine as is, but nevertheless allows for a successive upgrade
of BPF JIT compilers to the new format.

The internal instruction set migration is being done after the
probing for JIT compilation, so in case JIT compilers are able to
create a native opcode image, we're going to use that, and in all
other cases we're doing a follow-up migration of the BPF program's
instruction set, so that it can be transparently run in the new
interpreter.

In short, the *internal* format extends BPF in the following way (more
details can be taken from the appended documentation):

  - Number of registers increase from 2 to 10
  - Register width increases from 32-bit to 64-bit
  - Conditional jt/jf targets replaced with jt/fall-through
  - Adds signed > and >= insns
  - 16 4-byte stack slots for register spill-fill replaced
    with up to 512 bytes of multi-use stack space
  - Introduction of bpf_call insn and register passing convention
    for zero overhead calls from/to other kernel functions
  - Adds arithmetic right shift and endianness conversion insns
  - Adds atomic_add insn
  - Old tax/txa insns are replaced with 'mov dst,src' insn

Performance of two BPF filters generated by libpcap resp. bpf_asm
was measured on x86_64, i386 and arm32 (other libpcap programs
have similar performance differences):

fprog #1 is taken from Documentation/networking/filter.txt:
tcpdump -i eth0 port 22 -dd

fprog #2 is taken from 'man tcpdump':
tcpdump -i eth0 'tcp port 22 and (((ip[2:2] - ((ip[0]&0xf)<<2)) -
   ((tcp[12]&0xf0)>>2)) != 0)' -dd

Raw performance data from BPF micro-benchmark: SK_RUN_FILTER on the
same SKB (cache-hit) or 10k SKBs (cache-miss); time in ns per call,
smaller is better:

--x86_64--
         fprog #1  fprog #1   fprog #2  fprog #2
         cache-hit cache-miss cache-hit cache-miss
old BPF      90       101        192       202
new BPF      31        71         47        97
old BPF jit  12        34         17        44
new BPF jit TBD

--i386--
         fprog #1  fprog #1   fprog #2  fprog #2
         cache-hit cache-miss cache-hit cache-miss
old BPF     107       136        227       252
new BPF      40       119         69       172

--arm32--
         fprog #1  fprog #1   fprog #2  fprog #2
         cache-hit cache-miss cache-hit cache-miss
old BPF     202       300        475       540
new BPF     180       270        330       470
old BPF jit  26       182         37       202
new BPF jit TBD

Thus, without changing any userland BPF filters, applications on
top of AF_PACKET (or other families) such as libpcap/tcpdump, cls_bpf
classifier, netfilter's xt_bpf, team driver's load-balancing mode,
and many more will have better interpreter filtering performance.

While we are replacing the internal BPF interpreter, we also need
to convert seccomp BPF in the same step to make use of the new
internal structure since it makes use of lower-level API details
without being further decoupled through higher-level calls like
sk_unattached_filter_{create,destroy}(), for example.

Just as for normal socket filtering, also seccomp BPF experiences
a time-to-verdict speedup:

05-sim-long_jumps.c of libseccomp was used as micro-benchmark:

  seccomp_rule_add_exact(ctx,...
  seccomp_rule_add_exact(ctx,...

  rc = seccomp_load(ctx);

  for (i = 0; i < 10000000; i++)
     syscall(199, 100);

'short filter' has 2 rules
'large filter' has 200 rules

'short filter' performance is slightly better on x86_64/i386/arm32
'large filter' is much faster on x86_64 and i386 and shows no
               difference on arm32

--x86_64-- short filter
old BPF: 2.7 sec
 39.12%  bench  libc-2.15.so       [.] syscall
  8.10%  bench  [kernel.kallsyms]  [k] sk_run_filter
  6.31%  bench  [kernel.kallsyms]  [k] system_call
  5.59%  bench  [kernel.kallsyms]  [k] trace_hardirqs_on_caller
  4.37%  bench  [kernel.kallsyms]  [k] trace_hardirqs_off_caller
  3.70%  bench  [kernel.kallsyms]  [k] __secure_computing
  3.67%  bench  [kernel.kallsyms]  [k] lock_is_held
  3.03%  bench  [kernel.kallsyms]  [k] seccomp_bpf_load
new BPF: 2.58 sec
 42.05%  bench  libc-2.15.so       [.] syscall
  6.91%  bench  [kernel.kallsyms]  [k] system_call
  6.25%  bench  [kernel.kallsyms]  [k] trace_hardirqs_on_caller
  6.07%  bench  [kernel.kallsyms]  [k] __secure_computing
  5.08%  bench  [kernel.kallsyms]  [k] sk_run_filter_int_seccomp

--arm32-- short filter
old BPF: 4.0 sec
 39.92%  bench  [kernel.kallsyms]  [k] vector_swi
 16.60%  bench  [kernel.kallsyms]  [k] sk_run_filter
 14.66%  bench  libc-2.17.so       [.] syscall
  5.42%  bench  [kernel.kallsyms]  [k] seccomp_bpf_load
  5.10%  bench  [kernel.kallsyms]  [k] __secure_computing
new BPF: 3.7 sec
 35.93%  bench  [kernel.kallsyms]  [k] vector_swi
 21.89%  bench  libc-2.17.so       [.] syscall
 13.45%  bench  [kernel.kallsyms]  [k] sk_run_filter_int_seccomp
  6.25%  bench  [kernel.kallsyms]  [k] __secure_computing
  3.96%  bench  [kernel.kallsyms]  [k] syscall_trace_exit

--x86_64-- large filter
old BPF: 8.6 seconds
    73.38%    bench  [kernel.kallsyms]  [k] sk_run_filter
    10.70%    bench  libc-2.15.so       [.] syscall
     5.09%    bench  [kernel.kallsyms]  [k] seccomp_bpf_load
     1.97%    bench  [kernel.kallsyms]  [k] system_call
new BPF: 5.7 seconds
    66.20%    bench  [kernel.kallsyms]  [k] sk_run_filter_int_seccomp
    16.75%    bench  libc-2.15.so       [.] syscall
     3.31%    bench  [kernel.kallsyms]  [k] system_call
     2.88%    bench  [kernel.kallsyms]  [k] __secure_computing

--i386-- large filter
old BPF: 5.4 sec
new BPF: 3.8 sec

--arm32-- large filter
old BPF: 13.5 sec
 73.88%  bench  [kernel.kallsyms]  [k] sk_run_filter
 10.29%  bench  [kernel.kallsyms]  [k] vector_swi
  6.46%  bench  libc-2.17.so       [.] syscall
  2.94%  bench  [kernel.kallsyms]  [k] seccomp_bpf_load
  1.19%  bench  [kernel.kallsyms]  [k] __secure_computing
  0.87%  bench  [kernel.kallsyms]  [k] sys_getuid
new BPF: 13.5 sec
 76.08%  bench  [kernel.kallsyms]  [k] sk_run_filter_int_seccomp
 10.98%  bench  [kernel.kallsyms]  [k] vector_swi
  5.87%  bench  libc-2.17.so       [.] syscall
  1.77%  bench  [kernel.kallsyms]  [k] __secure_computing
  0.93%  bench  [kernel.kallsyms]  [k] sys_getuid

BPF filters generated by seccomp are very branchy, so the new
internal BPF performance is better than the old one. Performance
gains will be even higher when BPF JIT is committed for the
new structure, which is planned in future work (as successive
JIT migrations).

BPF has also been stress-tested with trinity's BPF fuzzer.

Joint work with Daniel Borkmann.

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Cc: Hagen Paul Pfeifer <hagen@jauu.net>
Cc: Kees Cook <keescook@chromium.org>
Cc: Paul Moore <pmoore@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: H. Peter Anvin <hpa@linux.intel.com>
Cc: linux-kernel@vger.kernel.org
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/filter.h  |   74 ++-
 include/linux/seccomp.h |    1 -
 kernel/seccomp.c        |  119 ++--
 net/core/filter.c       | 1457 +++++++++++++++++++++++++++++++++++++----------
 4 files changed, 1279 insertions(+), 372 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 9bde3ed19fe6..262dcbb75ffe 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -9,13 +9,58 @@
 #include <linux/workqueue.h>
 #include <uapi/linux/filter.h>
 
-#ifdef CONFIG_COMPAT
-/*
- * A struct sock_filter is architecture independent.
+/* Internally used and optimized filter representation with extended
+ * instruction set based on top of classic BPF.
  */
+
+/* instruction classes */
+#define BPF_ALU64	0x07	/* alu mode in double word width */
+
+/* ld/ldx fields */
+#define BPF_DW		0x18	/* double word */
+#define BPF_XADD	0xc0	/* exclusive add */
+
+/* alu/jmp fields */
+#define BPF_MOV		0xb0	/* mov reg to reg */
+#define BPF_ARSH	0xc0	/* sign extending arithmetic shift right */
+
+/* change endianness of a register */
+#define BPF_END		0xd0	/* flags for endianness conversion: */
+#define BPF_TO_LE	0x00	/* convert to little-endian */
+#define BPF_TO_BE	0x08	/* convert to big-endian */
+#define BPF_FROM_LE	BPF_TO_LE
+#define BPF_FROM_BE	BPF_TO_BE
+
+#define BPF_JNE		0x50	/* jump != */
+#define BPF_JSGT	0x60	/* SGT is signed '>', GT in x86 */
+#define BPF_JSGE	0x70	/* SGE is signed '>=', GE in x86 */
+#define BPF_CALL	0x80	/* function call */
+#define BPF_EXIT	0x90	/* function return */
+
+/* BPF has 10 general purpose 64-bit registers and stack frame. */
+#define MAX_BPF_REG	11
+
+/* BPF program can access up to 512 bytes of stack space. */
+#define MAX_BPF_STACK	512
+
+/* Arg1, context and stack frame pointer register positions. */
+#define ARG1_REG	1
+#define CTX_REG		6
+#define FP_REG		10
+
+struct sock_filter_int {
+	__u8	code;		/* opcode */
+	__u8	a_reg:4;	/* dest register */
+	__u8	x_reg:4;	/* source register */
+	__s16	off;		/* signed offset */
+	__s32	imm;		/* signed immediate constant */
+};
+
+#ifdef CONFIG_COMPAT
+/* A struct sock_filter is architecture independent. */
 struct compat_sock_fprog {
 	u16		len;
-	compat_uptr_t	filter;		/* struct sock_filter * */
+	compat_uptr_t	filter;	/* struct sock_filter * */
 };
 #endif
 
@@ -26,6 +71,7 @@ struct sock_fprog_kern {
 
 struct sk_buff;
 struct sock;
+struct seccomp_data;
 
 struct sk_filter {
 	atomic_t		refcnt;
@@ -34,9 +80,10 @@ struct sk_filter {
 	struct sock_fprog_kern	*orig_prog;	/* Original BPF program */
 	struct rcu_head		rcu;
 	unsigned int		(*bpf_func)(const struct sk_buff *skb,
-					    const struct sock_filter *filter);
+					    const struct sock_filter_int *filter);
 	union {
-		struct sock_filter     	insns[0];
+		struct sock_filter	insns[0];
+		struct sock_filter_int	insnsi[0];
 		struct work_struct	work;
 	};
 };
@@ -50,9 +97,18 @@ static inline unsigned int sk_filter_size(unsigned int proglen)
 #define sk_filter_proglen(fprog)			\
 		(fprog->len * sizeof(fprog->filter[0]))
 
+#define SK_RUN_FILTER(filter, ctx)			\
+		(*filter->bpf_func)(ctx, filter->insnsi)
+
 int sk_filter(struct sock *sk, struct sk_buff *skb);
-unsigned int sk_run_filter(const struct sk_buff *skb,
-			   const struct sock_filter *filter);
+
+u32 sk_run_filter_int_seccomp(const struct seccomp_data *ctx,
+			      const struct sock_filter_int *insni);
+u32 sk_run_filter_int_skb(const struct sk_buff *ctx,
+			  const struct sock_filter_int *insni);
+
+int sk_convert_filter(struct sock_filter *prog, int len,
+		      struct sock_filter_int *new_prog, int *new_len);
 
 int sk_unattached_filter_create(struct sk_filter **pfp,
 				struct sock_fprog *fprog);
@@ -86,7 +142,6 @@ static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen,
 		print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET,
 			       16, 1, image, proglen, false);
 }
-#define SK_RUN_FILTER(FILTER, SKB) (*FILTER->bpf_func)(SKB, FILTER->insns)
 #else
 #include <linux/slab.h>
 static inline void bpf_jit_compile(struct sk_filter *fp)
@@ -96,7 +151,6 @@ static inline void bpf_jit_free(struct sk_filter *fp)
 {
 	kfree(fp);
 }
-#define SK_RUN_FILTER(FILTER, SKB) sk_run_filter(SKB, FILTER->insns)
 #endif
 
 static inline int bpf_tell_extensions(void)
diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 6f19cfd1840e..4054b0994071 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -76,7 +76,6 @@ static inline int seccomp_mode(struct seccomp *s)
 #ifdef CONFIG_SECCOMP_FILTER
 extern void put_seccomp_filter(struct task_struct *tsk);
 extern void get_seccomp_filter(struct task_struct *tsk);
-extern u32 seccomp_bpf_load(int off);
 #else  /* CONFIG_SECCOMP_FILTER */
 static inline void put_seccomp_filter(struct task_struct *tsk)
 {
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index b7a10048a32c..4f18e754c23e 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -55,60 +55,33 @@ struct seccomp_filter {
 	atomic_t usage;
 	struct seccomp_filter *prev;
 	unsigned short len;  /* Instruction count */
-	struct sock_filter insns[];
+	struct sock_filter_int insnsi[];
 };
 
 /* Limit any path through the tree to 256KB worth of instructions. */
 #define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter))
 
-/**
- * get_u32 - returns a u32 offset into data
- * @data: a unsigned 64 bit value
- * @index: 0 or 1 to return the first or second 32-bits
- *
- * This inline exists to hide the length of unsigned long.  If a 32-bit
- * unsigned long is passed in, it will be extended and the top 32-bits will be
- * 0. If it is a 64-bit unsigned long, then whatever data is resident will be
- * properly returned.
- *
+/*
  * Endianness is explicitly ignored and left for BPF program authors to manage
  * as per the specific architecture.
  */
-static inline u32 get_u32(u64 data, int index)
+static void populate_seccomp_data(struct seccomp_data *sd)
 {
-	return ((u32 *)&data)[index];
-}
+	struct task_struct *task = current;
+	struct pt_regs *regs = task_pt_regs(task);
 
-/* Helper for bpf_load below. */
-#define BPF_DATA(_name) offsetof(struct seccomp_data, _name)
-/**
- * bpf_load: checks and returns a pointer to the requested offset
- * @off: offset into struct seccomp_data to load from
- *
- * Returns the requested 32-bits of data.
- * seccomp_check_filter() should assure that @off is 32-bit aligned
- * and not out of bounds.  Failure to do so is a BUG.
- */
-u32 seccomp_bpf_load(int off)
-{
-	struct pt_regs *regs = task_pt_regs(current);
-	if (off == BPF_DATA(nr))
-		return syscall_get_nr(current, regs);
-	if (off == BPF_DATA(arch))
-		return syscall_get_arch(current, regs);
-	if (off >= BPF_DATA(args[0]) && off < BPF_DATA(args[6])) {
-		unsigned long value;
-		int arg = (off - BPF_DATA(args[0])) / sizeof(u64);
-		int index = !!(off % sizeof(u64));
-		syscall_get_arguments(current, regs, arg, 1, &value);
-		return get_u32(value, index);
-	}
-	if (off == BPF_DATA(instruction_pointer))
-		return get_u32(KSTK_EIP(current), 0);
-	if (off == BPF_DATA(instruction_pointer) + sizeof(u32))
-		return get_u32(KSTK_EIP(current), 1);
-	/* seccomp_check_filter should make this impossible. */
-	BUG();
+	sd->nr = syscall_get_nr(task, regs);
+	sd->arch = syscall_get_arch(task, regs);
+
+	/* Unroll syscall_get_args to help gcc on arm. */
+	syscall_get_arguments(task, regs, 0, 1, (unsigned long *) &sd->args[0]);
+	syscall_get_arguments(task, regs, 1, 1, (unsigned long *) &sd->args[1]);
+	syscall_get_arguments(task, regs, 2, 1, (unsigned long *) &sd->args[2]);
+	syscall_get_arguments(task, regs, 3, 1, (unsigned long *) &sd->args[3]);
+	syscall_get_arguments(task, regs, 4, 1, (unsigned long *) &sd->args[4]);
+	syscall_get_arguments(task, regs, 5, 1, (unsigned long *) &sd->args[5]);
+
+	sd->instruction_pointer = KSTK_EIP(task);
 }
 
 /**
@@ -133,17 +106,17 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
 
 		switch (code) {
 		case BPF_S_LD_W_ABS:
-			ftest->code = BPF_S_ANC_SECCOMP_LD_W;
+			ftest->code = BPF_LDX | BPF_W | BPF_ABS;
 			/* 32-bit aligned and not out of bounds. */
 			if (k >= sizeof(struct seccomp_data) || k & 3)
 				return -EINVAL;
 			continue;
 		case BPF_S_LD_W_LEN:
-			ftest->code = BPF_S_LD_IMM;
+			ftest->code = BPF_LD | BPF_IMM;
 			ftest->k = sizeof(struct seccomp_data);
 			continue;
 		case BPF_S_LDX_W_LEN:
-			ftest->code = BPF_S_LDX_IMM;
+			ftest->code = BPF_LDX | BPF_IMM;
 			ftest->k = sizeof(struct seccomp_data);
 			continue;
 		/* Explicitly include allowed calls. */
@@ -185,6 +158,7 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
 		case BPF_S_JMP_JGT_X:
 		case BPF_S_JMP_JSET_K:
 		case BPF_S_JMP_JSET_X:
+			sk_decode_filter(ftest, ftest);
 			continue;
 		default:
 			return -EINVAL;
@@ -202,18 +176,21 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen)
 static u32 seccomp_run_filters(int syscall)
 {
 	struct seccomp_filter *f;
+	struct seccomp_data sd;
 	u32 ret = SECCOMP_RET_ALLOW;
 
 	/* Ensure unexpected behavior doesn't result in failing open. */
 	if (WARN_ON(current->seccomp.filter == NULL))
 		return SECCOMP_RET_KILL;
 
+	populate_seccomp_data(&sd);
+
 	/*
 	 * All filters in the list are evaluated and the lowest BPF return
 	 * value always takes priority (ignoring the DATA).
 	 */
 	for (f = current->seccomp.filter; f; f = f->prev) {
-		u32 cur_ret = sk_run_filter(NULL, f->insns);
+		u32 cur_ret = sk_run_filter_int_seccomp(&sd, f->insnsi);
 		if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
 			ret = cur_ret;
 	}
@@ -231,6 +208,8 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
 	struct seccomp_filter *filter;
 	unsigned long fp_size = fprog->len * sizeof(struct sock_filter);
 	unsigned long total_insns = fprog->len;
+	struct sock_filter *fp;
+	int new_len;
 	long ret;
 
 	if (fprog->len == 0 || fprog->len > BPF_MAXINSNS)
@@ -252,28 +231,43 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
 				     CAP_SYS_ADMIN) != 0)
 		return -EACCES;
 
-	/* Allocate a new seccomp_filter */
-	filter = kzalloc(sizeof(struct seccomp_filter) + fp_size,
-			 GFP_KERNEL|__GFP_NOWARN);
-	if (!filter)
+	fp = kzalloc(fp_size, GFP_KERNEL|__GFP_NOWARN);
+	if (!fp)
 		return -ENOMEM;
-	atomic_set(&filter->usage, 1);
-	filter->len = fprog->len;
 
 	/* Copy the instructions from fprog. */
 	ret = -EFAULT;
-	if (copy_from_user(filter->insns, fprog->filter, fp_size))
-		goto fail;
+	if (copy_from_user(fp, fprog->filter, fp_size))
+		goto free_prog;
 
 	/* Check and rewrite the fprog via the skb checker */
-	ret = sk_chk_filter(filter->insns, filter->len);
+	ret = sk_chk_filter(fp, fprog->len);
 	if (ret)
-		goto fail;
+		goto free_prog;
 
 	/* Check and rewrite the fprog for seccomp use */
-	ret = seccomp_check_filter(filter->insns, filter->len);
+	ret = seccomp_check_filter(fp, fprog->len);
+	if (ret)
+		goto free_prog;
+
+	/* Convert 'sock_filter' insns to 'sock_filter_int' insns */
+	ret = sk_convert_filter(fp, fprog->len, NULL, &new_len);
+	if (ret)
+		goto free_prog;
+
+	/* Allocate a new seccomp_filter */
+	filter = kzalloc(sizeof(struct seccomp_filter) +
+			 sizeof(struct sock_filter_int) * new_len,
+			 GFP_KERNEL|__GFP_NOWARN);
+	if (!filter)
+		goto free_prog;
+
+	ret = sk_convert_filter(fp, fprog->len, filter->insnsi, &new_len);
 	if (ret)
-		goto fail;
+		goto free_filter;
+
+	atomic_set(&filter->usage, 1);
+	filter->len = new_len;
 
 	/*
 	 * If there is an existing filter, make it the prev and don't drop its
@@ -282,8 +276,11 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
 	filter->prev = current->seccomp.filter;
 	current->seccomp.filter = filter;
 	return 0;
-fail:
+
+free_filter:
 	kfree(filter);
+free_prog:
+	kfree(fp);
 	return ret;
 }
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 5b3427aaeca5..3733381190ec 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1,11 +1,16 @@
 /*
  * Linux Socket Filter - Kernel level socket filtering
  *
- * Author:
- *     Jay Schulist <jschlst@samba.org>
+ * Based on the design of the Berkeley Packet Filter. The new
+ * internal format has been designed by PLUMgrid:
  *
- * Based on the design of:
- *     - The Berkeley Packet Filter
+ *	Copyright (c) 2011 - 2014 PLUMgrid, http://plumgrid.com
+ *
+ * Authors:
+ *
+ *	Jay Schulist <jschlst@samba.org>
+ *	Alexei Starovoitov <ast@plumgrid.com>
+ *	Daniel Borkmann <dborkman@redhat.com>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -108,304 +113,1045 @@ int sk_filter(struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(sk_filter);
 
+/* Base function for offset calculation. Needs to go into .text section,
+ * therefore keeping it non-static as well; will also be used by JITs
+ * anyway later on, so do not let the compiler omit it.
+ */
+noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+	return 0;
+}
+
 /**
- *	sk_run_filter - run a filter on a socket
- *	@skb: buffer to run the filter on
+ *	__sk_run_filter - run a filter on a given context
+ *	@ctx: buffer to run the filter on
  *	@fentry: filter to apply
  *
- * Decode and apply filter instructions to the skb->data.
- * Return length to keep, 0 for none. @skb is the data we are
- * filtering, @filter is the array of filter instructions.
- * Because all jumps are guaranteed to be before last instruction,
- * and last instruction guaranteed to be a RET, we dont need to check
- * flen. (We used to pass to this function the length of filter)
+ * Decode and apply filter instructions to the skb->data. Return length to
+ * keep, 0 for none. @ctx is the data we are operating on, @filter is the
+ * array of filter instructions.
  */
-unsigned int sk_run_filter(const struct sk_buff *skb,
-			   const struct sock_filter *fentry)
+unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn)
 {
+	u64 stack[MAX_BPF_STACK / sizeof(u64)];
+	u64 regs[MAX_BPF_REG], tmp;
 	void *ptr;
-	u32 A = 0;			/* Accumulator */
-	u32 X = 0;			/* Index Register */
-	u32 mem[BPF_MEMWORDS];		/* Scratch Memory Store */
-	u32 tmp;
-	int k;
+	int off;
+
+#define K  insn->imm
+#define A  regs[insn->a_reg]
+#define X  regs[insn->x_reg]
+#define R0 regs[0]
+
+#define CONT	 ({insn++; goto select_insn; })
+#define CONT_JMP ({insn++; goto select_insn; })
+
+	static const void *jumptable[256] = {
+		[0 ... 255] = &&default_label,
+		/* Now overwrite non-defaults ... */
+#define DL(A, B, C)	[A|B|C] = &&A##_##B##_##C
+		DL(BPF_ALU, BPF_ADD, BPF_X),
+		DL(BPF_ALU, BPF_ADD, BPF_K),
+		DL(BPF_ALU, BPF_SUB, BPF_X),
+		DL(BPF_ALU, BPF_SUB, BPF_K),
+		DL(BPF_ALU, BPF_AND, BPF_X),
+		DL(BPF_ALU, BPF_AND, BPF_K),
+		DL(BPF_ALU, BPF_OR, BPF_X),
+		DL(BPF_ALU, BPF_OR, BPF_K),
+		DL(BPF_ALU, BPF_LSH, BPF_X),
+		DL(BPF_ALU, BPF_LSH, BPF_K),
+		DL(BPF_ALU, BPF_RSH, BPF_X),
+		DL(BPF_ALU, BPF_RSH, BPF_K),
+		DL(BPF_ALU, BPF_XOR, BPF_X),
+		DL(BPF_ALU, BPF_XOR, BPF_K),
+		DL(BPF_ALU, BPF_MUL, BPF_X),
+		DL(BPF_ALU, BPF_MUL, BPF_K),
+		DL(BPF_ALU, BPF_MOV, BPF_X),
+		DL(BPF_ALU, BPF_MOV, BPF_K),
+		DL(BPF_ALU, BPF_DIV, BPF_X),
+		DL(BPF_ALU, BPF_DIV, BPF_K),
+		DL(BPF_ALU, BPF_MOD, BPF_X),
+		DL(BPF_ALU, BPF_MOD, BPF_K),
+		DL(BPF_ALU, BPF_NEG, 0),
+		DL(BPF_ALU, BPF_END, BPF_TO_BE),
+		DL(BPF_ALU, BPF_END, BPF_TO_LE),
+		DL(BPF_ALU64, BPF_ADD, BPF_X),
+		DL(BPF_ALU64, BPF_ADD, BPF_K),
+		DL(BPF_ALU64, BPF_SUB, BPF_X),
+		DL(BPF_ALU64, BPF_SUB, BPF_K),
+		DL(BPF_ALU64, BPF_AND, BPF_X),
+		DL(BPF_ALU64, BPF_AND, BPF_K),
+		DL(BPF_ALU64, BPF_OR, BPF_X),
+		DL(BPF_ALU64, BPF_OR, BPF_K),
+		DL(BPF_ALU64, BPF_LSH, BPF_X),
+		DL(BPF_ALU64, BPF_LSH, BPF_K),
+		DL(BPF_ALU64, BPF_RSH, BPF_X),
+		DL(BPF_ALU64, BPF_RSH, BPF_K),
+		DL(BPF_ALU64, BPF_XOR, BPF_X),
+		DL(BPF_ALU64, BPF_XOR, BPF_K),
+		DL(BPF_ALU64, BPF_MUL, BPF_X),
+		DL(BPF_ALU64, BPF_MUL, BPF_K),
+		DL(BPF_ALU64, BPF_MOV, BPF_X),
+		DL(BPF_ALU64, BPF_MOV, BPF_K),
+		DL(BPF_ALU64, BPF_ARSH, BPF_X),
+		DL(BPF_ALU64, BPF_ARSH, BPF_K),
+		DL(BPF_ALU64, BPF_DIV, BPF_X),
+		DL(BPF_ALU64, BPF_DIV, BPF_K),
+		DL(BPF_ALU64, BPF_MOD, BPF_X),
+		DL(BPF_ALU64, BPF_MOD, BPF_K),
+		DL(BPF_ALU64, BPF_NEG, 0),
+		DL(BPF_JMP, BPF_CALL, 0),
+		DL(BPF_JMP, BPF_JA, 0),
+		DL(BPF_JMP, BPF_JEQ, BPF_X),
+		DL(BPF_JMP, BPF_JEQ, BPF_K),
+		DL(BPF_JMP, BPF_JNE, BPF_X),
+		DL(BPF_JMP, BPF_JNE, BPF_K),
+		DL(BPF_JMP, BPF_JGT, BPF_X),
+		DL(BPF_JMP, BPF_JGT, BPF_K),
+		DL(BPF_JMP, BPF_JGE, BPF_X),
+		DL(BPF_JMP, BPF_JGE, BPF_K),
+		DL(BPF_JMP, BPF_JSGT, BPF_X),
+		DL(BPF_JMP, BPF_JSGT, BPF_K),
+		DL(BPF_JMP, BPF_JSGE, BPF_X),
+		DL(BPF_JMP, BPF_JSGE, BPF_K),
+		DL(BPF_JMP, BPF_JSET, BPF_X),
+		DL(BPF_JMP, BPF_JSET, BPF_K),
+		DL(BPF_JMP, BPF_EXIT, 0),
+		DL(BPF_STX, BPF_MEM, BPF_B),
+		DL(BPF_STX, BPF_MEM, BPF_H),
+		DL(BPF_STX, BPF_MEM, BPF_W),
+		DL(BPF_STX, BPF_MEM, BPF_DW),
+		DL(BPF_STX, BPF_XADD, BPF_W),
+		DL(BPF_STX, BPF_XADD, BPF_DW),
+		DL(BPF_ST, BPF_MEM, BPF_B),
+		DL(BPF_ST, BPF_MEM, BPF_H),
+		DL(BPF_ST, BPF_MEM, BPF_W),
+		DL(BPF_ST, BPF_MEM, BPF_DW),
+		DL(BPF_LDX, BPF_MEM, BPF_B),
+		DL(BPF_LDX, BPF_MEM, BPF_H),
+		DL(BPF_LDX, BPF_MEM, BPF_W),
+		DL(BPF_LDX, BPF_MEM, BPF_DW),
+		DL(BPF_LD, BPF_ABS, BPF_W),
+		DL(BPF_LD, BPF_ABS, BPF_H),
+		DL(BPF_LD, BPF_ABS, BPF_B),
+		DL(BPF_LD, BPF_IND, BPF_W),
+		DL(BPF_LD, BPF_IND, BPF_H),
+		DL(BPF_LD, BPF_IND, BPF_B),
+#undef DL
+	};
 
-	/*
-	 * Process array of filter instructions.
-	 */
-	for (;; fentry++) {
-#if defined(CONFIG_X86_32)
-#define	K (fentry->k)
-#else
-		const u32 K = fentry->k;
-#endif
-
-		switch (fentry->code) {
-		case BPF_S_ALU_ADD_X:
-			A += X;
-			continue;
-		case BPF_S_ALU_ADD_K:
-			A += K;
-			continue;
-		case BPF_S_ALU_SUB_X:
-			A -= X;
-			continue;
-		case BPF_S_ALU_SUB_K:
-			A -= K;
-			continue;
-		case BPF_S_ALU_MUL_X:
-			A *= X;
-			continue;
-		case BPF_S_ALU_MUL_K:
-			A *= K;
-			continue;
-		case BPF_S_ALU_DIV_X:
-			if (X == 0)
-				return 0;
-			A /= X;
-			continue;
-		case BPF_S_ALU_DIV_K:
-			A /= K;
-			continue;
-		case BPF_S_ALU_MOD_X:
-			if (X == 0)
-				return 0;
-			A %= X;
-			continue;
-		case BPF_S_ALU_MOD_K:
-			A %= K;
-			continue;
-		case BPF_S_ALU_AND_X:
-			A &= X;
-			continue;
-		case BPF_S_ALU_AND_K:
-			A &= K;
-			continue;
-		case BPF_S_ALU_OR_X:
-			A |= X;
-			continue;
-		case BPF_S_ALU_OR_K:
-			A |= K;
-			continue;
-		case BPF_S_ANC_ALU_XOR_X:
-		case BPF_S_ALU_XOR_X:
-			A ^= X;
-			continue;
-		case BPF_S_ALU_XOR_K:
-			A ^= K;
-			continue;
-		case BPF_S_ALU_LSH_X:
-			A <<= X;
-			continue;
-		case BPF_S_ALU_LSH_K:
-			A <<= K;
-			continue;
-		case BPF_S_ALU_RSH_X:
-			A >>= X;
-			continue;
-		case BPF_S_ALU_RSH_K:
-			A >>= K;
-			continue;
-		case BPF_S_ALU_NEG:
-			A = -A;
-			continue;
-		case BPF_S_JMP_JA:
-			fentry += K;
-			continue;
-		case BPF_S_JMP_JGT_K:
-			fentry += (A > K) ? fentry->jt : fentry->jf;
-			continue;
-		case BPF_S_JMP_JGE_K:
-			fentry += (A >= K) ? fentry->jt : fentry->jf;
-			continue;
-		case BPF_S_JMP_JEQ_K:
-			fentry += (A == K) ? fentry->jt : fentry->jf;
-			continue;
-		case BPF_S_JMP_JSET_K:
-			fentry += (A & K) ? fentry->jt : fentry->jf;
-			continue;
-		case BPF_S_JMP_JGT_X:
-			fentry += (A > X) ? fentry->jt : fentry->jf;
-			continue;
-		case BPF_S_JMP_JGE_X:
-			fentry += (A >= X) ? fentry->jt : fentry->jf;
-			continue;
-		case BPF_S_JMP_JEQ_X:
-			fentry += (A == X) ? fentry->jt : fentry->jf;
-			continue;
-		case BPF_S_JMP_JSET_X:
-			fentry += (A & X) ? fentry->jt : fentry->jf;
-			continue;
-		case BPF_S_LD_W_ABS:
-			k = K;
-load_w:
-			ptr = load_pointer(skb, k, 4, &tmp);
-			if (ptr != NULL) {
-				A = get_unaligned_be32(ptr);
-				continue;
-			}
-			return 0;
-		case BPF_S_LD_H_ABS:
-			k = K;
-load_h:
-			ptr = load_pointer(skb, k, 2, &tmp);
-			if (ptr != NULL) {
-				A = get_unaligned_be16(ptr);
-				continue;
+	regs[FP_REG]  = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)];
+	regs[ARG1_REG] = (u64) (unsigned long) ctx;
+
+select_insn:
+	goto *jumptable[insn->code];
+
+	/* ALU */
+#define ALU(OPCODE, OP)			\
+	BPF_ALU64_##OPCODE##_BPF_X:	\
+		A = A OP X;		\
+		CONT;			\
+	BPF_ALU_##OPCODE##_BPF_X:	\
+		A = (u32) A OP (u32) X;	\
+		CONT;			\
+	BPF_ALU64_##OPCODE##_BPF_K:	\
+		A = A OP K;		\
+		CONT;			\
+	BPF_ALU_##OPCODE##_BPF_K:	\
+		A = (u32) A OP (u32) K;	\
+		CONT;
+
+	ALU(BPF_ADD,  +)
+	ALU(BPF_SUB,  -)
+	ALU(BPF_AND,  &)
+	ALU(BPF_OR,   |)
+	ALU(BPF_LSH, <<)
+	ALU(BPF_RSH, >>)
+	ALU(BPF_XOR,  ^)
+	ALU(BPF_MUL,  *)
+#undef ALU
+	BPF_ALU_BPF_NEG_0:
+		A = (u32) -A;
+		CONT;
+	BPF_ALU64_BPF_NEG_0:
+		A = -A;
+		CONT;
+	BPF_ALU_BPF_MOV_BPF_X:
+		A = (u32) X;
+		CONT;
+	BPF_ALU_BPF_MOV_BPF_K:
+		A = (u32) K;
+		CONT;
+	BPF_ALU64_BPF_MOV_BPF_X:
+		A = X;
+		CONT;
+	BPF_ALU64_BPF_MOV_BPF_K:
+		A = K;
+		CONT;
+	BPF_ALU64_BPF_ARSH_BPF_X:
+		(*(s64 *) &A) >>= X;
+		CONT;
+	BPF_ALU64_BPF_ARSH_BPF_K:
+		(*(s64 *) &A) >>= K;
+		CONT;
+	BPF_ALU64_BPF_MOD_BPF_X:
+		tmp = A;
+		if (X)
+			A = do_div(tmp, X);
+		CONT;
+	BPF_ALU_BPF_MOD_BPF_X:
+		tmp = (u32) A;
+		if (X)
+			A = do_div(tmp, (u32) X);
+		CONT;
+	BPF_ALU64_BPF_MOD_BPF_K:
+		tmp = A;
+		if (K)
+			A = do_div(tmp, K);
+		CONT;
+	BPF_ALU_BPF_MOD_BPF_K:
+		tmp = (u32) A;
+		if (K)
+			A = do_div(tmp, (u32) K);
+		CONT;
+	BPF_ALU64_BPF_DIV_BPF_X:
+		if (X)
+			do_div(A, X);
+		CONT;
+	BPF_ALU_BPF_DIV_BPF_X:
+		tmp = (u32) A;
+		if (X)
+			do_div(tmp, (u32) X);
+		A = (u32) tmp;
+		CONT;
+	BPF_ALU64_BPF_DIV_BPF_K:
+		if (K)
+			do_div(A, K);
+		CONT;
+	BPF_ALU_BPF_DIV_BPF_K:
+		tmp = (u32) A;
+		if (K)
+			do_div(tmp, (u32) K);
+		A = (u32) tmp;
+		CONT;
+	BPF_ALU_BPF_END_BPF_TO_BE:
+		switch (K) {
+		case 16:
+			A = (__force u16) cpu_to_be16(A);
+			break;
+		case 32:
+			A = (__force u32) cpu_to_be32(A);
+			break;
+		case 64:
+			A = (__force u64) cpu_to_be64(A);
+			break;
+		}
+		CONT;
+	BPF_ALU_BPF_END_BPF_TO_LE:
+		switch (K) {
+		case 16:
+			A = (__force u16) cpu_to_le16(A);
+			break;
+		case 32:
+			A = (__force u32) cpu_to_le32(A);
+			break;
+		case 64:
+			A = (__force u64) cpu_to_le64(A);
+			break;
+		}
+		CONT;
+
+	/* CALL */
+	BPF_JMP_BPF_CALL_0:
+		/* Function call scratches R1-R5 registers, preserves R6-R9,
+		 * and stores return value into R0.
+		 */
+		R0 = (__bpf_call_base + insn->imm)(regs[1], regs[2], regs[3],
+						   regs[4], regs[5]);
+		CONT;
+
+	/* JMP */
+	BPF_JMP_BPF_JA_0:
+		insn += insn->off;
+		CONT;
+	BPF_JMP_BPF_JEQ_BPF_X:
+		if (A == X) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	BPF_JMP_BPF_JEQ_BPF_K:
+		if (A == K) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	BPF_JMP_BPF_JNE_BPF_X:
+		if (A != X) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	BPF_JMP_BPF_JNE_BPF_K:
+		if (A != K) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	BPF_JMP_BPF_JGT_BPF_X:
+		if (A > X) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	BPF_JMP_BPF_JGT_BPF_K:
+		if (A > K) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	BPF_JMP_BPF_JGE_BPF_X:
+		if (A >= X) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	BPF_JMP_BPF_JGE_BPF_K:
+		if (A >= K) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	BPF_JMP_BPF_JSGT_BPF_X:
+		if (((s64)A) > ((s64)X)) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	BPF_JMP_BPF_JSGT_BPF_K:
+		if (((s64)A) > ((s64)K)) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	BPF_JMP_BPF_JSGE_BPF_X:
+		if (((s64)A) >= ((s64)X)) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	BPF_JMP_BPF_JSGE_BPF_K:
+		if (((s64)A) >= ((s64)K)) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	BPF_JMP_BPF_JSET_BPF_X:
+		if (A & X) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	BPF_JMP_BPF_JSET_BPF_K:
+		if (A & K) {
+			insn += insn->off;
+			CONT_JMP;
+		}
+		CONT;
+	BPF_JMP_BPF_EXIT_0:
+		return R0;
+
+	/* STX and ST and LDX*/
+#define LDST(SIZEOP, SIZE)					\
+	BPF_STX_BPF_MEM_##SIZEOP:				\
+		*(SIZE *)(unsigned long) (A + insn->off) = X;	\
+		CONT;						\
+	BPF_ST_BPF_MEM_##SIZEOP:				\
+		*(SIZE *)(unsigned long) (A + insn->off) = K;	\
+		CONT;						\
+	BPF_LDX_BPF_MEM_##SIZEOP:				\
+		A = *(SIZE *)(unsigned long) (X + insn->off);	\
+		CONT;
+
+	LDST(BPF_B,   u8)
+	LDST(BPF_H,  u16)
+	LDST(BPF_W,  u32)
+	LDST(BPF_DW, u64)
+#undef LDST
+	BPF_STX_BPF_XADD_BPF_W: /* lock xadd *(u32 *)(A + insn->off) += X */
+		atomic_add((u32) X, (atomic_t *)(unsigned long)
+			   (A + insn->off));
+		CONT;
+	BPF_STX_BPF_XADD_BPF_DW: /* lock xadd *(u64 *)(A + insn->off) += X */
+		atomic64_add((u64) X, (atomic64_t *)(unsigned long)
+			     (A + insn->off));
+		CONT;
+	BPF_LD_BPF_ABS_BPF_W: /* R0 = ntohl(*(u32 *) (skb->data + K)) */
+		off = K;
+load_word:
+		/* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are only
+		 * appearing in the programs where ctx == skb. All programs
+		 * keep 'ctx' in regs[CTX_REG] == R6, sk_convert_filter()
+		 * saves it in R6, internal BPF verifier will check that
+		 * R6 == ctx.
+		 *
+		 * BPF_ABS and BPF_IND are wrappers of function calls, so
+		 * they scratch R1-R5 registers, preserve R6-R9, and store
+		 * return value into R0.
+		 *
+		 * Implicit input:
+		 *   ctx
+		 *
+		 * Explicit input:
+		 *   X == any register
+		 *   K == 32-bit immediate
+		 *
+		 * Output:
+		 *   R0 - 8/16/32-bit skb data converted to cpu endianness
+		 */
+		ptr = load_pointer((struct sk_buff *) ctx, off, 4, &tmp);
+		if (likely(ptr != NULL)) {
+			R0 = get_unaligned_be32(ptr);
+			CONT;
+		}
+		return 0;
+	BPF_LD_BPF_ABS_BPF_H: /* R0 = ntohs(*(u16 *) (skb->data + K)) */
+		off = K;
+load_half:
+		ptr = load_pointer((struct sk_buff *) ctx, off, 2, &tmp);
+		if (likely(ptr != NULL)) {
+			R0 = get_unaligned_be16(ptr);
+			CONT;
+		}
+		return 0;
+	BPF_LD_BPF_ABS_BPF_B: /* R0 = *(u8 *) (ctx + K) */
+		off = K;
+load_byte:
+		ptr = load_pointer((struct sk_buff *) ctx, off, 1, &tmp);
+		if (likely(ptr != NULL)) {
+			R0 = *(u8 *)ptr;
+			CONT;
+		}
+		return 0;
+	BPF_LD_BPF_IND_BPF_W: /* R0 = ntohl(*(u32 *) (skb->data + X + K)) */
+		off = K + X;
+		goto load_word;
+	BPF_LD_BPF_IND_BPF_H: /* R0 = ntohs(*(u16 *) (skb->data + X + K)) */
+		off = K + X;
+		goto load_half;
+	BPF_LD_BPF_IND_BPF_B: /* R0 = *(u8 *) (skb->data + X + K) */
+		off = K + X;
+		goto load_byte;
+
+	default_label:
+		/* If we ever reach this, we have a bug somewhere. */
+		WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code);
+		return 0;
+#undef CONT_JMP
+#undef CONT
+
+#undef R0
+#undef X
+#undef A
+#undef K
+}
+
+u32 sk_run_filter_int_seccomp(const struct seccomp_data *ctx,
+			      const struct sock_filter_int *insni)
+    __attribute__ ((alias ("__sk_run_filter")));
+
+u32 sk_run_filter_int_skb(const struct sk_buff *ctx,
+			  const struct sock_filter_int *insni)
+    __attribute__ ((alias ("__sk_run_filter")));
+EXPORT_SYMBOL_GPL(sk_run_filter_int_skb);
+
+/* Helper to find the offset of pkt_type in sk_buff structure. We want
+ * to make sure its still a 3bit field starting at a byte boundary;
+ * taken from arch/x86/net/bpf_jit_comp.c.
+ */
+#define PKT_TYPE_MAX	7
+static unsigned int pkt_type_offset(void)
+{
+	struct sk_buff skb_probe = { .pkt_type = ~0, };
+	u8 *ct = (u8 *) &skb_probe;
+	unsigned int off;
+
+	for (off = 0; off < sizeof(struct sk_buff); off++) {
+		if (ct[off] == PKT_TYPE_MAX)
+			return off;
+	}
+
+	pr_err_once("Please fix %s, as pkt_type couldn't be found!\n", __func__);
+	return -1;
+}
+
+static u64 __skb_get_pay_offset(u64 ctx, u64 A, u64 X, u64 r4, u64 r5)
+{
+	struct sk_buff *skb = (struct sk_buff *)(long) ctx;
+
+	return __skb_get_poff(skb);
+}
+
+static u64 __skb_get_nlattr(u64 ctx, u64 A, u64 X, u64 r4, u64 r5)
+{
+	struct sk_buff *skb = (struct sk_buff *)(long) ctx;
+	struct nlattr *nla;
+
+	if (skb_is_nonlinear(skb))
+		return 0;
+
+	if (A > skb->len - sizeof(struct nlattr))
+		return 0;
+
+	nla = nla_find((struct nlattr *) &skb->data[A], skb->len - A, X);
+	if (nla)
+		return (void *) nla - (void *) skb->data;
+
+	return 0;
+}
+
+static u64 __skb_get_nlattr_nest(u64 ctx, u64 A, u64 X, u64 r4, u64 r5)
+{
+	struct sk_buff *skb = (struct sk_buff *)(long) ctx;
+	struct nlattr *nla;
+
+	if (skb_is_nonlinear(skb))
+		return 0;
+
+	if (A > skb->len - sizeof(struct nlattr))
+		return 0;
+
+	nla = (struct nlattr *) &skb->data[A];
+	if (nla->nla_len > A - skb->len)
+		return 0;
+
+	nla = nla_find_nested(nla, X);
+	if (nla)
+		return (void *) nla - (void *) skb->data;
+
+	return 0;
+}
+
+static u64 __get_raw_cpu_id(u64 ctx, u64 A, u64 X, u64 r4, u64 r5)
+{
+	return raw_smp_processor_id();
+}
+
+/* Register mappings for user programs. */
+#define A_REG		0
+#define X_REG		7
+#define TMP_REG		8
+#define ARG2_REG	2
+#define ARG3_REG	3
+
+static bool convert_bpf_extensions(struct sock_filter *fp,
+				   struct sock_filter_int **insnp)
+{
+	struct sock_filter_int *insn = *insnp;
+
+	switch (fp->k) {
+	case SKF_AD_OFF + SKF_AD_PROTOCOL:
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2);
+
+		insn->code = BPF_LDX | BPF_MEM | BPF_H;
+		insn->a_reg = A_REG;
+		insn->x_reg = CTX_REG;
+		insn->off = offsetof(struct sk_buff, protocol);
+		insn++;
+
+		/* A = ntohs(A) [emitting a nop or swap16] */
+		insn->code = BPF_ALU | BPF_END | BPF_FROM_BE;
+		insn->a_reg = A_REG;
+		insn->imm = 16;
+		break;
+
+	case SKF_AD_OFF + SKF_AD_PKTTYPE:
+		insn->code = BPF_LDX | BPF_MEM | BPF_B;
+		insn->a_reg = A_REG;
+		insn->x_reg = CTX_REG;
+		insn->off = pkt_type_offset();
+		if (insn->off < 0)
+			return false;
+		insn++;
+
+		insn->code = BPF_ALU | BPF_AND | BPF_K;
+		insn->a_reg = A_REG;
+		insn->imm = PKT_TYPE_MAX;
+		break;
+
+	case SKF_AD_OFF + SKF_AD_IFINDEX:
+	case SKF_AD_OFF + SKF_AD_HATYPE:
+		if (FIELD_SIZEOF(struct sk_buff, dev) == 8)
+			insn->code = BPF_LDX | BPF_MEM | BPF_DW;
+		else
+			insn->code = BPF_LDX | BPF_MEM | BPF_W;
+		insn->a_reg = TMP_REG;
+		insn->x_reg = CTX_REG;
+		insn->off = offsetof(struct sk_buff, dev);
+		insn++;
+
+		insn->code = BPF_JMP | BPF_JNE | BPF_K;
+		insn->a_reg = TMP_REG;
+		insn->imm = 0;
+		insn->off = 1;
+		insn++;
+
+		insn->code = BPF_JMP | BPF_EXIT;
+		insn++;
+
+		BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4);
+		BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2);
+
+		insn->a_reg = A_REG;
+		insn->x_reg = TMP_REG;
+
+		if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX) {
+			insn->code = BPF_LDX | BPF_MEM | BPF_W;
+			insn->off = offsetof(struct net_device, ifindex);
+		} else {
+			insn->code = BPF_LDX | BPF_MEM | BPF_H;
+			insn->off = offsetof(struct net_device, type);
+		}
+		break;
+
+	case SKF_AD_OFF + SKF_AD_MARK:
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4);
+
+		insn->code = BPF_LDX | BPF_MEM | BPF_W;
+		insn->a_reg = A_REG;
+		insn->x_reg = CTX_REG;
+		insn->off = offsetof(struct sk_buff, mark);
+		break;
+
+	case SKF_AD_OFF + SKF_AD_RXHASH:
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4);
+
+		insn->code = BPF_LDX | BPF_MEM | BPF_W;
+		insn->a_reg = A_REG;
+		insn->x_reg = CTX_REG;
+		insn->off = offsetof(struct sk_buff, hash);
+		break;
+
+	case SKF_AD_OFF + SKF_AD_QUEUE:
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2);
+
+		insn->code = BPF_LDX | BPF_MEM | BPF_H;
+		insn->a_reg = A_REG;
+		insn->x_reg = CTX_REG;
+		insn->off = offsetof(struct sk_buff, queue_mapping);
+		break;
+
+	case SKF_AD_OFF + SKF_AD_VLAN_TAG:
+	case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT:
+		BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2);
+
+		insn->code = BPF_LDX | BPF_MEM | BPF_H;
+		insn->a_reg = A_REG;
+		insn->x_reg = CTX_REG;
+		insn->off = offsetof(struct sk_buff, vlan_tci);
+		insn++;
+
+		BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000);
+
+		if (fp->k == SKF_AD_OFF + SKF_AD_VLAN_TAG) {
+			insn->code = BPF_ALU | BPF_AND | BPF_K;
+			insn->a_reg = A_REG;
+			insn->imm = ~VLAN_TAG_PRESENT;
+		} else {
+			insn->code = BPF_ALU | BPF_RSH | BPF_K;
+			insn->a_reg = A_REG;
+			insn->imm = 12;
+			insn++;
+
+			insn->code = BPF_ALU | BPF_AND | BPF_K;
+			insn->a_reg = A_REG;
+			insn->imm = 1;
+		}
+		break;
+
+	case SKF_AD_OFF + SKF_AD_PAY_OFFSET:
+	case SKF_AD_OFF + SKF_AD_NLATTR:
+	case SKF_AD_OFF + SKF_AD_NLATTR_NEST:
+	case SKF_AD_OFF + SKF_AD_CPU:
+		/* arg1 = ctx */
+		insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+		insn->a_reg = ARG1_REG;
+		insn->x_reg = CTX_REG;
+		insn++;
+
+		/* arg2 = A */
+		insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+		insn->a_reg = ARG2_REG;
+		insn->x_reg = A_REG;
+		insn++;
+
+		/* arg3 = X */
+		insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+		insn->a_reg = ARG3_REG;
+		insn->x_reg = X_REG;
+		insn++;
+
+		/* Emit call(ctx, arg2=A, arg3=X) */
+		insn->code = BPF_JMP | BPF_CALL;
+		switch (fp->k) {
+		case SKF_AD_OFF + SKF_AD_PAY_OFFSET:
+			insn->imm = __skb_get_pay_offset - __bpf_call_base;
+			break;
+		case SKF_AD_OFF + SKF_AD_NLATTR:
+			insn->imm = __skb_get_nlattr - __bpf_call_base;
+			break;
+		case SKF_AD_OFF + SKF_AD_NLATTR_NEST:
+			insn->imm = __skb_get_nlattr_nest - __bpf_call_base;
+			break;
+		case SKF_AD_OFF + SKF_AD_CPU:
+			insn->imm = __get_raw_cpu_id - __bpf_call_base;
+			break;
+		}
+		break;
+
+	case SKF_AD_OFF + SKF_AD_ALU_XOR_X:
+		insn->code = BPF_ALU | BPF_XOR | BPF_X;
+		insn->a_reg = A_REG;
+		insn->x_reg = X_REG;
+		break;
+
+	default:
+		/* This is just a dummy call to avoid letting the compiler
+		 * evict __bpf_call_base() as an optimization. Placed here
+		 * where no-one bothers.
+		 */
+		BUG_ON(__bpf_call_base(0, 0, 0, 0, 0) != 0);
+		return false;
+	}
+
+	*insnp = insn;
+	return true;
+}
+
+/**
+ *	sk_convert_filter - convert filter program
+ *	@prog: the user passed filter program
+ *	@len: the length of the user passed filter program
+ *	@new_prog: buffer where converted program will be stored
+ *	@new_len: pointer to store length of converted program
+ *
+ * Remap 'sock_filter' style BPF instruction set to 'sock_filter_ext' style.
+ * Conversion workflow:
+ *
+ * 1) First pass for calculating the new program length:
+ *   sk_convert_filter(old_prog, old_len, NULL, &new_len)
+ *
+ * 2) 2nd pass to remap in two passes: 1st pass finds new
+ *    jump offsets, 2nd pass remapping:
+ *   new_prog = kmalloc(sizeof(struct sock_filter_int) * new_len);
+ *   sk_convert_filter(old_prog, old_len, new_prog, &new_len);
+ *
+ * User BPF's register A is mapped to our BPF register 6, user BPF
+ * register X is mapped to BPF register 7; frame pointer is always
+ * register 10; Context 'void *ctx' is stored in register 1, that is,
+ * for socket filters: ctx == 'struct sk_buff *', for seccomp:
+ * ctx == 'struct seccomp_data *'.
+ */
+int sk_convert_filter(struct sock_filter *prog, int len,
+		      struct sock_filter_int *new_prog, int *new_len)
+{
+	int new_flen = 0, pass = 0, target, i;
+	struct sock_filter_int *new_insn;
+	struct sock_filter *fp;
+	int *addrs = NULL;
+	u8 bpf_src;
+
+	BUILD_BUG_ON(BPF_MEMWORDS * sizeof(u32) > MAX_BPF_STACK);
+	BUILD_BUG_ON(FP_REG + 1 != MAX_BPF_REG);
+
+	if (len <= 0 || len >= BPF_MAXINSNS)
+		return -EINVAL;
+
+	if (new_prog) {
+		addrs = kzalloc(len * sizeof(*addrs), GFP_KERNEL);
+		if (!addrs)
+			return -ENOMEM;
+	}
+
+do_pass:
+	new_insn = new_prog;
+	fp = prog;
+
+	if (new_insn) {
+		new_insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+		new_insn->a_reg = CTX_REG;
+		new_insn->x_reg = ARG1_REG;
+	}
+	new_insn++;
+
+	for (i = 0; i < len; fp++, i++) {
+		struct sock_filter_int tmp_insns[6] = { };
+		struct sock_filter_int *insn = tmp_insns;
+
+		if (addrs)
+			addrs[i] = new_insn - new_prog;
+
+		switch (fp->code) {
+		/* All arithmetic insns and skb loads map as-is. */
+		case BPF_ALU | BPF_ADD | BPF_X:
+		case BPF_ALU | BPF_ADD | BPF_K:
+		case BPF_ALU | BPF_SUB | BPF_X:
+		case BPF_ALU | BPF_SUB | BPF_K:
+		case BPF_ALU | BPF_AND | BPF_X:
+		case BPF_ALU | BPF_AND | BPF_K:
+		case BPF_ALU | BPF_OR | BPF_X:
+		case BPF_ALU | BPF_OR | BPF_K:
+		case BPF_ALU | BPF_LSH | BPF_X:
+		case BPF_ALU | BPF_LSH | BPF_K:
+		case BPF_ALU | BPF_RSH | BPF_X:
+		case BPF_ALU | BPF_RSH | BPF_K:
+		case BPF_ALU | BPF_XOR | BPF_X:
+		case BPF_ALU | BPF_XOR | BPF_K:
+		case BPF_ALU | BPF_MUL | BPF_X:
+		case BPF_ALU | BPF_MUL | BPF_K:
+		case BPF_ALU | BPF_DIV | BPF_X:
+		case BPF_ALU | BPF_DIV | BPF_K:
+		case BPF_ALU | BPF_MOD | BPF_X:
+		case BPF_ALU | BPF_MOD | BPF_K:
+		case BPF_ALU | BPF_NEG:
+		case BPF_LD | BPF_ABS | BPF_W:
+		case BPF_LD | BPF_ABS | BPF_H:
+		case BPF_LD | BPF_ABS | BPF_B:
+		case BPF_LD | BPF_IND | BPF_W:
+		case BPF_LD | BPF_IND | BPF_H:
+		case BPF_LD | BPF_IND | BPF_B:
+			/* Check for overloaded BPF extension and
+			 * directly convert it if found, otherwise
+			 * just move on with mapping.
+			 */
+			if (BPF_CLASS(fp->code) == BPF_LD &&
+			    BPF_MODE(fp->code) == BPF_ABS &&
+			    convert_bpf_extensions(fp, &insn))
+				break;
+
+			insn->code = fp->code;
+			insn->a_reg = A_REG;
+			insn->x_reg = X_REG;
+			insn->imm = fp->k;
+			break;
+
+		/* Jump opcodes map as-is, but offsets need adjustment. */
+		case BPF_JMP | BPF_JA:
+			target = i + fp->k + 1;
+			insn->code = fp->code;
+#define EMIT_JMP							\
+	do {								\
+		if (target >= len || target < 0)			\
+			goto err;					\
+		insn->off = addrs ? addrs[target] - addrs[i] - 1 : 0;	\
+		/* Adjust pc relative offset for 2nd or 3rd insn. */	\
+		insn->off -= insn - tmp_insns;				\
+	} while (0)
+
+			EMIT_JMP;
+			break;
+
+		case BPF_JMP | BPF_JEQ | BPF_K:
+		case BPF_JMP | BPF_JEQ | BPF_X:
+		case BPF_JMP | BPF_JSET | BPF_K:
+		case BPF_JMP | BPF_JSET | BPF_X:
+		case BPF_JMP | BPF_JGT | BPF_K:
+		case BPF_JMP | BPF_JGT | BPF_X:
+		case BPF_JMP | BPF_JGE | BPF_K:
+		case BPF_JMP | BPF_JGE | BPF_X:
+			if (BPF_SRC(fp->code) == BPF_K && (int) fp->k < 0) {
+				/* BPF immediates are signed, zero extend
+				 * immediate into tmp register and use it
+				 * in compare insn.
+				 */
+				insn->code = BPF_ALU | BPF_MOV | BPF_K;
+				insn->a_reg = TMP_REG;
+				insn->imm = fp->k;
+				insn++;
+
+				insn->a_reg = A_REG;
+				insn->x_reg = TMP_REG;
+				bpf_src = BPF_X;
+			} else {
+				insn->a_reg = A_REG;
+				insn->x_reg = X_REG;
+				insn->imm = fp->k;
+				bpf_src = BPF_SRC(fp->code);
 			}
-			return 0;
-		case BPF_S_LD_B_ABS:
-			k = K;
-load_b:
-			ptr = load_pointer(skb, k, 1, &tmp);
-			if (ptr != NULL) {
-				A = *(u8 *)ptr;
-				continue;
+
+			/* Common case where 'jump_false' is next insn. */
+			if (fp->jf == 0) {
+				insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src;
+				target = i + fp->jt + 1;
+				EMIT_JMP;
+				break;
 			}
-			return 0;
-		case BPF_S_LD_W_LEN:
-			A = skb->len;
-			continue;
-		case BPF_S_LDX_W_LEN:
-			X = skb->len;
-			continue;
-		case BPF_S_LD_W_IND:
-			k = X + K;
-			goto load_w;
-		case BPF_S_LD_H_IND:
-			k = X + K;
-			goto load_h;
-		case BPF_S_LD_B_IND:
-			k = X + K;
-			goto load_b;
-		case BPF_S_LDX_B_MSH:
-			ptr = load_pointer(skb, K, 1, &tmp);
-			if (ptr != NULL) {
-				X = (*(u8 *)ptr & 0xf) << 2;
-				continue;
+
+			/* Convert JEQ into JNE when 'jump_true' is next insn. */
+			if (fp->jt == 0 && BPF_OP(fp->code) == BPF_JEQ) {
+				insn->code = BPF_JMP | BPF_JNE | bpf_src;
+				target = i + fp->jf + 1;
+				EMIT_JMP;
+				break;
 			}
-			return 0;
-		case BPF_S_LD_IMM:
-			A = K;
-			continue;
-		case BPF_S_LDX_IMM:
-			X = K;
-			continue;
-		case BPF_S_LD_MEM:
-			A = mem[K];
-			continue;
-		case BPF_S_LDX_MEM:
-			X = mem[K];
-			continue;
-		case BPF_S_MISC_TAX:
-			X = A;
-			continue;
-		case BPF_S_MISC_TXA:
-			A = X;
-			continue;
-		case BPF_S_RET_K:
-			return K;
-		case BPF_S_RET_A:
-			return A;
-		case BPF_S_ST:
-			mem[K] = A;
-			continue;
-		case BPF_S_STX:
-			mem[K] = X;
-			continue;
-		case BPF_S_ANC_PROTOCOL:
-			A = ntohs(skb->protocol);
-			continue;
-		case BPF_S_ANC_PKTTYPE:
-			A = skb->pkt_type;
-			continue;
-		case BPF_S_ANC_IFINDEX:
-			if (!skb->dev)
-				return 0;
-			A = skb->dev->ifindex;
-			continue;
-		case BPF_S_ANC_MARK:
-			A = skb->mark;
-			continue;
-		case BPF_S_ANC_QUEUE:
-			A = skb->queue_mapping;
-			continue;
-		case BPF_S_ANC_HATYPE:
-			if (!skb->dev)
-				return 0;
-			A = skb->dev->type;
-			continue;
-		case BPF_S_ANC_RXHASH:
-			A = skb->hash;
-			continue;
-		case BPF_S_ANC_CPU:
-			A = raw_smp_processor_id();
-			continue;
-		case BPF_S_ANC_VLAN_TAG:
-			A = vlan_tx_tag_get(skb);
-			continue;
-		case BPF_S_ANC_VLAN_TAG_PRESENT:
-			A = !!vlan_tx_tag_present(skb);
-			continue;
-		case BPF_S_ANC_PAY_OFFSET:
-			A = __skb_get_poff(skb);
-			continue;
-		case BPF_S_ANC_NLATTR: {
-			struct nlattr *nla;
-
-			if (skb_is_nonlinear(skb))
-				return 0;
-			if (A > skb->len - sizeof(struct nlattr))
-				return 0;
-
-			nla = nla_find((struct nlattr *)&skb->data[A],
-				       skb->len - A, X);
-			if (nla)
-				A = (void *)nla - (void *)skb->data;
-			else
-				A = 0;
-			continue;
-		}
-		case BPF_S_ANC_NLATTR_NEST: {
-			struct nlattr *nla;
-
-			if (skb_is_nonlinear(skb))
-				return 0;
-			if (A > skb->len - sizeof(struct nlattr))
-				return 0;
-
-			nla = (struct nlattr *)&skb->data[A];
-			if (nla->nla_len > A - skb->len)
-				return 0;
-
-			nla = nla_find_nested(nla, X);
-			if (nla)
-				A = (void *)nla - (void *)skb->data;
-			else
-				A = 0;
-			continue;
-		}
-#ifdef CONFIG_SECCOMP_FILTER
-		case BPF_S_ANC_SECCOMP_LD_W:
-			A = seccomp_bpf_load(fentry->k);
-			continue;
-#endif
+
+			/* Other jumps are mapped into two insns: Jxx and JA. */
+			target = i + fp->jt + 1;
+			insn->code = BPF_JMP | BPF_OP(fp->code) | bpf_src;
+			EMIT_JMP;
+			insn++;
+
+			insn->code = BPF_JMP | BPF_JA;
+			target = i + fp->jf + 1;
+			EMIT_JMP;
+			break;
+
+		/* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */
+		case BPF_LDX | BPF_MSH | BPF_B:
+			insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+			insn->a_reg = TMP_REG;
+			insn->x_reg = A_REG;
+			insn++;
+
+			insn->code = BPF_LD | BPF_ABS | BPF_B;
+			insn->a_reg = A_REG;
+			insn->imm = fp->k;
+			insn++;
+
+			insn->code = BPF_ALU | BPF_AND | BPF_K;
+			insn->a_reg = A_REG;
+			insn->imm = 0xf;
+			insn++;
+
+			insn->code = BPF_ALU | BPF_LSH | BPF_K;
+			insn->a_reg = A_REG;
+			insn->imm = 2;
+			insn++;
+
+			insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+			insn->a_reg = X_REG;
+			insn->x_reg = A_REG;
+			insn++;
+
+			insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+			insn->a_reg = A_REG;
+			insn->x_reg = TMP_REG;
+			break;
+
+		/* RET_K, RET_A are remaped into 2 insns. */
+		case BPF_RET | BPF_A:
+		case BPF_RET | BPF_K:
+			insn->code = BPF_ALU | BPF_MOV |
+				     (BPF_RVAL(fp->code) == BPF_K ?
+				      BPF_K : BPF_X);
+			insn->a_reg = 0;
+			insn->x_reg = A_REG;
+			insn->imm = fp->k;
+			insn++;
+
+			insn->code = BPF_JMP | BPF_EXIT;
+			break;
+
+		/* Store to stack. */
+		case BPF_ST:
+		case BPF_STX:
+			insn->code = BPF_STX | BPF_MEM | BPF_W;
+			insn->a_reg = FP_REG;
+			insn->x_reg = fp->code == BPF_ST ? A_REG : X_REG;
+			insn->off = -(BPF_MEMWORDS - fp->k) * 4;
+			break;
+
+		/* Load from stack. */
+		case BPF_LD | BPF_MEM:
+		case BPF_LDX | BPF_MEM:
+			insn->code = BPF_LDX | BPF_MEM | BPF_W;
+			insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ?
+				      A_REG : X_REG;
+			insn->x_reg = FP_REG;
+			insn->off = -(BPF_MEMWORDS - fp->k) * 4;
+			break;
+
+		/* A = K or X = K */
+		case BPF_LD | BPF_IMM:
+		case BPF_LDX | BPF_IMM:
+			insn->code = BPF_ALU | BPF_MOV | BPF_K;
+			insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ?
+				      A_REG : X_REG;
+			insn->imm = fp->k;
+			break;
+
+		/* X = A */
+		case BPF_MISC | BPF_TAX:
+			insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+			insn->a_reg = X_REG;
+			insn->x_reg = A_REG;
+			break;
+
+		/* A = X */
+		case BPF_MISC | BPF_TXA:
+			insn->code = BPF_ALU64 | BPF_MOV | BPF_X;
+			insn->a_reg = A_REG;
+			insn->x_reg = X_REG;
+			break;
+
+		/* A = skb->len or X = skb->len */
+		case BPF_LD | BPF_W | BPF_LEN:
+		case BPF_LDX | BPF_W | BPF_LEN:
+			insn->code = BPF_LDX | BPF_MEM | BPF_W;
+			insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ?
+				      A_REG : X_REG;
+			insn->x_reg = CTX_REG;
+			insn->off = offsetof(struct sk_buff, len);
+			break;
+
+		/* access seccomp_data fields */
+		case BPF_LDX | BPF_ABS | BPF_W:
+			insn->code = BPF_LDX | BPF_MEM | BPF_W;
+			insn->a_reg = A_REG;
+			insn->x_reg = CTX_REG;
+			insn->off = fp->k;
+			break;
+
 		default:
-			WARN_RATELIMIT(1, "Unknown code:%u jt:%u tf:%u k:%u\n",
-				       fentry->code, fentry->jt,
-				       fentry->jf, fentry->k);
-			return 0;
+			goto err;
 		}
+
+		insn++;
+		if (new_prog)
+			memcpy(new_insn, tmp_insns,
+			       sizeof(*insn) * (insn - tmp_insns));
+
+		new_insn += insn - tmp_insns;
 	}
 
+	if (!new_prog) {
+		/* Only calculating new length. */
+		*new_len = new_insn - new_prog;
+		return 0;
+	}
+
+	pass++;
+	if (new_flen != new_insn - new_prog) {
+		new_flen = new_insn - new_prog;
+		if (pass > 2)
+			goto err;
+
+		goto do_pass;
+	}
+
+	kfree(addrs);
+	BUG_ON(*new_len != new_flen);
 	return 0;
+err:
+	kfree(addrs);
+	return -EINVAL;
 }
-EXPORT_SYMBOL(sk_run_filter);
 
-/*
- * Security :
+/* Security:
+ *
  * A BPF program is able to use 16 cells of memory to store intermediate
- * values (check u32 mem[BPF_MEMWORDS] in sk_run_filter())
+ * values (check u32 mem[BPF_MEMWORDS] in sk_run_filter()).
+ *
  * As we dont want to clear mem[] array for each packet going through
  * sk_run_filter(), we check that filter loaded by user never try to read
  * a cell if not previously written, and we check all branches to be sure
@@ -696,19 +1442,130 @@ void sk_filter_charge(struct sock *sk, struct sk_filter *fp)
 	atomic_add(sk_filter_size(fp->len), &sk->sk_omem_alloc);
 }
 
-static int __sk_prepare_filter(struct sk_filter *fp)
+static struct sk_filter *__sk_migrate_realloc(struct sk_filter *fp,
+					      struct sock *sk,
+					      unsigned int len)
+{
+	struct sk_filter *fp_new;
+
+	if (sk == NULL)
+		return krealloc(fp, len, GFP_KERNEL);
+
+	fp_new = sock_kmalloc(sk, len, GFP_KERNEL);
+	if (fp_new) {
+		memcpy(fp_new, fp, sizeof(struct sk_filter));
+		/* As we're kepping orig_prog in fp_new along,
+		 * we need to make sure we're not evicting it
+		 * from the old fp.
+		 */
+		fp->orig_prog = NULL;
+		sk_filter_uncharge(sk, fp);
+	}
+
+	return fp_new;
+}
+
+static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp,
+					     struct sock *sk)
+{
+	struct sock_filter *old_prog;
+	struct sk_filter *old_fp;
+	int i, err, new_len, old_len = fp->len;
+
+	/* We are free to overwrite insns et al right here as it
+	 * won't be used at this point in time anymore internally
+	 * after the migration to the internal BPF instruction
+	 * representation.
+	 */
+	BUILD_BUG_ON(sizeof(struct sock_filter) !=
+		     sizeof(struct sock_filter_int));
+
+	/* For now, we need to unfiddle BPF_S_* identifiers in place.
+	 * This can sooner or later on be subject to removal, e.g. when
+	 * JITs have been converted.
+	 */
+	for (i = 0; i < fp->len; i++)
+		sk_decode_filter(&fp->insns[i], &fp->insns[i]);
+
+	/* Conversion cannot happen on overlapping memory areas,
+	 * so we need to keep the user BPF around until the 2nd
+	 * pass. At this time, the user BPF is stored in fp->insns.
+	 */
+	old_prog = kmemdup(fp->insns, old_len * sizeof(struct sock_filter),
+			   GFP_KERNEL);
+	if (!old_prog) {
+		err = -ENOMEM;
+		goto out_err;
+	}
+
+	/* 1st pass: calculate the new program length. */
+	err = sk_convert_filter(old_prog, old_len, NULL, &new_len);
+	if (err)
+		goto out_err_free;
+
+	/* Expand fp for appending the new filter representation. */
+	old_fp = fp;
+	fp = __sk_migrate_realloc(old_fp, sk, sk_filter_size(new_len));
+	if (!fp) {
+		/* The old_fp is still around in case we couldn't
+		 * allocate new memory, so uncharge on that one.
+		 */
+		fp = old_fp;
+		err = -ENOMEM;
+		goto out_err_free;
+	}
+
+	fp->bpf_func = sk_run_filter_int_skb;
+	fp->len = new_len;
+
+	/* 2nd pass: remap sock_filter insns into sock_filter_int insns. */
+	err = sk_convert_filter(old_prog, old_len, fp->insnsi, &new_len);
+	if (err)
+		/* 2nd sk_convert_filter() can fail only if it fails
+		 * to allocate memory, remapping must succeed. Note,
+		 * that at this time old_fp has already been released
+		 * by __sk_migrate_realloc().
+		 */
+		goto out_err_free;
+
+	kfree(old_prog);
+	return fp;
+
+out_err_free:
+	kfree(old_prog);
+out_err:
+	/* Rollback filter setup. */
+	if (sk != NULL)
+		sk_filter_uncharge(sk, fp);
+	else
+		kfree(fp);
+	return ERR_PTR(err);
+}
+
+static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp,
+					     struct sock *sk)
 {
 	int err;
 
-	fp->bpf_func = sk_run_filter;
+	fp->bpf_func = NULL;
 	fp->jited = 0;
 
 	err = sk_chk_filter(fp->insns, fp->len);
 	if (err)
-		return err;
+		return ERR_PTR(err);
 
+	/* Probe if we can JIT compile the filter and if so, do
+	 * the compilation of the filter.
+	 */
 	bpf_jit_compile(fp);
-	return 0;
+
+	/* JIT compiler couldn't process this filter, so do the
+	 * internal BPF translation for the optimized interpreter.
+	 */
+	if (!fp->jited)
+		fp = __sk_migrate_filter(fp, sk);
+
+	return fp;
 }
 
 /**
@@ -726,7 +1583,6 @@ int sk_unattached_filter_create(struct sk_filter **pfp,
 {
 	unsigned int fsize = sk_filter_proglen(fprog);
 	struct sk_filter *fp;
-	int err;
 
 	/* Make sure new filter is there and in the right amounts. */
 	if (fprog->filter == NULL)
@@ -746,15 +1602,15 @@ int sk_unattached_filter_create(struct sk_filter **pfp,
 	 */
 	fp->orig_prog = NULL;
 
-	err = __sk_prepare_filter(fp);
-	if (err)
-		goto free_mem;
+	/* __sk_prepare_filter() already takes care of uncharging
+	 * memory in case something goes wrong.
+	 */
+	fp = __sk_prepare_filter(fp, NULL);
+	if (IS_ERR(fp))
+		return PTR_ERR(fp);
 
 	*pfp = fp;
 	return 0;
-free_mem:
-	kfree(fp);
-	return err;
 }
 EXPORT_SYMBOL_GPL(sk_unattached_filter_create);
 
@@ -806,11 +1662,12 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 		return -ENOMEM;
 	}
 
-	err = __sk_prepare_filter(fp);
-	if (err) {
-		sk_filter_uncharge(sk, fp);
-		return err;
-	}
+	/* __sk_prepare_filter() already takes care of uncharging
+	 * memory in case something goes wrong.
+	 */
+	fp = __sk_prepare_filter(fp, sk);
+	if (IS_ERR(fp))
+		return PTR_ERR(fp);
 
 	old_fp = rcu_dereference_protected(sk->sk_filter,
 					   sock_owned_by_user(sk));
-- 
cgit v1.2.3


From 24cbe7845ea50b636ab2218b9d648270ff55f148 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@redhat.com>
Date: Mon, 3 Feb 2014 12:13:06 -0500
Subject: locks: close potential race between setlease and open

As Al Viro points out, there is an unlikely, but possible race between
opening a file and setting a lease on it. generic_add_lease is done with
the i_lock held, but the inode->i_flock check in break_lease is
lockless. It's possible for another task doing an open to do the entire
pathwalk and call break_lease between the point where generic_add_lease
checks for a conflicting open and adds the lease to the list. If this
occurs, we can end up with a lease set on the file with a conflicting
open.

To guard against that, check again for a conflicting open after adding
the lease to the i_flock list. If the above race occurs, then we can
simply unwind the lease setting and return -EAGAIN.

Because we take dentry references and acquire write access on the file
before calling break_lease, we know that if the i_flock list is empty
when the open caller goes to check it then the necessary refcounts have
already been incremented. Thus the additional check for a conflicting
open will see that there is one and the setlease call will fail.

Cc: Bruce Fields <bfields@fieldses.org>
Cc: David Howells <dhowells@redhat.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Reported-by: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@fieldses.org>
---
 fs/locks.c         | 75 ++++++++++++++++++++++++++++++++++++++++++++----------
 include/linux/fs.h |  6 +++++
 2 files changed, 68 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/fs/locks.c b/fs/locks.c
index 92a0f0a52b06..2cfeea622f28 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -652,15 +652,18 @@ static void locks_insert_lock(struct file_lock **pos, struct file_lock *fl)
 	locks_insert_global_locks(fl);
 }
 
-/*
- * Delete a lock and then free it.
- * Wake up processes that are blocked waiting for this lock,
- * notify the FS that the lock has been cleared and
- * finally free the lock.
+/**
+ * locks_delete_lock - Delete a lock and then free it.
+ * @thisfl_p: pointer that points to the fl_next field of the previous
+ * 	      inode->i_flock list entry
+ *
+ * Unlink a lock from all lists and free the namespace reference, but don't
+ * free it yet. Wake up processes that are blocked waiting for this lock and
+ * notify the FS that the lock has been cleared.
  *
  * Must be called with the i_lock held!
  */
-static void locks_delete_lock(struct file_lock **thisfl_p)
+static void locks_unlink_lock(struct file_lock **thisfl_p)
 {
 	struct file_lock *fl = *thisfl_p;
 
@@ -675,6 +678,18 @@ static void locks_delete_lock(struct file_lock **thisfl_p)
 	}
 
 	locks_wake_up_blocks(fl);
+}
+
+/*
+ * Unlink a lock from all lists and free it.
+ *
+ * Must be called with i_lock held!
+ */
+static void locks_delete_lock(struct file_lock **thisfl_p)
+{
+	struct file_lock *fl = *thisfl_p;
+
+	locks_unlink_lock(thisfl_p);
 	locks_free_lock(fl);
 }
 
@@ -1472,6 +1487,32 @@ int fcntl_getlease(struct file *filp)
 	return type;
 }
 
+/**
+ * check_conflicting_open - see if the given dentry points to a file that has
+ * 			    an existing open that would conflict with the
+ * 			    desired lease.
+ * @dentry:	dentry to check
+ * @arg:	type of lease that we're trying to acquire
+ *
+ * Check to see if there's an existing open fd on this file that would
+ * conflict with the lease we're trying to set.
+ */
+static int
+check_conflicting_open(const struct dentry *dentry, const long arg)
+{
+	int ret = 0;
+	struct inode *inode = dentry->d_inode;
+
+	if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0))
+		return -EAGAIN;
+
+	if ((arg == F_WRLCK) && ((d_count(dentry) > 1) ||
+	    (atomic_read(&inode->i_count) > 1)))
+		ret = -EAGAIN;
+
+	return ret;
+}
+
 static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp)
 {
 	struct file_lock *fl, **before, **my_before = NULL, *lease;
@@ -1499,12 +1540,8 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
 		return -EINVAL;
 	}
 
-	error = -EAGAIN;
-	if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0))
-		goto out;
-	if ((arg == F_WRLCK)
-	    && ((d_count(dentry) > 1)
-		|| (atomic_read(&inode->i_count) > 1)))
+	error = check_conflicting_open(dentry, arg);
+	if (error)
 		goto out;
 
 	/*
@@ -1549,7 +1586,19 @@ static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp
 		goto out;
 
 	locks_insert_lock(before, lease);
-	error = 0;
+	/*
+	 * The check in break_lease() is lockless. It's possible for another
+	 * open to race in after we did the earlier check for a conflicting
+	 * open but before the lease was inserted. Check again for a
+	 * conflicting open and cancel the lease if there is one.
+	 *
+	 * We also add a barrier here to ensure that the insertion of the lock
+	 * precedes these checks.
+	 */
+	smp_mb();
+	error = check_conflicting_open(dentry, arg);
+	if (error)
+		locks_unlink_lock(flp);
 out:
 	if (is_deleg)
 		mutex_unlock(&inode->i_mutex);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 09f553c59813..df8474408331 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1964,6 +1964,12 @@ static inline int locks_verify_truncate(struct inode *inode,
 
 static inline int break_lease(struct inode *inode, unsigned int mode)
 {
+	/*
+	 * Since this check is lockless, we must ensure that any refcounts
+	 * taken are done before checking inode->i_flock. Otherwise, we could
+	 * end up racing with tasks trying to set a new lease on this file.
+	 */
+	smp_mb();
 	if (inode->i_flock)
 		return __break_lease(inode, mode, FL_LEASE);
 	return 0;
-- 
cgit v1.2.3


From 78ed8a13382b1354e95d0f2233577eba15cb8171 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@redhat.com>
Date: Mon, 3 Feb 2014 12:13:08 -0500
Subject: locks: rename locks_remove_flock to locks_remove_file

This function currently removes leases in addition to flock locks and in
a later patch we'll have it deal with file-private locks too. Rename it
to locks_remove_file to indicate that it removes locks that are
associated with a particular struct file, and not just flock locks.

Acked-by: J. Bruce Fields <bfields@fieldses.org>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
---
 fs/file_table.c    | 2 +-
 fs/locks.c         | 2 +-
 include/linux/fs.h | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/fs/file_table.c b/fs/file_table.c
index 5fff9030be34..468543c1973d 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -234,7 +234,7 @@ static void __fput(struct file *file)
 	 * in the file cleanup chain.
 	 */
 	eventpoll_release(file);
-	locks_remove_flock(file);
+	locks_remove_file(file);
 
 	if (unlikely(file->f_flags & FASYNC)) {
 		if (file->f_op->fasync)
diff --git a/fs/locks.c b/fs/locks.c
index 4cd25781b0a4..4d4e790150e0 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2196,7 +2196,7 @@ EXPORT_SYMBOL(locks_remove_posix);
 /*
  * This function is called on the last close of an open file.
  */
-void locks_remove_flock(struct file *filp)
+void locks_remove_file(struct file *filp)
 {
 	struct inode * inode = file_inode(filp);
 	struct file_lock *fl;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index df8474408331..7527d96913d3 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1012,7 +1012,7 @@ extern struct file_lock * locks_alloc_lock(void);
 extern void locks_copy_lock(struct file_lock *, struct file_lock *);
 extern void __locks_copy_lock(struct file_lock *, const struct file_lock *);
 extern void locks_remove_posix(struct file *, fl_owner_t);
-extern void locks_remove_flock(struct file *);
+extern void locks_remove_file(struct file *);
 extern void locks_release_private(struct file_lock *);
 extern void posix_test_lock(struct file *, struct file_lock *);
 extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *);
@@ -1083,7 +1083,7 @@ static inline void locks_remove_posix(struct file *filp, fl_owner_t owner)
 	return;
 }
 
-static inline void locks_remove_flock(struct file *filp)
+static inline void locks_remove_file(struct file *filp)
 {
 	return;
 }
-- 
cgit v1.2.3


From c918d42a27a9be0d78be490997d16d79cd5b9193 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@redhat.com>
Date: Mon, 3 Feb 2014 12:13:09 -0500
Subject: locks: make /proc/locks show IS_FILE_PVT locks as type "FLPVT"

In a later patch, we'll be adding a new type of lock that's owned by
the struct file instead of the files_struct. Those sorts of locks
will be flagged with a new FL_FILE_PVT flag.

Report these types of locks as "FLPVT" in /proc/locks to distinguish
them from "classic" POSIX locks.

Acked-by: J. Bruce Fields <bfields@fieldses.org>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
---
 fs/locks.c         | 11 +++++++++--
 include/linux/fs.h |  1 +
 2 files changed, 10 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/locks.c b/fs/locks.c
index 4d4e790150e0..0e1f0df8de12 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -135,6 +135,7 @@
 #define IS_POSIX(fl)	(fl->fl_flags & FL_POSIX)
 #define IS_FLOCK(fl)	(fl->fl_flags & FL_FLOCK)
 #define IS_LEASE(fl)	(fl->fl_flags & (FL_LEASE|FL_DELEG))
+#define IS_FILE_PVT(fl)	(fl->fl_flags & FL_FILE_PVT)
 
 static bool lease_breaking(struct file_lock *fl)
 {
@@ -2313,8 +2314,14 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
 
 	seq_printf(f, "%lld:%s ", id, pfx);
 	if (IS_POSIX(fl)) {
-		seq_printf(f, "%6s %s ",
-			     (fl->fl_flags & FL_ACCESS) ? "ACCESS" : "POSIX ",
+		if (fl->fl_flags & FL_ACCESS)
+			seq_printf(f, "ACCESS");
+		else if (IS_FILE_PVT(fl))
+			seq_printf(f, "FLPVT ");
+		else
+			seq_printf(f, "POSIX ");
+
+		seq_printf(f, " %s ",
 			     (inode == NULL) ? "*NOINODE*" :
 			     mandatory_lock(inode) ? "MANDATORY" : "ADVISORY ");
 	} else if (IS_FLOCK(fl)) {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7527d96913d3..5ddeb8de5e77 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -888,6 +888,7 @@ static inline int file_check_writeable(struct file *filp)
 #define FL_SLEEP	128	/* A blocking lock */
 #define FL_DOWNGRADE_PENDING	256 /* Lease is being downgraded */
 #define FL_UNLOCK_PENDING	512 /* Lease is being broken */
+#define FL_FILE_PVT	1024	/* lock is private to the file */
 
 /*
  * Special return value from posix_lock_file() and vfs_lock_file() for
-- 
cgit v1.2.3


From c1e62b8fc355e0c3706f1ae0dacb72d1c514dc80 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@redhat.com>
Date: Mon, 3 Feb 2014 12:13:09 -0500
Subject: locks: pass the cmd value to fcntl_getlk/getlk64

Once we introduce file private locks, we'll need to know what cmd value
was used, as that affects the ownership and whether a conflict would
arise.

Signed-off-by: Jeff Layton <jlayton@redhat.com>
---
 fs/fcntl.c         |  4 ++--
 fs/locks.c         |  4 ++--
 include/linux/fs.h | 10 ++++++----
 3 files changed, 10 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/fs/fcntl.c b/fs/fcntl.c
index ef6866592a0f..7ef7f2d2b608 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -273,7 +273,7 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 		err = setfl(fd, filp, arg);
 		break;
 	case F_GETLK:
-		err = fcntl_getlk(filp, (struct flock __user *) arg);
+		err = fcntl_getlk(filp, cmd, (struct flock __user *) arg);
 		break;
 	case F_SETLK:
 	case F_SETLKW:
@@ -389,7 +389,7 @@ SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
 	
 	switch (cmd) {
 		case F_GETLK64:
-			err = fcntl_getlk64(f.file, (struct flock64 __user *) arg);
+			err = fcntl_getlk64(f.file, cmd, (struct flock64 __user *) arg);
 			break;
 		case F_SETLK64:
 		case F_SETLKW64:
diff --git a/fs/locks.c b/fs/locks.c
index 57f1d5fc876a..442052b413af 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1898,7 +1898,7 @@ static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl)
 /* Report the first existing lock that would conflict with l.
  * This implements the F_GETLK command of fcntl().
  */
-int fcntl_getlk(struct file *filp, struct flock __user *l)
+int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock __user *l)
 {
 	struct file_lock file_lock;
 	struct flock flock;
@@ -2066,7 +2066,7 @@ out:
 /* Report the first existing lock that would conflict with l.
  * This implements the F_GETLK command of fcntl().
  */
-int fcntl_getlk64(struct file *filp, struct flock64 __user *l)
+int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 __user *l)
 {
 	struct file_lock file_lock;
 	struct flock64 flock;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5ddeb8de5e77..ae91dce8a547 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -993,12 +993,12 @@ struct file_lock {
 extern void send_sigio(struct fown_struct *fown, int fd, int band);
 
 #ifdef CONFIG_FILE_LOCKING
-extern int fcntl_getlk(struct file *, struct flock __user *);
+extern int fcntl_getlk(struct file *, unsigned int, struct flock __user *);
 extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
 			struct flock __user *);
 
 #if BITS_PER_LONG == 32
-extern int fcntl_getlk64(struct file *, struct flock64 __user *);
+extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 __user *);
 extern int fcntl_setlk64(unsigned int, struct file *, unsigned int,
 			struct flock64 __user *);
 #endif
@@ -1031,7 +1031,8 @@ extern int lease_modify(struct file_lock **, int);
 extern int lock_may_read(struct inode *, loff_t start, unsigned long count);
 extern int lock_may_write(struct inode *, loff_t start, unsigned long count);
 #else /* !CONFIG_FILE_LOCKING */
-static inline int fcntl_getlk(struct file *file, struct flock __user *user)
+static inline int fcntl_getlk(struct file *file, unsigned int cmd,
+			      struct flock __user *user)
 {
 	return -EINVAL;
 }
@@ -1043,7 +1044,8 @@ static inline int fcntl_setlk(unsigned int fd, struct file *file,
 }
 
 #if BITS_PER_LONG == 32
-static inline int fcntl_getlk64(struct file *file, struct flock64 __user *user)
+static inline int fcntl_getlk64(struct file *file, unsigned int cmd,
+				struct flock64 __user *user)
 {
 	return -EINVAL;
 }
-- 
cgit v1.2.3


From d7a06983a01a33605191c0766857b832ac32a2b6 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@redhat.com>
Date: Mon, 10 Mar 2014 09:54:15 -0400
Subject: locks: fix locks_mandatory_locked to respect file-private locks

As Trond pointed out, you can currently deadlock yourself by setting a
file-private lock on a file that requires mandatory locking and then
trying to do I/O on it.

Avoid this problem by plumbing some knowledge of file-private locks into
the mandatory locking code. In order to do this, we must pass down
information about the struct file that's being used to
locks_verify_locked.

Reported-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Acked-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/locks.c         |  7 ++++---
 fs/namei.c         |  2 +-
 include/linux/fs.h | 22 +++++++++++-----------
 mm/mmap.c          |  2 +-
 mm/nommu.c         |  2 +-
 5 files changed, 18 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/fs/locks.c b/fs/locks.c
index 09d6c8c33c81..d82c51c4fcd2 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1155,13 +1155,14 @@ EXPORT_SYMBOL(posix_lock_file_wait);
 
 /**
  * locks_mandatory_locked - Check for an active lock
- * @inode: the file to check
+ * @file: the file to check
  *
  * Searches the inode's list of locks to find any POSIX locks which conflict.
  * This function is called from locks_verify_locked() only.
  */
-int locks_mandatory_locked(struct inode *inode)
+int locks_mandatory_locked(struct file *file)
 {
+	struct inode *inode = file_inode(file);
 	fl_owner_t owner = current->files;
 	struct file_lock *fl;
 
@@ -1172,7 +1173,7 @@ int locks_mandatory_locked(struct inode *inode)
 	for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
 		if (!IS_POSIX(fl))
 			continue;
-		if (fl->fl_owner != owner)
+		if (fl->fl_owner != owner && fl->fl_owner != (fl_owner_t)file)
 			break;
 	}
 	spin_unlock(&inode->i_lock);
diff --git a/fs/namei.c b/fs/namei.c
index d580df2e6804..dc51bac037c9 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2542,7 +2542,7 @@ static int handle_truncate(struct file *filp)
 	/*
 	 * Refuse to truncate files with mandatory locks held on them.
 	 */
-	error = locks_verify_locked(inode);
+	error = locks_verify_locked(filp);
 	if (!error)
 		error = security_path_truncate(path);
 	if (!error) {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ae91dce8a547..4aa81e6ae067 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1912,6 +1912,11 @@ extern int current_umask(void);
 extern void ihold(struct inode * inode);
 extern void iput(struct inode *);
 
+static inline struct inode *file_inode(struct file *f)
+{
+	return f->f_inode;
+}
+
 /* /sys/fs */
 extern struct kobject *fs_kobj;
 
@@ -1921,7 +1926,7 @@ extern struct kobject *fs_kobj;
 #define FLOCK_VERIFY_WRITE 2
 
 #ifdef CONFIG_FILE_LOCKING
-extern int locks_mandatory_locked(struct inode *);
+extern int locks_mandatory_locked(struct file *);
 extern int locks_mandatory_area(int, struct inode *, struct file *, loff_t, size_t);
 
 /*
@@ -1944,10 +1949,10 @@ static inline int mandatory_lock(struct inode *ino)
 	return IS_MANDLOCK(ino) && __mandatory_lock(ino);
 }
 
-static inline int locks_verify_locked(struct inode *inode)
+static inline int locks_verify_locked(struct file *file)
 {
-	if (mandatory_lock(inode))
-		return locks_mandatory_locked(inode);
+	if (mandatory_lock(file_inode(file)))
+		return locks_mandatory_locked(file);
 	return 0;
 }
 
@@ -2008,7 +2013,7 @@ static inline int break_deleg_wait(struct inode **delegated_inode)
 }
 
 #else /* !CONFIG_FILE_LOCKING */
-static inline int locks_mandatory_locked(struct inode *inode)
+static inline int locks_mandatory_locked(struct file *file)
 {
 	return 0;
 }
@@ -2030,7 +2035,7 @@ static inline int mandatory_lock(struct inode *inode)
 	return 0;
 }
 
-static inline int locks_verify_locked(struct inode *inode)
+static inline int locks_verify_locked(struct file *file)
 {
 	return 0;
 }
@@ -2297,11 +2302,6 @@ static inline bool execute_ok(struct inode *inode)
 	return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode);
 }
 
-static inline struct inode *file_inode(struct file *f)
-{
-	return f->f_inode;
-}
-
 static inline void file_start_write(struct file *file)
 {
 	if (!S_ISREG(file_inode(file)->i_mode))
diff --git a/mm/mmap.c b/mm/mmap.c
index 20ff0c33274c..5932ce961218 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1299,7 +1299,7 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 			/*
 			 * Make sure there are no mandatory locks on the file.
 			 */
-			if (locks_verify_locked(inode))
+			if (locks_verify_locked(file))
 				return -EAGAIN;
 
 			vm_flags |= VM_SHARED | VM_MAYSHARE;
diff --git a/mm/nommu.c b/mm/nommu.c
index 8740213b1647..a554e5a451cd 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -995,7 +995,7 @@ static int validate_mmap_request(struct file *file,
 			    (file->f_mode & FMODE_WRITE))
 				return -EACCES;
 
-			if (locks_verify_locked(file_inode(file)))
+			if (locks_verify_locked(file))
 				return -EAGAIN;
 
 			if (!(capabilities & BDI_CAP_MAP_DIRECT))
-- 
cgit v1.2.3


From 1ee481fb4cf8044632fa869bafc41345afa5957b Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevic@redhat.com>
Date: Thu, 27 Mar 2014 17:32:29 -0400
Subject: net: Allow modules to use is_skb_forwardable

Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 1 +
 net/core/dev.c            | 4 ++--
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 06287c110241..29b579fb5196 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2629,6 +2629,7 @@ int dev_get_phys_port_id(struct net_device *dev,
 int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 			struct netdev_queue *txq);
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
+bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb);
 
 extern int		netdev_budget;
 
diff --git a/net/core/dev.c b/net/core/dev.c
index cf92139b229c..a923eed976ae 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1640,8 +1640,7 @@ static inline void net_timestamp_set(struct sk_buff *skb)
 			__net_timestamp(SKB);		\
 	}						\
 
-static inline bool is_skb_forwardable(struct net_device *dev,
-				      struct sk_buff *skb)
+bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb)
 {
 	unsigned int len;
 
@@ -1660,6 +1659,7 @@ static inline bool is_skb_forwardable(struct net_device *dev,
 
 	return false;
 }
+EXPORT_SYMBOL_GPL(is_skb_forwardable);
 
 /**
  * dev_forward_skb - loopback an skb to another netif
-- 
cgit v1.2.3


From 339e022396d58f4b4f9b4200ea5309768934bb33 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 28 Mar 2014 14:25:58 -0700
Subject: net: export NET_ADDR_* values to user-space API

NET_ADDR_* values are exported in the
/sys/class/net/<iface>/addr_assign_type sysfs attributes, and as such
constitutes an user-space ABI. Move the NET_ADDR_* definitions from
include/linux/netdevice.h to include/uapi/linux/netdevice.h

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h      | 7 -------
 include/uapi/linux/netdevice.h | 6 ++++++
 2 files changed, 6 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 29b579fb5196..34cae3ee74f1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -63,13 +63,6 @@ struct wireless_dev;
 void netdev_set_default_ethtool_ops(struct net_device *dev,
 				    const struct ethtool_ops *ops);
 
-/* hardware address assignment types */
-#define NET_ADDR_PERM		0	/* address is permanent (default) */
-#define NET_ADDR_RANDOM		1	/* address is generated randomly */
-#define NET_ADDR_STOLEN		2	/* address is stolen from other device */
-#define NET_ADDR_SET		3	/* address is set using
-					 * dev_set_mac_address() */
-
 /* Backlog congestion levels */
 #define NET_RX_SUCCESS		0	/* keep 'em coming, baby */
 #define NET_RX_DROP		1	/* packet dropped */
diff --git a/include/uapi/linux/netdevice.h b/include/uapi/linux/netdevice.h
index 6b9500bc2d56..fdfbd1c17065 100644
--- a/include/uapi/linux/netdevice.h
+++ b/include/uapi/linux/netdevice.h
@@ -49,5 +49,11 @@ enum {
         IF_PORT_100BASEFX
 };
 
+/* hardware address assignment types */
+#define NET_ADDR_PERM		0	/* address is permanent (default) */
+#define NET_ADDR_RANDOM		1	/* address is generated randomly */
+#define NET_ADDR_STOLEN		2	/* address is stolen from other device */
+#define NET_ADDR_SET		3	/* address is set using
+					 * dev_set_mac_address() */
 
 #endif /* _UAPI_LINUX_NETDEVICE_H */
-- 
cgit v1.2.3


From 2d3b479df41a10e2f41f9259fcba775bd34de6e4 Mon Sep 17 00:00:00 2001
From: david decotigny <decot@googlers.com>
Date: Sat, 29 Mar 2014 09:48:35 -0700
Subject: net-sysfs: expose number of carrier on/off changes

This allows to monitor carrier on/off transitions and detect link
flapping issues:
 - new /sys/class/net/X/carrier_changes
 - new rtnetlink IFLA_CARRIER_CHANGES (getlink)

Tested:
  - grep . /sys/class/net/*/carrier_changes
    + ip link set dev X down/up
    + plug/unplug cable
  - updated iproute2: prints IFLA_CARRIER_CHANGES
  - iproute2 20121211-2 (debian): unchanged behavior

Signed-off-by: David Decotigny <decot@googlers.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h    |  3 +++
 include/uapi/linux/if_link.h |  1 +
 net/core/net-sysfs.c         | 11 +++++++++++
 net/core/rtnetlink.c         |  6 +++++-
 net/sched/sch_generic.c      |  2 ++
 5 files changed, 22 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 34cae3ee74f1..45537ed7a5b3 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1308,6 +1308,9 @@ struct net_device {
 	atomic_long_t		rx_dropped;
 	atomic_long_t		tx_dropped;
 
+	/* Stats to monitor carrier on<->off transitions */
+	atomic_t		carrier_changes;
+
 #ifdef CONFIG_WIRELESS_EXT
 	/* List of functions to handle Wireless Extensions (instead of ioctl).
 	 * See <net/iw_handler.h> for details. Jean II */
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 16410b6e7819..9a7f7ace6649 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -144,6 +144,7 @@ enum {
 	IFLA_NUM_RX_QUEUES,
 	IFLA_CARRIER,
 	IFLA_PHYS_PORT_ID,
+	IFLA_CARRIER_CHANGES,
 	__IFLA_MAX
 };
 
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index daed9a64c6f6..462396278484 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -253,6 +253,16 @@ static ssize_t operstate_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(operstate);
 
+static ssize_t carrier_changes_show(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf)
+{
+	struct net_device *netdev = to_net_dev(dev);
+	return sprintf(buf, fmt_dec,
+		       atomic_read(&netdev->carrier_changes));
+}
+static DEVICE_ATTR_RO(carrier_changes);
+
 /* read-write attributes */
 
 static int change_mtu(struct net_device *net, unsigned long new_mtu)
@@ -386,6 +396,7 @@ static struct attribute *net_class_attrs[] = {
 	&dev_attr_duplex.attr,
 	&dev_attr_dormant.attr,
 	&dev_attr_operstate.attr,
+	&dev_attr_carrier_changes.attr,
 	&dev_attr_ifalias.attr,
 	&dev_attr_carrier.attr,
 	&dev_attr_mtu.attr,
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e7c6006bc3ea..d4ff41739b0f 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -822,6 +822,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(4) /* IFLA_NUM_RX_QUEUES */
 	       + nla_total_size(1) /* IFLA_OPERSTATE */
 	       + nla_total_size(1) /* IFLA_LINKMODE */
+	       + nla_total_size(4) /* IFLA_CARRIER_CHANGES */
 	       + nla_total_size(ext_filter_mask
 			        & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */
 	       + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */
@@ -970,7 +971,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 	    (dev->qdisc &&
 	     nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) ||
 	    (dev->ifalias &&
-	     nla_put_string(skb, IFLA_IFALIAS, dev->ifalias)))
+	     nla_put_string(skb, IFLA_IFALIAS, dev->ifalias)) ||
+	    nla_put_u32(skb, IFLA_CARRIER_CHANGES,
+			atomic_read(&dev->carrier_changes)))
 		goto nla_put_failure;
 
 	if (1) {
@@ -1147,6 +1150,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_NUM_TX_QUEUES]	= { .type = NLA_U32 },
 	[IFLA_NUM_RX_QUEUES]	= { .type = NLA_U32 },
 	[IFLA_PHYS_PORT_ID]	= { .type = NLA_BINARY, .len = MAX_PHYS_PORT_ID_LEN },
+	[IFLA_CARRIER_CHANGES]	= { .type = NLA_U32 },  /* ignored */
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index e82e43b69c33..e1543b03e39d 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -310,6 +310,7 @@ void netif_carrier_on(struct net_device *dev)
 	if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state)) {
 		if (dev->reg_state == NETREG_UNINITIALIZED)
 			return;
+		atomic_inc(&dev->carrier_changes);
 		linkwatch_fire_event(dev);
 		if (netif_running(dev))
 			__netdev_watchdog_up(dev);
@@ -328,6 +329,7 @@ void netif_carrier_off(struct net_device *dev)
 	if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state)) {
 		if (dev->reg_state == NETREG_UNINITIALIZED)
 			return;
+		atomic_inc(&dev->carrier_changes);
 		linkwatch_fire_event(dev);
 	}
 }
-- 
cgit v1.2.3


From a50e233c50dbc881abaa0e4070789064e8d12d70 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 29 Mar 2014 21:28:21 -0700
Subject: net-gro: restore frag0 optimization

Main difference between napi_frags_skb() and napi_gro_receive() is that
the later is called while ethernet header was already pulled by the NIC
driver (eth_type_trans() was called before napi_gro_receive())

Jerry Chu in commit 299603e8370a ("net-gro: Prepare GRO stack for the
upcoming tunneling support") tried to remove this difference by calling
eth_type_trans() from napi_frags_skb() instead of doing this later from
napi_frags_finish()

Goal was that napi_gro_complete() could call
ptype->callbacks.gro_complete(skb, 0)  (offset of first network header =
0)

Also, xxx_gro_receive() handlers all use off = skb_gro_offset(skb) to
point to their own header, for the current skb and ones held in gro_list

Problem is this cleanup work defeated the frag0 optimization:
It turns out the consecutive pskb_may_pull() calls are too expensive.

This patch brings back the frag0 stuff in napi_frags_skb().

As all skb have their mac header in skb head, we no longer need
skb_gro_mac_header()

Reported-by: Michal Schmidt <mschmidt@redhat.com>
Fixes: 299603e8370a ("net-gro: Prepare GRO stack for the upcoming tunneling support")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jerry Chu <hkchu@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  5 ---
 net/core/dev.c            | 96 +++++++++++++++++++++++++++++++----------------
 2 files changed, 64 insertions(+), 37 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 45537ed7a5b3..775cc956ff78 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2014,11 +2014,6 @@ static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen,
 	return skb->data + offset;
 }
 
-static inline void *skb_gro_mac_header(struct sk_buff *skb)
-{
-	return NAPI_GRO_CB(skb)->frag0 ?: skb_mac_header(skb);
-}
-
 static inline void *skb_gro_network_header(struct sk_buff *skb)
 {
 	return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) +
diff --git a/net/core/dev.c b/net/core/dev.c
index a923eed976ae..48d81e4a256e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3833,10 +3833,10 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb)
 		diffs |= p->vlan_tci ^ skb->vlan_tci;
 		if (maclen == ETH_HLEN)
 			diffs |= compare_ether_header(skb_mac_header(p),
-						      skb_gro_mac_header(skb));
+						      skb_mac_header(skb));
 		else if (!diffs)
 			diffs = memcmp(skb_mac_header(p),
-				       skb_gro_mac_header(skb),
+				       skb_mac_header(skb),
 				       maclen);
 		NAPI_GRO_CB(p)->same_flow = !diffs;
 	}
@@ -3859,6 +3859,27 @@ static void skb_gro_reset_offset(struct sk_buff *skb)
 	}
 }
 
+static void gro_pull_from_frag0(struct sk_buff *skb, int grow)
+{
+	struct skb_shared_info *pinfo = skb_shinfo(skb);
+
+	BUG_ON(skb->end - skb->tail < grow);
+
+	memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow);
+
+	skb->data_len -= grow;
+	skb->tail += grow;
+
+	pinfo->frags[0].page_offset += grow;
+	skb_frag_size_sub(&pinfo->frags[0], grow);
+
+	if (unlikely(!skb_frag_size(&pinfo->frags[0]))) {
+		skb_frag_unref(skb, 0);
+		memmove(pinfo->frags, pinfo->frags + 1,
+			--pinfo->nr_frags * sizeof(pinfo->frags[0]));
+	}
+}
+
 static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
 	struct sk_buff **pp = NULL;
@@ -3867,6 +3888,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	struct list_head *head = &offload_base;
 	int same_flow;
 	enum gro_result ret;
+	int grow;
 
 	if (!(skb->dev->features & NETIF_F_GRO))
 		goto normal;
@@ -3874,7 +3896,6 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	if (skb_is_gso(skb) || skb_has_frag_list(skb))
 		goto normal;
 
-	skb_gro_reset_offset(skb);
 	gro_list_prepare(napi, skb);
 	NAPI_GRO_CB(skb)->csum = skb->csum; /* Needed for CHECKSUM_COMPLETE */
 
@@ -3938,27 +3959,9 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	ret = GRO_HELD;
 
 pull:
-	if (skb_headlen(skb) < skb_gro_offset(skb)) {
-		int grow = skb_gro_offset(skb) - skb_headlen(skb);
-
-		BUG_ON(skb->end - skb->tail < grow);
-
-		memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow);
-
-		skb->tail += grow;
-		skb->data_len -= grow;
-
-		skb_shinfo(skb)->frags[0].page_offset += grow;
-		skb_frag_size_sub(&skb_shinfo(skb)->frags[0], grow);
-
-		if (unlikely(!skb_frag_size(&skb_shinfo(skb)->frags[0]))) {
-			skb_frag_unref(skb, 0);
-			memmove(skb_shinfo(skb)->frags,
-				skb_shinfo(skb)->frags + 1,
-				--skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t));
-		}
-	}
-
+	grow = skb_gro_offset(skb) - skb_headlen(skb);
+	if (grow > 0)
+		gro_pull_from_frag0(skb, grow);
 ok:
 	return ret;
 
@@ -4026,6 +4029,8 @@ gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
 	trace_napi_gro_receive_entry(skb);
 
+	skb_gro_reset_offset(skb);
+
 	return napi_skb_finish(dev_gro_receive(napi, skb), skb);
 }
 EXPORT_SYMBOL(napi_gro_receive);
@@ -4054,12 +4059,16 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi)
 }
 EXPORT_SYMBOL(napi_get_frags);
 
-static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb,
-			       gro_result_t ret)
+static gro_result_t napi_frags_finish(struct napi_struct *napi,
+				      struct sk_buff *skb,
+				      gro_result_t ret)
 {
 	switch (ret) {
 	case GRO_NORMAL:
-		if (netif_receive_skb_internal(skb))
+	case GRO_HELD:
+		__skb_push(skb, ETH_HLEN);
+		skb->protocol = eth_type_trans(skb, skb->dev);
+		if (ret == GRO_NORMAL && netif_receive_skb_internal(skb))
 			ret = GRO_DROP;
 		break;
 
@@ -4068,7 +4077,6 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *
 		napi_reuse_skb(napi, skb);
 		break;
 
-	case GRO_HELD:
 	case GRO_MERGED:
 		break;
 	}
@@ -4076,17 +4084,41 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *
 	return ret;
 }
 
+/* Upper GRO stack assumes network header starts at gro_offset=0
+ * Drivers could call both napi_gro_frags() and napi_gro_receive()
+ * We copy ethernet header into skb->data to have a common layout.
+ */
 static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
 {
 	struct sk_buff *skb = napi->skb;
+	const struct ethhdr *eth;
+	unsigned int hlen = sizeof(*eth);
 
 	napi->skb = NULL;
 
-	if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr)))) {
-		napi_reuse_skb(napi, skb);
-		return NULL;
+	skb_reset_mac_header(skb);
+	skb_gro_reset_offset(skb);
+
+	eth = skb_gro_header_fast(skb, 0);
+	if (unlikely(skb_gro_header_hard(skb, hlen))) {
+		eth = skb_gro_header_slow(skb, hlen, 0);
+		if (unlikely(!eth)) {
+			napi_reuse_skb(napi, skb);
+			return NULL;
+		}
+	} else {
+		gro_pull_from_frag0(skb, hlen);
+		NAPI_GRO_CB(skb)->frag0 += hlen;
+		NAPI_GRO_CB(skb)->frag0_len -= hlen;
 	}
-	skb->protocol = eth_type_trans(skb, skb->dev);
+	__skb_pull(skb, hlen);
+
+	/*
+	 * This works because the only protocols we care about don't require
+	 * special handling.
+	 * We'll fix it up properly in napi_frags_finish()
+	 */
+	skb->protocol = eth->h_proto;
 
 	return skb;
 }
-- 
cgit v1.2.3


From 3064639423c48d6e0eb9ecc27c512a58e38c6c57 Mon Sep 17 00:00:00 2001
From: Stanislav Kinsbursky <skinsbursky@parallels.com>
Date: Wed, 26 Feb 2014 16:50:01 +0300
Subject: nfsd: check passed socket's net matches NFSd superblock's one

There could be a case, when NFSd file system is mounted in network, different
to socket's one, like below:

"ip netns exec" creates new network and mount namespace, which duplicates NFSd
mount point, created in init_net context. And thus NFS server stop in nested
network context leads to RPCBIND client destruction in init_net.
Then, on NFSd start in nested network context, rpc.nfsd process creates socket
in nested net and passes it into "write_ports", which leads to RPCBIND sockets
creation in init_net context because of the same reason (NFSd monut point was
created in init_net context). An attempt to register passed socket in nested
net leads to panic, because no RPCBIND client present in nexted network
namespace.

This patch add check that passed socket's net matches NFSd superblock's one.
And returns -EINVAL error to user psace otherwise.

v2: Put socket on exit.

Reported-by: Weng Meiling <wengmeiling.weng@huawei.com>
Signed-off-by: Stanislav Kinsbursky <skinsbursky@parallels.com>
Cc: stable@vger.kernel.org
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/nfsd/nfsctl.c               |  5 +++++
 include/linux/sunrpc/svcsock.h |  1 +
 net/sunrpc/svcsock.c           | 16 ++++++++++++++++
 3 files changed, 22 insertions(+)

(limited to 'include/linux')

diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 7f555179bf81..f34d9de802ab 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -699,6 +699,11 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net)
 	if (err != 0 || fd < 0)
 		return -EINVAL;
 
+	if (svc_alien_sock(net, fd)) {
+		printk(KERN_ERR "%s: socket net is different to NFSd's one\n", __func__);
+		return -EINVAL;
+	}
+
 	err = nfsd_create_serv(net);
 	if (err != 0)
 		return err;
diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h
index 62fd1b756e99..947009ed5996 100644
--- a/include/linux/sunrpc/svcsock.h
+++ b/include/linux/sunrpc/svcsock.h
@@ -56,6 +56,7 @@ int		svc_recv(struct svc_rqst *, long);
 int		svc_send(struct svc_rqst *);
 void		svc_drop(struct svc_rqst *);
 void		svc_sock_update_bufs(struct svc_serv *serv);
+bool		svc_alien_sock(struct net *net, int fd);
 int		svc_addsock(struct svc_serv *serv, const int fd,
 					char *name_return, const size_t len);
 void		svc_init_xprt_sock(void);
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index b6e59f0a9475..d06cb8752dcd 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1397,6 +1397,22 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 	return svsk;
 }
 
+bool svc_alien_sock(struct net *net, int fd)
+{
+	int err;
+	struct socket *sock = sockfd_lookup(fd, &err);
+	bool ret = false;
+
+	if (!sock)
+		goto out;
+	if (sock_net(sock->sk) != net)
+		ret = true;
+	sockfd_put(sock);
+out:
+	return ret;
+}
+EXPORT_SYMBOL_GPL(svc_alien_sock);
+
 /**
  * svc_addsock - add a listener socket to an RPC service
  * @serv: pointer to RPC service to which to add a new listener
-- 
cgit v1.2.3


From 24f870d8f0adcd38639f2f66e37aa7591a3fc408 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Wed, 12 Mar 2014 17:06:19 +0900
Subject: slab: fix wrongly used macro

commit 'slab: restrict the number of objects in a slab' uses
__builtin_constant_p() on #if macro. It is wrong usage of builtin
function, but it is compiled on x86 without any problem, so I can't
find it before 0 day build system find it.

This commit fixes the situation by using KMALLOC_MIN_SIZE, instead of
KMALLOC_SHIFT_LOW. KMALLOC_SHIFT_LOW is parsed to ilog2() on some
architecture and this ilog2() uses __builtin_constant_p() and results in
the problem. This problem would disappear by using KMALLOC_MIN_SIZE,
since it is just constant.

Tested-by: David Rientjes <rientjes@google.com>
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
---
 include/linux/slab.h | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/slab.h b/include/linux/slab.h
index d015dec02bf3..5df89f777a54 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -201,17 +201,6 @@ struct kmem_cache {
 #ifndef KMALLOC_SHIFT_LOW
 #define KMALLOC_SHIFT_LOW	5
 #endif
-
-/*
- * This restriction comes from byte sized index implementation.
- * Page size is normally 2^12 bytes and, in this case, if we want to use
- * byte sized index which can represent 2^8 entries, the size of the object
- * should be equal or greater to 2^12 / 2^8 = 2^4 = 16.
- * If minimum size of kmalloc is less than 16, we use it as minimum object
- * size and give up to use byte sized index.
- */
-#define SLAB_OBJ_MIN_SIZE	(KMALLOC_SHIFT_LOW < 4 ? \
-				(1 << KMALLOC_SHIFT_LOW) : 16)
 #endif
 
 #ifdef CONFIG_SLUB
@@ -253,6 +242,17 @@ struct kmem_cache {
 #define KMALLOC_MIN_SIZE (1 << KMALLOC_SHIFT_LOW)
 #endif
 
+/*
+ * This restriction comes from byte sized index implementation.
+ * Page size is normally 2^12 bytes and, in this case, if we want to use
+ * byte sized index which can represent 2^8 entries, the size of the object
+ * should be equal or greater to 2^12 / 2^8 = 2^4 = 16.
+ * If minimum size of kmalloc is less than 16, we use it as minimum object
+ * size and give up to use byte sized index.
+ */
+#define SLAB_OBJ_MIN_SIZE      (KMALLOC_MIN_SIZE < 16 ? \
+                               (KMALLOC_MIN_SIZE) : 16)
+
 #ifndef CONFIG_SLOB
 extern struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1];
 #ifdef CONFIG_ZONE_DMA
-- 
cgit v1.2.3


From 44b1d53043c482225196e8a9cd9f35163a1b3336 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@suse.cz>
Date: Tue, 1 Apr 2014 17:08:41 +0200
Subject: vfs: add d_is_dir()

Add d_is_dir(dentry) helper which is analogous to S_ISDIR().

To avoid confusion, rename d_is_directory() to d_can_lookup().

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Reviewed-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/namei.c             | 23 +++++++++++------------
 include/linux/dcache.h |  7 ++++++-
 2 files changed, 17 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/fs/namei.c b/fs/namei.c
index 4b491b431990..e987ea7c305f 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1796,7 +1796,7 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 			if (err)
 				return err;
 		}
-		if (!d_is_directory(nd->path.dentry)) {
+		if (!d_can_lookup(nd->path.dentry)) {
 			err = -ENOTDIR; 
 			break;
 		}
@@ -1817,7 +1817,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 		struct dentry *root = nd->root.dentry;
 		struct inode *inode = root->d_inode;
 		if (*name) {
-			if (!d_is_directory(root))
+			if (!d_can_lookup(root))
 				return -ENOTDIR;
 			retval = inode_permission(inode, MAY_EXEC);
 			if (retval)
@@ -1873,7 +1873,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 		dentry = f.file->f_path.dentry;
 
 		if (*name) {
-			if (!d_is_directory(dentry)) {
+			if (!d_can_lookup(dentry)) {
 				fdput(f);
 				return -ENOTDIR;
 			}
@@ -1955,7 +1955,7 @@ static int path_lookupat(int dfd, const char *name,
 		err = complete_walk(nd);
 
 	if (!err && nd->flags & LOOKUP_DIRECTORY) {
-		if (!d_is_directory(nd->path.dentry)) {
+		if (!d_can_lookup(nd->path.dentry)) {
 			path_put(&nd->path);
 			err = -ENOTDIR;
 		}
@@ -2414,11 +2414,11 @@ static int may_delete(struct inode *dir, struct dentry *victim, bool isdir)
 	    IS_IMMUTABLE(inode) || IS_SWAPFILE(inode))
 		return -EPERM;
 	if (isdir) {
-		if (!d_is_directory(victim) && !d_is_autodir(victim))
+		if (!d_is_dir(victim))
 			return -ENOTDIR;
 		if (IS_ROOT(victim))
 			return -EBUSY;
-	} else if (d_is_directory(victim) || d_is_autodir(victim))
+	} else if (d_is_dir(victim))
 		return -EISDIR;
 	if (IS_DEADDIR(dir))
 		return -ENOENT;
@@ -3016,11 +3016,10 @@ finish_open:
 	}
 	audit_inode(name, nd->path.dentry, 0);
 	error = -EISDIR;
-	if ((open_flag & O_CREAT) &&
-	    (d_is_directory(nd->path.dentry) || d_is_autodir(nd->path.dentry)))
+	if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry))
 		goto out;
 	error = -ENOTDIR;
-	if ((nd->flags & LOOKUP_DIRECTORY) && !d_is_directory(nd->path.dentry))
+	if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry))
 		goto out;
 	if (!S_ISREG(nd->inode->i_mode))
 		will_truncate = false;
@@ -3744,7 +3743,7 @@ exit1:
 slashes:
 	if (d_is_negative(dentry))
 		error = -ENOENT;
-	else if (d_is_directory(dentry) || d_is_autodir(dentry))
+	else if (d_is_dir(dentry))
 		error = -EISDIR;
 	else
 		error = -ENOTDIR;
@@ -4123,7 +4122,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	       struct inode **delegated_inode)
 {
 	int error;
-	int is_dir = d_is_directory(old_dentry) || d_is_autodir(old_dentry);
+	int is_dir = d_is_dir(old_dentry);
 	const unsigned char *old_name;
 
 	if (old_dentry->d_inode == new_dentry->d_inode)
@@ -4216,7 +4215,7 @@ retry_deleg:
 	if (d_is_negative(old_dentry))
 		goto exit4;
 	/* unless the source is a directory trailing slashes give -ENOTDIR */
-	if (!d_is_directory(old_dentry) && !d_is_autodir(old_dentry)) {
+	if (!d_is_dir(old_dentry)) {
 		error = -ENOTDIR;
 		if (oldnd.last.name[oldnd.last.len])
 			goto exit4;
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index bf72e9ac6de0..3b50cac7ccb3 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -429,7 +429,7 @@ static inline unsigned __d_entry_type(const struct dentry *dentry)
 	return dentry->d_flags & DCACHE_ENTRY_TYPE;
 }
 
-static inline bool d_is_directory(const struct dentry *dentry)
+static inline bool d_can_lookup(const struct dentry *dentry)
 {
 	return __d_entry_type(dentry) == DCACHE_DIRECTORY_TYPE;
 }
@@ -439,6 +439,11 @@ static inline bool d_is_autodir(const struct dentry *dentry)
 	return __d_entry_type(dentry) == DCACHE_AUTODIR_TYPE;
 }
 
+static inline bool d_is_dir(const struct dentry *dentry)
+{
+	return d_can_lookup(dentry) || d_is_autodir(dentry);
+}
+
 static inline bool d_is_symlink(const struct dentry *dentry)
 {
 	return __d_entry_type(dentry) == DCACHE_SYMLINK_TYPE;
-- 
cgit v1.2.3


From 520c8b16505236fc82daa352e6c5e73cd9870cff Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@suse.cz>
Date: Tue, 1 Apr 2014 17:08:42 +0200
Subject: vfs: add renameat2 syscall

Add new renameat2 syscall, which is the same as renameat with an added
flags argument.

Pass flags to vfs_rename() and to i_op->rename() as well.

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Reviewed-by: J. Bruce Fields <bfields@redhat.com>
---
 Documentation/filesystems/Locking                  |  6 +++-
 Documentation/filesystems/vfs.txt                  | 16 ++++++++++
 arch/x86/syscalls/syscall_64.tbl                   |  1 +
 .../lustre/lustre/include/linux/lustre_compat25.h  |  4 +--
 drivers/staging/lustre/lustre/lvfs/lvfs_linux.c    |  2 +-
 fs/cachefiles/namei.c                              |  2 +-
 fs/ecryptfs/inode.c                                |  2 +-
 fs/namei.c                                         | 34 +++++++++++++++++-----
 fs/nfsd/vfs.c                                      |  2 +-
 include/linux/fs.h                                 |  4 ++-
 10 files changed, 58 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 5b0c083d7c0e..f424e0e5b46b 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -47,6 +47,8 @@ prototypes:
 	int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
 	int (*rename) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *);
+	int (*rename2) (struct inode *, struct dentry *,
+			struct inode *, struct dentry *, unsigned int);
 	int (*readlink) (struct dentry *, char __user *,int);
 	void * (*follow_link) (struct dentry *, struct nameidata *);
 	void (*put_link) (struct dentry *, struct nameidata *, void *);
@@ -78,6 +80,7 @@ mkdir:		yes
 unlink:		yes (both)
 rmdir:		yes (both)	(see below)
 rename:		yes (all)	(see below)
+rename2:	yes (all)	(see below)
 readlink:	no
 follow_link:	no
 put_link:	no
@@ -96,7 +99,8 @@ tmpfile:	no
 
 	Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
 victim.
-	cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem.
+	cross-directory ->rename() and rename2() has (per-superblock)
+->s_vfs_rename_sem.
 
 See Documentation/filesystems/directory-locking for more detailed discussion
 of the locking scheme for directory operations.
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index c53784c119c8..94eb86287bcb 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -347,6 +347,8 @@ struct inode_operations {
 	int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
 	int (*rename) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *);
+	int (*rename2) (struct inode *, struct dentry *,
+			struct inode *, struct dentry *, unsigned int);
 	int (*readlink) (struct dentry *, char __user *,int);
         void * (*follow_link) (struct dentry *, struct nameidata *);
         void (*put_link) (struct dentry *, struct nameidata *, void *);
@@ -414,6 +416,20 @@ otherwise noted.
   rename: called by the rename(2) system call to rename the object to
 	have the parent and name given by the second inode and dentry.
 
+  rename2: this has an additional flags argument compared to rename.
+	If no flags are supported by the filesystem then this method
+	need not be implemented.  If some flags are supported then the
+	filesystem must return -EINVAL for any unsupported or unknown
+	flags.  Currently the following flags are implemented:
+	(1) RENAME_NOREPLACE: this flag indicates that if the target
+	of the rename exists the rename should fail with -EEXIST
+	instead of replacing the target.  The VFS already checks for
+	existence, so for local filesystems the RENAME_NOREPLACE
+	implementation is equivalent to plain rename.
+	(2) RENAME_EXCHANGE: exchange source and target.  Both must
+	exist; this is checked by the VFS.  Unlike plain rename,
+	source and target may be of different type.
+
   readlink: called by the readlink(2) system call. Only required if
 	you want to support reading symbolic links
 
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index a12bddc7ccea..04376ac3d9ef 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -322,6 +322,7 @@
 313	common	finit_module		sys_finit_module
 314	common	sched_setattr		sys_sched_setattr
 315	common	sched_getattr		sys_sched_getattr
+316	common	renameat2		sys_renameat2
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h b/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h
index eefdb8d061b1..81cc7a0134bb 100644
--- a/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h
+++ b/drivers/staging/lustre/lustre/include/linux/lustre_compat25.h
@@ -105,8 +105,8 @@ static inline void ll_set_fs_pwd(struct fs_struct *fs, struct vfsmount *mnt,
 #define ll_vfs_unlink(inode,entry,mnt)	  vfs_unlink(inode,entry)
 #define ll_vfs_mknod(dir,entry,mnt,mode,dev)    vfs_mknod(dir,entry,mode,dev)
 #define ll_security_inode_unlink(dir,entry,mnt) security_inode_unlink(dir,entry)
-#define ll_vfs_rename(old,old_dir,mnt,new,new_dir,mnt1,delegated_inode) \
-		vfs_rename(old,old_dir,new,new_dir,delegated_inode)
+#define ll_vfs_rename(old, old_dir, mnt, new, new_dir, mnt1) \
+		vfs_rename(old, old_dir, new, new_dir, NULL, 0)
 
 #define cfs_bio_io_error(a,b)   bio_io_error((a))
 #define cfs_bio_endio(a,b,c)    bio_endio((a),(c))
diff --git a/drivers/staging/lustre/lustre/lvfs/lvfs_linux.c b/drivers/staging/lustre/lustre/lvfs/lvfs_linux.c
index 428ffd8c37b7..d50822be3230 100644
--- a/drivers/staging/lustre/lustre/lvfs/lvfs_linux.c
+++ b/drivers/staging/lustre/lustre/lvfs/lvfs_linux.c
@@ -223,7 +223,7 @@ int lustre_rename(struct dentry *dir, struct vfsmount *mnt,
 		GOTO(put_old, err = PTR_ERR(dchild_new));
 
 	err = ll_vfs_rename(dir->d_inode, dchild_old, mnt,
-			    dir->d_inode, dchild_new, mnt, NULL);
+			    dir->d_inode, dchild_new, mnt);
 
 	dput(dchild_new);
 put_old:
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index ca65f39dc8dc..31088a969351 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -396,7 +396,7 @@ try_again:
 		cachefiles_io_error(cache, "Rename security error %d", ret);
 	} else {
 		ret = vfs_rename(dir->d_inode, rep,
-				 cache->graveyard->d_inode, grave, NULL);
+				 cache->graveyard->d_inode, grave, NULL, 0);
 		if (ret != 0 && ret != -ENOMEM)
 			cachefiles_io_error(cache,
 					    "Rename failed with error %d", ret);
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index b167ca48b8ee..d4a9431ec73c 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -641,7 +641,7 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	}
 	rc = vfs_rename(lower_old_dir_dentry->d_inode, lower_old_dentry,
 			lower_new_dir_dentry->d_inode, lower_new_dentry,
-			NULL);
+			NULL, 0);
 	if (rc)
 		goto out_lock;
 	if (target_inode)
diff --git a/fs/namei.c b/fs/namei.c
index 12b8f56ba942..ab4e48c4a80a 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3980,6 +3980,7 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
  * @new_dir:	parent of destination
  * @new_dentry:	destination
  * @delegated_inode: returns an inode needing a delegation break
+ * @flags:	rename flags
  *
  * The caller must hold multiple mutexes--see lock_rename()).
  *
@@ -4023,7 +4024,7 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
  */
 int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	       struct inode *new_dir, struct dentry *new_dentry,
-	       struct inode **delegated_inode)
+	       struct inode **delegated_inode, unsigned int flags)
 {
 	int error;
 	bool is_dir = d_is_dir(old_dentry);
@@ -4048,6 +4049,9 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (!old_dir->i_op->rename)
 		return -EPERM;
 
+	if (flags && !old_dir->i_op->rename2)
+		return -EINVAL;
+
 	/*
 	 * If we are going to change the parent - check write permissions,
 	 * we'll need to flip '..'.
@@ -4093,7 +4097,13 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 				goto out;
 		}
 	}
-	error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
+	if (!flags) {
+		error = old_dir->i_op->rename(old_dir, old_dentry,
+					      new_dir, new_dentry);
+	} else {
+		error = old_dir->i_op->rename2(old_dir, old_dentry,
+					       new_dir, new_dentry, flags);
+	}
 	if (error)
 		goto out;
 
@@ -4118,8 +4128,8 @@ out:
 	return error;
 }
 
-SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
-		int, newdfd, const char __user *, newname)
+SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
+		int, newdfd, const char __user *, newname, unsigned int, flags)
 {
 	struct dentry *old_dir, *new_dir;
 	struct dentry *old_dentry, *new_dentry;
@@ -4131,6 +4141,10 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
 	unsigned int lookup_flags = 0;
 	bool should_retry = false;
 	int error;
+
+	if (flags)
+		return -EINVAL;
+
 retry:
 	from = user_path_parent(olddfd, oldname, &oldnd, lookup_flags);
 	if (IS_ERR(from)) {
@@ -4202,8 +4216,8 @@ retry_deleg:
 	if (error)
 		goto exit5;
 	error = vfs_rename(old_dir->d_inode, old_dentry,
-				   new_dir->d_inode, new_dentry,
-				   &delegated_inode);
+			   new_dir->d_inode, new_dentry,
+			   &delegated_inode, flags);
 exit5:
 	dput(new_dentry);
 exit4:
@@ -4233,9 +4247,15 @@ exit:
 	return error;
 }
 
+SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
+		int, newdfd, const char __user *, newname)
+{
+	return sys_renameat2(olddfd, oldname, newdfd, newname, 0);
+}
+
 SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname)
 {
-	return sys_renameat(AT_FDCWD, oldname, AT_FDCWD, newname);
+	return sys_renameat2(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
 }
 
 int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen, const char *link)
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 6d7be3f80356..915808b36df7 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1694,7 +1694,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 	if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry)
 		goto out_dput_new;
 
-	host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL);
+	host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL, 0);
 	if (!host_err) {
 		host_err = commit_metadata(tfhp);
 		if (!host_err)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 23b2a35d712e..3b3670e97da6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1460,7 +1460,7 @@ extern int vfs_symlink(struct inode *, struct dentry *, const char *);
 extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **);
 extern int vfs_rmdir(struct inode *, struct dentry *);
 extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
-extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **);
+extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int);
 
 /*
  * VFS dentry helper functions.
@@ -1571,6 +1571,8 @@ struct inode_operations {
 	int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t);
 	int (*rename) (struct inode *, struct dentry *,
 			struct inode *, struct dentry *);
+	int (*rename2) (struct inode *, struct dentry *,
+			struct inode *, struct dentry *, unsigned int);
 	int (*setattr) (struct dentry *, struct iattr *);
 	int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
 	int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
-- 
cgit v1.2.3


From 0b3974eb04c4874e85fa1d4fc70450d12f28611d Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@suse.cz>
Date: Tue, 1 Apr 2014 17:08:43 +0200
Subject: security: add flags to rename hooks

Add flags to security_path_rename() and security_inode_rename() hooks.

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Reviewed-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/cachefiles/namei.c    |  2 +-
 fs/namei.c               |  5 +++--
 include/linux/security.h | 12 ++++++++----
 security/security.c      |  6 ++++--
 4 files changed, 16 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index 31088a969351..6494d9f673aa 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -391,7 +391,7 @@ try_again:
 	path.dentry = dir;
 	path_to_graveyard.mnt = cache->mnt;
 	path_to_graveyard.dentry = cache->graveyard;
-	ret = security_path_rename(&path, rep, &path_to_graveyard, grave);
+	ret = security_path_rename(&path, rep, &path_to_graveyard, grave, 0);
 	if (ret < 0) {
 		cachefiles_io_error(cache, "Rename security error %d", ret);
 	} else {
diff --git a/fs/namei.c b/fs/namei.c
index 0e9d186b7f77..4096d589bb3f 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -4062,7 +4062,8 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			return error;
 	}
 
-	error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry);
+	error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry,
+				      flags);
 	if (error)
 		return error;
 
@@ -4217,7 +4218,7 @@ retry_deleg:
 		goto exit5;
 
 	error = security_path_rename(&oldnd.path, old_dentry,
-				     &newnd.path, new_dentry);
+				     &newnd.path, new_dentry, flags);
 	if (error)
 		goto exit5;
 	error = vfs_rename(old_dir->d_inode, old_dentry,
diff --git a/include/linux/security.h b/include/linux/security.h
index 2fc42d191f79..6478ce3252c7 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1793,7 +1793,8 @@ int security_inode_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 int security_inode_rmdir(struct inode *dir, struct dentry *dentry);
 int security_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev);
 int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry,
-			  struct inode *new_dir, struct dentry *new_dentry);
+			  struct inode *new_dir, struct dentry *new_dentry,
+			  unsigned int flags);
 int security_inode_readlink(struct dentry *dentry);
 int security_inode_follow_link(struct dentry *dentry, struct nameidata *nd);
 int security_inode_permission(struct inode *inode, int mask);
@@ -2161,7 +2162,8 @@ static inline int security_inode_mknod(struct inode *dir,
 static inline int security_inode_rename(struct inode *old_dir,
 					 struct dentry *old_dentry,
 					 struct inode *new_dir,
-					 struct dentry *new_dentry)
+					 struct dentry *new_dentry,
+					 unsigned int flags)
 {
 	return 0;
 }
@@ -2955,7 +2957,8 @@ int security_path_symlink(struct path *dir, struct dentry *dentry,
 int security_path_link(struct dentry *old_dentry, struct path *new_dir,
 		       struct dentry *new_dentry);
 int security_path_rename(struct path *old_dir, struct dentry *old_dentry,
-			 struct path *new_dir, struct dentry *new_dentry);
+			 struct path *new_dir, struct dentry *new_dentry,
+			 unsigned int flags);
 int security_path_chmod(struct path *path, umode_t mode);
 int security_path_chown(struct path *path, kuid_t uid, kgid_t gid);
 int security_path_chroot(struct path *path);
@@ -3003,7 +3006,8 @@ static inline int security_path_link(struct dentry *old_dentry,
 static inline int security_path_rename(struct path *old_dir,
 				       struct dentry *old_dentry,
 				       struct path *new_dir,
-				       struct dentry *new_dentry)
+				       struct dentry *new_dentry,
+				       unsigned int flags)
 {
 	return 0;
 }
diff --git a/security/security.c b/security/security.c
index 919cad93ac82..284fbc99aa9d 100644
--- a/security/security.c
+++ b/security/security.c
@@ -433,7 +433,8 @@ int security_path_link(struct dentry *old_dentry, struct path *new_dir,
 }
 
 int security_path_rename(struct path *old_dir, struct dentry *old_dentry,
-			 struct path *new_dir, struct dentry *new_dentry)
+			 struct path *new_dir, struct dentry *new_dentry,
+			 unsigned int flags)
 {
 	if (unlikely(IS_PRIVATE(old_dentry->d_inode) ||
 		     (new_dentry->d_inode && IS_PRIVATE(new_dentry->d_inode))))
@@ -524,7 +525,8 @@ int security_inode_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
 }
 
 int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry,
-			   struct inode *new_dir, struct dentry *new_dentry)
+			   struct inode *new_dir, struct dentry *new_dentry,
+			   unsigned int flags)
 {
         if (unlikely(IS_PRIVATE(old_dentry->d_inode) ||
             (new_dentry->d_inode && IS_PRIVATE(new_dentry->d_inode))))
-- 
cgit v1.2.3


From da1ce0670c14d8380e423a3239e562a1dc15fa9e Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@suse.cz>
Date: Tue, 1 Apr 2014 17:08:43 +0200
Subject: vfs: add cross-rename

If flags contain RENAME_EXCHANGE then exchange source and destination files.
There's no restriction on the type of the files; e.g. a directory can be
exchanged with a symlink.

