From 04f08eb44b5011493d77b602fdec29ff0f5c6cd5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Sep 2021 17:00:29 -0700 Subject: net/af_unix: fix a data-race in unix_dgram_poll syzbot reported another data-race in af_unix [1] Lets change __skb_insert() to use WRITE_ONCE() when changing skb head qlen. Also, change unix_dgram_poll() to use lockless version of unix_recvq_full() It is verry possible we can switch all/most unix_recvq_full() to the lockless version, this will be done in a future kernel version. [1] HEAD commit: 8596e589b787732c8346f0482919e83cc9362db1 BUG: KCSAN: data-race in skb_queue_tail / unix_dgram_poll write to 0xffff88814eeb24e0 of 4 bytes by task 25815 on cpu 0: __skb_insert include/linux/skbuff.h:1938 [inline] __skb_queue_before include/linux/skbuff.h:2043 [inline] __skb_queue_tail include/linux/skbuff.h:2076 [inline] skb_queue_tail+0x80/0xa0 net/core/skbuff.c:3264 unix_dgram_sendmsg+0xff2/0x1600 net/unix/af_unix.c:1850 sock_sendmsg_nosec net/socket.c:703 [inline] sock_sendmsg net/socket.c:723 [inline] ____sys_sendmsg+0x360/0x4d0 net/socket.c:2392 ___sys_sendmsg net/socket.c:2446 [inline] __sys_sendmmsg+0x315/0x4b0 net/socket.c:2532 __do_sys_sendmmsg net/socket.c:2561 [inline] __se_sys_sendmmsg net/socket.c:2558 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2558 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff88814eeb24e0 of 4 bytes by task 25834 on cpu 1: skb_queue_len include/linux/skbuff.h:1869 [inline] unix_recvq_full net/unix/af_unix.c:194 [inline] unix_dgram_poll+0x2bc/0x3e0 net/unix/af_unix.c:2777 sock_poll+0x23e/0x260 net/socket.c:1288 vfs_poll include/linux/poll.h:90 [inline] ep_item_poll fs/eventpoll.c:846 [inline] ep_send_events fs/eventpoll.c:1683 [inline] ep_poll fs/eventpoll.c:1798 [inline] do_epoll_wait+0x6ad/0xf00 fs/eventpoll.c:2226 __do_sys_epoll_wait fs/eventpoll.c:2238 [inline] __se_sys_epoll_wait fs/eventpoll.c:2233 [inline] __x64_sys_epoll_wait+0xf6/0x120 fs/eventpoll.c:2233 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x0000001b -> 0x00000001 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 25834 Comm: syz-executor.1 Tainted: G W 5.14.0-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 86b18aaa2b5b ("skbuff: fix a data race in skb_queue_len()") Cc: Qian Cai Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6bdb0db3e825..841e2f0f5240 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1940,7 +1940,7 @@ static inline void __skb_insert(struct sk_buff *newsk, WRITE_ONCE(newsk->prev, prev); WRITE_ONCE(next->prev, newsk); WRITE_ONCE(prev->next, newsk); - list->qlen++; + WRITE_ONCE(list->qlen, list->qlen + 1); } static inline void __skb_queue_splice(const struct sk_buff_head *list, -- cgit From 2f1aaf3ea666b737ad717b3d88667225aca23149 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 9 Sep 2021 08:49:59 -0700 Subject: bpf, mm: Fix lockdep warning triggered by stack_map_get_build_id_offset() Currently the bpf selftest "get_stack_raw_tp" triggered the warning: [ 1411.304463] WARNING: CPU: 3 PID: 140 at include/linux/mmap_lock.h:164 find_vma+0x47/0xa0 [ 1411.304469] Modules linked in: bpf_testmod(O) [last unloaded: bpf_testmod] [ 1411.304476] CPU: 3 PID: 140 Comm: systemd-journal Tainted: G W O 5.14.0+ #53 [ 1411.304479] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [ 1411.304481] RIP: 0010:find_vma+0x47/0xa0 [ 1411.304484] Code: de 48 89 ef e8 ba f5 fe ff 48 85 c0 74 2e 48 83 c4 08 5b 5d c3 48 8d bf 28 01 00 00 be ff ff ff ff e8 2d 9f d8 00 85 c0 75 d4 <0f> 0b 48 89 de 48 8 [ 1411.304487] RSP: 0018:ffffabd440403db8 EFLAGS: 00010246 [ 1411.304490] RAX: 0000000000000000 RBX: 00007f00ad80a0e0 RCX: 0000000000000000 [ 1411.304492] RDX: 0000000000000001 RSI: ffffffff9776b144 RDI: ffffffff977e1b0e [ 1411.304494] RBP: ffff9cf5c2f50000 R08: ffff9cf5c3eb25d8 R09: 00000000fffffffe [ 1411.304496] R10: 0000000000000001 R11: 00000000ef974e19 R12: ffff9cf5c39ae0e0 [ 1411.304498] R13: 0000000000000000 R14: 0000000000000000 R15: ffff9cf5c39ae0e0 [ 1411.304501] FS: 00007f00ae754780(0000) GS:ffff9cf5fba00000(0000) knlGS:0000000000000000 [ 1411.304504] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1411.304506] CR2: 000000003e34343c CR3: 0000000103a98005 CR4: 0000000000370ee0 [ 1411.304508] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1411.304510] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 1411.304512] Call Trace: [ 1411.304517] stack_map_get_build_id_offset+0x17c/0x260 [ 1411.304528] __bpf_get_stack+0x18f/0x230 [ 1411.304541] bpf_get_stack_raw_tp+0x5a/0x70 [ 1411.305752] RAX: 0000000000000000 RBX: 5541f689495641d7 RCX: 0000000000000000 [ 1411.305756] RDX: 0000000000000001 RSI: ffffffff9776b144 RDI: ffffffff977e1b0e [ 1411.305758] RBP: ffff9cf5c02b2f40 R08: ffff9cf5ca7606c0 R09: ffffcbd43ee02c04 [ 1411.306978] bpf_prog_32007c34f7726d29_bpf_prog1+0xaf/0xd9c [ 1411.307861] R10: 0000000000000001 R11: 0000000000000044 R12: ffff9cf5c2ef60e0 [ 1411.307865] R13: 0000000000000005 R14: 0000000000000000 R15: ffff9cf5c2ef6108 [ 1411.309074] bpf_trace_run2+0x8f/0x1a0 [ 1411.309891] FS: 00007ff485141700(0000) GS:ffff9cf5fae00000(0000) knlGS:0000000000000000 [ 1411.309896] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1411.311221] syscall_trace_enter.isra.20+0x161/0x1f0 [ 1411.311600] CR2: 00007ff48514d90e CR3: 0000000107114001 CR4: 0000000000370ef0 [ 1411.312291] do_syscall_64+0x15/0x80 [ 1411.312941] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1411.313803] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 1411.314223] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 1411.315082] RIP: 0033:0x7f00ad80a0e0 [ 1411.315626] Call Trace: [ 1411.315632] stack_map_get_build_id_offset+0x17c/0x260 To reproduce, first build `test_progs` binary: make -C tools/testing/selftests/bpf -j60 and then run the binary at tools/testing/selftests/bpf directory: ./test_progs -t get_stack_raw_tp The warning is due to commit 5b78ed24e8ec ("mm/pagemap: add mmap_assert_locked() annotations to find_vma*()") which added mmap_assert_locked() in find_vma() function. The mmap_assert_locked() function asserts that mm->mmap_lock needs to be held. But this is not the case for bpf_get_stack() or bpf_get_stackid() helper (kernel/bpf/stackmap.c), which uses mmap_read_trylock_non_owner() instead. Since mm->mmap_lock is not held in bpf_get_stack[id]() use case, the above warning is emitted during test run. This patch fixed the issue by (1). using mmap_read_trylock() instead of mmap_read_trylock_non_owner() to satisfy lockdep checking in find_vma(), and (2). droping lockdep for mmap_lock right before the irq_work_queue(). The function mmap_read_trylock_non_owner() is also removed since after this patch nobody calls it any more. Fixes: 5b78ed24e8ec ("mm/pagemap: add mmap_assert_locked() annotations to find_vma*()") Suggested-by: Jason Gunthorpe Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann Reviewed-by: Liam R. Howlett Cc: Luigi Rizzo Cc: Jason Gunthorpe Cc: linux-mm@kvack.org Link: https://lore.kernel.org/bpf/20210909155000.1610299-1-yhs@fb.com --- include/linux/mmap_lock.h | 9 --------- kernel/bpf/stackmap.c | 10 ++++++++-- 2 files changed, 8 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 0540f0156f58..3af8f7fb067d 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -144,15 +144,6 @@ static inline void mmap_read_unlock(struct mm_struct *mm) __mmap_lock_trace_released(mm, false); } -static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm) -{ - if (mmap_read_trylock(mm)) { - rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_); - return true; - } - return false; -} - static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) { up_read_non_owner(&mm->mmap_lock); diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index e8eefdf8cf3e..09a3fd97d329 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -179,7 +179,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, * with build_id. */ if (!user || !current || !current->mm || irq_work_busy || - !mmap_read_trylock_non_owner(current->mm)) { + !mmap_read_trylock(current->mm)) { /* cannot access current->mm, fall back to ips */ for (i = 0; i < trace_nr; i++) { id_offs[i].status = BPF_STACK_BUILD_ID_IP; @@ -204,9 +204,15 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, } if (!work) { - mmap_read_unlock_non_owner(current->mm); + mmap_read_unlock(current->mm); } else { work->mm = current->mm; + + /* The lock will be released once we're out of interrupt + * context. Tell lockdep that we've released it now so + * it doesn't complain that we forgot to release it. + */ + rwsem_release(¤t->mm->mmap_lock.dep_map, _RET_IP_); irq_work_queue(&work->irq_work); } } -- cgit From 4eb6bd55cfb22ffc20652732340c4962f3ac9a91 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 10 Sep 2021 16:40:39 -0700 Subject: compiler.h: drop fallback overflow checkers Once upgrading the minimum supported version of GCC to 5.1, we can drop the fallback code for !COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW. This is effectively a revert of commit f0907827a8a9 ("compiler.h: enable builtin overflow checkers and add fallback code") Link: https://github.com/ClangBuiltLinux/linux/issues/1438#issuecomment-916745801 Suggested-by: Rasmus Villemoes Signed-off-by: Nick Desaulniers Acked-by: Kees Cook Reviewed-by: Nathan Chancellor Signed-off-by: Linus Torvalds --- include/linux/compiler-clang.h | 13 ---- include/linux/compiler-gcc.h | 4 -- include/linux/overflow.h | 138 +----------------------------------- tools/include/linux/compiler-gcc.h | 4 -- tools/include/linux/overflow.h | 140 +------------------------------------ 5 files changed, 6 insertions(+), 293 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 49b0ac8b6fd3..3c4de9b6c6e3 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -62,19 +62,6 @@ #define __no_sanitize_coverage #endif -/* - * Not all versions of clang implement the type-generic versions - * of the builtin overflow checkers. Fortunately, clang implements - * __has_builtin allowing us to avoid awkward version - * checks. Unfortunately, we don't know which version of gcc clang - * pretends to be, so the macro may or may not be defined. - */ -#if __has_builtin(__builtin_mul_overflow) && \ - __has_builtin(__builtin_add_overflow) && \ - __has_builtin(__builtin_sub_overflow) -#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 -#endif - #if __has_feature(shadow_call_stack) # define __noscs __attribute__((__no_sanitize__("shadow-call-stack"))) #endif diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index cb9217fc60af..3f7f6fa0e051 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -128,10 +128,6 @@ #define __no_sanitize_coverage #endif -#if GCC_VERSION >= 50100 -#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 -#endif - /* * Turn individual warnings and errors on and off locally, depending * on version. diff --git a/include/linux/overflow.h b/include/linux/overflow.h index 0f12345c21fb..4669632bd72b 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -6,12 +6,9 @@ #include /* - * In the fallback code below, we need to compute the minimum and - * maximum values representable in a given type. These macros may also - * be useful elsewhere, so we provide them outside the - * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block. - * - * It would seem more obvious to do something like + * We need to compute the minimum and maximum values representable in a given + * type. These macros may also be useful elsewhere. It would seem more obvious + * to do something like: * * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0) * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0) @@ -54,7 +51,6 @@ static inline bool __must_check __must_check_overflow(bool