From 7c4de881f7eba40088241f1c3ff5ca28c4e7fa48 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Mon, 15 Nov 2021 16:50:22 +0000
Subject: KVM: selftests: Add event channel upcall support to xen_shinfo_test

When I first looked at this, there was no support for guest exception
handling in the KVM selftests. In fact it was merged into 5.10 before
the Xen support got merged in 5.11, and I could have used it from the
start.

Hook it up now, to exercise the Xen upcall delivery. I'm about to make
things a bit more interesting by handling the full 2level event channel
stuff in-kernel on top of the basic vector injection that we already
have, and I'll want to build more tests on top.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <20211115165030.7422-3-dwmw2@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../testing/selftests/kvm/x86_64/xen_shinfo_test.c | 75 +++++++++++++++++++---
 1 file changed, 66 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index eda0d2a51224..a0699f00b3d6 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -24,8 +24,12 @@
 
 #define PVTIME_ADDR	(SHINFO_REGION_GPA + PAGE_SIZE)
 #define RUNSTATE_ADDR	(SHINFO_REGION_GPA + PAGE_SIZE + 0x20)
+#define VCPU_INFO_ADDR	(SHINFO_REGION_GPA + 0x40)
 
 #define RUNSTATE_VADDR	(SHINFO_REGION_GVA + PAGE_SIZE + 0x20)
+#define VCPU_INFO_VADDR	(SHINFO_REGION_GVA + 0x40)
+
+#define EVTCHN_VECTOR	0x10
 
 static struct kvm_vm *vm;
 
@@ -56,15 +60,44 @@ struct vcpu_runstate_info {
     uint64_t time[4];
 };
 
+struct arch_vcpu_info {
+    unsigned long cr2;
+    unsigned long pad; /* sizeof(vcpu_info_t) == 64 */
+};
+
+struct vcpu_info {
+        uint8_t evtchn_upcall_pending;
+        uint8_t evtchn_upcall_mask;
+        unsigned long evtchn_pending_sel;
+        struct arch_vcpu_info arch;
+        struct pvclock_vcpu_time_info time;
+}; /* 64 bytes (x86) */
+
 #define RUNSTATE_running  0
 #define RUNSTATE_runnable 1
 #define RUNSTATE_blocked  2
 #define RUNSTATE_offline  3
 
+static void evtchn_handler(struct ex_regs *regs)
+{
+	struct vcpu_info *vi = (void *)VCPU_INFO_VADDR;
+	vi->evtchn_upcall_pending = 0;
+
+	GUEST_SYNC(0x20);
+}
+
 static void guest_code(void)
 {
 	struct vcpu_runstate_info *rs = (void *)RUNSTATE_VADDR;
 
+	__asm__ __volatile__(
+		"sti\n"
+		"nop\n"
+	);
+
+	/* Trigger an interrupt injection */
+	GUEST_SYNC(0);
+
 	/* Test having the host set runstates manually */
 	GUEST_SYNC(RUNSTATE_runnable);
 	GUEST_ASSERT(rs->time[RUNSTATE_runnable] != 0);
@@ -153,7 +186,7 @@ int main(int argc, char *argv[])
 
 	struct kvm_xen_vcpu_attr vi = {
 		.type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO,
-		.u.gpa = SHINFO_REGION_GPA + 0x40,
+		.u.gpa = VCPU_INFO_ADDR,
 	};
 	vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &vi);
 
@@ -163,6 +196,16 @@ int main(int argc, char *argv[])
 	};
 	vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &pvclock);
 
+	struct kvm_xen_hvm_attr vec = {
+		.type = KVM_XEN_ATTR_TYPE_UPCALL_VECTOR,
+		.u.vector = EVTCHN_VECTOR,
+	};
+	vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &vec);
+
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(vm, VCPU_ID);
+	vm_install_exception_handler(vm, EVTCHN_VECTOR, evtchn_handler);
+
 	if (do_runstate_tests) {
 		struct kvm_xen_vcpu_attr st = {
 			.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR,
@@ -171,9 +214,14 @@ int main(int argc, char *argv[])
 		vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &st);
 	}
 
+	struct vcpu_info *vinfo = addr_gpa2hva(vm, VCPU_INFO_VADDR);
+	vinfo->evtchn_upcall_pending = 0;
+
 	struct vcpu_runstate_info *rs = addr_gpa2hva(vm, RUNSTATE_ADDR);
 	rs->state = 0x5a;
 
+	bool evtchn_irq_expected = false;
+
 	for (;;) {
 		volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
 		struct ucall uc;
@@ -193,16 +241,21 @@ int main(int argc, char *argv[])
 			struct kvm_xen_vcpu_attr rst;
 			long rundelay;
 
-			/* If no runstate support, bail out early */
-			if (!do_runstate_tests)
-				goto done;
-
-			TEST_ASSERT(rs->state_entry_time == rs->time[0] +
-				    rs->time[1] + rs->time[2] + rs->time[3],
-				    "runstate times don't add up");
+			if (do_runstate_tests)
+				TEST_ASSERT(rs->state_entry_time == rs->time[0] +
+					    rs->time[1] + rs->time[2] + rs->time[3],
+					    "runstate times don't add up");
 
 			switch (uc.args[1]) {
-			case RUNSTATE_running...RUNSTATE_offline:
+			case 0:
+				evtchn_irq_expected = true;
+				vinfo->evtchn_upcall_pending = 1;
+				break;
+
+			case RUNSTATE_runnable...RUNSTATE_offline:
+				TEST_ASSERT(!evtchn_irq_expected, "Event channel IRQ not seen");
+				if (!do_runstate_tests)
+					goto done;
 				rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT;
 				rst.u.runstate.state = uc.args[1];
 				vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst);
@@ -236,6 +289,10 @@ int main(int argc, char *argv[])
 					sched_yield();
 				} while (get_run_delay() < rundelay);
 				break;
+			case 0x20:
+				TEST_ASSERT(evtchn_irq_expected, "Unexpected event channel IRQ");
+				evtchn_irq_expected = false;
+				break;
 			}
 			break;
 		}
-- 
cgit v1.2.3-59-g8ed1b


From 531ca3d6d518f520f67a71e270ac733901896d8f Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:02:59 +0000
Subject: KVM: selftests: Explicitly state indicies for vm_guest_mode_params
 array

Explicitly state the indices when populating vm_guest_mode_params to
make it marginally easier to visualize what's going on.

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
[Added indices for new guest modes.]
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111000310.1435032-2-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/lib/kvm_util.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 041004c0fda7..b624c24290dd 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -187,15 +187,15 @@ const char *vm_guest_mode_string(uint32_t i)
 }
 
 const struct vm_guest_mode_params vm_guest_mode_params[] = {
-	{ 52, 48,  0x1000, 12 },
-	{ 52, 48, 0x10000, 16 },
-	{ 48, 48,  0x1000, 12 },
-	{ 48, 48, 0x10000, 16 },
-	{ 40, 48,  0x1000, 12 },
-	{ 40, 48, 0x10000, 16 },
-	{  0,  0,  0x1000, 12 },
-	{ 47, 64,  0x1000, 12 },
-	{ 44, 64,  0x1000, 12 },
+	[VM_MODE_P52V48_4K]	= { 52, 48,  0x1000, 12 },
+	[VM_MODE_P52V48_64K]	= { 52, 48, 0x10000, 16 },
+	[VM_MODE_P48V48_4K]	= { 48, 48,  0x1000, 12 },
+	[VM_MODE_P48V48_64K]	= { 48, 48, 0x10000, 16 },
+	[VM_MODE_P40V48_4K]	= { 40, 48,  0x1000, 12 },
+	[VM_MODE_P40V48_64K]	= { 40, 48, 0x10000, 16 },
+	[VM_MODE_PXXV48_4K]	= {  0,  0,  0x1000, 12 },
+	[VM_MODE_P47V64_4K]	= { 47, 64,  0x1000, 12 },
+	[VM_MODE_P44V64_4K]	= { 44, 64,  0x1000, 12 },
 };
 _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
 	       "Missing new mode params?");
-- 
cgit v1.2.3-59-g8ed1b


From c071ff41e1502990a0902c7c3fcf72a462e46330 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:00 +0000
Subject: KVM: selftests: Expose align() helpers to tests

Refactor align() to work with non-pointers and split into separate
helpers for aligning up vs. down. Add align_ptr_up() for use with
pointers. Expose all helpers so that they can be used by tests and/or
other utilities.  The align_down() helper in particular will be used to
ensure gpa alignment for hugepages.

No functional change intended.

[Added sepearate up/down helpers and replaced open-coded alignment
 bit math throughout the KVM selftests.]

Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Message-Id: <20211111000310.1435032-3-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/dirty_log_test.c      |  6 +++---
 tools/testing/selftests/kvm/include/test_util.h   | 25 +++++++++++++++++++++++
 tools/testing/selftests/kvm/kvm_page_table_test.c |  2 +-
 tools/testing/selftests/kvm/lib/elf.c             |  3 +--
 tools/testing/selftests/kvm/lib/kvm_util.c        | 13 ++----------
 tools/testing/selftests/kvm/lib/perf_test_util.c  |  4 ++--
 6 files changed, 34 insertions(+), 19 deletions(-)

diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 792c60e1b17d..3fcd89e195c7 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -115,7 +115,7 @@ static void guest_code(void)
 			addr = guest_test_virt_mem;
 			addr += (READ_ONCE(random_array[i]) % guest_num_pages)
 				* guest_page_size;
-			addr &= ~(host_page_size - 1);
+			addr = align_down(addr, host_page_size);
 			*(uint64_t *)addr = READ_ONCE(iteration);
 		}
 
@@ -737,14 +737,14 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	if (!p->phys_offset) {
 		guest_test_phys_mem = (vm_get_max_gfn(vm) -
 				       guest_num_pages) * guest_page_size;
-		guest_test_phys_mem &= ~(host_page_size - 1);
+		guest_test_phys_mem = align_down(guest_test_phys_mem, host_page_size);
 	} else {
 		guest_test_phys_mem = p->phys_offset;
 	}
 
 #ifdef __s390x__
 	/* Align to 1M (segment size) */
-	guest_test_phys_mem &= ~((1 << 20) - 1);
+	guest_test_phys_mem = align_down(guest_test_phys_mem, 1 << 20);
 #endif
 
 	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index f8fddc84c0d3..78c06310cc0e 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -117,4 +117,29 @@ static inline bool backing_src_is_shared(enum vm_mem_backing_src_type t)
 	return vm_mem_backing_src_alias(t)->flag & MAP_SHARED;
 }
 
+/* Aligns x up to the next multiple of size. Size must be a power of 2. */
+static inline uint64_t align_up(uint64_t x, uint64_t size)
+{
+	uint64_t mask = size - 1;
+
+	TEST_ASSERT(size != 0 && !(size & (size - 1)),
+		    "size not a power of 2: %lu", size);
+	return ((x + mask) & ~mask);
+}
+
+static inline uint64_t align_down(uint64_t x, uint64_t size)
+{
+	uint64_t x_aligned_up = align_up(x, size);
+
+	if (x == x_aligned_up)
+		return x;
+	else
+		return x_aligned_up - size;
+}
+
+static inline void *align_ptr_up(void *x, size_t size)
+{
+	return (void *)align_up((unsigned long)x, size);
+}
+
 #endif /* SELFTEST_KVM_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c
index 36407cb0ec85..3836322add00 100644
--- a/tools/testing/selftests/kvm/kvm_page_table_test.c
+++ b/tools/testing/selftests/kvm/kvm_page_table_test.c
@@ -280,7 +280,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg)
 #ifdef __s390x__
 	alignment = max(0x100000, alignment);
 #endif
-	guest_test_phys_mem &= ~(alignment - 1);
+	guest_test_phys_mem = align_down(guest_test_virt_mem, alignment);
 
 	/* Set up the shared data structure test_args */
 	test_args.vm = vm;
diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c
index eac44f5d0db0..13e8e3dcf984 100644
--- a/tools/testing/selftests/kvm/lib/elf.c
+++ b/tools/testing/selftests/kvm/lib/elf.c
@@ -157,8 +157,7 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename)
 			"memsize of 0,\n"
 			"  phdr index: %u p_memsz: 0x%" PRIx64,
 			n1, (uint64_t) phdr.p_memsz);
-		vm_vaddr_t seg_vstart = phdr.p_vaddr;
-		seg_vstart &= ~(vm_vaddr_t)(vm->page_size - 1);
+		vm_vaddr_t seg_vstart = align_down(phdr.p_vaddr, vm->page_size);
 		vm_vaddr_t seg_vend = phdr.p_vaddr + phdr.p_memsz - 1;
 		seg_vend |= vm->page_size - 1;
 		size_t seg_size = seg_vend - seg_vstart + 1;
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index b624c24290dd..63375118d48f 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -22,15 +22,6 @@
 
 static int vcpu_mmap_sz(void);
 
-/* Aligns x up to the next multiple of size. Size must be a power of 2. */
-static void *align(void *x, size_t size)
-{
-	size_t mask = size - 1;
-	TEST_ASSERT(size != 0 && !(size & (size - 1)),
-		    "size not a power of 2: %lu", size);
-	return (void *) (((size_t) x + mask) & ~mask);
-}
-
 /*
  * Open KVM_DEV_PATH if available, otherwise exit the entire program.
  *
@@ -911,7 +902,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 		    region->mmap_start, errno);
 
 	/* Align host address */
-	region->host_mem = align(region->mmap_start, alignment);
+	region->host_mem = align_ptr_up(region->mmap_start, alignment);
 
 	/* As needed perform madvise */
 	if ((src_type == VM_MEM_SRC_ANONYMOUS ||
@@ -954,7 +945,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 			    "mmap of alias failed, errno: %i", errno);
 
 		/* Align host alias address */
-		region->host_alias = align(region->mmap_alias, alignment);
+		region->host_alias = align_ptr_up(region->mmap_alias, alignment);
 	}
 }
 
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index 0ef80dbdc116..6b8d5020dc54 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -92,10 +92,10 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 
 	guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
 			      perf_test_args.guest_page_size;
-	guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1);
+	guest_test_phys_mem = align_down(guest_test_phys_mem, perf_test_args.host_page_size);
 #ifdef __s390x__
 	/* Align to 1M (segment size) */
-	guest_test_phys_mem &= ~((1 << 20) - 1);
+	guest_test_phys_mem = align_down(guest_test_phys_mem, 1 << 20);
 #endif
 	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
 
-- 
cgit v1.2.3-59-g8ed1b


From f4870ef3e15ab889a689f99a579fe0fe7c53a960 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:01 +0000
Subject: KVM: selftests: Assert mmap HVA is aligned when using HugeTLB

Manually padding and aligning the mmap region is only needed when using
THP. When using HugeTLB, mmap will always return an address aligned to
the HugeTLB page size. Add a comment to clarify this and assert the mmap
behavior for HugeTLB.

