Skip to contentSkip to conversation

KVM: selftests: Add nested support to dirty_log_perf_test

PATCH Superseded David Matlack 1 participant 11 messages May 20, 2022

Subsystems (2)

v3 of 4 Superseded Latest is v4 →

lore
Share & tools
lore
#0 lore raw

v3 cover KVM: selftests: Add nested support to dirty_log_perf_test

This series adds support for taking any perf_test_util-based test and configuring it to run vCPUs in L2 instead of L1, and adds an option to dirty_log_perf_test to enable it.

This series was used to collect the performance data for eager page spliting for nested MMUs [1].

[1] https://lore.kernel.org/kvm/[email protected]/

v3:
- Only identity map a subset of the nGPA space [Sean, Peter]
- Fail if nested_paddr contains more than 48 bits [me]
- Move patch to delete all rule earlier [Peter]

v2: https://lore.kernel.org/kvm/[email protected]/
- Collect R-b tags from Peter.
- Use level macros instead of raw numbers [Peter]
- Remove "upper" from function name [Peter]
- Bring back setting the A/D bits on EPT PTEs [Peter]
- Drop "all" rule from Makefile [Peter]
- Reserve memory for EPT pages [Peter]
- Fix off-by-one error in nested_map_all_1g() [me]

v1: https://lore.kernel.org/kvm/[email protected]/

David Matlack (10):
KVM: selftests: Replace x86_page_size with PG_LEVEL_XX
KVM: selftests: Add option to create 2M and 1G EPT mappings
KVM: selftests: Drop stale function parameter comment for nested_map()
KVM: selftests: Refactor nested_map() to specify target level
KVM: selftests: Move VMX_EPT_VPID_CAP_AD_BITS to vmx.h
KVM: selftests: Add a helper to check EPT/VPID capabilities
KVM: selftests: Drop unnecessary rule for STATIC_LIBS
KVM: selftests: Link selftests directly with lib object files
KVM: selftests: Clean up LIBKVM files in Makefile
KVM: selftests: Add option to run dirty_log_perf_test vCPUs in L2

 tools/testing/selftests/kvm/Makefile          |  49 ++++--
 .../selftests/kvm/dirty_log_perf_test.c       |  10 +-
 .../selftests/kvm/include/perf_test_util.h    |   9 ++
 .../selftests/kvm/include/x86_64/processor.h  |  25 +--
 .../selftests/kvm/include/x86_64/vmx.h        |   6 +
 .../selftests/kvm/lib/perf_test_util.c        |  35 +++-
 .../selftests/kvm/lib/x86_64/perf_test_util.c | 112 +++++++++++++
 .../selftests/kvm/lib/x86_64/processor.c      |  33 ++--
 tools/testing/selftests/kvm/lib/x86_64/vmx.c  | 149 +++++++++++-------
 .../selftests/kvm/max_guest_memory_test.c     |   2 +-
 .../selftests/kvm/x86_64/mmu_role_test.c      |   2 +-
 11 files changed, 328 insertions(+), 104 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c

base-commit: a3808d88461270c71d3fece5e51cc486ecdac7d0

Signature · 1 line
2.36.1.124.g0e6072fb45-goog
#1 lore raw

PATCH v3 1/10 KVM: selftests: Replace x86_page_size with PG_LEVEL_XX

x86_page_size is an enum used to communicate the desired page size with which to map a range of memory. Under the hood they just encode the desired level at which to map the page. This ends up being clunky in a few ways:

- The name suggests it encodes the size of the page rather than the level.
- In other places in x86_64/processor.c we just use a raw int to encode the level.

Simplify this by adopting the kernel style of PG_LEVEL_XX enums and pass around raw ints when referring to the level. This makes the code easier to understand since these macros are very common in KVM MMU code.

---
 .../selftests/kvm/include/x86_64/processor.h  | 18 ++++++----
 .../selftests/kvm/lib/x86_64/processor.c      | 33 ++++++++++---------
 .../selftests/kvm/max_guest_memory_test.c     |  2 +-
 .../selftests/kvm/x86_64/mmu_role_test.c      |  2 +-
 4 files changed, 31 insertions(+), 24 deletions(-)
tools/testing/selftests/kvm/include/x86_64/processor.h +12 -6
index 37db341d4cc5..434a4f60f4d9 100644
@@ -465,13 +465,19 @@ void vcpu_set_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid);
 struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vm *vm, uint32_t vcpuid);
 void vm_xsave_req_perm(int bit);
 
-enum x86_page_size {
-	X86_PAGE_SIZE_4K = 0,
-	X86_PAGE_SIZE_2M,
-	X86_PAGE_SIZE_1G,
+enum pg_level {
+	PG_LEVEL_NONE,
+	PG_LEVEL_4K,
+	PG_LEVEL_2M,
+	PG_LEVEL_1G,
+	PG_LEVEL_512G,
+	PG_LEVEL_NUM
 };
-void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
-		   enum x86_page_size page_size);
+
+#define PG_LEVEL_SHIFT(_level) ((_level - 1) * 9 + 12)
+#define PG_LEVEL_SIZE(_level) (1ull << PG_LEVEL_SHIFT(_level))
+
+void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level);
 
