Relocate the estatus cache allocation and lookup helpers from ghes.c into ghes_cper.c. This code move keeps the logic intact while making the cache implementation available to forthcoming users.
Fix ghes_estatus_cache_add() by freeing new_cache and decrementing ghes_estatus_cache_alloced. This avoids leaks and counter exhaustion that can disable estatus deduplication. Reviewed-by: Jonathan Cameron <[email protected]> Signed-off-by: Ahmed Tiba <[email protected]> --- drivers/acpi/apei/ghes.c | 138 +--------------------------------------- drivers/acpi/apei/ghes_cper.c | 143 ++++++++++++++++++++++++++++++++++++++++++ include/acpi/ghes_cper.h | 5 ++ 3 files changed, 149 insertions(+), 137 deletions(-) diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index bda535224422..e9cb576eefcf 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -113,10 +113,7 @@ static DEFINE_MUTEX(ghes_devs_mutex); */ static DEFINE_SPINLOCK(ghes_notify_lock_irq); -static struct gen_pool *ghes_estatus_pool; - -static struct ghes_estatus_cache __rcu *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE]; -static atomic_t ghes_estatus_cache_alloced; +struct gen_pool *ghes_estatus_pool; int ghes_estatus_pool_init(unsigned int num_ghes) { @@ -733,139 +730,6 @@ static int ghes_print_estatus(const char *pfx, return 0; } -/* - * GHES error status reporting throttle, to report more kinds of - * errors, instead of just most frequently occurred errors. - */ -static int ghes_estatus_cached(struct acpi_hest_generic_status *estatus) -{ - u32 len; - int i, cached = 0; - unsigned long long now; - struct ghes_estatus_cache *cache; - struct acpi_hest_generic_status *cache_estatus; - - len = cper_estatus_len(estatus); - rcu_read_lock(); - for (i = 0; i < GHES_ESTATUS_CACHES_SIZE; i++) { - cache = rcu_dereference(ghes_estatus_caches[i]); - if (cache == NULL) - continue; - if (len != cache->estatus_len) - continue; - cache_estatus = GHES_ESTATUS_FROM_CACHE(cache); - if (memcmp(estatus, cache_estatus, len)) - continue; - atomic_inc(&cache->count); - now = sched_clock(); - if (now - cache->time_in < GHES_ESTATUS_IN_CACHE_MAX_NSEC) - cached = 1; - break; - } - rcu_read_unlock(); - return cached; -} - -static struct ghes_estatus_cache *ghes_estatus_cache_alloc( - struct acpi_hest_generic *generic, - struct acpi_hest_generic_status *estatus) -{ - int alloced; - u32 len, cache_len; - struct ghes_estatus_cache *cache; - struct acpi_hest_generic_status *cache_estatus; - - alloced = atomic_add_return(1, &ghes_estatus_cache_alloced); - if (alloced > GHES_ESTATUS_CACHE_ALLOCED_MAX) { - atomic_dec(&ghes_estatus_cache_alloced); - return NULL; - } - len = cper_estatus_len(estatus); - cache_len = GHES_ESTATUS_CACHE_LEN(len); - cache = (void *)gen_pool_alloc(ghes_estatus_pool, cache_len); - if (!cache) { - atomic_dec(&ghes_estatus_cache_alloced); - return NULL; - } - cache_estatus = GHES_ESTATUS_FROM_CACHE(cache); - memcpy(cache_estatus, estatus, len); - cache->estatus_len = len; - atomic_set(&cache->count, 0); - cache->generic = generic; - cache->time_in = sched_clock(); - return cache; -} - -static void ghes_estatus_cache_rcu_free(struct rcu_head *head) -{ - struct ghes_estatus_cache *cache; - u32 len; - - cache = container_of(head, struct ghes_estatus_cache, rcu); - len = cper_estatus_len(GHES_ESTATUS_FROM_CACHE(cache)); - len = GHES_ESTATUS_CACHE_LEN(len); - gen_pool_free(ghes_estatus_pool, (unsigned long)cache, len); - atomic_dec(&ghes_estatus_cache_alloced); -} - -static void -ghes_estatus_cache_add(struct acpi_hest_generic *generic, - struct acpi_hest_generic_status *estatus) -{ - unsigned long