Lines Matching full:allocations

98 /* Pool usage% threshold when currently covered allocations are skipped. */
135  * to gate allocations, to avoid a load and compare if KFENCE is disabled.
144  * allocations of the same source filling up the pool.
146  * Assuming a range of 15%-85% unique allocations in the pool at any point in
183 	[KFENCE_COUNTER_ALLOCS]		= "total allocations",
185 	[KFENCE_COUNTER_ZOMBIES]	= "zombie allocations",
187 	[KFENCE_COUNTER_SKIP_INCOMPAT]	= "skipped allocations (incompatible)",
188 	[KFENCE_COUNTER_SKIP_CAPACITY]	= "skipped allocations (capacity)",
189 	[KFENCE_COUNTER_SKIP_COVERED]	= "skipped allocations (covered)",
438 	 * Note: for allocations made before RNG initialization, will always  in kfence_guarded_alloc()
441 	 * KFENCE to detect bugs due to earlier allocations. The only downside  in kfence_guarded_alloc()
443 	 * such allocations.  in kfence_guarded_alloc()
674 		 * otherwise overlap with allocations returned by kfence_alloc(), which  in kfence_init_pool_early()
819  * avoids IPIs, at the cost of not immediately capturing allocations if the
1016 			 * This cache still has allocations, and we should not  in kfence_shutdown_cache()
1019 			 * behaviour of keeping the allocations alive (leak the  in kfence_shutdown_cache()
1021 			 * allocations" as the KFENCE objects are the only ones  in kfence_shutdown_cache()
1063 	 * Skip allocations from non-default zones, including DMA. We cannot  in __kfence_alloc()
1074 	 * Skip allocations for this slab, if KFENCE has been disabled for  in __kfence_alloc()
1089 		 * Calling wake_up() here may deadlock when allocations happen  in __kfence_alloc()
1107 	 * full, including avoiding long-lived allocations of the same source  in __kfence_alloc()
1108 	 * filling up the pool (e.g. pagecache allocations).  in __kfence_alloc()