Commit aa319bcd authored May 22, 2015 by Alexander Shishkin Committed by Ingo Molnar May 27, 2015

perf: Disallow sparse AUX allocations for non-SG PMUs in overwrite mode



PMUs that don't support hardware scatter tables require big contiguous
chunks of memory and a PMI to switch between them. However, in overwrite
using a PMI for this purpose adds extra overhead that the users would
like to avoid. Thus, in overwrite mode for such PMUs we can only allow
one contiguous chunk for the entire requested buffer.

This patch changes the behavior accordingly, so that if the buddy allocator
fails to come up with a single high-order chunk for the entire requested
buffer, the allocation will fail.

Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: acme@infradead.org
Cc: adrian.hunter@intel.com
Cc: hpa@zytor.com
Link: http://lkml.kernel.org/r/1432308626-18845-2-git-send-email-alexander.shishkin@linux.intel.com


Signed-off-by: Ingo Molnar <mingo@kernel.org>

parent cc1790cf

kernel/events/ring_buffer.c

+14 −0

Original line number	Diff line number	Diff line
		@@ -493,6 +493,20 @@ int rb_alloc_aux(struct ring_buffer rb, struct perf_event event,
		rb->aux_pages[rb->aux_nr_pages] = page_address(page++);
		}

		/*
		* In overwrite mode, PMUs that don't support SG may not handle more
		* than one contiguous allocation, since they rely on PMI to do double
		* buffering. In this case, the entire buffer has to be one contiguous
		* chunk.
		*/
		if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_NO_SG) &&
		overwrite) {
		struct page *page = virt_to_page(rb->aux_pages[0]);

		if (page_private(page) != max_order)
		goto out;
		}

		rb->aux_priv = event->pmu->setup_aux(event->cpu, rb->aux_pages, nr_pages,
		overwrite);
		if (!rb->aux_priv)