summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
Diffstat (limited to 'include')
-rw-r--r--include/asm-generic/barrier.h2
-rw-r--r--include/drm/bridge/aux-bridge.h15
-rw-r--r--include/kunit/test.h12
-rw-r--r--include/linux/async.h1
-rw-r--r--include/linux/backing-dev.h1
-rw-r--r--include/linux/bitmap.h3
-rw-r--r--include/linux/blk-integrity.h1
-rw-r--r--include/linux/blk-mq.h12
-rw-r--r--include/linux/blk_types.h44
-rw-r--r--include/linux/blkdev.h86
-rw-r--r--include/linux/bvec.h2
-rw-r--r--include/linux/clocksource_ids.h3
-rw-r--r--include/linux/compiler_attributes.h4
-rw-r--r--include/linux/cpuset.h10
-rw-r--r--include/linux/cxl-event.h18
-rw-r--r--include/linux/dcache.h19
-rw-r--r--include/linux/device-mapper.h2
-rw-r--r--include/linux/dpll.h19
-rw-r--r--include/linux/file.h2
-rw-r--r--include/linux/filelock.h129
-rw-r--r--include/linux/fs.h140
-rw-r--r--include/linux/fscrypt.h66
-rw-r--r--include/linux/gfp.h9
-rw-r--r--include/linux/hyperv.h22
-rw-r--r--include/linux/io_uring_types.h137
-rw-r--r--include/linux/iomap.h19
-rw-r--r--include/linux/iommu.h3
-rw-r--r--include/linux/irq.h2
-rw-r--r--include/linux/irqdomain.h17
-rw-r--r--include/linux/irqdomain_defs.h2
-rw-r--r--include/linux/irqhandler.h2
-rw-r--r--include/linux/kvm_host.h26
-rw-r--r--include/linux/lockd/lockd.h8
-rw-r--r--include/linux/lockd/xdr.h2
-rw-r--r--include/linux/maple_tree.h7
-rw-r--r--include/linux/memblock.h2
-rw-r--r--include/linux/mlx5/mlx5_ifc.h6
-rw-r--r--include/linux/mlx5/qp.h5
-rw-r--r--include/linux/msi.h24
-rw-r--r--include/linux/netdevice.h25
-rw-r--r--include/linux/netfilter.h1
-rw-r--r--include/linux/nfs_fs_sb.h2
-rw-r--r--include/linux/ns_common.h2
-rw-r--r--include/linux/nvme-rdma.h6
-rw-r--r--include/linux/nvme.h2
-rw-r--r--include/linux/pid.h10
-rw-r--r--include/linux/pidfs.h9
-rw-r--r--include/linux/pktcdvd.h4
-rw-r--r--include/linux/poison.h3
-rw-r--r--include/linux/poll.h4
-rw-r--r--include/linux/proc_fs.h1
-rw-r--r--include/linux/proc_ns.h2
-rw-r--r--include/linux/ptp_kvm.h4
-rw-r--r--include/linux/rcu_sync.h1
-rw-r--r--include/linux/rcupdate.h4
-rw-r--r--include/linux/rw_hint.h24
-rw-r--r--include/linux/sched.h4
-rw-r--r--include/linux/sched/signal.h2
-rw-r--r--include/linux/sched/topology.h6
-rw-r--r--include/linux/smp.h2
-rw-r--r--include/linux/soc/andes/irq.h18
-rw-r--r--include/linux/swap.h7
-rw-r--r--include/linux/timekeeping.h10
-rw-r--r--include/linux/trace_seq.h8
-rw-r--r--include/linux/uio.h16
-rw-r--r--include/linux/usb/hcd.h2
-rw-r--r--include/linux/workqueue.h141
-rw-r--r--include/net/busy_poll.h4
-rw-r--r--include/net/mctp.h1
-rw-r--r--include/net/netfilter/nf_flow_table.h2
-rw-r--r--include/net/sch_generic.h7
-rw-r--r--include/net/switchdev.h3
-rw-r--r--include/net/tcp.h2
-rw-r--r--include/scsi/scsi_device.h5
-rw-r--r--include/sound/soc-card.h2
-rw-r--r--include/trace/events/afs.h4
-rw-r--r--include/trace/events/filelock.h102
-rw-r--r--include/trace/events/io_uring.h30
-rw-r--r--include/trace/events/qdisc.h20
-rw-r--r--include/uapi/drm/nouveau_drm.h14
-rw-r--r--include/uapi/drm/xe_drm.h22
-rw-r--r--include/uapi/linux/fs.h30
-rw-r--r--include/uapi/linux/in6.h2
-rw-r--r--include/uapi/linux/io_uring.h13
-rw-r--r--include/uapi/linux/magic.h1
-rw-r--r--include/uapi/linux/pidfd.h8
-rw-r--r--include/uapi/linux/ublk_cmd.h2
-rw-r--r--include/uapi/sound/asound.h4
88 files changed, 1009 insertions, 473 deletions
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 961f4d88f9ef..0c0695763bea 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -193,7 +193,6 @@ do { \
#ifndef smp_store_release
#define smp_store_release(p, v) \
do { \
- compiletime_assert_atomic_type(*p); \
barrier(); \
WRITE_ONCE(*p, v); \
} while (0)
@@ -203,7 +202,6 @@ do { \
#define smp_load_acquire(p) \
({ \
__unqual_scalar_typeof(*p) ___p1 = READ_ONCE(*p); \
- compiletime_assert_atomic_type(*p); \
barrier(); \
(typeof(*p))___p1; \
})
diff --git a/include/drm/bridge/aux-bridge.h b/include/drm/bridge/aux-bridge.h
index c4c423e97f06..4453906105ca 100644
--- a/include/drm/bridge/aux-bridge.h
+++ b/include/drm/bridge/aux-bridge.h
@@ -9,6 +9,8 @@
#include <drm/drm_connector.h>
+struct auxiliary_device;
+
#if IS_ENABLED(CONFIG_DRM_AUX_BRIDGE)
int drm_aux_bridge_register(struct device *parent);
#else
@@ -19,10 +21,23 @@ static inline int drm_aux_bridge_register(struct device *parent)
#endif
#if IS_ENABLED(CONFIG_DRM_AUX_HPD_BRIDGE)
+struct auxiliary_device *devm_drm_dp_hpd_bridge_alloc(struct device *parent, struct device_node *np);
+int devm_drm_dp_hpd_bridge_add(struct device *dev, struct auxiliary_device *adev);
struct device *drm_dp_hpd_bridge_register(struct device *parent,
struct device_node *np);
void drm_aux_hpd_bridge_notify(struct device *dev, enum drm_connector_status status);
#else
+static inline struct auxiliary_device *devm_drm_dp_hpd_bridge_alloc(struct device *parent,
+ struct device_node *np)
+{
+ return NULL;
+}
+
+static inline int devm_drm_dp_hpd_bridge_add(struct auxiliary_device *adev)
+{
+ return 0;
+}
+
static inline struct device *drm_dp_hpd_bridge_register(struct device *parent,
struct device_node *np)
{
diff --git a/include/kunit/test.h b/include/kunit/test.h
index fcb4a4940ace..61637ef32302 100644
--- a/include/kunit/test.h
+++ b/include/kunit/test.h
@@ -579,12 +579,12 @@ void __printf(2, 3) kunit_log_append(struct string_stream *log, const char *fmt,
void __noreturn __kunit_abort(struct kunit *test);
-void __kunit_do_failed_assertion(struct kunit *test,
- const struct kunit_loc *loc,
- enum kunit_assert_type type,
- const struct kunit_assert *assert,
- assert_format_t assert_format,
- const char *fmt, ...);
+void __printf(6, 7) __kunit_do_failed_assertion(struct kunit *test,
+ const struct kunit_loc *loc,
+ enum kunit_assert_type type,
+ const struct kunit_assert *assert,
+ assert_format_t assert_format,
+ const char *fmt, ...);
#define _KUNIT_FAILED(test, assert_type, assert_class, assert_format, INITIALIZER, fmt, ...) do { \
static const struct kunit_loc __loc = KUNIT_CURRENT_LOC; \
diff --git a/include/linux/async.h b/include/linux/async.h
index 33c9ff4afb49..19b778d08600 100644
--- a/include/linux/async.h
+++ b/include/linux/async.h
@@ -120,4 +120,5 @@ extern void async_synchronize_cookie(async_cookie_t cookie);
extern void async_synchronize_cookie_domain(async_cookie_t cookie,
struct async_domain *domain);
extern bool current_is_async(void);
+extern void async_init(void);
#endif
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 1a97277f99b1..8e7af9a03b41 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -38,7 +38,6 @@ struct backing_dev_info *bdi_alloc(int node_id);
void wb_start_background_writeback(struct bdi_writeback *wb);
void wb_workfn(struct work_struct *work);
-void wb_wakeup_delayed(struct bdi_writeback *wb);
void wb_wait_for_completion(struct wb_completion *done);
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 99451431e4d6..df24c8fb1009 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -6,6 +6,7 @@
#include <linux/align.h>
#include <linux/bitops.h>
+#include <linux/cleanup.h>
#include <linux/errno.h>
#include <linux/find.h>
#include <linux/limits.h>
@@ -127,6 +128,8 @@ unsigned long *bitmap_alloc_node(unsigned int nbits, gfp_t flags, int node);
unsigned long *bitmap_zalloc_node(unsigned int nbits, gfp_t flags, int node);
void bitmap_free(const unsigned long *bitmap);
+DEFINE_FREE(bitmap, unsigned long *, if (_T) bitmap_free(_T))
+
/* Managed variants of the above. */
unsigned long *devm_bitmap_alloc(struct device *dev,
unsigned int nbits, gfp_t flags);
diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h
index 378b2459efe2..e253e7bd0d17 100644
--- a/include/linux/blk-integrity.h
+++ b/include/linux/blk-integrity.h
@@ -20,6 +20,7 @@ struct blk_integrity_iter {
unsigned int data_size;
unsigned short interval;
unsigned char tuple_size;
+ unsigned char pi_offset;
const char *disk_name;
};
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 7a8150a5f051..d3d8fd8e229b 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -8,6 +8,7 @@
#include <linux/scatterlist.h>
#include <linux/prefetch.h>
#include <linux/srcu.h>
+#include <linux/rw_hint.h>
struct blk_mq_tags;
struct blk_flush_queue;
@@ -135,6 +136,7 @@ struct request {
struct blk_crypto_keyslot *crypt_keyslot;
#endif
+ enum rw_hint write_hint;
unsigned short ioprio;
enum mq_rq_state state;
@@ -682,17 +684,19 @@ enum {
#define BLK_MQ_NO_HCTX_IDX (-1U)
-struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata,
+struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set,
+ struct queue_limits *lim, void *queuedata,
struct lock_class_key *lkclass);
-#define blk_mq_alloc_disk(set, queuedata) \
+#define blk_mq_alloc_disk(set, lim, queuedata) \
({ \
static struct lock_class_key __key; \
\
- __blk_mq_alloc_disk(set, queuedata, &__key); \
+ __blk_mq_alloc_disk(set, lim, queuedata, &__key); \
})
struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q,
struct lock_class_key *lkclass);
-struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *);
+struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set,
+ struct queue_limits *lim, void *queuedata);
int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
struct request_queue *q);
void blk_mq_destroy_queue(struct request_queue *);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index f288c94374b3..cb1526ec44b5 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -10,6 +10,7 @@
#include <linux/bvec.h>
#include <linux/device.h>
#include <linux/ktime.h>
+#include <linux/rw_hint.h>
struct bio_set;
struct bio;
@@ -206,52 +207,10 @@ static inline bool blk_path_error(blk_status_t error)
return true;
}
-/*
- * From most significant bit:
- * 1 bit: reserved for other usage, see below
- * 12 bits: original size of bio
- * 51 bits: issue time of bio
- */
-#define BIO_ISSUE_RES_BITS 1
-#define BIO_ISSUE_SIZE_BITS 12
-#define BIO_ISSUE_RES_SHIFT (64 - BIO_ISSUE_RES_BITS)
-#define BIO_ISSUE_SIZE_SHIFT (BIO_ISSUE_RES_SHIFT - BIO_ISSUE_SIZE_BITS)
-#define BIO_ISSUE_TIME_MASK ((1ULL << BIO_ISSUE_SIZE_SHIFT) - 1)
-#define BIO_ISSUE_SIZE_MASK \
- (((1ULL << BIO_ISSUE_SIZE_BITS) - 1) << BIO_ISSUE_SIZE_SHIFT)
-#define BIO_ISSUE_RES_MASK (~((1ULL << BIO_ISSUE_RES_SHIFT) - 1))
-
-/* Reserved bit for blk-throtl */
-#define BIO_ISSUE_THROTL_SKIP_LATENCY (1ULL << 63)
-
struct bio_issue {
u64 value;
};
-static inline u64 __bio_issue_time(u64 time)
-{
- return time & BIO_ISSUE_TIME_MASK;
-}
-
-static inline u64 bio_issue_time(struct bio_issue *issue)
-{
- return __bio_issue_time(issue->value);
-}
-
-static inline sector_t bio_issue_size(struct bio_issue *issue)
-{
- return ((issue->value & BIO_ISSUE_SIZE_MASK) >> BIO_ISSUE_SIZE_SHIFT);
-}
-
-static inline void bio_issue_init(struct bio_issue *issue,
- sector_t size)
-{
- size &= (1ULL << BIO_ISSUE_SIZE_BITS) - 1;
- issue->value = ((issue->value & BIO_ISSUE_RES_MASK) |
- (ktime_get_ns() & BIO_ISSUE_TIME_MASK) |
- ((u64)size << BIO_ISSUE_SIZE_SHIFT));
-}
-
typedef __u32 __bitwise blk_opf_t;
typedef unsigned int blk_qc_t;
@@ -269,6 +228,7 @@ struct bio {
*/
unsigned short bi_flags; /* BIO_* below */
unsigned short bi_ioprio;
+ enum rw_hint bi_write_hint;
blk_status_t bi_status;
atomic_t __bi_remaining;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 99e4f5e72213..f9b87c39cab0 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -24,6 +24,7 @@
#include <linux/sbitmap.h>
#include <linux/uuid.h>
#include <linux/xarray.h>
+#include <linux/file.h>
struct module;
struct request_queue;
@@ -42,7 +43,7 @@ struct blk_crypto_profile;
extern const struct device_type disk_type;
extern const struct device_type part_type;
-extern struct class block_class;
+extern const struct class block_class;
/*
* Maximum number of blkcg policies allowed to be registered concurrently.
@@ -108,6 +109,7 @@ struct blk_integrity {
const struct blk_integrity_profile *profile;
unsigned char flags;
unsigned char tuple_size;
+ unsigned char pi_offset;
unsigned char interval_exp;
unsigned char tag_size;
};
@@ -189,8 +191,6 @@ struct gendisk {
* blk_mq_unfreeze_queue().
*/
unsigned int nr_zones;
- unsigned int max_open_zones;
- unsigned int max_active_zones;
unsigned long *conv_zones_bitmap;
unsigned long *seq_zones_wlock;
#endif /* CONFIG_BLK_DEV_ZONED */
@@ -292,6 +292,7 @@ struct queue_limits {
unsigned int io_opt;
unsigned int max_discard_sectors;
unsigned int max_hw_discard_sectors;
+ unsigned int max_user_discard_sectors;
unsigned int max_secure_erase_sectors;
unsigned int max_write_zeroes_sectors;
unsigned int max_zone_append_sectors;
@@ -307,6 +308,8 @@ struct queue_limits {
unsigned char discard_misaligned;
unsigned char raid_partial_stripes_expensive;
bool zoned;
+ unsigned int max_open_zones;
+ unsigned int max_active_zones;
/*
* Drivers that set dma_alignment to less than 511 must be prepared to
@@ -325,7 +328,7 @@ void disk_set_zoned(struct gendisk *disk);
int blkdev_report_zones(struct block_device *bdev, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data);
int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
- sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask);
+ sector_t sectors, sector_t nr_sectors);
int blk_revalidate_disk_zones(struct gendisk *disk,
void (*update_driver_data)(struct gendisk *disk));
@@ -473,6 +476,7 @@ struct request_queue {
struct mutex sysfs_lock;
struct mutex sysfs_dir_lock;
+ struct mutex limits_lock;
/*
* for reusing dead hctx instance in case of updating
@@ -639,23 +643,23 @@ static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector)
static inline void disk_set_max_open_zones(struct gendisk *disk,
unsigned int max_open_zones)
{
- disk->max_open_zones = max_open_zones;
+ disk->queue->limits.max_open_zones = max_open_zones;
}
static inline void disk_set_max_active_zones(struct gendisk *disk,
unsigned int max_active_zones)
{
- disk->max_active_zones = max_active_zones;
+ disk->queue->limits.max_active_zones = max_active_zones;
}
static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
{
- return bdev->bd_disk->max_open_zones;
+ return bdev->bd_disk->queue->limits.max_open_zones;
}
static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
{
- return bdev->bd_disk->max_active_zones;
+ return bdev->bd_disk->queue->limits.max_active_zones;
}
#else /* CONFIG_BLK_DEV_ZONED */
@@ -763,22 +767,26 @@ static inline u64 sb_bdev_nr_blocks(struct super_block *sb)
int bdev_disk_changed(struct gendisk *disk, bool invalidate);
void put_disk(struct gendisk *disk);
-struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass);
+struct gendisk *__blk_alloc_disk(struct queue_limits *lim, int node,
+ struct lock_class_key *lkclass);
/**
* blk_alloc_disk - allocate a gendisk structure
+ * @lim: queue limits to be used for this disk.
* @node_id: numa node to allocate on
*
* Allocate and pre-initialize a gendisk structure for use with BIO based
* drivers.
*
+ * Returns an ERR_PTR on error, else the allocated disk.
