From c0a5c81ca9bedaf38356a6290bf895313fd7361c Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 10 Sep 2021 16:40:41 -0700 Subject: Kconfig.debug: drop GCC 5+ version check for DWARF5 Now that the minimum supported version of GCC is 5.1, we no longer need this Kconfig version check for CONFIG_DEBUG_INFO_DWARF5. Signed-off-by: Nick Desaulniers Reviewed-by: Kees Cook Reviewed-by: Nathan Chancellor Signed-off-by: Linus Torvalds --- lib/Kconfig.debug | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index ed4a31e34098..d566f601780f 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -295,7 +295,7 @@ config DEBUG_INFO_DWARF4 config DEBUG_INFO_DWARF5 bool "Generate DWARF Version 5 debuginfo" - depends on GCC_VERSION >= 50000 || (CC_IS_CLANG && (AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502))) + depends on !CC_IS_CLANG || (CC_IS_CLANG && (AS_IS_LLVM || (AS_IS_GNU && AS_VERSION >= 23502))) depends on !DEBUG_INFO_BTF help Generate DWARF v5 debug info. Requires binutils 2.35.2, gcc 5.0+ (gcc -- cgit v1.3-14-g43fede From 8fb0f47a9d7acf620d0fd97831b69da9bc5e22ed Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 10 Sep 2021 11:18:36 -0600 Subject: iov_iter: add helper to save iov_iter state In an ideal world, when someone is passed an iov_iter and returns X bytes, then X bytes would have been consumed/advanced from the iov_iter. But we have use cases that always consume the entire iterator, a few examples of that are iomap and bdev O_DIRECT. This means we cannot rely on the state of the iov_iter once we've called ->read_iter() or ->write_iter(). This would be easier if we didn't always have to deal with truncate of the iov_iter, as rewinding would be trivial without that. We recently added a commit to track the truncate state, but that grew the iov_iter by 8 bytes and wasn't the best solution. Implement a helper to save enough of the iov_iter state to sanely restore it after we've called the read/write iterator helpers. This currently only works for IOVEC/BVEC/KVEC as that's all we need, support for other iterator types are left as an exercise for the reader. Link: https://lore.kernel.org/linux-fsdevel/CAHk-=wiacKV4Gh-MYjteU0LwNBSGpWrK-Ov25HdqB1ewinrFPg@mail.gmail.com/ Signed-off-by: Jens Axboe --- include/linux/uio.h | 15 +++++++++++++++ lib/iov_iter.c | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 51 insertions(+) (limited to 'lib') diff --git a/include/linux/uio.h b/include/linux/uio.h index 5265024e8b90..984c4ab74859 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -27,6 +27,12 @@ enum iter_type { ITER_DISCARD, }; +struct iov_iter_state { + size_t iov_offset; + size_t count; + unsigned long nr_segs; +}; + struct iov_iter { u8 iter_type; bool data_source; @@ -55,6 +61,14 @@ static inline enum iter_type iov_iter_type(const struct iov_iter *i) return i->iter_type; } +static inline void iov_iter_save_state(struct iov_iter *iter, + struct iov_iter_state *state) +{ + state->iov_offset = iter->iov_offset; + state->count = iter->count; + state->nr_segs = iter->nr_segs; +} + static inline bool iter_is_iovec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_IOVEC; @@ -233,6 +247,7 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); +void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index f2d50d69a6c3..755c10c5138c 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1972,3 +1972,39 @@ int import_single_range(int rw, void __user *buf, size_t len, return 0; } EXPORT_SYMBOL(import_single_range); + +/** + * iov_iter_restore() - Restore a &struct iov_iter to the same state as when + * iov_iter_save_state() was called. + * + * @i: &struct iov_iter to restore + * @state: state to restore from + * + * Used after iov_iter_save_state() to bring restore @i, if operations may + * have advanced it. + * + * Note: only works on ITER_IOVEC, ITER_BVEC, and ITER_KVEC + */ +void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state) +{ + if (WARN_ON_ONCE(!iov_iter_is_bvec(i) && !iter_is_iovec(i)) && + !iov_iter_is_kvec(i)) + return; + i->iov_offset = state->iov_offset; + i->count = state->count; + /* + * For the *vec iters, nr_segs + iov is constant - if we increment + * the vec, then we also decrement the nr_segs count. Hence we don't + * need to track both of these, just one is enough and we can deduct + * the other from that. ITER_KVEC and ITER_IOVEC are the same struct + * size, so we can just increment the iov pointer as they are unionzed. + * ITER_BVEC _may_ be the same size on some archs, but on others it is + * not. Be safe and handle it separately. + */ + BUILD_BUG_ON(sizeof(struct iovec) != sizeof(struct kvec)); + if (iov_iter_is_bvec(i)) + i->bvec -= state->nr_segs - i->nr_segs; + else + i->iov -= state->nr_segs - i->nr_segs; + i->nr_segs = state->nr_segs; +} -- cgit v1.3-14-g43fede From 77e02cf57b6cff9919949defb7fd9b8ac16399a2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 14 Sep 2021 13:23:22 -0700 Subject: memblock: introduce saner 'memblock_free_ptr()' interface The boot-time allocation interface for memblock is a mess, with 'memblock_alloc()' returning a virtual pointer, but then you are supposed to free it with 'memblock_free()' that takes a _physical_ address. Not only is that all kinds of strange and illogical, but it actually causes bugs, when people then use it like a normal allocation function, and it fails spectacularly on a NULL pointer: https://lore.kernel.org/all/20210912140820.GD25450@xsang-OptiPlex-9020/ or just random memory corruption if the debug checks don't catch it: https://lore.kernel.org/all/61ab2d0c-3313-aaab-514c-e15b7aa054a0@suse.cz/ I really don't want to apply patches that treat the symptoms, when the fundamental cause is this horribly confusing interface. I started out looking at just automating a sane replacement sequence, but because of this mix or virtual and physical addresses, and because people have used the "__pa()" macro that can take either a regular kernel pointer, or just the raw "unsigned long" address, it's all quite messy. So this just introduces a new saner interface for freeing a virtual address that was allocated using 'memblock_alloc()', and that was kept as a regular kernel pointer. And then it converts a couple of users that are obvious and easy to test, including the 'xbc_nodes' case in lib/bootconfig.c that caused problems. Reported-by: kernel test robot Fixes: 40caa127f3c7 ("init: bootconfig: Remove all bootconfig data when the init memory is removed") Cc: Steven Rostedt Cc: Mike Rapoport Cc: Andrew Morton Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Vlastimil Babka Signed-off-by: Linus Torvalds --- arch/x86/kernel/setup_percpu.c | 2 +- arch/x86/mm/kasan_init_64.c | 6 ++---- arch/x86/mm/numa.c | 2 +- arch/x86/mm/numa_emulation.c | 3 +-- drivers/base/arch_numa.c | 2 +- drivers/macintosh/smu.c | 2 +- include/linux/memblock.h | 1 + init/main.c | 2 +- kernel/printk/printk.c | 4 ++-- lib/bootconfig.c | 2 +- mm/memblock.c | 16 +++++++++++++++- 11 files changed, 27 insertions(+), 15 deletions(-) (limited to 'lib') diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 78a32b956e81..5afd98559193 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -135,7 +135,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) static void __init pcpu_fc_free(void *ptr, size_t size) { - memblock_free(__pa(ptr), size); + memblock_free_ptr(ptr, size); } static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 1a50434c8a4d..ef885370719a 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -49,8 +49,7 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, p = early_alloc(PMD_SIZE, nid, false); if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL)) return; - else if (p) - memblock_free(__pa(p), PMD_SIZE); + memblock_free_ptr(p, PMD_SIZE); } p = early_alloc(PAGE_SIZE, nid, true); @@ -86,8 +85,7 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr, p = early_alloc(PUD_SIZE, nid, false); if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL)) return; - else if (p) - memblock_free(__pa(p), PUD_SIZE); + memblock_free_ptr(p, PUD_SIZE); } p = early_alloc(PAGE_SIZE, nid, true); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index a1b5c71099e6..1e9b93b088db 