Adding upstream version 6.10.3.upstream/6.10.3

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

16 files changed, 662 insertions, 337 deletions

diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic.c b/tools/testing/selftests/kvm/lib/aarch64/gic.c
index 55668631d5..7abbf88665 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/gic.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic.c
@@ -17,13 +17,12 @@
 static const struct gic_common_ops *gic_common_ops;
 static struct spinlock gic_lock;
 
-static void gic_cpu_init(unsigned int cpu, void *redist_base)
+static void gic_cpu_init(unsigned int cpu)
 {
-	gic_common_ops->gic_cpu_init(cpu, redist_base);
+	gic_common_ops->gic_cpu_init(cpu);
 }
 
-static void
-gic_dist_init(enum gic_type type, unsigned int nr_cpus, void *dist_base)
+static void gic_dist_init(enum gic_type type, unsigned int nr_cpus)
 {
 	const struct gic_common_ops *gic_ops = NULL;
 
@@ -40,7 +39,7 @@ gic_dist_init(enum gic_type type, unsigned int nr_cpus, void *dist_base)
 
 	GUEST_ASSERT(gic_ops);
 
-	gic_ops->gic_init(nr_cpus, dist_base);
+	gic_ops->gic_init(nr_cpus);
 	gic_common_ops = gic_ops;
 
 	/* Make sure that the initialized data is visible to all the vCPUs */
@@ -49,18 +48,15 @@ gic_dist_init(enum gic_type type, unsigned int nr_cpus, void *dist_base)
 	spin_unlock(&gic_lock);
 }
 
-void gic_init(enum gic_type type, unsigned int nr_cpus,
-		void *dist_base, void *redist_base)
+void gic_init(enum gic_type type, unsigned int nr_cpus)
 {
 	uint32_t cpu = guest_get_vcpuid();
 
 	GUEST_ASSERT(type < GIC_TYPE_MAX);
-	GUEST_ASSERT(dist_base);
-	GUEST_ASSERT(redist_base);
 	GUEST_ASSERT(nr_cpus);
 
-	gic_dist_init(type, nr_cpus, dist_base);
-	gic_cpu_init(cpu, redist_base);
+	gic_dist_init(type, nr_cpus);
+	gic_cpu_init(cpu);
 }
 
 void gic_irq_enable(unsigned int intid)
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_private.h b/tools/testing/selftests/kvm/lib/aarch64/gic_private.h
index 75d07313c8..d24e9ecc96 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/gic_private.h
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic_private.h
@@ -8,8 +8,8 @@
 #define SELFTEST_KVM_GIC_PRIVATE_H
 
 struct gic_common_ops {
-	void (*gic_init)(unsigned int nr_cpus, void *dist_base);
-	void (*gic_cpu_init)(unsigned int cpu, void *redist_base);
+	void (*gic_init)(unsigned int nr_cpus);
+	void (*gic_cpu_init)(unsigned int cpu);
 	void (*gic_irq_enable)(unsigned int intid);
 	void (*gic_irq_disable)(unsigned int intid);
 	uint64_t (*gic_read_iar)(void);
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
index 263bf3ed8f..66d05506f7 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
@@ -9,12 +9,21 @@
 #include "processor.h"
 #include "delay.h"
 
+#include "gic.h"
 #include "gic_v3.h"
 #include "gic_private.h"
 
+#define GICV3_MAX_CPUS			512
+
+#define GICD_INT_DEF_PRI		0xa0
+#define GICD_INT_DEF_PRI_X4		((GICD_INT_DEF_PRI << 24) |\
+					(GICD_INT_DEF_PRI << 16) |\
+					(GICD_INT_DEF_PRI << 8) |\
+					GICD_INT_DEF_PRI)
+
+#define ICC_PMR_DEF_PRIO		0xf0
+
 struct gicv3_data {
-	void *dist_base;
-	void *redist_base[GICV3_MAX_CPUS];
 	unsigned int nr_cpus;
 	unsigned int nr_spis;
 };
@@ -35,17 +44,23 @@ static void gicv3_gicd_wait_for_rwp(void)
 {
 	unsigned int count = 100000; /* 1s */
 
-	while (readl(gicv3_data.dist_base + GICD_CTLR) & GICD_CTLR_RWP) {
+	while (readl(GICD_BASE_GVA + GICD_CTLR) & GICD_CTLR_RWP) {
 		GUEST_ASSERT(count--);
 		udelay(10);
 	}
 }
 
-static void gicv3_gicr_wait_for_rwp(void *redist_base)
+static inline volatile void *gicr_base_cpu(uint32_t cpu)
+{
+	/* Align all the redistributors sequentially */
+	return GICR_BASE_GVA + cpu * SZ_64K * 2;
+}
+
+static void gicv3_gicr_wait_for_rwp(uint32_t cpu)
 {
 	unsigned int count = 100000; /* 1s */
 
-	while (readl(redist_base + GICR_CTLR) & GICR_CTLR_RWP) {
+	while (readl(gicr_base_cpu(cpu) + GICR_CTLR) & GICR_CTLR_RWP) {
 		GUEST_ASSERT(count--);
 		udelay(10);
 	}
@@ -56,7 +71,7 @@ static void gicv3_wait_for_rwp(uint32_t cpu_or_dist)
 	if (cpu_or_dist & DIST_BIT)
 		gicv3_gicd_wait_for_rwp();
 	else
-		gicv3_gicr_wait_for_rwp(gicv3_data.redist_base[cpu_or_dist]);
+		gicv3_gicr_wait_for_rwp(cpu_or_dist);
 }
 
 static enum gicv3_intid_range get_intid_range(unsigned int intid)
@@ -116,15 +131,15 @@ static void gicv3_set_eoi_split(bool split)
 
 uint32_t gicv3_reg_readl(uint32_t cpu_or_dist, uint64_t offset)
 {
-	void *base = cpu_or_dist & DIST_BIT ? gicv3_data.dist_base
-		: sgi_base_from_redist(gicv3_data.redist_base[cpu_or_dist]);
+	volatile void *base = cpu_or_dist & DIST_BIT ? GICD_BASE_GVA
+			: sgi_base_from_redist(gicr_base_cpu(cpu_or_dist));
 	return readl(base + offset);
 }
 
 void gicv3_reg_writel(uint32_t cpu_or_dist, uint64_t offset, uint32_t reg_val)
 {
-	void *base = cpu_or_dist & DIST_BIT ? gicv3_data.dist_base
-		: sgi_base_from_redist(gicv3_data.redist_base[cpu_or_dist]);
+	volatile void *base = cpu_or_dist & DIST_BIT ? GICD_BASE_GVA
+			: sgi_base_from_redist(gicr_base_cpu(cpu_or_dist));
 	writel(reg_val, base + offset);
 }
 
@@ -263,7 +278,7 @@ static bool gicv3_irq_get_pending(uint32_t intid)
 	return gicv3_read_reg(intid, GICD_ISPENDR, 32, 1);
 }
 
-static void gicv3_enable_redist(void *redist_base)
+static void gicv3_enable_redist(volatile void *redist_base)
 {
 	uint32_t val = readl(redist_base + GICR_WAKER);
 	unsigned int count = 100000; /* 1s */
@@ -278,21 +293,15 @@ static void gicv3_enable_redist(void *redist_base)
 	}
 }
 
-static inline void *gicr_base_cpu(void *redist_base, uint32_t cpu)
+static void gicv3_cpu_init(unsigned int cpu)
 {
-	/* Align all the redistributors sequentially */
-	return redist_base + cpu * SZ_64K * 2;
-}
-
-static void gicv3_cpu_init(unsigned int cpu, void *redist_base)
-{
-	void *sgi_base;
+	volatile void *sgi_base;
 	unsigned int i;
-	void *redist_base_cpu;
+	volatile void *redist_base_cpu;
 
