Merge tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linuxgrafted

Pull io_uring fixes from Jens Axboe:

 - Fix a task_work add use-after-free with SQPOLL.

   The sqpoll thread could pop and complete the last request while
   io_req_normal_work_add() was still looking at them after the mpscq
   push.

   Use the same approach as DEFER_TASKRUN to protect from that, holding
   an RCU read lock across the add, and have exit wait for an RCU grace
   period for SQPOLL rings as well.

 - CQE32 ring fixes: correct the free entry check for 32b CQEs, zero the
   big_cqe for aux CQEs, and only post the dummy skip CQE on CQE_MIXED
   rings

 - Mark the source filter table as COW when cloning bpf filters, so
   registering another filter on the source doesn't modify the shared
   table in place

 - Initialize the task context before running the BPF loop

 - Requeue zcrx multishot receives stopped by a local resource

 - End a TX_TIMESTAMP multishot cmd when the CQ is full (lollipopkit)

* tag 'io_uring-7.3-20261002' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux:
  io_uring: fix task_work add use-after-free with SQPOLL
  io_uring/cmd_net: end TX_TIMESTAMP multishot when the CQ is full
  io_uring/zcrx: requeue multishot receives stopped by a local resource
  io_uring: initialize task context before running the BPF loop
  io_uring: zero big_cqe for aux CQEs on CQE32 rings
  io_uring: fix free entry check for 32b CQEs on CQE32 rings
  io_uring: only post the dummy skip CQE on CQE_MIXED rings
  io_uring/bpf_filter: mark source as COW when cloning filters

1 files changed, 66 insertions, 0 deletions

diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h
new file mode 100644
index 000000000..356cbfbaa
--- /dev/null
+++ b/include/asm-generic/pgtable-nopud.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _PGTABLE_NOPUD_H
+#define _PGTABLE_NOPUD_H
+
+#ifndef __ASSEMBLER__
+
+#include <asm-generic/pgtable-nop4d.h>
+
+#define __PAGETABLE_PUD_FOLDED 1
+
+/*
+ * Having the pud type consist of a p4d gets the size right, and allows
+ * us to conceptually access the p4d entry that this pud is folded into
+ * without casting.
+ */
+typedef struct { p4d_t p4d; } pud_t;
+
+#define PUD_SHIFT	P4D_SHIFT
+#define PTRS_PER_PUD	1
+#define PUD_SIZE  	(1UL << PUD_SHIFT)
+#define PUD_MASK  	(~(PUD_SIZE-1))
+
+/*
+ * The "p4d_xxx()" functions here are trivial for a folded two-level
+ * setup: the pud is never bad, and a pud always exists (as it's folded
+ * into the p4d entry)
+ */
+static inline int p4d_none(p4d_t p4d)		{ return 0; }
+static inline int p4d_bad(p4d_t p4d)		{ return 0; }
+static inline int p4d_present(p4d_t p4d)	{ return 1; }
+static inline void p4d_clear(p4d_t *p4d)	{ }
+#define pud_ERROR(pud)				(p4d_ERROR((pud).p4d))
+
+#define p4d_populate(mm, p4d, pud)		do { } while (0)
+#define p4d_populate_safe(mm, p4d, pud)		do { } while (0)
+/*
+ * (puds are folded into p4ds so this doesn't get actually called,
+ * but the define is needed for a generic inline function.)
+ */
+#define set_p4d(p4dptr, p4dval)	set_pud((pud_t *)(p4dptr), (pud_t) { p4dval })
+
+static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+{
+	return (pud_t *)p4d;
+}
+#define pud_offset pud_offset
+
+#define pud_val(x)				(p4d_val((x).p4d))
+#define __pud(x)				((pud_t) { __p4d(x) })
+
+#define p4d_page(p4d)				(pud_page((pud_t){ p4d }))
+#define p4d_pgtable(p4d)			((pud_t *)(pud_pgtable((pud_t){ p4d })))
+
+/*
+ * allocating and freeing a pud is trivial: the 1-entry pud is
+ * inside the p4d, so has no extra memory associated with it.
+ */
+#define pud_alloc_one(mm, address)		NULL
+#define pud_free(mm, x)				do { } while (0)
+#define pud_free_tlb(tlb, x, a)		        do { } while (0)
+
+#undef  pud_addr_end
+#define pud_addr_end(addr, end)			(end)
+
+#endif /* __ASSEMBLER__ */
+#endif /* _PGTABLE_NOPUD_H */