May 2022 - Linux-stable-mirror

[PATCH 3/4] bcache: remove incremental dirty sector counting for bch_sectors_dirty_init()

by Coly Li

After making bch_sectors_dirty_init() being multithreaded, the existing incremental dirty sector counting in bch_root_node_dirty_init() doesn't release btree occupation after iterating 500000 (INIT_KEYS_EACH_TIME) bkeys. Because a read lock is added on btree root node to prevent the btree to be split during the dirty sectors counting, other I/O requester has no chance to gain the write lock even restart bcache_btree(). That is to say, the incremental dirty sectors counting is incompatible to the multhreaded bch_sectors_dirty_init(). We have to choose one and drop another one. In my testing, with 512 bytes random writes, I generate 1.2T dirty data and a btree with 400K nodes. With single thread and incremental dirty sectors counting, it takes 30+ minites to register the backing device. And with multithreaded dirty sectors counting, the backing device registration can be accomplished within 2 minutes. The 30+ minutes V.S. 2- minutes difference makes me decide to keep multithreaded bch_sectors_dirty_init() and drop the incremental dirty sectors counting. This is what this patch does. But INIT_KEYS_EACH_TIME is kept, in sectors_dirty_init_fn() the CPU will be released by cond_resched() after every INIT_KEYS_EACH_TIME keys iterated. This is to avoid the watchdog reports a bogus soft lockup warning. Fixes: b144e45fc576 ("bcache: make bch_sectors_dirty_init() to be multithreaded") Signed-off-by: Coly Li <colyli(a)suse.de> Cc: stable(a)vger.kernel.org --- drivers/md/bcache/writeback.c | 41 +++++++++++------------------------ 1 file changed, 13 insertions(+), 28 deletions(-) diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index d24c09490f8e..75b71199800d 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -805,13 +805,11 @@ static int bch_writeback_thread(void *arg) /* Init */ #define INIT_KEYS_EACH_TIME 500000 -#define INIT_KEYS_SLEEP_MS 100 struct sectors_dirty_init { struct btree_op op; unsigned int inode; size_t count; - struct bkey start; }; static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b, @@ -827,11 +825,8 @@ static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b, KEY_START(k), KEY_SIZE(k)); op->count++; - if (atomic_read(&b->c->search_inflight) && - !(op->count % INIT_KEYS_EACH_TIME)) { - bkey_copy_key(&op->start, k); - return -EAGAIN; - } + if (!(op->count % INIT_KEYS_EACH_TIME)) + cond_resched(); return MAP_CONTINUE; } @@ -846,24 +841,16 @@ static int bch_root_node_dirty_init(struct cache_set *c, bch_btree_op_init(&op.op, -1); op.inode = d->id; op.count = 0; - op.start = KEY(op.inode, 0, 0); - - do { - ret = bcache_btree(map_keys_recurse, - k, - c->root, - &op.op, - &op.start, - sectors_dirty_init_fn, - 0); - if (ret == -EAGAIN) - schedule_timeout_interruptible( - msecs_to_jiffies(INIT_KEYS_SLEEP_MS)); - else if (ret < 0) { - pr_warn("sectors dirty init failed, ret=%d!\n", ret); - break; - } - } while (ret == -EAGAIN); + + ret = bcache_btree(map_keys_recurse, + k, + c->root, + &op.op, + &KEY(op.inode, 0, 0), + sectors_dirty_init_fn, + 0); + if (ret < 0) + pr_warn("sectors dirty init failed, ret=%d!\n", ret); return ret; } @@ -907,7 +894,6 @@ static int bch_dirty_init_thread(void *arg) goto out; } skip_nr--; - cond_resched(); } if (p) { @@ -917,7 +903,6 @@ static int bch_dirty_init_thread(void *arg) p = NULL; prev_idx = cur_idx; - cond_resched(); } out: @@ -956,11 +941,11 @@ void bch_sectors_dirty_init(struct bcache_device *d) bch_btree_op_init(&op.op, -1); op.inode = d->id; op.count = 0; - op.start = KEY(op.inode, 0, 0); for_each_key_filter(&c->root->keys, k, &iter, bch_ptr_invalid) sectors_dirty_init_fn(&op.op, c->root, k); + rw_unlock(0, c->root); return; } -- 2.35.3

