From 02669b17a433c242a40f01f14b691c9c9d1f8a13 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 5 Dec 2018 16:37:03 -0500 Subject: XArray: Turn xa_init_flags into a static inline A regular xa_init_flags() put all dynamically-initialised XArrays into the same locking class. That leads to lockdep believing that taking one XArray lock while holding another is a deadlock. It's possible to work around some of these situations with separate locking classes for irq/bh/regular XArrays, and SINGLE_DEPTH_NESTING, but that's ugly, and it doesn't work for all situations (where we have completely unrelated XArrays). Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index f492e21c4aa2..4cf3cd128689 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -286,7 +286,6 @@ struct xarray { */ #define DEFINE_XARRAY_ALLOC(name) DEFINE_XARRAY_FLAGS(name, XA_FLAGS_ALLOC) -void xa_init_flags(struct xarray *, gfp_t flags); void *xa_load(struct xarray *, unsigned long index); void *xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *xa_erase(struct xarray *, unsigned long index); @@ -303,6 +302,24 @@ unsigned int xa_extract(struct xarray *, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t); void xa_destroy(struct xarray *); +/** + * xa_init_flags() - Initialise an empty XArray with flags. + * @xa: XArray. + * @flags: XA_FLAG values. + * + * If you need to initialise an XArray with special flags (eg you need + * to take the lock from interrupt context), use this function instead + * of xa_init(). + * + * Context: Any context. + */ +static inline void xa_init_flags(struct xarray *xa, gfp_t flags) +{ + spin_lock_init(&xa->xa_lock); + xa->xa_flags = flags; + xa->xa_head = NULL; +} + /** * xa_init() - Initialise an empty XArray. * @xa: XArray. -- cgit v1.2.3 From 4a31896c5b5a2715ecf4033426aa0a35066d92d6 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 17 Dec 2018 14:45:36 -0500 Subject: XArray: Change xa_for_each iterator There were three problems with this API: 1. It took too many arguments; almost all users wanted to iterate over every element in the array rather than a subset. 2. It required that 'index' be initialised before use, and there's no realistic way to make GCC catch that. 3. 'index' and 'entry' were the opposite way round from every other member of the XArray APIs. So split it into three different APIs: xa_for_each(xa, index, entry) xa_for_each_start(xa, index, entry, start) xa_for_each_marked(xa, index, entry, filter) Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 78 +++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 65 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 4cf3cd128689..3d0ce8b267e3 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -359,20 +359,45 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) } /** - * xa_for_each() - Iterate over a portion of an XArray. + * xa_for_each_start() - Iterate over a portion of an XArray. * @xa: XArray. + * @index: Index of @entry. * @entry: Entry retrieved from array. + * @start: First index to retrieve from array. + * + * During the iteration, @entry will have the value of the entry stored + * in @xa at @index. You may modify @index during the iteration if you + * want to skip or reprocess indices. It is safe to modify the array + * during the iteration. At the end of the iteration, @entry will be set + * to NULL and @index will have a value less than or equal to max. + * + * xa_for_each_start() is O(n.log(n)) while xas_for_each() is O(n). You have + * to handle your own locking with xas_for_each(), and if you have to unlock + * after each iteration, it will also end up being O(n.log(n)). + * xa_for_each_start() will spin if it hits a retry entry; if you intend to + * see retry entries, you should use the xas_for_each() iterator instead. + * The xas_for_each() iterator will expand into more inline code than + * xa_for_each_start(). + * + * Context: Any context. Takes and releases the RCU lock. + */ +#define xa_for_each_start(xa, index, entry, start) \ + for (index = start, \ + entry = xa_find(xa, &index, ULONG_MAX, XA_PRESENT); \ + entry; \ + entry = xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT)) + +/** + * xa_for_each() - Iterate over present entries in an XArray. + * @xa: XArray. * @index: Index of @entry. - * @max: Maximum index to retrieve from array. - * @filter: Selection criterion. + * @entry: Entry retrieved from array. * - * Initialise @index to the lowest index you want to retrieve from the - * array. During the iteration, @entry will have the value of the entry - * stored in @xa at @index. The iteration will skip all entries in the - * array which do not match @filter. You may modify @index during the - * iteration if you want to skip or reprocess indices. It is safe to modify - * the array during the iteration. At the end of the iteration, @entry will - * be set to NULL and @index will have a value less than or equal to max. + * During the iteration, @entry will have the value of the entry stored + * in @xa at @index. You may modify @index during the iteration if you want + * to skip or reprocess indices. It is safe to modify the array during the + * iteration. At the end of the iteration, @entry will be set to NULL and + * @index will have a value less than or equal to max. * * xa_for_each() is O(n.log(n)) while xas_for_each() is O(n). You have * to handle your own locking with xas_for_each(), and if you have to unlock @@ -383,9 +408,36 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) * * Context: Any context. Takes and releases the RCU lock. */ -#define xa_for_each(xa, entry, index, max, filter) \ - for (entry = xa_find(xa, &index, max, filter); entry; \ - entry = xa_find_after(xa, &index, max, filter)) +#define xa_for_each(xa, index, entry) \ + xa_for_each_start(xa, index, entry, 0) + +/** + * xa_for_each_marked() - Iterate over marked entries in an XArray. + * @xa: XArray. + * @index: Index of @entry. + * @entry: Entry retrieved from array. + * @filter: Selection criterion. + * + * During the iteration, @entry will have the value of the entry stored + * in @xa at @index. The iteration will skip all entries in the array + * which do not match @filter. You may modify @index during the iteration + * if you want to skip or reprocess indices. It is safe to modify the array + * during the iteration. At the end of the iteration, @entry will be set to + * NULL and @index will have a value less than or equal to max. + * + * xa_for_each_marked() is O(n.log(n)) while xas_for_each_marked() is O(n). + * You have to handle your own locking with xas_for_each(), and if you have + * to unlock after each iteration, it will also end up being O(n.log(n)). + * xa_for_each_marked() will spin if it hits a retry entry; if you intend to + * see retry entries, you should use the xas_for_each_marked() iterator + * instead. The xas_for_each_marked() iterator will expand into more inline + * code than xa_for_each_marked(). + * + * Context: Any context. Takes and releases the RCU lock. + */ +#define xa_for_each_marked(xa, index, entry, filter) \ + for (index = 0, entry = xa_find(xa, &index, ULONG_MAX, filter); \ + entry; entry = xa_find_after(xa, &index, ULONG_MAX, filter)) #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) -- cgit v1.2.3 From 76b4e52995654af260f14558e0e07b5b039ae202 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 28 Dec 2018 23:20:44 -0500 Subject: XArray: Permit storing 2-byte-aligned pointers On m68k, statically allocated pointers may only be two-byte aligned. This clashes with the XArray's method for tagging internal pointers. Permit storing these pointers in single slots (ie not in multislots). Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 3d0ce8b267e3..435c25b29079 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -176,7 +176,8 @@ static inline bool xa_is_internal(const void *entry) */ static inline bool xa_is_err(const void *entry) { - return unlikely(xa_is_internal(entry)); + return unlikely(xa_is_internal(entry) && + (unsigned long)entry >= -((MAX_ERRNO << 2) + 2)); } /** @@ -1039,8 +1040,8 @@ static inline bool xa_is_sibling(const void *entry) (entry < xa_mk_sibling(XA_CHUNK_SIZE - 1)); } -#define XA_ZERO_ENTRY xa_mk_internal(256) -#define XA_RETRY_ENTRY xa_mk_internal(257) +#define XA_RETRY_ENTRY xa_mk_internal(256) +#define XA_ZERO_ENTRY xa_mk_internal(257) /** * xa_is_zero() - Is the entry a zero entry? @@ -1064,6 +1065,17 @@ static inline bool xa_is_retry(const void *entry) return unlikely(entry == XA_RETRY_ENTRY); } +/** + * xa_is_advanced() - Is the entry only permitted for the advanced API? + * @entry: Entry to be stored in the XArray. + * + * Return: %true if the entry cannot be stored by the normal API. + */ +static inline bool xa_is_advanced(const void *entry) +{ + return xa_is_internal(entry) && (entry <= XA_RETRY_ENTRY); +} + /** * typedef xa_update_node_t - A callback function from the XArray. * @node: The node which is being processed -- cgit v1.2.3 From b0606fed6eece16a421034eca0bbea9a08b90e91 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 2 Jan 2019 13:57:03 -0500 Subject: XArray: Honour reserved entries in xa_insert xa_insert() should treat reserved entries as occupied, not as available. Also, it should treat requests to insert a NULL pointer as a request to reserve the slot. Add xa_insert_bh() and xa_insert_irq() for completeness. Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 110 +++++++++++++++++++++++++++++++------------------ 1 file changed, 71 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 435c25b29079..12244aa98a69 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -463,39 +463,12 @@ void *__xa_erase(struct xarray *, unsigned long index); void *__xa_store(struct xarray *, unsigned long index, void *entry, gfp_t); void *__xa_cmpxchg(struct xarray *, unsigned long index, void *old, void *entry, gfp_t); +int __xa_insert(struct xarray *, unsigned long index, void *entry, gfp_t); int __xa_alloc(struct xarray *, u32 *id, u32 max, void *entry, gfp_t); int __xa_reserve(struct xarray *, unsigned long index, gfp_t); void __xa_set_mark(struct xarray *, unsigned long index, xa_mark_t); void __xa_clear_mark(struct xarray *, unsigned long index, xa_mark_t); -/** - * __xa_insert() - Store this entry in the XArray unless another entry is - * already present. - * @xa: XArray. - * @index: Index into array. - * @entry: New entry. - * @gfp: Memory allocation flags. - * - * If you would rather see the existing entry in the array, use __xa_cmpxchg(). - * This function is for users who don't care what the entry is, only that - * one is present. - * - * Context: Any context. Expects xa_lock to be held on entry. May - * release and reacquire xa_lock if the @gfp flags permit. - * Return: 0 if the store succeeded. -EEXIST if another entry was present. - * -ENOMEM if memory could not be allocated. - */ -static inline int __xa_insert(struct xarray *xa, unsigned long index, - void *entry, gfp_t gfp) -{ - void *curr = __xa_cmpxchg(xa, index, NULL, entry, gfp); - if (!curr) - return 0; - if (xa_is_err(curr)) - return xa_err(curr); - return -EEXIST; -} - /** * xa_store_bh() - Store this entry in the XArray. * @xa: XArray. @@ -685,24 +658,83 @@ static inline void *xa_cmpxchg_irq(struct xarray *xa, unsigned long index, * @entry: New entry. * @gfp: Memory allocation flags. * - * If you would rather see the existing entry in the array, use xa_cmpxchg(). - * This function is for users who don't care what the entry is, only that - * one is present. + * Inserting a NULL entry will store a reserved entry (like xa_reserve()) + * if no entry is present. Inserting will fail if a reserved entry is + * present, even though loading from this index will return NULL. * - * Context: Process context. Takes and releases the xa_lock. - * May sleep if the @gfp flags permit. + * Context: Any context. Takes and releases the xa_lock. May sleep if + * the @gfp flags permit. * Return: 0 if the store succeeded. -EEXIST if another entry was present. * -ENOMEM if memory could not be allocated. */ static inline int xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { - void *curr = xa_cmpxchg(xa, index, NULL, entry, gfp); - if (!curr) - return 0; - if (xa_is_err(curr)) - return xa_err(curr); - return -EEXIST; + int err; + + xa_lock(xa); + err = __xa_insert(xa, index, entry, gfp); + xa_unlock(xa); + + return err; +} + +/** + * xa_insert_bh() - Store this entry in the XArray unless another entry is + * already present. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * Inserting a NULL entry will store a reserved entry (like xa_reserve()) + * if no entry is present. Inserting will fail if a reserved entry is + * present, even though loading from this index will return NULL. + * + * Context: Any context. Takes and releases the xa_lock while + * disabling softirqs. May sleep if the @gfp flags permit. + * Return: 0 if the store succeeded. -EEXIST if another entry was present. + * -ENOMEM if memory could not be allocated. + */ +static inline int xa_insert_bh(struct xarray *xa, unsigned long index, + void *entry, gfp_t gfp) +{ + int err; + + xa_lock_bh(xa); + err = __xa_insert(xa, index, entry, gfp); + xa_unlock_bh(xa); + + return err; +} + +/** + * xa_insert_irq() - Store this entry in the XArray unless another entry is + * already present. + * @xa: XArray. + * @index: Index into array. + * @entry: New entry. + * @gfp: Memory allocation flags. + * + * Inserting a NULL entry will store a reserved entry (like xa_reserve()) + * if no entry is present. Inserting will fail if a reserved entry is + * present, even though loading from this index will return NULL. + * + * Context: Process context. Takes and releases the xa_lock while + * disabling interrupts. May sleep if the @gfp flags permit. + * Return: 0 if the store succeeded. -EEXIST if another entry was present. + * -ENOMEM if memory could not be allocated. + */ +static inline int xa_insert_irq(struct xarray *xa, unsigned long index, + void *entry, gfp_t gfp) +{ + int err; + + xa_lock_irq(xa); + err = __xa_insert(xa, index, entry, gfp); + xa_unlock_irq(xa); + + return err; } /** -- cgit v1.2.3 From ba50bf1ce9a51fc97db58b96d01306aa70bc3979 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Mon, 17 Dec 2018 20:16:09 +0000 Subject: Drivers: hv: vmbus: Check for ring when getting debug info fc96df16a1ce is good and can already fix the "return stack garbage" issue, but let's also improve hv_ringbuffer_get_debuginfo(), which would silently return stack garbage, if people forget to check channel->state or ring_info->ring_buffer, when using the function in the future. Having an error check in the function would eliminate the potential risk. Add a Fixes tag to indicate the patch depdendency. Fixes: fc96df16a1ce ("Drivers: hv: vmbus: Return -EINVAL for the sys files for unopened channels") Cc: stable@vger.kernel.org Cc: K. Y. Srinivasan Cc: Haiyang Zhang Signed-off-by: Stephen Hemminger Signed-off-by: Dexuan Cui Signed-off-by: Sasha Levin --- include/linux/hyperv.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index f0885cc01db6..dcb6977afce9 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1159,8 +1159,9 @@ struct hv_ring_buffer_debug_info { u32 bytes_avail_towrite; }; -void hv_ringbuffer_get_debuginfo(const struct hv_ring_buffer_info *ring_info, - struct hv_ring_buffer_debug_info *debug_info); + +int hv_ringbuffer_get_debuginfo(const struct hv_ring_buffer_info *ring_info, + struct hv_ring_buffer_debug_info *debug_info); /* Vmbus interface */ #define vmbus_driver_register(driver) \ -- cgit v1.2.3 From ee46967fc6e74d412fe1ec15f77fdb8624bde2b0 Mon Sep 17 00:00:00 2001 From: Peter Hutterer Date: Wed, 9 Jan 2019 13:50:18 +1000 Subject: HID: core: replace the collection tree pointers with indices Previously, the pointer to the parent collection was stored. If a device exceeds 16 collections (HID_DEFAULT_NUM_COLLECTIONS), the array to store the collections is reallocated, the pointer to the parent collection becomes invalid. Replace the pointers with an index-based lookup into the collections array. Fixes: c53431eb696f3c ("HID: core: store the collections as a basic tree") Reported-by: Pandruvada, Srinivas Signed-off-by: Peter Hutterer Tested-by: Kyle Pelton Signed-off-by: Jiri Kosina --- include/linux/hid.