From 8e7ae2518f5265f0ef09d561748098fde5a87ccd Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 13 Mar 2020 18:02:09 -0700 Subject: bpf: Sanitize the bpf_struct_ops tcp-cc name The bpf_struct_ops tcp-cc name should be sanitized in order to avoid problematic chars (e.g. whitespaces). This patch reuses the bpf_obj_name_cpy() for accepting the same set of characters in order to keep a consistent bpf programming experience. A "size" param is added. Also, the strlen is returned on success so that the caller (like the bpf_tcp_ca here) can error out on empty name. The existing callers of the bpf_obj_name_cpy() only need to change the testing statement to "if (err < 0)". For all these existing callers, the err will be overwritten later, so no extra change is needed for the new strlen return value. v3: - reverse xmas tree style v2: - Save the orig_src to avoid "end - size" (Andrii) Fixes: 0baf26b0fcd7 ("bpf: tcp: Support tcp_congestion_ops in bpf") Signed-off-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20200314010209.1131542-1-kafai@fb.com --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 49b1a70e12c8..212991f6f2a5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -160,6 +160,7 @@ static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) } void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); +int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size); struct bpf_offload_dev; struct bpf_offloaded_map; -- cgit v1.2.3 From 692b65c84f0bb0ca70c11e62c865cbaf7e8e3afd Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Tue, 17 Mar 2020 15:54:22 +0100 Subject: i2c: fix a doc warning Don't let non-letters inside a literal block without escaping it, as the toolchain would mis-interpret it: ./include/linux/i2c.h:518: WARNING: Inline strong start-string without end-string. Signed-off-by: Mauro Carvalho Chehab Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index f834687989f7..f6b942150631 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -506,7 +506,7 @@ i2c_register_board_info(int busnum, struct i2c_board_info const *info, * @smbus_xfer_atomic: same as @smbus_xfer. Yet, only using atomic context * so e.g. PMICs can be accessed very late before shutdown. Optional. * @functionality: Return the flags that this algorithm/adapter pair supports - * from the I2C_FUNC_* flags. + * from the ``I2C_FUNC_*`` flags. * @reg_slave: Register given client to I2C slave mode of this adapter * @unreg_slave: Unregister given client from I2C slave mode of this adapter * @@ -515,7 +515,7 @@ i2c_register_board_info(int busnum, struct i2c_board_info const *info, * be addressed using the same bus algorithms - i.e. bit-banging or the PCF8584 * to name two of the most common. * - * The return codes from the @master_xfer{_atomic} fields should indicate the + * The return codes from the ``master_xfer{_atomic}`` fields should indicate the * type of error code that occurred during the transfer, as documented in the * Kernel Documentation file Documentation/i2c/fault-codes.rst. */ -- cgit v1.2.3 From 7614209736fbc4927584d4387faade4f31444fce Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 9 Mar 2020 12:03:14 +0100 Subject: ceph: check POOL_FLAG_FULL/NEARFULL in addition to OSDMAP_FULL/NEARFULL CEPH_OSDMAP_FULL/NEARFULL aren't set since mimic, so we need to consult per-pool flags as well. Unfortunately the backwards compatibility here is lacking: - the change that deprecated OSDMAP_FULL/NEARFULL went into mimic, but was guarded by require_osd_release >= RELEASE_LUMINOUS - it was subsequently backported to luminous in v12.2.2, but that makes no difference to clients that only check OSDMAP_FULL/NEARFULL because require_osd_release is not client-facing -- it is for OSDs Since all kernels are affected, the best we can do here is just start checking both map flags and pool flags and send that to stable. These checks are best effort, so take osdc->lock and look up pool flags just once. Remove the FIXME, since filesystem quotas are checked above and RADOS quotas are reflected in POOL_FLAG_FULL: when the pool reaches its quota, both POOL_FLAG_FULL and POOL_FLAG_FULL_QUOTA are set. Cc: stable@vger.kernel.org Reported-by: Yanhu