[Removed requirement that HugeTLB mmaps must be padded per Yanan's
 feedback and added assertion that mmap returns aligned addresses
 when using HugeTLB.]

Cc: Ben Gardon <bgardon@google.com>
Cc: Yanan Wang <wangyanan55@huawei.com>
Cc: Andrew Jones <drjones@redhat.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Aaron Lewis <aaronlewis@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111000310.1435032-4-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/test_util.h |  1 +
 tools/testing/selftests/kvm/lib/kvm_util.c      | 11 +++++++++++
 tools/testing/selftests/kvm/lib/test_util.c     |  5 +++++
 3 files changed, 17 insertions(+)

diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index 78c06310cc0e..99e0dcdc923f 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -104,6 +104,7 @@ size_t get_trans_hugepagesz(void);
 size_t get_def_hugetlb_pagesz(void);
 const struct vm_mem_backing_src_alias *vm_mem_backing_src_alias(uint32_t i);
 size_t get_backing_src_pagesz(uint32_t i);
+bool is_backing_src_hugetlb(uint32_t i);
 void backing_src_help(const char *flag);
 enum vm_mem_backing_src_type parse_backing_src_type(const char *type_name);
 long get_run_delay(void);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 63375118d48f..07f37456bba0 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -866,6 +866,12 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	alignment = 1;
 #endif
 
+	/*
+	 * When using THP mmap is not guaranteed to returned a hugepage aligned
+	 * address so we have to pad the mmap. Padding is not needed for HugeTLB
+	 * because mmap will always return an address aligned to the HugeTLB
+	 * page size.
+	 */
 	if (src_type == VM_MEM_SRC_ANONYMOUS_THP)
 		alignment = max(backing_src_pagesz, alignment);
 
@@ -901,6 +907,11 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 		    "test_malloc failed, mmap_start: %p errno: %i",
 		    region->mmap_start, errno);
 
+	TEST_ASSERT(!is_backing_src_hugetlb(src_type) ||
+		    region->mmap_start == align_ptr_up(region->mmap_start, backing_src_pagesz),
+		    "mmap_start %p is not aligned to HugeTLB page size 0x%lx",
+		    region->mmap_start, backing_src_pagesz);
+
 	/* Align host address */
 	region->host_mem = align_ptr_up(region->mmap_start, alignment);
 
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index b72429108993..6d23878bbfe1 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -283,6 +283,11 @@ size_t get_backing_src_pagesz(uint32_t i)
 	}
 }
 
+bool is_backing_src_hugetlb(uint32_t i)
+{
+	return !!(vm_mem_backing_src_alias(i)->flag & MAP_HUGETLB);
+}
+
 static void print_available_backing_src_types(const char *prefix)
 {
 	int i;
-- 
cgit v1.2.3-59-g8ed1b


From 69cdcfa6f321da2cc1dd2e62fa4a9ee256299b18 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:02 +0000
Subject: KVM: selftests: Require GPA to be aligned when backed by hugepages

Assert that the GPA for a memslot backed by a hugepage is aligned to
the hugepage size and fix perf_test_util accordingly.  Lack of GPA
alignment prevents KVM from backing the guest with hugepages, e.g. x86's
write-protection of hugepages when dirty logging is activated is
otherwise not exercised.

Add a comment explaining that guest_page_size is for non-huge pages to
try and avoid confusion about what it actually tracks.

Cc: Ben Gardon <bgardon@google.com>
Cc: Yanan Wang <wangyanan55@huawei.com>
Cc: Andrew Jones <drjones@redhat.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Aaron Lewis <aaronlewis@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
[Used get_backing_src_pagesz() to determine alignment dynamically.]
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111000310.1435032-5-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/lib/kvm_util.c       | 2 ++
 tools/testing/selftests/kvm/lib/perf_test_util.c | 7 ++++++-
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 07f37456bba0..1f6a01c33dce 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -875,6 +875,8 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 	if (src_type == VM_MEM_SRC_ANONYMOUS_THP)
 		alignment = max(backing_src_pagesz, alignment);
 
+	ASSERT_EQ(guest_paddr, align_up(guest_paddr, backing_src_pagesz));
+
 	/* Add enough memory to align up if necessary */
 	if (alignment > 1)
 		region->mmap_size += alignment;
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index 6b8d5020dc54..a015f267d945 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -55,11 +55,16 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 {
 	struct kvm_vm *vm;
 	uint64_t guest_num_pages;
+	uint64_t backing_src_pagesz = get_backing_src_pagesz(backing_src);
 	int i;
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
 	perf_test_args.host_page_size = getpagesize();
+	/*
+	 * Snapshot the non-huge page size.  This is used by the guest code to
+	 * access/dirty pages at the logging granularity.
+	 */
 	perf_test_args.guest_page_size = vm_guest_mode_params[mode].page_size;
 
 	guest_num_pages = vm_adjust_num_guest_pages(mode,
@@ -92,7 +97,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 
 	guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
 			      perf_test_args.guest_page_size;
-	guest_test_phys_mem = align_down(guest_test_phys_mem, perf_test_args.host_page_size);
+	guest_test_phys_mem = align_down(guest_test_phys_mem, backing_src_pagesz);
 #ifdef __s390x__
 	/* Align to 1M (segment size) */
 	guest_test_phys_mem = align_down(guest_test_phys_mem, 1 << 20);
-- 
cgit v1.2.3-59-g8ed1b


From b65e1051e489be4fe783cb14f1cd33235a0f9803 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:03 +0000
Subject: KVM: selftests: Use shorthand local var to access struct
 perf_tests_args

Use 'pta' as a local pointer to the global perf_tests_args in order to
shorten line lengths and make the code borderline readable.

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111000310.1435032-6-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/lib/perf_test_util.c | 35 +++++++++++++-----------
 1 file changed, 19 insertions(+), 16 deletions(-)

diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index a015f267d945..ccdc950c829e 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -24,7 +24,8 @@ static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
  */
 static void guest_code(uint32_t vcpu_id)
 {
-	struct perf_test_vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+	struct perf_test_args *pta = &perf_test_args;
+	struct perf_test_vcpu_args *vcpu_args = &pta->vcpu_args[vcpu_id];
 	uint64_t gva;
 	uint64_t pages;
 	int i;
@@ -37,9 +38,9 @@ static void guest_code(uint32_t vcpu_id)
 
 	while (true) {
 		for (i = 0; i < pages; i++) {
-			uint64_t addr = gva + (i * perf_test_args.guest_page_size);
+			uint64_t addr = gva + (i * pta->guest_page_size);
 
-			if (i % perf_test_args.wr_fract == 0)
+			if (i % pta->wr_fract == 0)
 				*(uint64_t *)addr = 0x0123456789ABCDEF;
 			else
 				READ_ONCE(*(uint64_t *)addr);
@@ -53,6 +54,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 				   uint64_t vcpu_memory_bytes, int slots,
 				   enum vm_mem_backing_src_type backing_src)
 {
+	struct perf_test_args *pta = &perf_test_args;
 	struct kvm_vm *vm;
 	uint64_t guest_num_pages;
 	uint64_t backing_src_pagesz = get_backing_src_pagesz(backing_src);
@@ -60,29 +62,29 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
-	perf_test_args.host_page_size = getpagesize();
+	pta->host_page_size = getpagesize();
 	/*
 	 * Snapshot the non-huge page size.  This is used by the guest code to
 	 * access/dirty pages at the logging granularity.
 	 */
-	perf_test_args.guest_page_size = vm_guest_mode_params[mode].page_size;
+	pta->guest_page_size = vm_guest_mode_params[mode].page_size;
 
 	guest_num_pages = vm_adjust_num_guest_pages(mode,
-				(vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size);
+				(vcpus * vcpu_memory_bytes) / pta->guest_page_size);
 
-	TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0,
+	TEST_ASSERT(vcpu_memory_bytes % pta->host_page_size == 0,
 		    "Guest memory size is not host page size aligned.");
-	TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0,
+	TEST_ASSERT(vcpu_memory_bytes % pta->guest_page_size == 0,
 		    "Guest memory size is not guest page size aligned.");
 	TEST_ASSERT(guest_num_pages % slots == 0,
 		    "Guest memory cannot be evenly divided into %d slots.",
 		    slots);
 
 	vm = vm_create_with_vcpus(mode, vcpus, DEFAULT_GUEST_PHY_PAGES,
-				  (vcpus * vcpu_memory_bytes) / perf_test_args.guest_page_size,
+				  (vcpus * vcpu_memory_bytes) / pta->guest_page_size,
 				  0, guest_code, NULL);
 
-	perf_test_args.vm = vm;
+	pta->vm = vm;
 
 	/*
 	 * If there should be more memory in the guest test region than there
@@ -96,7 +98,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 		    vcpu_memory_bytes);
 
 	guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
-			      perf_test_args.guest_page_size;
+			      pta->guest_page_size;
 	guest_test_phys_mem = align_down(guest_test_phys_mem, backing_src_pagesz);
 #ifdef __s390x__
 	/* Align to 1M (segment size) */
@@ -108,7 +110,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 	for (i = 0; i < slots; i++) {
 		uint64_t region_pages = guest_num_pages / slots;
 		vm_paddr_t region_start = guest_test_phys_mem +
-			region_pages * perf_test_args.guest_page_size * i;
+			region_pages * pta->guest_page_size * i;
 
 		vm_userspace_mem_region_add(vm, backing_src, region_start,
 					    PERF_TEST_MEM_SLOT_INDEX + i,
@@ -133,25 +135,26 @@ void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
 			   uint64_t vcpu_memory_bytes,
 			   bool partition_vcpu_memory_access)
 {
+	struct perf_test_args *pta = &perf_test_args;
 	vm_paddr_t vcpu_gpa;
 	struct perf_test_vcpu_args *vcpu_args;
 	int vcpu_id;
 
 	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
-		vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+		vcpu_args = &pta->vcpu_args[vcpu_id];
 
 		vcpu_args->vcpu_id = vcpu_id;
 		if (partition_vcpu_memory_access) {
 			vcpu_args->gva = guest_test_virt_mem +
 					 (vcpu_id * vcpu_memory_bytes);
 			vcpu_args->pages = vcpu_memory_bytes /
-					   perf_test_args.guest_page_size;
+					   pta->guest_page_size;
 			vcpu_gpa = guest_test_phys_mem +
 				   (vcpu_id * vcpu_memory_bytes);
 		} else {
 			vcpu_args->gva = guest_test_virt_mem;
 			vcpu_args->pages = (vcpus * vcpu_memory_bytes) /
-					   perf_test_args.guest_page_size;
+					   pta->guest_page_size;
 			vcpu_gpa = guest_test_phys_mem;
 		}
 
@@ -159,6 +162,6 @@ void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
 
 		pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
 			 vcpu_id, vcpu_gpa, vcpu_gpa +
-			 (vcpu_args->pages * perf_test_args.guest_page_size));
+			 (vcpu_args->pages * pta->guest_page_size));
 	}
 }
-- 
cgit v1.2.3-59-g8ed1b


From 613d61182fffca6b36ea0df1e44927ccf45b1e9b Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:04 +0000
Subject: KVM: selftests: Capture per-vCPU GPA in perf_test_vcpu_args

Capture the per-vCPU GPA in perf_test_vcpu_args so that tests can get
the GPA without having to calculate the GPA on their own.

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111000310.1435032-7-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/perf_test_util.h | 1 +
 tools/testing/selftests/kvm/lib/perf_test_util.c     | 9 ++++-----
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index df9f1a3a3ffb..20aec72fe7b8 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -18,6 +18,7 @@
 #define PERF_TEST_MEM_SLOT_INDEX	1
 
 struct perf_test_vcpu_args {
+	uint64_t gpa;
 	uint64_t gva;
 	uint64_t pages;
 
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index ccdc950c829e..d9c6bcb7964d 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -136,7 +136,6 @@ void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
 			   bool partition_vcpu_memory_access)
 {
 	struct perf_test_args *pta = &perf_test_args;
-	vm_paddr_t vcpu_gpa;
 	struct perf_test_vcpu_args *vcpu_args;
 	int vcpu_id;
 
@@ -149,19 +148,19 @@ void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
 					 (vcpu_id * vcpu_memory_bytes);
 			vcpu_args->pages = vcpu_memory_bytes /
 					   pta->guest_page_size;
-			vcpu_gpa = guest_test_phys_mem +
-				   (vcpu_id * vcpu_memory_bytes);
+			vcpu_args->gpa = guest_test_phys_mem +
+					 (vcpu_id * vcpu_memory_bytes);
 		} else {
 			vcpu_args->gva = guest_test_virt_mem;
 			vcpu_args->pages = (vcpus * vcpu_memory_bytes) /
 					   pta->guest_page_size;
-			vcpu_gpa = guest_test_phys_mem;
+			vcpu_args->gpa = guest_test_phys_mem;
 		}
 
 		vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
 
 		pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
-			 vcpu_id, vcpu_gpa, vcpu_gpa +
+			 vcpu_id, vcpu_args->gpa, vcpu_args->gpa +
 			 (vcpu_args->pages * pta->guest_page_size));
 	}
 }
-- 
cgit v1.2.3-59-g8ed1b


From 92e34c9974f55519bc0c3386221aadf387162ea6 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:05 +0000
Subject: KVM: selftests: Use perf util's per-vCPU GPA/pages in demand paging
 test

Grab the per-vCPU GPA and number of pages from perf_util in the demand
paging test instead of duplicating perf_util's calculations.

Note, this may or may not result in a functional change.  It's not clear
that the test's calculations are guaranteed to yield the same value as
perf_util, e.g. if guest_percpu_mem_size != vcpu_args->pages.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111000310.1435032-8-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/demand_paging_test.c | 21 +++++----------------
 1 file changed, 5 insertions(+), 16 deletions(-)

diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 1510b21e6306..3c729a0a1ab1 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -322,26 +322,15 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd");
 
 		for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
-			vm_paddr_t vcpu_gpa;
+			struct perf_test_vcpu_args *vcpu_args;
 			void *vcpu_hva;
 			void *vcpu_alias;
-			uint64_t vcpu_mem_size;
 
-
-			if (p->partition_vcpu_memory_access) {
-				vcpu_gpa = guest_test_phys_mem +
-					   (vcpu_id * guest_percpu_mem_size);
-				vcpu_mem_size = guest_percpu_mem_size;
-			} else {
-				vcpu_gpa = guest_test_phys_mem;
-				vcpu_mem_size = guest_percpu_mem_size * nr_vcpus;
-			}
-			PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n",
-				       vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_mem_size);
+			vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
 
 			/* Cache the host addresses of the region */
-			vcpu_hva = addr_gpa2hva(vm, vcpu_gpa);
-			vcpu_alias = addr_gpa2alias(vm, vcpu_gpa);
+			vcpu_hva = addr_gpa2hva(vm, vcpu_args->gpa);
+			vcpu_alias = addr_gpa2alias(vm, vcpu_args->gpa);
 
 			/*
 			 * Set up user fault fd to handle demand paging
@@ -355,7 +344,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 					    pipefds[vcpu_id * 2], p->uffd_mode,
 					    p->uffd_delay, &uffd_args[vcpu_id],
 					    vcpu_hva, vcpu_alias,
-					    vcpu_mem_size);
+					    vcpu_args->pages * perf_test_args.guest_page_size);
 		}
 	}
 
-- 
cgit v1.2.3-59-g8ed1b


From b91b637f4a595c5be435e215f78b1a3bd8c252b3 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:06 +0000
Subject: KVM: selftests: Move per-VM GPA into perf_test_args

Move the per-VM GPA into perf_test_args instead of storing it as a
separate global variable.  It's not obvious that guest_test_phys_mem
holds a GPA, nor that it's connected/coupled with per_vcpu->gpa.

