This is the backport of recently upstreamed series that moves VERW execution to a later point in exit-to-user path. This is needed because in some cases it may be possible for data accessed after VERW executions may end into MDS affected CPU buffers. Moving VERW closer to ring transition reduces the attack surface.
Patch 1/6 includes a minor fix that is queued for upstream: https://lore.kernel.org/lkml/170899674562.398.6398007479766564897.tip-bot2@t...
Patch 2/6 needed a conflict to be resolved for the hunk swapgs_restore_regs_and_return_to_usermode.
Signed-off-by: Pawan Gupta pawan.kumar.gupta@linux.intel.com --- Pawan Gupta (5): x86/bugs: Add asm helpers for executing VERW x86/entry_64: Add VERW just before userspace transition x86/entry_32: Add VERW just before userspace transition x86/bugs: Use ALTERNATIVE() instead of mds_user_clear static key KVM/VMX: Move VERW closer to VMentry for MDS mitigation
Sean Christopherson (1): KVM/VMX: Use BT+JNC, i.e. EFLAGS.CF to select VMRESUME vs. VMLAUNCH
Documentation/arch/x86/mds.rst | 38 +++++++++++++++++++++++++----------- arch/x86/entry/entry.S | 23 ++++++++++++++++++++++ arch/x86/entry/entry_32.S | 3 +++ arch/x86/entry/entry_64.S | 11 +++++++++++ arch/x86/entry/entry_64_compat.S | 1 + arch/x86/include/asm/cpufeatures.h | 2 +- arch/x86/include/asm/entry-common.h | 1 - arch/x86/include/asm/nospec-branch.h | 25 ++++++++++++------------ arch/x86/kernel/cpu/bugs.c | 15 ++++++-------- arch/x86/kernel/nmi.c | 3 --- arch/x86/kvm/vmx/run_flags.h | 7 +++++-- arch/x86/kvm/vmx/vmenter.S | 9 ++++++--- arch/x86/kvm/vmx/vmx.c | 20 +++++++++++++++---- 13 files changed, 112 insertions(+), 46 deletions(-) --- base-commit: b631f5b445dc3379f67ff63a2e4c58f22d4975dc change-id: 20240226-delay-verw-backport-6-7-y-a2cb3f26bb90
Best regards,
commit baf8361e54550a48a7087b603313ad013cc13386 upstream.
MDS mitigation requires clearing the CPU buffers before returning to user. This needs to be done late in the exit-to-user path. Current location of VERW leaves a possibility of kernel data ending up in CPU buffers for memory accesses done after VERW such as:
1. Kernel data accessed by an NMI between VERW and return-to-user can remain in CPU buffers since NMI returning to kernel does not execute VERW to clear CPU buffers. 2. Alyssa reported that after VERW is executed, CONFIG_GCC_PLUGIN_STACKLEAK=y scrubs the stack used by a system call. Memory accesses during stack scrubbing can move kernel stack contents into CPU buffers. 3. When caller saved registers are restored after a return from function executing VERW, the kernel stack accesses can remain in CPU buffers(since they occur after VERW).
To fix this VERW needs to be moved very late in exit-to-user path.
In preparation for moving VERW to entry/exit asm code, create macros that can be used in asm. Also make VERW patching depend on a new feature flag X86_FEATURE_CLEAR_CPU_BUF.