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index d99287327ef2..992bbb7196df 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -430,7 +430,7 @@ struct hid_local { */ struct hid_collection { - struct hid_collection *parent; + int parent_idx; /* device->collection */ unsigned type; unsigned usage; unsigned level; @@ -658,7 +658,7 @@ struct hid_parser { unsigned int *collection_stack; unsigned int collection_stack_ptr; unsigned int collection_stack_size; - struct hid_collection *active_collection; + int active_collection_idx; /* device->collection */ struct hid_device *device; unsigned int scan_flags; }; -- cgit v1.2.3 From ee17e5d6201c66492a0e8053190fca2ed2b8457d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 12 Jan 2019 11:48:20 -0600 Subject: signal: Make siginmask safe when passed a signal of 0 Eric Biggers reported: > The following commit, which went into v4.20, introduced undefined behavior when > sys_rt_sigqueueinfo() is called with sig=0: > > commit 4ce5f9c9e7546915c559ffae594e6d73f918db00 > Author: Eric W. Biederman > Date: Tue Sep 25 12:59:31 2018 +0200 > > signal: Use a smaller struct siginfo in the kernel > > In sig_specific_sicodes(), used from known_siginfo_layout(), the expression > '1ULL << ((sig)-1)' is undefined as it evaluates to 1ULL << 4294967295. > > Reproducer: > > #include > #include > #include > > int main(void) > { > siginfo_t si = { .si_code = 1 }; > syscall(__NR_rt_sigqueueinfo, 0, 0, &si); > } > > UBSAN report for v5.0-rc1: > > UBSAN: Undefined behaviour in kernel/signal.c:2946:7 > shift exponent 4294967295 is too large for 64-bit type 'long unsigned int' > CPU: 2 PID: 346 Comm: syz_signal Not tainted 5.0.0-rc1 #25 > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 > Call Trace: > __dump_stack lib/dump_stack.c:77 [inline] > dump_stack+0x70/0xa5 lib/dump_stack.c:113 > ubsan_epilogue+0xd/0x40 lib/ubsan.c:159 > __ubsan_handle_shift_out_of_bounds+0x12c/0x170 lib/ubsan.c:425 > known_siginfo_layout+0xae/0xe0 kernel/signal.c:2946 > post_copy_siginfo_from_user kernel/signal.c:3009 [inline] > __copy_siginfo_from_user+0x35/0x60 kernel/signal.c:3035 > __do_sys_rt_sigqueueinfo kernel/signal.c:3553 [inline] > __se_sys_rt_sigqueueinfo kernel/signal.c:3549 [inline] > __x64_sys_rt_sigqueueinfo+0x31/0x70 kernel/signal.c:3549 > do_syscall_64+0x4c/0x1b0 arch/x86/entry/common.c:290 > entry_SYSCALL_64_after_hwframe+0x49/0xbe > RIP: 0033:0x433639 > Code: c4 18 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b 27 00 00 c3 66 2e 0f 1f 84 00 00 00 00 > RSP: 002b:00007fffcb289fc8 EFLAGS: 00000246 ORIG_RAX: 0000000000000081 > RAX: ffffffffffffffda RBX: 00000000004002e0 RCX: 0000000000433639 > RDX: 00007fffcb289fd0 RSI: 0000000000000000 RDI: 0000000000000000 > RBP: 00000000006b2018 R08: 000000000000004d R09: 0000000000000000 > R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000401560 > R13: 00000000004015f0 R14: 0000000000000000 R15: 0000000000000000 I have looked at the other callers of siginmask and they all appear to in locations where sig can not be zero. I have looked at the code generation of adding an extra test against zero and gcc was able with a simple decrement instruction to combine the two tests together. So the at most adding this test cost a single cpu cycle. In practice that decrement instruction was already present as part of the mask comparison, so the only change was when the instruction was executed. So given that it is cheap, and obviously correct to update siginmask to verify the signal is not zero. Fix this issue there to avoid any future problems. Reported-by: Eric Biggers Fixes: 4ce5f9c9e754 ("signal: Use a smaller struct siginfo in the kernel") Signed-off-by: "Eric W. Biederman" --- include/linux/signal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index cc7e2c1cd444..9702016734b1 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -392,7 +392,7 @@ extern bool unhandled_signal(struct task_struct *tsk, int sig); #endif #define siginmask(sig, mask) \ - ((sig) < SIGRTMIN && (rt_sigmask(sig) & (mask))) + ((sig) > 0 && (sig) < SIGRTMIN && (rt_sigmask(sig) & (mask))) #define SIG_KERNEL_ONLY_MASK (\ rt_sigmask(SIGKILL) | rt_sigmask(SIGSTOP)) -- cgit v1.2.3 From 19ba9ecf24189bd74d070aa1b1c4bcb9fe4ae849 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Mon, 14 Jan 2019 11:40:47 +0300 Subject: XArray: Fix typo in comment Seems copy and paste typo, not a big deal but still for consistency sake better to fix. Signed-off-by: Cyrill Gorcunov Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 12244aa98a69..7da665f5cb20 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -496,7 +496,7 @@ static inline void *xa_store_bh(struct xarray *xa, unsigned long index, } /** - * xa_store_irq() - Erase this entry from the XArray. + * xa_store_irq() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. -- cgit v1.2.3 From 1950f462916edc9581168ca8d5882a8101e8bbcf Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Mon, 14 Jan 2019 08:19:22 +0100 Subject: HID: core: simplify active collection tracking Manually tracking an active collection to set collection parents is not necessary, we just have to look one step back into the collection stack to find the correct parent. Signed-off-by: Philipp Zabel Reviewed-by: Peter Hutterer Signed-off-by: Benjamin Tissoires --- include/linux/hid.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index 992bbb7196df..f9707d1dcb58 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -658,7 +658,6 @@ struct hid_parser { unsigned int *collection_stack; unsigned int collection_stack_ptr; unsigned int collection_stack_size; - int active_collection_idx; /* device->collection */ struct hid_device *device; unsigned int scan_flags; }; -- cgit v1.2.3 From edcddd4c879af48ec922d680b2d56834c085683b Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Thu, 17 Jan 2019 07:15:35 -0500 Subject: XArray: Fix an arithmetic error in xa_is_err There is a math problem here which leads to a lot of static checker warnings for me: net/sunrpc/clnt.c:451 rpc_new_client() error: (-4096) too low for ERR_PTR Error values are from -1 to -4095 or from 0xffffffff to 0xfffff001 in hexadecimal. (I am assuming a 32 bit system for simplicity). We are using the lowest two bits to hold some internal XArray data so the error is shifted two spaces to the left. 0xfffff001 << 2 is 0xffffc004. And finally we want to check that BIT(1) is set so we add 2 which gives us 0xffffc006. In other words, we should be checking that "entry >= 0xffffc006", but the check is actually testing if "entry >= 0xffffc002". Fixes: 76b4e5299565 ("XArray: Permit storing 2-byte-aligned pointers") Signed-off-by: Dan Carpenter [Use xa_mk_internal() instead of changing the bracketing] Signed-off-by: Matthew Wilcox --- include/linux/xarray.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 7da665f5cb20..5d9d318bcf7a 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -177,7 +177,7 @@ static inline bool xa_is_internal(const void *entry) static inline bool xa_is_err(const void *entry) { return unlikely(xa_is_internal(entry) && - (unsigned long)entry >= -((MAX_ERRNO << 2) + 2)); + entry >= xa_mk_internal(-MAX_ERRNO)); } /** -- cgit v1.2.3 From 70921ae25f944423f0abf096f73455c586da0652 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Tue, 8 Jan 2019 17:04:32 -0700 Subject: genirq: Fix the kerneldoc comment for struct irq_affinity_desc A recent commit added a new field but did not update the kerneldoc comment, leading to this build warning: ./include/linux/interrupt.h:268: warning: Function parameter or member 'is_managed' not described in 'irq_affinity_desc' Add the missing information, making the docs build 0.001% quieter. Fixes: c410abbbacb9 ("genirq/affinity: Add is_managed to struct irq_affinity_desc") Signed-off-by: Jonathan Corbet Signed-off-by: Thomas Gleixner Cc: Dou Liyang Link: https://lkml.kernel.org/r/20190108170432.59bae8a6@lwn.net --- include/linux/interrupt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index c672f34235e7..4a728dba02e2 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -260,6 +260,7 @@ struct irq_affinity { /** * struct irq_affinity_desc - Interrupt affinity descriptor * @mask: cpumask to hold the affinity assignment + * @is_managed: 1 if the interrupt is managed internally */ struct irq_affinity_desc { struct cpumask mask; -- cgit v1.2.3 From e6018c0f5c996e61639adce6a0697391a2861916 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 17 Dec 2018 10:14:53 +0100 Subject: sched/wake_q: Document wake_q_add() The only guarantee provided by wake_q_add() is that a wakeup will happen after it, it does _NOT_ guarantee the wakeup will be delayed until the matching wake_up_q(). If wake_q_add() fails the cmpxchg() a concurrent wakeup is pending and that can happen at any time after the cmpxchg(). This means we should not rely on the wakeup happening at wake_q_up(), but should be ready for wake_q_add() to issue the wakeup. The delay; if provided (most likely); should only result in more efficient behaviour. Reported-by: Yongji Xie Signed-off-by: Peter Zijlstra (Intel) Cc: Davidlohr Bueso Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Waiman Long Cc: Will Deacon Signed-off-by: Ingo Molnar --- include/linux/sched/wake_q.