3 years, 1 month

1
0
0 0

[PATCH 2/4] bcache: improve multithreaded bch_sectors_dirty_init()

by Coly Li

Commit b144e45fc576 ("bcache: make bch_sectors_dirty_init() to be multithreaded") makes bch_sectors_dirty_init() to be much faster when counting dirty sectors by iterating all dirty keys in the btree. But it isn't in ideal shape yet, still can be improved. This patch does the following changes to improve current parallel dirty keys iteration on the btree, - Add read lock to root node when multiple threads iterating the btree, to prevent the root node gets split by I/Os from other registered bcache devices. - Remove local variable "char name[32]" and generate kernel thread name string directly when calling kthread_run(). - Allocate "struct bch_dirty_init_state state" directly on stack and avoid the unnecessary dynamic memory allocation for it. - Increase &state->started to count created kernel thread after it succeeds to create. - When wait for all dirty key counting threads to finish, use wait_event() to replace wait_event_interruptible(). With the above changes, the code is more clear, and some potential error conditions are avoided. Fixes: b144e45fc576 ("bcache: make bch_sectors_dirty_init() to be multithreaded") Signed-off-by: Coly Li <colyli(a)suse.de> Cc: stable(a)vger.kernel.org --- drivers/md/bcache/writeback.c | 62 ++++++++++++++--------------------- 1 file changed, 25 insertions(+), 37 deletions(-) diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 9ee0005874cd..d24c09490f8e 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -948,10 +948,10 @@ void bch_sectors_dirty_init(struct bcache_device *d) struct btree_iter iter; struct sectors_dirty_init op; struct cache_set *c = d->c; - struct bch_dirty_init_state *state; - char name[32]; + struct bch_dirty_init_state state; /* Just count root keys if no leaf node */ + rw_lock(0, c->root, c->root->level); if (c->root->level == 0) { bch_btree_op_init(&op.op, -1); op.inode = d->id; @@ -961,54 +961,42 @@ void bch_sectors_dirty_init(struct bcache_device *d) for_each_key_filter(&c->root->keys, k, &iter, bch_ptr_invalid) sectors_dirty_init_fn(&op.op, c->root, k); + rw_unlock(0, c->root); return; } - state = kzalloc(sizeof(struct bch_dirty_init_state), GFP_KERNEL); - if (!state) { - pr_warn("sectors dirty init failed: cannot allocate memory\n"); - return; - } - - state->c = c; - state->d = d; - state->total_threads = bch_btre_dirty_init_thread_nr(); - state->key_idx = 0; - spin_lock_init(&state->idx_lock); - atomic_set(&state->started, 0); - atomic_set(&state->enough, 0); - init_waitqueue_head(&state->wait); - - for (i = 0; i < state->total_threads; i++) { - /* Fetch latest state->enough earlier */ + state.c = c; + state.d = d; + state.total_threads = bch_btre_dirty_init_thread_nr(); + state.key_idx = 0; + spin_lock_init(&state.idx_lock); + atomic_set(&state.started, 0); + atomic_set(&state.enough, 0); + init_waitqueue_head(&state.wait); + + for (i = 0; i < state.total_threads; i++) { + /* Fetch latest state.enough earlier */ smp_mb__before_atomic(); - if (atomic_read(&state->enough)) + if (atomic_read(&state.enough)) break; - state->infos[i].state = state; - atomic_inc(&state->started); - snprintf(name, sizeof(name), "bch_dirty_init[%d]", i); - - state->infos[i].thread = - kthread_run(bch_dirty_init_thread, - &state->infos[i], - name); - if (IS_ERR(state->infos[i].thread)) { + state.infos[i].state = &state; + state.infos[i].thread = + kthread_run(bch_dirty_init_thread, &state.infos[i], + "bch_dirtcnt[%d]", i); + if (IS_ERR(state.infos[i].thread)) { pr_err("fails to run thread bch_dirty_init[%d]\n", i); for (--i; i >= 0; i--) - kthread_stop(state->infos[i].thread); + kthread_stop(state.infos[i].thread); goto out; } + atomic_inc(&state.started); } - /* - * Must wait for all threads to stop. - */ - wait_event_interruptible(state->wait, - atomic_read(&state->started) == 0); - out: - kfree(state); + /* Must wait for all threads to stop. */ + wait_event(state.wait, atomic_read(&state.started) == 0); + rw_unlock(0, c->root); } void bch_cached_dev_writeback_init(struct cached_dev *dc) -- 2.35.3

3 years, 1 month

1
0
0 0

[PATCH 1/4] bcache: improve multithreaded bch_btree_check()