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -355,7 +355,7 @@ void __init numa_reset_distance(void) /* numa_distance could be 1LU marking allocation failure, test cnt */ if (numa_distance_cnt) - memblock_free(__pa(numa_distance), size); + memblock_free_ptr(numa_distance, size); numa_distance_cnt = 0; numa_distance = NULL; /* enable table creation */ } diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index 737491b13728..e801e30089c4 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -517,8 +517,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) } /* free the copied physical distance table */ - if (phys_dist) - memblock_free(__pa(phys_dist), phys_size); + memblock_free_ptr(phys_dist, phys_size); return; no_emu: diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index 46c503486e96..00fb4120a5b3 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -264,7 +264,7 @@ void __init numa_free_distance(void) size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]); - memblock_free(__pa(numa_distance), size); + memblock_free_ptr(numa_distance, size); numa_distance_cnt = 0; numa_distance = NULL; } diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index 94fb63a7b357..fe63d5ee201b 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -570,7 +570,7 @@ fail_msg_node: fail_db_node: of_node_put(smu->db_node); fail_bootmem: - memblock_free(__pa(smu), sizeof(struct smu_device)); + memblock_free_ptr(smu, sizeof(struct smu_device)); smu = NULL; fail_np: of_node_put(np); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index b066024c62e3..34de69b3b8ba 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -118,6 +118,7 @@ int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); void memblock_free_all(void); +void memblock_free_ptr(void *ptr, size_t size); void reset_node_managed_pages(pg_data_t *pgdat); void reset_all_zones_managed_pages(void); diff --git a/init/main.c b/init/main.c index 5c9a48df90e1..3f7216934441 100644 --- a/init/main.c +++ b/init/main.c @@ -924,7 +924,7 @@ static void __init print_unknown_bootoptions(void) end += sprintf(end, " %s", *p); pr_notice("Unknown command line parameters:%s\n", unknown_options); - memblock_free(__pa(unknown_options), len); + memblock_free_ptr(unknown_options, len); } asmlinkage __visible void __init __no_sanitize_address start_kernel(void) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 825277e1e742..a8d0a58deebc 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1166,9 +1166,9 @@ void __init setup_log_buf(int early) return; err_free_descs: - memblock_free(__pa(new_descs), new_descs_size); + memblock_free_ptr(new_descs, new_descs_size); err_free_log_buf: - memblock_free(__pa(new_log_buf), new_log_buf_len); + memblock_free_ptr(new_log_buf, new_log_buf_len); } static bool __read_mostly ignore_loglevel; diff --git a/lib/bootconfig.c b/lib/bootconfig.c index f8419cff1147..5ae248b29373 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -792,7 +792,7 @@ void __init xbc_destroy_all(void) xbc_data = NULL; xbc_data_size = 0; xbc_node_num = 0; - memblock_free(__pa(xbc_nodes), sizeof(struct xbc_node) * XBC_NODE_MAX); + memblock_free_ptr(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX); xbc_nodes = NULL; brace_index = 0; } diff --git a/mm/memblock.c b/mm/memblock.c index 0ab5a749bfa6..184dcd2e5d99 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -472,7 +472,7 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, kfree(old_array); else if (old_array != memblock_memory_init_regions && old_array != memblock_reserved_init_regions) - memblock_free(__pa(old_array), old_alloc_size); + memblock_free_ptr(old_array, old_alloc_size); /* * Reserve the new array if that comes from the memblock. Otherwise, we @@ -795,6 +795,20 @@ int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) return memblock_remove_range(&memblock.memory, base, size); } +/** + * memblock_free_ptr - free boot memory allocation + * @ptr: starting address of the boot memory allocation + * @size: size of the boot memory block in bytes + * + * Free boot memory block previously allocated by memblock_alloc_xx() API. + * The