 	GUEST_ASSERT(cpu < gicv3_data.nr_cpus);
 
-	redist_base_cpu = gicr_base_cpu(redist_base, cpu);
+	redist_base_cpu = gicr_base_cpu(cpu);
 	sgi_base = sgi_base_from_redist(redist_base_cpu);
 
 	gicv3_enable_redist(redist_base_cpu);
@@ -310,7 +319,7 @@ static void gicv3_cpu_init(unsigned int cpu, void *redist_base)
 		writel(GICD_INT_DEF_PRI_X4,
 				sgi_base + GICR_IPRIORITYR0 + i);
 
-	gicv3_gicr_wait_for_rwp(redist_base_cpu);
+	gicv3_gicr_wait_for_rwp(cpu);
 
 	/* Enable the GIC system register (ICC_*) access */
 	write_sysreg_s(read_sysreg_s(SYS_ICC_SRE_EL1) | ICC_SRE_EL1_SRE,
@@ -320,18 +329,15 @@ static void gicv3_cpu_init(unsigned int cpu, void *redist_base)
 	write_sysreg_s(ICC_PMR_DEF_PRIO, SYS_ICC_PMR_EL1);
 
 	/* Enable non-secure Group-1 interrupts */
-	write_sysreg_s(ICC_IGRPEN1_EL1_ENABLE, SYS_ICC_GRPEN1_EL1);
-
-	gicv3_data.redist_base[cpu] = redist_base_cpu;
+	write_sysreg_s(ICC_IGRPEN1_EL1_MASK, SYS_ICC_IGRPEN1_EL1);
 }
 
 static void gicv3_dist_init(void)
 {
-	void *dist_base = gicv3_data.dist_base;
 	unsigned int i;
 
 	/* Disable the distributor until we set things up */
-	writel(0, dist_base + GICD_CTLR);
+	writel(0, GICD_BASE_GVA + GICD_CTLR);
 	gicv3_gicd_wait_for_rwp();
 
 	/*
@@ -339,33 +345,32 @@ static void gicv3_dist_init(void)
 	 * Also, deactivate and disable them.
 	 */
 	for (i = 32; i < gicv3_data.nr_spis; i += 32) {
-		writel(~0, dist_base + GICD_IGROUPR + i / 8);
-		writel(~0, dist_base + GICD_ICACTIVER + i / 8);
-		writel(~0, dist_base + GICD_ICENABLER + i / 8);
+		writel(~0, GICD_BASE_GVA + GICD_IGROUPR + i / 8);
+		writel(~0, GICD_BASE_GVA + GICD_ICACTIVER + i / 8);
+		writel(~0, GICD_BASE_GVA + GICD_ICENABLER + i / 8);
 	}
 
 	/* Set a default priority for all the SPIs */
 	for (i = 32; i < gicv3_data.nr_spis; i += 4)
 		writel(GICD_INT_DEF_PRI_X4,
-				dist_base + GICD_IPRIORITYR + i);
+				GICD_BASE_GVA + GICD_IPRIORITYR + i);
 
 	/* Wait for the settings to sync-in */
 	gicv3_gicd_wait_for_rwp();
 
 	/* Finally, enable the distributor globally with ARE */
 	writel(GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A |
-			GICD_CTLR_ENABLE_G1, dist_base + GICD_CTLR);
+			GICD_CTLR_ENABLE_G1, GICD_BASE_GVA + GICD_CTLR);
 	gicv3_gicd_wait_for_rwp();
 }
 
-static void gicv3_init(unsigned int nr_cpus, void *dist_base)
+static void gicv3_init(unsigned int nr_cpus)
 {
 	GUEST_ASSERT(nr_cpus <= GICV3_MAX_CPUS);
 
 	gicv3_data.nr_cpus = nr_cpus;
-	gicv3_data.dist_base = dist_base;
 	gicv3_data.nr_spis = GICD_TYPER_SPIS(
-				readl(gicv3_data.dist_base + GICD_TYPER));
+				readl(GICD_BASE_GVA + GICD_TYPER));
 	if (gicv3_data.nr_spis > 1020)
 		gicv3_data.nr_spis = 1020;
 
