From 5de2055d31ea88fd9ae9709ac95c372a505a60fa Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Tue, 16 Mar 2021 11:31:16 -0400 Subject: locking/ww_mutex: Simplify use_ww_ctx & ww_ctx handling The use_ww_ctx flag is passed to mutex_optimistic_spin(), but the function doesn't use it. The frequent use of the (use_ww_ctx && ww_ctx) combination is repetitive. In fact, ww_ctx should not be used at all if !use_ww_ctx. Simplify ww_mutex code by dropping use_ww_ctx from mutex_optimistic_spin() an clear ww_ctx if !use_ww_ctx. In this way, we can replace (use_ww_ctx && ww_ctx) by just (ww_ctx). Signed-off-by: Waiman Long Signed-off-by: Ingo Molnar Acked-by: Davidlohr Bueso Link: https://lore.kernel.org/r/20210316153119.13802-2-longman@redhat.com --- kernel/locking/mutex.c | 25 ++++++++++++++----------- 1 file changed, 14 insertions(+), 11 deletions(-) diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index adb935090768..622ebdfcd083 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -626,7 +626,7 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock) */ static __always_inline bool mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx, - const bool use_ww_ctx, struct mutex_waiter *waiter) + struct mutex_waiter *waiter) { if (!waiter) { /* @@ -702,7 +702,7 @@ fail: #else static __always_inline bool mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx, - const bool use_ww_ctx, struct mutex_waiter *waiter) + struct mutex_waiter *waiter) { return false; } @@ -922,6 +922,9 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, struct ww_mutex *ww; int ret; + if (!use_ww_ctx) + ww_ctx = NULL; + might_sleep(); #ifdef CONFIG_DEBUG_MUTEXES @@ -929,7 +932,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, #endif ww = container_of(lock, struct ww_mutex, base); - if (use_ww_ctx && ww_ctx) { + if (ww_ctx) { if (unlikely(ww_ctx == READ_ONCE(ww->ctx))) return -EALREADY; @@ -946,10 +949,10 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip); if (__mutex_trylock(lock) || - mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, NULL)) { + mutex_optimistic_spin(lock, ww_ctx, NULL)) { /* got the lock, yay! */ lock_acquired(&lock->dep_map, ip); - if (use_ww_ctx && ww_ctx) + if (ww_ctx) ww_mutex_set_context_fastpath(ww, ww_ctx); preempt_enable(); return 0; @@ -960,7 +963,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, * After waiting to acquire the wait_lock, try again. */ if (__mutex_trylock(lock)) { - if (use_ww_ctx && ww_ctx) + if (ww_ctx) __ww_mutex_check_waiters(lock, ww_ctx); goto skip_wait; @@ -1013,7 +1016,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, goto err; } - if (use_ww_ctx && ww_ctx) { + if (ww_ctx) { ret = __ww_mutex_check_kill(lock, &waiter, ww_ctx); if (ret) goto err; @@ -1026,7 +1029,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, * ww_mutex needs to always recheck its position since its waiter * list is not FIFO ordered. */ - if ((use_ww_ctx && ww_ctx) || !first) { + if (ww_ctx || !first) { first = __mutex_waiter_is_first(lock, &waiter); if (first) __mutex_set_flag(lock, MUTEX_FLAG_HANDOFF); @@ -1039,7 +1042,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, * or we must see its unlock and acquire. */ if (__mutex_trylock(lock) || - (first && mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, &waiter))) + (first && mutex_optimistic_spin(lock, ww_ctx, &waiter))) break; spin_lock(&lock->wait_lock); @@ -1048,7 +1051,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, acquired: __set_current_state(TASK_RUNNING); - if (use_ww_ctx && ww_ctx) { + if (ww_ctx) { /* * Wound-Wait; we stole the lock (!first_waiter), check the * waiters as anyone might want to wound us. @@ -1068,7 +1071,7 @@ skip_wait: /* got the lock - cleanup and rejoice! */ lock_acquired(&lock->dep_map, ip); - if (use_ww_ctx && ww_ctx) + if (ww_ctx) ww_mutex_lock_acquired(ww, ww_ctx); spin_unlock(&lock->wait_lock); -- cgit v1.2.3-70-g09d2 From bee645788e07eea63055d261d2884ea45c2ba857 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Tue, 16 Mar 2021 11:31:17 -0400 Subject: locking/ww_mutex: Fix acquire/release