overflow) return unlikely(overflow); } -#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW /* * For simplicity and code hygiene, the fallback code below insists on * a, b and *d having the same type (similar to the min() and max() @@ -90,134 +86,6 @@ static inline bool __must_check __must_check_overflow(bool overflow) __builtin_mul_overflow(__a, __b, __d); \ })) -#else - - -/* Checking for unsigned overflow is relatively easy without causing UB. */ -#define __unsigned_add_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a + __b; \ - *__d < __a; \ -}) -#define __unsigned_sub_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a - __b; \ - __a < __b; \ -}) -/* - * If one of a or b is a compile-time constant, this avoids a division. - */ -#define __unsigned_mul_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a * __b; \ - __builtin_constant_p(__b) ? \ - __b > 0 && __a > type_max(typeof(__a)) / __b : \ - __a > 0 && __b > type_max(typeof(__b)) / __a; \ -}) - -/* - * For signed types, detecting overflow is much harder, especially if - * we want to avoid UB. But the interface of these macros is such that - * we must provide a result in *d, and in fact we must produce the - * result promised by gcc's builtins, which is simply the possibly - * wrapped-around value. Fortunately, we can just formally do the - * operations in the widest relevant unsigned type (u64) and then - * truncate the result - gcc is smart enough to generate the same code - * with and without the (u64) casts. - */ - -/* - * Adding two signed integers can overflow only if they have the same - * sign, and overflow has happened iff the result has the opposite - * sign. - */ -#define __signed_add_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a + (u64)__b; \ - (((~(__a ^ __b)) & (*__d ^ __a)) \ - & type_min(typeof(__a))) != 0; \ -}) - -/* - * Subtraction is similar, except that overflow can now happen only - * when the signs are opposite. In this case, overflow has happened if - * the result has the opposite sign of a. - */ -#define __signed_sub_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a - (u64)__b; \ - ((((__a ^ __b)) & (*__d ^ __a)) \ - & type_min(typeof(__a))) != 0; \ -}) - -/* - * Signed multiplication is rather hard. gcc always follows C99, so - * division is truncated towards 0. This means that we can write the - * overflow check like this: - * - * (a > 0 && (b > MAX/a || b < MIN/a)) || - * (a < -1 && (b > MIN/a || b < MAX/a) || - * (a == -1 && b == MIN) - * - * The redundant casts of -1 are to silence an annoying -Wtype-limits - * (included in -Wextra) warning: When the type is u8 or u16, the - * __b_c_e in check_mul_overflow obviously selects - * __unsigned_mul_overflow, but unfortunately gcc still parses this - * code and warns about the limited range of __b. - */ - -#define __signed_mul_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - typeof(a) __tmax = type_max(typeof(a)); \ - typeof(a) __tmin = type_min(typeof(a)); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a * (u64)__b; \ - (__b > 0 && (__a > __tmax/__b || __a < __tmin/__b)) || \ - (__b < (typeof(__b))-1 && (__a > __tmin/__b || __a < __tmax/__b)) || \ - (__b == (typeof(__b))-1 && __a == __tmin); \ -}) - - -#define check_add_overflow(a, b, d) __must_check_overflow( \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_add_overflow(a, b, d), \ - __unsigned_add_overflow(a, b, d))) - -#define check_sub_overflow(a, b, d) __must_check_overflow( \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_sub_overflow(a, b, d), \ - __unsigned_sub_overflow(a, b, d))) - -#define check_mul_overflow(a, b, d) __must_check_overflow( \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_mul_overflow(a, b, d), \ - __unsigned_mul_overflow(a, b, d))) - -#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */ - /** check_shl_overflow() - Calculate a left-shifted value and check overflow * * @a: Value to be shifted diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h index 95c072b70d0e..a590a1dfafd9 100644 --- a/tools/include/linux/compiler-gcc.h +++ b/tools/include/linux/compiler-gcc.h @@ -38,7 +38,3 @@ #endif #define __printf(a, b) __attribute__((format(printf, a, b))) #define __scanf(a, b) __attribute__((format(scanf, a, b))) - -#if GCC_VERSION >= 50100 -#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 -#endif diff --git a/tools/include/linux/overflow.h b/tools/include/linux/overflow.h index 8712ff70995f..dcb0c1bf6866 100644 --- a/tools/include/linux/overflow.h +++ b/tools/include/linux/overflow.h @@ -5,12 +5,9 @@ #include /* - * In the fallback code below, we need to compute the minimum and - * maximum values representable in a given type. These macros may also - * be useful elsewhere, so we provide them outside the - * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block. - * - * It would seem more obvious to do something like + * We need to compute the minimum and maximum values representable in a given + * type. These macros may also be useful elsewhere. It would seem more obvious + * to do something like: * * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0) * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0) @@ -36,8 +33,6 @@ #define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T))) #define type_min(T) ((T)((T)-type_max(T)-(T)1)) - -#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW /* * For simplicity and code hygiene, the fallback code below insists on * a, b and *d having the same type (similar to the min() and max() @@ -73,135 +68,6 @@ __builtin_mul_overflow(__a, __b, __d); \ }) -#else - - -/* Checking for unsigned overflow is relatively easy without causing UB. */ -#define __unsigned_add_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a + __b; \ - *__d < __a; \ -}) -#define __unsigned_sub_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a - __b; \ - __a < __b; \ -}) -/* - * If one of a or b is a compile-time constant, this avoids a division. - */ -#define __unsigned_mul_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = __a * __b; \ - __builtin_constant_p(__b) ? \ - __b > 0 && __a > type_max(typeof(__a)) / __b : \ - __a > 0 && __b > type_max(typeof(__b)) / __a; \ -}) - -/* - * For signed types, detecting overflow is much harder, especially if - * we want to avoid UB. But the interface of these macros is such that - * we must provide a result in *d, and in fact we must produce the - * result promised by gcc's builtins, which is simply the possibly - * wrapped-around value. Fortunately, we can just formally do the - * operations in the widest relevant unsigned type (u64) and then - * truncate the result - gcc is smart enough to generate the same code - * with and without the (u64) casts. - */ - -/* - * Adding two signed integers can overflow only if they have the same - * sign, and overflow has happened iff the result has the opposite - * sign. - */ -#define __signed_add_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a + (u64)__b; \ - (((~(__a ^ __b)) & (*__d ^ __a)) \ - & type_min(typeof(__a))) != 0; \ -}) - -/* - * Subtraction is similar, except that overflow can now happen only - * when the signs are opposite. In this case, overflow has happened if - * the result has the opposite sign of a. - */ -#define __signed_sub_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a - (u64)__b; \ - ((((__a ^ __b)) & (*__d ^ __a)) \ - & type_min(typeof(__a))) != 0; \ -}) - -/* - * Signed multiplication is rather hard. gcc always follows C99, so - * division is truncated towards 0. This means that we can write the - * overflow check like this: - * - * (a > 0 && (b > MAX/a || b < MIN/a)) || - * (a < -1 && (b > MIN/a || b < MAX/a) || - * (a == -1 && b == MIN) - * - * The redundant casts of -1 are to silence an annoying -Wtype-limits - * (included in -Wextra) warning: When the type is u8 or u16, the - * __b_c_e in check_mul_overflow obviously selects - * __unsigned_mul_overflow, but unfortunately gcc still parses this - * code and warns about the limited range of __b. - */ - -#define __signed_mul_overflow(a, b, d) ({ \ - typeof(a) __a = (a); \ - typeof(b) __b = (b); \ - typeof(d) __d = (d); \ - typeof(a) __tmax = type_max(typeof(a)); \ - typeof(a) __tmin = type_min(typeof(a)); \ - (void) (&__a == &__b); \ - (void) (&__a == __d); \ - *__d = (u64)__a * (u64)__b; \ - (__b > 0 && (__a > __tmax/__b || __a < __tmin/__b)) || \ - (__b < (typeof(__b))-1 && (__a > __tmin/__b || __a < __tmax/__b)) || \ - (__b == (typeof(__b))-1 && __a == __tmin); \ -}) - - -#define check_add_overflow(a, b, d) \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_add_overflow(a, b, d), \ - __unsigned_add_overflow(a, b, d)) - -#define check_sub_overflow(a, b, d) \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_sub_overflow(a, b, d), \ - __unsigned_sub_overflow(a, b, d)) - -#define check_mul_overflow(a, b, d) \ - __builtin_choose_expr(is_signed_type(typeof(a)), \ - __signed_mul_overflow(a, b, d), \ - __unsigned_mul_overflow(a, b, d)) - - -#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */ - /** * array_size() - Calculate size of 2-dimensional array. * -- cgit From 4e59869aa6550657cb148ad49835605660ec9b88 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 10 Sep 2021 16:40:46 -0700 Subject: compiler-gcc.h: drop checks for older GCC versions Now that GCC 5.1 is the minimally supported default, drop the values we don't use. Signed-off-by: Nick Desaulniers Reviewed-by: Kees Cook Reviewed-by: Nathan Chancellor Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc.h | 4 +--- tools/include/linux/compiler-gcc.h | 4 +--- 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 3f7f6fa0e051..fd82ce169ce9 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -98,10 +98,8 @@ #if GCC_VERSION >= 70000 #define KASAN_ABI_VERSION 5 -#elif GCC_VERSION >= 50000 +#else #define KASAN_ABI_VERSION 4 -#elif GCC_VERSION >= 40902 -#define KASAN_ABI_VERSION 3 #endif #if __has_attribute(__no_sanitize_address__) diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h index a590a1dfafd9..43d9a46d36f0 100644 --- a/tools/include/linux/compiler-gcc.h +++ b/tools/include/linux/compiler-gcc.h @@ -16,9 +16,7 @@ # define __fallthrough __attribute__ ((fallthrough)) #endif -#if GCC_VERSION >= 40300 -# define __compiletime_error(message) __attribute__((error(message))) -#endif /* GCC_VERSION >= 40300 */ +#define __compiletime_error(message) __attribute__((error(message))) /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) -- cgit From 6d2ef226f2f18d530e48ead0cb5704505628b797 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 13 Sep 2021 10:20:01 -0700 Subject: compiler_attributes.h: drop __has_attribute() support for gcc4 Now that GCC 5.1 is the minimally supported default, the manual workaround for older gcc versions not having __has_attribute() are no longer relevant and can be removed. Signed-off-by: Linus Torvalds --- include/linux/compiler_attributes.h | 20 -------------------- 1 file changed, 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 2487be0e7199..ba417a5c80af 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -20,26 +20,6 @@ * Provide links to the documentation of each supported compiler, if it exists. */ -/* - * __has_attribute is supported on gcc >= 5, clang >= 2.9 and icc >= 17. - * In the meantime, to support gcc < 5, we implement __has_attribute - * by hand. - */ -#ifndef __has_attribute -# define __has_attribute(x) __GCC4_has_attribute_##x -# define __GCC4_has_attribute___assume_aligned__ 1 -# define __GCC4_has_attribute___copy__ 0 -# define __GCC4_has_attribute___designated_init__ 0 -# define __GCC4_has_attribute___externally_visible__ 1 -# define __GCC4_has_attribute___no_caller_saved_registers__ 0 -# define __GCC4_has_attribute___noclone__ 1 -# define __GCC4_has_attribute___no_profile_instrument_function__ 0 -# define __GCC4_has_attribute___nonstring__ 0 -# define __GCC4_has_attribute___no_sanitize_address__ 1 -# define __GCC4_has_attribute___no_sanitize_undefined__ 1 -# define __GCC4_has_attribute___fallthrough__ 0 -#endif - /* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-alias-function-attribute */ -- cgit From df26327ea097eb78e7967c45df6b23010c43c28d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 13 Sep 2021 10:29:44 -0700 Subject: Drop some straggling mentions of gcc-4.9 as being stale Fix up the admin-guide README file to the new gcc-5.1 requirement, and remove a stale comment about gcc support for the __assume_aligned__ attribute. Signed-off-by: Linus Torvalds --- Documentation/admin-guide/README.rst | 2 +- Documentation/translations/zh_CN/admin-guide/README.rst | 2 +- Documentation/translations/zh_TW/admin-guide/README.rst | 2 +- include/linux/compiler_attributes.h | 1 - 4 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/README.rst b/Documentation/admin-guide/README.rst index 35314b63008c..caa3c09a5c3f 100644 --- a/Documentation/admin-guide/README.rst +++ b/Documentation/admin-guide/README.rst @@ -259,7 +259,7 @@ Configuring the kernel Compiling the kernel -------------------- - - Make sure you have at least gcc 4.9 available. + - Make sure you have at least gcc 5.1 available. For more information, refer to :ref:`Documentation/process/changes.rst `. Please note that you can still run a.out user programs with this kernel. diff --git a/Documentation/translations/zh_CN/admin-guide/README.rst b/Documentation/translations/zh_CN/admin-guide/README.rst index 669a022f6817..980eb20521cf 100644 --- a/Documentation/translations/zh_CN/admin-guide/README.rst +++ b/Documentation/translations/zh_CN/admin-guide/README.rst @@ -223,7 +223,7 @@ Linux内核5.x版本 编译内核 --------- - - 确保您至少有gcc 4.9可用。 + - 确保您至少有gcc 5.1可用。 有关更多信息，请参阅 :ref:`Documentation/process/changes.rst ` 。 请注意，您仍然可以使用此内核运行a.out用户程序。 diff --git a/Documentation/translations/zh_TW/admin-guide/README.rst b/Documentation/translations/zh_TW/admin-guide/README.rst index b752e50359e6..6ce97edbab37 100644 --- a/Documentation/translations/zh_TW/admin-guide/README.rst +++ b/Documentation/translations/zh_TW/admin-guide/README.rst @@ -226,7 +226,7 @@ Linux內核5.x版本 編譯內核 --------- - - 確保您至少有gcc 4.9可用。 + - 確保您至少有gcc 5.1可用。 有關更多信息，請參閱 :ref:`Documentation/process/changes.rst ` 。 請注意，您仍然可以使用此內核運行a.out用戶程序。 diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index ba417a5c80af..ee19cebabcf5 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -54,7 +54,6 @@ * compiler should see some alignment anyway, when the return value is * massaged by 'flags = ptr & 3; ptr &= ~3;'). * - * Optional: only supported since gcc >= 4.9 * Optional: not supported by icc * * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-assume_005faligned-function-attribute -- cgit From 8520e224f547cd070c7c8f97b1fc6d58cff7ccaa Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 14 Sep 2021 01:07:57 +0200 Subject: bpf, cgroups: Fix cgroup v2 fallback on v1/v2 mixed mode Fix cgroup v1 interference when non-root cgroup v2 BPF programs are used. Back in the days, commit bd1060a1d671 ("sock, cgroup: add sock->sk_cgroup") embedded per-socket cgroup information into sock->sk_cgrp_data and in order to save 8 bytes in struct sock made both mutually exclusive, that is, when cgroup v1 socket tagging (e.g. net_cls/net_prio) is used, then cgroup v2 falls back to the root cgroup in sock_cgroup_ptr() (&cgrp_dfl_root.cgrp). The assumption made was "there is no reason to mix the two and this is in line with how legacy and v2 compatibility is handled" as stated in bd1060a1d671. However, with Kubernetes more widely supporting cgroups v2 as well nowadays, this assumption no longer holds, and the possibility of the v1/v2 mixed mode with the v2 root fallback being hit becomes a real security issue. Many of the cgroup v2 BPF programs are also used for policy enforcement, just to pick _one_ example, that is, to programmatically deny socket related system calls like connect(2) or bind(2). A v2 root fallback would implicitly cause a policy bypass for the affected Pods. In production environments, we have recently seen this case due to various circumstances: i) a different 3rd party agent and/or ii) a container runtime such as [0] in the user's environment configuring legacy cgroup v1 net_cls tags, which triggered implicitly mentioned root fallback. Another case is Kubernetes projects like kind [1] which create Kubernetes nodes in a container and also add cgroup namespaces to the mix, meaning programs which are attached to the cgroup v2 root of the cgroup namespace get attached to a non-root cgroup v2 path from init namespace point of view. And the latter's root is out of reach for agents on a kind Kubernetes node to configure. Meaning, any entity on the node setting cgroup v1 net_cls tag will trigger the bypass despite cgroup v2 BPF programs attached to the namespace root. Generally, this mutual exclusiveness does not hold anymore in today's user environments and makes cgroup v2 usage from BPF side fragile and unreliable. This fix adds proper struct cgroup pointer for the cgroup v2 case to struct sock_cgroup_data in order to address these issues; this implicitly also fixes the tradeoffs being made back then with regards to races and refcount leaks as stated in bd1060a1d671, and removes the fallback, so that cgroup v2 BPF programs always operate as expected. [0] https://github.com/nestybox/sysbox/ [1] https://kind.sigs.k8s.io/ Fixes: bd1060a1d671 ("sock, cgroup: add sock->sk_cgroup") Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Acked-by: Stanislav Fomichev Acked-by: Tejun Heo Link: https://lore.kernel.org/bpf/20210913230759.2313-1-daniel@iogearbox.net --- include/linux/cgroup-defs.h | 107 +++++++++++-------------------------------- include/linux/cgroup.h | 22 +-------- kernel/cgroup/cgroup.c | 50 ++++---------------- net/core/netclassid_cgroup.c | 7 +-- net/core/netprio_cgroup.c | 10 +--- 5 files changed, 41 insertions(+), 155 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index e1c705fdfa7c..db2e147e069f 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -752,107 +752,54 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {} * sock_cgroup_data is embedded at sock->sk_cgrp_data and contains * per-socket cgroup information except for memcg association. * - * On legacy hierarchies, net_prio and net_cls controllers directly set - * attributes on each sock which can then be tested by the network layer. - * On the default hierarchy, each sock is associated with the cgroup it was - * created in and the networking layer can match the cgroup directly. - * - * To avoid carrying all three cgroup related fields separately in sock, - * sock_cgroup_data overloads (prioidx, classid) and the cgroup pointer. - * On boot, sock_cgroup_data records the cgroup that the sock was created - * in so that cgroup2 matches can be made; however, once either net_prio or - * net_cls starts being used, the area is overridden to carry prioidx and/or - * classid. The two modes are distinguished by whether the lowest bit is - * set. Clear bit indicates cgroup pointer while set bit prioidx and - * classid. - * - * While userland may start using net_prio or net_cls at any time, once - * either is used, cgroup2 matching no longer works. There is no reason to - * mix the two and this is in line with how legacy and v2 compatibility is - * handled. On mode switch, cgroup references which are already being - * pointed to by socks may be leaked. While this can be remedied by adding - * synchronization around sock_cgroup_data, given that the number of leaked - * cgroups is bound and highly unlikely to be high, this seems to be the - * better trade-off. + * On legacy hierarchies, net_prio and net_cls controllers directly + * set attributes on each sock which can then be tested by the network + * layer. On the default hierarchy, each sock is associated with the + * cgroup it was created in and the networking layer can match the + * cgroup directly. */ struct sock_cgroup_data { - union { -#ifdef __LITTLE_ENDIAN - struct { - u8 is_data : 1; - u8 no_refcnt : 1; - u8 unused : 6; - u8 padding; - u16 prioidx; - u32 classid; - } __packed; -#else - struct { - u32 classid; - u16 prioidx; - u8 padding; - u8 unused : 6; - u8 no_refcnt : 1; - u8 is_data : 1; - } __packed; + struct cgroup *cgroup; /* v2 */ +#ifdef CONFIG_CGROUP_NET_CLASSID + u32 classid; /* v1 */ +#endif +#ifdef CONFIG_CGROUP_NET_PRIO + u16 prioidx; /* v1 */ #endif - u64 val; - }; }; -/* - * There's a theoretical window where the following accessors race with - * updaters and return part of the previous pointer as the prioidx or - * classid. Such races are short-lived and the result isn't critical. - */ static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd) { - /* fallback to 1 which is always the ID of the root cgroup */ - return (skcd->is_data & 1) ? skcd->prioidx : 1; +#ifdef CONFIG_CGROUP_NET_PRIO + return READ_ONCE(skcd->prioidx); +#else + return 1; +#endif } static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd) { - /* fallback to 0 which is the unconfigured default classid */ - return (skcd->is_data & 1) ? skcd->classid : 0; +#ifdef CONFIG_CGROUP_NET_CLASSID + return READ_ONCE(skcd->classid); +#else + return 0; +#endif } -/* - * If invoked concurrently, the updaters may clobber each other. The - * caller is responsible for synchronization. - */ static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd, u16 prioidx) { - struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }}; - - if (sock_cgroup_prioidx(&skcd_buf) == prioidx) - return; - - if (!(skcd_buf.is_data & 1)) { - skcd_buf.val = 0; - skcd_buf.is_data = 1; - } - - skcd_buf.prioidx = prioidx; - WRITE_ONCE(skcd->val, skcd_buf.val); /* see sock_cgroup_ptr() */ +#ifdef CONFIG_CGROUP_NET_PRIO + WRITE_ONCE(skcd->prioidx, prioidx); +#endif } static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd, u32 classid) { - struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }}; - - if (sock_cgroup_classid(&skcd_buf) == classid) - return; - - if (!