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

Pull perf fixes from Thomas Gleixner:

 - Prevent a division by zero in the perf aux buffer handling

 - Sync kernel headers with perf tool headers

 - Fix a build failure in the syscalltbl code

 - Make the debug messages of perf report --call-graph work correctly

 - Make sure that all required perf files are in the MANIFEST for
   container builds

 - Fix the atrr.exclude kernel handling so it respects the
   perf_event_paranoid and the user permissions

 - Make perf test on s390x work correctly

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/aux: Only update ->aux_wakeup in non-overwrite mode
  perf test: Fix vmlinux failure on s390x part 2
  perf test: Fix vmlinux failure on s390x
  perf tools: Fix syscalltbl build failure
  perf report: Fix debug messages with --call-graph option
  perf evsel: Fix attr.exclude_kernel setting for default cycles:p
  tools include: Sync kernel ABI headers with tooling headers
  perf tools: Get all of tools/{arch,include}/ in the MANIFEST

19 files changed, 210 insertions, 174 deletions

diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index af71a84e12ee..f684d8e5fa2b 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -412,6 +412,19 @@ err:
         return NULL;
 }
 
+static bool __always_inline rb_need_aux_wakeup(struct ring_buffer *rb)
+{
+        if (rb->aux_overwrite)
+                return false;
+
+        if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) {
+                rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark);
+                return true;
+        }
+
+        return false;
+}
+
 /*
  * Commit the data written by hardware into the ring buffer by adjusting
  * aux_head and posting a PERF_RECORD_AUX into the perf buffer. It is the
@@ -451,10 +464,8 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
         }
 
         rb->user_page->aux_head = rb->aux_head;
-        if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) {
+        if (rb_need_aux_wakeup(rb))
                 wakeup = true;
-                rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark);
-        }
 
         if (wakeup) {
                 if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED)
@@ -484,9 +495,8 @@ 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;
-        if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) {
+        if (rb_need_aux_wakeup(rb)) {
                 perf_output_wakeup(handle);
-                rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark);
                 handle->wakeup = rb->aux_wakeup + rb->aux_watermark;
         }
 
diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h
index 69d09c39bbcd..cd7359e23d86 100644
--- a/tools/arch/s390/include/uapi/asm/kvm.h
+++ b/tools/arch/s390/include/uapi/asm/kvm.h
@@ -88,6 +88,12 @@ struct kvm_s390_io_adapter_req {
 /* kvm attributes for KVM_S390_VM_TOD */
 #define KVM_S390_VM_TOD_LOW             0
 #define KVM_S390_VM_TOD_HIGH            1
+#define KVM_S390_VM_TOD_EXT             2
+
+struct kvm_s390_vm_tod_clock {
+        __u8  epoch_idx;
+        __u64 tod;
+};
 
 /* kvm attributes for KVM_S390_VM_CPU_MODEL */
 /* processor related attributes are r/w */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 8ea315a11fe0..2519c6c801c9 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -196,6 +196,7 @@
 
 #define X86_FEATURE_HW_PSTATE   ( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
+#define X86_FEATURE_SME         ( 7*32+10) /* AMD Secure Memory Encryption */
 
 #define X86_FEATURE_INTEL_PPIN  ( 7*32+14) /* Intel Processor Inventory Number */
 #define X86_FEATURE_INTEL_PT    ( 7*32+15) /* Intel Processor Trace */
@@ -287,6 +288,7 @@
 #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
 #define X86_FEATURE_AVIC        (15*32+13) /* Virtual Interrupt Controller */
 #define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */
+#define X86_FEATURE_VGIF        (15*32+16) /* Virtual GIF */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
 #define X86_FEATURE_AVX512VBMI  (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 5dff775af7cd..c10c9128f54e 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -21,11 +21,13 @@
 # define DISABLE_K6_MTRR        (1<<(X86_FEATURE_K6_MTRR & 31))
 # define DISABLE_CYRIX_ARR      (1<<(X86_FEATURE_CYRIX_ARR & 31))
 # define DISABLE_CENTAUR_MCR    (1<<(X86_FEATURE_CENTAUR_MCR & 31))
+# define DISABLE_PCID           0
 #else
 # define DISABLE_VME            0
 # define DISABLE_K6_MTRR        0
 # define DISABLE_CYRIX_ARR      0
 # define DISABLE_CENTAUR_MCR    0
+# define DISABLE_PCID           (1<<(X86_FEATURE_PCID & 31))
 #endif /* CONFIG_X86_64 */
 
