From 1a499150e4ec1299232e24389f648d059ce5617a Mon Sep 17 00:00:00 2001 From: "Luck, Tony" Date: Mon, 14 Jan 2008 09:59:24 -0800 Subject: [IA64] Fix unaligned handler for floating point instructions with base update The compiler team did the hard work for this distilling a problem in large fortran application which showed up when applied to a 290MB input data set down to this instruction: ldfd f34=[r17],-8 Which they noticed incremented r17 by 0x10 rather than decrementing it by 8 when the value in r17 caused an unaligned data fault. I tracked it down to some bad instruction decoding in unaligned.c. The code assumes that the 'x' bit can determine whether the instruction is an "ldf" or "ldfp" ... which it is for opcode=6 (see table 4-29 on page 3:302 of the SDM). But for opcode=7 the 'x' bit is irrelevent, all variants are "ldf" instructions (see table 4-36 on page 3:306). Note also that interpreting the instruction as "ldfp" means that the "paired" floating point register (f35 in the example here) will also be corrupted. Signed-off-by: Tony Luck --- arch/ia64/kernel/unaligned.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/ia64/kernel/unaligned.c b/arch/ia64/kernel/unaligned.c index 2173de9fe91..f6a1aeb742b 100644 --- a/arch/ia64/kernel/unaligned.c +++ b/arch/ia64/kernel/unaligned.c @@ -1488,16 +1488,19 @@ ia64_handle_unaligned (unsigned long ifa, struct pt_regs *regs) case LDFA_OP: case LDFCCLR_OP: case LDFCNC_OP: - case LDF_IMM_OP: - case LDFA_IMM_OP: - case LDFCCLR_IMM_OP: - case LDFCNC_IMM_OP: if (u.insn.x) ret = emulate_load_floatpair(ifa, u.insn, regs); else ret = emulate_load_float(ifa, u.insn, regs); break; + case LDF_IMM_OP: + case LDFA_IMM_OP: + case LDFCCLR_IMM_OP: + case LDFCNC_IMM_OP: + ret = emulate_load_float(ifa, u.insn, regs); + break; + case STF_OP: case STF_IMM_OP: ret = emulate_store_float(ifa, u.insn, regs); -- cgit v1.2.3-70-g09d2