 /*
  * Basic CPU control in CR0
tools/testing/selftests/kvm/lib/x86_64/processor.c +17 -16
index 9f000dfb5594..f733c5b02da5 100644
@@ -190,7 +190,7 @@ static void *virt_get_pte(struct kvm_vm *vm, uint64_t pt_pfn, uint64_t vaddr,
 			  int level)
 {
 	uint64_t *page_table = addr_gpa2hva(vm, pt_pfn << vm->page_shift);
-	int index = vaddr >> (vm->page_shift + level * 9) & 0x1ffu;
+	int index = (vaddr >> PG_LEVEL_SHIFT(level)) & 0x1ffu;
 
 	return &page_table[index];
 }
@@ -199,15 +199,15 @@ static struct pageUpperEntry *virt_create_upper_pte(struct kvm_vm *vm,
 						    uint64_t pt_pfn,
 						    uint64_t vaddr,
 						    uint64_t paddr,
-						    int level,
-						    enum x86_page_size page_size)
+						    int current_level,
+						    int target_level)
 {
-	struct pageUpperEntry *pte = virt_get_pte(vm, pt_pfn, vaddr, level);
+	struct pageUpperEntry *pte = virt_get_pte(vm, pt_pfn, vaddr, current_level);
 
 	if (!pte->present) {
 		pte->writable = true;
 		pte->present = true;
-		pte->page_size = (level == page_size);
+		pte->page_size = (current_level == target_level);
 		if (pte->page_size)
 			pte->pfn = paddr >> vm->page_shift;
 		else
@@ -218,20 +218,19 @@ static struct pageUpperEntry *virt_create_upper_pte(struct kvm_vm *vm,
 		 * a hugepage at this level, and that there isn't a hugepage at
 		 * this level.
 		 */
-		TEST_ASSERT(level != page_size,
+		TEST_ASSERT(current_level != target_level,
 			    "Cannot create hugepage at level: %u, vaddr: 0x%lx\n",
-			    page_size, vaddr);
+			    current_level, vaddr);
 		TEST_ASSERT(!pte->page_size,
 			    "Cannot create page table at level: %u, vaddr: 0x%lx\n",
-			    level, vaddr);
+			    current_level, vaddr);
 	}
 	return pte;
 }
 
-void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
-		   enum x86_page_size page_size)
+void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level)
 {
-	const uint64_t pg_size = 1ull << ((page_size * 9) + 12);
+	const uint64_t pg_size = PG_LEVEL_SIZE(level);
 	struct pageUpperEntry *pml4e, *pdpe, *pde;
 	struct pageTableEntry *pte;
 
@@ -256,20 +255,22 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 	 * early if a hugepage was created.
 	 */
 	pml4e = virt_create_upper_pte(vm, vm->pgd >> vm->page_shift,
-				      vaddr, paddr, 3, page_size);
+				      vaddr, paddr, PG_LEVEL_512G, level);
 	if (pml4e->page_size)
 		return;
 
-	pdpe = virt_create_upper_pte(vm, pml4e->pfn, vaddr, paddr, 2, page_size);
+	pdpe = virt_create_upper_pte(vm, pml4e->pfn, vaddr, paddr, PG_LEVEL_1G,
+				     level);
 	if (pdpe->page_size)
 		return;
 
-	pde = virt_create_upper_pte(vm, pdpe->pfn, vaddr, paddr, 1, page_size);
+	pde = virt_create_upper_pte(vm, pdpe->pfn, vaddr, paddr, PG_LEVEL_2M,
+				    level);
 	if (pde->page_size)
 		return;
 
 	/* Fill in page table entry. */
-	pte = virt_get_pte(vm, pde->pfn, vaddr, 0);
+	pte = virt_get_pte(vm, pde->pfn, vaddr, PG_LEVEL_4K);
 	TEST_ASSERT(!pte->present,
 		    "PTE already present for 4k page at vaddr: 0x%lx\n", vaddr);
 	pte->pfn = paddr >> vm->page_shift;
@@ -279,7 +280,7 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 
 void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
 {
-	__virt_pg_map(vm, vaddr, paddr, X86_PAGE_SIZE_4K);
+	__virt_pg_map(vm, vaddr, paddr, PG_LEVEL_4K);
 }
 
 static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid,
tools/testing/selftests/kvm/max_guest_memory_test.c +1 -1
index 3875c4b23a04..15f046e19cb2 100644
@@ -244,7 +244,7 @@ int main(int argc, char *argv[])
 #ifdef __x86_64__
 		/* Identity map memory in the guest using 1gb pages. */
 		for (i = 0; i < slot_size; i += size_1gb)
-			__virt_pg_map(vm, gpa + i, gpa + i, X86_PAGE_SIZE_1G);
+			__virt_pg_map(vm, gpa + i, gpa + i, PG_LEVEL_1G);
 #else
 		for (i = 0; i < slot_size; i += vm_get_page_size(vm))
 			virt_pg_map(vm, gpa + i, gpa + i);
tools/testing/selftests/kvm/x86_64/mmu_role_test.c +1 -1
index da2325fcad87..bdecd532f935 100644
@@ -35,7 +35,7 @@ static void mmu_role_test(u32 *cpuid_reg, u32 evil_cpuid_val)
 	run = vcpu_state(vm, VCPU_ID);
 
 	/* Map 1gb page without a backing memlot. */
-	__virt_pg_map(vm, MMIO_GPA, MMIO_GPA, X86_PAGE_SIZE_1G);
+	__virt_pg_map(vm, MMIO_GPA, MMIO_GPA, PG_LEVEL_1G);
 
 	r = _vcpu_run(vm, VCPU_ID);
 
Signature · 1 line
2.36.1.124.g0e6072fb45-goog
#2 lore raw

PATCH v3 2/10 KVM: selftests: Add option to create 2M and 1G EPT mappings

In reply to David Matlack

The current EPT mapping code in the selftests only supports mapping 4K pages. This commit extends that support with an option to map at 2M or 1G. This will be used in a future commit to create large page mappings to test eager page splitting.

