Merge 5.10.129 into android12-5.10-lts

Changes in 5.10.129
	drm/amdgpu: To flush tlb for MMHUB of RAVEN series
	ipv6: take care of disable_policy when restoring routes
	nvme-pci: add NVME_QUIRK_BOGUS_NID for ADATA XPG SX6000LNP (AKA SPECTRIX S40G)
	nvdimm: Fix badblocks clear off-by-one error
	powerpc/prom_init: Fix kernel config grep
	powerpc/book3e: Fix PUD allocation size in map_kernel_page()
	powerpc/bpf: Fix use of user_pt_regs in uapi
	dm raid: fix accesses beyond end of raid member array
	dm raid: fix KASAN warning in raid5_add_disks
	s390/archrandom: simplify back to earlier design and initialize earlier
	SUNRPC: Fix READ_PLUS crasher
	net: rose: fix UAF bugs caused by timer handler
	net: usb: ax88179_178a: Fix packet receiving
	virtio-net: fix race between ndo_open() and virtio_device_ready()
	selftests/net: pass ipv6_args to udpgso_bench's IPv6 TCP test
	net: dsa: bcm_sf2: force pause link settings
	net: tun: unlink NAPI from device on destruction
	net: tun: stop NAPI when detaching queues
	net: dp83822: disable false carrier interrupt
	net: dp83822: disable rx error interrupt
	RDMA/qedr: Fix reporting QP timeout attribute
	RDMA/cm: Fix memory leak in ib_cm_insert_listen
	linux/dim: Fix divide by 0 in RDMA DIM
	usbnet: fix memory allocation in helpers
	net: ipv6: unexport __init-annotated seg6_hmac_net_init()
	NFSD: restore EINVAL error translation in nfsd_commit()
	caif_virtio: fix race between virtio_device_ready() and ndo_open()
	PM / devfreq: exynos-ppmu: Fix refcount leak in of_get_devfreq_events
	s390: remove unneeded 'select BUILD_BIN2C'
	netfilter: nft_dynset: restore set element counter when failing to update
	net/sched: act_api: Notify user space if any actions were flushed before error
	net: bonding: fix possible NULL deref in rlb code
	net: bonding: fix use-after-free after 802.3ad slave unbind
	nfc: nfcmrvl: Fix irq_of_parse_and_map() return value
	NFC: nxp-nci: Don't issue a zero length i2c_master_read()
	tipc: move bc link creation back to tipc_node_create
	epic100: fix use after free on rmmod
	io_uring: ensure that send/sendmsg and recv/recvmsg check sqe->ioprio
	tunnels: do not assume mac header is set in skb_tunnel_check_pmtu()
	net: tun: avoid disabling NAPI twice
	xfs: use current->journal_info for detecting transaction recursion
	xfs: rename variable mp to parsing_mp
	xfs: Skip repetitive warnings about mount options
	xfs: ensure xfs_errortag_random_default matches XFS_ERRTAG_MAX
	xfs: fix xfs_trans slab cache name
	xfs: update superblock counters correctly for !lazysbcount
	xfs: fix xfs_reflink_unshare usage of filemap_write_and_wait_range
	tcp: add a missing nf_reset_ct() in 3WHS handling
	xen/gntdev: Avoid blocking in unmap_grant_pages()
	drivers: cpufreq: Add missing of_node_put() in qoriq-cpufreq.c
	sit: use min
	ipv6/sit: fix ipip6_tunnel_get_prl return value
	hwmon: (ibmaem) don't call platform_device_del() if platform_device_add() fails
	selftests/rseq: remove ARRAY_SIZE define from individual tests
	selftests/rseq: introduce own copy of rseq uapi header
	selftests/rseq: Remove useless assignment to cpu variable
	selftests/rseq: Remove volatile from __rseq_abi
	selftests/rseq: Introduce rseq_get_abi() helper
	selftests/rseq: Introduce thread pointer getters
	selftests/rseq: Uplift rseq selftests for compatibility with glibc-2.35
	selftests/rseq: Fix ppc32: wrong rseq_cs 32-bit field pointer on big endian
	selftests/rseq: Fix ppc32 missing instruction selection "u" and "x" for load/store
	selftests/rseq: Fix ppc32 offsets by using long rather than off_t
	selftests/rseq: Fix warnings about #if checks of undefined tokens
	selftests/rseq: Remove arm/mips asm goto compiler work-around
	selftests/rseq: Fix: work-around asm goto compiler bugs
	selftests/rseq: x86-64: use %fs segment selector for accessing rseq thread area
	selftests/rseq: x86-32: use %gs segment selector for accessing rseq thread area
	selftests/rseq: Change type of rseq_offset to ptrdiff_t
	xen/blkfront: fix leaking data in shared pages
	xen/netfront: fix leaking data in shared pages
	xen/netfront: force data bouncing when backend is untrusted
	xen/blkfront: force data bouncing when backend is untrusted
	xen-netfront: restore __skb_queue_tail() positioning in xennet_get_responses()
	xen/arm: Fix race in RB-tree based P2M accounting
	net: usb: qmi_wwan: add Telit 0x1060 composition
	net: usb: qmi_wwan: add Telit 0x1070 composition
	clocksource/drivers/ixp4xx: remove EXPORT_SYMBOL_GPL from ixp4xx_timer_setup()
	Linux 5.10.129

