summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/asm-generic/preempt.h4
-rw-r--r--include/drm/drm_dp_dual_mode_helper.h92
-rw-r--r--include/dt-bindings/thermal/tegra124-soctherm.h1
-rw-r--r--include/kvm/arm_arch_timer.h11
-rw-r--r--include/kvm/arm_vgic.h20
-rw-r--r--include/kvm/vgic/vgic.h246
-rw-r--r--include/linux/blkdev.h15
-rw-r--r--include/linux/ceph/ceph_frag.h4
-rw-r--r--include/linux/ceph/ceph_fs.h20
-rw-r--r--include/linux/ceph/decode.h2
-rw-r--r--include/linux/ceph/libceph.h57
-rw-r--r--include/linux/ceph/mon_client.h23
-rw-r--r--include/linux/ceph/osd_client.h231
-rw-r--r--include/linux/ceph/osdmap.h158
-rw-r--r--include/linux/ceph/rados.h34
-rw-r--r--include/linux/dax.h41
-rw-r--r--include/linux/err.h2
-rw-r--r--include/linux/errno.h1
-rw-r--r--include/linux/export.h33
-rw-r--r--include/linux/fs.h1
-rw-r--r--include/linux/iova.h23
-rw-r--r--include/linux/irqchip/arm-gic-v3.h6
-rw-r--r--include/linux/irqchip/arm-gic.h2
-rw-r--r--include/linux/kvm_host.h7
-rw-r--r--include/linux/memory_hotplug.h2
-rw-r--r--include/linux/mm.h9
-rw-r--r--include/linux/mm_types.h2
-rw-r--r--include/linux/mmc/host.h4
-rw-r--r--include/linux/nfs4.h28
-rw-r--r--include/linux/nfs_fs_sb.h1
-rw-r--r--include/linux/nfs_xdr.h30
-rw-r--r--include/linux/perf_event.h34
-rw-r--r--include/linux/sched.h5
-rw-r--r--include/linux/seqlock.h4
-rw-r--r--include/linux/slub_def.h16
-rw-r--r--include/linux/sunrpc/auth.h26
-rw-r--r--include/linux/sunrpc/clnt.h1
-rw-r--r--include/linux/sunrpc/msg_prot.h4
-rw-r--r--include/linux/sunrpc/xprt.h1
-rw-r--r--include/linux/sunrpc/xprtrdma.h4
-rw-r--r--include/linux/thermal.h1
-rw-r--r--include/trace/events/kvm.h6
-rw-r--r--include/uapi/linux/nvme_ioctl.h1
-rw-r--r--include/uapi/linux/perf_event.h1
-rw-r--r--include/video/imx-ipu-v3.h2
45 files changed, 986 insertions, 230 deletions
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index 5d8ffa3e6f8c..c1cde3577551 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -7,10 +7,10 @@
static __always_inline int preempt_count(void)
{
- return current_thread_info()->preempt_count;
+ return READ_ONCE(current_thread_info()->preempt_count);
}
-static __always_inline int *preempt_count_ptr(void)
+static __always_inline volatile int *preempt_count_ptr(void)
{
return &current_thread_info()->preempt_count;
}
diff --git a/include/drm/drm_dp_dual_mode_helper.h b/include/drm/drm_dp_dual_mode_helper.h
new file mode 100644
index 000000000000..e8a9dfd0e055
--- /dev/null
+++ b/include/drm/drm_dp_dual_mode_helper.h
@@ -0,0 +1,92 @@
+/*
+ * Copyright © 2016 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef DRM_DP_DUAL_MODE_HELPER_H
+#define DRM_DP_DUAL_MODE_HELPER_H
+
+#include <linux/types.h>
+
+/*
+ * Optional for type 1 DVI adaptors
+ * Mandatory for type 1 HDMI and type 2 adaptors
+ */
+#define DP_DUAL_MODE_HDMI_ID 0x00 /* 00-0f */
+#define DP_DUAL_MODE_HDMI_ID_LEN 16
+/*
+ * Optional for type 1 adaptors
+ * Mandatory for type 2 adaptors
+ */
+#define DP_DUAL_MODE_ADAPTOR_ID 0x10
+#define DP_DUAL_MODE_REV_MASK 0x07
+#define DP_DUAL_MODE_REV_TYPE2 0x00
+#define DP_DUAL_MODE_TYPE_MASK 0xf0
+#define DP_DUAL_MODE_TYPE_TYPE2 0xa0
+#define DP_DUAL_MODE_IEEE_OUI 0x11 /* 11-13*/
+#define DP_DUAL_IEEE_OUI_LEN 3
+#define DP_DUAL_DEVICE_ID 0x14 /* 14-19 */
+#define DP_DUAL_DEVICE_ID_LEN 6
+#define DP_DUAL_MODE_HARDWARE_REV 0x1a
+#define DP_DUAL_MODE_FIRMWARE_MAJOR_REV 0x1b
+#define DP_DUAL_MODE_FIRMWARE_MINOR_REV 0x1c
+#define DP_DUAL_MODE_MAX_TMDS_CLOCK 0x1d
+#define DP_DUAL_MODE_I2C_SPEED_CAP 0x1e
+#define DP_DUAL_MODE_TMDS_OEN 0x20
+#define DP_DUAL_MODE_TMDS_DISABLE 0x01
+#define DP_DUAL_MODE_HDMI_PIN_CTRL 0x21
+#define DP_DUAL_MODE_CEC_ENABLE 0x01
+#define DP_DUAL_MODE_I2C_SPEED_CTRL 0x22
+
+struct i2c_adapter;
+
+ssize_t drm_dp_dual_mode_read(struct i2c_adapter *adapter,
+ u8 offset, void *buffer, size_t size);
+ssize_t drm_dp_dual_mode_write(struct i2c_adapter *adapter,
+ u8 offset, const void *buffer, size_t size);
+
+/**
+ * enum drm_dp_dual_mode_type - Type of the DP dual mode adaptor
+ * @DRM_DP_DUAL_MODE_NONE: No DP dual mode adaptor
+ * @DRM_DP_DUAL_MODE_UNKNOWN: Could be either none or type 1 DVI adaptor
+ * @DRM_DP_DUAL_MODE_TYPE1_DVI: Type 1 DVI adaptor
+ * @DRM_DP_DUAL_MODE_TYPE1_HDMI: Type 1 HDMI adaptor
+ * @DRM_DP_DUAL_MODE_TYPE2_DVI: Type 2 DVI adaptor
+ * @DRM_DP_DUAL_MODE_TYPE2_HDMI: Type 2 HDMI adaptor
+ */
+enum drm_dp_dual_mode_type {
+ DRM_DP_DUAL_MODE_NONE,
+ DRM_DP_DUAL_MODE_UNKNOWN,
+ DRM_DP_DUAL_MODE_TYPE1_DVI,
+ DRM_DP_DUAL_MODE_TYPE1_HDMI,
+ DRM_DP_DUAL_MODE_TYPE2_DVI,
+ DRM_DP_DUAL_MODE_TYPE2_HDMI,
+};
+
+enum drm_dp_dual_mode_type drm_dp_dual_mode_detect(struct i2c_adapter *adapter);
+int drm_dp_dual_mode_max_tmds_clock(enum drm_dp_dual_mode_type type,
+ struct i2c_adapter *adapter);
+int drm_dp_dual_mode_get_tmds_output(enum drm_dp_dual_mode_type type,
+ struct i2c_adapter *adapter, bool *enabled);
+int drm_dp_dual_mode_set_tmds_output(enum drm_dp_dual_mode_type type,
+ struct i2c_adapter *adapter, bool enable);
+const char *drm_dp_get_dual_mode_type_name(enum drm_dp_dual_mode_type type);
+
+#endif
diff --git a/include/dt-bindings/thermal/tegra124-soctherm.h b/include/dt-bindings/thermal/tegra124-soctherm.h
index 85aaf66690f9..729ab9fc325e 100644
--- a/include/dt-bindings/thermal/tegra124-soctherm.h
+++ b/include/dt-bindings/thermal/tegra124-soctherm.h
@@ -9,5 +9,6 @@
#define TEGRA124_SOCTHERM_SENSOR_MEM 1
#define TEGRA124_SOCTHERM_SENSOR_GPU 2
#define TEGRA124_SOCTHERM_SENSOR_PLLX 3
+#define TEGRA124_SOCTHERM_SENSOR_NUM 4
#endif
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index b651aed9dc6b..dda39d8fa189 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -24,9 +24,6 @@
#include <linux/workqueue.h>
struct arch_timer_kvm {
- /* Is the timer enabled */
- bool enabled;
-
/* Virtual offset */
cycle_t cntvoff;
};
@@ -53,15 +50,15 @@ struct arch_timer_cpu {
/* Timer IRQ */
struct kvm_irq_level irq;
- /* VGIC mapping */
- struct irq_phys_map *map;
-
/* Active IRQ state caching */
bool active_cleared_last;
+
+ /* Is the timer enabled */
+ bool enabled;
};
int kvm_timer_hyp_init(void);
-void kvm_timer_enable(struct kvm *kvm);
+int kvm_timer_enable(struct kvm_vcpu *vcpu);
void kvm_timer_init(struct kvm *kvm);
int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
const struct kvm_irq_level *irq);
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index be6037aa703d..da0a524802cb 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -19,6 +19,10 @@
#ifndef __ASM_ARM_KVM_VGIC_H
#define __ASM_ARM_KVM_VGIC_H
+#ifdef CONFIG_KVM_NEW_VGIC
+#include <kvm/vgic/vgic.h>
+#else
+
#include <linux/kernel.h>
#include <linux/kvm.h>
#include <linux/irqreturn.h>
@@ -158,7 +162,6 @@ struct vgic_io_device {
struct irq_phys_map {
u32 virt_irq;
u32 phys_irq;
- u32 irq;
};
struct irq_phys_map_entry {
@@ -305,9 +308,6 @@ struct vgic_cpu {
unsigned long *active_shared;
unsigned long *pend_act_shared;
- /* Number of list registers on this CPU */
- int nr_lr;
-
/* CPU vif control registers for world switch */
union {
struct vgic_v2_cpu_if vgic_v2;
@@ -342,17 +342,18 @@ void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
bool level);
int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid,
- struct irq_phys_map *map, bool level);
+ unsigned int virt_irq, bool level);
void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg);
int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
-struct irq_phys_map *kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu,
- int virt_irq, int irq);
-int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map);
-bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, struct irq_phys_map *map);
+int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, int virt_irq, int phys_irq);
+int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int virt_irq);
+bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int virt_irq);
#define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel))
#define vgic_initialized(k) (!!((k)->arch.vgic.nr_cpus))
#define vgic_ready(k) ((k)->arch.vgic.ready)
+#define vgic_valid_spi(k, i) (((i) >= VGIC_NR_PRIVATE_IRQS) && \
+ ((i) < (k)->arch.vgic.nr_irqs))
int vgic_v2_probe(const struct gic_kvm_info *gic_kvm_info,
const struct vgic_ops **ops,
@@ -370,4 +371,5 @@ static inline int vgic_v3_probe(const struct gic_kvm_info *gic_kvm_info,
}
#endif
+#endif /* old VGIC include */
#endif
diff --git a/include/kvm/vgic/vgic.h b/include/kvm/vgic/vgic.h
new file mode 100644
index 000000000000..3fbd175265ae
--- /dev/null
+++ b/include/kvm/vgic/vgic.h
@@ -0,0 +1,246 @@
+/*
+ * Copyright (C) 2015, 2016 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_ARM_KVM_VGIC_VGIC_H
+#define __ASM_ARM_KVM_VGIC_VGIC_H
+
+#include <linux/kernel.h>
+#include <linux/kvm.h>
+#include <linux/irqreturn.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <kvm/iodev.h>
+
+#define VGIC_V3_MAX_CPUS 255
+#define VGIC_V2_MAX_CPUS 8
+#define VGIC_NR_IRQS_LEGACY 256
