From 6ecec74520d8a357726e6c12f99080dbe7b347dd Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Wed, 26 Sep 2012 12:49:27 -0600
Subject: NVMe: Define SMART log

This data structure is defined in the NVMe specification.  It's not used
by the kernel, but is available for use by userspace software.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
---
 include/linux/nvme.h | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

(limited to 'include')

diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index c25cccaa555a..4fa3b0b9b071 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -137,6 +137,34 @@ enum {
 	NVME_LBAF_RP_DEGRADED	= 3,
 };
 
+struct nvme_smart_log {
+	__u8			critical_warning;
+	__u8			temperature[2];
+	__u8			avail_spare;
+	__u8			spare_thresh;
+	__u8			percent_used;
+	__u8			rsvd6[26];
+	__u8			data_units_read[16];
+	__u8			data_units_written[16];
+	__u8			host_reads[16];
+	__u8			host_writes[16];
+	__u8			ctrl_busy_time[16];
+	__u8			power_cycles[16];
+	__u8			power_on_hours[16];
+	__u8			unsafe_shutdowns[16];
+	__u8			media_errors[16];
+	__u8			num_err_log_entries[16];
+	__u8			rsvd192[320];
+};
+
+enum {
+	NVME_SMART_CRIT_SPARE		= 1 << 0,
+	NVME_SMART_CRIT_TEMPERATURE	= 1 << 1,
+	NVME_SMART_CRIT_RELIABILITY	= 1 << 2,
+	NVME_SMART_CRIT_MEDIA		= 1 << 3,
+	NVME_SMART_CRIT_VOLATILE_MEMORY	= 1 << 4,
+};
+
 struct nvme_lba_range_type {
 	__u8			type;
 	__u8			attributes;
-- 
cgit v1.2.3


From 8af294b472067e9034fe288d912455cc0961d1b9 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@opensource.wolfsonmicro.com>
Date: Fri, 22 Feb 2013 17:48:15 +0000
Subject: ASoC: dapm: Fix handling of loops

Currently if a path loops back on itself we correctly skip over it to
avoid going into an infinite loop but this causes us to ignore the need
to power up the path as we don't count the loop for the purposes of
counting inputs and outputs. This means that internal loopbacks within a
device that have powered devices on them won't be powered up.

Fix this by treating any path that is currently in the process of being
recursed as having a single input or output so that it is counted for
the purposes of power decisions.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Acked-by: Liam Girdwood <liam.r.girdwood@linux.intel.com>
---
 include/sound/soc-dapm.h |  1 +
 sound/soc/soc-dapm.c     | 15 +++++++++++++++
 2 files changed, 16 insertions(+)

(limited to 'include')

diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index e1ef63d4a5c4..44a30b108683 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -488,6 +488,7 @@ struct snd_soc_dapm_path {
 	/* status */
 	u32 connect:1;	/* source and sink widgets are connected */
 	u32 walked:1;	/* path has been walked */
+	u32 walking:1;  /* path is in the process of being walked */
 	u32 weak:1;	/* path ignored for power management */
 
 	int (*connected)(struct snd_soc_dapm_widget *source,
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 258acadb9e7d..f3255517de79 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -821,6 +821,7 @@ static int is_connected_output_ep(struct snd_soc_dapm_widget *widget,
 		    (widget->id == snd_soc_dapm_line &&
 		     !list_empty(&widget->sources))) {
 			widget->outputs = snd_soc_dapm_suspend_check(widget);
+			path->walking = 0;
 			return widget->outputs;
 		}
 	}
@@ -831,6 +832,9 @@ static int is_connected_output_ep(struct snd_soc_dapm_widget *widget,
 		if (path->weak)
 			continue;
 
+		if (path->walking)
+			return 1;
+
 		if (path->walked)
 			continue;
 
@@ -838,6 +842,7 @@ static int is_connected_output_ep(struct snd_soc_dapm_widget *widget,
 
 		if (path->sink && path->connect) {
 			path->walked = 1;
+			path->walking = 1;
 
 			/* do we need to add this widget to the list ? */
 			if (list) {
@@ -847,11 +852,14 @@ static int is_connected_output_ep(struct snd_soc_dapm_widget *widget,
 					dev_err(widget->dapm->dev,
 						"ASoC: could not add widget %s\n",
 						widget->name);
+					path->walking = 0;
 					return con;
 				}
 			}
 
 			con += is_connected_output_ep(path->sink, list);
+
+			path->walking = 0;
 		}
 	}
 
@@ -931,6 +939,9 @@ static int is_connected_input_ep(struct snd_soc_dapm_widget *widget,
 		if (path->weak)
 			continue;
 
+		if (path->walking)
+			return 1;
+
 		if (path->walked)
 			continue;
 
@@ -938,6 +949,7 @@ static int is_connected_input_ep(struct snd_soc_dapm_widget *widget,
 
 		if (path->source && path->connect) {
 			path->walked = 1;
+			path->walking = 1;
 
 			/* do we need to add this widget to the list ? */
 			if (list) {
@@ -947,11 +959,14 @@ static int is_connected_input_ep(struct snd_soc_dapm_widget *widget,
 					dev_err(widget->dapm->dev,
 						"ASoC: could not add widget %s\n",
 						widget->name);
+					path->walking = 0;
 					return con;
 				}
 			}
 
 			con += is_connected_input_ep(path->source, list);
+
+			path->walking = 0;
 		}
 	}
 
-- 
cgit v1.2.3


From 5a4d729139b4e94f670288a3505657311f95c886 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Fri, 1 Mar 2013 15:57:00 +0000
Subject: iio: Fix build error seen if IIO_TRIGGER is defined but IIO_BUFFER is
 not
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If CONFIG_IIO_TRIGGER is defined but CONFIG_IIO_BUFFER is not, the following
build error is seen.

drivers/iio/common/st_sensors/st_sensors_trigger.c:21:5: error:
redefinition of ‘st_sensors_allocate_trigger’
In file included from
drivers/iio/common/st_sensors/st_sensors_trigger.c:18:0:
include/linux/iio/common/st_sensors.h:239:19: note: previous
definition of ‘st_sensors_allocate_trigger’ was here
drivers/iio/common/st_sensors/st_sensors_trigger.c:65:6: error:
redefinition of ‘st_sensors_deallocate_trigger’
In file included from
drivers/iio/common/st_sensors/st_sensors_trigger.c:18:0:
include/linux/iio/common/st_sensors.h:244:20: note: previous
definition of ‘st_sensors_deallocate_trigger’ was here

This occurs because st_sensors_deallocate_trigger is built if CONFIG_IIO_TRIGGER
is defined, but the dummy function is compiled if CONFIG_IIO_BUFFER is defined.

Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Denis Ciocca <denis.ciocca@st.com>
Signed-off-by: Jonathan Cameron <jic23@kernel.org>
---
 include/linux/iio/common/st_sensors.h | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h
index 1f86a97ab2e2..8bd12be0b02f 100644
--- a/include/linux/iio/common/st_sensors.h
+++ b/include/linux/iio/common/st_sensors.h
@@ -227,14 +227,17 @@ struct st_sensor_data {
 };
 
 #ifdef CONFIG_IIO_BUFFER
+irqreturn_t st_sensors_trigger_handler(int irq, void *p);
+
+int st_sensors_get_buffer_element(struct iio_dev *indio_dev, u8 *buf);
+#endif
+
+#ifdef CONFIG_IIO_TRIGGER
 int st_sensors_allocate_trigger(struct iio_dev *indio_dev,
 				const struct iio_trigger_ops *trigger_ops);
 
 void st_sensors_deallocate_trigger(struct iio_dev *indio_dev);
 
-irqreturn_t st_sensors_trigger_handler(int irq, void *p);
-
-int st_sensors_get_buffer_element(struct iio_dev *indio_dev, u8 *buf);
 #else
 static inline int st_sensors_allocate_trigger(struct iio_dev *indio_dev,
 				const struct iio_trigger_ops *trigger_ops)
-- 
cgit v1.2.3


From 43febb27dcdaf9a15e2f362a6d09b0f191c4dcea Mon Sep 17 00:00:00 2001
From: Nishanth Menon <nm@ti.com>
Date: Mon, 4 Mar 2013 16:52:38 -0600
Subject: usb: gadget: composite: fix kernel-doc warnings

A few trivial fixes for composite driver:

Warning(include/linux/usb/composite.h:165): No description found for parameter
	'fs_descriptors'
Warning(include/linux/usb/composite.h:165): Excess struct/union/enum/typedef
	member 'descriptors' description in 'usb_function'
Warning(include/linux/usb/composite.h:321): No description found for parameter
	'gadget_driver'
Warning(drivers/usb/gadget/composite.c:1777): Excess function parameter 'bind'
	description in 'usb_composite_probe'

Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jiri Kosina <trivial@kernel.org>
Cc: linux-usb@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Nishanth Menon <nm@ti.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 drivers/usb/gadget/composite.c | 5 +----
 include/linux/usb/composite.h  | 3 ++-
 2 files changed, 3 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 7c821de8ce3d..c0d62b278610 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -1757,10 +1757,7 @@ static const struct usb_gadget_driver composite_driver_template = {
 /**
  * usb_composite_probe() - register a composite driver
  * @driver: the driver to register
- * @bind: the callback used to allocate resources that are shared across the
- *	whole device, such as string IDs, and add its configurations using
- *	@usb_add_config().  This may fail by returning a negative errno
- *	value; it should return zero on successful initialization.
+ *
  * Context: single threaded during gadget setup
  *
  * This function is used to register drivers using the composite driver
diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h
index 3c671c1b37f6..8860594d6364 100644
--- a/include/linux/usb/composite.h
+++ b/include/linux/usb/composite.h
@@ -60,7 +60,7 @@ struct usb_configuration;
  * @name: For diagnostics, identifies the function.
  * @strings: tables of strings, keyed by identifiers assigned during bind()
  *	and by language IDs provided in control requests
- * @descriptors: Table of full (or low) speed descriptors, using interface and
+ * @fs_descriptors: Table of full (or low) speed descriptors, using interface and
  *	string identifiers assigned during @bind().  If this pointer is null,
  *	the function will not be available at full speed (or at low speed).
  * @hs_descriptors: Table of high speed descriptors, using interface and
@@ -290,6 +290,7 @@ enum {
  *	after function notifications
  * @resume: Notifies configuration when the host restarts USB traffic,
  *	before function notifications
+ * @gadget_driver: Gadget driver controlling this driver
  *
  * Devices default to reporting self powered operation.  Devices which rely
  * on bus powered operation should report this in their @bind method.
-- 
cgit v1.2.3


From c705c78c0d0835a4aa5d0d9a3422e3218462030c Mon Sep 17 00:00:00 2001
From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Date: Tue, 5 Mar 2013 13:42:54 -0500
Subject: acpi: Export the acpi_processor_get_performance_info

The git commit d5aaffa9dd531c978c6f3fea06a2972653bd7fc8
(cpufreq: handle cpufreq being disabled for all exported function)
tightens the cpufreq API by returning errors when disable_cpufreq()
had been called.

The problem we are hitting is that the module xen-acpi-processor which
uses the ACPI's functions: acpi_processor_register_performance,
acpi_processor_preregister_performance, and acpi_processor_notify_smm
fails at acpi_processor_register_performance with -22.

Note that earlier during bootup in arch/x86/xen/setup.c there is also
an call to cpufreq's API: disable_cpufreq().

This is b/c we want the Linux kernel to parse the ACPI data, but leave
the cpufreq decisions to the hypervisor.

In v3.9 all the checks that d5aaffa9dd531c978c6f3fea06a2972653bd7fc8
added are now hit and the calls to cpufreq_register_notifier will now
fail. This means that acpi_processor_ppc_init ends up printing:

"Warning: Processor Platform Limit not supported"

and the acpi_processor_ppc_status is not set.

The repercussions of that is that the call to
acpi_processor_register_performance fails right away at:

	if (!(acpi_processor_ppc_status & PPC_REGISTERED))

and we don't progress any further on parsing and extracting the _P*
objects.

The only reason the Xen code called that function was b/c it was
exported and the only way to gather the P-states. But we can also
just make acpi_processor_get_performance_info be exported and not
use acpi_processor_register_performance. This patch does so.

Acked-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 drivers/acpi/processor_perflib.c | 4 ++--
 drivers/xen/xen-acpi-processor.c | 8 ++++----
 include/acpi/processor.h         | 3 +++
 3 files changed, 9 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index 53e7ac9403a7..e854582f29a6 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -465,7 +465,7 @@ static int acpi_processor_get_performance_states(struct acpi_processor *pr)
 	return result;
 }
 
-static int acpi_processor_get_performance_info(struct acpi_processor *pr)
+int acpi_processor_get_performance_info(struct acpi_processor *pr)
 {
 	int result = 0;
 	acpi_status status = AE_OK;
@@ -509,7 +509,7 @@ static int acpi_processor_get_performance_info(struct acpi_processor *pr)
 #endif
 	return result;
 }
-
+EXPORT_SYMBOL_GPL(acpi_processor_get_performance_info);
 int acpi_processor_notify_smm(struct module *calling_module)
 {
 	acpi_status status;
diff --git a/drivers/xen/xen-acpi-processor.c b/drivers/xen/xen-acpi-processor.c
index 316df65163cf..f3278a6603ca 100644
--- a/drivers/xen/xen-acpi-processor.c
+++ b/drivers/xen/xen-acpi-processor.c
@@ -500,16 +500,16 @@ static int __init xen_acpi_processor_init(void)
 	(void)acpi_processor_preregister_performance(acpi_perf_data);
 
 	for_each_possible_cpu(i) {
+		struct acpi_processor *pr;
 		struct acpi_processor_performance *perf;
 
+		pr = per_cpu(processors, i);
 		perf = per_cpu_ptr(acpi_perf_data, i);
-		rc = acpi_processor_register_performance(perf, i);
+		pr->performance = perf;
+		rc = acpi_processor_get_performance_info(pr);
 		if (rc)
 			goto err_out;
 	}
-	rc = acpi_processor_notify_smm(THIS_MODULE);
-	if (rc)
-		goto err_unregister;
 
 	for_each_possible_cpu(i) {
 		struct acpi_processor *_pr;
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index 555d0337ad95..b327b5a9296d 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -235,6 +235,9 @@ extern void acpi_processor_unregister_performance(struct
          if a _PPC object exists, rmmod is disallowed then */
 int acpi_processor_notify_smm(struct module *calling_module);
 
+/* parsing the _P* objects. */
+extern int acpi_processor_get_performance_info(struct acpi_processor *pr);
+
 /* for communication between multiple parts of the processor kernel module */
 DECLARE_PER_CPU(struct acpi_processor *, processors);
 extern struct acpi_processor_errata errata;
-- 
cgit v1.2.3


From 0e367ae46503cfe7791460c8ba8434a5d60b2bd5 Mon Sep 17 00:00:00 2001
From: David Vrabel <david.vrabel@citrix.com>
Date: Thu, 7 Mar 2013 17:32:01 +0000
Subject: xen/blkback: correctly respond to unknown, non-native requests

If the frontend is using a non-native protocol (e.g., a 64-bit
frontend with a 32-bit backend) and it sent an unrecognized request,
the request was not translated and the response would have the
incorrect ID.  This may cause the frontend driver to behave
incorrectly or crash.

Since the ID field in the request is always in the same place,
regardless of the request type we can get the correct ID and make a
valid response (which will report BLKIF_RSP_EOPNOTSUPP).

This bug affected 64-bit SLES 11 guests when using a 32-bit backend.
This guest does a BLKIF_OP_RESERVED_1 (BLKIF_OP_PACKET in the SLES
source) and would crash in blkif_int() as the ID in the response would
be invalid.

Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Cc: stable@vger.kernel.org
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 drivers/block/xen-blkback/blkback.c | 31 +++++++++++++++++++++++++++----
 drivers/block/xen-blkback/common.h  | 25 +++++++++++++++++++++++++
 include/xen/interface/io/blkif.h    | 10 ++++++++++
 3 files changed, 62 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 6d1cc3df2ac6..1a0faf6370ca 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -679,6 +679,16 @@ static int dispatch_discard_io(struct xen_blkif *blkif,
 	return err;
 }
 
+static int dispatch_other_io(struct xen_blkif *blkif,
+			     struct blkif_request *req,
+			     struct pending_req *pending_req)
+{
+	free_req(pending_req);
+	make_response(blkif, req->u.other.id, req->operation,
+		      BLKIF_RSP_EOPNOTSUPP);
+	return -EIO;
+}
+
 static void xen_blk_drain_io(struct xen_blkif *blkif)
 {
 	atomic_set(&blkif->drain, 1);
@@ -800,17 +810,30 @@ __do_block_io_op(struct xen_blkif *blkif)
 
 		/* Apply all sanity checks to /private copy/ of request. */
 		barrier();
-		if (unlikely(req.operation == BLKIF_OP_DISCARD)) {
+
+		switch (req.operation) {
+		case BLKIF_OP_READ:
+		case BLKIF_OP_WRITE:
+		case BLKIF_OP_WRITE_BARRIER:
+		case BLKIF_OP_FLUSH_DISKCACHE:
+			if (dispatch_rw_block_io(blkif, &req, pending_req))
+				goto done;
+			break;
+		case BLKIF_OP_DISCARD:
 			free_req(pending_req);
 			if (dispatch_discard_io(blkif, &req))
-				break;
-		} else if (dispatch_rw_block_io(blkif, &req, pending_req))
+				goto done;
+			break;
+		default:
+			if (dispatch_other_io(blkif, &req, pending_req))
+				goto done;
 			break;
+		}
 
 		/* Yield point for this unbounded loop. */
 		cond_resched();
 	}
-
+done:
 	return more_to_do;
 }
 
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index 6072390c7f57..195278ae993d 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -77,11 +77,18 @@ struct blkif_x86_32_request_discard {
 	uint64_t       nr_sectors;
 } __attribute__((__packed__));
 
+struct blkif_x86_32_request_other {
+	uint8_t        _pad1;
+	blkif_vdev_t   _pad2;
+	uint64_t       id;           /* private guest value, echoed in resp  */
+} __attribute__((__packed__));
+
 struct blkif_x86_32_request {
 	uint8_t        operation;    /* BLKIF_OP_???                         */
 	union {
 		struct blkif_x86_32_request_rw rw;
 		struct blkif_x86_32_request_discard discard;
+		struct blkif_x86_32_request_other other;
 	} u;
 } __attribute__((__packed__));
 
@@ -113,11 +120,19 @@ struct blkif_x86_64_request_discard {
 	uint64_t       nr_sectors;
 } __attribute__((__packed__));
 
+struct blkif_x86_64_request_other {
+	uint8_t        _pad1;
+	blkif_vdev_t   _pad2;
+	uint32_t       _pad3;        /* offsetof(blkif_..,u.discard.id)==8   */
+	uint64_t       id;           /* private guest value, echoed in resp  */
+} __attribute__((__packed__));
+
 struct blkif_x86_64_request {
 	uint8_t        operation;    /* BLKIF_OP_???                         */
 	union {
 		struct blkif_x86_64_request_rw rw;
 		struct blkif_x86_64_request_discard discard;
+		struct blkif_x86_64_request_other other;
 	} u;
 } __attribute__((__packed__));
 
@@ -278,6 +293,11 @@ static inline void blkif_get_x86_32_req(struct blkif_request *dst,
 		dst->u.discard.nr_sectors = src->u.discard.nr_sectors;
 		break;
 	default:
+		/*
+		 * Don't know how to translate this op. Only get the
+		 * ID so failure can be reported to the frontend.
+		 */
+		dst->u.other.id = src->u.other.id;
 		break;
 	}
 }
@@ -309,6 +329,11 @@ static inline void blkif_get_x86_64_req(struct blkif_request *dst,
 		dst->u.discard.nr_sectors = src->u.discard.nr_sectors;
 		break;
 	default:
+		/*
+		 * Don't know how to translate this op. Only get the
+		 * ID so failure can be reported to the frontend.
+		 */
+		dst->u.other.id = src->u.other.id;
 		break;
 	}
 }
diff --git a/include/xen/interface/io/blkif.h b/include/xen/interface/io/blkif.h
index 01c3d62436ef..ffd4652de91c 100644
--- a/include/xen/interface/io/blkif.h
+++ b/include/xen/interface/io/blkif.h
@@ -138,11 +138,21 @@ struct blkif_request_discard {
 	uint8_t        _pad3;
 } __attribute__((__packed__));
 
+struct blkif_request_other {
+	uint8_t      _pad1;
+	blkif_vdev_t _pad2;        /* only for read/write requests         */
+#ifdef CONFIG_X86_64
+	uint32_t     _pad3;        /* offsetof(blkif_req..,u.other.id)==8*/
+#endif
+	uint64_t     id;           /* private guest value, echoed in resp  */
+} __attribute__((__packed__));
+
 struct blkif_request {
 	uint8_t        operation;    /* BLKIF_OP_???                         */
 	union {
 		struct blkif_request_rw rw;
 		struct blkif_request_discard discard;
+		struct blkif_request_other other;
 	} u;
 } __attribute__((__packed__));
 
-- 
cgit v1.2.3


From df545d1cd01aab3ba3f687d5423e6c3687b069d8 Mon Sep 17 00:00:00 2001
From: Laxman Dewangan <ldewangan@nvidia.com>
Date: Fri, 1 Mar 2013 20:13:46 +0530
Subject: mfd: palmas: Provide irq flags through DT/platform data

Currently driver sets the irq type to IRQF_TRIGGER_LOW which is
causing interrupt registration failure in ARM based SoCs as:
[    0.208479] genirq: Setting trigger mode 8 for irq 118 failed (gic_set_type+0x0/0xf0)
[    0.208513] dummy 0-0059: Failed to request IRQ 118: -22

Provide the irq flags through platform data if device is registered
through board file or get the irq type from DT node property in place
of hardcoding the irq flag in driver to support multiple platforms.

Also configure the device to generate the interrupt signal according to
flag type.

Signed-off-by: Laxman Dewangan <ldewangan@nvidia.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/palmas.c       | 36 +++++++++++++++++++++++++++++++++---
 include/linux/mfd/palmas.h |  1 +
 2 files changed, 34 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/palmas.c b/drivers/mfd/palmas.c
index bbdbc50a3cca..73bf76df1044 100644
--- a/drivers/mfd/palmas.c
+++ b/drivers/mfd/palmas.c
@@ -257,9 +257,24 @@ static struct regmap_irq_chip palmas_irq_chip = {
 			PALMAS_INT1_MASK),
 };
 
-static void palmas_dt_to_pdata(struct device_node *node,
+static int palmas_set_pdata_irq_flag(struct i2c_client *i2c,
 		struct palmas_platform_data *pdata)
 {
+	struct irq_data *irq_data = irq_get_irq_data(i2c->irq);
+	if (!irq_data) {
+		dev_err(&i2c->dev, "Invalid IRQ: %d\n", i2c->irq);
+		return -EINVAL;
+	}
+
+	pdata->irq_flags = irqd_get_trigger_type(irq_data);
+	dev_info(&i2c->dev, "Irq flag is 0x%08x\n", pdata->irq_flags);
+	return 0;
+}
+
+static void palmas_dt_to_pdata(struct i2c_client *i2c,
+		struct palmas_platform_data *pdata)
+{
+	struct device_node *node = i2c->dev.of_node;
 	int ret;
 	u32 prop;
 
@@ -283,6 +298,8 @@ static void palmas_dt_to_pdata(struct device_node *node,
 		pdata->power_ctrl = PALMAS_POWER_CTRL_NSLEEP_MASK |
 					PALMAS_POWER_CTRL_ENABLE1_MASK |
 					PALMAS_POWER_CTRL_ENABLE2_MASK;
+	if (i2c->irq)
+		palmas_set_pdata_irq_flag(i2c, pdata);
 }
 
 static int palmas_i2c_probe(struct i2c_client *i2c,
@@ -304,7 +321,7 @@ static int palmas_i2c_probe(struct i2c_client *i2c,
 		if (!pdata)
 			return -ENOMEM;
 
-		palmas_dt_to_pdata(node, pdata);
+		palmas_dt_to_pdata(i2c, pdata);
 	}
 
 	if (!pdata)
@@ -344,6 +361,19 @@ static int palmas_i2c_probe(struct i2c_client *i2c,
 		}
 	}
 
+	/* Change interrupt line output polarity */
+	if (pdata->irq_flags & IRQ_TYPE_LEVEL_HIGH)
+		reg = PALMAS_POLARITY_CTRL_INT_POLARITY;
+	else
+		reg = 0;
+	ret = palmas_update_bits(palmas, PALMAS_PU_PD_OD_BASE,
+			PALMAS_POLARITY_CTRL, PALMAS_POLARITY_CTRL_INT_POLARITY,
+			reg);
+	if (ret < 0) {
+		dev_err(palmas->dev, "POLARITY_CTRL updat failed: %d\n", ret);
+		goto err;
+	}
+
 	/* Change IRQ into clear on read mode for efficiency */
 	slave = PALMAS_BASE_TO_SLAVE(PALMAS_INTERRUPT_BASE);
 	addr = PALMAS_BASE_TO_REG(PALMAS_INTERRUPT_BASE, PALMAS_INT_CTRL);
@@ -352,7 +382,7 @@ static int palmas_i2c_probe(struct i2c_client *i2c,
 	regmap_write(palmas->regmap[slave], addr, reg);
 
 	ret = regmap_add_irq_chip(palmas->regmap[slave], palmas->irq,
-			IRQF_ONESHOT | IRQF_TRIGGER_LOW, 0, &palmas_irq_chip,
+			IRQF_ONESHOT | pdata->irq_flags, 0, &palmas_irq_chip,
 			&palmas->irq_data);
 	if (ret < 0)
 		goto err;
diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h
index a4d13d7cd001..3bbda22721ea 100644
--- a/include/linux/mfd/palmas.h
+++ b/include/linux/mfd/palmas.h
@@ -221,6 +221,7 @@ struct palmas_clk_platform_data {
 };
 
 struct palmas_platform_data {
+	int irq_flags;
 	int gpio_base;
 
 	/* bit value to be loaded to the POWER_CTRL register */
-- 
cgit v1.2.3


From 80e4e6716e43500c5c7d4ff4f73fc1b56f024083 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@opensource.wolfsonmicro.com>
Date: Sat, 2 Mar 2013 15:25:50 +0800
Subject: mfd: tps65912: Declare and use tps65912_irq_exit()

Clean up interrupts on exit, silencing a sparse warning caused by
tps65912_irq_exit() being defined but not prototyped as we go.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 drivers/mfd/tps65912-core.c  | 1 +
 include/linux/mfd/tps65912.h | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/drivers/mfd/tps65912-core.c b/drivers/mfd/tps65912-core.c
index 4658b5bdcd84..aeb8e40ab424 100644
--- a/drivers/mfd/tps65912-core.c
+++ b/drivers/mfd/tps65912-core.c
@@ -169,6 +169,7 @@ err:
 void tps65912_device_exit(struct tps65912 *tps65912)
 {
 	mfd_remove_devices(tps65912->dev);
+	tps65912_irq_exit(tps65912);
 	kfree(tps65912);
 }
 
diff --git a/include/linux/mfd/tps65912.h b/include/linux/mfd/tps65912.h
index aaceab402ec5..6d309032dc0d 100644
--- a/include/linux/mfd/tps65912.h
+++ b/include/linux/mfd/tps65912.h
@@ -323,5 +323,6 @@ int tps65912_device_init(struct tps65912 *tps65912);
 void tps65912_device_exit(struct tps65912 *tps65912);
 int tps65912_irq_init(struct tps65912 *tps65912, int irq,
 			struct tps65912_platform_data *pdata);
+int tps65912_irq_exit(struct tps65912 *tps65912);
 
 #endif /*  __LINUX_MFD_TPS65912_H */
-- 
cgit v1.2.3


From fd860195a4f9d661754345bd06a3adb30d12d882 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@opensource.wolfsonmicro.com>
Date: Fri, 8 Mar 2013 10:47:21 +0800
Subject: mfd: wm831x: Don't forward declare enum wm831x_auxadc

We can't forward declare enums.

Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Samuel Ortiz <sameo@linux.intel.com>
---
 include/linux/mfd/wm831x/auxadc.h | 2 ++
 include/linux/mfd/wm831x/core.h   | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mfd/wm831x/auxadc.h b/include/linux/mfd/wm831x/auxadc.h
index b132067e9e99..867aa23f9370 100644
--- a/include/linux/mfd/wm831x/auxadc.h
+++ b/include/linux/mfd/wm831x/auxadc.h
@@ -15,6 +15,8 @@
 #ifndef __MFD_WM831X_AUXADC_H__
 #define __MFD_WM831X_AUXADC_H__
 
+struct wm831x;
+
 /*
  * R16429 (0x402D) - AuxADC Data
  */
diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h
index 4a3b83a77614..76c22648436f 100644
--- a/include/linux/mfd/wm831x/core.h
+++ b/include/linux/mfd/wm831x/core.h
@@ -20,6 +20,7 @@
 #include <linux/irqdomain.h>
 #include <linux/list.h>
 #include <linux/regmap.h>
+#include <linux/mfd/wm831x/auxadc.h>
 
 /*
  * Register values.
@@ -355,7 +356,6 @@ enum wm831x_parent {
 };
 
 struct wm831x;
-enum wm831x_auxadc;
 
 typedef int (*wm831x_auxadc_read_fn)(struct wm831x *wm831x,
 				     enum wm831x_auxadc input);
-- 
cgit v1.2.3


From e06c93cacb82dd147266fd1bdb2d0a0bd45ff2c1 Mon Sep 17 00:00:00 2001
From: Ley Foon Tan <lftan@altera.com>
Date: Thu, 7 Mar 2013 10:28:37 +0800
Subject: tty/serial: Add support for Altera serial port

Add support for Altera 8250/16550 compatible serial port.

Signed-off-by: Ley Foon Tan <lftan@altera.com>
Cc: stable <stable@vger.kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 .../devicetree/bindings/tty/serial/of-serial.txt   |  3 +++
 drivers/tty/serial/8250/8250.c                     | 23 +++++++++++++++++++++-
 drivers/tty/serial/of_serial.c                     |  6 ++++++
 include/uapi/linux/serial_core.h                   |  5 ++++-
 4 files changed, 35 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/Documentation/devicetree/bindings/tty/serial/of-serial.txt b/Documentation/devicetree/bindings/tty/serial/of-serial.txt
index 1e1145ca4f3c..8f01cb190f25 100644
--- a/Documentation/devicetree/bindings/tty/serial/of-serial.txt
+++ b/Documentation/devicetree/bindings/tty/serial/of-serial.txt
@@ -11,6 +11,9 @@ Required properties:
 	- "nvidia,tegra20-uart"
 	- "nxp,lpc3220-uart"
 	- "ibm,qpace-nwp-serial"
+	- "altr,16550-FIFO32"
+	- "altr,16550-FIFO64"
+	- "altr,16550-FIFO128"
 	- "serial" if the port type is unknown.
 - reg : offset and length of the register set for the device.
 - interrupts : should contain uart interrupt.
diff --git a/drivers/tty/serial/8250/8250.c b/drivers/tty/serial/8250/8250.c
index 0efc815a4968..661096d25620 100644
--- a/drivers/tty/serial/8250/8250.c
+++ b/drivers/tty/serial/8250/8250.c
@@ -301,7 +301,28 @@ static const struct serial8250_config uart_config[] = {
 	},
 	[PORT_8250_CIR] = {
 		.name		= "CIR port"
-	}
+	},
+	[PORT_ALTR_16550_F32] = {
+		.name		= "Altera 16550 FIFO32",
+		.fifo_size	= 32,
+		.tx_loadsz	= 32,
+		.fcr		= UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10,
+		.flags		= UART_CAP_FIFO | UART_CAP_AFE,
+	},
+	[PORT_ALTR_16550_F64] = {
+		.name		= "Altera 16550 FIFO64",
+		.fifo_size	= 64,
+		.tx_loadsz	= 64,
+		.fcr		= UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10,
+		.flags		= UART_CAP_FIFO | UART_CAP_AFE,
+	},
+	[PORT_ALTR_16550_F128] = {
+		.name		= "Altera 16550 FIFO128",
+		.fifo_size	= 128,
+		.tx_loadsz	= 128,
+		.fcr		= UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10,
+		.flags		= UART_CAP_FIFO | UART_CAP_AFE,
+	},
 };
 
 /* Uart divisor latch read */
diff --git a/drivers/tty/serial/of_serial.c b/drivers/tty/serial/of_serial.c
index d5874605682b..b025d5438275 100644
--- a/drivers/tty/serial/of_serial.c
+++ b/drivers/tty/serial/of_serial.c
@@ -241,6 +241,12 @@ static struct of_device_id of_platform_serial_table[] = {
 	{ .compatible = "ns16850",  .data = (void *)PORT_16850, },
 	{ .compatible = "nvidia,tegra20-uart", .data = (void *)PORT_TEGRA, },
 	{ .compatible = "nxp,lpc3220-uart", .data = (void *)PORT_LPC3220, },
+	{ .compatible = "altr,16550-FIFO32",
+		.data = (void *)PORT_ALTR_16550_F32, },
+	{ .compatible = "altr,16550-FIFO64",
+		.data = (void *)PORT_ALTR_16550_F64, },
+	{ .compatible = "altr,16550-FIFO128",
+		.data = (void *)PORT_ALTR_16550_F128, },
 #ifdef CONFIG_SERIAL_OF_PLATFORM_NWPSERIAL
 	{ .compatible = "ibm,qpace-nwp-serial",
 		.data = (void *)PORT_NWPSERIAL, },
diff --git a/include/uapi/linux/serial_core.h b/include/uapi/linux/serial_core.h
index b6a23a483d74..74c2bf7211f8 100644
--- a/include/uapi/linux/serial_core.h
+++ b/include/uapi/linux/serial_core.h
@@ -51,7 +51,10 @@
 #define PORT_8250_CIR	23	/* CIR infrared port, has its own driver */
 #define PORT_XR17V35X	24	/* Exar XR17V35x UARTs */
 #define PORT_BRCM_TRUMANAGE	25
-#define PORT_MAX_8250	25	/* max port ID */
+#define PORT_ALTR_16550_F32 26	/* Altera 16550 UART with 32 FIFOs */
+#define PORT_ALTR_16550_F64 27	/* Altera 16550 UART with 64 FIFOs */
+#define PORT_ALTR_16550_F128 28 /* Altera 16550 UART with 128 FIFOs */
+#define PORT_MAX_8250	28	/* max port ID */
 
 /*
  * ARM specific type numbers.  These are not currently guaranteed
-- 
cgit v1.2.3


From 5857f70c8a62377c2304d8ad27e579881728fc5a Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 4 Mar 2013 14:32:54 -0800
Subject: idr: fix new kernel-doc warnings

Fix new kernel-doc warnings in idr:

  Warning(include/linux/idr.h:113): No description found for parameter 'idr'
  Warning(include/linux/idr.h:113): Excess function parameter 'idp' description in 'idr_find'
  Warning(lib/idr.c:232): Excess function parameter 'id' description in 'sub_alloc'
  Warning(lib/idr.c:232): Excess function parameter 'id' description in 'sub_alloc'

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/idr.h | 2 +-
 lib/idr.c           | 1 -
 2 files changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/idr.h b/include/linux/idr.h
index a6f38b5c34e4..8c1f81f823c8 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -99,7 +99,7 @@ static inline void idr_preload_end(void)
 
 /**
  * idr_find - return pointer for given id
- * @idp: idr handle
+ * @idr: idr handle
  * @id: lookup key
  *
  * Return the pointer given the id it has been registered with.  A %NULL
diff --git a/lib/idr.c b/lib/idr.c
index 00739aaf95a2..4f82a284c6a2 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -214,7 +214,6 @@ EXPORT_SYMBOL(idr_pre_get);
  * sub_alloc - try to allocate an id without growing the tree depth
  * @idp: idr handle
  * @starting_id: id to start search at
- * @id: pointer to the allocated handle
  * @pa: idr_layer[MAX_IDR_LEVEL] used as backtrack buffer
  * @gfp_mask: allocation mask for idr_layer_alloc()
  * @layer_idr: optional idr passed to idr_layer_alloc()
-- 
cgit v1.2.3


From 00c30e0681bf5563c8670c0ab419886f56626430 Mon Sep 17 00:00:00 2001
From: Jonas Bonn <jonas@southpole.se>
Date: Thu, 28 Feb 2013 06:37:05 +0100
Subject: asm-generic: move cmpxchg*_local defs to cmpxchg.h

asm/cmpxchg.h can be included on its own and needs to be self-consistent.
The definitions for the cmpxchg*_local macros, as such, need to be part
of this file.

This fixes a build issue on OpenRISC since the system.h smashing patch
96f951edb1f1bdbbc99b0cd458f9808bb83d58ae that introdued the direct inclusion
asm/cmpxchg.h into linux/llist.h.

CC: David Howells <dhowells@redhat.com>
Signed-off-by: Jonas Bonn <jonas@southpole.se>
Acked-by: Arnd Bergmann <arnd@arndb.de>
---
 include/asm-generic/atomic.h  |  6 ------
 include/asm-generic/cmpxchg.h | 10 ++++++++++
 2 files changed, 10 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index 1ced6413ea03..33bd2de3bc1e 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -136,12 +136,6 @@ static inline void atomic_dec(atomic_t *v)
 #define atomic_xchg(ptr, v)		(xchg(&(ptr)->counter, (v)))
 #define atomic_cmpxchg(v, old, new)	(cmpxchg(&((v)->counter), (old), (new)))
 
-#define cmpxchg_local(ptr, o, n)				  	       \
-	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
-			(unsigned long)(n), sizeof(*(ptr))))
-
-#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
-
 static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 {
   int c, old;
diff --git a/include/asm-generic/cmpxchg.h b/include/asm-generic/cmpxchg.h
index 14883026015d..811fb1e9b061 100644
--- a/include/asm-generic/cmpxchg.h
+++ b/include/asm-generic/cmpxchg.h
@@ -92,6 +92,16 @@ unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
  */
 #include <asm-generic/cmpxchg-local.h>
 
+#ifndef cmpxchg_local
+#define cmpxchg_local(ptr, o, n)				  	       \
+	((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\
+			(unsigned long)(n), sizeof(*(ptr))))
+#endif
+
+#ifndef cmpxchg64_local
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+#endif
+
 #define cmpxchg(ptr, o, n)	cmpxchg_local((ptr), (o), (n))
 #define cmpxchg64(ptr, o, n)	cmpxchg64_local((ptr), (o), (n))
 
-- 
cgit v1.2.3


From 0ec83bd2460ed6aed0e7f29f9e0633b054621c02 Mon Sep 17 00:00:00 2001
From: Chanwoo Choi <cw00.choi@samsung.com>
Date: Wed, 13 Mar 2013 17:38:57 +0900
Subject: extcon: max77693: Initialize register of MUIC device to bring up it
 without platform data

This patch set default value of MUIC register to bring up MUIC device.

If user don't set some initial value for MUIC device through platform data,
extcon-max77693 driver use 'default_init_data' to bring up base operation
of MAX77693 MUIC device.

Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: Myungjoo Ham <myungjoo.ham@samsung.com>
---
 drivers/extcon/extcon-max77693.c     | 93 ++++++++++++++++++++++++++----------
 include/linux/mfd/max77693-private.h | 23 +++++++++
 2 files changed, 91 insertions(+), 25 deletions(-)

(limited to 'include')

diff --git a/drivers/extcon/extcon-max77693.c b/drivers/extcon/extcon-max77693.c
index fea10624f3e5..8f3c947b0029 100644
--- a/drivers/extcon/extcon-max77693.c
+++ b/drivers/extcon/extcon-max77693.c
@@ -32,6 +32,38 @@
 #define	DEV_NAME			"max77693-muic"
 #define	DELAY_MS_DEFAULT		20000		/* unit: millisecond */
 
+/*
+ * Default value of MAX77693 register to bring up MUIC device.
+ * If user don't set some initial value for MUIC device through platform data,
+ * extcon-max77693 driver use 'default_init_data' to bring up base operation
+ * of MAX77693 MUIC device.
+ */
+struct max77693_reg_data default_init_data[] = {
+	{
+		/* STATUS2 - [3]ChgDetRun */
+		.addr = MAX77693_MUIC_REG_STATUS2,
+		.data = STATUS2_CHGDETRUN_MASK,
+	}, {
+		/* INTMASK1 - Unmask [3]ADC1KM,[0]ADCM */
+		.addr = MAX77693_MUIC_REG_INTMASK1,
+		.data = INTMASK1_ADC1K_MASK
+			| INTMASK1_ADC_MASK,
+	}, {
+		/* INTMASK2 - Unmask [0]ChgTypM */
+		.addr = MAX77693_MUIC_REG_INTMASK2,
+		.data = INTMASK2_CHGTYP_MASK,
+	}, {
+		/* INTMASK3 - Mask all of interrupts */
+		.addr = MAX77693_MUIC_REG_INTMASK3,
+		.data = 0x0,
+	}, {
+		/* CDETCTRL2 */
+		.addr = MAX77693_MUIC_REG_CDETCTRL2,
+		.data = CDETCTRL2_VIDRMEN_MASK
+			| CDETCTRL2_DXOVPEN_MASK,
+	},
+};
+
 enum max77693_muic_adc_debounce_time {
 	ADC_DEBOUNCE_TIME_5MS = 0,
 	ADC_DEBOUNCE_TIME_10MS,
@@ -1046,6 +1078,8 @@ static int max77693_muic_probe(struct platform_device *pdev)
 	struct max77693_dev *max77693 = dev_get_drvdata(pdev->dev.parent);
 	struct max77693_platform_data *pdata = dev_get_platdata(max77693->dev);
 	struct max77693_muic_info *info;
+	struct max77693_reg_data *init_data;
+	int num_init_data;
 	int delay_jiffies;
 	int ret;
 	int i;
@@ -1144,35 +1178,44 @@ static int max77693_muic_probe(struct platform_device *pdev)
 		goto err_irq;
 	}
 
+
+	/* Initialize MUIC register by using platform data or default data */
 	if (pdata->muic_data) {
-		struct max77693_muic_platform_data *muic_pdata = pdata->muic_data;
+		init_data = pdata->muic_data->init_data;
+		num_init_data = pdata->muic_data->num_init_data;
+	} else {
+		init_data = default_init_data;
+		num_init_data = ARRAY_SIZE(default_init_data);
+	}
+
+	for (i = 0 ; i < num_init_data ; i++) {
+		enum max77693_irq_source irq_src
+				= MAX77693_IRQ_GROUP_NR;
 
-		/* Initialize MUIC register by using platform data */
-		for (i = 0 ; i < muic_pdata->num_init_data ; i++) {
-			enum max77693_irq_source irq_src
-					= MAX77693_IRQ_GROUP_NR;
-
-			max77693_write_reg(info->max77693->regmap_muic,
-					muic_pdata->init_data[i].addr,
-					muic_pdata->init_data[i].data);
-
-			switch (muic_pdata->init_data[i].addr) {
-			case MAX77693_MUIC_REG_INTMASK1:
-				irq_src = MUIC_INT1;
-				break;
-			case MAX77693_MUIC_REG_INTMASK2:
-				irq_src = MUIC_INT2;
-				break;
-			case MAX77693_MUIC_REG_INTMASK3:
-				irq_src = MUIC_INT3;
-				break;
-			}
-
-			if (irq_src < MAX77693_IRQ_GROUP_NR)
-				info->max77693->irq_masks_cur[irq_src]
-					= muic_pdata->init_data[i].data;
+		max77693_write_reg(info->max77693->regmap_muic,
+				init_data[i].addr,
+				init_data[i].data);
+
+		switch (init_data[i].addr) {
+		case MAX77693_MUIC_REG_INTMASK1:
+			irq_src = MUIC_INT1;
+			break;
+		case MAX77693_MUIC_REG_INTMASK2:
+			irq_src = MUIC_INT2;
+			break;
+		case MAX77693_MUIC_REG_INTMASK3:
+			irq_src = MUIC_INT3;
+			break;
 		}
 
+		if (irq_src < MAX77693_IRQ_GROUP_NR)
+			info->max77693->irq_masks_cur[irq_src]
+				= init_data[i].data;
+	}
+
+	if (pdata->muic_data) {
+		struct max77693_muic_platform_data *muic_pdata = pdata->muic_data;
+
 		/*
 		 * Default usb/uart path whether UART/USB or AUX_UART/AUX_USB
 		 * h/w path of COMP2/COMN1 on CONTROL1 register.
diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h
index 5b18ecde69b5..1aa4f13cdfa6 100644
--- a/include/linux/mfd/max77693-private.h
+++ b/include/linux/mfd/max77693-private.h
@@ -106,6 +106,29 @@ enum max77693_muic_reg {
 	MAX77693_MUIC_REG_END,
 };
 
+/* MAX77693 INTMASK1~2 Register */
+#define INTMASK1_ADC1K_SHIFT		3
+#define INTMASK1_ADCERR_SHIFT		2
+#define INTMASK1_ADCLOW_SHIFT		1
+#define INTMASK1_ADC_SHIFT		0
+#define INTMASK1_ADC1K_MASK		(1 << INTMASK1_ADC1K_SHIFT)
+#define INTMASK1_ADCERR_MASK		(1 << INTMASK1_ADCERR_SHIFT)
+#define INTMASK1_ADCLOW_MASK		(1 << INTMASK1_ADCLOW_SHIFT)
+#define INTMASK1_ADC_MASK		(1 << INTMASK1_ADC_SHIFT)
+
+#define INTMASK2_VIDRM_SHIFT		5
+#define INTMASK2_VBVOLT_SHIFT		4
+#define INTMASK2_DXOVP_SHIFT		3
+#define INTMASK2_DCDTMR_SHIFT		2
+#define INTMASK2_CHGDETRUN_SHIFT	1
+#define INTMASK2_CHGTYP_SHIFT		0
+#define INTMASK2_VIDRM_MASK		(1 << INTMASK2_VIDRM_SHIFT)
+#define INTMASK2_VBVOLT_MASK		(1 << INTMASK2_VBVOLT_SHIFT)
+#define INTMASK2_DXOVP_MASK		(1 << INTMASK2_DXOVP_SHIFT)
+#define INTMASK2_DCDTMR_MASK		(1 << INTMASK2_DCDTMR_SHIFT)
+#define INTMASK2_CHGDETRUN_MASK		(1 << INTMASK2_CHGDETRUN_SHIFT)
+#define INTMASK2_CHGTYP_MASK		(1 << INTMASK2_CHGTYP_SHIFT)
+
 /* MAX77693 MUIC - STATUS1~3 Register */
 #define STATUS1_ADC_SHIFT		(0)
 #define STATUS1_ADCLOW_SHIFT		(5)
-- 
cgit v1.2.3


From a79eac7165ed62114e6ca197195aa5060a54f137 Mon Sep 17 00:00:00 2001
From: Johan Hovold <jhovold@gmail.com>
Date: Tue, 5 Feb 2013 14:35:11 +0100
Subject: atmel_lcdfb: fix 16-bpp modes on older SOCs

Fix regression introduced by commit 787f9fd23283 ("atmel_lcdfb: support
16bit BGR:565 mode, remove unsupported 15bit modes") which broke 16-bpp
modes for older SOCs which use IBGR:555 (msb is intensity) rather
than BGR:565.