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: I7a2bdb1fd13c78604c728f4cbfb6f659d7a348e3

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 10
-SUBLEVEL = 128
+SUBLEVEL = 129
 EXTRAVERSION =
 NAME = Dare mighty things
 

arch/arm/xen/p2m.c

@@ -62,11 +62,12 @@ out:
 
 unsigned long __pfn_to_mfn(unsigned long pfn)
 {
-	struct rb_node *n = phys_to_mach.rb_node;
+	struct rb_node *n;
 	struct xen_p2m_entry *entry;
 	unsigned long irqflags;
 
 	read_lock_irqsave(&p2m_lock, irqflags);
+	n = phys_to_mach.rb_node;
 	while (n) {
 		entry = rb_entry(n, struct xen_p2m_entry, rbnode_phys);
 		if (entry->pfn <= pfn &&
@@ -153,10 +154,11 @@ bool __set_phys_to_machine_multi(unsigned long pfn,
 	int rc;
 	unsigned long irqflags;
 	struct xen_p2m_entry *p2m_entry;
-	struct rb_node *n = phys_to_mach.rb_node;
+	struct rb_node *n;
 
 	if (mfn == INVALID_P2M_ENTRY) {
 		write_lock_irqsave(&p2m_lock, irqflags);
+		n = phys_to_mach.rb_node;
 		while (n) {
 			p2m_entry = rb_entry(n, struct xen_p2m_entry, rbnode_phys);
 			if (p2m_entry->pfn <= pfn &&

arch/powerpc/include/asm/bpf_perf_event.h

@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BPF_PERF_EVENT_H
+#define _ASM_POWERPC_BPF_PERF_EVENT_H
+
+#include <asm/ptrace.h>
+
+typedef struct user_pt_regs bpf_user_pt_regs_t;
+
+#endif /* _ASM_POWERPC_BPF_PERF_EVENT_H */

arch/powerpc/include/uapi/asm/bpf_perf_event.h

@@ -1,9 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__
-#define _UAPI__ASM_BPF_PERF_EVENT_H__
-
-#include <asm/ptrace.h>
-
-typedef struct user_pt_regs bpf_user_pt_regs_t;
-
-#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */

arch/powerpc/kernel/prom_init_check.sh

@@ -13,7 +13,7 @@
 # If you really need to reference something from prom_init.o add
 # it to the list below:
 
