Merge tag 'v6.2' into iommufd.git for-next

Resolve conflicts from the signature change in iommu_map:

 - drivers/infiniband/hw/usnic/usnic_uiom.c
   Switch iommu_map_atomic() to iommu_map(.., GFP_ATOMIC)

 - drivers/vfio/vfio_iommu_type1.c
   Following indenting change for GFP_KERNEL

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

28 files changed, 669 insertions, 245 deletions

diff --git a/tools/testing/selftests/amd-pstate/Makefile b/tools/testing/selftests/amd-pstate/Makefile
index 5f195ee756d6..5fd1424db37d 100644
--- a/tools/testing/selftests/amd-pstate/Makefile
+++ b/tools/testing/selftests/amd-pstate/Makefile
@@ -7,11 +7,6 @@ all:
 uname_M := $(shell uname -m 2>/dev/null || echo not)
 ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
 
-ifeq (x86,$(ARCH))
-TEST_GEN_FILES += ../../../power/x86/amd_pstate_tracer/amd_pstate_trace.py
-TEST_GEN_FILES += ../../../power/x86/intel_pstate_tracer/intel_pstate_tracer.py
-endif
-
 TEST_PROGS := run.sh
 TEST_FILES := basic.sh tbench.sh gitsource.sh
 
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index 2cf0c7a3fe23..567e07c19ecc 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -30,6 +30,8 @@
 #define MAX_STRERR_LEN 256
 #define MAX_TEST_NAME 80
 
+#define __always_unused	__attribute__((__unused__))
+
 #define _FAIL(errnum, fmt...)                                                  \
 	({                                                                     \
 		error_at_line(0, (errnum), __func__, __LINE__, fmt);           \
@@ -321,7 +323,8 @@ static int socket_loopback(int family, int sotype)
 	return socket_loopback_reuseport(family, sotype, -1);
 }
 
-static void test_insert_invalid(int family, int sotype, int mapfd)
+static void test_insert_invalid(struct test_sockmap_listen *skel __always_unused,
+				int family, int sotype, int mapfd)
 {
 	u32 key = 0;
 	u64 value;
@@ -338,7 +341,8 @@ static void test_insert_invalid(int family, int sotype, int mapfd)
 		FAIL_ERRNO("map_update: expected EBADF");
 }
 
-static void test_insert_opened(int family, int sotype, int mapfd)
+static void test_insert_opened(struct test_sockmap_listen *skel __always_unused,
+			       int family, int sotype, int mapfd)
 {
 	u32 key = 0;
 	u64 value;
@@ -359,7 +363,8 @@ static void test_insert_opened(int family, int sotype, int mapfd)
 	xclose(s);
 }
 
-static void test_insert_bound(int family, int sotype, int mapfd)
+static void test_insert_bound(struct test_sockmap_listen *skel __always_unused,
+			      int family, int sotype, int mapfd)
 {
 	struct sockaddr_storage addr;
 	socklen_t len;
@@ -386,7 +391,8 @@ close:
 	xclose(s);
 }
 
-static void test_insert(int family, int sotype, int mapfd)
+static void test_insert(struct test_sockmap_listen *skel __always_unused,
+			int family, int sotype, int mapfd)
 {
 	u64 value;
 	u32 key;
@@ -402,7 +408,8 @@ static void test_insert(int family, int sotype, int mapfd)
 	xclose(s);
 }
 
-static void test_delete_after_insert(int family, int sotype, int mapfd)
+static void test_delete_after_insert(struct test_sockmap_listen *skel __always_unused,
+				     int family, int sotype, int mapfd)
 {
 	u64 value;
 	u32 key;
@@ -419,7 +426,8 @@ static void test_delete_after_insert(int family, int sotype, int mapfd)
 	xclose(s);
 }
 
-static void test_delete_after_close(int family, int sotype, int mapfd)
+static void test_delete_after_close(struct test_sockmap_listen *skel __always_unused,
+				    int family, int sotype, int mapfd)
 {
 	int err, s;
 	u64 value;
@@ -442,7 +450,8 @@ static void test_delete_after_close(int family, int sotype, int mapfd)
 		FAIL_ERRNO("map_delete: expected EINVAL/EINVAL");
 }
 
