/* * Quicklist support. * * Quicklists are light weight lists of pages that have a defined state * on alloc and free. Pages must be in the quicklist specific defined state * (zero by default) when the page is freed. It seems that the initial idea * for such lists first came from Dave Miller and then various other people * improved on it. * * Copyright (C) 2007 SGI, * Christoph Lameter * Generalized, added support for multiple lists and * constructors / destructors. */ #include #include #include #include #include DEFINE_PER_CPU(struct quicklist [CONFIG_NR_QUICK], quicklist); #define FRACTION_OF_NODE_MEM 16 static unsigned long max_pages(unsigned long min_pages) { unsigned long node_free_pages, max; int node = numa_node_id(); struct zone *zones = NODE_DATA(node)->node_zones; int num_cpus_on_node; node_free_pages = #ifdef CONFIG_ZONE_DMA zone_page_state(&zones[ZONE_DMA], NR_FREE_PAGES) + #endif #ifdef CONFIG_ZONE_DMA32 zone_page_state(&zones[ZONE_DMA32], NR_FREE_PAGES) + #endif zone_page_state(&zones[ZONE_NORMAL], NR_FREE_PAGES); max = node_free_pages / FRACTION_OF_NODE_MEM; num_cpus_on_node = cpumask_weight(cpumask_of_node(node)); max /= num_cpus_on_node; return max(max, min_pages); } static long min_pages_to_free(struct quicklist *q, unsigned long min_pages, long max_free) { long pages_to_free; pages_to_free = q->nr_pages - max_pages(min_pages); return min(pages_to_free, max_free); } /* * Trim down the number of pages in the quicklist */ void quicklist_trim(int nr, void (*dtor)(void *), unsigned long min_pages, unsigned long max_free) { long pages_to_free; struct quicklist *q; q = &get_cpu_var(quicklist)[nr]; if (q->nr_pages > min_pages) { pages_to_free = min_pages_to_free(q, min_pages, max_free); while (pages_to_free > 0) { /* * We pass a gfp_t of 0 to quicklist_alloc here * because we will never call into the page allocator. */ void *p = quicklist_alloc(nr, 0, NULL); if (dtor) dtor(p); free_page((unsigned long)p); pages_to_free--; } } put_cpu_var(quicklist); } unsigned long quicklist_total_size(void) { unsigned long count = 0; int cpu; struct quicklist *ql, *q; for_each_online_cpu(cpu) { ql = per_cpu(quicklist, cpu); for (q = ql; q < ql + CONFIG_NR_QUICK; q++) count += q->nr_pages; } return count; } c040319aaebfec09e0144dc3341'/>
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/ptp/.gitignore
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/ptp/.gitignore')