Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Ingo Molnar:
 "On the kernel side there's a bunch of ring-buffer ordering fixes for a
  reproducible bug, plus a PEBS constraints regression fix.

  Plus tooling fixes"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  tools headers UAPI: Sync kvm.h headers with the kernel sources
  perf record: Fix s390 missing module symbol and warning for non-root users
  perf machine: Read also the end of the kernel
  perf test vmlinux-kallsyms: Ignore aliases to _etext when searching on kallsyms
  perf session: Add missing swap ops for namespace events
  perf namespace: Protect reading thread's namespace
  tools headers UAPI: Sync drm/drm.h with the kernel
  tools headers UAPI: Sync drm/i915_drm.h with the kernel
  tools headers UAPI: Sync linux/fs.h with the kernel
  tools headers UAPI: Sync linux/sched.h with the kernel
  tools arch x86: Sync asm/cpufeatures.h with the with the kernel
  tools include UAPI: Update copy of files related to new fspick, fsmount, fsconfig, fsopen, move_mount and open_tree syscalls
  perf arm64: Fix mksyscalltbl when system kernel headers are ahead of the kernel
  perf data: Fix 'strncat may truncate' build failure with recent gcc
  perf/ring-buffer: Use regular variables for nesting
  perf/ring-buffer: Always use {READ,WRITE}_ONCE() for rb->user_page data
  perf/ring_buffer: Add ordering to rb->nest increment
  perf/ring_buffer: Fix exposing a temporarily decreased data_head
  perf/x86/intel/ds: Fix EVENT vs. UEVENT PEBS constraints

23 files changed, 547 insertions, 124 deletions

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 7a9f5dac5abe..7acc526b4ad2 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -684,7 +684,7 @@ struct event_constraint intel_core2_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1),    /* MEM_LOAD_RETIRED.* */
 	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x01),
 	EVENT_CONSTRAINT_END
 };
 
@@ -693,7 +693,7 @@ struct event_constraint intel_atom_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1),    /* MEM_LOAD_RETIRED.* */
 	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x01),
 	/* Allow all events as PEBS with no flags */
 	INTEL_ALL_EVENT_CONSTRAINT(0, 0x1),
 	EVENT_CONSTRAINT_END
@@ -701,7 +701,7 @@ struct event_constraint intel_atom_pebs_event_constraints[] = {
 
 struct event_constraint intel_slm_pebs_event_constraints[] = {
 	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x1),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x1),
 	/* Allow all events as PEBS with no flags */
 	INTEL_ALL_EVENT_CONSTRAINT(0, 0x1),
 	EVENT_CONSTRAINT_END
@@ -726,7 +726,7 @@ struct event_constraint intel_nehalem_pebs_event_constraints[] = {
 	INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf),    /* MEM_LOAD_RETIRED.* */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf),    /* FP_ASSIST.* */
 	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x0f),
 	EVENT_CONSTRAINT_END
 };
 
@@ -743,7 +743,7 @@ struct event_constraint intel_westmere_pebs_event_constraints[] = {
 	INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf),    /* MEM_LOAD_RETIRED.* */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf),    /* FP_ASSIST.* */
 	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x0f),
 	EVENT_CONSTRAINT_END
 };
 
@@ -752,7 +752,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
 	INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
 	INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
 	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf),
         INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
         INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
         INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -767,9 +767,9 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = {
         INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
 	INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
 	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf),
 	/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2),
 	INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -783,9 +783,9 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
 	INTEL_PLD_CONSTRAINT(0x01cd, 0xf),    /* MEM_TRANS_RETIRED.* */
 	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf),
 	/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2),
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */
@@ -806,9 +806,9 @@ struct event_constraint intel_bdw_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
 	INTEL_PLD_CONSTRAINT(0x01cd, 0xf),    /* MEM_TRANS_RETIRED.* */
 	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf),
 	/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2),
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */
@@ -829,9 +829,9 @@ struct event_constraint intel_bdw_pebs_event_constraints[] = {
 struct event_constraint intel_skl_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x2),	/* INST_RETIRED.PREC_DIST */
 	/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2),
 	/* INST_RETIRED.TOTAL_CYCLES_PS (inv=1, cmask=16) (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f),
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x0f),
 	INTEL_PLD_CONSTRAINT(0x1cd, 0xf),		      /* MEM_TRANS_RETIRED.* */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 79c47076700a..3aef4191798c 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -24,7 +24,7 @@ struct ring_buffer {
 	atomic_t			poll;		/* POLL_ for wakeups */
 
