Merge tag 'kvmarm-6.2' of https://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for 6.2 - Enable the per-vcpu dirty-ring tracking mechanism, together with an option to keep the good old dirty log around for pages that are dirtied by something other than a vcpu. - Switch to the relaxed parallel fault handling, using RCU to delay page table reclaim and giving better performance under load. - Relax the MTE ABI, allowing a VMM to use the MAP_SHARED mapping option, which multi-process VMMs such as crosvm rely on. - Merge the pKVM shadow vcpu state tracking that allows the hypervisor to have its own view of a vcpu, keeping that state private. - Add support for the PMUv3p5 architecture revision, bringing support for 64bit counters on systems that support it, and fix the no-quite-compliant CHAIN-ed counter support for the machines that actually exist out there. - Fix a handful of minor issues around 52bit VA/PA support (64kB pages only) as a prefix of the oncoming support for 4kB and 16kB pages. - Add/Enable/Fix a bunch of selftests covering memslots, breakpoints, stage-2 faults and access tracking. You name it, we got it, we probably broke it. - Pick a small set of documentation and spelling fixes, because no good merge window would be complete without those. As a side effect, this tag also drags: - The 'kvmarm-fixes-6.1-3' tag as a dependency to the dirty-ring series - A shared branch with the arm64 tree that repaints all the system registers to match the ARM ARM's naming, and resulting in interesting conflicts
2026-04-23 14:02:06 -04:00 · 2022-12-06 12:27:39 -05:00
parent 1e79a9e3ab 753d734f3f
commit eb5618911a
91 changed files with 6095 additions and 1788 deletions
--- 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)
@@ -11,17 +12,24 @@
 #define DBGBCR_EXEC	(0x0 << 3)
 #define DBGBCR_EL1	(0x1 << 1)
 #define DBGBCR_E	(0x1 << 0)
+#define DBGBCR_LBN_SHIFT	16
+#define DBGBCR_BT_SHIFT		20
+#define DBGBCR_BT_ADDR_LINK_CTX	(0x1 << DBGBCR_BT_SHIFT)
+#define DBGBCR_BT_CTX_LINK	(0x3 << DBGBCR_BT_SHIFT)

 #define DBGWCR_LEN8	(0xff << 5)
 #define DBGWCR_RD	(0x1 << 3)
 #define DBGWCR_WR	(0x2 << 3)
 #define DBGWCR_EL1	(0x1 << 1)
 #define DBGWCR_E	(0x1 << 0)
+#define DBGWCR_LBN_SHIFT	16
+#define DBGWCR_WT_SHIFT		20
+#define DBGWCR_WT_LINK		(0x1 << DBGWCR_WT_SHIFT)

 #define SPSR_D		(1 << 9)
 #define SPSR_SS		(1 << 21)

-extern unsigned char sw_bp, sw_bp2, hw_bp, hw_bp2, bp_svc, bp_brk, hw_wp, ss_start;
+extern unsigned char sw_bp, sw_bp2, hw_bp, hw_bp2, bp_svc, bp_brk, hw_wp, ss_start, hw_bp_ctx;
 extern unsigned char iter_ss_begin, iter_ss_end;
 static volatile uint64_t sw_bp_addr, hw_bp_addr;
 static volatile uint64_t wp_addr, wp_data_addr;
@@ -29,8 +37,74 @@ static volatile uint64_t svc_addr;
 static volatile uint64_t ss_addr[4], ss_idx;
 #define  PC(v)  ((uint64_t)&(v))

