From d7b028f56a971a2e4d8d7887540a144eeefcd4ab Mon Sep 17 00:00:00 2001 From: Dan Streetman Date: Fri, 3 Feb 2017 13:13:09 -0800 Subject: zswap: disable changing params if init fails Add zswap_init_failed bool that prevents changing any of the module params, if init_zswap() fails, and set zswap_enabled to false. Change 'enabled' param to a callback, and check zswap_init_failed before allowing any change to 'enabled', 'zpool', or 'compressor' params. Any driver that is built-in to the kernel will not be unloaded if its init function returns error, and its module params remain accessible for users to change via sysfs. Since zswap uses param callbacks, which assume that zswap has been initialized, changing the zswap params after a failed initialization will result in WARNING due to the param callbacks expecting a pool to already exist. This prevents that by immediately exiting any of the param callbacks if initialization failed. This was reported here: https://marc.info/?l=linux-mm&m=147004228125528&w=4 And fixes this WARNING: [ 429.723476] WARNING: CPU: 0 PID: 5140 at mm/zswap.c:503 __zswap_pool_current+0x56/0x60 The warning is just noise, and not serious. However, when init fails, zswap frees all its percpu dstmem pages and its kmem cache. The kmem cache might be serious, if kmem_cache_alloc(NULL, gfp) has problems; but the percpu dstmem pages are definitely a problem, as they're used as temporary buffer for compressed pages before copying into place in the zpool. If the user does get zswap enabled after an init failure, then zswap will likely Oops on the first page it tries to compress (or worse, start corrupting memory). Fixes: 90b0fc26d5db ("zswap: change zpool/compressor at runtime") Link: http://lkml.kernel.org/r/20170124200259.16191-2-ddstreet@ieee.org Signed-off-by: Dan Streetman Reported-by: Marcin Miroslaw Cc: Seth Jennings Cc: Michal Hocko Cc: Sergey Senozhatsky Cc: Minchan Kim Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/zswap.c | 30 +++++++++++++++++++++++++++++- 1 file changed, 29 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/zswap.c b/mm/zswap.c index 067a0d62f318..cabf09e0128b 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -78,7 +78,13 @@ static u64 zswap_duplicate_entry; /* Enable/disable zswap (disabled by default) */ static bool zswap_enabled; -module_param_named(enabled, zswap_enabled, bool, 0644); +static int zswap_enabled_param_set(const char *, + const struct kernel_param *); +static struct kernel_param_ops zswap_enabled_param_ops = { + .set = zswap_enabled_param_set, + .get = param_get_bool, +}; +module_param_cb(enabled, &zswap_enabled_param_ops, &zswap_enabled, 0644); /* Crypto compressor to use */ #define ZSWAP_COMPRESSOR_DEFAULT "lzo" @@ -176,6 +182,9 @@ static atomic_t zswap_pools_count = ATOMIC_INIT(0); /* used by param callback function */ static bool zswap_init_started; +/* fatal error during init */ +static bool zswap_init_failed; + /********************************* * helpers and fwd declarations **********************************/ @@ -624,6 +633,11 @@ static int __zswap_param_set(const char *val, const struct kernel_param *kp, char *s = strstrip((char *)val); int ret; + if (zswap_init_failed) { + pr_err("can't set param, initialization failed\n"); + return -ENODEV; + } + /* no change required */ if (!strcmp(s, *(char **)kp->arg)) return 0; @@ -703,6 +717,17 @@ static int zswap_zpool_param_set(const char *val, return __zswap_param_set(val, kp, NULL, zswap_compressor); } +static int zswap_enabled_param_set(const char *val, + const struct kernel_param *kp) +{ + if (zswap_init_failed) { + pr_err("can't enable, initialization failed\n"); + return -ENODEV; + } + + return param_set_bool(val, kp); +} + /********************************* * writeback code **********************************/ @@ -1201,6 +1226,9 @@ hp_fail: dstmem_fail: zswap_entry_cache_destroy(); cache_fail: + /* if built-in, we aren't unloaded on failure; don't allow use */ + zswap_init_failed = true; + zswap_enabled = false; return -ENOMEM; } /* must