Cao Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton Acked-by: Sage Weil --- fs/ceph/file.c | 14 +++++++++++--- include/linux/ceph/osdmap.h | 4 ++++ include/linux/ceph/rados.h | 6 ++++-- net/ceph/osdmap.c | 9 +++++++++ 4 files changed, 28 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 7e0190b1f821..5a478cd06e11 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1415,10 +1415,13 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) struct inode *inode = file_inode(file); struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_fs_client *fsc = ceph_inode_to_client(inode); + struct ceph_osd_client *osdc = &fsc->client->osdc; struct ceph_cap_flush *prealloc_cf; ssize_t count, written = 0; int err, want, got; bool direct_lock = false; + u32 map_flags; + u64 pool_flags; loff_t pos; loff_t limit = max(i_size_read(inode), fsc->max_file_size); @@ -1481,8 +1484,12 @@ retry_snap: goto out; } - /* FIXME: not complete since it doesn't account for being at quota */ - if (ceph_osdmap_flag(&fsc->client->osdc, CEPH_OSDMAP_FULL)) { + down_read(&osdc->lock); + map_flags = osdc->osdmap->flags; + pool_flags = ceph_pg_pool_flags(osdc->osdmap, ci->i_layout.pool_id); + up_read(&osdc->lock); + if ((map_flags & CEPH_OSDMAP_FULL) || + (pool_flags & CEPH_POOL_FLAG_FULL)) { err = -ENOSPC; goto out; } @@ -1575,7 +1582,8 @@ retry_snap: } if (written >= 0) { - if (ceph_osdmap_flag(&fsc->client->osdc, CEPH_OSDMAP_NEARFULL)) + if ((map_flags & CEPH_OSDMAP_NEARFULL) || + (pool_flags & CEPH_POOL_FLAG_NEARFULL)) iocb->ki_flags |= IOCB_DSYNC; written = generic_write_sync(iocb, written); } diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index e081b56f1c1d..5e601975745f 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -37,6 +37,9 @@ int ceph_spg_compare(const struct ceph_spg *lhs, const struct ceph_spg *rhs); #define CEPH_POOL_FLAG_HASHPSPOOL (1ULL << 0) /* hash pg seed and pool id together */ #define CEPH_POOL_FLAG_FULL (1ULL << 1) /* pool is full */ +#define CEPH_POOL_FLAG_FULL_QUOTA (1ULL << 10) /* pool ran out of quota, + will set FULL too */ +#define CEPH_POOL_FLAG_NEARFULL (1ULL << 11) /* pool is nearfull */ struct ceph_pg_pool_info { struct rb_node node; @@ -304,5 +307,6 @@ extern struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map, extern const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id); extern int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name); +u64 ceph_pg_pool_flags(struct ceph_osdmap *map, u64 id); #endif diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index 59bdfd470100..88ed3c5c04c5 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -143,8 +143,10 @@ extern const char *ceph_osd_state_name(int s); /* * osd map flag bits */ -#define CEPH_OSDMAP_NEARFULL (1<<0) /* sync writes (near ENOSPC) */ -#define CEPH_OSDMAP_FULL (1<<1) /* no data writes (ENOSPC) */ +#define CEPH_OSDMAP_NEARFULL (1<<0) /* sync writes (near ENOSPC), + not set since ~luminous */ +#define CEPH_OSDMAP_FULL (1<<1) /* no data writes (ENOSPC), + not set since ~luminous */ #define CEPH_OSDMAP_PAUSERD (1<<2) /* pause all reads */ #define CEPH_OSDMAP_PAUSEWR (1<<3) /* pause all writes */ #define CEPH_OSDMAP_PAUSEREC (1<<4) /* pause recovery */ diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 4e0de14f80bb..2a6e63a8edbe 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -710,6 +710,15 @@ int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name) } EXPORT_SYMBOL(ceph_pg_poolid_by_name); +u64 ceph_pg_pool_flags(struct ceph_osdmap *map, u64 id) +{ + struct ceph_pg_pool_info *pi; + + pi = __lookup_pg_pool(&map->pg_pools, id); + return pi ? pi->flags : 0; +} +EXPORT_SYMBOL(ceph_pg_pool_flags); + static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi) { rb_erase(&pi->node, root); -- cgit v1.2.3 From e886274031200bb60965c1b9c49b7acda56a93bd Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 10 Mar 2020 16:19:01 +0100 Subject: libceph: fix alloc_msg_with_page_vector() memory leaks Make it so that CEPH_MSG_DATA_PAGES data item can own pages, fixing a bunch of memory leaks for a page vector allocated in alloc_msg_with_page_vector(). Currently, only watch-notify messages trigger this allocation, and