No functional change intended.

---
 tools/testing/selftests/kvm/lib/x86_64/vmx.c | 110 ++++++++++---------
 1 file changed, 60 insertions(+), 50 deletions(-)
tools/testing/selftests/kvm/lib/x86_64/vmx.c +60 -50
index d089d8b850b5..fdc1e6deb922 100644
@@ -392,80 +392,90 @@ void nested_vmx_check_supported(void)
 	}
 }
 
-void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
-		   uint64_t nested_paddr, uint64_t paddr)
+static void nested_create_pte(struct kvm_vm *vm,
+			      struct eptPageTableEntry *pte,
+			      uint64_t nested_paddr,
+			      uint64_t paddr,
+			      int current_level,
+			      int target_level)
+{
+	if (!pte->readable) {
+		pte->writable = true;
+		pte->readable = true;
+		pte->executable = true;
+		pte->page_size = (current_level == target_level);
+		if (pte->page_size)
+			pte->address = paddr >> vm->page_shift;
+		else
+			pte->address = vm_alloc_page_table(vm) >> vm->page_shift;
+	} else {
+		/*
+		 * Entry already present.  Assert that the caller doesn't want
+		 * a hugepage at this level, and that there isn't a hugepage at
+		 * this level.
+		 */
+		TEST_ASSERT(current_level != target_level,
+			    "Cannot create hugepage at level: %u, nested_paddr: 0x%lx\n",
+			    current_level, nested_paddr);
+		TEST_ASSERT(!pte->page_size,
+			    "Cannot create page table at level: %u, nested_paddr: 0x%lx\n",
+			    current_level, nested_paddr);
+	}
+}
+
+
+void __nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+		     uint64_t nested_paddr, uint64_t paddr, int target_level)
 {
-	uint16_t index[4];
-	struct eptPageTableEntry *pml4e;
+	const uint64_t page_size = PG_LEVEL_SIZE(target_level);
+	struct eptPageTableEntry *pt = vmx->eptp_hva, *pte;
+	uint16_t index;
 
 	TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
 		    "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
 
-	TEST_ASSERT((nested_paddr % vm->page_size) == 0,
+	TEST_ASSERT((nested_paddr % page_size) == 0,
 		    "Nested physical address not on page boundary,\n"
-		    "  nested_paddr: 0x%lx vm->page_size: 0x%x",
-		    nested_paddr, vm->page_size);
+		    "  nested_paddr: 0x%lx page_size: 0x%lx",
+		    nested_paddr, page_size);
 	TEST_ASSERT((nested_paddr >> vm->page_shift) <= vm->max_gfn,
 		    "Physical address beyond beyond maximum supported,\n"
 		    "  nested_paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
 		    paddr, vm->max_gfn, vm->page_size);
-	TEST_ASSERT((paddr % vm->page_size) == 0,
+	TEST_ASSERT((paddr % page_size) == 0,
 		    "Physical address not on page boundary,\n"
-		    "  paddr: 0x%lx vm->page_size: 0x%x",
-		    paddr, vm->page_size);
+		    "  paddr: 0x%lx page_size: 0x%lx",
+		    paddr, page_size);
 	TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn,
 		    "Physical address beyond beyond maximum supported,\n"
 		    "  paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
 		    paddr, vm->max_gfn, vm->page_size);
 
-	index[0] = (nested_paddr >> 12) & 0x1ffu;
-	index[1] = (nested_paddr >> 21) & 0x1ffu;
-	index[2] = (nested_paddr >> 30) & 0x1ffu;
-	index[3] = (nested_paddr >> 39) & 0x1ffu;
-
-	/* Allocate page directory pointer table if not present. */
-	pml4e = vmx->eptp_hva;
-	if (!pml4e[index[3]].readable) {
-		pml4e[index[3]].address = vm_alloc_page_table(vm) >> vm->page_shift;
-		pml4e[index[3]].writable = true;
-		pml4e[index[3]].readable = true;
-		pml4e[index[3]].executable = true;
-	}
+	for (int level = PG_LEVEL_512G; level >= PG_LEVEL_4K; level--) {
+		index = (nested_paddr >> PG_LEVEL_SHIFT(level)) & 0x1ffu;
+		pte = &pt[index];
 
-	/* Allocate page directory table if not present. */
-	struct eptPageTableEntry *pdpe;
-	pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
-	if (!pdpe[index[2]].readable) {
-		pdpe[index[2]].address = vm_alloc_page_table(vm) >> vm->page_shift;
-		pdpe[index[2]].writable = true;
-		pdpe[index[2]].readable = true;
-		pdpe[index[2]].executable = true;
-	}
+		nested_create_pte(vm, pte, nested_paddr, paddr, level, target_level);
 