+#define GEN_DEBUG_WRITE_REG(reg_name)			\
+static void write_##reg_name(int num, uint64_t val)	\
+{							\
+	switch (num) {					\
+	case 0:						\
+		write_sysreg(val, reg_name##0_el1);	\
+		break;					\
+	case 1:						\
+		write_sysreg(val, reg_name##1_el1);	\
+		break;					\
+	case 2:						\
+		write_sysreg(val, reg_name##2_el1);	\
+		break;					\
+	case 3:						\
+		write_sysreg(val, reg_name##3_el1);	\
+		break;					\
+	case 4:						\
+		write_sysreg(val, reg_name##4_el1);	\
+		break;					\
+	case 5:						\
+		write_sysreg(val, reg_name##5_el1);	\
+		break;					\
+	case 6:						\
+		write_sysreg(val, reg_name##6_el1);	\
+		break;					\
+	case 7:						\
+		write_sysreg(val, reg_name##7_el1);	\
+		break;					\
+	case 8:						\
+		write_sysreg(val, reg_name##8_el1);	\
+		break;					\
+	case 9:						\
+		write_sysreg(val, reg_name##9_el1);	\
+		break;					\
+	case 10:					\
+		write_sysreg(val, reg_name##10_el1);	\
+		break;					\
+	case 11:					\
+		write_sysreg(val, reg_name##11_el1);	\
+		break;					\
+	case 12:					\
+		write_sysreg(val, reg_name##12_el1);	\
+		break;					\
+	case 13:					\
+		write_sysreg(val, reg_name##13_el1);	\
+		break;					\
+	case 14:					\
+		write_sysreg(val, reg_name##14_el1);	\
+		break;					\
+	case 15:					\
+		write_sysreg(val, reg_name##15_el1);	\
+		break;					\
+	default:					\
+		GUEST_ASSERT(0);			\
+	}						\
+}
+
+/* Define write_dbgbcr()/write_dbgbvr()/write_dbgwcr()/write_dbgwvr() */
+GEN_DEBUG_WRITE_REG(dbgbcr)
+GEN_DEBUG_WRITE_REG(dbgbvr)
+GEN_DEBUG_WRITE_REG(dbgwcr)
+GEN_DEBUG_WRITE_REG(dbgwvr)
+
 static void reset_debug_state(void)
 {
+	uint8_t brps, wrps, i;
+	uint64_t dfr0;
+
 	asm volatile("msr daifset, #8");

 	write_sysreg(0, osdlr_el1);
@@ -38,11 +112,21 @@ static void reset_debug_state(void)
 	isb();

 	write_sysreg(0, mdscr_el1);
-	/* This test only uses the first bp and wp slot. */
-	write_sysreg(0, dbgbvr0_el1);
-	write_sysreg(0, dbgbcr0_el1);
-	write_sysreg(0, dbgwcr0_el1);
-	write_sysreg(0, dbgwvr0_el1);
+	write_sysreg(0, contextidr_el1);
+
+	/* Reset all bcr/bvr/wcr/wvr registers */
+	dfr0 = read_sysreg(id_aa64dfr0_el1);
+	brps = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_BRPS), dfr0);
+	for (i = 0; i <= brps; i++) {
+		write_dbgbcr(i, 0);
+		write_dbgbvr(i, 0);
+	}
+	wrps = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_WRPS), dfr0);
+	for (i = 0; i <= wrps; i++) {
+		write_dbgwcr(i, 0);
+		write_dbgwvr(i, 0);
+	}
+
 	isb();
 }

@@ -54,16 +138,10 @@ static void enable_os_lock(void)
 	GUEST_ASSERT(read_sysreg(oslsr_el1) & 2);
 }

-static void install_wp(uint64_t addr)
+static void enable_monitor_debug_exceptions(void)
 {
-	uint32_t wcr;
 	uint32_t mdscr;

-	wcr = DBGWCR_LEN8 | DBGWCR_RD | DBGWCR_WR | DBGWCR_EL1 | DBGWCR_E;
-	write_sysreg(wcr, dbgwcr0_el1);
-	write_sysreg(addr, dbgwvr0_el1);
-	isb();
-
 	asm volatile("msr daifclr, #8");

 	mdscr = read_sysreg(mdscr_el1) | MDSCR_KDE | MDSCR_MDE;
@@ -71,21 +149,76 @@ static void install_wp(uint64_t addr)
 	isb();
 }

-static void install_hw_bp(uint64_t addr)
+static void install_wp(uint8_t wpn, uint64_t addr)
+{
+	uint32_t wcr;
+
+	wcr = DBGWCR_LEN8 | DBGWCR_RD | DBGWCR_WR | DBGWCR_EL1 | DBGWCR_E;
+	write_dbgwcr(wpn, wcr);
+	write_dbgwvr(wpn, addr);
+
+	isb();
+
+	enable_monitor_debug_exceptions();
+}
+
+static void install_hw_bp(uint8_t bpn, uint64_t addr)
 {
 	uint32_t bcr;
-	uint32_t mdscr;

 	bcr = DBGBCR_LEN8 | DBGBCR_EXEC | DBGBCR_EL1 | DBGBCR_E;
-	write_sysreg(bcr, dbgbcr0_el1);
-	write_sysreg(addr, dbgbvr0_el1);
+	write_dbgbcr(bpn, bcr);
+	write_dbgbvr(bpn, addr);
 	isb();