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111000310.1435032-9-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../testing/selftests/kvm/include/perf_test_util.h  |  8 +-------
 tools/testing/selftests/kvm/lib/perf_test_util.c    | 21 ++++++++-------------
 .../kvm/memslot_modification_stress_test.c          |  2 +-
 3 files changed, 10 insertions(+), 21 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index 20aec72fe7b8..d7cde1ab2a85 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -29,6 +29,7 @@ struct perf_test_vcpu_args {
 struct perf_test_args {
 	struct kvm_vm *vm;
 	uint64_t host_page_size;
+	uint64_t gpa;
 	uint64_t guest_page_size;
 	int wr_fract;
 
@@ -37,13 +38,6 @@ struct perf_test_args {
 
 extern struct perf_test_args perf_test_args;
 
-/*
- * Guest physical memory offset of the testing memory slot.
- * This will be set to the topmost valid physical address minus
- * the test memory size.
- */
-extern uint64_t guest_test_phys_mem;
-
 struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 				   uint64_t vcpu_memory_bytes, int slots,
 				   enum vm_mem_backing_src_type backing_src);
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index d9c6bcb7964d..0fc2d834c1c7 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -10,8 +10,6 @@
 
 struct perf_test_args perf_test_args;
 
-uint64_t guest_test_phys_mem;
-
 /*
  * Guest virtual memory offset of the testing memory slot.
  * Must not conflict with identity mapped test code.
@@ -97,20 +95,18 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 		    guest_num_pages, vm_get_max_gfn(vm), vcpus,
 		    vcpu_memory_bytes);
 
-	guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
-			      pta->guest_page_size;
-	guest_test_phys_mem = align_down(guest_test_phys_mem, backing_src_pagesz);
+	pta->gpa = (vm_get_max_gfn(vm) - guest_num_pages) * pta->guest_page_size;
+	pta->gpa = align_down(pta->gpa, backing_src_pagesz);
 #ifdef __s390x__
 	/* Align to 1M (segment size) */
-	guest_test_phys_mem = align_down(guest_test_phys_mem, 1 << 20);
+	pta->gpa = align_down(pta->gpa, 1 << 20);
 #endif
-	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
+	pr_info("guest physical test memory offset: 0x%lx\n", pta->gpa);
 
 	/* Add extra memory slots for testing */
 	for (i = 0; i < slots; i++) {
 		uint64_t region_pages = guest_num_pages / slots;
-		vm_paddr_t region_start = guest_test_phys_mem +
-			region_pages * pta->guest_page_size * i;
+		vm_paddr_t region_start = pta->gpa + region_pages * pta->guest_page_size * i;
 
 		vm_userspace_mem_region_add(vm, backing_src, region_start,
 					    PERF_TEST_MEM_SLOT_INDEX + i,
@@ -118,7 +114,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 	}
 
 	/* Do mapping for the demand paging memory slot */
-	virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages);
+	virt_map(vm, guest_test_virt_mem, pta->gpa, guest_num_pages);
 
 	ucall_init(vm, NULL);
 
@@ -148,13 +144,12 @@ void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
 					 (vcpu_id * vcpu_memory_bytes);
 			vcpu_args->pages = vcpu_memory_bytes /
 					   pta->guest_page_size;
-			vcpu_args->gpa = guest_test_phys_mem +
-					 (vcpu_id * vcpu_memory_bytes);
+			vcpu_args->gpa = pta->gpa + (vcpu_id * vcpu_memory_bytes);
 		} else {
 			vcpu_args->gva = guest_test_virt_mem;
 			vcpu_args->pages = (vcpus * vcpu_memory_bytes) /
 					   pta->guest_page_size;
-			vcpu_args->gpa = guest_test_phys_mem;
+			vcpu_args->gpa = pta->gpa;
 		}
 
 		vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
index 4cfcafea9f5a..d105180d5e8c 100644
--- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c
+++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
@@ -80,7 +80,7 @@ static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay,
 	 * Add the dummy memslot just below the perf_test_util memslot, which is
 	 * at the top of the guest physical address space.
 	 */
-	gpa = guest_test_phys_mem - pages * vm_get_page_size(vm);
+	gpa = perf_test_args.gpa - pages * vm_get_page_size(vm);
 
 	for (i = 0; i < nr_modifications; i++) {
 		usleep(delay);
-- 
cgit v1.2.3-59-g8ed1b


From a5ac0fd1b90ae811ba51da6a9928633bddefb792 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:07 +0000
Subject: KVM: selftests: Remove perf_test_args.host_page_size

Remove perf_test_args.host_page_size and instead use getpagesize() so
that it's somewhat obvious that, for tests that care about the host page
size, they care about the system page size, not the hardware page size,
e.g. that the logic is unchanged if hugepages are in play.

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111000310.1435032-10-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/include/perf_test_util.h | 1 -
 tools/testing/selftests/kvm/lib/perf_test_util.c     | 3 +--
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index d7cde1ab2a85..9348580dc5be 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -28,7 +28,6 @@ struct perf_test_vcpu_args {
 
 struct perf_test_args {
 	struct kvm_vm *vm;
-	uint64_t host_page_size;
 	uint64_t gpa;
 	uint64_t guest_page_size;
 	int wr_fract;
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index 0fc2d834c1c7..a0aded8cfce3 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -60,7 +60,6 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
-	pta->host_page_size = getpagesize();
 	/*
 	 * Snapshot the non-huge page size.  This is used by the guest code to
 	 * access/dirty pages at the logging granularity.
@@ -70,7 +69,7 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 	guest_num_pages = vm_adjust_num_guest_pages(mode,
 				(vcpus * vcpu_memory_bytes) / pta->guest_page_size);
 
-	TEST_ASSERT(vcpu_memory_bytes % pta->host_page_size == 0,
+	TEST_ASSERT(vcpu_memory_bytes % getpagesize() == 0,
 		    "Guest memory size is not host page size aligned.");
 	TEST_ASSERT(vcpu_memory_bytes % pta->guest_page_size == 0,
 		    "Guest memory size is not guest page size aligned.");
-- 
cgit v1.2.3-59-g8ed1b


From f5e8fe2a92e4923b63d1edd6ed53d9856b6515ce Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:08 +0000
Subject: KVM: selftests: Create VM with adjusted number of guest pages for
 perf tests

Use the already computed guest_num_pages when creating the so called
extra VM pages for a perf test, and add a comment explaining why the
pages are allocated as extra pages.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111000310.1435032-11-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/lib/perf_test_util.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index a0aded8cfce3..b3154b5b0cfd 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -77,9 +77,13 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 		    "Guest memory cannot be evenly divided into %d slots.",
 		    slots);
 
+	/*
+	 * 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,
-				  (vcpus * vcpu_memory_bytes) / pta->guest_page_size,
-				  0, guest_code, NULL);
+				  guest_num_pages, 0, guest_code, NULL);
 
 	pta->vm = vm;
 
-- 
cgit v1.2.3-59-g8ed1b


From cf1d59300ab27af6a2e96b4882fe3d9a72b32b15 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:09 +0000
Subject: KVM: selftests: Fill per-vCPU struct during "perf_test" VM creation

Fill the per-vCPU args when creating the perf_test VM instead of having
the caller do so.  This helps ensure that any adjustments to the number
of pages (and thus vcpu_memory_bytes) are reflected in the per-VM args.
Automatically filling the per-vCPU args will also allow a future patch
to do the sync to the guest during creation.

Signed-off-by: Sean Christopherson <seanjc@google.com>
[Updated access_tracking_perf_test as well.]
Signed-off-by: David Matlack <dmatlack@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Message-Id: <20211111000310.1435032-12-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../selftests/kvm/access_tracking_perf_test.c      |  5 +-
 tools/testing/selftests/kvm/demand_paging_test.c   |  5 +-
 tools/testing/selftests/kvm/dirty_log_perf_test.c  |  6 +-
 .../testing/selftests/kvm/include/perf_test_util.h |  6 +-
 tools/testing/selftests/kvm/lib/perf_test_util.c   | 71 +++++++++++-----------
 .../kvm/memslot_modification_stress_test.c         |  6 +-
 6 files changed, 45 insertions(+), 54 deletions(-)

diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c
index 5d95113c7b7c..fdef6c906388 100644
--- a/tools/testing/selftests/kvm/access_tracking_perf_test.c
+++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c
@@ -332,10 +332,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	int vcpus = params->vcpus;
 
 	vm = perf_test_create_vm(mode, vcpus, params->vcpu_memory_bytes, 1,
-				 params->backing_src);
-
-	perf_test_setup_vcpus(vm, vcpus, params->vcpu_memory_bytes,
-			      !overlap_memory_access);
+				 params->backing_src, !overlap_memory_access);
 
 	vcpu_threads = create_vcpu_threads(vcpus);
 
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 3c729a0a1ab1..0fee44f5e5ae 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -293,7 +293,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	int r;
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
-				 p->src_type);
+				 p->src_type, p->partition_vcpu_memory_access);
 
 	perf_test_args.wr_fract = 1;
 
@@ -307,9 +307,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
 	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
 
-	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
-			      p->partition_vcpu_memory_access);
-
 	if (p->uffd_mode) {
 		uffd_handler_threads =
 			malloc(nr_vcpus * sizeof(*uffd_handler_threads));
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 7ffab5bd5ce5..62f9cc2a3146 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -186,7 +186,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	struct timespec clear_dirty_log_total = (struct timespec){0};
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size,
-				 p->slots, p->backing_src);
+				 p->slots, p->backing_src,
+				 p->partition_vcpu_memory_access);
 
 	perf_test_args.wr_fract = p->wr_fract;
 
@@ -206,9 +207,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
 	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
 
-	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
-			      p->partition_vcpu_memory_access);
-
 	sync_global_to_guest(vm, perf_test_args);
 
 	/* Start the iterations */
diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index 9348580dc5be..91804be1cf53 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -39,10 +39,8 @@ extern struct perf_test_args perf_test_args;
 
 struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 				   uint64_t vcpu_memory_bytes, int slots,
-				   enum vm_mem_backing_src_type backing_src);
+				   enum vm_mem_backing_src_type backing_src,
+				   bool partition_vcpu_memory_access);
 void perf_test_destroy_vm(struct kvm_vm *vm);
-void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
-			   uint64_t vcpu_memory_bytes,
-			   bool partition_vcpu_memory_access);
 
 #endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index b3154b5b0cfd..13c8bc22f4e1 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -48,9 +48,43 @@ static void guest_code(uint32_t vcpu_id)
 	}
 }
 
+void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
+			   uint64_t vcpu_memory_bytes,
+			   bool partition_vcpu_memory_access)
+{
+	struct perf_test_args *pta = &perf_test_args;
+	struct perf_test_vcpu_args *vcpu_args;
+	int vcpu_id;
+
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+		vcpu_args = &pta->vcpu_args[vcpu_id];
+
+		vcpu_args->vcpu_id = vcpu_id;
+		if (partition_vcpu_memory_access) {
+			vcpu_args->gva = guest_test_virt_mem +
+					 (vcpu_id * vcpu_memory_bytes);
+			vcpu_args->pages = vcpu_memory_bytes /
+					   pta->guest_page_size;
+			vcpu_args->gpa = pta->gpa + (vcpu_id * vcpu_memory_bytes);
+		} else {
+			vcpu_args->gva = guest_test_virt_mem;
+			vcpu_args->pages = (vcpus * vcpu_memory_bytes) /
+					   pta->guest_page_size;
+			vcpu_args->gpa = pta->gpa;
+		}
+
+		vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
+
+		pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
+			 vcpu_id, vcpu_args->gpa, vcpu_args->gpa +
+			 (vcpu_args->pages * pta->guest_page_size));
+	}
+}
+
 struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 				   uint64_t vcpu_memory_bytes, int slots,
-				   enum vm_mem_backing_src_type backing_src)
+				   enum vm_mem_backing_src_type backing_src,
+				   bool partition_vcpu_memory_access)
 {
 	struct perf_test_args *pta = &perf_test_args;
 	struct kvm_vm *vm;
@@ -119,6 +153,8 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 	/* Do mapping for the demand paging memory slot */
 	virt_map(vm, guest_test_virt_mem, pta->gpa, guest_num_pages);
 
+	perf_test_setup_vcpus(vm, vcpus, vcpu_memory_bytes, partition_vcpu_memory_access);
+
 	ucall_init(vm, NULL);
 
 	return vm;
@@ -129,36 +165,3 @@ void perf_test_destroy_vm(struct kvm_vm *vm)
 	ucall_uninit(vm);
 	kvm_vm_free(vm);
 }
-
-void perf_test_setup_vcpus(struct kvm_vm *vm, int vcpus,
-			   uint64_t vcpu_memory_bytes,
-			   bool partition_vcpu_memory_access)
-{
-	struct perf_test_args *pta = &perf_test_args;
-	struct perf_test_vcpu_args *vcpu_args;
-	int vcpu_id;
-
-	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
-		vcpu_args = &pta->vcpu_args[vcpu_id];
-
-		vcpu_args->vcpu_id = vcpu_id;
-		if (partition_vcpu_memory_access) {
-			vcpu_args->gva = guest_test_virt_mem +
-					 (vcpu_id * vcpu_memory_bytes);
-			vcpu_args->pages = vcpu_memory_bytes /
-					   pta->guest_page_size;
-			vcpu_args->gpa = pta->gpa + (vcpu_id * vcpu_memory_bytes);
-		} else {
-			vcpu_args->gva = guest_test_virt_mem;
-			vcpu_args->pages = (vcpus * vcpu_memory_bytes) /
-					   pta->guest_page_size;
-			vcpu_args->gpa = pta->gpa;
-		}
-
-		vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
-
-		pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
-			 vcpu_id, vcpu_args->gpa, vcpu_args->gpa +
-			 (vcpu_args->pages * pta->guest_page_size));
-	}
-}
diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
index d105180d5e8c..27af0bb8deb7 100644
--- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c
+++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
@@ -105,16 +105,14 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	int vcpu_id;
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
-				 VM_MEM_SRC_ANONYMOUS);
+				 VM_MEM_SRC_ANONYMOUS,
+				 p->partition_vcpu_memory_access);
 
 	perf_test_args.wr_fract = 1;
 
 	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
 	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
 
-	perf_test_setup_vcpus(vm, nr_vcpus, guest_percpu_mem_size,
-			      p->partition_vcpu_memory_access);
-
 	/* Export the shared variables to the guest */
 	sync_global_to_guest(vm, perf_test_args);
 
-- 
cgit v1.2.3-59-g8ed1b


From 13bbc70329c8df003e64c4fbea8678f9db0e75d5 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 11 Nov 2021 00:03:10 +0000
Subject: KVM: selftests: Sync perf_test_args to guest during VM creation

Copy perf_test_args to the guest during VM creation instead of relying on
the caller to do so at their leisure.  Ideally, tests wouldn't even be
able to modify perf_test_args, i.e. they would have no motivation to do
the sync, but enforcing that is arguably a net negative for readability.