-static void test_lookup_after_insert(int family, int sotype, int mapfd)
+static void test_lookup_after_insert(struct test_sockmap_listen *skel __always_unused,
+				     int family, int sotype, int mapfd)
 {
 	u64 cookie, value;
 	socklen_t len;
@@ -470,7 +479,8 @@ static void test_lookup_after_insert(int family, int sotype, int mapfd)
 	xclose(s);
 }
 
-static void test_lookup_after_delete(int family, int sotype, int mapfd)
+static void test_lookup_after_delete(struct test_sockmap_listen *skel __always_unused,
+				     int family, int sotype, int mapfd)
 {
 	int err, s;
 	u64 value;
@@ -493,7 +503,8 @@ static void test_lookup_after_delete(int family, int sotype, int mapfd)
 	xclose(s);
 }
 
-static void test_lookup_32_bit_value(int family, int sotype, int mapfd)
+static void test_lookup_32_bit_value(struct test_sockmap_listen *skel __always_unused,
+				     int family, int sotype, int mapfd)
 {
 	u32 key, value32;
 	int err, s;
@@ -523,7 +534,8 @@ close:
 	xclose(s);
 }
 
-static void test_update_existing(int family, int sotype, int mapfd)
+static void test_update_existing(struct test_sockmap_listen *skel __always_unused,
+				 int family, int sotype, int mapfd)
 {
 	int s1, s2;
 	u64 value;
@@ -551,7 +563,7 @@ close_s1:
 /* Exercise the code path where we destroy child sockets that never
  * got accept()'ed, aka orphans, when parent socket gets closed.
  */
-static void test_destroy_orphan_child(int family, int sotype, int mapfd)
+static void do_destroy_orphan_child(int family, int sotype, int mapfd)
 {
 	struct sockaddr_storage addr;
 	socklen_t len;
@@ -582,10 +594,38 @@ close_srv:
 	xclose(s);
 }
 
+static void test_destroy_orphan_child(struct test_sockmap_listen *skel,
+				      int family, int sotype, int mapfd)
+{
+	int msg_verdict = bpf_program__fd(skel->progs.prog_msg_verdict);
+	int skb_verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+	const struct test {
+		int progfd;
+		enum bpf_attach_type atype;
+	} tests[] = {
+		{ -1, -1 },
+		{ msg_verdict, BPF_SK_MSG_VERDICT },
+		{ skb_verdict, BPF_SK_SKB_VERDICT },
+	};
+	const struct test *t;
+
+	for (t = tests; t < tests + ARRAY_SIZE(tests); t++) {
+		if (t->progfd != -1 &&
+		    xbpf_prog_attach(t->progfd, mapfd, t->atype, 0) != 0)
+			return;
+
+		do_destroy_orphan_child(family, sotype, mapfd);
+
+		if (t->progfd != -1)
+			xbpf_prog_detach2(t->progfd, mapfd, t->atype);
+	}
+}
+
 /* Perform a passive open after removing listening socket from SOCKMAP
  * to ensure that callbacks get restored properly.
  */
-static void test_clone_after_delete(int family, int sotype, int mapfd)
+static void test_clone_after_delete(struct test_sockmap_listen *skel __always_unused,
+				    int family, int sotype, int mapfd)
 {
 	struct sockaddr_storage addr;
 	socklen_t len;
@@ -621,7 +661,8 @@ close_srv:
  * SOCKMAP, but got accept()'ed only after the parent has been removed
  * from SOCKMAP, gets cloned without parent psock state or callbacks.
  */
-static void test_accept_after_delete(int family, int sotype, int mapfd)
+static void test_accept_after_delete(struct test_sockmap_listen *skel __always_unused,
+				     int family, int sotype, int mapfd)
 {
 	struct sockaddr_storage addr;
 	const u32 zero = 0;
@@ -675,7 +716,8 @@ close_srv:
 /* Check that child socket that got created and accepted while parent
  * was in a SOCKMAP is cloned without parent psock state or callbacks.
  */
-static void test_accept_before_delete(int family, int sotype, int mapfd)
+static void test_accept_before_delete(struct test_sockmap_listen *skel __always_unused,
+				      int family, int sotype, int mapfd)
 {
 	struct sockaddr_storage addr;
 	const u32 zero = 0, one = 1;
@@ -784,7 +826,8 @@ done:
 	return NULL;
 }
 
-static void test_syn_recv_insert_delete(int family, int sotype, int mapfd)
+static void test_syn_recv_insert_delete(struct test_sockmap_listen *skel __always_unused,
+					int family, int sotype, int mapfd)
 {
 	struct connect_accept_ctx ctx = { 0 };
 	struct sockaddr_storage addr;
@@ -847,7 +890,8 @@ static void *listen_thread(void *arg)
 	return NULL;
 }
 