normally the page vector is freed either in handle_watch_notify() or by the caller of ceph_osdc_notify(). But if the message is freed before that (e.g. if the session faults while reading in the message or if the notify is stale), we leak the page vector. This was supposed to be fixed by switching to a message-owned pagelist, but that never happened. Fixes: 1907920324f1 ("libceph: support for sending notifies") Reported-by: Roman Penyaev Signed-off-by: Ilya Dryomov Reviewed-by: Roman Penyaev --- include/linux/ceph/messenger.h | 7 ++++--- net/ceph/messenger.c | 9 +++++++-- net/ceph/osd_client.c | 14 +++----------- 3 files changed, 14 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index c4458dc6a757..76371aaae2d1 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -175,9 +175,10 @@ struct ceph_msg_data { #endif /* CONFIG_BLOCK */ struct ceph_bvec_iter bvec_pos; struct { - struct page **pages; /* NOT OWNER. */ + struct page **pages; size_t length; /* total # bytes */ unsigned int alignment; /* first page */ + bool own_pages; }; struct ceph_pagelist *pagelist; }; @@ -356,8 +357,8 @@ extern void ceph_con_keepalive(struct ceph_connection *con); extern bool ceph_con_keepalive_expired(struct ceph_connection *con, unsigned long interval); -extern void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages, - size_t length, size_t alignment); +void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages, + size_t length, size_t alignment, bool own_pages); extern void ceph_msg_data_add_pagelist(struct ceph_msg *msg, struct ceph_pagelist *pagelist); #ifdef CONFIG_BLOCK diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 5b4bd8261002..f8ca5edc5f2c 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -3248,12 +3248,16 @@ static struct ceph_msg_data *ceph_msg_data_add(struct ceph_msg *msg) static void ceph_msg_data_destroy(struct ceph_msg_data *data) { - if (data->type == CEPH_MSG_DATA_PAGELIST) + if (data->type == CEPH_MSG_DATA_PAGES && data->own_pages) { + int num_pages = calc_pages_for(data->alignment, data->length); + ceph_release_page_vector(data->pages, num_pages); + } else if (data->type == CEPH_MSG_DATA_PAGELIST) { ceph_pagelist_release(data->pagelist); + } } void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages, - size_t length, size_t alignment) + size_t length, size_t alignment, bool own_pages) { struct ceph_msg_data *data; @@ -3265,6 +3269,7 @@ void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages, data->pages = pages; data->length = length; data->alignment = alignment & ~PAGE_MASK; + data->own_pages = own_pages; msg->data_length += length; } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index b68b376d8c2f..af868d3923b9 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -962,7 +962,7 @@ static void ceph_osdc_msg_data_add(struct ceph_msg *msg, BUG_ON(length > (u64) SIZE_MAX); if (length) ceph_msg_data_add_pages(msg, osd_data->pages, - length, osd_data->alignment); + length, osd_data->alignment, false); } else if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGELIST) { BUG_ON(!length); ceph_msg_data_add_pagelist(msg, osd_data->pagelist); @@ -4436,9 +4436,7 @@ static void handle_watch_notify(struct ceph_osd_client *osdc, CEPH_MSG_DATA_PAGES); *lreq->preply_pages = data->pages; *lreq->preply_len = data->length; - } else { - ceph_release_page_vector(data->pages, - calc_pages_for(0, data->length)); + data->own_pages = false; } } lreq->notify_finish_error = return_code; @@ -5506,9 +5504,6 @@ out_unlock_osdc: return m; } -/* - * TODO: switch to a msg-owned pagelist - */ static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr) { struct ceph_msg *m; @@ -5522,7 +5517,6 @@ static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr) if (data_len) { struct page **pages; - struct ceph_osd_data osd_data; pages = ceph_alloc_page_vector(calc_pages_for(0, data_len), GFP_NOIO); @@ -5531,9 +5525,7 @@ static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr) return NULL; } - ceph_osd_data_pages_init(&osd_data, pages, data_len, 0, false, - false); - ceph_osdc_msg_data_add(m, &osd_data); + ceph_msg_data_add_pages(m, pages, data_len, 0, true); } return m; -- cgit v1.2.3 From 