@@ -396,3 +401,27 @@ const struct gic_common_ops gicv3_ops = {
 	.gic_irq_get_pending = gicv3_irq_get_pending,
 	.gic_irq_set_config = gicv3_irq_set_config,
 };
+
+void gic_rdist_enable_lpis(vm_paddr_t cfg_table, size_t cfg_table_size,
+			   vm_paddr_t pend_table)
+{
+	volatile void *rdist_base = gicr_base_cpu(guest_get_vcpuid());
+
+	u32 ctlr;
+	u64 val;
+
+	val = (cfg_table |
+	       GICR_PROPBASER_InnerShareable |
+	       GICR_PROPBASER_RaWaWb |
+	       ((ilog2(cfg_table_size) - 1) & GICR_PROPBASER_IDBITS_MASK));
+	writeq_relaxed(val, rdist_base + GICR_PROPBASER);
+
+	val = (pend_table |
+	       GICR_PENDBASER_InnerShareable |
+	       GICR_PENDBASER_RaWaWb);
+	writeq_relaxed(val, rdist_base + GICR_PENDBASER);
+
+	ctlr = readl_relaxed(rdist_base + GICR_CTLR);
+	ctlr |= GICR_CTLR_ENABLE_LPIS;
+	writel_relaxed(ctlr, rdist_base + GICR_CTLR);
+}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3_its.c b/tools/testing/selftests/kvm/lib/aarch64/gic_v3_its.c
new file mode 100644
index 0000000000..09f2705456
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic_v3_its.c
@@ -0,0 +1,248 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Guest ITS library, generously donated by drivers/irqchip/irq-gic-v3-its.c
+ * over in the kernel tree.
+ */
+
+#include <linux/kvm.h>
+#include <linux/sizes.h>
+#include <asm/kvm_para.h>
+#include <asm/kvm.h>
+
+#include "kvm_util.h"
+#include "vgic.h"
+#include "gic.h"
+#include "gic_v3.h"
+#include "processor.h"
+
+static u64 its_read_u64(unsigned long offset)
+{
+	return readq_relaxed(GITS_BASE_GVA + offset);
+}
+
+static void its_write_u64(unsigned long offset, u64 val)
+{
+	writeq_relaxed(val, GITS_BASE_GVA + offset);
+}
+
+static u32 its_read_u32(unsigned long offset)
+{
+	return readl_relaxed(GITS_BASE_GVA + offset);
+}
+
+static void its_write_u32(unsigned long offset, u32 val)
+{
+	writel_relaxed(val, GITS_BASE_GVA + offset);
+}
+
+static unsigned long its_find_baser(unsigned int type)
+{
+	int i;
+
+	for (i = 0; i < GITS_BASER_NR_REGS; i++) {
+		u64 baser;
+		unsigned long offset = GITS_BASER + (i * sizeof(baser));
+
+		baser = its_read_u64(offset);
+		if (GITS_BASER_TYPE(baser) == type)
+			return offset;
+	}
+
+	GUEST_FAIL("Couldn't find an ITS BASER of type %u", type);
+	return -1;
+}
+
+static void its_install_table(unsigned int type, vm_paddr_t base, size_t size)
+{
+	unsigned long offset = its_find_baser(type);
+	u64 baser;
+
+	baser = ((size / SZ_64K) - 1) |
+		GITS_BASER_PAGE_SIZE_64K |
+		GITS_BASER_InnerShareable |
+		base |
+		GITS_BASER_RaWaWb |
+		GITS_BASER_VALID;
+
+	its_write_u64(offset, baser);
+}
+
+static void its_install_cmdq(vm_paddr_t base, size_t size)
+{
+	u64 cbaser;
+
+	cbaser = ((size / SZ_4K) - 1) |
+		 GITS_CBASER_InnerShareable |
+		 base |
+		 GITS_CBASER_RaWaWb |
+		 GITS_CBASER_VALID;
+
+	its_write_u64(GITS_CBASER, cbaser);
+}
+
+void its_init(vm_paddr_t coll_tbl, size_t coll_tbl_sz,
+	      vm_paddr_t device_tbl, size_t device_tbl_sz,
+	      vm_paddr_t cmdq, size_t cmdq_size)
+{
+	u32 ctlr;
+
+	its_install_table(GITS_BASER_TYPE_COLLECTION, coll_tbl, coll_tbl_sz);
+	its_install_table(GITS_BASER_TYPE_DEVICE, device_tbl, device_tbl_sz);
+	its_install_cmdq(cmdq, cmdq_size);
+
+	ctlr = its_read_u32(GITS_CTLR);
+	ctlr |= GITS_CTLR_ENABLE;
+	its_write_u32(GITS_CTLR, ctlr);
+}
+
+struct its_cmd_block {
+	union {
+		u64	raw_cmd[4];
+		__le64	raw_cmd_le[4];
+	};
+};
+
+static inline void its_fixup_cmd(struct its_cmd_block *cmd)
+{
+	/* Let's fixup BE commands */
+	cmd->raw_cmd_le[0] = cpu_to_le64(cmd->raw_cmd[0]);
+	cmd->raw_cmd_le[1] = cpu_to_le64(cmd->raw_cmd[1]);
+	cmd->raw_cmd_le[2] = cpu_to_le64(cmd->raw_cmd[2]);
+	cmd->raw_cmd_le[3] = cpu_to_le64(cmd->raw_cmd[3]);
+}
+
+static void its_mask_encode(u64 *raw_cmd, u64 val, int h, int l)
+{
+	u64 mask = GENMASK_ULL(h, l);
+	*raw_cmd &= ~mask;
+	*raw_cmd |= (val << l) & mask;
+}
+
+static void its_encode_cmd(struct its_cmd_block *cmd, u8 cmd_nr)
+{
+	its_mask_encode(&cmd->raw_cmd[0], cmd_nr, 7, 0);
+}
+
+static void its_encode_devid(struct its_cmd_block *cmd, u32 devid)
+{
+	its_mask_encode(&cmd->raw_cmd[0], devid, 63, 32);
+}
+
+static void its_encode_event_id(struct its_cmd_block *cmd, u32 id)
+{
+	its_mask_encode(&cmd->raw_cmd[1], id, 31, 0);
+}
+
+static void its_encode_phys_id(struct its_cmd_block *cmd, u32 phys_id)
+{
+	its_mask_encode(&cmd->raw_cmd[1], phys_id, 63, 32);
+}
+
+static void its_encode_size(struct its_cmd_block *cmd, u8 size)
+{
+	its_mask_encode(&cmd->raw_cmd[1], size, 4, 0);
+}
+
+static void its_encode_itt(struct its_cmd_block *cmd, u64 itt_addr)
+{
+	its_mask_encode(&cmd->raw_cmd[2], itt_addr >> 8, 51, 8);
+}
+
+static void its_encode_valid(struct its_cmd_block *cmd, int valid)
+{
+	its_mask_encode(&cmd->raw_cmd[2], !!valid, 63, 63);
+}
+
+static void its_encode_target(struct its_cmd_block *cmd, u64 target_addr)
+{
+	its_mask_encode(&cmd->raw_cmd[2], target_addr >> 16, 51, 16);
+}
+
+static void its_encode_collection(struct its_cmd_block *cmd, u16 col)
+{
+	its_mask_encode(&cmd->raw_cmd[2], col, 15, 0);
+}
+
+#define GITS_CMDQ_POLL_ITERATIONS	0
+
+static void its_send_cmd(void *cmdq_base, struct its_cmd_block *cmd)
+{
+	u64 cwriter = its_read_u64(GITS_CWRITER);
+	struct its_cmd_block *dst = cmdq_base + cwriter;
+	u64 cbaser = its_read_u64(GITS_CBASER);
+	size_t cmdq_size;
+	u64 next;
+	int i;
+
+	cmdq_size = ((cbaser & 0xFF) + 1) * SZ_4K;
+
+	its_fixup_cmd(cmd);
+
+	WRITE_ONCE(*dst, *cmd);
+	dsb(ishst);
+	next = (cwriter + sizeof(*cmd)) % cmdq_size;
+	its_write_u64(GITS_CWRITER, next);
+
+	/*
+	 * Polling isn't necessary considering KVM's ITS emulation at the time
+	 * of writing this, as the CMDQ is processed synchronously after a write
+	 * to CWRITER.
+	 */
+	for (i = 0; its_read_u64(GITS_CREADR) != next; i++) {
+		__GUEST_ASSERT(i < GITS_CMDQ_POLL_ITERATIONS,
+			       "ITS didn't process command at offset %lu after %d iterations\n",
+			       cwriter, i);
+
+		cpu_relax();
+	}
+}
+
+void its_send_mapd_cmd(void *cmdq_base, u32 device_id, vm_paddr_t itt_base,
+		       size_t itt_size, bool valid)
+{
+	struct its_cmd_block cmd = {};
+
+	its_encode_cmd(&cmd, GITS_CMD_MAPD);
+	its_encode_devid(&cmd, device_id);
+	its_encode_size(&cmd, ilog2(itt_size) - 1);
+	its_encode_itt(&cmd, itt_base);
+	its_encode_valid(&cmd, valid);
+
+	its_send_cmd(cmdq_base, &cmd);
+}
+
+void its_send_mapc_cmd(void *cmdq_base, u32 vcpu_id, u32 collection_id, bool valid)
+{
+	struct its_cmd_block cmd = {};
+
+	its_encode_cmd(&cmd, GITS_CMD_MAPC);
+	its_encode_collection(&cmd, collection_id);
+	its_encode_target(&cmd, vcpu_id);
+	its_encode_valid(&cmd, valid);
+
+	its_send_cmd(cmdq_base, &cmd);
+}
+
+void its_send_mapti_cmd(void *cmdq_base, u32 device_id, u32 event_id,
+			u32 collection_id, u32 intid)
+{
+	struct its_cmd_block cmd = {};
+
+	its_encode_cmd(&cmd, GITS_CMD_MAPTI);
+	its_encode_devid(&cmd, device_id);
+	its_encode_event_id(&cmd, event_id);
+	its_encode_phys_id(&cmd, intid);
+	its_encode_collection(&cmd, collection_id);
+
+	its_send_cmd(cmdq_base, &cmd);
+}
+
+void its_send_invall_cmd(void *cmdq_base, u32 collection_id)
+{
+	struct its_cmd_block cmd = {};
+
+	its_encode_cmd(&cmd, GITS_CMD_INVALL);
+	its_encode_collection(&cmd, collection_id);
+
+	its_send_cmd(cmdq_base, &cmd);
+}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index a9eb17295b..0ac7cc89f3 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -11,6 +11,8 @@
 #include "guest_modes.h"
 #include "kvm_util.h"
 #include "processor.h"
+#include "ucall_common.h"
+
 #include <linux/bitfield.h>
 #include <linux/sizes.h>
 
diff --git a/tools/testing/selftests/kvm/lib/aarch64/vgic.c b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
index 184378d593..4427f43f73 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/vgic.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
@@ -3,8 +3,10 @@
  * ARM Generic Interrupt Controller (GIC) v3 host support
  */
 
+#include <linux/kernel.h>
 #include <linux/kvm.h>
 #include <linux/sizes.h>
+#include <asm/cputype.h>
 #include <asm/kvm_para.h>
 #include <asm/kvm.h>
 