+ *
* Context: can sleep
*/
-#define blk_alloc_disk(node_id) \
+#define blk_alloc_disk(lim, node_id) \
({ \
static struct lock_class_key __key; \
\
- __blk_alloc_disk(node_id, &__key); \
+ __blk_alloc_disk(lim, node_id, &__key); \
})
int __register_blkdev(unsigned int major, const char *name,
@@ -861,6 +869,29 @@ static inline unsigned int blk_chunk_sectors_left(sector_t offset,
return chunk_sectors - (offset & (chunk_sectors - 1));
}
+/**
+ * queue_limits_start_update - start an atomic update of queue limits
+ * @q: queue to update
+ *
+ * This functions starts an atomic update of the queue limits. It takes a lock
+ * to prevent other updates and returns a snapshot of the current limits that
+ * the caller can modify. The caller must call queue_limits_commit_update()
+ * to finish the update.
+ *
+ * Context: process context. The caller must have frozen the queue or ensured
+ * that there is outstanding I/O by other means.
+ */
+static inline struct queue_limits
+queue_limits_start_update(struct request_queue *q)
+ __acquires(q->limits_lock)
+{
+ mutex_lock(&q->limits_lock);
+ return q->limits;
+}
+int queue_limits_commit_update(struct request_queue *q,
+ struct queue_limits *lim);
+int queue_limits_set(struct request_queue *q, struct queue_limits *lim);
+
/*
* Access functions for manipulating queue properties
*/
@@ -894,8 +925,8 @@ extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth);
extern void blk_set_stacking_limits(struct queue_limits *lim);
extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
sector_t offset);
-extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
- sector_t offset);
+void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev,
+ sector_t offset, const char *pfx);
extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
extern void blk_queue_segment_boundary(struct request_queue *, unsigned long);
extern void blk_queue_virt_boundary(struct request_queue *, unsigned long);
@@ -942,6 +973,7 @@ struct blk_plug {
/* if ios_left is > 1, we can batch tag/rq allocations */
struct request *cached_rq;
+ u64 cur_ktime;
unsigned short nr_ios;
unsigned short rq_count;
@@ -972,6 +1004,18 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async)
__blk_flush_plug(plug, async);
}
+/*
+ * tsk == current here
+ */
+static inline void blk_plug_invalidate_ts(struct task_struct *tsk)
+{
+ struct blk_plug *plug = tsk->plug;
+
+ if (plug)
+ plug->cur_ktime = 0;
+ current->flags &= ~PF_BLOCK_TS;
+}
+
int blkdev_issue_flush(struct block_device *bdev);
long nr_blockdev_pages(void);
#else /* CONFIG_BLOCK */
@@ -995,6 +1039,10 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async)
{
}
+static inline void blk_plug_invalidate_ts(struct task_struct *tsk)
+{
+}
+
static inline int blkdev_issue_flush(struct block_device *bdev)
{
return 0;
@@ -1474,26 +1522,20 @@ extern const struct blk_holder_ops fs_holder_ops;
(BLK_OPEN_READ | BLK_OPEN_RESTRICT_WRITES | \
(((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE))
-struct bdev_handle {
- struct block_device *bdev;
- void *holder;
- blk_mode_t mode;
-};
-
-struct bdev_handle *bdev_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
+struct file *bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
const struct blk_holder_ops *hops);
-struct bdev_handle *bdev_open_by_path(const char *path, blk_mode_t mode,
+struct file *bdev_file_open_by_path(const char *path, blk_mode_t mode,
void *holder, const struct blk_holder_ops *hops);
int bd_prepare_to_claim(struct block_device *bdev, void *holder,
const struct blk_holder_ops *hops);
void bd_abort_claiming(struct block_device *bdev, void *holder);
-void bdev_release(struct bdev_handle *handle);
/* just for blk-cgroup, don't use elsewhere */
struct block_device *blkdev_get_no_open(dev_t dev);
void blkdev_put_no_open(struct block_device *bdev);
struct block_device *I_BDEV(struct inode *inode);
+struct block_device *file_bdev(struct file *bdev_file);
#ifdef CONFIG_BLOCK
void invalidate_bdev(struct block_device *bdev);
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index 555aae5448ae..bd1e361b351c 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -83,7 +83,7 @@ struct bvec_iter {
unsigned int bi_bvec_done; /* number of bytes completed in
current bvec */
-} __packed;
+} __packed __aligned(4);
struct bvec_iter_all {
struct bio_vec bv;
diff --git a/include/linux/clocksource_ids.h b/include/linux/clocksource_ids.h
index 16775d7d8f8d..a4fa3436940c 100644
--- a/include/linux/clocksource_ids.h
+++ b/include/linux/clocksource_ids.h
@@ -6,6 +6,9 @@
enum clocksource_ids {
CSID_GENERIC = 0,
CSID_ARM_ARCH_COUNTER,
+ CSID_X86_TSC_EARLY,
+ CSID_X86_TSC,
+ CSID_X86_KVM_CLK,
CSID_MAX,
};
diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index 28566624f008..289810685fc5 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -95,11 +95,11 @@
#endif
/*
- * Optional: only supported since gcc >= 14
+ * Optional: only supported since gcc >= 15
* Optional: only supported since clang >= 18
*
* gcc: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108896
- * clang: https://reviews.llvm.org/D148381
+ * clang: https://github.com/llvm/llvm-project/pull/76348
*/
#if __has_attribute(__counted_by__)
# define __counted_by(member) __attribute__((__counted_by__(member)))
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 875d12598bd2..0ce6ff0d9c9a 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -121,11 +121,6 @@ static inline int cpuset_do_page_mem_spread(void)
return task_spread_page(current);
}
-static inline int cpuset_do_slab_mem_spread(void)
-{
- return task_spread_slab(current);
-}
-
extern bool current_cpuset_is_being_rebound(void);
extern void rebuild_sched_domains(void);
@@ -264,11 +259,6 @@ static inline int cpuset_do_page_mem_spread(void)
return 0;
}
-static inline int cpuset_do_slab_mem_spread(void)
-{
- return 0;
-}
-
static inline bool current_cpuset_is_being_rebound(void)
{
return false;
diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h
index 91125eca4c8a..03fa6d50d46f 100644
--- a/include/linux/cxl-event.h
+++ b/include/linux/cxl-event.h
@@ -140,22 +140,4 @@ struct cxl_cper_event_rec {
union cxl_event event;
} __packed;
-typedef void (*cxl_cper_callback)(enum cxl_event_type type,
- struct cxl_cper_event_rec *rec);
-
-#ifdef CONFIG_ACPI_APEI_GHES
-int cxl_cper_register_callback(cxl_cper_callback callback);
-int cxl_cper_unregister_callback(cxl_cper_callback callback);
-#else
-static inline int cxl_cper_register_callback(cxl_cper_callback callback)
-{
- return 0;
-}
-
-static inline int cxl_cper_unregister_callback(cxl_cper_callback callback)
-{
- return 0;
-}
-#endif
-
#endif /* _LINUX_CXL_EVENT_H */
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 1666c387861f..bf53e3894aae 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -125,6 +125,11 @@ enum dentry_d_lock_class
DENTRY_D_LOCK_NESTED
};
+enum d_real_type {
+ D_REAL_DATA,
+ D_REAL_METADATA,
+};
+
struct dentry_operations {
int (*d_revalidate)(struct dentry *, unsigned int);
int (*d_weak_revalidate)(struct dentry *, unsigned int);
@@ -139,7 +144,7 @@ struct dentry_operations {
char *(*d_dname)(struct dentry *, char *, int);
struct vfsmount *(*d_automount)(struct path *);
int (*d_manage)(const struct path *, bool);
- struct dentry *(*d_real)(struct dentry *, const struct inode *);
+ struct dentry *(*d_real)(struct dentry *, enum d_real_type type);
} ____cacheline_aligned;
/*
@@ -173,6 +178,7 @@ struct dentry_operations {
#define DCACHE_DONTCACHE BIT(7) /* Purge from memory on final dput() */
#define DCACHE_CANT_MOUNT BIT(8)
+#define DCACHE_GENOCIDE BIT(9)
#define DCACHE_SHRINK_LIST BIT(10)
#define DCACHE_OP_WEAK_REVALIDATE BIT(11)
@@ -546,24 +552,23 @@ static inline struct inode *d_backing_inode(const struct dentry *upper)
/**
* d_real - Return the real dentry
* @dentry: the dentry to query
- * @inode: inode to select the dentry from multiple layers (can be NULL)
+ * @type: the type of real dentry (data or metadata)
*
* If dentry is on a union/overlay, then return the underlying, real dentry.
* Otherwise return the dentry itself.
*
* See also: Documentation/filesystems/vfs.rst
*/
-static inline struct dentry *d_real(struct dentry *dentry,
- const struct inode *inode)
+static inline struct dentry *d_real(struct dentry *dentry, enum d_real_type type)
{
if (unlikely(dentry->d_flags & DCACHE_OP_REAL))
- return dentry->d_op->d_real(dentry, inode);
+ return dentry->d_op->d_real(dentry, type);
else
return dentry;
}
/**
- * d_real_inode - Return the real inode
+ * d_real_inode - Return the real inode hosting the data
* @dentry: The dentry to query
*
* If dentry is on a union/overlay, then return the underlying, real inode.
@@ -572,7 +577,7 @@ static inline struct dentry *d_real(struct dentry *dentry,
static inline struct inode *d_real_inode(const struct dentry *dentry)
{
/* This usage of d_real() results in const dentry */
- return d_backing_inode(d_real((struct dentry *) dentry, NULL));
+ return d_inode(d_real((struct dentry *) dentry, D_REAL_DATA));
}
struct name_snapshot {
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 772ab4d74d94..82b2195efaca 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -165,7 +165,7 @@ void dm_error(const char *message);
struct dm_dev {
struct block_device *bdev;
- struct bdev_handle *bdev_handle;
+ struct file *bdev_file;
struct dax_device *dax_dev;
blk_mode_t mode;
char name[16];
diff --git a/include/linux/dpll.h b/include/linux/dpll.h
index 9cf896ea1d41..e37344f6a231 100644
--- a/include/linux/dpll.h
+++ b/include/linux/dpll.h
@@ -10,6 +10,8 @@
#include <uapi/linux/dpll.h>
#include <linux/device.h>
#include <linux/netlink.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
struct dpll_device;
struct dpll_pin;
@@ -120,15 +122,24 @@ struct dpll_pin_properties {
};
#if IS_ENABLED(CONFIG_DPLL)
-size_t dpll_msg_pin_handle_size(struct dpll_pin *pin);
-int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin);
+void dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin);
+void dpll_netdev_pin_clear(struct net_device *dev);
+
+size_t dpll_netdev_pin_handle_size(const struct net_device *dev);
+int dpll_netdev_add_pin_handle(struct sk_buff *msg,
+ const struct net_device *dev);
#else
-static inline size_t dpll_msg_pin_handle_size(struct dpll_pin *pin)
+static inline void
+dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin) { }
+static inline void dpll_netdev_pin_clear(struct net_device *dev) { }
+
+static inline size_t dpll_netdev_pin_handle_size(const struct net_device *dev)
{
return 0;
}
-static inline int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin)
+static inline int
+dpll_netdev_add_pin_handle(struct sk_buff *msg, const struct net_device *dev)
{
return 0;
}
diff --git a/include/linux/file.h b/include/linux/file.h
index 6834a29338c4..169692cb1906 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -24,6 +24,8 @@ struct inode;
struct path;
extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *,
const char *, int flags, const struct file_operations *);
+extern struct file *alloc_file_pseudo_noaccount(struct inode *, struct vfsmount *,
+ const char *, int flags, const struct file_operations *);
extern struct file *alloc_file_clone(struct file *, int flags,
const struct file_operations *);
diff --git a/include/linux/filelock.h b/include/linux/filelock.h
index 95e868e09e29..daee999d05f3 100644
--- a/include/linux/filelock.h
+++ b/include/linux/filelock.h
@@ -27,6 +27,7 @@
#define FILE_LOCK_DEFERRED 1
struct file_lock;
+struct file_lease;
struct file_lock_operations {
void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
@@ -39,14 +40,17 @@ struct lock_manager_operations {
void (*lm_put_owner)(fl_owner_t);
void (*lm_notify)(struct file_lock *); /* unblock callback */
int (*lm_grant)(struct file_lock *, int);
- bool (*lm_break)(struct file_lock *);
- int (*lm_change)(struct file_lock *, int, struct list_head *);
- void (*lm_setup)(struct file_lock *, void **);
- bool (*lm_breaker_owns_lease)(struct file_lock *);
bool (*lm_lock_expirable)(struct file_lock *cfl);
void (*lm_expire_lock)(void);
};
+struct lease_manager_operations {
+ bool (*lm_break)(struct file_lease *);
+ int (*lm_change)(struct file_lease *, int, struct list_head *);
+ void (*lm_setup)(struct file_lease *, void **);
+ bool (*lm_breaker_owns_lease)(struct file_lease *);
+};
+
struct lock_manager {
struct list_head list;
/*
@@ -85,31 +89,31 @@ bool opens_in_grace(struct net *);
*
* Obviously, the last two criteria only matter for POSIX locks.
*/
-struct file_lock {
- struct file_lock *fl_blocker; /* The lock, that is blocking us */
- struct list_head fl_list; /* link into file_lock_context */
- struct hlist_node fl_link; /* node in global lists */
- struct list_head fl_blocked_requests; /* list of requests with
+
+struct file_lock_core {
+ struct file_lock_core *flc_blocker; /* The lock that is blocking us */
+ struct list_head flc_list; /* link into file_lock_context */
+ struct hlist_node flc_link; /* node in global lists */
+ struct list_head flc_blocked_requests; /* list of requests with
* ->fl_blocker pointing here
*/
- struct list_head fl_blocked_member; /* node in
+ struct list_head flc_blocked_member; /* node in
* ->fl_blocker->fl_blocked_requests
*/
- fl_owner_t fl_owner;
- unsigned int fl_flags;
- unsigned char fl_type;
- unsigned int fl_pid;
- int fl_link_cpu; /* what cpu's list is this on? */
- wait_queue_head_t fl_wait;
- struct file *fl_file;
+ fl_owner_t flc_owner;
+ unsigned int flc_flags;
+ unsigned char flc_type;
+ pid_t flc_pid;
+ int flc_link_cpu; /* what cpu's list is this on? */
+ wait_queue_head_t flc_wait;
+ struct file *flc_file;
+};
+
+struct file_lock {
+ struct file_lock_core c;
loff_t fl_start;
loff_t fl_end;
- struct fasync_struct * fl_fasync; /* for lease break notifications */
- /* for lease breaks: */
- unsigned long fl_break_time;
- unsigned long fl_downgrade_time;
-
const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */
const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */
union {
@@ -126,6 +130,15 @@ struct file_lock {
} fl_u;
} __randomize_layout;
+struct file_lease {
+ struct file_lock_core c;
+ struct fasync_struct * fl_fasync; /* for lease break notifications */
+ /* for lease breaks: */
+ unsigned long fl_break_time;
+ unsigned long fl_downgrade_time;
+ const struct lease_manager_operations *fl_lmops; /* Callbacks for lease managers */
+} __randomize_layout;
+
struct file_lock_context {
spinlock_t flc_lock;
struct list_head flc_flock;
@@ -147,11 +160,31 @@ int fcntl_setlk64(unsigned int, struct file *, unsigned int,
int fcntl_setlease(unsigned int fd, struct file *filp, int arg);
int fcntl_getlease(struct file *filp);
+static inline bool lock_is_unlock(struct file_lock *fl)
+{
+ return fl->c.flc_type == F_UNLCK;
+}
+
+static inline bool lock_is_read(struct file_lock *fl)
+{
+ return fl->c.flc_type == F_RDLCK;
+}
+
+static inline bool lock_is_write(struct file_lock *fl)
+{
+ return fl->c.flc_type == F_WRLCK;
+}
+
+static inline void locks_wake_up(struct file_lock *fl)
+{
+ wake_up(&fl->c.flc_wait);
+}
+
/* fs/locks.c */
void locks_free_lock_context(struct inode *inode);
void locks_free_lock(struct file_lock *fl);
void locks_init_lock(struct file_lock *);
-struct file_lock * locks_alloc_lock(void);
+struct file_lock *locks_alloc_lock(void);
void locks_copy_lock(struct file_lock *, struct file_lock *);
void locks_copy_conflock(struct file_lock *, struct file_lock *);
void locks_remove_posix(struct file *, fl_owner_t);
@@ -165,11 +198,16 @@ int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_l
int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
bool vfs_inode_has_locks(struct inode *inode);
int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl);
+
+void locks_init_lease(struct file_lease *);
+void locks_free_lease(struct file_lease *fl);
+struct file_lease *locks_alloc_lease(void);
int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
void lease_get_mtime(struct inode *, struct timespec64 *time);
-int generic_setlease(struct file *, int, struct file_lock **, void **priv);
-int vfs_setlease(struct file *, int, struct file_lock **, void **);
-int lease_modify(struct file_lock *, int, struct list_head *);
+int generic_setlease(struct file *, int, struct file_lease **, void **priv);
+int kernel_setlease(struct file *, int, struct file_lease **, void **);
+int vfs_setlease(struct file *, int, struct file_lease **, void **);
+int lease_modify(struct file_lease *, int, struct list_head *);
struct notifier_block;
int lease_register_notifier(struct notifier_block *);
@@ -223,6 +261,25 @@ static inline int fcntl_getlease(struct file *filp)
return F_UNLCK;
}
+static inline bool lock_is_unlock(struct file_lock *fl)
+{
+ return false;
+}
+
+static inline bool lock_is_read(struct file_lock *fl)
+{
+ return false;
+}
+
+static inline bool lock_is_write(struct file_lock *fl)
+{
+ return false;
+}
+
+static inline void locks_wake_up(struct file_lock *fl)
+{
+}
+
static inline void
locks_free_lock_context(struct inode *inode)
{
@@ -233,6 +290,11 @@ static inline void locks_init_lock(struct file_lock *fl)
return;
}
+static inline void locks_init_lease(struct file_lease *fl)
+{
+ return;
+}
+
static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
{
return;
@@ -307,18 +369,24 @@ static inline void lease_get_mtime(struct inode *inode,
}
static inline int generic_setlease(struct file *filp, int arg,
- struct file_lock **flp, void **priv)
+ struct file_lease **flp, void **priv)
+{
+ return -EINVAL;
+}
+
+static inline int kernel_setlease(struct file *filp, int arg,
+ struct file_lease **lease, void **priv)
{
return -EINVAL;
}
static inline int vfs_setlease(struct file *filp, int arg,
- struct file_lock **lease, void **priv)
+ struct file_lease **lease, void **priv)
{
return -EINVAL;
}
-static inline int lease_modify(struct file_lock *fl, int arg,
+static inline int lease_modify(struct file_lease *fl, int arg,
struct list_head *dispose)
{
return -EINVAL;
@@ -341,6 +409,9 @@ locks_inode_context(const struct inode *inode)
#endif /* !CONFIG_FILE_LOCKING */
+/* for walking lists of file_locks linked by fl_list */
+#define for_each_file_lock(_fl, _head) list_for_each_entry(_fl, _head, c.flc_list)
+
static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl)
{
return locks_lock_inode_wait(file_inode(filp), fl);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 023f37c60709..0a22b7245982 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -43,6 +43,8 @@
#include <linux/cred.h>
#include <linux/mnt_idmapping.h>
#include <linux/slab.h>
+#include <linux/maple_tree.h>
+#include <linux/rw_hint.h>
#include <asm/byteorder.h>
#include <uapi/linux/fs.h>
@@ -309,19 +311,6 @@ struct address_space;
struct writeback_control;
struct readahead_control;
-/*
- * Write life time hint values.