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: J. Bruce Fields <bfields@redhat.com>
---
 fs/dcache.c             |  50 ++++++++++++++++++-----
 fs/namei.c              | 104 +++++++++++++++++++++++++++++++++---------------
 include/linux/dcache.h  |   1 +
 include/uapi/linux/fs.h |   1 +
 security/security.c     |  16 ++++++++
 5 files changed, 131 insertions(+), 41 deletions(-)

(limited to 'include/linux')

diff --git a/fs/dcache.c b/fs/dcache.c
index ca02c13a84aa..66cba5a8a346 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2483,12 +2483,14 @@ static void switch_names(struct dentry *dentry, struct dentry *target)
 			dentry->d_name.name = dentry->d_iname;
 		} else {
 			/*
-			 * Both are internal.  Just copy target to dentry
+			 * Both are internal.
 			 */
-			memcpy(dentry->d_iname, target->d_name.name,
-					target->d_name.len + 1);
-			dentry->d_name.len = target->d_name.len;
-			return;
+			unsigned int i;
+			BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long)));
+			for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) {
+				swap(((long *) &dentry->d_iname)[i],
+				     ((long *) &target->d_iname)[i]);
+			}
 		}
 	}
 	swap(dentry->d_name.len, target->d_name.len);
@@ -2545,13 +2547,15 @@ static void dentry_unlock_parents_for_move(struct dentry *dentry,
  * __d_move - move a dentry
  * @dentry: entry to move
  * @target: new dentry
+ * @exchange: exchange the two dentries
  *
  * Update the dcache to reflect the move of a file name. Negative
  * dcache entries should not be moved in this way. Caller must hold
  * rename_lock, the i_mutex of the source and target directories,
  * and the sb->s_vfs_rename_mutex if they differ. See lock_rename().
  */
-static void __d_move(struct dentry * dentry, struct dentry * target)
+static void __d_move(struct dentry *dentry, struct dentry *target,
+		     bool exchange)
 {
 	if (!dentry->d_inode)
 		printk(KERN_WARNING "VFS: moving negative dcache entry\n");
@@ -2573,8 +2577,15 @@ static void __d_move(struct dentry * dentry, struct dentry * target)
 	__d_drop(dentry);
 	__d_rehash(dentry, d_hash(target->d_parent, target->d_name.hash));
 
-	/* Unhash the target: dput() will then get rid of it */
+	/*
+	 * Unhash the target (d_delete() is not usable here).  If exchanging
+	 * the two dentries, then rehash onto the other's hash queue.
+	 */
 	__d_drop(target);
+	if (exchange) {
+		__d_rehash(target,
+			   d_hash(dentry->d_parent, dentry->d_name.hash));
+	}
 
 	list_del(&dentry->d_u.d_child);
 	list_del(&target->d_u.d_child);
@@ -2601,6 +2612,8 @@ static void __d_move(struct dentry * dentry, struct dentry * target)
 	write_seqcount_end(&dentry->d_seq);
 
 	dentry_unlock_parents_for_move(dentry, target);
+	if (exchange)
+		fsnotify_d_move(target);
 	spin_unlock(&target->d_lock);
 	fsnotify_d_move(dentry);
 	spin_unlock(&dentry->d_lock);
@@ -2618,11 +2631,30 @@ static void __d_move(struct dentry * dentry, struct dentry * target)
 void d_move(struct dentry *dentry, struct dentry *target)
 {
 	write_seqlock(&rename_lock);
-	__d_move(dentry, target);
+	__d_move(dentry, target, false);
 	write_sequnlock(&rename_lock);
 }
 EXPORT_SYMBOL(d_move);
 
+/*
+ * d_exchange - exchange two dentries
+ * @dentry1: first dentry
+ * @dentry2: second dentry
+ */
+void d_exchange(struct dentry *dentry1, struct dentry *dentry2)
+{
+	write_seqlock(&rename_lock);
+
+	WARN_ON(!dentry1->d_inode);
+	WARN_ON(!dentry2->d_inode);
+	WARN_ON(IS_ROOT(dentry1));
+	WARN_ON(IS_ROOT(dentry2));
+
+	__d_move(dentry1, dentry2, true);
+
+	write_sequnlock(&rename_lock);
+}
+
 /**
  * d_ancestor - search for an ancestor
  * @p1: ancestor dentry
@@ -2670,7 +2702,7 @@ static struct dentry *__d_unalias(struct inode *inode,
 	m2 = &alias->d_parent->d_inode->i_mutex;
 out_unalias:
 	if (likely(!d_mountpoint(alias))) {
-		__d_move(alias, dentry);
+		__d_move(alias, dentry, false);
 		ret = alias;
 	}
 out_err:
diff --git a/fs/namei.c b/fs/namei.c
index 4096d589bb3f..c1178880f23c 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -4031,6 +4031,8 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	const unsigned char *old_name;
 	struct inode *source = old_dentry->d_inode;
 	struct inode *target = new_dentry->d_inode;
+	bool new_is_dir = false;
+	unsigned max_links = new_dir->i_sb->s_max_links;
 
 	if (source == target)
 		return 0;
@@ -4039,10 +4041,16 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (error)
 		return error;
 
-	if (!target)
+	if (!target) {
 		error = may_create(new_dir, new_dentry);
-	else
-		error = may_delete(new_dir, new_dentry, is_dir);
+	} else {
+		new_is_dir = d_is_dir(new_dentry);
+
+		if (!(flags & RENAME_EXCHANGE))
+			error = may_delete(new_dir, new_dentry, is_dir);
+		else
+			error = may_delete(new_dir, new_dentry, new_is_dir);
+	}
 	if (error)
 		return error;
 
@@ -4056,10 +4064,17 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	 * If we are going to change the parent - check write permissions,
 	 * we'll need to flip '..'.
 	 */
-	if (is_dir && new_dir != old_dir) {
-		error = inode_permission(source, MAY_WRITE);
-		if (error)
-			return error;
+	if (new_dir != old_dir) {
+		if (is_dir) {
+			error = inode_permission(source, MAY_WRITE);
+			if (error)
+				return error;
+		}
+		if ((flags & RENAME_EXCHANGE) && new_is_dir) {
+			error = inode_permission(target, MAY_WRITE);
+			if (error)
+				return error;
+		}
 	}
 
 	error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry,
@@ -4069,7 +4084,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	old_name = fsnotify_oldname_init(old_dentry->d_name.name);
 	dget(new_dentry);
-	if (!is_dir)
+	if (!is_dir || (flags & RENAME_EXCHANGE))
 		lock_two_nondirectories(source, target);
 	else if (target)
 		mutex_lock(&target->i_mutex);
@@ -4078,25 +4093,25 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (d_mountpoint(old_dentry) || d_mountpoint(new_dentry))
 		goto out;
 
-	if (is_dir) {
-		unsigned max_links = new_dir->i_sb->s_max_links;
-
+	if (max_links && new_dir != old_dir) {
 		error = -EMLINK;
-		if (max_links && !target && new_dir != old_dir &&
-		    new_dir->i_nlink >= max_links)
+		if (is_dir && !new_is_dir && new_dir->i_nlink >= max_links)
 			goto out;
-
-		if (target)
-			shrink_dcache_parent(new_dentry);
-	} else {
+		if ((flags & RENAME_EXCHANGE) && !is_dir && new_is_dir &&
+		    old_dir->i_nlink >= max_links)
+			goto out;
+	}
+	if (is_dir && !(flags & RENAME_EXCHANGE) && target)
+		shrink_dcache_parent(new_dentry);
+	if (!is_dir) {
 		error = try_break_deleg(source, delegated_inode);
 		if (error)
 			goto out;
-		if (target) {
-			error = try_break_deleg(target, delegated_inode);
-			if (error)
-				goto out;
-		}
+	}
+	if (target && !new_is_dir) {
+		error = try_break_deleg(target, delegated_inode);
+		if (error)
+			goto out;
 	}
 	if (!flags) {
 		error = old_dir->i_op->rename(old_dir, old_dentry,
@@ -4108,22 +4123,31 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (error)
 		goto out;
 
-	if (target) {
+	if (!(flags & RENAME_EXCHANGE) && target) {
 		if (is_dir)
 			target->i_flags |= S_DEAD;
 		dont_mount(new_dentry);
 	}
-	if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE))
-		d_move(old_dentry, new_dentry);
+	if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) {
+		if (!(flags & RENAME_EXCHANGE))
+			d_move(old_dentry, new_dentry);
+		else
+			d_exchange(old_dentry, new_dentry);
+	}
 out:
-	if (!is_dir)
+	if (!is_dir || (flags & RENAME_EXCHANGE))
 		unlock_two_nondirectories(source, target);
 	else if (target)
 		mutex_unlock(&target->i_mutex);
 	dput(new_dentry);
-	if (!error)
+	if (!error) {
 		fsnotify_move(old_dir, new_dir, old_name, is_dir,
-			      target, old_dentry);
+			      !(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry);
+		if (flags & RENAME_EXCHANGE) {
+			fsnotify_move(new_dir, old_dir, old_dentry->d_name.name,
+				      new_is_dir, NULL, new_dentry);
+		}
+	}
 	fsnotify_oldname_free(old_name);
 
 	return error;
@@ -4143,7 +4167,10 @@ SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname,
 	bool should_retry = false;
 	int error;
 
-	if (flags & ~RENAME_NOREPLACE)
+	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
+		return -EINVAL;
+
+	if ((flags & RENAME_NOREPLACE) && (flags & RENAME_EXCHANGE))
 		return -EINVAL;
 
 retry:
@@ -4180,7 +4207,8 @@ retry:
 
 	oldnd.flags &= ~LOOKUP_PARENT;
 	newnd.flags &= ~LOOKUP_PARENT;
-	newnd.flags |= LOOKUP_RENAME_TARGET;
+	if (!(flags & RENAME_EXCHANGE))
+		newnd.flags |= LOOKUP_RENAME_TARGET;
 
 retry_deleg:
 	trap = lock_rename(new_dir, old_dir);
@@ -4200,12 +4228,23 @@ retry_deleg:
 	error = -EEXIST;
 	if ((flags & RENAME_NOREPLACE) && d_is_positive(new_dentry))
 		goto exit5;
+	if (flags & RENAME_EXCHANGE) {
+		error = -ENOENT;
+		if (d_is_negative(new_dentry))
+			goto exit5;
+
+		if (!d_is_dir(new_dentry)) {
+			error = -ENOTDIR;
+			if (newnd.last.name[newnd.last.len])
+				goto exit5;
+		}
+	}
 	/* unless the source is a directory trailing slashes give -ENOTDIR */
 	if (!d_is_dir(old_dentry)) {
 		error = -ENOTDIR;
 		if (oldnd.last.name[oldnd.last.len])
 			goto exit5;
-		if (newnd.last.name[newnd.last.len])
+		if (!(flags & RENAME_EXCHANGE) && newnd.last.name[newnd.last.len])
 			goto exit5;
 	}
 	/* source should not be ancestor of target */
@@ -4213,7 +4252,8 @@ retry_deleg:
 	if (old_dentry == trap)
 		goto exit5;
 	/* target should not be an ancestor of source */
-	error = -ENOTEMPTY;
+	if (!(flags & RENAME_EXCHANGE))
+		error = -ENOTEMPTY;
 	if (new_dentry == trap)
 		goto exit5;
 
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 3b50cac7ccb3..3b9bfdb83ba6 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -308,6 +308,7 @@ extern void dentry_update_name_case(struct dentry *, struct qstr *);
 
 /* used for rename() and baskets */
 extern void d_move(struct dentry *, struct dentry *);
+extern void d_exchange(struct dentry *, struct dentry *);
 extern struct dentry *d_ancestor(struct dentry *, struct dentry *);
 
 /* appendix may either be NULL or be used for transname suffixes */
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 9250f4dd7d96..ca1a11bb4443 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -36,6 +36,7 @@
 #define SEEK_MAX	SEEK_HOLE
 
 #define RENAME_NOREPLACE	(1 << 0)	/* Don't overwrite target */
+#define RENAME_EXCHANGE		(1 << 1)	/* Exchange source and dest */
 
 struct fstrim_range {
 	__u64 start;
diff --git a/security/security.c b/security/security.c
index 284fbc99aa9d..8b774f362a3d 100644
--- a/security/security.c
+++ b/security/security.c
@@ -439,6 +439,14 @@ int security_path_rename(struct path *old_dir, struct dentry *old_dentry,
 	if (unlikely(IS_PRIVATE(old_dentry->d_inode) ||
 		     (new_dentry->d_inode && IS_PRIVATE(new_dentry->d_inode))))
 		return 0;
+
+	if (flags & RENAME_EXCHANGE) {
+		int err = security_ops->path_rename(new_dir, new_dentry,
+						    old_dir, old_dentry);
+		if (err)
+			return err;
+	}
+
 	return security_ops->path_rename(old_dir, old_dentry, new_dir,
 					 new_dentry);
 }
@@ -531,6 +539,14 @@ int security_inode_rename(struct inode *old_dir, struct dentry *old_dentry,
         if (unlikely(IS_PRIVATE(old_dentry->d_inode) ||
             (new_dentry->d_inode && IS_PRIVATE(new_dentry->d_inode))))
 		return 0;
+
+	if (flags & RENAME_EXCHANGE) {
+		int err = security_ops->inode_rename(new_dir, new_dentry,
+						     old_dir, old_dentry);
+		if (err)
+			return err;
+	}
+
 	return security_ops->inode_rename(old_dir, old_dentry,
 					   new_dir, new_dentry);
 }
-- 
cgit v1.2.3


From e462ded699aa2cca04b68fbf203ea4675d4c44d4 Mon Sep 17 00:00:00 2001
From: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Date: Mon, 31 Mar 2014 21:37:46 +0200
Subject: mac802154: make csma/cca parameters per-wpan

Commit 9b2777d6089bcd (ieee802154: add TX power control to wpan_phy)
and following erroneously added CSMA and CCA parameters for 802.15.4
devices as PHY parameters, while they are actually MAC parameters and
can differ for any two WPAN instances. Since it is now sensible to have
multiple WPAN devices with differing CSMA/CCA parameters, make these
parameters MAC parameters instead.

Signed-off-by: Phoebe Buckheister <phoebe.buckheister@itwm.fraunhofer.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/nl802154.h        |   2 +-
 include/net/ieee802154_netdev.h |  17 ++++
 net/ieee802154/ieee802154.h     |   2 +-
 net/ieee802154/netlink.c        |   2 +-
 net/ieee802154/nl-mac.c         | 122 +++++++++++++++++++++++-
 net/ieee802154/nl-phy.c         | 200 +---------------------------------------
 net/ieee802154/wpan-class.c     |   6 --
 net/mac802154/ieee802154_dev.c  |  36 +++-----
 net/mac802154/mac802154.h       |   9 ++
 net/mac802154/mac_cmd.c         |   3 +
 net/mac802154/wpan.c            |  89 +++++++++++++++++-
 11 files changed, 252 insertions(+), 236 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/nl802154.h b/include/linux/nl802154.h
index e110b8c266f5..c8d7f3965fff 100644
--- a/include/linux/nl802154.h
+++ b/include/linux/nl802154.h
@@ -132,7 +132,7 @@ enum {
 	IEEE802154_ADD_IFACE,
 	IEEE802154_DEL_IFACE,
 
-	IEEE802154_SET_PHYPARAMS,
+	IEEE802154_SET_MACPARAMS,
 
 	__IEEE802154_CMD_MAX,
 };
diff --git a/include/net/ieee802154_netdev.h b/include/net/ieee802154_netdev.h
index e1717cbf609b..5a719ca892f4 100644
--- a/include/net/ieee802154_netdev.h
+++ b/include/net/ieee802154_netdev.h
@@ -229,6 +229,18 @@ static inline int mac_cb_type(struct sk_buff *skb)
 #define IEEE802154_MAC_SCAN_PASSIVE	2
 #define IEEE802154_MAC_SCAN_ORPHAN	3
 
+struct ieee802154_mac_params {
+	s8 transmit_power;
+	u8 min_be;
+	u8 max_be;
+	u8 csma_retries;
+	s8 frame_retries;
+
+	bool lbt;
+	u8 cca_mode;
+	s32 cca_ed_level;
+};
+
 struct wpan_phy;
 /*
  * This should be located at net_device->ml_priv
@@ -255,6 +267,11 @@ struct ieee802154_mlme_ops {
 	int (*scan_req)(struct net_device *dev,
 			u8 type, u32 channels, u8 page, u8 duration);
 
+	int (*set_mac_params)(struct net_device *dev,
+			      const struct ieee802154_mac_params *params);
+	void (*get_mac_params)(struct net_device *dev,
+			       struct ieee802154_mac_params *params);
+
 	/* The fields below are required. */
 
 	struct wpan_phy *(*get_phy)(const struct net_device *dev);
diff --git a/net/ieee802154/ieee802154.h b/net/ieee802154/ieee802154.h
index 6cbc8965be91..6693a5cf01ce 100644
--- a/net/ieee802154/ieee802154.h
+++ b/net/ieee802154/ieee802154.h
@@ -53,7 +53,6 @@ int ieee802154_list_phy(struct sk_buff *skb, struct genl_info *info);
 int ieee802154_dump_phy(struct sk_buff *skb, struct netlink_callback *cb);
 int ieee802154_add_iface(struct sk_buff *skb, struct genl_info *info);
 int ieee802154_del_iface(struct sk_buff *skb, struct genl_info *info);
-int ieee802154_set_phyparams(struct sk_buff *skb, struct genl_info *info);
 
 enum ieee802154_mcgrp_ids {
 	IEEE802154_COORD_MCGRP,
@@ -67,5 +66,6 @@ int ieee802154_scan_req(struct sk_buff *skb, struct genl_info *info);
 int ieee802154_start_req(struct sk_buff *skb, struct genl_info *info);
 int ieee802154_list_iface(struct sk_buff *skb, struct genl_info *info);
 int ieee802154_dump_iface(struct sk_buff *skb, struct netlink_callback *cb);
+int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info);
 
 #endif
diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c
index 67c151bf4b91..04b20589d97a 100644
--- a/net/ieee802154/netlink.c
+++ b/net/ieee802154/netlink.c
@@ -115,7 +115,6 @@ static const struct genl_ops ieee8021154_ops[] = {
 			ieee802154_dump_phy),
 	IEEE802154_OP(IEEE802154_ADD_IFACE, ieee802154_add_iface),
 	IEEE802154_OP(IEEE802154_DEL_IFACE, ieee802154_del_iface),
-	IEEE802154_OP(IEEE802154_SET_PHYPARAMS, ieee802154_set_phyparams),
 	/* see nl-mac.c */
 	IEEE802154_OP(IEEE802154_ASSOCIATE_REQ, ieee802154_associate_req),
 	IEEE802154_OP(IEEE802154_ASSOCIATE_RESP, ieee802154_associate_resp),
@@ -124,6 +123,7 @@ static const struct genl_ops ieee8021154_ops[] = {
 	IEEE802154_OP(IEEE802154_START_REQ, ieee802154_start_req),
 	IEEE802154_DUMP(IEEE802154_LIST_IFACE, ieee802154_list_iface,
 			ieee802154_dump_iface),
+	IEEE802154_OP(IEEE802154_SET_MACPARAMS, ieee802154_set_macparams),
 };
 
 static const struct genl_multicast_group ieee802154_mcgrps[] = {
diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c
index bda8dba4f993..5d285498c0f6 100644
--- a/net/ieee802154/nl-mac.c
+++ b/net/ieee802154/nl-mac.c
@@ -264,6 +264,7 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid,
 {
 	void *hdr;
 	struct wpan_phy *phy;
+	struct ieee802154_mlme_ops *ops;
 	__le16 short_addr, pan_id;
 
 	pr_debug("%s\n", __func__);
@@ -273,11 +274,12 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid,
 	if (!hdr)
 		goto out;
 
-	phy = ieee802154_mlme_ops(dev)->get_phy(dev);
+	ops = ieee802154_mlme_ops(dev);
+	phy = ops->get_phy(dev);
 	BUG_ON(!phy);
 
-	short_addr = ieee802154_mlme_ops(dev)->get_short_addr(dev);
-	pan_id = ieee802154_mlme_ops(dev)->get_pan_id(dev);
+	short_addr = ops->get_short_addr(dev);
+	pan_id = ops->get_pan_id(dev);
 
 	if (nla_put_string(msg, IEEE802154_ATTR_DEV_NAME, dev->name) ||
 	    nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) ||
@@ -287,6 +289,30 @@ static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid,
 	    nla_put_shortaddr(msg, IEEE802154_ATTR_SHORT_ADDR, short_addr) ||
 	    nla_put_shortaddr(msg, IEEE802154_ATTR_PAN_ID, pan_id))
 		goto nla_put_failure;
+
+	if (ops->get_mac_params) {
+		struct ieee802154_mac_params params;
+
+		ops->get_mac_params(dev, &params);
+
+		if (nla_put_s8(msg, IEEE802154_ATTR_TXPOWER,
+			       params.transmit_power) ||
+		    nla_put_u8(msg, IEEE802154_ATTR_LBT_ENABLED, params.lbt) ||
+		    nla_put_u8(msg, IEEE802154_ATTR_CCA_MODE,
+			       params.cca_mode) ||
+		    nla_put_s32(msg, IEEE802154_ATTR_CCA_ED_LEVEL,
+				params.cca_ed_level) ||
+		    nla_put_u8(msg, IEEE802154_ATTR_CSMA_RETRIES,
+			       params.csma_retries) ||
+		    nla_put_u8(msg, IEEE802154_ATTR_CSMA_MIN_BE,
+			       params.min_be) ||
+		    nla_put_u8(msg, IEEE802154_ATTR_CSMA_MAX_BE,
+			       params.max_be) ||
+		    nla_put_s8(msg, IEEE802154_ATTR_FRAME_RETRIES,
+			       params.frame_retries))
+			goto nla_put_failure;
+	}
+
 	wpan_phy_put(phy);
 	return genlmsg_end(msg, hdr);
 
@@ -599,3 +625,93 @@ cont:
 
 	return skb->len;
 }
+
+int ieee802154_set_macparams(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net_device *dev = NULL;
+	struct ieee802154_mlme_ops *ops;
+	struct ieee802154_mac_params params;
+	struct wpan_phy *phy;
+	int rc = -EINVAL;
+
+	pr_debug("%s\n", __func__);
+
+	dev = ieee802154_nl_get_dev(info);
+	if (!dev)
+		return -ENODEV;
+
+	ops = ieee802154_mlme_ops(dev);
+
+	if (!ops->get_mac_params || !ops->set_mac_params) {
+		rc = -EOPNOTSUPP;
+		goto out;
+	}
+
+	if (netif_running(dev)) {
+		rc = -EBUSY;
+		goto out;
+	}
+
+	if (!info->attrs[IEEE802154_ATTR_LBT_ENABLED] &&
+	    !info->attrs[IEEE802154_ATTR_CCA_MODE] &&
+	    !info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL] &&
+	    !info->attrs[IEEE802154_ATTR_CSMA_RETRIES] &&
+	    !info->attrs[IEEE802154_ATTR_CSMA_MIN_BE] &&
+	    !info->attrs[IEEE802154_ATTR_CSMA_MAX_BE] &&
+	    !info->attrs[IEEE802154_ATTR_FRAME_RETRIES])
+		goto out;
+
+	phy = ops->get_phy(dev);
+
+	if ((!phy->set_lbt && info->attrs[IEEE802154_ATTR_LBT_ENABLED]) ||
+	    (!phy->set_cca_mode && info->attrs[IEEE802154_ATTR_CCA_MODE]) ||
+	    (!phy->set_cca_ed_level &&
+	     info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]) ||
+	    (!phy->set_csma_params &&
+	     (info->attrs[IEEE802154_ATTR_CSMA_RETRIES] ||
+	      info->attrs[IEEE802154_ATTR_CSMA_MIN_BE] ||
+	      info->attrs[IEEE802154_ATTR_CSMA_MAX_BE])) ||
+	    (!phy->set_frame_retries &&
+	     info->attrs[IEEE802154_ATTR_FRAME_RETRIES])) {
+		rc = -EOPNOTSUPP;
+		goto out_phy;
+	}
+
+	ops->get_mac_params(dev, &params);
+
+	if (info->attrs[IEEE802154_ATTR_TXPOWER])
+		params.transmit_power = nla_get_s8(info->attrs[IEEE802154_ATTR_TXPOWER]);
+
+	if (info->attrs[IEEE802154_ATTR_LBT_ENABLED])
+		params.lbt = nla_get_u8(info->attrs[IEEE802154_ATTR_LBT_ENABLED]);
+
+	if (info->attrs[IEEE802154_ATTR_CCA_MODE])
+		params.cca_mode = nla_get_u8(info->attrs[IEEE802154_ATTR_CCA_MODE]);
+
+	if (info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL])
+		params.cca_ed_level = nla_get_s32(info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]);
+
+	if (info->attrs[IEEE802154_ATTR_CSMA_RETRIES])
+		params.csma_retries = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_RETRIES]);
+
+	if (info->attrs[IEEE802154_ATTR_CSMA_MIN_BE])
+		params.min_be = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_MIN_BE]);
+
+	if (info->attrs[IEEE802154_ATTR_CSMA_MAX_BE])
+		params.max_be = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_MAX_BE]);
+
+	if (info->attrs[IEEE802154_ATTR_FRAME_RETRIES])
+		params.frame_retries = nla_get_s8(info->attrs[IEEE802154_ATTR_FRAME_RETRIES]);
+
+	rc = ops->set_mac_params(dev, &params);
+
+	wpan_phy_put(phy);
+	dev_put(dev);
+	return rc;
+
+out_phy:
+	wpan_phy_put(phy);
+out:
+	dev_put(dev);
+	return rc;
+}
diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c
index 222310a07762..89b265aea151 100644
--- a/net/ieee802154/nl-phy.c
+++ b/net/ieee802154/nl-phy.c
@@ -55,15 +55,7 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 portid,
 	mutex_lock(&phy->pib_lock);
 	if (nla_put_string(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)) ||
 	    nla_put_u8(msg, IEEE802154_ATTR_PAGE, phy->current_page) ||
-	    nla_put_u8(msg, IEEE802154_ATTR_CHANNEL, phy->current_channel) ||
-	    nla_put_s8(msg, IEEE802154_ATTR_TXPOWER, phy->transmit_power) ||
-	    nla_put_u8(msg, IEEE802154_ATTR_LBT_ENABLED, phy->lbt) ||
-	    nla_put_u8(msg, IEEE802154_ATTR_CCA_MODE, phy->cca_mode) ||
-	    nla_put_s32(msg, IEEE802154_ATTR_CCA_ED_LEVEL, phy->cca_ed_level) ||
-	    nla_put_u8(msg, IEEE802154_ATTR_CSMA_RETRIES, phy->csma_retries) ||
-	    nla_put_u8(msg, IEEE802154_ATTR_CSMA_MIN_BE, phy->min_be) ||
-	    nla_put_u8(msg, IEEE802154_ATTR_CSMA_MAX_BE, phy->max_be) ||
-	    nla_put_s8(msg, IEEE802154_ATTR_FRAME_RETRIES, phy->frame_retries))
+	    nla_put_u8(msg, IEEE802154_ATTR_CHANNEL, phy->current_channel))
 		goto nla_put_failure;
 	for (i = 0; i < 32; i++) {
 		if (phy->channels_supported[i])
@@ -362,193 +354,3 @@ out_dev:
 
 	return rc;
 }
-
-static int phy_set_txpower(struct wpan_phy *phy, struct genl_info *info)
-{
-	int txpower = nla_get_s8(info->attrs[IEEE802154_ATTR_TXPOWER]);
-	int rc;
-
-	rc = phy->set_txpower(phy, txpower);
-	if (rc < 0)
-		return rc;
-
-	phy->transmit_power = txpower;
-
-	return 0;
-}
-
-static int phy_set_lbt(struct wpan_phy *phy, struct genl_info *info)
-{
-	u8 on = !!nla_get_u8(info->attrs[IEEE802154_ATTR_LBT_ENABLED]);
-	int rc;
-
-	rc = phy->set_lbt(phy, on);
-	if (rc < 0)
-		return rc;
-
-	phy->lbt = on;
-
-	return 0;
-}
-
-static int phy_set_cca_mode(struct wpan_phy *phy, struct genl_info *info)
-{
-	u8 mode = nla_get_u8(info->attrs[IEEE802154_ATTR_CCA_MODE]);
-	int rc;
-
-	if (mode > 3)
-		return -EINVAL;
-
-	rc = phy->set_cca_mode(phy, mode);
-	if (rc < 0)
-		return rc;
-
-	phy->cca_mode = mode;
-
-	return 0;
-}
-
-static int phy_set_cca_ed_level(struct wpan_phy *phy, struct genl_info *info)
-{
-	s32 level = nla_get_s32(info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]);
-	int rc;
-
-	rc = phy->set_cca_ed_level(phy, level);
-	if (rc < 0)
-		return rc;
-
-	phy->cca_ed_level = level;
-
-	return 0;
-}
-
-static int phy_set_csma_params(struct wpan_phy *phy, struct genl_info *info)
-{
-	int rc;
-	u8 min_be = phy->min_be;
-	u8 max_be = phy->max_be;
-	u8 retries = phy->csma_retries;
-
-	if (info->attrs[IEEE802154_ATTR_CSMA_RETRIES])
-		retries = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_RETRIES]);
-	if (info->attrs[IEEE802154_ATTR_CSMA_MIN_BE])
-		min_be = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_MIN_BE]);
-	if (info->attrs[IEEE802154_ATTR_CSMA_MAX_BE])
-		max_be = nla_get_u8(info->attrs[IEEE802154_ATTR_CSMA_MAX_BE]);
-
-	if (retries > 5 || max_be < 3 || max_be > 8 || min_be > max_be)
-		return -EINVAL;
-
-	rc = phy->set_csma_params(phy, min_be, max_be, retries);
-	if (rc < 0)
-		return rc;
-
-	phy->min_be = min_be;
-	phy->max_be = max_be;
-	phy->csma_retries = retries;
-
-	return 0;
-}
-
-static int phy_set_frame_retries(struct wpan_phy *phy, struct genl_info *info)
-{
-	s8 retries = nla_get_s8(info->attrs[IEEE802154_ATTR_FRAME_RETRIES]);
-	int rc;
-
-	if (retries < -1 || retries > 7)
-		return -EINVAL;
-
-	rc = phy->set_frame_retries(phy, retries);
-	if (rc < 0)
-		return rc;
-
-	phy->frame_retries = retries;
-
-	return 0;
-}
-
-int ieee802154_set_phyparams(struct sk_buff *skb, struct genl_info *info)
-{
-	struct wpan_phy *phy;
-	const char *name;
-	int rc = -ENOTSUPP;
-
-	pr_debug("%s\n", __func__);
-
-	if (!info->attrs[IEEE802154_ATTR_PHY_NAME] &&
-	    !info->attrs[IEEE802154_ATTR_LBT_ENABLED] &&
-	    !info->attrs[IEEE802154_ATTR_CCA_MODE] &&
-	    !info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL] &&
-	    !info->attrs[IEEE802154_ATTR_CSMA_RETRIES] &&
-	    !info->attrs[IEEE802154_ATTR_CSMA_MIN_BE] &&
-	    !info->attrs[IEEE802154_ATTR_CSMA_MAX_BE] &&
-	    !info->attrs[IEEE802154_ATTR_FRAME_RETRIES])
-		return -EINVAL;
-
-	name = nla_data(info->attrs[IEEE802154_ATTR_PHY_NAME]);
-	if (name[nla_len(info->attrs[IEEE802154_ATTR_PHY_NAME]) - 1] != '\0')
-		return -EINVAL; /* phy name should be null-terminated */
-
-	phy = wpan_phy_find(name);
-	if (!phy)
-		return -ENODEV;
-
-	if ((!phy->set_txpower && info->attrs[IEEE802154_ATTR_TXPOWER]) ||
-	    (!phy->set_lbt && info->attrs[IEEE802154_ATTR_LBT_ENABLED]) ||
-	    (!phy->set_cca_mode && info->attrs[IEEE802154_ATTR_CCA_MODE]) ||
-	    (!phy->set_cca_ed_level &&
-	     info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]))
-		goto out;
-
-	mutex_lock(&phy->pib_lock);
-
-	if (info->attrs[IEEE802154_ATTR_TXPOWER]) {
-		rc = phy_set_txpower(phy, info);
-		if (rc < 0)
-			goto error;
-	}
-
-	if (info->attrs[IEEE802154_ATTR_LBT_ENABLED]) {
-		rc = phy_set_lbt(phy, info);
-		if (rc < 0)
-			goto error;
-	}
-
-	if (info->attrs[IEEE802154_ATTR_CCA_MODE]) {
-		rc = phy_set_cca_mode(phy, info);
-		if (rc < 0)
-			goto error;
-	}
-
-	if (info->attrs[IEEE802154_ATTR_CCA_ED_LEVEL]) {
-		rc = phy_set_cca_ed_level(phy, info);
-		if (rc < 0)
-			goto error;
-	}
-
-	if (info->attrs[IEEE802154_ATTR_CSMA_RETRIES] ||
-	    info->attrs[IEEE802154_ATTR_CSMA_MIN_BE] ||
-	    info->attrs[IEEE802154_ATTR_CSMA_MAX_BE]) {
-		rc = phy_set_csma_params(phy, info);
-		if (rc < 0)
-			goto error;
-	}
-
-	if (info->attrs[IEEE802154_ATTR_FRAME_RETRIES]) {
-		rc = phy_set_frame_retries(phy, info);
-		if (rc < 0)
-			goto error;
-	}
-
-	mutex_unlock(&phy->pib_lock);
-
-	wpan_phy_put(phy);
-
-	return 0;
-
-error:
-	mutex_unlock(&phy->pib_lock);
-out:
-	wpan_phy_put(phy);
-	return rc;
-}
diff --git a/net/ieee802154/wpan-class.c b/net/ieee802154/wpan-class.c
index edd0962d55f9..8d6f6704da84 100644
--- a/net/ieee802154/wpan-class.c
+++ b/net/ieee802154/wpan-class.c
@@ -169,12 +169,6 @@ struct wpan_phy *wpan_phy_alloc(size_t priv_size)
 	phy->current_channel = -1; /* not initialised */
 	phy->current_page = 0; /* for compatibility */
 
-	/* defaults per 802.15.4-2011 */
-	phy->min_be = 3;
-	phy->max_be = 5;
-	phy->csma_retries = 4;
-	phy->frame_retries = -1; /* for compatibility, actual default is 3 */
-
 	return phy;
 
 out:
diff --git a/net/mac802154/ieee802154_dev.c b/net/mac802154/ieee802154_dev.c
index e7aa76445fe1..2cf66d885e68 100644
--- a/net/mac802154/ieee802154_dev.c
+++ b/net/mac802154/ieee802154_dev.c
@@ -197,9 +197,6 @@ static int mac802154_set_txpower(struct wpan_phy *phy, int db)
 {
 	struct mac802154_priv *priv = wpan_phy_priv(phy);
 
-	if (!priv->ops->set_txpower)
-		return -ENOTSUPP;
-
 	return priv->ops->set_txpower(&priv->hw, db);
 }
 
@@ -207,9 +204,6 @@ static int mac802154_set_lbt(struct wpan_phy *phy, bool on)
 {
 	struct mac802154_priv *priv = wpan_phy_priv(phy);
 
-	if (!priv->ops->set_lbt)
-		return -ENOTSUPP;
-
 	return priv->ops->set_lbt(&priv->hw, on);
 }
 
@@ -217,9 +211,6 @@ static int mac802154_set_cca_mode(struct wpan_phy *phy, u8 mode)
 {
 	struct mac802154_priv *priv = wpan_phy_priv(phy);
 
-	if (!priv->ops->set_cca_mode)
-		return -ENOTSUPP;
-
 	return priv->ops->set_cca_mode(&priv->hw, mode);
 }
 
@@ -227,9 +218,6 @@ static int mac802154_set_cca_ed_level(struct wpan_phy *phy, s32 level)
 {
 	struct mac802154_priv *priv = wpan_phy_priv(phy);
 
-	if (!priv->ops->set_cca_ed_level)
-		return -ENOTSUPP;
-
 	return priv->ops->set_cca_ed_level(&priv->hw, level);
 }
 
@@ -238,9 +226,6 @@ static int mac802154_set_csma_params(struct wpan_phy *phy, u8 min_be,
 {
 	struct mac802154_priv *priv = wpan_phy_priv(phy);
 
-	if (!priv->ops->set_csma_params)
-		return -ENOTSUPP;
-
 	return priv->ops->set_csma_params(&priv->hw, min_be, max_be, retries);
 }
 
@@ -248,9 +233,6 @@ static int mac802154_set_frame_retries(struct wpan_phy *phy, s8 retries)
 {
 	struct mac802154_priv *priv = wpan_phy_priv(phy);
 
-	if (!priv->ops->set_frame_retries)
-		return -ENOTSUPP;
-
 	return priv->ops->set_frame_retries(&priv->hw, retries);
 }
 
@@ -331,12 +313,18 @@ int ieee802154_register_device(struct ieee802154_dev *dev)
 
 	priv->phy->add_iface = mac802154_add_iface;
 	priv->phy->del_iface = mac802154_del_iface;
-	priv->phy->set_txpower = mac802154_set_txpower;
-	priv->phy->set_lbt = mac802154_set_lbt;
-	priv->phy->set_cca_mode = mac802154_set_cca_mode;
-	priv->phy->set_cca_ed_level = mac802154_set_cca_ed_level;
-	priv->phy->set_csma_params = mac802154_set_csma_params;
-	priv->phy->set_frame_retries = mac802154_set_frame_retries;
+	if (priv->ops->set_txpower)
+		priv->phy->set_txpower = mac802154_set_txpower;
+	if (priv->ops->set_lbt)
+		priv->phy->set_lbt = mac802154_set_lbt;
+	if (priv->ops->set_cca_mode)
+		priv->phy->set_cca_mode = mac802154_set_cca_mode;
+	if (priv->ops->set_cca_ed_level)
+		priv->phy->set_cca_ed_level = mac802154_set_cca_ed_level;
+	if (priv->ops->set_csma_params)
+		priv->phy->set_csma_params = mac802154_set_csma_params;
+	if (priv->ops->set_frame_retries)
+		priv->phy->set_frame_retries = mac802154_set_frame_retries;
 
 	rc = wpan_phy_register(priv->phy);
 	if (rc < 0)
diff --git a/net/mac802154/mac802154.h b/net/mac802154/mac802154.h
index f40522ef288c..28ef59c566e6 100644
--- a/net/mac802154/mac802154.h
+++ b/net/mac802154/mac802154.h
@@ -23,6 +23,8 @@
 #ifndef MAC802154_H
 #define MAC802154_H
 
+#include <net/ieee802154_netdev.h>
+
 /* mac802154 device private data */
 struct mac802154_priv {
 	struct ieee802154_dev hw;
@@ -82,6 +84,8 @@ struct mac802154_sub_if_data {
 	u8 chan;
 	u8 page;
 
+	struct ieee802154_mac_params mac_params;
+
 	/* MAC BSN field */
 	u8 bsn;
 	/* MAC DSN field */
@@ -116,4 +120,9 @@ void mac802154_dev_set_pan_id(struct net_device *dev, __le16 val);
 void mac802154_dev_set_page_channel(struct net_device *dev, u8 page, u8 chan);
 u8 mac802154_dev_get_dsn(const struct net_device *dev);
 
+int mac802154_set_mac_params(struct net_device *dev,
+			     const struct ieee802154_mac_params *params);
+void mac802154_get_mac_params(struct net_device *dev,
+			      struct ieee802154_mac_params *params);
+
 #endif /* MAC802154_H */
diff --git a/net/mac802154/mac_cmd.c b/net/mac802154/mac_cmd.c
index 15bac3358889..d40c0928bc62 100644
--- a/net/mac802154/mac_cmd.c
+++ b/net/mac802154/mac_cmd.c
@@ -74,4 +74,7 @@ struct ieee802154_mlme_ops mac802154_mlme_wpan = {
 	.get_pan_id = mac802154_dev_get_pan_id,
 	.get_short_addr = mac802154_dev_get_short_addr,
 	.get_dsn = mac802154_dev_get_dsn,
+
+	.set_mac_params = mac802154_set_mac_params,
+	.get_mac_params = mac802154_get_mac_params,
 };
diff --git a/net/mac802154/wpan.c b/net/mac802154/wpan.c
index 80cbee1a2f56..1df7a6a57386 100644
--- a/net/mac802154/wpan.c
+++ b/net/mac802154/wpan.c
@@ -102,6 +102,87 @@ static int mac802154_wpan_mac_addr(struct net_device *dev, void *p)
 	return 0;
 }
 
+int mac802154_set_mac_params(struct net_device *dev,
+			     const struct ieee802154_mac_params *params)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+
+	mutex_lock(&priv->hw->slaves_mtx);
+	priv->mac_params = *params;
+	mutex_unlock(&priv->hw->slaves_mtx);
+
+	return 0;
+}
+
+void mac802154_get_mac_params(struct net_device *dev,
+			      struct ieee802154_mac_params *params)
+{
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+
+	mutex_lock(&priv->hw->slaves_mtx);
+	*params = priv->mac_params;
+	mutex_unlock(&priv->hw->slaves_mtx);
+}
+
+int mac802154_wpan_open(struct net_device *dev)
+{
+	int rc;
+	struct mac802154_sub_if_data *priv = netdev_priv(dev);
+	struct wpan_phy *phy = priv->hw->phy;
+
+	rc = mac802154_slave_open(dev);
+	if (rc < 0)
+		return rc;
+
+	mutex_lock(&phy->pib_lock);
+
+	if (phy->set_txpower) {
+		rc = phy->set_txpower(phy, priv->mac_params.transmit_power);
+		if (rc < 0)
+			goto out;
+	}
+
+	if (phy->set_lbt) {
+		rc = phy->set_lbt(phy, priv->mac_params.lbt);
+		if (rc < 0)
+			goto out;
+	}
+
+	if (phy->set_cca_mode) {
+		rc = phy->set_cca_mode(phy, priv->mac_params.cca_mode);
+		if (rc < 0)
+			goto out;
+	}
+
+	if (phy->set_cca_ed_level) {
+		rc = phy->set_cca_ed_level(phy, priv->mac_params.cca_ed_level);
+		if (rc < 0)
+			goto out;
+	}
+
+	if (phy->set_csma_params) {
+		rc = phy->set_csma_params(phy, priv->mac_params.min_be,
+					  priv->mac_params.max_be,
+					  priv->mac_params.csma_retries);
+		if (rc < 0)
+			goto out;
+	}
+
+	if (phy->set_frame_retries) {
+		rc = phy->set_frame_retries(phy,
+					    priv->mac_params.frame_retries);
+		if (rc < 0)
+			goto out;
+	}
+
+	mutex_unlock(&phy->pib_lock);
+	return 0;
+
+out:
+	mutex_unlock(&phy->pib_lock);
+	return rc;
+}
+
 static int mac802154_header_create(struct sk_buff *skb,
 				   struct net_device *dev,
 				   unsigned short type,
@@ -204,7 +285,7 @@ static struct header_ops mac802154_header_ops = {
 };
 
 static const struct net_device_ops mac802154_wpan_ops = {
-	.ndo_open		= mac802154_slave_open,
+	.ndo_open		= mac802154_wpan_open,
 	.ndo_stop		= mac802154_slave_close,
 	.ndo_start_xmit		= mac802154_wpan_xmit,
 	.ndo_do_ioctl		= mac802154_wpan_ioctl,
@@ -242,6 +323,12 @@ void mac802154_wpan_setup(struct net_device *dev)
 	get_random_bytes(&priv->bsn, 1);
 	get_random_bytes(&priv->dsn, 1);
 
+	/* defaults per 802.15.4-2011 */
+	priv->mac_params.min_be = 3;
+	priv->mac_params.max_be = 5;
+	priv->mac_params.csma_retries = 4;
+	priv->mac_params.frame_retries = -1; /* for compatibility, actual default is 3 */
+
 	priv->pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST);
 	priv->short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST);
 }
-- 
cgit v1.2.3


From 408eccce32044ee3285a7f6a812723ba3540c3e7 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Tue, 1 Apr 2014 16:20:23 +0200
Subject: net: ptp: move PTP classifier in its own file

This commit fixes a build error reported by Fengguang, that is
triggered when CONFIG_NETWORK_PHY_TIMESTAMPING is not set:

  ERROR: "ptp_classify_raw" [drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.ko] undefined!

The fix is to introduce its own file for the PTP BPF classifier,
so that PTP_1588_CLOCK and/or NETWORK_PHY_TIMESTAMPING can select
it independently from each other. IXP4xx driver on ARM needs to
select it as well since it does not seem to select PTP_1588_CLOCK
or similar that would pull it in automatically.

This also allows for hiding all of the internals of the BPF PTP
program inside that file, and only exporting relevant API bits
to drivers.

This patch also adds a kdoc documentation of ptp_classify_raw()
API to make it clear that it can return PTP_CLASS_* defines. Also,
the BPF program has been translated into bpf_asm code, so that it
can be more easily read and altered (extensively documented in [1]).

In the kernel tree under tools/net/ we have bpf_asm and bpf_dbg
tools, so the commented program can simply be translated via
`./bpf_asm -c prog` where prog is a file that contains the
commented code. This makes it easily readable/verifiable and when
there's a need to change something, jump offsets etc do not need
to be replaced manually which can be very error prone. Instead,
a newly translated version via bpf_asm can simply replace the old
code. I have checked opcode diffs before/after and it's the very
same filter.

  [1] Documentation/networking/filter.txt

Fixes: 164d8c666521 ("net: ptp: do not reimplement PTP/BPF classifier")
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Jiri Benc <jbenc@redhat.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/xscale/Kconfig |   1 +
 drivers/net/phy/dp83640.c           |   1 +
 drivers/ptp/Kconfig                 |   1 +
 include/linux/ptp_classify.h        |  95 ++++++------------------
 include/linux/skbuff.h              |   2 -
 net/Kconfig                         |   4 +
 net/core/Makefile                   |   1 +
 net/core/ptp_classifier.c           | 141 ++++++++++++++++++++++++++++++++++++
 net/core/timestamping.c             |  18 -----
 net/socket.c                        |   5 +-
 10 files changed, 173 insertions(+), 96 deletions(-)
 create mode 100644 net/core/ptp_classifier.c

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/xscale/Kconfig b/drivers/net/ethernet/xscale/Kconfig
index 3f431019e615..b81bc9fca378 100644
--- a/drivers/net/ethernet/xscale/Kconfig
+++ b/drivers/net/ethernet/xscale/Kconfig
@@ -23,6 +23,7 @@ config IXP4XX_ETH
 	tristate "Intel IXP4xx Ethernet support"
 	depends on ARM && ARCH_IXP4XX && IXP4XX_NPE && IXP4XX_QMGR
 	select PHYLIB
+	select NET_PTP_CLASSIFY
 	---help---
 	  Say Y here if you want to use built-in Ethernet ports
 	  on IXP4xx processor.
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 352c5e45fe9c..6a999e6814a0 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -27,6 +27,7 @@
 #include <linux/module.h>
 #include <linux/net_tstamp.h>
 #include <linux/netdevice.h>
+#include <linux/if_vlan.h>
 #include <linux/phy.h>
 #include <linux/ptp_classify.h>
 #include <linux/ptp_clock_kernel.h>
diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig
index 5a7910e61e17..6963bdf54175 100644
--- a/drivers/ptp/Kconfig
+++ b/drivers/ptp/Kconfig
@@ -7,6 +7,7 @@ menu "PTP clock support"
 config PTP_1588_CLOCK
 	tristate "PTP clock support"
 	select PPS
+	select NET_PTP_CLASSIFY
 	help
 	  The IEEE 1588 standard defines a method to precisely
 	  synchronize distributed clocks over Ethernet networks. The
diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h
index 6d3b0a2ef9ce..7dfed71d76a6 100644
--- a/include/linux/ptp_classify.h
+++ b/include/linux/ptp_classify.h
@@ -23,11 +23,8 @@
 #ifndef _PTP_CLASSIFY_H_
 #define _PTP_CLASSIFY_H_
 
-#include <linux/if_ether.h>
-#include <linux/if_vlan.h>
 #include <linux/ip.h>
-#include <linux/filter.h>
-#include <linux/in.h>
+#include <linux/skbuff.h>
 
 #define PTP_CLASS_NONE  0x00 /* not a PTP event message */
 #define PTP_CLASS_V1    0x01 /* protocol version 1 */
@@ -40,7 +37,7 @@
 #define PTP_CLASS_PMASK 0xf0 /* mask for the packet type field */
 
 #define PTP_CLASS_V1_IPV4 (PTP_CLASS_V1 | PTP_CLASS_IPV4)
-#define PTP_CLASS_V1_IPV6 (PTP_CLASS_V1 | PTP_CLASS_IPV6) /*probably DNE*/
+#define PTP_CLASS_V1_IPV6 (PTP_CLASS_V1 | PTP_CLASS_IPV6) /* probably DNE */
 #define PTP_CLASS_V2_IPV4 (PTP_CLASS_V2 | PTP_CLASS_IPV4)
 #define PTP_CLASS_V2_IPV6 (PTP_CLASS_V2 | PTP_CLASS_IPV6)
 #define PTP_CLASS_V2_L2   (PTP_CLASS_V2 | PTP_CLASS_L2)
@@ -49,82 +46,34 @@
 #define PTP_EV_PORT 319
 #define PTP_GEN_BIT 0x08 /* indicates general message, if set in message type */
 
-#define OFF_ETYPE	12
-#define OFF_IHL		14
-#define OFF_FRAG	20
-#define OFF_PROTO4	23
-#define OFF_NEXT	6
-#define OFF_UDP_DST	2
-
 #define OFF_PTP_SOURCE_UUID	22 /* PTPv1 only */
 #define OFF_PTP_SEQUENCE_ID	30
 #define OFF_PTP_CONTROL		32 /* PTPv1 only */
 
-#define IPV4_HLEN(data) (((struct iphdr *)(data + OFF_IHL))->ihl << 2)
-
+/* Below defines should actually be removed at some point in time. */
 #define IP6_HLEN	40
 #define UDP_HLEN	8
-
-#define RELOFF_DST4	(ETH_HLEN + OFF_UDP_DST)
-#define OFF_DST6	(ETH_HLEN + IP6_HLEN + OFF_UDP_DST)
+#define OFF_IHL		14
 #define OFF_PTP6	(ETH_HLEN + IP6_HLEN + UDP_HLEN)
+#define IPV4_HLEN(data) (((struct iphdr *)(data + OFF_IHL))->ihl << 2)
 
-#define OP_AND	(BPF_ALU | BPF_AND  | BPF_K)
-#define OP_JEQ	(BPF_JMP | BPF_JEQ  | BPF_K)
-#define OP_JSET	(BPF_JMP | BPF_JSET | BPF_K)
-#define OP_LDB	(BPF_LD  | BPF_B    | BPF_ABS)
-#define OP_LDH	(BPF_LD  | BPF_H    | BPF_ABS)
-#define OP_LDHI	(BPF_LD  | BPF_H    | BPF_IND)
-#define OP_LDX	(BPF_LDX | BPF_B    | BPF_MSH)
-#define OP_OR	(BPF_ALU | BPF_OR   | BPF_K)
-#define OP_RETA	(BPF_RET | BPF_A)
-#define OP_RETK	(BPF_RET | BPF_K)
-
-#define PTP_FILTER \
-	{OP_LDH,	0,   0, OFF_ETYPE		}, /*              */ \
-	{OP_JEQ,	0,  12, ETH_P_IP		}, /* f goto L20   */ \
-	{OP_LDB,	0,   0, OFF_PROTO4		}, /*              */ \
-	{OP_JEQ,	0,   9, IPPROTO_UDP		}, /* f goto L10   */ \
-	{OP_LDH,	0,   0, OFF_FRAG		}, /*              */ \
-	{OP_JSET,	7,   0, 0x1fff			}, /* t goto L11   */ \
-	{OP_LDX,	0,   0, OFF_IHL			}, /*              */ \
-	{OP_LDHI,	0,   0, RELOFF_DST4		}, /*              */ \
-	{OP_JEQ,	0,   4, PTP_EV_PORT		}, /* f goto L12   */ \
-	{OP_LDHI,	0,   0, ETH_HLEN + UDP_HLEN	}, /*              */ \
-	{OP_AND,	0,   0, PTP_CLASS_VMASK		}, /*              */ \
-	{OP_OR,		0,   0, PTP_CLASS_IPV4		}, /*              */ \
-	{OP_RETA,	0,   0, 0			}, /*              */ \
-/*L1x*/	{OP_RETK,	0,   0, PTP_CLASS_NONE		}, /*              */ \
-/*L20*/	{OP_JEQ,	0,   9, ETH_P_IPV6		}, /* f goto L40   */ \
-	{OP_LDB,	0,   0, ETH_HLEN + OFF_NEXT	}, /*              */ \
-	{OP_JEQ,	0,   6, IPPROTO_UDP		}, /* f goto L30   */ \
-	{OP_LDH,	0,   0, OFF_DST6		}, /*              */ \
-	{OP_JEQ,	0,   4, PTP_EV_PORT		}, /* f goto L31   */ \
-	{OP_LDH,	0,   0, OFF_PTP6		}, /*              */ \
-	{OP_AND,	0,   0, PTP_CLASS_VMASK		}, /*              */ \
-	{OP_OR,		0,   0, PTP_CLASS_IPV6		}, /*              */ \
-	{OP_RETA,	0,   0, 0			}, /*              */ \
-/*L3x*/	{OP_RETK,	0,   0, PTP_CLASS_NONE		}, /*              */ \
-/*L40*/	{OP_JEQ,	0,   9, ETH_P_8021Q		}, /* f goto L50   */ \
-	{OP_LDH,	0,   0, OFF_ETYPE + 4		}, /*              */ \
-	{OP_JEQ,	0,  15, ETH_P_1588		}, /* f goto L60   */ \
-	{OP_LDB,	0,   0, ETH_HLEN + VLAN_HLEN	}, /*              */ \
-	{OP_AND,	0,   0, PTP_GEN_BIT		}, /*              */ \
-	{OP_JEQ,	0,  12, 0			}, /* f goto L6x   */ \
-	{OP_LDH,	0,   0, ETH_HLEN + VLAN_HLEN	}, /*              */ \
-	{OP_AND,	0,   0, PTP_CLASS_VMASK		}, /*              */ \
-	{OP_OR,		0,   0, PTP_CLASS_VLAN		}, /*              */ \
-	{OP_RETA,	0,   0, 0			}, /*              */ \
-/*L50*/	{OP_JEQ,	0,   7, ETH_P_1588		}, /* f goto L61   */ \
-	{OP_LDB,	0,   0, ETH_HLEN		}, /*              */ \
-	{OP_AND,	0,   0, PTP_GEN_BIT		}, /*              */ \
-	{OP_JEQ,	0,   4, 0			}, /* f goto L6x   */ \
-	{OP_LDH,	0,   0, ETH_HLEN		}, /*              */ \
-	{OP_AND,	0,   0, PTP_CLASS_VMASK		}, /*              */ \
-	{OP_OR,		0,   0, PTP_CLASS_L2		}, /*              */ \
-	{OP_RETA,	0,   0, 0			}, /*              */ \
-/*L6x*/	{OP_RETK,	0,   0, PTP_CLASS_NONE		},
-
+#if defined(CONFIG_NET_PTP_CLASSIFY)
+/**
+ * ptp_classify_raw - classify a PTP packet
+ * @skb: buffer
+ *
+ * Runs a minimal BPF dissector to classify a network packet to
+ * determine the PTP class. In case the skb does not contain any
+ * PTP protocol data, PTP_CLASS_NONE will be returned, otherwise
+ * PTP_CLASS_V1_IPV{4,6}, PTP_CLASS_V2_IPV{4,6} or
+ * PTP_CLASS_V2_{L2,VLAN}, depending on the packet content.
+ */
 unsigned int ptp_classify_raw(const struct sk_buff *skb);
 
+void __init ptp_classifier_init(void);
+#else
+static inline void ptp_classifier_init(void)
+{
+}
 #endif
+#endif /* _PTP_CLASSIFY_H_ */
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 18ef0224fb6a..31edf63937a1 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2630,8 +2630,6 @@ static inline ktime_t net_invalid_timestamp(void)
 	return ktime_set(0, 0);
 }
 
-void skb_timestamping_init(void);
-
 #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING
 
 void skb_clone_tx_timestamp(struct sk_buff *skb);
diff --git a/net/Kconfig b/net/Kconfig
index e411046a62e3..d1f6f968fc09 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -89,8 +89,12 @@ config NETWORK_SECMARK
 	  to nfmark, but designated for security purposes.
 	  If you are unsure how to answer this question, answer N.
 
+config NET_PTP_CLASSIFY
+	def_bool n
+
 config NETWORK_PHY_TIMESTAMPING
 	bool "Timestamping in PHY devices"
+	select NET_PTP_CLASSIFY
 	help
 	  This allows timestamping of network packets by PHYs with
 	  hardware timestamping capabilities. This option adds some
diff --git a/net/core/Makefile b/net/core/Makefile
index 9628c20acff6..826b925aa453 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -21,5 +21,6 @@ obj-$(CONFIG_FIB_RULES) += fib_rules.o
 obj-$(CONFIG_TRACEPOINTS) += net-traces.o
 obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o
 obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o
+obj-$(CONFIG_NET_PTP_CLASSIFY) += ptp_classifier.o
 obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o
 obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o
diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c
new file mode 100644
index 000000000000..eaba0f68f860
--- /dev/null
+++ b/net/core/ptp_classifier.c
@@ -0,0 +1,141 @@
+/* PTP classifier
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+/* The below program is the bpf_asm (tools/net/) representation of
+ * the opcode array in the ptp_filter structure.
+ *
+ * For convenience, this can easily be altered and reviewed with
+ * bpf_asm and bpf_dbg, e.g. `./bpf_asm -c prog` where prog is a
+ * simple file containing the below program:
+ *
+ * ldh [12]                        ; load ethertype
+ *
+ * ; PTP over UDP over IPv4 over Ethernet
+ * test_ipv4:
+ *   jneq #0x800, test_ipv6        ; ETH_P_IP ?
+ *   ldb [23]                      ; load proto
+ *   jneq #17, drop_ipv4           ; IPPROTO_UDP ?
+ *   ldh [20]                      ; load frag offset field
+ *   jset #0x1fff, drop_ipv4       ; don't allow fragments
+ *   ldxb 4*([14]&0xf)             ; load IP header len
+ *   ldh [x + 16]                  ; load UDP dst port
+ *   jneq #319, drop_ipv4          ; is port PTP_EV_PORT ?
+ *   ldh [x + 22]                  ; load payload
+ *   and #0xf                      ; mask PTP_CLASS_VMASK
+ *   or #0x10                      ; PTP_CLASS_IPV4
+ *   ret a                         ; return PTP class
+ *   drop_ipv4: ret #0x0           ; PTP_CLASS_NONE
+ *
+ * ; PTP over UDP over IPv6 over Ethernet
+ * test_ipv6:
+ *   jneq #0x86dd, test_8021q      ; ETH_P_IPV6 ?
+ *   ldb [20]                      ; load proto
+ *   jneq #17, drop_ipv6           ; IPPROTO_UDP ?
+ *   ldh [56]                      ; load UDP dst port
+ *   jneq #319, drop_ipv6          ; is port PTP_EV_PORT ?
+ *   ldh [62]                      ; load payload
+ *   and #0xf                      ; mask PTP_CLASS_VMASK
+ *   or #0x20                      ; PTP_CLASS_IPV6
+ *   ret a                         ; return PTP class
+ *   drop_ipv6: ret #0x0           ; PTP_CLASS_NONE
+ *
+ * ; PTP over 802.1Q over Ethernet
+ * test_8021q:
+ *   jneq #0x8100, test_ieee1588   ; ETH_P_8021Q ?
+ *   ldh [16]                      ; load inner type
+ *   jneq #0x88f7, drop_ieee1588   ; ETH_P_1588 ?
+ *   ldb [18]                      ; load payload
+ *   and #0x8                      ; as we don't have ports here, test
+ *   jneq #0x0, drop_ieee1588      ; for PTP_GEN_BIT and drop these
+ *   ldh [18]                      ; reload payload
+ *   and #0xf                      ; mask PTP_CLASS_VMASK
+ *   or #0x40                      ; PTP_CLASS_V2_VLAN
+ *   ret a                         ; return PTP class
+ *
+ * ; PTP over Ethernet
+ * test_ieee1588:
+ *   jneq #0x88f7, drop_ieee1588   ; ETH_P_1588 ?
+ *   ldb [14]                      ; load payload
+ *   and #0x8                      ; as we don't have ports here, test
+ *   jneq #0x0, drop_ieee1588      ; for PTP_GEN_BIT and drop these
+ *   ldh [14]                      ; reload payload
+ *   and #0xf                      ; mask PTP_CLASS_VMASK
+ *   or #0x30                      ; PTP_CLASS_L2
+ *   ret a                         ; return PTP class
+ *   drop_ieee1588: ret #0x0       ; PTP_CLASS_NONE
+ */
+
+#include <linux/skbuff.h>
+#include <linux/filter.h>
+#include <linux/ptp_classify.h>
+
+static struct sk_filter *ptp_insns __read_mostly;
+
+unsigned int ptp_classify_raw(const struct sk_buff *skb)
+{
+	return SK_RUN_FILTER(ptp_insns, skb);
+}
+EXPORT_SYMBOL_GPL(ptp_classify_raw);
+
+void __init ptp_classifier_init(void)
+{
+	static struct sock_filter ptp_filter[] = {
+		{ 0x28,  0,  0, 0x0000000c },
+		{ 0x15,  0, 12, 0x00000800 },
+		{ 0x30,  0,  0, 0x00000017 },
+		{ 0x15,  0,  9, 0x00000011 },
+		{ 0x28,  0,  0, 0x00000014 },
+		{ 0x45,  7,  0, 0x00001fff },
+		{ 0xb1,  0,  0, 0x0000000e },
+		{ 0x48,  0,  0, 0x00000010 },
+		{ 0x15,  0,  4, 0x0000013f },
+		{ 0x48,  0,  0, 0x00000016 },
+		{ 0x54,  0,  0, 0x0000000f },
+		{ 0x44,  0,  0, 0x00000010 },
+		{ 0x16,  0,  0, 0x00000000 },
+		{ 0x06,  0,  0, 0x00000000 },
+		{ 0x15,  0,  9, 0x000086dd },
+		{ 0x30,  0,  0, 0x00000014 },
+		{ 0x15,  0,  6, 0x00000011 },
+		{ 0x28,  0,  0, 0x00000038 },
+		{ 0x15,  0,  4, 0x0000013f },
+		{ 0x28,  0,  0, 0x0000003e },
+		{ 0x54,  0,  0, 0x0000000f },
+		{ 0x44,  0,  0, 0x00000020 },
+		{ 0x16,  0,  0, 0x00000000 },
+		{ 0x06,  0,  0, 0x00000000 },
+		{ 0x15,  0,  9, 0x00008100 },
+		{ 0x28,  0,  0, 0x00000010 },
+		{ 0x15,  0, 15, 0x000088f7 },
+		{ 0x30,  0,  0, 0x00000012 },
+		{ 0x54,  0,  0, 0x00000008 },
+		{ 0x15,  0, 12, 0x00000000 },
+		{ 0x28,  0,  0, 0x00000012 },
+		{ 0x54,  0,  0, 0x0000000f },
+		{ 0x44,  0,  0, 0x00000040 },
+		{ 0x16,  0,  0, 0x00000000 },
+		{ 0x15,  0,  7, 0x000088f7 },
+		{ 0x30,  0,  0, 0x0000000e },
+		{ 0x54,  0,  0, 0x00000008 },
+		{ 0x15,  0,  4, 0x00000000 },
+		{ 0x28,  0,  0, 0x0000000e },
+		{ 0x54,  0,  0, 0x0000000f },
+		{ 0x44,  0,  0, 0x00000030 },
+		{ 0x16,  0,  0, 0x00000000 },
+		{ 0x06,  0,  0, 0x00000000 },
+	};
+	struct sock_fprog ptp_prog = {
+		.len = ARRAY_SIZE(ptp_filter), .filter = ptp_filter,
+	};
+
+	BUG_ON(sk_unattached_filter_create(&ptp_insns, &ptp_prog));
+}
diff --git a/net/core/timestamping.c b/net/core/timestamping.c
index 9ff26b3cc021..6521dfd8b7c8 100644
--- a/net/core/timestamping.c
+++ b/net/core/timestamping.c
@@ -23,14 +23,6 @@
 #include <linux/skbuff.h>
 #include <linux/export.h>
 
-static struct sk_filter *ptp_insns __read_mostly;
-
-unsigned int ptp_classify_raw(const struct sk_buff *skb)
-{
-	return SK_RUN_FILTER(ptp_insns, skb);
-}
-EXPORT_SYMBOL_GPL(ptp_classify_raw);
-
 static unsigned int classify(const struct sk_buff *skb)
 {
 	if (likely(skb->dev && skb->dev->phydev &&
@@ -140,13 +132,3 @@ bool skb_defer_rx_timestamp(struct sk_buff *skb)
 	return false;
 }
 EXPORT_SYMBOL_GPL(skb_defer_rx_timestamp);
-
-void __init skb_timestamping_init(void)
-{
-	static struct sock_filter ptp_filter[] = { PTP_FILTER };
-	struct sock_fprog ptp_prog = {
-		.len = ARRAY_SIZE(ptp_filter), .filter = ptp_filter,
-	};
-
-	BUG_ON(sk_unattached_filter_create(&ptp_insns, &ptp_prog));
-}
diff --git a/net/socket.c b/net/socket.c
index f25eaa30b690..1b1e7e6a960f 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -72,6 +72,7 @@
 #include <linux/if_bridge.h>
 #include <linux/if_frad.h>
 #include <linux/if_vlan.h>
+#include <linux/ptp_classify.h>
 #include <linux/init.h>
 #include <linux/poll.h>
 #include <linux/cache.h>
@@ -2685,9 +2686,7 @@ static int __init sock_init(void)
 		goto out;
 #endif
 
-#ifdef CONFIG_NETWORK_PHY_TIMESTAMPING
-	skb_timestamping_init();
-#endif
+	ptp_classifier_init();
 
 out:
 	return err;
-- 
cgit v1.2.3


From 574f7194f693cd80de96a39f0c43dbb346c38a15 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Tue, 1 Apr 2014 12:20:24 -0700
Subject: net: Add a test to see if a skb is freeable in irq context

Currently netpoll and skb_release_head_state assume that a skb is
freeable in hard irq context except when skb->destructor is set.

The reality is far from this.  So add a function skb_irq_freeable to
compute the full test and in the process be the living documentation
of what the requirements are of actually freeing a skb in hard irq
context.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 31edf63937a1..350eebe770d9 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2831,6 +2831,19 @@ static inline void skb_init_secmark(struct sk_buff *skb)
 { }
 #endif
 
+static inline bool skb_irq_freeable(const struct sk_buff *skb)
+{
+	return !skb->destructor &&
+#if IS_ENABLED(CONFIG_XFRM)
+		!skb->sp &&
+#endif
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+		!skb->nfct &&
+#endif
+		!skb->_skb_refdst &&
+		!skb_has_frag_list(skb);
+}
+
 static inline void skb_set_queue_mapping(struct sk_buff *skb, u16 queue_mapping)
 {
 	skb->queue_mapping = queue_mapping;
-- 
cgit v1.2.3


From f2ebb3a921c1ca1e2ddd9242e95a1989a50c4c68 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 27 Feb 2014 09:35:45 -0500
Subject: smarter propagate_mnt()

The current mainline has copies propagated to *all* nodes, then
tears down the copies we made for nodes that do not contain
counterparts of the desired mountpoint.  That sets the right
propagation graph for the copies (at teardown time we move
the slaves of removed node to a surviving peer or directly
to master), but we end up paying a fairly steep price in
useless allocations.  It's fairly easy to create a situation
where N calls of mount(2) create exactly N bindings, with
O(N^2) vfsmounts allocated and freed in process.

Fortunately, it is possible to avoid those allocations/freeings.
The trick is to create copies in the right order and find which
one would've eventually become a master with the current algorithm.
It turns out to be possible in O(nodes getting propagation) time
and with no extra allocations at all.

One part is that we need to make sure that eventual master will be
created before its slaves, so we need to walk the propagation
tree in a different order - by peer groups.  And iterate through
the peers before dealing with the next group.

Another thing is finding the (earlier) copy that will be a master
of one we are about to create; to do that we are (temporary) marking
the masters of mountpoints we are attaching the copies to.

Either we are in a peer of the last mountpoint we'd dealt with,
or we have the following situation: we are attaching to mountpoint M,
the last copy S_0 had been attached to M_0 and there are sequences
S_0...S_n, M_0...M_n such that S_{i+1} is a master of S_{i},
S_{i} mounted on M{i} and we need to create a slave of the first S_{k}
such that M is getting propagation from M_{k}.  It means that the master
of M_{k} will be among the sequence of masters of M.  On the
other hand, the nearest marked node in that sequence will either
be the master of M_{k} or the master of M_{k-1} (the latter -
in the case if M_{k-1} is a slave of something M gets propagation
from, but in a wrong peer group).

So we go through the sequence of masters of M until we find
a marked one (P).  Let N be the one before it.  Then we go through
the sequence of masters of S_0 until we find one (say, S) mounted
on a node D that has P as master and check if D is a peer of N.
If it is, S will be the master of new copy, if not - the master of S
will be.

That's it for the hard part; the rest is fairly simple.  Iterator
is in next_group(), handling of one prospective mountpoint is
propagate_one().

It seems to survive all tests and gives a noticably better performance
than the current mainline for setups that are seriously using shared
subtrees.

Cc: stable@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namespace.c        |  11 ++-
 fs/pnode.c            | 198 ++++++++++++++++++++++++++++++--------------------
 fs/pnode.h            |   3 +
 include/linux/mount.h |   3 +
 4 files changed, 133 insertions(+), 82 deletions(-)

(limited to 'include/linux')

diff --git a/fs/namespace.c b/fs/namespace.c
index 2ffc5a2905d4..65233a5f390a 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -885,7 +885,7 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 			goto out_free;
 	}
 
-	mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD;
+	mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~(MNT_WRITE_HOLD|MNT_MARKED);
 	/* Don't allow unprivileged users to change mount flags */
 	if ((flag & CL_UNPRIVILEGED) && (mnt->mnt.mnt_flags & MNT_READONLY))
 		mnt->mnt.mnt_flags |= MNT_LOCK_READONLY;
@@ -1661,9 +1661,9 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 		if (err)
 			goto out;
 		err = propagate_mnt(dest_mnt, dest_mp, source_mnt, &tree_list);
+		lock_mount_hash();
 		if (err)
 			goto out_cleanup_ids;
-		lock_mount_hash();
 		for (p = source_mnt; p; p = next_mnt(p, source_mnt))
 			set_mnt_shared(p);
 	} else {
@@ -1690,6 +1690,11 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 	return 0;
 
  out_cleanup_ids:
+	while (!hlist_empty(&tree_list)) {
+		child = hlist_entry(tree_list.first, struct mount, mnt_hash);
+		umount_tree(child, 0);
+	}
+	unlock_mount_hash();
 	cleanup_group_ids(source_mnt, NULL);
  out:
 	return err;
@@ -2044,7 +2049,7 @@ static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags)
 	struct mount *parent;
 	int err;
 
-	mnt_flags &= ~(MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | MNT_DOOMED | MNT_SYNC_UMOUNT);
+	mnt_flags &= ~MNT_INTERNAL_FLAGS;
 
 	mp = lock_mount(path);
 	if (IS_ERR(mp))
diff --git a/fs/pnode.c b/fs/pnode.c
index 88396df725b4..302bf22c4a30 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -164,46 +164,94 @@ static struct mount *propagation_next(struct mount *m,
 	}
 }
 
-/*
- * return the source mount to be used for cloning
- *
- * @dest 	the current destination mount
- * @last_dest  	the last seen destination mount
- * @last_src  	the last seen source mount
- * @type	return CL_SLAVE if the new mount has to be
- * 		cloned as a slave.
- */
-static struct mount *get_source(struct mount *dest,
-				struct mount *last_dest,
-				struct mount *last_src,
-				int *type)
+static struct mount *next_group(struct mount *m, struct mount *origin)
 {
-	struct mount *p_last_src = NULL;
-	struct mount *p_last_dest = NULL;
-
-	while (last_dest != dest->mnt_master) {
-		p_last_dest = last_dest;
-		p_last_src = last_src;
-		last_dest = last_dest->mnt_master;
-		last_src = last_src->mnt_master;
+	while (1) {
+		while (1) {
+			struct mount *next;
+			if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
+				return first_slave(m);
+			next = next_peer(m);
+			if (m->mnt_group_id == origin->mnt_group_id) {
+				if (next == origin)
+					return NULL;
+			} else if (m->mnt_slave.next != &next->mnt_slave)
+				break;
+			m = next;
+		}
+		/* m is the last peer */
+		while (1) {
+			struct mount *master = m->mnt_master;
+			if (m->mnt_slave.next != &master->mnt_slave_list)
+				return next_slave(m);
+			m = next_peer(master);
+			if (master->mnt_group_id == origin->mnt_group_id)
+				break;
+			if (master->mnt_slave.next == &m->mnt_slave)
+				break;
+			m = master;
+		}
+		if (m == origin)
+			return NULL;
 	}
+}
 
-	if (p_last_dest) {
-		do {
-			p_last_dest = next_peer(p_last_dest);
-		} while (IS_MNT_NEW(p_last_dest));
-		/* is that a peer of the earlier? */
-		if (dest == p_last_dest) {
-			*type = CL_MAKE_SHARED;
-			return p_last_src;
+/* all accesses are serialized by namespace_sem */
+static struct user_namespace *user_ns;
+static struct mount *last_dest, *last_source, *dest_master;
+static struct mountpoint *mp;
+static struct hlist_head *list;
+
+static int propagate_one(struct mount *m)
+{
+	struct mount *child;
+	int type;
+	/* skip ones added by this propagate_mnt() */
+	if (IS_MNT_NEW(m))
+		return 0;
+	/* skip if mountpoint isn't covered by it */
+	if (!is_subdir(mp->m_dentry, m->mnt.mnt_root))
+		return 0;
+	if (m->mnt_group_id == last_dest->mnt_group_id) {
+		type = CL_MAKE_SHARED;
+	} else {
+		struct mount *n, *p;
+		for (n = m; ; n = p) {
+			p = n->mnt_master;
+			if (p == dest_master || IS_MNT_MARKED(p)) {
+				while (last_dest->mnt_master != p) {
+					last_source = last_source->mnt_master;
+					last_dest = last_source->mnt_parent;
+				}
+				if (n->mnt_group_id != last_dest->mnt_group_id) {
+					last_source = last_source->mnt_master;
+					last_dest = last_source->mnt_parent;
+				}
+				break;
+			}
 		}
+		type = CL_SLAVE;
+		/* beginning of peer group among the slaves? */
+		if (IS_MNT_SHARED(m))
+			type |= CL_MAKE_SHARED;
 	}
-	/* slave of the earlier, then */
-	*type = CL_SLAVE;
-	/* beginning of peer group among the slaves? */
-	if (IS_MNT_SHARED(dest))
-		*type |= CL_MAKE_SHARED;
-	return last_src;
+		
+	/* Notice when we are propagating across user namespaces */
+	if (m->mnt_ns->user_ns != user_ns)
+		type |= CL_UNPRIVILEGED;
+	child = copy_tree(last_source, last_source->mnt.mnt_root, type);
+	if (IS_ERR(child))
+		return PTR_ERR(child);
+	mnt_set_mountpoint(m, mp, child);
+	last_dest = m;
+	last_source = child;
+	if (m->mnt_master != dest_master) {
+		read_seqlock_excl(&mount_lock);
+		SET_MNT_MARK(m->mnt_master);
+		read_sequnlock_excl(&mount_lock);
+	}
+	hlist_add_head(&child->mnt_hash, list);
+	return 0;
 }
 
 /*
@@ -222,56 +270,48 @@ static struct mount *get_source(struct mount *dest,
 int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,
 		    struct mount *source_mnt, struct hlist_head *tree_list)
 {
-	struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns;
-	struct mount *m, *child;
+	struct mount *m, *n;
 	int ret = 0;
-	struct mount *prev_dest_mnt = dest_mnt;
-	struct mount *prev_src_mnt  = source_mnt;
-	HLIST_HEAD(tmp_list);
-
-	for (m = propagation_next(dest_mnt, dest_mnt); m;
-			m = propagation_next(m, dest_mnt)) {
-		int type;
-		struct mount *source;
-
-		if (IS_MNT_NEW(m))
-			continue;
-
-		source =  get_source(m, prev_dest_mnt, prev_src_mnt, &type);
-
-		/* Notice when we are propagating across user namespaces */
-		if (m->mnt_ns->user_ns != user_ns)
-			type |= CL_UNPRIVILEGED;
-
-		child = copy_tree(source, source->mnt.mnt_root, type);
-		if (IS_ERR(child)) {
-			ret = PTR_ERR(child);
-			tmp_list = *tree_list;
-			tmp_list.first->pprev = &tmp_list.first;
-			INIT_HLIST_HEAD(tree_list);
+
+	/*
+	 * we don't want to bother passing tons of arguments to
+	 * propagate_one(); everything is serialized by namespace_sem,
+	 * so globals will do just fine.
+	 */
+	user_ns = current->nsproxy->mnt_ns->user_ns;
+	last_dest = dest_mnt;
+	last_source = source_mnt;
+	mp = dest_mp;
+	list = tree_list;
+	dest_master = dest_mnt->mnt_master;
+
+	/* all peers of dest_mnt, except dest_mnt itself */
+	for (n = next_peer(dest_mnt); n != dest_mnt; n = next_peer(n)) {
+		ret = propagate_one(n);
+		if (ret)
 			goto out;
-		}
+	}
 
-		if (is_subdir(dest_mp->m_dentry, m->mnt.mnt_root)) {
-			mnt_set_mountpoint(m, dest_mp, child);
-			hlist_add_head(&child->mnt_hash, tree_list);
-		} else {
-			/*
-			 * This can happen if the parent mount was bind mounted
-			 * on some subdirectory of a shared/slave mount.
-			 */
-			hlist_add_head(&child->mnt_hash, &tmp_list);
-		}
-		prev_dest_mnt = m;
-		prev_src_mnt  = child;
+	/* all slave groups */
+	for (m = next_group(dest_mnt, dest_mnt); m;
+			m = next_group(m, dest_mnt)) {
+		/* everything in that slave group */
+		n = m;
+		do {
+			ret = propagate_one(n);
+			if (ret)
+				goto out;
+			n = next_peer(n);
+		} while (n != m);
 	}
 out:
-	lock_mount_hash();
-	while (!hlist_empty(&tmp_list)) {
-		child = hlist_entry(tmp_list.first, struct mount, mnt_hash);
-		umount_tree(child, 0);
+	read_seqlock_excl(&mount_lock);
+	hlist_for_each_entry(n, tree_list, mnt_hash) {
+		m = n->mnt_parent;
+		if (m->mnt_master != dest_mnt->mnt_master)
+			CLEAR_MNT_MARK(m->mnt_master);
 	}
-	unlock_mount_hash();
+	read_sequnlock_excl(&mount_lock);
 	return ret;
 }
 
diff --git a/fs/pnode.h b/fs/pnode.h
index fc28a27fa892..4a246358b031 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -16,6 +16,9 @@
 #define IS_MNT_NEW(m)  (!(m)->mnt_ns)
 #define CLEAR_MNT_SHARED(m) ((m)->mnt.mnt_flags &= ~MNT_SHARED)
 #define IS_MNT_UNBINDABLE(m) ((m)->mnt.mnt_flags & MNT_UNBINDABLE)
+#define IS_MNT_MARKED(m) ((m)->mnt.mnt_flags & MNT_MARKED)
+#define SET_MNT_MARK(m) ((m)->mnt.mnt_flags |= MNT_MARKED)
+#define CLEAR_MNT_MARK(m) ((m)->mnt.mnt_flags &= ~MNT_MARKED)
 
 #define CL_EXPIRE    		0x01
 #define CL_SLAVE     		0x02
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 371d346fa270..839bac270904 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -44,6 +44,8 @@ struct mnt_namespace;
 #define MNT_SHARED_MASK	(MNT_UNBINDABLE)
 #define MNT_PROPAGATION_MASK	(MNT_SHARED | MNT_UNBINDABLE)
 
+#define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \
+			    MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED)
 
 #define MNT_INTERNAL	0x4000
 
@@ -51,6 +53,7 @@ struct mnt_namespace;
 #define MNT_LOCKED		0x800000
 #define MNT_DOOMED		0x1000000
 #define MNT_SYNC_UMOUNT		0x2000000
+#define MNT_MARKED		0x4000000
 
 struct vfsmount {
 	struct dentry *mnt_root;	/* root of the mounted tree */
-- 
cgit v1.2.3


From e25115786ee540fc428a14872ebd4f56252aba32 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 5 Mar 2014 20:41:36 -0500
Subject: switch nbd to sockfd_lookup/sockfd_put

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/block/nbd.c | 48 +++++++++++++++++++-----------------------------
 include/linux/nbd.h |  3 +--
 2 files changed, 20 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 55298db36b2d..3a70ea2f7cd6 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -630,37 +630,29 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 	}
  
 	case NBD_CLEAR_SOCK: {
-		struct file *file;
-
+		struct socket *sock = nbd->sock;
 		nbd->sock = NULL;
-		file = nbd->file;
-		nbd->file = NULL;
 		nbd_clear_que(nbd);
 		BUG_ON(!list_empty(&nbd->queue_head));
 		BUG_ON(!list_empty(&nbd->waiting_queue));
 		kill_bdev(bdev);
-		if (file)
-			fput(file);
+		if (sock)
+			sockfd_put(sock);
 		return 0;
 	}
 
 	case NBD_SET_SOCK: {
-		struct file *file;
-		if (nbd->file)
+		struct socket *sock;
+		int err;
+		if (nbd->sock)
 			return -EBUSY;
-		file = fget(arg);
-		if (file) {
-			struct inode *inode = file_inode(file);
-			if (S_ISSOCK(inode->i_mode)) {
-				nbd->file = file;
-				nbd->sock = SOCKET_I(inode);
-				if (max_part > 0)
-					bdev->bd_invalidated = 1;
-				nbd->disconnect = 0; /* we're connected now */
-				return 0;
-			} else {
-				fput(file);
-			}
+		sock = sockfd_lookup(arg, &err);
+		if (sock) {
+			nbd->sock = sock;
+			if (max_part > 0)
+				bdev->bd_invalidated = 1;
+			nbd->disconnect = 0; /* we're connected now */
+			return 0;
 		}
 		return -EINVAL;
 	}
@@ -697,12 +689,12 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 
 	case NBD_DO_IT: {
 		struct task_struct *thread;
-		struct file *file;
+		struct socket *sock;
 		int error;
 
 		if (nbd->pid)
 			return -EBUSY;
-		if (!nbd->file)
+		if (!nbd->sock)
 			return -EINVAL;
 
 		mutex_unlock(&nbd->tx_lock);
@@ -731,15 +723,15 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 		if (error)
 			return error;
 		sock_shutdown(nbd, 0);
-		file = nbd->file;
-		nbd->file = NULL;
+		sock = nbd->sock;
+		nbd->sock = NULL;
 		nbd_clear_que(nbd);
 		dev_warn(disk_to_dev(nbd->disk), "queue cleared\n");
 		kill_bdev(bdev);
 		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue);
 		set_device_ro(bdev, false);
-		if (file)
-			fput(file);
+		if (sock)
+			sockfd_put(sock);
 		nbd->flags = 0;
 		nbd->bytesize = 0;
 		bdev->bd_inode->i_size = 0;
@@ -875,9 +867,7 @@ static int __init nbd_init(void)
 
 	for (i = 0; i < nbds_max; i++) {
 		struct gendisk *disk = nbd_dev[i].disk;
-		nbd_dev[i].file = NULL;
 		nbd_dev[i].magic = NBD_MAGIC;
-		nbd_dev[i].flags = 0;
 		INIT_LIST_HEAD(&nbd_dev[i].waiting_queue);
 		spin_lock_init(&nbd_dev[i].queue_lock);
 		INIT_LIST_HEAD(&nbd_dev[i].queue_head);
diff --git a/include/linux/nbd.h b/include/linux/nbd.h
index ae4981ebd18e..f62f78aef4ac 100644
--- a/include/linux/nbd.h
+++ b/include/linux/nbd.h
@@ -24,8 +24,7 @@ struct request;
 struct nbd_device {
 	int flags;
 	int harderror;		/* Code of hard error			*/
-	struct socket * sock;
-	struct file * file; 	/* If == NULL, device is not ready, yet	*/
+	struct socket * sock;	/* If == NULL, device is not ready, yet	*/
 	int magic;
 
 	spinlock_t queue_lock;
-- 
cgit v1.2.3


From 4597e695b8baa3e2620da89c7593be70cf20566b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 14 Mar 2014 10:06:32 -0400
Subject: get rid of DEBUG_WRITECOUNT

it only makes control flow in __fput() and friends more convoluted.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/powerpc/configs/ppc6xx_defconfig |  1 -
 arch/powerpc/configs/ps3_defconfig    |  1 -
 arch/s390/configs/default_defconfig   |  1 -
 arch/sh/configs/rsk7203_defconfig     |  1 -
 arch/xtensa/configs/iss_defconfig     |  1 -
 arch/xtensa/configs/s6105_defconfig   |  1 -
 fs/file_table.c                       |  5 ----
 fs/open.c                             |  8 ------
 include/linux/fs.h                    | 49 -----------------------------------
 lib/Kconfig.debug                     | 10 -------
 10 files changed, 78 deletions(-)

(limited to 'include/linux')

diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index c2353bf059fd..175a8b99c196 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -1244,7 +1244,6 @@ CONFIG_DEBUG_SPINLOCK_SLEEP=y
 CONFIG_DEBUG_HIGHMEM=y
 CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_VM=y
-CONFIG_DEBUG_WRITECOUNT=y
 CONFIG_DEBUG_LIST=y
 CONFIG_DEBUG_SG=y
 # CONFIG_RCU_CPU_STALL_DETECTOR is not set
diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig
index 139a8308070c..fdee37fab81c 100644
--- a/arch/powerpc/configs/ps3_defconfig
+++ b/arch/powerpc/configs/ps3_defconfig
@@ -174,7 +174,6 @@ CONFIG_DETECT_HUNG_TASK=y
 CONFIG_PROVE_LOCKING=y
 CONFIG_DEBUG_LOCKDEP=y
 CONFIG_DEBUG_INFO=y
-CONFIG_DEBUG_WRITECOUNT=y
 CONFIG_DEBUG_MEMORY_INIT=y
 CONFIG_DEBUG_LIST=y
 CONFIG_RCU_CPU_STALL_TIMEOUT=60
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index e0af2ee58751..3f538468a86e 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -550,7 +550,6 @@ CONFIG_LOCK_STAT=y
 CONFIG_DEBUG_LOCKDEP=y
 CONFIG_DEBUG_ATOMIC_SLEEP=y
 CONFIG_DEBUG_LOCKING_API_SELFTESTS=y
-CONFIG_DEBUG_WRITECOUNT=y
 CONFIG_DEBUG_LIST=y
 CONFIG_DEBUG_SG=y
 CONFIG_DEBUG_NOTIFIERS=y
diff --git a/arch/sh/configs/rsk7203_defconfig b/arch/sh/configs/rsk7203_defconfig
index 4e5229b0c5bb..47236573db83 100644
--- a/arch/sh/configs/rsk7203_defconfig
+++ b/arch/sh/configs/rsk7203_defconfig
@@ -128,7 +128,6 @@ CONFIG_DEBUG_MUTEXES=y
 CONFIG_DEBUG_SPINLOCK_SLEEP=y
 CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_VM=y
-CONFIG_DEBUG_WRITECOUNT=y
 CONFIG_DEBUG_LIST=y
 CONFIG_DEBUG_SG=y
 CONFIG_FRAME_POINTER=y
diff --git a/arch/xtensa/configs/iss_defconfig b/arch/xtensa/configs/iss_defconfig
index 4f233204faf9..711f8aa14743 100644
--- a/arch/xtensa/configs/iss_defconfig
+++ b/arch/xtensa/configs/iss_defconfig
@@ -627,7 +627,6 @@ CONFIG_SCHED_DEBUG=y
 # CONFIG_DEBUG_KOBJECT is not set
 # CONFIG_DEBUG_INFO is not set
 # CONFIG_DEBUG_VM is not set
-# CONFIG_DEBUG_WRITECOUNT is not set
 # CONFIG_DEBUG_MEMORY_INIT is not set
 # CONFIG_DEBUG_LIST is not set
 # CONFIG_DEBUG_SG is not set
diff --git a/arch/xtensa/configs/s6105_defconfig b/arch/xtensa/configs/s6105_defconfig
index d929f77a0360..78318a76fa16 100644
--- a/arch/xtensa/configs/s6105_defconfig
+++ b/arch/xtensa/configs/s6105_defconfig
@@ -569,7 +569,6 @@ CONFIG_DEBUG_SPINLOCK_SLEEP=y
 # CONFIG_DEBUG_INFO is not set
 # CONFIG_DEBUG_VM is not set
 CONFIG_DEBUG_NOMMU_REGIONS=y
-# CONFIG_DEBUG_WRITECOUNT is not set
 # CONFIG_DEBUG_MEMORY_INIT is not set
 # CONFIG_DEBUG_LIST is not set
 # CONFIG_DEBUG_SG is not set
diff --git a/fs/file_table.c b/fs/file_table.c
index 79ecae62209a..ee20658a0647 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -52,7 +52,6 @@ static void file_free_rcu(struct rcu_head *head)
 static inline void file_free(struct file *f)
 {
 	percpu_counter_dec(&nr_files);
-	file_check_state(f);
 	call_rcu(&f->f_u.fu_rcuhead, file_free_rcu);
 }
 
@@ -186,7 +185,6 @@ struct file *alloc_file(struct path *path, fmode_t mode,
 	 * that we can do debugging checks at __fput()
 	 */
 	if ((mode & FMODE_WRITE) && !special_file(path->dentry->d_inode->i_mode)) {
-		file_take_write(file);
 		WARN_ON(mnt_clone_write(path->mnt));
 	}
 	if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
@@ -213,10 +211,7 @@ static void drop_file_write_access(struct file *file)
 		return;
 
 	put_write_access(inode);
-	if (file_check_writeable(file) != 0)
-		return;
 	__mnt_drop_write(mnt);
-	file_release_write(file);
 }
 
 /* the real guts of fput() - releasing the last reference to file
diff --git a/fs/open.c b/fs/open.c
index 2ed7325f713e..8d0b6adfe7b8 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -683,7 +683,6 @@ static int do_dentry_open(struct file *f,
 		error = __get_file_write_access(inode, f->f_path.mnt);
 		if (error)
 			goto cleanup_file;
-		file_take_write(f);
 	}
 
 	f->f_mapping = inode->i_mapping;
@@ -731,14 +730,7 @@ cleanup_all:
 	fops_put(f->f_op);
 	if (f->f_mode & FMODE_WRITE) {
 		if (!special_file(inode->i_mode)) {
-			/*
-			 * We don't consider this a real
-			 * mnt_want/drop_write() pair
-			 * because it all happenend right
-			 * here, so just reset the state.
-			 */
 			put_write_access(inode);
-			file_reset_write(f);
 			__mnt_drop_write(f->f_path.mnt);
 		}
 	}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 23b2a35d712e..e80659ed78fc 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -769,9 +769,6 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
 		index <  ra->start + ra->size);
 }
 
-#define FILE_MNT_WRITE_TAKEN	1
-#define FILE_MNT_WRITE_RELEASED	2
-
 struct file {
 	union {
 		struct llist_node	fu_llist;
@@ -809,9 +806,6 @@ struct file {
 	struct list_head	f_tfile_llink;
 #endif /* #ifdef CONFIG_EPOLL */
 	struct address_space	*f_mapping;
-#ifdef CONFIG_DEBUG_WRITECOUNT
-	unsigned long f_mnt_write_state;
-#endif
 } __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */
 
 struct file_handle {
@@ -829,49 +823,6 @@ static inline struct file *get_file(struct file *f)
 #define fput_atomic(x)	atomic_long_add_unless(&(x)->f_count, -1, 1)
 #define file_count(x)	atomic_long_read(&(x)->f_count)
 
-#ifdef CONFIG_DEBUG_WRITECOUNT
-static inline void file_take_write(struct file *f)
-{
-	WARN_ON(f->f_mnt_write_state != 0);
-	f->f_mnt_write_state = FILE_MNT_WRITE_TAKEN;
-}
-static inline void file_release_write(struct file *f)
-{
-	f->f_mnt_write_state |= FILE_MNT_WRITE_RELEASED;
-}
-static inline void file_reset_write(struct file *f)
-{
-	f->f_mnt_write_state = 0;
-}
-static inline void file_check_state(struct file *f)
-{
-	/*
-	 * At this point, either both or neither of these bits
-	 * should be set.
-	 */
-	WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN);
-	WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_RELEASED);
-}
-static inline int file_check_writeable(struct file *f)
-{
-	if (f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN)
-		return 0;
-	printk(KERN_WARNING "writeable file with no "
-			    "mnt_want_write()\n");
-	WARN_ON(1);
-	return -EINVAL;
-}
-#else /* !CONFIG_DEBUG_WRITECOUNT */
-static inline void file_take_write(struct file *filp) {}
-static inline void file_release_write(struct file *filp) {}
-static inline void file_reset_write(struct file *filp) {}
-static inline void file_check_state(struct file *filp) {}
-static inline int file_check_writeable(struct file *filp)
-{
-	return 0;
-}
-#endif /* CONFIG_DEBUG_WRITECOUNT */
-
 #define	MAX_NON_LFS	((1UL<<31) - 1)
 
 /* Page cache limit. The filesystems should put that into their s_maxbytes 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index a48abeac753f..7a0859314bdf 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1030,16 +1030,6 @@ config DEBUG_BUGVERBOSE
 	  of the BUG call as well as the EIP and oops trace.  This aids
 	  debugging but costs about 70-100K of memory.
 
-config DEBUG_WRITECOUNT
-	bool "Debug filesystem writers count"
-	depends on DEBUG_KERNEL
-	help
-	  Enable this to catch wrong use of the writers count in struct
-	  vfsmount.  This will increase the size of each file struct by
-	  32 bits.
-
-	  If unsure, say N.
-
 config DEBUG_LIST
 	bool "Debug linked list manipulation"
 	depends on DEBUG_KERNEL
-- 
cgit v1.2.3


From 83f936c75e3689a63253d89c47a4d239c56d7410 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 14 Mar 2014 12:02:47 -0400
Subject: mark struct file that had write access grabbed by open()

new flag in ->f_mode - FMODE_WRITER.  Set by do_dentry_open() in case
when it has grabbed write access, checked by __fput() to decide whether
it wants to drop the sucker.  Allows to stop bothering with mnt_clone_write()
in alloc_file(), along with fewer special_file() checks.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/file_table.c    | 37 ++++---------------------------------
 fs/namespace.c     |  4 +---
 fs/open.c          |  9 ++++-----
 include/linux/fs.h |  2 ++
 4 files changed, 11 insertions(+), 41 deletions(-)

(limited to 'include/linux')

diff --git a/fs/file_table.c b/fs/file_table.c
index ee20658a0647..ce1504fec5a1 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -177,43 +177,12 @@ struct file *alloc_file(struct path *path, fmode_t mode,
 	file->f_mapping = path->dentry->d_inode->i_mapping;
 	file->f_mode = mode;
 	file->f_op = fop;
-
-	/*
-	 * These mounts don't really matter in practice
-	 * for r/o bind mounts.  They aren't userspace-
-	 * visible.  We do this for consistency, and so
-	 * that we can do debugging checks at __fput()
-	 */
-	if ((mode & FMODE_WRITE) && !special_file(path->dentry->d_inode->i_mode)) {
-		WARN_ON(mnt_clone_write(path->mnt));
-	}
 	if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
 		i_readcount_inc(path->dentry->d_inode);
 	return file;
 }
 EXPORT_SYMBOL(alloc_file);
 
-/**
- * drop_file_write_access - give up ability to write to a file
- * @file: the file to which we will stop writing
- *
- * This is a central place which will give up the ability
- * to write to @file, along with access to write through
- * its vfsmount.
- */
-static void drop_file_write_access(struct file *file)
-{
-	struct vfsmount *mnt = file->f_path.mnt;
-	struct dentry *dentry = file->f_path.dentry;
-	struct inode *inode = dentry->d_inode;
-
-	if (special_file(inode->i_mode))
-		return;
-
-	put_write_access(inode);
-	__mnt_drop_write(mnt);
-}
-
 /* the real guts of fput() - releasing the last reference to file
  */
 static void __fput(struct file *file)
@@ -248,8 +217,10 @@ static void __fput(struct file *file)
 	put_pid(file->f_owner.pid);
 	if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
 		i_readcount_dec(inode);
-	if (file->f_mode & FMODE_WRITE)
-		drop_file_write_access(file);
+	if (file->f_mode & FMODE_WRITER) {
+		put_write_access(inode);
+		__mnt_drop_write(mnt);
+	}
 	file->f_path.dentry = NULL;
 	file->f_path.mnt = NULL;
 	file->f_inode = NULL;
diff --git a/fs/namespace.c b/fs/namespace.c
index a66aff5bd3fe..20e8696c31a7 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -414,9 +414,7 @@ EXPORT_SYMBOL_GPL(mnt_clone_write);
  */
 int __mnt_want_write_file(struct file *file)
 {
-	struct inode *inode = file_inode(file);
-
-	if (!(file->f_mode & FMODE_WRITE) || special_file(inode->i_mode))
+	if (!(file->f_mode & FMODE_WRITER))
 		return __mnt_want_write(file->f_path.mnt);
 	else
 		return mnt_clone_write(file->f_path.mnt);
diff --git a/fs/open.c b/fs/open.c
index ebef0c5fa10c..dcefb2f02d10 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -670,6 +670,7 @@ static int do_dentry_open(struct file *f,
 			put_write_access(inode);
 			goto cleanup_file;
 		}
+		f->f_mode |= FMODE_WRITER;
 	}
 
 	f->f_mapping = inode->i_mapping;
@@ -715,11 +716,9 @@ static int do_dentry_open(struct file *f,
 
 cleanup_all:
 	fops_put(f->f_op);
-	if (f->f_mode & FMODE_WRITE) {
-		if (!special_file(inode->i_mode)) {
-			put_write_access(inode);
-			__mnt_drop_write(f->f_path.mnt);
-		}
+	if (f->f_mode & FMODE_WRITER) {
+		put_write_access(inode);
+		__mnt_drop_write(f->f_path.mnt);
 	}
 cleanup_file:
 	path_put(&f->f_path);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e80659ed78fc..d9d88a0b456e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -125,6 +125,8 @@ typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 
 /* File needs atomic accesses to f_pos */
 #define FMODE_ATOMIC_POS	((__force fmode_t)0x8000)
+/* Write access to underlying fs */
+#define FMODE_WRITER		((__force fmode_t)0x10000)
 
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY		((__force fmode_t)0x1000000)
-- 
cgit v1.2.3


From 7f4b36f9bb930b3b2105a9a2cb0121fa7028c432 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 14 Mar 2014 12:45:29 -0400
Subject: get rid of files_defer_init()

the only thing it's doing these days is calculation of
upper limit for fs.nr_open sysctl and that can be done
statically

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/file.c               | 11 ++++-------
 fs/file_table.c         |  1 -
 include/linux/fdtable.h |  2 --
 3 files changed, 4 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/fs/file.c b/fs/file.c
index eb56a13dab3e..682103b95f8f 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -25,7 +25,10 @@
 
 int sysctl_nr_open __read_mostly = 1024*1024;
 int sysctl_nr_open_min = BITS_PER_LONG;
-int sysctl_nr_open_max = 1024 * 1024; /* raised later */
+/* our max() is unusable in constant expressions ;-/ */
+#define __const_max(x, y) ((x) < (y) ? (x) : (y))
+int sysctl_nr_open_max = __const_max(INT_MAX, ~(size_t)0/sizeof(void *)) &
+			 -BITS_PER_LONG;
 
 static void *alloc_fdmem(size_t size)
 {
@@ -429,12 +432,6 @@ void exit_files(struct task_struct *tsk)
 	}
 }
 
-void __init files_defer_init(void)
-{
-	sysctl_nr_open_max = min((size_t)INT_MAX, ~(size_t)0/sizeof(void *)) &
-			     -BITS_PER_LONG;
-}
-
 struct files_struct init_files = {
 	.count		= ATOMIC_INIT(1),
 	.fdt		= &init_files.fdtab,
diff --git a/fs/file_table.c b/fs/file_table.c
index ce1504fec5a1..718e8e5224f8 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -325,6 +325,5 @@ void __init files_init(unsigned long mempages)
 
 	n = (mempages * (PAGE_SIZE / 1024)) / 10;
 	files_stat.max_files = max_t(unsigned long, n, NR_FILE);
-	files_defer_init();
 	percpu_counter_init(&nr_files, 0);
 } 
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index 70e8e21c0a30..230f87bdf5ad 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -63,8 +63,6 @@ struct file_operations;
 struct vfsmount;
 struct dentry;
 
-extern void __init files_defer_init(void);
-
 #define rcu_dereference_check_fdtable(files, fdtfd) \
 	rcu_dereference_check((fdtfd), lockdep_is_held(&(files)->file_lock))
 
-- 
cgit v1.2.3


From 5d826c847b34de6415b4f1becd88a57ff619af50 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 14 Mar 2014 13:42:45 -0400
Subject: new helper: readlink_copy()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c           | 13 +++++--------
 fs/proc/namespaces.c | 14 ++++----------
 fs/proc/self.c       |  2 +-
 fs/xfs/xfs_ioctl.c   | 28 +---------------------------
 include/linux/fs.h   |  2 +-
 5 files changed, 12 insertions(+), 47 deletions(-)

(limited to 'include/linux')

diff --git a/fs/namei.c b/fs/namei.c
index 617de9e9967b..4fb52f0ca5cb 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -4297,11 +4297,9 @@ SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newna
 	return sys_renameat(AT_FDCWD, oldname, AT_FDCWD, newname);
 }
 
-int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen, const char *link)
+int readlink_copy(char __user *buffer, int buflen, const char *link)
 {
-	int len;
-
-	len = PTR_ERR(link);
+	int len = PTR_ERR(link);
 	if (IS_ERR(link))
 		goto out;
 
@@ -4313,7 +4311,7 @@ int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen, const c
 out:
 	return len;
 }
-EXPORT_SYMBOL(vfs_readlink);
+EXPORT_SYMBOL(readlink_copy);
 
 /*
  * A helper for ->readlink().  This should be used *ONLY* for symlinks that
@@ -4331,7 +4329,7 @@ int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 	if (IS_ERR(cookie))
 		return PTR_ERR(cookie);
 
-	res = vfs_readlink(dentry, buffer, buflen, nd_get_link(&nd));
+	res = readlink_copy(buffer, buflen, nd_get_link(&nd));
 	if (dentry->d_inode->i_op->put_link)
 		dentry->d_inode->i_op->put_link(dentry, &nd, cookie);
 	return res;
@@ -4356,8 +4354,7 @@ static char *page_getlink(struct dentry * dentry, struct page **ppage)
 int page_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 {
 	struct page *page = NULL;
-	char *s = page_getlink(dentry, &page);
-	int res = vfs_readlink(dentry,buffer,buflen,s);
+	int res = readlink_copy(buffer, buflen, page_getlink(dentry, &page));
 	if (page) {
 		kunmap(page);
 		page_cache_release(page);
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 9ae46b87470d..89026095f2b5 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -146,7 +146,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl
 	struct task_struct *task;
 	void *ns;
 	char name[50];
-	int len = -EACCES;
+	int res = -EACCES;
 
 	task = get_proc_task(inode);
 	if (!task)
@@ -155,24 +155,18 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl
 	if (!ptrace_may_access(task, PTRACE_MODE_READ))
 		goto out_put_task;
 
-	len = -ENOENT;
+	res = -ENOENT;
 	ns = ns_ops->get(task);
 	if (!ns)
 		goto out_put_task;
 
 	snprintf(name, sizeof(name), "%s:[%u]", ns_ops->name, ns_ops->inum(ns));
-	len = strlen(name);
-
-	if (len > buflen)
-		len = buflen;
-	if (copy_to_user(buffer, name, len))
-		len = -EFAULT;
-
+	res = readlink_copy(buffer, buflen, name);
 	ns_ops->put(ns);
 out_put_task:
 	put_task_struct(task);
 out:
-	return len;
+	return res;
 }
 
 static const struct inode_operations proc_ns_link_inode_operations = {
diff --git a/fs/proc/self.c b/fs/proc/self.c
index ffeb202ec942..4348bb8907c2 100644
--- a/fs/proc/self.c
+++ b/fs/proc/self.c
@@ -16,7 +16,7 @@ static int proc_self_readlink(struct dentry *dentry, char __user *buffer,
 	if (!tgid)
 		return -ENOENT;
 	sprintf(tmp, "%d", tgid);
-	return vfs_readlink(dentry,buffer,buflen,tmp);
+	return readlink_copy(buffer, buflen, tmp);
 }
 
 static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd)
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index bcfe61202115..0b18776b075e 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -271,32 +271,6 @@ xfs_open_by_handle(
 	return error;
 }
 
-/*
- * This is a copy from fs/namei.c:vfs_readlink(), except for removing it's
- * unused first argument.
- */
-STATIC int
-do_readlink(
-	char __user		*buffer,
-	int			buflen,
-	const char		*link)
-{
-        int len;
-
-	len = PTR_ERR(link);
-	if (IS_ERR(link))
-		goto out;
-
-	len = strlen(link);
-	if (len > (unsigned) buflen)
-		len = buflen;
-	if (copy_to_user(buffer, link, len))
-		len = -EFAULT;
- out:
-	return len;
-}
-
-
 int
 xfs_readlink_by_handle(
 	struct file		*parfilp,
@@ -334,7 +308,7 @@ xfs_readlink_by_handle(
 	error = -xfs_readlink(XFS_I(dentry->d_inode), link);
 	if (error)
 		goto out_kfree;
-	error = do_readlink(hreq->ohandle, olen, link);
+	error = readlink_copy(hreq->ohandle, olen, link);
 	if (error)
 		goto out_kfree;
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index d9d88a0b456e..db181b542db1 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2517,7 +2517,7 @@ extern const struct file_operations generic_ro_fops;
 
 #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m))
 
-extern int vfs_readlink(struct dentry *, char __user *, int, const char *);
+extern int readlink_copy(char __user *, int, const char *);
 extern int page_readlink(struct dentry *, char __user *, int);
 extern void *page_follow_link_light(struct dentry *, struct nameidata *);
 extern void page_put_link(struct dentry *, struct nameidata *, void *);
-- 
cgit v1.2.3


From fbb32750a62df75d1ffea547f3908b21c5496d9f Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 2 Feb 2014 21:09:54 -0500
Subject: pipe: kill ->map() and ->unmap()

all pipe_buffer_operations have the same instances of those...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/char/virtio_console.c |  4 +--
 fs/fuse/dev.c                 |  6 ++--
 fs/pipe.c                     | 70 ++++++++++---------------------------------
 fs/splice.c                   | 24 +++++----------
 include/linux/pipe_fs_i.h     | 19 ------------
 kernel/relay.c                |  2 --
 kernel/trace/trace.c          |  4 ---
 7 files changed, 29 insertions(+), 100 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 6928d094451d..60aafb8a1f2e 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -901,9 +901,9 @@ static int pipe_to_sg(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 		if (len + offset > PAGE_SIZE)
 			len = PAGE_SIZE - offset;
 
-		src = buf->ops->map(pipe, buf, 1);
+		src = kmap_atomic(buf->page);
 		memcpy(page_address(page) + offset, src + buf->offset, len);
-		buf->ops->unmap(pipe, buf, src);
+		kunmap_atomic(src);
 
 		sg_set_page(&(sgl->sg[sgl->n]), page, len, offset);
 	}
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index f90af6fe6884..aac71ce373e4 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -667,7 +667,7 @@ static void fuse_copy_finish(struct fuse_copy_state *cs)
 		struct pipe_buffer *buf = cs->currbuf;
 
 		if (!cs->write) {
-			buf->ops->unmap(cs->pipe, buf, cs->mapaddr);
+			kunmap_atomic(cs->mapaddr);
 		} else {
 			kunmap_atomic(cs->mapaddr);
 			buf->len = PAGE_SIZE - cs->len;
@@ -706,7 +706,7 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
 
 			BUG_ON(!cs->nr_segs);
 			cs->currbuf = buf;
-			cs->mapaddr = buf->ops->map(cs->pipe, buf, 1);
+			cs->mapaddr = kmap_atomic(buf->page);
 			cs->len = buf->len;
 			cs->buf = cs->mapaddr + buf->offset;
 			cs->pipebufs++;
@@ -874,7 +874,7 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
 out_fallback_unlock:
 	unlock_page(newpage);
 out_fallback:
-	cs->mapaddr = buf->ops->map(cs->pipe, buf, 1);
+	cs->mapaddr = kmap_atomic(buf->page);
 	cs->buf = cs->mapaddr + buf->offset;
 
 	err = lock_request(cs->fc, cs->req);
diff --git a/fs/pipe.c b/fs/pipe.c
index 78fd0d0788db..6679c95eb4c3 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -225,52 +225,6 @@ static void anon_pipe_buf_release(struct pipe_inode_info *pipe,
 		page_cache_release(page);
 }
 
-/**
- * generic_pipe_buf_map - virtually map a pipe buffer
- * @pipe:	the pipe that the buffer belongs to
- * @buf:	the buffer that should be mapped
- * @atomic:	whether to use an atomic map
- *
- * Description:
- *	This function returns a kernel virtual address mapping for the
- *	pipe_buffer passed in @buf. If @atomic is set, an atomic map is provided
- *	and the caller has to be careful not to fault before calling
- *	the unmap function.
- *
- *	Note that this function calls kmap_atomic() if @atomic != 0.
- */
-void *generic_pipe_buf_map(struct pipe_inode_info *pipe,
-			   struct pipe_buffer *buf, int atomic)
-{
-	if (atomic) {
-		buf->flags |= PIPE_BUF_FLAG_ATOMIC;
-		return kmap_atomic(buf->page);
-	}
-
-	return kmap(buf->page);
-}
-EXPORT_SYMBOL(generic_pipe_buf_map);
-
-/**
- * generic_pipe_buf_unmap - unmap a previously mapped pipe buffer
- * @pipe:	the pipe that the buffer belongs to
- * @buf:	the buffer that should be unmapped
- * @map_data:	the data that the mapping function returned
- *
- * Description:
- *	This function undoes the mapping that ->map() provided.
- */
-void generic_pipe_buf_unmap(struct pipe_inode_info *pipe,
-			    struct pipe_buffer *buf, void *map_data)
-{
-	if (buf->flags & PIPE_BUF_FLAG_ATOMIC) {
-		buf->flags &= ~PIPE_BUF_FLAG_ATOMIC;
-		kunmap_atomic(map_data);
-	} else
-		kunmap(buf->page);
-}
-EXPORT_SYMBOL(generic_pipe_buf_unmap);
-
 /**
  * generic_pipe_buf_steal - attempt to take ownership of a &pipe_buffer
  * @pipe:	the pipe that the buffer belongs to
@@ -351,8 +305,6 @@ EXPORT_SYMBOL(generic_pipe_buf_release);
 
 static const struct pipe_buf_operations anon_pipe_buf_ops = {
 	.can_merge = 1,
-	.map = generic_pipe_buf_map,
-	.unmap = generic_pipe_buf_unmap,
 	.confirm = generic_pipe_buf_confirm,
 	.release = anon_pipe_buf_release,
 	.steal = generic_pipe_buf_steal,
@@ -361,8 +313,6 @@ static const struct pipe_buf_operations anon_pipe_buf_ops = {
 
 static const struct pipe_buf_operations packet_pipe_buf_ops = {
 	.can_merge = 0,
-	.map = generic_pipe_buf_map,
-	.unmap = generic_pipe_buf_unmap,
 	.confirm = generic_pipe_buf_confirm,
 	.release = anon_pipe_buf_release,
 	.steal = generic_pipe_buf_steal,
@@ -410,9 +360,15 @@ pipe_read(struct kiocb *iocb, const struct iovec *_iov,
 
 			atomic = !iov_fault_in_pages_write(iov, chars);
 redo:
-			addr = ops->map(pipe, buf, atomic);
+			if (atomic)
+				addr = kmap_atomic(buf->page);
+			else
+				addr = kmap(buf->page);
 			error = pipe_iov_copy_to_user(iov, addr + buf->offset, chars, atomic);
-			ops->unmap(pipe, buf, addr);
+			if (atomic)
+				kunmap_atomic(addr);
+			else
+				kunmap(buf->page);
 			if (unlikely(error)) {
 				/*
 				 * Just retry with the slow path if we failed.
@@ -538,10 +494,16 @@ pipe_write(struct kiocb *iocb, const struct iovec *_iov,
 
 			iov_fault_in_pages_read(iov, chars);
 redo1:
-			addr = ops->map(pipe, buf, atomic);
+			if (atomic)
+				addr = kmap_atomic(buf->page);
+			else
+				addr = kmap(buf->page);
 			error = pipe_iov_copy_from_user(offset + addr, iov,
 							chars, atomic);
-			ops->unmap(pipe, buf, addr);
+			if (atomic)
+				kunmap_atomic(addr);
+			else
+				kunmap(buf->page);
 			ret = error;
 			do_wakeup = 1;
 			if (error) {
diff --git a/fs/splice.c b/fs/splice.c
index 12028fa41def..ca3bfbd970f3 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -136,8 +136,6 @@ error:
 
 const struct pipe_buf_operations page_cache_pipe_buf_ops = {
 	.can_merge = 0,
-	.map = generic_pipe_buf_map,
-	.unmap = generic_pipe_buf_unmap,
 	.confirm = page_cache_pipe_buf_confirm,
 	.release = page_cache_pipe_buf_release,
 	.steal = page_cache_pipe_buf_steal,
@@ -156,8 +154,6 @@ static int user_page_pipe_buf_steal(struct pipe_inode_info *pipe,
 
 static const struct pipe_buf_operations user_page_pipe_buf_ops = {
 	.can_merge = 0,
-	.map = generic_pipe_buf_map,
-	.unmap = generic_pipe_buf_unmap,
 	.confirm = generic_pipe_buf_confirm,
 	.release = page_cache_pipe_buf_release,
 	.steal = user_page_pipe_buf_steal,
@@ -547,8 +543,6 @@ EXPORT_SYMBOL(generic_file_splice_read);
 
 static const struct pipe_buf_operations default_pipe_buf_ops = {
 	.can_merge = 0,
-	.map = generic_pipe_buf_map,
-	.unmap = generic_pipe_buf_unmap,
 	.confirm = generic_pipe_buf_confirm,
 	.release = generic_pipe_buf_release,
 	.steal = generic_pipe_buf_steal,
@@ -564,8 +558,6 @@ static int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe,
 /* Pipe buffer operations for a socket and similar. */
 const struct pipe_buf_operations nosteal_pipe_buf_ops = {
 	.can_merge = 0,
-	.map = generic_pipe_buf_map,
-	.unmap = generic_pipe_buf_unmap,
 	.confirm = generic_pipe_buf_confirm,
 	.release = generic_pipe_buf_release,
 	.steal = generic_pipe_buf_nosteal,
@@ -767,13 +759,13 @@ int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 		goto out;
 
 	if (buf->page != page) {
-		char *src = buf->ops->map(pipe, buf, 1);
+		char *src = kmap_atomic(buf->page);
 		char *dst = kmap_atomic(page);
 
 		memcpy(dst + offset, src + buf->offset, this_len);
 		flush_dcache_page(page);
 		kunmap_atomic(dst);
-		buf->ops->unmap(pipe, buf, src);
+		kunmap_atomic(src);
 	}
 	ret = pagecache_write_end(file, mapping, sd->pos, this_len, this_len,
 				page, fsdata);
@@ -1067,9 +1059,9 @@ static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 	void *data;
 	loff_t tmp = sd->pos;
 
-	data = buf->ops->map(pipe, buf, 0);
+	data = kmap(buf->page);
 	ret = __kernel_write(sd->u.file, data + buf->offset, sd->len, &tmp);
-	buf->ops->unmap(pipe, buf, data);
+	kunmap(buf->page);
 
 	return ret;
 }
@@ -1536,10 +1528,10 @@ static int pipe_to_user(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 	 * pages and doing an atomic copy
 	 */
 	if (!fault_in_pages_writeable(sd->u.userptr, sd->len)) {
-		src = buf->ops->map(pipe, buf, 1);
+		src = kmap_atomic(buf->page);
 		ret = __copy_to_user_inatomic(sd->u.userptr, src + buf->offset,
 							sd->len);
-		buf->ops->unmap(pipe, buf, src);
+		kunmap_atomic(src);
 		if (!ret) {
 			ret = sd->len;
 			goto out;
@@ -1549,13 +1541,13 @@ static int pipe_to_user(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
 	/*
 	 * No dice, use slow non-atomic map and copy
  	 */
-	src = buf->ops->map(pipe, buf, 0);
+	src = kmap(buf->page);
 
 	ret = sd->len;
 	if (copy_to_user(sd->u.userptr, src + buf->offset, sd->len))
 		ret = -EFAULT;
 
-	buf->ops->unmap(pipe, buf, src);
+	kunmap(buf->page);
 out:
 	if (ret > 0)
 		sd->u.userptr += ret;
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index ab5752692113..6dffcebe6105 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -82,23 +82,6 @@ struct pipe_buf_operations {
 	 */
 	int can_merge;
 
-	/*
-	 * ->map() returns a virtual address mapping of the pipe buffer.
-	 * The last integer flag reflects whether this should be an atomic
-	 * mapping or not. The atomic map is faster, however you can't take
-	 * page faults before calling ->unmap() again. So if you need to eg
-	 * access user data through copy_to/from_user(), then you must get
-	 * a non-atomic map. ->map() uses the kmap_atomic slot for
-	 * atomic maps, you have to be careful if mapping another page as
-	 * source or destination for a copy.
-	 */
-	void * (*map)(struct pipe_inode_info *, struct pipe_buffer *, int);
-
-	/*
-	 * Undoes ->map(), finishes the virtual mapping of the pipe buffer.
-	 */
-	void (*unmap)(struct pipe_inode_info *, struct pipe_buffer *, void *);
-
 	/*
 	 * ->confirm() verifies that the data in the pipe buffer is there
 	 * and that the contents are good. If the pages in the pipe belong
@@ -150,8 +133,6 @@ struct pipe_inode_info *alloc_pipe_info(void);
 void free_pipe_info(struct pipe_inode_info *);
 
 /* Generic pipe buffer ops functions */
-void *generic_pipe_buf_map(struct pipe_inode_info *, struct pipe_buffer *, int);
-void generic_pipe_buf_unmap(struct pipe_inode_info *, struct pipe_buffer *, void *);
 void generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *);
diff --git a/kernel/relay.c b/kernel/relay.c
index 5001c9887db1..98833f664fb6 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -1195,8 +1195,6 @@ static void relay_pipe_buf_release(struct pipe_inode_info *pipe,
 
 static const struct pipe_buf_operations relay_pipe_buf_ops = {
 	.can_merge = 0,
-	.map = generic_pipe_buf_map,
-	.unmap = generic_pipe_buf_unmap,
 	.confirm = generic_pipe_buf_confirm,
 	.release = relay_pipe_buf_release,
 	.steal = generic_pipe_buf_steal,
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 24c1f2382557..7511de35257f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4316,8 +4316,6 @@ static void tracing_spd_release_pipe(struct splice_pipe_desc *spd,
 
 static const struct pipe_buf_operations tracing_pipe_buf_ops = {
 	.can_merge		= 0,
-	.map			= generic_pipe_buf_map,
-	.unmap			= generic_pipe_buf_unmap,
 	.confirm		= generic_pipe_buf_confirm,
 	.release		= generic_pipe_buf_release,
 	.steal			= generic_pipe_buf_steal,
@@ -5194,8 +5192,6 @@ static void buffer_pipe_buf_get(struct pipe_inode_info *pipe,
 /* Pipe buffer operations for a buffer. */
 static const struct pipe_buf_operations buffer_pipe_buf_ops = {
 	.can_merge		= 0,
-	.map			= generic_pipe_buf_map,
-	.unmap			= generic_pipe_buf_unmap,
 	.confirm		= generic_pipe_buf_confirm,
 	.release		= buffer_pipe_buf_release,
 	.steal			= generic_pipe_buf_steal,
-- 
cgit v1.2.3


From c186afb4dbd0050a537b96c7fbee2dba3b57fc38 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 2 Feb 2014 21:16:54 -0500
Subject: switch ->is_partially_uptodate() to saner arguments

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 Documentation/filesystems/Locking | 2 +-
 Documentation/filesystems/vfs.txt | 2 +-
 fs/buffer.c                       | 6 +++---
 include/linux/buffer_head.h       | 4 ++--
 include/linux/fs.h                | 2 +-
 mm/filemap.c                      | 2 +-
 6 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 5b0c083d7c0e..bb2534bc0b03 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -198,7 +198,7 @@ prototypes:
 				unsigned long *);
 	int (*migratepage)(struct address_space *, struct page *, struct page *);
 	int (*launder_page)(struct page *);
-	int (*is_partially_uptodate)(struct page *, read_descriptor_t *, unsigned long);
+	int (*is_partially_uptodate)(struct page *, unsigned long, unsigned long);
 	int (*error_remove_page)(struct address_space *, struct page *);
 	int (*swap_activate)(struct file *);
 	int (*swap_deactivate)(struct file *);
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index c53784c119c8..419e7348c481 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -580,7 +580,7 @@ struct address_space_operations {
 	/* migrate the contents of a page to the specified target */
 	int (*migratepage) (struct page *, struct page *);
 	int (*launder_page) (struct page *);
-	int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
+	int (*is_partially_uptodate) (struct page *, unsigned long,
 					unsigned long);
 	void (*is_dirty_writeback) (struct page *, bool *, bool *);
 	int (*error_remove_page) (struct mapping *mapping, struct page *page);
diff --git a/fs/buffer.c b/fs/buffer.c
index 27265a8b43c1..027ae3bdfbbd 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2114,8 +2114,8 @@ EXPORT_SYMBOL(generic_write_end);
  * Returns true if all buffers which correspond to a file portion
  * we want to read are uptodate.
  */
-int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
-					unsigned long from)
+int block_is_partially_uptodate(struct page *page, unsigned long from,
+					unsigned long count)
 {
 	unsigned block_start, block_end, blocksize;
 	unsigned to;
@@ -2127,7 +2127,7 @@ int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
 
 	head = page_buffers(page);
 	blocksize = head->b_size;
-	to = min_t(unsigned, PAGE_CACHE_SIZE - from, desc->count);
+	to = min_t(unsigned, PAGE_CACHE_SIZE - from, count);
 	to = from + to;
 	if (from < blocksize && to > PAGE_CACHE_SIZE - blocksize)
 		return 0;
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index d77797a52b7b..c40302f909ce 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -210,8 +210,8 @@ int block_write_full_page(struct page *page, get_block_t *get_block,
 int block_write_full_page_endio(struct page *page, get_block_t *get_block,
 			struct writeback_control *wbc, bh_end_io_t *handler);
 int block_read_full_page(struct page*, get_block_t*);
-int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
-				unsigned long from);
+int block_is_partially_uptodate(struct page *page, unsigned long from,
+				unsigned long count);
 int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
 		unsigned flags, struct page **pagep, get_block_t *get_block);
 int __block_write_begin(struct page *page, loff_t pos, unsigned len,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index db181b542db1..ddfff2ecef0b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -385,7 +385,7 @@ struct address_space_operations {
 	int (*migratepage) (struct address_space *,
 			struct page *, struct page *, enum migrate_mode);
 	int (*launder_page) (struct page *);
-	int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
+	int (*is_partially_uptodate) (struct page *, unsigned long,
 					unsigned long);
 	void (*is_dirty_writeback) (struct page *, bool *, bool *);
 	int (*error_remove_page)(struct address_space *, struct page *);
diff --git a/mm/filemap.c b/mm/filemap.c
index 7a13f6ac5421..46e98019af6c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1148,7 +1148,7 @@ find_page:
 			if (!page->mapping)
 				goto page_not_up_to_date_locked;
 			if (!mapping->a_ops->is_partially_uptodate(page,
-								desc, offset))
+							offset, desc->count))
 				goto page_not_up_to_date_locked;
 			unlock_page(page);
 		}
-- 
cgit v1.2.3


From 9223687863ffa63fa655f52ef64148ee08dee4d1 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kmo@daterainc.com>
Date: Wed, 27 Nov 2013 16:29:46 -0800
Subject: iov_iter: Move iov_iter to uio.h

Signed-off-by: Kent Overstreet <kmo@daterainc.com>
---
 include/linux/fs.h  | 32 --------------------------------
 include/linux/uio.h | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 50 insertions(+), 32 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index ddfff2ecef0b..2261ac8f0534 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -295,38 +295,6 @@ struct page;
 struct address_space;
 struct writeback_control;
 
-struct iov_iter {
-	const struct iovec *iov;
-	unsigned long nr_segs;
-	size_t iov_offset;
-	size_t count;
-};
-
-size_t iov_iter_copy_from_user_atomic(struct page *page,
-		struct iov_iter *i, unsigned long offset, size_t bytes);
-size_t iov_iter_copy_from_user(struct page *page,
-		struct iov_iter *i, unsigned long offset, size_t bytes);
-void iov_iter_advance(struct iov_iter *i, size_t bytes);
-int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
-size_t iov_iter_single_seg_count(const struct iov_iter *i);
-
-static inline void iov_iter_init(struct iov_iter *i,
-			const struct iovec *iov, unsigned long nr_segs,
-			size_t count, size_t written)
-{
-	i->iov = iov;
-	i->nr_segs = nr_segs;
-	i->iov_offset = 0;
-	i->count = count + written;
-
-	iov_iter_advance(i, written);
-}
-
-static inline size_t iov_iter_count(struct iov_iter *i)
-{
-	return i->count;
-}
-
 /*
  * "descriptor" for what we're up to with a read.
  * This allows us to use the same read code yet
diff --git a/include/linux/uio.h b/include/linux/uio.h
index c55ce243cc09..347d70ce098e 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -9,14 +9,23 @@
 #ifndef __LINUX_UIO_H
 #define __LINUX_UIO_H
 
+#include <linux/kernel.h>
 #include <uapi/linux/uio.h>
 
+struct page;
 
 struct kvec {
 	void *iov_base; /* and that should *never* hold a userland pointer */
 	size_t iov_len;
 };
 
+struct iov_iter {
+	const struct iovec *iov;
+	unsigned long nr_segs;
+	size_t iov_offset;
+	size_t count;
+};
+
 /*
  * Total number of bytes covered by an iovec.
  *
@@ -34,8 +43,49 @@ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs)
 	return ret;
 }
 
+static inline struct iovec iov_iter_iovec(const struct iov_iter *iter)
+{
+	return (struct iovec) {
+		.iov_base = iter->iov->iov_base + iter->iov_offset,
+		.iov_len = min(iter->count,
+			       iter->iov->iov_len - iter->iov_offset),
+	};
+}
+
+#define iov_for_each(iov, iter, start)				\
+	for (iter = (start);					\
+	     (iter).count &&					\
+	     ((iov = iov_iter_iovec(&(iter))), 1);		\
+	     iov_iter_advance(&(iter), (iov).iov_len))
+
 unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to);
 
+size_t iov_iter_copy_from_user_atomic(struct page *page,
+		struct iov_iter *i, unsigned long offset, size_t bytes);
+size_t iov_iter_copy_from_user(struct page *page,
+		struct iov_iter *i, unsigned long offset, size_t bytes);
+void iov_iter_advance(struct iov_iter *i, size_t bytes);
+int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
+size_t iov_iter_single_seg_count(const struct iov_iter *i);
+
+static inline void iov_iter_init(struct iov_iter *i,
+			const struct iovec *iov, unsigned long nr_segs,
+			size_t count, size_t written)
+{
+	i->iov = iov;
+	i->nr_segs = nr_segs;
+	i->iov_offset = 0;
+	i->count = count + written;
+
+	iov_iter_advance(i, written);
+}
+
+static inline size_t iov_iter_count(struct iov_iter *i)
+{
+	return i->count;
+}
+
 int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len);
 int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len);
+
 #endif
-- 
cgit v1.2.3


From 6e58e79db8a16222b31fc8da1ca2ac2dccfc4237 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 3 Feb 2014 17:07:03 -0500
Subject: introduce copy_page_to_iter, kill loop over iovec in
 generic_file_aio_read()

generic_file_aio_read() was looping over the target iovec, with loop over
(source) pages nested inside that.  Just set an iov_iter up and pass *that*
to do_generic_file_aio_read().  With copy_page_to_iter() doing all work
of mapping and copying a page to iovec and advancing iov_iter.

