Merge tag 'loongarch-kvm-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson into HEAD

LoongArch KVM changes for v6.11

1. Add ParaVirt steal time support.
2. Add some VM migration enhancement.
3. Add perf kvm-stat support for loongarch.

16 files changed, 289 insertions, 15 deletions

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 5c35c0d89306..e6d56b555369 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -214,6 +214,7 @@ NON_CONFIG_TARGETS := clean python-clean TAGS tags cscope help
 
 ifdef MAKECMDGOALS
 ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
+  VMLINUX_H=$(src-perf)/util/bpf_skel/vmlinux/vmlinux.h
   config := 0
 endif
 endif
diff --git a/tools/perf/arch/loongarch/Makefile b/tools/perf/arch/loongarch/Makefile
index 3992a67a87d9..c89d6bb6b184 100644
--- a/tools/perf/arch/loongarch/Makefile
+++ b/tools/perf/arch/loongarch/Makefile
@@ -4,6 +4,7 @@ PERF_HAVE_DWARF_REGS := 1
 endif
 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
 PERF_HAVE_JITDUMP := 1
+HAVE_KVM_STAT_SUPPORT := 1
 
 #
 # Syscall table generation for perf
diff --git a/tools/perf/arch/loongarch/util/Build b/tools/perf/arch/loongarch/util/Build
index d776125a2d06..b12d374d7096 100644
--- a/tools/perf/arch/loongarch/util/Build
+++ b/tools/perf/arch/loongarch/util/Build
@@ -1,5 +1,7 @@
+perf-y += header.o
 perf-y += perf_regs.o
 
