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

6 files changed, 444 insertions, 0 deletions

diff --git a/lib/raid/raid6/arm/neon.c b/lib/raid/raid6/arm/neon.c
new file mode 100644
index 000000000..af90869aa
--- /dev/null
+++ b/lib/raid/raid6/arm/neon.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * RAID6 syndrome calculation using ARM NEON intrinsics
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/simd.h>
+#include "algos.h"
+
+/*
+ * There are 2 reasons these wrappers are kept in a separate compilation unit
+ * from the actual implementations in neonN.c (generated from neon.uc by
+ * unroll.awk):
+ * - the actual implementations use NEON intrinsics, and the GCC support header
+ *   (arm_neon.h) is not fully compatible (type wise) with the kernel;
+ * - the neonN.c files are compiled with -mfpu=neon and optimization enabled,
+ *   and we have to make sure that we never use *any* NEON/VFP instructions
+ *   outside a kernel_neon_begin()/kernel_neon_end() pair.
+ */
+
+#define RAID6_NEON_WRAPPER(_n)						\
+	static void raid6_neon ## _n ## _gen_syndrome(int disks,	\
+					size_t bytes, void **ptrs)	\
+	{								\
+		void raid6_neon ## _n  ## _gen_syndrome_real(int,	\
+						unsigned long, void**);	\
+		scoped_ksimd()						\
+			raid6_neon ## _n ## _gen_syndrome_real(disks,	\
+					(unsigned long)bytes, ptrs);	\
+	}								\
+	static void raid6_neon ## _n ## _xor_syndrome(int disks,	\
+					int start, int stop, 		\
+					size_t bytes, void **ptrs)	\
+	{								\
+		void raid6_neon ## _n  ## _xor_syndrome_real(int,	\
+				int, int, unsigned long, void**);	\
+		scoped_ksimd()						\
+			raid6_neon ## _n ## _xor_syndrome_real(disks,	\
+				start, stop, (unsigned long)bytes, ptrs);\
+	}								\
+	struct raid6_calls const raid6_neonx ## _n = {			\
+		.gen_syndrome	= raid6_neon ## _n ## _gen_syndrome,	\
+		.xor_syndrome	= raid6_neon ## _n ## _xor_syndrome,	\
+		.name		= "neonx" #_n,				\
+	}
+
+RAID6_NEON_WRAPPER(1);
+RAID6_NEON_WRAPPER(2);
+RAID6_NEON_WRAPPER(4);
+RAID6_NEON_WRAPPER(8);
diff --git a/lib/raid/raid6/arm/neon.h b/lib/raid/raid6/arm/neon.h
new file mode 100644
index 000000000..2ca41ee9b
--- /dev/null
+++ b/lib/raid/raid6/arm/neon.h
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+void raid6_neon1_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs);
+void raid6_neon1_xor_syndrome_real(int disks, int start, int stop,
+				    unsigned long bytes, void **ptrs);
+void raid6_neon2_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs);
+void raid6_neon2_xor_syndrome_real(int disks, int start, int stop,
+				    unsigned long bytes, void **ptrs);
+void raid6_neon4_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs);
+void raid6_neon4_xor_syndrome_real(int disks, int start, int stop,
+				    unsigned long bytes, void **ptrs);
+void raid6_neon8_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs);
+void raid6_neon8_xor_syndrome_real(int disks, int start, int stop,
+				    unsigned long bytes, void **ptrs);
+void __raid6_2data_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dp,
+			      uint8_t *dq, const uint8_t *pbmul,
+			      const uint8_t *qmul);
+
+void __raid6_datap_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dq,
+			      const uint8_t *qmul);
+
+
diff --git a/lib/raid/raid6/arm/neon.uc b/lib/raid/raid6/arm/neon.uc
new file mode 100644
index 000000000..14a9fc2c6
--- /dev/null
+++ b/lib/raid/raid6/arm/neon.uc
@@ -0,0 +1,153 @@
+/* -----------------------------------------------------------------------
+ *
+ *   neon.uc - RAID-6 syndrome calculation using ARM NEON instructions
+ *
+ *   Copyright (C) 2012 Rob Herring
+ *   Copyright (C) 2015 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ *   Based on altivec.uc:
+ *     Copyright 2002-2004 H. Peter Anvin - All Rights Reserved
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation, Inc., 53 Temple Place Ste 330,
+ *   Boston MA 02111-1307, USA; either version 2 of the License, or
+ *   (at your option) any later version; incorporated herein by reference.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * neon$#.c
+ *
+ * $#-way unrolled NEON intrinsics math RAID-6 instruction set
+ *
+ * This file is postprocessed using unroll.awk
+ */
+
+#include <arm_neon.h>
+#include "arm/neon.h"
+
+typedef uint8x16_t unative_t;
+
+#define NSIZE	sizeof(unative_t)
+
+/*
+ * The SHLBYTE() operation shifts each byte left by 1, *not*
+ * rolling over into the next byte
+ */
+static inline unative_t SHLBYTE(unative_t v)
+{
+	return vshlq_n_u8(v, 1);
+}
+
+/*
+ * The MASK() operation returns 0xFF in any byte for which the high
+ * bit is 1, 0x00 for any byte for which the high bit is 0.
