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 43606de22511..9f97a8bd11e8 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -223,6 +223,7 @@ 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 @@ -663,6 +664,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) /* Restore RDI. */ popq %rdi swapgs + CLEAR_CPU_BUFFERS jmp .Lnative_iret

@@ -774,6 +776,8 @@ 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 @@ -1502,6 +1506,12 @@ 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 @@ -1520,6 +1530,7 @@ SYM_CODE_START(ignore_sysret) UNWIND_HINT_END_OF_STACK ENDBR mov $-ENOSYS, %eax + CLEAR_CPU_BUFFERS sysretl SYM_CODE_END(ignore_sysret) #endif diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 4e88f8438706..306181e4fcb9 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -271,6 +271,7 @@ 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 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 a3db9647428b..8ae2cb30ade3 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -549,7 +549,6 @@ 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); @@ -583,17 +582,6 @@ 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 0bc55472f303..17eb4d76e3a5 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 4766b6bed443..07e045399348 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -556,9 +556,6 @@ 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 792245d7aa35..0775196ddea9 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))

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 0775196ddea9..b2ed051611b0 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();