@@ -19,8 +21,6 @@
  * Input args:
  *	vm - KVM VM
  *	nr_vcpus - Number of vCPUs supported by this VM
- *	gicd_base_gpa - Guest Physical Address of the Distributor region
- *	gicr_base_gpa - Guest Physical Address of the Redistributor region
  *
  * Output args: None
  *
@@ -30,11 +30,10 @@
  * redistributor regions of the guest. Since it depends on the number of
  * vCPUs for the VM, it must be called after all the vCPUs have been created.
  */
-int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs,
-		uint64_t gicd_base_gpa, uint64_t gicr_base_gpa)
+int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs)
 {
 	int gic_fd;
-	uint64_t redist_attr;
+	uint64_t attr;
 	struct list_head *iter;
 	unsigned int nr_gic_pages, nr_vcpus_created = 0;
 
@@ -60,18 +59,19 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs,
 	kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL,
 			    KVM_DEV_ARM_VGIC_CTRL_INIT, NULL);
 
+	attr = GICD_BASE_GPA;
 	kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
-			    KVM_VGIC_V3_ADDR_TYPE_DIST, &gicd_base_gpa);
+			    KVM_VGIC_V3_ADDR_TYPE_DIST, &attr);
 	nr_gic_pages = vm_calc_num_guest_pages(vm->mode, KVM_VGIC_V3_DIST_SIZE);
-	virt_map(vm, gicd_base_gpa, gicd_base_gpa,  nr_gic_pages);
+	virt_map(vm, GICD_BASE_GPA, GICD_BASE_GPA, nr_gic_pages);
 
 	/* Redistributor setup */
-	redist_attr = REDIST_REGION_ATTR_ADDR(nr_vcpus, gicr_base_gpa, 0, 0);
+	attr = REDIST_REGION_ATTR_ADDR(nr_vcpus, GICR_BASE_GPA, 0, 0);
 	kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
-			    KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &redist_attr);
+			    KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &attr);
 	nr_gic_pages = vm_calc_num_guest_pages(vm->mode,
 						KVM_VGIC_V3_REDIST_SIZE * nr_vcpus);
-	virt_map(vm, gicr_base_gpa, gicr_base_gpa,  nr_gic_pages);
+	virt_map(vm, GICR_BASE_GPA, GICR_BASE_GPA, nr_gic_pages);
 
 	kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL,
 			    KVM_DEV_ARM_VGIC_CTRL_INIT, NULL);
@@ -168,3 +168,21 @@ void kvm_irq_write_isactiver(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu)
 {
 	vgic_poke_irq(gic_fd, intid, vcpu, GICD_ISACTIVER);
 }
+
+int vgic_its_setup(struct kvm_vm *vm)
+{
+	int its_fd = kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_ITS);
+	u64 attr;
+
+	attr = GITS_BASE_GPA;
+	kvm_device_attr_set(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+			    KVM_VGIC_ITS_ADDR_TYPE, &attr);
+
+	kvm_device_attr_set(its_fd, KVM_DEV_ARM_VGIC_GRP_CTRL,
+			    KVM_DEV_ARM_VGIC_CTRL_INIT, NULL);
+
+	virt_map(vm, GITS_BASE_GPA, GITS_BASE_GPA,
+		 vm_calc_num_guest_pages(vm->mode, KVM_VGIC_V3_ITS_SIZE));
+
+	return its_fd;
+}
diff --git a/tools/testing/selftests/kvm/lib/assert.c b/tools/testing/selftests/kvm/lib/assert.c
index 2bd25b191d..b49690658c 100644
--- a/tools/testing/selftests/kvm/lib/assert.c
+++ b/tools/testing/selftests/kvm/lib/assert.c
@@ -4,9 +4,6 @@
  *
  * Copyright (C) 2018, Google LLC.
  */
-
-#define _GNU_SOURCE /* for getline(3) and strchrnul(3)*/
-
 #include "test_util.h"
 
 #include <execinfo.h>
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index b2262b5fad..ad00e47618 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -4,11 +4,10 @@
  *
  * Copyright (C) 2018, Google LLC.
  */
-
-#define _GNU_SOURCE /* for program_invocation_name */
 #include "test_util.h"
 #include "kvm_util.h"
 #include "processor.h"
+#include "ucall_common.h"
 
 #include <assert.h>
 #include <sched.h>
@@ -20,6 +19,9 @@
 
 #define KVM_UTIL_MIN_PFN	2
 
+uint32_t guest_random_seed;
+struct guest_random_state guest_rng;
+
 static int vcpu_mmap_sz(void);
 
 int open_path_or_exit(const char *path, int flags)
@@ -276,7 +278,6 @@ struct kvm_vm *____vm_create(struct vm_shape shape)
 
 	vm->mode = shape.mode;
 	vm->type = shape.type;
-	vm->subtype = shape.subtype;
 
 	vm->pa_bits = vm_guest_mode_params[vm->mode].pa_bits;
 	vm->va_bits = vm_guest_mode_params[vm->mode].va_bits;
@@ -433,6 +434,10 @@ struct kvm_vm *__vm_create(struct vm_shape shape, uint32_t nr_runnable_vcpus,
 	slot0 = memslot2region(vm, 0);
 	ucall_init(vm, slot0->region.guest_phys_addr + slot0->region.memory_size);
 
+	pr_info("Random seed: 0x%x\n", guest_random_seed);
+	guest_rng = new_guest_random_state(guest_random_seed);
+	sync_global_to_guest(vm, guest_rng);
+
 	kvm_arch_vm_post_create(vm);
 
 	return vm;
@@ -930,6 +935,10 @@ void vm_set_user_memory_region(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
 		    errno, strerror(errno));
 }
 
+#define TEST_REQUIRE_SET_USER_MEMORY_REGION2()			\
+	__TEST_REQUIRE(kvm_has_cap(KVM_CAP_USER_MEMORY2),	\
+		       "KVM selftests now require KVM_SET_USER_MEMORY_REGION2 (introduced in v6.8)")
+
 int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flags,
 				 uint64_t gpa, uint64_t size, void *hva,
 				 uint32_t guest_memfd, uint64_t guest_memfd_offset)
@@ -944,6 +953,8 @@ int __vm_set_user_memory_region2(struct kvm_vm *vm, uint32_t slot, uint32_t flag
 		.guest_memfd_offset = guest_memfd_offset,
 	};
 
+	TEST_REQUIRE_SET_USER_MEMORY_REGION2();
+
 	return ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION2, &region);
 }
 
@@ -970,6 +981,8 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type,
 	size_t mem_size = npages * vm->page_size;
 	size_t alignment;
 
+	TEST_REQUIRE_SET_USER_MEMORY_REGION2();
+
 	TEST_ASSERT(vm_adjust_num_guest_pages(vm->mode, npages) == npages,
 		"Number of guest pages is not compatible with the host. "
 		"Try npages=%d", vm_adjust_num_guest_pages(vm->mode, npages));
@@ -2306,6 +2319,8 @@ void __attribute((constructor)) kvm_selftest_init(void)
 	/* Tell stdout not to buffer its content. */
 	setbuf(stdout, NULL);
 
+	guest_random_seed = random();
+
 	kvm_selftest_arch_init();
 }
 
diff --git a/tools/testing/selftests/kvm/lib/memstress.c b/tools/testing/selftests/kvm/lib/memstress.c
index cf2c739713..313277486a 100644
--- a/tools/testing/selftests/kvm/lib/memstress.c
+++ b/tools/testing/selftests/kvm/lib/memstress.c
@@ -2,14 +2,13 @@
 /*
  * Copyright (C) 2020, Google LLC.
  */
-#define _GNU_SOURCE
-
 #include <inttypes.h>
 #include <linux/bitmap.h>
 
 #include "kvm_util.h"
 #include "memstress.h"
 #include "processor.h"
+#include "ucall_common.h"
 
 struct memstress_args memstress_args;
 
@@ -56,7 +55,7 @@ void memstress_guest_code(uint32_t vcpu_idx)
 	uint64_t page;
 	int i;
 
-	rand_state = new_guest_random_state(args->random_seed + vcpu_idx);
+	rand_state = new_guest_random_state(guest_random_seed + vcpu_idx);
 
 	gva = vcpu_args->gva;
 	pages = vcpu_args->pages;
@@ -76,7 +75,7 @@ void memstress_guest_code(uint32_t vcpu_idx)
 
 			addr = gva + (page * args->guest_page_size);
 
-			if (guest_random_u32(&rand_state) % 100 < args->write_percent)
+			if (__guest_random_bool(&rand_state, args->write_percent))
 				*(uint64_t *)addr = 0x0123456789ABCDEF;
 			else
 				READ_ONCE(*(uint64_t *)addr);
@@ -243,12 +242,6 @@ void memstress_set_write_percent(struct kvm_vm *vm, uint32_t write_percent)
 	sync_global_to_guest(vm, memstress_args.write_percent);
 }
 
-void memstress_set_random_seed(struct kvm_vm *vm, uint32_t random_seed)
-{
-	memstress_args.random_seed = random_seed;
-	sync_global_to_guest(vm, memstress_args.random_seed);
-}
-
 void memstress_set_random_access(struct kvm_vm *vm, bool random_access)
 {
 	memstress_args.random_access = random_access;
diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c
index e8211f5d68..6ae47b3d6b 100644
--- a/tools/testing/selftests/kvm/lib/riscv/processor.c
+++ b/tools/testing/selftests/kvm/lib/riscv/processor.c
@@ -10,6 +10,7 @@
 
 #include "kvm_util.h"
 #include "processor.h"
+#include "ucall_common.h"
 
 #define DEFAULT_RISCV_GUEST_STACK_VADDR_MIN	0xac0000
 
@@ -502,3 +503,15 @@ bool guest_sbi_probe_extension(int extid, long *out_val)
 
 	return true;
 }
+
+unsigned long get_host_sbi_spec_version(void)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_BASE, SBI_EXT_BASE_GET_SPEC_VERSION, 0,
+		       0, 0, 0, 0, 0);
+
+	GUEST_ASSERT(!ret.error);
+
+	return ret.value;
+}
diff --git a/tools/testing/selftests/kvm/lib/riscv/ucall.c b/tools/testing/selftests/kvm/lib/riscv/ucall.c
index 14ee17151a..b5035c63d5 100644
--- a/tools/testing/selftests/kvm/lib/riscv/ucall.c
+++ b/tools/testing/selftests/kvm/lib/riscv/ucall.c
@@ -9,6 +9,7 @@
 
 #include "kvm_util.h"
 #include "processor.h"
+#include "sbi.h"
 
 void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu)
 {
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index 5a8f8becb1..8ed0b74ae8 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -4,8 +4,6 @@
  *
  * Copyright (C) 2020, Google LLC.
  */
-
-#define _GNU_SOURCE
 #include <stdio.h>
 #include <stdarg.h>
 #include <assert.h>
diff --git a/tools/testing/selftests/kvm/lib/ucall_common.c b/tools/testing/selftests/kvm/lib/ucall_common.c
index f5af65a41c..42151e5719 100644
--- a/tools/testing/selftests/kvm/lib/ucall_common.c
+++ b/tools/testing/selftests/kvm/lib/ucall_common.c
@@ -1,9 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0-only
-#include "kvm_util.h"
 #include "linux/types.h"
 #include "linux/bitmap.h"
 #include "linux/atomic.h"
 
+#include "kvm_util.h"
+#include "ucall_common.h"
+
+
 #define GUEST_UCALL_FAILED -1
 
 struct ucall_header {
diff --git a/tools/testing/selftests/kvm/lib/userfaultfd_util.c b/tools/testing/selftests/kvm/lib/userfaultfd_util.c
index f4eef6eb2d..7c9de84144 100644
--- a/tools/testing/selftests/kvm/lib/userfaultfd_util.c
+++ b/tools/testing/selftests/kvm/lib/userfaultfd_util.c
@@ -6,9 +6,6 @@
  * 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>
@@ -16,6 +13,7 @@
 #include <poll.h>
 #include <pthread.h>
 #include <linux/userfaultfd.h>
+#include <sys/epoll.h>
 #include <sys/syscall.h>
 
 #include "kvm_util.h"
@@ -27,76 +25,69 @@
 
 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;
+	struct uffd_reader_args *reader_args = (struct uffd_reader_args *)arg;
+	int uffd = reader_args->uffd;
 	int64_t pages = 0;
 	struct timespec start;
 	struct timespec ts_diff;
+	struct epoll_event evt;
+	int epollfd;
+
+	epollfd = epoll_create(1);
+	TEST_ASSERT(epollfd >= 0, "Failed to create epollfd.");
+
+	evt.events = EPOLLIN | EPOLLEXCLUSIVE;
+	evt.data.u32 = 0;
+	TEST_ASSERT(!epoll_ctl(epollfd, EPOLL_CTL_ADD, uffd, &evt),
+		    "Failed to add uffd to epollfd");
+
+	evt.events = EPOLLIN;
+	evt.data.u32 = 1;
+	TEST_ASSERT(!epoll_ctl(epollfd, EPOLL_CTL_ADD, reader_args->pipe, &evt),
+		    "Failed to add pipe to epollfd");
 
 	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 = epoll_wait(epollfd, &evt, 1, -1);
+		TEST_ASSERT(r == 1,
+			    "Unexpected number of events (%d) from epoll, errno = %d",
+			    r, errno);
 
-		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 (evt.data.u32 == 1) {
+			char tmp_chr;
 
-		if (pollfd[1].revents & POLLIN) {
-			r = read(pollfd[1].fd, &tmp_chr, 1);
+			TEST_ASSERT(!(evt.events & (EPOLLERR | EPOLLHUP)),
+				    "Reader thread received EPOLLERR or EPOLLHUP on pipe.");
+			r = read(reader_args->pipe, &tmp_chr, 1);
 			TEST_ASSERT(r == 1,
-				    "Error reading pipefd in UFFD thread");
+				    "Error reading pipefd in uffd reader thread");
 			break;
 		}
 
-		if (!(pollfd[0].revents & POLLIN))
-			continue;
+		TEST_ASSERT(!(evt.events & (EPOLLERR | EPOLLHUP)),
+			    "Reader thread received EPOLLERR or EPOLLHUP on uffd.");
 
 		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;
+			TEST_ASSERT(errno == EAGAIN,
+				    "Error reading from UFFD: errno = %d", errno);
+			continue;
 		}
 
-		if (r != sizeof(msg)) {
-			pr_info("Read on uffd returned unexpected size: %d bytes", r);
-			return NULL;
-		}
+		TEST_ASSERT(r == sizeof(msg),
+			    "Read on uffd returned unexpected number of bytes (%d)", r);
 
 		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;
+		if (reader_args->delay)
+			usleep(reader_args->delay);
+		r = reader_args->handler(reader_args->uffd_mode, uffd, &msg);
+		TEST_ASSERT(r >= 0,
+			    "Reader thread handler fn returned negative value %d", r);
 		pages++;
 	}
 
@@ -110,6 +101,7 @@ static void *uffd_handler_thread_fn(void *arg)
 
 struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay,
 					   void *hva, uint64_t len,
+					   uint64_t num_readers,
 					   uffd_handler_t handler)
 {
 	struct uffd_desc *uffd_desc;
@@ -118,14 +110,25 @@ struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay,
 	struct uffdio_api uffdio_api;
 	struct uffdio_register uffdio_register;
 	uint64_t expected_ioctls = ((uint64_t) 1) << _UFFDIO_COPY;
-	int ret;
+	int ret, i;
 
 	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");
+	TEST_ASSERT(uffd_desc, "Failed to malloc uffd descriptor");
+
+	uffd_desc->pipefds = calloc(sizeof(int), num_readers);
+	TEST_ASSERT(uffd_desc->pipefds, "Failed to alloc pipes");
+
+	uffd_desc->readers = calloc(sizeof(pthread_t), num_readers);
+	TEST_ASSERT(uffd_desc->readers, "Failed to alloc reader threads");
+
+	uffd_desc->reader_args = calloc(sizeof(struct uffd_reader_args), num_readers);
+	TEST_ASSERT(uffd_desc->reader_args, "Failed to alloc reader_args");
+
+	uffd_desc->num_readers = num_readers;
 
 	/* In order to get minor faults, prefault via the alias. */
 	if (is_minor)
@@ -148,18 +151,28 @@ struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay,
 	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);
+	for (i = 0; i < uffd_desc->num_readers; ++i) {
+		int pipes[2];
 
-	PER_VCPU_DEBUG("Created uffd thread for HVA range [%p, %p)\n",
-		       hva, hva + len);
+		ret = pipe2((int *) &pipes, O_CLOEXEC | O_NONBLOCK);
+		TEST_ASSERT(!ret, "Failed to set up pipefd %i for uffd_desc %p",
+			    i, uffd_desc);
+
+		uffd_desc->pipefds[i] = pipes[1];
+
+		uffd_desc->reader_args[i].uffd_mode = uffd_mode;
+		uffd_desc->reader_args[i].uffd = uffd;
+		uffd_desc->reader_args[i].delay = delay;
+		uffd_desc->reader_args[i].handler = handler;
+		uffd_desc->reader_args[i].pipe = pipes[0];
+
+		pthread_create(&uffd_desc->readers[i], NULL, uffd_handler_thread_fn,
+			       &uffd_desc->reader_args[i]);
+
+		PER_VCPU_DEBUG("Created uffd thread %i for HVA range [%p, %p)\n",
+			       i, hva, hva + len);
+	}
 
 	return uffd_desc;
 }
@@ -167,19 +180,26 @@ struct uffd_desc *uffd_setup_demand_paging(int uffd_mode, useconds_t delay,
 void uffd_stop_demand_paging(struct uffd_desc *uffd)
 {
 	char c = 0;
-	int ret;
+	int i;
 
-	ret = write(uffd->pipefds[1], &c, 1);
-	TEST_ASSERT(ret == 1, "Unable to write to pipefd");
+	for (i = 0; i < uffd->num_readers; ++i)
+		TEST_ASSERT(write(uffd->pipefds[i], &c, 1) == 1,
+			    "Unable to write to pipefd %i for uffd_desc %p", i, uffd);
 
-	ret = pthread_join(uffd->thread, NULL);
-	TEST_ASSERT(ret == 0, "Pthread_join failed.");
+	for (i = 0; i < uffd->num_readers; ++i)
+		TEST_ASSERT(!pthread_join(uffd->readers[i], NULL),
+			    "Pthread_join failed on reader %i for uffd_desc %p", i, uffd);
 
 	close(uffd->uffd);
 
-	close(uffd->pipefds[1]);
-	close(uffd->pipefds[0]);
+	for (i = 0; i < uffd->num_readers; ++i) {
+		close(uffd->pipefds[i]);
+		close(uffd->reader_args[i].pipe);
+	}
 
+	free(uffd->pipefds);
+	free(uffd->readers);
+	free(uffd->reader_args);
 	free(uffd);
 }
 
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 74a4c736c9..594b061aef 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -15,14 +15,16 @@
 #define NUM_INTERRUPTS 256
 #endif
 
-#define DEFAULT_CODE_SELECTOR 0x8
-#define DEFAULT_DATA_SELECTOR 0x10
+#define KERNEL_CS	0x8
+#define KERNEL_DS	0x10
+#define KERNEL_TSS	0x18
 
 #define MAX_NR_CPUID_ENTRIES 100
 
 vm_vaddr_t exception_handlers;
 bool host_cpu_is_amd;
 bool host_cpu_is_intel;
+bool is_forced_emulation_enabled;
 
 static void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent)
 {
@@ -417,7 +419,7 @@ static void kvm_seg_set_unusable(struct kvm_segment *segp)
 
 static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp)
 {
-	void *gdt = addr_gva2hva(vm, vm->gdt);
+	void *gdt = addr_gva2hva(vm, vm->arch.gdt);
 	struct desc64 *desc = gdt + (segp->selector >> 3) * 8;
 
 	desc->limit0 = segp->limit & 0xFFFF;
@@ -437,27 +439,10 @@ static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp)
 		desc->base3 = segp->base >> 32;
 }
 
-
-/*
- * Set Long Mode Flat Kernel Code Segment
- *
- * Input Args:
- *   vm - VM whose GDT is being filled, or NULL to only write segp
- *   selector - selector value
- *
- * Output Args:
- *   segp - Pointer to KVM segment
- *
- * Return: None
- *
- * Sets up the KVM segment pointed to by @segp, to be a code segment
- * with the selector value given by @selector.
- */
-static void kvm_seg_set_kernel_code_64bit(struct kvm_vm *vm, uint16_t selector,
-	struct kvm_segment *segp)
+static void kvm_seg_set_kernel_code_64bit(struct kvm_segment *segp)
 {
 	memset(segp, 0, sizeof(*segp));
-	segp->selector = selector;
+	segp->selector = KERNEL_CS;
 	segp->limit = 0xFFFFFFFFu;
 	segp->s = 0x1; /* kTypeCodeData */
 	segp->type = 0x08 | 0x01 | 0x02; /* kFlagCode | kFlagCodeAccessed
@@ -466,30 +451,12 @@ static void kvm_seg_set_kernel_code_64bit(struct kvm_vm *vm, uint16_t selector,
 	segp->g = true;
 	segp->l = true;
 	segp->present = 1;
-	if (vm)
-		kvm_seg_fill_gdt_64bit(vm, segp);
 }
 
-/*
- * Set Long Mode Flat Kernel Data Segment
- *
- * Input Args:
- *   vm - VM whose GDT is being filled, or NULL to only write segp
- *   selector - selector value
- *
- * Output Args:
- *   segp - Pointer to KVM segment
- *
- * Return: None
- *
- * Sets up the KVM segment pointed to by @segp, to be a data segment
- * with the selector value given by @selector.
- */
-static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector,
-	struct kvm_segment *segp)
+static void kvm_seg_set_kernel_data_64bit(struct kvm_segment *segp)
 {
 	memset(segp, 0, sizeof(*segp));
-	segp->selector = selector;
+	segp->selector = KERNEL_DS;
 	segp->limit = 0xFFFFFFFFu;
 	segp->s = 0x1; /* kTypeCodeData */
 	segp->type = 0x00 | 0x01 | 0x02; /* kFlagData | kFlagDataAccessed
@@ -497,8 +464,6 @@ static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector,
 					  */
 	segp->g = true;
 	segp->present = true;
-	if (vm)
-		kvm_seg_fill_gdt_64bit(vm, segp);
 }
 
 vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
@@ -516,72 +481,153 @@ vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
 	return vm_untag_gpa(vm, PTE_GET_PA(*pte)) | (gva & ~HUGEPAGE_MASK(level));
 }
 
-static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt)
-{
-	if (!vm->gdt)
-		vm->gdt = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA);
-
-	dt->base = vm->gdt;
-	dt->limit = getpagesize();
-}
-
-static void kvm_setup_tss_64bit(struct kvm_vm *vm, struct kvm_segment *segp,
-				int selector)
+static void kvm_seg_set_tss_64bit(vm_vaddr_t base, struct kvm_segment *segp)
 {
-	if (!vm->tss)
-		vm->tss = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA);
-
 	memset(segp, 0, sizeof(*segp));
-	segp->base = vm->tss;
+	segp->base = base;
 	segp->limit = 0x67;
-	segp->selector = selector;
+	segp->selector = KERNEL_TSS;
 	segp->type = 0xb;
 	segp->present = 1;
-	kvm_seg_fill_gdt_64bit(vm, segp);
 }
 
-static void vcpu_setup(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
+static void vcpu_init_sregs(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
 {
 	struct kvm_sregs sregs;
 
+	TEST_ASSERT_EQ(vm->mode, VM_MODE_PXXV48_4K);
+
 	/* Set mode specific system register values. */
 	vcpu_sregs_get(vcpu, &sregs);
 
-	sregs.idt.limit = 0;
+	sregs.idt.base = vm->arch.idt;
+	sregs.idt.limit = NUM_INTERRUPTS * sizeof(struct idt_entry) - 1;
+	sregs.gdt.base = vm->arch.gdt;
+	sregs.gdt.limit = getpagesize() - 1;
+
+	sregs.cr0 = X86_CR0_PE | X86_CR0_NE | X86_CR0_PG;
+	sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR;
+	sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
+
+	kvm_seg_set_unusable(&sregs.ldt);
+	kvm_seg_set_kernel_code_64bit(&sregs.cs);
+	kvm_seg_set_kernel_data_64bit(&sregs.ds);
+	kvm_seg_set_kernel_data_64bit(&sregs.es);
+	kvm_seg_set_kernel_data_64bit(&sregs.gs);
+	kvm_seg_set_tss_64bit(vm->arch.tss, &sregs.tr);
+
+	sregs.cr3 = vm->pgd;
+	vcpu_sregs_set(vcpu, &sregs);
+}
+
+static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr,
+			  int dpl, unsigned short selector)
+{
+	struct idt_entry *base =
+		(struct idt_entry *)addr_gva2hva(vm, vm->arch.idt);
+	struct idt_entry *e = &base[vector];
+
+	memset(e, 0, sizeof(*e));
+	e->offset0 = addr;
+	e->selector = selector;
+	e->ist = 0;
+	e->type = 14;
+	e->dpl = dpl;
+	e->p = 1;
+	e->offset1 = addr >> 16;
+	e->offset2 = addr >> 32;
+}
+
+static bool kvm_fixup_exception(struct ex_regs *regs)
+{
+	if (regs->r9 != KVM_EXCEPTION_MAGIC || regs->rip != regs->r10)
+		return false;
 
-	kvm_setup_gdt(vm, &sregs.gdt);
+	if (regs->vector == DE_VECTOR)
+		return false;
 
-	switch (vm->mode) {
-	case VM_MODE_PXXV48_4K:
-		sregs.cr0 = X86_CR0_PE | X86_CR0_NE | X86_CR0_PG;
-		sregs.cr4 |= X86_CR4_PAE | X86_CR4_OSFXSR;
-		sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
+	regs->rip = regs->r11;
+	regs->r9 = regs->vector;
+	regs->r10 = regs->error_code;
+	return true;
+}
 
-		kvm_seg_set_unusable(&sregs.ldt);
-		kvm_seg_set_kernel_code_64bit(vm, DEFAULT_CODE_SELECTOR, &sregs.cs);
-		kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.ds);
-		kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.es);
-		kvm_setup_tss_64bit(vm, &sregs.tr, 0x18);
-		break;
+void route_exception(struct ex_regs *regs)
+{
+	typedef void(*handler)(struct ex_regs *);
+	handler *handlers = (handler *)exception_handlers;
 
-	default:
-		TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
+	if (handlers && handlers[regs->vector]) {
+		handlers[regs->vector](regs);
+		return;
 	}
 
-	sregs.cr3 = vm->pgd;
-	vcpu_sregs_set(vcpu, &sregs);
+	if (kvm_fixup_exception(regs))
+		return;
+
+	ucall_assert(UCALL_UNHANDLED,
+		     "Unhandled exception in guest", __FILE__, __LINE__,
+		     "Unhandled exception '0x%lx' at guest RIP '0x%lx'",
+		     regs->vector, regs->rip);
+}
+
+static void vm_init_descriptor_tables(struct kvm_vm *vm)
+{
+	extern void *idt_handlers;
+	struct kvm_segment seg;
+	int i;
+
+	vm->arch.gdt = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA);
+	vm->arch.idt = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA);
+	vm->handlers = __vm_vaddr_alloc_page(vm, MEM_REGION_DATA);
+	vm->arch.tss = __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, KERNEL_CS);
+
+	*(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers;
+
+	kvm_seg_set_kernel_code_64bit(&seg);
+	kvm_seg_fill_gdt_64bit(vm, &seg);
+
+	kvm_seg_set_kernel_data_64bit(&seg);
+	kvm_seg_fill_gdt_64bit(vm, &seg);
+
+	kvm_seg_set_tss_64bit(vm->arch.tss, &seg);
+	kvm_seg_fill_gdt_64bit(vm, &seg);
+}
+
+void vm_install_exception_handler(struct kvm_vm *vm, int vector,
+			       void (*handler)(struct ex_regs *))
+{
+	vm_vaddr_t *handlers = (vm_vaddr_t *)addr_gva2hva(vm, vm->handlers);
+
+	handlers[vector] = (vm_vaddr_t)handler;
+}
+
+void assert_on_unhandled_exception(struct kvm_vcpu *vcpu)
+{
+	struct ucall uc;
+
+	if (get_ucall(vcpu, &uc) == UCALL_UNHANDLED)
+		REPORT_GUEST_ASSERT(uc);
 }
 
 void kvm_arch_vm_post_create(struct kvm_vm *vm)
 {
 	vm_create_irqchip(vm);
+	vm_init_descriptor_tables(vm);
+
 	sync_global_to_guest(vm, host_cpu_is_intel);
 	sync_global_to_guest(vm, host_cpu_is_amd);
+	sync_global_to_guest(vm, is_forced_emulation_enabled);
+
+	if (vm->type == KVM_X86_SEV_VM || vm->type == KVM_X86_SEV_ES_VM) {
+		struct kvm_sev_init init = { 0 };
 
-	if (vm->subtype == VM_SUBTYPE_SEV)
-		sev_vm_init(vm);
-	else if (vm->subtype == VM_SUBTYPE_SEV_ES)
-		sev_es_vm_init(vm);
+		vm_sev_ioctl(vm, KVM_SEV_INIT2, &init);
+	}
 }
 
 void vcpu_arch_set_entry_point(struct kvm_vcpu *vcpu, void *guest_code)
@@ -621,7 +667,7 @@ struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
 
 	vcpu = __vm_vcpu_add(vm, vcpu_id);
 	vcpu_init_cpuid(vcpu, kvm_get_supported_cpuid());
-	vcpu_setup(vm, vcpu);
+	vcpu_init_sregs(vm, vcpu);
 
 	/* Setup guest general purpose registers */
 	vcpu_regs_get(vcpu, &regs);
@@ -1081,108 +1127,15 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits)
 
 void kvm_init_vm_address_properties(struct kvm_vm *vm)
 {
-	if (vm->subtype == VM_SUBTYPE_SEV || vm->subtype == VM_SUBTYPE_SEV_ES) {
+	if (vm->type == KVM_X86_SEV_VM || vm->type == KVM_X86_SEV_ES_VM) {
+		vm->arch.sev_fd = open_sev_dev_path_or_exit();
 		vm->arch.c_bit = BIT_ULL(this_cpu_property(X86_PROPERTY_SEV_C_BIT));
 		vm->gpa_tag_mask = vm->arch.c_bit;
+	} else {
+		vm->arch.sev_fd = -1;
 	}
 }
 
