From 3b3bf80b994f0c6c35a25ef8965ab956b4bcced5 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Thu, 4 Aug 2016 12:37:17 +0200 Subject: rhashtable-test: Fix max_size parameter description Looks like a simple copy'n'paste error. Fixes: 1aa661f5c3df1 ("rhashtable-test: Measure time to insert, remove & traverse entries") Signed-off-by: Phil Sutter Signed-off-by: David S. Miller --- lib/test_rhashtable.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index 297fdb5e74bd..64e899b63337 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -38,7 +38,7 @@ MODULE_PARM_DESC(runs, "Number of test runs per variant (default: 4)"); static int max_size = 0; module_param(max_size, int, 0); -MODULE_PARM_DESC(runs, "Maximum table size (default: calculated)"); +MODULE_PARM_DESC(max_size, "Maximum table size (default: calculated)"); static bool shrinking = false; module_param(shrinking, bool, 0); -- cgit v1.3-14-g43fede From 4cf0b354d92ee2c642532ee39e330f8f580fd985 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 12 Aug 2016 12:03:52 +0200 Subject: rhashtable: avoid large lock-array allocations Sander reports following splat after netfilter nat bysrc table got converted to rhashtable: swapper/0: page allocation failure: order:3, mode:0x2084020(GFP_ATOMIC|__GFP_COMP) CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.8.0-rc1 [..] [] warn_alloc_failed+0xdd/0x140 [] __alloc_pages_nodemask+0x3e1/0xcf0 [] alloc_pages_current+0x8d/0x110 [] kmalloc_order+0x1f/0x70 [] __kmalloc+0x129/0x140 [] bucket_table_alloc+0xc1/0x1d0 [] rhashtable_insert_rehash+0x5d/0xe0 [] nf_nat_setup_info+0x2ef/0x400 The failure happens when allocating the spinlock array. Even with GFP_KERNEL its unlikely for such a large allocation to succeed. Thomas Graf pointed me at inet_ehash_locks_alloc(), so in addition to adding NOWARN for atomic allocations this also makes the bucket-array sizing more conservative. In commit 095dc8e0c3686 ("tcp: fix/cleanup inet_ehash_locks_alloc()"), Eric Dumazet says: "Budget 2 cache lines per cpu worth of 'spinlocks'". IOW, consider size needed by a single spinlock when determining number of locks per cpu. So with 64 byte per cacheline and 4 byte per spinlock this gives 32 locks per cpu. Resulting size of the lock-array (sizeof(spinlock) == 4): cpus: 1 2 4 8 16 32 64 old: 1k 1k 4k 8k 16k 16k 16k new: 128 256 512 1k 2k 4k 8k 8k allocation should have decent chance of success even with GFP_ATOMIC, and should not fail with GFP_KERNEL. With 72-byte spinlock (LOCKDEP): cpus : 1 2 old: 9k 18k new: ~2k ~4k Reported-by: Sander Eikelenboom Suggested-by: Thomas Graf Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- lib/rhashtable.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 5d845ffd7982..42acd81f10db 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -30,7 +30,7 @@ #define HASH_DEFAULT_SIZE 64UL #define HASH_MIN_SIZE 4U -#define BUCKET_LOCKS_PER_CPU 128UL +#define BUCKET_LOCKS_PER_CPU 32UL static u32 head_hashfn(struct rhashtable *ht, const struct bucket_table *tbl, @@ -70,7 +70,7 @@ static int alloc_bucket_locks(struct rhashtable *ht, struct bucket_table *tbl, unsigned int nr_pcpus = num_possible_cpus(); #endif - nr_pcpus = min_t(unsigned int, nr_pcpus, 32UL); + nr_pcpus = min_t(unsigned int, nr_pcpus, 64UL); size = roundup_pow_of_two(nr_pcpus * ht->p.locks_mul); /* Never allocate more than 0.5 locks per bucket */ @@ -83,6 +83,9 @@ static int alloc_bucket_locks(struct rhashtable *ht, struct bucket_table *tbl, tbl->locks = vmalloc(size * sizeof(spinlock_t)); else #endif + if (gfp != GFP_KERNEL) + gfp |= __GFP_NOWARN | __GFP_NORETRY; + tbl->locks = kmalloc_array(size, sizeof(spinlock_t), gfp); if (!tbl->locks) -- cgit v1.3-14-g43fede From 12311959ecf8a3a64676c01b62ce67a0c5f0fd49 Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Fri, 12 Aug 2016 20:10:44 +0200 Subject: rhashtable: fix shift by 64 when shrinking I got this: ================================================================================ UBSAN: Undefined behaviour in ./include/linux/log2.h:63:13 shift exponent 64 is too large for 64-bit type 'long unsigned int' CPU: 1 PID: 721 Comm: kworker/1:1 Not tainted 4.8.0-rc1+ #87 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014 Workqueue: events rht_deferred_worker 0000000000000000 ffff88011661f8d8 ffffffff82344f50 0000000041b58ab3 