Use SOC-type to determine the pixel layout.

Tested on at91sam9263 and at91sam9g45.

Cc: <stable@vger.kernel.org>
Acked-by: Peter Korsgaard <jacmet@sunsite.dk>
Signed-off-by: Johan Hovold <jhovold@gmail.com>
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
---
 drivers/video/atmel_lcdfb.c | 22 +++++++++++++++-------
 include/video/atmel_lcdc.h  |  1 +
 2 files changed, 16 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/video/atmel_lcdfb.c b/drivers/video/atmel_lcdfb.c
index 12cf5f31ee8f..025428e04c33 100644
--- a/drivers/video/atmel_lcdfb.c
+++ b/drivers/video/atmel_lcdfb.c
@@ -422,17 +422,22 @@ static int atmel_lcdfb_check_var(struct fb_var_screeninfo *var,
 			= var->bits_per_pixel;
 		break;
 	case 16:
+		/* Older SOCs use IBGR:555 rather than BGR:565. */
+		if (sinfo->have_intensity_bit)
+			var->green.length = 5;
+		else
+			var->green.length = 6;
+
 		if (sinfo->lcd_wiring_mode == ATMEL_LCDC_WIRING_RGB) {
-			/* RGB:565 mode */
-			var->red.offset = 11;
+			/* RGB:5X5 mode */
+			var->red.offset = var->green.length + 5;
 			var->blue.offset = 0;
 		} else {
-			/* BGR:565 mode */
+			/* BGR:5X5 mode */
 			var->red.offset = 0;
-			var->blue.offset = 11;
+			var->blue.offset = var->green.length + 5;
 		}
 		var->green.offset = 5;
-		var->green.length = 6;
 		var->red.length = var->blue.length = 5;
 		break;
 	case 32:
@@ -679,8 +684,7 @@ static int atmel_lcdfb_setcolreg(unsigned int regno, unsigned int red,
 
 	case FB_VISUAL_PSEUDOCOLOR:
 		if (regno < 256) {
-			if (cpu_is_at91sam9261() || cpu_is_at91sam9263()
-			    || cpu_is_at91sam9rl()) {
+			if (sinfo->have_intensity_bit) {
 				/* old style I+BGR:555 */
 				val  = ((red   >> 11) & 0x001f);
 				val |= ((green >>  6) & 0x03e0);
@@ -870,6 +874,10 @@ static int __init atmel_lcdfb_probe(struct platform_device *pdev)
 	}
 	sinfo->info = info;
 	sinfo->pdev = pdev;
+	if (cpu_is_at91sam9261() || cpu_is_at91sam9263() ||
+							cpu_is_at91sam9rl()) {
+		sinfo->have_intensity_bit = true;
+	}
 
 	strcpy(info->fix.id, sinfo->pdev->name);
 	info->flags = ATMEL_LCDFB_FBINFO_DEFAULT;
diff --git a/include/video/atmel_lcdc.h b/include/video/atmel_lcdc.h
index 28447f1594fa..5f0e234026c0 100644
--- a/include/video/atmel_lcdc.h
+++ b/include/video/atmel_lcdc.h
@@ -62,6 +62,7 @@ struct atmel_lcdfb_info {
 	void (*atmel_lcdfb_power_control)(int on);
 	struct fb_monspecs	*default_monspecs;
 	u32			pseudo_palette[16];
+	bool			have_intensity_bit;
 };
 
 #define ATMEL_LCDC_DMABADDR1	0x00
-- 
cgit v1.2.3


From 67cf9c0a00bd88443adb7d6c3efa8b18d03f97c5 Mon Sep 17 00:00:00 2001
From: Johan Hovold <jhovold@gmail.com>
Date: Wed, 13 Mar 2013 10:56:13 +0100
Subject: ARM: at91: fix LCD-wiring mode

Fix regression introduced by commit 787f9fd23283 ("atmel_lcdfb: support
16bit BGR:565 mode, remove unsupported 15bit modes") which broke 16-bpp
modes for older SOCs which use IBGR:555 (msb is intensity) rather than
BGR:565.

The above commit removes the RGB:555-wiring hack by
removing the no longer used ATMEL_LCDC_WIRING_RGB555 define.

Acked-by: Peter Korsgaard <jacmet@sunsite.dk>
Signed-off-by: Johan Hovold <jhovold@gmail.com>
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
---
 include/video/atmel_lcdc.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include')

diff --git a/include/video/atmel_lcdc.h b/include/video/atmel_lcdc.h
index 5f0e234026c0..8deb22672ada 100644
--- a/include/video/atmel_lcdc.h
+++ b/include/video/atmel_lcdc.h
@@ -30,7 +30,6 @@
  */
 #define ATMEL_LCDC_WIRING_BGR	0
 #define ATMEL_LCDC_WIRING_RGB	1
-#define ATMEL_LCDC_WIRING_RGB555	2
 
 
  /* LCD Controller info data structure, stored in device platform_data */
-- 
cgit v1.2.3


From 5b9e12dbf92b441b37136ea71dac59f05f2673a9 Mon Sep 17 00:00:00 2001
From: "Denis V. Lunev" <den@openvz.org>
Date: Wed, 13 Mar 2013 00:24:15 +0000
Subject: ipv4: fix definition of FIB_TABLE_HASHSZ

a long time ago by the commit

  commit 93456b6d7753def8760b423ac6b986eb9d5a4a95
  Author: Denis V. Lunev <den@openvz.org>
  Date:   Thu Jan 10 03:23:38 2008 -0800

    [IPV4]: Unify access to the routing tables.

the defenition of FIB_HASH_TABLE size has obtained wrong dependency:
it should depend upon CONFIG_IP_MULTIPLE_TABLES (as was in the original
code) but it was depended from CONFIG_IP_ROUTE_MULTIPATH

This patch returns the situation to the original state.

The problem was spotted by Tingwei Liu.

Signed-off-by: Denis V. Lunev <den@openvz.org>
CC: Tingwei Liu <tingw.liu@gmail.com>
CC: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip_fib.h | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 9497be1ad4c0..e49db91593a9 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -152,18 +152,16 @@ struct fib_result_nl {
 };
 
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
-
 #define FIB_RES_NH(res)		((res).fi->fib_nh[(res).nh_sel])
-
-#define FIB_TABLE_HASHSZ 2
-
 #else /* CONFIG_IP_ROUTE_MULTIPATH */
-
 #define FIB_RES_NH(res)		((res).fi->fib_nh[0])
+#endif /* CONFIG_IP_ROUTE_MULTIPATH */
 
+#ifdef CONFIG_IP_MULTIPLE_TABLES
 #define FIB_TABLE_HASHSZ 256
-
-#endif /* CONFIG_IP_ROUTE_MULTIPATH */
+#else
+#define FIB_TABLE_HASHSZ 2
+#endif
 
 extern __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh);
 
-- 
cgit v1.2.3


From ebf47beb660e5580df7bee06d5cf9d37c0f22fac Mon Sep 17 00:00:00 2001
From: Andrew Morton <akpm@linux-foundation.org>
Date: Wed, 13 Mar 2013 14:59:30 -0700
Subject: include/linux/res_counter.h needs errno.h

alpha allmodconfig:

  In file included from mm/memcontrol.c:28:
  include/linux/res_counter.h: In function 'res_counter_set_limit':
  include/linux/res_counter.h:203: error: 'EBUSY' undeclared (first use in this function)
  include/linux/res_counter.h:203: error: (Each undeclared identifier is reported only once
  include/linux/res_counter.h:203: error: for each function it appears in.)

Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Glauber Costa <glommer@parallels.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Frederic Weisbecker <fweisbec@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/res_counter.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
index 5ae8456d9670..c23099413ad6 100644
--- a/include/linux/res_counter.h
+++ b/include/linux/res_counter.h
@@ -14,6 +14,7 @@
  */
 
 #include <linux/cgroup.h>
+#include <linux/errno.h>
 
 /*
  * The core object. the cgroup that wishes to account for some
-- 
cgit v1.2.3


From c8615d3716fe327c2540cf514a34b227dc9b39e8 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 13 Mar 2013 14:59:42 -0700
Subject: idr: deprecate idr_pre_get() and idr_get_new[_above]()

Now that all in-kernel users are converted to ues the new alloc
interface, mark the old interface deprecated.  We should be able to
remove these in a few releases.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/idr.h | 66 ++++++++++++++++++++++++++++++++++++++++-------------
 lib/idr.c           | 41 ++++-----------------------------
 2 files changed, 55 insertions(+), 52 deletions(-)

(limited to 'include')

diff --git a/include/linux/idr.h b/include/linux/idr.h
index 8c1f81f823c8..2640c7e99e51 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -73,8 +73,6 @@ struct idr {
  */
 
 void *idr_find_slowpath(struct idr *idp, int id);
-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_preload(gfp_t gfp_mask);
 int idr_alloc(struct idr *idp, void *ptr, int start, int end, gfp_t gfp_mask);
 int idr_for_each(struct idr *idp,
@@ -119,19 +117,6 @@ static inline void *idr_find(struct idr *idr, int id)
 	return idr_find_slowpath(idr, 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
- *
- * Simple wrapper around idr_get_new_above() w/ @starting_id of zero.
- */
-static inline int idr_get_new(struct idr *idp, void *ptr, int *id)
-{
-	return idr_get_new_above(idp, ptr, 0, id);
-}
-
 /**
  * idr_for_each_entry - iterate over an idr's elements of a given type
  * @idp:     idr handle
@@ -143,7 +128,56 @@ static inline int idr_get_new(struct idr *idp, void *ptr, int *id)
 	     entry != NULL;                                             \
 	     ++id, entry = (typeof(entry))idr_get_next((idp), &(id)))
 
-void __idr_remove_all(struct idr *idp);	/* don't use */
+/*
+ * 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
diff --git a/lib/idr.c b/lib/idr.c
index 4f82a284c6a2..c6fb8295507b 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -184,20 +184,7 @@ static void idr_mark_full(struct idr_layer **pa, int id)
 	}
 }
 
-/**
- * idr_pre_get - reserve resources for idr allocation
- * @idp:	idr handle
- * @gfp_mask:	memory allocation flags
- *
- * This function should be called prior to calling the idr_get_new* functions.
- * It preallocates enough memory to satisfy the worst possible allocation. The
- * caller should pass in GFP_KERNEL if possible.  This of course requires that
- * no spinning locks be held.
- *
- * If the system is REALLY out of memory this function returns %0,
- * otherwise %1.
- */
-int idr_pre_get(struct idr *idp, gfp_t gfp_mask)
+int __idr_pre_get(struct idr *idp, gfp_t gfp_mask)
 {
 	while (idp->id_free_cnt < MAX_IDR_FREE) {
 		struct idr_layer *new;
@@ -208,7 +195,7 @@ int idr_pre_get(struct idr *idp, gfp_t gfp_mask)
 	}
 	return 1;
 }
-EXPORT_SYMBOL(idr_pre_get);
+EXPORT_SYMBOL(__idr_pre_get);
 
 /**
  * sub_alloc - try to allocate an id without growing the tree depth
@@ -375,25 +362,7 @@ static void idr_fill_slot(struct idr *idr, void *ptr, int id,
 	idr_mark_full(pa, id);
 }
 
-/**
- * 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
- *
- * This is the allocate id function.  It should be called with any
- * required locks.
- *
- * If allocation from IDR's private freelist fails, idr_get_new_above() will
- * return %-EAGAIN.  The caller should retry the idr_pre_get() call to refill
- * IDR's preallocation and then retry the idr_get_new_above() call.
- *
- * If the idr is full idr_get_new_above() will return %-ENOSPC.
- *
- * @id returns a value in the range @starting_id ... %0x7fffffff
- */
-int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *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;
@@ -406,7 +375,7 @@ int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id)
 	*id = rv;
 	return 0;
 }
-EXPORT_SYMBOL(idr_get_new_above);
+EXPORT_SYMBOL(__idr_get_new_above);
 
 /**
  * idr_preload - preload for idr_alloc()
@@ -907,7 +876,7 @@ static void free_bitmap(struct ida *ida, struct ida_bitmap *bitmap)
 int ida_pre_get(struct ida *ida, gfp_t gfp_mask)
 {
 	/* allocate idr_layers */
-	if (!idr_pre_get(&ida->idr, gfp_mask))
+	if (!__idr_pre_get(&ida->idr, gfp_mask))
 		return 0;
 
 	/* allocate free_bitmap */
-- 
cgit v1.2.3


From 51b154ed5289682364b830858a4a1ca47fcd04e7 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 13 Mar 2013 14:59:45 -0700
Subject: UAPI: fix endianness conditionals in linux/aio_abi.h

In the UAPI header files, __BIG_ENDIAN and __LITTLE_ENDIAN must be
compared against __BYTE_ORDER in preprocessor conditionals where these are
exposed to userspace (that is they're not inside __KERNEL__ conditionals).

However, in the main kernel the norm is to check for
"defined(__XXX_ENDIAN)" rather than comparing against __BYTE_ORDER and
this has incorrectly leaked into the userspace headers.

The definition of PADDED() in linux/aio_abi.h is wrong in this way.  Note
that userspace will likely interpret this and thus the order of fields in
struct iocb incorrectly as the little-endian variant on big-endian
machines - depending on header inclusion order.

[!!!] NOTE [!!!]  This patch may adversely change the userspace API.  It might
be better to fix the ordering of aio_key and aio_reserved1 in struct iocb.

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Benjamin LaHaise <bcrl@kvack.org>
Acked-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/uapi/linux/aio_abi.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
index 86fa7a71336a..bb2554f7fbd1 100644
--- a/include/uapi/linux/aio_abi.h
+++ b/include/uapi/linux/aio_abi.h
@@ -62,9 +62,9 @@ struct io_event {
 	__s64		res2;		/* secondary result */
 };
 
-#if defined(__LITTLE_ENDIAN)
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
 #define PADDED(x,y)	x, y
-#elif defined(__BIG_ENDIAN)
+#elif defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN)
 #define PADDED(x,y)	y, x
 #else
 #error edit for your odd byteorder.
-- 
cgit v1.2.3


From 29ba06b9ed51d49dea6c79c3c16b961d661262bd Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 13 Mar 2013 14:59:46 -0700
Subject: UAPI: fix endianness conditionals in linux/acct.h

In the UAPI header files, __BIG_ENDIAN and __LITTLE_ENDIAN must be
compared against __BYTE_ORDER in preprocessor conditionals where these are
exposed to userspace (that is they're not inside __KERNEL__ conditionals).

However, in the main kernel the norm is to check for
"defined(__XXX_ENDIAN)" rather than comparing against __BYTE_ORDER and
this has incorrectly leaked into the userspace headers.

The definition of ACCT_BYTEORDER in linux/acct.h is wrong in this way.
Note that userspace will likely interpret this incorrectly as the
big-endian variant on little-endian machines - depending on header
inclusion order.

[!!!] NOTE [!!!]  This patch may adversely change the userspace API.  It might
be better to fix the value of ACCT_BYTEORDER.

Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/uapi/linux/acct.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/acct.h b/include/uapi/linux/acct.h
index 11b6ca3e0873..df2f9a0bba6a 100644
--- a/include/uapi/linux/acct.h
+++ b/include/uapi/linux/acct.h
@@ -107,10 +107,12 @@ struct acct_v3
 #define ACORE		0x08	/* ... dumped core */
 #define AXSIG		0x10	/* ... was killed by a signal */
 
-#ifdef __BIG_ENDIAN
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN)
 #define ACCT_BYTEORDER	0x80	/* accounting file is big endian */
-#else
+#elif defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
 #define ACCT_BYTEORDER	0x00	/* accounting file is little endian */
+#else
+#error unspecified endianness
 #endif
 
 #ifndef __KERNEL__
-- 
cgit v1.2.3


From ca044f9a9ed492f0f7e52df999c10ca6f7cfc5c0 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 13 Mar 2013 14:59:47 -0700
Subject: UAPI: fix endianness conditionals in linux/raid/md_p.h

In the UAPI header files, __BIG_ENDIAN and __LITTLE_ENDIAN must be
compared against __BYTE_ORDER in preprocessor conditionals where these are
exposed to userspace (that is they're not inside __KERNEL__ conditionals).

However, in the main kernel the norm is to check for
"defined(__XXX_ENDIAN)" rather than comparing against __BYTE_ORDER and
this has incorrectly leaked into the userspace headers.

The definition of struct mdp_superblock_s in linux/raid/md_p.h is wrong in
this way.  Note that userspace will likely interpret the ordering of the
fields incorrectly as the big-endian variant on a little-endian machines -
depending on header inclusion order.

[!!!] NOTE [!!!]  This patch may adversely change the userspace API.  It might
be better to fix the ordering of events_hi, events_lo, cp_events_hi and
cp_events_lo in struct mdp_superblock_s / typedef mdp_super_t.

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: NeilBrown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/uapi/linux/raid/md_p.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h
index ee753536ab70..fe1a5406d4d9 100644
--- a/include/uapi/linux/raid/md_p.h
+++ b/include/uapi/linux/raid/md_p.h
@@ -145,16 +145,18 @@ typedef struct mdp_superblock_s {
 	__u32 failed_disks;	/*  4 Number of failed disks		      */
 	__u32 spare_disks;	/*  5 Number of spare disks		      */
 	__u32 sb_csum;		/*  6 checksum of the whole superblock        */
-#ifdef __BIG_ENDIAN
+#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN)
 	__u32 events_hi;	/*  7 high-order of superblock update count   */
 	__u32 events_lo;	/*  8 low-order of superblock update count    */
 	__u32 cp_events_hi;	/*  9 high-order of checkpoint update count   */
 	__u32 cp_events_lo;	/* 10 low-order of checkpoint update count    */
-#else
+#elif defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
 	__u32 events_lo;	/*  7 low-order of superblock update count    */
 	__u32 events_hi;	/*  8 high-order of superblock update count   */
 	__u32 cp_events_lo;	/*  9 low-order of checkpoint update count    */
 	__u32 cp_events_hi;	/* 10 high-order of checkpoint update count   */
+#else
+#error unspecified endianness
 #endif
 	__u32 recovery_cp;	/* 11 recovery checkpoint sector count	      */
 	/* There are only valid for minor_version > 90 */
-- 
cgit v1.2.3


From 5bc7c33ca93a285dcfe7b7fd64970f6314440ad1 Mon Sep 17 00:00:00 2001
From: Brian Norris <computersforpeace@gmail.com>
Date: Wed, 13 Mar 2013 09:51:31 -0700
Subject: mtd: nand: reintroduce NAND_NO_READRDY as NAND_NEED_READRDY

This partially reverts commit 1696e6bc2ae83734e64e206ac99766ea19e9a14e
("mtd: nand: kill NAND_NO_READRDY").

In that patch I overlooked a few things.

The original documentation for NAND_NO_READRDY included "True for all
large page devices, as they do not support autoincrement." I was
conflating "not support autoincrement" with the NAND_NO_AUTOINCR option,
which was in fact doing nothing. So, when I dropped NAND_NO_AUTOINCR, I
concluded that I then could harmlessly drop NAND_NO_READRDY. But of
course the fact the NAND_NO_AUTOINCR was doing nothing didn't mean
NAND_NO_READRDY was doing nothing...

So, NAND_NO_READRDY is re-introduced as NAND_NEED_READRDY and applied
only to those few remaining small-page NAND which needed it in the first
place.

Cc: stable@kernel.org [3.5+]
Reported-by: Alexander Shiyan <shc_work@mail.ru>
Tested-by: Alexander Shiyan <shc_work@mail.ru>
Signed-off-by: Brian Norris <computersforpeace@gmail.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
---
 drivers/mtd/nand/nand_base.c | 16 +++++++++
 drivers/mtd/nand/nand_ids.c  | 80 +++++++++++++++++++++++---------------------
 include/linux/mtd/nand.h     |  7 ++++
 3 files changed, 64 insertions(+), 39 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 43214151b882..42c63927609d 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -1523,6 +1523,14 @@ static int nand_do_read_ops(struct mtd_info *mtd, loff_t from,
 					oobreadlen -= toread;
 				}
 			}
+
+			if (chip->options & NAND_NEED_READRDY) {
+				/* Apply delay or wait for ready/busy pin */
+				if (!chip->dev_ready)
+					udelay(chip->chip_delay);
+				else
+					nand_wait_ready(mtd);
+			}
 		} else {
 			memcpy(buf, chip->buffers->databuf + col, bytes);
 			buf += bytes;
@@ -1787,6 +1795,14 @@ static int nand_do_read_oob(struct mtd_info *mtd, loff_t from,
 		len = min(len, readlen);
 		buf = nand_transfer_oob(chip, buf, ops, len);
 
+		if (chip->options & NAND_NEED_READRDY) {
+			/* Apply delay or wait for ready/busy pin */
+			if (!chip->dev_ready)
+				udelay(chip->chip_delay);
+			else
+				nand_wait_ready(mtd);
+		}
+
 		readlen -= len;
 		if (!readlen)
 			break;
diff --git a/drivers/mtd/nand/nand_ids.c b/drivers/mtd/nand/nand_ids.c
index e3aa2748a6e7..9c612388e5de 100644
--- a/drivers/mtd/nand/nand_ids.c
+++ b/drivers/mtd/nand/nand_ids.c
@@ -22,49 +22,51 @@
 *	512	512 Byte page size
 */
 struct nand_flash_dev nand_flash_ids[] = {
+#define SP_OPTIONS NAND_NEED_READRDY
+#define SP_OPTIONS16 (SP_OPTIONS | NAND_BUSWIDTH_16)
 
 #ifdef CONFIG_MTD_NAND_MUSEUM_IDS
-	{"NAND 1MiB 5V 8-bit",		0x6e, 256, 1, 0x1000, 0},
-	{"NAND 2MiB 5V 8-bit",		0x64, 256, 2, 0x1000, 0},
-	{"NAND 4MiB 5V 8-bit",		0x6b, 512, 4, 0x2000, 0},
-	{"NAND 1MiB 3,3V 8-bit",	0xe8, 256, 1, 0x1000, 0},
-	{"NAND 1MiB 3,3V 8-bit",	0xec, 256, 1, 0x1000, 0},
-	{"NAND 2MiB 3,3V 8-bit",	0xea, 256, 2, 0x1000, 0},
-	{"NAND 4MiB 3,3V 8-bit",	0xd5, 512, 4, 0x2000, 0},
-	{"NAND 4MiB 3,3V 8-bit",	0xe3, 512, 4, 0x2000, 0},
-	{"NAND 4MiB 3,3V 8-bit",	0xe5, 512, 4, 0x2000, 0},
-	{"NAND 8MiB 3,3V 8-bit",	0xd6, 512, 8, 0x2000, 0},
-
-	{"NAND 8MiB 1,8V 8-bit",	0x39, 512, 8, 0x2000, 0},
-	{"NAND 8MiB 3,3V 8-bit",	0xe6, 512, 8, 0x2000, 0},
-	{"NAND 8MiB 1,8V 16-bit",	0x49, 512, 8, 0x2000, NAND_BUSWIDTH_16},
-	{"NAND 8MiB 3,3V 16-bit",	0x59, 512, 8, 0x2000, NAND_BUSWIDTH_16},
+	{"NAND 1MiB 5V 8-bit",		0x6e, 256, 1, 0x1000, SP_OPTIONS},
+	{"NAND 2MiB 5V 8-bit",		0x64, 256, 2, 0x1000, SP_OPTIONS},
+	{"NAND 4MiB 5V 8-bit",		0x6b, 512, 4, 0x2000, SP_OPTIONS},
+	{"NAND 1MiB 3,3V 8-bit",	0xe8, 256, 1, 0x1000, SP_OPTIONS},
+	{"NAND 1MiB 3,3V 8-bit",	0xec, 256, 1, 0x1000, SP_OPTIONS},
+	{"NAND 2MiB 3,3V 8-bit",	0xea, 256, 2, 0x1000, SP_OPTIONS},
+	{"NAND 4MiB 3,3V 8-bit",	0xd5, 512, 4, 0x2000, SP_OPTIONS},
+	{"NAND 4MiB 3,3V 8-bit",	0xe3, 512, 4, 0x2000, SP_OPTIONS},
+	{"NAND 4MiB 3,3V 8-bit",	0xe5, 512, 4, 0x2000, SP_OPTIONS},
+	{"NAND 8MiB 3,3V 8-bit",	0xd6, 512, 8, 0x2000, SP_OPTIONS},
+
+	{"NAND 8MiB 1,8V 8-bit",	0x39, 512, 8, 0x2000, SP_OPTIONS},
+	{"NAND 8MiB 3,3V 8-bit",	0xe6, 512, 8, 0x2000, SP_OPTIONS},
+	{"NAND 8MiB 1,8V 16-bit",	0x49, 512, 8, 0x2000, SP_OPTIONS16},
+	{"NAND 8MiB 3,3V 16-bit",	0x59, 512, 8, 0x2000, SP_OPTIONS16},
 #endif
 
-	{"NAND 16MiB 1,8V 8-bit",	0x33, 512, 16, 0x4000, 0},
-	{"NAND 16MiB 3,3V 8-bit",	0x73, 512, 16, 0x4000, 0},
-	{"NAND 16MiB 1,8V 16-bit",	0x43, 512, 16, 0x4000, NAND_BUSWIDTH_16},
-	{"NAND 16MiB 3,3V 16-bit",	0x53, 512, 16, 0x4000, NAND_BUSWIDTH_16},
-
-	{"NAND 32MiB 1,8V 8-bit",	0x35, 512, 32, 0x4000, 0},
-	{"NAND 32MiB 3,3V 8-bit",	0x75, 512, 32, 0x4000, 0},
-	{"NAND 32MiB 1,8V 16-bit",	0x45, 512, 32, 0x4000, NAND_BUSWIDTH_16},
-	{"NAND 32MiB 3,3V 16-bit",	0x55, 512, 32, 0x4000, NAND_BUSWIDTH_16},
-
-	{"NAND 64MiB 1,8V 8-bit",	0x36, 512, 64, 0x4000, 0},
-	{"NAND 64MiB 3,3V 8-bit",	0x76, 512, 64, 0x4000, 0},
-	{"NAND 64MiB 1,8V 16-bit",	0x46, 512, 64, 0x4000, NAND_BUSWIDTH_16},
-	{"NAND 64MiB 3,3V 16-bit",	0x56, 512, 64, 0x4000, NAND_BUSWIDTH_16},
-
-	{"NAND 128MiB 1,8V 8-bit",	0x78, 512, 128, 0x4000, 0},
-	{"NAND 128MiB 1,8V 8-bit",	0x39, 512, 128, 0x4000, 0},
-	{"NAND 128MiB 3,3V 8-bit",	0x79, 512, 128, 0x4000, 0},
-	{"NAND 128MiB 1,8V 16-bit",	0x72, 512, 128, 0x4000, NAND_BUSWIDTH_16},
-	{"NAND 128MiB 1,8V 16-bit",	0x49, 512, 128, 0x4000, NAND_BUSWIDTH_16},
-	{"NAND 128MiB 3,3V 16-bit",	0x74, 512, 128, 0x4000, NAND_BUSWIDTH_16},
-	{"NAND 128MiB 3,3V 16-bit",	0x59, 512, 128, 0x4000, NAND_BUSWIDTH_16},
-
-	{"NAND 256MiB 3,3V 8-bit",	0x71, 512, 256, 0x4000, 0},
+	{"NAND 16MiB 1,8V 8-bit",	0x33, 512, 16, 0x4000, SP_OPTIONS},
+	{"NAND 16MiB 3,3V 8-bit",	0x73, 512, 16, 0x4000, SP_OPTIONS},
+	{"NAND 16MiB 1,8V 16-bit",	0x43, 512, 16, 0x4000, SP_OPTIONS16},
+	{"NAND 16MiB 3,3V 16-bit",	0x53, 512, 16, 0x4000, SP_OPTIONS16},
+
+	{"NAND 32MiB 1,8V 8-bit",	0x35, 512, 32, 0x4000, SP_OPTIONS},
+	{"NAND 32MiB 3,3V 8-bit",	0x75, 512, 32, 0x4000, SP_OPTIONS},
+	{"NAND 32MiB 1,8V 16-bit",	0x45, 512, 32, 0x4000, SP_OPTIONS16},
+	{"NAND 32MiB 3,3V 16-bit",	0x55, 512, 32, 0x4000, SP_OPTIONS16},
+
+	{"NAND 64MiB 1,8V 8-bit",	0x36, 512, 64, 0x4000, SP_OPTIONS},
+	{"NAND 64MiB 3,3V 8-bit",	0x76, 512, 64, 0x4000, SP_OPTIONS},
+	{"NAND 64MiB 1,8V 16-bit",	0x46, 512, 64, 0x4000, SP_OPTIONS16},
+	{"NAND 64MiB 3,3V 16-bit",	0x56, 512, 64, 0x4000, SP_OPTIONS16},
+
+	{"NAND 128MiB 1,8V 8-bit",	0x78, 512, 128, 0x4000, SP_OPTIONS},
+	{"NAND 128MiB 1,8V 8-bit",	0x39, 512, 128, 0x4000, SP_OPTIONS},
+	{"NAND 128MiB 3,3V 8-bit",	0x79, 512, 128, 0x4000, SP_OPTIONS},
+	{"NAND 128MiB 1,8V 16-bit",	0x72, 512, 128, 0x4000, SP_OPTIONS16},
+	{"NAND 128MiB 1,8V 16-bit",	0x49, 512, 128, 0x4000, SP_OPTIONS16},
+	{"NAND 128MiB 3,3V 16-bit",	0x74, 512, 128, 0x4000, SP_OPTIONS16},
+	{"NAND 128MiB 3,3V 16-bit",	0x59, 512, 128, 0x4000, SP_OPTIONS16},
+
+	{"NAND 256MiB 3,3V 8-bit",	0x71, 512, 256, 0x4000, SP_OPTIONS},
 
 	/*
 	 * These are the new chips with large page size. The pagesize and the
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 7ccb3c59ed60..ef52d9c91459 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -187,6 +187,13 @@ typedef enum {
  * This happens with the Renesas AG-AND chips, possibly others.
  */
 #define BBT_AUTO_REFRESH	0x00000080
+/*
+ * Chip requires ready check on read (for auto-incremented sequential read).
+ * True only for small page devices; large page devices do not support
+ * autoincrement.
+ */
+#define NAND_NEED_READRDY	0x00000100
+
 /* Chip does not allow subpage writes */
 #define NAND_NO_SUBPAGE_WRITE	0x00000200
 
-- 
cgit v1.2.3


From 16fad69cfe4adbbfa813de516757b87bcae36d93 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 14 Mar 2013 05:40:32 +0000
Subject: tcp: fix skb_availroom()

Chrome OS team reported a crash on a Pixel ChromeBook in TCP stack :

https://code.google.com/p/chromium/issues/detail?id=182056

commit a21d45726acac (tcp: avoid order-1 allocations on wifi and tx
path) did a poor choice adding an 'avail_size' field to skb, while
what we really needed was a 'reserved_tailroom' one.

It would have avoided commit 22b4a4f22da (tcp: fix retransmit of
partially acked frames) and this commit.

Crash occurs because skb_split() is not aware of the 'avail_size'
management (and should not be aware)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Mukesh Agrawal <quiche@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 7 +++++--
 net/ipv4/tcp.c         | 2 +-
 net/ipv4/tcp_output.c  | 1 -
 3 files changed, 6 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 821c7f45d2a7..6f2bb860e051 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -500,7 +500,7 @@ struct sk_buff {
 	union {
 		__u32		mark;
 		__u32		dropcount;
-		__u32		avail_size;
+		__u32		reserved_tailroom;
 	};
 
 	sk_buff_data_t		inner_transport_header;
@@ -1447,7 +1447,10 @@ static inline int skb_tailroom(const struct sk_buff *skb)
  */
 static inline int skb_availroom(const struct sk_buff *skb)
 {
-	return skb_is_nonlinear(skb) ? 0 : skb->avail_size - skb->len;
+	if (skb_is_nonlinear(skb))
+		return 0;
+
+	return skb->end - skb->tail - skb->reserved_tailroom;
 }
 
 /**
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 47e854fcae24..e22020790709 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -775,7 +775,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp)
 			 * Make sure that we have exactly size bytes
 			 * available to the caller, no more, no less.
 			 */
-			skb->avail_size = size;
+			skb->reserved_tailroom = skb->end - skb->tail - size;
 			return skb;
 		}
 		__kfree_skb(skb);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e2b4461074da..817fbb396bc8 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1298,7 +1298,6 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
 	eat = min_t(int, len, skb_headlen(skb));
 	if (eat) {
 		__skb_pull(skb, eat);
-		skb->avail_size -= eat;
 		len -= eat;
 		if (!len)
 			return;
-- 
cgit v1.2.3


From cca7af3889bfa343d33d5e657a38d876abd10e58 Mon Sep 17 00:00:00 2001
From: Pavel Emelyanov <xemul@parallels.com>
Date: Thu, 14 Mar 2013 03:29:40 +0000
Subject: skb: Propagate pfmemalloc on skb from head page only

Hi.

I'm trying to send big chunks of memory from application address space via
TCP socket using vmsplice + splice like this

   mem = mmap(128Mb);
   vmsplice(pipe[1], mem); /* splice memory into pipe */
   splice(pipe[0], tcp_socket); /* send it into network */

When I'm lucky and a huge page splices into the pipe and then into the socket
_and_ client and server ends of the TCP connection are on the same host,
communicating via lo, the whole connection gets stuck! The sending queue
becomes full and app stops writing/splicing more into it, but the receiving
queue remains empty, and that's why.

The __skb_fill_page_desc observes a tail page of a huge page and erroneously
propagates its page->pfmemalloc value onto socket (the pfmemalloc on tail pages
contain garbage). Then this skb->pfmemalloc leaks through lo and due to the

    tcp_v4_rcv
    sk_filter
        if (skb->pfmemalloc && !sock_flag(sk, SOCK_MEMALLOC)) /* true */
            return -ENOMEM
        goto release_and_discard;

no packets reach the socket. Even TCP re-transmits are dropped by this, as skb
cloning clones the pfmemalloc flag as well.

That said, here's the proper page->pfmemalloc propagation onto socket: we
must check the huge-page's head page only, other pages' pfmemalloc and mapping
values do not contain what is expected in this place. However, I'm not sure
whether this fix is _complete_, since pfmemalloc propagation via lo also
oesn't look great.

Both, bit propagation from page to skb and this check in sk_filter, were
introduced by c48a11c7 (netvm: propagate page->pfmemalloc to skb), in v3.5 so
Mel and stable@ are in Cc.

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6f2bb860e051..441f5bfdab8e 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1288,11 +1288,13 @@ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i,
 	 * do not lose pfmemalloc information as the pages would not be
 	 * allocated using __GFP_MEMALLOC.
 	 */
-	if (page->pfmemalloc && !page->mapping)
-		skb->pfmemalloc	= true;
 	frag->page.p		  = page;
 	frag->page_offset	  = off;
 	skb_frag_size_set(frag, size);
+
+	page = compound_head(page);
+	if (page->pfmemalloc && !page->mapping)
+		skb->pfmemalloc	= true;
 }
 
 /**
-- 
cgit v1.2.3


From f65846a1800ef8c48d1ae1973c30dae4c356a800 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sat, 9 Mar 2013 07:38:41 -0800
Subject: list: Fix double fetch of pointer in hlist_entry_safe()

The current version of hlist_entry_safe() fetches the pointer twice,
once to test for NULL and the other to compute the offset back to the
enclosing structure.  This is OK for normal lock-based use because in
that case, the pointer cannot change.  However, when the pointer is
protected by RCU (as in "rcu_dereference(p)"), then the pointer can
change at any time.  This use case can result in the following sequence
of events:

1.	CPU 0 invokes hlist_entry_safe(), fetches the RCU-protected
	pointer as sees that it is non-NULL.

2.	CPU 1 invokes hlist_del_rcu(), deleting the entry that CPU 0
	just fetched a pointer to.  Because this is the last entry
	in the list, the pointer fetched by CPU 0 is now NULL.

3.	CPU 0 refetches the pointer, obtains NULL, and then gets a
	NULL-pointer crash.

This commit therefore applies gcc's "({ })" statement expression to
create a temporary variable so that the specified pointer is fetched
only once, avoiding the above sequence of events.  Please note that
it is the caller's responsibility to use rcu_dereference() as needed.
This allows RCU-protected uses to work correctly without imposing
any additional overhead on the non-RCU case.

Many thanks to Eric Dumazet for spotting root cause!

Reported-by: CAI Qian <caiqian@redhat.com>
Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Tested-by: Li Zefan <lizefan@huawei.com>
---
 include/linux/list.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/list.h b/include/linux/list.h
index d991cc147c98..6a1f8df9144b 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -667,7 +667,9 @@ static inline void hlist_move_list(struct hlist_head *old,
 	     pos = n)
 
 #define hlist_entry_safe(ptr, type, member) \
-	(ptr) ? hlist_entry(ptr, type, member) : NULL
+	({ typeof(ptr) ____ptr = (ptr); \
+	   ____ptr ? hlist_entry(____ptr, type, member) : NULL; \
+	})
 
 /**
  * hlist_for_each_entry	- iterate over list of given type
-- 
cgit v1.2.3


From aaa0c23cb90141309f5076ba5e3bfbd39544b985 Mon Sep 17 00:00:00 2001
From: Zhouyi Zhou <zhouzhouyi@gmail.com>
Date: Thu, 14 Mar 2013 17:21:50 +0000
Subject: Fix dst_neigh_lookup/dst_neigh_lookup_skb return value handling bug

When neighbour table is full, dst_neigh_lookup/dst_neigh_lookup_skb will return
-ENOBUFS which is absolutely non zero, while all the code in kernel which use
above functions assume failure only on zero return which will cause panic. (for
example: : https://bugzilla.kernel.org/show_bug.cgi?id=54731).

This patch corrects above error with smallest changes to kernel source code and
also correct two return value check missing bugs in drivers/infiniband/hw/cxgb4/cm.c

Tested on my x86_64 SMP machine

Reported-by: Zhouyi Zhou <zhouzhouyi@gmail.com>
Tested-by: Zhouyi Zhou <zhouzhouyi@gmail.com>
Signed-off-by: Zhouyi Zhou <zhouzhouyi@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/cxgb4/cm.c | 12 ++++++++++++
 include/net/dst.h                |  6 ++++--
 2 files changed, 16 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 565bfb161c1a..a3fde52840ca 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -1575,6 +1575,12 @@ static int c4iw_reconnect(struct c4iw_ep *ep)
 
 	neigh = dst_neigh_lookup(ep->dst,
 			&ep->com.cm_id->remote_addr.sin_addr.s_addr);
+	if (!neigh) {
+		pr_err("%s - cannot alloc neigh.\n", __func__);
+		err = -ENOMEM;
+		goto fail4;
+	}
+
 	/* get a l2t entry */
 	if (neigh->dev->flags & IFF_LOOPBACK) {
 		PDBG("%s LOOPBACK\n", __func__);
@@ -3053,6 +3059,12 @@ static int rx_pkt(struct c4iw_dev *dev, struct sk_buff *skb)
 	dst = &rt->dst;
 	neigh = dst_neigh_lookup_skb(dst, skb);
 
+	if (!neigh) {
+		pr_err("%s - failed to allocate neigh!\n",
+		       __func__);
+		goto free_dst;
+	}
+
 	if (neigh->dev->flags & IFF_LOOPBACK) {
 		pdev = ip_dev_find(&init_net, iph->daddr);
 		e = cxgb4_l2t_get(dev->rdev.lldi.l2t, neigh,
diff --git a/include/net/dst.h b/include/net/dst.h
index 853cda11e518..1f8fd109e225 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -413,13 +413,15 @@ static inline int dst_neigh_output(struct dst_entry *dst, struct neighbour *n,
 
 static inline struct neighbour *dst_neigh_lookup(const struct dst_entry *dst, const void *daddr)
 {
-	return dst->ops->neigh_lookup(dst, NULL, daddr);
+	struct neighbour *n = dst->ops->neigh_lookup(dst, NULL, daddr);
+	return IS_ERR(n) ? NULL : n;
 }
 
 static inline struct neighbour *dst_neigh_lookup_skb(const struct dst_entry *dst,
 						     struct sk_buff *skb)
 {
-	return dst->ops->neigh_lookup(dst, skb, NULL);
+	struct neighbour *n =  dst->ops->neigh_lookup(dst, skb, NULL);
+	return IS_ERR(n) ? NULL : n;
 }
 
 static inline void dst_link_failure(struct sk_buff *skb)
-- 
cgit v1.2.3


From 1d9d8639c063caf6efc2447f5f26aa637f844ff6 Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Fri, 15 Mar 2013 14:26:07 +0100
Subject: perf,x86: fix kernel crash with PEBS/BTS after suspend/resume

This patch fixes a kernel crash when using precise sampling (PEBS)
after a suspend/resume. Turns out the CPU notifier code is not invoked
on CPU0 (BP). Therefore, the DS_AREA (used by PEBS) is not restored properly
by the kernel and keeps it power-on/resume value of 0 causing any PEBS
measurement to crash when running on CPU0.

The workaround is to add a hook in the actual resume code to restore
the DS Area MSR value. It is invoked for all CPUS. So for all but CPU0,
the DS_AREA will be restored twice but this is harmless.

Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/kernel/cpu/perf_event_intel_ds.c | 8 ++++++++
 arch/x86/power/cpu.c                      | 2 ++
 include/linux/perf_event.h                | 2 ++
 3 files changed, 12 insertions(+)

(limited to 'include')

diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 826054a4f2ee..0e9bdd3cb01e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -729,3 +729,11 @@ void intel_ds_init(void)
 		}
 	}
 }
+
+void perf_restore_debug_store(void)
+{
+	if (!x86_pmu.bts && !x86_pmu.pebs)
+		return;
+
+	init_debug_store_on_cpu(smp_processor_id());
+}
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 120cee1c3f8d..3c68768d7a75 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -11,6 +11,7 @@
 #include <linux/suspend.h>
 #include <linux/export.h>
 #include <linux/smp.h>
+#include <linux/perf_event.h>
 
 #include <asm/pgtable.h>
 #include <asm/proto.h>
@@ -228,6 +229,7 @@ static void __restore_processor_state(struct saved_context *ctxt)
 	do_fpu_end();
 	x86_platform.restore_sched_clock_state();
 	mtrr_bp_restore();
+	perf_restore_debug_store();
 }
 
 /* Needed by apm.c */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e47ee462c2f2..71caed8626be 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -758,6 +758,7 @@ extern void perf_event_enable(struct perf_event *event);
 extern void perf_event_disable(struct perf_event *event);
 extern int __perf_event_disable(void *info);
 extern void perf_event_task_tick(void);
+extern void perf_restore_debug_store(void);
 #else
 static inline void
 perf_event_task_sched_in(struct task_struct *prev,
@@ -797,6 +798,7 @@ static inline void perf_event_enable(struct perf_event *event)		{ }
 static inline void perf_event_disable(struct perf_event *event)		{ }
 static inline int __perf_event_disable(void *info)			{ return -1; }
 static inline void perf_event_task_tick(void)				{ }
+static inline void perf_restore_debug_store(void)			{ }
 #endif
 
 #define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x))
-- 
cgit v1.2.3


From b75bbaa038ffc426e88ea3df6c4ae11834fc3e4f Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 8 Mar 2013 13:36:54 -0500
Subject: drm/radeon: add Richland pci ids

Reviewed-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 include/drm/drm_pciids.h | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index a386b0b654cc..918e8fe2f5e9 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -581,7 +581,11 @@
 	{0x1002, 0x9908, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9909, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x990A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
-	{0x1002, 0x990F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x990B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x990C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x990D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x990E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x990F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9910, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9913, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9917, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
@@ -592,6 +596,13 @@
 	{0x1002, 0x9992, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9993, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9994, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9995, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9996, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9997, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9998, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9999, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x999A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x999B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x99A0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x99A2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x99A4, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
-- 
cgit v1.2.3


From 1eef1282549d7accdd33ee36d409b039b1f911fb Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab@redhat.com>
Date: Mon, 11 Mar 2013 09:07:46 -0300
Subject: amd64_edac: Correct DIMM sizes

We were filling the csrow size with a wrong value. 16a528ee3975 ("EDAC:
Fix csrow size reported in sysfs") tried to address the issue. It fixed
the report with the old API but not with the new one. Correct it for the
new API too.

Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
[ make it a per-csrow accounting regardless of ->channel_count ]
Signed-off-by: Borislav Petkov <bp@suse.de>
---
 drivers/edac/amd64_edac.c    | 14 +++++++++-----
 drivers/edac/edac_mc_sysfs.c | 13 +++----------
 include/linux/edac.h         |  1 -
 3 files changed, 12 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 910b0116c128..532de775a184 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -2048,12 +2048,18 @@ static int init_csrows(struct mem_ctl_info *mci)
 		edac_dbg(1, "MC node: %d, csrow: %d\n",
 			    pvt->mc_node_id, i);
 
-		if (row_dct0)
+		if (row_dct0) {
 			nr_pages = amd64_csrow_nr_pages(pvt, 0, i);
+			csrow->channels[0]->dimm->nr_pages = nr_pages;
+		}
 
 		/* K8 has only one DCT */
-		if (boot_cpu_data.x86 != 0xf && row_dct1)
-			nr_pages += amd64_csrow_nr_pages(pvt, 1, i);
+		if (boot_cpu_data.x86 != 0xf && row_dct1) {
+			int row_dct1_pages = amd64_csrow_nr_pages(pvt, 1, i);
+
+			csrow->channels[1]->dimm->nr_pages = row_dct1_pages;
+			nr_pages += row_dct1_pages;
+		}
 
 		mtype = amd64_determine_memory_type(pvt, i);
 
@@ -2072,9 +2078,7 @@ static int init_csrows(struct mem_ctl_info *mci)
 			dimm = csrow->channels[j]->dimm;
 			dimm->mtype = mtype;
 			dimm->edac_mode = edac_mode;
-			dimm->nr_pages = nr_pages;
 		}
-		csrow->nr_pages = nr_pages;
 	}
 
 	return empty;
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index 0cbf670efa23..4c50a4760db7 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -180,9 +180,6 @@ static ssize_t csrow_size_show(struct device *dev,
 	int i;
 	u32 nr_pages = 0;
 
-	if (csrow->mci->csbased)
-		return sprintf(data, "%u\n", PAGES_TO_MiB(csrow->nr_pages));
-
 	for (i = 0; i < csrow->nr_channels; i++)
 		nr_pages += csrow->channels[i]->dimm->nr_pages;
 	return sprintf(data, "%u\n", PAGES_TO_MiB(nr_pages));
@@ -778,14 +775,10 @@ static ssize_t mci_size_mb_show(struct device *dev,
 	for (csrow_idx = 0; csrow_idx < mci->nr_csrows; csrow_idx++) {
 		struct csrow_info *csrow = mci->csrows[csrow_idx];
 
-		if (csrow->mci->csbased) {
-			total_pages += csrow->nr_pages;
-		} else {
-			for (j = 0; j < csrow->nr_channels; j++) {
-				struct dimm_info *dimm = csrow->channels[j]->dimm;
+		for (j = 0; j < csrow->nr_channels; j++) {
+			struct dimm_info *dimm = csrow->channels[j]->dimm;
 
-				total_pages += dimm->nr_pages;
-			}
+			total_pages += dimm->nr_pages;
 		}
 	}
 
diff --git a/include/linux/edac.h b/include/linux/edac.h
index 4fd4999ccb5b..ab1ea98e767c 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -561,7 +561,6 @@ struct csrow_info {
 
 	u32 ue_count;		/* Uncorrectable Errors for this csrow */
 	u32 ce_count;		/* Correctable Errors for this csrow */
-	u32 nr_pages;		/* combined pages count of all channels */
 
 	struct mem_ctl_info *mci;	/* the parent */
 
-- 
cgit v1.2.3


From 9713faecff3d071de1208b081d4943b002e9cb1c Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab@redhat.com>
Date: Mon, 11 Mar 2013 09:28:48 -0300
Subject: EDAC: Merge mci.mem_is_per_rank with mci.csbased

Both mci.mem_is_per_rank and mci.csbased denote the same thing: the
memory controller is csrows based. Merge both fields into one.

There's no need for the driver to actually fill it, as the core detects
it by checking if one of the layers has the csrows type as part of the
memory hierarchy:

	if (layers[i].type == EDAC_MC_LAYER_CHIP_SELECT)
			per_rank = true;

Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
---
 drivers/edac/amd64_edac.c    | 1 -
 drivers/edac/edac_mc.c       | 6 +++---
 drivers/edac/edac_mc_sysfs.c | 2 +-
 include/linux/edac.h         | 6 ++----
 4 files changed, 6 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 532de775a184..e1d13c463c90 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -2423,7 +2423,6 @@ static int amd64_init_one_instance(struct pci_dev *F2)
 
 	mci->pvt_info = pvt;
 	mci->pdev = &pvt->F2->dev;
-	mci->csbased = 1;
 
 	setup_mci_misc_attrs(mci, fam_type);
 
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index cdb81aa73ab7..27e86d938262 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -86,7 +86,7 @@ static void edac_mc_dump_dimm(struct dimm_info *dimm, int number)
 	edac_dimm_info_location(dimm, location, sizeof(location));
 
 	edac_dbg(4, "%s%i: %smapped as virtual row %d, chan %d\n",
-		 dimm->mci->mem_is_per_rank ? "rank" : "dimm",
+		 dimm->mci->csbased ? "rank" : "dimm",
 		 number, location, dimm->csrow, dimm->cschannel);
 	edac_dbg(4, "  dimm = %p\n", dimm);
 	edac_dbg(4, "  dimm->label = '%s'\n", dimm->label);
@@ -341,7 +341,7 @@ struct mem_ctl_info *edac_mc_alloc(unsigned mc_num,
 	memcpy(mci->layers, layers, sizeof(*layer) * n_layers);
 	mci->nr_csrows = tot_csrows;
 	mci->num_cschannel = tot_channels;
-	mci->mem_is_per_rank = per_rank;
+	mci->csbased = per_rank;
 
 	/*
 	 * Alocate and fill the csrow/channels structs
@@ -1235,7 +1235,7 @@ void edac_mc_handle_error(const enum hw_event_mc_err_type type,
 			 * incrementing the compat API counters
 			 */
 			edac_dbg(4, "%s csrows map: (%d,%d)\n",
-				 mci->mem_is_per_rank ? "rank" : "dimm",
+				 mci->csbased ? "rank" : "dimm",
 				 dimm->csrow, dimm->cschannel);
 			if (row == -1)
 				row = dimm->csrow;
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index 4c50a4760db7..5899a76eec3b 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -609,7 +609,7 @@ static int edac_create_dimm_object(struct mem_ctl_info *mci,
 	device_initialize(&dimm->dev);
 
 	dimm->dev.parent = &mci->dev;
-	if (mci->mem_is_per_rank)
+	if (mci->csbased)
 		dev_set_name(&dimm->dev, "rank%d", index);
 	else
 		dev_set_name(&dimm->dev, "dimm%d", index);
diff --git a/include/linux/edac.h b/include/linux/edac.h
index ab1ea98e767c..0b763276f619 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -675,11 +675,11 @@ struct mem_ctl_info {
 	 * sees memory sticks ("dimms"), and the ones that sees memory ranks.
 	 * All old memory controllers enumerate memories per rank, but most
 	 * of the recent drivers enumerate memories per DIMM, instead.
-	 * When the memory controller is per rank, mem_is_per_rank is true.
+	 * When the memory controller is per rank, csbased is true.
 	 */
 	unsigned n_layers;
 	struct edac_mc_layer *layers;
-	bool mem_is_per_rank;
+	bool csbased;
 
 	/*
 	 * DIMM info. Will eventually remove the entire csrows_info some day
@@ -740,8 +740,6 @@ struct mem_ctl_info {
 	u32 fake_inject_ue;
 	u16 fake_inject_count;
 #endif
-	__u8 csbased : 1,	/* csrow-based memory controller */
-	     __resv  : 7;
 };
 
 #endif
-- 
cgit v1.2.3


From 1e8bbe6cd02fc300c88bd48244ce61ad9c7d1776 Mon Sep 17 00:00:00 2001
From: Bjørn Mork <bjorn@mork.no>
Date: Thu, 14 Mar 2013 01:05:13 +0000
Subject: net: cdc_ncm, cdc_mbim: allow user to prefer NCM for backwards
 compatibility
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit bd329e1 ("net: cdc_ncm: do not bind to NCM compatible MBIM devices")
introduced a new policy, preferring MBIM for dual NCM/MBIM functions if
the cdc_mbim driver was enabled.  This caused a regression for users
wanting to use NCM.

Devices implementing NCM backwards compatibility according to section
3.2 of the MBIM v1.0 specification allow either NCM or MBIM on a single
USB function, using different altsettings.  The cdc_ncm and cdc_mbim
drivers will both probe such functions, and must agree on a common
policy for selecting either MBIM or NCM.  Until now, this policy has
been set at build time based on CONFIG_USB_NET_CDC_MBIM.

Use a module parameter to set the system policy at runtime, allowing the
user to prefer NCM on systems with the cdc_mbim driver.

Cc: Greg Suarez <gsuarez@smithmicro.com>
Cc: Alexey Orishko <alexey.orishko@stericsson.com>
Reported-by: Geir Haatveit <nospam@haatveit.nu>
Reported-by: Tommi Kyntola <kynde@ts.ray.fi>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=54791
Signed-off-by: Bjørn Mork <bjorn@mork.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc_mbim.c  | 11 +---------
 drivers/net/usb/cdc_ncm.c   | 49 +++++++++++++++++++++++++++++----------------
 include/linux/usb/cdc_ncm.h |  1 +
 3 files changed, 34 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index 248d2dc765a5..16c842997291 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -68,18 +68,9 @@ static int cdc_mbim_bind(struct usbnet *dev, struct usb_interface *intf)
 	struct cdc_ncm_ctx *ctx;
 	struct usb_driver *subdriver = ERR_PTR(-ENODEV);
 	int ret = -ENODEV;
-	u8 data_altsetting = CDC_NCM_DATA_ALTSETTING_NCM;
+	u8 data_altsetting = cdc_ncm_select_altsetting(dev, intf);
 	struct cdc_mbim_state *info = (void *)&dev->data;
 
-	/* see if interface supports MBIM alternate setting */
-	if (intf->num_altsetting == 2) {
-		if (!cdc_ncm_comm_intf_is_mbim(intf->cur_altsetting))
-			usb_set_interface(dev->udev,
-					  intf->cur_altsetting->desc.bInterfaceNumber,
-					  CDC_NCM_COMM_ALTSETTING_MBIM);
-		data_altsetting = CDC_NCM_DATA_ALTSETTING_MBIM;
-	}
-
 	/* Probably NCM, defer for cdc_ncm_bind */
 	if (!cdc_ncm_comm_intf_is_mbim(intf->cur_altsetting))
 		goto err;
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 61b74a2b89ac..4709fa3497cf 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -55,6 +55,14 @@
 
 #define	DRIVER_VERSION				"14-Mar-2012"
 
+#if IS_ENABLED(CONFIG_USB_NET_CDC_MBIM)
+static bool prefer_mbim = true;
+#else
+static bool prefer_mbim;
+#endif
+module_param(prefer_mbim, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(prefer_mbim, "Prefer MBIM setting on dual NCM/MBIM functions");
+
 static void cdc_ncm_txpath_bh(unsigned long param);
 static void cdc_ncm_tx_timeout_start(struct cdc_ncm_ctx *ctx);
 static enum hrtimer_restart cdc_ncm_tx_timer_cb(struct hrtimer *hr_timer);
@@ -550,9 +558,12 @@ void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf)
 }
 EXPORT_SYMBOL_GPL(cdc_ncm_unbind);
 
-static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf)
+/* Select the MBIM altsetting iff it is preferred and available,
+ * returning the number of the corresponding data interface altsetting
+ */
+u8 cdc_ncm_select_altsetting(struct usbnet *dev, struct usb_interface *intf)
 {
-	int ret;
+	struct usb_host_interface *alt;
 
 	/* The MBIM spec defines a NCM compatible default altsetting,
 	 * which we may have matched:
@@ -568,23 +579,27 @@ static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf)
 	 *   endpoint descriptors, shall be constructed according to
 	 *   the rules given in section 6 (USB Device Model) of this
 	 *   specification."
-	 *
-	 * Do not bind to such interfaces, allowing cdc_mbim to handle
-	 * them
 	 */
-#if IS_ENABLED(CONFIG_USB_NET_CDC_MBIM)
-	if ((intf->num_altsetting == 2) &&
-	    !usb_set_interface(dev->udev,
-			       intf->cur_altsetting->desc.bInterfaceNumber,
-			       CDC_NCM_COMM_ALTSETTING_MBIM)) {
-		if (cdc_ncm_comm_intf_is_mbim(intf->cur_altsetting))
-			return -ENODEV;
-		else
-			usb_set_interface(dev->udev,
-					  intf->cur_altsetting->desc.bInterfaceNumber,
-					  CDC_NCM_COMM_ALTSETTING_NCM);
+	if (prefer_mbim && intf->num_altsetting == 2) {
+		alt = usb_altnum_to_altsetting(intf, CDC_NCM_COMM_ALTSETTING_MBIM);
+		if (alt && cdc_ncm_comm_intf_is_mbim(alt) &&
+		    !usb_set_interface(dev->udev,
+				       intf->cur_altsetting->desc.bInterfaceNumber,
+				       CDC_NCM_COMM_ALTSETTING_MBIM))
+			return CDC_NCM_DATA_ALTSETTING_MBIM;
 	}
-#endif
+	return CDC_NCM_DATA_ALTSETTING_NCM;
+}
+EXPORT_SYMBOL_GPL(cdc_ncm_select_altsetting);
+
+static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf)
+{
+	int ret;
+
+	/* MBIM backwards compatible function? */
+	cdc_ncm_select_altsetting(dev, intf);
+	if (cdc_ncm_comm_intf_is_mbim(intf->cur_altsetting))
+		return -ENODEV;
 
 	/* NCM data altsetting is always 1 */
 	ret = cdc_ncm_bind_common(dev, intf, 1);
diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index 3b8f9d4fc3fe..cc25b70af33c 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -127,6 +127,7 @@ struct cdc_ncm_ctx {
 	u16 connected;
 };
 
+extern u8 cdc_ncm_select_altsetting(struct usbnet *dev, struct usb_interface *intf);
 extern int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting);
 extern void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf);
 extern struct sk_buff *cdc_ncm_fill_tx_frame(struct cdc_ncm_ctx *ctx, struct sk_buff *skb, __le32 sign);
-- 
cgit v1.2.3


From 6c4d3bc99b3341067775efd4d9d13cc8e655fd7c Mon Sep 17 00:00:00 2001
From: David Rientjes <rientjes@google.com>
Date: Sun, 17 Mar 2013 15:49:10 -0700
Subject: perf,x86: fix link failure for non-Intel configs

Commit 1d9d8639c063 ("perf,x86: fix kernel crash with PEBS/BTS after
suspend/resume") introduces a link failure since
perf_restore_debug_store() is only defined for CONFIG_CPU_SUP_INTEL:

	arch/x86/power/built-in.o: In function `restore_processor_state':
	(.text+0x45c): undefined reference to `perf_restore_debug_store'

Fix it by defining the dummy function appropriately.

Signed-off-by: David Rientjes <rientjes@google.com>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/perf_event.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 71caed8626be..1d795df6f4cf 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -758,7 +758,6 @@ extern void perf_event_enable(struct perf_event *event);
 extern void perf_event_disable(struct perf_event *event);
 extern int __perf_event_disable(void *info);
 extern void perf_event_task_tick(void);
-extern void perf_restore_debug_store(void);
 #else
 static inline void
 perf_event_task_sched_in(struct task_struct *prev,
@@ -798,6 +797,11 @@ static inline void perf_event_enable(struct perf_event *event)		{ }
 static inline void perf_event_disable(struct perf_event *event)		{ }
 static inline int __perf_event_disable(void *info)			{ return -1; }
 static inline void perf_event_task_tick(void)				{ }
+#endif
+
+#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
+extern void perf_restore_debug_store(void);
+#else
 static inline void perf_restore_debug_store(void)			{ }
 #endif
 
-- 
cgit v1.2.3


From 65c10553552b487a71bf5e4676743435046fae6f Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Date: Thu, 14 Mar 2013 20:52:30 +0900
Subject: kprobes: Make hash_64() as always inlined

Because hash_64() is called from the get_kprobe() inside
int3 handler, kernel causes int3 recursion and crashes if
kprobes user puts a probe on it.

Usually hash_64() is inlined into caller function, but in
some cases, it has instances by gcc's interprocedural
constant propagation.

This patch uses __always_inline instead of inline to
prevent gcc from doing such things.

Reported-by: Timo Juhani Lindfors <timo.lindfors@iki.fi>
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Acked-by: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Nadia Yvette Chambers <nyc@holomorphy.com>
Cc: yrl.pp-manager.tt@hitachi.com
Cc: David S. Miller <davem@davemloft.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20130314115230.19690.39387.stgit@mhiramat-M0-7522
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/hash.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/hash.h b/include/linux/hash.h
index 61c97ae22e01..f09a0ae4d858 100644
--- a/include/linux/hash.h
+++ b/include/linux/hash.h
@@ -15,6 +15,7 @@
  */
 
 #include <asm/types.h>
+#include <linux/compiler.h>
 
 /* 2^31 + 2^29 - 2^25 + 2^22 - 2^19 - 2^16 + 1 */
 #define GOLDEN_RATIO_PRIME_32 0x9e370001UL
@@ -31,7 +32,7 @@
 #error Wordsize not 32 or 64
 #endif
 
-static inline u64 hash_64(u64 val, unsigned int bits)
+static __always_inline u64 hash_64(u64 val, unsigned int bits)
 {
 	u64 hash = val;
 
-- 
cgit v1.2.3


From f445f11eb2cc265dd47da5b2e864df46cd6e5a82 Mon Sep 17 00:00:00 2001
From: Kevin Hilman <khilman@linaro.org>
Date: Thu, 14 Mar 2013 17:13:46 -0700
Subject: KVM: allow host header to be included even for !CONFIG_KVM

The new context tracking subsystem unconditionally includes kvm_host.h
headers for the guest enter/exit macros.  This causes a compile
failure when KVM is not enabled.

Fix by adding an IS_ENABLED(CONFIG_KVM) check to kvm_host so it can
be included/compiled even when KVM is not enabled.

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Kevin Hilman <khilman@linaro.org>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 include/linux/kvm_host.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index cad77fe09d77..a9428635c9fd 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1,6 +1,8 @@
 #ifndef __KVM_HOST_H
 #define __KVM_HOST_H
 
+#if IS_ENABLED(CONFIG_KVM)
+
 /*
  * This work is licensed under the terms of the GNU GPL, version 2.  See
  * the COPYING file in the top-level directory.
@@ -1055,5 +1057,8 @@ static inline bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
 }
 
 #endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */
+#else
+static inline void __guest_enter(void) { return; }
+static inline void __guest_exit(void) { return; }
+#endif /* IS_ENABLED(CONFIG_KVM) */
 #endif
-
-- 
cgit v1.2.3


From 6a15075eced2d780fa6c5d83682410f47f2e800b Mon Sep 17 00:00:00 2001
From: Marek Vasut <marex@denx.de>
Date: Mon, 18 Mar 2013 19:24:02 +0100
Subject: ARM: video: mxs: Fix mxsfb misconfiguring VDCTRL0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The issue fixed by this patch manifests only then using X11
with mxsfb driver. The X11 will display either shifted image
or otherwise distorted image on the LCD.

The problem is that the X11 tries to reconfigure the framebuffer
and along the way calls fb_ops.fb_set_par() with X11's desired
configuration values. The field of particular interest is
fb_info->var.sync which contains non-standard values if
configured by kernel. These are either FB_SYNC_DATA_ENABLE_HIGH_ACT,
FB_SYNC_DOTCLK_FAILING_ACT or both, depending on the platform
configuration. Both of these values are defined in the
include/linux/mxsfb.h file.

The driver interprets these values and configures the LCD controller
accordingly. Yet X11 only has access to the standard values for this
field defined in include/uapi/linux/fb.h and thus, unlike kernel,
omits these special values. This results in distorted image on the
LCD.

This patch moves these non-standard values into new field of the
mxsfb_platform_data structure so the driver can in turn check this
field instead of the video mode field for these specific portions.

Moreover, this patch prefixes these values with MXSFB_SYNC_ prefix
instead of FB_SYNC_ prefix to prevent confusion of subsequent users.

Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Fabio Estevam <fabio.estevam@freescale.com>
Cc: Linux ARM <linux-arm-kernel@lists.infradead.org>
Cc: Linux FBDEV <linux-fbdev@vger.kernel.org>
Cc: Lothar Waßmann <LW@karo-electronics.de>
Cc: Sascha Hauer <kernel@pengutronix.de>
Tested-by: Fabio Estevam <fabio.estevam@freescale.com>
Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
---
 arch/arm/mach-mxs/mach-mxs.c | 24 ++++++++++++------------
 drivers/video/mxsfb.c        |  7 +++++--
 include/linux/mxsfb.h        |  7 +++++--
 3 files changed, 22 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-mxs/mach-mxs.c b/arch/arm/mach-mxs/mach-mxs.c
index 3218f1f2c0e0..e7b781d3788f 100644
--- a/arch/arm/mach-mxs/mach-mxs.c
+++ b/arch/arm/mach-mxs/mach-mxs.c
@@ -41,8 +41,6 @@ static struct fb_videomode mx23evk_video_modes[] = {
 		.lower_margin	= 4,
 		.hsync_len	= 1,
 		.vsync_len	= 1,
-		.sync		= FB_SYNC_DATA_ENABLE_HIGH_ACT |
-				  FB_SYNC_DOTCLK_FAILING_ACT,
 	},
 };
 
@@ -59,8 +57,6 @@ static struct fb_videomode mx28evk_video_modes[] = {
 		.lower_margin	= 10,
 		.hsync_len	= 10,
 		.vsync_len	= 10,
-		.sync		= FB_SYNC_DATA_ENABLE_HIGH_ACT |
-				  FB_SYNC_DOTCLK_FAILING_ACT,
 	},
 };
 
@@ -77,7 +73,6 @@ static struct fb_videomode m28evk_video_modes[] = {
 		.lower_margin	= 45,
 		.hsync_len	= 1,
 		.vsync_len	= 1,
-		.sync		= FB_SYNC_DATA_ENABLE_HIGH_ACT,
 	},
 };
 
@@ -94,9 +89,7 @@ static struct fb_videomode apx4devkit_video_modes[] = {
 		.lower_margin	= 13,
 		.hsync_len	= 48,
 		.vsync_len	= 3,
-		.sync		= FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT |
-				  FB_SYNC_DATA_ENABLE_HIGH_ACT |
-				  FB_SYNC_DOTCLK_FAILING_ACT,
+		.sync		= FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
 	},
 };
 
@@ -113,9 +106,7 @@ static struct fb_videomode apf28dev_video_modes[] = {
 		.lower_margin = 0x15,
 		.hsync_len = 64,
 		.vsync_len = 4,
-		.sync = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT |
-				FB_SYNC_DATA_ENABLE_HIGH_ACT |
-				FB_SYNC_DOTCLK_FAILING_ACT,
+		.sync = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
 	},
 };
 
@@ -132,7 +123,6 @@ static struct fb_videomode cfa10049_video_modes[] = {
 		.lower_margin	= 2,
 		.hsync_len	= 15,
 		.vsync_len	= 15,
-		.sync		= FB_SYNC_DATA_ENABLE_HIGH_ACT
 	},
 };
 
@@ -259,6 +249,8 @@ static void __init imx23_evk_init(void)
 	mxsfb_pdata.mode_count = ARRAY_SIZE(mx23evk_video_modes);
 	mxsfb_pdata.default_bpp = 32;
 	mxsfb_pdata.ld_intf_width = STMLCDIF_24BIT;
+	mxsfb_pdata.sync = MXSFB_SYNC_DATA_ENABLE_HIGH_ACT |
+				MXSFB_SYNC_DOTCLK_FAILING_ACT;
 }
 
 static inline void enable_clk_enet_out(void)
@@ -278,6 +270,8 @@ static void __init imx28_evk_init(void)
 	mxsfb_pdata.mode_count = ARRAY_SIZE(mx28evk_video_modes);
 	mxsfb_pdata.default_bpp = 32;
 	mxsfb_pdata.ld_intf_width = STMLCDIF_24BIT;
+	mxsfb_pdata.sync = MXSFB_SYNC_DATA_ENABLE_HIGH_ACT |
+				MXSFB_SYNC_DOTCLK_FAILING_ACT;
 
 	mxs_saif_clkmux_select(MXS_DIGCTL_SAIF_CLKMUX_EXTMSTR0);
 }
@@ -297,6 +291,7 @@ static void __init m28evk_init(void)
 	mxsfb_pdata.mode_count = ARRAY_SIZE(m28evk_video_modes);
 	mxsfb_pdata.default_bpp = 16;
 	mxsfb_pdata.ld_intf_width = STMLCDIF_18BIT;
+	mxsfb_pdata.sync = MXSFB_SYNC_DATA_ENABLE_HIGH_ACT;
 }
 
 static void __init sc_sps1_init(void)
@@ -322,6 +317,8 @@ static void __init apx4devkit_init(void)
 	mxsfb_pdata.mode_count = ARRAY_SIZE(apx4devkit_video_modes);
 	mxsfb_pdata.default_bpp = 32;
 	mxsfb_pdata.ld_intf_width = STMLCDIF_24BIT;
+	mxsfb_pdata.sync = MXSFB_SYNC_DATA_ENABLE_HIGH_ACT |
+				MXSFB_SYNC_DOTCLK_FAILING_ACT;
 }
 
 #define ENET0_MDC__GPIO_4_0	MXS_GPIO_NR(4, 0)
@@ -407,6 +404,7 @@ static void __init cfa10049_init(void)
 	mxsfb_pdata.mode_count = ARRAY_SIZE(cfa10049_video_modes);
 	mxsfb_pdata.default_bpp = 32;
 	mxsfb_pdata.ld_intf_width = STMLCDIF_18BIT;
+	mxsfb_pdata.sync = MXSFB_SYNC_DATA_ENABLE_HIGH_ACT;
 }
 
 static void __init cfa10037_init(void)
@@ -423,6 +421,8 @@ static void __init apf28_init(void)
 	mxsfb_pdata.mode_count = ARRAY_SIZE(apf28dev_video_modes);
 	mxsfb_pdata.default_bpp = 16;
 	mxsfb_pdata.ld_intf_width = STMLCDIF_16BIT;
+	mxsfb_pdata.sync = MXSFB_SYNC_DATA_ENABLE_HIGH_ACT |
+				MXSFB_SYNC_DOTCLK_FAILING_ACT;
 }
 
 static void __init mxs_machine_init(void)
diff --git a/drivers/video/mxsfb.c b/drivers/video/mxsfb.c
index 755556ca5b2d..45169cbaba6e 100644
--- a/drivers/video/mxsfb.c
+++ b/drivers/video/mxsfb.c
@@ -169,6 +169,7 @@ struct mxsfb_info {
 	unsigned dotclk_delay;
 	const struct mxsfb_devdata *devdata;
 	int mapped;
+	u32 sync;
 };
 
 #define mxsfb_is_v3(host) (host->devdata->ipversion == 3)
@@ -456,9 +457,9 @@ static int mxsfb_set_par(struct fb_info *fb_info)
 		vdctrl0 |= VDCTRL0_HSYNC_ACT_HIGH;
 	if (fb_info->var.sync & FB_SYNC_VERT_HIGH_ACT)
 		vdctrl0 |= VDCTRL0_VSYNC_ACT_HIGH;
-	if (fb_info->var.sync & FB_SYNC_DATA_ENABLE_HIGH_ACT)
+	if (host->sync & MXSFB_SYNC_DATA_ENABLE_HIGH_ACT)
 		vdctrl0 |= VDCTRL0_ENABLE_ACT_HIGH;
-	if (fb_info->var.sync & FB_SYNC_DOTCLK_FAILING_ACT)
+	if (host->sync & MXSFB_SYNC_DOTCLK_FAILING_ACT)
 		vdctrl0 |= VDCTRL0_DOTCLK_ACT_FAILING;
 
 	writel(vdctrl0, host->base + LCDC_VDCTRL0);
@@ -861,6 +862,8 @@ static int mxsfb_probe(struct platform_device *pdev)
 
 	INIT_LIST_HEAD(&fb_info->modelist);
 
+	host->sync = pdata->sync;
+
 	ret = mxsfb_init_fbinfo(host);
 	if (ret != 0)
 		goto error_init_fb;
diff --git a/include/linux/mxsfb.h b/include/linux/mxsfb.h
index f14943d55315..f80af8674342 100644
--- a/include/linux/mxsfb.h
+++ b/include/linux/mxsfb.h
@@ -24,8 +24,8 @@
 #define STMLCDIF_18BIT 2 /** pixel data bus to the display is of 18 bit width */
 #define STMLCDIF_24BIT 3 /** pixel data bus to the display is of 24 bit width */
 
-#define FB_SYNC_DATA_ENABLE_HIGH_ACT	(1 << 6)
-#define FB_SYNC_DOTCLK_FAILING_ACT	(1 << 7) /* failing/negtive edge sampling */
+#define MXSFB_SYNC_DATA_ENABLE_HIGH_ACT	(1 << 6)
+#define MXSFB_SYNC_DOTCLK_FAILING_ACT	(1 << 7) /* failing/negtive edge sampling */
 
 struct mxsfb_platform_data {
 	struct fb_videomode *mode_list;
@@ -44,6 +44,9 @@ struct mxsfb_platform_data {
 				 * allocated. If specified,fb_size must also be specified.
 				 * fb_phys must be unused by Linux.
 				 */
+	u32 sync;		/* sync mask, contains MXSFB specifics not
+				 * carried in fb_info->var.sync
+				 */
 };
 
 #endif /* __LINUX_MXSFB_H */
-- 
cgit v1.2.3


From 0c12582fbcdea0cbb0dfd224e1c5f9a8428ffa18 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Sat, 9 Mar 2013 23:25:04 +0200
Subject: ipvs: add backup_only flag to avoid loops

Dmitry Akindinov is reporting for a problem where SYNs are looping
between the master and backup server when the backup server is used as
real server in DR mode and has IPVS rules to function as director.

Even when the backup function is enabled we continue to forward
traffic and schedule new connections when the current master is using
the backup server as real server. While this is not a problem for NAT,
for DR and TUN method the backup server can not determine if a request
comes from client or from director.

To avoid such loops add new sysctl flag backup_only. It can be needed
for DR/TUN setups that do not need backup and director function at the
same time. When the backup function is enabled we stop any forwarding
and pass the traffic to the local stack (real server mode). The flag
disables the director function when the backup function is enabled.

For setups that enable backup function for some virtual services and
director function for other virtual services there should be another
more complex solution to support DR/TUN mode, may be to assign
per-virtual service syncid value, so that we can differentiate the
requests.

Reported-by: Dmitry Akindinov <dimak@stalker.com>
Tested-by: German Myzovsky <lawyer@sipnet.ru>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 Documentation/networking/ipvs-sysctl.txt |  7 +++++++
 include/net/ip_vs.h                      | 12 ++++++++++++
 net/netfilter/ipvs/ip_vs_core.c          | 12 ++++++++----
 net/netfilter/ipvs/ip_vs_ctl.c           |  7 +++++++
 4 files changed, 34 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/ipvs-sysctl.txt b/Documentation/networking/ipvs-sysctl.txt
index f2a2488f1bf3..9573d0c48c6e 100644
--- a/Documentation/networking/ipvs-sysctl.txt
+++ b/Documentation/networking/ipvs-sysctl.txt
@@ -15,6 +15,13 @@ amemthresh - INTEGER
         enabled and the variable is automatically set to 2, otherwise
         the strategy is disabled and the variable is  set  to 1.
 
+backup_only - BOOLEAN
+	0 - disabled (default)
+	not 0 - enabled
+
+	If set, disable the director function while the server is
+	in backup mode to avoid packet loops for DR/TUN methods.
+
 conntrack - BOOLEAN
 	0 - disabled (default)
 	not 0 - enabled
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 68c69d54d392..fce8e6b66d55 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -976,6 +976,7 @@ struct netns_ipvs {
 	int			sysctl_sync_retries;
 	int			sysctl_nat_icmp_send;
 	int			sysctl_pmtu_disc;
+	int			sysctl_backup_only;
 
 	/* ip_vs_lblc */
 	int			sysctl_lblc_expiration;
@@ -1067,6 +1068,12 @@ static inline int sysctl_pmtu_disc(struct netns_ipvs *ipvs)
 	return ipvs->sysctl_pmtu_disc;
 }
 
+static inline int sysctl_backup_only(struct netns_ipvs *ipvs)
+{
+	return ipvs->sync_state & IP_VS_STATE_BACKUP &&
+	       ipvs->sysctl_backup_only;
+}
+
 #else
 
 static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
@@ -1114,6 +1121,11 @@ static inline int sysctl_pmtu_disc(struct netns_ipvs *ipvs)
 	return 1;
 }
 
+static inline int sysctl_backup_only(struct netns_ipvs *ipvs)
+{
+	return 0;
+}
+
 #endif
 
 /*
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 47edf5a40a59..18b4bc55fa3d 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1577,7 +1577,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	}
 	/* ipvs enabled in this netns ? */
 	net = skb_net(skb);
-	if (!net_ipvs(net)->enable)
+	ipvs = net_ipvs(net);
+	if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable))
 		return NF_ACCEPT;
 
 	ip_vs_fill_iph_skb(af, skb, &iph);
@@ -1654,7 +1655,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 	}
 
 	IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet");
-	ipvs = net_ipvs(net);
 	/* Check the server status */
 	if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
 		/* the destination server is not available */
@@ -1815,13 +1815,15 @@ ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb,
 {
 	int r;
 	struct net *net;
+	struct netns_ipvs *ipvs;
 
 	if (ip_hdr(skb)->protocol != IPPROTO_ICMP)
 		return NF_ACCEPT;
 
 	/* ipvs enabled in this netns ? */
 	net = skb_net(skb);
-	if (!net_ipvs(net)->enable)
+	ipvs = net_ipvs(net);
+	if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable))
 		return NF_ACCEPT;
 
 	return ip_vs_in_icmp(skb, &r, hooknum);
@@ -1835,6 +1837,7 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb,
 {
 	int r;
 	struct net *net;
+	struct netns_ipvs *ipvs;
 	struct ip_vs_iphdr iphdr;
 
 	ip_vs_fill_iph_skb(AF_INET6, skb, &iphdr);
@@ -1843,7 +1846,8 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb,
 
 	/* ipvs enabled in this netns ? */
 	net = skb_net(skb);
-	if (!net_ipvs(net)->enable)
+	ipvs = net_ipvs(net);
+	if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable))
 		return NF_ACCEPT;
 
 	return ip_vs_in_icmp_v6(skb, &r, hooknum, &iphdr);
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index c68198bf9128..9e2d1cccd1eb 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1808,6 +1808,12 @@ static struct ctl_table vs_vars[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "backup_only",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 #ifdef CONFIG_IP_VS_DEBUG
 	{
 		.procname	= "debug_level",
@@ -3741,6 +3747,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net)
 	tbl[idx++].data = &ipvs->sysctl_nat_icmp_send;
 	ipvs->sysctl_pmtu_disc = 1;
 	tbl[idx++].data = &ipvs->sysctl_pmtu_disc;
+	tbl[idx++].data = &ipvs->sysctl_backup_only;
 
 
 	ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl);
-- 
cgit v1.2.3


From 5a3da1fe9561828d0ca7eca664b16ec2b9bf0055 Mon Sep 17 00:00:00 2001
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Fri, 15 Mar 2013 11:32:30 +0000
Subject: inet: limit length of fragment queue hash table bucket lists

This patch introduces a constant limit of the fragment queue hash
table bucket list lengths. Currently the limit 128 is choosen somewhat
arbitrary and just ensures that we can fill up the fragment cache with
empty packets up to the default ip_frag_high_thresh limits. It should
just protect from list iteration eating considerable amounts of cpu.

If we reach the maximum length in one hash bucket a warning is printed.
This is implemented on the caller side of inet_frag_find to distinguish
between the different users of inet_fragment.c.

I dropped the out of memory warning in the ipv4 fragment lookup path,
because we already get a warning by the slab allocator.

Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Jesper Dangaard Brouer <jbrouer@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_frag.h                 |  9 +++++++++
 net/ipv4/inet_fragment.c                | 20 +++++++++++++++++++-
 net/ipv4/ip_fragment.c                  | 11 ++++-------
 net/ipv6/netfilter/nf_conntrack_reasm.c | 12 ++++++------
 net/ipv6/reassembly.c                   |  8 ++++++--
 5 files changed, 44 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 76c3fe5ecc2e..0a1dcc2fa2f5 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -43,6 +43,13 @@ struct inet_frag_queue {
 
 #define INETFRAGS_HASHSZ		64
 
+/* averaged:
+ * max_depth = default ipfrag_high_thresh / INETFRAGS_HASHSZ /
+ *	       rounded up (SKB_TRUELEN(0) + sizeof(struct ipq or
+ *	       struct frag_queue))
+ */
+#define INETFRAGS_MAXDEPTH		128
+
 struct inet_frags {
 	struct hlist_head	hash[INETFRAGS_HASHSZ];
 	/* This rwlock is a global lock (seperate per IPv4, IPv6 and
@@ -76,6 +83,8 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force);
 struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
 		struct inet_frags *f, void *key, unsigned int hash)
 	__releases(&f->lock);
+void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
+				   const char *prefix);
 
 static inline void inet_frag_put(struct inet_frag_queue *q, struct inet_frags *f)
 {
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 245ae078a07f..f4fd23de9b13 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -21,6 +21,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/slab.h>
 
+#include <net/sock.h>
 #include <net/inet_frag.h>
 
 static void inet_frag_secret_rebuild(unsigned long dummy)
@@ -277,6 +278,7 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
 	__releases(&f->lock)
 {
 	struct inet_frag_queue *q;
+	int depth = 0;
 
 	hlist_for_each_entry(q, &f->hash[hash], list) {
 		if (q->net == nf && f->match(q, key)) {
@@ -284,9 +286,25 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
 			read_unlock(&f->lock);
 			return q;
 		}
+		depth++;
 	}
 	read_unlock(&f->lock);
 
-	return inet_frag_create(nf, f, key);
+	if (depth <= INETFRAGS_MAXDEPTH)
+		return inet_frag_create(nf, f, key);
+	else
+		return ERR_PTR(-ENOBUFS);
 }
 EXPORT_SYMBOL(inet_frag_find);
+
+void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
+				   const char *prefix)
+{
+	static const char msg[] = "inet_frag_find: Fragment hash bucket"
+		" list length grew over limit " __stringify(INETFRAGS_MAXDEPTH)
+		". Dropping fragment.\n";
+
+	if (PTR_ERR(q) == -ENOBUFS)
+		LIMIT_NETDEBUG(KERN_WARNING "%s%s", prefix, msg);
+}
+EXPORT_SYMBOL(inet_frag_maybe_warn_overflow);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index b6d30acb600c..a6445b843ef4 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -292,14 +292,11 @@ static inline struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user)
 	hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);
 
 	q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash);
-	if (q == NULL)
-		goto out_nomem;
-
+	if (IS_ERR_OR_NULL(q)) {
+		inet_frag_maybe_warn_overflow(q, pr_fmt());
+		return NULL;
+	}
 	return container_of(q, struct ipq, q);
-
-out_nomem:
-	LIMIT_NETDEBUG(KERN_ERR pr_fmt("ip_frag_create: no memory left !\n"));
-	return NULL;
 }
 
 /* Is the fragment too far ahead to be part of ipq? */
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 54087e96d7b8..6700069949dd 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -14,6 +14,8 @@
  * 2 of the License, or (at your option) any later version.
  */
 
+#define pr_fmt(fmt) "IPv6-nf: " fmt
+
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/string.h>
@@ -180,13 +182,11 @@ static inline struct frag_queue *fq_find(struct net *net, __be32 id,
 
 	q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash);
 	local_bh_enable();
-	if (q == NULL)
-		goto oom;
-
+	if (IS_ERR_OR_NULL(q)) {
+		inet_frag_maybe_warn_overflow(q, pr_fmt());
+		return NULL;
+	}
 	return container_of(q, struct frag_queue, q);
-
-oom:
-	return NULL;
 }
 
 
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 3c6a77290c6e..196ab9347ad1 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -26,6 +26,9 @@
  *	YOSHIFUJI,H. @USAGI	Always remove fragment header to
  *				calculate ICV correctly.
  */
+
+#define pr_fmt(fmt) "IPv6: " fmt
+
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/string.h>
@@ -185,9 +188,10 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src, const struct in6
 	hash = inet6_hash_frag(id, src, dst, ip6_frags.rnd);
 
 	q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash);
-	if (q == NULL)
+	if (IS_ERR_OR_NULL(q)) {
+		inet_frag_maybe_warn_overflow(q, pr_fmt());
 		return NULL;
-
+	}
 	return container_of(q, struct frag_queue, q);
 }
 
-- 
cgit v1.2.3


From 2a1486981c1317dc4f4aad568f2cc6e49dfb8c82 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 19 Mar 2013 14:00:53 +0000
Subject: Fix breakage in MIPS siginfo handling

MIPS's siginfo handling has been broken since this commit:

	commit 574c4866e33d648520a8bd5bf6f573ea6e554e88
	Author: Al Viro <viro@zeniv.linux.org.uk>
	Date:   Sun Nov 25 22:24:19 2012 -0500
	consolidate kernel-side struct sigaction declarations

for 64-bit BE MIPS CPUs.

The UAPI variant looks like this:

	struct sigaction {
		unsigned int	sa_flags;
		__sighandler_t	sa_handler;
		sigset_t	sa_mask;
	};

but the core kernel's variant looks like this:

	struct sigaction {
	#ifndef __ARCH_HAS_ODD_SIGACTION
		__sighandler_t	sa_handler;
		unsigned long	sa_flags;
	#else
		unsigned long	sa_flags;
		__sighandler_t	sa_handler;
	#endif
	#ifdef __ARCH_HAS_SA_RESTORER
		__sigrestore_t sa_restorer;
	#endif
		sigset_t	sa_mask;
	};

The problem is that sa_flags has been changed from an unsigned int to an
unsigned long.

Fix this by making sa_flags unsigned int if __ARCH_HAS_ODD_SIGACTION is
defined.

Whilst we're at it, rename __ARCH_HAS_ODD_SIGACTION to
__ARCH_HAS_IRIX_SIGACTION.

Signed-off-by: David Howells <dhowells@redhat.com>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Cc: stable@vger.kernel.org
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
---
 arch/mips/include/asm/signal.h | 2 +-
 include/linux/compat.h         | 4 ++--
 include/linux/signal.h         | 4 ++--
 3 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/arch/mips/include/asm/signal.h b/arch/mips/include/asm/signal.h
index 197f6367c201..8efe5a9e2c3e 100644
--- a/arch/mips/include/asm/signal.h
+++ b/arch/mips/include/asm/signal.h
@@ -21,6 +21,6 @@
 #include <asm/sigcontext.h>
 #include <asm/siginfo.h>
 
-#define __ARCH_HAS_ODD_SIGACTION
+#define __ARCH_HAS_IRIX_SIGACTION
 
 #endif /* _ASM_SIGNAL_H */
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 76a87fb57ac2..377cd8c3395e 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -141,11 +141,11 @@ typedef struct {
 } compat_sigset_t;
 
 struct compat_sigaction {
-#ifndef __ARCH_HAS_ODD_SIGACTION
+#ifndef __ARCH_HAS_IRIX_SIGACTION
 	compat_uptr_t			sa_handler;
 	compat_ulong_t			sa_flags;
 #else
-	compat_ulong_t			sa_flags;
+	compat_uint_t			sa_flags;
 	compat_uptr_t			sa_handler;
 #endif
 #ifdef __ARCH_HAS_SA_RESTORER
diff --git a/include/linux/signal.h b/include/linux/signal.h
index a2dcb94ea49d..9475c5cb28bc 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -250,11 +250,11 @@ extern int show_unhandled_signals;
 extern int sigsuspend(sigset_t *);
 
 struct sigaction {
-#ifndef __ARCH_HAS_ODD_SIGACTION
+#ifndef __ARCH_HAS_IRIX_SIGACTION
 	__sighandler_t	sa_handler;
 	unsigned long	sa_flags;
 #else
-	unsigned long	sa_flags;
+	unsigned int	sa_flags;
 	__sighandler_t	sa_handler;
 #endif
 #ifdef __ARCH_HAS_SA_RESTORER
-- 
cgit v1.2.3


From 4480764f57ba494e3f64003e13223c0b5ec6a2ca Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Tue, 19 Mar 2013 14:58:43 -0700
Subject: ASoC:: max98090: Remove executable bit

Source files shouldn't have the executable bit set.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
---
 include/sound/max98090.h    | 0
 sound/soc/codecs/max98090.c | 0
 sound/soc/codecs/max98090.h | 0
 3 files changed, 0 insertions(+), 0 deletions(-)
 mode change 100755 => 100644 include/sound/max98090.h
 mode change 100755 => 100644 sound/soc/codecs/max98090.c
 mode change 100755 => 100644 sound/soc/codecs/max98090.h

(limited to 'include')

diff --git a/include/sound/max98090.h b/include/sound/max98090.h
old mode 100755
new mode 100644
diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c
old mode 100755
new mode 100644
diff --git a/sound/soc/codecs/max98090.h b/sound/soc/codecs/max98090.h
old mode 100755
new mode 100644
-- 
cgit v1.2.3


From 7fa4cd1a78ea5af688ffce45553abbee9d7afd84 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@freescale.com>
Date: Wed, 20 Mar 2013 10:35:44 -0300
Subject: usb: ulpi: Define a *otg_ulpi_create no-op

Building a kernel for imx_v4_v5_defconfig with CONFIG_USB_ULPI disabled, results
in the following error:

arch/arm/mach-imx/built-in.o: In function 'pca100_init':
platform-mx2-emma.c:(.init.text+0x6788): undefined reference to 'otg_ulpi_create'
platform-mx2-emma.c:(.init.text+0x682c): undefined reference to 'mxc_ulpi_access_ops'

Fix this by providing a no-op definition of *otg_ulpi_create for the case when
CONFIG_USB_ULPI is not defined.