 perf-$(CONFIG_DWARF)     += dwarf-regs.o
 perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
 perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
+perf-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o
diff --git a/tools/perf/arch/loongarch/util/header.c b/tools/perf/arch/loongarch/util/header.c
new file mode 100644
index 000000000000..d962dff55512
--- /dev/null
+++ b/tools/perf/arch/loongarch/util/header.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Implementation of get_cpuid().
+ *
+ * Author: Nikita Shubin <n.shubin@yadro.com>
+ *         Bibo Mao <maobibo@loongson.cn>
+ *         Huacai Chen <chenhuacai@loongson.cn>
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <api/fs/fs.h>
+#include <errno.h>
+#include "util/debug.h"
+#include "util/header.h"
+
+/*
+ * Output example from /proc/cpuinfo
+ *   CPU Family              : Loongson-64bit
+ *   Model Name              : Loongson-3C5000
+ *   CPU Revision            : 0x10
+ *   FPU Revision            : 0x01
+ */
+#define CPUINFO_MODEL	"Model Name"
+#define CPUINFO		"/proc/cpuinfo"
+
+static char *_get_field(const char *line)
+{
+	char *line2, *nl;
+
+	line2 = strrchr(line, ' ');
+	if (!line2)
+		return NULL;
+
+	line2++;
+	nl = strrchr(line, '\n');
+	if (!nl)
+		return NULL;
+
+	return strndup(line2, nl - line2);
+}
+
+static char *_get_cpuid(void)
+{
+	unsigned long line_sz;
+	char *line, *model, *cpuid;
+	FILE *file;
+
+	file = fopen(CPUINFO, "r");
+	if (file == NULL)
+		return NULL;
+
+	line = model = cpuid = NULL;
+	while (getline(&line, &line_sz, file) != -1) {
+		if (strncmp(line, CPUINFO_MODEL, strlen(CPUINFO_MODEL)))
+			continue;
+
+		model = _get_field(line);
+		if (!model)
+			goto out_free;
+		break;
+	}
+
+	if (model && (asprintf(&cpuid, "%s", model) < 0))
+		cpuid = NULL;
+
+out_free:
+	fclose(file);
+	free(model);
+	return cpuid;
+}
+
+int get_cpuid(char *buffer, size_t sz)
+{
+	int ret = 0;
+	char *cpuid = _get_cpuid();
+
+	if (!cpuid)
+		return EINVAL;
+
+	if (sz < strlen(cpuid)) {
+		ret = ENOBUFS;
+		goto out_free;
+	}
+
+	scnprintf(buffer, sz, "%s", cpuid);
+
+out_free:
+	free(cpuid);
+	return ret;
+}
+
+char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
+{
+	return _get_cpuid();
+}
diff --git a/tools/perf/arch/loongarch/util/kvm-stat.c b/tools/perf/arch/loongarch/util/kvm-stat.c
new file mode 100644
index 000000000000..a7859a3a9a51
--- /dev/null
+++ b/tools/perf/arch/loongarch/util/kvm-stat.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+#include <memory.h>
+#include "util/kvm-stat.h"
+#include "util/parse-events.h"
+#include "util/debug.h"
+#include "util/evsel.h"
+#include "util/evlist.h"
+#include "util/pmus.h"
+
+#define LOONGARCH_EXCEPTION_INT		0
+#define LOONGARCH_EXCEPTION_PIL		1
+#define LOONGARCH_EXCEPTION_PIS		2
+#define LOONGARCH_EXCEPTION_PIF		3
+#define LOONGARCH_EXCEPTION_PME		4
+#define LOONGARCH_EXCEPTION_FPD		15
+#define LOONGARCH_EXCEPTION_SXD		16
+#define LOONGARCH_EXCEPTION_ASXD	17
+#define LOONGARCH_EXCEPTION_GSPR	22
+#define  LOONGARCH_EXCEPTION_CPUCFG	100
+#define  LOONGARCH_EXCEPTION_CSR	101
+#define  LOONGARCH_EXCEPTION_IOCSR	102
+#define  LOONGARCH_EXCEPTION_IDLE	103
+#define  LOONGARCH_EXCEPTION_OTHERS	104
+#define LOONGARCH_EXCEPTION_HVC		23
+
+#define loongarch_exception_type				\
+	{LOONGARCH_EXCEPTION_INT,  "Interrupt" },		\
+	{LOONGARCH_EXCEPTION_PIL,  "Mem Read" },		\
+	{LOONGARCH_EXCEPTION_PIS,  "Mem Store" },		\
+	{LOONGARCH_EXCEPTION_PIF,  "Inst Fetch" },		\
+	{LOONGARCH_EXCEPTION_PME,  "Mem Modify" },		\
+	{LOONGARCH_EXCEPTION_FPD,  "FPU" },			\
+	{LOONGARCH_EXCEPTION_SXD,  "LSX" },			\
+	{LOONGARCH_EXCEPTION_ASXD, "LASX" },			\
+	{LOONGARCH_EXCEPTION_GSPR, "Privilege Error" },		\
+	{LOONGARCH_EXCEPTION_HVC,  "Hypercall" },		\
+	{LOONGARCH_EXCEPTION_CPUCFG, "CPUCFG" },		\
+	{LOONGARCH_EXCEPTION_CSR,    "CSR" },			\
+	{LOONGARCH_EXCEPTION_IOCSR,  "IOCSR" },			\
+	{LOONGARCH_EXCEPTION_IDLE,   "Idle" },			\
+	{LOONGARCH_EXCEPTION_OTHERS, "Others" }
+
+define_exit_reasons_table(loongarch_exit_reasons, loongarch_exception_type);
+
+const char *vcpu_id_str = "vcpu_id";
+const char *kvm_exit_reason = "reason";
+const char *kvm_entry_trace = "kvm:kvm_enter";
+const char *kvm_reenter_trace = "kvm:kvm_reenter";
+const char *kvm_exit_trace = "kvm:kvm_exit";
