From a737f5ffb1e883e580730122be11c9eb832a7749 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gshan@redhat.com>
Date: Thu, 10 Nov 2022 18:49:12 +0800
Subject: KVM: selftests: Use host page size to map ring buffer in
 dirty_log_test

In vcpu_map_dirty_ring(), the guest's page size is used to figure out
the offset in the virtual area. It works fine when we have same page
sizes on host and guest. However, it fails when the page sizes on host
and guest are different on arm64, like below error messages indicates.

  # ./dirty_log_test -M dirty-ring -m 7
  Setting log mode to: 'dirty-ring'
  Test iterations: 32, interval: 10 (ms)
  Testing guest mode: PA-bits:40,  VA-bits:48, 64K pages
  guest physical test memory offset: 0xffbffc0000
  vcpu stops because vcpu is kicked out...
  Notifying vcpu to continue
  vcpu continues now.
  ==== Test Assertion Failure ====
  lib/kvm_util.c:1477: addr == MAP_FAILED
  pid=9000 tid=9000 errno=0 - Success
  1  0x0000000000405f5b: vcpu_map_dirty_ring at kvm_util.c:1477
  2  0x0000000000402ebb: dirty_ring_collect_dirty_pages at dirty_log_test.c:349
  3  0x00000000004029b3: log_mode_collect_dirty_pages at dirty_log_test.c:478
  4  (inlined by) run_test at dirty_log_test.c:778
  5  (inlined by) run_test at dirty_log_test.c:691
  6  0x0000000000403a57: for_each_guest_mode at guest_modes.c:105
  7  0x0000000000401ccf: main at dirty_log_test.c:921
  8  0x0000ffffb06ec79b: ?? ??:0
  9  0x0000ffffb06ec86b: ?? ??:0
  10 0x0000000000401def: _start at ??:?
  Dirty ring mapped private

Fix the issue by using host's page size to map the ring buffer.

Signed-off-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221110104914.31280-6-gshan@redhat.com
---
 tools/testing/selftests/kvm/lib/kvm_util.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools/testing/selftests/kvm/lib')

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index f1cb1627161f..89a1a420ebd5 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1506,7 +1506,7 @@ struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vcpu *vcpu)
 
 void *vcpu_map_dirty_ring(struct kvm_vcpu *vcpu)
 {
-	uint32_t page_size = vcpu->vm->page_size;
+	uint32_t page_size = getpagesize();
 	uint32_t size = vcpu->vm->dirty_ring_size;
 
 	TEST_ASSERT(size > 0, "Should enable dirty ring first");
-- 
cgit v1.2.3


From 1a6182033f2d5c481aec1f8c1c26ebc649693d57 Mon Sep 17 00:00:00 2001
From: Reiji Watanabe <reijiw@google.com>
Date: Wed, 19 Oct 2022 22:41:54 -0700
Subject: KVM: arm64: selftests: Use FIELD_GET() to extract ID register fields

Use FIELD_GET() macro to extract ID register fields for existing
aarch64 selftests code. No functional change intended.

Signed-off-by: Reiji Watanabe <reijiw@google.com>
Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221020054202.2119018-2-reijiw@google.com
---
 tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c  | 3 ++-
 tools/testing/selftests/kvm/aarch64/debug-exceptions.c | 3 ++-
 tools/testing/selftests/kvm/lib/aarch64/processor.c    | 7 ++++---
 3 files changed, 8 insertions(+), 5 deletions(-)

(limited to 'tools/testing/selftests/kvm/lib')

diff --git a/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c b/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c
index 6f9c1f19c7f6..b6a5e8861b35 100644
--- a/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c
+++ b/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c
@@ -13,6 +13,7 @@
 #include "kvm_util.h"
 #include "processor.h"
 #include "test_util.h"
+#include <linux/bitfield.h>
 
 #define BAD_ID_REG_VAL	0x1badc0deul
 
@@ -145,7 +146,7 @@ static bool vcpu_aarch64_only(struct kvm_vcpu *vcpu)
 
 	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1), &val);
 
-	el0 = (val & ARM64_FEATURE_MASK(ID_AA64PFR0_EL0)) >> ID_AA64PFR0_EL0_SHIFT;
+	el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL0), val);
 	return el0 == ID_AA64PFR0_ELx_64BIT_ONLY;
 }
 
diff --git a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
index 947bd201435c..3808d3d75055 100644
--- a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
+++ b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
@@ -2,6 +2,7 @@
 #include <test_util.h>
 #include <kvm_util.h>
 #include <processor.h>
+#include <linux/bitfield.h>
 
 #define MDSCR_KDE	(1 << 13)
 #define MDSCR_MDE	(1 << 15)
@@ -284,7 +285,7 @@ static int debug_version(struct kvm_vcpu *vcpu)
 	uint64_t id_aa64dfr0;
 
 	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1), &id_aa64dfr0);
-	return id_aa64dfr0 & 0xf;
+	return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_DEBUGVER), id_aa64dfr0);
 }
 
 static void test_guest_debug_exceptions(void)
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 6f5551368944..7c96b931edd5 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -11,6 +11,7 @@
 #include "guest_modes.h"
 #include "kvm_util.h"
 #include "processor.h"
+#include <linux/bitfield.h>
 
 #define DEFAULT_ARM64_GUEST_STACK_VADDR_MIN	0xac0000
 
@@ -486,9 +487,9 @@ void aarch64_get_supported_page_sizes(uint32_t ipa,
 	err = ioctl(vcpu_fd, KVM_GET_ONE_REG, &reg);
 	TEST_ASSERT(err == 0, KVM_IOCTL_ERROR(KVM_GET_ONE_REG, vcpu_fd));
 
-	*ps4k = ((val >> 28) & 0xf) != 0xf;
-	*ps64k = ((val >> 24) & 0xf) == 0;
-	*ps16k = ((val >> 20) & 0xf) != 0;
+	*ps4k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_TGRAN4), val) != 0xf;
+	*ps64k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_TGRAN64), val) == 0;
+	*ps16k = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_TGRAN16), val) != 0;
 
 	close(vcpu_fd);
 	close(vm_fd);
-- 
cgit v1.2.3


From a93871d0ea9fd59fb5eb783619334183d7f07f51 Mon Sep 17 00:00:00 2001
From: Ricardo Koller <ricarkol@google.com>
Date: Mon, 17 Oct 2022 19:58:21 +0000
Subject: KVM: selftests: Add a userfaultfd library

Move the generic userfaultfd code out of demand_paging_test.c into a
common library, userfaultfd_util. This library consists of a setup and a
stop function. The setup function starts a thread for handling page
faults using the handler callback function. This setup returns a
uffd_desc object which is then used in the stop function (to wait and
destroy the threads).

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: Ricardo Koller <ricarkol@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221017195834.2295901-2-ricarkol@google.com
---
 tools/testing/selftests/kvm/Makefile               |   1 +
 tools/testing/selftests/kvm/demand_paging_test.c   | 228 +++------------------
 .../selftests/kvm/include/userfaultfd_util.h       |  45 ++++
 tools/testing/selftests/kvm/lib/userfaultfd_util.c | 186 +++++++++++++++++
 4 files changed, 262 insertions(+), 198 deletions(-)
 create mode 100644 tools/testing/selftests/kvm/include/userfaultfd_util.h
 create mode 100644 tools/testing/selftests/kvm/lib/userfaultfd_util.c

(limited to 'tools/testing/selftests/kvm/lib')

diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 0172eb6cb6ee..08a2606aff33 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -47,6 +47,7 @@ LIBKVM += lib/perf_test_util.c
 LIBKVM += lib/rbtree.c
 LIBKVM += lib/sparsebit.c
 LIBKVM += lib/test_util.c
+LIBKVM += lib/userfaultfd_util.c
 
 LIBKVM_STRING += lib/string_override.c
 
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 779ae54f89c4..8e1fe4ffcccd 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -22,23 +22,13 @@
 #include "test_util.h"
 #include "perf_test_util.h"
 #include "guest_modes.h"
+#include "userfaultfd_util.h"
 
