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') 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 v1.2.3 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 --------- 1 file changed, 9 deletions(-) (limited to 'include') 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); -- cgit v1.2.3 From 7ad9bb9d0f357dcab5eb9a0f28d1c8983c48434c Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Fri, 10 Sep 2021 18:57:13 +0000 Subject: asm-generic/hyperv: provide cpumask_to_vpset_noself This is a new variant which removes `self' cpu from the vpset. It will be used in Hyper-V enlightened IPI code. Signed-off-by: Wei Liu Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20210910185714.299411-2-wei.liu@kernel.org --- include/asm-generic/mshyperv.h | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index 9a000ba2bb75..9a134806f1d5 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -184,10 +184,12 @@ static inline int hv_cpu_number_to_vp_number(int cpu_number) return hv_vp_index[cpu_number]; } -static inline int cpumask_to_vpset(struct hv_vpset *vpset, - const struct cpumask *cpus) +static inline int __cpumask_to_vpset(struct hv_vpset *vpset, + const struct cpumask *cpus, + bool exclude_self) { int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1; + int this_cpu = smp_processor_id(); /* valid_bank_mask can represent up to 64 banks */ if (hv_max_vp_index / 64 >= 64) @@ -205,6 +207,8 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset, * Some banks may end up being empty but this is acceptable. */ for_each_cpu(cpu, cpus) { + if (exclude_self && cpu == this_cpu) + continue; vcpu = hv_cpu_number_to_vp_number(cpu); if (vcpu == VP_INVAL) return -1; @@ -219,6 +223,19 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset, return nr_bank; } +static inline int cpumask_to_vpset(struct hv_vpset *vpset, + const struct cpumask *cpus) +{ + return __cpumask_to_vpset(vpset, cpus, false); +} + +static inline int cpumask_to_vpset_noself(struct hv_vpset *vpset, + const struct cpumask *cpus) +{ + WARN_ON_ONCE(preemptible()); + return __cpumask_to_vpset(vpset, cpus, true); +} + void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die); bool hv_is_hyperv_initialized(void); bool hv_is_hibernation_supported(void); -- cgit v1.2.3 From 4fe6a946823a9bc8619fd16b7ea7d15914a30f22 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 2 Sep 2021 21:51:01 +0100 Subject: afs: Try to avoid taking RCU read lock when checking vnode validity Try to avoid taking the RCU read lock when checking the validity of a vnode's callback state. The only thing it's needed for is to pin the parent volume's server list whilst we search it to find the record of the server we're currently using to see if it has been reinitialised (ie. it sent us a CB.InitCallBackState* RPC). Do this by the following means: (1) Keep an additional per-cell counter (fs_s_break) that's incremented each time any of the fileservers in the cell reinitialises. Since the new counter can be accessed without RCU from the vnode, we can check that first - and only if it differs, get the RCU read lock and check the volume's server list. (2) Replace afs_get_s_break_rcu() with afs_check_server_good() which now indicates whether the callback promise is still expected to be present on the server. This does the checks as described in (1). (3) Restructure afs_check_validity() to take account of the change in (2). We can also get rid of the valid variable and just use the need_clear variable with the addition of the afs_cb_break_no_promise reason. (4) afs_check_validity() probably shouldn't be altering vnode->cb_v_break and vnode->cb_s_break when it doesn't have cb_lock exclusively locked. Move the change to vnode->cb_v_break to __afs_break_callback(). Delegate the change to vnode->cb_s_break to afs_select_fileserver() and set vnode->cb_fs_s_break there also. (5) afs_validate() no longer needs to get the RCU read lock around its call to afs_check_validity() - and can skip the call entirely if we don't have a promise. Signed-off-by: David Howells Tested-by: Markus Suvanto cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/163111669583.283156.1397603105683094563.stgit@warthog.procyon.org.uk/ --- include/trace/events/afs.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index 9f73ed2cf061..bca73e8c8cde 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -306,11 +306,13 @@ enum afs_flock_operation { enum afs_cb_break_reason { afs_cb_break_no_break, + afs_cb_break_no_promise, afs_cb_break_for_callback, afs_cb_break_for_deleted, afs_cb_break_for_lapsed, + afs_cb_break_for_s_reinit, afs_cb_break_for_unlink, - afs_cb_break_for_vsbreak, + afs_cb_break_for_v_break, afs_cb_break_for_volume_callback, afs_cb_break_for_zap, }; @@ -602,11 +604,13 @@ enum afs_cb_break_reason { #define afs_cb_break_reasons \ EM(afs_cb_break_no_break, "no-break") \ + EM(afs_cb_break_no_promise, "no-promise") \ EM(afs_cb_break_for_callback, "break-cb") \ EM(afs_cb_break_for_deleted, "break-del") \ EM(afs_cb_break_for_lapsed, "break-lapsed") \ + EM(afs_cb_break_for_s_reinit, "s-reinit") \ EM(afs_cb_break_for_unlink, "break-unlink") \ - EM(afs_cb_break_for_vsbreak, "break-vs") \ + EM(afs_cb_break_for_v_break, "break-v") \ EM(afs_cb_break_for_volume_callback, "break-v-cb") \ E_(afs_cb_break_for_zap, "break-zap") -- cgit v1.2.3 From dd47c104533dedb90434a3f142e94a671ac623a6 Mon Sep 17 00:00:00 2001 From: Eugene Syromiatnikov Date: Mon, 13 Sep 2021 17:44:15 +0200 Subject: io-wq: provide IO_WQ_* constants for IORING_REGISTER_IOWQ_MAX_WORKERS arg items The items passed in the array pointed by the arg parameter of IORING_REGISTER_IOWQ_MAX_WORKERS io_uring_register operation carry certain semantics: they refer