 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
@@ -49,7 +51,7 @@
 #define DISABLED_MASK1  0
 #define DISABLED_MASK2  0
 #define DISABLED_MASK3  (DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR)
-#define DISABLED_MASK4  0
+#define DISABLED_MASK4  (DISABLE_PCID)
 #define DISABLED_MASK5  0
 #define DISABLED_MASK6  0
 #define DISABLED_MASK7  0
diff --git a/tools/include/asm-generic/hugetlb_encode.h b/tools/include/asm-generic/hugetlb_encode.h
new file mode 100644
index 000000000000..e4732d3c2998
--- /dev/null
+++ b/tools/include/asm-generic/hugetlb_encode.h
@@ -0,0 +1,34 @@
+#ifndef _ASM_GENERIC_HUGETLB_ENCODE_H_
+#define _ASM_GENERIC_HUGETLB_ENCODE_H_
+
+/*
+ * Several system calls take a flag to request "hugetlb" huge pages.
+ * Without further specification, these system calls will use the
+ * system's default huge page size.  If a system supports multiple
+ * huge page sizes, the desired huge page size can be specified in
+ * bits [26:31] of the flag arguments.  The value in these 6 bits
+ * will encode the log2 of the huge page size.
+ *
+ * The following definitions are associated with this huge page size
+ * encoding in flag arguments.  System call specific header files
+ * that use this encoding should include this file.  They can then
+ * provide definitions based on these with their own specific prefix.
+ * for example:
+ * #define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT
+ */
+
+#define HUGETLB_FLAG_ENCODE_SHIFT       26
+#define HUGETLB_FLAG_ENCODE_MASK        0x3f
+
+#define HUGETLB_FLAG_ENCODE_64KB        (16 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_512KB       (19 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_1MB         (20 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_2MB         (21 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_8MB         (23 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_16MB        (24 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_256MB       (28 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_1GB         (30 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_2GB         (31 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_16GB        (34 << HUGETLB_FLAG_ENCODE_SHIFT)
+
+#endif /* _ASM_GENERIC_HUGETLB_ENCODE_H_ */
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index 8c27db0c5c08..203268f9231e 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -58,20 +58,12 @@
                                            overrides the coredump filter bits */
 #define MADV_DODUMP     17              /* Clear the MADV_DONTDUMP flag */
 
+#define MADV_WIPEONFORK 18              /* Zero memory on fork, child only */
+#define MADV_KEEPONFORK 19              /* Undo MADV_WIPEONFORK */
+
 /* compatibility flags */
 #define MAP_FILE        0
 
-/*
- * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
- * This gives us 6 bits, which is enough until someone invents 128 bit address
- * spaces.
- *
- * Assume these are all power of twos.
- * When 0 use the default page size.
- */
-#define MAP_HUGE_SHIFT  26
-#define MAP_HUGE_MASK   0x3f
-
 #define PKEY_DISABLE_ACCESS     0x1
 #define PKEY_DISABLE_WRITE      0x2
 #define PKEY_ACCESS_MASK        (PKEY_DISABLE_ACCESS |\
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 101593ab10ac..97677cd6964d 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -700,6 +700,7 @@ struct drm_prime_handle {
 
 struct drm_syncobj_create {
         __u32 handle;
+#define DRM_SYNCOBJ_CREATE_SIGNALED (1 << 0)
         __u32 flags;
 };
 
@@ -718,6 +719,24 @@ struct drm_syncobj_handle {
         __u32 pad;
 };
 