Acked-by: Igor Grinberg <grinberg@compulab.co.il>
Signed-off-by: Fabio Estevam <fabio.estevam@freescale.com>
Signed-off-by: Felipe Balbi <balbi@ti.com>
---
 include/linux/usb/ulpi.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/linux/usb/ulpi.h b/include/linux/usb/ulpi.h
index 6f033a415ecb..5c295c26ad37 100644
--- a/include/linux/usb/ulpi.h
+++ b/include/linux/usb/ulpi.h
@@ -181,8 +181,16 @@
 
 /*-------------------------------------------------------------------------*/
 
+#if IS_ENABLED(CONFIG_USB_ULPI)
 struct usb_phy *otg_ulpi_create(struct usb_phy_io_ops *ops,
 					unsigned int flags);
+#else
+static inline struct usb_phy *otg_ulpi_create(struct usb_phy_io_ops *ops,
+					      unsigned int flags)
+{
+	return NULL;
+}
+#endif
 
 #ifdef CONFIG_USB_ULPI_VIEWPORT
 /* access ops for controllers with a viewport register */
-- 
cgit v1.2.3


From 44046a593eb770dbecdabf1c82bcd252f2a8337b Mon Sep 17 00:00:00 2001
From: Tom Parkin <tparkin@katalix.com>
Date: Tue, 19 Mar 2013 06:11:12 +0000
Subject: udp: add encap_destroy callback

Users of udp encapsulation currently have an encap_rcv callback which they can
use to hook into the udp receive path.

In situations where a encapsulation user allocates resources associated with a
udp encap socket, it may be convenient to be able to also hook the proto
.destroy operation.  For example, if an encap user holds a reference to the
udp socket, the destroy hook might be used to relinquish this reference.

This patch adds a socket destroy hook into udp, which is set and enabled
in the same way as the existing encap_rcv hook.

Signed-off-by: Tom Parkin <tparkin@katalix.com>
Signed-off-by: James Chapman <jchapman@katalix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/udp.h | 1 +
 net/ipv4/udp.c      | 7 +++++++
 net/ipv6/udp.c      | 8 ++++++++
 3 files changed, 16 insertions(+)

(limited to 'include')

diff --git a/include/linux/udp.h b/include/linux/udp.h
index 9d81de123c90..42278bbf7a88 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -68,6 +68,7 @@ struct udp_sock {
 	 * For encapsulation sockets.
 	 */
 	int (*encap_rcv)(struct sock *sk, struct sk_buff *skb);
+	void (*encap_destroy)(struct sock *sk);
 };
 
 static inline struct udp_sock *udp_sk(const struct sock *sk)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 265c42cf963c..0a073a263720 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1762,9 +1762,16 @@ int udp_rcv(struct sk_buff *skb)
 
 void udp_destroy_sock(struct sock *sk)
 {
+	struct udp_sock *up = udp_sk(sk);
 	bool slow = lock_sock_fast(sk);
 	udp_flush_pending_frames(sk);
 	unlock_sock_fast(sk, slow);
+	if (static_key_false(&udp_encap_needed) && up->encap_type) {
+		void (*encap_destroy)(struct sock *sk);
+		encap_destroy = ACCESS_ONCE(up->encap_destroy);
+		if (encap_destroy)
+			encap_destroy(sk);
+	}
 }
 
 /*
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 599e1ba6d1ce..d8e5e852fc7a 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1285,10 +1285,18 @@ do_confirm:
 
 void udpv6_destroy_sock(struct sock *sk)
 {
+	struct udp_sock *up = udp_sk(sk);
 	lock_sock(sk);
 	udp_v6_flush_pending_frames(sk);
 	release_sock(sk);
 
+	if (static_key_false(&udpv6_encap_needed) && up->encap_type) {
+		void (*encap_destroy)(struct sock *sk);
+		encap_destroy = ACCESS_ONCE(up->encap_destroy);
+		if (encap_destroy)
+			encap_destroy(sk);
+	}
+
 	inet6_destroy_sock(sk);
 }
 
-- 
cgit v1.2.3


From 8ed781668dd49b608f1e67a22e3b445fd0c2cd6f Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <dborkman@redhat.com>
Date: Tue, 19 Mar 2013 06:39:29 +0000
Subject: flow_keys: include thoff into flow_keys for later usage

In skb_flow_dissect(), we perform a dissection of a skbuff. Since we're
doing the work here anyway, also store thoff for a later usage, e.g. in
the BPF filter.

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow_keys.h   | 1 +
 net/core/flow_dissector.c | 2 ++
 2 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/net/flow_keys.h b/include/net/flow_keys.h
index 80461c1ae9ef..bb8271d487b7 100644
--- a/include/net/flow_keys.h
+++ b/include/net/flow_keys.h
@@ -9,6 +9,7 @@ struct flow_keys {
 		__be32 ports;
 		__be16 port16[2];
 	};
+	u16 thoff;
 	u8 ip_proto;
 };
 
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 9d4c7201400d..e187bf06d673 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -140,6 +140,8 @@ ipv6:
 			flow->ports = *ports;
 	}
 
+	flow->thoff = (u16) nhoff;
+
 	return true;
 }
 EXPORT_SYMBOL(skb_flow_dissect);
-- 
cgit v1.2.3


From 73214f5d9f33b79918b1f7babddd5c8af28dd23d Mon Sep 17 00:00:00 2001
From: Masatake YAMATO <yamato@redhat.com>
Date: Tue, 19 Mar 2013 01:47:28 +0000
Subject: thermal: shorten too long mcast group name

The original name is too long.

Signed-off-by: Masatake YAMATO <yamato@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/thermal.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index f0bd7f90a90d..e3c0ae9bb1fa 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -44,7 +44,7 @@
 /* Adding event notification support elements */
 #define THERMAL_GENL_FAMILY_NAME                "thermal_event"
 #define THERMAL_GENL_VERSION                    0x01
-#define THERMAL_GENL_MCAST_GROUP_NAME           "thermal_mc_group"
+#define THERMAL_GENL_MCAST_GROUP_NAME           "thermal_mc_grp"
 
 /* Default Thermal Governor */
 #if defined(CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE)
-- 
cgit v1.2.3


From ae5fc98728c8bbbd6d7cab0b9781671fc4419c1b Mon Sep 17 00:00:00 2001
From: Andrey Vagin <avagin@openvz.org>
Date: Thu, 21 Mar 2013 20:33:46 +0400
Subject: net: fix *_DIAG_MAX constants

Follow the common pattern and define *_DIAG_MAX like:

        [...]
        __XXX_DIAG_MAX,
};

Because everyone is used to do:

        struct nlattr *attrs[XXX_DIAG_MAX+1];

        nla_parse([...], XXX_DIAG_MAX, [...]

Reported-by: Thomas Graf <tgraf@suug.ch>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Andrey Vagin <avagin@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/packet_diag.h | 4 +++-
 include/uapi/linux/unix_diag.h   | 4 +++-
 2 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/packet_diag.h b/include/uapi/linux/packet_diag.h
index 93f5fa94a431..afafd703ad92 100644
--- a/include/uapi/linux/packet_diag.h
+++ b/include/uapi/linux/packet_diag.h
@@ -33,9 +33,11 @@ enum {
 	PACKET_DIAG_TX_RING,
 	PACKET_DIAG_FANOUT,
 
-	PACKET_DIAG_MAX,
+	__PACKET_DIAG_MAX,
 };
 
+#define PACKET_DIAG_MAX (__PACKET_DIAG_MAX - 1)
+
 struct packet_diag_info {
 	__u32	pdi_index;
 	__u32	pdi_version;
diff --git a/include/uapi/linux/unix_diag.h b/include/uapi/linux/unix_diag.h
index b8a24941db21..b9e2a6a7446f 100644
--- a/include/uapi/linux/unix_diag.h
+++ b/include/uapi/linux/unix_diag.h
@@ -39,9 +39,11 @@ enum {
 	UNIX_DIAG_MEMINFO,
 	UNIX_DIAG_SHUTDOWN,
 
-	UNIX_DIAG_MAX,
+	__UNIX_DIAG_MAX,
 };
 
+#define UNIX_DIAG_MAX (__UNIX_DIAG_MAX - 1)
+
 struct unix_diag_vfs {
 	__u32	udiag_vfs_ino;
 	__u32	udiag_vfs_dev;
-- 
cgit v1.2.3


From e5b33dc9d16053c2ae4c2c669cf008829530364b Mon Sep 17 00:00:00 2001
From: Johan Hovold <jhovold@gmail.com>
Date: Tue, 19 Mar 2013 09:21:10 +0100
Subject: USB: serial: add modem-status-change wait queue

Add modem-status-change wait queue to struct usb_serial_port that
subdrivers can use to implement TIOCMIWAIT.

Currently subdrivers use a private wait queue which may have been
released when waking up after device disconnected.

Note that we're adding a new wait queue rather than reusing the tty-port
one as we do not want to get woken up at hangup (yet).

Cc: stable <stable@vger.kernel.org>
Signed-off-by: Johan Hovold <jhovold@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb/serial.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h
index ef9be7e1e190..1819b59aab2a 100644
--- a/include/linux/usb/serial.h
+++ b/include/linux/usb/serial.h
@@ -66,6 +66,7 @@
  *	port.
  * @flags: usb serial port flags
  * @write_wait: a wait_queue_head_t used by the port.
+ * @delta_msr_wait: modem-status-change wait queue
  * @work: work queue entry for the line discipline waking up.
  * @throttled: nonzero if the read urb is inactive to throttle the device
  * @throttle_req: nonzero if the tty wants to throttle us
@@ -112,6 +113,7 @@ struct usb_serial_port {
 
 	unsigned long		flags;
 	wait_queue_head_t	write_wait;
+	wait_queue_head_t	delta_msr_wait;
 	struct work_struct	work;
 	char			throttled;
 	char			throttle_req;
-- 
cgit v1.2.3


From 09a6e1f4ad32243989b30485f78985c0923284cd Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Fri, 22 Mar 2013 08:08:06 -0300
Subject: Revert "KVM: allow host header to be included even for !CONFIG_KVM"

This reverts commit f445f11eb2cc265dd47da5b2e864df46cd6e5a82 as
it breaks PPC with CONFIG_KVM=n.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 include/linux/kvm_host.h | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index a9428635c9fd..cad77fe09d77 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1,8 +1,6 @@
 #ifndef __KVM_HOST_H
 #define __KVM_HOST_H
 
-#if IS_ENABLED(CONFIG_KVM)
-
 /*
  * This work is licensed under the terms of the GNU GPL, version 2.  See
  * the COPYING file in the top-level directory.
@@ -1057,8 +1055,5 @@ static inline bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
 }
 
 #endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */
-#else
-static inline void __guest_enter(void) { return; }
-static inline void __guest_exit(void) { return; }
-#endif /* IS_ENABLED(CONFIG_KVM) */
 #endif
+
-- 
cgit v1.2.3


From 909b3fdb0dd4f3db07b2d75425a00a2adb551383 Mon Sep 17 00:00:00 2001
From: Jan Beulich <JBeulich@suse.com>
Date: Tue, 12 Mar 2013 15:06:23 +0000
Subject: xen-pciback: notify hypervisor about devices intended to be assigned
 to guests

For MSI-X capable devices the hypervisor wants to write protect the
MSI-X table and PBA, yet it can't assume that resources have been
assigned to their final values at device enumeration time. Thus have
pciback do that notification, as having the device controlled by it is
a prerequisite to assigning the device to guests anyway.

This is the kernel part of hypervisor side commit 4245d33 ("x86/MSI:
add mechanism to fully protect MSI-X table from PV guest accesses") on
the master branch of git://xenbits.xen.org/xen.git.

CC: stable@vger.kernel.org
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/x86/include/asm/xen/hypercall.h |  4 +--
 drivers/xen/fallback.c               |  3 +-
 drivers/xen/xen-pciback/pci_stub.c   | 59 +++++++++++++++++++++++++++---------
 include/xen/interface/physdev.h      |  6 ++++
 4 files changed, 54 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index c20d1ce62dc6..e709884d0ef9 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -382,14 +382,14 @@ HYPERVISOR_console_io(int cmd, int count, char *str)
 	return _hypercall3(int, console_io, cmd, count, str);
 }
 
-extern int __must_check HYPERVISOR_physdev_op_compat(int, void *);
+extern int __must_check xen_physdev_op_compat(int, void *);
 
 static inline int
 HYPERVISOR_physdev_op(int cmd, void *arg)
 {
 	int rc = _hypercall2(int, physdev_op, cmd, arg);
 	if (unlikely(rc == -ENOSYS))
-		rc = HYPERVISOR_physdev_op_compat(cmd, arg);
+		rc = xen_physdev_op_compat(cmd, arg);
 	return rc;
 }
 
diff --git a/drivers/xen/fallback.c b/drivers/xen/fallback.c
index 0ef7c4d40f86..b04fb64c5a91 100644
--- a/drivers/xen/fallback.c
+++ b/drivers/xen/fallback.c
@@ -44,7 +44,7 @@ int xen_event_channel_op_compat(int cmd, void *arg)
 }
 EXPORT_SYMBOL_GPL(xen_event_channel_op_compat);
 
-int HYPERVISOR_physdev_op_compat(int cmd, void *arg)
+int xen_physdev_op_compat(int cmd, void *arg)
 {
 	struct physdev_op op;
 	int rc;
@@ -78,3 +78,4 @@ int HYPERVISOR_physdev_op_compat(int cmd, void *arg)
 
 	return rc;
 }
+EXPORT_SYMBOL_GPL(xen_physdev_op_compat);
diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c
index 9204126f1560..a2278ba7fb27 100644
--- a/drivers/xen/xen-pciback/pci_stub.c
+++ b/drivers/xen/xen-pciback/pci_stub.c
@@ -17,6 +17,7 @@
 #include <xen/events.h>
 #include <asm/xen/pci.h>
 #include <asm/xen/hypervisor.h>
+#include <xen/interface/physdev.h>
 #include "pciback.h"
 #include "conf_space.h"
 #include "conf_space_quirks.h"
@@ -85,37 +86,52 @@ static struct pcistub_device *pcistub_device_alloc(struct pci_dev *dev)
 static void pcistub_device_release(struct kref *kref)
 {
 	struct pcistub_device *psdev;
+	struct pci_dev *dev;
 	struct xen_pcibk_dev_data *dev_data;
 
 	psdev = container_of(kref, struct pcistub_device, kref);
-	dev_data = pci_get_drvdata(psdev->dev);
+	dev = psdev->dev;
+	dev_data = pci_get_drvdata(dev);
 
-	dev_dbg(&psdev->dev->dev, "pcistub_device_release\n");
+	dev_dbg(&dev->dev, "pcistub_device_release\n");
 
-	xen_unregister_device_domain_owner(psdev->dev);
+	xen_unregister_device_domain_owner(dev);
 
 	/* Call the reset function which does not take lock as this
 	 * is called from "unbind" which takes a device_lock mutex.
 	 */
-	__pci_reset_function_locked(psdev->dev);
-	if (pci_load_and_free_saved_state(psdev->dev,
-					  &dev_data->pci_saved_state)) {
-		dev_dbg(&psdev->dev->dev, "Could not reload PCI state\n");
-	} else
-		pci_restore_state(psdev->dev);
+	__pci_reset_function_locked(dev);
+	if (pci_load_and_free_saved_state(dev, &dev_data->pci_saved_state))
+		dev_dbg(&dev->dev, "Could not reload PCI state\n");
+	else
+		pci_restore_state(dev);
+
+	if (pci_find_capability(dev, PCI_CAP_ID_MSIX)) {
+		struct physdev_pci_device ppdev = {
+			.seg = pci_domain_nr(dev->bus),
+			.bus = dev->bus->number,
+			.devfn = dev->devfn
+		};
+		int err = HYPERVISOR_physdev_op(PHYSDEVOP_release_msix,
+						&ppdev);
+
+		if (err)
+			dev_warn(&dev->dev, "MSI-X release failed (%d)\n",
+				 err);
+	}
 
 	/* Disable the device */
-	xen_pcibk_reset_device(psdev->dev);
+	xen_pcibk_reset_device(dev);
 
 	kfree(dev_data);
-	pci_set_drvdata(psdev->dev, NULL);
+	pci_set_drvdata(dev, NULL);
 
 	/* Clean-up the device */
-	xen_pcibk_config_free_dyn_fields(psdev->dev);
-	xen_pcibk_config_free_dev(psdev->dev);
+	xen_pcibk_config_free_dyn_fields(dev);
+	xen_pcibk_config_free_dev(dev);
 
-	psdev->dev->dev_flags &= ~PCI_DEV_FLAGS_ASSIGNED;
-	pci_dev_put(psdev->dev);
+	dev->dev_flags &= ~PCI_DEV_FLAGS_ASSIGNED;
+	pci_dev_put(dev);
 
 	kfree(psdev);
 }
@@ -355,6 +371,19 @@ static int pcistub_init_device(struct pci_dev *dev)
 	if (err)
 		goto config_release;
 
+	if (pci_find_capability(dev, PCI_CAP_ID_MSIX)) {
+		struct physdev_pci_device ppdev = {
+			.seg = pci_domain_nr(dev->bus),
+			.bus = dev->bus->number,
+			.devfn = dev->devfn
+		};
+
+		err = HYPERVISOR_physdev_op(PHYSDEVOP_prepare_msix, &ppdev);
+		if (err)
+			dev_err(&dev->dev, "MSI-X preparation failed (%d)\n",
+				err);
+	}
+
 	/* We need the device active to save the state. */
 	dev_dbg(&dev->dev, "save state of device\n");
 	pci_save_state(dev);
diff --git a/include/xen/interface/physdev.h b/include/xen/interface/physdev.h
index 1844d31f4552..7000bb1f6e96 100644
--- a/include/xen/interface/physdev.h
+++ b/include/xen/interface/physdev.h
@@ -251,6 +251,12 @@ struct physdev_pci_device_add {
 
 #define PHYSDEVOP_pci_device_remove     26
 #define PHYSDEVOP_restore_msi_ext       27
+/*
+ * Dom0 should use these two to announce MMIO resources assigned to
+ * MSI-X capable devices won't (prepare) or may (release) change.
+ */
+#define PHYSDEVOP_prepare_msix          30
+#define PHYSDEVOP_release_msix          31
 struct physdev_pci_device {
     /* IN */
     uint16_t seg;
-- 
cgit v1.2.3


From fe8d52614bd419cedef85ef55850fd090373f481 Mon Sep 17 00:00:00 2001
From: James Hogan <james.hogan@imgtec.com>
Date: Fri, 22 Mar 2013 15:04:37 -0700
Subject: irq_work.h: fix warning when CONFIG_IRQ_WORK=n

A randconfig caught repeated compiler warnings when CONFIG_IRQ_WORK=n
due to the definition of a non-inline static function in
<linux/irq_work.h>:

  include/linux/irq_work.h +40 : warning: 'irq_work_needs_cpu' defined but not used

Make it inline to supress the warning.  This is caused commit
00b42959106a ("irq_work: Don't stop the tick with pending works") merged
in v3.9-rc1.

Signed-off-by: James Hogan <james.hogan@imgtec.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/irq_work.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index f5dbce50466e..66017028dcb3 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -37,7 +37,7 @@ void irq_work_sync(struct irq_work *work);
 #ifdef CONFIG_IRQ_WORK
 bool irq_work_needs_cpu(void);
 #else
-static bool irq_work_needs_cpu(void) { return false; }
+static inline bool irq_work_needs_cpu(void) { return false; }
 #endif
 
 #endif /* _LINUX_IRQ_WORK_H */
-- 
cgit v1.2.3


From dc72c32e1fd872a9a4fdfe645283c9dcd68e556d Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Fri, 22 Mar 2013 15:04:39 -0700
Subject: printk: Provide a wake_up_klogd() off-case

wake_up_klogd() is useless when CONFIG_PRINTK=n because neither printk()
nor printk_sched() are in use and there are actually no waiter on
log_wait waitqueue.  It should be a stub in this case for users like
bust_spinlocks().

Otherwise this results in this warning when CONFIG_PRINTK=n and
CONFIG_IRQ_WORK=n:

	kernel/built-in.o In function `wake_up_klogd':
	(.text.wake_up_klogd+0xb4): undefined reference to `irq_work_queue'

To fix this, provide an off-case for wake_up_klogd() when
CONFIG_PRINTK=n.

There is much more from console_unlock() and other console related code
in printk.c that should be moved under CONFIG_PRINTK.  But for now,
focus on a minimal fix as we passed the merged window already.

[akpm@linux-foundation.org: include printk.h in bust_spinlocks.c]
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Reported-by: James Hogan <james.hogan@imgtec.com>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/kernel.h |  1 -
 include/linux/printk.h |  6 ++++
 kernel/printk.c        | 80 ++++++++++++++++++++++++--------------------------
 lib/bust_spinlocks.c   |  3 +-
 4 files changed, 46 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 80d36874689b..79fdd80a42d4 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -390,7 +390,6 @@ extern struct pid *session_of_pgrp(struct pid *pgrp);
 unsigned long int_sqrt(unsigned long);
 
 extern void bust_spinlocks(int yes);
-extern void wake_up_klogd(void);
 extern int oops_in_progress;		/* If set, an oops, panic(), BUG() or die() is in progress */
 extern int panic_timeout;
 extern int panic_on_oops;
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 1249a54d17e0..822171fcb1c8 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -134,6 +134,8 @@ extern int printk_delay_msec;
 extern int dmesg_restrict;
 extern int kptr_restrict;
 
+extern void wake_up_klogd(void);
+
 void log_buf_kexec_setup(void);
 void __init setup_log_buf(int early);
 #else
@@ -162,6 +164,10 @@ static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies,
 	return false;
 }
 
+static inline void wake_up_klogd(void)
+{
+}
+
 static inline void log_buf_kexec_setup(void)
 {
 }
diff --git a/kernel/printk.c b/kernel/printk.c
index 0b31715f335a..abbdd9e2ac82 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -63,8 +63,6 @@ void asmlinkage __attribute__((weak)) early_printk(const char *fmt, ...)
 #define MINIMUM_CONSOLE_LOGLEVEL 1 /* Minimum loglevel we let people use */
 #define DEFAULT_CONSOLE_LOGLEVEL 7 /* anything MORE serious than KERN_DEBUG */
 
-DECLARE_WAIT_QUEUE_HEAD(log_wait);
-
 int console_printk[4] = {
 	DEFAULT_CONSOLE_LOGLEVEL,	/* console_loglevel */
 	DEFAULT_MESSAGE_LOGLEVEL,	/* default_message_loglevel */
@@ -224,6 +222,7 @@ struct log {
 static DEFINE_RAW_SPINLOCK(logbuf_lock);
 
 #ifdef CONFIG_PRINTK
+DECLARE_WAIT_QUEUE_HEAD(log_wait);
 /* the next printk record to read by syslog(READ) or /proc/kmsg */
 static u64 syslog_seq;
 static u32 syslog_idx;
@@ -1957,45 +1956,6 @@ int is_console_locked(void)
 	return console_locked;
 }
 
-/*
- * Delayed printk version, for scheduler-internal messages:
- */
-#define PRINTK_BUF_SIZE		512
-
-#define PRINTK_PENDING_WAKEUP	0x01
-#define PRINTK_PENDING_SCHED	0x02
-
-static DEFINE_PER_CPU(int, printk_pending);
-static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf);
-
-static void wake_up_klogd_work_func(struct irq_work *irq_work)
-{
-	int pending = __this_cpu_xchg(printk_pending, 0);
-
-	if (pending & PRINTK_PENDING_SCHED) {
-		char *buf = __get_cpu_var(printk_sched_buf);
-		printk(KERN_WARNING "[sched_delayed] %s", buf);
-	}
-
-	if (pending & PRINTK_PENDING_WAKEUP)
-		wake_up_interruptible(&log_wait);
-}
-
-static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = {
-	.func = wake_up_klogd_work_func,
-	.flags = IRQ_WORK_LAZY,
-};
-
-void wake_up_klogd(void)
-{
-	preempt_disable();
-	if (waitqueue_active(&log_wait)) {
-		this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
-		irq_work_queue(&__get_cpu_var(wake_up_klogd_work));
-	}
-	preempt_enable();
-}
-
 static void console_cont_flush(char *text, size_t size)
 {
 	unsigned long flags;
@@ -2458,6 +2418,44 @@ static int __init printk_late_init(void)
 late_initcall(printk_late_init);
 
 #if defined CONFIG_PRINTK
+/*
+ * Delayed printk version, for scheduler-internal messages:
+ */
+#define PRINTK_BUF_SIZE		512
+
+#define PRINTK_PENDING_WAKEUP	0x01
+#define PRINTK_PENDING_SCHED	0x02
+
+static DEFINE_PER_CPU(int, printk_pending);
+static DEFINE_PER_CPU(char [PRINTK_BUF_SIZE], printk_sched_buf);
+
+static void wake_up_klogd_work_func(struct irq_work *irq_work)
+{
+	int pending = __this_cpu_xchg(printk_pending, 0);
+
+	if (pending & PRINTK_PENDING_SCHED) {
+		char *buf = __get_cpu_var(printk_sched_buf);
+		printk(KERN_WARNING "[sched_delayed] %s", buf);
+	}
+
+	if (pending & PRINTK_PENDING_WAKEUP)
+		wake_up_interruptible(&log_wait);
+}
+
+static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = {
+	.func = wake_up_klogd_work_func,
+	.flags = IRQ_WORK_LAZY,
+};
+
+void wake_up_klogd(void)
+{
+	preempt_disable();
+	if (waitqueue_active(&log_wait)) {
+		this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
+		irq_work_queue(&__get_cpu_var(wake_up_klogd_work));
+	}
+	preempt_enable();
+}
 
 int printk_sched(const char *fmt, ...)
 {
diff --git a/lib/bust_spinlocks.c b/lib/bust_spinlocks.c
index 9681d54b95d1..f8e0e5367398 100644
--- a/lib/bust_spinlocks.c
+++ b/lib/bust_spinlocks.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/printk.h>
 #include <linux/spinlock.h>
 #include <linux/tty.h>
 #include <linux/wait.h>
@@ -28,5 +29,3 @@ void __attribute__((weak)) bust_spinlocks(int yes)
 			wake_up_klogd();
 	}
 }
-
-
-- 
cgit v1.2.3


From f9228b204f789493117e458d2fefae937edb7272 Mon Sep 17 00:00:00 2001
From: Russ Anderson <rja@sgi.com>
Date: Fri, 22 Mar 2013 15:04:43 -0700
Subject: mm: zone_end_pfn is too small

Booting with 32 TBytes memory hits BUG at mm/page_alloc.c:552! (output
below).

The key hint is "page 4294967296 outside zone".
4294967296 = 0x100000000 (bit 32 is set).

The problem is in include/linux/mmzone.h:

  530 static inline unsigned zone_end_pfn(const struct zone *zone)
  531 {
  532         return zone->zone_start_pfn + zone->spanned_pages;
  533 }

zone_end_pfn is "unsigned" (32 bits).  Changing it to "unsigned long"
(64 bits) fixes the problem.

zone_end_pfn() was added recently in commit 108bcc96ef70 ("mm: add & use
zone_end_pfn() and zone_spans_pfn()")

Output from the failure.

  No AGP bridge found
  page 4294967296 outside zone [ 4294967296 - 4327469056 ]
  ------------[ cut here ]------------
  kernel BUG at mm/page_alloc.c:552!
  invalid opcode: 0000 [#1] SMP
  Modules linked in:
  CPU 0
  Pid: 0, comm: swapper Not tainted 3.9.0-rc2.dtp+ #10
  RIP: free_one_page+0x382/0x430
  Process swapper (pid: 0, threadinfo ffffffff81942000, task ffffffff81955420)
  Call Trace:
    __free_pages_ok+0x96/0xb0
    __free_pages+0x25/0x50
    __free_pages_bootmem+0x8a/0x8c
    __free_memory_core+0xea/0x131
    free_low_memory_core_early+0x4a/0x98
    free_all_bootmem+0x45/0x47
    mem_init+0x7b/0x14c
    start_kernel+0x216/0x433
    x86_64_start_reservations+0x2a/0x2c
    x86_64_start_kernel+0x144/0x153
  Code: 89 f1 ba 01 00 00 00 31 f6 d3 e2 4c 89 ef e8 66 a4 01 00 e9 2c fe ff ff 0f 0b eb fe 0f 0b 66 66 2e 0f 1f 84 00 00 00 00 00 eb f3 <0f> 0b eb fe 0f 0b 0f 1f 84 00 00 00 00 00 eb f6 0f 0b eb fe 49

Signed-off-by: Russ Anderson <rja@sgi.com>
Reported-by: George Beshers <gbeshers@sgi.com>
Acked-by: Hedi Berriche <hedi@sgi.com>
Cc: Cody P Schafer <cody@linux.vnet.ibm.com>
Cc: 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/mmzone.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index ede274957e05..c74092eebf5c 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -527,7 +527,7 @@ static inline int zone_is_oom_locked(const struct zone *zone)
 	return test_bit(ZONE_OOM_LOCKED, &zone->flags);
 }
 
-static inline unsigned zone_end_pfn(const struct zone *zone)
+static inline unsigned long zone_end_pfn(const struct zone *zone)
 {
 	return zone->zone_start_pfn + zone->spanned_pages;
 }
-- 
cgit v1.2.3


From 130549fed828cc34c22624c6195afcf9e7ae56fe Mon Sep 17 00:00:00 2001
From: Gao feng <gaofeng@cn.fujitsu.com>
Date: Thu, 21 Mar 2013 19:48:41 +0000
Subject: netfilter: reset nf_trace in nf_reset

We forgot to clear the nf_trace of sk_buff in nf_reset,
When we use veth device, this nf_trace information will
be leaked from one net namespace to another net namespace.

Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/skbuff.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 441f5bfdab8e..72b396751de7 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2641,6 +2641,9 @@ static inline void nf_reset(struct sk_buff *skb)
 	nf_bridge_put(skb->nf_bridge);
 	skb->nf_bridge = NULL;
 #endif
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
+	skb->nf_trace = 0;
+#endif
 }
 
 /* Note: This doesn't put any conntrack and bridge info in dst. */
-- 
cgit v1.2.3


From 3f5eb14135ba9d97ba4b8514fc7ef5e0dac2abf4 Mon Sep 17 00:00:00 2001
From: Lan Tianyu <tianyu.lan@intel.com>
Date: Tue, 19 Mar 2013 16:48:12 +0800
Subject: usb: add find_raw_port_number callback to struct hc_driver()

xhci driver divides the root hub into two logical hubs which work
respectively for usb 2.0 and usb 3.0 devices. They are independent
devices in the usb core. But in the ACPI table, it's one device node
and all usb2.0 and usb3.0 ports are under it. Binding usb port with
its acpi node needs the raw port number which is reflected in the xhci
extended capabilities table. This patch is to add find_raw_port_number
callback to struct hc_driver(), fill it with xhci_find_raw_port_number()
which will return raw port number and add a wrap usb_hcd_find_raw_port_number().

Otherwise, refactor xhci_find_real_port_number(). Using
xhci_find_raw_port_number() to get real index in the HW port status
registers instead of scanning through the xHCI roothub port array.
This can help to speed up.

All addresses in xhci->usb2_ports and xhci->usb3_ports array are
kown good ports and don't include following bad ports in the extended
capabilities talbe.
     (1) root port that doesn't have an entry
     (2) root port with unknown speed
     (3) root port that is listed twice and with different speeds.

So xhci_find_raw_port_number() will only return port num of good ones
and never touch bad ports above.

Signed-off-by: Lan Tianyu <tianyu.lan@intel.com>
Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
---
 drivers/usb/core/hcd.c      |  8 ++++++++
 drivers/usb/host/xhci-mem.c | 36 ++++++++----------------------------
 drivers/usb/host/xhci-pci.c |  1 +
 drivers/usb/host/xhci.c     | 22 ++++++++++++++++++++++
 drivers/usb/host/xhci.h     |  1 +
 include/linux/usb/hcd.h     |  2 ++
 6 files changed, 42 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 99b34a30354f..f9ec44cbb82f 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -2412,6 +2412,14 @@ int usb_hcd_is_primary_hcd(struct usb_hcd *hcd)
 }
 EXPORT_SYMBOL_GPL(usb_hcd_is_primary_hcd);
 
+int usb_hcd_find_raw_port_number(struct usb_hcd *hcd, int port1)
+{
+	if (!hcd->driver->find_raw_port_number)
+		return port1;
+
+	return hcd->driver->find_raw_port_number(hcd, port1);
+}
+
 static int usb_hcd_request_irqs(struct usb_hcd *hcd,
 		unsigned int irqnum, unsigned long irqflags)
 {
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 35616ffbe3ae..6dc238c592bc 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1022,44 +1022,24 @@ void xhci_copy_ep0_dequeue_into_input_ctx(struct xhci_hcd *xhci,
  * is attached to (or the roothub port its ancestor hub is attached to).  All we
  * know is the index of that port under either the USB 2.0 or the USB 3.0
  * roothub, but that doesn't give us the real index into the HW port status
- * registers.  Scan through the xHCI roothub port array, looking for the Nth
- * entry of the correct port speed.  Return the port number of that entry.
+ * registers. Call xhci_find_raw_port_number() to get real index.
  */
 static u32 xhci_find_real_port_number(struct xhci_hcd *xhci,
 		struct usb_device *udev)
 {
 	struct usb_device *top_dev;
-	unsigned int num_similar_speed_ports;
-	unsigned int faked_port_num;
-	int i;
+	struct usb_hcd *hcd;
+
+	if (udev->speed == USB_SPEED_SUPER)
+		hcd = xhci->shared_hcd;
+	else
+		hcd = xhci->main_hcd;
 
 	for (top_dev = udev; top_dev->parent && top_dev->parent->parent;
 			top_dev = top_dev->parent)
 		/* Found device below root hub */;
-	faked_port_num = top_dev->portnum;
-	for (i = 0, num_similar_speed_ports = 0;
-			i < HCS_MAX_PORTS(xhci->hcs_params1); i++) {
-		u8 port_speed = xhci->port_array[i];
-
-		/*
-		 * Skip ports that don't have known speeds, or have duplicate
-		 * Extended Capabilities port speed entries.
-		 */
-		if (port_speed == 0 || port_speed == DUPLICATE_ENTRY)
-			continue;
 
-		/*
-		 * USB 3.0 ports are always under a USB 3.0 hub.  USB 2.0 and
-		 * 1.1 ports are under the USB 2.0 hub.  If the port speed
-		 * matches the device speed, it's a similar speed port.
-		 */
-		if ((port_speed == 0x03) == (udev->speed == USB_SPEED_SUPER))
-			num_similar_speed_ports++;
-		if (num_similar_speed_ports == faked_port_num)
-			/* Roothub ports are numbered from 1 to N */
-			return i+1;
-	}
-	return 0;
+	return	xhci_find_raw_port_number(hcd, top_dev->portnum);
 }
 
 /* Setup an xHCI virtual device for a Set Address command */
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index af259e0ec172..1a30c380043c 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -313,6 +313,7 @@ static const struct hc_driver xhci_pci_hc_driver = {
 	.set_usb2_hw_lpm =	xhci_set_usb2_hardware_lpm,
 	.enable_usb3_lpm_timeout =	xhci_enable_usb3_lpm_timeout,
 	.disable_usb3_lpm_timeout =	xhci_disable_usb3_lpm_timeout,
+	.find_raw_port_number =	xhci_find_raw_port_number,
 };
 
 /*-------------------------------------------------------------------------*/
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 849470b18831..53b8f89a0b1c 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -3779,6 +3779,28 @@ int xhci_address_device(struct usb_hcd *hcd, struct usb_device *udev)
 	return 0;
 }
 
+/*
+ * Transfer the port index into real index in the HW port status
+ * registers. Caculate offset between the port's PORTSC register
+ * and port status base. Divide the number of per port register
+ * to get the real index. The raw port number bases 1.
+ */
+int xhci_find_raw_port_number(struct usb_hcd *hcd, int port1)
+{
+	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
+	__le32 __iomem *base_addr = &xhci->op_regs->port_status_base;
+	__le32 __iomem *addr;
+	int raw_port;
+
+	if (hcd->speed != HCD_USB3)
+		addr = xhci->usb2_ports[port1 - 1];
+	else
+		addr = xhci->usb3_ports[port1 - 1];
+
+	raw_port = (addr - base_addr)/NUM_PORT_REGS + 1;
+	return raw_port;
+}
+
 #ifdef CONFIG_USB_SUSPEND
 
 /* BESL to HIRD Encoding array for USB2 LPM */
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 2c510e4a7d4c..d798b6931914 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1829,6 +1829,7 @@ void xhci_test_and_clear_bit(struct xhci_hcd *xhci, __le32 __iomem **port_array,
 int xhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, u16 wIndex,
 		char *buf, u16 wLength);
 int xhci_hub_status_data(struct usb_hcd *hcd, char *buf);
+int xhci_find_raw_port_number(struct usb_hcd *hcd, int port1);
 
 #ifdef CONFIG_PM
 int xhci_bus_suspend(struct usb_hcd *hcd);
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index 0a78df5f6cfd..59694b5e5e90 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -357,6 +357,7 @@ struct hc_driver {
 		 */
 	int	(*disable_usb3_lpm_timeout)(struct usb_hcd *,
 			struct usb_device *, enum usb3_link_state state);
+	int	(*find_raw_port_number)(struct usb_hcd *, int);
 };
 
 extern int usb_hcd_link_urb_to_ep(struct usb_hcd *hcd, struct urb *urb);
@@ -396,6 +397,7 @@ extern int usb_hcd_is_primary_hcd(struct usb_hcd *hcd);
 extern int usb_add_hcd(struct usb_hcd *hcd,
 		unsigned int irqnum, unsigned long irqflags);
 extern void usb_remove_hcd(struct usb_hcd *hcd);
+extern int usb_hcd_find_raw_port_number(struct usb_hcd *hcd, int port1);
 
 struct platform_device;
 extern void usb_hcd_platform_shutdown(struct platform_device *dev);
-- 
cgit v1.2.3


From 8a9a71381208b2364a2d12b0d257ae333917a1bc Mon Sep 17 00:00:00 2001
From: Robert Love <robert.w.love@intel.com>
Date: Mon, 25 Mar 2013 11:00:27 -0700
Subject: libfc, fcoe, bnx2fc: Always use fcoe_disc_init for discovery layer
 initialization

Currently libfcoe is doing some libfc discovery layer initialization outside of
libfc. This patch moves this code into libfc and sets up a split in discovery
(one time) initialization code and (re-configurable) settings that will come in
the next patch.

Signed-off-by: Robert Love <robert.w.love@intel.com>
Tested-by: Jack Morgan <jack.morgan@intel.com>
Reviewed-by: Bhanu Prakash Gollapudi <bprakash@broadcom.com>
---
 drivers/scsi/bnx2fc/bnx2fc_fcoe.c |  2 +-
 drivers/scsi/fcoe/fcoe_ctlr.c     | 11 ++++++-----
 drivers/scsi/libfc/fc_disc.c      |  5 +++--
 include/scsi/libfc.h              |  2 +-
 4 files changed, 11 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index cc4791cf575b..b867b1bfa908 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -939,7 +939,7 @@ static int bnx2fc_libfc_config(struct fc_lport *lport)
 	fc_elsct_init(lport);
 	fc_exch_init(lport);
 	fc_rport_init(lport);
-	fc_disc_init(lport);
+	fc_disc_init(lport, lport);
 	return 0;
 }
 
diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index 08c3bc398da2..ba2f977a6e1d 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -2826,6 +2826,8 @@ unlock:
 int fcoe_libfc_config(struct fc_lport *lport, struct fcoe_ctlr *fip,
 		      const struct libfc_function_template *tt, int init_fcp)
 {
+	void *priv = lport;
+
 	/* Set the function pointers set by the LLDD */
 	memcpy(&lport->tt, tt, sizeof(*tt));
 	if (init_fcp && fc_fcp_init(lport))
@@ -2842,12 +2844,11 @@ int fcoe_libfc_config(struct fc_lport *lport, struct fcoe_ctlr *fip,
 		lport->tt.disc_start = fcoe_ctlr_disc_start;
 		lport->tt.disc_stop = fcoe_ctlr_disc_stop;
 		lport->tt.disc_stop_final = fcoe_ctlr_disc_stop_final;
-		mutex_init(&lport->disc.disc_mutex);
-		INIT_LIST_HEAD(&lport->disc.rports);
-		lport->disc.priv = fip;
-	} else {
-		fc_disc_init(lport);
+		priv = fip;
 	}
+
+	fc_disc_init(lport, priv);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(fcoe_libfc_config);
diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c
index 8e561e6a557c..141c54b97082 100644
--- a/drivers/scsi/libfc/fc_disc.c
+++ b/drivers/scsi/libfc/fc_disc.c
@@ -714,8 +714,9 @@ static void fc_disc_stop_final(struct fc_lport *lport)
 /**
  * fc_disc_init() - Initialize the discovery layer for a local port
  * @lport: The local port that needs the discovery layer to be initialized
+ * @priv: Private data structre for users of the discovery layer
  */
-int fc_disc_init(struct fc_lport *lport)
+int fc_disc_init(struct fc_lport *lport, void *priv)
 {
 	struct fc_disc *disc;
 
@@ -736,7 +737,7 @@ int fc_disc_init(struct fc_lport *lport)
 	mutex_init(&disc->disc_mutex);
 	INIT_LIST_HEAD(&disc->rports);
 
-	disc->priv = lport;
+	disc->priv = priv;
 
 	return 0;
 }
diff --git a/include/scsi/libfc.h b/include/scsi/libfc.h
index 399162b50a8d..add2a498bd44 100644
--- a/include/scsi/libfc.h
+++ b/include/scsi/libfc.h
@@ -1074,7 +1074,7 @@ void fc_rport_terminate_io(struct fc_rport *);
 /*
  * DISCOVERY LAYER
  *****************************/
-int fc_disc_init(struct fc_lport *);
+int fc_disc_init(struct fc_lport *, void *);
 
 static inline struct fc_lport *fc_disc_lport(struct fc_disc *disc)
 {
-- 
cgit v1.2.3


From 0807619d3c64d935c257a377ac86982c777f969c Mon Sep 17 00:00:00 2001
From: Robert Love <robert.w.love@intel.com>
Date: Mon, 25 Mar 2013 11:00:28 -0700
Subject: libfc, fcoe, bnx2fc: Split fc_disc_init into fc_disc_{init, config}

Split discovery initialization in code that is setup once (fcoe_disc_init)
and code that can be re-configured (fcoe_disc_config).

Signed-off-by: Robert Love <robert.w.love@intel.com>
Tested-by: Jack Morgan <jack.morgan@intel.com>
Reviewed-by: Bhanu Prakash Gollapudi <bprakash@broadcom.com>
---
 drivers/scsi/bnx2fc/bnx2fc_fcoe.c |  3 ++-
 drivers/scsi/fcoe/fcoe_ctlr.c     |  3 ++-
 drivers/scsi/libfc/fc_disc.c      | 25 +++++++++++++++++--------
 include/scsi/libfc.h              |  3 ++-
 4 files changed, 23 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index b867b1bfa908..90bc7bd00966 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -939,7 +939,8 @@ static int bnx2fc_libfc_config(struct fc_lport *lport)
 	fc_elsct_init(lport);
 	fc_exch_init(lport);
 	fc_rport_init(lport);
-	fc_disc_init(lport, lport);
+	fc_disc_init(lport);
+	fc_disc_config(lport, lport);
 	return 0;
 }
 
diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index ba2f977a6e1d..34ee56cf4bcc 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -2847,7 +2847,8 @@ int fcoe_libfc_config(struct fc_lport *lport, struct fcoe_ctlr *fip,
 		priv = fip;
 	}
 
-	fc_disc_init(lport, priv);
+	fc_disc_init(lport);
+	fc_disc_config(lport, priv);
 
 	return 0;
 }
diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c
index 141c54b97082..880a9068ca12 100644
--- a/drivers/scsi/libfc/fc_disc.c
+++ b/drivers/scsi/libfc/fc_disc.c
@@ -712,13 +712,13 @@ static void fc_disc_stop_final(struct fc_lport *lport)
 }
 
 /**
- * fc_disc_init() - Initialize the discovery layer for a local port
- * @lport: The local port that needs the discovery layer to be initialized
+ * fc_disc_config() - Configure the discovery layer for a local port
+ * @lport: The local port that needs the discovery layer to be configured
  * @priv: Private data structre for users of the discovery layer
  */
-int fc_disc_init(struct fc_lport *lport, void *priv)
+void fc_disc_config(struct fc_lport *lport, void *priv)
 {
-	struct fc_disc *disc;
+	struct fc_disc *disc = &lport->disc;
 
 	if (!lport->tt.disc_start)
 		lport->tt.disc_start = fc_disc_start;
@@ -733,12 +733,21 @@ int fc_disc_init(struct fc_lport *lport, void *priv)
 		lport->tt.disc_recv_req = fc_disc_recv_req;
 
 	disc = &lport->disc;
-	INIT_DELAYED_WORK(&disc->disc_work, fc_disc_timeout);
-	mutex_init(&disc->disc_mutex);
-	INIT_LIST_HEAD(&disc->rports);
 
 	disc->priv = priv;
+}
+EXPORT_SYMBOL(fc_disc_config);
 
-	return 0;
+/**
+ * fc_disc_init() - Initialize the discovery layer for a local port
+ * @lport: The local port that needs the discovery layer to be initialized
+ */
+void fc_disc_init(struct fc_lport *lport)
+{
+	struct fc_disc *disc = &lport->disc;
+
+	INIT_DELAYED_WORK(&disc->disc_work, fc_disc_timeout);
+	mutex_init(&disc->disc_mutex);
+	INIT_LIST_HEAD(&disc->rports);
 }
 EXPORT_SYMBOL(fc_disc_init);
diff --git a/include/scsi/libfc.h b/include/scsi/libfc.h
index add2a498bd44..e1379b4e8faf 100644
--- a/include/scsi/libfc.h
+++ b/include/scsi/libfc.h
@@ -1074,7 +1074,8 @@ void fc_rport_terminate_io(struct fc_rport *);
 /*
  * DISCOVERY LAYER
  *****************************/
-int fc_disc_init(struct fc_lport *, void *);
+void fc_disc_init(struct fc_lport *);
+void fc_disc_config(struct fc_lport *, void *);
 
 static inline struct fc_lport *fc_disc_lport(struct fc_disc *disc)
 {
-- 
cgit v1.2.3


From 330305cc4a6b0cb75c22fc01b8826f0ad755550f Mon Sep 17 00:00:00 2001
From: Pravin B Shelar <pshelar@nicira.com>
Date: Sun, 24 Mar 2013 17:36:29 +0000
Subject: ipv4: Fix ip-header identification for gso packets.

ip-header id needs to be incremented even if IP_DF flag is set.
This behaviour was changed in commit 490ab08127cebc25e3a26
(IP_GRE: Fix IP-Identification).