Switch shmem_file_aio_read() to the same and kill file_read_actor(), while
we are at it.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/fs.h  |   1 -
 include/linux/uio.h |   2 +
 mm/filemap.c        | 202 ++++++++++++++++++++++++++++------------------------
 mm/shmem.c          |  77 +++++++-------------
 4 files changed, 138 insertions(+), 144 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2261ac8f0534..2a5b1744f80a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2390,7 +2390,6 @@ extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr,
 		unsigned long size, pgoff_t pgoff);
-extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size);
 int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
 extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);
 extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long,
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 347d70ce098e..199bcc34241b 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -67,6 +67,8 @@ size_t iov_iter_copy_from_user(struct page *page,
 void iov_iter_advance(struct iov_iter *i, size_t bytes);
 int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
 size_t iov_iter_single_seg_count(const struct iov_iter *i);
+size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
+			 struct iov_iter *i);
 
 static inline void iov_iter_init(struct iov_iter *i,
 			const struct iovec *iov, unsigned long nr_segs,
diff --git a/mm/filemap.c b/mm/filemap.c
index bfb7a97d6d0f..a16eb2c4f316 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1085,11 +1085,90 @@ static void shrink_readahead_size_eio(struct file *filp,
 	ra->ra_pages /= 4;
 }
 
+size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
+			 struct iov_iter *i)
+{
+	size_t skip, copy, left, wanted;
+	const struct iovec *iov;
+	char __user *buf;
+	void *kaddr, *from;
+
+	if (unlikely(bytes > i->count))
+		bytes = i->count;
+
+	if (unlikely(!bytes))
+		return 0;
+
+	wanted = bytes;
+	iov = i->iov;
+	skip = i->iov_offset;
+	buf = iov->iov_base + skip;
+	copy = min(bytes, iov->iov_len - skip);
+
+	if (!fault_in_pages_writeable(buf, copy)) {
+		kaddr = kmap_atomic(page);
+		from = kaddr + offset;
+
+		/* first chunk, usually the only one */
+		left = __copy_to_user_inatomic(buf, from, copy);
+		copy -= left;
+		skip += copy;
+		from += copy;
+		bytes -= copy;
+
+		while (unlikely(!left && bytes)) {
+			iov++;
+			buf = iov->iov_base;
+			copy = min(bytes, iov->iov_len);
+			left = __copy_to_user_inatomic(buf, from, copy);
+			copy -= left;
+			skip = copy;
+			from += copy;
+			bytes -= copy;
+		}
+		if (likely(!bytes)) {
+			kunmap_atomic(kaddr);
+			goto done;
+		}
+		offset = from - kaddr;
+		buf += copy;
+		kunmap_atomic(kaddr);
+		copy = min(bytes, iov->iov_len - skip);
+	}
+	/* Too bad - revert to non-atomic kmap */
+	kaddr = kmap(page);
+	from = kaddr + offset;
+	left = __copy_to_user(buf, from, copy);
+	copy -= left;
+	skip += copy;
+	from += copy;
+	bytes -= copy;
+	while (unlikely(!left && bytes)) {
+		iov++;
+		buf = iov->iov_base;
+		copy = min(bytes, iov->iov_len);
+		left = __copy_to_user(buf, from, copy);
+		copy -= left;
+		skip = copy;
+		from += copy;
+		bytes -= copy;
+	}
+	kunmap(page);
+done:
+	i->count -= wanted - bytes;
+	i->nr_segs -= iov - i->iov;
+	i->iov = iov;
+	i->iov_offset = skip;
+	return wanted - bytes;
+}
+EXPORT_SYMBOL(copy_page_to_iter);
+
 /**
  * do_generic_file_read - generic file read routine
  * @filp:	the file to read
  * @ppos:	current file position
- * @desc:	read_descriptor
+ * @iter:	data destination
+ * @written:	already copied
  *
  * This is a generic file read routine, and uses the
  * mapping->a_ops->readpage() function for the actual low-level stuff.
@@ -1097,8 +1176,8 @@ static void shrink_readahead_size_eio(struct file *filp,
  * This is really ugly. But the goto's actually try to clarify some
  * of the logic when it comes to error handling etc.
  */
-static void do_generic_file_read(struct file *filp, loff_t *ppos,
-		read_descriptor_t *desc)
+static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos,
+		struct iov_iter *iter, ssize_t written)
 {
 	struct address_space *mapping = filp->f_mapping;
 	struct inode *inode = mapping->host;
@@ -1108,12 +1187,12 @@ static void do_generic_file_read(struct file *filp, loff_t *ppos,
 	pgoff_t prev_index;
 	unsigned long offset;      /* offset into pagecache page */
 	unsigned int prev_offset;
-	int error;
+	int error = 0;
 
 	index = *ppos >> PAGE_CACHE_SHIFT;
 	prev_index = ra->prev_pos >> PAGE_CACHE_SHIFT;
 	prev_offset = ra->prev_pos & (PAGE_CACHE_SIZE-1);
-	last_index = (*ppos + desc->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
+	last_index = (*ppos + iter->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
 	offset = *ppos & ~PAGE_CACHE_MASK;
 
 	for (;;) {
@@ -1148,7 +1227,7 @@ find_page:
 			if (!page->mapping)
 				goto page_not_up_to_date_locked;
 			if (!mapping->a_ops->is_partially_uptodate(page,
-							offset, desc->count))
+							offset, iter->count))
 				goto page_not_up_to_date_locked;
 			unlock_page(page);
 		}
@@ -1198,24 +1277,23 @@ page_ok:
 		/*
 		 * Ok, we have the page, and it's up-to-date, so
 		 * now we can copy it to user space...
-		 *
-		 * The file_read_actor routine returns how many bytes were
-		 * actually used..
-		 * NOTE! This may not be the same as how much of a user buffer
-		 * we filled up (we may be padding etc), so we can only update
-		 * "pos" here (the actor routine has to update the user buffer
-		 * pointers and the remaining count).
 		 */
-		ret = file_read_actor(desc, page, offset, nr);
+
+		ret = copy_page_to_iter(page, offset, nr, iter);
 		offset += ret;
 		index += offset >> PAGE_CACHE_SHIFT;
 		offset &= ~PAGE_CACHE_MASK;
 		prev_offset = offset;
 
 		page_cache_release(page);
-		if (ret == nr && desc->count)
-			continue;
-		goto out;
+		written += ret;
+		if (!iov_iter_count(iter))
+			goto out;
+		if (ret < nr) {
+			error = -EFAULT;
+			goto out;
+		}
+		continue;
 
 page_not_up_to_date:
 		/* Get exclusive access to the page ... */
@@ -1250,6 +1328,7 @@ readpage:
 		if (unlikely(error)) {
 			if (error == AOP_TRUNCATED_PAGE) {
 				page_cache_release(page);
+				error = 0;
 				goto find_page;
 			}
 			goto readpage_error;
@@ -1280,7 +1359,6 @@ readpage:
 
 readpage_error:
 		/* UHHUH! A synchronous read error occurred. Report it */
-		desc->error = error;
 		page_cache_release(page);
 		goto out;
 
@@ -1291,16 +1369,17 @@ no_cached_page:
 		 */
 		page = page_cache_alloc_cold(mapping);
 		if (!page) {
-			desc->error = -ENOMEM;
+			error = -ENOMEM;
 			goto out;
 		}
 		error = add_to_page_cache_lru(page, mapping,
 						index, GFP_KERNEL);
 		if (error) {
 			page_cache_release(page);
-			if (error == -EEXIST)
+			if (error == -EEXIST) {
+				error = 0;
 				goto find_page;
-			desc->error = error;
+			}
 			goto out;
 		}
 		goto readpage;
@@ -1313,44 +1392,7 @@ out:
 
 	*ppos = ((loff_t)index << PAGE_CACHE_SHIFT) + offset;
 	file_accessed(filp);
-}
-
-int file_read_actor(read_descriptor_t *desc, struct page *page,
-			unsigned long offset, unsigned long size)
-{
-	char *kaddr;
-	unsigned long left, count = desc->count;
-
-	if (size > count)
-		size = count;
-
-	/*
-	 * Faults on the destination of a read are common, so do it before
-	 * taking the kmap.
-	 */
-	if (!fault_in_pages_writeable(desc->arg.buf, size)) {
-		kaddr = kmap_atomic(page);
-		left = __copy_to_user_inatomic(desc->arg.buf,
-						kaddr + offset, size);
-		kunmap_atomic(kaddr);
-		if (left == 0)
-			goto success;
-	}
-
-	/* Do it the slow way */
-	kaddr = kmap(page);
-	left = __copy_to_user(desc->arg.buf, kaddr + offset, size);
-	kunmap(page);
-
-	if (left) {
-		size -= left;
-		desc->error = -EFAULT;
-	}
-success:
-	desc->count = count - size;
-	desc->written += size;
-	desc->arg.buf += size;
-	return size;
+	return written ? written : error;
 }
 
 /*
@@ -1408,14 +1450,15 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 {
 	struct file *filp = iocb->ki_filp;
 	ssize_t retval;
-	unsigned long seg = 0;
 	size_t count;
 	loff_t *ppos = &iocb->ki_pos;
+	struct iov_iter i;
 
 	count = 0;
 	retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
 	if (retval)
 		return retval;
+	iov_iter_init(&i, iov, nr_segs, count, 0);
 
 	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
 	if (filp->f_flags & O_DIRECT) {
@@ -1437,6 +1480,11 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 		if (retval > 0) {
 			*ppos = pos + retval;
 			count -= retval;
+			/*
+			 * If we did a short DIO read we need to skip the
+			 * section of the iov that we've already read data into.
+			 */
+			iov_iter_advance(&i, retval);
 		}
 
 		/*
@@ -1453,39 +1501,7 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 		}
 	}
 
-	count = retval;
-	for (seg = 0; seg < nr_segs; seg++) {
-		read_descriptor_t desc;
-		loff_t offset = 0;
-
-		/*
-		 * If we did a short DIO read we need to skip the section of the
-		 * iov that we've already read data into.
-		 */
-		if (count) {
-			if (count > iov[seg].iov_len) {
-				count -= iov[seg].iov_len;
-				continue;
-			}
-			offset = count;
-			count = 0;
-		}
-
-		desc.written = 0;
-		desc.arg.buf = iov[seg].iov_base + offset;
-		desc.count = iov[seg].iov_len - offset;
-		if (desc.count == 0)
-			continue;
-		desc.error = 0;
-		do_generic_file_read(filp, ppos, &desc);
-		retval += desc.written;
-		if (desc.error) {
-			retval = retval ?: desc.error;
-			break;
-		}
-		if (desc.count > 0)
-			break;
-	}
+	retval = do_generic_file_read(filp, ppos, &i, retval);
 out:
 	return retval;
 }
diff --git a/mm/shmem.c b/mm/shmem.c
index 9398e6cd48cb..17d3799d04bd 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1462,13 +1462,25 @@ shmem_write_end(struct file *file, struct address_space *mapping,
 	return copied;
 }
 
-static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_t *desc)
+static ssize_t shmem_file_aio_read(struct kiocb *iocb,
+		const struct iovec *iov, unsigned long nr_segs, loff_t pos)
 {
-	struct inode *inode = file_inode(filp);
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
 	struct address_space *mapping = inode->i_mapping;
 	pgoff_t index;
 	unsigned long offset;
 	enum sgp_type sgp = SGP_READ;
+	int error;
+	ssize_t retval;
+	size_t count;
+	loff_t *ppos = &iocb->ki_pos;
+	struct iov_iter iter;
+
+	retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
+	if (retval)
+		return retval;
+	iov_iter_init(&iter, iov, nr_segs, count, 0);
 
 	/*
 	 * Might this read be for a stacking filesystem?  Then when reading
@@ -1496,10 +1508,10 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_
 				break;
 		}
 
-		desc->error = shmem_getpage(inode, index, &page, sgp, NULL);
-		if (desc->error) {
-			if (desc->error == -EINVAL)
-				desc->error = 0;
+		error = shmem_getpage(inode, index, &page, sgp, NULL);
+		if (error) {
+			if (error == -EINVAL)
+				error = 0;
 			break;
 		}
 		if (page)
@@ -1543,61 +1555,26 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_
 		/*
 		 * Ok, we have the page, and it's up-to-date, so
 		 * now we can copy it to user space...
-		 *
-		 * The actor routine returns how many bytes were actually used..
-		 * NOTE! This may not be the same as how much of a user buffer
-		 * we filled up (we may be padding etc), so we can only update
-		 * "pos" here (the actor routine has to update the user buffer
-		 * pointers and the remaining count).
 		 */
-		ret = file_read_actor(desc, page, offset, nr);
+		ret = copy_page_to_iter(page, offset, nr, &iter);
+		retval += ret;
 		offset += ret;
 		index += offset >> PAGE_CACHE_SHIFT;
 		offset &= ~PAGE_CACHE_MASK;
 
 		page_cache_release(page);
-		if (ret != nr || !desc->count)
+		if (!iov_iter_count(&iter))
 			break;
-
+		if (ret < nr) {
+			error = -EFAULT;
+			break;
+		}
 		cond_resched();
 	}
 
 	*ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset;
-	file_accessed(filp);
-}
-
-static ssize_t shmem_file_aio_read(struct kiocb *iocb,
-		const struct iovec *iov, unsigned long nr_segs, loff_t pos)
-{
-	struct file *filp = iocb->ki_filp;
-	ssize_t retval;
-	unsigned long seg;
-	size_t count;
-	loff_t *ppos = &iocb->ki_pos;
-
-	retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
-	if (retval)
-		return retval;
-
-	for (seg = 0; seg < nr_segs; seg++) {
-		read_descriptor_t desc;
-
-		desc.written = 0;
-		desc.arg.buf = iov[seg].iov_base;
-		desc.count = iov[seg].iov_len;
-		if (desc.count == 0)
-			continue;
-		desc.error = 0;
-		do_shmem_file_read(filp, ppos, &desc);
-		retval += desc.written;
-		if (desc.error) {
-			retval = retval ?: desc.error;
-			break;
-		}
-		if (desc.count > 0)
-			break;
-	}
-	return retval;
+	file_accessed(file);
+	return retval ? retval : error;
 }
 
 static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
-- 
cgit v1.2.3


From 86d564c84c38b1ec06d9f2120d6a7373dcaeff0c Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 8 Feb 2014 20:42:52 -0500
Subject: constify blk_rq_map_user_iov() and friends

sg_iovec array passed to it can be const

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 block/blk-map.c        |  2 +-
 fs/bio.c               | 10 +++++-----
 include/linux/bio.h    |  5 +++--
 include/linux/blkdev.h |  4 ++--
 4 files changed, 11 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-map.c b/block/blk-map.c
index ae4ae1047fd9..86d93779c066 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -188,7 +188,7 @@ EXPORT_SYMBOL(blk_rq_map_user);
  *    unmapping.
  */
 int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
-			struct rq_map_data *map_data, struct sg_iovec *iov,
+			struct rq_map_data *map_data, const struct sg_iovec *iov,
 			int iov_count, unsigned int len, gfp_t gfp_mask)
 {
 	struct bio *bio;
diff --git a/fs/bio.c b/fs/bio.c
index 8754e7b6eb49..7065837ae9f3 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -1003,7 +1003,7 @@ struct bio_map_data {
 };
 
 static void bio_set_map_data(struct bio_map_data *bmd, struct bio *bio,
-			     struct sg_iovec *iov, int iov_count,
+			     const struct sg_iovec *iov, int iov_count,
 			     int is_our_pages)
 {
 	memcpy(bmd->sgvecs, iov, sizeof(struct sg_iovec) * iov_count);
@@ -1023,7 +1023,7 @@ static struct bio_map_data *bio_alloc_map_data(int nr_segs,
 		       sizeof(struct sg_iovec) * iov_count, gfp_mask);
 }
 
-static int __bio_copy_iov(struct bio *bio, struct sg_iovec *iov, int iov_count,
+static int __bio_copy_iov(struct bio *bio, const struct sg_iovec *iov, int iov_count,
 			  int to_user, int from_user, int do_free_page)
 {
 	int ret = 0, i;
@@ -1121,7 +1121,7 @@ EXPORT_SYMBOL(bio_uncopy_user);
  */
 struct bio *bio_copy_user_iov(struct request_queue *q,
 			      struct rq_map_data *map_data,
-			      struct sg_iovec *iov, int iov_count,
+			      const struct sg_iovec *iov, int iov_count,
 			      int write_to_vm, gfp_t gfp_mask)
 {
 	struct bio_map_data *bmd;
@@ -1260,7 +1260,7 @@ EXPORT_SYMBOL(bio_copy_user);
 
 static struct bio *__bio_map_user_iov(struct request_queue *q,
 				      struct block_device *bdev,
-				      struct sg_iovec *iov, int iov_count,
+				      const struct sg_iovec *iov, int iov_count,
 				      int write_to_vm, gfp_t gfp_mask)
 {
 	int i, j;
@@ -1408,7 +1408,7 @@ EXPORT_SYMBOL(bio_map_user);
  *	device. Returns an error pointer in case of error.
  */
 struct bio *bio_map_user_iov(struct request_queue *q, struct block_device *bdev,
-			     struct sg_iovec *iov, int iov_count,
+			     const struct sg_iovec *iov, int iov_count,
 			     int write_to_vm, gfp_t gfp_mask)
 {
 	struct bio *bio;
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 5a4d39b4686b..21e27208316c 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -388,7 +388,7 @@ struct sg_iovec;
 struct rq_map_data;
 extern struct bio *bio_map_user_iov(struct request_queue *,
 				    struct block_device *,
-				    struct sg_iovec *, int, int, gfp_t);
+				    const struct sg_iovec *, int, int, gfp_t);
 extern void bio_unmap_user(struct bio *);
 extern struct bio *bio_map_kern(struct request_queue *, void *, unsigned int,
 				gfp_t);
@@ -414,7 +414,8 @@ extern int bio_alloc_pages(struct bio *bio, gfp_t gfp);
 extern struct bio *bio_copy_user(struct request_queue *, struct rq_map_data *,
 				 unsigned long, unsigned int, int, gfp_t);
 extern struct bio *bio_copy_user_iov(struct request_queue *,
-				     struct rq_map_data *, struct sg_iovec *,
+				     struct rq_map_data *,
+				     const struct sg_iovec *,
 				     int, int, gfp_t);
 extern int bio_uncopy_user(struct bio *);
 void zero_fill_bio(struct bio *bio);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 4afa4f8f6090..a639fd8a6d7b 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -823,8 +823,8 @@ extern int blk_rq_map_user(struct request_queue *, struct request *,
 extern int blk_rq_unmap_user(struct bio *);
 extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t);
 extern int blk_rq_map_user_iov(struct request_queue *, struct request *,
-			       struct rq_map_data *, struct sg_iovec *, int,
-			       unsigned int, gfp_t);
+			       struct rq_map_data *, const struct sg_iovec *,
+			       int, unsigned int, gfp_t);
 extern int blk_execute_rq(struct request_queue *, struct gendisk *,
 			  struct request *, int);
 extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
-- 
cgit v1.2.3


From 41fc56d573c35a212688b12b48af8c303f9bb6d2 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 9 Feb 2014 12:58:52 -0500
Subject: kill the 4th argument of __generic_file_aio_write()

It's always equal to &iocb->ki_pos, where iocb is the value of the 1st
argument.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/block_dev.c     |  2 +-
 fs/ext4/file.c     |  2 +-
 fs/udf/file.c      |  2 +-
 include/linux/fs.h |  3 +--
 mm/filemap.c       | 13 ++++++-------
 5 files changed, 10 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 1e86823a9cbd..764bd3b8d2fa 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1518,7 +1518,7 @@ ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	BUG_ON(iocb->ki_pos != pos);
 
 	blk_start_plug(&plug);
-	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+	ret = __generic_file_aio_write(iocb, iov, nr_segs);
 	if (ret > 0) {
 		ssize_t err;
 
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 1a5073959f32..d564bcfb23c5 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -146,7 +146,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
 			overwrite = 1;
 	}
 
-	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+	ret = __generic_file_aio_write(iocb, iov, nr_segs);
 	mutex_unlock(&inode->i_mutex);
 
 	if (ret > 0) {
diff --git a/fs/udf/file.c b/fs/udf/file.c
index 1037637957c7..d2c170f8b035 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -171,7 +171,7 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	} else
 		up_write(&iinfo->i_data_sem);
 
-	retval = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+	retval = __generic_file_aio_write(iocb, iov, nr_segs);
 	mutex_unlock(&inode->i_mutex);
 
 	if (retval > 0) {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2a5b1744f80a..e677d1e1189f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2392,8 +2392,7 @@ extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr,
 		unsigned long size, pgoff_t pgoff);
 int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
 extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);
-extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long,
-		loff_t *);
+extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long);
 extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t);
 extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *,
 		unsigned long *, loff_t, loff_t *, size_t, size_t);
diff --git a/mm/filemap.c b/mm/filemap.c
index c4730efa5d9e..ce2246dd90de 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2222,14 +2222,14 @@ EXPORT_SYMBOL(generic_file_buffered_write);
  * avoid syncing under i_mutex.
  */
 ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
-				 unsigned long nr_segs, loff_t *ppos)
+				 unsigned long nr_segs)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space * mapping = file->f_mapping;
 	size_t ocount;		/* original count */
 	size_t count;		/* after file limit checks */
 	struct inode 	*inode = mapping->host;
-	loff_t		pos;
+	loff_t		pos = iocb->ki_pos;
 	ssize_t		written;
 	ssize_t		err;
 
@@ -2239,7 +2239,6 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		return err;
 
 	count = ocount;
-	pos = *ppos;
 
 	/* We can write back this queue in page reclaim */
 	current->backing_dev_info = mapping->backing_dev_info;
@@ -2266,7 +2265,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		ssize_t written_buffered;
 
 		written = generic_file_direct_write(iocb, iov, &nr_segs, pos,
-							ppos, count, ocount);
+							&iocb->ki_pos, count, ocount);
 		if (written < 0 || written == count)
 			goto out;
 		/*
@@ -2276,7 +2275,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		pos += written;
 		count -= written;
 		written_buffered = generic_file_buffered_write(iocb, iov,
-						nr_segs, pos, ppos, count,
+						nr_segs, pos, &iocb->ki_pos, count,
 						written);
 		/*
 		 * If generic_file_buffered_write() retuned a synchronous error
@@ -2310,7 +2309,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		}
 	} else {
 		written = generic_file_buffered_write(iocb, iov, nr_segs,
-				pos, ppos, count, written);
+				pos, &iocb->ki_pos, count, written);
 	}
 out:
 	current->backing_dev_info = NULL;
@@ -2339,7 +2338,7 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	BUG_ON(iocb->ki_pos != pos);
 
 	mutex_lock(&inode->i_mutex);
-	ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+	ret = __generic_file_aio_write(iocb, iov, nr_segs);
 	mutex_unlock(&inode->i_mutex);
 
 	if (ret > 0) {
-- 
cgit v1.2.3


From fcacafd269adc88f41b68cb77a3f957a66563428 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 9 Feb 2014 13:37:49 -0500
Subject: kill the 5th argument of generic_file_buffered_write()

same story - it's &iocb->ki_pos in all cases

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/ceph/file.c     | 3 +--
 fs/ocfs2/file.c    | 2 +-
 fs/xfs/xfs_file.c  | 2 +-
 include/linux/fs.h | 2 +-
 mm/filemap.c       | 9 ++++-----
 5 files changed, 8 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 09c7afe32e49..a798db5e5e39 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -978,8 +978,7 @@ retry_snap:
 		 * can not run at the same time
 		 */
 		written = generic_file_buffered_write(iocb, iov, nr_segs,
-						      pos, &iocb->ki_pos,
-						      count, 0);
+						      pos, count, 0);
 		mutex_unlock(&inode->i_mutex);
 	}
 
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 51632c40e896..89099cce14fe 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2383,7 +2383,7 @@ relock:
 	} else {
 		current->backing_dev_info = file->f_mapping->backing_dev_info;
 		written = generic_file_buffered_write(iocb, iov, nr_segs, *ppos,
-						      ppos, count, 0);
+						      count, 0);
 		current->backing_dev_info = NULL;
 	}
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 64b48eade91d..175ce58fbfa3 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -738,7 +738,7 @@ xfs_file_buffered_aio_write(
 write_retry:
 	trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, 0);
 	ret = generic_file_buffered_write(iocb, iovp, nr_segs,
-			pos, &iocb->ki_pos, count, 0);
+			pos, count, 0);
 
 	/*
 	 * If we just got an ENOSPC, try to write back all dirty inodes to
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e677d1e1189f..830e37420f5e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2397,7 +2397,7 @@ extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsi
 extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *,
 		unsigned long *, loff_t, loff_t *, size_t, size_t);
 extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *,
-		unsigned long, loff_t, loff_t *, size_t, ssize_t);
+		unsigned long, loff_t, size_t, ssize_t);
 extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos);
 extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos);
 extern int generic_segment_checks(const struct iovec *iov,
diff --git a/mm/filemap.c b/mm/filemap.c
index ce2246dd90de..9d515a1a2372 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2183,7 +2183,7 @@ again:
 
 ssize_t
 generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
-		unsigned long nr_segs, loff_t pos, loff_t *ppos,
+		unsigned long nr_segs, loff_t pos,
 		size_t count, ssize_t written)
 {
 	struct file *file = iocb->ki_filp;
@@ -2195,7 +2195,7 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
 
 	if (likely(status >= 0)) {
 		written += status;
-		*ppos = pos + status;
+		iocb->ki_pos = pos + status;
   	}
 	
 	return written ? written : status;
@@ -2275,8 +2275,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		pos += written;
 		count -= written;
 		written_buffered = generic_file_buffered_write(iocb, iov,
-						nr_segs, pos, &iocb->ki_pos, count,
-						written);
+						nr_segs, pos, count, written);
 		/*
 		 * If generic_file_buffered_write() retuned a synchronous error
 		 * then we want to return the number of bytes which were
@@ -2309,7 +2308,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		}
 	} else {
 		written = generic_file_buffered_write(iocb, iov, nr_segs,
-				pos, &iocb->ki_pos, count, written);
+				pos, count, written);
 	}
 out:
 	current->backing_dev_info = NULL;
-- 
cgit v1.2.3


From 5cb6c6c7eb1ed24744b41fad47d9a25b72207098 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 11 Feb 2014 20:58:20 -0500
Subject: generic_file_direct_write(): get rid of ppos argument

always equal to &iocb->ki_pos.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/btrfs/file.c    | 2 +-
 fs/fuse/file.c     | 3 +--
 fs/ocfs2/file.c    | 2 +-
 fs/xfs/xfs_file.c  | 2 +-
 include/linux/fs.h | 2 +-
 mm/filemap.c       | 6 +++---
 6 files changed, 8 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index f6032a2bfab9..8ed4b165abbd 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1640,7 +1640,7 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb,
 	loff_t endbyte;
 	int err;
 
-	written = generic_file_direct_write(iocb, iov, &nr_segs, pos, &iocb->ki_pos,
+	written = generic_file_direct_write(iocb, iov, &nr_segs, pos,
 					    count, ocount);
 
 	if (written < 0 || written == count)
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index a91d3b4d32f3..fd06d1ebc2eb 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1143,8 +1143,7 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		goto out;
 
 	if (file->f_flags & O_DIRECT) {
-		written = generic_file_direct_write(iocb, iov, &nr_segs,
-						    pos, &iocb->ki_pos,
+		written = generic_file_direct_write(iocb, iov, &nr_segs, pos, 
 						    count, ocount);
 		if (written < 0 || written == count)
 			goto out;
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 89099cce14fe..77b8a742866f 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2375,7 +2375,7 @@ relock:
 
 	if (direct_io) {
 		written = generic_file_direct_write(iocb, iov, &nr_segs, *ppos,
-						    ppos, count, ocount);
+						    count, ocount);
 		if (written < 0) {
 			ret = written;
 			goto out_dio;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 175ce58fbfa3..e593554ce65e 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -699,7 +699,7 @@ xfs_file_dio_aio_write(
 
 	trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0);
 	ret = generic_file_direct_write(iocb, iovp,
-			&nr_segs, pos, &iocb->ki_pos, count, ocount);
+			&nr_segs, pos, count, ocount);
 
 out:
 	xfs_rw_iunlock(ip, iolock);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 830e37420f5e..9dfd7c7ff8e3 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2395,7 +2395,7 @@ extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsig
 extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long);
 extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t);
 extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *,
-		unsigned long *, loff_t, loff_t *, size_t, size_t);
+		unsigned long *, loff_t, size_t, size_t);
 extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *,
 		unsigned long, loff_t, size_t, ssize_t);
 extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos);
diff --git a/mm/filemap.c b/mm/filemap.c
index 9d515a1a2372..93e9cf576452 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1985,7 +1985,7 @@ EXPORT_SYMBOL(pagecache_write_end);
 
 ssize_t
 generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
-		unsigned long *nr_segs, loff_t pos, loff_t *ppos,
+		unsigned long *nr_segs, loff_t pos,
 		size_t count, size_t ocount)
 {
 	struct file	*file = iocb->ki_filp;
@@ -2046,7 +2046,7 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 			i_size_write(inode, pos);
 			mark_inode_dirty(inode);
 		}
-		*ppos = pos;
+		iocb->ki_pos = pos;
 	}
 out:
 	return written;
@@ -2265,7 +2265,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 		ssize_t written_buffered;
 
 		written = generic_file_direct_write(iocb, iov, &nr_segs, pos,
-							&iocb->ki_pos, count, ocount);
+							count, ocount);
 		if (written < 0 || written == count)
 			goto out;
 		/*
-- 
cgit v1.2.3


From 3b93f911d55cf8b3540f82fac4eeddfee7b5de0c Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 11 Feb 2014 21:34:08 -0500
Subject: export generic_perform_write(), start getting rid of
 generic_file_buffer_write()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/fs.h |  2 ++
 mm/filemap.c       | 37 +++++++++++++++++++++----------------
 2 files changed, 23 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9dfd7c7ff8e3..87be51aff9d7 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -48,6 +48,7 @@ struct cred;
 struct swap_info_struct;
 struct seq_file;
 struct workqueue_struct;
+struct iov_iter;
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
@@ -2396,6 +2397,7 @@ extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, un
 extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t);
 extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *,
 		unsigned long *, loff_t, size_t, size_t);
+extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t);
 extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *,
 		unsigned long, loff_t, size_t, ssize_t);
 extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos);
diff --git a/mm/filemap.c b/mm/filemap.c
index 93e9cf576452..09bfc9b3bb51 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2092,7 +2092,7 @@ found:
 }
 EXPORT_SYMBOL(grab_cache_page_write_begin);
 
-static ssize_t generic_perform_write(struct file *file,
+ssize_t generic_perform_write(struct file *file,
 				struct iov_iter *i, loff_t pos)
 {
 	struct address_space *mapping = file->f_mapping;
@@ -2180,6 +2180,7 @@ again:
 
 	return written ? written : status;
 }
+EXPORT_SYMBOL(generic_perform_write);
 
 ssize_t
 generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
@@ -2230,8 +2231,10 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	size_t count;		/* after file limit checks */
 	struct inode 	*inode = mapping->host;
 	loff_t		pos = iocb->ki_pos;
-	ssize_t		written;
+	ssize_t		written = 0;
 	ssize_t		err;
+	ssize_t		status;
+	struct iov_iter from;
 
 	ocount = 0;
 	err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ);
@@ -2242,8 +2245,6 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 
 	/* We can write back this queue in page reclaim */
 	current->backing_dev_info = mapping->backing_dev_info;
-	written = 0;
-
 	err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
 	if (err)
 		goto out;
@@ -2259,44 +2260,47 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	if (err)
 		goto out;
 
+	iov_iter_init(&from, iov, nr_segs, count, 0);
+
 	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
 	if (unlikely(file->f_flags & O_DIRECT)) {
 		loff_t endbyte;
-		ssize_t written_buffered;
 
-		written = generic_file_direct_write(iocb, iov, &nr_segs, pos,
+		written = generic_file_direct_write(iocb, iov, &from.nr_segs, pos,
 							count, ocount);
 		if (written < 0 || written == count)
 			goto out;
+		iov_iter_advance(&from, written);
+
 		/*
 		 * direct-io write to a hole: fall through to buffered I/O
 		 * for completing the rest of the request.
 		 */
 		pos += written;
 		count -= written;
-		written_buffered = generic_file_buffered_write(iocb, iov,
-						nr_segs, pos, count, written);
+
+		status = generic_perform_write(file, &from, pos);
 		/*
-		 * If generic_file_buffered_write() retuned a synchronous error
+		 * If generic_perform_write() returned a synchronous error
 		 * then we want to return the number of bytes which were
 		 * direct-written, or the error code if that was zero.  Note
 		 * that this differs from normal direct-io semantics, which
 		 * will return -EFOO even if some bytes were written.
 		 */
-		if (written_buffered < 0) {
-			err = written_buffered;
+		if (unlikely(status < 0) && !written) {
+			err = status;
 			goto out;
 		}
-
+		iocb->ki_pos = pos + status;
 		/*
 		 * We need to ensure that the page cache pages are written to
 		 * disk and invalidated to preserve the expected O_DIRECT
 		 * semantics.
 		 */
-		endbyte = pos + written_buffered - written - 1;
+		endbyte = pos + status - 1;
 		err = filemap_write_and_wait_range(file->f_mapping, pos, endbyte);
 		if (err == 0) {
-			written = written_buffered;
+			written += status;
 			invalidate_mapping_pages(mapping,
 						 pos >> PAGE_CACHE_SHIFT,
 						 endbyte >> PAGE_CACHE_SHIFT);
@@ -2307,8 +2311,9 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
 			 */
 		}
 	} else {
-		written = generic_file_buffered_write(iocb, iov, nr_segs,
-				pos, count, written);
+		written = generic_perform_write(file, &from, pos);
+		if (likely(written >= 0))
+			iocb->ki_pos = pos + written;
 	}
 out:
 	current->backing_dev_info = NULL;
-- 
cgit v1.2.3


From ccad2365668f12336dd497d9039e8584af836070 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 11 Feb 2014 22:36:48 -0500
Subject: kill generic_file_buffered_write()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/fs.h |  2 --
 mm/filemap.c       | 23 +----------------------
 2 files changed, 1 insertion(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 87be51aff9d7..c309b7a0da2d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2398,8 +2398,6 @@ extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsi
 extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *,
 		unsigned long *, loff_t, size_t, size_t);
 extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t);
-extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *,
-		unsigned long, loff_t, size_t, ssize_t);
 extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos);
 extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos);
 extern int generic_segment_checks(const struct iovec *iov,
diff --git a/mm/filemap.c b/mm/filemap.c
index 09bfc9b3bb51..1a455142784d 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -76,7 +76,7 @@
  *  ->mmap_sem
  *    ->lock_page		(access_process_vm)
  *
- *  ->i_mutex			(generic_file_buffered_write)
+ *  ->i_mutex			(generic_perform_write)
  *    ->mmap_sem		(fault_in_pages_readable->do_page_fault)
  *
  *  bdi->wb.list_lock
@@ -2182,27 +2182,6 @@ again:
 }
 EXPORT_SYMBOL(generic_perform_write);
 
-ssize_t
-generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
-		unsigned long nr_segs, loff_t pos,
-		size_t count, ssize_t written)
-{
-	struct file *file = iocb->ki_filp;
-	ssize_t status;
-	struct iov_iter i;
-
-	iov_iter_init(&i, iov, nr_segs, count, written);
-	status = generic_perform_write(file, &i, pos);
-
-	if (likely(status >= 0)) {
-		written += status;
-		iocb->ki_pos = pos + status;
-  	}
-	
-	return written ? written : status;
-}
-EXPORT_SYMBOL(generic_file_buffered_write);
-
 /**
  * __generic_file_aio_write - write data to a file
  * @iocb:	IO state structure (file, offset, etc.)
-- 
cgit v1.2.3


From 9d521470a40f16110bd31018034155c60c1a1275 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <ilya.dryomov@inktank.com>
Date: Fri, 31 Jan 2014 17:54:26 +0200
Subject: libceph: a per-osdc crush scratch buffer

With the addition of erasure coding support in the future, scratch
variable-length array in crush_do_rule_ary() is going to grow to at
least 200 bytes on average, on top of another 128 bytes consumed by
rawosd/osd arrays in the call chain.  Replace it with a buffer inside
struct osdmap and a mutex.  This shouldn't result in any contention,
because all osd requests were already serialized by request_mutex at
that point; the only unlocked caller was ceph_ioctl_get_dataloc().

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
---
 include/linux/ceph/osdmap.h |  3 +++
 net/ceph/osdmap.c           | 25 ++++++++++++++++---------
 2 files changed, 19 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index 49ff69f0746b..8c8b3cefc28b 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -84,6 +84,9 @@ struct ceph_osdmap {
 	/* the CRUSH map specifies the mapping of placement groups to
 	 * the list of osds that store+replicate them. */
 	struct crush_map *crush;
+
+	struct mutex crush_scratch_mutex;
+	int crush_scratch_ary[CEPH_PG_MAX_SIZE * 3];
 };
 
 static inline void ceph_oid_set_name(struct ceph_object_id *oid,
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index aade4a5c1c07..9d1aaa24def6 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -698,7 +698,9 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end)
 	map = kzalloc(sizeof(*map), GFP_NOFS);
 	if (map == NULL)
 		return ERR_PTR(-ENOMEM);
+
 	map->pg_temp = RB_ROOT;
+	mutex_init(&map->crush_scratch_mutex);
 
 	ceph_decode_16_safe(p, end, version, bad);
 	if (version > 6) {
@@ -1142,14 +1144,20 @@ int ceph_oloc_oid_to_pg(struct ceph_osdmap *osdmap,
 }
 EXPORT_SYMBOL(ceph_oloc_oid_to_pg);
 
-static int crush_do_rule_ary(const struct crush_map *map, int ruleno, int x,
-			     int *result, int result_max,
-			     const __u32 *weight, int weight_max)
+static int do_crush(struct ceph_osdmap *map, int ruleno, int x,
+		    int *result, int result_max,
+		    const __u32 *weight, int weight_max)
 {
-	int scratch[result_max * 3];
+	int r;
+
+	BUG_ON(result_max > CEPH_PG_MAX_SIZE);
+
+	mutex_lock(&map->crush_scratch_mutex);
+	r = crush_do_rule(map->crush, ruleno, x, result, result_max,
+			  weight, weight_max, map->crush_scratch_ary);
+	mutex_unlock(&map->crush_scratch_mutex);
 
-	return crush_do_rule(map, ruleno, x, result, result_max,
-			     weight, weight_max, scratch);
+	return r;
 }
 
 /*
@@ -1205,9 +1213,8 @@ static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
 				      pool->pgp_num_mask) +
 			(unsigned)pgid.pool;
 	}
-	r = crush_do_rule_ary(osdmap->crush, ruleno, pps,
-			      osds, min_t(int, pool->size, *num),
-			      osdmap->osd_weight, osdmap->max_osd);
+	r = do_crush(osdmap, ruleno, pps, osds, min_t(int, pool->size, *num),
+		     osdmap->osd_weight, osdmap->max_osd);
 	if (r < 0) {
 		pr_err("error %d from crush rule: pool %lld ruleset %d type %d"
 		       " size %d\n", r, pgid.pool, pool->crush_ruleset,
-- 
cgit v1.2.3


From 7b25bf5f02c5c80adf96120e031dc3a1756ce54d Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <ilya.dryomov@inktank.com>
Date: Tue, 25 Feb 2014 16:22:26 +0200
Subject: libceph: encode CEPH_OSD_OP_FLAG_* op flags

Encode ceph_osd_op::flags field so that it gets sent over the wire.

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
---
 include/linux/ceph/osd_client.h | 1 +
 include/linux/ceph/rados.h      | 2 +-
 net/ceph/osd_client.c           | 2 ++
 3 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index fd47e872ebcc..e94f5da251d6 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -76,6 +76,7 @@ struct ceph_osd_data {
 
 struct ceph_osd_req_op {
 	u16 op;           /* CEPH_OSD_OP_* */
+	u32 flags;        /* CEPH_OSD_OP_FLAG_* */
 	u32 payload_len;
 	union {
 		struct ceph_osd_data raw_data_in;
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index 96292df4041b..8f9bf4570215 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -382,7 +382,7 @@ enum {
  */
 struct ceph_osd_op {
 	__le16 op;           /* CEPH_OSD_OP_* */
-	__le32 flags;        /* CEPH_OSD_FLAG_* */
+	__le32 flags;        /* CEPH_OSD_OP_FLAG_* */
 	union {
 		struct {
 			__le64 offset, length;
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 0676f2b199d6..5d7fd0b8c1c8 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -688,7 +688,9 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req,
 
 		return 0;
 	}
+
 	dst->op = cpu_to_le16(src->op);
+	dst->flags = cpu_to_le32(src->flags);
 	dst->payload_len = cpu_to_le32(src->payload_len);
 
 	return request_data_len;
-- 
cgit v1.2.3


From c647b8a8c6366f849c2a237bfe525cb1d316d5f4 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <ilya.dryomov@inktank.com>
Date: Tue, 25 Feb 2014 16:22:27 +0200
Subject: libceph: add support for CEPH_OSD_OP_SETALLOCHINT osd op

This is primarily for rbd's benefit and is supposed to combat
fragmentation:

"... knowing that rbd images have a 4m size, librbd can pass a hint
that will let the osd do the xfs allocation size ioctl on new files so
that they are allocated in 1m or 4m chunks.  We've seen cases where
users with rbd workloads have very high levels of fragmentation in xfs
and this would mitigate that and probably have a pretty nice
performance benefit."

SETALLOCHINT is considered advisory, so our backwards compatibility
mechanism here is to set FAILOK flag for all SETALLOCHINT ops.

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
---
 include/linux/ceph/osd_client.h |  8 ++++++++
 include/linux/ceph/rados.h      |  7 +++++++
 net/ceph/osd_client.c           | 27 +++++++++++++++++++++++++++
 3 files changed, 42 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index e94f5da251d6..c42d1ada685f 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -103,6 +103,10 @@ struct ceph_osd_req_op {
 			u32 timeout;
 			__u8 flag;
 		} watch;
+		struct {
+			u64 expected_object_size;
+			u64 expected_write_size;
+		} alloc_hint;
 	};
 };
 
@@ -294,6 +298,10 @@ extern void osd_req_op_cls_init(struct ceph_osd_request *osd_req,
 extern void osd_req_op_watch_init(struct ceph_osd_request *osd_req,
 					unsigned int which, u16 opcode,
 					u64 cookie, u64 version, int flag);
+extern void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req,
+				       unsigned int which,
+				       u64 expected_object_size,
+				       u64 expected_write_size);
 
 extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
 					       struct ceph_snap_context *snapc,
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index 8f9bf4570215..2caabef8d369 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -227,6 +227,9 @@ enum {
 	CEPH_OSD_OP_OMAPRMKEYS    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 24,
 	CEPH_OSD_OP_OMAP_CMP      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 25,
 
+	/* hints */
+	CEPH_OSD_OP_SETALLOCHINT = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 35,
+
 	/** multi **/
 	CEPH_OSD_OP_CLONERANGE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_MULTI | 1,
 	CEPH_OSD_OP_ASSERT_SRC_VERSION = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_MULTI | 2,
@@ -416,6 +419,10 @@ struct ceph_osd_op {
 			__le64 offset, length;
 			__le64 src_offset;
 		} __attribute__ ((packed)) clonerange;
+		struct {
+			__le64 expected_object_size;
+			__le64 expected_write_size;
+		} __attribute__ ((packed)) alloc_hint;
 	};
 	__le32 payload_len;
 } __attribute__ ((packed));
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 5d7fd0b8c1c8..71830d79b0f4 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -436,6 +436,7 @@ static bool osd_req_opcode_valid(u16 opcode)
 	case CEPH_OSD_OP_OMAPCLEAR:
 	case CEPH_OSD_OP_OMAPRMKEYS:
 	case CEPH_OSD_OP_OMAP_CMP:
+	case CEPH_OSD_OP_SETALLOCHINT:
 	case CEPH_OSD_OP_CLONERANGE:
 	case CEPH_OSD_OP_ASSERT_SRC_VERSION:
 	case CEPH_OSD_OP_SRC_CMPXATTR:
@@ -591,6 +592,26 @@ void osd_req_op_watch_init(struct ceph_osd_request *osd_req,
 }
 EXPORT_SYMBOL(osd_req_op_watch_init);
 
+void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req,
+				unsigned int which,
+				u64 expected_object_size,
+				u64 expected_write_size)
+{
+	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
+						      CEPH_OSD_OP_SETALLOCHINT);
+
+	op->alloc_hint.expected_object_size = expected_object_size;
+	op->alloc_hint.expected_write_size = expected_write_size;
+
+	/*
+	 * CEPH_OSD_OP_SETALLOCHINT op is advisory and therefore deemed
+	 * not worth a feature bit.  Set FAILOK per-op flag to make
+	 * sure older osds don't trip over an unsupported opcode.
+	 */
+	op->flags |= CEPH_OSD_OP_FLAG_FAILOK;
+}
+EXPORT_SYMBOL(osd_req_op_alloc_hint_init);
+
 static void ceph_osdc_msg_data_add(struct ceph_msg *msg,
 				struct ceph_osd_data *osd_data)
 {
@@ -681,6 +702,12 @@ static u64 osd_req_encode_op(struct ceph_osd_request *req,
 		dst->watch.ver = cpu_to_le64(src->watch.ver);
 		dst->watch.flag = src->watch.flag;
 		break;
+	case CEPH_OSD_OP_SETALLOCHINT:
+		dst->alloc_hint.expected_object_size =
+		    cpu_to_le64(src->alloc_hint.expected_object_size);
+		dst->alloc_hint.expected_write_size =
+		    cpu_to_le64(src->alloc_hint.expected_write_size);
+		break;
 	default:
 		pr_err("unsupported osd opcode %s\n",
 			ceph_osd_op_name(src->op));
-- 
cgit v1.2.3


From 7cc69d42e6950404587bef9489a5ed6f9f6bab4e Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <ilya.dryomov@inktank.com>
Date: Tue, 25 Feb 2014 16:22:27 +0200
Subject: libceph: bump CEPH_OSD_MAX_OP to 3

Our longest osd request now contains 3 ops: copyup+hint+write.

Also, CEPH_OSD_MAX_OP value in a BUG_ON in rbd_osd_req_callback() was
hard-coded to 2.  Fix it, and switch to rbd_assert while at it.

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
---
 drivers/block/rbd.c             | 2 +-
 include/linux/ceph/osd_client.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index b55b7812cf93..4c612c4041b6 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -1654,7 +1654,7 @@ static void rbd_osd_req_callback(struct ceph_osd_request *osd_req,
 	if (osd_req->r_result < 0)
 		obj_request->result = osd_req->r_result;
 
-	BUG_ON(osd_req->r_num_ops > 2);
+	rbd_assert(osd_req->r_num_ops <= CEPH_OSD_MAX_OP);
 
 	/*
 	 * We support a 64-bit length, but ultimately it has to be
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index c42d1ada685f..94ec69672164 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -43,7 +43,7 @@ struct ceph_osd {
 };
 
 
-#define CEPH_OSD_MAX_OP	2
+#define CEPH_OSD_MAX_OP	3
 
 enum ceph_osd_data_type {
 	CEPH_OSD_DATA_TYPE_NONE = 0,
-- 
cgit v1.2.3


From 19913b4eac4a230dccb548931358398f45dabe4c Mon Sep 17 00:00:00 2001
From: "Yan, Zheng" <zheng.z.yan@intel.com>
Date: Thu, 6 Mar 2014 16:40:32 +0800
Subject: ceph: add get_name() NFS export callback

Use the newly introduced LOOKUPNAME MDS request to connect child
inode to its parent directory.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Sage Weil <sage@inktank.com>
---
 fs/ceph/export.c             | 40 ++++++++++++++++++++++++++++++++++
 fs/ceph/inode.c              | 51 +++++++++++++++++++++++++++++++++++++++++++-
 fs/ceph/strings.c            |  1 +
 include/linux/ceph/ceph_fs.h |  1 +
 4 files changed, 92 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index eb66408ff236..00d6af6a32ec 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -202,9 +202,49 @@ static struct dentry *ceph_fh_to_parent(struct super_block *sb,
 	return dentry;
 }
 
+static int ceph_get_name(struct dentry *parent, char *name,
+			 struct dentry *child)
+{
+	struct ceph_mds_client *mdsc;
+	struct ceph_mds_request *req;
+	int err;
+
+	mdsc = ceph_inode_to_client(child->d_inode)->mdsc;
+	req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPNAME,
+				       USE_ANY_MDS);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	mutex_lock(&parent->d_inode->i_mutex);
+
+	req->r_inode = child->d_inode;
+	ihold(child->d_inode);
+	req->r_ino2 = ceph_vino(parent->d_inode);
+	req->r_locked_dir = parent->d_inode;
+	req->r_num_caps = 2;
+	err = ceph_mdsc_do_request(mdsc, NULL, req);
+
+	mutex_unlock(&parent->d_inode->i_mutex);
+
+	if (!err) {
+		struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
+		memcpy(name, rinfo->dname, rinfo->dname_len);
+		name[rinfo->dname_len] = 0;
+		dout("get_name %p ino %llx.%llx name %s\n",
+		     child, ceph_vinop(child->d_inode), name);
+	} else {
+		dout("get_name %p ino %llx.%llx err %d\n",
+		     child, ceph_vinop(child->d_inode), err);
+	}
+
+	ceph_mdsc_put_request(req);
+	return err;
+}
+
 const struct export_operations ceph_export_ops = {
 	.encode_fh = ceph_encode_fh,
 	.fh_to_dentry = ceph_fh_to_dentry,
 	.fh_to_parent = ceph_fh_to_parent,
 	.get_parent = ceph_get_parent,
+	.get_name = ceph_get_name,
 };
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 8bf2384bd423..91d6c9d49e3e 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1044,10 +1044,59 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 					 session, req->r_request_started, -1,
 					 &req->r_caps_reservation);
 			if (err < 0)
-				return err;
+				goto done;
 		} else {
 			WARN_ON_ONCE(1);
 		}
+
+		if (dir && req->r_op == CEPH_MDS_OP_LOOKUPNAME) {
+			struct qstr dname;
+			struct dentry *dn, *parent;
+
+			BUG_ON(!rinfo->head->is_target);
+			BUG_ON(req->r_dentry);
+
+			parent = d_find_any_alias(dir);
+			BUG_ON(!parent);
+
+			dname.name = rinfo->dname;
+			dname.len = rinfo->dname_len;
+			dname.hash = full_name_hash(dname.name, dname.len);
+			vino.ino = le64_to_cpu(rinfo->targeti.in->ino);
+			vino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
+retry_lookup:
+			dn = d_lookup(parent, &dname);
+			dout("d_lookup on parent=%p name=%.*s got %p\n",
+			     parent, dname.len, dname.name, dn);
+
+			if (!dn) {
+				dn = d_alloc(parent, &dname);
+				dout("d_alloc %p '%.*s' = %p\n", parent,
+				     dname.len, dname.name, dn);
+				if (dn == NULL) {
+					dput(parent);
+					err = -ENOMEM;
+					goto done;
+				}
+				err = ceph_init_dentry(dn);
+				if (err < 0) {
+					dput(dn);
+					dput(parent);
+					goto done;
+				}
+			} else if (dn->d_inode &&
+				   (ceph_ino(dn->d_inode) != vino.ino ||
+				    ceph_snap(dn->d_inode) != vino.snap)) {
+				dout(" dn %p points to wrong inode %p\n",
+				     dn, dn->d_inode);
+				d_delete(dn);
+				dput(dn);
+				goto retry_lookup;
+			}
+
+			req->r_dentry = dn;
+			dput(parent);
+		}
 	}
 
 	if (rinfo->head->is_target) {
diff --git a/fs/ceph/strings.c b/fs/ceph/strings.c
index 4440f447fd3f..51cc23e48111 100644
--- a/fs/ceph/strings.c
+++ b/fs/ceph/strings.c
@@ -54,6 +54,7 @@ const char *ceph_mds_op_name(int op)
 	case CEPH_MDS_OP_LOOKUPHASH:  return "lookuphash";
 	case CEPH_MDS_OP_LOOKUPPARENT:  return "lookupparent";
 	case CEPH_MDS_OP_LOOKUPINO:  return "lookupino";
+	case CEPH_MDS_OP_LOOKUPNAME:  return "lookupname";
 	case CEPH_MDS_OP_GETATTR:  return "getattr";
 	case CEPH_MDS_OP_SETXATTR: return "setxattr";
 	case CEPH_MDS_OP_SETATTR: return "setattr";
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 25bfb0eff772..35f345f7b3a3 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -332,6 +332,7 @@ enum {
 	CEPH_MDS_OP_LOOKUPHASH = 0x00102,
 	CEPH_MDS_OP_LOOKUPPARENT = 0x00103,
 	CEPH_MDS_OP_LOOKUPINO  = 0x00104,
+	CEPH_MDS_OP_LOOKUPNAME = 0x00105,
 
 	CEPH_MDS_OP_SETXATTR   = 0x01105,
 	CEPH_MDS_OP_RMXATTR    = 0x01106,
-- 
cgit v1.2.3


From 8e2f1a63f2217365223026422a2f8ba5967051d6 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Wed, 2 Apr 2014 20:52:57 +0200
Subject: packet: fix packet_direct_xmit for BQL enabled drivers

Currently, in packet_direct_xmit() we test the assigned netdevice queue
for netif_xmit_frozen_or_stopped() before doing an ndo_start_xmit().

This can have the side-effect that BQL enabled drivers which make use
of netdev_tx_sent_queue() internally, set __QUEUE_STATE_STACK_XOFF from
within the stack and would not fully fill the device's TX ring from
packet sockets with PACKET_QDISC_BYPASS enabled.

Instead, use a test without BQL bit so that bursts can be absorbed
into the NICs TX ring. Fix and code suggested by Eric Dumazet, thanks!

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 24 +++++++++++++++++++-----
 net/packet/af_packet.c    |  2 +-
 2 files changed, 20 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 775cc956ff78..7ed3a3aa6604 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -519,11 +519,18 @@ enum netdev_queue_state_t {
 	__QUEUE_STATE_DRV_XOFF,
 	__QUEUE_STATE_STACK_XOFF,
 	__QUEUE_STATE_FROZEN,
-#define QUEUE_STATE_ANY_XOFF ((1 << __QUEUE_STATE_DRV_XOFF)		| \
-			      (1 << __QUEUE_STATE_STACK_XOFF))
-#define QUEUE_STATE_ANY_XOFF_OR_FROZEN (QUEUE_STATE_ANY_XOFF		| \
-					(1 << __QUEUE_STATE_FROZEN))
 };
+
+#define QUEUE_STATE_DRV_XOFF	(1 << __QUEUE_STATE_DRV_XOFF)
+#define QUEUE_STATE_STACK_XOFF	(1 << __QUEUE_STATE_STACK_XOFF)
+#define QUEUE_STATE_FROZEN	(1 << __QUEUE_STATE_FROZEN)
+
+#define QUEUE_STATE_ANY_XOFF	(QUEUE_STATE_DRV_XOFF | QUEUE_STATE_STACK_XOFF)
+#define QUEUE_STATE_ANY_XOFF_OR_FROZEN (QUEUE_STATE_ANY_XOFF | \
+					QUEUE_STATE_FROZEN)
+#define QUEUE_STATE_DRV_XOFF_OR_FROZEN (QUEUE_STATE_DRV_XOFF | \
+					QUEUE_STATE_FROZEN)
+
 /*
  * __QUEUE_STATE_DRV_XOFF is used by drivers to stop the transmit queue.  The
  * netif_tx_* functions below are used to manipulate this flag.  The
@@ -2252,11 +2259,18 @@ static inline bool netif_xmit_stopped(const struct netdev_queue *dev_queue)
 	return dev_queue->state & QUEUE_STATE_ANY_XOFF;
 }
 
-static inline bool netif_xmit_frozen_or_stopped(const struct netdev_queue *dev_queue)
+static inline bool
+netif_xmit_frozen_or_stopped(const struct netdev_queue *dev_queue)
 {
 	return dev_queue->state & QUEUE_STATE_ANY_XOFF_OR_FROZEN;
 }
 
+static inline bool
+netif_xmit_frozen_or_drv_stopped(const struct netdev_queue *dev_queue)
+{
+	return dev_queue->state & QUEUE_STATE_DRV_XOFF_OR_FROZEN;
+}
+
 static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue,
 					unsigned int bytes)
 {
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index c81a9719b5b2..72e0c71fb01d 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -261,7 +261,7 @@ static int packet_direct_xmit(struct sk_buff *skb)
 	local_bh_disable();
 
 	HARD_TX_LOCK(dev, txq, smp_processor_id());
-	if (!netif_xmit_frozen_or_stopped(txq)) {
+	if (!netif_xmit_frozen_or_drv_stopped(txq)) {
 		ret = ops->ndo_start_xmit(skb, dev);
 		if (ret == NETDEV_TX_OK)
 			txq_trans_update(txq);
-- 
cgit v1.2.3


From d0290214de712150b118a532ded378a29255893b Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@resnulli.us>
Date: Wed, 2 Apr 2014 23:09:31 +0200
Subject: net: add busy_poll device feature

Currently there is no way how to find out if a device supports busy
polling. So add a feature and make it dependent on ndo_busy_poll
existence.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdev_features.h | 2 ++
 net/core/dev.c                  | 7 +++++++
 net/core/ethtool.c              | 1 +
 3 files changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 5a09a48f2658..c26d0ec2ef3a 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -63,6 +63,7 @@ enum {
 	NETIF_F_HW_VLAN_STAG_RX_BIT,	/* Receive VLAN STAG HW acceleration */
 	NETIF_F_HW_VLAN_STAG_FILTER_BIT,/* Receive filtering on VLAN STAGs */
 	NETIF_F_HW_L2FW_DOFFLOAD_BIT,	/* Allow L2 Forwarding in Hardware */
+	NETIF_F_BUSY_POLL_BIT,		/* Busy poll */
 
 	/*
 	 * Add your fresh new feature above and remember to update
@@ -118,6 +119,7 @@ enum {
 #define NETIF_F_HW_VLAN_STAG_RX	__NETIF_F(HW_VLAN_STAG_RX)
 #define NETIF_F_HW_VLAN_STAG_TX	__NETIF_F(HW_VLAN_STAG_TX)
 #define NETIF_F_HW_L2FW_DOFFLOAD	__NETIF_F(HW_L2FW_DOFFLOAD)
+#define NETIF_F_BUSY_POLL	__NETIF_F(BUSY_POLL)
 
 /* Features valid for ethtool to change */
 /* = all defined minus driver/device-class-related */
diff --git a/net/core/dev.c b/net/core/dev.c
index 757063420ce0..75e88e0372cb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5696,6 +5696,13 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
 		}
 	}
 
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	if (dev->netdev_ops->ndo_busy_poll)
+		features |= NETIF_F_BUSY_POLL;
+	else
+#endif
+		features &= ~NETIF_F_BUSY_POLL;
+
 	return features;
 }
 
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 30071dec287a..640ba0e5831c 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -97,6 +97,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_RXFCS_BIT] =            "rx-fcs",
 	[NETIF_F_RXALL_BIT] =            "rx-all",
 	[NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload",
+	[NETIF_F_BUSY_POLL_BIT] =        "busy-poll",
 };
 
 static int ethtool_get_features(struct net_device *dev, void __user *useraddr)
-- 
cgit v1.2.3


From 5acda9d12dcf1ad0d9a5a2a7c646de3472fa7555 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Thu, 3 Apr 2014 14:46:23 -0700
Subject: bdi: avoid oops on device removal

After commit 839a8e8660b6 ("writeback: replace custom worker pool
implementation with unbound workqueue") when device is removed while we
are writing to it we crash in bdi_writeback_workfn() ->
set_worker_desc() because bdi->dev is NULL.

This can happen because even though bdi_unregister() cancels all pending
flushing work, nothing really prevents new ones from being queued from
balance_dirty_pages() or other places.

Fix the problem by clearing BDI_registered bit in bdi_unregister() and
checking it before scheduling of any flushing work.

Fixes: 839a8e8660b6777e7fe4e80af1a048aebe2b5977

Reviewed-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jan Kara <jack@suse.cz>
Cc: Derek Basehore <dbasehore@chromium.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/fs-writeback.c           | 23 ++++++++++++++++++-----
 include/linux/backing-dev.h |  2 +-
 mm/backing-dev.c            | 13 +++++++++----
 3 files changed, 28 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 6788fe0c9761..a16315957ef3 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -89,16 +89,29 @@ static inline struct inode *wb_inode(struct list_head *head)
 #define CREATE_TRACE_POINTS
 #include <trace/events/writeback.h>
 
+static void bdi_wakeup_thread(struct backing_dev_info *bdi)
+{
+	spin_lock_bh(&bdi->wb_lock);
+	if (test_bit(BDI_registered, &bdi->state))
+		mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+	spin_unlock_bh(&bdi->wb_lock);
+}
+
 static void bdi_queue_work(struct backing_dev_info *bdi,
 			   struct wb_writeback_work *work)
 {
 	trace_writeback_queue(bdi, work);
 
 	spin_lock_bh(&bdi->wb_lock);
+	if (!test_bit(BDI_registered, &bdi->state)) {
+		if (work->done)
+			complete(work->done);
+		goto out_unlock;
+	}
 	list_add_tail(&work->list, &bdi->work_list);
-	spin_unlock_bh(&bdi->wb_lock);
-
 	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+out_unlock:
+	spin_unlock_bh(&bdi->wb_lock);
 }
 
 static void
@@ -114,7 +127,7 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
 	work = kzalloc(sizeof(*work), GFP_ATOMIC);
 	if (!work) {
 		trace_writeback_nowork(bdi);
-		mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+		bdi_wakeup_thread(bdi);
 		return;
 	}
 
@@ -161,7 +174,7 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi)
 	 * writeback as soon as there is no other work to do.
 	 */
 	trace_writeback_wake_background(bdi);
-	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
+	bdi_wakeup_thread(bdi);
 }
 
 /*
@@ -1017,7 +1030,7 @@ void bdi_writeback_workfn(struct work_struct *work)
 	current->flags |= PF_SWAPWRITE;
 
 	if (likely(!current_is_workqueue_rescuer() ||
-		   list_empty(&bdi->bdi_list))) {
+		   !test_bit(BDI_registered, &bdi->state))) {
 		/*
 		 * The normal path.  Keep writing back @bdi until its
 		 * work_list is empty.  Note that this path is also taken
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 24819001f5c8..e488e9459a93 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -95,7 +95,7 @@ struct backing_dev_info {
 	unsigned int max_ratio, max_prop_frac;
 
 	struct bdi_writeback wb;  /* default writeback info for this bdi */
-	spinlock_t wb_lock;	  /* protects work_list */
+	spinlock_t wb_lock;	  /* protects work_list & wb.dwork scheduling */
 
 	struct list_head work_list;
 
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index fab8401fc54e..09d9591b7708 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -297,7 +297,10 @@ void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi)
 	unsigned long timeout;
 
 	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
-	queue_delayed_work(bdi_wq, &bdi->wb.dwork, timeout);
+	spin_lock_bh(&bdi->wb_lock);
+	if (test_bit(BDI_registered, &bdi->state))
+		queue_delayed_work(bdi_wq, &bdi->wb.dwork, timeout);
+	spin_unlock_bh(&bdi->wb_lock);
 }
 
 /*
@@ -310,9 +313,6 @@ static void bdi_remove_from_list(struct backing_dev_info *bdi)
 	spin_unlock_bh(&bdi_lock);
 
 	synchronize_rcu_expedited();
-
-	/* bdi_list is now unused, clear it to mark @bdi dying */
-	INIT_LIST_HEAD(&bdi->bdi_list);
 }
 
 int bdi_register(struct backing_dev_info *bdi, struct device *parent,
@@ -363,6 +363,11 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
 	 */
 	bdi_remove_from_list(bdi);
 
+	/* Make sure nobody queues further work */
+	spin_lock_bh(&bdi->wb_lock);
+	clear_bit(BDI_registered, &bdi->state);
+	spin_unlock_bh(&bdi->wb_lock);
+
 	/*
 	 * Drain work list and shutdown the delayed_work.  At this point,
 	 * @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi
-- 
cgit v1.2.3


From 5f3bf19aeb8ed5cef0926bc10c80b6a50ac6bdeb Mon Sep 17 00:00:00 2001
From: Li Zefan <lizefan@huawei.com>
Date: Thu, 3 Apr 2014 14:46:28 -0700
Subject: kmemleak: remove redundant code

Remove kmemleak_padding() and kmemleak_release().

Signed-off-by: Li Zefan <lizefan@huawei.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kmemleak.h | 2 --
 mm/kmemleak.c            | 7 +------
 2 files changed, 1 insertion(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h
index 2a5e5548a1d2..5bb424659c04 100644
--- a/include/linux/kmemleak.h
+++ b/include/linux/kmemleak.h
@@ -30,8 +30,6 @@ extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size) __ref;
 extern void kmemleak_free(const void *ptr) __ref;
 extern void kmemleak_free_part(const void *ptr, size_t size) __ref;
 extern void kmemleak_free_percpu(const void __percpu *ptr) __ref;
-extern void kmemleak_padding(const void *ptr, unsigned long offset,
-			     size_t size) __ref;
 extern void kmemleak_not_leak(const void *ptr) __ref;
 extern void kmemleak_ignore(const void *ptr) __ref;
 extern void kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp) __ref;
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 06cd22035a92..6f90d003830a 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1549,11 +1549,6 @@ static int kmemleak_open(struct inode *inode, struct file *file)
 	return seq_open(file, &kmemleak_seq_ops);
 }
 
-static int kmemleak_release(struct inode *inode, struct file *file)
-{
-	return seq_release(inode, file);
-}
-
 static int dump_str_object_info(const char *str)
 {
 	unsigned long flags;
@@ -1691,7 +1686,7 @@ static const struct file_operations kmemleak_fops = {
 	.read		= seq_read,
 	.write		= kmemleak_write,
 	.llseek		= seq_lseek,
-	.release	= kmemleak_release,
+	.release	= seq_release,
 };
 
 static void __kmemleak_do_cleanup(void)
-- 
cgit v1.2.3


From 9573f79355ff3711c98227d14a9b7f4cb3222b97 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Thu, 3 Apr 2014 14:46:34 -0700
Subject: fanotify: convert access_mutex to spinlock

access_mutex is used only to guard operations on access_list.  There's
no need for sleeping within this lock so just make a spinlock out of it.

Signed-off-by: Jan Kara <jack@suse.cz>
Cc: Eric Paris <eparis@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/notify/fanotify/fanotify_user.c | 14 +++++++-------
 include/linux/fsnotify_backend.h   |  2 +-
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 8f5e85269110..2a57278afb80 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -134,7 +134,7 @@ static struct fanotify_perm_event_info *dequeue_event(
 {
 	struct fanotify_perm_event_info *event, *return_e = NULL;
 
-	mutex_lock(&group->fanotify_data.access_mutex);
+	spin_lock(&group->fanotify_data.access_lock);
 	list_for_each_entry(event, &group->fanotify_data.access_list,
 			    fae.fse.list) {
 		if (event->fd != fd)
@@ -144,7 +144,7 @@ static struct fanotify_perm_event_info *dequeue_event(
 		return_e = event;
 		break;
 	}
-	mutex_unlock(&group->fanotify_data.access_mutex);
+	spin_unlock(&group->fanotify_data.access_lock);
 
 	pr_debug("%s: found return_re=%p\n", __func__, return_e);
 
@@ -213,10 +213,10 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 
 		pevent = FANOTIFY_PE(event);
 		pevent->fd = fd;
-		mutex_lock(&group->fanotify_data.access_mutex);
+		spin_lock(&group->fanotify_data.access_lock);
 		list_add_tail(&pevent->fae.fse.list,
 			      &group->fanotify_data.access_list);
-		mutex_unlock(&group->fanotify_data.access_mutex);
+		spin_unlock(&group->fanotify_data.access_lock);
 	}
 #endif
 
@@ -346,7 +346,7 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
 	struct fanotify_perm_event_info *event, *next;
 
-	mutex_lock(&group->fanotify_data.access_mutex);
+	spin_lock(&group->fanotify_data.access_lock);
 
 	atomic_inc(&group->fanotify_data.bypass_perm);
 
@@ -358,7 +358,7 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 		list_del_init(&event->fae.fse.list);
 		event->response = FAN_ALLOW;
 	}
-	mutex_unlock(&group->fanotify_data.access_mutex);
+	spin_unlock(&group->fanotify_data.access_lock);
 
 	wake_up(&group->fanotify_data.access_waitq);
 #endif
@@ -700,7 +700,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 
 	group->fanotify_data.f_flags = event_f_flags;
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
-	mutex_init(&group->fanotify_data.access_mutex);
+	spin_lock_init(&group->fanotify_data.access_lock);
 	init_waitqueue_head(&group->fanotify_data.access_waitq);
 	INIT_LIST_HEAD(&group->fanotify_data.access_list);
 	atomic_set(&group->fanotify_data.bypass_perm, 0);
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 64cf3ef50696..fc7718c6bd3e 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -178,7 +178,7 @@ struct fsnotify_group {
 		struct fanotify_group_private_data {
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
 			/* allows a group to block waiting for a userspace response */
-			struct mutex access_mutex;
+			spinlock_t access_lock;
 			struct list_head access_list;
 			wait_queue_head_t access_waitq;
 			atomic_t bypass_perm;
-- 
cgit v1.2.3


From 9f985cb6c45bc3f8b7e161c9658d409d051d576f Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Thu, 3 Apr 2014 14:46:55 -0700
Subject: quota: provide function to grab quota structure reference

Provide dqgrab() function to get quota structure reference when we are
sure it already has at least one active reference.  Make use of this
function inside quota code.

Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Mark Fasheh <mfasheh@suse.de>
Reviewed-by: Srinivas Eeda <srinivas.eeda@oracle.com>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/quota/dquot.c         | 4 ++--
 include/linux/quotaops.h | 8 ++++++++
 2 files changed, 10 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index cfc8dcc16043..9cd5f63715c0 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -528,7 +528,7 @@ restart:
 		if (atomic_read(&dquot->dq_count)) {
 			DEFINE_WAIT(wait);
 
-			atomic_inc(&dquot->dq_count);
+			dqgrab(dquot);
 			prepare_to_wait(&dquot->dq_wait_unused, &wait,
 					TASK_UNINTERRUPTIBLE);
 			spin_unlock(&dq_list_lock);
@@ -632,7 +632,7 @@ int dquot_writeback_dquots(struct super_block *sb, int type)
 			/* Now we have active dquot from which someone is
  			 * holding reference so we can safely just increase
 			 * use count */
-			atomic_inc(&dquot->dq_count);
+			dqgrab(dquot);
 			spin_unlock(&dq_list_lock);
 			dqstats_inc(DQST_LOOKUPS);
 			err = sb->dq_op->write_dquot(dquot);
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index 6965fe394c3b..1d3eee594cd6 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -46,6 +46,14 @@ void inode_reclaim_rsv_space(struct inode *inode, qsize_t number);
 void dquot_initialize(struct inode *inode);
 void dquot_drop(struct inode *inode);
 struct dquot *dqget(struct super_block *sb, struct kqid qid);
+static inline struct dquot *dqgrab(struct dquot *dquot)
+{
+	/* Make sure someone else has active reference to dquot */
+	WARN_ON_ONCE(!atomic_read(&dquot->dq_count));
+	WARN_ON_ONCE(!test_bit(DQ_ACTIVE_B, &dquot->dq_flags));
+	atomic_inc(&dquot->dq_count);
+	return dquot;
+}
 void dqput(struct dquot *dquot);
 int dquot_scan_active(struct super_block *sb,
 		      int (*fn)(struct dquot *dquot, unsigned long priv),
-- 
cgit v1.2.3


From d26914d11751b23ca2e8747725f2cae10c2f2c1b Mon Sep 17 00:00:00 2001
From: Mel Gorman <mgorman@suse.de>
Date: Thu, 3 Apr 2014 14:47:24 -0700
Subject: mm: optimize put_mems_allowed() usage

Since put_mems_allowed() is strictly optional, its a seqcount retry, we
don't need to evaluate the function if the allocation was in fact
successful, saving a smp_rmb some loads and comparisons on some relative
fast-paths.

Since the naming, get/put_mems_allowed() does suggest a mandatory
pairing, rename the interface, as suggested by Mel, to resemble the
seqcount interface.

This gives us: read_mems_allowed_begin() and read_mems_allowed_retry(),
where it is important to note that the return value of the latter call
is inverted from its previous incarnation.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/cpuset.h | 27 ++++++++++++++-------------
 kernel/cpuset.c        |  2 +-
 mm/filemap.c           |  4 ++--
 mm/hugetlb.c           |  4 ++--
 mm/mempolicy.c         | 12 ++++++------
 mm/page_alloc.c        |  8 ++++----
 mm/slab.c              |  4 ++--
 mm/slub.c              | 16 +++++++---------
 8 files changed, 38 insertions(+), 39 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 3fe661fe96d1..b19d3dc2e651 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -87,25 +87,26 @@ extern void rebuild_sched_domains(void);
 extern void cpuset_print_task_mems_allowed(struct task_struct *p);
 
 /*
- * get_mems_allowed is required when making decisions involving mems_allowed
- * such as during page allocation. mems_allowed can be updated in parallel
- * and depending on the new value an operation can fail potentially causing
- * process failure. A retry loop with get_mems_allowed and put_mems_allowed
- * prevents these artificial failures.
+ * read_mems_allowed_begin is required when making decisions involving
+ * mems_allowed such as during page allocation. mems_allowed can be updated in
+ * parallel and depending on the new value an operation can fail potentially
+ * causing process failure. A retry loop with read_mems_allowed_begin and
+ * read_mems_allowed_retry prevents these artificial failures.
  */
-static inline unsigned int get_mems_allowed(void)
+static inline unsigned int read_mems_allowed_begin(void)
 {
 	return read_seqcount_begin(&current->mems_allowed_seq);
 }
 
 /*
- * If this returns false, the operation that took place after get_mems_allowed
- * may have failed. It is up to the caller to retry the operation if
+ * If this returns true, the operation that took place after
+ * read_mems_allowed_begin may have failed artificially due to a concurrent
+ * update of mems_allowed. It is up to the caller to retry the operation if
  * appropriate.
  */
-static inline bool put_mems_allowed(unsigned int seq)
+static inline bool read_mems_allowed_retry(unsigned int seq)
 {
-	return !read_seqcount_retry(&current->mems_allowed_seq, seq);
+	return read_seqcount_retry(&current->mems_allowed_seq, seq);
 }
 
 static inline void set_mems_allowed(nodemask_t nodemask)
@@ -225,14 +226,14 @@ static inline void set_mems_allowed(nodemask_t nodemask)
 {
 }
 
-static inline unsigned int get_mems_allowed(void)
+static inline unsigned int read_mems_allowed_begin(void)
 {
 	return 0;
 }
 
-static inline bool put_mems_allowed(unsigned int seq)
+static inline bool read_mems_allowed_retry(unsigned int seq)
 {
-	return true;
+	return false;
 }
 
 #endif /* !CONFIG_CPUSETS */
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index e6b1b66afe52..f6fc7475f1a1 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1022,7 +1022,7 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
 	task_lock(tsk);
 	/*
 	 * Determine if a loop is necessary if another thread is doing
-	 * get_mems_allowed().  If at least one node remains unchanged and
+	 * read_mems_allowed_begin().  If at least one node remains unchanged and
 	 * tsk does not have a mempolicy, then an empty nodemask will not be
 	 * possible when mems_allowed is larger than a word.
 	 */
diff --git a/mm/filemap.c b/mm/filemap.c
index 7a13f6ac5421..068cd2a63d32 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -520,10 +520,10 @@ struct page *__page_cache_alloc(gfp_t gfp)
 	if (cpuset_do_page_mem_spread()) {
 		unsigned int cpuset_mems_cookie;
 		do {
-			cpuset_mems_cookie = get_mems_allowed();
+			cpuset_mems_cookie = read_mems_allowed_begin();
 			n = cpuset_mem_spread_node();
 			page = alloc_pages_exact_node(n, gfp, 0);
-		} while (!put_mems_allowed(cpuset_mems_cookie) && !page);
+		} while (!page && read_mems_allowed_retry(cpuset_mems_cookie));
 
 		return page;
 	}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index c01cb9fedb18..139b7462203b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -540,7 +540,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 		goto err;
 
 retry_cpuset:
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 	zonelist = huge_zonelist(vma, address,
 					htlb_alloc_mask(h), &mpol, &nodemask);
 
@@ -562,7 +562,7 @@ retry_cpuset:
 	}
 
 	mpol_cond_put(mpol);
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 	return page;
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 4755c8576942..e3ab02822799 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1899,7 +1899,7 @@ int node_random(const nodemask_t *maskp)
  * If the effective policy is 'BIND, returns a pointer to the mempolicy's
  * @nodemask for filtering the zonelist.
  *
- * Must be protected by get_mems_allowed()
+ * Must be protected by read_mems_allowed_begin()
  */
 struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr,
 				gfp_t gfp_flags, struct mempolicy **mpol,
@@ -2063,7 +2063,7 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 
 retry_cpuset:
 	pol = get_vma_policy(current, vma, addr);
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 
 	if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
 		unsigned nid;
@@ -2071,7 +2071,7 @@ retry_cpuset:
 		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order);
 		mpol_cond_put(pol);
 		page = alloc_page_interleave(gfp, order, nid);
-		if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 			goto retry_cpuset;
 
 		return page;
@@ -2081,7 +2081,7 @@ retry_cpuset:
 				      policy_nodemask(gfp, pol));
 	if (unlikely(mpol_needs_cond_ref(pol)))
 		__mpol_put(pol);
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 	return page;
 }
@@ -2115,7 +2115,7 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 		pol = &default_policy;
 
 retry_cpuset:
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 
 	/*
 	 * No reference counting needed for current->mempolicy
@@ -2128,7 +2128,7 @@ retry_cpuset:
 				policy_zonelist(gfp, pol, numa_node_id()),
 				policy_nodemask(gfp, pol));
 
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 
 	return page;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3bac76ae4b30..979378deccbf 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2739,7 +2739,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 		return NULL;
 
 retry_cpuset:
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 
 	/* The preferred zone is used for statistics later */
 	first_zones_zonelist(zonelist, high_zoneidx,
@@ -2777,7 +2777,7 @@ out:
 	 * the mask is being updated. If a page allocation is about to fail,
 	 * check if the cpuset changed during allocation and if so, retry.
 	 */
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 
 	memcg_kmem_commit_charge(page, memcg, order);
@@ -3045,9 +3045,9 @@ bool skip_free_areas_node(unsigned int flags, int nid)
 		goto out;
 
 	do {
-		cpuset_mems_cookie = get_mems_allowed();
+		cpuset_mems_cookie = read_mems_allowed_begin();
 		ret = !node_isset(nid, cpuset_current_mems_allowed);
-	} while (!put_mems_allowed(cpuset_mems_cookie));
+	} while (read_mems_allowed_retry(cpuset_mems_cookie));
 out:
 	return ret;
 }
diff --git a/mm/slab.c b/mm/slab.c
index b264214c77ea..9153c802e2fe 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3073,7 +3073,7 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
 	local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);
 
 retry_cpuset:
-	cpuset_mems_cookie = get_mems_allowed();
+	cpuset_mems_cookie = read_mems_allowed_begin();
 	zonelist = node_zonelist(slab_node(), flags);
 
 retry:
@@ -3131,7 +3131,7 @@ retry:
 		}
 	}
 
-	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !obj))
+	if (unlikely(!obj && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
 	return obj;
 }
diff --git a/mm/slub.c b/mm/slub.c
index 25f14ad8f817..7611f148ee81 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1684,7 +1684,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
 		return NULL;
 
 	do {
-		cpuset_mems_cookie = get_mems_allowed();
+		cpuset_mems_cookie = read_mems_allowed_begin();
 		zonelist = node_zonelist(slab_node(), flags);
 		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
 			struct kmem_cache_node *n;
@@ -1696,19 +1696,17 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
 				object = get_partial_node(s, n, c, flags);
 				if (object) {
 					/*
-					 * Return the object even if
-					 * put_mems_allowed indicated that
-					 * the cpuset mems_allowed was
-					 * updated in parallel. It's a
-					 * harmless race between the alloc
-					 * and the cpuset update.
+					 * Don't check read_mems_allowed_retry()
+					 * here - if mems_allowed was updated in
+					 * parallel, that was a harmless race
+					 * between allocation and the cpuset
+					 * update
 					 */
-					put_mems_allowed(cpuset_mems_cookie);
 					return object;
 				}
 			}
 		}
-	} while (!put_mems_allowed(cpuset_mems_cookie));
+	} while (read_mems_allowed_retry(cpuset_mems_cookie));
 #endif
 	return NULL;
 }
-- 
cgit v1.2.3


From 9119a41e9091fb3a8204039d595bcdae24193c57 Mon Sep 17 00:00:00 2001
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Date: Thu, 3 Apr 2014 14:47:25 -0700
Subject: mm, hugetlb: unify region structure handling

Currently, to track reserved and allocated regions, we use two different
ways, depending on the mapping.  For MAP_SHARED, we use
address_mapping's private_list and, while for MAP_PRIVATE, we use a
resv_map.

Now, we are preparing to change a coarse grained lock which protect a
region structure to fine grained lock, and this difference hinder it.
So, before changing it, unify region structure handling, consistently
using a resv_map regardless of the kind of mapping.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/hugetlbfs/inode.c    | 17 +++++++++++++++--
 include/linux/hugetlb.h |  9 +++++++++
 mm/hugetlb.c            | 37 +++++++++++++++++++++----------------
 3 files changed, 45 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index d19b30ababf1..204027520937 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -366,7 +366,13 @@ static void truncate_hugepages(struct inode *inode, loff_t lstart)
 
 static void hugetlbfs_evict_inode(struct inode *inode)
 {
+	struct resv_map *resv_map;
+
 	truncate_hugepages(inode, 0);
+	resv_map = (struct resv_map *)inode->i_mapping->private_data;
+	/* root inode doesn't have the resv_map, so we should check it */
+	if (resv_map)
+		resv_map_release(&resv_map->refs);
 	clear_inode(inode);
 }
 
@@ -476,6 +482,11 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 					umode_t mode, dev_t dev)
 {
 	struct inode *inode;
+	struct resv_map *resv_map;
+
+	resv_map = resv_map_alloc();
+	if (!resv_map)
+		return NULL;
 
 	inode = new_inode(sb);
 	if (inode) {
@@ -487,7 +498,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 		inode->i_mapping->a_ops = &hugetlbfs_aops;
 		inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-		INIT_LIST_HEAD(&inode->i_mapping->private_list);
+		inode->i_mapping->private_data = resv_map;
 		info = HUGETLBFS_I(inode);
 		/*
 		 * The policy is initialized here even if we are creating a
@@ -517,7 +528,9 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 			break;
 		}
 		lockdep_annotate_inode_mutex_key(inode);
-	}
+	} else
+		kref_put(&resv_map->refs, resv_map_release);
+
 	return inode;
 }
 
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 8c43cc469d78..f62c2f6c6059 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -6,6 +6,8 @@
 #include <linux/fs.h>
 #include <linux/hugetlb_inline.h>
 #include <linux/cgroup.h>
+#include <linux/list.h>
+#include <linux/kref.h>
 
 struct ctl_table;
 struct user_struct;
@@ -23,6 +25,13 @@ struct hugepage_subpool {
 	long max_hpages, used_hpages;
 };
 
+struct resv_map {
+	struct kref refs;
+	struct list_head regions;
+};
+extern struct resv_map *resv_map_alloc(void);
+void resv_map_release(struct kref *ref);
+
 extern spinlock_t hugetlb_lock;
 extern int hugetlb_max_hstate __read_mostly;
 #define for_each_hstate(h) \
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 139b7462203b..63699afc7b7f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -376,12 +376,7 @@ static void set_vma_private_data(struct vm_area_struct *vma,
 	vma->vm_private_data = (void *)value;
 }
 
-struct resv_map {
-	struct kref refs;
-	struct list_head regions;
-};
-
-static struct resv_map *resv_map_alloc(void)
+struct resv_map *resv_map_alloc(void)
 {
 	struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL);
 	if (!resv_map)
@@ -393,7 +388,7 @@ static struct resv_map *resv_map_alloc(void)
 	return resv_map;
 }
 
-static void resv_map_release(struct kref *ref)
+void resv_map_release(struct kref *ref)
 {
 	struct resv_map *resv_map = container_of(ref, struct resv_map, refs);
 
@@ -1155,8 +1150,9 @@ static long vma_needs_reservation(struct hstate *h,
 
 	if (vma->vm_flags & VM_MAYSHARE) {
 		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
-		return region_chg(&inode->i_mapping->private_list,
-							idx, idx + 1);
+		struct resv_map *resv = inode->i_mapping->private_data;
+
+		return region_chg(&resv->regions, idx, idx + 1);
 
 	} else if (!is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
 		return 1;
@@ -1180,7 +1176,9 @@ static void vma_commit_reservation(struct hstate *h,
 
 	if (vma->vm_flags & VM_MAYSHARE) {
 		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
-		region_add(&inode->i_mapping->private_list, idx, idx + 1);
+		struct resv_map *resv = inode->i_mapping->private_data;
+
+		region_add(&resv->regions, idx, idx + 1);
 
 	} else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
 		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
@@ -3161,6 +3159,7 @@ int hugetlb_reserve_pages(struct inode *inode,
 	long ret, chg;
 	struct hstate *h = hstate_inode(inode);
 	struct hugepage_subpool *spool = subpool_inode(inode);
+	struct resv_map *resv_map;
 
 	/*
 	 * Only apply hugepage reservation if asked. At fault time, an
@@ -3176,10 +3175,13 @@ int hugetlb_reserve_pages(struct inode *inode,
 	 * to reserve the full area even if read-only as mprotect() may be
 	 * called to make the mapping read-write. Assume !vma is a shm mapping
 	 */
-	if (!vma || vma->vm_flags & VM_MAYSHARE)
-		chg = region_chg(&inode->i_mapping->private_list, from, to);
-	else {
-		struct resv_map *resv_map = resv_map_alloc();
+	if (!vma || vma->vm_flags & VM_MAYSHARE) {
+		resv_map = inode->i_mapping->private_data;
+
+		chg = region_chg(&resv_map->regions, from, to);
+
+	} else {
+		resv_map = resv_map_alloc();
 		if (!resv_map)
 			return -ENOMEM;
 
@@ -3222,7 +3224,7 @@ int hugetlb_reserve_pages(struct inode *inode,
 	 * else has to be done for private mappings here
 	 */
 	if (!vma || vma->vm_flags & VM_MAYSHARE)
-		region_add(&inode->i_mapping->private_list, from, to);
+		region_add(&resv_map->regions, from, to);
 	return 0;
 out_err:
 	if (vma)
@@ -3233,9 +3235,12 @@ out_err:
 void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
 {
 	struct hstate *h = hstate_inode(inode);
-	long chg = region_truncate(&inode->i_mapping->private_list, offset);
+	struct resv_map *resv_map = inode->i_mapping->private_data;
+	long chg = 0;
 	struct hugepage_subpool *spool = subpool_inode(inode);
 
+	if (resv_map)
+		chg = region_truncate(&resv_map->regions, offset);
 	spin_lock(&inode->i_lock);
 	inode->i_blocks -= (blocks_per_huge_page(h) * freed);
 	spin_unlock(&inode->i_lock);
-- 
cgit v1.2.3


From 7b24d8616be33616efd41ff67d3c76362c60ca84 Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <davidlohr@hp.com>
Date: Thu, 3 Apr 2014 14:47:27 -0700
Subject: mm, hugetlb: fix race in region tracking

There is a race condition if we map a same file on different processes.
Region tracking is protected by mmap_sem and hugetlb_instantiation_mutex.
When we do mmap, we don't grab a hugetlb_instantiation_mutex, but only
mmap_sem (exclusively).  This doesn't prevent other tasks from modifying
the region structure, so it can be modified by two processes
concurrently.

To solve this, introduce a spinlock to resv_map and make region
manipulation function grab it before they do actual work.

[davidlohr@hp.com: updated changelog]
Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Suggested-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: David Gibson <david@gibson.dropbear.id.au>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/hugetlb.h |  1 +
 mm/hugetlb.c            | 58 ++++++++++++++++++++++++++++++++-----------------
 2 files changed, 39 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index f62c2f6c6059..5b337cf8fb86 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -27,6 +27,7 @@ struct hugepage_subpool {
 
 struct resv_map {
 	struct kref refs;
+	spinlock_t lock;
 	struct list_head regions;
 };
 extern struct resv_map *resv_map_alloc(void);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 454b311373c5..5a2515a774b5 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -135,15 +135,8 @@ static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma)
  * Region tracking -- allows tracking of reservations and instantiated pages
  *                    across the pages in a mapping.
  *
- * The region data structures are protected by a combination of the mmap_sem
- * and the hugetlb_instantiation_mutex.  To access or modify a region the caller
- * must either hold the mmap_sem for write, or the mmap_sem for read and
- * the hugetlb_instantiation_mutex:
- *
- *	down_write(&mm->mmap_sem);
- * or
- *	down_read(&mm->mmap_sem);
- *	mutex_lock(&hugetlb_instantiation_mutex);
+ * The region data structures are embedded into a resv_map and
+ * protected by a resv_map's lock
  */
 struct file_region {
 	struct list_head link;
@@ -156,6 +149,7 @@ static long region_add(struct resv_map *resv, long f, long t)
 	struct list_head *head = &resv->regions;
 	struct file_region *rg, *nrg, *trg;
 
+	spin_lock(&resv->lock);
 	/* Locate the region we are either in or before. */
 	list_for_each_entry(rg, head, link)
 		if (f <= rg->to)
@@ -185,15 +179,18 @@ static long region_add(struct resv_map *resv, long f, long t)
 	}
 	nrg->from = f;
 	nrg->to = t;
+	spin_unlock(&resv->lock);
 	return 0;
 }
 
 static long region_chg(struct resv_map *resv, long f, long t)
 {
 	struct list_head *head = &resv->regions;
-	struct file_region *rg, *nrg;
+	struct file_region *rg, *nrg = NULL;
 	long chg = 0;
 
+retry:
+	spin_lock(&resv->lock);
 	/* Locate the region we are before or in. */
 	list_for_each_entry(rg, head, link)
 		if (f <= rg->to)
@@ -203,15 +200,21 @@ static long region_chg(struct resv_map *resv, long f, long t)
 	 * Subtle, allocate a new region at the position but make it zero
 	 * size such that we can guarantee to record the reservation. */
 	if (&rg->link == head || t < rg->from) {
-		nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
-		if (!nrg)
-			return -ENOMEM;
-		nrg->from = f;
-		nrg->to   = f;
-		INIT_LIST_HEAD(&nrg->link);
-		list_add(&nrg->link, rg->link.prev);
+		if (!nrg) {
+			spin_unlock(&resv->lock);
+			nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
+			if (!nrg)
+				return -ENOMEM;
+
+			nrg->from = f;
+			nrg->to   = f;
+			INIT_LIST_HEAD(&nrg->link);
+			goto retry;
+		}
 
-		return t - f;
+		list_add(&nrg->link, rg->link.prev);
+		chg = t - f;
+		goto out_nrg;
 	}
 
 	/* Round our left edge to the current segment if it encloses us. */
@@ -224,7 +227,7 @@ static long region_chg(struct resv_map *resv, long f, long t)
 		if (&rg->link == head)
 			break;
 		if (rg->from > t)
-			return chg;
+			goto out;
 
 		/* We overlap with this area, if it extends further than
 		 * us then we must extend ourselves.  Account for its
@@ -235,6 +238,14 @@ static long region_chg(struct resv_map *resv, long f, long t)
 		}
 		chg -= rg->to - rg->from;
 	}
+
+out:
+	spin_unlock(&resv->lock);
+	/*  We already know we raced and no longer need the new region */
+	kfree(nrg);
+	return chg;
+out_nrg:
+	spin_unlock(&resv->lock);
 	return chg;
 }
 
@@ -244,12 +255,13 @@ static long region_truncate(struct resv_map *resv, long end)
 	struct file_region *rg, *trg;
 	long chg = 0;
 
+	spin_lock(&resv->lock);
 	/* Locate the region we are either in or before. */
 	list_for_each_entry(rg, head, link)
 		if (end <= rg->to)
 			break;
 	if (&rg->link == head)
-		return 0;
+		goto out;
 
 	/* If we are in the middle of a region then adjust it. */
 	if (end > rg->from) {
@@ -266,6 +278,9 @@ static long region_truncate(struct resv_map *resv, long end)
 		list_del(&rg->link);
 		kfree(rg);
 	}
+
+out:
+	spin_unlock(&resv->lock);
 	return chg;
 }
 
@@ -275,6 +290,7 @@ static long region_count(struct resv_map *resv, long f, long t)
 	struct file_region *rg;
 	long chg = 0;
 
+	spin_lock(&resv->lock);
 	/* Locate each segment we overlap with, and count that overlap. */
 	list_for_each_entry(rg, head, link) {
 		long seg_from;
@@ -290,6 +306,7 @@ static long region_count(struct resv_map *resv, long f, long t)
 
 		chg += seg_to - seg_from;
 	}
+	spin_unlock(&resv->lock);
 
 	return chg;
 }
@@ -387,6 +404,7 @@ struct resv_map *resv_map_alloc(void)
 		return NULL;
 
 	kref_init(&resv_map->refs);
+	spin_lock_init(&resv_map->lock);
 	INIT_LIST_HEAD(&resv_map->regions);
 
 	return resv_map;
-- 
cgit v1.2.3


From 6a3ed2123a78de22a9e2b2855068a8d89f8e14f4 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Thu, 3 Apr 2014 14:47:34 -0700
Subject: mm: vmstat: fix UP zone state accounting

Summary:

The VM maintains cached filesystem pages on two types of lists.  One
list holds the pages recently faulted into the cache, the other list
holds pages that have been referenced repeatedly on that first list.
The idea is to prefer reclaiming young pages over those that have shown
to benefit from caching in the past.  We call the recently used list
"inactive list" and the frequently used list "active list".

Currently, the VM aims for a 1:1 ratio between the lists, which is the
"perfect" trade-off between the ability to *protect* frequently used
pages and the ability to *detect* frequently used pages.  This means
that working set changes bigger than half of cache memory go undetected
and thrash indefinitely, whereas working sets bigger than half of cache
memory are unprotected against used-once streams that don't even need
caching.

This happens on file servers and media streaming servers, where the
popular files and file sections change over time.  Even though the
individual files might be smaller than half of memory, concurrent access
to many of them may still result in their inter-reference distance being
greater than half of memory.  It's also been reported as a problem on
database workloads that switch back and forth between tables that are
bigger than half of memory.  In these cases the VM never recognizes the
new working set and will for the remainder of the workload thrash disk
data which could easily live in memory.

Historically, every reclaim scan of the inactive list also took a
smaller number of pages from the tail of the active list and moved them
to the head of the inactive list.  This model gave established working
sets more gracetime in the face of temporary use-once streams, but
ultimately was not significantly better than a FIFO policy and still
thrashed cache based on eviction speed, rather than actual demand for
cache.

This series solves the problem by maintaining a history of pages evicted
from the inactive list, enabling the VM to detect frequently used pages
regardless of inactive list size and facilitate working set transitions.

Tests:

The reported database workload is easily demonstrated on a 8G machine
with two filesets a 6G.  This fio workload operates on one set first,
then switches to the other.  The VM should obviously always cache the
set that the workload is currently using.

This test is based on a problem encountered by Citus Data customers:
  http://citusdata.com/blog/72-linux-memory-manager-and-your-big-data

unpatched:
  db1: READ: io=98304MB, aggrb=885559KB/s, minb=885559KB/s, maxb=885559KB/s, mint= 113672msec, maxt= 113672msec
  db2: READ: io=98304MB, aggrb= 66169KB/s, minb= 66169KB/s, maxb= 66169KB/s, mint=1521302msec, maxt=1521302msec
  sdb: ios=835750/4, merge=2/1, ticks=4659739/60016, in_queue=4719203, util=98.92%

  real    27m15.541s
  user    0m19.059s
  sys     0m51.459s

patched:
  db1: READ: io=98304MB, aggrb=877783KB/s, minb=877783KB/s, maxb=877783KB/s, mint=114679msec, maxt=114679msec
  db2: READ: io=98304MB, aggrb=397449KB/s, minb=397449KB/s, maxb=397449KB/s, mint=253273msec, maxt=253273msec
  sdb: ios=170587/4, merge=2/1, ticks=954910/61123, in_queue=1015923, util=90.40%

  real    6m8.630s
  user    0m14.714s
  sys     0m31.233s

As can be seen, the unpatched kernel simply never adapts to the
workingset change and db2 is stuck indefinitely with secondary storage
speed.  The patched kernel needs 2-3 iterations over db2 before it
replaces db1 and reaches full memory speed.  Given the unbounded
negative affect of the existing VM behavior, these patches should be
considered correctness fixes rather than performance optimizations.

Another test resembles a fileserver or streaming server workload, where
data in excess of memory size is accessed at different frequencies.
There is very hot data accessed at a high frequency.  Machines should be
fitted so that the hot set of such a workload can be fully cached or all
bets are off.  Then there is a very big (compared to available memory)
set of data that is used-once or at a very low frequency; this is what
drives the inactive list and does not really benefit from caching.
Lastly, there is a big set of warm data in between that is accessed at
medium frequencies and benefits from caching the pages between the first
and last streamer of each burst.

unpatched:
   hot: READ: io=128000MB, aggrb=160693KB/s, minb=160693KB/s, maxb=160693KB/s, mint=815665msec, maxt=815665msec
  warm: READ: io= 81920MB, aggrb=109853KB/s, minb= 27463KB/s, maxb= 29244KB/s, mint=717110msec, maxt=763617msec
  cold: READ: io= 30720MB, aggrb= 35245KB/s, minb= 35245KB/s, maxb= 35245KB/s, mint=892530msec, maxt=892530msec
   sdb: ios=797960/4, merge=11763/1, ticks=4307910/796, in_queue=4308380, util=100.00%

patched:
   hot: READ: io=128000MB, aggrb=160678KB/s, minb=160678KB/s, maxb=160678KB/s, mint=815740msec, maxt=815740msec
  warm: READ: io= 81920MB, aggrb=147747KB/s, minb= 36936KB/s, maxb= 40960KB/s, mint=512000msec, maxt=567767msec
  cold: READ: io= 30720MB, aggrb= 40960KB/s, minb= 40960KB/s, maxb= 40960KB/s, mint=768000msec, maxt=768000msec
   sdb: ios=596514/4, merge=9341/1, ticks=2395362/997, in_queue=2396484, util=79.18%

In both kernels, the hot set is propagated to the active list and then
served from cache.

In both kernels, the beginning of the warm set is propagated to the
active list as well, but in the unpatched case the active list
eventually takes up half of memory and no new pages from the warm set
get activated, despite repeated access, and despite most of the active
list soon being stale.  The patched kernel on the other hand detects the
thrashing and manages to keep this cache window rolling through the data
set.  This frees up enough IO bandwidth that the cold set is served at
full speed as well and disk utilization even drops by 20%.

For reference, this same test was performed with the traditional
demotion mechanism, where deactivation is coupled to inactive list
reclaim.  However, this had the same outcome as the unpatched kernel:
while the warm set does indeed get activated continuously, it is forced
out of the active list by inactive list pressure, which is dictated
primarily by the unrelated cold set.  The warm set is evicted before
subsequent streamers can benefit from it, even though there would be
enough space available to cache the pages of interest.

Costs:

Page reclaim used to shrink the radix trees but now the tree nodes are
reused for shadow entries, where the cost depends heavily on the page
cache access patterns.  However, with workloads that maintain spatial or
temporal locality, the shadow entries are either refaulted quickly or
reclaimed along with the inode object itself.  Workloads that will
experience a memory cost increase are those that don't really benefit
from caching in the first place.

A more predictable alternative would be a fixed-cost separate pool of
shadow entries, but this would incur relatively higher memory cost for
well-behaved workloads at the benefit of cornercases.  It would also
make the shadow entry lookup more costly compared to storing them
directly in the cache structure.

Future:

To simplify the merging process, this patch set is implementing thrash
detection on a global per-zone level only for now, but the design is
such that it can be extended to memory cgroups as well.  All we need to
do is store the unique cgroup ID along the node and zone identifier
inside the eviction cookie to identify the lruvec.

Right now we have a fixed ratio (50:50) between inactive and active list
but we already have complaints about working sets exceeding half of
memory being pushed out of the cache by simple streaming in the
background.  Ultimately, we want to adjust this ratio and allow for a
much smaller inactive list.  These patches are an essential step in this
direction because they decouple the VMs ability to detect working set
changes from the inactive list size.  This would allow us to base the
inactive list size on the combined readahead window size for example and
potentially protect a much bigger working set.

It's also a big step towards activating pages with a reuse distance
larger than memory, as long as they are the most frequently used pages
in the workload.  This will require knowing more about the access
frequency of active pages than what we measure right now, so it's also
deferred in this series.

Another possibility of having thrashing information would be to revisit
the idea of local reclaim in the form of zero-config memory control
groups.  Instead of having allocating tasks go straight to global
reclaim, they could try to reclaim the pages in the memcg they are part
of first as long as the group is not thrashing.  This would allow a user
to drop e.g.  a back-up job in an otherwise unconfigured memcg and it
would only inflate (and possibly do global reclaim) until it has enough
memory to do proper readahead.  But once it reaches that point and stops
thrashing it would just recycle its own used-once pages without kicking
out the cache of any other tasks in the system more than necessary.

This patch (of 10):

Fengguang Wu's build testing spotted problems with inc_zone_state() and
dec_zone_state() on UP configurations in out-of-tree patches.

inc_zone_state() is declared but not defined, dec_zone_state() is
missing entirely.

Just like with *_zone_page_state(), they can be defined like their
preemption-unsafe counterparts on UP.

[akpm@linux-foundation.org: make it build]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/vmstat.h | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 67ce70c8279b..ea4476157e00 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -187,8 +187,6 @@ extern void zone_statistics(struct zone *, struct zone *, gfp_t gfp);
 #define add_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, __d)
 #define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d))
 
-extern void inc_zone_state(struct zone *, enum zone_stat_item);
-
 #ifdef CONFIG_SMP
 void __mod_zone_page_state(struct zone *, enum zone_stat_item item, int);
 void __inc_zone_page_state(struct page *, enum zone_stat_item);
@@ -230,18 +228,18 @@ static inline void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
 	atomic_long_inc(&vm_stat[item]);
 }
 
-static inline void __inc_zone_page_state(struct page *page,
-			enum zone_stat_item item)
-{
-	__inc_zone_state(page_zone(page), item);
-}
-
 static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
 {
 	atomic_long_dec(&zone->vm_stat[item]);
 	atomic_long_dec(&vm_stat[item]);
 }
 
+static inline void __inc_zone_page_state(struct page *page,
+			enum zone_stat_item item)
+{
+	__inc_zone_state(page_zone(page), item);
+}
+
 static inline void __dec_zone_page_state(struct page *page,
 			enum zone_stat_item item)
 {
@@ -256,6 +254,9 @@ static inline void __dec_zone_page_state(struct page *page,
 #define dec_zone_page_state __dec_zone_page_state
 #define mod_zone_page_state __mod_zone_page_state
 
+#define inc_zone_state __inc_zone_state
+#define dec_zone_state __dec_zone_state
+
 #define set_pgdat_percpu_threshold(pgdat, callback) { }
 
 static inline void refresh_cpu_vm_stats(int cpu) { }
-- 
cgit v1.2.3


From 53c59f262d747ea82e7414774c59a489501186a0 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Thu, 3 Apr 2014 14:47:39 -0700
Subject: lib: radix-tree: add radix_tree_delete_item()

Provide a function that does not just delete an entry at a given index,
but also allows passing in an expected item.  Delete only if that item
is still located at the specified index.

This is handy when lockless tree traversals want to delete entries as
well because they don't have to do an second, locked lookup to verify
the slot has not changed under them before deleting the entry.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/radix-tree.h |  1 +
 lib/radix-tree.c           | 31 +++++++++++++++++++++++++++----
 2 files changed, 28 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 403940787be1..1bf0a9c388d9 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -219,6 +219,7 @@ static inline void radix_tree_replace_slot(void **pslot, void *item)
 int radix_tree_insert(struct radix_tree_root *, unsigned long, void *);
 void *radix_tree_lookup(struct radix_tree_root *, unsigned long);
 void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long);
+void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *);
 void *radix_tree_delete(struct radix_tree_root *, unsigned long);
 unsigned int
 radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index bd4a8dfdf0b8..d832117e7d94 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -1337,15 +1337,18 @@ static inline void radix_tree_shrink(struct radix_tree_root *root)
 }
 
 /**
- *	radix_tree_delete    -    delete an item from a radix tree
+ *	radix_tree_delete_item    -    delete an item from a radix tree
  *	@root:		radix tree root
  *	@index:		index key
+ *	@item:		expected item
  *
- *	Remove the item at @index from the radix tree rooted at @root.
+ *	Remove @item at @index from the radix tree rooted at @root.
  *
- *	Returns the address of the deleted item, or NULL if it was not present.
+ *	Returns the address of the deleted item, or NULL if it was not present
+ *	or the entry at the given @index was not @item.
  */
-void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
+void *radix_tree_delete_item(struct radix_tree_root *root,
+			     unsigned long index, void *item)
 {
 	struct radix_tree_node *node = NULL;
 	struct radix_tree_node *slot = NULL;
@@ -1380,6 +1383,11 @@ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
 	if (slot == NULL)
 		goto out;
 
+	if (item && slot != item) {
+		slot = NULL;
+		goto out;
+	}
+
 	/*
 	 * Clear all tags associated with the item to be deleted.
 	 * This way of doing it would be inefficient, but seldom is any set.
@@ -1424,6 +1432,21 @@ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
 out:
 	return slot;
 }
+EXPORT_SYMBOL(radix_tree_delete_item);
+
+/**
+ *	radix_tree_delete    -    delete an item from a radix tree
+ *	@root:		radix tree root
+ *	@index:		index key
+ *
+ *	Remove the item at @index from the radix tree rooted at @root.
+ *
+ *	Returns the address of the deleted item, or NULL if it was not present.
+ */
+void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
+{
+	return radix_tree_delete_item(root, index, NULL);
+}
 EXPORT_SYMBOL(radix_tree_delete);
 
 /**
-- 
cgit v1.2.3


From e7b563bb2a6f4d974208da46200784b9c5b5a47e Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Thu, 3 Apr 2014 14:47:44 -0700
Subject: mm: filemap: move radix tree hole searching here

The radix tree hole searching code is only used for page cache, for
example the readahead code trying to get a a picture of the area
surrounding a fault.

It sufficed to rely on the radix tree definition of holes, which is
"empty tree slot".  But this is about to change, though, as shadow page
descriptors will be stored in the page cache after the actual pages get
evicted from memory.

Move the functions over to mm/filemap.c and make them native page cache
operations, where they can later be adapted to handle the new definition
of "page cache hole".

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/nfs/blocklayout/blocklayout.c |  2 +-
 include/linux/pagemap.h          |  5 +++
 include/linux/radix-tree.h       |  4 ---
 lib/radix-tree.c                 | 75 ---------------------------------------
 mm/filemap.c                     | 76 ++++++++++++++++++++++++++++++++++++++++
 mm/readahead.c                   |  4 +--
 6 files changed, 84 insertions(+), 82 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 56ff823ca82e..65d849bdf77a 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -1213,7 +1213,7 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx)
 	end = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE);
 	if (end != NFS_I(inode)->npages) {
 		rcu_read_lock();
-		end = radix_tree_next_hole(&mapping->page_tree, idx + 1, ULONG_MAX);
+		end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX);
 		rcu_read_unlock();
 	}
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 1710d1b060ba..52d56872fe26 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -243,6 +243,11 @@ static inline struct page *page_cache_alloc_readahead(struct address_space *x)
 
 typedef int filler_t(void *, struct page *);
 
+pgoff_t page_cache_next_hole(struct address_space *mapping,
+			     pgoff_t index, unsigned long max_scan);
+pgoff_t page_cache_prev_hole(struct address_space *mapping,
+			     pgoff_t index, unsigned long max_scan);
+
 extern struct page * find_get_page(struct address_space *mapping,
 				pgoff_t index);
 extern struct page * find_lock_page(struct address_space *mapping,
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 1bf0a9c388d9..e8be53ecfc45 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -227,10 +227,6 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
 unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root,
 			void ***results, unsigned long *indices,
 			unsigned long first_index, unsigned int max_items);
-unsigned long radix_tree_next_hole(struct radix_tree_root *root,
-				unsigned long index, unsigned long max_scan);
-unsigned long radix_tree_prev_hole(struct radix_tree_root *root,
-				unsigned long index, unsigned long max_scan);
 int radix_tree_preload(gfp_t gfp_mask);
 int radix_tree_maybe_preload(gfp_t gfp_mask);
 void radix_tree_init(void);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index d832117e7d94..7e30d2a7f346 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -946,81 +946,6 @@ next:
 }
 EXPORT_SYMBOL(radix_tree_range_tag_if_tagged);
 
-
-/**
- *	radix_tree_next_hole    -    find the next hole (not-present entry)
- *	@root:		tree root
- *	@index:		index key
- *	@max_scan:	maximum range to search
- *
- *	Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the lowest
- *	indexed hole.
- *
- *	Returns: the index of the hole if found, otherwise returns an index
- *	outside of the set specified (in which case 'return - index >= max_scan'
- *	will be true). In rare cases of index wrap-around, 0 will be returned.
- *
- *	radix_tree_next_hole may be called under rcu_read_lock. However, like
- *	radix_tree_gang_lookup, this will not atomically search a snapshot of
- *	the tree at a single point in time. For example, if a hole is created
- *	at index 5, then subsequently a hole is created at index 10,
- *	radix_tree_next_hole covering both indexes may return 10 if called
- *	under rcu_read_lock.
- */
-unsigned long radix_tree_next_hole(struct radix_tree_root *root,
-				unsigned long index, unsigned long max_scan)
-{
-	unsigned long i;
-
-	for (i = 0; i < max_scan; i++) {
-		if (!radix_tree_lookup(root, index))
-			break;
-		index++;
-		if (index == 0)
-			break;
-	}
-
-	return index;
-}
-EXPORT_SYMBOL(radix_tree_next_hole);
-
-/**
- *	radix_tree_prev_hole    -    find the prev hole (not-present entry)
- *	@root:		tree root
- *	@index:		index key
- *	@max_scan:	maximum range to search
- *
- *	Search backwards in the range [max(index-max_scan+1, 0), index]
- *	for the first hole.
- *
- *	Returns: the index of the hole if found, otherwise returns an index
- *	outside of the set specified (in which case 'index - return >= max_scan'
- *	will be true). In rare cases of wrap-around, ULONG_MAX will be returned.
- *
- *	radix_tree_next_hole may be called under rcu_read_lock. However, like
- *	radix_tree_gang_lookup, this will not atomically search a snapshot of
- *	the tree at a single point in time. For example, if a hole is created
- *	at index 10, then subsequently a hole is created at index 5,
- *	radix_tree_prev_hole covering both indexes may return 5 if called under
- *	rcu_read_lock.
- */
-unsigned long radix_tree_prev_hole(struct radix_tree_root *root,
-				   unsigned long index, unsigned long max_scan)
-{
-	unsigned long i;
-
-	for (i = 0; i < max_scan; i++) {
-		if (!radix_tree_lookup(root, index))
-			break;
-		index--;
-		if (index == ULONG_MAX)
-			break;
-	}
-
-	return index;
-}
-EXPORT_SYMBOL(radix_tree_prev_hole);
-
 /**
  *	radix_tree_gang_lookup - perform multiple lookup on a radix tree
  *	@root:		radix tree root
diff --git a/mm/filemap.c b/mm/filemap.c
index 068cd2a63d32..40115c6c0791 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -685,6 +685,82 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
 	}
 }
 
+/**
+ * page_cache_next_hole - find the next hole (not-present entry)
+ * @mapping: mapping
+ * @index: index
+ * @max_scan: maximum range to search
+ *
+ * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the
+ * lowest indexed hole.
+ *
+ * Returns: the index of the hole if found, otherwise returns an index
+ * outside of the set specified (in which case 'return - index >=
+ * max_scan' will be true). In rare cases of index wrap-around, 0 will
+ * be returned.
+ *
+ * page_cache_next_hole may be called under rcu_read_lock. However,
+ * like radix_tree_gang_lookup, this will not atomically search a
+ * snapshot of the tree at a single point in time. For example, if a
+ * hole is created at index 5, then subsequently a hole is created at
+ * index 10, page_cache_next_hole covering both indexes may return 10
+ * if called under rcu_read_lock.
+ */
+pgoff_t page_cache_next_hole(struct address_space *mapping,
+			     pgoff_t index, unsigned long max_scan)
+{
+	unsigned long i;
+
+	for (i = 0; i < max_scan; i++) {
+		if (!radix_tree_lookup(&mapping->page_tree, index))
+			break;
+		index++;
+		if (index == 0)
+			break;
+	}
+
+	return index;
+}
+EXPORT_SYMBOL(page_cache_next_hole);
+
+/**
+ * page_cache_prev_hole - find the prev hole (not-present entry)
+ * @mapping: mapping
+ * @index: index
+ * @max_scan: maximum range to search
+ *
+ * Search backwards in the range [max(index-max_scan+1, 0), index] for
+ * the first hole.
+ *
+ * Returns: the index of the hole if found, otherwise returns an index
+ * outside of the set specified (in which case 'index - return >=
+ * max_scan' will be true). In rare cases of wrap-around, ULONG_MAX
+ * will be returned.
+ *
+ * page_cache_prev_hole may be called under rcu_read_lock. However,
+ * like radix_tree_gang_lookup, this will not atomically search a
+ * snapshot of the tree at a single point in time. For example, if a
+ * hole is created at index 10, then subsequently a hole is created at
+ * index 5, page_cache_prev_hole covering both indexes may return 5 if
+ * called under rcu_read_lock.
+ */
+pgoff_t page_cache_prev_hole(struct address_space *mapping,
+			     pgoff_t index, unsigned long max_scan)
+{
+	unsigned long i;
+
+	for (i = 0; i < max_scan; i++) {
+		if (!radix_tree_lookup(&mapping->page_tree, index))
+			break;
+		index--;
+		if (index == ULONG_MAX)
+			break;
+	}
+
+	return index;
+}
+EXPORT_SYMBOL(page_cache_prev_hole);
+
 /**
  * find_get_page - find and get a page reference
  * @mapping: the address_space to search
diff --git a/mm/readahead.c b/mm/readahead.c
index 0de2360d65f3..c62d85ace0cc 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -347,7 +347,7 @@ static pgoff_t count_history_pages(struct address_space *mapping,
 	pgoff_t head;
 
 	rcu_read_lock();
-	head = radix_tree_prev_hole(&mapping->page_tree, offset - 1, max);
+	head = page_cache_prev_hole(mapping, offset - 1, max);
 	rcu_read_unlock();
 
 	return offset - 1 - head;
@@ -427,7 +427,7 @@ ondemand_readahead(struct address_space *mapping,
 		pgoff_t start;
 
 		rcu_read_lock();
-		start = radix_tree_next_hole(&mapping->page_tree, offset+1,max);
+		start = page_cache_next_hole(mapping, offset + 1, max);
 		rcu_read_unlock();
 
 		if (!start || start - offset > max)
-- 
cgit v1.2.3


From 0cd6144aadd2afd19d1aca880153530c52957604 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Thu, 3 Apr 2014 14:47:46 -0700
Subject: mm + fs: prepare for non-page entries in page cache radix trees

shmem mappings already contain exceptional entries where swap slot
information is remembered.

To be able to store eviction information for regular page cache, prepare
every site dealing with the radix trees directly to handle entries other
than pages.

The common lookup functions will filter out non-page entries and return
NULL for page cache holes, just as before.  But provide a raw version of
the API which returns non-page entries as well, and switch shmem over to
use it.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/btrfs/compression.c   |   2 +-
 include/linux/mm.h       |   8 ++
 include/linux/pagemap.h  |  15 ++--
 include/linux/pagevec.h  |   5 ++
 include/linux/shmem_fs.h |   1 +
 mm/filemap.c             | 202 +++++++++++++++++++++++++++++++++++++++++------
 mm/mincore.c             |  20 +++--
 mm/readahead.c           |   2 +-
 mm/shmem.c               |  99 +++++------------------
 mm/swap.c                |  51 ++++++++++++
 mm/truncate.c            |  74 ++++++++++++++---
 11 files changed, 349 insertions(+), 130 deletions(-)

(limited to 'include/linux')

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index b01fb6c527e3..d43c544d3b68 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -472,7 +472,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 		rcu_read_lock();
 		page = radix_tree_lookup(&mapping->page_tree, pg_index);
 		rcu_read_unlock();
-		if (page) {
+		if (page && !radix_tree_exceptional_entry(page)) {
 			misses++;
 			if (misses > 4)
 				break;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2eec61fe75c9..b1331aff769c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1041,6 +1041,14 @@ extern void show_free_areas(unsigned int flags);
 extern bool skip_free_areas_node(unsigned int flags, int nid);
 
 int shmem_zero_setup(struct vm_area_struct *);
+#ifdef CONFIG_SHMEM
+bool shmem_mapping(struct address_space *mapping);
+#else
+static inline bool shmem_mapping(struct address_space *mapping)
+{
+	return false;
+}
+#endif
 
 extern int can_do_mlock(void);
 extern int user_shm_lock(size_t, struct user_struct *);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 52d56872fe26..493bfd85214e 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -248,12 +248,15 @@ pgoff_t page_cache_next_hole(struct address_space *mapping,
 pgoff_t page_cache_prev_hole(struct address_space *mapping,
 			     pgoff_t index, unsigned long max_scan);
 
-extern struct page * find_get_page(struct address_space *mapping,
-				pgoff_t index);
-extern struct page * find_lock_page(struct address_space *mapping,
-				pgoff_t index);
-extern struct page * find_or_create_page(struct address_space *mapping,
-				pgoff_t index, gfp_t gfp_mask);
+struct page *find_get_entry(struct address_space *mapping, pgoff_t offset);
+struct page *find_get_page(struct address_space *mapping, pgoff_t offset);
+struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset);
+struct page *find_lock_page(struct address_space *mapping, pgoff_t offset);
+struct page *find_or_create_page(struct address_space *mapping, pgoff_t index,
+				 gfp_t gfp_mask);
+unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
+			  unsigned int nr_entries, struct page **entries,
+			  pgoff_t *indices);
 unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
 			unsigned int nr_pages, struct page **pages);
 unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start,
diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h
index e4dbfab37729..b45d391b4540 100644
--- a/include/linux/pagevec.h
+++ b/include/linux/pagevec.h
@@ -22,6 +22,11 @@ struct pagevec {
 
 void __pagevec_release(struct pagevec *pvec);
 void __pagevec_lru_add(struct pagevec *pvec);
+unsigned pagevec_lookup_entries(struct pagevec *pvec,
+				struct address_space *mapping,
+				pgoff_t start, unsigned nr_entries,
+				pgoff_t *indices);
+void pagevec_remove_exceptionals(struct pagevec *pvec);
 unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping,
 		pgoff_t start, unsigned nr_pages);
 unsigned pagevec_lookup_tag(struct pagevec *pvec,
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 9d55438bc4ad..4d1771c2d29f 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -51,6 +51,7 @@ extern struct file *shmem_kernel_file_setup(const char *name, loff_t size,
 					    unsigned long flags);
 extern int shmem_zero_setup(struct vm_area_struct *);
 extern int shmem_lock(struct file *file, int lock, struct user_struct *user);
+extern bool shmem_mapping(struct address_space *mapping);
 extern void shmem_unlock_mapping(struct address_space *mapping);
 extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
 					pgoff_t index, gfp_t gfp_mask);
diff --git a/mm/filemap.c b/mm/filemap.c
index 40115c6c0791..efc63876477f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -446,6 +446,29 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 }
 EXPORT_SYMBOL_GPL(replace_page_cache_page);
 
+static int page_cache_tree_insert(struct address_space *mapping,
+				  struct page *page)
+{
+	void **slot;
+	int error;
+
+	slot = radix_tree_lookup_slot(&mapping->page_tree, page->index);
+	if (slot) {
+		void *p;
+
+		p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
+		if (!radix_tree_exceptional_entry(p))
+			return -EEXIST;
+		radix_tree_replace_slot(slot, page);
+		mapping->nrpages++;
+		return 0;
+	}
+	error = radix_tree_insert(&mapping->page_tree, page->index, page);
+	if (!error)
+		mapping->nrpages++;
+	return error;
+}
+
 /**
  * add_to_page_cache_locked - add a locked page to the pagecache
  * @page:	page to add
@@ -480,11 +503,10 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
 	page->index = offset;
 
 	spin_lock_irq(&mapping->tree_lock);
-	error = radix_tree_insert(&mapping->page_tree, offset, page);
+	error = page_cache_tree_insert(mapping, page);
 	radix_tree_preload_end();
 	if (unlikely(error))
 		goto err_insert;
-	mapping->nrpages++;
 	__inc_zone_page_state(page, NR_FILE_PAGES);
 	spin_unlock_irq(&mapping->tree_lock);
 	trace_mm_filemap_add_to_page_cache(page);
@@ -712,7 +734,10 @@ pgoff_t page_cache_next_hole(struct address_space *mapping,
 	unsigned long i;
 
 	for (i = 0; i < max_scan; i++) {
-		if (!radix_tree_lookup(&mapping->page_tree, index))
+		struct page *page;
+
+		page = radix_tree_lookup(&mapping->page_tree, index);
+		if (!page || radix_tree_exceptional_entry(page))
 			break;
 		index++;
 		if (index == 0)
@@ -750,7 +775,10 @@ pgoff_t page_cache_prev_hole(struct address_space *mapping,
 	unsigned long i;
 
 	for (i = 0; i < max_scan; i++) {
-		if (!radix_tree_lookup(&mapping->page_tree, index))
+		struct page *page;
+
+		page = radix_tree_lookup(&mapping->page_tree, index);
+		if (!page || radix_tree_exceptional_entry(page))
 			break;
 		index--;
 		if (index == ULONG_MAX)
@@ -762,14 +790,19 @@ pgoff_t page_cache_prev_hole(struct address_space *mapping,
 EXPORT_SYMBOL(page_cache_prev_hole);
 
 /**
- * find_get_page - find and get a page reference
+ * find_get_entry - find and get a page cache entry
  * @mapping: the address_space to search
- * @offset: the page index
+ * @offset: the page cache index
+ *
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned with an increased refcount.
  *
- * Is there a pagecache struct page at the given (mapping, offset) tuple?
- * If yes, increment its refcount and return it; if no, return NULL.
+ * If the slot holds a shadow entry of a previously evicted page, it
+ * is returned.
+ *
+ * Otherwise, %NULL is returned.
  */
-struct page *find_get_page(struct address_space *mapping, pgoff_t offset)
+struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
 {
 	void **pagep;
 	struct page *page;
@@ -810,24 +843,50 @@ out:
 
 	return page;
 }
-EXPORT_SYMBOL(find_get_page);
+EXPORT_SYMBOL(find_get_entry);
 
 /**
- * find_lock_page - locate, pin and lock a pagecache page
+ * find_get_page - find and get a page reference
  * @mapping: the address_space to search
  * @offset: the page index
  *
- * Locates the desired pagecache page, locks it, increments its reference
- * count and returns its address.
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned with an increased refcount.
  *
- * Returns zero if the page was not present. find_lock_page() may sleep.
+ * Otherwise, %NULL is returned.
  */
-struct page *find_lock_page(struct address_space *mapping, pgoff_t offset)
+struct page *find_get_page(struct address_space *mapping, pgoff_t offset)
+{
+	struct page *page = find_get_entry(mapping, offset);
+
+	if (radix_tree_exceptional_entry(page))
+		page = NULL;
+	return page;
+}
+EXPORT_SYMBOL(find_get_page);
+
+/**
+ * find_lock_entry - locate, pin and lock a page cache entry
+ * @mapping: the address_space to search
+ * @offset: the page cache index
+ *
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned locked and with an increased
+ * refcount.
+ *
+ * If the slot holds a shadow entry of a previously evicted page, it
+ * is returned.
+ *
+ * Otherwise, %NULL is returned.
+ *
+ * find_lock_entry() may sleep.
+ */
+struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset)
 {
 	struct page *page;
 
 repeat:
-	page = find_get_page(mapping, offset);
+	page = find_get_entry(mapping, offset);
 	if (page && !radix_tree_exception(page)) {
 		lock_page(page);
 		/* Has the page been truncated? */
@@ -840,6 +899,29 @@ repeat:
 	}
 	return page;
 }
+EXPORT_SYMBOL(find_lock_entry);
+
+/**
+ * find_lock_page - locate, pin and lock a pagecache page
+ * @mapping: the address_space to search
+ * @offset: the page index
+ *
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned locked and with an increased
+ * refcount.
+ *
+ * Otherwise, %NULL is returned.
+ *
+ * find_lock_page() may sleep.
+ */
+struct page *find_lock_page(struct address_space *mapping, pgoff_t offset)
+{
+	struct page *page = find_lock_entry(mapping, offset);
+
+	if (radix_tree_exceptional_entry(page))
+		page = NULL;
+	return page;
+}
 EXPORT_SYMBOL(find_lock_page);
 
 /**
@@ -848,16 +930,18 @@ EXPORT_SYMBOL(find_lock_page);
  * @index: the page's index into the mapping
  * @gfp_mask: page allocation mode
  *
- * Locates a page in the pagecache.  If the page is not present, a new page
- * is allocated using @gfp_mask and is added to the pagecache and to the VM's
- * LRU list.  The returned page is locked and has its reference count
- * incremented.
+ * Looks up the page cache slot at @mapping & @offset.  If there is a
+ * page cache page, it is returned locked and with an increased
+ * refcount.
+ *
+ * If the page is not present, a new page is allocated using @gfp_mask
+ * and added to the page cache and the VM's LRU list.  The page is
+ * returned locked and with an increased refcount.
  *
- * find_or_create_page() may sleep, even if @gfp_flags specifies an atomic
- * allocation!
+ * On memory exhaustion, %NULL is returned.
  *
- * find_or_create_page() returns the desired page's address, or zero on
- * memory exhaustion.
+ * find_or_create_page() may sleep, even if @gfp_flags specifies an
+ * atomic allocation!
  */
 struct page *find_or_create_page(struct address_space *mapping,
 		pgoff_t index, gfp_t gfp_mask)
@@ -889,6 +973,76 @@ repeat:
 }
 EXPORT_SYMBOL(find_or_create_page);
 
+/**
+ * find_get_entries - gang pagecache lookup
+ * @mapping:	The address_space to search
+ * @start:	The starting page cache index
+ * @nr_entries:	The maximum number of entries
+ * @entries:	Where the resulting entries are placed
+ * @indices:	The cache indices corresponding to the entries in @entries
+ *
+ * find_get_entries() will search for and return a group of up to
+ * @nr_entries entries in the mapping.  The entries are placed at
+ * @entries.  find_get_entries() takes a reference against any actual
+ * pages it returns.
+ *
+ * The search returns a group of mapping-contiguous page cache entries
+ * with ascending indexes.  There may be holes in the indices due to
+ * not-present pages.
+ *
+ * Any shadow entries of evicted pages are included in the returned
+ * array.
+ *
+ * find_get_entries() returns the number of pages and shadow entries
+ * which were found.
+ */
+unsigned find_get_entries(struct address_space *mapping,
+			  pgoff_t start, unsigned int nr_entries,
+			  struct page **entries, pgoff_t *indices)
+{
+	void **slot;
+	unsigned int ret = 0;
+	struct radix_tree_iter iter;
+
+	if (!nr_entries)
+		return 0;
+
+	rcu_read_lock();
+restart:
+	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
+		struct page *page;
+repeat:
+		page = radix_tree_deref_slot(slot);
+		if (unlikely(!page))
+			continue;
+		if (radix_tree_exception(page)) {
+			if (radix_tree_deref_retry(page))
+				goto restart;
+			/*
+			 * Otherwise, we must be storing a swap entry
+			 * here as an exceptional entry: so return it
+			 * without attempting to raise page count.
+			 */
+			goto export;
+		}
+		if (!page_cache_get_speculative(page))
+			goto repeat;
+
+		/* Has the page moved? */
+		if (unlikely(page != *slot)) {
+			page_cache_release(page);
+			goto repeat;
+		}
+export:
+		indices[ret] = iter.index;
+		entries[ret] = page;
+		if (++ret == nr_entries)
+			break;
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
 /**
  * find_get_pages - gang pagecache lookup
  * @mapping:	The address_space to search
diff --git a/mm/mincore.c b/mm/mincore.c
index 101623378fbf..725c80961048 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -70,13 +70,21 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
 	 * any other file mapping (ie. marked !present and faulted in with
 	 * tmpfs's .fault). So swapped out tmpfs mappings are tested here.
 	 */
-	page = find_get_page(mapping, pgoff);
 #ifdef CONFIG_SWAP
-	/* shmem/tmpfs may return swap: account for swapcache page too. */
-	if (radix_tree_exceptional_entry(page)) {
-		swp_entry_t swap = radix_to_swp_entry(page);
-		page = find_get_page(swap_address_space(swap), swap.val);
-	}
+	if (shmem_mapping(mapping)) {
+		page = find_get_entry(mapping, pgoff);
+		/*
+		 * shmem/tmpfs may return swap: account for swapcache
+		 * page too.
+		 */
+		if (radix_tree_exceptional_entry(page)) {
+			swp_entry_t swp = radix_to_swp_entry(page);
+			page = find_get_page(swap_address_space(swp), swp.val);
+		}
+	} else
+		page = find_get_page(mapping, pgoff);
+#else
+	page = find_get_page(mapping, pgoff);
 #endif
 	if (page) {
 		present = PageUptodate(page);
diff --git a/mm/readahead.c b/mm/readahead.c
index c62d85ace0cc..62c500a088a7 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -179,7 +179,7 @@ __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
 		rcu_read_lock();
 		page = radix_tree_lookup(&mapping->page_tree, page_offset);
 		rcu_read_unlock();
-		if (page)
+		if (page && !radix_tree_exceptional_entry(page))
 			continue;
 
 		page = page_cache_alloc_readahead(mapping);
diff --git a/mm/shmem.c b/mm/shmem.c
index e470997010cd..a3ba988ec946 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -328,56 +328,6 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap)
 	BUG_ON(error);
 }
 
-/*
- * Like find_get_pages, but collecting swap entries as well as pages.
- */
-static unsigned shmem_find_get_pages_and_swap(struct address_space *mapping,
-					pgoff_t start, unsigned int nr_pages,
-					struct page **pages, pgoff_t *indices)
-{
-	void **slot;
-	unsigned int ret = 0;
-	struct radix_tree_iter iter;
-
-	if (!nr_pages)
-		return 0;
-
-	rcu_read_lock();
-restart:
-	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
-		struct page *page;
-repeat:
-		page = radix_tree_deref_slot(slot);
-		if (unlikely(!page))
-			continue;
-		if (radix_tree_exception(page)) {
-			if (radix_tree_deref_retry(page))
-				goto restart;
-			/*
-			 * Otherwise, we must be storing a swap entry
-			 * here as an exceptional entry: so return it
-			 * without attempting to raise page count.
-			 */
-			goto export;
-		}
-		if (!page_cache_get_speculative(page))
-			goto repeat;
-
-		/* Has the page moved? */
-		if (unlikely(page != *slot)) {
-			page_cache_release(page);
-			goto repeat;
-		}
-export:
-		indices[ret] = iter.index;
-		pages[ret] = page;
-		if (++ret == nr_pages)
-			break;
-	}
-	rcu_read_unlock();
-	return ret;
-}
-
 /*
  * Remove swap entry from radix tree, free the swap and its page cache.
  */
@@ -395,21 +345,6 @@ static int shmem_free_swap(struct address_space *mapping,
 	return 0;
 }
 
-/*
- * Pagevec may contain swap entries, so shuffle up pages before releasing.
- */
-static void shmem_deswap_pagevec(struct pagevec *pvec)
-{
-	int i, j;
-
-	for (i = 0, j = 0; i < pagevec_count(pvec); i++) {
-		struct page *page = pvec->pages[i];
-		if (!radix_tree_exceptional_entry(page))
-			pvec->pages[j++] = page;
-	}
-	pvec->nr = j;
-}
-
 /*
  * SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists.
  */
@@ -428,12 +363,12 @@ void shmem_unlock_mapping(struct address_space *mapping)
 		 * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it
 		 * has finished, if it hits a row of PAGEVEC_SIZE swap entries.
 		 */
-		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
-					PAGEVEC_SIZE, pvec.pages, indices);
+		pvec.nr = find_get_entries(mapping, index,
+					   PAGEVEC_SIZE, pvec.pages, indices);
 		if (!pvec.nr)
 			break;
 		index = indices[pvec.nr - 1] + 1;
-		shmem_deswap_pagevec(&pvec);
+		pagevec_remove_exceptionals(&pvec);
 		check_move_unevictable_pages(pvec.pages, pvec.nr);
 		pagevec_release(&pvec);
 		cond_resched();
@@ -465,9 +400,9 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 	pagevec_init(&pvec, 0);
 	index = start;
 	while (index < end) {
-		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
-				min(end - index, (pgoff_t)PAGEVEC_SIZE),
-							pvec.pages, indices);
+		pvec.nr = find_get_entries(mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE),
+			pvec.pages, indices);
 		if (!pvec.nr)
 			break;
 		mem_cgroup_uncharge_start();
@@ -496,7 +431,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			}
 			unlock_page(page);
 		}
-		shmem_deswap_pagevec(&pvec);
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		cond_resched();
@@ -534,9 +469,10 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 	index = start;
 	for ( ; ; ) {
 		cond_resched();
-		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
+
+		pvec.nr = find_get_entries(mapping, index,
 				min(end - index, (pgoff_t)PAGEVEC_SIZE),
-							pvec.pages, indices);
+				pvec.pages, indices);
 		if (!pvec.nr) {
 			if (index == start || unfalloc)
 				break;
@@ -544,7 +480,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			continue;
 		}
 		if ((index == start || unfalloc) && indices[0] >= end) {
-			shmem_deswap_pagevec(&pvec);
+			pagevec_remove_exceptionals(&pvec);
 			pagevec_release(&pvec);
 			break;
 		}
@@ -573,7 +509,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			}
 			unlock_page(page);
 		}
-		shmem_deswap_pagevec(&pvec);
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		index++;
@@ -1079,7 +1015,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 		return -EFBIG;
 repeat:
 	swap.val = 0;
-	page = find_lock_page(mapping, index);
+	page = find_lock_entry(mapping, index);
 	if (radix_tree_exceptional_entry(page)) {
 		swap = radix_to_swp_entry(page);
 		page = NULL;
@@ -1416,6 +1352,11 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 	return inode;
 }
 
+bool shmem_mapping(struct address_space *mapping)
+{
+	return mapping->backing_dev_info == &shmem_backing_dev_info;
+}
+
 #ifdef CONFIG_TMPFS
 static const struct inode_operations shmem_symlink_inode_operations;
 static const struct inode_operations shmem_short_symlink_operations;
@@ -1728,7 +1669,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
 	pagevec_init(&pvec, 0);
 	pvec.nr = 1;		/* start small: we may be there already */
 	while (!done) {
-		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
+		pvec.nr = find_get_entries(mapping, index,
 					pvec.nr, pvec.pages, indices);
 		if (!pvec.nr) {
 			if (whence == SEEK_DATA)
@@ -1755,7 +1696,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
 				break;
 			}
 		}
-		shmem_deswap_pagevec(&pvec);
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		pvec.nr = PAGEVEC_SIZE;
 		cond_resched();
diff --git a/mm/swap.c b/mm/swap.c
index 0092097b3f4c..c8048d71c642 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -947,6 +947,57 @@ void __pagevec_lru_add(struct pagevec *pvec)
 }
 EXPORT_SYMBOL(__pagevec_lru_add);
 
+/**
+ * pagevec_lookup_entries - gang pagecache lookup
+ * @pvec:	Where the resulting entries are placed
+ * @mapping:	The address_space to search
+ * @start:	The starting entry index
+ * @nr_entries:	The maximum number of entries
+ * @indices:	The cache indices corresponding to the entries in @pvec
+ *
+ * pagevec_lookup_entries() will search for and return a group of up
+ * to @nr_entries pages and shadow entries in the mapping.  All
+ * entries are placed in @pvec.  pagevec_lookup_entries() takes a
+ * reference against actual pages in @pvec.
+ *
+ * The search returns a group of mapping-contiguous entries with
+ * ascending indexes.  There may be holes in the indices due to
+ * not-present entries.
+ *
+ * pagevec_lookup_entries() returns the number of entries which were
+ * found.
+ */
+unsigned pagevec_lookup_entries(struct pagevec *pvec,
+				struct address_space *mapping,
+				pgoff_t start, unsigned nr_pages,
+				pgoff_t *indices)
+{
+	pvec->nr = find_get_entries(mapping, start, nr_pages,
+				    pvec->pages, indices);
+	return pagevec_count(pvec);
+}
+
+/**
+ * pagevec_remove_exceptionals - pagevec exceptionals pruning
+ * @pvec:	The pagevec to prune
+ *
+ * pagevec_lookup_entries() fills both pages and exceptional radix
+ * tree entries into the pagevec.  This function prunes all
+ * exceptionals from @pvec without leaving holes, so that it can be
+ * passed on to page-only pagevec operations.
+ */
+void pagevec_remove_exceptionals(struct pagevec *pvec)
+{
+	int i, j;
+
+	for (i = 0, j = 0; i < pagevec_count(pvec); i++) {
+		struct page *page = pvec->pages[i];
+		if (!radix_tree_exceptional_entry(page))
+			pvec->pages[j++] = page;
+	}
+	pvec->nr = j;
+}
+
 /**
  * pagevec_lookup - gang pagecache lookup
  * @pvec:	Where the resulting pages are placed
diff --git a/mm/truncate.c b/mm/truncate.c
index 353b683afd6e..2e84fe59190b 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -22,6 +22,22 @@
 #include <linux/cleancache.h>
 #include "internal.h"
 
+static void clear_exceptional_entry(struct address_space *mapping,
+				    pgoff_t index, void *entry)
+{
+	/* Handled by shmem itself */
+	if (shmem_mapping(mapping))
+		return;
+
+	spin_lock_irq(&mapping->tree_lock);
+	/*
+	 * Regular page slots are stabilized by the page lock even
+	 * without the tree itself locked.  These unlocked entries
+	 * need verification under the tree lock.
+	 */
+	radix_tree_delete_item(&mapping->page_tree, index, entry);
+	spin_unlock_irq(&mapping->tree_lock);
+}
 
 /**
  * do_invalidatepage - invalidate part or all of a page
@@ -208,6 +224,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 	unsigned int	partial_start;	/* inclusive */
 	unsigned int	partial_end;	/* exclusive */
 	struct pagevec	pvec;
+	pgoff_t		indices[PAGEVEC_SIZE];
 	pgoff_t		index;
 	int		i;
 
@@ -238,17 +255,23 @@ void truncate_inode_pages_range(struct address_space *mapping,
 
 	pagevec_init(&pvec, 0);
 	index = start;
-	while (index < end && pagevec_lookup(&pvec, mapping, index,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE))) {
+	while (index < end && pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE),
+			indices)) {
 		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
 			/* We rely upon deletion not changing page->index */
-			index = page->index;
+			index = indices[i];
 			if (index >= end)
 				break;
 
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
 			if (!trylock_page(page))
 				continue;
 			WARN_ON(page->index != index);
@@ -259,6 +282,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 			truncate_inode_page(mapping, page);
 			unlock_page(page);
 		}
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		cond_resched();
@@ -307,14 +331,16 @@ void truncate_inode_pages_range(struct address_space *mapping,
 	index = start;
 	for ( ; ; ) {
 		cond_resched();
-		if (!pagevec_lookup(&pvec, mapping, index,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE))) {
+		if (!pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE),
+			indices)) {
 			if (index == start)
 				break;
 			index = start;
 			continue;
 		}
-		if (index == start && pvec.pages[0]->index >= end) {
+		if (index == start && indices[0] >= end) {
+			pagevec_remove_exceptionals(&pvec);
 			pagevec_release(&pvec);
 			break;
 		}
@@ -323,16 +349,22 @@ void truncate_inode_pages_range(struct address_space *mapping,
 			struct page *page = pvec.pages[i];
 
 			/* We rely upon deletion not changing page->index */
-			index = page->index;
+			index = indices[i];
 			if (index >= end)
 				break;
 
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
 			lock_page(page);
 			WARN_ON(page->index != index);
 			wait_on_page_writeback(page);
 			truncate_inode_page(mapping, page);
 			unlock_page(page);
 		}
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		index++;
@@ -375,6 +407,7 @@ EXPORT_SYMBOL(truncate_inode_pages);
 unsigned long invalidate_mapping_pages(struct address_space *mapping,
 		pgoff_t start, pgoff_t end)
 {
+	pgoff_t indices[PAGEVEC_SIZE];
 	struct pagevec pvec;
 	pgoff_t index = start;
 	unsigned long ret;
@@ -390,17 +423,23 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 	 */
 
 	pagevec_init(&pvec, 0);
-	while (index <= end && pagevec_lookup(&pvec, mapping, index,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
+	while (index <= end && pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
+			indices)) {
 		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
 			/* We rely upon deletion not changing page->index */
-			index = page->index;
+			index = indices[i];
 			if (index > end)
 				break;
 
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
 			if (!trylock_page(page))
 				continue;
 			WARN_ON(page->index != index);
@@ -414,6 +453,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 				deactivate_page(page);
 			count += ret;
 		}
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		cond_resched();
@@ -481,6 +521,7 @@ static int do_launder_page(struct address_space *mapping, struct page *page)
 int invalidate_inode_pages2_range(struct address_space *mapping,
 				  pgoff_t start, pgoff_t end)
 {
+	pgoff_t indices[PAGEVEC_SIZE];
 	struct pagevec pvec;
 	pgoff_t index;
 	int i;
@@ -491,17 +532,23 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 	cleancache_invalidate_inode(mapping);
 	pagevec_init(&pvec, 0);
 	index = start;
-	while (index <= end && pagevec_lookup(&pvec, mapping, index,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
+	while (index <= end && pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
+			indices)) {
 		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
 			/* We rely upon deletion not changing page->index */
-			index = page->index;
+			index = indices[i];
 			if (index > end)
 				break;
 
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
 			lock_page(page);
 			WARN_ON(page->index != index);
 			if (page->mapping != mapping) {
@@ -539,6 +586,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 				ret = ret2;
 			unlock_page(page);
 		}
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		cond_resched();
-- 
cgit v1.2.3


From 91b0abe36a7b2b3b02d7500925a5f8455334f0e5 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Thu, 3 Apr 2014 14:47:49 -0700
Subject: mm + fs: store shadow entries in page cache

Reclaim will be leaving shadow entries in the page cache radix tree upon
evicting the real page.  As those pages are found from the LRU, an
iput() can lead to the inode being freed concurrently.  At this point,
reclaim must no longer install shadow pages because the inode freeing
code needs to ensure the page tree is really empty.

Add an address_space flag, AS_EXITING, that the inode freeing code sets
under the tree lock before doing the final truncate.  Reclaim will check
for this flag before installing shadow pages.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/filesystems/porting               |  6 +--
 drivers/staging/lustre/lustre/llite/llite_lib.c |  2 +-
 fs/9p/vfs_inode.c                               |  2 +-
 fs/affs/inode.c                                 |  2 +-
 fs/afs/inode.c                                  |  2 +-
 fs/bfs/inode.c                                  |  2 +-
 fs/block_dev.c                                  |  4 +-
 fs/btrfs/inode.c                                |  2 +-
 fs/cifs/cifsfs.c                                |  2 +-
 fs/coda/inode.c                                 |  2 +-
 fs/ecryptfs/super.c                             |  2 +-
 fs/exofs/inode.c                                |  2 +-
 fs/ext2/inode.c                                 |  2 +-
 fs/ext3/inode.c                                 |  2 +-
 fs/ext4/inode.c                                 |  4 +-
 fs/f2fs/inode.c                                 |  2 +-
 fs/fat/inode.c                                  |  2 +-
 fs/freevxfs/vxfs_inode.c                        |  2 +-
 fs/fuse/inode.c                                 |  2 +-
 fs/gfs2/super.c                                 |  2 +-
 fs/hfs/inode.c                                  |  2 +-
 fs/hfsplus/super.c                              |  2 +-
 fs/hostfs/hostfs_kern.c                         |  2 +-
 fs/hpfs/inode.c                                 |  2 +-
 fs/inode.c                                      |  4 +-
 fs/jffs2/fs.c                                   |  2 +-
 fs/jfs/inode.c                                  |  4 +-
 fs/kernfs/inode.c                               |  2 +-
 fs/logfs/readwrite.c                            |  2 +-
 fs/minix/inode.c                                |  2 +-
 fs/ncpfs/inode.c                                |  2 +-
 fs/nfs/inode.c                                  |  2 +-
 fs/nfs/nfs4super.c                              |  2 +-
 fs/nilfs2/inode.c                               |  6 +--
 fs/ntfs/inode.c                                 |  2 +-
 fs/ocfs2/inode.c                                |  4 +-
 fs/omfs/inode.c                                 |  2 +-
 fs/proc/inode.c                                 |  2 +-
 fs/reiserfs/inode.c                             |  2 +-
 fs/sysv/inode.c                                 |  2 +-
 fs/ubifs/super.c                                |  2 +-
 fs/udf/inode.c                                  |  4 +-
 fs/ufs/inode.c                                  |  2 +-
 fs/xfs/xfs_super.c                              |  2 +-
 include/linux/fs.h                              |  1 +
 include/linux/mm.h                              |  1 +
 include/linux/pagemap.h                         | 13 +++++-
 mm/filemap.c                                    | 33 ++++++++++++---
 mm/truncate.c                                   | 54 +++++++++++++++++++++++--
 mm/vmscan.c                                     |  2 +-
 50 files changed, 147 insertions(+), 65 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index fe2b7ae6f962..0f3a1390bf00 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -295,9 +295,9 @@ in the beginning of ->setattr unconditionally.
 	->clear_inode() and ->delete_inode() are gone; ->evict_inode() should
 be used instead.  It gets called whenever the inode is evicted, whether it has
 remaining links or not.  Caller does *not* evict the pagecache or inode-associated
-metadata buffers; getting rid of those is responsibility of method, as it had
-been for ->delete_inode(). Caller makes sure async writeback cannot be running
-for the inode while (or after) ->evict_inode() is called.
+metadata buffers; the method has to use truncate_inode_pages_final() to get rid
+of those. Caller makes sure async writeback cannot be running for the inode while
+(or after) ->evict_inode() is called.
 
