mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-30 06:10:56 +00:00
x86/entry_64: Add VERW just before userspace transition
Mitigation for MDS is to use VERW instruction to clear any secrets in CPU Buffers. Any memory accesses after VERW execution can still remain in CPU buffers. It is safer to execute VERW late in return to user path to minimize the window in which kernel data can end up in CPU buffers. There are not many kernel secrets to be had after SWITCH_TO_USER_CR3. Add support for deploying VERW mitigation after user register state is restored. This helps minimize the chances of kernel data ending up into CPU buffers after executing VERW. Note that the mitigation at the new location is not yet enabled. Corner case not handled ======================= Interrupts returning to kernel don't clear CPUs buffers since the exit-to-user path is expected to do that anyways. But, there could be a case when an NMI is generated in kernel after the exit-to-user path has cleared the buffers. This case is not handled and NMI returning to kernel don't clear CPU buffers because: 1. It is rare to get an NMI after VERW, but before returning to userspace. 2. For an unprivileged user, there is no known way to make that NMI less rare or target it. 3. It would take a large number of these precisely-timed NMIs to mount an actual attack. There's presumably not enough bandwidth. 4. The NMI in question occurs after a VERW, i.e. when user state is restored and most interesting data is already scrubbed. Whats left is only the data that NMI touches, and that may or may not be of any interest. Suggested-by: Dave Hansen <dave.hansen@intel.com> Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Link: https://lore.kernel.org/all/20240213-delay-verw-v8-2-a6216d83edb7%40linux.intel.com
This commit is contained in:
parent
baf8361e54
commit
3c7501722e
2 changed files with 12 additions and 0 deletions
|
@ -161,6 +161,7 @@ syscall_return_via_sysret:
|
||||||
SYM_INNER_LABEL(entry_SYSRETQ_unsafe_stack, SYM_L_GLOBAL)
|
SYM_INNER_LABEL(entry_SYSRETQ_unsafe_stack, SYM_L_GLOBAL)
|
||||||
ANNOTATE_NOENDBR
|
ANNOTATE_NOENDBR
|
||||||
swapgs
|
swapgs
|
||||||
|
CLEAR_CPU_BUFFERS
|
||||||
sysretq
|
sysretq
|
||||||
SYM_INNER_LABEL(entry_SYSRETQ_end, SYM_L_GLOBAL)
|
SYM_INNER_LABEL(entry_SYSRETQ_end, SYM_L_GLOBAL)
|
||||||
ANNOTATE_NOENDBR
|
ANNOTATE_NOENDBR
|
||||||
|
@ -573,6 +574,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
|
||||||
|
|
||||||
.Lswapgs_and_iret:
|
.Lswapgs_and_iret:
|
||||||
swapgs
|
swapgs
|
||||||
|
CLEAR_CPU_BUFFERS
|
||||||
/* Assert that the IRET frame indicates user mode. */
|
/* Assert that the IRET frame indicates user mode. */
|
||||||
testb $3, 8(%rsp)
|
testb $3, 8(%rsp)
|
||||||
jnz .Lnative_iret
|
jnz .Lnative_iret
|
||||||
|
@ -723,6 +725,8 @@ native_irq_return_ldt:
|
||||||
*/
|
*/
|
||||||
popq %rax /* Restore user RAX */
|
popq %rax /* Restore user RAX */
|
||||||
|
|
||||||
|
CLEAR_CPU_BUFFERS
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* RSP now points to an ordinary IRET frame, except that the page
|
* RSP now points to an ordinary IRET frame, except that the page
|
||||||
* is read-only and RSP[31:16] are preloaded with the userspace
|
* is read-only and RSP[31:16] are preloaded with the userspace
|
||||||
|
@ -1449,6 +1453,12 @@ nmi_restore:
|
||||||
std
|
std
|
||||||
movq $0, 5*8(%rsp) /* clear "NMI executing" */
|
movq $0, 5*8(%rsp) /* clear "NMI executing" */
|
||||||
|
|
||||||
|
/*
|
||||||
|
* Skip CLEAR_CPU_BUFFERS here, since it only helps in rare cases like
|
||||||
|
* NMI in kernel after user state is restored. For an unprivileged user
|
||||||
|
* these conditions are hard to meet.
|
||||||
|
*/
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* iretq reads the "iret" frame and exits the NMI stack in a
|
* iretq reads the "iret" frame and exits the NMI stack in a
|
||||||
* single instruction. We are returning to kernel mode, so this
|
* single instruction. We are returning to kernel mode, so this
|
||||||
|
@ -1466,6 +1476,7 @@ SYM_CODE_START(entry_SYSCALL32_ignore)
|
||||||
UNWIND_HINT_END_OF_STACK
|
UNWIND_HINT_END_OF_STACK
|
||||||
ENDBR
|
ENDBR
|
||||||
mov $-ENOSYS, %eax
|
mov $-ENOSYS, %eax
|
||||||
|
CLEAR_CPU_BUFFERS
|
||||||
sysretl
|
sysretl
|
||||||
SYM_CODE_END(entry_SYSCALL32_ignore)
|
SYM_CODE_END(entry_SYSCALL32_ignore)
|
||||||
|
|
||||||
|
|
|
@ -270,6 +270,7 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_unsafe_stack, SYM_L_GLOBAL)
|
||||||
xorl %r9d, %r9d
|
xorl %r9d, %r9d
|
||||||
xorl %r10d, %r10d
|
xorl %r10d, %r10d
|
||||||
swapgs
|
swapgs
|
||||||
|
CLEAR_CPU_BUFFERS
|
||||||
sysretl
|
sysretl
|
||||||
SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL)
|
SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL)
|
||||||
ANNOTATE_NOENDBR
|
ANNOTATE_NOENDBR
|
||||||
|
|
Loading…
Reference in a new issue