From 002ebddd695a53999550e241b71950f1aa0e1ac4 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Tue, 9 Sep 2025 13:11:20 +0200 Subject: pmdomain: core: Restore behaviour for disabling unused PM domains Recent changes to genpd prevents those PM domains being powered-on during initialization from being powered-off during the boot sequence. Based upon whether CONFIG_PM_CONFIG_PM_GENERIC_DOMAINS_OF is set of not, genpd relies on the sync_state mechanism or the genpd_power_off_unused() (which is a late_initcall_sync), to understand when it's okay to allow these PM domains to be powered-off. This new behaviour in genpd has lead to problems on different platforms. Let's therefore restore the behavior of genpd_power_off_unused(). Moreover, let's introduce GENPD_FLAG_NO_STAY_ON, to allow genpd OF providers to opt-out from the new behaviour. Link: https://lore.kernel.org/all/20250701114733.636510-1-ulf.hansson@linaro.org/ Reported-by: Geert Uytterhoeven Link: https://lore.kernel.org/all/20250902-rk3576-lockup-regression-v1-1-c4a0c9daeb00@collabora.com/ Reported-by: Nicolas Frattaroli Fixes: 0e789b491ba0 ("pmdomain: core: Leave powered-on genpds on until sync_state") Fixes: 13a4b7fb6260 ("pmdomain: core: Leave powered-on genpds on until late_initcall_sync") Tested-by: Heiko Stuebner Reviewed-by: Geert Uytterhoeven Tested-by: Geert Uytterhoeven Signed-off-by: Ulf Hansson --- include/linux/pm_domain.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index c84edf217819..f67a2cb7d781 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -115,6 +115,12 @@ struct dev_pm_domain_list { * genpd provider specific way, likely through a * parent device node. This flag makes genpd to * skip its internal support for this. + * + * GENPD_FLAG_NO_STAY_ON: For genpd OF providers a powered-on PM domain at + * initialization is prevented from being + * powered-off until the ->sync_state() callback is + * invoked. This flag informs genpd to allow a + * power-off without waiting for ->sync_state(). */ #define GENPD_FLAG_PM_CLK (1U << 0) #define GENPD_FLAG_IRQ_SAFE (1U << 1) @@ -126,6 +132,7 @@ struct dev_pm_domain_list { #define GENPD_FLAG_OPP_TABLE_FW (1U << 7) #define GENPD_FLAG_DEV_NAME_FW (1U << 8) #define GENPD_FLAG_NO_SYNC_STATE (1U << 9) +#define GENPD_FLAG_NO_STAY_ON (1U << 10) enum gpd_status { GENPD_STATE_ON = 0, /* PM domain is on */ -- cgit v1.2.3 From 2da6de30e60dd9bb14600eff1cc99df2fa2ddae3 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Mon, 8 Sep 2025 15:23:15 -0700 Subject: mm: folio_may_be_lru_cached() unless folio_test_large() mm/swap.c and mm/mlock.c agree to drain any per-CPU batch as soon as a large folio is added: so collect_longterm_unpinnable_folios() just wastes effort when calling lru_add_drain[_all]() on a large folio. But although there is good reason not to batch up PMD-sized folios, we might well benefit from batching a small number of low-order mTHPs (though unclear how that "small number" limitation will be implemented). So ask if folio_may_be_lru_cached() rather than !folio_test_large(), to insulate those particular checks from future change. Name preferred to "folio_is_batchable" because large folios can well be put on a batch: it's just the per-CPU LRU caches, drained much later, which need care. Marked for stable, to counter the increase in lru_add_drain_all()s from "mm/gup: check ref_count instead of lru before migration". Link: https://lkml.kernel.org/r/57d2eaf8-3607-f318-e0c5-be02dce61ad0@google.com Fixes: 9a4e9f3b2d73 ("mm: update get_user_pages_longterm to migrate pages allocated from CMA region") Signed-off-by: Hugh Dickins Suggested-by: David Hildenbrand Acked-by: David Hildenbrand Cc: "Aneesh Kumar K.V" Cc: Axel Rasmussen Cc: Chris Li Cc: Christoph Hellwig Cc: Jason Gunthorpe Cc: Johannes Weiner Cc: John Hubbard Cc: Keir Fraser Cc: Konstantin Khlebnikov Cc: Li Zhe Cc: Matthew Wilcox (Oracle) Cc: Peter Xu Cc: Rik van Riel Cc: Shivank