be late so crypto has time to come up */ -- cgit v1.2.3 From 4f40c6e5627ea73b4e7c615c59631f38cc880885 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 3 Feb 2017 13:13:12 -0800 Subject: kasan: respect /proc/sys/kernel/traceoff_on_warning After much waiting I finally reproduced a KASAN issue, only to find my trace-buffer empty of useful information because it got spooled out :/ Make kasan_report honour the /proc/sys/kernel/traceoff_on_warning interface. Link: http://lkml.kernel.org/r/20170125164106.3514-1-aryabinin@virtuozzo.com Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Andrey Ryabinin Acked-by: Alexander Potapenko Cc: Dmitry Vyukov Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kasan/report.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'mm') diff --git a/mm/kasan/report.c b/mm/kasan/report.c index b82b3e215157..f479365530b6 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -13,6 +13,7 @@ * */ +#include #include #include #include @@ -300,6 +301,8 @@ void kasan_report(unsigned long addr, size_t size, if (likely(!kasan_report_enabled())) return; + disable_trace_on_warning(); + info.access_addr = (void *)addr; info.access_size = size; info.is_write = is_write; -- cgit v1.2.3 From 253fd0f02040a19c6fe80e4171659fa3482a422d Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 3 Feb 2017 13:13:15 -0800 Subject: shmem: fix sleeping from atomic context Syzkaller fuzzer managed to trigger this: BUG: sleeping function called from invalid context at mm/shmem.c:852 in_atomic(): 1, irqs_disabled(): 0, pid: 529, name: khugepaged 3 locks held by khugepaged/529: #0: (shrinker_rwsem){++++..}, at: [] shrink_slab.part.59+0x121/0xd30 mm/vmscan.c:451 #1: (&type->s_umount_key#29){++++..}, at: [] trylock_super+0x20/0x100 fs/super.c:392 #2: (&(&sbinfo->shrinklist_lock)->rlock){+.+.-.}, at: [] spin_lock include/linux/spinlock.h:302 [inline] #2: (&(&sbinfo->shrinklist_lock)->rlock){+.+.-.}, at: [] shmem_unused_huge_shrink+0x28e/0x1490 mm/shmem.c:427 CPU: 2 PID: 529 Comm: khugepaged Not tainted 4.10.0-rc5+ #201 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: shmem_undo_range+0xb20/0x2710 mm/shmem.c:852 shmem_truncate_range+0x27/0xa0 mm/shmem.c:939 shmem_evict_inode+0x35f/0xca0 mm/shmem.c:1030 evict+0x46e/0x980 fs/inode.c:553 iput_final fs/inode.c:1515 [inline] iput+0x589/0xb20 fs/inode.c:1542 shmem_unused_huge_shrink+0xbad/0x1490 mm/shmem.c:446 shmem_unused_huge_scan+0x10c/0x170 mm/shmem.c:512 super_cache_scan+0x376/0x450 fs/super.c:106 do_shrink_slab mm/vmscan.c:378 [inline] shrink_slab.part.59+0x543/0xd30 mm/vmscan.c:481 shrink_slab mm/vmscan.c:2592 [inline] shrink_node+0x2c7/0x870 mm/vmscan.c:2592 shrink_zones mm/vmscan.c:2734 [inline] do_try_to_free_pages+0x369/0xc80 mm/vmscan.c:2776 try_to_free_pages+0x3c6/0x900 mm/vmscan.c:2982 __perform_reclaim mm/page_alloc.c:3301 [inline] __alloc_pages_direct_reclaim mm/page_alloc.c:3322 [inline] __alloc_pages_slowpath+0xa24/0x1c30 mm/page_alloc.c:3683 __alloc_pages_nodemask+0x544/0xae0 mm/page_alloc.c:3848 __alloc_pages include/linux/gfp.h:426 [inline] __alloc_pages_node include/linux/gfp.h:439 [inline] khugepaged_alloc_page+0xc2/0x1b0 mm/khugepaged.c:750 collapse_huge_page+0x182/0x1fe0 mm/khugepaged.c:955 khugepaged_scan_pmd+0xfdf/0x12a0 mm/khugepaged.c:1208 khugepaged_scan_mm_slot mm/khugepaged.c:1727 [inline] khugepaged_do_scan mm/khugepaged.c:1808 [inline] khugepaged+0xe9b/0x1590 mm/khugepaged.c:1853 kthread+0x326/0x3f0 kernel/kthread.c:227 ret_from_fork+0x31/0x40 arch/x86/entry/entry_64.S:430 The iput() from atomic context was a bad idea: if after igrab() somebody else calls iput() and we left with the last inode reference, our iput() would lead to inode eviction and therefore sleeping. This patch should fix the situation. Link: http://lkml.kernel.org/r/20170131093141.GA15899@node.shutemov.name Signed-off-by: Kirill A. Shutemov Reported-by: Dmitry Vyukov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/shmem.