Following patch fixes it so that identification is always
incremented.

Reported-by: Cong Wang <amwang@redhat.com>
Signed-off-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipip.h | 16 ++++++----------
 net/ipv4/af_inet.c |  3 +--
 2 files changed, 7 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/ipip.h b/include/net/ipip.h
index fd19625ff99d..982141c15200 100644
--- a/include/net/ipip.h
+++ b/include/net/ipip.h
@@ -77,15 +77,11 @@ static inline void tunnel_ip_select_ident(struct sk_buff *skb,
 {
 	struct iphdr *iph = ip_hdr(skb);
 
-	if (iph->frag_off & htons(IP_DF))
-		iph->id	= 0;
-	else {
-		/* Use inner packet iph-id if possible. */
-		if (skb->protocol == htons(ETH_P_IP) && old_iph->id)
-			iph->id	= old_iph->id;
-		else
-			__ip_select_ident(iph, dst,
-					  (skb_shinfo(skb)->gso_segs ?: 1) - 1);
-	}
+	/* Use inner packet iph-id if possible. */
+	if (skb->protocol == htons(ETH_P_IP) && old_iph->id)
+		iph->id	= old_iph->id;
+	else
+		__ip_select_ident(iph, dst,
+				  (skb_shinfo(skb)->gso_segs ?: 1) - 1);
 }
 #endif
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 68f6a94f7661..c929d9c1c4b6 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1333,8 +1333,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 				iph->frag_off |= htons(IP_MF);
 			offset += (skb->len - skb->mac_len - iph->ihl * 4);
 		} else  {
-			if (!(iph->frag_off & htons(IP_DF)))
-				iph->id = htons(id++);
+			iph->id = htons(id++);
 		}
 		iph->tot_len = htons(skb->len - skb->mac_len);
 		iph->check = 0;
-- 
cgit v1.2.3


From fffe01f7a768d07cc50ace71abe28fbf2f786a43 Mon Sep 17 00:00:00 2001
From: Matthew Garrett <matthew.garrett@nebula.com>
Date: Tue, 26 Mar 2013 17:25:54 -0400
Subject: PCI: Add PCI ROM helper for platform-provided ROM images
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It turns out that some UEFI systems provide apparently an apparently valid
PCI ROM BAR that turns out to contain garbage, so the attempt in 547b52463
to prefer the ROM from the BAR actually breaks a different set of machines.
As Linus pointed out, the graphics drivers are probably in the best
position to make this judgement, so this basically reverts 547b52463 and
f9a37be0f and adds a new helper function. Followup patches will add support
to nouveau and radeon for probing this ROM source if they can't find a ROM
from some other source.

[bhelgaas: added reporter and bugzilla pointers, s/f4eb5ff05/547b52463]
Reference: https://bugzilla.redhat.com/show_bug.cgi?id=927451
Reference: http://lkml.kernel.org/r/kg69ef$vdb$1@ger.gmane.org
Reported-by: Mantas Mikulėnas <grawity@gmail.com>
Reported-by: Chris Murphy <bugzilla@colorremedies.com>
Signed-off-by: Matthew Garrett <matthew.garrett@nebula.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/rom.c   | 67 +++++++++++++++++++++++++----------------------------
 include/linux/pci.h |  1 +
 2 files changed, 32 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c
index b41ac7756a4b..c5d0a08a8747 100644
--- a/drivers/pci/rom.c
+++ b/drivers/pci/rom.c
@@ -100,27 +100,6 @@ size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size)
 	return min((size_t)(image - rom), size);
 }
 
-static loff_t pci_find_rom(struct pci_dev *pdev, size_t *size)
-{
-	struct resource *res = &pdev->resource[PCI_ROM_RESOURCE];
-	loff_t start;
-
-	/* assign the ROM an address if it doesn't have one */
-	if (res->parent == NULL && pci_assign_resource(pdev, PCI_ROM_RESOURCE))
-		return 0;
-	start = pci_resource_start(pdev, PCI_ROM_RESOURCE);
-	*size = pci_resource_len(pdev, PCI_ROM_RESOURCE);
-
-	if (*size == 0)
-		return 0;
-
-	/* Enable ROM space decodes */
-	if (pci_enable_rom(pdev))
-		return 0;
-
-	return start;
-}
-
 /**
  * pci_map_rom - map a PCI ROM to kernel space
  * @pdev: pointer to pci device struct
@@ -135,7 +114,7 @@ static loff_t pci_find_rom(struct pci_dev *pdev, size_t *size)
 void __iomem *pci_map_rom(struct pci_dev *pdev, size_t *size)
 {
 	struct resource *res = &pdev->resource[PCI_ROM_RESOURCE];
-	loff_t start = 0;
+	loff_t start;
 	void __iomem *rom;
 
 	/*
@@ -154,21 +133,21 @@ void __iomem *pci_map_rom(struct pci_dev *pdev, size_t *size)
 			return (void __iomem *)(unsigned long)
 				pci_resource_start(pdev, PCI_ROM_RESOURCE);
 		} else {
-			start = pci_find_rom(pdev, size);
-		}
-	}
+			/* assign the ROM an address if it doesn't have one */
+			if (res->parent == NULL &&
+			    pci_assign_resource(pdev,PCI_ROM_RESOURCE))
+				return NULL;
+			start = pci_resource_start(pdev, PCI_ROM_RESOURCE);
+			*size = pci_resource_len(pdev, PCI_ROM_RESOURCE);
+			if (*size == 0)
+				return NULL;
 
-	/*
-	 * Some devices may provide ROMs via a source other than the BAR
-	 */
-	if (!start && pdev->rom && pdev->romlen) {
-		*size = pdev->romlen;
-		return phys_to_virt(pdev->rom);
+			/* Enable ROM space decodes */
+			if (pci_enable_rom(pdev))
+				return NULL;
+		}
 	}
 
-	if (!start)
-		return NULL;
-
 	rom = ioremap(start, *size);
 	if (!rom) {
 		/* restore enable if ioremap fails */
@@ -202,8 +181,7 @@ void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom)
 	if (res->flags & (IORESOURCE_ROM_COPY | IORESOURCE_ROM_BIOS_COPY))
 		return;
 
-	if (!pdev->rom || !pdev->romlen)
-		iounmap(rom);
+	iounmap(rom);
 
 	/* Disable again before continuing, leave enabled if pci=rom */
 	if (!(res->flags & (IORESOURCE_ROM_ENABLE | IORESOURCE_ROM_SHADOW)))
@@ -227,7 +205,24 @@ void pci_cleanup_rom(struct pci_dev *pdev)
 	}
 }
 
+/**
+ * pci_platform_rom - provides a pointer to any ROM image provided by the
+ * platform
+ * @pdev: pointer to pci device struct
+ * @size: pointer to receive size of pci window over ROM
+ */
+void __iomem *pci_platform_rom(struct pci_dev *pdev, size_t *size)
+{
+	if (pdev->rom && pdev->romlen) {
+		*size = pdev->romlen;
+		return phys_to_virt((phys_addr_t)pdev->rom);
+	}
+
+	return NULL;
+}
+
 EXPORT_SYMBOL(pci_map_rom);
 EXPORT_SYMBOL(pci_unmap_rom);
 EXPORT_SYMBOL_GPL(pci_enable_rom);
 EXPORT_SYMBOL_GPL(pci_disable_rom);
+EXPORT_SYMBOL(pci_platform_rom);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 2461033a7987..710067f3618c 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -916,6 +916,7 @@ void pci_disable_rom(struct pci_dev *pdev);
 void __iomem __must_check *pci_map_rom(struct pci_dev *pdev, size_t *size);
 void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom);
 size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size);
+void __iomem __must_check *pci_platform_rom(struct pci_dev *pdev, size_t *size);
 
 /* Power management related routines */
 int pci_save_state(struct pci_dev *dev);
-- 
cgit v1.2.3


From 3151527ee007b73a0ebd296010f1c0454a919c7d Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 15 Mar 2013 01:45:51 -0700
Subject: userns:  Don't allow creation if the user is chrooted

Guarantee that the policy of which files may be access that is
established by setting the root directory will not be violated
by user namespaces by verifying that the root directory points
to the root of the mount namespace at the time of user namespace
creation.

Changing the root is a privileged operation, and as a matter of policy
it serves to limit unprivileged processes to files below the current
root directory.

For reasons of simplicity and comprehensibility the privilege to
change the root directory is gated solely on the CAP_SYS_CHROOT
capability in the user namespace.  Therefore when creating a user
namespace we must ensure that the policy of which files may be access
can not be violated by changing the root directory.

Anyone who runs a processes in a chroot and would like to use user
namespace can setup the same view of filesystems with a mount
namespace instead.  With this result that this is not a practical
limitation for using user namespaces.

Cc: stable@vger.kernel.org
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Reported-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 fs/namespace.c            | 24 ++++++++++++++++++++++++
 include/linux/fs_struct.h |  2 ++
 kernel/user_namespace.c   |  9 +++++++++
 3 files changed, 35 insertions(+)

(limited to 'include')

diff --git a/fs/namespace.c b/fs/namespace.c
index 50ca17d3cb45..a3035223d421 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2732,6 +2732,30 @@ bool our_mnt(struct vfsmount *mnt)
 	return check_mnt(real_mount(mnt));
 }
 
+bool current_chrooted(void)
+{
+	/* Does the current process have a non-standard root */
+	struct path ns_root;
+	struct path fs_root;
+	bool chrooted;
+
+	/* Find the namespace root */
+	ns_root.mnt = &current->nsproxy->mnt_ns->root->mnt;
+	ns_root.dentry = ns_root.mnt->mnt_root;
+	path_get(&ns_root);
+	while (d_mountpoint(ns_root.dentry) && follow_down_one(&ns_root))
+		;
+
+	get_fs_root(current->fs, &fs_root);
+
+	chrooted = !path_equal(&fs_root, &ns_root);
+
+	path_put(&fs_root);
+	path_put(&ns_root);
+
+	return chrooted;
+}
+
 static void *mntns_get(struct task_struct *task)
 {
 	struct mnt_namespace *ns = NULL;
diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h
index 729eded4b24f..2b93a9a5a1e6 100644
--- a/include/linux/fs_struct.h
+++ b/include/linux/fs_struct.h
@@ -50,4 +50,6 @@ static inline void get_fs_root_and_pwd(struct fs_struct *fs, struct path *root,
 	spin_unlock(&fs->lock);
 }
 
+extern bool current_chrooted(void);
+
 #endif /* _LINUX_FS_STRUCT_H */
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index b14f4d342043..0f1e42884577 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -61,6 +61,15 @@ int create_user_ns(struct cred *new)
 	kgid_t group = new->egid;
 	int ret;
 
+	/*
+	 * Verify that we can not violate the policy of which files
+	 * may be accessed that is specified by the root directory,
+	 * by verifing that the root directory is at the root of the
+	 * mount namespace which allows all files to be accessed.
+	 */
+	if (current_chrooted())
+		return -EPERM;
+
 	/* The creator needs a mapping in the parent user namespace
 	 * or else we won't be able to reasonably tell userspace who
 	 * created a user_namespace.
-- 
cgit v1.2.3


From 90563b198e4c6674c63672fae1923da467215f45 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Fri, 22 Mar 2013 03:10:15 -0700
Subject: vfs: Add a mount flag to lock read only bind mounts

When a read-only bind mount is copied from mount namespace in a higher
privileged user namespace to a mount namespace in a lesser privileged
user namespace, it should not be possible to remove the the read-only
restriction.

Add a MNT_LOCK_READONLY mount flag to indicate that a mount must
remain read-only.

CC: stable@vger.kernel.org
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 fs/namespace.c        | 3 +++
 include/linux/mount.h | 2 ++
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/fs/namespace.c b/fs/namespace.c
index a3035223d421..8505b5ece5de 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1713,6 +1713,9 @@ static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
 	if (readonly_request == __mnt_is_readonly(mnt))
 		return 0;
 
+	if (mnt->mnt_flags & MNT_LOCK_READONLY)
+		return -EPERM;
+
 	if (readonly_request)
 		error = mnt_make_readonly(real_mount(mnt));
 	else
diff --git a/include/linux/mount.h b/include/linux/mount.h
index d7029f4a191a..73005f9957ea 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -47,6 +47,8 @@ struct mnt_namespace;
 
 #define MNT_INTERNAL	0x4000
 
+#define MNT_LOCK_READONLY	0x400000
+
 struct vfsmount {
 	struct dentry *mnt_root;	/* root of the mounted tree */
 	struct super_block *mnt_sb;	/* pointer to superblock */
-- 
cgit v1.2.3


From 87a8ebd637dafc255070f503909a053cf0d98d3f Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Sun, 24 Mar 2013 14:28:27 -0700
Subject: userns: Restrict when proc and sysfs can be mounted

Only allow unprivileged mounts of proc and sysfs if they are already
mounted when the user namespace is created.

proc and sysfs are interesting because they have content that is
per namespace, and so fresh mounts are needed when new namespaces
are created while at the same time proc and sysfs have content that
is shared between every instance.

Respect the policy of who may see the shared content of proc and sysfs
by only allowing new mounts if there was an existing mount at the time
the user namespace was created.

In practice there are only two interesting cases: proc and sysfs are
mounted at their usual places, proc and sysfs are not mounted at all
(some form of mount namespace jail).

Cc: stable@vger.kernel.org
Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
---
 fs/namespace.c                 | 21 +++++++++++++++++++++
 fs/proc/root.c                 |  4 ++++
 fs/sysfs/mount.c               |  4 ++++
 include/linux/user_namespace.h |  4 ++++
 kernel/user.c                  |  2 ++
 kernel/user_namespace.c        |  2 ++
 6 files changed, 37 insertions(+)

(limited to 'include')

diff --git a/fs/namespace.c b/fs/namespace.c
index 968d4c5eae03..d581e45c0a9f 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2763,6 +2763,27 @@ bool current_chrooted(void)
 	return chrooted;
 }
 
+void update_mnt_policy(struct user_namespace *userns)
+{
+	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
+	struct mount *mnt;
+
+	down_read(&namespace_sem);
+	list_for_each_entry(mnt, &ns->list, mnt_list) {
+		switch (mnt->mnt.mnt_sb->s_magic) {
+		case SYSFS_MAGIC:
+			userns->may_mount_sysfs = true;
+			break;
+		case PROC_SUPER_MAGIC:
+			userns->may_mount_proc = true;
+			break;
+		}
+		if (userns->may_mount_sysfs && userns->may_mount_proc)
+			break;
+	}
+	up_read(&namespace_sem);
+}
+
 static void *mntns_get(struct task_struct *task)
 {
 	struct mnt_namespace *ns = NULL;
diff --git a/fs/proc/root.c b/fs/proc/root.c
index c6e9fac26bac..9c7fab1d23f0 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -16,6 +16,7 @@
 #include <linux/sched.h>
 #include <linux/module.h>
 #include <linux/bitops.h>
+#include <linux/user_namespace.h>
 #include <linux/mount.h>
 #include <linux/pid_namespace.h>
 #include <linux/parser.h>
@@ -108,6 +109,9 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
 	} else {
 		ns = task_active_pid_ns(current);
 		options = data;
+
+		if (!current_user_ns()->may_mount_proc)
+			return ERR_PTR(-EPERM);
 	}
 
 	sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns);
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 8d924b5ec733..afd83273e6ce 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -19,6 +19,7 @@
 #include <linux/module.h>
 #include <linux/magic.h>
 #include <linux/slab.h>
+#include <linux/user_namespace.h>
 
 #include "sysfs.h"
 
@@ -111,6 +112,9 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
 	struct super_block *sb;
 	int error;
 
+	if (!(flags & MS_KERNMOUNT) && !current_user_ns()->may_mount_sysfs)
+		return ERR_PTR(-EPERM);
+
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info)
 		return ERR_PTR(-ENOMEM);
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 4ce009324933..b6b215f13b45 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -26,6 +26,8 @@ struct user_namespace {
 	kuid_t			owner;
 	kgid_t			group;
 	unsigned int		proc_inum;
+	bool			may_mount_sysfs;
+	bool			may_mount_proc;
 };
 
 extern struct user_namespace init_user_ns;
@@ -82,4 +84,6 @@ static inline void put_user_ns(struct user_namespace *ns)
 
 #endif
 
+void update_mnt_policy(struct user_namespace *userns);
+
 #endif /* _LINUX_USER_H */
diff --git a/kernel/user.c b/kernel/user.c
index e81978e8c03b..8e635a18ab52 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -51,6 +51,8 @@ struct user_namespace init_user_ns = {
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
 	.proc_inum = PROC_USER_INIT_INO,
+	.may_mount_sysfs = true,
+	.may_mount_proc = true,
 };
 EXPORT_SYMBOL_GPL(init_user_ns);
 
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 0f1e42884577..a54f26f82eb2 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -96,6 +96,8 @@ int create_user_ns(struct cred *new)
 
 	set_cred_user_ns(new, ns);
 
+	update_mnt_policy(ns);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 24f11a5cf538a8fcc10d61f457e9a2094fb965b4 Mon Sep 17 00:00:00 2001
From: Dmitry Kravkov <dmitry@broadcom.com>
Date: Wed, 27 Mar 2013 06:54:00 +0000
Subject: line up comment for ndo_bridge_getlink

Signed-off-by: Dmitry Kravkov <dmitry@broadcom.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')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b3d00fa4b314..8bfa95600e48 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -895,7 +895,7 @@ struct netdev_fcoe_hbainfo {
  *
  * int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh)
  * int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq,
- *			     struct net_device *dev)
+ *			     struct net_device *dev, u32 filter_mask)
  *
  * int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier);
  *	Called to change device carrier. Soft-devices (like dummy, team, etc)
-- 
cgit v1.2.3


From 09a9f1d27892255cfb9c91203f19476765e2d8d1 Mon Sep 17 00:00:00 2001
From: Michel Lespinasse <walken@google.com>
Date: Thu, 28 Mar 2013 16:26:23 -0700
Subject: Revert "mm: introduce VM_POPULATE flag to better deal with racy
 userspace programs"

This reverts commit 186930500985 ("mm: introduce VM_POPULATE flag to
better deal with racy userspace programs").

VM_POPULATE only has any effect when userspace plays racy games with
vmas by trying to unmap and remap memory regions that mmap or mlock are
operating on.

Also, the only effect of VM_POPULATE when userspace plays such games is
that it avoids populating new memory regions that get remapped into the
address range that was being operated on by the original mmap or mlock
calls.

Let's remove VM_POPULATE as there isn't any strong argument to mandate a
new vm_flag.

Signed-off-by: Michel Lespinasse <walken@google.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h   |  1 -
 include/linux/mman.h |  4 +---
 mm/fremap.c          | 12 ++----------
 mm/mlock.c           | 11 +++++------
 mm/mmap.c            |  4 +++-
 5 files changed, 11 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7acc9dc73c9f..e19ff30ad0a2 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -87,7 +87,6 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_PFNMAP	0x00000400	/* Page-ranges managed without "struct page", just pure PFN */
 #define VM_DENYWRITE	0x00000800	/* ETXTBSY on write attempts.. */
 
-#define VM_POPULATE     0x00001000
 #define VM_LOCKED	0x00002000
 #define VM_IO           0x00004000	/* Memory mapped I/O or similar */
 
diff --git a/include/linux/mman.h b/include/linux/mman.h
index 61c7a87e5d2b..9aa863da287f 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -79,8 +79,6 @@ calc_vm_flag_bits(unsigned long flags)
 {
 	return _calc_vm_trans(flags, MAP_GROWSDOWN,  VM_GROWSDOWN ) |
 	       _calc_vm_trans(flags, MAP_DENYWRITE,  VM_DENYWRITE ) |
-	       ((flags & MAP_LOCKED) ? (VM_LOCKED | VM_POPULATE) : 0) |
-	       (((flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE) ?
-							VM_POPULATE : 0);
+	       _calc_vm_trans(flags, MAP_LOCKED,     VM_LOCKED    );
 }
 #endif /* _LINUX_MMAN_H */
diff --git a/mm/fremap.c b/mm/fremap.c
index 4723ac8d2fc2..87da3590c61e 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -204,10 +204,8 @@ get_write_lock:
 			unsigned long addr;
 			struct file *file = get_file(vma->vm_file);
 
-			vm_flags = vma->vm_flags;
-			if (!(flags & MAP_NONBLOCK))
-				vm_flags |= VM_POPULATE;
-			addr = mmap_region(file, start, size, vm_flags, pgoff);
+			addr = mmap_region(file, start, size,
+					vma->vm_flags, pgoff);
 			fput(file);
 			if (IS_ERR_VALUE(addr)) {
 				err = addr;
@@ -226,12 +224,6 @@ get_write_lock:
 		mutex_unlock(&mapping->i_mmap_mutex);
 	}
 
-	if (!(flags & MAP_NONBLOCK) && !(vma->vm_flags & VM_POPULATE)) {
-		if (!has_write_lock)
-			goto get_write_lock;
-		vma->vm_flags |= VM_POPULATE;
-	}
-
 	if (vma->vm_flags & VM_LOCKED) {
 		/*
 		 * drop PG_Mlocked flag for over-mapped range
diff --git a/mm/mlock.c b/mm/mlock.c
index 1c5e33fce639..79b7cf7d1bca 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -358,7 +358,7 @@ static int do_mlock(unsigned long start, size_t len, int on)
 
 		newflags = vma->vm_flags & ~VM_LOCKED;
 		if (on)
-			newflags |= VM_LOCKED | VM_POPULATE;
+			newflags |= VM_LOCKED;
 
 		tmp = vma->vm_end;
 		if (tmp > end)
@@ -418,8 +418,7 @@ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
 		 * range with the first VMA. Also, skip undesirable VMA types.
 		 */
 		nend = min(end, vma->vm_end);
-		if ((vma->vm_flags & (VM_IO | VM_PFNMAP | VM_POPULATE)) !=
-		    VM_POPULATE)
+		if (vma->vm_flags & (VM_IO | VM_PFNMAP))
 			continue;
 		if (nstart < vma->vm_start)
 			nstart = vma->vm_start;
@@ -492,9 +491,9 @@ static int do_mlockall(int flags)
 	struct vm_area_struct * vma, * prev = NULL;
 
 	if (flags & MCL_FUTURE)
-		current->mm->def_flags |= VM_LOCKED | VM_POPULATE;
+		current->mm->def_flags |= VM_LOCKED;
 	else
-		current->mm->def_flags &= ~(VM_LOCKED | VM_POPULATE);
+		current->mm->def_flags &= ~VM_LOCKED;
 	if (flags == MCL_FUTURE)
 		goto out;
 
@@ -503,7 +502,7 @@ static int do_mlockall(int flags)
 
 		newflags = vma->vm_flags & ~VM_LOCKED;
 		if (flags & MCL_CURRENT)
-			newflags |= VM_LOCKED | VM_POPULATE;
+			newflags |= VM_LOCKED;
 
 		/* Ignore errors */
 		mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
diff --git a/mm/mmap.c b/mm/mmap.c
index 2664a47cec93..6466699b16cb 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1306,7 +1306,9 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 	}
 
 	addr = mmap_region(file, addr, len, vm_flags, pgoff);
-	if (!IS_ERR_VALUE(addr) && (vm_flags & VM_POPULATE))
+	if (!IS_ERR_VALUE(addr) &&
+	    ((vm_flags & VM_LOCKED) ||
+	     (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE))
 		*populate = len;
 	return addr;
 }
-- 
cgit v1.2.3


From dbf520a9d7d4d5ba28d2947be11e34099a5e3e20 Mon Sep 17 00:00:00 2001
From: Paul Walmsley <paul@pwsan.com>
Date: Sun, 31 Mar 2013 00:04:40 +0000
Subject: Revert "lockdep: check that no locks held at freeze time"

This reverts commit 6aa9707099c4b25700940eb3d016f16c4434360d.

Commit 6aa9707099c4 ("lockdep: check that no locks held at freeze time")
causes problems with NFS root filesystems.  The failures were noticed on
OMAP2 and 3 boards during kernel init:

  [ BUG: swapper/0/1 still has locks held! ]
  3.9.0-rc3-00344-ga937536 #1 Not tainted
  -------------------------------------
  1 lock held by swapper/0/1:
   #0:  (&type->s_umount_key#13/1){+.+.+.}, at: [<c011e84c>] sget+0x248/0x574

  stack backtrace:
    rpc_wait_bit_killable
    __wait_on_bit
    out_of_line_wait_on_bit
    __rpc_execute
    rpc_run_task
    rpc_call_sync
    nfs_proc_get_root
    nfs_get_root
    nfs_fs_mount_common
    nfs_try_mount
    nfs_fs_mount
    mount_fs
    vfs_kern_mount
    do_mount
    sys_mount
    do_mount_root
    mount_root
    prepare_namespace
    kernel_init_freeable
    kernel_init

Although the rootfs mounts, the system is unstable.  Here's a transcript
from a PM test:

  http://www.pwsan.com/omap/testlogs/test_v3.9-rc3/20130317194234/pm/37xxevm/37xxevm_log.txt

Here's what the test log should look like:

  http://www.pwsan.com/omap/testlogs/test_v3.8/20130218214403/pm/37xxevm/37xxevm_log.txt

Mailing list discussion is here:

  http://lkml.org/lkml/2013/3/4/221

Deal with this for v3.9 by reverting the problem commit, until folks can
figure out the right long-term course of action.

Signed-off-by: Paul Walmsley <paul@pwsan.com>
Cc: Mandeep Singh Baines <msb@chromium.org>
Cc: Jeff Layton <jlayton@redhat.com>
Cc: Shawn Guo <shawn.guo@linaro.org>
Cc: <maciej.rutecki@gmail.com>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Ben Chan <benchan@chromium.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/debug_locks.h |  4 ++--
 include/linux/freezer.h     |  3 ---
 kernel/exit.c               |  2 +-
 kernel/lockdep.c            | 17 +++++++++--------
 4 files changed, 12 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h
index a975de1ff59f..3bd46f766751 100644
--- a/include/linux/debug_locks.h
+++ b/include/linux/debug_locks.h
@@ -51,7 +51,7 @@ struct task_struct;
 extern void debug_show_all_locks(void);
 extern void debug_show_held_locks(struct task_struct *task);
 extern void debug_check_no_locks_freed(const void *from, unsigned long len);
-extern void debug_check_no_locks_held(void);
+extern void debug_check_no_locks_held(struct task_struct *task);
 #else
 static inline void debug_show_all_locks(void)
 {
@@ -67,7 +67,7 @@ debug_check_no_locks_freed(const void *from, unsigned long len)
 }
 
 static inline void
-debug_check_no_locks_held(void)
+debug_check_no_locks_held(struct task_struct *task)
 {
 }
 #endif
diff --git a/include/linux/freezer.h b/include/linux/freezer.h
index 043a5cf8b5ba..e70df40d84f6 100644
--- a/include/linux/freezer.h
+++ b/include/linux/freezer.h
@@ -3,7 +3,6 @@
 #ifndef FREEZER_H_INCLUDED
 #define FREEZER_H_INCLUDED
 
-#include <linux/debug_locks.h>
 #include <linux/sched.h>
 #include <linux/wait.h>
 #include <linux/atomic.h>
@@ -49,8 +48,6 @@ extern void thaw_kernel_threads(void);
 
 static inline bool try_to_freeze(void)
 {
-	if (!(current->flags & PF_NOFREEZE))
-		debug_check_no_locks_held();
 	might_sleep();
 	if (likely(!freezing(current)))
 		return false;
diff --git a/kernel/exit.c b/kernel/exit.c
index 51e485ca9935..60bc027c61c3 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -835,7 +835,7 @@ void do_exit(long code)
 	/*
 	 * Make sure we are holding no locks:
 	 */
-	debug_check_no_locks_held();
+	debug_check_no_locks_held(tsk);
 	/*
 	 * We can do this unlocked here. The futex code uses this flag
 	 * just to verify whether the pi state cleanup has been done
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 259db207b5d9..8a0efac4f99d 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -4088,7 +4088,7 @@ void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len)
 }
 EXPORT_SYMBOL_GPL(debug_check_no_locks_freed);
 
-static void print_held_locks_bug(void)
+static void print_held_locks_bug(struct task_struct *curr)
 {
 	if (!debug_locks_off())
 		return;
@@ -4097,21 +4097,22 @@ static void print_held_locks_bug(void)
 
 	printk("\n");
 	printk("=====================================\n");
-	printk("[ BUG: %s/%d still has locks held! ]\n",
-	       current->comm, task_pid_nr(current));
+	printk("[ BUG: lock held at task exit time! ]\n");
 	print_kernel_ident();
 	printk("-------------------------------------\n");
-	lockdep_print_held_locks(current);
+	printk("%s/%d is exiting with locks still held!\n",
+		curr->comm, task_pid_nr(curr));
+	lockdep_print_held_locks(curr);
+
 	printk("\nstack backtrace:\n");
 	dump_stack();
 }
 
-void debug_check_no_locks_held(void)
+void debug_check_no_locks_held(struct task_struct *task)
 {
-	if (unlikely(current->lockdep_depth > 0))
-		print_held_locks_bug();
+	if (unlikely(task->lockdep_depth > 0))
+		print_held_locks_bug(task);
 }
-EXPORT_SYMBOL_GPL(debug_check_no_locks_held);
 
 void debug_show_all_locks(void)
 {
-- 
cgit v1.2.3


From 5faaa035ddc16d3d2e31c0bfc1c4756b6869dbcc Mon Sep 17 00:00:00 2001
From: Rajagopal Venkat <rajagopal.venkat@linaro.org>
Date: Thu, 21 Mar 2013 13:28:25 +0000
Subject: PM / devfreq: Fix compiler warnings for CONFIG_PM_DEVFREQ unset

Fix compiler warnings generated when devfreq is not enabled
(CONFIG_PM_DEVFREQ is not set).

Signed-off-by: Rajagopal Venkat <rajagopal.venkat@linaro.org>
Acked-by: MyungJoo Ham <myungjoo.ham@samsung.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/devfreq.h | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index e83ef39b3bea..fe8c4476f7e4 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -213,7 +213,7 @@ struct devfreq_simple_ondemand_data {
 #endif
 
 #else /* !CONFIG_PM_DEVFREQ */
-static struct devfreq *devfreq_add_device(struct device *dev,
+static inline struct devfreq *devfreq_add_device(struct device *dev,
 					  struct devfreq_dev_profile *profile,
 					  const char *governor_name,
 					  void *data)
@@ -221,34 +221,34 @@ static struct devfreq *devfreq_add_device(struct device *dev,
 	return NULL;
 }
 
-static int devfreq_remove_device(struct devfreq *devfreq)
+static inline int devfreq_remove_device(struct devfreq *devfreq)
 {
 	return 0;
 }
 
-static int devfreq_suspend_device(struct devfreq *devfreq)
+static inline int devfreq_suspend_device(struct devfreq *devfreq)
 {
 	return 0;
 }
 
-static int devfreq_resume_device(struct devfreq *devfreq)
+static inline int devfreq_resume_device(struct devfreq *devfreq)
 {
 	return 0;
 }
 
-static struct opp *devfreq_recommended_opp(struct device *dev,
+static inline struct opp *devfreq_recommended_opp(struct device *dev,
 					   unsigned long *freq, u32 flags)
 {
-	return -EINVAL;
+	return ERR_PTR(-EINVAL);
 }
 
-static int devfreq_register_opp_notifier(struct device *dev,
+static inline int devfreq_register_opp_notifier(struct device *dev,
 					 struct devfreq *devfreq)
 {
 	return -EINVAL;
 }
 
-static int devfreq_unregister_opp_notifier(struct device *dev,
+static inline int devfreq_unregister_opp_notifier(struct device *dev,
 					   struct devfreq *devfreq)
 {
 	return -EINVAL;
-- 
cgit v1.2.3


From d8668fcb0b257d9fdcfbe5c172a99b8d85e1cd82 Mon Sep 17 00:00:00 2001
From: Shan Hai <shan.hai@windriver.com>
Date: Mon, 18 Mar 2013 10:30:43 +0800
Subject: libata: Use integer return value for atapi_command_packet_set

The function returns type of ATAPI drives so it should return integer value.
The commit 4dce8ba94c7 (libata: Use 'bool' return value for ata_id_XXX) since
v2.6.39 changed the type of return value from int to bool, the change would
cause all of the ATAPI class drives to be treated as TYPE_TAPE and the
max_sectors of the drives to be set to 65535 because of the commit
f8d8e5799b7(libata: increase 128 KB / cmd limit for ATAPI tape drives), for the
function would return true for all ATAPI class drives and the TYPE_TAPE is
defined as 0x01.

Cc: stable@vger.kernel.org
Signed-off-by: Shan Hai <shan.hai@windriver.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
---
 include/linux/ata.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ata.h b/include/linux/ata.h
index 8f7a3d68371a..ee0bd9524055 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -954,7 +954,7 @@ static inline int atapi_cdb_len(const u16 *dev_id)
 	}
 }
 
-static inline bool atapi_command_packet_set(const u16 *dev_id)
+static inline int atapi_command_packet_set(const u16 *dev_id)
 {
 	return (dev_id[ATA_ID_CONFIG] >> 8) & 0x1f;
 }
-- 
cgit v1.2.3


From a32450e127fc6e5ca6d958ceb3cfea4d30a00846 Mon Sep 17 00:00:00 2001
From: Shan Hai <shan.hai@windriver.com>
Date: Mon, 18 Mar 2013 10:30:44 +0800
Subject: libata: Set max sector to 65535 for Slimtype DVD A DS8A8SH drive

The Slimtype DVD A  DS8A8SH drive locks up when max sector is smaller than
65535, and the blow backtrace is observed on locking up:

INFO: task flush-8:32:1130 blocked for more than 120 seconds.
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
flush-8:32      D ffffffff8180cf60     0  1130      2 0x00000000
 ffff880273aef618 0000000000000046 0000000000000005 ffff880273aee000
 ffff880273aee000 ffff880273aeffd8 ffff880273aee010 ffff880273aee000
 ffff880273aeffd8 ffff880273aee000 ffff88026e842ea0 ffff880274a10000
Call Trace:
 [<ffffffff8168fc2d>] schedule+0x5d/0x70
 [<ffffffff8168fccc>] io_schedule+0x8c/0xd0
 [<ffffffff81324461>] get_request+0x731/0x7d0
 [<ffffffff8133dc60>] ? cfq_allow_merge+0x50/0x90
 [<ffffffff81083aa0>] ? wake_up_bit+0x40/0x40
 [<ffffffff81320443>] ? bio_attempt_back_merge+0x33/0x110
 [<ffffffff813248ea>] blk_queue_bio+0x23a/0x3f0
 [<ffffffff81322176>] generic_make_request+0xc6/0x120
 [<ffffffff81322308>] submit_bio+0x138/0x160
 [<ffffffff811d7596>] ? bio_alloc_bioset+0x96/0x120
 [<ffffffff811d1f61>] submit_bh+0x1f1/0x220
 [<ffffffff811d48b8>] __block_write_full_page+0x228/0x340
 [<ffffffff811d3650>] ? attach_nobh_buffers+0xc0/0xc0
 [<ffffffff811d8960>] ? I_BDEV+0x10/0x10
 [<ffffffff811d8960>] ? I_BDEV+0x10/0x10
 [<ffffffff811d4ab6>] block_write_full_page_endio+0xe6/0x100
 [<ffffffff811d4ae5>] block_write_full_page+0x15/0x20
 [<ffffffff811d9268>] blkdev_writepage+0x18/0x20
 [<ffffffff81142527>] __writepage+0x17/0x40
 [<ffffffff811438ba>] write_cache_pages+0x34a/0x4a0
 [<ffffffff81142510>] ? set_page_dirty+0x70/0x70
 [<ffffffff81143a61>] generic_writepages+0x51/0x80
 [<ffffffff81143ab0>] do_writepages+0x20/0x50
 [<ffffffff811c9ed6>] __writeback_single_inode+0xa6/0x2b0
 [<ffffffff811ca861>] writeback_sb_inodes+0x311/0x4d0
 [<ffffffff811caaa6>] __writeback_inodes_wb+0x86/0xd0
 [<ffffffff811cad43>] wb_writeback+0x1a3/0x330
 [<ffffffff816916cf>] ? _raw_spin_lock_irqsave+0x3f/0x50
 [<ffffffff811b8362>] ? get_nr_inodes+0x52/0x70
 [<ffffffff811cb0ac>] wb_do_writeback+0x1dc/0x260
 [<ffffffff8168dd34>] ? schedule_timeout+0x204/0x240
 [<ffffffff811cb232>] bdi_writeback_thread+0x102/0x2b0
 [<ffffffff811cb130>] ? wb_do_writeback+0x260/0x260
 [<ffffffff81083550>] kthread+0xc0/0xd0
 [<ffffffff81083490>] ? kthread_worker_fn+0x1b0/0x1b0
 [<ffffffff8169a3ec>] ret_from_fork+0x7c/0xb0
 [<ffffffff81083490>] ? kthread_worker_fn+0x1b0/0x1b0

 The above trace was triggered by
   "dd if=/dev/zero of=/dev/sr0 bs=2048 count=32768"

 It was previously working by accident, since another bug introduced
 by 4dce8ba94c7 (libata: Use 'bool' return value for ata_id_XXX) caused
 all drives to use maxsect=65535.

Cc: stable@vger.kernel.org
Signed-off-by: Shan Hai <shan.hai@windriver.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
---
 drivers/ata/libata-core.c | 4 ++++
 include/linux/libata.h    | 1 +
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 497adea1f0d6..0075944a64dc 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2439,6 +2439,9 @@ int ata_dev_configure(struct ata_device *dev)
 		dev->max_sectors = min_t(unsigned int, ATA_MAX_SECTORS_128,
 					 dev->max_sectors);
 
+	if (dev->horkage & ATA_HORKAGE_MAX_SEC_LBA48)
+		dev->max_sectors = ATA_MAX_SECTORS_LBA48;
+
 	if (ap->ops->dev_config)
 		ap->ops->dev_config(dev);
 
@@ -4100,6 +4103,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	/* Weird ATAPI devices */
 	{ "TORiSAN DVD-ROM DRD-N216", NULL,	ATA_HORKAGE_MAX_SEC_128 },
 	{ "QUANTUM DAT    DAT72-000", NULL,	ATA_HORKAGE_ATAPI_MOD16_DMA },
+	{ "Slimtype DVD A  DS8A8SH", NULL,	ATA_HORKAGE_MAX_SEC_LBA48 },
 
 	/* Devices we expect to fail diagnostics */
 
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 91c9d109e5f1..eae7a053dc51 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -398,6 +398,7 @@ enum {
 	ATA_HORKAGE_NOSETXFER	= (1 << 14),	/* skip SETXFER, SATA only */
 	ATA_HORKAGE_BROKEN_FPDMA_AA	= (1 << 15),	/* skip AA */
 	ATA_HORKAGE_DUMP_ID	= (1 << 16),	/* dump IDENTIFY data */
+	ATA_HORKAGE_MAX_SEC_LBA48 = (1 << 17),	/* Set max sects to 65535 */
 
 	 /* DMA mask for user DMA control: User visible values; DO NOT
 	    renumber */
-- 
cgit v1.2.3


From 4543fbefe6e06a9e40d9f2b28d688393a299f079 Mon Sep 17 00:00:00 2001
From: Vlad Yasevich <vyasevic@redhat.com>
Date: Tue, 2 Apr 2013 17:10:07 -0400
Subject: net: count hw_addr syncs so that unsync works properly.

A few drivers use dev_uc_sync/unsync to synchronize the
address lists from master down to slave/lower devices.  In
some cases (bond/team) a single address list is synched down
to multiple devices.  At the time of unsync, we have a leak
in these lower devices, because "synced" is treated as a
boolean and the address will not be unsynced for anything after
the first device/call.

Treat "synced" as a count (same as refcount) and allow all
unsync calls to work.

Signed-off-by: Vlad Yasevich <vyasevic@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 2 +-
 net/core/dev_addr_lists.c | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 8bfa95600e48..6151e903eef0 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -210,9 +210,9 @@ struct netdev_hw_addr {
 #define NETDEV_HW_ADDR_T_SLAVE		3
 #define NETDEV_HW_ADDR_T_UNICAST	4
 #define NETDEV_HW_ADDR_T_MULTICAST	5
-	bool			synced;
 	bool			global_use;
 	int			refcount;
+	int			synced;
 	struct rcu_head		rcu_head;
 };
 
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index bd2eb9d3e369..abdc9e6ef33e 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -37,7 +37,7 @@ static int __hw_addr_create_ex(struct netdev_hw_addr_list *list,
 	ha->type = addr_type;
 	ha->refcount = 1;
 	ha->global_use = global;
-	ha->synced = false;
+	ha->synced = 0;
 	list_add_tail_rcu(&ha->list, &list->list);
 	list->count++;
 
@@ -165,7 +165,7 @@ int __hw_addr_sync(struct netdev_hw_addr_list *to_list,
 					    addr_len, ha->type);
 			if (err)
 				break;
-			ha->synced = true;
+			ha->synced++;
 			ha->refcount++;
 		} else if (ha->refcount == 1) {
 			__hw_addr_del(to_list, ha->addr, addr_len, ha->type);
@@ -186,7 +186,7 @@ void __hw_addr_unsync(struct netdev_hw_addr_list *to_list,
 		if (ha->synced) {
 			__hw_addr_del(to_list, ha->addr,
 				      addr_len, ha->type);
-			ha->synced = false;
+			ha->synced--;
 			__hw_addr_del(from_list, ha->addr,
 				      addr_len, ha->type);
 		}
-- 
cgit v1.2.3


From 124dff01afbdbff251f0385beca84ba1b9adda68 Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Fri, 5 Apr 2013 20:42:05 +0200
Subject: netfilter: don't reset nf_trace in nf_reset()

Commit 130549fe ("netfilter: reset nf_trace in nf_reset") added code
to reset nf_trace in nf_reset(). This is wrong and unnecessary.

nf_reset() is used in the following cases:

- when passing packets up the the socket layer, at which point we want to
  release all netfilter references that might keep modules pinned while
  the packet is queued. nf_trace doesn't matter anymore at this point.

- when encapsulating or decapsulating IPsec packets. We want to continue
  tracing these packets after IPsec processing.

- when passing packets through virtual network devices. Only devices on
  that encapsulate in IPv4/v6 matter since otherwise nf_trace is not
  used anymore. Its not entirely clear whether those packets should
  be traced after that, however we've always done that.

- when passing packets through virtual network devices that make the
  packet cross network namespace boundaries. This is the only cases
  where we clearly want to reset nf_trace and is also what the
  original patch intended to fix.

Add a new function nf_reset_trace() and use it in dev_forward_skb() to
fix this properly.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 4 ++++
 net/core/dev.c         | 1 +
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 72b396751de7..b8292d8cc9fa 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2641,6 +2641,10 @@ static inline void nf_reset(struct sk_buff *skb)
 	nf_bridge_put(skb->nf_bridge);
 	skb->nf_bridge = NULL;
 #endif
+}
+
+static inline void nf_reset_trace(struct sk_buff *skb)
+{
 #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
 	skb->nf_trace = 0;
 #endif
diff --git a/net/core/dev.c b/net/core/dev.c
index 13e6447f0398..e7d68ed8aafe 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1639,6 +1639,7 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 	skb->mark = 0;
 	secpath_reset(skb);
 	nf_reset(skb);
+	nf_reset_trace(skb);
 	return netif_rx(skb);
 }
 EXPORT_SYMBOL_GPL(dev_forward_skb);
-- 
cgit v1.2.3


From 8f964525a121f2ff2df948dac908dcc65be21b5b Mon Sep 17 00:00:00 2001
From: Andrew Honig <ahonig@google.com>
Date: Fri, 29 Mar 2013 09:35:21 -0700
Subject: KVM: Allow cross page reads and writes from cached translations.

This patch adds support for kvm_gfn_to_hva_cache_init functions for
reads and writes that will cross a page.  If the range falls within
the same memslot, then this will be a fast operation.  If the range
is split between two memslots, then the slower kvm_read_guest and
kvm_write_guest are used.

Tested: Test against kvm_clock unit tests.