No functional change intended.

[Set wr_fract=1 by default and add helper to override it since the new
 access_tracking_perf_test needs to set it dynamically.]

Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: David Matlack <dmatlack@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Message-Id: <20211111000310.1435032-13-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/access_tracking_perf_test.c      |  3 +--
 tools/testing/selftests/kvm/demand_paging_test.c             |  5 -----
 tools/testing/selftests/kvm/dirty_log_perf_test.c            |  4 +---
 tools/testing/selftests/kvm/include/perf_test_util.h         |  2 ++
 tools/testing/selftests/kvm/lib/perf_test_util.c             | 12 ++++++++++++
 .../testing/selftests/kvm/memslot_modification_stress_test.c |  5 -----
 6 files changed, 16 insertions(+), 15 deletions(-)

diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c
index fdef6c906388..5364a2ed7c68 100644
--- a/tools/testing/selftests/kvm/access_tracking_perf_test.c
+++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c
@@ -277,8 +277,7 @@ static void run_iteration(struct kvm_vm *vm, int vcpus, const char *description)
 static void access_memory(struct kvm_vm *vm, int vcpus, enum access_type access,
 			  const char *description)
 {
-	perf_test_args.wr_fract = (access == ACCESS_READ) ? INT_MAX : 1;
-	sync_global_to_guest(vm, perf_test_args);
+	perf_test_set_wr_fract(vm, (access == ACCESS_READ) ? INT_MAX : 1);
 	iteration_work = ITERATION_ACCESS_MEMORY;
 	run_iteration(vm, vcpus, description);
 }
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 0fee44f5e5ae..26f8fd8a57ec 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -295,8 +295,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
 				 p->src_type, p->partition_vcpu_memory_access);
 
-	perf_test_args.wr_fract = 1;
-
 	demand_paging_size = get_backing_src_pagesz(p->src_type);
 
 	guest_data_prototype = malloc(demand_paging_size);
@@ -345,9 +343,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		}
 	}
 
-	/* Export the shared variables to the guest */
-	sync_global_to_guest(vm, perf_test_args);
-
 	pr_info("Finished creating vCPUs and starting uffd threads\n");
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 62f9cc2a3146..583b4d95aa98 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -189,7 +189,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 				 p->slots, p->backing_src,
 				 p->partition_vcpu_memory_access);
 
-	perf_test_args.wr_fract = p->wr_fract;
+	perf_test_set_wr_fract(vm, p->wr_fract);
 
 	guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm);
 	guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
@@ -207,8 +207,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
 	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
 
-	sync_global_to_guest(vm, perf_test_args);
-
 	/* Start the iterations */
 	iteration = 0;
 	host_quit = false;
diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index 91804be1cf53..74e3622b3a6e 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -43,4 +43,6 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 				   bool partition_vcpu_memory_access);
 void perf_test_destroy_vm(struct kvm_vm *vm);
 
+void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract);
+
 #endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index 13c8bc22f4e1..77f9eb5667c9 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -94,6 +94,9 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
+	/* By default vCPUs will write to memory. */
+	pta->wr_fract = 1;
+
 	/*
 	 * Snapshot the non-huge page size.  This is used by the guest code to
 	 * access/dirty pages at the logging granularity.
@@ -157,6 +160,9 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int vcpus,
 
 	ucall_init(vm, NULL);
 
+	/* Export the shared variables to the guest. */
+	sync_global_to_guest(vm, perf_test_args);
+
 	return vm;
 }
 
@@ -165,3 +171,9 @@ void perf_test_destroy_vm(struct kvm_vm *vm)
 	ucall_uninit(vm);
 	kvm_vm_free(vm);
 }
+
+void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract)
+{
+	perf_test_args.wr_fract = wr_fract;
+	sync_global_to_guest(vm, perf_test_args);
+}
diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
index 27af0bb8deb7..df431d0da1ee 100644
--- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c
+++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
@@ -108,14 +108,9 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 				 VM_MEM_SRC_ANONYMOUS,
 				 p->partition_vcpu_memory_access);
 
-	perf_test_args.wr_fract = 1;
-
 	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
 	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
 
-	/* Export the shared variables to the guest */
-	sync_global_to_guest(vm, perf_test_args);
-
 	pr_info("Finished creating vCPUs\n");
 
 	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
-- 
cgit v1.2.3-59-g8ed1b


From 36c5ad73d7016f34146cf0821c78f08737bdb5e9 Mon Sep 17 00:00:00 2001
From: David Matlack <dmatlack@google.com>
Date: Thu, 11 Nov 2021 00:12:54 +0000
Subject: KVM: selftests: Start at iteration 0 instead of -1

Start at iteration 0 instead of -1 to avoid having to initialize
vcpu_last_completed_iteration when setting up vCPU threads. This
simplifies the next commit where we move vCPU thread initialization
out to a common helper.

No functional change intended.

Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111001257.1446428-2-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/access_tracking_perf_test.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c
index 5364a2ed7c68..7f25a06e19c9 100644
--- a/tools/testing/selftests/kvm/access_tracking_perf_test.c
+++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c
@@ -47,7 +47,7 @@
 #include "guest_modes.h"
 
 /* Global variable used to synchronize all of the vCPU threads. */
-static int iteration = -1;
+static int iteration;
 
 /* Defines what vCPU threads should do during a given iteration. */
 static enum {
@@ -220,7 +220,7 @@ static void *vcpu_thread_main(void *arg)
 	struct perf_test_vcpu_args *vcpu_args = arg;
 	struct kvm_vm *vm = perf_test_args.vm;
 	int vcpu_id = vcpu_args->vcpu_id;
-	int current_iteration = -1;
+	int current_iteration = 0;
 
 	while (spin_wait_for_next_iteration(&current_iteration)) {
 		switch (READ_ONCE(iteration_work)) {
@@ -303,11 +303,9 @@ static pthread_t *create_vcpu_threads(int vcpus)
 	vcpu_threads = malloc(vcpus * sizeof(vcpu_threads[0]));
 	TEST_ASSERT(vcpu_threads, "Failed to allocate vcpu_threads.");
 
-	for (i = 0; i < vcpus; i++) {
-		vcpu_last_completed_iteration[i] = iteration;
+	for (i = 0; i < vcpus; i++)
 		pthread_create(&vcpu_threads[i], NULL, vcpu_thread_main,
 			       &perf_test_args.vcpu_args[i]);
-	}
 
 	return vcpu_threads;
 }
-- 
cgit v1.2.3-59-g8ed1b


From 81bcb26172a8f00840e0ca44277272dcb673887a Mon Sep 17 00:00:00 2001
From: David Matlack <dmatlack@google.com>
Date: Thu, 11 Nov 2021 00:12:55 +0000
Subject: KVM: selftests: Move vCPU thread creation and joining to common
 helpers

Move vCPU thread creation and joining to common helper functions. This
is in preparation for the next commit which ensures that all vCPU
threads are fully created before entering guest mode on any one
vCPU.

No functional change intended.

Signed-off-by: David Matlack <dmatlack@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Message-Id: <20211111001257.1446428-3-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 .../selftests/kvm/access_tracking_perf_test.c      | 40 +++----------------
 tools/testing/selftests/kvm/demand_paging_test.c   | 25 ++----------
 tools/testing/selftests/kvm/dirty_log_perf_test.c  | 19 ++-------
 .../testing/selftests/kvm/include/perf_test_util.h |  5 +++
 tools/testing/selftests/kvm/lib/perf_test_util.c   | 46 ++++++++++++++++++++++
 .../kvm/memslot_modification_stress_test.c         | 22 ++---------
 6 files changed, 67 insertions(+), 90 deletions(-)

diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c
index 7f25a06e19c9..d8909032317a 100644
--- a/tools/testing/selftests/kvm/access_tracking_perf_test.c
+++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c
@@ -215,9 +215,8 @@ static bool spin_wait_for_next_iteration(int *current_iteration)
 	return true;
 }
 
-static void *vcpu_thread_main(void *arg)
+static void vcpu_thread_main(struct perf_test_vcpu_args *vcpu_args)
 {
-	struct perf_test_vcpu_args *vcpu_args = arg;
 	struct kvm_vm *vm = perf_test_args.vm;
 	int vcpu_id = vcpu_args->vcpu_id;
 	int current_iteration = 0;
@@ -235,8 +234,6 @@ static void *vcpu_thread_main(void *arg)
 
 		vcpu_last_completed_iteration[vcpu_id] = current_iteration;
 	}
-
-	return NULL;
 }
 
 static void spin_wait_for_vcpu(int vcpu_id, int target_iteration)
@@ -295,43 +292,16 @@ static void mark_memory_idle(struct kvm_vm *vm, int vcpus)
 	run_iteration(vm, vcpus, "Mark memory idle");
 }
 
-static pthread_t *create_vcpu_threads(int vcpus)
-{
-	pthread_t *vcpu_threads;
-	int i;
-
-	vcpu_threads = malloc(vcpus * sizeof(vcpu_threads[0]));
-	TEST_ASSERT(vcpu_threads, "Failed to allocate vcpu_threads.");
-
-	for (i = 0; i < vcpus; i++)
-		pthread_create(&vcpu_threads[i], NULL, vcpu_thread_main,
-			       &perf_test_args.vcpu_args[i]);
-
-	return vcpu_threads;
-}
-
-static void terminate_vcpu_threads(pthread_t *vcpu_threads, int vcpus)
-{
-	int i;
-
-	/* Set done to signal the vCPU threads to exit */
-	done = true;
-
-	for (i = 0; i < vcpus; i++)
-		pthread_join(vcpu_threads[i], NULL);
-}
-
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *params = arg;
 	struct kvm_vm *vm;
-	pthread_t *vcpu_threads;
 	int vcpus = params->vcpus;
 
 	vm = perf_test_create_vm(mode, vcpus, params->vcpu_memory_bytes, 1,
 				 params->backing_src, !overlap_memory_access);
 
-	vcpu_threads = create_vcpu_threads(vcpus);
+	perf_test_start_vcpu_threads(vcpus, vcpu_thread_main);
 
 	pr_info("\n");
 	access_memory(vm, vcpus, ACCESS_WRITE, "Populating memory");
@@ -346,8 +316,10 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	mark_memory_idle(vm, vcpus);
 	access_memory(vm, vcpus, ACCESS_READ, "Reading from idle memory");
 
-	terminate_vcpu_threads(vcpu_threads, vcpus);
-	free(vcpu_threads);
+	/* Set done to signal the vCPU threads to exit */
+	done = true;
+
+	perf_test_join_vcpu_threads(vcpus);
 	perf_test_destroy_vm(vm);
 }
 
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 26f8fd8a57ec..6a719d065599 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -42,10 +42,9 @@ static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
 static size_t demand_paging_size;
 static char *guest_data_prototype;
 
-static void *vcpu_worker(void *data)
+static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
 {
 	int ret;
-	struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data;
 	int vcpu_id = vcpu_args->vcpu_id;
 	struct kvm_vm *vm = perf_test_args.vm;
 	struct kvm_run *run;
@@ -68,8 +67,6 @@ static void *vcpu_worker(void *data)
 	ts_diff = timespec_elapsed(start);
 	PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id,
 		       ts_diff.tv_sec, ts_diff.tv_nsec);
-
-	return NULL;
 }
 
 static int handle_uffd_page_request(int uffd_mode, int uffd, uint64_t addr)
@@ -282,7 +279,6 @@ struct test_params {
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *p = arg;
-	pthread_t *vcpu_threads;
 	pthread_t *uffd_handler_threads = NULL;
 	struct uffd_handler_args *uffd_args = NULL;
 	struct timespec start;
@@ -302,9 +298,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		    "Failed to allocate buffer for guest data pattern");
 	memset(guest_data_prototype, 0xAB, demand_paging_size);
 
-	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
-	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
-
 	if (p->uffd_mode) {
 		uffd_handler_threads =
 			malloc(nr_vcpus * sizeof(*uffd_handler_threads));
@@ -346,22 +339,11 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	pr_info("Finished creating vCPUs and starting uffd threads\n");
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
-
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
-		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
-			       &perf_test_args.vcpu_args[vcpu_id]);
-	}
-
+	perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
 	pr_info("Started all vCPUs\n");
 
-	/* Wait for the vcpu threads to quit */
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
-		pthread_join(vcpu_threads[vcpu_id], NULL);
-		PER_VCPU_DEBUG("Joined thread for vCPU %d\n", vcpu_id);
-	}
-
+	perf_test_join_vcpu_threads(nr_vcpus);
 	ts_diff = timespec_elapsed(start);
-
 	pr_info("All vCPU threads joined\n");
 
 	if (p->uffd_mode) {
@@ -385,7 +367,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	perf_test_destroy_vm(vm);
 
 	free(guest_data_prototype);
-	free(vcpu_threads);
 	if (p->uffd_mode) {
 		free(uffd_handler_threads);
 		free(uffd_args);
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 583b4d95aa98..1954b964d1cf 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -31,7 +31,7 @@ static bool host_quit;
 static int iteration;
 static int vcpu_last_completed_iteration[KVM_MAX_VCPUS];
 
-static void *vcpu_worker(void *data)
+static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
 {
 	int ret;
 	struct kvm_vm *vm = perf_test_args.vm;
@@ -41,7 +41,6 @@ static void *vcpu_worker(void *data)
 	struct timespec ts_diff;
 	struct timespec total = (struct timespec){0};
 	struct timespec avg;
-	struct perf_test_vcpu_args *vcpu_args = (struct perf_test_vcpu_args *)data;
 	int vcpu_id = vcpu_args->vcpu_id;
 
 	run = vcpu_state(vm, vcpu_id);
@@ -83,8 +82,6 @@ static void *vcpu_worker(void *data)
 	pr_debug("\nvCPU %d dirtied 0x%lx pages over %d iterations in %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
 		vcpu_id, pages_count, vcpu_last_completed_iteration[vcpu_id],
 		total.tv_sec, total.tv_nsec, avg.tv_sec, avg.tv_nsec);
-
-	return NULL;
 }
 
 struct test_params {
@@ -170,7 +167,6 @@ static void free_bitmaps(unsigned long *bitmaps[], int slots)
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *p = arg;
-	pthread_t *vcpu_threads;
 	struct kvm_vm *vm;
 	unsigned long **bitmaps;
 	uint64_t guest_num_pages;
@@ -204,20 +200,15 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 		vm_enable_cap(vm, &cap);
 	}
 