 	->drop_inode() returns int now; it's called on final iput() with
 inode->i_lock held and it returns true if filesystems wants the inode to be
diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c
index 26003d3c1be7..7c4fd97a7fa0 100644
--- a/drivers/staging/lustre/lustre/llite/llite_lib.c
+++ b/drivers/staging/lustre/lustre/llite/llite_lib.c
@@ -1877,7 +1877,7 @@ void ll_delete_inode(struct inode *inode)
 		cl_sync_file_range(inode, 0, OBD_OBJECT_EOF,
 				   CL_FSYNC_DISCARD, 1);
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 
 	/* Workaround for LU-118 */
 	if (inode->i_data.nrpages) {
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index bb7991c7e5c7..53161ec058a7 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -451,7 +451,7 @@ void v9fs_evict_inode(struct inode *inode)
 {
 	struct v9fs_inode *v9inode = V9FS_I(inode);
 
-	truncate_inode_pages(inode->i_mapping, 0);
+	truncate_inode_pages_final(inode->i_mapping);
 	clear_inode(inode);
 	filemap_fdatawrite(inode->i_mapping);
 
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index 0e092d08680e..96df91e8c334 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -259,7 +259,7 @@ affs_evict_inode(struct inode *inode)
 {
 	unsigned long cache_page;
 	pr_debug("AFFS: evict_inode(ino=%lu, nlink=%u)\n", inode->i_ino, inode->i_nlink);
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 
 	if (!inode->i_nlink) {
 		inode->i_size = 0;
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index ce25d755b7aa..294671288449 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -422,7 +422,7 @@ void afs_evict_inode(struct inode *inode)
 
 	ASSERTCMP(inode->i_ino, ==, vnode->fid.vnode);
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 
 	afs_give_up_callback(vnode);
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index 8defc6b3f9a2..29aa5cf6639b 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -172,7 +172,7 @@ static void bfs_evict_inode(struct inode *inode)
 
 	dprintf("ino=%08lx\n", ino);
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index e4cba21a627e..ba0d2b05bb78 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -83,7 +83,7 @@ void kill_bdev(struct block_device *bdev)
 {
 	struct address_space *mapping = bdev->bd_inode->i_mapping;
 
-	if (mapping->nrpages == 0)
+	if (mapping->nrpages == 0 && mapping->nrshadows == 0)
 		return;
 
 	invalidate_bh_lrus();
@@ -419,7 +419,7 @@ static void bdev_evict_inode(struct inode *inode)
 {
 	struct block_device *bdev = &BDEV_I(inode)->bdev;
 	struct list_head *p;
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	invalidate_inode_buffers(inode); /* is it needed here? */
 	clear_inode(inode);
 	spin_lock(&bdev_lock);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d3d44486290b..49ec1398879f 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4593,7 +4593,7 @@ static void evict_inode_truncate_pages(struct inode *inode)
 	struct rb_node *node;
 
 	ASSERT(inode->i_state & I_FREEING);
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 
 	write_lock(&map_tree->lock);
 	while (!RB_EMPTY_ROOT(&map_tree->map)) {
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index e8ae8323c058..ab8ad2546c3e 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -286,7 +286,7 @@ cifs_destroy_inode(struct inode *inode)
 static void
 cifs_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	cifs_fscache_release_inode_cookie(inode);
 }
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index 506de34a4ef3..62618ec9356c 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -250,7 +250,7 @@ static void coda_put_super(struct super_block *sb)
 
 static void coda_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	coda_cache_clear_inode(inode);
 }
diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c
index e879cf8ff0b1..afa1b81c3418 100644
--- a/fs/ecryptfs/super.c
+++ b/fs/ecryptfs/super.c
@@ -132,7 +132,7 @@ static int ecryptfs_statfs(struct dentry *dentry, struct kstatfs *buf)
  */
 static void ecryptfs_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	iput(ecryptfs_inode_to_lower(inode));
 }
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index ee4317faccb1..d1c244d67667 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -1486,7 +1486,7 @@ void exofs_evict_inode(struct inode *inode)
 	struct ore_io_state *ios;
 	int ret;
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 
 	/* TODO: should do better here */
 	if (inode->i_nlink || is_bad_inode(inode))
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 94ed36849b71..b1d2a4675d42 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -78,7 +78,7 @@ void ext2_evict_inode(struct inode * inode)
 		dquot_drop(inode);
 	}
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 
 	if (want_delete) {
 		sb_start_intwrite(inode->i_sb);
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 384b6ebb655f..efce2bbfb5e5 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -228,7 +228,7 @@ void ext3_evict_inode (struct inode *inode)
 		log_wait_commit(journal, commit_tid);
 		filemap_write_and_wait(&inode->i_data);
 	}
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 
 	ext3_discard_reservation(inode);
 	rsv = ei->i_block_alloc_info;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 24bfd7ff3049..175c3f933816 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -215,7 +215,7 @@ void ext4_evict_inode(struct inode *inode)
 			jbd2_complete_transaction(journal, commit_tid);
 			filemap_write_and_wait(&inode->i_data);
 		}
-		truncate_inode_pages(&inode->i_data, 0);
+		truncate_inode_pages_final(&inode->i_data);
 
 		WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count));
 		goto no_delete;
@@ -226,7 +226,7 @@ void ext4_evict_inode(struct inode *inode)
 
 	if (ext4_should_order_data(inode))
 		ext4_begin_ordered_truncate(inode, 0);
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 
 	WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count));
 	if (is_bad_inode(inode))
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 4d67ed736dca..28cea76d78c6 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -260,7 +260,7 @@ void f2fs_evict_inode(struct inode *inode)
 	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
 
 	trace_f2fs_evict_inode(inode);
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 
 	if (inode->i_ino == F2FS_NODE_INO(sbi) ||
 			inode->i_ino == F2FS_META_INO(sbi))
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 854b578f6695..c68d9f27135e 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -490,7 +490,7 @@ EXPORT_SYMBOL_GPL(fat_build_inode);
 
 static void fat_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	if (!inode->i_nlink) {
 		inode->i_size = 0;
 		fat_truncate_blocks(inode, 0);
diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c
index f47df72cef17..363e3ae25f6b 100644
--- a/fs/freevxfs/vxfs_inode.c
+++ b/fs/freevxfs/vxfs_inode.c
@@ -354,7 +354,7 @@ static void vxfs_i_callback(struct rcu_head *head)
 void
 vxfs_evict_inode(struct inode *ip)
 {
-	truncate_inode_pages(&ip->i_data, 0);
+	truncate_inode_pages_final(&ip->i_data);
 	clear_inode(ip);
 	call_rcu(&ip->i_rcu, vxfs_i_callback);
 }
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index d468643a68b2..9c761b611c54 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -123,7 +123,7 @@ static void fuse_destroy_inode(struct inode *inode)
 
 static void fuse_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	if (inode->i_sb->s_flags & MS_ACTIVE) {
 		struct fuse_conn *fc = get_fuse_conn(inode);
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 60f60f6181f3..24410cd9a82a 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1558,7 +1558,7 @@ out_unlock:
 		fs_warn(sdp, "gfs2_evict_inode: %d\n", error);
 out:
 	/* Case 3 starts here */
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	gfs2_rs_delete(ip, NULL);
 	gfs2_ordered_del_inode(ip);
 	clear_inode(inode);
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 380ab31b5e0f..9e2fecd62f62 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -547,7 +547,7 @@ out:
 
 void hfs_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	if (HFS_IS_RSRC(inode) && HFS_I(inode)->rsrc_inode) {
 		HFS_I(HFS_I(inode)->rsrc_inode)->rsrc_inode = NULL;
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 80875aa640ef..a6abf87d79d0 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -161,7 +161,7 @@ static int hfsplus_write_inode(struct inode *inode,
 static void hfsplus_evict_inode(struct inode *inode)
 {
 	hfs_dbg(INODE, "hfsplus_evict_inode: %lu\n", inode->i_ino);
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	if (HFSPLUS_IS_RSRC(inode)) {
 		HFSPLUS_I(HFSPLUS_I(inode)->rsrc_inode)->rsrc_inode = NULL;
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index fe649d325b1f..9c470fde9878 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -230,7 +230,7 @@ static struct inode *hostfs_alloc_inode(struct super_block *sb)
 
 static void hostfs_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	if (HOSTFS_I(inode)->fd != -1) {
 		close_file(&HOSTFS_I(inode)->fd);
diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c
index 9edeeb0ea97e..50a427313835 100644
--- a/fs/hpfs/inode.c
+++ b/fs/hpfs/inode.c
@@ -304,7 +304,7 @@ void hpfs_write_if_changed(struct inode *inode)
 
 void hpfs_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	if (!inode->i_nlink) {
 		hpfs_lock(inode->i_sb);
diff --git a/fs/inode.c b/fs/inode.c
index 4bcdad3c9361..e6905152c39f 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -503,6 +503,7 @@ void clear_inode(struct inode *inode)
 	 */
 	spin_lock_irq(&inode->i_data.tree_lock);
 	BUG_ON(inode->i_data.nrpages);
+	BUG_ON(inode->i_data.nrshadows);
 	spin_unlock_irq(&inode->i_data.tree_lock);
 	BUG_ON(!list_empty(&inode->i_data.private_list));
 	BUG_ON(!(inode->i_state & I_FREEING));
@@ -548,8 +549,7 @@ static void evict(struct inode *inode)
 	if (op->evict_inode) {
 		op->evict_inode(inode);
 	} else {
-		if (inode->i_data.nrpages)
-			truncate_inode_pages(&inode->i_data, 0);
+		truncate_inode_pages_final(&inode->i_data);
 		clear_inode(inode);
 	}
 	if (S_ISBLK(inode->i_mode) && inode->i_bdev)
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index a69e426435dd..a012e16a8bb3 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -242,7 +242,7 @@ void jffs2_evict_inode (struct inode *inode)
 
 	jffs2_dbg(1, "%s(): ino #%lu mode %o\n",
 		  __func__, inode->i_ino, inode->i_mode);
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	jffs2_do_clear_inode(c, f);
 }
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index f4aab719add5..6f8fe72c2a7a 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -154,7 +154,7 @@ void jfs_evict_inode(struct inode *inode)
 		dquot_initialize(inode);
 
 		if (JFS_IP(inode)->fileset == FILESYSTEM_I) {
-			truncate_inode_pages(&inode->i_data, 0);
+			truncate_inode_pages_final(&inode->i_data);
 
 			if (test_cflag(COMMIT_Freewmap, inode))
 				jfs_free_zero_link(inode);
@@ -168,7 +168,7 @@ void jfs_evict_inode(struct inode *inode)
 			dquot_free_inode(inode);
 		}
 	} else {
-		truncate_inode_pages(&inode->i_data, 0);
+		truncate_inode_pages_final(&inode->i_data);
 	}
 	clear_inode(inode);
 	dquot_drop(inode);
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index e55126f85bd2..abb0f1f53d93 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -355,7 +355,7 @@ void kernfs_evict_inode(struct inode *inode)
 {
 	struct kernfs_node *kn = inode->i_private;
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	kernfs_put(kn);
 }
diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c
index 9a59cbade2fb..48140315f627 100644
--- a/fs/logfs/readwrite.c
+++ b/fs/logfs/readwrite.c
@@ -2180,7 +2180,7 @@ void logfs_evict_inode(struct inode *inode)
 			do_delete_inode(inode);
 		}
 	}
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 
 	/* Cheaper version of write_inode.  All changes are concealed in
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index 0332109162a5..03aaeb1a694a 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -26,7 +26,7 @@ static int minix_remount (struct super_block * sb, int * flags, char * data);
 
 static void minix_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	if (!inode->i_nlink) {
 		inode->i_size = 0;
 		minix_truncate(inode);
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index 2cf2ebecb55f..ee59d35ff069 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -296,7 +296,7 @@ ncp_iget(struct super_block *sb, struct ncp_entry_info *info)
 static void
 ncp_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 
 	if (S_ISDIR(inode->i_mode)) {
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 360114ae8b82..c4702baa22b8 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -128,7 +128,7 @@ EXPORT_SYMBOL_GPL(nfs_clear_inode);
 
 void nfs_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	nfs_clear_inode(inode);
 }
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index 808f29574412..6f340f02f2ba 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -90,7 +90,7 @@ static int nfs4_write_inode(struct inode *inode, struct writeback_control *wbc)
  */
 static void nfs4_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	pnfs_return_layout(inode);
 	pnfs_destroy_layout(NFS_I(inode));
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 7e350c562e0e..b9c5726120e3 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -783,16 +783,14 @@ void nilfs_evict_inode(struct inode *inode)
 	int ret;
 
 	if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) {
-		if (inode->i_data.nrpages)
-			truncate_inode_pages(&inode->i_data, 0);
+		truncate_inode_pages_final(&inode->i_data);
 		clear_inode(inode);
 		nilfs_clear_inode(inode);
 		return;
 	}
 	nilfs_transaction_begin(sb, &ti, 0); /* never fails */
 
-	if (inode->i_data.nrpages)
-		truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 
 	/* TODO: some of the following operations may fail.  */
 	nilfs_truncate_bmap(ii, 0);
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index ffb9b3675736..9d8153ebacfb 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -2259,7 +2259,7 @@ void ntfs_evict_big_inode(struct inode *vi)
 {
 	ntfs_inode *ni = NTFS_I(vi);
 
-	truncate_inode_pages(&vi->i_data, 0);
+	truncate_inode_pages_final(&vi->i_data);
 	clear_inode(vi);
 
 #ifdef NTFS_RW
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index d437f3ba90b0..437de7f768c6 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -964,7 +964,7 @@ static void ocfs2_cleanup_delete_inode(struct inode *inode,
 		(unsigned long long)OCFS2_I(inode)->ip_blkno, sync_data);
 	if (sync_data)
 		filemap_write_and_wait(inode->i_mapping);
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 }
 
 static void ocfs2_delete_inode(struct inode *inode)
@@ -1181,7 +1181,7 @@ void ocfs2_evict_inode(struct inode *inode)
 	    (OCFS2_I(inode)->ip_flags & OCFS2_INODE_MAYBE_ORPHANED)) {
 		ocfs2_delete_inode(inode);
 	} else {
-		truncate_inode_pages(&inode->i_data, 0);
+		truncate_inode_pages_final(&inode->i_data);
 	}
 	ocfs2_clear_inode(inode);
 }
diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c
index d8b0afde2179..ec58c7659183 100644
--- a/fs/omfs/inode.c
+++ b/fs/omfs/inode.c
@@ -183,7 +183,7 @@ int omfs_sync_inode(struct inode *inode)
  */
 static void omfs_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 
 	if (inode->i_nlink)
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 124fc43c7090..8f20e3404fd2 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -35,7 +35,7 @@ static void proc_evict_inode(struct inode *inode)
 	const struct proc_ns_operations *ns_ops;
 	void *ns;
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 
 	/* Stop tracking associated processes */
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index ad62bdbb451e..bc8b8009897d 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -35,7 +35,7 @@ void reiserfs_evict_inode(struct inode *inode)
 	if (!inode->i_nlink && !is_bad_inode(inode))
 		dquot_initialize(inode);
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	if (inode->i_nlink)
 		goto no_delete;
 
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index c327d4ee1235..5625ca920f5e 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -295,7 +295,7 @@ int sysv_sync_inode(struct inode *inode)
 
 static void sysv_evict_inode(struct inode *inode)
 {
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	if (!inode->i_nlink) {
 		inode->i_size = 0;
 		sysv_truncate(inode);
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 5ded8490c0c6..48f943f7f5d5 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -351,7 +351,7 @@ static void ubifs_evict_inode(struct inode *inode)
 	dbg_gen("inode %lu, mode %#x", inode->i_ino, (int)inode->i_mode);
 	ubifs_assert(!atomic_read(&inode->i_count));
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 
 	if (inode->i_nlink)
 		goto done;
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 982ce05c87ed..5d643706212f 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -146,8 +146,8 @@ void udf_evict_inode(struct inode *inode)
 		want_delete = 1;
 		udf_setsize(inode, 0);
 		udf_update_inode(inode, IS_SYNC(inode));
-	} else
-		truncate_inode_pages(&inode->i_data, 0);
+	}
+	truncate_inode_pages_final(&inode->i_data);
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
 	if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB &&
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index c8ca96086784..61e8a9b021dd 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -885,7 +885,7 @@ void ufs_evict_inode(struct inode * inode)
 	if (!inode->i_nlink && !is_bad_inode(inode))
 		want_delete = 1;
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	if (want_delete) {
 		loff_t old_i_size;
 		/*UFS_I(inode)->i_dtime = CURRENT_TIME;*/
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index d971f4932b5d..0ef599218991 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -996,7 +996,7 @@ xfs_fs_evict_inode(
 
 	trace_xfs_evict_inode(ip);
 
-	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 	XFS_STATS_INC(vn_rele);
 	XFS_STATS_INC(vn_remove);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 6e765d28841b..3ca9420f627e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -419,6 +419,7 @@ struct address_space {
 	struct mutex		i_mmap_mutex;	/* protect tree, count, list */
 	/* Protected by tree_lock together with the radix tree */
 	unsigned long		nrpages;	/* number of total pages */
+	unsigned long		nrshadows;	/* number of shadow entries */
 	pgoff_t			writeback_index;/* writeback starts here */
 	const struct address_space_operations *a_ops;	/* methods */
 	unsigned long		flags;		/* error bits/gfp mask */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index b1331aff769c..58d6ddba5db3 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1834,6 +1834,7 @@ vm_unmapped_area(struct vm_unmapped_area_info *info)
 extern void truncate_inode_pages(struct address_space *, loff_t);
 extern void truncate_inode_pages_range(struct address_space *,
 				       loff_t lstart, loff_t lend);
+extern void truncate_inode_pages_final(struct address_space *);
 
 /* generic vm_area_ops exported for stackable file systems */
 extern int filemap_fault(struct vm_area_struct *, struct vm_fault *);
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 493bfd85214e..ff43253f568a 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -25,6 +25,7 @@ enum mapping_flags {
 	AS_MM_ALL_LOCKS	= __GFP_BITS_SHIFT + 2,	/* under mm_take_all_locks() */
 	AS_UNEVICTABLE	= __GFP_BITS_SHIFT + 3,	/* e.g., ramdisk, SHM_LOCK */
 	AS_BALLOON_MAP  = __GFP_BITS_SHIFT + 4, /* balloon page special map */
+	AS_EXITING	= __GFP_BITS_SHIFT + 5, /* final truncate in progress */
 };
 
 static inline void mapping_set_error(struct address_space *mapping, int error)
@@ -69,6 +70,16 @@ static inline int mapping_balloon(struct address_space *mapping)
 	return mapping && test_bit(AS_BALLOON_MAP, &mapping->flags);
 }
 
+static inline void mapping_set_exiting(struct address_space *mapping)
+{
+	set_bit(AS_EXITING, &mapping->flags);
+}
+
+static inline int mapping_exiting(struct address_space *mapping)
+{
+	return test_bit(AS_EXITING, &mapping->flags);
+}
+
 static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
 {
 	return (__force gfp_t)mapping->flags & __GFP_BITS_MASK;
@@ -547,7 +558,7 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
 int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 				pgoff_t index, gfp_t gfp_mask);
 extern void delete_from_page_cache(struct page *page);
-extern void __delete_from_page_cache(struct page *page);
+extern void __delete_from_page_cache(struct page *page, void *shadow);
 int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask);
 
 /*
diff --git a/mm/filemap.c b/mm/filemap.c
index efc63876477f..05c44aa44188 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -107,12 +107,33 @@
  *   ->tasklist_lock            (memory_failure, collect_procs_ao)
  */
 
+static void page_cache_tree_delete(struct address_space *mapping,
+				   struct page *page, void *shadow)
+{
+	if (shadow) {
+		void **slot;
+
+		slot = radix_tree_lookup_slot(&mapping->page_tree, page->index);
+		radix_tree_replace_slot(slot, shadow);
+		mapping->nrshadows++;
+		/*
+		 * Make sure the nrshadows update is committed before
+		 * the nrpages update so that final truncate racing
+		 * with reclaim does not see both counters 0 at the
+		 * same time and miss a shadow entry.
+		 */
+		smp_wmb();
+	} else
+		radix_tree_delete(&mapping->page_tree, page->index);
+	mapping->nrpages--;
+}
+
 /*
  * Delete a page from the page cache and free it. Caller has to make
  * sure the page is locked and that nobody else uses it - or that usage
  * is safe.  The caller must hold the mapping's tree_lock.
  */
-void __delete_from_page_cache(struct page *page)
+void __delete_from_page_cache(struct page *page, void *shadow)
 {
 	struct address_space *mapping = page->mapping;
 
@@ -127,10 +148,11 @@ void __delete_from_page_cache(struct page *page)
 	else
 		cleancache_invalidate_page(mapping, page);
 
-	radix_tree_delete(&mapping->page_tree, page->index);
+	page_cache_tree_delete(mapping, page, shadow);
+
 	page->mapping = NULL;
 	/* Leave page->index set: truncation lookup relies upon it */
-	mapping->nrpages--;
+
 	__dec_zone_page_state(page, NR_FILE_PAGES);
 	if (PageSwapBacked(page))
 		__dec_zone_page_state(page, NR_SHMEM);
@@ -166,7 +188,7 @@ void delete_from_page_cache(struct page *page)
 
 	freepage = mapping->a_ops->freepage;
 	spin_lock_irq(&mapping->tree_lock);
-	__delete_from_page_cache(page);
+	__delete_from_page_cache(page, NULL);
 	spin_unlock_irq(&mapping->tree_lock);
 	mem_cgroup_uncharge_cache_page(page);
 
@@ -426,7 +448,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 		new->index = offset;
 
 		spin_lock_irq(&mapping->tree_lock);
-		__delete_from_page_cache(old);
+		__delete_from_page_cache(old, NULL);
 		error = radix_tree_insert(&mapping->page_tree, offset, new);
 		BUG_ON(error);
 		mapping->nrpages++;
@@ -460,6 +482,7 @@ static int page_cache_tree_insert(struct address_space *mapping,
 		if (!radix_tree_exceptional_entry(p))
 			return -EEXIST;
 		radix_tree_replace_slot(slot, page);
+		mapping->nrshadows--;
 		mapping->nrpages++;
 		return 0;
 	}
diff --git a/mm/truncate.c b/mm/truncate.c
index 2e84fe59190b..0db9258319f0 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -35,7 +35,8 @@ static void clear_exceptional_entry(struct address_space *mapping,
 	 * without the tree itself locked.  These unlocked entries
 	 * need verification under the tree lock.
 	 */
-	radix_tree_delete_item(&mapping->page_tree, index, entry);
+	if (radix_tree_delete_item(&mapping->page_tree, index, entry) == entry)
+		mapping->nrshadows--;
 	spin_unlock_irq(&mapping->tree_lock);
 }
 
@@ -229,7 +230,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 	int		i;
 
 	cleancache_invalidate_inode(mapping);
-	if (mapping->nrpages == 0)
+	if (mapping->nrpages == 0 && mapping->nrshadows == 0)
 		return;
 
 	/* Offsets within partial pages */
@@ -391,6 +392,53 @@ void truncate_inode_pages(struct address_space *mapping, loff_t lstart)
 }
 EXPORT_SYMBOL(truncate_inode_pages);
 
+/**
+ * truncate_inode_pages_final - truncate *all* pages before inode dies
+ * @mapping: mapping to truncate
+ *
+ * Called under (and serialized by) inode->i_mutex.
+ *
+ * Filesystems have to use this in the .evict_inode path to inform the
+ * VM that this is the final truncate and the inode is going away.
+ */
+void truncate_inode_pages_final(struct address_space *mapping)
+{
+	unsigned long nrshadows;
+	unsigned long nrpages;
+
+	/*
+	 * Page reclaim can not participate in regular inode lifetime
+	 * management (can't call iput()) and thus can race with the
+	 * inode teardown.  Tell it when the address space is exiting,
+	 * so that it does not install eviction information after the
+	 * final truncate has begun.
+	 */
+	mapping_set_exiting(mapping);
+
+	/*
+	 * When reclaim installs eviction entries, it increases
+	 * nrshadows first, then decreases nrpages.  Make sure we see
+	 * this in the right order or we might miss an entry.
+	 */
+	nrpages = mapping->nrpages;
+	smp_rmb();
+	nrshadows = mapping->nrshadows;
+
+	if (nrpages || nrshadows) {
+		/*
+		 * As truncation uses a lockless tree lookup, cycle
+		 * the tree lock to make sure any ongoing tree
+		 * modification that does not see AS_EXITING is
+		 * completed before starting the final truncate.
+		 */
+		spin_lock_irq(&mapping->tree_lock);
+		spin_unlock_irq(&mapping->tree_lock);
+
+		truncate_inode_pages(mapping, 0);
+	}
+}
+EXPORT_SYMBOL(truncate_inode_pages_final);
+
 /**
  * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode
  * @mapping: the address_space which holds the pages to invalidate
@@ -484,7 +532,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
 		goto failed;
 
 	BUG_ON(page_has_private(page));
-	__delete_from_page_cache(page);
+	__delete_from_page_cache(page, NULL);
 	spin_unlock_irq(&mapping->tree_lock);
 	mem_cgroup_uncharge_cache_page(page);
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c53d1a54964c..2a0bb8fdb259 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -572,7 +572,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page)
 
 		freepage = mapping->a_ops->freepage;
 
-		__delete_from_page_cache(page);
+		__delete_from_page_cache(page, NULL);
 		spin_unlock_irq(&mapping->tree_lock);
 		mem_cgroup_uncharge_cache_page(page);
 
-- 
cgit v1.2.3


From a528910e12ec7ee203095eb1711468a66b9b60b0 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Thu, 3 Apr 2014 14:47:51 -0700
Subject: mm: thrash detection-based file cache sizing

The VM maintains cached filesystem pages on two types of lists.  One
list holds the pages recently faulted into the cache, the other list
holds pages that have been referenced repeatedly on that first list.
The idea is to prefer reclaiming young pages over those that have shown
to benefit from caching in the past.  We call the recently usedbut
ultimately was not significantly better than a FIFO policy and still
thrashed cache based on eviction speed, rather than actual demand for
cache.

This patch solves one half of the problem by decoupling the ability to
detect working set changes from the inactive list size.  By maintaining
a history of recently evicted file pages it can detect frequently used
pages with an arbitrarily small inactive list size, and subsequently
apply pressure on the active list based on actual demand for cache, not
just overall eviction speed.

Every zone maintains a counter that tracks inactive list aging speed.
When a page is evicted, a snapshot of this counter is stored in the
now-empty page cache radix tree slot.  On refault, the minimum access
distance of the page can be assessed, to evaluate whether the page
should be part of the active list or not.

This fixes the VM's blindness towards working set changes in excess of
the inactive list.  And it's the foundation to further improve the
protection ability and reduce the minimum inactive list size of 50%.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Bob Liu <bob.liu@oracle.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h |   5 +
 include/linux/swap.h   |   5 +
 mm/Makefile            |   2 +-
 mm/filemap.c           |  61 ++++++++----
 mm/swap.c              |   2 +
 mm/vmscan.c            |  24 ++++-
 mm/vmstat.c            |   2 +
 mm/workingset.c        | 253 +++++++++++++++++++++++++++++++++++++++++++++++++
 8 files changed, 331 insertions(+), 23 deletions(-)
 create mode 100644 mm/workingset.c

(limited to 'include/linux')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 9b61b9bf81ac..f25db1d74a21 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -142,6 +142,8 @@ enum zone_stat_item {
 	NUMA_LOCAL,		/* allocation from local node */
 	NUMA_OTHER,		/* allocation from other node */
 #endif
+	WORKINGSET_REFAULT,
+	WORKINGSET_ACTIVATE,
 	NR_ANON_TRANSPARENT_HUGEPAGES,
 	NR_FREE_CMA_PAGES,
 	NR_VM_ZONE_STAT_ITEMS };
@@ -392,6 +394,9 @@ struct zone {
 	spinlock_t		lru_lock;
 	struct lruvec		lruvec;
 
+	/* Evictions & activations on the inactive file list */
+	atomic_long_t		inactive_age;
+
 	unsigned long		pages_scanned;	   /* since last reclaim */
 	unsigned long		flags;		   /* zone flags, see below */
 
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 46ba0c6c219f..b83cf61403ed 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -260,6 +260,11 @@ struct swap_list_t {
 	int next;	/* swapfile to be used next */
 };
 
+/* linux/mm/workingset.c */
+void *workingset_eviction(struct address_space *mapping, struct page *page);
+bool workingset_refault(void *shadow);
+void workingset_activation(struct page *page);
+
 /* linux/mm/page_alloc.c */
 extern unsigned long totalram_pages;
 extern unsigned long totalreserve_pages;
diff --git a/mm/Makefile b/mm/Makefile
index 310c90a09264..cdd741519ee0 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -17,7 +17,7 @@ obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 			   util.o mmzone.o vmstat.o backing-dev.o \
 			   mm_init.o mmu_context.o percpu.o slab_common.o \
 			   compaction.o balloon_compaction.o \
-			   interval_tree.o list_lru.o $(mmu-y)
+			   interval_tree.o list_lru.o workingset.o $(mmu-y)
 
 obj-y += init-mm.o
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 05c44aa44188..a603c4d7d3c9 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -469,7 +469,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 EXPORT_SYMBOL_GPL(replace_page_cache_page);
 
 static int page_cache_tree_insert(struct address_space *mapping,
-				  struct page *page)
+				  struct page *page, void **shadowp)
 {
 	void **slot;
 	int error;
@@ -484,6 +484,8 @@ static int page_cache_tree_insert(struct address_space *mapping,
 		radix_tree_replace_slot(slot, page);
 		mapping->nrshadows--;
 		mapping->nrpages++;
+		if (shadowp)
+			*shadowp = p;
 		return 0;
 	}
 	error = radix_tree_insert(&mapping->page_tree, page->index, page);
@@ -492,18 +494,10 @@ static int page_cache_tree_insert(struct address_space *mapping,
 	return error;
 }
 
-/**
- * add_to_page_cache_locked - add a locked page to the pagecache
- * @page:	page to add
- * @mapping:	the page's address_space
- * @offset:	page index
- * @gfp_mask:	page allocation mode
- *
- * This function is used to add a page to the pagecache. It must be locked.
- * This function does not add the page to the LRU.  The caller must do that.
- */
-int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
-		pgoff_t offset, gfp_t gfp_mask)
+static int __add_to_page_cache_locked(struct page *page,
+				      struct address_space *mapping,
+				      pgoff_t offset, gfp_t gfp_mask,
+				      void **shadowp)
 {
 	int error;
 
@@ -526,7 +520,7 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
 	page->index = offset;
 
 	spin_lock_irq(&mapping->tree_lock);
-	error = page_cache_tree_insert(mapping, page);
+	error = page_cache_tree_insert(mapping, page, shadowp);
 	radix_tree_preload_end();
 	if (unlikely(error))
 		goto err_insert;
@@ -542,16 +536,49 @@ err_insert:
 	page_cache_release(page);
 	return error;
 }
+
+/**
+ * add_to_page_cache_locked - add a locked page to the pagecache
+ * @page:	page to add
+ * @mapping:	the page's address_space
+ * @offset:	page index
+ * @gfp_mask:	page allocation mode
+ *
+ * This function is used to add a page to the pagecache. It must be locked.
+ * This function does not add the page to the LRU.  The caller must do that.
+ */
+int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
+		pgoff_t offset, gfp_t gfp_mask)
+{
+	return __add_to_page_cache_locked(page, mapping, offset,
+					  gfp_mask, NULL);
+}
 EXPORT_SYMBOL(add_to_page_cache_locked);
 
 int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 				pgoff_t offset, gfp_t gfp_mask)
 {
+	void *shadow = NULL;
 	int ret;
 
-	ret = add_to_page_cache(page, mapping, offset, gfp_mask);
-	if (ret == 0)
-		lru_cache_add_file(page);
+	__set_page_locked(page);
+	ret = __add_to_page_cache_locked(page, mapping, offset,
+					 gfp_mask, &shadow);
+	if (unlikely(ret))
+		__clear_page_locked(page);
+	else {
+		/*
+		 * The page might have been evicted from cache only
+		 * recently, in which case it should be activated like
+		 * any other repeatedly accessed page.
+		 */
+		if (shadow && workingset_refault(shadow)) {
+			SetPageActive(page);
+			workingset_activation(page);
+		} else
+			ClearPageActive(page);
+		lru_cache_add(page);
+	}
 	return ret;
 }
 EXPORT_SYMBOL_GPL(add_to_page_cache_lru);
diff --git a/mm/swap.c b/mm/swap.c
index c8048d71c642..9ce43ba4498b 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -574,6 +574,8 @@ void mark_page_accessed(struct page *page)
 		else
 			__lru_cache_activate_page(page);
 		ClearPageReferenced(page);
+		if (page_is_file_cache(page))
+			workingset_activation(page);
 	} else if (!PageReferenced(page)) {
 		SetPageReferenced(page);
 	}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2a0bb8fdb259..1f56a80a7c41 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -523,7 +523,8 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
  * Same as remove_mapping, but if the page is removed from the mapping, it
  * gets returned with a refcount of 0.
  */
-static int __remove_mapping(struct address_space *mapping, struct page *page)
+static int __remove_mapping(struct address_space *mapping, struct page *page,
+			    bool reclaimed)
 {
 	BUG_ON(!PageLocked(page));
 	BUG_ON(mapping != page_mapping(page));
@@ -569,10 +570,23 @@ static int __remove_mapping(struct address_space *mapping, struct page *page)
 		swapcache_free(swap, page);
 	} else {
 		void (*freepage)(struct page *);
+		void *shadow = NULL;
 
 		freepage = mapping->a_ops->freepage;
-
-		__delete_from_page_cache(page, NULL);
+		/*
+		 * Remember a shadow entry for reclaimed file cache in
+		 * order to detect refaults, thus thrashing, later on.
+		 *
+		 * But don't store shadows in an address space that is
+		 * already exiting.  This is not just an optizimation,
+		 * inode reclaim needs to empty out the radix tree or
+		 * the nodes are lost.  Don't plant shadows behind its
+		 * back.
+		 */
+		if (reclaimed && page_is_file_cache(page) &&
+		    !mapping_exiting(mapping))
+			shadow = workingset_eviction(mapping, page);
+		__delete_from_page_cache(page, shadow);
 		spin_unlock_irq(&mapping->tree_lock);
 		mem_cgroup_uncharge_cache_page(page);
 
@@ -595,7 +609,7 @@ cannot_free:
  */
 int remove_mapping(struct address_space *mapping, struct page *page)
 {
-	if (__remove_mapping(mapping, page)) {
+	if (__remove_mapping(mapping, page, false)) {
 		/*
 		 * Unfreezing the refcount with 1 rather than 2 effectively
 		 * drops the pagecache ref for us without requiring another
@@ -1065,7 +1079,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			}
 		}
 
-		if (!mapping || !__remove_mapping(mapping, page))
+		if (!mapping || !__remove_mapping(mapping, page, true))
 			goto keep_locked;
 
 		/*
diff --git a/mm/vmstat.c b/mm/vmstat.c
index def5dd2fbe61..843125a0e255 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -770,6 +770,8 @@ const char * const vmstat_text[] = {
 	"numa_local",
 	"numa_other",
 #endif
+	"workingset_refault",
+	"workingset_activate",
 	"nr_anon_transparent_hugepages",
 	"nr_free_cma",
 	"nr_dirty_threshold",
diff --git a/mm/workingset.c b/mm/workingset.c
new file mode 100644
index 000000000000..8a6c7cff4923
--- /dev/null
+++ b/mm/workingset.c
@@ -0,0 +1,253 @@
+/*
+ * Workingset detection
+ *
+ * Copyright (C) 2013 Red Hat, Inc., Johannes Weiner
+ */
+
+#include <linux/memcontrol.h>
+#include <linux/writeback.h>
+#include <linux/pagemap.h>
+#include <linux/atomic.h>
+#include <linux/module.h>
+#include <linux/swap.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+
+/*
+ *		Double CLOCK lists
+ *
+ * Per zone, two clock lists are maintained for file pages: the
+ * inactive and the active list.  Freshly faulted pages start out at
+ * the head of the inactive list and page reclaim scans pages from the
+ * tail.  Pages that are accessed multiple times on the inactive list
+ * are promoted to the active list, to protect them from reclaim,
+ * whereas active pages are demoted to the inactive list when the
+ * active list grows too big.
+ *
+ *   fault ------------------------+
+ *                                 |
+ *              +--------------+   |            +-------------+
+ *   reclaim <- |   inactive   | <-+-- demotion |    active   | <--+
+ *              +--------------+                +-------------+    |
+ *                     |                                           |
+ *                     +-------------- promotion ------------------+
+ *
+ *
+ *		Access frequency and refault distance
+ *
+ * A workload is thrashing when its pages are frequently used but they
+ * are evicted from the inactive list every time before another access
+ * would have promoted them to the active list.
+ *
+ * In cases where the average access distance between thrashing pages
+ * is bigger than the size of memory there is nothing that can be
+ * done - the thrashing set could never fit into memory under any
+ * circumstance.
+ *
+ * However, the average access distance could be bigger than the
+ * inactive list, yet smaller than the size of memory.  In this case,
+ * the set could fit into memory if it weren't for the currently
+ * active pages - which may be used more, hopefully less frequently:
+ *
+ *      +-memory available to cache-+
+ *      |                           |
+ *      +-inactive------+-active----+
+ *  a b | c d e f g h i | J K L M N |
+ *      +---------------+-----------+
+ *
+ * It is prohibitively expensive to accurately track access frequency
+ * of pages.  But a reasonable approximation can be made to measure
+ * thrashing on the inactive list, after which refaulting pages can be
+ * activated optimistically to compete with the existing active pages.
+ *
+ * Approximating inactive page access frequency - Observations:
+ *
+ * 1. When a page is accessed for the first time, it is added to the
+ *    head of the inactive list, slides every existing inactive page
+ *    towards the tail by one slot, and pushes the current tail page
+ *    out of memory.
+ *
+ * 2. When a page is accessed for the second time, it is promoted to
+ *    the active list, shrinking the inactive list by one slot.  This
+ *    also slides all inactive pages that were faulted into the cache
+ *    more recently than the activated page towards the tail of the
+ *    inactive list.
+ *
+ * Thus:
+ *
+ * 1. The sum of evictions and activations between any two points in
+ *    time indicate the minimum number of inactive pages accessed in
+ *    between.
+ *
+ * 2. Moving one inactive page N page slots towards the tail of the
+ *    list requires at least N inactive page accesses.
+ *
+ * Combining these:
+ *
+ * 1. When a page is finally evicted from memory, the number of
+ *    inactive pages accessed while the page was in cache is at least
+ *    the number of page slots on the inactive list.
+ *
+ * 2. In addition, measuring the sum of evictions and activations (E)
+ *    at the time of a page's eviction, and comparing it to another
+ *    reading (R) at the time the page faults back into memory tells
+ *    the minimum number of accesses while the page was not cached.
+ *    This is called the refault distance.
+ *
+ * Because the first access of the page was the fault and the second
+ * access the refault, we combine the in-cache distance with the
+ * out-of-cache distance to get the complete minimum access distance
+ * of this page:
+ *
+ *      NR_inactive + (R - E)
+ *
+ * And knowing the minimum access distance of a page, we can easily
+ * tell if the page would be able to stay in cache assuming all page
+ * slots in the cache were available:
+ *
+ *   NR_inactive + (R - E) <= NR_inactive + NR_active
+ *
+ * which can be further simplified to
+ *
+ *   (R - E) <= NR_active
+ *
+ * Put into words, the refault distance (out-of-cache) can be seen as
+ * a deficit in inactive list space (in-cache).  If the inactive list
+ * had (R - E) more page slots, the page would not have been evicted
+ * in between accesses, but activated instead.  And on a full system,
+ * the only thing eating into inactive list space is active pages.
+ *
+ *
+ *		Activating refaulting pages
+ *
+ * All that is known about the active list is that the pages have been
+ * accessed more than once in the past.  This means that at any given
+ * time there is actually a good chance that pages on the active list
+ * are no longer in active use.
+ *
+ * So when a refault distance of (R - E) is observed and there are at
+ * least (R - E) active pages, the refaulting page is activated
+ * optimistically in the hope that (R - E) active pages are actually
+ * used less frequently than the refaulting page - or even not used at
+ * all anymore.
+ *
+ * If this is wrong and demotion kicks in, the pages which are truly
+ * used more frequently will be reactivated while the less frequently
+ * used once will be evicted from memory.
+ *
+ * But if this is right, the stale pages will be pushed out of memory
+ * and the used pages get to stay in cache.
+ *
+ *
+ *		Implementation
+ *
+ * For each zone's file LRU lists, a counter for inactive evictions
+ * and activations is maintained (zone->inactive_age).
+ *
+ * On eviction, a snapshot of this counter (along with some bits to
+ * identify the zone) is stored in the now empty page cache radix tree
+ * slot of the evicted page.  This is called a shadow entry.
+ *
+ * On cache misses for which there are shadow entries, an eligible
+ * refault distance will immediately activate the refaulting page.
+ */
+
+static void *pack_shadow(unsigned long eviction, struct zone *zone)
+{
+	eviction = (eviction << NODES_SHIFT) | zone_to_nid(zone);
+	eviction = (eviction << ZONES_SHIFT) | zone_idx(zone);
+	eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT);
+
+	return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY);
+}
+
+static void unpack_shadow(void *shadow,
+			  struct zone **zone,
+			  unsigned long *distance)
+{
+	unsigned long entry = (unsigned long)shadow;
+	unsigned long eviction;
+	unsigned long refault;
+	unsigned long mask;
+	int zid, nid;
+
+	entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT;
+	zid = entry & ((1UL << ZONES_SHIFT) - 1);
+	entry >>= ZONES_SHIFT;
+	nid = entry & ((1UL << NODES_SHIFT) - 1);
+	entry >>= NODES_SHIFT;
+	eviction = entry;
+
+	*zone = NODE_DATA(nid)->node_zones + zid;
+
+	refault = atomic_long_read(&(*zone)->inactive_age);
+	mask = ~0UL >> (NODES_SHIFT + ZONES_SHIFT +
+			RADIX_TREE_EXCEPTIONAL_SHIFT);
+	/*
+	 * The unsigned subtraction here gives an accurate distance
+	 * across inactive_age overflows in most cases.
+	 *
+	 * There is a special case: usually, shadow entries have a
+	 * short lifetime and are either refaulted or reclaimed along
+	 * with the inode before they get too old.  But it is not
+	 * impossible for the inactive_age to lap a shadow entry in
+	 * the field, which can then can result in a false small
+	 * refault distance, leading to a false activation should this
+	 * old entry actually refault again.  However, earlier kernels
+	 * used to deactivate unconditionally with *every* reclaim
+	 * invocation for the longest time, so the occasional
+	 * inappropriate activation leading to pressure on the active
+	 * list is not a problem.
+	 */
+	*distance = (refault - eviction) & mask;
+}
+
+/**
+ * workingset_eviction - note the eviction of a page from memory
+ * @mapping: address space the page was backing
+ * @page: the page being evicted
+ *
+ * Returns a shadow entry to be stored in @mapping->page_tree in place
+ * of the evicted @page so that a later refault can be detected.
+ */
+void *workingset_eviction(struct address_space *mapping, struct page *page)
+{
+	struct zone *zone = page_zone(page);
+	unsigned long eviction;
+
+	eviction = atomic_long_inc_return(&zone->inactive_age);
+	return pack_shadow(eviction, zone);
+}
+
+/**
+ * workingset_refault - evaluate the refault of a previously evicted page
+ * @shadow: shadow entry of the evicted page
+ *
+ * Calculates and evaluates the refault distance of the previously
+ * evicted page in the context of the zone it was allocated in.
+ *
+ * Returns %true if the page should be activated, %false otherwise.
+ */
+bool workingset_refault(void *shadow)
+{
+	unsigned long refault_distance;
+	struct zone *zone;
+
+	unpack_shadow(shadow, &zone, &refault_distance);
+	inc_zone_state(zone, WORKINGSET_REFAULT);
+
+	if (refault_distance <= zone_page_state(zone, NR_ACTIVE_FILE)) {
+		inc_zone_state(zone, WORKINGSET_ACTIVATE);
+		return true;
+	}
+	return false;
+}
+
+/**
+ * workingset_activation - note a page activation
+ * @page: page that is being activated
+ */
+void workingset_activation(struct page *page)
+{
+	atomic_long_inc(&page_zone(page)->inactive_age);
+}
-- 
cgit v1.2.3


From 139e561660fe11e0fc35e142a800df3dd7d03e9d Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Thu, 3 Apr 2014 14:47:54 -0700
Subject: lib: radix_tree: tree node interface

Make struct radix_tree_node part of the public interface and provide API
functions to create, look up, and delete whole nodes.  Refactor the
existing insert, look up, delete functions on top of these new node
primitives.

This will allow the VM to track and garbage collect page cache radix
tree nodes.

[sasha.levin@oracle.com: return correct error code on insertion failure]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/radix-tree.h |  34 ++++++
 lib/radix-tree.c           | 263 +++++++++++++++++++++++++--------------------
 2 files changed, 182 insertions(+), 115 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index e8be53ecfc45..13636c40bc42 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -60,6 +60,33 @@ static inline int radix_tree_is_indirect_ptr(void *ptr)
 
 #define RADIX_TREE_MAX_TAGS 3
 
+#ifdef __KERNEL__
+#define RADIX_TREE_MAP_SHIFT	(CONFIG_BASE_SMALL ? 4 : 6)
+#else
+#define RADIX_TREE_MAP_SHIFT	3	/* For more stressful testing */
+#endif
+
+#define RADIX_TREE_MAP_SIZE	(1UL << RADIX_TREE_MAP_SHIFT)
+#define RADIX_TREE_MAP_MASK	(RADIX_TREE_MAP_SIZE-1)
+
+#define RADIX_TREE_TAG_LONGS	\
+	((RADIX_TREE_MAP_SIZE + BITS_PER_LONG - 1) / BITS_PER_LONG)
+
+struct radix_tree_node {
+	unsigned int	height;		/* Height from the bottom */
+	unsigned int	count;
+	union {
+		struct radix_tree_node *parent;	/* Used when ascending tree */
+		struct rcu_head	rcu_head;	/* Used when freeing node */
+	};
+	void __rcu	*slots[RADIX_TREE_MAP_SIZE];
+	unsigned long	tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS];
+};
+
+#define RADIX_TREE_INDEX_BITS  (8 /* CHAR_BIT */ * sizeof(unsigned long))
+#define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \
+					  RADIX_TREE_MAP_SHIFT))
+
 /* root tags are stored in gfp_mask, shifted by __GFP_BITS_SHIFT */
 struct radix_tree_root {
 	unsigned int		height;
@@ -101,6 +128,7 @@ do {									\
  *   concurrently with other readers.
  *
  * The notable exceptions to this rule are the following functions:
+ * __radix_tree_lookup
  * radix_tree_lookup
  * radix_tree_lookup_slot
  * radix_tree_tag_get
@@ -216,9 +244,15 @@ static inline void radix_tree_replace_slot(void **pslot, void *item)
 	rcu_assign_pointer(*pslot, item);
 }
 
+int __radix_tree_create(struct radix_tree_root *root, unsigned long index,
+			struct radix_tree_node **nodep, void ***slotp);
 int radix_tree_insert(struct radix_tree_root *, unsigned long, void *);
+void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index,
+			  struct radix_tree_node **nodep, void ***slotp);
 void *radix_tree_lookup(struct radix_tree_root *, unsigned long);
 void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long);
+bool __radix_tree_delete_node(struct radix_tree_root *root, unsigned long index,
+			      struct radix_tree_node *node);
 void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *);
 void *radix_tree_delete(struct radix_tree_root *, unsigned long);
 unsigned int
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 7e30d2a7f346..d60be40c111b 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -35,33 +35,6 @@
 #include <linux/hardirq.h>		/* in_interrupt() */
 
 
-#ifdef __KERNEL__
-#define RADIX_TREE_MAP_SHIFT	(CONFIG_BASE_SMALL ? 4 : 6)
-#else
-#define RADIX_TREE_MAP_SHIFT	3	/* For more stressful testing */
-#endif
-
-#define RADIX_TREE_MAP_SIZE	(1UL << RADIX_TREE_MAP_SHIFT)
-#define RADIX_TREE_MAP_MASK	(RADIX_TREE_MAP_SIZE-1)
-
-#define RADIX_TREE_TAG_LONGS	\
-	((RADIX_TREE_MAP_SIZE + BITS_PER_LONG - 1) / BITS_PER_LONG)
-
-struct radix_tree_node {
-	unsigned int	height;		/* Height from the bottom */
-	unsigned int	count;
-	union {
-		struct radix_tree_node *parent;	/* Used when ascending tree */
-		struct rcu_head	rcu_head;	/* Used when freeing node */
-	};
-	void __rcu	*slots[RADIX_TREE_MAP_SIZE];
-	unsigned long	tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS];
-};
-
-#define RADIX_TREE_INDEX_BITS  (8 /* CHAR_BIT */ * sizeof(unsigned long))
-#define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \
-					  RADIX_TREE_MAP_SHIFT))
-
 /*
  * The height_to_maxindex array needs to be one deeper than the maximum
  * path as height 0 holds only 1 entry.
@@ -387,23 +360,28 @@ out:
 }
 
 /**
- *	radix_tree_insert    -    insert into a radix tree
+ *	__radix_tree_create	-	create a slot in a radix tree
  *	@root:		radix tree root
  *	@index:		index key
- *	@item:		item to insert
+ *	@nodep:		returns node
+ *	@slotp:		returns slot
  *
- *	Insert an item into the radix tree at position @index.
+ *	Create, if necessary, and return the node and slot for an item
+ *	at position @index in the radix tree @root.
+ *
+ *	Until there is more than one item in the tree, no nodes are
+ *	allocated and @root->rnode is used as a direct slot instead of
+ *	pointing to a node, in which case *@nodep will be NULL.
+ *
+ *	Returns -ENOMEM, or 0 for success.
  */
-int radix_tree_insert(struct radix_tree_root *root,
-			unsigned long index, void *item)
+int __radix_tree_create(struct radix_tree_root *root, unsigned long index,
+			struct radix_tree_node **nodep, void ***slotp)
 {
 	struct radix_tree_node *node = NULL, *slot;
-	unsigned int height, shift;
-	int offset;
+	unsigned int height, shift, offset;
 	int error;
 
-	BUG_ON(radix_tree_is_indirect_ptr(item));
-
 	/* Make sure the tree is high enough.  */
 	if (index > radix_tree_maxindex(root->height)) {
 		error = radix_tree_extend(root, index);
@@ -439,16 +417,42 @@ int radix_tree_insert(struct radix_tree_root *root,
 		height--;
 	}
 
-	if (slot != NULL)
+	if (nodep)
+		*nodep = node;
+	if (slotp)
+		*slotp = node ? node->slots + offset : (void **)&root->rnode;
+	return 0;
+}
+
+/**
+ *	radix_tree_insert    -    insert into a radix tree
+ *	@root:		radix tree root
+ *	@index:		index key
+ *	@item:		item to insert
+ *
+ *	Insert an item into the radix tree at position @index.
+ */
+int radix_tree_insert(struct radix_tree_root *root,
+			unsigned long index, void *item)
+{
+	struct radix_tree_node *node;
+	void **slot;
+	int error;
+
+	BUG_ON(radix_tree_is_indirect_ptr(item));
+
+	error = __radix_tree_create(root, index, &node, &slot);
+	if (error)
+		return error;
+	if (*slot != NULL)
 		return -EEXIST;
+	rcu_assign_pointer(*slot, item);
 
 	if (node) {
 		node->count++;
-		rcu_assign_pointer(node->slots[offset], item);
-		BUG_ON(tag_get(node, 0, offset));
-		BUG_ON(tag_get(node, 1, offset));
+		BUG_ON(tag_get(node, 0, index & RADIX_TREE_MAP_MASK));
+		BUG_ON(tag_get(node, 1, index & RADIX_TREE_MAP_MASK));
 	} else {
-		rcu_assign_pointer(root->rnode, item);
 		BUG_ON(root_tag_get(root, 0));
 		BUG_ON(root_tag_get(root, 1));
 	}
@@ -457,15 +461,26 @@ int radix_tree_insert(struct radix_tree_root *root,
 }
 EXPORT_SYMBOL(radix_tree_insert);
 
-/*
- * is_slot == 1 : search for the slot.
- * is_slot == 0 : search for the node.
+/**
+ *	__radix_tree_lookup	-	lookup an item in a radix tree
+ *	@root:		radix tree root
+ *	@index:		index key
+ *	@nodep:		returns node
+ *	@slotp:		returns slot
+ *
+ *	Lookup and return the item at position @index in the radix
+ *	tree @root.
+ *
+ *	Until there is more than one item in the tree, no nodes are
+ *	allocated and @root->rnode is used as a direct slot instead of
+ *	pointing to a node, in which case *@nodep will be NULL.
  */
-static void *radix_tree_lookup_element(struct radix_tree_root *root,
-				unsigned long index, int is_slot)
+void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index,
+			  struct radix_tree_node **nodep, void ***slotp)
 {
+	struct radix_tree_node *node, *parent;
 	unsigned int height, shift;
-	struct radix_tree_node *node, **slot;
+	void **slot;
 
 	node = rcu_dereference_raw(root->rnode);
 	if (node == NULL)
@@ -474,7 +489,12 @@ static void *radix_tree_lookup_element(struct radix_tree_root *root,
 	if (!radix_tree_is_indirect_ptr(node)) {
 		if (index > 0)
 			return NULL;
-		return is_slot ? (void *)&root->rnode : node;
+
+		if (nodep)
+			*nodep = NULL;
+		if (slotp)
+			*slotp = (void **)&root->rnode;
+		return node;
 	}
 	node = indirect_to_ptr(node);
 
@@ -485,8 +505,8 @@ static void *radix_tree_lookup_element(struct radix_tree_root *root,
 	shift = (height-1) * RADIX_TREE_MAP_SHIFT;
 
 	do {
-		slot = (struct radix_tree_node **)
-			(node->slots + ((index>>shift) & RADIX_TREE_MAP_MASK));
+		parent = node;
+		slot = node->slots + ((index >> shift) & RADIX_TREE_MAP_MASK);
 		node = rcu_dereference_raw(*slot);
 		if (node == NULL)
 			return NULL;
@@ -495,7 +515,11 @@ static void *radix_tree_lookup_element(struct radix_tree_root *root,
 		height--;
 	} while (height > 0);
 
-	return is_slot ? (void *)slot : indirect_to_ptr(node);
+	if (nodep)
+		*nodep = parent;
+	if (slotp)
+		*slotp = slot;
+	return node;
 }
 
 /**
@@ -513,7 +537,11 @@ static void *radix_tree_lookup_element(struct radix_tree_root *root,
  */
 void **radix_tree_lookup_slot(struct radix_tree_root *root, unsigned long index)
 {
-	return (void **)radix_tree_lookup_element(root, index, 1);
+	void **slot;
+
+	if (!__radix_tree_lookup(root, index, NULL, &slot))
+		return NULL;
+	return slot;
 }
 EXPORT_SYMBOL(radix_tree_lookup_slot);
 
@@ -531,7 +559,7 @@ EXPORT_SYMBOL(radix_tree_lookup_slot);
  */
 void *radix_tree_lookup(struct radix_tree_root *root, unsigned long index)
 {
-	return radix_tree_lookup_element(root, index, 0);
+	return __radix_tree_lookup(root, index, NULL, NULL);
 }
 EXPORT_SYMBOL(radix_tree_lookup);
 
@@ -1261,6 +1289,56 @@ static inline void radix_tree_shrink(struct radix_tree_root *root)
 	}
 }
 
+/**
+ *	__radix_tree_delete_node    -    try to free node after clearing a slot
+ *	@root:		radix tree root
+ *	@index:		index key
+ *	@node:		node containing @index
+ *
+ *	After clearing the slot at @index in @node from radix tree
+ *	rooted at @root, call this function to attempt freeing the
+ *	node and shrinking the tree.
+ *
+ *	Returns %true if @node was freed, %false otherwise.
+ */
+bool __radix_tree_delete_node(struct radix_tree_root *root, unsigned long index,
+			      struct radix_tree_node *node)
+{
+	bool deleted = false;
+
+	do {
+		struct radix_tree_node *parent;
+
+		if (node->count) {
+			if (node == indirect_to_ptr(root->rnode)) {
+				radix_tree_shrink(root);
+				if (root->height == 0)
+					deleted = true;
+			}
+			return deleted;
+		}
+
+		parent = node->parent;
+		if (parent) {
+			index >>= RADIX_TREE_MAP_SHIFT;
+
+			parent->slots[index & RADIX_TREE_MAP_MASK] = NULL;
+			parent->count--;
+		} else {
+			root_tag_clear_all(root);
+			root->height = 0;
+			root->rnode = NULL;
+		}
+
+		radix_tree_node_free(node);
+		deleted = true;
+
+		node = parent;
+	} while (node);
+
+	return deleted;
+}
+
 /**
  *	radix_tree_delete_item    -    delete an item from a radix tree
  *	@root:		radix tree root
@@ -1275,43 +1353,26 @@ static inline void radix_tree_shrink(struct radix_tree_root *root)
 void *radix_tree_delete_item(struct radix_tree_root *root,
 			     unsigned long index, void *item)
 {
-	struct radix_tree_node *node = NULL;
-	struct radix_tree_node *slot = NULL;
-	struct radix_tree_node *to_free;
-	unsigned int height, shift;
+	struct radix_tree_node *node;
+	unsigned int offset;
+	void **slot;
+	void *entry;
 	int tag;
-	int uninitialized_var(offset);
 
-	height = root->height;
-	if (index > radix_tree_maxindex(height))
-		goto out;
+	entry = __radix_tree_lookup(root, index, &node, &slot);
+	if (!entry)
+		return NULL;
 
-	slot = root->rnode;
-	if (height == 0) {
+	if (item && entry != item)
+		return NULL;
+
+	if (!node) {
 		root_tag_clear_all(root);
 		root->rnode = NULL;
-		goto out;
+		return entry;
 	}
-	slot = indirect_to_ptr(slot);
-	shift = height * RADIX_TREE_MAP_SHIFT;
-
-	do {
-		if (slot == NULL)
-			goto out;
-
-		shift -= RADIX_TREE_MAP_SHIFT;
-		offset = (index >> shift) & RADIX_TREE_MAP_MASK;
-		node = slot;
-		slot = slot->slots[offset];
-	} while (shift);
-
-	if (slot == NULL)
-		goto out;
 
-	if (item && slot != item) {
-		slot = NULL;
-		goto out;
-	}
+	offset = index & RADIX_TREE_MAP_MASK;
 
 	/*
 	 * Clear all tags associated with the item to be deleted.
@@ -1322,40 +1383,12 @@ void *radix_tree_delete_item(struct radix_tree_root *root,
 			radix_tree_tag_clear(root, index, tag);
 	}
 
-	to_free = NULL;
-	/* Now free the nodes we do not need anymore */
-	while (node) {
-		node->slots[offset] = NULL;
-		node->count--;
-		/*
-		 * Queue the node for deferred freeing after the
-		 * last reference to it disappears (set NULL, above).
-		 */
-		if (to_free)
-			radix_tree_node_free(to_free);
-
-		if (node->count) {
-			if (node == indirect_to_ptr(root->rnode))
-				radix_tree_shrink(root);
-			goto out;
-		}
-
-		/* Node with zero slots in use so free it */
-		to_free = node;
-
-		index >>= RADIX_TREE_MAP_SHIFT;
-		offset = index & RADIX_TREE_MAP_MASK;
-		node = node->parent;
-	}
+	node->slots[offset] = NULL;
+	node->count--;
 
-	root_tag_clear_all(root);
-	root->height = 0;
-	root->rnode = NULL;
-	if (to_free)
-		radix_tree_node_free(to_free);
+	__radix_tree_delete_node(root, index, node);
 
-out:
-	return slot;
+	return entry;
 }
 EXPORT_SYMBOL(radix_tree_delete_item);
 
-- 
cgit v1.2.3


From 449dd6984d0e47643c04c807f609dd56d48d5bcc Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Thu, 3 Apr 2014 14:47:56 -0700
Subject: mm: keep page cache radix tree nodes in check

Previously, page cache radix tree nodes were freed after reclaim emptied
out their page pointers.  But now reclaim stores shadow entries in their
place, which are only reclaimed when the inodes themselves are
reclaimed.  This is problematic for bigger files that are still in use
after they have a significant amount of their cache reclaimed, without
any of those pages actually refaulting.  The shadow entries will just
sit there and waste memory.  In the worst case, the shadow entries will
accumulate until the machine runs out of memory.

To get this under control, the VM will track radix tree nodes
exclusively containing shadow entries on a per-NUMA node list.  Per-NUMA
rather than global because we expect the radix tree nodes themselves to
be allocated node-locally and we want to reduce cross-node references of
otherwise independent cache workloads.  A simple shrinker will then
reclaim these nodes on memory pressure.

A few things need to be stored in the radix tree node to implement the
shadow node LRU and allow tree deletions coming from the list:

1. There is no index available that would describe the reverse path
   from the node up to the tree root, which is needed to perform a
   deletion.  To solve this, encode in each node its offset inside the
   parent.  This can be stored in the unused upper bits of the same
   member that stores the node's height at no extra space cost.

2. The number of shadow entries needs to be counted in addition to the
   regular entries, to quickly detect when the node is ready to go to
   the shadow node LRU list.  The current entry count is an unsigned
   int but the maximum number of entries is 64, so a shadow counter
   can easily be stored in the unused upper bits.

3. Tree modification needs tree lock and tree root, which are located
   in the address space, so store an address_space backpointer in the
   node.  The parent pointer of the node is in a union with the 2-word
   rcu_head, so the backpointer comes at no extra cost as well.

4. The node needs to be linked to an LRU list, which requires a list
   head inside the node.  This does increase the size of the node, but
   it does not change the number of objects that fit into a slab page.

[akpm@linux-foundation.org: export the right function]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/list_lru.h   |   8 ++-
 include/linux/mmzone.h     |   1 +
 include/linux/radix-tree.h |  32 ++++++---
 include/linux/swap.h       |  31 +++++++++
 lib/radix-tree.c           |  36 ++++++----
 mm/filemap.c               |  90 ++++++++++++++++++++-----
 mm/list_lru.c              |  16 ++++-
 mm/truncate.c              |  26 +++++++-
 mm/vmstat.c                |   1 +
 mm/workingset.c            | 161 +++++++++++++++++++++++++++++++++++++++++++++
 10 files changed, 359 insertions(+), 43 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index 3ce541753c88..f3434533fbf8 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -13,6 +13,8 @@
 /* list_lru_walk_cb has to always return one of those */
 enum lru_status {
 	LRU_REMOVED,		/* item removed from list */
+	LRU_REMOVED_RETRY,	/* item removed, but lock has been
+				   dropped and reacquired */
 	LRU_ROTATE,		/* item referenced, give another pass */
 	LRU_SKIP,		/* item cannot be locked, skip */
 	LRU_RETRY,		/* item not freeable. May drop the lock
@@ -32,7 +34,11 @@ struct list_lru {
 };
 
 void list_lru_destroy(struct list_lru *lru);
-int list_lru_init(struct list_lru *lru);
+int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key);
+static inline int list_lru_init(struct list_lru *lru)
+{
+	return list_lru_init_key(lru, NULL);
+}
 
 /**
  * list_lru_add: add an element to the lru list's tail
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index f25db1d74a21..fac5509c18f0 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -144,6 +144,7 @@ enum zone_stat_item {
 #endif
 	WORKINGSET_REFAULT,
 	WORKINGSET_ACTIVATE,
+	WORKINGSET_NODERECLAIM,
 	NR_ANON_TRANSPARENT_HUGEPAGES,
 	NR_FREE_CMA_PAGES,
 	NR_VM_ZONE_STAT_ITEMS };
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 13636c40bc42..33170dbd9db4 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -72,21 +72,37 @@ static inline int radix_tree_is_indirect_ptr(void *ptr)
 #define RADIX_TREE_TAG_LONGS	\
 	((RADIX_TREE_MAP_SIZE + BITS_PER_LONG - 1) / BITS_PER_LONG)
 
+#define RADIX_TREE_INDEX_BITS  (8 /* CHAR_BIT */ * sizeof(unsigned long))
+#define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \
+					  RADIX_TREE_MAP_SHIFT))
+
+/* Height component in node->path */
+#define RADIX_TREE_HEIGHT_SHIFT	(RADIX_TREE_MAX_PATH + 1)
+#define RADIX_TREE_HEIGHT_MASK	((1UL << RADIX_TREE_HEIGHT_SHIFT) - 1)
+
+/* Internally used bits of node->count */
+#define RADIX_TREE_COUNT_SHIFT	(RADIX_TREE_MAP_SHIFT + 1)
+#define RADIX_TREE_COUNT_MASK	((1UL << RADIX_TREE_COUNT_SHIFT) - 1)
+
 struct radix_tree_node {
-	unsigned int	height;		/* Height from the bottom */
+	unsigned int	path;	/* Offset in parent & height from the bottom */
 	unsigned int	count;
 	union {
-		struct radix_tree_node *parent;	/* Used when ascending tree */
-		struct rcu_head	rcu_head;	/* Used when freeing node */
+		struct {
+			/* Used when ascending tree */
+			struct radix_tree_node *parent;
+			/* For tree user */
+			void *private_data;
+		};
+		/* Used when freeing node */
+		struct rcu_head	rcu_head;
 	};
+	/* For tree user */
+	struct list_head private_list;
 	void __rcu	*slots[RADIX_TREE_MAP_SIZE];
 	unsigned long	tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS];
 };
 
-#define RADIX_TREE_INDEX_BITS  (8 /* CHAR_BIT */ * sizeof(unsigned long))
-#define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \
-					  RADIX_TREE_MAP_SHIFT))
-
 /* root tags are stored in gfp_mask, shifted by __GFP_BITS_SHIFT */
 struct radix_tree_root {
 	unsigned int		height;
@@ -251,7 +267,7 @@ void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index,
 			  struct radix_tree_node **nodep, void ***slotp);
 void *radix_tree_lookup(struct radix_tree_root *, unsigned long);
 void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long);
-bool __radix_tree_delete_node(struct radix_tree_root *root, unsigned long index,
+bool __radix_tree_delete_node(struct radix_tree_root *root,
 			      struct radix_tree_node *node);
 void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *);
 void *radix_tree_delete(struct radix_tree_root *, unsigned long);
diff --git a/include/linux/swap.h b/include/linux/swap.h
index b83cf61403ed..350711560753 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -264,6 +264,37 @@ struct swap_list_t {
 void *workingset_eviction(struct address_space *mapping, struct page *page);
 bool workingset_refault(void *shadow);
 void workingset_activation(struct page *page);
+extern struct list_lru workingset_shadow_nodes;
+
+static inline unsigned int workingset_node_pages(struct radix_tree_node *node)
+{
+	return node->count & RADIX_TREE_COUNT_MASK;
+}
+
+static inline void workingset_node_pages_inc(struct radix_tree_node *node)
+{
+	node->count++;
+}
+
+static inline void workingset_node_pages_dec(struct radix_tree_node *node)
+{
+	node->count--;
+}
+
+static inline unsigned int workingset_node_shadows(struct radix_tree_node *node)
+{
+	return node->count >> RADIX_TREE_COUNT_SHIFT;
+}
+
+static inline void workingset_node_shadows_inc(struct radix_tree_node *node)
+{
+	node->count += 1U << RADIX_TREE_COUNT_SHIFT;
+}
+
+static inline void workingset_node_shadows_dec(struct radix_tree_node *node)
+{
+	node->count -= 1U << RADIX_TREE_COUNT_SHIFT;
+}
 
 /* linux/mm/page_alloc.c */
 extern unsigned long totalram_pages;
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index d60be40c111b..9599aa72d7a0 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -342,7 +342,8 @@ static int radix_tree_extend(struct radix_tree_root *root, unsigned long index)
 
 		/* Increase the height.  */
 		newheight = root->height+1;
-		node->height = newheight;
+		BUG_ON(newheight & ~RADIX_TREE_HEIGHT_MASK);
+		node->path = newheight;
 		node->count = 1;
 		node->parent = NULL;
 		slot = root->rnode;
@@ -400,11 +401,12 @@ int __radix_tree_create(struct radix_tree_root *root, unsigned long index,
 			/* Have to add a child node.  */
 			if (!(slot = radix_tree_node_alloc(root)))
 				return -ENOMEM;
-			slot->height = height;
+			slot->path = height;
 			slot->parent = node;
 			if (node) {
 				rcu_assign_pointer(node->slots[offset], slot);
 				node->count++;
+				slot->path |= offset << RADIX_TREE_HEIGHT_SHIFT;
 			} else
 				rcu_assign_pointer(root->rnode, ptr_to_indirect(slot));
 		}
@@ -498,7 +500,7 @@ void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index,
 	}
 	node = indirect_to_ptr(node);
 
-	height = node->height;
+	height = node->path & RADIX_TREE_HEIGHT_MASK;
 	if (index > radix_tree_maxindex(height))
 		return NULL;
 
@@ -704,7 +706,7 @@ int radix_tree_tag_get(struct radix_tree_root *root,
 		return (index == 0);
 	node = indirect_to_ptr(node);
 
-	height = node->height;
+	height = node->path & RADIX_TREE_HEIGHT_MASK;
 	if (index > radix_tree_maxindex(height))
 		return 0;
 
@@ -741,7 +743,7 @@ void **radix_tree_next_chunk(struct radix_tree_root *root,
 {
 	unsigned shift, tag = flags & RADIX_TREE_ITER_TAG_MASK;
 	struct radix_tree_node *rnode, *node;
-	unsigned long index, offset;
+	unsigned long index, offset, height;
 
 	if ((flags & RADIX_TREE_ITER_TAGGED) && !root_tag_get(root, tag))
 		return NULL;
@@ -772,7 +774,8 @@ void **radix_tree_next_chunk(struct radix_tree_root *root,
 		return NULL;
 
 restart:
-	shift = (rnode->height - 1) * RADIX_TREE_MAP_SHIFT;
+	height = rnode->path & RADIX_TREE_HEIGHT_MASK;
+	shift = (height - 1) * RADIX_TREE_MAP_SHIFT;
 	offset = index >> shift;
 
 	/* Index outside of the tree */
@@ -1142,7 +1145,7 @@ static unsigned long __locate(struct radix_tree_node *slot, void *item,
 	unsigned int shift, height;
 	unsigned long i;
 
-	height = slot->height;
+	height = slot->path & RADIX_TREE_HEIGHT_MASK;
 	shift = (height-1) * RADIX_TREE_MAP_SHIFT;
 
 	for ( ; height > 1; height--) {
@@ -1205,7 +1208,8 @@ unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item)
 		}
 
 		node = indirect_to_ptr(node);
-		max_index = radix_tree_maxindex(node->height);
+		max_index = radix_tree_maxindex(node->path &
+						RADIX_TREE_HEIGHT_MASK);
 		if (cur_index > max_index) {
 			rcu_read_unlock();
 			break;
@@ -1301,7 +1305,7 @@ static inline void radix_tree_shrink(struct radix_tree_root *root)
  *
  *	Returns %true if @node was freed, %false otherwise.
  */
-bool __radix_tree_delete_node(struct radix_tree_root *root, unsigned long index,
+bool __radix_tree_delete_node(struct radix_tree_root *root,
 			      struct radix_tree_node *node)
 {
 	bool deleted = false;
@@ -1320,9 +1324,10 @@ bool __radix_tree_delete_node(struct radix_tree_root *root, unsigned long index,
 
 		parent = node->parent;
 		if (parent) {
-			index >>= RADIX_TREE_MAP_SHIFT;
+			unsigned int offset;
 
-			parent->slots[index & RADIX_TREE_MAP_MASK] = NULL;
+			offset = node->path >> RADIX_TREE_HEIGHT_SHIFT;
+			parent->slots[offset] = NULL;
 			parent->count--;
 		} else {
 			root_tag_clear_all(root);
@@ -1386,7 +1391,7 @@ void *radix_tree_delete_item(struct radix_tree_root *root,
 	node->slots[offset] = NULL;
 	node->count--;
 
-	__radix_tree_delete_node(root, index, node);
+	__radix_tree_delete_node(root, node);
 
 	return entry;
 }
@@ -1419,9 +1424,12 @@ int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag)
 EXPORT_SYMBOL(radix_tree_tagged);
 
 static void
-radix_tree_node_ctor(void *node)
+radix_tree_node_ctor(void *arg)
 {
-	memset(node, 0, sizeof(struct radix_tree_node));
+	struct radix_tree_node *node = arg;
+
+	memset(node, 0, sizeof(*node));
+	INIT_LIST_HEAD(&node->private_list);
 }
 
 static __init unsigned long __maxindex(unsigned int height)
diff --git a/mm/filemap.c b/mm/filemap.c
index a603c4d7d3c9..d6df3bacb0fb 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -110,11 +110,17 @@
 static void page_cache_tree_delete(struct address_space *mapping,
 				   struct page *page, void *shadow)
 {
-	if (shadow) {
-		void **slot;
+	struct radix_tree_node *node;
+	unsigned long index;
+	unsigned int offset;
+	unsigned int tag;
+	void **slot;
 
-		slot = radix_tree_lookup_slot(&mapping->page_tree, page->index);
-		radix_tree_replace_slot(slot, shadow);
+	VM_BUG_ON(!PageLocked(page));
+
+	__radix_tree_lookup(&mapping->page_tree, page->index, &node, &slot);
+
+	if (shadow) {
 		mapping->nrshadows++;
 		/*
 		 * Make sure the nrshadows update is committed before
@@ -123,9 +129,45 @@ static void page_cache_tree_delete(struct address_space *mapping,
 		 * same time and miss a shadow entry.
 		 */
 		smp_wmb();
-	} else
-		radix_tree_delete(&mapping->page_tree, page->index);
+	}
 	mapping->nrpages--;
+
+	if (!node) {
+		/* Clear direct pointer tags in root node */
+		mapping->page_tree.gfp_mask &= __GFP_BITS_MASK;
+		radix_tree_replace_slot(slot, shadow);
+		return;
+	}
+
+	/* Clear tree tags for the removed page */
+	index = page->index;
+	offset = index & RADIX_TREE_MAP_MASK;
+	for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) {
+		if (test_bit(offset, node->tags[tag]))
+			radix_tree_tag_clear(&mapping->page_tree, index, tag);
+	}
+
+	/* Delete page, swap shadow entry */
+	radix_tree_replace_slot(slot, shadow);
+	workingset_node_pages_dec(node);
+	if (shadow)
+		workingset_node_shadows_inc(node);
+	else
+		if (__radix_tree_delete_node(&mapping->page_tree, node))
+			return;
+
+	/*
+	 * Track node that only contains shadow entries.
+	 *
+	 * Avoid acquiring the list_lru lock if already tracked.  The
+	 * list_empty() test is safe as node->private_list is
+	 * protected by mapping->tree_lock.
+	 */
+	if (!workingset_node_pages(node) &&
+	    list_empty(&node->private_list)) {
+		node->private_data = mapping;
+		list_lru_add(&workingset_shadow_nodes, &node->private_list);
+	}
 }
 
 /*
@@ -471,27 +513,43 @@ EXPORT_SYMBOL_GPL(replace_page_cache_page);
 static int page_cache_tree_insert(struct address_space *mapping,
 				  struct page *page, void **shadowp)
 {
+	struct radix_tree_node *node;
 	void **slot;
 	int error;
 
-	slot = radix_tree_lookup_slot(&mapping->page_tree, page->index);
-	if (slot) {
+	error = __radix_tree_create(&mapping->page_tree, page->index,
+				    &node, &slot);
+	if (error)
+		return error;
+	if (*slot) {
 		void *p;
 
 		p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
 		if (!radix_tree_exceptional_entry(p))
 			return -EEXIST;
-		radix_tree_replace_slot(slot, page);
-		mapping->nrshadows--;
-		mapping->nrpages++;
 		if (shadowp)
 			*shadowp = p;
-		return 0;
+		mapping->nrshadows--;
+		if (node)
+			workingset_node_shadows_dec(node);
 	}
-	error = radix_tree_insert(&mapping->page_tree, page->index, page);
-	if (!error)
-		mapping->nrpages++;
-	return error;
+	radix_tree_replace_slot(slot, page);
+	mapping->nrpages++;
+	if (node) {
+		workingset_node_pages_inc(node);
+		/*
+		 * Don't track node that contains actual pages.
+		 *
+		 * Avoid acquiring the list_lru lock if already
+		 * untracked.  The list_empty() test is safe as
+		 * node->private_list is protected by
+		 * mapping->tree_lock.
+		 */
+		if (!list_empty(&node->private_list))
+			list_lru_del(&workingset_shadow_nodes,
+				     &node->private_list);
+	}
+	return 0;
 }
 
 static int __add_to_page_cache_locked(struct page *page,
diff --git a/mm/list_lru.c b/mm/list_lru.c
index 72f9decb0104..f1a0db194173 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -87,11 +87,20 @@ restart:
 
 		ret = isolate(item, &nlru->lock, cb_arg);
 		switch (ret) {
+		case LRU_REMOVED_RETRY:
+			assert_spin_locked(&nlru->lock);
 		case LRU_REMOVED:
 			if (--nlru->nr_items == 0)
 				node_clear(nid, lru->active_nodes);
 			WARN_ON_ONCE(nlru->nr_items < 0);
 			isolated++;
+			/*
+			 * If the lru lock has been dropped, our list
+			 * traversal is now invalid and so we have to
+			 * restart from scratch.
+			 */
+			if (ret == LRU_REMOVED_RETRY)
+				goto restart;
 			break;
 		case LRU_ROTATE:
 			list_move_tail(item, &nlru->list);
@@ -103,6 +112,7 @@ restart:
 			 * The lru lock has been dropped, our list traversal is
 			 * now invalid and so we have to restart from scratch.
 			 */
+			assert_spin_locked(&nlru->lock);
 			goto restart;
 		default:
 			BUG();
@@ -114,7 +124,7 @@ restart:
 }
 EXPORT_SYMBOL_GPL(list_lru_walk_node);
 
-int list_lru_init(struct list_lru *lru)
+int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key)
 {
 	int i;
 	size_t size = sizeof(*lru->node) * nr_node_ids;
@@ -126,12 +136,14 @@ int list_lru_init(struct list_lru *lru)
 	nodes_clear(lru->active_nodes);
 	for (i = 0; i < nr_node_ids; i++) {
 		spin_lock_init(&lru->node[i].lock);
+		if (key)
+			lockdep_set_class(&lru->node[i].lock, key);
 		INIT_LIST_HEAD(&lru->node[i].list);
 		lru->node[i].nr_items = 0;
 	}
 	return 0;
 }
-EXPORT_SYMBOL_GPL(list_lru_init);
+EXPORT_SYMBOL_GPL(list_lru_init_key);
 
 void list_lru_destroy(struct list_lru *lru)
 {
diff --git a/mm/truncate.c b/mm/truncate.c
index 0db9258319f0..e5cc39ab0751 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -25,6 +25,9 @@
 static void clear_exceptional_entry(struct address_space *mapping,
 				    pgoff_t index, void *entry)
 {
+	struct radix_tree_node *node;
+	void **slot;
+
 	/* Handled by shmem itself */
 	if (shmem_mapping(mapping))
 		return;
@@ -35,8 +38,27 @@ static void clear_exceptional_entry(struct address_space *mapping,
 	 * without the tree itself locked.  These unlocked entries
 	 * need verification under the tree lock.
 	 */
-	if (radix_tree_delete_item(&mapping->page_tree, index, entry) == entry)
-		mapping->nrshadows--;
+	if (!__radix_tree_lookup(&mapping->page_tree, index, &node, &slot))
+		goto unlock;
+	if (*slot != entry)
+		goto unlock;
+	radix_tree_replace_slot(slot, NULL);
+	mapping->nrshadows--;
+	if (!node)
+		goto unlock;
+	workingset_node_shadows_dec(node);
+	/*
+	 * Don't track node without shadow entries.
+	 *
+	 * Avoid acquiring the list_lru lock if already untracked.
+	 * The list_empty() test is safe as node->private_list is
+	 * protected by mapping->tree_lock.
+	 */
+	if (!workingset_node_shadows(node) &&
+	    !list_empty(&node->private_list))
+		list_lru_del(&workingset_shadow_nodes, &node->private_list);
+	__radix_tree_delete_node(&mapping->page_tree, node);
+unlock:
 	spin_unlock_irq(&mapping->tree_lock);
 }
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 843125a0e255..f3155d51acfd 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -772,6 +772,7 @@ const char * const vmstat_text[] = {
 #endif
 	"workingset_refault",
 	"workingset_activate",
+	"workingset_nodereclaim",
 	"nr_anon_transparent_hugepages",
 	"nr_free_cma",
 	"nr_dirty_threshold",
diff --git a/mm/workingset.c b/mm/workingset.c
index 8a6c7cff4923..f7216fa7da27 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -251,3 +251,164 @@ void workingset_activation(struct page *page)
 {
 	atomic_long_inc(&page_zone(page)->inactive_age);
 }
+
+/*
+ * Shadow entries reflect the share of the working set that does not
+ * fit into memory, so their number depends on the access pattern of
+ * the workload.  In most cases, they will refault or get reclaimed
+ * along with the inode, but a (malicious) workload that streams
+ * through files with a total size several times that of available
+ * memory, while preventing the inodes from being reclaimed, can
+ * create excessive amounts of shadow nodes.  To keep a lid on this,
+ * track shadow nodes and reclaim them when they grow way past the
+ * point where they would still be useful.
+ */
+
+struct list_lru workingset_shadow_nodes;
+
+static unsigned long count_shadow_nodes(struct shrinker *shrinker,
+					struct shrink_control *sc)
+{
+	unsigned long shadow_nodes;
+	unsigned long max_nodes;
+	unsigned long pages;
+
+	/* list_lru lock nests inside IRQ-safe mapping->tree_lock */
+	local_irq_disable();
+	shadow_nodes = list_lru_count_node(&workingset_shadow_nodes, sc->nid);
+	local_irq_enable();
+
+	pages = node_present_pages(sc->nid);
+	/*
+	 * Active cache pages are limited to 50% of memory, and shadow
+	 * entries that represent a refault distance bigger than that
+	 * do not have any effect.  Limit the number of shadow nodes
+	 * such that shadow entries do not exceed the number of active
+	 * cache pages, assuming a worst-case node population density
+	 * of 1/8th on average.
+	 *
+	 * On 64-bit with 7 radix_tree_nodes per page and 64 slots
+	 * each, this will reclaim shadow entries when they consume
+	 * ~2% of available memory:
+	 *
+	 * PAGE_SIZE / radix_tree_nodes / node_entries / PAGE_SIZE
+	 */
+	max_nodes = pages >> (1 + RADIX_TREE_MAP_SHIFT - 3);
+
+	if (shadow_nodes <= max_nodes)
+		return 0;
+
+	return shadow_nodes - max_nodes;
+}
+
+static enum lru_status shadow_lru_isolate(struct list_head *item,
+					  spinlock_t *lru_lock,
+					  void *arg)
+{
+	struct address_space *mapping;
+	struct radix_tree_node *node;
+	unsigned int i;
+	int ret;
+
+	/*
+	 * Page cache insertions and deletions synchroneously maintain
+	 * the shadow node LRU under the mapping->tree_lock and the
+	 * lru_lock.  Because the page cache tree is emptied before
+	 * the inode can be destroyed, holding the lru_lock pins any
+	 * address_space that has radix tree nodes on the LRU.
+	 *
+	 * We can then safely transition to the mapping->tree_lock to
+	 * pin only the address_space of the particular node we want
+	 * to reclaim, take the node off-LRU, and drop the lru_lock.
+	 */
+
+	node = container_of(item, struct radix_tree_node, private_list);
+	mapping = node->private_data;
+
+	/* Coming from the list, invert the lock order */
+	if (!spin_trylock(&mapping->tree_lock)) {
+		spin_unlock(lru_lock);
+		ret = LRU_RETRY;
+		goto out;
+	}
+
+	list_del_init(item);
+	spin_unlock(lru_lock);
+
+	/*
+	 * The nodes should only contain one or more shadow entries,
+	 * no pages, so we expect to be able to remove them all and
+	 * delete and free the empty node afterwards.
+	 */
+
+	BUG_ON(!node->count);
+	BUG_ON(node->count & RADIX_TREE_COUNT_MASK);
+
+	for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) {
+		if (node->slots[i]) {
+			BUG_ON(!radix_tree_exceptional_entry(node->slots[i]));
+			node->slots[i] = NULL;
+			BUG_ON(node->count < (1U << RADIX_TREE_COUNT_SHIFT));
+			node->count -= 1U << RADIX_TREE_COUNT_SHIFT;
+			BUG_ON(!mapping->nrshadows);
+			mapping->nrshadows--;
+		}
+	}
+	BUG_ON(node->count);
+	inc_zone_state(page_zone(virt_to_page(node)), WORKINGSET_NODERECLAIM);
+	if (!__radix_tree_delete_node(&mapping->page_tree, node))
+		BUG();
+
+	spin_unlock(&mapping->tree_lock);
+	ret = LRU_REMOVED_RETRY;
+out:
+	local_irq_enable();
+	cond_resched();
+	local_irq_disable();
+	spin_lock(lru_lock);
+	return ret;
+}
+
+static unsigned long scan_shadow_nodes(struct shrinker *shrinker,
+				       struct shrink_control *sc)
+{
+	unsigned long ret;
+
+	/* list_lru lock nests inside IRQ-safe mapping->tree_lock */
+	local_irq_disable();
+	ret =  list_lru_walk_node(&workingset_shadow_nodes, sc->nid,
+				  shadow_lru_isolate, NULL, &sc->nr_to_scan);
+	local_irq_enable();
+	return ret;
+}
+
+static struct shrinker workingset_shadow_shrinker = {
+	.count_objects = count_shadow_nodes,
+	.scan_objects = scan_shadow_nodes,
+	.seeks = DEFAULT_SEEKS,
+	.flags = SHRINKER_NUMA_AWARE,
+};
+
+/*
+ * Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe
+ * mapping->tree_lock.
+ */
+static struct lock_class_key shadow_nodes_key;
+
+static int __init workingset_init(void)
+{
+	int ret;
+
+	ret = list_lru_init_key(&workingset_shadow_nodes, &shadow_nodes_key);
+	if (ret)
+		goto err;
+	ret = register_shrinker(&workingset_shadow_shrinker);
+	if (ret)
+		goto err_list_lru;
+	return 0;
+err_list_lru:
+	list_lru_destroy(&workingset_shadow_nodes);
+err:
+	return ret;
+}
+module_init(workingset_init);
-- 
cgit v1.2.3


From c558784fa9e65363ed32cf6ff137c89bc8b54f81 Mon Sep 17 00:00:00 2001
From: Rashika Kheria <rashika.kheria@gmail.com>
Date: Thu, 3 Apr 2014 14:48:07 -0700
Subject: include/linux/mm.h: remove ifdef condition

The ifdef conditions in include/linux/mm.h presents three cases:

 - !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID)

   There is no actual definition of function but include/linux/mm.h has a
   static inline stub defined.

 - defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID)

   linux/mm.h does not define a prototype, but mm/page_alloc.c defines
   the function.

   Hence, compiler reports the following warning:

     mm/page_alloc.c:4300:15: warning: no previous prototype for `__early_pfn_to_nid' [-Wmissing-prototypes]

 - defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID)

   The architecture defines the function, and linux/mm.h has a
   prototype.

Thus, join the conditions of Case 2 and 3 ie eliminate the ifdef
condition of CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID to eliminate the missing
prototype warning from file mm/page_alloc.c.

Signed-off-by: Rashika Kheria <rashika.kheria@gmail.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 58d6ddba5db3..35300f390eb6 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1666,10 +1666,8 @@ static inline int __early_pfn_to_nid(unsigned long pfn)
 #else
 /* please see mm/page_alloc.c */
 extern int __meminit early_pfn_to_nid(unsigned long pfn);
-#ifdef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
 /* there is a per-arch backend function. */
 extern int __meminit __early_pfn_to_nid(unsigned long pfn);
-#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
 #endif
 
 extern void set_dma_reserve(unsigned long new_dma_reserve);
-- 
cgit v1.2.3


From 67f9fd91f93c582b7de2ab9325b6e179db77e4d5 Mon Sep 17 00:00:00 2001
From: Sasha Levin <sasha.levin@oracle.com>
Date: Thu, 3 Apr 2014 14:48:18 -0700
Subject: mm: remove read_cache_page_async()

This patch removes read_cache_page_async() which wasn't really needed
anywhere and simplifies the code around it a bit.

read_cache_page_async() is useful when we want to read a page into the
cache without waiting for it to complete.  This happens when the
appropriate callback 'filler' doesn't complete its read operation and
releases the page lock immediately, and instead queues a different
completion routine to do that.  This never actually happened anywhere in
the code.

read_cache_page_async() had 3 different callers:

- read_cache_page() which is the sync version, it would just wait for
  the requested read to complete using wait_on_page_read().

- JFFS2 would call it from jffs2_gc_fetch_page(), but the filler
  function it supplied doesn't do any async reads, and would complete
  before the filler function returns - making it actually a sync read.

- CRAMFS would call it using the read_mapping_page_async() wrapper, with
  a similar story to JFFS2 - the filler function doesn't do anything that
  reminds async reads and would always complete before the filler function
  returns.

To sum it up, the code in mm/filemap.c never took advantage of having
read_cache_page_async().  While there are filler callbacks that do async
reads (such as the block one), we always called it with the
read_cache_page().

This patch adds a mandatory wait for read to complete when adding a new
page to the cache, and removes read_cache_page_async() and its wrappers.

Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/cramfs/inode.c       |  3 +--
 fs/jffs2/fs.c           |  2 +-
 include/linux/pagemap.h | 10 --------
 mm/filemap.c            | 64 ++++++++++++++++++-------------------------------
 4 files changed, 25 insertions(+), 54 deletions(-)

(limited to 'include/linux')

diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 06610cf94d57..a1f801c14fbc 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -195,8 +195,7 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i
 		struct page *page = NULL;
 
 		if (blocknr + i < devsize) {
-			page = read_mapping_page_async(mapping, blocknr + i,
-									NULL);
+			page = read_mapping_page(mapping, blocknr + i, NULL);
 			/* synchronous error? */
 			if (IS_ERR(page))
 				page = NULL;
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index a012e16a8bb3..f73991522672 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -687,7 +687,7 @@ unsigned char *jffs2_gc_fetch_page(struct jffs2_sb_info *c,
 	struct inode *inode = OFNI_EDONI_2SFFJ(f);
 	struct page *pg;
 
-	pg = read_cache_page_async(inode->i_mapping, offset >> PAGE_CACHE_SHIFT,
+	pg = read_cache_page(inode->i_mapping, offset >> PAGE_CACHE_SHIFT,
 			     (void *)jffs2_do_readpage_unlock, inode);
 	if (IS_ERR(pg))
 		return (void *)pg;
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index ff43253f568a..45598f1e9aa3 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -289,8 +289,6 @@ static inline struct page *grab_cache_page(struct address_space *mapping,
 
 extern struct page * grab_cache_page_nowait(struct address_space *mapping,
 				pgoff_t index);
-extern struct page * read_cache_page_async(struct address_space *mapping,
-				pgoff_t index, filler_t *filler, void *data);
 extern struct page * read_cache_page(struct address_space *mapping,
 				pgoff_t index, filler_t *filler, void *data);
 extern struct page * read_cache_page_gfp(struct address_space *mapping,
@@ -298,14 +296,6 @@ extern struct page * read_cache_page_gfp(struct address_space *mapping,
 extern int read_cache_pages(struct address_space *mapping,
 		struct list_head *pages, filler_t *filler, void *data);
 
-static inline struct page *read_mapping_page_async(
-				struct address_space *mapping,
-				pgoff_t index, void *data)
-{
-	filler_t *filler = (filler_t *)mapping->a_ops->readpage;
-	return read_cache_page_async(mapping, index, filler, data);
-}
-
 static inline struct page *read_mapping_page(struct address_space *mapping,
 				pgoff_t index, void *data)
 {
diff --git a/mm/filemap.c b/mm/filemap.c
index d6df3bacb0fb..21781f1fe52b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2133,6 +2133,18 @@ int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma)
 EXPORT_SYMBOL(generic_file_mmap);
 EXPORT_SYMBOL(generic_file_readonly_mmap);
 
+static struct page *wait_on_page_read(struct page *page)
+{
+	if (!IS_ERR(page)) {
+		wait_on_page_locked(page);
+		if (!PageUptodate(page)) {
+			page_cache_release(page);
+			page = ERR_PTR(-EIO);
+		}
+	}
+	return page;
+}
+
 static struct page *__read_cache_page(struct address_space *mapping,
 				pgoff_t index,
 				int (*filler)(void *, struct page *),
@@ -2159,6 +2171,8 @@ repeat:
 		if (err < 0) {
 			page_cache_release(page);
 			page = ERR_PTR(err);
+		} else {
+			page = wait_on_page_read(page);
 		}
 	}
 	return page;
@@ -2195,6 +2209,10 @@ retry:
 	if (err < 0) {
 		page_cache_release(page);
 		return ERR_PTR(err);
+	} else {
+		page = wait_on_page_read(page);
+		if (IS_ERR(page))
+			return page;
 	}
 out:
 	mark_page_accessed(page);
@@ -2202,40 +2220,25 @@ out:
 }
 
 /**
- * read_cache_page_async - read into page cache, fill it if needed
+ * read_cache_page - read into page cache, fill it if needed
  * @mapping:	the page's address_space
  * @index:	the page index
  * @filler:	function to perform the read
  * @data:	first arg to filler(data, page) function, often left as NULL
  *
- * Same as read_cache_page, but don't wait for page to become unlocked
- * after submitting it to the filler.
- *
  * Read into the page cache. If a page already exists, and PageUptodate() is
- * not set, try to fill the page but don't wait for it to become unlocked.
+ * not set, try to fill the page and wait for it to become unlocked.
  *
  * If the page does not get brought uptodate, return -EIO.
  */
-struct page *read_cache_page_async(struct address_space *mapping,
+struct page *read_cache_page(struct address_space *mapping,
 				pgoff_t index,
 				int (*filler)(void *, struct page *),
 				void *data)
 {
 	return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping));
 }
-EXPORT_SYMBOL(read_cache_page_async);
-
-static struct page *wait_on_page_read(struct page *page)
-{
-	if (!IS_ERR(page)) {
-		wait_on_page_locked(page);
-		if (!PageUptodate(page)) {
-			page_cache_release(page);
-			page = ERR_PTR(-EIO);
-		}
-	}
-	return page;
-}
+EXPORT_SYMBOL(read_cache_page);
 
 /**
  * read_cache_page_gfp - read into page cache, using specified page allocation flags.
@@ -2254,31 +2257,10 @@ struct page *read_cache_page_gfp(struct address_space *mapping,
 {
 	filler_t *filler = (filler_t *)mapping->a_ops->readpage;
 
-	return wait_on_page_read(do_read_cache_page(mapping, index, filler, NULL, gfp));
+	return do_read_cache_page(mapping, index, filler, NULL, gfp);
 }
 EXPORT_SYMBOL(read_cache_page_gfp);
 
-/**
- * read_cache_page - read into page cache, fill it if needed
- * @mapping:	the page's address_space
- * @index:	the page index
- * @filler:	function to perform the read
- * @data:	first arg to filler(data, page) function, often left as NULL
- *
- * Read into the page cache. If a page already exists, and PageUptodate() is
- * not set, try to fill the page then wait for it to become unlocked.
- *
- * If the page does not get brought uptodate, return -EIO.
- */
-struct page *read_cache_page(struct address_space *mapping,
-				pgoff_t index,
-				int (*filler)(void *, struct page *),
-				void *data)
-{
-	return wait_on_page_read(read_cache_page_async(mapping, index, filler, data));
-}
-EXPORT_SYMBOL(read_cache_page);
-
 static size_t __iovec_copy_from_user_inatomic(char *vaddr,
 			const struct iovec *iov, size_t base, size_t bytes)
 {
-- 
cgit v1.2.3


From 5509a5d27b971a90b940e148ca9ca53312e4fa7a Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave@linux.vnet.ibm.com>
Date: Thu, 3 Apr 2014 14:48:19 -0700
Subject: drop_caches: add some documentation and info message

There is plenty of anecdotal evidence and a load of blog posts
suggesting that using "drop_caches" periodically keeps your system
running in "tip top shape".  Perhaps adding some kernel documentation
will increase the amount of accurate data on its use.

If we are not shrinking caches effectively, then we have real bugs.
Using drop_caches will simply mask the bugs and make them harder to
find, but certainly does not fix them, nor is it an appropriate
"workaround" to limit the size of the caches.  On the contrary, there
have been bug reports on issues that turned out to be misguided use of
cache dropping.

Dropping caches is a very drastic and disruptive operation that is good
for debugging and running tests, but if it creates bug reports from
production use, kernel developers should be aware of its use.

Add a bit more documentation about it, a syslog message to track down
abusers, and vmstat drop counters to help analyze problem reports.

[akpm@linux-foundation.org: checkpatch fixes]
[hannes@cmpxchg.org: add runtime suppression control]
Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com>
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/sysctl/vm.txt   | 33 +++++++++++++++++++++++++++------
 fs/drop_caches.c              | 16 ++++++++++++++--
 include/linux/vm_event_item.h |  1 +
 kernel/sysctl.c               |  4 ++--
 mm/vmstat.c                   |  3 +++
 5 files changed, 47 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index d614a9b6a280..dd9d0e33b443 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -175,18 +175,39 @@ Setting this to zero disables periodic writeback altogether.
 
 drop_caches
 
-Writing to this will cause the kernel to drop clean caches, dentries and
-inodes from memory, causing that memory to become free.
+Writing to this will cause the kernel to drop clean caches, as well as
+reclaimable slab objects like dentries and inodes.  Once dropped, their
+memory becomes free.
 
 To free pagecache:
 	echo 1 > /proc/sys/vm/drop_caches
-To free dentries and inodes:
+To free reclaimable slab objects (includes dentries and inodes):
 	echo 2 > /proc/sys/vm/drop_caches
-To free pagecache, dentries and inodes:
+To free slab objects and pagecache:
 	echo 3 > /proc/sys/vm/drop_caches
 
-As this is a non-destructive operation and dirty objects are not freeable, the
-user should run `sync' first.
+This is a non-destructive operation and will not free any dirty objects.
+To increase the number of objects freed by this operation, the user may run
+`sync' prior to writing to /proc/sys/vm/drop_caches.  This will minimize the
+number of dirty objects on the system and create more candidates to be
+dropped.
+
+This file is not a means to control the growth of the various kernel caches
+(inodes, dentries, pagecache, etc...)  These objects are automatically
+reclaimed by the kernel when memory is needed elsewhere on the system.
+
+Use of this file can cause performance problems.  Since it discards cached
+objects, it may cost a significant amount of I/O and CPU to recreate the
+dropped objects, especially if they were under heavy use.  Because of this,
+use outside of a testing or debugging environment is not recommended.
+
+You may see informational messages in your kernel log when this file is
+used:
+
+	cat (1234): drop_caches: 3
+
+These are informational only.  They do not mean that anything is wrong
+with your system.  To disable them, echo 4 (bit 3) into drop_caches.
 
 ==============================================================
 
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 9fd702f5bfb2..9280202e488c 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -59,10 +59,22 @@ int drop_caches_sysctl_handler(ctl_table *table, int write,
 	if (ret)
 		return ret;
 	if (write) {
-		if (sysctl_drop_caches & 1)
+		static int stfu;
+
+		if (sysctl_drop_caches & 1) {
 			iterate_supers(drop_pagecache_sb, NULL);
-		if (sysctl_drop_caches & 2)
+			count_vm_event(DROP_PAGECACHE);
+		}
+		if (sysctl_drop_caches & 2) {
 			drop_slab();
+			count_vm_event(DROP_SLAB);
+		}
+		if (!stfu) {
+			pr_info("%s (%d): drop_caches: %d\n",
+				current->comm, task_pid_nr(current),
+				sysctl_drop_caches);
+		}
+		stfu |= sysctl_drop_caches & 4;
 	}
 	return 0;
 }
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 3a712e2e7d76..486c3972c0be 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -37,6 +37,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL,
 		KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY,
 		PAGEOUTRUN, ALLOCSTALL, PGROTATED,
+		DROP_PAGECACHE, DROP_SLAB,
 #ifdef CONFIG_NUMA_BALANCING
 		NUMA_PTE_UPDATES,
 		NUMA_HUGE_PTE_UPDATES,
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 09d2e2413605..5c14b547882e 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -123,7 +123,7 @@ static int __maybe_unused neg_one = -1;
 static int zero;
 static int __maybe_unused one = 1;
 static int __maybe_unused two = 2;
-static int __maybe_unused three = 3;
+static int __maybe_unused four = 4;
 static unsigned long one_ul = 1;
 static int one_hundred = 100;
 #ifdef CONFIG_PRINTK
@@ -1264,7 +1264,7 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= drop_caches_sysctl_handler,
 		.extra1		= &one,
-		.extra2		= &three,
+		.extra2		= &four,
 	},
 #ifdef CONFIG_COMPACTION
 	{
diff --git a/mm/vmstat.c b/mm/vmstat.c
index f3155d51acfd..197b4c4a9587 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -813,6 +813,9 @@ const char * const vmstat_text[] = {
 
 	"pgrotated",
 
+	"drop_pagecache",
+	"drop_slab",
+
 #ifdef CONFIG_NUMA_BALANCING
 	"numa_pte_updates",
 	"numa_huge_pte_updates",
-- 
cgit v1.2.3


From bcccff93af359533683603255124fc19eb12613d Mon Sep 17 00:00:00 2001
From: Vladimir Davydov <vdavydov@parallels.com>
Date: Thu, 3 Apr 2014 14:48:21 -0700
Subject: kobject: don't block for each kobject_uevent

Currently kobject_uevent has somewhat unpredictable semantics.  The
point is, since it may call a usermode helper and wait for it to execute
(UMH_WAIT_EXEC), it is impossible to say for sure what lock dependencies
it will introduce for the caller - strictly speaking it depends on what
fs the binary is located on and the set of locks fork may take.  There
are quite a few kobject_uevent's users that do not take this into
account and call it with various mutexes taken, e.g.  rtnl_mutex,
net_mutex, which might potentially lead to a deadlock.

Since there is actually no reason to wait for the usermode helper to
execute there, let's make kobject_uevent start the helper asynchronously
with the aid of the UMH_NO_WAIT flag.

Personally, I'm interested in this, because I really want kobject_uevent
to be called under the slab_mutex in the slub implementation as it used
to be some time ago, because it greatly simplifies synchronization and
automatically fixes a kmemcg-related race.  However, there was a
deadlock detected on an attempt to call kobject_uevent under the
slab_mutex (see https://lkml.org/lkml/2012/1/14/45), which was reported
to be fixed by releasing the slab_mutex for kobject_uevent.

Unfortunately, there was no information about who exactly blocked on the
slab_mutex causing the usermode helper to stall, neither have I managed
to find this out or reproduce the issue.

BTW, this is not the first attempt to make kobject_uevent use
UMH_NO_WAIT.  Previous one was made by commit f520360d93cd ("kobject:
don't block for each kobject_uevent"), but it was wrong (it passed
arguments allocated on stack to async thread) so it was reverted in
05f54c13cd0c ("Revert "kobject: don't block for each kobject_uevent".").
It targeted on speeding up the boot process though.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Greg KH <greg@kroah.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kobject.h |  1 +
 lib/kobject_uevent.c    | 42 ++++++++++++++++++++++++++++++++++++------
 2 files changed, 37 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kobject.h b/include/linux/kobject.h
index 926afb6f6b5f..f896a33e8341 100644
--- a/include/linux/kobject.h
+++ b/include/linux/kobject.h
@@ -119,6 +119,7 @@ struct kobj_type {
 };
 
 struct kobj_uevent_env {
+	char *argv[3];
 	char *envp[UEVENT_NUM_ENVP];
 	int envp_idx;
 	char buf[UEVENT_BUFFER_SIZE];
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 5f72767ddd9b..4e3bd71bd949 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -124,6 +124,30 @@ static int kobj_usermode_filter(struct kobject *kobj)
 	return 0;
 }
 
+static int init_uevent_argv(struct kobj_uevent_env *env, const char *subsystem)
+{
+	int len;
+
+	len = strlcpy(&env->buf[env->buflen], subsystem,
+		      sizeof(env->buf) - env->buflen);
+	if (len >= (sizeof(env->buf) - env->buflen)) {
+		WARN(1, KERN_ERR "init_uevent_argv: buffer size too small\n");
+		return -ENOMEM;
+	}
+
+	env->argv[0] = uevent_helper;
+	env->argv[1] = &env->buf[env->buflen];
+	env->argv[2] = NULL;
+
+	env->buflen += len + 1;
+	return 0;
+}
+
+static void cleanup_uevent_env(struct subprocess_info *info)
+{
+	kfree(info->data);
+}
+
 /**
  * kobject_uevent_env - send an uevent with environmental data
  *
@@ -301,11 +325,8 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 
 	/* call uevent_helper, usually only enabled during early boot */
 	if (uevent_helper[0] && !kobj_usermode_filter(kobj)) {
-		char *argv [3];
+		struct subprocess_info *info;
 
-		argv [0] = uevent_helper;
-		argv [1] = (char *)subsystem;
-		argv [2] = NULL;
 		retval = add_uevent_var(env, "HOME=/");
 		if (retval)
 			goto exit;
@@ -313,9 +334,18 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 					"PATH=/sbin:/bin:/usr/sbin:/usr/bin");
 		if (retval)
 			goto exit;
+		retval = init_uevent_argv(env, subsystem);
+		if (retval)
+			goto exit;
 
-		retval = call_usermodehelper(argv[0], argv,
-					     env->envp, UMH_WAIT_EXEC);
+		retval = -ENOMEM;
+		info = call_usermodehelper_setup(env->argv[0], env->argv,
+						 env->envp, GFP_KERNEL,
+						 NULL, cleanup_uevent_env, env);
+		if (info) {
+			retval = call_usermodehelper_exec(info, UMH_NO_WAIT);
+			env = NULL;	/* freed by cleanup_uevent_env */
+		}
 	}
 
 exit:
-- 
cgit v1.2.3


From e3a0cfdc8c8904236f91a506c1e760b0d60dd918 Mon Sep 17 00:00:00 2001
From: Rashika Kheria <rashika.kheria@gmail.com>
Date: Thu, 3 Apr 2014 14:48:24 -0700
Subject: include/linux/syscalls.h: add sys32_quotactl() prototype

This eliminates the following warning in quota/compat.c:

  fs/quota/compat.c:43:17: warning: no previous prototype for `sys32_quotactl' [-Wmissing-prototypes]

Signed-off-by: Rashika Kheria <rashika.kheria@gmail.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/syscalls.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 1e67b7a5968c..2aa8b749f13d 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -200,6 +200,8 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 	}								\
 	static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__))
 
+asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special,
+			       qid_t id, void __user *addr);
 asmlinkage long sys_time(time_t __user *tloc);
 asmlinkage long sys_stime(time_t __user *tptr);
 asmlinkage long sys_gettimeofday(struct timeval __user *tv,
-- 
cgit v1.2.3


From 8f6c5ffc8987f4f5b5a3e9d557d94bbf3a9bf216 Mon Sep 17 00:00:00 2001
From: Wang YanQing <udknight@gmail.com>
Date: Thu, 3 Apr 2014 14:48:26 -0700
Subject: kernel/groups.c: remove return value of set_groups

After commit 6307f8fee295 ("security: remove dead hook task_setgroups"),
set_groups will always return zero, so we could just remove return value
of set_groups.

This patch reduces code size, and simplfies code to use set_groups,
because we don't need to check its return value any more.

[akpm@linux-foundation.org: remove obsolete claims from set_groups() comment]
Signed-off-by: Wang YanQing <udknight@gmail.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Serge Hallyn <serge.hallyn@canonical.com>
Cc: Eric Paris <eparis@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/nfsd/auth.c       |  5 +----
 include/linux/cred.h |  2 +-
 kernel/groups.c      | 14 ++------------
 3 files changed, 4 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c
index 06cddd572264..2645be435e75 100644
--- a/fs/nfsd/auth.c
+++ b/fs/nfsd/auth.c
@@ -71,10 +71,8 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
 	if (gid_eq(new->fsgid, INVALID_GID))
 		new->fsgid = exp->ex_anon_gid;
 
-	ret = set_groups(new, gi);
+	set_groups(new, gi);
 	put_group_info(gi);
-	if (ret < 0)
-		goto error;
 
 	if (!uid_eq(new->fsuid, GLOBAL_ROOT_UID))
 		new->cap_effective = cap_drop_nfsd_set(new->cap_effective);
@@ -89,7 +87,6 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
 
 oom:
 	ret = -ENOMEM;
-error:
 	abort_creds(new);
 	return ret;
 }
diff --git a/include/linux/cred.h b/include/linux/cred.h
index 04421e825365..f61d6c8f5ef3 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -66,7 +66,7 @@ extern struct group_info *groups_alloc(int);
 extern struct group_info init_groups;
 extern void groups_free(struct group_info *);
 extern int set_current_groups(struct group_info *);
-extern int set_groups(struct cred *, struct group_info *);
+extern void set_groups(struct cred *, struct group_info *);
 extern int groups_search(const struct group_info *, kgid_t);
 
 /* access the groups "array" with this macro */
diff --git a/kernel/groups.c b/kernel/groups.c
index 90cf1c38c8ea..451698f86cfa 100644
--- a/kernel/groups.c
+++ b/kernel/groups.c
@@ -157,17 +157,13 @@ int groups_search(const struct group_info *group_info, kgid_t grp)
  * set_groups - Change a group subscription in a set of credentials
  * @new: The newly prepared set of credentials to alter
  * @group_info: The group list to install
- *
- * Validate a group subscription and, if valid, insert it into a set
- * of credentials.
  */
-int set_groups(struct cred *new, struct group_info *group_info)
+void set_groups(struct cred *new, struct group_info *group_info)
 {
 	put_group_info(new->group_info);
 	groups_sort(group_info);
 	get_group_info(group_info);
 	new->group_info = group_info;
-	return 0;
 }
 
 EXPORT_SYMBOL(set_groups);
@@ -182,18 +178,12 @@ EXPORT_SYMBOL(set_groups);
 int set_current_groups(struct group_info *group_info)
 {
 	struct cred *new;
-	int ret;
 
 	new = prepare_creds();
 	if (!new)
 		return -ENOMEM;
 
-	ret = set_groups(new, group_info);
-	if (ret < 0) {
-		abort_creds(new);
-		return ret;
-	}
-
+	set_groups(new, group_info);
 	return commit_creds(new);
 }
 
-- 
cgit v1.2.3


From a5ed3cee944abf2c80ae146b06f9055d7da03f94 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Thu, 3 Apr 2014 14:48:31 -0700
Subject: err.h: use bool for IS_ERR and IS_ERR_OR_NULL

Use the more natural return of bool for these tests.

No difference observed in .o files produced by gcc for x86.

Remove the dentry description of kernel pointers left over from the 90's
and 2002's cleanup move of parts of fs.h to err.h.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/err.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/err.h b/include/linux/err.h
index 15f92e072450..a729120644d5 100644
--- a/include/linux/err.h
+++ b/include/linux/err.h
@@ -2,12 +2,13 @@
 #define _LINUX_ERR_H
 
 #include <linux/compiler.h>
+#include <linux/types.h>
 
 #include <asm/errno.h>
 
 /*
  * Kernel pointers have redundant information, so we can use a
- * scheme where we can return either an error code or a dentry
+ * scheme where we can return either an error code or a normal
  * pointer with the same return value.
  *
  * This should be a per-architecture thing, to allow different
@@ -29,12 +30,12 @@ static inline long __must_check PTR_ERR(__force const void *ptr)
 	return (long) ptr;
 }
 
-static inline long __must_check IS_ERR(__force const void *ptr)
+static inline bool __must_check IS_ERR(__force const void *ptr)
 {
 	return IS_ERR_VALUE((unsigned long)ptr);
 }
 
-static inline long __must_check IS_ERR_OR_NULL(__force const void *ptr)
+static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr)
 {
 	return !ptr || IS_ERR_VALUE((unsigned long)ptr);
 }
-- 
cgit v1.2.3


From 0185698c0f543d4e8677bb97227ebe46024e3eb8 Mon Sep 17 00:00:00 2001
From: Petr Mladek <pmladek@suse.cz>
Date: Thu, 3 Apr 2014 14:48:38 -0700
Subject: printk: remove duplicated check for log level

The check for the exact log level is already done in printk_get_level.
We do not need to duplicate it in printk_skip_level.

Signed-off-by: Petr Mladek <pmladek@suse.cz>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Kay Sievers <kay@vrfy.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/printk.h | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/printk.h b/include/linux/printk.h
index fa47e2708c01..8860575899f2 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -24,13 +24,9 @@ static inline int printk_get_level(const char *buffer)
 
 static inline const char *printk_skip_level(const char *buffer)
 {
-	if (printk_get_level(buffer)) {
-		switch (buffer[1]) {
-		case '0' ... '7':
-		case 'd':	/* KERN_DEFAULT */
-			return buffer + 2;
-		}
-	}
+	if (printk_get_level(buffer))
+		return buffer + 2;
+
 	return buffer;
 }
 
-- 
cgit v1.2.3


From d487d57581057abd271651334ea2996aa1b31e28 Mon Sep 17 00:00:00 2001
From: Simon Kågström <simon.kagstrom@netinsight.net>
Date: Thu, 3 Apr 2014 14:48:44 -0700
Subject: include/linux/printk.h: remove double asmlinkage in printk_emit

The double asmlinkage was introduced in commit 7ff9554bb578 ("printk:
convert byte-buffer to variable-length record buffer").

Signed-off-by: Simon Kagstrom <simon.kagstrom@netinsight.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/printk.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/printk.h b/include/linux/printk.h
index 8860575899f2..8752f7595b27 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -120,9 +120,9 @@ asmlinkage __printf(1, 0)
 int vprintk(const char *fmt, va_list args);
 
 asmlinkage __printf(5, 6) __cold
-asmlinkage int printk_emit(int facility, int level,
-			   const char *dict, size_t dictlen,
-			   const char *fmt, ...);
+int printk_emit(int facility, int level,
+		const char *dict, size_t dictlen,
+		const char *fmt, ...);
 
 asmlinkage __printf(1, 2) __cold
 int printk(const char *fmt, ...);
-- 
cgit v1.2.3


From a55944ca82d287ca099ca90413af857af9086773 Mon Sep 17 00:00:00 2001
From: Liu Ying <Ying.Liu@freescale.com>
Date: Thu, 3 Apr 2014 14:48:54 -0700
Subject: backlight: update bd state & fb_blank properties when necessary

We don't have to update the state and fb_blank properties of a backlight
device every time a blanking or unblanking event comes because they may
have already been what we want.  Another thought is that one backlight
device may be shared by multiple framebuffers.  The backlight driver
should take the backlight device as a resource shared by all the
associated framebuffers.

This patch adds some logic to record each framebuffer's backlight usage
to determine the backlight device use count and whether the two
properties should be updated or not.  To be more specific, only one
unblank operation on a certain blanked framebuffer may increase the
backlight device's use count by one, while one blank operation on a
certain unblanked framebuffer may decrease the use count by one, because
the userspace is likely to unblank an unblanked framebuffer or blank a
blanked framebuffer.

Signed-off-by: Liu Ying <Ying.Liu@freescale.com>
Cc: Jingoo Han <jg1.han@samsung.com>
Cc: Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com>
Cc: Tomi Valkeinen <tomi.valkeinen@ti.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/video/backlight/backlight.c | 23 ++++++++++++++++++-----
 include/linux/backlight.h           |  6 ++++++
 2 files changed, 24 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/video/backlight/backlight.c b/drivers/video/backlight/backlight.c
index 5d05555fe841..efc9a2da918d 100644
--- a/drivers/video/backlight/backlight.c
+++ b/drivers/video/backlight/backlight.c
@@ -41,6 +41,8 @@ static int fb_notifier_callback(struct notifier_block *self,
 {
 	struct backlight_device *bd;
 	struct fb_event *evdata = data;
+	int node = evdata->info->node;
+	int fb_blank = 0;
 
 	/* If we aren't interested in this event, skip it immediately ... */
 	if (event != FB_EVENT_BLANK && event != FB_EVENT_CONBLANK)
@@ -51,11 +53,22 @@ static int fb_notifier_callback(struct notifier_block *self,
 	if (bd->ops)
 		if (!bd->ops->check_fb ||
 		    bd->ops->check_fb(bd, evdata->info)) {
-			bd->props.fb_blank = *(int *)evdata->data;
-			if (bd->props.fb_blank == FB_BLANK_UNBLANK)
-				bd->props.state &= ~BL_CORE_FBBLANK;
-			else
-				bd->props.state |= BL_CORE_FBBLANK;
+			fb_blank = *(int *)evdata->data;
+			if (fb_blank == FB_BLANK_UNBLANK &&
+			    !bd->fb_bl_on[node]) {
+				bd->fb_bl_on[node] = true;
+				if (!bd->use_count++) {
+					bd->props.state &= ~BL_CORE_FBBLANK;
+					bd->props.fb_blank = FB_BLANK_UNBLANK;
+				}
+			} else if (fb_blank != FB_BLANK_UNBLANK &&
+				   bd->fb_bl_on[node]) {
+				bd->fb_bl_on[node] = false;
+				if (!(--bd->use_count)) {
+					bd->props.state |= BL_CORE_FBBLANK;
+					bd->props.fb_blank = fb_blank;
+				}
+			}
 			backlight_update_status(bd);
 		}
 	mutex_unlock(&bd->ops_lock);
diff --git a/include/linux/backlight.h b/include/linux/backlight.h
index 5f9cd963213d..72647429adf6 100644
--- a/include/linux/backlight.h
+++ b/include/linux/backlight.h
@@ -9,6 +9,7 @@
 #define _LINUX_BACKLIGHT_H
 
 #include <linux/device.h>
+#include <linux/fb.h>
 #include <linux/mutex.h>
 #include <linux/notifier.h>
 
@@ -104,6 +105,11 @@ struct backlight_device {
 	struct list_head entry;
 
 	struct device dev;
+
+	/* Multiple framebuffers may share one backlight device */
+	bool fb_bl_on[FB_MAX];
+
+	int use_count;
 };
 
 static inline void backlight_update_status(struct backlight_device *bd)
-- 
cgit v1.2.3


From af661e836039cbc2aadb3bccfd7d3ddfc1bcc456 Mon Sep 17 00:00:00 2001
From: Rashika Kheria <rashika.kheria@gmail.com>
Date: Thu, 3 Apr 2014 14:49:10 -0700
Subject: lib/decompress_inflate.c: include appropriate header file

Include appropriate header file include/linux/decompress/inflate.h in
lib/decompress_inflate.c because it has prototype declaration of
function defined in lib/decompress_inflate.c.

Also, fix the guard around the header file
include/linux/decompress/inflate.h to use a more unique guard symbol.
This avoids conflict with the INFLATE_H defined by
zlib_inflate/inflate.h.

This eliminates the following warning in lib/decompress_inflate.c:

  lib/decompress_inflate.c:35:17: warning: no previous prototype for `gunzip' [-Wmissing-prototypes]

Signed-off-by: Rashika Kheria <rashika.kheria@gmail.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/decompress/inflate.h | 4 ++--
 lib/decompress_inflate.c           | 1 +
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/decompress/inflate.h b/include/linux/decompress/inflate.h
index 8c0aef1ba5f5..1d0aedef9822 100644
--- a/include/linux/decompress/inflate.h
+++ b/include/linux/decompress/inflate.h
@@ -1,5 +1,5 @@
-#ifndef INFLATE_H
-#define INFLATE_H
+#ifndef LINUX_DECOMPRESS_INFLATE_H
+#define LINUX_DECOMPRESS_INFLATE_H
 
 int gunzip(unsigned char *inbuf, int len,
 	   int(*fill)(void*, unsigned int),
diff --git a/lib/decompress_inflate.c b/lib/decompress_inflate.c
index d619b28c456f..0edfd742a154 100644
--- a/lib/decompress_inflate.c
+++ b/lib/decompress_inflate.c
@@ -19,6 +19,7 @@
 #include "zlib_inflate/inflate.h"
 
 #include "zlib_inflate/infutil.h"
+#include <linux/decompress/inflate.h>
 
 #endif /* STATIC */
 
-- 
cgit v1.2.3


From 5a418558cdae4fd0699b7b6a960f03a8bb38a338 Mon Sep 17 00:00:00 2001
From: Josh Cartwright <joshc@codeaurora.org>
Date: Thu, 3 Apr 2014 14:50:13 -0700
Subject: rtc: pm8xxx: add support for devicetree

Add support for describing the PM8921/PM8058 RTC in device tree.

Additionally:
   - drop support for describing the RTC using platform data,
     as there are no current in tree users who do so.
   - make allow_set_time a device-specific flag, instead of mucking
     with the rtc_ops

Signed-off-by: Josh Cartwright <joshc@codeaurora.org>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Acked-by: Lee Jones <lee.jones@linaro.org>
Cc: Alessandro Zummo <a.zummo@towertech.it>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/rtc/rtc-pm8xxx.c       | 52 +++++++++++++++++++++++-------------------
 include/linux/mfd/pm8xxx/rtc.h | 25 --------------------
 2 files changed, 29 insertions(+), 48 deletions(-)
 delete mode 100644 include/linux/mfd/pm8xxx/rtc.h

(limited to 'include/linux')

diff --git a/drivers/rtc/rtc-pm8xxx.c b/drivers/rtc/rtc-pm8xxx.c
index 91ac2e346aea..6e3cd345379d 100644
--- a/drivers/rtc/rtc-pm8xxx.c
+++ b/drivers/rtc/rtc-pm8xxx.c
@@ -9,7 +9,7 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  */
-
+#include <linux/of.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/rtc.h>
@@ -19,9 +19,6 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 
-#include <linux/mfd/pm8xxx/rtc.h>
-
-
 /* RTC Register offsets from RTC CTRL REG */
 #define PM8XXX_ALARM_CTRL_OFFSET	0x01
 #define PM8XXX_RTC_WRITE_OFFSET		0x02
@@ -39,6 +36,7 @@
  * struct pm8xxx_rtc -  rtc driver internal structure
  * @rtc:		rtc device for this driver.
  * @regmap:		regmap used to access RTC registers
+ * @allow_set_time:	indicates whether writing to the RTC is allowed
  * @rtc_alarm_irq:	rtc alarm irq number.
  * @rtc_base:		address of rtc control register.
  * @rtc_read_base:	base address of read registers.
@@ -51,6 +49,7 @@
 struct pm8xxx_rtc {
 	struct rtc_device *rtc;
 	struct regmap *regmap;
+	bool allow_set_time;
 	int rtc_alarm_irq;
 	int rtc_base;
 	int rtc_read_base;
@@ -75,6 +74,9 @@ static int pm8xxx_rtc_set_time(struct device *dev, struct rtc_time *tm)
 	u8 value[NUM_8_BIT_RTC_REGS], alarm_enabled = 0, ctrl_reg;
 	struct pm8xxx_rtc *rtc_dd = dev_get_drvdata(dev);
 
+	if (!rtc_dd->allow_set_time)
+		return -EACCES;
+
 	rtc_tm_to_time(tm, &secs);
 
 	for (i = 0; i < NUM_8_BIT_RTC_REGS; i++) {
@@ -298,8 +300,9 @@ rtc_rw_fail:
 	return rc;
 }
 
-static struct rtc_class_ops pm8xxx_rtc_ops = {
+static const struct rtc_class_ops pm8xxx_rtc_ops = {
 	.read_time	= pm8xxx_rtc_read_time,
+	.set_time	= pm8xxx_rtc_set_time,
 	.set_alarm	= pm8xxx_rtc_set_alarm,
 	.read_alarm	= pm8xxx_rtc_read_alarm,
 	.alarm_irq_enable = pm8xxx_rtc_alarm_irq_enable,
@@ -353,18 +356,26 @@ rtc_alarm_handled:
 	return IRQ_HANDLED;
 }
 
+/*
+ * Hardcoded RTC bases until IORESOURCE_REG mapping is figured out
+ */
+static const struct of_device_id pm8xxx_id_table[] = {
+	{ .compatible = "qcom,pm8921-rtc", .data = (void *) 0x11D },
+	{ .compatible = "qcom,pm8058-rtc", .data = (void *) 0x1E8 },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, pm8xxx_id_table);
+
 static int pm8xxx_rtc_probe(struct platform_device *pdev)
 {
 	int rc;
 	unsigned int ctrl_reg;
-	bool rtc_write_enable = false;
 	struct pm8xxx_rtc *rtc_dd;
-	struct resource *rtc_resource;
-	const struct pm8xxx_rtc_platform_data *pdata =
-						dev_get_platdata(&pdev->dev);
+	const struct of_device_id *match;
 
-	if (pdata != NULL)
-		rtc_write_enable = pdata->rtc_write_enable;
+	match = of_match_node(pm8xxx_id_table, pdev->dev.of_node);
+	if (!match)
+		return -ENXIO;
 
 	rtc_dd = devm_kzalloc(&pdev->dev, sizeof(*rtc_dd), GFP_KERNEL);
 	if (rtc_dd == NULL)
@@ -385,14 +396,10 @@ static int pm8xxx_rtc_probe(struct platform_device *pdev)
 		return -ENXIO;
 	}
 
-	rtc_resource = platform_get_resource_byname(pdev, IORESOURCE_IO,
-						    "pmic_rtc_base");
-	if (!(rtc_resource && rtc_resource->start)) {
-		dev_err(&pdev->dev, "RTC IO resource absent!\n");
-		return -ENXIO;
-	}
+	rtc_dd->allow_set_time = of_property_read_bool(pdev->dev.of_node,
+						      "allow-set-time");
 
-	rtc_dd->rtc_base = rtc_resource->start;
+	rtc_dd->rtc_base = (long) match->data;
 
 	/* Setup RTC register addresses */
 	rtc_dd->rtc_write_base = rtc_dd->rtc_base + PM8XXX_RTC_WRITE_OFFSET;
@@ -419,8 +426,6 @@ static int pm8xxx_rtc_probe(struct platform_device *pdev)
 	}
 
 	rtc_dd->ctrl_reg = ctrl_reg;
-	if (rtc_write_enable)
-		pm8xxx_rtc_ops.set_time = pm8xxx_rtc_set_time;
 
 	platform_set_drvdata(pdev, rtc_dd);
 
@@ -479,9 +484,10 @@ static SIMPLE_DEV_PM_OPS(pm8xxx_rtc_pm_ops,
 static struct platform_driver pm8xxx_rtc_driver = {
 	.probe		= pm8xxx_rtc_probe,
 	.driver	= {
-		.name	= PM8XXX_RTC_DEV_NAME,
-		.owner	= THIS_MODULE,
-		.pm	= &pm8xxx_rtc_pm_ops,
+		.name		= "rtc-pm8xxx",
+		.owner		= THIS_MODULE,
+		.pm		= &pm8xxx_rtc_pm_ops,
+		.of_match_table	= pm8xxx_id_table,
 	},
 };
 
diff --git a/include/linux/mfd/pm8xxx/rtc.h b/include/linux/mfd/pm8xxx/rtc.h
deleted file mode 100644
index 14f1983eaecc..000000000000
--- a/include/linux/mfd/pm8xxx/rtc.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/* Copyright (c) 2010-2011, Code Aurora Forum. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#ifndef __RTC_PM8XXX_H__
-#define __RTC_PM8XXX_H__
-
-#define PM8XXX_RTC_DEV_NAME     "rtc-pm8xxx"
-/**
- * struct pm8xxx_rtc_pdata - RTC driver platform data
- * @rtc_write_enable: variable stating RTC write capability
- */
-struct pm8xxx_rtc_platform_data {
-	bool rtc_write_enable;
-};
-
-#endif /* __RTC_PM8XXX_H__ */
-- 
cgit v1.2.3


From 90ccf7dde9527672553c3a809aa93654c95672d0 Mon Sep 17 00:00:00 2001
From: Andreas Rohner <andreas.rohner@gmx.net>
Date: Thu, 3 Apr 2014 14:50:26 -0700
Subject: nilfs2: add struct nilfs_suinfo_update and flags

Add the nilfs_suinfo_update structure, which contains the information
needed to update one segment usage entry.  The flags specify, which
fields need to be updated.

Signed-off-by: Andreas Rohner <andreas.rohner@gmx.net>
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/nilfs2_fs.h | 42 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h
index 98755767c7b0..252657874a19 100644
--- a/include/linux/nilfs2_fs.h
+++ b/include/linux/nilfs2_fs.h
@@ -710,6 +710,48 @@ static inline int nilfs_suinfo_clean(const struct nilfs_suinfo *si)
 }
 
 /* ioctl */
+/**
+ * nilfs_suinfo_update - segment usage information update
+ * @sup_segnum: segment number
+ * @sup_flags: flags for which fields are active in sup_sui
+ * @sup_reserved: reserved necessary for alignment
+ * @sup_sui: segment usage information
+ */
+struct nilfs_suinfo_update {
+	__u64 sup_segnum;
+	__u32 sup_flags;
+	__u32 sup_reserved;
+	struct nilfs_suinfo sup_sui;
+};
+
+enum {
+	NILFS_SUINFO_UPDATE_LASTMOD,
+	NILFS_SUINFO_UPDATE_NBLOCKS,
+	NILFS_SUINFO_UPDATE_FLAGS,
+	__NR_NILFS_SUINFO_UPDATE_FIELDS,
+};
+
+#define NILFS_SUINFO_UPDATE_FNS(flag, name)				\
+static inline void							\
+nilfs_suinfo_update_set_##name(struct nilfs_suinfo_update *sup)		\
+{									\
+	sup->sup_flags |= 1UL << NILFS_SUINFO_UPDATE_##flag;		\
+}									\
+static inline void							\
+nilfs_suinfo_update_clear_##name(struct nilfs_suinfo_update *sup)	\
+{									\
+	sup->sup_flags &= ~(1UL << NILFS_SUINFO_UPDATE_##flag);		\
+}									\
+static inline int							\
+nilfs_suinfo_update_##name(const struct nilfs_suinfo_update *sup)	\
+{									\
+	return !!(sup->sup_flags & (1UL << NILFS_SUINFO_UPDATE_##flag));\
+}
+
+NILFS_SUINFO_UPDATE_FNS(LASTMOD, lastmod)
+NILFS_SUINFO_UPDATE_FNS(NBLOCKS, nblocks)
+NILFS_SUINFO_UPDATE_FNS(FLAGS, flags)
+
 enum {
 	NILFS_CHECKPOINT,
 	NILFS_SNAPSHOT,
-- 
cgit v1.2.3


From 2cc88f3a5f16ae9a3c8f54de1b2fd4a397b36075 Mon Sep 17 00:00:00 2001
From: Andreas Rohner <andreas.rohner@gmx.net>
Date: Thu, 3 Apr 2014 14:50:28 -0700
Subject: nilfs2: implementation of NILFS_IOCTL_SET_SUINFO ioctl

With this ioctl the segment usage entries in the SUFILE can be updated
from userspace.

This is useful, because it allows the userspace GC to modify and update
segment usage entries for specific segments, which enables it to avoid
unnecessary write operations.

If a segment needs to be cleaned, but there is no or very little
reclaimable space in it, the cleaning operation basically degrades to a
useless moving operation.  In the end the only thing that changes is the
location of the data and a timestamp in the segment usage information.
With this ioctl the GC can skip the cleaning and update the segment
usage entries directly instead.

This is basically a shortcut to cleaning the segment.  It is still
necessary to read the segment summary information, but the writing of
the live blocks can be skipped if it's not worth it.

[konishi.ryusuke@lab.ntt.co.jp: add description of NILFS_IOCTL_SET_SUINFO ioctl]
Signed-off-by: Andreas Rohner <andreas.rohner@gmx.net>
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/filesystems/nilfs2.txt |  7 +++
 fs/nilfs2/ioctl.c                    | 92 ++++++++++++++++++++++++++++++++++++
 include/linux/nilfs2_fs.h            |  2 +
 3 files changed, 101 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/nilfs2.txt b/Documentation/filesystems/nilfs2.txt
index 06887d46ccf2..8b887ae4e39e 100644
--- a/Documentation/filesystems/nilfs2.txt
+++ b/Documentation/filesystems/nilfs2.txt
@@ -111,6 +111,13 @@ Table of NILFS2 specific ioctls
 			        nilfs_resize utilities and by nilfs_cleanerd
 			        daemon.
 
+ NILFS_IOCTL_SET_SUINFO         Modify segment usage info of requested
+				segments. This ioctl is used by
+				nilfs_cleanerd daemon to skip unnecessary
+				cleaning operation of segments and reduce
+				performance penalty or wear of flash device
+				due to redundant move of in-use blocks.
+
  NILFS_IOCTL_GET_SUSTAT         Return segment usage statistics. This ioctl
 			        is used in lssu, nilfs_resize utilities and
 			        by nilfs_cleanerd daemon.
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 2b34021948e4..c19a23158487 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -1163,6 +1163,95 @@ static int nilfs_ioctl_get_info(struct inode *inode, struct file *filp,
 	return ret;
 }
 
+/**
+ * nilfs_ioctl_set_suinfo - set segment usage info
+ * @inode: inode object
+ * @filp: file object
+ * @cmd: ioctl's request code
+ * @argp: pointer on argument from userspace
+ *
+ * Description: Expects an array of nilfs_suinfo_update structures
+ * encapsulated in nilfs_argv and updates the segment usage info
+ * according to the flags in nilfs_suinfo_update.
+ *
+ * Return Value: On success, 0 is returned. On error, one of the
+ * following negative error codes is returned.
+ *
+ * %-EPERM - Not enough permissions
+ *
+ * %-EFAULT - Error copying input data
+ *
+ * %-EIO - I/O error.
+ *
+ * %-ENOMEM - Insufficient amount of memory available.
+ *
+ * %-EINVAL - Invalid values in input (segment number, flags or nblocks)
+ */
+static int nilfs_ioctl_set_suinfo(struct inode *inode, struct file *filp,
+				unsigned int cmd, void __user *argp)
+{
+	struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
+	struct nilfs_transaction_info ti;
+	struct nilfs_argv argv;
+	size_t len;
+	void __user *base;
+	void *kbuf;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
+
+	ret = -EFAULT;
+	if (copy_from_user(&argv, argp, sizeof(argv)))
+		goto out;
+
+	ret = -EINVAL;
+	if (argv.v_size < sizeof(struct nilfs_suinfo_update))
+		goto out;
+
+	if (argv.v_nmembs > nilfs->ns_nsegments)
+		goto out;
+
+	if (argv.v_nmembs >= UINT_MAX / argv.v_size)
+		goto out;
+
+	len = argv.v_size * argv.v_nmembs;
+	if (!len) {
+		ret = 0;
+		goto out;
+	}
+
+	base = (void __user *)(unsigned long)argv.v_base;
+	kbuf = vmalloc(len);
+	if (!kbuf) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	if (copy_from_user(kbuf, base, len)) {
+		ret = -EFAULT;
+		goto out_free;
+	}
+
+	nilfs_transaction_begin(inode->i_sb, &ti, 0);
+	ret = nilfs_sufile_set_suinfo(nilfs->ns_sufile, kbuf, argv.v_size,
+			argv.v_nmembs);
+	if (unlikely(ret < 0))
+		nilfs_transaction_abort(inode->i_sb);
+	else
+		nilfs_transaction_commit(inode->i_sb); /* never fails */
+
+out_free:
+	vfree(kbuf);
+out:
+	mnt_drop_write_file(filp);
+	return ret;
+}
+
 long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
@@ -1189,6 +1278,8 @@ long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		return nilfs_ioctl_get_info(inode, filp, cmd, argp,
 					    sizeof(struct nilfs_suinfo),
 					    nilfs_ioctl_do_get_suinfo);
+	case NILFS_IOCTL_SET_SUINFO:
+		return nilfs_ioctl_set_suinfo(inode, filp, cmd, argp);
 	case NILFS_IOCTL_GET_SUSTAT:
 		return nilfs_ioctl_get_sustat(inode, filp, cmd, argp);
 	case NILFS_IOCTL_GET_VINFO:
@@ -1228,6 +1319,7 @@ long nilfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	case NILFS_IOCTL_GET_CPINFO:
 	case NILFS_IOCTL_GET_CPSTAT:
 	case NILFS_IOCTL_GET_SUINFO:
+	case NILFS_IOCTL_SET_SUINFO:
 	case NILFS_IOCTL_GET_SUSTAT:
 	case NILFS_IOCTL_GET_VINFO:
 	case NILFS_IOCTL_GET_BDESCS:
diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h
index 252657874a19..1fb465f9baf2 100644
--- a/include/linux/nilfs2_fs.h
+++ b/include/linux/nilfs2_fs.h
@@ -905,5 +905,7 @@ struct nilfs_bdesc {
 	_IOW(NILFS_IOCTL_IDENT, 0x8B, __u64)
 #define NILFS_IOCTL_SET_ALLOC_RANGE  \
 	_IOW(NILFS_IOCTL_IDENT, 0x8C, __u64[2])
+#define NILFS_IOCTL_SET_SUINFO  \
+	_IOW(NILFS_IOCTL_IDENT, 0x8D, struct nilfs_argv)
 
 #endif	/* _LINUX_NILFS_FS_H */
-- 
cgit v1.2.3


From 0ec060d1881a24c270fdf0d6616e33e23a209ef2 Mon Sep 17 00:00:00 2001
From: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Date: Thu, 3 Apr 2014 14:50:31 -0700
Subject: nilfs2: verify metadata sizes read from disk

Add code to check sizes of on-disk data of metadata files such as inode
size, segment usage size, DAT entry size, and checkpoint size.  Although
these sizes are read from disk, the current implementation doesn't check
them.

If these sizes are not sane on disk, it can cause out-of-range access to
metadata or memory access overrun on metadata block buffers due to
overflow in sundry calculations.

Both lower limit and upper limit of metadata sizes are verified to
prevent these issues.

Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Cc: Andreas Rohner <andreas.rohner@gmx.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/nilfs2/cpfile.c        | 12 ++++++++++++
 fs/nilfs2/dat.c           | 12 ++++++++++++
 fs/nilfs2/sufile.c        | 12 ++++++++++++
 fs/nilfs2/the_nilfs.c     | 10 ++++++++++
 include/linux/nilfs2_fs.h |  8 ++++++++
 5 files changed, 54 insertions(+)

(limited to 'include/linux')

diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c
index deaa3d33a0aa..0d58075f34e2 100644
--- a/fs/nilfs2/cpfile.c
+++ b/fs/nilfs2/cpfile.c
@@ -942,6 +942,18 @@ int nilfs_cpfile_read(struct super_block *sb, size_t cpsize,
 	struct inode *cpfile;
 	int err;
 
+	if (cpsize > sb->s_blocksize) {
+		printk(KERN_ERR
+		       "NILFS: too large checkpoint size: %zu bytes.\n",
+		       cpsize);
+		return -EINVAL;
+	} else if (cpsize < NILFS_MIN_CHECKPOINT_SIZE) {
+		printk(KERN_ERR
+		       "NILFS: too small checkpoint size: %zu bytes.\n",
+		       cpsize);
+		return -EINVAL;
+	}
+
 	cpfile = nilfs_iget_locked(sb, NULL, NILFS_CPFILE_INO);
 	if (unlikely(!cpfile))
 		return -ENOMEM;
diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c
index fa0f80308c2d..0d5fada91191 100644
--- a/fs/nilfs2/dat.c
+++ b/fs/nilfs2/dat.c
@@ -484,6 +484,18 @@ int nilfs_dat_read(struct super_block *sb, size_t entry_size,
 	struct nilfs_dat_info *di;
 	int err;
 
+	if (entry_size > sb->s_blocksize) {
+		printk(KERN_ERR
+		       "NILFS: too large DAT entry size: %zu bytes.\n",
+		       entry_size);
+		return -EINVAL;
+	} else if (entry_size < NILFS_MIN_DAT_ENTRY_SIZE) {
+		printk(KERN_ERR
+		       "NILFS: too small DAT entry size: %zu bytes.\n",
+		       entry_size);
+		return -EINVAL;
+	}
+
 	dat = nilfs_iget_locked(sb, NULL, NILFS_DAT_INO);
 	if (unlikely(!dat))
 		return -ENOMEM;
diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index 84e384dae663..2a869c35c362 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -1169,6 +1169,18 @@ int nilfs_sufile_read(struct super_block *sb, size_t susize,
 	void *kaddr;
 	int err;
 
+	if (susize > sb->s_blocksize) {
+		printk(KERN_ERR
+		       "NILFS: too large segment usage size: %zu bytes.\n",
+		       susize);
+		return -EINVAL;
+	} else if (susize < NILFS_MIN_SEGMENT_USAGE_SIZE) {
+		printk(KERN_ERR
+		       "NILFS: too small segment usage size: %zu bytes.\n",
+		       susize);
+		return -EINVAL;
+	}
+
 	sufile = nilfs_iget_locked(sb, NULL, NILFS_SUFILE_INO);
 	if (unlikely(!sufile))
 		return -ENOMEM;
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index 94c451ce6d24..8ba8229ba076 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -399,6 +399,16 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs,
 		return -EINVAL;
 
 	nilfs->ns_inode_size = le16_to_cpu(sbp->s_inode_size);
+	if (nilfs->ns_inode_size > nilfs->ns_blocksize) {
+		printk(KERN_ERR "NILFS: too large inode size: %d bytes.\n",
+		       nilfs->ns_inode_size);
+		return -EINVAL;
+	} else if (nilfs->ns_inode_size < NILFS_MIN_INODE_SIZE) {
+		printk(KERN_ERR "NILFS: too small inode size: %d bytes.\n",
+		       nilfs->ns_inode_size);
+		return -EINVAL;
+	}
+
 	nilfs->ns_first_ino = le32_to_cpu(sbp->s_first_ino);
 
 	nilfs->ns_blocks_per_segment = le32_to_cpu(sbp->s_blocks_per_segment);
diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h
index 1fb465f9baf2..ff3fea3194c6 100644
--- a/include/linux/nilfs2_fs.h
+++ b/include/linux/nilfs2_fs.h
@@ -82,6 +82,8 @@ struct nilfs_inode {
 	__le32	i_pad;
 };
 
+#define NILFS_MIN_INODE_SIZE		128
+
 /**
  * struct nilfs_super_root - structure of super root
  * @sr_sum: check sum
@@ -482,6 +484,8 @@ struct nilfs_dat_entry {
 	__le64 de_rsv;
 };
 
+#define NILFS_MIN_DAT_ENTRY_SIZE	32
+
 /**
  * struct nilfs_snapshot_list - snapshot list
  * @ssl_next: next checkpoint number on snapshot list
@@ -520,6 +524,8 @@ struct nilfs_checkpoint {
 	struct nilfs_inode cp_ifile_inode;
 };
 
+#define NILFS_MIN_CHECKPOINT_SIZE	(64 + NILFS_MIN_INODE_SIZE)
+
 /* checkpoint flags */
 enum {
 	NILFS_CHECKPOINT_SNAPSHOT,
@@ -615,6 +621,8 @@ struct nilfs_segment_usage {
 	__le32 su_flags;
 };
 
+#define NILFS_MIN_SEGMENT_USAGE_SIZE	16
+
 /* segment usage flag */
 enum {
 	NILFS_SEGMENT_USAGE_ACTIVE,
-- 
cgit v1.2.3


From 1b416c4b41351c3eb8fc42dbb4cd8eba463c0813 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Sat, 2 Nov 2013 13:00:03 +0000
Subject: dmaengine: omap-dma: provide a hook to get the underlying DMA
 platform ops

Provide and use a hook to obtain the underlying DMA platform operations
so that omap-dma.c can access the hardware more directly without
involving the legacy DMA driver.

Acked-by: Tony Lindgren <tony@atomide.com>
Acked-by: Vinod Koul <vinod.koul@intel.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/plat-omap/dma.c | 6 ++++++
 drivers/dma/omap-dma.c   | 7 +++++++
 include/linux/omap-dma.h | 2 ++
 3 files changed, 15 insertions(+)

(limited to 'include/linux')

diff --git a/arch/arm/plat-omap/dma.c b/arch/arm/plat-omap/dma.c
index 01619c2910e3..d4d9a5e62152 100644
--- a/arch/arm/plat-omap/dma.c
+++ b/arch/arm/plat-omap/dma.c
@@ -2000,6 +2000,12 @@ void omap_dma_global_context_restore(void)
 			omap_clear_dma(ch);
 }
 
+struct omap_system_dma_plat_info *omap_get_plat_info(void)
+{
+	return p;
+}
+EXPORT_SYMBOL_GPL(omap_get_plat_info);
+
 static int omap_system_dma_probe(struct platform_device *pdev)
 {
 	int ch, ret = 0;
diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c
index 98034e8c558f..4ac26bf0ad30 100644
--- a/drivers/dma/omap-dma.c
+++ b/drivers/dma/omap-dma.c
@@ -26,11 +26,13 @@ struct omap_dmadev {
 	spinlock_t lock;
 	struct tasklet_struct task;
 	struct list_head pending;
+	struct omap_system_dma_plat_info *plat;
 };
 
 struct omap_chan {
 	struct virt_dma_chan vc;
 	struct list_head node;
+	struct omap_system_dma_plat_info *plat;
 
 	struct dma_slave_config	cfg;
 	unsigned dma_sig;
@@ -573,6 +575,7 @@ static int omap_dma_chan_init(struct omap_dmadev *od, int dma_sig)
 	if (!c)
 		return -ENOMEM;
 
+	c->plat = od->plat;
 	c->dma_sig = dma_sig;
 	c->vc.desc_free = omap_dma_desc_free;
 	vchan_init(&c->vc, &od->ddev);
@@ -605,6 +608,10 @@ static int omap_dma_probe(struct platform_device *pdev)
 	if (!od)
 		return -ENOMEM;
 
+	od->plat = omap_get_plat_info();
+	if (!od->plat)
+		return -EPROBE_DEFER;
+
 	dma_cap_set(DMA_SLAVE, od->ddev.cap_mask);
 	dma_cap_set(DMA_CYCLIC, od->ddev.cap_mask);
 	od->ddev.device_alloc_chan_resources = omap_dma_alloc_chan_resources;
diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h
index 7af25a9c9c51..14742fc2aefe 100644
--- a/include/linux/omap-dma.h
+++ b/include/linux/omap-dma.h
@@ -292,6 +292,8 @@ struct omap_system_dma_plat_info {
 #define dma_omap15xx()	((dma_omap1() && (d->dev_caps & ENABLE_1510_MODE)))
 #define dma_omap16xx()	((dma_omap1() && (d->dev_caps & ENABLE_16XX_MODE)))
 
+extern struct omap_system_dma_plat_info *omap_get_plat_info(void);
+
 extern void omap_set_dma_priority(int lch, int dst_port, int priority);
 extern int omap_request_dma(int dev_id, const char *dev_name,
 			void (*callback)(int lch, u16 ch_status, void *data),
-- 
cgit v1.2.3


From b9e97822da374f52aaf99cb502f531ff2184b8f5 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Sat, 2 Nov 2013 13:26:57 +0000
Subject: dmaengine: omap-dma: program hardware directly

Program the transfer parameters directly into the hardware, rather
than using the functions in arch/arm/plat-omap/dma.c.

Acked-by: Tony Lindgren <tony@atomide.com>
Acked-by: Vinod Koul <vinod.koul@intel.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 drivers/dma/omap-dma.c   | 142 +++++++++++++++++++++++++++++++++++++++++------
 include/linux/omap-dma.h |   6 +-
 2 files changed, 130 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c
index 4ac26bf0ad30..47a3fa5bc38e 100644
--- a/drivers/dma/omap-dma.c
+++ b/drivers/dma/omap-dma.c
@@ -99,16 +99,94 @@ static void omap_dma_start_sg(struct omap_chan *c, struct omap_desc *d,
 	unsigned idx)
 {
 	struct omap_sg *sg = d->sg + idx;
+	uint32_t val;
+
+	if (d->dir == DMA_DEV_TO_MEM) {
+		if (dma_omap1()) {
+			val = c->plat->dma_read(CSDP, c->dma_ch);
+			val &= ~(0x1f << 9);
+			val |= OMAP_DMA_PORT_EMIFF << 9;
+			c->plat->dma_write(val, CSDP, c->dma_ch);
+		}
 
-	if (d->dir == DMA_DEV_TO_MEM)
-		omap_set_dma_dest_params(c->dma_ch, OMAP_DMA_PORT_EMIFF,
-			OMAP_DMA_AMODE_POST_INC, sg->addr, 0, 0);
-	else
-		omap_set_dma_src_params(c->dma_ch, OMAP_DMA_PORT_EMIFF,
-			OMAP_DMA_AMODE_POST_INC, sg->addr, 0, 0);
+		val = c->plat->dma_read(CCR, c->dma_ch);
+		val &= ~(0x03 << 14);
+		val |= OMAP_DMA_AMODE_POST_INC << 14;
+		c->plat->dma_write(val, CCR, c->dma_ch);
+
+		c->plat->dma_write(sg->addr, CDSA, c->dma_ch);
+		c->plat->dma_write(0, CDEI, c->dma_ch);
+		c->plat->dma_write(0, CDFI, c->dma_ch);
+	} else {
+		if (dma_omap1()) {
+			val = c->plat->dma_read(CSDP, c->dma_ch);
+			val &= ~(0x1f << 2);
+			val |= OMAP_DMA_PORT_EMIFF << 2;
+			c->plat->dma_write(val, CSDP, c->dma_ch);
+		}
+
+		val = c->plat->dma_read(CCR, c->dma_ch);
+		val &= ~(0x03 << 12);
+		val |= OMAP_DMA_AMODE_POST_INC << 12;
+		c->plat->dma_write(val, CCR, c->dma_ch);
+
+		c->plat->dma_write(sg->addr, CSSA, c->dma_ch);
+		c->plat->dma_write(0, CSEI, c->dma_ch);
+		c->plat->dma_write(0, CSFI, c->dma_ch);
+	}
+
+	val = c->plat->dma_read(CSDP, c->dma_ch);
+	val &= ~0x03;
+	val |= d->es;
+	c->plat->dma_write(val, CSDP, c->dma_ch);
+
+	if (dma_omap1()) {
+		val = c->plat->dma_read(CCR, c->dma_ch);
+		val &= ~(1 << 5);
+		if (d->sync_mode == OMAP_DMA_SYNC_FRAME)
+			val |= 1 << 5;
+		c->plat->dma_write(val, CCR, c->dma_ch);
+
+		val = c->plat->dma_read(CCR2, c->dma_ch);
+		val &= ~(1 << 2);
+		if (d->sync_mode == OMAP_DMA_SYNC_BLOCK)
+			val |= 1 << 2;
+		c->plat->dma_write(val, CCR2, c->dma_ch);
+	} else if (c->dma_sig) {
+		val = c->plat->dma_read(CCR, c->dma_ch);
+
+		/* DMA_SYNCHRO_CONTROL_UPPER depends on the channel number */
+		val &= ~((1 << 23) | (3 << 19) | 0x1f);
+		val |= (c->dma_sig & ~0x1f) << 14;
+		val |= c->dma_sig & 0x1f;
+
+		if (d->sync_mode & OMAP_DMA_SYNC_FRAME)
+			val |= 1 << 5;
+		else
+			val &= ~(1 << 5);
+
+		if (d->sync_mode & OMAP_DMA_SYNC_BLOCK)
+			val |= 1 << 18;
+		else
+			val &= ~(1 << 18);
+
+		switch (d->sync_type) {
+		case OMAP_DMA_DST_SYNC_PREFETCH:
+			val &= ~(1 << 24);	/* dest synch */
+			val |= 1 << 23;		/* Prefetch */
+			break;
+		case 0:
+			val &= ~(1 << 24);	/* dest synch */
+			break;
+		default:
+			val |= 1 << 24;		/* source synch */
+			break;
+		}
+		c->plat->dma_write(val, CCR, c->dma_ch);
+	}
 
-	omap_set_dma_transfer_params(c->dma_ch, d->es, sg->en, sg->fn,
-		d->sync_mode, c->dma_sig, d->sync_type);
+	c->plat->dma_write(sg->en, CEN, c->dma_ch);
+	c->plat->dma_write(sg->fn, CFN, c->dma_ch);
 
 	omap_start_dma(c->dma_ch);
 }
@@ -117,6 +195,7 @@ static void omap_dma_start_desc(struct omap_chan *c)
 {
 	struct virt_dma_desc *vd = vchan_next_desc(&c->vc);
 	struct omap_desc *d;
+	uint32_t val;
 
 	if (!vd) {
 		c->desc = NULL;
@@ -128,12 +207,39 @@ static void omap_dma_start_desc(struct omap_chan *c)
 	c->desc = d = to_omap_dma_desc(&vd->tx);
 	c->sgidx = 0;
 
-	if (d->dir == DMA_DEV_TO_MEM)
-		omap_set_dma_src_params(c->dma_ch, d->periph_port,
-			OMAP_DMA_AMODE_CONSTANT, d->dev_addr, 0, d->fi);
-	else
-		omap_set_dma_dest_params(c->dma_ch, d->periph_port,
-			OMAP_DMA_AMODE_CONSTANT, d->dev_addr, 0, d->fi);
+	if (d->dir == DMA_DEV_TO_MEM) {
+		if (dma_omap1()) {
+			val = c->plat->dma_read(CSDP, c->dma_ch);
+			val &= ~(0x1f << 2);
+			val |= d->periph_port << 2;
+			c->plat->dma_write(val, CSDP, c->dma_ch);
+		}
+
+		val = c->plat->dma_read(CCR, c->dma_ch);
+		val &= ~(0x03 << 12);
+		val |= OMAP_DMA_AMODE_CONSTANT << 12;
+		c->plat->dma_write(val, CCR, c->dma_ch);
+
+		c->plat->dma_write(d->dev_addr, CSSA, c->dma_ch);
+		c->plat->dma_write(0, CSEI, c->dma_ch);
+		c->plat->dma_write(d->fi, CSFI, c->dma_ch);
+	} else {
+		if (dma_omap1()) {
+			val = c->plat->dma_read(CSDP, c->dma_ch);
+			val &= ~(0x1f << 9);
+			val |= d->periph_port << 9;
+			c->plat->dma_write(val, CSDP, c->dma_ch);
+		}
+
+		val = c->plat->dma_read(CCR, c->dma_ch);
+		val &= ~(0x03 << 14);
+		val |= OMAP_DMA_AMODE_CONSTANT << 14;
+		c->plat->dma_write(val, CCR, c->dma_ch);
+
+		c->plat->dma_write(d->dev_addr, CDSA, c->dma_ch);
+		c->plat->dma_write(0, CDEI, c->dma_ch);
+		c->plat->dma_write(d->fi, CDFI, c->dma_ch);
+	}
 
 	omap_dma_start_sg(c, d, 0);
 }
@@ -452,8 +558,12 @@ static struct dma_async_tx_descriptor *omap_dma_prep_dma_cyclic(
 	}
 
 	if (dma_omap2plus()) {
-		omap_set_dma_src_burst_mode(c->dma_ch, OMAP_DMA_DATA_BURST_16);
-		omap_set_dma_dest_burst_mode(c->dma_ch, OMAP_DMA_DATA_BURST_16);
+		uint32_t val;
+
+		val = c->plat->dma_read(CSDP, c->dma_ch);
+		val |= 0x03 << 7; /* src burst mode 16 */
+		val |= 0x03 << 14; /* dst burst mode 16 */
+		c->plat->dma_write(val, CSDP, c->dma_ch);
 	}
 
 	return vchan_tx_prep(&c->vc, &d->vd, flags);
diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h
index 14742fc2aefe..d631658e2237 100644
--- a/include/linux/omap-dma.h
+++ b/include/linux/omap-dma.h
@@ -289,8 +289,10 @@ struct omap_system_dma_plat_info {
 #define dma_omap2plus()	0
 #endif
 #define dma_omap1()	(!dma_omap2plus())
-#define dma_omap15xx()	((dma_omap1() && (d->dev_caps & ENABLE_1510_MODE)))
-#define dma_omap16xx()	((dma_omap1() && (d->dev_caps & ENABLE_16XX_MODE)))
+#define __dma_omap15xx(d) (dma_omap1() && (d)->dev_caps & ENABLE_1510_MODE)
+#define __dma_omap16xx(d) (dma_omap1() && (d)->dev_caps & ENABLE_16XX_MODE)
+#define dma_omap15xx()	__dma_omap15xx(d)
+#define dma_omap16xx()	__dma_omap16xx(d)
 
 extern struct omap_system_dma_plat_info *omap_get_plat_info(void);
 
-- 
cgit v1.2.3


From e38b1485fde832f72ab478f947f6e78a8e28c58b Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Fri, 8 Nov 2013 14:48:55 +0000
Subject: ARM: omap: remove references to disable_irq_lch

The disable_irq_lch method is never actually used, so there's not much
point it existing; remove it.

Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/mach-omap1/dma.c |  1 -
 arch/arm/mach-omap2/dma.c | 10 ----------
 include/linux/omap-dma.h  |  1 -
 3 files changed, 12 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-omap1/dma.c b/arch/arm/mach-omap1/dma.c
index 5bb8ce86d54b..d292055d3117 100644
--- a/arch/arm/mach-omap1/dma.c
+++ b/arch/arm/mach-omap1/dma.c
@@ -363,7 +363,6 @@ static int __init omap1_system_dma_init(void)
 	p->clear_dma		= omap1_clear_dma;
 	p->dma_write		= dma_write;
 	p->dma_read		= dma_read;
-	p->disable_irq_lch	= NULL;
 
 	p->errata = configure_dma_errata();
 
diff --git a/arch/arm/mach-omap2/dma.c b/arch/arm/mach-omap2/dma.c
index 49fd0d501c9b..81c2d3383bc5 100644
--- a/arch/arm/mach-omap2/dma.c
+++ b/arch/arm/mach-omap2/dma.c
@@ -112,15 +112,6 @@ static inline u32 dma_read(int reg, int lch)
 	return val;
 }
 
-static inline void omap2_disable_irq_lch(int lch)
-{
-	u32 val;
-
-	val = dma_read(IRQENABLE_L0, lch);
-	val &= ~(1 << lch);
-	dma_write(val, IRQENABLE_L0, lch);
-}
-
 static void omap2_clear_dma(int lch)
 {
 	int i = dma_common_ch_start;
@@ -239,7 +230,6 @@ static int __init omap2_system_dma_init_dev(struct omap_hwmod *oh, void *unused)
 	}
 
 	p->dma_attr		= (struct omap_dma_dev_attr *)oh->dev_attr;
-	p->disable_irq_lch	= omap2_disable_irq_lch;
 	p->show_dma_caps	= omap2_show_dma_caps;
 	p->clear_dma		= omap2_clear_dma;
 	p->dma_write		= dma_write;
diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h
index d631658e2237..0bb7de77d478 100644
--- a/include/linux/omap-dma.h
+++ b/include/linux/omap-dma.h
@@ -275,7 +275,6 @@ struct omap_dma_dev_attr {
 struct omap_system_dma_plat_info {
 	struct omap_dma_dev_attr *dma_attr;
 	u32 errata;
-	void (*disable_irq_lch)(int lch);
 	void (*show_dma_caps)(void);
 	void (*clear_lch_regs)(int lch);
 	void (*clear_dma)(int lch);
-- 
cgit v1.2.3


From 64a2dc3d3de4235eb73921d870a674a23d9888f0 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Fri, 8 Nov 2013 18:04:06 +0000
Subject: ARM: omap: clean up DMA register accesses

We can do much better with this by using a structure to describe each
register, rather than code.

Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/mach-omap1/dma.c | 117 +++++++++++++++++++++-------------------------
 arch/arm/mach-omap2/dma.c |  99 +++++++++++++++++++--------------------
 include/linux/omap-dma.h  |  13 ++++++
 3 files changed, 115 insertions(+), 114 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-omap1/dma.c b/arch/arm/mach-omap1/dma.c
index 11f0b0ee67a3..b680db7a35d4 100644
--- a/arch/arm/mach-omap1/dma.c
+++ b/arch/arm/mach-omap1/dma.c
@@ -32,53 +32,52 @@
 
 #define OMAP1_DMA_BASE			(0xfffed800)
 #define OMAP1_LOGICAL_DMA_CH_COUNT	17
-#define OMAP1_DMA_STRIDE		0x40
 
 static u32 errata;
 static u32 enable_1510_mode;
 
-static u16 reg_map[] = {
-	[GCR]		= 0x400,
-	[GSCR]		= 0x404,
-	[GRST1]		= 0x408,
-	[HW_ID]		= 0x442,
-	[PCH2_ID]	= 0x444,
-	[PCH0_ID]	= 0x446,
-	[PCH1_ID]	= 0x448,
-	[PCHG_ID]	= 0x44a,
-	[PCHD_ID]	= 0x44c,
-	[CAPS_0]	= 0x44e,
-	[CAPS_1]	= 0x452,
-	[CAPS_2]	= 0x456,
-	[CAPS_3]	= 0x458,
-	[CAPS_4]	= 0x45a,
-	[PCH2_SR]	= 0x460,
-	[PCH0_SR]	= 0x480,
-	[PCH1_SR]	= 0x482,
-	[PCHD_SR]	= 0x4c0,
+static const struct omap_dma_reg reg_map[] = {
+	[GCR]		= { 0x0400, 0x00, OMAP_DMA_REG_16BIT },
+	[GSCR]		= { 0x0404, 0x00, OMAP_DMA_REG_16BIT },
+	[GRST1]		= { 0x0408, 0x00, OMAP_DMA_REG_16BIT },
+	[HW_ID]		= { 0x0442, 0x00, OMAP_DMA_REG_16BIT },
+	[PCH2_ID]	= { 0x0444, 0x00, OMAP_DMA_REG_16BIT },
+	[PCH0_ID]	= { 0x0446, 0x00, OMAP_DMA_REG_16BIT },
+	[PCH1_ID]	= { 0x0448, 0x00, OMAP_DMA_REG_16BIT },
+	[PCHG_ID]	= { 0x044a, 0x00, OMAP_DMA_REG_16BIT },
+	[PCHD_ID]	= { 0x044c, 0x00, OMAP_DMA_REG_16BIT },
+	[CAPS_0]	= { 0x044e, 0x00, OMAP_DMA_REG_2X16BIT },
+	[CAPS_1]	= { 0x0452, 0x00, OMAP_DMA_REG_2X16BIT },
+	[CAPS_2]	= { 0x0456, 0x00, OMAP_DMA_REG_16BIT },
+	[CAPS_3]	= { 0x0458, 0x00, OMAP_DMA_REG_16BIT },
+	[CAPS_4]	= { 0x045a, 0x00, OMAP_DMA_REG_16BIT },
+	[PCH2_SR]	= { 0x0460, 0x00, OMAP_DMA_REG_16BIT },
+	[PCH0_SR]	= { 0x0480, 0x00, OMAP_DMA_REG_16BIT },
+	[PCH1_SR]	= { 0x0482, 0x00, OMAP_DMA_REG_16BIT },
+	[PCHD_SR]	= { 0x04c0, 0x00, OMAP_DMA_REG_16BIT },
 
 	/* Common Registers */
-	[CSDP]		= 0x00,
-	[CCR]		= 0x02,
-	[CICR]		= 0x04,
-	[CSR]		= 0x06,
-	[CEN]		= 0x10,
-	[CFN]		= 0x12,
-	[CSFI]		= 0x14,
-	[CSEI]		= 0x16,
-	[CPC]		= 0x18,	/* 15xx only */
-	[CSAC]		= 0x18,
-	[CDAC]		= 0x1a,
-	[CDEI]		= 0x1c,
-	[CDFI]		= 0x1e,
-	[CLNK_CTRL]	= 0x28,
+	[CSDP]		= { 0x0000, 0x40, OMAP_DMA_REG_16BIT },
+	[CCR]		= { 0x0002, 0x40, OMAP_DMA_REG_16BIT },
+	[CICR]		= { 0x0004, 0x40, OMAP_DMA_REG_16BIT },
+	[CSR]		= { 0x0006, 0x40, OMAP_DMA_REG_16BIT },
+	[CEN]		= { 0x0010, 0x40, OMAP_DMA_REG_16BIT },
+	[CFN]		= { 0x0012, 0x40, OMAP_DMA_REG_16BIT },
+	[CSFI]		= { 0x0014, 0x40, OMAP_DMA_REG_16BIT },
+	[CSEI]		= { 0x0016, 0x40, OMAP_DMA_REG_16BIT },
+	[CPC]		= { 0x0018, 0x40, OMAP_DMA_REG_16BIT },	/* 15xx only */
+	[CSAC]		= { 0x0018, 0x40, OMAP_DMA_REG_16BIT },
+	[CDAC]		= { 0x001a, 0x40, OMAP_DMA_REG_16BIT },
+	[CDEI]		= { 0x001c, 0x40, OMAP_DMA_REG_16BIT },
+	[CDFI]		= { 0x001e, 0x40, OMAP_DMA_REG_16BIT },
+	[CLNK_CTRL]	= { 0x0028, 0x40, OMAP_DMA_REG_16BIT },
 
 	/* Channel specific register offsets */
-	[CSSA]		= 0x08,
-	[CDSA]		= 0x0c,
-	[COLOR]		= 0x20,
-	[CCR2]		= 0x24,
-	[LCH_CTRL]	= 0x2a,
+	[CSSA]		= { 0x0008, 0x40, OMAP_DMA_REG_2X16BIT },
+	[CDSA]		= { 0x000c, 0x40, OMAP_DMA_REG_2X16BIT },
+	[COLOR]		= { 0x0020, 0x40, OMAP_DMA_REG_2X16BIT },
+	[CCR2]		= { 0x0024, 0x40, OMAP_DMA_REG_16BIT },
+	[LCH_CTRL]	= { 0x002a, 0x40, OMAP_DMA_REG_16BIT },
 };
 
 static struct resource res[] __initdata = {
@@ -179,36 +178,28 @@ static struct resource res[] __initdata = {
 static void __iomem *dma_base;
 static inline void dma_write(u32 val, int reg, int lch)
 {
-	u8  stride;
-	u32 offset;
+	void __iomem *addr = dma_base;
 
-	stride = (reg >= CPC) ? OMAP1_DMA_STRIDE : 0;
-	offset = reg_map[reg] + (stride * lch);
+	addr += reg_map[reg].offset;
+	addr += reg_map[reg].stride * lch;
 
-	__raw_writew(val, dma_base + offset);
-	if ((reg > CLNK_CTRL && reg < CCEN) ||
-			(reg > PCHD_ID && reg < CAPS_2)) {
-		u32 offset2 = reg_map[reg] + 2 + (stride * lch);
-		__raw_writew(val >> 16, dma_base + offset2);
-	}
+	__raw_writew(val, addr);
+	if (reg_map[reg].type == OMAP_DMA_REG_2X16BIT)
+		__raw_writew(val >> 16, addr + 2);
 }
 
 static inline u32 dma_read(int reg, int lch)
 {
-	u8 stride;
-	u32 offset, val;
-
-	stride = (reg >= CPC) ? OMAP1_DMA_STRIDE : 0;
-	offset = reg_map[reg] + (stride * lch);
-
-	val = __raw_readw(dma_base + offset);
-	if ((reg > CLNK_CTRL && reg < CCEN) ||
-			(reg > PCHD_ID && reg < CAPS_2)) {
-		u16 upper;
-		u32 offset2 = reg_map[reg] + 2 + (stride * lch);
-		upper = __raw_readw(dma_base + offset2);
-		val |= (upper << 16);
-	}
+	void __iomem *addr = dma_base;
+	uint32_t val;
+
+	addr += reg_map[reg].offset;
+	addr += reg_map[reg].stride * lch;
+
+	val = __raw_readw(addr);
+	if (reg_map[reg].type == OMAP_DMA_REG_2X16BIT)
+		val |= __raw_readw(addr + 2) << 16;
+
 	return val;
 }
 
diff --git a/arch/arm/mach-omap2/dma.c b/arch/arm/mach-omap2/dma.c
index e4ac7ac9a228..e633b48a3fcb 100644
--- a/arch/arm/mach-omap2/dma.c
+++ b/arch/arm/mach-omap2/dma.c
@@ -35,80 +35,77 @@
 #include "omap_hwmod.h"
 #include "omap_device.h"
 
-#define OMAP2_DMA_STRIDE	0x60
-
 static u32 errata;
 
 static struct omap_dma_dev_attr *d;
 
 static enum omap_reg_offsets dma_common_ch_end;
 
-static u16 reg_map[] = {
-	[REVISION]		= 0x00,
-	[GCR]			= 0x78,
-	[IRQSTATUS_L0]		= 0x08,
-	[IRQSTATUS_L1]		= 0x0c,
-	[IRQSTATUS_L2]		= 0x10,
-	[IRQSTATUS_L3]		= 0x14,
-	[IRQENABLE_L0]		= 0x18,
-	[IRQENABLE_L1]		= 0x1c,
-	[IRQENABLE_L2]		= 0x20,
-	[IRQENABLE_L3]		= 0x24,
-	[SYSSTATUS]		= 0x28,
-	[OCP_SYSCONFIG]		= 0x2c,
-	[CAPS_0]		= 0x64,
-	[CAPS_2]		= 0x6c,
-	[CAPS_3]		= 0x70,
-	[CAPS_4]		= 0x74,
+static const struct omap_dma_reg reg_map[] = {
+	[REVISION]	= { 0x0000, 0x00, OMAP_DMA_REG_32BIT },
+	[GCR]		= { 0x0078, 0x00, OMAP_DMA_REG_32BIT },
+	[IRQSTATUS_L0]	= { 0x0008, 0x00, OMAP_DMA_REG_32BIT },
+	[IRQSTATUS_L1]	= { 0x000c, 0x00, OMAP_DMA_REG_32BIT },
+	[IRQSTATUS_L2]	= { 0x0010, 0x00, OMAP_DMA_REG_32BIT },
+	[IRQSTATUS_L3]	= { 0x0014, 0x00, OMAP_DMA_REG_32BIT },
+	[IRQENABLE_L0]	= { 0x0018, 0x00, OMAP_DMA_REG_32BIT },
+	[IRQENABLE_L1]	= { 0x001c, 0x00, OMAP_DMA_REG_32BIT },
+	[IRQENABLE_L2]	= { 0x0020, 0x00, OMAP_DMA_REG_32BIT },
+	[IRQENABLE_L3]	= { 0x0024, 0x00, OMAP_DMA_REG_32BIT },
+	[SYSSTATUS]	= { 0x0028, 0x00, OMAP_DMA_REG_32BIT },
+	[OCP_SYSCONFIG]	= { 0x002c, 0x00, OMAP_DMA_REG_32BIT },
+	[CAPS_0]	= { 0x0064, 0x00, OMAP_DMA_REG_32BIT },
+	[CAPS_2]	= { 0x006c, 0x00, OMAP_DMA_REG_32BIT },
+	[CAPS_3]	= { 0x0070, 0x00, OMAP_DMA_REG_32BIT },
+	[CAPS_4]	= { 0x0074, 0x00, OMAP_DMA_REG_32BIT },
 
 	/* Common register offsets */
-	[CCR]			= 0x80,
-	[CLNK_CTRL]		= 0x84,
-	[CICR]			= 0x88,
-	[CSR]			= 0x8c,
-	[CSDP]			= 0x90,
-	[CEN]			= 0x94,
-	[CFN]			= 0x98,
-	[CSEI]			= 0xa4,
-	[CSFI]			= 0xa8,
-	[CDEI]			= 0xac,
-	[CDFI]			= 0xb0,
-	[CSAC]			= 0xb4,
-	[CDAC]			= 0xb8,
+	[CCR]		= { 0x0080, 0x60, OMAP_DMA_REG_32BIT },
+	[CLNK_CTRL]	= { 0x0084, 0x60, OMAP_DMA_REG_32BIT },
+	[CICR]		= { 0x0088, 0x60, OMAP_DMA_REG_32BIT },
+	[CSR]		= { 0x008c, 0x60, OMAP_DMA_REG_32BIT },
+	[CSDP]		= { 0x0090, 0x60, OMAP_DMA_REG_32BIT },
+	[CEN]		= { 0x0094, 0x60, OMAP_DMA_REG_32BIT },
+	[CFN]		= { 0x0098, 0x60, OMAP_DMA_REG_32BIT },
+	[CSEI]		= { 0x00a4, 0x60, OMAP_DMA_REG_32BIT },
+	[CSFI]		= { 0x00a8, 0x60, OMAP_DMA_REG_32BIT },
+	[CDEI]		= { 0x00ac, 0x60, OMAP_DMA_REG_32BIT },
+	[CDFI]		= { 0x00b0, 0x60, OMAP_DMA_REG_32BIT },
+	[CSAC]		= { 0x00b4, 0x60, OMAP_DMA_REG_32BIT },
+	[CDAC]		= { 0x00b8, 0x60, OMAP_DMA_REG_32BIT },
 
 	/* Channel specific register offsets */
-	[CSSA]			= 0x9c,
-	[CDSA]			= 0xa0,
-	[CCEN]			= 0xbc,
-	[CCFN]			= 0xc0,
-	[COLOR]			= 0xc4,
+	[CSSA]		= { 0x009c, 0x60, OMAP_DMA_REG_32BIT },
+	[CDSA]		= { 0x00a0, 0x60, OMAP_DMA_REG_32BIT },
+	[CCEN]		= { 0x00bc, 0x60, OMAP_DMA_REG_32BIT },
+	[CCFN]		= { 0x00c0, 0x60, OMAP_DMA_REG_32BIT },
+	[COLOR]		= { 0x00c4, 0x60, OMAP_DMA_REG_32BIT },
 
 	/* OMAP4 specific registers */
-	[CDP]			= 0xd0,
-	[CNDP]			= 0xd4,
-	[CCDN]			= 0xd8,
+	[CDP]		= { 0x00d0, 0x60, OMAP_DMA_REG_32BIT },
+	[CNDP]		= { 0x00d4, 0x60, OMAP_DMA_REG_32BIT },
+	[CCDN]		= { 0x00d8, 0x60, OMAP_DMA_REG_32BIT },
 };
 
 static void __iomem *dma_base;
 static inline void dma_write(u32 val, int reg, int lch)
 {
-	u8  stride;
-	u32 offset;
+	void __iomem *addr = dma_base;
+
+	addr += reg_map[reg].offset;
+	addr += reg_map[reg].stride * lch;
 
-	stride = (reg >= CSDP) ? OMAP2_DMA_STRIDE : 0;
-	offset = reg_map[reg] + (stride * lch);
-	__raw_writel(val, dma_base + offset);
+	__raw_writel(val, addr);
 }
 
 static inline u32 dma_read(int reg, int lch)
 {
-	u8 stride;
-	u32 offset, val;
+	void __iomem *addr = dma_base;
+
+	addr += reg_map[reg].offset;
+	addr += reg_map[reg].stride * lch;
 
-	stride = (reg >= CSDP) ? OMAP2_DMA_STRIDE : 0;
-	offset = reg_map[reg] + (stride * lch);
-	val = __raw_readl(dma_base + offset);
-	return val;
+	return __raw_readl(addr);
 }
 
 static void omap2_clear_dma(int lch)
diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h
index 0bb7de77d478..41328725721a 100644
--- a/include/linux/omap-dma.h
+++ b/include/linux/omap-dma.h
@@ -271,6 +271,19 @@ struct omap_dma_dev_attr {
 	struct omap_dma_lch *chan;
 };
 
+enum {
+	OMAP_DMA_REG_NONE,
+	OMAP_DMA_REG_16BIT,
+	OMAP_DMA_REG_2X16BIT,
+	OMAP_DMA_REG_32BIT,
+};
+
+struct omap_dma_reg {
+	u16	offset;
+	u8	stride;
+	u8	type;
+};
+
 /* System DMA platform data structure */
 struct omap_system_dma_plat_info {
 	struct omap_dma_dev_attr *dma_attr;
-- 
cgit v1.2.3


From 9834f81314b2a5b1bb3cd0d8f46e61528b60d580 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Fri, 8 Nov 2013 18:10:42 +0000
Subject: ARM: omap: move dma channel allocation into plat-omap code

This really needs to be there, because otherwise the plat-omap code can
kfree() this data structure, and then re-use the pointer later.

Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/mach-omap1/dma.c | 17 ++---------------
 arch/arm/mach-omap2/dma.c |  7 -------
 arch/arm/plat-omap/dma.c  | 11 ++++++++---
 include/linux/omap-dma.h  |  1 -
 4 files changed, 10 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-omap1/dma.c b/arch/arm/mach-omap1/dma.c
index c979e3f88bbb..d170f7d0a6ac 100644
--- a/arch/arm/mach-omap1/dma.c
+++ b/arch/arm/mach-omap1/dma.c
@@ -325,17 +325,6 @@ static int __init omap1_system_dma_init(void)
 	d->dev_caps		|= CLEAR_CSR_ON_READ;
 	d->dev_caps		|= IS_WORD_16;
 
-
-	d->chan = kzalloc(sizeof(struct omap_dma_lch) *
-					(d->lch_count), GFP_KERNEL);
-	if (!d->chan) {
-		dev_err(&pdev->dev,
-			"%s: Memory allocation failed for d->chan!\n",
-			__func__);
-		ret = -ENOMEM;
-		goto exit_release_d;
-	}
-
 	if (cpu_is_omap15xx())
 		d->chan_count = 9;
 	else if (cpu_is_omap16xx() || cpu_is_omap7xx()) {
@@ -359,14 +348,14 @@ static int __init omap1_system_dma_init(void)
 	if (ret) {
 		dev_err(&pdev->dev, "%s: Unable to add resources for %s%d\n",
 			__func__, pdev->name, pdev->id);
-		goto exit_release_chan;
+		goto exit_release_d;
 	}
 
 	ret = platform_device_add(pdev);
 	if (ret) {
 		dev_err(&pdev->dev, "%s: Unable to add resources for %s%d\n",
 			__func__, pdev->name, pdev->id);
-		goto exit_release_chan;
+		goto exit_release_d;
 	}
 
 	dma_pdev = platform_device_register_full(&omap_dma_dev_info);
@@ -379,8 +368,6 @@ static int __init omap1_system_dma_init(void)
 
 exit_release_pdev:
 	platform_device_del(pdev);
-exit_release_chan:
-	kfree(d->chan);
 exit_release_d:
 	kfree(d);
 exit_release_p:
diff --git a/arch/arm/mach-omap2/dma.c b/arch/arm/mach-omap2/dma.c
index 244ff5012aed..9f210d637354 100644
--- a/arch/arm/mach-omap2/dma.c
+++ b/arch/arm/mach-omap2/dma.c
@@ -251,13 +251,6 @@ static int __init omap2_system_dma_init_dev(struct omap_hwmod *oh, void *unused)
 	}
 
 	d = oh->dev_attr;
-	d->chan = kzalloc(sizeof(struct omap_dma_lch) *
-					(d->lch_count), GFP_KERNEL);
-
-	if (!d->chan) {
-		dev_err(&pdev->dev, "%s: kzalloc fail\n", __func__);
-		return -ENOMEM;
-	}
 
 	if (cpu_is_omap34xx() && (omap_type() != OMAP2_DEVICE_TYPE_GP))
 		d->dev_caps |= HS_CHANNELS_RESERVED;
diff --git a/arch/arm/plat-omap/dma.c b/arch/arm/plat-omap/dma.c
index d4d9a5e62152..5f5b975887fc 100644
--- a/arch/arm/plat-omap/dma.c
+++ b/arch/arm/plat-omap/dma.c
@@ -2030,9 +2030,16 @@ static int omap_system_dma_probe(struct platform_device *pdev)
 
 	dma_lch_count		= d->lch_count;
 	dma_chan_count		= dma_lch_count;
-	dma_chan		= d->chan;
 	enable_1510_mode	= d->dev_caps & ENABLE_1510_MODE;
 
+	dma_chan = devm_kcalloc(&pdev->dev, dma_lch_count,
+				sizeof(struct omap_dma_lch), GFP_KERNEL);
+	if (!dma_chan) {
+		dev_err(&pdev->dev, "%s: kzalloc fail\n", __func__);
+		return -ENOMEM;
+	}
+
+
 	if (dma_omap2plus()) {
 		dma_linked_lch = kzalloc(sizeof(struct dma_link_info) *
 						dma_lch_count, GFP_KERNEL);
@@ -2117,7 +2124,6 @@ exit_dma_irq_fail:
 	}
 
 exit_dma_lch_fail:
-	kfree(dma_chan);
 	return ret;
 }
 
@@ -2137,7 +2143,6 @@ static int omap_system_dma_remove(struct platform_device *pdev)
 			free_irq(dma_irq, (void *)(irq_rel + 1));
 		}
 	}
-	kfree(dma_chan);
 	return 0;
 }
 
diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h
index 41328725721a..7813636a193d 100644
--- a/include/linux/omap-dma.h
+++ b/include/linux/omap-dma.h
@@ -268,7 +268,6 @@ struct omap_dma_dev_attr {
 	u32 dev_caps;
 	u16 lch_count;
 	u16 chan_count;
-	struct omap_dma_lch *chan;
 };
 
 enum {
-- 
cgit v1.2.3


From 596c471b69249764d8e241b004736878204daa0f Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Tue, 10 Dec 2013 11:08:01 +0000
Subject: dmaengine: omap-dma: move register read/writes into omap-dma.c

Export the DMA register information from the SoC specific data, such
that we can access the registers directly in omap-dma.c, mapping the
register region ourselves as well.

Rather than calculating the DMA channel register in its entirety for
each access, we pre-calculate an offset base address for the allocated
DMA channel and then just use the appropriate register offset.

Acked-by: Tony Lindgren <tony@atomide.com>
Acked-by: Vinod Koul <vinod.koul@intel.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/mach-omap1/dma.c |  4 ++
 arch/arm/mach-omap2/dma.c | 18 ++++++---
 drivers/dma/omap-dma.c    | 96 ++++++++++++++++++++++++++++++++++++++++++-----
 include/linux/omap-dma.h  |  2 +
 4 files changed, 105 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mach-omap1/dma.c b/arch/arm/mach-omap1/dma.c
index a8c83ccc36fb..4be601b638d7 100644
--- a/arch/arm/mach-omap1/dma.c
+++ b/arch/arm/mach-omap1/dma.c
@@ -261,9 +261,13 @@ static const struct platform_device_info omap_dma_dev_info = {
 	.name = "omap-dma-engine",
 	.id = -1,
 	.dma_mask = DMA_BIT_MASK(32),
+	.res = res,
+	.num_res = 1,
 };
 
 static struct omap_system_dma_plat_info dma_plat_info __initdata = {
+	.reg_map	= reg_map,
+	.channel_stride	= 0x40,
 	.show_dma_caps	= omap1_show_dma_caps,
 	.clear_lch_regs	= omap1_clear_lch_regs,
 	.clear_dma	= omap1_clear_dma,
diff --git a/arch/arm/mach-omap2/dma.c b/arch/arm/mach-omap2/dma.c
index 6331fc4b4054..5689c88d986d 100644
--- a/arch/arm/mach-omap2/dma.c
+++ b/arch/arm/mach-omap2/dma.c
@@ -205,12 +205,20 @@ static unsigned configure_dma_errata(void)
 }
 
 static struct omap_system_dma_plat_info dma_plat_info __initdata = {
+	.reg_map	= reg_map,
+	.channel_stride	= 0x60,
 	.show_dma_caps	= omap2_show_dma_caps,
 	.clear_dma	= omap2_clear_dma,
 	.dma_write	= dma_write,
 	.dma_read	= dma_read,
 };
 
+static struct platform_device_info omap_dma_dev_info = {
+	.name = "omap-dma-engine",
+	.id = -1,
+	.dma_mask = DMA_BIT_MASK(32),
+};
+
 /* One time initializations */
 static int __init omap2_system_dma_init_dev(struct omap_hwmod *oh, void *unused)
 {
@@ -231,11 +239,15 @@ static int __init omap2_system_dma_init_dev(struct omap_hwmod *oh, void *unused)
 		return PTR_ERR(pdev);
 	}
 
+	omap_dma_dev_info.res = pdev->resource;
+	omap_dma_dev_info.num_res = pdev->num_resources;
+
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!mem) {
 		dev_err(&pdev->dev, "%s: no mem resource\n", __func__);
 		return -EINVAL;
 	}
+
 	dma_base = ioremap(mem->start, resource_size(mem));
 	if (!dma_base) {
 		dev_err(&pdev->dev, "%s: ioremap fail\n", __func__);
@@ -256,12 +268,6 @@ static int __init omap2_system_dma_init_dev(struct omap_hwmod *oh, void *unused)
 	return 0;
 }
 
-static const struct platform_device_info omap_dma_dev_info = {
-	.name = "omap-dma-engine",
-	.id = -1,
-	.dma_mask = DMA_BIT_MASK(32),
-};
-
 static int __init omap2_system_dma_init(void)
 {
 	struct platform_device *pdev;
diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c
index 1e0018f36384..00f8e566cf12 100644
--- a/drivers/dma/omap-dma.c
+++ b/drivers/dma/omap-dma.c
@@ -27,13 +27,16 @@ struct omap_dmadev {
 	spinlock_t lock;
 	struct tasklet_struct task;
 	struct list_head pending;
+	void __iomem *base;
+	const struct omap_dma_reg *reg_map;
 	struct omap_system_dma_plat_info *plat;
 };
 
 struct omap_chan {
 	struct virt_dma_chan vc;
 	struct list_head node;
-	struct omap_system_dma_plat_info *plat;
+	void __iomem *channel_base;
+	const struct omap_dma_reg *reg_map;
 
 	struct dma_slave_config	cfg;
 	unsigned dma_sig;
@@ -170,24 +173,77 @@ static void omap_dma_desc_free(struct virt_dma_desc *vd)
 	kfree(container_of(vd, struct omap_desc, vd));
 }
 
+static void omap_dma_write(uint32_t val, unsigned type, void __iomem *addr)
+{
+	switch (type) {
+	case OMAP_DMA_REG_16BIT:
+		writew_relaxed(val, addr);
+		break;
+	case OMAP_DMA_REG_2X16BIT:
+		writew_relaxed(val, addr);
+		writew_relaxed(val >> 16, addr + 2);
+		break;
+	case OMAP_DMA_REG_32BIT:
+		writel_relaxed(val, addr);
+		break;
+	default:
+		WARN_ON(1);
+	}
+}
+
+static unsigned omap_dma_read(unsigned type, void __iomem *addr)
+{
+	unsigned val;
+
+	switch (type) {
+	case OMAP_DMA_REG_16BIT:
+		val = readw_relaxed(addr);
+		break;
+	case OMAP_DMA_REG_2X16BIT:
+		val = readw_relaxed(addr);
+		val |= readw_relaxed(addr + 2) << 16;
+		break;
+	case OMAP_DMA_REG_32BIT:
+		val = readl_relaxed(addr);
+		break;
+	default:
+		WARN_ON(1);
+		val = 0;
+	}
+
+	return val;
+}
+
 static void omap_dma_glbl_write(struct omap_dmadev *od, unsigned reg, unsigned val)
 {
-	od->plat->dma_write(val, reg, 0);
+	const struct omap_dma_reg *r = od->reg_map + reg;
+
+	WARN_ON(r->stride);
+
+	omap_dma_write(val, r->type, od->base + r->offset);
 }
 
 static unsigned omap_dma_glbl_read(struct omap_dmadev *od, unsigned reg)
 {
-	return od->plat->dma_read(reg, 0);
+	const struct omap_dma_reg *r = od->reg_map + reg;
+
+	WARN_ON(r->stride);
+
+	return omap_dma_read(r->type, od->base + r->offset);
 }
 
 static void omap_dma_chan_write(struct omap_chan *c, unsigned reg, unsigned val)
 {
-	c->plat->dma_write(val, reg, c->dma_ch);
+	const struct omap_dma_reg *r = c->reg_map + reg;
+
+	omap_dma_write(val, r->type, c->channel_base + r->offset);
 }
 
 static unsigned omap_dma_chan_read(struct omap_chan *c, unsigned reg)
 {
-	return c->plat->dma_read(reg, c->dma_ch);
+	const struct omap_dma_reg *r = c->reg_map + reg;
+
+	return omap_dma_read(r->type, c->channel_base + r->offset);
 }
 
 static void omap_dma_clear_csr(struct omap_chan *c)
@@ -198,6 +254,12 @@ static void omap_dma_clear_csr(struct omap_chan *c)
 		omap_dma_chan_write(c, CSR, ~0);
 }
 
+static void omap_dma_assign(struct omap_dmadev *od, struct omap_chan *c,
+	unsigned lch)
+{
+	c->channel_base = od->base + od->plat->channel_stride * lch;
+}
+
 static void omap_dma_start(struct omap_chan *c, struct omap_desc *d)
 {
 	struct omap_dmadev *od = to_omap_dma_dev(c->vc.chan.device);
@@ -400,18 +462,26 @@ static void omap_dma_sched(unsigned long data)
 
 static int omap_dma_alloc_chan_resources(struct dma_chan *chan)
 {
+	struct omap_dmadev *od = to_omap_dma_dev(chan->device);
 	struct omap_chan *c = to_omap_dma_chan(chan);
+	int ret;
+
+	dev_dbg(od->ddev.dev, "allocating channel for %u\n", c->dma_sig);
 
-	dev_dbg(c->vc.chan.device->dev, "allocating channel for %u\n", c->dma_sig);
+	ret = omap_request_dma(c->dma_sig, "DMA engine", omap_dma_callback,
+			       c, &c->dma_ch);
 
-	return omap_request_dma(c->dma_sig, "DMA engine",
-		omap_dma_callback, c, &c->dma_ch);
+	if (ret >= 0)
+		omap_dma_assign(od, c, c->dma_ch);
+
+	return ret;
 }
 
 static void omap_dma_free_chan_resources(struct dma_chan *chan)
 {
 	struct omap_chan *c = to_omap_dma_chan(chan);
 
+	c->channel_base = NULL;
 	vchan_free_chan_resources(&c->vc);
 	omap_free_dma(c->dma_ch);
 
@@ -917,7 +987,7 @@ static int omap_dma_chan_init(struct omap_dmadev *od, int dma_sig)
 	if (!c)
 		return -ENOMEM;
 
-	c->plat = od->plat;
+	c->reg_map = od->reg_map;
 	c->dma_sig = dma_sig;
 	c->vc.desc_free = omap_dma_desc_free;
 	vchan_init(&c->vc, &od->ddev);
@@ -944,16 +1014,24 @@ static void omap_dma_free(struct omap_dmadev *od)
 static int omap_dma_probe(struct platform_device *pdev)
 {
 	struct omap_dmadev *od;
+	struct resource *res;
 	int rc, i;
 
 	od = devm_kzalloc(&pdev->dev, sizeof(*od), GFP_KERNEL);
 	if (!od)
 		return -ENOMEM;
 
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	od->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(od->base))
+		return PTR_ERR(od->base);
+
 	od->plat = omap_get_plat_info();
 	if (!od->plat)
 		return -EPROBE_DEFER;
 
+	od->reg_map = od->plat->reg_map;
+
 	dma_cap_set(DMA_SLAVE, od->ddev.cap_mask);
 	dma_cap_set(DMA_CYCLIC, od->ddev.cap_mask);
 	od->ddev.device_alloc_chan_resources = omap_dma_alloc_chan_resources;
diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h
index 7813636a193d..41a13e70f41f 100644
--- a/include/linux/omap-dma.h
+++ b/include/linux/omap-dma.h
@@ -285,6 +285,8 @@ struct omap_dma_reg {
 
 /* System DMA platform data structure */
 struct omap_system_dma_plat_info {
+	const struct omap_dma_reg *reg_map;
+	unsigned channel_stride;
 	struct omap_dma_dev_attr *dma_attr;
 	u32 errata;
 	void (*show_dma_caps)(void);
-- 
cgit v1.2.3


From 64400c3791d9fcebf23318a289f9da964547a6f3 Mon Sep 17 00:00:00 2001
From: Bryan Wu <pengw@nvidia.com>
Date: Wed, 19 Feb 2014 14:48:36 -0800
Subject: gpu: host1x: export host1x_syncpt_incr_max() function

Tegra V4L2 camera driver needs this function to do frame capture.

Signed-off-by: Bryan Wu <pengw@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
---
 drivers/gpu/host1x/syncpt.c | 1 +
 include/linux/host1x.h      | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/gpu/host1x/syncpt.c b/drivers/gpu/host1x/syncpt.c
index bfb09d802abd..b10550ee1d89 100644
--- a/drivers/gpu/host1x/syncpt.c
+++ b/drivers/gpu/host1x/syncpt.c
@@ -102,6 +102,7 @@ u32 host1x_syncpt_incr_max(struct host1x_syncpt *sp, u32 incrs)
 {
 	return (u32)atomic_add_return(incrs, &sp->max_val);
 }
+EXPORT_SYMBOL(host1x_syncpt_incr_max);
 
  /*
  * Write cached syncpoint and waitbase values to hardware.
diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index 3af847273277..d2b52999e771 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -136,6 +136,7 @@ u32 host1x_syncpt_id(struct host1x_syncpt *sp);
 u32 host1x_syncpt_read_min(struct host1x_syncpt *sp);
 u32 host1x_syncpt_read_max(struct host1x_syncpt *sp);
 int host1x_syncpt_incr(struct host1x_syncpt *sp);
+u32 host1x_syncpt_incr_max(struct host1x_syncpt *sp, u32 incrs);
 int host1x_syncpt_wait(struct host1x_syncpt *sp, u32 thresh, long timeout,
 		       u32 *value);
 struct host1x_syncpt *host1x_syncpt_request(struct device *dev,
-- 
cgit v1.2.3


From eb13e832f823f6c110ea53e3067bafe22b87de63 Mon Sep 17 00:00:00 2001
From: "Yan, Zheng" <zheng.z.yan@intel.com>
Date: Sun, 9 Mar 2014 23:16:40 +0800
Subject: ceph: use fl->fl_file as owner identifier of flock and posix lock

flock and posix lock should use fl->fl_file instead of process ID
as owner identifier. (posix lock uses fl->fl_owner. fl->fl_owner
is usually equal to fl->fl_file, but it also can be a customized
value). The process ID of who holds the lock is just for F_GETLK
fcntl(2).

The fix is rename the 'pid' fields of struct ceph_mds_request_args
and struct ceph_filelock to 'owner', rename 'pid_namespace' fields
to 'pid'. Assign fl->fl_file to the 'owner' field of lock messages.
We also set the most significant bit of the 'owner' field. MDS can
use that bit to distinguish between old and new clients.

The MDS counterpart of this patch modifies the flock code to not
take the 'pid_namespace' into consideration when checking conflict
locks.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Sage Weil <sage@inktank.com>
---
 fs/ceph/locks.c              | 61 +++++++++++++++++++++++++++++---------------
 fs/ceph/super.c              |  1 +
 fs/ceph/super.h              |  1 +
 include/linux/ceph/ceph_fs.h |  4 +--
 4 files changed, 45 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index f91a569a20fb..d94ba0df9f4d 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -2,11 +2,31 @@
 
 #include <linux/file.h>
 #include <linux/namei.h>
+#include <linux/random.h>
 
 #include "super.h"
 #include "mds_client.h"
 #include <linux/ceph/pagelist.h>
 
+static u64 lock_secret;
+
+static inline u64 secure_addr(void *addr)
+{
+	u64 v = lock_secret ^ (u64)(unsigned long)addr;
+	/*
+	 * Set the most significant bit, so that MDS knows the 'owner'
+	 * is sufficient to identify the owner of lock. (old code uses
+	 * both 'owner' and 'pid')
+	 */
+	v |= (1ULL << 63);
+	return v;
+}
+
+void __init ceph_flock_init(void)
+{
+	get_random_bytes(&lock_secret, sizeof(lock_secret));
+}
+
 /**
  * Implement fcntl and flock locking functions.
  */
@@ -14,11 +34,11 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
 			     int cmd, u8 wait, struct file_lock *fl)
 {
 	struct inode *inode = file_inode(file);
-	struct ceph_mds_client *mdsc =
-		ceph_sb_to_client(inode->i_sb)->mdsc;
+	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 	struct ceph_mds_request *req;
 	int err;
 	u64 length = 0;
+	u64 owner;
 
 	req = ceph_mdsc_create_request(mdsc, operation, USE_AUTH_MDS);
 	if (IS_ERR(req))
@@ -32,25 +52,27 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
 	else
 		length = fl->fl_end - fl->fl_start + 1;
 
-	dout("ceph_lock_message: rule: %d, op: %d, pid: %llu, start: %llu, "
-	     "length: %llu, wait: %d, type: %d", (int)lock_type,
-	     (int)operation, (u64)fl->fl_pid, fl->fl_start,
-	     length, wait, fl->fl_type);
+	if (lock_type == CEPH_LOCK_FCNTL)
+		owner = secure_addr(fl->fl_owner);
+	else
+		owner = secure_addr(fl->fl_file);
+
+	dout("ceph_lock_message: rule: %d, op: %d, owner: %llx, pid: %llu, "
+	     "start: %llu, length: %llu, wait: %d, type: %d", (int)lock_type,
+	     (int)operation, owner, (u64)fl->fl_pid, fl->fl_start, length,
+	     wait, fl->fl_type);
 
 	req->r_args.filelock_change.rule = lock_type;
 	req->r_args.filelock_change.type = cmd;
+	req->r_args.filelock_change.owner = cpu_to_le64(owner);
 	req->r_args.filelock_change.pid = cpu_to_le64((u64)fl->fl_pid);
-	/* This should be adjusted, but I'm not sure if
-	   namespaces actually get id numbers*/
-	req->r_args.filelock_change.pid_namespace =
-		cpu_to_le64((u64)(unsigned long)fl->fl_nspid);
 	req->r_args.filelock_change.start = cpu_to_le64(fl->fl_start);
 	req->r_args.filelock_change.length = cpu_to_le64(length);
 	req->r_args.filelock_change.wait = wait;
 
 	err = ceph_mdsc_do_request(mdsc, inode, req);
 
-	if ( operation == CEPH_MDS_OP_GETFILELOCK){
+	if (operation == CEPH_MDS_OP_GETFILELOCK) {
 		fl->fl_pid = le64_to_cpu(req->r_reply_info.filelock_reply->pid);
 		if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type)
 			fl->fl_type = F_RDLCK;
@@ -93,8 +115,7 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
 	if (__mandatory_lock(file->f_mapping->host) && fl->fl_type != F_UNLCK)
 		return -ENOLCK;
 
-	fl->fl_nspid = get_pid(task_tgid(current));
-	dout("ceph_lock, fl_pid:%d", fl->fl_pid);
+	dout("ceph_lock, fl_owner: %p", fl->fl_owner);
 
 	/* set wait bit as appropriate, then make command as Ceph expects it*/
 	if (IS_GETLK(cmd))
@@ -111,7 +132,7 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl)
 
 	err = ceph_lock_message(CEPH_LOCK_FCNTL, op, file, lock_cmd, wait, fl);
 	if (!err) {
-		if ( op != CEPH_MDS_OP_GETFILELOCK ){
+		if (op != CEPH_MDS_OP_GETFILELOCK) {
 			dout("mds locked, locking locally");
 			err = posix_lock_file(file, fl, NULL);
 			if (err && (CEPH_MDS_OP_SETFILELOCK == op)) {
@@ -145,8 +166,7 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
 	if (__mandatory_lock(file->f_mapping->host) && fl->fl_type != F_UNLCK)
 		return -ENOLCK;
 
-	fl->fl_nspid = get_pid(task_tgid(current));
-	dout("ceph_flock, fl_pid:%d", fl->fl_pid);
+	dout("ceph_flock, fl_file: %p", fl->fl_file);
 
 	if (IS_SETLKW(cmd))
 		wait = 1;
@@ -289,13 +309,14 @@ int lock_to_ceph_filelock(struct file_lock *lock,
 			  struct ceph_filelock *cephlock)
 {
 	int err = 0;
-
 	cephlock->start = cpu_to_le64(lock->fl_start);
 	cephlock->length = cpu_to_le64(lock->fl_end - lock->fl_start + 1);
 	cephlock->client = cpu_to_le64(0);
-	cephlock->pid = cpu_to_le64(lock->fl_pid);
-	cephlock->pid_namespace =
-	        cpu_to_le64((u64)(unsigned long)lock->fl_nspid);
+	cephlock->pid = cpu_to_le64((u64)lock->fl_pid);
+	if (lock->fl_flags & FL_POSIX)
+		cephlock->owner = cpu_to_le64(secure_addr(lock->fl_owner));
+	else
+		cephlock->owner = cpu_to_le64(secure_addr(lock->fl_file));
 
 	switch (lock->fl_type) {
 	case F_RDLCK:
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 10a4ccbf38da..06150fd745ac 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -1026,6 +1026,7 @@ static int __init init_ceph(void)
 	if (ret)
 		goto out;
 
+	ceph_flock_init();
 	ceph_xattr_init();
 	ret = register_filesystem(&ceph_fs_type);
 	if (ret)
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 70bb183385b7..7866cd05a6bb 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -871,6 +871,7 @@ extern long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 extern const struct export_operations ceph_export_ops;
 
 /* locks.c */
+extern __init void ceph_flock_init(void);
 extern int ceph_lock(struct file *file, int cmd, struct file_lock *fl);
 extern int ceph_flock(struct file *file, int cmd, struct file_lock *fl);
 extern void ceph_count_locks(struct inode *inode, int *p_num, int *f_num);
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 35f345f7b3a3..5f6db18d72e8 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -421,8 +421,8 @@ union ceph_mds_request_args {
 	struct {
 		__u8 rule; /* currently fcntl or flock */
 		__u8 type; /* shared, exclusive, remove*/
+		__le64 owner; /* owner of the lock */
 		__le64 pid; /* process id requesting the lock */
-		__le64 pid_namespace;
 		__le64 start; /* initial location to lock */
 		__le64 length; /* num bytes to lock from start */
 		__u8 wait; /* will caller wait for lock to become available? */
@@ -533,8 +533,8 @@ struct ceph_filelock {
 	__le64 start;/* file offset to start lock at */
 	__le64 length; /* num bytes to lock; 0 for all following start */
 	__le64 client; /* which client holds the lock */
+	__le64 owner; /* owner the lock */
 	__le64 pid; /* process id holding the lock on the client */
-	__le64 pid_namespace;
 	__u8 type; /* shared lock, exclusive lock, or unlock */
 } __attribute__ ((packed));
 
-- 
cgit v1.2.3


From e2b149cc4ba00766aceb87950c6de72ea7fc8b2e Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <ilya.dryomov@inktank.com>
Date: Wed, 19 Mar 2014 16:58:37 +0200
Subject: crush: add chooseleaf_vary_r tunable

The current crush_choose_firstn code will re-use the same 'r' value for
the recursive call.  That means that if we are hitting a collision or
rejection for some reason (say, an OSD that is marked out) and need to
retry, we will keep making the same (bad) choice in that recursive
selection.

Introduce a tunable that fixes that behavior by incorporating the parent
'r' value into the recursive starting point, so that a different path
will be taken in subsequent placement attempts.

Note that this was done from the get-go for the new crush_choose_indep
algorithm.

This was exposed by a user who was seeing PGs stuck in active+remapped
after reweight-by-utilization because the up set mapped to a single OSD.

Reflects ceph.git commit a8e6c9fbf88bad056dd05d3eb790e98a5e43451a.

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
---
 include/linux/crush/crush.h |  6 ++++++
 net/ceph/crush/mapper.c     | 30 ++++++++++++++++++++++++------
 2 files changed, 30 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h
index acaa5615d634..75f36a6c7f67 100644
--- a/include/linux/crush/crush.h
+++ b/include/linux/crush/crush.h
@@ -173,6 +173,12 @@ struct crush_map {
 	 * apply to a collision: in that case we will retry as we used
 	 * to. */
 	__u32 chooseleaf_descend_once;
+
+	/* if non-zero, feed r into chooseleaf, bit-shifted right by (r-1)
+	 * bits.  a value of 1 is best for new clusters.  for legacy clusters
+	 * that want to limit reshuffling, a value of 3 or 4 will make the
+	 * mappings line up a bit better with previous mappings. */
+	__u8 chooseleaf_vary_r;
 };
 
 
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index b3fb84903b30..947150cde297 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -295,7 +295,9 @@ static int is_out(const struct crush_map *map,
  * @local_retries: localized retries
  * @local_fallback_retries: localized fallback retries
  * @recurse_to_leaf: true if we want one device under each item of given type (chooseleaf instead of choose)
+ * @vary_r: pass r to recursive calls
  * @out2: second output vector for leaf items (if @recurse_to_leaf)
+ * @parent_r: r value passed from the parent
  */
 static int crush_choose_firstn(const struct crush_map *map,
 			       struct crush_bucket *bucket,
@@ -307,7 +309,9 @@ static int crush_choose_firstn(const struct crush_map *map,
 			       unsigned int local_retries,
 			       unsigned int local_fallback_retries,
 			       int recurse_to_leaf,
-			       int *out2)
+			       unsigned int vary_r,
+			       int *out2,
+			       int parent_r)
 {
 	int rep;
 	unsigned int ftotal, flocal;
@@ -319,8 +323,11 @@ static int crush_choose_firstn(const struct crush_map *map,
 	int itemtype;
 	int collide, reject;
 
-	dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d\n", recurse_to_leaf ? "_LEAF" : "",
-		bucket->id, x, outpos, numrep);
+	dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d tries %d recurse_tries %d local_retries %d local_fallback_retries %d parent_r %d\n",
+		recurse_to_leaf ? "_LEAF" : "",
+		bucket->id, x, outpos, numrep,
+		tries, recurse_tries, local_retries, local_fallback_retries,
+		parent_r);
 
 	for (rep = outpos; rep < numrep; rep++) {
 		/* keep trying until we get a non-out, non-colliding item */
@@ -335,7 +342,7 @@ static int crush_choose_firstn(const struct crush_map *map,
 			do {
 				collide = 0;
 				retry_bucket = 0;
-				r = rep;
+				r = rep + parent_r;
 				/* r' = r + f_total */
 				r += ftotal;
 
@@ -387,6 +394,11 @@ static int crush_choose_firstn(const struct crush_map *map,
 				reject = 0;
 				if (!collide && recurse_to_leaf) {
 					if (item < 0) {
+						int sub_r;
+						if (vary_r)
+							sub_r = r >> (vary_r-1);
+						else
+							sub_r = 0;
 						if (crush_choose_firstn(map,
 							 map->buckets[-1-item],
 							 weight, weight_max,
@@ -396,7 +408,9 @@ static int crush_choose_firstn(const struct crush_map *map,
 							 local_retries,
 							 local_fallback_retries,
 							 0,
-							 NULL) <= outpos)
+							 vary_r,
+							 NULL,
+							 sub_r) <= outpos)
 							/* didn't get leaf */
 							reject = 1;
 					} else {
@@ -653,6 +667,8 @@ int crush_do_rule(const struct crush_map *map,
 	int choose_local_retries = map->choose_local_tries;
 	int choose_local_fallback_retries = map->choose_local_fallback_tries;
 
+	int vary_r = map->chooseleaf_vary_r;
+
 	if ((__u32)ruleno >= map->max_rules) {
 		dprintk(" bad ruleno %d\n", ruleno);
 		return 0;
@@ -745,7 +761,9 @@ int crush_do_rule(const struct crush_map *map,
 						choose_local_retries,
 						choose_local_fallback_retries,
 						recurse_to_leaf,
-						c+osize);
+						vary_r,
+						c+osize,
+						0);
 				} else {
 					crush_choose_indep(
 						map,
-- 
cgit v1.2.3


From d83ed858f144e3cfbef883d4bc499113cdddabeb Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <ilya.dryomov@inktank.com>
Date: Wed, 19 Mar 2014 16:58:37 +0200
Subject: crush: add SET_CHOOSELEAF_VARY_R step

This lets you adjust the vary_r tunable on a per-rule basis.

Reflects ceph.git commit f944ccc20aee60a7d8da7e405ec75ad1cd449fac.

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
---
 include/linux/crush/crush.h | 1 +
 net/ceph/crush/mapper.c     | 5 +++++
 2 files changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h
index 75f36a6c7f67..4fad5f8ee01d 100644
--- a/include/linux/crush/crush.h
+++ b/include/linux/crush/crush.h
@@ -51,6 +51,7 @@ enum {
 	CRUSH_RULE_SET_CHOOSELEAF_TRIES = 9, /* override chooseleaf_descend_once */
 	CRUSH_RULE_SET_CHOOSE_LOCAL_TRIES = 10,
 	CRUSH_RULE_SET_CHOOSE_LOCAL_FALLBACK_TRIES = 11,
+	CRUSH_RULE_SET_CHOOSELEAF_VARY_R = 12
 };
 
 /*
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index 947150cde297..a1ef53c04415 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -709,6 +709,11 @@ int crush_do_rule(const struct crush_map *map,
 				choose_local_fallback_retries = curstep->arg1;
 			break;
 
+		case CRUSH_RULE_SET_CHOOSELEAF_VARY_R:
+			if (curstep->arg1 >= 0)
+				vary_r = curstep->arg1;
+			break;
+
 		case CRUSH_RULE_CHOOSELEAF_FIRSTN:
 		case CRUSH_RULE_CHOOSE_FIRSTN:
 			firstn = 1;
-- 
cgit v1.2.3


From 07bd7de47a65767432ceb66d4ab30cdc05ed2b35 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <ilya.dryomov@inktank.com>
Date: Wed, 19 Mar 2014 16:58:37 +0200
Subject: crush: support chooseleaf_vary_r tunable (tunables3) by default

Add TUNABLES3 feature (chooseleaf_vary_r tunable) to a set of features
supported by default.

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
---
 include/linux/ceph/ceph_features.h | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index 138448f766b4..77c097fe9ea9 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -43,6 +43,13 @@
 #define CEPH_FEATURE_CRUSH_V2      (1ULL<<36)  /* new indep; SET_* steps */
 #define CEPH_FEATURE_EXPORT_PEER   (1ULL<<37)
 #define CEPH_FEATURE_OSD_ERASURE_CODES (1ULL<<38)
+#define CEPH_FEATURE_OSD_TMAP2OMAP (1ULL<<38)   /* overlap with EC */
+/* The process supports new-style OSDMap encoding. Monitors also use
+   this bit to determine if peers support NAK messages. */
+#define CEPH_FEATURE_OSDMAP_ENC    (1ULL<<39)
+#define CEPH_FEATURE_MDS_INLINE_DATA     (1ULL<<40)
+#define CEPH_FEATURE_CRUSH_TUNABLES3     (1ULL<<41)
+#define CEPH_FEATURE_OSD_PRIMARY_AFFINITY (1ULL<<41)  /* overlap w/ tunables3 */
 
 /*
  * The introduction of CEPH_FEATURE_OSD_SNAPMAPPER caused the feature
@@ -82,7 +89,8 @@ static inline u64 ceph_sanitize_features(u64 features)
 	 CEPH_FEATURE_OSDHASHPSPOOL |		\
 	 CEPH_FEATURE_OSD_CACHEPOOL |		\
 	 CEPH_FEATURE_CRUSH_V2 |		\
-	 CEPH_FEATURE_EXPORT_PEER)
+	 CEPH_FEATURE_EXPORT_PEER |		\
+	 CEPH_FEATURE_CRUSH_TUNABLES3)
 
 #define CEPH_FEATURES_REQUIRED_DEFAULT   \
 	(CEPH_FEATURE_NOSRCADDR |	 \
-- 
cgit v1.2.3


From a2505d63ee0541d9b4685250b033192e68222e97 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <ilya.dryomov@inktank.com>
Date: Thu, 13 Mar 2014 16:36:13 +0200
Subject: libceph: split osdmap allocation and decode steps

Split osdmap allocation and initialization into a separate function,
ceph_osdmap_decode().

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
---
 include/linux/ceph/osdmap.h |  2 +-
 net/ceph/osd_client.c       |  2 +-
 net/ceph/osdmap.c           | 44 +++++++++++++++++++++++++++++---------------
 3 files changed, 31 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index 8c8b3cefc28b..46c3e304c3d8 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -156,7 +156,7 @@ static inline int ceph_decode_pgid(void **p, void *end, struct ceph_pg *pgid)
 	return 0;
 }
 
-extern struct ceph_osdmap *osdmap_decode(void **p, void *end);
+extern struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end);
 extern struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 					    struct ceph_osdmap *map,
 					    struct ceph_messenger *msgr);
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 71830d79b0f4..6f64eec18851 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -2062,7 +2062,7 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg)
 			int skipped_map = 0;
 
 			dout("taking full map %u len %d\n", epoch, maplen);
-			newmap = osdmap_decode(&p, p+maplen);
+			newmap = ceph_osdmap_decode(&p, p+maplen);
 			if (IS_ERR(newmap)) {
 				err = PTR_ERR(newmap);
 				goto bad;
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 4dd000d128fd..a82df6ea0749 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -684,9 +684,8 @@ static int osdmap_set_max_osd(struct ceph_osdmap *map, int max)
 /*
  * decode a full map.
  */
-struct ceph_osdmap *osdmap_decode(void **p, void *end)
+static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map)
 {
-	struct ceph_osdmap *map;
 	u16 version;
 	u32 len, max, i;
 	int err = -EINVAL;
@@ -694,14 +693,7 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end)
 	void *start = *p;
 	struct ceph_pg_pool_info *pi;
 
-	dout("osdmap_decode %p to %p len %d\n", *p, end, (int)(end - *p));
-
-	map = kzalloc(sizeof(*map), GFP_NOFS);
-	if (map == NULL)
-		return ERR_PTR(-ENOMEM);
-
-	map->pg_temp = RB_ROOT;
-	mutex_init(&map->crush_scratch_mutex);
+	dout("%s %p to %p len %d\n", __func__, *p, end, (int)(end - *p));
 
 	ceph_decode_16_safe(p, end, version, bad);
 	if (version > 6) {
@@ -751,7 +743,6 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end)
 	err = osdmap_set_max_osd(map, max);
 	if (err < 0)
 		goto bad;
-	dout("osdmap_decode max_osd = %d\n", map->max_osd);
 
 	/* osds */
 	err = -EINVAL;
@@ -819,7 +810,7 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end)
 	*p = end;
 
 	dout("full osdmap epoch %d max_osd %d\n", map->epoch, map->max_osd);
-	return map;
+	return 0;
 
 bad:
 	pr_err("corrupt full osdmap (%d) epoch %d off %d (%p of %p-%p)\n",
@@ -827,8 +818,31 @@ bad:
 	print_hex_dump(KERN_DEBUG, "osdmap: ",
 		       DUMP_PREFIX_OFFSET, 16, 1,
 		       start, end - start, true);
-	ceph_osdmap_destroy(map);
-	return ERR_PTR(err);
+	return err;
+}
+
+/*
+ * Allocate and decode a full map.
+ */
+struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end)
+{
+	struct ceph_osdmap *map;
+	int ret;
+
+	map = kzalloc(sizeof(*map), GFP_NOFS);
+	if (!map)
+		return ERR_PTR(-ENOMEM);
+
+	map->pg_temp = RB_ROOT;
+	mutex_init(&map->crush_scratch_mutex);
+
+	ret = osdmap_decode(p, end, map);
+	if (ret) {
+		ceph_osdmap_destroy(map);
+		return ERR_PTR(ret);
+	}
+
+	return map;
 }
 
 /*
@@ -872,7 +886,7 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 	if (len > 0) {
 		dout("apply_incremental full map len %d, %p to %p\n",
 		     len, *p, end);
-		return osdmap_decode(p, min(*p+len, end));
+		return ceph_osdmap_decode(p, min(*p+len, end));
 	}
 
 	/* new crush? */
-- 
cgit v1.2.3


From 35a935d75d51abe58d3427a8b4ae3745a5a14e1c Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <ilya.dryomov@inktank.com>
Date: Fri, 21 Mar 2014 19:05:29 +0200
Subject: libceph: generalize ceph_pg_mapping

In preparation for adding support for primary_temp mappings, generalize
struct ceph_pg_mapping so it can hold mappings other than pg_temp.

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
---
 include/linux/ceph/osdmap.h | 9 +++++++--
 net/ceph/debugfs.c          | 4 ++--
 net/ceph/osdmap.c           | 8 ++++----
 3 files changed, 13 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index 46c3e304c3d8..4837e58e3203 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -60,8 +60,13 @@ struct ceph_object_id {
 struct ceph_pg_mapping {
 	struct rb_node node;
 	struct ceph_pg pgid;
-	int len;
-	int osds[];
+
+	union {
+		struct {
+			int len;
+			int osds[];
+		} pg_temp;
+	};
 };
 
 struct ceph_osdmap {
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index c45d235e774e..5865f2c9580a 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -88,9 +88,9 @@ static int osdmap_show(struct seq_file *s, void *p)
 
 		seq_printf(s, "pg_temp %llu.%x [", pg->pgid.pool,
 			   pg->pgid.seed);
-		for (i = 0; i < pg->len; i++)
+		for (i = 0; i < pg->pg_temp.len; i++)
 			seq_printf(s, "%s%d", (i == 0 ? "" : ","),
-				   pg->osds[i]);
+				   pg->pg_temp.osds[i]);
 		seq_printf(s, "]\n");
 	}
 
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index be2a65fbd902..c67a309fdfc2 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -822,9 +822,9 @@ static int __decode_pg_temp(void **p, void *end, struct ceph_osdmap *map,
 				return -ENOMEM;
 
 			pg->pgid = pgid;
-			pg->len = len;
+			pg->pg_temp.len = len;
 			for (i = 0; i < len; i++)
-				pg->osds[i] = ceph_decode_32(p);
+				pg->pg_temp.osds[i] = ceph_decode_32(p);
 
 			ret = __insert_pg_mapping(pg, &map->pg_temp);
 			if (ret) {
@@ -1281,8 +1281,8 @@ static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
 				    pool->pg_num_mask);
 	pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid);
 	if (pg) {
-		*num = pg->len;
-		return pg->osds;
+		*num = pg->pg_temp.len;
+		return pg->pg_temp.osds;
 	}
 
 	/* crush */
-- 
cgit v1.2.3


From 9686f94c8cfc06e8afb7b2233ab8f1f6ac01957f Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <ilya.dryomov@inktank.com>
Date: Fri, 21 Mar 2014 19:05:29 +0200
Subject: libceph: primary_temp infrastructure

Add primary_temp mappings infrastructure.  struct ceph_pg_mapping is
overloaded, primary_temp mappings are stored in an rb-tree, rooted at
ceph_osdmap, in a manner similar to pg_temp mappings.

Dump primary_temp mappings to /sys/kernel/debug/ceph/<client>/osdmap,
one 'primary_temp <pgid> <osd>' per line, e.g:

    primary_temp 2.6 4

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
---
 include/linux/ceph/osdmap.h |  5 +++++
 net/ceph/debugfs.c          |  7 +++++++
 net/ceph/osdmap.c           | 10 +++++++++-
 3 files changed, 21 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index 4837e58e3203..db4fb6322aae 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -66,6 +66,9 @@ struct ceph_pg_mapping {
 			int len;
 			int osds[];
 		} pg_temp;
+		struct {
+			int osd;
+		} primary_temp;
 	};
 };
 
@@ -83,6 +86,8 @@ struct ceph_osdmap {
 	struct ceph_entity_addr *osd_addr;
 
 	struct rb_root pg_temp;
+	struct rb_root primary_temp;
+
 	struct rb_root pg_pools;
 	u32 pool_max;
 
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index 5865f2c9580a..612bf55e6a8b 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -93,6 +93,13 @@ static int osdmap_show(struct seq_file *s, void *p)
 				   pg->pg_temp.osds[i]);
 		seq_printf(s, "]\n");
 	}
+	for (n = rb_first(&map->primary_temp); n; n = rb_next(n)) {
+		struct ceph_pg_mapping *pg =
+			rb_entry(n, struct ceph_pg_mapping, node);
+
+		seq_printf(s, "primary_temp %llu.%x %d\n", pg->pgid.pool,
+			   pg->pgid.seed, pg->primary_temp.osd);
+	}
 
 	return 0;
 }
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index c67a309fdfc2..c0fc517ab321 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -343,7 +343,7 @@ bad:
 
 /*
  * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid
- * to a set of osds)
+ * to a set of osds) and primary_temp (explicit primary setting)
  */
 static int pgid_cmp(struct ceph_pg l, struct ceph_pg r)
 {
@@ -633,6 +633,13 @@ void ceph_osdmap_destroy(struct ceph_osdmap *map)
 		rb_erase(&pg->node, &map->pg_temp);
 		kfree(pg);
 	}
+	while (!RB_EMPTY_ROOT(&map->primary_temp)) {
+		struct ceph_pg_mapping *pg =
+			rb_entry(rb_first(&map->primary_temp),
+				 struct ceph_pg_mapping, node);
+		rb_erase(&pg->node, &map->primary_temp);
+		kfree(pg);
+	}
 	while (!RB_EMPTY_ROOT(&map->pg_pools)) {
 		struct ceph_pg_pool_info *pi =
 			rb_entry(rb_first(&map->pg_pools),
@@ -966,6 +973,7 @@ struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end)
 		return ERR_PTR(-ENOMEM);
 
 	map->pg_temp = RB_ROOT;
+	map->primary_temp = RB_ROOT;
 	mutex_init(&map->crush_scratch_mutex);
 
 	ret = osdmap_decode(p, end, map);
-- 
cgit v1.2.3


From 2cfa34f2d67a36e292cbe6e4c1e60d212b7ba4d1 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <ilya.dryomov@inktank.com>
Date: Fri, 21 Mar 2014 19:05:30 +0200
Subject: libceph: primary_affinity infrastructure

Add primary_affinity infrastructure.  primary_affinity values are
stored in an max_osd-sized array, hanging off ceph_osdmap, similar to
a osd_weight array.

Introduce {get,set}_primary_affinity() helpers, primarily to return
CEPH_OSD_DEFAULT_PRIMARY_AFFINITY when no affinity has been set and to
abstract out osd_primary_affinity array allocation and initialization.

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
---
 include/linux/ceph/osdmap.h |  3 +++
 include/linux/ceph/rados.h  |  4 ++++
 net/ceph/debugfs.c          |  5 +++--
 net/ceph/osdmap.c           | 47 +++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 57 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index db4fb6322aae..6e030cb3c9ca 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -88,6 +88,8 @@ struct ceph_osdmap {
 	struct rb_root pg_temp;
 	struct rb_root primary_temp;
 
+	u32 *osd_primary_affinity;
+
 	struct rb_root pg_pools;
 	u32 pool_max;
 
@@ -134,6 +136,7 @@ static inline bool ceph_osdmap_flag(struct ceph_osdmap *map, int flag)
 }
 
 extern char *ceph_osdmap_state_str(char *str, int len, int state);
+extern u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd);
 
 static inline struct ceph_entity_addr *ceph_osd_addr(struct ceph_osdmap *map,
 						     int osd)
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index 2caabef8d369..bb6f40c9cb0f 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -133,6 +133,10 @@ extern const char *ceph_osd_state_name(int s);
 #define CEPH_OSD_IN  0x10000
 #define CEPH_OSD_OUT 0
 
+/* osd primary-affinity.  fixed point value: 0x10000 == baseline */
+#define CEPH_OSD_MAX_PRIMARY_AFFINITY 0x10000
+#define CEPH_OSD_DEFAULT_PRIMARY_AFFINITY 0x10000
+
 
 /*
  * osd map flag bits
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
index 612bf55e6a8b..34453a2b4b4d 100644
--- a/net/ceph/debugfs.c
+++ b/net/ceph/debugfs.c
@@ -77,10 +77,11 @@ static int osdmap_show(struct seq_file *s, void *p)
 		int state = map->osd_state[i];
 		char sb[64];
 
-		seq_printf(s, "osd%d\t%s\t%3d%%\t(%s)\n",
+		seq_printf(s, "osd%d\t%s\t%3d%%\t(%s)\t%3d%%\n",
 			   i, ceph_pr_addr(&addr->in_addr),
 			   ((map->osd_weight[i]*100) >> 16),
-			   ceph_osdmap_state_str(sb, sizeof(sb), state));
+			   ceph_osdmap_state_str(sb, sizeof(sb), state),
+			   ((ceph_get_primary_affinity(map, i)*100) >> 16));
 	}
 	for (n = rb_first(&map->pg_temp); n; n = rb_next(n)) {
 		struct ceph_pg_mapping *pg =
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index c2d793d3d98d..0ac129388e07 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -649,6 +649,7 @@ void ceph_osdmap_destroy(struct ceph_osdmap *map)
 	kfree(map->osd_state);
 	kfree(map->osd_weight);
 	kfree(map->osd_addr);
+	kfree(map->osd_primary_affinity);
 	kfree(map);
 }
 
@@ -685,6 +686,20 @@ static int osdmap_set_max_osd(struct ceph_osdmap *map, int max)
 	map->osd_weight = weight;
 	map->osd_addr = addr;
 
+	if (map->osd_primary_affinity) {
+		u32 *affinity;
+
+		affinity = krealloc(map->osd_primary_affinity,
+				    max*sizeof(*affinity), GFP_NOFS);
+		if (!affinity)
+			return -ENOMEM;
+
+		for (i = map->max_osd; i < max; i++)
+			affinity[i] = CEPH_OSD_DEFAULT_PRIMARY_AFFINITY;
+
+		map->osd_primary_affinity = affinity;
+	}
+
 	map->max_osd = max;
 
 	return 0;
@@ -912,6 +927,38 @@ static int decode_new_primary_temp(void **p, void *end,
 	return __decode_primary_temp(p, end, map, true);
 }
 
+u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd)
+{
+	BUG_ON(osd >= map->max_osd);
+
+	if (!map->osd_primary_affinity)
+		return CEPH_OSD_DEFAULT_PRIMARY_AFFINITY;
+
+	return map->osd_primary_affinity[osd];
+}
+
+static int set_primary_affinity(struct ceph_osdmap *map, int osd, u32 aff)
+{
+	BUG_ON(osd >= map->max_osd);
+
+	if (!map->osd_primary_affinity) {
+		int i;
+
+		map->osd_primary_affinity = kmalloc(map->max_osd*sizeof(u32),
+						    GFP_NOFS);
+		if (!map->osd_primary_affinity)
+			return -ENOMEM;
+
+		for (i = 0; i < map->max_osd; i++)
+			map->osd_primary_affinity[i] =
+			    CEPH_OSD_DEFAULT_PRIMARY_AFFINITY;
+	}
+
+	map->osd_primary_affinity[osd] = aff;
+
+	return 0;
+}
+
 /*
  * decode a full map.
  */
-- 
cgit v1.2.3


From ddf3a21a03d0f01c5ba83deaecd2d0c381d5ef42 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <ilya.dryomov@inktank.com>
Date: Fri, 21 Mar 2014 19:05:31 +0200
Subject: libceph: enable OSDMAP_ENC feature bit

Announce our support for "new" (v7 - split and separately versioned
client and osd sections) osdmap enconding.

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
---
 include/linux/ceph/ceph_features.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index 77c097fe9ea9..7a4cab50b2cd 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -90,6 +90,7 @@ static inline u64 ceph_sanitize_features(u64 features)
 	 CEPH_FEATURE_OSD_CACHEPOOL |		\
 	 CEPH_FEATURE_CRUSH_V2 |		\
 	 CEPH_FEATURE_EXPORT_PEER |		\
+	 CEPH_FEATURE_OSDMAP_ENC |		\
 	 CEPH_FEATURE_CRUSH_TUNABLES3)
 
 #define CEPH_FEATURES_REQUIRED_DEFAULT   \
-- 
cgit v1.2.3


From 246138fa6787db6f4016f26604fdc05dc9f95627 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <ilya.dryomov@inktank.com>
Date: Mon, 24 Mar 2014 17:12:46 +0200
Subject: libceph: ceph_osd_{exists,is_up,is_down}(osd) definitions

Sync up with ceph.git definitions.  Bring in ceph_osd_is_down().

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
---
 include/linux/ceph/osdmap.h | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index 6e030cb3c9ca..0895797b9e28 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -125,9 +125,21 @@ static inline void ceph_oid_copy(struct ceph_object_id *dest,
 	dest->name_len = src->name_len;
 }
 
+static inline int ceph_osd_exists(struct ceph_osdmap *map, int osd)
+{
+	return osd >= 0 && osd < map->max_osd &&
+	       (map->osd_state[osd] & CEPH_OSD_EXISTS);
+}
+
 static inline int ceph_osd_is_up(struct ceph_osdmap *map, int osd)
 {
-	return (osd < map->max_osd) && (map->osd_state[osd] & CEPH_OSD_UP);
+	return ceph_osd_exists(map, osd) &&
+	       (map->osd_state[osd] & CEPH_OSD_UP);
+}
+
+static inline int ceph_osd_is_down(struct ceph_osdmap *map, int osd)
+{
+	return !ceph_osd_is_up(map, osd);
 }
 
 static inline bool ceph_osdmap_flag(struct ceph_osdmap *map, int flag)
-- 
cgit v1.2.3


From 2abebdbca7997422bfab6bf8b6559384a6b95294 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <ilya.dryomov@inktank.com>
Date: Mon, 24 Mar 2014 17:12:47 +0200
Subject: libceph: ceph_can_shift_osds(pool) and pool type defines

Bring in pg_pool_t::can_shift_osds() counterpart along with pool type
defines.

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
---
 include/linux/ceph/osdmap.h | 12 ++++++++++++
 include/linux/ceph/rados.h  |  5 +++--
 2 files changed, 15 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index 0895797b9e28..4e28c1e5d62f 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -41,6 +41,18 @@ struct ceph_pg_pool_info {
 	char *name;
 };
 
+static inline bool ceph_can_shift_osds(struct ceph_pg_pool_info *pool)
+{
+	switch (pool->type) {
+	case CEPH_POOL_TYPE_REP:
+		return true;
+	case CEPH_POOL_TYPE_EC:
+		return false;
+	default:
+		BUG_ON(1);
+	}
+}
+
 struct ceph_object_locator {
 	s64 pool;
 };
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index bb6f40c9cb0f..f20e0d8a2155 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -81,8 +81,9 @@ struct ceph_pg_v1 {
  */
 #define CEPH_NOPOOL  ((__u64) (-1))  /* pool id not defined */
 
-#define CEPH_PG_TYPE_REP     1
-#define CEPH_PG_TYPE_RAID4   2
+#define CEPH_POOL_TYPE_REP     1
+#define CEPH_POOL_TYPE_RAID4   2 /* never implemented */
+#define CEPH_POOL_TYPE_EC      3
 
 /*
  * stable_mod func is used to control number of placement groups.
-- 
cgit v1.2.3


From ac972230e20581b044f5ce66dcaf3c5af8d57444 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <ilya.dryomov@inktank.com>
Date: Mon, 24 Mar 2014 17:12:48 +0200
Subject: libceph: switch ceph_calc_pg_acting() to new helpers

Switch ceph_calc_pg_acting() to new helpers: pg_to_raw_osds(),
raw_to_up_osds() and apply_temps().

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
---
 include/linux/ceph/osdmap.h |  2 +-
 net/ceph/osdmap.c           | 51 +++++++++++++++++++++++++++++++++------------
 2 files changed, 39 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index 4e28c1e5d62f..b0c8f8490663 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -212,7 +212,7 @@ extern int ceph_oloc_oid_to_pg(struct ceph_osdmap *osdmap,
 
 extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap,
 			       struct ceph_pg pgid,
-			       int *acting);
+			       int *osds);
 extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap,
 				struct ceph_pg pgid);
 
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index bd40f56b53ed..f1cad21d1533 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -1649,24 +1649,49 @@ static int apply_temps(struct ceph_osdmap *osdmap,
 }
 
 /*
- * Return acting set for given pgid.
+ * Calculate acting set for given pgid.
+ *
+ * Return acting set length, or error.
  */
 int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
-			int *acting)
+			int *osds)
 {
-	int rawosds[CEPH_PG_MAX_SIZE], *osds;
-	int i, o, num = CEPH_PG_MAX_SIZE;
+	struct ceph_pg_pool_info *pool;
+	u32 pps;
+	int len;
+	int primary;
 
-	osds = calc_pg_raw(osdmap, pgid, rawosds, &num);
-	if (!osds)
-		return -1;
+	pool = __lookup_pg_pool(&osdmap->pg_pools, pgid.pool);
+	if (!pool)
+		return 0;
 
-	/* primary is first up osd */
-	o = 0;
-	for (i = 0; i < num; i++)
-		if (ceph_osd_is_up(osdmap, osds[i]))
-			acting[o++] = osds[i];
-	return o;
+	if (pool->flags & CEPH_POOL_FLAG_HASHPSPOOL) {
+		/* hash pool id and seed so that pool PGs do not overlap */
+		pps = crush_hash32_2(CRUSH_HASH_RJENKINS1,
+				     ceph_stable_mod(pgid.seed, pool->pgp_num,
+						     pool->pgp_num_mask),
+				     pgid.pool);
+	} else {
+		/*
+		 * legacy behavior: add ps and pool together.  this is
+		 * not a great approach because the PGs from each pool
+		 * will overlap on top of each other: 0.5 == 1.4 ==
+		 * 2.3 == ...
+		 */
+		pps = ceph_stable_mod(pgid.seed, pool->pgp_num,
+				      pool->pgp_num_mask) +
+			(unsigned)pgid.pool;
+	}
+
+	len = pg_to_raw_osds(osdmap, pool, pgid, pps, osds);
+	if (len < 0)
+		return len;
+
+	len = raw_to_up_osds(osdmap, pool, osds, len, &primary);
+
+	len = apply_temps(osdmap, pool, pgid, osds, len, &primary);
+
+	return len;
 }
 
 /*
-- 
cgit v1.2.3


From 8008ab1080c1768b02d232dcfd9e161cd47cc9f7 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <ilya.dryomov@inktank.com>
Date: Mon, 24 Mar 2014 17:12:48 +0200
Subject: libceph: return primary from ceph_calc_pg_acting()

In preparation for adding support for primary_temp, stop assuming
primaryness: add a primary out parameter to ceph_calc_pg_acting() and
change call sites accordingly.  Primary is now specified separately
from the order of osds in the set.

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
---
 include/linux/ceph/osdmap.h |  2 +-
 net/ceph/osd_client.c       | 10 ++++------
 net/ceph/osdmap.c           | 20 ++++++++++++--------
 3 files changed, 17 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index b0c8f8490663..561ea896c657 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -212,7 +212,7 @@ extern int ceph_oloc_oid_to_pg(struct ceph_osdmap *osdmap,
 
 extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap,
 			       struct ceph_pg pgid,
-			       int *osds);
+			       int *osds, int *primary);
 extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap,
 				struct ceph_pg pgid);
 
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 6f64eec18851..b4157dc22199 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1333,7 +1333,7 @@ static int __map_request(struct ceph_osd_client *osdc,
 {
 	struct ceph_pg pgid;
 	int acting[CEPH_PG_MAX_SIZE];
-	int o = -1, num = 0;
+	int num, o;
 	int err;
 	bool was_paused;
 
@@ -1346,11 +1346,9 @@ static int __map_request(struct ceph_osd_client *osdc,
 	}
 	req->r_pgid = pgid;
 
-	err = ceph_calc_pg_acting(osdc->osdmap, pgid, acting);
-	if (err > 0) {
-		o = acting[0];
-		num = err;
-	}
+	num = ceph_calc_pg_acting(osdc->osdmap, pgid, acting, &o);
+	if (num < 0)
+		num = 0;
 
 	was_paused = req->r_paused;
 	req->r_paused = __req_should_be_paused(osdc, req);
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index f1cad21d1533..df9389ddd56c 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -1651,19 +1651,21 @@ static int apply_temps(struct ceph_osdmap *osdmap,
 /*
  * Calculate acting set for given pgid.
  *
- * Return acting set length, or error.
+ * Return acting set length, or error.  *primary is set to acting
+ * primary osd id, or -1 if acting set is empty or on error.
  */
 int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
-			int *osds)
+			int *osds, int *primary)
 {
 	struct ceph_pg_pool_info *pool;
 	u32 pps;
 	int len;
-	int primary;
 
 	pool = __lookup_pg_pool(&osdmap->pg_pools, pgid.pool);
-	if (!pool)
-		return 0;
+	if (!pool) {
+		*primary = -1;
+		return -ENOENT;
+	}
 
 	if (pool->flags & CEPH_POOL_FLAG_HASHPSPOOL) {
 		/* hash pool id and seed so that pool PGs do not overlap */
@@ -1684,12 +1686,14 @@ int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
 	}
 
 	len = pg_to_raw_osds(osdmap, pool, pgid, pps, osds);
-	if (len < 0)
+	if (len < 0) {
+		*primary = -1;
 		return len;
+	}
 
-	len = raw_to_up_osds(osdmap, pool, osds, len, &primary);
+	len = raw_to_up_osds(osdmap, pool, osds, len, primary);
 
-	len = apply_temps(osdmap, pool, pgid, osds, len, &primary);
+	len = apply_temps(osdmap, pool, pgid, osds, len, primary);
 
 	return len;
 }
-- 
cgit v1.2.3


From 18cb95af2d7c69aa136ab13f02dd55188c120e75 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <ilya.dryomov@inktank.com>
Date: Mon, 24 Mar 2014 17:12:50 +0200
Subject: libceph: enable PRIMARY_AFFINITY feature bit

Announce our support for osdmaps with non-default primary affinity
values.

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Reviewed-by: Alex Elder <elder@linaro.org>
---
 include/linux/ceph/ceph_features.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index 7a4cab50b2cd..d12659ce550d 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -91,7 +91,8 @@ static inline u64 ceph_sanitize_features(u64 features)
 	 CEPH_FEATURE_CRUSH_V2 |		\
 	 CEPH_FEATURE_EXPORT_PEER |		\
 	 CEPH_FEATURE_OSDMAP_ENC |		\
-	 CEPH_FEATURE_CRUSH_TUNABLES3)
+	 CEPH_FEATURE_CRUSH_TUNABLES3 |		\
+	 CEPH_FEATURE_OSD_PRIMARY_AFFINITY)
 
 #define CEPH_FEATURES_REQUIRED_DEFAULT   \
 	(CEPH_FEATURE_NOSRCADDR |	 \
-- 
cgit v1.2.3


From 7f4b04614a273089ad65654f53771c033fadc65e Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Fri, 28 Mar 2014 19:11:47 +0530
Subject: cpufreq: create another field .flags in cpufreq_frequency_table

Currently cpufreq frequency table has two fields: frequency and driver_data.
driver_data is only for drivers' internal use and cpufreq core shouldn't use
it at all. But with the introduction of BOOST frequencies, this assumption
was broken and we started using it as a flag instead.

There are two problems due to this:
- It is against the description of this field, as driver's data is used by
  the core now.
- if drivers fill it with -3 for any frequency, then those frequencies are
  never considered by cpufreq core as it is exactly same as value of
  CPUFREQ_BOOST_FREQ, i.e. ~2.

The best way to get this fixed is by creating another field flags which
will be used for such flags. This patch does that. Along with that various
drivers need modifications due to the change of struct cpufreq_frequency_table.

Reviewed-by: Gautham R Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/mips/loongson/lemote-2f/clock.c   | 20 ++++++++++----------
 drivers/cpufreq/cris-artpec3-cpufreq.c |  6 +++---
 drivers/cpufreq/cris-etraxfs-cpufreq.c |  6 +++---
 drivers/cpufreq/elanfreq.c             | 18 +++++++++---------
 drivers/cpufreq/exynos4210-cpufreq.c   | 12 ++++++------
 drivers/cpufreq/exynos4x12-cpufreq.c   | 30 +++++++++++++++---------------
 drivers/cpufreq/exynos5250-cpufreq.c   | 34 +++++++++++++++++-----------------
 drivers/cpufreq/freq_table.c           |  4 ++--
 drivers/cpufreq/kirkwood-cpufreq.c     |  6 +++---
 drivers/cpufreq/maple-cpufreq.c        |  6 +++---
 drivers/cpufreq/p4-clockmod.c          | 20 ++++++++++----------
 drivers/cpufreq/pasemi-cpufreq.c       | 12 ++++++------
 drivers/cpufreq/pmac32-cpufreq.c       |  6 +++---
 drivers/cpufreq/pmac64-cpufreq.c       |  6 +++---
 drivers/cpufreq/powernow-k6.c          | 18 +++++++++---------
 drivers/cpufreq/ppc_cbe_cpufreq.c      | 18 +++++++++---------
 drivers/cpufreq/s3c2416-cpufreq.c      | 20 ++++++++++----------
 drivers/cpufreq/s3c64xx-cpufreq.c      | 26 +++++++++++++-------------
 drivers/cpufreq/s5pv210-cpufreq.c      | 12 ++++++------
 drivers/cpufreq/sc520_freq.c           |  6 +++---
 drivers/cpufreq/speedstep-ich.c        |  6 +++---
 drivers/cpufreq/speedstep-smi.c        |  6 +++---
 include/linux/cpufreq.h                |  9 ++++++---
 23 files changed, 155 insertions(+), 152 deletions(-)

(limited to 'include/linux')

diff --git a/arch/mips/loongson/lemote-2f/clock.c b/arch/mips/loongson/lemote-2f/clock.c
index aed32b88576c..e1f427f4f5f3 100644
--- a/arch/mips/loongson/lemote-2f/clock.c
+++ b/arch/mips/loongson/lemote-2f/clock.c
@@ -28,16 +28,16 @@ enum {
 };
 
 struct cpufreq_frequency_table loongson2_clockmod_table[] = {
-	{DC_RESV, CPUFREQ_ENTRY_INVALID},
-	{DC_ZERO, CPUFREQ_ENTRY_INVALID},
-	{DC_25PT, 0},
-	{DC_37PT, 0},
-	{DC_50PT, 0},
-	{DC_62PT, 0},
-	{DC_75PT, 0},
-	{DC_87PT, 0},
-	{DC_DISABLE, 0},
-	{DC_RESV, CPUFREQ_TABLE_END},
+	{0, DC_RESV, CPUFREQ_ENTRY_INVALID},
+	{0, DC_ZERO, CPUFREQ_ENTRY_INVALID},
+	{0, DC_25PT, 0},
+	{0, DC_37PT, 0},
+	{0, DC_50PT, 0},
+	{0, DC_62PT, 0},
+	{0, DC_75PT, 0},
+	{0, DC_87PT, 0},
+	{0, DC_DISABLE, 0},
+	{0, DC_RESV, CPUFREQ_TABLE_END},
 };
 EXPORT_SYMBOL_GPL(loongson2_clockmod_table);
 
diff --git a/drivers/cpufreq/cris-artpec3-cpufreq.c b/drivers/cpufreq/cris-artpec3-cpufreq.c
index d4573032cbbc..601b88c490cf 100644
--- a/drivers/cpufreq/cris-artpec3-cpufreq.c
+++ b/drivers/cpufreq/cris-artpec3-cpufreq.c
@@ -15,9 +15,9 @@ static struct notifier_block cris_sdram_freq_notifier_block = {
 };
 
 static struct cpufreq_frequency_table cris_freq_table[] = {
-	{0x01,	6000},
-	{0x02,	200000},
-	{0,	CPUFREQ_TABLE_END},
+	{0, 0x01, 6000},
+	{0, 0x02, 200000},
+	{0, 0, CPUFREQ_TABLE_END},
 };
 
 static unsigned int cris_freq_get_cpu_frequency(unsigned int cpu)
diff --git a/drivers/cpufreq/cris-etraxfs-cpufreq.c b/drivers/cpufreq/cris-etraxfs-cpufreq.c
index 13c3361437f7..22b2cdde74d9 100644
--- a/drivers/cpufreq/cris-etraxfs-cpufreq.c
+++ b/drivers/cpufreq/cris-etraxfs-cpufreq.c
@@ -15,9 +15,9 @@ static struct notifier_block cris_sdram_freq_notifier_block = {
 };
 
 static struct cpufreq_frequency_table cris_freq_table[] = {
-	{0x01, 6000},
-	{0x02, 200000},
-	{0, CPUFREQ_TABLE_END},
+	{0, 0x01, 6000},
+	{0, 0x02, 200000},
+	{0, 0, CPUFREQ_TABLE_END},
 };
 
 static unsigned int cris_freq_get_cpu_frequency(unsigned int cpu)
diff --git a/drivers/cpufreq/elanfreq.c b/drivers/cpufreq/elanfreq.c
index c987e94708f5..7f5d2a68c353 100644
--- a/drivers/cpufreq/elanfreq.c
+++ b/drivers/cpufreq/elanfreq.c
@@ -56,15 +56,15 @@ static struct s_elan_multiplier elan_multiplier[] = {
 };
 
 static struct cpufreq_frequency_table elanfreq_table[] = {
-	{0,	1000},
-	{1,	2000},
-	{2,	4000},
-	{3,	8000},
-	{4,	16000},
-	{5,	33000},
-	{6,	66000},
-	{7,	99000},
-	{0,	CPUFREQ_TABLE_END},
+	{0, 0,	1000},
+	{0, 1,	2000},
+	{0, 2,	4000},
+	{0, 3,	8000},
+	{0, 4,	16000},
+	{0, 5,	33000},
+	{0, 6,	66000},
+	{0, 7,	99000},
+	{0, 0,	CPUFREQ_TABLE_END},
 };
 
 
diff --git a/drivers/cpufreq/exynos4210-cpufreq.c b/drivers/cpufreq/exynos4210-cpufreq.c
index 40d84c43d8f4..6384e5b9a347 100644
--- a/drivers/cpufreq/exynos4210-cpufreq.c
+++ b/drivers/cpufreq/exynos4210-cpufreq.c
@@ -29,12 +29,12 @@ static unsigned int exynos4210_volt_table[] = {
 };
 
 static struct cpufreq_frequency_table exynos4210_freq_table[] = {
-	{L0, 1200 * 1000},
-	{L1, 1000 * 1000},
-	{L2,  800 * 1000},
-	{L3,  500 * 1000},
-	{L4,  200 * 1000},
-	{0, CPUFREQ_TABLE_END},
+	{0, L0, 1200 * 1000},
+	{0, L1, 1000 * 1000},
+	{0, L2,  800 * 1000},
+	{0, L3,  500 * 1000},
+	{0, L4,  200 * 1000},
+	{0, 0, CPUFREQ_TABLE_END},
 };
 
 static struct apll_freq apll_freq_4210[] = {
diff --git a/drivers/cpufreq/exynos4x12-cpufreq.c b/drivers/cpufreq/exynos4x12-cpufreq.c
index 7c11ace3b3fc..466c76ad335b 100644
--- a/drivers/cpufreq/exynos4x12-cpufreq.c
+++ b/drivers/cpufreq/exynos4x12-cpufreq.c
@@ -30,21 +30,21 @@ static unsigned int exynos4x12_volt_table[] = {
 };
 
 static struct cpufreq_frequency_table exynos4x12_freq_table[] = {
-	{CPUFREQ_BOOST_FREQ, 1500 * 1000},
-	{L1, 1400 * 1000},
-	{L2, 1300 * 1000},
-	{L3, 1200 * 1000},
-	{L4, 1100 * 1000},
-	{L5, 1000 * 1000},
-	{L6,  900 * 1000},
-	{L7,  800 * 1000},
-	{L8,  700 * 1000},
-	{L9,  600 * 1000},
-	{L10, 500 * 1000},
-	{L11, 400 * 1000},
-	{L12, 300 * 1000},
-	{L13, 200 * 1000},
-	{0, CPUFREQ_TABLE_END},
+	{CPUFREQ_BOOST_FREQ, L0, 1500 * 1000},
+	{0, L1, 1400 * 1000},
+	{0, L2, 1300 * 1000},
+	{0, L3, 1200 * 1000},
+	{0, L4, 1100 * 1000},
+	{0, L5, 1000 * 1000},
+	{0, L6,  900 * 1000},
+	{0, L7,  800 * 1000},
+	{0, L8,  700 * 1000},
+	{0, L9,  600 * 1000},
+	{0, L10, 500 * 1000},
+	{0, L11, 400 * 1000},
+	{0, L12, 300 * 1000},
+	{0, L13, 200 * 1000},
+	{0, 0, CPUFREQ_TABLE_END},
 };
 
 static struct apll_freq *apll_freq_4x12;
diff --git a/drivers/cpufreq/exynos5250-cpufreq.c b/drivers/cpufreq/exynos5250-cpufreq.c
index 5f90b82a4082..363a0b3fe1b1 100644
--- a/drivers/cpufreq/exynos5250-cpufreq.c
+++ b/drivers/cpufreq/exynos5250-cpufreq.c
@@ -34,23 +34,23 @@ static unsigned int exynos5250_volt_table[] = {
 };
 
 static struct cpufreq_frequency_table exynos5250_freq_table[] = {
-	{L0, 1700 * 1000},
-	{L1, 1600 * 1000},
-	{L2, 1500 * 1000},
-	{L3, 1400 * 1000},
-	{L4, 1300 * 1000},
-	{L5, 1200 * 1000},
-	{L6, 1100 * 1000},
-	{L7, 1000 * 1000},
-	{L8,  900 * 1000},
-	{L9,  800 * 1000},
-	{L10, 700 * 1000},
-	{L11, 600 * 1000},
-	{L12, 500 * 1000},
-	{L13, 400 * 1000},
-	{L14, 300 * 1000},
-	{L15, 200 * 1000},
-	{0, CPUFREQ_TABLE_END},
+	{0, L0, 1700 * 1000},
+	{0, L1, 1600 * 1000},
+	{0, L2, 1500 * 1000},
+	{0, L3, 1400 * 1000},
+	{0, L4, 1300 * 1000},
+	{0, L5, 1200 * 1000},
+	{0, L6, 1100 * 1000},
+	{0, L7, 1000 * 1000},
+	{0, L8,  900 * 1000},
+	{0, L9,  800 * 1000},
+	{0, L10, 700 * 1000},
+	{0, L11, 600 * 1000},
+	{0, L12, 500 * 1000},
+	{0, L13, 400 * 1000},
+	{0, L14, 300 * 1000},
+	{0, L15, 200 * 1000},
+	{0, 0, CPUFREQ_TABLE_END},
 };
 
 static struct apll_freq apll_freq_5250[] = {
diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index 53ff3c209606..08e7bbcf6d73 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -33,7 +33,7 @@ int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
 			continue;
 		}
 		if (!cpufreq_boost_enabled()
-		    && table[i].driver_data == CPUFREQ_BOOST_FREQ)
+		    && (table[i].flags & CPUFREQ_BOOST_FREQ))
 			continue;
 
 		pr_debug("table entry %u: %u kHz\n", i, freq);
@@ -229,7 +229,7 @@ static ssize_t show_available_freqs(struct cpufreq_policy *policy, char *buf,
 		 * show_boost = false and driver_data != BOOST freq
 		 * display NON BOOST freqs
 		 */
-		if (show_boost ^ (table[i].driver_data == CPUFREQ_BOOST_FREQ))
+		if (show_boost ^ (table[i].flags & CPUFREQ_BOOST_FREQ))
 			continue;
 
 		count += sprintf(&buf[count], "%d ", table[i].frequency);
diff --git a/drivers/cpufreq/kirkwood-cpufreq.c b/drivers/cpufreq/kirkwood-cpufreq.c
index 3d114bc5a97a..37a480680cd0 100644
--- a/drivers/cpufreq/kirkwood-cpufreq.c
+++ b/drivers/cpufreq/kirkwood-cpufreq.c
@@ -43,9 +43,9 @@ static struct priv
  * table.
  */
 static struct cpufreq_frequency_table kirkwood_freq_table[] = {
-	{STATE_CPU_FREQ,	0}, /* CPU uses cpuclk */
-	{STATE_DDR_FREQ,	0}, /* CPU uses ddrclk */
-	{0,			CPUFREQ_TABLE_END},
+	{0, STATE_CPU_FREQ,	0}, /* CPU uses cpuclk */
+	{0, STATE_DDR_FREQ,	0}, /* CPU uses ddrclk */
+	{0, 0,			CPUFREQ_TABLE_END},
 };
 
 static unsigned int kirkwood_cpufreq_get_cpu_frequency(unsigned int cpu)
diff --git a/drivers/cpufreq/maple-cpufreq.c b/drivers/cpufreq/maple-cpufreq.c
index c4dfa42a75ac..cc3408fc073f 100644
--- a/drivers/cpufreq/maple-cpufreq.c
+++ b/drivers/cpufreq/maple-cpufreq.c
@@ -59,9 +59,9 @@
 #define CPUFREQ_LOW                   1
 
 static struct cpufreq_frequency_table maple_cpu_freqs[] = {
-	{CPUFREQ_HIGH,		0},
-	{CPUFREQ_LOW,		0},
-	{0,			CPUFREQ_TABLE_END},
+	{0, CPUFREQ_HIGH,		0},
+	{0, CPUFREQ_LOW,		0},
+	{0, 0,				CPUFREQ_TABLE_END},
 };
 
 /* Power mode data is an array of the 32 bits PCR values to use for
diff --git a/drivers/cpufreq/p4-clockmod.c b/drivers/cpufreq/p4-clockmod.c
index 74f593e70e19..529cfd92158f 100644
--- a/drivers/cpufreq/p4-clockmod.c
+++ b/drivers/cpufreq/p4-clockmod.c
@@ -92,16 +92,16 @@ static int cpufreq_p4_setdc(unsigned int cpu, unsigned int newstate)
 
 
 static struct cpufreq_frequency_table p4clockmod_table[] = {
-	{DC_RESV, CPUFREQ_ENTRY_INVALID},
-	{DC_DFLT, 0},
-	{DC_25PT, 0},
-	{DC_38PT, 0},
-	{DC_50PT, 0},
-	{DC_64PT, 0},
-	{DC_75PT, 0},
-	{DC_88PT, 0},
-	{DC_DISABLE, 0},
-	{DC_RESV, CPUFREQ_TABLE_END},
+	{0, DC_RESV, CPUFREQ_ENTRY_INVALID},
+	{0, DC_DFLT, 0},
+	{0, DC_25PT, 0},
+	{0, DC_38PT, 0},
+	{0, DC_50PT, 0},
+	{0, DC_64PT, 0},
+	{0, DC_75PT, 0},
+	{0, DC_88PT, 0},
+	{0, DC_DISABLE, 0},
+	{0, DC_RESV, CPUFREQ_TABLE_END},
 };
 
 
diff --git a/drivers/cpufreq/pasemi-cpufreq.c b/drivers/cpufreq/pasemi-cpufreq.c
index 6a2b7d3e85a7..84c84b5f0f3a 100644
--- a/drivers/cpufreq/pasemi-cpufreq.c
+++ b/drivers/cpufreq/pasemi-cpufreq.c
@@ -60,12 +60,12 @@ static int current_astate;
 
 /* We support 5(A0-A4) power states excluding turbo(A5-A6) modes */
 static struct cpufreq_frequency_table pas_freqs[] = {
-	{0,	0},
-	{1,	0},
-	{2,	0},
-	{3,	0},
-	{4,	0},
-	{0,	CPUFREQ_TABLE_END},
+	{0, 0,	0},
+	{0, 1,	0},
+	{0, 2,	0},
+	{0, 3,	0},
+	{0, 4,	0},
+	{0, 0,	CPUFREQ_TABLE_END},
 };
 
 /*
diff --git a/drivers/cpufreq/pmac32-cpufreq.c b/drivers/cpufreq/pmac32-cpufreq.c
index cf55d202f332..7615180d7ee3 100644
--- a/drivers/cpufreq/pmac32-cpufreq.c
+++ b/drivers/cpufreq/pmac32-cpufreq.c
@@ -81,9 +81,9 @@ static int is_pmu_based;
 #define CPUFREQ_LOW                   1
 
 static struct cpufreq_frequency_table pmac_cpu_freqs[] = {
-	{CPUFREQ_HIGH, 		0},
-	{CPUFREQ_LOW,		0},
-	{0,			CPUFREQ_TABLE_END},
+	{0, CPUFREQ_HIGH,	0},
+	{0, CPUFREQ_LOW,	0},
+	{0, 0,			CPUFREQ_TABLE_END},
 };
 
 static inline void local_delay(unsigned long ms)
diff --git a/drivers/cpufreq/pmac64-cpufreq.c b/drivers/cpufreq/pmac64-cpufreq.c
index 6a338f8c3860..8bc422977b5b 100644
--- a/drivers/cpufreq/pmac64-cpufreq.c
+++ b/drivers/cpufreq/pmac64-cpufreq.c
@@ -65,9 +65,9 @@
 #define CPUFREQ_LOW                   1
 
 static struct cpufreq_frequency_table g5_cpu_freqs[] = {
-	{CPUFREQ_HIGH, 		0},
-	{CPUFREQ_LOW,		0},
-	{0,			CPUFREQ_TABLE_END},
+	{0, CPUFREQ_HIGH,	0},
+	{0, CPUFREQ_LOW,	0},
+	{0, 0,			CPUFREQ_TABLE_END},
 };
 
 /* Power mode data is an array of the 32 bits PCR values to use for
diff --git a/drivers/cpufreq/powernow-k6.c b/drivers/cpufreq/powernow-k6.c
index 62c6f2e5afce..49f120e1bc7b 100644
--- a/drivers/cpufreq/powernow-k6.c
+++ b/drivers/cpufreq/powernow-k6.c
@@ -37,15 +37,15 @@ MODULE_PARM_DESC(bus_frequency, "Bus frequency in kHz");
 
 /* Clock ratio multiplied by 10 - see table 27 in AMD#23446 */
 static struct cpufreq_frequency_table clock_ratio[] = {
-	{60,  /* 110 -> 6.0x */ 0},
-	{55,  /* 011 -> 5.5x */ 0},
-	{50,  /* 001 -> 5.0x */ 0},
-	{45,  /* 000 -> 4.5x */ 0},
-	{40,  /* 010 -> 4.0x */ 0},
-	{35,  /* 111 -> 3.5x */ 0},
-	{30,  /* 101 -> 3.0x */ 0},
-	{20,  /* 100 -> 2.0x */ 0},
-	{0, CPUFREQ_TABLE_END}
+	{0, 60,  /* 110 -> 6.0x */ 0},
+	{0, 55,  /* 011 -> 5.5x */ 0},
+	{0, 50,  /* 001 -> 5.0x */ 0},
+	{0, 45,  /* 000 -> 4.5x */ 0},
+	{0, 40,  /* 010 -> 4.0x */ 0},
+	{0, 35,  /* 111 -> 3.5x */ 0},
+	{0, 30,  /* 101 -> 3.0x */ 0},
+	{0, 20,  /* 100 -> 2.0x */ 0},
+	{0, 0, CPUFREQ_TABLE_END}
 };
 
 static const u8 index_to_register[8] = { 6, 3, 1, 0, 2, 7, 5, 4 };
diff --git a/drivers/cpufreq/ppc_cbe_cpufreq.c b/drivers/cpufreq/ppc_cbe_cpufreq.c
index af7b1cabd1e7..5be8a48dba74 100644
--- a/drivers/cpufreq/ppc_cbe_cpufreq.c
+++ b/drivers/cpufreq/ppc_cbe_cpufreq.c
@@ -32,15 +32,15 @@
 
 /* the CBE supports an 8 step frequency scaling */
 static struct cpufreq_frequency_table cbe_freqs[] = {
-	{1,	0},
-	{2,	0},
-	{3,	0},
-	{4,	0},
-	{5,	0},
-	{6,	0},
-	{8,	0},
-	{10,	0},
-	{0,	CPUFREQ_TABLE_END},
+	{0, 1,	0},
+	{0, 2,	0},
+	{0, 3,	0},
+	{0, 4,	0},
+	{0, 5,	0},
+	{0, 6,	0},
+	{0, 8,	0},
+	{0, 10,	0},
+	{0, 0,	CPUFREQ_TABLE_END},
 };
 
 /*
diff --git a/drivers/cpufreq/s3c2416-cpufreq.c b/drivers/cpufreq/s3c2416-cpufreq.c
index 826b8be23099..4626f90559b5 100644
--- a/drivers/cpufreq/s3c2416-cpufreq.c
+++ b/drivers/cpufreq/s3c2416-cpufreq.c
@@ -72,19 +72,19 @@ static struct s3c2416_dvfs s3c2416_dvfs_table[] = {
 #endif
 
 static struct cpufreq_frequency_table s3c2416_freq_table[] = {
-	{ SOURCE_HCLK, FREQ_DVS },
-	{ SOURCE_ARMDIV, 133333 },
-	{ SOURCE_ARMDIV, 266666 },
-	{ SOURCE_ARMDIV, 400000 },
-	{ 0, CPUFREQ_TABLE_END },
+	{ 0, SOURCE_HCLK, FREQ_DVS },
+	{ 0, SOURCE_ARMDIV, 133333 },
+	{ 0, SOURCE_ARMDIV, 266666 },
+	{ 0, SOURCE_ARMDIV, 400000 },
+	{ 0, 0, CPUFREQ_TABLE_END },
 };
 
 static struct cpufreq_frequency_table s3c2450_freq_table[] = {
-	{ SOURCE_HCLK, FREQ_DVS },
-	{ SOURCE_ARMDIV, 133500 },
-	{ SOURCE_ARMDIV, 267000 },
-	{ SOURCE_ARMDIV, 534000 },
-	{ 0, CPUFREQ_TABLE_END },
+	{ 0, SOURCE_HCLK, FREQ_DVS },
+	{ 0, SOURCE_ARMDIV, 133500 },
+	{ 0, SOURCE_ARMDIV, 267000 },
+	{ 0, SOURCE_ARMDIV, 534000 },
+	{ 0, 0, CPUFREQ_TABLE_END },
 };
 
 static unsigned int s3c2416_cpufreq_get_speed(unsigned int cpu)
diff --git a/drivers/cpufreq/s3c64xx-cpufreq.c b/drivers/cpufreq/s3c64xx-cpufreq.c
index c4226de079ab..ff7d3ecb85f0 100644
--- a/drivers/cpufreq/s3c64xx-cpufreq.c
+++ b/drivers/cpufreq/s3c64xx-cpufreq.c
@@ -37,19 +37,19 @@ static struct s3c64xx_dvfs s3c64xx_dvfs_table[] = {
 };
 
 static struct cpufreq_frequency_table s3c64xx_freq_table[] = {
-	{ 0,  66000 },
-	{ 0, 100000 },
-	{ 0, 133000 },
-	{ 1, 200000 },
-	{ 1, 222000 },
-	{ 1, 266000 },
-	{ 2, 333000 },
-	{ 2, 400000 },
-	{ 2, 532000 },
-	{ 2, 533000 },
-	{ 3, 667000 },
-	{ 4, 800000 },
-	{ 0, CPUFREQ_TABLE_END },
+	{ 0, 0,  66000 },
+	{ 0, 0, 100000 },
+	{ 0, 0, 133000 },
+	{ 0, 1, 200000 },
+	{ 0, 1, 222000 },
+	{ 0, 1, 266000 },
+	{ 0, 2, 333000 },
+	{ 0, 2, 400000 },
+	{ 0, 2, 532000 },
+	{ 0, 2, 533000 },
+	{ 0, 3, 667000 },
+	{ 0, 4, 800000 },
+	{ 0, 0, CPUFREQ_TABLE_END },
 };
 #endif
 
diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c
index 72421534fff5..ab2c1a40d437 100644
--- a/drivers/cpufreq/s5pv210-cpufreq.c
+++ b/drivers/cpufreq/s5pv210-cpufreq.c
@@ -64,12 +64,12 @@ enum s5pv210_dmc_port {
 };
 
 static struct cpufreq_frequency_table s5pv210_freq_table[] = {
-	{L0, 1000*1000},
-	{L1, 800*1000},
-	{L2, 400*1000},
-	{L3, 200*1000},
-	{L4, 100*1000},
-	{0, CPUFREQ_TABLE_END},
+	{0, L0, 1000*1000},
+	{0, L1, 800*1000},
+	{0, L2, 400*1000},
+	{0, L3, 200*1000},
+	{0, L4, 100*1000},
+	{0, 0, CPUFREQ_TABLE_END},
 };
 
 static struct regulator *arm_regulator;
diff --git a/drivers/cpufreq/sc520_freq.c b/drivers/cpufreq/sc520_freq.c
index 69371bf0886d..ac84e4818014 100644
--- a/drivers/cpufreq/sc520_freq.c
+++ b/drivers/cpufreq/sc520_freq.c
@@ -33,9 +33,9 @@ static __u8 __iomem *cpuctl;
 #define PFX "sc520_freq: "
 
 static struct cpufreq_frequency_table sc520_freq_table[] = {
-	{0x01,	100000},
-	{0x02,	133000},
-	{0,	CPUFREQ_TABLE_END},
+	{0, 0x01,	100000},
+	{0, 0x02,	133000},
+	{0, 0,	CPUFREQ_TABLE_END},
 };
 
 static unsigned int sc520_freq_get_cpu_frequency(unsigned int cpu)
diff --git a/drivers/cpufreq/speedstep-ich.c b/drivers/cpufreq/speedstep-ich.c
index 394ac159312a..1a07b5904ed5 100644
--- a/drivers/cpufreq/speedstep-ich.c
+++ b/drivers/cpufreq/speedstep-ich.c
@@ -49,9 +49,9 @@ static u32 pmbase;
  * are in kHz for the time being.
  */
 static struct cpufreq_frequency_table speedstep_freqs[] = {
-	{SPEEDSTEP_HIGH,	0},
-	{SPEEDSTEP_LOW,		0},
-	{0,			CPUFREQ_TABLE_END},
+	{0, SPEEDSTEP_HIGH,	0},
+	{0, SPEEDSTEP_LOW,	0},
+	{0, 0,			CPUFREQ_TABLE_END},
 };
 
 
diff --git a/drivers/cpufreq/speedstep-smi.c b/drivers/cpufreq/speedstep-smi.c
index db5d274dc13a..8635eec96da5 100644
--- a/drivers/cpufreq/speedstep-smi.c
+++ b/drivers/cpufreq/speedstep-smi.c
@@ -42,9 +42,9 @@ static enum speedstep_processor speedstep_processor;
  * are in kHz for the time being.
  */
 static struct cpufreq_frequency_table speedstep_freqs[] = {
-	{SPEEDSTEP_HIGH,	0},
-	{SPEEDSTEP_LOW,		0},
-	{0,			CPUFREQ_TABLE_END},
+	{0, SPEEDSTEP_HIGH,	0},
+	{0, SPEEDSTEP_LOW,	0},
+	{0, 0,			CPUFREQ_TABLE_END},
 };
 
 #define GET_SPEEDSTEP_OWNER 0
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index c48e595f623e..5ae5100c1f24 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -455,11 +455,14 @@ extern struct cpufreq_governor cpufreq_gov_conservative;
  *                     FREQUENCY TABLE HELPERS                       *
  *********************************************************************/
 
-#define CPUFREQ_ENTRY_INVALID ~0
-#define CPUFREQ_TABLE_END     ~1
-#define CPUFREQ_BOOST_FREQ    ~2
+/* Special Values of .frequency field */
+#define CPUFREQ_ENTRY_INVALID	~0
+#define CPUFREQ_TABLE_END	~1
+/* Special Values of .flags field */
+#define CPUFREQ_BOOST_FREQ	(1 << 0)
 
 struct cpufreq_frequency_table {
+	unsigned int	flags;
 	unsigned int	driver_data; /* driver specific data, not used by core */
 	unsigned int	frequency; /* kHz - doesn't need to be in ascending
 				    * order */
-- 
cgit v1.2.3


From 403c63cb6d7ec2caca2f9222ff843ac89d7d700a Mon Sep 17 00:00:00 2001
From: Jon Mason <jon.mason@intel.com>
Date: Mon, 29 Jul 2013 16:31:18 -0700
Subject: NTB: client event cleanup

Provide a better event interface between the client and transport

Signed-off-by: Jon Mason <jon.mason@intel.com>
---
 drivers/net/ntb_netdev.c    | 16 ++++++++++++----
 drivers/ntb/ntb_hw.h        |  4 +---
 drivers/ntb/ntb_transport.c |  1 -
 include/linux/ntb.h         |  5 +++++
 4 files changed, 18 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c
index 8e6752fd89ac..14570b28d528 100644
--- a/drivers/net/ntb_netdev.c
+++ b/drivers/net/ntb_netdev.c
@@ -78,11 +78,19 @@ static void ntb_netdev_event_handler(void *data, int status)
 	netdev_dbg(ndev, "Event %x, Link %x\n", status,
 		   ntb_transport_link_query(dev->qp));
 
-	/* Currently, only link status event is supported */
-	if (status)
-		netif_carrier_on(ndev);
-	else
+	switch (status) {
+	case NTB_LINK_DOWN:
 		netif_carrier_off(ndev);
+		break;
+	case NTB_LINK_UP:
+		if (!ntb_transport_link_query(dev->qp))
+			return;
+
+		netif_carrier_on(ndev);
+		break;
+	default:
+		netdev_warn(ndev, "Unsupported event type %d\n", status);
+	}
 }
 
 static void ntb_netdev_rx_handler(struct ntb_transport_qp *qp, void *qp_data,
diff --git a/drivers/ntb/ntb_hw.h b/drivers/ntb/ntb_hw.h
index bbdb7edca10c..d1960ffb4bbc 100644
--- a/drivers/ntb/ntb_hw.h
+++ b/drivers/ntb/ntb_hw.h
@@ -45,6 +45,7 @@
  * Contact Information:
  * Jon Mason <jon.mason@intel.com>
  */
+#include <linux/ntb.h>
 
 #define PCI_DEVICE_ID_INTEL_NTB_B2B_JSF		0x3725
 #define PCI_DEVICE_ID_INTEL_NTB_PS_JSF		0x3726
@@ -83,9 +84,6 @@ static inline void writeq(u64 val, void __iomem *addr)
 #define NTB_BAR_MASK		((1 << NTB_BAR_MMIO) | (1 << NTB_BAR_23) |\
 				 (1 << NTB_BAR_45))
 
-#define NTB_LINK_DOWN		0
-#define NTB_LINK_UP		1
-
 #define NTB_HB_TIMEOUT		msecs_to_jiffies(1000)
 
 #define NTB_MAX_NUM_MW		2
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index 3217f394d45b..042fb3dd354f 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -56,7 +56,6 @@
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/types.h>
-#include <linux/ntb.h>
 #include "ntb_hw.h"
 
 #define NTB_TRANSPORT_VERSION	3
diff --git a/include/linux/ntb.h b/include/linux/ntb.h
index f6a15205853b..cbc792cd745e 100644
--- a/include/linux/ntb.h
+++ b/include/linux/ntb.h
@@ -54,6 +54,11 @@ struct ntb_client {
 	void (*remove) (struct pci_dev *pdev);
 };
 
+enum {
+	NTB_LINK_DOWN = 0,
+	NTB_LINK_UP,
+};
+
 int ntb_register_client(struct ntb_client *drvr);
 void ntb_unregister_client(struct ntb_client *drvr);
 int ntb_register_client_dev(char *device_name);
-- 
cgit v1.2.3


From 53ca4fea0bbe966b3123509125898b286a136f47 Mon Sep 17 00:00:00 2001
From: Jon Mason <jon.mason@intel.com>
Date: Tue, 26 Nov 2013 11:21:50 -0700
Subject: NTB: Code Style Clean-up

Some white space and 80 char overruns corrected.

Signed-off-by: Jon Mason <jon.mason@intel.com>
---
 drivers/net/ntb_netdev.c    |  2 +-
 drivers/ntb/ntb_hw.c        | 19 ++++++++++---------
 drivers/ntb/ntb_hw.h        |  2 +-
 drivers/ntb/ntb_transport.c | 19 +++++++++----------
 include/linux/ntb.h         | 14 +++++++-------
 5 files changed, 28 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c
index 14570b28d528..63aa9d9e34c5 100644
--- a/drivers/net/ntb_netdev.c
+++ b/drivers/net/ntb_netdev.c
@@ -377,7 +377,7 @@ static void ntb_netdev_remove(struct pci_dev *pdev)
 {
 	struct net_device *ndev;
 	struct ntb_netdev *dev;
-	bool found  = false;
+	bool found = false;
 
 	list_for_each_entry(dev, &dev_list, list) {
 		if (dev->pdev == pdev) {
diff --git a/drivers/ntb/ntb_hw.c b/drivers/ntb/ntb_hw.c
index 0e8ae70fd918..eba1ed58471d 100644
--- a/drivers/ntb/ntb_hw.c
+++ b/drivers/ntb/ntb_hw.c
@@ -91,7 +91,7 @@ static struct dentry *debugfs_dir;
 /* Translate memory window 0,1 to BAR 2,4 */
 #define MW_TO_BAR(mw)	(mw * NTB_MAX_NUM_MW + 2)
 
-static DEFINE_PCI_DEVICE_TABLE(ntb_pci_tbl) = {
+static const struct pci_device_id ntb_pci_tbl[] = {
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_B2B_BWD)},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_B2B_JSF)},
 	{PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_NTB_B2B_SNB)},
@@ -120,7 +120,8 @@ MODULE_DEVICE_TABLE(pci, ntb_pci_tbl);
  * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
  */
 int ntb_register_event_callback(struct ntb_device *ndev,
-			    void (*func)(void *handle, enum ntb_hw_event event))
+				void (*func)(void *handle,
+					     enum ntb_hw_event event))
 {
 	if (ndev->event_cb)
 		return -EINVAL;
@@ -715,9 +716,9 @@ static int ntb_xeon_setup(struct ntb_device *ndev)
 			       SNB_PBAR4LMT_OFFSET);
 			/* HW errata on the Limit registers.  They can only be
 			 * written when the base register is 4GB aligned and
-			 * < 32bit.  This should already be the case based on the
-			 * driver defaults, but write the Limit registers first
-			 * just in case.
+			 * < 32bit.  This should already be the case based on
+			 * the driver defaults, but write the Limit registers
+			 * first just in case.
 			 */
 		} else {
 			ndev->limits.max_mw = SNB_MAX_MW;
@@ -739,9 +740,9 @@ static int ntb_xeon_setup(struct ntb_device *ndev)
 			writeq(0, ndev->reg_base + SNB_PBAR4LMT_OFFSET);
 			/* HW errata on the Limit registers.  They can only be
 			 * written when the base register is 4GB aligned and
-			 * < 32bit.  This should already be the case based on the
-			 * driver defaults, but write the Limit registers first
-			 * just in case.
+			 * < 32bit.  This should already be the case based on
+			 * the driver defaults, but write the Limit registers
+			 * first just in case.
 			 */
 		}
 
@@ -803,7 +804,7 @@ static int ntb_xeon_setup(struct ntb_device *ndev)
 		ndev->conn_type = NTB_CONN_RP;
 
 		if (xeon_errata_workaround) {
-			dev_err(&ndev->pdev->dev, 
+			dev_err(&ndev->pdev->dev,
 				"NTB-RP disabled due to hardware errata.  To disregard this warning and potentially lock-up the system, add the parameter 'xeon_errata_workaround=0'.\n");
 			return -EINVAL;
 		}
diff --git a/drivers/ntb/ntb_hw.h b/drivers/ntb/ntb_hw.h
index d1960ffb4bbc..923a0fbb0eb8 100644
--- a/drivers/ntb/ntb_hw.h
+++ b/drivers/ntb/ntb_hw.h
@@ -231,7 +231,7 @@ int ntb_register_db_callback(struct ntb_device *ndev, unsigned int idx,
 							   int db_num));
 void ntb_unregister_db_callback(struct ntb_device *ndev, unsigned int idx);
 int ntb_register_event_callback(struct ntb_device *ndev,
-				void (*event_cb_func) (void *handle,
+				void (*event_cb_func)(void *handle,
 						      enum ntb_hw_event event));
 void ntb_unregister_event_callback(struct ntb_device *ndev);
 int ntb_get_max_spads(struct ntb_device *ndev);
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index 042fb3dd354f..9dd63b822025 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -106,8 +106,8 @@ struct ntb_transport_qp {
 	struct ntb_rx_info __iomem *rx_info;
 	struct ntb_rx_info *remote_rx_info;
 
-	void (*tx_handler) (struct ntb_transport_qp *qp, void *qp_data,
-			    void *data, int len);
+	void (*tx_handler)(struct ntb_transport_qp *qp, void *qp_data,
+			   void *data, int len);
 	struct list_head tx_free_q;
 	spinlock_t ntb_tx_free_q_lock;
 	void __iomem *tx_mw;
@@ -116,8 +116,8 @@ struct ntb_transport_qp {
 	unsigned int tx_max_entry;
 	unsigned int tx_max_frame;
 
-	void (*rx_handler) (struct ntb_transport_qp *qp, void *qp_data,
-			    void *data, int len);
+	void (*rx_handler)(struct ntb_transport_qp *qp, void *qp_data,
+			   void *data, int len);
 	struct list_head rx_pend_q;
 	struct list_head rx_free_q;
 	spinlock_t ntb_rx_pend_q_lock;
@@ -128,7 +128,7 @@ struct ntb_transport_qp {
 	unsigned int rx_max_frame;
 	dma_cookie_t last_cookie;
 
-	void (*event_handler) (void *data, int status);
+	void (*event_handler)(void *data, int status);
 	struct delayed_work link_work;
 	struct work_struct link_cleanup;
 
@@ -479,7 +479,7 @@ static void ntb_list_add(spinlock_t *lock, struct list_head *entry,
 }
 
 static struct ntb_queue_entry *ntb_list_rm(spinlock_t *lock,
-						struct list_head *list)
+					   struct list_head *list)
 {
 	struct ntb_queue_entry *entry;
 	unsigned long flags;
@@ -838,7 +838,7 @@ static void ntb_qp_link_work(struct work_struct *work)
 }
 
 static int ntb_transport_init_queue(struct ntb_transport *nt,
-				     unsigned int qp_num)
+				    unsigned int qp_num)
 {
 	struct ntb_transport_qp *qp;
 	unsigned int num_qps_mw, tx_size;
@@ -1054,7 +1054,7 @@ static void ntb_async_rx(struct ntb_queue_entry *entry, void *offset,
 	if (!chan)
 		goto err;
 
-	if (len < copy_bytes) 
+	if (len < copy_bytes)
 		goto err_wait;
 
 	device = chan->device;
@@ -1189,8 +1189,7 @@ out:
 	return 0;
 
 err:
-	ntb_list_add(&qp->ntb_rx_pend_q_lock, &entry->entry,
-		     &qp->rx_pend_q);
+	ntb_list_add(&qp->ntb_rx_pend_q_lock, &entry->entry, &qp->rx_pend_q);
 	/* Ensure that the data is fully copied out before clearing the flag */
 	wmb();
 	hdr->flags = 0;
diff --git a/include/linux/ntb.h b/include/linux/ntb.h
index cbc792cd745e..9ac1a62fc6f5 100644
--- a/include/linux/ntb.h
+++ b/include/linux/ntb.h
@@ -50,8 +50,8 @@ struct ntb_transport_qp;
 
 struct ntb_client {
 	struct device_driver driver;
-	int (*probe) (struct pci_dev *pdev);
-	void (*remove) (struct pci_dev *pdev);
+	int (*probe)(struct pci_dev *pdev);
+	void (*remove)(struct pci_dev *pdev);
 };
 
 enum {
@@ -65,11 +65,11 @@ int ntb_register_client_dev(char *device_name);
 void ntb_unregister_client_dev(char *device_name);
 
 struct ntb_queue_handlers {
-	void (*rx_handler) (struct ntb_transport_qp *qp, void *qp_data,
-			    void *data, int len);
-	void (*tx_handler) (struct ntb_transport_qp *qp, void *qp_data,
-			    void *data, int len);
-	void (*event_handler) (void *data, int status);
+	void (*rx_handler)(struct ntb_transport_qp *qp, void *qp_data,
+			   void *data, int len);
+	void (*tx_handler)(struct ntb_transport_qp *qp, void *qp_data,
+			   void *data, int len);
+	void (*event_handler)(void *data, int status);
 };
 
 unsigned char ntb_transport_qp_num(struct ntb_transport_qp *qp);
-- 
cgit v1.2.3


From b8780c363d808a726a34793caa900923d32b6b80 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 7 Apr 2014 17:33:06 +0200
Subject: sched: remove sleep_on() and friends

This is the final piece in the puzzle, as all patches to remove the
last users of \(interruptible_\|\)sleep_on\(_timeout\|\) have made it
into the 3.15 merge window. The work was long overdue, and this
interface in particular should not have survived the BKL removal
that was done a couple of years ago.