-grep "^CONFIG_KASAN=y$" .config >/dev/null
+grep "^CONFIG_KASAN=y$" ${KCONFIG_CONFIG} >/dev/null
 if [ $? -eq 0 ]
 then
 	MEM_FUNCS="__memcpy __memset"

arch/powerpc/mm/nohash/book3e_pgtable.c

@@ -95,8 +95,8 @@ int __ref map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot)
 		pgdp = pgd_offset_k(ea);
 		p4dp = p4d_offset(pgdp, ea);
 		if (p4d_none(*p4dp)) {
-			pmdp = early_alloc_pgtable(PMD_TABLE_SIZE);
+			pudp = early_alloc_pgtable(PUD_TABLE_SIZE);
-			p4d_populate(&init_mm, p4dp, pmdp);
+			p4d_populate(&init_mm, p4dp, pudp);
 		}
 		pudp = pud_offset(p4dp, ea);
 		if (pud_none(*pudp)) {
@@ -105,7 +105,7 @@ int __ref map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot)
 		}
 		pmdp = pmd_offset(pudp, ea);
 		if (!pmd_present(*pmdp)) {
-			ptep = early_alloc_pgtable(PAGE_SIZE);
+			ptep = early_alloc_pgtable(PTE_TABLE_SIZE);
 			pmd_populate_kernel(&init_mm, pmdp, ptep);
 		}
 		ptep = pte_offset_kernel(pmdp, ea);

arch/s390/Kconfig

@@ -507,7 +507,6 @@ config KEXEC
 config KEXEC_FILE
 	bool "kexec file based system call"
 	select KEXEC_CORE
-	select BUILD_BIN2C
 	depends on CRYPTO
 	depends on CRYPTO_SHA256
 	depends on CRYPTO_SHA256_S390

arch/s390/crypto/arch_random.c

@@ -2,126 +2,17 @@
 /*
  * s390 arch random implementation.
  *
- * Copyright IBM Corp. 2017, 2018
+ * Copyright IBM Corp. 2017, 2020
  * Author(s): Harald Freudenberger
- *
- * The s390_arch_random_generate() function may be called from random.c
- * in interrupt context. So this implementation does the best to be very
- * fast. There is a buffer of random data which is asynchronously checked
- * and filled by a workqueue thread.
- * If there are enough bytes in the buffer the s390_arch_random_generate()
- * just delivers these bytes. Otherwise false is returned until the
- * worker thread refills the buffer.
- * The worker fills the rng buffer by pulling fresh entropy from the
- * high quality (but slow) true hardware random generator. This entropy
- * is then spread over the buffer with an pseudo random generator PRNG.
- * As the arch_get_random_seed_long() fetches 8 bytes and the calling
- * function add_interrupt_randomness() counts this as 1 bit entropy the
- * distribution needs to make sure there is in fact 1 bit entropy contained
- * in 8 bytes of the buffer. The current values pull 32 byte entropy
- * and scatter this into a 2048 byte buffer. So 8 byte in the buffer
- * will contain 1 bit of entropy.
- * The worker thread is rescheduled based on the charge level of the
- * buffer but at least with 500 ms delay to avoid too much CPU consumption.
- * So the max. amount of rng data delivered via arch_get_random_seed is
- * limited to 4k bytes per second.
  */
 
 #include <linux/kernel.h>
 #include <linux/atomic.h>
 #include <linux/random.h>
-#include <linux/slab.h>
 #include <linux/static_key.h>
-#include <linux/workqueue.h>
 #include <asm/cpacf.h>
 
 DEFINE_STATIC_KEY_FALSE(s390_arch_random_available);
 