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0)
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1)
+struct drm_syncobj_wait {
+        __u64 handles;
+        /* 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;
+};
+
 #if defined(__cplusplus)
 }
 #endif
@@ -840,6 +859,9 @@ extern "C" {
 #define DRM_IOCTL_SYNCOBJ_DESTROY       DRM_IOWR(0xC0, struct drm_syncobj_destroy)
 #define DRM_IOCTL_SYNCOBJ_HANDLE_TO_FD  DRM_IOWR(0xC1, struct drm_syncobj_handle)
 #define DRM_IOCTL_SYNCOBJ_FD_TO_HANDLE  DRM_IOWR(0xC2, struct drm_syncobj_handle)
+#define DRM_IOCTL_SYNCOBJ_WAIT          DRM_IOWR(0xC3, struct drm_syncobj_wait)
+#define DRM_IOCTL_SYNCOBJ_RESET         DRM_IOWR(0xC4, struct drm_syncobj_array)
+#define DRM_IOCTL_SYNCOBJ_SIGNAL        DRM_IOWR(0xC5, struct drm_syncobj_array)
 
 /**
  * Device specific ioctls should only be in their respective headers
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 7ccbd6a2bbe0..6598fb76d2c2 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -260,6 +260,8 @@ typedef struct _drm_i915_sarea {
 #define DRM_I915_GEM_CONTEXT_GETPARAM   0x34
 #define DRM_I915_GEM_CONTEXT_SETPARAM   0x35
 #define DRM_I915_PERF_OPEN              0x36
+#define DRM_I915_PERF_ADD_CONFIG        0x37
+#define DRM_I915_PERF_REMOVE_CONFIG     0x38
 
 #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)
@@ -315,6 +317,8 @@ typedef struct _drm_i915_sarea {
 #define DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM     DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_GETPARAM, struct drm_i915_gem_context_param)
 #define DRM_IOCTL_I915_GEM_CONTEXT_SETPARAM     DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_SETPARAM, struct drm_i915_gem_context_param)
 #define DRM_IOCTL_I915_PERF_OPEN        DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param)
+#define DRM_IOCTL_I915_PERF_ADD_CONFIG  DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config)
+#define DRM_IOCTL_I915_PERF_REMOVE_CONFIG       DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64)
 
 /* Allow drivers to submit batchbuffers directly to hardware, relying
  * on the security mechanisms provided by hardware.
@@ -431,6 +435,11 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_HAS_EXEC_BATCH_FIRST  48
 
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
+ * drm_i915_gem_exec_fence structures.  See I915_EXEC_FENCE_ARRAY.
+ */
+#define I915_PARAM_HAS_EXEC_FENCE_ARRAY  49
+
 typedef struct drm_i915_getparam {
         __s32 param;
         /*
@@ -812,6 +821,17 @@ struct drm_i915_gem_exec_object2 {
         __u64 rsvd2;
 };
 
+struct drm_i915_gem_exec_fence {
+        /**
+         * User's handle for a drm_syncobj to wait on or signal.
+         */
+        __u32 handle;
+
+#define I915_EXEC_FENCE_WAIT            (1<<0)
+#define I915_EXEC_FENCE_SIGNAL          (1<<1)
+        __u32 flags;
+};
+
 struct drm_i915_gem_execbuffer2 {
         /**
          * List of gem_exec_object2 structs
@@ -826,7 +846,11 @@ struct drm_i915_gem_execbuffer2 {
         __u32 DR1;
         __u32 DR4;
         __u32 num_cliprects;
-        /** This is a struct drm_clip_rect *cliprects */
+        /**
+         * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY
+         * is not set.  If I915_EXEC_FENCE_ARRAY is set, then this is a
+         * struct drm_i915_gem_exec_fence *fences.
+         */
         __u64 cliprects_ptr;
 #define I915_EXEC_RING_MASK              (7<<0)
 #define I915_EXEC_DEFAULT                (0<<0)
@@ -927,7 +951,14 @@ struct drm_i915_gem_execbuffer2 {
  * element).
  */
 #define I915_EXEC_BATCH_FIRST           (1<<18)
-#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_BATCH_FIRST<<1))
+
+/* Setting I915_FENCE_ARRAY implies that num_cliprects and cliprects_ptr
+ * define an array of i915_gem_exec_fence structures which specify a set of
+ * dma fences to wait upon or signal.
+ */
+#define I915_EXEC_FENCE_ARRAY   (1<<19)
+
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_ARRAY<<1))
 