-static void test_race_insert_listen(int family, int socktype, int mapfd)
+static void test_race_insert_listen(struct test_sockmap_listen *skel __always_unused,
+				    int family, int socktype, int mapfd)
 {
 	struct connect_accept_ctx ctx = { 0 };
 	const u32 zero = 0;
@@ -1473,7 +1517,8 @@ static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map,
 		     int family, int sotype)
 {
 	const struct op_test {
-		void (*fn)(int family, int sotype, int mapfd);
+		void (*fn)(struct test_sockmap_listen *skel,
+			   int family, int sotype, int mapfd);
 		const char *name;
 		int sotype;
 	} tests[] = {
@@ -1520,7 +1565,7 @@ static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map,
 		if (!test__start_subtest(s))
 			continue;
 
-		t->fn(family, sotype, map_fd);
+		t->fn(skel, family, sotype, map_fd);
 		test_ops_cleanup(map);
 	}
 }
diff --git a/tools/testing/selftests/bpf/verifier/search_pruning.c b/tools/testing/selftests/bpf/verifier/search_pruning.c
index 68b14fdfebdb..d63fd8991b03 100644
--- a/tools/testing/selftests/bpf/verifier/search_pruning.c
+++ b/tools/testing/selftests/bpf/verifier/search_pruning.c
@@ -225,3 +225,39 @@
 	.result_unpriv = ACCEPT,
 	.insn_processed = 15,
 },
+/* The test performs a conditional 64-bit write to a stack location
+ * fp[-8], this is followed by an unconditional 8-bit write to fp[-8],
+ * then data is read from fp[-8]. This sequence is unsafe.
+ *
+ * The test would be mistakenly marked as safe w/o dst register parent
+ * preservation in verifier.c:copy_register_state() function.
+ *
+ * Note the usage of BPF_F_TEST_STATE_FREQ to force creation of the
+ * checkpoint state after conditional 64-bit assignment.
+ */
+{
+	"write tracking and register parent chain bug",
+	.insns = {
+	/* r6 = ktime_get_ns() */
+	BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	/* r0 = ktime_get_ns() */
+	BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
+	/* if r0 > r6 goto +1 */
+	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_6, 1),
+	/* *(u64 *)(r10 - 8) = 0xdeadbeef */
+	BPF_ST_MEM(BPF_DW, BPF_REG_FP, -8, 0xdeadbeef),
+	/* r1 = 42 */
+	BPF_MOV64_IMM(BPF_REG_1, 42),
+	/* *(u8 *)(r10 - 8) = r1 */
+	BPF_STX_MEM(BPF_B, BPF_REG_FP, BPF_REG_1, -8),
+	/* r2 = *(u64 *)(r10 - 8) */
+	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_FP, -8),
+	/* exit(0) */
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.flags = BPF_F_TEST_STATE_FREQ,
+	.errstr = "invalid read from stack off -8+1 size 8",
+	.result = REJECT,
+},
diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
index 186e1c26867e..75c100de90ff 100755
--- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh
+++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh
@@ -268,6 +268,7 @@ TEST_MATRIX=(
 	# Taking away all CPUs from parent or itself if there are tasks
 	# will make the partition invalid.
 	"  S+ C2-3:P1:S+  C3:P1  .      .      T     C2-3    .      .     0 A1:2-3,A2:2-3 A1:P1,A2:P-1"
+	"  S+  C3:P1:S+    C3    .      .      T      P1     .      .     0 A1:3,A2:3 A1:P1,A2:P-1"
 	"  S+ $SETUP_A123_PARTITIONS    .    T:C2-3   .      .      .     0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1"
 	"  S+ $SETUP_A123_PARTITIONS    . T:C2-3:C1-3 .      .      .     0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1"
 
diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
index 9c79bbcce5a8..aff0a59f92d9 100755
--- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
+++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
@@ -246,7 +246,7 @@ test_vlan_ingress_modify()
 	bridge vlan add dev $swp2 vid 300
 
 	tc filter add dev $swp1 ingress chain $(IS1 2) pref 3 \
-		protocol 802.1Q flower skip_sw vlan_id 200 \
+		protocol 802.1Q flower skip_sw vlan_id 200 src_mac $h1_mac \
 		action vlan modify id 300 \
 		action goto chain $(IS2 0 0)
 