Reported-by: Alyssa Milburn alyssa.milburn@intel.com Suggested-by: Andrew Cooper andrew.cooper3@citrix.com Suggested-by: Peter Zijlstra peterz@infradead.org 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-v8-1-a6216d83edb7%40linux.in... --- arch/x86/entry/entry.S | 23 +++++++++++++++++++++++ arch/x86/include/asm/cpufeatures.h | 2 +- arch/x86/include/asm/nospec-branch.h | 13 +++++++++++++ 3 files changed, 37 insertions(+), 1 deletion(-)
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S index 8c8d38f0cb1d..003379049924 100644 --- a/arch/x86/entry/entry.S +++ b/arch/x86/entry/entry.S @@ -6,6 +6,9 @@ #include <linux/export.h> #include <linux/linkage.h> #include <asm/msr-index.h> +#include <asm/unwind_hints.h> +#include <asm/segment.h> +#include <asm/cache.h>
.pushsection .noinstr.text, "ax"
@@ -20,3 +23,23 @@ SYM_FUNC_END(entry_ibpb) EXPORT_SYMBOL_GPL(entry_ibpb);
.popsection + +/* + * Define the VERW operand that is disguised as entry code so that + * it can be referenced with KPTI enabled. This ensure VERW can be + * used late in exit-to-user path after page tables are switched. + */ +.pushsection .entry.text, "ax" + +.align L1_CACHE_BYTES, 0xcc +SYM_CODE_START_NOALIGN(mds_verw_sel) + UNWIND_HINT_UNDEFINED + ANNOTATE_NOENDBR + .word __KERNEL_DS +.align L1_CACHE_BYTES, 0xcc +SYM_CODE_END(mds_verw_sel); +/* For KVM */ +EXPORT_SYMBOL_GPL(mds_verw_sel); + +.popsection + diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 3e973ff20e23..caf4cf2e1036 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -97,7 +97,7 @@ #define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */ #define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */ #define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */ -/* FREE, was #define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) "" LFENCE synchronizes RDTSC */ +#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* "" Clear CPU buffers using VERW */ #define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ #define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ #define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index f93e9b96927a..e191711de0f2 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -315,6 +315,17 @@ #endif .endm
+/* + * Macro to execute VERW instruction that mitigate transient data sampling + * attacks such as MDS. On affected systems a microcode update overloaded VERW + * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF. + * + * Note: Only the memory operand variant of VERW clears the CPU buffers. + */ +.macro CLEAR_CPU_BUFFERS + ALTERNATIVE "", __stringify(verw mds_verw_sel), X86_FEATURE_CLEAR_CPU_BUF +.endm + #else /* __ASSEMBLY__ */
#define ANNOTATE_RETPOLINE_SAFE \ @@ -536,6 +547,8 @@ DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear);
+extern u16 mds_verw_sel; + #include <asm/segment.h>
/**
On 27. 02. 24, 6:00, Pawan Gupta wrote:
commit baf8361e54550a48a7087b603313ad013cc13386 upstream.
MDS mitigation requires clearing the CPU buffers before returning to user. This needs to be done late in the exit-to-user path. Current location of VERW leaves a possibility of kernel data ending up in CPU buffers for memory accesses done after VERW such as:
- Kernel data accessed by an NMI between VERW and return-to-user can remain in CPU buffers since NMI returning to kernel does not execute VERW to clear CPU buffers.
- Alyssa reported that after VERW is executed, CONFIG_GCC_PLUGIN_STACKLEAK=y scrubs the stack used by a system call. Memory accesses during stack scrubbing can move kernel stack contents into CPU buffers.
- When caller saved registers are restored after a return from function executing VERW, the kernel stack accesses can remain in CPU buffers(since they occur after VERW).
To fix this VERW needs to be moved very late in exit-to-user path.
In preparation for moving VERW to entry/exit asm code, create macros that can be used in asm. Also make VERW patching depend on a new feature flag X86_FEATURE_CLEAR_CPU_BUF.
...
--- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -315,6 +315,17 @@ #endif .endm +/*
- Macro to execute VERW instruction that mitigate transient data sampling
- attacks such as MDS. On affected systems a microcode update overloaded VERW
- instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF.
- Note: Only the memory operand variant of VERW clears the CPU buffers.
- */
+.macro CLEAR_CPU_BUFFERS
- ALTERNATIVE "", __stringify(verw mds_verw_sel), X86_FEATURE_CLEAR_CPU_BUF
Why is not rip-relative preserved here? Will this work at all (it looks like verw would now touch random memory)?
In any way, should you do any changes during the backport, you shall document that.
On Tue, Feb 27, 2024 at 08:40:26AM +0100, Jiri Slaby wrote:
On 27. 02. 24, 6:00, Pawan Gupta wrote:
commit baf8361e54550a48a7087b603313ad013cc13386 upstream.
MDS mitigation requires clearing the CPU buffers before returning to user. This needs to be done late in the exit-to-user path. Current location of VERW leaves a possibility of kernel data ending up in CPU buffers for memory accesses done after VERW such as:
- Kernel data accessed by an NMI between VERW and return-to-user can remain in CPU buffers since NMI returning to kernel does not execute VERW to clear CPU buffers.
