[ 11/25] x86_64/entry/xen: Do not invoke espfix64 on Xen

From: Willy Tarreau
Date: Sat Dec 06 2014 - 12:55:18 EST

2.6.32-longterm review patch. If anyone has any objections, please let me know.


From: Andy Lutomirski <luto@xxxxxxxxxxxxxx>

commit 7209a75d2009dbf7745e2fd354abf25c3deb3ca3 upstream.

This moves the espfix64 logic into native_iret. To make this work,
it gets rid of the native patch for INTERRUPT_RETURN:
INTERRUPT_RETURN on native kernels is now 'jmp native_iret'.

This changes the 16-bit SS behavior on Xen from OOPSing to leaking
some bits of the Xen hypervisor's RSP (I think).

[ hpa: this is a nonzero cost on native, but probably not enough to
measure. Xen needs to fix this in their own code, probably doing
something equivalent to espfix64. ]

Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Link: http://lkml.kernel.org/r/7b8f1d8ef6597cb16ae004a43c56980a7de3cf94.1406129132.git.luto@xxxxxxxxxxxxxx
Signed-off-by: H. Peter Anvin <hpa@xxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
(cherry picked from 3.2 commit 8ba19cd8c351e16b6be4caca9338d19b0cb8eaa4)
Signed-off-by: Willy Tarreau <w@xxxxxx>
arch/x86/include/asm/irqflags.h | 2 +-
arch/x86/kernel/entry_64.S | 31 ++++++++++---------------------
arch/x86/kernel/paravirt_patch_64.c | 2 --
3 files changed, 11 insertions(+), 24 deletions(-)

diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 9e2b952..58b0c5c 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -130,7 +130,7 @@ static inline unsigned long __raw_local_irq_save(void)


-#define INTERRUPT_RETURN iretq
+#define INTERRUPT_RETURN jmp native_iret
#define USERGS_SYSRET64 \
swapgs; \
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index cf9e7d2..4313d48 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -859,33 +859,27 @@ restore_args:

* Are we returning to a stack segment from the LDT? Note: in
* 64-bit mode SS:RSP on the exception stack is always valid.
#ifdef CONFIG_X86_ESPFIX64
testb $4,(SS-RIP)(%rsp)
- jnz irq_return_ldt
+ jnz native_irq_return_ldt

- .section __ex_table, "a"
- .quad irq_return_iret, bad_iret
- .previous

.section __ex_table,"a"
- .quad native_iret, bad_iret
+ .quad native_irq_return_iret, bad_iret

#ifdef CONFIG_X86_ESPFIX64
pushq_cfi %rax
pushq_cfi %rdi
@@ -907,7 +901,7 @@ irq_return_ldt:
movq %rax,%rsp
popq_cfi %rax
- jmp irq_return_iret
+ jmp native_irq_return_iret

.section .fixup,"ax"
@@ -995,13 +989,8 @@ __do_double_fault:
cmpl $__KERNEL_CS,CS(%rdi)
jne do_double_fault
movq RIP(%rdi),%rax
- cmpq $irq_return_iret,%rax
- je 1f
- cmpq $native_iret,%rax
+ cmpq $native_irq_return_iret,%rax
jne do_double_fault /* This shouldn't happen... */
movq PER_CPU_VAR(kernel_stack),%rax
subq $(6*8-KERNEL_STACK_OFFSET),%rax /* Reset to original stack */
movq %rax,RSP(%rdi)
@@ -1560,7 +1549,7 @@ error_sti:
incl %ebx
- leaq irq_return_iret(%rip),%rcx
+ leaq native_irq_return_iret(%rip),%rcx
cmpq %rcx,RIP+8(%rsp)
je error_swapgs
movl %ecx,%eax /* zero extend */
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 3f08f34..a1da673 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -6,7 +6,6 @@ DEF_NATIVE(pv_irq_ops, irq_disable, "cli");
DEF_NATIVE(pv_irq_ops, irq_enable, "sti");
DEF_NATIVE(pv_irq_ops, restore_fl, "pushq %rdi; popfq");
DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax");
-DEF_NATIVE(pv_cpu_ops, iret, "iretq");
DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax");
DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax");
DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3");
@@ -50,7 +49,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
PATCH_SITE(pv_irq_ops, save_fl);
PATCH_SITE(pv_irq_ops, irq_enable);
PATCH_SITE(pv_irq_ops, irq_disable);
- PATCH_SITE(pv_cpu_ops, iret);
PATCH_SITE(pv_cpu_ops, irq_enable_sysexit);
PATCH_SITE(pv_cpu_ops, usergs_sysret32);
PATCH_SITE(pv_cpu_ops, usergs_sysret64);

To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/