diff --git a/tools/testing/selftests/filesystems/fat/run_fat_tests.sh b/tools/testing/selftests/filesystems/fat/run_fat_tests.sh
index 7f35dc3d15df..7f35dc3d15df 100644..100755
--- a/tools/testing/selftests/filesystems/fat/run_fat_tests.sh
+++ b/tools/testing/selftests/filesystems/fat/run_fat_tests.sh
diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
index beb944fa6fd4..54680dc5887f 100644
--- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c
+++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c
@@ -237,6 +237,11 @@ static void guest_check_s1ptw_wr_in_dirty_log(void)
 	GUEST_SYNC(CMD_CHECK_S1PTW_WR_IN_DIRTY_LOG);
 }
 
+static void guest_check_no_s1ptw_wr_in_dirty_log(void)
+{
+	GUEST_SYNC(CMD_CHECK_NO_S1PTW_WR_IN_DIRTY_LOG);
+}
+
 static void guest_exec(void)
 {
 	int (*code)(void) = (int (*)(void))TEST_EXEC_GVA;
@@ -304,7 +309,7 @@ static struct uffd_args {
 
 /* Returns true to continue the test, and false if it should be skipped. */
 static int uffd_generic_handler(int uffd_mode, int uffd, struct uffd_msg *msg,
-				struct uffd_args *args, bool expect_write)
+				struct uffd_args *args)
 {
 	uint64_t addr = msg->arg.pagefault.address;
 	uint64_t flags = msg->arg.pagefault.flags;
@@ -313,7 +318,6 @@ static int uffd_generic_handler(int uffd_mode, int uffd, struct uffd_msg *msg,
 
 	TEST_ASSERT(uffd_mode == UFFDIO_REGISTER_MODE_MISSING,
 		    "The only expected UFFD mode is MISSING");
-	ASSERT_EQ(!!(flags & UFFD_PAGEFAULT_FLAG_WRITE), expect_write);
 	ASSERT_EQ(addr, (uint64_t)args->hva);
 
 	pr_debug("uffd fault: addr=%p write=%d\n",
@@ -337,19 +341,14 @@ static int uffd_generic_handler(int uffd_mode, int uffd, struct uffd_msg *msg,
 	return 0;
 }
 
-static int uffd_pt_write_handler(int mode, int uffd, struct uffd_msg *msg)
-{
-	return uffd_generic_handler(mode, uffd, msg, &pt_args, true);
-}
-
-static int uffd_data_write_handler(int mode, int uffd, struct uffd_msg *msg)
+static int uffd_pt_handler(int mode, int uffd, struct uffd_msg *msg)
 {
-	return uffd_generic_handler(mode, uffd, msg, &data_args, true);
+	return uffd_generic_handler(mode, uffd, msg, &pt_args);
 }
 
-static int uffd_data_read_handler(int mode, int uffd, struct uffd_msg *msg)
+static int uffd_data_handler(int mode, int uffd, struct uffd_msg *msg)
 {
-	return uffd_generic_handler(mode, uffd, msg, &data_args, false);
+	return uffd_generic_handler(mode, uffd, msg, &data_args);
 }
 
 static void setup_uffd_args(struct userspace_mem_region *region,
@@ -471,9 +470,12 @@ static bool handle_cmd(struct kvm_vm *vm, int cmd)
 {
 	struct userspace_mem_region *data_region, *pt_region;
 	bool continue_test = true;
+	uint64_t pte_gpa, pte_pg;
 
 	data_region = vm_get_mem_region(vm, MEM_REGION_TEST_DATA);
 	pt_region = vm_get_mem_region(vm, MEM_REGION_PT);
+	pte_gpa = addr_hva2gpa(vm, virt_get_pte_hva(vm, TEST_GVA));
+	pte_pg = (pte_gpa - pt_region->region.guest_phys_addr) / getpagesize();
 