-	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
-	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
-
 	/* Start the iterations */
 	iteration = 0;
 	host_quit = false;
 
 	clock_gettime(CLOCK_MONOTONIC, &start);
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
+	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
 		vcpu_last_completed_iteration[vcpu_id] = -1;
 
-		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
-			       &perf_test_args.vcpu_args[vcpu_id]);
-	}
+	perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
 
 	/* Allow the vCPUs to populate memory */
 	pr_debug("Starting iteration %d - Populating\n", iteration);
@@ -286,8 +277,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	/* Tell the vcpu thread to quit */
 	host_quit = true;
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
-		pthread_join(vcpu_threads[vcpu_id], NULL);
+	perf_test_join_vcpu_threads(nr_vcpus);
 
 	avg = timespec_div(get_dirty_log_total, p->iterations);
 	pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
@@ -302,7 +292,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	}
 
 	free_bitmaps(bitmaps, p->slots);
-	free(vcpu_threads);
 	perf_test_destroy_vm(vm);
 }
 
diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
index 74e3622b3a6e..a86f953d8d36 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -8,6 +8,8 @@
 #ifndef SELFTEST_KVM_PERF_TEST_UTIL_H
 #define SELFTEST_KVM_PERF_TEST_UTIL_H
 
+#include <pthread.h>
+
 #include "kvm_util.h"
 
 /* Default guest test virtual memory offset */
@@ -45,4 +47,7 @@ void perf_test_destroy_vm(struct kvm_vm *vm);
 
 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);
+
 #endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index 77f9eb5667c9..d646477ed16a 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -16,6 +16,20 @@ struct perf_test_args perf_test_args;
  */
 static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
 
+struct vcpu_thread {
+	/* The id of the vCPU. */
+	int vcpu_id;
+
+	/* The pthread backing the vCPU. */
+	pthread_t thread;
+};
+
+/* The vCPU threads involved in this test. */
+static struct vcpu_thread vcpu_threads[KVM_MAX_VCPUS];
+
+/* The function run by each vCPU thread, as provided by the test. */
+static void (*vcpu_thread_fn)(struct perf_test_vcpu_args *);
+
 /*
  * Continuously write to the first 8 bytes of each page in the
  * specified region.
@@ -177,3 +191,35 @@ void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract)
 	perf_test_args.wr_fract = wr_fract;
 	sync_global_to_guest(vm, perf_test_args);
 }
+
+static void *vcpu_thread_main(void *data)
+{
+	struct vcpu_thread *vcpu = data;
+
+	vcpu_thread_fn(&perf_test_args.vcpu_args[vcpu->vcpu_id]);
+
+	return NULL;
+}
+
+void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *))
+{
+	int vcpu_id;
+
+	vcpu_thread_fn = vcpu_fn;
+
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+		struct vcpu_thread *vcpu = &vcpu_threads[vcpu_id];
+
+		vcpu->vcpu_id = vcpu_id;
+
+		pthread_create(&vcpu->thread, NULL, vcpu_thread_main, vcpu);
+	}
+}
+
+void perf_test_join_vcpu_threads(int vcpus)
+{
+	int vcpu_id;
+
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++)
+		pthread_join(vcpu_threads[vcpu_id].thread, NULL);
+}
diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
index df431d0da1ee..5bd0b076f57f 100644
--- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c
+++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
@@ -36,11 +36,9 @@ static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
 
 static bool run_vcpus = true;
 
-static void *vcpu_worker(void *data)
+static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
 {
 	int ret;
-	struct perf_test_vcpu_args *vcpu_args =
-		(struct perf_test_vcpu_args *)data;
 	int vcpu_id = vcpu_args->vcpu_id;
 	struct kvm_vm *vm = perf_test_args.vm;
 	struct kvm_run *run;
@@ -59,8 +57,6 @@ static void *vcpu_worker(void *data)
 			    "Invalid guest sync status: exit_reason=%s\n",
 			    exit_reason_str(run->exit_reason));
 	}
-
-	return NULL;
 }
 
 struct memslot_antagonist_args {
@@ -100,22 +96,15 @@ struct test_params {
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *p = arg;
-	pthread_t *vcpu_threads;
 	struct kvm_vm *vm;
-	int vcpu_id;
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
 				 VM_MEM_SRC_ANONYMOUS,
 				 p->partition_vcpu_memory_access);
 
-	vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads));
-	TEST_ASSERT(vcpu_threads, "Memory allocation failed");
-
 	pr_info("Finished creating vCPUs\n");
 
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
-		pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker,
-			       &perf_test_args.vcpu_args[vcpu_id]);
+	perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
 
 	pr_info("Started all vCPUs\n");
 
@@ -124,16 +113,11 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 
 	run_vcpus = false;
 
-	/* Wait for the vcpu threads to quit */
-	for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++)
-		pthread_join(vcpu_threads[vcpu_id], NULL);
-
+	perf_test_join_vcpu_threads(nr_vcpus);
 	pr_info("All vCPU threads joined\n");
 
 	ucall_uninit(vm);
 	kvm_vm_free(vm);
-
-	free(vcpu_threads);
 }
 
 static void help(char *name)
-- 
cgit v1.2.3-59-g8ed1b


From 89d9a43c1d2d3d703fae25c990a1d98dd178dd17 Mon Sep 17 00:00:00 2001
From: David Matlack <dmatlack@google.com>
Date: Thu, 11 Nov 2021 00:12:56 +0000
Subject: KVM: selftests: Wait for all vCPU to be created before entering guest
 mode

Thread creation requires taking the mmap_sem in write mode, which causes
vCPU threads running in guest mode to block while they are populating
memory. Fix this by waiting for all vCPU threads to be created and start
running before entering guest mode on any one vCPU thread.

This substantially improves the "Populate memory time" when using 1GiB
pages since it allows all vCPUs to zero pages in parallel rather than
blocking because a writer is waiting (which is waiting for another vCPU
that is busy zeroing a 1GiB page).

Before:

  $ ./dirty_log_perf_test -v256 -s anonymous_hugetlb_1gb
  ...
  Populate memory time: 52.811184013s

After:

  $ ./dirty_log_perf_test -v256 -s anonymous_hugetlb_1gb
  ...
  Populate memory time: 10.204573342s

Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <20211111001257.1446428-4-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/lib/perf_test_util.c | 26 ++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index d646477ed16a..722df3a28791 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -22,6 +22,9 @@ struct vcpu_thread {
 
 	/* The pthread backing the vCPU. */
 	pthread_t thread;
+
+	/* Set to true once the vCPU thread is up and running. */
+	bool running;
 };
 
 /* The vCPU threads involved in this test. */
@@ -30,6 +33,9 @@ static struct vcpu_thread vcpu_threads[KVM_MAX_VCPUS];
 /* The function run by each vCPU thread, as provided by the test. */
 static void (*vcpu_thread_fn)(struct perf_test_vcpu_args *);
 
+/* Set to true once all vCPU threads are up and running. */
+static bool all_vcpu_threads_running;
+
 /*
  * Continuously write to the first 8 bytes of each page in the
  * specified region.
@@ -196,6 +202,17 @@ static void *vcpu_thread_main(void *data)
 {
 	struct vcpu_thread *vcpu = data;
 
+	WRITE_ONCE(vcpu->running, true);
+
+	/*
+	 * Wait for all vCPU threads to be up and running before calling the test-
+	 * provided vCPU thread function. This prevents thread creation (which
+	 * requires taking the mmap_sem in write mode) from interfering with the
+	 * guest faulting in its memory.
+	 */
+	while (!READ_ONCE(all_vcpu_threads_running))
+		;
+
 	vcpu_thread_fn(&perf_test_args.vcpu_args[vcpu->vcpu_id]);
 
 	return NULL;
@@ -206,14 +223,23 @@ void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vc
 	int vcpu_id;
 
 	vcpu_thread_fn = vcpu_fn;
+	WRITE_ONCE(all_vcpu_threads_running, false);
 
 	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
 		struct vcpu_thread *vcpu = &vcpu_threads[vcpu_id];
 
 		vcpu->vcpu_id = vcpu_id;
+		WRITE_ONCE(vcpu->running, false);
 
 		pthread_create(&vcpu->thread, NULL, vcpu_thread_main, vcpu);
 	}
+
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+		while (!READ_ONCE(vcpu_threads[vcpu_id].running))
+			;
+	}
+
+	WRITE_ONCE(all_vcpu_threads_running, true);
 }
 
 void perf_test_join_vcpu_threads(int vcpus)
-- 
cgit v1.2.3-59-g8ed1b


From e2bd936581038f3107c45e8ae32309a567b54bf4 Mon Sep 17 00:00:00 2001
From: David Matlack <dmatlack@google.com>
Date: Thu, 11 Nov 2021 00:12:57 +0000
Subject: KVM: selftests: Use perf_test_destroy_vm in
 memslot_modification_stress_test

Change memslot_modification_stress_test to use perf_test_destroy_vm
instead of manually calling ucall_uninit and kvm_vm_free.

No functional change intended.

Signed-off-by: David Matlack <dmatlack@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Message-Id: <20211111001257.1446428-5-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/memslot_modification_stress_test.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
index 5bd0b076f57f..1410d0a9141a 100644
--- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c
+++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
@@ -116,8 +116,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	perf_test_join_vcpu_threads(nr_vcpus);
 	pr_info("All vCPU threads joined\n");
 
-	ucall_uninit(vm);
-	kvm_vm_free(vm);
+	perf_test_destroy_vm(vm);
 }
 
 static void help(char *name)
-- 
cgit v1.2.3-59-g8ed1b


From c5adbb3af051079f35abfa26551107e2c653087f Mon Sep 17 00:00:00 2001
From: 黄乐 <huangle1@jd.com>
Date: Mon, 15 Nov 2021 14:08:29 +0000
Subject: KVM: x86: Fix uninitialized eoi_exit_bitmap usage in
 vcpu_load_eoi_exitmap()

In vcpu_load_eoi_exitmap(), currently the eoi_exit_bitmap[4] array is
initialized only when Hyper-V context is available, in other path it is
just passed to kvm_x86_ops.load_eoi_exitmap() directly from on the stack,
which would cause unexpected interrupt delivery/handling issues, e.g. an
*old* linux kernel that relies on PIT to do clock calibration on KVM might
randomly fail to boot.

Fix it by passing ioapic_handled_vectors to load_eoi_exitmap() when Hyper-V
context is not available.

Fixes: f2bc14b69c38 ("KVM: x86: hyper-v: Prepare to meet unallocated Hyper-V context")
Cc: stable@vger.kernel.org
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Huang Le <huangle1@jd.com>
Message-Id: <62115b277dab49ea97da5633f8522daf@jd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/x86.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5c479ae57693..2c03b76caf11 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9640,12 +9640,16 @@ static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu)
 	if (!kvm_apic_hw_enabled(vcpu->arch.apic))
 		return;
 
-	if (to_hv_vcpu(vcpu))
+	if (to_hv_vcpu(vcpu)) {
 		bitmap_or((ulong *)eoi_exit_bitmap,
 			  vcpu->arch.ioapic_handled_vectors,
 			  to_hv_synic(vcpu)->vec_bitmap, 256);
+		static_call(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap);
+		return;
+	}
 
-	static_call(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap);
+	static_call(kvm_x86_load_eoi_exitmap)(
+		vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors);
 }
 
 void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
-- 
cgit v1.2.3-59-g8ed1b


From dc23a5110b106da13502de5735399ad83ed1a682 Mon Sep 17 00:00:00 2001
From: Paul Durrant <pdurrant@amazon.com>
Date: Mon, 15 Nov 2021 14:41:31 +0000
Subject: cpuid: kvm_find_kvm_cpuid_features() should be declared 'static'

The lack a static declaration currently results in:

arch/x86/kvm/cpuid.c:128:26: warning: no previous prototype for function 'kvm_find_kvm_cpuid_features'

when compiling with "W=1".

Reported-by: kernel test robot <lkp@intel.com>
Fixes: 760849b1476c ("KVM: x86: Make sure KVM_CPUID_FEATURES really are KVM_CPUID_FEATURES")
Signed-off-by: Paul Durrant <pdurrant@amazon.com>
Message-Id: <20211115144131.5943-1-pdurrant@amazon.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/cpuid.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index e19dabf1848b..07e9215e911d 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -125,7 +125,7 @@ static void kvm_update_kvm_cpuid_base(struct kvm_vcpu *vcpu)
 	}
 }
 
-struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu)
+static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu)
 {
 	u32 base = vcpu->arch.kvm_cpuid_base;
 
-- 
cgit v1.2.3-59-g8ed1b


From 964b7aa0b040bdc6ec1c543ee620cda3f8b4c68a Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Sun, 14 Nov 2021 08:59:02 +0000
Subject: KVM: Fix steal time asm constraints

In 64-bit mode, x86 instruction encoding allows us to use the low 8 bits
of any GPR as an 8-bit operand. In 32-bit mode, however, we can only use
the [abcd] registers. For which, GCC has the "q" constraint instead of
the less restrictive "r".

Also fix st->preempted, which is an input/output operand rather than an
input.

Fixes: 7e2175ebd695 ("KVM: x86: Fix recording of guest steal time / preempted status")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <89bf72db1b859990355f9c40713a34e0d2d86c98.camel@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/x86.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2c03b76caf11..4ae77e1dadf6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3307,9 +3307,9 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 			     "xor %1, %1\n"
 			     "2:\n"
 			     _ASM_EXTABLE_UA(1b, 2b)
-			     : "+r" (st_preempted),
-			       "+&r" (err)
-			     : "m" (st->preempted));
+			     : "+q" (st_preempted),
+			       "+&r" (err),
+			       "+m" (st->preempted));
 		if (err)
 			goto out;
 
-- 
cgit v1.2.3-59-g8ed1b


From af957eebfcc17433ee83ab85b1195a933ab5049c Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Mon, 15 Nov 2021 15:18:36 +0200
Subject: KVM: nVMX: don't use vcpu->arch.efer when checking host state on
 nested state load

When loading nested state, don't use check vcpu->arch.efer to get the
L1 host's 64-bit vs. 32-bit state and don't check it for consistency
with respect to VM_EXIT_HOST_ADDR_SPACE_SIZE, as register state in vCPU
may be stale when KVM_SET_NESTED_STATE is called---and architecturally
does not exist.  When restoring L2 state in KVM, the CPU is placed in
non-root where nested VMX code has no snapshot of L1 host state: VMX
(conditionally) loads host state fields loaded on VM-exit, but they need
not correspond to the state before entry.  A simple case occurs in KVM
itself, where the host RIP field points to vmx_vmexit rather than the
instruction following vmlaunch/vmresume.