 #define I915_EXEC_CONTEXT_ID_MASK       (0xffffffff)
 #define i915_execbuffer2_set_context_id(eb2, context) \
@@ -1467,6 +1498,22 @@ enum drm_i915_perf_record_type {
         DRM_I915_PERF_RECORD_MAX /* non-ABI */
 };
 
+/**
+ * Structure to upload perf dynamic configuration into the kernel.
+ */
+struct drm_i915_perf_oa_config {
+        /** String formatted like "%08x-%04x-%04x-%04x-%012x" */
+        char uuid[36];
+
+        __u32 n_mux_regs;
+        __u32 n_boolean_regs;
+        __u32 n_flex_regs;
+
+        __u64 __user mux_regs_ptr;
+        __u64 __user boolean_regs_ptr;
+        __u64 __user flex_regs_ptr;
+};
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 461811e57140..43ab5c402f98 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -143,12 +143,6 @@ enum bpf_attach_type {
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
-enum bpf_sockmap_flags {
-        BPF_SOCKMAP_UNSPEC,
-        BPF_SOCKMAP_STRPARSER,
-        __MAX_BPF_SOCKMAP_FLAG
-};
-
 /* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
  * to the given target_fd cgroup the descendent cgroup will be able to
  * override effective bpf program that was inherited from this cgroup
@@ -368,9 +362,20 @@ union bpf_attr {
  * int bpf_redirect(ifindex, flags)
  *     redirect to another netdev
  *     @ifindex: ifindex of the net device
- *     @flags: bit 0 - if set, redirect to ingress instead of egress
- *             other bits - reserved
- *     Return: TC_ACT_REDIRECT
+ *     @flags:
+ *        cls_bpf:
+ *          bit 0 - if set, redirect to ingress instead of egress
+ *          other bits - reserved
+ *        xdp_bpf:
+ *          all bits - reserved
+ *     Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error
+ *             xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error
+ * int bpf_redirect_map(map, key, flags)
+ *     redirect to endpoint in map
+ *     @map: pointer to dev map
+ *     @key: index in map to lookup
+ *     @flags: --
+ *     Return: XDP_REDIRECT on success or XDP_ABORT on error
  *
  * u32 bpf_get_route_realm(skb)
  *     retrieve a dst's tclassid
@@ -632,7 +637,7 @@ union bpf_attr {
         FN(skb_adjust_room),            \
         FN(redirect_map),               \
         FN(sk_redirect_map),            \
-        FN(sock_map_update),
+        FN(sock_map_update),            \
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -753,20 +758,23 @@ struct bpf_sock {
         __u32 family;
         __u32 type;
         __u32 protocol;
+        __u32 mark;
+        __u32 priority;
 };
 
 #define XDP_PACKET_HEADROOM 256
 
 /* User return codes for XDP prog type.
  * A valid XDP program must return one of these defined values. All other
- * return codes are reserved for future use. Unknown return codes will result
- * in packet drop.
+ * return codes are reserved for future use. Unknown return codes will
+ * result in packet drops and a warning via bpf_warn_invalid_xdp_action().
  */
 enum xdp_action {
         XDP_ABORTED = 0,
         XDP_DROP,
         XDP_PASS,
         XDP_TX,
+        XDP_REDIRECT,
 };
 
 /* user accessible metadata for XDP packet hook
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 6cd63c18708a..838887587411 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -711,7 +711,8 @@ struct kvm_ppc_one_seg_page_size {
 struct kvm_ppc_smmu_info {
         __u64 flags;
         __u32 slb_size;
-        __u32 pad;
+        __u16 data_keys;        /* # storage keys supported for data */
+        __u16 instr_keys;       /* # storage keys supported for instructions */
         struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
 };
 
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
index 81d8edf11789..a937480d7cd3 100644
--- a/tools/include/uapi/linux/mman.h
+++ b/tools/include/uapi/linux/mman.h
@@ -1,7 +1,8 @@
 #ifndef _UAPI_LINUX_MMAN_H
 #define _UAPI_LINUX_MMAN_H
 
-#include <uapi/asm/mman.h>
+#include <asm/mman.h>
+#include <asm-generic/hugetlb_encode.h>
 
 #define MREMAP_MAYMOVE  1
 #define MREMAP_FIXED    2
@@ -10,4 +11,25 @@
 #define OVERCOMMIT_ALWAYS               1
 #define OVERCOMMIT_NEVER                2
 