 	local_t				head;		/* write position    */
-	local_t				nest;		/* nested writers    */
+	unsigned int			nest;		/* nested writers    */
 	local_t				events;		/* event limit       */
 	local_t				wakeup;		/* wakeup stamp      */
 	local_t				lost;		/* nr records lost   */
@@ -41,7 +41,7 @@ struct ring_buffer {
 
 	/* AUX area */
 	long				aux_head;
-	local_t				aux_nest;
+	unsigned int			aux_nest;
 	long				aux_wakeup;	/* last aux_watermark boundary crossed by aux_head */
 	unsigned long			aux_pgoff;
 	int				aux_nr_pages;
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 674b35383491..ffb59a4ef4ff 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -38,7 +38,12 @@ static void perf_output_get_handle(struct perf_output_handle *handle)
 	struct ring_buffer *rb = handle->rb;
 
 	preempt_disable();
-	local_inc(&rb->nest);
+
+	/*
+	 * Avoid an explicit LOAD/STORE such that architectures with memops
+	 * can use them.
+	 */
+	(*(volatile unsigned int *)&rb->nest)++;
 	handle->wakeup = local_read(&rb->wakeup);
 }
 
@@ -46,17 +51,35 @@ static void perf_output_put_handle(struct perf_output_handle *handle)
 {
 	struct ring_buffer *rb = handle->rb;
 	unsigned long head;
+	unsigned int nest;
+
+	/*
+	 * If this isn't the outermost nesting, we don't have to update
+	 * @rb->user_page->data_head.
+	 */
+	nest = READ_ONCE(rb->nest);
+	if (nest > 1) {
+		WRITE_ONCE(rb->nest, nest - 1);
+		goto out;
+	}
 
 again:
+	/*
+	 * In order to avoid publishing a head value that goes backwards,
+	 * we must ensure the load of @rb->head happens after we've
+	 * incremented @rb->nest.
+	 *
+	 * Otherwise we can observe a @rb->head value before one published
+	 * by an IRQ/NMI happening between the load and the increment.
+	 */
+	barrier();
 	head = local_read(&rb->head);
 
 	/*
-	 * IRQ/NMI can happen here, which means we can miss a head update.
+	 * IRQ/NMI can happen here and advance @rb->head, causing our
+	 * load above to be stale.
 	 */
 
-	if (!local_dec_and_test(&rb->nest))
-		goto out;
-
 	/*
 	 * Since the mmap() consumer (userspace) can run on a different CPU:
 	 *
@@ -84,14 +107,23 @@ again:
 	 * See perf_output_begin().
 	 */
 	smp_wmb(); /* B, matches C */
-	rb->user_page->data_head = head;
+	WRITE_ONCE(rb->user_page->data_head, head);
 
 	/*
-	 * Now check if we missed an update -- rely on previous implied
-	 * compiler barriers to force a re-read.
+	 * We must publish the head before decrementing the nest count,
+	 * otherwise an IRQ/NMI can publish a more recent head value and our
+	 * write will (temporarily) publish a stale value.
 	 */
+	barrier();
+	WRITE_ONCE(rb->nest, 0);
+
+	/*
+	 * Ensure we decrement @rb->nest before we validate the @rb->head.
+	 * Otherwise we cannot be sure we caught the 'last' nested update.
+	 */
+	barrier();
 	if (unlikely(head != local_read(&rb->head))) {
-		local_inc(&rb->nest);
+		WRITE_ONCE(rb->nest, 1);
 		goto again;
 	}
 
