From 293180f5934278d294c9cb4a87c7de4d1c084e0e Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Wed, 21 Jul 2021 17:26:47 +0300 Subject: virtio: Protect vqs list access [ Upstream commit 0e566c8f0f2e8325e35f6f97e13cde5356b41814 ] VQs may be accessed to mark the device broken while they are created/destroyed. Hence protect the access to the vqs list. Fixes: e2dcdfe95c0b ("virtio: virtio_break_device() to mark all virtqueues broken.") Signed-off-by: Parav Pandit Link: https://lore.kernel.org/r/20210721142648.1525924-4-parav@nvidia.com Signed-off-by: Michael S. Tsirkin Signed-off-by: Sasha Levin --- include/linux/virtio.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 55ea329fe72a..8ecc2e208d61 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -110,6 +110,7 @@ struct virtio_device { bool config_enabled; bool config_change_pending; spinlock_t config_lock; + spinlock_t vqs_list_lock; /* Protects VQs list access */ struct device dev; struct virtio_device_id id; const struct virtio_config_ops *config; -- cgit v1.2.3 From 6715cefa72f6c008cf104761331ed1cb14392caa Mon Sep 17 00:00:00 2001 From: Yongqiang Niu Date: Tue, 6 Oct 2020 21:33:17 +0200 Subject: soc / drm: mediatek: Move DDP component defines into mtk-mmsys.h [ Upstream commit 51c0e618b219c025ddaaf14baea8942cb7e2105b ] MMSYS is the driver which controls the routing of these DDP components, so the definition of the mtk_ddp_comp_id enum should be placed in mtk-mmsys.h Signed-off-by: Yongqiang Niu Signed-off-by: Enric Balletbo i Serra Reviewed-by: Chun-Kuang Hu Link: https://lore.kernel.org/r/20201006193320.405529-2-enric.balletbo@collabora.com Signed-off-by: Matthias Brugger Signed-off-by: Sasha Levin --- drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h | 34 +---------------------------- drivers/soc/mediatek/mtk-mmsys.c | 4 +--- include/linux/soc/mediatek/mtk-mmsys.h | 33 ++++++++++++++++++++++++++++ 3 files changed, 35 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h index 1d9e00b69462..5aa52b7afeec 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h +++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h @@ -7,6 +7,7 @@ #define MTK_DRM_DDP_COMP_H #include +#include struct device; struct device_node; @@ -35,39 +36,6 @@ enum mtk_ddp_comp_type { MTK_DDP_COMP_TYPE_MAX, }; -enum mtk_ddp_comp_id { - DDP_COMPONENT_AAL0, - DDP_COMPONENT_AAL1, - DDP_COMPONENT_BLS, - DDP_COMPONENT_CCORR, - DDP_COMPONENT_COLOR0, - DDP_COMPONENT_COLOR1, - DDP_COMPONENT_DITHER, - DDP_COMPONENT_DPI0, - DDP_COMPONENT_DPI1, - DDP_COMPONENT_DSI0, - DDP_COMPONENT_DSI1, - DDP_COMPONENT_DSI2, - DDP_COMPONENT_DSI3, - DDP_COMPONENT_GAMMA, - DDP_COMPONENT_OD0, - DDP_COMPONENT_OD1, - DDP_COMPONENT_OVL0, - DDP_COMPONENT_OVL_2L0, - DDP_COMPONENT_OVL_2L1, - DDP_COMPONENT_OVL1, - DDP_COMPONENT_PWM0, - DDP_COMPONENT_PWM1, - DDP_COMPONENT_PWM2, - DDP_COMPONENT_RDMA0, - DDP_COMPONENT_RDMA1, - DDP_COMPONENT_RDMA2, - DDP_COMPONENT_UFOE, - DDP_COMPONENT_WDMA0, - DDP_COMPONENT_WDMA1, - DDP_COMPONENT_ID_MAX, -}; - struct mtk_ddp_comp; struct cmdq_pkt; struct mtk_ddp_comp_funcs { diff --git a/drivers/soc/mediatek/mtk-mmsys.c b/drivers/soc/mediatek/mtk-mmsys.c index a55f25511173..36ad66bb221b 100644 --- a/drivers/soc/mediatek/mtk-mmsys.c +++ b/drivers/soc/mediatek/mtk-mmsys.c @@ -5,13 +5,11 @@ */ #include +#include #include #include #include -#include "../../gpu/drm/mediatek/mtk_drm_ddp.h" -#include "../../gpu/drm/mediatek/mtk_drm_ddp_comp.h" - #define DISP_REG_CONFIG_DISP_OVL0_MOUT_EN 0x040 #define DISP_REG_CONFIG_DISP_OVL1_MOUT_EN 0x044 #define DISP_REG_CONFIG_DISP_OD_MOUT_EN 0x048 diff --git a/include/linux/soc/mediatek/mtk-mmsys.h b/include/linux/soc/mediatek/mtk-mmsys.h index 7bab5d9a3d31..2228bf6133da 100644 --- a/include/linux/soc/mediatek/mtk-mmsys.h +++ b/include/linux/soc/mediatek/mtk-mmsys.h @@ -9,6 +9,39 @@ enum mtk_ddp_comp_id; struct device; +enum mtk_ddp_comp_id { + DDP_COMPONENT_AAL0, + DDP_COMPONENT_AAL1, + DDP_COMPONENT_BLS, + DDP_COMPONENT_CCORR, + DDP_COMPONENT_COLOR0, + DDP_COMPONENT_COLOR1, + DDP_COMPONENT_DITHER, + DDP_COMPONENT_DPI0, + DDP_COMPONENT_DPI1, + DDP_COMPONENT_DSI0, + DDP_COMPONENT_DSI1, + DDP_COMPONENT_DSI2, + DDP_COMPONENT_DSI3, + DDP_COMPONENT_GAMMA, + DDP_COMPONENT_OD0, + DDP_COMPONENT_OD1, + DDP_COMPONENT_OVL0, + DDP_COMPONENT_OVL_2L0, + DDP_COMPONENT_OVL_2L1, + DDP_COMPONENT_OVL1, + DDP_COMPONENT_PWM0, + DDP_COMPONENT_PWM1, + DDP_COMPONENT_PWM2, + DDP_COMPONENT_RDMA0, + DDP_COMPONENT_RDMA1, + DDP_COMPONENT_RDMA2, + DDP_COMPONENT_UFOE, + DDP_COMPONENT_WDMA0, + DDP_COMPONENT_WDMA1, + DDP_COMPONENT_ID_MAX, +}; + void mtk_mmsys_ddp_connect(struct device *dev, enum mtk_ddp_comp_id cur, enum mtk_ddp_comp_id next); -- cgit v1.2.3 From 8132fc2bf4b70d19f666e82e7ce28dc871ed3b92 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 19 Aug 2021 19:04:21 -0700 Subject: mm: memcontrol: fix occasional OOMs due to proportional memory.low reclaim [ Upstream commit f56ce412a59d7d938b81de8878faef128812482c ] We've noticed occasional OOM killing when memory.low settings are in effect for cgroups. This is unexpected and undesirable as memory.low is supposed to express non-OOMing memory priorities between cgroups. The reason for this is proportional memory.low reclaim. When cgroups are below their memory.low threshold, reclaim passes them over in the first round, and then retries if it couldn't find pages anywhere else. But when cgroups are slightly above their memory.low setting, page scan force is scaled down and diminished in proportion to the overage, to the point where it can cause reclaim to fail as well - only in that case we currently don't retry, and instead trigger OOM. To fix this, hook proportional reclaim into the same retry logic we have in place for when cgroups are skipped entirely. This way if reclaim fails and some cgroups were scanned with diminished pressure, we'll try another full-force cycle before giving up and OOMing. [akpm@linux-foundation.org: coding-style fixes] Link: https://lkml.kernel.org/r/20210817180506.220056-1-hannes@cmpxchg.org Fixes: 9783aa9917f8 ("mm, memcg: proportional memory.{low,min} reclaim") Signed-off-by: Johannes Weiner Reported-by: Leon Yang Reviewed-by: Rik van Riel Reviewed-by: Shakeel Butt Acked-by: Roman Gushchin Acked-by: Chris Down Acked-by: Michal Hocko Cc: [5.4+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin --- include/linux/memcontrol.h | 29 +++++++++++++++-------------- mm/vmscan.c | 27 +++++++++++++++++++-------- 2 files changed, 34 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index c691b1ac95f8..4b975111b536 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -360,12 +360,15 @@ static inline bool mem_cgroup_disabled(void) return !cgroup_subsys_enabled(memory_cgrp_subsys); } -static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root, - struct mem_cgroup *memcg, - bool in_low_reclaim) +static inline void mem_cgroup_protection(struct mem_cgroup *root, + struct mem_cgroup *memcg, + unsigned long *min, + unsigned long *low) { + *min = *low = 0; + if (mem_cgroup_disabled()) - return 0; + return; /* * There is no reclaim protection applied to a targeted reclaim. @@ -401,13 +404,10 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root, * */ if (root == memcg) - return 0; - - if (in_low_reclaim) - return READ_ONCE(memcg->memory.emin); + return; - return max(READ_ONCE(memcg->memory.emin), - READ_ONCE(memcg->memory.elow)); + *min = READ_ONCE(memcg->memory.emin); + *low = READ_ONCE(memcg->memory.elow); } void mem_cgroup_calculate_protection(struct mem_cgroup *root, @@ -966,11 +966,12 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm, { } -static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root, - struct mem_cgroup *memcg, - bool in_low_reclaim) +static inline void mem_cgroup_protection(struct mem_cgroup *root, + struct mem_cgroup *memcg, + unsigned long *min, + unsigned long *low) { - return 0; + *min = *low = 0; } static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root, diff --git a/mm/vmscan.c b/mm/vmscan.c index 67d38334052e..7fb9af001ed5 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -102,9 +102,12 @@ struct scan_control { unsigned int may_swap:1; /* - * Cgroups are not reclaimed below their configured memory.low, - * unless we threaten to OOM. If any cgroups are skipped due to - * memory.low and nothing was reclaimed, go back for memory.low. + * Cgroup memory below memory.low is protected as long as we + * don't threaten to OOM. If any cgroup is reclaimed at + * reduced force or passed over entirely due to its memory.low + * setting (memcg_low_skipped), and nothing is reclaimed as a + * result, then go back for one more cycle that reclaims the protected + * memory (memcg_low_reclaim) to avert OOM. */ unsigned int memcg_low_reclaim:1; unsigned int memcg_low_skipped:1; @@ -2323,15 +2326,14 @@ out: for_each_evictable_lru(lru) { int file = is_file_lru(lru); unsigned long lruvec_size; + unsigned long low, min; unsigned long scan; - unsigned long protection; lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); - protection = mem_cgroup_protection(sc->target_mem_cgroup, - memcg, - sc->memcg_low_reclaim); + mem_cgroup_protection(sc->target_mem_cgroup, memcg, + &min, &low); - if (protection) { + if (min || low) { /* * Scale a cgroup's reclaim pressure by proportioning * its current usage to its memory.low or memory.min @@ -2362,6 +2364,15 @@ out: * hard protection. */ unsigned long cgroup_size = mem_cgroup_size(memcg); + unsigned long protection; + + /* memory.low scaling, make sure we retry before OOM */ + if (!sc->memcg_low_reclaim && low > min) { + protection = low; + sc->memcg_low_skipped = 1; + } else { + protection = min; + } /* Avoid TOCTOU with earlier protection check */ cgroup_size = max(cgroup_size, protection); -- cgit v1.2.3 From d81ddadabdee32732477f9f85f1c7cec3c89b00f Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 23 Aug 2021 10:36:46 -0700 Subject: bpf: Fix NULL pointer dereference in bpf_get_local_storage() helper commit b910eaaaa4b89976ef02e5d6448f3f73dc671d91 upstream. Jiri Olsa reported a bug ([1]) in kernel where cgroup local storage pointer may be NULL in bpf_get_local_storage() helper. There are two issues uncovered by this bug: (1). kprobe or tracepoint prog incorrectly sets cgroup local storage before prog run, (2). due to change from preempt_disable to migrate_disable, preemption is possible and percpu storage might be overwritten by other tasks. This issue (1) is fixed in [2]. This patch tried to address issue (2). The following shows how things can go wrong: task 1: bpf_cgroup_storage_set() for percpu local storage preemption happens task 2: bpf_cgroup_storage_set() for percpu local storage preemption happens task 1: run bpf program task 1 will effectively use the percpu local storage setting by task 2 which will be either NULL or incorrect ones. Instead of just one common local storage per cpu, this patch fixed the issue by permitting 8 local storages per cpu and each local storage is identified by a task_struct pointer. This way, we allow at most 8 nested preemption between bpf_cgroup_storage_set() and bpf_cgroup_storage_unset(). The percpu local storage slot is released (calling bpf_cgroup_storage_unset()) by the same task after bpf program finished running. bpf_test_run() is also fixed to use the new bpf_cgroup_storage_set() interface. The patch is tested on top of [2] with reproducer in [1]. Without this patch, kernel will emit error in 2-3 minutes. With this patch, after one hour, still no error. [1] https://lore.kernel.org/bpf/CAKH8qBuXCfUz=w8L+Fj74OaUpbosO29niYwTki7e3Ag044_aww@mail.gmail.com/T [2] https://lore.kernel.org/bpf/20210309185028.3763817-1-yhs@fb.com Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Roman Gushchin Link: https://lore.kernel.org/bpf/20210323055146.3334476-1-yhs@fb.com Cc: # 5.10.x Signed-off-by: Stanislav Fomichev Signed-off-by: Sasha Levin --- include/linux/bpf-cgroup.h | 57 +++++++++++++++++++++++++++++++++++++++------- include/linux/bpf.h | 15 ++++++++---- kernel/bpf/helpers.c | 15 ++++++++---- kernel/bpf/local_storage.c | 5 ++-- net/bpf/test_run.c | 6 ++++- 5 files changed, 79 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index ed71bd1a0825..53f14e8827cc 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -20,14 +20,25 @@ struct bpf_sock_ops_kern; struct bpf_cgroup_storage; struct ctl_table; struct ctl_table_header; +struct task_struct; #ifdef CONFIG_CGROUP_BPF extern struct static_key_false cgroup_bpf_enabled_key; #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) -DECLARE_PER_CPU(struct bpf_cgroup_storage*, - bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); +#define BPF_CGROUP_STORAGE_NEST_MAX 8 + +struct bpf_cgroup_storage_info { + struct task_struct *task; + struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]; +}; + +/* For each cpu, permit maximum BPF_CGROUP_STORAGE_NEST_MAX number of tasks + * to use bpf cgroup storage simultaneously. + */ +DECLARE_PER_CPU(struct bpf_cgroup_storage_info, + bpf_cgroup_storage_info[BPF_CGROUP_STORAGE_NEST_MAX]); #define for_each_cgroup_storage_type(stype) \ for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++) @@ -156,13 +167,42 @@ static inline enum bpf_cgroup_storage_type cgroup_storage_type( return BPF_CGROUP_STORAGE_SHARED; } -static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage - *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) +static inline int bpf_cgroup_storage_set(struct bpf_cgroup_storage + *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) { enum bpf_cgroup_storage_type stype; + int i, err = 0; + + preempt_disable(); + for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { + if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != NULL)) + continue; + + this_cpu_write(bpf_cgroup_storage_info[i].task, current); + for_each_cgroup_storage_type(stype) + this_cpu_write(bpf_cgroup_storage_info[i].storage[stype], + storage[stype]); + goto out; + } + err = -EBUSY; + WARN_ON_ONCE(1); + +out: + preempt_enable(); + return err; +} + +static inline void bpf_cgroup_storage_unset(void) +{ + int i; + + for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { + if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) + continue; - for_each_cgroup_storage_type(stype) - this_cpu_write(bpf_cgroup_storage[stype], storage[stype]); + this_cpu_write(bpf_cgroup_storage_info[i].task, NULL); + return; + } } struct bpf_cgroup_storage * @@ -410,8 +450,9 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr, return -EINVAL; } -static inline void bpf_cgroup_storage_set( - struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) {} +static inline int bpf_cgroup_storage_set( + struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) { return 0; } +static inline void bpf_cgroup_storage_unset(void) {} static inline int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux, struct bpf_map *map) { return 0; } static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc( diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c3ccb242d199..3f93a50c25ef 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1089,9 +1089,14 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, goto _out; \ _item = &_array->items[0]; \ while ((_prog = READ_ONCE(_item->prog))) { \ - if (set_cg_storage) \ - bpf_cgroup_storage_set(_item->cgroup_storage); \ - _ret &= func(_prog, ctx); \ + if (!set_cg_storage) { \ + _ret &= func(_prog, ctx); \ + } else { \ + if (unlikely(bpf_cgroup_storage_set(_item->cgroup_storage))) \ + break; \ + _ret &= func(_prog, ctx); \ + bpf_cgroup_storage_unset(); \ + } \ _item++; \ } \ _out: \ @@ -1135,8 +1140,10 @@ _out: \ _array = rcu_dereference(array); \ _item = &_array->items[0]; \ while ((_prog = READ_ONCE(_item->prog))) { \ - bpf_cgroup_storage_set(_item->cgroup_storage); \ + if (unlikely(bpf_cgroup_storage_set(_item->cgroup_storage))) \ + break; \ ret = func(_prog, ctx); \ + bpf_cgroup_storage_unset(); \ _ret &= (ret & 1); \ _cn |= (ret & 2); \ _item++; \ diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index f7e99bb8c3b6..3bd7fbd8c543 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -372,8 +372,8 @@ const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto = { }; #ifdef CONFIG_CGROUP_BPF -DECLARE_PER_CPU(struct bpf_cgroup_storage*, - bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); +DECLARE_PER_CPU(struct bpf_cgroup_storage_info, + bpf_cgroup_storage_info[BPF_CGROUP_STORAGE_NEST_MAX]); BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) { @@ -382,10 +382,17 @@ BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) * verifier checks that its value is correct. */ enum bpf_cgroup_storage_type stype = cgroup_storage_type(map); - struct bpf_cgroup_storage *storage; + struct bpf_cgroup_storage *storage = NULL; void *ptr; + int i; - storage = this_cpu_read(bpf_cgroup_storage[stype]); + for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { + if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) + continue; + + storage = this_cpu_read(bpf_cgroup_storage_info[i].storage[stype]); + break; + } if (stype == BPF_CGROUP_STORAGE_SHARED) ptr = &READ_ONCE(storage->buf)->data[0]; diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 571bb351ed3b..b139247d2dd3 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -9,10 +9,11 @@ #include #include -DEFINE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); - #ifdef CONFIG_CGROUP_BPF +DEFINE_PER_CPU(struct bpf_cgroup_storage_info, + bpf_cgroup_storage_info[BPF_CGROUP_STORAGE_NEST_MAX]); + #include "../cgroup/cgroup-internal.h" #define LOCAL_STORAGE_CREATE_FLAG_MASK \ diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index e7cbd1b4a5e5..72d424a5a142 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -42,13 +42,17 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, migrate_disable(); time_start = ktime_get_ns(); for (i = 0; i < repeat; i++) { - bpf_cgroup_storage_set(storage); + ret = bpf_cgroup_storage_set(storage); + if (ret) + break; if (xdp) *retval = bpf_prog_run_xdp(prog, ctx); else *retval = BPF_PROG_RUN(prog, ctx); + bpf_cgroup_storage_unset(); + if (signal_pending(current)) { ret = -EINTR; break; -- cgit v1.2.3 From 6815e21fe28ddfe8f55b4ca53031957dcd65843a Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 6 Aug 2021 16:21:24 +0800 Subject: once: Fix panic when module unload [ Upstream commit 1027b96ec9d34f9abab69bc1a4dc5b1ad8ab1349 ] DO_ONCE DEFINE_STATIC_KEY_TRUE(___once_key); __do_once_done once_disable_jump(once_key); INIT_WORK(&w->work, once_deferred); struct once_work *w; w->key = key; schedule_work(&w->work); module unload //*the key is destroy* process_one_work once_deferred BUG_ON(!static_key_enabled(work->key)); static_key_count((struct static_key *)x) //*access key, crash* When module uses DO_ONCE mechanism, it could crash due to the above concurrency problem, we could reproduce it with link[1]. Fix it by add/put module refcount in the once work process. [1] https://lore.kernel.org/netdev/eaa6c371-465e-57eb-6be9-f4b16b9d7cbf@huawei.com/ Cc: Hannes Frederic Sowa Cc: Daniel Borkmann Cc: David S. Miller Cc: Eric Dumazet Reported-by: Minmin chen Signed-off-by: Kefeng Wang Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/linux/once.h | 4 ++-- lib/once.c | 11 ++++++++--- 2 files changed, 10 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/once.h b/include/linux/once.h index 9225ee6d96c7..ae6f4eb41cbe 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -7,7 +7,7 @@ bool __do_once_start(bool *done, unsigned long *flags); void __do_once_done(bool *done, struct static_key_true *once_key, - unsigned long *flags); + unsigned long *flags, struct module *mod); /* Call a function exactly once. The idea of DO_ONCE() is to perform * a function call such as initialization of random seeds, etc, only @@ -46,7 +46,7 @@ void __do_once_done(bool *done, struct static_key_true *once_key, if (unlikely(___ret)) { \ func(__VA_ARGS__); \ __do_once_done(&___done, &___once_key, \ - &___flags); \ + &___flags, THIS_MODULE); \ } \ } \ ___ret; \ diff --git a/lib/once.c b/lib/once.c index 8b7d6235217e..59149bf3bfb4 100644 --- a/lib/once.c +++ b/lib/once.c @@ -3,10 +3,12 @@ #include #include #include +#include struct once_work { struct work_struct work; struct static_key_true *key; + struct module *module; }; static void once_deferred(struct work_struct *w) @@ -16,10 +18,11 @@ static void once_deferred(struct work_struct *w) work = container_of(w, struct once_work, work); BUG_ON(!static_key_enabled(work->key)); static_branch_disable(work->key); + module_put(work->module); kfree(work); } -static void once_disable_jump(struct static_key_true *key) +static void once_disable_jump(struct static_key_true *key, struct module *mod) { struct once_work *w; @@ -29,6 +32,8 @@ static void once_disable_jump(struct static_key_true *key) INIT_WORK(&w->work, once_deferred); w->key = key; + w->module = mod; + __module_get(mod); schedule_work(&w->work); } @@ -53,11 +58,11 @@ bool __do_once_start(bool *done, unsigned long *flags) EXPORT_SYMBOL(__do_once_start); void __do_once_done(bool *done, struct static_key_true *once_key, - unsigned long *flags) + unsigned long *flags, struct module *mod) __releases(once_lock) { *done = true; spin_unlock_irqrestore(&once_lock, *flags); - once_disable_jump(once_key); + once_disable_jump(once_key, mod); } EXPORT_SYMBOL(__do_once_done); -- cgit v1.2.3 From b2091d47a14e8e6b3f03d792c1b25255d60b3219 Mon Sep 17 00:00:00 2001 From: Xiaoliang Yang Date: Mon, 5 Jul 2021 18:26:54 +0800 Subject: net: stmmac: add mutex lock to protect est parameters [ Upstream commit b2aae654a4794ef898ad33a179f341eb610f6b85 ] Add a mutex lock to protect est structure parameters so that the EST parameters can be updated by other threads. Signed-off-by: Xiaoliang Yang Signed-off-by: David S. Miller Signed-off-by: Pavel Machek (CIP) Signed-off-by: Sasha Levin --- drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c | 14 +++++++++++++- include/linux/stmmac.h | 1 + 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 40dc14d1415f..6bd9f0c50ffe 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -689,14 +689,18 @@ static int tc_setup_taprio(struct stmmac_priv *priv, GFP_KERNEL); if (!plat->est) return -ENOMEM; + + mutex_init(&priv->plat->est->lock); } else { memset(plat->est, 0, sizeof(*plat->est)); } size = qopt->num_entries; + mutex_lock(&priv->plat->est->lock); priv->plat->est->gcl_size = size; priv->plat->est->enable = qopt->enable; + mutex_unlock(&priv->plat->est->lock); for (i = 0; i < size; i++) { s64 delta_ns = qopt->entries[i].interval; @@ -727,6 +731,7 @@ static int tc_setup_taprio(struct stmmac_priv *priv, priv->plat->est->gcl[i] = delta_ns | (gates << wid); } + mutex_lock(&priv->plat->est->lock); /* Adjust for real system time */ priv->ptp_clock_ops.gettime64(&priv->ptp_clock_ops, ¤t_time); current_time_ns = timespec64_to_ktime(current_time); @@ -751,19 +756,23 @@ static int tc_setup_taprio(struct stmmac_priv *priv, priv->plat->est->ctr[0] = do_div(ctr, NSEC_PER_SEC); priv->plat->est->ctr[1] = (u32)ctr; - if (fpe && !priv->dma_cap.fpesel) + if (fpe && !priv->dma_cap.fpesel) { + mutex_unlock(&priv->plat->est->lock); return -EOPNOTSUPP; + } ret = stmmac_fpe_configure(priv, priv->ioaddr, priv->plat->tx_queues_to_use, priv->plat->rx_queues_to_use, fpe); if (ret && fpe) { + mutex_unlock(&priv->plat->est->lock); netdev_err(priv->dev, "failed to enable Frame Preemption\n"); return ret; } ret = stmmac_est_configure(priv, priv->ioaddr, priv->plat->est, priv->plat->clk_ptp_rate); + mutex_unlock(&priv->plat->est->lock); if (ret) { netdev_err(priv->dev, "failed to configure EST\n"); goto disable; @@ -773,9 +782,12 @@ static int tc_setup_taprio(struct stmmac_priv *priv, return 0; disable: + mutex_lock(&priv->plat->est->lock); priv->plat->est->enable = false; stmmac_est_configure(priv, priv->ioaddr, priv->plat->est, priv->plat->clk_ptp_rate); + mutex_unlock(&priv->plat->est->lock); + return ret; } diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 15ca6b4167cc..b56e1dedcf2f 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -112,6 +112,7 @@ struct stmmac_axi { #define EST_GCL 1024 struct stmmac_est { + struct mutex lock; int enable; u32 btr_offset[2]; u32 btr[2]; -- cgit v1.2.3 From e91da23c1be16ebcfca0991976ed9377a8233935 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 5 Aug 2021 10:04:43 -0700 Subject: pipe: avoid unnecessary EPOLLET wakeups under normal loads commit 3b844826b6c6affa80755254da322b017358a2f4 upstream. I had forgotten just how sensitive hackbench is to extra pipe wakeups, and commit 3a34b13a88ca ("pipe: make pipe writes always wake up readers") ended up causing a quite noticeable regression on larger machines. Now, hackbench isn't necessarily a hugely meaningful benchmark, and it's not clear that this matters in real life all that much, but as Mel points out, it's used often enough when comparing kernels and so the performance regression shows up like a sore thumb. It's easy enough to fix at least for the common cases where pipes are used purely for data transfer, and you never have any exciting poll usage at all. So set a special 'poll_usage' flag when there is polling activity, and make the ugly "EPOLLET has crazy legacy expectations" semantics explicit to only that case. I would love to limit it to just the broken EPOLLET case, but the pipe code can't see the difference between epoll and regular select/poll, so any non-read/write waiting will trigger the extra wakeup behavior. That is sufficient for at least the hackbench case. Apart from making the odd extra wakeup cases more explicitly about EPOLLET, this also makes the extra wakeup be at the _end_ of the pipe write, not at the first write chunk. That is actually much saner semantics (as much as you can call any of the legacy edge-triggered expectations for EPOLLET "sane") since it means that you know the wakeup will happen once the write is done, rather than possibly in the middle of one. [ For stable people: I'm putting a "Fixes" tag on this, but I leave it up to you to decide whether you actually want to backport it or not. It likely has no impact outside of synthetic benchmarks - Linus ] Link: https://lore.kernel.org/lkml/20210802024945.GA8372@xsang-OptiPlex-9020/ Fixes: 3a34b13a88ca ("pipe: make pipe writes always wake up readers") Reported-by: kernel test robot Tested-by: Sandeep Patil Tested-by: Mel Gorman Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- fs/pipe.c | 15 +++++++++------ include/linux/pipe_fs_i.h | 2 ++ 2 files changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/pipe.c b/fs/pipe.c index 28b2e973f10e..48abe65333c4 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -444,9 +444,6 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) #endif /* - * Epoll nonsensically wants a wakeup whether the pipe - * was already empty or not. - * * If it wasn't empty we try to merge new data into * the last buffer. * @@ -455,9 +452,9 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) * spanning multiple pages. */ head = pipe->head; - was_empty = true; + was_empty = pipe_empty(head, pipe->tail); chars = total_len & (PAGE_SIZE-1); - if (chars && !pipe_empty(head, pipe->tail)) { + if (chars && !was_empty) { unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf = &pipe->bufs[(head - 1) & mask]; int offset = buf->offset + buf->len; @@ -590,8 +587,11 @@ out: * This is particularly important for small writes, because of * how (for example) the GNU make jobserver uses small writes to * wake up pending jobs + * + * Epoll nonsensically wants a wakeup whether the pipe + * was already empty or not. */ - if (was_empty) { + if (was_empty || pipe->poll_usage) { wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); } @@ -654,6 +654,9 @@ pipe_poll(struct file *filp, poll_table *wait) struct pipe_inode_info *pipe = filp->private_data; unsigned int head, tail; + /* Epoll has some historical nasty semantics, this enables them */ + pipe->poll_usage = 1; + /* * Reading pipe state only -- no need for acquiring the semaphore. * diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 5d2705f1d01c..fc5642431b92 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -48,6 +48,7 @@ struct pipe_buffer { * @files: number of struct file referring this pipe (protected by ->i_lock) * @r_counter: reader counter * @w_counter: writer counter + * @poll_usage: is this pipe used for epoll, which has crazy wakeups? * @fasync_readers: reader side fasync * @fasync_writers: writer side fasync * @bufs: the circular array of pipe buffers @@ -70,6 +71,7 @@ struct pipe_inode_info { unsigned int files; unsigned int r_counter; unsigned int w_counter; + unsigned int poll_usage; struct page *tmp_page; struct fasync_struct *fasync_readers; struct fasync_struct *fasync_writers; -- cgit v1.2.3 From 450948b06ce8ba3e22df094ef324dbf5fa52f050 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 12 Nov 2020 16:34:09 -0800 Subject: srcu: Make Tiny SRCU use multi-bit grace-period counter commit 74612a07b83fc46c2b2e6f71a541d55b024ebefc upstream. There is a need for a polling interface for SRCU grace periods. This polling needs to distinguish between an SRCU instance being idle on the one hand or in the middle of a grace period on the other. This commit therefore converts the Tiny SRCU srcu_struct structure's srcu_idx from a defacto boolean to a free-running counter, using the bottom bit to indicate that a grace period is in progress. The second-from-bottom bit is thus used as the index returned by srcu_read_lock(). Link: https://lore.kernel.org/rcu/20201112201547.GF3365678@moria.home.lan/ Reported-by: Kent Overstreet [ paulmck: Fix ->srcu_lock_nesting[] indexing per Neeraj Upadhyay. ] Reviewed-by: Neeraj Upadhyay Signed-off-by: Paul E. McKenney Signed-off-by: Greg Kroah-Hartman --- include/linux/srcutiny.h | 6 +++--- kernel/rcu/srcutiny.c | 5 +++-- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index 5a5a1941ca15..b8b42d0a24f1 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -15,7 +15,7 @@ struct srcu_struct { short srcu_lock_nesting[2]; /* srcu_read_lock() nesting depth. */ - short srcu_idx; /* Current reader array element. */ + unsigned short srcu_idx; /* Current reader array element in bit 0x2. */ u8 srcu_gp_running; /* GP workqueue running? */ u8 srcu_gp_waiting; /* GP waiting for readers? */ struct swait_queue_head srcu_wq; @@ -59,7 +59,7 @@ static inline int __srcu_read_lock(struct srcu_struct *ssp) { int idx; - idx = READ_ONCE(ssp->srcu_idx); + idx = ((READ_ONCE(ssp->srcu_idx) + 1) & 0x2) >> 1; WRITE_ONCE(ssp->srcu_lock_nesting[idx], ssp->srcu_lock_nesting[idx] + 1); return idx; } @@ -80,7 +80,7 @@ static inline void srcu_torture_stats_print(struct srcu_struct *ssp, { int idx; - idx = READ_ONCE(ssp->srcu_idx) & 0x1; + idx = ((READ_ONCE(ssp->srcu_idx) + 1) & 0x2) >> 1; pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%hd,%hd)\n", tt, tf, idx, READ_ONCE(ssp->srcu_lock_nesting[!idx]), diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c index ee25b365c3ea..3bac1db85a85 100644 --- a/kernel/rcu/srcutiny.c +++ b/kernel/rcu/srcutiny.c @@ -124,11 +124,12 @@ void srcu_drive_gp(struct work_struct *wp) ssp->srcu_cb_head = NULL; ssp->srcu_cb_tail = &ssp->srcu_cb_head; local_irq_enable(); - idx = ssp->srcu_idx; - WRITE_ONCE(ssp->srcu_idx, !ssp->srcu_idx); + idx = (ssp->srcu_idx & 0x2) / 2; + WRITE_ONCE(ssp->srcu_idx, ssp->srcu_idx + 1); WRITE_ONCE(ssp->srcu_gp_waiting, true); /* srcu_read_unlock() wakes! */ swait_event_exclusive(ssp->srcu_wq, !READ_ONCE(ssp->srcu_lock_nesting[idx])); WRITE_ONCE(ssp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */ + WRITE_ONCE(ssp->srcu_idx, ssp->srcu_idx + 1); /* Invoke the callbacks we removed above. */ while (lh) { -- cgit v1.2.3 From b6ae3854075e67a2764e30447f8603ef964aecc5 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 13 Nov 2020 12:54:48 -0800 Subject: srcu: Provide polling interfaces for Tiny SRCU grace periods commit 8b5bd67cf6422b63ee100d76d8de8960ca2df7f0 upstream. There is a need for a polling interface for SRCU grace periods, so this commit supplies get_state_synchronize_srcu(), start_poll_synchronize_srcu(), and poll_state_synchronize_srcu() for this purpose. The first can be used if future grace periods are inevitable (perhaps due to a later call_srcu() invocation), the second if future grace periods might not otherwise happen, and the third to check if a grace period has elapsed since the corresponding call to either of the first two. As with get_state_synchronize_rcu() and cond_synchronize_rcu(), the return value from either get_state_synchronize_srcu() or start_poll_synchronize_srcu() must be passed in to a later call to poll_state_synchronize_srcu(). Link: https://lore.kernel.org/rcu/20201112201547.GF3365678@moria.home.lan/ Reported-by: Kent Overstreet [ paulmck: Add EXPORT_SYMBOL_GPL() per kernel test robot feedback. ] [ paulmck: Apply feedback from Neeraj Upadhyay. ] Link: https://lore.kernel.org/lkml/20201117004017.GA7444@paulmck-ThinkPad-P72/ Reviewed-by: Neeraj Upadhyay Signed-off-by: Paul E. McKenney