 atomic64_t s390_arch_random_counter = ATOMIC64_INIT(0);
 EXPORT_SYMBOL(s390_arch_random_counter);
-
-#define ARCH_REFILL_TICKS (HZ/2)
-#define ARCH_PRNG_SEED_SIZE 32
-#define ARCH_RNG_BUF_SIZE 2048
-
-static DEFINE_SPINLOCK(arch_rng_lock);
-static u8 *arch_rng_buf;
-static unsigned int arch_rng_buf_idx;
-
-static void arch_rng_refill_buffer(struct work_struct *);
-static DECLARE_DELAYED_WORK(arch_rng_work, arch_rng_refill_buffer);
-
-bool s390_arch_random_generate(u8 *buf, unsigned int nbytes)
-{
-	/* max hunk is ARCH_RNG_BUF_SIZE */
-	if (nbytes > ARCH_RNG_BUF_SIZE)
-		return false;
-
-	/* lock rng buffer */
-	if (!spin_trylock(&arch_rng_lock))
-		return false;
-
-	/* try to resolve the requested amount of bytes from the buffer */
-	arch_rng_buf_idx -= nbytes;
-	if (arch_rng_buf_idx < ARCH_RNG_BUF_SIZE) {
-		memcpy(buf, arch_rng_buf + arch_rng_buf_idx, nbytes);
-		atomic64_add(nbytes, &s390_arch_random_counter);
-		spin_unlock(&arch_rng_lock);
-		return true;
-	}
-
-	/* not enough bytes in rng buffer, refill is done asynchronously */
-	spin_unlock(&arch_rng_lock);
-
-	return false;
-}
-EXPORT_SYMBOL(s390_arch_random_generate);
-
-static void arch_rng_refill_buffer(struct work_struct *unused)
-{
-	unsigned int delay = ARCH_REFILL_TICKS;
-
-	spin_lock(&arch_rng_lock);
-	if (arch_rng_buf_idx > ARCH_RNG_BUF_SIZE) {
-		/* buffer is exhausted and needs refill */
-		u8 seed[ARCH_PRNG_SEED_SIZE];
-		u8 prng_wa[240];
-		/* fetch ARCH_PRNG_SEED_SIZE bytes of entropy */
-		cpacf_trng(NULL, 0, seed, sizeof(seed));
-		/* blow this entropy up to ARCH_RNG_BUF_SIZE with PRNG */
-		memset(prng_wa, 0, sizeof(prng_wa));
-		cpacf_prno(CPACF_PRNO_SHA512_DRNG_SEED,
-			   &prng_wa, NULL, 0, seed, sizeof(seed));
-		cpacf_prno(CPACF_PRNO_SHA512_DRNG_GEN,
-			   &prng_wa, arch_rng_buf, ARCH_RNG_BUF_SIZE, NULL, 0);
-		arch_rng_buf_idx = ARCH_RNG_BUF_SIZE;
-	}
-	delay += (ARCH_REFILL_TICKS * arch_rng_buf_idx) / ARCH_RNG_BUF_SIZE;
-	spin_unlock(&arch_rng_lock);
-
-	/* kick next check */
-	queue_delayed_work(system_long_wq, &arch_rng_work, delay);
-}
-
-static int __init s390_arch_random_init(void)
-{
-	/* all the needed PRNO subfunctions available ? */
-	if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG) &&
-	    cpacf_query_func(CPACF_PRNO, CPACF_PRNO_SHA512_DRNG_GEN)) {
-
-		/* alloc arch random working buffer */
-		arch_rng_buf = kmalloc(ARCH_RNG_BUF_SIZE, GFP_KERNEL);
-		if (!arch_rng_buf)
-			return -ENOMEM;
-
-		/* kick worker queue job to fill the random buffer */
-		queue_delayed_work(system_long_wq,
-				   &arch_rng_work, ARCH_REFILL_TICKS);
-
-		/* enable arch random to the outside world */
-		static_branch_enable(&s390_arch_random_available);
-	}
-
-	return 0;
-}
-arch_initcall(s390_arch_random_init);

arch/s390/include/asm/archrandom.h

@@ -2,7 +2,7 @@
 /*
  * Kernel interface for the s390 arch_random_* functions
  *
- * Copyright IBM Corp. 2017
+ * Copyright IBM Corp. 2017, 2020
  *
  * Author: Harald Freudenberger <freude@de.ibm.com>
  *
@@ -15,12 +15,11 @@
 
 #include <linux/static_key.h>
 #include <linux/atomic.h>
+#include <asm/cpacf.h>
 
 DECLARE_STATIC_KEY_FALSE(s390_arch_random_available);
 extern atomic64_t s390_arch_random_counter;
 