575a97acc3b7446094b0dcaf6285c7c6934c2477 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 25 Mar 2020 09:09:19 +0100 Subject: ieee80211: fix HE SPR size calculation The he_sr_control field is just a u8, so le32_to_cpu() shouldn't be applied to it; this was evidently copied from ieee80211_he_oper_size(). Fix it, and also adjust the type of the local variable. Fixes: ef11a931bd1c ("mac80211: HE: add Spatial Reuse element parsing support") Signed-off-by: Johannes Berg Link: https://lore.kernel.org/r/20200325090918.dfe483b49e06.Ia53622f23b2610a2ae6ea39a199866196fe946c1@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 7d3f2ced92d1..73c66a3a33ae 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2102,14 +2102,14 @@ ieee80211_he_spr_size(const u8 *he_spr_ie) { struct ieee80211_he_spr *he_spr = (void *)he_spr_ie; u8 spr_len = sizeof(struct ieee80211_he_spr); - u32 he_spr_params; + u8 he_spr_params; /* Make sure the input is not NULL */ if (!he_spr_ie) return 0; /* Calc required length */ - he_spr_params = le32_to_cpu(he_spr->he_sr_control); + he_spr_params = he_spr->he_sr_control; if (he_spr_params & IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT) spr_len++; if (he_spr_params & IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT) -- cgit v1.2.3 From 4e934301203648b1705360c1c52d4ce2e2acec5e Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Tue, 24 Mar 2020 19:22:57 -0700 Subject: clk: Pass correct arguments to __clk_hw_register_gate() I copy/pasted these macros and forgot to update the argument names and where they're passed to. Fix it so that these macros make sense. Reported-by: Maxime Ripard Fixes: 194efb6e2667 ("clk: gate: Add support for specifying parents via DT/pointers") Signed-off-by: Stephen Boyd Link: https://lkml.kernel.org/r/20200325022257.148244-1-sboyd@kernel.org Tested-by: Maxime Ripard --- include/linux/clk-provider.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 952ac035bab9..bd1ee9039558 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -522,9 +522,9 @@ struct clk *clk_register_gate(struct device *dev, const char *name, * @clk_gate_flags: gate-specific flags for this clock * @lock: shared register lock for this clock */ -#define clk_hw_register_gate_parent_hw(dev, name, parent_name, flags, reg, \ +#define clk_hw_register_gate_parent_hw(dev, name, parent_hw, flags, reg, \ bit_idx, clk_gate_flags, lock) \ - __clk_hw_register_gate((dev), NULL, (name), (parent_name), NULL, \ + __clk_hw_register_gate((dev), NULL, (name), NULL, (parent_hw), \ NULL, (flags), (reg), (bit_idx), \ (clk_gate_flags), (lock)) /** @@ -539,10 +539,10 @@ struct clk *clk_register_gate(struct device *dev, const char *name, * @clk_gate_flags: gate-specific flags for this clock * @lock: shared register lock for this clock */ -#define clk_hw_register_gate_parent_data(dev, name, parent_name, flags, reg, \ +#define clk_hw_register_gate_parent_data(dev, name, parent_data, flags, reg, \ bit_idx, clk_gate_flags, lock) \ - __clk_hw_register_gate((dev), NULL, (name), (parent_name), NULL, \ - NULL, (flags), (reg), (bit_idx), \ + __clk_hw_register_gate((dev), NULL, (name), NULL, NULL, (parent_data), \ + (flags), (reg), (bit_idx), \ (clk_gate_flags), (lock)) void clk_unregister_gate(struct clk *clk); void clk_hw_unregister_gate(struct clk_hw *hw); -- cgit v1.2.3 From 8380ce479010f2f779587b462a9b4681934297c3 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Sat, 28 Mar 2020 19:17:25 -0700 Subject: mm: fork: fix kernel_stack memcg stats for various stack implementations Depending on CONFIG_VMAP_STACK and the THREAD_SIZE / PAGE_SIZE ratio the space for task stacks can be allocated using __vmalloc_node_range(), alloc_pages_node() and kmem_cache_alloc_node(). In the first and the second cases page->mem_cgroup pointer is set, but in the third it's not: memcg membership of a slab page should be determined using the memcg_from_slab_page() function, which looks at page->slab_cache->memcg_params.memcg . In this case, using mod_memcg_page_state() (as in account_kernel_stack()) is incorrect: page->mem_cgroup pointer is NULL even for pages charged to a non-root memory cgroup. It can lead to kernel_stack per-memcg counters