Lines Matching full:allocations

99 /* Pool usage% threshold when currently covered allocations are skipped. */
136  * to gate allocations, to avoid a load and compare if KFENCE is disabled.
145  * allocations of the same source filling up the pool.
147  * Assuming a range of 15%-85% unique allocations in the pool at any point in
184 	[KFENCE_COUNTER_ALLOCS]		= "total allocations",
186 	[KFENCE_COUNTER_ZOMBIES]	= "zombie allocations",
188 	[KFENCE_COUNTER_SKIP_INCOMPAT]	= "skipped allocations (incompatible)",
189 	[KFENCE_COUNTER_SKIP_CAPACITY]	= "skipped allocations (capacity)",
190 	[KFENCE_COUNTER_SKIP_COVERED]	= "skipped allocations (covered)",
439 	 * Note: for allocations made before RNG initialization, will always  in kfence_guarded_alloc()
442 	 * KFENCE to detect bugs due to earlier allocations. The only downside  in kfence_guarded_alloc()
444 	 * such allocations.  in kfence_guarded_alloc()
675 		 * otherwise overlap with allocations returned by kfence_alloc(), which  in kfence_init_pool_early()
820  * avoids IPIs, at the cost of not immediately capturing allocations if the
1017 			 * This cache still has allocations, and we should not  in kfence_shutdown_cache()
1020 			 * behaviour of keeping the allocations alive (leak the  in kfence_shutdown_cache()
1022 			 * allocations" as the KFENCE objects are the only ones  in kfence_shutdown_cache()
1064 	 * Skip allocations from non-default zones, including DMA. We cannot  in __kfence_alloc()
1076 	 * Skip allocations for this slab, if KFENCE has been disabled for  in __kfence_alloc()
1091 		 * Calling wake_up() here may deadlock when allocations happen  in __kfence_alloc()
1109 	 * full, including avoiding long-lived allocations of the same source  in __kfence_alloc()
1110 	 * filling up the pool (e.g. pagecache allocations).  in __kfence_alloc()