 	if (cmd == CMD_SKIP_TEST)
 		continue_test = false;
@@ -486,13 +488,13 @@ static bool handle_cmd(struct kvm_vm *vm, int cmd)
 		TEST_ASSERT(check_write_in_dirty_log(vm, data_region, 0),
 			    "Missing write in dirty log");
 	if (cmd & CMD_CHECK_S1PTW_WR_IN_DIRTY_LOG)
-		TEST_ASSERT(check_write_in_dirty_log(vm, pt_region, 0),
+		TEST_ASSERT(check_write_in_dirty_log(vm, pt_region, pte_pg),
 			    "Missing s1ptw write in dirty log");
 	if (cmd & CMD_CHECK_NO_WRITE_IN_DIRTY_LOG)
 		TEST_ASSERT(!check_write_in_dirty_log(vm, data_region, 0),
 			    "Unexpected write in dirty log");
 	if (cmd & CMD_CHECK_NO_S1PTW_WR_IN_DIRTY_LOG)
-		TEST_ASSERT(!check_write_in_dirty_log(vm, pt_region, 0),
+		TEST_ASSERT(!check_write_in_dirty_log(vm, pt_region, pte_pg),
 			    "Unexpected s1ptw write in dirty log");
 
 	return continue_test;
@@ -797,7 +799,7 @@ static void help(char *name)
 	.expected_events	= { .uffd_faults = _uffd_faults, },		\
 }
 
-#define TEST_DIRTY_LOG(_access, _with_af, _test_check)				\
+#define TEST_DIRTY_LOG(_access, _with_af, _test_check, _pt_check)		\
 {										\
 	.name			= SCAT3(dirty_log, _access, _with_af),		\
 	.data_memslot_flags	= KVM_MEM_LOG_DIRTY_PAGES,			\
@@ -805,13 +807,12 @@ static void help(char *name)
 	.guest_prepare		= { _PREPARE(_with_af),				\
 				    _PREPARE(_access) },			\
 	.guest_test		= _access,					\
-	.guest_test_check	= { _CHECK(_with_af), _test_check,		\
-				    guest_check_s1ptw_wr_in_dirty_log},		\
+	.guest_test_check	= { _CHECK(_with_af), _test_check, _pt_check },	\
 	.expected_events	= { 0 },					\
 }
 
 #define TEST_UFFD_AND_DIRTY_LOG(_access, _with_af, _uffd_data_handler,		\
-				_uffd_faults, _test_check)			\
+				_uffd_faults, _test_check, _pt_check)		\
 {										\
 	.name			= SCAT3(uffd_and_dirty_log, _access, _with_af),	\
 	.data_memslot_flags	= KVM_MEM_LOG_DIRTY_PAGES,			\
@@ -820,16 +821,17 @@ static void help(char *name)
 				    _PREPARE(_access) },			\
 	.guest_test		= _access,					\
 	.mem_mark_cmd		= CMD_HOLE_DATA | CMD_HOLE_PT,			\
-	.guest_test_check	= { _CHECK(_with_af), _test_check },		\
+	.guest_test_check	= { _CHECK(_with_af), _test_check, _pt_check },	\
 	.uffd_data_handler	= _uffd_data_handler,				\
-	.uffd_pt_handler	= uffd_pt_write_handler,			\
+	.uffd_pt_handler	= uffd_pt_handler,				\
 	.expected_events	= { .uffd_faults = _uffd_faults, },		\
 }
 