+#define VGIC_NR_SGIS 16
+#define VGIC_NR_PPIS 16
+#define VGIC_NR_PRIVATE_IRQS (VGIC_NR_SGIS + VGIC_NR_PPIS)
+#define VGIC_MAX_PRIVATE (VGIC_NR_PRIVATE_IRQS - 1)
+#define VGIC_MAX_SPI 1019
+#define VGIC_MAX_RESERVED 1023
+#define VGIC_MIN_LPI 8192
+
+enum vgic_type {
+ VGIC_V2, /* Good ol' GICv2 */
+ VGIC_V3, /* New fancy GICv3 */
+};
+
+/* same for all guests, as depending only on the _host's_ GIC model */
+struct vgic_global {
+ /* type of the host GIC */
+ enum vgic_type type;
+
+ /* Physical address of vgic virtual cpu interface */
+ phys_addr_t vcpu_base;
+
+ /* virtual control interface mapping */
+ void __iomem *vctrl_base;
+
+ /* Number of implemented list registers */
+ int nr_lr;
+
+ /* Maintenance IRQ number */
+ unsigned int maint_irq;
+
+ /* maximum number of VCPUs allowed (GICv2 limits us to 8) */
+ int max_gic_vcpus;
+
+ /* Only needed for the legacy KVM_CREATE_IRQCHIP */
+ bool can_emulate_gicv2;
+};
+
+extern struct vgic_global kvm_vgic_global_state;
+
+#define VGIC_V2_MAX_LRS (1 << 6)
+#define VGIC_V3_MAX_LRS 16
+#define VGIC_V3_LR_INDEX(lr) (VGIC_V3_MAX_LRS - 1 - lr)
+
+enum vgic_irq_config {
+ VGIC_CONFIG_EDGE = 0,
+ VGIC_CONFIG_LEVEL
+};
+
+struct vgic_irq {
+ spinlock_t irq_lock; /* Protects the content of the struct */
+ struct list_head ap_list;
+
+ struct kvm_vcpu *vcpu; /* SGIs and PPIs: The VCPU
+ * SPIs and LPIs: The VCPU whose ap_list
+ * this is queued on.
+ */
+
+ struct kvm_vcpu *target_vcpu; /* The VCPU that this interrupt should
+ * be sent to, as a result of the
+ * targets reg (v2) or the
+ * affinity reg (v3).
+ */
+
+ u32 intid; /* Guest visible INTID */
+ bool pending;
+ bool line_level; /* Level only */
+ bool soft_pending; /* Level only */
+ bool active; /* not used for LPIs */
+ bool enabled;
+ bool hw; /* Tied to HW IRQ */
+ u32 hwintid; /* HW INTID number */
+ union {
+ u8 targets; /* GICv2 target VCPUs mask */
+ u32 mpidr; /* GICv3 target VCPU */
+ };
+ u8 source; /* GICv2 SGIs only */
+ u8 priority;
+ enum vgic_irq_config config; /* Level or edge */
+};
+
+struct vgic_register_region;
+
+struct vgic_io_device {
+ gpa_t base_addr;
+ struct kvm_vcpu *redist_vcpu;
+ const struct vgic_register_region *regions;
+ int nr_regions;
+ struct kvm_io_device dev;
+};
+
+struct vgic_dist {
+ bool in_kernel;
+ bool ready;
+ bool initialized;
+
+ /* vGIC model the kernel emulates for the guest (GICv2 or GICv3) */
+ u32 vgic_model;
+
+ int nr_spis;
+
+ /* TODO: Consider moving to global state */
+ /* Virtual control interface mapping */
+ void __iomem *vctrl_base;
+
+ /* base addresses in guest physical address space: */
+ gpa_t vgic_dist_base; /* distributor */
+ union {
+ /* either a GICv2 CPU interface */
+ gpa_t vgic_cpu_base;
+ /* or a number of GICv3 redistributor regions */
+ gpa_t vgic_redist_base;
+ };
+
+ /* distributor enabled */
+ bool enabled;
+
+ struct vgic_irq *spis;
+
+ struct vgic_io_device dist_iodev;
+ struct vgic_io_device *redist_iodevs;
+};
+
+struct vgic_v2_cpu_if {
+ u32 vgic_hcr;
+ u32 vgic_vmcr;
+ u32 vgic_misr; /* Saved only */
+ u64 vgic_eisr; /* Saved only */
+ u64 vgic_elrsr; /* Saved only */
+ u32 vgic_apr;
+ u32 vgic_lr[VGIC_V2_MAX_LRS];
+};
+
+struct vgic_v3_cpu_if {
+#ifdef CONFIG_KVM_ARM_VGIC_V3
+ u32 vgic_hcr;
+ u32 vgic_vmcr;
+ u32 vgic_sre; /* Restored only, change ignored */
+ u32 vgic_misr; /* Saved only */
+ u32 vgic_eisr; /* Saved only */
+ u32 vgic_elrsr; /* Saved only */
+ u32 vgic_ap0r[4];
+ u32 vgic_ap1r[4];
+ u64 vgic_lr[VGIC_V3_MAX_LRS];
+#endif
+};
+
+struct vgic_cpu {
+ /* CPU vif control registers for world switch */
+ union {
+ struct vgic_v2_cpu_if vgic_v2;
+ struct vgic_v3_cpu_if vgic_v3;
+ };
+
+ unsigned int used_lrs;
+ struct vgic_irq private_irqs[VGIC_NR_PRIVATE_IRQS];
+
+ spinlock_t ap_list_lock; /* Protects the ap_list */
+
+ /*
+ * List of IRQs that this VCPU should consider because they are either
+ * Active or Pending (hence the name; AP list), or because they recently
+ * were one of the two and need to be migrated off this list to another
+ * VCPU.
+ */
+ struct list_head ap_list_head;
+
+ u64 live_lrs;
+};
+
+int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
+void kvm_vgic_early_init(struct kvm *kvm);
+int kvm_vgic_create(struct kvm *kvm, u32 type);
+void kvm_vgic_destroy(struct kvm *kvm);
+void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu);
+void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
+int kvm_vgic_map_resources(struct kvm *kvm);
+int kvm_vgic_hyp_init(void);
+
+int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
+ bool level);
+int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid, unsigned int intid,
+ bool level);
+int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, u32 virt_irq, u32 phys_irq);
+int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int virt_irq);
+bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int virt_irq);
+
+int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
+
+#define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel))
+#define vgic_initialized(k) ((k)->arch.vgic.initialized)
+#define vgic_ready(k) ((k)->arch.vgic.ready)
+#define vgic_valid_spi(k, i) (((i) >= VGIC_NR_PRIVATE_IRQS) && \
+ ((i) < (k)->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS))
+
+bool kvm_vcpu_has_pending_irqs(struct kvm_vcpu *vcpu);
+void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
+void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
+
+#ifdef CONFIG_KVM_ARM_VGIC_V3
+void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg);
+#else
+static inline void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg)
+{
+}
+#endif
+
+/**
+ * kvm_vgic_get_max_vcpus - Get the maximum number of VCPUs allowed by HW
+ *
+ * The host's GIC naturally limits the maximum amount of VCPUs a guest
+ * can use.
+ */
+static inline int kvm_vgic_get_max_vcpus(void)
+{
+ return kvm_vgic_global_state.max_gic_vcpus;
+}
+
+#endif /* __ASM_ARM_KVM_VGIC_VGIC_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1fd8fdff2f81..3d9cf326574f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -768,6 +768,17 @@ static inline void rq_flush_dcache_pages(struct request *rq)
}
#endif
+#ifdef CONFIG_PRINTK
+#define vfs_msg(sb, level, fmt, ...) \
+ __vfs_msg(sb, level, fmt, ##__VA_ARGS__)
+#else
+#define vfs_msg(sb, level, fmt, ...) \
+do { \
+ no_printk(fmt, ##__VA_ARGS__); \
+ __vfs_msg(sb, "", " "); \
+} while (0)
+#endif
+
extern int blk_register_queue(struct gendisk *disk);
extern void blk_unregister_queue(struct gendisk *disk);
extern blk_qc_t generic_make_request(struct bio *bio);
@@ -1660,7 +1671,7 @@ struct block_device_operations {
int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
long (*direct_access)(struct block_device *, sector_t, void __pmem **,
- pfn_t *);
+ pfn_t *, long);
unsigned int (*check_events) (struct gendisk *disk,
unsigned int clearing);
/* ->media_changed() is DEPRECATED, use ->check_events() instead */
@@ -1680,6 +1691,8 @@ extern int bdev_read_page(struct block_device *, sector_t, struct page *);
extern int bdev_write_page(struct block_device *, sector_t, struct page *,
struct writeback_control *);
extern long bdev_direct_access(struct block_device *, struct blk_dax_ctl *);
+extern int bdev_dax_supported(struct super_block *, int);
+extern bool bdev_dax_capable(struct block_device *);
#else /* CONFIG_BLOCK */
struct block_device;
diff --git a/include/linux/ceph/ceph_frag.h b/include/linux/ceph/ceph_frag.h
index b827e066e55a..146507df8650 100644
--- a/include/linux/ceph/ceph_frag.h
+++ b/include/linux/ceph/ceph_frag.h
@@ -51,11 +51,11 @@ static inline __u32 ceph_frag_make_child(__u32 f, int by, int i)
return ceph_frag_make(newbits,
ceph_frag_value(f) | (i << (24 - newbits)));
}
-static inline int ceph_frag_is_leftmost(__u32 f)
+static inline bool ceph_frag_is_leftmost(__u32 f)
{
return ceph_frag_value(f) == 0;
}
-static inline int ceph_frag_is_rightmost(__u32 f)
+static inline bool ceph_frag_is_rightmost(__u32 f)
{
return ceph_frag_value(f) == ceph_frag_mask(f);
}
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 37f28bf55ce4..dfce616002ad 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -153,8 +153,9 @@ struct ceph_dir_layout {
/* watch-notify operations */
enum {
- WATCH_NOTIFY = 1, /* notifying watcher */
- WATCH_NOTIFY_COMPLETE = 2, /* notifier notified when done */
+ CEPH_WATCH_EVENT_NOTIFY = 1, /* notifying watcher */
+ CEPH_WATCH_EVENT_NOTIFY_COMPLETE = 2, /* notifier notified when done */
+ CEPH_WATCH_EVENT_DISCONNECT = 3, /* we were disconnected */
};
@@ -207,6 +208,8 @@ struct ceph_mon_subscribe_ack {
struct ceph_fsid fsid;
} __attribute__ ((packed));
+#define CEPH_FS_CLUSTER_ID_NONE -1
+
/*
* mdsmap flags
*/
@@ -344,6 +347,18 @@ extern const char *ceph_mds_op_name(int op);
#define CEPH_XATTR_REPLACE (1 << 1)
#define CEPH_XATTR_REMOVE (1 << 31)
+/*
+ * readdir request flags;
+ */
+#define CEPH_READDIR_REPLY_BITFLAGS (1<<0)
+
+/*
+ * readdir reply flags.