@@ -330,6 +362,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
 	struct perf_event *output_event = event;
 	unsigned long aux_head, aux_tail;
 	struct ring_buffer *rb;
+	unsigned int nest;
 
 	if (output_event->parent)
 		output_event = output_event->parent;
@@ -360,13 +393,16 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
 	if (!refcount_inc_not_zero(&rb->aux_refcount))
 		goto err;
 
+	nest = READ_ONCE(rb->aux_nest);
 	/*
 	 * Nesting is not supported for AUX area, make sure nested
 	 * writers are caught early
 	 */
-	if (WARN_ON_ONCE(local_xchg(&rb->aux_nest, 1)))
+	if (WARN_ON_ONCE(nest))
 		goto err_put;
 
+	WRITE_ONCE(rb->aux_nest, nest + 1);
+
 	aux_head = rb->aux_head;
 
 	handle->rb = rb;
@@ -394,7 +430,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
 		if (!handle->size) { /* A, matches D */
 			event->pending_disable = smp_processor_id();
 			perf_output_wakeup(handle);
-			local_set(&rb->aux_nest, 0);
+			WRITE_ONCE(rb->aux_nest, 0);
 			goto err_put;
 		}
 	}
@@ -471,7 +507,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 		perf_event_aux_event(handle->event, aux_head, size,
 				     handle->aux_flags);
 
-	rb->user_page->aux_head = rb->aux_head;
+	WRITE_ONCE(rb->user_page->aux_head, rb->aux_head);
 	if (rb_need_aux_wakeup(rb))
 		wakeup = true;
 
@@ -483,7 +519,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 
 	handle->event = NULL;
 
-	local_set(&rb->aux_nest, 0);
+	WRITE_ONCE(rb->aux_nest, 0);
 	/* can't be last */
 	rb_free_aux(rb);
 	ring_buffer_put(rb);
@@ -503,7 +539,7 @@ int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size)
 
 	rb->aux_head += size;
 
-	rb->user_page->aux_head = rb->aux_head;
+	WRITE_ONCE(rb->user_page->aux_head, rb->aux_head);
 	if (rb_need_aux_wakeup(rb)) {
 		perf_output_wakeup(handle);
 		handle->wakeup = rb->aux_wakeup + rb->aux_watermark;
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 97c3478ee6e7..7b7ac0f6cec9 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -35,6 +35,7 @@
 #include <linux/psci.h>
 #include <linux/types.h>
 #include <asm/ptrace.h>
+#include <asm/sve_context.h>
 
 #define __KVM_HAVE_GUEST_DEBUG
 #define __KVM_HAVE_IRQ_LINE
@@ -102,6 +103,9 @@ struct kvm_regs {
 #define KVM_ARM_VCPU_EL1_32BIT		1 /* CPU running a 32bit VM */
 #define KVM_ARM_VCPU_PSCI_0_2		2 /* CPU uses PSCI v0.2 */
 #define KVM_ARM_VCPU_PMU_V3		3 /* Support guest PMUv3 */
+#define KVM_ARM_VCPU_SVE		4 /* enable SVE for this CPU */
+#define KVM_ARM_VCPU_PTRAUTH_ADDRESS	5 /* VCPU uses address authentication */
+#define KVM_ARM_VCPU_PTRAUTH_GENERIC	6 /* VCPU uses generic authentication */
 
 struct kvm_vcpu_init {
 	__u32 target;
@@ -226,6 +230,45 @@ struct kvm_vcpu_events {
 					 KVM_REG_ARM_FW | ((r) & 0xffff))
 #define KVM_REG_ARM_PSCI_VERSION	KVM_REG_ARM_FW_REG(0)
 