+/*
+ * Huge page size encoding when MAP_HUGETLB is specified, and a huge page
+ * size other than the default is desired.  See hugetlb_encode.h.
+ * All known huge page size encodings are provided here.  It is the
+ * responsibility of the application to know which sizes are supported on
+ * the running system.  See mmap(2) man page for details.
+ */
+#define MAP_HUGE_SHIFT  HUGETLB_FLAG_ENCODE_SHIFT
+#define MAP_HUGE_MASK   HUGETLB_FLAG_ENCODE_MASK
+
+#define MAP_HUGE_64KB   HUGETLB_FLAG_ENCODE_64KB
+#define MAP_HUGE_512KB  HUGETLB_FLAG_ENCODE_512KB
+#define MAP_HUGE_1MB    HUGETLB_FLAG_ENCODE_1MB
+#define MAP_HUGE_2MB    HUGETLB_FLAG_ENCODE_2MB
+#define MAP_HUGE_8MB    HUGETLB_FLAG_ENCODE_8MB
+#define MAP_HUGE_16MB   HUGETLB_FLAG_ENCODE_16MB
+#define MAP_HUGE_256MB  HUGETLB_FLAG_ENCODE_256MB
+#define MAP_HUGE_1GB    HUGETLB_FLAG_ENCODE_1GB
+#define MAP_HUGE_2GB    HUGETLB_FLAG_ENCODE_2GB
+#define MAP_HUGE_16GB   HUGETLB_FLAG_ENCODE_16GB
+
 #endif /* _UAPI_LINUX_MMAN_H */
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 62072822dc85..627b7cada144 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -1,34 +1,8 @@
 tools/perf
-tools/arch/alpha/include/asm/barrier.h
-tools/arch/arm/include/asm/barrier.h
-tools/arch/arm64/include/asm/barrier.h
-tools/arch/ia64/include/asm/barrier.h
-tools/arch/mips/include/asm/barrier.h
-tools/arch/powerpc/include/asm/barrier.h
-tools/arch/s390/include/asm/barrier.h
-tools/arch/sh/include/asm/barrier.h
-tools/arch/sparc/include/asm/barrier.h
-tools/arch/sparc/include/asm/barrier_32.h
-tools/arch/sparc/include/asm/barrier_64.h
-tools/arch/tile/include/asm/barrier.h
-tools/arch/x86/include/asm/barrier.h
-tools/arch/x86/include/asm/cmpxchg.h
-tools/arch/x86/include/asm/cpufeatures.h
-tools/arch/x86/include/asm/disabled-features.h
-tools/arch/x86/include/asm/required-features.h
-tools/arch/x86/include/uapi/asm/svm.h
-tools/arch/x86/include/uapi/asm/vmx.h
-tools/arch/x86/include/uapi/asm/kvm.h
-tools/arch/x86/include/uapi/asm/kvm_perf.h
-tools/arch/x86/lib/memcpy_64.S
-tools/arch/x86/lib/memset_64.S
-tools/arch/s390/include/uapi/asm/kvm_perf.h
-tools/arch/s390/include/uapi/asm/sie.h
-tools/arch/xtensa/include/asm/barrier.h
+tools/arch
 tools/scripts
 tools/build
-tools/arch/x86/include/asm/atomic.h
-tools/arch/x86/include/asm/rmwcc.h
+tools/include
 tools/lib/traceevent
 tools/lib/api
 tools/lib/bpf
@@ -42,60 +16,3 @@ tools/lib/find_bit.c
 tools/lib/bitmap.c
 tools/lib/str_error_r.c
 tools/lib/vsprintf.c
-tools/include/asm/alternative-asm.h
-tools/include/asm/atomic.h
-tools/include/asm/barrier.h
-tools/include/asm/bug.h
-tools/include/asm-generic/atomic-gcc.h
-tools/include/asm-generic/barrier.h
-tools/include/asm-generic/bitops/arch_hweight.h
-tools/include/asm-generic/bitops/atomic.h
-tools/include/asm-generic/bitops/const_hweight.h
-tools/include/asm-generic/bitops/__ffs.h
-tools/include/asm-generic/bitops/__ffz.h
-tools/include/asm-generic/bitops/__fls.h
-tools/include/asm-generic/bitops/find.h
-tools/include/asm-generic/bitops/fls64.h
-tools/include/asm-generic/bitops/fls.h