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h index 10b19a192b2d..545f37138057 100644 --- a/include/linux/sched/wake_q.h +++ b/include/linux/sched/wake_q.h @@ -24,9 +24,13 @@ * called near the end of a function. Otherwise, the list can be * re-initialized for later re-use by wake_q_init(). * - * Note that this can cause spurious wakeups. schedule() callers + * NOTE that this can cause spurious wakeups. schedule() callers * must ensure the call is done inside a loop, confirming that the * wakeup condition has in fact occurred. + * + * NOTE that there is no guarantee the wakeup will happen any later than the + * wake_q_add() location. Therefore task must be ready to be woken at the + * location of the wake_q_add(). */ #include -- cgit v1.2.3 From 1cd7386549f9b6f2f230da54aa9e7fe2d6c216d2 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sat, 19 Jan 2019 08:45:56 -0800 Subject: libnvdimm/security: Require nvdimm_security_setup_events() to succeed The following warning: ACPI0012:00: security event setup failed: -19 ...is meant to capture exceptional failures of sysfs_get_dirent(), however it will also fail in the common case when security support is disabled. A few issues: 1/ A dev_warn() report for a common case is too chatty 2/ The setup of this notifier is generic, no need for it to be driven from the nfit driver, it can exist completely in the core. 3/ If it fails for any reason besides security support being disabled, that's fatal and should abort DIMM activation. Userspace may hang if it never gets overwrite notifications. 4/ The dirent needs to be released. Move the call to the core 'dimm' driver, make it conditional on security support being active, make it fatal for the exceptional case, add the missing sysfs_put() at device disable time. Fixes: 7d988097c546 ("...Add security DSM overwrite support") Reviewed-by: Dave Jiang Signed-off-by: Dan Williams --- include/linux/libnvdimm.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 7315977b64da..ad609617aeb8 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -235,7 +235,6 @@ static inline struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, cmd_mask, num_flush, flush_wpq, NULL, NULL); } -int nvdimm_security_setup_events(struct nvdimm *nvdimm); const struct nd_cmd_desc *nd_cmd_dimm_desc(int cmd); const struct nd_cmd_desc *nd_cmd_bus_desc(int cmd); u32 nd_cmd_in_size(struct nvdimm *nvdimm, int cmd, -- cgit v1.2.3 From 7fc5854f8c6efae9e7624970ab49a1eac2faefb1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Dec 2017 08:38:30 -0800 Subject: writeback: synchronize sync(2) against cgroup writeback membership switches sync_inodes_sb() can race against cgwb (cgroup writeback) membership switches and fail to writeback some inodes. For example, if an inode switches to another wb while sync_inodes_sb() is in progress, the new wb might not be visible to bdi_split_work_to_wbs() at all or the inode might jump from a wb which hasn't issued writebacks yet to one which already has. This patch adds backing_dev_info->wb_switch_rwsem to synchronize cgwb switch path against sync_inodes_sb() so that sync_inodes_sb() is guaranteed to see all the target wbs and inodes can't jump wbs to escape syncing. v2: Fixed misplaced rwsem init. Spotted by Jiufei. Signed-off-by: Tejun Heo Reported-by: Jiufei Xue Link: http://lkml.kernel.org/r/dc694ae2-f07f-61e1-7097-7c8411cee12d@gmail.com Acked-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/backing-dev-defs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index c31157135598..07e02d6df5ad 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -190,6 +190,7 @@ struct backing_dev_info { struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ struct rb_root cgwb_congested_tree; /* their congested states */ struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */ + struct rw_semaphore wb_switch_rwsem; /* no cgwb switch while syncing */ #else struct bdi_writeback_congested *wb_congested; #endif -- cgit v1.2.3 From c75860e48a7634ff8dc050842211f79a0e4e6c46 Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Sun, 20 Jan 2019 11:36:38 +0200 Subject: qed: Add infrastructure for error detection and recovery This patch adds the detection and handling of a parity error ("process kill event"), including the update of the protocol drivers, and the prevention of any HW access that will lead to device access towards the host while recovery is in progress. It also provides the means for the protocol drivers to trigger a recovery process on their decision. Signed-off-by: Tomer Tayar Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 91c536a01b56..c2a1b7dbe4eb 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -764,6 +764,7 @@ struct qed_probe_params { u32 dp_module; u8 dp_level; bool is_vf; + bool recov_in_prog; }; #define QED_DRV_VER_STR_SIZE 12 @@ -810,6 +811,7 @@ struct qed_common_cb_ops { void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc); void (*link_update)(void *dev, struct qed_link_output *link); + void (*schedule_recovery_handler)(void *dev); void (*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type); void (*get_generic_tlv_data)(void *dev, struct qed_generic_tlvs *data); void (*get_protocol_tlv_data)(void *dev, void *data); @@ -1057,6 +1059,24 @@ struct qed_common_ops { int (*db_recovery_del)(struct qed_dev *cdev, void __iomem *db_addr, void *db_data); +/** + * @brief recovery_process - Trigger a recovery process + * + * @param cdev + * + * @return 0 on success, error otherwise. + */ + int (*recovery_process)(struct qed_dev *cdev); + +/** + * @brief recovery_prolog - Execute the prolog operations of a recovery process + * + * @param cdev + * + * @return 0 on success, error otherwise. + */ + int (*recovery_prolog)(struct qed_dev *cdev); + /** * @brief update_drv_state - API to inform the change in the driver state. * -- cgit v1.2.3 From 278396de78a9b59a692bc140233bde3a9d8a8a31 Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Sun, 20 Jan 2019 11:36:39 +0200 Subject: qede: Error recovery process This patch adds the error recovery process in the qede driver. The process includes a partial/customized driver unload and load, which allows it to look like a short suspend period to the kernel while preserving the net devices' state. Signed-off-by: Tomer Tayar Signed-off-by: Ariel Elior Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qede_rdma.h | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qede_rdma.h b/include/linux/qed/qede_rdma.h index 9904617a9730..e29d7199c10e 100644 --- a/include/linux/qed/qede_rdma.h +++ b/include/linux/qed/qede_rdma.h @@ -55,6 +55,16 @@ struct qede_rdma_event_work { enum qede_rdma_event event; }; +enum qede_rdma_probe_mode { + QEDE_RDMA_PROBE_NORMAL, + QEDE_RDMA_PROBE_RECOVERY, +}; + +enum qede_rdma_remove_mode { + QEDE_RDMA_REMOVE_NORMAL, + QEDE_RDMA_REMOVE_RECOVERY, +}; + struct qedr_driver { unsigned char name[32]; @@ -74,21 +84,24 @@ void qede_rdma_unregister_driver(struct qedr_driver *drv); bool qede_rdma_supported(struct qede_dev *dev); #if IS_ENABLED(CONFIG_QED_RDMA) -int qede_rdma_dev_add(struct qede_dev *dev); +int qede_rdma_dev_add(struct qede_dev *dev, enum qede_rdma_probe_mode mode); void qede_rdma_dev_event_open(struct qede_dev *dev); void qede_rdma_dev_event_close(struct qede_dev *dev); -void qede_rdma_dev_remove(struct qede_dev *dev); +void qede_rdma_dev_remove(struct qede_dev *dev, + enum qede_rdma_remove_mode mode); void qede_rdma_event_changeaddr(struct qede_dev *edr); #else -static inline int qede_rdma_dev_add(struct qede_dev *dev) +static inline int qede_rdma_dev_add(struct qede_dev *dev, + enum qede_rdma_probe_mode mode) { return 0; } static inline void qede_rdma_dev_event_open(struct qede_dev *dev) {} static inline void qede_rdma_dev_event_close(struct qede_dev *dev) {} -static inline void qede_rdma_dev_remove(struct qede_dev *dev) {} +static inline void qede_rdma_dev_remove(struct qede_dev *dev, + enum qede_rdma_remove_mode mode) {} static inline void qede_rdma_event_changeaddr(struct qede_dev *edr) {} #endif #endif -- cgit v1.2.3 From 8367de2c99a13d35960a51d6084631c883e93a4d Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 24 Jan 2019 18:20:14 +0900 Subject: block: Fix comment typo Fix typo in REQ_OP_ZONE_RESET description. Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 5c7e7f859a24..d66bf5f32610 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -287,7 +287,7 @@ enum req_opf { REQ_OP_DISCARD = 3, /* securely erase sectors */ REQ_OP_SECURE_ERASE = 5, - /* seset a zone write pointer */ + /* reset a zone write pointer */ REQ_OP_ZONE_RESET = 6, /* write the same sector many times */ REQ_OP_WRITE_SAME = 7, -- cgit v1.2.3 From 3b707c3008cad04604c1f50e39f456621821c414 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Maciej=20=C5=BBenczykowski?