+/* SVE registers */
+#define KVM_REG_ARM64_SVE		(0x15 << KVM_REG_ARM_COPROC_SHIFT)
+
+/* Z- and P-regs occupy blocks at the following offsets within this range: */
+#define KVM_REG_ARM64_SVE_ZREG_BASE	0
+#define KVM_REG_ARM64_SVE_PREG_BASE	0x400
+#define KVM_REG_ARM64_SVE_FFR_BASE	0x600
+
+#define KVM_ARM64_SVE_NUM_ZREGS		__SVE_NUM_ZREGS
+#define KVM_ARM64_SVE_NUM_PREGS		__SVE_NUM_PREGS
+
+#define KVM_ARM64_SVE_MAX_SLICES	32
+
+#define KVM_REG_ARM64_SVE_ZREG(n, i)					\
+	(KVM_REG_ARM64 | KVM_REG_ARM64_SVE | KVM_REG_ARM64_SVE_ZREG_BASE | \
+	 KVM_REG_SIZE_U2048 |						\
+	 (((n) & (KVM_ARM64_SVE_NUM_ZREGS - 1)) << 5) |			\
+	 ((i) & (KVM_ARM64_SVE_MAX_SLICES - 1)))
+
+#define KVM_REG_ARM64_SVE_PREG(n, i)					\
+	(KVM_REG_ARM64 | KVM_REG_ARM64_SVE | KVM_REG_ARM64_SVE_PREG_BASE | \
+	 KVM_REG_SIZE_U256 |						\
+	 (((n) & (KVM_ARM64_SVE_NUM_PREGS - 1)) << 5) |			\
+	 ((i) & (KVM_ARM64_SVE_MAX_SLICES - 1)))
+
+#define KVM_REG_ARM64_SVE_FFR(i)					\
+	(KVM_REG_ARM64 | KVM_REG_ARM64_SVE | KVM_REG_ARM64_SVE_FFR_BASE | \
+	 KVM_REG_SIZE_U256 |						\
+	 ((i) & (KVM_ARM64_SVE_MAX_SLICES - 1)))
+
+#define KVM_ARM64_SVE_VQ_MIN __SVE_VQ_MIN
+#define KVM_ARM64_SVE_VQ_MAX __SVE_VQ_MAX
+
+/* Vector lengths pseudo-register: */
+#define KVM_REG_ARM64_SVE_VLS		(KVM_REG_ARM64 | KVM_REG_ARM64_SVE | \
+					 KVM_REG_SIZE_U512 | 0xffff)
+#define KVM_ARM64_SVE_VLS_WORDS	\
+	((KVM_ARM64_SVE_VQ_MAX - KVM_ARM64_SVE_VQ_MIN) / 64 + 1)
+
 /* Device Control API: ARM VGIC */
 #define KVM_DEV_ARM_VGIC_GRP_ADDR	0
 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS	1
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 26ca425f4c2c..b0f72dea8b11 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -482,6 +482,8 @@ struct kvm_ppc_cpu_char {
 #define  KVM_REG_PPC_ICP_PPRI_SHIFT	16	/* pending irq priority */
 #define  KVM_REG_PPC_ICP_PPRI_MASK	0xff
 
+#define KVM_REG_PPC_VP_STATE	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x8d)
+
 /* Device control API: PPC-specific devices */
 #define KVM_DEV_MPIC_GRP_MISC		1
 #define   KVM_DEV_MPIC_BASE_ADDR	0	/* 64-bit */
@@ -677,4 +679,48 @@ struct kvm_ppc_cpu_char {
 #define  KVM_XICS_PRESENTED		(1ULL << 43)
 #define  KVM_XICS_QUEUED		(1ULL << 44)
 
+/* POWER9 XIVE Native Interrupt Controller */
+#define KVM_DEV_XIVE_GRP_CTRL		1
+#define   KVM_DEV_XIVE_RESET		1
+#define   KVM_DEV_XIVE_EQ_SYNC		2
+#define KVM_DEV_XIVE_GRP_SOURCE		2	/* 64-bit source identifier */
+#define KVM_DEV_XIVE_GRP_SOURCE_CONFIG	3	/* 64-bit source identifier */
+#define KVM_DEV_XIVE_GRP_EQ_CONFIG	4	/* 64-bit EQ identifier */
+#define KVM_DEV_XIVE_GRP_SOURCE_SYNC	5       /* 64-bit source identifier */
+
+/* Layout of 64-bit XIVE source attribute values */
+#define KVM_XIVE_LEVEL_SENSITIVE	(1ULL << 0)
+#define KVM_XIVE_LEVEL_ASSERTED		(1ULL << 1)
+
+/* Layout of 64-bit XIVE source configuration attribute values */
+#define KVM_XIVE_SOURCE_PRIORITY_SHIFT	0
+#define KVM_XIVE_SOURCE_PRIORITY_MASK	0x7
+#define KVM_XIVE_SOURCE_SERVER_SHIFT	3
+#define KVM_XIVE_SOURCE_SERVER_MASK	0xfffffff8ULL
+#define KVM_XIVE_SOURCE_MASKED_SHIFT	32
+#define KVM_XIVE_SOURCE_MASKED_MASK	0x100000000ULL
+#define KVM_XIVE_SOURCE_EISN_SHIFT	33
+#define KVM_XIVE_SOURCE_EISN_MASK	0xfffffffe00000000ULL
+
+/* Layout of 64-bit EQ identifier */
+#define KVM_XIVE_EQ_PRIORITY_SHIFT	0
+#define KVM_XIVE_EQ_PRIORITY_MASK	0x7
+#define KVM_XIVE_EQ_SERVER_SHIFT	3
+#define KVM_XIVE_EQ_SERVER_MASK		0xfffffff8ULL
+
+/* Layout of EQ configuration values (64 bytes) */
+struct kvm_ppc_xive_eq {
+	__u32 flags;
+	__u32 qshift;
+	__u64 qaddr;
+	__u32 qtoggle;
+	__u32 qindex;
+	__u8  pad[40];
+};
+
+#define KVM_XIVE_EQ_ALWAYS_NOTIFY	0x00000001
+
+#define KVM_XIVE_TIMA_PAGE_OFFSET	0
+#define KVM_XIVE_ESB_PAGE_OFFSET	4
+
 #endif /* __LINUX_KVM_POWERPC_H */
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 09652eabe769..47104e5b47fd 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -153,7 +153,9 @@ struct kvm_s390_vm_cpu_subfunc {
 	__u8 ppno[16];		/* with MSA5 */
 	__u8 kma[16];		/* with MSA8 */
 	__u8 kdsa[16];		/* with MSA9 */
-	__u8 reserved[1792];
+	__u8 sortl[32];		/* with STFLE.150 */
+	__u8 dfltcc[32];	/* with STFLE.151 */
+	__u8 reserved[1728];
 };
 
 /* kvm attributes for crypto */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 981ff9479648..75f27ee2c263 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -344,6 +344,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
 #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
@@ -382,5 +383,7 @@
 #define X86_BUG_SPECTRE_V2		X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
 #define X86_BUG_SPEC_STORE_BYPASS	X86_BUG(17) /* CPU is affected by speculative store bypass attack */
 #define X86_BUG_L1TF			X86_BUG(18) /* CPU is affected by L1 Terminal Fault */
+#define X86_BUG_MDS			X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */
+#define X86_BUG_MSBDS_ONLY		X86_BUG(20) /* CPU is only affected by the  MSDBS variant of BUG_MDS */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index dee7292e1df6..a87904daf103 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -832,9 +832,21 @@ __SYSCALL(__NR_io_uring_setup, sys_io_uring_setup)
 __SYSCALL(__NR_io_uring_enter, sys_io_uring_enter)
 #define __NR_io_uring_register 427
 __SYSCALL(__NR_io_uring_register, sys_io_uring_register)
+#define __NR_open_tree 428
+__SYSCALL(__NR_open_tree, sys_open_tree)
+#define __NR_move_mount 429
+__SYSCALL(__NR_move_mount, sys_move_mount)
+#define __NR_fsopen 430
+__SYSCALL(__NR_fsopen, sys_fsopen)
+#define __NR_fsconfig 431
+__SYSCALL(__NR_fsconfig, sys_fsconfig)
+#define __NR_fsmount 432
+__SYSCALL(__NR_fsmount, sys_fsmount)
+#define __NR_fspick 433
+__SYSCALL(__NR_fspick, sys_fspick)
 
