Merge tag 'for-6.9/block-20240310' of git://git.kernel.dk/linux
Pull block updates from Jens Axboe:
- MD pull requests via Song:
- Cleanup redundant checks (Yu Kuai)
- Remove deprecated headers (Marc Zyngier, Song Liu)
- Concurrency fixes (Li Lingfeng)
- Memory leak fix (Li Nan)
- Refactor raid1 read_balance (Yu Kuai, Paul Luse)
- Clean up and fix for md_ioctl (Li Nan)
- Other small fixes (Gui-Dong Han, Heming Zhao)
- MD atomic limits (Christoph)
- NVMe pull request via Keith:
- RDMA target enhancements (Max)
- Fabrics fixes (Max, Guixin, Hannes)
- Atomic queue_limits usage (Christoph)
- Const use for class_register (Ricardo)
- Identification error handling fixes (Shin'ichiro, Keith)
- Improvement and cleanup for cached request handling (Christoph)
- Moving towards atomic queue limits. Core changes and driver bits so
far (Christoph)
- Fix UAF issues in aoeblk (Chun-Yi)
- Zoned fix and cleanups (Damien)
- s390 dasd cleanups and fixes (Jan, Miroslav)
- Block issue timestamp caching (me)
- noio scope guarding for zoned IO (Johannes)
- block/nvme PI improvements (Kanchan)
- Ability to terminate long running discard loop (Keith)
- bdev revalidation fix (Li)
- Get rid of old nr_queues hack for kdump kernels (Ming)
- Support for async deletion of ublk (Ming)
- Improve IRQ bio recycling (Pavel)
- Factor in CPU capacity for remote vs local completion (Qais)
- Add shared_tags configfs entry for null_blk (Shin'ichiro
- Fix for a regression in page refcounts introduced by the folio
unification (Tony)
- Misc fixes and cleanups (Arnd, Colin, John, Kunwu, Li, Navid,
Ricardo, Roman, Tang, Uwe)
* tag 'for-6.9/block-20240310' of git://git.kernel.dk/linux: (221 commits)
block: partitions: only define function mac_fix_string for CONFIG_PPC_PMAC
block/swim: Convert to platform remove callback returning void
cdrom: gdrom: Convert to platform remove callback returning void
block: remove disk_stack_limits
md: remove mddev->queue
md: don't initialize queue limits
md/raid10: use the atomic queue limit update APIs
md/raid5: use the atomic queue limit update APIs
md/raid1: use the atomic queue limit update APIs
md/raid0: use the atomic queue limit update APIs
md: add queue limit helpers
md: add a mddev_is_dm helper
md: add a mddev_add_trace_msg helper
md: add a mddev_trace_remap helper
bcache: move calculation of stripe_size and io_opt into bcache_device_init
virtio_blk: Do not use disk_set_max_open/active_zones()
aoe: fix the potential use-after-free problem in aoecmd_cfg_pkts
block: move capacity validation to blkpg_do_ioctl()
block: prevent division by zero in blk_rq_stat_sum()
drbd: atomically update queue limits in drbd_reconsider_queue_parameters
...
diff --git a/block/blk.h b/block/blk.h
index f02b25f..a19b7b4 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -4,6 +4,8 @@
#include <linux/blk-crypto.h>
#include <linux/memblock.h> /* for max_pfn/max_low_pfn */
+#include <linux/sched/sysctl.h>
+#include <linux/timekeeping.h>
#include <xen/xen.h>
#include "blk-crypto-internal.h"
@@ -70,6 +72,18 @@ static inline int bio_queue_enter(struct bio *bio)
return __bio_queue_enter(q, bio);
}
+static inline void blk_wait_io(struct completion *done)
+{
+ /* Prevent hang_check timer from firing at us during very long I/O */
+ unsigned long timeout = sysctl_hung_task_timeout_secs * HZ / 2;
+
+ if (timeout)
+ while (!wait_for_completion_io_timeout(done, timeout))
+ ;
+ else
+ wait_for_completion_io(done);
+}
+
#define BIO_INLINE_VECS 4
struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs,
gfp_t gfp_mask);
@@ -329,7 +343,7 @@ void blk_rq_set_mixed_merge(struct request *rq);
bool blk_rq_merge_ok(struct request *rq, struct bio *bio);
enum elv_merge blk_try_merge(struct request *rq, struct bio *bio);
-void blk_set_default_limits(struct queue_limits *lim);
+int blk_set_default_limits(struct queue_limits *lim);
int blk_dev_init(void);
/*
@@ -447,7 +461,7 @@ static inline void bio_release_page(struct bio *bio, struct page *page)
unpin_user_page(page);
}
-struct request_queue *blk_alloc_queue(int node_id);
+struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id);
int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode);
@@ -516,8 +530,75 @@ static inline int req_ref_read(struct request *req)
return atomic_read(&req->ref);
}
+static inline u64 blk_time_get_ns(void)
+{
+ struct blk_plug *plug = current->plug;
+
+ if (!plug)
+ return ktime_get_ns();
+
+ /*
+ * 0 could very well be a valid time, but rather than flag "this is
+ * a valid timestamp" separately, just accept that we'll do an extra
+ * ktime_get_ns() if we just happen to get 0 as the current time.
+ */
+ if (!plug->cur_ktime) {
+ plug->cur_ktime = ktime_get_ns();
+ current->flags |= PF_BLOCK_TS;
+ }
+ return plug->cur_ktime;
+}
+
+static inline ktime_t blk_time_get(void)
+{
+ return ns_to_ktime(blk_time_get_ns());
+}
+
+/*
+ * 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)
+
+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) |
+ (blk_time_get_ns() & BIO_ISSUE_TIME_MASK) |
+ ((u64)size << BIO_ISSUE_SIZE_SHIFT));
+}
+
void bdev_release(struct file *bdev_file);
int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder,
const struct blk_holder_ops *hops, struct file *bdev_file);
int bdev_permission(dev_t dev, blk_mode_t mode, void *holder);
+
#endif /* BLK_INTERNAL_H */