= Date: Thu, 24 Jan 2019 03:07:02 -0800 Subject: net: dev_is_mac_header_xmit() true for ARPHRD_RAWIP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit __bpf_redirect() and act_mirred checks this boolean to determine whether to prefix an ethernet header. Signed-off-by: Maciej Żenczykowski Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/if_arp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index 6756fea18b69..e44746de95cd 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -54,6 +54,7 @@ static inline bool dev_is_mac_header_xmit(const struct net_device *dev) case ARPHRD_IPGRE: case ARPHRD_VOID: case ARPHRD_NONE: + case ARPHRD_RAWIP: return false; default: return true; -- cgit v1.2.3 From abfd04f738c2625f63e04c8fc7cadb3b7a70d580 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 25 Jan 2019 15:32:28 -0800 Subject: qed: Revert error handling changes. This is new code and not bug fixes. This reverts all changes added by merge commit 8fb18be93efd7292d6ee403b9f61af1008239639 Signed-off-by: David S. Miller --- include/linux/qed/qed_if.h | 20 -------------------- include/linux/qed/qede_rdma.h | 21 ++++----------------- 2 files changed, 4 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index c2a1b7dbe4eb..91c536a01b56 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -764,7 +764,6 @@ struct qed_probe_params { u32 dp_module; u8 dp_level; bool is_vf; - bool recov_in_prog; }; #define QED_DRV_VER_STR_SIZE 12 @@ -811,7 +810,6 @@ struct qed_common_cb_ops { void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc); void (*link_update)(void *dev, struct qed_link_output *link); - void (*schedule_recovery_handler)(void *dev); void (*dcbx_aen)(void *dev, struct qed_dcbx_get *get, u32 mib_type); void (*get_generic_tlv_data)(void *dev, struct qed_generic_tlvs *data); void (*get_protocol_tlv_data)(void *dev, void *data); @@ -1059,24 +1057,6 @@ struct qed_common_ops { int (*db_recovery_del)(struct qed_dev *cdev, void __iomem *db_addr, void *db_data); -/** - * @brief recovery_process - Trigger a recovery process - * - * @param cdev - * - * @return 0 on success, error otherwise. - */ - int (*recovery_process)(struct qed_dev *cdev); - -/** - * @brief recovery_prolog - Execute the prolog operations of a recovery process - * - * @param cdev - * - * @return 0 on success, error otherwise. - */ - int (*recovery_prolog)(struct qed_dev *cdev); - /** * @brief update_drv_state - API to inform the change in the driver state. * diff --git a/include/linux/qed/qede_rdma.h b/include/linux/qed/qede_rdma.h index e29d7199c10e..9904617a9730 100644 --- a/include/linux/qed/qede_rdma.h +++ b/include/linux/qed/qede_rdma.h @@ -55,16 +55,6 @@ struct qede_rdma_event_work { enum qede_rdma_event event; }; -enum qede_rdma_probe_mode { - QEDE_RDMA_PROBE_NORMAL, - QEDE_RDMA_PROBE_RECOVERY, -}; - -enum qede_rdma_remove_mode { - QEDE_RDMA_REMOVE_NORMAL, - QEDE_RDMA_REMOVE_RECOVERY, -}; - struct qedr_driver { unsigned char name[32]; @@ -84,24 +74,21 @@ void qede_rdma_unregister_driver(struct qedr_driver *drv); bool qede_rdma_supported(struct qede_dev *dev); #if IS_ENABLED(CONFIG_QED_RDMA) -int qede_rdma_dev_add(struct qede_dev *dev, enum qede_rdma_probe_mode mode); +int qede_rdma_dev_add(struct qede_dev *dev); void qede_rdma_dev_event_open(struct qede_dev *dev); void qede_rdma_dev_event_close(struct qede_dev *dev); -void qede_rdma_dev_remove(struct qede_dev *dev, - enum qede_rdma_remove_mode mode); +void qede_rdma_dev_remove(struct qede_dev *dev); void qede_rdma_event_changeaddr(struct qede_dev *edr); #else -static inline int qede_rdma_dev_add(struct qede_dev *dev, - enum qede_rdma_probe_mode mode) +static inline int qede_rdma_dev_add(struct qede_dev *dev) { return 0; } static inline void qede_rdma_dev_event_open(struct qede_dev *dev) {} static inline void qede_rdma_dev_event_close(struct qede_dev *dev) {} -static inline void qede_rdma_dev_remove(struct qede_dev *dev, - enum qede_rdma_remove_mode mode) {} +static inline void qede_rdma_dev_remove(struct qede_dev *dev) {} static inline void qede_rdma_event_changeaddr(struct qede_dev *edr) {} #endif #endif -- cgit v1.2.3 From 13054abbaa4f1fd4e6f3b4b63439ec033b4c8035 Mon Sep 17 00:00:00 2001 From: Vladis Dronov Date: Tue, 29 Jan 2019 11:58:35 +0100 Subject: HID: debug: fix the ring buffer implementation Ring buffer implementation in hid_debug_event() and hid_debug_events_read() is strange allowing lost or corrupted data. After commit 717adfdaf147 ("HID: debug: check length before copy_to_user()") it is possible to enter an infinite loop in hid_debug_events_read() by providing 0 as count, this locks up a system. Fix this by rewriting the ring buffer implementation with kfifo and simplify the code. This fixes CVE-2019-3819. v2: fix an execution logic and add a comment v3: use __set_current_state() instead of set_current_state() Link: https://bugzilla.redhat.com/show_bug.cgi?id=1669187 Cc: stable@vger.kernel.org # v4.18+ Fixes: cd667ce24796 ("HID: use debugfs for events/reports dumping") Fixes: 717adfdaf147 ("HID: debug: check length before copy_to_user()") Signed-off-by: Vladis Dronov Reviewed-by: Oleg Nesterov Signed-off-by: Benjamin Tissoires --- include/linux/hid-debug.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid-debug.h b/include/linux/hid-debug.h index 8663f216c563..2d6100edf204 100644 --- a/include/linux/hid-debug.h +++ b/include/linux/hid-debug.h @@ -24,7 +24,10 @@ #ifdef CONFIG_DEBUG_FS +#include + #define HID_DEBUG_BUFSIZE 512 +#define HID_DEBUG_FIFOSIZE 512 void hid_dump_input(struct hid_device *, struct hid_usage *, __s32); void hid_dump_report(struct hid_device *, int , u8 *, int); @@ -37,11 +40,8 @@ void hid_debug_init(void); void hid_debug_exit(void); void hid_debug_event(struct hid_device *, char *); - struct hid_debug_list { - char *hid_debug_buf; - int head; - int tail; + DECLARE_KFIFO_PTR(hid_debug_fifo, char); struct fasync_struct *fasync; struct hid_device *hdev; struct list_head node; @@ -64,4 +64,3 @@ struct hid_debug_list { #endif #endif - -- cgit v1.2.3 From b284909abad48b07d3071a9fc9b5692b3e64914b Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 30 Jan 2019 07:13:58 -0600 Subject: cpu/hotplug: Fix "SMT disabled by BIOS" detection for KVM With the following commit: 73d5e2b47264 ("cpu/hotplug: detect SMT disabled by BIOS") ... the hotplug code attempted to detect when SMT was disabled by BIOS, in which case it reported SMT as permanently disabled. However, that code broke a virt hotplug scenario, where the guest is booted with only primary CPU threads, and a sibling is brought online later. The problem is that there doesn't seem to be a way to reliably distinguish between the HW "SMT disabled by BIOS" case and the virt "sibling not yet brought online" case. So the above-mentioned commit was a bit misguided, as it permanently disabled SMT for both cases, preventing future virt sibling hotplugs. Going back and reviewing the original problems which were attempted to be solved by that commit, when SMT was disabled in BIOS: 1) /sys/devices/system/cpu/smt/control showed "on" instead of "notsupported"; and 2) vmx_vm_init() was incorrectly showing the L1TF_MSG_SMT warning. I'd propose that we instead consider #1 above to not actually be a problem. Because, at least in the virt case, it's possible that SMT wasn't disabled by BIOS and a sibling thread could be brought online later. So it makes sense to just always default the smt control to "on" to allow for that possibility (assuming cpuid indicates that the CPU supports SMT). The real problem is #2, which has a simple fix: change vmx_vm_init() to query the actual current SMT state -- i.e., whether any siblings are currently online -- instead of looking at the SMT "control" sysfs value. So fix it by: a) reverting the original "fix" and its followup fix: 73d5e2b47264 ("cpu/hotplug: detect SMT disabled by BIOS") bc2d8d262cba ("cpu/hotplug: Fix SMT supported evaluation") and b) changing vmx_vm_init() to query the actual current SMT state -- instead of the sysfs control value -- to determine whether the L1TF warning is needed. This also requires the 'sched_smt_present' variable to exported, instead of 'cpu_smt_control'. Fixes: 73d5e2b47264 ("cpu/hotplug: detect SMT disabled by BIOS") Reported-by: Igor Mammedov Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Cc: Joe Mario Cc: Jiri Kosina Cc: Peter Zijlstra Cc: kvm@vger.kernel.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/e3a85d585da28cc333ecbc1e78ee9216e6da9396.1548794349.git.jpoimboe@redhat.com --- include/linux/cpu.