[PATCH kernel v5 5/6] KVM: SEV: Enable data breakpoints in SEV-ES

[Alexey Kardashevskiy]

Prior to SEV-ES, KVM saved/restored host debug registers upon switching
to/from a VM. Changing those registers inside a running SEV VM
triggered #VMEXIT to KVM.

SEV-ES added encrypted state (ES) which uses an encrypted page
for the VM state (VMSA). The hardware saves/restores certain registers
on VMRUN/VMEXIT according to a swap type (A, B, C), see
"Table B-3. Swap Types" in the AMD Architecture Programmer’s Manual
volume 2.

The DR6 and DR7 registers have always been swapped as Type A for SEV-ES
guests, but a new feature is available, identified via
CPUID Fn8000001F_EAX[14] "DebugSwap for SEV-ES guests", that provides
support for swapping additional debug registers. DR[0-3] and
DR[0-3]_ADDR_MASK are swapped as Type B when SEV_FEATURES[5] (DebugSwap)
is set.

Enable DebugSwap for a VMSA but only do so if CPUID Fn80000021_EAX[0]
("NoNestedDataBp", "Processor ignores nested data breakpoints") is
supported by the SOC as otherwise a malicious SEV-ES guest can set up
data breakpoints on the #DB IDT entry/stack and cause an infinite loop.
Set the features bit in sev_es_sync_vmsa() which is the last point
when VMSA is not encrypted yet as sev_(es_)init_vmcb() (where the most
init happens) is called not only when VCPU is initialized but also on
intrahost migration when VMSA is encrypted.

Eliminate DR7 and #DB intercepts as:
- they are not needed when DebugSwap is supported;
- #VC for these intercepts is most likely not supported anyway and
kills the VM.

Signed-off-by: Alexey Kardashevskiy <aik@xxxxxxx>
Reviewed-by: Tom Lendacky <thomas.lendacky@xxxxxxx>
---
Changes:
v8:
* added CPUID's DebugSwap feature
* commit log, comments updated
* redid the whole thing

v4:
* removed sev_es_is_debug_swap_enabled() helper
* made sev_es_debug_swap_enabled (module param) static
* set sev_feature early in sev_es_init_vmcb() and made intercepts
  dependend on it vs. module param
* move set_/clr_dr_intercepts to .c

v3:
* rewrote the commit log again
* rebased on tip/master to use recently defined X86_FEATURE_NO_NESTED_DATA_BP
* s/boot_cpu_has/cpu_feature_enabled/

v2:
* debug_swap moved from vcpu to module_param
* rewrote commit log

---
Tested with:
===
int x;
int main(int argc, char *argv[])
{
        x = 1;
        return 0;
}
===
gcc -g a.c
rsync a.out ruby-954vm:~/
ssh -t ruby-954vm 'gdb -ex "file a.out" -ex "watch x" -ex r'

where ruby-954vm is a VM.

With "/sys/module/kvm_amd/parameters/debug_swap = 0", gdb does not stop
on the watchpoint, with "= 1" - gdb does.
---
 arch/x86/include/asm/cpufeatures.h |  1 +
 arch/x86/include/asm/svm.h         |  1 +
 arch/x86/kvm/svm/sev.c             | 36 ++++++++++++++++++--
 3 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index d9c190cdefa9..3a5eeb178778 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -435,6 +435,7 @@
 #define X86_FEATURE_SEV_ES		(19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */
 #define X86_FEATURE_V_TSC_AUX		(19*32+ 9) /* "" Virtual TSC_AUX */
 #define X86_FEATURE_SME_COHERENT	(19*32+10) /* "" AMD hardware-enforced cache coherency */
+#define X86_FEATURE_DEBUG_SWAP		(19*32+14) /* AMD SEV-ES full debug state swap support */
 
 /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */
 #define X86_FEATURE_NO_NESTED_DATA_BP	(20*32+ 0) /* "" No Nested Data Breakpoints */
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 770dcf75eaa9..3a422d213010 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -280,6 +280,7 @@ static_assert((X2AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == X2AVIC_
 #define AVIC_HPA_MASK	~((0xFFFULL << 52) | 0xFFF)
 #define VMCB_AVIC_APIC_BAR_MASK		0xFFFFFFFFFF000ULL
 
