From ed5bd7dc88edf4a4a9c67130742b1b59aa017a5f Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Wed, 8 Feb 2017 14:30:50 -0800 Subject: [PATCH 1/4] kernel/ucount.c: mark user_header with kmemleak_ignore() The user_header gets caught by kmemleak with the following splat as missing a free: unreferenced object 0xffff99667a733d80 (size 96): comm "swapper/0", pid 1, jiffies 4294892317 (age 62191.468s) hex dump (first 32 bytes): a0 b6 92 b4 ff ff ff ff 00 00 00 00 01 00 00 00 ................ 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: kmemleak_alloc+0x4a/0xa0 __kmalloc+0x144/0x260 __register_sysctl_table+0x54/0x5e0 register_sysctl+0x1b/0x20 user_namespace_sysctl_init+0x17/0x34 do_one_initcall+0x52/0x1a0 kernel_init_freeable+0x173/0x200 kernel_init+0xe/0x100 ret_from_fork+0x2c/0x40 The BUG_ON()s are intended to crash so no need to clean up after ourselves on error there. This is also a kernel/ subsys_init() we don't need a respective exit call here as this is never modular, so just white list it. Link: http://lkml.kernel.org/r/20170203211404.31458-1-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez Cc: Eric W. Biederman Cc: Kees Cook Cc: Nikolay Borisov Cc: Serge Hallyn Cc: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/ucount.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/kernel/ucount.c b/kernel/ucount.c index 4bbd38ec3788..95c6336fc2b3 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -227,11 +227,10 @@ static __init int user_namespace_sysctl_init(void) * properly. */ user_header = register_sysctl("user", empty); + kmemleak_ignore(user_header); BUG_ON(!user_header); BUG_ON(!setup_userns_sysctls(&init_user_ns)); #endif return 0; } subsys_initcall(user_namespace_sysctl_init); - - From 0911d0041c22922228ca52a977d7b0b0159fee4b Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 8 Feb 2017 14:30:53 -0800 Subject: [PATCH 2/4] mm: avoid returning VM_FAULT_RETRY from ->page_mkwrite handlers Some ->page_mkwrite handlers may return VM_FAULT_RETRY as its return code (GFS2 or Lustre can definitely do this). However VM_FAULT_RETRY from ->page_mkwrite is completely unhandled by the mm code and results in locking and writeably mapping the page which definitely is not what the caller wanted. Fix Lustre and block_page_mkwrite_ret() used by other filesystems (notably GFS2) to return VM_FAULT_NOPAGE instead which results in bailing out from the fault code, the CPU then retries the access, and we fault again effectively doing what the handler wanted. Link: http://lkml.kernel.org/r/20170203150729.15863-1-jack@suse.cz Signed-off-by: Jan Kara Reported-by: Al Viro Reviewed-by: Jinshan Xiong Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/staging/lustre/lustre/llite/llite_mmap.c | 4 +--- include/linux/buffer_head.h | 4 +--- 2 files changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/staging/lustre/lustre/llite/llite_mmap.c b/drivers/staging/lustre/lustre/llite/llite_mmap.c index ee01f20d8b11..9afa6bec3e6f 100644 --- a/drivers/staging/lustre/lustre/llite/llite_mmap.c +++ b/drivers/staging/lustre/lustre/llite/llite_mmap.c @@ -390,15 +390,13 @@ static int ll_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) result = VM_FAULT_LOCKED; break; case -ENODATA: + case -EAGAIN: case -EFAULT: result = VM_FAULT_NOPAGE; break; case -ENOMEM: result = VM_FAULT_OOM; break; - case -EAGAIN: - result = VM_FAULT_RETRY; - break; default: result = VM_FAULT_SIGBUS; break; diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index d67ab83823ad..79591c3660cc 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -243,12 +243,10 @@ static inline int block_page_mkwrite_return(int err) { if (err == 0) return VM_FAULT_LOCKED; - if (err == -EFAULT) + if (err == -EFAULT || err == -EAGAIN) return VM_FAULT_NOPAGE; if (err == -ENOMEM) return VM_FAULT_OOM; - if (err == -EAGAIN) - return VM_FAULT_RETRY; /* -ENOSPC, -EDQUOT, -EIO ... */ return VM_FAULT_SIGBUS; } From 4d59b6ccf000862beed6fc0765d3209f98a8d8a2 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 8 Feb 2017 14:30:56 -0800 Subject: [PATCH 3/4] cpumask: use nr_cpumask_bits for parsing functions Commit 513e3d2d11c9 ("cpumask: always use nr_cpu_ids in formatting and parsing functions") converted both cpumask printing and parsing functions to use nr_cpu_ids instead of nr_cpumask_bits. While this was okay for the printing functions as it just picked one of the two output formats that we were alternating between depending on a kernel config, doing the same for parsing wasn't okay. nr_cpumask_bits can be either nr_cpu_ids or NR_CPUS. We can always use nr_cpu_ids but that is a variable while NR_CPUS is a constant, so it can be more efficient to use NR_CPUS when we can get away with it. Converting the printing functions to nr_cpu_ids makes sense because it affects how the masks get presented to userspace and doesn't break anything; however, using nr_cpu_ids for parsing functions can incorrectly leave the higher bits uninitialized while reading in these masks from userland. As all testing and comparison functions use nr_cpumask_bits which can be larger than nr_cpu_ids, the parsed cpumasks can erroneously yield false negative results. This made the taskstats interface incorrectly return -EINVAL even when the inputs were correct. Fix it by restoring the parse functions to use nr_cpumask_bits instead of nr_cpu_ids. Link: http://lkml.kernel.org/r/20170206182442.GB31078@htj.duckdns.org Fixes: 513e3d2d11c9 ("cpumask: always use nr_cpu_ids in formatting and parsing functions") Signed-off-by: Tejun Heo Reported-by: Martin Steigerwald Debugged-by: Ben Hutchings Cc: [4.0+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpumask.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index c717f5ea88cb..b3d2c1a89ac4 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -560,7 +560,7 @@ static inline void cpumask_copy(struct cpumask *dstp, static inline int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp) { - return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpu_ids); + return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** @@ -575,7 +575,7 @@ static inline int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parselist_user(buf, len, cpumask_bits(dstp), - nr_cpu_ids); + nr_cpumask_bits); } /** @@ -590,7 +590,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp) char *nl = strchr(buf, '\n'); unsigned int len = nl ? (unsigned int)(nl - buf) : strlen(buf); - return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpu_ids); + return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** @@ -602,7 +602,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp) */ static inline int cpulist_parse(const char *buf, struct cpumask *dstp) { - return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpu_ids); + return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits); } /** From a810007afe239d59c1115fcaa06eb5b480f876e9 Mon Sep 17 00:00:00 2001 From: Sean Rees Date: Wed, 8 Feb 2017 14:30:59 -0800 Subject: [PATCH 4/4] 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(+) 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",