linux-kernel - [PATCH 1/2] percpu: allow pcpu_alloc() to be called with IRQs off

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-next>] [day] [month] [year] [list]

Message-ID: <alpine.LSU.2.00.0910271328340.19847@wotan.suse.de>
Date:	Tue, 27 Oct 2009 13:32:21 +0100 (CET)
From:	Jiri Kosina <jkosina@...e.cz>
To:	Ingo Molnar <mingo@...e.hu>, Peter Zijlstra <peterz@...radead.org>,
	Tejun Heo <tj@...nel.org>, Jeff Mahoney <jeffm@...e.com>
Cc:	Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
	Tony Luck <tony.luck@...el.com>,
	Fenghua Yu <fenghua.yu@...el.com>, linux-ia64@...r.kernel.org
Subject: [PATCH 1/2] percpu: allow pcpu_alloc() to be called with IRQs off

pcpu_alloc() and pcpu_extend_area_map() perform a series of
spin_lock_irq()/spin_unlock_irq() calls, which make them unsafe
with respect to being called from contexts which have IRQs off.

This patch converts the code to perform save/restore of flags instead,
making pcpu_alloc() (or __alloc_percpu() respectively) to be called
from early kernel startup stage, where IRQs are off.

This is needed for proper initialization of per-cpu rq_weight data from
sched_init().

Signed-off-by: Jiri Kosina <jkosina@...e.cz>
---
 mm/percpu.c |   25 +++++++++++++------------
 1 files changed, 13 insertions(+), 12 deletions(-)

diff --git a/mm/percpu.c b/mm/percpu.c
index 6af78c1..6b82bbf 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -366,7 +366,7 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
  * RETURNS:
  * 0 if noop, 1 if successfully extended, -errno on failure.
  */
-static int pcpu_extend_area_map(struct pcpu_chunk *chunk)
+static int pcpu_extend_area_map(struct pcpu_chunk *chunk, unsigned long *flags)
 {
 	int new_alloc;
 	int *new;
@@ -376,7 +376,7 @@ static int pcpu_extend_area_map(struct pcpu_chunk *chunk)
 	if (chunk->map_alloc >= chunk->map_used + 2)
 		return 0;
 
-	spin_unlock_irq(&pcpu_lock);
+	spin_unlock_irqrestore(&pcpu_lock, *flags);
 
 	new_alloc = PCPU_DFL_MAP_ALLOC;
 	while (new_alloc < chunk->map_used + 2)
@@ -384,7 +384,7 @@ static int pcpu_extend_area_map(struct pcpu_chunk *chunk)
 
 	new = pcpu_mem_alloc(new_alloc * sizeof(new[0]));
 	if (!new) {
-		spin_lock_irq(&pcpu_lock);
+		spin_lock_irqsave(&pcpu_lock, *flags);
 		return -ENOMEM;
 	}
 
@@ -393,7 +393,7 @@ static int pcpu_extend_area_map(struct pcpu_chunk *chunk)
 	 * could have happened inbetween, so map_used couldn't have
 	 * grown.
 	 */
-	spin_lock_irq(&pcpu_lock);
+	spin_lock_irqsave(&pcpu_lock, *flags);
 	BUG_ON(new_alloc < chunk->map_used + 2);
 
 	size = chunk->map_alloc * sizeof(chunk->map[0]);
@@ -1047,6 +1047,7 @@ static void *pcpu_alloc(size_t size, size_t align, bool reserved)
 	struct pcpu_chunk *chunk;
 	const char *err;
 	int slot, off;
+	unsigned long flags;
 
 	if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) {
 		WARN(true, "illegal size (%zu) or align (%zu) for "
@@ -1055,13 +1056,13 @@ static void *pcpu_alloc(size_t size, size_t align, bool reserved)
 	}
 
 	mutex_lock(&pcpu_alloc_mutex);
-	spin_lock_irq(&pcpu_lock);
+	spin_lock_irqsave(&pcpu_lock, flags);
 
 	/* serve reserved allocations from the reserved chunk if available */
 	if (reserved && pcpu_reserved_chunk) {
 		chunk = pcpu_reserved_chunk;
 		if (size > chunk->contig_hint ||
-		    pcpu_extend_area_map(chunk) < 0) {
+		    pcpu_extend_area_map(chunk, &flags) < 0) {
 			err = "failed to extend area map of reserved chunk";
 			goto fail_unlock;
 		}
@@ -1079,7 +1080,7 @@ restart:
 			if (size > chunk->contig_hint)
 				continue;
 
-			switch (pcpu_extend_area_map(chunk)) {
+			switch (pcpu_extend_area_map(chunk, &flags)) {
 			case 0:
 				break;
 			case 1:
@@ -1096,7 +1097,7 @@ restart:
 	}
 
 	/* hmmm... no space left, create a new chunk */
-	spin_unlock_irq(&pcpu_lock);
+	spin_unlock_irqrestore(&pcpu_lock, flags);
 
 	chunk = alloc_pcpu_chunk();
 	if (!chunk) {
@@ -1104,16 +1105,16 @@ restart:
 		goto fail_unlock_mutex;
 	}
 
-	spin_lock_irq(&pcpu_lock);
+	spin_lock_irqsave(&pcpu_lock, flags);
 	pcpu_chunk_relocate(chunk, -1);
 	goto restart;
 
 area_found:
-	spin_unlock_irq(&pcpu_lock);
+	spin_unlock_irqrestore(&pcpu_lock, flags);
 
 	/* populate, map and clear the area */
 	if (pcpu_populate_chunk(chunk, off, size)) {
-		spin_lock_irq(&pcpu_lock);
+		spin_lock_irqsave(&pcpu_lock, flags);
 		pcpu_free_area(chunk, off);
 		err = "failed to populate";
 		goto fail_unlock;
@@ -1125,7 +1126,7 @@ area_found:
 	return __addr_to_pcpu_ptr(chunk->base_addr + off);
 
 fail_unlock:
-	spin_unlock_irq(&pcpu_lock);
+	spin_unlock_irqrestore(&pcpu_lock, flags);
 fail_unlock_mutex:
 	mutex_unlock(&pcpu_alloc_mutex);
 	if (warn_limit) {
-- 
1.6.4.2

--
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/