- Alyssa reported that after VERW is executed, CONFIG_GCC_PLUGIN_STACKLEAK=y scrubs the stack used by a system call. Memory accesses during stack scrubbing can move kernel stack contents into CPU buffers.
- When caller saved registers are restored after a return from function executing VERW, the kernel stack accesses can remain in CPU buffers(since they occur after VERW).
To fix this VERW needs to be moved very late in exit-to-user path.
In preparation for moving VERW to entry/exit asm code, create macros that can be used in asm. Also make VERW patching depend on a new feature flag X86_FEATURE_CLEAR_CPU_BUF.
...
--- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -315,6 +315,17 @@ #endif .endm +/*
- Macro to execute VERW instruction that mitigate transient data sampling
- attacks such as MDS. On affected systems a microcode update overloaded VERW
- instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF.
- Note: Only the memory operand variant of VERW clears the CPU buffers.
- */
+.macro CLEAR_CPU_BUFFERS
- ALTERNATIVE "", __stringify(verw mds_verw_sel), X86_FEATURE_CLEAR_CPU_BUF
Why is not rip-relative preserved here? Will this work at all (it looks like verw would now touch random memory)?
In any way, should you do any changes during the backport, you shall document that.
s/shall/MUST/
thanks,
greg k-h
On Tue, Feb 27, 2024 at 08:47:46AM +0100, Greg KH wrote:
On Tue, Feb 27, 2024 at 08:40:26AM +0100, Jiri Slaby wrote:
On 27. 02. 24, 6:00, Pawan Gupta wrote:
commit baf8361e54550a48a7087b603313ad013cc13386 upstream.
MDS mitigation requires clearing the CPU buffers before returning to user. This needs to be done late in the exit-to-user path. Current location of VERW leaves a possibility of kernel data ending up in CPU buffers for memory accesses done after VERW such as:
- Kernel data accessed by an NMI between VERW and return-to-user can remain in CPU buffers since NMI returning to kernel does not execute VERW to clear CPU buffers.
- Alyssa reported that after VERW is executed, CONFIG_GCC_PLUGIN_STACKLEAK=y scrubs the stack used by a system call. Memory accesses during stack scrubbing can move kernel stack contents into CPU buffers.
- When caller saved registers are restored after a return from function executing VERW, the kernel stack accesses can remain in CPU buffers(since they occur after VERW).
To fix this VERW needs to be moved very late in exit-to-user path.
In preparation for moving VERW to entry/exit asm code, create macros that can be used in asm. Also make VERW patching depend on a new feature flag X86_FEATURE_CLEAR_CPU_BUF.
...
--- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -315,6 +315,17 @@ #endif .endm +/*
- Macro to execute VERW instruction that mitigate transient data sampling
- attacks such as MDS. On affected systems a microcode update overloaded VERW
- instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF.
- Note: Only the memory operand variant of VERW clears the CPU buffers.
- */
+.macro CLEAR_CPU_BUFFERS
- ALTERNATIVE "", __stringify(verw mds_verw_sel), X86_FEATURE_CLEAR_CPU_BUF
Why is not rip-relative preserved here? Will this work at all (it looks like verw would now touch random memory)?
In any way, should you do any changes during the backport, you shall document that.
s/shall/MUST/
Noted.
On Tue, Feb 27, 2024 at 08:40:26AM +0100, Jiri Slaby wrote:
On 27. 02. 24, 6:00, Pawan Gupta wrote:
commit baf8361e54550a48a7087b603313ad013cc13386 upstream.
MDS mitigation requires clearing the CPU buffers before returning to user. This needs to be done late in the exit-to-user path. Current location of VERW leaves a possibility of kernel data ending up in CPU buffers for memory accesses done after VERW such as:
- Kernel data accessed by an NMI between VERW and return-to-user can remain in CPU buffers since NMI returning to kernel does not execute VERW to clear CPU buffers.
- Alyssa reported that after VERW is executed, CONFIG_GCC_PLUGIN_STACKLEAK=y scrubs the stack used by a system call. Memory accesses during stack scrubbing can move kernel stack contents into CPU buffers.
- When caller saved registers are restored after a return from function executing VERW, the kernel stack accesses can remain in CPU buffers(since they occur after VERW).
To fix this VERW needs to be moved very late in exit-to-user path.