 #ifdef __NR_userfaultfd
 
-#ifdef PRINT_PER_PAGE_UPDATES
-#define PER_PAGE_DEBUG(...) printf(__VA_ARGS__)
-#else
-#define PER_PAGE_DEBUG(...) _no_printf(__VA_ARGS__)
-#endif
-
-#ifdef PRINT_PER_VCPU_UPDATES
-#define PER_VCPU_DEBUG(...) printf(__VA_ARGS__)
-#else
-#define PER_VCPU_DEBUG(...) _no_printf(__VA_ARGS__)
-#endif
-
 static int nr_vcpus = 1;
 static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
+
 static size_t demand_paging_size;
 static char *guest_data_prototype;
 
@@ -67,9 +57,11 @@ static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
 		       ts_diff.tv_sec, ts_diff.tv_nsec);
 }
 
-static int handle_uffd_page_request(int uffd_mode, int uffd, uint64_t addr)
+static int handle_uffd_page_request(int uffd_mode, int uffd,
+		struct uffd_msg *msg)
 {
 	pid_t tid = syscall(__NR_gettid);
+	uint64_t addr = msg->arg.pagefault.address;
 	struct timespec start;
 	struct timespec ts_diff;
 	int r;
@@ -116,174 +108,32 @@ static int handle_uffd_page_request(int uffd_mode, int uffd, uint64_t addr)
 	return 0;
 }
 
-bool quit_uffd_thread;
-
-struct uffd_handler_args {
+struct test_params {
 	int uffd_mode;
-	int uffd;
-	int pipefd;
-	useconds_t delay;
+	useconds_t uffd_delay;
+	enum vm_mem_backing_src_type src_type;
+	bool partition_vcpu_memory_access;
 };
 
-static void *uffd_handler_thread_fn(void *arg)
-{
-	struct uffd_handler_args *uffd_args = (struct uffd_handler_args *)arg;
-	int uffd = uffd_args->uffd;
-	int pipefd = uffd_args->pipefd;
-	useconds_t delay = uffd_args->delay;
-	int64_t pages = 0;
-	struct timespec start;
-	struct timespec ts_diff;
-
-	clock_gettime(CLOCK_MONOTONIC, &start);
-	while (!quit_uffd_thread) {
-		struct uffd_msg msg;
-		struct pollfd pollfd[2];
-		char tmp_chr;
-		int r;
-		uint64_t addr;
-
-		pollfd[0].fd = uffd;
-		pollfd[0].events = POLLIN;
-		pollfd[1].fd = pipefd;
-		pollfd[1].events = POLLIN;
-
-		r = poll(pollfd, 2, -1);
-		switch (r) {
-		case -1:
-			pr_info("poll err");
-			continue;
-		case 0:
-			continue;
-		case 1:
-			break;
-		default:
-			pr_info("Polling uffd returned %d", r);
-			return NULL;
-		}
-
-		if (pollfd[0].revents & POLLERR) {
-			pr_info("uffd revents has POLLERR");
-			return NULL;
-		}
-
-		if (pollfd[1].revents & POLLIN) {
-			r = read(pollfd[1].fd, &tmp_chr, 1);
-			TEST_ASSERT(r == 1,
-				    "Error reading pipefd in UFFD thread\n");
-			return NULL;
-		}
-
-		if (!(pollfd[0].revents & POLLIN))
-			continue;
-
-		r = read(uffd, &msg, sizeof(msg));
-		if (r == -1) {
-			if (errno == EAGAIN)
-				continue;
-			pr_info("Read of uffd got errno %d\n", errno);
-			return NULL;
-		}
-
-		if (r != sizeof(msg)) {
-			pr_info("Read on uffd returned unexpected size: %d bytes", r);
-			return NULL;
-		}
-
-		if (!(msg.event & UFFD_EVENT_PAGEFAULT))
-			continue;
-
-		if (delay)
-			usleep(delay);
-		addr =  msg.arg.pagefault.address;
-		r = handle_uffd_page_request(uffd_args->uffd_mode, uffd, addr);
-		if (r < 0)
-			return NULL;
-		pages++;
-	}
-
-	ts_diff = timespec_elapsed(start);
-	PER_VCPU_DEBUG("userfaulted %ld pages over %ld.%.9lds. (%f/sec)\n",
-		       pages, ts_diff.tv_sec, ts_diff.tv_nsec,
-		       pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
-
-	return NULL;
-}
-
-static void setup_demand_paging(struct kvm_vm *vm,
-				pthread_t *uffd_handler_thread, int pipefd,
-				int uffd_mode, useconds_t uffd_delay,
-				struct uffd_handler_args *uffd_args,
-				void *hva, void *alias, uint64_t len)
+static void prefault_mem(void *alias, uint64_t len)
 {
-	bool is_minor = (uffd_mode == UFFDIO_REGISTER_MODE_MINOR);
-	int uffd;
-	struct uffdio_api uffdio_api;
-	struct uffdio_register uffdio_register;
-	uint64_t expected_ioctls = ((uint64_t) 1) << _UFFDIO_COPY;
-	int ret;
+	size_t p;
 
-	PER_PAGE_DEBUG("Userfaultfd %s mode, faults resolved with %s\n",
-		       is_minor ? "MINOR" : "MISSING",
-		       is_minor ? "UFFDIO_CONINUE" : "UFFDIO_COPY");
-
-	/* In order to get minor faults, prefault via the alias. */
-	if (is_minor) {
-		size_t p;
-
-		expected_ioctls = ((uint64_t) 1) << _UFFDIO_CONTINUE;
-
-		TEST_ASSERT(alias != NULL, "Alias required for minor faults");
-		for (p = 0; p < (len / demand_paging_size); ++p) {
-			memcpy(alias + (p * demand_paging_size),
-			       guest_data_prototype, demand_paging_size);
-		}
+	TEST_ASSERT(alias != NULL, "Alias required for minor faults");
+	for (p = 0; p < (len / demand_paging_size); ++p) {
+		memcpy(alias + (p * demand_paging_size),
+		       guest_data_prototype, demand_paging_size);
 	}
-
-	uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
-	TEST_ASSERT(uffd >= 0, __KVM_SYSCALL_ERROR("userfaultfd()", uffd));
-
-	uffdio_api.api = UFFD_API;
-	uffdio_api.features = 0;
-	ret = ioctl(uffd, UFFDIO_API, &uffdio_api);
-	TEST_ASSERT(ret != -1, __KVM_SYSCALL_ERROR("UFFDIO_API", ret));
-
-	uffdio_register.range.start = (uint64_t)hva;
-	uffdio_register.range.len = len;
-	uffdio_register.mode = uffd_mode;
-	ret = ioctl(uffd, UFFDIO_REGISTER, &uffdio_register);
-	TEST_ASSERT(ret != -1, __KVM_SYSCALL_ERROR("UFFDIO_REGISTER", ret));
-	TEST_ASSERT((uffdio_register.ioctls & expected_ioctls) ==
-		    expected_ioctls, "missing userfaultfd ioctls");
-
-	uffd_args->uffd_mode = uffd_mode;
-	uffd_args->uffd = uffd;
-	uffd_args->pipefd = pipefd;
-	uffd_args->delay = uffd_delay;
-	pthread_create(uffd_handler_thread, NULL, uffd_handler_thread_fn,
-		       uffd_args);
-
-	PER_VCPU_DEBUG("Created uffd thread for HVA range [%p, %p)\n",
-		       hva, hva + len);
 }
 