to different io-wq worker categories; provide IO_WQ_* constants in the UAPI, so these categories can be referenced in the user space code. Suggested-by: Jens Axboe Complements: 2e480058ddc21ec5 ("io-wq: provide a way to limit max number of workers") Signed-off-by: Eugene Syromiatnikov Link: https://lore.kernel.org/r/20210913154415.GA12890@asgard.redhat.com Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 59ef35154e3d..b270a07b285e 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -317,13 +317,19 @@ enum { IORING_REGISTER_IOWQ_AFF = 17, IORING_UNREGISTER_IOWQ_AFF = 18, - /* set/get max number of workers */ + /* set/get max number of io-wq workers */ IORING_REGISTER_IOWQ_MAX_WORKERS = 19, /* this goes last */ IORING_REGISTER_LAST }; +/* io-wq worker categories */ +enum { + IO_WQ_BOUND, + IO_WQ_UNBOUND, +}; + /* deprecated, see struct io_uring_rsrc_update */ struct io_uring_files_update { __u32 offset; -- cgit v1.2.3 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 +---------------------------------------- 3 files changed, 3 insertions(+), 152 deletions(-) (limited to 'include') 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 -- cgit v1.2.3 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 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') 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__) -- cgit v1.2.3 From 6f20fa2dfa549401860479328371f0d5cee9b114 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 10 Sep 2021 16:40:47 -0700 Subject: vmlinux.lds.h: remove old check for GCC 4.9 Now that GCC 5.1 is the minimally supported version of GCC, we can effectively revert commit 85c2ce9104eb ("sched, vmlinux.lds: Increase STRUCT_ALIGNMENT to 64 bytes for GCC-4.9") Cc: Peter Zijlstra Signed-off-by: Nick Desaulniers Acked-by: Kees Cook Signed-off-by: Linus Torvalds --- include/asm-generic/vmlinux.lds.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index aa50bf2959fe..f2984af2b85b 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -116,11 +116,7 @@ * GCC 4.5 and later have a 32 bytes section alignment for structures. * Except GCC 4.9, that feels the need to align on 64 bytes. */ -#if __GNUC__ == 4 && __GNUC_MINOR__ == 9 -#define STRUCT_ALIGNMENT 64 -#else #define STRUCT_ALIGNMENT 32 -#endif #define STRUCT_ALIGN() . = ALIGN(STRUCT_ALIGNMENT) /* -- cgit v1.2.3 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') 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 v1.2.3 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 --- include/linux/compiler_attributes.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') 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 v1.2.3 From 099dd788e31b4f426ef49c2785069804925a84e1 Mon Sep 17 00:00:00 2001 From: Steve French Date: Mon, 13 Sep 2021 14:51:10 -0500 Subject: cifs: remove pathname for file from SPDX header checkpatch complains about source files with filenames (e.g. in these cases just below the SPDX header in comments at the top of various files in fs/cifs). It also is helpful to change this now so will be less confusing when the parent directory is renamed e.g. from fs/cifs to fs/smb_client (or fs/smbfs) Reviewed-by: Ronnie Sahlberg Signed-off-by: Steve French --- include/uapi/linux/cifs/cifs_mount.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/cifs/cifs_mount.h b/include/uapi/linux/cifs/cifs_mount.h index 69829205fdb5..8e87d27b0951 100644 --- a/include/uapi/linux/cifs/cifs_mount.h +++ b/include/uapi/linux/cifs/cifs_mount.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ /* - * include/uapi/linux/cifs/cifs_mount.h * * Author(s): Scott Lovenberg (scott.lovenberg@gmail.com) * -- cgit v1.2.3 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 +-------- 2 files changed, 28 insertions(+), 101 deletions(-) (limited to 'include') 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 */ -- cgit v1.2.3 From b564171ade70570b7f335fa8ed17adb28409e3ac Mon Sep 17 00:00:00 2001 From: Li Li Date: Fri, 10 Sep 2021 09:42:10 -0700 Subject: binder: fix freeze race Currently cgroup freezer is used to freeze the application threads, and BINDER_FREEZE is used to freeze the corresponding binder interface. There's already a mechanism in ioctl(BINDER_FREEZE) to wait for any existing transactions to drain out before actually freezing the binder interface. But freezing an app requires 2 steps, freezing the binder interface with ioctl(BINDER_FREEZE) and then freezing the application main threads with cgroupfs. This is not an atomic operation. The following race issue might happen. 1) Binder interface is frozen by ioctl(BINDER_FREEZE); 2) Main thread A initiates a new sync binder transaction to process B; 3) Main thread A is frozen by "echo 1 > cgroup.freeze"; 4) The response from process B reaches the frozen thread, which will unexpectedly fail. This patch provides a mechanism to check if there's any new pending transaction happening between ioctl(BINDER_FREEZE) and freezing the main thread. If there's any, the main thread freezing operation can be rolled back to finish the pending transaction. Furthermore, the response might reach the binder driver before the rollback actually happens. That will still cause failed transaction. As the other process doesn't wait for another response of the response, the response transaction failure can be fixed by treating the response transaction like an oneway/async one, allowing it to reach the frozen thread. And it will be consumed when the thread gets unfrozen later. NOTE: This patch reuses the existing definition of struct binder_frozen_status_info but expands the bit assignments of __u32 member sync_recv. To ensure backward compatibility, bit 0 of sync_recv still indicates there's an outstanding