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/shmem.c b/mm/shmem.c index bb53285a1d99..3a7587a0314d 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -415,6 +415,7 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, struct shrink_control *sc, unsigned long nr_to_split) { LIST_HEAD(list), *pos, *next; + LIST_HEAD(to_remove); struct inode *inode; struct shmem_inode_info *info; struct page *page; @@ -441,9 +442,8 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, /* Check if there's anything to gain */ if (round_up(inode->i_size, PAGE_SIZE) == round_up(inode->i_size, HPAGE_PMD_SIZE)) { - list_del_init(&info->shrinklist); + list_move(&info->shrinklist, &to_remove); removed++; - iput(inode); goto next; } @@ -454,6 +454,13 @@ next: } spin_unlock(&sbinfo->shrinklist_lock); + list_for_each_safe(pos, next, &to_remove) { + info = list_entry(pos, struct shmem_inode_info, shrinklist); + inode = &info->vfs_inode; + list_del_init(&info->shrinklist); + iput(inode); + } + list_for_each_safe(pos, next, &list) { int ret; -- cgit v1.2.3 From deb88a2a19e85842d79ba96b05031739ec327ff4 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Fri, 3 Feb 2017 13:13:20 -0800 Subject: mm/memory_hotplug.c: check start_pfn in test_pages_in_a_zone() Patch series "fix a kernel oops when reading sysfs valid_zones", v2. A sysfs memory file is created for each 2GiB memory block on x86-64 when the system has 64GiB or more memory. [1] When the start address of a memory block is not backed by struct page, i.e. a memory range is not aligned by 2GiB, reading its 'valid_zones' attribute file leads to a kernel oops. This issue was observed on multiple x86-64 systems with more than 64GiB of memory. This patch-set fixes this issue. Patch 1 first fixes an issue in test_pages_in_a_zone(), which does not test the start section. Patch 2 then fixes the kernel oops by extending test_pages_in_a_zone() to return valid [start, end). Note for stable kernels: The memory block size change was made by commit bdee237c0343 ("x86: mm: Use 2GB memory block size on large-memory x86-64 systems"), which was accepted to 3.9. However, this patch-set depends on (and fixes) the change to test_pages_in_a_zone() made by commit 5f0f2887f4de ("mm/memory_hotplug.c: check for missing sections in test_pages_in_a_zone()"), which was accepted to 4.4. So, I recommend that we backport it up to 4.4. [1] 'Commit bdee237c0343 ("x86: mm: Use 2GB memory block size on large-memory x86-64 systems")' This patch (of 2): test_pages_in_a_zone() does not check 'start_pfn' when it is aligned by section since 'sec_end_pfn' is set equal to 'pfn'. Since this function is called for testing the range of a sysfs memory file, 'start_pfn' is always aligned by section. Fix it by properly setting 'sec_end_pfn' to the next section pfn. Also make sure that this function returns 1 only when the range belongs to a zone. Link: http://lkml.kernel.org/r/20170127222149.30893-2-toshi.kani@hpe.com Signed-off-by: Toshi Kani Cc: Andrew Banman Cc: Reza Arbab Cc: Greg KH Cc: [4.4+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index ca2723d47338..1218f73890b6 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1483,7 +1483,7 @@ bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) } /* - * Confirm all pages in a range [start, end) is belongs to the same zone. + * Confirm all pages in a range [start, end) belong to the same zone. */ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn) { @@ -1491,9 +1491,9 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn) struct zone *zone = NULL; struct page *page; int i; - for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn); + for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn + 1); pfn < end_pfn; - pfn = sec_end_pfn + 1, sec_end_pfn += PAGES_PER_SECTION) { + pfn = sec_end_pfn, sec_end_pfn += PAGES_PER_SECTION) { /* Make sure the memory section is present first */ if (!present_section_nr(pfn_to_section_nr(pfn))) continue; @@ -1512,7 +1512,11 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn) zone = page_zone(page); } } - return 1; + + if (zone) + return 1; + else + return 0; } /* -- cgit