-	asm volatile("msr daifclr, #8");
+	enable_monitor_debug_exceptions();
+}

-	mdscr = read_sysreg(mdscr_el1) | MDSCR_KDE | MDSCR_MDE;
-	write_sysreg(mdscr, mdscr_el1);
+static void install_wp_ctx(uint8_t addr_wp, uint8_t ctx_bp, uint64_t addr,
+			   uint64_t ctx)
+{
+	uint32_t wcr;
+	uint64_t ctx_bcr;
+
+	/* Setup a context-aware breakpoint for Linked Context ID Match */
+	ctx_bcr = DBGBCR_LEN8 | DBGBCR_EXEC | DBGBCR_EL1 | DBGBCR_E |
+		  DBGBCR_BT_CTX_LINK;
+	write_dbgbcr(ctx_bp, ctx_bcr);
+	write_dbgbvr(ctx_bp, ctx);
+
+	/* Setup a linked watchpoint (linked to the context-aware breakpoint) */
+	wcr = DBGWCR_LEN8 | DBGWCR_RD | DBGWCR_WR | DBGWCR_EL1 | DBGWCR_E |
+	      DBGWCR_WT_LINK | ((uint32_t)ctx_bp << DBGWCR_LBN_SHIFT);
+	write_dbgwcr(addr_wp, wcr);
+	write_dbgwvr(addr_wp, addr);
 	isb();
+
+	enable_monitor_debug_exceptions();
+}
+
+void install_hw_bp_ctx(uint8_t addr_bp, uint8_t ctx_bp, uint64_t addr,
+		       uint64_t ctx)
+{
+	uint32_t addr_bcr, ctx_bcr;
+
+	/* Setup a context-aware breakpoint for Linked Context ID Match */
+	ctx_bcr = DBGBCR_LEN8 | DBGBCR_EXEC | DBGBCR_EL1 | DBGBCR_E |
+		  DBGBCR_BT_CTX_LINK;
+	write_dbgbcr(ctx_bp, ctx_bcr);
+	write_dbgbvr(ctx_bp, ctx);
+
+	/*
+	 * Setup a normal breakpoint for Linked Address Match, and link it
+	 * to the context-aware breakpoint.
+	 */
+	addr_bcr = DBGBCR_LEN8 | DBGBCR_EXEC | DBGBCR_EL1 | DBGBCR_E |
+		   DBGBCR_BT_ADDR_LINK_CTX |
+		   ((uint32_t)ctx_bp << DBGBCR_LBN_SHIFT);
+	write_dbgbcr(addr_bp, addr_bcr);
+	write_dbgbvr(addr_bp, addr);
+	isb();
+
+	enable_monitor_debug_exceptions();
 }

 static void install_ss(void)
@@ -101,52 +234,42 @@ static void install_ss(void)

 static volatile char write_data;

-static void guest_code(void)
+static void guest_code(uint8_t bpn, uint8_t wpn, uint8_t ctx_bpn)
 {
-	GUEST_SYNC(0);
+	uint64_t ctx = 0xabcdef;	/* a random context number */

 	/* Software-breakpoint */
 	reset_debug_state();
 	asm volatile("sw_bp: brk #0");
 	GUEST_ASSERT_EQ(sw_bp_addr, PC(sw_bp));

-	GUEST_SYNC(1);
-
 	/* Hardware-breakpoint */
 	reset_debug_state();
-	install_hw_bp(PC(hw_bp));
+	install_hw_bp(bpn, PC(hw_bp));
 	asm volatile("hw_bp: nop");
 	GUEST_ASSERT_EQ(hw_bp_addr, PC(hw_bp));

-	GUEST_SYNC(2);
-
 	/* Hardware-breakpoint + svc */
 	reset_debug_state();
-	install_hw_bp(PC(bp_svc));
+	install_hw_bp(bpn, PC(bp_svc));
 	asm volatile("bp_svc: svc #0");
 	GUEST_ASSERT_EQ(hw_bp_addr, PC(bp_svc));
 	GUEST_ASSERT_EQ(svc_addr, PC(bp_svc) + 4);