 #undef __NR_syscalls
-#define __NR_syscalls 428
+#define __NR_syscalls 434
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 300f336633f2..661d73f9a919 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -649,6 +649,7 @@ struct drm_gem_open {
 #define DRM_CAP_PAGE_FLIP_TARGET	0x11
 #define DRM_CAP_CRTC_IN_VBLANK_EVENT	0x12
 #define DRM_CAP_SYNCOBJ		0x13
+#define DRM_CAP_SYNCOBJ_TIMELINE	0x14
 
 /** DRM_IOCTL_GET_CAP ioctl argument type */
 struct drm_get_cap {
@@ -735,8 +736,18 @@ struct drm_syncobj_handle {
 	__u32 pad;
 };
 
+struct drm_syncobj_transfer {
+	__u32 src_handle;
+	__u32 dst_handle;
+	__u64 src_point;
+	__u64 dst_point;
+	__u32 flags;
+	__u32 pad;
+};
+
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0)
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1)
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE (1 << 2) /* wait for time point to become available */
 struct drm_syncobj_wait {
 	__u64 handles;
 	/* absolute timeout */
@@ -747,12 +758,33 @@ struct drm_syncobj_wait {
 	__u32 pad;
 };
 
+struct drm_syncobj_timeline_wait {
+	__u64 handles;
+	/* wait on specific timeline point for every handles*/
+	__u64 points;
+	/* absolute timeout */
+	__s64 timeout_nsec;
+	__u32 count_handles;
+	__u32 flags;
+	__u32 first_signaled; /* only valid when not waiting all */
+	__u32 pad;
+};
+
+
 struct drm_syncobj_array {
 	__u64 handles;
 	__u32 count_handles;
 	__u32 pad;
 };
 
+struct drm_syncobj_timeline_array {
+	__u64 handles;
+	__u64 points;
+	__u32 count_handles;
+	__u32 pad;
+};
+
+
 /* Query current scanout sequence number */
 struct drm_crtc_get_sequence {
 	__u32 crtc_id;		/* requested crtc_id */
@@ -909,6 +941,11 @@ extern "C" {
 #define DRM_IOCTL_MODE_GET_LEASE	DRM_IOWR(0xC8, struct drm_mode_get_lease)
 #define DRM_IOCTL_MODE_REVOKE_LEASE	DRM_IOWR(0xC9, struct drm_mode_revoke_lease)
 
+#define DRM_IOCTL_SYNCOBJ_TIMELINE_WAIT	DRM_IOWR(0xCA, struct drm_syncobj_timeline_wait)
+#define DRM_IOCTL_SYNCOBJ_QUERY		DRM_IOWR(0xCB, struct drm_syncobj_timeline_array)
+#define DRM_IOCTL_SYNCOBJ_TRANSFER	DRM_IOWR(0xCC, struct drm_syncobj_transfer)
+#define DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL	DRM_IOWR(0xCD, struct drm_syncobj_timeline_array)
+
 /**
  * Device specific ioctls should only be in their respective headers
  * The device specific ioctl range is from 0x40 to 0x9f.
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 397810fa2d33..3a73f5316766 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -63,6 +63,28 @@ extern "C" {
 #define I915_RESET_UEVENT		"RESET"
 
 /*
+ * i915_user_extension: Base class for defining a chain of extensions
+ *
+ * Many interfaces need to grow over time. In most cases we can simply
+ * extend the struct and have userspace pass in more data. Another option,
+ * as demonstrated by Vulkan's approach to providing extensions for forward
+ * and backward compatibility, is to use a list of optional structs to
+ * provide those extra details.
+ *
+ * The key advantage to using an extension chain is that it allows us to
+ * redefine the interface more easily than an ever growing struct of
+ * increasing complexity, and for large parts of that interface to be
+ * entirely optional. The downside is more pointer chasing; chasing across
+ * the __user boundary with pointers encapsulated inside u64.
+ */
+struct i915_user_extension {
+	__u64 next_extension;
+	__u32 name;
+	__u32 flags; /* All undefined bits must be zero. */
+	__u32 rsvd[4]; /* Reserved for future use; must be zero. */
+};
+
+/*
  * MOCS indexes used for GPU surfaces, defining the cacheability of the
  * surface data and the coherency for this data wrt. CPU vs. GPU accesses.
  */
@@ -99,9 +121,23 @@ enum drm_i915_gem_engine_class {
 	I915_ENGINE_CLASS_VIDEO		= 2,
 	I915_ENGINE_CLASS_VIDEO_ENHANCE	= 3,
 