by Coly Li

Commit 8e7102273f59 ("bcache: make bch_btree_check() to be multithreaded") makes bch_btree_check() to be much faster when checking all btree nodes during cache device registration. But it isn't in ideal shap yet, still can be improved. This patch does the following thing to improve current parallel btree nodes check by multiple threads in bch_btree_check(), - Add read lock to root node while checking all the btree nodes with multiple threads. Although currently it is not mandatory but it is good to have a read lock in code logic. - Remove local variable 'char name[32]', and generate kernel thread name string directly when calling kthread_run(). - Allocate local variable "struct btree_check_state check_state" on the stack and avoid unnecessary dynamic memory allocation for it. - Increase check_state->started to count created kernel thread after it succeeds to create. - When wait for all checking kernel threads to finish, use wait_event() to replace wait_event_interruptible(). With this change, the code is more clear, and some potential error conditions are avoided. Fixes: 8e7102273f59 ("bcache: make bch_btree_check() to be multithreaded") Signed-off-by: Coly Li <colyli(a)suse.de> Cc: stable(a)vger.kernel.org --- drivers/md/bcache/btree.c | 58 ++++++++++++++++++--------------------- 1 file changed, 26 insertions(+), 32 deletions(-) diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index ad9f16689419..2362bb8ef6d1 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -2006,8 +2006,7 @@ int bch_btree_check(struct cache_set *c) int i; struct bkey *k = NULL; struct btree_iter iter; - struct btree_check_state *check_state; - char name[32]; + struct btree_check_state check_state; /* check and mark root node keys */ for_each_key_filter(&c->root->keys, k, &iter, bch_ptr_invalid) @@ -2018,63 +2017,58 @@ int bch_btree_check(struct cache_set *c) if (c->root->level == 0) return 0; - check_state = kzalloc(sizeof(struct btree_check_state), GFP_KERNEL); - if (!check_state) - return -ENOMEM; - - check_state->c = c; - check_state->total_threads = bch_btree_chkthread_nr(); - check_state->key_idx = 0; - spin_lock_init(&check_state->idx_lock); - atomic_set(&check_state->started, 0); - atomic_set(&check_state->enough, 0); - init_waitqueue_head(&check_state->wait); + check_state.c = c; + check_state.total_threads = bch_btree_chkthread_nr(); + check_state.key_idx = 0; + spin_lock_init(&check_state.idx_lock); + atomic_set(&check_state.started, 0); + atomic_set(&check_state.enough, 0); + init_waitqueue_head(&check_state.wait); + rw_lock(0, c->root, c->root->level); /* * Run multiple threads to check btree nodes in parallel, - * if check_state->enough is non-zero, it means current + * if check_state.enough is non-zero, it means current * running check threads are enough, unncessary to create * more. */ - for (i = 0; i < check_state->total_threads; i++) { - /* fetch latest check_state->enough earlier */ + for (i = 0; i < check_state.total_threads; i++) { + /* fetch latest check_state.enough earlier */ smp_mb__before_atomic(); - if (atomic_read(&check_state->enough)) + if (atomic_read(&check_state.enough)) break; - check_state->infos[i].result = 0; - check_state->infos[i].state = check_state; - snprintf(name, sizeof(name), "bch_btrchk[%u]", i); - atomic_inc(&check_state->started); + check_state.infos[i].result = 0; + check_state.infos[i].state = &check_state; - check_state->infos[i].thread = + check_state.infos[i].thread = kthread_run(bch_btree_check_thread, - &check_state->infos[i], - name); - if (IS_ERR(check_state->infos[i].thread)) { + &check_state.infos[i], + "bch_btrchk[%d]", i); + if (IS_ERR(check_state.infos[i].thread)) { pr_err("fails to run thread bch_btrchk[%d]\n", i); for (--i; i >= 0; i--) - kthread_stop(check_state->infos[i].thread); + kthread_stop(check_state.infos[i].thread); ret = -ENOMEM; goto out; } + atomic_inc(&check_state.started); } /* * Must wait for all threads to stop. */ - wait_event_interruptible(check_state->wait, - atomic_read(&check_state->started) == 0); + wait_event(check_state.wait, atomic_read(&check_state.started) == 0); - for (i = 0; i < check_state->total_threads; i++) { - if (check_state->infos[i].result) { - ret = check_state->infos[i].result; + for (i = 0; i < check_state.total_threads; i++) { + if (check_state.infos[i].result) { + ret = check_state.infos[i].result; goto out; } } out: - kfree(check_state); + rw_unlock(0, c->root); return ret; } -- 2.35.3

3 years, 1 month

1
0
0 0

May God bless you In Jesus name Amen!!!

by Mrs Elodie Antoine

Dear Altruist, With confidence that this message will find you in good fate, i wish to share with you my last wish. I have a terminal ailment and writing from my hospital bed. I got your contact from humanitarian event with hope you have the welfare of less privilege around the globe at heart. I wish to submit my remaining fund the sum of ($ 6,200,000.00 Dollars) to you for continuation of charity service. My life is no longer promising as a result of cancer. I need your urgent cooperation for more details. Thanks in advance for your kind heart and quick response to this gesture. Yours faithfully, Elodie Antoine.

3 years, 1 month

1
0
0 0

VERY VERY URGENT,

by Mr.Azzedine Guessous

Good days to you Please kindly accept my apology for sending you this email without your consent i am Mr.Azzedine Guessous,The director in charge of auditing and accounting section of Bank Of Africa Ouagadougou Burkina-Faso in West Africa, I am writing to request your assistance to transfer the sum of ( $18.6 Million US DOLLARS) feel free to contact me here (azzedineguessous1(a)gmail.com) for more clarifications if you are really interested in my proposal Have a nice day Mr.Azzedine Guessous