ffffffff84f98000 ffffffff82344ea4 ffff88011661f900 ffff88011661f8b0 0000000000000001 ffff88011661f6b8 dffffc0000000000 ffffffff867f7640 Call Trace: [] dump_stack+0xac/0xfc [] ? _atomic_dec_and_lock+0xc4/0xc4 [] ubsan_epilogue+0xd/0x8a [] __ubsan_handle_shift_out_of_bounds+0x255/0x29a [] ? __ubsan_handle_out_of_bounds+0x180/0x180 [] ? nl80211_req_set_reg+0x256/0x2f0 [] ? print_context_stack+0x8a/0x160 [] ? amd_pmu_reset+0x341/0x380 [] rht_deferred_worker+0x1618/0x1790 [] ? rht_deferred_worker+0x1618/0x1790 [] ? rhashtable_jhash2+0x370/0x370 [] ? process_one_work+0x6fd/0x1970 [] process_one_work+0x79f/0x1970 [] ? process_one_work+0x6fd/0x1970 [] ? try_to_grab_pending+0x4c0/0x4c0 [] ? worker_thread+0x1c4/0x1340 [] worker_thread+0x55f/0x1340 [] ? __schedule+0x4df/0x1d40 [] ? process_one_work+0x1970/0x1970 [] ? process_one_work+0x1970/0x1970 [] kthread+0x237/0x390 [] ? __kthread_parkme+0x280/0x280 [] ? _raw_spin_unlock_irq+0x33/0x50 [] ret_from_fork+0x1f/0x40 [] ? __kthread_parkme+0x280/0x280 ================================================================================ roundup_pow_of_two() is undefined when called with an argument of 0, so let's avoid the call and just fall back to ht->p.min_size (which should never be smaller than HASH_MIN_SIZE). Cc: Herbert Xu Signed-off-by: Vegard Nossum Acked-by: Herbert Xu Signed-off-by: David S. Miller --- lib/rhashtable.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'lib') diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 42acd81f10db..5ba520b544d7 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -324,12 +324,14 @@ static int rhashtable_expand(struct rhashtable *ht) static int rhashtable_shrink(struct rhashtable *ht) { struct bucket_table *new_tbl, *old_tbl = rht_dereference(ht->tbl, ht); - unsigned int size; + unsigned int nelems = atomic_read(&ht->nelems); + unsigned int size = 0; int err; ASSERT_RHT_MUTEX(ht); - size = roundup_pow_of_two(atomic_read(&ht->nelems) * 3 / 2); + if (nelems) + size = roundup_pow_of_two(nelems * 3 / 2); if (size < ht->p.min_size) size = ht->p.min_size; -- cgit v1.3-14-g43fede From 9dbeea7f08f3784b152d9fb3b86beb34aad77c72 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 26 Aug 2016 08:51:39 -0700 Subject: rhashtable: fix a memory leak in alloc_bucket_locks() If vmalloc() was successful, do not attempt a kmalloc_array() Fixes: 4cf0b354d92e ("rhashtable: avoid large lock-array allocations") Reported-by: CAI Qian Signed-off-by: Eric Dumazet Cc: Florian Westphal Acked-by: Herbert Xu Tested-by: CAI Qian Signed-off-by: David S. Miller --- lib/rhashtable.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'lib') diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 5ba520b544d7..56054e541a0f 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -77,17 +77,18 @@ static int alloc_bucket_locks(struct rhashtable *ht, struct bucket_table *tbl, size = min_t(unsigned int, size, tbl->size >> 1); if (sizeof(spinlock_t) != 0) { + tbl->locks = NULL; #ifdef CONFIG_NUMA if (size * sizeof(spinlock_t) > PAGE_SIZE && gfp == GFP_KERNEL) tbl->locks = vmalloc(size * sizeof(spinlock_t)); - else #endif if (gfp != GFP_KERNEL) gfp |= __GFP_NOWARN | __GFP_NORETRY; - tbl->locks = kmalloc_array(size, sizeof(spinlock_t), - gfp); + if (!tbl->locks) + tbl->locks = kmalloc_array(size, sizeof(spinlock_t), + gfp); if (!tbl->locks) return -ENOMEM; for (i = 0; i < size; i++) -- cgit v1.3-14-g43fede From 0d025d271e55f3de21f0aaaf54b42d20404d2b23 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 30 Aug 2016 08:04:16 -0500 Subject: mm/usercopy: get rid of CONFIG_DEBUG_STRICT_USER_COPY_CHECKS There are three usercopy warnings which are currently being silenced for gcc 4.6 and newer: 1) "copy_from_user() buffer size is too small" compile warning/error This is a static warning which happens when object size and copy size are both const, and copy size > object size. I didn't see any false positives for this one. So the function warning attribute seems to be working fine here. Note this scenario is always a bug and so I think it should be changed to *always* be an error, regardless of CONFIG_DEBUG_STRICT_USER_COPY_CHECKS. 