-	GUEST_SYNC(3);
-
 	/* Hardware-breakpoint + software-breakpoint */
 	reset_debug_state();
-	install_hw_bp(PC(bp_brk));
+	install_hw_bp(bpn, PC(bp_brk));
 	asm volatile("bp_brk: brk #0");
 	GUEST_ASSERT_EQ(sw_bp_addr, PC(bp_brk));
 	GUEST_ASSERT_EQ(hw_bp_addr, PC(bp_brk));

-	GUEST_SYNC(4);
-
 	/* Watchpoint */
 	reset_debug_state();
-	install_wp(PC(write_data));
+	install_wp(wpn, PC(write_data));
 	write_data = 'x';
 	GUEST_ASSERT_EQ(write_data, 'x');
 	GUEST_ASSERT_EQ(wp_data_addr, PC(write_data));

-	GUEST_SYNC(5);
-
 	/* Single-step */
 	reset_debug_state();
 	install_ss();
@@ -160,8 +283,6 @@ static void guest_code(void)
 	GUEST_ASSERT_EQ(ss_addr[1], PC(ss_start) + 4);
 	GUEST_ASSERT_EQ(ss_addr[2], PC(ss_start) + 8);

-	GUEST_SYNC(6);
-
 	/* OS Lock does not block software-breakpoint */
 	reset_debug_state();
 	enable_os_lock();
@@ -169,30 +290,24 @@ static void guest_code(void)
 	asm volatile("sw_bp2: brk #0");
 	GUEST_ASSERT_EQ(sw_bp_addr, PC(sw_bp2));

-	GUEST_SYNC(7);
-
 	/* OS Lock blocking hardware-breakpoint */
 	reset_debug_state();
 	enable_os_lock();
-	install_hw_bp(PC(hw_bp2));
+	install_hw_bp(bpn, PC(hw_bp2));
 	hw_bp_addr = 0;
 	asm volatile("hw_bp2: nop");
 	GUEST_ASSERT_EQ(hw_bp_addr, 0);

-	GUEST_SYNC(8);
-
 	/* OS Lock blocking watchpoint */
 	reset_debug_state();
 	enable_os_lock();
 	write_data = '\0';
 	wp_data_addr = 0;
-	install_wp(PC(write_data));
+	install_wp(wpn, PC(write_data));
 	write_data = 'x';
 	GUEST_ASSERT_EQ(write_data, 'x');
 	GUEST_ASSERT_EQ(wp_data_addr, 0);

-	GUEST_SYNC(9);
-
 	/* OS Lock blocking single-step */
 	reset_debug_state();
 	enable_os_lock();
@@ -205,6 +320,27 @@ static void guest_code(void)
 		     : : : "x0");
 	GUEST_ASSERT_EQ(ss_addr[0], 0);

+	/* Linked hardware-breakpoint */
+	hw_bp_addr = 0;
+	reset_debug_state();
+	install_hw_bp_ctx(bpn, ctx_bpn, PC(hw_bp_ctx), ctx);
+	/* Set context id */
+	write_sysreg(ctx, contextidr_el1);
+	isb();
+	asm volatile("hw_bp_ctx: nop");
+	write_sysreg(0, contextidr_el1);
+	GUEST_ASSERT_EQ(hw_bp_addr, PC(hw_bp_ctx));
+
+	/* Linked watchpoint */
+	reset_debug_state();
+	install_wp_ctx(wpn, ctx_bpn, PC(write_data), ctx);
+	/* Set context id */
+	write_sysreg(ctx, contextidr_el1);
+	isb();
+	write_data = 'x';
+	GUEST_ASSERT_EQ(write_data, 'x');
+	GUEST_ASSERT_EQ(wp_data_addr, PC(write_data));
+
 	GUEST_DONE();
 }

@@ -276,20 +412,16 @@ static void guest_code_ss(int test_cnt)
 	GUEST_DONE();
 }

-static int debug_version(struct kvm_vcpu *vcpu)
+static int debug_version(uint64_t id_aa64dfr0)
 {
-	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)
+static void test_guest_debug_exceptions(uint8_t bpn, uint8_t wpn, uint8_t ctx_bpn)
 {
 	struct kvm_vcpu *vcpu;
 	struct kvm_vm *vm;
 	struct ucall uc;
-	int stage;

 	vm = vm_create_with_one_vcpu(&vcpu, guest_code);