(skcd_buf.is_data & 1)) { - skcd_buf.val = 0; - skcd_buf.is_data = 1; - } - - skcd_buf.classid = classid; - WRITE_ONCE(skcd->val, skcd_buf.val); /* see sock_cgroup_ptr() */ +#ifdef CONFIG_CGROUP_NET_CLASSID + WRITE_ONCE(skcd->classid, classid); +#endif } #else /* CONFIG_SOCK_CGROUP_DATA */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 7bf60454a313..75c151413fda 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -829,33 +829,13 @@ static inline void cgroup_account_cputime_field(struct task_struct *task, */ #ifdef CONFIG_SOCK_CGROUP_DATA -#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID) -extern spinlock_t cgroup_sk_update_lock; -#endif - -void cgroup_sk_alloc_disable(void); void cgroup_sk_alloc(struct sock_cgroup_data *skcd); void cgroup_sk_clone(struct sock_cgroup_data *skcd); void cgroup_sk_free(struct sock_cgroup_data *skcd); static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd) { -#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID) - unsigned long v; - - /* - * @skcd->val is 64bit but the following is safe on 32bit too as we - * just need the lower ulong to be written and read atomically. - */ - v = READ_ONCE(skcd->val); - - if (v & 3) - return &cgrp_dfl_root.cgrp; - - return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp; -#else - return (struct cgroup *)(unsigned long)skcd->val; -#endif + return skcd->cgroup; } #else /* CONFIG_CGROUP_DATA */ diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 881ce1470beb..8afa8690d288 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6572,74 +6572,44 @@ int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v) */ #ifdef CONFIG_SOCK_CGROUP_DATA -#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID) - -DEFINE_SPINLOCK(cgroup_sk_update_lock); -static bool cgroup_sk_alloc_disabled __read_mostly; - -void cgroup_sk_alloc_disable(void) -{ - if (cgroup_sk_alloc_disabled) - return; - pr_info("cgroup: disabling cgroup2 socket matching due to net_prio or net_cls activation\n"); - cgroup_sk_alloc_disabled = true; -} - -#else - -#define cgroup_sk_alloc_disabled false - -#endif - void cgroup_sk_alloc(struct sock_cgroup_data *skcd) { - if (cgroup_sk_alloc_disabled) { - skcd->no_refcnt = 1; - return; - } - /* Don't associate the sock with unrelated interrupted task's cgroup. */ if (in_interrupt()) return; rcu_read_lock(); - while (true) { struct css_set *cset; cset = task_css_set(current); if (likely(cgroup_tryget(cset->dfl_cgrp))) { - skcd->val = (unsigned long)cset->dfl_cgrp; + skcd->cgroup = cset->dfl_cgrp; cgroup_bpf_get(cset->dfl_cgrp); break; } cpu_relax(); } - rcu_read_unlock(); } void cgroup_sk_clone(struct sock_cgroup_data *skcd) { - if (skcd->val) { - if (skcd->no_refcnt) - return; - /* - * We might be cloning a socket which is left in an empty - * cgroup and the cgroup might have already been rmdir'd. - * Don't use cgroup_get_live(). - */ - cgroup_get(sock_cgroup_ptr(skcd)); - cgroup_bpf_get(sock_cgroup_ptr(skcd)); - } + struct cgroup *cgrp = sock_cgroup_ptr(skcd); + + /* + * We might be cloning a socket which is left in an empty + * cgroup and the cgroup might have already been rmdir'd. + * Don't use cgroup_get_live(). + */ + cgroup_get(cgrp); + cgroup_bpf_get(cgrp); } void cgroup_sk_free(struct sock_cgroup_data *skcd) { struct cgroup *cgrp = sock_cgroup_ptr(skcd); - if (skcd->no_refcnt) - return; cgroup_bpf_put(cgrp); cgroup_put(cgrp); } diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c index b49c57d35a88..1a6a86693b74 100644 --- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -71,11 +71,8 @@ static int update_classid_sock(const void *v, struct file *file, unsigned n) struct update_classid_context *ctx = (void *)v; struct socket *sock = sock_from_file(file); - if (sock) { - spin_lock(&cgroup_sk_update_lock); + if (sock) sock_cgroup_set_classid(&sock->sk->sk_cgrp_data, ctx->classid); - spin_unlock(&cgroup_sk_update_lock); - } if (--ctx->batch == 0) { ctx->batch = UPDATE_CLASSID_BATCH; return n + 1; @@ -121,8 +118,6 @@ static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft, struct css_task_iter it; struct task_struct *p; - cgroup_sk_alloc_disable(); - cs->classid = (u32)value; css_task_iter_start(css, 0, &it); diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 99a431c56f23..8456dfbe2eb4 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -207,8 +207,6 @@ static ssize_t write_priomap(struct kernfs_open_file *of, if (!dev) return -ENODEV; - cgroup_sk_alloc_disable(); - rtnl_lock(); ret = netprio_set_prio(of_css(of), dev, prio); @@ -221,12 +219,10 @@ static ssize_t write_priomap(struct kernfs_open_file *of, static int update_netprio(const void *v, struct file *file, unsigned n) { struct socket *sock = sock_from_file(file); - if (sock) { - spin_lock(&cgroup_sk_update_lock); + + if (sock) sock_cgroup_set_prioidx(&sock->sk->sk_cgrp_data, (unsigned long)v); - spin_unlock(&cgroup_sk_update_lock); - } return 0; } @@ -235,8 +231,6 @@ static void net_prio_attach(struct cgroup_taskset *tset) struct task_struct *p; struct cgroup_subsys_state *css; - cgroup_sk_alloc_disable(); - cgroup_taskset_for_each(p, css, tset) { void *v = (void *)(unsigned long)css->id; -- cgit From 7a8aa39d44564703620d937bb54cdea2d003657f Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Mon, 13 Sep 2021 17:05:51 +0100 Subject: nvmem: core: Add stubs for nvmem_cell_read_variable_le_u32/64 if !CONFIG_NVMEM When I added nvmem_cell_read_variable_le_u32() and nvmem_cell_read_variable_le_u64() I forgot to add the "static inline" stub functions for when CONFIG_NVMEM wasn't defined. Add them now. This was causing problems with randconfig builds that compiled `drivers/soc/qcom/cpr.c`. Fixes: 6feba6a62c57 ("PM: AVS: qcom-cpr: Use nvmem_cell_read_variable_le_u32()") Fixes: a28e824fb827 ("nvmem: core: Add functions to make number reading easy") Reported-by: kernel test robot Reviewed-by: Bjorn Andersson Signed-off-by: Douglas Anderson Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20210913160551.12907-1-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- include/linux/nvmem-consumer.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 923dada24eb4..c0c0cefc3b92 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -150,6 +150,20 @@ static inline int nvmem_cell_read_u64(struct device *dev, return -EOPNOTSUPP; } +static inline int nvmem_cell_read_variable_le_u32(struct device *dev, + const char *cell_id, + u32 *val) +{ + return -EOPNOTSUPP; +} + +static inline int nvmem_cell_read_variable_le_u64(struct device *dev, + const char *cell_id, + u64 *val) +{ + return -EOPNOTSUPP; +} + static inline struct nvmem_device *nvmem_device_get(struct device *dev, const char *name) { -- cgit From 81065b35e2486c024c7aa86caed452e1f01a59d4 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Mon, 13 Sep 2021 14:52:39 -0700 Subject: x86/mce: Avoid infinite loop for copy from user recovery There are two cases for machine check recovery: 1) The machine check was triggered by ring3 (application) code. This is the simpler case. The machine check handler simply queues work to be executed on return to user. That code unmaps the page from all users and arranges to send a SIGBUS to the task that triggered the poison. 2) The machine check was triggered in kernel code that is covered by an exception table entry. In this case the machine check handler still queues a work entry to unmap the page, etc. but this will not be called right away because the #MC handler returns to the fix up code address in the exception table entry. Problems occur if the kernel triggers another machine check before the return to user processes the first queued work item. Specifically, the work is queued using the ->mce_kill_me callback structure in the task struct for the current thread. Attempting to queue a second work item using this same callback results in a loop in the linked list of work functions to call. So when the kernel does return to user, it enters an infinite loop processing the same entry for ever. There are some legitimate scenarios where the kernel may take a second machine check before returning to the user. 1) Some code (e.g. futex) first tries a get_user() with page faults disabled. If this fails, the code retries with page faults enabled expecting that this will resolve the page fault. 2) Copy from user code retries a copy in byte-at-time mode to check whether any additional bytes can be copied. On the other side of the fence are some bad drivers that do not check the return value from individual get_user() calls and may access multiple user addresses without noticing that some/all calls have failed. Fix by adding a counter (current->mce_count) to keep track of repeated machine checks before task_work() is called. First machine check saves the address information and calls task_work_add(). Subsequent machine checks before that task_work call back is executed check that the address is in the same page as the first machine check (since the callback will offline exactly one page). Expected worst case is four machine checks before moving on (e.g. one user access with page faults disabled, then a repeat to the same address with page faults enabled ... repeat in copy tail bytes). Just in case there is some code that loops forever enforce a limit of 10. [ bp: Massage commit message, drop noinstr, fix typo, extend panic messages. ] Fixes: 5567d11c21a1 ("x86/mce: Send #MC singal from task work") Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Cc: Link: https://lkml.kernel.org/r/YT/IJ9ziLqmtqEPu@agluck-desk2.amr.corp.intel.com --- arch/x86/kernel/cpu/mce/core.c | 43 +++++++++++++++++++++++++++++++----------- include/linux/sched.h | 1 + 2 files changed, 33 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 8cb7816d03b4..193204aee880 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1253,6 +1253,9 @@ static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *fin static void kill_me_now(struct callback_head *ch) { + struct task_struct *p = container_of(ch, struct task_struct, mce_kill_me); + + p->mce_count = 0; force_sig(SIGBUS); } @@ -1262,6 +1265,7 @@ static void kill_me_maybe(struct callback_head *cb) int flags = MF_ACTION_REQUIRED; int ret; + p->mce_count = 0; pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr); if (!p->mce_ripv) @@ -1290,17 +1294,34 @@ static void kill_me_maybe(struct callback_head *cb) } } -static void queue_task_work(struct mce *m, int kill_current_task) +static void queue_task_work(struct mce *m, char *msg, int kill_current_task) { - current->mce_addr = m->addr; - current->mce_kflags = m->kflags; - current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV); - current->mce_whole_page = whole_page(m); + int count = ++current->mce_count; - if (kill_current_task) - current->mce_kill_me.func = kill_me_now; - else - current->mce_kill_me.func = kill_me_maybe; + /* First call, save all the details */ + if (count == 1) { + current->mce_addr = m->addr; + current->mce_kflags = m->kflags; + current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV); + current->mce_whole_page = whole_page(m); + + if (kill_current_task) + current->mce_kill_me.func = kill_me_now; + else + current->mce_kill_me.func = kill_me_maybe; + } + + /* Ten is likely overkill. Don't expect more than two faults before task_work() */ + if (count > 10) + mce_panic("Too many consecutive machine checks while accessing user data", m, msg); + + /* Second or later call, make sure page address matches the one from first call */ + if (count > 1 && (current->mce_addr >> PAGE_SHIFT) != (m->addr >> PAGE_SHIFT)) + mce_panic("Consecutive machine checks to different user pages", m, msg); + + /* Do not call task_work_add() more than once */ + if (count > 1) + return; task_work_add(current, ¤t->mce_kill_me, TWA_RESUME); } @@ -1438,7 +1459,7 @@ noinstr void do_machine_check(struct pt_regs *regs) /* If this triggers there is no way to recover. Die hard. */ BUG_ON(!on_thread_stack() || !user_mode(regs)); - queue_task_work(&m, kill_current_task); + queue_task_work(&m, msg, kill_current_task); } else { /* @@ -1456,7 +1477,7 @@ noinstr void do_machine_check(struct pt_regs *regs) } if (m.kflags & MCE_IN_KERNEL_COPYIN) - queue_task_work(&m, kill_current_task); + queue_task_work(&m, msg, kill_current_task); } out: mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); diff --git a/include/linux/sched.h b/include/linux/sched.h index 1780260f237b..361c7bc72cbb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1468,6 +1468,7 @@ struct task_struct { mce_whole_page : 1, __mce_reserved : 62; struct callback_head mce_kill_me; + int mce_count; #endif #ifdef CONFIG_KRETPROBES -- cgit From 58877b0824da15698bd85a0a9dbfa8c354e6ecb7 Mon Sep 17 00:00:00 2001 From: Kishon Vijay Abraham I Date: Thu, 9 Sep 2021 12:11:58 +0530 Subject: usb: core: hcd: Add support for deferring roothub registration It has been observed with certain PCIe USB cards (like Inateck connected to AM64 EVM or J7200 EVM) that as soon as the primary roothub is registered, port status change is handled even before xHC is running leading to cold plug USB devices not detected. For such cases, registering both the root hubs along with the second HCD is required. Add support for deferring roothub registration in usb_add_hcd(), so that both primary and secondary roothubs are registered along with the second HCD. CC: stable@vger.kernel.org # 5.4+ Suggested-by: Mathias Nyman Tested-by: Chris Chiu Acked-by: Alan Stern Signed-off-by: Kishon Vijay Abraham I Link: https://lore.kernel.org/r/20210909064200.16216-2-kishon@ti.