- * Stored in struct inode as u8.
- */
-enum rw_hint {
- WRITE_LIFE_NOT_SET = 0,
- WRITE_LIFE_NONE = RWH_WRITE_LIFE_NONE,
- WRITE_LIFE_SHORT = RWH_WRITE_LIFE_SHORT,
- WRITE_LIFE_MEDIUM = RWH_WRITE_LIFE_MEDIUM,
- WRITE_LIFE_LONG = RWH_WRITE_LIFE_LONG,
- WRITE_LIFE_EXTREME = RWH_WRITE_LIFE_EXTREME,
-};
-
/* Match RWF_* bits to IOCB bits */
#define IOCB_HIPRI (__force int) RWF_HIPRI
#define IOCB_DSYNC (__force int) RWF_DSYNC
@@ -352,6 +341,8 @@ enum rw_hint {
* unrelated IO (like cache flushing, new IO generation, etc).
*/
#define IOCB_DIO_CALLER_COMP (1 << 22)
+/* kiocb is a read or write operation submitted by fs/aio.c. */
+#define IOCB_AIO_RW (1 << 23)
/* for use in trace events */
#define TRACE_IOCB_STRINGS \
@@ -482,10 +473,10 @@ struct address_space {
pgoff_t writeback_index;
const struct address_space_operations *a_ops;
unsigned long flags;
- struct rw_semaphore i_mmap_rwsem;
errseq_t wb_err;
spinlock_t i_private_lock;
struct list_head i_private_list;
+ struct rw_semaphore i_mmap_rwsem;
void * i_private_data;
} __attribute__((aligned(sizeof(long)))) __randomize_layout;
/*
@@ -677,7 +668,7 @@ struct inode {
spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */
unsigned short i_bytes;
u8 i_blkbits;
- u8 i_write_hint;
+ enum rw_hint i_write_hint;
blkcnt_t i_blocks;
#ifdef __NEED_I_SIZE_ORDERED
@@ -907,7 +898,8 @@ static inline loff_t i_size_read(const struct inode *inode)
preempt_enable();
return i_size;
#else
- return inode->i_size;
+ /* Pairs with smp_store_release() in i_size_write() */
+ return smp_load_acquire(&inode->i_size);
#endif
}
@@ -929,7 +921,12 @@ static inline void i_size_write(struct inode *inode, loff_t i_size)
inode->i_size = i_size;
preempt_enable();
#else
- inode->i_size = i_size;
+ /*
+ * Pairs with smp_load_acquire() in i_size_read() to ensure
+ * changes related to inode size (such as page contents) are
+ * visible before we see the changed inode size.
+ */
+ smp_store_release(&inode->i_size, i_size);
#endif
}
@@ -1064,6 +1061,7 @@ struct file *get_file_active(struct file **f);
typedef void *fl_owner_t;
struct file_lock;
+struct file_lease;
/* The following constant reflects the upper bound of the file/locking space */
#ifndef OFFSET_MAX
@@ -1078,9 +1076,20 @@ static inline struct inode *file_inode(const struct file *f)
return f->f_inode;
}
+/*
+ * file_dentry() is a relic from the days that overlayfs was using files with a
+ * "fake" path, meaning, f_path on overlayfs and f_inode on underlying fs.
+ * In those days, file_dentry() was needed to get the underlying fs dentry that
+ * matches f_inode.
+ * Files with "fake" path should not exist nowadays, so use an assertion to make
+ * sure that file_dentry() was not papering over filesystem bugs.
+ */
static inline struct dentry *file_dentry(const struct file *file)
{
- return d_real(file->f_path.dentry, file_inode(file));
+ struct dentry *dentry = file->f_path.dentry;
+
+ WARN_ON_ONCE(d_inode(dentry) != file_inode(file));
+ return dentry;
}
struct fasync_struct {
@@ -1228,8 +1237,8 @@ struct super_block {
#endif
struct hlist_bl_head s_roots; /* alternate root dentries for NFS */
struct list_head s_mounts; /* list of mounts; _not_ for fs use */
- struct block_device *s_bdev;
- struct bdev_handle *s_bdev_handle;
+ struct block_device *s_bdev; /* can go away once we use an accessor for @s_bdev_file */
+ struct file *s_bdev_file;
struct backing_dev_info *s_bdi;
struct mtd_info *s_mtd;
struct hlist_node s_instances;
@@ -1255,8 +1264,22 @@ struct super_block {
struct fsnotify_mark_connector __rcu *s_fsnotify_marks;
#endif
+ /*
+ * q: why are s_id and s_sysfs_name not the same? both are human
+ * readable strings that identify the filesystem
+ * a: s_id is allowed to change at runtime; it's used in log messages,
+ * and we want to when a device starts out as single device (s_id is dev
+ * name) but then a device is hot added and we have to switch to
+ * identifying it by UUID
+ * but s_sysfs_name is a handle for programmatic access, and can't
+ * change at runtime
+ */
char s_id[32]; /* Informational name */
uuid_t s_uuid; /* UUID */
+ u8 s_uuid_len; /* Default 16, possibly smaller for weird filesystems */
+
+ /* if set, fs shows up under sysfs at /sys/fs/$FSTYP/s_sysfs_name */
+ char s_sysfs_name[UUID_STRING_LEN + 1];
unsigned int s_max_links;
@@ -2005,7 +2028,7 @@ struct file_operations {
ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
void (*splice_eof)(struct file *file);
- int (*setlease)(struct file *, int, struct file_lock **, void **);
+ int (*setlease)(struct file *, int, struct file_lease **, void **);
long (*fallocate)(struct file *file, int mode, loff_t offset,
loff_t len);
void (*show_fdinfo)(struct seq_file *m, struct file *f);
@@ -2529,6 +2552,44 @@ extern __printf(2, 3)
int super_setup_bdi_name(struct super_block *sb, char *fmt, ...);
extern int super_setup_bdi(struct super_block *sb);
+static inline void super_set_uuid(struct super_block *sb, const u8 *uuid, unsigned len)
+{
+ if (WARN_ON(len > sizeof(sb->s_uuid)))
+ len = sizeof(sb->s_uuid);
+ sb->s_uuid_len = len;
+ memcpy(&sb->s_uuid, uuid, len);
+}
+
+/* set sb sysfs name based on sb->s_bdev */
+static inline void super_set_sysfs_name_bdev(struct super_block *sb)
+{
+ snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pg", sb->s_bdev);
+}
+
+/* set sb sysfs name based on sb->s_uuid */
+static inline void super_set_sysfs_name_uuid(struct super_block *sb)
+{
+ WARN_ON(sb->s_uuid_len != sizeof(sb->s_uuid));
+ snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pU", sb->s_uuid.b);
+}
+
+/* set sb sysfs name based on sb->s_id */
+static inline void super_set_sysfs_name_id(struct super_block *sb)
+{
+ strscpy(sb->s_sysfs_name, sb->s_id, sizeof(sb->s_sysfs_name));
+}
+
+/* try to use something standard before you use this */
+__printf(2, 3)
+static inline void super_set_sysfs_name_generic(struct super_block *sb, const char *fmt, ...)
+{
+ va_list args;
+
+ va_start(args, fmt);
+ vsnprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), fmt, args);
+ va_end(args);
+}
+
extern int current_umask(void);
extern void ihold(struct inode * inode);
@@ -2925,6 +2986,17 @@ extern bool path_is_under(const struct path *, const struct path *);
extern char *file_path(struct file *, char *, int);
+/**
+ * is_dot_dotdot - returns true only if @name is "." or ".."
+ * @name: file name to check
+ * @len: length of file name, in bytes
+ */
+static inline bool is_dot_dotdot(const char *name, size_t len)
+{
+ return len && unlikely(name[0] == '.') &&
+ (len == 1 || (len == 2 && name[1] == '.'));
+}
+
#include <linux/err.h>
/* needed for stackable file system support */
@@ -3235,7 +3307,7 @@ extern int simple_write_begin(struct file *file, struct address_space *mapping,
extern const struct address_space_operations ram_aops;
extern int always_delete_dentry(const struct dentry *);
extern struct inode *alloc_anon_inode(struct super_block *);
-extern int simple_nosetlease(struct file *, int, struct file_lock **, void **);
+extern int simple_nosetlease(struct file *, int, struct file_lease **, void **);
extern const struct dentry_operations simple_dentry_operations;
extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
@@ -3257,13 +3329,14 @@ extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos,
const void __user *from, size_t count);
struct offset_ctx {
- struct xarray xa;
- u32 next_offset;
+ struct maple_tree mt;
+ unsigned long next_offset;
};
void simple_offset_init(struct offset_ctx *octx);
int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry);
void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry);
+int simple_offset_empty(struct dentry *dentry);
int simple_offset_rename_exchange(struct inode *old_dir,
struct dentry *old_dentry,
struct inode *new_dir,
@@ -3277,7 +3350,16 @@ extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
extern int generic_check_addressable(unsigned, u64);
-extern void generic_set_encrypted_ci_d_ops(struct dentry *dentry);
+extern void generic_set_sb_d_ops(struct super_block *sb);
+
+static inline bool sb_has_encoding(const struct super_block *sb)
+{
+#if IS_ENABLED(CONFIG_UNICODE)
+ return !!sb->s_encoding;
+#else
+ return false;
+#endif
+}
int may_setattr(struct mnt_idmap *idmap, struct inode *inode,
unsigned int ia_valid);
@@ -3332,6 +3414,8 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
return 0;
if (unlikely(flags & ~RWF_SUPPORTED))
return -EOPNOTSUPP;
+ if (unlikely((flags & RWF_APPEND) && (flags & RWF_NOAPPEND)))
+ return -EINVAL;
if (flags & RWF_NOWAIT) {
if (!(ki->ki_filp->f_mode & FMODE_NOWAIT))
@@ -3342,6 +3426,12 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
if (flags & RWF_SYNC)
kiocb_flags |= IOCB_DSYNC;
+ if ((flags & RWF_NOAPPEND) && (ki->ki_flags & IOCB_APPEND)) {
+ if (IS_APPEND(file_inode(ki->ki_filp)))
+ return -EPERM;
+ ki->ki_flags &= ~IOCB_APPEND;
+ }
+
ki->ki_flags |= kiocb_flags;
return 0;
}
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 12f9e455d569..772f822dc6b8 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -192,6 +192,8 @@ struct fscrypt_operations {
unsigned int *num_devs);
};
+int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags);
+
static inline struct fscrypt_inode_info *
fscrypt_get_inode_info(const struct inode *inode)
{
@@ -221,15 +223,29 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode)
}
/*
- * When d_splice_alias() moves a directory's no-key alias to its plaintext alias
- * as a result of the encryption key being added, DCACHE_NOKEY_NAME must be
- * cleared. Note that we don't have to support arbitrary moves of this flag
- * because fscrypt doesn't allow no-key names to be the source or target of a
- * rename().
+ * When d_splice_alias() moves a directory's no-key alias to its
+ * plaintext alias as a result of the encryption key being added,
+ * DCACHE_NOKEY_NAME must be cleared and there might be an opportunity
+ * to disable d_revalidate. Note that we don't have to support the
+ * inverse operation because fscrypt doesn't allow no-key names to be
+ * the source or target of a rename().
*/
static inline void fscrypt_handle_d_move(struct dentry *dentry)
{
- dentry->d_flags &= ~DCACHE_NOKEY_NAME;
+ /*
+ * VFS calls fscrypt_handle_d_move even for non-fscrypt
+ * filesystems.
+ */
+ if (dentry->d_flags & DCACHE_NOKEY_NAME) {
+ dentry->d_flags &= ~DCACHE_NOKEY_NAME;
+
+ /*
+ * Other filesystem features might be handling dentry
+ * revalidation, in which case it cannot be disabled.
+ */
+ if (dentry->d_op->d_revalidate == fscrypt_d_revalidate)
+ dentry->d_flags &= ~DCACHE_OP_REVALIDATE;
+ }
}
/**
@@ -261,6 +277,35 @@ static inline bool fscrypt_is_nokey_name(const struct dentry *dentry)
return dentry->d_flags & DCACHE_NOKEY_NAME;
}
+static inline void fscrypt_prepare_dentry(struct dentry *dentry,
+ bool is_nokey_name)
+{
+ /*
+ * This code tries to only take ->d_lock when necessary to write
+ * to ->d_flags. We shouldn't be peeking on d_flags for
+ * DCACHE_OP_REVALIDATE unlocked, but in the unlikely case
+ * there is a race, the worst it can happen is that we fail to
+ * unset DCACHE_OP_REVALIDATE and pay the cost of an extra
+ * d_revalidate.
+ */
+ if (is_nokey_name) {
+ spin_lock(&dentry->d_lock);
+ dentry->d_flags |= DCACHE_NOKEY_NAME;
+ spin_unlock(&dentry->d_lock);
+ } else if (dentry->d_flags & DCACHE_OP_REVALIDATE &&
+ dentry->d_op->d_revalidate == fscrypt_d_revalidate) {
+ /*
+ * Unencrypted dentries and encrypted dentries where the
+ * key is available are always valid from fscrypt
+ * perspective. Avoid the cost of calling
+ * fscrypt_d_revalidate unnecessarily.
+ */
+ spin_lock(&dentry->d_lock);
+ dentry->d_flags &= ~DCACHE_OP_REVALIDATE;
+ spin_unlock(&dentry->d_lock);
+ }
+}
+
/* crypto.c */
void fscrypt_enqueue_decrypt_work(struct work_struct *);
@@ -368,7 +413,6 @@ int fscrypt_fname_disk_to_usr(const struct inode *inode,
bool fscrypt_match_name(const struct fscrypt_name *fname,
const u8 *de_name, u32 de_name_len);
u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name);
-int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags);
/* bio.c */
bool fscrypt_decrypt_bio(struct bio *bio);
@@ -425,6 +469,11 @@ static inline bool fscrypt_is_nokey_name(const struct dentry *dentry)
return false;
}
+static inline void fscrypt_prepare_dentry(struct dentry *dentry,
+ bool is_nokey_name)
+{
+}
+
/* crypto.c */
static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work)
{
@@ -982,6 +1031,9 @@ static inline int fscrypt_prepare_lookup(struct inode *dir,
fname->usr_fname = &dentry->d_name;
fname->disk_name.name = (unsigned char *)dentry->d_name.name;
fname->disk_name.len = dentry->d_name.len;
+
+ fscrypt_prepare_dentry(dentry, false);
+
return 0;
}
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index de292a007138..e2a916cf29c4 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -353,6 +353,15 @@ static inline bool gfp_has_io_fs(gfp_t gfp)
return (gfp & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS);
}
+/*
+ * Check if the gfp flags allow compaction - GFP_NOIO is a really
+ * tricky context because the migration might require IO.
+ */
+static inline bool gfp_compaction_allowed(gfp_t gfp_mask)
+{
+ return IS_ENABLED(CONFIG_COMPACTION) && (gfp_mask & __GFP_IO);
+}
+
extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma);
#ifdef CONFIG_CONTIG_ALLOC
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 2b00faf98017..6ef0557b4bff 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -164,8 +164,28 @@ struct hv_ring_buffer {
u8 buffer[];
} __packed;
+
+/*
+ * If the requested ring buffer size is at least 8 times the size of the
+ * header, steal space from the ring buffer for the header. Otherwise, add
+ * space for the header so that is doesn't take too much of the ring buffer
+ * space.
+ *
+ * The factor of 8 is somewhat arbitrary. The goal is to prevent adding a
+ * relatively small header (4 Kbytes on x86) to a large-ish power-of-2 ring
+ * buffer size (such as 128 Kbytes) and so end up making a nearly twice as
+ * large allocation that will be almost half wasted. As a contrasting example,
+ * on ARM64 with 64 Kbyte page size, we don't want to take 64 Kbytes for the
+ * header from a 128 Kbyte allocation, leaving only 64 Kbytes for the ring.
+ * In this latter case, we must add 64 Kbytes for the header and not worry
+ * about what's wasted.