-struct test_params {
-	int uffd_mode;
-	useconds_t uffd_delay;
-	enum vm_mem_backing_src_type src_type;
-	bool partition_vcpu_memory_access;
-};
-
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *p = arg;
-	pthread_t *uffd_handler_threads = NULL;
-	struct uffd_handler_args *uffd_args = NULL;
+	struct uffd_desc **uffd_descs = NULL;
 	struct timespec start;
 	struct timespec ts_diff;
-	int *pipefds = NULL;
 	struct kvm_vm *vm;
-	int r, i;
+	int i;
 
 	vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
 				 p->src_type, p->partition_vcpu_memory_access);
@@ -296,15 +146,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	memset(guest_data_prototype, 0xAB, demand_paging_size);
 
 	if (p->uffd_mode) {
-		uffd_handler_threads =
-			malloc(nr_vcpus * sizeof(*uffd_handler_threads));
-		TEST_ASSERT(uffd_handler_threads, "Memory allocation failed");
-
-		uffd_args = malloc(nr_vcpus * sizeof(*uffd_args));
-		TEST_ASSERT(uffd_args, "Memory allocation failed");
-
-		pipefds = malloc(sizeof(int) * nr_vcpus * 2);
-		TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd");
+		uffd_descs = malloc(nr_vcpus * sizeof(struct uffd_desc *));
+		TEST_ASSERT(uffd_descs, "Memory allocation failed");
 
 		for (i = 0; i < nr_vcpus; i++) {
 			struct perf_test_vcpu_args *vcpu_args;
@@ -317,19 +160,17 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 			vcpu_hva = addr_gpa2hva(vm, vcpu_args->gpa);
 			vcpu_alias = addr_gpa2alias(vm, vcpu_args->gpa);
 
+			prefault_mem(vcpu_alias,
+				vcpu_args->pages * perf_test_args.guest_page_size);
+
 			/*
 			 * Set up user fault fd to handle demand paging
 			 * requests.
 			 */
-			r = pipe2(&pipefds[i * 2],
-				  O_CLOEXEC | O_NONBLOCK);
-			TEST_ASSERT(!r, "Failed to set up pipefd");
-
-			setup_demand_paging(vm, &uffd_handler_threads[i],
-					    pipefds[i * 2], p->uffd_mode,
-					    p->uffd_delay, &uffd_args[i],
-					    vcpu_hva, vcpu_alias,
-					    vcpu_args->pages * perf_test_args.guest_page_size);
+			uffd_descs[i] = uffd_setup_demand_paging(
+				p->uffd_mode, p->uffd_delay, vcpu_hva,
+				vcpu_args->pages * perf_test_args.guest_page_size,
+				&handle_uffd_page_request);
 		}
 	}
 
@@ -344,15 +185,9 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	pr_info("All vCPU threads joined\n");
 
 	if (p->uffd_mode) {
-		char c;
-
 		/* Tell the user fault fd handler threads to quit */
-		for (i = 0; i < nr_vcpus; i++) {
-			r = write(pipefds[i * 2 + 1], &c, 1);
-			TEST_ASSERT(r == 1, "Unable to write to pipefd");
-
-			pthread_join(uffd_handler_threads[i], NULL);
-		}
+		for (i = 0; i < nr_vcpus; i++)
+			uffd_stop_demand_paging(uffd_descs[i]);
 	}
 
 	pr_info("Total guest execution time: %ld.%.9lds\n",
@@ -364,11 +199,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	perf_test_destroy_vm(vm);
 
 	free(guest_data_prototype);
-	if (p->uffd_mode) {
-		free(uffd_handler_threads);
-		free(uffd_args);
-		free(pipefds);
-	}
+	if (p->uffd_mode)
+		free(uffd_descs);
 }
 
 static void help(char *name)
diff --git a/tools/testing/selftests/kvm/include/userfaultfd_util.h b/tools/testing/selftests/kvm/include/userfaultfd_util.h
new file mode 100644
index 000000000000..877449c34592
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/userfaultfd_util.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * KVM userfaultfd util
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ * Copyright (C) 2019-2022 Google LLC
+ */
+
+#define _GNU_SOURCE /* for pipe2 */
+
+#include <inttypes.h>
+#include <time.h>
+#include <pthread.h>
+#include <linux/userfaultfd.h>
+
+#include "test_util.h"
+
+typedef int (*uffd_handler_t)(int uffd_mode, int uffd, struct uffd_msg *msg);
+
+struct uffd_desc {
+	int uffd_mode;
+	int uffd;
+	int pipefds[2];
+	useconds_t delay;
+	uffd_handler_t handler;
+	pthread_t thread;
+};
+
+struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay,
+					   void *hva, uint64_t len,
+					   uffd_handler_t handler);
+
+void uffd_stop_demand_paging(struct uffd_desc *uffd);
+
+#ifdef PRINT_PER_PAGE_UPDATES
+#define PER_PAGE_DEBUG(...) printf(__VA_ARGS__)
+#else
+#define PER_PAGE_DEBUG(...) _no_printf(__VA_ARGS__)
+#endif
+
+#ifdef PRINT_PER_VCPU_UPDATES
+#define PER_VCPU_DEBUG(...) printf(__VA_ARGS__)
+#else
+#define PER_VCPU_DEBUG(...) _no_printf(__VA_ARGS__)
+#endif
diff --git a/tools/testing/selftests/kvm/lib/userfaultfd_util.c b/tools/testing/selftests/kvm/lib/userfaultfd_util.c
new file mode 100644
index 000000000000..3b44846fc277
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/userfaultfd_util.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * KVM userfaultfd util
+ * Adapted from demand_paging_test.c
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ * Copyright (C) 2019-2022 Google LLC
+ */
+
+#define _GNU_SOURCE /* for pipe2 */
+
+#include <inttypes.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <time.h>
+#include <poll.h>
+#include <pthread.h>
+#include <linux/userfaultfd.h>
+#include <sys/syscall.h>
+
+#include "kvm_util.h"
+#include "test_util.h"
+#include "perf_test_util.h"
+#include "userfaultfd_util.h"
+
+#ifdef __NR_userfaultfd
+
+static void *uffd_handler_thread_fn(void *arg)
+{
+	struct uffd_desc *uffd_desc = (struct uffd_desc *)arg;
+	int uffd = uffd_desc->uffd;
+	int pipefd = uffd_desc->pipefds[0];
+	useconds_t delay = uffd_desc->delay;
+	int64_t pages = 0;
+	struct timespec start;
+	struct timespec ts_diff;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	while (1) {
+		struct uffd_msg msg;
+		struct pollfd pollfd[2];
+		char tmp_chr;
+		int r;
+
+		pollfd[0].fd = uffd;
+		pollfd[0].events = POLLIN;
+		pollfd[1].fd = pipefd;
+		pollfd[1].events = POLLIN;
+
+		r = poll(pollfd, 2, -1);
+		switch (r) {
+		case -1:
+			pr_info("poll err");
+			continue;
+		case 0:
+			continue;
+		case 1:
+			break;
+		default:
+			pr_info("Polling uffd returned %d", r);
+			return NULL;
+		}
+
+		if (pollfd[0].revents & POLLERR) {
+			pr_info("uffd revents has POLLERR");
+			return NULL;
+		}
+
+		if (pollfd[1].revents & POLLIN) {
+			r = read(pollfd[1].fd, &tmp_chr, 1);
+			TEST_ASSERT(r == 1,
+				    "Error reading pipefd in UFFD thread\n");
+			return NULL;
+		}
+
+		if (!(pollfd[0].revents & POLLIN))
+			continue;
+
+		r = read(uffd, &msg, sizeof(msg));
+		if (r == -1) {
+			if (errno == EAGAIN)
+				continue;
+			pr_info("Read of uffd got errno %d\n", errno);
+			return NULL;
+		}
+
+		if (r != sizeof(msg)) {
+			pr_info("Read on uffd returned unexpected size: %d bytes", r);
+			return NULL;
+		}
+
+		if (!(msg.event & UFFD_EVENT_PAGEFAULT))
+			continue;
+
+		if (delay)
+			usleep(delay);
+		r = uffd_desc->handler(uffd_desc->uffd_mode, uffd, &msg);
+		if (r < 0)
+			return NULL;
+		pages++;
+	}
+
+	ts_diff = timespec_elapsed(start);
+	PER_VCPU_DEBUG("userfaulted %ld pages over %ld.%.9lds. (%f/sec)\n",
+		       pages, ts_diff.tv_sec, ts_diff.tv_nsec,
+		       pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
+
+	return NULL;
+}
+
+struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay,
+					   void *hva, uint64_t len,
+					   uffd_handler_t handler)
+{
+	struct uffd_desc *uffd_desc;
+	bool is_minor = (uffd_mode == UFFDIO_REGISTER_MODE_MINOR);
+	int uffd;
+	struct uffdio_api uffdio_api;
+	struct uffdio_register uffdio_register;
+	uint64_t expected_ioctls = ((uint64_t) 1) << _UFFDIO_COPY;
+	int ret;
+
+	PER_PAGE_DEBUG("Userfaultfd %s mode, faults resolved with %s\n",
+		       is_minor ? "MINOR" : "MISSING",
+		       is_minor ? "UFFDIO_CONINUE" : "UFFDIO_COPY");
+
+	uffd_desc = malloc(sizeof(struct uffd_desc));
+	TEST_ASSERT(uffd_desc, "malloc failed");
+
+	/* In order to get minor faults, prefault via the alias. */
+	if (is_minor)
+		expected_ioctls = ((uint64_t) 1) << _UFFDIO_CONTINUE;
+
+	uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
+	TEST_ASSERT(uffd >= 0, "uffd creation failed, errno: %d", errno);
+
+	uffdio_api.api = UFFD_API;
+	uffdio_api.features = 0;
+	TEST_ASSERT(ioctl(uffd, UFFDIO_API, &uffdio_api) != -1,
+		    "ioctl UFFDIO_API failed: %" PRIu64,
+		    (uint64_t)uffdio_api.api);
+
+	uffdio_register.range.start = (uint64_t)hva;
+	uffdio_register.range.len = len;
+	uffdio_register.mode = uffd_mode;
+	TEST_ASSERT(ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) != -1,
+		    "ioctl UFFDIO_REGISTER failed");
+	TEST_ASSERT((uffdio_register.ioctls & expected_ioctls) ==
+		    expected_ioctls, "missing userfaultfd ioctls");
+
+	ret = pipe2(uffd_desc->pipefds, O_CLOEXEC | O_NONBLOCK);
+	TEST_ASSERT(!ret, "Failed to set up pipefd");
+
+	uffd_desc->uffd_mode = uffd_mode;
+	uffd_desc->uffd = uffd;
+	uffd_desc->delay = delay;
+	uffd_desc->handler = handler;
+	pthread_create(&uffd_desc->thread, NULL, uffd_handler_thread_fn,
+		       uffd_desc);
+
+	PER_VCPU_DEBUG("Created uffd thread for HVA range [%p, %p)\n",
+		       hva, hva + len);
+
+	return uffd_desc;
+}
+
+void uffd_stop_demand_paging(struct uffd_desc *uffd)
+{
+	char c = 0;
+	int ret;
+
+	ret = write(uffd->pipefds[1], &c, 1);
+	TEST_ASSERT(ret == 1, "Unable to write to pipefd");
+
+	ret = pthread_join(uffd->thread, NULL);
+	TEST_ASSERT(ret == 0, "Pthread_join failed.");
+
+	close(uffd->uffd);
+
+	close(uffd->pipefds[1]);
+	close(uffd->pipefds[0]);
+
+	free(uffd);
+}
+
+#endif /* __NR_userfaultfd */
-- 
cgit v1.2.3