+ */
+#define CEPH_READDIR_FRAG_END (1<<0)
+#define CEPH_READDIR_FRAG_COMPLETE (1<<8)
+#define CEPH_READDIR_HASH_ORDER (1<<9)
+
union ceph_mds_request_args {
struct {
__le32 mask; /* CEPH_CAP_* */
@@ -361,6 +376,7 @@ union ceph_mds_request_args {
__le32 frag; /* which dir fragment */
__le32 max_entries; /* how many dentries to grab */
__le32 max_bytes;
+ __le16 flags;
} __attribute__ ((packed)) readdir;
struct {
__le32 mode;
diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h
index a6ef9cc267ec..19e9932f3e77 100644
--- a/include/linux/ceph/decode.h
+++ b/include/linux/ceph/decode.h
@@ -47,7 +47,7 @@ static inline void ceph_decode_copy(void **p, void *pv, size_t n)
/*
* bounds check input.
*/
-static inline int ceph_has_room(void **p, void *end, size_t n)
+static inline bool ceph_has_room(void **p, void *end, size_t n)
{
return end >= *p && n <= end - *p;
}
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index db92a8d4926e..690985daad1c 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -180,6 +180,63 @@ static inline int calc_pages_for(u64 off, u64 len)
(off >> PAGE_SHIFT);
}
+/*
+ * These are not meant to be generic - an integer key is assumed.
+ */
+#define DEFINE_RB_INSDEL_FUNCS(name, type, keyfld, nodefld) \
+static void insert_##name(struct rb_root *root, type *t) \
+{ \
+ struct rb_node **n = &root->rb_node; \
+ struct rb_node *parent = NULL; \
+ \
+ BUG_ON(!RB_EMPTY_NODE(&t->nodefld)); \
+ \
+ while (*n) { \
+ type *cur = rb_entry(*n, type, nodefld); \
+ \
+ parent = *n; \
+ if (t->keyfld < cur->keyfld) \
+ n = &(*n)->rb_left; \
+ else if (t->keyfld > cur->keyfld) \
+ n = &(*n)->rb_right; \
+ else \
+ BUG(); \
+ } \
+ \
+ rb_link_node(&t->nodefld, parent, n); \
+ rb_insert_color(&t->nodefld, root); \
+} \
+static void erase_##name(struct rb_root *root, type *t) \
+{ \
+ BUG_ON(RB_EMPTY_NODE(&t->nodefld)); \
+ rb_erase(&t->nodefld, root); \
+ RB_CLEAR_NODE(&t->nodefld); \
+}
+
+#define DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld) \
+static type *lookup_##name(struct rb_root *root, \
+ typeof(((type *)0)->keyfld) key) \
+{ \
+ struct rb_node *n = root->rb_node; \
+ \
+ while (n) { \
+ type *cur = rb_entry(n, type, nodefld); \
+ \
+ if (key < cur->keyfld) \
+ n = n->rb_left; \
+ else if (key > cur->keyfld) \
+ n = n->rb_right; \
+ else \
+ return cur; \
+ } \
+ \
+ return NULL; \
+}
+
+#define DEFINE_RB_FUNCS(name, type, keyfld, nodefld) \
+DEFINE_RB_INSDEL_FUNCS(name, type, keyfld, nodefld) \
+DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld)
+
extern struct kmem_cache *ceph_inode_cachep;
extern struct kmem_cache *ceph_cap_cachep;
extern struct kmem_cache *ceph_cap_flush_cachep;
diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h
index e230e7ed60d3..e2a92df08b47 100644
--- a/include/linux/ceph/mon_client.h
+++ b/include/linux/ceph/mon_client.h
@@ -39,20 +39,31 @@ struct ceph_mon_request {
ceph_monc_request_func_t do_request;
};
+typedef void (*ceph_monc_callback_t)(struct ceph_mon_generic_request *);
+
/*
* ceph_mon_generic_request is being used for the statfs and
* mon_get_version requests which are being done a bit differently
* because we need to get data back to the caller
*/
struct ceph_mon_generic_request {
+ struct ceph_mon_client *monc;
struct kref kref;
u64 tid;
struct rb_node node;
int result;
- void *buf;
+
struct completion completion;
+ ceph_monc_callback_t complete_cb;
+ u64 private_data; /* r_tid/linger_id */
+
struct ceph_msg *request; /* original request */
struct ceph_msg *reply; /* and reply */
+
+ union {
+ struct ceph_statfs *st;
+ u64 newest;
+ } u;
};
struct ceph_mon_client {
@@ -77,7 +88,6 @@ struct ceph_mon_client {
/* pending generic requests */
struct rb_root generic_request_tree;
- int num_generic_requests;
u64 last_tid;
/* subs, indexed with CEPH_SUB_* */
@@ -86,6 +96,7 @@ struct ceph_mon_client {
bool want;
u32 have; /* epoch */
} subs[3];
+ int fs_cluster_id; /* "mdsmap.<id>" sub */
#ifdef CONFIG_DEBUG_FS
struct dentry *debugfs_file;
@@ -116,16 +127,18 @@ extern const char *ceph_sub_str[];
bool ceph_monc_want_map(struct ceph_mon_client *monc, int sub, u32 epoch,
bool continuous);
void ceph_monc_got_map(struct ceph_mon_client *monc, int sub, u32 epoch);
+void ceph_monc_renew_subs(struct ceph_mon_client *monc);
-extern void ceph_monc_request_next_osdmap(struct ceph_mon_client *monc);
extern int ceph_monc_wait_osdmap(struct ceph_mon_client *monc, u32 epoch,
unsigned long timeout);
extern int ceph_monc_do_statfs(struct ceph_mon_client *monc,
struct ceph_statfs *buf);
-extern int ceph_monc_do_get_version(struct ceph_mon_client *monc,
- const char *what, u64 *newest);
+int ceph_monc_get_version(struct ceph_mon_client *monc, const char *what,
+ u64 *newest);
+int ceph_monc_get_version_async(struct ceph_mon_client *monc, const char *what,
+ ceph_monc_callback_t cb, u64 private_data);
extern int ceph_monc_open_session(struct ceph_mon_client *monc);
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index cbf460927c42..19b14862d3e0 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -20,10 +20,11 @@ struct ceph_osd_client;
/*
* completion callback for async writepages
*/
-typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *,
- struct ceph_msg *);
+typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *);
typedef void (*ceph_osdc_unsafe_callback_t)(struct ceph_osd_request *, bool);
+#define CEPH_HOMELESS_OSD -1
+
/* a given osd we're communicating with */
struct ceph_osd {
atomic_t o_ref;
@@ -32,16 +33,15 @@ struct ceph_osd {
int o_incarnation;
struct rb_node o_node;
struct ceph_connection o_con;
- struct list_head o_requests;
- struct list_head o_linger_requests;
+ struct rb_root o_requests;
+ struct rb_root o_linger_requests;
struct list_head o_osd_lru;
struct ceph_auth_handshake o_auth;
unsigned long lru_ttl;
- int o_marked_for_keepalive;
struct list_head o_keepalive_item;
+ struct mutex lock;
};
-
#define CEPH_OSD_SLAB_OPS 2
#define CEPH_OSD_MAX_OPS 16
@@ -104,76 +104,95 @@ struct ceph_osd_req_op {
struct ceph_osd_data response_data;
__u8 class_len;
__u8 method_len;
- __u8 argc;
+ u32 indata_len;
} cls;
struct {
u64 cookie;
- u64 ver;
- u32 prot_ver;
- u32 timeout;
- __u8 flag;
+ __u8 op; /* CEPH_OSD_WATCH_OP_ */
+ u32 gen;
} watch;
struct {
+ struct ceph_osd_data request_data;
+ } notify_ack;
+ struct {
+ u64 cookie;
+ struct ceph_osd_data request_data;
+ struct ceph_osd_data response_data;
+ } notify;
+ struct {
u64 expected_object_size;
u64 expected_write_size;
} alloc_hint;
};
};
+struct ceph_osd_request_target {
+ struct ceph_object_id base_oid;
+ struct ceph_object_locator base_oloc;
+ struct ceph_object_id target_oid;
+ struct ceph_object_locator target_oloc;
+
+ struct ceph_pg pgid;
+ u32 pg_num;
+ u32 pg_num_mask;
+ struct ceph_osds acting;
+ struct ceph_osds up;
+ int size;
+ int min_size;
+ bool sort_bitwise;
+
+ unsigned int flags; /* CEPH_OSD_FLAG_* */
+ bool paused;
+
+ int osd;
+};
+
/* an in-flight request */
struct ceph_osd_request {
u64 r_tid; /* unique for this client */
struct rb_node r_node;
- struct list_head r_req_lru_item;
- struct list_head r_osd_item;
- struct list_head r_linger_item;
- struct list_head r_linger_osd_item;
+ struct rb_node r_mc_node; /* map check */
struct ceph_osd *r_osd;
- struct ceph_pg r_pgid;
- int r_pg_osds[CEPH_PG_MAX_SIZE];
- int r_num_pg_osds;
+
+ struct ceph_osd_request_target r_t;
+#define r_base_oid r_t.base_oid
+#define r_base_oloc r_t.base_oloc
+#define r_flags r_t.flags
struct ceph_msg *r_request, *r_reply;
- int r_flags; /* any additional flags for the osd */
u32 r_sent; /* >0 if r_request is sending/sent */
/* request osd ops array */
unsigned int r_num_ops;
- /* these are updated on each send */
- __le32 *r_request_osdmap_epoch;
- __le32 *r_request_flags;
- __le64 *r_request_pool;
- void *r_request_pgid;
- __le32 *r_request_attempts;
- bool r_paused;
- struct ceph_eversion *r_request_reassert_version;
-
int r_result;
- int r_got_reply;
- int r_linger;
+ bool r_got_reply;
struct ceph_osd_client *r_osdc;
struct kref r_kref;
bool r_mempool;
- struct completion r_completion, r_safe_completion;
+ struct completion r_completion;
+ struct completion r_safe_completion; /* fsync waiter */
ceph_osdc_callback_t r_callback;
ceph_osdc_unsafe_callback_t r_unsafe_callback;
- struct ceph_eversion r_reassert_version;
struct list_head r_unsafe_item;
struct inode *r_inode; /* for use by callbacks */
void *r_priv; /* ditto */
- struct ceph_object_locator r_base_oloc;
- struct ceph_object_id r_base_oid;
- struct ceph_object_locator r_target_oloc;
- struct ceph_object_id r_target_oid;
-
- u64 r_snapid;
- unsigned long r_stamp; /* send OR check time */