+#define SVM_SEV_FEAT_DEBUG_SWAP                        BIT(5)
 
 struct vmcb_seg {
 	u16 selector;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index f0885250252d..ba12e7962e94 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -22,6 +22,7 @@
 #include <asm/pkru.h>
 #include <asm/trapnr.h>
 #include <asm/fpu/xcr.h>
+#include <asm/debugreg.h>
 
 #include "mmu.h"
 #include "x86.h"
@@ -53,9 +54,14 @@ module_param_named(sev, sev_enabled, bool, 0444);
 /* enable/disable SEV-ES support */
 static bool sev_es_enabled = true;
 module_param_named(sev_es, sev_es_enabled, bool, 0444);
+
+/* enable/disable SEV-ES DebugSwap support */
+static bool sev_es_debug_swap_enabled = true;
+module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444);
 #else
 #define sev_enabled false
 #define sev_es_enabled false
+#define sev_es_debug_swap_enabled false
 #endif /* CONFIG_KVM_AMD_SEV */
 
 static u8 sev_enc_bit;
@@ -605,6 +611,9 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm)
 	save->xss  = svm->vcpu.arch.ia32_xss;
 	save->dr6  = svm->vcpu.arch.dr6;
 
+	if (sev_es_debug_swap_enabled)
+		save->sev_features |= SVM_SEV_FEAT_DEBUG_SWAP;
+
 	pr_debug("Virtual Machine Save Area (VMSA):\n");
 	print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, save, sizeof(*save), false);
 
@@ -2256,6 +2265,9 @@ void __init sev_hardware_setup(void)
 out:
 	sev_enabled = sev_supported;
 	sev_es_enabled = sev_es_supported;
+	if (!sev_es_enabled || !cpu_feature_enabled(X86_FEATURE_DEBUG_SWAP) ||
+	    !cpu_feature_enabled(X86_FEATURE_NO_NESTED_DATA_BP))
+		sev_es_debug_swap_enabled = false;
 #endif
 }
 
@@ -2976,14 +2988,20 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 	svm_set_intercept(svm, TRAP_CR8_WRITE);
 
 	/*
+	 * Unless DebugSwap (depends on X86_FEATURE_NO_NESTED_DATA_BP) is enabled,
 	 * DR7 access must remain intercepted for an SEV-ES guest to disallow
 	 * the guest kernel enable debugging as otherwise a VM writing to DR7
 	 * from the #DB handler may trigger infinite loop of #DB's.
 	 */
 	vmcb->control.intercepts[INTERCEPT_DR] = 0;
-	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ);
-	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE);
-	recalc_intercepts(svm);
+	if (sev_es_debug_swap_enabled) {
+		clr_exception_intercept(svm, DB_VECTOR);
+		/* clr_exception_intercept() called recalc_intercepts() */
+	} else {
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE);
+		recalc_intercepts(svm);
+	}
 
 	/* Can't intercept XSETBV, HV can't modify XCR0 directly */
 	svm_clr_intercept(svm, INTERCEPT_XSETBV);
@@ -3048,6 +3066,18 @@ void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa)
 
 	/* MSR_IA32_XSS is restored on VMEXIT, save the currnet host value */
 	hostsa->xss = host_xss;
+
+	/* The DebugSwap SEV feature does Type B swaps of DR[0-3] */
+	if (sev_es_debug_swap_enabled) {
+		hostsa->dr0 = native_get_debugreg(0);
+		hostsa->dr1 = native_get_debugreg(1);
+		hostsa->dr2 = native_get_debugreg(2);
+		hostsa->dr3 = native_get_debugreg(3);
+		hostsa->dr0_addr_mask = amd_get_dr_addr_mask(0);
+		hostsa->dr1_addr_mask = amd_get_dr_addr_mask(1);
+		hostsa->dr2_addr_mask = amd_get_dr_addr_mask(2);
+		hostsa->dr3_addr_mask = amd_get_dr_addr_mask(3);
+	}
 }
 
 void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
-- 
2.39.1