Merge branch 'devx-async' into k.o/for-next

Yishai Hadas says:

Enable DEVX asynchronous query commands

This series enables querying a DEVX object in an asynchronous mode.

The userspace application won't block when calling the firmware and it will be
able to get the response back once that it will be ready.

To enable the above functionality:

- DEVX asynchronous command completion FD object was introduced.
- The applicable file operations were implemented to enable using it by
  the user application.
- Query asynchronous method was added to the DEVX object, it will call the
  firmware asynchronously and manages the response on the given input FD.
- Hot unplug support was added for the FD to work properly upon
  unbind/disassociate.
- mlx5 core fence for asynchronous commands was implemented and used to
  prevent racing upon unbind/disassociate.

This branch is based on mlx5-next & v5.0-rc2 due to dependencies, from
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux

* branch 'devx-async':
  IB/mlx5: Implement DEVX hot unplug for async command FD
  IB/mlx5: Implement the file ops of DEVX async command FD
  IB/mlx5: Introduce async DEVX obj query API
  IB/mlx5: Introduce MLX5_IB_OBJECT_DEVX_ASYNC_CMD_FD

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

8 files changed, 33 insertions, 25 deletions

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index ac9805e0bc76..70de8f6b3aee 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1723,15 +1723,14 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 	err = asprintf(&command,
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
-		 " -l -d %s %s -C \"%s\" 2>/dev/null|grep -v \"%s:\"|expand",
+		 " -l -d %s %s -C \"$1\" 2>/dev/null|grep -v \"$1:\"|expand",
 		 opts->objdump_path ?: "objdump",
 		 opts->disassembler_style ? "-M " : "",
 		 opts->disassembler_style ?: "",
 		 map__rip_2objdump(map, sym->start),
 		 map__rip_2objdump(map, sym->end),
 		 opts->show_asm_raw ? "" : "--no-show-raw",
-		 opts->annotate_src ? "-S" : "",
-		 symfs_filename, symfs_filename);
+		 opts->annotate_src ? "-S" : "");
 
 	if (err < 0) {
 		pr_err("Failure allocating memory for the command to run\n");
@@ -1756,7 +1755,8 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 		close(stdout_fd[0]);
 		dup2(stdout_fd[1], 1);
 		close(stdout_fd[1]);
-		execl("/bin/sh", "sh", "-c", command, NULL);
+		execl("/bin/sh", "sh", "-c", command, "--", symfs_filename,
+		      NULL);
 		perror(command);
 		exit(-1);
 	}
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 32ef7bdca1cf..dc2212e12184 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -766,6 +766,7 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
 			cnode->cycles_count += node->branch_flags.cycles;
 			cnode->iter_count += node->nr_loop_iter;
 			cnode->iter_cycles += node->iter_cycles;
+			cnode->from_count++;
 		}
 	}
 
@@ -1345,10 +1346,10 @@ static int branch_to_str(char *bf, int bfsize,
 static int branch_from_str(char *bf, int bfsize,
 			   u64 branch_count,
 			   u64 cycles_count, u64 iter_count,
-			   u64 iter_cycles)
+			   u64 iter_cycles, u64 from_count)
 {
 	int printed = 0, i = 0;
-	u64 cycles;
+	u64 cycles, v = 0;
 
 	cycles = cycles_count / branch_count;
 	if (cycles) {
@@ -1357,14 +1358,16 @@ static int branch_from_str(char *bf, int bfsize,
 				bf + printed, bfsize - printed);
 	}
 
-	if (iter_count) {
-		printed += count_pri64_printf(i++, "iter",
-				iter_count,
-				bf + printed, bfsize - printed);
+	if (iter_count && from_count) {
+		v = iter_count / from_count;
+		if (v) {
+			printed += count_pri64_printf(i++, "iter",
+					v, bf + printed, bfsize - printed);
 
-		printed += count_pri64_printf(i++, "avg_cycles",
-				iter_cycles / iter_count,
-				bf + printed, bfsize - printed);
+			printed += count_pri64_printf(i++, "avg_cycles",
+					iter_cycles / iter_count,
+					bf + printed, bfsize - printed);
+		}
 	}
 
 	if (i)
@@ -1377,6 +1380,7 @@ static int counts_str_build(char *bf, int bfsize,
 			     u64 branch_count, u64 predicted_count,
 			     u64 abort_count, u64 cycles_count,
 			     u64 iter_count, u64 iter_cycles,
+			     u64 from_count,
 			     struct branch_type_stat *brtype_stat)
 {
 	int printed;
@@ -1389,7 +1393,8 @@ static int counts_str_build(char *bf, int bfsize,
 				predicted_count, abort_count, brtype_stat);
 	} else {
 		printed = branch_from_str(bf, bfsize, branch_count,
-				cycles_count, iter_count, iter_cycles);
+				cycles_count, iter_count, iter_cycles,
+				from_count);
 	}
 