2) "copy_from_user() buffer size is not provably correct" compile warning This is another static warning which happens when I enable __compiletime_object_size() for new compilers (and CONFIG_DEBUG_STRICT_USER_COPY_CHECKS). It happens when object size is const, but copy size is *not*. In this case there's no way to compare the two at build time, so it gives the warning. (Note the warning is a byproduct of the fact that gcc has no way of knowing whether the overflow function will be called, so the call isn't dead code and the warning attribute is activated.) So this warning seems to only indicate "this is an unusual pattern, maybe you should check it out" rather than "this is a bug". I get 102(!) of these warnings with allyesconfig and the __compiletime_object_size() gcc check removed. I don't know if there are any real bugs hiding in there, but from looking at a small sample, I didn't see any. According to Kees, it does sometimes find real bugs. But the false positive rate seems high. 3) "Buffer overflow detected" runtime warning This is a runtime warning where object size is const, and copy size > object size. All three warnings (both static and runtime) were completely disabled for gcc 4.6 with the following commit: 2fb0815c9ee6 ("gcc4: disable __compiletime_object_size for GCC 4.6+") That commit mistakenly assumed that the false positives were caused by a gcc bug in __compiletime_object_size(). But in fact, __compiletime_object_size() seems to be working fine. The false positives were instead triggered by #2 above. (Though I don't have an explanation for why the warnings supposedly only started showing up in gcc 4.6.) So remove warning #2 to get rid of all the false positives, and re-enable warnings #1 and #3 by reverting the above commit. Furthermore, since #1 is a real bug which is detected at compile time, upgrade it to always be an error. Having done all that, CONFIG_DEBUG_STRICT_USER_COPY_CHECKS is no longer needed. Signed-off-by: Josh Poimboeuf Cc: Kees Cook Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H . Peter Anvin" Cc: Andy Lutomirski Cc: Steven Rostedt Cc: Brian Gerst Cc: Peter Zijlstra Cc: Frederic Weisbecker Cc: Byungchul Park Cc: Nilay Vaish Signed-off-by: Linus Torvalds --- arch/parisc/Kconfig | 1 - arch/parisc/configs/c8000_defconfig | 1 - arch/parisc/configs/generic-64bit_defconfig | 1 - arch/parisc/include/asm/uaccess.h | 22 ++++----- arch/s390/Kconfig | 1 - arch/s390/configs/default_defconfig | 1 - arch/s390/configs/gcov_defconfig | 1 - arch/s390/configs/performance_defconfig | 1 - arch/s390/defconfig | 1 - arch/s390/include/asm/uaccess.h | 19 +++++--- arch/tile/Kconfig | 1 - arch/tile/include/asm/uaccess.h | 22 +++++---- arch/x86/Kconfig | 1 - arch/x86/include/asm/uaccess.h | 69 ++++------------------------- include/asm-generic/uaccess.h | 1 + include/linux/compiler-gcc.h | 2 +- lib/Kconfig.debug | 18 -------- lib/Makefile | 1 - lib/usercopy.c | 9 ---- 19 files changed, 45 insertions(+), 128 deletions(-) delete mode 100644 lib/usercopy.c (limited to 'lib') diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index cd8778103165..af12c2db9bb8 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -1,6 +1,5 @@ config PARISC def_bool y - select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_MIGHT_HAVE_PC_PARPORT select HAVE_IDE select HAVE_OPROFILE diff --git a/arch/parisc/configs/c8000_defconfig b/arch/parisc/configs/c8000_defconfig index 1a8f6f95689e..f6a4c016304b 100644 --- a/arch/parisc/configs/c8000_defconfig +++ b/arch/parisc/configs/c8000_defconfig @@ -245,7 +245,6 @@ CONFIG_DEBUG_RT_MUTEXES=y CONFIG_PROVE_RCU_DELAY=y CONFIG_DEBUG_BLOCK_EXT_DEVT=y CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_KEYS=y # CONFIG_CRYPTO_HW is not set CONFIG_FONTS=y diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig index 7e0792658952..c564e6e1fa23 100644 --- a/arch/parisc/configs/generic-64bit_defconfig +++ b/arch/parisc/configs/generic-64bit_defconfig @@ -291,7 +291,6 @@ CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y CONFIG_BOOTPARAM_HUNG_TASK_PANIC=y # CONFIG_SCHED_DEBUG is not set CONFIG_TIMER_STATS=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_PCBC=m diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 0f59fd9ca205..e9150487e20d 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -208,13 +208,13 @@ unsigned long copy_in_user(void __user *dst, const void __user *src, unsigned lo #define __copy_to_user_inatomic __copy_to_user #define __copy_from_user_inatomic __copy_from_user -extern void copy_from_user_overflow(void) -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS - __compiletime_error("copy_from_user() buffer size is not provably correct") -#else - __compiletime_warning("copy_from_user() buffer size is not provably correct") -#endif -; +extern void __compiletime_error("usercopy buffer size is too small") +__bad_copy_user(void); + +static inline void copy_user_overflow(int size, unsigned long count) +{ + WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); +} static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, @@ -223,10 +223,12 @@ static inline unsigned long __must_check copy_from_user(void *to, int sz = __compiletime_object_size(to); int ret = -EFAULT; - if (likely(sz == -1 || !__builtin_constant_p(n) || sz >= n)) + if (likely(sz == -1 || sz >= n)) ret = __copy_from_user(to, from, n); - else - copy_from_user_overflow(); + else if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); + else + __bad_copy_user(); return ret; } diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index e751fe25d6ab..c109f073d454 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -68,7 +68,6 @@ config DEBUG_RODATA config S390 def_bool y select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_GCOV_PROFILE_ALL diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig index 26e0c7f08814..412b1bd21029 100644 --- a/arch/s390/configs/default_defconfig +++ b/arch/s390/configs/default_defconfig @@ -602,7 +602,6 @@ CONFIG_FAIL_FUTEX=y CONFIG_FAULT_INJECTION_DEBUG_FS=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_IRQSOFF_TRACER=y CONFIG_PREEMPT_TRACER=y CONFIG_SCHED_TRACER=y diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig index 24879dab47bc..bec279eb4b93 100644 --- a/arch/s390/configs/gcov_defconfig +++ b/arch/s390/configs/gcov_defconfig @@ -552,7 +552,6 @@ CONFIG_NOTIFIER_ERROR_INJECTION=m CONFIG_CPU_NOTIFIER_ERROR_INJECT=m CONFIG_PM_NOTIFIER_ERROR_INJECT=m CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_BLK_DEV_IO_TRACE=y # CONFIG_KPROBE_EVENT is not set CONFIG_TRACE_ENUM_MAP_FILE=y diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig index a5c1e5f2a0ca..1751446a5bbb 100644 --- a/arch/s390/configs/performance_defconfig +++ b/arch/s390/configs/performance_defconfig @@ -549,7 +549,6 @@ CONFIG_TIMER_STATS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_STACK_TRACER=y diff --git a/arch/s390/defconfig b/arch/s390/defconfig index 73610f2e3b4f..2d40ef0a6295 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -172,7 +172,6 @@ CONFIG_DEBUG_NOTIFIERS=y CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_RCU_TRACE=y CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index 9b49cf1daa8f..95aefdba4be2 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -311,6 +311,14 @@ int __get_user_bad(void) __attribute__((noreturn)); #define __put_user_unaligned __put_user #define __get_user_unaligned __get_user +extern void __compiletime_error("usercopy buffer size is too small") +__bad_copy_user(void); + +static inline void copy_user_overflow(int size, unsigned long count) +{ + WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); +} + /** * copy_to_user: - Copy a block of data into user space. * @to: Destination address, in user space. @@ -332,12 +340,6 @@ copy_to_user(void __user *to, const void *from, unsigned long n) return __copy_to_user(to, from, n); } -void copy_from_user_overflow(void) -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS -__compiletime_warning("copy_from_user() buffer size is not provably correct") -#endif -; - /** * copy_from_user: - Copy a block of data from user space. * @to: Destination address, in kernel space. @@ -362,7 +364,10 @@ copy_from_user(void *to, const void __user *from, unsigned long n) might_fault(); if (unlikely(sz != -1 && sz < n)) { - copy_from_user_overflow(); + if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); + else + __bad_copy_user(); return n; } return __copy_from_user(to, from, n); diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 4820a02838ac..78da75b670bc 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -4,7 +4,6 @@ config TILE def_bool y select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_WANT_FRAME_POINTERS diff --git a/arch/tile/include/asm/uaccess.h b/arch/tile/include/asm/uaccess.h index 0a9c4265763b..a77369e91e54 100644 --- a/arch/tile/include/asm/uaccess.h +++ b/arch/tile/include/asm/uaccess.h @@ -416,14 +416,13 @@ _copy_from_user(void *to, const void __user *from, unsigned long n) return n; } -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS -/* - * There are still unprovable places in the generic code as of 2.6.34, so this - * option is not really compatible with -Werror, which is more useful in - * general. - */ -extern void copy_from_user_overflow(void) - __compiletime_warning("copy_from_user() size is not provably correct"); +extern void __compiletime_error("usercopy buffer size is too small") +__bad_copy_user(void); + +static inline void copy_user_overflow(int size, unsigned long count) +{ + WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); +} static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, @@ -433,14 +432,13 @@ static inline unsigned long __must_check copy_from_user(void *to, if (likely(sz == -1 || sz >= n)) n = _copy_from_user(to, from, n); + else if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); else - copy_from_user_overflow(); + __bad_copy_user(); return n; } -#else -#define copy_from_user _copy_from_user -#endif #ifdef __tilegx__ /** diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c580d8c33562..2a1f0ce7c59a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -24,7 +24,6 @@ config X86 select ARCH_DISCARD_MEMBLOCK select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FAST_MULTIPLIER diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index a0ae610b9280..c3f291195294 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -697,43 +697,14 @@ unsigned long __must_check _copy_from_user(void *to, const void __user *from, unsigned long __must_check _copy_to_user(void __user *to, const void *from, unsigned n); -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS -# define copy_user_diag __compiletime_error -#else -# define copy_user_diag __compiletime_warning -#endif - -extern void copy_user_diag("copy_from_user() buffer size is too small") -copy_from_user_overflow(void); -extern void copy_user_diag("copy_to_user() buffer size is too small") -copy_to_user_overflow(void) __asm__("copy_from_user_overflow"); - -#undef copy_user_diag - -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS - -extern void -__compiletime_warning("copy_from_user() buffer size is not provably correct") -__copy_from_user_overflow(void) __asm__("copy_from_user_overflow"); -#define __copy_from_user_overflow(size, count) __copy_from_user_overflow() - -extern void -__compiletime_warning("copy_to_user() buffer size is not provably correct") -__copy_to_user_overflow(void) __asm__("copy_from_user_overflow"); -#define __copy_to_user_overflow(size, count) __copy_to_user_overflow() - -#else +extern void __compiletime_error("usercopy buffer size is too small") +__bad_copy_user(void); -static inline void -__copy_from_user_overflow(int size, unsigned long count) +static inline void copy_user_overflow(int size, unsigned long count) { WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); } -#define __copy_to_user_overflow __copy_from_user_overflow - -#endif - static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { @@ -743,31 +714,13 @@ copy_from_user(void *to, const void __user *from, unsigned long n) kasan_check_write(to, n); - /* - * While we would like to have the compiler do the checking for us - * even in the non-constant size case, any false positives there are - * a problem (especially when DEBUG_STRICT_USER_COPY_CHECKS, but even - * without - the [hopefully] dangerous looking nature of the warning - * would make people go look at the respecitive call sites over and - * over again just to find that there's no problem). - * - * And there are cases where it's just not realistic for the compiler - * to prove the count to be in range. For example when multiple call - * sites of a helper function - perhaps in different source files - - * all doing proper range checking, yet the helper function not doing - * so again. - * - * Therefore limit the compile time checking to the constant size - * case, and do only runtime checking for non-constant sizes. - */ - if (likely(sz < 0 || sz >= n)) { check_object_size(to, n, false); n = _copy_from_user(to, from, n); - } else if (__builtin_constant_p(n)) - copy_from_user_overflow(); + } else if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); else - __copy_from_user_overflow(sz, n); + __bad_copy_user(); return n; } @@ -781,21 +734,17 @@ copy_to_user(void __user *to, const void *from, unsigned long n) might_fault(); - /* See the comment in copy_from_user() above. */ if (likely(sz < 0 || sz >= n)) { check_object_size(from, n, true); n = _copy_to_user(to, from, n); - } else if (__builtin_constant_p(n)) - copy_to_user_overflow(); + } else if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); else - __copy_to_user_overflow(sz, n); + __bad_copy_user(); return n; } -#undef __copy_from_user_overflow -#undef __copy_to_user_overflow - /* * We rely on the nested NMI work to allow atomic faults from the NMI path; the * nested NMI paths are careful to preserve CR2. diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h index 1bfa602958f2..5dea1fb6979c 100644 --- a/include/asm-generic/uaccess.h +++ b/include/asm-generic/uaccess.h @@ -72,6 +72,7 @@ struct exception_table_entry /* Returns 0 if exception not found and fixup otherwise. */ extern unsigned long search_exception_table(unsigned long); + /* * architectures with an MMU should override these two */ diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 8dbc8929a6a0..573c5a18908f 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -158,7 +158,7 @@ #define __compiler_offsetof(a, b) \ __builtin_offsetof(a, b) -#if GCC_VERSION >= 40100 && GCC_VERSION < 40600 +#if GCC_VERSION >= 40100 # define __compiletime_object_size(obj) __builtin_object_size(obj, 0) #endif diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2307d7c89dac..2e2cca509231 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1686,24 +1686,6 @@ config LATENCYTOP Enable this option if you want to use the LatencyTOP tool to find out which userspace is blocking on what kernel operations. -config ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS - bool - -config DEBUG_STRICT_USER_COPY_CHECKS - bool "Strict user copy size checks" - depends on ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS - depends on DEBUG_KERNEL && !TRACE_BRANCH_PROFILING - help - Enabling this option turns a certain set of sanity checks for user - copy operations into compile time failures. - - The copy_from_user() etc checks are there to help test if there - are sufficient security checks on the length argument of - the copy operation, by having gcc prove that the argument is - within bounds. - - If unsure, say N. - source kernel/trace/Kconfig menu "Runtime Testing" diff --git a/lib/Makefile b/lib/Makefile index cfa68eb269e4..5dc77a8ec297 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -24,7 +24,6 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ earlycpio.o seq_buf.o nmi_backtrace.o nodemask.o -obj-$(CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS) += usercopy.o lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o lib-$(CONFIG_HAS_DMA) += dma-noop.o diff --git a/lib/usercopy.c b/lib/usercopy.c deleted file mode 100644 index 4f5b1ddbcd25..000000000000 --- a/lib/usercopy.c +++ /dev/null @@ -1,9 +0,0 @@ -#include -#include -#include - -void copy_from_user_overflow(void) -{ - WARN(1, "Buffer overflow detected!\n"); -} -EXPORT_SYMBOL(copy_from_user_overflow); -- cgit v1.3-14-g43fede From ed76b7a131f41c91b0c725d472f9b969d75ce888 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 1 Sep 2016 16:14:50 -0700 Subject: lib/test_hash.c: fix warning in two-dimensional array init lib/test_hash.c: In function 'test_hash_init': lib/test_hash.c:146:2: warning: missing braces around initializer [-Wmissing-braces] Fixes: 468a9428521e7d00 (": Add support for architecture-specific functions") Link: http://lkml.kernel.org/r/20160829214952.1334674-3-arnd@arndb.de Signed-off-by: Geert Uytterhoeven Signed-off-by: Arnd Bergmann Acked-by: George Spelvin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_hash.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/test_hash.c b/lib/test_hash.c index 66c5fc8351e8..81702ee4c41c 100644 --- a/lib/test_hash.c +++ b/lib/test_hash.c @@ -143,7 +143,7 @@ static int __init test_hash_init(void) { char buf[SIZE+1]; - u32 string_or = 0, hash_or[2][33] = { 0 }; + u32 string_or = 0, hash_or[2][33] = { { 0, } }; unsigned tests = 0; unsigned long long h64 = 0; int i, j; -- cgit v1.3-14-g43fede From e6173ba42bbdba05fd4f3021c0beda0506271507 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 1 Sep 2016 16:14:53 -0700 Subject: lib/test_hash.c: fix warning in preprocessor symbol evaluation Some versions of gcc don't like tests for the value of an undefined preprocessor symbol, even in the #else branch of an #ifndef: lib/test_hash.c:224:7: warning: "HAVE_ARCH__HASH_32" is not defined [-Wundef] #elif HAVE_ARCH__HASH_32 != 1 ^ lib/test_hash.c:229:7: warning: "HAVE_ARCH_HASH_32" is not defined [-Wundef] #elif HAVE_ARCH_HASH_32 != 1 ^ lib/test_hash.c:234:7: warning: "HAVE_ARCH_HASH_64" is not defined [-Wundef] #elif HAVE_ARCH_HASH_64 != 1 ^ Seen with gcc 4.9, not seen with 4.1.2. Change the logic to only check the value inside an #ifdef to fix this. Fixes: 468a9428521e7d00 (": Add support for architecture-specific functions") Link: http://lkml.kernel.org/r/20160829214952.1334674-4-arnd@arndb.de Signed-off-by: Geert Uytterhoeven Signed-off-by: Arnd Bergmann Acked-by: George Spelvin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_hash.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-) (limited to 'lib') diff --git a/lib/test_hash.c b/lib/test_hash.c index 81702ee4c41c..cac20c5fb304 100644 --- a/lib/test_hash.c +++ b/lib/test_hash.c @@ -219,21 +219,27 @@ test_hash_init(void) } /* Issue notices about skipped tests. */ -#ifndef HAVE_ARCH__HASH_32 - pr_info("__hash_32() has no arch implementation to test."); -#elif HAVE_ARCH__HASH_32 != 1 +#ifdef HAVE_ARCH__HASH_32 +#if HAVE_ARCH__HASH_32 != 1 pr_info("__hash_32() is arch-specific; not compared to generic."); #endif -#ifndef HAVE_ARCH_HASH_32 - pr_info("hash_32() has no arch implementation to test."); -#elif HAVE_ARCH_HASH_32 != 1 +#else + pr_info("__hash_32() has no arch implementation to test."); +#endif +#ifdef HAVE_ARCH_HASH_32 +#if HAVE_ARCH_HASH_32 != 1 pr_info("hash_32() is arch-specific; not compared to generic."); #endif -#ifndef HAVE_ARCH_HASH_64 - pr_info("hash_64() has no arch implementation to test."); -#elif HAVE_ARCH_HASH_64 != 1 +#else + pr_info("hash_32() has no arch implementation to test."); +#endif +#ifdef HAVE_ARCH_HASH_64 +#if HAVE_ARCH_HASH_64 != 1 pr_info("hash_64() is arch-specific; not compared to generic."); #endif +#else + pr_info("hash_64() has no arch implementation to test."); +#endif pr_notice("%u tests passed.", tests); -- cgit v1.3-14-g43fede From d4690f1e1cdabb4d61207b6787b1605a0dc0aeab Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 16 Sep 2016 00:11:45 +0100 Subject: fix iov_iter_fault_in_readable() ... by turning it into what used to be multipages counterpart Cc: stable@vger.kernel.org Signed-off-by: Al Viro Signed-off-by: Linus Torvalds --- include/linux/uio.h | 2 +- lib/iov_iter.c | 24 ++---------------------- 2 files changed, 3 insertions(+), 23 deletions(-) (limited to 'lib') diff --git a/include/linux/uio.h b/include/linux/uio.h index 1b5d1cd796e2..75b4aaf31a9d 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -76,7 +76,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes); void iov_iter_advance(struct iov_iter *i, size_t bytes); int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes); -int iov_iter_fault_in_multipages_readable(struct iov_iter *i, size_t bytes); +#define iov_iter_fault_in_multipages_readable iov_iter_fault_in_readable size_t iov_iter_single_seg_count(const struct iov_iter *i); size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 9e8c7386b3a0..7e3138cfc8c9 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -290,26 +290,6 @@ done: return wanted - bytes; } -/* - * Fault in the first iovec of the given iov_iter, to a maximum length - * of bytes. Returns 0 on success, or non-zero if the memory could not be - * accessed (ie. because it is an invalid address). - * - * writev-intensive code may want this to prefault several iovecs -- that - * would be possible (callers must not rely on the fact that _only_ the - * first iovec will be faulted with the current implementation). - */ -int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) -{ - if (!