sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling buggrafted

alb_break_llc() decides whether to break LLC preference during active
load balance. It does so by testing that every runnable fair task on the
source rq prefers its LLC:

	env->src_rq->nr_pref_llc_running == env->src_rq->cfs.h_nr_runnable

But the two counters cover different sets. nr_pref_llc_running is updated
in account_llc_enqueue()/account_llc_dequeue(), next to cfs_rq->nr_queued,
so it follows queued tasks. h_nr_runnable is updated in set_delayed()/
clear_delayed() and drops delay-dequeued tasks.

So under DELAY_DEQUEUE, a preferring task that goes to sleep stays counted
in nr_pref_llc_running while h_nr_runnable falls. The equality then breaks,
alb_break_llc() returns false, and active balance is free to pull a task
off its preferred LLC. Active balance only moves runnable tasks, and this
is the only LLC check it consults: once the stopper runs, LBF_ACTIVE_LB
skips the per-task test in can_migrate_task(). The runnable set is the one
we want.

Fix it on the counter side. A task should be counted in
nr_pref_llc_running exactly while it is both queued on its preferred LLC
(pref_llc_queued) and runnable (!sched_delayed). Define that membership
once in task_pref_llc_runnable(), and adjust the counter only through
pref_llc_running_inc()/pref_llc_running_dec() from the four sites that
change either input: account_llc_enqueue(), account_llc_dequeue(),
set_delayed() and clear_delayed(). Gating every update on the same
predicate keeps the delay, wake and dequeue paths from double-counting
or underflowing; see the comments at those sites for the ordering.

nr_llc_running and sd->llc_counts are not touched and stay on queued
semantics.

Fixes: 714059f79ff0 ("sched/cache: Handle moving single tasks to/from their preferred LLC")
Closes: https://lore.kernel.org/lkml/20260827135000.735138-1-zhanxusheng@xiaomi.com/
Reported-by: Zhan Xusheng <zhanxusheng@xiaomi.com>
Suggested-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kayra Cizmeci <kayracizmeci@gmail.com>
Cc: <stable@kernel.org> # v7.2.x
Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com