+const char *kvm_events_tp[] = {
+	"kvm:kvm_enter",
+	"kvm:kvm_reenter",
+	"kvm:kvm_exit",
+	"kvm:kvm_exit_gspr",
+	NULL,
+};
+
+static bool event_begin(struct evsel *evsel,
+			struct perf_sample *sample, struct event_key *key)
+{
+	return exit_event_begin(evsel, sample, key);
+}
+
+static bool event_end(struct evsel *evsel,
+		      struct perf_sample *sample __maybe_unused,
+		      struct event_key *key __maybe_unused)
+{
+	/*
+	 * LoongArch kvm is different with other architectures
+	 *
+	 * There is kvm:kvm_reenter or kvm:kvm_enter event adjacent with
+	 * kvm:kvm_exit event.
+	 *   kvm:kvm_enter   means returning to vmm and then to guest
+	 *   kvm:kvm_reenter means returning to guest immediately
+	 */
+	return evsel__name_is(evsel, kvm_entry_trace) || evsel__name_is(evsel, kvm_reenter_trace);
+}
+
+static void event_gspr_get_key(struct evsel *evsel,
+			       struct perf_sample *sample, struct event_key *key)
+{
+	unsigned int insn;
+
+	key->key = LOONGARCH_EXCEPTION_OTHERS;
+	insn = evsel__intval(evsel, sample, "inst_word");
+
+	switch (insn >> 24) {
+	case 0:
+		/* CPUCFG inst trap */
+		if ((insn >> 10) == 0x1b)
+			key->key = LOONGARCH_EXCEPTION_CPUCFG;
+		break;
+	case 4:
+		/* CSR inst trap */
+		key->key = LOONGARCH_EXCEPTION_CSR;
+		break;
+	case 6:
+		/* IOCSR inst trap */
+		if ((insn >> 15) == 0xc90)
+			key->key = LOONGARCH_EXCEPTION_IOCSR;
+		else if ((insn >> 15) == 0xc91)
+			/* Idle inst trap */
+			key->key = LOONGARCH_EXCEPTION_IDLE;
+		break;
+	default:
+		key->key = LOONGARCH_EXCEPTION_OTHERS;
+		break;
+	}
+}
+
+static struct child_event_ops child_events[] = {
+	{ .name = "kvm:kvm_exit_gspr", .get_key = event_gspr_get_key },
+	{ NULL, NULL },
+};
+
+static struct kvm_events_ops exit_events = {
+	.is_begin_event = event_begin,
+	.is_end_event = event_end,
+	.child_ops = child_events,
+	.decode_key = exit_event_decode_key,
+	.name = "VM-EXIT"
+};
+
+struct kvm_reg_events_ops kvm_reg_events_ops[] = {
+	{ .name	= "vmexit", .ops = &exit_events, },
+	{ NULL, NULL },
+};
+
+const char * const kvm_skip_events[] = {
+	NULL,
+};
+
+int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid __maybe_unused)
+{
+	kvm->exit_reasons_isa = "loongarch64";
+	kvm->exit_reasons = loongarch_exit_reasons;
+	return 0;
+}
diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index 532b855df589..1464c6be6eb3 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -376,3 +376,4 @@
 459	n64	lsm_get_self_attr		sys_lsm_get_self_attr
 460	n64	lsm_set_self_attr		sys_lsm_set_self_attr
 461	n64	lsm_list_modules		sys_lsm_list_modules
+462	n64	mseal				sys_mseal
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 17173b82ca21..3656f1ca7a21 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -548,3 +548,4 @@
 459	common	lsm_get_self_attr		sys_lsm_get_self_attr
 460	common	lsm_set_self_attr		sys_lsm_set_self_attr
 461	common	lsm_list_modules		sys_lsm_list_modules
+462	common	mseal				sys_mseal
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index 095bb86339a7..bd0fee24ad10 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -464,3 +464,4 @@
 459  common	lsm_get_self_attr	sys_lsm_get_self_attr		sys_lsm_get_self_attr
 460  common	lsm_set_self_attr	sys_lsm_set_self_attr		sys_lsm_set_self_attr
 461  common	lsm_list_modules	sys_lsm_list_modules		sys_lsm_list_modules
+462  common	mseal			sys_mseal			sys_mseal
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 7e8d46f4147f..a396f6e6ab5b 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -374,7 +374,7 @@
 450	common	set_mempolicy_home_node	sys_set_mempolicy_home_node
 451	common	cachestat		sys_cachestat
 452	common	fchmodat2		sys_fchmodat2
-453	64	map_shadow_stack	sys_map_shadow_stack
+453	common	map_shadow_stack	sys_map_shadow_stack
 454	common	futex_wake		sys_futex_wake
 455	common	futex_wait		sys_futex_wait
 456	common	futex_requeue		sys_futex_requeue
@@ -383,6 +383,7 @@
 459	common	lsm_get_self_attr	sys_lsm_get_self_attr
 460	common	lsm_set_self_attr	sys_lsm_set_self_attr
 461	common	lsm_list_modules	sys_lsm_list_modules
+462 	common  mseal			sys_mseal
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 66a3de8ac661..0a8ba1323d64 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1956,8 +1956,7 @@ static void record__read_lost_samples(struct record *rec)
 