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hcd.c | 29 +++++++++++++++++++++++------ include/linux/usb/hcd.h | 2 ++ 2 files changed, 25 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index 0f8b7c93310e..99ff2d23be05 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -2775,6 +2775,7 @@ int usb_add_hcd(struct usb_hcd *hcd, { int retval; struct usb_device *rhdev; + struct usb_hcd *shared_hcd; if (!hcd->skip_phy_initialization && usb_hcd_is_primary_hcd(hcd)) { hcd->phy_roothub = usb_phy_roothub_alloc(hcd->self.sysdev); @@ -2935,13 +2936,26 @@ int usb_add_hcd(struct usb_hcd *hcd, goto err_hcd_driver_start; } + /* starting here, usbcore will pay attention to the shared HCD roothub */ + shared_hcd = hcd->shared_hcd; + if (!usb_hcd_is_primary_hcd(hcd) && shared_hcd && HCD_DEFER_RH_REGISTER(shared_hcd)) { + retval = register_root_hub(shared_hcd); + if (retval != 0) + goto err_register_root_hub; + + if (shared_hcd->uses_new_polling && HCD_POLL_RH(shared_hcd)) + usb_hcd_poll_rh_status(shared_hcd); + } + /* starting here, usbcore will pay attention to this root hub */ - retval = register_root_hub(hcd); - if (retval != 0) - goto err_register_root_hub; + if (!HCD_DEFER_RH_REGISTER(hcd)) { + retval = register_root_hub(hcd); + if (retval != 0) + goto err_register_root_hub; - if (hcd->uses_new_polling && HCD_POLL_RH(hcd)) - usb_hcd_poll_rh_status(hcd); + if (hcd->uses_new_polling && HCD_POLL_RH(hcd)) + usb_hcd_poll_rh_status(hcd); + } return retval; @@ -2985,6 +2999,7 @@ EXPORT_SYMBOL_GPL(usb_add_hcd); void usb_remove_hcd(struct usb_hcd *hcd) { struct usb_device *rhdev = hcd->self.root_hub; + bool rh_registered; dev_info(hcd->self.controller, "remove, state %x\n", hcd->state); @@ -2995,6 +3010,7 @@ void usb_remove_hcd(struct usb_hcd *hcd) dev_dbg(hcd->self.controller, "roothub graceful disconnect\n"); spin_lock_irq (&hcd_root_hub_lock); + rh_registered = hcd->rh_registered; hcd->rh_registered = 0; spin_unlock_irq (&hcd_root_hub_lock); @@ -3004,7 +3020,8 @@ void usb_remove_hcd(struct usb_hcd *hcd) cancel_work_sync(&hcd->died_work); mutex_lock(&usb_bus_idr_lock); - usb_disconnect(&rhdev); /* Sets rhdev to NULL */ + if (rh_registered) + usb_disconnect(&rhdev); /* Sets rhdev to NULL */ mutex_unlock(&usb_bus_idr_lock); /* diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 548a028f2dab..2c1fc9212cf2 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -124,6 +124,7 @@ struct usb_hcd { #define HCD_FLAG_RH_RUNNING 5 /* root hub is running? */ #define HCD_FLAG_DEAD 6 /* controller has died? */ #define HCD_FLAG_INTF_AUTHORIZED 7 /* authorize interfaces? */ +#define HCD_FLAG_DEFER_RH_REGISTER 8 /* Defer roothub registration */ /* The flags can be tested using these macros; they are likely to * be slightly faster than test_bit(). @@ -134,6 +135,7 @@ struct usb_hcd { #define HCD_WAKEUP_PENDING(hcd) ((hcd)->flags & (1U << HCD_FLAG_WAKEUP_PENDING)) #define HCD_RH_RUNNING(hcd) ((hcd)->flags & (1U << HCD_FLAG_RH_RUNNING)) #define HCD_DEAD(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEAD)) +#define HCD_DEFER_RH_REGISTER(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEFER_RH_REGISTER)) /* * Specifies if interfaces are authorized by default -- cgit From 8fb0f47a9d7acf620d0fd97831b69da9bc5e22ed Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 10 Sep 2021 11:18:36 -0600 Subject: iov_iter: add helper to save iov_iter state In an ideal world, when someone is passed an iov_iter and returns X bytes, then X bytes would have been consumed/advanced from the iov_iter. But we have use cases that always consume the entire iterator, a few examples of that are iomap and bdev O_DIRECT. This means we cannot rely on the state of the iov_iter once we've called ->read_iter() or ->write_iter(). This would be easier if we didn't always have to deal with truncate of the iov_iter, as rewinding would be trivial without that. We recently added a commit to track the truncate state, but that grew the iov_iter by 8 bytes and wasn't the best solution. Implement a helper to save enough of the iov_iter state to sanely restore it after we've called the read/write iterator helpers. This currently only works for IOVEC/BVEC/KVEC as that's all we need, support for other iterator types are left as an exercise for the reader. Link: https://lore.kernel.org/linux-fsdevel/CAHk-=wiacKV4Gh-MYjteU0LwNBSGpWrK-Ov25HdqB1ewinrFPg@mail.gmail.com/ Signed-off-by: Jens Axboe --- include/linux/uio.h | 15 +++++++++++++++ lib/iov_iter.c | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 51 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 5265024e8b90..984c4ab74859 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -27,6 +27,12 @@ enum iter_type { ITER_DISCARD, }; +struct iov_iter_state { + size_t iov_offset; + size_t count; + unsigned long nr_segs; +}; + struct iov_iter { u8 iter_type; bool data_source; @@ -55,6 +61,14 @@ static inline enum iter_type iov_iter_type(const struct iov_iter *i) return i->iter_type; } +static inline void iov_iter_save_state(struct iov_iter *iter, + struct iov_iter_state *state) +{ + state->iov_offset = iter->iov_offset; + state->count = iter->count; + state->nr_segs = iter->nr_segs; +} + static inline bool iter_is_iovec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_IOVEC; @@ -233,6 +247,7 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); +void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index f2d50d69a6c3..755c10c5138c 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1972,3 +1972,39 @@ int import_single_range(int rw, void __user *buf, size_t len, return 0; } EXPORT_SYMBOL(import_single_range); + +/** + * iov_iter_restore() - Restore a &struct iov_iter to the same state as when + * iov_iter_save_state() was called. + * + * @i: &struct iov_iter to restore + * @state: state to restore from + * + * Used after iov_iter_save_state() to bring restore @i, if operations may + * have advanced it. + * + * Note: only works on ITER_IOVEC, ITER_BVEC, and ITER_KVEC + */ +void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state) +{ + if (WARN_ON_ONCE(!iov_iter_is_bvec(i) && !iter_is_iovec(i)) && + !iov_iter_is_kvec(i)) + return; + i->iov_offset = state->iov_offset; + i->count = state->count; + /* + * For the *vec iters, nr_segs + iov is constant - if we increment + * the vec, then we also decrement the nr_segs count. Hence we don't + * need to track both of these, just one is enough and we can deduct + * the other from that. ITER_KVEC and ITER_IOVEC are the same struct + * size, so we can just increment the iov pointer as they are unionzed. + * ITER_BVEC _may_ be the same size on some archs, but on others it is + * not. Be safe and handle it separately. + */ + BUILD_BUG_ON(sizeof(struct iovec) != sizeof(struct kvec)); + if (iov_iter_is_bvec(i)) + i->bvec -= state->nr_segs - i->nr_segs; + else + i->iov -= state->nr_segs - i->nr_segs; + i->nr_segs = state->nr_segs; +} -- cgit From 77e02cf57b6cff9919949defb7fd9b8ac16399a2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 14 Sep 2021 13:23:22 -0700 Subject: memblock: introduce saner 'memblock_free_ptr()' interface The boot-time allocation interface for memblock is a mess, with 'memblock_alloc()' returning a virtual pointer, but then you are supposed to free it with 'memblock_free()' that takes a _physical_ address. Not only is that all kinds of strange and illogical, but it actually causes bugs, when people then use it like a normal allocation function, and it fails spectacularly on a NULL pointer: https://lore.kernel.org/all/20210912140820.GD25450@xsang-OptiPlex-9020/ or just random memory corruption if the debug checks don't catch it: https://lore.kernel.org/all/61ab2d0c-3313-aaab-514c-e15b7aa054a0@suse.cz/ I really don't want to apply patches that treat the symptoms, when the fundamental cause is this horribly confusing interface. I started out looking at just automating a sane replacement sequence, but because of this mix or virtual and physical addresses, and because people have used the "__pa()" macro that can take either a regular kernel pointer, or just the raw "unsigned long" address, it's all quite messy. So this just introduces a new saner interface for freeing a virtual address that was allocated using 'memblock_alloc()', and that was kept as a regular kernel pointer. And then it converts a couple of users that are obvious and easy to test, including the 'xbc_nodes' case in lib/bootconfig.c that caused problems. Reported-by: kernel test robot Fixes: 40caa127f3c7 ("init: bootconfig: Remove all bootconfig data when the init memory is removed") Cc: Steven Rostedt Cc: Mike Rapoport Cc: Andrew Morton Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Vlastimil Babka Signed-off-by: Linus Torvalds --- arch/x86/kernel/setup_percpu.c | 2 +- arch/x86/mm/kasan_init_64.c | 6 ++---- arch/x86/mm/numa.c | 2 +- arch/x86/mm/numa_emulation.c | 3 +-- drivers/base/arch_numa.c | 2 +- drivers/macintosh/smu.c | 2 +- include/linux/memblock.h | 1 + init/main.c | 2 +- kernel/printk/printk.c | 4 ++-- lib/bootconfig.c | 2 +- mm/memblock.c | 16 +++++++++++++++- 11 files changed, 27 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 78a32b956e81..5afd98559193 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -135,7 +135,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) static void __init pcpu_fc_free(void *ptr, size_t size) { - memblock_free(__pa(ptr), size); + memblock_free_ptr(ptr, size); } static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 1a50434c8a4d..ef885370719a 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -49,8 +49,7 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, p = early_alloc(PMD_SIZE, nid, false); if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL)) return; - else if (p) - memblock_free(__pa(p), PMD_SIZE); + memblock_free_ptr(p, PMD_SIZE); } p = early_alloc(PAGE_SIZE, nid, true); @@ -86,8 +85,7 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr, p = early_alloc(PUD_SIZE, nid, false); if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL)) return; - else if (p) - memblock_free(__pa(p), PUD_SIZE); + memblock_free_ptr(p, PUD_SIZE); } p = early_alloc(PAGE_SIZE, nid, true); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index a1b5c71099e6..1e9b93b088db 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -355,7 +355,7 @@ void __init numa_reset_distance(void) /* numa_distance could be 1LU marking allocation failure, test cnt */ if (numa_distance_cnt) - memblock_free(__pa(numa_distance), size); + memblock_free_ptr(numa_distance, size); numa_distance_cnt = 0; numa_distance = NULL; /* enable table creation */ } diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index 737491b13728..e801e30089c4 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -517,8 +517,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) } /* free the copied physical distance table */ - if (phys_dist) - memblock_free(__pa(phys_dist), phys_size); + memblock_free_ptr(phys_dist, phys_size); return; no_emu: diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index 46c503486e96..00fb4120a5b3 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -264,7 +264,7 @@ void __init numa_free_distance(void) size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]); - memblock_free(__pa(numa_distance), size); + memblock_free_ptr(numa_distance, size); numa_distance_cnt = 0; numa_distance = NULL; } diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index 94fb63a7b357..fe63d5ee201b 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -570,7 +570,7 @@ fail_msg_node: fail_db_node: of_node_put(smu->db_node); fail_bootmem: - memblock_free(__pa(smu), sizeof(struct smu_device)); + memblock_free_ptr(smu, sizeof(struct smu_device)); smu = NULL; fail_np: of_node_put(np); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index b066024c62e3..34de69b3b8ba 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -118,6 +118,7 @@ int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); void memblock_free_all(void); +void memblock_free_ptr(void *ptr, size_t size); void reset_node_managed_pages(pg_data_t *pgdat); void reset_all_zones_managed_pages(void); diff --git a/init/main.c b/init/main.c index 5c9a48df90e1..3f7216934441 100644 --- a/init/main.c +++ b/init/main.c @@ -924,7 +924,7 @@ static void __init print_unknown_bootoptions(void) end += sprintf(end, " %s", *p); pr_notice("Unknown command line parameters:%s\n", unknown_options); - memblock_free(__pa(unknown_options), len); + memblock_free_ptr(unknown_options, len); } asmlinkage __visible void __init __no_sanitize_address start_kernel(void) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 825277e1e742..a8d0a58deebc 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1166,9 +1166,9 @@ void __init setup_log_buf(int early) return; err_free_descs: - memblock_free(__pa(new_descs), new_descs_size); + memblock_free_ptr(new_descs, new_descs_size); err_free_log_buf: - memblock_free(__pa(new_log_buf), new_log_buf_len); + memblock_free_ptr(new_log_buf, new_log_buf_len); } static bool __read_mostly ignore_loglevel; diff --git a/lib/bootconfig.c b/lib/bootconfig.c index f8419cff1147..5ae248b29373 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -792,7 +792,7 @@ void __init xbc_destroy_all(void) xbc_data = NULL; xbc_data_size = 0; xbc_node_num = 0; - memblock_free(__pa(xbc_nodes), sizeof(struct xbc_node) * XBC_NODE_MAX); + memblock_free_ptr(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX); xbc_nodes = NULL; brace_index = 0; } diff --git a/mm/memblock.c b/mm/memblock.c index 0ab5a749bfa6..184dcd2e5d99 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -472,7 +472,7 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, kfree(old_array); else if (old_array != memblock_memory_init_regions && old_array != memblock_reserved_init_regions) - memblock_free(__pa(old_array), old_alloc_size); + memblock_free_ptr(old_array, old_alloc_size); /* * Reserve the new array if that comes from the memblock. Otherwise, we @@ -795,6 +795,20 @@ int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) return memblock_remove_range(&memblock.memory, base, size); } +/** + * memblock_free_ptr - free boot memory allocation + * @ptr: starting address of the boot memory allocation + * @size: size of the boot memory block in bytes + * + * Free boot memory block previously allocated by memblock_alloc_xx() API. + * The freeing memory will not be released to the buddy allocator. + */ +void __init_memblock memblock_free_ptr(void *ptr, size_t size) +{ + if (ptr) + memblock_free(__pa(ptr), size); +} + /** * memblock_free - free boot memory block * @base: phys starting address of the boot memory block -- cgit From 7dedd3e18077f996a10c47250ac85d080e5f474e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 10 Sep 2021 11:19:58 -0600 Subject: Revert "iov_iter: track truncated size" This reverts commit 2112ff5ce0c1128fe7b4d19cfe7f2b8ce5b595fa. We no longer need to track the truncation count, the one user that did need it has been converted to using iov_iter_restore() instead. Signed-off-by: Jens Axboe --- include/linux/uio.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 984c4ab74859..207101a9c5c3 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -53,7 +53,6 @@ struct iov_iter { }; loff_t xarray_start; }; - size_t truncated; }; static inline enum iter_type iov_iter_type(const struct iov_iter *i) @@ -270,10 +269,8 @@ static inline void iov_iter_truncate(struct iov_iter *i, u64 count) * conversion in assignement is by definition greater than all * values of size_t, including old i->count. */ - if (i->count > count) { - i->truncated += i->count - count; + if (i->count > count) i->count = count; - } } /* @@ -282,7 +279,6 @@ static inline void iov_iter_truncate(struct iov_iter *i, u64 count) */ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) { - i->truncated -= count - i->count; i->count = count; } -- cgit From f6b5f1a56987de837f8e25cd560847106b8632a8 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 14 Sep 2021 20:52:24 -0700 Subject: compiler.h: Introduce absolute_pointer macro absolute_pointer() disassociates a pointer from its originating symbol type and context. Use it to prevent compiler warnings/errors such as drivers/net/ethernet/i825xx/82596.c: In function 'i82596_probe': arch/m68k/include/asm/string.h:72:25: error: '__builtin_memcpy' reading 6 bytes from a region of size 0 [-Werror=stringop-overread] Such warnings may be reported by gcc 11.x for string and memory operations on fixed addresses. Suggested-by: Linus Torvalds Signed-off-by: Guenter Roeck Reviewed-by: Geert Uytterhoeven Signed-off-by: Linus Torvalds --- include/linux/compiler.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index b67261a1e3e9..3d5af56337bd 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -188,6 +188,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, (typeof(ptr)) (__ptr + (off)); }) #endif +#define absolute_pointer(val) RELOC_HIDE((void *)(val), 0) + #ifndef OPTIMIZER_HIDE_VAR /* Make the optimizer believe the variable can be manipulated arbitrarily. */ #define OPTIMIZER_HIDE_VAR(var) \ -- cgit From 3c9cfb5269f76d447dbadb67835368f3111a91d7 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 17 Sep 2021 14:17:35 +0300 Subject: net: update NXP copyright text NXP Legal insists that the following are not fine: - Saying "NXP Semiconductors" instead of "NXP", since the company's registered name is "NXP" - Putting a "(c)" sign in the copyright string - Putting a comma in the copyright string The only accepted copyright string format is "Copyright NXP". This patch changes the copyright headers in the networking files that were sent by me, or derived from code sent by me. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/ocelot/felix.c | 2 +- drivers/net/dsa/ocelot/felix.h | 2 +- drivers/net/dsa/ocelot/felix_vsc9959.c | 2 +- drivers/net/dsa/sja1105/sja1105_clocking.c | 2 +- drivers/net/dsa/sja1105/sja1105_devlink.c | 2 +- drivers/net/dsa/sja1105/sja1105_flower.c | 2 +- drivers/net/dsa/sja1105/sja1105_mdio.c | 2 +- drivers/net/dsa/sja1105/sja1105_spi.c | 2 +- drivers/net/dsa/sja1105/sja1105_static_config.c | 2 +- drivers/net/dsa/sja1105/sja1105_static_config.h | 2 +- drivers/net/dsa/sja1105/sja1105_vl.c | 2 +- drivers/net/dsa/sja1105/sja1105_vl.h | 2 +- drivers/net/ethernet/freescale/enetc/enetc_ierb.c | 2 +- drivers/net/ethernet/freescale/enetc/enetc_ierb.h | 2 +- drivers/net/ethernet/mscc/ocelot_devlink.c | 2 +- drivers/net/ethernet/mscc/ocelot_mrp.c | 2 +- drivers/net/ethernet/mscc/ocelot_net.c | 2 +- drivers/net/pcs/pcs-xpcs-nxp.c | 2 +- include/linux/dsa/ocelot.h | 2 +- include/linux/packing.h | 2 +- lib/packing.c | 2 +- net/dsa/tag_ocelot.c | 2 +- net/dsa/tag_ocelot_8021q.c | 2 +- tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh | 2 +- 24 files changed, 24 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 3656e67af789..a3a9636430d6 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2019-2021 NXP Semiconductors +/* Copyright 2019-2021 NXP * * This is an umbrella module for all network switches that are * register-compatible with Ocelot and that perform I/O to their host CPU diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h index 5854bab43327..54024b6f9498 100644 --- a/drivers/net/dsa/ocelot/felix.h +++ b/drivers/net/dsa/ocelot/felix.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright 2019 NXP Semiconductors +/* Copyright 2019 NXP */ #ifndef _MSCC_FELIX_H #define _MSCC_FELIX_H diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index f966a253d1c7..9e2ac8e46619 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: (GPL-2.0 OR MIT) /* Copyright 2017 Microsemi Corporation - * Copyright 2018-2019 NXP Semiconductors + * Copyright 2018-2019 NXP */ #include #include diff --git a/drivers/net/dsa/sja1105/sja1105_clocking.c b/drivers/net/dsa/sja1105/sja1105_clocking.c index 387a1f2f161c..5bbf1707f2af 100644 --- a/drivers/net/dsa/sja1105/sja1105_clocking.c +++ b/drivers/net/dsa/sja1105/sja1105_clocking.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: BSD-3-Clause -/* Copyright (c) 2016-2018, NXP Semiconductors +/* Copyright 2016-2018 NXP * Copyright (c) 2018-2019, Vladimir Oltean */ #include diff --git a/drivers/net/dsa/sja1105/sja1105_devlink.c b/drivers/net/dsa/sja1105/sja1105_devlink.c index 05c7f4ca3b1a..0569ff066634 100644 --- a/drivers/net/dsa/sja1105/sja1105_devlink.c +++ b/drivers/net/dsa/sja1105/sja1105_devlink.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2018-2019, Vladimir Oltean - * Copyright 2020 NXP Semiconductors + * Copyright 2020 NXP */ #include "sja1105.h" diff --git a/drivers/net/dsa/sja1105/sja1105_flower.c b/drivers/net/dsa/sja1105/sja1105_flower.c index 6c10ffa968ce..72b9b39b0989 100644 --- a/drivers/net/dsa/sja1105/sja1105_flower.c +++ b/drivers/net/dsa/sja1105/sja1105_flower.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2020, NXP Semiconductors +/* Copyright 2020 NXP */ #include "sja1105.h" #include "sja1105_vl.h" diff --git a/drivers/net/dsa/sja1105/sja1105_mdio.c b/drivers/net/dsa/sja1105/sja1105_mdio.c index 705d3900e43a..215dd17ca790 100644 --- a/drivers/net/dsa/sja1105/sja1105_mdio.c +++ b/drivers/net/dsa/sja1105/sja1105_mdio.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2021, NXP Semiconductors +/* Copyright 2021 NXP */ #include #include diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c index d60a530d0272..d3c9ad6d39d4 100644 --- a/drivers/net/dsa/sja1105/sja1105_spi.c +++ b/drivers/net/dsa/sja1105/sja1105_spi.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: BSD-3-Clause -/* Copyright (c) 2016-2018, NXP Semiconductors +/* Copyright 2016-2018 NXP * Copyright (c) 2018, Sensor-Technik Wiedemann GmbH * Copyright (c) 2018-2019, Vladimir Oltean */ diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.c b/drivers/net/dsa/sja1105/sja1105_static_config.c index 7a422ef4deb6..baba204ad62f 100644 --- a/drivers/net/dsa/sja1105/sja1105_static_config.c +++ b/drivers/net/dsa/sja1105/sja1105_static_config.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: BSD-3-Clause -/* Copyright (c) 2016-2018, NXP Semiconductors +/* Copyright 2016-2018 NXP * Copyright (c) 2018-2019, Vladimir Oltean */ #include "sja1105_static_config.h" diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.h b/drivers/net/dsa/sja1105/sja1105_static_config.h index bce0f5c03d0b..6a372d5f22ae 100644 --- a/drivers/net/dsa/sja1105/sja1105_static_config.h +++ b/drivers/net/dsa/sja1105/sja1105_static_config.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: BSD-3-Clause */ -/* Copyright (c) 2016-2018, NXP Semiconductors +/* Copyright 2016-2018 NXP * Copyright (c) 2018-2019, Vladimir Oltean */ #ifndef _SJA1105_STATIC_CONFIG_H diff --git a/drivers/net/dsa/sja1105/sja1105_vl.c b/drivers/net/dsa/sja1105/sja1105_vl.c index ec7b65daec20..6802f4057cc0 100644 --- a/drivers/net/dsa/sja1105/sja1105_vl.c +++ b/drivers/net/dsa/sja1105/sja1105_vl.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2020, NXP Semiconductors +/* Copyright 2020 NXP */ #include #include diff --git a/drivers/net/dsa/sja1105/sja1105_vl.h b/drivers/net/dsa/sja1105/sja1105_vl.h index 173d78963fed..51fba0dce91a 100644 --- a/drivers/net/dsa/sja1105/sja1105_vl.h +++ b/drivers/net/dsa/sja1105/sja1105_vl.