+ /* set by submitter */
+ u64 r_snapid; /* for reads, CEPH_NOSNAP o/w */
+ struct ceph_snap_context *r_snapc; /* for writes */
+ struct timespec r_mtime; /* ditto */
+ u64 r_data_offset; /* ditto */
+ bool r_linger; /* don't resend on failure */
- struct ceph_snap_context *r_snapc; /* snap context for writes */
+ /* internal */
+ unsigned long r_stamp; /* jiffies, send or check time */
+ int r_attempts;
+ struct ceph_eversion r_replay_version; /* aka reassert_version */
+ u32 r_last_force_resend;
+ u32 r_map_dne_bound;
struct ceph_osd_req_op r_ops[];
};
@@ -182,44 +201,70 @@ struct ceph_request_redirect {
struct ceph_object_locator oloc;
};
-struct ceph_osd_event {
- u64 cookie;
- int one_shot;
+typedef void (*rados_watchcb2_t)(void *arg, u64 notify_id, u64 cookie,
+ u64 notifier_id, void *data, size_t data_len);
+typedef void (*rados_watcherrcb_t)(void *arg, u64 cookie, int err);
+
+struct ceph_osd_linger_request {
struct ceph_osd_client *osdc;
- void (*cb)(u64, u64, u8, void *);
- void *data;
- struct rb_node node;
- struct list_head osd_node;
+ u64 linger_id;
+ bool committed;
+ bool is_watch; /* watch or notify */
+
+ struct ceph_osd *osd;
+ struct ceph_osd_request *reg_req;
+ struct ceph_osd_request *ping_req;
+ unsigned long ping_sent;
+ unsigned long watch_valid_thru;
+ struct list_head pending_lworks;
+
+ struct ceph_osd_request_target t;
+ u32 last_force_resend;
+ u32 map_dne_bound;
+
+ struct timespec mtime;
+
struct kref kref;
-};
+ struct mutex lock;
+ struct rb_node node; /* osd */
+ struct rb_node osdc_node; /* osdc */
+ struct rb_node mc_node; /* map check */
+ struct list_head scan_item;
+
+ struct completion reg_commit_wait;
+ struct completion notify_finish_wait;
+ int reg_commit_error;
+ int notify_finish_error;
+ int last_error;
+
+ u32 register_gen;
+ u64 notify_id;
+
+ rados_watchcb2_t wcb;
+ rados_watcherrcb_t errcb;
+ void *data;
-struct ceph_osd_event_work {
- struct work_struct work;
- struct ceph_osd_event *event;
- u64 ver;
- u64 notify_id;
- u8 opcode;
+ struct page ***preply_pages;
+ size_t *preply_len;
};
struct ceph_osd_client {
struct ceph_client *client;
struct ceph_osdmap *osdmap; /* current map */
- struct rw_semaphore map_sem;
- struct completion map_waiters;
- u64 last_requested_map;
+ struct rw_semaphore lock;
- struct mutex request_mutex;
struct rb_root osds; /* osds */
struct list_head osd_lru; /* idle osds */
- u64 timeout_tid; /* tid of timeout triggering rq */
- u64 last_tid; /* tid of last request */
- struct rb_root requests; /* pending requests */
- struct list_head req_lru; /* in-flight lru */
- struct list_head req_unsent; /* unsent/need-resend queue */
- struct list_head req_notarget; /* map to no osd */
- struct list_head req_linger; /* lingering requests */
- int num_requests;
+ spinlock_t osd_lru_lock;
+ struct ceph_osd homeless_osd;
+ atomic64_t last_tid; /* tid of last request */
+ u64 last_linger_id;
+ struct rb_root linger_requests; /* lingering requests */
+ struct rb_root map_checks;
+ struct rb_root linger_map_checks;
+ atomic_t num_requests;
+ atomic_t num_homeless;
struct delayed_work timeout_work;
struct delayed_work osds_timeout_work;
#ifdef CONFIG_DEBUG_FS
@@ -231,10 +276,6 @@ struct ceph_osd_client {
struct ceph_msgpool msgpool_op;
struct ceph_msgpool msgpool_op_reply;
- spinlock_t event_lock;
- struct rb_root event_tree;
- u64 event_count;
-
struct workqueue_struct *notify_wq;
};
@@ -271,9 +312,6 @@ extern void osd_req_op_extent_dup_last(struct ceph_osd_request *osd_req,
extern struct ceph_osd_data *osd_req_op_extent_osd_data(
struct ceph_osd_request *osd_req,
unsigned int which);
-extern struct ceph_osd_data *osd_req_op_cls_response_data(
- struct ceph_osd_request *osd_req,
- unsigned int which);
extern void osd_req_op_extent_osd_data_pages(struct ceph_osd_request *,
unsigned int which,
@@ -309,9 +347,6 @@ extern void osd_req_op_cls_init(struct ceph_osd_request *osd_req,
extern int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which,
u16 opcode, const char *name, const void *value,
size_t size, u8 cmp_op, u8 cmp_mode);
-extern void osd_req_op_watch_init(struct ceph_osd_request *osd_req,
- unsigned int which, u16 opcode,
- u64 cookie, u64 version, int flag);
extern void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req,
unsigned int which,
u64 expected_object_size,
@@ -322,11 +357,7 @@ extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *
unsigned int num_ops,
bool use_mempool,
gfp_t gfp_flags);
-
-extern void ceph_osdc_build_request(struct ceph_osd_request *req, u64 off,
- struct ceph_snap_context *snapc,
- u64 snap_id,
- struct timespec *mtime);
+int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp);
extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *,
struct ceph_file_layout *layout,
@@ -338,9 +369,6 @@ extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *,
u32 truncate_seq, u64 truncate_size,
bool use_mempool);
-extern void ceph_osdc_set_request_linger(struct ceph_osd_client *osdc,
- struct ceph_osd_request *req);
-
extern void ceph_osdc_get_request(struct ceph_osd_request *req);
extern void ceph_osdc_put_request(struct ceph_osd_request *req);
@@ -353,6 +381,7 @@ extern int ceph_osdc_wait_request(struct ceph_osd_client *osdc,
extern void ceph_osdc_sync(struct ceph_osd_client *osdc);
extern void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc);
+void ceph_osdc_maybe_request_map(struct ceph_osd_client *osdc);
extern int ceph_osdc_readpages(struct ceph_osd_client *osdc,
struct ceph_vino vino,
@@ -371,11 +400,33 @@ extern int ceph_osdc_writepages(struct ceph_osd_client *osdc,
struct timespec *mtime,
struct page **pages, int nr_pages);
-/* watch/notify events */
-extern int ceph_osdc_create_event(struct ceph_osd_client *osdc,
- void (*event_cb)(u64, u64, u8, void *),
- void *data, struct ceph_osd_event **pevent);
-extern void ceph_osdc_cancel_event(struct ceph_osd_event *event);
-extern void ceph_osdc_put_event(struct ceph_osd_event *event);
+/* watch/notify */
+struct ceph_osd_linger_request *
+ceph_osdc_watch(struct ceph_osd_client *osdc,
+ struct ceph_object_id *oid,
+ struct ceph_object_locator *oloc,
+ rados_watchcb2_t wcb,
+ rados_watcherrcb_t errcb,
+ void *data);
+int ceph_osdc_unwatch(struct ceph_osd_client *osdc,
+ struct ceph_osd_linger_request *lreq);
+
+int ceph_osdc_notify_ack(struct ceph_osd_client *osdc,
+ struct ceph_object_id *oid,
+ struct ceph_object_locator *oloc,
+ u64 notify_id,
+ u64 cookie,
+ void *payload,
+ size_t payload_len);
+int ceph_osdc_notify(struct ceph_osd_client *osdc,
+ struct ceph_object_id *oid,
+ struct ceph_object_locator *oloc,
+ void *payload,
+ size_t payload_len,
+ u32 timeout,
+ struct page ***preply_pages,
+ size_t *preply_len);
+int ceph_osdc_watch_check(struct ceph_osd_client *osdc,
+ struct ceph_osd_linger_request *lreq);
#endif
diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index e55c08bc3a96..ddc426b22d81 100644
--- a/include/linux/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -24,21 +24,29 @@ struct ceph_pg {
uint32_t seed;
};
-#define CEPH_POOL_FLAG_HASHPSPOOL 1
+int ceph_pg_compare(const struct ceph_pg *lhs, const struct ceph_pg *rhs);
+
+#define CEPH_POOL_FLAG_HASHPSPOOL (1ULL << 0) /* hash pg seed and pool id
+ together */
+#define CEPH_POOL_FLAG_FULL (1ULL << 1) /* pool is full */
struct ceph_pg_pool_info {
struct rb_node node;
s64 id;
- u8 type;
+ u8 type; /* CEPH_POOL_TYPE_* */
u8 size;
+ u8 min_size;
u8 crush_ruleset;
u8 object_hash;
+ u32 last_force_request_resend;
u32 pg_num, pgp_num;
int pg_num_mask, pgp_num_mask;
s64 read_tier;
s64 write_tier; /* wins for read+write ops */
- u64 flags;
+ u64 flags; /* CEPH_POOL_FLAG_* */
char *name;
+
+ bool was_full; /* for handle_one_map() */
};
static inline bool ceph_can_shift_osds(struct ceph_pg_pool_info *pool)
@@ -57,6 +65,22 @@ struct ceph_object_locator {
s64 pool;
};
+static inline void ceph_oloc_init(struct ceph_object_locator *oloc)
+{
+ oloc->pool = -1;
+}
+
+static inline bool ceph_oloc_empty(const struct ceph_object_locator *oloc)
+{
+ return oloc->pool == -1;
+}
+
+static inline void ceph_oloc_copy(struct ceph_object_locator *dest,
+ const struct ceph_object_locator *src)
+{
+ dest->pool = src->pool;
+}
+
/*
* Maximum supported by kernel client object name length
*
@@ -64,11 +88,47 @@ struct ceph_object_locator {
*/
#define CEPH_MAX_OID_NAME_LEN 100
+/*
+ * 51-char inline_name is long enough for all cephfs and all but one
+ * rbd requests: <imgname> in "<imgname>.rbd"/"rbd_id.<imgname>" can be
+ * arbitrarily long (~PAGE_SIZE). It's done once during rbd map; all
+ * other rbd requests fit into inline_name.