+ */
+#define VMBUS_HEADER_ADJ(payload_sz) \
+ ((payload_sz) >= 8 * sizeof(struct hv_ring_buffer) ? \
+ 0 : sizeof(struct hv_ring_buffer))
+
/* Calculate the proper size of a ringbuffer, it must be page-aligned */
-#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(sizeof(struct hv_ring_buffer) + \
+#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(VMBUS_HEADER_ADJ(payload_sz) + \
(payload_sz))
struct hv_ring_buffer_info {
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 854ad67a5f70..e24893625085 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -2,6 +2,7 @@
#define IO_URING_TYPES_H
#include <linux/blkdev.h>
+#include <linux/hashtable.h>
#include <linux/task_work.h>
#include <linux/bitmap.h>
#include <linux/llist.h>
@@ -240,12 +241,14 @@ struct io_ring_ctx {
unsigned int poll_activated: 1;
unsigned int drain_disabled: 1;
unsigned int compat: 1;
+ unsigned int iowq_limits_set : 1;
struct task_struct *submitter_task;
struct io_rings *rings;
struct percpu_ref refs;
enum task_work_notify_mode notify_method;
+ unsigned sq_thread_idle;
} ____cacheline_aligned_in_smp;
/* submission data */
@@ -274,10 +277,20 @@ struct io_ring_ctx {
*/
struct io_rsrc_node *rsrc_node;
atomic_t cancel_seq;
+
+ /*
+ * ->iopoll_list is protected by the ctx->uring_lock for
+ * io_uring instances that don't use IORING_SETUP_SQPOLL.
+ * For SQPOLL, only the single threaded io_sq_thread() will
+ * manipulate the list, hence no extra locking is needed there.
+ */
+ bool poll_multi_queue;
+ struct io_wq_work_list iopoll_list;
+
struct io_file_table file_table;
+ struct io_mapped_ubuf **user_bufs;
unsigned nr_user_files;
unsigned nr_user_bufs;
- struct io_mapped_ubuf **user_bufs;
struct io_submit_state submit_state;
@@ -289,15 +302,6 @@ struct io_ring_ctx {
struct io_alloc_cache netmsg_cache;
/*
- * ->iopoll_list is protected by the ctx->uring_lock for
- * io_uring instances that don't use IORING_SETUP_SQPOLL.
- * For SQPOLL, only the single threaded io_sq_thread() will
- * manipulate the list, hence no extra locking is needed there.
- */
- struct io_wq_work_list iopoll_list;
- bool poll_multi_queue;
-
- /*
* Any cancelable uring_cmd is added to this list in
* ->uring_cmd() by io_uring_cmd_insert_cancelable()
*/
@@ -343,8 +347,8 @@ struct io_ring_ctx {
spinlock_t completion_lock;
/* IRQ completion list, under ->completion_lock */
- struct io_wq_work_list locked_free_list;
unsigned int locked_free_nr;
+ struct io_wq_work_list locked_free_list;
struct list_head io_buffers_comp;
struct list_head cq_overflow_list;
@@ -366,9 +370,6 @@ struct io_ring_ctx {
unsigned int file_alloc_start;
unsigned int file_alloc_end;
- struct xarray personalities;
- u32 pers_next;
-
struct list_head io_buffers_cache;
/* deferred free list, protected by ->uring_lock */
@@ -389,6 +390,9 @@ struct io_ring_ctx {
struct wait_queue_head rsrc_quiesce_wq;
unsigned rsrc_quiesce;
+ u32 pers_next;
+ struct xarray personalities;
+
/* hashed buffered write serialization */
struct io_wq_hash *hash_map;
@@ -405,11 +409,22 @@ struct io_ring_ctx {
/* io-wq management, e.g. thread count */
u32 iowq_limits[2];
- bool iowq_limits_set;
struct callback_head poll_wq_task_work;
struct list_head defer_list;
- unsigned sq_thread_idle;
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+ struct list_head napi_list; /* track busy poll napi_id */
+ spinlock_t napi_lock; /* napi_list lock */
+
+ /* napi busy poll default timeout */
+ unsigned int napi_busy_poll_to;
+ bool napi_prefer_busy_poll;
+ bool napi_enabled;
+
+ DECLARE_HASHTABLE(napi_ht, 4);
+#endif
+
/* protected by ->completion_lock */
unsigned evfd_last_cq_tail;
@@ -455,7 +470,6 @@ enum {
REQ_F_SKIP_LINK_CQES_BIT,
REQ_F_SINGLE_POLL_BIT,
REQ_F_DOUBLE_POLL_BIT,
- REQ_F_PARTIAL_IO_BIT,
REQ_F_APOLL_MULTISHOT_BIT,
REQ_F_CLEAR_POLLIN_BIT,
REQ_F_HASH_LOCKED_BIT,
@@ -463,75 +477,88 @@ enum {
REQ_F_SUPPORT_NOWAIT_BIT,
REQ_F_ISREG_BIT,
REQ_F_POLL_NO_LAZY_BIT,
+ REQ_F_CANCEL_SEQ_BIT,
+ REQ_F_CAN_POLL_BIT,
+ REQ_F_BL_EMPTY_BIT,
+ REQ_F_BL_NO_RECYCLE_BIT,
/* not a real bit, just to check we're not overflowing the space */
__REQ_F_LAST_BIT,
};
+typedef u64 __bitwise io_req_flags_t;
+#define IO_REQ_FLAG(bitno) ((__force io_req_flags_t) BIT_ULL((bitno)))
+
enum {
/* ctx owns file */
- REQ_F_FIXED_FILE = BIT(REQ_F_FIXED_FILE_BIT),
+ REQ_F_FIXED_FILE = IO_REQ_FLAG(REQ_F_FIXED_FILE_BIT),
/* drain existing IO first */
- REQ_F_IO_DRAIN = BIT(REQ_F_IO_DRAIN_BIT),
+ REQ_F_IO_DRAIN = IO_REQ_FLAG(REQ_F_IO_DRAIN_BIT),
/* linked sqes */
- REQ_F_LINK = BIT(REQ_F_LINK_BIT),
+ REQ_F_LINK = IO_REQ_FLAG(REQ_F_LINK_BIT),
/* doesn't sever on completion < 0 */
- REQ_F_HARDLINK = BIT(REQ_F_HARDLINK_BIT),
+ REQ_F_HARDLINK = IO_REQ_FLAG(REQ_F_HARDLINK_BIT),
/* IOSQE_ASYNC */
- REQ_F_FORCE_ASYNC = BIT(REQ_F_FORCE_ASYNC_BIT),
+ REQ_F_FORCE_ASYNC = IO_REQ_FLAG(REQ_F_FORCE_ASYNC_BIT),
/* IOSQE_BUFFER_SELECT */
- REQ_F_BUFFER_SELECT = BIT(REQ_F_BUFFER_SELECT_BIT),
+ REQ_F_BUFFER_SELECT = IO_REQ_FLAG(REQ_F_BUFFER_SELECT_BIT),
/* IOSQE_CQE_SKIP_SUCCESS */
- REQ_F_CQE_SKIP = BIT(REQ_F_CQE_SKIP_BIT),
+ REQ_F_CQE_SKIP = IO_REQ_FLAG(REQ_F_CQE_SKIP_BIT),
/* fail rest of links */
- REQ_F_FAIL = BIT(REQ_F_FAIL_BIT),
+ REQ_F_FAIL = IO_REQ_FLAG(REQ_F_FAIL_BIT),
/* on inflight list, should be cancelled and waited on exit reliably */
- REQ_F_INFLIGHT = BIT(REQ_F_INFLIGHT_BIT),
+ REQ_F_INFLIGHT = IO_REQ_FLAG(REQ_F_INFLIGHT_BIT),
/* read/write uses file position */
- REQ_F_CUR_POS = BIT(REQ_F_CUR_POS_BIT),
+ REQ_F_CUR_POS = IO_REQ_FLAG(REQ_F_CUR_POS_BIT),
/* must not punt to workers */
- REQ_F_NOWAIT = BIT(REQ_F_NOWAIT_BIT),
+ REQ_F_NOWAIT = IO_REQ_FLAG(REQ_F_NOWAIT_BIT),
/* has or had linked timeout */
- REQ_F_LINK_TIMEOUT = BIT(REQ_F_LINK_TIMEOUT_BIT),
+ REQ_F_LINK_TIMEOUT = IO_REQ_FLAG(REQ_F_LINK_TIMEOUT_BIT),
/* needs cleanup */
- REQ_F_NEED_CLEANUP = BIT(REQ_F_NEED_CLEANUP_BIT),
+ REQ_F_NEED_CLEANUP = IO_REQ_FLAG(REQ_F_NEED_CLEANUP_BIT),
/* already went through poll handler */
- REQ_F_POLLED = BIT(REQ_F_POLLED_BIT),
+ REQ_F_POLLED = IO_REQ_FLAG(REQ_F_POLLED_BIT),
/* buffer already selected */
- REQ_F_BUFFER_SELECTED = BIT(REQ_F_BUFFER_SELECTED_BIT),
+ REQ_F_BUFFER_SELECTED = IO_REQ_FLAG(REQ_F_BUFFER_SELECTED_BIT),
/* buffer selected from ring, needs commit */
- REQ_F_BUFFER_RING = BIT(REQ_F_BUFFER_RING_BIT),
+ REQ_F_BUFFER_RING = IO_REQ_FLAG(REQ_F_BUFFER_RING_BIT),
/* caller should reissue async */
- REQ_F_REISSUE = BIT(REQ_F_REISSUE_BIT),
+ REQ_F_REISSUE = IO_REQ_FLAG(REQ_F_REISSUE_BIT),
/* supports async reads/writes */
- REQ_F_SUPPORT_NOWAIT = BIT(REQ_F_SUPPORT_NOWAIT_BIT),
+ REQ_F_SUPPORT_NOWAIT = IO_REQ_FLAG(REQ_F_SUPPORT_NOWAIT_BIT),
/* regular file */
- REQ_F_ISREG = BIT(REQ_F_ISREG_BIT),
+ REQ_F_ISREG = IO_REQ_FLAG(REQ_F_ISREG_BIT),
/* has creds assigned */
- REQ_F_CREDS = BIT(REQ_F_CREDS_BIT),
+ REQ_F_CREDS = IO_REQ_FLAG(REQ_F_CREDS_BIT),
/* skip refcounting if not set */
- REQ_F_REFCOUNT = BIT(REQ_F_REFCOUNT_BIT),
+ REQ_F_REFCOUNT = IO_REQ_FLAG(REQ_F_REFCOUNT_BIT),
/* there is a linked timeout that has to be armed */
- REQ_F_ARM_LTIMEOUT = BIT(REQ_F_ARM_LTIMEOUT_BIT),
+ REQ_F_ARM_LTIMEOUT = IO_REQ_FLAG(REQ_F_ARM_LTIMEOUT_BIT),
/* ->async_data allocated */
- REQ_F_ASYNC_DATA = BIT(REQ_F_ASYNC_DATA_BIT),
+ REQ_F_ASYNC_DATA = IO_REQ_FLAG(REQ_F_ASYNC_DATA_BIT),
/* don't post CQEs while failing linked requests */
- REQ_F_SKIP_LINK_CQES = BIT(REQ_F_SKIP_LINK_CQES_BIT),
+ REQ_F_SKIP_LINK_CQES = IO_REQ_FLAG(REQ_F_SKIP_LINK_CQES_BIT),
/* single poll may be active */
- REQ_F_SINGLE_POLL = BIT(REQ_F_SINGLE_POLL_BIT),
+ REQ_F_SINGLE_POLL = IO_REQ_FLAG(REQ_F_SINGLE_POLL_BIT),
/* double poll may active */
- REQ_F_DOUBLE_POLL = BIT(REQ_F_DOUBLE_POLL_BIT),
- /* request has already done partial IO */
- REQ_F_PARTIAL_IO = BIT(REQ_F_PARTIAL_IO_BIT),
+ REQ_F_DOUBLE_POLL = IO_REQ_FLAG(REQ_F_DOUBLE_POLL_BIT),
/* fast poll multishot mode */
- REQ_F_APOLL_MULTISHOT = BIT(REQ_F_APOLL_MULTISHOT_BIT),
+ REQ_F_APOLL_MULTISHOT = IO_REQ_FLAG(REQ_F_APOLL_MULTISHOT_BIT),
/* recvmsg special flag, clear EPOLLIN */
- REQ_F_CLEAR_POLLIN = BIT(REQ_F_CLEAR_POLLIN_BIT),
+ REQ_F_CLEAR_POLLIN = IO_REQ_FLAG(REQ_F_CLEAR_POLLIN_BIT),
/* hashed into ->cancel_hash_locked, protected by ->uring_lock */
- REQ_F_HASH_LOCKED = BIT(REQ_F_HASH_LOCKED_BIT),
+ REQ_F_HASH_LOCKED = IO_REQ_FLAG(REQ_F_HASH_LOCKED_BIT),
/* don't use lazy poll wake for this request */
- REQ_F_POLL_NO_LAZY = BIT(REQ_F_POLL_NO_LAZY_BIT),
+ REQ_F_POLL_NO_LAZY = IO_REQ_FLAG(REQ_F_POLL_NO_LAZY_BIT),
+ /* cancel sequence is set and valid */
+ REQ_F_CANCEL_SEQ = IO_REQ_FLAG(REQ_F_CANCEL_SEQ_BIT),
+ /* file is pollable */
+ REQ_F_CAN_POLL = IO_REQ_FLAG(REQ_F_CAN_POLL_BIT),
+ /* buffer list was empty after selection of buffer */
+ REQ_F_BL_EMPTY = IO_REQ_FLAG(REQ_F_BL_EMPTY_BIT),
+ /* don't recycle provided buffers for this request */
+ REQ_F_BL_NO_RECYCLE = IO_REQ_FLAG(REQ_F_BL_NO_RECYCLE_BIT),
};
typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts);
@@ -592,15 +619,17 @@ struct io_kiocb {
* and after selection it points to the buffer ID itself.
*/
u16 buf_index;
- unsigned int flags;
+
+ unsigned nr_tw;
+
+ /* REQ_F_* flags */
+ io_req_flags_t flags;
struct io_cqe cqe;
struct io_ring_ctx *ctx;
struct task_struct *task;
- struct io_rsrc_node *rsrc_node;
-
union {
/* store used ubuf, so we can prevent reloading */
struct io_mapped_ubuf *imu;
@@ -621,10 +650,12 @@ struct io_kiocb {
/* cache ->apoll->events */
__poll_t apoll_events;
};
+
+ struct io_rsrc_node *rsrc_node;
+
atomic_t refs;
atomic_t poll_refs;
struct io_task_work io_task_work;
- unsigned nr_tw;
/* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */
struct hlist_node hash_node;
/* internal polling, see IORING_FEAT_FAST_POLL */
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 96dd0acbba44..6fc1c858013d 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -293,22 +293,32 @@ struct iomap_ioend {
struct list_head io_list; /* next ioend in chain */
u16 io_type;
u16 io_flags; /* IOMAP_F_* */
- u32 io_folios; /* folios added to ioend */
struct inode *io_inode; /* file being written to */
size_t io_size; /* size of the extent */
loff_t io_offset; /* offset in the file */
sector_t io_sector; /* start sector of ioend */
- struct bio *io_bio; /* bio being built */
- struct bio io_inline_bio; /* MUST BE LAST! */
+ struct bio io_bio; /* MUST BE LAST! */
};
+static inline struct iomap_ioend *iomap_ioend_from_bio(struct bio *bio)
+{
+ return container_of(bio, struct iomap_ioend, io_bio);
+}
+
struct iomap_writeback_ops {
/*
* Required, maps the blocks so that writeback can be performed on
* the range starting at offset.
+ *
+ * Can return arbitrarily large regions, but we need to call into it at
+ * least once per folio to allow the file systems to synchronize with
+ * the write path that could be invalidating mappings.
+ *
+ * An existing mapping from a previous call to this method can be reused
+ * by the file system if it is still valid.
*/
int (*map_blocks)(struct iomap_writepage_ctx *wpc, struct inode *inode,
- loff_t offset);
+ loff_t offset, unsigned len);
/*
* Optional, allows the file systems to perform actions just before
@@ -329,6 +339,7 @@ struct iomap_writepage_ctx {
struct iomap iomap;
struct iomap_ioend *ioend;
const struct iomap_writeback_ops *ops;
+ u32 nr_folios; /* folios added to the ioend */
};
void iomap_finish_ioends(struct iomap_ioend *ioend, int error);
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 1ea2a820e1eb..5e27cb3a3be9 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -892,11 +892,14 @@ struct iommu_fwspec {
struct iommu_sva {
struct device *dev;
struct iommu_domain *domain;
+ struct list_head handle_item;
+ refcount_t users;
};
struct iommu_mm_data {
u32 pasid;
struct list_head sva_domains;
+ struct list_head sva_handles;
};
int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode,
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 90081afa10ce..97baa937ab5b 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -179,7 +179,7 @@ struct irq_common_data {
struct irq_data {
u32 mask;
unsigned int irq;
- unsigned long hwirq;
+ irq_hw_number_t hwirq;
struct irq_common_data *common;
struct irq_chip *chip;
struct irq_domain *domain;
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index ee0a82c60508..21ecf582a0fe 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -619,6 +619,23 @@ static inline bool irq_domain_is_msi_device(struct irq_domain *domain)
#endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */
+#ifdef CONFIG_GENERIC_MSI_IRQ
+int msi_device_domain_alloc_wired(struct irq_domain *domain, unsigned int hwirq,
+ unsigned int type);
+void msi_device_domain_free_wired(struct irq_domain *domain, unsigned int virq);
+#else
+static inline int msi_device_domain_alloc_wired(struct irq_domain *domain, unsigned int hwirq,
+ unsigned int type)
+{
+ WARN_ON_ONCE(1);
+ return -EINVAL;
+}
+static inline void msi_device_domain_free_wired(struct irq_domain *domain, unsigned int virq)
+{
+ WARN_ON_ONCE(1);
+}
+#endif
+
#else /* CONFIG_IRQ_DOMAIN */
static inline void irq_dispose_mapping(unsigned int virq) { }
static inline struct irq_domain *irq_find_matching_fwnode(
diff --git a/include/linux/irqdomain_defs.h b/include/linux/irqdomain_defs.h
index c29921fd8cd1..5c1fe6f1fcde 100644
--- a/include/linux/irqdomain_defs.h
+++ b/include/linux/irqdomain_defs.h
@@ -26,6 +26,8 @@ enum irq_domain_bus_token {
DOMAIN_BUS_DMAR,
DOMAIN_BUS_AMDVI,
DOMAIN_BUS_PCI_DEVICE_IMS,
+ DOMAIN_BUS_DEVICE_MSI,
+ DOMAIN_BUS_WIRED_TO_MSI,
};
#endif /* _LINUX_IRQDOMAIN_DEFS_H */
diff --git a/include/linux/irqhandler.h b/include/linux/irqhandler.h
index c30f454a9518..72dd1eb3a0e7 100644
--- a/include/linux/irqhandler.h
+++ b/include/linux/irqhandler.h
@@ -8,7 +8,7 @@
*/
struct irq_desc;
-struct irq_data;
+
typedef void (*irq_flow_handler_t)(struct irq_desc *desc);
#endif
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 7e7fd25b09b3..179df96b20f8 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2031,6 +2031,32 @@ static inline int mmu_invalidate_retry_gfn(struct kvm *kvm,
return 1;
return 0;
}
+
+/*
+ * This lockless version of the range-based retry check *must* be paired with a
+ * call to the locked version after acquiring mmu_lock, i.e. this is safe to
+ * use only as a pre-check to avoid contending mmu_lock. This version *will*
+ * get false negatives and false positives.