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright 2020, NXP Semiconductors +/* Copyright 2020 NXP */ #ifndef _SJA1105_VL_H #define _SJA1105_VL_H diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ierb.c b/drivers/net/ethernet/freescale/enetc/enetc_ierb.c index ee1468e3eaa3..91f02c505028 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ierb.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ierb.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) -/* Copyright 2021 NXP Semiconductors +/* Copyright 2021 NXP * * The Integrated Endpoint Register Block (IERB) is configured by pre-boot * software and is supposed to be to ENETC what a NVRAM is to a 'real' PCIe diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ierb.h b/drivers/net/ethernet/freescale/enetc/enetc_ierb.h index b3b774e0998a..c2ce47c4be9f 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ierb.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_ierb.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ -/* Copyright 2021 NXP Semiconductors */ +/* Copyright 2021 NXP */ #include #include diff --git a/drivers/net/ethernet/mscc/ocelot_devlink.c b/drivers/net/ethernet/mscc/ocelot_devlink.c index edafbd37d12c..b8737efd2a85 100644 --- a/drivers/net/ethernet/mscc/ocelot_devlink.c +++ b/drivers/net/ethernet/mscc/ocelot_devlink.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: (GPL-2.0 OR MIT) -/* Copyright 2020-2021 NXP Semiconductors +/* Copyright 2020-2021 NXP */ #include #include "ocelot.h" diff --git a/drivers/net/ethernet/mscc/ocelot_mrp.c b/drivers/net/ethernet/mscc/ocelot_mrp.c index 08b481a93460..4b0941f09f71 100644 --- a/drivers/net/ethernet/mscc/ocelot_mrp.c +++ b/drivers/net/ethernet/mscc/ocelot_mrp.c @@ -2,7 +2,7 @@ /* Microsemi Ocelot Switch driver * * Copyright (c) 2017, 2019 Microsemi Corporation - * Copyright 2020-2021 NXP Semiconductors + * Copyright 2020-2021 NXP */ #include diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index c0c465a4a981..e54b9fb2a97a 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -5,7 +5,7 @@ * mscc_ocelot_switch_lib. * * Copyright (c) 2017, 2019 Microsemi Corporation - * Copyright 2020-2021 NXP Semiconductors + * Copyright 2020-2021 NXP */ #include diff --git a/drivers/net/pcs/pcs-xpcs-nxp.c b/drivers/net/pcs/pcs-xpcs-nxp.c index 984c9f7f16a8..d16fc58cd48d 100644 --- a/drivers/net/pcs/pcs-xpcs-nxp.c +++ b/drivers/net/pcs/pcs-xpcs-nxp.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2021 NXP Semiconductors +/* Copyright 2021 NXP */ #include #include "pcs-xpcs.h" diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index c6bc45ae5e03..435777a0073c 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 - * Copyright 2019-2021 NXP Semiconductors + * Copyright 2019-2021 NXP */ #ifndef _NET_DSA_TAG_OCELOT_H diff --git a/include/linux/packing.h b/include/linux/packing.h index 54667735cc67..8d6571feb95d 100644 --- a/include/linux/packing.h +++ b/include/linux/packing.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: BSD-3-Clause - * Copyright (c) 2016-2018, NXP Semiconductors + * Copyright 2016-2018 NXP * Copyright (c) 2018-2019, Vladimir Oltean */ #ifndef _LINUX_PACKING_H diff --git a/lib/packing.c b/lib/packing.c index 6ed72dccfdb5..9a72f4bbf0e2 100644 --- a/lib/packing.c +++ b/lib/packing.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 -/* Copyright (c) 2016-2018, NXP Semiconductors +/* Copyright 2016-2018 NXP * Copyright (c) 2018-2019, Vladimir Oltean */ #include diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index d37ab98e7fe1..8025ed778d33 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2019 NXP Semiconductors +/* Copyright 2019 NXP */ #include #include diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index 3038a257ba05..59072930cb02 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2020-2021 NXP Semiconductors +/* Copyright 2020-2021 NXP * * An implementation of the software-defined tag_8021q.c tagger format, which * also preserves full functionality under a vlan_filtering bridge. It does diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh index beee0d5646a6..f7d84549cc3e 100755 --- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh +++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh @@ -1,6 +1,6 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -# Copyright 2020 NXP Semiconductors +# Copyright 2020 NXP WAIT_TIME=1 NUM_NETIFS=4 -- cgit From cf9579976f724ad517cc15b7caadea728c7e245c Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 17 Sep 2021 16:34:32 +0300 Subject: net: mdio: introduce a shutdown method to mdio device drivers MDIO-attached devices might have interrupts and other things that might need quiesced when we kexec into a new kernel. Things are even more creepy when those interrupt lines are shared, and in that case it is absolutely mandatory to disable all interrupt sources. Moreover, MDIO devices might be DSA switches, and DSA needs its own shutdown method to unlink from the DSA master, which is a new requirement that appeared after commit 2f1e8ea726e9 ("net: dsa: link interfaces with the DSA master to get rid of lockdep warnings"). So introduce a ->shutdown method in the MDIO device driver structure. Signed-off-by: Vladimir Oltean Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/mdio_device.c | 11 +++++++++++ include/linux/mdio.h | 3 +++ 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c index c94cb5382dc9..250742ffdfd9 100644 --- a/drivers/net/phy/mdio_device.c +++ b/drivers/net/phy/mdio_device.c @@ -179,6 +179,16 @@ static int mdio_remove(struct device *dev) return 0; } +static void mdio_shutdown(struct device *dev) +{ + struct mdio_device *mdiodev = to_mdio_device(dev); + struct device_driver *drv = mdiodev->dev.driver; + struct mdio_driver *mdiodrv = to_mdio_driver(drv); + + if (mdiodrv->shutdown) + mdiodrv->shutdown(mdiodev); +} + /** * mdio_driver_register - register an mdio_driver with the MDIO layer * @drv: new mdio_driver to register @@ -193,6 +203,7 @@ int mdio_driver_register(struct mdio_driver *drv) mdiodrv->driver.bus = &mdio_bus_type; mdiodrv->driver.probe = mdio_probe; mdiodrv->driver.remove = mdio_remove; + mdiodrv->driver.shutdown = mdio_shutdown; retval = driver_register(&mdiodrv->driver); if (retval) { diff --git a/include/linux/mdio.h b/include/linux/mdio.h index ffb787d5ebde..5e6dc38f418e 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -80,6 +80,9 @@ struct mdio_driver { /* Clears up any memory if needed */ void (*remove)(struct mdio_device *mdiodev); + + /* Quiesces the device on system shutdown, turns off interrupts etc */ + void (*shutdown)(struct mdio_device *mdiodev); }; static inline struct mdio_driver * -- cgit From d4ffd5df9d18031b6a53f934388726775b4452d3 Mon Sep 17 00:00:00 2001 From: Jiashuo Liang Date: Fri, 30 Jul 2021 11:01:52 +0800 Subject: x86/fault: Fix wrong signal when vsyscall fails with pkey The function __bad_area_nosemaphore() calls kernelmode_fixup_or_oops() with the parameter @signal being actually @pkey, which will send a signal numbered with the argument in @pkey. This bug can be triggered when the kernel fails to access user-given memory pages that are protected by a pkey, so it can go down the do_user_addr_fault() path and pass the !user_mode() check in __bad_area_nosemaphore(). Most cases will simply run the kernel fixup code to make an -EFAULT. But when another condition current->thread.sig_on_uaccess_err is met, which is only used to emulate vsyscall, the kernel will generate the wrong signal. Add a new parameter @pkey to kernelmode_fixup_or_oops() to fix this. [ bp: Massage commit message, fix build error as reported by the 0day bot: https://lkml.kernel.org/r/202109202245.APvuT8BX-lkp@intel.com ] Fixes: 5042d40a264c ("x86/fault: Bypass no_context() for implicit kernel faults from usermode") Reported-by: kernel test robot Signed-off-by: Jiashuo Liang Signed-off-by: Borislav Petkov Acked-by: Dave Hansen Link: https://lkml.kernel.org/r/20210730030152.249106-1-liangjs@pku.edu.cn --- arch/x86/include/asm/pkeys.h | 2 -- arch/x86/mm/fault.c | 26 ++++++++++++++++++-------- include/linux/pkeys.h | 2 ++ 3 files changed, 20 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index 5c7bcaa79623..1d5f14aff5f6 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -2,8 +2,6 @@ #ifndef _ASM_X86_PKEYS_H #define _ASM_X86_PKEYS_H -#define ARCH_DEFAULT_PKEY 0 - /* * If more than 16 keys are ever supported, a thorough audit * will be necessary to ensure that the types that store key diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index b2eefdefc108..84a2c8c4af73 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -710,7 +710,8 @@ oops: static noinline void kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code, - unsigned long address, int signal, int si_code) + unsigned long address, int signal, int si_code, + u32 pkey) { WARN_ON_ONCE(user_mode(regs)); @@ -735,8 +736,12 @@ kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code, set_signal_archinfo(address, error_code); - /* XXX: hwpoison faults will set the wrong code. */ - force_sig_fault(signal, si_code, (void __user *)address); + if (si_code == SEGV_PKUERR) { + force_sig_pkuerr((void __user *)address, pkey); + } else { + /* XXX: hwpoison faults will set the wrong code. */ + force_sig_fault(signal, si_code, (void __user *)address); + } } /* @@ -798,7 +803,8 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, struct task_struct *tsk = current; if (!user_mode(regs)) { - kernelmode_fixup_or_oops(regs, error_code, address, pkey, si_code); + kernelmode_fixup_or_oops(regs, error_code, address, + SIGSEGV, si_code, pkey); return; } @@ -930,7 +936,8 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, { /* Kernel mode? Handle exceptions or die: */ if (!user_mode(regs)) { - kernelmode_fixup_or_oops(regs, error_code, address, SIGBUS, BUS_ADRERR); + kernelmode_fixup_or_oops(regs, error_code, address, + SIGBUS, BUS_ADRERR, ARCH_DEFAULT_PKEY); return; } @@ -1396,7 +1403,8 @@ good_area: */ if (!user_mode(regs)) kernelmode_fixup_or_oops(regs, error_code, address, - SIGBUS, BUS_ADRERR); + SIGBUS, BUS_ADRERR, + ARCH_DEFAULT_PKEY); return; } @@ -1416,7 +1424,8 @@ good_area: return; if (fatal_signal_pending(current) && !user_mode(regs)) { - kernelmode_fixup_or_oops(regs, error_code, address, 0, 0); + kernelmode_fixup_or_oops(regs, error_code, address, + 0, 0, ARCH_DEFAULT_PKEY); return; } @@ -1424,7 +1433,8 @@ good_area: /* Kernel mode? Handle exceptions or die: */ if (!user_mode(regs)) { kernelmode_fixup_or_oops(regs, error_code, address, - SIGSEGV, SEGV_MAPERR); + SIGSEGV, SEGV_MAPERR, + ARCH_DEFAULT_PKEY); return; } diff --git a/include/linux/pkeys.h b/include/linux/pkeys.h index 6beb26b7151d..86be8bf27b41 100644 --- a/include/linux/pkeys.h +++ b/include/linux/pkeys.h @@ -4,6 +4,8 @@ #include +#define ARCH_DEFAULT_PKEY 0 + #ifdef CONFIG_ARCH_HAS_PKEYS #include #else /* ! CONFIG_ARCH_HAS_PKEYS */ -- cgit From 20c36ce2164f1774b487d443ece99b754bc6ad43 Mon Sep 17 00:00:00 2001 From: Bixuan Cui Date: Thu, 16 Sep 2021 10:52:03 +0800 Subject: irqdomain: Change the type of 'size' in __irq_domain_add() to be consistent The 'size' is used in struct_size(domain, revmap, size) and its input parameter type is 'size_t'(unsigned int). Changing the size to 'unsigned int' to make the type consistent. Signed-off-by: Bixuan Cui Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210916025203.44841-1-cuibixuan@huawei.com --- include/linux/irqdomain.h | 2 +- kernel/irq/irqdomain.