Citing Jon Corbet from http://lwn.net/2001/0201/kernel.php3":

 "[...] it was suggested that the janitors look for and fix all code
  that calls sleep_on() [...] since (1) almost all such code is
  incorrect, and (2) Linus has agreed that those functions should
  be removed in the 2.5 development series".

We haven't quite made it for 2.5, but maybe we can merge this for 3.15.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/DocBook/kernel-hacking.tmpl | 10 -------
 include/linux/wait.h                      | 11 --------
 kernel/sched/core.c                       | 46 -------------------------------
 3 files changed, 67 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/DocBook/kernel-hacking.tmpl b/Documentation/DocBook/kernel-hacking.tmpl
index d0758b241b23..bd9015d10cff 100644
--- a/Documentation/DocBook/kernel-hacking.tmpl
+++ b/Documentation/DocBook/kernel-hacking.tmpl
@@ -850,16 +850,6 @@ printk(KERN_INFO "my ip: %pI4\n", &amp;ipaddress);
     <returnvalue>-ERESTARTSYS</returnvalue> if a signal is received.
     The <function>wait_event()</function> version ignores signals.
    </para>
-   <para>
-   Do not use the <function>sleep_on()</function> function family -
-   it is very easy to accidentally introduce races; almost certainly
-   one of the <function>wait_event()</function> family will do, or a
-   loop around <function>schedule_timeout()</function>. If you choose
-   to loop around <function>schedule_timeout()</function> remember
-   you must set the task state (with 
-   <function>set_current_state()</function>) on each iteration to avoid
-   busy-looping.
-   </para>
  
   </sect1>
 
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 559044c79232..e7d9d9ed14f5 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -803,17 +803,6 @@ do {									\
 	__ret;								\
 })
 
-
-/*
- * These are the old interfaces to sleep waiting for an event.
- * They are racy.  DO NOT use them, use the wait_event* interfaces above.
- * We plan to remove these interfaces.
- */
-extern void sleep_on(wait_queue_head_t *q);
-extern long sleep_on_timeout(wait_queue_head_t *q, signed long timeout);
-extern void interruptible_sleep_on(wait_queue_head_t *q);
-extern long interruptible_sleep_on_timeout(wait_queue_head_t *q, signed long timeout);
-
 /*
  * Waitqueues which are removed from the waitqueue_head at wakeup time
  */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1d1b87b36778..0ff3f34bc7e3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2845,52 +2845,6 @@ int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags,
 }
 EXPORT_SYMBOL(default_wake_function);
 
-static long __sched
-sleep_on_common(wait_queue_head_t *q, int state, long timeout)
-{
-	unsigned long flags;
-	wait_queue_t wait;
-
-	init_waitqueue_entry(&wait, current);
-
-	__set_current_state(state);
-
-	spin_lock_irqsave(&q->lock, flags);
-	__add_wait_queue(q, &wait);
-	spin_unlock(&q->lock);
-	timeout = schedule_timeout(timeout);
-	spin_lock_irq(&q->lock);
-	__remove_wait_queue(q, &wait);
-	spin_unlock_irqrestore(&q->lock, flags);
-
-	return timeout;
-}
-
-void __sched interruptible_sleep_on(wait_queue_head_t *q)
-{
-	sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
-}
-EXPORT_SYMBOL(interruptible_sleep_on);
-
-long __sched
-interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
-{
-	return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout);
-}
-EXPORT_SYMBOL(interruptible_sleep_on_timeout);
-
-void __sched sleep_on(wait_queue_head_t *q)
-{
-	sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
-}
-EXPORT_SYMBOL(sleep_on);
-
-long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout)
-{
-	return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout);
-}
-EXPORT_SYMBOL(sleep_on_timeout);
-
 #ifdef CONFIG_RT_MUTEXES
 
 /*
-- 
cgit v1.2.3


From a0715cc22601e8830ace98366c0c2bd8da52af52 Mon Sep 17 00:00:00 2001
From: Alex Thorlton <athorlton@sgi.com>
Date: Mon, 7 Apr 2014 15:37:10 -0700
Subject: mm, thp: add VM_INIT_DEF_MASK and PRCTL_THP_DISABLE

Add VM_INIT_DEF_MASK, to allow us to set the default flags for VMs.  It
also adds a prctl control which allows us to set the THP disable bit in
mm->def_flags so that VMs will pick up the setting as they are created.

Signed-off-by: Alex Thorlton <athorlton@sgi.com>
Suggested-by: Oleg Nesterov <oleg@redhat.com>
Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h         |  3 +++
 include/uapi/linux/prctl.h |  3 +++
 kernel/fork.c              | 11 ++++++++---
 kernel/sys.c               | 15 +++++++++++++++
 4 files changed, 29 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 35300f390eb6..c270fa68a32b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -177,6 +177,9 @@ extern unsigned int kobjsize(const void *objp);
  */
 #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP)
 
+/* This mask defines which mm->def_flags a process can inherit its parent */
+#define VM_INIT_DEF_MASK	VM_NOHUGEPAGE
+
 /*
  * mapping from the currently active vm_flags protection bits (the
  * low four bits) to a page protection mask..
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index 289760f424aa..58afc04c107e 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -149,4 +149,7 @@
 
 #define PR_GET_TID_ADDRESS	40
 
+#define PR_SET_THP_DISABLE	41
+#define PR_GET_THP_DISABLE	42
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/kernel/fork.c b/kernel/fork.c
index abc45890f0a5..e40c0a01d5a6 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -530,8 +530,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	atomic_set(&mm->mm_count, 1);
 	init_rwsem(&mm->mmap_sem);
 	INIT_LIST_HEAD(&mm->mmlist);
-	mm->flags = (current->mm) ?
-		(current->mm->flags & MMF_INIT_MASK) : default_dump_filter;
 	mm->core_state = NULL;
 	atomic_long_set(&mm->nr_ptes, 0);
 	memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
@@ -540,8 +538,15 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	mm_init_owner(mm, p);
 	clear_tlb_flush_pending(mm);
 
-	if (likely(!mm_alloc_pgd(mm))) {
+	if (current->mm) {
+		mm->flags = current->mm->flags & MMF_INIT_MASK;
+		mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK;
+	} else {
+		mm->flags = default_dump_filter;
 		mm->def_flags = 0;
+	}
+
+	if (likely(!mm_alloc_pgd(mm))) {
 		mmu_notifier_mm_init(mm);
 		return mm;
 	}
diff --git a/kernel/sys.c b/kernel/sys.c
index adaeab6f7a87..fba0f29401ea 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1996,6 +1996,21 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 		if (arg2 || arg3 || arg4 || arg5)
 			return -EINVAL;
 		return current->no_new_privs ? 1 : 0;
+	case PR_GET_THP_DISABLE:
+		if (arg2 || arg3 || arg4 || arg5)
+			return -EINVAL;
+		error = !!(me->mm->def_flags & VM_NOHUGEPAGE);
+		break;
+	case PR_SET_THP_DISABLE:
+		if (arg3 || arg4 || arg5)
+			return -EINVAL;
+		down_write(&me->mm->mmap_sem);
+		if (arg2)
+			me->mm->def_flags |= VM_NOHUGEPAGE;
+		else
+			me->mm->def_flags &= ~VM_NOHUGEPAGE;
+		up_write(&me->mm->mmap_sem);
+		break;
 	default:
 		error = -EINVAL;
 		break;
-- 
cgit v1.2.3


From 8c6e50b0290c4c708a3e6462729e1e9151a9a7df Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Mon, 7 Apr 2014 15:37:18 -0700
Subject: mm: introduce vm_ops->map_pages()

Here's new version of faultaround patchset.  It took a while to tune it
and collect performance data.

First patch adds new callback ->map_pages to vm_operations_struct.

->map_pages() is called when VM asks to map easy accessible pages.
Filesystem should find and map pages associated with offsets from
"pgoff" till "max_pgoff".  ->map_pages() is called with page table
locked and must not block.  If it's not possible to reach a page without
blocking, filesystem should skip it.  Filesystem should use do_set_pte()
to setup page table entry.  Pointer to entry associated with offset
"pgoff" is passed in "pte" field in vm_fault structure.  Pointers to
entries for other offsets should be calculated relative to "pte".

Currently VM use ->map_pages only on read page fault path.  We try to
map FAULT_AROUND_PAGES a time.  FAULT_AROUND_PAGES is 16 for now.
Performance data for different FAULT_AROUND_ORDER is below.

TODO:
 - implement ->map_pages() for shmem/tmpfs;
 - modify get_user_pages() to be able to use ->map_pages() and implement
   mmap(MAP_POPULATE|MAP_NONBLOCK) on top.

=========================================================================
Tested on 4-socket machine (120 threads) with 128GiB of RAM.

Few real-world workloads. The sweet spot for FAULT_AROUND_ORDER here is
somewhere between 3 and 5. Let's say 4 :)

Linux build (make -j60)
FAULT_AROUND_ORDER		Baseline	1		3		4		5		7		9
	minor-faults		283,301,572	247,151,987	212,215,789	204,772,882	199,568,944	194,703,779	193,381,485
	time, seconds		151.227629483	153.920996480	151.356125472	150.863792049	150.879207877	151.150764954	151.450962358
Linux rebuild (make -j60)
FAULT_AROUND_ORDER		Baseline	1		3		4		5		7		9
	minor-faults		5,396,854	4,148,444	2,855,286	2,577,282	2,361,957	2,169,573	2,112,643
	time, seconds		27.404543757	27.559725591	27.030057426	26.855045126	26.678618635	26.974523490	26.761320095
Git test suite (make -j60 test)
FAULT_AROUND_ORDER		Baseline	1		3		4		5		7		9
	minor-faults		129,591,823	99,200,751	66,106,718	57,606,410	51,510,808	45,776,813	44,085,515
	time, seconds		66.087215026	64.784546905	64.401156567	65.282708668	66.034016829	66.793780811	67.237810413

Two synthetic tests: access every word in file in sequential/random order.
It doesn't improve much after FAULT_AROUND_ORDER == 4.

Sequential access 16GiB file
FAULT_AROUND_ORDER		Baseline	1		3		4		5		7		9
 1 thread
	minor-faults		4,195,437	2,098,275	525,068		262,251		131,170		32,856		8,282
	time, seconds		7.250461742	6.461711074	5.493859139	5.488488147	5.707213983	5.898510832	5.109232856
 8 threads
	minor-faults		33,557,540	16,892,728	4,515,848	2,366,999	1,423,382	442,732		142,339
	time, seconds		16.649304881	9.312555263	6.612490639	6.394316732	6.669827501	6.75078944	6.371900528
 32 threads
	minor-faults		134,228,222	67,526,810	17,725,386	9,716,537	4,763,731	1,668,921	537,200
	time, seconds		49.164430543	29.712060103	12.938649729	10.175151004	11.840094583	9.594081325	9.928461797
 60 threads
	minor-faults		251,687,988	126,146,952	32,919,406	18,208,804	10,458,947	2,733,907	928,217
	time, seconds		86.260656897	49.626551828	22.335007632	17.608243696	16.523119035	16.339489186	16.326390902
 120 threads
	minor-faults		503,352,863	252,939,677	67,039,168	35,191,827	19,170,091	4,688,357	1,471,862
	time, seconds		124.589206333	79.757867787	39.508707872	32.167281632	29.972989292	28.729834575	28.042251622
Random access 1GiB file
 1 thread
	minor-faults		262,636		132,743		34,369		17,299		8,527		3,451		1,222
	time, seconds		15.351890914	16.613802482	16.569227308	15.179220992	16.557356122	16.578247824	15.365266994
 8 threads
	minor-faults		2,098,948	1,061,871	273,690		154,501		87,110		25,663		7,384
	time, seconds		15.040026343	15.096933500	14.474757288	14.289129964	14.411537468	14.296316837	14.395635804
 32 threads
	minor-faults		8,390,734	4,231,023	1,054,432	528,847		269,242		97,746		26,881
	time, seconds		20.430433109	21.585235358	22.115062928	14.872878951	14.880856305	14.883370649	14.821261690
 60 threads
	minor-faults		15,733,258	7,892,809	1,973,393	988,266		594,789		164,994		51,691
	time, seconds		26.577302548	25.692397770	18.728863715	20.153026398	21.619101933	17.745086260	17.613215273
 120 threads
	minor-faults		31,471,111	15,816,616	3,959,209	1,978,685	1,008,299	264,635		96,010
	time, seconds		41.835322703	40.459786095	36.085306105	35.313894834	35.814445675	36.552633793	34.289210594

Touch only one page in page table in 16GiB file
FAULT_AROUND_ORDER		Baseline	1		3		4		5		7		9
 1 thread
	minor-faults		8,372		8,324		8,270		8,260		8,249		8,239		8,237
	time, seconds		0.039892712	0.045369149	0.051846126	0.063681685	0.079095975	0.17652406	0.541213386
 8 threads
	minor-faults		65,731		65,681		65,628		65,620		65,608		65,599		65,596
	time, seconds		0.124159196	0.488600638	0.156854426	0.191901957	0.242631486	0.543569456	1.677303984
 32 threads
	minor-faults		262,388		262,341		262,285		262,276		262,266		262,257		263,183
	time, seconds		0.452421421	0.488600638	0.565020946	0.648229739	0.789850823	1.651584361	5.000361559
 60 threads
	minor-faults		491,822		491,792		491,723		491,711		491,701		491,691		491,825
	time, seconds		0.763288616	0.869620515	0.980727360	1.161732354	1.466915814	3.04041448	9.308612938
 120 threads
	minor-faults		983,466		983,655		983,366		983,372		983,363		984,083		984,164
	time, seconds		1.595846553	1.667902182	2.008959376	2.425380942	2.941368804	5.977807890	18.401846125

This patch (of 2):

Introduce new vm_ops callback ->map_pages() and uses it for mapping easy
accessible pages around fault address.

On read page fault, if filesystem provides ->map_pages(), we try to map up
to FAULT_AROUND_PAGES pages around page fault address in hope to reduce
number of minor page faults.

We call ->map_pages first and use ->fault() as fallback if page by the
offset is not ready to be mapped (cold page cache or something).

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Ning Qu <quning@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/filesystems/Locking | 10 +++++
 include/linux/mm.h                |  8 ++++
 mm/memory.c                       | 81 +++++++++++++++++++++++++++++++++++++--
 3 files changed, 96 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index f424e0e5b46b..efca5c1bbb10 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -529,6 +529,7 @@ locking rules:
 open:		yes
 close:		yes
 fault:		yes		can return with page locked
+map_pages:	yes
 page_mkwrite:	yes		can return with page locked
 access:		yes
 
@@ -540,6 +541,15 @@ the page, then ensure it is not already truncated (the page lock will block
 subsequent truncate), and then return with VM_FAULT_LOCKED, and the page
 locked. The VM will unlock the page.
 
+	->map_pages() is called when VM asks to map easy accessible pages.
+Filesystem should find and map pages associated with offsets from "pgoff"
+till "max_pgoff". ->map_pages() is called with page table locked and must
+not block.  If it's not possible to reach a page without blocking,
+filesystem should skip it. Filesystem should use do_set_pte() to setup
+page table entry. Pointer to entry associated with offset "pgoff" is
+passed in "pte" field in vm_fault structure. Pointers to entries for other
+offsets should be calculated relative to "pte".
+
 	->page_mkwrite() is called when a previously read-only pte is
 about to become writeable. The filesystem again must ensure that there are
 no truncate/invalidate races, and then return with the page locked. If
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c270fa68a32b..f710d32291e8 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -213,6 +213,10 @@ struct vm_fault {
 					 * is set (which is also implied by
 					 * VM_FAULT_ERROR).
 					 */
+	/* for ->map_pages() only */
+	pgoff_t max_pgoff;		/* map pages for offset from pgoff till
+					 * max_pgoff inclusive */
+	pte_t *pte;			/* pte entry associated with ->pgoff */
 };
 
 /*
@@ -224,6 +228,7 @@ struct vm_operations_struct {
 	void (*open)(struct vm_area_struct * area);
 	void (*close)(struct vm_area_struct * area);
 	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
+	void (*map_pages)(struct vm_area_struct *vma, struct vm_fault *vmf);
 
 	/* notification that a previously read-only page is about to become
 	 * writable, if an error is returned it will cause a SIGBUS */
@@ -584,6 +589,9 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 		pte = pte_mkwrite(pte);
 	return pte;
 }
+
+void do_set_pte(struct vm_area_struct *vma, unsigned long address,
+		struct page *page, pte_t *pte, bool write, bool anon);
 #endif
 
 /*
diff --git a/mm/memory.c b/mm/memory.c
index c6ee34d10fcc..4eefb7e31521 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3342,7 +3342,22 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address,
 	return ret;
 }
 
-static void do_set_pte(struct vm_area_struct *vma, unsigned long address,
+/**
+ * do_set_pte - setup new PTE entry for given page and add reverse page mapping.
+ *
+ * @vma: virtual memory area
+ * @address: user virtual address
+ * @page: page to map
+ * @pte: pointer to target page table entry
+ * @write: true, if new entry is writable
+ * @anon: true, if it's anonymous page
+ *
+ * Caller must hold page table lock relevant for @pte.
+ *
+ * Target users are page handler itself and implementations of
+ * vm_ops->map_pages.
+ */
+void do_set_pte(struct vm_area_struct *vma, unsigned long address,
 		struct page *page, pte_t *pte, bool write, bool anon)
 {
 	pte_t entry;
@@ -3366,6 +3381,52 @@ static void do_set_pte(struct vm_area_struct *vma, unsigned long address,
 	update_mmu_cache(vma, address, pte);
 }
 
+#define FAULT_AROUND_ORDER 4
+#define FAULT_AROUND_PAGES (1UL << FAULT_AROUND_ORDER)
+#define FAULT_AROUND_MASK ~((1UL << (PAGE_SHIFT + FAULT_AROUND_ORDER)) - 1)
+
+static void do_fault_around(struct vm_area_struct *vma, unsigned long address,
+		pte_t *pte, pgoff_t pgoff, unsigned int flags)
+{
+	unsigned long start_addr;
+	pgoff_t max_pgoff;
+	struct vm_fault vmf;
+	int off;
+
+	BUILD_BUG_ON(FAULT_AROUND_PAGES > PTRS_PER_PTE);
+
+	start_addr = max(address & FAULT_AROUND_MASK, vma->vm_start);
+	off = ((address - start_addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
+	pte -= off;
+	pgoff -= off;
+
+	/*
+	 *  max_pgoff is either end of page table or end of vma
+	 *  or FAULT_AROUND_PAGES from pgoff, depending what is neast.
+	 */
+	max_pgoff = pgoff - ((start_addr >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) +
+		PTRS_PER_PTE - 1;
+	max_pgoff = min3(max_pgoff, vma_pages(vma) + vma->vm_pgoff - 1,
+			pgoff + FAULT_AROUND_PAGES - 1);
+
+	/* Check if it makes any sense to call ->map_pages */
+	while (!pte_none(*pte)) {
+		if (++pgoff > max_pgoff)
+			return;
+		start_addr += PAGE_SIZE;
+		if (start_addr >= vma->vm_end)
+			return;
+		pte++;
+	}
+
+	vmf.virtual_address = (void __user *) start_addr;
+	vmf.pte = pte;
+	vmf.pgoff = pgoff;
+	vmf.max_pgoff = max_pgoff;
+	vmf.flags = flags;
+	vma->vm_ops->map_pages(vma, &vmf);
+}
+
 static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned long address, pmd_t *pmd,
 		pgoff_t pgoff, unsigned int flags, pte_t orig_pte)
@@ -3373,7 +3434,20 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *fault_page;
 	spinlock_t *ptl;
 	pte_t *pte;
-	int ret;
+	int ret = 0;
+
+	/*
+	 * Let's call ->map_pages() first and use ->fault() as fallback
+	 * if page by the offset is not ready to be mapped (cold cache or
+	 * something).
+	 */
+	if (vma->vm_ops->map_pages) {
+		pte = pte_offset_map_lock(mm, pmd, address, &ptl);
+		do_fault_around(vma, address, pte, pgoff, flags);
+		if (!pte_same(*pte, orig_pte))
+			goto unlock_out;
+		pte_unmap_unlock(pte, ptl);
+	}
 
 	ret = __do_fault(vma, address, pgoff, flags, &fault_page);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
@@ -3387,8 +3461,9 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		return ret;
 	}
 	do_set_pte(vma, address, fault_page, pte, false, false);
-	pte_unmap_unlock(pte, ptl);
 	unlock_page(fault_page);
+unlock_out:
+	pte_unmap_unlock(pte, ptl);
 	return ret;
 }
 
-- 
cgit v1.2.3


From f1820361f83d556a7f0a9f629100f3825e594328 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Mon, 7 Apr 2014 15:37:19 -0700
Subject: mm: implement ->map_pages for page cache

filemap_map_pages() is generic implementation of ->map_pages() for
filesystems who uses page cache.

It should be safe to use filemap_map_pages() for ->map_pages() if
filesystem use filemap_fault() for ->fault().

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Ning Qu <quning@gmail.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/9p/vfs_file.c   |  2 ++
 fs/btrfs/file.c    |  1 +
 fs/cifs/file.c     |  1 +
 fs/ext4/file.c     |  1 +
 fs/f2fs/file.c     |  1 +
 fs/fuse/file.c     |  1 +
 fs/gfs2/file.c     |  1 +
 fs/nfs/file.c      |  1 +
 fs/nilfs2/file.c   |  1 +
 fs/ubifs/file.c    |  1 +
 fs/xfs/xfs_file.c  |  1 +
 include/linux/mm.h |  1 +
 mm/filemap.c       | 74 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 mm/nommu.c         |  6 +++++
 14 files changed, 93 insertions(+)

(limited to 'include/linux')

diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index a16b0ff497ca..d8223209d4b1 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -832,6 +832,7 @@ static void v9fs_mmap_vm_close(struct vm_area_struct *vma)
 
 static const struct vm_operations_struct v9fs_file_vm_ops = {
 	.fault = filemap_fault,
+	.map_pages = filemap_map_pages,
 	.page_mkwrite = v9fs_vm_page_mkwrite,
 	.remap_pages = generic_file_remap_pages,
 };
@@ -839,6 +840,7 @@ static const struct vm_operations_struct v9fs_file_vm_ops = {
 static const struct vm_operations_struct v9fs_mmap_file_vm_ops = {
 	.close = v9fs_mmap_vm_close,
 	.fault = filemap_fault,
+	.map_pages = filemap_map_pages,
 	.page_mkwrite = v9fs_vm_page_mkwrite,
 	.remap_pages = generic_file_remap_pages,
 };
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index e1ffb1e22898..c660527af838 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2025,6 +2025,7 @@ out:
 
 static const struct vm_operations_struct btrfs_file_vm_ops = {
 	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= btrfs_page_mkwrite,
 	.remap_pages	= generic_file_remap_pages,
 };
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 834fce759d80..216d7e99f921 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3113,6 +3113,7 @@ cifs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 static struct vm_operations_struct cifs_file_vm_ops = {
 	.fault = filemap_fault,
+	.map_pages = filemap_map_pages,
 	.page_mkwrite = cifs_page_mkwrite,
 	.remap_pages = generic_file_remap_pages,
 };
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 6db7f7db7777..4e508fc83dcf 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -200,6 +200,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
 
 static const struct vm_operations_struct ext4_file_vm_ops = {
 	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
 	.page_mkwrite   = ext4_page_mkwrite,
 	.remap_pages	= generic_file_remap_pages,
 };
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 0dfcef53a6ed..129a3bdb05ca 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -84,6 +84,7 @@ out:
 
 static const struct vm_operations_struct f2fs_file_vm_ops = {
 	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= f2fs_vm_page_mkwrite,
 	.remap_pages	= generic_file_remap_pages,
 };
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 65df7d8be4f5..48992cac714b 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2117,6 +2117,7 @@ static int fuse_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 static const struct vm_operations_struct fuse_file_vm_ops = {
 	.close		= fuse_vma_close,
 	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= fuse_page_mkwrite,
 	.remap_pages	= generic_file_remap_pages,
 };
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 6c794085abac..80d67253623c 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -494,6 +494,7 @@ out:
 
 static const struct vm_operations_struct gfs2_vm_ops = {
 	.fault = filemap_fault,
+	.map_pages = filemap_map_pages,
 	.page_mkwrite = gfs2_page_mkwrite,
 	.remap_pages = generic_file_remap_pages,
 };
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 5bb790a69c71..284ca901fe16 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -617,6 +617,7 @@ out:
 
 static const struct vm_operations_struct nfs_file_vm_ops = {
 	.fault = filemap_fault,
+	.map_pages = filemap_map_pages,
 	.page_mkwrite = nfs_vm_page_mkwrite,
 	.remap_pages = generic_file_remap_pages,
 };
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index 08fdb77852ac..f3a82fbcae02 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -134,6 +134,7 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 static const struct vm_operations_struct nilfs_file_vm_ops = {
 	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= nilfs_page_mkwrite,
 	.remap_pages	= generic_file_remap_pages,
 };
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index 123c79b7261e..4f34dbae823d 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -1538,6 +1538,7 @@ out_unlock:
 
 static const struct vm_operations_struct ubifs_file_vm_ops = {
 	.fault        = filemap_fault,
+	.map_pages = filemap_map_pages,
 	.page_mkwrite = ubifs_vm_page_mkwrite,
 	.remap_pages = generic_file_remap_pages,
 };
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index f7abff8c16ca..003c0051b62f 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1483,6 +1483,7 @@ const struct file_operations xfs_dir_file_operations = {
 
 static const struct vm_operations_struct xfs_file_vm_ops = {
 	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= xfs_vm_page_mkwrite,
 	.remap_pages	= generic_file_remap_pages,
 };
diff --git a/include/linux/mm.h b/include/linux/mm.h
index f710d32291e8..9132faed1a41 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1847,6 +1847,7 @@ extern void truncate_inode_pages_final(struct address_space *);
 
 /* generic vm_area_ops exported for stackable file systems */
 extern int filemap_fault(struct vm_area_struct *, struct vm_fault *);
+extern void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf);
 extern int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
 
 /* mm/page-writeback.c */
diff --git a/mm/filemap.c b/mm/filemap.c
index 21781f1fe52b..3f9b5fbb623f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -33,6 +33,7 @@
 #include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */
 #include <linux/memcontrol.h>
 #include <linux/cleancache.h>
+#include <linux/rmap.h>
 #include "internal.h"
 
 #define CREATE_TRACE_POINTS
@@ -2064,6 +2065,78 @@ page_not_uptodate:
 }
 EXPORT_SYMBOL(filemap_fault);
 
+void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct radix_tree_iter iter;
+	void **slot;
+	struct file *file = vma->vm_file;
+	struct address_space *mapping = file->f_mapping;
+	loff_t size;
+	struct page *page;
+	unsigned long address = (unsigned long) vmf->virtual_address;
+	unsigned long addr;
+	pte_t *pte;
+
+	rcu_read_lock();
+	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, vmf->pgoff) {
+		if (iter.index > vmf->max_pgoff)
+			break;
+repeat:
+		page = radix_tree_deref_slot(slot);
+		if (unlikely(!page))
+			goto next;
+		if (radix_tree_exception(page)) {
+			if (radix_tree_deref_retry(page))
+				break;
+			else
+				goto next;
+		}
+
+		if (!page_cache_get_speculative(page))
+			goto repeat;
+
+		/* Has the page moved? */
+		if (unlikely(page != *slot)) {
+			page_cache_release(page);
+			goto repeat;
+		}
+
+		if (!PageUptodate(page) ||
+				PageReadahead(page) ||
+				PageHWPoison(page))
+			goto skip;
+		if (!trylock_page(page))
+			goto skip;
+
+		if (page->mapping != mapping || !PageUptodate(page))
+			goto unlock;
+
+		size = i_size_read(mapping->host) + PAGE_CACHE_SIZE - 1;
+		if (page->index >= size	>> PAGE_CACHE_SHIFT)
+			goto unlock;
+
+		pte = vmf->pte + page->index - vmf->pgoff;
+		if (!pte_none(*pte))
+			goto unlock;
+
+		if (file->f_ra.mmap_miss > 0)
+			file->f_ra.mmap_miss--;
+		addr = address + (page->index - vmf->pgoff) * PAGE_SIZE;
+		do_set_pte(vma, addr, page, pte, false, false);
+		unlock_page(page);
+		goto next;
+unlock:
+		unlock_page(page);
+skip:
+		page_cache_release(page);
+next:
+		if (iter.index == vmf->max_pgoff)
+			break;
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(filemap_map_pages);
+
 int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct page *page = vmf->page;
@@ -2093,6 +2166,7 @@ EXPORT_SYMBOL(filemap_page_mkwrite);
 
 const struct vm_operations_struct generic_file_vm_ops = {
 	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= filemap_page_mkwrite,
 	.remap_pages	= generic_file_remap_pages,
 };
diff --git a/mm/nommu.c b/mm/nommu.c
index a554e5a451cd..e19482533ce3 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1985,6 +1985,12 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 }
 EXPORT_SYMBOL(filemap_fault);
 
+void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	BUG();
+}
+EXPORT_SYMBOL(filemap_map_pages);
+
 int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr,
 			     unsigned long size, pgoff_t pgoff)
 {
-- 
cgit v1.2.3


From 615d6e8756c87149f2d4c1b93d471bca002bd849 Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <davidlohr@hp.com>
Date: Mon, 7 Apr 2014 15:37:25 -0700
Subject: mm: per-thread vma caching

This patch is a continuation of efforts trying to optimize find_vma(),
avoiding potentially expensive rbtree walks to locate a vma upon faults.
The original approach (https://lkml.org/lkml/2013/11/1/410), where the
largest vma was also cached, ended up being too specific and random,
thus further comparison with other approaches were needed.  There are
two things to consider when dealing with this, the cache hit rate and
the latency of find_vma().  Improving the hit-rate does not necessarily
translate in finding the vma any faster, as the overhead of any fancy
caching schemes can be too high to consider.

We currently cache the last used vma for the whole address space, which
provides a nice optimization, reducing the total cycles in find_vma() by
up to 250%, for workloads with good locality.  On the other hand, this
simple scheme is pretty much useless for workloads with poor locality.
Analyzing ebizzy runs shows that, no matter how many threads are
running, the mmap_cache hit rate is less than 2%, and in many situations
below 1%.

The proposed approach is to replace this scheme with a small per-thread
cache, maximizing hit rates at a very low maintenance cost.
Invalidations are performed by simply bumping up a 32-bit sequence
number.  The only expensive operation is in the rare case of a seq
number overflow, where all caches that share the same address space are
flushed.  Upon a miss, the proposed replacement policy is based on the
page number that contains the virtual address in question.  Concretely,
the following results are seen on an 80 core, 8 socket x86-64 box:

1) System bootup: Most programs are single threaded, so the per-thread
   scheme does improve ~50% hit rate by just adding a few more slots to
   the cache.

+----------------+----------+------------------+
| caching scheme | hit-rate | cycles (billion) |
+----------------+----------+------------------+
| baseline       | 50.61%   | 19.90            |
| patched        | 73.45%   | 13.58            |
+----------------+----------+------------------+

2) Kernel build: This one is already pretty good with the current
   approach as we're dealing with good locality.

+----------------+----------+------------------+
| caching scheme | hit-rate | cycles (billion) |
+----------------+----------+------------------+
| baseline       | 75.28%   | 11.03            |
| patched        | 88.09%   | 9.31             |
+----------------+----------+------------------+

3) Oracle 11g Data Mining (4k pages): Similar to the kernel build workload.

+----------------+----------+------------------+
| caching scheme | hit-rate | cycles (billion) |
+----------------+----------+------------------+
| baseline       | 70.66%   | 17.14            |
| patched        | 91.15%   | 12.57            |
+----------------+----------+------------------+

4) Ebizzy: There's a fair amount of variation from run to run, but this
   approach always shows nearly perfect hit rates, while baseline is just
   about non-existent.  The amounts of cycles can fluctuate between
   anywhere from ~60 to ~116 for the baseline scheme, but this approach
   reduces it considerably.  For instance, with 80 threads:

+----------------+----------+------------------+
| caching scheme | hit-rate | cycles (billion) |
+----------------+----------+------------------+
| baseline       | 1.06%    | 91.54            |
| patched        | 99.97%   | 14.18            |
+----------------+----------+------------------+

[akpm@linux-foundation.org: fix nommu build, per Davidlohr]
[akpm@linux-foundation.org: document vmacache_valid() logic]
[akpm@linux-foundation.org: attempt to untangle header files]
[akpm@linux-foundation.org: add vmacache_find() BUG_ON]
[hughd@google.com: add vmacache_valid_mm() (from Oleg)]
[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: adjust and enhance comments]
Signed-off-by: Davidlohr Bueso <davidlohr@hp.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Michel Lespinasse <walken@google.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Tested-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/unicore32/include/asm/mmu_context.h |   4 +-
 fs/exec.c                                |   5 +-
 fs/proc/task_mmu.c                       |   3 +-
 include/linux/mm_types.h                 |   4 +-
 include/linux/sched.h                    |   7 ++
 include/linux/vmacache.h                 |  38 +++++++++++
 kernel/debug/debug_core.c                |  14 +++-
 kernel/fork.c                            |   7 +-
 mm/Makefile                              |   2 +-
 mm/mmap.c                                |  55 ++++++++-------
 mm/nommu.c                               |  24 ++++---
 mm/vmacache.c                            | 112 +++++++++++++++++++++++++++++++
 12 files changed, 231 insertions(+), 44 deletions(-)
 create mode 100644 include/linux/vmacache.h
 create mode 100644 mm/vmacache.c

(limited to 'include/linux')

diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h
index fb5e4c658f7a..ef470a7a3d0f 100644
--- a/arch/unicore32/include/asm/mmu_context.h
+++ b/arch/unicore32/include/asm/mmu_context.h
@@ -14,6 +14,8 @@
 
 #include <linux/compiler.h>
 #include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/io.h>
 
 #include <asm/cacheflush.h>
@@ -73,7 +75,7 @@ do { \
 		else \
 			mm->mmap = NULL; \
 		rb_erase(&high_vma->vm_rb, &mm->mm_rb); \
-		mm->mmap_cache = NULL; \
+		vmacache_invalidate(mm); \
 		mm->map_count--; \
 		remove_vma(high_vma); \
 	} \
diff --git a/fs/exec.c b/fs/exec.c
index 25dfeba6d55f..b60ccf969a8b 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -26,6 +26,7 @@
 #include <linux/file.h>
 #include <linux/fdtable.h>
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/stat.h>
 #include <linux/fcntl.h>
 #include <linux/swap.h>
@@ -822,7 +823,7 @@ EXPORT_SYMBOL(read_code);
 static int exec_mmap(struct mm_struct *mm)
 {
 	struct task_struct *tsk;
-	struct mm_struct * old_mm, *active_mm;
+	struct mm_struct *old_mm, *active_mm;
 
 	/* Notify parent that we're no longer interested in the old VM */
 	tsk = current;
@@ -848,6 +849,8 @@ static int exec_mmap(struct mm_struct *mm)
 	tsk->mm = mm;
 	tsk->active_mm = mm;
 	activate_mm(active_mm, mm);
+	tsk->mm->vmacache_seqnum = 0;
+	vmacache_flush(tsk);
 	task_unlock(tsk);
 	if (old_mm) {
 		up_read(&old_mm->mmap_sem);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index fb52b548080d..442177b1119a 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1,4 +1,5 @@
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/hugetlb.h>
 #include <linux/huge_mm.h>
 #include <linux/mount.h>
@@ -152,7 +153,7 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 
 	/*
 	 * We remember last_addr rather than next_addr to hit with
-	 * mmap_cache most of the time. We have zero last_addr at
+	 * vmacache most of the time. We have zero last_addr at
 	 * the beginning and also after lseek. We will have -1 last_addr
 	 * after the end of the vmas.
 	 */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 290901a8c1de..2b58d192ea24 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -342,9 +342,9 @@ struct mm_rss_stat {
 
 struct kioctx_table;
 struct mm_struct {
-	struct vm_area_struct * mmap;		/* list of VMAs */
+	struct vm_area_struct *mmap;		/* list of VMAs */
 	struct rb_root mm_rb;
-	struct vm_area_struct * mmap_cache;	/* last find_vma result */
+	u32 vmacache_seqnum;                   /* per-thread vmacache */
 #ifdef CONFIG_MMU
 	unsigned long (*get_unmapped_area) (struct file *filp,
 				unsigned long addr, unsigned long len,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 7cb07fd26680..642477dd814a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -132,6 +132,10 @@ struct perf_event_context;
 struct blk_plug;
 struct filename;
 
+#define VMACACHE_BITS 2
+#define VMACACHE_SIZE (1U << VMACACHE_BITS)
+#define VMACACHE_MASK (VMACACHE_SIZE - 1)
+
 /*
  * List of flags we want to share for kernel threads,
  * if only because they are not used by them anyway.
@@ -1235,6 +1239,9 @@ struct task_struct {
 #ifdef CONFIG_COMPAT_BRK
 	unsigned brk_randomized:1;
 #endif
+	/* per-thread vma caching */
+	u32 vmacache_seqnum;
+	struct vm_area_struct *vmacache[VMACACHE_SIZE];
 #if defined(SPLIT_RSS_COUNTING)
 	struct task_rss_stat	rss_stat;
 #endif
diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h
new file mode 100644
index 000000000000..c3fa0fd43949
--- /dev/null
+++ b/include/linux/vmacache.h
@@ -0,0 +1,38 @@
+#ifndef __LINUX_VMACACHE_H
+#define __LINUX_VMACACHE_H
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+
+/*
+ * Hash based on the page number. Provides a good hit rate for
+ * workloads with good locality and those with random accesses as well.
+ */
+#define VMACACHE_HASH(addr) ((addr >> PAGE_SHIFT) & VMACACHE_MASK)
+
+static inline void vmacache_flush(struct task_struct *tsk)
+{
+	memset(tsk->vmacache, 0, sizeof(tsk->vmacache));
+}
+
+extern void vmacache_flush_all(struct mm_struct *mm);
+extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma);
+extern struct vm_area_struct *vmacache_find(struct mm_struct *mm,
+						    unsigned long addr);
+
+#ifndef CONFIG_MMU
+extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm,
+						  unsigned long start,
+						  unsigned long end);
+#endif
+
+static inline void vmacache_invalidate(struct mm_struct *mm)
+{
+	mm->vmacache_seqnum++;
+
+	/* deal with overflows */
+	if (unlikely(mm->vmacache_seqnum == 0))
+		vmacache_flush_all(mm);
+}
+
+#endif /* __LINUX_VMACACHE_H */
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 99982a70ddad..2956c8da1605 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -49,6 +49,7 @@
 #include <linux/pid.h>
 #include <linux/smp.h>
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/rcupdate.h>
 
 #include <asm/cacheflush.h>
@@ -224,10 +225,17 @@ static void kgdb_flush_swbreak_addr(unsigned long addr)
 	if (!CACHE_FLUSH_IS_SAFE)
 		return;
 
-	if (current->mm && current->mm->mmap_cache) {
-		flush_cache_range(current->mm->mmap_cache,
-				  addr, addr + BREAK_INSTR_SIZE);
+	if (current->mm) {
+		int i;
+
+		for (i = 0; i < VMACACHE_SIZE; i++) {
+			if (!current->vmacache[i])
+				continue;
+			flush_cache_range(current->vmacache[i],
+					  addr, addr + BREAK_INSTR_SIZE);
+		}
 	}
+
 	/* Force flush instruction cache if it was outside the mm */
 	flush_icache_range(addr, addr + BREAK_INSTR_SIZE);
 }
diff --git a/kernel/fork.c b/kernel/fork.c
index e40c0a01d5a6..bc0e96b78dfd 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -28,6 +28,8 @@
 #include <linux/mman.h>
 #include <linux/mmu_notifier.h>
 #include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/nsproxy.h>
 #include <linux/capability.h>
 #include <linux/cpu.h>
@@ -364,7 +366,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 
 	mm->locked_vm = 0;
 	mm->mmap = NULL;
-	mm->mmap_cache = NULL;
+	mm->vmacache_seqnum = 0;
 	mm->map_count = 0;
 	cpumask_clear(mm_cpumask(mm));
 	mm->mm_rb = RB_ROOT;
@@ -882,6 +884,9 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
 	if (!oldmm)
 		return 0;
 
+	/* initialize the new vmacache entries */
+	vmacache_flush(tsk);
+
 	if (clone_flags & CLONE_VM) {
 		atomic_inc(&oldmm->mm_users);
 		mm = oldmm;
diff --git a/mm/Makefile b/mm/Makefile
index cdd741519ee0..23a6f7e23019 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -16,7 +16,7 @@ obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   util.o mmzone.o vmstat.o backing-dev.o \
 			   mm_init.o mmu_context.o percpu.o slab_common.o \
-			   compaction.o balloon_compaction.o \
+			   compaction.o balloon_compaction.o vmacache.o \
 			   interval_tree.o list_lru.o workingset.o $(mmu-y)
 
 obj-y += init-mm.o
diff --git a/mm/mmap.c b/mm/mmap.c
index 46433e137abc..b1202cf81f4b 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/backing-dev.h>
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/shm.h>
 #include <linux/mman.h>
 #include <linux/pagemap.h>
@@ -681,8 +682,9 @@ __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma,
 	prev->vm_next = next = vma->vm_next;
 	if (next)
 		next->vm_prev = prev;
-	if (mm->mmap_cache == vma)
-		mm->mmap_cache = prev;
+
+	/* Kill the cache */
+	vmacache_invalidate(mm);
 }
 
 /*
@@ -1989,34 +1991,33 @@ EXPORT_SYMBOL(get_unmapped_area);
 /* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
 struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 {
-	struct vm_area_struct *vma = NULL;
+	struct rb_node *rb_node;
+	struct vm_area_struct *vma;
 
 	/* Check the cache first. */
-	/* (Cache hit rate is typically around 35%.) */
-	vma = ACCESS_ONCE(mm->mmap_cache);
-	if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) {
-		struct rb_node *rb_node;
+	vma = vmacache_find(mm, addr);
+	if (likely(vma))
+		return vma;
 
-		rb_node = mm->mm_rb.rb_node;
-		vma = NULL;
+	rb_node = mm->mm_rb.rb_node;
+	vma = NULL;
 
-		while (rb_node) {
-			struct vm_area_struct *vma_tmp;
-
-			vma_tmp = rb_entry(rb_node,
-					   struct vm_area_struct, vm_rb);
-
-			if (vma_tmp->vm_end > addr) {
-				vma = vma_tmp;
-				if (vma_tmp->vm_start <= addr)
-					break;
-				rb_node = rb_node->rb_left;
-			} else
-				rb_node = rb_node->rb_right;
-		}
-		if (vma)
-			mm->mmap_cache = vma;
+	while (rb_node) {
+		struct vm_area_struct *tmp;
+
+		tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb);
+
+		if (tmp->vm_end > addr) {
+			vma = tmp;
+			if (tmp->vm_start <= addr)
+				break;
+			rb_node = rb_node->rb_left;
+		} else
+			rb_node = rb_node->rb_right;
 	}
+
+	if (vma)
+		vmacache_update(addr, vma);
 	return vma;
 }
 
@@ -2388,7 +2389,9 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 	} else
 		mm->highest_vm_end = prev ? prev->vm_end : 0;
 	tail_vma->vm_next = NULL;
-	mm->mmap_cache = NULL;		/* Kill the cache. */
+
+	/* Kill the cache */
+	vmacache_invalidate(mm);
 }
 
 /*
diff --git a/mm/nommu.c b/mm/nommu.c
index e19482533ce3..5d3f3524bbdc 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -15,6 +15,7 @@
 
 #include <linux/export.h>
 #include <linux/mm.h>
+#include <linux/vmacache.h>
 #include <linux/mman.h>
 #include <linux/swap.h>
 #include <linux/file.h>
@@ -768,16 +769,23 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
  */
 static void delete_vma_from_mm(struct vm_area_struct *vma)
 {
+	int i;
 	struct address_space *mapping;
 	struct mm_struct *mm = vma->vm_mm;
+	struct task_struct *curr = current;
 
 	kenter("%p", vma);
 
 	protect_vma(vma, 0);
 
 	mm->map_count--;
-	if (mm->mmap_cache == vma)
-		mm->mmap_cache = NULL;
+	for (i = 0; i < VMACACHE_SIZE; i++) {
+		/* if the vma is cached, invalidate the entire cache */
+		if (curr->vmacache[i] == vma) {
+			vmacache_invalidate(curr->mm);
+			break;
+		}
+	}
 
 	/* remove the VMA from the mapping */
 	if (vma->vm_file) {
@@ -825,8 +833,8 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 	struct vm_area_struct *vma;
 
 	/* check the cache first */
-	vma = ACCESS_ONCE(mm->mmap_cache);
-	if (vma && vma->vm_start <= addr && vma->vm_end > addr)
+	vma = vmacache_find(mm, addr);
+	if (likely(vma))
 		return vma;
 
 	/* trawl the list (there may be multiple mappings in which addr
@@ -835,7 +843,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 		if (vma->vm_start > addr)
 			return NULL;
 		if (vma->vm_end > addr) {
-			mm->mmap_cache = vma;
+			vmacache_update(addr, vma);
 			return vma;
 		}
 	}
@@ -874,8 +882,8 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
 	unsigned long end = addr + len;
 
 	/* check the cache first */
-	vma = mm->mmap_cache;
-	if (vma && vma->vm_start == addr && vma->vm_end == end)
+	vma = vmacache_find_exact(mm, addr, end);
+	if (vma)
 		return vma;
 
 	/* trawl the list (there may be multiple mappings in which addr
@@ -886,7 +894,7 @@ static struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
 		if (vma->vm_start > addr)
 			return NULL;
 		if (vma->vm_end == end) {
-			mm->mmap_cache = vma;
+			vmacache_update(addr, vma);
 			return vma;
 		}
 	}
diff --git a/mm/vmacache.c b/mm/vmacache.c
new file mode 100644
index 000000000000..d4224b397c0e
--- /dev/null
+++ b/mm/vmacache.c
@@ -0,0 +1,112 @@
+/*
+ * Copyright (C) 2014 Davidlohr Bueso.
+ */
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/vmacache.h>
+
+/*
+ * Flush vma caches for threads that share a given mm.
+ *
+ * The operation is safe because the caller holds the mmap_sem
+ * exclusively and other threads accessing the vma cache will
+ * have mmap_sem held at least for read, so no extra locking
+ * is required to maintain the vma cache.
+ */
+void vmacache_flush_all(struct mm_struct *mm)
+{
+	struct task_struct *g, *p;
+
+	rcu_read_lock();
+	for_each_process_thread(g, p) {
+		/*
+		 * Only flush the vmacache pointers as the
+		 * mm seqnum is already set and curr's will
+		 * be set upon invalidation when the next
+		 * lookup is done.
+		 */
+		if (mm == p->mm)
+			vmacache_flush(p);
+	}
+	rcu_read_unlock();
+}
+
+/*
+ * This task may be accessing a foreign mm via (for example)
+ * get_user_pages()->find_vma().  The vmacache is task-local and this
+ * task's vmacache pertains to a different mm (ie, its own).  There is
+ * nothing we can do here.
+ *
+ * Also handle the case where a kernel thread has adopted this mm via use_mm().
+ * That kernel thread's vmacache is not applicable to this mm.
+ */
+static bool vmacache_valid_mm(struct mm_struct *mm)
+{
+	return current->mm == mm && !(current->flags & PF_KTHREAD);
+}
+
+void vmacache_update(unsigned long addr, struct vm_area_struct *newvma)
+{
+	if (vmacache_valid_mm(newvma->vm_mm))
+		current->vmacache[VMACACHE_HASH(addr)] = newvma;
+}
+
+static bool vmacache_valid(struct mm_struct *mm)
+{
+	struct task_struct *curr;
+
+	if (!vmacache_valid_mm(mm))
+		return false;
+
+	curr = current;
+	if (mm->vmacache_seqnum != curr->vmacache_seqnum) {
+		/*
+		 * First attempt will always be invalid, initialize
+		 * the new cache for this task here.
+		 */
+		curr->vmacache_seqnum = mm->vmacache_seqnum;
+		vmacache_flush(curr);
+		return false;
+	}
+	return true;
+}
+
+struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr)
+{
+	int i;
+
+	if (!vmacache_valid(mm))
+		return NULL;
+
+	for (i = 0; i < VMACACHE_SIZE; i++) {
+		struct vm_area_struct *vma = current->vmacache[i];
+
+		if (vma && vma->vm_start <= addr && vma->vm_end > addr) {
+			BUG_ON(vma->vm_mm != mm);
+			return vma;
+		}
+	}
+
+	return NULL;
+}
+
+#ifndef CONFIG_MMU
+struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm,
+					   unsigned long start,
+					   unsigned long end)
+{
+	int i;
+
+	if (!vmacache_valid(mm))
+		return NULL;
+
+	for (i = 0; i < VMACACHE_SIZE; i++) {
+		struct vm_area_struct *vma = current->vmacache[i];
+
+		if (vma && vma->vm_start == start && vma->vm_end == end)
+			return vma;
+	}
+
+	return NULL;
+}
+#endif
-- 
cgit v1.2.3


From 2a389610a7331d22344698f23ef2e8c55b2cde7b Mon Sep 17 00:00:00 2001
From: David Rientjes <rientjes@google.com>
Date: Mon, 7 Apr 2014 15:37:29 -0700
Subject: mm, mempolicy: rename slab_node for clarity

slab_node() is actually a mempolicy function, so rename it to
mempolicy_slab_node() to make it clearer that it used for processes with
mempolicies.

At the same time, cleanup its code by saving numa_mem_id() in a local
variable (since we require a node with memory, not just any node) and
remove an obsolete comment that assumes the mempolicy is actually passed
into the function.

Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: Christoph Lameter <cl@linux.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Jianguo Wu <wujianguo@huawei.com>
Cc: Tim Hockin <thockin@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mempolicy.h |  2 +-
 mm/mempolicy.c            | 15 ++++++---------
 mm/slab.c                 |  4 ++--
 mm/slub.c                 |  2 +-
 4 files changed, 10 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 5f1ea756aace..cfe55dfca015 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -151,7 +151,7 @@ extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
 extern bool init_nodemask_of_mempolicy(nodemask_t *mask);
 extern bool mempolicy_nodemask_intersects(struct task_struct *tsk,
 				const nodemask_t *mask);
-extern unsigned slab_node(void);
+extern unsigned int mempolicy_slab_node(void);
 
 extern enum zone_type policy_zone;
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e3ab02822799..0ad0ba31979f 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1782,21 +1782,18 @@ static unsigned interleave_nodes(struct mempolicy *policy)
 /*
  * Depending on the memory policy provide a node from which to allocate the
  * next slab entry.
- * @policy must be protected by freeing by the caller.  If @policy is
- * the current task's mempolicy, this protection is implicit, as only the
- * task can change it's policy.  The system default policy requires no
- * such protection.
  */
-unsigned slab_node(void)
+unsigned int mempolicy_slab_node(void)
 {
 	struct mempolicy *policy;
+	int node = numa_mem_id();
 
 	if (in_interrupt())
-		return numa_node_id();
+		return node;
 
 	policy = current->mempolicy;
 	if (!policy || policy->flags & MPOL_F_LOCAL)
-		return numa_node_id();
+		return node;
 
 	switch (policy->mode) {
 	case MPOL_PREFERRED:
@@ -1816,11 +1813,11 @@ unsigned slab_node(void)
 		struct zonelist *zonelist;
 		struct zone *zone;
 		enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL);
-		zonelist = &NODE_DATA(numa_node_id())->node_zonelists[0];
+		zonelist = &NODE_DATA(node)->node_zonelists[0];
 		(void)first_zones_zonelist(zonelist, highest_zoneidx,
 							&policy->v.nodes,
 							&zone);
-		return zone ? zone->node : numa_node_id();
+		return zone ? zone->node : node;
 	}
 
 	default:
diff --git a/mm/slab.c b/mm/slab.c
index 9153c802e2fe..4b17f4c2e92d 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3042,7 +3042,7 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
 	if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
 		nid_alloc = cpuset_slab_spread_node();
 	else if (current->mempolicy)
-		nid_alloc = slab_node();
+		nid_alloc = mempolicy_slab_node();
 	if (nid_alloc != nid_here)
 		return ____cache_alloc_node(cachep, flags, nid_alloc);
 	return NULL;
@@ -3074,7 +3074,7 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
 
 retry_cpuset:
 	cpuset_mems_cookie = read_mems_allowed_begin();
-	zonelist = node_zonelist(slab_node(), flags);
+	zonelist = node_zonelist(mempolicy_slab_node(), flags);
 
 retry:
 	/*
diff --git a/mm/slub.c b/mm/slub.c
index fe6d7be22ef0..5b05e4fe9a1a 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1685,7 +1685,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
 
 	do {
 		cpuset_mems_cookie = read_mems_allowed_begin();
-		zonelist = node_zonelist(slab_node(), flags);
+		zonelist = node_zonelist(mempolicy_slab_node(), flags);
 		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
 			struct kmem_cache_node *n;
 
-- 
cgit v1.2.3


From f0432d159601f96839f514f286eaa5b75c4112dc Mon Sep 17 00:00:00 2001
From: David Rientjes <rientjes@google.com>
Date: Mon, 7 Apr 2014 15:37:30 -0700
Subject: mm, mempolicy: remove per-process flag

PF_MEMPOLICY is an unnecessary optimization for CONFIG_SLAB users.
There's no significant performance degradation to checking
current->mempolicy rather than current->flags & PF_MEMPOLICY in the
allocation path, especially since this is considered unlikely().

Running TCP_RR with netperf-2.4.5 through localhost on 16 cpu machine with
64GB of memory and without a mempolicy:

	threads		before		after
	16		1249409		1244487
	32		1281786		1246783
	48		1239175		1239138
	64		1244642		1241841
	80		1244346		1248918
	96		1266436		1254316
	112		1307398		1312135
	128		1327607		1326502

Per-process flags are a scarce resource so we should free them up whenever
possible and make them available.  We'll be using it shortly for memcg oom
reserves.

Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Jianguo Wu <wujianguo@huawei.com>
Cc: Tim Hockin <thockin@google.com>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mempolicy.h |  1 -
 include/linux/sched.h     |  1 -
 kernel/fork.c             |  1 -
 mm/mempolicy.c            | 31 -------------------------------
 mm/slab.c                 |  4 ++--
 5 files changed, 2 insertions(+), 36 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index cfe55dfca015..3c1b968da0ca 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -143,7 +143,6 @@ extern void numa_policy_init(void);
 extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new,
 				enum mpol_rebind_step step);
 extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new);
-extern void mpol_fix_fork_child_flag(struct task_struct *p);
 
 extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
 				unsigned long addr, gfp_t gfp_flags,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 642477dd814a..6c70645eb3b6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1851,7 +1851,6 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 #define PF_SPREAD_SLAB	0x02000000	/* Spread some slab caches over cpuset */
 #define PF_NO_SETAFFINITY 0x04000000	/* Userland is not allowed to meddle with cpus_allowed */
 #define PF_MCE_EARLY    0x08000000      /* Early kill for mce process policy */
-#define PF_MEMPOLICY	0x10000000	/* Non-default NUMA mempolicy */
 #define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */
 #define PF_FREEZER_SKIP	0x40000000	/* Freezer should not count it as freezable */
 #define PF_SUSPEND_TASK 0x80000000      /* this thread called freeze_processes and should not be frozen */
diff --git a/kernel/fork.c b/kernel/fork.c
index c777964c0662..e905e9c6b224 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1276,7 +1276,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		p->mempolicy = NULL;
 		goto bad_fork_cleanup_threadgroup_lock;
 	}
-	mpol_fix_fork_child_flag(p);
 #endif
 #ifdef CONFIG_CPUSETS
 	p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 0ad0ba31979f..78e1472933ea 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -795,36 +795,6 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
 	return err;
 }
 
-/*
- * Update task->flags PF_MEMPOLICY bit: set iff non-default
- * mempolicy.  Allows more rapid checking of this (combined perhaps
- * with other PF_* flag bits) on memory allocation hot code paths.
- *
- * If called from outside this file, the task 'p' should -only- be
- * a newly forked child not yet visible on the task list, because
- * manipulating the task flags of a visible task is not safe.
- *
- * The above limitation is why this routine has the funny name
- * mpol_fix_fork_child_flag().
- *
- * It is also safe to call this with a task pointer of current,
- * which the static wrapper mpol_set_task_struct_flag() does,
- * for use within this file.
- */
-
-void mpol_fix_fork_child_flag(struct task_struct *p)
-{
-	if (p->mempolicy)
-		p->flags |= PF_MEMPOLICY;
-	else
-		p->flags &= ~PF_MEMPOLICY;
-}
-
-static void mpol_set_task_struct_flag(void)
-{
-	mpol_fix_fork_child_flag(current);
-}
-
 /* Set the process memory policy */
 static long do_set_mempolicy(unsigned short mode, unsigned short flags,
 			     nodemask_t *nodes)
@@ -861,7 +831,6 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
 	}
 	old = current->mempolicy;
 	current->mempolicy = new;
-	mpol_set_task_struct_flag();
 	if (new && new->mode == MPOL_INTERLEAVE &&
 	    nodes_weight(new->v.nodes))
 		current->il_next = first_node(new->v.nodes);
diff --git a/mm/slab.c b/mm/slab.c
index 4b17f4c2e92d..3db4cb06e32e 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3027,7 +3027,7 @@ out:
 
 #ifdef CONFIG_NUMA
 /*
- * Try allocating on another node if PF_SPREAD_SLAB|PF_MEMPOLICY.
+ * Try allocating on another node if PF_SPREAD_SLAB is a mempolicy is set.
  *
  * If we are in_interrupt, then process context, including cpusets and
  * mempolicy, may not apply and should not be used for allocation policy.
@@ -3259,7 +3259,7 @@ __do_cache_alloc(struct kmem_cache *cache, gfp_t flags)
 {
 	void *objp;
 
-	if (unlikely(current->flags & (PF_SPREAD_SLAB | PF_MEMPOLICY))) {
+	if (current->mempolicy || unlikely(current->flags & PF_SPREAD_SLAB)) {
 		objp = alternate_node_alloc(cache, flags);
 		if (objp)
 			goto out;
-- 
cgit v1.2.3


From 539a13b47e462d28c48f076c63871580f694a366 Mon Sep 17 00:00:00 2001
From: David Rientjes <rientjes@google.com>
Date: Mon, 7 Apr 2014 15:37:32 -0700
Subject: res_counter: remove interface for locked charging and uncharging

The res_counter_{charge,uncharge}_locked() variants are not used in the
kernel outside of the resource counter code itself, so remove the
interface.

Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Jianguo Wu <wujianguo@huawei.com>
Cc: Tim Hockin <thockin@google.com>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/cgroups/resource_counter.txt | 12 ++----------
 include/linux/res_counter.h                |  6 +-----
 kernel/res_counter.c                       | 23 ++++++++++++-----------
 3 files changed, 15 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/cgroups/resource_counter.txt b/Documentation/cgroups/resource_counter.txt
index 5108afb3645c..762ca54eb929 100644
--- a/Documentation/cgroups/resource_counter.txt
+++ b/Documentation/cgroups/resource_counter.txt
@@ -76,15 +76,7 @@ to work with it.
 	limit_fail_at parameter is set to the particular res_counter element
 	where the charging failed.
 
- d. int res_counter_charge_locked
-			(struct res_counter *rc, unsigned long val, bool force)
-
-	The same as res_counter_charge(), but it must not acquire/release the
-	res_counter->lock internally (it must be called with res_counter->lock
-	held). The force parameter indicates whether we can bypass the limit.
-
- e. u64 res_counter_uncharge[_locked]
-			(struct res_counter *rc, unsigned long val)
+ d. u64 res_counter_uncharge(struct res_counter *rc, unsigned long val)
 
 	When a resource is released (freed) it should be de-accounted
 	from the resource counter it was accounted to.  This is called
@@ -93,7 +85,7 @@ to work with it.
 
 	The _locked routines imply that the res_counter->lock is taken.
 
- f. u64 res_counter_uncharge_until
+ e. u64 res_counter_uncharge_until
 		(struct res_counter *rc, struct res_counter *top,
 		 unsigned long val)
 
diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
index 201a69749659..56b7bc32db4f 100644
--- a/include/linux/res_counter.h
+++ b/include/linux/res_counter.h
@@ -104,15 +104,13 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent);
  *       units, e.g. numbers, bytes, Kbytes, etc
  *
  * returns 0 on success and <0 if the counter->usage will exceed the
- * counter->limit _locked call expects the counter->lock to be taken
+ * counter->limit
  *
  * charge_nofail works the same, except that it charges the resource
  * counter unconditionally, and returns < 0 if the after the current
  * charge we are over limit.
  */
 
-int __must_check res_counter_charge_locked(struct res_counter *counter,
-					   unsigned long val, bool force);
 int __must_check res_counter_charge(struct res_counter *counter,
 		unsigned long val, struct res_counter **limit_fail_at);
 int res_counter_charge_nofail(struct res_counter *counter,
@@ -125,12 +123,10 @@ int res_counter_charge_nofail(struct res_counter *counter,
  * @val: the amount of the resource
  *
  * these calls check for usage underflow and show a warning on the console
- * _locked call expects the counter->lock to be taken
  *
  * returns the total charges still present in @counter.
  */
 
-u64 res_counter_uncharge_locked(struct res_counter *counter, unsigned long val);
 u64 res_counter_uncharge(struct res_counter *counter, unsigned long val);
 
 u64 res_counter_uncharge_until(struct res_counter *counter,
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index 4aa8a305aede..51dbac6a3633 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -22,8 +22,18 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent)
 	counter->parent = parent;
 }
 
-int res_counter_charge_locked(struct res_counter *counter, unsigned long val,
-			      bool force)
+static u64 res_counter_uncharge_locked(struct res_counter *counter,
+				       unsigned long val)
+{
+	if (WARN_ON(counter->usage < val))
+		val = counter->usage;
+
+	counter->usage -= val;
+	return counter->usage;
+}
+
+static int res_counter_charge_locked(struct res_counter *counter,
+				     unsigned long val, bool force)
 {
 	int ret = 0;
 
@@ -86,15 +96,6 @@ int res_counter_charge_nofail(struct res_counter *counter, unsigned long val,
 	return __res_counter_charge(counter, val, limit_fail_at, true);
 }
 
-u64 res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
-{
-	if (WARN_ON(counter->usage < val))
-		val = counter->usage;
-
-	counter->usage -= val;
-	return counter->usage;
-}
-
 u64 res_counter_uncharge_until(struct res_counter *counter,
 			       struct res_counter *top,
 			       unsigned long val)
-- 
cgit v1.2.3


From d230dec18dc9a581f153c14cb5371640cd62543b Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Mon, 7 Apr 2014 15:37:38 -0700
Subject: mm: use 'const char *' insted of 'char *' for reason in dump_page()

I tried to use 'dump_page(page, __func__)' for debugging, but it triggers
warning:

  warning: passing argument 2 of `dump_page' discards `const' qualifier from pointer target type [enabled by default]

Let's convert 'reason' to 'const char *' in dump_page() and friends: we
shouldn't modify it anyway.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmdebug.h |  4 ++--
 mm/page_alloc.c         | 12 +++++++-----
 2 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
index 5042c036dda9..2d57efa64cc1 100644
--- a/include/linux/mmdebug.h
+++ b/include/linux/mmdebug.h
@@ -3,8 +3,8 @@
 
 struct page;
 
-extern void dump_page(struct page *page, char *reason);
-extern void dump_page_badflags(struct page *page, char *reason,
+extern void dump_page(struct page *page, const char *reason);
+extern void dump_page_badflags(struct page *page, const char *reason,
 			       unsigned long badflags);
 
 #ifdef CONFIG_DEBUG_VM
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 336ee925f756..73c25912c7c4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -295,7 +295,8 @@ static inline int bad_range(struct zone *zone, struct page *page)
 }
 #endif
 
-static void bad_page(struct page *page, char *reason, unsigned long bad_flags)
+static void bad_page(struct page *page, const char *reason,
+		unsigned long bad_flags)
 {
 	static unsigned long resume;
 	static unsigned long nr_shown;
@@ -623,7 +624,7 @@ out:
 
 static inline int free_pages_check(struct page *page)
 {
-	char *bad_reason = NULL;
+	const char *bad_reason = NULL;
 	unsigned long bad_flags = 0;
 
 	if (unlikely(page_mapcount(page)))
@@ -859,7 +860,7 @@ static inline void expand(struct zone *zone, struct page *page,
  */
 static inline int check_new_page(struct page *page)
 {
-	char *bad_reason = NULL;
+	const char *bad_reason = NULL;
 	unsigned long bad_flags = 0;
 
 	if (unlikely(page_mapcount(page)))
@@ -6545,7 +6546,8 @@ static void dump_page_flags(unsigned long flags)
 	printk(")\n");
 }
 
-void dump_page_badflags(struct page *page, char *reason, unsigned long badflags)
+void dump_page_badflags(struct page *page, const char *reason,
+		unsigned long badflags)
 {
 	printk(KERN_ALERT
 	       "page:%p count:%d mapcount:%d mapping:%p index:%#lx\n",
@@ -6561,7 +6563,7 @@ void dump_page_badflags(struct page *page, char *reason, unsigned long badflags)
 	mem_cgroup_print_bad_page(page);
 }
 
-void dump_page(struct page *page, char *reason)
+void dump_page(struct page *page, const char *reason)
 {
 	dump_page_badflags(page, reason, 0);
 }
-- 
cgit v1.2.3


From df381975463996178d685f6ef7d3555c5f887201 Mon Sep 17 00:00:00 2001
From: Johannes Weiner <hannes@cmpxchg.org>
Date: Mon, 7 Apr 2014 15:37:43 -0700
Subject: memcg: get_mem_cgroup_from_mm()

Instead of returning NULL from try_get_mem_cgroup_from_mm() when the mm
owner is exiting, just return root_mem_cgroup.  This makes sense for all
callsites and gets rid of some of them having to fallback manually.

[fengguang.wu@intel.com: fix warnings]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  6 ------
 mm/memcontrol.c            | 18 ++++--------------
 2 files changed, 4 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index eccfb4a4b379..134636f835f7 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -94,7 +94,6 @@ bool task_in_mem_cgroup(struct task_struct *task,
 
 extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
 extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
-extern struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm);
 
 extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
 extern struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css);
@@ -294,11 +293,6 @@ static inline struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
 	return NULL;
 }
 
-static inline struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
-{
-	return NULL;
-}
-
 static inline bool mm_match_cgroup(struct mm_struct *mm,
 		struct mem_cgroup *memcg)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c3b674f9774f..87c3ec37dd26 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1071,7 +1071,7 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 	return mem_cgroup_from_css(task_css(p, memory_cgrp_id));
 }
 
-struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
+static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 {
 	struct mem_cgroup *memcg = NULL;
 
@@ -1079,7 +1079,7 @@ struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
 	do {
 		memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
 		if (unlikely(!memcg))
-			break;
+			memcg = root_mem_cgroup;
 	} while (!css_tryget(&memcg->css));
 	rcu_read_unlock();
 	return memcg;
@@ -1475,7 +1475,7 @@ bool task_in_mem_cgroup(struct task_struct *task,
 
 	p = find_lock_task_mm(task);
 	if (p) {
-		curr = try_get_mem_cgroup_from_mm(p->mm);
+		curr = get_mem_cgroup_from_mm(p->mm);
 		task_unlock(p);
 	} else {
 		/*
@@ -1489,8 +1489,6 @@ bool task_in_mem_cgroup(struct task_struct *task,
 			css_get(&curr->css);
 		rcu_read_unlock();
 	}
-	if (!curr)
-		return false;
 	/*
 	 * We should check use_hierarchy of "memcg" not "curr". Because checking
 	 * use_hierarchy of "curr" here make this function true if hierarchy is
@@ -3617,15 +3615,7 @@ __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order)
 	if (!current->mm || current->memcg_kmem_skip_account)
 		return true;
 
-	memcg = try_get_mem_cgroup_from_mm(current->mm);
-
-	/*
-	 * very rare case described in mem_cgroup_from_task. Unfortunately there
-	 * isn't much we can do without complicating this too much, and it would
-	 * be gfp-dependent anyway. Just let it go
-	 */
-	if (unlikely(!memcg))
-		return true;
+	memcg = get_mem_cgroup_from_mm(current->mm);
 
 	if (!memcg_can_account_kmem(memcg)) {
 		css_put(&memcg->css);
-- 
cgit v1.2.3


From d715ae08f2ff87508a081c4df78061bf4f7211d6 Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.cz>
Date: Mon, 7 Apr 2014 15:37:46 -0700
Subject: memcg: rename high level charging functions

mem_cgroup_newpage_charge is used only for charging anonymous memory so
it is better to rename it to mem_cgroup_charge_anon.

mem_cgroup_cache_charge is used for file backed memory so rename it to
mem_cgroup_charge_file.

Signed-off-by: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/cgroups/memcg_test.txt | 4 ++--
 include/linux/memcontrol.h           | 8 ++++----
 mm/filemap.c                         | 2 +-
 mm/huge_memory.c                     | 8 ++++----
 mm/memcontrol.c                      | 4 ++--
 mm/memory.c                          | 6 +++---
 mm/shmem.c                           | 6 +++---
 7 files changed, 19 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/cgroups/memcg_test.txt b/Documentation/cgroups/memcg_test.txt
index ce94a83a7d9a..80ac454704b8 100644
--- a/Documentation/cgroups/memcg_test.txt
+++ b/Documentation/cgroups/memcg_test.txt
@@ -24,7 +24,7 @@ Please note that implementation details can be changed.
 
    a page/swp_entry may be charged (usage += PAGE_SIZE) at
 
-	mem_cgroup_newpage_charge()
+	mem_cgroup_charge_anon()
 	  Called at new page fault and Copy-On-Write.
 
 	mem_cgroup_try_charge_swapin()
@@ -32,7 +32,7 @@ Please note that implementation details can be changed.
 	  Followed by charge-commit-cancel protocol. (With swap accounting)
 	  At commit, a charge recorded in swap_cgroup is removed.
 
-	mem_cgroup_cache_charge()
+	mem_cgroup_charge_file()
 	  Called at add_to_page_cache()
 
 	mem_cgroup_cache_charge_swapin()
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 134636f835f7..96f3fc87ab96 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -65,7 +65,7 @@ struct mem_cgroup_reclaim_cookie {
  * (Of course, if memcg does memory allocation in future, GFP_KERNEL is sane.)
  */
 
-extern int mem_cgroup_newpage_charge(struct page *page, struct mm_struct *mm,
+extern int mem_cgroup_charge_anon(struct page *page, struct mm_struct *mm,
 				gfp_t gfp_mask);
 /* for swap handling */
 extern int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
@@ -74,7 +74,7 @@ extern void mem_cgroup_commit_charge_swapin(struct page *page,
 					struct mem_cgroup *memcg);
 extern void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg);
 
-extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
+extern int mem_cgroup_charge_file(struct page *page, struct mm_struct *mm,
 					gfp_t gfp_mask);
 
 struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *);
@@ -233,13 +233,13 @@ void mem_cgroup_print_bad_page(struct page *page);
 #else /* CONFIG_MEMCG */
 struct mem_cgroup;
 
-static inline int mem_cgroup_newpage_charge(struct page *page,
+static inline int mem_cgroup_charge_anon(struct page *page,
 					struct mm_struct *mm, gfp_t gfp_mask)
 {
 	return 0;
 }
 
-static inline int mem_cgroup_cache_charge(struct page *page,
+static inline int mem_cgroup_charge_file(struct page *page,
 					struct mm_struct *mm, gfp_t gfp_mask)
 {
 	return 0;
diff --git a/mm/filemap.c b/mm/filemap.c
index b952d99c827c..27ebc0c9571b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -563,7 +563,7 @@ static int __add_to_page_cache_locked(struct page *page,
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(PageSwapBacked(page), page);
 
-	error = mem_cgroup_cache_charge(page, current->mm,
+	error = mem_cgroup_charge_file(page, current->mm,
 					gfp_mask & GFP_RECLAIM_MASK);
 	if (error)
 		return error;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index a2f4981418fc..64635f5278ff 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -827,7 +827,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		count_vm_event(THP_FAULT_FALLBACK);
 		return VM_FAULT_FALLBACK;
 	}
-	if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
+	if (unlikely(mem_cgroup_charge_anon(page, mm, GFP_KERNEL))) {
 		put_page(page);
 		count_vm_event(THP_FAULT_FALLBACK);
 		return VM_FAULT_FALLBACK;
@@ -968,7 +968,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 					       __GFP_OTHER_NODE,
 					       vma, address, page_to_nid(page));
 		if (unlikely(!pages[i] ||
-			     mem_cgroup_newpage_charge(pages[i], mm,
+			     mem_cgroup_charge_anon(pages[i], mm,
 						       GFP_KERNEL))) {
 			if (pages[i])
 				put_page(pages[i]);
@@ -1101,7 +1101,7 @@ alloc:
 		goto out;
 	}
 
-	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
+	if (unlikely(mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL))) {
 		put_page(new_page);
 		if (page) {
 			split_huge_page(page);
@@ -2359,7 +2359,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	if (!new_page)
 		return;
 
-	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL)))
+	if (unlikely(mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL)))
 		return;
 
 	/*
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 038b037f8d67..e33b1d09eb1f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3818,7 +3818,7 @@ out:
 	return ret;
 }
 
-int mem_cgroup_newpage_charge(struct page *page,
+int mem_cgroup_charge_anon(struct page *page,
 			      struct mm_struct *mm, gfp_t gfp_mask)
 {
 	unsigned int nr_pages = 1;
@@ -3954,7 +3954,7 @@ void mem_cgroup_commit_charge_swapin(struct page *page,
 					  MEM_CGROUP_CHARGE_TYPE_ANON);
 }
 
-int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
+int mem_cgroup_charge_file(struct page *page, struct mm_struct *mm,
 				gfp_t gfp_mask)
 {
 	enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE;
diff --git a/mm/memory.c b/mm/memory.c
index 1b88da5c08b3..854e4027719f 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2828,7 +2828,7 @@ gotten:
 	}
 	__SetPageUptodate(new_page);
 
-	if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))
+	if (mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL))
 		goto oom_free_new;
 
 	mmun_start  = address & PAGE_MASK;
@@ -3281,7 +3281,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	 */
 	__SetPageUptodate(page);
 
-	if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))
+	if (mem_cgroup_charge_anon(page, mm, GFP_KERNEL))
 		goto oom_free_page;
 
 	entry = mk_pte(page, vma->vm_page_prot);
@@ -3537,7 +3537,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (!new_page)
 		return VM_FAULT_OOM;
 
-	if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL)) {
+	if (mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL)) {
 		page_cache_release(new_page);
 		return VM_FAULT_OOM;
 	}
diff --git a/mm/shmem.c b/mm/shmem.c
index 70709347a1e2..70273f8df586 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -683,7 +683,7 @@ int shmem_unuse(swp_entry_t swap, struct page *page)
 	 * the shmem_swaplist_mutex which might hold up shmem_writepage().
 	 * Charged back to the user (not to caller) when swap account is used.
 	 */
-	error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL);
+	error = mem_cgroup_charge_file(page, current->mm, GFP_KERNEL);
 	if (error)
 		goto out;
 	/* No radix_tree_preload: swap entry keeps a place for page in tree */
@@ -1080,7 +1080,7 @@ repeat:
 				goto failed;
 		}
 
-		error = mem_cgroup_cache_charge(page, current->mm,
+		error = mem_cgroup_charge_file(page, current->mm,
 						gfp & GFP_RECLAIM_MASK);
 		if (!error) {
 			error = shmem_add_to_page_cache(page, mapping, index,
@@ -1134,7 +1134,7 @@ repeat:
 
 		SetPageSwapBacked(page);
 		__set_page_locked(page);
-		error = mem_cgroup_cache_charge(page, current->mm,
+		error = mem_cgroup_charge_file(page, current->mm,
 						gfp & GFP_RECLAIM_MASK);
 		if (error)
 			goto decused;
-- 
cgit v1.2.3


From ed6d7c8e578331cad594ee70d60e2e146b5dce7b Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@suse.cz>
Date: Mon, 7 Apr 2014 15:37:51 -0700
Subject: mm: remove unused arg of set_page_dirty_balance()

There's only one caller of set_page_dirty_balance() and that will call it
with page_mkwrite == 0.

The page_mkwrite argument was unused since commit b827e496c893 "mm: close
page_mkwrite races".

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/writeback.h | 2 +-
 mm/memory.c               | 2 +-
 mm/page-writeback.c       | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 021b8a319b9e..5777c13849ba 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -178,7 +178,7 @@ int write_cache_pages(struct address_space *mapping,
 		      struct writeback_control *wbc, writepage_t writepage,
 		      void *data);
 int do_writepages(struct address_space *mapping, struct writeback_control *wbc);
-void set_page_dirty_balance(struct page *page, int page_mkwrite);
+void set_page_dirty_balance(struct page *page);
 void writeback_set_ratelimit(void);
 void tag_pages_for_writeback(struct address_space *mapping,
 			     pgoff_t start, pgoff_t end);
diff --git a/mm/memory.c b/mm/memory.c
index 854e4027719f..d0f0bef3be48 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2782,7 +2782,7 @@ reuse:
 		 */
 		if (!page_mkwrite) {
 			wait_on_page_locked(dirty_page);
-			set_page_dirty_balance(dirty_page, page_mkwrite);
+			set_page_dirty_balance(dirty_page);
 			/* file_update_time outside page_lock */
 			if (vma->vm_file)
 				file_update_time(vma->vm_file);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 7106cb1aca8e..ef413492a149 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1562,9 +1562,9 @@ pause:
 		bdi_start_background_writeback(bdi);
 }
 
-void set_page_dirty_balance(struct page *page, int page_mkwrite)
+void set_page_dirty_balance(struct page *page)
 {
-	if (set_page_dirty(page) || page_mkwrite) {
+	if (set_page_dirty(page)) {
 		struct address_space *mapping = page_mapping(page);
 
 		if (mapping)
-- 
cgit v1.2.3


From 29f175d125f0f3a9503af8a5596f93d714cceb08 Mon Sep 17 00:00:00 2001
From: Fabian Frederick <fabf@skynet.be>
Date: Mon, 7 Apr 2014 15:37:55 -0700
Subject: mm/readahead.c: inline ra_submit

Commit f9acc8c7b35a ("readahead: sanify file_ra_state names") left
ra_submit with a single function call.

Move ra_submit to internal.h and inline it to save some stack.  Thanks
to Andrew Morton for commenting different versions.

Signed-off-by: Fabian Frederick <fabf@skynet.be>
Suggested-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h |  3 ---
 mm/internal.h      | 15 +++++++++++++++
 mm/readahead.c     | 21 +++------------------
 3 files changed, 18 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9132faed1a41..6edcea720ddd 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1875,9 +1875,6 @@ void page_cache_async_readahead(struct address_space *mapping,
 				unsigned long size);
 
 unsigned long max_sane_readahead(unsigned long nr);
-unsigned long ra_submit(struct file_ra_state *ra,
-			struct address_space *mapping,
-			struct file *filp);
 
 /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
 extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
diff --git a/mm/internal.h b/mm/internal.h
index 3e910000fda4..07b67361a40a 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -11,6 +11,7 @@
 #ifndef __MM_INTERNAL_H
 #define __MM_INTERNAL_H
 
+#include <linux/fs.h>
 #include <linux/mm.h>
 
 void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
@@ -21,6 +22,20 @@ static inline void set_page_count(struct page *page, int v)
 	atomic_set(&page->_count, v);
 }
 
+extern int __do_page_cache_readahead(struct address_space *mapping,
+		struct file *filp, pgoff_t offset, unsigned long nr_to_read,
+		unsigned long lookahead_size);
+
+/*
+ * Submit IO for the read-ahead request in file_ra_state.
+ */
+static inline unsigned long ra_submit(struct file_ra_state *ra,
+		struct address_space *mapping, struct file *filp)
+{
+	return __do_page_cache_readahead(mapping, filp,
+					ra->start, ra->size, ra->async_size);
+}
+
 /*
  * Turn a non-refcounted page (->_count == 0) into refcounted with
  * a count of one.
diff --git a/mm/readahead.c b/mm/readahead.c
index 29c5e1af5a0c..0ca36a7770b1 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -8,9 +8,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/fs.h>
 #include <linux/gfp.h>
-#include <linux/mm.h>
 #include <linux/export.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
@@ -20,6 +18,8 @@
 #include <linux/syscalls.h>
 #include <linux/file.h>
 
+#include "internal.h"
+
 /*
  * Initialise a struct file's readahead state.  Assumes that the caller has
  * memset *ra to zero.
@@ -149,8 +149,7 @@ out:
  *
  * Returns the number of pages requested, or the maximum amount of I/O allowed.
  */
-static int
-__do_page_cache_readahead(struct address_space *mapping, struct file *filp,
+int __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
 			pgoff_t offset, unsigned long nr_to_read,
 			unsigned long lookahead_size)
 {
@@ -243,20 +242,6 @@ unsigned long max_sane_readahead(unsigned long nr)
 	return min(nr, MAX_READAHEAD);
 }
 
-/*
- * Submit IO for the read-ahead request in file_ra_state.
- */
-unsigned long ra_submit(struct file_ra_state *ra,
-		       struct address_space *mapping, struct file *filp)
-{
-	int actual;
-
-	actual = __do_page_cache_readahead(mapping, filp,
-					ra->start, ra->size, ra->async_size);
-
-	return actual;
-}
-
 /*
  * Set the initial window size, round to next power of 2 and square
  * for small size, x 4 for medium, and x 2 for large
-- 
cgit v1.2.3


From 834a964a098e7726fc296d7cd8f65ed3eeedd412 Mon Sep 17 00:00:00 2001
From: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Date: Mon, 7 Apr 2014 15:37:57 -0700
Subject: numa: use LAST_CPUPID_SHIFT to calculate LAST_CPUPID_MASK

LAST_CPUPID_MASK is calculated using LAST_CPUPID_WIDTH.  However
LAST_CPUPID_WIDTH itself can be 0.  (when LAST_CPUPID_NOT_IN_PAGE_FLAGS is
set).  In such a case LAST_CPUPID_MASK turns out to be 0.

But with recent commit 1ae71d0319: (mm: numa: bugfix for
LAST_CPUPID_NOT_IN_PAGE_FLAGS) if LAST_CPUPID_MASK is 0,
page_cpupid_xchg_last() and page_cpupid_reset_last() causes
page->_last_cpupid to be set to 0.

This causes performance regression. Its almost as if numa_balancing is
off.

Fix LAST_CPUPID_MASK by using LAST_CPUPID_SHIFT instead of
LAST_CPUPID_WIDTH.

Some performance numbers and perf stats with and without the fix.

(3.14-rc6)
----------
numa01

 Performance counter stats for '/usr/bin/time -f %e %S %U %c %w -o start_bench.out -a ./numa01':

         12,27,462 cs                                                           [100.00%]
          2,41,957 migrations                                                   [100.00%]
       1,68,01,713 faults                                                       [100.00%]
    7,99,35,29,041 cache-misses
            98,808 migrate:mm_migrate_pages                                     [100.00%]

    1407.690148814 seconds time elapsed

numa02

 Performance counter stats for '/usr/bin/time -f %e %S %U %c %w -o start_bench.out -a ./numa02':

            63,065 cs                                                           [100.00%]
            14,364 migrations                                                   [100.00%]
          2,08,118 faults                                                       [100.00%]
      25,32,59,404 cache-misses
                12 migrate:mm_migrate_pages                                     [100.00%]

      63.840827219 seconds time elapsed

(3.14-rc6 with fix)
-------------------
numa01

 Performance counter stats for '/usr/bin/time -f %e %S %U %c %w -o start_bench.out -a ./numa01':

          9,68,911 cs                                                           [100.00%]
          1,01,414 migrations                                                   [100.00%]
         88,38,697 faults                                                       [100.00%]
    4,42,92,51,042 cache-misses
          4,25,060 migrate:mm_migrate_pages                                     [100.00%]

     685.965331189 seconds time elapsed

numa02

 Performance counter stats for '/usr/bin/time -f %e %S %U %c %w -o start_bench.out -a ./numa02':

            17,543 cs                                                           [100.00%]
             2,962 migrations                                                   [100.00%]
          1,17,843 faults                                                       [100.00%]
      11,80,61,644 cache-misses
            12,358 migrate:mm_migrate_pages                                     [100.00%]

      20.380132343 seconds time elapsed

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Liu Ping Fan <pingfank@linux.vnet.ibm.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 6edcea720ddd..abc848412e3c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -695,7 +695,7 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address,
 #define ZONES_MASK		((1UL << ZONES_WIDTH) - 1)
 #define NODES_MASK		((1UL << NODES_WIDTH) - 1)
 #define SECTIONS_MASK		((1UL << SECTIONS_WIDTH) - 1)
-#define LAST_CPUPID_MASK	((1UL << LAST_CPUPID_WIDTH) - 1)
+#define LAST_CPUPID_MASK	((1UL << LAST_CPUPID_SHIFT) - 1)
 #define ZONEID_MASK		((1UL << ZONEID_SHIFT) - 1)
 
 static inline enum zone_type page_zonenum(const struct page *page)
-- 
cgit v1.2.3


From 23aebe1691a3d98a79676db6c0fd813e16478804 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Mon, 7 Apr 2014 15:38:39 -0700
Subject: exec: kill bprm->tcomm[], simplify the "basename" logic

Starting from commit c4ad8f98bef7 ("execve: use 'struct filename *' for
executable name passing") bprm->filename can not go away after
flush_old_exec(), so we do not need to save the binary name in
bprm->tcomm[] added by 96e02d158678 ("exec: fix use-after-free bug in
setup_new_exec()").

And there was never need for filename_to_taskname-like code, we can
simply do set_task_comm(kbasename(filename).

This patch has to change set_task_comm() and trace_task_rename() to
accept "const char *", but I think this change is also good.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/exec.c                   | 21 ++-------------------
 include/linux/binfmts.h     |  1 -
 include/linux/sched.h       |  2 +-
 include/trace/events/task.h |  2 +-
 4 files changed, 4 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/fs/exec.c b/fs/exec.c
index b60ccf969a8b..9e81c630dfa7 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1046,7 +1046,7 @@ EXPORT_SYMBOL_GPL(get_task_comm);
  * so that a new one can be started
  */
 
-void set_task_comm(struct task_struct *tsk, char *buf)
+void set_task_comm(struct task_struct *tsk, const char *buf)
 {
 	task_lock(tsk);
 	trace_task_rename(tsk, buf);
@@ -1055,21 +1055,6 @@ void set_task_comm(struct task_struct *tsk, char *buf)
 	perf_event_comm(tsk);
 }
 
-static void filename_to_taskname(char *tcomm, const char *fn, unsigned int len)
-{
-	int i, ch;
-
-	/* Copies the binary name from after last slash */
-	for (i = 0; (ch = *(fn++)) != '\0';) {
-		if (ch == '/')
-			i = 0; /* overwrite what we wrote */
-		else
-			if (i < len - 1)
-				tcomm[i++] = ch;
-	}
-	tcomm[i] = '\0';
-}
-
 int flush_old_exec(struct linux_binprm * bprm)
 {
 	int retval;
@@ -1083,8 +1068,6 @@ int flush_old_exec(struct linux_binprm * bprm)
 		goto out;
 
 	set_mm_exe_file(bprm->mm, bprm->file);
-
-	filename_to_taskname(bprm->tcomm, bprm->filename, sizeof(bprm->tcomm));
 	/*
 	 * Release all of the old mmap stuff
 	 */
@@ -1127,7 +1110,7 @@ void setup_new_exec(struct linux_binprm * bprm)
 	else
 		set_dumpable(current->mm, suid_dumpable);
 
-	set_task_comm(current, bprm->tcomm);
+	set_task_comm(current, kbasename(bprm->filename));
 
 	/* Set the new mm task size. We have to do that late because it may
 	 * depend on TIF_32BIT which is only updated in flush_thread() on
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index b4a745d7d9a9..61f29e5ea840 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -44,7 +44,6 @@ struct linux_binprm {
 	unsigned interp_flags;
 	unsigned interp_data;
 	unsigned long loader, exec;
-	char tcomm[TASK_COMM_LEN];
 };
 
 #define BINPRM_FLAGS_ENFORCE_NONDUMP_BIT 0
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6c70645eb3b6..f8497059f88c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2357,7 +2357,7 @@ extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, i
 struct task_struct *fork_idle(int);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
 
-extern void set_task_comm(struct task_struct *tsk, char *from);
+extern void set_task_comm(struct task_struct *tsk, const char *from);
 extern char *get_task_comm(char *to, struct task_struct *tsk);
 
 #ifdef CONFIG_SMP
diff --git a/include/trace/events/task.h b/include/trace/events/task.h
index 102a646e1996..dee3bb1d5a6b 100644
--- a/include/trace/events/task.h
+++ b/include/trace/events/task.h
@@ -32,7 +32,7 @@ TRACE_EVENT(task_newtask,
 
 TRACE_EVENT(task_rename,
 
-	TP_PROTO(struct task_struct *task, char *comm),
+	TP_PROTO(struct task_struct *task, const char *comm),
 
 	TP_ARGS(task, comm),
 
-- 
cgit v1.2.3


From abd50b39e783e1b6c75c7534c37f1eb2d94a89cd Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Mon, 7 Apr 2014 15:38:42 -0700
Subject: wait: introduce EXIT_TRACE to avoid the racy EXIT_DEAD->EXIT_ZOMBIE
 transition

wait_task_zombie() first does EXIT_ZOMBIE->EXIT_DEAD transition and
drops tasklist_lock.  If this task is not the natural child and it is
traced, we change its state back to EXIT_ZOMBIE for ->real_parent.

The last transition is racy, this is even documented in 50b8d257486a
"ptrace: partially fix the do_wait(WEXITED) vs EXIT_DEAD->EXIT_ZOMBIE
race".  wait_consider_task() tries to detect this transition and clear
->notask_error but we can't rely on ptrace_reparented(), debugger can
exit and do ptrace_unlink() before its sub-thread sets EXIT_ZOMBIE.

And there is another problem which were missed before: this transition
can also race with reparent_leader() which doesn't reset >exit_signal if
EXIT_DEAD, assuming that this task must be reaped by someone else.  So
the tracee can be re-parented with ->exit_signal != SIGCHLD, and if
/sbin/init doesn't use __WALL it becomes unreapable.  This was fixed by
the previous commit, but it was the temporary hack.

1. Add the new exit_state, EXIT_TRACE. It means that the task is the
   traced zombie, debugger is going to detach and notify its natural
   parent.

   This new state is actually EXIT_ZOMBIE | EXIT_DEAD. This way we
   can avoid the changes in proc/kgdb code, get_task_state() still
   reports "X (dead)" in this case.

   Note: with or without this change userspace can see Z -> X -> Z
   transition. Not really bad, but probably makes sense to fix.

2. Change wait_task_zombie() to use EXIT_TRACE instead of EXIT_DEAD
   if we need to notify the ->real_parent.

3. Revert the previous hack in reparent_leader(), now that EXIT_DEAD
   is always the final state we can safely ignore such a task.

4. Change wait_consider_task() to check EXIT_TRACE separately and kill
   the racy and no longer needed ptrace_reparented() case.

   If ptrace == T an EXIT_TRACE thread should be simply ignored, the
   owner of this state is going to ptrace_unlink() this task. We can
   pretend that it was already removed from ->ptraced list.

   Otherwise we should skip this thread too but clear ->notask_error,
   we must be the natural parent and debugger is going to untrace and
   notify us. IOW, this doesn't differ from "EXIT_ZOMBIE && p->ptrace"
   even if the task was already untraced.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reported-by: Jan Kratochvil <jan.kratochvil@redhat.com>
Reported-by: Michal Schmidt <mschmidt@redhat.com>
Tested-by: Michal Schmidt <mschmidt@redhat.com>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Lennart Poettering <lpoetter@redhat.com>
Cc: Roland McGrath <roland@hack.frob.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/sched.h |  1 +
 kernel/exit.c         | 50 +++++++++++++++++++++-----------------------------
 2 files changed, 22 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index f8497059f88c..7781de5e5e7b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -212,6 +212,7 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
 /* in tsk->exit_state */
 #define EXIT_ZOMBIE		16
 #define EXIT_DEAD		32
+#define EXIT_TRACE		(EXIT_ZOMBIE | EXIT_DEAD)
 /* in tsk->state again */
 #define TASK_DEAD		64
 #define TASK_WAKEKILL		128
diff --git a/kernel/exit.c b/kernel/exit.c
index e354cbb13a9b..022a0ff17318 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -560,6 +560,9 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 				struct list_head *dead)
 {
 	list_move_tail(&p->sibling, &p->real_parent->children);
+
+	if (p->exit_state == EXIT_DEAD)
+		return;
 	/*
 	 * If this is a threaded reparent there is no need to
 	 * notify anyone anything has happened.
@@ -567,19 +570,9 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 	if (same_thread_group(p->real_parent, father))
 		return;
 
-	/*
-	 * We don't want people slaying init.
-	 *
-	 * Note: we do this even if it is EXIT_DEAD, wait_task_zombie()
-	 * can change ->exit_state to EXIT_ZOMBIE. If this is the final
-	 * state, do_notify_parent() was already called and ->exit_signal
-	 * doesn't matter.
-	 */
+	/* We don't want people slaying init. */
 	p->exit_signal = SIGCHLD;
 
-	if (p->exit_state == EXIT_DEAD)
-		return;
-
 	/* If it has exited notify the new parent about this child's death. */
 	if (!p->ptrace &&
 	    p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {
@@ -1043,17 +1036,13 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		return wait_noreap_copyout(wo, p, pid, uid, why, status);
 	}
 
+	traced = ptrace_reparented(p);
 	/*
-	 * Try to move the task's state to DEAD
-	 * only one thread is allowed to do this:
+	 * Move the task's state to DEAD/TRACE, only one thread can do this.
 	 */
-	state = xchg(&p->exit_state, EXIT_DEAD);
-	if (state != EXIT_ZOMBIE) {
-		BUG_ON(state != EXIT_DEAD);
+	state = traced ? EXIT_TRACE : EXIT_DEAD;
+	if (cmpxchg(&p->exit_state, EXIT_ZOMBIE, state) != EXIT_ZOMBIE)
 		return 0;
-	}
-
-	traced = ptrace_reparented(p);
 	/*
 	 * It can be ptraced but not reparented, check
 	 * thread_group_leader() to filter out sub-threads.
@@ -1114,7 +1103,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 
 	/*
 	 * Now we are sure this task is interesting, and no other
-	 * thread can reap it because we set its state to EXIT_DEAD.
+	 * thread can reap it because we its state == DEAD/TRACE.
 	 */
 	read_unlock(&tasklist_lock);
 
@@ -1159,14 +1148,14 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		 * If this is not a sub-thread, notify the parent.
 		 * If parent wants a zombie, don't release it now.
 		 */
+		state = EXIT_DEAD;
 		if (thread_group_leader(p) &&
-		    !do_notify_parent(p, p->exit_signal)) {
-			p->exit_state = EXIT_ZOMBIE;
-			p = NULL;
-		}
+		    !do_notify_parent(p, p->exit_signal))
+			state = EXIT_ZOMBIE;
+		p->exit_state = state;
 		write_unlock_irq(&tasklist_lock);
 	}
-	if (p != NULL)
+	if (state == EXIT_DEAD)
 		release_task(p);
 
 	return retval;
@@ -1362,12 +1351,15 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
 	}
 
 	/* dead body doesn't have much to contribute */
-	if (unlikely(p->exit_state == EXIT_DEAD)) {
+	if (unlikely(p->exit_state == EXIT_DEAD))
+		return 0;
+
+	if (unlikely(p->exit_state == EXIT_TRACE)) {
 		/*
-		 * But do not ignore this task until the tracer does
-		 * wait_task_zombie()->do_notify_parent().
+		 * ptrace == 0 means we are the natural parent. In this case
+		 * we should clear notask_error, debugger will notify us.
 		 */
-		if (likely(!ptrace) && unlikely(ptrace_reparented(p)))
+		if (likely(!ptrace))
 			wo->notask_error = 0;
 		return 0;
 	}
-- 
cgit v1.2.3


From ad86622b478eaafdc25b74237df82b10fce6326d Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Mon, 7 Apr 2014 15:38:46 -0700
Subject: wait: swap EXIT_ZOMBIE and EXIT_DEAD to hide EXIT_TRACE from
 user-space

get_task_state() uses the most significant bit to report the state to
user-space, this means that EXIT_ZOMBIE->EXIT_TRACE->EXIT_DEAD transition
can be noticed via /proc as Z -> X -> Z change.  Note that this was
possible even before EXIT_TRACE was introduced.

This is not really bad but imho it make sense to hide EXIT_TRACE from
user-space completely.  So the patch simply swaps EXIT_ZOMBIE and
EXIT_DEAD, this way EXIT_TRACE will be seen as EXIT_ZOMBIE by user-space.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Jan Kratochvil <jan.kratochvil@redhat.com>
Cc: Michal Schmidt <mschmidt@redhat.com>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Lennart Poettering <lpoetter@redhat.com>
Cc: Roland McGrath <roland@hack.frob.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/array.c       | 4 ++--
 include/linux/sched.h | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/fs/proc/array.c b/fs/proc/array.c
index 656e401794de..64db2bceac59 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -138,8 +138,8 @@ static const char * const task_state_array[] = {
 	"D (disk sleep)",	/*   2 */
 	"T (stopped)",		/*   4 */
 	"t (tracing stop)",	/*   8 */
-	"Z (zombie)",		/*  16 */
-	"X (dead)",		/*  32 */
+	"X (dead)",		/*  16 */
+	"Z (zombie)",		/*  32 */
 };
 
 static inline const char *get_task_state(struct task_struct *tsk)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 7781de5e5e7b..075b3056c0c0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -210,8 +210,8 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
 #define __TASK_STOPPED		4
 #define __TASK_TRACED		8
 /* in tsk->exit_state */
-#define EXIT_ZOMBIE		16
-#define EXIT_DEAD		32
+#define EXIT_DEAD		16
+#define EXIT_ZOMBIE		32
 #define EXIT_TRACE		(EXIT_ZOMBIE | EXIT_DEAD)
 /* in tsk->state again */
 #define TASK_DEAD		64
-- 
cgit v1.2.3


From 82e0703b6ca8b549952c1e4f04746f27eaec012d Mon Sep 17 00:00:00 2001
From: Rashika Kheria <rashika.kheria@gmail.com>
Date: Mon, 7 Apr 2014 15:38:50 -0700
Subject: include/linux/crash_dump.h: add vmcore_cleanup() prototype

Eliminate the following warning in proc/vmcore.c:

  fs/proc/vmcore.c:1088:6: warning: no previous prototype for `vmcore_cleanup' [-Wmissing-prototypes]

[akpm@linux-foundation.org: clean up powerpc, remove unneeded EXPORT_SYMBOL]
Signed-off-by: Rashika Kheria <rashika.kheria@gmail.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/powerpc/include/asm/fadump.h | 1 -
 fs/proc/vmcore.c                  | 1 -
 include/linux/crash_dump.h        | 1 +
 3 files changed, 1 insertion(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index 88dbf9659185..a6774560afe3 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -210,7 +210,6 @@ extern int is_fadump_active(void);
 extern void crash_fadump(struct pt_regs *, const char *);
 extern void fadump_cleanup(void);
 
-extern void vmcore_cleanup(void);
 #else	/* CONFIG_FA_DUMP */
 static inline int is_fadump_active(void) { return 0; }
 static inline void crash_fadump(struct pt_regs *regs, const char *str) { }
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 88d4585b30f1..ab852715916d 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -1118,4 +1118,3 @@ void vmcore_cleanup(void)
 	}
 	free_elfcorebuf();
 }
-EXPORT_SYMBOL_GPL(vmcore_cleanup);
diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
index 7032518f8542..72ab536ad3de 100644
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -25,6 +25,7 @@ extern int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma,
 
 extern ssize_t copy_oldmem_page(unsigned long, char *, size_t,
 						unsigned long, int);
+void vmcore_cleanup(void);
 
 /* Architecture code defines this if there are other possible ELF
  * machine types, e.g. on bi-arch capable hardware. */
-- 
cgit v1.2.3


From 90ae3ae539246984d36e43b0e23554bca941476f Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Mon, 7 Apr 2014 15:38:52 -0700
Subject: idr: remove dead code

Remove no longer used deprecated code, and make local functions
static.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Jean Delvare <jdelvare@suse.de>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: Jeff Layton <jlayton@redhat.com>
Cc: Philipp Reisner <philipp.reisner@linbit.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: George Spelvin <linux@horizon.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/idr.h | 63 -----------------------------------------------------
 lib/idr.c           | 20 ++---------------
 2 files changed, 2 insertions(+), 81 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/idr.h b/include/linux/idr.h
index f669585c4fc5..6af3400b9b2f 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -132,69 +132,6 @@ static inline void *idr_find(struct idr *idr, int id)
 #define idr_for_each_entry(idp, entry, id)			\
 	for (id = 0; ((entry) = idr_get_next(idp, &(id))) != NULL; ++id)
 
-/*
- * Don't use the following functions.  These exist only to suppress
- * deprecated warnings on EXPORT_SYMBOL()s.
- */
-int __idr_pre_get(struct idr *idp, gfp_t gfp_mask);
-int __idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id);
-void __idr_remove_all(struct idr *idp);
-
-/**
- * idr_pre_get - reserve resources for idr allocation
- * @idp:	idr handle
- * @gfp_mask:	memory allocation flags
- *
- * Part of old alloc interface.  This is going away.  Use
- * idr_preload[_end]() and idr_alloc() instead.
- */
-static inline int __deprecated idr_pre_get(struct idr *idp, gfp_t gfp_mask)
-{
-	return __idr_pre_get(idp, gfp_mask);
-}
-
-/**
- * idr_get_new_above - allocate new idr entry above or equal to a start id
- * @idp: idr handle
- * @ptr: pointer you want associated with the id
- * @starting_id: id to start search at
- * @id: pointer to the allocated handle
- *
- * Part of old alloc interface.  This is going away.  Use
- * idr_preload[_end]() and idr_alloc() instead.
- */
-static inline int __deprecated idr_get_new_above(struct idr *idp, void *ptr,
-						 int starting_id, int *id)
-{
-	return __idr_get_new_above(idp, ptr, starting_id, id);
-}
-
-/**
- * idr_get_new - allocate new idr entry
- * @idp: idr handle
- * @ptr: pointer you want associated with the id
- * @id: pointer to the allocated handle
- *
- * Part of old alloc interface.  This is going away.  Use
- * idr_preload[_end]() and idr_alloc() instead.
- */
-static inline int __deprecated idr_get_new(struct idr *idp, void *ptr, int *id)
-{
-	return __idr_get_new_above(idp, ptr, 0, id);
-}
-
-/**
- * idr_remove_all - remove all ids from the given idr tree
- * @idp: idr handle
- *
- * If you're trying to destroy @idp, calling idr_destroy() is enough.
- * This is going away.  Don't use.
- */
-static inline void __deprecated idr_remove_all(struct idr *idp)
-{
-	__idr_remove_all(idp);
-}
-
 /*
  * IDA - IDR based id allocator, use when translation from id to
  * pointer isn't necessary.
diff --git a/lib/idr.c b/lib/idr.c
index 1ba4956bfbff..ba2df393c3b0 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -196,7 +196,7 @@ static void idr_mark_full(struct idr_layer **pa, int id)
 	}
 }
 
-int __idr_pre_get(struct idr *idp, gfp_t gfp_mask)
+static int __idr_pre_get(struct idr *idp, gfp_t gfp_mask)
 {
 	while (idp->id_free_cnt < MAX_IDR_FREE) {
 		struct idr_layer *new;
@@ -207,7 +207,6 @@ int __idr_pre_get(struct idr *idp, gfp_t gfp_mask)
 	}
 	return 1;
 }
-EXPORT_SYMBOL(__idr_pre_get);
 
 /**
  * sub_alloc - try to allocate an id without growing the tree depth
@@ -374,20 +373,6 @@ static void idr_fill_slot(struct idr *idr, void *ptr, int id,
 	idr_mark_full(pa, id);
 }
 
-int __idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id)
-{
-	struct idr_layer *pa[MAX_IDR_LEVEL + 1];
-	int rv;
-
-	rv = idr_get_empty_slot(idp, starting_id, pa, 0, idp);
-	if (rv < 0)
-		return rv == -ENOMEM ? -EAGAIN : rv;
-
-	idr_fill_slot(idp, ptr, rv, pa);
-	*id = rv;
-	return 0;
-}
-EXPORT_SYMBOL(__idr_get_new_above);
 
 /**
  * idr_preload - preload for idr_alloc()
@@ -607,7 +592,7 @@ void idr_remove(struct idr *idp, int id)
 }
 EXPORT_SYMBOL(idr_remove);
 
-void __idr_remove_all(struct idr *idp)
+static void __idr_remove_all(struct idr *idp)
 {
 	int n, id, max;
 	int bt_mask;
@@ -640,7 +625,6 @@ void __idr_remove_all(struct idr *idp)
 	}
 	idp->layers = 0;
 }
-EXPORT_SYMBOL(__idr_remove_all);
 
 /**
  * idr_destroy - release all cached layers within an idr tree
-- 
cgit v1.2.3


From 2aaf308b95b24649a6dcfed89cd956e972089b2a Mon Sep 17 00:00:00 2001
From: Alexandre Bounine <alexandre.bounine@idt.com>
Date: Mon, 7 Apr 2014 15:38:56 -0700
Subject: rapidio: rework device hierarchy and introduce mport class of devices

This patch removes an artificial RapidIO bus root device and establishes
actual device hierarchy by providing reference to real parent devices.
It also introduces device class for RapidIO controller devices (on-chip
or an eternal bridge, known as "mport").

Existing implementation was sufficient for SoC-based platforms that have
a single RapidIO controller.  With introduction of devices using
multiple RapidIO controllers and PCIe-to-RapidIO bridges the old scheme
is very limiting or does not work at all.  The implemented changes allow
to properly reference platform's local RapidIO mport devices and provide
device details needed for upper layers.

This change to RapidIO device hierarchy does not break any known
existing kernel or user space interfaces.

Signed-off-by: Alexandre Bounine <alexandre.bounine@idt.com>
Cc: Matt Porter <mporter@kernel.crashing.org>
Cc: Li Yang <leoli@freescale.com>
Cc: Kumar Gala <galak@kernel.crashing.org>
Cc: Andre van Herk <andre.van.herk@prodrive-technologies.com>
Cc: Stef van Os <stef.van.os@prodrive-technologies.com>
Cc: Jerry Jacobs <jerry.jacobs@prodrive-technologies.com>
Cc: Arno Tiemersma <arno.tiemersma@prodrive-technologies.com>
Cc: Rob Landley <rob@landley.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/rapidio/sysfs.txt  | 66 +++++++++++++++++++++++++++++++++++-----
 arch/powerpc/sysdev/fsl_rio.c    |  1 +
 drivers/net/rionet.c             |  1 +
 drivers/rapidio/devices/tsi721.c |  1 +
 drivers/rapidio/rio-driver.c     | 22 +++++++++-----
 drivers/rapidio/rio-scan.c       |  1 +
 drivers/rapidio/rio-sysfs.c      | 40 ++++++++++++++++++++++++
 drivers/rapidio/rio.c            | 11 +++++++
 drivers/rapidio/rio.h            |  1 +
 include/linux/rio.h              |  5 ++-
 10 files changed, 133 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/rapidio/sysfs.txt b/Documentation/rapidio/sysfs.txt
index 271438c0617f..47ce9a5336e1 100644
--- a/Documentation/rapidio/sysfs.txt
+++ b/Documentation/rapidio/sysfs.txt
@@ -2,8 +2,8 @@
 
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-1. Device Subdirectories
-------------------------
+1. RapidIO Device Subdirectories
+--------------------------------
 
 For each RapidIO device, the RapidIO subsystem creates files in an individual
 subdirectory with the following name, /sys/bus/rapidio/devices/<device_name>.
@@ -25,8 +25,8 @@ seen by the enumerating host (destID = 1):
 NOTE: An enumerating or discovering endpoint does not create a sysfs entry for
 itself, this is why an endpoint with destID=1 is not shown in the list.
 
-2. Attributes Common for All Devices
-------------------------------------
+2. Attributes Common for All RapidIO Devices
+--------------------------------------------
 
 Each device subdirectory contains the following informational read-only files:
 
@@ -52,16 +52,16 @@ This attribute is similar in behavior to the "config" attribute of PCI devices
 and provides an access to the RapidIO device registers using standard file read
 and write operations.
 
-3. Endpoint Device Attributes
------------------------------
+3. RapidIO Endpoint Device Attributes
+-------------------------------------
 
 Currently Linux RapidIO subsystem does not create any endpoint specific sysfs
 attributes. It is possible that RapidIO master port drivers and endpoint device
 drivers will add their device-specific sysfs attributes but such attributes are
 outside the scope of this document.
 
-4. Switch Device Attributes
----------------------------
+4. RapidIO Switch Device Attributes
+-----------------------------------
 
 RapidIO switches have additional attributes in sysfs. RapidIO subsystem supports
 common and device-specific sysfs attributes for switches. Because switches are
@@ -106,3 +106,53 @@ attribute:
 	 for that controller always will be 0.
 	 To initiate RapidIO enumeration/discovery on all available mports
 	 a user must write '-1' (or RIO_MPORT_ANY) into this attribute file.
+
+
+6. RapidIO Bus Controllers/Ports
+--------------------------------
+
+On-chip RapidIO controllers and PCIe-to-RapidIO bridges (referenced as
+"Master Port" or "mport") are presented in sysfs as the special class of
+devices: "rapidio_port".
+
+The /sys/class/rapidio_port subdirectory contains individual subdirectories
+named as "rapidioN" where N = mport ID registered with RapidIO subsystem.
+
+NOTE: An mport ID is not a RapidIO destination ID assigned to a given local
+mport device.
+
+Each mport device subdirectory in addition to standard entries contains the
+following device-specific attributes:
+
+   port_destid - reports RapidIO destination ID assigned to the given RapidIO
+                 mport device. If value 0xFFFFFFFF is returned this means that
+                 no valid destination ID have been assigned to the mport (yet).
+                 Normally, before enumeration/discovery have been executed only
+                 fabric enumerating mports have a valid destination ID assigned
+                 to them using "hdid=..." rapidio module parameter.
+      sys_size - reports RapidIO common transport system size:
+                   0 = small (8-bit destination ID, max. 256 devices),
+                   1 = large (16-bit destination ID, max. 65536 devices).
+
+After enumeration or discovery was performed for a given mport device,
+the corresponding subdirectory will also contain subdirectories for each
+child RapidIO device connected to the mport. Naming conventions for RapidIO
+devices are described in Section 1 above.
+
+The example below shows mport device subdirectory with several child RapidIO
+devices attached to it.
+
+[rio@rapidio ~]$ ls /sys/class/rapidio_port/rapidio0/ -l
+total 0
+drwxr-xr-x 3 root root    0 Feb 11 15:10 00:e:0001
+drwxr-xr-x 3 root root    0 Feb 11 15:10 00:e:0004
+drwxr-xr-x 3 root root    0 Feb 11 15:10 00:e:0007
+drwxr-xr-x 3 root root    0 Feb 11 15:10 00:s:0002
+drwxr-xr-x 3 root root    0 Feb 11 15:10 00:s:0003
+drwxr-xr-x 3 root root    0 Feb 11 15:10 00:s:0005
+lrwxrwxrwx 1 root root    0 Feb 11 15:11 device -> ../../../0000:01:00.0
+-r--r--r-- 1 root root 4096 Feb 11 15:11 port_destid
+drwxr-xr-x 2 root root    0 Feb 11 15:11 power
+lrwxrwxrwx 1 root root    0 Feb 11 15:04 subsystem -> ../../../../../../class/rapidio_port
+-r--r--r-- 1 root root 4096 Feb 11 15:11 sys_size
+-rw-r--r-- 1 root root 4096 Feb 11 15:04 uevent
diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c
index 95dd892e9904..cf2b0840a672 100644
--- a/arch/powerpc/sysdev/fsl_rio.c
+++ b/arch/powerpc/sysdev/fsl_rio.c
@@ -531,6 +531,7 @@ int fsl_rio_setup(struct platform_device *dev)
 		sprintf(port->name, "RIO mport %d", i);
 
 		priv->dev = &dev->dev;
+		port->dev.parent = &dev->dev;
 		port->ops = ops;
 		port->priv = priv;
 		port->phys_efptr = 0x100;
diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c
index 6d1f6ed3113f..a8497183ff8b 100644
--- a/drivers/net/rionet.c
+++ b/drivers/net/rionet.c
@@ -493,6 +493,7 @@ static int rionet_setup_netdev(struct rio_mport *mport, struct net_device *ndev)
 	ndev->netdev_ops = &rionet_netdev_ops;
 	ndev->mtu = RIO_MAX_MSG_SIZE - 14;
 	ndev->features = NETIF_F_LLTX;
+	SET_NETDEV_DEV(ndev, &mport->dev);
 	SET_ETHTOOL_OPS(ndev, &rionet_ethtool_ops);
 
 	spin_lock_init(&rnet->lock);
diff --git a/drivers/rapidio/devices/tsi721.c b/drivers/rapidio/devices/tsi721.c
index ff7cbf2d28e3..1753dc693c15 100644
--- a/drivers/rapidio/devices/tsi721.c
+++ b/drivers/rapidio/devices/tsi721.c
@@ -2256,6 +2256,7 @@ static int tsi721_setup_mport(struct tsi721_device *priv)
 	mport->phy_type = RIO_PHY_SERIAL;
 	mport->priv = (void *)priv;
 	mport->phys_efptr = 0x100;
+	mport->dev.parent = &pdev->dev;
 	priv->mport = mport;
 
 	INIT_LIST_HEAD(&mport->dbells);
diff --git a/drivers/rapidio/rio-driver.c b/drivers/rapidio/rio-driver.c
index c9ae692d3451..f301f059bb85 100644
--- a/drivers/rapidio/rio-driver.c
+++ b/drivers/rapidio/rio-driver.c
@@ -167,7 +167,6 @@ void rio_unregister_driver(struct rio_driver *rdrv)
 void rio_attach_device(struct rio_dev *rdev)
 {
 	rdev->dev.bus = &rio_bus_type;
-	rdev->dev.parent = &rio_bus;
 }
 EXPORT_SYMBOL_GPL(rio_attach_device);
 
@@ -216,9 +215,12 @@ static int rio_uevent(struct device *dev, struct kobj_uevent_env *env)
 	return 0;
 }
 
-struct device rio_bus = {
-	.init_name = "rapidio",
+struct class rio_mport_class = {
+	.name		= "rapidio_port",
+	.owner		= THIS_MODULE,
+	.dev_groups	= rio_mport_groups,
 };
+EXPORT_SYMBOL_GPL(rio_mport_class);
 
 struct bus_type rio_bus_type = {
 	.name = "rapidio",
@@ -233,14 +235,20 @@ struct bus_type rio_bus_type = {
 /**
  *  rio_bus_init - Register the RapidIO bus with the device model
  *
- *  Registers the RIO bus device and RIO bus type with the Linux
+ *  Registers the RIO mport device class and RIO bus type with the Linux
  *  device model.
  */
 static int __init rio_bus_init(void)
 {
-	if (device_register(&rio_bus) < 0)
-		printk("RIO: failed to register RIO bus device\n");
-	return bus_register(&rio_bus_type);
+	int ret;
+
+	ret = class_register(&rio_mport_class);
+	if (!ret) {
+		ret = bus_register(&rio_bus_type);
+		if (ret)
+			class_unregister(&rio_mport_class);
+	}
+	return ret;
 }
 
 postcore_initcall(rio_bus_init);
diff --git a/drivers/rapidio/rio-scan.c b/drivers/rapidio/rio-scan.c
index d3a6539a77cc..47a1b2ea76c4 100644
--- a/drivers/rapidio/rio-scan.c
+++ b/drivers/rapidio/rio-scan.c
@@ -461,6 +461,7 @@ static struct rio_dev *rio_setup_device(struct rio_net *net,
 			     rdev->comp_tag & RIO_CTAG_UDEVID);
 	}
 
+	rdev->dev.parent = &port->dev;
 	rio_attach_device(rdev);
 
 	device_initialize(&rdev->dev);
diff --git a/drivers/rapidio/rio-sysfs.c b/drivers/rapidio/rio-sysfs.c
index e0221c6d0cc2..cdb005c0094d 100644
--- a/drivers/rapidio/rio-sysfs.c
+++ b/drivers/rapidio/rio-sysfs.c
@@ -341,3 +341,43 @@ const struct attribute_group *rio_bus_groups[] = {
 	&rio_bus_group,
 	NULL,
 };
+
+static ssize_t
+port_destid_show(struct device *dev, struct device_attribute *attr,
+		 char *buf)
+{
+	struct rio_mport *mport = to_rio_mport(dev);
+
+	if (mport)
+		return sprintf(buf, "0x%04x\n", mport->host_deviceid);
+	else
+		return -ENODEV;
+}
+static DEVICE_ATTR_RO(port_destid);
+
+static ssize_t sys_size_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
+{
+	struct rio_mport *mport = to_rio_mport(dev);
+
+	if (mport)
+		return sprintf(buf, "%u\n", mport->sys_size);
+	else
+		return -ENODEV;
+}
+static DEVICE_ATTR_RO(sys_size);
+
+static struct attribute *rio_mport_attrs[] = {
+	&dev_attr_port_destid.attr,
+	&dev_attr_sys_size.attr,
+	NULL,
+};
+
+static const struct attribute_group rio_mport_group = {
+	.attrs = rio_mport_attrs,
+};
+
+const struct attribute_group *rio_mport_groups[] = {
+	&rio_mport_group,
+	NULL,
+};
diff --git a/drivers/rapidio/rio.c b/drivers/rapidio/rio.c
index 2e8a20cac588..a54ba0494dd3 100644
--- a/drivers/rapidio/rio.c
+++ b/drivers/rapidio/rio.c
@@ -1884,6 +1884,7 @@ static int rio_get_hdid(int index)
 int rio_register_mport(struct rio_mport *port)
 {
 	struct rio_scan_node *scan = NULL;
+	int res = 0;
 
 	if (next_portid >= RIO_MAX_MPORTS) {
 		pr_err("RIO: reached specified max number of mports\n");
@@ -1894,6 +1895,16 @@ int rio_register_mport(struct rio_mport *port)
 	port->host_deviceid = rio_get_hdid(port->id);
 	port->nscan = NULL;
 
+	dev_set_name(&port->dev, "rapidio%d", port->id);
+	port->dev.class = &rio_mport_class;
+
+	res = device_register(&port->dev);
+	if (res)
+		dev_err(&port->dev, "RIO: mport%d registration failed ERR=%d\n",
+			port->id, res);
+	else
+		dev_dbg(&port->dev, "RIO: mport%d registered\n", port->id);
+
 	mutex_lock(&rio_mport_list_lock);
 	list_add_tail(&port->node, &rio_mports);
 
diff --git a/drivers/rapidio/rio.h b/drivers/rapidio/rio.h
index 5f99d22ad0b0..2d0550e08ea2 100644
--- a/drivers/rapidio/rio.h
+++ b/drivers/rapidio/rio.h
@@ -50,6 +50,7 @@ extern int rio_mport_scan(int mport_id);
 /* Structures internal to the RIO core code */
 extern const struct attribute_group *rio_dev_groups[];
 extern const struct attribute_group *rio_bus_groups[];
+extern const struct attribute_group *rio_mport_groups[];
 
 #define RIO_GET_DID(size, x)	(size ? (x & 0xffff) : ((x & 0x00ff0000) >> 16))
 #define RIO_SET_DID(size, x)	(size ? (x & 0xffff) : ((x & 0x000000ff) << 16))
diff --git a/include/linux/rio.h b/include/linux/rio.h
index b71d5738e683..6bda06f21930 100644
--- a/include/linux/rio.h
+++ b/include/linux/rio.h
@@ -83,7 +83,7 @@
 #define RIO_CTAG_UDEVID	0x0001ffff /* Unique device identifier */
 
 extern struct bus_type rio_bus_type;
-extern struct device rio_bus;
+extern struct class rio_mport_class;
 
 struct rio_mport;
 struct rio_dev;
@@ -201,6 +201,7 @@ struct rio_dev {
 #define rio_dev_f(n) list_entry(n, struct rio_dev, net_list)
 #define	to_rio_dev(n) container_of(n, struct rio_dev, dev)
 #define sw_to_rio_dev(n) container_of(n, struct rio_dev, rswitch[0])
+#define	to_rio_mport(n) container_of(n, struct rio_mport, dev)
 
 /**
  * struct rio_msg - RIO message event
@@ -248,6 +249,7 @@ enum rio_phy_type {
  * @phy_type: RapidIO phy type
  * @phys_efptr: RIO port extended features pointer
  * @name: Port name string
+ * @dev: device structure associated with an mport
  * @priv: Master port private data
  * @dma: DMA device associated with mport
  * @nscan: RapidIO network enumeration/discovery operations
@@ -272,6 +274,7 @@ struct rio_mport {
 	enum rio_phy_type phy_type;	/* RapidIO phy type */
 	u32 phys_efptr;
 	unsigned char name[RIO_MAX_MPORT_NAME];
+	struct device dev;
 	void *priv;		/* Master port private data */
 #ifdef CONFIG_RAPIDIO_DMA_ENGINE
 	struct dma_device	dma;
-- 
cgit v1.2.3


From ce816fa88cca083c47ab9000b2138a83043a78be Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Mon, 7 Apr 2014 15:39:19 -0700
Subject: Kconfig: rename HAS_IOPORT to HAS_IOPORT_MAP
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If the renamed symbol is defined lib/iomap.c implements ioport_map and
ioport_unmap and currently (nearly) all platforms define the port
accessor functions outb/inb and friend unconditionally.  So
HAS_IOPORT_MAP is the better name for this.

Consequently NO_IOPORT is renamed to NO_IOPORT_MAP.

The motivation for this change is to reintroduce a symbol HAS_IOPORT
that signals if outb/int et al are available.  I will address that at
least one merge window later though to keep surprises to a minimum and
catch new introductions of (HAS|NO)_IOPORT.

