From b6a9501658530d8b8374e37f1edb549039a8a260 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 13 Jul 2011 13:14:19 +0800 Subject: ACPI, APEI, GHES, Support disable GHES at boot time Some machine may have broken firmware so that GHES and firmware first mode should be disabled. This patch adds support to that. Signed-off-by: Huang Ying Reviewed-by: Andi Kleen Reviewed-by: Matthew Garrett Signed-off-by: Len Brown --- include/acpi/apei.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/acpi/apei.h b/include/acpi/apei.h index e67b523..d40bc55 100644 --- a/include/acpi/apei.h +++ b/include/acpi/apei.h @@ -18,6 +18,7 @@ extern int hest_disable; extern int erst_disable; +extern int ghes_disable; #ifdef CONFIG_ACPI_APEI void __init acpi_hest_init(void); -- cgit v1.1 From eccddd32ced0df8f9130024157bf8d37df860d76 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 13 Jul 2011 13:14:20 +0800 Subject: ACPI, APEI, Add APEI bit support in generic _OSC call In APEI firmware first mode, hardware error is reported by hardware to firmware firstly, then firmware reports the error to Linux in a GHES error record via POLL/SCI/IRQ/NMI etc. This may result in some issues if OS has no full APEI support. So some firmware implementation will work in a back-compatible mode by default. Where firmware will only notify OS in old-fashion, without GHES record. For example, for a fatal hardware error, only NMI is signaled, no GHES record. To gain full APEI power on these machines, APEI bit in generic _OSC call can be specified to tell firmware that Linux has full APEI support. This patch adds the APEI bit support in generic _OSC call. Signed-off-by: Huang Ying Reviewed-by: Andi Kleen Reviewed-by: Matthew Garrett Signed-off-by: Len Brown --- include/linux/acpi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 1deb2a7..e19527d 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -280,6 +280,8 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); #define OSC_SB_CPUHP_OST_SUPPORT 8 #define OSC_SB_APEI_SUPPORT 16 +extern bool osc_sb_apei_support_acked; + /* PCI defined _OSC bits */ /* _OSC DW1 Definition (OS Support Fields) */ #define OSC_EXT_PCI_CONFIG_SUPPORT 1 -- cgit v1.1 From f49f23abf3dd786ddcac1c1e7db3c2013b07413f Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 13 Jul 2011 13:14:23 +0800 Subject: lib, Add lock-less NULL terminated single list Cmpxchg is used to implement adding new entry to the list, deleting all entries from the list, deleting first entry of the list and some other operations. Because this is a single list, so the tail can not be accessed in O(1). If there are multiple producers and multiple consumers, llist_add can be used in producers and llist_del_all can be used in consumers. They can work simultaneously without lock. But llist_del_first can not be used here. Because llist_del_first depends on list->first->next does not changed if list->first is not changed during its operation, but llist_del_first, llist_add, llist_add (or llist_del_all, llist_add, llist_add) sequence in another consumer may violate that. If there are multiple producers and one consumer, llist_add can be used in producers and llist_del_all or llist_del_first can be used in the consumer. This can be summarized as follow: | add | del_first | del_all add | - | - | - del_first | | L | L del_all | | | - Where "-" stands for no lock is needed, while "L" stands for lock is needed. The list entries deleted via llist_del_all can be traversed with traversing function such as llist_for_each etc. But the list entries can not be traversed safely before deleted from the list. The order of deleted entries is from the newest to the oldest added one. If you want to traverse from the oldest to the newest, you must reverse the order by yourself before traversing. The basic atomic operation of this list is cmpxchg on long. On architectures that don't have NMI-safe cmpxchg implementation, the list can NOT be used in NMI handler. So code uses the list in NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. Signed-off-by: Huang Ying Reviewed-by: Andi Kleen Reviewed-by: Mathieu Desnoyers Cc: Andrew Morton Signed-off-by: Len Brown --- include/linux/llist.h | 126 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 126 insertions(+) create mode 100644 include/linux/llist.h (limited to 'include') diff --git a/include/linux/llist.h b/include/linux/llist.h new file mode 100644 index 0000000..aa0c8b5 --- /dev/null +++ b/include/linux/llist.h @@ -0,0 +1,126 @@ +#ifndef LLIST_H +#define LLIST_H +/* + * Lock-less NULL terminated single linked list + * + * If there are multiple producers and multiple consumers, llist_add + * can be used in producers and llist_del_all can be used in + * consumers. They can work simultaneously without lock. But + * llist_del_first can not be used here. Because llist_del_first + * depends on list->first->next does not changed if list->first is not + * changed during its operation, but llist_del_first, llist_add, + * llist_add (or llist_del_all, llist_add, llist_add) sequence in + * another consumer may violate that. + * + * If there are multiple producers and one consumer, llist_add can be + * used in producers and llist_del_all or llist_del_first can be used + * in the consumer. + * + * This can be summarized as follow: + * + * | add | del_first | del_all + * add | - | - | - + * del_first | | L | L + * del_all | | | - + * + * Where "-" stands for no lock is needed, while "L" stands for lock + * is needed. + * + * The list entries deleted via llist_del_all can be traversed with + * traversing function such as llist_for_each etc. But the list + * entries can not be traversed safely before deleted from the list. + * The order of deleted entries is from the newest to the oldest added + * one. If you want to traverse from the oldest to the newest, you + * must reverse the order by yourself before traversing. + * + * The basic atomic operation of this list is cmpxchg on long. On + * architectures that don't have NMI-safe cmpxchg implementation, the + * list can NOT be used in NMI handler. So code uses the list in NMI + * handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. + */ + +struct llist_head { + struct llist_node *first; +}; + +struct llist_node { + struct llist_node *next; +}; + +#define LLIST_HEAD_INIT(name) { NULL } +#define LLIST_HEAD(name) struct llist_head name = LLIST_HEAD_INIT(name) + +/** + * init_llist_head - initialize lock-less list head + * @head: the head for your lock-less list + */ +static inline void init_llist_head(struct llist_head *list) +{ + list->first = NULL; +} + +/** + * llist_entry - get the struct of this entry + * @ptr: the &struct llist_node pointer. + * @type: the type of the struct this is embedded in. + * @member: the name of the llist_node within the struct. + */ +#define llist_entry(ptr, type, member) \ + container_of(ptr, type, member) + +/** + * llist_for_each - iterate over some deleted entries of a lock-less list + * @pos: the &struct llist_node to use as a loop cursor + * @node: the first entry of deleted list entries + * + * In general, some entries of the lock-less list can be traversed + * safely only after being deleted from list, so start with an entry + * instead of list head. + * + * If being used on entries deleted from lock-less list directly, the + * traverse order is from the newest to the oldest added entry. If + * you want to traverse from the oldest to the newest, you must + * reverse the order by yourself before traversing. + */ +#define llist_for_each(pos, node) \ + for ((pos) = (node); pos; (pos) = (pos)->next) + +/** + * llist_for_each_entry - iterate over some deleted entries of lock-less list of given type + * @pos: the type * to use as a loop cursor. + * @node: the fist entry of deleted list entries. + * @member: the name of the llist_node with the struct. + * + * In general, some entries of the lock-less list can be traversed + * safely only after being removed from list, so start with an entry + * instead of list head. + * + * If being used on entries deleted from lock-less list directly, the + * traverse order is from the newest to the oldest added entry. If + * you want to traverse from the oldest to the newest, you must + * reverse the order by yourself before traversing. + */ +#define llist_for_each_entry(pos, node, member) \ + for ((pos) = llist_entry((node), typeof(*(pos)), member); \ + &(pos)->member != NULL; \ + (pos) = llist_entry((pos)->member.next, typeof(*(pos)), member)) + +/** + * llist_empty - tests whether a lock-less list is empty + * @head: the list to test + * + * Not guaranteed to be accurate or up to date. Just a quick way to + * test whether the list is empty without deleting something from the + * list. + */ +static inline int llist_empty(const struct llist_head *head) +{ + return ACCESS_ONCE(head->first) == NULL; +} + +void llist_add(struct llist_node *new, struct llist_head *head); +void llist_add_batch(struct llist_node *new_first, struct llist_node *new_last, + struct llist_head *head); +struct llist_node *llist_del_first(struct llist_head *head); +struct llist_node *llist_del_all(struct llist_head *head); +#endif /* LLIST_H */ -- cgit v1.1 From 7f184275aa306046fe7edcbef3229754f0d97402 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 13 Jul 2011 13:14:24 +0800 Subject: lib, Make gen_pool memory allocator lockless This version of the gen_pool memory allocator supports lockless operation. This makes it safe to use in NMI handlers and other special unblockable contexts that could otherwise deadlock on locks. This is implemented by using atomic operations and retries on any conflicts. The disadvantage is that there may be livelocks in extreme cases. For better scalability, one gen_pool allocator can be used for each CPU. The lockless operation only works if there is enough memory available. If new memory is added to the pool a lock has to be still taken. So any user relying on locklessness has to ensure that sufficient memory is preallocated. The basic atomic operation of this allocator is cmpxchg on long. On architectures that don't have NMI-safe cmpxchg implementation, the allocator can NOT be used in NMI handler. So code uses the allocator in NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. Signed-off-by: Huang Ying Reviewed-by: Andi Kleen Reviewed-by: Mathieu Desnoyers Cc: Andrew Morton Signed-off-by: Len Brown --- include/linux/bitmap.h | 1 + include/linux/genalloc.h | 34 ++++++++++++++++++++++++++++------ 2 files changed, 29 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index dcafe0b..907dd58 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -145,6 +145,7 @@ extern void bitmap_release_region(unsigned long *bitmap, int pos, int order); extern