In preparation for moving VERW to entry/exit asm code, create macros that can be used in asm. Also make VERW patching depend on a new feature flag X86_FEATURE_CLEAR_CPU_BUF.
...
--- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -315,6 +315,17 @@ #endif .endm +/*
- Macro to execute VERW instruction that mitigate transient data sampling
- attacks such as MDS. On affected systems a microcode update overloaded VERW
- instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF.
- Note: Only the memory operand variant of VERW clears the CPU buffers.
- */
+.macro CLEAR_CPU_BUFFERS
- ALTERNATIVE "", __stringify(verw mds_verw_sel), X86_FEATURE_CLEAR_CPU_BUF
Why is not rip-relative preserved here?
Because Nikolay reported that it was creating a problem for backports on kernels that don't support relocations in alternatives. More on this here:
https://lore.kernel.org/lkml/20558f89-299b-472e-9a96-171403a83bd6@suse.com/
Also, RIP-relative addressing was a requirement only for the initial versions of the series, where the VERW operand was pointing within the macro. For performance gains, later versions switched to the implementation in which all VERW sites were pointing to single memory location. With that, RIP-relative addressing could be droped in favor of fixed addresses.
Will this work at all (it looks like verw would now touch random memory)?
AFAIK, all memory operand variants of VERW have the CPU buffer clearing behavior. I will confirm this with the CPU architects.
In any way, should you do any changes during the backport, you shall document that.
Sorry, I missed to mention this change in 6.7.y backport. I did include this info in the other backports I sent:
https://lore.kernel.org/stable/20240226-delay-verw-backport-6-6-y-v1-0-aa17b... https://lore.kernel.org/stable/20240226-delay-verw-backport-6-1-y-v1-0-b3a2c...
On 27. 02. 24, 9:27, Pawan Gupta wrote:
On Tue, Feb 27, 2024 at 08:40:26AM +0100, Jiri Slaby wrote:
...
--- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -315,6 +315,17 @@ #endif .endm +/*
- Macro to execute VERW instruction that mitigate transient data sampling
- attacks such as MDS. On affected systems a microcode update overloaded VERW
- instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF.
- Note: Only the memory operand variant of VERW clears the CPU buffers.
- */
+.macro CLEAR_CPU_BUFFERS
- ALTERNATIVE "", __stringify(verw mds_verw_sel), X86_FEATURE_CLEAR_CPU_BUF
Why is not rip-relative preserved here?
Because Nikolay reported that it was creating a problem for backports on kernels that don't support relocations in alternatives. More on this here:
https://lore.kernel.org/lkml/20558f89-299b-472e-9a96-171403a83bd6@suse.com/
Sure, I know about the issue.
Also, RIP-relative addressing was a requirement only for the initial versions of the series, where the VERW operand was pointing within the macro. For performance gains, later versions switched to the implementation in which all VERW sites were pointing to single memory location. With that, RIP-relative addressing could be droped in favor of fixed addresses.
Will this work at all (it looks like verw would now touch random memory)?
AFAIK, all memory operand variants of VERW have the CPU buffer clearing behavior. I will confirm this with the CPU architects.
I might be too dumb to understand this, so sorry if the below does not make sense. Neither I cannot see "why it works" in the minor patch you sent (and incorporated here). You only explain it's easier for backports and "was needed in earlier versions".
But verw can #PF (and actually used to before Nik invented the jmp workaround in the SUSE backport). I assume it's the case when the store of the segment (mds_verw_sel) cannot be accessed/read. Now, with fixed addressing this works unless KASLR is employed. If it is, the fixed address of mds_verw_sel no longer points to the correct memory. Or what am I missing?
In any way, should you do any changes during the backport, you shall document that.
Sorry, I missed to mention this change in 6.7.y backport. I did include this info in the other backports I sent:
https://lore.kernel.org/stable/20240226-delay-verw-backport-6-6-y-v1-0-aa17b... https://lore.kernel.org/stable/20240226-delay-verw-backport-6-1-y-v1-0-b3a2c...
I am sure you are aware you need NOT doing this very change in 6.6 and 6.7 ;). It somehow confused me too.
thanks,
On 27. 02. 24, 9:41, Jiri Slaby wrote:
Also, RIP-relative addressing was a requirement only for the initial versions of the series, where the VERW operand was pointing within the macro. For performance gains, later versions switched to the implementation in which all VERW sites were pointing to single memory location. With that, RIP-relative addressing could be droped in favor of fixed addresses.