-tools/include/asm-generic/bitops/hweight.h
-tools/include/asm-generic/bitops.h
-tools/include/linux/atomic.h
-tools/include/linux/bitops.h
-tools/include/linux/compiler.h
-tools/include/linux/compiler-gcc.h
-tools/include/linux/coresight-pmu.h
-tools/include/linux/bug.h
-tools/include/linux/filter.h
-tools/include/linux/hash.h
-tools/include/linux/kernel.h
-tools/include/linux/list.h
-tools/include/linux/log2.h
-tools/include/uapi/asm-generic/fcntl.h
-tools/include/uapi/asm-generic/ioctls.h
-tools/include/uapi/asm-generic/mman-common.h
-tools/include/uapi/asm-generic/mman.h
-tools/include/uapi/drm/drm.h
-tools/include/uapi/drm/i915_drm.h
-tools/include/uapi/linux/bpf.h
-tools/include/uapi/linux/bpf_common.h
-tools/include/uapi/linux/fcntl.h
-tools/include/uapi/linux/hw_breakpoint.h
-tools/include/uapi/linux/kvm.h
-tools/include/uapi/linux/mman.h
-tools/include/uapi/linux/perf_event.h
-tools/include/uapi/linux/sched.h
-tools/include/uapi/linux/stat.h
-tools/include/uapi/linux/vhost.h
-tools/include/uapi/sound/asound.h
-tools/include/linux/poison.h
-tools/include/linux/rbtree.h
-tools/include/linux/rbtree_augmented.h
-tools/include/linux/refcount.h
-tools/include/linux/string.h
-tools/include/linux/stringify.h
-tools/include/linux/types.h
-tools/include/linux/err.h
-tools/include/linux/bitmap.h
-tools/include/linux/time64.h
-tools/arch/*/include/uapi/asm/mman.h
-tools/arch/*/include/uapi/asm/perf_regs.h
diff --git a/tools/perf/arch/s390/util/Build b/tools/perf/arch/s390/util/Build
index bd518b623d7a..5bd7b9260cc0 100644
--- a/tools/perf/arch/s390/util/Build
+++ b/tools/perf/arch/s390/util/Build
@@ -1,5 +1,4 @@
 libperf-y += header.o
-libperf-y += sym-handling.o
 libperf-y += kvm-stat.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
diff --git a/tools/perf/arch/s390/util/sym-handling.c b/tools/perf/arch/s390/util/sym-handling.c
deleted file mode 100644
index e103f6e46afe..000000000000
--- a/tools/perf/arch/s390/util/sym-handling.c
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * Architecture specific ELF symbol handling and relocation mapping.
- *
- * Copyright 2017 IBM Corp.
- * Author(s): Thomas Richter <tmricht@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- */
-
-#include "symbol.h"
-
-#ifdef HAVE_LIBELF_SUPPORT
-bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
-{
-        if (ehdr.e_type == ET_EXEC)
-                return false;
-        return ehdr.e_type == ET_REL || ehdr.e_type == ET_DYN;
-}
-
-void arch__adjust_sym_map_offset(GElf_Sym *sym,
-                                 GElf_Shdr *shdr __maybe_unused,
-                                 struct map *map)
-{
-        if (map->type == MAP__FUNCTION)
-                sym->st_value += map->start;
-}
-#endif
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 510b513e0f01..be09d77cade0 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -65,8 +65,6 @@ static int parse_callchain_mode(const char *value)
                 callchain_param.mode = CHAIN_FOLDED;
                 return 0;
         }
-
-        pr_err("Invalid callchain mode: %s\n", value);
         return -1;
 }
 
