[RFC PATCH v2] prevent top pte being overwritten before flushing
Andrew Yan-Pai Chen
yanpai.chen at gmail.com
Sun Oct 14 13:42:22 EDT 2012
From: Yan-Pai Chen <ypchen at faraday-tech.com>
Since flush_pfn_alias() is preemptible, it is possible to be
preempted just after set_top_pte() is done. If the process
which preempts the previous happened to invoke flush_pfn_alias()
with the same colour vaddr as that of the previous, the same
top pte will be overwritten. When switching back to the previous,
it attempts to flush cache lines with incorrect mapping. Then
no lines (or wrong lines) will be flushed because of the nature
of vipt caches.
flush_icache_alias() has the same problem as well. However, as it
could be called in SMP setups, we prevent concurrent overwrites of
top pte by having a lock on it.
Signed-off-by: JasonLin <wwlin at faraday-tech.com>
Signed-off-by: Yan-Pai Chen <ypchen at faraday-tech.com>
---
arch/arm/mm/flush.c | 11 +++++++++++
1 files changed, 11 insertions(+), 0 deletions(-)
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 40ca11e..b6510f4 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -11,6 +11,7 @@
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
+#include <linux/spinlock.h>
#include <asm/cacheflush.h>
#include <asm/cachetype.h>
@@ -22,11 +23,15 @@
#ifdef CONFIG_CPU_CACHE_VIPT
+static DEFINE_RAW_SPINLOCK(flush_lock);
+
+/* Beware that this function is not to be called for SMP setups. */
static void flush_pfn_alias(unsigned long pfn, unsigned long vaddr)
{
unsigned long to = FLUSH_ALIAS_START + (CACHE_COLOUR(vaddr) << PAGE_SHIFT);
const int zero = 0;
+ preempt_disable();
set_top_pte(to, pfn_pte(pfn, PAGE_KERNEL));
asm( "mcrr p15, 0, %1, %0, c14\n"
@@ -34,6 +39,8 @@ static void flush_pfn_alias(unsigned long pfn, unsigned long vaddr)
:
: "r" (to), "r" (to + PAGE_SIZE - L1_CACHE_BYTES), "r" (zero)
: "cc");
+
+ preempt_enable();
}
static void flush_icache_alias(unsigned long pfn, unsigned long vaddr, unsigned long len)
@@ -42,9 +49,13 @@ static void flush_icache_alias(unsigned long pfn, unsigned long vaddr, unsigned
unsigned long offset = vaddr & (PAGE_SIZE - 1);
unsigned long to;
+ raw_spin_lock(&flush_lock);
+
set_top_pte(va, pfn_pte(pfn, PAGE_KERNEL));
to = va + offset;
flush_icache_range(to, to + len);
+
+ raw_spin_unlock(&flush_lock);
}
void flush_cache_mm(struct mm_struct *mm)
--
1.7.4.1
More information about the linux-arm-kernel
mailing list