Garg Cc: Vlastimil Babka Cc: Wei Xu Cc: Will Deacon Cc: yangge Cc: Yuanchu Xie Cc: Yu Zhao Cc: Signed-off-by: Andrew Morton --- include/linux/swap.h | 10 ++++++++++ mm/gup.c | 4 ++-- mm/mlock.c | 6 +++--- mm/swap.c | 2 +- 4 files changed, 16 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 2fe6ed2cc3fd..7012a0f758d8 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -385,6 +385,16 @@ void folio_add_lru_vma(struct folio *, struct vm_area_struct *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); +static inline bool folio_may_be_lru_cached(struct folio *folio) +{ + /* + * Holding PMD-sized folios in per-CPU LRU cache unbalances accounting. + * Holding small numbers of low-order mTHP folios in per-CPU LRU cache + * will be sensible, but nobody has implemented and tested that yet. + */ + return !folio_test_large(folio); +} + extern atomic_t lru_disable_count; static inline bool lru_cache_disabled(void) diff --git a/mm/gup.c b/mm/gup.c index b47066a54f52..0bc4d140fc07 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -2307,13 +2307,13 @@ static unsigned long collect_longterm_unpinnable_folios( continue; } - if (drained == 0 && + if (drained == 0 && folio_may_be_lru_cached(folio) && folio_ref_count(folio) != folio_expected_ref_count(folio) + 1) { lru_add_drain(); drained = 1; } - if (drained == 1 && + if (drained == 1 && folio_may_be_lru_cached(folio) && folio_ref_count(folio) != folio_expected_ref_count(folio) + 1) { lru_add_drain_all(); diff --git a/mm/mlock.c b/mm/mlock.c index a1d93ad33c6d..bb0776f5ef7c 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -255,7 +255,7 @@ void mlock_folio(struct folio *folio) folio_get(folio); if (!folio_batch_add(fbatch, mlock_lru(folio)) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } @@ -278,7 +278,7 @@ void mlock_new_folio(struct folio *folio) folio_get(folio); if (!folio_batch_add(fbatch, mlock_new(folio)) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } @@ -299,7 +299,7 @@ void munlock_folio(struct folio *folio) */ folio_get(folio); if (!folio_batch_add(fbatch, folio) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) mlock_folio_batch(fbatch); local_unlock(&mlock_fbatch.lock); } diff --git a/mm/swap.c b/mm/swap.c index 6ae2d5680574..b74ebe865dd9 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -192,7 +192,7 @@ static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch, local_lock(&cpu_fbatches.lock); if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || - folio_test_large(folio) || lru_cache_disabled()) + !folio_may_be_lru_cached(folio) || lru_cache_disabled()) folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn); if (disable_irq) -- cgit v1.2.3 From e6a0deb6fa5b0fc134ee2aa127d1cfc9456d8445 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Mon, 8 Sep 2025 13:15:12 -0700 Subject: mm/damon/core: introduce damon_call_control->dealloc_on_cancel Patch series "mm/damon/sysfs: fix refresh_ms control overwriting on multi-kdamonds usages". Automatic esssential DAMON/DAMOS status update feature of DAMON sysfs interface (refresh_ms) is broken [1] for multiple DAMON contexts (kdamonds) use case, since it uses a global single damon_call_control object for all created DAMON contexts. The fields of the object, particularly the list field is over-written for the contexts and it makes unexpected results including user-space hangup and kernel crashes [2]. Fix it by extending damon_call_control for the use case and updating the usage on DAMON sysfs interface to use per-context dynamically allocated damon_call_control object. This patch (of 2): When damon_call_control->repeat is set, damon_call() is executed asynchronously, and is eventually canceled when kdamond finishes. If the damon_call_control object is dynamically allocated, finding the place to deallocate the object is difficult. Introduce a new damon_call_control field, namely dealloc_on_cancel, to ask the kdamond deallocates those dynamically allocated objects when those are canceled. Link: https://lkml.kernel.org/r/20250908201513.60802-3-sj@kernel.org Link: https://lkml.kernel.org/r/20250908201513.60802-2-sj@kernel.org Fixes: d809a7c64ba8 ("mm/damon/sysfs: implement refresh_ms file internal work") Signed-off-by: SeongJae Park Cc: Yunjeong Mun Signed-off-by: Andrew Morton --- include/linux/damon.h | 2 ++ mm/damon/core.c | 8 ++++++-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index f13664c62ddd..9e62b2a85538 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -636,6 +636,7 @@ struct damon_operations { * @data: Data that will be passed to @fn. * @repeat: Repeat invocations. * @return_code: Return code from @fn invocation. + * @dealloc_on_cancel: De-allocate when canceled. * * Control damon_call(), which requests specific kdamond to invoke a given * function. Refer to damon_call() for more details. @@ -645,6 +646,7 @@ struct damon_call_control { void *data; bool repeat; int return_code; + bool dealloc_on_cancel; /* private: internal use only */ /* informs if the kdamond finished handling of the request */ struct completion completion; diff --git a/mm/damon/core.c b/mm/damon/core.c index c2e0b469fd43..08065b363972 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -2479,10 +2479,14 @@ static void kdamond_call(struct damon_ctx *ctx, bool cancel) mutex_lock(&ctx->call_controls_lock); list_del(&control->list); mutex_unlock(&ctx->call_controls_lock); - if (!control->repeat) + if (!control->repeat) { complete(&control->completion); - else + } else if (control->canceled && control->dealloc_on_cancel) { + kfree(control); + continue; + } else { list_add(&control->list, &repeat_controls); + } } control = list_first_entry_or_null(&repeat_controls, struct damon_call_control, list); -- cgit v1.2.3 From 3afaff7a0ce97457c8ab46862f2c06603a89962e Mon Sep 17 00:00:00 2001 From: Akhilesh Patil Date: Mon, 11 Aug 2025 17:42:53 +0530 Subject: include/linux/rv.h: remove redundant include file Remove redundant include to clean up the code. Move all unique include files inside CONFIG_RV as they are only needed when CONFIG_RV is enabled. Arrange include files alphabetically. Fixes: 24cbfe18d55a ("rv: Merge struct rv_monitor_def into struct rv_monitor") [1] Reported-by: kernel test robot Closes: https://lore.kernel.org/r/202507312017.oyD08TL5-lkp@intel.com/ Signed-off-by: Akhilesh Patil Reviewed-by: Gabriele Monaco Link: https://lore.kernel.org/r/aJneRbHGlNFg7lr9@bhairav-test.ee.iitb.ac.in Signed-off-by: Gabriele Monaco --- include/linux/rv.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rv.h b/include/linux/rv.h index 14410a42faef..9520aab34bcb 100644 --- a/include/linux/rv.h +++ b/include/linux/rv.h @@ -7,16 +7,14 @@ #ifndef _LINUX_RV_H #define _LINUX_RV_H -#include -#include - #define MAX_DA_NAME_LEN 32 #define MAX_DA_RETRY_RACING_EVENTS 3 #ifdef CONFIG_RV +#include #include +#include #include -#include /* * Deterministic automaton per-object variables. -- cgit v1.2.3 From 6b4be64fd9fec16418f365c2d8e47a7566e9eba5 Mon Sep 17 00:00:00 2001 From: Jianbo Liu Date: Mon, 15 Sep 2025 15:24:32 +0300 Subject: net/mlx5e: Harden uplink netdev access against device unbind The function mlx5_uplink_netdev_get() gets the uplink netdevice pointer from mdev->mlx5e_res.uplink_netdev. However, the netdevice can be removed and its pointer cleared when unbound from the mlx5_core.eth driver. This results in a NULL pointer, causing a kernel panic. BUG: unable to handle page fault for address: 0000000000001300 at RIP: 0010:mlx5e_vport_rep_load+0x22a/0x270 [mlx5_core] Call Trace: mlx5_esw_offloads_rep_load+0x68/0xe0 [mlx5_core] esw_offloads_enable+0x593/0x910 [mlx5_core] mlx5_eswitch_enable_locked+0x341/0x420 [mlx5_core] mlx5_devlink_eswitch_mode_set+0x17e/0x3a0 [mlx5_core] devlink_nl_eswitch_set_doit+0x60/0xd0 genl_family_rcv_msg_doit+0xe0/0x130 genl_rcv_msg+0x183/0x290 netlink_rcv_skb+0x4b/0xf0 genl_rcv+0x24/0x40 netlink_unicast+0x255/0x380 netlink_sendmsg+0x1f3/0x420 __sock_sendmsg+0x38/0x60 __sys_sendto+0x119/0x180 do_syscall_64+0x53/0x1d0 entry_SYSCALL_64_after_hwframe+0x4b/0x53 Ensure the pointer is valid before use by checking it for NULL. If it is valid, immediately call netdev_hold() to take a reference, and preventing the netdevice from being freed while it is in use. Fixes: 7a9fb35e8c3a ("net/mlx5e: Do not reload ethernet ports when changing eswitch mode") Signed-off-by: Jianbo Liu Reviewed-by: Cosmin Ratiu Reviewed-by: Jiri Pirko Reviewed-by: Dragos Tatulea Signed-off-by: Tariq Toukan Link: https://patch.msgid.link/1757939074-617281-2-git-send-email-tariqt@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 27 ++++++++++++++++++---- drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h | 15 +++++++++++- include/linux/mlx5/driver.h | 1 + 4 files changed, 38 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 63a7a788fb0d..cd0242eb008c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1506,12 +1506,21 @@ static const struct mlx5e_profile mlx5e_uplink_rep_profile = { static int mlx5e_vport_uplink_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) { - struct mlx5e_priv *priv = netdev_priv(mlx5_uplink_netdev_get(dev)); struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep); + struct net_device *netdev; + struct mlx5e_priv *priv; + int err; + + netdev = mlx5_uplink_netdev_get(dev); + if (!netdev) + return 0; + priv = netdev_priv(netdev); rpriv->netdev = priv->netdev; - return mlx5e_netdev_change_profile(priv, &mlx5e_uplink_rep_profile, - rpriv); + err = mlx5e_netdev_change_profile(priv, &mlx5e_uplink_rep_profile, + rpriv); + mlx5_uplink_netdev_put(dev, netdev); + return err; } static void @@ -1638,8 +1647,16 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) { struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep); struct net_device *netdev = rpriv->netdev; - struct mlx5e_priv *priv = netdev_priv(netdev); - void *ppriv = priv->ppriv; + struct mlx5e_priv *priv; + void *ppriv; + + if (!netdev) { + ppriv = rpriv; + goto free_ppriv; + } + + priv = netdev_priv(netdev); + ppriv = priv->ppriv; if (rep->vport == MLX5_VPORT_UPLINK) { mlx5e_vport_uplink_rep_unload(rpriv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index 8b4977650183..5f2d6c35f1ad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -1515,6 +1515,7 @@ static u32 mlx5_esw_qos_lag_link_speed_get_locked(struct mlx5_core_dev *mdev) speed = lksettings.base.speed; out: + mlx5_uplink_netdev_put(mdev, slave); return speed; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h index b111ccd03b02..74ea5da58b7e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h @@ -47,7 +47,20 @@ int mlx5_crdump_collect(struct mlx5_core_dev *dev, u32 *cr_data); static inline struct net_device *mlx5_uplink_netdev_get(struct mlx5_core_dev *mdev) { - return mdev->mlx5e_res.uplink_netdev; + struct mlx5e_resources *mlx5e_res = &mdev->mlx5e_res; + struct net_device *netdev; + + mutex_lock(&mlx5e_res->uplink_netdev_lock); + netdev = mlx5e_res->uplink_netdev; + netdev_hold(netdev, &mlx5e_res->tracker, GFP_KERNEL); + mutex_unlock(&mlx5e_res->uplink_netdev_lock); + return netdev; +} + +static inline void mlx5_uplink_netdev_put(struct mlx5_core_dev *mdev, + struct net_device *netdev) +{ + netdev_put(netdev, &mdev->mlx5e_res.tracker); } struct mlx5_sd; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 8c5fbfb85749..10fe492e1fed 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -663,6 +663,7 @@ struct mlx5e_resources { bool tisn_valid; } hw_objs; struct net_device *uplink_netdev; + netdevice_tracker tracker; struct mutex uplink_netdev_lock; struct mlx5_crypto_dek_priv *dek_priv; }; -- cgit v1.2.3 From df8922afc37aa2111ca79a216653a629146763ad Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 18 Sep 2025 13:59:15 -0600 Subject: io_uring/msg_ring: kill alloc_cache for io_kiocb allocations A recent commit: fc582cd26e88 ("io_uring/msg_ring: ensure io_kiocb freeing is deferred for RCU") fixed an issue with not deferring freeing of io_kiocb structs that msg_ring allocates to after the current RCU grace period. But this only covers requests that don't end up in the allocation cache. If a request goes into the alloc cache, it can get reused before it is sane to do so. A recent syzbot report would seem to indicate that there's something there, however it may very well just be because of the KASAN poisoning that the alloc_cache handles manually. Rather than attempt to make the alloc_cache sane for that use case, just drop the usage of the alloc_cache for msg_ring request payload data. Fixes: 50cf5f3842af ("io_uring/msg_ring: add an alloc cache for io_kiocb entries") Link: https://lore.kernel.org/io-uring/68cc2687.050a0220.139b6.0005.GAE@google.com/ Reported-by: syzbot+baa2e0f4e02df602583e@syzkaller.appspotmail.com Signed-off-by: Jens Axboe --- include/linux/io_uring_types.h | 3 --- io_uring/io_uring.c | 4 ---- io_uring/msg_ring.c | 24 ++---------------------- 3 files changed, 2 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 80a178f3d896..12f5ee43850e 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -420,9 +420,6 @@ struct io_ring_ctx { struct list_head defer_list; unsigned nr_drained; - struct io_alloc_cache msg_cache; - spinlock_t msg_lock; - #ifdef CONFIG_NET_RX_BUSY_POLL struct list_head napi_list; /* track busy poll napi_id */ spinlock_t napi_lock; /* napi_list lock */ diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index bcec12256f34..93665cebe9bd 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -290,7 +290,6 @@ static void io_free_alloc_caches(struct io_ring_ctx *ctx) io_alloc_cache_free(&ctx->netmsg_cache, io_netmsg_cache_free); io_alloc_cache_free(&ctx->rw_cache, io_rw_cache_free); io_alloc_cache_free(&ctx->cmd_cache, io_cmd_cache_free); - io_alloc_cache_free(&ctx->msg_cache, kfree); io_futex_cache_free(ctx); io_rsrc_cache_free(ctx); } @@ -337,9 +336,6 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) ret |= io_alloc_cache_init(&ctx->cmd_cache, IO_ALLOC_CACHE_MAX, sizeof(struct io_async_cmd), sizeof(struct io_async_cmd)); - spin_lock_init(&ctx->msg_lock); - ret |= io_alloc_cache_init(&ctx->msg_cache, IO_ALLOC_CACHE_MAX, - sizeof(struct io_kiocb), 0); ret |= io_futex_cache_init(ctx); ret |= io_rsrc_cache_init(ctx); if (ret) diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c index 4c2578f2efcb..5e5b94236d72 100644 --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -11,7 +11,6 @@ #include "io_uring.h" #include "rsrc.h" #include "filetable.h" -#include "alloc_cache.h" #include "msg_ring.h" /* All valid masks for MSG_RING */ @@ -76,13 +75,7 @@ static void io_msg_tw_complete(struct io_kiocb *req, io_tw_token_t tw) struct io_ring_ctx *ctx = req->ctx; io_add_aux_cqe(ctx, req->cqe.user_data, req->cqe.res, req->cqe.flags); - if (spin_trylock(&ctx->msg_lock)) { - if (io_alloc_cache_put(&ctx->msg_cache, req)) - req = NULL; - spin_unlock(&ctx->msg_lock); - } - if (req) - kfree_rcu(req, rcu_head); + kfree_rcu(req, rcu_head); percpu_ref_put(&ctx->refs); } @@ -104,26 +97,13 @@ static int io_msg_remote_post(struct io_ring_ctx *ctx, struct io_kiocb *req, return 0; } -static struct io_kiocb *io_msg_get_kiocb(struct io_ring_ctx *ctx) -{ - struct io_kiocb *req = NULL; - - if (spin_trylock(&ctx->msg_lock)) { - req = io_alloc_cache_get(&ctx->msg_cache); - spin_unlock(&ctx->msg_lock); - if (req) - return req; - } - return kmem_cache_alloc(req_cachep, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO); -} - static int io_msg_data_remote(struct io_ring_ctx *target_ctx, struct io_msg *msg) { struct io_kiocb *target; u32 flags = 0; - target = io_msg_get_kiocb(target_ctx); + target = kmem_cache_alloc(req_cachep, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO) ; if (unlikely(!target)) return -ENOMEM; -- cgit v1.2.3