@@ -82,8 +80,6 @@ static int parse_callchain_order(const char *value)
                 callchain_param.order_set = true;
                 return 0;
         }
-
-        pr_err("Invalid callchain order: %s\n", value);
         return -1;
 }
 
@@ -105,8 +101,6 @@ static int parse_callchain_sort_key(const char *value)
                 callchain_param.branch_callstack = 1;
                 return 0;
         }
-
-        pr_err("Invalid callchain sort key: %s\n", value);
         return -1;
 }
 
@@ -124,8 +118,6 @@ static int parse_callchain_value(const char *value)
                 callchain_param.value = CCVAL_COUNT;
                 return 0;
         }
-
-        pr_err("Invalid callchain config key: %s\n", value);
         return -1;
 }
 
@@ -319,12 +311,27 @@ int perf_callchain_config(const char *var, const char *value)
 
                 return ret;
         }
-        if (!strcmp(var, "print-type"))
-                return parse_callchain_mode(value);
-        if (!strcmp(var, "order"))
-                return parse_callchain_order(value);
-        if (!strcmp(var, "sort-key"))
-                return parse_callchain_sort_key(value);
+        if (!strcmp(var, "print-type")){
+                int ret;
+                ret = parse_callchain_mode(value);
+                if (ret == -1)
+                        pr_err("Invalid callchain mode: %s\n", value);
+                return ret;
+        }
+        if (!strcmp(var, "order")){
+                int ret;
+                ret = parse_callchain_order(value);
+                if (ret == -1)
+                        pr_err("Invalid callchain order: %s\n", value);
+                return ret;
+        }
+        if (!strcmp(var, "sort-key")){
+                int ret;
+                ret = parse_callchain_sort_key(value);
+                if (ret == -1)
+                        pr_err("Invalid callchain sort key: %s\n", value);
+                return ret;
+        }
         if (!strcmp(var, "threshold")) {
                 callchain_param.min_percent = strtod(value, &endptr);
                 if (value == endptr) {
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 4bb89373eb52..0dccdb89572c 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -271,12 +271,17 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
         return evsel;
 }
 
+static bool perf_event_can_profile_kernel(void)
+{
+        return geteuid() == 0 || perf_event_paranoid() == -1;
+}
+
 struct perf_evsel *perf_evsel__new_cycles(bool precise)
 {
         struct perf_event_attr attr = {
                 .type   = PERF_TYPE_HARDWARE,
                 .config = PERF_COUNT_HW_CPU_CYCLES,
-                .exclude_kernel = geteuid() != 0,
+                .exclude_kernel = !perf_event_can_profile_kernel(),
         };
         struct perf_evsel *evsel;
 
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 5c39f420111e..9cf781f0d8a2 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -810,12 +810,6 @@ static u64 ref_reloc(struct kmap *kmap)
 void __weak arch__sym_update(struct symbol *s __maybe_unused,
                 GElf_Sym *sym __maybe_unused) { }
 
-void __weak arch__adjust_sym_map_offset(GElf_Sym *sym, GElf_Shdr *shdr,
-                                       struct map *map __maybe_unused)
-{
-        sym->st_value -= shdr->sh_addr - shdr->sh_offset;
-}
-
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
                   struct symsrc *runtime_ss, int kmodule)
 {
@@ -996,7 +990,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 
                         /* Adjust symbol to map to file offset */
                         if (adjust_kernel_syms)
-                                arch__adjust_sym_map_offset(&sym, &shdr, map);
+                                sym.st_value -= shdr.sh_addr - shdr.sh_offset;
 
                         if (strcmp(section_name,
                                    (curr_dso->short_name +
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 2bd6a1f01a1c..aad99e7e179b 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -344,9 +344,6 @@ int setup_intlist(struct intlist **list, const char *list_str,
 #ifdef HAVE_LIBELF_SUPPORT
 bool elf__needs_adjust_symbols(GElf_Ehdr ehdr);
 void arch__sym_update(struct symbol *s, GElf_Sym *sym);
-void arch__adjust_sym_map_offset(GElf_Sym *sym,
-                                 GElf_Shdr *shdr __maybe_unused,
-                                 struct map *map __maybe_unused);
 #endif
 
 #define SYMBOL_A 0
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index 19e5db90394c..6eea7cff3d4e 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -15,9 +15,9 @@
 
 #include "syscalltbl.h"
 #include <stdlib.h>
+#include <linux/compiler.h>
 
 #ifdef HAVE_SYSCALL_TABLE
-#include <linux/compiler.h>
 #include <string.h>
 #include "string2.h"
 #include "util.h"