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, 158 insertions, 0 deletions

diff --git a/io_uring/filetable.c b/io_uring/filetable.c
new file mode 100644
index 000000000..cb1838c9f
--- /dev/null
+++ b/io_uring/filetable.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/nospec.h>
+#include <linux/io_uring.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "io_uring.h"
+#include "rsrc.h"
+#include "filetable.h"
+
+static int io_file_bitmap_get(struct io_ring_ctx *ctx)
+{
+	struct io_file_table *table = &ctx->file_table;
+	unsigned long nr = ctx->file_alloc_end;
+	int ret;
+
+	if (!table->bitmap)
+		return -ENFILE;
+
+	if (table->alloc_hint < ctx->file_alloc_start ||
+	    table->alloc_hint >= ctx->file_alloc_end)
+		table->alloc_hint = ctx->file_alloc_start;
+
+	do {
+		ret = find_next_zero_bit(table->bitmap, nr, table->alloc_hint);
+		if (ret != nr)
+			return ret;
+
+		if (table->alloc_hint == ctx->file_alloc_start)
+			break;
+		nr = table->alloc_hint;
+		table->alloc_hint = ctx->file_alloc_start;
+	} while (1);
+
+	return -ENFILE;
+}
+
+bool io_alloc_file_tables(struct io_ring_ctx *ctx, struct io_file_table *table,
+			  unsigned nr_files)
+{
+	if (io_rsrc_data_alloc(&table->data, nr_files))
+		return false;
+	table->bitmap = bitmap_zalloc(nr_files, GFP_KERNEL_ACCOUNT);
+	if (table->bitmap)
+		return true;
+	io_rsrc_data_free(ctx, &table->data);
+	return false;
+}
+
+void io_free_file_tables(struct io_ring_ctx *ctx, struct io_file_table *table)
+{
+	io_rsrc_data_free(ctx, &table->data);
+	bitmap_free(table->bitmap);
+	table->bitmap = NULL;
+}
+
+static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file,
+				 u32 slot_index)
+	__must_hold(&ctx->uring_lock)
+{
+	struct io_rsrc_node *node;
+
+	if (io_is_uring_fops(file))
+		return -EBADF;
+	if (!ctx->file_table.data.nr)
+		return -ENXIO;
+	if (slot_index >= ctx->file_table.data.nr)
+		return -EINVAL;
+
+	node = io_rsrc_node_alloc(ctx, IORING_RSRC_FILE);
+	if (!node)
+		return -ENOMEM;
+
+	if (!io_reset_rsrc_node(ctx, &ctx->file_table.data, slot_index))
+		io_file_bitmap_set(&ctx->file_table, slot_index);
+
+	ctx->file_table.data.nodes[slot_index] = node;
+	io_fixed_file_set(node, file);
+	return 0;
+}
+
+int __io_fixed_fd_install(struct io_ring_ctx *ctx, struct file *file,
+			  unsigned int file_slot)
+{
+	bool alloc_slot = file_slot == IORING_FILE_INDEX_ALLOC;
+	int ret;
+
+	if (alloc_slot) {
+		ret = io_file_bitmap_get(ctx);
+		if (unlikely(ret < 0))
+			return ret;
+		file_slot = ret;
+	} else {
+		file_slot--;
+	}
+
+	ret = io_install_fixed_file(ctx, file, file_slot);
+	if (!ret && alloc_slot)
+		ret = file_slot;
+	return ret;
+}
+/*
+ * Note when io_fixed_fd_install() returns error value, it will ensure
+ * fput() is called correspondingly.
+ */
+int io_fixed_fd_install(struct io_kiocb *req, unsigned int issue_flags,
+			struct file *file, unsigned int file_slot)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+	int ret;
+
+	io_ring_submit_lock(ctx, issue_flags);
+	ret = __io_fixed_fd_install(ctx, file, file_slot);
+	io_ring_submit_unlock(ctx, issue_flags);
+
+	if (unlikely(ret < 0))
+		fput(file);
+	return ret;
+}
+
+int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset)
+{
+	struct io_rsrc_node *node;
+
+	if (unlikely(!ctx->file_table.data.nr))
+		return -ENXIO;
+	if (offset >= ctx->file_table.data.nr)
+		return -EINVAL;
+
+	node = io_rsrc_node_lookup(&ctx->file_table.data, offset);
+	if (!node)
+		return -EBADF;
+	io_reset_rsrc_node(ctx, &ctx->file_table.data, offset);
+	io_file_bitmap_clear(&ctx->file_table, offset);
+	return 0;
+}
+
+int io_register_file_alloc_range(struct io_ring_ctx *ctx,
+				 struct io_uring_file_index_range __user *arg)
+{
+	struct io_uring_file_index_range range;
+	u32 end;
+
+	if (copy_from_user(&range, arg, sizeof(range)))
+		return -EFAULT;
+	if (check_add_overflow(range.off, range.len, &end))
+		return -EOVERFLOW;
+	if (range.resv || end > ctx->file_table.data.nr)
+		return -EINVAL;
+
+	io_file_table_set_alloc_range(ctx, range.off, range.len);
+	return 0;
+}