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

Pull more perf updates from Thomas Gleixner:
 "A rather large set of perf updates:

  Kernel:

   - Fix various initialization issues

   - Prevent creating [ku]probes for not CAP_SYS_ADMIN users

  Tooling:

   - Show only failing syscalls with 'perf trace --failure' (Arnaldo
     Carvalho de Melo)

            e.g: See what 'openat' syscalls are failing:

        # perf trace --failure -e openat
         762.323 ( 0.007 ms): VideoCapture/4566 openat(dfd: CWD, filename: /dev/video2) = -1 ENOENT No such file or directory
         <SNIP N /dev/videoN open attempts... sigh, where is that improvised camera lid?!? >
         790.228 ( 0.008 ms): VideoCapture/4566 openat(dfd: CWD, filename: /dev/video63) = -1 ENOENT No such file or directory
        ^C#

   - Show information about the event (freq, nr_samples, total
     period/nr_events) in the annotate --tui and --stdio2 'perf
     annotate' output, similar to the first line in the 'perf report
     --tui', but just for the samples for a the annotated symbol
     (Arnaldo Carvalho de Melo)

   - Introduce 'perf version --build-options' to show what features were
     linked, aliased as well as a shorter 'perf -vv' (Jin Yao)

   - Add a "dso_size" sort order (Kim Phillips)

   - Remove redundant ')' in the tracepoint output in 'perf trace'
     (Changbin Du)

   - Synchronize x86's cpufeatures.h, no effect on toolss (Arnaldo
     Carvalho de Melo)

   - Show group details on the title line in the annotate browser and
     'perf annotate --stdio2' output, so that the per-event columns can
     have headers (Arnaldo Carvalho de Melo)

   - Fixup vertical line separating metrics from instructions and
     cleaning unused lines at the bottom, both in the annotate TUI
     browser (Arnaldo Carvalho de Melo)

   - Remove duplicated 'samples' in lost samples warning in
     'perf report' (Arnaldo Carvalho de Melo)

   - Synchronize i915_drm.h, silencing the perf build process,
     automagically adding support for the new DRM_I915_QUERY ioctl
     (Arnaldo Carvalho de Melo)

   - Make auxtrace_queues__add_buffer() allocate struct buffer, from a
     patchkit already applied (Adrian Hunter)

   - Fix the --stdio2/TUI annotate output to include group details, be
     it for a recorded '{a,b,f}' explicit event group or when forcing
     group display using 'perf report --group' for a set of events not
     recorded as a group (Arnaldo Carvalho de Melo)

   - Fix display artifacts in the ui browser (base class for the
     annotate and main report/top TUI browser) related to the extra
     title lines work (Arnaldo Carvalho de Melo)

   - perf auxtrace refactorings, leftovers from a previously partially
     processed patchset (Adrian Hunter)

   - Fix the builtin clang build (Sandipan Das, Arnaldo Carvalho de
     Melo)

   - Synchronize i915_drm.h, silencing a perf build warning and in the
     process automagically adding support for a new ioctl command
     (Arnaldo Carvalho de Melo)

   - Fix a strncpy issue in uprobe tracing"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (36 commits)
  perf/core: Need CAP_SYS_ADMIN to create k/uprobe with perf_event_open()
  tracing/uprobe_event: Fix strncpy corner case
  perf/core: Fix perf_uprobe_init()
  perf/core: Fix perf_kprobe_init()
  perf/core: Fix use-after-free in uprobe_perf_close()
  perf tests clang: Fix function name for clang IR test
  perf clang: Add support for recent clang versions
  perf tools: Fix perf builds with clang support
  perf tools: No need to include namespaces.h in util.h
  perf hists browser: Remove leftover from row returned from refresh
  perf hists browser: Show extra_title_lines in the 'D' debug hotkey
  perf auxtrace: Make auxtrace_queues__add_buffer() do CPU filtering
  tools headers uapi: Synchronize i915_drm.h
  perf report: Remove duplicated 'samples' in lost samples warning
  perf ui browser: Fixup cleaning unused lines at the bottom
  perf annotate browser: Fixup vertical line separating metrics from instructions
  perf annotate: Show group details on the title line
  perf auxtrace: Make auxtrace_queues__add_buffer() allocate struct buffer
  perf/x86/intel: Move regs->flags EXACT bit init
  perf trace: Remove redundant ')'
  ...

2 files changed, 142 insertions, 4 deletions

diff --git a/tools/include/tools/config.h b/tools/include/tools/config.h
new file mode 100644
index 000000000000..08ade7df8132
--- /dev/null
+++ b/tools/include/tools/config.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_CONFIG_H
+#define _TOOLS_CONFIG_H
+
+/* Subset of include/linux/kconfig.h */
+
+#define __ARG_PLACEHOLDER_1 0,
+#define __take_second_arg(__ignored, val, ...) val
+
+/*
+ * Helper macros to use CONFIG_ options in C/CPP expressions. Note that
+ * these only work with boolean and tristate options.
+ */
+
+/*
+ * Getting something that works in C and CPP for an arg that may or may
+ * not be defined is tricky.  Here, if we have "#define CONFIG_BOOGER 1"
+ * we match on the placeholder define, insert the "0," for arg1 and generate
+ * the triplet (0, 1, 0).  Then the last step cherry picks the 2nd arg (a one).
+ * When CONFIG_BOOGER is not defined, we generate a (... 1, 0) pair, and when
+ * the last step cherry picks the 2nd arg, we get a zero.
+ */
+#define __is_defined(x)                 ___is_defined(x)
+#define ___is_defined(val)              ____is_defined(__ARG_PLACEHOLDER_##val)
+#define ____is_defined(arg1_or_junk)    __take_second_arg(arg1_or_junk 1, 0)
+
+/*
+ * IS_BUILTIN(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y', 0
+ * otherwise. For boolean options, this is equivalent to
+ * IS_ENABLED(CONFIG_FOO).
+ */
+#define IS_BUILTIN(option) __is_defined(option)
+
+#endif /* _TOOLS_CONFIG_H */
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 536ee4febd74..7f5634ce8e88 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -318,6 +318,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_I915_PERF_OPEN              0x36
 #define DRM_I915_PERF_ADD_CONFIG        0x37
 #define DRM_I915_PERF_REMOVE_CONFIG     0x38
+#define DRM_I915_QUERY                  0x39
 