+ */
+static inline bool mmu_invalidate_retry_gfn_unsafe(struct kvm *kvm,
+ unsigned long mmu_seq,
+ gfn_t gfn)
+{
+ /*
+ * Use READ_ONCE() to ensure the in-progress flag and sequence counter
+ * are always read from memory, e.g. so that checking for retry in a
+ * loop won't result in an infinite retry loop. Don't force loads for
+ * start+end, as the key to avoiding infinite retry loops is observing
+ * the 1=>0 transition of in-progress, i.e. getting false negatives
+ * due to stale start+end values is acceptable.
+ */
+ if (unlikely(READ_ONCE(kvm->mmu_invalidate_in_progress)) &&
+ gfn >= kvm->mmu_invalidate_range_start &&
+ gfn < kvm->mmu_invalidate_range_end)
+ return true;
+
+ return READ_ONCE(kvm->mmu_invalidate_seq) != mmu_seq;
+}
#endif
#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index 9f565416d186..1b95fe31051f 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -375,12 +375,12 @@ static inline int nlm_privileged_requester(const struct svc_rqst *rqstp)
static inline int nlm_compare_locks(const struct file_lock *fl1,
const struct file_lock *fl2)
{
- return file_inode(fl1->fl_file) == file_inode(fl2->fl_file)
- && fl1->fl_pid == fl2->fl_pid
- && fl1->fl_owner == fl2->fl_owner
+ return file_inode(fl1->c.flc_file) == file_inode(fl2->c.flc_file)
+ && fl1->c.flc_pid == fl2->c.flc_pid
+ && fl1->c.flc_owner == fl2->c.flc_owner
&& fl1->fl_start == fl2->fl_start
&& fl1->fl_end == fl2->fl_end
- &&(fl1->fl_type == fl2->fl_type || fl2->fl_type == F_UNLCK);
+ &&(fl1->c.flc_type == fl2->c.flc_type || fl2->c.flc_type == F_UNLCK);
}
extern const struct lock_manager_operations nlmsvc_lock_operations;
diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h
index b60fbcd8cdfa..80cca9426761 100644
--- a/include/linux/lockd/xdr.h
+++ b/include/linux/lockd/xdr.h
@@ -52,7 +52,7 @@ struct nlm_lock {
* FreeBSD uses 16, Apple Mac OS X 10.3 uses 20. Therefore we set it to
* 32 bytes.
*/
-
+
struct nlm_cookie
{
unsigned char data[NLM_MAXCOOKIELEN];
diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h
index b3d63123b945..a53ad4dabd7e 100644
--- a/include/linux/maple_tree.h
+++ b/include/linux/maple_tree.h
@@ -171,6 +171,7 @@ enum maple_type {
#define MT_FLAGS_LOCK_IRQ 0x100
#define MT_FLAGS_LOCK_BH 0x200
#define MT_FLAGS_LOCK_EXTERN 0x300
+#define MT_FLAGS_ALLOC_WRAPPED 0x0800
#define MAPLE_HEIGHT_MAX 31
@@ -319,6 +320,9 @@ int mtree_insert_range(struct maple_tree *mt, unsigned long first,
int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp,
void *entry, unsigned long size, unsigned long min,
unsigned long max, gfp_t gfp);
+int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp,
+ void *entry, unsigned long range_lo, unsigned long range_hi,
+ unsigned long *next, gfp_t gfp);
int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp,
void *entry, unsigned long size, unsigned long min,
unsigned long max, gfp_t gfp);
@@ -499,6 +503,9 @@ void *mas_find_range(struct ma_state *mas, unsigned long max);
void *mas_find_rev(struct ma_state *mas, unsigned long min);
void *mas_find_range_rev(struct ma_state *mas, unsigned long max);
int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp);
+int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp,
+ void *entry, unsigned long range_lo, unsigned long range_hi,
+ unsigned long *next, gfp_t gfp);
bool mas_nomem(struct ma_state *mas, gfp_t gfp);
void mas_pause(struct ma_state *mas);
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index b695f9e946da..e2082240586d 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -121,6 +121,8 @@ int memblock_reserve(phys_addr_t base, phys_addr_t size);
int memblock_physmem_add(phys_addr_t base, phys_addr_t size);
#endif
void memblock_trim_memory(phys_addr_t align);
+unsigned long memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,
+ phys_addr_t base2, phys_addr_t size2);
bool memblock_overlaps_region(struct memblock_type *type,
phys_addr_t base, phys_addr_t size);
bool memblock_validate_numa_coverage(unsigned long threshold_bytes);
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index c726f90ab752..486b7492050c 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1103,7 +1103,7 @@ struct mlx5_ifc_roce_cap_bits {
u8 sw_r_roce_src_udp_port[0x1];
u8 fl_rc_qp_when_roce_disabled[0x1];
u8 fl_rc_qp_when_roce_enabled[0x1];
- u8 reserved_at_7[0x1];
+ u8 roce_cc_general[0x1];
u8 qp_ooo_transmit_default[0x1];
u8 reserved_at_9[0x15];
u8 qp_ts_format[0x2];
@@ -10261,7 +10261,9 @@ struct mlx5_ifc_mcam_access_reg_bits {
u8 regs_63_to_46[0x12];
u8 mrtc[0x1];
- u8 regs_44_to_32[0xd];
+ u8 regs_44_to_41[0x4];
+ u8 mfrl[0x1];
+ u8 regs_39_to_32[0x8];
u8 regs_31_to_10[0x16];
u8 mtmp[0x1];
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index bd53cf4be7bd..f0e55bf3ec8b 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -269,7 +269,10 @@ struct mlx5_wqe_eth_seg {
union {
struct {
__be16 sz;
- u8 start[2];
+ union {
+ u8 start[2];
+ DECLARE_FLEX_ARRAY(u8, data);
+ };
} inline_hdr;
struct {
__be16 type;
diff --git a/include/linux/msi.h b/include/linux/msi.h
index ddace8c34dcf..26d07e23052e 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -412,6 +412,7 @@ bool arch_restore_msi_irqs(struct pci_dev *dev);
struct irq_domain;
struct irq_domain_ops;
struct irq_chip;
+struct irq_fwspec;
struct device_node;
struct fwnode_handle;
struct msi_domain_info;
@@ -431,6 +432,8 @@ struct msi_domain_info;
* function.
* @msi_post_free: Optional function which is invoked after freeing
* all interrupts.
+ * @msi_translate: Optional translate callback to support the odd wire to
+ * MSI bridges, e.g. MBIGEN
*
* @get_hwirq, @msi_init and @msi_free are callbacks used by the underlying
* irqdomain.
@@ -468,6 +471,8 @@ struct msi_domain_ops {
struct device *dev);
void (*msi_post_free)(struct irq_domain *domain,
struct device *dev);
+ int (*msi_translate)(struct irq_domain *domain, struct irq_fwspec *fwspec,
+ irq_hw_number_t *hwirq, unsigned int *type);
};
/**
@@ -547,6 +552,10 @@ enum {
MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS = (1 << 5),
/* Free MSI descriptors */
MSI_FLAG_FREE_MSI_DESCS = (1 << 6),
+ /* Use dev->fwnode for MSI device domain creation */
+ MSI_FLAG_USE_DEV_FWNODE = (1 << 7),
+ /* Set parent->dev into domain->pm_dev on device domain creation */
+ MSI_FLAG_PARENT_PM_DEV = (1 << 8),
/* Mask for the generic functionality */
MSI_GENERIC_FLAGS_MASK = GENMASK(15, 0),
@@ -572,6 +581,11 @@ enum {
* struct msi_parent_ops - MSI parent domain callbacks and configuration info
*
* @supported_flags: Required: The supported MSI flags of the parent domain
+ * @required_flags: Optional: The required MSI flags of the parent MSI domain
+ * @bus_select_token: Optional: The bus token of the real parent domain for
+ * irq_domain::select()
+ * @bus_select_mask: Optional: A mask of supported BUS_DOMAINs for
+ * irq_domain::select()
* @prefix: Optional: Prefix for the domain and chip name
* @init_dev_msi_info: Required: Callback for MSI parent domains to setup parent
* domain specific domain flags, domain ops and interrupt chip
@@ -579,6 +593,9 @@ enum {
*/
struct msi_parent_ops {
u32 supported_flags;
+ u32 required_flags;
+ u32 bus_select_token;
+ u32 bus_select_mask;
const char *prefix;
bool (*init_dev_msi_info)(struct device *dev, struct irq_domain *domain,
struct irq_domain *msi_parent_domain,
@@ -627,9 +644,6 @@ struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain);
struct irq_domain *platform_msi_create_irq_domain(struct fwnode_handle *fwnode,
struct msi_domain_info *info,
struct irq_domain *parent);
-int platform_msi_domain_alloc_irqs(struct device *dev, unsigned int nvec,
- irq_write_msi_msg_t write_msi_msg);
-void platform_msi_domain_free_irqs(struct device *dev);
/* When an MSI domain is used as an intermediate domain */
int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev,
@@ -656,6 +670,10 @@ int platform_msi_device_domain_alloc(struct irq_domain *domain, unsigned int vir
void platform_msi_device_domain_free(struct irq_domain *domain, unsigned int virq,
unsigned int nvec);
void *platform_msi_get_host_data(struct irq_domain *domain);
+/* Per device platform MSI */
+int platform_device_msi_init_and_alloc_irqs(struct device *dev, unsigned int nvec,
+ irq_write_msi_msg_t write_msi_msg);
+void platform_device_msi_free_irqs_all(struct device *dev);
bool msi_device_has_isolated_msi(struct device *dev);
#else /* CONFIG_GENERIC_MSI_IRQ */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ef7bfbb98497..78a09af89e39 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -79,8 +79,6 @@ struct xdp_buff;
struct xdp_frame;
struct xdp_metadata_ops;
struct xdp_md;
-/* DPLL specific */
-struct dpll_pin;
typedef u32 xdp_features_t;
@@ -2469,7 +2467,7 @@ struct net_device {
struct devlink_port *devlink_port;
#if IS_ENABLED(CONFIG_DPLL)
- struct dpll_pin *dpll_pin;
+ struct dpll_pin __rcu *dpll_pin;
#endif
#if IS_ENABLED(CONFIG_PAGE_POOL)
/** @page_pools: page pools created for this netdevice */
@@ -3499,6 +3497,16 @@ static inline void netdev_queue_set_dql_min_limit(struct netdev_queue *dev_queue
#endif
}
+static inline int netdev_queue_dql_avail(const struct netdev_queue *txq)
+{
+#ifdef CONFIG_BQL
+ /* Non-BQL migrated drivers will return 0, too. */
+ return dql_avail(&txq->dql);
+#else
+ return 0;
+#endif
+}
+
/**
* netdev_txq_bql_enqueue_prefetchw - prefetch bql data for write
* @dev_queue: pointer to transmit queue
@@ -4032,17 +4040,6 @@ int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name);
int dev_get_port_parent_id(struct net_device *dev,
struct netdev_phys_item_id *ppid, bool recurse);
bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b);
-void netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin);
-void netdev_dpll_pin_clear(struct net_device *dev);
-
-static inline struct dpll_pin *netdev_dpll_pin(const struct net_device *dev)
-{
-#if IS_ENABLED(CONFIG_DPLL)
- return dev->dpll_pin;
-#else
- return NULL;
-#endif
-}
struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again);
struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 80900d910992..ce660d51549b 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -474,6 +474,7 @@ struct nf_ct_hook {
const struct sk_buff *);
void (*attach)(struct sk_buff *nskb, const struct sk_buff *skb);
void (*set_closing)(struct nf_conntrack *nfct);
+ int (*confirm)(struct sk_buff *skb);
};
extern const struct nf_ct_hook __rcu *nf_ct_hook;
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index cd797e00fe35..92de074e63b9 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -124,6 +124,7 @@ struct nfs_client {
char cl_ipaddr[48];
struct net *cl_net;
struct list_head pending_cb_stateids;
+ struct rcu_head rcu;
};
/*
@@ -265,6 +266,7 @@ struct nfs_server {
const struct cred *cred;
bool has_sec_mnt_opts;
struct kobject kobj;
+ struct rcu_head rcu;
};
/* Server capabilities */
diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h
index 0f1d024bd958..7d22ea50b098 100644
--- a/include/linux/ns_common.h
+++ b/include/linux/ns_common.h
@@ -7,7 +7,7 @@
struct proc_ns_operations;
struct ns_common {
- atomic_long_t stashed;
+ struct dentry *stashed;
const struct proc_ns_operations *ops;
unsigned int inum;
refcount_t count;
diff --git a/include/linux/nvme-rdma.h b/include/linux/nvme-rdma.h
index 4dd7e6fe92fb..eb2f04d636c8 100644
--- a/include/linux/nvme-rdma.h
+++ b/include/linux/nvme-rdma.h
@@ -6,7 +6,11 @@
#ifndef _LINUX_NVME_RDMA_H
#define _LINUX_NVME_RDMA_H
-#define NVME_RDMA_MAX_QUEUE_SIZE 128
+#define NVME_RDMA_IP_PORT 4420
+
+#define NVME_RDMA_MAX_QUEUE_SIZE 256
+#define NVME_RDMA_MAX_METADATA_QUEUE_SIZE 128
+#define NVME_RDMA_DEFAULT_QUEUE_SIZE 128
enum nvme_rdma_cm_fmt {
NVME_RDMA_CM_FMT_1_0 = 0x0,
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 3ef4053ea950..425573202295 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -23,8 +23,6 @@
#define NVME_DISC_SUBSYS_NAME "nqn.2014-08.org.nvmexpress.discovery"
-#define NVME_RDMA_IP_PORT 4420
-
#define NVME_NSID_ALL 0xffffffff
enum nvme_subsys_type {
diff --git a/include/linux/pid.h b/include/linux/pid.h
index 395cacce1179..c79a0efd0258 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -55,6 +55,10 @@ struct pid
refcount_t count;
unsigned int level;
spinlock_t lock;
+#ifdef CONFIG_FS_PID
+ struct dentry *stashed;
+ unsigned long ino;
+#endif
/* lists of tasks that use this pid */
struct hlist_head tasks[PIDTYPE_MAX];
struct hlist_head inodes;
@@ -66,15 +70,13 @@ struct pid
extern struct pid init_struct_pid;
-extern const struct file_operations pidfd_fops;
-
struct file;
-extern struct pid *pidfd_pid(const struct file *file);
+struct pid *pidfd_pid(const struct file *file);
struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags);
struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags);
-int pidfd_create(struct pid *pid, unsigned int flags);
int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret);
+void do_notify_pidfd(struct task_struct *task);
static inline struct pid *get_pid(struct pid *pid)
{
diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h
new file mode 100644
index 000000000000..40dd325a32a6
--- /dev/null
+++ b/include/linux/pidfs.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_PID_FS_H
+#define _LINUX_PID_FS_H
+
+struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags);
+void __init pidfs_init(void);
+bool is_pidfs_sb(const struct super_block *sb);
+
+#endif /* _LINUX_PID_FS_H */
diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h
index 79594aeb160d..2f1b952d596a 100644
--- a/include/linux/pktcdvd.h
+++ b/include/linux/pktcdvd.h
@@ -154,9 +154,9 @@ struct packet_stacked_data
struct pktcdvd_device
{
- struct bdev_handle *bdev_handle; /* dev attached */
+ struct file *bdev_file; /* dev attached */
/* handle acquired for bdev during pkt_open_dev() */
- struct bdev_handle *open_bdev_handle;
+ struct file *f_open_bdev;
dev_t pkt_dev; /* our dev */
struct packet_settings settings;
struct packet_stats stats;
diff --git a/include/linux/poison.h b/include/linux/poison.h
index 27a7dad17eef..1f0ee2459f2a 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -92,4 +92,7 @@
/********** VFS **********/
#define VFS_PTR_POISON ((void *)(0xF5 + POISON_POINTER_DELTA))
+/********** lib/stackdepot.c **********/
+#define STACK_DEPOT_POISON ((void *)(0xD390 + POISON_POINTER_DELTA))
+
#endif
diff --git a/include/linux/poll.h b/include/linux/poll.h
index a9e0e1c2d1f2..d1ea4f3714a8 100644
--- a/include/linux/poll.h
+++ b/include/linux/poll.h
@@ -14,11 +14,7 @@
/* ~832 bytes of stack space used max in sys_select/sys_poll before allocating
additional memory. */
-#ifdef __clang__
-#define MAX_STACK_ALLOC 768
-#else
#define MAX_STACK_ALLOC 832
-#endif
#define FRONTEND_STACK_ALLOC 256
#define SELECT_STACK_ALLOC FRONTEND_STACK_ALLOC
#define POLL_STACK_ALLOC FRONTEND_STACK_ALLOC