Signed-off-by: Greg Kroah-Hartman --- include/linux/rcupdate.h | 2 ++ include/linux/srcu.h | 3 +++ include/linux/srcutiny.h | 1 + kernel/rcu/srcutiny.c | 55 ++++++++++++++++++++++++++++++++++++++++++++++-- 4 files changed, 59 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 7d12c76e8fa4..0d7013da818c 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -33,6 +33,8 @@ #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) #define ulong2long(a) (*(long *)(&(a))) +#define USHORT_CMP_GE(a, b) (USHRT_MAX / 2 >= (unsigned short)((a) - (b))) +#define USHORT_CMP_LT(a, b) (USHRT_MAX / 2 < (unsigned short)((a) - (b))) /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); diff --git a/include/linux/srcu.h b/include/linux/srcu.h index e432cc92c73d..a0895bbf71ce 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -60,6 +60,9 @@ void cleanup_srcu_struct(struct srcu_struct *ssp); int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp); void synchronize_srcu(struct srcu_struct *ssp); +unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp); +unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp); +bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie); #ifdef CONFIG_DEBUG_LOCK_ALLOC diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index b8b42d0a24f1..0e0cf4d6a72a 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -16,6 +16,7 @@ struct srcu_struct { short srcu_lock_nesting[2]; /* srcu_read_lock() nesting depth. */ unsigned short srcu_idx; /* Current reader array element in bit 0x2. */ + unsigned short srcu_idx_max; /* Furthest future srcu_idx request. */ u8 srcu_gp_running; /* GP workqueue running? */ u8 srcu_gp_waiting; /* GP waiting for readers? */ struct swait_queue_head srcu_wq; diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c index 3bac1db85a85..26344dc6483b 100644 --- a/kernel/rcu/srcutiny.c +++ b/kernel/rcu/srcutiny.c @@ -34,6 +34,7 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp) ssp->srcu_gp_running = false; ssp->srcu_gp_waiting = false; ssp->srcu_idx = 0; + ssp->srcu_idx_max = 0; INIT_WORK(&ssp->srcu_work, srcu_drive_gp); INIT_LIST_HEAD(&ssp->srcu_work.entry); return 0; @@ -84,6 +85,8 @@ void cleanup_srcu_struct(struct srcu_struct *ssp) WARN_ON(ssp->srcu_gp_waiting); WARN_ON(ssp->srcu_cb_head); WARN_ON(&ssp->srcu_cb_head != ssp->srcu_cb_tail); + WARN_ON(ssp->srcu_idx != ssp->srcu_idx_max); + WARN_ON(ssp->srcu_idx & 0x1); } EXPORT_SYMBOL_GPL(cleanup_srcu_struct); @@ -114,7 +117,7 @@ void srcu_drive_gp(struct work_struct *wp) struct srcu_struct *ssp; ssp = container_of(wp, struct srcu_struct, srcu_work); - if (ssp->srcu_gp_running || !READ_ONCE(ssp->srcu_cb_head)) + if (ssp->srcu_gp_running || USHORT_CMP_GE(ssp->srcu_idx, READ_ONCE(ssp->srcu_idx_max))) return; /* Already running or nothing to do. */ /* Remove recently arrived callbacks and wait for readers. */ @@ -147,13 +150,19 @@ void srcu_drive_gp(struct work_struct *wp) * straighten that out. */ WRITE_ONCE(ssp->srcu_gp_running, false); - if (READ_ONCE(ssp->srcu_cb_head)) + if (USHORT_CMP_LT(ssp->srcu_idx, READ_ONCE(ssp->srcu_idx_max))) schedule_work(&ssp->srcu_work); } EXPORT_SYMBOL_GPL(srcu_drive_gp); static void srcu_gp_start_if_needed(struct srcu_struct *ssp) { + unsigned short cookie; + + cookie = get_state_synchronize_srcu(ssp); + if (USHORT_CMP_GE(READ_ONCE(ssp->srcu_idx_max), cookie)) + return; + WRITE_ONCE(ssp->srcu_idx_max, cookie); if (!READ_ONCE(ssp->srcu_gp_running)) { if (likely(srcu_init_done)) schedule_work(&ssp->srcu_work); @@ -196,6 +205,48 @@ void synchronize_srcu(struct srcu_struct *ssp) } EXPORT_SYMBOL_GPL(synchronize_srcu); +/* + * get_state_synchronize_srcu - Provide an end-of-grace-period cookie + */ +unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp) +{ + unsigned long ret; + + barrier(); + ret = (READ_ONCE(ssp->srcu_idx) + 3) & ~0x1; + barrier(); + return ret & USHRT_MAX; +} +EXPORT_SYMBOL_GPL(get_state_synchronize_srcu); + +/* + * start_poll_synchronize_srcu - Provide cookie and start grace period + * + * The difference between this and get_state_synchronize_srcu() is that + * this function ensures that the poll_state_synchronize_srcu() will + * eventually return the value true. + */ +unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp) +{ + unsigned long ret = get_state_synchronize_srcu(ssp); + + srcu_gp_start_if_needed(ssp); + return ret; +} +EXPORT_SYMBOL_GPL(start_poll_synchronize_srcu); + +/* + * poll_state_synchronize_srcu - Has cookie's grace period ended? + */ +bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie) +{ + bool ret = USHORT_CMP_GE(READ_ONCE(ssp->srcu_idx), cookie); + + barrier(); + return ret; +} +EXPORT_SYMBOL_GPL(poll_state_synchronize_srcu); + /* Lockdep diagnostics. */ void __init rcu_scheduler_starting(void) { -- cgit v1.2.3 From 1890ee7ff87fc48806c37f3543e025e2252ac2e3 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Thu, 26 Aug 2021 12:46:01 -0700 Subject: net: don't unconditionally copy_from_user a struct ifreq for socket ioctls commit d0efb16294d145d157432feda83877ae9d7cdf37 upstream. A common implementation of isatty(3) involves calling a ioctl passing a dummy struct argument and checking whether the syscall failed -- bionic and glibc use TCGETS (passing a struct termios), and musl uses TIOCGWINSZ (passing a struct winsize). If the FD is a socket, we will copy sizeof(struct ifreq) bytes of data from the argument and return -EFAULT if that fails. The result is that the isatty implementations may return a non-POSIX-compliant value in errno in the case where part of the dummy struct argument is inaccessible, as both struct termios and struct winsize are smaller than struct ifreq (at least on arm64). Although there is usually enough stack space following the argument on the stack that this did not present a practical problem up to now, with MTE stack instrumentation it's more likely for the copy to fail, as the memory following the struct may have a different tag. Fix the problem by adding an early check for whether the ioctl is a valid socket ioctl, and return -ENOTTY if it isn't. Fixes: 44c02a2c3dc5 ("dev_ioctl(): move copyin/copyout to callers") Link: https://linux-review.googlesource.com/id/I869da6cf6daabc3e4b7b82ac979683ba05e27d4d Signed-off-by: Peter Collingbourne Cc: # 4.19 Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- include/linux/netdevice.h | 4 ++++ net/socket.c | 6 +++++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e37480b5f4c0..4fdeccf22378 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3884,6 +3884,10 @@ int netdev_rx_handler_register(struct net_device *dev, void netdev_rx_handler_unregister(struct net_device *dev); bool dev_valid_name(const char *name); +static inline bool is_socket_ioctl_cmd(unsigned int cmd) +{ + return _IOC_TYPE(cmd) == SOCK_IOC_TYPE; +} int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, bool *need_copyout); int dev_ifconf(struct net *net, struct ifconf *, int); diff --git a/net/socket.c b/net/socket.c index 002d5952ae5d..dd5da07bc1ff 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1062,7 +1062,7 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, rtnl_unlock(); if (!err && copy_to_user(argp, &ifc, sizeof(struct ifconf))) err = -EFAULT; - } else { + } else if (is_socket_ioctl_cmd(cmd)) { struct ifreq ifr; bool need_copyout; if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) @@ -1071,6 +1071,8 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, if (!err && need_copyout) if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) return -EFAULT; + } else { + err = -ENOTTY; } return err; } @@ -3264,6 +3266,8 @@ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd, struct ifreq ifreq; u32 data32; + if (!is_socket_ioctl_cmd(cmd)) + return -ENOTTY; if (copy_from_user(ifreq.ifr_name, u_ifreq32->ifr_name, IFNAMSIZ)) return -EFAULT; if (get_user(data32, &u_ifreq32->ifr_data)) -- cgit v1.2.3 From 0c9a876f2897c64d21a5a414a9007a10cd015a9e Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Mon, 9 Aug 2021 18:04:13 -0700 Subject: bpf: Fix potentially incorrect results with bpf_get_local_storage() commit a2baf4e8bb0f306fbed7b5e6197c02896a638ab5 upstream. Commit b910eaaaa4b8 ("bpf: Fix NULL pointer dereference in bpf_get_local_storage() helper") fixed a bug for bpf_get_local_storage() helper so different tasks won't mess up with each other's percpu local storage. The percpu data contains 8 slots so it can hold up to 8 contexts (same or different tasks), for 8 different program runs, at the same time. This in general is sufficient. But our internal testing showed the following warning multiple times: [...] warning: WARNING: CPU: 13 PID: 41661 at include/linux/bpf-cgroup.h:193 __cgroup_bpf_run_filter_sock_ops+0x13e/0x180 RIP: 0010:__cgroup_bpf_run_filter_sock_ops+0x13e/0x180 tcp_call_bpf.constprop.99+0x93/0xc0 tcp_conn_request+0x41e/0xa50 ? tcp_rcv_state_process+0x203/0xe00 tcp_rcv_state_process+0x203/0xe00 ? sk_filter_trim_cap+0xbc/0x210 ? tcp_v6_inbound_md5_hash.constprop.41+0x44/0x160 tcp_v6_do_rcv+0x181/0x3e0 tcp_v6_rcv+0xc65/0xcb0 ip6_protocol_deliver_rcu+0xbd/0x450 ip6_input_finish+0x11/0x20 ip6_input+0xb5/0xc0 ip6_sublist_rcv_finish+0x37/0x50 ip6_sublist_rcv+0x1dc/0x270 ipv6_list_rcv+0x113/0x140 __netif_receive_skb_list_core+0x1a0/0x210 netif_receive_skb_list_internal+0x186/0x2a0 gro_normal_list.part.170+0x19/0x40 napi_complete_done+0x65/0x150 mlx5e_napi_poll+0x1ae/0x680 __napi_poll+0x25/0x120 net_rx_action+0x11e/0x280 __do_softirq+0xbb/0x271 irq_exit_rcu+0x97/0xa0 common_interrupt+0x7f/0xa0 asm_common_interrupt+0x1e/0x40 RIP: 0010:bpf_prog_1835a9241238291a_tw_egress+0x5/0xbac ? __cgroup_bpf_run_filter_skb+0x378/0x4e0 ? do_softirq+0x34/0x70 ? ip6_finish_output2+0x266/0x590 ? ip6_finish_output+0x66/0xa0 ? ip6_output+0x6c/0x130 ? ip6_xmit+0x279/0x550 ? ip6_dst_check+0x61/0xd0 [...] Using drgn [0] to dump the percpu buffer contents showed that on this CPU slot 0 is still available, but slots 1-7 are occupied and those tasks in slots 1-7 mostly don't exist any more. So we might have issues in bpf_cgroup_storage_unset(). Further debugging confirmed that there is a bug in bpf_cgroup_storage_unset(). Currently, it tries to unset "current" slot with searching from the start. So the following sequence is possible: 1. A task is running and claims slot 0 2. Running BPF program is done, and it checked slot 0 has the "task" and ready to reset it to NULL (not yet). 3. An interrupt happens, another BPF program runs and it claims slot 1 with the *same* task. 4. The unset() in interrupt context releases slot 0 since it matches "task". 5. Interrupt is done, the task in process context reset slot 0. At the end, slot 1 is not reset and the same process can continue to occupy slots 2-7 and finally, when the above step 1-5 is repeated again, step 3 BPF program won't be able to claim an empty slot and a warning will be issued. To fix the issue, for unset() function, we should traverse from the last slot to the first. This way, the above issue can be avoided. The same reverse traversal should also be done in bpf_get_local_storage() helper itself. Otherwise, incorrect local storage may be returned to BPF program. [0] https://github.com/osandov/drgn Fixes: b910eaaaa4b8 ("bpf: Fix NULL pointer dereference in bpf_get_local_storage() helper") Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210810010413.1976277-1-yhs@fb.com Signed-off-by: Greg Kroah-Hartman --- include/linux/bpf-cgroup.h | 4 ++-- kernel/bpf/helpers.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 53f14e8827cc..91b966978541 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -196,8 +196,8 @@ static inline void bpf_cgroup_storage_unset(void) { int i; - for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { - if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) + for (i = BPF_CGROUP_STORAGE_NEST_MAX - 1; i >= 0; i--) { + if (likely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) continue; this_cpu_write(bpf_cgroup_storage_info[i].task, NULL); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 3bd7fbd8c543..0efe7c7bfe5e 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -386,8 +386,8 @@ BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) void *ptr; int i; - for (i = 0; i < BPF_CGROUP_STORAGE_NEST_MAX; i++) { - if (unlikely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) + for (i = BPF_CGROUP_STORAGE_NEST_MAX - 1; i >= 0; i--) { + if (likely(this_cpu_read(bpf_cgroup_storage_info[i].task) != current)) continue; storage = this_cpu_read(bpf_cgroup_storage_info[i].storage[stype]); -- cgit v1.2.3 From b8c298cf57dcb5b18855f11437199fd0eb1ea388 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 1 Sep 2021 09:27:18 -0700 Subject: fscrypt: add fscrypt_symlink_getattr() for computing st_size commit d18760560593e5af921f51a8c9b64b6109d634c2 upstream. Add a helper function fscrypt_symlink_getattr() which will be called from the various filesystems' ->getattr() methods to read and decrypt the target of encrypted symlinks in order to report the correct st_size. Detailed explanation: As required by POSIX and as documented in various man pages, st_size for a symlink is supposed to be the length of the symlink target. Unfortunately, st_size has always been wrong for encrypted symlinks because st_size is populated from i_size from disk, which intentionally contains the length of the encrypted symlink target. That's slightly greater than the length of the decrypted symlink target (which is the symlink target that userspace usually sees), and usually won't match the length of the no-key encoded symlink target either. This hadn't been fixed yet because reporting the correct st_size would require reading the symlink target from disk and decrypting or encoding it, which historically has been considered too heavyweight to do in ->getattr(). Also historically, the wrong st_size had only broken a test (LTP lstat03) and there were no known complaints from real users. (This is probably because the st_size of symlinks isn't used too often, and when it is, typically it's for a hint for what buffer size to pass to readlink() -- which a slightly-too-large size still works for.) However, a couple things have changed now. First, there have recently been complaints about the current behavior from real users: - Breakage in rpmbuild: https://github.com/rpm-software-management/rpm/issues/1682 https://github.com/google/fscrypt/issues/305 - Breakage in toybox cpio: https://www.mail-archive.com/toybox@lists.landley.net/msg07193.html - Breakage in libgit2: https://issuetracker.google.com/issues/189629152 (on Android public issue tracker, requires login) Second, we now cache decrypted symlink targets in ->i_link. Therefore, taking the performance hit of reading and decrypting the symlink target in ->getattr() wouldn't be as big a deal as it used to be, since usually it will just save having to do the same thing later. Also note that eCryptfs ended up having to read and decrypt symlink targets in ->getattr() as well, to fix this same issue; see commit 3a60a1686f0d ("eCryptfs: Decrypt symlink target for stat size"). So, let's just bite the bullet, and read and decrypt the symlink target in ->getattr() in order to report the correct st_size. Add a function fscrypt_symlink_getattr() which the filesystems will call to do this. (Alternatively, we could store the decrypted size of symlinks on-disk. But there isn't a great place to do so, and encryption is meant to hide the original size to some extent; that property would be lost.) Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20210702065350.209646-2-ebiggers@kernel.org Signed-off-by: Eric Biggers Signed-off-by: Greg Kroah-Hartman --- fs/crypto/hooks.