permanently showing 0 on some architectures (depending on the configuration). In order to fix it, let's introduce a mod_memcg_obj_state() helper, which takes a pointer to a kernel object as a first argument, uses mem_cgroup_from_obj() to get a RCU-protected memcg pointer and calls mod_memcg_state(). It allows to handle all possible configurations (CONFIG_VMAP_STACK and various THREAD_SIZE/PAGE_SIZE values) without spilling any memcg/kmem specifics into fork.c . Note: This is a special version of the patch created for stable backports. It contains code from the following two patches: - mm: memcg/slab: introduce mem_cgroup_from_obj() - mm: fork: fix kernel_stack memcg stats for various stack implementations [guro@fb.com: introduce mem_cgroup_from_obj()] Link: http://lkml.kernel.org/r/20200324004221.GA36662@carbon.dhcp.thefacebook.com Fixes: 4d96ba353075 ("mm: memcg/slab: stop setting page->mem_cgroup pointer for slab pages") Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Bharata B Rao Cc: Shakeel Butt Cc: Link: http://lkml.kernel.org/r/20200303233550.251375-1-guro@fb.com Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 12 ++++++++++++ kernel/fork.c | 4 ++-- mm/memcontrol.c | 38 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 52 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index a7a0a1a5c8d5..e9ba01336d4e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -695,6 +695,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val); +void mod_memcg_obj_state(void *p, int idx, int val); static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) @@ -1123,6 +1124,10 @@ static inline void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, __mod_node_page_state(page_pgdat(page), idx, val); } +static inline void mod_memcg_obj_state(void *p, int idx, int val) +{ +} + static inline unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, @@ -1427,6 +1432,8 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg) return memcg ? memcg->kmemcg_id : -1; } +struct mem_cgroup *mem_cgroup_from_obj(void *p); + #else static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) @@ -1468,6 +1475,11 @@ static inline void memcg_put_cache_ids(void) { } +static inline struct mem_cgroup *mem_cgroup_from_obj(void *p) +{ + return NULL; +} + #endif /* CONFIG_MEMCG_KMEM */ #endif /* _LINUX_MEMCONTROL_H */ diff --git a/kernel/fork.c b/kernel/fork.c index 86425305cd4a..d90af13431c7 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -397,8 +397,8 @@ static void account_kernel_stack(struct task_struct *tsk, int account) mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB, THREAD_SIZE / 1024 * account); - mod_memcg_page_state(first_page, MEMCG_KERNEL_STACK_KB, - account * (THREAD_SIZE / 1024)); + mod_memcg_obj_state(stack, MEMCG_KERNEL_STACK_KB, + account * (THREAD_SIZE / 1024)); } } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7a4bd8b9adc2..7ddf91c4295f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -777,6 +777,17 @@ void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) rcu_read_unlock(); } +void mod_memcg_obj_state(void *p, int idx, int val) +{ + struct mem_cgroup *memcg; + + rcu_read_lock(); + memcg = mem_cgroup_from_obj(p); + if (memcg) + mod_memcg_state(memcg, idx, val); + rcu_read_unlock(); +} + /** * __count_memcg_events - account VM events in a cgroup * @memcg: the memory cgroup @@ -2661,6 +2672,33 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg, } #ifdef CONFIG_MEMCG_KMEM +/* + * Returns a pointer to the memory cgroup to which the kernel object is charged. + * + * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(), + * cgroup_mutex, etc. + */ +struct mem_cgroup *mem_cgroup_from_obj(void *p) +{ + struct page *page; + + if (mem_cgroup_disabled()) + return NULL; + + page = virt_to_head_page(p); + + /* + * Slab pages don't have page->mem_cgroup set because corresponding + * kmem caches can be reparented during the lifetime. That's why + * memcg_from_slab_page() should be used instead. + */ + if (PageSlab(page)) + return memcg_from_slab_page(page); + + /* All other pages use page->mem_cgroup */ + return page->mem_cgroup; +} + static int memcg_alloc_cache_id(void) { int id, size; -- cgit v1.2.3