From f98b733e93e00365b4df78fbb33c2cad3080f6bb Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 14 May 2015 15:16:50 -0700 Subject: drivers/rtc/rtc-armada38x.c: remove unused local `flags' Reported-by: Fengguang Wu Cc: Gregory CLEMENT Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/rtc/rtc-armada38x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/rtc/rtc-armada38x.c b/drivers/rtc/rtc-armada38x.c index cb70ced7e0db..4b62d1a875e4 100644 --- a/drivers/rtc/rtc-armada38x.c +++ b/drivers/rtc/rtc-armada38x.c @@ -64,7 +64,7 @@ static void rtc_delayed_write(u32 val, struct armada38x_rtc *rtc, int offset) static int armada38x_rtc_read_time(struct device *dev, struct rtc_time *tm) { struct armada38x_rtc *rtc = dev_get_drvdata(dev); - unsigned long time, time_check, flags; + unsigned long time, time_check; mutex_lock(&rtc->mutex_time); time = readl(rtc->regs + RTC_TIME); -- cgit v1.2.3 From 4933f55fe72c86e57efc454dd6e673c7f17af5a3 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 14 May 2015 15:16:53 -0700 Subject: tools/vm: fix page-flags build libabikfs.a doesn't exist anymore, so we now need to link with libapi.a. Signed-off-by: Andi Kleen Cc: Naoya Horiguchi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- tools/vm/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/vm/Makefile b/tools/vm/Makefile index ac884b65a072..93aadaf7ff63 100644 --- a/tools/vm/Makefile +++ b/tools/vm/Makefile @@ -3,7 +3,7 @@ TARGETS=page-types slabinfo page_owner_sort LIB_DIR = ../lib/api -LIBS = $(LIB_DIR)/libapikfs.a +LIBS = $(LIB_DIR)/libapi.a CC = $(CROSS_COMPILE)gcc CFLAGS = -Wall -Wextra -I../lib/ -- cgit v1.2.3 From 8f4fc071b1926d0b20336e2b3f8ab85c94c734c5 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 14 May 2015 15:16:55 -0700 Subject: gfp: add __GFP_NOACCOUNT Not all kmem allocations should be accounted to memcg. The following patch gives an example when accounting of a certain type of allocations to memcg can effectively result in a memory leak. This patch adds the __GFP_NOACCOUNT flag which if passed to kmalloc and friends will force the allocation to go through the root cgroup. It will be used by the next patch. Note, since in case of kmemleak enabled each kmalloc implies yet another allocation from the kmemleak_object cache, we add __GFP_NOACCOUNT to gfp_kmemleak_mask. Alternatively, we could introduce a per kmem cache flag disabling accounting for all allocations of a particular kind, but (a) we would not be able to bypass accounting for kmalloc then and (b) a kmem cache with this flag set could not be merged with a kmem cache without this flag, which would increase the number of global caches and therefore fragmentation even if the memory cgroup controller is not used. Despite its generic name, currently __GFP_NOACCOUNT disables accounting only for kmem allocations while user page allocations are always charged. To catch abusing of this flag, a warning is issued on an attempt of passing it to mem_cgroup_try_charge. Signed-off-by: Vladimir Davydov Cc: Tejun Heo Cc: Johannes Weiner Cc: Michal Hocko Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Greg Thelen Cc: Greg Kroah-Hartman Cc: [4.0.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 ++ include/linux/memcontrol.h | 4 ++++ mm/kmemleak.c | 3 ++- 3 files changed, 8 insertions(+), 1 deletion(-) diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 97a9373e61e8..15928f0647e4 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -30,6 +30,7 @@ struct vm_area_struct; #define ___GFP_HARDWALL 0x20000u #define ___GFP_THISNODE 0x40000u #define ___GFP_RECLAIMABLE 0x80000u +#define ___GFP_NOACCOUNT 0x100000u #define ___GFP_NOTRACK 0x200000u #define ___GFP_NO_KSWAPD 0x400000u #define ___GFP_OTHER_NODE 0x800000u @@ -87,6 +88,7 @@ struct vm_area_struct; #define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) /* Enforce hardwall cpuset memory allocs */ #define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE)/* No fallback, no policies */ #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) /* Page is reclaimable */ +#define __GFP_NOACCOUNT ((__force gfp_t)___GFP_NOACCOUNT) /* Don't account to kmemcg */ #define __GFP_NOTRACK ((__force gfp_t)___GFP_NOTRACK) /* Don't track with kmemcheck */ #define __GFP_NO_KSWAPD ((__force gfp_t)___GFP_NO_KSWAPD) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 72dff5fb0d0c..6c8918114804 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -463,6 +463,8 @@ memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order) if (!memcg_kmem_enabled()) return true; + if (gfp & __GFP_NOACCOUNT) + return true; /* * __GFP_NOFAIL allocations will move on even if charging is not * possible. Therefore we