3 years, 1 month

1
0
0 0

5.4.188 and later: massive performance regression with nfsd

by Wolfgang Walter

Hi, starting with 5.4.188 wie see a massive performance regression on our nfs-server. It basically is serving requests very very slowly with cpu utilization of 100% (with 5.4.187 and earlier it is 10%) so that it is unusable as a fileserver. The culprit are commits (or one of it): c32f1041382a88b17da5736886da4a492353a1bb "nfsd: cleanup nfsd_file_lru_dispose()" 628adfa21815f74c04724abc85847f24b5dd1645 "nfsd: Containerise filecache laundrette" (upstream 36ebbdb96b694dd9c6b25ad98f2bbd263d022b63 and 9542e6a643fc69d528dfb3303f145719c61d3050) If I revert them in v5.4.192 the kernel works as before and performance is ok again. I did not try to revert them one by one as any disruption of our nfs-server is a severe problem for us and I'm not sure if they are related. 5.10 and 5.15 both always performed very badly on our nfs-server in a similar way so we were stuck with 5.4. I now think this is because of 36ebbdb96b694dd9c6b25ad98f2bbd263d022b63 and/or 9542e6a643fc69d528dfb3303f145719c61d3050 though I didn't tried to revert them in 5.15 yet. Regards, -- Wolfgang Walter Studentenwerk München Anstalt des öffentlichen Rechts

3 years, 1 month

5
18
0 0

[PATCH] drm/bridge: fix anx6345 power up sequence

by Torsten Duwe

Align the power-up sequence with the known-good procedure documented in [1]: un-swap dvdd12 and dvdd25, and allow a little extra time for them to settle before de-asserting reset. Fixes: 6aa192698089b ("drm/bridge: Add Analogix anx6345 support") [1] https://github.com/OLIMEX/DIY-LAPTOP/blob/master/ HARDWARE/A64-TERES/TERES-PCB1-A64-MAIN/Rev.C/TERES_PCB1-A64-MAIN_Rev.C.pdf (page 5, blue comment down left) Reported-by: Harald Geyer <harald(a)ccbib.org> Signed-off-by: Torsten Duwe <duwe(a)lst.de> Cc: stable(a)vger.kernel.org --- This fixes the problem that e.g. X screensaver turns the screen black, and it stays black until the next reboot; definitely on the Teres-I, probably on the pinebook64, too. --- a/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c +++ b/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c @@ -309,27 +309,27 @@ static void anx6345_poweron(struct anx63 gpiod_set_value_cansleep(anx6345->gpiod_reset, 1); usleep_range(1000, 2000); - err = regulator_enable(anx6345->dvdd12); + err = regulator_enable(anx6345->dvdd25); if (err) { - DRM_ERROR("Failed to enable dvdd12 regulator: %d\n", + DRM_ERROR("Failed to enable dvdd25 regulator: %d\n", err); return; } - /* T1 - delay between VDD12 and VDD25 should be 0-2ms */ + /* T1 - delay between VDD25 and VDD12 should be 0-2ms */ usleep_range(1000, 2000); - err = regulator_enable(anx6345->dvdd25); + err = regulator_enable(anx6345->dvdd12); if (err) { - DRM_ERROR("Failed to enable dvdd25 regulator: %d\n", + DRM_ERROR("Failed to enable dvdd12 regulator: %d\n", err); return; } /* T2 - delay between RESETN and all power rail stable, - * should be 2-5ms + * should be at least 2-5ms, 10ms to be safe. */ - usleep_range(2000, 5000); + usleep_range(9000, 11000); gpiod_set_value_cansleep(anx6345->gpiod_reset, 0);

3 years, 1 month

2
6
0 0

[PATCH stable 4.19 0/3] MMC timeout back ports

by Florian Fainelli

These 3 commits from upstream allow us to have more fine grained control over the MMC command timeouts and this solves the following timeouts that we have seen on our systems across suspend/resume cycles: [ 14.907496] usb usb2: root hub lost power or was reset [ 15.216232] usb 1-1: reset high-speed USB device number 2 using xhci-hcd [ 15.485812] bcmgenet 8f00000.ethernet eth0: Link is Down [ 15.525328] mmc1: error -110 doing runtime resume [ 15.531864] OOM killer enabled. Thanks! Ulf Hansson (3): mmc: core: Specify timeouts for BKOPS and CACHE_FLUSH for eMMC mmc: block: Use generic_cmd6_time when modifying INAND_CMD38_ARG_EXT_CSD mmc: core: Default to generic_cmd6_time as timeout in __mmc_switch() drivers/mmc/core/block.c | 6 +++--- drivers/mmc/core/mmc_ops.c | 25 +++++++++++++------------ 2 files changed, 16 insertions(+), 15 deletions(-) -- 2.25.1

3 years, 1 month

2
6
0 0

Greetings

by paul michael

Every time I retest your email, it tells me to check with my ISP or Log onto incoming mail server (POP3): Your e-mail server rejected . Kindly verify if your email is still valid for us to talk.