sync binder transaction. This patch adds new information to bit 1 of sync_recv, indicating the binder transaction happens exactly when there's a race. If an existing userspace app runs on a new kernel, a sync binder call will set bit 0 of sync_recv so ioctl(BINDER_GET_FROZEN_INFO) still return the expected value (true). The app just doesn't check bit 1 intentionally so it doesn't have the ability to tell if there's a race. This behavior is aligned with what happens on an old kernel which doesn't set bit 1 at all. A new userspace app can 1) check bit 0 to know if there's a sync binder transaction happened when being frozen - same as before; and 2) check bit 1 to know if that sync binder transaction happened exactly when there's a race - a new information for rollback decision. the same time, confirmed the pending transactions succeeded. Fixes: 432ff1e91694 ("binder: BINDER_FREEZE ioctl") Acked-by: Todd Kjos Cc: stable Signed-off-by: Li Li Test: stress test with apps being frozen and initiating binder calls at Link: https://lore.kernel.org/r/20210910164210.2282716-2-dualli@chromium.org Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/android/binder.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index 20e435fe657a..3246f2c74696 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -225,7 +225,14 @@ struct binder_freeze_info { struct binder_frozen_status_info { __u32 pid; + + /* process received sync transactions since last frozen + * bit 0: received sync transaction after being frozen + * bit 1: new pending sync transaction during freezing + */ __u32 sync_recv; + + /* process received async transactions since last frozen */ __u32 async_recv; }; -- cgit v1.2.3 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') 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 v1.2.3 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 --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') 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 v1.2.3 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 --- include/linux/usb/hcd.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') 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 v1.2.3 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 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include') 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); -- cgit v1.2.3 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 --- include/linux/memblock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') 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); -- cgit v1.2.3 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') 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 v1.2.3 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') 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 v1.2.3 From a57d8c217aadac75530b8e7ffb3a3e1b7bfd0330 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 14 Sep 2021 16:47:26 +0300 Subject: net: dsa: flush switchdev workqueue before tearing down CPU/DSA ports Sometimes when unbinding the mv88e6xxx driver on Turris MOX, these error messages appear: mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete be:79:b4:9e:9e:96 vid 1 from fdb: -2 mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete be:79:b4:9e:9e:96 vid 0 from fdb: -2 mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete d8:58:d7:00:ca:6d vid 100 from fdb: -2 mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete d8:58:d7:00:ca:6d vid 1 from fdb: -2 mv88e6085 d0032004.mdio-mii:12: port 1 failed to delete d8:58:d7:00:ca:6d vid 0 from fdb: -2 (and similarly for other ports) What happens is that DSA has a policy "even if there are bugs, let's at least not leak memory" and dsa_port_teardown() clears the dp->fdbs and dp->mdbs lists, which are supposed to be empty. But deleting that cleanup code, the warnings go away. => the FDB and MDB lists (used for refcounting on shared ports, aka CPU and DSA ports) will eventually be empty, but are not empty by the time we tear down those ports. Aka we are deleting them too soon. The addresses that DSA complains about are host-trapped addresses: the local addresses of the ports, and the MAC address of the bridge device. The problem is that offloading those entries happens from a deferred work item scheduled by the SWITCHDEV_FDB_DEL_TO_DEVICE handler, and this races with the teardown of the CPU and DSA ports where the refcounting is kept. In fact, not only it races, but fundamentally speaking, if we iterate through the port list linearly, we might end up tearing down the shared ports even before we delete a DSA user port which has a bridge upper. So as it turns out, we need to first tear down the user ports (and the unused ones, for no better place of doing that), then the shared ports (the CPU and DSA ports). In between, we need to ensure that all work items scheduled by our switchdev handlers (which only run for user ports, hence the reason why we tear them down first) have finished. Fixes: 161ca59d39e9 ("net: dsa: reference count the MDB entries at the cross-chip notifier level") Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/20210914134726.2305133-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- include/net/dsa.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index f9a17145255a..258867eff230 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -447,6 +447,11 @@ static inline bool dsa_port_is_user(struct dsa_port *dp) return dp->type == DSA_PORT_TYPE_USER; } +static inline bool dsa_port_is_unused(struct dsa_port *dp) +{ + return dp->type == DSA_PORT_TYPE_UNUSED; +} + static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) { return dsa_to_port(ds, p)->type == DSA_PORT_TYPE_UNUSED; -- cgit v1.2.3 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 --- include/linux/dsa/ocelot.h | 2 +- include/linux/packing.