+ *
+ * Makes ceph_object_id 64 bytes on 64-bit.
+ */
+#define CEPH_OID_INLINE_LEN 52
+
+/*
+ * Both inline and external buffers have space for a NUL-terminator,
+ * which is carried around. It's not required though - RADOS object
+ * names don't have to be NUL-terminated and may contain NULs.
+ */
struct ceph_object_id {
- char name[CEPH_MAX_OID_NAME_LEN];
+ char *name;
+ char inline_name[CEPH_OID_INLINE_LEN];
int name_len;
};
+static inline void ceph_oid_init(struct ceph_object_id *oid)
+{
+ oid->name = oid->inline_name;
+ oid->name_len = 0;
+}
+
+static inline bool ceph_oid_empty(const struct ceph_object_id *oid)
+{
+ return oid->name == oid->inline_name && !oid->name_len;
+}
+
+void ceph_oid_copy(struct ceph_object_id *dest,
+ const struct ceph_object_id *src);
+__printf(2, 3)
+void ceph_oid_printf(struct ceph_object_id *oid, const char *fmt, ...);
+__printf(3, 4)
+int ceph_oid_aprintf(struct ceph_object_id *oid, gfp_t gfp,
+ const char *fmt, ...);
+void ceph_oid_destroy(struct ceph_object_id *oid);
+
struct ceph_pg_mapping {
struct rb_node node;
struct ceph_pg pgid;
@@ -87,7 +147,6 @@ struct ceph_pg_mapping {
struct ceph_osdmap {
struct ceph_fsid fsid;
u32 epoch;
- u32 mkfs_epoch;
struct ceph_timespec created, modified;
u32 flags; /* CEPH_OSDMAP_* */
@@ -113,43 +172,19 @@ struct ceph_osdmap {
int crush_scratch_ary[CEPH_PG_MAX_SIZE * 3];
};
-static inline void ceph_oid_set_name(struct ceph_object_id *oid,
- const char *name)
-{
- int len;
-
- len = strlen(name);
- if (len > sizeof(oid->name)) {
- WARN(1, "ceph_oid_set_name '%s' len %d vs %zu, truncating\n",
- name, len, sizeof(oid->name));
- len = sizeof(oid->name);
- }
-
- memcpy(oid->name, name, len);
- oid->name_len = len;
-}
-
-static inline void ceph_oid_copy(struct ceph_object_id *dest,
- struct ceph_object_id *src)
-{
- BUG_ON(src->name_len > sizeof(dest->name));
- memcpy(dest->name, src->name, src->name_len);
- dest->name_len = src->name_len;
-}
-
-static inline int ceph_osd_exists(struct ceph_osdmap *map, int osd)
+static inline bool ceph_osd_exists(struct ceph_osdmap *map, int osd)
{
return osd >= 0 && osd < map->max_osd &&
(map->osd_state[osd] & CEPH_OSD_EXISTS);
}
-static inline int ceph_osd_is_up(struct ceph_osdmap *map, int osd)
+static inline bool ceph_osd_is_up(struct ceph_osdmap *map, int osd)
{
return ceph_osd_exists(map, osd) &&
(map->osd_state[osd] & CEPH_OSD_UP);
}
-static inline int ceph_osd_is_down(struct ceph_osdmap *map, int osd)
+static inline bool ceph_osd_is_down(struct ceph_osdmap *map, int osd)
{
return !ceph_osd_is_up(map, osd);
}
@@ -192,28 +227,59 @@ static inline int ceph_decode_pgid(void **p, void *end, struct ceph_pg *pgid)
return 0;
}
+struct ceph_osdmap *ceph_osdmap_alloc(void);
extern struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end);
-extern struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
- struct ceph_osdmap *map,
- struct ceph_messenger *msgr);
+struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
+ struct ceph_osdmap *map);
extern void ceph_osdmap_destroy(struct ceph_osdmap *map);
+struct ceph_osds {
+ int osds[CEPH_PG_MAX_SIZE];
+ int size;
+ int primary; /* id, NOT index */
+};
+
+static inline void ceph_osds_init(struct ceph_osds *set)
+{
+ set->size = 0;
+ set->primary = -1;
+}
+
+void ceph_osds_copy(struct ceph_osds *dest, const struct ceph_osds *src);
+
+bool ceph_is_new_interval(const struct ceph_osds *old_acting,
+ const struct ceph_osds *new_acting,
+ const struct ceph_osds *old_up,
+ const struct ceph_osds *new_up,
+ int old_size,
+ int new_size,
+ int old_min_size,
+ int new_min_size,
+ u32 old_pg_num,
+ u32 new_pg_num,
+ bool old_sort_bitwise,
+ bool new_sort_bitwise,
+ const struct ceph_pg *pgid);
+bool ceph_osds_changed(const struct ceph_osds *old_acting,
+ const struct ceph_osds *new_acting,
+ bool any_change);
+
/* calculate mapping of a file extent to an object */
extern int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
u64 off, u64 len,
u64 *bno, u64 *oxoff, u64 *oxlen);
-/* calculate mapping of object to a placement group */
-extern int ceph_oloc_oid_to_pg(struct ceph_osdmap *osdmap,
- struct ceph_object_locator *oloc,
- struct ceph_object_id *oid,
- struct ceph_pg *pg_out);
-
-extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap,
- struct ceph_pg pgid,
- int *osds, int *primary);
-extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap,
- struct ceph_pg pgid);
+int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap,
+ struct ceph_object_id *oid,
+ struct ceph_object_locator *oloc,
+ struct ceph_pg *raw_pgid);
+
+void ceph_pg_to_up_acting_osds(struct ceph_osdmap *osdmap,
+ const struct ceph_pg *raw_pgid,
+ struct ceph_osds *up,
+ struct ceph_osds *acting);
+int ceph_pg_to_acting_primary(struct ceph_osdmap *osdmap,
+ const struct ceph_pg *raw_pgid);
extern struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map,
u64 id);
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index 2f822dca1046..5c0da61cb763 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -114,8 +114,8 @@ struct ceph_object_layout {
* compound epoch+version, used by storage layer to serialize mutations
*/
struct ceph_eversion {
- __le32 epoch;
__le64 version;
+ __le32 epoch;
} __attribute__ ((packed));
/*
@@ -153,6 +153,11 @@ extern const char *ceph_osd_state_name(int s);
#define CEPH_OSDMAP_NOIN (1<<8) /* block osd auto mark-in */
#define CEPH_OSDMAP_NOBACKFILL (1<<9) /* block osd backfill */
#define CEPH_OSDMAP_NORECOVER (1<<10) /* block osd recovery and backfill */
+#define CEPH_OSDMAP_NOSCRUB (1<<11) /* block periodic scrub */
+#define CEPH_OSDMAP_NODEEP_SCRUB (1<<12) /* block periodic deep-scrub */
+#define CEPH_OSDMAP_NOTIERAGENT (1<<13) /* disable tiering agent */
+#define CEPH_OSDMAP_NOREBALANCE (1<<14) /* block osd backfill unless pg is degraded */
+#define CEPH_OSDMAP_SORTBITWISE (1<<15) /* use bitwise hobject_t sort */
/*
* The error code to return when an OSD can't handle a write
@@ -389,6 +394,13 @@ enum {
CEPH_OSD_FLAG_SKIPRWLOCKS = 0x10000, /* skip rw locks */
CEPH_OSD_FLAG_IGNORE_OVERLAY = 0x20000, /* ignore pool overlay */
CEPH_OSD_FLAG_FLUSH = 0x40000, /* this is part of flush */
+ CEPH_OSD_FLAG_MAP_SNAP_CLONE = 0x80000, /* map snap direct to clone id */
+ CEPH_OSD_FLAG_ENFORCE_SNAPC = 0x100000, /* use snapc provided even if
+ pool uses pool snaps */
+ CEPH_OSD_FLAG_REDIRECTED = 0x200000, /* op has been redirected */
+ CEPH_OSD_FLAG_KNOWN_REDIR = 0x400000, /* redirect bit is authoritative */
+ CEPH_OSD_FLAG_FULL_TRY = 0x800000, /* try op despite full flag */
+ CEPH_OSD_FLAG_FULL_FORCE = 0x1000000, /* force op despite full flag */
};
enum {
@@ -415,7 +427,17 @@ enum {
CEPH_OSD_CMPXATTR_MODE_U64 = 2
};
-#define RADOS_NOTIFY_VER 1
+enum {
+ CEPH_OSD_WATCH_OP_UNWATCH = 0,
+ CEPH_OSD_WATCH_OP_LEGACY_WATCH = 1,
+ /* note: use only ODD ids to prevent pre-giant code from
+ interpreting the op as UNWATCH */
+ CEPH_OSD_WATCH_OP_WATCH = 3,
+ CEPH_OSD_WATCH_OP_RECONNECT = 5,
+ CEPH_OSD_WATCH_OP_PING = 7,
+};
+
+const char *ceph_osd_watch_op_name(int o);
/*
* an individual object operation. each may be accompanied by some data
@@ -450,10 +472,14 @@ struct ceph_osd_op {
} __attribute__ ((packed)) snap;
struct {
__le64 cookie;
- __le64 ver;
- __u8 flag; /* 0 = unwatch, 1 = watch */
+ __le64 ver; /* no longer used */
+ __u8 op; /* CEPH_OSD_WATCH_OP_* */
+ __le32 gen; /* registration generation */
} __attribute__ ((packed)) watch;
struct {
+ __le64 cookie;
+ } __attribute__ ((packed)) notify;
+ struct {
__le64 offset, length;
__le64 src_offset;
} __attribute__ ((packed)) clonerange;
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 982a6c4a62f3..43d5f0b799c7 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -3,45 +3,62 @@
#include <linux/fs.h>
#include <linux/mm.h>
+#include <linux/radix-tree.h>
#include <asm/pgtable.h>
+/* We use lowest available exceptional entry bit for locking */
+#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT)
+
ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *,
get_block_t, dio_iodone_t, int flags);
-int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size);
int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
int dax_truncate_page(struct inode *, loff_t from, get_block_t);
-int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
- dax_iodone_t);
-int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
- dax_iodone_t);
+int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
+int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
+int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
+void dax_wake_mapping_entry_waiter(struct address_space *mapping,
+ pgoff_t index, bool wake_all);
#ifdef CONFIG_FS_DAX
struct page *read_dax_sector(struct block_device *bdev, sector_t n);
+void dax_unlock_mapping_entry(struct address_space *mapping, pgoff_t index);
+int __dax_zero_page_range(struct block_device *bdev, sector_t sector,
+ unsigned int offset, unsigned int length);
#else
static inline struct page *read_dax_sector(struct block_device *bdev,