freeing memory will not be released to the buddy allocator. + */ +void __init_memblock memblock_free_ptr(void *ptr, size_t size) +{ + if (ptr) + memblock_free(__pa(ptr), size); +} + /** * memblock_free - free boot memory block * @base: phys starting address of the boot memory block -- cgit v1.3-14-g43fede From 12235da8c80a1f9909008e4ca6036d5772b81192 Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Thu, 9 Sep 2021 11:32:18 +0200 Subject: kernel/locking: Add context to ww_mutex_trylock() i915 will soon gain an eviction path that trylock a whole lot of locks for eviction, getting dmesg failures like below: BUG: MAX_LOCK_DEPTH too low! turning off the locking correctness validator. depth: 48 max: 48! 48 locks held by i915_selftest/5776: #0: ffff888101a79240 (&dev->mutex){....}-{3:3}, at: __driver_attach+0x88/0x160 #1: ffffc900009778c0 (reservation_ww_class_acquire){+.+.}-{0:0}, at: i915_vma_pin.constprop.63+0x39/0x1b0 [i915] #2: ffff88800cf74de8 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_vma_pin.constprop.63+0x5f/0x1b0 [i915] #3: ffff88810c7f9e38 (&vm->mutex/1){+.+.}-{3:3}, at: i915_vma_pin_ww+0x1c4/0x9d0 [i915] #4: ffff88810bad5768 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_gem_evict_something+0x110/0x860 [i915] #5: ffff88810bad60e8 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_gem_evict_something+0x110/0x860 [i915] ... #46: ffff88811964d768 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_gem_evict_something+0x110/0x860 [i915] #47: ffff88811964e0e8 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_gem_evict_something+0x110/0x860 [i915] INFO: lockdep is turned off. Fixing eviction to nest into ww_class_acquire is a high priority, but it requires a rework of the entire driver, which can only be done one step at a time. As an intermediate solution, add an acquire context to ww_mutex_trylock, which allows us to do proper nesting annotations on the trylocks, making the above lockdep splat disappear. This is also useful in regulator_lock_nested, which may avoid dropping regulator_nesting_mutex in the uncontended path, so use it there. TTM may be another user for this, where we could lock a buffer in a fastpath with list locks held, without dropping all locks we hold. [peterz: rework actual ww_mutex_trylock() implementations] Signed-off-by: Maarten Lankhorst Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/YUBGPdDDjKlxAuXJ@hirez.programming.kicks-ass.net --- drivers/gpu/drm/drm_modeset_lock.c | 2 +- drivers/regulator/core.c | 2 +- include/linux/dma-resv.h | 2 +- include/linux/ww_mutex.h | 15 +------ kernel/locking/mutex.c | 41 ++++++++++++++++++ kernel/locking/test-ww_mutex.c | 86 ++++++++++++++++++++++++++++---------- kernel/locking/ww_rt_mutex.c | 25 +++++++++++ lib/locking-selftest.c | 2 +- 8 files changed, 137 insertions(+), 38 deletions(-) (limited to 'lib') diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c index fcfe1a03c4a1..bf8a6e823a15 100644 --- a/drivers/gpu/drm/drm_modeset_lock.c +++ b/drivers/gpu/drm/drm_modeset_lock.c @@ -248,7 +248,7 @@ static inline int modeset_lock(struct drm_modeset_lock *lock, if (ctx->trylock_only) { lockdep_assert_held(&ctx->ww_ctx); - if (!ww_mutex_trylock(&lock->mutex)) + if (!ww_mutex_trylock(&lock->mutex, NULL)) return -EBUSY; else return 0; diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index ca6caba8a191..f4d441b1a8bf 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -145,7 +145,7 @@ static inline int regulator_lock_nested(struct regulator_dev *rdev, mutex_lock(®ulator_nesting_mutex); - if (ww_ctx || !ww_mutex_trylock(&rdev->mutex)) { + if (!ww_mutex_trylock(&rdev->mutex, ww_ctx)) { if (rdev->mutex_owner == current) rdev->ref_cnt++; else diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index e1ca2080a1ff..39fefb86780b 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -173,7 +173,7 @@ static inline int dma_resv_lock_slow_interruptible(struct dma_resv *obj, */ static inline bool __must_check dma_resv_trylock(struct dma_resv *obj) { - return ww_mutex_trylock(&obj->lock); + return