 				if (count.lost) {
 					if (!lost) {
-						lost = zalloc(sizeof(*lost) +
-							      session->machines.host.id_hdr_size);
+						lost = zalloc(PERF_SAMPLE_MAX_SIZE);
 						if (!lost) {
 							pr_debug("Memory allocation failed\n");
 							return;
@@ -1973,8 +1972,7 @@ static void record__read_lost_samples(struct record *rec)
 		lost_count = perf_bpf_filter__lost_count(evsel);
 		if (lost_count) {
 			if (!lost) {
-				lost = zalloc(sizeof(*lost) +
-					      session->machines.host.id_hdr_size);
+				lost = zalloc(PERF_SAMPLE_MAX_SIZE);
 				if (!lost) {
 					pr_debug("Memory allocation failed\n");
 					return;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 51eca671c797..08a3a6effac1 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -765,7 +765,7 @@ static const char *fcntl_cmds[] = {
 static DEFINE_STRARRAY(fcntl_cmds, "F_");
 
 static const char *fcntl_linux_specific_cmds[] = {
-	"SETLEASE", "GETLEASE", "NOTIFY", [5] =	"CANCELLK", "DUPFD_CLOEXEC",
+	"SETLEASE", "GETLEASE", "NOTIFY", "DUPFD_QUERY", [5] = "CANCELLK", "DUPFD_CLOEXEC",
 	"SETPIPE_SZ", "GETPIPE_SZ", "ADD_SEALS", "GET_SEALS",
 	"GET_RW_HINT", "SET_RW_HINT", "GET_FILE_RW_HINT", "SET_FILE_RW_HINT",
 };
diff --git a/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h b/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h
index d18bfb238f66..13aea8fc3d45 100644
--- a/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h
+++ b/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h
@@ -97,10 +97,16 @@
 
 #define LOCAL_TIMER_VECTOR		0xec
 
+/*
+ * Posted interrupt notification vector for all device MSIs delivered to
+ * the host kernel.
+ */
+#define POSTED_MSI_NOTIFICATION_VECTOR	0xeb
+
 #define NR_VECTORS			 256
 
 #ifdef CONFIG_X86_LOCAL_APIC
-#define FIRST_SYSTEM_VECTOR		LOCAL_TIMER_VECTOR
+#define FIRST_SYSTEM_VECTOR		POSTED_MSI_NOTIFICATION_VECTOR
 #else
 #define FIRST_SYSTEM_VECTOR		NR_VECTORS
 #endif
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
index 139c330ccf2c..89d16b90370b 100644
--- a/tools/perf/trace/beauty/include/linux/socket.h
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -16,6 +16,7 @@ struct cred;
 struct socket;
 struct sock;
 struct sk_buff;
+struct proto_accept_arg;
 
 #define __sockaddr_check_size(size)	\
 	BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage)))
@@ -433,7 +434,7 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size,
 extern int __sys_sendto(int fd, void __user *buff, size_t len,
 			unsigned int flags, struct sockaddr __user *addr,
 			int addr_len);
-extern struct file *do_accept(struct file *file, unsigned file_flags,
+extern struct file *do_accept(struct file *file, struct proto_accept_arg *arg,
 			      struct sockaddr __user *upeer_sockaddr,
 			      int __user *upeer_addrlen, int flags);
 extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
diff --git a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
index 282e90aeb163..c0bcc185fa48 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
@@ -9,6 +9,14 @@
 #define F_GETLEASE	(F_LINUX_SPECIFIC_BASE + 1)
 