-bool s390_arch_random_generate(u8 *buf, unsigned int nbytes);
-
 static inline bool __must_check arch_get_random_long(unsigned long *v)
 {
 	return false;
@@ -34,7 +33,9 @@ static inline bool __must_check arch_get_random_int(unsigned int *v)
 static inline bool __must_check arch_get_random_seed_long(unsigned long *v)
 {
 	if (static_branch_likely(&s390_arch_random_available)) {
-		return s390_arch_random_generate((u8 *)v, sizeof(*v));
+		cpacf_trng(NULL, 0, (u8 *)v, sizeof(*v));
+		atomic64_add(sizeof(*v), &s390_arch_random_counter);
+		return true;
 	}
 	return false;
 }
@@ -42,7 +43,9 @@ static inline bool __must_check arch_get_random_seed_long(unsigned long *v)
 static inline bool __must_check arch_get_random_seed_int(unsigned int *v)
 {
 	if (static_branch_likely(&s390_arch_random_available)) {
-		return s390_arch_random_generate((u8 *)v, sizeof(*v));
+		cpacf_trng(NULL, 0, (u8 *)v, sizeof(*v));
+		atomic64_add(sizeof(*v), &s390_arch_random_counter);
+		return true;
 	}
 	return false;
 }

arch/s390/kernel/setup.c

@@ -1009,6 +1009,11 @@ static void __init setup_randomness(void)
 	if (stsi(vmms, 3, 2, 2) == 0 && vmms->count)
 		add_device_randomness(&vmms->vm, sizeof(vmms->vm[0]) * vmms->count);
 	memblock_free((unsigned long) vmms, PAGE_SIZE);
+
+#ifdef CONFIG_ARCH_RANDOM
+	if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG))
+		static_branch_enable(&s390_arch_random_available);
+#endif
 }
 
 /*

drivers/block/xen-blkfront.c

@@ -151,6 +151,10 @@ static unsigned int xen_blkif_max_ring_order;
 module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, 0444);
 MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the shared ring");
 
+static bool __read_mostly xen_blkif_trusted = true;
+module_param_named(trusted, xen_blkif_trusted, bool, 0644);
+MODULE_PARM_DESC(trusted, "Is the backend trusted");
+
 #define BLK_RING_SIZE(info)	\
 	__CONST_RING_SIZE(blkif, XEN_PAGE_SIZE * (info)->nr_ring_pages)
 
@@ -208,6 +212,7 @@ struct blkfront_info
 	unsigned int feature_discard:1;
 	unsigned int feature_secdiscard:1;
 	unsigned int feature_persistent:1;
+	unsigned int bounce:1;
 	unsigned int discard_granularity;
 	unsigned int discard_alignment;
 	/* Number of 4KB segments handled */
@@ -310,8 +315,8 @@ static int fill_grant_buffer(struct blkfront_ring_info *rinfo, int num)
 		if (!gnt_list_entry)
 			goto out_of_memory;
 
-		if (info->feature_persistent) {
+		if (info->bounce) {
-			granted_page = alloc_page(GFP_NOIO);
+			granted_page = alloc_page(GFP_NOIO | __GFP_ZERO);
 			if (!granted_page) {
 				kfree(gnt_list_entry);
 				goto out_of_memory;
@@ -330,7 +335,7 @@ out_of_memory:
 	list_for_each_entry_safe(gnt_list_entry, n,
 	                         &rinfo->grants, node) {
 		list_del(&gnt_list_entry->node);
-		if (info->feature_persistent)
+		if (info->bounce)
 			__free_page(gnt_list_entry->page);
 		kfree(gnt_list_entry);
 		i--;
@@ -376,7 +381,7 @@ static struct grant *get_grant(grant_ref_t *gref_head,
 	/* Assign a gref to this page */
 	gnt_list_entry->gref = gnttab_claim_grant_reference(gref_head);
 	BUG_ON(gnt_list_entry->gref == -ENOSPC);
-	if (info->feature_persistent)
+	if (info->bounce)
 		grant_foreign_access(gnt_list_entry, info);
 	else {
 		/* Grant access to the GFN passed by the caller */
@@ -400,7 +405,7 @@ static struct grant *get_indirect_grant(grant_ref_t *gref_head,
 	/* Assign a gref to this page */
 	gnt_list_entry->gref = gnttab_claim_grant_reference(gref_head);
 	BUG_ON(gnt_list_entry->gref == -ENOSPC);
-	if (!info->feature_persistent) {
+	if (!info->bounce) {
 		struct page *indirect_page;
 