However, for the particular case of L1 being in 32- or 64-bit mode
on entry, the exit controls can be treated instead as the source of
truth regarding the state of L1 on entry, and can be used to check
that vmcs12.VM_EXIT_HOST_ADDR_SPACE_SIZE matches vmcs12.HOST_EFER if
vmcs12.VM_EXIT_LOAD_IA32_EFER is set.  The consistency check on CPU
EFER vs. vmcs12.VM_EXIT_HOST_ADDR_SPACE_SIZE, instead, happens only
on VM-Enter.  That's because, again, there's conceptually no "current"
L1 EFER to check on KVM_SET_NESTED_STATE.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20211115131837.195527-2-mlevitsk@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx/nested.c | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index b213ca966d41..e307d3c1d26b 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2830,6 +2830,17 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu,
+				       struct vmcs12 *vmcs12)
+{
+#ifdef CONFIG_X86_64
+	if (CC(!!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) !=
+		!!(vcpu->arch.efer & EFER_LMA)))
+		return -EINVAL;
+#endif
+	return 0;
+}
+
 static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 				       struct vmcs12 *vmcs12)
 {
@@ -2854,18 +2865,16 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 
 #ifdef CONFIG_X86_64
-	ia32e = !!(vcpu->arch.efer & EFER_LMA);
+	ia32e = !!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE);
 #else
 	ia32e = false;
 #endif
 
 	if (ia32e) {
-		if (CC(!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)) ||
-		    CC(!(vmcs12->host_cr4 & X86_CR4_PAE)))
+		if (CC(!(vmcs12->host_cr4 & X86_CR4_PAE)))
 			return -EINVAL;
 	} else {
-		if (CC(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) ||
-		    CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) ||
+		if (CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) ||
 		    CC(vmcs12->host_cr4 & X86_CR4_PCIDE) ||
 		    CC((vmcs12->host_rip) >> 32))
 			return -EINVAL;
@@ -3535,6 +3544,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	if (nested_vmx_check_controls(vcpu, vmcs12))
 		return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
 
+	if (nested_vmx_check_address_space_size(vcpu, vmcs12))
+		return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD);
+
 	if (nested_vmx_check_host_state(vcpu, vmcs12))
 		return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD);
 
-- 
cgit v1.2.3-59-g8ed1b


From b8453cdcf26020030da182f0156d7bf59ae5719f Mon Sep 17 00:00:00 2001
From: Maxim Levitsky <mlevitsk@redhat.com>
Date: Mon, 15 Nov 2021 15:18:37 +0200
Subject: KVM: x86/mmu: include EFER.LMA in extended mmu role

Incorporate EFER.LMA into kvm_mmu_extended_role, as it used to compute the
guest root level and is not reflected in kvm_mmu_page_role.level when TDP
is in use.  When simply running the guest, it is impossible for EFER.LMA
and kvm_mmu.root_level to get out of sync, as the guest cannot transition
from PAE paging to 64-bit paging without toggling CR0.PG, i.e. without
first bouncing through a different MMU context.  And stuffing guest state
via KVM_SET_SREGS{,2} also ensures a full MMU context reset.

However, if KVM_SET_SREGS{,2} is followed by KVM_SET_NESTED_STATE, e.g. to
set guest state when migrating the VM while L2 is active, the vCPU state
will reflect L2, not L1.  If L1 is using TDP for L2, then root_mmu will
have been configured using L2's state, despite not being used for L2.  If
L2.EFER.LMA != L1.EFER.LMA, and L2 is using PAE paging, then root_mmu will
be configured for guest PAE paging, but will match the mmu_role for 64-bit
paging and cause KVM to not reconfigure root_mmu on the next nested VM-Exit.

Alternatively, the root_mmu's role could be invalidated after a successful
KVM_SET_NESTED_STATE that yields vcpu->arch.mmu != vcpu->arch.root_mmu,
i.e. that switches the active mmu to guest_mmu, but doing so is unnecessarily
tricky, and not even needed if L1 and L2 do have the same role (e.g., they
are both 64-bit guests and run with the same CR4).

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Message-Id: <20211115131837.195527-3-mlevitsk@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/kvm_host.h | 1 +
 arch/x86/kvm/mmu/mmu.c          | 1 +
 2 files changed, 2 insertions(+)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 33e3292233f3..e977634333d4 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -363,6 +363,7 @@ union kvm_mmu_extended_role {
 		unsigned int cr4_smap:1;
 		unsigned int cr4_smep:1;
 		unsigned int cr4_la57:1;
+		unsigned int efer_lma:1;
 	};
 };
 
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 04c00c34517e..0571b1c7bf6f 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4682,6 +4682,7 @@ static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu,
 		/* PKEY and LA57 are active iff long mode is active. */
 		ext.cr4_pke = ____is_efer_lma(regs) && ____is_cr4_pke(regs);
 		ext.cr4_la57 = ____is_efer_lma(regs) && ____is_cr4_la57(regs);
+		ext.efer_lma = ____is_efer_lma(regs);
 	}
 
 	ext.valid = 1;
-- 
cgit v1.2.3-59-g8ed1b


From 4e8436479ad3be76a3823e6ce466ae464ce71300 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Mon, 15 Nov 2021 16:50:21 +0000
Subject: KVM: x86/xen: Fix get_attr of KVM_XEN_ATTR_TYPE_SHARED_INFO

In commit 319afe68567b ("KVM: xen: do not use struct gfn_to_hva_cache") we
stopped storing this in-kernel as a GPA, and started storing it as a GFN.
Which means we probably should have stopped calling gpa_to_gfn() on it
when userspace asks for it back.

Cc: stable@vger.kernel.org
Fixes: 319afe68567b ("KVM: xen: do not use struct gfn_to_hva_cache")
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <20211115165030.7422-2-dwmw2@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/xen.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 9ea9c3dabe37..79090dbe1e66 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -282,7 +282,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data)
 		break;
 
 	case KVM_XEN_ATTR_TYPE_SHARED_INFO:
-		data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_gfn);
+		data->u.shared_info.gfn = kvm->arch.xen.shinfo_gfn;
 		r = 0;
 		break;
 
-- 
cgit v1.2.3-59-g8ed1b


From 297d597a6da38fc1b40fa470044a767e33801438 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Mon, 15 Nov 2021 16:50:24 +0000
Subject: KVM: nVMX: Use kvm_{read,write}_guest_cached() for shadow_vmcs12

Using kvm_vcpu_map() for reading from the guest is entirely gratuitous,
when all we do is a single memcpy and unmap it again. Fix it up to use
kvm_read_guest()... but in fact I couldn't bring myself to do that
without also making it use a gfn_to_hva_cache for both that *and* the
copy in the other direction.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <20211115165030.7422-5-dwmw2@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx/nested.c | 24 +++++++++++++++---------
 arch/x86/kvm/vmx/vmx.h    |  5 +++++
 2 files changed, 20 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index e307d3c1d26b..fff6b326dc2b 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -670,33 +670,39 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 static void nested_cache_shadow_vmcs12(struct kvm_vcpu *vcpu,
 				       struct vmcs12 *vmcs12)
 {
-	struct kvm_host_map map;
-	struct vmcs12 *shadow;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache;
 
 	if (!nested_cpu_has_shadow_vmcs(vmcs12) ||
 	    vmcs12->vmcs_link_pointer == INVALID_GPA)
 		return;
 
-	shadow = get_shadow_vmcs12(vcpu);
-
-	if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map))
+	if (ghc->gpa != vmcs12->vmcs_link_pointer &&
+	    kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc,
+				      vmcs12->vmcs_link_pointer, VMCS12_SIZE))
 		return;
 
-	memcpy(shadow, map.hva, VMCS12_SIZE);
-	kvm_vcpu_unmap(vcpu, &map, false);
+	kvm_read_guest_cached(vmx->vcpu.kvm, ghc, get_shadow_vmcs12(vcpu),
+			      VMCS12_SIZE);
 }
 
 static void nested_flush_cached_shadow_vmcs12(struct kvm_vcpu *vcpu,
 					      struct vmcs12 *vmcs12)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache;
 
 	if (!nested_cpu_has_shadow_vmcs(vmcs12) ||
 	    vmcs12->vmcs_link_pointer == INVALID_GPA)
 		return;
 
-	kvm_write_guest(vmx->vcpu.kvm, vmcs12->vmcs_link_pointer,
-			get_shadow_vmcs12(vcpu), VMCS12_SIZE);
+	if (ghc->gpa != vmcs12->vmcs_link_pointer &&
+	    kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc,
+				      vmcs12->vmcs_link_pointer, VMCS12_SIZE))
+		return;
+
+	kvm_write_guest_cached(vmx->vcpu.kvm, ghc, get_shadow_vmcs12(vcpu),
+			       VMCS12_SIZE);
 }
 
 /*
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index a4ead6023133..cdadbd5dc0ca 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -141,6 +141,11 @@ struct nested_vmx {
 	 */
 	struct vmcs12 *cached_shadow_vmcs12;
 
+	/*
+	 * GPA to HVA cache for accessing vmcs12->vmcs_link_pointer
+	 */
+	struct gfn_to_hva_cache shadow_vmcs12_cache;
+
 	/*
 	 * Indicates if the shadow vmcs or enlightened vmcs must be updated
 	 * with the data held by struct vmcs12.
-- 
cgit v1.2.3-59-g8ed1b


From 6a834754a568bb809a1466001a0523dab8e6adef Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Mon, 15 Nov 2021 16:50:23 +0000
Subject: KVM: x86/xen: Use sizeof_field() instead of open-coding it

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <20211115165030.7422-4-dwmw2@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/xen.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 79090dbe1e66..272be5c1ebed 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -127,9 +127,9 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state)
 	state_entry_time = vx->runstate_entry_time;
 	state_entry_time |= XEN_RUNSTATE_UPDATE;
 
-	BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->state_entry_time) !=
+	BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, state_entry_time) !=
 		     sizeof(state_entry_time));
-	BUILD_BUG_ON(sizeof(((struct compat_vcpu_runstate_info *)0)->state_entry_time) !=
+	BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state_entry_time) !=
 		     sizeof(state_entry_time));
 
 	if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache,
@@ -144,9 +144,9 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state)
 	 */
 	BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state) !=
 		     offsetof(struct compat_vcpu_runstate_info, state));
-	BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->state) !=
+	BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, state) !=
 		     sizeof(vx->current_runstate));
-	BUILD_BUG_ON(sizeof(((struct compat_vcpu_runstate_info *)0)->state) !=
+	BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state) !=
 		     sizeof(vx->current_runstate));
 
 	if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache,
@@ -163,9 +163,9 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state)
 		     offsetof(struct vcpu_runstate_info, time) - sizeof(u64));
 	BUILD_BUG_ON(offsetof(struct compat_vcpu_runstate_info, state_entry_time) !=
 		     offsetof(struct compat_vcpu_runstate_info, time) - sizeof(u64));
-	BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->time) !=
-		     sizeof(((struct compat_vcpu_runstate_info *)0)->time));
-	BUILD_BUG_ON(sizeof(((struct vcpu_runstate_info *)0)->time) !=
+	BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) !=
+		     sizeof_field(struct compat_vcpu_runstate_info, time));
+	BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) !=
 		     sizeof(vx->runstate_times));
 
 	if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache,
@@ -204,9 +204,9 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v)
 	BUILD_BUG_ON(offsetof(struct vcpu_info, evtchn_upcall_pending) !=
 		     offsetof(struct compat_vcpu_info, evtchn_upcall_pending));
 	BUILD_BUG_ON(sizeof(rc) !=
-		     sizeof(((struct vcpu_info *)0)->evtchn_upcall_pending));
+		     sizeof_field(struct vcpu_info, evtchn_upcall_pending));
 	BUILD_BUG_ON(sizeof(rc) !=
-		     sizeof(((struct compat_vcpu_info *)0)->evtchn_upcall_pending));
+		     sizeof_field(struct compat_vcpu_info, evtchn_upcall_pending));
 
 	/*
 	 * For efficiency, this mirrors the checks for using the valid
-- 
cgit v1.2.3-59-g8ed1b


From 7d0172b3ca4231f0a0566157e9a28a3d3ffc0142 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Mon, 15 Nov 2021 16:50:25 +0000
Subject: KVM: nVMX: Use kvm_read_guest_offset_cached() for nested VMCS check

Kill another mostly gratuitous kvm_vcpu_map() which could just use the
userspace HVA for it.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <20211115165030.7422-6-dwmw2@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx/nested.c | 26 +++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index fff6b326dc2b..4fb904ff7f12 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2925,9 +2925,9 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu,
 					  struct vmcs12 *vmcs12)
 {
-	int r = 0;
-	struct vmcs12 *shadow;
-	struct kvm_host_map map;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct gfn_to_hva_cache *ghc = &vmx->nested.shadow_vmcs12_cache;
+	struct vmcs_hdr hdr;
 
 	if (vmcs12->vmcs_link_pointer == INVALID_GPA)
 		return 0;
@@ -2935,17 +2935,21 @@ static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu,
 	if (CC(!page_address_valid(vcpu, vmcs12->vmcs_link_pointer)))
 		return -EINVAL;
 
-	if (CC(kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->vmcs_link_pointer), &map)))
-		return -EINVAL;
+	if (ghc->gpa != vmcs12->vmcs_link_pointer &&
+	    CC(kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc,
+					 vmcs12->vmcs_link_pointer, VMCS12_SIZE)))
+                return -EINVAL;
 
-	shadow = map.hva;
+	if (CC(kvm_read_guest_offset_cached(vcpu->kvm, ghc, &hdr,
+					    offsetof(struct vmcs12, hdr),
+					    sizeof(hdr))))
+		return -EINVAL;
 
-	if (CC(shadow->hdr.revision_id != VMCS12_REVISION) ||
-	    CC(shadow->hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12)))
-		r = -EINVAL;
+	if (CC(hdr.revision_id != VMCS12_REVISION) ||
+	    CC(hdr.shadow_vmcs != nested_cpu_has_shadow_vmcs(vmcs12)))
+		return -EINVAL;
 
-	kvm_vcpu_unmap(vcpu, &map, false);
-	return r;
+	return 0;
 }
 
 /*
-- 
cgit v1.2.3-59-g8ed1b


From cee66664dcd6241a943380ef9dcd2f8a0a7dc47d Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Mon, 15 Nov 2021 16:50:26 +0000
Subject: KVM: nVMX: Use a gfn_to_hva_cache for vmptrld