ww_mutex_trylock(&obj->lock, NULL); } /** diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index 29db736af86d..bb763085479a 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -28,12 +28,10 @@ #ifndef CONFIG_PREEMPT_RT #define WW_MUTEX_BASE mutex #define ww_mutex_base_init(l,n,k) __mutex_init(l,n,k) -#define ww_mutex_base_trylock(l) mutex_trylock(l) #define ww_mutex_base_is_locked(b) mutex_is_locked((b)) #else #define WW_MUTEX_BASE rt_mutex #define ww_mutex_base_init(l,n,k) __rt_mutex_init(l,n,k) -#define ww_mutex_base_trylock(l) rt_mutex_trylock(l) #define ww_mutex_base_is_locked(b) rt_mutex_base_is_locked(&(b)->rtmutex) #endif @@ -339,17 +337,8 @@ ww_mutex_lock_slow_interruptible(struct ww_mutex *lock, extern void ww_mutex_unlock(struct ww_mutex *lock); -/** - * ww_mutex_trylock - tries to acquire the w/w mutex without acquire context - * @lock: mutex to lock - * - * Trylocks a mutex without acquire context, so no deadlock detection is - * possible. Returns 1 if the mutex has been acquired successfully, 0 otherwise. - */ -static inline int __must_check ww_mutex_trylock(struct ww_mutex *lock) -{ - return ww_mutex_base_trylock(&lock->base); -} +extern int __must_check ww_mutex_trylock(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx); /*** * ww_mutex_destroy - mark a w/w mutex unusable diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index d456579d0952..2fede72b6af5 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -94,6 +94,9 @@ static inline unsigned long __owner_flags(unsigned long owner) return owner & MUTEX_FLAGS; } +/* + * Returns: __mutex_owner(lock) on failure or NULL on success. + */ static inline struct task_struct *__mutex_trylock_common(struct mutex *lock, bool handoff) { unsigned long owner, curr = (unsigned long)current; @@ -736,6 +739,44 @@ __ww_mutex_lock(struct mutex *lock, unsigned int state, unsigned int subclass, return __mutex_lock_common(lock, state, subclass, NULL, ip, ww_ctx, true); } +/** + * ww_mutex_trylock - tries to acquire the w/w mutex with optional acquire context + * @ww: mutex to lock + * @ww_ctx: optional w/w acquire context + * + * Trylocks a mutex with the optional acquire context; no deadlock detection is + * possible. Returns 1 if the mutex has been acquired successfully, 0 otherwise. + * + * Unlike ww_mutex_lock, no deadlock handling is performed. However, if a @ctx is + * specified, -EALREADY handling may happen in calls to ww_mutex_trylock. + * + * A mutex acquired with this function must be released with ww_mutex_unlock. + */ +int ww_mutex_trylock(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx) +{ + if (!ww_ctx) + return mutex_trylock(&ww->base); + + MUTEX_WARN_ON(ww->base.magic != &ww->base); + + /* + * Reset the wounded flag after a kill. No other process can + * race and wound us here, since they can't have a valid owner + * pointer if we don't have any locks held. + */ + if (ww_ctx->acquired == 0) + ww_ctx->wounded = 0; + + if (__mutex_trylock(&ww->base)) { + ww_mutex_set_context_fastpath(ww, ww_ctx); + mutex_acquire_nest(&ww->base.dep_map, 0, 1, &ww_ctx->dep_map, _RET_IP_); + return 1; + } + + return 0; +} +EXPORT_SYMBOL(ww_mutex_trylock); + #ifdef CONFIG_DEBUG_LOCK_ALLOC void __sched mutex_lock_nested(struct mutex *lock, unsigned int subclass) diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c index 3e82f449b4ff..d63ac411f367 100644 --- a/kernel/locking/test-ww_mutex.c +++ b/kernel/locking/test-ww_mutex.c @@ -16,6 +16,15 @@ static DEFINE_WD_CLASS(ww_class); struct workqueue_struct *wq; +#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH +#define ww_acquire_init_noinject(a, b) do { \ + ww_acquire_init((a), (b)); \ + (a)->deadlock_inject_countdown = ~0U; \ + } while (0) +#else +#define ww_acquire_init_noinject(a, b) ww_acquire_init((a), (b)) +#endif + struct test_mutex { struct work_struct work; struct ww_mutex mutex; @@ -36,7 +45,7 @@ static void test_mutex_work(struct work_struct *work) wait_for_completion(&mtx->go); if (mtx->flags & TEST_MTX_TRY) { - while (!ww_mutex_trylock(&mtx->mutex)) + while (!ww_mutex_trylock(&mtx->mutex, NULL)) cond_resched(); } else { ww_mutex_lock(&mtx->mutex, NULL); @@ -109,19 +118,38 @@ static int test_mutex(void) return 0; } -static int test_aa(void) +static int test_aa(bool trylock) { struct ww_mutex mutex; struct ww_acquire_ctx ctx; int ret; + const char *from = trylock ? "trylock" : "lock"; ww_mutex_init(&mutex, &ww_class); ww_acquire_init(&ctx, &ww_class); - ww_mutex_lock(&mutex, &ctx); + if (!trylock) { + ret = ww_mutex_lock(&mutex, &ctx); + if (ret) { + pr_err("%s: initial lock failed!