int bitmap_allocate_region(unsigned long *bitmap, int pos, int order); extern void bitmap_copy_le(void *dst, const unsigned long *src, int nbits); +#define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) % BITS_PER_LONG)) #define BITMAP_LAST_WORD_MASK(nbits) \ ( \ ((nbits) % BITS_PER_LONG) ? \ diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h index 5bbebda..5e98eeb 100644 --- a/include/linux/genalloc.h +++ b/include/linux/genalloc.h @@ -1,8 +1,26 @@ /* - * Basic general purpose allocator for managing special purpose memory - * not managed by the regular kmalloc/kfree interface. - * Uses for this includes on-device special memory, uncached memory - * etc. + * Basic general purpose allocator for managing special purpose + * memory, for example, memory that is not managed by the regular + * kmalloc/kfree interface. Uses for this includes on-device special + * memory, uncached memory etc. + * + * It is safe to use the allocator in NMI handlers and other special + * unblockable contexts that could otherwise deadlock on locks. This + * is implemented by using atomic operations and retries on any + * conflicts. The disadvantage is that there may be livelocks in + * extreme cases. For better scalability, one allocator can be used + * for each CPU. + * + * The lockless operation only works if there is enough memory + * available. If new memory is added to the pool a lock has to be + * still taken. So any user relying on locklessness has to ensure + * that sufficient memory is preallocated. + * + * The basic atomic operation of this allocator is cmpxchg on long. + * On architectures that don't have NMI-safe cmpxchg implementation, + * the allocator can NOT be used in NMI handler. So code uses the + * allocator in NMI handler should depend on + * CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG. * * This source code is licensed under the GNU General Public License, * Version 2. See the file COPYING for more details. @@ -15,7 +33,7 @@ * General purpose special memory pool descriptor. */ struct gen_pool { - rwlock_t lock; + spinlock_t lock; struct list_head chunks; /* list of chunks in this pool */ int min_alloc_order; /* minimum allocation order */ }; @@ -24,8 +42,8 @@ struct gen_pool { * General purpose special memory pool chunk descriptor. */ struct gen_pool_chunk { - spinlock_t lock; struct list_head next_chunk; /* next chunk in pool */ + atomic_t avail; phys_addr_t phys_addr; /* physical starting address of memory chunk */ unsigned long start_addr; /* starting address of memory chunk */ unsigned long end_addr; /* ending address of memory chunk */ @@ -56,4 +74,8 @@ static inline int gen_pool_add(struct gen_pool *pool, unsigned long addr, extern void gen_pool_destroy(struct gen_pool *); extern unsigned long gen_pool_alloc(struct gen_pool *, size_t); extern void gen_pool_free(struct gen_pool *, unsigned long, size_t); +extern void gen_pool_for_each_chunk(struct gen_pool *, + void (*)(struct gen_pool *, struct gen_pool_chunk *, void *), void *); +extern size_t gen_pool_avail(struct gen_pool *); +extern size_t gen_pool_size(struct gen_pool *); #endif /* __GENALLOC_H__ */ -- cgit v1.1 From ea8f5fb8a71fddaf5f3a17100d3247855701f732 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 13 Jul 2011 13:14:27 +0800 Subject: HWPoison: add memory_failure_queue() memory_failure() is the entry point for HWPoison memory error recovery. It must be called in process context. But commonly hardware memory errors are notified via MCE or NMI, so some delayed execution mechanism must be used. In MCE handler, a work queue + ring buffer mechanism is used. In addition to MCE, now APEI (ACPI Platform Error Interface) GHES (Generic Hardware Error Source) can be used to report memory errors too. To add support to APEI GHES memory recovery, a mechanism similar to that of MCE is implemented. memory_failure_queue() is the new entry point that can be called in IRQ context. The next step is to make MCE handler uses this interface too. Signed-off-by: Huang Ying Cc: Andi Kleen Cc: Wu Fengguang Cc: Andrew Morton Signed-off-by: Len Brown --- include/linux/mm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9670f71..303108e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1633,6 +1633,7 @@ enum mf_flags { }; extern void memory_failure(unsigned long pfn, int trapno); extern int __memory_failure(unsigned long pfn, int trapno, int flags); +extern void memory_failure_queue(unsigned long pfn, int trapno, int flags); extern int unpoison_memory(unsigned long pfn); extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; -- cgit v1.1 From a7e09d450b2e0b068e850d103b6ee1af537d1910 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Sat, 16 Jul 2011 18:14:21 -0400 Subject: ACPI: APEI build fix as GHES is optional... When # CONFIG_ACPI_APEI_GHES is not set: (.init.text+0x4c22): undefined reference to `ghes_disable' Reported-by: Randy Dunlap Acked-by: Randy Dunlap Signed-off-by: Len Brown --- include/acpi/apei.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/acpi/apei.h b/include/acpi/apei.h index d40bc55..51a527d 100644 --- a/include/acpi/apei.h +++ b/include/acpi/apei.h @@ -18,7 +18,11 @@ extern int hest_disable; extern int erst_disable; +#ifdef CONFIG_ACPI_APEI_GHES extern int ghes_disable; +#else +#define ghes_disable 1 +#endif #ifdef CONFIG_ACPI_APEI void __init acpi_hest_init(void); -- cgit v1.1