-	/* Allocate page table if not present. */
-	struct eptPageTableEntry *pde;
-	pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
-	if (!pde[index[1]].readable) {
-		pde[index[1]].address = vm_alloc_page_table(vm) >> vm->page_shift;
-		pde[index[1]].writable = true;
-		pde[index[1]].readable = true;
-		pde[index[1]].executable = true;
-	}
+		if (pte->page_size)
+			break;
 
-	/* Fill in page table entry. */
-	struct eptPageTableEntry *pte;
-	pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
-	pte[index[0]].address = paddr >> vm->page_shift;
-	pte[index[0]].writable = true;
-	pte[index[0]].readable = true;
-	pte[index[0]].executable = true;
+		pt = addr_gpa2hva(vm, pte->address * vm->page_size);
+	}
 
 	/*
 	 * For now mark these as accessed and dirty because the only
 	 * testcase we have needs that.  Can be reconsidered later.
 	 */
-	pte[index[0]].accessed = true;
-	pte[index[0]].dirty = true;
+	pte->accessed = true;
+	pte->dirty = true;
+
+}
+
+void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+		   uint64_t nested_paddr, uint64_t paddr)
+{
+	__nested_pg_map(vmx, vm, nested_paddr, paddr, PG_LEVEL_4K);
 }
 
 /*
Signature · 1 line
2.36.1.124.g0e6072fb45-goog
#3 lore raw

PATCH v3 3/10 KVM: selftests: Drop stale function parameter comment for nested_map()

In reply to David Matlack

nested_map() does not take a parameter named eptp_memslot. Drop the comment referring to it.

---
 tools/testing/selftests/kvm/lib/x86_64/vmx.c | 1 -
 1 file changed, 1 deletion(-)
tools/testing/selftests/kvm/lib/x86_64/vmx.c +0 -1
index fdc1e6deb922..baeaa35de113 100644
@@ -486,7 +486,6 @@ void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
  *   nested_paddr - Nested guest physical address to map
  *   paddr - VM Physical Address
  *   size - The size of the range to map
- *   eptp_memslot - Memory region slot for new virtual translation tables
  *
  * Output Args: None
  *
Signature · 1 line
2.36.1.124.g0e6072fb45-goog
#4 lore raw

PATCH v3 4/10 KVM: selftests: Refactor nested_map() to specify target level

In reply to David Matlack

Refactor nested_map() to specify that it explicityl wants 4K mappings (the existing behavior) and push the implementation down into __nested_map(), which can be used in subsequent commits to create huge page mappings.

No function change intended.

---
 tools/testing/selftests/kvm/lib/x86_64/vmx.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)
tools/testing/selftests/kvm/lib/x86_64/vmx.c +12 -4
index baeaa35de113..b8cfe4914a3a 100644
@@ -486,6 +486,7 @@ void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
  *   nested_paddr - Nested guest physical address to map
  *   paddr - VM Physical Address
  *   size - The size of the range to map
+ *   level - The level at which to map the range
  *
  * Output Args: None
  *
@@ -494,22 +495,29 @@ void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
  * Within the VM given by vm, creates a nested guest translation for the
  * page range starting at nested_paddr to the page range starting at paddr.
  */
-void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
-		uint64_t nested_paddr, uint64_t paddr, uint64_t size)
+void __nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+		  uint64_t nested_paddr, uint64_t paddr, uint64_t size,
+		  int level)
 {
-	size_t page_size = vm->page_size;
+	size_t page_size = PG_LEVEL_SIZE(level);
 	size_t npages = size / page_size;
 
 	TEST_ASSERT(nested_paddr + size > nested_paddr, "Vaddr overflow");
 	TEST_ASSERT(paddr + size > paddr, "Paddr overflow");
 
 	while (npages--) {
-		nested_pg_map(vmx, vm, nested_paddr, paddr);
+		__nested_pg_map(vmx, vm, nested_paddr, paddr, level);
 		nested_paddr += page_size;
 		paddr += page_size;
 	}
 }
 
+void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
+		uint64_t nested_paddr, uint64_t paddr, uint64_t size)
+{
+	__nested_map(vmx, vm, nested_paddr, paddr, size, PG_LEVEL_4K);
+}
+
 /* Prepare an identity extended page table that maps all the
  * physical pages in VM.
  */
Signature · 1 line
2.36.1.124.g0e6072fb45-goog
#5 lore raw

PATCH v3 5/10 KVM: selftests: Move VMX_EPT_VPID_CAP_AD_BITS to vmx.h

In reply to David Matlack

This is a VMX-related macro so move it to vmx.h. While here, open code the mask like the rest of the VMX bitmask macros.

No functional change intended.