+ */
+static inline unative_t MASK(unative_t v)
+{
+	return (unative_t)vshrq_n_s8((int8x16_t)v, 7);
+}
+
+static inline unative_t PMUL(unative_t v, unative_t u)
+{
+	return (unative_t)vmulq_p8((poly8x16_t)v, (poly8x16_t)u);
+}
+
+void raid6_neon$#_gen_syndrome_real(int disks, unsigned long bytes, void **ptrs)
+{
+	uint8_t **dptr = (uint8_t **)ptrs;
+	uint8_t *p, *q;
+	int d, z, z0;
+
+	register unative_t wd$$, wq$$, wp$$, w1$$, w2$$;
+	const unative_t x1d = vdupq_n_u8(0x1d);
+
+	z0 = disks - 3;		/* Highest data disk */
+	p = dptr[z0+1];		/* XOR parity */
+	q = dptr[z0+2];		/* RS syndrome */
+
+	for ( d = 0 ; d < bytes ; d += NSIZE*$# ) {
+		wq$$ = wp$$ = vld1q_u8(&dptr[z0][d+$$*NSIZE]);
+		for ( z = z0-1 ; z >= 0 ; z-- ) {
+			wd$$ = vld1q_u8(&dptr[z][d+$$*NSIZE]);
+			wp$$ = veorq_u8(wp$$, wd$$);
+			w2$$ = MASK(wq$$);
+			w1$$ = SHLBYTE(wq$$);
+
+			w2$$ = vandq_u8(w2$$, x1d);
+			w1$$ = veorq_u8(w1$$, w2$$);
+			wq$$ = veorq_u8(w1$$, wd$$);
+		}
+		vst1q_u8(&p[d+NSIZE*$$], wp$$);
+		vst1q_u8(&q[d+NSIZE*$$], wq$$);
+	}
+}
+
+void raid6_neon$#_xor_syndrome_real(int disks, int start, int stop,
+				    unsigned long bytes, void **ptrs)
+{
+	uint8_t **dptr = (uint8_t **)ptrs;
+	uint8_t *p, *q;
+	int d, z, z0;
+
+	register unative_t wd$$, wq$$, wp$$, w1$$, w2$$;
+	const unative_t x1d = vdupq_n_u8(0x1d);
+
+	z0 = stop;		/* P/Q right side optimization */
+	p = dptr[disks-2];	/* XOR parity */
+	q = dptr[disks-1];	/* RS syndrome */
+
+	for ( d = 0 ; d < bytes ; d += NSIZE*$# ) {
+		wq$$ = vld1q_u8(&dptr[z0][d+$$*NSIZE]);
+		wp$$ = veorq_u8(vld1q_u8(&p[d+$$*NSIZE]), wq$$);
+
+		/* P/Q data pages */
+		for ( z = z0-1 ; z >= start ; z-- ) {
+			wd$$ = vld1q_u8(&dptr[z][d+$$*NSIZE]);
+			wp$$ = veorq_u8(wp$$, wd$$);
+			w2$$ = MASK(wq$$);
+			w1$$ = SHLBYTE(wq$$);
+
+			w2$$ = vandq_u8(w2$$, x1d);
+			w1$$ = veorq_u8(w1$$, w2$$);
+			wq$$ = veorq_u8(w1$$, wd$$);
+		}
+		/* P/Q left side optimization */
+		for ( z = start-1 ; z >= 3 ; z -= 4 ) {
+			w2$$ = vshrq_n_u8(wq$$, 4);
+			w1$$ = vshlq_n_u8(wq$$, 4);
+
+			w2$$ = PMUL(w2$$, x1d);
+			wq$$ = veorq_u8(w1$$, w2$$);
+		}
+
+		switch (z) {
+		case 2:
+			w2$$ = vshrq_n_u8(wq$$, 5);
+			w1$$ = vshlq_n_u8(wq$$, 3);
+
+			w2$$ = PMUL(w2$$, x1d);
+			wq$$ = veorq_u8(w1$$, w2$$);
+			break;
+		case 1:
+			w2$$ = vshrq_n_u8(wq$$, 6);
+			w1$$ = vshlq_n_u8(wq$$, 2);
+
+			w2$$ = PMUL(w2$$, x1d);
+			wq$$ = veorq_u8(w1$$, w2$$);
+			break;
+		case 0:
+			w2$$ = MASK(wq$$);
+			w1$$ = SHLBYTE(wq$$);
+
+			w2$$ = vandq_u8(w2$$, x1d);
+			wq$$ = veorq_u8(w1$$, w2$$);
+		}
+		w1$$ = vld1q_u8(&q[d+NSIZE*$$]);
+		wq$$ = veorq_u8(wq$$, w1$$);
+
+		vst1q_u8(&p[d+NSIZE*$$], wp$$);
+		vst1q_u8(&q[d+NSIZE*$$], wq$$);
+	}
+}
diff --git a/lib/raid/raid6/arm/pq_arch.h b/lib/raid/raid6/arm/pq_arch.h
new file mode 100644
index 000000000..3f876ea67
--- /dev/null
+++ b/lib/raid/raid6/arm/pq_arch.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#include <asm/neon.h>
+
+extern const struct raid6_calls raid6_neonx1;
+extern const struct raid6_calls raid6_neonx2;
+extern const struct raid6_calls raid6_neonx4;
+extern const struct raid6_calls raid6_neonx8;
+extern const struct raid6_recov_calls raid6_recov_neon;
+
+static __always_inline void __init arch_raid6_init(void)
+{
+	raid6_algo_add_default();
+	if (cpu_has_neon()) {
+		raid6_algo_add(&raid6_neonx1);
+		raid6_algo_add(&raid6_neonx2);
+		raid6_algo_add(&raid6_neonx4);
+		raid6_algo_add(&raid6_neonx8);
+		raid6_recov_algo_add(&raid6_recov_neon);
+	}
+}
diff --git a/lib/raid/raid6/arm/recov_neon.c b/lib/raid/raid6/arm/recov_neon.c
new file mode 100644
index 000000000..1524050d0
--- /dev/null
+++ b/lib/raid/raid6/arm/recov_neon.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 Intel Corporation
+ * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <linux/mm.h>
+#include <linux/raid/pq.h>
+#include <asm/simd.h>
+#include "algos.h"
+#include "arm/neon.h"
+
+static void raid6_2data_recov_neon(int disks, size_t bytes, int faila,
+		int failb, void **ptrs)
+{
+	u8 *p, *q, *dp, *dq;
+	const u8 *pbmul;	/* P multiplier table for B data */
+	const u8 *qmul;		/* Q multiplier table (for both) */
+
+	p = (u8 *)ptrs[disks - 2];
+	q = (u8 *)ptrs[disks - 1];
+
+	/*
+	 * Compute syndrome with zero for the missing data pages
+	 * Use the dead data pages as temporary storage for
+	 * delta p and delta q
+	 */
+	dp = (u8 *)ptrs[faila];
+	ptrs[faila] = page_address(ZERO_PAGE(0));
+	ptrs[disks - 2] = dp;
+	dq = (u8 *)ptrs[failb];
+	ptrs[failb] = page_address(ZERO_PAGE(0));
+	ptrs[disks - 1] = dq;
+
+	raid6_gen_syndrome(disks, bytes, ptrs);
+
+	/* Restore pointer table */
+	ptrs[faila]     = dp;
+	ptrs[failb]     = dq;
+	ptrs[disks - 2] = p;
+	ptrs[disks - 1] = q;
+
+	/* Now, pick the proper data tables */
+	pbmul = raid6_vgfmul[raid6_gfexi[failb-faila]];
+	qmul  = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila] ^
+					 raid6_gfexp[failb]]];
+
+	scoped_ksimd()
+		__raid6_2data_recov_neon(bytes, p, q, dp, dq, pbmul, qmul);
+}
+
+static void raid6_datap_recov_neon(int disks, size_t bytes, int faila,
+		void **ptrs)
+{
+	u8 *p, *q, *dq;
+	const u8 *qmul;		/* Q multiplier table */
+
+	p = (u8 *)ptrs[disks - 2];
+	q = (u8 *)ptrs[disks - 1];
+
+	/*
+	 * Compute syndrome with zero for the missing data page
+	 * Use the dead data page as temporary storage for delta q
+	 */
+	dq = (u8 *)ptrs[faila];
+	ptrs[faila] = page_address(ZERO_PAGE(0));
+	ptrs[disks - 1] = dq;
+
+	raid6_gen_syndrome(disks, bytes, ptrs);
+
+	/* Restore pointer table */
+	ptrs[faila]     = dq;
+	ptrs[disks - 1] = q;
+
+	/* Now, pick the proper data tables */
+	qmul = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila]]];
+
+	scoped_ksimd()
+		__raid6_datap_recov_neon(bytes, p, q, dq, qmul);
+}
+
+const struct raid6_recov_calls raid6_recov_neon = {
+	.data2		= raid6_2data_recov_neon,
+	.datap		= raid6_datap_recov_neon,
+	.name		= "neon",
+};
diff --git a/lib/raid/raid6/arm/recov_neon_inner.c b/lib/raid/raid6/arm/recov_neon_inner.c
new file mode 100644
index 000000000..53c355efa
--- /dev/null
+++ b/lib/raid/raid6/arm/recov_neon_inner.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2012 Intel Corporation
+ * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <arm_neon.h>
+#include "arm/neon.h"
+
+#ifdef CONFIG_ARM
+/*
+ * AArch32 does not provide this intrinsic natively because it does not
+ * implement the underlying instruction. AArch32 only provides a 64-bit
+ * wide vtbl.8 instruction, so use that instead.