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 218df7f4d3e1..5041357d0297 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -180,12 +180,10 @@ enum cpuhp_smt_control { #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT) extern enum cpuhp_smt_control cpu_smt_control; extern void cpu_smt_disable(bool force); -extern void cpu_smt_check_topology_early(void); extern void cpu_smt_check_topology(void); #else # define cpu_smt_control (CPU_SMT_ENABLED) static inline void cpu_smt_disable(bool force) { } -static inline void cpu_smt_check_topology_early(void) { } static inline void cpu_smt_check_topology(void) { } #endif -- cgit v1.2.3 From 7d10f70fc198877b43d92bdcd7604279788b9568 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 30 Jan 2019 13:52:37 -0500 Subject: fs: Don't need to put list_lru into its own cacheline The list_lru structure is essentially just a pointer to a table of per-node LRU lists. Even if CONFIG_MEMCG_KMEM is defined, the list field is just used for LRU list registration and shrinker_id is set at initialization. Those fields won't need to be touched that often. So there is no point to make the list_lru structures to sit in their own cachelines. Signed-off-by: Waiman Long Reviewed-by: Dave Chinner Signed-off-by: Linus Torvalds --- include/linux/fs.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 811c77743dad..29d8e2cfed0e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1479,11 +1479,12 @@ struct super_block { struct user_namespace *s_user_ns; /* - * Keep the lru lists last in the structure so they always sit on their - * own individual cachelines. + * The list_lru structure is essentially just a pointer to a table + * of per-node lru lists, each of which has its own spinlock. + * There is no need to put them into separate cachelines. */ - struct list_lru s_dentry_lru ____cacheline_aligned_in_smp; - struct list_lru s_inode_lru ____cacheline_aligned_in_smp; + struct list_lru s_dentry_lru; + struct list_lru s_inode_lru; struct rcu_head rcu; struct work_struct destroy_work; -- cgit v1.2.3 From af0c9af1b3f66052c369d08be3f60fa9a9559e48 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 30 Jan 2019 13:52:38 -0500 Subject: fs/dcache: Track & report number of negative dentries The current dentry number tracking code doesn't distinguish between positive & negative dentries. It just reports the total number of dentries in the LRU lists. As excessive number of negative dentries can have an impact on system performance, it will be wise to track the number of positive and negative dentries separately. This patch adds tracking for the total number of negative dentries in the system LRU lists and reports it in the 5th field in the /proc/sys/fs/dentry-state file. The number, however, does not include negative dentries that are in flight but not in the LRU yet as well as those in the shrinker lists which are on the way out anyway. The number of positive dentries in the LRU lists can be roughly found by subtracting the number of negative dentries from the unused count. Matthew Wilcox had confirmed that since the introduction of the dentry_stat structure in 2.1.60, the dummy array was there, probably for future extension. They were not replacements of pre-existing fields. So no sane applications that read the value of /proc/sys/fs/dentry-state will do dummy thing if the last 2 fields of the sysctl parameter are not zero. IOW, it will be safe to use one of the dummy array entry for negative dentry count. Signed-off-by: Waiman Long Signed-off-by: Linus Torvalds --- include/linux/dcache.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index ef4b70f64f33..60996e64c579 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -62,9 +62,10 @@ extern const struct qstr slash_name; struct dentry_stat_t { long nr_dentry; long nr_unused; - long age_limit; /* age in seconds */ - long want_pages; /* pages requested by system */ - long dummy[2]; + long age_limit; /* age in seconds */ + long want_pages; /* pages requested by system */ + long nr_negative; /* # of unused negative dentries */ + long dummy; /* Reserved for future use */ }; extern struct dentry_stat_t dentry_stat; -- cgit v1.2.3 From 15efb47dc560849d0c07db96fdad5121f2cf736e Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Wed, 30 Jan 2019 18:26:02 +0100 Subject: PM-runtime: Fix deadlock with ktime_get() A deadlock has been seen when swicthing clocksources which use PM-runtime. The call path is: change_clocksource ... write_seqcount_begin ... timekeeping_update ... sh_cmt_clocksource_enable ... rpm_resume pm_runtime_mark_last_busy ktime_get do read_seqcount_begin while read_seqcount_retry .... write_seqcount_end Although we should be safe because we haven't yet changed the clocksource at that time, we can't do that because of seqcount protection. Use ktime_get_mono_fast_ns() instead which is lock safe for such cases. With ktime_get_mono_fast_ns, the timestamp is not guaranteed to be monotonic across an update and as a result can goes backward. According to update_fast_timekeeper() description: "In the worst case, this can result is a slightly wrong timestamp (a few nanoseconds)". For PM-runtime autosuspend, this means only that the suspend decision may be slightly suboptimal. Fixes: 8234f6734c5d ("PM-runtime: Switch autosuspend over to using hrtimers") Reported-by: Biju Das Signed-off-by: Vincent Guittot Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_runtime.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 54af4eef169f..fed5be706bc9 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -105,7 +105,7 @@ static inline bool pm_runtime_callbacks_present(struct device *dev) static inline void pm_runtime_mark_last_busy(struct device *dev) { - WRITE_ONCE(dev->power.last_busy, ktime_to_ns(ktime_get())); + WRITE_ONCE(dev->power.last_busy, ktime_get_mono_fast_ns()); } static inline bool pm_runtime_is_irq_safe(struct device *dev) -- cgit v1.2.3 From d5256083f62e2720f75bb3c5a928a0afe47d6bc3 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 30 Jan 2019 12:49:48 +0100 Subject: ipvlan, l3mdev: fix broken l3s mode wrt local routes While implementing ipvlan l3 and l3s mode for kubernetes CNI plugin, I ran into the issue that while l3 mode is working fine, l3s mode does not have any connectivity to kube-apiserver and hence all pods end up in Error state as well. The ipvlan master device sits on top of a bond device and hostns traffic to kube-apiserver (also running in hostns) is DNATed from 10.152.183.1:443 to 139.178.29.207:37573 where the latter is the address of the bond0. While in l3 mode, a curl to https://10.152.183.1:443 or to https://139.178.29.207:37573 works fine from hostns, neither of them do in case of l3s. In the latter only a curl to https://127.0.0.1:37573 appeared to work where for local addresses of bond0 I saw kernel suddenly starting to emit ARP requests to query HW address of bond0 which remained unanswered and neighbor entries in INCOMPLETE state. These ARP requests only happen while in l3s. Debugging this further, I found the issue is that l3s mode is piggy- backing on l3 master device, and in this case local routes are using l3mdev_master_dev_rcu(dev) instead of net->loopback_dev as per commit f5a0aab84b74 ("net: ipv4: dst for local input routes should use l3mdev if relevant") and 5f02ce24c269 ("net: l3mdev: Allow the l3mdev to be a loopback"). I found that reverting them back into using the net->loopback_dev fixed ipvlan l3s connectivity and got everything working for the CNI. Now judging from 4fbae7d83c98 ("ipvlan: Introduce l3s mode") and the l3mdev paper in [0] the only sole reason why ipvlan l3s is relying on l3 master device is to get the l3mdev_ip_rcv() receive hook for setting the dst entry of the input route without adding its own ipvlan specific hacks into the receive path, however, any l3 domain semantics beyond just that are breaking l3s operation. Note that ipvlan also has the ability to dynamically switch its internal operation from l3 to l3s for all ports via ipvlan_set_port_mode() at runtime. In any case, l3 vs l3s soley distinguishes itself by 'de-confusing' netfilter through switching skb->dev to ipvlan slave device late in NF_INET_LOCAL_IN before handing the skb to L4. Minimal fix taken here is to add a IFF_L3MDEV_RX_HANDLER flag which, if set from ipvlan setup, gets us only the wanted l3mdev_l3_rcv() hook without any additional l3mdev semantics on top. This should also have minimal impact since dev->priv_flags is already hot in cache. With this set, l3s mode is working fine and I also get things like masquerading pod traffic on the ipvlan master properly working. [0] https://netdevconf.org/1.2/papers/ahern-what-is-l3mdev-paper.pdf