Will this work at all (it looks like verw would now touch random memory)?
AFAIK, all memory operand variants of VERW have the CPU buffer clearing behavior. I will confirm this with the CPU architects.
I might be too dumb to understand this, so sorry if the below does not make sense. Neither I cannot see "why it works" in the minor patch you sent (and incorporated here). You only explain it's easier for backports and "was needed in earlier versions".
But verw can #PF (and actually used to before Nik invented the jmp workaround in the SUSE backport). I assume it's the case when the store of the segment (mds_verw_sel) cannot be accessed/read. Now, with fixed addressing this works unless KASLR is employed. If it is, the fixed address of mds_verw_sel no longer points to the correct memory. Or what am I missing?
The assembler generates a relocation for the fixed address anyway. And the linker resolves it as rip-relative. At least the pair from my binutils-2.42.
But if it generates a rip-relative address, is < 6.5 with no support of rip-rel in alternatives still fine?
Another question: can we rely on the assembler to generate a relocation and on the linker to resolve it as rip-relative?
thanks,
commit 3c7501722e6b31a6e56edd23cea5e77dbb9ffd1a upstream.
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.
[ pawan: resolved conflict for hunk swapgs_restore_regs_and_return_to_usermode in backport ]
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.in... --- arch/x86/entry/entry_64.S | 11 +++++++++++ arch/x86/entry/entry_64_compat.S | 1 + 2 files changed, 12 insertions(+)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index de6469dffe3a..bdb17fad5d04 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -161,6 +161,7 @@ syscall_return_via_sysret: SYM_INNER_LABEL(entry_SYSRETQ_unsafe_stack, SYM_L_GLOBAL) ANNOTATE_NOENDBR swapgs + CLEAR_CPU_BUFFERS sysretq SYM_INNER_LABEL(entry_SYSRETQ_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR @@ -601,6 +602,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) /* Restore RDI. */ popq %rdi swapgs + CLEAR_CPU_BUFFERS jmp .Lnative_iret
@@ -712,6 +714,8 @@ native_irq_return_ldt: */ popq %rax /* Restore user RAX */
+ CLEAR_CPU_BUFFERS + /* * RSP now points to an ordinary IRET frame, except that the page * is read-only and RSP[31:16] are preloaded with the userspace @@ -1438,6 +1442,12 @@ nmi_restore: std 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 * single instruction. We are returning to kernel mode, so this @@ -1455,6 +1465,7 @@ SYM_CODE_START(entry_SYSCALL32_ignore) UNWIND_HINT_END_OF_STACK ENDBR mov $-ENOSYS, %eax + CLEAR_CPU_BUFFERS sysretl SYM_CODE_END(entry_SYSCALL32_ignore)
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index de94e2e84ecc..eabf48c4d4b4 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -270,6 +270,7 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_unsafe_stack, SYM_L_GLOBAL) xorl %r9d, %r9d xorl %r10d, %r10d swapgs + CLEAR_CPU_BUFFERS sysretl SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR
commit a0e2dab44d22b913b4c228c8b52b2a104434b0b3 upstream.
As done for entry_64, add support for executing VERW late in exit to user path for 32-bit mode.
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-v8-3-a6216d83edb7%40linux.in... --- arch/x86/entry/entry_32.S | 3 +++ 1 file changed, 3 insertions(+)
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index c73047bf9f4b..fba427646805 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -885,6 +885,7 @@ SYM_FUNC_START(entry_SYSENTER_32) BUG_IF_WRONG_CR3 no_user_check=1 popfl popl %eax + CLEAR_CPU_BUFFERS
/* * Return back to the vDSO, which will pop ecx and edx. @@ -954,6 +955,7 @@ restore_all_switch_stack:
/* Restore user state */ RESTORE_REGS pop=4 # skip orig_eax/error_code + CLEAR_CPU_BUFFERS .Lirq_return: /* * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization @@ -1146,6 +1148,7 @@ SYM_CODE_START(asm_exc_nmi)
/* Not on SYSENTER stack. */ call exc_nmi + CLEAR_CPU_BUFFERS jmp .Lnmi_return
.Lnmi_from_sysenter_stack:
commit 6613d82e617dd7eb8b0c40b2fe3acea655b1d611 upstream.