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') 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 -- cgit v1.2.3 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 --- include/linux/mdio.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include') 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 v1.2.3 From 0650bf52b31ff35dc6430fc2e37969c36baba724 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 17 Sep 2021 16:34:33 +0300 Subject: net: dsa: be compatible with masters which unregister on shutdown Lino reports that on his system with bcmgenet as DSA master and KSZ9897 as a switch, rebooting or shutting down never works properly. What does the bcmgenet driver have special to trigger this, that other DSA masters do not? It has an implementation of ->shutdown which simply calls its ->remove implementation. Otherwise said, it unregisters its network interface on shutdown. This message can be seen in a loop, and it hangs the reboot process there: unregister_netdevice: waiting for eth0 to become free. Usage count = 3 So why 3? A usage count of 1 is normal for a registered network interface, and any virtual interface which links itself as an upper of that will increment it via dev_hold. In the case of DSA, this is the call path: dsa_slave_create -> netdev_upper_dev_link -> __netdev_upper_dev_link -> __netdev_adjacent_dev_insert -> dev_hold So a DSA switch with 3 interfaces will result in a usage count elevated by two, and netdev_wait_allrefs will wait until they have gone away. Other stacked interfaces, like VLAN, watch NETDEV_UNREGISTER events and delete themselves, but DSA cannot just vanish and go poof, at most it can unbind itself from the switch devices, but that must happen strictly earlier compared to when the DSA master unregisters its net_device, so reacting on the NETDEV_UNREGISTER event is way too late. It seems that it is a pretty established pattern to have a driver's ->shutdown hook redirect to its ->remove hook, so the same code is executed regardless of whether the driver is unbound from the device, or the system is just shutting down. As Florian puts it, it is quite a big hammer for bcmgenet to unregister its net_device during shutdown, but having a common code path with the driver unbind helps ensure it is well tested. So DSA, for better or for worse, has to live with that and engage in an arms race of implementing the ->shutdown hook too, from all individual drivers, and do something sane when paired with masters that unregister their net_device there. The only sane thing to do, of course, is to unlink from the master. However, complications arise really quickly. The pattern of redirecting ->shutdown to ->remove is not unique to bcmgenet or even to net_device drivers. In fact, SPI controllers do it too (see dspi_shutdown -> dspi_remove), and presumably, I2C controllers and MDIO controllers do it too (this is something I have not researched too deeply, but even if this is not the case today, it is certainly plausible to happen in the future, and must be taken into consideration). Since DSA switches might be SPI devices, I2C devices, MDIO devices, the insane implication is that for the exact same DSA switch device, we might have both ->shutdown and ->remove getting called. So we need to do something with that insane environment. The pattern I've come up with is "if this, then not that", so if either ->shutdown or ->remove gets called, we set the device's drvdata to NULL, and in the other hook, we check whether the drvdata is NULL and just do nothing. This is probably not necessary for platform devices, just for devices on buses, but I would really insist for consistency among drivers, because when code is copy-pasted, it is not always copy-pasted from the best sources. So depending on whether the DSA switch's ->remove or ->shutdown will get called first, we cannot really guarantee even for the same driver if rebooting will result in the same code path on all platforms. But nonetheless, we need to do something minimally reasonable on ->shutdown too to fix the bug. Of course, the ->remove will do more (a full teardown of the tree, with all data structures freed, and this is why the bug was not caught for so long). The new ->shutdown method is kept separate from dsa_unregister_switch not because we couldn't have unregistered the switch, but simply in the interest of doing something quick and to the point. The big question is: does the DSA switch's ->shutdown get called earlier than the DSA master's ->shutdown? If not, there is still a risk that we might still trigger the WARN_ON in unregister_netdevice that says we are attempting to unregister a net_device which has uppers. That's no good. Although the reference to the master net_device won't physically go away even if DSA's ->shutdown comes afterwards, remember we have a dev_hold on it. The answer to that question lies in this comment above device_link_add: * A side effect of the link creation is re-ordering of dpm_list and the * devices_kset list by moving the consumer device and all devices depending * on it to the ends of these lists (that does not happen to devices that have * not been registered when this function is called). so the fact that DSA uses device_link_add towards its master is not exactly for nothing. device_shutdown() walks devices_kset from the back, so this is our guarantee that DSA's shutdown happens before the master's shutdown. Fixes: 2f1e8ea726e9 ("net: dsa: link interfaces with the DSA master to get rid of lockdep warnings") Link: https://lore.kernel.org/netdev/20210909095324.12978-1-LinoSanfilippo@gmx.de/ Reported-by: Lino Sanfilippo Signed-off-by: Vladimir Oltean Tested-by: Andrew Lunn Signed-off-by: David S. Miller --- include/net/dsa.