(i->type & (ITER_BVEC|ITER_KVEC))) { - char __user *buf = i->iov->iov_base + i->iov_offset; - bytes = min(bytes, i->iov->iov_len - i->iov_offset); - return fault_in_pages_readable(buf, bytes); - } - return 0; -} -EXPORT_SYMBOL(iov_iter_fault_in_readable); - /* * Fault in one or more iovecs of the given iov_iter, to a maximum length of * bytes. For each iovec, fault in each page that constitutes the iovec. @@ -317,7 +297,7 @@ EXPORT_SYMBOL(iov_iter_fault_in_readable); * Return 0 on success, or non-zero if the memory could not be accessed (i.e. * because it is an invalid address). */ -int iov_iter_fault_in_multipages_readable(struct iov_iter *i, size_t bytes) +int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) { size_t skip = i->iov_offset; const struct iovec *iov; @@ -334,7 +314,7 @@ int iov_iter_fault_in_multipages_readable(struct iov_iter *i, size_t bytes) } return 0; } -EXPORT_SYMBOL(iov_iter_fault_in_multipages_readable); +EXPORT_SYMBOL(iov_iter_fault_in_readable); void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov, unsigned long nr_segs, -- cgit v1.3-14-g43fede From 96b03ab86d843524ec4aed7fe0ceef412c684c68 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Thu, 22 Sep 2016 16:55:13 -0400 Subject: locking/hung_task: Fix typo in CONFIG_DETECT_HUNG_TASK help text Fix the indefinitiley -> indefinitely typo in Kconfig.debug. Signed-off-by: Vivien Didelot Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20160922205513.17821-1-vivien.didelot@savoirfairelinux.com Signed-off-by: Ingo Molnar --- lib/Kconfig.debug | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2e2cca509231..cab7405f48d2 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -821,7 +821,7 @@ config DETECT_HUNG_TASK help Say Y here to enable the kernel to detect "hung tasks", which are bugs that cause the task to be stuck in - uninterruptible "D" state indefinitiley. + uninterruptible "D" state indefinitely. When a hung task is detected, the kernel will print the current stack trace (which you should report), but the -- cgit v1.3-14-g43fede From 8d2c0d36d6826ddc3114801c599619d3f2932f0a Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 25 Sep 2016 13:32:46 -0700 Subject: radix tree: fix sibling entry handling in radix_tree_descend() The fixes to the radix tree test suite show that the multi-order case is broken. The basic reason is that the radix tree code uses tagged pointers with the "internal" bit in the low bits, and calculating the pointer indices was supposed to mask off those bits. But gcc will notice that we then use the index to re-create the pointer, and will avoid doing the arithmetic and use the tagged pointer directly. This cleans the code up, using the existing is_sibling_entry() helper to validate the sibling pointer range (instead of open-coding it), and using entry_to_node() to mask off the low tag bit from the pointer. And once you do that, you might as well just use the now cleaned-up pointer directly. [ Side note: the multi-order code isn't actually ever used in the kernel right now, and the only reason I didn't just delete all that code is that Kirill Shutemov piped up and said: "Well, my ext4-with-huge-pages patchset[1] uses multi-order entries. It also converts shmem-with-huge-pages and hugetlb to them. I'm okay with converting it to other mechanism, but I need something. (I looked into Konstantin's RFC patchset[2]. It looks okay, but I don't feel myself qualified to review it as I don't know much about radix-tree internals.)" [1] http://lkml.kernel.org/r/20160915115523.29737-1-kirill.shutemov@linux.intel.com [2] http://lkml.kernel.org/r/147230727479.9957.1087787722571077339.stgit@zurg ] Reported-by: Matthew Wilcox Cc: Andrew Morton Cc: Ross Zwisler Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Konstantin Khlebnikov Cc: Cedric Blancher Signed-off-by: Linus Torvalds --- lib/radix-tree.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'lib') diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 1b7bf7314141..91f0727e3cad 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -105,10 +105,10 @@ static unsigned int radix_tree_descend(struct radix_tree_node *parent, #ifdef CONFIG_RADIX_TREE_MULTIORDER if (radix_tree_is_internal_node(entry)) { - unsigned long siboff = get_slot_offset(parent, entry); - if (siboff < RADIX_TREE_MAP_SIZE) { - offset = siboff; - entry = rcu_dereference_raw(parent->slots[offset]); + if (is_sibling_entry(parent, entry)) { + void **sibentry = (void **) entry_to_node(entry); + offset = get_slot_offset(parent, sibentry); + entry = rcu_dereference_raw(*sibentry); } } #endif -- cgit v1.3-14-g43fede