The changes in this commit were done using:

	$ git grep -l -E '(NO|HAS)_IOPORT' | xargs perl -p -i -e 's/\b((?:CONFIG_)?(?:NO|HAS)_IOPORT)\b/$1_MAP/'

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arc/Kconfig                    |  2 +-
 arch/arm/Kconfig                    | 12 ++++++------
 arch/arm/mach-picoxcell/Kconfig     |  2 +-
 arch/arm/mach-prima2/Kconfig        |  2 +-
 arch/arm/mach-s3c24xx/Kconfig       |  2 +-
 arch/arm/mach-shmobile/Kconfig      |  2 +-
 arch/arm/mach-vexpress/Kconfig      |  2 +-
 arch/arm/plat-samsung/Kconfig       |  4 ++--
 arch/arm64/Kconfig                  |  2 +-
 arch/cris/Kconfig                   |  2 +-
 arch/hexagon/Kconfig                |  2 +-
 arch/m32r/Kconfig                   |  2 +-
 arch/m68k/Kconfig                   |  2 +-
 arch/metag/Kconfig                  |  2 +-
 arch/mips/Kconfig                   |  4 ++--
 arch/openrisc/Kconfig               |  2 +-
 arch/s390/Kconfig                   |  2 +-
 arch/sh/Kconfig                     |  4 ++--
 arch/sh/boards/Kconfig              |  8 ++++----
 arch/sh/include/asm/io.h            |  4 ++--
 arch/sh/include/asm/io_trapped.h    |  2 +-
 arch/sh/include/asm/machvec.h       |  2 +-
 arch/sh/kernel/Makefile             |  2 +-
 arch/sh/kernel/io_trapped.c         |  4 ++--
 arch/tile/Kconfig                   |  2 +-
 arch/unicore32/Kconfig              |  2 +-
 arch/xtensa/Kconfig                 |  4 ++--
 arch/xtensa/configs/iss_defconfig   |  2 +-
 arch/xtensa/configs/s6105_defconfig |  2 +-
 drivers/char/tpm/Kconfig            |  2 +-
 drivers/i2c/busses/Kconfig          |  2 +-
 drivers/net/can/sja1000/Kconfig     |  2 +-
 drivers/net/ethernet/3com/Kconfig   |  2 +-
 include/asm-generic/io.h            |  4 ++--
 include/asm-generic/iomap.h         |  2 +-
 include/linux/io.h                  |  2 +-
 lib/Kconfig                         |  4 ++--
 lib/devres.c                        |  4 ++--
 lib/iomap.c                         |  4 ++--
 sound/isa/Kconfig                   |  2 +-
 sound/pci/Kconfig                   |  2 +-
 41 files changed, 59 insertions(+), 59 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 75de197a2fef..9596b0ab108d 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -57,7 +57,7 @@ config ARCH_FLATMEM_ENABLE
 config MMU
 	def_bool y
 
-config NO_IOPORT
+config NO_IOPORT_MAP
 	def_bool y
 
 config GENERIC_CALIBRATE_DELAY
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index d7a71e3ef55f..5db05f6a0412 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -126,7 +126,7 @@ config HAVE_TCM
 config HAVE_PROC_CPU
 	bool
 
-config NO_IOPORT
+config NO_IOPORT_MAP
 	bool
 
 config EISA
@@ -410,7 +410,7 @@ config ARCH_EBSA110
 	select ISA
 	select NEED_MACH_IO_H
 	select NEED_MACH_MEMORY_H
-	select NO_IOPORT
+	select NO_IOPORT_MAP
 	help
 	  This is an evaluation board for the StrongARM processor available
 	  from Digital. It has limited hardware on-board, including an
@@ -428,7 +428,7 @@ config ARCH_EFM32
 	select CPU_V7M
 	select GENERIC_CLOCKEVENTS
 	select NO_DMA
-	select NO_IOPORT
+	select NO_IOPORT_MAP
 	select SPARSE_IRQ
 	select USE_OF
 	help
@@ -677,7 +677,7 @@ config ARCH_SHMOBILE_LEGACY
 	select HAVE_SMP
 	select MIGHT_HAVE_CACHE_L2X0
 	select MULTI_IRQ_HANDLER
-	select NO_IOPORT
+	select NO_IOPORT_MAP
 	select PINCTRL
 	select PM_GENERIC_DOMAINS if PM
 	select SPARSE_IRQ
@@ -699,7 +699,7 @@ config ARCH_RPC
 	select ISA_DMA_API
 	select NEED_MACH_IO_H
 	select NEED_MACH_MEMORY_H
-	select NO_IOPORT
+	select NO_IOPORT_MAP
 	select VIRT_TO_BUS
 	help
 	  On the Acorn Risc-PC, Linux can support the internal IDE disk and
@@ -760,7 +760,7 @@ config ARCH_S3C64XX
 	select HAVE_S3C2410_I2C if I2C
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
 	select HAVE_TCM
-	select NO_IOPORT
+	select NO_IOPORT_MAP
 	select PLAT_SAMSUNG
 	select PM_GENERIC_DOMAINS if PM
 	select S3C_DEV_NAND
diff --git a/arch/arm/mach-picoxcell/Kconfig b/arch/arm/mach-picoxcell/Kconfig
index eca9eb1c5931..62240f69b4ee 100644
--- a/arch/arm/mach-picoxcell/Kconfig
+++ b/arch/arm/mach-picoxcell/Kconfig
@@ -4,4 +4,4 @@ config ARCH_PICOXCELL
 	select ARM_VIC
 	select DW_APB_TIMER_OF
 	select HAVE_TCM
-	select NO_IOPORT
+	select NO_IOPORT_MAP
diff --git a/arch/arm/mach-prima2/Kconfig b/arch/arm/mach-prima2/Kconfig
index 3e8189186a5b..e4e505f52ba0 100644
--- a/arch/arm/mach-prima2/Kconfig
+++ b/arch/arm/mach-prima2/Kconfig
@@ -3,7 +3,7 @@ config ARCH_SIRF
 	select ARCH_HAS_RESET_CONTROLLER
 	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_IRQ_CHIP
-	select NO_IOPORT
+	select NO_IOPORT_MAP
 	select PINCTRL
 	select PINCTRL_SIRF
 	help
diff --git a/arch/arm/mach-s3c24xx/Kconfig b/arch/arm/mach-s3c24xx/Kconfig
index ba1cc6246778..40cf50b9940c 100644
--- a/arch/arm/mach-s3c24xx/Kconfig
+++ b/arch/arm/mach-s3c24xx/Kconfig
@@ -12,7 +12,7 @@ if ARCH_S3C24XX
 config PLAT_S3C24XX
 	def_bool y
 	select ARCH_REQUIRE_GPIOLIB
-	select NO_IOPORT
+	select NO_IOPORT_MAP
 	select S3C_DEV_NAND
 	select IRQ_DOMAIN
 	help
diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig
index a182008e3aeb..0f92ba8e7884 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -10,7 +10,7 @@ config ARCH_SHMOBILE_MULTI
 	select ARM_GIC
 	select MIGHT_HAVE_PCI
 	select ARCH_DMA_ADDR_T_64BIT if ARM_LPAE
-	select NO_IOPORT
+	select NO_IOPORT_MAP
 	select PINCTRL
 	select ARCH_REQUIRE_GPIOLIB
 
diff --git a/arch/arm/mach-vexpress/Kconfig b/arch/arm/mach-vexpress/Kconfig
index 80b4be36f10a..657d52d0391f 100644
--- a/arch/arm/mach-vexpress/Kconfig
+++ b/arch/arm/mach-vexpress/Kconfig
@@ -10,7 +10,7 @@ config ARCH_VEXPRESS
 	select HAVE_ARM_TWD if SMP
 	select HAVE_PATA_PLATFORM
 	select ICST
-	select NO_IOPORT
+	select NO_IOPORT_MAP
 	select PLAT_VERSATILE
 	select PLAT_VERSATILE_CLCD
 	select POWER_RESET
diff --git a/arch/arm/plat-samsung/Kconfig b/arch/arm/plat-samsung/Kconfig
index b57e922f1614..243dfcb2ca0e 100644
--- a/arch/arm/plat-samsung/Kconfig
+++ b/arch/arm/plat-samsung/Kconfig
@@ -9,7 +9,7 @@ config PLAT_SAMSUNG
 	depends on PLAT_S3C24XX || ARCH_S3C64XX || PLAT_S5P || ARCH_EXYNOS
 	default y
 	select GENERIC_IRQ_CHIP
-	select NO_IOPORT
+	select NO_IOPORT_MAP
 	help
 	  Base platform code for all Samsung SoC based systems
 
@@ -19,7 +19,7 @@ config PLAT_S5P
 	default y
 	select ARCH_REQUIRE_GPIOLIB
 	select ARM_VIC
-	select NO_IOPORT
+	select NO_IOPORT_MAP
 	select PLAT_SAMSUNG
 	select S3C_GPIO_TRACK
 	select S5P_GPIO_DRVSTR
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 9711a5fd948d..8079a23e2701 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -66,7 +66,7 @@ config ARCH_PHYS_ADDR_T_64BIT
 config MMU
 	def_bool y
 
-config NO_IOPORT
+config NO_IOPORT_MAP
 	def_bool y
 
 config STACKTRACE_SUPPORT
diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig
index 7cb90a54b598..52731e221851 100644
--- a/arch/cris/Kconfig
+++ b/arch/cris/Kconfig
@@ -29,7 +29,7 @@ config GENERIC_CALIBRATE_DELAY
 	bool
 	default y
 
-config NO_IOPORT
+config NO_IOPORT_MAP
 	def_bool y
 
 config FORCE_MAX_ZONEORDER
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index fbc5c78c9ac7..0fd6138f6203 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -19,7 +19,7 @@ config HEXAGON
 	select GENERIC_IRQ_SHOW
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
-	select NO_IOPORT
+	select NO_IOPORT_MAP
 	select GENERIC_IOMAP
 	select GENERIC_SMP_IDLE_THREAD
 	select STACKTRACE_SUPPORT
diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig
index ca4504424dae..9e44bbd8051e 100644
--- a/arch/m32r/Kconfig
+++ b/arch/m32r/Kconfig
@@ -28,7 +28,7 @@ config ZONE_DMA
 	bool
 	default y
 
-config NO_IOPORT
+config NO_IOPORT_MAP
 	def_bool y
 
 config NO_DMA
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index b2e322939256..87b7c7581b1d 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -52,7 +52,7 @@ config TIME_LOW_RES
 	bool
 	default y
 
-config NO_IOPORT
+config NO_IOPORT_MAP
 	def_bool y
 
 config NO_DMA
diff --git a/arch/metag/Kconfig b/arch/metag/Kconfig
index b1d3c9c0eff8..499b7610eaaf 100644
--- a/arch/metag/Kconfig
+++ b/arch/metag/Kconfig
@@ -52,7 +52,7 @@ config GENERIC_HWEIGHT
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
 
-config NO_IOPORT
+config NO_IOPORT_MAP
 	def_bool y
 
 source "init/Kconfig"
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 16d5ab1615b1..5cd695f905a1 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -175,7 +175,7 @@ config MACH_DECSTATION
 	select CPU_R4000_WORKAROUNDS if 64BIT
 	select CPU_R4400_WORKAROUNDS if 64BIT
 	select DMA_NONCOHERENT
-	select NO_IOPORT
+	select NO_IOPORT_MAP
 	select IRQ_CPU
 	select SYS_HAS_CPU_R3000
 	select SYS_HAS_CPU_R4X00
@@ -947,7 +947,7 @@ config SYNC_R4K
 config MIPS_MACHINE
 	def_bool n
 
-config NO_IOPORT
+config NO_IOPORT_MAP
 	def_bool n
 
 config GENERIC_ISA_DMA
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 9488209a5253..e71d712afb79 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -41,7 +41,7 @@ config RWSEM_XCHGADD_ALGORITHM
 config GENERIC_HWEIGHT
 	def_bool y
 
-config NO_IOPORT
+config NO_IOPORT_MAP
 	def_bool y
 
 config TRACE_IRQFLAGS_SUPPORT
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 953f17c8d17c..346d21678ffd 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -52,7 +52,7 @@ config KEXEC
 config AUDIT_ARCH
 	def_bool y
 
-config NO_IOPORT
+config NO_IOPORT_MAP
 	def_bool y
 
 config PCI_QUIRKS
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 1399383315a3..ba55e939a820 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -3,7 +3,7 @@ config SUPERH
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select EXPERT
 	select CLKDEV_LOOKUP
-	select HAVE_IDE if HAS_IOPORT
+	select HAVE_IDE if HAS_IOPORT_MAP
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
 	select ARCH_DISCARD_MEMBLOCK
@@ -138,7 +138,7 @@ config ARCH_HAS_ILOG2_U32
 config ARCH_HAS_ILOG2_U64
 	def_bool n
 
-config NO_IOPORT
+config NO_IOPORT_MAP
 	def_bool !PCI
 	depends on !SH_CAYMAN && !SH_SH4202_MICRODEV && !SH_SHMIN && \
 		   !SH_HP6XX && !SH_SOLUTION_ENGINE
diff --git a/arch/sh/boards/Kconfig b/arch/sh/boards/Kconfig
index eb1cf84231a2..e331e5373b8e 100644
--- a/arch/sh/boards/Kconfig
+++ b/arch/sh/boards/Kconfig
@@ -158,7 +158,7 @@ config SH_SDK7786
 	bool "SDK7786"
 	depends on CPU_SUBTYPE_SH7786
 	select SYS_SUPPORTS_PCI
-	select NO_IOPORT if !PCI
+	select NO_IOPORT_MAP if !PCI
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select HAVE_SRAM_POOL
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
@@ -204,7 +204,7 @@ config SH_URQUELL
 	depends on CPU_SUBTYPE_SH7786
 	select ARCH_REQUIRE_GPIOLIB
 	select SYS_SUPPORTS_PCI
-	select NO_IOPORT if !PCI
+	select NO_IOPORT_MAP if !PCI
 
 config SH_MIGOR
 	bool "Migo-R"
@@ -306,7 +306,7 @@ config SH_LBOX_RE2
 config SH_X3PROTO
 	bool "SH-X3 Prototype board"
 	depends on CPU_SUBTYPE_SHX3
-	select NO_IOPORT if !PCI
+	select NO_IOPORT_MAP if !PCI
 	select IRQ_DOMAIN
 
 config SH_MAGIC_PANEL_R2
@@ -333,7 +333,7 @@ config SH_POLARIS
 
 config SH_SH2007
 	bool "SH-2007 board"
-	select NO_IOPORT
+	select NO_IOPORT_MAP
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 	depends on CPU_SUBTYPE_SH7780
 	help
diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h
index 629db2ad7916..728c4c571f40 100644
--- a/arch/sh/include/asm/io.h
+++ b/arch/sh/include/asm/io.h
@@ -122,7 +122,7 @@ __BUILD_MEMORY_STRING(__raw_, l, u32)
 
 __BUILD_MEMORY_STRING(__raw_, q, u64)
 
-#ifdef CONFIG_HAS_IOPORT
+#ifdef CONFIG_HAS_IOPORT_MAP
 
 /*
  * Slowdown I/O port space accesses for antique hardware.
@@ -218,7 +218,7 @@ __BUILD_IOPORT_STRING(w, u16)
 __BUILD_IOPORT_STRING(l, u32)
 __BUILD_IOPORT_STRING(q, u64)
 
-#else /* !CONFIG_HAS_IOPORT */
+#else /* !CONFIG_HAS_IOPORT_MAP */
 
 #include <asm/io_noioport.h>
 
diff --git a/arch/sh/include/asm/io_trapped.h b/arch/sh/include/asm/io_trapped.h
index f1251d4f0ba9..4ab94ef51071 100644
--- a/arch/sh/include/asm/io_trapped.h
+++ b/arch/sh/include/asm/io_trapped.h
@@ -36,7 +36,7 @@ __ioremap_trapped(unsigned long offset, unsigned long size)
 #define __ioremap_trapped(offset, size) NULL
 #endif
 
-#ifdef CONFIG_HAS_IOPORT
+#ifdef CONFIG_HAS_IOPORT_MAP
 extern struct list_head trapped_io;
 
 static inline void __iomem *
diff --git a/arch/sh/include/asm/machvec.h b/arch/sh/include/asm/machvec.h
index eb9c20d971dd..d3324e4f372e 100644
--- a/arch/sh/include/asm/machvec.h
+++ b/arch/sh/include/asm/machvec.h
@@ -21,7 +21,7 @@ struct sh_machine_vector {
 	int (*mv_irq_demux)(int irq);
 	void (*mv_init_irq)(void);
 
-#ifdef CONFIG_HAS_IOPORT
+#ifdef CONFIG_HAS_IOPORT_MAP
 	void __iomem *(*mv_ioport_map)(unsigned long port, unsigned int size);
 	void (*mv_ioport_unmap)(void __iomem *);
 #endif
diff --git a/arch/sh/kernel/Makefile b/arch/sh/kernel/Makefile
index 261c8bfd75ce..2ccf36c824c6 100644
--- a/arch/sh/kernel/Makefile
+++ b/arch/sh/kernel/Makefile
@@ -22,7 +22,7 @@ obj-y	:= debugtraps.o dma-nommu.o dumpstack.o 		\
 
 ifndef CONFIG_GENERIC_IOMAP
 obj-y				+= iomap.o
-obj-$(CONFIG_HAS_IOPORT)	+= ioport.o
+obj-$(CONFIG_HAS_IOPORT_MAP)	+= ioport.o
 endif
 
 obj-$(CONFIG_SUPERH32)		+= sys_sh32.o
diff --git a/arch/sh/kernel/io_trapped.c b/arch/sh/kernel/io_trapped.c
index c0a9761f2f8a..f8ce36286cea 100644
--- a/arch/sh/kernel/io_trapped.c
+++ b/arch/sh/kernel/io_trapped.c
@@ -22,7 +22,7 @@
 
 #define TRAPPED_PAGES_MAX 16
 
-#ifdef CONFIG_HAS_IOPORT
+#ifdef CONFIG_HAS_IOPORT_MAP
 LIST_HEAD(trapped_io);
 EXPORT_SYMBOL_GPL(trapped_io);
 #endif
@@ -90,7 +90,7 @@ int register_trapped_io(struct trapped_io *tiop)
 	tiop->magic = IO_TRAPPED_MAGIC;
 	INIT_LIST_HEAD(&tiop->list);
 	spin_lock_irq(&trapped_lock);
-#ifdef CONFIG_HAS_IOPORT
+#ifdef CONFIG_HAS_IOPORT_MAP
 	if (flags & IORESOURCE_IO)
 		list_add(&tiop->list, &trapped_io);
 #endif
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index 31c8c6223995..85258ca43ff5 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -411,7 +411,7 @@ config PCI_DOMAINS
 config NO_IOMEM
 	def_bool !PCI
 
-config NO_IOPORT
+config NO_IOPORT_MAP
 	def_bool !PCI
 
 config TILE_PCI_IO
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index 25c0dba508cc..aafad6fa1667 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -27,7 +27,7 @@ config UNICORE32
 config GENERIC_CSUM
 	def_bool y
 
-config NO_IOPORT
+config NO_IOPORT_MAP
 	bool
 
 config STACKTRACE_SUPPORT
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index c87ae7c6e5f9..02d6d29a63c1 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -41,7 +41,7 @@ config ARCH_HAS_ILOG2_U32
 config ARCH_HAS_ILOG2_U64
 	def_bool n
 
-config NO_IOPORT
+config NO_IOPORT_MAP
 	def_bool n
 
 config HZ
@@ -239,7 +239,7 @@ config XTENSA_PLATFORM_XT2000
 config XTENSA_PLATFORM_S6105
 	bool "S6105"
 	select SERIAL_CONSOLE
-	select NO_IOPORT
+	select NO_IOPORT_MAP
 
 config XTENSA_PLATFORM_XTFPGA
 	bool "XTFPGA"
diff --git a/arch/xtensa/configs/iss_defconfig b/arch/xtensa/configs/iss_defconfig
index 4f233204faf9..d57d917ff240 100644
--- a/arch/xtensa/configs/iss_defconfig
+++ b/arch/xtensa/configs/iss_defconfig
@@ -11,7 +11,7 @@ CONFIG_GENERIC_FIND_NEXT_BIT=y
 CONFIG_GENERIC_HWEIGHT=y
 # CONFIG_ARCH_HAS_ILOG2_U32 is not set
 # CONFIG_ARCH_HAS_ILOG2_U64 is not set
-CONFIG_NO_IOPORT=y
+CONFIG_NO_IOPORT_MAP=y
 CONFIG_HZ=100
 CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
 CONFIG_CONSTRUCTORS=y
diff --git a/arch/xtensa/configs/s6105_defconfig b/arch/xtensa/configs/s6105_defconfig
index d929f77a0360..583c2b0974ca 100644
--- a/arch/xtensa/configs/s6105_defconfig
+++ b/arch/xtensa/configs/s6105_defconfig
@@ -11,7 +11,7 @@ CONFIG_GENERIC_FIND_NEXT_BIT=y
 CONFIG_GENERIC_HWEIGHT=y
 # CONFIG_ARCH_HAS_ILOG2_U32 is not set
 # CONFIG_ARCH_HAS_ILOG2_U64 is not set
-CONFIG_NO_IOPORT=y
+CONFIG_NO_IOPORT_MAP=y
 CONFIG_HZ=100
 CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
 
diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig
index 1a65838888cd..c54cac3f8bc8 100644
--- a/drivers/char/tpm/Kconfig
+++ b/drivers/char/tpm/Kconfig
@@ -74,7 +74,7 @@ config TCG_NSC
 
 config TCG_ATMEL
 	tristate "Atmel TPM Interface"
-	depends on PPC64 || HAS_IOPORT
+	depends on PPC64 || HAS_IOPORT_MAP
 	---help---
 	  If you have a TPM security chip from Atmel say Yes and it 
 	  will be accessible from within Linux.  To compile this driver 
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index de17c5593d97..014afab1d551 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -936,7 +936,7 @@ config I2C_ACORN
 
 config I2C_ELEKTOR
 	tristate "Elektor ISA card"
-	depends on ISA && HAS_IOPORT && BROKEN_ON_SMP
+	depends on ISA && HAS_IOPORT_MAP && BROKEN_ON_SMP
 	select I2C_ALGOPCF
 	help
 	  This supports the PCF8584 ISA bus I2C adapter.  Say Y if you own
diff --git a/drivers/net/can/sja1000/Kconfig b/drivers/net/can/sja1000/Kconfig
index 4b18b8765523..1e65cb6c2591 100644
--- a/drivers/net/can/sja1000/Kconfig
+++ b/drivers/net/can/sja1000/Kconfig
@@ -39,7 +39,7 @@ config CAN_EMS_PCI
 config CAN_PEAK_PCMCIA
 	tristate "PEAK PCAN-PC Card"
 	depends on PCMCIA
-	depends on HAS_IOPORT
+	depends on HAS_IOPORT_MAP
 	---help---
 	  This driver is for the PCAN-PC Card PCMCIA adapter (1 or 2 channels)
 	  from PEAK-System (http://www.peak-system.com). To compile this
diff --git a/drivers/net/ethernet/3com/Kconfig b/drivers/net/ethernet/3com/Kconfig
index 65b735d4a6ad..afaab4b2333f 100644
--- a/drivers/net/ethernet/3com/Kconfig
+++ b/drivers/net/ethernet/3com/Kconfig
@@ -66,7 +66,7 @@ config PCMCIA_3C589
 
 config VORTEX
 	tristate "3c590/3c900 series (592/595/597) \"Vortex/Boomerang\" support"
-	depends on (PCI || EISA) && HAS_IOPORT
+	depends on (PCI || EISA) && HAS_IOPORT_MAP
 	select MII
 	---help---
 	  This option enables driver support for a large number of 10Mbps and
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index d5afe96adba6..975e1cc75edb 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -327,7 +327,7 @@ static inline void iounmap(void __iomem *addr)
 }
 #endif /* CONFIG_MMU */
 
-#ifdef CONFIG_HAS_IOPORT
+#ifdef CONFIG_HAS_IOPORT_MAP
 #ifndef CONFIG_GENERIC_IOMAP
 static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
 {
@@ -341,7 +341,7 @@ static inline void ioport_unmap(void __iomem *p)
 extern void __iomem *ioport_map(unsigned long port, unsigned int nr);
 extern void ioport_unmap(void __iomem *p);
 #endif /* CONFIG_GENERIC_IOMAP */
-#endif /* CONFIG_HAS_IOPORT */
+#endif /* CONFIG_HAS_IOPORT_MAP */
 
 #ifndef xlate_dev_kmem_ptr
 #define xlate_dev_kmem_ptr(p)	p
diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h
index 6afd7d6a9899..1b41011643a5 100644
--- a/include/asm-generic/iomap.h
+++ b/include/asm-generic/iomap.h
@@ -56,7 +56,7 @@ extern void iowrite8_rep(void __iomem *port, const void *buf, unsigned long coun
 extern void iowrite16_rep(void __iomem *port, const void *buf, unsigned long count);
 extern void iowrite32_rep(void __iomem *port, const void *buf, unsigned long count);
 
-#ifdef CONFIG_HAS_IOPORT
+#ifdef CONFIG_HAS_IOPORT_MAP
 /* Create a virtual mapping cookie for an IO port range */
 extern void __iomem *ioport_map(unsigned long port, unsigned int nr);
 extern void ioport_unmap(void __iomem *);
diff --git a/include/linux/io.h b/include/linux/io.h
index 8a18e75600cc..b76e6e545806 100644
--- a/include/linux/io.h
+++ b/include/linux/io.h
@@ -41,7 +41,7 @@ static inline int ioremap_page_range(unsigned long addr, unsigned long end,
 /*
  * Managed iomap interface
  */
-#ifdef CONFIG_HAS_IOPORT
+#ifdef CONFIG_HAS_IOPORT_MAP
 void __iomem * devm_ioport_map(struct device *dev, unsigned long port,
 			       unsigned int nr);
 void devm_ioport_unmap(struct device *dev, void __iomem *addr);
diff --git a/lib/Kconfig b/lib/Kconfig
index 991c98bc4a3f..5d4984c505f8 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -342,9 +342,9 @@ config HAS_IOMEM
 	select GENERIC_IO
 	default y
 
-config HAS_IOPORT
+config HAS_IOPORT_MAP
 	boolean
-	depends on HAS_IOMEM && !NO_IOPORT
+	depends on HAS_IOMEM && !NO_IOPORT_MAP
 	default y
 
 config HAS_DMA
diff --git a/lib/devres.c b/lib/devres.c
index 48cb3c7bd7de..2f16c133fd36 100644
--- a/lib/devres.c
+++ b/lib/devres.c
@@ -170,7 +170,7 @@ void __iomem *devm_request_and_ioremap(struct device *device,
 }
 EXPORT_SYMBOL(devm_request_and_ioremap);
 
-#ifdef CONFIG_HAS_IOPORT
+#ifdef CONFIG_HAS_IOPORT_MAP
 /*
  * Generic iomap devres
  */
@@ -229,7 +229,7 @@ void devm_ioport_unmap(struct device *dev, void __iomem *addr)
 			       devm_ioport_map_match, (__force void *)addr));
 }
 EXPORT_SYMBOL(devm_ioport_unmap);
-#endif /* CONFIG_HAS_IOPORT */
+#endif /* CONFIG_HAS_IOPORT_MAP */
 
 #ifdef CONFIG_PCI
 /*
diff --git a/lib/iomap.c b/lib/iomap.c
index 2c08f36862eb..fc3dcb4b238e 100644
--- a/lib/iomap.c
+++ b/lib/iomap.c
@@ -224,7 +224,7 @@ EXPORT_SYMBOL(iowrite8_rep);
 EXPORT_SYMBOL(iowrite16_rep);
 EXPORT_SYMBOL(iowrite32_rep);
 
-#ifdef CONFIG_HAS_IOPORT
+#ifdef CONFIG_HAS_IOPORT_MAP
 /* Create a virtual mapping cookie for an IO port range */
 void __iomem *ioport_map(unsigned long port, unsigned int nr)
 {
@@ -239,7 +239,7 @@ void ioport_unmap(void __iomem *addr)
 }
 EXPORT_SYMBOL(ioport_map);
 EXPORT_SYMBOL(ioport_unmap);
-#endif /* CONFIG_HAS_IOPORT */
+#endif /* CONFIG_HAS_IOPORT_MAP */
 
 #ifdef CONFIG_PCI
 /* Hide the details if this is a MMIO or PIO address space and just do what
diff --git a/sound/isa/Kconfig b/sound/isa/Kconfig
index affa13480659..0216475fc759 100644
--- a/sound/isa/Kconfig
+++ b/sound/isa/Kconfig
@@ -191,7 +191,7 @@ config SND_ES18XX
 
 config SND_SC6000
 	tristate "Gallant SC-6000/6600/7000 and Audio Excel DSP 16"
-	depends on HAS_IOPORT
+	depends on HAS_IOPORT_MAP
 	select SND_WSS_LIB
 	select SND_OPL3_LIB
 	select SND_MPU401_UART
diff --git a/sound/pci/Kconfig b/sound/pci/Kconfig
index 0b0c0cf13f74..3a3a3a71088b 100644
--- a/sound/pci/Kconfig
+++ b/sound/pci/Kconfig
@@ -688,7 +688,7 @@ config SND_LOLA
 
 config SND_LX6464ES
 	tristate "Digigram LX6464ES"
-	depends on HAS_IOPORT
+	depends on HAS_IOPORT_MAP
 	select SND_PCM
 	help
 	  Say Y here to include support for Digigram LX6464ES boards.
-- 
cgit v1.2.3


From 5722d094ad2b56fa2c1cb3adaf40071a55bbf242 Mon Sep 17 00:00:00 2001
From: Vladimir Davydov <vdavydov@parallels.com>
Date: Mon, 7 Apr 2014 15:39:24 -0700
Subject: memcg, slab: cleanup memcg cache creation

This patch cleans up the memcg cache creation path as follows:

- Move memcg cache name creation to a separate function to be called
  from kmem_cache_create_memcg().  This allows us to get rid of the mutex
  protecting the temporary buffer used for the name formatting, because
  the whole cache creation path is protected by the slab_mutex.

- Get rid of memcg_create_kmem_cache().  This function serves as a proxy
  to kmem_cache_create_memcg().  After separating the cache name creation
  path, it would be reduced to a function call, so let's inline it.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Glauber Costa <glommer@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  9 +++++
 mm/memcontrol.c            | 89 ++++++++++++++++++++--------------------------
 mm/slab_common.c           |  5 ++-
 3 files changed, 52 insertions(+), 51 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 96f3fc87ab96..ab7f02884983 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -491,6 +491,9 @@ void __memcg_kmem_commit_charge(struct page *page,
 void __memcg_kmem_uncharge_pages(struct page *page, int order);
 
 int memcg_cache_id(struct mem_cgroup *memcg);
+
+char *memcg_create_cache_name(struct mem_cgroup *memcg,
+			      struct kmem_cache *root_cache);
 int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s,
 			     struct kmem_cache *root_cache);
 void memcg_free_cache_params(struct kmem_cache *s);
@@ -635,6 +638,12 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg)
 	return -1;
 }
 
+static inline char *memcg_create_cache_name(struct mem_cgroup *memcg,
+					    struct kmem_cache *root_cache)
+{
+	return NULL;
+}
+
 static inline int memcg_alloc_cache_params(struct mem_cgroup *memcg,
 		struct kmem_cache *s, struct kmem_cache *root_cache)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e33b1d09eb1f..32c7342df4bf 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3094,6 +3094,29 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups)
 	return 0;
 }
 
+char *memcg_create_cache_name(struct mem_cgroup *memcg,
+			      struct kmem_cache *root_cache)
+{
+	static char *buf = NULL;
+
+	/*
+	 * We need a mutex here to protect the shared buffer. Since this is
+	 * expected to be called only on cache creation, we can employ the
+	 * slab_mutex for that purpose.
+	 */
+	lockdep_assert_held(&slab_mutex);
+
+	if (!buf) {
+		buf = kmalloc(NAME_MAX + 1, GFP_KERNEL);
+		if (!buf)
+			return NULL;
+	}
+
+	cgroup_name(memcg->css.cgroup, buf, NAME_MAX + 1);
+	return kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name,
+			 memcg_cache_id(memcg), buf);
+}
+
 int memcg_alloc_cache_params(struct mem_cgroup *memcg, struct kmem_cache *s,
 			     struct kmem_cache *root_cache)
 {
@@ -3298,46 +3321,6 @@ void mem_cgroup_destroy_cache(struct kmem_cache *cachep)
 	schedule_work(&cachep->memcg_params->destroy);
 }
 
-static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
-						  struct kmem_cache *s)
-{
-	struct kmem_cache *new = NULL;
-	static char *tmp_path = NULL, *tmp_name = NULL;
-	static DEFINE_MUTEX(mutex);	/* protects tmp_name */
-
-	BUG_ON(!memcg_can_account_kmem(memcg));
-
-	mutex_lock(&mutex);
-	/*
-	 * kmem_cache_create_memcg duplicates the given name and
-	 * cgroup_name for this name requires RCU context.
-	 * This static temporary buffer is used to prevent from
-	 * pointless shortliving allocation.
-	 */
-	if (!tmp_path || !tmp_name) {
-		if (!tmp_path)
-			tmp_path = kmalloc(PATH_MAX, GFP_KERNEL);
-		if (!tmp_name)
-			tmp_name = kmalloc(NAME_MAX + 1, GFP_KERNEL);
-		if (!tmp_path || !tmp_name)
-			goto out;
-	}
-
-	cgroup_name(memcg->css.cgroup, tmp_name, NAME_MAX + 1);
-	snprintf(tmp_path, PATH_MAX, "%s(%d:%s)", s->name,
-		 memcg_cache_id(memcg), tmp_name);
-
-	new = kmem_cache_create_memcg(memcg, tmp_path, s->object_size, s->align,
-				      (s->flags & ~SLAB_PANIC), s->ctor, s);
-	if (new)
-		new->allocflags |= __GFP_KMEMCG;
-	else
-		new = s;
-out:
-	mutex_unlock(&mutex);
-	return new;
-}
-
 void kmem_cache_destroy_memcg_children(struct kmem_cache *s)
 {
 	struct kmem_cache *c;
@@ -3384,12 +3367,6 @@ void kmem_cache_destroy_memcg_children(struct kmem_cache *s)
 	mutex_unlock(&activate_kmem_mutex);
 }
 
-struct create_work {
-	struct mem_cgroup *memcg;
-	struct kmem_cache *cachep;
-	struct work_struct work;
-};
-
 static void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg)
 {
 	struct kmem_cache *cachep;
@@ -3407,13 +3384,25 @@ static void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg)
 	mutex_unlock(&memcg->slab_caches_mutex);
 }
 
+struct create_work {
+	struct mem_cgroup *memcg;
+	struct kmem_cache *cachep;
+	struct work_struct work;
+};
+
 static void memcg_create_cache_work_func(struct work_struct *w)
 {
-	struct create_work *cw;
+	struct create_work *cw = container_of(w, struct create_work, work);
+	struct mem_cgroup *memcg = cw->memcg;
+	struct kmem_cache *cachep = cw->cachep;
+	struct kmem_cache *new;
 
-	cw = container_of(w, struct create_work, work);
-	memcg_create_kmem_cache(cw->memcg, cw->cachep);
-	css_put(&cw->memcg->css);
+	new = kmem_cache_create_memcg(memcg, cachep->name,
+			cachep->object_size, cachep->align,
+			cachep->flags & ~SLAB_PANIC, cachep->ctor, cachep);
+	if (new)
+		new->allocflags |= __GFP_KMEMCG;
+	css_put(&memcg->css);
 	kfree(cw);
 }
 
diff --git a/mm/slab_common.c b/mm/slab_common.c
index e77b51eb7347..11857abf7057 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -215,7 +215,10 @@ kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size,
 	s->align = calculate_alignment(flags, align, size);
 	s->ctor = ctor;
 
-	s->name = kstrdup(name, GFP_KERNEL);
+	if (memcg)
+		s->name = memcg_create_cache_name(memcg, parent_cache);
+	else
+		s->name = kstrdup(name, GFP_KERNEL);
 	if (!s->name)
 		goto out_free_cache;
 
-- 
cgit v1.2.3


From 794b1248be4e7e157f5535c3ee49168aa4643349 Mon Sep 17 00:00:00 2001
From: Vladimir Davydov <vdavydov@parallels.com>
Date: Mon, 7 Apr 2014 15:39:26 -0700
Subject: memcg, slab: separate memcg vs root cache creation paths

Memcg-awareness turned kmem_cache_create() into a dirty interweaving of
memcg-only and except-for-memcg calls.  To clean this up, let's move the
code responsible for memcg cache creation to a separate function.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Glauber Costa <glommer@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |   6 --
 include/linux/slab.h       |   6 +-
 mm/memcontrol.c            |   7 +-
 mm/slab_common.c           | 187 ++++++++++++++++++++++++++-------------------
 4 files changed, 111 insertions(+), 95 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index ab7f02884983..02d3072841e9 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -638,12 +638,6 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg)
 	return -1;
 }
 
-static inline char *memcg_create_cache_name(struct mem_cgroup *memcg,
-					    struct kmem_cache *root_cache)
-{
-	return NULL;
-}
-
 static inline int memcg_alloc_cache_params(struct mem_cgroup *memcg,
 		struct kmem_cache *s, struct kmem_cache *root_cache)
 {
diff --git a/include/linux/slab.h b/include/linux/slab.h
index b5b2df60299e..3dd389aa91c7 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -115,9 +115,9 @@ int slab_is_available(void);
 struct kmem_cache *kmem_cache_create(const char *, size_t, size_t,
 			unsigned long,
 			void (*)(void *));
-struct kmem_cache *
-kmem_cache_create_memcg(struct mem_cgroup *, const char *, size_t, size_t,
-			unsigned long, void (*)(void *), struct kmem_cache *);
+#ifdef CONFIG_MEMCG_KMEM
+void kmem_cache_create_memcg(struct mem_cgroup *, struct kmem_cache *);
+#endif
 void kmem_cache_destroy(struct kmem_cache *);
 int kmem_cache_shrink(struct kmem_cache *);
 void kmem_cache_free(struct kmem_cache *, void *);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 32c7342df4bf..451523c3bd4e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3395,13 +3395,8 @@ static void memcg_create_cache_work_func(struct work_struct *w)
 	struct create_work *cw = container_of(w, struct create_work, work);
 	struct mem_cgroup *memcg = cw->memcg;
 	struct kmem_cache *cachep = cw->cachep;
-	struct kmem_cache *new;
 
-	new = kmem_cache_create_memcg(memcg, cachep->name,
-			cachep->object_size, cachep->align,
-			cachep->flags & ~SLAB_PANIC, cachep->ctor, cachep);
-	if (new)
-		new->allocflags |= __GFP_KMEMCG;
+	kmem_cache_create_memcg(memcg, cachep);
 	css_put(&memcg->css);
 	kfree(cw);
 }
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 11857abf7057..ccc012f00126 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -29,8 +29,7 @@ DEFINE_MUTEX(slab_mutex);
 struct kmem_cache *kmem_cache;
 
 #ifdef CONFIG_DEBUG_VM
-static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name,
-				   size_t size)
+static int kmem_cache_sanity_check(const char *name, size_t size)
 {
 	struct kmem_cache *s = NULL;
 
@@ -57,13 +56,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name,
 		}
 
 #if !defined(CONFIG_SLUB) || !defined(CONFIG_SLUB_DEBUG_ON)
-		/*
-		 * For simplicity, we won't check this in the list of memcg
-		 * caches. We have control over memcg naming, and if there
-		 * aren't duplicates in the global list, there won't be any
-		 * duplicates in the memcg lists as well.
-		 */
-		if (!memcg && !strcmp(s->name, name)) {
+		if (!strcmp(s->name, name)) {
 			pr_err("%s (%s): Cache name already exists.\n",
 			       __func__, name);
 			dump_stack();
@@ -77,8 +70,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name,
 	return 0;
 }
 #else
-static inline int kmem_cache_sanity_check(struct mem_cgroup *memcg,
-					  const char *name, size_t size)
+static inline int kmem_cache_sanity_check(const char *name, size_t size)
 {
 	return 0;
 }
@@ -139,6 +131,46 @@ unsigned long calculate_alignment(unsigned long flags,
 	return ALIGN(align, sizeof(void *));
 }
 
+static struct kmem_cache *
+do_kmem_cache_create(char *name, size_t object_size, size_t size, size_t align,
+		     unsigned long flags, void (*ctor)(void *),
+		     struct mem_cgroup *memcg, struct kmem_cache *root_cache)
+{
+	struct kmem_cache *s;
+	int err;
+
+	err = -ENOMEM;
+	s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL);
+	if (!s)
+		goto out;
+
+	s->name = name;
+	s->object_size = object_size;
+	s->size = size;
+	s->align = align;
+	s->ctor = ctor;
+
+	err = memcg_alloc_cache_params(memcg, s, root_cache);
+	if (err)
+		goto out_free_cache;
+
+	err = __kmem_cache_create(s, flags);
+	if (err)
+		goto out_free_cache;
+
+	s->refcount = 1;
+	list_add(&s->list, &slab_caches);
+	memcg_register_cache(s);
+out:
+	if (err)
+		return ERR_PTR(err);
+	return s;
+
+out_free_cache:
+	memcg_free_cache_params(s);
+	kfree(s);
+	goto out;
+}
 
 /*
  * kmem_cache_create - Create a cache.
@@ -164,34 +196,21 @@ unsigned long calculate_alignment(unsigned long flags,
  * cacheline.  This can be beneficial if you're counting cycles as closely
  * as davem.
  */
-
 struct kmem_cache *
-kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size,
-			size_t align, unsigned long flags, void (*ctor)(void *),
-			struct kmem_cache *parent_cache)
+kmem_cache_create(const char *name, size_t size, size_t align,
+		  unsigned long flags, void (*ctor)(void *))
 {
-	struct kmem_cache *s = NULL;
+	struct kmem_cache *s;
+	char *cache_name;
 	int err;
 
 	get_online_cpus();
 	mutex_lock(&slab_mutex);
 
-	err = kmem_cache_sanity_check(memcg, name, size);
+	err = kmem_cache_sanity_check(name, size);
 	if (err)
 		goto out_unlock;
 
-	if (memcg) {
-		/*
-		 * Since per-memcg caches are created asynchronously on first
-		 * allocation (see memcg_kmem_get_cache()), several threads can
-		 * try to create the same cache, but only one of them may
-		 * succeed. Therefore if we get here and see the cache has
-		 * already been created, we silently return NULL.
-		 */
-		if (cache_from_memcg_idx(parent_cache, memcg_cache_id(memcg)))
-			goto out_unlock;
-	}
-
 	/*
 	 * Some allocators will constraint the set of valid flags to a subset
 	 * of all flags. We expect them to define CACHE_CREATE_MASK in this
@@ -200,55 +219,29 @@ kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size,
 	 */
 	flags &= CACHE_CREATE_MASK;
 
-	if (!memcg) {
-		s = __kmem_cache_alias(name, size, align, flags, ctor);
-		if (s)
-			goto out_unlock;
-	}
-
-	err = -ENOMEM;
-	s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL);
-	if (!s)
+	s = __kmem_cache_alias(name, size, align, flags, ctor);
+	if (s)
 		goto out_unlock;
 
-	s->object_size = s->size = size;
-	s->align = calculate_alignment(flags, align, size);
-	s->ctor = ctor;
-
-	if (memcg)
-		s->name = memcg_create_cache_name(memcg, parent_cache);
-	else
-		s->name = kstrdup(name, GFP_KERNEL);
-	if (!s->name)
-		goto out_free_cache;
-
-	err = memcg_alloc_cache_params(memcg, s, parent_cache);
-	if (err)
-		goto out_free_cache;
-
-	err = __kmem_cache_create(s, flags);
-	if (err)
-		goto out_free_cache;
+	cache_name = kstrdup(name, GFP_KERNEL);
+	if (!cache_name) {
+		err = -ENOMEM;
+		goto out_unlock;
+	}
 
-	s->refcount = 1;
-	list_add(&s->list, &slab_caches);
-	memcg_register_cache(s);
+	s = do_kmem_cache_create(cache_name, size, size,
+				 calculate_alignment(flags, align, size),
+				 flags, ctor, NULL, NULL);
+	if (IS_ERR(s)) {
+		err = PTR_ERR(s);
+		kfree(cache_name);
+	}
 
 out_unlock:
 	mutex_unlock(&slab_mutex);
 	put_online_cpus();
 
 	if (err) {
-		/*
-		 * There is no point in flooding logs with warnings or
-		 * especially crashing the system if we fail to create a cache
-		 * for a memcg. In this case we will be accounting the memcg
-		 * allocation to the root cgroup until we succeed to create its
-		 * own cache, but it isn't that critical.
-		 */
-		if (!memcg)
-			return NULL;
-
 		if (flags & SLAB_PANIC)
 			panic("kmem_cache_create: Failed to create slab '%s'. Error %d\n",
 				name, err);
@@ -260,21 +253,55 @@ out_unlock:
 		return NULL;
 	}
 	return s;
-
-out_free_cache:
-	memcg_free_cache_params(s);
-	kfree(s->name);
-	kmem_cache_free(kmem_cache, s);
-	goto out_unlock;
 }
+EXPORT_SYMBOL(kmem_cache_create);
 
-struct kmem_cache *
-kmem_cache_create(const char *name, size_t size, size_t align,
-		  unsigned long flags, void (*ctor)(void *))
+#ifdef CONFIG_MEMCG_KMEM
+/*
+ * kmem_cache_create_memcg - Create a cache for a memory cgroup.
+ * @memcg: The memory cgroup the new cache is for.
+ * @root_cache: The parent of the new cache.
+ *
+ * This function attempts to create a kmem cache that will serve allocation
+ * requests going from @memcg to @root_cache. The new cache inherits properties
+ * from its parent.
+ */
+void kmem_cache_create_memcg(struct mem_cgroup *memcg, struct kmem_cache *root_cache)
 {
-	return kmem_cache_create_memcg(NULL, name, size, align, flags, ctor, NULL);
+	struct kmem_cache *s;
+	char *cache_name;
+
+	get_online_cpus();
+	mutex_lock(&slab_mutex);
+
+	/*
+	 * Since per-memcg caches are created asynchronously on first
+	 * allocation (see memcg_kmem_get_cache()), several threads can try to
+	 * create the same cache, but only one of them may succeed.
+	 */
+	if (cache_from_memcg_idx(root_cache, memcg_cache_id(memcg)))
+		goto out_unlock;
+
+	cache_name = memcg_create_cache_name(memcg, root_cache);
+	if (!cache_name)
+		goto out_unlock;
+
+	s = do_kmem_cache_create(cache_name, root_cache->object_size,
+				 root_cache->size, root_cache->align,
+				 root_cache->flags, root_cache->ctor,
+				 memcg, root_cache);
+	if (IS_ERR(s)) {
+		kfree(cache_name);
+		goto out_unlock;
+	}
+
+	s->allocflags |= __GFP_KMEMCG;
+
+out_unlock:
+	mutex_unlock(&slab_mutex);
+	put_online_cpus();
 }
-EXPORT_SYMBOL(kmem_cache_create);
+#endif /* CONFIG_MEMCG_KMEM */
 
 void kmem_cache_destroy(struct kmem_cache *s)
 {
-- 
cgit v1.2.3


From b8529907ba35d625fa4b85d3e4dc8021be97c1f3 Mon Sep 17 00:00:00 2001
From: Vladimir Davydov <vdavydov@parallels.com>
Date: Mon, 7 Apr 2014 15:39:28 -0700
Subject: memcg, slab: do not destroy children caches if parent has aliases

Currently we destroy children caches at the very beginning of
kmem_cache_destroy().  This is wrong, because the root cache will not
necessarily be destroyed in the end - if it has aliases (refcount > 0),
kmem_cache_destroy() will simply decrement its refcount and return.  In
this case, at best we will get a bunch of warnings in dmesg, like this
one:

  kmem_cache_destroy kmalloc-32:0: Slab cache still has objects
  CPU: 1 PID: 7139 Comm: modprobe Tainted: G    B   W    3.13.0+ #117
  Call Trace:
    dump_stack+0x49/0x5b
    kmem_cache_destroy+0xdf/0xf0
    kmem_cache_destroy_memcg_children+0x97/0xc0
    kmem_cache_destroy+0xf/0xf0
    xfs_mru_cache_uninit+0x21/0x30 [xfs]
    exit_xfs_fs+0x2e/0xc44 [xfs]
    SyS_delete_module+0x198/0x1f0
    system_call_fastpath+0x16/0x1b

At worst - if kmem_cache_destroy() will race with an allocation from a
memcg cache - the kernel will panic.

This patch fixes this by moving children caches destruction after the
check if the cache has aliases.  Plus, it forbids destroying a root
cache if it still has children caches, because each children cache keeps
a reference to its parent.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Glauber Costa <glommer@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  6 +---
 mm/memcontrol.c            | 13 ++++----
 mm/slab_common.c           | 75 ++++++++++++++++++++++++++++++----------------
 3 files changed, 57 insertions(+), 37 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 02d3072841e9..b569b8be5c5a 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -507,7 +507,7 @@ struct kmem_cache *
 __memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp);
 
 void mem_cgroup_destroy_cache(struct kmem_cache *cachep);
-void kmem_cache_destroy_memcg_children(struct kmem_cache *s);
+int __kmem_cache_destroy_memcg_children(struct kmem_cache *s);
 
 /**
  * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed.
@@ -661,10 +661,6 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 {
 	return cachep;
 }
-
-static inline void kmem_cache_destroy_memcg_children(struct kmem_cache *s)
-{
-}
 #endif /* CONFIG_MEMCG_KMEM */
 #endif /* _LINUX_MEMCONTROL_H */
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c22d8bf42d9a..29501f040568 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3321,15 +3321,10 @@ void mem_cgroup_destroy_cache(struct kmem_cache *cachep)
 	schedule_work(&cachep->memcg_params->destroy);
 }
 
-void kmem_cache_destroy_memcg_children(struct kmem_cache *s)
+int __kmem_cache_destroy_memcg_children(struct kmem_cache *s)
 {
 	struct kmem_cache *c;
-	int i;
-
-	if (!s->memcg_params)
-		return;
-	if (!s->memcg_params->is_root_cache)
-		return;
+	int i, failed = 0;
 
 	/*
 	 * If the cache is being destroyed, we trust that there is no one else
@@ -3363,8 +3358,12 @@ void kmem_cache_destroy_memcg_children(struct kmem_cache *s)
 		c->memcg_params->dead = false;
 		cancel_work_sync(&c->memcg_params->destroy);
 		kmem_cache_destroy(c);
+
+		if (cache_from_memcg_idx(s, i))
+			failed++;
 	}
 	mutex_unlock(&activate_kmem_mutex);
+	return failed;
 }
 
 static void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg)
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 0c2879ff414c..f3cfccf76dda 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -301,39 +301,64 @@ out_unlock:
 	mutex_unlock(&slab_mutex);
 	put_online_cpus();
 }
+
+static int kmem_cache_destroy_memcg_children(struct kmem_cache *s)
+{
+	int rc;
+
+	if (!s->memcg_params ||
+	    !s->memcg_params->is_root_cache)
+		return 0;
+
+	mutex_unlock(&slab_mutex);
+	rc = __kmem_cache_destroy_memcg_children(s);
+	mutex_lock(&slab_mutex);
+
+	return rc;
+}
+#else
+static int kmem_cache_destroy_memcg_children(struct kmem_cache *s)
+{
+	return 0;
+}
 #endif /* CONFIG_MEMCG_KMEM */
 
 void kmem_cache_destroy(struct kmem_cache *s)
 {
-	/* Destroy all the children caches if we aren't a memcg cache */
-	kmem_cache_destroy_memcg_children(s);
-
 	get_online_cpus();
 	mutex_lock(&slab_mutex);
+
 	s->refcount--;
-	if (!s->refcount) {
-		list_del(&s->list);
-		memcg_unregister_cache(s);
-
-		if (!__kmem_cache_shutdown(s)) {
-			mutex_unlock(&slab_mutex);
-			if (s->flags & SLAB_DESTROY_BY_RCU)
-				rcu_barrier();
-
-			memcg_free_cache_params(s);
-			kfree(s->name);
-			kmem_cache_free(kmem_cache, s);
-		} else {
-			list_add(&s->list, &slab_caches);
-			memcg_register_cache(s);
-			mutex_unlock(&slab_mutex);
-			printk(KERN_ERR "kmem_cache_destroy %s: Slab cache still has objects\n",
-				s->name);
-			dump_stack();
-		}
-	} else {
-		mutex_unlock(&slab_mutex);
+	if (s->refcount)
+		goto out_unlock;
+
+	if (kmem_cache_destroy_memcg_children(s) != 0)
+		goto out_unlock;
+
+	list_del(&s->list);
+	memcg_unregister_cache(s);
+
+	if (__kmem_cache_shutdown(s) != 0) {
+		list_add(&s->list, &slab_caches);
+		memcg_register_cache(s);
+		printk(KERN_ERR "kmem_cache_destroy %s: "
+		       "Slab cache still has objects\n", s->name);
+		dump_stack();
+		goto out_unlock;
 	}
+
+	mutex_unlock(&slab_mutex);
+	if (s->flags & SLAB_DESTROY_BY_RCU)
+		rcu_barrier();
+
+	memcg_free_cache_params(s);
+	kfree(s->name);
+	kmem_cache_free(kmem_cache, s);
+	goto out_put_cpus;
+
+out_unlock:
+	mutex_unlock(&slab_mutex);
+out_put_cpus:
 	put_online_cpus();
 }
 EXPORT_SYMBOL(kmem_cache_destroy);
-- 
cgit v1.2.3


From 9a41707bd3a0811919000daf094e9d50ea65f7da Mon Sep 17 00:00:00 2001
From: Vladimir Davydov <vdavydov@parallels.com>
Date: Mon, 7 Apr 2014 15:39:31 -0700
Subject: slub: rework sysfs layout for memcg caches

Currently, we try to arrange sysfs entries for memcg caches in the same
manner as for global caches.  Apart from turning /sys/kernel/slab into a
mess when there are a lot of kmem-active memcgs created, it actually
does not work properly - we won't create more than one link to a memcg
cache in case its parent is merged with another cache.  For instance, if
A is a root cache merged with another root cache B, we will have the
following sysfs setup:

  X
  A -> X
  B -> X

where X is some unique id (see create_unique_id()).  Now if memcgs M and
N start to allocate from cache A (or B, which is the same), we will get:

  X
  X:M
  X:N
  A -> X
  B -> X
  A:M -> X:M
  A:N -> X:N

Since B is an alias for A, we won't get entries B:M and B:N, which is
confusing.

It is more logical to have entries for memcg caches under the
corresponding root cache's sysfs directory.  This would allow us to keep
sysfs layout clean, and avoid such inconsistencies like one described
above.

This patch does the trick.  It creates a "cgroup" kset in each root
cache kobject to keep its children caches there.

Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Glauber Costa <glommer@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/slub_def.h |  3 +++
 mm/slub.c                | 26 +++++++++++++++++++++++++-
 2 files changed, 28 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index f56bfa9e4526..f2f7398848cf 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -87,6 +87,9 @@ struct kmem_cache {
 #ifdef CONFIG_MEMCG_KMEM
 	struct memcg_cache_params *memcg_params;
 	int max_attr_size; /* for propagation, maximum size of a stored attr */
+#ifdef CONFIG_SYSFS
+	struct kset *memcg_kset;
+#endif
 #endif
 
 #ifdef CONFIG_NUMA
diff --git a/mm/slub.c b/mm/slub.c
index 33939e72bc37..3508edec19f9 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -5138,6 +5138,15 @@ static const struct kset_uevent_ops slab_uevent_ops = {
 
 static struct kset *slab_kset;
 
+static inline struct kset *cache_kset(struct kmem_cache *s)
+{
+#ifdef CONFIG_MEMCG_KMEM
+	if (!is_root_cache(s))
+		return s->memcg_params->root_cache->memcg_kset;
+#endif
+	return slab_kset;
+}
+
 #define ID_STR_LENGTH 64
 
 /* Create a unique string id for a slab cache:
@@ -5203,7 +5212,7 @@ static int sysfs_slab_add(struct kmem_cache *s)
 		name = create_unique_id(s);
 	}
 
-	s->kobj.kset = slab_kset;
+	s->kobj.kset = cache_kset(s);
 	err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name);
 	if (err) {
 		kobject_put(&s->kobj);
@@ -5216,6 +5225,18 @@ static int sysfs_slab_add(struct kmem_cache *s)
 		kobject_put(&s->kobj);
 		return err;
 	}
+
+#ifdef CONFIG_MEMCG_KMEM
+	if (is_root_cache(s)) {
+		s->memcg_kset = kset_create_and_add("cgroup", NULL, &s->kobj);
+		if (!s->memcg_kset) {
+			kobject_del(&s->kobj);
+			kobject_put(&s->kobj);
+			return -ENOMEM;
+		}
+	}
+#endif
+
 	kobject_uevent(&s->kobj, KOBJ_ADD);
 	if (!unmergeable) {
 		/* Setup first alias */
@@ -5234,6 +5255,9 @@ static void sysfs_slab_remove(struct kmem_cache *s)
 		 */
 		return;
 
+#ifdef CONFIG_MEMCG_KMEM
+	kset_unregister(s->memcg_kset);
+#endif
 	kobject_uevent(&s->kobj, KOBJ_REMOVE);
 	kobject_del(&s->kobj);
 	kobject_put(&s->kobj);
-- 
cgit v1.2.3


From b3ca1c10d7b32fdfdfaf5484eda486323f52d9be Mon Sep 17 00:00:00 2001
From: Christoph Lameter <cl@linux.com>
Date: Mon, 7 Apr 2014 15:39:34 -0700
Subject: percpu: add raw_cpu_ops

The kernel has never been audited to ensure that this_cpu operations are
consistently used throughout the kernel.  The code generated in many
places can be improved through the use of this_cpu operations (which
uses a segment register for relocation of per cpu offsets instead of
performing address calculations).

The patch set also addresses various consistency issues in general with
the per cpu macros.

A. The semantics of __this_cpu_ptr() differs from this_cpu_ptr only
   because checks are skipped. This is typically shown through a raw_
   prefix. So this patch set changes the places where __this_cpu_ptr()
   is used to raw_cpu_ptr().

B. There has been the long term wish by some that __this_cpu operations
   would check for preemption. However, there are cases where preemption
   checks need to be skipped. This patch set adds raw_cpu operations that
   do not check for preemption and then adds preemption checks to the
   __this_cpu operations.

C. The use of __get_cpu_var is always a reference to a percpu variable
   that can also be handled via a this_cpu operation. This patch set
   replaces all uses of __get_cpu_var with this_cpu operations.

D. We can then use this_cpu RMW operations in various places replacing
   sequences of instructions by a single one.

E. The use of this_cpu operations throughout will allow other arches than
   x86 to implement optimized references and RMV operations to work with
   per cpu local data.

F. The use of this_cpu operations opens up the possibility to
   further optimize code that relies on synchronization through
   per cpu data.

The patch set works in a couple of stages:

I. Patch 1 adds the additional raw_cpu operations and raw_cpu_ptr().
    Also converts the existing __this_cpu_xx_# primitive in the x86
    code to raw_cpu_xx_#.

II. Patch 2-4 use the raw_cpu operations in places that would give
     us false positives once they are enabled.

III. Patch 5 adds preemption checks to __this_cpu operations to allow
    checking if preemption is properly disabled when these functions
    are used.

IV. Patches 6-20 are patches that simply replace uses of __get_cpu_var
   with this_cpu_ptr. They do not depend on any changes to the percpu
   code. No preemption tests are skipped if they are applied.

V. Patches 21-46 are conversion patches that use this_cpu operations
   in various kernel subsystems/drivers or arch code.

VI.  Patches 47/48 (not included in this series) remove no longer used
    functions (__this_cpu_ptr and __get_cpu_var).  These should only be
    applied after all the conversion patches have made it and after we
    have done additional passes through the kernel to ensure that none of
    the uses of these functions remain.

This patch (of 46):

The patches following this one will add preemption checks to __this_cpu
ops so we need to have an alternative way to use this_cpu operations
without preemption checks.

raw_cpu_ops will be the basis for all other ops since these will be the
operations that do not implement any checks.

Primitive operations are renamed by this patch from __this_cpu_xxx to
raw_cpu_xxxx.

Also change the uses of the x86 percpu primitives in preempt.h.
These depend directly on asm/percpu.h (header #include nesting issue).

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Christoph Lameter <cl@linux.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: "James E.J. Bottomley" <jejb@parisc-linux.org>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Alex Shi <alex.shi@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Bryan Wu <cooloney@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: David Daney <david.daney@cavium.com>
Cc: David Miller <davem@davemloft.net>
Cc: David S. Miller <davem@davemloft.net>
Cc: Dimitri Sivanich <sivanich@sgi.com>
Cc: Dipankar Sarma <dipankar@in.ibm.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: H. Peter Anvin <hpa@linux.intel.com>
Cc: Haavard Skinnemoen <hskinnemoen@gmail.com>
Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no>
Cc: Hedi Berriche <hedi@sgi.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Helge Deller <deller@gmx.de>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: Mike Travis <travis@sgi.com>
Cc: Neil Brown <neilb@suse.de>
Cc: Nicolas Pitre <nicolas.pitre@linaro.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Robert Richter <rric@kernel.org>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Russell King <rmk+kernel@arm.linux.org.uk>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Wim Van Sebroeck <wim@iguana.be>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/include/asm/percpu.h  |  98 ++++++------
 arch/x86/include/asm/preempt.h |  16 +-
 include/asm-generic/percpu.h   |  13 +-
 include/linux/percpu.h         | 331 ++++++++++++++++++++++++-----------------
 4 files changed, 260 insertions(+), 198 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 94220d14d5cc..851bcdc5db04 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -52,7 +52,7 @@
  * Compared to the generic __my_cpu_offset version, the following
  * saves one instruction and avoids clobbering a temp register.
  */
-#define __this_cpu_ptr(ptr)				\
+#define raw_cpu_ptr(ptr)				\
 ({							\
 	unsigned long tcp_ptr__;			\
 	__verify_pcpu_ptr(ptr);				\
@@ -362,25 +362,25 @@ do {									\
  */
 #define this_cpu_read_stable(var)	percpu_from_op("mov", var, "p" (&(var)))
 
-#define __this_cpu_read_1(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
-#define __this_cpu_read_2(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
-#define __this_cpu_read_4(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
-
-#define __this_cpu_write_1(pcp, val)	percpu_to_op("mov", (pcp), val)
-#define __this_cpu_write_2(pcp, val)	percpu_to_op("mov", (pcp), val)
-#define __this_cpu_write_4(pcp, val)	percpu_to_op("mov", (pcp), val)
-#define __this_cpu_add_1(pcp, val)	percpu_add_op((pcp), val)
-#define __this_cpu_add_2(pcp, val)	percpu_add_op((pcp), val)
-#define __this_cpu_add_4(pcp, val)	percpu_add_op((pcp), val)
-#define __this_cpu_and_1(pcp, val)	percpu_to_op("and", (pcp), val)
-#define __this_cpu_and_2(pcp, val)	percpu_to_op("and", (pcp), val)
-#define __this_cpu_and_4(pcp, val)	percpu_to_op("and", (pcp), val)
-#define __this_cpu_or_1(pcp, val)	percpu_to_op("or", (pcp), val)
-#define __this_cpu_or_2(pcp, val)	percpu_to_op("or", (pcp), val)
-#define __this_cpu_or_4(pcp, val)	percpu_to_op("or", (pcp), val)
-#define __this_cpu_xchg_1(pcp, val)	percpu_xchg_op(pcp, val)
-#define __this_cpu_xchg_2(pcp, val)	percpu_xchg_op(pcp, val)
-#define __this_cpu_xchg_4(pcp, val)	percpu_xchg_op(pcp, val)
+#define raw_cpu_read_1(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
+#define raw_cpu_read_2(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
+#define raw_cpu_read_4(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
+
+#define raw_cpu_write_1(pcp, val)	percpu_to_op("mov", (pcp), val)
+#define raw_cpu_write_2(pcp, val)	percpu_to_op("mov", (pcp), val)
+#define raw_cpu_write_4(pcp, val)	percpu_to_op("mov", (pcp), val)
+#define raw_cpu_add_1(pcp, val)		percpu_add_op((pcp), val)
+#define raw_cpu_add_2(pcp, val)		percpu_add_op((pcp), val)
+#define raw_cpu_add_4(pcp, val)		percpu_add_op((pcp), val)
+#define raw_cpu_and_1(pcp, val)		percpu_to_op("and", (pcp), val)
+#define raw_cpu_and_2(pcp, val)		percpu_to_op("and", (pcp), val)
+#define raw_cpu_and_4(pcp, val)		percpu_to_op("and", (pcp), val)
+#define raw_cpu_or_1(pcp, val)		percpu_to_op("or", (pcp), val)
+#define raw_cpu_or_2(pcp, val)		percpu_to_op("or", (pcp), val)
+#define raw_cpu_or_4(pcp, val)		percpu_to_op("or", (pcp), val)
+#define raw_cpu_xchg_1(pcp, val)	percpu_xchg_op(pcp, val)
+#define raw_cpu_xchg_2(pcp, val)	percpu_xchg_op(pcp, val)
+#define raw_cpu_xchg_4(pcp, val)	percpu_xchg_op(pcp, val)
 
 #define this_cpu_read_1(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
 #define this_cpu_read_2(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
@@ -401,16 +401,16 @@ do {									\
 #define this_cpu_xchg_2(pcp, nval)	percpu_xchg_op(pcp, nval)
 #define this_cpu_xchg_4(pcp, nval)	percpu_xchg_op(pcp, nval)
 
-#define __this_cpu_add_return_1(pcp, val) percpu_add_return_op(pcp, val)
-#define __this_cpu_add_return_2(pcp, val) percpu_add_return_op(pcp, val)
-#define __this_cpu_add_return_4(pcp, val) percpu_add_return_op(pcp, val)
-#define __this_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
-#define __this_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
-#define __this_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+#define raw_cpu_add_return_1(pcp, val)		percpu_add_return_op(pcp, val)
+#define raw_cpu_add_return_2(pcp, val)		percpu_add_return_op(pcp, val)
+#define raw_cpu_add_return_4(pcp, val)		percpu_add_return_op(pcp, val)
+#define raw_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+#define raw_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+#define raw_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
 
-#define this_cpu_add_return_1(pcp, val)	percpu_add_return_op(pcp, val)
-#define this_cpu_add_return_2(pcp, val)	percpu_add_return_op(pcp, val)
-#define this_cpu_add_return_4(pcp, val)	percpu_add_return_op(pcp, val)
+#define this_cpu_add_return_1(pcp, val)		percpu_add_return_op(pcp, val)
+#define this_cpu_add_return_2(pcp, val)		percpu_add_return_op(pcp, val)
+#define this_cpu_add_return_4(pcp, val)		percpu_add_return_op(pcp, val)
 #define this_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
 #define this_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
 #define this_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
@@ -427,7 +427,7 @@ do {									\
 	__ret;								\
 })
 
-#define __this_cpu_cmpxchg_double_4	percpu_cmpxchg8b_double
+#define raw_cpu_cmpxchg_double_4	percpu_cmpxchg8b_double
 #define this_cpu_cmpxchg_double_4	percpu_cmpxchg8b_double
 #endif /* CONFIG_X86_CMPXCHG64 */
 
@@ -436,22 +436,22 @@ do {									\
  * 32 bit must fall back to generic operations.
  */
 #ifdef CONFIG_X86_64
-#define __this_cpu_read_8(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
-#define __this_cpu_write_8(pcp, val)	percpu_to_op("mov", (pcp), val)
-#define __this_cpu_add_8(pcp, val)	percpu_add_op((pcp), val)
-#define __this_cpu_and_8(pcp, val)	percpu_to_op("and", (pcp), val)
-#define __this_cpu_or_8(pcp, val)	percpu_to_op("or", (pcp), val)
-#define __this_cpu_add_return_8(pcp, val) percpu_add_return_op(pcp, val)
-#define __this_cpu_xchg_8(pcp, nval)	percpu_xchg_op(pcp, nval)
-#define __this_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
-
-#define this_cpu_read_8(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
-#define this_cpu_write_8(pcp, val)	percpu_to_op("mov", (pcp), val)
-#define this_cpu_add_8(pcp, val)	percpu_add_op((pcp), val)
-#define this_cpu_and_8(pcp, val)	percpu_to_op("and", (pcp), val)
-#define this_cpu_or_8(pcp, val)		percpu_to_op("or", (pcp), val)
-#define this_cpu_add_return_8(pcp, val)	percpu_add_return_op(pcp, val)
-#define this_cpu_xchg_8(pcp, nval)	percpu_xchg_op(pcp, nval)
+#define raw_cpu_read_8(pcp)			percpu_from_op("mov", (pcp), "m"(pcp))
+#define raw_cpu_write_8(pcp, val)		percpu_to_op("mov", (pcp), val)
+#define raw_cpu_add_8(pcp, val)			percpu_add_op((pcp), val)
+#define raw_cpu_and_8(pcp, val)			percpu_to_op("and", (pcp), val)
+#define raw_cpu_or_8(pcp, val)			percpu_to_op("or", (pcp), val)
+#define raw_cpu_add_return_8(pcp, val)		percpu_add_return_op(pcp, val)
+#define raw_cpu_xchg_8(pcp, nval)		percpu_xchg_op(pcp, nval)
+#define raw_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+
+#define this_cpu_read_8(pcp)			percpu_from_op("mov", (pcp), "m"(pcp))
+#define this_cpu_write_8(pcp, val)		percpu_to_op("mov", (pcp), val)
+#define this_cpu_add_8(pcp, val)		percpu_add_op((pcp), val)
+#define this_cpu_and_8(pcp, val)		percpu_to_op("and", (pcp), val)
+#define this_cpu_or_8(pcp, val)			percpu_to_op("or", (pcp), val)
+#define this_cpu_add_return_8(pcp, val)		percpu_add_return_op(pcp, val)
+#define this_cpu_xchg_8(pcp, nval)		percpu_xchg_op(pcp, nval)
 #define this_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
 
 /*
@@ -474,7 +474,7 @@ do {									\
 	__ret;								\
 })
 
-#define __this_cpu_cmpxchg_double_8	percpu_cmpxchg16b_double
+#define raw_cpu_cmpxchg_double_8	percpu_cmpxchg16b_double
 #define this_cpu_cmpxchg_double_8	percpu_cmpxchg16b_double
 
 #endif
@@ -495,9 +495,9 @@ static __always_inline int x86_this_cpu_constant_test_bit(unsigned int nr,
 	unsigned long __percpu *a = (unsigned long *)addr + nr / BITS_PER_LONG;
 
 #ifdef CONFIG_X86_64
-	return ((1UL << (nr % BITS_PER_LONG)) & __this_cpu_read_8(*a)) != 0;
+	return ((1UL << (nr % BITS_PER_LONG)) & raw_cpu_read_8(*a)) != 0;
 #else
-	return ((1UL << (nr % BITS_PER_LONG)) & __this_cpu_read_4(*a)) != 0;
+	return ((1UL << (nr % BITS_PER_LONG)) & raw_cpu_read_4(*a)) != 0;
 #endif
 }
 
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index c8b051933b1b..7024c12f7bfe 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -19,12 +19,12 @@ DECLARE_PER_CPU(int, __preempt_count);
  */
 static __always_inline int preempt_count(void)
 {
-	return __this_cpu_read_4(__preempt_count) & ~PREEMPT_NEED_RESCHED;
+	return raw_cpu_read_4(__preempt_count) & ~PREEMPT_NEED_RESCHED;
 }
 
 static __always_inline void preempt_count_set(int pc)
 {
-	__this_cpu_write_4(__preempt_count, pc);
+	raw_cpu_write_4(__preempt_count, pc);
 }
 
 /*
@@ -53,17 +53,17 @@ static __always_inline void preempt_count_set(int pc)
 
 static __always_inline void set_preempt_need_resched(void)
 {
-	__this_cpu_and_4(__preempt_count, ~PREEMPT_NEED_RESCHED);
+	raw_cpu_and_4(__preempt_count, ~PREEMPT_NEED_RESCHED);
 }
 
 static __always_inline void clear_preempt_need_resched(void)
 {
-	__this_cpu_or_4(__preempt_count, PREEMPT_NEED_RESCHED);
+	raw_cpu_or_4(__preempt_count, PREEMPT_NEED_RESCHED);
 }
 
 static __always_inline bool test_preempt_need_resched(void)
 {
-	return !(__this_cpu_read_4(__preempt_count) & PREEMPT_NEED_RESCHED);
+	return !(raw_cpu_read_4(__preempt_count) & PREEMPT_NEED_RESCHED);
 }
 
 /*
@@ -72,12 +72,12 @@ static __always_inline bool test_preempt_need_resched(void)
 
 static __always_inline void __preempt_count_add(int val)
 {
-	__this_cpu_add_4(__preempt_count, val);
+	raw_cpu_add_4(__preempt_count, val);
 }
 
 static __always_inline void __preempt_count_sub(int val)
 {
-	__this_cpu_add_4(__preempt_count, -val);
+	raw_cpu_add_4(__preempt_count, -val);
 }
 
 /*
@@ -95,7 +95,7 @@ static __always_inline bool __preempt_count_dec_and_test(void)
  */
 static __always_inline bool should_resched(void)
 {
-	return unlikely(!__this_cpu_read_4(__preempt_count));
+	return unlikely(!raw_cpu_read_4(__preempt_count));
 }
 
 #ifdef CONFIG_PREEMPT
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index d17784ea37ff..0703aa75b5e8 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -56,17 +56,17 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
 #define per_cpu(var, cpu) \
 	(*SHIFT_PERCPU_PTR(&(var), per_cpu_offset(cpu)))
 
-#ifndef __this_cpu_ptr
-#define __this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, __my_cpu_offset)
+#ifndef raw_cpu_ptr
+#define raw_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, __my_cpu_offset)
 #endif
 #ifdef CONFIG_DEBUG_PREEMPT
 #define this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, my_cpu_offset)
 #else
-#define this_cpu_ptr(ptr) __this_cpu_ptr(ptr)
+#define this_cpu_ptr(ptr) raw_cpu_ptr(ptr)
 #endif
 
 #define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
-#define __raw_get_cpu_var(var) (*__this_cpu_ptr(&(var)))
+#define __raw_get_cpu_var(var) (*raw_cpu_ptr(&(var)))
 
 #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
 extern void setup_per_cpu_areas(void);
@@ -83,7 +83,7 @@ extern void setup_per_cpu_areas(void);
 #define __get_cpu_var(var)	(*VERIFY_PERCPU_PTR(&(var)))
 #define __raw_get_cpu_var(var)	(*VERIFY_PERCPU_PTR(&(var)))
 #define this_cpu_ptr(ptr)	per_cpu_ptr(ptr, 0)
-#define __this_cpu_ptr(ptr)	this_cpu_ptr(ptr)
+#define raw_cpu_ptr(ptr)	this_cpu_ptr(ptr)
 
 #endif	/* SMP */
 
@@ -122,4 +122,7 @@ extern void setup_per_cpu_areas(void);
 #define PER_CPU_DEF_ATTRIBUTES
 #endif
 
+/* Keep until we have removed all uses of __this_cpu_ptr */
+#define __this_cpu_ptr raw_cpu_ptr
+
 #endif /* _ASM_GENERIC_PERCPU_H_ */
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index e3817d2441b6..4e4d2afcc0c7 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -243,6 +243,8 @@ do {									\
 } while (0)
 
 /*
+ * this_cpu operations (C) 2008-2013 Christoph Lameter <cl@linux.com>
+ *
  * Optimized manipulation for memory allocated through the per cpu
  * allocator or for addresses of per cpu variables.
  *
@@ -296,7 +298,7 @@ do {									\
 do {									\
 	unsigned long flags;						\
 	raw_local_irq_save(flags);					\
-	*__this_cpu_ptr(&(pcp)) op val;					\
+	*raw_cpu_ptr(&(pcp)) op val;					\
 	raw_local_irq_restore(flags);					\
 } while (0)
 
@@ -381,8 +383,8 @@ do {									\
 	typeof(pcp) ret__;						\
 	unsigned long flags;						\
 	raw_local_irq_save(flags);					\
-	__this_cpu_add(pcp, val);					\
-	ret__ = __this_cpu_read(pcp);					\
+	raw_cpu_add(pcp, val);					\
+	ret__ = raw_cpu_read(pcp);					\
 	raw_local_irq_restore(flags);					\
 	ret__;								\
 })
@@ -411,8 +413,8 @@ do {									\
 ({	typeof(pcp) ret__;						\
 	unsigned long flags;						\
 	raw_local_irq_save(flags);					\
-	ret__ = __this_cpu_read(pcp);					\
-	__this_cpu_write(pcp, nval);					\
+	ret__ = raw_cpu_read(pcp);					\
+	raw_cpu_write(pcp, nval);					\
 	raw_local_irq_restore(flags);					\
 	ret__;								\
 })
@@ -439,9 +441,9 @@ do {									\
 	typeof(pcp) ret__;						\
 	unsigned long flags;						\
 	raw_local_irq_save(flags);					\
-	ret__ = __this_cpu_read(pcp);					\
+	ret__ = raw_cpu_read(pcp);					\
 	if (ret__ == (oval))						\
-		__this_cpu_write(pcp, nval);				\
+		raw_cpu_write(pcp, nval);				\
 	raw_local_irq_restore(flags);					\
 	ret__;								\
 })
@@ -476,7 +478,7 @@ do {									\
 	int ret__;							\
 	unsigned long flags;						\
 	raw_local_irq_save(flags);					\
-	ret__ = __this_cpu_generic_cmpxchg_double(pcp1, pcp2,		\
+	ret__ = raw_cpu_generic_cmpxchg_double(pcp1, pcp2,		\
 			oval1, oval2, nval1, nval2);			\
 	raw_local_irq_restore(flags);					\
 	ret__;								\
@@ -504,12 +506,8 @@ do {									\
 #endif
 
 /*
- * Generic percpu operations for context that are safe from preemption/interrupts.
- * Either we do not care about races or the caller has the
- * responsibility of handling preemption/interrupt issues. Arch code can still
- * override these instructions since the arch per cpu code may be more
- * efficient and may actually get race freeness for free (that is the
- * case for x86 for example).
+ * Generic percpu operations for contexts where we do not want to do
+ * any checks for preemptiosn.
  *
  * If there is no other protection through preempt disable and/or
  * disabling interupts then one of these RMW operations can show unexpected
@@ -517,211 +515,272 @@ do {									\
  * or an interrupt occurred and the same percpu variable was modified from
  * the interrupt context.
  */
-#ifndef __this_cpu_read
-# ifndef __this_cpu_read_1
-#  define __this_cpu_read_1(pcp)	(*__this_cpu_ptr(&(pcp)))
+#ifndef raw_cpu_read
+# ifndef raw_cpu_read_1
+#  define raw_cpu_read_1(pcp)	(*raw_cpu_ptr(&(pcp)))
 # endif
-# ifndef __this_cpu_read_2
-#  define __this_cpu_read_2(pcp)	(*__this_cpu_ptr(&(pcp)))
+# ifndef raw_cpu_read_2
+#  define raw_cpu_read_2(pcp)	(*raw_cpu_ptr(&(pcp)))
 # endif
-# ifndef __this_cpu_read_4
-#  define __this_cpu_read_4(pcp)	(*__this_cpu_ptr(&(pcp)))
+# ifndef raw_cpu_read_4
+#  define raw_cpu_read_4(pcp)	(*raw_cpu_ptr(&(pcp)))
 # endif
-# ifndef __this_cpu_read_8
-#  define __this_cpu_read_8(pcp)	(*__this_cpu_ptr(&(pcp)))
+# ifndef raw_cpu_read_8
+#  define raw_cpu_read_8(pcp)	(*raw_cpu_ptr(&(pcp)))
 # endif
-# define __this_cpu_read(pcp)	__pcpu_size_call_return(__this_cpu_read_, (pcp))
+# define raw_cpu_read(pcp)	__pcpu_size_call_return(raw_cpu_read_, (pcp))
 #endif
 
-#define __this_cpu_generic_to_op(pcp, val, op)				\
+#define raw_cpu_generic_to_op(pcp, val, op)				\
 do {									\
-	*__this_cpu_ptr(&(pcp)) op val;					\
+	*raw_cpu_ptr(&(pcp)) op val;					\
 } while (0)
 
-#ifndef __this_cpu_write
-# ifndef __this_cpu_write_1
-#  define __this_cpu_write_1(pcp, val)	__this_cpu_generic_to_op((pcp), (val), =)
+
+#ifndef raw_cpu_write
+# ifndef raw_cpu_write_1
+#  define raw_cpu_write_1(pcp, val)	raw_cpu_generic_to_op((pcp), (val), =)
 # endif
-# ifndef __this_cpu_write_2
-#  define __this_cpu_write_2(pcp, val)	__this_cpu_generic_to_op((pcp), (val), =)
+# ifndef raw_cpu_write_2
+#  define raw_cpu_write_2(pcp, val)	raw_cpu_generic_to_op((pcp), (val), =)
 # endif
-# ifndef __this_cpu_write_4
-#  define __this_cpu_write_4(pcp, val)	__this_cpu_generic_to_op((pcp), (val), =)
+# ifndef raw_cpu_write_4
+#  define raw_cpu_write_4(pcp, val)	raw_cpu_generic_to_op((pcp), (val), =)
 # endif
-# ifndef __this_cpu_write_8
-#  define __this_cpu_write_8(pcp, val)	__this_cpu_generic_to_op((pcp), (val), =)
+# ifndef raw_cpu_write_8
+#  define raw_cpu_write_8(pcp, val)	raw_cpu_generic_to_op((pcp), (val), =)
 # endif
-# define __this_cpu_write(pcp, val)	__pcpu_size_call(__this_cpu_write_, (pcp), (val))
+# define raw_cpu_write(pcp, val)	__pcpu_size_call(raw_cpu_write_, (pcp), (val))
 #endif
 
-#ifndef __this_cpu_add
-# ifndef __this_cpu_add_1
-#  define __this_cpu_add_1(pcp, val)	__this_cpu_generic_to_op((pcp), (val), +=)
+#ifndef raw_cpu_add
+# ifndef raw_cpu_add_1
+#  define raw_cpu_add_1(pcp, val)	raw_cpu_generic_to_op((pcp), (val), +=)
 # endif
-# ifndef __this_cpu_add_2
-#  define __this_cpu_add_2(pcp, val)	__this_cpu_generic_to_op((pcp), (val), +=)
+# ifndef raw_cpu_add_2
+#  define raw_cpu_add_2(pcp, val)	raw_cpu_generic_to_op((pcp), (val), +=)
 # endif
-# ifndef __this_cpu_add_4
-#  define __this_cpu_add_4(pcp, val)	__this_cpu_generic_to_op((pcp), (val), +=)
+# ifndef raw_cpu_add_4
+#  define raw_cpu_add_4(pcp, val)	raw_cpu_generic_to_op((pcp), (val), +=)
 # endif
-# ifndef __this_cpu_add_8
-#  define __this_cpu_add_8(pcp, val)	__this_cpu_generic_to_op((pcp), (val), +=)
+# ifndef raw_cpu_add_8
+#  define raw_cpu_add_8(pcp, val)	raw_cpu_generic_to_op((pcp), (val), +=)
 # endif
-# define __this_cpu_add(pcp, val)	__pcpu_size_call(__this_cpu_add_, (pcp), (val))
+# define raw_cpu_add(pcp, val)	__pcpu_size_call(raw_cpu_add_, (pcp), (val))
 #endif
 
-#ifndef __this_cpu_sub
-# define __this_cpu_sub(pcp, val)	__this_cpu_add((pcp), -(typeof(pcp))(val))
+#ifndef raw_cpu_sub
+# define raw_cpu_sub(pcp, val)	raw_cpu_add((pcp), -(val))
 #endif
 
-#ifndef __this_cpu_inc
-# define __this_cpu_inc(pcp)		__this_cpu_add((pcp), 1)
+#ifndef raw_cpu_inc
+# define raw_cpu_inc(pcp)		raw_cpu_add((pcp), 1)
 #endif
 
-#ifndef __this_cpu_dec
-# define __this_cpu_dec(pcp)		__this_cpu_sub((pcp), 1)
+#ifndef raw_cpu_dec
+# define raw_cpu_dec(pcp)		raw_cpu_sub((pcp), 1)
 #endif
 
-#ifndef __this_cpu_and
-# ifndef __this_cpu_and_1
-#  define __this_cpu_and_1(pcp, val)	__this_cpu_generic_to_op((pcp), (val), &=)
+#ifndef raw_cpu_and
+# ifndef raw_cpu_and_1
+#  define raw_cpu_and_1(pcp, val)	raw_cpu_generic_to_op((pcp), (val), &=)
 # endif
-# ifndef __this_cpu_and_2
-#  define __this_cpu_and_2(pcp, val)	__this_cpu_generic_to_op((pcp), (val), &=)
+# ifndef raw_cpu_and_2
+#  define raw_cpu_and_2(pcp, val)	raw_cpu_generic_to_op((pcp), (val), &=)
 # endif
-# ifndef __this_cpu_and_4
-#  define __this_cpu_and_4(pcp, val)	__this_cpu_generic_to_op((pcp), (val), &=)
+# ifndef raw_cpu_and_4
+#  define raw_cpu_and_4(pcp, val)	raw_cpu_generic_to_op((pcp), (val), &=)
 # endif
-# ifndef __this_cpu_and_8
-#  define __this_cpu_and_8(pcp, val)	__this_cpu_generic_to_op((pcp), (val), &=)
+# ifndef raw_cpu_and_8
+#  define raw_cpu_and_8(pcp, val)	raw_cpu_generic_to_op((pcp), (val), &=)
 # endif
-# define __this_cpu_and(pcp, val)	__pcpu_size_call(__this_cpu_and_, (pcp), (val))
+# define raw_cpu_and(pcp, val)	__pcpu_size_call(raw_cpu_and_, (pcp), (val))
 #endif
 
-#ifndef __this_cpu_or
-# ifndef __this_cpu_or_1
-#  define __this_cpu_or_1(pcp, val)	__this_cpu_generic_to_op((pcp), (val), |=)
+#ifndef raw_cpu_or
+# ifndef raw_cpu_or_1
+#  define raw_cpu_or_1(pcp, val)	raw_cpu_generic_to_op((pcp), (val), |=)
 # endif
-# ifndef __this_cpu_or_2
-#  define __this_cpu_or_2(pcp, val)	__this_cpu_generic_to_op((pcp), (val), |=)
+# ifndef raw_cpu_or_2
+#  define raw_cpu_or_2(pcp, val)	raw_cpu_generic_to_op((pcp), (val), |=)
 # endif
-# ifndef __this_cpu_or_4
-#  define __this_cpu_or_4(pcp, val)	__this_cpu_generic_to_op((pcp), (val), |=)
+# ifndef raw_cpu_or_4
+#  define raw_cpu_or_4(pcp, val)	raw_cpu_generic_to_op((pcp), (val), |=)
 # endif
-# ifndef __this_cpu_or_8
-#  define __this_cpu_or_8(pcp, val)	__this_cpu_generic_to_op((pcp), (val), |=)
+# ifndef raw_cpu_or_8
+#  define raw_cpu_or_8(pcp, val)	raw_cpu_generic_to_op((pcp), (val), |=)
 # endif
-# define __this_cpu_or(pcp, val)	__pcpu_size_call(__this_cpu_or_, (pcp), (val))
+# define raw_cpu_or(pcp, val)	__pcpu_size_call(raw_cpu_or_, (pcp), (val))
 #endif
 
-#define __this_cpu_generic_add_return(pcp, val)				\
+#define raw_cpu_generic_add_return(pcp, val)				\
 ({									\
-	__this_cpu_add(pcp, val);					\
-	__this_cpu_read(pcp);						\
+	raw_cpu_add(pcp, val);						\
+	raw_cpu_read(pcp);						\
 })
 
-#ifndef __this_cpu_add_return
-# ifndef __this_cpu_add_return_1
-#  define __this_cpu_add_return_1(pcp, val)	__this_cpu_generic_add_return(pcp, val)
+#ifndef raw_cpu_add_return
+# ifndef raw_cpu_add_return_1
+#  define raw_cpu_add_return_1(pcp, val)	raw_cpu_generic_add_return(pcp, val)
 # endif
-# ifndef __this_cpu_add_return_2
-#  define __this_cpu_add_return_2(pcp, val)	__this_cpu_generic_add_return(pcp, val)
+# ifndef raw_cpu_add_return_2
+#  define raw_cpu_add_return_2(pcp, val)	raw_cpu_generic_add_return(pcp, val)
 # endif
-# ifndef __this_cpu_add_return_4
-#  define __this_cpu_add_return_4(pcp, val)	__this_cpu_generic_add_return(pcp, val)
+# ifndef raw_cpu_add_return_4
+#  define raw_cpu_add_return_4(pcp, val)	raw_cpu_generic_add_return(pcp, val)
 # endif
-# ifndef __this_cpu_add_return_8
-#  define __this_cpu_add_return_8(pcp, val)	__this_cpu_generic_add_return(pcp, val)
+# ifndef raw_cpu_add_return_8
+#  define raw_cpu_add_return_8(pcp, val)	raw_cpu_generic_add_return(pcp, val)
 # endif
-# define __this_cpu_add_return(pcp, val)	\
-	__pcpu_size_call_return2(__this_cpu_add_return_, pcp, val)
+# define raw_cpu_add_return(pcp, val)	\
+	__pcpu_size_call_return2(raw_add_return_, pcp, val)
 #endif
 
-#define __this_cpu_sub_return(pcp, val)	__this_cpu_add_return(pcp, -(typeof(pcp))(val))
-#define __this_cpu_inc_return(pcp)	__this_cpu_add_return(pcp, 1)
-#define __this_cpu_dec_return(pcp)	__this_cpu_add_return(pcp, -1)
+#define raw_cpu_sub_return(pcp, val)	raw_cpu_add_return(pcp, -(typeof(pcp))(val))
+#define raw_cpu_inc_return(pcp)	raw_cpu_add_return(pcp, 1)
+#define raw_cpu_dec_return(pcp)	raw_cpu_add_return(pcp, -1)
 
-#define __this_cpu_generic_xchg(pcp, nval)				\
+#define raw_cpu_generic_xchg(pcp, nval)					\
 ({	typeof(pcp) ret__;						\
-	ret__ = __this_cpu_read(pcp);					\
-	__this_cpu_write(pcp, nval);					\
+	ret__ = raw_cpu_read(pcp);					\
+	raw_cpu_write(pcp, nval);					\
 	ret__;								\
 })
 
-#ifndef __this_cpu_xchg
-# ifndef __this_cpu_xchg_1
-#  define __this_cpu_xchg_1(pcp, nval)	__this_cpu_generic_xchg(pcp, nval)
+#ifndef raw_cpu_xchg
+# ifndef raw_cpu_xchg_1
+#  define raw_cpu_xchg_1(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
 # endif
-# ifndef __this_cpu_xchg_2
-#  define __this_cpu_xchg_2(pcp, nval)	__this_cpu_generic_xchg(pcp, nval)
+# ifndef raw_cpu_xchg_2
+#  define raw_cpu_xchg_2(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
 # endif
-# ifndef __this_cpu_xchg_4
-#  define __this_cpu_xchg_4(pcp, nval)	__this_cpu_generic_xchg(pcp, nval)
+# ifndef raw_cpu_xchg_4
+#  define raw_cpu_xchg_4(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
 # endif
-# ifndef __this_cpu_xchg_8
-#  define __this_cpu_xchg_8(pcp, nval)	__this_cpu_generic_xchg(pcp, nval)
+# ifndef raw_cpu_xchg_8
+#  define raw_cpu_xchg_8(pcp, nval)	raw_cpu_generic_xchg(pcp, nval)
 # endif
-# define __this_cpu_xchg(pcp, nval)	\
-	__pcpu_size_call_return2(__this_cpu_xchg_, (pcp), nval)
+# define raw_cpu_xchg(pcp, nval)	\
+	__pcpu_size_call_return2(raw_cpu_xchg_, (pcp), nval)
 #endif
 
-#define __this_cpu_generic_cmpxchg(pcp, oval, nval)			\
+#define raw_cpu_generic_cmpxchg(pcp, oval, nval)			\
 ({									\
 	typeof(pcp) ret__;						\
-	ret__ = __this_cpu_read(pcp);					\
+	ret__ = raw_cpu_read(pcp);					\
 	if (ret__ == (oval))						\
-		__this_cpu_write(pcp, nval);				\
+		raw_cpu_write(pcp, nval);				\
 	ret__;								\
 })
 
-#ifndef __this_cpu_cmpxchg
-# ifndef __this_cpu_cmpxchg_1
-#  define __this_cpu_cmpxchg_1(pcp, oval, nval)	__this_cpu_generic_cmpxchg(pcp, oval, nval)
+#ifndef raw_cpu_cmpxchg
+# ifndef raw_cpu_cmpxchg_1
+#  define raw_cpu_cmpxchg_1(pcp, oval, nval)	raw_cpu_generic_cmpxchg(pcp, oval, nval)
 # endif
-# ifndef __this_cpu_cmpxchg_2
-#  define __this_cpu_cmpxchg_2(pcp, oval, nval)	__this_cpu_generic_cmpxchg(pcp, oval, nval)
+# ifndef raw_cpu_cmpxchg_2
+#  define raw_cpu_cmpxchg_2(pcp, oval, nval)	raw_cpu_generic_cmpxchg(pcp, oval, nval)
 # endif
-# ifndef __this_cpu_cmpxchg_4
-#  define __this_cpu_cmpxchg_4(pcp, oval, nval)	__this_cpu_generic_cmpxchg(pcp, oval, nval)
+# ifndef raw_cpu_cmpxchg_4
+#  define raw_cpu_cmpxchg_4(pcp, oval, nval)	raw_cpu_generic_cmpxchg(pcp, oval, nval)
 # endif
-# ifndef __this_cpu_cmpxchg_8
-#  define __this_cpu_cmpxchg_8(pcp, oval, nval)	__this_cpu_generic_cmpxchg(pcp, oval, nval)
+# ifndef raw_cpu_cmpxchg_8
+#  define raw_cpu_cmpxchg_8(pcp, oval, nval)	raw_cpu_generic_cmpxchg(pcp, oval, nval)
 # endif
-# define __this_cpu_cmpxchg(pcp, oval, nval)	\
-	__pcpu_size_call_return2(__this_cpu_cmpxchg_, pcp, oval, nval)
+# define raw_cpu_cmpxchg(pcp, oval, nval)	\
+	__pcpu_size_call_return2(raw_cpu_cmpxchg_, pcp, oval, nval)
 #endif
 
-#define __this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+#define raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
 ({									\
 	int __ret = 0;							\
-	if (__this_cpu_read(pcp1) == (oval1) &&				\
-			 __this_cpu_read(pcp2)  == (oval2)) {		\
-		__this_cpu_write(pcp1, (nval1));			\
-		__this_cpu_write(pcp2, (nval2));			\
+	if (raw_cpu_read(pcp1) == (oval1) &&				\
+			 raw_cpu_read(pcp2)  == (oval2)) {		\
+		raw_cpu_write(pcp1, (nval1));				\
+		raw_cpu_write(pcp2, (nval2));				\
 		__ret = 1;						\
 	}								\
 	(__ret);							\
 })
 
-#ifndef __this_cpu_cmpxchg_double
-# ifndef __this_cpu_cmpxchg_double_1
-#  define __this_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	__this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+#ifndef raw_cpu_cmpxchg_double
+# ifndef raw_cpu_cmpxchg_double_1
+#  define raw_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
 # endif
-# ifndef __this_cpu_cmpxchg_double_2
-#  define __this_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	__this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# ifndef raw_cpu_cmpxchg_double_2
+#  define raw_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
 # endif
-# ifndef __this_cpu_cmpxchg_double_4
-#  define __this_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	__this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# ifndef raw_cpu_cmpxchg_double_4
+#  define raw_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
 # endif
-# ifndef __this_cpu_cmpxchg_double_8
-#  define __this_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	__this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+# ifndef raw_cpu_cmpxchg_double_8
+#  define raw_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
 # endif
+# define raw_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
+	__pcpu_double_call_return_bool(raw_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2))
+#endif
+
+/*
+ * Generic percpu operations for context that are safe from preemption/interrupts.
+ * Checks will be added here soon.
+ */
+#ifndef __this_cpu_read
+# define __this_cpu_read(pcp)	__pcpu_size_call_return(raw_cpu_read_, (pcp))
+#endif
+
+#ifndef __this_cpu_write
+# define __this_cpu_write(pcp, val)	__pcpu_size_call(raw_cpu_write_, (pcp), (val))
+#endif
+
+#ifndef __this_cpu_add
+# define __this_cpu_add(pcp, val)	__pcpu_size_call(raw_cpu_add_, (pcp), (val))
+#endif
+
+#ifndef __this_cpu_sub
+# define __this_cpu_sub(pcp, val)	__this_cpu_add((pcp), -(typeof(pcp))(val))
+#endif
+
+#ifndef __this_cpu_inc
+# define __this_cpu_inc(pcp)		__this_cpu_add((pcp), 1)
+#endif
+
+#ifndef __this_cpu_dec
+# define __this_cpu_dec(pcp)		__this_cpu_sub((pcp), 1)
+#endif
+
+#ifndef __this_cpu_and
+# define __this_cpu_and(pcp, val)	__pcpu_size_call(raw_cpu_and_, (pcp), (val))
+#endif
+
+#ifndef __this_cpu_or
+# define __this_cpu_or(pcp, val)	__pcpu_size_call(raw_cpu_or_, (pcp), (val))
+#endif
+
+#ifndef __this_cpu_add_return
+# define __this_cpu_add_return(pcp, val)	\
+	__pcpu_size_call_return2(raw_cpu_add_return_, pcp, val)
+#endif
+
+#define __this_cpu_sub_return(pcp, val)	__this_cpu_add_return(pcp, -(typeof(pcp))(val))
+#define __this_cpu_inc_return(pcp)	__this_cpu_add_return(pcp, 1)
+#define __this_cpu_dec_return(pcp)	__this_cpu_add_return(pcp, -1)
+
+#ifndef __this_cpu_xchg
+# define __this_cpu_xchg(pcp, nval)	\
+	__pcpu_size_call_return2(raw_cpu_xchg_, (pcp), nval)
+#endif
+
+#ifndef __this_cpu_cmpxchg
+# define __this_cpu_cmpxchg(pcp, oval, nval)	\
+	__pcpu_size_call_return2(raw_cpu_cmpxchg_, pcp, oval, nval)
+#endif
+
+#ifndef __this_cpu_cmpxchg_double
 # define __this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	__pcpu_double_call_return_bool(__this_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2))
+	__pcpu_double_call_return_bool(raw_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2))
 #endif
 
 #endif /* __LINUX_PERCPU_H */
-- 
cgit v1.2.3


From dc322a99d31fff5d3f8acfa061ad033953efdebe Mon Sep 17 00:00:00 2001
From: Christoph Lameter <cl@linux.com>
Date: Mon, 7 Apr 2014 15:39:38 -0700
Subject: mm: use raw_cpu ops for determining current NUMA node

With the preempt checking logic for __this_cpu_ops we will get false
positives from locations in the code that use numa_node_id.

Before the __this_cpu ops where introduced there were no checks for
preemption present either.  smp_raw_processor_id() was used.  See

  http://www.spinics.net/lists/linux-numa/msg00641.html

Therefore we need to use raw_cpu_read here to avoid false postives.

Note that this issue has been discussed in prior years.  If the process
changes nodes after retrieving the current numa node then that is
acceptable since most uses of numa_node etc are for optimization and not
for correctness.

There were suggestions to implement a raw_numa_node_id in order to do
preempt checks for numa_node_id as well.  But I think we better defer
that to another patch since that would mean investigating how
numa_node_id() is used throughout the kernel which would increase the
scope of this patchset significantly.  After all preemption was never
checked before when numa_node_id() was used.

Some sample traces:

__this_cpu_read operation in preemptible [00000000] code: login/1456
caller is __this_cpu_preempt_check+0x2b/0x2d
CPU: 0 PID: 1456 Comm: login Not tainted 3.12.0-rc4-cl-00062-g2fe80d3-dirty #185
Call Trace:
  dump_stack+0x4e/0x82
  check_preemption_disabled+0xc5/0xe0
  __this_cpu_preempt_check+0x2b/0x2d
  get_task_policy+0x1d/0x49
  get_vma_policy+0x14/0x76
  alloc_pages_vma+0x35/0xff
  handle_mm_fault+0x290/0x73b
  __do_page_fault+0x3fe/0x44d
  do_page_fault+0x9/0xc
  page_fault+0x22/0x30
  generic_file_aio_read+0x38e/0x624
  do_sync_read+0x54/0x73
  vfs_read+0x9d/0x12a
  SyS_read+0x47/0x7e
  cstar_dispatch+0x7/0x23

caller is __this_cpu_preempt_check+0x2b/0x2d
CPU: 0 PID: 1456 Comm: login Not tainted 3.12.0-rc4-cl-00062-g2fe80d3-dirty #185
Call Trace:
  dump_stack+0x4e/0x82
  check_preemption_disabled+0xc5/0xe0
  __this_cpu_preempt_check+0x2b/0x2d
  alloc_pages_current+0x8f/0xbc
  __page_cache_alloc+0xb/0xd
  __do_page_cache_readahead+0xf4/0x219
  ra_submit+0x1c/0x20
  ondemand_readahead+0x28c/0x2b4
  page_cache_sync_readahead+0x38/0x3a
  generic_file_aio_read+0x261/0x624
  do_sync_read+0x54/0x73
  vfs_read+0x9d/0x12a
  SyS_read+0x47/0x7e
  cstar_dispatch+0x7/0x23

Signed-off-by: Christoph Lameter <cl@linux.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: Alex Shi <alex.shi@intel.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/topology.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/topology.h b/include/linux/topology.h
index 12ae6ce997d6..7062330a1329 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -188,7 +188,7 @@ DECLARE_PER_CPU(int, numa_node);
 /* Returns the number of the current Node. */
 static inline int numa_node_id(void)
 {
-	return __this_cpu_read(numa_node);
+	return raw_cpu_read(numa_node);
 }
 #endif
 
@@ -245,7 +245,7 @@ static inline void set_numa_mem(int node)
 /* Returns the number of the nearest Node with memory */
 static inline int numa_mem_id(void)
 {
-	return __this_cpu_read(_numa_mem_);
+	return raw_cpu_read(_numa_mem_);
 }
 #endif
 
-- 
cgit v1.2.3


From 293b6a4c875c3b49853bff7de99954f49f59aa75 Mon Sep 17 00:00:00 2001
From: Christoph Lameter <cl@linux.com>
Date: Mon, 7 Apr 2014 15:39:43 -0700
Subject: vmstat: use raw_cpu_ops to avoid false positives on preemption checks

vm counters are allowed to be racy.  Use raw_cpu_ops to avoid the
local_irq_disable overhead and to avoid preemption checks which will be
added to the __this_cpu operations.

[akpm@linux-foundation.org: Add comment.  Again.]
Signed-off-by: Christoph Lameter <cl@linux.com>
Reported-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/vmstat.h | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index ea4476157e00..45c9cd1daf7a 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -27,9 +27,13 @@ struct vm_event_state {
 
 DECLARE_PER_CPU(struct vm_event_state, vm_event_states);
 
+/*
+ * vm counters are allowed to be racy. Use raw_cpu_ops to avoid the
+ * local_irq_disable overhead.
+ */
 static inline void __count_vm_event(enum vm_event_item item)
 {
-	__this_cpu_inc(vm_event_states.event[item]);
+	raw_cpu_inc(vm_event_states.event[item]);
 }
 
 static inline void count_vm_event(enum vm_event_item item)
@@ -39,7 +43,7 @@ static inline void count_vm_event(enum vm_event_item item)
 
 static inline void __count_vm_events(enum vm_event_item item, long delta)
 {
-	__this_cpu_add(vm_event_states.event[item], delta);
+	raw_cpu_add(vm_event_states.event[item], delta);
 }
 
 static inline void count_vm_events(enum vm_event_item item, long delta)
-- 
cgit v1.2.3


From 188a81409ff7de1c5aae947a96356ddd8ff4aaa3 Mon Sep 17 00:00:00 2001
From: Christoph Lameter <cl@linux.com>
Date: Mon, 7 Apr 2014 15:39:44 -0700
Subject: percpu: add preemption checks to __this_cpu ops

We define a check function in order to avoid trouble with the include
files.  Then the higher level __this_cpu macros are modified to invoke
the preemption check.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Christoph Lameter <cl@linux.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Tested-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/percpu.h | 39 +++++++++++++++++++++++++++++----------
 lib/smp_processor_id.c | 18 ++++++++++++++----
 2 files changed, 43 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 4e4d2afcc0c7..e7a0b95ed527 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -173,6 +173,12 @@ extern phys_addr_t per_cpu_ptr_to_phys(void *addr);
 
 extern void __bad_size_call_parameter(void);
 
+#ifdef CONFIG_DEBUG_PREEMPT
+extern void __this_cpu_preempt_check(const char *op);
+#else
+static inline void __this_cpu_preempt_check(const char *op) { }
+#endif
+
 #define __pcpu_size_call_return(stem, variable)				\
 ({	typeof(variable) pscr_ret__;					\
 	__verify_pcpu_ptr(&(variable));					\
@@ -725,18 +731,24 @@ do {									\
 
 /*
  * Generic percpu operations for context that are safe from preemption/interrupts.
- * Checks will be added here soon.
  */
 #ifndef __this_cpu_read
-# define __this_cpu_read(pcp)	__pcpu_size_call_return(raw_cpu_read_, (pcp))
+# define __this_cpu_read(pcp) \
+	(__this_cpu_preempt_check("read"),__pcpu_size_call_return(raw_cpu_read_, (pcp)))
 #endif
 
 #ifndef __this_cpu_write
-# define __this_cpu_write(pcp, val)	__pcpu_size_call(raw_cpu_write_, (pcp), (val))
+# define __this_cpu_write(pcp, val)					\
+do { __this_cpu_preempt_check("write");					\
+     __pcpu_size_call(raw_cpu_write_, (pcp), (val));			\
+} while (0)
 #endif
 
 #ifndef __this_cpu_add
-# define __this_cpu_add(pcp, val)	__pcpu_size_call(raw_cpu_add_, (pcp), (val))
+# define __this_cpu_add(pcp, val)					 \
+do { __this_cpu_preempt_check("add");					\
+	__pcpu_size_call(raw_cpu_add_, (pcp), (val));			\
+} while (0)
 #endif
 
 #ifndef __this_cpu_sub
@@ -752,16 +764,23 @@ do {									\
 #endif
 
 #ifndef __this_cpu_and
-# define __this_cpu_and(pcp, val)	__pcpu_size_call(raw_cpu_and_, (pcp), (val))
+# define __this_cpu_and(pcp, val)					\
+do { __this_cpu_preempt_check("and");					\
+	__pcpu_size_call(raw_cpu_and_, (pcp), (val));			\
+} while (0)
+
 #endif
 
 #ifndef __this_cpu_or
-# define __this_cpu_or(pcp, val)	__pcpu_size_call(raw_cpu_or_, (pcp), (val))
+# define __this_cpu_or(pcp, val)					\
+do { __this_cpu_preempt_check("or");					\
+	__pcpu_size_call(raw_cpu_or_, (pcp), (val));			\
+} while (0)
 #endif
 
 #ifndef __this_cpu_add_return
 # define __this_cpu_add_return(pcp, val)	\
-	__pcpu_size_call_return2(raw_cpu_add_return_, pcp, val)
+	(__this_cpu_preempt_check("add_return"),__pcpu_size_call_return2(raw_cpu_add_return_, pcp, val))
 #endif
 
 #define __this_cpu_sub_return(pcp, val)	__this_cpu_add_return(pcp, -(typeof(pcp))(val))
@@ -770,17 +789,17 @@ do {									\
 
 #ifndef __this_cpu_xchg
 # define __this_cpu_xchg(pcp, nval)	\
-	__pcpu_size_call_return2(raw_cpu_xchg_, (pcp), nval)
+	(__this_cpu_preempt_check("xchg"),__pcpu_size_call_return2(raw_cpu_xchg_, (pcp), nval))
 #endif
 
 #ifndef __this_cpu_cmpxchg
 # define __this_cpu_cmpxchg(pcp, oval, nval)	\
-	__pcpu_size_call_return2(raw_cpu_cmpxchg_, pcp, oval, nval)
+	(__this_cpu_preempt_check("cmpxchg"),__pcpu_size_call_return2(raw_cpu_cmpxchg_, pcp, oval, nval))
 #endif
 
 #ifndef __this_cpu_cmpxchg_double
 # define __this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	__pcpu_double_call_return_bool(raw_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2))
+	(__this_cpu_preempt_check("cmpxchg_double"),__pcpu_double_call_return_bool(raw_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2)))
 #endif
 
 #endif /* __LINUX_PERCPU_H */
diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c
index 04abe53f12a1..1afec32de6f2 100644
--- a/lib/smp_processor_id.c
+++ b/lib/smp_processor_id.c
@@ -7,7 +7,8 @@
 #include <linux/kallsyms.h>
 #include <linux/sched.h>
 
-notrace unsigned int debug_smp_processor_id(void)
+notrace static unsigned int check_preemption_disabled(const char *what1,
+							const char *what2)
 {
 	int this_cpu = raw_smp_processor_id();
 
@@ -38,9 +39,9 @@ notrace unsigned int debug_smp_processor_id(void)
 	if (!printk_ratelimit())
 		goto out_enable;
 
-	printk(KERN_ERR "BUG: using smp_processor_id() in preemptible [%08x] "
-			"code: %s/%d\n",
-			preempt_count() - 1, current->comm, current->pid);
+	printk(KERN_ERR "BUG: using %s%s() in preemptible [%08x] code: %s/%d\n",
+		what1, what2, preempt_count() - 1, current->comm, current->pid);
+
 	print_symbol("caller is %s\n", (long)__builtin_return_address(0));
 	dump_stack();
 
@@ -50,5 +51,14 @@ out:
 	return this_cpu;
 }
 
+notrace unsigned int debug_smp_processor_id(void)
+{
+	return check_preemption_disabled("smp_processor_id", "");
+}
 EXPORT_SYMBOL(debug_smp_processor_id);
 
+notrace void __this_cpu_preempt_check(const char *op)
+{
+	check_preemption_disabled("__this_cpu_", op);
+}
+EXPORT_SYMBOL(__this_cpu_preempt_check);
-- 
cgit v1.2.3


From 64b47e8fdb40a0d46e8cf458dd3e24f8afa073f6 Mon Sep 17 00:00:00 2001
From: Josh Triplett <josh@joshtriplett.org>
Date: Mon, 7 Apr 2014 15:39:45 -0700
Subject: lglock: map to spinlock when !CONFIG_SMP

When the system has only one CPU, lglock is effectively a spinlock; map
it directly to spinlock to eliminate the indirection and duplicate code.

In addition to removing overhead, this drops 1.6k of code with a
defconfig modified to have !CONFIG_SMP, and 1.1k with a minimal config.

Signed-off-by: Josh Triplett <josh@joshtriplett.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Michal Marek <mmarek@suse.cz>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: David Howells <dhowells@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/lglock.h  | 16 ++++++++++++++++
 kernel/locking/Makefile |  3 ++-
 2 files changed, 18 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/lglock.h b/include/linux/lglock.h
index 96549abe8842..0081f000e34b 100644
--- a/include/linux/lglock.h
+++ b/include/linux/lglock.h
@@ -25,6 +25,8 @@
 #include <linux/cpu.h>
 #include <linux/notifier.h>
 
+#ifdef CONFIG_SMP
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 #define LOCKDEP_INIT_MAP lockdep_init_map
 #else
@@ -57,4 +59,18 @@ void lg_local_unlock_cpu(struct lglock *lg, int cpu);
 void lg_global_lock(struct lglock *lg);
 void lg_global_unlock(struct lglock *lg);
 
+#else
+/* When !CONFIG_SMP, map lglock to spinlock */
+#define lglock spinlock
+#define DEFINE_LGLOCK(name) DEFINE_SPINLOCK(name)
+#define DEFINE_STATIC_LGLOCK(name) static DEFINE_SPINLOCK(name)
+#define lg_lock_init(lg, name) spin_lock_init(lg)
+#define lg_local_lock spin_lock
+#define lg_local_unlock spin_unlock
+#define lg_local_lock_cpu(lg, cpu) spin_lock(lg)
+#define lg_local_unlock_cpu(lg, cpu) spin_unlock(lg)
+#define lg_global_lock spin_lock
+#define lg_global_unlock spin_unlock
+#endif
+
 #endif
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 306a76b51e0f..b8bdcd4785b7 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -1,5 +1,5 @@
 
-obj-y += mutex.o semaphore.o rwsem.o lglock.o mcs_spinlock.o
+obj-y += mutex.o semaphore.o rwsem.o mcs_spinlock.o
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_lockdep.o = -pg
@@ -14,6 +14,7 @@ ifeq ($(CONFIG_PROC_FS),y)
 obj-$(CONFIG_LOCKDEP) += lockdep_proc.o
 endif
 obj-$(CONFIG_SMP) += spinlock.o
+obj-$(CONFIG_SMP) += lglock.o
 obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
 obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
 obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
-- 
cgit v1.2.3


From 5fb6b953bb7aa86a9c8ea760934982cedc45c52b Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Tue, 8 Apr 2014 12:55:46 +0200
Subject: include/linux/syscalls.h: add sys_renameat2() prototype

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/syscalls.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 2aa8b749f13d..697ceb70a9a9 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -748,6 +748,9 @@ asmlinkage long sys_linkat(int olddfd, const char __user *oldname,
 			   int newdfd, const char __user *newname, int flags);
 asmlinkage long sys_renameat(int olddfd, const char __user * oldname,
 			     int newdfd, const char __user * newname);
+asmlinkage long sys_renameat2(int olddfd, const char __user *oldname,
+			      int newdfd, const char __user *newname,
+			      unsigned int flags);
 asmlinkage long sys_futimesat(int dfd, const char __user *filename,
 			      struct timeval __user *utimes);
 asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode);
-- 
cgit v1.2.3


From de7b2973903c6cc50b31ee5682a69b2219b9919d Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Date: Tue, 8 Apr 2014 17:26:21 -0400
Subject: tracepoint: Use struct pointer instead of name hash for reg/unreg
 tracepoints

Register/unregister tracepoint probes with struct tracepoint pointer
rather than tracepoint name.

This change, which vastly simplifies tracepoint.c, has been proposed by
Steven Rostedt. It also removes 8.8kB (mostly of text) to the vmlinux
size.

From this point on, the tracers need to pass a struct tracepoint pointer
to probe register/unregister. A probe can now only be connected to a
tracepoint that exists. Moreover, tracers are responsible for
unregistering the probe before the module containing its associated
tracepoint is unloaded.

   text    data     bss     dec     hex filename
10443444        4282528 10391552        25117524        17f4354 vmlinux.orig
10434930        4282848 10391552        25109330        17f2352 vmlinux

Link: http://lkml.kernel.org/r/1396992381-23785-2-git-send-email-mathieu.desnoyers@efficios.com

CC: Ingo Molnar <mingo@kernel.org>
CC: Frederic Weisbecker <fweisbec@gmail.com>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Frank Ch. Eigler <fche@redhat.com>
CC: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
[ SDR - fixed return val in void func in tracepoint_module_going() ]
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace_event.h        |  22 +-
 include/linux/tracepoint.h          |  41 +--
 include/trace/ftrace.h              |   9 +-
 kernel/trace/trace_events.c         |  55 ++--
 kernel/trace/trace_events_trigger.c |   2 +-
 kernel/trace/trace_kprobe.c         |  21 +-
 kernel/trace/trace_output.c         |   2 +-
 kernel/trace/trace_uprobe.c         |  20 +-
 kernel/tracepoint.c                 | 511 ++++++++++++++++--------------------
 9 files changed, 331 insertions(+), 352 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index cdc30111d2f8..d16da3e53bc7 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -7,6 +7,7 @@
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
 #include <linux/perf_event.h>
+#include <linux/tracepoint.h>
 
 struct trace_array;
 struct trace_buffer;
@@ -232,6 +233,7 @@ enum {
 	TRACE_EVENT_FL_IGNORE_ENABLE_BIT,
 	TRACE_EVENT_FL_WAS_ENABLED_BIT,
 	TRACE_EVENT_FL_USE_CALL_FILTER_BIT,
+	TRACE_EVENT_FL_TRACEPOINT_BIT,
 };
 
 /*
@@ -244,6 +246,7 @@ enum {
  *                    (used for module unloading, if a module event is enabled,
  *                     it is best to clear the buffers that used it).
  *  USE_CALL_FILTER - For ftrace internal events, don't use file filter
+ *  TRACEPOINT    - Event is a tracepoint
  */
 enum {
 	TRACE_EVENT_FL_FILTERED		= (1 << TRACE_EVENT_FL_FILTERED_BIT),
@@ -252,12 +255,17 @@ enum {
 	TRACE_EVENT_FL_IGNORE_ENABLE	= (1 << TRACE_EVENT_FL_IGNORE_ENABLE_BIT),
 	TRACE_EVENT_FL_WAS_ENABLED	= (1 << TRACE_EVENT_FL_WAS_ENABLED_BIT),
 	TRACE_EVENT_FL_USE_CALL_FILTER	= (1 << TRACE_EVENT_FL_USE_CALL_FILTER_BIT),
+	TRACE_EVENT_FL_TRACEPOINT	= (1 << TRACE_EVENT_FL_TRACEPOINT_BIT),
 };
 
 struct ftrace_event_call {
 	struct list_head	list;
 	struct ftrace_event_class *class;
-	char			*name;
+	union {
+		char			*name;
+		/* Set TRACE_EVENT_FL_TRACEPOINT flag when using "tp" */
+		struct tracepoint	*tp;
+	};
 	struct trace_event	event;
 	const char		*print_fmt;
 	struct event_filter	*filter;
@@ -271,6 +279,7 @@ struct ftrace_event_call {
 	 *   bit 3:		ftrace internal event (do not enable)
 	 *   bit 4:		Event was enabled by module
 	 *   bit 5:		use call filter rather than file filter
+	 *   bit 6:		Event is a tracepoint
 	 */
 	int			flags; /* static flags of different events */
 
@@ -283,6 +292,15 @@ struct ftrace_event_call {
 #endif
 };
 
+static inline const char *
+ftrace_event_name(struct ftrace_event_call *call)
+{
+	if (call->flags & TRACE_EVENT_FL_TRACEPOINT)
+		return call->tp ? call->tp->name : NULL;
+	else
+		return call->name;
+}
+
 struct trace_array;
 struct ftrace_subsystem_dir;
 
@@ -353,7 +371,7 @@ struct ftrace_event_file {
 #define __TRACE_EVENT_FLAGS(name, value)				\
 	static int __init trace_init_flags_##name(void)			\
 	{								\
-		event_##name.flags = value;				\
+		event_##name.flags |= value;				\
 		return 0;						\
 	}								\
 	early_initcall(trace_init_flags_##name);
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 812b2553dfd8..08150e265761 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -6,7 +6,7 @@
  *
  * See Documentation/trace/tracepoints.txt.
  *
- * (C) Copyright 2008 Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
+ * Copyright (C) 2008-2014 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
  *
  * Heavily inspired from the Linux Kernel Markers.
  *
@@ -21,6 +21,7 @@
 
 struct module;
 struct tracepoint;
+struct notifier_block;
 
 struct tracepoint_func {
 	void *func;
@@ -35,18 +36,13 @@ struct tracepoint {
 	struct tracepoint_func __rcu *funcs;
 };
 
-/*
- * Connect a probe to a tracepoint.
- * Internal API, should not be used directly.
- */
-extern int tracepoint_probe_register(const char *name, void *probe, void *data);
-
-/*
- * Disconnect a probe from a tracepoint.
- * Internal API, should not be used directly.
- */
 extern int
-tracepoint_probe_unregister(const char *name, void *probe, void *data);
+tracepoint_probe_register(struct tracepoint *tp, void *probe, void *data);
+extern int
+tracepoint_probe_unregister(struct tracepoint *tp, void *probe, void *data);
+extern void
+for_each_kernel_tracepoint(void (*fct)(struct tracepoint *tp, void *priv),
+		void *priv);
 
 #ifdef CONFIG_MODULES
 struct tp_module {
@@ -54,12 +50,25 @@ struct tp_module {
 	unsigned int num_tracepoints;
 	struct tracepoint * const *tracepoints_ptrs;
 };
+
 bool trace_module_has_bad_taint(struct module *mod);
+extern int register_tracepoint_module_notifier(struct notifier_block *nb);
+extern int unregister_tracepoint_module_notifier(struct notifier_block *nb);
 #else
 static inline bool trace_module_has_bad_taint(struct module *mod)
 {
 	return false;
 }
+static inline
+int register_tracepoint_module_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+static inline
+int unregister_tracepoint_module_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
 #endif /* CONFIG_MODULES */
 
 /*
@@ -160,14 +169,14 @@ static inline void tracepoint_synchronize_unregister(void)
 	static inline int						\
 	register_trace_##name(void (*probe)(data_proto), void *data)	\
 	{								\
-		return tracepoint_probe_register(#name, (void *)probe,	\
-						 data);			\
+		return tracepoint_probe_register(&__tracepoint_##name,	\
+						(void *)probe, data);	\
 	}								\
 	static inline int						\
 	unregister_trace_##name(void (*probe)(data_proto), void *data)	\
 	{								\
-		return tracepoint_probe_unregister(#name, (void *)probe, \
-						   data);		\
+		return tracepoint_probe_unregister(&__tracepoint_##name,\
+						(void *)probe, data);	\
 	}								\
 	static inline void						\
 	check_trace_callback_type_##name(void (*cb)(data_proto))	\
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 8765126b328c..9c44c11cd9bb 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -470,10 +470,11 @@ static inline notrace int ftrace_get_offsets_##call(			\
  * };
  *
  * static struct ftrace_event_call event_<call> = {
- *	.name			= "<call>",
+ *	.tp			= &__tracepoint_<call>,
  *	.class			= event_class_<template>,
  *	.event			= &ftrace_event_type_<call>,
  *	.print_fmt		= print_fmt_<call>,
+ *	.flags			= TRACE_EVENT_FL_TRACEPOINT,
  * };
  * // its only safe to use pointers when doing linker tricks to
  * // create an array.
@@ -605,10 +606,11 @@ static struct ftrace_event_class __used __refdata event_class_##call = { \
 #define DEFINE_EVENT(template, call, proto, args)			\
 									\
 static struct ftrace_event_call __used event_##call = {			\
-	.name			= #call,				\
+	.tp			= &__tracepoint_##call,			\
 	.class			= &event_class_##template,		\
 	.event.funcs		= &ftrace_event_type_funcs_##template,	\
 	.print_fmt		= print_fmt_##template,			\
+	.flags			= TRACE_EVENT_FL_TRACEPOINT,		\
 };									\
 static struct ftrace_event_call __used					\
 __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
@@ -619,10 +621,11 @@ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
 static const char print_fmt_##call[] = print;				\
 									\
 static struct ftrace_event_call __used event_##call = {			\
-	.name			= #call,				\
+	.tp			= &__tracepoint_##call,			\
 	.class			= &event_class_##template,		\
 	.event.funcs		= &ftrace_event_type_funcs_##call,	\
 	.print_fmt		= print_fmt_##call,			\
+	.flags			= TRACE_EVENT_FL_TRACEPOINT,		\
 };									\
 static struct ftrace_event_call __used					\
 __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 83a4378dc5e0..3ddfd8f62c05 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -223,24 +223,25 @@ int ftrace_event_reg(struct ftrace_event_call *call,
 {
 	struct ftrace_event_file *file = data;
 
+	WARN_ON(!(call->flags & TRACE_EVENT_FL_TRACEPOINT));
 	switch (type) {
 	case TRACE_REG_REGISTER:
-		return tracepoint_probe_register(call->name,
+		return tracepoint_probe_register(call->tp,
 						 call->class->probe,
 						 file);
 	case TRACE_REG_UNREGISTER:
-		tracepoint_probe_unregister(call->name,
+		tracepoint_probe_unregister(call->tp,
 					    call->class->probe,
 					    file);
 		return 0;
 
 #ifdef CONFIG_PERF_EVENTS
 	case TRACE_REG_PERF_REGISTER:
-		return tracepoint_probe_register(call->name,
+		return tracepoint_probe_register(call->tp,
 						 call->class->perf_probe,
 						 call);
 	case TRACE_REG_PERF_UNREGISTER:
-		tracepoint_probe_unregister(call->name,
+		tracepoint_probe_unregister(call->tp,
 					    call->class->perf_probe,
 					    call);
 		return 0;
@@ -352,7 +353,7 @@ static int __ftrace_event_enable_disable(struct ftrace_event_file *file,
 			if (ret) {
 				tracing_stop_cmdline_record();
 				pr_info("event trace: Could not enable event "
-					"%s\n", call->name);
+					"%s\n", ftrace_event_name(call));
 				break;
 			}
 			set_bit(FTRACE_EVENT_FL_ENABLED_BIT, &file->flags);
@@ -481,27 +482,29 @@ __ftrace_set_clr_event_nolock(struct trace_array *tr, const char *match,
 {
 	struct ftrace_event_file *file;
 	struct ftrace_event_call *call;
+	const char *name;
 	int ret = -EINVAL;
 
 	list_for_each_entry(file, &tr->events, list) {
 
 		call = file->event_call;
+		name = ftrace_event_name(call);
 
-		if (!call->name || !call->class || !call->class->reg)
+		if (!name || !call->class || !call->class->reg)
 			continue;
 
 		if (call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)
 			continue;
 
 		if (match &&
-		    strcmp(match, call->name) != 0 &&
+		    strcmp(match, name) != 0 &&
 		    strcmp(match, call->class->system) != 0)
 			continue;
 
 		if (sub && strcmp(sub, call->class->system) != 0)
 			continue;
 
-		if (event && strcmp(event, call->name) != 0)
+		if (event && strcmp(event, name) != 0)
 			continue;
 
 		ftrace_event_enable_disable(file, set);
@@ -699,7 +702,7 @@ static int t_show(struct seq_file *m, void *v)
 
 	if (strcmp(call->class->system, TRACE_SYSTEM) != 0)
 		seq_printf(m, "%s:", call->class->system);
-	seq_printf(m, "%s\n", call->name);
+	seq_printf(m, "%s\n", ftrace_event_name(call));
 
 	return 0;
 }
@@ -792,7 +795,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
 	mutex_lock(&event_mutex);
 	list_for_each_entry(file, &tr->events, list) {
 		call = file->event_call;
-		if (!call->name || !call->class || !call->class->reg)
+		if (!ftrace_event_name(call) || !call->class || !call->class->reg)
 			continue;
 
 		if (system && strcmp(call->class->system, system->name) != 0)
@@ -907,7 +910,7 @@ static int f_show(struct seq_file *m, void *v)
 
 	switch ((unsigned long)v) {
 	case FORMAT_HEADER:
-		seq_printf(m, "name: %s\n", call->name);
+		seq_printf(m, "name: %s\n", ftrace_event_name(call));
 		seq_printf(m, "ID: %d\n", call->event.type);
 		seq_printf(m, "format:\n");
 		return 0;
@@ -1527,6 +1530,7 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file)
 	struct trace_array *tr = file->tr;
 	struct list_head *head;
 	struct dentry *d_events;
+	const char *name;
 	int ret;
 
 	/*
@@ -1540,10 +1544,11 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file)
 	} else
 		d_events = parent;
 
-	file->dir = debugfs_create_dir(call->name, d_events);
+	name = ftrace_event_name(call);
+	file->dir = debugfs_create_dir(name, d_events);
 	if (!file->dir) {
 		pr_warning("Could not create debugfs '%s' directory\n",
-			   call->name);
+			   name);
 		return -1;
 	}
 
@@ -1567,7 +1572,7 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file)
 		ret = call->class->define_fields(call);
 		if (ret < 0) {
 			pr_warning("Could not initialize trace point"
-				   " events/%s\n", call->name);
+				   " events/%s\n", name);
 			return -1;
 		}
 	}
@@ -1631,15 +1636,17 @@ static void event_remove(struct ftrace_event_call *call)
 static int event_init(struct ftrace_event_call *call)
 {
 	int ret = 0;
+	const char *name;
 
-	if (WARN_ON(!call->name))
+	name = ftrace_event_name(call);
+	if (WARN_ON(!name))
 		return -EINVAL;
 
 	if (call->class->raw_init) {
 		ret = call->class->raw_init(call);
 		if (ret < 0 && ret != -ENOSYS)
 			pr_warn("Could not initialize trace events/%s\n",
-				call->name);
+				name);
 	}
 
 	return ret;
@@ -1885,7 +1892,7 @@ __trace_add_event_dirs(struct trace_array *tr)
 		ret = __trace_add_new_event(call, tr);
 		if (ret < 0)
 			pr_warning("Could not create directory for event %s\n",
-				   call->name);
+				   ftrace_event_name(call));
 	}
 }
 
@@ -1894,18 +1901,20 @@ find_event_file(struct trace_array *tr, const char *system,  const char *event)
 {
 	struct ftrace_event_file *file;
 	struct ftrace_event_call *call;
+	const char *name;
 
 	list_for_each_entry(file, &tr->events, list) {
 
 		call = file->event_call;
+		name = ftrace_event_name(call);
 
-		if (!call->name || !call->class || !call->class->reg)
+		if (!name || !call->class || !call->class->reg)
 			continue;
 
 		if (call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)
 			continue;
 
-		if (strcmp(event, call->name) == 0 &&
+		if (strcmp(event, name) == 0 &&
 		    strcmp(system, call->class->system) == 0)
 			return file;
 	}
@@ -1973,7 +1982,7 @@ event_enable_print(struct seq_file *m, unsigned long ip,
 	seq_printf(m, "%s:%s:%s",
 		   data->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR,
 		   data->file->event_call->class->system,
-		   data->file->event_call->name);
+		   ftrace_event_name(data->file->event_call));
 
 	if (data->count == -1)
 		seq_printf(m, ":unlimited\n");
@@ -2193,7 +2202,7 @@ __trace_early_add_event_dirs(struct trace_array *tr)
 		ret = event_create_dir(tr->event_dir, file);
 		if (ret < 0)
 			pr_warning("Could not create directory for event %s\n",
-				   file->event_call->name);
+				   ftrace_event_name(file->event_call));
 	}
 }
 
@@ -2217,7 +2226,7 @@ __trace_early_add_events(struct trace_array *tr)
 		ret = __trace_early_add_new_event(call, tr);
 		if (ret < 0)
 			pr_warning("Could not create early event %s\n",
-				   call->name);
+				   ftrace_event_name(call));
 	}
 }
 
@@ -2549,7 +2558,7 @@ static __init void event_trace_self_tests(void)
 			continue;
 #endif
 
-		pr_info("Testing event %s: ", call->name);
+		pr_info("Testing event %s: ", ftrace_event_name(call));
 
 		/*
 		 * If an event is already enabled, someone is using
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 8efbb69b04f0..925f537f07d1 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -1095,7 +1095,7 @@ event_enable_trigger_print(struct seq_file *m, struct event_trigger_ops *ops,
 	seq_printf(m, "%s:%s:%s",
 		   enable_data->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR,
 		   enable_data->file->event_call->class->system,
-		   enable_data->file->event_call->name);
+		   ftrace_event_name(enable_data->file->event_call));
 
 	if (data->count == -1)
 		seq_puts(m, ":unlimited");
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index d021d21dd150..903ae28962be 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -341,7 +341,7 @@ static struct trace_kprobe *find_trace_kprobe(const char *event,
 	struct trace_kprobe *tk;
 
 	list_for_each_entry(tk, &probe_list, list)
-		if (strcmp(tk->tp.call.name, event) == 0 &&
+		if (strcmp(ftrace_event_name(&tk->tp.call), event) == 0 &&
 		    strcmp(tk->tp.call.class->system, group) == 0)
 			return tk;
 	return NULL;
@@ -516,7 +516,8 @@ static int register_trace_kprobe(struct trace_kprobe *tk)
 	mutex_lock(&probe_lock);
 
 	/* Delete old (same name) event if exist */
-	old_tk = find_trace_kprobe(tk->tp.call.name, tk->tp.call.class->system);
+	old_tk = find_trace_kprobe(ftrace_event_name(&tk->tp.call),
+			tk->tp.call.class->system);
 	if (old_tk) {
 		ret = unregister_trace_kprobe(old_tk);
 		if (ret < 0)
@@ -564,7 +565,8 @@ static int trace_kprobe_module_callback(struct notifier_block *nb,
 			if (ret)
 				pr_warning("Failed to re-register probe %s on"
 					   "%s: %d\n",
-					   tk->tp.call.name, mod->name, ret);
+					   ftrace_event_name(&tk->tp.call),
+					   mod->name, ret);
 		}
 	}
 	mutex_unlock(&probe_lock);
@@ -818,7 +820,8 @@ static int probes_seq_show(struct seq_file *m, void *v)
 	int i;
 
 	seq_printf(m, "%c", trace_kprobe_is_return(tk) ? 'r' : 'p');
-	seq_printf(m, ":%s/%s", tk->tp.call.class->system, tk->tp.call.name);
+	seq_printf(m, ":%s/%s", tk->tp.call.class->system,
+			ftrace_event_name(&tk->tp.call));
 
 	if (!tk->symbol)
 		seq_printf(m, " 0x%p", tk->rp.kp.addr);
@@ -876,7 +879,8 @@ static int probes_profile_seq_show(struct seq_file *m, void *v)
 {
 	struct trace_kprobe *tk = v;
 
-	seq_printf(m, "  %-44s %15lu %15lu\n", tk->tp.call.name, tk->nhit,
+	seq_printf(m, "  %-44s %15lu %15lu\n",
+		   ftrace_event_name(&tk->tp.call), tk->nhit,
 		   tk->rp.kp.nmissed);
 
 	return 0;
@@ -1011,7 +1015,7 @@ print_kprobe_event(struct trace_iterator *iter, int flags,
 	field = (struct kprobe_trace_entry_head *)iter->ent;
 	tp = container_of(event, struct trace_probe, call.event);
 
-	if (!trace_seq_printf(s, "%s: (", tp->call.name))
+	if (!trace_seq_printf(s, "%s: (", ftrace_event_name(&tp->call)))
 		goto partial;
 
 	if (!seq_print_ip_sym(s, field->ip, flags | TRACE_ITER_SYM_OFFSET))
@@ -1047,7 +1051,7 @@ print_kretprobe_event(struct trace_iterator *iter, int flags,
 	field = (struct kretprobe_trace_entry_head *)iter->ent;
 	tp = container_of(event, struct trace_probe, call.event);
 
-	if (!trace_seq_printf(s, "%s: (", tp->call.name))
+	if (!trace_seq_printf(s, "%s: (", ftrace_event_name(&tp->call)))
 		goto partial;
 
 	if (!seq_print_ip_sym(s, field->ret_ip, flags | TRACE_ITER_SYM_OFFSET))
@@ -1286,7 +1290,8 @@ static int register_kprobe_event(struct trace_kprobe *tk)
 	call->data = tk;
 	ret = trace_add_event_call(call);
 	if (ret) {
-		pr_info("Failed to register kprobe event: %s\n", call->name);
+		pr_info("Failed to register kprobe event: %s\n",
+			ftrace_event_name(call));
 		kfree(call->print_fmt);
 		unregister_ftrace_event(&call->event);
 	}
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index ca0e79e2abaa..a436de18aa99 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -431,7 +431,7 @@ int ftrace_raw_output_prep(struct trace_iterator *iter,
 	}
 
 	trace_seq_init(p);
-	ret = trace_seq_printf(s, "%s: ", event->name);
+	ret = trace_seq_printf(s, "%s: ", ftrace_event_name(event));
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index e4473367e7a4..930e51462dc8 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -294,7 +294,7 @@ static struct trace_uprobe *find_probe_event(const char *event, const char *grou
 	struct trace_uprobe *tu;
 
 	list_for_each_entry(tu, &uprobe_list, list)
-		if (strcmp(tu->tp.call.name, event) == 0 &&
+		if (strcmp(ftrace_event_name(&tu->tp.call), event) == 0 &&
 		    strcmp(tu->tp.call.class->system, group) == 0)
 			return tu;
 
@@ -324,7 +324,8 @@ static int register_trace_uprobe(struct trace_uprobe *tu)
 	mutex_lock(&uprobe_lock);
 
 	/* register as an event */
-	old_tu = find_probe_event(tu->tp.call.name, tu->tp.call.class->system);
+	old_tu = find_probe_event(ftrace_event_name(&tu->tp.call),
+			tu->tp.call.class->system);
 	if (old_tu) {
 		/* delete old event */
 		ret = unregister_trace_uprobe(old_tu);
@@ -599,7 +600,8 @@ static int probes_seq_show(struct seq_file *m, void *v)
 	char c = is_ret_probe(tu) ? 'r' : 'p';
 	int i;
 
-	seq_printf(m, "%c:%s/%s", c, tu->tp.call.class->system, tu->tp.call.name);
+	seq_printf(m, "%c:%s/%s", c, tu->tp.call.class->system,
+			ftrace_event_name(&tu->tp.call));
 	seq_printf(m, " %s:0x%p", tu->filename, (void *)tu->offset);
 
 	for (i = 0; i < tu->tp.nr_args; i++)
@@ -649,7 +651,8 @@ static int probes_profile_seq_show(struct seq_file *m, void *v)
 {
 	struct trace_uprobe *tu = v;
 
-	seq_printf(m, "  %s %-44s %15lu\n", tu->filename, tu->tp.call.name, tu->nhit);
+	seq_printf(m, "  %s %-44s %15lu\n", tu->filename,
+			ftrace_event_name(&tu->tp.call), tu->nhit);
 	return 0;
 }
 
@@ -844,12 +847,14 @@ print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *e
 	tu = container_of(event, struct trace_uprobe, tp.call.event);
 
 	if (is_ret_probe(tu)) {
-		if (!trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", tu->tp.call.name,
+		if (!trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)",
+					ftrace_event_name(&tu->tp.call),
 					entry->vaddr[1], entry->vaddr[0]))
 			goto partial;
 		data = DATAOF_TRACE_ENTRY(entry, true);
 	} else {
-		if (!trace_seq_printf(s, "%s: (0x%lx)", tu->tp.call.name,
+		if (!trace_seq_printf(s, "%s: (0x%lx)",
+					ftrace_event_name(&tu->tp.call),
 					entry->vaddr[0]))
 			goto partial;
 		data = DATAOF_TRACE_ENTRY(entry, false);
@@ -1275,7 +1280,8 @@ static int register_uprobe_event(struct trace_uprobe *tu)
 	ret = trace_add_event_call(call);
 
 	if (ret) {
-		pr_info("Failed to register uprobe event: %s\n", call->name);
+		pr_info("Failed to register uprobe event: %s\n",
+			ftrace_event_name(call));
 		kfree(call->print_fmt);
 		unregister_ftrace_event(&call->event);
 	}
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 50f8329c2042..01b3bd84daa1 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2008 Mathieu Desnoyers
+ * Copyright (C) 2008-2014 Mathieu Desnoyers
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -33,39 +33,27 @@ extern struct tracepoint * const __stop___tracepoints_ptrs[];
 /* Set to 1 to enable tracepoint debug output */
 static const int tracepoint_debug;
 
+#ifdef CONFIG_MODULES
 /*
- * Tracepoints mutex protects the builtin and module tracepoints and the hash
- * table, as well as the local module list.
+ * Tracepoint module list mutex protects the local module list.
  */
-static DEFINE_MUTEX(tracepoints_mutex);
+static DEFINE_MUTEX(tracepoint_module_list_mutex);
 
-#ifdef CONFIG_MODULES
-/* Local list of struct module */
+/* Local list of struct tp_module */
 static LIST_HEAD(tracepoint_module_list);
 #endif /* CONFIG_MODULES */
 
 /*
- * Tracepoint hash table, containing the active tracepoints.
- * Protected by tracepoints_mutex.
+ * tracepoints_mutex protects the builtin and module tracepoints.
+ * tracepoints_mutex nests inside tracepoint_module_list_mutex.
  */
-#define TRACEPOINT_HASH_BITS 6
-#define TRACEPOINT_TABLE_SIZE (1 << TRACEPOINT_HASH_BITS)
-static struct hlist_head tracepoint_table[TRACEPOINT_TABLE_SIZE];
+static DEFINE_MUTEX(tracepoints_mutex);
 
 /*
  * Note about RCU :
  * It is used to delay the free of multiple probes array until a quiescent
  * state is reached.
- * Tracepoint entries modifications are protected by the tracepoints_mutex.
  */
-struct tracepoint_entry {
-	struct hlist_node hlist;
-	struct tracepoint_func *funcs;
-	int refcount;	/* Number of times armed. 0 if disarmed. */
-	int enabled;	/* Tracepoint enabled */
-	char name[0];
-};
-
 struct tp_probes {
 	struct rcu_head rcu;
 	struct tracepoint_func probes[0];
@@ -92,34 +80,33 @@ static inline void release_probes(struct tracepoint_func *old)
 	}
 }
 
-static void debug_print_probes(struct tracepoint_entry *entry)
+static void debug_print_probes(struct tracepoint_func *funcs)
 {
 	int i;
 
-	if (!tracepoint_debug || !entry->funcs)
+	if (!tracepoint_debug || !funcs)
 		return;
 
-	for (i = 0; entry->funcs[i].func; i++)
-		printk(KERN_DEBUG "Probe %d : %p\n", i, entry->funcs[i].func);
+	for (i = 0; funcs[i].func; i++)
+		printk(KERN_DEBUG "Probe %d : %p\n", i, funcs[i].func);
 }
 
-static struct tracepoint_func *
-tracepoint_entry_add_probe(struct tracepoint_entry *entry,
-			   void *probe, void *data)
+static struct tracepoint_func *func_add(struct tracepoint_func **funcs,
+		struct tracepoint_func *tp_func)
 {
 	int nr_probes = 0;
 	struct tracepoint_func *old, *new;
 
-	if (WARN_ON(!probe))
+	if (WARN_ON(!tp_func->func))
 		return ERR_PTR(-EINVAL);
 
-	debug_print_probes(entry);
-	old = entry->funcs;
+	debug_print_probes(*funcs);
+	old = *funcs;
 	if (old) {
 		/* (N -> N+1), (N != 0, 1) probes */
 		for (nr_probes = 0; old[nr_probes].func; nr_probes++)
-			if (old[nr_probes].func == probe &&
-			    old[nr_probes].data == data)
+			if (old[nr_probes].func == tp_func->func &&
+			    old[nr_probes].data == tp_func->data)
 				return ERR_PTR(-EEXIST);
 	}
 	/* + 2 : one for new probe, one for NULL func */
@@ -128,33 +115,30 @@ tracepoint_entry_add_probe(struct tracepoint_entry *entry,
 		return ERR_PTR(-ENOMEM);
 	if (old)
 		memcpy(new, old, nr_probes * sizeof(struct tracepoint_func));
-	new[nr_probes].func = probe;
-	new[nr_probes].data = data;
+	new[nr_probes] = *tp_func;
 	new[nr_probes + 1].func = NULL;
-	entry->refcount = nr_probes + 1;
-	entry->funcs = new;
-	debug_print_probes(entry);
+	*funcs = new;
+	debug_print_probes(*funcs);
 	return old;
 }
 
-static void *
-tracepoint_entry_remove_probe(struct tracepoint_entry *entry,
-			      void *probe, void *data)
+static void *func_remove(struct tracepoint_func **funcs,
+		struct tracepoint_func *tp_func)
 {
 	int nr_probes = 0, nr_del = 0, i;
 	struct tracepoint_func *old, *new;
 
-	old = entry->funcs;
+	old = *funcs;
 
 	if (!old)
 		return ERR_PTR(-ENOENT);
 
-	debug_print_probes(entry);
+	debug_print_probes(*funcs);
 	/* (N -> M), (N > 1, M >= 0) probes */
-	if (probe) {
+	if (tp_func->func) {
 		for (nr_probes = 0; old[nr_probes].func; nr_probes++) {
-			if (old[nr_probes].func == probe &&
-			     old[nr_probes].data == data)
+			if (old[nr_probes].func == tp_func->func &&
+			     old[nr_probes].data == tp_func->data)
 				nr_del++;
 		}
 	}
@@ -165,9 +149,8 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry,
 	 */
 	if (nr_probes - nr_del == 0) {
 		/* N -> 0, (N > 1) */
-		entry->funcs = NULL;
-		entry->refcount = 0;
-		debug_print_probes(entry);
+		*funcs = NULL;
+		debug_print_probes(*funcs);
 		return old;
 	} else {
 		int j = 0;
@@ -177,91 +160,34 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry,
 		if (new == NULL)
 			return ERR_PTR(-ENOMEM);
 		for (i = 0; old[i].func; i++)
-			if (old[i].func != probe || old[i].data != data)
+			if (old[i].func != tp_func->func
+					|| old[i].data != tp_func->data)
 				new[j++] = old[i];
 		new[nr_probes - nr_del].func = NULL;
-		entry->refcount = nr_probes - nr_del;
-		entry->funcs = new;
+		*funcs = new;
 	}
-	debug_print_probes(entry);
+	debug_print_probes(*funcs);
 	return old;
 }
 
 /*
- * Get tracepoint if the tracepoint is present in the tracepoint hash table.
- * Must be called with tracepoints_mutex held.
- * Returns NULL if not present.
+ * Add the probe function to a tracepoint.
  */
-static struct tracepoint_entry *get_tracepoint(const char *name)
+static int tracepoint_add_func(struct tracepoint *tp,
+		struct tracepoint_func *func)
 {
-	struct hlist_head *head;
-	struct tracepoint_entry *e;
-	u32 hash = jhash(name, strlen(name), 0);
-
-	head = &tracepoint_table[hash & (TRACEPOINT_TABLE_SIZE - 1)];
-	hlist_for_each_entry(e, head, hlist) {
-		if (!strcmp(name, e->name))
-			return e;
-	}
-	return NULL;
-}
+	struct tracepoint_func *old, *tp_funcs;
 
-/*
- * Add the tracepoint to the tracepoint hash table. Must be called with
- * tracepoints_mutex held.
- */
-static struct tracepoint_entry *add_tracepoint(const char *name)
-{
-	struct hlist_head *head;
-	struct tracepoint_entry *e;
-	size_t name_len = strlen(name) + 1;
-	u32 hash = jhash(name, name_len-1, 0);
-
-	head = &tracepoint_table[hash & (TRACEPOINT_TABLE_SIZE - 1)];
-	hlist_for_each_entry(e, head, hlist) {
-		if (!strcmp(name, e->name)) {
-			printk(KERN_NOTICE
-				"tracepoint %s busy\n", name);
-			return ERR_PTR(-EEXIST);	/* Already there */
-		}
-	}
-	/*
-	 * Using kmalloc here to allocate a variable length element. Could
-	 * cause some memory fragmentation if overused.
-	 */
-	e = kmalloc(sizeof(struct tracepoint_entry) + name_len, GFP_KERNEL);
-	if (!e)
-		return ERR_PTR(-ENOMEM);
-	memcpy(&e->name[0], name, name_len);
-	e->funcs = NULL;
-	e->refcount = 0;
-	e->enabled = 0;
-	hlist_add_head(&e->hlist, head);
-	return e;
-}
+	if (tp->regfunc && !static_key_enabled(&tp->key))
+		tp->regfunc();
 
-/*
- * Remove the tracepoint from the tracepoint hash table. Must be called with
- * mutex_lock held.
- */
-static inline void remove_tracepoint(struct tracepoint_entry *e)
-{
-	hlist_del(&e->hlist);
-	kfree(e);
-}
-
-/*
- * Sets the probe callback corresponding to one tracepoint.
- */
-static void set_tracepoint(struct tracepoint_entry **entry,
-	struct tracepoint *elem, int active)
-{
-	WARN_ON(strcmp((*entry)->name, elem->name) != 0);
-
-	if (elem->regfunc && !static_key_enabled(&elem->key) && active)
-		elem->regfunc();
-	else if (elem->unregfunc && static_key_enabled(&elem->key) && !active)
-		elem->unregfunc();
+	tp_funcs = tp->funcs;
+	old = func_add(&tp_funcs, func);
+	if (IS_ERR(old)) {
+		WARN_ON_ONCE(1);
+		return PTR_ERR(old);
+	}
+	release_probes(old);
 
 	/*
 	 * rcu_assign_pointer has a smp_wmb() which makes sure that the new
@@ -270,199 +196,163 @@ static void set_tracepoint(struct tracepoint_entry **entry,
 	 * include/linux/tracepoints.h. A matching smp_read_barrier_depends()
 	 * is used.
 	 */
-	rcu_assign_pointer(elem->funcs, (*entry)->funcs);
-	if (active && !static_key_enabled(&elem->key))
-		static_key_slow_inc(&elem->key);
-	else if (!active && static_key_enabled(&elem->key))
-		static_key_slow_dec(&elem->key);
+	rcu_assign_pointer(tp->funcs, tp_funcs);
+	if (!static_key_enabled(&tp->key))
+		static_key_slow_inc(&tp->key);
+	return 0;
 }
 
 /*
- * Disable a tracepoint and its probe callback.
+ * Remove a probe function from a tracepoint.
  * Note: only waiting an RCU period after setting elem->call to the empty
  * function insures that the original callback is not used anymore. This insured
  * by preempt_disable around the call site.
  */
-static void disable_tracepoint(struct tracepoint *elem)
+static int tracepoint_remove_func(struct tracepoint *tp,
+		struct tracepoint_func *func)
 {
-	if (elem->unregfunc && static_key_enabled(&elem->key))
-		elem->unregfunc();
-
-	if (static_key_enabled(&elem->key))
-		static_key_slow_dec(&elem->key);
-	rcu_assign_pointer(elem->funcs, NULL);
-}
+	struct tracepoint_func *old, *tp_funcs;
 
-/**
- * tracepoint_update_probe_range - Update a probe range
- * @begin: beginning of the range
- * @end: end of the range
- *
- * Updates the probe callback corresponding to a range of tracepoints.
- * Called with tracepoints_mutex held.
- */
-static void tracepoint_update_probe_range(struct tracepoint * const *begin,
-					  struct tracepoint * const *end)
-{
-	struct tracepoint * const *iter;
-	struct tracepoint_entry *mark_entry;
-
-	if (!begin)
-		return;
-
-	for (iter = begin; iter < end; iter++) {
-		mark_entry = get_tracepoint((*iter)->name);
-		if (mark_entry) {
-			set_tracepoint(&mark_entry, *iter,
-					!!mark_entry->refcount);
-			mark_entry->enabled = !!mark_entry->refcount;
-		} else {
-			disable_tracepoint(*iter);
-		}
+	tp_funcs = tp->funcs;
+	old = func_remove(&tp_funcs, func);
+	if (IS_ERR(old)) {
+		WARN_ON_ONCE(1);
+		return PTR_ERR(old);
 	}
-}
-
-#ifdef CONFIG_MODULES
-void module_update_tracepoints(void)
-{
-	struct tp_module *tp_mod;
-
-	list_for_each_entry(tp_mod, &tracepoint_module_list, list)
-		tracepoint_update_probe_range(tp_mod->tracepoints_ptrs,
-			tp_mod->tracepoints_ptrs + tp_mod->num_tracepoints);
-}
-#else /* CONFIG_MODULES */
-void module_update_tracepoints(void)
-{
-}
-#endif /* CONFIG_MODULES */
+	release_probes(old);
 
+	if (!tp_funcs) {
+		/* Removed last function */
+		if (tp->unregfunc && static_key_enabled(&tp->key))
+			tp->unregfunc();
 
-/*
- * Update probes, removing the faulty probes.
- * Called with tracepoints_mutex held.
- */
-static void tracepoint_update_probes(void)
-{
-	/* Core kernel tracepoints */
-	tracepoint_update_probe_range(__start___tracepoints_ptrs,
-		__stop___tracepoints_ptrs);
-	/* tracepoints in modules. */
-	module_update_tracepoints();
-}
-
-static struct tracepoint_func *
-tracepoint_add_probe(const char *name, void *probe, void *data)
-{
-	struct tracepoint_entry *entry;
-	struct tracepoint_func *old;
-
-	entry = get_tracepoint(name);
-	if (!entry) {
-		entry = add_tracepoint(name);
-		if (IS_ERR(entry))
-			return (struct tracepoint_func *)entry;
+		if (static_key_enabled(&tp->key))
+			static_key_slow_dec(&tp->key);
 	}
-	old = tracepoint_entry_add_probe(entry, probe, data);
-	if (IS_ERR(old) && !entry->refcount)
-		remove_tracepoint(entry);
-	return old;
+	rcu_assign_pointer(tp->funcs, tp_funcs);
+	return 0;
 }
 
 /**
  * tracepoint_probe_register -  Connect a probe to a tracepoint
- * @name: tracepoint name
+ * @tp: tracepoint
  * @probe: probe handler
- * @data: probe private data
- *
- * Returns:
- * - 0 if the probe was successfully registered, and tracepoint
- *   callsites are currently loaded for that probe,
- * - -ENODEV if the probe was successfully registered, but no tracepoint
- *   callsite is currently loaded for that probe,
- * - other negative error value on error.
- *
- * When tracepoint_probe_register() returns either 0 or -ENODEV,
- * parameters @name, @probe, and @data may be used by the tracepoint
- * infrastructure until the probe is unregistered.
  *
- * The probe address must at least be aligned on the architecture pointer size.
+ * Returns 0 if ok, error value on error.
+ * Note: if @tp is within a module, the caller is responsible for
+ * unregistering the probe before the module is gone. This can be
+ * performed either with a tracepoint module going notifier, or from
+ * within module exit functions.
  */
-int tracepoint_probe_register(const char *name, void *probe, void *data)
+int tracepoint_probe_register(struct tracepoint *tp, void *probe, void *data)
 {
-	struct tracepoint_func *old;
-	struct tracepoint_entry *entry;
-	int ret = 0;
+	struct tracepoint_func tp_func;
+	int ret;
 
 	mutex_lock(&tracepoints_mutex);
-	old = tracepoint_add_probe(name, probe, data);
-	if (IS_ERR(old)) {
-		mutex_unlock(&tracepoints_mutex);
-		return PTR_ERR(old);
-	}
-	tracepoint_update_probes();		/* may update entry */
-	entry = get_tracepoint(name);
-	/* Make sure the entry was enabled */
-	if (!entry || !entry->enabled)
-		ret = -ENODEV;
+	tp_func.func = probe;
+	tp_func.data = data;
+	ret = tracepoint_add_func(tp, &tp_func);
 	mutex_unlock(&tracepoints_mutex);
-	release_probes(old);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(tracepoint_probe_register);
 
-static struct tracepoint_func *
-tracepoint_remove_probe(const char *name, void *probe, void *data)
-{
-	struct tracepoint_entry *entry;
-	struct tracepoint_func *old;
-
-	entry = get_tracepoint(name);
-	if (!entry)
-		return ERR_PTR(-ENOENT);
-	old = tracepoint_entry_remove_probe(entry, probe, data);
-	if (IS_ERR(old))
-		return old;
-	if (!entry->refcount)
-		remove_tracepoint(entry);
-	return old;
-}
-
 /**
  * tracepoint_probe_unregister -  Disconnect a probe from a tracepoint
- * @name: tracepoint name
+ * @tp: tracepoint
  * @probe: probe function pointer
- * @data: probe private data
  *
- * We do not need to call a synchronize_sched to make sure the probes have
- * finished running before doing a module unload, because the module unload
- * itself uses stop_machine(), which insures that every preempt disabled section
- * have finished.
+ * Returns 0 if ok, error value on error.
  */
-int tracepoint_probe_unregister(const char *name, void *probe, void *data)
+int tracepoint_probe_unregister(struct tracepoint *tp, void *probe, void *data)
 {
-	struct tracepoint_func *old;
+	struct tracepoint_func tp_func;
+	int ret;
 
 	mutex_lock(&tracepoints_mutex);
-	old = tracepoint_remove_probe(name, probe, data);
-	if (IS_ERR(old)) {
-		mutex_unlock(&tracepoints_mutex);
-		return PTR_ERR(old);
-	}
-	tracepoint_update_probes();		/* may update entry */
+	tp_func.func = probe;
+	tp_func.data = data;
+	ret = tracepoint_remove_func(tp, &tp_func);
 	mutex_unlock(&tracepoints_mutex);
-	release_probes(old);
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(tracepoint_probe_unregister);
 
-
 #ifdef CONFIG_MODULES
 bool trace_module_has_bad_taint(struct module *mod)
 {
 	return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP));
 }
 
+static BLOCKING_NOTIFIER_HEAD(tracepoint_notify_list);
+
+/**
+ * register_tracepoint_notifier - register tracepoint coming/going notifier
+ * @nb: notifier block
+ *
+ * Notifiers registered with this function are called on module
+ * coming/going with the tracepoint_module_list_mutex held.
+ * The notifier block callback should expect a "struct tp_module" data
+ * pointer.
+ */
+int register_tracepoint_module_notifier(struct notifier_block *nb)
+{
+	struct tp_module *tp_mod;
+	int ret;
+
+	mutex_lock(&tracepoint_module_list_mutex);
+	ret = blocking_notifier_chain_register(&tracepoint_notify_list, nb);
+	if (ret)
+		goto end;
+	list_for_each_entry(tp_mod, &tracepoint_module_list, list)
+		(void) nb->notifier_call(nb, MODULE_STATE_COMING, tp_mod);
+end:
+	mutex_unlock(&tracepoint_module_list_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(register_tracepoint_module_notifier);
+
+/**
+ * unregister_tracepoint_notifier - unregister tracepoint coming/going notifier
+ * @nb: notifier block
+ *
+ * The notifier block callback should expect a "struct tp_module" data
+ * pointer.
+ */
+int unregister_tracepoint_module_notifier(struct notifier_block *nb)
+{
+	struct tp_module *tp_mod;
+	int ret;
+
+	mutex_lock(&tracepoint_module_list_mutex);
+	ret = blocking_notifier_chain_unregister(&tracepoint_notify_list, nb);
+	if (ret)
+		goto end;
+	list_for_each_entry(tp_mod, &tracepoint_module_list, list)
+		(void) nb->notifier_call(nb, MODULE_STATE_GOING, tp_mod);
+end:
+	mutex_unlock(&tracepoint_module_list_mutex);
+	return ret;
+
+}
+EXPORT_SYMBOL_GPL(unregister_tracepoint_module_notifier);
+
+/*
+ * Ensure the tracer unregistered the module's probes before the module
+ * teardown is performed. Prevents leaks of probe and data pointers.
+ */
+static void tp_module_going_check_quiescent(struct tracepoint * const *begin,
+		struct tracepoint * const *end)
+{
+	struct tracepoint * const *iter;
+
+	if (!begin)
+		return;
+	for (iter = begin; iter < end; iter++)
+		WARN_ON_ONCE((*iter)->funcs);
+}
+
 static int tracepoint_module_coming(struct module *mod)
 {
 	struct tp_module *tp_mod;
@@ -478,7 +368,7 @@ static int tracepoint_module_coming(struct module *mod)
 	 */
 	if (trace_module_has_bad_taint(mod))
 		return 0;
-	mutex_lock(&tracepoints_mutex);
+	mutex_lock(&tracepoint_module_list_mutex);
 	tp_mod = kmalloc(sizeof(struct tp_module), GFP_KERNEL);
 	if (!tp_mod) {
 		ret = -ENOMEM;
@@ -487,27 +377,33 @@ static int tracepoint_module_coming(struct module *mod)
 	tp_mod->num_tracepoints = mod->num_tracepoints;
 	tp_mod->tracepoints_ptrs = mod->tracepoints_ptrs;
 	list_add_tail(&tp_mod->list, &tracepoint_module_list);
-	tracepoint_update_probe_range(mod->tracepoints_ptrs,
-		mod->tracepoints_ptrs + mod->num_tracepoints);
+	blocking_notifier_call_chain(&tracepoint_notify_list,
+			MODULE_STATE_COMING, tp_mod);
 end:
-	mutex_unlock(&tracepoints_mutex);
+	mutex_unlock(&tracepoint_module_list_mutex);
 	return ret;
 }
 
-static int tracepoint_module_going(struct module *mod)
+static void tracepoint_module_going(struct module *mod)
 {
-	struct tp_module *pos;
+	struct tp_module *tp_mod;
 
 	if (!mod->num_tracepoints)
-		return 0;
+		return;
 
-	mutex_lock(&tracepoints_mutex);
-	tracepoint_update_probe_range(mod->tracepoints_ptrs,
-		mod->tracepoints_ptrs + mod->num_tracepoints);
-	list_for_each_entry(pos, &tracepoint_module_list, list) {
-		if (pos->tracepoints_ptrs == mod->tracepoints_ptrs) {
-			list_del(&pos->list);
-			kfree(pos);
+	mutex_lock(&tracepoint_module_list_mutex);
+	list_for_each_entry(tp_mod, &tracepoint_module_list, list) {
+		if (tp_mod->tracepoints_ptrs == mod->tracepoints_ptrs) {
+			blocking_notifier_call_chain(&tracepoint_notify_list,
+					MODULE_STATE_GOING, tp_mod);
+			list_del(&tp_mod->list);
+			kfree(tp_mod);
+			/*
+			 * Called the going notifier before checking for
+			 * quiescence.
+			 */
+			tp_module_going_check_quiescent(mod->tracepoints_ptrs,
+				mod->tracepoints_ptrs + mod->num_tracepoints);
 			break;
 		}
 	}
@@ -517,12 +413,11 @@ static int tracepoint_module_going(struct module *mod)
 	 * flag on "going", in case a module taints the kernel only after being
 	 * loaded.
 	 */
-	mutex_unlock(&tracepoints_mutex);
-	return 0;
+	mutex_unlock(&tracepoint_module_list_mutex);
 }
 
-int tracepoint_module_notify(struct notifier_block *self,
-			     unsigned long val, void *data)
+static int tracepoint_module_notify(struct notifier_block *self,
+		unsigned long val, void *data)
 {
 	struct module *mod = data;
 	int ret = 0;
@@ -534,24 +429,58 @@ int tracepoint_module_notify(struct notifier_block *self,
 	case MODULE_STATE_LIVE:
 		break;
 	case MODULE_STATE_GOING:
-		ret = tracepoint_module_going(mod);
+		tracepoint_module_going(mod);
+		break;
+	case MODULE_STATE_UNFORMED:
 		break;
 	}
 	return ret;
 }
 
-struct notifier_block tracepoint_module_nb = {
+static struct notifier_block tracepoint_module_nb = {
 	.notifier_call = tracepoint_module_notify,
 	.priority = 0,
 };
 
-static int init_tracepoints(void)
+static __init int init_tracepoints(void)
 {
-	return register_module_notifier(&tracepoint_module_nb);
+	int ret;
+
+	ret = register_module_notifier(&tracepoint_module_nb);
+	if (ret) {
+		pr_warning("Failed to register tracepoint module enter notifier\n");
+	}
+	return ret;
 }
 __initcall(init_tracepoints);
 #endif /* CONFIG_MODULES */
 
+static void for_each_tracepoint_range(struct tracepoint * const *begin,
+		struct tracepoint * const *end,
+		void (*fct)(struct tracepoint *tp, void *priv),
+		void *priv)
+{
+	struct tracepoint * const *iter;
+
+	if (!begin)
+		return;
+	for (iter = begin; iter < end; iter++)
+		fct(*iter, priv);
+}
+
+/**
+ * for_each_kernel_tracepoint - iteration on all kernel tracepoints
+ * @fct: callback
+ * @priv: private data
+ */
+void for_each_kernel_tracepoint(void (*fct)(struct tracepoint *tp, void *priv),
+		void *priv)
+{
+	for_each_tracepoint_range(__start___tracepoints_ptrs,
+		__stop___tracepoints_ptrs, fct, priv);
+}
+EXPORT_SYMBOL_GPL(for_each_kernel_tracepoint);
+
 #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
 
 /* NB: reg/unreg are called while guarded with the tracepoints_mutex */
-- 
cgit v1.2.3


From eb7d035c59431bb12e1aa6e69ddd3940352faddb Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Tue, 8 Apr 2014 20:09:40 -0400
Subject: tracepoint: Simplify tracepoint module search

Instead of copying the num_tracepoints and tracepoints_ptrs from
the module structure to the tp_mod structure, which only uses it to
find the module associated to tracepoints of modules that are coming
and going, simply copy the pointer to the module struct to the tracepoint
tp_module structure.