sector_t n)
{
return ERR_PTR(-ENXIO);
}
+/* Shouldn't ever be called when dax is disabled. */
+static inline void dax_unlock_mapping_entry(struct address_space *mapping,
+ pgoff_t index)
+{
+ BUG();
+}
+static inline int __dax_zero_page_range(struct block_device *bdev,
+ sector_t sector, unsigned int offset, unsigned int length)
+{
+ return -ENXIO;
+}
#endif
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE)
int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
- unsigned int flags, get_block_t, dax_iodone_t);
+ unsigned int flags, get_block_t);
int __dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
- unsigned int flags, get_block_t, dax_iodone_t);
+ unsigned int flags, get_block_t);
#else
static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
- pmd_t *pmd, unsigned int flags, get_block_t gb,
- dax_iodone_t di)
+ pmd_t *pmd, unsigned int flags, get_block_t gb)
{
return VM_FAULT_FALLBACK;
}
#define __dax_pmd_fault dax_pmd_fault
#endif
int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
-#define dax_mkwrite(vma, vmf, gb, iod) dax_fault(vma, vmf, gb, iod)
-#define __dax_mkwrite(vma, vmf, gb, iod) __dax_fault(vma, vmf, gb, iod)
+#define dax_mkwrite(vma, vmf, gb) dax_fault(vma, vmf, gb)
+#define __dax_mkwrite(vma, vmf, gb) __dax_fault(vma, vmf, gb)
static inline bool vma_is_dax(struct vm_area_struct *vma)
{
diff --git a/include/linux/err.h b/include/linux/err.h
index 56762ab41713..1e3558845e4c 100644
--- a/include/linux/err.h
+++ b/include/linux/err.h
@@ -18,7 +18,7 @@
#ifndef __ASSEMBLY__
-#define IS_ERR_VALUE(x) unlikely((x) >= (unsigned long)-MAX_ERRNO)
+#define IS_ERR_VALUE(x) unlikely((unsigned long)(void *)(x) >= (unsigned long)-MAX_ERRNO)
static inline void * __must_check ERR_PTR(long error)
{
diff --git a/include/linux/errno.h b/include/linux/errno.h
index 89627b9187f9..7ce9fb1b7d28 100644
--- a/include/linux/errno.h
+++ b/include/linux/errno.h
@@ -28,5 +28,6 @@
#define EBADTYPE 527 /* Type not supported by server */
#define EJUKEBOX 528 /* Request initiated, but will not complete before timeout */
#define EIOCBQUEUED 529 /* iocb queued, will get completion event */
+#define ERECALLCONFLICT 530 /* conflict with recalled state */
#endif
diff --git a/include/linux/export.h b/include/linux/export.h
index 96e45ea463e7..2f9ccbe6a639 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -38,7 +38,7 @@ extern struct module __this_module;
#ifdef CONFIG_MODULES
-#ifndef __GENKSYMS__
+#if defined(__KERNEL__) && !defined(__GENKSYMS__)
#ifdef CONFIG_MODVERSIONS
/* Mark the CRC weak since genksyms apparently decides not to
* generate a checksums for some symbols */
@@ -53,7 +53,7 @@ extern struct module __this_module;
#endif
/* For every exported symbol, place a struct in the __ksymtab section */
-#define __EXPORT_SYMBOL(sym, sec) \
+#define ___EXPORT_SYMBOL(sym, sec) \
extern typeof(sym) sym; \
__CRC_SYMBOL(sym, sec) \
static const char __kstrtab_##sym[] \
@@ -65,6 +65,35 @@ extern struct module __this_module;
__attribute__((section("___ksymtab" sec "+" #sym), unused)) \
= { (unsigned long)&sym, __kstrtab_##sym }
+#if defined(__KSYM_DEPS__)
+
+/*
+ * For fine grained build dependencies, we want to tell the build system
+ * about each possible exported symbol even if they're not actually exported.
+ * We use a string pattern that is unlikely to be valid code that the build
+ * system filters out from the preprocessor output (see ksym_dep_filter
+ * in scripts/Kbuild.include).
+ */
+#define __EXPORT_SYMBOL(sym, sec) === __KSYM_##sym ===
+
+#elif defined(CONFIG_TRIM_UNUSED_KSYMS)
+
+#include <linux/kconfig.h>
+#include <generated/autoksyms.h>
+
+#define __EXPORT_SYMBOL(sym, sec) \
+ __cond_export_sym(sym, sec, config_enabled(__KSYM_##sym))
+#define __cond_export_sym(sym, sec, conf) \
+ ___cond_export_sym(sym, sec, conf)
+#define ___cond_export_sym(sym, sec, enabled) \
+ __cond_export_sym_##enabled(sym, sec)
+#define __cond_export_sym_1(sym, sec) ___EXPORT_SYMBOL(sym, sec)
+#define __cond_export_sym_0(sym, sec) /* nothing */
+
+#else
+#define __EXPORT_SYMBOL ___EXPORT_SYMBOL
+#endif
+
#define EXPORT_SYMBOL(sym) \
__EXPORT_SYMBOL(sym, "")
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 62bdb0a6cf2d..dd288148a6b1 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -74,7 +74,6 @@ typedef int (get_block_t)(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
ssize_t bytes, void *private);
-typedef void (dax_iodone_t)(struct buffer_head *bh_map, int uptodate);
#define MAY_EXEC 0x00000001
#define MAY_WRITE 0x00000002
diff --git a/include/linux/iova.h b/include/linux/iova.h
index 92f7177db2ce..f27bb2c62fca 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -19,8 +19,21 @@
/* iova structure */
struct iova {
struct rb_node node;
- unsigned long pfn_hi; /* IOMMU dish out addr hi */
- unsigned long pfn_lo; /* IOMMU dish out addr lo */
+ unsigned long pfn_hi; /* Highest allocated pfn */
+ unsigned long pfn_lo; /* Lowest allocated pfn */
+};
+
+struct iova_magazine;
+struct iova_cpu_rcache;
+
+#define IOVA_RANGE_CACHE_MAX_SIZE 6 /* log of max cached IOVA range size (in pages) */
+#define MAX_GLOBAL_MAGS 32 /* magazines per bin */
+
+struct iova_rcache {
+ spinlock_t lock;
+ unsigned long depot_size;
+ struct iova_magazine *depot[MAX_GLOBAL_MAGS];
+ struct iova_cpu_rcache __percpu *cpu_rcaches;
};
/* holds all the iova translations for a domain */
@@ -31,6 +44,7 @@ struct iova_domain {
unsigned long granule; /* pfn granularity for this domain */
unsigned long start_pfn; /* Lower limit for this domain */
unsigned long dma_32bit_pfn;
+ struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE]; /* IOVA range caches */
};
static inline unsigned long iova_size(struct iova *iova)
@@ -78,6 +92,10 @@ void __free_iova(struct iova_domain *iovad, struct iova *iova);
struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size,
unsigned long limit_pfn,
bool size_aligned);
+void free_iova_fast(struct iova_domain *iovad, unsigned long pfn,
+ unsigned long size);
+unsigned long alloc_iova_fast(struct iova_domain *iovad, unsigned long size,
+ unsigned long limit_pfn);
struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo,
unsigned long pfn_hi);
void copy_reserved_iova(struct iova_domain *from, struct iova_domain *to);
@@ -87,5 +105,6 @@ struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn);
void put_iova_domain(struct iova_domain *iovad);
struct iova *split_and_remove_iova(struct iova_domain *iovad,
struct iova *iova, unsigned long pfn_lo, unsigned long pfn_hi);
+void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad);
#endif
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 9e6fdd33bdb2..bfbd707de390 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -273,6 +273,12 @@
#define ICH_LR_ACTIVE_BIT (1ULL << 63)
#define ICH_LR_PHYS_ID_SHIFT 32
#define ICH_LR_PHYS_ID_MASK (0x3ffULL << ICH_LR_PHYS_ID_SHIFT)
+#define ICH_LR_PRIORITY_SHIFT 48
+
+/* These are for GICv2 emulation only */
+#define GICH_LR_VIRTUALID (0x3ffUL << 0)
+#define GICH_LR_PHYSID_CPUID_SHIFT (10)
+#define GICH_LR_PHYSID_CPUID (7UL << GICH_LR_PHYSID_CPUID_SHIFT)
#define ICH_MISR_EOI (1 << 0)
#define ICH_MISR_U (1 << 1)
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index 9c940263ca23..fd051855539b 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -33,6 +33,7 @@
#define GIC_DIST_CTRL 0x000
#define GIC_DIST_CTR 0x004
+#define GIC_DIST_IIDR 0x008
#define GIC_DIST_IGROUP 0x080
#define GIC_DIST_ENABLE_SET 0x100
#define GIC_DIST_ENABLE_CLEAR 0x180
@@ -76,6 +77,7 @@
#define GICH_LR_VIRTUALID (0x3ff << 0)
#define GICH_LR_PHYSID_CPUID_SHIFT (10)
#define GICH_LR_PHYSID_CPUID (0x3ff << GICH_LR_PHYSID_CPUID_SHIFT)
+#define GICH_LR_PRIORITY_SHIFT 23
#define GICH_LR_STATE (3 << 28)
#define GICH_LR_PENDING_BIT (1 << 28)
#define GICH_LR_ACTIVE_BIT (1 << 29)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index b1fa8f11c95b..1c9c973a7dd9 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -412,6 +412,8 @@ struct kvm {
#endif
long tlbs_dirty;
struct list_head devices;
+ struct dentry *debugfs_dentry;
+ struct kvm_stat_data **debugfs_stat_data;
};
#define kvm_err(fmt, ...) \
@@ -991,6 +993,11 @@ enum kvm_stat_kind {
KVM_STAT_VCPU,
};
+struct kvm_stat_data {
+ int offset;
+ struct kvm *kvm;
+};
+
struct kvm_stats_debugfs_item {
const char *name;
int offset;
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 20d8a5d4d133..5145620ba48a 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -182,7 +182,7 @@ static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
-extern void register_page_bootmem_info_node(struct pglist_data *pgdat);
+extern void __init register_page_bootmem_info_node(struct pglist_data *pgdat);
#else
static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
{
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2835d598d258..5df5feb49575 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -303,6 +303,12 @@ struct vm_fault {
* is set (which is also implied by
* VM_FAULT_ERROR).