 #define TEST_RO_MEMSLOT(_access, _mmio_handler, _mmio_exits)			\
 {										\
-	.name			= SCAT3(ro_memslot, _access, _with_af),		\
+	.name			= SCAT2(ro_memslot, _access),			\
 	.data_memslot_flags	= KVM_MEM_READONLY,				\
+	.pt_memslot_flags	= KVM_MEM_READONLY,				\
 	.guest_prepare		= { _PREPARE(_access) },			\
 	.guest_test		= _access,					\
 	.mmio_handler		= _mmio_handler,				\
@@ -840,6 +842,7 @@ static void help(char *name)
 {										\
 	.name			= SCAT2(ro_memslot_no_syndrome, _access),	\
 	.data_memslot_flags	= KVM_MEM_READONLY,				\
+	.pt_memslot_flags	= KVM_MEM_READONLY,				\
 	.guest_test		= _access,					\
 	.fail_vcpu_run_handler	= fail_vcpu_run_mmio_no_syndrome_handler,	\
 	.expected_events	= { .fail_vcpu_runs = 1 },			\
@@ -848,9 +851,9 @@ static void help(char *name)
 #define TEST_RO_MEMSLOT_AND_DIRTY_LOG(_access, _mmio_handler, _mmio_exits,	\
 				      _test_check)				\
 {										\
-	.name			= SCAT3(ro_memslot, _access, _with_af),		\
+	.name			= SCAT2(ro_memslot, _access),			\
 	.data_memslot_flags	= KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES,	\
-	.pt_memslot_flags	= KVM_MEM_LOG_DIRTY_PAGES,			\
+	.pt_memslot_flags	= KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES,	\
 	.guest_prepare		= { _PREPARE(_access) },			\
 	.guest_test		= _access,					\
 	.guest_test_check	= { _test_check },				\
@@ -862,7 +865,7 @@ static void help(char *name)
 {										\
 	.name			= SCAT2(ro_memslot_no_syn_and_dlog, _access),	\
 	.data_memslot_flags	= KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES,	\
-	.pt_memslot_flags	= KVM_MEM_LOG_DIRTY_PAGES,			\
+	.pt_memslot_flags	= KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES,	\
 	.guest_test		= _access,					\
 	.guest_test_check	= { _test_check },				\
 	.fail_vcpu_run_handler	= fail_vcpu_run_mmio_no_syndrome_handler,	\
@@ -874,11 +877,12 @@ static void help(char *name)
 {										\
 	.name			= SCAT2(ro_memslot_uffd, _access),		\
 	.data_memslot_flags	= KVM_MEM_READONLY,				\
+	.pt_memslot_flags	= KVM_MEM_READONLY,				\
 	.mem_mark_cmd		= CMD_HOLE_DATA | CMD_HOLE_PT,			\
 	.guest_prepare		= { _PREPARE(_access) },			\
 	.guest_test		= _access,					\
 	.uffd_data_handler	= _uffd_data_handler,				\
-	.uffd_pt_handler	= uffd_pt_write_handler,			\
+	.uffd_pt_handler	= uffd_pt_handler,				\
 	.mmio_handler		= _mmio_handler,				\
 	.expected_events	= { .mmio_exits = _mmio_exits,			\
 				    .uffd_faults = _uffd_faults },		\
@@ -889,10 +893,11 @@ static void help(char *name)
 {										\
 	.name			= SCAT2(ro_memslot_no_syndrome, _access),	\
 	.data_memslot_flags	= KVM_MEM_READONLY,				\
+	.pt_memslot_flags	= KVM_MEM_READONLY,				\
 	.mem_mark_cmd		= CMD_HOLE_DATA | CMD_HOLE_PT,			\
 	.guest_test		= _access,					\
 	.uffd_data_handler	= _uffd_data_handler,				\
-	.uffd_pt_handler	= uffd_pt_write_handler,			\
+	.uffd_pt_handler	= uffd_pt_handler,			\
 	.fail_vcpu_run_handler	= fail_vcpu_run_mmio_no_syndrome_handler,	\
 	.expected_events	= { .fail_vcpu_runs = 1,			\
 				    .uffd_faults = _uffd_faults },		\
@@ -933,44 +938,51 @@ static struct test_desc tests[] = {
 	 * (S1PTW).
 	 */
 	TEST_UFFD(guest_read64, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
-		  uffd_data_read_handler, uffd_pt_write_handler, 2),
-	/* no_af should also lead to a PT write. */
+		  uffd_data_handler, uffd_pt_handler, 2),
 	TEST_UFFD(guest_read64, no_af, CMD_HOLE_DATA | CMD_HOLE_PT,
-		  uffd_data_read_handler, uffd_pt_write_handler, 2),
-	/* Note how that cas invokes the read handler. */
+		  uffd_data_handler, uffd_pt_handler, 2),
 	TEST_UFFD(guest_cas, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
-		  uffd_data_read_handler, uffd_pt_write_handler, 2),
+		  uffd_data_handler, uffd_pt_handler, 2),
 	/*
 	 * Can't test guest_at with_af as it's IMPDEF whether the AF is set.
 	 * The S1PTW fault should still be marked as a write.
 	 */
 	TEST_UFFD(guest_at, no_af, CMD_HOLE_DATA | CMD_HOLE_PT,
-		  uffd_data_read_handler, uffd_pt_write_handler, 1),
+		  uffd_no_handler, uffd_pt_handler, 1),
 	TEST_UFFD(guest_ld_preidx, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
-		  uffd_data_read_handler, uffd_pt_write_handler, 2),
+		  uffd_data_handler, uffd_pt_handler, 2),
 	TEST_UFFD(guest_write64, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
-		  uffd_data_write_handler, uffd_pt_write_handler, 2),
+		  uffd_data_handler, uffd_pt_handler, 2),
 	TEST_UFFD(guest_dc_zva, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
-		  uffd_data_write_handler, uffd_pt_write_handler, 2),
+		  uffd_data_handler, uffd_pt_handler, 2),
 	TEST_UFFD(guest_st_preidx, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
-		  uffd_data_write_handler, uffd_pt_write_handler, 2),
+		  uffd_data_handler, uffd_pt_handler, 2),
 	TEST_UFFD(guest_exec, with_af, CMD_HOLE_DATA | CMD_HOLE_PT,
-		  uffd_data_read_handler, uffd_pt_write_handler, 2),
+		  uffd_data_handler, uffd_pt_handler, 2),
 
