[PATCH 1/2] powerpc: Send SIGBUS on unaligned copy and paste

Subsystems: linux for powerpc (32-bit and 64-bit), the rest

STALE3718d

3 messages, 2 authors, 2016-06-14 · open the first message on its own page

[PATCH 1/2] powerpc: Send SIGBUS on unaligned copy and paste

From: Chris Smart <hidden>
Date: 2016-06-09 06:08:26

Calling ISA 3.0 instructions copy, copy_first, paste and paste_last
generates an alignment fault when copying or pasting unaligned
data (128 byte). We catch this and send SIGBUS to the userspace
process that caused it.

We do not emulate these because paste may contain additional metadata
when pasting to a co-processor and paste_last is the synchronisation
point for preceding copy/paste sequences.

Thanks to Michael Neuling [off-list ref] for his help.

Signed-off-by: Chris Smart <redacted>
---
 arch/powerpc/kernel/align.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index 8e7cb8e2b21a..fcdf09476eec 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -875,6 +875,21 @@ int fix_alignment(struct pt_regs *regs)
 		return emulate_vsx(addr, reg, areg, regs, flags, nb, elsize);
 	}
 #endif
+
+	/*
+	 * ISA 3.0 (such as P9) copy, copy_first, paste and paste_last alignment
+	 * check.
+	 *
+	 * Send a SIGBUS to the process that caused the fault.
+	 *
+	 * We do not emulate these because paste may contain additional metadata
+	 * when pasting to a co-processor. Furthermore, paste_last is the
+	 * synchronisation point for preceding copy/paste sequences.
+	 */
+	if ((instruction & 0xfc0006fe) == 0x7c00060c){
+		return -EIO;
+	}
+
 	/* A size of 0 indicates an instruction we don't support, with
 	 * the exception of DCBZ which is handled as a special case here
 	 */
-- 
2.7.4

Re: [PATCH 1/2] powerpc: Send SIGBUS on unaligned copy and paste

From: Christophe Leroy <hidden>
Date: 2016-06-09 06:57:54

Le 09/06/2016 à 08:01, Chris Smart a écrit :
quoted hunk
Calling ISA 3.0 instructions copy, copy_first, paste and paste_last
generates an alignment fault when copying or pasting unaligned
data (128 byte). We catch this and send SIGBUS to the userspace
process that caused it.

We do not emulate these because paste may contain additional metadata
when pasting to a co-processor and paste_last is the synchronisation
point for preceding copy/paste sequences.

Thanks to Michael Neuling [off-list ref] for his help.

Signed-off-by: Chris Smart <redacted>
---
arch/powerpc/kernel/align.c | 15 +++++++++++++++
1 file changed, 15 insertions(+)
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index 8e7cb8e2b21a..fcdf09476eec 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -875,6 +875,21 @@ int fix_alignment(struct pt_regs *regs)
        return emulate_vsx(addr, reg, areg, regs, flags, nb, elsize);
    }
#endif
+
+    /*
+     * ISA 3.0 (such as P9) copy, copy_first, paste and paste_last 
alignment
+     * check.
+     *
+     * Send a SIGBUS to the process that caused the fault.
+     *
+     * We do not emulate these because paste may contain additional 
metadata
+     * when pasting to a co-processor. Furthermore, paste_last is the
+     * synchronisation point for preceding copy/paste sequences.
+     */
+    if ((instruction & 0xfc0006fe) == 0x7c00060c){
Can you define corresponding instruction and mask in 
arch/powerpc/include/asm/ppc-opcode.h
and use symbolic names here instead of raw values ?

Christophe

Re: [PATCH 1/2] powerpc: Send SIGBUS on unaligned copy and paste

From: Chris Smart <hidden>
Date: 2016-06-14 01:51:09

On Thu, Jun 09, 2016 at 08:57:50AM +0200, Christophe Leroy wrote:
Le 09/06/2016 à 08:01, Chris Smart a écrit :
quoted
Calling ISA 3.0 instructions copy, copy_first, paste and paste_last
generates an alignment fault when copying or pasting unaligned
data (128 byte). We catch this and send SIGBUS to the userspace
process that caused it.
[snip]
quoted
+    if ((instruction & 0xfc0006fe) == 0x7c00060c){
Can you define corresponding instruction and mask in 
arch/powerpc/include/asm/ppc-opcode.h
and use symbolic names here instead of raw values ?
Yep, thanks. Will look at doing this for V2.

Cheers,
-c
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help