-static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr,
-			  int dpl, unsigned short selector)
-{
-	struct idt_entry *base =
-		(struct idt_entry *)addr_gva2hva(vm, vm->idt);
-	struct idt_entry *e = &base[vector];
-
-	memset(e, 0, sizeof(*e));
-	e->offset0 = addr;
-	e->selector = selector;
-	e->ist = 0;
-	e->type = 14;
-	e->dpl = dpl;
-	e->p = 1;
-	e->offset1 = addr >> 16;
-	e->offset2 = addr >> 32;
-}
-
-
-static bool kvm_fixup_exception(struct ex_regs *regs)
-{
-	if (regs->r9 != KVM_EXCEPTION_MAGIC || regs->rip != regs->r10)
-		return false;
-
-	if (regs->vector == DE_VECTOR)
-		return false;
-
-	regs->rip = regs->r11;
-	regs->r9 = regs->vector;
-	regs->r10 = regs->error_code;
-	return true;
-}
-
-void route_exception(struct ex_regs *regs)
-{
-	typedef void(*handler)(struct ex_regs *);
-	handler *handlers = (handler *)exception_handlers;
-
-	if (handlers && handlers[regs->vector]) {
-		handlers[regs->vector](regs);
-		return;
-	}
-
-	if (kvm_fixup_exception(regs))
-		return;
-
-	ucall_assert(UCALL_UNHANDLED,
-		     "Unhandled exception in guest", __FILE__, __LINE__,
-		     "Unhandled exception '0x%lx' at guest RIP '0x%lx'",
-		     regs->vector, regs->rip);
-}
-
-void vm_init_descriptor_tables(struct kvm_vm *vm)
-{
-	extern void *idt_handlers;
-	int i;
-
-	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,
-			DEFAULT_CODE_SELECTOR);
-}
-
-void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu)
-{
-	struct kvm_vm *vm = vcpu->vm;
-	struct kvm_sregs sregs;
-
-	vcpu_sregs_get(vcpu, &sregs);
-	sregs.idt.base = vm->idt;
-	sregs.idt.limit = NUM_INTERRUPTS * sizeof(struct idt_entry) - 1;
-	sregs.gdt.base = vm->gdt;
-	sregs.gdt.limit = getpagesize() - 1;
-	kvm_seg_set_kernel_data_64bit(NULL, DEFAULT_DATA_SELECTOR, &sregs.gs);
-	vcpu_sregs_set(vcpu, &sregs);
-	*(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers;
-}
-
-void vm_install_exception_handler(struct kvm_vm *vm, int vector,
-			       void (*handler)(struct ex_regs *))
-{
-	vm_vaddr_t *handlers = (vm_vaddr_t *)addr_gva2hva(vm, vm->handlers);
-
-	handlers[vector] = (vm_vaddr_t)handler;
-}
-
-void assert_on_unhandled_exception(struct kvm_vcpu *vcpu)
-{
-	struct ucall uc;
-
-	if (get_ucall(vcpu, &uc) == UCALL_UNHANDLED)
-		REPORT_GUEST_ASSERT(uc);
-}
-
 const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid,
 					       uint32_t function, uint32_t index)
 {
@@ -1294,9 +1247,20 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm)
 {
 	const unsigned long num_ht_pages = 12 << (30 - vm->page_shift); /* 12 GiB */
 	unsigned long ht_gfn, max_gfn, max_pfn;
-	uint8_t maxphyaddr;
+	uint8_t maxphyaddr, guest_maxphyaddr;
+
+	/*
+	 * Use "guest MAXPHYADDR" from KVM if it's available.  Guest MAXPHYADDR
+	 * enumerates the max _mappable_ GPA, which can be less than the raw
+	 * MAXPHYADDR, e.g. if MAXPHYADDR=52, KVM is using TDP, and the CPU
+	 * doesn't support 5-level TDP.
+	 */
+	guest_maxphyaddr = kvm_cpu_property(X86_PROPERTY_GUEST_MAX_PHY_ADDR);
+	guest_maxphyaddr = guest_maxphyaddr ?: vm->pa_bits;
+	TEST_ASSERT(guest_maxphyaddr <= vm->pa_bits,
+		    "Guest MAXPHYADDR should never be greater than raw MAXPHYADDR");
 
-	max_gfn = (1ULL << (vm->pa_bits - vm->page_shift)) - 1;
+	max_gfn = (1ULL << (guest_maxphyaddr - vm->page_shift)) - 1;
 
 	/* Avoid reserved HyperTransport region on AMD processors.  */
 	if (!host_cpu_is_amd)
@@ -1344,6 +1308,7 @@ void kvm_selftest_arch_init(void)
 {
 	host_cpu_is_intel = this_cpu_is_intel();
 	host_cpu_is_amd = this_cpu_is_amd();
+	is_forced_emulation_enabled = kvm_is_forced_emulation_enabled();
 }
 
 bool sys_clocksource_is_based_on_tsc(void)
diff --git a/tools/testing/selftests/kvm/lib/x86_64/sev.c b/tools/testing/selftests/kvm/lib/x86_64/sev.c
index e248d3364b..e9535ee20b 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/sev.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/sev.c
@@ -1,5 +1,4 @@
 // SPDX-License-Identifier: GPL-2.0-only
-#define _GNU_SOURCE /* for program_invocation_short_name */
 #include <stdint.h>
 #include <stdbool.h>
 
@@ -35,6 +34,32 @@ static void encrypt_region(struct kvm_vm *vm, struct userspace_mem_region *regio
 	}
 }
 
+void sev_vm_init(struct kvm_vm *vm)
+{
+	if (vm->type == KVM_X86_DEFAULT_VM) {
+		assert(vm->arch.sev_fd == -1);
+		vm->arch.sev_fd = open_sev_dev_path_or_exit();
+		vm_sev_ioctl(vm, KVM_SEV_INIT, NULL);
+	} else {
+		struct kvm_sev_init init = { 0 };
+		assert(vm->type == KVM_X86_SEV_VM);
+		vm_sev_ioctl(vm, KVM_SEV_INIT2, &init);
+	}
+}
+
+void sev_es_vm_init(struct kvm_vm *vm)
+{
+	if (vm->type == KVM_X86_DEFAULT_VM) {
+		assert(vm->arch.sev_fd == -1);
+		vm->arch.sev_fd = open_sev_dev_path_or_exit();
+		vm_sev_ioctl(vm, KVM_SEV_ES_INIT, NULL);
+	} else {
+		struct kvm_sev_init init = { 0 };
+		assert(vm->type == KVM_X86_SEV_ES_VM);
+		vm_sev_ioctl(vm, KVM_SEV_INIT2, &init);
+	}
+}
+
 void sev_vm_launch(struct kvm_vm *vm, uint32_t policy)
 {
 	struct kvm_sev_launch_start launch_start = {
@@ -87,28 +112,30 @@ void sev_vm_launch_finish(struct kvm_vm *vm)
 	TEST_ASSERT_EQ(status.state, SEV_GUEST_STATE_RUNNING);
 }
 
-struct kvm_vm *vm_sev_create_with_one_vcpu(uint32_t policy, void *guest_code,
+struct kvm_vm *vm_sev_create_with_one_vcpu(uint32_t type, void *guest_code,
 					   struct kvm_vcpu **cpu)
 {
 	struct vm_shape shape = {
-		.type = VM_TYPE_DEFAULT,
 		.mode = VM_MODE_DEFAULT,
-		.subtype = policy & SEV_POLICY_ES ? VM_SUBTYPE_SEV_ES :
-						    VM_SUBTYPE_SEV,
+		.type = type,
 	};
 	struct kvm_vm *vm;
 	struct kvm_vcpu *cpus[1];
-	uint8_t measurement[512];
 
 	vm = __vm_create_with_vcpus(shape, 1, 0, guest_code, cpus);
 	*cpu = cpus[0];
 
+	return vm;
+}
+
+void vm_sev_launch(struct kvm_vm *vm, uint32_t policy, uint8_t *measurement)
+{
 	sev_vm_launch(vm, policy);
 
-	/* TODO: Validate the measurement is as expected. */
+	if (!measurement)
+		measurement = alloca(256);
+
 	sev_vm_launch_measure(vm, measurement);
 
 	sev_vm_launch_finish(vm);
-
-	return vm;
 }