And thus another call to kvm_vcpu_map() can die.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <20211115165030.7422-7-dwmw2@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx/nested.c | 26 +++++++++++++++++---------
 arch/x86/kvm/vmx/vmx.h    |  5 +++++
 2 files changed, 22 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 4fb904ff7f12..1e2f66951566 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -5286,10 +5286,11 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 		return 1;
 
 	if (vmx->nested.current_vmptr != vmptr) {
-		struct kvm_host_map map;
-		struct vmcs12 *new_vmcs12;
+		struct gfn_to_hva_cache *ghc = &vmx->nested.vmcs12_cache;
+		struct vmcs_hdr hdr;
 
-		if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmptr), &map)) {
+		if (ghc->gpa != vmptr &&
+		    kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, vmptr, VMCS12_SIZE)) {
 			/*
 			 * Reads from an unbacked page return all 1s,
 			 * which means that the 32 bits located at the
@@ -5300,12 +5301,16 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 				VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
 		}
 
-		new_vmcs12 = map.hva;
+		if (kvm_read_guest_offset_cached(vcpu->kvm, ghc, &hdr,
+						 offsetof(struct vmcs12, hdr),
+						 sizeof(hdr))) {
+			return nested_vmx_fail(vcpu,
+				VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
+		}
 
-		if (new_vmcs12->hdr.revision_id != VMCS12_REVISION ||
-		    (new_vmcs12->hdr.shadow_vmcs &&
+		if (hdr.revision_id != VMCS12_REVISION ||
+		    (hdr.shadow_vmcs &&
 		     !nested_cpu_has_vmx_shadow_vmcs(vcpu))) {
-			kvm_vcpu_unmap(vcpu, &map, false);
 			return nested_vmx_fail(vcpu,
 				VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
 		}
@@ -5316,8 +5321,11 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 		 * Load VMCS12 from guest memory since it is not already
 		 * cached.
 		 */
-		memcpy(vmx->nested.cached_vmcs12, new_vmcs12, VMCS12_SIZE);
-		kvm_vcpu_unmap(vcpu, &map, false);
+		if (kvm_read_guest_cached(vcpu->kvm, ghc, vmx->nested.cached_vmcs12,
+					  VMCS12_SIZE)) {
+			return nested_vmx_fail(vcpu,
+				VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
+		}
 
 		set_current_vmptr(vmx, vmptr);
 	}
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index cdadbd5dc0ca..4df2ac24ffc1 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -146,6 +146,11 @@ struct nested_vmx {
 	 */
 	struct gfn_to_hva_cache shadow_vmcs12_cache;
 
+	/*
+	 * GPA to HVA cache for VMCS12
+	 */
+	struct gfn_to_hva_cache vmcs12_cache;
+
 	/*
 	 * Indicates if the shadow vmcs or enlightened vmcs must be updated
 	 * with the data held by struct vmcs12.
-- 
cgit v1.2.3-59-g8ed1b


From 357a18ad230f0867791b788d2b1d6f280f6f6e61 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Mon, 15 Nov 2021 16:50:27 +0000
Subject: KVM: Kill kvm_map_gfn() / kvm_unmap_gfn() and gfn_to_pfn_cache

In commit 7e2175ebd695 ("KVM: x86: Fix recording of guest steal time /
preempted status") I removed the only user of these functions because
it was basically impossible to use them safely.

There are two stages to the GFN->PFN mapping; first through the KVM
memslots to a userspace HVA and then through the page tables to
translate that HVA to an underlying PFN. Invalidations of the former
were being handled correctly, but no attempt was made to use the MMU
notifiers to invalidate the cache when the HVA->GFN mapping changed.

As a prelude to reinventing the gfn_to_pfn_cache with more usable
semantics, rip it out entirely and untangle the implementation of
the unsafe kvm_vcpu_map()/kvm_vcpu_unmap() functions from it.

All current users of kvm_vcpu_map() also look broken right now, and
will be dealt with separately. They broadly fall into two classes:

* Those which map, access the data and immediately unmap. This is
  mostly gratuitous and could just as well use the existing user
  HVA, and could probably benefit from a gfn_to_hva_cache as they
  do so.

* Those which keep the mapping around for a longer time, perhaps
  even using the PFN directly from the guest. These will need to
  be converted to the new gfn_to_pfn_cache and then kvm_vcpu_map()
  can be removed too.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <20211115165030.7422-8-dwmw2@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h  |   6 +--
 include/linux/kvm_types.h |   7 ----
 virt/kvm/kvm_main.c       | 100 +++++-----------------------------------------
 3 files changed, 12 insertions(+), 101 deletions(-)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 60a35d9fe259..eb625af4fc5e 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -866,7 +866,7 @@ void kvm_release_pfn_dirty(kvm_pfn_t pfn);
 void kvm_set_pfn_dirty(kvm_pfn_t pfn);
 void kvm_set_pfn_accessed(kvm_pfn_t pfn);
 
-void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache);
+void kvm_release_pfn(kvm_pfn_t pfn, bool dirty);
 int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
 			int len);
 int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len);
@@ -942,12 +942,8 @@ struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn
 kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn);
 kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map);
-int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map,
-		struct gfn_to_pfn_cache *cache, bool atomic);
 struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn);
 void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty);
-int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map,
-		  struct gfn_to_pfn_cache *cache, bool dirty, bool atomic);
 unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn);
 unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable);
 int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset,
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index 2237abb93ccd..234eab059839 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -53,13 +53,6 @@ struct gfn_to_hva_cache {
 	struct kvm_memory_slot *memslot;
 };
 
-struct gfn_to_pfn_cache {
-	u64 generation;
-	gfn_t gfn;
-	kvm_pfn_t pfn;
-	bool dirty;
-};
-
 #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
 /*
  * Memory caches are used to preallocate memory ahead of various MMU flows,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 3f6d450355f0..7a28c29dca8a 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2548,72 +2548,36 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(gfn_to_page);
 
-void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache)
+void kvm_release_pfn(kvm_pfn_t pfn, bool dirty)
 {
 	if (pfn == 0)
 		return;
 
-	if (cache)
-		cache->pfn = cache->gfn = 0;
-
 	if (dirty)
 		kvm_release_pfn_dirty(pfn);
 	else
 		kvm_release_pfn_clean(pfn);
 }
 
-static void kvm_cache_gfn_to_pfn(struct kvm_memory_slot *slot, gfn_t gfn,
-				 struct gfn_to_pfn_cache *cache, u64 gen)
-{
-	kvm_release_pfn(cache->pfn, cache->dirty, cache);
-
-	cache->pfn = gfn_to_pfn_memslot(slot, gfn);
-	cache->gfn = gfn;
-	cache->dirty = false;
-	cache->generation = gen;
-}
-
-static int __kvm_map_gfn(struct kvm_memslots *slots, gfn_t gfn,
-			 struct kvm_host_map *map,
-			 struct gfn_to_pfn_cache *cache,
-			 bool atomic)
+int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map)
 {
 	kvm_pfn_t pfn;
 	void *hva = NULL;
 	struct page *page = KVM_UNMAPPED_PAGE;
-	struct kvm_memory_slot *slot = __gfn_to_memslot(slots, gfn);
-	u64 gen = slots->generation;
 
 	if (!map)
 		return -EINVAL;
 
-	if (cache) {
-		if (!cache->pfn || cache->gfn != gfn ||
-			cache->generation != gen) {
-			if (atomic)
-				return -EAGAIN;
-			kvm_cache_gfn_to_pfn(slot, gfn, cache, gen);
-		}
-		pfn = cache->pfn;
-	} else {
-		if (atomic)
-			return -EAGAIN;
-		pfn = gfn_to_pfn_memslot(slot, gfn);
-	}
+	pfn = gfn_to_pfn(vcpu->kvm, gfn);
 	if (is_error_noslot_pfn(pfn))
 		return -EINVAL;
 
 	if (pfn_valid(pfn)) {
 		page = pfn_to_page(pfn);
-		if (atomic)
-			hva = kmap_atomic(page);
-		else
-			hva = kmap(page);
+		hva = kmap(page);
 #ifdef CONFIG_HAS_IOMEM
-	} else if (!atomic) {
-		hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB);
 	} else {
-		return -EINVAL;
+		hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB);
 #endif
 	}
 
@@ -2627,27 +2591,9 @@ static int __kvm_map_gfn(struct kvm_memslots *slots, gfn_t gfn,
 
 	return 0;
 }
-
-int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map,
-		struct gfn_to_pfn_cache *cache, bool atomic)
-{
-	return __kvm_map_gfn(kvm_memslots(vcpu->kvm), gfn, map,
-			cache, atomic);
-}
-EXPORT_SYMBOL_GPL(kvm_map_gfn);
-
-int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map)
-{
-	return __kvm_map_gfn(kvm_vcpu_memslots(vcpu), gfn, map,
-		NULL, false);
-}
 EXPORT_SYMBOL_GPL(kvm_vcpu_map);
 
-static void __kvm_unmap_gfn(struct kvm *kvm,
-			struct kvm_memory_slot *memslot,
-			struct kvm_host_map *map,
-			struct gfn_to_pfn_cache *cache,
-			bool dirty, bool atomic)
+void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty)
 {
 	if (!map)
 		return;
@@ -2655,45 +2601,21 @@ static void __kvm_unmap_gfn(struct kvm *kvm,
 	if (!map->hva)
 		return;
 
-	if (map->page != KVM_UNMAPPED_PAGE) {
-		if (atomic)
-			kunmap_atomic(map->hva);
-		else
-			kunmap(map->page);
-	}
+	if (map->page != KVM_UNMAPPED_PAGE)
+		kunmap(map->page);
 #ifdef CONFIG_HAS_IOMEM
-	else if (!atomic)
-		memunmap(map->hva);
 	else
-		WARN_ONCE(1, "Unexpected unmapping in atomic context");
+		memunmap(map->hva);
 #endif
 
 	if (dirty)
-		mark_page_dirty_in_slot(kvm, memslot, map->gfn);
+		kvm_vcpu_mark_page_dirty(vcpu, map->gfn);
 
-	if (cache)
-		cache->dirty |= dirty;
-	else
-		kvm_release_pfn(map->pfn, dirty, NULL);
+	kvm_release_pfn(map->pfn, dirty);
 
 	map->hva = NULL;
 	map->page = NULL;
 }
-
-int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map, 
-		  struct gfn_to_pfn_cache *cache, bool dirty, bool atomic)
-{
-	__kvm_unmap_gfn(vcpu->kvm, gfn_to_memslot(vcpu->kvm, map->gfn), map,
-			cache, dirty, atomic);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(kvm_unmap_gfn);
-
-void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty)
-{
-	__kvm_unmap_gfn(vcpu->kvm, kvm_vcpu_gfn_to_memslot(vcpu, map->gfn),
-			map, NULL, dirty, false);
-}
 EXPORT_SYMBOL_GPL(kvm_vcpu_unmap);
 
 struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn)
-- 
cgit v1.2.3-59-g8ed1b


From 79b11142763791bdead8b6460052cbdde8e08e2f Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 9 Nov 2021 21:50:56 +0000
Subject: KVM: SEV: Disallow COPY_ENC_CONTEXT_FROM if target has created vCPUs

Reject COPY_ENC_CONTEXT_FROM if the destination VM has created vCPUs.
KVM relies on SEV activation to occur before vCPUs are created, e.g. to
set VMCB flags and intercepts correctly.

Fixes: 54526d1fd593 ("KVM: x86: Support KVM VMs sharing SEV context")
Cc: stable@vger.kernel.org
Cc: Peter Gonda <pgonda@google.com>
Cc: Marc Orr <marcorr@google.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Nathan Tempelman <natet@google.com>
Cc: Brijesh Singh <brijesh.singh@amd.com>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20211109215101.2211373-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/sev.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 3e2769855e51..eeec499e4372 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1775,7 +1775,12 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd)
 	mutex_unlock(&source_kvm->lock);
 	mutex_lock(&kvm->lock);
 
-	if (sev_guest(kvm)) {
+	/*
+	 * Disallow out-of-band SEV/SEV-ES init if the target is already an
+	 * SEV guest, or if vCPUs have been created.  KVM relies on vCPUs being
+	 * created after SEV/SEV-ES initialization, e.g. to init intercepts.
+	 */
+	if (sev_guest(kvm) || kvm->created_vcpus) {
 		ret = -EINVAL;
 		goto e_mirror_unlock;
 	}
-- 
cgit v1.2.3-59-g8ed1b


From a41fb26e61697382b2428ae63e039e97b0e6d164 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 9 Nov 2021 21:50:58 +0000
Subject: KVM: SEV: Set sev_info.active after initial checks in
 sev_guest_init()

Set sev_info.active during SEV/SEV-ES activation before calling any code
that can potentially consume sev_info.es_active, e.g. set "active" and
"es_active" as a pair immediately after the initial sanity checks.  KVM
generally expects that es_active can be true if and only if active is
true, e.g. sev_asid_new() deliberately avoids sev_es_guest() so that it
doesn't get a false negative.  This will allow WARNing in sev_es_guest()
if the VM is tagged as SEV-ES but not SEV.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20211109215101.2211373-4-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/sev.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index eeec499e4372..50b9d76e9137 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -229,7 +229,6 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
 static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
 	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
-	bool es_active = argp->id == KVM_SEV_ES_INIT;
 	int asid, ret;
 
 	if (kvm->created_vcpus)
@@ -239,7 +238,8 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	if (unlikely(sev->active))
 		return ret;
 
-	sev->es_active = es_active;
+	sev->active = true;
+	sev->es_active = argp->id == KVM_SEV_ES_INIT;
 	asid = sev_asid_new(sev);
 	if (asid < 0)
 		goto e_no_asid;
@@ -249,7 +249,6 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	if (ret)
 		goto e_free;
 
-	sev->active = true;
 	sev->asid = asid;
 	INIT_LIST_HEAD(&sev->regions_list);
 
@@ -260,6 +259,7 @@ e_free:
 	sev->asid = 0;
 e_no_asid:
 	sev->es_active = false;
+	sev->active = false;
 	return ret;
 }
 
-- 
cgit v1.2.3-59-g8ed1b


From 1bd00a4257a86db654499137fd8e6db7d1e484dc Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 9 Nov 2021 21:50:59 +0000
Subject: KVM: SEV: WARN if SEV-ES is marked active but SEV is not

WARN if the VM is tagged as SEV-ES but not SEV.  KVM relies on SEV and
SEV-ES being set atomically, and guards common flows with "is SEV", i.e.
observing SEV-ES without SEV means KVM has a fatal bug.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20211109215101.2211373-5-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/svm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 0d7bbe548ac3..a345f557be4a 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -242,7 +242,7 @@ static inline bool sev_es_guest(struct kvm *kvm)
 #ifdef CONFIG_KVM_AMD_SEV
 	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 
-	return sev_guest(kvm) && sev->es_active;
+	return sev->es_active && !WARN_ON_ONCE(!sev->active);
 #else
 	return false;
 #endif
-- 
cgit v1.2.3-59-g8ed1b


From ea410ef4dad6282420bde00e1ffca874344f0e95 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 9 Nov 2021 21:51:00 +0000
Subject: KVM: SEV: Drop a redundant setting of sev->asid during initialization

Remove a fully redundant write to sev->asid during SEV/SEV-ES guest
initialization.  The ASID is set a few lines earlier prior to the call to
sev_platform_init(), which doesn't take "sev" as a param, i.e. can't
muck with the ASID barring some truly magical behind-the-scenes code.