*/
+ void *entry; /* ->fault handler can alternatively
+ * return locked DAX entry. In that
+ * case handler should return
+ * VM_FAULT_DAX_LOCKED and fill in
+ * entry here.
+ */
/* for ->map_pages() only */
pgoff_t max_pgoff; /* map pages for offset from pgoff till
* max_pgoff inclusive */
@@ -1076,6 +1082,7 @@ static inline void clear_page_pfmemalloc(struct page *page)
#define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */
#define VM_FAULT_RETRY 0x0400 /* ->fault blocked, must retry */
#define VM_FAULT_FALLBACK 0x0800 /* huge page fault failed, fall back to small */
+#define VM_FAULT_DAX_LOCKED 0x1000 /* ->fault has locked DAX entry */
#define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
@@ -2011,7 +2018,7 @@ static inline void mm_populate(unsigned long addr, unsigned long len) {}
#endif
/* These take the mm semaphore themselves */
-extern unsigned long __must_check vm_brk(unsigned long, unsigned long);
+extern int __must_check vm_brk(unsigned long, unsigned long);
extern int vm_munmap(unsigned long, size_t);
extern unsigned long __must_check vm_mmap(struct file *, unsigned long,
unsigned long, unsigned long,
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index d553855503e6..ca3e517980a0 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -514,7 +514,9 @@ struct mm_struct {
#ifdef CONFIG_HUGETLB_PAGE
atomic_long_t hugetlb_usage;
#endif
+#ifdef CONFIG_MMU
struct work_struct async_put_work;
+#endif
};
static inline void mm_init_cpumask(struct mm_struct *mm)
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 85800b48241f..45cde8cd39f2 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -329,6 +329,7 @@ struct mmc_host {
unsigned int can_retune:1; /* re-tuning can be used */
unsigned int doing_retune:1; /* re-tuning in progress */
unsigned int retune_now:1; /* do re-tuning at next req */
+ unsigned int retune_paused:1; /* re-tuning is temporarily disabled */
int rescan_disable; /* disable card detection */
int rescan_entered; /* used with nonremovable devices */
@@ -526,4 +527,7 @@ static inline void mmc_retune_recheck(struct mmc_host *host)
host->retune_now = 1;
}
+void mmc_retune_pause(struct mmc_host *host);
+void mmc_retune_unpause(struct mmc_host *host);
+
#endif /* LINUX_MMC_HOST_H */
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 011433478a14..bfed6b367350 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -50,12 +50,27 @@ struct nfs4_label {
typedef struct { char data[NFS4_VERIFIER_SIZE]; } nfs4_verifier;
-struct nfs_stateid4 {
- __be32 seqid;
- char other[NFS4_STATEID_OTHER_SIZE];
-} __attribute__ ((packed));
+struct nfs4_stateid_struct {
+ union {
+ char data[NFS4_STATEID_SIZE];
+ struct {
+ __be32 seqid;
+ char other[NFS4_STATEID_OTHER_SIZE];
+ } __attribute__ ((packed));
+ };
+
+ enum {
+ NFS4_INVALID_STATEID_TYPE = 0,
+ NFS4_SPECIAL_STATEID_TYPE,
+ NFS4_OPEN_STATEID_TYPE,
+ NFS4_LOCK_STATEID_TYPE,
+ NFS4_DELEGATION_STATEID_TYPE,
+ NFS4_LAYOUT_STATEID_TYPE,
+ NFS4_PNFS_DS_STATEID_TYPE,
+ } type;
+};
-typedef struct nfs_stateid4 nfs4_stateid;
+typedef struct nfs4_stateid_struct nfs4_stateid;
enum nfs_opnum4 {
OP_ACCESS = 3,
@@ -504,6 +519,7 @@ enum {
NFSPROC4_CLNT_DEALLOCATE,
NFSPROC4_CLNT_LAYOUTSTATS,
NFSPROC4_CLNT_CLONE,
+ NFSPROC4_CLNT_COPY,
};
/* nfs41 types */
@@ -621,7 +637,9 @@ enum pnfs_update_layout_reason {
PNFS_UPDATE_LAYOUT_IO_TEST_FAIL,
PNFS_UPDATE_LAYOUT_FOUND_CACHED,
PNFS_UPDATE_LAYOUT_RETURN,
+ PNFS_UPDATE_LAYOUT_RETRY,
PNFS_UPDATE_LAYOUT_BLOCKED,
+ PNFS_UPDATE_LAYOUT_INVALID_OPEN,
PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET,
};
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 7fcc13c8cf1f..14a762d2734d 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -246,5 +246,6 @@ struct nfs_server {
#define NFS_CAP_DEALLOCATE (1U << 21)
#define NFS_CAP_LAYOUTSTATS (1U << 22)
#define NFS_CAP_CLONE (1U << 23)
+#define NFS_CAP_COPY (1U << 24)
#endif
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index ee8491dadbf3..c304a11b5b1a 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -233,7 +233,6 @@ struct nfs4_layoutget_args {
struct inode *inode;
struct nfs_open_context *ctx;
nfs4_stateid stateid;
- unsigned long timestamp;
struct nfs4_layoutdriver_data layout;
};
@@ -251,7 +250,6 @@ struct nfs4_layoutget {
struct nfs4_layoutget_res res;
struct rpc_cred *cred;
gfp_t gfp_flags;
- long timeout;
};
struct nfs4_getdeviceinfo_args {
@@ -1343,6 +1341,32 @@ struct nfs42_falloc_res {
const struct nfs_server *falloc_server;
};
+struct nfs42_copy_args {
+ struct nfs4_sequence_args seq_args;
+
+ struct nfs_fh *src_fh;
+ nfs4_stateid src_stateid;
+ u64 src_pos;
+
+ struct nfs_fh *dst_fh;
+ nfs4_stateid dst_stateid;
+ u64 dst_pos;
+
+ u64 count;
+};
+
+struct nfs42_write_res {
+ u64 count;
+ struct nfs_writeverf verifier;
+};
+
+struct nfs42_copy_res {
+ struct nfs4_sequence_res seq_res;
+ struct nfs42_write_res write_res;
+ bool consecutive;
+ bool synchronous;
+};
+
struct nfs42_seek_args {
struct nfs4_sequence_args seq_args;
@@ -1431,7 +1455,7 @@ struct nfs_commit_completion_ops {
};
struct nfs_commit_info {
- spinlock_t *lock; /* inode->i_lock */
+ struct inode *inode; /* Needed for inode->i_lock */
struct nfs_mds_commit_info *mds;
struct pnfs_ds_commit_info *ds;
struct nfs_direct_req *dreq; /* O_DIRECT request */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 44f33834ad78..1a827cecd62f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -61,6 +61,14 @@ struct perf_callchain_entry {
__u64 ip[0]; /* /proc/sys/kernel/perf_event_max_stack */
};
+struct perf_callchain_entry_ctx {
+ struct perf_callchain_entry *entry;
+ u32 max_stack;
+ u32 nr;
+ short contexts;
+ bool contexts_maxed;
+};
+
struct perf_raw_record {
u32 size;
void *data;
@@ -1061,20 +1069,36 @@ extern void perf_event_fork(struct task_struct *tsk);
/* Callchains */
DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
-extern void perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs);
-extern void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs);
+extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
+extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
extern struct perf_callchain_entry *
get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
- bool crosstask, bool add_mark);
+ u32 max_stack, bool crosstask, bool add_mark);
extern int get_callchain_buffers(void);
extern void put_callchain_buffers(void);
extern int sysctl_perf_event_max_stack;
+extern int sysctl_perf_event_max_contexts_per_stack;
+
+static inline int perf_callchain_store_context(struct perf_callchain_entry_ctx *ctx, u64 ip)
+{
+ if (ctx->contexts < sysctl_perf_event_max_contexts_per_stack) {
+ struct perf_callchain_entry *entry = ctx->entry;
+ entry->ip[entry->nr++] = ip;
+ ++ctx->contexts;
+ return 0;
+ } else {
+ ctx->contexts_maxed = true;
+ return -1; /* no more room, stop walking the stack */
+ }
+}
-static inline int perf_callchain_store(struct perf_callchain_entry *entry, u64 ip)
+static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 ip)
{
- if (entry->nr < sysctl_perf_event_max_stack) {
+ if (ctx->nr < ctx->max_stack && !ctx->contexts_maxed) {
+ struct perf_callchain_entry *entry = ctx->entry;
entry->ip[entry->nr++] = ip;
+ ++ctx->nr;
return 0;
} else {
return -1; /* no more room, stop walking the stack */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 21c26e78aec5..6e42ada26345 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1539,6 +1539,7 @@ struct task_struct {
unsigned sched_reset_on_fork:1;
unsigned sched_contributes_to_load:1;
unsigned sched_migrated:1;
+ unsigned sched_remote_wakeup:1;
unsigned :0; /* force alignment to the next boundary */
/* unserialized, strictly 'current' */
@@ -2744,10 +2745,12 @@ static inline bool mmget_not_zero(struct mm_struct *mm)
/* mmput gets rid of the mappings and all user-space */
extern void mmput(struct mm_struct *);
-/* same as above but performs the slow path from the async kontext. Can
+#ifdef CONFIG_MMU
+/* same as above but performs the slow path from the async context. Can
* be called from the atomic context as well
*/
extern void mmput_async(struct mm_struct *);
+#endif
/* Grab a reference to a task's mm, if it is not already going away */
extern struct mm_struct *get_task_mm(struct task_struct *task);
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index e0582106ef4f..7973a821ac58 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -277,7 +277,7 @@ static inline void raw_write_seqcount_barrier(seqcount_t *s)
static inline int raw_read_seqcount_latch(seqcount_t *s)
{
- return lockless_dereference(s->sequence);
+ return lockless_dereference(s)->sequence;
}
/**
@@ -331,7 +331,7 @@ static inline int raw_read_seqcount_latch(seqcount_t *s)
* unsigned seq, idx;
*
* do {
- * seq = lockless_dereference(latch->seq);
+ * seq = lockless_dereference(latch)->seq;
*
* idx = seq & 0x01;
* entry = data_query(latch->data[idx], ...);
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 665cd0cd18b8..d1faa019c02a 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -111,22 +111,6 @@ static inline void sysfs_slab_remove(struct kmem_cache *s)
}
#endif
-
-/**
- * virt_to_obj - returns address of the beginning of object.