 		/* Fetch a pre-allocated page to use for indirect grefs */
@@ -715,7 +720,7 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri
 		.grant_idx = 0,
 		.segments = NULL,
 		.rinfo = rinfo,
-		.need_copy = rq_data_dir(req) && info->feature_persistent,
+		.need_copy = rq_data_dir(req) && info->bounce,
 	};
 
 	/*
@@ -1035,11 +1040,12 @@ static void xlvbd_flush(struct blkfront_info *info)
 {
 	blk_queue_write_cache(info->rq, info->feature_flush ? true : false,
 			      info->feature_fua ? true : false);
-	pr_info("blkfront: %s: %s %s %s %s %s\n",
+	pr_info("blkfront: %s: %s %s %s %s %s %s %s\n",
 		info->gd->disk_name, flush_info(info),
 		"persistent grants:", info->feature_persistent ?
 		"enabled;" : "disabled;", "indirect descriptors:",
-		info->max_indirect_segments ? "enabled;" : "disabled;");
+		info->max_indirect_segments ? "enabled;" : "disabled;",
+		"bounce buffer:", info->bounce ? "enabled" : "disabled;");
 }
 
 static int xen_translate_vdev(int vdevice, int *minor, unsigned int *offset)
@@ -1273,7 +1279,7 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo)
 	if (!list_empty(&rinfo->indirect_pages)) {
 		struct page *indirect_page, *n;
 
-		BUG_ON(info->feature_persistent);
+		BUG_ON(info->bounce);
 		list_for_each_entry_safe(indirect_page, n, &rinfo->indirect_pages, lru) {
 			list_del(&indirect_page->lru);
 			__free_page(indirect_page);
@@ -1290,7 +1296,7 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo)
 							  0, 0UL);
 				rinfo->persistent_gnts_c--;
 			}
-			if (info->feature_persistent)
+			if (info->bounce)
 				__free_page(persistent_gnt->page);
 			kfree(persistent_gnt);
 		}
@@ -1311,7 +1317,7 @@ static void blkif_free_ring(struct blkfront_ring_info *rinfo)
 		for (j = 0; j < segs; j++) {
 			persistent_gnt = rinfo->shadow[i].grants_used[j];
 			gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
-			if (info->feature_persistent)
+			if (info->bounce)
 				__free_page(persistent_gnt->page);
 			kfree(persistent_gnt);
 		}
@@ -1501,7 +1507,7 @@ static int blkif_completion(unsigned long *id,
 	data.s = s;
 	num_sg = s->num_sg;
 
-	if (bret->operation == BLKIF_OP_READ && info->feature_persistent) {
+	if (bret->operation == BLKIF_OP_READ && info->bounce) {
 		for_each_sg(s->sg, sg, num_sg, i) {
 			BUG_ON(sg->offset + sg->length > PAGE_SIZE);
 
@@ -1560,7 +1566,7 @@ static int blkif_completion(unsigned long *id,
 				 * Add the used indirect page back to the list of
 				 * available pages for indirect grefs.
 				 */
-				if (!info->feature_persistent) {
+				if (!info->bounce) {
 					indirect_page = s->indirect_grants[i]->page;
 					list_add(&indirect_page->lru, &rinfo->indirect_pages);
 				}
@@ -1753,7 +1759,7 @@ static int setup_blkring(struct xenbus_device *dev,
 	for (i = 0; i < info->nr_ring_pages; i++)
 		rinfo->ring_ref[i] = GRANT_INVALID_REF;
 
-	sring = alloc_pages_exact(ring_size, GFP_NOIO);
+	sring = alloc_pages_exact(ring_size, GFP_NOIO | __GFP_ZERO);
 	if (!sring) {
 		xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring");
 		return -ENOMEM;
@@ -1857,6 +1863,10 @@ static int talk_to_blkback(struct xenbus_device *dev,
 	if (!info)
 		return -ENODEV;
 