From 228f324dc718f702e8777164c4e2e7426824fb13 Mon Sep 17 00:00:00 2001
From: Ricardo Koller <ricarkol@google.com>
Date: Mon, 17 Oct 2022 19:58:22 +0000
Subject: KVM: selftests: aarch64: Add virt_get_pte_hva() library function

Add a library function to get the PTE (a host virtual address) of a
given GVA.  This will be used in a future commit by a test to clear and
check the access flag of a particular page.

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Reviewed-by: Andrew Jones <andrew.jones@linux.dev>
Signed-off-by: Ricardo Koller <ricarkol@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221017195834.2295901-3-ricarkol@google.com
---
 tools/testing/selftests/kvm/include/aarch64/processor.h |  2 ++
 tools/testing/selftests/kvm/lib/aarch64/processor.c     | 13 ++++++++++---
 2 files changed, 12 insertions(+), 3 deletions(-)

(limited to 'tools/testing/selftests/kvm/lib')

diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
index a8124f9dd68a..df4bfac69551 100644
--- a/tools/testing/selftests/kvm/include/aarch64/processor.h
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -109,6 +109,8 @@ void vm_install_exception_handler(struct kvm_vm *vm,
 void vm_install_sync_handler(struct kvm_vm *vm,
 		int vector, int ec, handler_fn handler);
 
+uint64_t *virt_get_pte_hva(struct kvm_vm *vm, vm_vaddr_t gva);
+
 static inline void cpu_relax(void)
 {
 	asm volatile("yield" ::: "memory");
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 6f5551368944..63ef3c78e55e 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -138,7 +138,7 @@ void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
 	_virt_pg_map(vm, vaddr, paddr, attr_idx);
 }
 
-vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
+uint64_t *virt_get_pte_hva(struct kvm_vm *vm, vm_vaddr_t gva)
 {
 	uint64_t *ptep;
 
@@ -169,11 +169,18 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 		TEST_FAIL("Page table levels must be 2, 3, or 4");
 	}
 
-	return pte_addr(vm, *ptep) + (gva & (vm->page_size - 1));
+	return ptep;
 
 unmapped_gva:
 	TEST_FAIL("No mapping for vm virtual address, gva: 0x%lx", gva);
-	exit(1);
+	exit(EXIT_FAILURE);
+}
+
+vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+	uint64_t *ptep = virt_get_pte_hva(vm, gva);
+
+	return pte_addr(vm, *ptep) + (gva & (vm->page_size - 1));
 }
 
 static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, uint64_t page, int level)
-- 
cgit v1.2.3


From b6b03b86c0250a80b671313dbc0d7bcdbab78f41 Mon Sep 17 00:00:00 2001
From: Ricardo Koller <ricarkol@google.com>
Date: Mon, 17 Oct 2022 19:58:23 +0000
Subject: KVM: selftests: Add missing close and munmap in
 __vm_mem_region_delete()

Deleting a memslot (when freeing a VM) is not closing the backing fd,
nor it's unmapping the alias mapping. Fix by adding the missing close
and munmap.

Reviewed-by: Andrew Jones <andrew.jones@linux.dev>
Reviewed-by: Oliver Upton <oupton@google.com>
Reviewed-by: Ben Gardon <bgardon@google.com>
Signed-off-by: Ricardo Koller <ricarkol@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221017195834.2295901-4-ricarkol@google.com
---
 tools/testing/selftests/kvm/lib/kvm_util.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'tools/testing/selftests/kvm/lib')

diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index f1cb1627161f..19e37fb7de7c 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -586,6 +586,12 @@ static void __vm_mem_region_delete(struct kvm_vm *vm,
 	sparsebit_free(&region->unused_phy_pages);
 	ret = munmap(region->mmap_start, region->mmap_size);
 	TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret));
+	if (region->fd >= 0) {
+		/* There's an extra map when using shared memory. */
+		ret = munmap(region->mmap_alias, region->mmap_size);
+		TEST_ASSERT(!ret, __KVM_SYSCALL_ERROR("munmap()", ret));
+		close(region->fd);
+	}
 
 	free(region);
 }
-- 
cgit v1.2.3


From 41f5189ea9c08f7fc28340a7aefc93d0d2dcb769 Mon Sep 17 00:00:00 2001
From: Ricardo Koller <ricarkol@google.com>
Date: Mon, 17 Oct 2022 19:58:24 +0000
Subject: KVM: selftests: aarch64: Construct DEFAULT_MAIR_EL1 using sysreg.h
 macros

Define macros for memory type indexes and construct DEFAULT_MAIR_EL1
with macros from asm/sysreg.h.  The index macros can then be used when
constructing PTEs (instead of using raw numbers).