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index de407e7c3b55..0b2a89854440 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -65,6 +65,7 @@ struct proc_fs_info {
kgid_t pid_gid;
enum proc_hidepid hide_pid;
enum proc_pidonly pidonly;
+ struct rcu_head rcu;
};
static inline struct proc_fs_info *proc_sb_info(struct super_block *sb)
diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h
index 49539bc416ce..5ea470eb4d76 100644
--- a/include/linux/proc_ns.h
+++ b/include/linux/proc_ns.h
@@ -66,7 +66,7 @@ static inline void proc_free_inum(unsigned int inum) {}
static inline int ns_alloc_inum(struct ns_common *ns)
{
- atomic_long_set(&ns->stashed, 0);
+ WRITE_ONCE(ns->stashed, NULL);
return proc_alloc_inum(&ns->inum);
}
diff --git a/include/linux/ptp_kvm.h b/include/linux/ptp_kvm.h
index 746fd67c3480..e8c74fa3f455 100644
--- a/include/linux/ptp_kvm.h
+++ b/include/linux/ptp_kvm.h
@@ -8,15 +8,15 @@
#ifndef _PTP_KVM_H_
#define _PTP_KVM_H_
+#include <linux/clocksource_ids.h>
#include <linux/types.h>
struct timespec64;
-struct clocksource;
int kvm_arch_ptp_init(void);
void kvm_arch_ptp_exit(void);
int kvm_arch_ptp_get_clock(struct timespec64 *ts);
int kvm_arch_ptp_get_crosststamp(u64 *cycle,
- struct timespec64 *tspec, struct clocksource **cs);
+ struct timespec64 *tspec, enum clocksource_ids *cs_id);
#endif /* _PTP_KVM_H_ */
diff --git a/include/linux/rcu_sync.h b/include/linux/rcu_sync.h
index 0027d4c8087c..3860dbb9107a 100644
--- a/include/linux/rcu_sync.h
+++ b/include/linux/rcu_sync.h
@@ -37,7 +37,6 @@ static inline bool rcu_sync_is_idle(struct rcu_sync *rsp)
}
extern void rcu_sync_init(struct rcu_sync *);
-extern void rcu_sync_enter_start(struct rcu_sync *);
extern void rcu_sync_enter(struct rcu_sync *);
extern void rcu_sync_exit(struct rcu_sync *);
extern void rcu_sync_dtor(struct rcu_sync *);
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 0746b1b0b663..16f519914415 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -184,9 +184,9 @@ void rcu_tasks_trace_qs_blkd(struct task_struct *t);
do { \
int ___rttq_nesting = READ_ONCE((t)->trc_reader_nesting); \
\
- if (likely(!READ_ONCE((t)->trc_reader_special.b.need_qs)) && \
+ if (unlikely(READ_ONCE((t)->trc_reader_special.b.need_qs) == TRC_NEED_QS) && \
likely(!___rttq_nesting)) { \
- rcu_trc_cmpxchg_need_qs((t), 0, TRC_NEED_QS_CHECKED); \
+ rcu_trc_cmpxchg_need_qs((t), TRC_NEED_QS, TRC_NEED_QS_CHECKED); \
} else if (___rttq_nesting && ___rttq_nesting != INT_MIN && \
!READ_ONCE((t)->trc_reader_special.b.blocked)) { \
rcu_tasks_trace_qs_blkd(t); \
diff --git a/include/linux/rw_hint.h b/include/linux/rw_hint.h
new file mode 100644
index 000000000000..309ca72f2dfb
--- /dev/null
+++ b/include/linux/rw_hint.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_RW_HINT_H
+#define _LINUX_RW_HINT_H
+
+#include <linux/build_bug.h>
+#include <linux/compiler_attributes.h>
+#include <uapi/linux/fcntl.h>
+
+/* Block storage write lifetime hint values. */
+enum rw_hint {
+ WRITE_LIFE_NOT_SET = RWH_WRITE_LIFE_NOT_SET,
+ WRITE_LIFE_NONE = RWH_WRITE_LIFE_NONE,
+ WRITE_LIFE_SHORT = RWH_WRITE_LIFE_SHORT,
+ WRITE_LIFE_MEDIUM = RWH_WRITE_LIFE_MEDIUM,
+ WRITE_LIFE_LONG = RWH_WRITE_LIFE_LONG,
+ WRITE_LIFE_EXTREME = RWH_WRITE_LIFE_EXTREME,
+} __packed;
+
+/* Sparse ignores __packed annotations on enums, hence the #ifndef below. */
+#ifndef __CHECKER__
+static_assert(sizeof(enum rw_hint) == 1);
+#endif
+
+#endif /* _LINUX_RW_HINT_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ffe8f618ab86..17cb0761ff65 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -858,6 +858,8 @@ struct task_struct {
u8 rcu_tasks_idx;
int rcu_tasks_idle_cpu;
struct list_head rcu_tasks_holdout_list;
+ int rcu_tasks_exit_cpu;
+ struct list_head rcu_tasks_exit_list;
#endif /* #ifdef CONFIG_TASKS_RCU */
#ifdef CONFIG_TASKS_TRACE_RCU
@@ -1642,7 +1644,7 @@ extern struct pid *cad_pid;
#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */
#define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */
#define PF_MEMALLOC_PIN 0x10000000 /* Allocation context constrained to zones which allow long term pinning. */
-#define PF__HOLE__20000000 0x20000000
+#define PF_BLOCK_TS 0x20000000 /* plug has ts that needs updating */
#define PF__HOLE__40000000 0x40000000
#define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 4b7664c56208..0a0e23c45406 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -735,8 +735,6 @@ static inline int thread_group_empty(struct task_struct *p)
#define delay_group_leader(p) \
(thread_group_leader(p) && !thread_group_empty(p))
-extern bool thread_group_exited(struct pid *pid);
-
extern struct sighand_struct *__lock_task_sighand(struct task_struct *task,
unsigned long *flags);
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index a6e04b4a21d7..11e0e00e0bb9 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -176,6 +176,7 @@ extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
+bool cpus_equal_capacity(int this_cpu, int that_cpu);
bool cpus_share_cache(int this_cpu, int that_cpu);
bool cpus_share_resources(int this_cpu, int that_cpu);
@@ -226,6 +227,11 @@ partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
{
}
+static inline bool cpus_equal_capacity(int this_cpu, int that_cpu)
+{
+ return true;
+}
+
static inline bool cpus_share_cache(int this_cpu, int that_cpu)
{
return true;
diff --git a/include/linux/smp.h b/include/linux/smp.h
index e87520dc2959..cc517002c599 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -261,7 +261,7 @@ static inline int get_boot_cpu_id(void)
* regular asm read for the stable.
*/
#ifndef __smp_processor_id
-#define __smp_processor_id(x) raw_smp_processor_id(x)
+#define __smp_processor_id() raw_smp_processor_id()
#endif
#ifdef CONFIG_DEBUG_PREEMPT
diff --git a/include/linux/soc/andes/irq.h b/include/linux/soc/andes/irq.h
new file mode 100644
index 000000000000..edc3182d6e66
--- /dev/null
+++ b/include/linux/soc/andes/irq.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 Andes Technology Corporation
+ */
+#ifndef __ANDES_IRQ_H
+#define __ANDES_IRQ_H
+
+/* Andes PMU irq number */
+#define ANDES_RV_IRQ_PMOVI 18
+#define ANDES_RV_IRQ_LAST ANDES_RV_IRQ_PMOVI
+#define ANDES_SLI_CAUSE_BASE 256
+
+/* Andes PMU related registers */
+#define ANDES_CSR_SLIE 0x9c4
+#define ANDES_CSR_SLIP 0x9c5
+#define ANDES_CSR_SCOUNTEROF 0x9d4
+
+#endif /* __ANDES_IRQ_H */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 4db00ddad261..378ab1cd23bd 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -298,7 +298,7 @@ struct swap_info_struct {
unsigned int __percpu *cluster_next_cpu; /*percpu index for next allocation */
struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */
struct rb_root swap_extent_root;/* root of the swap extent rbtree */
- struct bdev_handle *bdev_handle;/* open handle of the bdev */
+ struct file *bdev_file; /* open handle of the bdev */
struct block_device *bdev; /* swap device or bdev of swap file */
struct file *swap_file; /* seldom referenced */
unsigned int old_block_size; /* seldom referenced */
@@ -549,6 +549,11 @@ static inline int swap_duplicate(swp_entry_t swp)
return 0;
}
+static inline int swapcache_prepare(swp_entry_t swp)
+{
+ return 0;
+}
+
static inline void swap_free(swp_entry_t swp)
{
}
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 7c43e98cf211..7e50cbd97f86 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -268,15 +268,17 @@ struct system_device_crosststamp {
};
/**
- * struct system_counterval_t - system counter value with the pointer to the
+ * struct system_counterval_t - system counter value with the ID of the
* corresponding clocksource
* @cycles: System counter value
- * @cs: Clocksource corresponding to system counter value. Used by
- * timekeeping code to verify comparibility of two cycle values
+ * @cs_id: Clocksource ID corresponding to system counter value. Used by
+ * timekeeping code to verify comparability of two cycle values.
+ * The default ID, CSID_GENERIC, does not identify a specific
+ * clocksource.
*/
struct system_counterval_t {
u64 cycles;
- struct clocksource *cs;
+ enum clocksource_ids cs_id;
};
/*
diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h
index 9ec229dfddaa..1ef95c0287f0 100644
--- a/include/linux/trace_seq.h
+++ b/include/linux/trace_seq.h
@@ -9,9 +9,15 @@
/*
* Trace sequences are used to allow a function to call several other functions
* to create a string of data to use.
+ *
+ * Have the trace seq to be 8K which is typically PAGE_SIZE * 2 on
+ * most architectures. The TRACE_SEQ_BUFFER_SIZE (which is
+ * TRACE_SEQ_SIZE minus the other fields of trace_seq), is the
+ * max size the output of a trace event may be.
*/
-#define TRACE_SEQ_BUFFER_SIZE (PAGE_SIZE * 2 - \
+#define TRACE_SEQ_SIZE 8192
+#define TRACE_SEQ_BUFFER_SIZE (TRACE_SEQ_SIZE - \
(sizeof(struct seq_buf) + sizeof(size_t) + sizeof(int)))
struct trace_seq {
diff --git a/include/linux/uio.h b/include/linux/uio.h
index bea9c89922d9..00cebe2b70de 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -40,7 +40,6 @@ struct iov_iter_state {
struct iov_iter {
u8 iter_type;
- bool copy_mc;
bool nofault;
bool data_source;
size_t iov_offset;
@@ -248,22 +247,8 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i);
#ifdef CONFIG_ARCH_HAS_COPY_MC
size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
-static inline void iov_iter_set_copy_mc(struct iov_iter *i)
-{
- i->copy_mc = true;
-}
-
-static inline bool iov_iter_is_copy_mc(const struct iov_iter *i)
-{
- return i->copy_mc;
-}
#else
#define _copy_mc_to_iter _copy_to_iter
-static inline void iov_iter_set_copy_mc(struct iov_iter *i) { }
-static inline bool iov_iter_is_copy_mc(const struct iov_iter *i)
-{
- return false;
-}
#endif
size_t iov_iter_zero(size_t bytes, struct iov_iter *);
@@ -355,7 +340,6 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction,
WARN_ON(direction & ~(READ | WRITE));
*i = (struct iov_iter) {
.iter_type = ITER_UBUF,
- .copy_mc = false,
.data_source = direction,
.ubuf = buf,
.count = count,
diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h
index cd77fc6095a1..ac95e7c89df5 100644
--- a/include/linux/usb/hcd.h
+++ b/include/linux/usb/hcd.h
@@ -55,7 +55,7 @@ struct giveback_urb_bh {
bool high_prio;
spinlock_t lock;
struct list_head head;
- struct tasklet_struct bh;
+ struct work_struct bh;
struct usb_host_endpoint *completing_ep;
};
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 2cc0a9606175..158784dd189a 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -22,20 +22,54 @@
*/
#define work_data_bits(work) ((unsigned long *)(&(work)->data))
-enum {
+enum work_bits {
WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */
- WORK_STRUCT_INACTIVE_BIT= 1, /* work item is inactive */
- WORK_STRUCT_PWQ_BIT = 2, /* data points to pwq */
- WORK_STRUCT_LINKED_BIT = 3, /* next work is linked to this one */
+ WORK_STRUCT_INACTIVE_BIT, /* work item is inactive */
+ WORK_STRUCT_PWQ_BIT, /* data points to pwq */
+ WORK_STRUCT_LINKED_BIT, /* next work is linked to this one */
#ifdef CONFIG_DEBUG_OBJECTS_WORK
- WORK_STRUCT_STATIC_BIT = 4, /* static initializer (debugobjects) */
- WORK_STRUCT_COLOR_SHIFT = 5, /* color for workqueue flushing */
-#else
- WORK_STRUCT_COLOR_SHIFT = 4, /* color for workqueue flushing */
+ WORK_STRUCT_STATIC_BIT, /* static initializer (debugobjects) */
#endif
+ WORK_STRUCT_FLAG_BITS,
+ /* color for workqueue flushing */
+ WORK_STRUCT_COLOR_SHIFT = WORK_STRUCT_FLAG_BITS,
WORK_STRUCT_COLOR_BITS = 4,
+ /*
+ * When WORK_STRUCT_PWQ is set, reserve 8 bits off of pwq pointer w/
+ * debugobjects turned off. This makes pwqs aligned to 256 bytes (512
+ * bytes w/ DEBUG_OBJECTS_WORK) and allows 16 workqueue flush colors.
+ *
+ * MSB
+ * [ pwq pointer ] [ flush color ] [ STRUCT flags ]
+ * 4 bits 4 or 5 bits
+ */
+ WORK_STRUCT_PWQ_SHIFT = WORK_STRUCT_COLOR_SHIFT + WORK_STRUCT_COLOR_BITS,
+
+ /*
+ * data contains off-queue information when !WORK_STRUCT_PWQ.
+ *
+ * MSB
+ * [ pool ID ] [ OFFQ flags ] [ STRUCT flags ]
+ * 1 bit 4 or 5 bits
+ */
+ WORK_OFFQ_FLAG_SHIFT = WORK_STRUCT_FLAG_BITS,
+ WORK_OFFQ_CANCELING_BIT = WORK_OFFQ_FLAG_SHIFT,
+ WORK_OFFQ_FLAG_END,
+ WORK_OFFQ_FLAG_BITS = WORK_OFFQ_FLAG_END - WORK_OFFQ_FLAG_SHIFT,
+
+ /*
+ * When a work item is off queue, the high bits encode off-queue flags
+ * and the last pool it was on. Cap pool ID to 31 bits and use the
+ * highest number to indicate that no pool is associated.
+ */
+ WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_FLAG_SHIFT + WORK_OFFQ_FLAG_BITS,
+ WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT,
+ WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31,
+};
+
+enum work_flags {
WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT,
WORK_STRUCT_INACTIVE = 1 << WORK_STRUCT_INACTIVE_BIT,
WORK_STRUCT_PWQ = 1 << WORK_STRUCT_PWQ_BIT,
@@ -45,35 +79,14 @@ enum {
#else
WORK_STRUCT_STATIC = 0,
#endif
+};
+enum wq_misc_consts {
WORK_NR_COLORS = (1 << WORK_STRUCT_COLOR_BITS),
/* not bound to any CPU, prefer the local CPU */
WORK_CPU_UNBOUND = NR_CPUS,
- /*
- * Reserve 8 bits off of pwq pointer w/ debugobjects turned off.
- * This makes pwqs aligned to 256 bytes and allows 16 workqueue
- * flush colors.
- */
- WORK_STRUCT_FLAG_BITS = WORK_STRUCT_COLOR_SHIFT +
- WORK_STRUCT_COLOR_BITS,
-
- /* data contains off-queue information when !WORK_STRUCT_PWQ */
- WORK_OFFQ_FLAG_BASE = WORK_STRUCT_COLOR_SHIFT,
-
- __WORK_OFFQ_CANCELING = WORK_OFFQ_FLAG_BASE,
-
- /*
- * When a work item is off queue, its high bits point to the last
- * pool it was on. Cap at 31 bits and use the highest number to
- * indicate that no pool is associated.
- */
- WORK_OFFQ_FLAG_BITS = 1,
- WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_FLAG_BASE + WORK_OFFQ_FLAG_BITS,
- WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT,
- WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31,
-
/* bit mask for work_busy() return values */
WORK_BUSY_PENDING = 1 << 0,
WORK_BUSY_RUNNING = 1 << 1,
@@ -83,12 +96,10 @@ enum {
};
/* Convenience constants - of type 'unsigned long', not 'enum'! */
-#define WORK_OFFQ_CANCELING (1ul << __WORK_OFFQ_CANCELING)
+#define WORK_OFFQ_CANCELING (1ul << WORK_OFFQ_CANCELING_BIT)
#define WORK_OFFQ_POOL_NONE ((1ul << WORK_OFFQ_POOL_BITS) - 1)
#define WORK_STRUCT_NO_POOL (WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT)
-
-#define WORK_STRUCT_FLAG_MASK ((1ul << WORK_STRUCT_FLAG_BITS) - 1)
-#define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK)
+#define WORK_STRUCT_PWQ_MASK (~((1ul << WORK_STRUCT_PWQ_SHIFT) - 1))
#define WORK_DATA_INIT() ATOMIC_LONG_INIT((unsigned long)WORK_STRUCT_NO_POOL)
#define WORK_DATA_STATIC_INIT() \
@@ -347,7 +358,8 @@ static inline unsigned int work_static(struct work_struct *work) { return 0; }
* Workqueue flags and constants. For details, please refer to
* Documentation/core-api/workqueue.rst.