Signed-off-by: Andrew Honig <ahonig@google.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>
---
 arch/x86/kvm/lapic.c      |  2 +-
 arch/x86/kvm/x86.c        | 13 ++++++-------
 include/linux/kvm_host.h  |  2 +-
 include/linux/kvm_types.h |  1 +
 virt/kvm/kvm_main.c       | 47 +++++++++++++++++++++++++++++++++++++----------
 5 files changed, 46 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 02b51dd4e4ad..f77df1c5de6e 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1857,7 +1857,7 @@ int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data)
 	if (!pv_eoi_enabled(vcpu))
 		return 0;
 	return kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_eoi.data,
-					 addr);
+					 addr, sizeof(u8));
 }
 
 void kvm_lapic_init(void)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f19ac0aca60d..e1721324c271 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1823,7 +1823,8 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 		return 0;
 	}
 
-	if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa))
+	if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa,
+					sizeof(u32)))
 		return 1;
 
 	vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);
@@ -1952,12 +1953,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 		gpa_offset = data & ~(PAGE_MASK | 1);
 
-		/* Check that the address is 32-byte aligned. */
-		if (gpa_offset & (sizeof(struct pvclock_vcpu_time_info) - 1))
-			break;
-
 		if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
-		     &vcpu->arch.pv_time, data & ~1ULL))
+		     &vcpu->arch.pv_time, data & ~1ULL,
+		     sizeof(struct pvclock_vcpu_time_info)))
 			vcpu->arch.pv_time_enabled = false;
 		else
 			vcpu->arch.pv_time_enabled = true;
@@ -1977,7 +1975,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 
 		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime,
-							data & KVM_STEAL_VALID_BITS))
+						data & KVM_STEAL_VALID_BITS,
+						sizeof(struct kvm_steal_time)))
 			return 1;
 
 		vcpu->arch.st.msr_val = data;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index cad77fe09d77..c13958251927 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -518,7 +518,7 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
 int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 			   void *data, unsigned long len);
 int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
-			      gpa_t gpa);
+			      gpa_t gpa, unsigned long len);
 int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len);
 int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len);
 struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index fa7cc7244cbd..b0bcce0ddc95 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -71,6 +71,7 @@ struct gfn_to_hva_cache {
 	u64 generation;
 	gpa_t gpa;
 	unsigned long hva;
+	unsigned long len;
 	struct kvm_memory_slot *memslot;
 };
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index adc68feb5c5a..f18013f09e68 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1541,21 +1541,38 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
 }
 
 int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
-			      gpa_t gpa)
+			      gpa_t gpa, unsigned long len)
 {
 	struct kvm_memslots *slots = kvm_memslots(kvm);
 	int offset = offset_in_page(gpa);
-	gfn_t gfn = gpa >> PAGE_SHIFT;
+	gfn_t start_gfn = gpa >> PAGE_SHIFT;
+	gfn_t end_gfn = (gpa + len - 1) >> PAGE_SHIFT;
+	gfn_t nr_pages_needed = end_gfn - start_gfn + 1;
+	gfn_t nr_pages_avail;
 
 	ghc->gpa = gpa;
 	ghc->generation = slots->generation;
-	ghc->memslot = gfn_to_memslot(kvm, gfn);
-	ghc->hva = gfn_to_hva_many(ghc->memslot, gfn, NULL);
-	if (!kvm_is_error_hva(ghc->hva))
+	ghc->len = len;
+	ghc->memslot = gfn_to_memslot(kvm, start_gfn);
+	ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, &nr_pages_avail);
+	if (!kvm_is_error_hva(ghc->hva) && nr_pages_avail >= nr_pages_needed) {
 		ghc->hva += offset;
-	else
-		return -EFAULT;
-
+	} else {
+		/*
+		 * If the requested region crosses two memslots, we still
+		 * verify that the entire region is valid here.
+		 */
+		while (start_gfn <= end_gfn) {
+			ghc->memslot = gfn_to_memslot(kvm, start_gfn);
+			ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn,
+						   &nr_pages_avail);
+			if (kvm_is_error_hva(ghc->hva))
+				return -EFAULT;
+			start_gfn += nr_pages_avail;
+		}
+		/* Use the slow path for cross page reads and writes. */
+		ghc->memslot = NULL;
+	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(kvm_gfn_to_hva_cache_init);
@@ -1566,8 +1583,13 @@ int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 	struct kvm_memslots *slots = kvm_memslots(kvm);
 	int r;
 
+	BUG_ON(len > ghc->len);
+
 	if (slots->generation != ghc->generation)
-		kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa);
+		kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa, ghc->len);
+
+	if (unlikely(!ghc->memslot))
+		return kvm_write_guest(kvm, ghc->gpa, data, len);
 
 	if (kvm_is_error_hva(ghc->hva))
 		return -EFAULT;
@@ -1587,8 +1609,13 @@ int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 	struct kvm_memslots *slots = kvm_memslots(kvm);
 	int r;
 
+	BUG_ON(len > ghc->len);
+
 	if (slots->generation != ghc->generation)
-		kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa);
+		kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa, ghc->len);
+
+	if (unlikely(!ghc->memslot))
+		return kvm_read_guest(kvm, ghc->gpa, data, len);
 
 	if (kvm_is_error_hva(ghc->hva))
 		return -EFAULT;
-- 
cgit v1.2.3


From 395b97a3aeff0b8d949ee3e67bf8c11c5ffd6861 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Wed, 27 Mar 2013 09:31:28 -0400
Subject: ftrace: Do not call stub functions in control loop

The function tracing control loop used by perf spits out a warning
if the called function is not a control function. This is because
the control function references a per cpu allocated data structure
on struct ftrace_ops that is not allocated for other types of
functions.

commit 0a016409e42 "ftrace: Optimize the function tracer list loop"

Had an optimization done to all function tracing loops to optimize
for a single registered ops. Unfortunately, this allows for a slight
race when tracing starts or ends, where the stub function might be
called after the current registered ops is removed. In this case we
get the following dump:

root# perf stat -e ftrace:function sleep 1
[   74.339105] WARNING: at include/linux/ftrace.h:209 ftrace_ops_control_func+0xde/0xf0()
[   74.349522] Hardware name: PRIMERGY RX200 S6
[   74.357149] Modules linked in: sg igb iTCO_wdt ptp pps_core iTCO_vendor_support i7core_edac dca lpc_ich i2c_i801 coretemp edac_core crc32c_intel mfd_core ghash_clmulni_intel dm_multipath acpi_power_meter pcspk
r microcode vhost_net tun macvtap macvlan nfsd kvm_intel kvm auth_rpcgss nfs_acl lockd sunrpc uinput xfs libcrc32c sd_mod crc_t10dif sr_mod cdrom mgag200 i2c_algo_bit drm_kms_helper ttm qla2xxx mptsas ahci drm li
bahci scsi_transport_sas mptscsih libata scsi_transport_fc i2c_core mptbase scsi_tgt dm_mirror dm_region_hash dm_log dm_mod
[   74.446233] Pid: 1377, comm: perf Tainted: G        W    3.9.0-rc1 #1
[   74.453458] Call Trace:
[   74.456233]  [<ffffffff81062e3f>] warn_slowpath_common+0x7f/0xc0
[   74.462997]  [<ffffffff810fbc60>] ? rcu_note_context_switch+0xa0/0xa0
[   74.470272]  [<ffffffff811041a2>] ? __unregister_ftrace_function+0xa2/0x1a0
[   74.478117]  [<ffffffff81062e9a>] warn_slowpath_null+0x1a/0x20
[   74.484681]  [<ffffffff81102ede>] ftrace_ops_control_func+0xde/0xf0
[   74.491760]  [<ffffffff8162f400>] ftrace_call+0x5/0x2f
[   74.497511]  [<ffffffff8162f400>] ? ftrace_call+0x5/0x2f
[   74.503486]  [<ffffffff8162f400>] ? ftrace_call+0x5/0x2f
[   74.509500]  [<ffffffff810fbc65>] ? synchronize_sched+0x5/0x50
[   74.516088]  [<ffffffff816254d5>] ? _cond_resched+0x5/0x40
[   74.522268]  [<ffffffff810fbc65>] ? synchronize_sched+0x5/0x50
[   74.528837]  [<ffffffff811041a2>] ? __unregister_ftrace_function+0xa2/0x1a0
[   74.536696]  [<ffffffff816254d5>] ? _cond_resched+0x5/0x40
[   74.542878]  [<ffffffff8162402d>] ? mutex_lock+0x1d/0x50
[   74.548869]  [<ffffffff81105c67>] unregister_ftrace_function+0x27/0x50
[   74.556243]  [<ffffffff8111eadf>] perf_ftrace_event_register+0x9f/0x140
[   74.563709]  [<ffffffff816254d5>] ? _cond_resched+0x5/0x40
[   74.569887]  [<ffffffff8162402d>] ? mutex_lock+0x1d/0x50
[   74.575898]  [<ffffffff8111e94e>] perf_trace_destroy+0x2e/0x50
[   74.582505]  [<ffffffff81127ba9>] tp_perf_event_destroy+0x9/0x10
[   74.589298]  [<ffffffff811295d0>] free_event+0x70/0x1a0
[   74.595208]  [<ffffffff8112a579>] perf_event_release_kernel+0x69/0xa0
[   74.602460]  [<ffffffff816254d5>] ? _cond_resched+0x5/0x40
[   74.608667]  [<ffffffff8112a640>] put_event+0x90/0xc0
[   74.614373]  [<ffffffff8112a740>] perf_release+0x10/0x20
[   74.620367]  [<ffffffff811a3044>] __fput+0xf4/0x280
[   74.625894]  [<ffffffff811a31de>] ____fput+0xe/0x10
[   74.631387]  [<ffffffff81083697>] task_work_run+0xa7/0xe0
[   74.637452]  [<ffffffff81014981>] do_notify_resume+0x71/0xb0
[   74.643843]  [<ffffffff8162fa92>] int_signal+0x12/0x17

To fix this a new ftrace_ops flag is added that denotes the ftrace_list_end
ftrace_ops stub as just that, a stub. This flag is now checked in the
control loop and the function is not called if the flag is set.

Thanks to Jovi for not just reporting the bug, but also pointing out
where the bug was in the code.

Link: http://lkml.kernel.org/r/514A8855.7090402@redhat.com
Link: http://lkml.kernel.org/r/1364377499-1900-15-git-send-email-jovi.zhangwei@huawei.com

Tested-by: WANG Chao <chaowang@redhat.com>
Reported-by: WANG Chao <chaowang@redhat.com>
Reported-by: zhangwei(Jovi) <jovi.zhangwei@huawei.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace.h | 2 ++
 kernel/trace/ftrace.c  | 5 +++--
 2 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index e5ca8ef50e9b..167abf907802 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -89,6 +89,7 @@ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
  *            that the call back has its own recursion protection. If it does
  *            not set this, then the ftrace infrastructure will add recursion
  *            protection for the caller.
+ * STUB   - The ftrace_ops is just a place holder.
  */
 enum {
 	FTRACE_OPS_FL_ENABLED			= 1 << 0,
@@ -98,6 +99,7 @@ enum {
 	FTRACE_OPS_FL_SAVE_REGS			= 1 << 4,
 	FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED	= 1 << 5,
 	FTRACE_OPS_FL_RECURSION_SAFE		= 1 << 6,
+	FTRACE_OPS_FL_STUB			= 1 << 7,
 };
 
 struct ftrace_ops {
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index cc4943c7ce6d..7e897106b7e0 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -66,7 +66,7 @@
 
 static struct ftrace_ops ftrace_list_end __read_mostly = {
 	.func		= ftrace_stub,
-	.flags		= FTRACE_OPS_FL_RECURSION_SAFE,
+	.flags		= FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_STUB,
 };
 
 /* ftrace_enabled is a method to turn ftrace on or off */
@@ -4131,7 +4131,8 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
 	preempt_disable_notrace();
 	trace_recursion_set(TRACE_CONTROL_BIT);
 	do_for_each_ftrace_op(op, ftrace_control_list) {
-		if (!ftrace_function_local_disabled(op) &&
+		if (!(op->flags & FTRACE_OPS_FL_STUB) &&
+		    !ftrace_function_local_disabled(op) &&
 		    ftrace_ops_test(op, ip))
 			op->func(ip, parent_ip, op, regs);
 	} while_for_each_ftrace_op(op);
-- 
cgit v1.2.3


From f9c41a62bba3f3f7ef3541b2a025e3371bcbba97 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ursula.braun@de.ibm.com>
Date: Sun, 7 Apr 2013 22:19:26 +0000
Subject: af_iucv: fix recvmsg by replacing skb_pull() function

When receiving data messages, the "BUG_ON(skb->len < skb->data_len)" in
the skb_pull() function triggers a kernel panic.

Replace the skb_pull logic by a per skb offset as advised by
Eric Dumazet.

Signed-off-by: Ursula Braun <ursula.braun@de.ibm.com>
Signed-off-by: Frank Blaschka <blaschka@linux.vnet.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/iucv/af_iucv.h |  8 ++++++++
 net/iucv/af_iucv.c         | 34 ++++++++++++++++------------------
 2 files changed, 24 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/net/iucv/af_iucv.h b/include/net/iucv/af_iucv.h
index cc7c19732389..714cc9a54a4c 100644
--- a/include/net/iucv/af_iucv.h
+++ b/include/net/iucv/af_iucv.h
@@ -130,6 +130,14 @@ struct iucv_sock {
 					       enum iucv_tx_notify n);
 };
 
+struct iucv_skb_cb {
+	u32	class;		/* target class of message */
+	u32	tag;		/* tag associated with message */
+	u32	offset;		/* offset for skb receival */
+};
+
+#define IUCV_SKB_CB(__skb)	((struct iucv_skb_cb *)&((__skb)->cb[0]))
+
 /* iucv socket options (SOL_IUCV) */
 #define SO_IPRMDATA_MSG	0x0080		/* send/recv IPRM_DATA msgs */
 #define SO_MSGLIMIT	0x1000		/* get/set IUCV MSGLIMIT */
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index bf6935820001..206ce6db2c36 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -49,12 +49,6 @@ static const u8 iprm_shutdown[8] =
 
 #define TRGCLS_SIZE	(sizeof(((struct iucv_message *)0)->class))
 
-/* macros to set/get socket control buffer at correct offset */
-#define CB_TAG(skb)	((skb)->cb)		/* iucv message tag */
-#define CB_TAG_LEN	(sizeof(((struct iucv_message *) 0)->tag))
-#define CB_TRGCLS(skb)	((skb)->cb + CB_TAG_LEN) /* iucv msg target class */
-#define CB_TRGCLS_LEN	(TRGCLS_SIZE)
-
 #define __iucv_sock_wait(sk, condition, timeo, ret)			\
 do {									\
 	DEFINE_WAIT(__wait);						\
@@ -1141,7 +1135,7 @@ static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 
 	/* increment and save iucv message tag for msg_completion cbk */
 	txmsg.tag = iucv->send_tag++;
-	memcpy(CB_TAG(skb), &txmsg.tag, CB_TAG_LEN);
+	IUCV_SKB_CB(skb)->tag = txmsg.tag;
 
 	if (iucv->transport == AF_IUCV_TRANS_HIPER) {
 		atomic_inc(&iucv->msg_sent);
@@ -1224,7 +1218,7 @@ static int iucv_fragment_skb(struct sock *sk, struct sk_buff *skb, int len)
 			return -ENOMEM;
 
 		/* copy target class to control buffer of new skb */
-		memcpy(CB_TRGCLS(nskb), CB_TRGCLS(skb), CB_TRGCLS_LEN);
+		IUCV_SKB_CB(nskb)->class = IUCV_SKB_CB(skb)->class;
 
 		/* copy data fragment */
 		memcpy(nskb->data, skb->data + copied, size);
@@ -1256,7 +1250,7 @@ static void iucv_process_message(struct sock *sk, struct sk_buff *skb,
 
 	/* store msg target class in the second 4 bytes of skb ctrl buffer */
 	/* Note: the first 4 bytes are reserved for msg tag */
-	memcpy(CB_TRGCLS(skb), &msg->class, CB_TRGCLS_LEN);
+	IUCV_SKB_CB(skb)->class = msg->class;
 
 	/* check for special IPRM messages (e.g. iucv_sock_shutdown) */
 	if ((msg->flags & IUCV_IPRMDATA) && len > 7) {
@@ -1292,6 +1286,7 @@ static void iucv_process_message(struct sock *sk, struct sk_buff *skb,
 		}
 	}
 
+	IUCV_SKB_CB(skb)->offset = 0;
 	if (sock_queue_rcv_skb(sk, skb))
 		skb_queue_head(&iucv_sk(sk)->backlog_skb_q, skb);
 }
@@ -1327,6 +1322,7 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	unsigned int copied, rlen;
 	struct sk_buff *skb, *rskb, *cskb;
 	int err = 0;
+	u32 offset;
 
 	msg->msg_namelen = 0;
 
@@ -1348,13 +1344,14 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 		return err;
 	}
 
-	rlen   = skb->len;		/* real length of skb */
+	offset = IUCV_SKB_CB(skb)->offset;
+	rlen   = skb->len - offset;		/* real length of skb */
 	copied = min_t(unsigned int, rlen, len);
 	if (!rlen)
 		sk->sk_shutdown = sk->sk_shutdown | RCV_SHUTDOWN;
 
 	cskb = skb;
-	if (skb_copy_datagram_iovec(cskb, 0, msg->msg_iov, copied)) {
+	if (skb_copy_datagram_iovec(cskb, offset, msg->msg_iov, copied)) {
 		if (!(flags & MSG_PEEK))
 			skb_queue_head(&sk->sk_receive_queue, skb);
 		return -EFAULT;
@@ -1372,7 +1369,8 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	 * get the trgcls from the control buffer of the skb due to
 	 * fragmentation of original iucv message. */
 	err = put_cmsg(msg, SOL_IUCV, SCM_IUCV_TRGCLS,
-			CB_TRGCLS_LEN, CB_TRGCLS(skb));
+		       sizeof(IUCV_SKB_CB(skb)->class),
+		       (void *)&IUCV_SKB_CB(skb)->class);
 	if (err) {
 		if (!(flags & MSG_PEEK))
 			skb_queue_head(&sk->sk_receive_queue, skb);
@@ -1384,9 +1382,8 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 		/* SOCK_STREAM: re-queue skb if it contains unreceived data */
 		if (sk->sk_type == SOCK_STREAM) {
-			skb_pull(skb, copied);
-			if (skb->len) {
-				skb_queue_head(&sk->sk_receive_queue, skb);
+			if (copied < rlen) {
+				IUCV_SKB_CB(skb)->offset = offset + copied;
 				goto done;
 			}
 		}
@@ -1405,6 +1402,7 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 		spin_lock_bh(&iucv->message_q.lock);
 		rskb = skb_dequeue(&iucv->backlog_skb_q);
 		while (rskb) {
+			IUCV_SKB_CB(rskb)->offset = 0;
 			if (sock_queue_rcv_skb(sk, rskb)) {
 				skb_queue_head(&iucv->backlog_skb_q,
 						rskb);
@@ -1832,7 +1830,7 @@ static void iucv_callback_txdone(struct iucv_path *path,
 		spin_lock_irqsave(&list->lock, flags);
 
 		while (list_skb != (struct sk_buff *)list) {
-			if (!memcmp(&msg->tag, CB_TAG(list_skb), CB_TAG_LEN)) {
+			if (msg->tag != IUCV_SKB_CB(list_skb)->tag) {
 				this = list_skb;
 				break;
 			}
@@ -2093,6 +2091,7 @@ static int afiucv_hs_callback_rx(struct sock *sk, struct sk_buff *skb)
 	skb_pull(skb, sizeof(struct af_iucv_trans_hdr));
 	skb_reset_transport_header(skb);
 	skb_reset_network_header(skb);
+	IUCV_SKB_CB(skb)->offset = 0;
 	spin_lock(&iucv->message_q.lock);
 	if (skb_queue_empty(&iucv->backlog_skb_q)) {
 		if (sock_queue_rcv_skb(sk, skb)) {
@@ -2197,8 +2196,7 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev,
 		/* fall through and receive zero length data */
 	case 0:
 		/* plain data frame */
-		memcpy(CB_TRGCLS(skb), &trans_hdr->iucv_hdr.class,
-		       CB_TRGCLS_LEN);
+		IUCV_SKB_CB(skb)->class = trans_hdr->iucv_hdr.class;
 		err = afiucv_hs_callback_rx(sk, skb);
 		break;
 	default:
-- 
cgit v1.2.3


From a6e4d5a03e9e3587e88aba687d8f225f4f04c792 Mon Sep 17 00:00:00 2001
From: Matt Fleming <matt.fleming@intel.com>
Date: Mon, 25 Mar 2013 09:14:30 +0000
Subject: x86, efivars: firmware bug workarounds should be in platform code

Let's not burden ia64 with checks in the common efivars code that we're not
writing too much data to the variable store. That kind of thing is an x86
firmware bug, plain and simple.

efi_query_variable_store() provides platforms with a wrapper in which they can
perform checks and workarounds for EFI variable storage bugs.

Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Matthew Garrett <mjg59@srcf.ucam.org>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
---
 arch/x86/platform/efi/efi.c | 25 +++++++++++++++++++++++++
 drivers/firmware/efivars.c  | 18 +++---------------
 include/linux/efi.h         |  9 ++++++++-
 3 files changed, 36 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 5f2ecaf3f9d8..c89c245eff40 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -999,3 +999,28 @@ u64 efi_mem_attributes(unsigned long phys_addr)
 	}
 	return 0;
 }
+
+/*
+ * Some firmware has serious problems when using more than 50% of the EFI
+ * variable store, i.e. it triggers bugs that can brick machines. Ensure that
+ * we never use more than this safe limit.
+ *
+ * Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable
+ * store.
+ */
+efi_status_t efi_query_variable_store(u32 attributes, unsigned long size)
+{
+	efi_status_t status;
+	u64 storage_size, remaining_size, max_size;
+
+	status = efi.query_variable_info(attributes, &storage_size,
+					 &remaining_size, &max_size);
+	if (status != EFI_SUCCESS)
+		return status;
+
+	if (!storage_size || size > remaining_size || size > max_size ||
+	    (remaining_size - size) < (storage_size / 2))
+		return EFI_OUT_OF_RESOURCES;
+
+	return EFI_SUCCESS;
+}
diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c
index 7acafb80fd4c..bf15d81d74e1 100644
--- a/drivers/firmware/efivars.c
+++ b/drivers/firmware/efivars.c
@@ -436,24 +436,12 @@ static efi_status_t
 check_var_size_locked(struct efivars *efivars, u32 attributes,
 			unsigned long size)
 {
-	u64 storage_size, remaining_size, max_size;
-	efi_status_t status;
 	const struct efivar_operations *fops = efivars->ops;
 
-	if (!efivars->ops->query_variable_info)
+	if (!efivars->ops->query_variable_store)
 		return EFI_UNSUPPORTED;
 
-	status = fops->query_variable_info(attributes, &storage_size,
-					   &remaining_size, &max_size);
-
-	if (status != EFI_SUCCESS)
-		return status;
-
-	if (!storage_size || size > remaining_size || size > max_size ||
-	    (remaining_size - size) < (storage_size / 2))
-		return EFI_OUT_OF_RESOURCES;
-
-	return status;
+	return fops->query_variable_store(attributes, size);
 }
 
 
@@ -2131,7 +2119,7 @@ efivars_init(void)
 	ops.get_variable = efi.get_variable;
 	ops.set_variable = efi.set_variable;
 	ops.get_next_variable = efi.get_next_variable;
-	ops.query_variable_info = efi.query_variable_info;
+	ops.query_variable_store = efi_query_variable_store;
 
 	error = register_efivars(&__efivars, &ops, efi_kobj);
 	if (error)
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 9bf2f1fcae27..3d7df3d32c66 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -333,6 +333,7 @@ typedef efi_status_t efi_query_capsule_caps_t(efi_capsule_header_t **capsules,
 					      unsigned long count,
 					      u64 *max_size,
 					      int *reset_type);
+typedef efi_status_t efi_query_variable_store_t(u32 attributes, unsigned long size);
 
 /*
  *  EFI Configuration Table and GUID definitions
@@ -575,9 +576,15 @@ extern void efi_enter_virtual_mode (void);	/* switch EFI to virtual mode, if pos
 #ifdef CONFIG_X86
 extern void efi_late_init(void);
 extern void efi_free_boot_services(void);
+extern efi_status_t efi_query_variable_store(u32 attributes, unsigned long size);
 #else
 static inline void efi_late_init(void) {}
 static inline void efi_free_boot_services(void) {}
+
+static inline efi_status_t efi_query_variable_store(u32 attributes, unsigned long size)
+{
+	return EFI_SUCCESS;
+}
 #endif
 extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr);
 extern u64 efi_get_iobase (void);
@@ -731,7 +738,7 @@ struct efivar_operations {
 	efi_get_variable_t *get_variable;
 	efi_get_next_variable_t *get_next_variable;
 	efi_set_variable_t *set_variable;
-	efi_query_variable_info_t *query_variable_info;
+	efi_query_variable_store_t *query_variable_store;
 };
 
 struct efivars {
-- 
cgit v1.2.3


From ca10b9e9a8ca7342ee07065289cbe74ac128c169 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 8 Apr 2013 17:58:11 +0000
Subject: selinux: add a skb_owned_by() hook

Commit 90ba9b1986b5ac (tcp: tcp_make_synack() can use alloc_skb())
broke certain SELinux/NetLabel configurations by no longer correctly
assigning the sock to the outgoing SYNACK packet.

Cost of atomic operations on the LISTEN socket is quite big,
and we would like it to happen only if really needed.

This patch introduces a new security_ops->skb_owned_by() method,
that is a void operation unless selinux is active.

Reported-by: Miroslav Vadkerti <mvadkert@redhat.com>
Diagnosed-by: Paul Moore <pmoore@redhat.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: linux-security-module@vger.kernel.org
Acked-by: James Morris <james.l.morris@oracle.com>
Tested-by: Paul Moore <pmoore@redhat.com>
Acked-by: Paul Moore <pmoore@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/security.h | 8 ++++++++
 net/ipv4/tcp_output.c    | 1 +
 security/capability.c    | 6 ++++++
 security/security.c      | 5 +++++
 security/selinux/hooks.c | 7 +++++++
 5 files changed, 27 insertions(+)

(limited to 'include')

diff --git a/include/linux/security.h b/include/linux/security.h
index eee7478cda70..6c3a78ace051 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1638,6 +1638,7 @@ struct security_operations {
 	int (*tun_dev_attach_queue) (void *security);
 	int (*tun_dev_attach) (struct sock *sk, void *security);
 	int (*tun_dev_open) (void *security);
+	void (*skb_owned_by) (struct sk_buff *skb, struct sock *sk);
 #endif	/* CONFIG_SECURITY_NETWORK */
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
@@ -2588,6 +2589,8 @@ int security_tun_dev_attach_queue(void *security);
 int security_tun_dev_attach(struct sock *sk, void *security);
 int security_tun_dev_open(void *security);
 
+void security_skb_owned_by(struct sk_buff *skb, struct sock *sk);
+
 #else	/* CONFIG_SECURITY_NETWORK */
 static inline int security_unix_stream_connect(struct sock *sock,
 					       struct sock *other,
@@ -2779,6 +2782,11 @@ static inline int security_tun_dev_open(void *security)
 {
 	return 0;
 }
+
+static inline void security_skb_owned_by(struct sk_buff *skb, struct sock *sk)
+{
+}
+
 #endif	/* CONFIG_SECURITY_NETWORK */
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 5d0b4387cba6..b44cf81d8178 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2709,6 +2709,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 	skb_reserve(skb, MAX_TCP_HEADER);
 
 	skb_dst_set(skb, dst);
+	security_skb_owned_by(skb, sk);
 
 	mss = dst_metric_advmss(dst);
 	if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss)
diff --git a/security/capability.c b/security/capability.c
index 579775088967..6783c3e6c88e 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -737,6 +737,11 @@ static int cap_tun_dev_open(void *security)
 {
 	return 0;
 }
+
+static void cap_skb_owned_by(struct sk_buff *skb, struct sock *sk)
+{
+}
+
 #endif	/* CONFIG_SECURITY_NETWORK */
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
@@ -1071,6 +1076,7 @@ void __init security_fixup_ops(struct security_operations *ops)
 	set_to_cap_if_null(ops, tun_dev_open);
 	set_to_cap_if_null(ops, tun_dev_attach_queue);
 	set_to_cap_if_null(ops, tun_dev_attach);
+	set_to_cap_if_null(ops, skb_owned_by);
 #endif	/* CONFIG_SECURITY_NETWORK */
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
 	set_to_cap_if_null(ops, xfrm_policy_alloc_security);
diff --git a/security/security.c b/security/security.c
index 7b88c6aeaed4..03f248b84e9f 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1290,6 +1290,11 @@ int security_tun_dev_open(void *security)
 }
 EXPORT_SYMBOL(security_tun_dev_open);
 
+void security_skb_owned_by(struct sk_buff *skb, struct sock *sk)
+{
+	security_ops->skb_owned_by(skb, sk);
+}
+
 #endif	/* CONFIG_SECURITY_NETWORK */
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 2fa28c88900c..7171a957b933 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -51,6 +51,7 @@
 #include <linux/tty.h>
 #include <net/icmp.h>
 #include <net/ip.h>		/* for local_port_range[] */
+#include <net/sock.h>
 #include <net/tcp.h>		/* struct or_callable used in sock_rcv_skb */
 #include <net/net_namespace.h>
 #include <net/netlabel.h>
@@ -4363,6 +4364,11 @@ static void selinux_inet_conn_established(struct sock *sk, struct sk_buff *skb)
 	selinux_skb_peerlbl_sid(skb, family, &sksec->peer_sid);
 }
 
+static void selinux_skb_owned_by(struct sk_buff *skb, struct sock *sk)
+{
+	skb_set_owner_w(skb, sk);
+}
+
 static int selinux_secmark_relabel_packet(u32 sid)
 {
 	const struct task_security_struct *__tsec;
@@ -5664,6 +5670,7 @@ static struct security_operations selinux_ops = {
 	.tun_dev_attach_queue =		selinux_tun_dev_attach_queue,
 	.tun_dev_attach =		selinux_tun_dev_attach,
 	.tun_dev_open =			selinux_tun_dev_open,
+	.skb_owned_by =			selinux_skb_owned_by,
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
 	.xfrm_policy_alloc_security =	selinux_xfrm_policy_alloc,
-- 
cgit v1.2.3


From 386afc91144b36b42117b0092893f15bc8798a80 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Tue, 9 Apr 2013 10:48:33 -0700
Subject: spinlocks and preemption points need to be at least compiler barriers

In UP and non-preempt respectively, the spinlocks and preemption
disable/enable points are stubbed out entirely, because there is no
regular code that can ever hit the kind of concurrency they are meant to
protect against.

However, while there is no regular code that can cause scheduling, we
_do_ end up having some exceptional (literally!) code that can do so,
and that we need to make sure does not ever get moved into the critical
region by the compiler.

In particular, get_user() and put_user() is generally implemented as
inline asm statements (even if the inline asm may then make a call
instruction to call out-of-line), and can obviously cause a page fault
and IO as a result.  If that inline asm has been scheduled into the
middle of a preemption-safe (or spinlock-protected) code region, we
obviously lose.

Now, admittedly this is *very* unlikely to actually ever happen, and
we've not seen examples of actual bugs related to this.  But partly
exactly because it's so hard to trigger and the resulting bug is so
subtle, we should be extra careful to get this right.

So make sure that even when preemption is disabled, and we don't have to
generate any actual *code* to explicitly tell the system that we are in
a preemption-disabled region, we need to at least tell the compiler not
to move things around the critical region.

This patch grew out of the same discussion that caused commits
79e5f05edcbf ("ARC: Add implicit compiler barrier to raw_local_irq*
functions") and 3e2e0d2c222b ("tile: comment assumption about
__insn_mtspr for <asm/irqflags.h>") to come about.

Note for stable: use discretion when/if applying this.  As mentioned,
this bug may never have actually bitten anybody, and gcc may never have
done the required code motion for it to possibly ever trigger in
practice.

Cc: stable@vger.kernel.org
Cc: Steven Rostedt <srostedt@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/preempt.h     | 22 ++++++++++++++--------
 include/linux/spinlock_up.h | 29 ++++++++++++++++++-----------
 2 files changed, 32 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 5a710b9c578e..87a03c746f17 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -93,14 +93,20 @@ do { \
 
 #else /* !CONFIG_PREEMPT_COUNT */
 
-#define preempt_disable()		do { } while (0)
-#define sched_preempt_enable_no_resched()	do { } while (0)
-#define preempt_enable_no_resched()	do { } while (0)
-#define preempt_enable()		do { } while (0)
-
-#define preempt_disable_notrace()		do { } while (0)
-#define preempt_enable_no_resched_notrace()	do { } while (0)
-#define preempt_enable_notrace()		do { } while (0)
+/*
+ * Even if we don't have any preemption, we need preempt disable/enable
+ * to be barriers, so that we don't have things like get_user/put_user
+ * that can cause faults and scheduling migrate into our preempt-protected
+ * region.
+ */
+#define preempt_disable()		barrier()
+#define sched_preempt_enable_no_resched()	barrier()
+#define preempt_enable_no_resched()	barrier()
+#define preempt_enable()		barrier()
+
+#define preempt_disable_notrace()		barrier()
+#define preempt_enable_no_resched_notrace()	barrier()
+#define preempt_enable_notrace()		barrier()
 
 #endif /* CONFIG_PREEMPT_COUNT */
 
diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h
index a26e2fb604e6..e2369c167dbd 100644
--- a/include/linux/spinlock_up.h
+++ b/include/linux/spinlock_up.h
@@ -16,7 +16,10 @@
  * In the debug case, 1 means unlocked, 0 means locked. (the values
  * are inverted, to catch initialization bugs)
  *
- * No atomicity anywhere, we are on UP.
+ * No atomicity anywhere, we are on UP. However, we still need
+ * the compiler barriers, because we do not want the compiler to
+ * move potentially faulting instructions (notably user accesses)
+ * into the locked sequence, resulting in non-atomic execution.
  */
 
 #ifdef CONFIG_DEBUG_SPINLOCK
@@ -25,6 +28,7 @@
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	lock->slock = 0;
+	barrier();
 }
 
 static inline void
@@ -32,6 +36,7 @@ arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags)
 {
 	local_irq_save(flags);
 	lock->slock = 0;
+	barrier();
 }
 
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
@@ -39,32 +44,34 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 	char oldval = lock->slock;
 
 	lock->slock = 0;
+	barrier();
 
 	return oldval > 0;
 }
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
+	barrier();
 	lock->slock = 1;
 }
 
 /*
  * Read-write spinlocks. No debug version.
  */
-#define arch_read_lock(lock)		do { (void)(lock); } while (0)
-#define arch_write_lock(lock)		do { (void)(lock); } while (0)
-#define arch_read_trylock(lock)	({ (void)(lock); 1; })
-#define arch_write_trylock(lock)	({ (void)(lock); 1; })
-#define arch_read_unlock(lock)		do { (void)(lock); } while (0)
-#define arch_write_unlock(lock)	do { (void)(lock); } while (0)
+#define arch_read_lock(lock)		do { barrier(); (void)(lock); } while (0)
+#define arch_write_lock(lock)		do { barrier(); (void)(lock); } while (0)
+#define arch_read_trylock(lock)	({ barrier(); (void)(lock); 1; })
+#define arch_write_trylock(lock)	({ barrier(); (void)(lock); 1; })
+#define arch_read_unlock(lock)		do { barrier(); (void)(lock); } while (0)
+#define arch_write_unlock(lock)	do { barrier(); (void)(lock); } while (0)
 
 #else /* DEBUG_SPINLOCK */
 #define arch_spin_is_locked(lock)	((void)(lock), 0)
 /* for sched.c and kernel_lock.c: */
-# define arch_spin_lock(lock)		do { (void)(lock); } while (0)
-# define arch_spin_lock_flags(lock, flags)	do { (void)(lock); } while (0)
-# define arch_spin_unlock(lock)	do { (void)(lock); } while (0)
-# define arch_spin_trylock(lock)	({ (void)(lock); 1; })
+# define arch_spin_lock(lock)		do { barrier(); (void)(lock); } while (0)
+# define arch_spin_lock_flags(lock, flags)	do { barrier(); (void)(lock); } while (0)
+# define arch_spin_unlock(lock)	do { barrier(); (void)(lock); } while (0)
+# define arch_spin_trylock(lock)	({ barrier(); (void)(lock); 1; })
 #endif /* DEBUG_SPINLOCK */
 
 #define arch_spin_is_contended(lock)	(((void)(lock), 0))
-- 
cgit v1.2.3


From 8ce584c7416d8a85a6f3edc17d1cddefe331e87e Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 30 Mar 2013 20:13:46 -0400
Subject: procfs: add proc_remove_subtree()

just what it sounds like; do that only to procfs subtrees you've
created - doing that to something shared with another driver is
not only antisocial, but might cause interesting races with
proc_create() and its ilk.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/proc/generic.c       | 119 ++++++++++++++++++++++++++++++++++++------------
 include/linux/proc_fs.h |   2 +
 2 files changed, 91 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 4b3b3ffb52f1..21e1a8f1659d 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -755,37 +755,8 @@ void pde_put(struct proc_dir_entry *pde)
 		free_proc_entry(pde);
 }
 
-/*
- * Remove a /proc entry and free it if it's not currently in use.
- */
-void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
+static void entry_rundown(struct proc_dir_entry *de)
 {
-	struct proc_dir_entry **p;
-	struct proc_dir_entry *de = NULL;
-	const char *fn = name;
-	unsigned int len;
-
-	spin_lock(&proc_subdir_lock);
-	if (__xlate_proc_name(name, &parent, &fn) != 0) {
-		spin_unlock(&proc_subdir_lock);
-		return;
-	}
-	len = strlen(fn);
-
-	for (p = &parent->subdir; *p; p=&(*p)->next ) {
-		if (proc_match(len, fn, *p)) {
-			de = *p;
-			*p = de->next;
-			de->next = NULL;
-			break;
-		}
-	}
-	spin_unlock(&proc_subdir_lock);
-	if (!de) {
-		WARN(1, "name '%s'\n", name);
-		return;
-	}
-
 	spin_lock(&de->pde_unload_lock);
 	/*
 	 * Stop accepting new callers into module. If you're
@@ -817,6 +788,40 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
 		spin_lock(&de->pde_unload_lock);
 	}
 	spin_unlock(&de->pde_unload_lock);
+}
+
+/*
+ * Remove a /proc entry and free it if it's not currently in use.
+ */
+void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
+{
+	struct proc_dir_entry **p;
+	struct proc_dir_entry *de = NULL;
+	const char *fn = name;
+	unsigned int len;
+
+	spin_lock(&proc_subdir_lock);
+	if (__xlate_proc_name(name, &parent, &fn) != 0) {
+		spin_unlock(&proc_subdir_lock);
+		return;
+	}
+	len = strlen(fn);
+
+	for (p = &parent->subdir; *p; p=&(*p)->next ) {
+		if (proc_match(len, fn, *p)) {
+			de = *p;
+			*p = de->next;
+			de->next = NULL;
+			break;
+		}
+	}
+	spin_unlock(&proc_subdir_lock);
+	if (!de) {
+		WARN(1, "name '%s'\n", name);
+		return;
+	}
+
+	entry_rundown(de);
 
 	if (S_ISDIR(de->mode))
 		parent->nlink--;
@@ -827,3 +832,57 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
 	pde_put(de);
 }
 EXPORT_SYMBOL(remove_proc_entry);
+
+int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
+{
+	struct proc_dir_entry **p;
+	struct proc_dir_entry *root = NULL, *de, *next;
+	const char *fn = name;
+	unsigned int len;
+
+	spin_lock(&proc_subdir_lock);
+	if (__xlate_proc_name(name, &parent, &fn) != 0) {
+		spin_unlock(&proc_subdir_lock);
+		return -ENOENT;
+	}
+	len = strlen(fn);
+
+	for (p = &parent->subdir; *p; p=&(*p)->next ) {
+		if (proc_match(len, fn, *p)) {
+			root = *p;
+			*p = root->next;
+			root->next = NULL;
+			break;
+		}
+	}
+	if (!root) {
+		spin_unlock(&proc_subdir_lock);
+		return -ENOENT;
+	}
+	de = root;
+	while (1) {
+		next = de->subdir;
+		if (next) {
+			de->subdir = next->next;
+			next->next = NULL;
+			de = next;
+			continue;
+		}
+		spin_unlock(&proc_subdir_lock);
+
+		entry_rundown(de);
+		next = de->parent;
+		if (S_ISDIR(de->mode))
+			next->nlink--;
+		de->nlink = 0;
+		if (de == root)
+			break;
+		pde_put(de);
+
+		spin_lock(&proc_subdir_lock);
+		de = next;
+	}
+	pde_put(root);
+	return 0;
+}
+EXPORT_SYMBOL(remove_proc_subtree);
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 8307f2f94d86..94dfb2aa5533 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -117,6 +117,7 @@ struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
 				const struct file_operations *proc_fops,
 				void *data);
 extern void remove_proc_entry(const char *name, struct proc_dir_entry *parent);
+extern int remove_proc_subtree(const char *name, struct proc_dir_entry *parent);
 
 struct pid_namespace;
 
@@ -202,6 +203,7 @@ static inline struct proc_dir_entry *proc_create_data(const char *name,
 	return NULL;
 }
 #define remove_proc_entry(name, parent) do {} while (0)
+#define remove_proc_subtree(name, parent) do {} while (0)
 
 static inline struct proc_dir_entry *proc_symlink(const char *name,
 		struct proc_dir_entry *parent,const char *dest) {return NULL;}
-- 
cgit v1.2.3


From 6eb4c7e96e19fd2c38a103472048fc0e0e0a3ec3 Mon Sep 17 00:00:00 2001
From: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Date: Tue, 9 Apr 2013 08:57:20 +0000
Subject: netfilter: ipset: hash:*net*: nomatch flag not excluded on set resize

If a resize is triggered the nomatch flag is not excluded at hashing,
which leads to the element missed at lookup in the resized set.

Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/ipset/ip_set_ahash.h | 30 +++++++++++++++++++++-------
 net/netfilter/ipset/ip_set_hash_ipportnet.c  | 18 +++++++++++++++++
 net/netfilter/ipset/ip_set_hash_net.c        | 22 ++++++++++++++++++--
 net/netfilter/ipset/ip_set_hash_netiface.c   | 22 ++++++++++++++++++--
 net/netfilter/ipset/ip_set_hash_netport.c    | 18 +++++++++++++++++
 5 files changed, 99 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h
index 01d25e6fc792..0214c4c146fa 100644
--- a/include/linux/netfilter/ipset/ip_set_ahash.h
+++ b/include/linux/netfilter/ipset/ip_set_ahash.h
@@ -291,6 +291,7 @@ ip_set_hash_destroy(struct ip_set *set)
 #define type_pf_data_tlist	TOKEN(TYPE, PF, _data_tlist)
 #define type_pf_data_next	TOKEN(TYPE, PF, _data_next)
 #define type_pf_data_flags	TOKEN(TYPE, PF, _data_flags)
+#define type_pf_data_reset_flags TOKEN(TYPE, PF, _data_reset_flags)
 #ifdef IP_SET_HASH_WITH_NETS
 #define type_pf_data_match	TOKEN(TYPE, PF, _data_match)
 #else
@@ -385,9 +386,9 @@ type_pf_resize(struct ip_set *set, bool retried)
 	struct ip_set_hash *h = set->data;
 	struct htable *t, *orig = h->table;
 	u8 htable_bits = orig->htable_bits;
-	const struct type_pf_elem *data;
+	struct type_pf_elem *data;
 	struct hbucket *n, *m;
-	u32 i, j;
+	u32 i, j, flags = 0;
 	int ret;
 
 retry:
@@ -412,9 +413,16 @@ retry:
 		n = hbucket(orig, i);
 		for (j = 0; j < n->pos; j++) {
 			data = ahash_data(n, j);
+#ifdef IP_SET_HASH_WITH_NETS
+			flags = 0;
+			type_pf_data_reset_flags(data, &flags);
+#endif
 			m = hbucket(t, HKEY(data, h->initval, htable_bits));
-			ret = type_pf_elem_add(m, data, AHASH_MAX(h), 0);
+			ret = type_pf_elem_add(m, data, AHASH_MAX(h), flags);
 			if (ret < 0) {
+#ifdef IP_SET_HASH_WITH_NETS
+				type_pf_data_flags(data, flags);
+#endif
 				read_unlock_bh(&set->lock);
 				ahash_destroy(t);
 				if (ret == -EAGAIN)
@@ -836,9 +844,9 @@ type_pf_tresize(struct ip_set *set, bool retried)
 	struct ip_set_hash *h = set->data;
 	struct htable *t, *orig = h->table;
 	u8 htable_bits = orig->htable_bits;
-	const struct type_pf_elem *data;
+	struct type_pf_elem *data;
 	struct hbucket *n, *m;
-	u32 i, j;
+	u32 i, j, flags = 0;
 	int ret;
 
 	/* Try to cleanup once */
@@ -873,10 +881,17 @@ retry:
 		n = hbucket(orig, i);
 		for (j = 0; j < n->pos; j++) {
 			data = ahash_tdata(n, j);
+#ifdef IP_SET_HASH_WITH_NETS
+			flags = 0;
+			type_pf_data_reset_flags(data, &flags);
+#endif
 			m = hbucket(t, HKEY(data, h->initval, htable_bits));
-			ret = type_pf_elem_tadd(m, data, AHASH_MAX(h), 0,
-						ip_set_timeout_get(type_pf_data_timeout(data)));
+			ret = type_pf_elem_tadd(m, data, AHASH_MAX(h), flags,
+				ip_set_timeout_get(type_pf_data_timeout(data)));
 			if (ret < 0) {
+#ifdef IP_SET_HASH_WITH_NETS
+				type_pf_data_flags(data, flags);
+#endif
 				read_unlock_bh(&set->lock);
 				ahash_destroy(t);
 				if (ret == -EAGAIN)
@@ -1187,6 +1202,7 @@ type_pf_gc_init(struct ip_set *set)
 #undef type_pf_data_tlist
 #undef type_pf_data_next
 #undef type_pf_data_flags
+#undef type_pf_data_reset_flags
 #undef type_pf_data_match
 
 #undef type_pf_elem
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index f2627226a087..10a30b4fc7db 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -104,6 +104,15 @@ hash_ipportnet4_data_flags(struct hash_ipportnet4_elem *dst, u32 flags)
 	dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
 }
 
+static inline void
+hash_ipportnet4_data_reset_flags(struct hash_ipportnet4_elem *dst, u32 *flags)
+{
+	if (dst->nomatch) {
+		*flags = IPSET_FLAG_NOMATCH;
+		dst->nomatch = 0;
+	}
+}
+
 static inline int
 hash_ipportnet4_data_match(const struct hash_ipportnet4_elem *elem)
 {
@@ -414,6 +423,15 @@ hash_ipportnet6_data_flags(struct hash_ipportnet6_elem *dst, u32 flags)
 	dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
 }
 
+static inline void
+hash_ipportnet6_data_reset_flags(struct hash_ipportnet6_elem *dst, u32 *flags)
+{
+	if (dst->nomatch) {
+		*flags = IPSET_FLAG_NOMATCH;
+		dst->nomatch = 0;
+	}
+}
+
 static inline int
 hash_ipportnet6_data_match(const struct hash_ipportnet6_elem *elem)
 {
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index 4b677cf6bf7d..d6a59154d710 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -87,7 +87,16 @@ hash_net4_data_copy(struct hash_net4_elem *dst,
 static inline void
 hash_net4_data_flags(struct hash_net4_elem *dst, u32 flags)
 {
-	dst->nomatch = flags & IPSET_FLAG_NOMATCH;
+	dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
+}
+
+static inline void
+hash_net4_data_reset_flags(struct hash_net4_elem *dst, u32 *flags)
+{
+	if (dst->nomatch) {
+		*flags = IPSET_FLAG_NOMATCH;
+		dst->nomatch = 0;
+	}
 }
 
 static inline int
@@ -308,7 +317,16 @@ hash_net6_data_copy(struct hash_net6_elem *dst,
 static inline void
 hash_net6_data_flags(struct hash_net6_elem *dst, u32 flags)
 {
-	dst->nomatch = flags & IPSET_FLAG_NOMATCH;
+	dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
+}
+
+static inline void
+hash_net6_data_reset_flags(struct hash_net6_elem *dst, u32 *flags)
+{
+	if (dst->nomatch) {
+		*flags = IPSET_FLAG_NOMATCH;
+		dst->nomatch = 0;
+	}
 }
 
 static inline int
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index 6ba985f1c96f..f2b0a3c30130 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -198,7 +198,16 @@ hash_netiface4_data_copy(struct hash_netiface4_elem *dst,
 static inline void
 hash_netiface4_data_flags(struct hash_netiface4_elem *dst, u32 flags)
 {
-	dst->nomatch = flags & IPSET_FLAG_NOMATCH;
+	dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
+}
+
+static inline void
+hash_netiface4_data_reset_flags(struct hash_netiface4_elem *dst, u32 *flags)
+{
+	if (dst->nomatch) {
+		*flags = IPSET_FLAG_NOMATCH;
+		dst->nomatch = 0;
+	}
 }
 
 static inline int
@@ -494,7 +503,7 @@ hash_netiface6_data_copy(struct hash_netiface6_elem *dst,
 static inline void
 hash_netiface6_data_flags(struct hash_netiface6_elem *dst, u32 flags)
 {
-	dst->nomatch = flags & IPSET_FLAG_NOMATCH;
+	dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
 }
 
 static inline int
@@ -503,6 +512,15 @@ hash_netiface6_data_match(const struct hash_netiface6_elem *elem)
 	return elem->nomatch ? -ENOTEMPTY : 1;
 }
 
+static inline void
+hash_netiface6_data_reset_flags(struct hash_netiface6_elem *dst, u32 *flags)
+{
+	if (dst->nomatch) {
+		*flags = IPSET_FLAG_NOMATCH;
+		dst->nomatch = 0;
+	}
+}
+
 static inline void
 hash_netiface6_data_zero_out(struct hash_netiface6_elem *elem)
 {
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index af20c0c5ced2..349deb672a2d 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -104,6 +104,15 @@ hash_netport4_data_flags(struct hash_netport4_elem *dst, u32 flags)
 	dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
 }
 
+static inline void
+hash_netport4_data_reset_flags(struct hash_netport4_elem *dst, u32 *flags)
+{
+	if (dst->nomatch) {
+		*flags = IPSET_FLAG_NOMATCH;
+		dst->nomatch = 0;
+	}
+}
+
 static inline int
 hash_netport4_data_match(const struct hash_netport4_elem *elem)
 {
@@ -375,6 +384,15 @@ hash_netport6_data_flags(struct hash_netport6_elem *dst, u32 flags)
 	dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
 }
 
+static inline void
+hash_netport6_data_reset_flags(struct hash_netport6_elem *dst, u32 *flags)
+{
+	if (dst->nomatch) {
+		*flags = IPSET_FLAG_NOMATCH;
+		dst->nomatch = 0;
+	}
+}
+
 static inline int
 hash_netport6_data_match(const struct hash_netport6_elem *elem)
 {
-- 
cgit v1.2.3


From 46fc4c909339f5a84d1679045297d9d2fb596987 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <zajec5@gmail.com>
Date: Tue, 2 Apr 2013 15:57:26 +0200
Subject: ssb: implement spurious tone avoidance
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

And make use of it in b43. This fixes a regression introduced with
49d55cef5b1925a5c1efb6aaddaa40fc7c693335
b43: N-PHY: implement spurious tone avoidance
This commit made BCM4322 use only MCS 0 on channel 13, which of course
resulted in performance drop (down to 0.7Mb/s).