Reviewed-by: Andrew Jones <andrew.jones@linux.dev>
Reviewed-by: Oliver Upton <oupton@google.com>
Signed-off-by: Ricardo Koller <ricarkol@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221017195834.2295901-5-ricarkol@google.com
---
 .../selftests/kvm/include/aarch64/processor.h      | 25 ++++++++++++++++------
 .../testing/selftests/kvm/lib/aarch64/processor.c  |  2 +-
 2 files changed, 20 insertions(+), 7 deletions(-)

(limited to 'tools/testing/selftests/kvm/lib')

diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
index df4bfac69551..c1ddca8db225 100644
--- a/tools/testing/selftests/kvm/include/aarch64/processor.h
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -38,12 +38,25 @@
  * NORMAL             4     1111:1111
  * NORMAL_WT          5     1011:1011
  */
-#define DEFAULT_MAIR_EL1 ((0x00ul << (0 * 8)) | \
-			  (0x04ul << (1 * 8)) | \
-			  (0x0cul << (2 * 8)) | \
-			  (0x44ul << (3 * 8)) | \
-			  (0xfful << (4 * 8)) | \
-			  (0xbbul << (5 * 8)))
+
+/* Linux doesn't use these memory types, so let's define them. */
+#define MAIR_ATTR_DEVICE_GRE	UL(0x0c)
+#define MAIR_ATTR_NORMAL_WT	UL(0xbb)
+
+#define MT_DEVICE_nGnRnE	0
+#define MT_DEVICE_nGnRE		1
+#define MT_DEVICE_GRE		2
+#define MT_NORMAL_NC		3
+#define MT_NORMAL		4
+#define MT_NORMAL_WT		5
+
+#define DEFAULT_MAIR_EL1							\
+	(MAIR_ATTRIDX(MAIR_ATTR_DEVICE_nGnRnE, MT_DEVICE_nGnRnE) |		\
+	 MAIR_ATTRIDX(MAIR_ATTR_DEVICE_nGnRE, MT_DEVICE_nGnRE) |		\
+	 MAIR_ATTRIDX(MAIR_ATTR_DEVICE_GRE, MT_DEVICE_GRE) |			\
+	 MAIR_ATTRIDX(MAIR_ATTR_NORMAL_NC, MT_NORMAL_NC) |			\
+	 MAIR_ATTRIDX(MAIR_ATTR_NORMAL, MT_NORMAL) |				\
+	 MAIR_ATTRIDX(MAIR_ATTR_NORMAL_WT, MT_NORMAL_WT))
 
 #define MPIDR_HWID_BITMASK (0xff00fffffful)
 
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 63ef3c78e55e..26f0eccff6fe 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -133,7 +133,7 @@ static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 
 void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
 {
-	uint64_t attr_idx = 4; /* NORMAL (See DEFAULT_MAIR_EL1) */
+	uint64_t attr_idx = MT_NORMAL;
 
 	_virt_pg_map(vm, vaddr, paddr, attr_idx);
 }
-- 
cgit v1.2.3


From bd3ed7e1a47eb7b3838ca09439f1eb289ec3be1f Mon Sep 17 00:00:00 2001
From: Ricardo Koller <ricarkol@google.com>
Date: Mon, 17 Oct 2022 19:58:26 +0000
Subject: KVM: selftests: Stash backing_src_type in struct userspace_mem_region

Add the backing_src_type into struct userspace_mem_region. This struct
already stores a lot of info about memory regions, except the backing
source type.  This info will be used by a future commit in order to
determine the method for punching a hole.

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Signed-off-by: Ricardo Koller <ricarkol@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221017195834.2295901-7-ricarkol@google.com
---
 tools/testing/selftests/kvm/include/kvm_util_base.h | 1 +
 tools/testing/selftests/kvm/lib/kvm_util.c          | 1 +
 2 files changed, 2 insertions(+)

(limited to 'tools/testing/selftests/kvm/lib')

diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index e42a09cd24a0..a9264ed22cca 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -34,6 +34,7 @@ struct userspace_mem_region {
 	struct sparsebit *unused_phy_pages;
 	int fd;
 	off_t offset;
+	enum vm_mem_backing_src_type backing_src_type;
 	void *host_mem;
 	void *host_alias;
 	void *mmap_start;
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 19e37fb7de7c..6affce47e899 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -929,6 +929,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm,
 			    vm_mem_backing_src_alias(src_type)->name);
 	}
 
+	region->backing_src_type = src_type;
 	region->unused_phy_pages = sparsebit_alloc();
 	sparsebit_set_num(region->unused_phy_pages,
 		guest_paddr >> vm->page_shift, npages);
-- 
cgit v1.2.3


From 290c5b54012b7f05e9c51af32d557574bf69a654 Mon Sep 17 00:00:00 2001
From: Ricardo Koller <ricarkol@google.com>
Date: Mon, 17 Oct 2022 19:58:27 +0000
Subject: KVM: selftests: Add vm->memslots[] and enum kvm_mem_region_type

The vm_create() helpers are hardcoded to place most page types (code,
page-tables, stacks, etc) in the same memslot #0, and always backed with
anonymous 4K.  There are a couple of issues with that.  First, tests
willing to differ a bit, like placing page-tables in a different backing
source type must replicate much of what's already done by the vm_create()
functions.  Second, the hardcoded assumption of memslot #0 holding most
things is spread everywhere; this makes it very hard to change.

Fix the above issues by having selftests specify how they want memory to be
laid out. Start by changing ____vm_create() to not create memslot #0; a
test (to come) will specify all memslots used by the VM.  Then, add the
vm->memslots[] array to specify the right memslot for different memory
allocators, e.g.,: lib/elf should use the vm->[MEM_REGION_CODE] memslot.
This will be used as a way to specify the page-tables memslots (to be
backed by huge pages for example).

There is no functional change intended. The current commit lays out memory
exactly as before. A future commit will change the allocators to get the
region they should be using, e.g.,: like the page table allocators using
the pt memslot.

Cc: Sean Christopherson <seanjc@google.com>
Cc: Andrew Jones <andrew.jones@linux.dev>
Signed-off-by: Ricardo Koller <ricarkol@google.com>
Reviewed-by: Andrew Jones <andrew.jones@linux.dev>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221017195834.2295901-8-ricarkol@google.com
---
 .../testing/selftests/kvm/include/kvm_util_base.h  | 26 ++++++++++++++++++++--
 tools/testing/selftests/kvm/lib/kvm_util.c         | 18 ++++++++-------
 2 files changed, 34 insertions(+), 10 deletions(-)

(limited to 'tools/testing/selftests/kvm/lib')

diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index a9264ed22cca..6442aa9e9061 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -65,6 +65,14 @@ struct userspace_mem_regions {
 	DECLARE_HASHTABLE(slot_hash, 9);
 };
 
+enum kvm_mem_region_type {
+	MEM_REGION_CODE,
+	MEM_REGION_DATA,
+	MEM_REGION_PT,
+	MEM_REGION_TEST_DATA,
+	NR_MEM_REGIONS,
+};
+
 struct kvm_vm {
 	int mode;
 	unsigned long type;
@@ -93,6 +101,13 @@ struct kvm_vm {
 	int stats_fd;
 	struct kvm_stats_header stats_header;
 	struct kvm_stats_desc *stats_desc;
+
+	/*
+	 * KVM region slots. These are the default memslots used by page
+	 * allocators, e.g., lib/elf uses the memslots[MEM_REGION_CODE]
+	 * memslot.
+	 */
+	uint32_t memslots[NR_MEM_REGIONS];
 };
 
 
@@ -105,6 +120,13 @@ struct kvm_vm {
 struct userspace_mem_region *
 memslot2region(struct kvm_vm *vm, uint32_t memslot);
 
+static inline struct userspace_mem_region *vm_get_mem_region(struct kvm_vm *vm,
+							     enum kvm_mem_region_type type)
+{
+	assert(type < NR_MEM_REGIONS);
+	return memslot2region(vm, vm->memslots[type]);
+}
+
 /* Minimum allocated guest virtual and physical addresses */
 #define KVM_UTIL_MIN_VADDR		0x2000
 #define KVM_GUEST_PAGE_TABLE_MIN_PADDR	0x180000
@@ -647,13 +669,13 @@ vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm);
  * __vm_create() does NOT create vCPUs, @nr_runnable_vcpus is used purely to
  * calculate the amount of memory needed for per-vCPU data, e.g. stacks.
  */
-struct kvm_vm *____vm_create(enum vm_guest_mode mode, uint64_t nr_pages);
+struct kvm_vm *____vm_create(enum vm_guest_mode mode);
 struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus,
 			   uint64_t nr_extra_pages);
 
 static inline struct kvm_vm *vm_create_barebones(void)
 {
-	return ____vm_create(VM_MODE_DEFAULT, 0);
+	return ____vm_create(VM_MODE_DEFAULT);
 }
 
 static inline struct kvm_vm *vm_create(uint32_t nr_runnable_vcpus)
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 6affce47e899..f3dfa4e9ee0f 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -185,13 +185,10 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = {
 _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
 	       "Missing new mode params?");
 
