Re: [PATCH v4] perf: Allocate non-contiguous AUX pages by default

On 07/05/2025 7:13 pm, Yabin Cui wrote:

perf always allocates contiguous AUX pages based on aux_watermark. However, this contiguous allocation doesn't benefit all PMUs. For instance, ARM SPE and TRBE operate with virtual pages, and Coresight ETR allocates a separate buffer. For these PMUs, allocating contiguous AUX pages unnecessarily exacerbates memory fragmentation. This fragmentation can prevent their use on long-running devices.

This patch modifies the perf driver to be memory-friendly by default, by allocating non-contiguous AUX pages. For PMUs requiring contiguous pages (Intel BTS and some Intel PT), the existing PERF_PMU_CAP_AUX_NO_SG capability can be used. For PMUs that don't require but can benefit from contiguous pages (some Intel PT), a new capability, PERF_PMU_CAP_AUX_PREFER_LARGE, is added to maintain their existing behavior.

Signed-off-by: Yabin Cui yabinc@google.com

Changes since v3: Add comments and a local variable to explain max_order value changes in rb_alloc_aux().

Changes since v2: Let NO_SG imply PREFER_LARGE. So PMUs don't need to set both flags. Then the only place needing PREFER_LARGE is intel/pt.c.

Changes since v1: In v1, default is preferring contiguous pages, and add a flag to allocate non-contiguous pages. In v2, default is allocating non-contiguous pages, and add a flag to prefer contiguous pages.

v1 patchset: perf,coresight: Reduce fragmentation with non-contiguous AUX pages for cs_etm

arch/x86/events/intel/pt.c | 2 ++ include/linux/perf_event.h | 1 + kernel/events/ring_buffer.c | 33 ++++++++++++++++++++++++--------- 3 files changed, 27 insertions(+), 9 deletions(-)

diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index fa37565f6418..25ead919fc48 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -1863,6 +1863,8 @@ static __init int pt_init(void) if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries)) pt_pmu.pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG;

• else

• pt_pmu.pmu.capabilities = PERF_PMU_CAP_AUX_PREFER_LARGE;
  

pt_pmu.pmu.capabilities |= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE | diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 0069ba6866a4..56d77348c511 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -301,6 +301,7 @@ struct perf_event_pmu_context; #define PERF_PMU_CAP_AUX_OUTPUT 0x0080 #define PERF_PMU_CAP_EXTENDED_HW_TYPE 0x0100 #define PERF_PMU_CAP_AUX_PAUSE 0x0200 +#define PERF_PMU_CAP_AUX_PREFER_LARGE 0x0400 /**

• pmu::scope

diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 5130b119d0ae..69c90ea1b79a 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -679,7 +679,19 @@ int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event, { bool overwrite = !(flags & RING_BUFFER_WRITABLE); int node = (event->cpu == -1) ? -1 : cpu_to_node(event->cpu);

• int ret = -ENOMEM, max_order;

• /*

• * True if the PMU needs a contiguous AUX buffer (CAP_AUX_NO_SG) or
  

• * prefers large contiguous pages (CAP_AUX_PREFER_LARGE).
  

• */
  

• bool use_contiguous_pages = event->pmu->capabilities & (> +

PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_AUX_PREFER_LARGE);

Reviewed-by: James Clark james.clark@linaro.org

Minor nit: this comment is a bit verbose IMO, and it's only describing what rather than why. But the other one is ok.

• /*

• * Initialize max_order to 0 for page allocation. This allocates single
  

• * pages to minimize memory fragmentation. This is overriden if
  

• * use_contiguous_pages is true.
  

• */
  

• int max_order = 0;
• int ret = -ENOMEM;

if (!has_aux(event)) return -EOPNOTSUPP; @@ -689,8 +701,8 @@ int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event, if (!overwrite) { /*

•  * Watermark defaults to half the buffer, and so does the
  

•  * max_order, to aid PMU drivers in double buffering.
  

•  * Watermark defaults to half the buffer, to aid PMU drivers
  

•  * in double buffering.
  

  */ if (!watermark) watermark = min_t(unsigned long,

@@ -698,16 +710,19 @@ int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event, (unsigned long)nr_pages << (PAGE_SHIFT - 1)); /*

•  * Use aux_watermark as the basis for chunking to
  

•  * help PMU drivers honor the watermark.
  

•  * If using contiguous pages, use aux_watermark as the basis
  

•  * for chunking to help PMU drivers honor the watermark.
  

  */

• max_order = get_order(watermark);
  

• if (use_contiguous_pages)
  

• 	max_order = get_order(watermark);
  

  } else { /*

•  * We need to start with the max_order that fits in nr_pages,
  

•  * not the other way around, hence ilog2() and not get_order.
  

•  * If using contiguous pages, we need to start with the
  

•  * max_order that fits in nr_pages, not the other way around,
  

•  * hence ilog2() and not get_order.
  

  */

• max_order = ilog2(nr_pages);
  

• if (use_contiguous_pages)
  

• 	max_order = ilog2(nr_pages);
  

  watermark = 0; }