Fixes: f5a0aab84b74 ("net: ipv4: dst for local input routes should use l3mdev if relevant") Fixes: 5f02ce24c269 ("net: l3mdev: Allow the l3mdev to be a loopback") Fixes: 4fbae7d83c98 ("ipvlan: Introduce l3s mode") Signed-off-by: Daniel Borkmann Cc: Mahesh Bandewar Cc: David Ahern Cc: Florian Westphal Cc: Martynas Pumputis Acked-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1377d085ef99..86dbb3e29139 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1483,6 +1483,7 @@ struct net_device_ops { * @IFF_NO_RX_HANDLER: device doesn't support the rx_handler hook * @IFF_FAILOVER: device is a failover master device * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device + * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1514,6 +1515,7 @@ enum netdev_priv_flags { IFF_NO_RX_HANDLER = 1<<26, IFF_FAILOVER = 1<<27, IFF_FAILOVER_SLAVE = 1<<28, + IFF_L3MDEV_RX_HANDLER = 1<<29, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1544,6 +1546,7 @@ enum netdev_priv_flags { #define IFF_NO_RX_HANDLER IFF_NO_RX_HANDLER #define IFF_FAILOVER IFF_FAILOVER #define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE +#define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER /** * struct net_device - The DEVICE structure. @@ -4549,6 +4552,11 @@ static inline bool netif_supports_nofcs(struct net_device *dev) return dev->priv_flags & IFF_SUPP_NOFCS; } +static inline bool netif_has_l3_rx_handler(const struct net_device *dev) +{ + return dev->priv_flags & IFF_L3MDEV_RX_HANDLER; +} + static inline bool netif_is_l3_master(const struct net_device *dev) { return dev->priv_flags & IFF_L3MDEV_MASTER; -- cgit v1.2.3 From 4ec5302fa906ec9d86597b236f62315bacdb9622 Mon Sep 17 00:00:00 2001 From: Jose Abreu Date: Wed, 30 Jan 2019 15:54:19 +0100 Subject: net: stmmac: Fallback to Platform Data clock in Watchdog conversion If we don't have DT then stmmac_clk will not be available. Let's add a new Platform Data field so that we can specify the refclk by this mean. This way we can still use the coalesce command in PCI based setups. Signed-off-by: Jose Abreu Cc: Joao Pinto Cc: David S. Miller Cc: Giuseppe Cavallaro Cc: Alexandre Torgue Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 7ddfc65586b0..4335bd771ce5 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -184,6 +184,7 @@ struct plat_stmmacenet_data { struct clk *pclk; struct clk *clk_ptp_ref; unsigned int clk_ptp_rate; + unsigned int clk_ref_rate; struct reset_control *stmmac_rst; struct stmmac_axi *axi; int has_gmac4; -- cgit v1.2.3 From 56841070ccc87b463ac037d2d1f2beb8e5e35f0c Mon Sep 17 00:00:00 2001 From: Zenghui Yu Date: Thu, 31 Jan 2019 11:19:43 +0000 Subject: irqchip/gic-v3-its: Fix ITT_entry_size accessor According to ARM IHI 0069C (ID070116), we should use GITS_TYPER's bits [7:4] as ITT_entry_size instead of [8:4]. Although this is pretty annoying, it only results in a potential over-allocation of memory, and nothing bad happens. Fixes: 3dfa576bfb45 ("irqchip/gic-v3-its: Add probing for VLPI properties") Signed-off-by: Zenghui Yu [maz: massaged subject and commit message] Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 071b4cbdf010..c848a7cc502e 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -319,7 +319,7 @@ #define GITS_TYPER_PLPIS (1UL << 0) #define GITS_TYPER_VLPIS (1UL << 1) #define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT 4 -#define GITS_TYPER_ITT_ENTRY_SIZE(r) ((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0x1f) + 1) +#define GITS_TYPER_ITT_ENTRY_SIZE(r) ((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0xf) + 1) #define GITS_TYPER_IDBITS_SHIFT 8 #define GITS_TYPER_DEVBITS_SHIFT 13 #define GITS_TYPER_DEVBITS(r) ((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1) -- cgit v1.2.3 From 9a6d5488002fdca7134a0e59b0ae252f61042810 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 30 Jan 2019 08:41:40 -0700 Subject: ide: ensure atapi sense request aren't preempted There's an issue with how sense requests are handled in IDE. If ide-cd encounters an error, it queues a sense request. With how IDE request handling is done, this is the next request we need to handle. But it's impossible to guarantee this, as another request could come in between the sense being queued, and ->queue_rq() being run and handling it. If that request ALSO fails, then we attempt to doubly queue the single sense request we have. Since we only support one active request at the time, defer request processing when a sense request is queued. Fixes: 600335205b8d "ide: convert to blk-mq" Reported-by: He Zhe Tested-by: He Zhe Signed-off-by: Jens Axboe --- include/linux/ide.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ide.h b/include/linux/ide.h index e7d29ae633cd..971cf76a78a0 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -615,6 +615,7 @@ struct ide_drive_s { /* current sense rq and buffer */ bool sense_rq_armed; + bool sense_rq_active; struct request *sense_rq; struct request_sense sense_data; @@ -1219,6 +1220,7 @@ extern void ide_stall_queue(ide_drive_t *drive, unsigned long timeout); extern void ide_timer_expiry(struct timer_list *t); extern irqreturn_t ide_intr(int irq, void *dev_id); extern blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); +extern blk_status_t ide_issue_rq(ide_drive_t *, struct request *, bool); extern void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq); void ide_init_disk(struct gendisk *, ide_drive_t *); -- cgit v1.2.3 From 6cab5e90ab2bd323c9f3811b6c70a4687df51e27 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 28 Jan 2019 18:43:34 -0800 Subject: bpf: run bpf programs with preemption disabled Disabled preemption is necessary for proper access to per-cpu maps from BPF programs. But the sender side of socket filters didn't have preemption disabled: unix_dgram_sendmsg->sk_filter->sk_filter_trim_cap->bpf_prog_run_save_cb->BPF_PROG_RUN and a combination of af_packet with tun device didn't disable either: tpacket_snd->packet_direct_xmit->packet_pick_tx_queue->ndo_select_queue-> tun_select_queue->tun_ebpf_select_queue->bpf_prog_run_clear_cb->BPF_PROG_RUN Disable preemption before executing BPF programs (both classic and extended). Reported-by: Jann Horn Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Signed-off-by: Daniel Borkmann --- include/linux/filter.h | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index ad106d845b22..e532fcc6e4b5 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -591,8 +591,8 @@ static inline u8 *bpf_skb_cb(struct sk_buff *skb) return qdisc_skb_cb(skb)->data; } -static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, - struct sk_buff *skb) +static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog, + struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); u8 cb_saved[BPF_SKB_CB_LEN]; @@ -611,15 +611,30 @@ static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, return res; } +static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, + struct sk_buff *skb) +{ + u32 res; + + preempt_disable(); + res = __bpf_prog_run_save_cb(prog, skb); + preempt_enable(); + return res; +} + static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); + u32 res; if (unlikely(prog->cb_access)) memset(cb_data, 0, BPF_SKB_CB_LEN); - return BPF_PROG_RUN(prog, skb); + preempt_disable(); + res = BPF_PROG_RUN(prog, skb); + preempt_enable(); + return res; } static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, -- cgit v1.2.3 From 9bcdeb51bd7d2ae9fe65ea4d60643d2aeef5bfe3 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Fri, 1 Feb 2019 14:20:31 -0800 Subject: oom, oom_reaper: do not enqueue same task twice Arkadiusz reported that enabling memcg's group oom killing causes strange memcg statistics where there is no task in a memcg despite the number of tasks in that memcg is not 0. It turned out that there is a bug in wake_oom_reaper() which allows enqueuing same task twice which makes impossible to decrease the number of tasks in that memcg due to a refcount leak. This bug existed since the OOM reaper became invokable from task_will_free_mem(current) path in out_of_memory() in Linux 4.7, T1@P1 |T2@P1 |T3@P1 |OOM reaper ----------+----------+----------+------------ # Processing an OOM victim in a different memcg domain. try_charge() mem_cgroup_out_of_memory() mutex_lock(&oom_lock) try_charge() mem_cgroup_out_of_memory() mutex_lock(&oom_lock) try_charge() mem_cgroup_out_of_memory() mutex_lock(&oom_lock) out_of_memory() oom_kill_process(P1) do_send_sig_info(SIGKILL, @P1) mark_oom_victim(T1@P1) wake_oom_reaper(T1@P1) # T1@P1 is