+	/* Check if backend is trusted. */
+	info->bounce = !xen_blkif_trusted ||
+		       !xenbus_read_unsigned(dev->nodename, "trusted", 1);
+
 	max_page_order = xenbus_read_unsigned(info->xbdev->otherend,
 					      "max-ring-page-order", 0);
 	ring_page_order = min(xen_blkif_max_ring_order, max_page_order);
@@ -2283,17 +2293,18 @@ static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo)
 	if (err)
 		goto out_of_memory;
 
-	if (!info->feature_persistent && info->max_indirect_segments) {
+	if (!info->bounce && info->max_indirect_segments) {
 		/*
-		 * We are using indirect descriptors but not persistent
+		 * We are using indirect descriptors but don't have a bounce
-		 * grants, we need to allocate a set of pages that can be
+		 * buffer, we need to allocate a set of pages that can be
 		 * used for mapping indirect grefs
 		 */
 		int num = INDIRECT_GREFS(grants) * BLK_RING_SIZE(info);
 
 		BUG_ON(!list_empty(&rinfo->indirect_pages));
 		for (i = 0; i < num; i++) {
-			struct page *indirect_page = alloc_page(GFP_KERNEL);
+			struct page *indirect_page = alloc_page(GFP_KERNEL |
+			                                        __GFP_ZERO);
 			if (!indirect_page)
 				goto out_of_memory;
 			list_add(&indirect_page->lru, &rinfo->indirect_pages);
@@ -2386,6 +2397,8 @@ static void blkfront_gather_backend_features(struct blkfront_info *info)
 		info->feature_persistent =
 			!!xenbus_read_unsigned(info->xbdev->otherend,
 					       "feature-persistent", 0);
+	if (info->feature_persistent)
+		info->bounce = true;
 
 	indirect_segments = xenbus_read_unsigned(info->xbdev->otherend,
 					"feature-max-indirect-segments", 0);
@@ -2759,6 +2772,13 @@ static void blkfront_delay_work(struct work_struct *work)
 	struct blkfront_info *info;
 	bool need_schedule_work = false;
 
+	/*
+	 * Note that when using bounce buffers but not persistent grants
+	 * there's no need to run blkfront_delay_work because grants are
+	 * revoked in blkif_completion or else an error is reported and the
+	 * connection is closed.
+	 */
+
 	mutex_lock(&blkfront_mutex);
 
 	list_for_each_entry(info, &info_list, info_list) {

drivers/clocksource/timer-ixp4xx.c

@@ -258,7 +258,6 @@ void __init ixp4xx_timer_setup(resource_size_t timerbase,
 	}
 	ixp4xx_timer_register(base, timer_irq, timer_freq);
 }
-EXPORT_SYMBOL_GPL(ixp4xx_timer_setup);
 
 #ifdef CONFIG_OF
 static __init int ixp4xx_of_timer_init(struct device_node *np)

drivers/cpufreq/qoriq-cpufreq.c

@@ -275,6 +275,7 @@ static int qoriq_cpufreq_probe(struct platform_device *pdev)
 
 	np = of_find_matching_node(NULL, qoriq_cpufreq_blacklist);
 	if (np) {
+		of_node_put(np);
 		dev_info(&pdev->dev, "Disabling due to erratum A-008083");
 		return -ENODEV;
 	}

drivers/devfreq/event/exynos-ppmu.c

@@ -514,15 +514,19 @@ static int of_get_devfreq_events(struct device_node *np,
 
 	count = of_get_child_count(events_np);
 	desc = devm_kcalloc(dev, count, sizeof(*desc), GFP_KERNEL);
-	if (!desc)
+	if (!desc) {
+		of_node_put(events_np);
 		return -ENOMEM;
+	}
 	info->num_events = count;
 
 	of_id = of_match_device(exynos_ppmu_id_match, dev);
 	if (of_id)
 		info->ppmu_type = (enum exynos_ppmu_type)of_id->data;
-	else
+	else {
+		of_node_put(events_np);
 		return -EINVAL;
+	}
 
 	j = 0;
 	for_each_child_of_node(events_np, node) {

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c

@@ -689,7 +689,8 @@ int amdgpu_amdkfd_flush_gpu_tlb_pasid(struct kgd_dev *kgd, uint16_t pasid)
 	const uint32_t flush_type = 0;
 	bool all_hub = false;
 