\n", __func__); + goto out; + } + } else { + if (!ww_mutex_trylock(&mutex, &ctx)) { + pr_err("%s: initial trylock failed!\n", __func__); + goto out; + } + } - if (ww_mutex_trylock(&mutex)) { - pr_err("%s: trylocked itself!\n", __func__); + if (ww_mutex_trylock(&mutex, NULL)) { + pr_err("%s: trylocked itself without context from %s!\n", __func__, from); + ww_mutex_unlock(&mutex); + ret = -EINVAL; + goto out; + } + + if (ww_mutex_trylock(&mutex, &ctx)) { + pr_err("%s: trylocked itself with context from %s!\n", __func__, from); ww_mutex_unlock(&mutex); ret = -EINVAL; goto out; @@ -129,17 +157,17 @@ static int test_aa(void) ret = ww_mutex_lock(&mutex, &ctx); if (ret != -EALREADY) { - pr_err("%s: missed deadlock for recursing, ret=%d\n", - __func__, ret); + pr_err("%s: missed deadlock for recursing, ret=%d from %s\n", + __func__, ret, from); if (!ret) ww_mutex_unlock(&mutex); ret = -EINVAL; goto out; } + ww_mutex_unlock(&mutex); ret = 0; out: - ww_mutex_unlock(&mutex); ww_acquire_fini(&ctx); return ret; } @@ -150,7 +178,7 @@ struct test_abba { struct ww_mutex b_mutex; struct completion a_ready; struct completion b_ready; - bool resolve; + bool resolve, trylock; int result; }; @@ -160,8 +188,13 @@ static void test_abba_work(struct work_struct *work) struct ww_acquire_ctx ctx; int err; - ww_acquire_init(&ctx, &ww_class); - ww_mutex_lock(&abba->b_mutex, &ctx); + ww_acquire_init_noinject(&ctx, &ww_class); + if (!abba->trylock) + ww_mutex_lock(&abba->b_mutex, &ctx); + else + WARN_ON(!ww_mutex_trylock(&abba->b_mutex, &ctx)); + + WARN_ON(READ_ONCE(abba->b_mutex.ctx) != &ctx); complete(&abba->b_ready); wait_for_completion(&abba->a_ready); @@ -181,7 +214,7 @@ static void test_abba_work(struct work_struct *work) abba->result = err; } -static int test_abba(bool resolve) +static int test_abba(bool trylock, bool resolve) { struct test_abba abba; struct ww_acquire_ctx ctx; @@ -192,12 +225,18 @@ static int test_abba(bool resolve) INIT_WORK_ONSTACK(&abba.work, test_abba_work); init_completion(&abba.a_ready); init_completion(&abba.b_ready); + abba.trylock = trylock; abba.resolve = resolve; schedule_work(&abba.work); - ww_acquire_init(&ctx, &ww_class); - ww_mutex_lock(&abba.a_mutex, &ctx); + ww_acquire_init_noinject(&ctx, &ww_class); + if (!trylock) + ww_mutex_lock(&abba.a_mutex, &ctx); + else + WARN_ON(!ww_mutex_trylock(&abba.a_mutex, &ctx)); + + WARN_ON(READ_ONCE(abba.a_mutex.ctx) != &ctx); complete(&abba.a_ready); wait_for_completion(&abba.b_ready); @@ -249,7 +288,7 @@ static void test_cycle_work(struct work_struct *work) struct ww_acquire_ctx ctx; int err, erra = 0; - ww_acquire_init(&ctx, &ww_class); + ww_acquire_init_noinject(&ctx, &ww_class); ww_mutex_lock(&cycle->a_mutex, &ctx); complete(cycle->a_signal); @@ -581,7 +620,9 @@ static int stress(int nlocks, int nthreads, unsigned int flags) static int __init test_ww_mutex_init(void) { int ncpus = num_online_cpus(); - int ret; + int ret, i; + + printk(KERN_INFO "Beginning ww mutex selftests\n"); wq = alloc_workqueue("test-ww_mutex", WQ_UNBOUND, 0); if (!wq) @@ -591,17 +632,19 @@ static int __init test_ww_mutex_init(void) if (ret) return ret; - ret = test_aa(); + ret = test_aa(false); if (ret) return ret; - ret = test_abba(false); + ret = test_aa(true); if (ret) return ret; - ret = test_abba(true); - if (ret) - return ret; + for (i = 0; i < 4; i++) { + ret = test_abba(i & 1, i & 2); + if (ret) + return ret; + } ret = test_cycle(ncpus); if (ret) @@ -619,6 +662,7 @@ static int __init test_ww_mutex_init(void) if (ret) return ret; + printk(KERN_INFO "All ww mutex selftests passed\n"); return 0; } diff --git a/kernel/locking/ww_rt_mutex.c b/kernel/locking/ww_rt_mutex.c