don't even try, and have this allocation @@ -522,6 +524,8 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp) { if (!memcg_kmem_enabled()) return cachep; + if (gfp & __GFP_NOACCOUNT) + return cachep; if (gfp & __GFP_NOFAIL) return cachep; if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD)) diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 5405aff5a590..f0fe4f2c1fa7 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -115,7 +115,8 @@ #define BYTES_PER_POINTER sizeof(void *) /* GFP bitmask for kmemleak internal allocations */ -#define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC)) | \ +#define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC | \ + __GFP_NOACCOUNT)) | \ __GFP_NORETRY | __GFP_NOMEMALLOC | \ __GFP_NOWARN) -- cgit v1.2.3 From 499611ed451508a42d1d7d1faff10177827755d5 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Thu, 14 May 2015 15:16:58 -0700 Subject: kernfs: do not account ino_ida allocations to memcg root->ino_ida is used for kernfs inode number allocations. Since IDA has a layered structure, different IDs can reside on the same layer, which is currently accounted to some memory cgroup. The problem is that each kmem cache of a memory cgroup has its own directory on sysfs (under /sys/fs/kernel//cgroup). If the inode number of such a directory or any file in it gets allocated from a layer accounted to the cgroup which the cache is created for, the cgroup will get pinned for good, because one has to free all kmem allocations accounted to a cgroup in order to release it and destroy all its kmem caches. That said we must not account layers of ino_ida to any memory cgroup. Since per net init operations may create new sysfs entries directly (e.g. lo device) or indirectly (nf_conntrack creates a new kmem cache per each namespace, which, in turn, creates new sysfs entries), an easy way to reproduce this issue is by creating network namespace(s) from inside a kmem-active memory cgroup. Signed-off-by: Vladimir Davydov Acked-by: Tejun Heo Cc: Johannes Weiner Cc: Michal Hocko Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Greg Thelen Cc: Greg Kroah-Hartman Cc: [4.0.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/kernfs/dir.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index f131fc23ffc4..fffca9517321 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -518,7 +518,14 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, if (!kn) goto err_out1; - ret = ida_simple_get(&root->ino_ida, 1, 0, GFP_KERNEL); + /* + * If the ino of the sysfs entry created for a kmem cache gets + * allocated from an ida layer, which is accounted to the memcg that + * owns the cache, the memcg will get pinned forever. So do not account + * ino ida allocations. + */ + ret = ida_simple_get(&root->ino_ida, 1, 0, + GFP_KERNEL | __GFP_NOACCOUNT); if (ret < 0) goto err_out2; kn->ino = ret; -- cgit v1.2.3 From 929aa5b250bfc59aca492d3213c7f3a53e2a5247 Mon Sep 17 00:00:00 2001 From: Josh Triplett Date: Thu, 14 May 2015 15:17:01 -0700 Subject: uidgid: make uid_valid and gid_valid work with !CONFIG_MULTIUSER {u,g}id_valid call {u,g}id_eq, which calls __k{u,g}id_val on both arguments and compares. With !CONFIG_MULTIUSER, __k{u,g}id_val return a constant 0, which makes {u,g}id_valid always return false. Change {u,g}id_valid to compare their argument against -1 instead. That produces identical results in the normal CONFIG_MULTIUSER=y case, but with !CONFIG_MULTIUSER will make {u,g}id_valid constant-fold into "return true;" rather than "return false;". This fixes uses of devpts without CONFIG_MULTIUSER. Signed-off-by: Josh Triplett Reported-by: Fengguang Wu , Cc: Peter Hurley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/uidgid.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/uidgid.h b/include/linux/uidgid.h index 0ee05da38899..03835522dfcb 100644 --- a/include/linux/uidgid.h +++ b/include/linux/uidgid.h @@ -109,12 +109,12 @@ static inline bool gid_lte(kgid_t left, kgid_t right) static inline bool uid_valid(kuid_t uid) { - return !uid_eq(uid, INVALID_UID); + return __kuid_val(uid) != (uid_t) -1; } static inline bool gid_valid(kgid_t gid) { - return !gid_eq(gid, INVALID_GID); + return __kgid_val(gid) != (gid_t) -1; } #ifdef CONFIG_USER_NS -- cgit v1.2.3 From 1ae7013dfa4281644a9a9591105c24d639216b22 Mon Sep 17 00:00:00 2001 From: Hui Zhu Date: Thu, 14 May 2015 15:17:04 -0700 Subject: CMA: page_isolation: check buddy before accessing it I had an issue: Unable to handle kernel NULL pointer dereference at virtual address 0000082a pgd = cc970000 [0000082a] *pgd=00000000 Internal error: Oops: 5 [#1] PREEMPT SMP ARM PC is at get_pageblock_flags_group+0x5c/0xb0 LR is at