enqueued. mutex_unlock(&oom_lock) out_of_memory() mark_oom_victim(T2@P1) wake_oom_reaper(T2@P1) # T2@P1 is enqueued. mutex_unlock(&oom_lock) out_of_memory() mark_oom_victim(T1@P1) wake_oom_reaper(T1@P1) # T1@P1 is enqueued again due to oom_reaper_list == T2@P1 && T1@P1->oom_reaper_list == NULL. mutex_unlock(&oom_lock) # Completed processing an OOM victim in a different memcg domain. spin_lock(&oom_reaper_lock) # T1P1 is dequeued. spin_unlock(&oom_reaper_lock) but memcg's group oom killing made it easier to trigger this bug by calling wake_oom_reaper() on the same task from one out_of_memory() request. Fix this bug using an approach used by commit 855b018325737f76 ("oom, oom_reaper: disable oom_reaper for oom_kill_allocating_task"). As a side effect of this patch, this patch also avoids enqueuing multiple threads sharing memory via task_will_free_mem(current) path. Link: http://lkml.kernel.org/r/e865a044-2c10-9858-f4ef-254bc71d6cc2@i-love.sakura.ne.jp Link: http://lkml.kernel.org/r/5ee34fc6-1485-34f8-8790-903ddabaa809@i-love.sakura.ne.jp Fixes: af8e15cc85a25315 ("oom, oom_reaper: do not enqueue task if it is on the oom_reaper_list head") Signed-off-by: Tetsuo Handa Reported-by: Arkadiusz Miskiewicz Tested-by: Arkadiusz Miskiewicz Acked-by: Michal Hocko Acked-by: Roman Gushchin Cc: Tejun Heo Cc: Aleksa Sarai Cc: Jay Kamat Cc: Johannes Weiner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/coredump.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index ec912d01126f..ecdc6542070f 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -71,6 +71,7 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ #define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ #define MMF_OOM_VICTIM 25 /* mm is the oom victim */ +#define MMF_OOM_REAP_QUEUED 26 /* mm was queued for oom_reaper */ #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ -- cgit v1.2.3 From b13bc35193d9e7a8c050a24928ca5c9e7c9a009b Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Fri, 1 Feb 2019 14:20:51 -0800 Subject: mm/hotplug: invalid PFNs from pfn_to_online_page() On an arm64 ThunderX2 server, the first kmemleak scan would crash [1] with CONFIG_DEBUG_VM_PGFLAGS=y due to page_to_nid() found a pfn that is not directly mapped (MEMBLOCK_NOMAP). Hence, the page->flags is uninitialized. This is due to the commit 9f1eb38e0e11 ("mm, kmemleak: little optimization while scanning") starts to use pfn_to_online_page() instead of pfn_valid(). However, in the CONFIG_MEMORY_HOTPLUG=y case, pfn_to_online_page() does not call memblock_is_map_memory() while pfn_valid() does. Historically, the commit 68709f45385a ("arm64: only consider memblocks with NOMAP cleared for linear mapping") causes pages marked as nomap being no long reassigned to the new zone in memmap_init_zone() by calling __init_single_page(). Since the commit 2d070eab2e82 ("mm: consider zone which is not fully populated to have holes") introduced pfn_to_online_page() and was designed to return a valid pfn only, but it is clearly broken on arm64. Therefore, let pfn_to_online_page() call pfn_valid_within(), so it can handle nomap thanks to the commit f52bb98f5ade ("arm64: mm: always enable CONFIG_HOLES_IN_ZONE"), while it will be optimized away on architectures where have no HOLES_IN_ZONE. [1] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000006 Mem abort info: ESR = 0x96000005 Exception class = DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 Data abort info: ISV = 0, ISS = 0x00000005 CM = 0, WnR = 0 Internal error: Oops: 96000005 [#1] SMP CPU: 60 PID: 1408 Comm: kmemleak Not tainted 5.0.0-rc2+ #8 pstate: 60400009 (nZCv daif +PAN -UAO) pc : page_mapping+0x24/0x144 lr : __dump_page+0x34/0x3dc sp : ffff00003a5cfd10 x29: ffff00003a5cfd10 x28: 000000000000802f x27: 0000000000000000 x26: 0000000000277d00 x25: ffff000010791f56 x24: ffff7fe000000000 x23: ffff000010772f8b x22: ffff00001125f670 x21: ffff000011311000 x20: ffff000010772f8b x19: fffffffffffffffe x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: ffff802698b19600 x13: ffff802698b1a200 x12: ffff802698b16f00 x11: ffff802698b1a400 x10: 0000000000001400 x9 : 0000000000000001 x8 : ffff00001121a000 x7 : 0000000000000000 x6 : ffff0000102c53b8 x5 : 0000000000000000 x4 : 0000000000000003 x3 : 0000000000000100 x2 : 0000000000000000 x1 : ffff000010772f8b x0 : ffffffffffffffff Process kmemleak (pid: 1408, stack limit = 0x(____ptrval____)) Call trace: page_mapping+0x24/0x144 __dump_page+0x34/0x3dc dump_page+0x28/0x4c kmemleak_scan+0x4ac/0x680 kmemleak_scan_thread+0xb4/0xdc kthread+0x12c/0x13c ret_from_fork+0x10/0x18 Code: d503201f f9400660 36000040 d1000413 (f9400661) ---[ end trace 4d4bd7f573490c8e ]--- Kernel panic - not syncing: Fatal exception SMP: stopping secondary CPUs Kernel Offset: disabled CPU features: 0x002,20000c38 Memory Limit: none ---[ end Kernel panic - not syncing: Fatal exception ]--- Link: http://lkml.kernel.org/r/20190122132916.28360-1-cai@lca.pw Fixes: 9f1eb38e0e11 ("mm, kmemleak: little optimization while scanning") Signed-off-by: Qian Cai Acked-by: Michal Hocko Cc: Oscar Salvador Cc: Catalin Marinas Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 07da5c6c5ba0..368267c1b71b 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -21,14 +21,16 @@ struct vmem_altmap; * walkers which rely on the fully initialized page->flags and others * should use this rather than pfn_valid && pfn_to_page */ -#define pfn_to_online_page(pfn) \ -({ \ - struct page *___page = NULL; \ - unsigned long ___nr = pfn_to_section_nr(pfn); \ - \ - if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr))\ - ___page = pfn_to_page(pfn); \ - ___page; \ +#define pfn_to_online_page(pfn) \ +({ \ + struct page *___page = NULL; \ + unsigned long ___pfn = pfn; \ + unsigned long ___nr = pfn_to_section_nr(___pfn); \ + \ + if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr) && \ + pfn_valid_within(___pfn)) \ + ___page = pfn_to_page(___pfn); \ + ___page; \ }) /* -- cgit v1.2.3 From e6d429313ea5c776d2e76b4494df69102e6b7115 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Tue, 29 Jan 2019 17:44:36 -0500 Subject: x86/resctrl: Avoid confusion over the new X86_RESCTRL config "Resource Control" is a very broad term for this CPU feature, and a term that is also associated with containers, cgroups etc. This can easily cause confusion. Make the user prompt more specific. Match the config symbol name. [ bp: In the future, the corresponding ARM arch-specific code will be under ARM_CPU_RESCTRL and the arch-agnostic bits will be carved out under the CPU_RESCTRL umbrella symbol. ] Signed-off-by: Johannes Weiner Signed-off-by: Borislav Petkov Cc: Babu Moger Cc: Fenghua Yu Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: James Morse Cc: Jonathan Corbet Cc: "Kirill A. Shutemov" Cc: linux-doc@vger.kernel.org Cc: Peter Zijlstra Cc: Pu Wen Cc: Reinette Chatre Cc: Thomas Gleixner Cc: Tony Luck Cc: x86-ml Link: https://lkml.kernel.org/r/20190130195621.GA30653@cmpxchg.org --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 224666226e87..8c328b14c424 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -995,7 +995,7 @@ struct task_struct { /* cg_list protected by css_set_lock and tsk->alloc_lock: */ struct list_head cg_list; #endif -#ifdef CONFIG_X86_RESCTRL +#ifdef CONFIG_X86_CPU_RESCTRL u32 closid; u32 rmid; #endif -- cgit v1.2.3 From 0803de78049fe1b0baf44bcddc727b036fb9139b Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 7 Feb 2019 11:55:39 +0100 Subject: blktrace: Show requests without sector Currently, blktrace will not show requests that don't have any data as rq->__sector is initialized to -1 which is out of device range and thus discarded by act_log_check(). This is most notably the case for cache flush requests sent to the device. Fix the problem by making blk_rq_trace_sector() return 0 for requests without initialized sector. Reviewed-by: Johannes Thumshirn Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- include/linux/blktrace_api.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 8804753805ac..7bb2d8de9f30 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -116,7 +116,13 @@ extern void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes); static inline sector_t blk_rq_trace_sector(struct request *rq) { - return blk_rq_is_passthrough(rq) ? 0 : blk_rq_pos(rq); + /* + * Tracing should ignore starting sector for passthrough requests and + * requests where starting sector didn't get set. + */ + if (blk_rq_is_passthrough(rq) || blk_rq_pos(rq) == (sector_t)-1) + return 0; + return blk_rq_pos(rq); } static inline unsigned int blk_rq_trace_nr_sectors(struct request *rq) -- cgit v1.2.3