Also removed un-needed brackets around an if statement.

Link: http://lkml.kernel.org/r/20140408201705.4dad2c4a@gandalf.local.home

Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/tracepoint.h | 3 +--
 kernel/tracepoint.c        | 9 ++++-----
 2 files changed, 5 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 08150e265761..69a298b07357 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -47,8 +47,7 @@ for_each_kernel_tracepoint(void (*fct)(struct tracepoint *tp, void *priv),
 #ifdef CONFIG_MODULES
 struct tp_module {
 	struct list_head list;
-	unsigned int num_tracepoints;
-	struct tracepoint * const *tracepoints_ptrs;
+	struct module *mod;
 };
 
 bool trace_module_has_bad_taint(struct module *mod);
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 01b3bd84daa1..162be198a247 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -374,8 +374,7 @@ static int tracepoint_module_coming(struct module *mod)
 		ret = -ENOMEM;
 		goto end;
 	}
-	tp_mod->num_tracepoints = mod->num_tracepoints;
-	tp_mod->tracepoints_ptrs = mod->tracepoints_ptrs;
+	tp_mod->mod = mod;
 	list_add_tail(&tp_mod->list, &tracepoint_module_list);
 	blocking_notifier_call_chain(&tracepoint_notify_list,
 			MODULE_STATE_COMING, tp_mod);
@@ -393,7 +392,7 @@ static void tracepoint_module_going(struct module *mod)
 
 	mutex_lock(&tracepoint_module_list_mutex);
 	list_for_each_entry(tp_mod, &tracepoint_module_list, list) {
-		if (tp_mod->tracepoints_ptrs == mod->tracepoints_ptrs) {
+		if (tp_mod->mod == mod) {
 			blocking_notifier_call_chain(&tracepoint_notify_list,
 					MODULE_STATE_GOING, tp_mod);
 			list_del(&tp_mod->list);
@@ -447,9 +446,9 @@ static __init int init_tracepoints(void)
 	int ret;
 
 	ret = register_module_notifier(&tracepoint_module_nb);
-	if (ret) {
+	if (ret)
 		pr_warning("Failed to register tracepoint module enter notifier\n");
-	}
+
 	return ret;
 }
 __initcall(init_tracepoints);
-- 
cgit v1.2.3


From b7aa84d9cb9f26da1a9312c3e39dbd1a3c25a426 Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Tue, 8 Apr 2014 22:43:43 -0400
Subject: block: Fix for_each_bvec()

Commit 4550dd6c6b062 introduced for_each_bvec() which iterates over each
bvec attached to a bio or bip. However, the macro fails to check bi_size
before dereferencing which can lead to crashes while counting/mapping
integrity scatterlist segments.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Cc: Kent Overstreet <kmo@daterainc.com>
Cc: Nicholas Bellinger <nab@linux-iscsi.org>
Cc: <stable@vger.kernel.org> # v3.14+
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 include/linux/bio.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 5a4d39b4686b..5aa372a7380c 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -216,9 +216,9 @@ static inline void bvec_iter_advance(struct bio_vec *bv, struct bvec_iter *iter,
 }
 
 #define for_each_bvec(bvl, bio_vec, iter, start)			\
-	for ((iter) = start;						\
-	     (bvl) = bvec_iter_bvec((bio_vec), (iter)),			\
-		(iter).bi_size;						\
+	for (iter = (start);						\
+	     (iter).bi_size &&						\
+		((bvl = bvec_iter_bvec((bio_vec), (iter))), 1);	\
 	     bvec_iter_advance((bio_vec), &(iter), (bvl).bv_len))
 
 
-- 
cgit v1.2.3


From b725dfea24b89de672c055b34b22398283a3f4bc Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Date: Wed, 9 Apr 2014 09:24:43 -0400
Subject: tracepoint: Fix sparse warnings in tracepoint.c

Fix the following sparse warnings:

  CHECK   kernel/tracepoint.c
kernel/tracepoint.c:184:18: warning: incorrect type in assignment (different address spaces)
kernel/tracepoint.c:184:18:    expected struct tracepoint_func *tp_funcs
kernel/tracepoint.c:184:18:    got struct tracepoint_func [noderef] <asn:4>*funcs
kernel/tracepoint.c:216:18: warning: incorrect type in assignment (different address spaces)
kernel/tracepoint.c:216:18:    expected struct tracepoint_func *tp_funcs
kernel/tracepoint.c:216:18:    got struct tracepoint_func [noderef] <asn:4>*funcs
kernel/tracepoint.c:392:24: error: return expression in void function
  CC      kernel/tracepoint.o
kernel/tracepoint.c: In function tracepoint_module_going:
kernel/tracepoint.c:491:6: warning: symbol 'syscall_regfunc' was not declared. Should it be static?
kernel/tracepoint.c:508:6: warning: symbol 'syscall_unregfunc' was not declared. Should it be static?

Link: http://lkml.kernel.org/r/1397049883-28692-1-git-send-email-mathieu.desnoyers@efficios.com

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/tracepoint.h      | 5 +++++
 include/trace/events/syscalls.h | 3 ---
 kernel/tracepoint.c             | 6 ++++--
 3 files changed, 9 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 69a298b07357..9d30ee469c2a 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -80,6 +80,11 @@ static inline void tracepoint_synchronize_unregister(void)
 	synchronize_sched();
 }
 
+#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
+extern void syscall_regfunc(void);
+extern void syscall_unregfunc(void);
+#endif /* CONFIG_HAVE_SYSCALL_TRACEPOINTS */
+
 #define PARAMS(args...) args
 
 #endif /* _LINUX_TRACEPOINT_H */
diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h
index 5a4c04a75b3d..14e49c798135 100644
--- a/include/trace/events/syscalls.h
+++ b/include/trace/events/syscalls.h
@@ -13,9 +13,6 @@
 
 #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
 
-extern void syscall_regfunc(void);
-extern void syscall_unregfunc(void);
-
 TRACE_EVENT_FN(sys_enter,
 
 	TP_PROTO(struct pt_regs *regs, long id),
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 162be198a247..ca2cfe21bb8e 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -181,7 +181,8 @@ static int tracepoint_add_func(struct tracepoint *tp,
 	if (tp->regfunc && !static_key_enabled(&tp->key))
 		tp->regfunc();
 
-	tp_funcs = tp->funcs;
+	tp_funcs = rcu_dereference_protected(tp->funcs,
+			lockdep_is_held(&tracepoints_mutex));
 	old = func_add(&tp_funcs, func);
 	if (IS_ERR(old)) {
 		WARN_ON_ONCE(1);
@@ -213,7 +214,8 @@ static int tracepoint_remove_func(struct tracepoint *tp,
 {
 	struct tracepoint_func *old, *tp_funcs;
 
-	tp_funcs = tp->funcs;
+	tp_funcs = rcu_dereference_protected(tp->funcs,
+			lockdep_is_held(&tracepoints_mutex));
 	old = func_remove(&tp_funcs, func);
 	if (IS_ERR(old)) {
 		WARN_ON_ONCE(1);
-- 
cgit v1.2.3


From 565cbdc2fec92ef2ae75995e06e69172ed2edecd Mon Sep 17 00:00:00 2001
From: Mark Charlebois <charlebm@gmail.com>
Date: Tue, 20 Nov 2012 22:13:10 +0100
Subject: LLVMLinux: Add support for clang to compiler.h and new
 compiler-clang.h

Add a compiler-clang.h file to add specific macros needed for compiling the
kernel with clang.

Initially the only override required is the macro for silencing the
compiler for a purposefully uninintialized variable.

Author: Mark Charlebois <charlebm@gmail.com>
Signed-off-by: Mark Charlebois <charlebm@gmail.com>
Signed-off-by: Behan Webster <behanw@converseincode.com>
---
 include/linux/compiler-clang.h | 12 ++++++++++++
 include/linux/compiler.h       |  7 +++++++
 2 files changed, 19 insertions(+)
 create mode 100644 include/linux/compiler-clang.h

(limited to 'include/linux')

diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
new file mode 100644
index 000000000000..d1e49d52b640
--- /dev/null
+++ b/include/linux/compiler-clang.h
@@ -0,0 +1,12 @@
+#ifndef __LINUX_COMPILER_H
+#error "Please don't include <linux/compiler-clang.h> directly, include <linux/compiler.h> instead."
+#endif
+
+/* Some compiler specific definitions are overwritten here
+ * for Clang compiler
+ */
+
+#ifdef uninitialized_var
+#undef uninitialized_var
+#define uninitialized_var(x) x = *(&(x))
+#endif
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 2472740d7ab2..ee7239ea1583 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -63,6 +63,13 @@ extern void __chk_io_ptr(const volatile void __iomem *);
 # include <linux/compiler-intel.h>
 #endif
 
+/* Clang compiler defines __GNUC__. So we will overwrite implementations
+ * coming from above header files here
+ */
+#ifdef __clang__
+#include <linux/compiler-clang.h>
+#endif
+
 /*
  * Generic compiler-dependent macros required for kernel
  * build go below this comment. Actual compiler/compiler version
-- 
cgit v1.2.3


From c4586256f0c440bc2bdb29d2cbb915f0ca785d26 Mon Sep 17 00:00:00 2001
From: Behan Webster <behanw@converseincode.com>
Date: Thu, 13 Feb 2014 12:21:48 -0800
Subject: x86: LLVMLinux: Fix "incomplete type const struct x86cpu_device_id"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Similar to the fix in 40413dcb7b273bda681dca38e6ff0bbb3728ef11

MODULE_DEVICE_TABLE(x86cpu, ...) expects the struct to be called struct
x86cpu_device_id, and not struct x86_cpu_id which is what is used in the rest
of the kernel code.  Although gcc seems to ignore this error, clang fails
without this define to fix the name.

Code from drivers/thermal/x86_pkg_temp_thermal.c
static const struct x86_cpu_id __initconst pkg_temp_thermal_ids[] = { ... };
MODULE_DEVICE_TABLE(x86cpu, pkg_temp_thermal_ids);

Error from clang:
drivers/thermal/x86_pkg_temp_thermal.c:577:1: error: variable has
      incomplete type 'const struct x86cpu_device_id'
MODULE_DEVICE_TABLE(x86cpu, pkg_temp_thermal_ids);
^
include/linux/module.h:145:3: note: expanded from macro
      'MODULE_DEVICE_TABLE'
  MODULE_GENERIC_TABLE(type##_device, name)
  ^
include/linux/module.h:87:32: note: expanded from macro
      'MODULE_GENERIC_TABLE'
extern const struct gtype##_id __mod_##gtype##_table            \
                               ^
<scratch space>:143:1: note: expanded from here
__mod_x86cpu_device_table
^
drivers/thermal/x86_pkg_temp_thermal.c:577:1: note: forward declaration of
      'struct x86cpu_device_id'
include/linux/module.h:145:3: note: expanded from macro
      'MODULE_DEVICE_TABLE'
  MODULE_GENERIC_TABLE(type##_device, name)
  ^
include/linux/module.h:87:21: note: expanded from macro
      'MODULE_GENERIC_TABLE'
extern const struct gtype##_id __mod_##gtype##_table            \
                    ^
<scratch space>:141:1: note: expanded from here
x86cpu_device_id
^
1 error generated.

Signed-off-by: Behan Webster <behanw@converseincode.com>
Signed-off-by: Jan-Simon Möller <dl9pf@gmx.de>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/mod_devicetable.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 9a165a213d93..44eeef0da186 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -556,6 +556,11 @@ struct amba_id {
  * See documentation of "x86_match_cpu" for details.
  */
 
+/*
+ * MODULE_DEVICE_TABLE expects this struct to be called x86cpu_device_id.
+ * Although gcc seems to ignore this error, clang fails without this define.
+ */
+#define x86cpu_device_id x86_cpu_id
 struct x86_cpu_id {
 	__u16 vendor;
 	__u16 family;
-- 
cgit v1.2.3


From abb43f6998eb6466ea392d3757e673bbdb6ae171 Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Date: Wed, 9 Apr 2014 17:06:08 -0400
Subject: tracing: Fix anonymous unions in struct ftrace_event_call

gcc <= 4.5.x has significant limitations with respect to initialization
of anonymous unions within structures. They need to be surrounded by
brackets, _and_ they need to be initialized in the same order in which
they appear in the structure declaration.

Link: http://gcc.gnu.org/bugzilla/show_bug.cgi?id=10676
Link: http://lkml.kernel.org/r/1397077568-3156-1-git-send-email-mathieu.desnoyers@efficios.com

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/syscalls.h    |  8 ++++++--
 include/trace/ftrace.h      | 12 +++++++++---
 kernel/trace/trace_export.c |  6 ++++--
 3 files changed, 19 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 1e67b7a5968c..af94c98087c4 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -119,8 +119,10 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 	static struct syscall_metadata __syscall_meta_##sname;		\
 	static struct ftrace_event_call __used				\
 	  event_enter_##sname = {					\
-		.name                   = "sys_enter"#sname,		\
 		.class			= &event_class_syscall_enter,	\
+		{							\
+			.name                   = "sys_enter"#sname,	\
+		},							\
 		.event.funcs            = &enter_syscall_print_funcs,	\
 		.data			= (void *)&__syscall_meta_##sname,\
 		.flags                  = TRACE_EVENT_FL_CAP_ANY,	\
@@ -133,8 +135,10 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 	static struct syscall_metadata __syscall_meta_##sname;		\
 	static struct ftrace_event_call __used				\
 	  event_exit_##sname = {					\
-		.name                   = "sys_exit"#sname,		\
 		.class			= &event_class_syscall_exit,	\
+		{							\
+			.name                   = "sys_exit"#sname,	\
+		},							\
 		.event.funcs		= &exit_syscall_print_funcs,	\
 		.data			= (void *)&__syscall_meta_##sname,\
 		.flags                  = TRACE_EVENT_FL_CAP_ANY,	\
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 9c44c11cd9bb..0a1a4f7caf09 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -470,8 +470,10 @@ static inline notrace int ftrace_get_offsets_##call(			\
  * };
  *
  * static struct ftrace_event_call event_<call> = {
- *	.tp			= &__tracepoint_<call>,
  *	.class			= event_class_<template>,
+ *	{
+ *		.tp			= &__tracepoint_<call>,
+ *	},
  *	.event			= &ftrace_event_type_<call>,
  *	.print_fmt		= print_fmt_<call>,
  *	.flags			= TRACE_EVENT_FL_TRACEPOINT,
@@ -606,8 +608,10 @@ static struct ftrace_event_class __used __refdata event_class_##call = { \
 #define DEFINE_EVENT(template, call, proto, args)			\
 									\
 static struct ftrace_event_call __used event_##call = {			\
-	.tp			= &__tracepoint_##call,			\
 	.class			= &event_class_##template,		\
+	{								\
+		.tp			= &__tracepoint_##call,		\
+	},								\
 	.event.funcs		= &ftrace_event_type_funcs_##template,	\
 	.print_fmt		= print_fmt_##template,			\
 	.flags			= TRACE_EVENT_FL_TRACEPOINT,		\
@@ -621,8 +625,10 @@ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
 static const char print_fmt_##call[] = print;				\
 									\
 static struct ftrace_event_call __used event_##call = {			\
-	.tp			= &__tracepoint_##call,			\
 	.class			= &event_class_##template,		\
+	{								\
+		.tp			= &__tracepoint_##call,		\
+	},								\
 	.event.funcs		= &ftrace_event_type_funcs_##call,	\
 	.print_fmt		= print_fmt_##call,			\
 	.flags			= TRACE_EVENT_FL_TRACEPOINT,		\
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index ee0a5098ac43..d4ddde28a81a 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -173,9 +173,11 @@ struct ftrace_event_class __refdata event_class_ftrace_##call = {	\
 };									\
 									\
 struct ftrace_event_call __used event_##call = {			\
-	.name			= #call,				\
-	.event.type		= etype,				\
 	.class			= &event_class_ftrace_##call,		\
+	{								\
+		.name			= #call,			\
+	},								\
+	.event.type		= etype,				\
 	.print_fmt		= print,				\
 	.flags			= TRACE_EVENT_FL_IGNORE_ENABLE | TRACE_EVENT_FL_USE_CALL_FILTER, \
 };									\
-- 
cgit v1.2.3


From 360f92c2443073143467a0088daffec96a17910b Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@fb.com>
Date: Wed, 9 Apr 2014 20:27:01 -0600
Subject: block: fix regression with block enabled tagging

Martin reported that his test system would not boot with
current git, it oopsed with this:

BUG: unable to handle kernel paging request at ffff88046c6c9e80
IP: [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150
PGD 1ddf067 PUD 1de2067 PMD 47fc7d067 PTE 800000046c6c9060
Oops: 0002 [#1] SMP DEBUG_PAGEALLOC
Modules linked in: sd_mod lpfc(+) scsi_transport_fc scsi_tgt oracleasm
rpcsec_gss_krb5 ipv6 igb dca i2c_algo_bit i2c_core hwmon
CPU: 3 PID: 87 Comm: kworker/u17:1 Not tainted 3.14.0+ #246
Hardware name: Supermicro X9DRX+-F/X9DRX+-F, BIOS 3.00 07/09/2013
Workqueue: events_unbound async_run_entry_fn
task: ffff8802743c2150 ti: ffff880273d02000 task.ti: ffff880273d02000
RIP: 0010:[<ffffffff812971e0>]  [<ffffffff812971e0>]
blk_queue_start_tag+0x90/0x150
RSP: 0018:ffff880273d03a58  EFLAGS: 00010092
RAX: ffff88046c6c9e78 RBX: ffff880077208e78 RCX: 00000000fffc8da6
RDX: 00000000fffc186d RSI: 0000000000000009 RDI: 00000000fffc8d9d
RBP: ffff880273d03a88 R08: 0000000000000001 R09: ffff8800021c2410
R10: 0000000000000005 R11: 0000000000015b30 R12: ffff88046c5bb8a0
R13: ffff88046c5c0890 R14: 000000000000001e R15: 000000000000001e
FS:  0000000000000000(0000) GS:ffff880277b00000(0000)
knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffff88046c6c9e80 CR3: 00000000018f6000 CR4: 00000000000407e0
Stack:
 ffff880273d03a98 ffff880474b18800 0000000000000000 ffff880474157000
 ffff88046c5c0890 ffff880077208e78 ffff880273d03ae8 ffffffff813b9e62
 ffff880200000010 ffff880474b18968 ffff880474b18848 ffff88046c5c0cd8
Call Trace:
 [<ffffffff813b9e62>] scsi_request_fn+0xf2/0x510
 [<ffffffff81293167>] __blk_run_queue+0x37/0x50
 [<ffffffff8129ac43>] blk_execute_rq_nowait+0xb3/0x130
 [<ffffffff8129ad24>] blk_execute_rq+0x64/0xf0
 [<ffffffff8108d2b0>] ? bit_waitqueue+0xd0/0xd0
 [<ffffffff813bba35>] scsi_execute+0xe5/0x180
 [<ffffffff813bbe4a>] scsi_execute_req_flags+0x9a/0x110
 [<ffffffffa01b1304>] sd_spinup_disk+0x94/0x460 [sd_mod]
 [<ffffffff81160000>] ? __unmap_hugepage_range+0x200/0x2f0
 [<ffffffffa01b2b9a>] sd_revalidate_disk+0xaa/0x3f0 [sd_mod]
 [<ffffffffa01b2fb8>] sd_probe_async+0xd8/0x200 [sd_mod]
 [<ffffffff8107703f>] async_run_entry_fn+0x3f/0x140
 [<ffffffff8106a1c5>] process_one_work+0x175/0x410
 [<ffffffff8106b373>] worker_thread+0x123/0x400
 [<ffffffff8106b250>] ? manage_workers+0x160/0x160
 [<ffffffff8107104e>] kthread+0xce/0xf0
 [<ffffffff81070f80>] ? kthread_freezable_should_stop+0x70/0x70
 [<ffffffff815f0bac>] ret_from_fork+0x7c/0xb0
 [<ffffffff81070f80>] ? kthread_freezable_should_stop+0x70/0x70
Code: 48 0f ab 11 72 db 48 81 4b 40 00 00 10 00 89 83 08 01 00 00 48 89
df 49 8b 04 24 48 89 1c d0 e8 f7 a8 ff ff 49 8b 85 28 05 00 00 <48> 89
58 08 48 89 03 49 8d 85 28 05 00 00 48 89 43 08 49 89 9d
RIP  [<ffffffff812971e0>] blk_queue_start_tag+0x90/0x150
 RSP <ffff880273d03a58>
CR2: ffff88046c6c9e80

Martin bisected and found this to be the problem patch;

	commit 6d113398dcf4dfcd9787a4ead738b186f7b7ff0f
	Author: Jan Kara <jack@suse.cz>
	Date:   Mon Feb 24 16:39:54 2014 +0100

	    block: Stop abusing rq->csd.list in blk-softirq

and the problem was immediately apparent. The patch states that
it is safe to reuse queuelist at completion time, since it is
no longer used. However, that is not true if a device is using
block enabled tagging. If that is the case, then the queuelist
is reused to keep track of busy tags. If a device also ended
up using softirq completions, we'd reuse ->queuelist for the
IPI handling while block tagging was still using it. Boom.

Fix this by adding a new ipi_list list head, and share the
memory used with the request hash table. The hash table is
never used after the request is moved to the dispatch list,
which happens long before any potential completion of the
request. Add a new request bit for this, so we don't have
cases that check rq->hash while it could potentially have
been reused for the IPI completion.

Reported-by: Martin K. Petersen <martin.petersen@oracle.com>
Tested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
---
 block/blk-core.c          |  2 +-
 block/blk-softirq.c       | 17 ++++++-----------
 block/blk.h               |  2 +-
 block/elevator.c          |  2 ++
 include/linux/blk_types.h |  2 ++
 include/linux/blkdev.h    | 13 ++++++++++++-
 6 files changed, 24 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-core.c b/block/blk-core.c
index 34d7c196338b..a0e3096c4bb5 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1307,7 +1307,7 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 		struct request_list *rl = blk_rq_rl(req);
 
 		BUG_ON(!list_empty(&req->queuelist));
-		BUG_ON(!hlist_unhashed(&req->hash));
+		BUG_ON(ELV_ON_HASH(req));
 
 		blk_free_request(rl, req);
 		freed_request(rl, flags);
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index ebd6b6f1bdeb..53b1737e978d 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -30,8 +30,8 @@ static void blk_done_softirq(struct softirq_action *h)
 	while (!list_empty(&local_list)) {
 		struct request *rq;
 
-		rq = list_entry(local_list.next, struct request, queuelist);
-		list_del_init(&rq->queuelist);
+		rq = list_entry(local_list.next, struct request, ipi_list);
+		list_del_init(&rq->ipi_list);
 		rq->q->softirq_done_fn(rq);
 	}
 }
@@ -45,14 +45,9 @@ static void trigger_softirq(void *data)
 
 	local_irq_save(flags);
 	list = this_cpu_ptr(&blk_cpu_done);
-	/*
-	 * We reuse queuelist for a list of requests to process. Since the
-	 * queuelist is used by the block layer only for requests waiting to be
-	 * submitted to the device it is unused now.
-	 */
-	list_add_tail(&rq->queuelist, list);
+	list_add_tail(&rq->ipi_list, list);
 
-	if (list->next == &rq->queuelist)
+	if (list->next == &rq->ipi_list)
 		raise_softirq_irqoff(BLOCK_SOFTIRQ);
 
 	local_irq_restore(flags);
@@ -141,7 +136,7 @@ void __blk_complete_request(struct request *req)
 		struct list_head *list;
 do_local:
 		list = this_cpu_ptr(&blk_cpu_done);
-		list_add_tail(&req->queuelist, list);
+		list_add_tail(&req->ipi_list, list);
 
 		/*
 		 * if the list only contains our just added request,
@@ -149,7 +144,7 @@ do_local:
 		 * entries there, someone already raised the irq but it
 		 * hasn't run yet.
 		 */
-		if (list->next == &req->queuelist)
+		if (list->next == &req->ipi_list)
 			raise_softirq_irqoff(BLOCK_SOFTIRQ);
 	} else if (raise_blk_irq(ccpu, req))
 		goto do_local;
diff --git a/block/blk.h b/block/blk.h
index d23b415b8a28..1d880f1f957f 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -78,7 +78,7 @@ static inline void blk_clear_rq_complete(struct request *rq)
 /*
  * Internal elevator interface
  */
-#define ELV_ON_HASH(rq) hash_hashed(&(rq)->hash)
+#define ELV_ON_HASH(rq) ((rq)->cmd_flags & REQ_HASHED)
 
 void blk_insert_flush(struct request *rq);
 void blk_abort_flushes(struct request_queue *q);
diff --git a/block/elevator.c b/block/elevator.c
index 42c45a7d6714..1e01b66a0b92 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -247,6 +247,7 @@ EXPORT_SYMBOL(elevator_exit);
 static inline void __elv_rqhash_del(struct request *rq)
 {
 	hash_del(&rq->hash);
+	rq->cmd_flags &= ~REQ_HASHED;
 }
 
 static void elv_rqhash_del(struct request_queue *q, struct request *rq)
@@ -261,6 +262,7 @@ static void elv_rqhash_add(struct request_queue *q, struct request *rq)
 
 	BUG_ON(ELV_ON_HASH(rq));
 	hash_add(e->hash, &rq->hash, rq_hash_key(rq));
+	rq->cmd_flags |= REQ_HASHED;
 }
 
 static void elv_rqhash_reposition(struct request_queue *q, struct request *rq)
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index bbc3a6c88fce..aa0eaa2d0bd8 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -189,6 +189,7 @@ enum rq_flag_bits {
 	__REQ_KERNEL, 		/* direct IO to kernel pages */
 	__REQ_PM,		/* runtime pm request */
 	__REQ_END,		/* last of chain of requests */
+	__REQ_HASHED,		/* on IO scheduler merge hash */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -241,5 +242,6 @@ enum rq_flag_bits {
 #define REQ_KERNEL		(1ULL << __REQ_KERNEL)
 #define REQ_PM			(1ULL << __REQ_PM)
 #define REQ_END			(1ULL << __REQ_END)
+#define REQ_HASHED		(1ULL << __REQ_HASHED)
 
 #endif /* __LINUX_BLK_TYPES_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1e1fa3f93d5f..99617cf7dd1a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -118,7 +118,18 @@ struct request {
 	struct bio *bio;
 	struct bio *biotail;
 
-	struct hlist_node hash;	/* merge hash */
+	/*
+	 * The hash is used inside the scheduler, and killed once the
+	 * request reaches the dispatch list. The ipi_list is only used
+	 * to queue the request for softirq completion, which is long
+	 * after the request has been unhashed (and even removed from
+	 * the dispatch list).
+	 */
+	union {
+		struct hlist_node hash;	/* merge hash */
+		struct list_head ipi_list;
+	};
+
 	/*
 	 * The rb_node is only used inside the io scheduler, requests
 	 * are pruned when moved to the dispatch queue. So let the
-- 
cgit v1.2.3


From 42f614201e80ff4cfb8b285d7190149a8e1e6cec Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Mon, 24 Mar 2014 10:46:25 -0600
Subject: NVMe: per-cpu io queues

The device's IO queues are associated with CPUs, so we can use a per-cpu
variable to map the a qid to a cpu. This provides a convienient way
to optimally assign queues to multiple cpus when the device supports
fewer queues than the host has cpus. The previous implementation may
have assigned these poorly in these situations. This patch addresses
this by sharing queues among cpus that are "close" together and should
have a lower lock contention penalty.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
---
 drivers/block/nvme-core.c | 204 +++++++++++++++++++++++++++++++++++++---------
 include/linux/nvme.h      |   6 +-
 2 files changed, 172 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index e9495f0bfad3..48d7bd55207a 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -20,6 +20,7 @@
 #include <linux/bio.h>
 #include <linux/bitops.h>
 #include <linux/blkdev.h>
+#include <linux/cpu.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
@@ -35,6 +36,7 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/pci.h>
+#include <linux/percpu.h>
 #include <linux/poison.h>
 #include <linux/ptrace.h>
 #include <linux/sched.h>
@@ -96,6 +98,7 @@ struct nvme_queue {
 	u8 cq_phase;
 	u8 cqe_seen;
 	u8 q_suspended;
+	cpumask_var_t cpu_mask;
 	struct async_cmd_info cmdinfo;
 	unsigned long cmdid_data[];
 };
@@ -270,14 +273,15 @@ static struct nvme_queue *raw_nvmeq(struct nvme_dev *dev, int qid)
 
 static struct nvme_queue *get_nvmeq(struct nvme_dev *dev) __acquires(RCU)
 {
+	unsigned queue_id = get_cpu_var(*dev->io_queue);
 	rcu_read_lock();
-	return rcu_dereference(dev->queues[get_cpu() + 1]);
+	return rcu_dereference(dev->queues[queue_id]);
 }
 
 static void put_nvmeq(struct nvme_queue *nvmeq) __releases(RCU)
 {
-	put_cpu();
 	rcu_read_unlock();
+	put_cpu_var(nvmeq->dev->io_queue);
 }
 
 static struct nvme_queue *lock_nvmeq(struct nvme_dev *dev, int q_idx)
@@ -1121,6 +1125,8 @@ static void nvme_free_queue(struct rcu_head *r)
 				(void *)nvmeq->cqes, nvmeq->cq_dma_addr);
 	dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
 					nvmeq->sq_cmds, nvmeq->sq_dma_addr);
+	if (nvmeq->qid)
+		free_cpumask_var(nvmeq->cpu_mask);
 	kfree(nvmeq);
 }
 
@@ -1128,8 +1134,6 @@ static void nvme_free_queues(struct nvme_dev *dev, int lowest)
 {
 	int i;
 
-	for (i = num_possible_cpus(); i > dev->queue_count - 1; i--)
-		rcu_assign_pointer(dev->queues[i], NULL);
 	for (i = dev->queue_count - 1; i >= lowest; i--) {
 		struct nvme_queue *nvmeq = raw_nvmeq(dev, i);
 		rcu_assign_pointer(dev->queues[i], NULL);
@@ -1154,6 +1158,7 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
 		return 1;
 	}
 	nvmeq->q_suspended = 1;
+	nvmeq->dev->online_queues--;
 	spin_unlock_irq(&nvmeq->q_lock);
 
 	irq_set_affinity_hint(vector, NULL);
@@ -1208,6 +1213,9 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 	if (!nvmeq->sq_cmds)
 		goto free_cqdma;
 
+	if (qid && !zalloc_cpumask_var(&nvmeq->cpu_mask, GFP_KERNEL))
+		goto free_sqdma;
+
 	nvmeq->q_dmadev = dmadev;
 	nvmeq->dev = dev;
 	snprintf(nvmeq->irqname, sizeof(nvmeq->irqname), "nvme%dq%d",
@@ -1228,6 +1236,9 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 
 	return nvmeq;
 
+ free_sqdma:
+	dma_free_coherent(dmadev, SQ_SIZE(depth), (void *)nvmeq->sq_cmds,
+							nvmeq->sq_dma_addr);
  free_cqdma:
 	dma_free_coherent(dmadev, CQ_SIZE(depth), (void *)nvmeq->cqes,
 							nvmeq->cq_dma_addr);
@@ -1260,6 +1271,7 @@ static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
 	memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth));
 	nvme_cancel_ios(nvmeq, false);
 	nvmeq->q_suspended = 0;
+	dev->online_queues++;
 }
 
 static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
@@ -1835,6 +1847,143 @@ static struct nvme_ns *nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid,
 	return NULL;
 }
 
+static int nvme_find_closest_node(int node)
+{
+	int n, val, min_val = INT_MAX, best_node = node;
+
+	for_each_online_node(n) {
+		if (n == node)
+			continue;
+		val = node_distance(node, n);
+		if (val < min_val) {
+			min_val = val;
+			best_node = n;
+		}
+	}
+	return best_node;
+}
+
+static void nvme_set_queue_cpus(cpumask_t *qmask, struct nvme_queue *nvmeq,
+								int count)
+{
+	int cpu;
+	for_each_cpu(cpu, qmask) {
+		if (cpumask_weight(nvmeq->cpu_mask) >= count)
+			break;
+		if (!cpumask_test_and_set_cpu(cpu, nvmeq->cpu_mask))
+			*per_cpu_ptr(nvmeq->dev->io_queue, cpu) = nvmeq->qid;
+	}
+}
+
+static void nvme_add_cpus(cpumask_t *mask, const cpumask_t *unassigned_cpus,
+	const cpumask_t *new_mask, struct nvme_queue *nvmeq, int cpus_per_queue)
+{
+	int next_cpu;
+	for_each_cpu(next_cpu, new_mask) {
+		cpumask_or(mask, mask, get_cpu_mask(next_cpu));
+		cpumask_or(mask, mask, topology_thread_cpumask(next_cpu));
+		cpumask_and(mask, mask, unassigned_cpus);
+		nvme_set_queue_cpus(mask, nvmeq, cpus_per_queue);
+	}
+}
+
+static void nvme_create_io_queues(struct nvme_dev *dev)
+{
+	unsigned i, max;
+
+	max = min(dev->max_qid, num_online_cpus());
+	for (i = dev->queue_count; i <= max; i++)
+		if (!nvme_alloc_queue(dev, i, dev->q_depth, i - 1))
+			break;
+
+	max = min(dev->queue_count - 1, num_online_cpus());
+	for (i = dev->online_queues; i <= max; i++)
+		if (nvme_create_queue(raw_nvmeq(dev, i), i))
+			break;
+}
+
+/*
+ * If there are fewer queues than online cpus, this will try to optimally
+ * assign a queue to multiple cpus by grouping cpus that are "close" together:
+ * thread siblings, core, socket, closest node, then whatever else is
+ * available.
+ */
+static void nvme_assign_io_queues(struct nvme_dev *dev)
+{
+	unsigned cpu, cpus_per_queue, queues, remainder, i;
+	cpumask_var_t unassigned_cpus;
+
+	nvme_create_io_queues(dev);
+
+	queues = min(dev->online_queues - 1, num_online_cpus());
+	if (!queues)
+		return;
+
+	cpus_per_queue = num_online_cpus() / queues;
+	remainder = queues - (num_online_cpus() - queues * cpus_per_queue);
+
+	if (!alloc_cpumask_var(&unassigned_cpus, GFP_KERNEL))
+		return;
+
+	cpumask_copy(unassigned_cpus, cpu_online_mask);
+	cpu = cpumask_first(unassigned_cpus);
+	for (i = 1; i <= queues; i++) {
+		struct nvme_queue *nvmeq = lock_nvmeq(dev, i);
+		cpumask_t mask;
+
+		cpumask_clear(nvmeq->cpu_mask);
+		if (!cpumask_weight(unassigned_cpus)) {
+			unlock_nvmeq(nvmeq);
+			break;
+		}
+
+		mask = *get_cpu_mask(cpu);
+		nvme_set_queue_cpus(&mask, nvmeq, cpus_per_queue);
+		if (cpus_weight(mask) < cpus_per_queue)
+			nvme_add_cpus(&mask, unassigned_cpus,
+				topology_thread_cpumask(cpu),
+				nvmeq, cpus_per_queue);
+		if (cpus_weight(mask) < cpus_per_queue)
+			nvme_add_cpus(&mask, unassigned_cpus,
+				topology_core_cpumask(cpu),
+				nvmeq, cpus_per_queue);
+		if (cpus_weight(mask) < cpus_per_queue)
+			nvme_add_cpus(&mask, unassigned_cpus,
+				cpumask_of_node(cpu_to_node(cpu)),
+				nvmeq, cpus_per_queue);
+		if (cpus_weight(mask) < cpus_per_queue)
+			nvme_add_cpus(&mask, unassigned_cpus,
+				cpumask_of_node(
+					nvme_find_closest_node(
+						cpu_to_node(cpu))),
+				nvmeq, cpus_per_queue);
+		if (cpus_weight(mask) < cpus_per_queue)
+			nvme_add_cpus(&mask, unassigned_cpus,
+				unassigned_cpus,
+				nvmeq, cpus_per_queue);
+
+		WARN(cpumask_weight(nvmeq->cpu_mask) != cpus_per_queue,
+			"nvme%d qid:%d mis-matched queue-to-cpu assignment\n",
+			dev->instance, i);
+
+		irq_set_affinity_hint(dev->entry[nvmeq->cq_vector].vector,
+							nvmeq->cpu_mask);
+		cpumask_andnot(unassigned_cpus, unassigned_cpus,
+						nvmeq->cpu_mask);
+		cpu = cpumask_next(cpu, unassigned_cpus);
+		if (remainder && !--remainder)
+			cpus_per_queue++;
+		unlock_nvmeq(nvmeq);
+	}
+	WARN(cpumask_weight(unassigned_cpus), "nvme%d unassigned online cpus\n",
+								dev->instance);
+	i = 0;
+	cpumask_andnot(unassigned_cpus, cpu_possible_mask, cpu_online_mask);
+	for_each_cpu(cpu, unassigned_cpus)
+		*per_cpu_ptr(dev->io_queue, cpu) = (i++ % queues) + 1;
+	free_cpumask_var(unassigned_cpus);
+}
+
 static int set_queue_count(struct nvme_dev *dev, int count)
 {
 	int status;
@@ -1857,9 +2006,9 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 {
 	struct nvme_queue *adminq = raw_nvmeq(dev, 0);
 	struct pci_dev *pdev = dev->pci_dev;
-	int result, cpu, i, vecs, nr_io_queues, size, q_depth;
+	int result, i, vecs, nr_io_queues, size;
 
-	nr_io_queues = num_online_cpus();
+	nr_io_queues = num_possible_cpus();
 	result = set_queue_count(dev, nr_io_queues);
 	if (result < 0)
 		return result;
@@ -1919,6 +2068,7 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	 * number of interrupts.
 	 */
 	nr_io_queues = vecs;
+	dev->max_qid = nr_io_queues;
 
 	result = queue_request_irq(dev, adminq, adminq->irqname);
 	if (result) {
@@ -1927,36 +2077,8 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	}
 
 	/* Free previously allocated queues that are no longer usable */
-	nvme_free_queues(dev, nr_io_queues);
-
-	cpu = cpumask_first(cpu_online_mask);
-	for (i = 0; i < nr_io_queues; i++) {
-		irq_set_affinity_hint(dev->entry[i].vector, get_cpu_mask(cpu));
-		cpu = cpumask_next(cpu, cpu_online_mask);
-	}
-
-	q_depth = min_t(int, NVME_CAP_MQES(readq(&dev->bar->cap)) + 1,
-								NVME_Q_DEPTH);
-	for (i = dev->queue_count - 1; i < nr_io_queues; i++) {
-		if (!nvme_alloc_queue(dev, i + 1, q_depth, i)) {
-			result = -ENOMEM;
-			goto free_queues;
-		}
-	}
-
-	for (; i < num_possible_cpus(); i++) {
-		int target = i % rounddown_pow_of_two(dev->queue_count - 1);
-		rcu_assign_pointer(dev->queues[i + 1], dev->queues[target + 1]);
-	}
-
-	for (i = 1; i < dev->queue_count; i++) {
-		result = nvme_create_queue(raw_nvmeq(dev, i), i);
-		if (result) {
-			for (--i; i > 0; i--)
-				nvme_disable_queue(dev, i);
-			goto free_queues;
-		}
-	}
+	nvme_free_queues(dev, nr_io_queues + 1);
+	nvme_assign_io_queues(dev);
 
 	return 0;
 
@@ -2035,6 +2157,7 @@ static int nvme_dev_add(struct nvme_dev *dev)
 
 static int nvme_dev_map(struct nvme_dev *dev)
 {
+	u64 cap;
 	int bars, result = -ENOMEM;
 	struct pci_dev *pdev = dev->pci_dev;
 
@@ -2058,7 +2181,9 @@ static int nvme_dev_map(struct nvme_dev *dev)
 		result = -ENODEV;
 		goto unmap;
 	}
-	dev->db_stride = 1 << NVME_CAP_STRIDE(readq(&dev->bar->cap));
+	cap = readq(&dev->bar->cap);
+	dev->q_depth = min_t(int, NVME_CAP_MQES(cap) + 1, NVME_Q_DEPTH);
+	dev->db_stride = 1 << NVME_CAP_STRIDE(cap);
 	dev->dbs = ((void __iomem *)dev->bar) + 4096;
 
 	return 0;
@@ -2332,6 +2457,7 @@ static void nvme_free_dev(struct kref *kref)
 	struct nvme_dev *dev = container_of(kref, struct nvme_dev, kref);
 
 	nvme_free_namespaces(dev);
+	free_percpu(dev->io_queue);
 	kfree(dev->queues);
 	kfree(dev->entry);
 	kfree(dev);
@@ -2477,6 +2603,9 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 								GFP_KERNEL);
 	if (!dev->queues)
 		goto free;
+	dev->io_queue = alloc_percpu(unsigned short);
+	if (!dev->io_queue)
+		goto free;
 
 	INIT_LIST_HEAD(&dev->namespaces);
 	INIT_WORK(&dev->reset_work, nvme_reset_failed_dev);
@@ -2526,6 +2655,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
  release:
 	nvme_release_instance(dev);
  free:
+	free_percpu(dev->io_queue);
 	kfree(dev->queues);
 	kfree(dev->entry);
 	kfree(dev);
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 7c3f85bc10f1..f0f95c719685 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -74,12 +74,16 @@ enum {
 struct nvme_dev {
 	struct list_head node;
 	struct nvme_queue __rcu **queues;
+	unsigned short __percpu *io_queue;
 	u32 __iomem *dbs;
 	struct pci_dev *pci_dev;
 	struct dma_pool *prp_page_pool;
 	struct dma_pool *prp_small_pool;
 	int instance;
-	int queue_count;
+	unsigned queue_count;
+	unsigned online_queues;
+	unsigned max_qid;
+	int q_depth;
 	u32 db_stride;
 	u32 ctrl_config;
 	struct msix_entry *entry;
-- 
cgit v1.2.3


From 33b1e95c90447ea73e37e837ea0268a894919f19 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Mon, 24 Mar 2014 10:46:26 -0600
Subject: NVMe: CPU hot plug notification

Registers with hot cpu notification to rebalance, and potentially allocate
additional, io queues.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
---
 drivers/block/nvme-core.c | 19 +++++++++++++++++++
 include/linux/nvme.h      |  1 +
 2 files changed, 20 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index 48d7bd55207a..ce5a4f1a3950 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -2002,6 +2002,19 @@ static size_t db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues)
 	return 4096 + ((nr_io_queues + 1) * 8 * dev->db_stride);
 }
 
+static int nvme_cpu_notify(struct notifier_block *self,
+				unsigned long action, void *hcpu)
+{
+	struct nvme_dev *dev = container_of(self, struct nvme_dev, nb);
+	switch (action) {
+	case CPU_ONLINE:
+	case CPU_DEAD:
+		nvme_assign_io_queues(dev);
+		break;
+	}
+	return NOTIFY_OK;
+}
+
 static int nvme_setup_io_queues(struct nvme_dev *dev)
 {
 	struct nvme_queue *adminq = raw_nvmeq(dev, 0);
@@ -2080,6 +2093,11 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	nvme_free_queues(dev, nr_io_queues + 1);
 	nvme_assign_io_queues(dev);
 
+	dev->nb.notifier_call = &nvme_cpu_notify;
+	result = register_hotcpu_notifier(&dev->nb);
+	if (result)
+		goto free_queues;
+
 	return 0;
 
  free_queues:
@@ -2357,6 +2375,7 @@ static void nvme_dev_shutdown(struct nvme_dev *dev)
 	int i;
 
 	dev->initialized = 0;
+	unregister_hotcpu_notifier(&dev->nb);
 
 	spin_lock(&dev_list_lock);
 	list_del_init(&dev->node);
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index f0f95c719685..15d071eba8b8 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -92,6 +92,7 @@ struct nvme_dev {
 	struct kref kref;
 	struct miscdevice miscdev;
 	struct work_struct reset_work;
+	struct notifier_block nb;
 	char name[12];
 	char serial[20];
 	char model[40];
-- 
cgit v1.2.3


From b355084a891985d4cd0ca23b1a83366af2c4232d Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Fri, 4 Apr 2014 11:43:36 -0600
Subject: NVMe: Make I/O timeout a module parameter

Increase the default timeout to 30 seconds to match SCSI.

Signed-off-by: Keith Busch <keith.busch@intel.com>
[use byte instead of ushort]
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
---
 drivers/block/nvme-core.c | 4 ++++
 include/linux/nvme.h      | 3 ++-
 2 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index ce5a4f1a3950..7c57b1d955a1 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -50,6 +50,10 @@
 #define CQ_SIZE(depth)		(depth * sizeof(struct nvme_completion))
 #define ADMIN_TIMEOUT	(60 * HZ)
 
+unsigned char io_timeout = 30;
+module_param(io_timeout, byte, 0644);
+MODULE_PARM_DESC(io_timeout, "timeout in seconds for I/O");
+
 static int nvme_major;
 module_param(nvme_major, int, 0);
 
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 15d071eba8b8..1da0807c65bc 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -66,7 +66,8 @@ enum {
 
 #define NVME_VS(major, minor)	(major << 16 | minor)
 
-#define NVME_IO_TIMEOUT	(5 * HZ)
+extern unsigned char io_timeout;
+#define NVME_IO_TIMEOUT	(io_timeout * HZ)
 
 /*
  * Represents an NVM Express device.  Each nvme_dev is a PCI function.
-- 
cgit v1.2.3


From edd10d33283899fb15d99a290dcc9ceb3604ca78 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Thu, 3 Apr 2014 16:45:23 -0600
Subject: NVMe: Retry failed commands with non-fatal errors

For commands returned with failed status, queue these for resubmission
and continue retrying them until success or for a limited amount of
time. The final timeout was arbitrarily chosen so requests can't be
retried indefinitely.

Since these are requeued on the nvmeq that submitted the command, the
callbacks have to take an nvmeq instead of an nvme_dev as a parameter
so that we can use the locked queue to append the iod to retry later.

The nvme_iod conviently can be used to track how long we've been trying
to successfully complete an iod request. The nvme_iod also provides the
nvme prp dma mappings, so I had to move a few things around so we can
keep those mappings.

Signed-off-by: Keith Busch <keith.busch@intel.com>
[fixed checkpatch issue with long line]
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
---
 drivers/block/nvme-core.c | 235 ++++++++++++++++++++++++++++------------------
 drivers/block/nvme-scsi.c |  10 +-
 include/linux/nvme.h      |   4 +-
 include/uapi/linux/nvme.h |   1 +
 4 files changed, 154 insertions(+), 96 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index 596e2abd7971..efa9c8f4a7a7 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -50,6 +50,7 @@
 #define SQ_SIZE(depth)		(depth * sizeof(struct nvme_command))
 #define CQ_SIZE(depth)		(depth * sizeof(struct nvme_completion))
 #define ADMIN_TIMEOUT	(60 * HZ)
+#define IOD_TIMEOUT	(4 * NVME_IO_TIMEOUT)
 
 unsigned char io_timeout = 30;
 module_param(io_timeout, byte, 0644);
@@ -94,6 +95,7 @@ struct nvme_queue {
 	wait_queue_head_t sq_full;
 	wait_queue_t sq_cong_wait;
 	struct bio_list sq_cong;
+	struct list_head iod_bio;
 	u32 __iomem *q_db;
 	u16 q_depth;
 	u16 cq_vector;
@@ -128,7 +130,7 @@ static inline void _nvme_check_size(void)
 	BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512);
 }
 
-typedef void (*nvme_completion_fn)(struct nvme_dev *, void *,
+typedef void (*nvme_completion_fn)(struct nvme_queue *, void *,
 						struct nvme_completion *);
 
 struct nvme_cmd_info {
@@ -200,7 +202,7 @@ static int alloc_cmdid_killable(struct nvme_queue *nvmeq, void *ctx,
 #define CMD_CTX_FLUSH		(0x318 + CMD_CTX_BASE)
 #define CMD_CTX_ABORT		(0x31C + CMD_CTX_BASE)
 
-static void special_completion(struct nvme_dev *dev, void *ctx,
+static void special_completion(struct nvme_queue *nvmeq, void *ctx,
 						struct nvme_completion *cqe)
 {
 	if (ctx == CMD_CTX_CANCELLED)
@@ -208,26 +210,26 @@ static void special_completion(struct nvme_dev *dev, void *ctx,
 	if (ctx == CMD_CTX_FLUSH)
 		return;
 	if (ctx == CMD_CTX_ABORT) {
-		++dev->abort_limit;
+		++nvmeq->dev->abort_limit;
 		return;
 	}
 	if (ctx == CMD_CTX_COMPLETED) {
-		dev_warn(&dev->pci_dev->dev,
+		dev_warn(nvmeq->q_dmadev,
 				"completed id %d twice on queue %d\n",
 				cqe->command_id, le16_to_cpup(&cqe->sq_id));
 		return;
 	}
 	if (ctx == CMD_CTX_INVALID) {
-		dev_warn(&dev->pci_dev->dev,
+		dev_warn(nvmeq->q_dmadev,
 				"invalid id %d completed on queue %d\n",
 				cqe->command_id, le16_to_cpup(&cqe->sq_id));
 		return;
 	}
 
-	dev_warn(&dev->pci_dev->dev, "Unknown special completion %p\n", ctx);
+	dev_warn(nvmeq->q_dmadev, "Unknown special completion %p\n", ctx);
 }
 
-static void async_completion(struct nvme_dev *dev, void *ctx,
+static void async_completion(struct nvme_queue *nvmeq, void *ctx,
 						struct nvme_completion *cqe)
 {
 	struct async_cmd_info *cmdinfo = ctx;
@@ -357,6 +359,7 @@ nvme_alloc_iod(unsigned nseg, unsigned nbytes, gfp_t gfp)
 		iod->npages = -1;
 		iod->length = nbytes;
 		iod->nents = 0;
+		iod->first_dma = 0ULL;
 		iod->start_time = jiffies;
 	}
 
@@ -405,19 +408,31 @@ static void nvme_end_io_acct(struct bio *bio, unsigned long start_time)
 	part_stat_unlock();
 }
 
-static void bio_completion(struct nvme_dev *dev, void *ctx,
+static void bio_completion(struct nvme_queue *nvmeq, void *ctx,
 						struct nvme_completion *cqe)
 {
 	struct nvme_iod *iod = ctx;
 	struct bio *bio = iod->private;
 	u16 status = le16_to_cpup(&cqe->status) >> 1;
 
+	if (unlikely(status)) {
+		if (!(status & NVME_SC_DNR ||
+				bio->bi_rw & REQ_FAILFAST_MASK) &&
+				(jiffies - iod->start_time) < IOD_TIMEOUT) {
+			if (!waitqueue_active(&nvmeq->sq_full))
+				add_wait_queue(&nvmeq->sq_full,
+							&nvmeq->sq_cong_wait);
+			list_add_tail(&iod->node, &nvmeq->iod_bio);
+			wake_up(&nvmeq->sq_full);
+			return;
+		}
+	}
 	if (iod->nents) {
-		dma_unmap_sg(&dev->pci_dev->dev, iod->sg, iod->nents,
+		dma_unmap_sg(nvmeq->q_dmadev, iod->sg, iod->nents,
 			bio_data_dir(bio) ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
 		nvme_end_io_acct(bio, iod->start_time);
 	}
-	nvme_free_iod(dev, iod);
+	nvme_free_iod(nvmeq->dev, iod);
 	if (status)
 		bio_endio(bio, -EIO);
 	else
@@ -425,8 +440,8 @@ static void bio_completion(struct nvme_dev *dev, void *ctx,
 }
 
 /* length is in bytes.  gfp flags indicates whether we may sleep. */
-int nvme_setup_prps(struct nvme_dev *dev, struct nvme_common_command *cmd,
-			struct nvme_iod *iod, int total_len, gfp_t gfp)
+int nvme_setup_prps(struct nvme_dev *dev, struct nvme_iod *iod, int total_len,
+								gfp_t gfp)
 {
 	struct dma_pool *pool;
 	int length = total_len;
@@ -439,7 +454,6 @@ int nvme_setup_prps(struct nvme_dev *dev, struct nvme_common_command *cmd,
 	dma_addr_t prp_dma;
 	int nprps, i;
 
-	cmd->prp1 = cpu_to_le64(dma_addr);
 	length -= (PAGE_SIZE - offset);
 	if (length <= 0)
 		return total_len;
@@ -454,7 +468,7 @@ int nvme_setup_prps(struct nvme_dev *dev, struct nvme_common_command *cmd,
 	}
 
 	if (length <= PAGE_SIZE) {
-		cmd->prp2 = cpu_to_le64(dma_addr);
+		iod->first_dma = dma_addr;
 		return total_len;
 	}
 
@@ -469,13 +483,12 @@ int nvme_setup_prps(struct nvme_dev *dev, struct nvme_common_command *cmd,
 
 	prp_list = dma_pool_alloc(pool, gfp, &prp_dma);
 	if (!prp_list) {
-		cmd->prp2 = cpu_to_le64(dma_addr);
+		iod->first_dma = dma_addr;
 		iod->npages = -1;
 		return (total_len - length) + PAGE_SIZE;
 	}
 	list[0] = prp_list;
 	iod->first_dma = prp_dma;
-	cmd->prp2 = cpu_to_le64(prp_dma);
 	i = 0;
 	for (;;) {
 		if (i == PAGE_SIZE / 8) {
@@ -514,10 +527,11 @@ static int nvme_split_and_submit(struct bio *bio, struct nvme_queue *nvmeq,
 
 	bio_chain(split, bio);
 
-	if (bio_list_empty(&nvmeq->sq_cong))
+	if (!waitqueue_active(&nvmeq->sq_full))
 		add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
 	bio_list_add(&nvmeq->sq_cong, split);
 	bio_list_add(&nvmeq->sq_cong, bio);
+	wake_up(&nvmeq->sq_full);
 
 	return 0;
 }
@@ -570,25 +584,13 @@ static int nvme_map_bio(struct nvme_queue *nvmeq, struct nvme_iod *iod,
 	return length;
 }
 
-/*
- * We reuse the small pool to allocate the 16-byte range here as it is not
- * worth having a special pool for these or additional cases to handle freeing
- * the iod.
- */
 static int nvme_submit_discard(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 		struct bio *bio, struct nvme_iod *iod, int cmdid)
 {
-	struct nvme_dsm_range *range;
+	struct nvme_dsm_range *range =
+				(struct nvme_dsm_range *)iod_list(iod)[0];
 	struct nvme_command *cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];
 
-	range = dma_pool_alloc(nvmeq->dev->prp_small_pool, GFP_ATOMIC,
-							&iod->first_dma);
-	if (!range)
-		return -ENOMEM;
-
-	iod_list(iod)[0] = (__le64 *)range;
-	iod->npages = 0;
-
 	range->cattr = cpu_to_le32(0);
 	range->nlb = cpu_to_le32(bio->bi_iter.bi_size >> ns->lba_shift);
 	range->slba = cpu_to_le64(nvme_block_nr(ns, bio->bi_iter.bi_sector));
@@ -635,44 +637,22 @@ int nvme_submit_flush_data(struct nvme_queue *nvmeq, struct nvme_ns *ns)
 	return nvme_submit_flush(nvmeq, ns, cmdid);
 }
 
-/*
- * Called with local interrupts disabled and the q_lock held.  May not sleep.
- */
-static int nvme_submit_bio_queue(struct nvme_queue *nvmeq, struct nvme_ns *ns,
-								struct bio *bio)
+static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod)
 {
+	struct bio *bio = iod->private;
+	struct nvme_ns *ns = bio->bi_bdev->bd_disk->private_data;
 	struct nvme_command *cmnd;
-	struct nvme_iod *iod;
-	enum dma_data_direction dma_dir;
-	int cmdid, length, result;
+	int cmdid;
 	u16 control;
 	u32 dsmgmt;
-	int psegs = bio_phys_segments(ns->queue, bio);
-
-	if ((bio->bi_rw & REQ_FLUSH) && psegs) {
-		result = nvme_submit_flush_data(nvmeq, ns);
-		if (result)
-			return result;
-	}
-
-	result = -ENOMEM;
-	iod = nvme_alloc_iod(psegs, bio->bi_iter.bi_size, GFP_ATOMIC);
-	if (!iod)
-		goto nomem;
-	iod->private = bio;
 
-	result = -EBUSY;
 	cmdid = alloc_cmdid(nvmeq, iod, bio_completion, NVME_IO_TIMEOUT);
 	if (unlikely(cmdid < 0))
-		goto free_iod;
+		return cmdid;
 
-	if (bio->bi_rw & REQ_DISCARD) {
-		result = nvme_submit_discard(nvmeq, ns, bio, iod, cmdid);
-		if (result)
-			goto free_cmdid;
-		return result;
-	}
-	if ((bio->bi_rw & REQ_FLUSH) && !psegs)
+	if (bio->bi_rw & REQ_DISCARD)
+		return nvme_submit_discard(nvmeq, ns, bio, iod, cmdid);
+	if ((bio->bi_rw & REQ_FLUSH) && !iod->nents)
 		return nvme_submit_flush(nvmeq, ns, cmdid);
 
 	control = 0;
@@ -686,42 +666,85 @@ static int nvme_submit_bio_queue(struct nvme_queue *nvmeq, struct nvme_ns *ns,
 		dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
 
 	cmnd = &nvmeq->sq_cmds[nvmeq->sq_tail];
-
 	memset(cmnd, 0, sizeof(*cmnd));
-	if (bio_data_dir(bio)) {
-		cmnd->rw.opcode = nvme_cmd_write;
-		dma_dir = DMA_TO_DEVICE;
-	} else {
-		cmnd->rw.opcode = nvme_cmd_read;
-		dma_dir = DMA_FROM_DEVICE;
-	}
-
-	result = nvme_map_bio(nvmeq, iod, bio, dma_dir, psegs);
-	if (result <= 0)
-		goto free_cmdid;
-	length = result;
 
+	cmnd->rw.opcode = bio_data_dir(bio) ? nvme_cmd_write : nvme_cmd_read;
 	cmnd->rw.command_id = cmdid;
 	cmnd->rw.nsid = cpu_to_le32(ns->ns_id);
-	length = nvme_setup_prps(nvmeq->dev, &cmnd->common, iod, length,
-								GFP_ATOMIC);
+	cmnd->rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
+	cmnd->rw.prp2 = cpu_to_le64(iod->first_dma);
 	cmnd->rw.slba = cpu_to_le64(nvme_block_nr(ns, bio->bi_iter.bi_sector));
-	cmnd->rw.length = cpu_to_le16((length >> ns->lba_shift) - 1);
+	cmnd->rw.length =
+		cpu_to_le16((bio->bi_iter.bi_size >> ns->lba_shift) - 1);
 	cmnd->rw.control = cpu_to_le16(control);
 	cmnd->rw.dsmgmt = cpu_to_le32(dsmgmt);
 
-	nvme_start_io_acct(bio);
 	if (++nvmeq->sq_tail == nvmeq->q_depth)
 		nvmeq->sq_tail = 0;
 	writel(nvmeq->sq_tail, nvmeq->q_db);
 
 	return 0;
+}
+
+/*
+ * Called with local interrupts disabled and the q_lock held.  May not sleep.
+ */
+static int nvme_submit_bio_queue(struct nvme_queue *nvmeq, struct nvme_ns *ns,
+								struct bio *bio)
+{
+	struct nvme_iod *iod;
+	int psegs = bio_phys_segments(ns->queue, bio);
+	int result;
+
+	if ((bio->bi_rw & REQ_FLUSH) && psegs) {
+		result = nvme_submit_flush_data(nvmeq, ns);
+		if (result)
+			return result;
+	}
+
+	iod = nvme_alloc_iod(psegs, bio->bi_iter.bi_size, GFP_ATOMIC);
+	if (!iod)
+		return -ENOMEM;
+
+	iod->private = bio;
+	if (bio->bi_rw & REQ_DISCARD) {
+		void *range;
+		/*
+		 * We reuse the small pool to allocate the 16-byte range here
+		 * as it is not worth having a special pool for these or
+		 * additional cases to handle freeing the iod.
+		 */
+		range = dma_pool_alloc(nvmeq->dev->prp_small_pool,
+						GFP_ATOMIC,
+						&iod->first_dma);
+		if (!range) {
+			result = -ENOMEM;
+			goto free_iod;
+		}
+		iod_list(iod)[0] = (__le64 *)range;
+		iod->npages = 0;
+	} else if (psegs) {
+		result = nvme_map_bio(nvmeq, iod, bio,
+			bio_data_dir(bio) ? DMA_TO_DEVICE : DMA_FROM_DEVICE,
+			psegs);
+		if (result <= 0)
+			goto free_iod;
+		if (nvme_setup_prps(nvmeq->dev, iod, result, GFP_ATOMIC) !=
+								result) {
+			result = -ENOMEM;
+			goto free_iod;
+		}
+		nvme_start_io_acct(bio);
+	}
+	if (unlikely(nvme_submit_iod(nvmeq, iod))) {
+		if (!waitqueue_active(&nvmeq->sq_full))
+			add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
+		list_add_tail(&iod->node, &nvmeq->iod_bio);
+	}
+	return 0;
 
- free_cmdid:
-	free_cmdid(nvmeq, cmdid, NULL);
  free_iod:
 	nvme_free_iod(nvmeq->dev, iod);
- nomem:
 	return result;
 }
 
@@ -745,7 +768,7 @@ static int nvme_process_cq(struct nvme_queue *nvmeq)
 		}
 
 		ctx = free_cmdid(nvmeq, cqe.command_id, &fn);
-		fn(nvmeq->dev, ctx, &cqe);
+		fn(nvmeq, ctx, &cqe);
 	}
 
 	/* If the controller ignores the cq head doorbell and continuously
@@ -781,7 +804,7 @@ static void nvme_make_request(struct request_queue *q, struct bio *bio)
 	if (!nvmeq->q_suspended && bio_list_empty(&nvmeq->sq_cong))
 		result = nvme_submit_bio_queue(nvmeq, ns, bio);
 	if (unlikely(result)) {
-		if (bio_list_empty(&nvmeq->sq_cong))
+		if (!waitqueue_active(&nvmeq->sq_full))
 			add_wait_queue(&nvmeq->sq_full, &nvmeq->sq_cong_wait);
 		bio_list_add(&nvmeq->sq_cong, bio);
 	}
@@ -825,7 +848,7 @@ struct sync_cmd_info {
 	int status;
 };
 
-static void sync_completion(struct nvme_dev *dev, void *ctx,
+static void sync_completion(struct nvme_queue *nvmeq, void *ctx,
 						struct nvme_completion *cqe)
 {
 	struct sync_cmd_info *cmdinfo = ctx;
@@ -1112,7 +1135,7 @@ static void nvme_cancel_ios(struct nvme_queue *nvmeq, bool timeout)
 		dev_warn(nvmeq->q_dmadev, "Cancelling I/O %d QID %d\n", cmdid,
 								nvmeq->qid);
 		ctx = cancel_cmdid(nvmeq, cmdid, &fn);
-		fn(nvmeq->dev, ctx, &cqe);
+		fn(nvmeq, ctx, &cqe);
 	}
 }
 
@@ -1125,6 +1148,17 @@ static void nvme_free_queue(struct rcu_head *r)
 		struct bio *bio = bio_list_pop(&nvmeq->sq_cong);
 		bio_endio(bio, -EIO);
 	}
+	while (!list_empty(&nvmeq->iod_bio)) {
+		static struct nvme_completion cqe = {
+			.status = cpu_to_le16(
+				(NVME_SC_ABORT_REQ | NVME_SC_DNR) << 1),
+		};
+		struct nvme_iod *iod = list_first_entry(&nvmeq->iod_bio,
+							struct nvme_iod,
+							node);
+		list_del(&iod->node);
+		bio_completion(nvmeq, iod, &cqe);
+	}
 	spin_unlock_irq(&nvmeq->q_lock);
 
 	dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
@@ -1232,6 +1266,7 @@ static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
 	init_waitqueue_head(&nvmeq->sq_full);
 	init_waitqueue_entry(&nvmeq->sq_cong_wait, nvme_thread);
 	bio_list_init(&nvmeq->sq_cong);
+	INIT_LIST_HEAD(&nvmeq->iod_bio);
 	nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
 	nvmeq->q_depth = depth;
 	nvmeq->cq_vector = vector;
@@ -1565,7 +1600,9 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 		c.rw.metadata = cpu_to_le64(meta_dma_addr);
 	}
 
-	length = nvme_setup_prps(dev, &c.common, iod, length, GFP_KERNEL);
+	length = nvme_setup_prps(dev, iod, length, GFP_KERNEL);
+	c.rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
+	c.rw.prp2 = cpu_to_le64(iod->first_dma);
 
 	if (length != (io.nblocks + 1) << ns->lba_shift)
 		status = -ENOMEM;
@@ -1635,8 +1672,9 @@ static int nvme_user_admin_cmd(struct nvme_dev *dev,
 								length);
 		if (IS_ERR(iod))
 			return PTR_ERR(iod);
-		length = nvme_setup_prps(dev, &c.common, iod, length,
-								GFP_KERNEL);
+		length = nvme_setup_prps(dev, iod, length, GFP_KERNEL);
+		c.common.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
+		c.common.prp2 = cpu_to_le64(iod->first_dma);
 	}
 
 	timeout = cmd.timeout_ms ? msecs_to_jiffies(cmd.timeout_ms) :
@@ -1733,17 +1771,33 @@ static const struct block_device_operations nvme_fops = {
 	.getgeo		= nvme_getgeo,
 };
 
+static void nvme_resubmit_iods(struct nvme_queue *nvmeq)
+{
+	struct nvme_iod *iod, *next;
+
+	list_for_each_entry_safe(iod, next, &nvmeq->iod_bio, node) {
+		if (unlikely(nvme_submit_iod(nvmeq, iod)))
+			break;
+		list_del(&iod->node);
+		if (bio_list_empty(&nvmeq->sq_cong) &&
+						list_empty(&nvmeq->iod_bio))
+			remove_wait_queue(&nvmeq->sq_full,
+						&nvmeq->sq_cong_wait);
+	}
+}
+
 static void nvme_resubmit_bios(struct nvme_queue *nvmeq)
 {
 	while (bio_list_peek(&nvmeq->sq_cong)) {
 		struct bio *bio = bio_list_pop(&nvmeq->sq_cong);
 		struct nvme_ns *ns = bio->bi_bdev->bd_disk->private_data;
 
-		if (bio_list_empty(&nvmeq->sq_cong))
+		if (bio_list_empty(&nvmeq->sq_cong) &&
+						list_empty(&nvmeq->iod_bio))
 			remove_wait_queue(&nvmeq->sq_full,
 							&nvmeq->sq_cong_wait);
 		if (nvme_submit_bio_queue(nvmeq, ns, bio)) {
-			if (bio_list_empty(&nvmeq->sq_cong))
+			if (!waitqueue_active(&nvmeq->sq_full))
 				add_wait_queue(&nvmeq->sq_full,
 							&nvmeq->sq_cong_wait);
 			bio_list_add_head(&nvmeq->sq_cong, bio);
@@ -1785,6 +1839,7 @@ static int nvme_kthread(void *data)
 				nvme_process_cq(nvmeq);
 				nvme_cancel_ios(nvmeq, true);
 				nvme_resubmit_bios(nvmeq);
+				nvme_resubmit_iods(nvmeq);
  unlock:
 				spin_unlock_irq(&nvmeq->q_lock);
 			}
diff --git a/drivers/block/nvme-scsi.c b/drivers/block/nvme-scsi.c
index 111c920c1574..2c3f5be06da1 100644
--- a/drivers/block/nvme-scsi.c
+++ b/drivers/block/nvme-scsi.c
@@ -1562,13 +1562,14 @@ static int nvme_trans_send_fw_cmd(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 			res = PTR_ERR(iod);
 			goto out;
 		}
-		length = nvme_setup_prps(dev, &c.common, iod, tot_len,
-								GFP_KERNEL);
+		length = nvme_setup_prps(dev, iod, tot_len, GFP_KERNEL);
 		if (length != tot_len) {
 			res = -ENOMEM;
 			goto out_unmap;
 		}
 
+		c.dlfw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
+		c.dlfw.prp2 = cpu_to_le64(iod->first_dma);
 		c.dlfw.numd = cpu_to_le32((tot_len/BYTES_TO_DWORDS) - 1);
 		c.dlfw.offset = cpu_to_le32(offset/BYTES_TO_DWORDS);
 	} else if (opcode == nvme_admin_activate_fw) {
@@ -2092,8 +2093,7 @@ static int nvme_trans_do_nvme_io(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 			res = PTR_ERR(iod);
 			goto out;
 		}
-		retcode = nvme_setup_prps(dev, &c.common, iod, unit_len,
-							GFP_KERNEL);
+		retcode = nvme_setup_prps(dev, iod, unit_len, GFP_KERNEL);
 		if (retcode != unit_len) {
 			nvme_unmap_user_pages(dev,
 				(is_write) ? DMA_TO_DEVICE : DMA_FROM_DEVICE,
@@ -2102,6 +2102,8 @@ static int nvme_trans_do_nvme_io(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 			res = -ENOMEM;
 			goto out;
 		}
+		c.rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
+		c.rw.prp2 = cpu_to_le64(iod->first_dma);
 
 		nvme_offset += unit_num_blocks;
 
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 1da0807c65bc..b95431d0338b 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -136,6 +136,7 @@ struct nvme_iod {
 	int length;		/* Of data, in bytes */
 	unsigned long start_time;
 	dma_addr_t first_dma;
+	struct list_head node;
 	struct scatterlist sg[0];
 };
 
@@ -151,8 +152,7 @@ static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector)
  */
 void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod);
 
-int nvme_setup_prps(struct nvme_dev *dev, struct nvme_common_command *cmd,
-			struct nvme_iod *iod, int total_len, gfp_t gfp);
+int nvme_setup_prps(struct nvme_dev *, struct nvme_iod *, int , gfp_t);
 struct nvme_iod *nvme_map_user_pages(struct nvme_dev *dev, int write,
 				unsigned long addr, unsigned length);
 void nvme_unmap_user_pages(struct nvme_dev *dev, int write,
diff --git a/include/uapi/linux/nvme.h b/include/uapi/linux/nvme.h
index e5ab62201119..096fe1c6f83d 100644
--- a/include/uapi/linux/nvme.h
+++ b/include/uapi/linux/nvme.h
@@ -434,6 +434,7 @@ enum {
 	NVME_SC_REFTAG_CHECK		= 0x284,
 	NVME_SC_COMPARE_FAILED		= 0x285,
 	NVME_SC_ACCESS_DENIED		= 0x286,
+	NVME_SC_DNR			= 0x4000,
 };
 
 struct nvme_completion {
-- 
cgit v1.2.3


From 312103d64d0fcadb332899a2c84b357ddb18f4e3 Mon Sep 17 00:00:00 2001
From: Chris Metcalf <cmetcalf@tilera.com>
Date: Tue, 25 Mar 2014 09:25:41 -0400
Subject: AUDIT: make audit_is_compat depend on CONFIG_AUDIT_COMPAT_GENERIC

On systems with CONFIG_COMPAT we introduced the new requirement that
audit_classify_compat_syscall() exists.  This wasn't true for everything
(apparently not for "tilegx", which I know less that nothing about.)

Instead of wrapping the preprocessor optomization with CONFIG_COMPAT we
should have used the new CONFIG_AUDIT_COMPAT_GENERIC.  This patch uses
that config option to make sure only arches which intend to implement
this have the requirement.

This works fine for tilegx according to Chris Metcalf
Signed-off-by: Eric Paris <eparis@redhat.com>
---
 include/linux/audit.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 611a59a56f1a..22cfddb75566 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -102,7 +102,7 @@ struct filename;
 
 extern void audit_log_session_info(struct audit_buffer *ab);
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_AUDIT_COMPAT_GENERIC
 #define audit_is_compat(arch)  (!((arch) & __AUDIT_ARCH_64BIT))
 #else
 #define audit_is_compat(arch)  false
-- 
cgit v1.2.3


From 34bf6ef94a835a8f1d8abd3e7d38c6c08d205867 Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Tue, 8 Apr 2014 13:44:27 -0700
Subject: mm: slab/slub: use page->list consistently instead of page->lru

'struct page' has two list_head fields: 'lru' and 'list'.  Conveniently,
they are unioned together.  This means that code can use them
interchangably, which gets horribly confusing like with this nugget from
slab.c:

>	list_del(&page->lru);
>	if (page->active == cachep->num)
>		list_add(&page->list, &n->slabs_full);

This patch makes the slab and slub code use page->lru universally instead
of mixing ->list and ->lru.

So, the new rule is: page->lru is what the you use if you want to keep
your page on a list.  Don't like the fact that it's not called ->list?
Too bad.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Christoph Lameter <cl@linux.com>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Pekka Enberg <penberg@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
---
 include/linux/mm_types.h |  3 ++-
 mm/slab.c                |  4 ++--
 mm/slob.c                | 10 +++++-----
 3 files changed, 9 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 290901a8c1de..84b74080beb7 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -124,6 +124,8 @@ struct page {
 	union {
 		struct list_head lru;	/* Pageout list, eg. active_list
 					 * protected by zone->lru_lock !
+					 * Can be used as a generic list
+					 * by the page owner.
 					 */
 		struct {		/* slub per cpu partial pages */
 			struct page *next;	/* Next partial slab */
@@ -136,7 +138,6 @@ struct page {
 #endif
 		};
 
-		struct list_head list;	/* slobs list of pages */
 		struct slab *slab_page; /* slab fields */
 		struct rcu_head rcu_head;	/* Used by SLAB
 						 * when destroying via RCU
diff --git a/mm/slab.c b/mm/slab.c
index 8dd8e0875e4c..f6718197cdd0 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2922,9 +2922,9 @@ retry:
 		/* move slabp to correct slabp list: */
 		list_del(&page->lru);
 		if (page->active == cachep->num)
-			list_add(&page->list, &n->slabs_full);
+			list_add(&page->lru, &n->slabs_full);
 		else
-			list_add(&page->list, &n->slabs_partial);
+			list_add(&page->lru, &n->slabs_partial);
 	}
 
 must_grow:
diff --git a/mm/slob.c b/mm/slob.c
index 4bf8809dfcce..730cad45d4be 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -111,13 +111,13 @@ static inline int slob_page_free(struct page *sp)
 
 static void set_slob_page_free(struct page *sp, struct list_head *list)
 {
-	list_add(&sp->list, list);
+	list_add(&sp->lru, list);
 	__SetPageSlobFree(sp);
 }
 
 static inline void clear_slob_page_free(struct page *sp)
 {
-	list_del(&sp->list);
+	list_del(&sp->lru);
 	__ClearPageSlobFree(sp);
 }
 
@@ -282,7 +282,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
 
 	spin_lock_irqsave(&slob_lock, flags);
 	/* Iterate through each partially free page, try to find room */
-	list_for_each_entry(sp, slob_list, list) {
+	list_for_each_entry(sp, slob_list, lru) {
 #ifdef CONFIG_NUMA
 		/*
 		 * If there's a node specification, search for a partial
@@ -296,7 +296,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
 			continue;
 
 		/* Attempt to alloc */
-		prev = sp->list.prev;
+		prev = sp->lru.prev;
 		b = slob_page_alloc(sp, size, align);
 		if (!b)
 			continue;
@@ -322,7 +322,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
 		spin_lock_irqsave(&slob_lock, flags);
 		sp->units = SLOB_UNITS(PAGE_SIZE);
 		sp->freelist = b;
-		INIT_LIST_HEAD(&sp->list);
+		INIT_LIST_HEAD(&sp->lru);
 		set_slob(b, SLOB_UNITS(PAGE_SIZE), b + SLOB_UNITS(PAGE_SIZE));
 		set_slob_page_free(sp, slob_list);
 		b = slob_page_alloc(sp, size, align);
-- 
cgit v1.2.3


From 676d23690fb62b5d51ba5d659935e9f7d9da9f8e Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 11 Apr 2014 16:15:36 -0400
Subject: net: Fix use after free by removing length arg from sk_data_ready
 callbacks.

Several spots in the kernel perform a sequence like:

	skb_queue_tail(&sk->s_receive_queue, skb);
	sk->sk_data_ready(sk, skb->len);

But at the moment we place the SKB onto the socket receive queue it
can be consumed and freed up.  So this skb->len access is potentially
to freed up memory.

Furthermore, the skb->len can be modified by the consumer so it is
possible that the value isn't accurate.

And finally, no actual implementation of this callback actually uses
the length argument.  And since nobody actually cared about it's
value, lots of call sites pass arbitrary values in such as '0' and
even '1'.

So just remove the length argument from the callback, that way there
is no confusion whatsoever and all of these use-after-free cases get
fixed as a side effect.

Based upon a patch by Eric Dumazet and his suggestion to audit this
issue tree-wide.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/scsi/iscsi_tcp.c                                  |  2 +-
 drivers/scsi/iscsi_tcp.h                                  |  2 +-
 .../staging/lustre/lnet/klnds/socklnd/socklnd_lib-linux.c |  4 ++--
 drivers/target/iscsi/iscsi_target_core.h                  |  2 +-
 drivers/target/iscsi/iscsi_target_nego.c                  |  2 +-
 fs/dlm/lowcomms.c                                         |  2 +-
 fs/ncpfs/ncp_fs_sb.h                                      |  4 ++--
 fs/ncpfs/sock.c                                           |  4 ++--
 fs/ocfs2/cluster/tcp.c                                    | 15 +++++++--------
 fs/ocfs2/cluster/tcp_internal.h                           |  2 +-
 include/linux/sunrpc/svcsock.h                            |  2 +-
 include/net/sctp/sctp.h                                   |  2 +-
 include/net/sock.h                                        |  2 +-
 net/atm/clip.c                                            |  2 +-
 net/atm/lec.c                                             | 10 +++++-----
 net/atm/mpc.c                                             |  6 +++---
 net/atm/raw.c                                             |  2 +-
 net/atm/signaling.c                                       |  2 +-
 net/ax25/ax25_in.c                                        |  2 +-
 net/bluetooth/l2cap_sock.c                                |  6 +++---
 net/bluetooth/rfcomm/core.c                               |  4 ++--
 net/bluetooth/rfcomm/sock.c                               |  4 ++--
 net/bluetooth/sco.c                                       |  2 +-
 net/caif/caif_socket.c                                    |  4 +---
 net/ceph/messenger.c                                      |  2 +-
 net/core/skbuff.c                                         |  4 +---
 net/core/sock.c                                           |  4 ++--
 net/dccp/input.c                                          |  2 +-
 net/dccp/minisocks.c                                      |  2 +-
 net/decnet/dn_nsp_in.c                                    |  4 +---
 net/ipv4/tcp_input.c                                      | 10 +++++-----
 net/ipv4/tcp_ipv4.c                                       |  2 +-
 net/ipv4/tcp_minisocks.c                                  |  2 +-
 net/iucv/af_iucv.c                                        |  4 ++--
 net/key/af_key.c                                          |  2 +-
 net/netlink/af_netlink.c                                  |  4 ++--
 net/netrom/af_netrom.c                                    |  2 +-
 net/nfc/llcp_core.c                                       |  2 +-
 net/packet/af_packet.c                                    |  6 +++---
 net/phonet/pep-gprs.c                                     |  4 ++--
 net/phonet/pep.c                                          |  8 +++-----
 net/rds/tcp.h                                             |  4 ++--
 net/rds/tcp_listen.c                                      |  6 +++---
 net/rds/tcp_recv.c                                        |  8 ++++----
 net/rose/af_rose.c                                        |  2 +-
 net/rxrpc/ar-input.c                                      |  6 +++---
 net/rxrpc/ar-internal.h                                   |  2 +-
 net/sctp/socket.c                                         |  2 +-
 net/sctp/ulpqueue.c                                       |  4 ++--
 net/sunrpc/svcsock.c                                      | 12 ++++++------
 net/sunrpc/xprtsock.c                                     |  8 ++++----
 net/tipc/server.c                                         |  4 ++--
 net/tipc/socket.c                                         |  6 +++---
 net/unix/af_unix.c                                        |  6 +++---
 net/vmw_vsock/vmci_transport_notify.c                     |  2 +-
 net/vmw_vsock/vmci_transport_notify_qstate.c              |  4 ++--
 net/x25/af_x25.c                                          |  2 +-
 net/x25/x25_in.c                                          |  2 +-
 58 files changed, 112 insertions(+), 121 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index bfb6d07d87f0..11854845393b 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -125,7 +125,7 @@ static inline int iscsi_sw_sk_state_check(struct sock *sk)
 	return 0;
 }
 
-static void iscsi_sw_tcp_data_ready(struct sock *sk, int flag)
+static void iscsi_sw_tcp_data_ready(struct sock *sk)
 {
 	struct iscsi_conn *conn;
 	struct iscsi_tcp_conn *tcp_conn;
diff --git a/drivers/scsi/iscsi_tcp.h b/drivers/scsi/iscsi_tcp.h
index 666fe09378fa..f42ecb238af5 100644
--- a/drivers/scsi/iscsi_tcp.h
+++ b/drivers/scsi/iscsi_tcp.h
@@ -40,7 +40,7 @@ struct iscsi_sw_tcp_conn {
 
 	struct iscsi_sw_tcp_send out;
 	/* old values for socket callbacks */
-	void			(*old_data_ready)(struct sock *, int);
+	void			(*old_data_ready)(struct sock *);
 	void			(*old_state_change)(struct sock *);
 	void			(*old_write_space)(struct sock *);
 
diff --git a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_lib-linux.c b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_lib-linux.c
index a54b506ba7ca..a9b5898347c2 100644
--- a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_lib-linux.c
+++ b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd_lib-linux.c
@@ -655,7 +655,7 @@ extern void ksocknal_write_callback (ksock_conn_t *conn);
  * socket call back in Linux
  */
 static void
-ksocknal_data_ready (struct sock *sk, int n)
+ksocknal_data_ready (struct sock *sk)
 {
 	ksock_conn_t  *conn;
 
@@ -666,7 +666,7 @@ ksocknal_data_ready (struct sock *sk, int n)
 	conn = sk->sk_user_data;
 	if (conn == NULL) {	     /* raced with ksocknal_terminate_conn */
 		LASSERT (sk->sk_data_ready != &ksocknal_data_ready);
-		sk->sk_data_ready (sk, n);
+		sk->sk_data_ready (sk);
 	} else
 		ksocknal_read_callback(conn);
 
diff --git a/drivers/target/iscsi/iscsi_target_core.h b/drivers/target/iscsi/iscsi_target_core.h
index 48f7b3bf4e8c..f452398fe0f0 100644
--- a/drivers/target/iscsi/iscsi_target_core.h
+++ b/drivers/target/iscsi/iscsi_target_core.h
@@ -556,7 +556,7 @@ struct iscsi_conn {
 	struct completion	rx_half_close_comp;
 	/* socket used by this connection */
 	struct socket		*sock;
-	void			(*orig_data_ready)(struct sock *, int);
+	void			(*orig_data_ready)(struct sock *);
 	void			(*orig_state_change)(struct sock *);
 #define LOGIN_FLAGS_READ_ACTIVE		1
 #define LOGIN_FLAGS_CLOSED		2
diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index 582ba84075ec..75b685960e80 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -375,7 +375,7 @@ static int iscsi_target_do_tx_login_io(struct iscsi_conn *conn, struct iscsi_log
 	return 0;
 }
 
-static void iscsi_target_sk_data_ready(struct sock *sk, int count)
+static void iscsi_target_sk_data_ready(struct sock *sk)
 {
 	struct iscsi_conn *conn = sk->sk_user_data;
 	bool rc;
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 3190ca973dd6..1e5b45359509 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -424,7 +424,7 @@ int dlm_lowcomms_addr(int nodeid, struct sockaddr_storage *addr, int len)
 }
 
 /* Data available on socket or listen socket received a connect */
-static void lowcomms_data_ready(struct sock *sk, int count_unused)
+static void lowcomms_data_ready(struct sock *sk)
 {
 	struct connection *con = sock2con(sk);
 	if (con && !test_and_set_bit(CF_READ_PENDING, &con->flags))
diff --git a/fs/ncpfs/ncp_fs_sb.h b/fs/ncpfs/ncp_fs_sb.h
index b81e97adc5a9..fbb08818775e 100644
--- a/fs/ncpfs/ncp_fs_sb.h
+++ b/fs/ncpfs/ncp_fs_sb.h
@@ -111,7 +111,7 @@ struct ncp_server {
 
 	spinlock_t requests_lock;	/* Lock accesses to tx.requests, tx.creq and rcv.creq when STREAM mode */
 
-	void (*data_ready)(struct sock* sk, int len);
+	void (*data_ready)(struct sock* sk);
 	void (*error_report)(struct sock* sk);
 	void (*write_space)(struct sock* sk);	/* STREAM mode only */
 	struct {
@@ -153,7 +153,7 @@ extern void ncp_tcp_tx_proc(struct work_struct *work);
 extern void ncpdgram_rcv_proc(struct work_struct *work);
 extern void ncpdgram_timeout_proc(struct work_struct *work);
 extern void ncpdgram_timeout_call(unsigned long server);
-extern void ncp_tcp_data_ready(struct sock* sk, int len);
+extern void ncp_tcp_data_ready(struct sock* sk);
 extern void ncp_tcp_write_space(struct sock* sk);
 extern void ncp_tcp_error_report(struct sock* sk);
 
diff --git a/fs/ncpfs/sock.c b/fs/ncpfs/sock.c
index 3a1587222c8a..652da0db932c 100644
--- a/fs/ncpfs/sock.c
+++ b/fs/ncpfs/sock.c
@@ -96,11 +96,11 @@ static void ncp_req_put(struct ncp_request_reply *req)
 		kfree(req);
 }
 
-void ncp_tcp_data_ready(struct sock *sk, int len)
+void ncp_tcp_data_ready(struct sock *sk)
 {
 	struct ncp_server *server = sk->sk_user_data;
 
-	server->data_ready(sk, len);
+	server->data_ready(sk);
 	schedule_work(&server->rcv.tq);
 }
 
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index eb649d23a4de..d857534b886e 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -137,7 +137,7 @@ static int o2net_sys_err_translations[O2NET_ERR_MAX] =
 static void o2net_sc_connect_completed(struct work_struct *work);
 static void o2net_rx_until_empty(struct work_struct *work);
 static void o2net_shutdown_sc(struct work_struct *work);
-static void o2net_listen_data_ready(struct sock *sk, int bytes);
+static void o2net_listen_data_ready(struct sock *sk);
 static void o2net_sc_send_keep_req(struct work_struct *work);
 static void o2net_idle_timer(unsigned long data);
 static void o2net_sc_postpone_idle(struct o2net_sock_container *sc);
@@ -597,9 +597,9 @@ static void o2net_set_nn_state(struct o2net_node *nn,
 }
 
 /* see o2net_register_callbacks() */
-static void o2net_data_ready(struct sock *sk, int bytes)
+static void o2net_data_ready(struct sock *sk)
 {
-	void (*ready)(struct sock *sk, int bytes);
+	void (*ready)(struct sock *sk);
 
 	read_lock(&sk->sk_callback_lock);
 	if (sk->sk_user_data) {
@@ -613,7 +613,7 @@ static void o2net_data_ready(struct sock *sk, int bytes)
 	}
 	read_unlock(&sk->sk_callback_lock);
 
-	ready(sk, bytes);
+	ready(sk);
 }
 
 /* see o2net_register_callbacks() */
@@ -1953,9 +1953,9 @@ static void o2net_accept_many(struct work_struct *work)
 		cond_resched();
 }
 
-static void o2net_listen_data_ready(struct sock *sk, int bytes)
+static void o2net_listen_data_ready(struct sock *sk)
 {
-	void (*ready)(struct sock *sk, int bytes);
+	void (*ready)(struct sock *sk);
 
 	read_lock(&sk->sk_callback_lock);
 	ready = sk->sk_user_data;
@@ -1978,7 +1978,6 @@ static void o2net_listen_data_ready(struct sock *sk, int bytes)
 	 */
 
 	if (sk->sk_state == TCP_LISTEN) {
-		mlog(ML_TCP, "bytes: %d\n", bytes);
 		queue_work(o2net_wq, &o2net_listen_work);
 	} else {
 		ready = NULL;
@@ -1987,7 +1986,7 @@ static void o2net_listen_data_ready(struct sock *sk, int bytes)
 out:
 	read_unlock(&sk->sk_callback_lock);
 	if (ready != NULL)
-		ready(sk, bytes);
+		ready(sk);
 }
 
 static int o2net_open_listening_sock(__be32 addr, __be16 port)
diff --git a/fs/ocfs2/cluster/tcp_internal.h b/fs/ocfs2/cluster/tcp_internal.h
index 4cbcb65784a3..dc024367110a 100644
--- a/fs/ocfs2/cluster/tcp_internal.h
+++ b/fs/ocfs2/cluster/tcp_internal.h
@@ -165,7 +165,7 @@ struct o2net_sock_container {
 
 	/* original handlers for the sockets */
 	void			(*sc_state_change)(struct sock *sk);
-	void			(*sc_data_ready)(struct sock *sk, int bytes);
+	void			(*sc_data_ready)(struct sock *sk);
 
 	u32			sc_msg_key;
 	u16			sc_msg_type;
diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h
index 62fd1b756e99..88f7e1a477fe 100644
--- a/include/linux/sunrpc/svcsock.h
+++ b/include/linux/sunrpc/svcsock.h
@@ -22,7 +22,7 @@ struct svc_sock {
 
 	/* We keep the old state_change and data_ready CB's here */
 	void			(*sk_ostate)(struct sock *);
-	void			(*sk_odata)(struct sock *, int bytes);
+	void			(*sk_odata)(struct sock *);
 	void			(*sk_owspace)(struct sock *);
 
 	/* private TCP part */
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index a3353f45ef94..8e4de46c052e 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -101,7 +101,7 @@ void sctp_addr_wq_mgmt(struct net *, struct sctp_sockaddr_entry *, int);
 int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb);
 int sctp_inet_listen(struct socket *sock, int backlog);
 void sctp_write_space(struct sock *sk);
-void sctp_data_ready(struct sock *sk, int len);
+void sctp_data_ready(struct sock *sk);
 unsigned int sctp_poll(struct file *file, struct socket *sock,
 		poll_table *wait);
 void sctp_sock_rfree(struct sk_buff *skb);
diff --git a/include/net/sock.h b/include/net/sock.h
index 06a5668f05c9..8338a14e4805 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -418,7 +418,7 @@ struct sock {
 	u32			sk_classid;
 	struct cg_proto		*sk_cgrp;
 	void			(*sk_state_change)(struct sock *sk);
-	void			(*sk_data_ready)(struct sock *sk, int bytes);
+	void			(*sk_data_ready)(struct sock *sk);
 	void			(*sk_write_space)(struct sock *sk);
 	void			(*sk_error_report)(struct sock *sk);
 	int			(*sk_backlog_rcv)(struct sock *sk,
diff --git a/net/atm/clip.c b/net/atm/clip.c
index 8215f7cb170b..ba291ce4bdff 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -68,7 +68,7 @@ static int to_atmarpd(enum atmarp_ctrl_type type, int itf, __be32 ip)
 
 	sk = sk_atm(atmarpd);
 	skb_queue_tail(&sk->sk_receive_queue, skb);
-	sk->sk_data_ready(sk, skb->len);
+	sk->sk_data_ready(sk);
 	return 0;
 }
 
diff --git a/net/atm/lec.c b/net/atm/lec.c
index 5a2f602d07e1..4c5b8ba0f84f 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -152,7 +152,7 @@ static void lec_handle_bridge(struct sk_buff *skb, struct net_device *dev)
 		atm_force_charge(priv->lecd, skb2->truesize);
 		sk = sk_atm(priv->lecd);
 		skb_queue_tail(&sk->sk_receive_queue, skb2);
-		sk->sk_data_ready(sk, skb2->len);
+		sk->sk_data_ready(sk);
 	}
 }
 #endif /* defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) */
@@ -447,7 +447,7 @@ static int lec_atm_send(struct atm_vcc *vcc, struct sk_buff *skb)
 			atm_force_charge(priv->lecd, skb2->truesize);
 			sk = sk_atm(priv->lecd);
 			skb_queue_tail(&sk->sk_receive_queue, skb2);
-			sk->sk_data_ready(sk, skb2->len);
+			sk->sk_data_ready(sk);
 		}
 	}
 #endif /* defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE) */
@@ -530,13 +530,13 @@ send_to_lecd(struct lec_priv *priv, atmlec_msg_type type,
 	atm_force_charge(priv->lecd, skb->truesize);
 	sk = sk_atm(priv->lecd);
 	skb_queue_tail(&sk->sk_receive_queue, skb);
-	sk->sk_data_ready(sk, skb->len);
+	sk->sk_data_ready(sk);
 
 	if (data != NULL) {
 		pr_debug("about to send %d bytes of data\n", data->len);
 		atm_force_charge(priv->lecd, data->truesize);
 		skb_queue_tail(&sk->sk_receive_queue, data);
-		sk->sk_data_ready(sk, skb->len);
+		sk->sk_data_ready(sk);
 	}
 
 	return 0;
@@ -616,7 +616,7 @@ static void lec_push(struct atm_vcc *vcc, struct sk_buff *skb)
 
 		pr_debug("%s: To daemon\n", dev->name);
 		skb_queue_tail(&sk->sk_receive_queue, skb);
-		sk->sk_data_ready(sk, skb->len);
+		sk->sk_data_ready(sk);
 	} else {		/* Data frame, queue to protocol handlers */
 		struct lec_arp_table *entry;
 		unsigned char *src, *dst;
diff --git a/net/atm/mpc.c b/net/atm/mpc.c
index 91dc58f1124d..e8e0e7a8a23d 100644
--- a/net/atm/mpc.c
+++ b/net/atm/mpc.c
@@ -706,7 +706,7 @@ static void mpc_push(struct atm_vcc *vcc, struct sk_buff *skb)
 		dprintk("(%s) control packet arrived\n", dev->name);
 		/* Pass control packets to daemon */
 		skb_queue_tail(&sk->sk_receive_queue, skb);
-		sk->sk_data_ready(sk, skb->len);
+		sk->sk_data_ready(sk);
 		return;
 	}
 
@@ -992,7 +992,7 @@ int msg_to_mpoad(struct k_message *mesg, struct mpoa_client *mpc)
 
 	sk = sk_atm(mpc->mpoad_vcc);
 	skb_queue_tail(&sk->sk_receive_queue, skb);
-	sk->sk_data_ready(sk, skb->len);
+	sk->sk_data_ready(sk);
 
 	return 0;
 }
@@ -1273,7 +1273,7 @@ static void purge_egress_shortcut(struct atm_vcc *vcc, eg_cache_entry *entry)
 
 	sk = sk_atm(vcc);
 	skb_queue_tail(&sk->sk_receive_queue, skb);
-	sk->sk_data_ready(sk, skb->len);
+	sk->sk_data_ready(sk);
 	dprintk("exiting\n");
 }
 
diff --git a/net/atm/raw.c b/net/atm/raw.c
index b4f7b9ff3c74..2e17e97a7a8b 100644
--- a/net/atm/raw.c
+++ b/net/atm/raw.c
@@ -25,7 +25,7 @@ static void atm_push_raw(struct atm_vcc *vcc, struct sk_buff *skb)
 		struct sock *sk = sk_atm(vcc);
 
 		skb_queue_tail(&sk->sk_receive_queue, skb);
-		sk->sk_data_ready(sk, skb->len);
+		sk->sk_data_ready(sk);
 	}
 }
 
diff --git a/net/atm/signaling.c b/net/atm/signaling.c
index 4176887e72eb..523bce72f698 100644
--- a/net/atm/signaling.c
+++ b/net/atm/signaling.c
@@ -51,7 +51,7 @@ static void sigd_put_skb(struct sk_buff *skb)
 #endif
 	atm_force_charge(sigd, skb->truesize);
 	skb_queue_tail(&sk_atm(sigd)->sk_receive_queue, skb);
-	sk_atm(sigd)->sk_data_ready(sk_atm(sigd), skb->len);
+	sk_atm(sigd)->sk_data_ready(sk_atm(sigd));
 }
 
 static void modify_qos(struct atm_vcc *vcc, struct atmsvc_msg *msg)
diff --git a/net/ax25/ax25_in.c b/net/ax25/ax25_in.c
index 96f4cab3a2f9..7ed8ab724819 100644
--- a/net/ax25/ax25_in.c
+++ b/net/ax25/ax25_in.c
@@ -422,7 +422,7 @@ static int ax25_rcv(struct sk_buff *skb, struct net_device *dev,
 
 	if (sk) {
 		if (!sock_flag(sk, SOCK_DEAD))
-			sk->sk_data_ready(sk, skb->len);
+			sk->sk_data_ready(sk);
 		sock_put(sk);
 	} else {
 free:
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index f59e00c2daa9..ef5e5b04f34f 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1271,7 +1271,7 @@ static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err)
 
 		if (parent) {
 			bt_accept_unlink(sk);
-			parent->sk_data_ready(parent, 0);
+			parent->sk_data_ready(parent);
 		} else {
 			sk->sk_state_change(sk);
 		}
@@ -1327,7 +1327,7 @@ static void l2cap_sock_ready_cb(struct l2cap_chan *chan)
 	sk->sk_state_change(sk);
 
 	if (parent)
-		parent->sk_data_ready(parent, 0);
+		parent->sk_data_ready(parent);
 
 	release_sock(sk);
 }
@@ -1340,7 +1340,7 @@ static void l2cap_sock_defer_cb(struct l2cap_chan *chan)
 
 	parent = bt_sk(sk)->parent;
 	if (parent)
-		parent->sk_data_ready(parent, 0);
+		parent->sk_data_ready(parent);
 
 	release_sock(sk);
 }
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index 633cceeb943e..cf620260affa 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -186,9 +186,9 @@ static void rfcomm_l2state_change(struct sock *sk)
 	rfcomm_schedule();
 }
 
-static void rfcomm_l2data_ready(struct sock *sk, int bytes)
+static void rfcomm_l2data_ready(struct sock *sk)
 {
-	BT_DBG("%p bytes %d", sk, bytes);
+	BT_DBG("%p", sk);
 	rfcomm_schedule();
 }
 
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index eabd25ab5ad9..c603a5eb4720 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -54,7 +54,7 @@ static void rfcomm_sk_data_ready(struct rfcomm_dlc *d, struct sk_buff *skb)
 
 	atomic_add(skb->len, &sk->sk_rmem_alloc);
 	skb_queue_tail(&sk->sk_receive_queue, skb);
-	sk->sk_data_ready(sk, skb->len);
+	sk->sk_data_ready(sk);
 
 	if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
 		rfcomm_dlc_throttle(d);
@@ -84,7 +84,7 @@ static void rfcomm_sk_state_change(struct rfcomm_dlc *d, int err)
 			sock_set_flag(sk, SOCK_ZAPPED);
 			bt_accept_unlink(sk);
 		}
-		parent->sk_data_ready(parent, 0);
+		parent->sk_data_ready(parent);
 	} else {
 		if (d->state == BT_CONNECTED)
 			rfcomm_session_getaddr(d->session,
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index ab1e6fcca4c5..c06dbd3938e8 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -1024,7 +1024,7 @@ static void sco_conn_ready(struct sco_conn *conn)
 			sk->sk_state = BT_CONNECTED;
 
 		/* Wake up parent */
-		parent->sk_data_ready(parent, 1);
+		parent->sk_data_ready(parent);
 
 		bh_unlock_sock(parent);
 
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index d6be3edb7a43..e8437094d15f 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -124,7 +124,6 @@ static void caif_flow_ctrl(struct sock *sk, int mode)
 static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	int err;
-	int skb_len;
 	unsigned long flags;
 	struct sk_buff_head *list = &sk->sk_receive_queue;
 	struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
@@ -153,14 +152,13 @@ static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	 * may be freed by other threads of control pulling packets
 	 * from the queue.
 	 */
-	skb_len = skb->len;
 	spin_lock_irqsave(&list->lock, flags);
 	if (!sock_flag(sk, SOCK_DEAD))
 		__skb_queue_tail(list, skb);
 	spin_unlock_irqrestore(&list->lock, flags);
 
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, skb_len);
+		sk->sk_data_ready(sk);
 	else
 		kfree_skb(skb);
 	return 0;
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 4f55f9ce63fa..dac7f9b98687 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -383,7 +383,7 @@ static void con_sock_state_closed(struct ceph_connection *con)
  */
 
 /* data available on socket, or listen socket received a connect */
-static void ceph_sock_data_ready(struct sock *sk, int count_unused)
+static void ceph_sock_data_ready(struct sock *sk)
 {
 	struct ceph_connection *con = sk->sk_user_data;
 	if (atomic_read(&con->msgr->stopping)) {
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 57e225c8914e..1b62343f5837 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3458,8 +3458,6 @@ static void sock_rmem_free(struct sk_buff *skb)
  */
 int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
 {
-	int len = skb->len;
-
 	if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
 	    (unsigned int)sk->sk_rcvbuf)
 		return -ENOMEM;
@@ -3474,7 +3472,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
 
 	skb_queue_tail(&sk->sk_error_queue, skb);
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, len);
+		sk->sk_data_ready(sk);
 	return 0;
 }
 EXPORT_SYMBOL(sock_queue_err_skb);
diff --git a/net/core/sock.c b/net/core/sock.c
index c0fc6bdad1e3..b4fff008136f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -428,7 +428,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	spin_unlock_irqrestore(&list->lock, flags);
 
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, skb_len);
+		sk->sk_data_ready(sk);
 	return 0;
 }
 EXPORT_SYMBOL(sock_queue_rcv_skb);
@@ -2196,7 +2196,7 @@ static void sock_def_error_report(struct sock *sk)
 	rcu_read_unlock();
 }
 
-static void sock_def_readable(struct sock *sk, int len)
+static void sock_def_readable(struct sock *sk)
 {
 	struct socket_wq *wq;
 
diff --git a/net/dccp/input.c b/net/dccp/input.c
index 14cdafad7a90..3c8ec7d4a34e 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -28,7 +28,7 @@ static void dccp_enqueue_skb(struct sock *sk, struct sk_buff *skb)
 	__skb_pull(skb, dccp_hdr(skb)->dccph_doff * 4);
 	__skb_queue_tail(&sk->sk_receive_queue, skb);
 	skb_set_owner_r(skb, sk);
-	sk->sk_data_ready(sk, 0);
+	sk->sk_data_ready(sk);
 }
 
 static void dccp_fin(struct sock *sk, struct sk_buff *skb)
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 9e2f78bc1553..c69eb9c4fbb8 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -237,7 +237,7 @@ int dccp_child_process(struct sock *parent, struct sock *child,
 
 		/* Wakeup parent, send SIGIO */
 		if (state == DCCP_RESPOND && child->sk_state != state)
-			parent->sk_data_ready(parent, 0);
+			parent->sk_data_ready(parent);
 	} else {
 		/* Alas, it is possible again, because we do lookup
 		 * in main socket hash table and lock on listening
diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c
index c344163e6ac0..fe5f01485d33 100644
--- a/net/decnet/dn_nsp_in.c
+++ b/net/decnet/dn_nsp_in.c
@@ -585,7 +585,6 @@ out:
 static __inline__ int dn_queue_skb(struct sock *sk, struct sk_buff *skb, int sig, struct sk_buff_head *queue)
 {
 	int err;
-	int skb_len;
 
 	/* Cast skb->rcvbuf to unsigned... It's pointless, but reduces
 	   number of warnings when compiling with -W --ANK
@@ -600,12 +599,11 @@ static __inline__ int dn_queue_skb(struct sock *sk, struct sk_buff *skb, int sig
 	if (err)
 		goto out;
 
-	skb_len = skb->len;
 	skb_set_owner_r(skb, sk);
 	skb_queue_tail(queue, skb);
 
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, skb_len);
+		sk->sk_data_ready(sk);
 out:
 	return err;
 }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e1661f46fd19..d6b46eb2f94c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4413,7 +4413,7 @@ queue_and_out:
 		if (eaten > 0)
 			kfree_skb_partial(skb, fragstolen);
 		if (!sock_flag(sk, SOCK_DEAD))
-			sk->sk_data_ready(sk, 0);
+			sk->sk_data_ready(sk);
 		return;
 	}
 
@@ -4914,7 +4914,7 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *t
 				BUG();
 			tp->urg_data = TCP_URG_VALID | tmp;
 			if (!sock_flag(sk, SOCK_DEAD))
-				sk->sk_data_ready(sk, 0);
+				sk->sk_data_ready(sk);
 		}
 	}
 }
@@ -5000,11 +5000,11 @@ static bool tcp_dma_try_early_copy(struct sock *sk, struct sk_buff *skb,
 		    (tcp_flag_word(tcp_hdr(skb)) & TCP_FLAG_PSH) ||
 		    (atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1))) {
 			tp->ucopy.wakeup = 1;
-			sk->sk_data_ready(sk, 0);
+			sk->sk_data_ready(sk);
 		}
 	} else if (chunk > 0) {
 		tp->ucopy.wakeup = 1;
-		sk->sk_data_ready(sk, 0);
+		sk->sk_data_ready(sk);
 	}
 out:
 	return copied_early;
@@ -5275,7 +5275,7 @@ no_ack:
 #endif
 			if (eaten)
 				kfree_skb_partial(skb, fragstolen);
-			sk->sk_data_ready(sk, 0);
+			sk->sk_data_ready(sk);
 			return;
 		}
 	}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 6379894ec210..438f3b95143d 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1434,7 +1434,7 @@ static int tcp_v4_conn_req_fastopen(struct sock *sk,
 		tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
 		tp->syn_data_acked = 1;
 	}
-	sk->sk_data_ready(sk, 0);
+	sk->sk_data_ready(sk);
 	bh_unlock_sock(child);
 	sock_put(child);
 	WARN_ON(req->sk == NULL);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index ca788ada5bd3..05c1b155251d 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -745,7 +745,7 @@ int tcp_child_process(struct sock *parent, struct sock *child,
 					    skb->len);
 		/* Wakeup parent, send SIGIO */
 		if (state == TCP_SYN_RECV && child->sk_state != state)
-			parent->sk_data_ready(parent, 0);
+			parent->sk_data_ready(parent);
 	} else {
 		/* Alas, it is possible again, because we do lookup
 		 * in main socket hash table and lock on listening
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index a5e03119107a..01e77b0ae075 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1757,7 +1757,7 @@ static int iucv_callback_connreq(struct iucv_path *path,
 
 	/* Wake up accept */
 	nsk->sk_state = IUCV_CONNECTED;
-	sk->sk_data_ready(sk, 1);
+	sk->sk_data_ready(sk);
 	err = 0;
 fail:
 	bh_unlock_sock(sk);
@@ -1968,7 +1968,7 @@ static int afiucv_hs_callback_syn(struct sock *sk, struct sk_buff *skb)
 	if (!err) {
 		iucv_accept_enqueue(sk, nsk);
 		nsk->sk_state = IUCV_CONNECTED;
-		sk->sk_data_ready(sk, 1);
+		sk->sk_data_ready(sk);
 	} else
 		iucv_sock_kill(nsk);
 	bh_unlock_sock(sk);
diff --git a/net/key/af_key.c b/net/key/af_key.c
index e72589a8400d..f3c83073afc4 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -205,7 +205,7 @@ static int pfkey_broadcast_one(struct sk_buff *skb, struct sk_buff **skb2,
 		if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) {
 			skb_set_owner_r(*skb2, sk);
 			skb_queue_tail(&sk->sk_receive_queue, *skb2);
-			sk->sk_data_ready(sk, (*skb2)->len);
+			sk->sk_data_ready(sk);
 			*skb2 = NULL;
 			err = 0;
 		}
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index c2d585c4f7c5..894cda0206bb 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1653,7 +1653,7 @@ static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb)
 	else
 #endif /* CONFIG_NETLINK_MMAP */
 		skb_queue_tail(&sk->sk_receive_queue, skb);
-	sk->sk_data_ready(sk, len);
+	sk->sk_data_ready(sk);
 	return len;
 }
 
@@ -2394,7 +2394,7 @@ out:
 	return err ? : copied;
 }
 
-static void netlink_data_ready(struct sock *sk, int len)
+static void netlink_data_ready(struct sock *sk)
 {
 	BUG();
 }
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index b74aa0755521..ede50d197e10 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1011,7 +1011,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev)
 	skb_queue_head(&sk->sk_receive_queue, skb);
 
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, skb->len);
+		sk->sk_data_ready(sk);
 
 	bh_unlock_sock(sk);
 
diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c
index b486f12ae243..b4671958fcf9 100644
--- a/net/nfc/llcp_core.c
+++ b/net/nfc/llcp_core.c
@@ -976,7 +976,7 @@ static void nfc_llcp_recv_connect(struct nfc_llcp_local *local,
 	new_sk->sk_state = LLCP_CONNECTED;
 
 	/* Wake the listening processes */
-	parent->sk_data_ready(parent, 0);
+	parent->sk_data_ready(parent);
 
 	/* Send CC */
 	nfc_llcp_send_cc(new_sock);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 72e0c71fb01d..b85c67ccb797 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1848,7 +1848,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
 	skb->dropcount = atomic_read(&sk->sk_drops);
 	__skb_queue_tail(&sk->sk_receive_queue, skb);
 	spin_unlock(&sk->sk_receive_queue.lock);
-	sk->sk_data_ready(sk, skb->len);
+	sk->sk_data_ready(sk);
 	return 0;
 
 drop_n_acct:
@@ -2054,7 +2054,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	else
 		prb_clear_blk_fill_status(&po->rx_ring);
 
-	sk->sk_data_ready(sk, 0);
+	sk->sk_data_ready(sk);
 
 drop_n_restore:
 	if (skb_head != skb->data && skb_shared(skb)) {
@@ -2069,7 +2069,7 @@ ring_is_full:
 	po->stats.stats1.tp_drops++;
 	spin_unlock(&sk->sk_receive_queue.lock);
 
-	sk->sk_data_ready(sk, 0);
+	sk->sk_data_ready(sk);
 	kfree_skb(copy_skb);
 	goto drop_n_restore;
 }
diff --git a/net/phonet/pep-gprs.c b/net/phonet/pep-gprs.c
index a2fba7edfd1f..66dc65e7c6a1 100644
--- a/net/phonet/pep-gprs.c
+++ b/net/phonet/pep-gprs.c
@@ -37,7 +37,7 @@
 struct gprs_dev {
 	struct sock		*sk;
 	void			(*old_state_change)(struct sock *);
-	void			(*old_data_ready)(struct sock *, int);
+	void			(*old_data_ready)(struct sock *);
 	void			(*old_write_space)(struct sock *);
 
 	struct net_device	*dev;
@@ -146,7 +146,7 @@ drop:
 	return err;
 }
 
-static void gprs_data_ready(struct sock *sk, int len)
+static void gprs_data_ready(struct sock *sk)
 {
 	struct gprs_dev *gp = sk->sk_user_data;
 	struct sk_buff *skb;
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index e77411735de8..70a547ea5177 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -462,10 +462,9 @@ out:
 queue:
 	skb->dev = NULL;
 	skb_set_owner_r(skb, sk);
-	err = skb->len;
 	skb_queue_tail(queue, skb);
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, err);
+		sk->sk_data_ready(sk);
 	return NET_RX_SUCCESS;
 }
 
@@ -587,10 +586,9 @@ static int pipe_handler_do_rcv(struct sock *sk, struct sk_buff *skb)
 		pn->rx_credits--;
 		skb->dev = NULL;
 		skb_set_owner_r(skb, sk);
-		err = skb->len;
 		skb_queue_tail(&sk->sk_receive_queue, skb);
 		if (!sock_flag(sk, SOCK_DEAD))
-			sk->sk_data_ready(sk, err);
+			sk->sk_data_ready(sk);
 		return NET_RX_SUCCESS;
 
 	case PNS_PEP_CONNECT_RESP:
@@ -698,7 +696,7 @@ static int pep_do_rcv(struct sock *sk, struct sk_buff *skb)
 		skb_queue_head(&sk->sk_receive_queue, skb);
 		sk_acceptq_added(sk);
 		if (!sock_flag(sk, SOCK_DEAD))
-			sk->sk_data_ready(sk, 0);
+			sk->sk_data_ready(sk);
 		return NET_RX_SUCCESS;
 
 	case PNS_PEP_DISCONNECT_REQ:
diff --git a/net/rds/tcp.h b/net/rds/tcp.h
index 9cf2927d0021..65637491f728 100644
--- a/net/rds/tcp.h
+++ b/net/rds/tcp.h
@@ -61,12 +61,12 @@ void rds_tcp_state_change(struct sock *sk);
 /* tcp_listen.c */
 int rds_tcp_listen_init(void);
 void rds_tcp_listen_stop(void);
-void rds_tcp_listen_data_ready(struct sock *sk, int bytes);
+void rds_tcp_listen_data_ready(struct sock *sk);
 
 /* tcp_recv.c */
 int rds_tcp_recv_init(void);
 void rds_tcp_recv_exit(void);
-void rds_tcp_data_ready(struct sock *sk, int bytes);
+void rds_tcp_data_ready(struct sock *sk);
 int rds_tcp_recv(struct rds_connection *conn);
 void rds_tcp_inc_free(struct rds_incoming *inc);
 int rds_tcp_inc_copy_to_user(struct rds_incoming *inc, struct iovec *iov,
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 7787537e9c2e..4e638f851185 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -108,9 +108,9 @@ static void rds_tcp_accept_worker(struct work_struct *work)
 		cond_resched();
 }
 
-void rds_tcp_listen_data_ready(struct sock *sk, int bytes)
+void rds_tcp_listen_data_ready(struct sock *sk)
 {
-	void (*ready)(struct sock *sk, int bytes);
+	void (*ready)(struct sock *sk);
 
 	rdsdebug("listen data ready sk %p\n", sk);
 
@@ -132,7 +132,7 @@ void rds_tcp_listen_data_ready(struct sock *sk, int bytes)
 
 out:
 	read_unlock(&sk->sk_callback_lock);
-	ready(sk, bytes);
+	ready(sk);
 }
 
 int rds_tcp_listen_init(void)
diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c
index 4fac4f2bb9dc..9ae6e0a264ec 100644
--- a/net/rds/tcp_recv.c
+++ b/net/rds/tcp_recv.c
@@ -314,13 +314,13 @@ int rds_tcp_recv(struct rds_connection *conn)
 	return ret;
 }
 
-void rds_tcp_data_ready(struct sock *sk, int bytes)
+void rds_tcp_data_ready(struct sock *sk)
 {
-	void (*ready)(struct sock *sk, int bytes);
+	void (*ready)(struct sock *sk);
 	struct rds_connection *conn;
 	struct rds_tcp_connection *tc;
 
-	rdsdebug("data ready sk %p bytes %d\n", sk, bytes);
+	rdsdebug("data ready sk %p\n", sk);
 
 	read_lock(&sk->sk_callback_lock);
 	conn = sk->sk_user_data;
@@ -337,7 +337,7 @@ void rds_tcp_data_ready(struct sock *sk, int bytes)
 		queue_delayed_work(rds_wq, &conn->c_recv_w, 0);
 out:
 	read_unlock(&sk->sk_callback_lock);
-	ready(sk, bytes);
+	ready(sk);
 }
 
 int rds_tcp_recv_init(void)
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index c2cca2ee6aef..8451c8cdc9de 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -1041,7 +1041,7 @@ int rose_rx_call_request(struct sk_buff *skb, struct net_device *dev, struct ros
 	rose_start_heartbeat(make);
 
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, skb->len);
+		sk->sk_data_ready(sk);
 
 	return 1;
 }
diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/ar-input.c
index 73742647c135..63b21e580de9 100644
--- a/net/rxrpc/ar-input.c
+++ b/net/rxrpc/ar-input.c
@@ -113,7 +113,7 @@ int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb,
 			spin_unlock_bh(&sk->sk_receive_queue.lock);
 
 			if (!sock_flag(sk, SOCK_DEAD))
-				sk->sk_data_ready(sk, skb_len);
+				sk->sk_data_ready(sk);
 		}
 		skb = NULL;
 	} else {
@@ -632,14 +632,14 @@ cant_find_conn:
  * handle data received on the local endpoint
  * - may be called in interrupt context
  */
-void rxrpc_data_ready(struct sock *sk, int count)
+void rxrpc_data_ready(struct sock *sk)
 {
 	struct rxrpc_skb_priv *sp;
 	struct rxrpc_local *local;
 	struct sk_buff *skb;
 	int ret;
 
-	_enter("%p, %d", sk, count);
+	_enter("%p", sk);
 
 	ASSERT(!irqs_disabled());
 
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index c831d44b0841..ba9fd36d3f15 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -518,7 +518,7 @@ void rxrpc_UDP_error_handler(struct work_struct *);
  */
 extern const char *rxrpc_pkts[];
 
-void rxrpc_data_ready(struct sock *, int);
+void rxrpc_data_ready(struct sock *);
 int rxrpc_queue_rcv_skb(struct rxrpc_call *, struct sk_buff *, bool, bool);
 void rxrpc_fast_process_packet(struct rxrpc_call *, struct sk_buff *);
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 270d5bd97d8b..e13519e9df80 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -6745,7 +6745,7 @@ do_nonblock:
 	goto out;
 }
 
-void sctp_data_ready(struct sock *sk, int len)
+void sctp_data_ready(struct sock *sk)
 {
 	struct socket_wq *wq;
 
diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index 5dc94117e9d4..7144eb6a1b95 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -259,7 +259,7 @@ int sctp_ulpq_tail_event(struct sctp_ulpq *ulpq, struct sctp_ulpevent *event)
 		sctp_ulpq_clear_pd(ulpq);
 
 	if (queue == &sk->sk_receive_queue)
-		sk->sk_data_ready(sk, 0);
+		sk->sk_data_ready(sk);
 	return 1;
 
 out_free:
@@ -1135,5 +1135,5 @@ void sctp_ulpq_abort_pd(struct sctp_ulpq *ulpq, gfp_t gfp)
 
 	/* If there is data waiting, send it up the socket now. */
 	if (sctp_ulpq_clear_pd(ulpq) || ev)
-		sk->sk_data_ready(sk, 0);
+		sk->sk_data_ready(sk);
 }
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index b6e59f0a9475..c26ce9556581 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -60,7 +60,7 @@
 
 static struct svc_sock *svc_setup_socket(struct svc_serv *, struct socket *,
 					 int flags);
-static void		svc_udp_data_ready(struct sock *, int);
+static void		svc_udp_data_ready(struct sock *);
 static int		svc_udp_recvfrom(struct svc_rqst *);
 static int		svc_udp_sendto(struct svc_rqst *);
 static void		svc_sock_detach(struct svc_xprt *);
@@ -403,14 +403,14 @@ static void svc_sock_setbufsize(struct socket *sock, unsigned int snd,
 /*
  * INET callback when data has been received on the socket.
  */
-static void svc_udp_data_ready(struct sock *sk, int count)
+static void svc_udp_data_ready(struct sock *sk)
 {
 	struct svc_sock	*svsk = (struct svc_sock *)sk->sk_user_data;
 	wait_queue_head_t *wq = sk_sleep(sk);
 
 	if (svsk) {
-		dprintk("svc: socket %p(inet %p), count=%d, busy=%d\n",
-			svsk, sk, count,
+		dprintk("svc: socket %p(inet %p), busy=%d\n",
+			svsk, sk,
 			test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags));
 		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 		svc_xprt_enqueue(&svsk->sk_xprt);
@@ -731,7 +731,7 @@ static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)
  * A data_ready event on a listening socket means there's a connection
  * pending. Do not use state_change as a substitute for it.
  */
-static void svc_tcp_listen_data_ready(struct sock *sk, int count_unused)
+static void svc_tcp_listen_data_ready(struct sock *sk)
 {
 	struct svc_sock	*svsk = (struct svc_sock *)sk->sk_user_data;
 	wait_queue_head_t *wq;
@@ -783,7 +783,7 @@ static void svc_tcp_state_change(struct sock *sk)
 		wake_up_interruptible_all(wq);
 }
 
-static void svc_tcp_data_ready(struct sock *sk, int count)
+static void svc_tcp_data_ready(struct sock *sk)
 {
 	struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data;
 	wait_queue_head_t *wq = sk_sleep(sk);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 966763d735e9..96458d434324 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -254,7 +254,7 @@ struct sock_xprt {
 	/*
 	 * Saved socket callback addresses
 	 */
-	void			(*old_data_ready)(struct sock *, int);
+	void			(*old_data_ready)(struct sock *);
 	void			(*old_state_change)(struct sock *);
 	void			(*old_write_space)(struct sock *);
 	void			(*old_error_report)(struct sock *);
@@ -946,7 +946,7 @@ static int xs_local_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb)
  *
  * Currently this assumes we can read the whole reply in a single gulp.
  */
-static void xs_local_data_ready(struct sock *sk, int len)
+static void xs_local_data_ready(struct sock *sk)
 {
 	struct rpc_task *task;
 	struct rpc_xprt *xprt;
@@ -1009,7 +1009,7 @@ static void xs_local_data_ready(struct sock *sk, int len)
  * @len: how much data to read
  *
  */
-static void xs_udp_data_ready(struct sock *sk, int len)
+static void xs_udp_data_ready(struct sock *sk)
 {
 	struct rpc_task *task;
 	struct rpc_xprt *xprt;
@@ -1432,7 +1432,7 @@ static int xs_tcp_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, uns
  * @bytes: how much data to read
  *
  */
-static void xs_tcp_data_ready(struct sock *sk, int bytes)
+static void xs_tcp_data_ready(struct sock *sk)
 {
 	struct rpc_xprt *xprt;
 	read_descriptor_t rd_desc;
diff --git a/net/tipc/server.c b/net/tipc/server.c
index 646a930eefbf..a538a02f869b 100644
--- a/net/tipc/server.c
+++ b/net/tipc/server.c
@@ -119,7 +119,7 @@ static struct tipc_conn *tipc_conn_lookup(struct tipc_server *s, int conid)
 	return con;
 }
 
-static void sock_data_ready(struct sock *sk, int unused)
+static void sock_data_ready(struct sock *sk)
 {
 	struct tipc_conn *con;
 
@@ -297,7 +297,7 @@ static int tipc_accept_from_sock(struct tipc_conn *con)
 	newcon->usr_data = s->tipc_conn_new(newcon->conid);
 
 	/* Wake up receive process in case of 'SYN+' message */
-	newsock->sk->sk_data_ready(newsock->sk, 0);
+	newsock->sk->sk_data_ready(newsock->sk);
 	return ret;
 }
 
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index adc12e227303..3c0256962f7d 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -45,7 +45,7 @@
 #define CONN_TIMEOUT_DEFAULT	8000	/* default connect timeout = 8s */
 
 static int backlog_rcv(struct sock *sk, struct sk_buff *skb);
-static void tipc_data_ready(struct sock *sk, int len);
+static void tipc_data_ready(struct sock *sk);
 static void tipc_write_space(struct sock *sk);
 static int tipc_release(struct socket *sock);
 static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags);
@@ -1248,7 +1248,7 @@ static void tipc_write_space(struct sock *sk)
  * @sk: socket
  * @len: the length of messages
  */
-static void tipc_data_ready(struct sock *sk, int len)
+static void tipc_data_ready(struct sock *sk)
 {
 	struct socket_wq *wq;
 
@@ -1410,7 +1410,7 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf)
 	__skb_queue_tail(&sk->sk_receive_queue, buf);
 	skb_set_owner_r(buf, sk);
 
-	sk->sk_data_ready(sk, 0);
+	sk->sk_data_ready(sk);
 	return TIPC_OK;
 }
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 94404f19f9de..bb7e8ba821f4 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1217,7 +1217,7 @@ restart:
 	__skb_queue_tail(&other->sk_receive_queue, skb);
 	spin_unlock(&other->sk_receive_queue.lock);
 	unix_state_unlock(other);
-	other->sk_data_ready(other, 0);
+	other->sk_data_ready(other);
 	sock_put(other);
 	return 0;
 
@@ -1600,7 +1600,7 @@ restart:
 	if (max_level > unix_sk(other)->recursion_level)
 		unix_sk(other)->recursion_level = max_level;
 	unix_state_unlock(other);
-	other->sk_data_ready(other, len);
+	other->sk_data_ready(other);
 	sock_put(other);
 	scm_destroy(siocb->scm);
 	return len;
@@ -1706,7 +1706,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		if (max_level > unix_sk(other)->recursion_level)
 			unix_sk(other)->recursion_level = max_level;
 		unix_state_unlock(other);
-		other->sk_data_ready(other, size);
+		other->sk_data_ready(other);
 		sent += size;
 	}
 
diff --git a/net/vmw_vsock/vmci_transport_notify.c b/net/vmw_vsock/vmci_transport_notify.c
index 9a730744e7bc..9b7f207f2bee 100644
--- a/net/vmw_vsock/vmci_transport_notify.c
+++ b/net/vmw_vsock/vmci_transport_notify.c
@@ -315,7 +315,7 @@ vmci_transport_handle_wrote(struct sock *sk,
 	struct vsock_sock *vsk = vsock_sk(sk);
 	PKT_FIELD(vsk, sent_waiting_read) = false;
 #endif
-	sk->sk_data_ready(sk, 0);
+	sk->sk_data_ready(sk);
 }
 
 static void vmci_transport_notify_pkt_socket_init(struct sock *sk)
diff --git a/net/vmw_vsock/vmci_transport_notify_qstate.c b/net/vmw_vsock/vmci_transport_notify_qstate.c
index 622bd7aa1016..dc9c7929a2f9 100644
--- a/net/vmw_vsock/vmci_transport_notify_qstate.c
+++ b/net/vmw_vsock/vmci_transport_notify_qstate.c
@@ -92,7 +92,7 @@ vmci_transport_handle_wrote(struct sock *sk,
 			    bool bottom_half,
 			    struct sockaddr_vm *dst, struct sockaddr_vm *src)
 {
-	sk->sk_data_ready(sk, 0);
+	sk->sk_data_ready(sk);
 }
 
 static void vsock_block_update_write_window(struct sock *sk)
@@ -290,7 +290,7 @@ vmci_transport_notify_pkt_recv_post_dequeue(
 		/* See the comment in
 		 * vmci_transport_notify_pkt_send_post_enqueue().
 		 */
-		sk->sk_data_ready(sk, 0);
+		sk->sk_data_ready(sk);
 	}
 
 	return err;
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 6177479c7de9..5ad4418ef093 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -1064,7 +1064,7 @@ int x25_rx_call_request(struct sk_buff *skb, struct x25_neigh *nb,
 	x25_start_heartbeat(make);
 
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, skb->len);
+		sk->sk_data_ready(sk);
 	rc = 1;
 	sock_put(sk);
 out:
diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c
index d1b0dc79bb6f..7ac50098a375 100644
--- a/net/x25/x25_in.c
+++ b/net/x25/x25_in.c
@@ -79,7 +79,7 @@ static int x25_queue_rx_frame(struct sock *sk, struct sk_buff *skb, int more)
 	skb_set_owner_r(skbn, sk);
 	skb_queue_tail(&sk->sk_receive_queue, skbn);
 	if (!sock_flag(sk, SOCK_DEAD))
-		sk->sk_data_ready(sk, skbn->len);
+		sk->sk_data_ready(sk);
 
 	return 0;
 }
-- 
cgit v1.2.3