3 years, 1 month

1
0
0 0

FAILED: patch "[PATCH] libceph: fix potential use-after-free on linger ping and" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 75dbb685f4e8786c33ddef8279bab0eadfb0731f Mon Sep 17 00:00:00 2001 From: Ilya Dryomov <idryomov(a)gmail.com> Date: Sat, 14 May 2022 12:16:47 +0200 Subject: [PATCH] libceph: fix potential use-after-free on linger ping and resends request_reinit() is not only ugly as the comment rightfully suggests, but also unsafe. Even though it is called with osdc->lock held for write in all cases, resetting the OSD request refcount can still race with handle_reply() and result in use-after-free. Taking linger ping as an example: handle_timeout thread handle_reply thread down_read(&osdc->lock) req = lookup_request(...) ... finish_request(req) # unregisters up_read(&osdc->lock) __complete_request(req) linger_ping_cb(req) # req->r_kref == 2 because handle_reply still holds its ref down_write(&osdc->lock) send_linger_ping(lreq) req = lreq->ping_req # same req # cancel_linger_request is NOT # called - handle_reply already # unregistered request_reinit(req) WARN_ON(req->r_kref != 1) # fires request_init(req) kref_init(req->r_kref) # req->r_kref == 1 after kref_init ceph_osdc_put_request(req) kref_put(req->r_kref) # req->r_kref == 0 after kref_put, req is freed <further req initialization/use> !!! This happens because send_linger_ping() always (re)uses the same OSD request for watch ping requests, relying on cancel_linger_request() to unregister it from the OSD client and rip its messages out from the messenger. send_linger() does the same for watch/notify registration and watch reconnect requests. Unfortunately cancel_request() doesn't guarantee that after it returns the OSD client would be completely done with the OSD request -- a ref could still be held and the callback (if specified) could still be invoked too. The original motivation for request_reinit() was inability to deal with allocation failures in send_linger() and send_linger_ping(). Switching to using osdc->req_mempool (currently only used by CephFS) respects that and allows us to get rid of request_reinit(). Cc: stable(a)vger.kernel.org Signed-off-by: Ilya Dryomov <idryomov(a)gmail.com> Reviewed-by: Xiubo Li <xiubli(a)redhat.com> Acked-by: Jeff Layton <jlayton(a)kernel.org> diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 3431011f364d..cba8a6ffc329 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -287,6 +287,9 @@ struct ceph_osd_linger_request { rados_watcherrcb_t errcb; void *data; + struct ceph_pagelist *request_pl; + struct page **notify_id_pages; + struct page ***preply_pages; size_t *preply_len; }; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 83eb97c94e83..4b88f2a4a6e2 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -537,43 +537,6 @@ static void request_init(struct ceph_osd_request *req) target_init(&req->r_t); } -/* - * This is ugly, but it allows us to reuse linger registration and ping - * requests, keeping the structure of the code around send_linger{_ping}() - * reasonable. Setting up a min_nr=2 mempool for each linger request - * and dealing with copying ops (this blasts req only, watch op remains - * intact) isn't any better. - */ -static void request_reinit(struct ceph_osd_request *req) -{ - struct ceph_osd_client *osdc = req->r_osdc; - bool mempool = req->r_mempool; - unsigned int num_ops = req->r_num_ops; - u64 snapid = req->r_snapid; - struct ceph_snap_context *snapc = req->r_snapc; - bool linger = req->r_linger; - struct ceph_msg *request_msg = req->r_request; - struct ceph_msg *reply_msg = req->r_reply; - - dout("%s req %p\n", __func__, req); - WARN_ON(kref_read(&req->r_kref) != 1); - request_release_checks(req); - - WARN_ON(kref_read(&request_msg->kref) != 1); - WARN_ON(kref_read(&reply_msg->kref) != 1); - target_destroy(&req->r_t); - - request_init(req); - req->r_osdc = osdc; - req->r_mempool = mempool; - req->r_num_ops = num_ops; - req->r_snapid = snapid; - req->r_snapc = snapc; - req->r_linger = linger; - req->r_request = request_msg; - req->r_reply = reply_msg; -} - struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, struct ceph_snap_context *snapc, unsigned int num_ops, @@ -918,14 +881,30 @@ EXPORT_SYMBOL(osd_req_op_xattr_init); * @watch_opcode: CEPH_OSD_WATCH_OP_* */ static void osd_req_op_watch_init(struct ceph_osd_request *req, int which, - u64 cookie, u8 watch_opcode) + u8 watch_opcode, u64 cookie, u32 gen) { struct ceph_osd_req_op *op; op = osd_req_op_init(req, which, CEPH_OSD_OP_WATCH, 0); op->watch.cookie = cookie; op->watch.op = watch_opcode; - op->watch.gen = 0; + op->watch.gen = gen; +} + +/* + * prot_ver, timeout and notify payload (may be empty) should already be + * encoded in @request_pl + */ +static void osd_req_op_notify_init(struct ceph_osd_request *req, int which, + u64 cookie, struct ceph_pagelist *request_pl) +{ + struct ceph_osd_req_op *op; + + op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0); + op->notify.cookie = cookie; + + ceph_osd_data_pagelist_init(&op->notify.request_data, request_pl); + op->indata_len = request_pl->length; } /* @@ -2731,10 +2710,13 @@ static void linger_release(struct kref *kref) WARN_ON(!list_empty(&lreq->pending_lworks)); WARN_ON(lreq->osd); - if (lreq->reg_req) - ceph_osdc_put_request(lreq->reg_req); - if (lreq->ping_req) - ceph_osdc_put_request(lreq->ping_req); + if (lreq->request_pl) + ceph_pagelist_release(lreq->request_pl); + if (lreq->notify_id_pages) + ceph_release_page_vector(lreq->notify_id_pages, 1); + + ceph_osdc_put_request(lreq->reg_req); + ceph_osdc_put_request(lreq->ping_req); target_destroy(&lreq->t); kfree(lreq); } @@ -3003,6 +2985,12 @@ static void linger_commit_cb(struct ceph_osd_request *req) struct ceph_osd_linger_request *lreq = req->r_priv; mutex_lock(&lreq->lock); + if (req != lreq->reg_req) { + dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", + __func__, lreq, lreq->linger_id, req, lreq->reg_req); + goto out; + } + dout("%s lreq %p linger_id %llu result %d\n", __func__, lreq, lreq->linger_id, req->r_result); linger_reg_commit_complete(lreq, req->r_result); @@ -3026,6 +3014,7 @@ static void linger_commit_cb(struct ceph_osd_request *req) } } +out: mutex_unlock(&lreq->lock); linger_put(lreq); } @@ -3048,6 +3037,12 @@ static void linger_reconnect_cb(struct ceph_osd_request *req) struct ceph_osd_linger_request *lreq = req->r_priv; mutex_lock(&lreq->lock); + if (req != lreq->reg_req) { + dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", + __func__, lreq, lreq->linger_id, req, lreq->reg_req); + goto out; + } + dout("%s lreq %p linger_id %llu result %d last_error %d\n", __func__, lreq, lreq->linger_id, req->r_result, lreq->last_error); if (req->r_result < 0) { @@ -3057,46 +3052,64 @@ static void linger_reconnect_cb(struct ceph_osd_request *req) } } +out: mutex_unlock(&lreq->lock); linger_put(lreq); } static void send_linger(struct ceph_osd_linger_request *lreq) { - struct ceph_osd_request *req = lreq->reg_req; - struct ceph_osd_req_op *op = &req->r_ops[0]; + struct ceph_osd_client *osdc = lreq->osdc; + struct ceph_osd_request *req; + int ret; - verify_osdc_wrlocked(req->r_osdc); + verify_osdc_wrlocked(osdc); + mutex_lock(&lreq->lock); dout("%s lreq %p linger_id %llu\n", __func__, lreq, lreq->linger_id); - if (req->r_osd) - cancel_linger_request(req); + if (lreq->reg_req) { + if (lreq->reg_req->r_osd) + cancel_linger_request(lreq->reg_req); + ceph_osdc_put_request(lreq->reg_req); + } + + req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO); + BUG_ON(!req); - request_reinit(req); target_copy(&req->r_t, &lreq->t); req->r_mtime = lreq->mtime; - mutex_lock(&lreq->lock); if (lreq->is_watch && lreq->committed) { - WARN_ON(op->op != CEPH_OSD_OP_WATCH || - op->watch.cookie != lreq->linger_id); - op->watch.op = CEPH_OSD_WATCH_OP_RECONNECT; - op->watch.gen = ++lreq->register_gen; + osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_RECONNECT, + lreq->linger_id, ++lreq->register_gen); dout("lreq %p reconnect register_gen %u\n", lreq, - op->watch.gen); + req->r_ops[0].watch.gen); req->r_callback = linger_reconnect_cb; } else { - if (!lreq->is_watch) + if (lreq->is_watch) { + osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_WATCH, + lreq->linger_id, 0); + } else { lreq->notify_id = 0; - else - WARN_ON(op->watch.op != CEPH_OSD_WATCH_OP_WATCH); + + refcount_inc(&lreq->request_pl->refcnt); + osd_req_op_notify_init(req, 