 	/*
 	 * Try accesses when the data and PT memory regions are both
 	 * tracked for dirty logging.
 	 */
-	TEST_DIRTY_LOG(guest_read64, with_af, guest_check_no_write_in_dirty_log),
-	/* no_af should also lead to a PT write. */
-	TEST_DIRTY_LOG(guest_read64, no_af, guest_check_no_write_in_dirty_log),
-	TEST_DIRTY_LOG(guest_ld_preidx, with_af, guest_check_no_write_in_dirty_log),
-	TEST_DIRTY_LOG(guest_at, no_af, guest_check_no_write_in_dirty_log),
-	TEST_DIRTY_LOG(guest_exec, with_af, guest_check_no_write_in_dirty_log),
-	TEST_DIRTY_LOG(guest_write64, with_af, guest_check_write_in_dirty_log),
-	TEST_DIRTY_LOG(guest_cas, with_af, guest_check_write_in_dirty_log),
-	TEST_DIRTY_LOG(guest_dc_zva, with_af, guest_check_write_in_dirty_log),
-	TEST_DIRTY_LOG(guest_st_preidx, with_af, guest_check_write_in_dirty_log),
+	TEST_DIRTY_LOG(guest_read64, with_af, guest_check_no_write_in_dirty_log,
+		       guest_check_s1ptw_wr_in_dirty_log),
+	TEST_DIRTY_LOG(guest_read64, no_af, guest_check_no_write_in_dirty_log,
+		       guest_check_no_s1ptw_wr_in_dirty_log),
+	TEST_DIRTY_LOG(guest_ld_preidx, with_af,
+		       guest_check_no_write_in_dirty_log,
+		       guest_check_s1ptw_wr_in_dirty_log),
+	TEST_DIRTY_LOG(guest_at, no_af, guest_check_no_write_in_dirty_log,
+		       guest_check_no_s1ptw_wr_in_dirty_log),
+	TEST_DIRTY_LOG(guest_exec, with_af, guest_check_no_write_in_dirty_log,
+		       guest_check_s1ptw_wr_in_dirty_log),
+	TEST_DIRTY_LOG(guest_write64, with_af, guest_check_write_in_dirty_log,
+		       guest_check_s1ptw_wr_in_dirty_log),
+	TEST_DIRTY_LOG(guest_cas, with_af, guest_check_write_in_dirty_log,
+		       guest_check_s1ptw_wr_in_dirty_log),
+	TEST_DIRTY_LOG(guest_dc_zva, with_af, guest_check_write_in_dirty_log,
+		       guest_check_s1ptw_wr_in_dirty_log),
+	TEST_DIRTY_LOG(guest_st_preidx, with_af, guest_check_write_in_dirty_log,
+		       guest_check_s1ptw_wr_in_dirty_log),
 