long now, duration, period, max_period = 0; - struct ghes_estatus_cache *cache, *new_cache; - struct ghes_estatus_cache __rcu *victim; - int i, slot = -1, count; - - new_cache = ghes_estatus_cache_alloc(generic, estatus); - if (!new_cache) - return; - - rcu_read_lock(); - now = sched_clock(); - for (i = 0; i < GHES_ESTATUS_CACHES_SIZE; i++) { - cache = rcu_dereference(ghes_estatus_caches[i]); - if (cache == NULL) { - slot = i; - break; - } - duration = now - cache->time_in; - if (duration >= GHES_ESTATUS_IN_CACHE_MAX_NSEC) { - slot = i; - break; - } - count = atomic_read(&cache->count); - period = duration; - do_div(period, (count + 1)); - if (period > max_period) { - max_period = period; - slot = i; - } - } - rcu_read_unlock(); - - if (slot != -1) { - /* - * Use release semantics to ensure that ghes_estatus_cached() - * running on another CPU will see the updated cache fields if - * it can see the new value of the pointer. - */ - victim = xchg_release(&ghes_estatus_caches[slot], - RCU_INITIALIZER(new_cache)); - - /* - * At this point, victim may point to a cached item different - * from the one based on which we selected the slot. Instead of - * going to the loop again to pick another slot, let's just - * drop the other item anyway: this may cause a false cache - * miss later on, but that won't cause any problems. - */ - if (victim) - call_rcu(&unrcu_pointer(victim)->rcu, - ghes_estatus_cache_rcu_free); - } -} - static void __ghes_panic(struct ghes *ghes, struct acpi_hest_generic_status *estatus, u64 buf_paddr, enum fixed_addresses fixmap_idx) diff --git a/drivers/acpi/apei/ghes_cper.c b/drivers/acpi/apei/ghes_cper.c index 9c668725e08a..44b644584703 100644 --- a/drivers/acpi/apei/ghes_cper.c +++ b/drivers/acpi/apei/ghes_cper.c @@ -13,10 +13,14 @@ */ #include <linux/err.h> +#include <linux/genalloc.h> #include <linux/io.h> #include <linux/kernel.h> +#include <linux/math64.h> #include <linux/mm.h> #include <linux/ratelimit.h> +#include <linux/rcupdate.h> +#include <linux/sched/clock.h> #include <linux/slab.h> #include <acpi/apei.h> @@ -28,6 +32,9 @@ #include "apei-internal.h" +static struct ghes_estatus_cache __rcu *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE]; +static atomic_t ghes_estatus_cache_alloced; + static void __iomem *ghes_map(u64 pfn, enum fixed_addresses fixmap_idx) { phys_addr_t paddr; @@ -273,3 +280,139 @@ void ghes_clear_estatus(struct ghes *ghes, if (is_hest_type_generic_v2(ghes)) ghes_ack_error(ghes->generic_v2); } + +/* + * GHES error status reporting throttle, to report more kinds of + * errors, instead of just most frequently occurred errors. + */ +int ghes_estatus_cached(struct acpi_hest_generic_status *estatus) +{ + u32 len; + int i, cached = 0; + unsigned long long now; + struct ghes_estatus_cache *cache; + struct acpi_hest_generic_status *cache_estatus; + + len = cper_estatus_len(estatus); + rcu_read_lock(); + for (i = 0; i < GHES_ESTATUS_CACHES_SIZE; i++) { + cache = rcu_dereference(ghes_estatus_caches[i]); + if (cache == NULL) + continue; + if (len != cache->estatus_len) + continue; + cache_estatus = GHES_ESTATUS_FROM_CACHE(cache); + if (memcmp(estatus, cache_estatus, len)) + continue; + atomic_inc(&cache->count); + now = sched_clock(); + if (now - cache->time_in < GHES_ESTATUS_IN_CACHE_MAX_NSEC) + cached = 1; + break; + } + rcu_read_unlock(); + return cached; +} + +static struct ghes_estatus_cache *ghes_estatus_cache_alloc( + struct acpi_hest_generic *generic, + struct acpi_hest_generic_status *estatus) +{ + int alloced; + u32 len, cache_len; + struct ghes_estatus_cache *cache; + struct acpi_hest_generic_status *cache_estatus; + + alloced = atomic_add_return(1, &ghes_estatus_cache_alloced); + if (alloced > GHES_ESTATUS_CACHE_ALLOCED_MAX) { + atomic_dec(&ghes_estatus_cache_alloced); + return NULL; + } + len = cper_estatus_len(estatus); + cache_len = GHES_ESTATUS_CACHE_LEN(len); + cache = (void *)gen_pool_alloc(ghes_estatus_pool, cache_len); + if (cache == NULL) { + atomic_dec(&ghes_estatus_cache_alloced); + return NULL; + } + cache_estatus = GHES_ESTATUS_FROM_CACHE(cache); + memcpy(cache_estatus, estatus, len); + cache->estatus_len = len; + atomic_set(&cache->count, 0); + cache->generic = generic; + cache->time_in = sched_clock(); + return cache; +} + +static void ghes_estatus_cache_rcu_free(struct rcu_head *head) +{ + struct ghes_estatus_cache *cache; + u32 len; + + cache = container_of(head, struct ghes_estatus_cache, rcu); + len = cper_estatus_len(GHES_ESTATUS_FROM_CACHE(cache)); + len = GHES_ESTATUS_CACHE_LEN(len); + gen_pool_free(ghes_estatus_pool, (unsigned long)cache, len); + atomic_dec(&ghes_estatus_cache_alloced); +} + +void ghes_estatus_cache_add(struct acpi_hest_generic *generic, + struct acpi_hest_generic_status *estatus) +{ + unsigned long long now, duration, period, max_period = 0; + struct ghes_estatus_cache *cache, *new_cache; + struct ghes_estatus_cache __rcu *victim; + int i, slot = -1, count; + + new_cache = ghes_estatus_cache_alloc(generic, estatus); + if (!new_cache) + return; + + rcu_read_lock(); + now = sched_clock(); + for (i = 0; i < GHES_ESTATUS_CACHES_SIZE; i++) { + cache = rcu_dereference(ghes_estatus_caches[i]); + if (cache == NULL) { + slot = i; + break; + } + duration = now - cache->time_in; + if (duration >= GHES_ESTATUS_IN_CACHE_MAX_NSEC) { + slot = i; + break; + } + count = atomic_read(&cache->count); + period = duration; + do_div(period, (count + 1)); + if (period > max_period) { + max_period = period; + slot = i; + } + } + rcu_read_unlock(); + + if (slot != -1) { + /* + * Use release semantics to ensure that ghes_estatus_cached() + * running on another CPU will see the updated cache fields if + * it can see the new value of the pointer. + */ + victim = xchg_release(&ghes_estatus_caches[slot], + RCU_INITIALIZER(new_cache)); + + /* + * At this point, victim may point to a cached item different + * from the one based on which we selected the slot. Instead of + * going to the loop again to pick another slot, let's just + * drop the other item anyway: this may cause a false cache + * miss later on, but that won't cause any problems. + */ + if (victim) + call_rcu(&unrcu_pointer(victim)->rcu, + ghes_estatus_cache_rcu_free); + } else { + gen_pool_free(ghes_estatus_pool, (unsigned long)new_cache, + GHES_ESTATUS_CACHE_LEN(new_cache->estatus_len)); + atomic_dec(&ghes_estatus_cache_alloced); + } +} diff --git a/include/acpi/ghes_cper.h b/include/acpi/ghes_cper.h index 4649e3140888..15305c8be9a7 100644 --- a/include/acpi/ghes_cper.h +++ b/include/acpi/ghes_cper.h @@ -55,6 +55,8 @@ ((struct acpi_hest_generic_data *) \ ((struct ghes_vendor_record_entry *)(vendor_entry) + 1)) +extern struct gen_pool *ghes_estatus_pool; + static inline bool is_hest_type_generic_v2(struct ghes *ghes) { return ghes->generic->header.type == ACPI_HEST_TYPE_GENERIC_ERROR_V2; @@ -99,5 +101,8 @@ int __ghes_read_estatus(struct acpi_hest_generic_status *estatus, u64 buf_paddr, enum fixed_addresses fixmap_idx, size_t buf_len); #endif +int ghes_estatus_cached(struct acpi_hest_generic_status *estatus); +void ghes_estatus_cache_add(struct acpi_hest_generic *generic, + struct acpi_hest_generic_status *estatus); #endif /* ACPI_APEI_GHES_CPER_H */ -- 2.43.0