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/fscrypt.h | 7 +++++++ 2 files changed, 51 insertions(+) (limited to 'include/linux') diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c index 061418be4b08..4180371bf864 100644 --- a/fs/crypto/hooks.c +++ b/fs/crypto/hooks.c @@ -379,3 +379,47 @@ err_kfree: return ERR_PTR(err); } EXPORT_SYMBOL_GPL(fscrypt_get_symlink); + +/** + * fscrypt_symlink_getattr() - set the correct st_size for encrypted symlinks + * @path: the path for the encrypted symlink being queried + * @stat: the struct being filled with the symlink's attributes + * + * Override st_size of encrypted symlinks to be the length of the decrypted + * symlink target (or the no-key encoded symlink target, if the key is + * unavailable) rather than the length of the encrypted symlink target. This is + * necessary for st_size to match the symlink target that userspace actually + * sees. POSIX requires this, and some userspace programs depend on it. + * + * This requires reading the symlink target from disk if needed, setting up the + * inode's encryption key if possible, and then decrypting or encoding the + * symlink target. This makes lstat() more heavyweight than is normally the + * case. However, decrypted symlink targets will be cached in ->i_link, so + * usually the symlink won't have to be read and decrypted again later if/when + * it is actually followed, readlink() is called, or lstat() is called again. + * + * Return: 0 on success, -errno on failure + */ +int fscrypt_symlink_getattr(const struct path *path, struct kstat *stat) +{ + struct dentry *dentry = path->dentry; + struct inode *inode = d_inode(dentry); + const char *link; + DEFINE_DELAYED_CALL(done); + + /* + * To get the symlink target that userspace will see (whether it's the + * decrypted target or the no-key encoded target), we can just get it in + * the same way the VFS does during path resolution and readlink(). + */ + link = READ_ONCE(inode->i_link); + if (!link) { + link = inode->i_op->get_link(dentry, inode, &done); + if (IS_ERR(link)) + return PTR_ERR(link); + } + stat->size = strlen(link); + do_delayed_call(&done); + return 0; +} +EXPORT_SYMBOL_GPL(fscrypt_symlink_getattr); diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 8e1d31c959bf..d0a1b8edfd9d 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -252,6 +252,7 @@ int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, unsigned int max_size, struct delayed_call *done); +int fscrypt_symlink_getattr(const struct path *path, struct kstat *stat); static inline void fscrypt_set_ops(struct super_block *sb, const struct fscrypt_operations *s_cop) { @@ -575,6 +576,12 @@ static inline const char *fscrypt_get_symlink(struct inode *inode, return ERR_PTR(-EOPNOTSUPP); } +static inline int fscrypt_symlink_getattr(const struct path *path, + struct kstat *stat) +{ + return -EOPNOTSUPP; +} + static inline void fscrypt_set_ops(struct super_block *sb, const struct fscrypt_operations *s_cop) { -- cgit v1.2.3 From ae16b7c668378ea00eb60ab9d29e0d46b0e7aa15 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 3 Sep 2021 16:06:50 +0200 Subject: Revert "Add a reference to ucounts for each cred" This reverts commit b2c4d9a33cc2dec7466f97eba2c4dd571ad798a5 which is commit 905ae01c4ae2ae3df05bb141801b1db4b7d83c61 upstream. This commit should not have been applied to the 5.10.y stable tree, so revert it. Reported-by: "Eric W. Biederman" Link: https://lore.kernel.org/r/87v93k4bl6.fsf@disp2133 Cc: Alexey Gladkov Cc: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- fs/exec.c | 4 ---- include/linux/cred.h | 2 -- include/linux/user_namespace.h | 4 ---- kernel/cred.c | 40 ---------------------------------------- kernel/fork.c | 6 ------ kernel/sys.c | 12 ------------ kernel/ucount.c | 40 +++------------------------------------- kernel/user_namespace.c | 3 --- 8 files changed, 3 insertions(+), 108 deletions(-) (limited to 'include/linux') diff --git a/fs/exec.c b/fs/exec.c index c7a4ef8df305..ca89e0e3ef10 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1347,10 +1347,6 @@ int begin_new_exec(struct linux_binprm * bprm) WRITE_ONCE(me->self_exec_id, me->self_exec_id + 1); flush_signal_handlers(me, 0); - retval = set_cred_ucounts(bprm->cred); - if (retval < 0) - goto out_unlock; - /* * install the new credentials for this executable */ diff --git a/include/linux/cred.h b/include/linux/cred.h index ad160e5fe5c6..18639c069263 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -144,7 +144,6 @@ struct cred { #endif struct user_struct *user; /* real user ID subscription */ struct user_namespace *user_ns; /* user_ns the caps and keyrings are relative to. */ - struct ucounts *ucounts; struct group_info *group_info; /* supplementary groups for euid/fsgid */ /* RCU deletion */ union { @@ -171,7 +170,6 @@ extern int set_security_override_from_ctx(struct cred *, const char *); extern int set_create_files_as(struct cred *, struct inode *); extern int cred_fscmp(const struct cred *, const struct cred *); extern void __init cred_init(void); -extern int set_cred_ucounts(struct cred *); /* * check for validity of credentials diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index e1bd560da1cd..7616c7bf4b24 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -101,15 +101,11 @@ struct ucounts { }; extern struct user_namespace init_user_ns; -extern struct ucounts init_ucounts; bool setup_userns_sysctls(struct user_namespace *ns); void retire_userns_sysctls(struct user_namespace *ns); struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid, enum ucount_type type); void dec_ucount(struct ucounts *ucounts, enum ucount_type type); -struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid); -struct ucounts *get_ucounts(struct ucounts *ucounts); -void put_ucounts(struct ucounts *ucounts); #ifdef CONFIG_USER_NS diff --git a/kernel/cred.c b/kernel/cred.c index 58a8a9e24347..421b1149c651 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -60,7 +60,6 @@ struct cred init_cred = { .user = INIT_USER, .user_ns = &init_user_ns, .group_info = &init_groups, - .ucounts = &init_ucounts, }; static inline void set_cred_subscribers(struct cred *cred, int n) @@ -120,8 +119,6 @@ static void put_cred_rcu(struct rcu_head *rcu) if (cred->group_info) put_group_info(cred->group_info); free_uid(cred->user); - if (cred->ucounts) - put_ucounts(cred->ucounts); put_user_ns(cred->user_ns); kmem_cache_free(cred_jar, cred); } @@ -225,7 +222,6 @@ struct cred *cred_alloc_blank(void) #ifdef CONFIG_DEBUG_CREDENTIALS new->magic = CRED_MAGIC; #endif - new->ucounts = get_ucounts(&init_ucounts); if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0) goto error; @@ -288,11 +284,6 @@ struct cred *prepare_creds(void) if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) goto error; - - new->ucounts = get_ucounts(new->ucounts); - if (!new->ucounts) - goto error; - validate_creds(new); return new; @@ -372,8 +363,6 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags) ret = create_user_ns(new); if (ret < 0) goto error_put; - if (set_cred_ucounts(new) < 0) - goto error_put; } #ifdef CONFIG_KEYS @@ -664,31 +653,6 @@ int cred_fscmp(const struct cred *a, const struct cred *b) } EXPORT_SYMBOL(cred_fscmp); -int set_cred_ucounts(struct cred *new) -{ - struct task_struct *task = current; - const struct cred *old = task->real_cred; - struct ucounts *old_ucounts = new->ucounts; - - if (new->user == old->user && new->user_ns == old->user_ns) - return 0; - - /* - * This optimization is needed because alloc_ucounts() uses locks - * for table lookups. - */ - if (old_ucounts && old_ucounts->ns == new->user_ns && uid_eq(old_ucounts->uid, new->euid)) - return 0; - - if (!(new->ucounts = alloc_ucounts(new->user_ns, new->euid))) - return -EAGAIN; - - if (old_ucounts) - put_ucounts(old_ucounts); - - return 0; -} - /* * initialise the credentials stuff */ @@ -755,10 +719,6 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon) if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0) goto error; - new->ucounts = get_ucounts(new->ucounts); - if (!new->ucounts) - goto error; - put_cred(old); validate_creds(new); return new; diff --git a/kernel/fork.c b/kernel/fork.c index 096945ef49ad..9705439439fe 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2960,12 +2960,6 @@ int ksys_unshare(unsigned long unshare_flags) if (err) goto bad_unshare_cleanup_cred; - if (new_cred) { - err = set_cred_ucounts(new_cred); - if (err) - goto bad_unshare_cleanup_cred; - } - if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) { if (do_sysvsem) { /* diff --git a/kernel/sys.c b/kernel/sys.c index 0670e824e019..a730c03ee607 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -552,10 +552,6 @@ long __sys_setreuid(uid_t ruid, uid_t euid) if (retval < 0) goto error; - retval = set_cred_ucounts(new); - if (retval < 0) - goto error; - return commit_creds(new); error: @@ -614,10 +610,6 @@ long __sys_setuid(uid_t uid) if (retval < 0) goto error; - retval = set_cred_ucounts(new); - if (retval < 0) - goto error; - return commit_creds(new); error: @@ -693,10 +685,6 @@ long __sys_setresuid(uid_t ruid, uid_t euid, uid_t suid) if (retval < 0) goto error; - retval = set_cred_ucounts(new); - if (retval < 0) - goto error; - return commit_creds(new); error: diff --git a/kernel/ucount.c b/kernel/ucount.c index 9894795043c4..11b1596e2542 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -8,12 +8,6 @@ #include #include -struct ucounts init_ucounts = { - .ns = &init_user_ns, - .uid = GLOBAL_ROOT_UID, - .count = 1, -}; - #define UCOUNTS_HASHTABLE_BITS 10 static struct hlist_head ucounts_hashtable[(1 << UCOUNTS_HASHTABLE_BITS)]; static DEFINE_SPINLOCK(ucounts_lock); @@ -131,15 +125,7 @@ static struct ucounts *find_ucounts(struct user_namespace *ns, kuid_t uid, struc return NULL; } -static void hlist_add_ucounts(struct ucounts *ucounts) -{ - struct hlist_head *hashent = ucounts_hashentry(ucounts->ns, ucounts->uid); - spin_lock_irq(&ucounts_lock); - hlist_add_head(&ucounts->node, hashent); - spin_unlock_irq(&ucounts_lock); -} - -struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid) +static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid) { struct hlist_head *hashent = ucounts_hashentry(ns, uid); struct ucounts *ucounts, *new; @@ -174,26 +160,7 @@ struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid) return ucounts; } -struct ucounts *get_ucounts(struct ucounts *ucounts) -{ - unsigned long flags; - - if (!ucounts) - return NULL; - - spin_lock_irqsave(&ucounts_lock, flags); - if (ucounts->count == INT_MAX) { - WARN_ONCE(1, "ucounts: counter has reached its maximum value"); - ucounts = NULL; - } else { - ucounts->count += 1; - } - spin_unlock_irqrestore(&ucounts_lock, flags); - - return ucounts; -} - -void put_ucounts(struct ucounts *ucounts) +static void put_ucounts(struct ucounts *ucounts) { unsigned long flags; @@ -227,7 +194,7 @@ struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid, { struct ucounts *ucounts, *iter, *bad; struct user_namespace *tns; - ucounts = alloc_ucounts(ns, uid); + ucounts = get_ucounts(ns, uid); for (iter = ucounts; iter; iter = tns->ucounts) { int max; tns = iter->ns; @@ -270,7 +237,6 @@ static __init int user_namespace_sysctl_init(void) BUG_ON(!user_header); BUG_ON(!setup_userns_sysctls(&init_user_ns)); #endif - hlist_add_ucounts(&init_ucounts); return 0; } subsys_initcall(user_namespace_sysctl_init); diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 8206a13c81eb..ce396ea4de60 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -1340,9 +1340,6 @@ static int userns_install(struct nsset *nsset, struct ns_common *ns) put_user_ns(cred->user_ns); set_cred_user_ns(cred, get_user_ns(user_ns)); - if (set_cred_ucounts(cred) < 0) - return -EINVAL; - return 0; } -- cgit v1.2.3 From ded9137fcf0d729dbe65aa98c411352f40b22970 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 10 May 2021 16:12:42 +0300 Subject: spi: Switch to signed types for *_native_cs SPI controller fields commit 35f3f8504c3b60a1ae5576e178b27fc0ddd6157d upstream. While fixing undefined behaviour the commit f60d7270c8a3 ("spi: Avoid undefined behaviour when counting unused native CSs") missed the case when all CSs are GPIOs and thus unused_native_cs will be evaluated to -1 in unsigned representation. This will falsely trigger a condition in the spi_get_gpio_descs(). Switch to signed types for *_native_cs SPI controller fields to fix above. Fixes: f60d7270c8a3 ("spi: Avoid undefined behaviour when counting unused native CSs") Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20210510131242.49455-1-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown Signed-off-by: Nobuhiro Iwamatsu (CIP) Signed-off-by: Greg Kroah-Hartman --- include/linux/spi/spi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 2d906b9c1499..e1d88630ff24 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -646,8 +646,8 @@ struct spi_controller { int *cs_gpios; struct gpio_desc **cs_gpiods; bool use_gpio_descriptors; - u8 unused_native_cs; - u8 max_native_cs; + s8 unused_native_cs; + s8 max_native_cs; /* statistics */ struct spi_statistics statistics; -- cgit v1.2.3 From 40ba433a85dbbf5b2e58f2ac6b161ce37ac872fc Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 1 Mar 2021 20:37:10 -0500 Subject: new helper: inode_wrong_type() commit 6e3e2c4362e41a2f18e3f7a5ad81bd2f49a47b85 upstream. inode_wrong_type(inode, mode) returns true if setting inode->i_mode to given value would've changed the inode type. We have enough of those checks open-coded to make a helper worthwhile. Signed-off-by: Al Viro Signed-off-by: Amir Goldstein Signed-off-by: Greg Kroah-Hartman --- fs/9p/vfs_inode.c | 4 ++-- fs/9p/vfs_inode_dotl.c | 4 ++-- fs/cifs/inode.c | 5 ++--- fs/fuse/dir.c | 6 +++--- fs/fuse/inode.c | 2 +- fs/fuse/readdir.c | 2 +- fs/nfs/inode.c | 6 +++--- fs/nfsd/nfsproc.c | 2 +- fs/overlayfs/namei.c | 4 ++-- include/linux/fs.h | 5 +++++ 10 files changed, 22 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index ae0c38ad1fcb..0791480bf922 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -398,7 +398,7 @@ static int v9fs_test_inode(struct inode *inode, void *data) umode = p9mode2unixmode(v9ses, st, &rdev); /* don't match inode of different type */ - if ((inode->i_mode & S_IFMT) != (umode & S_IFMT)) + if (inode_wrong_type(inode, umode)) return 0; /* compare qid details */ @@ -1360,7 +1360,7 @@ int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode) * Don't update inode if the file type is different */ umode = p9mode2unixmode(v9ses, st, &rdev); - if ((inode->i_mode & S_IFMT) != (umode & S_IFMT)) + if (inode_wrong_type(inode, umode)) goto out; /* diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 0028eccb665a..72b67d810b8c 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -59,7 +59,7 @@ static int v9fs_test_inode_dotl(struct inode *inode, void *data) struct p9_stat_dotl *st = (struct p9_stat_dotl *)data; /* don't match inode of different type */ - if ((inode->i_mode & S_IFMT) != (st->st_mode & S_IFMT)) + if (inode_wrong_type(inode, st->st_mode)) return 0; if (inode->i_generation != st->st_gen) @@ -933,7 +933,7 @@ int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode) /* * Don't update inode if the file type is different */ - if ((inode->i_mode & S_IFMT) != (st->st_mode & S_IFMT)) + if (inode_wrong_type(inode, st->st_mode)) goto out; /* diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index b1f0c05d6eaf..b11a919b9cab 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -425,8 +425,7 @@ int cifs_get_inode_info_unix(struct inode **pinode, } /* if filetype is different, return error */ - if (unlikely(((*pinode)->i_mode & S_IFMT) != - (fattr.cf_mode & S_IFMT))) { + if (unlikely(inode_wrong_type(*pinode, fattr.cf_mode))) { CIFS_I(*pinode)->time = 0; /* force reval */ rc = -ESTALE; goto cgiiu_exit; @@ -1243,7 +1242,7 @@ cifs_find_inode(struct inode *inode, void *opaque) return 0; /* don't match inode of different type */ - if ((inode->i_mode & S_IFMT) != (fattr->cf_mode & S_IFMT)) + if (inode_wrong_type(inode, fattr->cf_mode)) return 0; /* if it's not a directory or has no dentries, then flag it */ diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 756bbdd563e0..37d50dde845e 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -252,7 +252,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) if (ret == -ENOMEM) goto out; if (ret || fuse_invalid_attr(&outarg.attr) || - (outarg.attr.mode ^ inode->i_mode) & S_IFMT) + inode_wrong_type(inode, outarg.attr.mode)) goto invalid; forget_all_cached_acls(inode); @@ -1062,7 +1062,7 @@ static int fuse_do_getattr(struct inode *inode, struct kstat *stat, err = fuse_simple_request(fm, &args); if (!err) { if (fuse_invalid_attr(&outarg.attr) || - (inode->i_mode ^ outarg.attr.mode) & S_IFMT) { + inode_wrong_type(inode, outarg.attr.mode)) { fuse_make_bad(inode); err = -EIO; } else { @@ -1699,7 +1699,7 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr, } if (fuse_invalid_attr(&outarg.attr) || - (inode->i_mode ^ outarg.attr.mode) & S_IFMT) { + inode_wrong_type(inode, outarg.attr.mode)) { fuse_make_bad(inode); err = -EIO; goto error; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index f94b0bb57619..6345c4679fb8 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -340,7 +340,7 @@ retry: inode->i_generation = generation; fuse_init_inode(inode, attr); unlock_new_inode(inode); - } else if ((inode->i_mode ^ attr->mode) & S_IFMT) { + } else if (inode_wrong_type(inode, attr->mode)) { /* Inode has changed type, any I/O on the old should fail */ fuse_make_bad(inode); iput(inode); diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c index 3441ffa740f3..277f7041d55a 100644 --- a/fs/fuse/readdir.c +++ b/fs/fuse/readdir.c @@ -202,7 +202,7 @@ retry: inode = d_inode(dentry); if (!inode || get_node_id(inode) != o->nodeid || - ((o->attr.mode ^ inode->i_mode) & S_IFMT)) { + inode_wrong_type(inode, o->attr.mode)) { d_invalidate(dentry); dput(dentry); goto retry; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 9811880470a0..21addb78523d 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -322,7 +322,7 @@ nfs_find_actor(struct inode *inode, void *opaque) if (NFS_FILEID(inode) != fattr->fileid) return 0; - if ((S_IFMT & inode->i_mode) != (S_IFMT & fattr->mode)) + if (inode_wrong_type(inode, fattr->mode)) return 0; if (nfs_compare_fh(NFS_FH(inode), fh)) return 0; @@ -1446,7 +1446,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat return 0; return -ESTALE; } - if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) + if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && inode_wrong_type(inode, fattr->mode)) return -ESTALE; @@ -1861,7 +1861,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) /* * Make sure the inode's type hasn't changed. */ - if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) { + if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && inode_wrong_type(inode, fattr->mode)) { /* * Big trouble! The inode has become a different object. */ diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 0d71549f9d42..9c9de2b66e64 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -376,7 +376,7 @@ nfsd_proc_create(struct svc_rqst *rqstp) /* Make sure the type and device matches */ resp->status = nfserr_exist; - if (inode && type != (inode->i_mode & S_IFMT)) + if (inode && inode_wrong_type(inode, type)) goto out_unlock; } diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index f3309e044f07..092812c2f118 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -366,7 +366,7 @@ int ovl_check_origin_fh(struct ovl_fs *ofs, struct ovl_fh *fh, bool connected, return PTR_ERR(origin); if (upperdentry && !ovl_is_whiteout(upperdentry) && - ((d_inode(origin)->i_mode ^ d_inode(upperdentry)->i_mode) & S_IFMT)) + inode_wrong_type(d_inode(upperdentry), d_inode(origin)->i_mode)) goto invalid; if (!