*/
-enum {
+enum wq_flags {
+ WQ_BH = 1 << 0, /* execute in bottom half (softirq) context */
WQ_UNBOUND = 1 << 1, /* not bound to any cpu */
WQ_FREEZABLE = 1 << 2, /* freeze during suspend */
WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */
@@ -386,11 +398,22 @@ enum {
__WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */
__WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */
__WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */
- __WQ_ORDERED_EXPLICIT = 1 << 19, /* internal: alloc_ordered_workqueue() */
+ /* BH wq only allows the following flags */
+ __WQ_BH_ALLOWS = WQ_BH | WQ_HIGHPRI,
+};
+
+enum wq_consts {
WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */
WQ_UNBOUND_MAX_ACTIVE = WQ_MAX_ACTIVE,
WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2,
+
+ /*
+ * Per-node default cap on min_active. Unless explicitly set, min_active
+ * is set to min(max_active, WQ_DFL_MIN_ACTIVE). For more details, see
+ * workqueue_struct->min_active definition.
+ */
+ WQ_DFL_MIN_ACTIVE = 8,
};
/*
@@ -420,6 +443,9 @@ enum {
* they are same as their non-power-efficient counterparts - e.g.
* system_power_efficient_wq is identical to system_wq if
* 'wq_power_efficient' is disabled. See WQ_POWER_EFFICIENT for more info.
+ *
+ * system_bh[_highpri]_wq are convenience interface to softirq. BH work items
+ * are executed in the queueing CPU's BH context in the queueing order.
*/
extern struct workqueue_struct *system_wq;
extern struct workqueue_struct *system_highpri_wq;
@@ -428,16 +454,43 @@ extern struct workqueue_struct *system_unbound_wq;
extern struct workqueue_struct *system_freezable_wq;
extern struct workqueue_struct *system_power_efficient_wq;
extern struct workqueue_struct *system_freezable_power_efficient_wq;
+extern struct workqueue_struct *system_bh_wq;
+extern struct workqueue_struct *system_bh_highpri_wq;
+
+void workqueue_softirq_action(bool highpri);
+void workqueue_softirq_dead(unsigned int cpu);
/**
* alloc_workqueue - allocate a workqueue
* @fmt: printf format for the name of the workqueue
* @flags: WQ_* flags
- * @max_active: max in-flight work items per CPU, 0 for default
+ * @max_active: max in-flight work items, 0 for default
* remaining args: args for @fmt
*
- * Allocate a workqueue with the specified parameters. For detailed
- * information on WQ_* flags, please refer to
+ * For a per-cpu workqueue, @max_active limits the number of in-flight work
+ * items for each CPU. e.g. @max_active of 1 indicates that each CPU can be
+ * executing at most one work item for the workqueue.
+ *
+ * For unbound workqueues, @max_active limits the number of in-flight work items
+ * for the whole system. e.g. @max_active of 16 indicates that that there can be
+ * at most 16 work items executing for the workqueue in the whole system.
+ *
+ * As sharing the same active counter for an unbound workqueue across multiple
+ * NUMA nodes can be expensive, @max_active is distributed to each NUMA node
+ * according to the proportion of the number of online CPUs and enforced
+ * independently.
+ *
+ * Depending on online CPU distribution, a node may end up with per-node
+ * max_active which is significantly lower than @max_active, which can lead to
+ * deadlocks if the per-node concurrency limit is lower than the maximum number
+ * of interdependent work items for the workqueue.
+ *
+ * To guarantee forward progress regardless of online CPU distribution, the
+ * concurrency limit on every node is guaranteed to be equal to or greater than
+ * min_active which is set to min(@max_active, %WQ_DFL_MIN_ACTIVE). This means
+ * that the sum of per-node max_active's may be larger than @max_active.
+ *
+ * For detailed information on %WQ_* flags, please refer to
* Documentation/core-api/workqueue.rst.
*
* RETURNS:
@@ -460,8 +513,7 @@ alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...);
* Pointer to the allocated workqueue on success, %NULL on failure.
*/
#define alloc_ordered_workqueue(fmt, flags, args...) \
- alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | \
- __WQ_ORDERED_EXPLICIT | (flags), 1, ##args)
+ alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
#define create_workqueue(name) \
alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name))
@@ -471,6 +523,9 @@ alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...);
#define create_singlethread_workqueue(name) \
alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name)
+#define from_work(var, callback_work, work_fieldname) \
+ container_of(callback_work, typeof(*var), work_fieldname)
+
extern void destroy_workqueue(struct workqueue_struct *wq);
struct workqueue_attrs *alloc_workqueue_attrs(void);
@@ -508,6 +563,8 @@ extern bool flush_rcu_work(struct rcu_work *rwork);
extern void workqueue_set_max_active(struct workqueue_struct *wq,
int max_active);
+extern void workqueue_set_min_active(struct workqueue_struct *wq,
+ int min_active);
extern struct work_struct *current_work(void);
extern bool current_is_workqueue_rescuer(void);
extern bool workqueue_congested(int cpu, struct workqueue_struct *wq);
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 4dabeb6c76d3..9b09acac538e 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -48,6 +48,10 @@ void napi_busy_loop(unsigned int napi_id,
bool (*loop_end)(void *, unsigned long),
void *loop_end_arg, bool prefer_busy_poll, u16 budget);
+void napi_busy_loop_rcu(unsigned int napi_id,
+ bool (*loop_end)(void *, unsigned long),
+ void *loop_end_arg, bool prefer_busy_poll, u16 budget);
+
#else /* CONFIG_NET_RX_BUSY_POLL */
static inline unsigned long net_busy_loop_on(void)
{
diff --git a/include/net/mctp.h b/include/net/mctp.h
index da86e106c91d..2bff5f47ce82 100644
--- a/include/net/mctp.h
+++ b/include/net/mctp.h
@@ -249,6 +249,7 @@ struct mctp_route {
struct mctp_route *mctp_route_lookup(struct net *net, unsigned int dnet,
mctp_eid_t daddr);
+/* always takes ownership of skb */
int mctp_local_output(struct sock *sk, struct mctp_route *rt,
struct sk_buff *skb, mctp_eid_t daddr, u8 req_tag);
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 956c752ceb31..a763dd327c6e 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -276,7 +276,7 @@ nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table,
}
void flow_offload_route_init(struct flow_offload *flow,
- const struct nf_flow_route *route);
+ struct nf_flow_route *route);
int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow);
void flow_offload_refresh(struct nf_flowtable *flow_table,
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 934fdb977551..cefe0c4bdae3 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -238,12 +238,7 @@ static inline bool qdisc_may_bulk(const struct Qdisc *qdisc)
static inline int qdisc_avail_bulklimit(const struct netdev_queue *txq)
{
-#ifdef CONFIG_BQL
- /* Non-BQL migrated drivers will return 0, too. */
- return dql_avail(&txq->dql);
-#else
- return 0;
-#endif
+ return netdev_queue_dql_avail(txq);
}
struct Qdisc_class_ops {
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index a43062d4c734..8346b0d29542 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -308,6 +308,9 @@ void switchdev_deferred_process(void);
int switchdev_port_attr_set(struct net_device *dev,
const struct switchdev_attr *attr,
struct netlink_ext_ack *extack);
+bool switchdev_port_obj_act_is_deferred(struct net_device *dev,
+ enum switchdev_notifier_type nt,
+ const struct switchdev_obj *obj);
int switchdev_port_obj_add(struct net_device *dev,
const struct switchdev_obj *obj,
struct netlink_ext_ack *extack);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index dd78a1181031..f6eba9652d01 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2506,7 +2506,7 @@ struct tcp_ulp_ops {
/* cleanup ulp */
void (*release)(struct sock *sk);
/* diagnostic */
- int (*get_info)(const struct sock *sk, struct sk_buff *skb);
+ int (*get_info)(struct sock *sk, struct sk_buff *skb);
size_t (*get_info_size)(const struct sock *sk);
/* clone ulp */
void (*clone)(const struct request_sock *req, struct sock *newsk,
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 5ec1e71a09de..c38f4fe5e64c 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -100,10 +100,6 @@ struct scsi_vpd {
unsigned char data[];
};
-enum scsi_vpd_parameters {
- SCSI_VPD_HEADER_SIZE = 4,
-};
-
struct scsi_device {
struct Scsi_Host *host;
struct request_queue *request_queue;
@@ -208,6 +204,7 @@ struct scsi_device {
unsigned use_10_for_rw:1; /* first try 10-byte read / write */
unsigned use_10_for_ms:1; /* first try 10-byte mode sense/select */
unsigned set_dbd_for_ms:1; /* Set "DBD" field in mode sense */
+ unsigned read_before_ms:1; /* perform a READ before MODE SENSE */
unsigned no_report_opcodes:1; /* no REPORT SUPPORTED OPERATION CODES */
unsigned no_write_same:1; /* no WRITE SAME command */
unsigned use_16_for_rw:1; /* Use read/write(16) over read/write(10) */
diff --git a/include/sound/soc-card.h b/include/sound/soc-card.h
index ecc02e955279..1f4c39922d82 100644
--- a/include/sound/soc-card.h
+++ b/include/sound/soc-card.h
@@ -30,6 +30,8 @@ static inline void snd_soc_card_mutex_unlock(struct snd_soc_card *card)
struct snd_kcontrol *snd_soc_card_get_kcontrol(struct snd_soc_card *soc_card,
const char *name);
+struct snd_kcontrol *snd_soc_card_get_kcontrol_locked(struct snd_soc_card *soc_card,
+ const char *name);
int snd_soc_card_jack_new(struct snd_soc_card *card, const char *id, int type,
struct snd_soc_jack *jack);
int snd_soc_card_jack_new_pins(struct snd_soc_card *card, const char *id,
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 08f2c93d6b16..450c44c83a5d 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -1189,8 +1189,8 @@ TRACE_EVENT(afs_flock_op,
__entry->from = fl->fl_start;
__entry->len = fl->fl_end - fl->fl_start + 1;
__entry->op = op;
- __entry->type = fl->fl_type;
- __entry->flags = fl->fl_flags;
+ __entry->type = fl->c.flc_type;
+ __entry->flags = fl->c.flc_flags;
__entry->debug_id = fl->fl_u.afs.debug_id;
),
diff --git a/include/trace/events/filelock.h b/include/trace/events/filelock.h
index 1646dadd7f37..b8d1e00a7982 100644
--- a/include/trace/events/filelock.h
+++ b/include/trace/events/filelock.h
@@ -68,11 +68,11 @@ DECLARE_EVENT_CLASS(filelock_lock,
__field(struct file_lock *, fl)
__field(unsigned long, i_ino)
__field(dev_t, s_dev)
- __field(struct file_lock *, fl_blocker)
- __field(fl_owner_t, fl_owner)
- __field(unsigned int, fl_pid)
- __field(unsigned int, fl_flags)
- __field(unsigned char, fl_type)
+ __field(struct file_lock_core *, blocker)
+ __field(fl_owner_t, owner)
+ __field(unsigned int, pid)
+ __field(unsigned int, flags)
+ __field(unsigned char, type)
__field(loff_t, fl_start)
__field(loff_t, fl_end)
__field(int, ret)
@@ -82,11 +82,11 @@ DECLARE_EVENT_CLASS(filelock_lock,
__entry->fl = fl ? fl : NULL;
__entry->s_dev = inode->i_sb->s_dev;
__entry->i_ino = inode->i_ino;
- __entry->fl_blocker = fl ? fl->fl_blocker : NULL;
- __entry->fl_owner = fl ? fl->fl_owner : NULL;
- __entry->fl_pid = fl ? fl->fl_pid : 0;
- __entry->fl_flags = fl ? fl->fl_flags : 0;
- __entry->fl_type = fl ? fl->fl_type : 0;
+ __entry->blocker = fl ? fl->c.flc_blocker : NULL;
+ __entry->owner = fl ? fl->c.flc_owner : NULL;
+ __entry->pid = fl ? fl->c.flc_pid : 0;
+ __entry->flags = fl ? fl->c.flc_flags : 0;
+ __entry->type = fl ? fl->c.flc_type : 0;
__entry->fl_start = fl ? fl->fl_start : 0;
__entry->fl_end = fl ? fl->fl_end : 0;
__entry->ret = ret;
@@ -94,9 +94,9 @@ DECLARE_EVENT_CLASS(filelock_lock,
TP_printk("fl=%p dev=0x%x:0x%x ino=0x%lx fl_blocker=%p fl_owner=%p fl_pid=%u fl_flags=%s fl_type=%s fl_start=%lld fl_end=%lld ret=%d",
__entry->fl, MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
- __entry->i_ino, __entry->fl_blocker, __entry->fl_owner,
- __entry->fl_pid, show_fl_flags(__entry->fl_flags),
- show_fl_type(__entry->fl_type),
+ __entry->i_ino, __entry->blocker, __entry->owner,
+ __entry->pid, show_fl_flags(__entry->flags),
+ show_fl_type(__entry->type),
__entry->fl_start, __entry->fl_end, __entry->ret)
);
@@ -117,59 +117,59 @@ DEFINE_EVENT(filelock_lock, flock_lock_inode,
TP_ARGS(inode, fl, ret));
DECLARE_EVENT_CLASS(filelock_lease,
- TP_PROTO(struct inode *inode, struct file_lock *fl),
+ TP_PROTO(struct inode *inode, struct file_lease *fl),
TP_ARGS(inode, fl),
TP_STRUCT__entry(
- __field(struct file_lock *, fl)
+ __field(struct file_lease *, fl)
__field(unsigned long, i_ino)
__field(dev_t, s_dev)
- __field(struct file_lock *, fl_blocker)
- __field(fl_owner_t, fl_owner)
- __field(unsigned int, fl_flags)
- __field(unsigned char, fl_type)
- __field(unsigned long, fl_break_time)
- __field(unsigned long, fl_downgrade_time)
+ __field(struct file_lock_core *, blocker)
+ __field(fl_owner_t, owner)
+ __field(unsigned int, flags)
+ __field(unsigned char, type)
+ __field(unsigned long, break_time)
+ __field(unsigned long, downgrade_time)
),
TP_fast_assign(
__entry->fl = fl ? fl : NULL;
__entry->s_dev = inode->i_sb->s_dev;
__entry->i_ino = inode->i_ino;
- __entry->fl_blocker = fl ? fl->fl_blocker : NULL;
- __entry->fl_owner = fl ? fl->fl_owner : NULL;
- __entry->fl_flags = fl ? fl->fl_flags : 0;
- __entry->fl_type = fl ? fl->fl_type : 0;
- __entry->fl_break_time = fl ? fl->fl_break_time : 0;
- __entry->fl_downgrade_time = fl ? fl->fl_downgrade_time : 0;
+ __entry->blocker = fl ? fl->c.flc_blocker : NULL;
+ __entry->owner = fl ? fl->c.flc_owner : NULL;
+ __entry->flags = fl ? fl->c.flc_flags : 0;
+ __entry->type = fl ? fl->c.flc_type : 0;
+ __entry->break_time = fl ? fl->fl_break_time : 0;
+ __entry->downgrade_time = fl ? fl->fl_downgrade_time : 0;
),
TP_printk("fl=%p dev=0x%x:0x%x ino=0x%lx fl_blocker=%p fl_owner=%p fl_flags=%s fl_type=%s fl_break_time=%lu fl_downgrade_time=%lu",
__entry->fl, MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
- __entry->i_ino, __entry->fl_blocker, __entry->fl_owner,
- show_fl_flags(__entry->fl_flags),
- show_fl_type(__entry->fl_type),
- __entry->fl_break_time, __entry->fl_downgrade_time)
+ __entry->i_ino, __entry->blocker, __entry->owner,
+ show_fl_flags(__entry->flags),
+ show_fl_type(__entry->type),
+ __entry->break_time, __entry->downgrade_time)
);
-DEFINE_EVENT(filelock_lease, break_lease_noblock, TP_PROTO(struct inode *inode, struct file_lock *fl),
+DEFINE_EVENT(filelock_lease, break_lease_noblock, TP_PROTO(struct inode *inode, struct file_lease *fl),
TP_ARGS(inode, fl));
-DEFINE_EVENT(filelock_lease, break_lease_block, TP_PROTO(struct inode *inode, struct file_lock *fl),
+DEFINE_EVENT(filelock_lease, break_lease_block, TP_PROTO(struct inode *inode, struct file_lease *fl),
TP_ARGS(inode, fl));
-DEFINE_EVENT(filelock_lease, break_lease_unblock, TP_PROTO(struct inode *inode, struct file_lock *fl),
+DEFINE_EVENT(filelock_lease, break_lease_unblock, TP_PROTO(struct inode *inode, struct file_lease *fl),
TP_ARGS(inode, fl));
-DEFINE_EVENT(filelock_lease, generic_delete_lease, TP_PROTO(struct inode *inode, struct file_lock *fl),