0, lreq->linger_id, + lreq->request_pl); + ceph_osd_data_pages_init( + osd_req_op_data(req, 0, notify, response_data), + lreq->notify_id_pages, PAGE_SIZE, 0, false, false); + } dout("lreq %p register\n", lreq); req->r_callback = linger_commit_cb; } - mutex_unlock(&lreq->lock); + + ret = ceph_osdc_alloc_messages(req, GFP_NOIO); + BUG_ON(ret); req->r_priv = linger_get(lreq); req->r_linger = true; + lreq->reg_req = req; + mutex_unlock(&lreq->lock); submit_request(req, true); } @@ -3106,6 +3119,12 @@ static void linger_ping_cb(struct ceph_osd_request *req) struct ceph_osd_linger_request *lreq = req->r_priv; mutex_lock(&lreq->lock); + if (req != lreq->ping_req) { + dout("%s lreq %p linger_id %llu unknown req (%p != %p)\n", + __func__, lreq, lreq->linger_id, req, lreq->ping_req); + goto out; + } + dout("%s lreq %p linger_id %llu result %d ping_sent %lu last_error %d\n", __func__, lreq, lreq->linger_id, req->r_result, lreq->ping_sent, lreq->last_error); @@ -3121,6 +3140,7 @@ static void linger_ping_cb(struct ceph_osd_request *req) lreq->register_gen, req->r_ops[0].watch.gen); } +out: mutex_unlock(&lreq->lock); linger_put(lreq); } @@ -3128,8 +3148,8 @@ static void linger_ping_cb(struct ceph_osd_request *req) static void send_linger_ping(struct ceph_osd_linger_request *lreq) { struct ceph_osd_client *osdc = lreq->osdc; - struct ceph_osd_request *req = lreq->ping_req; - struct ceph_osd_req_op *op = &req->r_ops[0]; + struct ceph_osd_request *req; + int ret; if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSERD)) { dout("%s PAUSERD\n", __func__); @@ -3141,19 +3161,26 @@ static void send_linger_ping(struct ceph_osd_linger_request *lreq) __func__, lreq, lreq->linger_id, lreq->ping_sent, lreq->register_gen); - if (req->r_osd) - cancel_linger_request(req); + if (lreq->ping_req) { + if (lreq->ping_req->r_osd) + cancel_linger_request(lreq->ping_req); + ceph_osdc_put_request(lreq->ping_req); + } - request_reinit(req); - target_copy(&req->r_t, &lreq->t); + req = ceph_osdc_alloc_request(osdc, NULL, 1, true, GFP_NOIO); + BUG_ON(!req); - WARN_ON(op->op != CEPH_OSD_OP_WATCH || - op->watch.cookie != lreq->linger_id || - op->watch.op != CEPH_OSD_WATCH_OP_PING); - op->watch.gen = lreq->register_gen; + target_copy(&req->r_t, &lreq->t); + osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_PING, lreq->linger_id, + lreq->register_gen); req->r_callback = linger_ping_cb; + + ret = ceph_osdc_alloc_messages(req, GFP_NOIO); + BUG_ON(ret); + req->r_priv = linger_get(lreq); req->r_linger = true; + lreq->ping_req = req; ceph_osdc_get_request(req); account_request(req); @@ -3169,12 +3196,6 @@ static void linger_submit(struct ceph_osd_linger_request *lreq) down_write(&osdc->lock); linger_register(lreq); - if (lreq->is_watch) { - lreq->reg_req->r_ops[0].watch.cookie = lreq->linger_id; - lreq->ping_req->r_ops[0].watch.cookie = lreq->linger_id; - } else { - lreq->reg_req->r_ops[0].notify.cookie = lreq->linger_id; - } calc_target(osdc, &lreq->t, false); osd = lookup_create_osd(osdc, lreq->t.osd, true); @@ -3206,9 +3227,9 @@ static void cancel_linger_map_check(struct ceph_osd_linger_request *lreq) */ static void __linger_cancel(struct ceph_osd_linger_request *lreq) { - if (lreq->is_watch && lreq->ping_req->r_osd) + if (lreq->ping_req && lreq->ping_req->r_osd) cancel_linger_request(lreq->ping_req); - if (lreq->reg_req->r_osd) + if (lreq->reg_req && lreq->reg_req->r_osd) cancel_linger_request(lreq->reg_req); cancel_linger_map_check(lreq); unlink_linger(lreq->osd, lreq); @@ -4657,43 +4678,6 @@ void ceph_osdc_sync(struct ceph_osd_client *osdc) } EXPORT_SYMBOL(ceph_osdc_sync); -static struct ceph_osd_request * -alloc_linger_request(struct ceph_osd_linger_request *lreq) -{ - struct ceph_osd_request *req; - - req = ceph_osdc_alloc_request(lreq->osdc, NULL, 1, false, GFP_NOIO); - if (!req) - return NULL; - - ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid); - ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc); - return req; -} - -static struct ceph_osd_request * -alloc_watch_request(struct ceph_osd_linger_request *lreq, u8 watch_opcode) -{ - struct ceph_osd_request *req; - - req = alloc_linger_request(lreq); - if (!req) - return NULL; - - /* - * Pass 