unset_migratetype_isolate+0x148/0x1b0 pc : [] lr : [] psr: 80000093 sp : c7029d00 ip : 00000105 fp : c7029d1c r10: 00000001 r9 : 0000000a r8 : 00000004 r7 : 60000013 r6 : 000000a4 r5 : c0a357e4 r4 : 00000000 r3 : 00000826 r2 : 00000002 r1 : 00000000 r0 : 0000003f Flags: Nzcv IRQs off FIQs on Mode SVC_32 ISA ARM Segment user Control: 10c5387d Table: 2cb7006a DAC: 00000015 Backtrace: get_pageblock_flags_group+0x0/0xb0 unset_migratetype_isolate+0x0/0x1b0 undo_isolate_page_range+0x0/0xdc __alloc_contig_range+0x0/0x34c alloc_contig_range+0x0/0x18 This issue is because when calling unset_migratetype_isolate() to unset a part of CMA memory, it try to access the buddy page to get its status: if (order >= pageblock_order) { page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1); buddy_idx = __find_buddy_index(page_idx, order); buddy = page + (buddy_idx - page_idx); if (!is_migrate_isolate_page(buddy)) { But the begin addr of this part of CMA memory is very close to a part of memory that is reserved at boot time (not in buddy system). So add a check before accessing it. [akpm@linux-foundation.org: use conventional code layout] Signed-off-by: Hui Zhu Suggested-by: Laura Abbott Suggested-by: Joonsoo Kim Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_isolation.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 755a42c76eb4..303c908790ef 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -101,7 +101,8 @@ void unset_migratetype_isolate(struct page *page, unsigned migratetype) buddy_idx = __find_buddy_index(page_idx, order); buddy = page + (buddy_idx - page_idx); - if (!is_migrate_isolate_page(buddy)) { + if (pfn_valid_within(page_to_pfn(buddy)) && + !is_migrate_isolate_page(buddy)) { __isolate_free_page(page, order); kernel_map_pages(page, (1 << order), 1); set_page_refcounted(page); -- cgit v1.2.3 From b77017555ce514262abcb28a0ff3cc065d4acfb8 Mon Sep 17 00:00:00 2001 From: Jingoo Han Date: Thu, 14 May 2015 15:17:07 -0700 Subject: MAINTAINERS: update Jingoo Han's email address Change my private email address. Signed-off-by: Jingoo Han Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 5d87ccbee19b..64b49f549211 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1935,7 +1935,7 @@ S: Maintained F: drivers/net/wireless/b43legacy/ BACKLIGHT CLASS/SUBSYSTEM -M: Jingoo Han +M: Jingoo Han M: Lee Jones S: Maintained F: drivers/video/backlight/ @@ -3918,7 +3918,7 @@ F: drivers/extcon/ F: Documentation/extcon/ EXYNOS DP DRIVER -M: Jingoo Han +M: Jingoo Han L: dri-devel@lists.freedesktop.org S: Maintained F: drivers/gpu/drm/exynos/exynos_dp* @@ -7557,7 +7557,7 @@ S: Maintained F: drivers/pci/host/*rcar* PCI DRIVER FOR SAMSUNG EXYNOS -M: Jingoo Han +M: Jingoo Han L: linux-pci@vger.kernel.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers) @@ -7565,7 +7565,7 @@ S: Maintained F: drivers/pci/host/pci-exynos.c PCI DRIVER FOR SYNOPSIS DESIGNWARE -M: Jingoo Han +M: Jingoo Han L: linux-pci@vger.kernel.org S: Maintained F: drivers/pci/host/*designware* @@ -8521,7 +8521,7 @@ S: Supported F: sound/soc/samsung/ SAMSUNG FRAMEBUFFER DRIVER -M: Jingoo Han +M: Jingoo Han L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/video/fbdev/s3c-fb.c -- cgit v1.2.3 From b0dc2b9bb4ab782115b964310518ee0b17784277 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 14 May 2015 15:17:09 -0700 Subject: mm, numa: really disable NUMA balancing by default on single node machines NUMA balancing is meant to be disabled by default on UMA machines but the check is using nr_node_ids (highest node) instead of num_online_nodes (online nodes). The consequences are that a UMA machine with a node ID of 1 or higher will enable NUMA balancing. This will incur useless overhead due to minor faults with the impact depending on the workload. These are the impact on the stats when running a kernel build on a single node machine whose node ID happened to be 1: vanilla patched NUMA base PTE updates 5113158 0 NUMA huge PMD updates 643 0 NUMA page range updates 5442374 0 NUMA hint faults 2109622 0 NUMA hint local faults 2109622 0 NUMA hint local percent 100 100 NUMA pages migrated 0 0 Signed-off-by: Mel Gorman Reviewed-by: Rik van Riel Cc: [3.8+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index ede26291d4aa..747743237d9f 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2518,7 +2518,7 @@ static void __init check_numabalancing_enable(void) if (numabalancing_override) set_numabalancing_state(numabalancing_override == 1); - if (nr_node_ids > 1 && !numabalancing_override) { + if (num_online_nodes() > 1 && !numabalancing_override) { pr_info("%s automatic NUMA balancing. " "Configure with numa_balancing= or the " "kernel.numa_balancing sysctl", -- cgit v1.2.3