#include #include /* * One struct ghes is created for each generic hardware error source. * It provides the context for APEI hardware error timer/IRQ/SCI/NMI * handler. * * estatus: memory buffer for error status block, allocated during * HEST parsing. */ #define GHES_TO_CLEAR 0x0001 #define GHES_EXITING 0x0002 struct ghes { struct acpi_hest_generic *generic; struct acpi_hest_generic_status *estatus; u64 buffer_paddr; unsigned long flags; union { struct list_head list; struct timer_list timer; unsigned int irq; }; }; struct ghes_estatus_node { struct llist_node llnode; struct acpi_hest_generic *generic; struct ghes *ghes; }; struct ghes_estatus_cache { u32 estatus_len; atomic_t count; struct acpi_hest_generic *generic; unsigned long long time_in; struct rcu_head rcu; }; enum { GHES_SEV_NO = 0x0, GHES_SEV_CORRECTED = 0x1, GHES_SEV_RECOVERABLE = 0x2, GHES_SEV_PANIC = 0x3, }; /* From drivers/edac/ghes_edac.c */ #ifdef CONFIG_EDAC_GHES void ghes_edac_report_mem_error(struct ghes *ghes, int sev, struct cper_sec_mem_err *mem_err); int ghes_edac_register(struct ghes *ghes, struct device *dev); void ghes_edac_unregister(struct ghes *ghes); #else static inline void ghes_edac_report_mem_error(struct ghes *ghes, int sev, struct cper_sec_mem_err *mem_err) { } static inline int ghes_edac_register(struct ghes *ghes, struct device *dev) { return 0; } static inline void ghes_edac_unregister(struct ghes *ghes) { } #endif net-next plumbingsTobias Klauser
summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDouglas Miller <dougmill@linux.vnet.ibm.com>2017-01-28 06:42:20 -0600
committerTejun Heo <tj@kernel.org>2017-01-28 07:49:42 -0500
commit966d2b04e070bc040319aaebfec09e0144dc3341 (patch)
tree4b96156e3d1dd4dfd6039b7c219c9dc4616da52d /tools/testing/selftests/futex/include/futextest.h
parent1b1bc42c1692e9b62756323c675a44cb1a1f9dbd (diff)
percpu-refcount: fix reference leak during percpu-atomic transition
percpu_ref_tryget() and percpu_ref_tryget_live() should return "true" IFF they acquire a reference. But the return value from atomic_long_inc_not_zero() is a long and may have high bits set, e.g. PERCPU_COUNT_BIAS, and the return value of the tryget routines is bool so the reference may actually be acquired but the routines return "false" which results in a reference leak since the caller assumes it does not need to do a corresponding percpu_ref_put(). This was seen when performing CPU hotplug during I/O, as hangs in blk_mq_freeze_queue_wait where percpu_ref_kill (blk_mq_freeze_queue_start) raced with percpu_ref_tryget (blk_mq_timeout_work). Sample stack trace: __switch_to+0x2c0/0x450 __schedule+0x2f8/0x970 schedule+0x48/0xc0 blk_mq_freeze_queue_wait+0x94/0x120 blk_mq_queue_reinit_work+0xb8/0x180 blk_mq_queue_reinit_prepare+0x84/0xa0 cpuhp_invoke_callback+0x17c/0x600 cpuhp_up_callbacks+0x58/0x150 _cpu_up+0xf0/0x1c0 do_cpu_up+0x120/0x150 cpu_subsys_online+0x64/0xe0 device_online+0xb4/0x120 online_store+0xb4/0xc0 dev_attr_store+0x68/0xa0 sysfs_kf_write+0x80/0xb0 kernfs_fop_write+0x17c/0x250 __vfs_write+0x6c/0x1e0 vfs_write+0xd0/0x270 SyS_write+0x6c/0x110 system_call+0x38/0xe0 Examination of the queue showed a single reference (no PERCPU_COUNT_BIAS, and __PERCPU_REF_DEAD, __PERCPU_REF_ATOMIC set) and no requests. However, conditions at the time of the race are count of PERCPU_COUNT_BIAS + 0 and __PERCPU_REF_DEAD and __PERCPU_REF_ATOMIC set. The fix is to make the tryget routines use an actual boolean internally instead of the atomic long result truncated to a int. Fixes: e625305b3907 percpu-refcount: make percpu_ref based on longs instead of ints Link: https://bugzilla.kernel.org/show_bug.cgi?id=190751 Signed-off-by: Douglas Miller <dougmill@linux.vnet.ibm.com> Reviewed-by: Jens Axboe <axboe@fb.com> Signed-off-by: Tejun Heo <tj@kernel.org> Fixes: e625305b3907 ("percpu-refcount: make percpu_ref based on longs instead of ints") Cc: stable@vger.kernel.org # v3.18+
Diffstat (limited to 'tools/testing/selftests/futex/include/futextest.h')