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 258867eff230..6e29c0e080f6 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -1046,6 +1046,7 @@ static inline int dsa_ndo_eth_ioctl(struct net_device *dev, struct ifreq *ifr, void dsa_unregister_switch(struct dsa_switch *ds); int dsa_register_switch(struct dsa_switch *ds); +void dsa_switch_shutdown(struct dsa_switch *ds); struct dsa_switch *dsa_switch_find(int tree_index, int sw_index); #ifdef CONFIG_PM_SLEEP int dsa_switch_suspend(struct dsa_switch *ds); -- cgit v1.2.3 From 2dcb96bacce36021c2f3eaae0cef607b5bb71ede Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 18 Sep 2021 14:42:35 +0200 Subject: net: core: Correct the sock::sk_lock.owned lockdep annotations lock_sock_fast() and lock_sock_nested() contain lockdep annotations for the sock::sk_lock.owned 'mutex'. sock::sk_lock.owned is not a regular mutex. It is just lockdep wise equivalent. In fact it's an open coded trivial mutex implementation with some interesting features. sock::sk_lock.slock is a regular spinlock protecting the 'mutex' representation sock::sk_lock.owned which is a plain boolean. If 'owned' is true, then some other task holds the 'mutex', otherwise it is uncontended. As this locking construct is obviously endangered by lock ordering issues as any other locking primitive it got lockdep annotated via a dedicated dependency map sock::sk_lock.dep_map which has to be updated at the lock and unlock sites. lock_sock_nested() is a straight forward 'mutex' lock operation: might_sleep(); spin_lock_bh(sock::sk_lock.slock) while (!try_lock(sock::sk_lock.owned)) { spin_unlock_bh(sock::sk_lock.slock); wait_for_release(); spin_lock_bh(sock::sk_lock.slock); } The lockdep annotation for sock::sk_lock.owned is for unknown reasons _after_ the lock has been acquired, i.e. after the code block above and after releasing sock::sk_lock.slock, but inside the bottom halves disabled region: spin_unlock(sock::sk_lock.slock); mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); local_bh_enable(); The placement after the unlock is obvious because otherwise the mutex_acquire() would nest into the spin lock held region. But that's from the lockdep perspective still the wrong place: 1) The mutex_acquire() is issued _after_ the successful acquisition which is pointless because in a dead lock scenario this point is never reached which means that if the deadlock is the first instance of exposing the wrong lock order lockdep does not have a chance to detect it. 2) It only works because lockdep is rather lax on the context from which the mutex_acquire() is issued. Acquiring a mutex inside a bottom halves and therefore non-preemptible region is obviously invalid, except for a trylock which is clearly not the case here. This 'works' stops working on RT enabled kernels where the bottom halves serialization is done via a local lock, which exposes this misplacement because the 'mutex' and the local lock nest the wrong way around and lockdep complains rightfully about a lock inversion. The placement is wrong since the initial commit a5b5bb9a053a ("[PATCH] lockdep: annotate sk_locks") which introduced this. Fix it by moving the mutex_acquire() in front of the actual lock acquisition, which is what the regular mutex_lock() operation does as well. lock_sock_fast() is not that straight forward. It looks at the first glance like a convoluted trylock operation: spin_lock_bh(sock::sk_lock.slock) if (!sock::sk_lock.owned) return false; while (!try_lock(sock::sk_lock.owned)) { spin_unlock_bh(sock::sk_lock.slock); wait_for_release(); spin_lock_bh(sock::sk_lock.slock); } spin_unlock(sock::sk_lock.slock); mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); local_bh_enable(); return true; But that's not the case: lock_sock_fast() is an interesting optimization for short critical sections which can run with bottom halves disabled and sock::sk_lock.slock held. This allows to shortcut the 'mutex' operation in the non contended case by preventing other lockers to acquire sock::sk_lock.owned because they are blocked on sock::sk_lock.slock, which in turn avoids the overhead of doing the heavy processing in release_sock() including waking up wait queue waiters. In the contended case, i.e. when sock::sk_lock.owned == true the behavior is the same as lock_sock_nested(). Semantically this shortcut means, that the task acquired the 'mutex' even if it does not touch the sock::sk_lock.owned field in the non-contended case. Not telling lockdep about this shortcut acquisition is hiding potential lock ordering violations in the fast path. As a consequence the same reasoning as for the above lock_sock_nested() case vs. the placement of the lockdep annotation applies. The current placement of the lockdep annotation was just copied from the original lock_sock(), now renamed to lock_sock_nested(), implementation. Fix this by moving the mutex_acquire() in front of the actual lock acquisition and adding the corresponding mutex_release() into unlock_sock_fast(). Also document the fast path return case with a comment. Reported-by: Sebastian Siewior Signed-off-by: Thomas Gleixner Cc: netdev@vger.kernel.org Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 66a9a90f9558..c005c3c750e8 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1640,6 +1640,7 @@ static inline void unlock_sock_fast(struct sock *sk, bool slow) release_sock(sk); __release(&sk->sk_lock.slock); } else { + mutex_release(&sk->sk_lock.dep_map, _RET_IP_); spin_unlock_bh(&sk->sk_lock.slock); } } -- cgit