@@ -307,23 +439,19 @@ static void test_guest_debug_exceptions(void)
 	vm_install_sync_handler(vm, VECTOR_SYNC_CURRENT,
 				ESR_EC_SVC64, guest_svc_handler);

-	for (stage = 0; stage < 11; stage++) {
-		vcpu_run(vcpu);
+	/* Specify bpn/wpn/ctx_bpn to be tested */
+	vcpu_args_set(vcpu, 3, bpn, wpn, ctx_bpn);
+	pr_debug("Use bpn#%d, wpn#%d and ctx_bpn#%d\n", bpn, wpn, ctx_bpn);

-		switch (get_ucall(vcpu, &uc)) {
-		case UCALL_SYNC:
-			TEST_ASSERT(uc.args[1] == stage,
-				"Stage %d: Unexpected sync ucall, got %lx",
-				stage, (ulong)uc.args[1]);
-			break;
-		case UCALL_ABORT:
-			REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx");
-			break;
-		case UCALL_DONE:
-			goto done;
-		default:
-			TEST_FAIL("Unknown ucall %lu", uc.cmd);
-		}
+	vcpu_run(vcpu);
+	switch (get_ucall(vcpu, &uc)) {
+	case UCALL_ABORT:
+		REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx");
+		break;
+	case UCALL_DONE:
+		goto done;
+	default:
+		TEST_FAIL("Unknown ucall %lu", uc.cmd);
 	}

 done:
@@ -400,6 +528,43 @@ void test_single_step_from_userspace(int test_cnt)
 	kvm_vm_free(vm);
 }

+/*
+ * Run debug testing using the various breakpoint#, watchpoint# and
+ * context-aware breakpoint# with the given ID_AA64DFR0_EL1 configuration.
+ */
+void test_guest_debug_exceptions_all(uint64_t aa64dfr0)
+{
+	uint8_t brp_num, wrp_num, ctx_brp_num, normal_brp_num, ctx_brp_base;
+	int b, w, c;
+
+	/* Number of breakpoints */
+	brp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_BRPS), aa64dfr0) + 1;
+	__TEST_REQUIRE(brp_num >= 2, "At least two breakpoints are required");
+
+	/* Number of watchpoints */
+	wrp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_WRPS), aa64dfr0) + 1;
+
+	/* Number of context aware breakpoints */
+	ctx_brp_num = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_CTX_CMPS), aa64dfr0) + 1;
+
+	pr_debug("%s brp_num:%d, wrp_num:%d, ctx_brp_num:%d\n", __func__,
+		 brp_num, wrp_num, ctx_brp_num);
+
+	/* Number of normal (non-context aware) breakpoints */
+	normal_brp_num = brp_num - ctx_brp_num;
+
+	/* Lowest context aware breakpoint number */
+	ctx_brp_base = normal_brp_num;
+
+	/* Run tests with all supported breakpoints/watchpoints */
+	for (c = ctx_brp_base; c < ctx_brp_base + ctx_brp_num; c++) {
+		for (b = 0; b < normal_brp_num; b++) {
+			for (w = 0; w < wrp_num; w++)
+				test_guest_debug_exceptions(b, w, c);
+		}
+	}
+}
+
 static void help(char *name)
 {
 	puts("");
@@ -414,9 +579,11 @@ int main(int argc, char *argv[])
 	struct kvm_vm *vm;
 	int opt;
 	int ss_iteration = 10000;
+	uint64_t aa64dfr0;

 	vm = vm_create_with_one_vcpu(&vcpu, guest_code);
-	__TEST_REQUIRE(debug_version(vcpu) >= 6,
+	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1), &aa64dfr0);
+	__TEST_REQUIRE(debug_version(aa64dfr0) >= 6,
 		       "Armv8 debug architecture not supported.");
 	kvm_vm_free(vm);

@@ -432,7 +599,7 @@ int main(int argc, char *argv[])
 		}
 	}

-	test_guest_debug_exceptions();
+	test_guest_debug_exceptions_all(aa64dfr0);
 	test_single_step_from_userspace(ss_iteration);

 	return 0;