 /*
+ * Request nofications on a directory.
+ * See below for events that may be notified.
+ */
+#define F_NOTIFY	(F_LINUX_SPECIFIC_BASE + 2)
+
+#define F_DUPFD_QUERY	(F_LINUX_SPECIFIC_BASE + 3)
+
+/*
  * Cancel a blocking posix lock; internal use only until we expose an
  * asynchronous lock api to userspace:
  */
@@ -18,12 +26,6 @@
 #define F_DUPFD_CLOEXEC	(F_LINUX_SPECIFIC_BASE + 6)
 
 /*
- * Request nofications on a directory.
- * See below for events that may be notified.
- */
-#define F_NOTIFY	(F_LINUX_SPECIFIC_BASE+2)
-
-/*
  * Set and get of pipe page size array
  */
 #define F_SETPIPE_SZ	(F_LINUX_SPECIFIC_BASE + 7)
diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
index 370ed14b1ae0..35791791a879 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
@@ -306,4 +306,26 @@ struct prctl_mm_map {
 # define PR_RISCV_V_VSTATE_CTRL_NEXT_MASK	0xc
 # define PR_RISCV_V_VSTATE_CTRL_MASK		0x1f
 
+#define PR_RISCV_SET_ICACHE_FLUSH_CTX	71
+# define PR_RISCV_CTX_SW_FENCEI_ON	0
+# define PR_RISCV_CTX_SW_FENCEI_OFF	1
+# define PR_RISCV_SCOPE_PER_PROCESS	0
+# define PR_RISCV_SCOPE_PER_THREAD	1
+
+/* PowerPC Dynamic Execution Control Register (DEXCR) controls */
+#define PR_PPC_GET_DEXCR		72
+#define PR_PPC_SET_DEXCR		73
+/* DEXCR aspect to act on */
+# define PR_PPC_DEXCR_SBHE		0 /* Speculative branch hint enable */
+# define PR_PPC_DEXCR_IBRTPD		1 /* Indirect branch recurrent target prediction disable */
+# define PR_PPC_DEXCR_SRAPD		2 /* Subroutine return address prediction disable */
+# define PR_PPC_DEXCR_NPHIE		3 /* Non-privileged hash instruction enable */
+/* Action to apply / return */
+# define PR_PPC_DEXCR_CTRL_EDITABLE	 0x1 /* Aspect can be modified with PR_PPC_SET_DEXCR */
+# define PR_PPC_DEXCR_CTRL_SET		 0x2 /* Set the aspect for this process */
+# define PR_PPC_DEXCR_CTRL_CLEAR	 0x4 /* Clear the aspect for this process */
+# define PR_PPC_DEXCR_CTRL_SET_ONEXEC	 0x8 /* Set the aspect on exec */
+# define PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC	0x10 /* Clear the aspect on exec */
+# define PR_PPC_DEXCR_CTRL_MASK		0x1f
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/tools/perf/trace/beauty/include/uapi/linux/stat.h b/tools/perf/trace/beauty/include/uapi/linux/stat.h
index 2f2ee82d5517..67626d535316 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/stat.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/stat.h
@@ -126,8 +126,9 @@ struct statx {
 	__u64	stx_mnt_id;
 	__u32	stx_dio_mem_align;	/* Memory buffer alignment for direct I/O */
 	__u32	stx_dio_offset_align;	/* File offset alignment for direct I/O */
+	__u64	stx_subvol;	/* Subvolume identifier */
 	/* 0xa0 */
-	__u64	__spare3[12];	/* Spare space for future expansion */
+	__u64	__spare3[11];	/* Spare space for future expansion */
 	/* 0x100 */
 };
 
@@ -155,6 +156,7 @@ struct statx {
 #define STATX_MNT_ID		0x00001000U	/* Got stx_mnt_id */
 #define STATX_DIOALIGN		0x00002000U	/* Want/got direct I/O alignment info */
 #define STATX_MNT_ID_UNIQUE	0x00004000U	/* Want/got extended stx_mount_id */
+#define STATX_SUBVOL		0x00008000U	/* Want/got stx_subvol */
 
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */