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, 88 insertions, 0 deletions

diff --git a/lib/math/gcd.c b/lib/math/gcd.c
new file mode 100644
index 000000000..62efca678
--- /dev/null
+++ b/lib/math/gcd.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/kernel.h>
+#include <linux/gcd.h>
+#include <linux/export.h>
+
+/*
+ * This implements the binary GCD algorithm. (Often attributed to Stein,
+ * but as Knuth has noted, appears in a first-century Chinese math text.)
+ *
+ * This is faster than the division-based algorithm even on x86, which
+ * has decent hardware division.
+ */
+
+DEFINE_STATIC_KEY_TRUE(efficient_ffs_key);
+
+#if !defined(CONFIG_CPU_NO_EFFICIENT_FFS)
+
+/* If __ffs is available, the even/odd algorithm benchmarks slower. */
+
+static unsigned long binary_gcd(unsigned long a, unsigned long b)
+{
+	unsigned long r = a | b;
+
+	b >>= __ffs(b);
+	if (b == 1)
+		return r & -r;
+
+	for (;;) {
+		a >>= __ffs(a);
+		if (a == 1)
+			return r & -r;
+		if (a == b)
+			return a << __ffs(r);
+
+		if (a < b)
+			swap(a, b);
+		a -= b;
+	}
+}
+
+#endif
+
+/* If normalization is done by loops, the even/odd algorithm is a win. */
+
+/**
+ * gcd - calculate and return the greatest common divisor of 2 unsigned longs
+ * @a: first value
+ * @b: second value
+ */
+unsigned long gcd(unsigned long a, unsigned long b)
+{
+	unsigned long r = a | b;
+
+	if (!a || !b)
+		return r;
+
+#if !defined(CONFIG_CPU_NO_EFFICIENT_FFS)
+	if (static_branch_likely(&efficient_ffs_key))
+		return binary_gcd(a, b);
+#endif
+
+	/* Isolate lsbit of r */
+	r &= -r;
+
+	while (!(b & r))
+		b >>= 1;
+	if (b == r)
+		return r;
+
+	for (;;) {
+		while (!(a & r))
+			a >>= 1;
+		if (a == r)
+			return r;
+		if (a == b)
+			return a;
+
+		if (a < b)
+			swap(a, b);
+		a -= b;
+		a >>= 1;
+		if (a & r)
+			a += b;
+		a >>= 1;
+	}
+}
+
+EXPORT_SYMBOL_GPL(gcd);