 	if (!printed)
@@ -1402,13 +1407,14 @@ static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
 				   u64 branch_count, u64 predicted_count,
 				   u64 abort_count, u64 cycles_count,
 				   u64 iter_count, u64 iter_cycles,
+				   u64 from_count,
 				   struct branch_type_stat *brtype_stat)
 {
 	char str[256];
 
 	counts_str_build(str, sizeof(str), branch_count,
 			 predicted_count, abort_count, cycles_count,
-			 iter_count, iter_cycles, brtype_stat);
+			 iter_count, iter_cycles, from_count, brtype_stat);
 
 	if (fp)
 		return fprintf(fp, "%s", str);
@@ -1422,6 +1428,7 @@ int callchain_list_counts__printf_value(struct callchain_list *clist,
 	u64 branch_count, predicted_count;
 	u64 abort_count, cycles_count;
 	u64 iter_count, iter_cycles;
+	u64 from_count;
 
 	branch_count = clist->branch_count;
 	predicted_count = clist->predicted_count;
@@ -1429,11 +1436,12 @@ int callchain_list_counts__printf_value(struct callchain_list *clist,
 	cycles_count = clist->cycles_count;
 	iter_count = clist->iter_count;
 	iter_cycles = clist->iter_cycles;
+	from_count = clist->from_count;
 
 	return callchain_counts_printf(fp, bf, bfsize, branch_count,
 				       predicted_count, abort_count,
 				       cycles_count, iter_count, iter_cycles,
-				       &clist->brtype_stat);
+				       from_count, &clist->brtype_stat);
 }
 
 static void free_callchain_node(struct callchain_node *node)
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 154560b1eb65..99d38ac019b8 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -118,6 +118,7 @@ struct callchain_list {
 		bool		has_children;
 	};
 	u64			branch_count;
+	u64			from_count;
 	u64			predicted_count;
 	u64			abort_count;
 	u64			cycles_count;
diff --git a/tools/perf/util/find-vdso-map.c b/tools/perf/util/find-map.c
index d7823e3508fc..7b2300588ece 100644
--- a/tools/perf/util/find-vdso-map.c
+++ b/tools/perf/util/find-map.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-static int find_vdso_map(void **start, void **end)
+static int find_map(void **start, void **end, const char *name)
 {
 	FILE *maps;
 	char line[128];
@@ -7,7 +7,7 @@ static int find_vdso_map(void **start, void **end)
 
 	maps = fopen("/proc/self/maps", "r");
 	if (!maps) {
-		fprintf(stderr, "vdso: cannot open maps\n");
+		fprintf(stderr, "cannot open maps\n");
 		return -1;
 	}
 
@@ -21,8 +21,7 @@ static int find_vdso_map(void **start, void **end)
 		if (m < 0)
 			continue;
 
-		if (!strncmp(&line[m], VDSO__MAP_NAME,
-			     sizeof(VDSO__MAP_NAME) - 1))
+		if (!strncmp(&line[m], name, strlen(name)))
 			found = 1;
 	}
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 6fcb3bce0442..143f7057d581 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2005,7 +2005,7 @@ static void save_iterations(struct iterations *iter,
 {
 	int i;
 
-	iter->nr_loop_iter = nr;
+	iter->nr_loop_iter++;
 	iter->cycles = 0;
 
 	for (i = 0; i < nr; i++)
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index 9005fbe0780e..23092fd6451d 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -109,7 +109,6 @@ static int strbuf_addv(struct strbuf *sb, const char *fmt, va_list ap)
 			return ret;
 		}
 		len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap_saved);
-		va_end(ap_saved);
 		if (len > strbuf_avail(sb)) {
 			pr_debug("this should not happen, your vsnprintf is broken");
 			va_end(ap_saved);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 01f2c7385e38..48efad6d0f90 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -614,6 +614,7 @@ out:
 static bool symbol__is_idle(const char *name)
 {
 	const char * const idle_symbols[] = {
+		"arch_cpu_idle",
 		"cpu_idle",
 		"cpu_startup_entry",
 		"intel_idle",
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 741af209b19d..3702cba11d7d 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -18,10 +18,10 @@
 #include "debug.h"
 
 /*
- * Include definition of find_vdso_map() also used in perf-read-vdso.c for
+ * Include definition of find_map() also used in perf-read-vdso.c for
  * building perf-read-vdso32 and perf-read-vdsox32.
  */
-#include "find-vdso-map.c"
+#include "find-map.c"
 
 #define VDSO__TEMP_FILE_NAME "/tmp/perf-vdso.so-XXXXXX"
 
@@ -76,7 +76,7 @@ static char *get_file(struct vdso_file *vdso_file)
 	if (vdso_file->found)
 		return vdso_file->temp_file_name;
 
-	if (vdso_file->error || find_vdso_map(&start, &end))
+	if (vdso_file->error || find_map(&start, &end, VDSO__MAP_NAME))
 		return NULL;
 
 	size = end - start;