The VERW mitigation at exit-to-user is enabled via a static branch mds_user_clear. This static branch is never toggled after boot, and can be safely replaced with an ALTERNATIVE() which is convenient to use in asm.
Switch to ALTERNATIVE() to use the VERW mitigation late in exit-to-user path. Also remove the now redundant VERW in exc_nmi() and arch_exit_to_user_mode().
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-v8-4-a6216d83edb7%40linux.in... --- Documentation/arch/x86/mds.rst | 38 +++++++++++++++++++++++++----------- arch/x86/include/asm/entry-common.h | 1 - arch/x86/include/asm/nospec-branch.h | 12 ------------ arch/x86/kernel/cpu/bugs.c | 15 ++++++-------- arch/x86/kernel/nmi.c | 3 --- arch/x86/kvm/vmx/vmx.c | 2 +- 6 files changed, 34 insertions(+), 37 deletions(-)
diff --git a/Documentation/arch/x86/mds.rst b/Documentation/arch/x86/mds.rst index e73fdff62c0a..c58c72362911 100644 --- a/Documentation/arch/x86/mds.rst +++ b/Documentation/arch/x86/mds.rst @@ -95,6 +95,9 @@ The kernel provides a function to invoke the buffer clearing:
mds_clear_cpu_buffers()
+Also macro CLEAR_CPU_BUFFERS can be used in ASM late in exit-to-user path. +Other than CFLAGS.ZF, this macro doesn't clobber any registers. + The mitigation is invoked on kernel/userspace, hypervisor/guest and C-state (idle) transitions.
@@ -138,17 +141,30 @@ Mitigation points
When transitioning from kernel to user space the CPU buffers are flushed on affected CPUs when the mitigation is not disabled on the kernel - command line. The migitation is enabled through the static key - mds_user_clear. - - The mitigation is invoked in prepare_exit_to_usermode() which covers - all but one of the kernel to user space transitions. The exception - is when we return from a Non Maskable Interrupt (NMI), which is - handled directly in do_nmi(). - - (The reason that NMI is special is that prepare_exit_to_usermode() can - enable IRQs. In NMI context, NMIs are blocked, and we don't want to - enable IRQs with NMIs blocked.) + command line. The mitigation is enabled through the feature flag + X86_FEATURE_CLEAR_CPU_BUF. + + The mitigation is invoked just before transitioning to userspace after + user registers are restored. This is done to minimize the window in + which kernel data could be accessed after VERW e.g. via an NMI after + VERW. + + **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.
2. C-State transition diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index ce8f50192ae3..7e523bb3d2d3 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -91,7 +91,6 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
static __always_inline void arch_exit_to_user_mode(void) { - mds_user_clear_cpu_buffers(); amd_clear_divider(); } #define arch_exit_to_user_mode arch_exit_to_user_mode diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index e191711de0f2..6a1fe302c1fd 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -540,7 +540,6 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
-DECLARE_STATIC_KEY_FALSE(mds_user_clear); DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); @@ -574,17 +573,6 @@ static __always_inline void mds_clear_cpu_buffers(void) asm volatile("verw %[ds]" : : [ds] "m" (ds) : "cc"); }
-/** - * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability - * - * Clear CPU buffers if the corresponding static key is enabled - */ -static __always_inline void mds_user_clear_cpu_buffers(void) -{ - if (static_branch_likely(&mds_user_clear)) - mds_clear_cpu_buffers(); -} - /** * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability * diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index bb0ab8466b91..48d049cd74e7 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -111,9 +111,6 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); /* Control unconditional IBPB in switch_mm() */ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
-/* Control MDS CPU buffer clear before returning to user space */ -DEFINE_STATIC_KEY_FALSE(mds_user_clear); -EXPORT_SYMBOL_GPL(mds_user_clear); /* Control MDS CPU buffer clear before idling (halt, mwait) */ DEFINE_STATIC_KEY_FALSE(mds_idle_clear); EXPORT_SYMBOL_GPL(mds_idle_clear); @@ -252,7 +249,7 @@ static void __init mds_select_mitigation(void) if (!boot_cpu_has(X86_FEATURE_MD_CLEAR)) mds_mitigation = MDS_MITIGATION_VMWERV;