-struct kvm_vm *____vm_create(enum vm_guest_mode mode, uint64_t nr_pages)
+struct kvm_vm *____vm_create(enum vm_guest_mode mode)
 {
 	struct kvm_vm *vm;
 
-	pr_debug("%s: mode='%s' pages='%ld'\n", __func__,
-		 vm_guest_mode_string(mode), nr_pages);
-
 	vm = calloc(1, sizeof(*vm));
 	TEST_ASSERT(vm != NULL, "Insufficient Memory");
 
@@ -287,9 +284,6 @@ struct kvm_vm *____vm_create(enum vm_guest_mode mode, uint64_t nr_pages)
 
 	/* Allocate and setup memory for guest. */
 	vm->vpages_mapped = sparsebit_alloc();
-	if (nr_pages != 0)
-		vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
-					    0, 0, nr_pages, 0);
 
 	return vm;
 }
@@ -335,8 +329,16 @@ struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus,
 	uint64_t nr_pages = vm_nr_pages_required(mode, nr_runnable_vcpus,
 						 nr_extra_pages);
 	struct kvm_vm *vm;
+	int i;
+
+	pr_debug("%s: mode='%s' pages='%ld'\n", __func__,
+		 vm_guest_mode_string(mode), nr_pages);
+
+	vm = ____vm_create(mode);
 
-	vm = ____vm_create(mode, nr_pages);
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, 0, 0, nr_pages, 0);
+	for (i = 0; i < NR_MEM_REGIONS; i++)
+		vm->memslots[i] = 0;
 
 	kvm_vm_elf_load(vm, program_invocation_name);
 
-- 
cgit v1.2.3


From 5485e822e31a75dfac3713d94b6b22025d4895da Mon Sep 17 00:00:00 2001
From: Ricardo Koller <ricarkol@google.com>
Date: Mon, 17 Oct 2022 19:58:28 +0000
Subject: KVM: selftests: Fix alignment in virt_arch_pgd_alloc() and
 vm_vaddr_alloc()

Refactor virt_arch_pgd_alloc() and vm_vaddr_alloc() in both RISC-V and
aarch64 to fix the alignment of parameters in a couple of calls. This will
make it easier to fix the alignment in a future commit that adds an extra
parameter (that happens to be very long).

No functional change intended.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Ricardo Koller <ricarkol@google.com>
Reviewed-by: Andrew Jones <andrew.jones@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221017195834.2295901-9-ricarkol@google.com
---
 .../testing/selftests/kvm/lib/aarch64/processor.c  | 27 ++++++++++++----------
 tools/testing/selftests/kvm/lib/riscv/processor.c  | 27 ++++++++++++----------
 2 files changed, 30 insertions(+), 24 deletions(-)

(limited to 'tools/testing/selftests/kvm/lib')

diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 26f0eccff6fe..6ff2b9d6cea6 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -76,13 +76,14 @@ static uint64_t __maybe_unused ptrs_per_pte(struct kvm_vm *vm)
 
 void virt_arch_pgd_alloc(struct kvm_vm *vm)
 {
-	if (!vm->pgd_created) {
-		vm_paddr_t paddr = vm_phy_pages_alloc(vm,
-			page_align(vm, ptrs_per_pgd(vm) * 8) / vm->page_size,
-			KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0);
-		vm->pgd = paddr;
-		vm->pgd_created = true;
-	}
+	size_t nr_pages = page_align(vm, ptrs_per_pgd(vm) * 8) / vm->page_size;
+
+	if (vm->pgd_created)
+		return;
+
+	vm->pgd = vm_phy_pages_alloc(vm, nr_pages,
+				     KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0);
+	vm->pgd_created = true;
 }
 
 static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
@@ -325,13 +326,15 @@ void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent)
 struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 				  struct kvm_vcpu_init *init, void *guest_code)
 {
-	size_t stack_size = vm->page_size == 4096 ?
-					DEFAULT_STACK_PGS * vm->page_size :
-					vm->page_size;
-	uint64_t stack_vaddr = vm_vaddr_alloc(vm, stack_size,
-					      DEFAULT_ARM64_GUEST_STACK_VADDR_MIN);
+	size_t stack_size;
+	uint64_t stack_vaddr;
 	struct kvm_vcpu *vcpu = __vm_vcpu_add(vm, vcpu_id);
 
+	stack_size = vm->page_size == 4096 ? DEFAULT_STACK_PGS * vm->page_size :
+					     vm->page_size;
+	stack_vaddr = vm_vaddr_alloc(vm, stack_size,
+				     DEFAULT_ARM64_GUEST_STACK_VADDR_MIN);
+
 	aarch64_vcpu_setup(vcpu, init);
 
 	vcpu_set_reg(vcpu, ARM64_CORE_REG(sp_el1), stack_vaddr + stack_size);
diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c
index 604478151212..ac7fc9d317db 100644
--- a/tools/testing/selftests/kvm/lib/riscv/processor.c
+++ b/tools/testing/selftests/kvm/lib/riscv/processor.c
@@ -55,13 +55,14 @@ static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva, int level)
 
 void virt_arch_pgd_alloc(struct kvm_vm *vm)
 {
-	if (!vm->pgd_created) {
-		vm_paddr_t paddr = vm_phy_pages_alloc(vm,
-			page_align(vm, ptrs_per_pte(vm) * 8) / vm->page_size,
-			KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0);
-		vm->pgd = paddr;
-		vm->pgd_created = true;
-	}
+	size_t nr_pages = page_align(vm, ptrs_per_pte(vm) * 8) / vm->page_size;
+
+	if (vm->pgd_created)
+		return;
+
+	vm->pgd = vm_phy_pages_alloc(vm, nr_pages,
+				     KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0);
+	vm->pgd_created = true;
 }
 
 void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
@@ -279,15 +280,17 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 				  void *guest_code)
 {
 	int r;
-	size_t stack_size = vm->page_size == 4096 ?
-					DEFAULT_STACK_PGS * vm->page_size :
-					vm->page_size;
-	unsigned long stack_vaddr = vm_vaddr_alloc(vm, stack_size,
-					DEFAULT_RISCV_GUEST_STACK_VADDR_MIN);
+	size_t stack_size;
+	unsigned long stack_vaddr;
 	unsigned long current_gp = 0;
 	struct kvm_mp_state mps;
 	struct kvm_vcpu *vcpu;
 
+	stack_size = vm->page_size == 4096 ? DEFAULT_STACK_PGS * vm->page_size :
+					     vm->page_size;
+	stack_vaddr = vm_vaddr_alloc(vm, stack_size,
+				     DEFAULT_RISCV_GUEST_STACK_VADDR_MIN);
+
 	vcpu = __vm_vcpu_add(vm, vcpu_id);
 	riscv_vcpu_mmu_setup(vcpu);
 
-- 
cgit v1.2.3


From 1446e331432d7f24ed56b870ad605a4345fee43f Mon Sep 17 00:00:00 2001
From: Ricardo Koller <ricarkol@google.com>
Date: Mon, 17 Oct 2022 19:58:29 +0000
Subject: KVM: selftests: Use the right memslot for code, page-tables, and data
 allocations

Now that kvm_vm allows specifying different memslots for code, page tables,
and data, use the appropriate memslot when making allocations in
common/libraty code. Change them accordingly:

- code (allocated by lib/elf) use the CODE memslot
- stacks, exception tables, and other core data pages (like the TSS in x86)
  use the DATA memslot
- page tables and the PGD use the PT memslot
- test data (anything allocated with vm_vaddr_alloc()) uses the TEST_DATA
  memslot

No functional change intended. All allocators keep using memslot #0.