- * @s: object's kmem_cache
- * @slab_page: address of slab page
- * @x: address within object memory range
- *
- * Returns address of the beginning of object
- */
-static inline void *virt_to_obj(struct kmem_cache *s,
- const void *slab_page,
- const void *x)
-{
- return (void *)x - ((x - slab_page) % s->size);
-}
-
void object_err(struct kmem_cache *s, struct page *page,
u8 *object, char *reason);
diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h
index 6a241a277249..899791573a40 100644
--- a/include/linux/sunrpc/auth.h
+++ b/include/linux/sunrpc/auth.h
@@ -127,7 +127,7 @@ struct rpc_authops {
void (*destroy)(struct rpc_auth *);
struct rpc_cred * (*lookup_cred)(struct rpc_auth *, struct auth_cred *, int);
- struct rpc_cred * (*crcreate)(struct rpc_auth*, struct auth_cred *, int);
+ struct rpc_cred * (*crcreate)(struct rpc_auth*, struct auth_cred *, int, gfp_t);
int (*list_pseudoflavors)(rpc_authflavor_t *, int);
rpc_authflavor_t (*info2flavor)(struct rpcsec_gss_info *);
int (*flavor2info)(rpc_authflavor_t,
@@ -167,6 +167,7 @@ void rpc_destroy_authunix(void);
struct rpc_cred * rpc_lookup_cred(void);
struct rpc_cred * rpc_lookup_cred_nonblock(void);
+struct rpc_cred * rpc_lookup_generic_cred(struct auth_cred *, int, gfp_t);
struct rpc_cred * rpc_lookup_machine_cred(const char *service_name);
int rpcauth_register(const struct rpc_authops *);
int rpcauth_unregister(const struct rpc_authops *);
@@ -178,7 +179,7 @@ rpc_authflavor_t rpcauth_get_pseudoflavor(rpc_authflavor_t,
int rpcauth_get_gssinfo(rpc_authflavor_t,
struct rpcsec_gss_info *);
int rpcauth_list_flavors(rpc_authflavor_t *, int);
-struct rpc_cred * rpcauth_lookup_credcache(struct rpc_auth *, struct auth_cred *, int);
+struct rpc_cred * rpcauth_lookup_credcache(struct rpc_auth *, struct auth_cred *, int, gfp_t);
void rpcauth_init_cred(struct rpc_cred *, const struct auth_cred *, struct rpc_auth *, const struct rpc_credops *);
struct rpc_cred * rpcauth_lookupcred(struct rpc_auth *, int);
struct rpc_cred * rpcauth_generic_bind_cred(struct rpc_task *, struct rpc_cred *, int);
@@ -201,9 +202,28 @@ char * rpcauth_stringify_acceptor(struct rpc_cred *);
static inline
struct rpc_cred * get_rpccred(struct rpc_cred *cred)
{
- atomic_inc(&cred->cr_count);
+ if (cred != NULL)
+ atomic_inc(&cred->cr_count);
return cred;
}
+/**
+ * get_rpccred_rcu - get a reference to a cred using rcu-protected pointer
+ * @cred: cred of which to take a reference
+ *
+ * In some cases, we may have a pointer to a credential to which we
+ * want to take a reference, but don't already have one. Because these
+ * objects are freed using RCU, we can access the cr_count while its
+ * on its way to destruction and only take a reference if it's not already
+ * zero.
+ */
+static inline struct rpc_cred *
+get_rpccred_rcu(struct rpc_cred *cred)
+{
+ if (atomic_inc_not_zero(&cred->cr_count))
+ return cred;
+ return NULL;
+}
+
#endif /* __KERNEL__ */
#endif /* _LINUX_SUNRPC_AUTH_H */
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 9a7ddbaf116e..19c659d1c0f8 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -176,6 +176,7 @@ void rpc_setbufsize(struct rpc_clnt *, unsigned int, unsigned int);
int rpc_protocol(struct rpc_clnt *);
struct net * rpc_net_ns(struct rpc_clnt *);
size_t rpc_max_payload(struct rpc_clnt *);
+size_t rpc_max_bc_payload(struct rpc_clnt *);
unsigned long rpc_get_timeout(struct rpc_clnt *clnt);
void rpc_force_rebind(struct rpc_clnt *);
size_t rpc_peeraddr(struct rpc_clnt *, struct sockaddr *, size_t);
diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h
index 807371357160..59cbf16eaeb5 100644
--- a/include/linux/sunrpc/msg_prot.h
+++ b/include/linux/sunrpc/msg_prot.h
@@ -158,9 +158,9 @@ typedef __be32 rpc_fraghdr;
/*
* Note that RFC 1833 does not put any size restrictions on the
- * netid string, but all currently defined netid's fit in 4 bytes.
+ * netid string, but all currently defined netid's fit in 5 bytes.
*/
-#define RPCBIND_MAXNETIDLEN (4u)
+#define RPCBIND_MAXNETIDLEN (5u)
/*
* Universal addresses are introduced in RFC 1833 and further spelled
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index fb0d212e0d3a..5aa3834619a8 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -142,6 +142,7 @@ struct rpc_xprt_ops {
int (*bc_setup)(struct rpc_xprt *xprt,
unsigned int min_reqs);
int (*bc_up)(struct svc_serv *serv, struct net *net);
+ size_t (*bc_maxpayload)(struct rpc_xprt *xprt);
void (*bc_free_rqst)(struct rpc_rqst *rqst);
void (*bc_destroy)(struct rpc_xprt *xprt,
unsigned int max_reqs);
diff --git a/include/linux/sunrpc/xprtrdma.h b/include/linux/sunrpc/xprtrdma.h
index 767190b01363..39267dc3486a 100644
--- a/include/linux/sunrpc/xprtrdma.h
+++ b/include/linux/sunrpc/xprtrdma.h
@@ -52,7 +52,9 @@
#define RPCRDMA_DEF_SLOT_TABLE (128U)
#define RPCRDMA_MAX_SLOT_TABLE (256U)
-#define RPCRDMA_DEF_INLINE (1024) /* default inline max */
+#define RPCRDMA_MIN_INLINE (1024) /* min inline thresh */
+#define RPCRDMA_DEF_INLINE (1024) /* default inline thresh */
+#define RPCRDMA_MAX_INLINE (3068) /* max inline thresh */
/* Memory registration strategies, by number.
* This is part of a kernel / user space API. Do not remove. */
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index 1b8a5a7876ce..e45abe7db9a6 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -340,6 +340,7 @@ struct thermal_zone_of_device_ops {
int (*get_temp)(void *, int *);
int (*get_trend)(void *, long *);
int (*set_emul_temp)(void *, int);
+ int (*set_trip_temp)(void *, int, int);
};
/**
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 526fb3d2e43a..f28292d73ddb 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -108,7 +108,7 @@ TRACE_EVENT(kvm_ioapic_set_irq,
__entry->coalesced = coalesced;
),
- TP_printk("pin %u dst %x vec=%u (%s|%s|%s%s)%s",
+ TP_printk("pin %u dst %x vec %u (%s|%s|%s%s)%s",
__entry->pin, (u8)(__entry->e >> 56), (u8)__entry->e,
__print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode),
(__entry->e & (1<<11)) ? "logical" : "physical",
@@ -129,7 +129,7 @@ TRACE_EVENT(kvm_ioapic_delayed_eoi_inj,
__entry->e = e;
),
- TP_printk("dst %x vec=%u (%s|%s|%s%s)",
+ TP_printk("dst %x vec %u (%s|%s|%s%s)",
(u8)(__entry->e >> 56), (u8)__entry->e,
__print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode),
(__entry->e & (1<<11)) ? "logical" : "physical",
@@ -151,7 +151,7 @@ TRACE_EVENT(kvm_msi_set_irq,
__entry->data = data;
),
- TP_printk("dst %u vec %x (%s|%s|%s%s)",
+ TP_printk("dst %u vec %u (%s|%s|%s%s)",
(u8)(__entry->address >> 12), (u8)__entry->data,
__print_symbolic((__entry->data >> 8 & 0x7), kvm_deliver_mode),
(__entry->address & (1<<2)) ? "logical" : "physical",
diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h
index c4b2a3f90829..50ff21f748b6 100644
--- a/include/uapi/linux/nvme_ioctl.h
+++ b/include/uapi/linux/nvme_ioctl.h
@@ -61,5 +61,6 @@ struct nvme_passthru_cmd {
#define NVME_IOCTL_IO_CMD _IOWR('N', 0x43, struct nvme_passthru_cmd)
#define NVME_IOCTL_RESET _IO('N', 0x44)
#define NVME_IOCTL_SUBSYS_RESET _IO('N', 0x45)
+#define NVME_IOCTL_RESCAN _IO('N', 0x46)
#endif /* _UAPI_LINUX_NVME_IOCTL_H */
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 43fc8d213472..36ce552cf6a9 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -862,6 +862,7 @@ enum perf_event_type {
};
#define PERF_MAX_STACK_DEPTH 127
+#define PERF_MAX_CONTEXTS_PER_STACK 8
enum perf_callchain_context {
PERF_CONTEXT_HV = (__u64)-32,
diff --git a/include/video/imx-ipu-v3.h b/include/video/imx-ipu-v3.h
index ad66589f2ae6..3a2a79401789 100644
--- a/include/video/imx-ipu-v3.h
+++ b/include/video/imx-ipu-v3.h
@@ -16,6 +16,7 @@
#include <linux/videodev2.h>
#include <linux/bitmap.h>
#include <linux/fb.h>
+#include <linux/of.h>
#include <media/v4l2-mediabus.h>
#include <video/videomode.h>
@@ -345,6 +346,7 @@ struct ipu_client_platformdata {
int dc;
int dp;
int dma[2];
+ struct device_node *of_node;
};
#endif /* __DRM_IPU_H__ */