---
 tools/testing/selftests/kvm/include/x86_64/processor.h | 3 ---
 tools/testing/selftests/kvm/include/x86_64/vmx.h       | 2 ++
 2 files changed, 2 insertions(+), 3 deletions(-)
tools/testing/selftests/kvm/include/x86_64/processor.h +0 -3
index 434a4f60f4d9..04f1d540bcb2 100644
@@ -494,9 +494,6 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level)
 #define X86_CR0_CD          (1UL<<30) /* Cache Disable */
 #define X86_CR0_PG          (1UL<<31) /* Paging */
 
-/* VMX_EPT_VPID_CAP bits */
-#define VMX_EPT_VPID_CAP_AD_BITS       (1ULL << 21)
-
 #define XSTATE_XTILE_CFG_BIT		17
 #define XSTATE_XTILE_DATA_BIT		18
 
tools/testing/selftests/kvm/include/x86_64/vmx.h +2 -0
index 583ceb0d1457..3b1794baa97c 100644
@@ -96,6 +96,8 @@
 #define VMX_MISC_PREEMPTION_TIMER_RATE_MASK	0x0000001f
 #define VMX_MISC_SAVE_EFER_LMA			0x00000020
 
+#define VMX_EPT_VPID_CAP_AD_BITS		0x00200000
+
 #define EXIT_REASON_FAILED_VMENTRY	0x80000000
 #define EXIT_REASON_EXCEPTION_NMI	0
 #define EXIT_REASON_EXTERNAL_INTERRUPT	1
Signature · 1 line
2.36.1.124.g0e6072fb45-goog
#6 lore raw

PATCH v3 6/10 KVM: selftests: Add a helper to check EPT/VPID capabilities

In reply to David Matlack

Create a small helper function to check if a given EPT/VPID capability is supported. This will be re-used in a follow-up commit to check for 1G page support.

No functional change intended.

---
 tools/testing/selftests/kvm/lib/x86_64/vmx.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)
tools/testing/selftests/kvm/lib/x86_64/vmx.c +6 -1
index b8cfe4914a3a..5bf169179455 100644
@@ -198,6 +198,11 @@ bool load_vmcs(struct vmx_pages *vmx)
 	return true;
 }
 
+static bool ept_vpid_cap_supported(uint64_t mask)
+{
+	return rdmsr(MSR_IA32_VMX_EPT_VPID_CAP) & mask;
+}
+
 /*
  * Initialize the control fields to the most basic settings possible.
  */
@@ -215,7 +220,7 @@ static inline void init_vmcs_control_fields(struct vmx_pages *vmx)
 		struct eptPageTablePointer eptp = {
 			.memory_type = VMX_BASIC_MEM_TYPE_WB,
 			.page_walk_length = 3, /* + 1 */
-			.ad_enabled = !!(rdmsr(MSR_IA32_VMX_EPT_VPID_CAP) & VMX_EPT_VPID_CAP_AD_BITS),
+			.ad_enabled = ept_vpid_cap_supported(VMX_EPT_VPID_CAP_AD_BITS),
 			.address = vmx->eptp_gpa >> PAGE_SHIFT_4K,
 		};
 
Signature · 1 line
2.36.1.124.g0e6072fb45-goog
#7 lore raw

PATCH v3 7/10 KVM: selftests: Drop unnecessary rule for STATIC_LIBS

In reply to David Matlack

Drop the "all: $(STATIC_LIBS)" rule. The KVM selftests already depend on $(STATIC_LIBS), so there is no reason to have an extra "all" rule.

---
 tools/testing/selftests/kvm/Makefile | 1 -
 1 file changed, 1 deletion(-)
tools/testing/selftests/kvm/Makefile +0 -1
index 8c3db2f75315..ae49abe682a7 100644
@@ -192,7 +192,6 @@ $(OUTPUT)/libkvm.a: $(LIBKVM_OBJS)
 	$(AR) crs $@ $^
 
 x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS))))
-all: $(STATIC_LIBS)
 $(TEST_GEN_PROGS): $(STATIC_LIBS)
 
 cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib ..
Signature · 1 line
2.36.1.124.g0e6072fb45-goog
#8 lore raw

PATCH v3 8/10 KVM: selftests: Link selftests directly with lib object files

In reply to David Matlack

The linker does obey strong/weak symbols when linking static libraries, it simply resolves an undefined symbol to the first-encountered symbol. This means that defining __weak arch-generic functions and then defining arch-specific strong functions to override them in libkvm will not always work.

More specifically, if we have:

lib/generic.c:

  void __weak foo(void)
  {
          pr_info("weak\n");
  }

  void bar(void)
  {
          foo();
  }

lib/x86_64/arch.c:

  void foo(void)
  {
          pr_info("strong\n");
  }

And a selftest that calls bar(), it will print "weak". Now if you make generic.o explicitly depend on arch.o (e.g. add function to arch.c that is called directly from generic.c) it will print "strong". In other words, it seems that the linker is free to throw out arch.o when linking because generic.o does not explicitly depend on it, which causes the linker to lose the strong symbol.

One solution is to link libkvm.a with --whole-archive so that the linker doesn't throw away object files it thinks are unnecessary. However that is a bit difficult to plumb since we are using the common selftests makefile rules. An easier solution is to drop libkvm.a just link selftests with all the .o files that were originally in libkvm.a.

---
 tools/testing/selftests/kvm/Makefile | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)
tools/testing/selftests/kvm/Makefile +4 -7
index ae49abe682a7..0889fc17baa5 100644
@@ -173,12 +173,13 @@ LDFLAGS += -pthread $(no-pie-option) $(pgste-option)
 # $(TEST_GEN_PROGS) starts with $(OUTPUT)/
 include ../lib.mk
 
-STATIC_LIBS := $(OUTPUT)/libkvm.a
 LIBKVM_C := $(filter %.c,$(LIBKVM))
 LIBKVM_S := $(filter %.S,$(LIBKVM))
 LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C))
 LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S))
-EXTRA_CLEAN += $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(STATIC_LIBS) cscope.*
+LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)
+
+EXTRA_CLEAN += $(LIBKVM_OBJS) cscope.*
 
 x := $(shell mkdir -p $(sort $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ))))
 $(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c
@@ -187,12 +188,8 @@ $(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c
 $(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S
 	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
 
-LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)
-$(OUTPUT)/libkvm.a: $(LIBKVM_OBJS)
-	$(AR) crs $@ $^
-
 x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS))))
-$(TEST_GEN_PROGS): $(STATIC_LIBS)
+$(TEST_GEN_PROGS): $(LIBKVM_OBJS)
 
 cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib ..
 cscope:
Signature · 1 line
2.36.1.124.g0e6072fb45-goog
#9 lore raw

PATCH v3 9/10 KVM: selftests: Clean up LIBKVM files in Makefile

In reply to David Matlack

Break up the long lines for LIBKVM and alphabetize each architecture. This makes reading the Makefile easier, and will make reading diffs to LIBKVM easier.

No functional change intended.

---
 tools/testing/selftests/kvm/Makefile | 36 ++++++++++++++++++++++++----
 1 file changed, 31 insertions(+), 5 deletions(-)
tools/testing/selftests/kvm/Makefile +31 -5
index 0889fc17baa5..83b9ffa456ea 100644
@@ -37,11 +37,37 @@ ifeq ($(ARCH),riscv)
 	UNAME_M := riscv
 endif
 
-LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/rbtree.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c
-LIBKVM_x86_64 = lib/x86_64/apic.c lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S
-LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c lib/aarch64/handlers.S lib/aarch64/spinlock.c lib/aarch64/gic.c lib/aarch64/gic_v3.c lib/aarch64/vgic.c
-LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c
-LIBKVM_riscv = lib/riscv/processor.c lib/riscv/ucall.c
+LIBKVM += lib/assert.c
+LIBKVM += lib/elf.c
+LIBKVM += lib/guest_modes.c
+LIBKVM += lib/io.c
+LIBKVM += lib/kvm_util.c
+LIBKVM += lib/perf_test_util.c
+LIBKVM += lib/rbtree.c
+LIBKVM += lib/sparsebit.c
+LIBKVM += lib/test_util.c
+
+LIBKVM_x86_64 += lib/x86_64/apic.c
+LIBKVM_x86_64 += lib/x86_64/handlers.S
+LIBKVM_x86_64 += lib/x86_64/processor.c
+LIBKVM_x86_64 += lib/x86_64/svm.c
+LIBKVM_x86_64 += lib/x86_64/ucall.c
+LIBKVM_x86_64 += lib/x86_64/vmx.c
+
+LIBKVM_aarch64 += lib/aarch64/gic.c
+LIBKVM_aarch64 += lib/aarch64/gic_v3.c
+LIBKVM_aarch64 += lib/aarch64/handlers.S
+LIBKVM_aarch64 += lib/aarch64/processor.c
+LIBKVM_aarch64 += lib/aarch64/spinlock.c
+LIBKVM_aarch64 += lib/aarch64/ucall.c
+LIBKVM_aarch64 += lib/aarch64/vgic.c
+
+LIBKVM_s390x += lib/s390x/diag318_test_handler.c
+LIBKVM_s390x += lib/s390x/processor.c
+LIBKVM_s390x += lib/s390x/ucall.c
+
+LIBKVM_riscv += lib/riscv/processor.c
+LIBKVM_riscv += lib/riscv/ucall.c
 
 TEST_GEN_PROGS_x86_64 = x86_64/cpuid_test
 TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
Signature · 1 line
2.36.1.124.g0e6072fb45-goog
#10 lore raw

PATCH v3 10/10 KVM: selftests: Add option to run dirty_log_perf_test vCPUs in L2

In reply to David Matlack

Add an option to dirty_log_perf_test that configures the vCPUs to run in L2 instead of L1. This makes it possible to benchmark the dirty logging performance of nested virtualization, which is particularly interesting because KVM must shadow L1's EPT/NPT tables.

For now this support only works on x86_64 CPUs with VMX. Otherwise passing -n results in the test being skipped.

---
 tools/testing/selftests/kvm/Makefile          |   1 +
 .../selftests/kvm/dirty_log_perf_test.c       |  10 +-
 .../selftests/kvm/include/perf_test_util.h    |   9 ++
 .../selftests/kvm/include/x86_64/processor.h  |   4 +
 .../selftests/kvm/include/x86_64/vmx.h        |   4 +
 .../selftests/kvm/lib/perf_test_util.c        |  35 +++++-
 .../selftests/kvm/lib/x86_64/perf_test_util.c | 112 ++++++++++++++++++
 tools/testing/selftests/kvm/lib/x86_64/vmx.c  |  15 +++
 8 files changed, 182 insertions(+), 8 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c
tools/testing/selftests/kvm/Makefile +1 -0
index 83b9ffa456ea..42cb904f6e54 100644
@@ -49,6 +49,7 @@ LIBKVM += lib/test_util.c
 
 LIBKVM_x86_64 += lib/x86_64/apic.c
 LIBKVM_x86_64 += lib/x86_64/handlers.S
+LIBKVM_x86_64 += lib/x86_64/perf_test_util.c
 LIBKVM_x86_64 += lib/x86_64/processor.c
 LIBKVM_x86_64 += lib/x86_64/svm.c
 LIBKVM_x86_64 += lib/x86_64/ucall.c
tools/testing/selftests/kvm/dirty_log_perf_test.c +7 -3
index 7b47ae4f952e..d60a34cdfaee 100644
@@ -336,8 +336,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 static void help(char *name)
 {
 	puts("");
-	printf("usage: %s [-h] [-i iterations] [-p offset] [-g]"
-	       "[-m mode] [-b vcpu bytes] [-v vcpus] [-o] [-s mem type]"
+	printf("usage: %s [-h] [-i iterations] [-p offset] [-g] "
+	       "[-m mode] [-n] [-b vcpu bytes] [-v vcpus] [-o] [-s mem type]"
 	       "[-x memslots]\n", name);
 	puts("");
 	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
@@ -351,6 +351,7 @@ static void help(char *name)
 	printf(" -p: specify guest physical test memory offset\n"
 	       "     Warning: a low offset can conflict with the loaded test code.\n");
 	guest_modes_help();
+	printf(" -n: Run the vCPUs in nested mode (L2)\n");
 	printf(" -b: specify the size of the memory region which should be\n"
 	       "     dirtied by each vCPU. e.g. 10M or 3G.\n"
 	       "     (default: 1G)\n");
@@ -387,7 +388,7 @@ int main(int argc, char *argv[])
 
 	guest_modes_append_default();
 
-	while ((opt = getopt(argc, argv, "ghi:p:m:b:f:v:os:x:")) != -1) {
+	while ((opt = getopt(argc, argv, "ghi:p:m:nb:f:v:os:x:")) != -1) {
 		switch (opt) {
 		case 'g':
 			dirty_log_manual_caps = 0;
@@ -401,6 +402,9 @@ int main(int argc, char *argv[])
 		case 'm':
 			guest_modes_cmdline(optarg);
 			break;
+		case 'n':
+			perf_test_args.nested = true;
+			break;
 		case 'b':
 			guest_percpu_mem_size = parse_size(optarg);
 			break;
tools/testing/selftests/kvm/include/perf_test_util.h +9 -0
index a86f953d8d36..d822cb670f1c 100644
@@ -30,10 +30,15 @@ struct perf_test_vcpu_args {
 
 struct perf_test_args {
 	struct kvm_vm *vm;
+	/* The starting address and size of the guest test region. */
 	uint64_t gpa;
+	uint64_t size;
 	uint64_t guest_page_size;
 	int wr_fract;
 
+	/* Run vCPUs in L2 instead of L1, if the architecture supports it. */
+	bool nested;
+
 	struct perf_test_vcpu_args vcpu_args[KVM_MAX_VCPUS];
 };
 
@@ -49,5 +54,9 @@ void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract);
 
 void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *));
 void perf_test_join_vcpu_threads(int vcpus);
+void perf_test_guest_code(uint32_t vcpu_id);
+
+uint64_t perf_test_nested_pages(int nr_vcpus);
+void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus);
 
 #endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */
tools/testing/selftests/kvm/include/x86_64/processor.h +4 -0
index 04f1d540bcb2..2aaea757432a 100644
@@ -477,6 +477,10 @@ enum pg_level {
 #define PG_LEVEL_SHIFT(_level) ((_level - 1) * 9 + 12)
 #define PG_LEVEL_SIZE(_level) (1ull << PG_LEVEL_SHIFT(_level))
 
+#define PG_SIZE_4K PG_LEVEL_SIZE(PG_LEVEL_4K)
+#define PG_SIZE_2M PG_LEVEL_SIZE(PG_LEVEL_2M)
+#define PG_SIZE_1G PG_LEVEL_SIZE(PG_LEVEL_1G)
+
 void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level);
 
 /*
tools/testing/selftests/kvm/include/x86_64/vmx.h +4 -0
index 3b1794baa97c..cc3604f8f1d3 100644
@@ -96,6 +96,7 @@
 #define VMX_MISC_PREEMPTION_TIMER_RATE_MASK	0x0000001f
 #define VMX_MISC_SAVE_EFER_LMA			0x00000020
 
+#define VMX_EPT_VPID_CAP_1G_PAGES		0x00020000
 #define VMX_EPT_VPID_CAP_AD_BITS		0x00200000
 