+	/* should be kept compact */
+
 	I915_ENGINE_CLASS_INVALID	= -1
 };
 
+/*
+ * There may be more than one engine fulfilling any role within the system.
+ * Each engine of a class is given a unique instance number and therefore
+ * any engine can be specified by its class:instance tuplet. APIs that allow
+ * access to any engine in the system will use struct i915_engine_class_instance
+ * for this identification.
+ */
+struct i915_engine_class_instance {
+	__u16 engine_class; /* see enum drm_i915_gem_engine_class */
+	__u16 engine_instance;
+};
+
 /**
  * DOC: perf_events exposed by i915 through /sys/bus/event_sources/drivers/i915
  *
@@ -319,6 +355,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_I915_PERF_ADD_CONFIG	0x37
 #define DRM_I915_PERF_REMOVE_CONFIG	0x38
 #define DRM_I915_QUERY			0x39
+/* Must be kept compact -- no holes */
 
 #define DRM_IOCTL_I915_INIT		DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
 #define DRM_IOCTL_I915_FLUSH		DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH)
@@ -367,6 +404,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_IOCTL_I915_GET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey)
 #define DRM_IOCTL_I915_GEM_WAIT		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_WAIT, struct drm_i915_gem_wait)
 #define DRM_IOCTL_I915_GEM_CONTEXT_CREATE	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_CREATE, struct drm_i915_gem_context_create)
+#define DRM_IOCTL_I915_GEM_CONTEXT_CREATE_EXT	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_CREATE, struct drm_i915_gem_context_create_ext)
 #define DRM_IOCTL_I915_GEM_CONTEXT_DESTROY	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_DESTROY, struct drm_i915_gem_context_destroy)
 #define DRM_IOCTL_I915_REG_READ			DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_REG_READ, struct drm_i915_reg_read)
 #define DRM_IOCTL_I915_GET_RESET_STATS		DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GET_RESET_STATS, struct drm_i915_reset_stats)
@@ -476,6 +514,7 @@ typedef struct drm_i915_irq_wait {
 #define   I915_SCHEDULER_CAP_ENABLED	(1ul << 0)
 #define   I915_SCHEDULER_CAP_PRIORITY	(1ul << 1)
 #define   I915_SCHEDULER_CAP_PREEMPTION	(1ul << 2)
+#define   I915_SCHEDULER_CAP_SEMAPHORES	(1ul << 3)
 
 #define I915_PARAM_HUC_STATUS		 42
 
@@ -559,6 +598,8 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_MMAP_GTT_COHERENT	52
 
+/* Must be kept compact -- no holes and well documented */
+
 typedef struct drm_i915_getparam {
 	__s32 param;
 	/*
@@ -574,6 +615,7 @@ typedef struct drm_i915_getparam {
 #define I915_SETPARAM_TEX_LRU_LOG_GRANULARITY             2
 #define I915_SETPARAM_ALLOW_BATCHBUFFER                   3
 #define I915_SETPARAM_NUM_USED_FENCES                     4
+/* Must be kept compact -- no holes */
 