v1.2.3 From fd292c189a979838622d5e03e15fa688c81dd50b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 17 Sep 2021 17:29:16 +0300 Subject: net: dsa: tear down devlink port regions when tearing down the devlink port on error Commit 86f8b1c01a0a ("net: dsa: Do not make user port errors fatal") decided it was fine to ignore errors on certain ports that fail to probe, and go on with the ports that do probe fine. Commit fb6ec87f7229 ("net: dsa: Fix type was not set for devlink port") noticed that devlink_port_type_eth_set(dlp, dp->slave); does not get called, and devlink notices after a timeout of 3600 seconds and prints a WARN_ON. So it went ahead to unregister the devlink port. And because there exists an UNUSED port flavour, we actually re-register the devlink port as UNUSED. Commit 08156ba430b4 ("net: dsa: Add devlink port regions support to DSA") added devlink port regions, which are set up by the driver and not by DSA. When we trigger the devlink port deregistration and reregistration as unused, devlink now prints another WARN_ON, from here: devlink_port_unregister: WARN_ON(!list_empty(&devlink_port->region_list)); So the port still has regions, which makes sense, because they were set up by the driver, and the driver doesn't know we're unregistering the devlink port. Somebody needs to tear them down, and optionally (actually it would be nice, to be consistent) set them up again for the new devlink port. But DSA's layering stays in our way quite badly here. The options I've considered are: 1. Introduce a function in devlink to just change a port's type and flavour. No dice, devlink keeps a lot of state, it really wants the port to not be registered when you set its parameters, so changing anything can only be done by destroying what we currently have and recreating it. 2. Make DSA cache the parameters passed to dsa_devlink_port_region_create, and the region returned, keep those in a list, then when the devlink port unregister needs to take place, the existing devlink regions are destroyed by DSA, and we replay the creation of new regions using the cached parameters. Problem: mv88e6xxx keeps the region pointers in chip->ports[port].region, and these will remain stale after DSA frees them. There are many things DSA can do, but updating mv88e6xxx's private pointers is not one of them. 3. Just let the driver do it (i.e. introduce a very specific method called ds->ops->port_reinit_as_unused, which unregisters its devlink port devlink regions, then the old devlink port, then registers the new one, then the devlink port regions for it). While it does work, as opposed to the others, it's pretty horrible from an API perspective and we can do better. 4. Introduce a new pair of methods, ->port_setup and ->port_teardown, which in the case of mv88e6xxx must register and unregister the devlink port regions. Call these 2 methods when the port must be reinitialized as unused. Naturally, I went for the 4th approach. Fixes: 08156ba430b4 ("net: dsa: Add devlink port regions support to DSA") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/net/dsa.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/net/dsa.h b/include/net/dsa.h index 6e29c0e080f6..d784e76113b8 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -585,8 +585,16 @@ struct dsa_switch_ops { int (*change_tag_protocol)(struct dsa_switch *ds, int port, enum dsa_tag_protocol proto); + /* Optional switch-wide initialization and destruction methods */ int (*setup)(struct dsa_switch *ds); void (*teardown)(struct dsa_switch *ds); + + /* Per-port initialization and destruction methods. Mandatory if the + * driver registers devlink port regions, optional otherwise. + */ + int (*port_setup)(struct dsa_switch *ds, int port); + void (*port_teardown)(struct dsa_switch *ds, int port); + u32 (*get_phy_flags)(struct dsa_switch *ds, int port); /* -- cgit v1.2.3 From 9caea0007601d3bc6debec04f8b4cd6f4c2394be Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sun, 19 Sep 2021 10:36:09 -0700 Subject: parisc: Declare pci_iounmap() parisc version only when CONFIG_PCI enabled Linus noticed odd declaration rules for pci_iounmap() in iomap.h and pci_iomap.h, where it dependend on either NO_GENERIC_PCI_IOPORT_MAP or GENERIC_IOMAP when CONFIG_PCI was disabled. Testing on parisc seems to indicate that we need pci_iounmap() only when CONFIG_PCI is enabled, so the declaration of pci_iounmap() can be moved cleanly into pci_iomap.h in sync with the declarations of pci_iomap(). Link: https://lore.kernel.org/all/CAHk-=wjRrh98pZoQ+AzfWmsTZacWxTJKXZ9eKU2X_0+jM=O8nw@mail.gmail.com/ Signed-off-by: Helge Deller Suggested-by: Linus Torvalds Fixes: 97a29d59fc22 ("[PARISC] fix compile break caused by iomap: make IOPORT/PCI mapping functions conditional") Cc: Arnd Bergmann Cc: Guenter Roeck Cc: Ulrich Teichert Cc: James Bottomley Signed-off-by: Linus Torvalds --- include/asm-generic/iomap.h | 10 ---------- include/asm-generic/pci_iomap.h | 3 +++ 2 files changed, 3 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h index 9b3eb6d86200..08237ae8b840 100644 --- a/include/asm-generic/iomap.h +++ b/include/asm-generic/iomap.h @@ -110,16 +110,6 @@ static inline void __iomem *ioremap_np(phys_addr_t offset, size_t size) } #endif -#ifdef CONFIG_PCI -/* Destroy a virtual mapping cookie for a PCI BAR (memory or IO) */ -struct pci_dev; -extern void pci_iounmap(struct pci_dev *dev, void __iomem *); -#elif defined(CONFIG_GENERIC_IOMAP) -struct pci_dev; -static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr) -{ } -#endif - #include #endif diff --git a/include/asm-generic/pci_iomap.h b/include/asm-generic/pci_iomap.h index df636c6d8e6c..5a2f9bf53384 100644 --- a/include/asm-generic/pci_iomap.h +++ b/include/asm-generic/pci_iomap.h @@ -18,6 +18,7 @@ extern void __iomem *pci_iomap_range(struct pci_dev *dev, int bar, extern void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar, unsigned long offset, unsigned long maxlen); +extern void pci_iounmap(struct pci_dev *dev, void __iomem *); /* Create a virtual mapping cookie for a port on a given PCI device. * Do not call this directly, it exists to make it easier for architectures * to override */ @@ -50,6 +51,8 @@ static inline void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar, { return NULL; } +static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr) +{ } #endif #endif /* __ASM_GENERIC_PCI_IOMAP_H */ -- cgit v1.2.3 From 316e8d79a0959c302b0c462ab64b069599f10eef Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 19 Sep 2021 17:13:35 -0700 Subject: pci_iounmap'2: Electric Boogaloo: try to make sense of it all Nathan Chancellor reports that the recent change to pci_iounmap in commit 9caea0007601 ("parisc: Declare pci_iounmap() parisc version only when CONFIG_PCI enabled") causes build errors on arm64. It took me about two hours to convince myself that I think I know what the logic of that mess of #ifdef's in the header file really aim to do, and rewrite it to be easier to follow. Famous last words. Anyway, the code has now been lifted from that grotty header file into lib/pci_iomap.c, and has fairly extensive comments about what the logic is. It also avoids indirecting through another confusing (and badly named) helper function that has other preprocessor config conditionals. Let's see what odd architecture did something else strange in this area to break things. But my arm64 cross build is clean. Fixes: 9caea0007601 ("parisc: Declare pci_iounmap() parisc version only when CONFIG_PCI enabled") Reported-by: Nathan Chancellor Cc: Helge Deller Cc: Arnd Bergmann Cc: Guenter Roeck Cc: Ulrich Teichert Cc: James Bottomley Signed-off-by: Linus Torvalds --- include/asm-generic/io.h | 26 +++----------------------- 1 file changed, 3 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index e93375c710b9..cc7338f9e0d1 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -1023,16 +1023,7 @@ static inline void __iomem *ioport_map(unsigned long port, unsigned int nr) port &= IO_SPACE_LIMIT; return (port > MMIO_UPPER_LIMIT) ? NULL : PCI_IOBASE + port; } -#define __pci_ioport_unmap __pci_ioport_unmap -static inline void __pci_ioport_unmap(void __iomem *p) -{ - uintptr_t start = (uintptr_t) PCI_IOBASE; - uintptr_t addr = (uintptr_t) p; - - if (addr >= start && addr < start + IO_SPACE_LIMIT) - return; - iounmap(p); -} +#define ARCH_HAS_GENERIC_IOPORT_MAP #endif #ifndef ioport_unmap @@ -1048,21 +1039,10 @@ extern void ioport_unmap(void __iomem *p); #endif /* CONFIG_HAS_IOPORT_MAP */ #ifndef CONFIG_GENERIC_IOMAP -struct pci_dev; -extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max); - -#ifndef __pci_ioport_unmap -static inline void __pci_ioport_unmap(void __iomem *p) {} -#endif - #ifndef pci_iounmap -#define pci_iounmap pci_iounmap -static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p) -{ - __pci_ioport_unmap(p); -} +#define ARCH_WANTS_GENERIC_PCI_IOUNMAP +#endif #endif -#endif /* CONFIG_GENERIC_IOMAP */ #ifndef xlate_dev_mem_ptr #define xlate_dev_mem_ptr xlate_dev_mem_ptr -- cgit v1.2.3 From 794d5b8a497ff053f56856472e2fae038fa761aa Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Fri, 17 Sep 2021 12:50:38 +0200 Subject: swiotlb-xen: this is PV-only on x86 The code is unreachable for HVM or PVH, and it also makes little sense in auto-translated environments. On Arm, with xen_{create,destroy}_contiguous_region() both being stubs, I have a hard time seeing what good the Xen specific variant does - the generic one ought to be fine for all purposes there. Still Arm code explicitly references symbols here, so the code will continue to be included there. Instead of making PCI_XEN's "select" conditional, simply drop it - SWIOTLB_XEN will be available unconditionally in the PV case anyway, and is - as explained above - dead code in non-PV environments. This in turn allows dropping the stubs for xen_{create,destroy}_contiguous_region(), the former of which was broken anyway - it failed to set the DMA handle output. Signed-off-by: Jan Beulich Reviewed-by: Christoph Hellwig Reviewed-by: Stefano Stabellini Link: https://lore.kernel.org/r/5947b8ae-fdc7-225c-4838-84712265fc1e@suse.com Signed-off-by: Juergen Gross --- include/xen/xen-ops.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include') diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 39a5580f8feb..db28e79b77ee 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -46,19 +46,7 @@ extern unsigned long *xen_contiguous_bitmap; int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, unsigned int address_bits, dma_addr_t *dma_handle); - void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order); -#else -static inline int xen_create_contiguous_region(phys_addr_t pstart, - unsigned int order, - unsigned int address_bits, - dma_addr_t *dma_handle) -{ - return 0; -} - -static inline void xen_destroy_contiguous_region(phys_addr_t pstart, - unsigned int order) { } #endif #if defined(CONFIG_XEN_PV) -- cgit v1.2.3 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 --- include/linux/pkeys.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') 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 v1.2.3 From a4869faf9642518145a8aa4b52e0d5ab0e7ee896 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 15 Sep 2021 17:07:15 +0800 Subject: scsi: core: Remove 'current_tag' The 'current_tag' field in struct scsi_device is unused now; remove it. Link: https://lore.kernel.org/r/1631696835-136198-4-git-send-email-john.garry@huawei.com Reviewed-by: Bart Van Assche Signed-off-by: Hannes Reinecke Signed-off-by: John Garry Signed-off-by: Martin K. Petersen --- include/scsi/scsi_device.