Reported-by: Stefan Brüns <stefan.bruens@rwth-aachen.de>
Signed-off-by: Rafał Miłecki <zajec5@gmail.com>
Cc: Stable <stable@vger.kernel.org>
Signed-off-by: John W. Linville <linville@tuxdriver.com>
---
 drivers/net/wireless/b43/phy_n.c          |  3 ++-
 drivers/ssb/driver_chipcommon_pmu.c       | 29 +++++++++++++++++++++++++++++
 include/linux/ssb/ssb_driver_chipcommon.h |  2 ++
 3 files changed, 33 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/net/wireless/b43/phy_n.c b/drivers/net/wireless/b43/phy_n.c
index e8486c1e091a..b70f220bc4b3 100644
--- a/drivers/net/wireless/b43/phy_n.c
+++ b/drivers/net/wireless/b43/phy_n.c
@@ -5165,7 +5165,8 @@ static void b43_nphy_pmu_spur_avoid(struct b43_wldev *dev, bool avoid)
 #endif
 #ifdef CONFIG_B43_SSB
 	case B43_BUS_SSB:
-		/* FIXME */
+		ssb_pmu_spuravoid_pllupdate(&dev->dev->sdev->bus->chipco,
+					    avoid);
 		break;
 #endif
 	}
diff --git a/drivers/ssb/driver_chipcommon_pmu.c b/drivers/ssb/driver_chipcommon_pmu.c
index 4c0f6d883dd3..7b0bce936762 100644
--- a/drivers/ssb/driver_chipcommon_pmu.c
+++ b/drivers/ssb/driver_chipcommon_pmu.c
@@ -675,3 +675,32 @@ u32 ssb_pmu_get_controlclock(struct ssb_chipcommon *cc)
 		return 0;
 	}
 }
+
+void ssb_pmu_spuravoid_pllupdate(struct ssb_chipcommon *cc, int spuravoid)
+{
+	u32 pmu_ctl = 0;
+
+	switch (cc->dev->bus->chip_id) {
+	case 0x4322:
+		ssb_chipco_pll_write(cc, SSB_PMU1_PLLCTL0, 0x11100070);
+		ssb_chipco_pll_write(cc, SSB_PMU1_PLLCTL1, 0x1014140a);
+		ssb_chipco_pll_write(cc, SSB_PMU1_PLLCTL5, 0x88888854);
+		if (spuravoid == 1)
+			ssb_chipco_pll_write(cc, SSB_PMU1_PLLCTL2, 0x05201828);
+		else
+			ssb_chipco_pll_write(cc, SSB_PMU1_PLLCTL2, 0x05001828);
+		pmu_ctl = SSB_CHIPCO_PMU_CTL_PLL_UPD;
+		break;
+	case 43222:
+		/* TODO: BCM43222 requires updating PLLs too */
+		return;
+	default:
+		ssb_printk(KERN_ERR PFX
+			   "Unknown spuravoidance settings for chip 0x%04X, not changing PLL\n",
+			   cc->dev->bus->chip_id);
+		return;
+	}
+
+	chipco_set32(cc, SSB_CHIPCO_PMU_CTL, pmu_ctl);
+}
+EXPORT_SYMBOL_GPL(ssb_pmu_spuravoid_pllupdate);
diff --git a/include/linux/ssb/ssb_driver_chipcommon.h b/include/linux/ssb/ssb_driver_chipcommon.h
index 9e492be5244b..6fcfe99bd999 100644
--- a/include/linux/ssb/ssb_driver_chipcommon.h
+++ b/include/linux/ssb/ssb_driver_chipcommon.h
@@ -219,6 +219,7 @@
 #define SSB_CHIPCO_PMU_CTL			0x0600 /* PMU control */
 #define  SSB_CHIPCO_PMU_CTL_ILP_DIV		0xFFFF0000 /* ILP div mask */
 #define  SSB_CHIPCO_PMU_CTL_ILP_DIV_SHIFT	16
+#define  SSB_CHIPCO_PMU_CTL_PLL_UPD		0x00000400
 #define  SSB_CHIPCO_PMU_CTL_NOILPONW		0x00000200 /* No ILP on wait */
 #define  SSB_CHIPCO_PMU_CTL_HTREQEN		0x00000100 /* HT req enable */
 #define  SSB_CHIPCO_PMU_CTL_ALPREQEN		0x00000080 /* ALP req enable */
@@ -667,5 +668,6 @@ enum ssb_pmu_ldo_volt_id {
 void ssb_pmu_set_ldo_voltage(struct ssb_chipcommon *cc,
 			     enum ssb_pmu_ldo_volt_id id, u32 voltage);
 void ssb_pmu_set_ldo_paref(struct ssb_chipcommon *cc, bool on);
+void ssb_pmu_spuravoid_pllupdate(struct ssb_chipcommon *cc, int spuravoid);
 
 #endif /* LINUX_SSB_CHIPCO_H_ */
-- 
cgit v1.2.3


From 6b07a24fc38476e04f591cc17594bc1835b9efdd Mon Sep 17 00:00:00 2001
From: Paul Moore <pmoore@redhat.com>
Date: Wed, 10 Apr 2013 15:34:14 -0400
Subject: lsm: add the missing documentation for the security_skb_owned_by()
 hook

Unfortunately we didn't catch the missing comments earlier when the
patch was merged.

Signed-off-by: Paul Moore <pmoore@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/security.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/security.h b/include/linux/security.h
index 6c3a78ace051..032c366ef1c6 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -1012,6 +1012,10 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	This hook can be used by the module to update any security state
  *	associated with the TUN device's security structure.
  *	@security pointer to the TUN devices's security structure.
+ * @skb_owned_by:
+ *	This hook sets the packet's owning sock.
+ *	@skb is the packet.
+ *	@sk the sock which owns the packet.
  *
  * Security hooks for XFRM operations.
  *
-- 
cgit v1.2.3


From f2530dc71cf0822f90bb63ea4600caaef33a66bb Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 9 Apr 2013 09:33:34 +0200
Subject: kthread: Prevent unpark race which puts threads on the wrong cpu

The smpboot threads rely on the park/unpark mechanism which binds per
cpu threads on a particular core. Though the functionality is racy:

CPU0	       	 	CPU1  	     	    CPU2
unpark(T)				    wake_up_process(T)
  clear(SHOULD_PARK)	T runs
			leave parkme() due to !SHOULD_PARK
  bind_to(CPU2)		BUG_ON(wrong CPU)

We cannot let the tasks move themself to the target CPU as one of
those tasks is actually the migration thread itself, which requires
that it starts running on the target cpu right away.

The solution to this problem is to prevent wakeups in park mode which
are not from unpark(). That way we can guarantee that the association
of the task to the target cpu is working correctly.

Add a new task state (TASK_PARKED) which prevents other wakeups and
use this state explicitly for the unpark wakeup.

Peter noticed: Also, since the task state is visible to userspace and
all the parked tasks are still in the PID space, its a good hint in ps
and friends that these tasks aren't really there for the moment.

The migration thread has another related issue.

CPU0	      	     	 CPU1
Bring up CPU2
create_thread(T)
park(T)
 wait_for_completion()
			 parkme()
			 complete()
sched_set_stop_task()
			 schedule(TASK_PARKED)

The sched_set_stop_task() call is issued while the task is on the
runqueue of CPU1 and that confuses the hell out of the stop_task class
on that cpu. So we need the same synchronizaion before
sched_set_stop_task().

Reported-by: Dave Jones <davej@redhat.com>
Reported-and-tested-by: Dave Hansen <dave@sr71.net>
Reported-and-tested-by: Borislav Petkov <bp@alien8.de>
Acked-by: Peter Ziljstra <peterz@infradead.org>
Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Cc: dhillf@gmail.com
Cc: Ingo Molnar <mingo@kernel.org>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1304091635430.21884@ionos
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 fs/proc/array.c              |  1 +
 include/linux/sched.h        |  5 +++--
 include/trace/events/sched.h |  2 +-
 kernel/kthread.c             | 52 ++++++++++++++++++++++++--------------------
 kernel/smpboot.c             | 14 ++++++++++--
 5 files changed, 45 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/fs/proc/array.c b/fs/proc/array.c
index f7ed9ee46eb9..cbd0f1b324b9 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -143,6 +143,7 @@ static const char * const task_state_array[] = {
 	"x (dead)",		/*  64 */
 	"K (wakekill)",		/* 128 */
 	"W (waking)",		/* 256 */
+	"P (parked)",		/* 512 */
 };
 
 static inline const char *get_task_state(struct task_struct *tsk)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d35d2b6ddbfb..e692a022527b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -163,9 +163,10 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 #define TASK_DEAD		64
 #define TASK_WAKEKILL		128
 #define TASK_WAKING		256
-#define TASK_STATE_MAX		512
+#define TASK_PARKED		512
+#define TASK_STATE_MAX		1024
 
-#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKW"
+#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP"
 
 extern char ___assert_task_state[1 - 2*!!(
 		sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 5a8671e8a67f..e5586caff67a 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -147,7 +147,7 @@ TRACE_EVENT(sched_switch,
 		  __print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|",
 				{ 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" },
 				{ 16, "Z" }, { 32, "X" }, { 64, "x" },
-				{ 128, "W" }) : "R",
+				{ 128, "K" }, { 256, "W" }, { 512, "P" }) : "R",
 		__entry->prev_state & TASK_STATE_MAX ? "+" : "",
 		__entry->next_comm, __entry->next_pid, __entry->next_prio)
 );
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 691dc2ef9baf..9eb7fed0bbaa 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -124,12 +124,12 @@ void *kthread_data(struct task_struct *task)
 
 static void __kthread_parkme(struct kthread *self)
 {
-	__set_current_state(TASK_INTERRUPTIBLE);
+	__set_current_state(TASK_PARKED);
 	while (test_bit(KTHREAD_SHOULD_PARK, &self->flags)) {
 		if (!test_and_set_bit(KTHREAD_IS_PARKED, &self->flags))
 			complete(&self->parked);
 		schedule();
-		__set_current_state(TASK_INTERRUPTIBLE);
+		__set_current_state(TASK_PARKED);
 	}
 	clear_bit(KTHREAD_IS_PARKED, &self->flags);
 	__set_current_state(TASK_RUNNING);
@@ -256,8 +256,13 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
 }
 EXPORT_SYMBOL(kthread_create_on_node);
 
-static void __kthread_bind(struct task_struct *p, unsigned int cpu)
+static void __kthread_bind(struct task_struct *p, unsigned int cpu, long state)
 {
+	/* Must have done schedule() in kthread() before we set_task_cpu */
+	if (!wait_task_inactive(p, state)) {
+		WARN_ON(1);
+		return;
+	}
 	/* It's safe because the task is inactive. */
 	do_set_cpus_allowed(p, cpumask_of(cpu));
 	p->flags |= PF_THREAD_BOUND;
@@ -274,12 +279,7 @@ static void __kthread_bind(struct task_struct *p, unsigned int cpu)
  */
 void kthread_bind(struct task_struct *p, unsigned int cpu)
 {
-	/* Must have done schedule() in kthread() before we set_task_cpu */
-	if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) {
-		WARN_ON(1);
-		return;
-	}
-	__kthread_bind(p, cpu);
+	__kthread_bind(p, cpu, TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL(kthread_bind);
 
@@ -324,6 +324,22 @@ static struct kthread *task_get_live_kthread(struct task_struct *k)
 	return NULL;
 }
 
+static void __kthread_unpark(struct task_struct *k, struct kthread *kthread)
+{
+	clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+	/*
+	 * We clear the IS_PARKED bit here as we don't wait
+	 * until the task has left the park code. So if we'd
+	 * park before that happens we'd see the IS_PARKED bit
+	 * which might be about to be cleared.
+	 */
+	if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
+		if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
+			__kthread_bind(k, kthread->cpu, TASK_PARKED);
+		wake_up_state(k, TASK_PARKED);
+	}
+}
+
 /**
  * kthread_unpark - unpark a thread created by kthread_create().
  * @k:		thread created by kthread_create().
@@ -336,20 +352,8 @@ void kthread_unpark(struct task_struct *k)
 {
 	struct kthread *kthread = task_get_live_kthread(k);
 
-	if (kthread) {
-		clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
-		/*
-		 * We clear the IS_PARKED bit here as we don't wait
-		 * until the task has left the park code. So if we'd
-		 * park before that happens we'd see the IS_PARKED bit
-		 * which might be about to be cleared.
-		 */
-		if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) {
-			if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
-				__kthread_bind(k, kthread->cpu);
-			wake_up_process(k);
-		}
-	}
+	if (kthread)
+		__kthread_unpark(k, kthread);
 	put_task_struct(k);
 }
 
@@ -407,7 +411,7 @@ int kthread_stop(struct task_struct *k)
 	trace_sched_kthread_stop(k);
 	if (kthread) {
 		set_bit(KTHREAD_SHOULD_STOP, &kthread->flags);
-		clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+		__kthread_unpark(k, kthread);
 		wake_up_process(k);
 		wait_for_completion(&kthread->exited);
 	}
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index 8eaed9aa9cf0..02fc5c933673 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -185,8 +185,18 @@ __smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu)
 	}
 	get_task_struct(tsk);
 	*per_cpu_ptr(ht->store, cpu) = tsk;
-	if (ht->create)
-		ht->create(cpu);
+	if (ht->create) {
+		/*
+		 * Make sure that the task has actually scheduled out
+		 * into park position, before calling the create
+		 * callback. At least the migration thread callback
+		 * requires that the task is off the runqueue.
+		 */
+		if (!wait_task_inactive(tsk, TASK_PARKED))
+			WARN_ON(1);
+		else
+			ht->create(cpu);
+	}
 	return 0;
 }
 
-- 
cgit v1.2.3


From 6a76f8c0ab19f215af2a3442870eeb5f0e81998d Mon Sep 17 00:00:00 2001
From: Namhyung Kim <namhyung.kim@lge.com>
Date: Thu, 11 Apr 2013 15:55:01 +0900
Subject: tracing: Fix possible NULL pointer dereferences

Currently set_ftrace_pid and set_graph_function files use seq_lseek
for their fops.  However seq_open() is called only for FMODE_READ in
the fops->open() so that if an user tries to seek one of those file
when she open it for writing, it sees NULL seq_file and then panic.

It can be easily reproduced with following command:

  $ cd /sys/kernel/debug/tracing
  $ echo 1234 | sudo tee -a set_ftrace_pid

In this example, GNU coreutils' tee opens the file with fopen(, "a")
and then the fopen() internally calls lseek().

Link: http://lkml.kernel.org/r/1365663302-2170-1-git-send-email-namhyung@kernel.org

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: stable@vger.kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace.h     |  2 +-
 kernel/trace/ftrace.c      | 10 +++++-----
 kernel/trace/trace_stack.c |  2 +-
 3 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 167abf907802..eb3ce327b975 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -396,7 +396,7 @@ ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf,
 			    size_t cnt, loff_t *ppos);
 ssize_t ftrace_notrace_write(struct file *file, const char __user *ubuf,
 			     size_t cnt, loff_t *ppos);
-loff_t ftrace_regex_lseek(struct file *file, loff_t offset, int whence);
+loff_t ftrace_filter_lseek(struct file *file, loff_t offset, int whence);
 int ftrace_regex_release(struct inode *inode, struct file *file);
 
 void __init
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 926ebfb74936..affc35d829cc 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2697,7 +2697,7 @@ ftrace_notrace_open(struct inode *inode, struct file *file)
 }
 
 loff_t
-ftrace_regex_lseek(struct file *file, loff_t offset, int whence)
+ftrace_filter_lseek(struct file *file, loff_t offset, int whence)
 {
 	loff_t ret;
 
@@ -3570,7 +3570,7 @@ static const struct file_operations ftrace_filter_fops = {
 	.open = ftrace_filter_open,
 	.read = seq_read,
 	.write = ftrace_filter_write,
-	.llseek = ftrace_regex_lseek,
+	.llseek = ftrace_filter_lseek,
 	.release = ftrace_regex_release,
 };
 
@@ -3578,7 +3578,7 @@ static const struct file_operations ftrace_notrace_fops = {
 	.open = ftrace_notrace_open,
 	.read = seq_read,
 	.write = ftrace_notrace_write,
-	.llseek = ftrace_regex_lseek,
+	.llseek = ftrace_filter_lseek,
 	.release = ftrace_regex_release,
 };
 
@@ -3783,8 +3783,8 @@ static const struct file_operations ftrace_graph_fops = {
 	.open		= ftrace_graph_open,
 	.read		= seq_read,
 	.write		= ftrace_graph_write,
+	.llseek		= ftrace_filter_lseek,
 	.release	= ftrace_graph_release,
-	.llseek		= seq_lseek,
 };
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
@@ -4439,7 +4439,7 @@ static const struct file_operations ftrace_pid_fops = {
 	.open		= ftrace_pid_open,
 	.write		= ftrace_pid_write,
 	.read		= seq_read,
-	.llseek		= seq_lseek,
+	.llseek		= ftrace_filter_lseek,
 	.release	= ftrace_pid_release,
 };
 
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 42ca822fc701..83a8b5b7bd35 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -322,7 +322,7 @@ static const struct file_operations stack_trace_filter_fops = {
 	.open = stack_trace_filter_open,
 	.read = seq_read,
 	.write = ftrace_filter_write,
-	.llseek = ftrace_regex_lseek,
+	.llseek = ftrace_filter_lseek,
 	.release = ftrace_regex_release,
 };
 
-- 
cgit v1.2.3


From 7f49ef69db6bbf756c0abca7e9b65b32e999eec8 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
Date: Fri, 12 Apr 2013 16:40:13 -0400
Subject: ftrace: Move ftrace_filter_lseek out of CONFIG_DYNAMIC_FTRACE section

As ftrace_filter_lseek is now used with ftrace_pid_fops, it needs to
be moved out of the #ifdef CONFIG_DYNAMIC_FTRACE section as the
ftrace_pid_fops is defined when DYNAMIC_FTRACE is not.

Cc: stable@vger.kernel.org
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace.h |  3 ++-
 kernel/trace/ftrace.c  | 28 ++++++++++++++--------------
 2 files changed, 16 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index eb3ce327b975..52da2a250795 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -396,7 +396,6 @@ ssize_t ftrace_filter_write(struct file *file, const char __user *ubuf,
 			    size_t cnt, loff_t *ppos);
 ssize_t ftrace_notrace_write(struct file *file, const char __user *ubuf,
 			     size_t cnt, loff_t *ppos);
-loff_t ftrace_filter_lseek(struct file *file, loff_t offset, int whence);
 int ftrace_regex_release(struct inode *inode, struct file *file);
 
 void __init
@@ -569,6 +568,8 @@ static inline int
 ftrace_regex_release(struct inode *inode, struct file *file) { return -ENODEV; }
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
+loff_t ftrace_filter_lseek(struct file *file, loff_t offset, int whence);
+
 /* totally disable ftrace - can not re-enable after this */
 void ftrace_kill(void);
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index affc35d829cc..2461ede45a8d 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1052,6 +1052,19 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
 
 static struct pid * const ftrace_swapper_pid = &init_struct_pid;
 
+loff_t
+ftrace_filter_lseek(struct file *file, loff_t offset, int whence)
+{
+	loff_t ret;
+
+	if (file->f_mode & FMODE_READ)
+		ret = seq_lseek(file, offset, whence);
+	else
+		file->f_pos = ret = 1;
+
+	return ret;
+}
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 #ifndef CONFIG_FTRACE_MCOUNT_RECORD
@@ -2612,7 +2625,7 @@ static void ftrace_filter_reset(struct ftrace_hash *hash)
  * routine, you can use ftrace_filter_write() for the write
  * routine if @flag has FTRACE_ITER_FILTER set, or
  * ftrace_notrace_write() if @flag has FTRACE_ITER_NOTRACE set.
- * ftrace_regex_lseek() should be used as the lseek routine, and
+ * ftrace_filter_lseek() should be used as the lseek routine, and
  * release must call ftrace_regex_release().
  */
 int
@@ -2696,19 +2709,6 @@ ftrace_notrace_open(struct inode *inode, struct file *file)
 				 inode, file);
 }
 
-loff_t
-ftrace_filter_lseek(struct file *file, loff_t offset, int whence)
-{
-	loff_t ret;
-
-	if (file->f_mode & FMODE_READ)
-		ret = seq_lseek(file, offset, whence);
-	else
-		file->f_pos = ret = 1;
-
-	return ret;
-}
-
 static int ftrace_match(char *str, char *regex, int len, int type)
 {
 	int matched = 0;
-- 
cgit v1.2.3


From 1de14c3c5cbc9bb17e9dcc648cda51c0c85d54b9 Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave@sr71.net>
Date: Fri, 12 Apr 2013 16:23:54 -0700
Subject: x86-32: Fix possible incomplete TLB invalidate with PAE pagetables

This patch attempts to fix:

	https://bugzilla.kernel.org/show_bug.cgi?id=56461

The symptom is a crash and messages like this:

	chrome: Corrupted page table at address 34a03000
	*pdpt = 0000000000000000 *pde = 0000000000000000
	Bad pagetable: 000f [#1] PREEMPT SMP

Ingo guesses this got introduced by commit 611ae8e3f520 ("x86/tlb:
enable tlb flush range support for x86") since that code started to free
unused pagetables.

On x86-32 PAE kernels, that new code has the potential to free an entire
PMD page and will clear one of the four page-directory-pointer-table
(aka pgd_t entries).

The hardware aggressively "caches" these top-level entries and invlpg
does not actually affect the CPU's copy.  If we clear one we *HAVE* to
do a full TLB flush, otherwise we might continue using a freed pmd page.
(note, we do this properly on the population side in pud_populate()).

This patch tracks whenever we clear one of these entries in the 'struct
mmu_gather', and ensures that we follow up with a full tlb flush.

BTW, I disassembled and checked that:

	if (tlb->fullmm == 0)
and
	if (!tlb->fullmm && !tlb->need_flush_all)

generate essentially the same code, so there should be zero impact there
to the !PAE case.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Peter Anvin <hpa@zytor.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Artem S Tashkinov <t.artem@mailcity.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/include/asm/tlb.h | 2 +-
 arch/x86/mm/pgtable.c      | 7 +++++++
 include/asm-generic/tlb.h  | 7 ++++++-
 mm/memory.c                | 1 +
 4 files changed, 15 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 4fef20773b8f..c7797307fc2b 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -7,7 +7,7 @@
 
 #define tlb_flush(tlb)							\
 {									\
-	if (tlb->fullmm == 0)						\
+	if (!tlb->fullmm && !tlb->need_flush_all) 			\
 		flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end, 0UL);	\
 	else								\
 		flush_tlb_mm_range(tlb->mm, 0UL, TLB_FLUSH_ALL, 0UL);	\
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 193350b51f90..17fda6a8b3c2 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -58,6 +58,13 @@ void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
 void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
 {
 	paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT);
+	/*
+	 * NOTE! For PAE, any changes to the top page-directory-pointer-table
+	 * entries need a full cr3 reload to flush.
+	 */
+#ifdef CONFIG_X86_PAE
+	tlb->need_flush_all = 1;
+#endif
 	tlb_remove_page(tlb, virt_to_page(pmd));
 }
 
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 25f01d0bc149..b1b1fa6ffffe 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -99,7 +99,12 @@ struct mmu_gather {
 	unsigned int		need_flush : 1,	/* Did free PTEs */
 				fast_mode  : 1; /* No batching   */
 
-	unsigned int		fullmm;
+	/* we are in the middle of an operation to clear
+	 * a full mm and can make some optimizations */
+	unsigned int		fullmm : 1,
+	/* we have performed an operation which
+	 * requires a complete flush of the tlb */
+				need_flush_all : 1;
 
 	struct mmu_gather_batch *active;
 	struct mmu_gather_batch	local;
diff --git a/mm/memory.c b/mm/memory.c
index 494526ae024a..13cbc420fead 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -216,6 +216,7 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm)
 	tlb->mm = mm;
 
 	tlb->fullmm     = fullmm;
+	tlb->need_flush_all = 0;
 	tlb->start	= -1UL;
 	tlb->end	= 0;
 	tlb->need_flush = 0;
-- 
cgit v1.2.3


From 935d8aabd4331f47a89c3e1daa5779d23cf244ee Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 14 Apr 2013 10:06:31 -0700
Subject: Add file_ns_capable() helper function for open-time capability
 checking

Nothing is using it yet, but this will allow us to delay the open-time
checks to use time, without breaking the normal UNIX permission
semantics where permissions are determined by the opener (and the file
descriptor can then be passed to a different process, or the process can
drop capabilities).

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/capability.h |  2 ++
 kernel/capability.c        | 24 ++++++++++++++++++++++++
 2 files changed, 26 insertions(+)

(limited to 'include')

diff --git a/include/linux/capability.h b/include/linux/capability.h
index 98503b792369..d9a4f7f40f32 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -35,6 +35,7 @@ struct cpu_vfs_cap_data {
 #define _KERNEL_CAP_T_SIZE     (sizeof(kernel_cap_t))
 
 
+struct file;
 struct inode;
 struct dentry;
 struct user_namespace;
@@ -211,6 +212,7 @@ extern bool capable(int cap);
 extern bool ns_capable(struct user_namespace *ns, int cap);
 extern bool nsown_capable(int cap);
 extern bool inode_capable(const struct inode *inode, int cap);
+extern bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap);
 
 /* audit system wants to get cap info from files as well */
 extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps);
diff --git a/kernel/capability.c b/kernel/capability.c
index 493d97259484..f6c2ce5701e1 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -392,6 +392,30 @@ bool ns_capable(struct user_namespace *ns, int cap)
 }
 EXPORT_SYMBOL(ns_capable);
 
+/**
+ * file_ns_capable - Determine if the file's opener had a capability in effect
+ * @file:  The file we want to check
+ * @ns:  The usernamespace we want the capability in
+ * @cap: The capability to be tested for
+ *
+ * Return true if task that opened the file had a capability in effect
+ * when the file was opened.
+ *
+ * This does not set PF_SUPERPRIV because the caller may not
+ * actually be privileged.
+ */
+bool file_ns_capable(const struct file *file, struct user_namespace *ns, int cap)
+{
+	if (WARN_ON_ONCE(!cap_valid(cap)))
+		return false;
+
+	if (security_capable(file->f_cred, ns, cap) == 0)
+		return true;
+
+	return false;
+}
+EXPORT_SYMBOL(file_ns_capable);
+
 /**
  * capable - Determine if the current task has a superior capability in effect
  * @cap: The capability to be tested for
-- 
cgit v1.2.3


From f88c91ddba958e9a5dd4a5ee8c52a0faa790f586 Mon Sep 17 00:00:00 2001
From: Cong Wang <amwang@redhat.com>
Date: Sun, 14 Apr 2013 23:18:43 +0800
Subject: ipv6: statically link register_inet6addr_notifier()

Tomas reported the following build error:

net/built-in.o: In function `ieee80211_unregister_hw':
(.text+0x10f0e1): undefined reference to `unregister_inet6addr_notifier'
net/built-in.o: In function `ieee80211_register_hw':
(.text+0x10f610): undefined reference to `register_inet6addr_notifier'
make: *** [vmlinux] Error 1

when built IPv6 as a module.

So we have to statically link these symbols.

Reported-by: Tomas Melin <tomas.melin@iki.fi>
Cc: Tomas Melin <tomas.melin@iki.fi>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: YOSHIFUJI Hidaki <yoshfuji@linux-ipv6.org>
Signed-off-by: Cong Wang <amwang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/addrconf.h   |  1 +
 net/ipv6/addrconf.c      | 24 +++---------------------
 net/ipv6/addrconf_core.c | 19 +++++++++++++++++++
 3 files changed, 23 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 40be2a0d8ae1..84a6440f1f19 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -199,6 +199,7 @@ extern bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev,
 /* Device notifier */
 extern int register_inet6addr_notifier(struct notifier_block *nb);
 extern int unregister_inet6addr_notifier(struct notifier_block *nb);
+extern int inet6addr_notifier_call_chain(unsigned long val, void *v);
 
 extern void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex,
 					 struct ipv6_devconf *devconf);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index a459c4f5b769..dae802c0af7c 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -168,8 +168,6 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev,
 static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr,
 			       struct net_device *dev);
 
-static ATOMIC_NOTIFIER_HEAD(inet6addr_chain);
-
 static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.forwarding		= 0,
 	.hop_limit		= IPV6_DEFAULT_HOPLIMIT,
@@ -837,7 +835,7 @@ out2:
 	rcu_read_unlock_bh();
 
 	if (likely(err == 0))
-		atomic_notifier_call_chain(&inet6addr_chain, NETDEV_UP, ifa);
+		inet6addr_notifier_call_chain(NETDEV_UP, ifa);
 	else {
 		kfree(ifa);
 		ifa = ERR_PTR(err);
@@ -927,7 +925,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
 
 	ipv6_ifa_notify(RTM_DELADDR, ifp);
 
-	atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifp);
+	inet6addr_notifier_call_chain(NETDEV_DOWN, ifp);
 
 	/*
 	 * Purge or update corresponding prefix
@@ -2988,7 +2986,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 
 		if (state != INET6_IFADDR_STATE_DEAD) {
 			__ipv6_ifa_notify(RTM_DELADDR, ifa);
-			atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifa);
+			inet6addr_notifier_call_chain(NETDEV_DOWN, ifa);
 		}
 		in6_ifa_put(ifa);
 
@@ -4869,22 +4867,6 @@ static struct pernet_operations addrconf_ops = {
 	.exit = addrconf_exit_net,
 };
 
-/*
- *      Device notifier
- */
-
-int register_inet6addr_notifier(struct notifier_block *nb)
-{
-	return atomic_notifier_chain_register(&inet6addr_chain, nb);
-}
-EXPORT_SYMBOL(register_inet6addr_notifier);
-
-int unregister_inet6addr_notifier(struct notifier_block *nb)
-{
-	return atomic_notifier_chain_unregister(&inet6addr_chain, nb);
-}
-EXPORT_SYMBOL(unregister_inet6addr_notifier);
-
 static struct rtnl_af_ops inet6_ops = {
 	.family		  = AF_INET6,
 	.fill_link_af	  = inet6_fill_link_af,
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index d051e5f4bf34..72104562c864 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -78,3 +78,22 @@ int __ipv6_addr_type(const struct in6_addr *addr)
 }
 EXPORT_SYMBOL(__ipv6_addr_type);
 
+static ATOMIC_NOTIFIER_HEAD(inet6addr_chain);
+
+int register_inet6addr_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_register(&inet6addr_chain, nb);
+}
+EXPORT_SYMBOL(register_inet6addr_notifier);
+
+int unregister_inet6addr_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_unregister(&inet6addr_chain, nb);
+}
+EXPORT_SYMBOL(unregister_inet6addr_notifier);
+
+int inet6addr_notifier_call_chain(unsigned long val, void *v)
+{
+	return atomic_notifier_call_chain(&inet6addr_chain, val, v);
+}
+EXPORT_SYMBOL(inet6addr_notifier_call_chain);
-- 
cgit v1.2.3


From 0635eb8a54cf0fea64b174bb68bc36b9c3d622db Mon Sep 17 00:00:00 2001
From: Matthew Garrett <matthew.garrett@nebula.com>
Date: Mon, 15 Apr 2013 13:09:45 -0700
Subject: Move utf16 functions to kernel core and rename

We want to be able to use the utf16 functions that are currently present
in the EFI variables code in platform-specific code as well. Move them to
the kernel core, and in the process rename them to accurately describe what
they do - they don't handle UTF16, only UCS2.

Signed-off-by: Matthew Garrett <matthew.garrett@nebula.com>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
---
 drivers/firmware/Kconfig    |  1 +
 drivers/firmware/efivars.c  | 80 ++++++++++-----------------------------------
 include/linux/ucs2_string.h | 14 ++++++++
 lib/Kconfig                 |  3 ++
 lib/Makefile                |  2 ++
 lib/ucs2_string.c           | 51 +++++++++++++++++++++++++++++
 6 files changed, 89 insertions(+), 62 deletions(-)
 create mode 100644 include/linux/ucs2_string.h
 create mode 100644 lib/ucs2_string.c

(limited to 'include')

diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index 42c759a4d047..3e532002e4d1 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -39,6 +39,7 @@ config FIRMWARE_MEMMAP
 config EFI_VARS
 	tristate "EFI Variable Support via sysfs"
 	depends on EFI
+	select UCS2_STRING
 	default n
 	help
 	  If you say Y here, you are able to get EFI (Extensible Firmware
diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c
index bf15d81d74e1..182ce9471175 100644
--- a/drivers/firmware/efivars.c
+++ b/drivers/firmware/efivars.c
@@ -80,6 +80,7 @@
 #include <linux/slab.h>
 #include <linux/pstore.h>
 #include <linux/ctype.h>
+#include <linux/ucs2_string.h>
 
 #include <linux/fs.h>
 #include <linux/ramfs.h>
@@ -172,51 +173,6 @@ static void efivar_update_sysfs_entries(struct work_struct *);
 static DECLARE_WORK(efivar_work, efivar_update_sysfs_entries);
 static bool efivar_wq_enabled = true;
 
-/* Return the number of unicode characters in data */
-static unsigned long
-utf16_strnlen(efi_char16_t *s, size_t maxlength)
-{
-	unsigned long length = 0;
-
-	while (*s++ != 0 && length < maxlength)
-		length++;
-	return length;
-}
-
-static inline unsigned long
-utf16_strlen(efi_char16_t *s)
-{
-	return utf16_strnlen(s, ~0UL);
-}
-
-/*
- * Return the number of bytes is the length of this string
- * Note: this is NOT the same as the number of unicode characters
- */
-static inline unsigned long
-utf16_strsize(efi_char16_t *data, unsigned long maxlength)
-{
-	return utf16_strnlen(data, maxlength/sizeof(efi_char16_t)) * sizeof(efi_char16_t);
-}
-
-static inline int
-utf16_strncmp(const efi_char16_t *a, const efi_char16_t *b, size_t len)
-{
-	while (1) {
-		if (len == 0)
-			return 0;
-		if (*a < *b)
-			return -1;
-		if (*a > *b)
-			return 1;
-		if (*a == 0) /* implies *b == 0 */
-			return 0;
-		a++;
-		b++;
-		len--;
-	}
-}
-
 static bool
 validate_device_path(struct efi_variable *var, int match, u8 *buffer,
 		     unsigned long len)
@@ -268,7 +224,7 @@ validate_load_option(struct efi_variable *var, int match, u8 *buffer,
 	u16 filepathlength;
 	int i, desclength = 0, namelen;
 
-	namelen = utf16_strnlen(var->VariableName, sizeof(var->VariableName));
+	namelen = ucs2_strnlen(var->VariableName, sizeof(var->VariableName));
 
 	/* Either "Boot" or "Driver" followed by four digits of hex */
 	for (i = match; i < match+4; i++) {
@@ -291,7 +247,7 @@ validate_load_option(struct efi_variable *var, int match, u8 *buffer,
 	 * There's no stored length for the description, so it has to be
 	 * found by hand
 	 */
-	desclength = utf16_strsize((efi_char16_t *)(buffer + 6), len - 6) + 2;
+	desclength = ucs2_strsize((efi_char16_t *)(buffer + 6), len - 6) + 2;
 
 	/* Each boot entry must have a descriptor */
 	if (!desclength)
@@ -581,7 +537,7 @@ efivar_store_raw(struct efivar_entry *entry, const char *buf, size_t count)
 	spin_lock_irq(&efivars->lock);
 
 	status = check_var_size_locked(efivars, new_var->Attributes,
-	       new_var->DataSize + utf16_strsize(new_var->VariableName, 1024));
+	       new_var->DataSize + ucs2_strsize(new_var->VariableName, 1024));
 
 	if (status == EFI_SUCCESS || status == EFI_UNSUPPORTED)
 		status = efivars->ops->set_variable(new_var->VariableName,
@@ -759,7 +715,7 @@ static ssize_t efivarfs_file_write(struct file *file,
 	 * QueryVariableInfo() isn't supported by the firmware.
 	 */
 
-	varsize = datasize + utf16_strsize(var->var.VariableName, 1024);
+	varsize = datasize + ucs2_strsize(var->var.VariableName, 1024);
 	status = check_var_size(efivars, attributes, varsize);
 
 	if (status != EFI_SUCCESS) {
@@ -1211,7 +1167,7 @@ static int efivarfs_fill_super(struct super_block *sb, void *data, int silent)
 
 		inode = NULL;
 
-		len = utf16_strlen(entry->var.VariableName);
+		len = ucs2_strlen(entry->var.VariableName);
 
 		/* name, plus '-', plus GUID, plus NUL*/
 		name = kmalloc(len + 1 + GUID_LEN + 1, GFP_ATOMIC);
@@ -1469,8 +1425,8 @@ static int efi_pstore_erase(enum pstore_type_id type, u64 id, int count,
 
 		if (efi_guidcmp(entry->var.VendorGuid, vendor))
 			continue;
-		if (utf16_strncmp(entry->var.VariableName, efi_name,
-				  utf16_strlen(efi_name))) {
+		if (ucs2_strncmp(entry->var.VariableName, efi_name,
+				  ucs2_strlen(efi_name))) {
 			/*
 			 * Check if an old format,
 			 * which doesn't support holding
@@ -1482,8 +1438,8 @@ static int efi_pstore_erase(enum pstore_type_id type, u64 id, int count,
 			for (i = 0; i < DUMP_NAME_LEN; i++)
 				efi_name_old[i] = name_old[i];
 
-			if (utf16_strncmp(entry->var.VariableName, efi_name_old,
-					  utf16_strlen(efi_name_old)))
+			if (ucs2_strncmp(entry->var.VariableName, efi_name_old,
+					  ucs2_strlen(efi_name_old)))
 				continue;
 		}
 
@@ -1561,8 +1517,8 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj,
 	 * Does this variable already exist?
 	 */
 	list_for_each_entry_safe(search_efivar, n, &efivars->list, list) {
-		strsize1 = utf16_strsize(search_efivar->var.VariableName, 1024);
-		strsize2 = utf16_strsize(new_var->VariableName, 1024);
+		strsize1 = ucs2_strsize(search_efivar->var.VariableName, 1024);
+		strsize2 = ucs2_strsize(new_var->VariableName, 1024);
 		if (strsize1 == strsize2 &&
 			!memcmp(&(search_efivar->var.VariableName),
 				new_var->VariableName, strsize1) &&
@@ -1578,7 +1534,7 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj,
 	}
 
 	status = check_var_size_locked(efivars, new_var->Attributes,
-	       new_var->DataSize + utf16_strsize(new_var->VariableName, 1024));
+	       new_var->DataSize + ucs2_strsize(new_var->VariableName, 1024));
 
 	if (status && status != EFI_UNSUPPORTED) {
 		spin_unlock_irq(&efivars->lock);
@@ -1602,7 +1558,7 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj,
 
 	/* Create the entry in sysfs.  Locking is not required here */
 	status = efivar_create_sysfs_entry(efivars,
-					   utf16_strsize(new_var->VariableName,
+					   ucs2_strsize(new_var->VariableName,
 							 1024),
 					   new_var->VariableName,
 					   &new_var->VendorGuid);
@@ -1632,8 +1588,8 @@ static ssize_t efivar_delete(struct file *filp, struct kobject *kobj,
 	 * Does this variable already exist?
 	 */
 	list_for_each_entry_safe(search_efivar, n, &efivars->list, list) {
-		strsize1 = utf16_strsize(search_efivar->var.VariableName, 1024);
-		strsize2 = utf16_strsize(del_var->VariableName, 1024);
+		strsize1 = ucs2_strsize(search_efivar->var.VariableName, 1024);
+		strsize2 = ucs2_strsize(del_var->VariableName, 1024);
 		if (strsize1 == strsize2 &&
 			!memcmp(&(search_efivar->var.VariableName),
 				del_var->VariableName, strsize1) &&
@@ -1679,9 +1635,9 @@ static bool variable_is_present(efi_char16_t *variable_name, efi_guid_t *vendor)
 	unsigned long strsize1, strsize2;
 	bool found = false;
 
-	strsize1 = utf16_strsize(variable_name, 1024);
+	strsize1 = ucs2_strsize(variable_name, 1024);
 	list_for_each_entry_safe(entry, n, &efivars->list, list) {
-		strsize2 = utf16_strsize(entry->var.VariableName, 1024);
+		strsize2 = ucs2_strsize(entry->var.VariableName, 1024);
 		if (strsize1 == strsize2 &&
 			!memcmp(variable_name, &(entry->var.VariableName),
 				strsize2) &&
diff --git a/include/linux/ucs2_string.h b/include/linux/ucs2_string.h
new file mode 100644
index 000000000000..cbb20afdbc01
--- /dev/null
+++ b/include/linux/ucs2_string.h
@@ -0,0 +1,14 @@
+#ifndef _LINUX_UCS2_STRING_H_
+#define _LINUX_UCS2_STRING_H_
+
+#include <linux/types.h>	/* for size_t */
+#include <linux/stddef.h>	/* for NULL */
+
+typedef u16 ucs2_char_t;
+
+unsigned long ucs2_strnlen(const ucs2_char_t *s, size_t maxlength);
+unsigned long ucs2_strlen(const ucs2_char_t *s);
+unsigned long ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength);
+int ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len);
+
+#endif /* _LINUX_UCS2_STRING_H_ */
diff --git a/lib/Kconfig b/lib/Kconfig
index 3958dc4389f9..fe01d418b09a 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -404,4 +404,7 @@ config OID_REGISTRY
 	help
 	  Enable fast lookup object identifier registry.
 