+ */
+static uint8x16_t vqtbl1q_u8(uint8x16_t a, uint8x16_t b)
+{
+	union {
+		uint8x16_t	val;
+		uint8x8x2_t	pair;
+	} __a = { a };
+
+	return vcombine_u8(vtbl2_u8(__a.pair, vget_low_u8(b)),
+			   vtbl2_u8(__a.pair, vget_high_u8(b)));
+}
+#endif
+
+void __raid6_2data_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dp,
+			      uint8_t *dq, const uint8_t *pbmul,
+			      const uint8_t *qmul)
+{
+	uint8x16_t pm0 = vld1q_u8(pbmul);
+	uint8x16_t pm1 = vld1q_u8(pbmul + 16);
+	uint8x16_t qm0 = vld1q_u8(qmul);
+	uint8x16_t qm1 = vld1q_u8(qmul + 16);
+	uint8x16_t x0f = vdupq_n_u8(0x0f);
+
+	/*
+	 * while ( bytes-- ) {
+	 *	uint8_t px, qx, db;
+	 *
+	 *	px    = *p ^ *dp;
+	 *	qx    = qmul[*q ^ *dq];
+	 *	*dq++ = db = pbmul[px] ^ qx;
+	 *	*dp++ = db ^ px;
+	 *	p++; q++;
+	 * }
+	 */
+
+	while (bytes) {
+		uint8x16_t vx, vy, px, qx, db;
+
+		px = veorq_u8(vld1q_u8(p), vld1q_u8(dp));
+		vx = veorq_u8(vld1q_u8(q), vld1q_u8(dq));
+
+		vy = vshrq_n_u8(vx, 4);
+		vx = vqtbl1q_u8(qm0, vandq_u8(vx, x0f));
+		vy = vqtbl1q_u8(qm1, vy);
+		qx = veorq_u8(vx, vy);
+
+		vy = vshrq_n_u8(px, 4);
+		vx = vqtbl1q_u8(pm0, vandq_u8(px, x0f));
+		vy = vqtbl1q_u8(pm1, vy);
+		vx = veorq_u8(vx, vy);
+		db = veorq_u8(vx, qx);
+
+		vst1q_u8(dq, db);
+		vst1q_u8(dp, veorq_u8(db, px));
+
+		bytes -= 16;
+		p += 16;
+		q += 16;
+		dp += 16;
+		dq += 16;
+	}
+}
+
+void __raid6_datap_recov_neon(int bytes, uint8_t *p, uint8_t *q, uint8_t *dq,
+			      const uint8_t *qmul)
+{
+	uint8x16_t qm0 = vld1q_u8(qmul);
+	uint8x16_t qm1 = vld1q_u8(qmul + 16);
+	uint8x16_t x0f = vdupq_n_u8(0x0f);
+
+	/*
+	 * while (bytes--) {
+	 *	*p++ ^= *dq = qmul[*q ^ *dq];
+	 *	q++; dq++;
+	 * }
+	 */
+
+	while (bytes) {
+		uint8x16_t vx, vy;
+
+		vx = veorq_u8(vld1q_u8(q), vld1q_u8(dq));
+
+		vy = vshrq_n_u8(vx, 4);
+		vx = vqtbl1q_u8(qm0, vandq_u8(vx, x0f));
+		vy = vqtbl1q_u8(qm1, vy);
+		vx = veorq_u8(vx, vy);
+		vy = veorq_u8(vx, vld1q_u8(p));
+
+		vst1q_u8(dq, vx);
+		vst1q_u8(p, vy);
+
+		bytes -= 16;
+		p += 16;
+		q += 16;
+		dq += 16;
+	}
+}