- static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) && (mds_nosmt || cpu_mitigations_auto_nosmt())) @@ -356,7 +353,7 @@ static void __init taa_select_mitigation(void) * For guests that can't determine whether the correct microcode is * present on host, enable the mitigation for UCODE_NEEDED as well. */ - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
if (taa_nosmt || cpu_mitigations_auto_nosmt()) cpu_smt_disable(false); @@ -424,7 +421,7 @@ static void __init mmio_select_mitigation(void) */ if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM))) - static_branch_enable(&mds_user_clear); + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); else static_branch_enable(&mmio_stale_data_clear);
@@ -484,12 +481,12 @@ static void __init md_clear_update_mitigation(void) if (cpu_mitigations_off()) return;
- if (!static_key_enabled(&mds_user_clear)) + if (!boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF)) goto out;
/* - * mds_user_clear is now enabled. Update MDS, TAA and MMIO Stale Data - * mitigation, if necessary. + * X86_FEATURE_CLEAR_CPU_BUF is now enabled. Update MDS, TAA and MMIO + * Stale Data mitigation, if necessary. */ if (mds_mitigation == MDS_MITIGATION_OFF && boot_cpu_has_bug(X86_BUG_MDS)) { diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 17e955ab69fe..3082cf24b69e 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -563,9 +563,6 @@ DEFINE_IDTENTRY_RAW(exc_nmi) } if (this_cpu_dec_return(nmi_state)) goto nmi_restart; - - if (user_mode(regs)) - mds_user_clear_cpu_buffers(); }
#if IS_ENABLED(CONFIG_KVM_INTEL) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 94082169bbbc..b59ac1525b17 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7229,7 +7229,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, /* L1D Flush includes CPU buffer clear to mitigate MDS */ if (static_branch_unlikely(&vmx_l1d_should_flush)) vmx_l1d_flush(vcpu); - else if (static_branch_unlikely(&mds_user_clear)) + else if (cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF)) mds_clear_cpu_buffers(); else if (static_branch_unlikely(&mmio_stale_data_clear) && kvm_arch_has_assigned_device(vcpu->kvm))
From: Sean Christopherson seanjc@google.com
commit 706a189dcf74d3b3f955e9384785e726ed6c7c80 upstream.
Use EFLAGS.CF instead of EFLAGS.ZF to track whether to use VMRESUME versus VMLAUNCH. Freeing up EFLAGS.ZF will allow doing VERW, which clobbers ZF, for MDS mitigations as late as possible without needing to duplicate VERW for both paths.
Signed-off-by: Sean Christopherson seanjc@google.com Signed-off-by: Pawan Gupta pawan.kumar.gupta@linux.intel.com Signed-off-by: Dave Hansen dave.hansen@linux.intel.com Reviewed-by: Nikolay Borisov nik.borisov@suse.com Link: https://lore.kernel.org/all/20240213-delay-verw-v8-5-a6216d83edb7%40linux.in... --- arch/x86/kvm/vmx/run_flags.h | 7 +++++-- arch/x86/kvm/vmx/vmenter.S | 6 +++--- 2 files changed, 8 insertions(+), 5 deletions(-)
diff --git a/arch/x86/kvm/vmx/run_flags.h b/arch/x86/kvm/vmx/run_flags.h index edc3f16cc189..6a9bfdfbb6e5 100644 --- a/arch/x86/kvm/vmx/run_flags.h +++ b/arch/x86/kvm/vmx/run_flags.h @@ -2,7 +2,10 @@ #ifndef __KVM_X86_VMX_RUN_FLAGS_H #define __KVM_X86_VMX_RUN_FLAGS_H
-#define VMX_RUN_VMRESUME (1 << 0) -#define VMX_RUN_SAVE_SPEC_CTRL (1 << 1) +#define VMX_RUN_VMRESUME_SHIFT 0 +#define VMX_RUN_SAVE_SPEC_CTRL_SHIFT 1 + +#define VMX_RUN_VMRESUME BIT(VMX_RUN_VMRESUME_SHIFT) +#define VMX_RUN_SAVE_SPEC_CTRL BIT(VMX_RUN_SAVE_SPEC_CTRL_SHIFT)
#endif /* __KVM_X86_VMX_RUN_FLAGS_H */ diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index be275a0410a8..b3b13ec04bac 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -139,7 +139,7 @@ SYM_FUNC_START(__vmx_vcpu_run) mov (%_ASM_SP), %_ASM_AX
/* Check if vmlaunch or vmresume is needed */ - test $VMX_RUN_VMRESUME, %ebx + bt $VMX_RUN_VMRESUME_SHIFT, %ebx
/* Load guest registers. Don't clobber flags. */ mov VCPU_RCX(%_ASM_AX), %_ASM_CX @@ -161,8 +161,8 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX
- /* Check EFLAGS.ZF from 'test VMX_RUN_VMRESUME' above */ - jz .Lvmlaunch + /* Check EFLAGS.CF from the VMX_RUN_VMRESUME bit test above. */ + jnc .Lvmlaunch
/* * After a successful VMRESUME/VMLAUNCH, control flow "magically"
commit 43fb862de8f628c5db5e96831c915b9aebf62d33 upstream.