index 3f1fff7d2780..0e00205cf467 100644 --- a/kernel/locking/ww_rt_mutex.c +++ b/kernel/locking/ww_rt_mutex.c @@ -9,6 +9,31 @@ #define WW_RT #include "rtmutex.c" +int ww_mutex_trylock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx) +{ + struct rt_mutex *rtm = &lock->base; + + if (!ww_ctx) + return rt_mutex_trylock(rtm); + + /* + * Reset the wounded flag after a kill. No other process can + * race and wound us here, since they can't have a valid owner + * pointer if we don't have any locks held. + */ + if (ww_ctx->acquired == 0) + ww_ctx->wounded = 0; + + if (__rt_mutex_trylock(&rtm->rtmutex)) { + ww_mutex_set_context_fastpath(lock, ww_ctx); + mutex_acquire_nest(&rtm->dep_map, 0, 1, ww_ctx->dep_map, _RET_IP_); + return 1; + } + + return 0; +} +EXPORT_SYMBOL(ww_mutex_trylock); + static int __sched __ww_rt_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx, unsigned int state, unsigned long ip) diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c index 161108e5d2fe..71652e1c397c 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -258,7 +258,7 @@ static void init_shared_classes(void) #define WWAF(x) ww_acquire_fini(x) #define WWL(x, c) ww_mutex_lock(x, c) -#define WWT(x) ww_mutex_trylock(x) +#define WWT(x) ww_mutex_trylock(x, NULL) #define WWL1(x) ww_mutex_lock(x, NULL) #define WWU(x) ww_mutex_unlock(x) -- cgit v1.3-14-g43fede 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 +++----------------------- lib/pci_iomap.c | 43 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 46 insertions(+), 23 deletions(-) (limited to 'lib') 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 diff --git a/lib/pci_iomap.c b/lib/pci_iomap.c index 2d3eb1cb73b8..ce39ce9f3526 100644 --- a/lib/pci_iomap.c +++ b/lib/pci_iomap.c @@ -134,4 +134,47 @@ void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long maxlen) return pci_iomap_wc_range(dev, bar, 0, maxlen); } EXPORT_SYMBOL_GPL(pci_iomap_wc); + +/* + * pci_iounmap() somewhat illogically comes from lib/iomap.c for the + * CONFIG_GENERIC_IOMAP case, because that's the code that knows about + * the different IOMAP ranges. + * + * But if the architecture does not use the generic iomap code, and if + * it has _not_ defined it's own private pci_iounmap function, we define + * it here. + * + * NOTE! This default implementation assumes that if the architecture + * support ioport mapping (HAS_IOPORT_MAP), the ioport mapping will + * be fixed to the range [ PCI_IOBASE, PCI_IOBASE+IO_SPACE_LIMIT [, + * and does not need unmapping with 'ioport_unmap()'. + * + * If you have different rules for your architecture, you need to + * implement your own pci_iounmap() that knows the rules for where + * and how IO vs MEM get mapped. + * + * This code is odd, and the ARCH_HAS/ARCH_WANTS #define logic comes + * from legacy header file behavior. In particular, + * it would seem to make sense to do the iounmap(p) for the non-IO-space + * case here regardless, but that's not what the old header file code + * did. Probably incorrectly, but this is meant to be bug-for-bug + * compatible. + */ +#if defined(ARCH_WANTS_GENERIC_PCI_IOUNMAP) + +void pci_iounmap(struct pci_dev *dev, void __iomem *p) +{ +#ifdef ARCH_HAS_GENERIC_IOPORT_MAP + uintptr_t start = (uintptr_t) PCI_IOBASE; + uintptr_t addr = (uintptr_t) p; + + if (addr >= start && addr < start + IO_SPACE_LIMIT) + return; + iounmap(p); +#endif +} +EXPORT_SYMBOL(pci_iounmap); + +#endif /* ARCH_WANTS_GENERIC_PCI_IOUNMAP */ + #endif /* CONFIG_PCI */ -- cgit v1.3-14-g43fede From 3229b906fb35b63515f0c703b917357c83e1ea22 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 16 Sep 2021 20:15:57 +0200 Subject: lib: devres: Add managed arch_phys_wc_add() Add devm_arch_phys_wc_add() as managed wrapper around arch_phys_wc_add(). Useful for several graphics drivers that set framebuffer memory to write combining. v2: * fix typo in commit description Signed-off-by: Thomas Zimmermann Reviewed-by: Hans de Goede Link: https://patchwork.freedesktop.org/patch/msgid/20210916181601.9146-2-tzimmermann@suse.de --- include/linux/io.h | 2 ++ lib/devres.c | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+) (limited to 'lib') diff --git a/include/linux/io.h b/include/linux/io.h index 9595151d800d..fcd8ea79c5df 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -132,6 +132,8 @@ static inline int arch_phys_wc_index(int handle) #endif #endif +int devm_arch_phys_wc_add(struct device *dev, unsigned long base, unsigned long size); + enum { /* See memremap() kernel-doc for usage description... */ MEMREMAP_WB = 1 << 0, diff --git a/lib/devres.c b/lib/devres.c index b0e1c6702c71..24d4d849ff67 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -528,3 +528,39 @@ void pcim_iounmap_regions(struct pci_dev *pdev, int mask) } EXPORT_SYMBOL(pcim_iounmap_regions); #endif /* CONFIG_PCI */ + +static void devm_arch_phys_ac_add_release(struct device *dev, void *res) +{ + arch_phys_wc_del(*((int *)res)); +} + +/** + * devm_arch_phys_wc_add - Managed arch_phys_wc_add() + * @dev: Managed device + * @base: Memory base address + * @size: Size of memory range + * + * Adds a WC MTRR using arch_phys_wc_add() and sets up a release callback. + * See arch_phys_wc_add() for more information. + */ +int devm_arch_phys_wc_add(struct device *dev, unsigned long base, unsigned long size) +{ + int *mtrr; + int ret; + + mtrr = devres_alloc(devm_arch_phys_ac_add_release, sizeof(*mtrr), GFP_KERNEL); + if (!mtrr) + return -ENOMEM; + + ret = arch_phys_wc_add(base, size); + if (ret < 0) { + devres_free(mtrr); + return ret; + } + + *mtrr = ret; + devres_add(dev, mtrr); + + return ret; +} +EXPORT_SYMBOL(devm_arch_phys_wc_add); -- cgit v1.3-14-g43fede From c822310725ee41af663de2448094155d442ff871 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 16 Sep 2021 20:15:58 +0200 Subject: lib: devres: Add managed arch_io_reserve_memtype_wc() Add devm_arch_io_reserve_memtype_wc() as managed wrapper around arch_io_reserve_memtype_wc(). Useful for several graphics drivers that set framebuffer memory to write combining. v2: * fix typo in commit description Signed-off-by: Thomas Zimmermann Reviewed-by: Hans de Goede Link: https://patchwork.freedesktop.org/patch/msgid/20210916181601.9146-3-tzimmermann@suse.de --- include/linux/io.h | 3 +++ lib/devres.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 49 insertions(+) (limited to 'lib') diff --git a/include/linux/io.h b/include/linux/io.h index fcd8ea79c5df..5fc800390fe4 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -168,4 +168,7 @@ static inline void arch_io_free_memtype_wc(resource_size_t base, } #endif +int devm_arch_io_reserve_memtype_wc(struct device *dev, resource_size_t start, + resource_size_t size); + #endif /* _LINUX_IO_H */ diff --git a/lib/devres.c b/lib/devres.c index 24d4d849ff67..14664bbb4875 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -564,3 +564,49 @@ int devm_arch_phys_wc_add(struct device *dev, unsigned long base, unsigned long return ret; } EXPORT_SYMBOL(devm_arch_phys_wc_add); + +struct arch_io_reserve_memtype_wc_devres { + resource_size_t start; + resource_size_t size; +}; + +static void devm_arch_io_free_memtype_wc_release(struct device *dev, void *res) +{ + const struct arch_io_reserve_memtype_wc_devres *this = res; + + arch_io_free_memtype_wc(this->start, this->size); +} + +/** + * devm_arch_io_reserve_memtype_wc - Managed arch_io_reserve_memtype_wc() + * @dev: Managed device + * @start: Memory base address + * @size: Size of memory range + * + * Reserves a memory range with WC caching using arch_io_reserve_memtype_wc() + * and sets up a release callback See arch_io_reserve_memtype_wc() for more + * information. + */ +int devm_arch_io_reserve_memtype_wc(struct device *dev, resource_size_t start, + resource_size_t size) +{ + struct arch_io_reserve_memtype_wc_devres *dr; + int ret; + + dr = devres_alloc(devm_arch_io_free_memtype_wc_release, sizeof(*dr), GFP_KERNEL); + if (!dr) + return -ENOMEM; + + ret = arch_io_reserve_memtype_wc(start, size); + if (ret < 0) { + devres_free(dr); + return ret; + } + + dr->start = start; + dr->size = size; + devres_add(dev, dr); + + return ret; +} +EXPORT_SYMBOL(devm_arch_io_reserve_memtype_wc); -- cgit v1.3-14-g43fede