 typedef struct drm_i915_setparam {
 	int param;
@@ -972,7 +1014,7 @@ struct drm_i915_gem_execbuffer2 {
 	 * struct drm_i915_gem_exec_fence *fences.
 	 */
 	__u64 cliprects_ptr;
-#define I915_EXEC_RING_MASK              (7<<0)
+#define I915_EXEC_RING_MASK              (0x3f)
 #define I915_EXEC_DEFAULT                (0<<0)
 #define I915_EXEC_RENDER                 (1<<0)
 #define I915_EXEC_BSD                    (2<<0)
@@ -1120,32 +1162,34 @@ struct drm_i915_gem_busy {
 	 * as busy may become idle before the ioctl is completed.
 	 *
 	 * Furthermore, if the object is busy, which engine is busy is only
-	 * provided as a guide. There are race conditions which prevent the
-	 * report of which engines are busy from being always accurate.
-	 * However, the converse is not true. If the object is idle, the
-	 * result of the ioctl, that all engines are idle, is accurate.
+	 * provided as a guide and only indirectly by reporting its class
+	 * (there may be more than one engine in each class). There are race
+	 * conditions which prevent the report of which engines are busy from
+	 * being always accurate.  However, the converse is not true. If the
+	 * object is idle, the result of the ioctl, that all engines are idle,
+	 * is accurate.
 	 *
 	 * The returned dword is split into two fields to indicate both
-	 * the engines on which the object is being read, and the
-	 * engine on which it is currently being written (if any).
+	 * the engine classess on which the object is being read, and the
+	 * engine class on which it is currently being written (if any).
 	 *
 	 * The low word (bits 0:15) indicate if the object is being written
 	 * to by any engine (there can only be one, as the GEM implicit
 	 * synchronisation rules force writes to be serialised). Only the
-	 * engine for the last write is reported.
+	 * engine class (offset by 1, I915_ENGINE_CLASS_RENDER is reported as
+	 * 1 not 0 etc) for the last write is reported.
 	 *
-	 * The high word (bits 16:31) are a bitmask of which engines are
-	 * currently reading from the object. Multiple engines may be
+	 * The high word (bits 16:31) are a bitmask of which engines classes
+	 * are currently reading from the object. Multiple engines may be
 	 * reading from the object simultaneously.
 	 *
-	 * The value of each engine is the same as specified in the
-	 * EXECBUFFER2 ioctl, i.e. I915_EXEC_RENDER, I915_EXEC_BSD etc.
-	 * Note I915_EXEC_DEFAULT is a symbolic value and is mapped to
-	 * the I915_EXEC_RENDER engine for execution, and so it is never
+	 * The value of each engine class is the same as specified in the
+	 * I915_CONTEXT_SET_ENGINES parameter and via perf, i.e.
+	 * I915_ENGINE_CLASS_RENDER, I915_ENGINE_CLASS_COPY, etc.
 	 * reported as active itself. Some hardware may have parallel
 	 * execution engines, e.g. multiple media engines, which are
-	 * mapped to the same identifier in the EXECBUFFER2 ioctl and
-	 * so are not separately reported for busyness.
+	 * mapped to the same class identifier and so are not separately
+	 * reported for busyness.
 	 *
 	 * Caveat emptor:
 	 * Only the boolean result of this query is reliable; that is whether
@@ -1412,65 +1456,17 @@ struct drm_i915_gem_wait {
 };
 
 struct drm_i915_gem_context_create {
-	/*  output: id of new context*/
-	__u32 ctx_id;
-	__u32 pad;
-};
-
-struct drm_i915_gem_context_destroy {
-	__u32 ctx_id;
+	__u32 ctx_id; /* output: id of new context*/
 	__u32 pad;
 };
 
-struct drm_i915_reg_read {
-	/*
-	 * Register offset.
-	 * For 64bit wide registers where the upper 32bits don't immediately
-	 * follow the lower 32bits, the offset of the lower 32bits must
-	 * be specified
-	 */
-	__u64 offset;
-#define I915_REG_READ_8B_WA (1ul << 0)
-
-	__u64 val; /* Return value */
-};
-/* Known registers:
- *
- * Render engine timestamp - 0x2358 + 64bit - gen7+
- * - Note this register returns an invalid value if using the default
- *   single instruction 8byte read, in order to workaround that pass
- *   flag I915_REG_READ_8B_WA in offset field.
- *
- */
-
-struct drm_i915_reset_stats {
-	__u32 ctx_id;
-	__u32 flags;
-
-	/* All resets since boot/module reload, for all contexts */
-	__u32 reset_count;
-
-	/* Number of batches lost when active in GPU, for this context */
-	__u32 batch_active;
-
-	/* Number of batches lost pending for execution, for this context */
-	__u32 batch_pending;
-