*stackp) @@ -724,7 +724,7 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper, index = ERR_PTR(-ESTALE); goto out; } else if (ovl_dentry_weird(index) || ovl_is_whiteout(index) || - ((inode->i_mode ^ d_inode(origin)->i_mode) & S_IFMT)) { + inode_wrong_type(inode, d_inode(origin)->i_mode)) { /* * Index should always be of the same file type as origin * except for the case of a whiteout index. A whiteout diff --git a/include/linux/fs.h b/include/linux/fs.h index 8bde32cf9711..43bb6a51e42d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2768,6 +2768,11 @@ static inline bool execute_ok(struct inode *inode) return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode); } +static inline bool inode_wrong_type(const struct inode *inode, umode_t mode) +{ + return (inode->i_mode ^ mode) & S_IFMT; +} + static inline void file_start_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) -- cgit v1.2.3 From 0757a883b97022ef50af422697993ee7fc4a1b79 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 16 Nov 2020 13:21:08 -0800 Subject: net: linux/skbuff.h: combine SKB_EXTENSIONS + KCOV handling commit 97f53a08cba128a724ebbbf34778d3553d559816 upstream. The previous Kconfig patch led to some other build errors as reported by the 0day bot and my own overnight build testing. These are all in when KCOV is enabled but SKB_EXTENSIONS is not enabled, so fix those by combining those conditions in the header file. Fixes: 6370cc3bbd8a ("net: add kcov handle to skb extensions") Fixes: 85ce50d337d1 ("net: kcov: don't select SKB_EXTENSIONS when there is no NET") Signed-off-by: Randy Dunlap Reported-by: kernel test robot Cc: Aleksandr Nogikh Cc: Willem de Bruijn Acked-by: Florian Westphal Link: https://lore.kernel.org/r/20201116212108.32465-1-rdunlap@infradead.org Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- include/linux/skbuff.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2d01b2bbb746..0a1239819fd2 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4608,7 +4608,7 @@ static inline void skb_reset_redirect(struct sk_buff *skb) #endif } -#ifdef CONFIG_KCOV +#if IS_ENABLED(CONFIG_KCOV) && IS_ENABLED(CONFIG_SKB_EXTENSIONS) static inline void skb_set_kcov_handle(struct sk_buff *skb, const u64 kcov_handle) { @@ -4636,7 +4636,7 @@ static inline u64 skb_get_kcov_handle(struct sk_buff *skb) static inline void skb_set_kcov_handle(struct sk_buff *skb, const u64 kcov_handle) { } static inline u64 skb_get_kcov_handle(struct sk_buff *skb) { return 0; } -#endif /* CONFIG_KCOV */ +#endif /* CONFIG_KCOV && CONFIG_SKB_EXTENSIONS */ #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ -- cgit v1.2.3 From 3d12ccecfa316730abaf0a930711ea5cce4fe87f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 13 Jul 2021 15:39:48 +0200 Subject: hrtimer: Ensure timerfd notification for HIGHRES=n [ Upstream commit 8c3b5e6ec0fee18bc2ce38d1dfe913413205f908 ] If high resolution timers are disabled the timerfd notification about a clock was set event is not happening for all cases which use clock_was_set_delayed() because that's a NOP for HIGHRES=n, which is wrong. Make clock_was_set_delayed() unconditially available to fix that. Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20210713135158.196661266@linutronix.de Signed-off-by: Sasha Levin --- include/linux/hrtimer.h | 5 ----- kernel/time/hrtimer.c | 32 ++++++++++++++++---------------- kernel/time/tick-internal.h | 3 +++ 3 files changed, 19 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 107cedd7019a..7f1b8549ebce 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -318,16 +318,12 @@ struct clock_event_device; extern void hrtimer_interrupt(struct clock_event_device *dev); -extern void clock_was_set_delayed(void); - extern unsigned int hrtimer_resolution; #else #define hrtimer_resolution (unsigned int)LOW_RES_NSEC -static inline void clock_was_set_delayed(void) { } - #endif static inline ktime_t @@ -351,7 +347,6 @@ hrtimer_expires_remaining_adjusted(const struct hrtimer *timer) timer->base->get_time()); } -extern void clock_was_set(void); #ifdef CONFIG_TIMERFD extern void timerfd_clock_was_set(void); #else diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 4bdceb1ff069..4ef90718c114 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -758,22 +758,6 @@ static void hrtimer_switch_to_hres(void) retrigger_next_event(NULL); } -static void clock_was_set_work(struct work_struct *work) -{ - clock_was_set(); -} - -static DECLARE_WORK(hrtimer_work, clock_was_set_work); - -/* - * Called from timekeeping and resume code to reprogram the hrtimer - * interrupt device on all cpus. - */ -void clock_was_set_delayed(void) -{ - schedule_work(&hrtimer_work); -} - #else static inline int hrtimer_is_hres_enabled(void) { return 0; } @@ -891,6 +875,22 @@ void clock_was_set(void) timerfd_clock_was_set(); } +static void clock_was_set_work(struct work_struct *work) +{ + clock_was_set(); +} + +static DECLARE_WORK(hrtimer_work, clock_was_set_work); + +/* + * Called from timekeeping and resume code to reprogram the hrtimer + * interrupt device on all cpus and to notify timerfd. + */ +void clock_was_set_delayed(void) +{ + schedule_work(&hrtimer_work); +} + /* * During resume we might have to reprogram the high resolution timer * interrupt on all online CPUs. However, all other CPUs will be diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 7b2496136729..5294f5b1f955 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -165,3 +165,6 @@ DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases); extern u64 get_next_timer_interrupt(unsigned long basej, u64 basem); void timer_clear_idle(void); + +void clock_was_set(void); +void clock_was_set_delayed(void); -- cgit v1.2.3 From d0831db736bb88ea60ac6982f1b5c355d861bd41 Mon Sep 17 00:00:00 2001 From: Sebastian Krzyszkowiak Date: Mon, 16 Aug 2021 18:50:14 +0200 Subject: power: supply: max17042_battery: fix typo in MAx17042_TOFF [ Upstream commit ed0d0a0506025f06061325cedae1bbebd081620a ] Signed-off-by: Sebastian Krzyszkowiak Signed-off-by: Sebastian Reichel Signed-off-by: Sasha Levin --- drivers/power/supply/max17042_battery.c | 2 +- include/linux/power/max17042_battery.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/power/supply/max17042_battery.c b/drivers/power/supply/max17042_battery.c index 794caf03658d..48d3985eaa8a 100644 --- a/drivers/power/supply/max17042_battery.c +++ b/drivers/power/supply/max17042_battery.c @@ -738,7 +738,7 @@ static inline void max17042_override_por_values(struct max17042_chip *chip) struct max17042_config_data *config = chip->pdata->config_data; max17042_override_por(map, MAX17042_TGAIN, config->tgain); - max17042_override_por(map, MAx17042_TOFF, config->toff); + max17042_override_por(map, MAX17042_TOFF, config->toff); max17042_override_por(map, MAX17042_CGAIN, config->cgain); max17042_override_por(map, MAX17042_COFF, config->coff); diff --git a/include/linux/power/max17042_battery.h b/include/linux/power/max17042_battery.h index d55c746ac56e..e00ad1cfb1f1 100644 --- a/include/linux/power/max17042_battery.h +++ b/include/linux/power/max17042_battery.h @@ -69,7 +69,7 @@ enum max17042_register { MAX17042_RelaxCFG = 0x2A, MAX17042_MiscCFG = 0x2B, MAX17042_TGAIN = 0x2C, - MAx17042_TOFF = 0x2D, + MAX17042_TOFF = 0x2D, MAX17042_CGAIN = 0x2E, MAX17042_COFF = 0x2F, -- cgit v1.2.3 From 87aa69aa10b420823174eedcfd16366ad3d7fe93 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 29 Jul 2021 11:42:26 +0800 Subject: block: return ELEVATOR_DISCARD_MERGE if possible [ Upstream commit 866663b7b52d2da267b28e12eed89ee781b8fed1 ] When merging one bio to request, if they are discard IO and the queue supports multi-range discard, we need to return ELEVATOR_DISCARD_MERGE because both block core and related drivers(nvme, virtio-blk) doesn't handle mixed discard io merge(traditional IO merge together with discard merge) well. Fix the issue by returning ELEVATOR_DISCARD_MERGE in this situation, so both blk-mq and drivers just need to handle multi-range discard. Reported-by: Oleksandr Natalenko Signed-off-by: Ming Lei Tested-by: Oleksandr Natalenko Fixes: 2705dfb20947 ("block: fix discard request merge") Link: https://lore.kernel.org/r/20210729034226.1591070-1-ming.lei@redhat.com Signed-off-by: Jens Axboe Signed-off-by: Sasha Levin --- block/bfq-iosched.c | 3 +++ block/blk-merge.c | 16 ---------------- block/elevator.c | 3 +++ block/mq-deadline.c | 2 ++ include/linux/blkdev.h | 16 ++++++++++++++++ 5 files changed, 24 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index c91dca641eb4..8ea37328ca84 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -2251,6 +2251,9 @@ static int bfq_request_merge(struct request_queue *q, struct request **req, __rq = bfq_find_rq_fmerge(bfqd, bio, q); if (__rq && elv_bio_merge_ok(__rq, bio)) { *req = __rq; + + if (blk_discard_mergable(__rq)) + return ELEVATOR_DISCARD_MERGE; return ELEVATOR_FRONT_MERGE; } diff --git a/block/blk-merge.c b/block/blk-merge.c index 110db636d230..26f4bcc10de9 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -702,22 +702,6 @@ static void blk_account_io_merge_request(struct request *req) } } -/* - * Two cases of handling DISCARD merge: - * If max_discard_segments > 1, the driver takes every bio - * as a range and send them to controller together. The ranges - * needn't to be contiguous. - * Otherwise, the bios/requests will be handled as same as - * others which should be contiguous. - */ -static inline bool blk_discard_mergable(struct request *req) -{ - if (req_op(req) == REQ_OP_DISCARD && - queue_max_discard_segments(req->q) > 1) - return true; - return false; -} - static enum elv_merge blk_try_req_merge(struct request *req, struct request *next) { diff --git a/block/elevator.c b/block/elevator.c index 293c5c81397a..2a525863d4e9 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -336,6 +336,9 @@ enum elv_merge elv_merge(struct request_queue *q, struct request **req, __rq = elv_rqhash_find(q, bio->bi_iter.bi_sector); if (__rq && elv_bio_merge_ok(__rq, bio)) { *req = __rq; + + if (blk_discard_mergable(__rq)) + return ELEVATOR_DISCARD_MERGE; return ELEVATOR_BACK_MERGE; } diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 2b9635d0dcba..e4e90761eab3 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -454,6 +454,8 @@ static int dd_request_merge(struct request_queue *q, struct request **rq, if (elv_bio_merge_ok(__rq, bio)) { *rq = __rq; + if (blk_discard_mergable(__rq)) + return ELEVATOR_DISCARD_MERGE; return ELEVATOR_FRONT_MERGE; } } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 542471b76f41..8aae375864b6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1534,6 +1534,22 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector return offset << SECTOR_SHIFT; } +/* + * Two cases of handling DISCARD merge: + * If max_discard_segments > 1, the driver takes every bio + * as a range and send them to controller together. The ranges + * needn't to be contiguous. + * Otherwise, the bios/requests will be handled as same as + * others which should be contiguous. + */ +static inline bool blk_discard_mergable(struct request *req) +{ + if (req_op(req) == REQ_OP_DISCARD && + queue_max_discard_segments(req->q) > 1) + return true; + return false; +} + static inline int bdev_discard_alignment(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); -- cgit v1.2.3 From 7a0b297480ddfc1416393cea49ae93bc4cfb3739 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Fri, 23 Apr 2021 20:34:48 +0300 Subject: net/mlx5e: Block LRO if firmware asks for tunneled LRO [ Upstream commit 26ab7b384525ccfa678c518577f7f0d841209c8b ] This commit does a cleanup in LRO configuration. LRO is a parameter of an RQ, but its state is changed by modifying a TIR related to the RQ. The current status: LRO for tunneled packets is not supported in the driver, inner TIRs may enable LRO on creation, but LRO status of inner TIRs isn't changed in mlx5e_modify_tirs_lro(). This is inconsistent, but as long as the firmware doesn't declare support for tunneled LRO, it works, because the same RQs are shared between the inner and outer TIRs. This commit does two fixes: 1. If the firmware has the tunneled LRO capability, LRO is blocked altogether, because it's not possible to block it for inner TIRs only, when the same RQs are shared between inner and outer TIRs, and the driver won't be able to handle tunneled LRO traffic. 2. mlx5e_modify_tirs_lro() is patched to modify LRO state for all TIRs, including inner ones, because all TIRs related to an RQ should agree on their LRO state. Fixes: 7b3722fa9ef6 ("net/mlx5e: Support RSS for GRE tunneled packets") Signed-off-by: Maxim Mikityanskiy Signed-off-by: Saeed Mahameed Signed-off-by: Sasha Levin --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 15 +++++++++++++++ include/linux/mlx5/mlx5_ifc.h | 3 ++- 2 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 6b4a3d90c9f7..6974090a7efa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2803,6 +2803,14 @@ static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv) err = mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in); if (err) goto free_in; + + /* Verify inner tirs resources allocated */ + if (!priv->inner_indir_tir[0].tirn) + continue; + + err = mlx5_core_modify_tir(mdev, priv->inner_indir_tir[tt].tirn, in); + if (err) + goto free_in; } for (ix = 0; ix < priv->max_nch; ix++) { @@ -4928,7 +4936,14 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->hw_enc_features |= NETIF_F_HW_VLAN_CTAG_TX; netdev->hw_enc_features |= NETIF_F_HW_VLAN_CTAG_RX; + /* Tunneled LRO is not supported in the driver, and the same RQs are + * shared between inner and outer TIRs, so the driver can't disable LRO + * for inner TIRs while having it enabled for outer TIRs. Due to this, + * block LRO altogether if the firmware declares tunneled LRO support. + */ if (!!MLX5_CAP_ETH(mdev, lro_cap) && + !MLX5_CAP_ETH(mdev, tunnel_lro_vxlan) && + !MLX5_CAP_ETH(mdev, tunnel_lro_gre) && mlx5e_check_fragmented_striding_rq_cap(mdev)) netdev->vlan_features |= NETIF_F_LRO; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index af8f4e2cf21d..70a3664785f8 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -876,7 +876,8 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 scatter_fcs[0x1]; u8 enhanced_multi_pkt_send_wqe[0x1]; u8 tunnel_lso_const_out_ip_id[0x1]; - u8 reserved_at_1c[0x2]; + u8 tunnel_lro_gre[0x1]; + u8 tunnel_lro_vxlan[0x1]; u8 tunnel_stateless_gre[0x1]; u8 tunnel_stateless_vxlan[0x1]; -- cgit v1.2.3 From d6337dfd1e772660102316ec04c5a2d3ef7bf7d1 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Tue, 3 Aug 2021 11:27:43 +0100 Subject: PM: EM: Increase energy calculation precision [ Upstream commit 7fcc17d0cb12938d2b3507973a6f93fc9ed2c7a1 ] The Energy Model (EM) provides useful information about device power in each performance state to other subsystems like: Energy Aware Scheduler (EAS). The energy calculation in EAS does arithmetic operation based on the EM em_cpu_energy(). Current implementation of that function uses em_perf_state::cost as a pre-computed cost coefficient equal to: cost = power * max_frequency / frequency. The 'power' is expressed in milli-Watts (or in abstract scale). There are corner cases when the EAS energy calculation for two Performance Domains (PDs) return the same value. The EAS compares these values to choose smaller one. It might happen that this values are equal due to rounding error. In such scenario, we need better resolution, e.g. 1000 times better. To provide this possibility increase the resolution in the em_perf_state::cost for 64-bit architectures. The cost of increasing resolution on 32-bit is pretty high (64-bit division) and is not justified since there are no new 32bit big.LITTLE EAS systems expected which would benefit from this higher resolution. This patch allows to avoid the rounding to milli-Watt errors, which might occur in EAS energy estimation for each PD. The rounding error is common for small tasks which have small utilization value. There are two places in the code where it makes a difference: 1. In the find_energy_efficient_cpu() where we are searching for best_delta. We might suffer there when two PDs return the same result, like in the example below. Scenario: Low utilized system e.g. ~200 sum_util for PD0 and ~220 for PD1. There are quite a few small tasks ~10-15 util. These tasks would suffer for the rounding error. These utilization values are typical when running games on Android. One of our partners has reported 5..10mA less battery drain when running with increased resolution. Some details: We have two PDs: PD0 (big) and PD1 (little) Let's compare w/o patch set ('old') and w/ patch set ('new') We are comparing energy w/ task and w/o task placed in the PDs a) 'old' w/o patch set, PD0 task_util = 13 cost = 480 sum_util_w/o_task = 215 sum_util_w_task = 228 scale_cpu = 1024 energy_w/o_task = 480 * 215 / 1024 = 100.78 => 100 energy_w_task = 480 * 228 / 1024 = 106.87 => 106 energy_diff = 106 - 100 = 6 (this is equal to 'old' PD1's energy_diff in 'c)') b) 'new' w/ patch set, PD0 task_util = 13 cost = 480 * 1000 = 480000 sum_util_w/o_task = 215 sum_util_w_task = 228 energy_w/o_task = 480000 * 215 / 1024 = 100781 energy_w_task = 480000 * 228 / 1024 = 106875 energy_diff = 106875 - 100781 = 6094 (this is not equal to 'new' PD1's energy_diff in 'd)') c) 'old' w/o patch set, PD1 task_util = 13 cost = 160 sum_util_w/o_task = 283 sum_util_w_task = 293 scale_cpu = 355 energy_w/o_task = 160 * 283 / 355 = 127.55 => 127 energy_w_task = 160 * 296 / 355 = 133.41 => 133 energy_diff = 133 - 127 = 6 (this is equal to 'old' PD0's energy_diff in 'a)') d) 'new' w/ patch set, PD1 task_util = 13 cost = 160 * 1000 = 160000 sum_util_w/o_task = 283 sum_util_w_task = 293 scale_cpu = 355 energy_w/o_task = 160000 * 283 / 355 = 127549 energy_w_task = 160000 * 296 / 355 = 133408 energy_diff = 133408 - 127549 = 5859 (this is not equal to 'new' PD0's energy_diff in 'b)') 2. Difference in the 6% energy margin filter at the end of find_energy_efficient_cpu(). With this patch the margin comparison also has better resolution, so it's possible to have better task placement thanks to that. Fixes: 27871f7a8a341ef ("PM: Introduce an Energy Model management framework") Reported-by: CCJ Yeh Reviewed-by: Dietmar Eggemann Signed-off-by: Lukasz Luba Signed-off-by: Rafael J. Wysocki Signed-off-by: Sasha Levin --- include/linux/energy_model.h | 16 ++++++++++++++++ kernel/power/energy_model.c | 4 +++- 2 files changed, 19 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index b67a51c574b9..5f04a2b35e80 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -51,6 +51,22 @@ struct em_perf_domain { #ifdef CONFIG_ENERGY_MODEL #define EM_MAX_POWER 0xFFFF +/* + * Increase resolution of energy estimation calculations for 64-bit + * architectures. The extra resolution improves decision made by EAS for the + * task placement when two Performance Domains might provide similar energy + * estimation values (w/o better resolution the values could be equal). + * + * We increase resolution only if we have enough bits to allow this increased + * resolution (i.e. 64-bit). The costs for increasing resolution when 32-bit + * are pretty high and the returns do not justify the increased costs. + */ +#ifdef CONFIG_64BIT +#define em_scale_power(p) ((p) * 1000) +#else +#define em_scale_power(p) (p) +#endif + struct em_data_callback { /** * active_power() - Provide power at the next performance state of diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 994ca8353543..be381eb6116a 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -157,7 +157,9 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, /* Compute the cost of each performance state. */ fmax = (u64) table[nr_states - 1].frequency; for (i = 0; i < nr_states; i++) { - table[i].cost = div64_u64(fmax * table[i].power, + unsigned long power_res = em_scale_power(table[i].power); + + table[i].cost = div64_u64(fmax * power_res, table[i].frequency); } -- cgit v1.2.3 From d5462a630f7de9fc9cc25106b2adcb8cc69e51c2 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 9 Dec 2020 16:06:21 +0100 Subject: locking/lockdep: Mark local_lock_t [ Upstream commit dfd5e3f5fe27bda91d5cc028c86ffbb7a0614489 ] The local_lock_t's are special, because they cannot form IRQ inversions, make sure we can tell them apart from the rest of the locks. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Sasha Levin --- include/linux/local_lock_internal.h | 5 ++++- include/linux/lockdep.h | 15 ++++++++++++--- include/linux/lockdep_types.h | 18 ++++++++++++++---- kernel/locking/lockdep.c | 16 +++++++++------- 4 files changed, 39 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index 4a8795b21d77..ded90b097e6e 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -18,6 +18,7 @@ typedef struct { .dep_map = { \ .name = #lockname, \ .wait_type_inner = LD_WAIT_CONFIG, \ + .lock_type = LD_LOCK_PERCPU, \ } #else # define LL_DEP_MAP_INIT(lockname) @@ -30,7 +31,9 @@ do { \ static struct lock_class_key __key; \ \ debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ - lockdep_init_map_wait(&(lock)->dep_map, #lock, &__key, 0, LD_WAIT_CONFIG);\ + lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, 0, \ + LD_WAIT_CONFIG, LD_WAIT_INV, \ + LD_LOCK_PERCPU); \ } while (0) #ifdef CONFIG_DEBUG_LOCK_ALLOC diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index f5594879175a..20b6797babe2 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -185,12 +185,19 @@ extern void lockdep_unregister_key(struct lock_class_key *key); * to lockdep: */ -extern void lockdep_init_map_waits(struct lockdep_map *lock, const char *name, - struct lock_class_key *key, int subclass, short inner, short outer); +extern void lockdep_init_map_type(struct lockdep_map *lock, const char *name, + struct lock_class_key *key, int subclass, u8 inner, u8 outer, u8 lock_type); + +static inline void +lockdep_init_map_waits(struct lockdep_map *lock, const char *name, + struct lock_class_key *key, int subclass, u8 inner, u8 outer) +{ + lockdep_init_map_type(lock, name, key, subclass, inner, LD_WAIT_INV, LD_LOCK_NORMAL); +} static inline void lockdep_init_map_wait(struct lockdep_map *lock, const char *name, - struct lock_class_key *key, int subclass, short inner) + struct lock_class_key *key, int subclass, u8 inner) { lockdep_init_map_waits(lock, name, key, subclass, inner, LD_WAIT_INV); } @@ -340,6 +347,8 @@ static inline void lockdep_set_selftest_task(struct task_struct *task) # define lock_set_class(l, n, k, s, i) do { } while (0) # define lock_set_subclass(l, s, i) do { } while (0) # define lockdep_init() do { } while (0) +# define lockdep_init_map_type(lock, name, key, sub, inner, outer, type) \ + do { (void)(name); (void)(key); } while (0) # define lockdep_init_map_waits(lock, name, key, sub, inner, outer) \ do { (void)(name); (void)(key); } while (0) # define lockdep_init_map_wait(lock, name, key, sub, inner) \ diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h index 9a1fd49df17f..2ec9ff5a7fff 100644 --- a/include/linux/lockdep_types.h +++ b/include/linux/lockdep_types.h @@ -30,6 +30,12 @@ enum lockdep_wait_type { LD_WAIT_MAX, /* must be last */ }; +enum lockdep_lock_type { + LD_LOCK_NORMAL = 0, /* normal, catch all */ + LD_LOCK_PERCPU, /* percpu */ + LD_LOCK_MAX, +}; + #ifdef CONFIG_LOCKDEP /* @@ -119,8 +125,10 @@ struct lock_class { int name_version; const char *name; - short wait_type_inner; - short wait_type_outer; + u8 wait_type_inner; + u8 wait_type_outer; + u8 lock_type; + /* u8 hole; */ #ifdef CONFIG_LOCK_STAT unsigned long contention_point[LOCKSTAT_POINTS]; @@ -169,8 +177,10 @@ struct lockdep_map { struct lock_class_key *key; struct lock_class *class_cache[NR_LOCKDEP_CACHING_CLASSES]; const char *name; - short wait_type_outer; /* can be taken in this context */ - short wait_type_inner; /* presents this context */ + u8 wait_type_outer; /* can be taken in this context */ + u8 wait_type_inner; /* presents this context */ + u8 lock_type; + /* u8 hole; */ #ifdef CONFIG_LOCK_STAT int cpu; unsigned long ip; diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 8ae9d7abebc0..5184f6896815 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -1293,6 +1293,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) class->name_version = count_matching_names(class); class->wait_type_inner = lock->wait_type_inner; class->wait_type_outer = lock->wait_type_outer; + class->lock_type = lock->lock_type; /* * We use RCU's safe list-add method to make * parallel walking of the hash-list safe: @@ -4621,9 +4622,9 @@ print_lock_invalid_wait_context(struct task_struct *curr, */ static int check_wait_context(struct task_struct *curr, struct held_lock *next) { - short next_inner = hlock_class(next)->wait_type_inner; - short next_outer = hlock_class(next)->wait_type_outer; - short curr_inner; + u8 next_inner = hlock_class(next)->wait_type_inner; + u8 next_outer = hlock_class(next)->wait_type_outer; + u8 curr_inner; int depth; if (!next_inner || next->trylock) @@ -4646,7 +4647,7 @@ static int check_wait_context(struct task_struct *curr, struct held_lock *next) for (; depth < curr->lockdep_depth; depth++) { struct held_lock *prev = curr->held_locks + depth; - short prev_inner = hlock_class(prev)->wait_type_inner; + u8 prev_inner = hlock_class(prev)->wait_type_inner; if (prev_inner) { /* @@ -4695,9 +4696,9 @@ static inline int check_wait_context(struct task_struct *curr, /* * Initialize a lock instance's lock-class mapping info: */ -void lockdep_init_map_waits(struct lockdep_map *lock, const char *name, +void lockdep_init_map_type(struct lockdep_map *lock, const char *name, struct lock_class_key *key, int subclass, - short inner, short outer) + u8 inner, u8 outer, u8 lock_type) { int i; @@ -4720,6 +4721,7 @@ void lockdep_init_map_waits(struct lockdep_map *lock, const char *name, lock->wait_type_outer = outer; lock->wait_type_inner = inner; + lock->lock_type = lock_type; /* * No key, no joy, we need to hash something. @@ -4754,7 +4756,7 @@ void lockdep_init_map_waits(struct lockdep_map *lock, const char *name, raw_local_irq_restore(flags); } } -EXPORT_SYMBOL_GPL(lockdep_init_map_waits); +EXPORT_SYMBOL_GPL(lockdep_init_map_type); struct lock_class_key __lockdep_no_validate__; EXPORT_SYMBOL_GPL(__lockdep_no_validate__); -- cgit v1.2.3 From 2600861b9069d57bff1cac0e73fd3aac4f181df1 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 15 Aug 2021 23:27:37 +0200 Subject: locking/local_lock: Add missing owner initialization [ Upstream commit d8bbd97ad0b99a9394f2cd8410b884c48e218cf0 ] If CONFIG_DEBUG_LOCK_ALLOC=y is enabled then local_lock_t has an 'owner' member which is checked for consistency, but nothing initialized it to zero explicitly. The static initializer does so implicit, and the run time allocated per CPU storage is usually zero initialized as well, but relying on that is not really good practice. Fixes: 91710728d172 ("locking: Introduce local_lock()") Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210815211301.969975279@linutronix.de Signed-off-by: Sasha Levin --- include/linux/local_lock_internal.h | 42 ++++++++++++++++++++----------------- 1 file changed, 23 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index ded90b097e6e..3f02b818625e 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -14,29 +14,14 @@ typedef struct { } local_lock_t; #ifdef CONFIG_DEBUG_LOCK_ALLOC -# define LL_DEP_MAP_INIT(lockname) \ +# define LOCAL_LOCK_DEBUG_INIT(lockname) \ .dep_map = { \ .name = #lockname, \ .wait_type_inner = LD_WAIT_CONFIG, \ - .lock_type = LD_LOCK_PERCPU, \ - } -#else -# define LL_DEP_MAP_INIT(lockname) -#endif - -#define INIT_LOCAL_LOCK(lockname) { LL_DEP_MAP_INIT(lockname) } - -#define __local_lock_init(lock) \ -do { \ - static struct lock_class_key __key; \ - \ - debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ - lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, 0, \ - LD_WAIT_CONFIG, LD_WAIT_INV, \ - LD_LOCK_PERCPU); \ -} while (0) + .lock_type = LD_LOCK_PERCPU, \ + }, \ + .owner = NULL, -#ifdef CONFIG_DEBUG_LOCK_ALLOC static inline void local_lock_acquire(local_lock_t *l) { lock_map_acquire(&l->dep_map); @@ -51,11 +36,30 @@ static inline void local_lock_release(local_lock_t *l) lock_map_release(&l->dep_map); } +static inline void local_lock_debug_init(local_lock_t *l) +{ + l->owner = NULL; +} #else /* CONFIG_DEBUG_LOCK_ALLOC */ +# define LOCAL_LOCK_DEBUG_INIT(lockname) static inline void local_lock_acquire(local_lock_t *l) { } static inline void local_lock_release(local_lock_t *l) { } +static inline void local_lock_debug_init(local_lock_t *l) { } #endif /* !CONFIG_DEBUG_LOCK_ALLOC */ +#define INIT_LOCAL_LOCK(lockname) { LOCAL_LOCK_DEBUG_INIT(lockname) } + +#define __local_lock_init(lock) \ +do { \ + static struct lock_class_key __key; \ + \ + debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ + lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, \ + 0, LD_WAIT_CONFIG, LD_WAIT_INV, \ + LD_LOCK_PERCPU); \ + local_lock_debug_init(lock); \ +} while (0) + #define __local_lock(lock) \ do { \ preempt_disable(); \ -- cgit v1.2.3 From 656f343d724b45295f73000eb6e7bd3d212af116 Mon Sep 17 00:00:00 2001 From: Lukas Hannen Date: Wed, 25 Aug 2021 10:12:43 +0000 Subject: time: Handle negative seconds correctly in timespec64_to_ns() commit 39ff83f2f6cc5cc1458dfcea9697f96338210beb upstream. timespec64_ns() prevents multiplication overflows by comparing the seconds value of the timespec to KTIME_SEC_MAX. If the value is greater or equal it returns KTIME_MAX. But that check casts the signed seconds value to unsigned which makes the comparision true for all negative values and therefore return wrongly KTIME_MAX. Negative second values are perfectly valid and required in some places, e.g. ptp_clock_adjtime(). Remove the cast and add a check for the negative boundary which is required to prevent undefined behaviour due to multiplication underflow. Fixes: cb47755725da ("time: Prevent undefined behaviour in timespec64_to_ns()")' Signed-off-by: Lukas Hannen Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/AM6PR01MB541637BD6F336B8FFB72AF80EEC69@AM6PR01MB5416.eurprd01.prod.exchangelabs.com Signed-off-by: Greg Kroah-Hartman --- include/linux/time64.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/time64.h b/include/linux/time64.h index 5117cb5b5656..81b9686a2079 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -25,7 +25,9 @@ struct itimerspec64 { #define TIME64_MIN (-TIME64_MAX - 1) #define KTIME_MAX ((s64)~((u64)1 << 63)) +#define KTIME_MIN (-KTIME_MAX - 1) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) +#define KTIME_SEC_MIN (KTIME_MIN / NSEC_PER_SEC) /* * Limits for settimeofday(): @@ -124,10 +126,13 @@ static inline bool timespec64_valid_settod(const struct timespec64 *ts) */ static inline s64 timespec64_to_ns(const struct timespec64 *ts) { - /* Prevent multiplication overflow */ - if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) + /* Prevent multiplication overflow / underflow */ + if (ts->tv_sec >= KTIME_SEC_MAX) return KTIME_MAX; + if (ts->tv_sec <= KTIME_SEC_MIN) + return KTIME_MIN; + return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; } -- cgit v1.2.3 From cb0f17e7584a2ad5047f23b9f0b7a0211304ff88 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Sun, 8 Nov 2020 19:51:09 +0100 Subject: clk: divider: add devm_clk_hw_register_divider_table() This will simplify drivers which would only unregister the clk in their remove() op. Signed-off-by: Michael Walle Link: https://lore.kernel.org/r/20201108185113.31377-6-michael@walle.cc Signed-off-by: Stephen Boyd (cherry picked from commit 26792699fe3681102aa85f4ae6d39e80a6a7e6b6) Signed-off-by: Joel Stanley --- drivers/clk/clk-divider.c | 34 ++++++++++++++++++++++++++++++++++ include/linux/clk-provider.h | 27 +++++++++++++++++++++++++++ 2 files changed, 61 insertions(+) (limited to 'include/linux') diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c index f32157cb4013..344997203f0e 100644 --- a/drivers/clk/clk-divider.c +++ b/drivers/clk/clk-divider.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include @@ -583,3 +584,36 @@ void clk_hw_unregister_divider(struct clk_hw *hw) kfree(div); } EXPORT_SYMBOL_GPL(clk_hw_unregister_divider); + +static void devm_clk_hw_release_divider(struct device *dev, void *res) +{ + clk_hw_unregister_divider(*(struct clk_hw **)res); +} + +struct clk_hw *__devm_clk_hw_register_divider(struct device *dev, + struct device_node *np, const char *name, + const char *parent_name, const struct clk_hw *parent_hw, + const struct clk_parent_data *parent_data, unsigned long flags, + void __iomem *reg, u8 shift, u8 width, u8 clk_divider_flags, + const struct clk_div_table *table, spinlock_t *lock) +{ + struct clk_hw **ptr, *hw; + + ptr = devres_alloc(devm_clk_hw_release_divider, sizeof(*ptr), GFP_KERNEL); + if (!ptr) + return ERR_PTR(-ENOMEM); + + hw = __clk_hw_register_divider(dev, np, name, parent_name, parent_hw, + parent_data, flags, reg, shift, width, + clk_divider_flags, table, lock); + + if (!IS_ERR(hw)) { + *ptr = hw; + devres_add(dev, ptr); + } else { + devres_free(ptr); + } + + return hw; +} +EXPORT_SYMBOL_GPL(__devm_clk_hw_register_divider); diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 03a5de5f99f4..9ead4633c8c8 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -639,6 +639,12 @@ struct clk_hw *__clk_hw_register_divider(struct device *dev, const struct clk_parent_data *parent_data, unsigned long flags, void __iomem *reg, u8 shift, u8 width, u8 clk_divider_flags, const struct clk_div_table *table, spinlock_t *lock); +struct clk_hw *__devm_clk_hw_register_divider(struct device *dev, + struct device_node *np, const char *name, + const char *parent_name, const struct clk_hw *parent_hw, + const struct clk_parent_data *parent_data, unsigned long flags, + void __iomem *reg, u8 shift, u8 width, u8 clk_divider_flags, + const struct clk_div_table *table, spinlock_t *lock); struct clk *clk_register_divider_table(struct device *dev, const char *name, const char *parent_name, unsigned long flags, void __iomem *reg, u8 shift, u8 width, @@ -779,6 +785,27 @@ struct clk *clk_register_divider_table(struct device *dev, const char *name, (parent_data), (flags), (reg), (shift), \ (width), (clk_divider_flags), (table), \ (lock)) +/** + * devm_clk_hw_register_divider_table - register a table based divider clock + * with the clock framework (devres variant) + * @dev: device registering this clock + * @name: name of this clock + * @parent_name: name of clock's parent + * @flags: framework-specific flags + * @reg: register address to adjust divider + * @shift: number of bits to shift the bitfield + * @width: width of the bitfield + * @clk_divider_flags: divider-specific flags for this clock + * @table: array of divider/value pairs ending with a div set to 0 + * @lock: shared register lock for this clock + */ +#define devm_clk_hw_register_divider_table(dev, name, parent_name, flags, \ + reg, shift, width, \ + clk_divider_flags, table, lock) \ + __devm_clk_hw_register_divider((dev), NULL, (name), (parent_name), \ + NULL, NULL, (flags), (reg), (shift), \ + (width), (clk_divider_flags), (table), \ + (lock)) void clk_unregister_divider(struct clk *clk); void clk_hw_unregister_divider(struct clk_hw *hw); -- cgit v1.2.3 From 855fcc506f334183bec79e2ddbc5382dfe4b9263 Mon Sep 17 00:00:00 2001 From: Dmitry Baryshkov Date: Wed, 31 Mar 2021 13:57:13 +0300 Subject: clk: divider: add devm_clk_hw_register_divider Add devm_clk_hw_register_divider() - devres version of clk_hw_register_divider(). Signed-off-by: Dmitry Baryshkov Reviewed-by: Abhinav Kumar Acked-by: Stephen Boyd Link: https://lore.kernel.org/r/20210331105735.3690009-3-dmitry.baryshkov@linaro.org Signed-off-by: Rob Clark (cherry picked from commit f4b43ac0b0af1d115effd08133046a694ac33dc2) Signed-off-by: Joel Stanley --- include/linux/clk-provider.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 9ead4633c8c8..a6ff403ebf13 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -807,6 +807,24 @@ struct clk *clk_register_divider_table(struct device *dev, const char *name, (width), (clk_divider_flags), (table), \ (lock)) +/** + * devm_clk_hw_register_divider - register a divider clock with the clock framework + * @dev: device registering this clock + * @name: name of this clock + * @parent_name: name of clock's parent + * @flags: framework-specific flags + * @reg: register address to adjust divider + * @shift: number of bits to shift the bitfield + * @width: width of the bitfield + * @clk_divider_flags: divider-specific flags for this clock + * @lock: shared register lock for this clock + */ +#define devm_clk_hw_register_divider(dev, name, parent_name, flags, reg, shift, \ + width, clk_divider_flags, lock) \ + __devm_clk_hw_register_divider((dev), NULL, (name), (parent_name), NULL, \ + NULL, (flags), (reg), (shift), (width), \ + (clk_divider_flags), NULL, (lock)) + void clk_unregister_divider(struct clk *clk); void clk_hw_unregister_divider(struct clk_hw *hw); -- cgit v1.2.3 From 1de280adb209e5b95528b00b878e0d9e35594102 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 16 Sep 2021 11:12:30 +0200 Subject: Revert "time: Handle negative seconds correctly in timespec64_to_ns()" This reverts commit 656f343d724b45295f73000eb6e7bd3d212af116 which is commit 39ff83f2f6cc5cc1458dfcea9697f96338210beb upstream. Arnd reports that this needs more review before being merged into all of the trees. Link: https://lore.kernel.org/r/CAK8P3a0z5jE=Z3Ps5bFTCFT7CHZR1JQ8VhdntDJAfsUxSPCcEw@mail.gmail.com Reported-by: Arnd Bergmann Cc: Lukas Hannen Cc: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- include/linux/time64.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/time64.h b/include/linux/time64.h index 81b9686a2079..5117cb5b5656 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -25,9 +25,7 @@ struct itimerspec64 { #define TIME64_MIN (-TIME64_MAX - 1) #define KTIME_MAX ((s64)~((u64)1 << 63)) -#define KTIME_MIN (-KTIME_MAX - 1) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) -#define KTIME_SEC_MIN (KTIME_MIN / NSEC_PER_SEC) /* * Limits for settimeofday(): @@ -126,13 +124,10 @@ static inline bool timespec64_valid_settod(const struct timespec64 *ts) */ static inline s64 timespec64_to_ns(const struct timespec64 *ts) { - /* Prevent multiplication overflow / underflow */ - if (ts->tv_sec >= KTIME_SEC_MAX) + /* Prevent multiplication overflow */ + if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) return KTIME_MAX; - if (ts->tv_sec <= KTIME_SEC_MIN) - return KTIME_MIN; - return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; } -- cgit v1.2.3 From f3d30161278776fb0a4a163c05f44a55acc47f1b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 26 Jul 2021 07:59:23 -0400 Subject: SUNRPC: Fix potential memory corruption [ Upstream commit c2dc3e5fad13aca5d7bdf4bcb52b1a1d707c8555 ] We really should not call rpc_wake_up_queued_task_set_status() with xprt->snd_task as an argument unless we are certain that is actually an rpc_task. Fixes: 0445f92c5d53 ("SUNRPC: Fix disconnection races") Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker Signed-off-by: Sasha Levin --- include/linux/sunrpc/xprt.h | 1 + net/sunrpc/xprt.c | 6 ++++-- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index cad1fa2b6baa..e7b997d6f031 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -421,6 +421,7 @@ void xprt_unlock_connect(struct rpc_xprt *, void *); #define XPRT_CONGESTED (9) #define XPRT_CWND_WAIT (10) #define XPRT_WRITE_SPACE (11) +#define XPRT_SND_IS_COOKIE (12) static inline void xprt_set_connected(struct rpc_xprt *xprt) { diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 9a50764be916..ccfa85e995fd 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -746,9 +746,9 @@ void xprt_force_disconnect(struct rpc_xprt *xprt) /* Try to schedule an autoclose RPC call */ if (test_and_set_bit(XPRT_LOCKED, &xprt->state) == 0) queue_work(xprtiod_workqueue, &xprt->task_cleanup); - else if (xprt->snd_task) + else if (xprt->snd_task && !test_bit(XPRT_SND_IS_COOKIE, &xprt->state)) rpc_wake_up_queued_task_set_status(&xprt->pending, - xprt->snd_task, -ENOTCONN); + xprt->snd_task, -ENOTCONN); spin_unlock(&xprt->transport_lock); } EXPORT_SYMBOL_GPL(xprt_force_disconnect); @@ -837,6 +837,7 @@ bool xprt_lock_connect(struct rpc_xprt *xprt, goto out; if (xprt->snd_task != task) goto out; + set_bit(XPRT_SND_IS_COOKIE, &xprt->state); xprt->snd_task = cookie; ret = true; out: @@ -852,6 +853,7 @@ void xprt_unlock_connect(struct rpc_xprt *xprt, void *cookie) if (!test_bit(XPRT_LOCKED, &xprt->state)) goto out; xprt->snd_task =NULL; + clear_bit(XPRT_SND_IS_COOKIE, &xprt->state); xprt->ops->release_xprt(xprt, NULL); xprt_schedule_autodisconnect(xprt); out: -- cgit v1.2.3 From 21a2be1a5145d072deedc7cdc5b2d17380abea75 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Wed, 23 Jun 2021 23:28:48 -0400 Subject: SUNRPC query transport's source port [ Upstream commit a8482488a7d6d320f63a9ee1912dbb5ae5b80a61 ] Provide ability to query transport's source port. Signed-off-by: Olga Kornievskaia Signed-off-by: Trond Myklebust Signed-off-by: Sasha Levin --- include/linux/sunrpc/xprtsock.h | 1 + net/sunrpc/xprtsock.c | 7 +++++++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 3c1423ee74b4..8c2a712cb242 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -10,6 +10,7 @@ int init_socket_xprt(void); void cleanup_socket_xprt(void); +unsigned short get_srcport(struct rpc_xprt *); #define RPC_MIN_RESVPORT (1U) #define RPC_MAX_RESVPORT (65535U) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 9c0f71e82d97..7d7c08af54de 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1639,6 +1639,13 @@ static int xs_get_srcport(struct sock_xprt *transport) return port; } +unsigned short get_srcport(struct rpc_xprt *xprt) +{ + struct sock_xprt *sock = container_of(xprt, struct sock_xprt, xprt); + return sock->srcport; +} +EXPORT_SYMBOL(get_srcport); + static unsigned short xs_next_srcport(struct sock_xprt *transport, unsigned short port) { if (transport->srcport != 0) -- cgit v1.2.3 From 253bac6c60ad317c805d3061aa813b74b8692b2a Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Wed, 18 Aug 2021 21:48:44 +0800 Subject: iommu/vt-d: Update the virtual command related registers [ Upstream commit 4d99efb229e63928c6b03a756a2e38cd4777fbe8 ] The VT-d spec Revision 3.3 updated the virtual command registers, virtual command opcode B register, virtual command response register and virtual command capability register (Section 10.4.43, 10.4.44, 10.4.45, 10.4.46). This updates the virtual command interface implementation in the Intel IOMMU driver accordingly. Fixes: 24f27d32ab6b7 ("iommu/vt-d: Enlightened PASID allocation") Signed-off-by: Lu Baolu Cc: Ashok Raj Cc: Sanjay Kumar Cc: Kevin Tian Link: https://lore.kernel.org/r/20210713042649.3547403-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20210818134852.1847070-2-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- drivers/iommu/intel/pasid.h | 10 +++++----- include/linux/intel-iommu.h | 6 +++--- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h index 30cb30046b15..35963e6bf9fa 100644 --- a/drivers/iommu/intel/pasid.h +++ b/drivers/iommu/intel/pasid.h @@ -28,12 +28,12 @@ #define VCMD_CMD_ALLOC 0x1 #define VCMD_CMD_FREE 0x2 #define VCMD_VRSP_IP 0x1 -#define VCMD_VRSP_SC(e) (((e) >> 1) & 0x3) +#define VCMD_VRSP_SC(e) (((e) & 0xff) >> 1) #define VCMD_VRSP_SC_SUCCESS 0 -#define VCMD_VRSP_SC_NO_PASID_AVAIL 2 -#define VCMD_VRSP_SC_INVALID_PASID 2 -#define VCMD_VRSP_RESULT_PASID(e) (((e) >> 8) & 0xfffff) -#define VCMD_CMD_OPERAND(e) ((e) << 8) +#define VCMD_VRSP_SC_NO_PASID_AVAIL 16 +#define VCMD_VRSP_SC_INVALID_PASID 16 +#define VCMD_VRSP_RESULT_PASID(e) (((e) >> 16) & 0xfffff) +#define VCMD_CMD_OPERAND(e) ((e) << 16) /* * Domain ID reserved for pasid entries programmed for first-level * only and pass-through transfer modes. diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index c00ee3458a91..142ec79cda84 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -122,9 +122,9 @@ #define DMAR_MTRR_PHYSMASK8_REG 0x208 #define DMAR_MTRR_PHYSBASE9_REG 0x210 #define DMAR_MTRR_PHYSMASK9_REG 0x218 -#define DMAR_VCCAP_REG 0xe00 /* Virtual command capability register */ -#define DMAR_VCMD_REG 0xe10 /* Virtual command register */ -#define DMAR_VCRSP_REG 0xe20 /* Virtual command response register */ +#define DMAR_VCCAP_REG 0xe30 /* Virtual command capability register */ +#define DMAR_VCMD_REG 0xe00 /* Virtual command register */ +#define DMAR_VCRSP_REG 0xe10 /* Virtual command response register */ #define OFFSET_STRIDE (9) -- cgit v1.2.3 From d3ca78775db42eedde8ce9fee5fbd5be4b36a0f1 Mon Sep 17 00:00:00 2001 From: Zhouyi Zhou Date: Tue, 13 Jul 2021 08:56:45 +0800 Subject: rcu: Fix macro name CONFIG_TASKS_RCU_TRACE [ Upstream commit fed31a4dd3adb5455df7c704de2abb639a1dc1c0 ] This commit fixes several typos where CONFIG_TASKS_RCU_TRACE should instead be CONFIG_TASKS_TRACE_RCU. Among other things, these typos could cause CONFIG_TASKS_TRACE_RCU_READ_MB=y kernels to suffer from memory-ordering bugs that could result in false-positive quiescent states and too-short grace periods. Signed-off-by: Zhouyi Zhou Signed-off-by: Paul E. McKenney Signed-off-by: Sasha Levin --- include/linux/rcupdate.h | 2 +- kernel/rcu/tree_plugin.h | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 0d7013da818c..095b3b39bd03 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -163,7 +163,7 @@ void synchronize_rcu_tasks(void); # define synchronize_rcu_tasks synchronize_rcu # endif -# ifdef CONFIG_TASKS_RCU_TRACE +# ifdef CONFIG_TASKS_TRACE_RCU # define rcu_tasks_trace_qs(t) \ do { \ if (!likely(READ_ONCE((t)->trc_reader_checked)) && \ diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 574aeaac9272..c5091aeaa37b 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -2591,17 +2591,17 @@ static void noinstr rcu_dynticks_task_exit(void) /* Turn on heavyweight RCU tasks trace readers on idle/user entry. */ static void rcu_dynticks_task_trace_enter(void) { -#ifdef CONFIG_TASKS_RCU_TRACE +#ifdef CONFIG_TASKS_TRACE_RCU if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) current->trc_reader_special.b.need_mb = true; -#endif /* #ifdef CONFIG_TASKS_RCU_TRACE */ +#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } /* Turn off heavyweight RCU tasks trace readers on idle/user exit. */ static void rcu_dynticks_task_trace_exit(void) { -#ifdef CONFIG_TASKS_RCU_TRACE +#ifdef CONFIG_TASKS_TRACE_RCU if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) current->trc_reader_special.b.need_mb = false; -#endif /* #ifdef CONFIG_TASKS_RCU_TRACE */ +#endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } -- cgit v1.2.3 From 5b3a45eedd27a5e3fac887fa6ad486f44723a4d9 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 22 Jul 2021 16:28:59 +0200 Subject: ethtool: improve compat ioctl handling [ Upstream commit dd98d2895de6485c884a9cb42de69fed02826fa4 ] The ethtool compat ioctl handling is hidden away in net/socket.c, which introduces a couple of minor oddities: - The implementation may end up diverging, as seen in the RXNFC extension in commit 84a1d9c48200 ("net: ethtool: extend RXNFC API to support RSS spreading of filter matches") that does not work in compat mode. - Most architectures do not need the compat handling at all because u64 and compat_u64 have the same alignment. - On x86, the conversion is done for both x32 and i386 user space, but it's actually wrong to do it for x32 and cannot work there. - On 32-bit Arm, it never worked for compat oabi user space, since that needs to do the same conversion but does not. - It would be nice to get rid of both compat_alloc_user_space() and copy_in_user() throughout the kernel. None of these actually seems to be a serious problem that real users are likely to encounter, but fixing all of them actually leads to code that is both shorter and more readable. Signed-off-by: Arnd Bergmann Reviewed-by: Christoph Hellwig Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- include/linux/ethtool.h | 4 -- net/ethtool/ioctl.c | 136 ++++++++++++++++++++++++++++++++++++++++++------ net/socket.c | 125 +------------------------------------------- 3 files changed, 121 insertions(+), 144 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 6408b446051f..b98291d391f3 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -17,8 +17,6 @@ #include #include -#ifdef CONFIG_COMPAT - struct compat_ethtool_rx_flow_spec { u32 flow_type; union ethtool_flow_union h_u; @@ -38,8 +36,6 @@ struct compat_ethtool_rxnfc { u32 rule_locs[]; }; -#endif /* CONFIG_COMPAT */ - #include /** diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 68ff19af195c..97b402b2d6fb 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -7,6 +7,7 @@ * the information ethtool needs. */ +#include #include #include #include @@ -807,6 +808,120 @@ out: return ret; } +static noinline_for_stack int +ethtool_rxnfc_copy_from_compat(struct ethtool_rxnfc *rxnfc, + const struct compat_ethtool_rxnfc __user *useraddr, + size_t size) +{ + struct compat_ethtool_rxnfc crxnfc = {}; + + /* We expect there to be holes between fs.m_ext and + * fs.ring_cookie and at the end of fs, but nowhere else. + * On non-x86, no conversion should be needed. + */ + BUILD_BUG_ON(!IS_ENABLED(CONFIG_X86_64) && + sizeof(struct compat_ethtool_rxnfc) != + sizeof(struct ethtool_rxnfc)); + BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.m_ext) + + sizeof(useraddr->fs.m_ext) != + offsetof(struct ethtool_rxnfc, fs.m_ext) + + sizeof(rxnfc->fs.m_ext)); + BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.location) - + offsetof(struct compat_ethtool_rxnfc, fs.ring_cookie) != + offsetof(struct ethtool_rxnfc, fs.location) - + offsetof(struct ethtool_rxnfc, fs.ring_cookie)); + + if (copy_from_user(&crxnfc, useraddr, min(size, sizeof(crxnfc)))) + return -EFAULT; + + *rxnfc = (struct ethtool_rxnfc) { + .cmd = crxnfc.cmd, + .flow_type = crxnfc.flow_type, + .data = crxnfc.data, + .fs = { + .flow_type = crxnfc.fs.flow_type, + .h_u = crxnfc.fs.h_u, + .h_ext = crxnfc.fs.h_ext, + .m_u = crxnfc.fs.m_u, + .m_ext = crxnfc.fs.m_ext, + .ring_cookie = crxnfc.fs.ring_cookie, + .location = crxnfc.fs.location, + }, + .rule_cnt = crxnfc.rule_cnt, + }; + + return 0; +} + +static int ethtool_rxnfc_copy_from_user(struct ethtool_rxnfc *rxnfc, + const void __user *useraddr, + size_t size) +{ + if (compat_need_64bit_alignment_fixup()) + return ethtool_rxnfc_copy_from_compat(rxnfc, useraddr, size); + + if (copy_from_user(rxnfc, useraddr, size)) + return -EFAULT; + + return 0; +} + +static int ethtool_rxnfc_copy_to_compat(void __user *useraddr, + const struct ethtool_rxnfc *rxnfc, + size_t size, const u32 *rule_buf) +{ + struct compat_ethtool_rxnfc crxnfc; + + memset(&crxnfc, 0, sizeof(crxnfc)); + crxnfc = (struct compat_ethtool_rxnfc) { + .cmd = rxnfc->cmd, + .flow_type = rxnfc->flow_type, + .data = rxnfc->data, + .fs = { + .flow_type = rxnfc->fs.flow_type, + .h_u = rxnfc->fs.h_u, + .h_ext = rxnfc->fs.h_ext, + .m_u = rxnfc->fs.m_u, + .m_ext = rxnfc->fs.m_ext, + .ring_cookie = rxnfc->fs.ring_cookie, + .location = rxnfc->fs.location, + }, + .rule_cnt = rxnfc->rule_cnt, + }; + + if (copy_to_user(useraddr, &crxnfc, min(size, sizeof(crxnfc)))) + return -EFAULT; + + return 0; +} + +static int ethtool_rxnfc_copy_to_user(void __user *useraddr, + const struct ethtool_rxnfc *rxnfc, + size_t size, const u32 *rule_buf) +{ + int ret; + + if (compat_need_64bit_alignment_fixup()) { + ret = ethtool_rxnfc_copy_to_compat(useraddr, rxnfc, size, + rule_buf); + useraddr += offsetof(struct compat_ethtool_rxnfc, rule_locs); + } else { + ret = copy_to_user(useraddr, &rxnfc, size); + useraddr += offsetof(struct ethtool_rxnfc, rule_locs); + } + + if (ret) + return -EFAULT; + + if (rule_buf) { + if (copy_to_user(useraddr, rule_buf, + rxnfc->rule_cnt * sizeof(u32))) + return -EFAULT; + } + + return 0; +} + static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, u32 cmd, void __user *useraddr) { @@ -825,7 +940,7 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, info_size = (offsetof(struct ethtool_rxnfc, data) + sizeof(info.data)); - if (copy_from_user(&info, useraddr, info_size)) + if (ethtool_rxnfc_copy_from_user(&info, useraddr, info_size)) return -EFAULT; rc = dev->ethtool_ops->set_rxnfc(dev, &info); @@ -833,7 +948,7 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, return rc; if (cmd == ETHTOOL_SRXCLSRLINS && - copy_to_user(useraddr, &info, info_size)) + ethtool_rxnfc_copy_to_user(useraddr, &info, info_size, NULL)) return -EFAULT; return 0; @@ -859,7 +974,7 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, info_size = (offsetof(struct ethtool_rxnfc, data) + sizeof(info.data)); - if (copy_from_user(&info, useraddr, info_size)) + if (ethtool_rxnfc_copy_from_user(&info, useraddr, info_size)) return -EFAULT; /* If FLOW_RSS was requested then user-space must be using the @@ -867,7 +982,7 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, */ if (cmd == ETHTOOL_GRXFH && info.flow_type & FLOW_RSS) { info_size = sizeof(info); - if (copy_from_user(&info, useraddr, info_size)) + if (ethtool_rxnfc_copy_from_user(&info, useraddr, info_size)) return -EFAULT; /* Since malicious users may modify the original data, * we need to check whether FLOW_RSS is still requested. @@ -893,18 +1008,7 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, if (ret < 0) goto err_out; - ret = -EFAULT; - if (copy_to_user(useraddr, &info, info_size)) - goto err_out; - - if (rule_buf) { - useraddr += offsetof(struct ethtool_rxnfc, rule_locs); - if (copy_to_user(useraddr, rule_buf, - info.rule_cnt * sizeof(u32))) - goto err_out; - } - ret = 0; - + ret = ethtool_rxnfc_copy_to_user(useraddr, &info, info_size, rule_buf); err_out: kfree(rule_buf); diff --git a/net/socket.c b/net/socket.c index dd5da07bc1ff..d52c265ad449 100644 --- a/net/socket.c +++ b/net/socket.c @@ -3112,128 +3112,6 @@ static int compat_dev_ifconf(struct net *net, struct compat_ifconf __user *uifc3 return 0; } -static int ethtool_ioctl(struct net *net, struct compat_ifreq __user *ifr32) -{ - struct compat_ethtool_rxnfc __user *compat_rxnfc; - bool convert_in = false, convert_out = false; - size_t buf_size = 0; - struct ethtool_rxnfc __user *rxnfc = NULL; - struct ifreq ifr; - u32 rule_cnt = 0, actual_rule_cnt; - u32 ethcmd; - u32 data; - int ret; - - if (get_user(data, &ifr32->ifr_ifru.ifru_data)) - return -EFAULT; - - compat_rxnfc = compat_ptr(data); - - if (get_user(ethcmd, &compat_rxnfc->cmd)) - return -EFAULT; - - /* Most ethtool structures are defined without padding. - * Unfortunately struct ethtool_rxnfc is an exception. - */ - switch (ethcmd) { - default: - break; - case ETHTOOL_GRXCLSRLALL: - /* Buffer size is variable */ - if (get_user(rule_cnt, &compat_rxnfc->rule_cnt)) - return -EFAULT; - if (rule_cnt > KMALLOC_MAX_SIZE / sizeof(u32)) - return -ENOMEM; - buf_size += rule_cnt * sizeof(u32); - fallthrough; - case ETHTOOL_GRXRINGS: - case ETHTOOL_GRXCLSRLCNT: - case ETHTOOL_GRXCLSRULE: - case ETHTOOL_SRXCLSRLINS: - convert_out = true; - fallthrough; - case ETHTOOL_SRXCLSRLDEL: - buf_size += sizeof(struct ethtool_rxnfc); - convert_in = true; - rxnfc = compat_alloc_user_space(buf_size); - break; - } - - if (copy_from_user(&ifr.ifr_name, &ifr32->ifr_name, IFNAMSIZ)) - return -EFAULT; - - ifr.ifr_data = convert_in ? rxnfc : (void __user *)compat_rxnfc; - - if (convert_in) { - /* We expect there to be holes between fs.m_ext and - * fs.ring_cookie and at the end of fs, but nowhere else. - */ - BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.m_ext) + - sizeof(compat_rxnfc->fs.m_ext) != - offsetof(struct ethtool_rxnfc, fs.m_ext) + - sizeof(rxnfc->fs.m_ext)); - BUILD_BUG_ON( - offsetof(struct compat_ethtool_rxnfc, fs.location) - - offsetof(struct compat_ethtool_rxnfc, fs.ring_cookie) != - offsetof(struct ethtool_rxnfc, fs.location) - - offsetof(struct ethtool_rxnfc, fs.ring_cookie)); - - if (copy_in_user(rxnfc, compat_rxnfc, - (void __user *)(&rxnfc->fs.m_ext + 1) - - (void __user *)rxnfc) || - copy_in_user(&rxnfc->fs.ring_cookie, - &compat_rxnfc->fs.ring_cookie, - (void __user *)(&rxnfc->fs.location + 1) - - (void __user *)&rxnfc->fs.ring_cookie)) - return -EFAULT; - if (ethcmd == ETHTOOL_GRXCLSRLALL) { - if (put_user(rule_cnt, &rxnfc->rule_cnt)) - return -EFAULT; - } else if (copy_in_user(&rxnfc->rule_cnt, - &compat_rxnfc->rule_cnt, - sizeof(rxnfc->rule_cnt))) - return -EFAULT; - } - - ret = dev_ioctl(net, SIOCETHTOOL, &ifr, NULL); - if (ret) - return ret; - - if (convert_out) { - if (copy_in_user(compat_rxnfc, rxnfc, - (const void __user *)(&rxnfc->fs.m_ext + 1) - - (const void __user *)rxnfc) || - copy_in_user(&compat_rxnfc->fs.ring_cookie, - &rxnfc->fs.ring_cookie, - (const void __user *)(&rxnfc->fs.location + 1) - - (const void __user *)&rxnfc->fs.ring_cookie) || - copy_in_user(&compat_rxnfc->rule_cnt, &rxnfc->rule_cnt, - sizeof(rxnfc->rule_cnt))) - return -EFAULT; - - if (ethcmd == ETHTOOL_GRXCLSRLALL) { - /* As an optimisation, we only copy the actual - * number of rules that the underlying - * function returned. Since Mallory might - * change the rule count in user memory, we - * check that it is less than the rule count - * originally given (as the user buffer size), - * which has been range-checked. - */ - if (get_user(actual_rule_cnt, &rxnfc->rule_cnt)) - return -EFAULT; - if (actual_rule_cnt < rule_cnt) - rule_cnt = actual_rule_cnt; - if (copy_in_user(&compat_rxnfc->rule_locs[0], - &rxnfc->rule_locs[0], - rule_cnt * sizeof(u32))) - return -EFAULT; - } - } - - return 0; -} - static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32) { compat_uptr_t uptr32; @@ -3390,8 +3268,6 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, return old_bridge_ioctl(argp); case SIOCGIFCONF: return compat_dev_ifconf(net, argp); - case SIOCETHTOOL: - return ethtool_ioctl(net, argp); case SIOCWANDEV: return compat_siocwandev(net, argp); case SIOCGIFMAP: @@ -3404,6 +3280,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, return sock->ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_OLD, !COMPAT_USE_64BIT_TIME); + case SIOCETHTOOL: case SIOCBONDSLAVEINFOQUERY: case SIOCBONDINFOQUERY: case SIOCSHWTSTAMP: -- cgit v1.2.3 From e1fa3b2b60abb9f43b937741e27c6531ef4cbef9 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Thu, 2 Sep 2021 14:58:53 -0700 Subject: hugetlb: fix hugetlb cgroup refcounting during vma split commit 09a26e832705fdb7a9484495b71a05e0bbc65207 upstream. Guillaume Morin reported hitting the following WARNING followed by GPF or NULL pointer deference either in cgroups_destroy or in the kill_css path.: percpu ref (css_release) <= 0 (-1) after switching to atomic WARNING: CPU: 23 PID: 130 at lib/percpu-refcount.c:196 percpu_ref_switch_to_atomic_rcu+0x127/0x130 CPU: 23 PID: 130 Comm: ksoftirqd/23 Kdump: loaded Tainted: G O 5.10.60 #1 RIP: 0010:percpu_ref_switch_to_atomic_rcu+0x127/0x130 Call Trace: rcu_core+0x30f/0x530 rcu_core_si+0xe/0x10 __do_softirq+0x103/0x2a2 run_ksoftirqd+0x2b/0x40 smpboot_thread_fn+0x11a/0x170 kthread+0x10a/0x140 ret_from_fork+0x22/0x30 Upon further examination, it was discovered that the css structure was associated with hugetlb reservations. For private hugetlb mappings the vma points to a reserve map that contains a pointer to the css. At mmap time, reservations are set up and a reference to the css is taken. This reference is dropped in the vma close operation; hugetlb_vm_op_close. However, if a vma is split no additional reference to the css is taken yet hugetlb_vm_op_close will be called twice for the split vma resulting in an underflow. Fix by taking another reference in hugetlb_vm_op_open. Note that the reference is only taken for the owner of the reserve map. In the more common fork case, the pointer to the reserve map is cleared for non-owning vmas. Link: https://lkml.kernel.org/r/20210830215015.155224-1-mike.kravetz@oracle.com Fixes: e9fe92ae0cd2 ("hugetlb_cgroup: add reservation accounting for private mappings") Signed-off-by: Mike Kravetz Reported-by: Guillaume Morin Suggested-by: Guillaume Morin Tested-by: Guillaume Morin Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/hugetlb_cgroup.h | 12 ++++++++++++ mm/hugetlb.c | 4 +++- 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index 0bff345c4bc6..171bf1be4011 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -118,6 +118,13 @@ static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg) css_put(&h_cg->css); } +static inline void resv_map_dup_hugetlb_cgroup_uncharge_info( + struct resv_map *resv_map) +{ + if (resv_map->css) + css_get(resv_map->css); +} + extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr); extern int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages, @@ -196,6 +203,11 @@ static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg) { } +static inline void resv_map_dup_hugetlb_cgroup_uncharge_info( + struct resv_map *resv_map) +{ +} + static inline int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index fa6b0ac6c280..6e92ab0ae070 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3659,8 +3659,10 @@ static void hugetlb_vm_op_open(struct vm_area_struct *vma) * after this open call completes. It is therefore safe to take a * new reference here without additional locking. */ - if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) + if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { + resv_map_dup_hugetlb_cgroup_uncharge_info(resv); kref_get(&resv->refs); + } } static void hugetlb_vm_op_close(struct vm_area_struct *vma) -- cgit v1.2.3 From 2d2d8b0eca6473eac0a142edea4c2b038da08cbd Mon Sep 17 00:00:00 2001 From: Liu Zixian Date: Wed, 8 Sep 2021 18:10:05 -0700 Subject: mm/hugetlb: initialize hugetlb_usage in mm_init commit 13db8c50477d83ad3e3b9b0ae247e5cd833a7ae4 upstream. After fork, the child process will get incorrect (2x) hugetlb_usage. If a process uses 5 2MB hugetlb pages in an anonymous mapping, HugetlbPages: 10240 kB and then forks, the child will show, HugetlbPages: 20480 kB The reason for double the amount is because hugetlb_usage will be copied from the parent and then increased when we copy page tables from parent to child. Child will have 2x actual usage. Fix this by adding hugetlb_count_init in mm_init. Link: https://lkml.kernel.org/r/20210826071742.877-1-liuzixian4@huawei.com Fixes: 5d317b2b6536 ("mm: hugetlb: proc: add HugetlbPages field to /proc/PID/status") Signed-off-by: Liu Zixian Reviewed-by: Naoya Horiguchi Reviewed-by: Mike Kravetz Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/hugetlb.h | 9 +++++++++ kernel/fork.c | 1 + 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 5b68c9787f7c..b9fbb6d4150e 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -722,6 +722,11 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h, void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm); +static inline void hugetlb_count_init(struct mm_struct *mm) +{ + atomic_long_set(&mm->hugetlb_usage, 0); +} + static inline void hugetlb_count_add(long l, struct mm_struct *mm) { atomic_long_add(l, &mm->hugetlb_usage); @@ -897,6 +902,10 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h, return &mm->page_table_lock; } +static inline void hugetlb_count_init(struct mm_struct *mm) +{ +} + static inline void hugetlb_report_usage(struct seq_file *f, struct mm_struct *m) { } diff --git a/kernel/fork.c b/kernel/fork.c index 9705439439fe..3f96400a0ac6 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1037,6 +1037,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm->pmd_huge_pte = NULL; #endif mm_init_uprobes_state(mm); + hugetlb_count_init(mm); if (current->mm) { mm->flags = current->mm->flags & MMF_INIT_MASK; -- cgit v1.2.3