linux/arch/x86
Nadav Amit 428e3d0857 KVM: x86: Fix zero iterations REP-string
When a REP-string is executed in 64-bit mode with an address-size prefix,
ECX/EDI/ESI are used as counter and pointers. When ECX is initially zero, Intel
CPUs clear the high 32-bits of RCX, and recent Intel CPUs update the high bits
of the pointers in MOVS/STOS. This behavior is specific to Intel according to
few experiments.

As one may guess, this is an undocumented behavior. Yet, it is observable in
the guest, since at least VMX traps REP-INS/OUTS even when ECX=0. Note that
VMware appears to get it right.  The behavior can be observed using the
following code:

 #include <stdio.h>

 #define LOW_MASK	(0xffffffff00000000ull)
 #define ALL_MASK	(0xffffffffffffffffull)
 #define TEST(opcode)							\
	do {								\
	asm volatile(".byte 0xf2 \n\t .byte 0x67 \n\t .byte " opcode "\n\t" \
			: "=S"(s), "=c"(c), "=D"(d) 			\
			: "S"(ALL_MASK), "c"(LOW_MASK), "D"(ALL_MASK));	\
	printf("opcode %s rcx=%llx rsi=%llx rdi=%llx\n",		\
		opcode, c, s, d);					\
	} while(0)

void main()
{
	unsigned long long s, d, c;
	iopl(3);
	TEST("0x6c");
	TEST("0x6d");
	TEST("0x6e");
	TEST("0x6f");
	TEST("0xa4");
	TEST("0xa5");
	TEST("0xa6");
	TEST("0xa7");
	TEST("0xaa");
	TEST("0xab");
	TEST("0xae");
	TEST("0xaf");
}

Signed-off-by: Nadav Amit <namit@cs.technion.ac.il>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2015-05-19 20:52:36 +02:00
..
boot Merge branch 'x86-boot-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2015-04-13 13:19:10 -07:00
configs x86/build/defconfig: Enable USB_EHCI_TT_NEWSCHED=y 2015-02-19 02:21:14 +01:00
crypto crypto: x86/sha512_ssse3 - fixup for asm function prototype change 2015-04-24 20:09:01 +08:00
ia32 x86_64, asm: Work around AMD SYSRET SS descriptor attribute issue 2015-04-26 17:57:38 -07:00
include x86: kvmclock: drop rdtsc_barrier() 2015-05-07 11:29:48 +02:00
kernel kvmclock: set scheduler clock stable 2015-05-07 11:28:20 +02:00
kvm KVM: x86: Fix zero iterations REP-string 2015-05-19 20:52:36 +02:00
lguest Some virtio internal cleanups, a new virtio device "virtio input", and 2015-04-22 10:55:06 -07:00
lib x86: fix special __probe_kernel_write() tail zeroing case 2015-04-24 06:58:27 -07:00
math-emu
mm mm: move memtest under mm 2015-04-14 16:49:06 -07:00
net Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2014-12-10 15:48:20 -05:00
oprofile x86/asm/entry: Change all 'user_mode_vm()' calls to 'user_mode()' 2015-03-23 11:14:17 +01:00
pci PCI changes for the v4.1 merge window: 2015-04-13 15:45:47 -07:00
platform TTY/Serial patches for 4.1-rc1 2015-04-21 09:33:10 -07:00
power x86/asm/entry: Rename 'init_tss' to 'cpu_tss' 2015-03-06 08:32:58 +01:00
purgatory Merge branches 'x86-build-for-linus', 'x86-cleanups-for-linus' and 'x86-debug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2014-12-10 12:35:46 -08:00
realmode Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2015-02-16 14:58:12 -08:00
syscalls xen: features and fixes for 4.1-rc0 2015-04-16 14:01:03 -05:00
tools x86, build: replace Perl script with Shell script 2015-01-26 13:37:18 -08:00
um Merge branch 'exec_domain_rip_v2' of git://git.kernel.org/pub/scm/linux/kernel/git/rw/misc 2015-04-15 13:53:55 -07:00
vdso x86: pvclock: Really remove the sched notifier for cross-cpu migrations 2015-04-27 15:49:30 +02:00
video
xen xen: features and fixes for 4.1-rc0 2015-04-16 14:01:03 -05:00
.gitignore x86/build: Add arch/x86/purgatory/ make generated files to gitignore 2014-10-09 09:29:46 +02:00
Kbuild
Kconfig Initial ACPI support for arm64: 2015-04-24 08:23:45 -07:00
Kconfig.cpu
Kconfig.debug x86, intel-mid: remove Intel MID specific serial support 2015-03-07 03:25:18 +01:00
Makefile kbuild: use relative path more to include Makefile 2015-04-02 16:42:08 +02:00
Makefile_32.cpu
Makefile.um kbuild: use relative path more to include Makefile 2015-04-02 16:42:08 +02:00