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 09a17f6e93a7..b97e142a7ca9 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -146,7 +146,6 @@ struct scsi_device { struct scsi_vpd __rcu *vpd_pg83; struct scsi_vpd __rcu *vpd_pg80; struct scsi_vpd __rcu *vpd_pg89; - unsigned char current_tag; /* current tag */ struct scsi_target *sdev_target; blist_flags_t sdev_bflags; /* black/white flags as also found in -- cgit v1.2.3 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 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') 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); -- cgit v1.2.3 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 --- include/linux/tracehook.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') 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); } /* -- cgit v1.2.3 From 93368aab0efc87288cac65e99c9ed2e0ffc9e7d0 Mon Sep 17 00:00:00 2001 From: Gao Xiang Date: Tue, 21 Sep 2021 22:35:30 +0800 Subject: erofs: fix up erofs_lookup tracepoint Fix up a misuse that the filename pointer isn't always valid in the ring buffer, and we should copy the content instead. Link: https://lore.kernel.org/r/20210921143531.81356-1-hsiangkao@linux.alibaba.com Fixes: 13f06f48f7bf ("staging: erofs: support tracepoint") Cc: stable@vger.kernel.org # 4.19+ Reviewed-by: Chao Yu Signed-off-by: Gao Xiang --- include/trace/events/erofs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/trace/events/erofs.h b/include/trace/events/erofs.h index bf9806fd1306..db4f2cec8360 100644 --- a/include/trace/events/erofs.h +++ b/include/trace/events/erofs.h @@ -35,20 +35,20 @@ TRACE_EVENT(erofs_lookup, TP_STRUCT__entry( __field(dev_t, dev ) __field(erofs_nid_t, nid ) - __field(const char *, name ) + __string(name, dentry->d_name.name ) __field(unsigned int, flags ) ), TP_fast_assign( __entry->dev = dir->i_sb->s_dev; __entry->nid = EROFS_I(dir)->nid; - __entry->name = dentry->d_name.name; + __assign_str(name, dentry->d_name.name); __entry->flags = flags; ), TP_printk("dev = (%d,%d), pnid = %llu, name:%s, flags:%x", show_dev_nid(__entry), - __entry->name, + __get_str(name), __entry->flags) ); -- cgit v1.2.3 From 12064c1768439fa0882547010afae6b52aafa7af Mon Sep 17 00:00:00 2001 From: Jia He Date: Thu, 23 Sep 2021 11:35:57 +0800 Subject: Revert "ACPI: Add memory semantics to acpi_os_map_memory()" This reverts commit 437b38c51162f8b87beb28a833c4d5dc85fa864e. The memory semantics added in commit 437b38c51162 causes SystemMemory Operation region, whose address range is not described in the EFI memory map to be mapped as NormalNC memory on arm64 platforms (through acpi_os_map_memory() in acpi_ex_system_memory_space_handler()). This triggers the following abort on an ARM64 Ampere eMAG machine, because presumably the physical address range area backing the Opregion does not support NormalNC memory attributes driven on the bus. Internal error: synchronous external abort: 96000410 [#1] SMP Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.14.0+ #462 Hardware name: MiTAC RAPTOR EV-883832-X3-0001/RAPTOR, BIOS 0.14 02/22/2019 pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) [...snip...] Call trace: acpi_ex_system_memory_space_handler+0x26c/0x2c8 acpi_ev_address_space_dispatch+0x228/0x2c4 acpi_ex_access_region+0x114/0x268 acpi_ex_field_datum_io+0x128/0x1b8 acpi_ex_extract_from_field+0x14c/0x2ac acpi_ex_read_data_from_field+0x190/0x1b8 acpi_ex_resolve_node_to_value+0x1ec/0x288 acpi_ex_resolve_to_value+0x250/0x274 acpi_ds_evaluate_name_path+0xac/0x124 acpi_ds_exec_end_op+0x90/0x410 acpi_ps_parse_loop+0x4ac/0x5d8 acpi_ps_parse_aml+0xe0/0x2c8 acpi_ps_execute_method+0x19c/0x1ac acpi_ns_evaluate+0x1f8/0x26c acpi_ns_init_one_device+0x104/0x140 acpi_ns_walk_namespace+0x158/0x1d0 acpi_ns_initialize_devices+0x194/0x218 acpi_initialize_objects+0x48/0x50 acpi_init+0xe0/0x498 If the Opregion address range is not present in the EFI memory map there is no way for us to determine the memory attributes to use to map it - defaulting to NormalNC does not work (and it is not correct on a memory region that may have read side-effects) and therefore commit 437b38c51162 should be reverted, which means reverting back to the original behavior whereby address ranges that are mapped using acpi_os_map_memory() default to the safe devicenGnRnE attributes on ARM64 if the mapped address range is not defined in the EFI memory map. Fixes: 437b38c51162 ("ACPI: Add memory semantics to acpi_os_map_memory()") Signed-off-by: Jia He Acked-by: Lorenzo Pieralisi Acked-by: Catalin Marinas Signed-off-by: Rafael J. Wysocki --- include/acpi/acpi_io.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include') diff --git a/include/acpi/acpi_io.h b/include/acpi/acpi_io.h index a0212e67d6f4..027faa8883aa 100644 --- a/include/acpi/acpi_io.h +++ b/include/acpi/acpi_io.h @@ -14,14 +14,6 @@ static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys, } #endif -#ifndef acpi_os_memmap -static inline void __iomem *acpi_os_memmap(acpi_physical_address phys, - acpi_size size) -{ - return ioremap_cache(phys, size); -} -#endif - extern bool acpi_permanent_mmap; void __iomem __ref -- cgit v1.2.3 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 --- include/linux/buffer_head.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') 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 -- cgit v1.2.3 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 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') 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 -- cgit v1.2.3