Cc: Sean Christopherson <seanjc@google.com>
Cc: Andrew Jones <andrew.jones@linux.dev>
Signed-off-by: Ricardo Koller <ricarkol@google.com>
Reviewed-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Andrew Jones <andrew.jones@linux.dev>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221017195834.2295901-10-ricarkol@google.com
---
 .../testing/selftests/kvm/include/kvm_util_base.h  |  4 ++
 .../testing/selftests/kvm/lib/aarch64/processor.c  | 12 +++--
 tools/testing/selftests/kvm/lib/elf.c              |  3 +-
 tools/testing/selftests/kvm/lib/kvm_util.c         | 57 +++++++++++++---------
 tools/testing/selftests/kvm/lib/riscv/processor.c  |  8 +--
 tools/testing/selftests/kvm/lib/s390x/processor.c  |  8 +--
 tools/testing/selftests/kvm/lib/x86_64/processor.c | 13 ++---
 7 files changed, 65 insertions(+), 40 deletions(-)

(limited to 'tools/testing/selftests/kvm/lib')

diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index 6442aa9e9061..b0da75af1ff3 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -407,7 +407,11 @@ void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa);
 void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot);
 struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id);
 vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min);
+vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
+			    enum kvm_mem_region_type type);
 vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages);
+vm_vaddr_t __vm_vaddr_alloc_page(struct kvm_vm *vm,
+				 enum kvm_mem_region_type type);
 vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm);
 
 void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 6ff2b9d6cea6..2883dfd1ad49 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -82,7 +82,8 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm)
 		return;
 
 	vm->pgd = vm_phy_pages_alloc(vm, nr_pages,
-				     KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0);
+				     KVM_GUEST_PAGE_TABLE_MIN_PADDR,
+				     vm->memslots[MEM_REGION_PT]);
 	vm->pgd_created = true;
 }
 
@@ -332,8 +333,9 @@ struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 
 	stack_size = vm->page_size == 4096 ? DEFAULT_STACK_PGS * vm->page_size :
 					     vm->page_size;
-	stack_vaddr = vm_vaddr_alloc(vm, stack_size,
-				     DEFAULT_ARM64_GUEST_STACK_VADDR_MIN);
+	stack_vaddr = __vm_vaddr_alloc(vm, stack_size,
+				       DEFAULT_ARM64_GUEST_STACK_VADDR_MIN,
+				       MEM_REGION_DATA);
 
 	aarch64_vcpu_setup(vcpu, init);
 
@@ -438,8 +440,8 @@ unexpected_exception:
 
 void vm_init_descriptor_tables(struct kvm_vm *vm)
 {
-	vm->handlers = vm_vaddr_alloc(vm, sizeof(struct handlers),
-			vm->page_size);
+	vm->handlers = __vm_vaddr_alloc(vm, sizeof(struct handlers),
+					vm->page_size, MEM_REGION_DATA);
 
 	*(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers;
 }
diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c
index 9f54c098d9d0..51f280c412ba 100644
--- a/tools/testing/selftests/kvm/lib/elf.c
+++ b/tools/testing/selftests/kvm/lib/elf.c
@@ -161,7 +161,8 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename)
 		seg_vend |= vm->page_size - 1;
 		size_t seg_size = seg_vend - seg_vstart + 1;
 
-		vm_vaddr_t vaddr = vm_vaddr_alloc(vm, seg_size, seg_vstart);
+		vm_vaddr_t vaddr = __vm_vaddr_alloc(vm, seg_size, seg_vstart,
+						    MEM_REGION_CODE);
 		TEST_ASSERT(vaddr == seg_vstart, "Unable to allocate "
 			"virtual memory for segment at requested min addr,\n"
 			"  segment idx: %u\n"
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index f3dfa4e9ee0f..5ad4acaec8e0 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -1226,32 +1226,15 @@ va_found:
 	return pgidx_start * vm->page_size;
 }
 
-/*
- * VM Virtual Address Allocate
- *
- * Input Args:
- *   vm - Virtual Machine
- *   sz - Size in bytes
- *   vaddr_min - Minimum starting virtual address
- *
- * Output Args: None
- *
- * Return:
- *   Starting guest virtual address
- *
- * Allocates at least sz bytes within the virtual address space of the vm
- * given by vm.  The allocated bytes are mapped to a virtual address >=
- * the address given by vaddr_min.  Note that each allocation uses a
- * a unique set of pages, with the minimum real allocation being at least
- * a page.
- */
-vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min)
+vm_vaddr_t __vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
+			    enum kvm_mem_region_type type)
 {
 	uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0);
 
 	virt_pgd_alloc(vm);
 	vm_paddr_t paddr = vm_phy_pages_alloc(vm, pages,
-					      KVM_UTIL_MIN_PFN * vm->page_size, 0);
+					      KVM_UTIL_MIN_PFN * vm->page_size,
+					      vm->memslots[type]);
 
 	/*
 	 * Find an unused range of virtual page addresses of at least
@@ -1272,6 +1255,30 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min)
 	return vaddr_start;
 }
 
+/*
+ * VM Virtual Address Allocate
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   sz - Size in bytes
+ *   vaddr_min - Minimum starting virtual address
+ *
+ * Output Args: None
+ *
+ * Return:
+ *   Starting guest virtual address
+ *
+ * Allocates at least sz bytes within the virtual address space of the vm
+ * given by vm.  The allocated bytes are mapped to a virtual address >=
+ * the address given by vaddr_min.  Note that each allocation uses a
+ * a unique set of pages, with the minimum real allocation being at least
+ * a page. The allocated physical space comes from the TEST_DATA memory region.
+ */
+vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min)
+{
+	return __vm_vaddr_alloc(vm, sz, vaddr_min, MEM_REGION_TEST_DATA);
+}
+
 /*
  * VM Virtual Address Allocate Pages
  *
@@ -1291,6 +1298,11 @@ vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages)
 	return vm_vaddr_alloc(vm, nr_pages * getpagesize(), KVM_UTIL_MIN_VADDR);
 }
 
+vm_vaddr_t __vm_vaddr_alloc_page(struct kvm_vm *vm, enum kvm_mem_region_type type)
+{
+	return __vm_vaddr_alloc(vm, getpagesize(), KVM_UTIL_MIN_VADDR, type);
+}
+
 /*
  * VM Virtual Address Allocate Page
  *
@@ -1856,7 +1868,8 @@ vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min,
 
 vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm)
 {
-	return vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0);
+	return vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR,
+				 vm->memslots[MEM_REGION_PT]);
 }
 
 /*
diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c
index ac7fc9d317db..d146ca71e0c0 100644
--- a/tools/testing/selftests/kvm/lib/riscv/processor.c
+++ b/tools/testing/selftests/kvm/lib/riscv/processor.c
@@ -61,7 +61,8 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm)
 		return;
 
 	vm->pgd = vm_phy_pages_alloc(vm, nr_pages,
-				     KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0);
+				     KVM_GUEST_PAGE_TABLE_MIN_PADDR,
+				     vm->memslots[MEM_REGION_PT]);
 	vm->pgd_created = true;
 }
 
@@ -288,8 +289,9 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 
 	stack_size = vm->page_size == 4096 ? DEFAULT_STACK_PGS * vm->page_size :
 					     vm->page_size;
-	stack_vaddr = vm_vaddr_alloc(vm, stack_size,
-				     DEFAULT_RISCV_GUEST_STACK_VADDR_MIN);
+	stack_vaddr = __vm_vaddr_alloc(vm, stack_size,
+				       DEFAULT_RISCV_GUEST_STACK_VADDR_MIN,
+				       MEM_REGION_DATA);
 
 	vcpu = __vm_vcpu_add(vm, vcpu_id);
 	riscv_vcpu_mmu_setup(vcpu);
diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c
index 89d7340d9cbd..15945121daf1 100644
--- a/tools/testing/selftests/kvm/lib/s390x/processor.c
+++ b/tools/testing/selftests/kvm/lib/s390x/processor.c
@@ -21,7 +21,8 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm)
 		return;
 
 	paddr = vm_phy_pages_alloc(vm, PAGES_PER_REGION,
-				   KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0);
+				   KVM_GUEST_PAGE_TABLE_MIN_PADDR,
+				   vm->memslots[MEM_REGION_PT]);
 	memset(addr_gpa2hva(vm, paddr), 0xff, PAGES_PER_REGION * vm->page_size);
 
 	vm->pgd = paddr;
@@ -167,8 +168,9 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 	TEST_ASSERT(vm->page_size == 4096, "Unsupported page size: 0x%x",
 		    vm->page_size);
 