 	/*
 	 * Access when the data and PT memory regions are both marked for
@@ -980,29 +992,43 @@ static struct test_desc tests[] = {
 	 * fault, and nothing in the dirty log.  Any S1PTW should result in
 	 * a write in the dirty log and a userfaultfd write.
 	 */
-	TEST_UFFD_AND_DIRTY_LOG(guest_read64, with_af, uffd_data_read_handler, 2,
-				guest_check_no_write_in_dirty_log),
-	/* no_af should also lead to a PT write. */
-	TEST_UFFD_AND_DIRTY_LOG(guest_read64, no_af, uffd_data_read_handler, 2,
-				guest_check_no_write_in_dirty_log),
-	TEST_UFFD_AND_DIRTY_LOG(guest_ld_preidx, with_af, uffd_data_read_handler,
-				2, guest_check_no_write_in_dirty_log),
-	TEST_UFFD_AND_DIRTY_LOG(guest_at, with_af, 0, 1,
-				guest_check_no_write_in_dirty_log),
-	TEST_UFFD_AND_DIRTY_LOG(guest_exec, with_af, uffd_data_read_handler, 2,
-				guest_check_no_write_in_dirty_log),
-	TEST_UFFD_AND_DIRTY_LOG(guest_write64, with_af, uffd_data_write_handler,
-				2, guest_check_write_in_dirty_log),
-	TEST_UFFD_AND_DIRTY_LOG(guest_cas, with_af, uffd_data_read_handler, 2,
-				guest_check_write_in_dirty_log),
-	TEST_UFFD_AND_DIRTY_LOG(guest_dc_zva, with_af, uffd_data_write_handler,
-				2, guest_check_write_in_dirty_log),
+	TEST_UFFD_AND_DIRTY_LOG(guest_read64, with_af,
+				uffd_data_handler, 2,
+				guest_check_no_write_in_dirty_log,
+				guest_check_s1ptw_wr_in_dirty_log),
+	TEST_UFFD_AND_DIRTY_LOG(guest_read64, no_af,
+				uffd_data_handler, 2,
+				guest_check_no_write_in_dirty_log,
+				guest_check_no_s1ptw_wr_in_dirty_log),
+	TEST_UFFD_AND_DIRTY_LOG(guest_ld_preidx, with_af,
+				uffd_data_handler,
+				2, guest_check_no_write_in_dirty_log,
+				guest_check_s1ptw_wr_in_dirty_log),
+	TEST_UFFD_AND_DIRTY_LOG(guest_at, with_af, uffd_no_handler, 1,
+				guest_check_no_write_in_dirty_log,
+				guest_check_s1ptw_wr_in_dirty_log),
+	TEST_UFFD_AND_DIRTY_LOG(guest_exec, with_af,
+				uffd_data_handler, 2,
+				guest_check_no_write_in_dirty_log,
+				guest_check_s1ptw_wr_in_dirty_log),
+	TEST_UFFD_AND_DIRTY_LOG(guest_write64, with_af,
+				uffd_data_handler,
+				2, guest_check_write_in_dirty_log,
+				guest_check_s1ptw_wr_in_dirty_log),
+	TEST_UFFD_AND_DIRTY_LOG(guest_cas, with_af,
+				uffd_data_handler, 2,
+				guest_check_write_in_dirty_log,
+				guest_check_s1ptw_wr_in_dirty_log),
+	TEST_UFFD_AND_DIRTY_LOG(guest_dc_zva, with_af,
+				uffd_data_handler,
+				2, guest_check_write_in_dirty_log,
+				guest_check_s1ptw_wr_in_dirty_log),
 	TEST_UFFD_AND_DIRTY_LOG(guest_st_preidx, with_af,
-				uffd_data_write_handler, 2,
-				guest_check_write_in_dirty_log),
-
+				uffd_data_handler, 2,
+				guest_check_write_in_dirty_log,
+				guest_check_s1ptw_wr_in_dirty_log),
 	/*
-	 * Try accesses when the data memory region is marked read-only
+	 * Access when both the PT and data regions are marked read-only
 	 * (with KVM_MEM_READONLY). Writes with a syndrome result in an
 	 * MMIO exit, writes with no syndrome (e.g., CAS) result in a
 	 * failed vcpu run, and reads/execs with and without syndroms do
@@ -1018,7 +1044,7 @@ static struct test_desc tests[] = {
 	TEST_RO_MEMSLOT_NO_SYNDROME(guest_st_preidx),
 
 	/*
-	 * Access when both the data region is both read-only and marked
+	 * The PT and data regions are both read-only and marked
 	 * for dirty logging at the same time. The expected result is that
 	 * for writes there should be no write in the dirty log. The
 	 * readonly handling is the same as if the memslot was not marked
@@ -1043,7 +1069,7 @@ static struct test_desc tests[] = {
 						  guest_check_no_write_in_dirty_log),
 
 	/*
-	 * Access when the data region is both read-only and punched with
+	 * The PT and data regions are both read-only and punched with
 	 * holes tracked with userfaultfd.  The expected result is the
 	 * union of both userfaultfd and read-only behaviors. For example,
 	 * write accesses result in a userfaultfd write fault and an MMIO
@@ -1051,22 +1077,15 @@ static struct test_desc tests[] = {
 	 * no userfaultfd write fault. Reads result in userfaultfd getting
 	 * tri