+config UCS2_STRING
+        tristate
+
 endmenu
diff --git a/lib/Makefile b/lib/Makefile
index d7946ff75b2e..6e2cc561f761 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -174,3 +174,5 @@ quiet_cmd_build_OID_registry = GEN     $@
       cmd_build_OID_registry = perl $(srctree)/$(src)/build_OID_registry $< $@
 
 clean-files	+= oid_registry_data.c
+
+obj-$(CONFIG_UCS2_STRING) += ucs2_string.o
diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c
new file mode 100644
index 000000000000..6f500ef2301d
--- /dev/null
+++ b/lib/ucs2_string.c
@@ -0,0 +1,51 @@
+#include <linux/ucs2_string.h>
+#include <linux/module.h>
+
+/* Return the number of unicode characters in data */
+unsigned long
+ucs2_strnlen(const ucs2_char_t *s, size_t maxlength)
+{
+        unsigned long length = 0;
+
+        while (*s++ != 0 && length < maxlength)
+                length++;
+        return length;
+}
+EXPORT_SYMBOL(ucs2_strnlen);
+
+unsigned long
+ucs2_strlen(const ucs2_char_t *s)
+{
+        return ucs2_strnlen(s, ~0UL);
+}
+EXPORT_SYMBOL(ucs2_strlen);
+
+/*
+ * Return the number of bytes is the length of this string
+ * Note: this is NOT the same as the number of unicode characters
+ */
+unsigned long
+ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength)
+{
+        return ucs2_strnlen(data, maxlength/sizeof(ucs2_char_t)) * sizeof(ucs2_char_t);
+}
+EXPORT_SYMBOL(ucs2_strsize);
+
+int
+ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len)
+{
+        while (1) {
+                if (len == 0)
+                        return 0;
+                if (*a < *b)
+                        return -1;
+                if (*a > *b)
+                        return 1;
+                if (*a == 0) /* implies *b == 0 */
+                        return 0;
+                a++;
+                b++;
+                len--;
+        }
+}
+EXPORT_SYMBOL(ucs2_strncmp);
-- 
cgit v1.2.3


From b4cbb197c7e7a68dbad0d491242e3ca67420c13e Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Tue, 16 Apr 2013 13:45:37 -0700
Subject: vm: add vm_iomap_memory() helper function

Various drivers end up replicating the code to mmap() their memory
buffers into user space, and our core memory remapping function may be
very flexible but it is unnecessarily complicated for the common cases
to use.

Our internal VM uses pfn's ("page frame numbers") which simplifies
things for the VM, and allows us to pass physical addresses around in a
denser and more efficient format than passing a "phys_addr_t" around,
and having to shift it up and down by the page size.  But it just means
that drivers end up doing that shifting instead at the interface level.

It also means that drivers end up mucking around with internal VM things
like the vma details (vm_pgoff, vm_start/end) way more than they really
need to.

So this just exports a function to map a certain physical memory range
into user space (using a phys_addr_t based interface that is much more
natural for a driver) and hides all the complexity from the driver.
Some drivers will still end up tweaking the vm_page_prot details for
things like prefetching or cacheability etc, but that's actually
relevant to the driver, rather than caring about what the page offset of
the mapping is into the particular IO memory region.

Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h |  2 ++
 mm/memory.c        | 47 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 49 insertions(+)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index e19ff30ad0a2..e2091b88d24c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1611,6 +1611,8 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn);
 int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn);
+int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len);
+
 
 struct page *follow_page_mask(struct vm_area_struct *vma,
 			      unsigned long address, unsigned int foll_flags,
diff --git a/mm/memory.c b/mm/memory.c
index 13cbc420fead..ba94dec5b259 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2393,6 +2393,53 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 }
 EXPORT_SYMBOL(remap_pfn_range);
 
+/**
+ * vm_iomap_memory - remap memory to userspace
+ * @vma: user vma to map to
+ * @start: start of area
+ * @len: size of area
+ *
+ * This is a simplified io_remap_pfn_range() for common driver use. The
+ * driver just needs to give us the physical memory range to be mapped,
+ * we'll figure out the rest from the vma information.
+ *
+ * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get
+ * whatever write-combining details or similar.
+ */
+int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len)
+{
+	unsigned long vm_len, pfn, pages;
+
+	/* Check that the physical memory area passed in looks valid */
+	if (start + len < start)
+		return -EINVAL;
+	/*
+	 * You *really* shouldn't map things that aren't page-aligned,
+	 * but we've historically allowed it because IO memory might
+	 * just have smaller alignment.
+	 */
+	len += start & ~PAGE_MASK;
+	pfn = start >> PAGE_SHIFT;
+	pages = (len + ~PAGE_MASK) >> PAGE_SHIFT;
+	if (pfn + pages < pfn)
+		return -EINVAL;
+
+	/* We start the mapping 'vm_pgoff' pages into the area */
+	if (vma->vm_pgoff > pages)
+		return -EINVAL;
+	pfn += vma->vm_pgoff;
+	pages -= vma->vm_pgoff;
+
+	/* Can we fit all of the mapping? */
+	vm_len = vma->vm_end - vma->vm_start;
+	if (vm_len >> PAGE_SHIFT > pages)
+		return -EINVAL;
+
+	/* Ok, let it rip */
+	return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot);
+}
+EXPORT_SYMBOL(vm_iomap_memory);
+
 static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				     unsigned long addr, unsigned long end,
 				     pte_fn_t fn, void *data)
-- 
cgit v1.2.3


From 4c82456eeb4da081dd63dc69e91aa6deabd29e03 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@suse.cz>
Date: Wed, 17 Apr 2013 12:30:40 +0200
Subject: fuse: fix type definitions in uapi header
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 7e98d53086d18c877cb44e9065219335184024de (Synchronize fuse header with
one used in library) added #ifdef __linux__ around defines if it is not set.
The kernel build is self-contained and can be built on non-Linux toolchains.
After the mentioned commit builds on non-Linux toolchains will try to include
stdint.h and fail due to -nostdinc, and then fail with a bunch of undefined type
errors.

Fix by checking for __KERNEL__ instead of __linux__ and using the standard int
types instead of the linux specific ones.

Reported-by: Arve Hjønnevåg <arve@android.com>
Reported-by: Colin Cross <ccross@android.com>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
---
 include/uapi/linux/fuse.h | 436 +++++++++++++++++++++++-----------------------
 1 file changed, 216 insertions(+), 220 deletions(-)

(limited to 'include')

diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 4c43b4448792..706d035fa748 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -95,15 +95,10 @@
 #ifndef _LINUX_FUSE_H
 #define _LINUX_FUSE_H
 
-#ifdef __linux__
+#ifdef __KERNEL__
 #include <linux/types.h>
 #else
 #include <stdint.h>
-#define __u64 uint64_t
-#define __s64 int64_t
-#define __u32 uint32_t
-#define __s32 int32_t
-#define __u16 uint16_t
 #endif
 
 /*
@@ -139,42 +134,42 @@
    userspace works under 64bit kernels */
 
 struct fuse_attr {
-	__u64	ino;
-	__u64	size;
-	__u64	blocks;
-	__u64	atime;
-	__u64	mtime;
-	__u64	ctime;
-	__u32	atimensec;
-	__u32	mtimensec;
-	__u32	ctimensec;
-	__u32	mode;
-	__u32	nlink;
-	__u32	uid;
-	__u32	gid;
-	__u32	rdev;
-	__u32	blksize;
-	__u32	padding;
+	uint64_t	ino;
+	uint64_t	size;
+	uint64_t	blocks;
+	uint64_t	atime;
+	uint64_t	mtime;
+	uint64_t	ctime;
+	uint32_t	atimensec;
+	uint32_t	mtimensec;
+	uint32_t	ctimensec;
+	uint32_t	mode;
+	uint32_t	nlink;
+	uint32_t	uid;
+	uint32_t	gid;
+	uint32_t	rdev;
+	uint32_t	blksize;
+	uint32_t	padding;
 };
 
 struct fuse_kstatfs {
-	__u64	blocks;
-	__u64	bfree;
-	__u64	bavail;
-	__u64	files;
-	__u64	ffree;
-	__u32	bsize;
-	__u32	namelen;
-	__u32	frsize;
-	__u32	padding;
-	__u32	spare[6];
+	uint64_t	blocks;
+	uint64_t	bfree;
+	uint64_t	bavail;
+	uint64_t	files;
+	uint64_t	ffree;
+	uint32_t	bsize;
+	uint32_t	namelen;
+	uint32_t	frsize;
+	uint32_t	padding;
+	uint32_t	spare[6];
 };
 
 struct fuse_file_lock {
-	__u64	start;
-	__u64	end;
-	__u32	type;
-	__u32	pid; /* tgid */
+	uint64_t	start;
+	uint64_t	end;
+	uint32_t	type;
+	uint32_t	pid; /* tgid */
 };
 
 /**
@@ -364,143 +359,143 @@ enum fuse_notify_code {
 #define FUSE_COMPAT_ENTRY_OUT_SIZE 120
 
 struct fuse_entry_out {
-	__u64	nodeid;		/* Inode ID */
-	__u64	generation;	/* Inode generation: nodeid:gen must
-				   be unique for the fs's lifetime */
-	__u64	entry_valid;	/* Cache timeout for the name */
-	__u64	attr_valid;	/* Cache timeout for the attributes */
-	__u32	entry_valid_nsec;
-	__u32	attr_valid_nsec;
+	uint64_t	nodeid;		/* Inode ID */
+	uint64_t	generation;	/* Inode generation: nodeid:gen must
+					   be unique for the fs's lifetime */
+	uint64_t	entry_valid;	/* Cache timeout for the name */
+	uint64_t	attr_valid;	/* Cache timeout for the attributes */
+	uint32_t	entry_valid_nsec;
+	uint32_t	attr_valid_nsec;
 	struct fuse_attr attr;
 };
 
 struct fuse_forget_in {
-	__u64	nlookup;
+	uint64_t	nlookup;
 };
 
 struct fuse_forget_one {
-	__u64	nodeid;
-	__u64	nlookup;
+	uint64_t	nodeid;
+	uint64_t	nlookup;
 };
 
 struct fuse_batch_forget_in {
-	__u32	count;
-	__u32	dummy;
+	uint32_t	count;
+	uint32_t	dummy;
 };
 
 struct fuse_getattr_in {
-	__u32	getattr_flags;
-	__u32	dummy;
-	__u64	fh;
+	uint32_t	getattr_flags;
+	uint32_t	dummy;
+	uint64_t	fh;
 };
 
 #define FUSE_COMPAT_ATTR_OUT_SIZE 96
 
 struct fuse_attr_out {
-	__u64	attr_valid;	/* Cache timeout for the attributes */
-	__u32	attr_valid_nsec;
-	__u32	dummy;
+	uint64_t	attr_valid;	/* Cache timeout for the attributes */
+	uint32_t	attr_valid_nsec;
+	uint32_t	dummy;
 	struct fuse_attr attr;
 };
 
 #define FUSE_COMPAT_MKNOD_IN_SIZE 8
 
 struct fuse_mknod_in {
-	__u32	mode;
-	__u32	rdev;
-	__u32	umask;
-	__u32	padding;
+	uint32_t	mode;
+	uint32_t	rdev;
+	uint32_t	umask;
+	uint32_t	padding;
 };
 
 struct fuse_mkdir_in {
-	__u32	mode;
-	__u32	umask;
+	uint32_t	mode;
+	uint32_t	umask;
 };
 
 struct fuse_rename_in {
-	__u64	newdir;
+	uint64_t	newdir;
 };
 
 struct fuse_link_in {
-	__u64	oldnodeid;
+	uint64_t	oldnodeid;
 };
 
 struct fuse_setattr_in {
-	__u32	valid;
-	__u32	padding;
-	__u64	fh;
-	__u64	size;
-	__u64	lock_owner;
-	__u64	atime;
-	__u64	mtime;
-	__u64	unused2;
-	__u32	atimensec;
-	__u32	mtimensec;
-	__u32	unused3;
-	__u32	mode;
-	__u32	unused4;
-	__u32	uid;
-	__u32	gid;
-	__u32	unused5;
+	uint32_t	valid;
+	uint32_t	padding;
+	uint64_t	fh;
+	uint64_t	size;
+	uint64_t	lock_owner;
+	uint64_t	atime;
+	uint64_t	mtime;
+	uint64_t	unused2;
+	uint32_t	atimensec;
+	uint32_t	mtimensec;
+	uint32_t	unused3;
+	uint32_t	mode;
+	uint32_t	unused4;
+	uint32_t	uid;
+	uint32_t	gid;
+	uint32_t	unused5;
 };
 
 struct fuse_open_in {
-	__u32	flags;
-	__u32	unused;
+	uint32_t	flags;
+	uint32_t	unused;
 };
 
 struct fuse_create_in {
-	__u32	flags;
-	__u32	mode;
-	__u32	umask;
-	__u32	padding;
+	uint32_t	flags;
+	uint32_t	mode;
+	uint32_t	umask;
+	uint32_t	padding;
 };
 
 struct fuse_open_out {
-	__u64	fh;
-	__u32	open_flags;
-	__u32	padding;
+	uint64_t	fh;
+	uint32_t	open_flags;
+	uint32_t	padding;
 };
 
 struct fuse_release_in {
-	__u64	fh;
-	__u32	flags;
-	__u32	release_flags;
-	__u64	lock_owner;
+	uint64_t	fh;
+	uint32_t	flags;
+	uint32_t	release_flags;
+	uint64_t	lock_owner;
 };
 
 struct fuse_flush_in {
-	__u64	fh;
-	__u32	unused;
-	__u32	padding;
-	__u64	lock_owner;
+	uint64_t	fh;
+	uint32_t	unused;
+	uint32_t	padding;
+	uint64_t	lock_owner;
 };
 
 struct fuse_read_in {
-	__u64	fh;
-	__u64	offset;
-	__u32	size;
-	__u32	read_flags;
-	__u64	lock_owner;
-	__u32	flags;
-	__u32	padding;
+	uint64_t	fh;
+	uint64_t	offset;
+	uint32_t	size;
+	uint32_t	read_flags;
+	uint64_t	lock_owner;
+	uint32_t	flags;
+	uint32_t	padding;
 };
 
 #define FUSE_COMPAT_WRITE_IN_SIZE 24
 
 struct fuse_write_in {
-	__u64	fh;
-	__u64	offset;
-	__u32	size;
-	__u32	write_flags;
-	__u64	lock_owner;
-	__u32	flags;
-	__u32	padding;
+	uint64_t	fh;
+	uint64_t	offset;
+	uint32_t	size;
+	uint32_t	write_flags;
+	uint64_t	lock_owner;
+	uint32_t	flags;
+	uint32_t	padding;
 };
 
 struct fuse_write_out {
-	__u32	size;
-	__u32	padding;
+	uint32_t	size;
+	uint32_t	padding;
 };
 
 #define FUSE_COMPAT_STATFS_SIZE 48
@@ -510,32 +505,32 @@ struct fuse_statfs_out {
 };
 
 struct fuse_fsync_in {
-	__u64	fh;
-	__u32	fsync_flags;
-	__u32	padding;
+	uint64_t	fh;
+	uint32_t	fsync_flags;
+	uint32_t	padding;
 };
 
 struct fuse_setxattr_in {
-	__u32	size;
-	__u32	flags;
+	uint32_t	size;
+	uint32_t	flags;
 };
 
 struct fuse_getxattr_in {
-	__u32	size;
-	__u32	padding;
+	uint32_t	size;
+	uint32_t	padding;
 };
 
 struct fuse_getxattr_out {
-	__u32	size;
-	__u32	padding;
+	uint32_t	size;
+	uint32_t	padding;
 };
 
 struct fuse_lk_in {
-	__u64	fh;
-	__u64	owner;
+	uint64_t	fh;
+	uint64_t	owner;
 	struct fuse_file_lock lk;
-	__u32	lk_flags;
-	__u32	padding;
+	uint32_t	lk_flags;
+	uint32_t	padding;
 };
 
 struct fuse_lk_out {
@@ -543,134 +538,135 @@ struct fuse_lk_out {
 };
 
 struct fuse_access_in {
-	__u32	mask;
-	__u32	padding;
+	uint32_t	mask;
+	uint32_t	padding;
 };
 
 struct fuse_init_in {
-	__u32	major;
-	__u32	minor;
-	__u32	max_readahead;
-	__u32	flags;
+	uint32_t	major;
+	uint32_t	minor;
+	uint32_t	max_readahead;
+	uint32_t	flags;
 };
 
 struct fuse_init_out {
-	__u32	major;
-	__u32	minor;
-	__u32	max_readahead;
-	__u32	flags;
-	__u16   max_background;
-	__u16   congestion_threshold;
-	__u32	max_write;
+	uint32_t	major;
+	uint32_t	minor;
+	uint32_t	max_readahead;
+	uint32_t	flags;
+	uint16_t	max_background;
+	uint16_t	congestion_threshold;
+	uint32_t	max_write;
 };
 
 #define CUSE_INIT_INFO_MAX 4096
 
 struct cuse_init_in {
-	__u32	major;
-	__u32	minor;
-	__u32	unused;
-	__u32	flags;
+	uint32_t	major;
+	uint32_t	minor;
+	uint32_t	unused;
+	uint32_t	flags;
 };
 
 struct cuse_init_out {
-	__u32	major;
-	__u32	minor;
-	__u32	unused;
-	__u32	flags;
-	__u32	max_read;
-	__u32	max_write;
-	__u32	dev_major;		/* chardev major */
-	__u32	dev_minor;		/* chardev minor */
-	__u32	spare[10];
+	uint32_t	major;
+	uint32_t	minor;
+	uint32_t	unused;
+	uint32_t	flags;
+	uint32_t	max_read;
+	uint32_t	max_write;
+	uint32_t	dev_major;		/* chardev major */
+	uint32_t	dev_minor;		/* chardev minor */
+	uint32_t	spare[10];
 };
 
 struct fuse_interrupt_in {
-	__u64	unique;
+	uint64_t	unique;
 };
 
 struct fuse_bmap_in {
-	__u64	block;
-	__u32	blocksize;
-	__u32	padding;
+	uint64_t	block;
+	uint32_t	blocksize;
+	uint32_t	padding;
 };
 
 struct fuse_bmap_out {
-	__u64	block;
+	uint64_t	block;
 };
 
 struct fuse_ioctl_in {
-	__u64	fh;
-	__u32	flags;
-	__u32	cmd;
-	__u64	arg;
-	__u32	in_size;
-	__u32	out_size;
+	uint64_t	fh;
+	uint32_t	flags;
+	uint32_t	cmd;
+	uint64_t	arg;
+	uint32_t	in_size;
+	uint32_t	out_size;
 };
 
 struct fuse_ioctl_iovec {
-	__u64	base;
-	__u64	len;
+	uint64_t	base;
+	uint64_t	len;
 };
 
 struct fuse_ioctl_out {
-	__s32	result;
-	__u32	flags;
-	__u32	in_iovs;
-	__u32	out_iovs;
+	int32_t		result;
+	uint32_t	flags;
+	uint32_t	in_iovs;
+	uint32_t	out_iovs;
 };
 
 struct fuse_poll_in {
-	__u64	fh;
-	__u64	kh;
-	__u32	flags;
-	__u32   events;
+	uint64_t	fh;
+	uint64_t	kh;
+	uint32_t	flags;
+	uint32_t	events;
 };
 
 struct fuse_poll_out {
-	__u32	revents;
-	__u32	padding;
+	uint32_t	revents;
+	uint32_t	padding;
 };
 
 struct fuse_notify_poll_wakeup_out {
-	__u64	kh;
+	uint64_t	kh;
 };
 
 struct fuse_fallocate_in {
-	__u64	fh;
-	__u64	offset;
-	__u64	length;
-	__u32	mode;
-	__u32	padding;
+	uint64_t	fh;
+	uint64_t	offset;
+	uint64_t	length;
+	uint32_t	mode;
+	uint32_t	padding;
 };
 
 struct fuse_in_header {
-	__u32	len;
-	__u32	opcode;
-	__u64	unique;
-	__u64	nodeid;
-	__u32	uid;
-	__u32	gid;
-	__u32	pid;
-	__u32	padding;
+	uint32_t	len;
+	uint32_t	opcode;
+	uint64_t	unique;
+	uint64_t	nodeid;
+	uint32_t	uid;
+	uint32_t	gid;
+	uint32_t	pid;
+	uint32_t	padding;
 };
 
 struct fuse_out_header {
-	__u32	len;
-	__s32	error;
-	__u64	unique;
+	uint32_t	len;
+	int32_t		error;
+	uint64_t	unique;
 };
 
 struct fuse_dirent {
-	__u64	ino;
-	__u64	off;
-	__u32	namelen;
-	__u32	type;
+	uint64_t	ino;
+	uint64_t	off;
+	uint32_t	namelen;
+	uint32_t	type;
 	char name[];
 };
 
 #define FUSE_NAME_OFFSET offsetof(struct fuse_dirent, name)
-#define FUSE_DIRENT_ALIGN(x) (((x) + sizeof(__u64) - 1) & ~(sizeof(__u64) - 1))
+#define FUSE_DIRENT_ALIGN(x) \
+	(((x) + sizeof(uint64_t) - 1) & ~(sizeof(uint64_t) - 1))
 #define FUSE_DIRENT_SIZE(d) \
 	FUSE_DIRENT_ALIGN(FUSE_NAME_OFFSET + (d)->namelen)
 
@@ -685,47 +681,47 @@ struct fuse_direntplus {
 	FUSE_DIRENT_ALIGN(FUSE_NAME_OFFSET_DIRENTPLUS + (d)->dirent.namelen)
 
 struct fuse_notify_inval_inode_out {
-	__u64	ino;
-	__s64	off;
-	__s64	len;
+	uint64_t	ino;
+	int64_t		off;
+	int64_t		len;
 };
 
 struct fuse_notify_inval_entry_out {
-	__u64	parent;
-	__u32	namelen;
-	__u32	padding;
+	uint64_t	parent;
+	uint32_t	namelen;
+	uint32_t	padding;
 };
 
 struct fuse_notify_delete_out {
-	__u64	parent;
-	__u64	child;
-	__u32	namelen;
-	__u32	padding;
+	uint64_t	parent;
+	uint64_t	child;
+	uint32_t	namelen;
+	uint32_t	padding;
 };
 
 struct fuse_notify_store_out {
-	__u64	nodeid;
-	__u64	offset;
-	__u32	size;
-	__u32	padding;
+	uint64_t	nodeid;
+	uint64_t	offset;
+	uint32_t	size;
+	uint32_t	padding;
 };
 
 struct fuse_notify_retrieve_out {
-	__u64	notify_unique;
-	__u64	nodeid;
-	__u64	offset;
-	__u32	size;
-	__u32	padding;
+	uint64_t	notify_unique;
+	uint64_t	nodeid;
+	uint64_t	offset;
+	uint32_t	size;
+	uint32_t	padding;
 };
 
 /* Matches the size of fuse_write_in */
 struct fuse_notify_retrieve_in {
-	__u64	dummy1;
-	__u64	offset;
-	__u32	size;
-	__u32	dummy2;
-	__u64	dummy3;
-	__u64	dummy4;
+	uint64_t	dummy1;
+	uint64_t	offset;
+	uint32_t	size;
+	uint32_t	dummy2;
+	uint64_t	dummy3;
+	uint64_t	dummy4;
 };
 
 #endif /* _LINUX_FUSE_H */
-- 
cgit v1.2.3


From c729de8fcea37a1c444e81857eace12494c804a9 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Mon, 15 Apr 2013 22:23:45 -0700
Subject: x86, kdump: Set crashkernel_low automatically

Chao said that kdump does does work well on his system on 3.8
without extra parameter, even iommu does not work with kdump.
And now have to append crashkernel_low=Y in first kernel to make
kdump work.

We have now modified crashkernel=X to allocate memory beyong 4G (if
available) and do not allocate low range for crashkernel if the user
does not specify that with crashkernel_low=Y.  This causes regression
if iommu is not enabled.  Without iommu, swiotlb needs to be setup in
first 4G and there is no low memory available to second kernel.

Set crashkernel_low automatically if the user does not specify that.

For system that does support IOMMU with kdump properly, user could
specify crashkernel_low=0 to save that 72M low ram.

-v3: add swiotlb_size() according to Konrad.
-v4: add comments what 8M is for according to hpa.
     also update more crashkernel_low= in kernel-parameters.txt
-v5: update changelog according to Vivek.
-v6: Change description about swiotlb referring according to HATAYAMA.

Reported-by: WANG Chao <chaowang@redhat.com>
Tested-by: WANG Chao <chaowang@redhat.com>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/1366089828-19692-2-git-send-email-yinghai@kernel.org
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 Documentation/kernel-parameters.txt | 14 +++++++++++---
 arch/x86/kernel/setup.c             | 21 ++++++++++++++++++---
 include/linux/swiotlb.h             |  1 +
 lib/swiotlb.c                       | 19 +++++++++++++++----
 4 files changed, 45 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 4609e81dbc37..cff672da2486 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -596,9 +596,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			is selected automatically. Check
 			Documentation/kdump/kdump.txt for further details.
 
-	crashkernel_low=size[KMG]
-			[KNL, x86] parts under 4G.
-
 	crashkernel=range1:size1[,range2:size2,...][@offset]
 			[KNL] Same as above, but depends on the memory
 			in the running system. The syntax of range is
@@ -606,6 +603,17 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			a memory unit (amount[KMG]). See also
 			Documentation/kdump/kdump.txt for an example.
 
+	crashkernel_low=size[KMG]
+			[KNL, x86_64] range under 4G. When crashkernel= is
+			passed, kernel allocate physical memory region
+			above 4G, that cause second kernel crash on system
+			that require some amount of low memory, e.g. swiotlb
+			requires at least 64M+32K low memory.  Kernel would
+			try to allocate 72M below 4G automatically.
+			This one let user to specify own low range under 4G
+			for second kernel instead.
+			0: to disable low allocation.
+
 	cs89x0_dma=	[HW,NET]
 			Format: <dma>
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 90d8cc930f5e..12349202cae7 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -521,19 +521,34 @@ static void __init reserve_crashkernel_low(void)
 	unsigned long long low_base = 0, low_size = 0;
 	unsigned long total_low_mem;
 	unsigned long long base;
+	bool auto_set = false;
 	int ret;
 
 	total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT));
 	ret = parse_crashkernel_low(boot_command_line, total_low_mem,
 						&low_size, &base);
-	if (ret != 0 || low_size <= 0)
-		return;
+	if (ret != 0) {
+		/*
+		 * two parts from lib/swiotlb.c:
+		 *	swiotlb size: user specified with swiotlb= or default.
+		 *	swiotlb overflow buffer: now is hardcoded to 32k.
+		 *		We round it to 8M for other buffers that
+		 *		may need to stay low too.
+		 */
+		low_size = swiotlb_size_or_default() + (8UL<<20);
+		auto_set = true;
+	} else {
+		/* passed with crashkernel_low=0 ? */
+		if (!low_size)
+			return;
+	}
 
 	low_base = memblock_find_in_range(low_size, (1ULL<<32),
 					low_size, alignment);
 
 	if (!low_base) {
-		pr_info("crashkernel low reservation failed - No suitable area found.\n");
+		if (!auto_set)
+			pr_info("crashkernel low reservation failed - No suitable area found.\n");
 
 		return;
 	}
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index 2de42f9401d2..a5ffd32642fd 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -25,6 +25,7 @@ extern int swiotlb_force;
 extern void swiotlb_init(int verbose);
 int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose);
 extern unsigned long swiotlb_nr_tbl(void);
+unsigned long swiotlb_size_or_default(void);
 extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs);
 
 /*
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index bfe02b8fc55b..d23762e6652c 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -105,9 +105,9 @@ setup_io_tlb_npages(char *str)
 	if (!strcmp(str, "force"))
 		swiotlb_force = 1;
 
-	return 1;
+	return 0;
 }
-__setup("swiotlb=", setup_io_tlb_npages);
+early_param("swiotlb", setup_io_tlb_npages);
 /* make io_tlb_overflow tunable too? */
 
 unsigned long swiotlb_nr_tbl(void)
@@ -115,6 +115,18 @@ unsigned long swiotlb_nr_tbl(void)
 	return io_tlb_nslabs;
 }
 EXPORT_SYMBOL_GPL(swiotlb_nr_tbl);
+
+/* default to 64MB */
+#define IO_TLB_DEFAULT_SIZE (64UL<<20)
+unsigned long swiotlb_size_or_default(void)
+{
+	unsigned long size;
+
+	size = io_tlb_nslabs << IO_TLB_SHIFT;
+
+	return size ? size : (IO_TLB_DEFAULT_SIZE);
+}
+
 /* Note that this doesn't work with highmem page */
 static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
 				      volatile void *address)
@@ -188,8 +200,7 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
 void  __init
 swiotlb_init(int verbose)
 {
-	/* default to 64MB */
-	size_t default_size = 64UL<<20;
+	size_t default_size = IO_TLB_DEFAULT_SIZE;
 	unsigned char *vstart;
 	unsigned long bytes;
 
-- 
cgit v1.2.3


From 55a20ee7804ab64ac90bcdd4e2868a42829e2784 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Mon, 15 Apr 2013 22:23:47 -0700
Subject: x86, kdump: Retore crashkernel= to allocate under 896M

Vivek found old kexec-tools does not work new kernel anymore.

So change back crashkernel= back to old behavoir, and add crashkernel_high=
to let user decide if buffer could be above 4G, and also new kexec-tools will
be needed.

-v2: let crashkernel=X override crashkernel_high=
    update description about _high will be ignored by crashkernel=X
-v3: update description about kernel-parameters.txt according to Vivek.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/1366089828-19692-4-git-send-email-yinghai@kernel.org
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
---
 Documentation/kernel-parameters.txt | 13 +++++++++++--
 arch/x86/kernel/setup.c             | 24 +++++++++++++++++++-----
 include/linux/kexec.h               |  2 ++
 kernel/kexec.c                      |  9 +++++++++
 4 files changed, 41 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index cff672da2486..709eb3edc6b2 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -603,9 +603,16 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			a memory unit (amount[KMG]). See also
 			Documentation/kdump/kdump.txt for an example.
 
+	crashkernel_high=size[KMG]
+			[KNL, x86_64] range could be above 4G. Allow kernel
+			to allocate physical memory region from top, so could
+			be above 4G if system have more than 4G ram installed.
+			Otherwise memory region will be allocated below 4G, if
+			available.
+			It will be ignored if crashkernel=X is specified.
 	crashkernel_low=size[KMG]
-			[KNL, x86_64] range under 4G. When crashkernel= is
-			passed, kernel allocate physical memory region
+			[KNL, x86_64] range under 4G. When crashkernel_high= is
+			passed, kernel could allocate physical memory region
 			above 4G, that cause second kernel crash on system
 			that require some amount of low memory, e.g. swiotlb
 			requires at least 64M+32K low memory.  Kernel would
@@ -613,6 +620,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			This one let user to specify own low range under 4G
 			for second kernel instead.
 			0: to disable low allocation.
+			It will be ignored when crashkernel_high=X is not used
+			or memory reserved is below 4G.
 
 	cs89x0_dma=	[HW,NET]
 			Format: <dma>
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 12349202cae7..a85a144f2052 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -507,11 +507,14 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 /*
  * Keep the crash kernel below this limit.  On 32 bits earlier kernels
  * would limit the kernel to the low 512 MiB due to mapping restrictions.
+ * On 64bit, old kexec-tools need to under 896MiB.
  */
 #ifdef CONFIG_X86_32
-# define CRASH_KERNEL_ADDR_MAX	(512 << 20)
+# define CRASH_KERNEL_ADDR_LOW_MAX	(512 << 20)
+# define CRASH_KERNEL_ADDR_HIGH_MAX	(512 << 20)
 #else
-# define CRASH_KERNEL_ADDR_MAX	MAXMEM
+# define CRASH_KERNEL_ADDR_LOW_MAX	(896UL<<20)
+# define CRASH_KERNEL_ADDR_HIGH_MAX	MAXMEM
 #endif
 
 static void __init reserve_crashkernel_low(void)
@@ -525,6 +528,7 @@ static void __init reserve_crashkernel_low(void)
 	int ret;
 
 	total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT));
+	/* crashkernel_low=YM */
 	ret = parse_crashkernel_low(boot_command_line, total_low_mem,
 						&low_size, &base);
 	if (ret != 0) {
@@ -569,14 +573,22 @@ static void __init reserve_crashkernel(void)
 	const unsigned long long alignment = 16<<20;	/* 16M */
 	unsigned long long total_mem;
 	unsigned long long crash_size, crash_base;
+	bool high = false;
 	int ret;
 
 	total_mem = memblock_phys_mem_size();
 
+	/* crashkernel=XM */
 	ret = parse_crashkernel(boot_command_line, total_mem,
 			&crash_size, &crash_base);
-	if (ret != 0 || crash_size <= 0)
-		return;
+	if (ret != 0 || crash_size <= 0) {
+		/* crashkernel_high=XM */
+		ret = parse_crashkernel_high(boot_command_line, total_mem,
+				&crash_size, &crash_base);
+		if (ret != 0 || crash_size <= 0)
+			return;
+		high = true;
+	}
 
 	/* 0 means: find the address automatically */
 	if (crash_base <= 0) {
@@ -584,7 +596,9 @@ static void __init reserve_crashkernel(void)
 		 *  kexec want bzImage is below CRASH_KERNEL_ADDR_MAX
 		 */
 		crash_base = memblock_find_in_range(alignment,
-			       CRASH_KERNEL_ADDR_MAX, crash_size, alignment);
+					high ? CRASH_KERNEL_ADDR_HIGH_MAX :
+					       CRASH_KERNEL_ADDR_LOW_MAX,
+					crash_size, alignment);
 
 		if (!crash_base) {
 			pr_info("crashkernel reservation failed - No suitable area found.\n");
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index d2e6927bbaae..d78d28a733b1 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -200,6 +200,8 @@ extern size_t vmcoreinfo_max_size;
 
 int __init parse_crashkernel(char *cmdline, unsigned long long system_ram,
 		unsigned long long *crash_size, unsigned long long *crash_base);
+int parse_crashkernel_high(char *cmdline, unsigned long long system_ram,
+		unsigned long long *crash_size, unsigned long long *crash_base);
 int parse_crashkernel_low(char *cmdline, unsigned long long system_ram,
 		unsigned long long *crash_size, unsigned long long *crash_base);
 int crash_shrink_memory(unsigned long new_size);
diff --git a/kernel/kexec.c b/kernel/kexec.c
index bddd3d7a74b6..1b2f73f5f9b9 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1422,6 +1422,15 @@ int __init parse_crashkernel(char *cmdline,
 					"crashkernel=");
 }
 
+int __init parse_crashkernel_high(char *cmdline,
+			     unsigned long long system_ram,
+			     unsigned long long *crash_size,
+			     unsigned long long *crash_base)
+{
+	return __parse_crashkernel(cmdline, system_ram, crash_size, crash_base,
+					"crashkernel_high=");
+}
+
 int __init parse_crashkernel_low(char *cmdline,
 			     unsigned long long system_ram,
 			     unsigned long long *crash_size,
-- 
cgit v1.2.3


From 0a82a8d132b26d438eb90b3ab35a7016e7227a1d Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 18 Apr 2013 09:00:26 -0700
Subject: Revert "block: add missing block_bio_complete() tracepoint"

This reverts commit 3a366e614d0837d9fc23f78cdb1a1186ebc3387f.

Wanlong Gao reports that it causes a kernel panic on his machine several
minutes after boot. Reverting it removes the panic.

Jens says:
 "It's not quite clear why that is yet, so I think we should just revert
  the commit for 3.9 final (which I'm assuming is pretty close).

  The wifi is crap at the LSF hotel, so sending this email instead of
  queueing up a revert and pull request."

Reported-by: Wanlong Gao <gaowanlong@cn.fujitsu.com>
Requested-by: Jens Axboe <axboe@kernel.dk>
Cc: Tejun Heo <tj@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 block/blk-core.c             |  1 +
 drivers/md/dm.c              |  1 +
 drivers/md/raid5.c           | 11 ++++++++++-
 fs/bio.c                     |  2 --
 include/linux/blktrace_api.h |  1 -
 include/trace/events/block.h |  8 ++++----
 kernel/trace/blktrace.c      | 26 +++-----------------------
 7 files changed, 19 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index 074b758efc42..7c288358a745 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -39,6 +39,7 @@
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
+EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug);
 
 DEFINE_IDA(blk_queue_ida);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 7e469260fe5e..9a0bdad9ad8f 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -611,6 +611,7 @@ static void dec_pending(struct dm_io *io, int error)
 			queue_io(md, bio);
 		} else {
 			/* done with normal IO or empty flush */
+			trace_block_bio_complete(md->queue, bio, io_error);
 			bio_endio(bio, io_error);
 		}
 	}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 24909eb13fec..f4e87bfc7567 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -184,6 +184,8 @@ static void return_io(struct bio *return_bi)
 		return_bi = bi->bi_next;
 		bi->bi_next = NULL;
 		bi->bi_size = 0;
+		trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
+					 bi, 0);
 		bio_endio(bi, 0);
 		bi = return_bi;
 	}
@@ -3914,6 +3916,8 @@ static void raid5_align_endio(struct bio *bi, int error)
 	rdev_dec_pending(rdev, conf->mddev);
 
 	if (!error && uptodate) {
+		trace_block_bio_complete(bdev_get_queue(raid_bi->bi_bdev),
+					 raid_bi, 0);
 		bio_endio(raid_bi, 0);
 		if (atomic_dec_and_test(&conf->active_aligned_reads))
 			wake_up(&conf->wait_for_stripe);
@@ -4382,6 +4386,8 @@ static void make_request(struct mddev *mddev, struct bio * bi)
 		if ( rw == WRITE )
 			md_write_end(mddev);
 
+		trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
+					 bi, 0);
 		bio_endio(bi, 0);
 	}
 }
@@ -4758,8 +4764,11 @@ static int  retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
 		handled++;
 	}
 	remaining = raid5_dec_bi_active_stripes(raid_bio);
-	if (remaining == 0)
+	if (remaining == 0) {
+		trace_block_bio_complete(bdev_get_queue(raid_bio->bi_bdev),
+					 raid_bio, 0);
 		bio_endio(raid_bio, 0);
+	}
 	if (atomic_dec_and_test(&conf->active_aligned_reads))
 		wake_up(&conf->wait_for_stripe);
 	return handled;
diff --git a/fs/bio.c b/fs/bio.c
index bb5768f59b32..b96fc6ce4855 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -1428,8 +1428,6 @@ void bio_endio(struct bio *bio, int error)
 	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
 		error = -EIO;
 
-	trace_block_bio_complete(bio, error);
-
 	if (bio->bi_end_io)
 		bio->bi_end_io(bio, error);
 }
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index 0ea61e07a91c..7c2e030e72f1 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -12,7 +12,6 @@
 
 struct blk_trace {
 	int trace_state;
-	bool rq_based;
 	struct rchan *rchan;
 	unsigned long __percpu *sequence;
 	unsigned char __percpu *msg_data;
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index 9961726523d0..9c1467357b03 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -257,6 +257,7 @@ TRACE_EVENT(block_bio_bounce,
 
 /**
  * block_bio_complete - completed all work on the block operation
+ * @q: queue holding the block operation
  * @bio: block operation completed
  * @error: io error value
  *
@@ -265,9 +266,9 @@ TRACE_EVENT(block_bio_bounce,
  */
 TRACE_EVENT(block_bio_complete,
 
-	TP_PROTO(struct bio *bio, int error),
+	TP_PROTO(struct request_queue *q, struct bio *bio, int error),
 
-	TP_ARGS(bio, error),
+	TP_ARGS(q, bio, error),
 
 	TP_STRUCT__entry(
 		__field( dev_t,		dev		)
@@ -278,8 +279,7 @@ TRACE_EVENT(block_bio_complete,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= bio->bi_bdev ?
-					  bio->bi_bdev->bd_dev : 0;
+		__entry->dev		= bio->bi_bdev->bd_dev;
 		__entry->sector		= bio->bi_sector;
 		__entry->nr_sector	= bio->bi_size >> 9;
 		__entry->error		= error;
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 9e5b8c272eec..5a0f781cd729 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -739,12 +739,6 @@ static void blk_add_trace_rq_complete(void *ignore,
 				      struct request_queue *q,
 				      struct request *rq)
 {
-	struct blk_trace *bt = q->blk_trace;
-
-	/* if control ever passes through here, it's a request based driver */
-	if (unlikely(bt && !bt->rq_based))
-		bt->rq_based = true;
-
 	blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
 }
 
@@ -780,24 +774,10 @@ static void blk_add_trace_bio_bounce(void *ignore,
 	blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0);
 }
 
-static void blk_add_trace_bio_complete(void *ignore, struct bio *bio, int error)
+static void blk_add_trace_bio_complete(void *ignore,
+				       struct request_queue *q, struct bio *bio,
+				       int error)
 {
-	struct request_queue *q;
-	struct blk_trace *bt;
-
-	if (!bio->bi_bdev)
-		return;
-
-	q = bdev_get_queue(bio->bi_bdev);
-	bt = q->blk_trace;
-
-	/*
-	 * Request based drivers will generate both rq and bio completions.
-	 * Ignore bio ones.
-	 */
-	if (likely(!bt) || bt->rq_based)
-		return;
-
 	blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error);
 }
 
-- 
cgit v1.2.3


From e15465e1808542743627f13d1c0cbb7eacc82b83 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 16 Apr 2013 21:10:38 +0000
Subject: irda: small read past the end of array in debug code

The "reason" can come from skb->data[] and it hasn't been capped so it
can be from 0-255 instead of just 0-6.  For example in irlmp_state_dtr()
the code does:

	reason = skb->data[3];
	...
	irlmp_disconnect_indication(self, reason, skb);

Also LMREASON has a couple other values which don't have entries in the
irlmp_reasons[] array.  And 0xff is a valid reason as well which means
"unknown".

So far as I can see we don't actually care about "reason" except for in
the debug code.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/irda/irlmp.h |  3 ++-
 net/irda/iriap.c         |  3 ++-
 net/irda/irlmp.c         | 10 +++++++++-
 3 files changed, 13 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/irda/irlmp.h b/include/net/irda/irlmp.h
index f74109144d3f..f132924cc9da 100644
--- a/include/net/irda/irlmp.h
+++ b/include/net/irda/irlmp.h
@@ -256,7 +256,8 @@ static inline __u32 irlmp_get_daddr(const struct lsap_cb *self)
 	return (self && self->lap) ? self->lap->daddr : 0;
 }
 
-extern const char *irlmp_reasons[];
+const char *irlmp_reason_str(LM_REASON reason);
+
 extern int sysctl_discovery_timeout;
 extern int sysctl_discovery_slots;
 extern int sysctl_discovery;
diff --git a/net/irda/iriap.c b/net/irda/iriap.c
index 29340a9a6fb9..e1b37f5a2691 100644
--- a/net/irda/iriap.c
+++ b/net/irda/iriap.c
@@ -303,7 +303,8 @@ static void iriap_disconnect_indication(void *instance, void *sap,
 {
 	struct iriap_cb *self;
 
-	IRDA_DEBUG(4, "%s(), reason=%s\n", __func__, irlmp_reasons[reason]);
+	IRDA_DEBUG(4, "%s(), reason=%s [%d]\n", __func__,
+		   irlmp_reason_str(reason), reason);
 
 	self = instance;
 
diff --git a/net/irda/irlmp.c b/net/irda/irlmp.c
index 6115a44c0a24..1064621da6f6 100644
--- a/net/irda/irlmp.c
+++ b/net/irda/irlmp.c
@@ -66,8 +66,15 @@ const char *irlmp_reasons[] = {
 	"LM_LAP_RESET",
 	"LM_INIT_DISCONNECT",
 	"ERROR, NOT USED",
+	"UNKNOWN",
 };
 
+const char *irlmp_reason_str(LM_REASON reason)
+{
+	reason = min_t(size_t, reason, ARRAY_SIZE(irlmp_reasons) - 1);
+	return irlmp_reasons[reason];
+}
+
 /*
  * Function irlmp_init (void)
  *
@@ -747,7 +754,8 @@ void irlmp_disconnect_indication(struct lsap_cb *self, LM_REASON reason,
 {
 	struct lsap_cb *lsap;
 
-	IRDA_DEBUG(1, "%s(), reason=%s\n", __func__, irlmp_reasons[reason]);
+	IRDA_DEBUG(1, "%s(), reason=%s [%d]\n", __func__,
+		   irlmp_reason_str(reason), reason);
 	IRDA_ASSERT(self != NULL, return;);
 	IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return;);
 
-- 
cgit v1.2.3


From 83f1b4ba917db5dc5a061a44b3403ddb6e783494 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri, 19 Apr 2013 15:32:32 +0000
Subject: net: fix incorrect credentials passing

Commit 257b5358b32f ("scm: Capture the full credentials of the scm
sender") changed the credentials passing code to pass in the effective
uid/gid instead of the real uid/gid.

Obviously this doesn't matter most of the time (since normally they are
the same), but it results in differences for suid binaries when the wrong
uid/gid ends up being used.

This just undoes that (presumably unintentional) part of the commit.

Reported-by: Andy Lutomirski <luto@amacapital.net>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Serge E. Hallyn <serge@hallyn.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/scm.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/scm.h b/include/net/scm.h
index 975cca01048b..b11708105681 100644
--- a/include/net/scm.h
+++ b/include/net/scm.h
@@ -56,8 +56,8 @@ static __inline__ void scm_set_cred(struct scm_cookie *scm,
 	scm->pid  = get_pid(pid);
 	scm->cred = cred ? get_cred(cred) : NULL;
 	scm->creds.pid = pid_vnr(pid);
-	scm->creds.uid = cred ? cred->euid : INVALID_UID;
-	scm->creds.gid = cred ? cred->egid : INVALID_GID;
+	scm->creds.uid = cred ? cred->uid : INVALID_UID;
+	scm->creds.gid = cred ? cred->gid : INVALID_GID;
 }
 
 static __inline__ void scm_destroy_cred(struct scm_cookie *scm)
-- 
cgit v1.2.3