v1.2.3 From a96dfddbcc04336bbed50dc2b24823e45e09e80c Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Fri, 3 Feb 2017 13:13:23 -0800 Subject: base/memory, hotplug: fix a kernel oops in show_valid_zones() Reading a sysfs "memoryN/valid_zones" file leads to the following oops when the first page of a range is not backed by struct page. show_valid_zones() assumes that 'start_pfn' is always valid for page_zone(). BUG: unable to handle kernel paging request at ffffea017a000000 IP: show_valid_zones+0x6f/0x160 This issue may happen on x86-64 systems with 64GiB or more memory since their memory block size is bumped up to 2GiB. [1] An example of such systems is desribed below. 0x3240000000 is only aligned by 1GiB and this memory block starts from 0x3200000000, which is not backed by struct page. BIOS-e820: [mem 0x0000003240000000-0x000000603fffffff] usable Since test_pages_in_a_zone() already checks holes, fix this issue by extending this function to return 'valid_start' and 'valid_end' for a given range. show_valid_zones() then proceeds with the valid range. [1] 'Commit bdee237c0343 ("x86: mm: Use 2GB memory block size on large-memory x86-64 systems")' Link: http://lkml.kernel.org/r/20170127222149.30893-3-toshi.kani@hpe.com Signed-off-by: Toshi Kani Cc: Greg Kroah-Hartman Cc: Zhang Zhen Cc: Reza Arbab Cc: David Rientjes Cc: Dan Williams Cc: [4.4+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/memory.c | 12 ++++++------ include/linux/memory_hotplug.h | 3 ++- mm/memory_hotplug.c | 20 +++++++++++++++----- 3 files changed, 23 insertions(+), 12 deletions(-) (limited to 'mm') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index dacb6a8418aa..fa26ffd25fa6 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -389,33 +389,33 @@ static ssize_t show_valid_zones(struct device *dev, { struct memory_block *mem = to_memory_block(dev); unsigned long start_pfn, end_pfn; + unsigned long valid_start, valid_end, valid_pages; unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block; - struct page *first_page; struct zone *zone; int zone_shift = 0; start_pfn = section_nr_to_pfn(mem->start_section_nr); end_pfn = start_pfn + nr_pages; - first_page = pfn_to_page(start_pfn); /* The block contains more than one zone can not be offlined. */ - if (!test_pages_in_a_zone(start_pfn, end_pfn)) + if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end)) return sprintf(buf, "none\n"); - zone = page_zone(first_page); + zone = page_zone(pfn_to_page(valid_start)); + valid_pages = valid_end - valid_start; /* MMOP_ONLINE_KEEP */ sprintf(buf, "%s", zone->name); /* MMOP_ONLINE_KERNEL */ - zone_can_shift(start_pfn, nr_pages, ZONE_NORMAL, &zone_shift); + zone_can_shift(valid_start, valid_pages, ZONE_NORMAL, &zone_shift); if (zone_shift) { strcat(buf, " "); strcat(buf, (zone + zone_shift)->name); } /* MMOP_ONLINE_MOVABLE */ - zone_can_shift(start_pfn, nr_pages, ZONE_MOVABLE, &zone_shift); + zone_can_shift(valid_start, valid_pages, ZONE_MOVABLE, &zone_shift); if (zone_shift) { strcat(buf, " "); strcat(buf, (zone + zone_shift)->name); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index c1784c0b4f35..134a2f69c21a 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -85,7 +85,8 @@ extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages); extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); /* VM interface that may be used by firmware interface */ extern int online_pages(unsigned long, unsigned long, int); -extern int test_pages_in_a_zone(unsigned long, unsigned long); +extern int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, + unsigned long *valid_start, unsigned long *valid_end); extern void __offline_isolated_pages(unsigned long, unsigned long); typedef void (*online_page_callback_t)(struct page *page); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 1218f73890b6..b8c11e063ff0 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1484,10 +1484,13 @@ bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) /* * Confirm all pages in a range [start, end) belong to