From 4716e488abc22d487e298ee6c0c7d7dada9fcb64 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 4 Sep 2017 13:59:00 +1000 Subject: [PATCH] powerpc: Fix kernel crash in emulation of vector loads and stores Commit 350779a29f11 ("powerpc: Handle most loads and stores in instruction emulation code", 2017-08-30) changed the register usage in get_vr and put_vr with the aim of leaving the register number in r3 untouched on return. Unfortunately, r6 was not a good choice, as the callers as of 350779a29f11 store a MSR value in r6. Then, in commit c22435a5f3d8 ("powerpc: Emulate FP/vector/VSX loads/stores correctly when regs not live", 2017-08-30), the saving and restoring of the MSR got moved into get_vr and put_vr. Either way, the effect is that we put a value in MSR that only has the 0x3f8 bits non-zero, meaning that we are switching to 32-bit mode. That leads to a crash like this: Unable to handle kernel paging request for instruction fetch Faulting instruction address: 0x0007bea0 Oops: Kernel access of bad area, sig: 11 [#12] LE SMP NR_CPUS=2048 NUMA PowerNV Modules linked in: vmx_crypto binfmt_misc ip_tables x_tables autofs4 crc32c_vpmsum CPU: 6 PID: 32659 Comm: trashy_testcase Tainted: G D 4.13.0-rc2-00313-gf3026f57e6ed-dirty #23 task: c000000f1bb9e780 task.stack: c000000f1ba98000 NIP: 000000000007bea0 LR: c00000000007b054 CTR: c00000000007be70 REGS: c000000f1ba9b960 TRAP: 0400 Tainted: G D (4.13.0-rc2-00313-gf3026f57e6ed-dirty) MSR: 10000000400010a1 CR: 48000228 XER: 00000000 CFAR: c00000000007be74 SOFTE: 1 GPR00: c00000000007b054 c000000f1ba9bbe0 c000000000e6e000 000000000000001d GPR04: c000000f1ba9bc00 c00000000007be70 00000000000000e8 9000000002009033 GPR08: 0000000002000000 100000000282f033 000000000b0a0900 0000000000001009 GPR12: 0000000000000000 c00000000fd42100 0706050303020100 a5a5a5a5a5a5a5a5 GPR16: 2e2e2e2e2e2de70c 2e2e2e2e2e2e2e2d 0000000000ff00ff 0606040202020000 GPR20: 000000000000005b ffffffffffffffff 0000000003020100 0000000000000000 GPR24: c000000f1ab90020 c000000f1ba9bc00 0000000000000001 0000000000000001 GPR28: c000000f1ba9bc90 c000000f1ba9bea0 000000000b0a0908 0000000000000001 NIP [000000000007bea0] 0x7bea0 LR [c00000000007b054] emulate_loadstore+0x1044/0x1280 Call Trace: [c000000f1ba9bbe0] [c000000000076b80] analyse_instr+0x60/0x34f0 (unreliable) [c000000f1ba9bc70] [c00000000007b7ec] emulate_step+0x23c/0x544 [c000000f1ba9bce0] [c000000000053424] arch_uprobe_skip_sstep+0x24/0x40 [c000000f1ba9bd00] [c00000000024b2f8] uprobe_notify_resume+0x598/0xba0 [c000000f1ba9be00] [c00000000001c284] do_notify_resume+0xd4/0xf0 [c000000f1ba9be30] [c00000000000bd44] ret_from_except_lite+0x70/0x74 Instruction dump: XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX ---[ end trace a7ae7a7f3e0256b5 ]--- To fix this, we just revert to using r3 as before, since the callers don't rely on r3 being left unmodified. Fortunately, this can't be triggered by a misaligned load or store, because vector loads and stores truncate misaligned addresses rather than taking an alignment interrupt. It can be triggered using uprobes. Fixes: 350779a29f11 ("powerpc: Handle most loads and stores in instruction emulation code") Reported-by: Anton Blanchard Signed-off-by: Paul Mackerras Tested-by: Anton Blanchard Signed-off-by: Michael Ellerman --- arch/powerpc/lib/ldstfp.S | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/lib/ldstfp.S b/arch/powerpc/lib/ldstfp.S index 7b5cf5e421ab..ae15eba49c1f 100644 --- a/arch/powerpc/lib/ldstfp.S +++ b/arch/powerpc/lib/ldstfp.S @@ -77,7 +77,7 @@ _GLOBAL(get_vr) oris r7, r6, MSR_VEC@h MTMSRD(r7) isync - rlwinm r6,r3,3,0xf8 + rlwinm r3,r3,3,0xf8 bcl 20,31,1f reg = 0 .rept 32 @@ -86,7 +86,7 @@ reg = 0 reg = reg + 1 .endr 1: mflr r5 - add r5,r6,r5 + add r5,r3,r5 mtctr r5 mtlr r0 bctr @@ -101,7 +101,7 @@ _GLOBAL(put_vr) oris r7, r6, MSR_VEC@h MTMSRD(r7) isync - rlwinm r6,r3,3,0xf8 + rlwinm r3,r3,3,0xf8 bcl 20,31,1f reg = 0 .rept 32 @@ -110,7 +110,7 @@ reg = 0 reg = reg + 1 .endr 1: mflr r5 - add r5,r6,r5 + add r5,r3,r5 mtctr r5 mtlr r0 bctr