The recent rework of probe_kernel_read() and its conversion to get_kernel_nofault() inadvertently broke is_prefetch(). We were using probe_kernel_read() as a sloppy "read user or kernel memory" helper, but it doens't do that any more. The new get_kernel_nofault() reads *kernel* memory only, which completely broke is_prefetch() for user access.

Adjust the code to the the correct accessor based on access mode. The manual address bounds check is no longer necessary, since the accessor helpers (get_user() / get_kernel_nofault()) do the right thing all by themselves. As a bonus, by using the correct accessor, we don't need the open-coded address bounds check.

While we're at it, disable the workaround on all CPUs except AMD Family 0xF. By my reading of the Revision Guide for AMD Athlon™ 64 and AMD Opteron™ Processors, only family 0xF is affected.

Fixes: eab0c6089b68 ("maccess: unify the probe kernel arch hooks") Cc: stable@vger.kernel.org Cc: Dave Hansen dave.hansen@linux.intel.com Cc: Peter Zijlstra peterz@infradead.org Cc: Christoph Hellwig hch@lst.de Cc: Alexei Starovoitov ast@kernel.org Cc: Daniel Borkmann daniel@iogearbox.net Cc: Masami Hiramatsu mhiramat@kernel.org Signed-off-by: Andy Lutomirski luto@kernel.org --- arch/x86/mm/fault.c | 31 +++++++++++++++++++++---------- 1 file changed, 21 insertions(+), 10 deletions(-)

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 106b22d1d189..50dfdc71761e 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -54,7 +54,7 @@ kmmio_fault(struct pt_regs *regs, unsigned long addr) * 32-bit mode: * * Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch. - * Check that here and ignore it. + * Check that here and ignore it. This is AMD erratum #91. * * 64-bit mode: * @@ -83,11 +83,7 @@ check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr, #ifdef CONFIG_X86_64 case 0x40: /* - * In AMD64 long mode 0x40..0x4F are valid REX prefixes - * Need to figure out under what instruction mode the - * instruction was issued. Could check the LDT for lm, - * but for now it's good enough to assume that long - * mode only uses well known segments or kernel. + * In 64-bit mode 0x40..0x4F are valid REX prefixes */ return (!user_mode(regs) || user_64bit_mode(regs)); #endif @@ -124,23 +120,38 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) if (error_code & X86_PF_INSTR) return 0;

+ if (likely(boot_cpu_data.x86_vendor != X86_VENDOR_AMD + || boot_cpu_data.x86 != 0xf)) + return 0; + instr = (void *)convert_ip_to_linear(current, regs); max_instr = instr + 15;

- if (user_mode(regs) && instr >= (unsigned char *)TASK_SIZE_MAX) - return 0; + /* + * This code has historically always bailed out if IP points to a + * not-present page (e.g. due to a race). No one has ever + * complained about this. + */ + pagefault_disable();

while (instr < max_instr) { unsigned char opcode;

- if (get_kernel_nofault(opcode, instr)) - break; + if (user_mode(regs)) { + if (get_user(opcode, instr)) + break; + } else { + if (get_kernel_nofault(opcode, instr)) + break; + }

instr++;

if (!check_prefetch_opcode(regs, instr, opcode, &prefetch)) break; } + + pagefault_enable(); return prefetch; }