imbalance in ww_acquire_init()/ww_acquire_fini() In ww_acquire_init(), mutex_acquire() is gated by CONFIG_DEBUG_LOCK_ALLOC. The dep_map in the ww_acquire_ctx structure is also gated by the same config. However mutex_release() in ww_acquire_fini() is gated by CONFIG_DEBUG_MUTEXES. It is possible to set CONFIG_DEBUG_MUTEXES without setting CONFIG_DEBUG_LOCK_ALLOC though it is an unlikely configuration. That may cause a compilation error as dep_map isn't defined in this case. Fix this potential problem by enclosing mutex_release() inside CONFIG_DEBUG_LOCK_ALLOC. Signed-off-by: Waiman Long Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20210316153119.13802-3-longman@redhat.com --- include/linux/ww_mutex.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index 850424e5d030..6ecf2a0220db 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -173,9 +173,10 @@ static inline void ww_acquire_done(struct ww_acquire_ctx *ctx) */ static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx) { -#ifdef CONFIG_DEBUG_MUTEXES +#ifdef CONFIG_DEBUG_LOCK_ALLOC mutex_release(&ctx->dep_map, _THIS_IP_); - +#endif +#ifdef CONFIG_DEBUG_MUTEXES DEBUG_LOCKS_WARN_ON(ctx->acquired); if (!IS_ENABLED(CONFIG_PROVE_LOCKING)) /* -- cgit v1.2.3-70-g09d2 From 68b1eddd421d2b16c6655eceb48918a1e896bbbc Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 18 Mar 2021 11:27:19 +0100 Subject: static_call: Fix static_call_set_init() It turns out that static_call_set_init() does not preserve the other flags; IOW. it clears TAIL if it was set. Fixes: 9183c3f9ed710 ("static_call: Add inline static call infrastructure") Reported-by: Sumit Garg Signed-off-by: Peter Zijlstra (Intel) Acked-by: Jarkko Sakkinen Tested-by: Sumit Garg Link: https://lkml.kernel.org/r/20210318113610.519406371@infradead.org --- kernel/static_call.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) diff --git a/kernel/static_call.c b/kernel/static_call.c index ae825295cf68..080c8a9ddfaf 100644 --- a/kernel/static_call.c +++ b/kernel/static_call.c @@ -35,27 +35,30 @@ static inline void *static_call_addr(struct static_call_site *site) return (void *)((long)site->addr + (long)&site->addr); } +static inline unsigned long __static_call_key(const struct static_call_site *site) +{ + return (long)site->key + (long)&site->key; +} static inline struct static_call_key *static_call_key(const struct static_call_site *site) { - return (struct static_call_key *) - (((long)site->key + (long)&site->key) & ~STATIC_CALL_SITE_FLAGS); + return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS); } /* These assume the key is word-aligned. */ static inline bool static_call_is_init(struct static_call_site *site) { - return ((long)site->key + (long)&site->key) & STATIC_CALL_SITE_INIT; + return __static_call_key(site) & STATIC_CALL_SITE_INIT; } static inline bool static_call_is_tail(struct static_call_site *site) { - return ((long)site->key + (long)&site->key) & STATIC_CALL_SITE_TAIL; + return __static_call_key(site) & STATIC_CALL_SITE_TAIL; } static inline void static_call_set_init(struct static_call_site *site) { - site->key = ((long)static_call_key(site) | STATIC_CALL_SITE_INIT) - + site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) - (long)&site->key; } @@ -190,7 +193,7 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func) } arch_static_call_transform(site_addr, NULL, func, - static_call_is_tail(site)); + static_call_is_tail(site)); } } @@ -349,7 +352,7 @@ static int static_call_add_module(struct module *mod) struct static_call_site *site; for (site = start; site != stop; site++) { - unsigned long s_key = (long)site->key + (long)&site->key; + unsigned long s_key = __static_call_key(site); unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS; unsigned long key; -- cgit v1.2.3-70-g09d2 From 698bacefe993ad2922c9d3b1380591ad489355e9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 18 Mar 2021 11:29:56 +0100 Subject: static_call: Align static_call_is_init() patching condition The intent is to avoid writing init code after init (because the text might have been freed). The code is needlessly different between jump_label and static_call and not obviously correct. The existing code relies on the fact that the module loader clears the init layout, such that within_module_init() always fails, while jump_label relies on the module state which is more obvious and matches the kernel logic. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Jarkko Sakkinen Tested-by: Sumit Garg Link: https://lkml.kernel.org/r/20210318113610.636651340@infradead.org --- kernel/static_call.c | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/kernel/static_call.c b/kernel/static_call.c index 080c8a9ddfaf..fc2259047be2 100644 --- a/kernel/static_call.c +++ b/kernel/static_call.c @@ -149,6 +149,7 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func) }; for (site_mod = &first; site_mod; site_mod = site_mod->next) { + bool init = system_state < SYSTEM_RUNNING; struct module *mod = site_mod->mod; if (!site_mod->sites) { @@ -168,6 +169,7 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func) if (mod) { stop = mod->static_call_sites + mod->num_static_call_sites; + init = mod->state == MODULE_STATE_COMING; } #endif @@ -175,16 +177,8 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func) site < stop && static_call_key(site) == key; site++) { void *site_addr = static_call_addr(site); - if (static_call_is_init(site)) { - /* - * Don't write to call sites which were in - * initmem and have since been freed. - */ - if (!mod && system_state >= SYSTEM_RUNNING) - continue; - if (mod && !within_module_init((unsigned long)site_addr, mod)) - continue; - } + if (!init && static_call_is_init(site)) + continue; if (!kernel_text_address((unsigned long)site_addr)) { WARN_ONCE(1, "can't patch static call site at %pS", -- cgit v1.2.3-70-g09d2 From 38c93587375053c5b9ef093f4a5ea754538cba32 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 18 Mar 2021 11:31:51 +0100 Subject: static_call: Fix static_call_update() sanity check Sites that match init_section_contains() get marked as INIT. For built-in code init_sections contains both __init and __exit text. OTOH kernel_text_address() only explicitly includes __init text (and there are no __exit text markers). Match what jump_label already does and ignore the warning for INIT sites. Also see the excellent changelog for commit: 8f35eaa5f2de ("jump_label: Don't warn on __exit jump entries") Fixes: 9183c3f9ed710 ("static_call: Add inline static call infrastructure") Reported-by: Sumit Garg Signed-off-by: Peter Zijlstra (Intel) Acked-by: Jarkko Sakkinen Tested-by: Sumit Garg Link: https://lkml.kernel.org/r/20210318113610.739542434@infradead.org --- kernel/jump_label.c | 8 ++++++++ kernel/static_call.c | 11 ++++++++++- 2 files changed, 18 insertions(+), 1 deletion(-) diff --git a/kernel/jump_label.c b/kernel/jump_label.c index c6a39d662935..ba39fbb1f8e7 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -407,6 +407,14 @@ static bool jump_label_can_update(struct jump_entry *entry, bool init) return false; if (!kernel_text_address(jump_entry_code(entry))) { + /* + * This skips patching built-in __exit, which + * is part of init_section_contains() but is + * not part of kernel_text_address(). + * + * Skipping built-in __exit is fine since it + * will never be executed. + */ WARN_ONCE(!jump_entry_is_init(entry), "can't patch jump_label at %pS", (void *)jump_entry_code(entry)); diff --git a/kernel/static_call.c b/kernel/static_call.c index fc2259047be2..2c5950b0b90e 100644 --- a/kernel/static_call.c +++ b/kernel/static_call.c @@ -181,7 +181,16 @@ void __static_call_update(struct static_call_key *key, void *tramp, void *func) continue; if (!kernel_text_address((unsigned long)site_addr)) { - WARN_ONCE(1, "can't patch static call site at %pS", + /* + * This skips patching built-in __exit, which + * is part of init_section_contains() but is + * not part of kernel_text_address(). + * + * Skipping built-in __exit is fine since it + * will never be executed. + */ + WARN_ONCE(!static_call_is_init(site), + "can't patch static call site at %pS", site_addr); continue; } -- cgit v1.2.3-70-g09d2