 #define EXIT_REASON_FAILED_VMENTRY	0x80000000
@@ -608,6 +609,7 @@ bool load_vmcs(struct vmx_pages *vmx);
 
 bool nested_vmx_supported(void);
 void nested_vmx_check_supported(void);
+bool ept_1g_pages_supported(void);
 
 void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
 		   uint64_t nested_paddr, uint64_t paddr);
@@ -615,6 +617,8 @@ void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
 		 uint64_t nested_paddr, uint64_t paddr, uint64_t size);
 void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm,
 			uint32_t memslot);
+void nested_identity_map_1g(struct vmx_pages *vmx, struct kvm_vm *vm,
+			    uint64_t addr, uint64_t size);
 void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
 		  uint32_t eptp_memslot);
 void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm);
tools/testing/selftests/kvm/lib/perf_test_util.c +30 -5
index 722df3a28791..b2ff2cee2e51 100644
@@ -40,7 +40,7 @@ static bool all_vcpu_threads_running;
  * Continuously write to the first 8 bytes of each page in the
  * specified region.
  */
-static void guest_code(uint32_t vcpu_id)
+void perf_test_guest_code(uint32_t vcpu_id)
 {
 	struct perf_test_args *pta = &perf_test_args;
 	struct perf_test_vcpu_args *vcpu_args = &pta->vcpu_args[vcpu_id];
@@ -108,7 +108,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 {
 	struct perf_test_args *pta = &perf_test_args;
 	struct kvm_vm *vm;
-	uint64_t guest_num_pages;
+	uint64_t guest_num_pages, slot0_pages = DEFAULT_GUEST_PHY_PAGES;
 	uint64_t backing_src_pagesz = get_backing_src_pagesz(backing_src);
 	int i;
 
@@ -134,13 +134,20 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 		    "Guest memory cannot be evenly divided into %d slots.",
 		    slots);
 
+	/*
+	 * If using nested, allocate extra pages for the nested page tables and
+	 * in-memory data structures.
+	 */
+	if (pta->nested)
+		slot0_pages += perf_test_nested_pages(vcpus);
+
 	/*
 	 * Pass guest_num_pages to populate the page tables for test memory.
 	 * The memory is also added to memslot 0, but that's a benign side
 	 * effect as KVM allows aliasing HVAs in meslots.
 	 */
-	vm = vm_create_with_vcpus(mode, vcpus, DEFAULT_GUEST_PHY_PAGES,
-				  guest_num_pages, 0, guest_code, NULL);
+	vm = vm_create_with_vcpus(mode, vcpus, slot0_pages, guest_num_pages, 0,
+				  perf_test_guest_code, NULL);
 
 	pta->vm = vm;
 
@@ -161,7 +168,9 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 	/* Align to 1M (segment size) */
 	pta->gpa = align_down(pta->gpa, 1 << 20);
 #endif
-	pr_info("guest physical test memory offset: 0x%lx\n", pta->gpa);
+	pta->size = guest_num_pages * pta->guest_page_size;
+	pr_info("guest physical test memory: [0x%lx, 0x%lx)\n",
+		pta->gpa, pta->gpa + pta->size);
 
 	/* Add extra memory slots for testing */
 	for (i = 0; i < slots; i++) {
@@ -178,6 +187,11 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 
 	perf_test_setup_vcpus(vm, vcpus, vcpu_memory_bytes, partition_vcpu_memory_access);
 
+	if (pta->nested) {
+		pr_info("Configuring vCPUs to run in L2 (nested).\n");
+		perf_test_setup_nested(vm, vcpus);
+	}
+
 	ucall_init(vm, NULL);
 
 	/* Export the shared variables to the guest. */
@@ -198,6 +212,17 @@ void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract)
 	sync_global_to_guest(vm, perf_test_args);
 }
 
+uint64_t __weak perf_test_nested_pages(int nr_vcpus)
+{
+	return 0;
+}
+
+void __weak perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus)
+{
+	pr_info("%s() not support on this architecture, skipping.\n", __func__);
+	exit(KSFT_SKIP);
+}
+
 static void *vcpu_thread_main(void *data)
 {
 	struct vcpu_thread *vcpu = data;
tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c new file +112 -0

112 lines not on this page · raw message

tools/testing/selftests/kvm/lib/x86_64/vmx.c +15 -0
index 5bf169179455..b77a01d0a271 100644
@@ -203,6 +203,11 @@ static bool ept_vpid_cap_supported(uint64_t mask)
 	return rdmsr(MSR_IA32_VMX_EPT_VPID_CAP) & mask;
 }
 
+bool ept_1g_pages_supported(void)
+{
+	return ept_vpid_cap_supported(VMX_EPT_VPID_CAP_1G_PAGES);
+}
+
 /*
  * Initialize the control fields to the most basic settings possible.
  */
@@ -439,6 +444,9 @@ void __nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
 	TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
 		    "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
 
+	TEST_ASSERT((nested_paddr >> 48) == 0,
+		    "Nested physical address 0x%lx requires 5-level paging",
+		    nested_paddr);
 	TEST_ASSERT((nested_paddr % page_size) == 0,
 		    "Nested physical address not on page boundary,\n"
 		    "  nested_paddr: 0x%lx page_size: 0x%lx",
@@ -547,6 +555,13 @@ void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm,
 	}
 }
 
+/* Identity map a region with 1GiB Pages. */
+void nested_identity_map_1g(struct vmx_pages *vmx, struct kvm_vm *vm,
+			    uint64_t addr, uint64_t size)
+{
+	__nested_map(vmx, vm, addr, addr, size, PG_LEVEL_1G);
+}
+
 void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
 		  uint32_t eptp_memslot)
 {
Signature · 1 line
2.36.1.124.g0e6072fb45-goog