[PATCH] RAID-6: x86-64 crash workaround

From: "H. Peter Anvin" <hpa@zytor.com>

Apparently, on x86-64, the stack isn't always aligned properly (16 bytes)
in the kernel at the moment.  This causes the RAID-6 code to crash the
system.  This patch is a workaround for that; the right thing is to muck
with the assembly entrypoints to enforce proper stack alignment.  However,
that's not anything I feel comfortable doing in an evening, especially
since I don't have a machine on which I can test the resulting kernels.

diff --git a/drivers/md/raid6x86.h b/drivers/md/raid6x86.h
index 0579c764dd095f57f8316eb8ebdb9feb0e087dee..41867a6903d62ef2ba53082d1c83d44579e4df8a 100644 (file)
--- a/drivers/md/raid6x86.h
+++ b/drivers/md/raid6x86.h
@@ -32,18 +32,20 @@ typedef struct {
 /* N.B.: For SSE we only save %xmm0-%xmm7 even for x86-64, since
    the code doesn't know about the additional x86-64 registers */
 typedef struct {
-       unsigned int sarea[8*4];
-       unsigned int cr0;
+       unsigned int sarea[8*4+2];
+       unsigned long cr0;
 } raid6_sse_save_t __attribute__((aligned(16)));
 
 /* This is for x86-64-specific code which uses all 16 XMM registers */
 typedef struct {
-       unsigned int sarea[16*4];
+       unsigned int sarea[16*4+2];
        unsigned long cr0;
 } raid6_sse16_save_t __attribute__((aligned(16)));
 
-/* On x86-64 the stack is 16-byte aligned */
-#define SAREA(x) (x->sarea)
+/* On x86-64 the stack *SHOULD* be 16-byte aligned, but currently this
+   is buggy in the kernel and it's only 8-byte aligned in places, so
+   we need to do this anyway.  Sigh. */
+#define SAREA(x) ((unsigned int *)((((unsigned long)&(x)->sarea)+15) & ~15))
 
 #else /* __i386__ */
 
@@ -60,6 +62,7 @@ typedef struct {
        unsigned long cr0;
 } raid6_sse_save_t;
 
+/* Find the 16-byte aligned save area */
 #define SAREA(x) ((unsigned int *)((((unsigned long)&(x)->sarea)+15) & ~15))
 
 #endif