-	stack_vaddr = vm_vaddr_alloc(vm, stack_size,
-				     DEFAULT_GUEST_STACK_VADDR_MIN);
+	stack_vaddr = __vm_vaddr_alloc(vm, stack_size,
+				       DEFAULT_GUEST_STACK_VADDR_MIN,
+				       MEM_REGION_DATA);
 
 	vcpu = __vm_vcpu_add(vm, vcpu_id);
 
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 39c4409ef56a..b199dde90e9f 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -552,7 +552,7 @@ unmapped_gva:
 static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt)
 {
 	if (!vm->gdt)
-		vm->gdt = vm_vaddr_alloc_page(vm);
+		vm->gdt = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA);
 
 	dt->base = vm->gdt;
 	dt->limit = getpagesize();
@@ -562,7 +562,7 @@ static void kvm_setup_tss_64bit(struct kvm_vm *vm, struct kvm_segment *segp,
 				int selector)
 {
 	if (!vm->tss)
-		vm->tss = vm_vaddr_alloc_page(vm);
+		vm->tss = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA);
 
 	memset(segp, 0, sizeof(*segp));
 	segp->base = vm->tss;
@@ -647,8 +647,9 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
 	vm_vaddr_t stack_vaddr;
 	struct kvm_vcpu *vcpu;
 
-	stack_vaddr = vm_vaddr_alloc(vm, DEFAULT_STACK_PGS * getpagesize(),
-				     DEFAULT_GUEST_STACK_VADDR_MIN);
+	stack_vaddr = __vm_vaddr_alloc(vm, DEFAULT_STACK_PGS * getpagesize(),
+				       DEFAULT_GUEST_STACK_VADDR_MIN,
+				       MEM_REGION_DATA);
 
 	vcpu = __vm_vcpu_add(vm, vcpu_id);
 	vcpu_init_cpuid(vcpu, kvm_get_supported_cpuid());
@@ -1145,8 +1146,8 @@ void vm_init_descriptor_tables(struct kvm_vm *vm)
 	extern void *idt_handlers;
 	int i;
 
-	vm->idt = vm_vaddr_alloc_page(vm);
-	vm->handlers = vm_vaddr_alloc_page(vm);
+	vm->idt = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA);
+	vm->handlers = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA);
 	/* Handlers have the same address in both address spaces.*/
 	for (i = 0; i < NUM_INTERRUPTS; i++)
 		set_idt_entry(vm, i, (unsigned long)(&idt_handlers)[i], 0,
-- 
cgit v1.2.3


From 9ec1eb1bcceec735fb3c9255cdcdbcc2acf860a0 Mon Sep 17 00:00:00 2001
From: Oliver Upton <oliver.upton@linux.dev>
Date: Fri, 18 Nov 2022 21:15:02 +0000
Subject: KVM: selftests: Have perf_test_util signal when to stop vCPUs

Signal that a test run is complete through perf_test_args instead of
having tests open code a similar solution. Ensure that the field resets
to false at the beginning of a test run as the structure is reused
between test runs, eliminating a couple of bugs:

access_tracking_perf_test hangs indefinitely on a subsequent test run,
as 'done' remains true. The bug doesn't amount to much right now, as x86
supports a single guest mode. However, this is a precondition of
enabling the test for other architectures with >1 guest mode, like
arm64.

memslot_modification_stress_test has the exact opposite problem, where
subsequent test runs complete immediately as 'run_vcpus' remains false.

Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
[oliver: added commit message, preserve spin_wait_for_next_iteration()]
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Reviewed-by: Gavin Shan <gshan@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221118211503.4049023-2-oliver.upton@linux.dev
---
 tools/testing/selftests/kvm/access_tracking_perf_test.c        | 8 +-------
 tools/testing/selftests/kvm/include/perf_test_util.h           | 3 +++
 tools/testing/selftests/kvm/lib/perf_test_util.c               | 3 +++
 tools/testing/selftests/kvm/memslot_modification_stress_test.c | 6 +-----
 4 files changed, 8 insertions(+), 12 deletions(-)

(limited to 'tools/testing/selftests/kvm/lib')

diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c
index 76c583a07ea2..942370d57392 100644
--- a/tools/testing/selftests/kvm/access_tracking_perf_test.c
+++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c
@@ -58,9 +58,6 @@ static enum {
 	ITERATION_MARK_IDLE,
 } iteration_work;
 
-/* Set to true when vCPU threads should exit. */
-static bool done;
-
 /* The iteration that was last completed by each vCPU. */
 static int vcpu_last_completed_iteration[KVM_MAX_VCPUS];
 
@@ -211,7 +208,7 @@ static bool spin_wait_for_next_iteration(int *current_iteration)
 	int last_iteration = *current_iteration;
 
 	do {
-		if (READ_ONCE(done))
+		if (READ_ONCE(perf_test_args.stop_vcpus))
 			return false;
 
 		*current_iteration = READ_ONCE(iteration);
@@ -321,9 +318,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	mark_memory_idle(vm, nr_vcpus);
 	access_memory(vm, nr_vcpus, ACCESS_READ, "Reading from idle memory");
 
-	/* Set done to signal the vCPU threads to exit */
-	done = true;
-
 	perf_test_join_vcpu_threads(nr_vcpus);
 	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 eaa88df0555a..536d7c3c3f14 100644
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ b/tools/testing/selftests/kvm/include/perf_test_util.h
@@ -40,6 +40,9 @@ struct perf_test_args {
 	/* Run vCPUs in L2 instead of L1, if the architecture supports it. */
 	bool nested;
 
+	/* Test is done, stop running vCPUs. */
+	bool stop_vcpus;
+
 	struct perf_test_vcpu_args vcpu_args[KVM_MAX_VCPUS];
 };
 
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/perf_test_util.c
index 9618b37c66f7..ee3f499ccbd2 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/perf_test_util.c
@@ -267,6 +267,7 @@ void perf_test_start_vcpu_threads(int nr_vcpus,
 
 	vcpu_thread_fn = vcpu_fn;
 	WRITE_ONCE(all_vcpu_threads_running, false);
+	WRITE_ONCE(perf_test_args.stop_vcpus, false);
 
 	for (i = 0; i < nr_vcpus; i++) {
 		struct vcpu_thread *vcpu = &vcpu_threads[i];
@@ -289,6 +290,8 @@ void perf_test_join_vcpu_threads(int nr_vcpus)
 {
 	int i;
 
+	WRITE_ONCE(perf_test_args.stop_vcpus, true);
+
 	for (i = 0; i < nr_vcpus; i++)
 		pthread_join(vcpu_threads[i].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 bb1d17a1171b..3a5e4518307c 100644
--- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c
+++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
@@ -34,8 +34,6 @@
 static int nr_vcpus = 1;
 static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
 
-static bool run_vcpus = true;
-
 static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
 {
 	struct kvm_vcpu *vcpu = vcpu_args->vcpu;
@@ -45,7 +43,7 @@ static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
 	run = vcpu->run;
 
 	/* Let the guest access its memory until a stop signal is received */
-	while (READ_ONCE(run_vcpus)) {
+	while (!READ_ONCE(perf_test_args.stop_vcpus)) {
 		ret = _vcpu_run(vcpu);
 		TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
 
@@ -110,8 +108,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	add_remove_memslot(vm, p->memslot_modification_delay,
 			   p->nr_memslot_modifications);
 
-	run_vcpus = false;
-
 	perf_test_join_vcpu_threads(nr_vcpus);
 	pr_info("All vCPU threads joined\n");
 
-- 
cgit v1.2.3