the same zone. + * When true, return its valid [start, end). */ -int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn) +int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, + unsigned long *valid_start, unsigned long *valid_end) { unsigned long pfn, sec_end_pfn; + unsigned long start, end; struct zone *zone = NULL; struct page *page; int i; @@ -1509,14 +1512,20 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn) page = pfn_to_page(pfn + i); if (zone && page_zone(page) != zone) return 0; + if (!zone) + start = pfn + i; zone = page_zone(page); + end = pfn + MAX_ORDER_NR_PAGES; } } - if (zone) + if (zone) { + *valid_start = start; + *valid_end = end; return 1; - else + } else { return 0; + } } /* @@ -1843,6 +1852,7 @@ static int __ref __offline_pages(unsigned long start_pfn, long offlined_pages; int ret, drain, retry_max, node; unsigned long flags; + unsigned long valid_start, valid_end; struct zone *zone; struct memory_notify arg; @@ -1853,10 +1863,10 @@ static int __ref __offline_pages(unsigned long start_pfn, return -EINVAL; /* This makes hotplug much easier...and readable. we assume this for now. .*/ - if (!test_pages_in_a_zone(start_pfn, end_pfn)) + if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end)) return -EINVAL; - zone = page_zone(pfn_to_page(start_pfn)); + zone = page_zone(pfn_to_page(valid_start)); node = zone_to_nid(zone); nr_pages = end_pfn - start_pfn; -- cgit v1.2.3 From 5abf186a30a89d5b9c18a6bf93a2c192c9fd52f6 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 3 Feb 2017 13:13:29 -0800 Subject: mm, fs: check for fatal signals in do_generic_file_read() do_generic_file_read() can be told to perform a large request from userspace. If the system is under OOM and the reading task is the OOM victim then it has an access to memory reserves and finishing the full request can lead to the full memory depletion which is dangerous. Make sure we rather go with a short read and allow the killed task to terminate. Link: http://lkml.kernel.org/r/20170201092706.9966-3-mhocko@kernel.org Signed-off-by: Michal Hocko Reviewed-by: Christoph Hellwig Cc: Tetsuo Handa Cc: Al Viro Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'mm') diff --git a/mm/filemap.c b/mm/filemap.c index b772a33ef640..3f9afded581b 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1791,6 +1791,11 @@ static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos, cond_resched(); find_page: + if (fatal_signal_pending(current)) { + error = -EINTR; + goto out; + } + page = find_get_page(mapping, index); if (!page) { page_cache_sync_readahead(mapping, -- cgit v1.2.3 From a810007afe239d59c1115fcaa06eb5b480f876e9 Mon Sep 17 00:00:00 2001 From: Sean Rees Date: Wed, 8 Feb 2017 14:30:59 -0800 Subject: mm/slub.c: fix random_seq offset destruction Commit 210e7a43fa90 ("mm: SLUB freelist randomization") broke USB hub initialisation as described in https://bugzilla.kernel.org/show_bug.cgi?id=177551. Bail out early from init_cache_random_seq if s->random_seq is already initialised. This prevents destroying the previously computed random_seq offsets later in the function. If the offsets are destroyed, then shuffle_freelist will truncate page->freelist to just the first object (orphaning the rest). Fixes: 210e7a43fa90 ("mm: SLUB freelist randomization") Link: http://lkml.kernel.org/r/20170207140707.20824-1-sean@erifax.org Signed-off-by: Sean Rees Reported-by: Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Thomas Garnier Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slub.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'mm') diff --git a/mm/slub.c b/mm/slub.c index 7aa6f433f4de..7ec0a965c6a3 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1422,6 +1422,10 @@ static int init_cache_random_seq(struct kmem_cache *s) int err; unsigned long i, count = oo_objects(s->oo); + /* Bailout if already initialised */ + if (s->random_seq) + return 0; + err = cache_random_seq_create(s, count, GFP_KERNEL); if (err) { pr_err("SLUB: Unable to initialize free list for %s\n", -- cgit v1.2.3