1 files changed, 215 insertions, 0 deletions

diff --git a/tools/perf/util/debuginfo.c b/tools/perf/util/debuginfo.c
new file mode 100644
index 000000000..84a78b30c
--- /dev/null
+++ b/tools/perf/util/debuginfo.c
@@ -0,0 +1,215 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * DWARF debug information handling code.  Copied from probe-finder.c.
+ *
+ * Written by Masami Hiramatsu <mhiramat@redhat.com>
+ */
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/zalloc.h>
+
+#include "build-id.h"
+#include "dso.h"
+#include "debug.h"
+#include "debuginfo.h"
+#include "symbol.h"
+
+#ifdef HAVE_DEBUGINFOD_SUPPORT
+#include <elfutils/debuginfod.h>
+#endif
+
+/* Dwarf FL wrappers */
+static char *debuginfo_path;	/* Currently dummy */
+
+static const Dwfl_Callbacks offline_callbacks = {
+	.find_debuginfo = dwfl_standard_find_debuginfo,
+	.debuginfo_path = &debuginfo_path,
+
+	.section_address = dwfl_offline_section_address,
+
+	/* We use this table for core files too.  */
+	.find_elf = dwfl_build_id_find_elf,
+};
+
+/* Get a Dwarf from offline image */
+static int debuginfo__init_offline_dwarf(struct debuginfo *dbg,
+					 const char *path)
+{
+	GElf_Addr dummy;
+	int fd;
+	bool fd_consumed = false;
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		return fd;
+
+	dbg->dwfl = dwfl_begin(&offline_callbacks);
+	if (!dbg->dwfl)
+		goto error;
+
+	dwfl_report_begin(dbg->dwfl);
+	dbg->mod = dwfl_report_offline(dbg->dwfl, "", "", fd);
+	if (!dbg->mod)
+		goto error;
+	fd_consumed = true;
+
+	dbg->dbg = dwfl_module_getdwarf(dbg->mod, &dbg->bias);
+	if (!dbg->dbg)
+		goto error;
+
+	dwfl_module_build_id(dbg->mod, &dbg->build_id, &dummy);
+
+	if (dwfl_report_end(dbg->dwfl, NULL, NULL) != 0)
+		goto error;
+
+	return 0;
+error:
+	if (dbg->dwfl)
+		dwfl_end(dbg->dwfl);
+	if (!fd_consumed)
+		close(fd);
+	memset(dbg, 0, sizeof(*dbg));
+
+	return -ENOENT;
+}
+
+static struct debuginfo *__debuginfo__new(const char *path)
+{
+	struct debuginfo *dbg = zalloc(sizeof(*dbg));
+	if (!dbg)
+		return NULL;
+
+	if (debuginfo__init_offline_dwarf(dbg, path) < 0)
+		zfree(&dbg);
+	if (dbg)
+		pr_debug("Open Debuginfo file: %s\n", path);
+	return dbg;
+}
+
+struct debuginfo *debuginfo__new(const char *path)
+{
+	static const enum dso_binary_type distro_dwarf_types[] = {
+		DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
+		DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
+		DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
+		DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
+		DSO_BINARY_TYPE__MIXEDUP_UBUNTU_DEBUGINFO,
+		DSO_BINARY_TYPE__NOT_FOUND,
+	};
+	const enum dso_binary_type *type;
+	char buf[PATH_MAX], nil = '\0';
+	struct dso *dso;
+	struct debuginfo *dinfo = NULL;
+	struct build_id bid = { .size = 0};
+
+	/* Try to open distro debuginfo files */
+	dso = dso__new(path);
+	if (!dso)
+		goto out;
+
+	/*
+	 * Set the build id for DSO_BINARY_TYPE__BUILDID_DEBUGINFO. Don't block
+	 * incase the path isn't for a regular file.
+	 */
+	assert(!dso__has_build_id(dso));
+	if (filename__read_build_id(path, &bid) > 0)
+		dso__set_build_id(dso, &bid);
+
+	for (type = distro_dwarf_types;
+	     !dinfo && *type != DSO_BINARY_TYPE__NOT_FOUND;
+	     type++) {
+		if (dso__read_binary_type_filename(dso, *type, &nil,
+						   buf, PATH_MAX) < 0)
+			continue;
+		dinfo = __debuginfo__new(buf);
+	}
+	dso__put(dso);
+
+out:
+	if (dinfo)
+		return dinfo;
+
+	/* if failed to open all distro debuginfo, open given binary */
+	symbol__join_symfs(buf, path);
+	return __debuginfo__new(buf);
+}
+
+void debuginfo__delete(struct debuginfo *dbg)
+{
+	if (dbg) {
+		if (dbg->dwfl)
+			dwfl_end(dbg->dwfl);
+		free(dbg);
+	}
+}
+
+/* For the kernel module, we need a special code to get a DIE */
+int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
+				bool adjust_offset)
+{
+	int n, i;
+	Elf32_Word shndx;
+	Elf_Scn *scn;
+	Elf *elf;
+	GElf_Shdr mem, *shdr;
+	const char *p;
+
+	elf = dwfl_module_getelf(dbg->mod, &dbg->bias);
+	if (!elf)
+		return -EINVAL;
+
+	/* Get the number of relocations */
+	n = dwfl_module_relocations(dbg->mod);
+	if (n < 0)
+		return -ENOENT;
+	/* Search the relocation related .text section */
+	for (i = 0; i < n; i++) {
+		p = dwfl_module_relocation_info(dbg->mod, i, &shndx);
+		if (p && strcmp(p, ".text") == 0) {
+			/* OK, get the section header */
+			scn = elf_getscn(elf, shndx);
+			if (!scn)
+				return -ENOENT;
+			shdr = gelf_getshdr(scn, &mem);
+			if (!shdr)
+				return -ENOENT;
+			*offs = shdr->sh_addr;
+			if (adjust_offset)
+				*offs -= shdr->sh_offset;
+		}
+	}
+	return 0;
+}
+
+#ifdef HAVE_DEBUGINFOD_SUPPORT
+int get_source_from_debuginfod(const char *raw_path,
+			       const char *sbuild_id, char **new_path)
+{
+	debuginfod_client *c = debuginfod_begin();
+	const char *p = raw_path;
+	int fd;
+
+	if (!c)
+		return -ENOMEM;
+
+	fd = debuginfod_find_source(c, (const unsigned char *)sbuild_id,
+				0, p, new_path);
+	pr_debug("Search %s from debuginfod -> %d\n", p, fd);
+	if (fd >= 0)
+		close(fd);
+	debuginfod_end(c);
+	if (fd < 0) {
+		pr_debug("Failed to find %s in debuginfod (%s)\n",
+			raw_path, sbuild_id);
+		return -ENOENT;
+	}
+	pr_debug("Got a source %s\n", *new_path);
+
+	return 0;
+}
+#endif /* HAVE_DEBUGINFOD_SUPPORT */