+DEFINE_EVENT(filelock_lease, generic_delete_lease, TP_PROTO(struct inode *inode, struct file_lease *fl),
TP_ARGS(inode, fl));
-DEFINE_EVENT(filelock_lease, time_out_leases, TP_PROTO(struct inode *inode, struct file_lock *fl),
+DEFINE_EVENT(filelock_lease, time_out_leases, TP_PROTO(struct inode *inode, struct file_lease *fl),
TP_ARGS(inode, fl));
TRACE_EVENT(generic_add_lease,
- TP_PROTO(struct inode *inode, struct file_lock *fl),
+ TP_PROTO(struct inode *inode, struct file_lease *fl),
TP_ARGS(inode, fl),
@@ -179,9 +179,9 @@ TRACE_EVENT(generic_add_lease,
__field(int, rcount)
__field(int, icount)
__field(dev_t, s_dev)
- __field(fl_owner_t, fl_owner)
- __field(unsigned int, fl_flags)
- __field(unsigned char, fl_type)
+ __field(fl_owner_t, owner)
+ __field(unsigned int, flags)
+ __field(unsigned char, type)
),
TP_fast_assign(
@@ -190,21 +190,21 @@ TRACE_EVENT(generic_add_lease,
__entry->wcount = atomic_read(&inode->i_writecount);
__entry->rcount = atomic_read(&inode->i_readcount);
__entry->icount = atomic_read(&inode->i_count);
- __entry->fl_owner = fl->fl_owner;
- __entry->fl_flags = fl->fl_flags;
- __entry->fl_type = fl->fl_type;
+ __entry->owner = fl->c.flc_owner;
+ __entry->flags = fl->c.flc_flags;
+ __entry->type = fl->c.flc_type;
),
TP_printk("dev=0x%x:0x%x ino=0x%lx wcount=%d rcount=%d icount=%d fl_owner=%p fl_flags=%s fl_type=%s",
MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
__entry->i_ino, __entry->wcount, __entry->rcount,
- __entry->icount, __entry->fl_owner,
- show_fl_flags(__entry->fl_flags),
- show_fl_type(__entry->fl_type))
+ __entry->icount, __entry->owner,
+ show_fl_flags(__entry->flags),
+ show_fl_type(__entry->type))
);
TRACE_EVENT(leases_conflict,
- TP_PROTO(bool conflict, struct file_lock *lease, struct file_lock *breaker),
+ TP_PROTO(bool conflict, struct file_lease *lease, struct file_lease *breaker),
TP_ARGS(conflict, lease, breaker),
@@ -220,11 +220,11 @@ TRACE_EVENT(leases_conflict,
TP_fast_assign(
__entry->lease = lease;
- __entry->l_fl_flags = lease->fl_flags;
- __entry->l_fl_type = lease->fl_type;
+ __entry->l_fl_flags = lease->c.flc_flags;
+ __entry->l_fl_type = lease->c.flc_type;
__entry->breaker = breaker;
- __entry->b_fl_flags = breaker->fl_flags;
- __entry->b_fl_type = breaker->fl_type;
+ __entry->b_fl_flags = breaker->c.flc_flags;
+ __entry->b_fl_type = breaker->c.flc_type;
__entry->conflict = conflict;
),
diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h
index 69454f1f98b0..e948df7ce625 100644
--- a/include/trace/events/io_uring.h
+++ b/include/trace/events/io_uring.h
@@ -148,7 +148,7 @@ TRACE_EVENT(io_uring_queue_async_work,
__field( void *, req )
__field( u64, user_data )
__field( u8, opcode )
- __field( unsigned int, flags )
+ __field( unsigned long long, flags )
__field( struct io_wq_work *, work )
__field( int, rw )
@@ -159,7 +159,7 @@ TRACE_EVENT(io_uring_queue_async_work,
__entry->ctx = req->ctx;
__entry->req = req;
__entry->user_data = req->cqe.user_data;
- __entry->flags = req->flags;
+ __entry->flags = (__force unsigned long long) req->flags;
__entry->opcode = req->opcode;
__entry->work = &req->work;
__entry->rw = rw;
@@ -167,10 +167,10 @@ TRACE_EVENT(io_uring_queue_async_work,
__assign_str(op_str, io_uring_get_opcode(req->opcode));
),
- TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, flags 0x%x, %s queue, work %p",
+ TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, flags 0x%llx, %s queue, work %p",
__entry->ctx, __entry->req, __entry->user_data,
- __get_str(op_str),
- __entry->flags, __entry->rw ? "hashed" : "normal", __entry->work)
+ __get_str(op_str), __entry->flags,
+ __entry->rw ? "hashed" : "normal", __entry->work)
);
/**
@@ -378,7 +378,7 @@ TRACE_EVENT(io_uring_submit_req,
__field( void *, req )
__field( unsigned long long, user_data )
__field( u8, opcode )
- __field( u32, flags )
+ __field( unsigned long long, flags )
__field( bool, sq_thread )
__string( op_str, io_uring_get_opcode(req->opcode) )
@@ -389,16 +389,16 @@ TRACE_EVENT(io_uring_submit_req,
__entry->req = req;
__entry->user_data = req->cqe.user_data;
__entry->opcode = req->opcode;
- __entry->flags = req->flags;
+ __entry->flags = (__force unsigned long long) req->flags;
__entry->sq_thread = req->ctx->flags & IORING_SETUP_SQPOLL;
__assign_str(op_str, io_uring_get_opcode(req->opcode));
),
- TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, flags 0x%x, "
+ TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, flags 0x%llx, "
"sq_thread %d", __entry->ctx, __entry->req,
- __entry->user_data, __get_str(op_str),
- __entry->flags, __entry->sq_thread)
+ __entry->user_data, __get_str(op_str), __entry->flags,
+ __entry->sq_thread)
);
/*
@@ -602,29 +602,25 @@ TRACE_EVENT(io_uring_cqe_overflow,
*
* @tctx: pointer to a io_uring_task
* @count: how many functions it ran
- * @loops: how many loops it ran
*
*/
TRACE_EVENT(io_uring_task_work_run,
- TP_PROTO(void *tctx, unsigned int count, unsigned int loops),
+ TP_PROTO(void *tctx, unsigned int count),
- TP_ARGS(tctx, count, loops),
+ TP_ARGS(tctx, count),
TP_STRUCT__entry (
__field( void *, tctx )
__field( unsigned int, count )
- __field( unsigned int, loops )
),
TP_fast_assign(
__entry->tctx = tctx;
__entry->count = count;
- __entry->loops = loops;
),
- TP_printk("tctx %p, count %u, loops %u",
- __entry->tctx, __entry->count, __entry->loops)
+ TP_printk("tctx %p, count %u", __entry->tctx, __entry->count)
);
TRACE_EVENT(io_uring_short_write,
diff --git a/include/trace/events/qdisc.h b/include/trace/events/qdisc.h
index a3995925cb05..1f4258308b96 100644
--- a/include/trace/events/qdisc.h
+++ b/include/trace/events/qdisc.h
@@ -81,14 +81,14 @@ TRACE_EVENT(qdisc_reset,
TP_ARGS(q),
TP_STRUCT__entry(
- __string( dev, qdisc_dev(q) )
- __string( kind, q->ops->id )
- __field( u32, parent )
- __field( u32, handle )
+ __string( dev, qdisc_dev(q)->name )
+ __string( kind, q->ops->id )
+ __field( u32, parent )
+ __field( u32, handle )
),
TP_fast_assign(
- __assign_str(dev, qdisc_dev(q));
+ __assign_str(dev, qdisc_dev(q)->name);
__assign_str(kind, q->ops->id);
__entry->parent = q->parent;
__entry->handle = q->handle;
@@ -106,14 +106,14 @@ TRACE_EVENT(qdisc_destroy,
TP_ARGS(q),
TP_STRUCT__entry(
- __string( dev, qdisc_dev(q) )
- __string( kind, q->ops->id )
- __field( u32, parent )
- __field( u32, handle )
+ __string( dev, qdisc_dev(q)->name )
+ __string( kind, q->ops->id )
+ __field( u32, parent )
+ __field( u32, handle )
),
TP_fast_assign(
- __assign_str(dev, qdisc_dev(q));
+ __assign_str(dev, qdisc_dev(q)->name);
__assign_str(kind, q->ops->id);
__entry->parent = q->parent;
__entry->handle = q->handle;
diff --git a/include/uapi/drm/nouveau_drm.h b/include/uapi/drm/nouveau_drm.h
index 0bade1592f34..77d7ff0d5b11 100644
--- a/include/uapi/drm/nouveau_drm.h
+++ b/include/uapi/drm/nouveau_drm.h
@@ -54,6 +54,20 @@ extern "C" {
*/
#define NOUVEAU_GETPARAM_EXEC_PUSH_MAX 17
+/*
+ * NOUVEAU_GETPARAM_VRAM_BAR_SIZE - query bar size
+ *
+ * Query the VRAM BAR size.
+ */
+#define NOUVEAU_GETPARAM_VRAM_BAR_SIZE 18
+
+/*
+ * NOUVEAU_GETPARAM_VRAM_USED
+ *
+ * Get remaining VRAM size.
+ */
+#define NOUVEAU_GETPARAM_VRAM_USED 19
+
struct drm_nouveau_getparam {
__u64 param;
__u64 value;
diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
index 9fa3ae324731..bb0c8a994116 100644
--- a/include/uapi/drm/xe_drm.h
+++ b/include/uapi/drm/xe_drm.h
@@ -831,11 +831,6 @@ struct drm_xe_vm_destroy {
* - %DRM_XE_VM_BIND_OP_PREFETCH
*
* and the @flags can be:
- * - %DRM_XE_VM_BIND_FLAG_READONLY
- * - %DRM_XE_VM_BIND_FLAG_ASYNC
- * - %DRM_XE_VM_BIND_FLAG_IMMEDIATE - Valid on a faulting VM only, do the
- * MAP operation immediately rather than deferring the MAP to the page
- * fault handler.
* - %DRM_XE_VM_BIND_FLAG_NULL - When the NULL flag is set, the page
* tables are setup with a special bit which indicates writes are
* dropped and all reads return zero. In the future, the NULL flags
@@ -928,9 +923,8 @@ struct drm_xe_vm_bind_op {
/** @op: Bind operation to perform */
__u32 op;
-#define DRM_XE_VM_BIND_FLAG_READONLY (1 << 0)
-#define DRM_XE_VM_BIND_FLAG_IMMEDIATE (1 << 1)
#define DRM_XE_VM_BIND_FLAG_NULL (1 << 2)
+#define DRM_XE_VM_BIND_FLAG_DUMPABLE (1 << 3)
/** @flags: Bind flags */
__u32 flags;
@@ -1045,20 +1039,6 @@ struct drm_xe_exec_queue_create {
#define DRM_XE_EXEC_QUEUE_EXTENSION_SET_PROPERTY 0
#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY 0
#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE 1
-#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_PREEMPTION_TIMEOUT 2
-#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_PERSISTENCE 3
-#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_JOB_TIMEOUT 4
-#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_TRIGGER 5
-#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_NOTIFY 6
-#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_GRANULARITY 7
-/* Monitor 128KB contiguous region with 4K sub-granularity */
-#define DRM_XE_ACC_GRANULARITY_128K 0
-/* Monitor 2MB contiguous region with 64KB sub-granularity */
-#define DRM_XE_ACC_GRANULARITY_2M 1
-/* Monitor 16MB contiguous region with 512KB sub-granularity */
-#define DRM_XE_ACC_GRANULARITY_16M 2
-/* Monitor 64MB contiguous region with 2M sub-granularity */
-#define DRM_XE_ACC_GRANULARITY_64M 3
/** @extensions: Pointer to the first extension struct, if any */
__u64 extensions;
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 48ad69f7722e..45e4e64fd664 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -64,6 +64,24 @@ struct fstrim_range {
__u64 minlen;
};
+/*
+ * We include a length field because some filesystems (vfat) have an identifier
+ * that we do want to expose as a UUID, but doesn't have the standard length.
+ *
+ * We use a fixed size buffer beacuse this interface will, by fiat, never
+ * support "UUIDs" longer than 16 bytes; we don't want to force all downstream
+ * users to have to deal with that.
+ */
+struct fsuuid2 {
+ __u8 len;
+ __u8 uuid[16];
+};
+
+struct fs_sysfs_path {
+ __u8 len;
+ __u8 name[128];
+};
+
/* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
#define FILE_DEDUPE_RANGE_SAME 0
#define FILE_DEDUPE_RANGE_DIFFERS 1
@@ -215,6 +233,13 @@ struct fsxattr {
#define FS_IOC_FSSETXATTR _IOW('X', 32, struct fsxattr)
#define FS_IOC_GETFSLABEL _IOR(0x94, 49, char[FSLABEL_MAX])
#define FS_IOC_SETFSLABEL _IOW(0x94, 50, char[FSLABEL_MAX])
+/* Returns the external filesystem UUID, the same one blkid returns */
+#define FS_IOC_GETFSUUID _IOR(0x15, 0, struct fsuuid2)
+/*
+ * Returns the path component under /sys/fs/ that refers to this filesystem;
+ * also /sys/kernel/debug/ for filesystems with debugfs exports
+ */
+#define FS_IOC_GETFSSYSFSPATH _IOR(0x15, 1, struct fs_sysfs_path)
/*
* Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
@@ -301,9 +326,12 @@ typedef int __bitwise __kernel_rwf_t;
/* per-IO O_APPEND */
#define RWF_APPEND ((__force __kernel_rwf_t)0x00000010)
+/* per-IO negation of O_APPEND */
+#define RWF_NOAPPEND ((__force __kernel_rwf_t)0x00000020)
+
/* mask of flags supported by the kernel */
#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
- RWF_APPEND)
+ RWF_APPEND | RWF_NOAPPEND)
/* Pagemap ioctl */
#define PAGEMAP_SCAN _IOWR('f', 16, struct pm_scan_arg)
diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h
index c4c53a9ab959..ff8d21f9e95b 100644
--- a/include/uapi/linux/in6.h
+++ b/include/uapi/linux/in6.h
@@ -145,7 +145,7 @@ struct in6_flowlabel_req {
#define IPV6_TLV_PADN 1
#define IPV6_TLV_ROUTERALERT 5
#define IPV6_TLV_CALIPSO 7 /* RFC 5570 */
-#define IPV6_TLV_IOAM 49 /* TEMPORARY IANA allocation for IOAM */
+#define IPV6_TLV_IOAM 49 /* RFC 9486 */
#define IPV6_TLV_JUMBO 194
#define IPV6_TLV_HAO 201 /* home address option */
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 7a673b52827b..7bd10201a02b 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -255,6 +255,7 @@ enum io_uring_op {
IORING_OP_FUTEX_WAKE,
IORING_OP_FUTEX_WAITV,
IORING_OP_FIXED_FD_INSTALL,
+ IORING_OP_FTRUNCATE,
/* this goes last, obviously */
IORING_OP_LAST,
@@ -570,6 +571,10 @@ enum {
/* return status information for a buffer group */
IORING_REGISTER_PBUF_STATUS = 26,
+ /* set/clear busy poll settings */
+ IORING_REGISTER_NAPI = 27,
+ IORING_UNREGISTER_NAPI = 28,
+
/* this goes last */
IORING_REGISTER_LAST,
@@ -703,6 +708,14 @@ struct io_uring_buf_status {
__u32 resv[8];
};
+/* argument for IORING_(UN)REGISTER_NAPI */
+struct io_uring_napi {
+ __u32 busy_poll_to;
+ __u8 prefer_busy_poll;
+ __u8 pad[3];
+ __u64 resv;
+};
+
/*
* io_uring_restriction->opcode values
*/
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index 6325d1d0e90f..1b40a968ba91 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -101,5 +101,6 @@
#define DMA_BUF_MAGIC 0x444d4142 /* "DMAB" */
#define DEVMEM_MAGIC 0x454d444d /* "DMEM" */
#define SECRETMEM_MAGIC 0x5345434d /* "SECM" */
+#define PID_FS_MAGIC 0x50494446 /* "PIDF" */
#endif /* __LINUX_MAGIC_H__ */
diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h
index 5406fbc13074..72ec000a97cd 100644
--- a/include/uapi/linux/pidfd.h
+++ b/include/uapi/linux/pidfd.h
@@ -7,6 +7,12 @@
#include <linux/fcntl.h>
/* Flags for pidfd_open(). */
-#define PIDFD_NONBLOCK O_NONBLOCK
+#define PIDFD_NONBLOCK O_NONBLOCK
+#define PIDFD_THREAD O_EXCL
+
+/* Flags for pidfd_send_signal(). */
+#define PIDFD_SIGNAL_THREAD (1UL << 0)
+#define PIDFD_SIGNAL_THREAD_GROUP (1UL << 1)
+#define PIDFD_SIGNAL_PROCESS_GROUP (1UL << 2)
#endif /* _UAPI_LINUX_PIDFD_H */
diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h
index b9cfc5c96268..c8dc5f8ea699 100644
--- a/include/uapi/linux/ublk_cmd.h
+++ b/include/uapi/linux/ublk_cmd.h
@@ -49,6 +49,8 @@
_IOR('u', UBLK_CMD_GET_DEV_INFO2, struct ublksrv_ctrl_cmd)
#define UBLK_U_CMD_GET_FEATURES \
_IOR('u', 0x13, struct ublksrv_ctrl_cmd)
+#define UBLK_U_CMD_DEL_DEV_ASYNC \
+ _IOR('u', 0x14, struct ublksrv_ctrl_cmd)
/*
* 64bits are enough now, and it should be easy to extend in case of
diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h
index d5b9cfbd9cea..628d46a0da92 100644
--- a/include/uapi/sound/asound.h
+++ b/include/uapi/sound/asound.h
@@ -142,7 +142,7 @@ struct snd_hwdep_dsp_image {
* *
*****************************************************************************/
-#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 16)
+#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 17)
typedef unsigned long snd_pcm_uframes_t;
typedef signed long snd_pcm_sframes_t;
@@ -416,7 +416,7 @@ struct snd_pcm_hw_params {
unsigned int rmask; /* W: requested masks */
unsigned int cmask; /* R: changed masks */
unsigned int info; /* R: Info flags for returned setup */
- unsigned int msbits; /* R: used most significant bits */
+ unsigned int msbits; /* R: used most significant bits (in sample bit-width) */
unsigned int rate_num; /* R: rate numerator */
unsigned int rate_den; /* R: rate denominator */
snd_pcm_uframes_t fifo_size; /* R: chip FIFO size in frames */