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20211109215101.2211373-6-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/sev.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 50b9d76e9137..80692435ac3d 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -249,7 +249,6 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	if (ret)
 		goto e_free;
 
-	sev->asid = asid;
 	INIT_LIST_HEAD(&sev->regions_list);
 
 	return 0;
-- 
cgit v1.2.3-59-g8ed1b


From 8e38e96a4e616ed0936faa964ceeb5d390b6425e Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Tue, 9 Nov 2021 21:51:01 +0000
Subject: KVM: SEV: Fix typo in and tweak name of cmd_allowed_from_miror()

Rename cmd_allowed_from_miror() to is_cmd_allowed_from_mirror(), fixing
a typo and making it obvious that the result is a boolean where
false means "not allowed".

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20211109215101.2211373-7-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/svm/sev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 80692435ac3d..87874c586531 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1509,7 +1509,7 @@ static int sev_receive_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	return sev_issue_cmd(kvm, SEV_CMD_RECEIVE_FINISH, &data, &argp->error);
 }
 
-static bool cmd_allowed_from_miror(u32 cmd_id)
+static bool is_cmd_allowed_from_mirror(u32 cmd_id)
 {
 	/*
 	 * Allow mirrors VM to call KVM_SEV_LAUNCH_UPDATE_VMSA to enable SEV-ES
@@ -1541,7 +1541,7 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 
 	/* Only the enc_context_owner handles some memory enc operations. */
 	if (is_mirroring_enc_context(kvm) &&
-	    !cmd_allowed_from_miror(sev_cmd.id)) {
+	    !is_cmd_allowed_from_mirror(sev_cmd.id)) {
 		r = -EINVAL;
 		goto out;
 	}
-- 
cgit v1.2.3-59-g8ed1b


From 0e2e641921000ffc647b12918cdfcc504a9f6e3b Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 6 Nov 2021 20:47:06 -0700
Subject: riscv: kvm: fix non-kernel-doc comment block

Don't use "/**" to begin a comment block for a non-kernel-doc comment.

Prevents this docs build warning:

vcpu_sbi.c:3: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst
 * Copyright (c) 2019 Western Digital Corporation or its affiliates.

Fixes: dea8ee31a039 ("RISC-V: KVM: Add SBI v0.1 support")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: kernel test robot <lkp@intel.com>
Cc: Atish Patra <atish.patra@wdc.com>
Cc: Anup Patel <anup.patel@wdc.com>
Cc: kvm@vger.kernel.org
Cc: kvm-riscv@lists.infradead.org
Cc: linux-riscv@lists.infradead.org
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Message-Id: <20211107034706.30672-1-rdunlap@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/riscv/kvm/vcpu_sbi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c
index eb3c045edf11..3b0e703d22cf 100644
--- a/arch/riscv/kvm/vcpu_sbi.c
+++ b/arch/riscv/kvm/vcpu_sbi.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/**
+/*
  * Copyright (c) 2019 Western Digital Corporation or its affiliates.
  *
  * Authors:
-- 
cgit v1.2.3-59-g8ed1b


From b768f60bd9791c528a4a4b98659674787b2e7c63 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@kernel.org>
Date: Tue, 16 Nov 2021 12:03:25 -0300
Subject: selftests: KVM: Add /x86_64/sev_migrate_tests to .gitignore

  $ git status
  nothing to commit, working tree clean
  $
  $ make -C tools/testing/selftests/kvm/ > /dev/null 2>&1
  $ git status

  Untracked files:
    (use "git add <file>..." to include in what will be committed)
  	tools/testing/selftests/kvm/x86_64/sev_migrate_tests

  nothing added to commit but untracked files present (use "git add" to track)
  $

Fixes: 6a58150859fdec76 ("selftest: KVM: Add intra host migration tests")
Cc: Brijesh Singh <brijesh.singh@amd.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Marc Orr <marcorr@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Gonda <pgonda@google.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Message-Id: <YZPIPfvYgRDCZi/w@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 tools/testing/selftests/kvm/.gitignore | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index d4a830139683..3763105029fb 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -23,6 +23,7 @@
 /x86_64/platform_info_test
 /x86_64/set_boot_cpu_id
 /x86_64/set_sregs_test
+/x86_64/sev_migrate_tests
 /x86_64/smm_test
 /x86_64/state_test
 /x86_64/svm_vmcall_test
-- 
cgit v1.2.3-59-g8ed1b


From b5aead0064f33ae5e693a364e3204fe1c0ac9af2 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Mon, 24 May 2021 12:48:57 -0500
Subject: KVM: x86: Assume a 64-bit hypercall for guests with protected state

When processing a hypercall for a guest with protected state, currently
SEV-ES guests, the guest CS segment register can't be checked to
determine if the guest is in 64-bit mode. For an SEV-ES guest, it is
expected that communication between the guest and the hypervisor is
performed to shared memory using the GHCB. In order to use the GHCB, the
guest must have been in long mode, otherwise writes by the guest to the
GHCB would be encrypted and not be able to be comprehended by the
hypervisor.

Create a new helper function, is_64_bit_hypercall(), that assumes the
guest is in 64-bit mode when the guest has protected state, and returns
true, otherwise invoking is_64_bit_mode() to determine the mode. Update
the hypercall related routines to use is_64_bit_hypercall() instead of
is_64_bit_mode().

Add a WARN_ON_ONCE() to is_64_bit_mode() to catch occurences of calls to
this helper function for a guest running with protected state.

Fixes: f1c6366e3043 ("KVM: SVM: Add required changes to support intercepts under SEV-ES")
Reported-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Message-Id: <e0b20c770c9d0d1403f23d83e785385104211f74.1621878537.git.thomas.lendacky@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/hyperv.c |  4 ++--
 arch/x86/kvm/x86.c    |  2 +-
 arch/x86/kvm/x86.h    | 12 ++++++++++++
 arch/x86/kvm/xen.c    |  2 +-
 4 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 4a555f32885a..5e19e6e4c2ce 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -2022,7 +2022,7 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result)
 {
 	bool longmode;
 
-	longmode = is_64_bit_mode(vcpu);
+	longmode = is_64_bit_hypercall(vcpu);
 	if (longmode)
 		kvm_rax_write(vcpu, result);
 	else {
@@ -2171,7 +2171,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 	}
 
 #ifdef CONFIG_X86_64
-	if (is_64_bit_mode(vcpu)) {
+	if (is_64_bit_hypercall(vcpu)) {
 		hc.param = kvm_rcx_read(vcpu);
 		hc.ingpa = kvm_rdx_read(vcpu);
 		hc.outgpa = kvm_r8_read(vcpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c85d70107057..ecd2041570d1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8848,7 +8848,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 
 	trace_kvm_hypercall(nr, a0, a1, a2, a3);
 
-	op_64_bit = is_64_bit_mode(vcpu);
+	op_64_bit = is_64_bit_hypercall(vcpu);
 	if (!op_64_bit) {
 		nr &= 0xFFFFFFFF;
 		a0 &= 0xFFFFFFFF;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index ea264c4502e4..997669ae9caa 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -153,12 +153,24 @@ static inline bool is_64_bit_mode(struct kvm_vcpu *vcpu)
 {
 	int cs_db, cs_l;
 
+	WARN_ON_ONCE(vcpu->arch.guest_state_protected);
+
 	if (!is_long_mode(vcpu))
 		return false;
 	static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l);
 	return cs_l;
 }
 
+static inline bool is_64_bit_hypercall(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * If running with protected guest state, the CS register is not
+	 * accessible. The hypercall register values will have had to been
+	 * provided in 64-bit mode, so assume the guest is in 64-bit.
+	 */
+	return vcpu->arch.guest_state_protected || is_64_bit_mode(vcpu);
+}
+
 static inline bool x86_exception_has_error_code(unsigned int vector)
 {
 	static u32 exception_has_error_code = BIT(DF_VECTOR) | BIT(TS_VECTOR) |
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 565da9c3853b..dff2bdf9507a 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -698,7 +698,7 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu)
 	    kvm_hv_hypercall_enabled(vcpu))
 		return kvm_hv_hypercall(vcpu);
 
-	longmode = is_64_bit_mode(vcpu);
+	longmode = is_64_bit_hypercall(vcpu);
 	if (!longmode) {
 		params[0] = (u32)kvm_rbx_read(vcpu);
 		params[1] = (u32)kvm_rcx_read(vcpu);
-- 
cgit v1.2.3-59-g8ed1b


From f60a00d7295057cb4baea5a321501efc72794453 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 16 Nov 2021 17:34:38 +0100
Subject: KVM: arm64: Cap KVM_CAP_NR_VCPUS by kvm_arm_default_max_vcpus()

Generally, it doesn't make sense to return the recommended maximum number
of vCPUs which exceeds the maximum possible number of vCPUs.

Note: ARM64 is special as the value returned by KVM_CAP_MAX_VCPUS differs
depending on whether it is a system-wide ioctl or a per-VM one. Previously,
KVM_CAP_NR_VCPUS didn't have this difference and it seems preferable to
keep the status quo. Cap KVM_CAP_NR_VCPUS by kvm_arm_default_max_vcpus()
which is what gets returned by system-wide KVM_CAP_MAX_VCPUS.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20211116163443.88707-2-vkuznets@redhat.com>
Acked-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/arm64/kvm/arm.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 2f03cbfefe67..e4727dc771bf 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -223,7 +223,14 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = 1;
 		break;
 	case KVM_CAP_NR_VCPUS:
-		r = num_online_cpus();
+		/*
+		 * ARM64 treats KVM_CAP_NR_CPUS differently from all other
+		 * architectures, as it does not always bound it to
+		 * KVM_CAP_MAX_VCPUS. It should not matter much because
+		 * this is just an advisory value.
+		 */
+		r = min_t(unsigned int, num_online_cpus(),
+			  kvm_arm_default_max_vcpus());
 		break;
 	case KVM_CAP_MAX_VCPUS:
 	case KVM_CAP_MAX_VCPU_ID:
-- 
cgit v1.2.3-59-g8ed1b


From 57a2e13ebdda8b65602b44ec8b80e385603eb84c Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 16 Nov 2021 17:34:39 +0100
Subject: KVM: MIPS: Cap KVM_CAP_NR_VCPUS by KVM_CAP_MAX_VCPUS

It doesn't make sense to return the recommended maximum number of
vCPUs which exceeds the maximum possible number of vCPUs.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20211116163443.88707-3-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/mips/kvm/mips.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 562aa878b266..aa20d074d388 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -1067,7 +1067,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = 1;
 		break;
 	case KVM_CAP_NR_VCPUS:
-		r = num_online_cpus();
+		r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS);
 		break;
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
-- 
cgit v1.2.3-59-g8ed1b


From b7915d55b1ac0e68a7586697fa2d06c018135c49 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 16 Nov 2021 17:34:40 +0100
Subject: KVM: PPC: Cap KVM_CAP_NR_VCPUS by KVM_CAP_MAX_VCPUS

It doesn't make sense to return the recommended maximum number of
vCPUs which exceeds the maximum possible number of vCPUs.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20211116163443.88707-4-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/powerpc/kvm/powerpc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 35e9cccdeef9..a72920f4f221 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -641,9 +641,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		 * implementations just count online CPUs.
 		 */
 		if (hv_enabled)
-			r = num_present_cpus();
+			r = min_t(unsigned int, num_present_cpus(), KVM_MAX_VCPUS);
 		else
-			r = num_online_cpus();
+			r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS);
 		break;
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
-- 
cgit v1.2.3-59-g8ed1b


From 37fd3ce1e64a2e86a986542a17bebf1553512da9 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 16 Nov 2021 17:34:41 +0100
Subject: KVM: RISC-V: Cap KVM_CAP_NR_VCPUS by KVM_CAP_MAX_VCPUS

It doesn't make sense to return the recommended maximum number of
vCPUs which exceeds the maximum possible number of vCPUs.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Acked-by: Anup Patel <anup.patel@wdc.com>
Reviewed-by: Anup Patel <anup.patel@wdc.com>
Message-Id: <20211116163443.88707-5-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/riscv/kvm/vm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c
index 26399df15b63..fb18af34a4b5 100644
--- a/arch/riscv/kvm/vm.c
+++ b/arch/riscv/kvm/vm.c
@@ -74,7 +74,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = 1;
 		break;
 	case KVM_CAP_NR_VCPUS:
-		r = num_online_cpus();
+		r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS);
 		break;
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
-- 
cgit v1.2.3-59-g8ed1b


From 82cc27eff4486f8e79ef8faac1af1f5573039aa4 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 16 Nov 2021 17:34:42 +0100
Subject: KVM: s390: Cap KVM_CAP_NR_VCPUS by num_online_cpus()

KVM_CAP_NR_VCPUS is a legacy advisory value which on other architectures
return num_online_cpus() caped by KVM_CAP_NR_VCPUS or something else
(ppc and arm64 are special cases). On s390, KVM_CAP_NR_VCPUS returns
the same as KVM_CAP_MAX_VCPUS and this may turn out to be a bad
'advice'. Switch s390 to returning caped num_online_cpus() too.

Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Message-Id: <20211116163443.88707-6-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/s390/kvm/kvm-s390.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index c6257f625929..14a18ba5ff2c 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -585,6 +585,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 			r = KVM_MAX_VCPUS;
 		else if (sclp.has_esca && sclp.has_64bscao)
 			r = KVM_S390_ESCA_CPU_SLOTS;
+		if (ext == KVM_CAP_NR_VCPUS)
+			r = min_t(unsigned int, num_online_cpus(), r);
 		break;
 	case KVM_CAP_S390_COW:
 		r = MACHINE_HAS_ESOP;
-- 
cgit v1.2.3-59-g8ed1b


From 2845e7353bc334d43309f5ea6d376c8fdbc94c93 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Tue, 16 Nov 2021 17:34:43 +0100
Subject: KVM: x86: Cap KVM_CAP_NR_VCPUS by KVM_CAP_MAX_VCPUS

It doesn't make sense to return the recommended maximum number of
vCPUs which exceeds the maximum possible number of vCPUs.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20211116163443.88707-7-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/x86.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ecd2041570d1..5a403d92833f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4179,7 +4179,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = !static_call(kvm_x86_cpu_has_accelerated_tpr)();
 		break;
 	case KVM_CAP_NR_VCPUS:
-		r = num_online_cpus();
+		r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS);
 		break;
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
-- 
cgit v1.2.3-59-g8ed1b