linux-kernel - [PATCH v8 03/14] perf: Support high-order allocations for AUX space

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1415972627-37514-4-git-send-email-alexander.shishkin@linux.intel.com>
Date:	Fri, 14 Nov 2014 15:43:36 +0200
From:	Alexander Shishkin <alexander.shishkin@...ux.intel.com>
To:	Peter Zijlstra <a.p.zijlstra@...llo.nl>
Cc:	Ingo Molnar <mingo@...hat.com>, linux-kernel@...r.kernel.org,
	Robert Richter <rric@...nel.org>,
	Frederic Weisbecker <fweisbec@...il.com>,
	Mike Galbraith <efault@....de>,
	Paul Mackerras <paulus@...ba.org>,
	Stephane Eranian <eranian@...gle.com>,
	Andi Kleen <ak@...ux.intel.com>, kan.liang@...el.com,
	adrian.hunter@...el.com, markus.t.metzger@...el.com,
	mathieu.poirier@...aro.org, acme@...radead.org,
	Alexander Shishkin <alexander.shishkin@...ux.intel.com>
Subject: [PATCH v8 03/14] perf: Support high-order allocations for AUX space

Some pmus (such as BTS or Intel PT without multiple-entry ToPA capability)
don't support scatter-gather and will prefer larger contiguous areas for
their output regions.

This patch adds a new pmu capability to request higher order allocations.

Signed-off-by: Alexander Shishkin <alexander.shishkin@...ux.intel.com>
---
 include/linux/perf_event.h  |  1 +
 kernel/events/ring_buffer.c | 56 ++++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 51 insertions(+), 6 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 344058c71d..71df948b4d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -171,6 +171,7 @@ struct perf_event;
  * pmu::capabilities flags
  */
 #define PERF_PMU_CAP_NO_INTERRUPT		0x01
+#define PERF_PMU_CAP_AUX_NO_SG			0x02
 
 /**
  * struct pmu - generic performance monitoring unit
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index c6fdce4ea0..6e700e8fd6 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -242,30 +242,74 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
 	spin_lock_init(&rb->event_lock);
 }
 
+#define PERF_AUX_GFP	(GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY)
+
+static struct page *rb_alloc_aux_page(int node, int order)
+{
+	struct page *page;
+
+	if (order > MAX_ORDER)
+		order = MAX_ORDER;
+
+	do {
+		page = alloc_pages_node(node, PERF_AUX_GFP, order);
+	} while (!page && order--);
+
+	if (page && order) {
+		/*
+		 * Communicate the allocation size to the driver
+		 */
+		split_page(page, order);
+		SetPagePrivate(page);
+		set_page_private(page, order);
+	}
+
+	return page;
+}
+
+static void rb_free_aux_page(struct ring_buffer *rb, int idx)
+{
+	struct page *page = virt_to_page(rb->aux_pages[idx]);
+
+	ClearPagePrivate(page);
+	page->mapping = NULL;
+	__free_page(page);
+}
+
 int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
 		 pgoff_t pgoff, int nr_pages, int flags)
 {
 	bool overwrite = !(flags & RING_BUFFER_WRITABLE);
 	int node = (event->cpu == -1) ? -1 : cpu_to_node(event->cpu);
-	int ret = -ENOMEM;
+	int ret = -ENOMEM, max_order = 0;
 
 	if (!has_aux(event))
 		return -ENOTSUPP;
 
+	if (event->pmu->capabilities & PERF_PMU_CAP_AUX_NO_SG)
+		/*
+		 * 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);
+
 	rb->aux_pages = kzalloc_node(nr_pages * sizeof(void *), GFP_KERNEL, node);
 	if (!rb->aux_pages)
 		return -ENOMEM;
 
 	rb->free_aux = event->pmu->free_aux;
-	for (rb->aux_nr_pages = 0; rb->aux_nr_pages < nr_pages;
-	     rb->aux_nr_pages++) {
+	for (rb->aux_nr_pages = 0; rb->aux_nr_pages < nr_pages;) {
 		struct page *page;
+		int last, order;
 
-		page = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0);
+		order = min(max_order, ilog2(nr_pages - rb->aux_nr_pages));
+		page = rb_alloc_aux_page(node, order);
 		if (!page)
 			goto out;
 
-		rb->aux_pages[rb->aux_nr_pages] = page_address(page);
+		for (last = rb->aux_nr_pages + (1 << page_private(page));
+		     last > rb->aux_nr_pages; rb->aux_nr_pages++)
+			rb->aux_pages[rb->aux_nr_pages] = page_address(page++);
 	}
 
 	rb->aux_priv = event->pmu->setup_aux(event->cpu, rb->aux_pages, nr_pages,
@@ -303,7 +347,7 @@ static void __rb_free_aux(struct ring_buffer *rb)
 	}
 
 	for (pg = 0; pg < rb->aux_nr_pages; pg++)
-		free_page((unsigned long)rb->aux_pages[pg]);
+		rb_free_aux_page(rb, pg);
 
 	kfree(rb->aux_pages);
 	rb->aux_nr_pages = 0;
-- 
2.1.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/