 #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)
@@ -375,6 +376,7 @@ typedef struct _drm_i915_sarea {
 #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)
+#define DRM_IOCTL_I915_QUERY                    DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_QUERY, struct drm_i915_query)
 
 /* Allow drivers to submit batchbuffers directly to hardware, relying
  * on the security mechanisms provided by hardware.
@@ -1358,7 +1360,9 @@ struct drm_intel_overlay_attrs {
  * active on a given plane.
  */
 
-#define I915_SET_COLORKEY_NONE          (1<<0) /* disable color key matching */
+#define I915_SET_COLORKEY_NONE          (1<<0) /* Deprecated. Instead set
+                                                * flags==0 to disable colorkeying.
+                                                */
 #define I915_SET_COLORKEY_DESTINATION   (1<<1)
 #define I915_SET_COLORKEY_SOURCE        (1<<2)
 struct drm_intel_sprite_colorkey {
@@ -1604,15 +1608,115 @@ struct drm_i915_perf_oa_config {
         __u32 n_flex_regs;
 
         /*
-         * These fields are pointers to tuples of u32 values (register
-         * address, value). For example the expected length of the buffer
-         * pointed by mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs).
+         * These fields are pointers to tuples of u32 values (register address,
+         * value). For example the expected length of the buffer pointed by
+         * mux_regs_ptr is (2 * sizeof(u32) * n_mux_regs).
          */
         __u64 mux_regs_ptr;
         __u64 boolean_regs_ptr;
         __u64 flex_regs_ptr;
 };
 
+struct drm_i915_query_item {
+        __u64 query_id;
+#define DRM_I915_QUERY_TOPOLOGY_INFO    1
+
+        /*
+         * When set to zero by userspace, this is filled with the size of the
+         * data to be written at the data_ptr pointer. The kernel sets this
+         * value to a negative value to signal an error on a particular query
+         * item.
+         */
+        __s32 length;
+
+        /*
+         * Unused for now. Must be cleared to zero.
+         */
+        __u32 flags;
+
+        /*
+         * Data will be written at the location pointed by data_ptr when the
+         * value of length matches the length of the data to be written by the
+         * kernel.
+         */
+        __u64 data_ptr;
+};
+
+struct drm_i915_query {
+        __u32 num_items;
+
+        /*
+         * Unused for now. Must be cleared to zero.
+         */
+        __u32 flags;
+
+        /*
+         * This points to an array of num_items drm_i915_query_item structures.
+         */
+        __u64 items_ptr;
+};
+
+/*
+ * Data written by the kernel with query DRM_I915_QUERY_TOPOLOGY_INFO :
+ *
+ * data: contains the 3 pieces of information :
+ *
+ * - the slice mask with one bit per slice telling whether a slice is
+ *   available. The availability of slice X can be queried with the following
+ *   formula :
+ *
+ *           (data[X / 8] >> (X % 8)) & 1
+ *
+ * - the subslice mask for each slice with one bit per subslice telling
+ *   whether a subslice is available. The availability of subslice Y in slice
+ *   X can be queried with the following formula :
+ *
+ *           (data[subslice_offset +
+ *                 X * subslice_stride +
+ *                 Y / 8] >> (Y % 8)) & 1
+ *
+ * - the EU mask for each subslice in each slice with one bit per EU telling
+ *   whether an EU is available. The availability of EU Z in subslice Y in
+ *   slice X can be queried with the following formula :
+ *
+ *           (data[eu_offset +
+ *                 (X * max_subslices + Y) * eu_stride +
+ *                 Z / 8] >> (Z % 8)) & 1
+ */
+struct drm_i915_query_topology_info {
+        /*
+         * Unused for now. Must be cleared to zero.
+         */
+        __u16 flags;
+
+        __u16 max_slices;
+        __u16 max_subslices;
+        __u16 max_eus_per_subslice;
+
+        /*
+         * Offset in data[] at which the subslice masks are stored.
+         */
+        __u16 subslice_offset;
+
+        /*
+         * Stride at which each of the subslice masks for each slice are
+         * stored.
+         */
+        __u16 subslice_stride;
+
+        /*
+         * Offset in data[] at which the EU masks are stored.
+         */
+        __u16 eu_offset;
+
+        /*
+         * Stride at which each of the EU masks for each subslice are stored.
+         */
+        __u16 eu_stride;
+
+        __u8 data[];
+};
+
 #if defined(__cplusplus)
 }
 #endif