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 23e4ee523576..9ee238ad29ce 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -251,7 +251,7 @@ static inline struct fwnode_handle *irq_domain_alloc_fwnode(phys_addr_t *pa) } void irq_domain_free_fwnode(struct fwnode_handle *fwnode); -struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, +struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int size, irq_hw_number_t hwirq_max, int direct_max, const struct irq_domain_ops *ops, void *host_data); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 62be16135e7c..bfa289ed57ab 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -136,7 +136,7 @@ EXPORT_SYMBOL_GPL(irq_domain_free_fwnode); * Allocates and initializes an irq_domain structure. * Returns pointer to IRQ domain, or NULL on failure. */ -struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, +struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int size, irq_hw_number_t hwirq_max, int direct_max, const struct irq_domain_ops *ops, void *host_data) -- cgit From a68de80f61f6af397bc06fb391ff2e571c9c4d80 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 1 Sep 2021 13:30:27 -0700 Subject: entry: rseq: Call rseq_handle_notify_resume() in tracehook_notify_resume() Invoke rseq_handle_notify_resume() from tracehook_notify_resume() now that the two function are always called back-to-back by architectures that have rseq. The rseq helper is stubbed out for architectures that don't support rseq, i.e. this is a nop across the board. Note, tracehook_notify_resume() is horribly named and arguably does not belong in tracehook.h as literally every line of code in it has nothing to do with tracing. But, that's been true since commit a42c6ded827d ("move key_repace_session_keyring() into tracehook_notify_resume()") first usurped tracehook_notify_resume() back in 2012. Punt cleaning that mess up to future patches. No functional change intended. Acked-by: Mathieu Desnoyers Signed-off-by: Sean Christopherson Message-Id: <20210901203030.1292304-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/arm/kernel/signal.c | 1 - arch/arm64/kernel/signal.c | 4 +--- arch/csky/kernel/signal.c | 4 +--- arch/mips/kernel/signal.c | 4 +--- arch/powerpc/kernel/signal.c | 4 +--- include/linux/tracehook.h | 2 ++ kernel/entry/common.c | 4 +--- kernel/entry/kvm.c | 4 +--- 8 files changed, 8 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index d0a800be0486..a41e27ace391 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -628,7 +628,6 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) uprobe_notify_resume(regs); } else { tracehook_notify_resume(regs); - rseq_handle_notify_resume(NULL, regs); } } local_irq_disable(); diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 9fe70b12b34f..c287b9407f28 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -940,10 +940,8 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags) if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs); - if (thread_flags & _TIF_NOTIFY_RESUME) { + if (thread_flags & _TIF_NOTIFY_RESUME) tracehook_notify_resume(regs); - rseq_handle_notify_resume(NULL, regs); - } if (thread_flags & _TIF_FOREIGN_FPSTATE) fpsimd_restore_current_state(); diff --git a/arch/csky/kernel/signal.c b/arch/csky/kernel/signal.c index 312f046d452d..bc4238b9f709 100644 --- a/arch/csky/kernel/signal.c +++ b/arch/csky/kernel/signal.c @@ -260,8 +260,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs); - if (thread_info_flags & _TIF_NOTIFY_RESUME) { + if (thread_info_flags & _TIF_NOTIFY_RESUME) tracehook_notify_resume(regs); - rseq_handle_notify_resume(NULL, regs); - } } diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c index f1e985109da0..c9b2a75563e1 100644 --- a/arch/mips/kernel/signal.c +++ b/arch/mips/kernel/signal.c @@ -906,10 +906,8 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, void *unused, if (thread_info_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) do_signal(regs); - if (thread_info_flags & _TIF_NOTIFY_RESUME) { + if (thread_info_flags & _TIF_NOTIFY_RESUME) tracehook_notify_resume(regs); - rseq_handle_notify_resume(NULL, regs); - } user_enter(); } diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index e600764a926c..b93b87df499d 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -293,10 +293,8 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags) do_signal(current); } - if (thread_info_flags & _TIF_NOTIFY_RESUME) { + if (thread_info_flags & _TIF_NOTIFY_RESUME) tracehook_notify_resume(regs); - rseq_handle_notify_resume(NULL, regs); - } } static unsigned long get_tm_stackpointer(struct task_struct *tsk) diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 3e80c4bc66f7..2564b7434b4d 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -197,6 +197,8 @@ static inline void tracehook_notify_resume(struct pt_regs *regs) mem_cgroup_handle_over_high(); blkcg_maybe_throttle_current(); + + rseq_handle_notify_resume(NULL, regs); } /* diff --git a/kernel/entry/common.c b/kernel/entry/common.c index bf16395b9e13..d5a61d565ad5 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -171,10 +171,8 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, if (ti_work & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) handle_signal_work(regs, ti_work); - if (ti_work & _TIF_NOTIFY_RESUME) { + if (ti_work & _TIF_NOTIFY_RESUME) tracehook_notify_resume(regs); - rseq_handle_notify_resume(NULL, regs); - } /* Architecture specific TIF work */ arch_exit_to_user_mode_work(regs, ti_work); diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c index 049fd06b4c3d..49972ee99aff 100644 --- a/kernel/entry/kvm.c +++ b/kernel/entry/kvm.c @@ -19,10 +19,8 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work) if (ti_work & _TIF_NEED_RESCHED) schedule(); - if (ti_work & _TIF_NOTIFY_RESUME) { + if (ti_work & _TIF_NOTIFY_RESUME) tracehook_notify_resume(NULL); - rseq_handle_notify_resume(NULL, NULL); - } ret = arch_xfer_to_guest_mode_handle_work(vcpu, ti_work); if (ret) -- cgit From 243418e3925d5b5b0657ae54c322d43035e97eed Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Fri, 24 Sep 2021 15:43:47 -0700 Subject: mm: fs: invalidate bh_lrus for only cold path The kernel test robot reported the regression of fio.write_iops[1] with commit 8cc621d2f45d ("mm: fs: invalidate BH LRU during page migration"). Since lru_add_drain is called frequently, invalidate bh_lrus there could increase bh_lrus cache miss ratio, which needs more IO in the end. This patch moves the bh_lrus invalidation from the hot path( e.g., zap_page_range, pagevec_release) to cold path(i.e., lru_add_drain_all, lru_cache_disable). Zhengjun Xing confirmed "I test the patch, the regression reduced to -2.9%" [1] https://lore.kernel.org/lkml/20210520083144.GD14190@xsang-OptiPlex-9020/ [2] 8cc621d2f45d, mm: fs: invalidate BH LRU during page migration Link: https://lkml.kernel.org/r/20210907212347.1977686-1-minchan@kernel.org Signed-off-by: Minchan Kim Reported-by: kernel test robot Reviewed-by: Chris Goldsworthy Tested-by: "Xing, Zhengjun" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/buffer.c | 8 ++++++-- include/linux/buffer_head.h | 4 ++-- mm/swap.c | 19 ++++++++++++++++--- 3 files changed, 24 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/fs/buffer.c b/fs/buffer.c index ab7573d72dd7..c615387aedca 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1425,12 +1425,16 @@ void invalidate_bh_lrus(void) } EXPORT_SYMBOL_GPL(invalidate_bh_lrus); -void invalidate_bh_lrus_cpu(int cpu) +/* + * It's called from workqueue context so we need a bh_lru_lock to close + * the race with preemption/irq. + */ +void invalidate_bh_lrus_cpu(void) { struct bh_lru *b; bh_lru_lock(); - b = per_cpu_ptr(&bh_lrus, cpu); + b = this_cpu_ptr(&bh_lrus); __invalidate_bh_lrus(b); bh_lru_unlock(); } diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 6486d3c19463..36f33685c8c0 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -194,7 +194,7 @@ void __breadahead_gfp(struct block_device *, sector_t block, unsigned int size, struct buffer_head *__bread_gfp(struct block_device *, sector_t block, unsigned size, gfp_t gfp); void invalidate_bh_lrus(void); -void invalidate_bh_lrus_cpu(int cpu); +void invalidate_bh_lrus_cpu(void); bool has_bh_in_lru(int cpu, void *dummy); struct buffer_head *alloc_buffer_head(gfp_t gfp_flags); void free_buffer_head(struct buffer_head * bh); @@ -408,7 +408,7 @@ static inline int inode_has_buffers(struct inode *inode) { return 0; } static inline void invalidate_inode_buffers(struct inode *inode) {} static inline int remove_inode_buffers(struct inode *inode) { return 1; } static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; } -static inline void invalidate_bh_lrus_cpu(int cpu) {} +static inline void invalidate_bh_lrus_cpu(void) {} static inline bool has_bh_in_lru(int cpu, void *dummy) { return false; } #define buffer_heads_over_limit 0 diff --git a/mm/swap.c b/mm/swap.c index 897200d27dd0..af3cad4e5378 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -620,7 +620,6 @@ void lru_add_drain_cpu(int cpu) pagevec_lru_move_fn(pvec, lru_lazyfree_fn); activate_page_drain(cpu); - invalidate_bh_lrus_cpu(cpu); } /** @@ -703,6 +702,20 @@ void lru_add_drain(void) local_unlock(&lru_pvecs.lock); } +/* + * It's called from per-cpu workqueue context in SMP case so + * lru_add_drain_cpu and invalidate_bh_lrus_cpu should run on + * the same cpu. It shouldn't be a problem in !SMP case since + * the core is only one and the locks will disable preemption. + */ +static void lru_add_and_bh_lrus_drain(void) +{ + local_lock(&lru_pvecs.lock); + lru_add_drain_cpu(smp_processor_id()); + local_unlock(&lru_pvecs.lock); + invalidate_bh_lrus_cpu(); +} + void lru_add_drain_cpu_zone(struct zone *zone) { local_lock(&lru_pvecs.lock); @@ -717,7 +730,7 @@ static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); static void lru_add_drain_per_cpu(struct work_struct *dummy) { - lru_add_drain(); + lru_add_and_bh_lrus_drain(); } /* @@ -858,7 +871,7 @@ void lru_cache_disable(void) */ __lru_add_drain_all(true); #else - lru_add_drain(); + lru_add_and_bh_lrus_drain(); #endif } -- cgit From 57ed7b4303a1c4d1885019fef03e6a5af2e8468a Mon Sep 17 00:00:00 2001 From: Weizhao Ouyang Date: Fri, 24 Sep 2021 15:43:53 -0700 Subject: mm/debug: sync up latest migrate_reason to migrate_reason_names Sync up MR_DEMOTION to migrate_reason_names and add a synch prompt. Link: https://lkml.kernel.org/r/20210921064553.293905-3-o451686892@gmail.com Fixes: 26aa2d199d6f ("mm/migrate: demote pages during reclaim") Signed-off-by: Weizhao Ouyang Reviewed-by: "Huang, Ying" Reviewed-by: John Hubbard Cc: Anshuman Khandual Cc: Michal Hocko Cc: Pavel Tatashin Cc: Yang Shi Cc: Zi Yan Cc: Dave Hansen Cc: Minchan Kim Cc: Mina Almasry Cc: "Matthew Wilcox (Oracle)" Cc: Oscar Salvador Cc: Wei Xu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 6 +++++- mm/debug.c | 1 + 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 326250996b4e..c8077e936691 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -19,6 +19,11 @@ struct migration_target_control; */ #define MIGRATEPAGE_SUCCESS 0 +/* + * Keep sync with: + * - macro MIGRATE_REASON in include/trace/events/migrate.h + * - migrate_reason_names[MR_TYPES] in mm/debug.c + */ enum migrate_reason { MR_COMPACTION, MR_MEMORY_FAILURE, @@ -32,7 +37,6 @@ enum migrate_reason { MR_TYPES }; -/* In mm/debug.c; also keep sync with include/trace/events/migrate.h */ extern const char *migrate_reason_names[MR_TYPES]; #ifdef CONFIG_MIGRATION diff --git a/mm/debug.c b/mm/debug.c index e61037cded98..fae0f81ad831 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -26,6 +26,7 @@ const char *migrate_reason_names[MR_TYPES] = { "numa_misplaced", "contig_range", "longterm_pin", + "demotion", }; const struct trace_print_flags pageflag_names[] = { -- cgit