0 for cookie because we don't know it yet, it will be - * filled in by linger_submit(). - */ - osd_req_op_watch_init(req, 0, 0, watch_opcode); - - if (ceph_osdc_alloc_messages(req, GFP_NOIO)) { - ceph_osdc_put_request(req); - return NULL; - } - - return req; -} - /* * Returns a handle, caller owns a ref. */ @@ -4723,18 +4707,6 @@ ceph_osdc_watch(struct ceph_osd_client *osdc, lreq->t.flags = CEPH_OSD_FLAG_WRITE; ktime_get_real_ts64(&lreq->mtime); - lreq->reg_req = alloc_watch_request(lreq, CEPH_OSD_WATCH_OP_WATCH); - if (!lreq->reg_req) { - ret = -ENOMEM; - goto err_put_lreq; - } - - lreq->ping_req = alloc_watch_request(lreq, CEPH_OSD_WATCH_OP_PING); - if (!lreq->ping_req) { - ret = -ENOMEM; - goto err_put_lreq; - } - linger_submit(lreq); ret = linger_reg_commit_wait(lreq); if (ret) { @@ -4772,8 +4744,8 @@ int ceph_osdc_unwatch(struct ceph_osd_client *osdc, ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc); req->r_flags = CEPH_OSD_FLAG_WRITE; ktime_get_real_ts64(&req->r_mtime); - osd_req_op_watch_init(req, 0, lreq->linger_id, - CEPH_OSD_WATCH_OP_UNWATCH); + osd_req_op_watch_init(req, 0, CEPH_OSD_WATCH_OP_UNWATCH, + lreq->linger_id, 0); ret = ceph_osdc_alloc_messages(req, GFP_NOIO); if (ret) @@ -4859,35 +4831,6 @@ int ceph_osdc_notify_ack(struct ceph_osd_client *osdc, } EXPORT_SYMBOL(ceph_osdc_notify_ack); -static int osd_req_op_notify_init(struct ceph_osd_request *req, int which, - u64 cookie, u32 prot_ver, u32 timeout, - void *payload, u32 payload_len) -{ - struct ceph_osd_req_op *op; - struct ceph_pagelist *pl; - int ret; - - op = osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0); - op->notify.cookie = cookie; - - pl = ceph_pagelist_alloc(GFP_NOIO); - if (!pl) - return -ENOMEM; - - ret = ceph_pagelist_encode_32(pl, 1); /* prot_ver */ - ret |= ceph_pagelist_encode_32(pl, timeout); - ret |= ceph_pagelist_encode_32(pl, payload_len); - ret |= ceph_pagelist_append(pl, payload, payload_len); - if (ret) { - ceph_pagelist_release(pl); - return -ENOMEM; - } - - ceph_osd_data_pagelist_init(&op->notify.request_data, pl); - op->indata_len = pl->length; - return 0; -} - /* * @timeout: in seconds * @@ -4906,7 +4849,6 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc, size_t *preply_len) { struct ceph_osd_linger_request *lreq; - struct page **pages; int ret; WARN_ON(!timeout); @@ -4919,41 +4861,35 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc, if (!lreq) return -ENOMEM; - lreq->preply_pages = preply_pages; - lreq->preply_len = preply_len; - - ceph_oid_copy(&lreq->t.base_oid, oid); - ceph_oloc_copy(&lreq->t.base_oloc, oloc); - lreq->t.flags = CEPH_OSD_FLAG_READ; - - lreq->reg_req = alloc_linger_request(lreq); - if (!lreq->reg_req) { + lreq->request_pl = ceph_pagelist_alloc(GFP_NOIO); + if (!lreq->request_pl) { ret = -ENOMEM; goto out_put_lreq; } - /* - * Pass 0 for cookie because we don't know it yet, it will be - * filled in by linger_submit(). - */ - ret = osd_req_op_notify_init(lreq->reg_req, 0, 0, 1, timeout, - payload, payload_len); - if (ret) + ret = ceph_pagelist_encode_32(lreq->request_pl, 1); /* prot_ver */ + ret |= ceph_pagelist_encode_32(lreq->request_pl, timeout); + ret |= ceph_pagelist_encode_32(lreq->request_pl, payload_len); + ret |= ceph_pagelist_append(lreq->request_pl, payload, payload_len); + if (ret) { + ret = -ENOMEM; goto out_put_lreq; + } /* for notify_id */ - pages = ceph_alloc_page_vector(1, GFP_NOIO); - if (IS_ERR(pages)) { - ret = PTR_ERR(pages); + lreq->notify_id_pages = ceph_alloc_page_vector(1, GFP_NOIO); + if (IS_ERR(lreq->notify_id_pages)) { + ret = PTR_ERR(lreq->notify_id_pages); + lreq->notify_id_pages = NULL; goto out_put_lreq; } - ceph_osd_data_pages_init(osd_req_op_data(lreq->reg_req, 0, notify, - response_data), - pages, PAGE_SIZE, 0, false, true); - ret = ceph_osdc_alloc_messages(lreq->reg_req, GFP_NOIO); - if (ret) - goto out_put_lreq; + lreq->preply_pages = preply_pages; + lreq->preply_len = preply_len; + + ceph_oid_copy(&lreq->t.base_oid, oid); + ceph_oloc_copy(&lreq->t.base_oloc, oloc); + lreq->t.flags = CEPH_OSD_FLAG_READ; linger_submit(lreq); ret = linger_reg_commit_wait(lreq);

3 years, 1 month

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror May 2022