During VMentry VERW is executed to mitigate MDS. After VERW, any memory access like register push onto stack may put host data in MDS affected CPU buffers. A guest can then use MDS to sample host data.
Although likelihood of secrets surviving in registers at current VERW callsite is less, but it can't be ruled out. Harden the MDS mitigation by moving the VERW mitigation late in VMentry path.
Note that VERW for MMIO Stale Data mitigation is unchanged because of the complexity of per-guest conditional VERW which is not easy to handle that late in asm with no GPRs available. If the CPU is also affected by MDS, VERW is unconditionally executed late in asm regardless of guest having MMIO access.
Signed-off-by: Pawan Gupta pawan.kumar.gupta@linux.intel.com Signed-off-by: Dave Hansen dave.hansen@linux.intel.com Acked-by: Sean Christopherson seanjc@google.com Link: https://lore.kernel.org/all/20240213-delay-verw-v8-6-a6216d83edb7%40linux.in... --- arch/x86/kvm/vmx/vmenter.S | 3 +++ arch/x86/kvm/vmx/vmx.c | 20 ++++++++++++++++---- 2 files changed, 19 insertions(+), 4 deletions(-)
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index b3b13ec04bac..139960deb736 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -161,6 +161,9 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX
+ /* Clobbers EFLAGS.ZF */ + CLEAR_CPU_BUFFERS + /* Check EFLAGS.CF from the VMX_RUN_VMRESUME bit test above. */ jnc .Lvmlaunch
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index b59ac1525b17..856eef56b3a8 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -387,7 +387,16 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx)
static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) { - vmx->disable_fb_clear = (host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) && + /* + * Disable VERW's behavior of clearing CPU buffers for the guest if the + * CPU isn't affected by MDS/TAA, and the host hasn't forcefully enabled + * the mitigation. Disabling the clearing behavior provides a + * performance boost for guests that aren't aware that manually clearing + * CPU buffers is unnecessary, at the cost of MSR accesses on VM-Entry + * and VM-Exit. + */ + vmx->disable_fb_clear = !cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF) && + (host_arch_capabilities & ARCH_CAP_FB_CLEAR_CTRL) && !boot_cpu_has_bug(X86_BUG_MDS) && !boot_cpu_has_bug(X86_BUG_TAA);
@@ -7226,11 +7235,14 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
guest_state_enter_irqoff();
- /* L1D Flush includes CPU buffer clear to mitigate MDS */ + /* + * L1D Flush includes CPU buffer clear to mitigate MDS, but VERW + * mitigation for MDS is done late in VMentry and is still + * executed in spite of L1D Flush. This is because an extra VERW + * should not matter much after the big hammer L1D Flush. + */ if (static_branch_unlikely(&vmx_l1d_should_flush)) vmx_l1d_flush(vcpu); - else if (cpu_feature_enabled(X86_FEATURE_CLEAR_CPU_BUF)) - mds_clear_cpu_buffers(); else if (static_branch_unlikely(&mmio_stale_data_clear) && kvm_arch_has_assigned_device(vcpu->kvm)) mds_clear_cpu_buffers();
linux-stable-mirror@lists.linaro.org
-
Greg KH -
Jiri Slaby -
Pawan Gupta