-	if (adev->family == AMDGPU_FAMILY_AI)
+	if (adev->family == AMDGPU_FAMILY_AI ||
+	    adev->family == AMDGPU_FAMILY_RV)
 		all_hub = true;
 
 	return amdgpu_gmc_flush_gpu_tlb_pasid(adev, pasid, flush_type, all_hub);

drivers/hwmon/ibmaem.c

@@ -550,7 +550,7 @@ static int aem_init_aem1_inst(struct aem_ipmi_data *probe, u8 module_handle)
 
 	res = platform_device_add(data->pdev);
 	if (res)
-		goto ipmi_err;
+		goto dev_add_err;
 
 	platform_set_drvdata(data->pdev, data);
 
@@ -598,7 +598,9 @@ hwmon_reg_err:
 	ipmi_destroy_user(data->ipmi.user);
 ipmi_err:
 	platform_set_drvdata(data->pdev, NULL);
-	platform_device_unregister(data->pdev);
+	platform_device_del(data->pdev);
+dev_add_err:
+	platform_device_put(data->pdev);
 dev_err:
 	ida_simple_remove(&aem_ida, data->id);
 id_err:
@@ -690,7 +692,7 @@ static int aem_init_aem2_inst(struct aem_ipmi_data *probe,
 
 	res = platform_device_add(data->pdev);
 	if (res)
-		goto ipmi_err;
+		goto dev_add_err;
 
 	platform_set_drvdata(data->pdev, data);
 
@@ -738,7 +740,9 @@ hwmon_reg_err:
 	ipmi_destroy_user(data->ipmi.user);
 ipmi_err:
 	platform_set_drvdata(data->pdev, NULL);
-	platform_device_unregister(data->pdev);
+	platform_device_del(data->pdev);
+dev_add_err:
+	platform_device_put(data->pdev);
 dev_err:
 	ida_simple_remove(&aem_ida, data->id);
 id_err:

drivers/infiniband/core/cm.c

@@ -1280,8 +1280,10 @@ struct ib_cm_id *ib_cm_insert_listen(struct ib_device *device,
 		return ERR_CAST(cm_id_priv);
 
 	err = cm_init_listen(cm_id_priv, service_id, 0);
-	if (err)
+	if (err) {
+		ib_destroy_cm_id(&cm_id_priv->id);
 		return ERR_PTR(err);
+	}
 
 	spin_lock_irq(&cm_id_priv->lock);
 	listen_id_priv = cm_insert_listen(cm_id_priv, cm_handler);

drivers/infiniband/hw/qedr/qedr.h

@@ -418,6 +418,7 @@ struct qedr_qp {
 	u32 sq_psn;
 	u32 qkey;
 	u32 dest_qp_num;
+	u8 timeout;
 
 	/* Relevant to qps created from kernel space only (ULPs) */
 	u8 prev_wqe_size;

drivers/infiniband/hw/qedr/verbs.c

@@ -2622,6 +2622,8 @@ int qedr_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 					1 << max_t(int, attr->timeout - 8, 0);
 		else
 			qp_params.ack_timeout = 0;
+
+		qp->timeout = attr->timeout;
 	}
 
 	if (attr_mask & IB_QP_RETRY_CNT) {
@@ -2781,7 +2783,7 @@ int qedr_query_qp(struct ib_qp *ibqp,
 	rdma_ah_set_dgid_raw(&qp_attr->ah_attr, &params.dgid.bytes[0]);
 	rdma_ah_set_port_num(&qp_attr->ah_attr, 1);
 	rdma_ah_set_sl(&qp_attr->ah_attr, 0);
-	qp_attr->timeout = params.timeout;
+	qp_attr->timeout = qp->timeout;
 	qp_attr->rnr_retry = params.rnr_retry;
 	qp_attr->retry_cnt = params.retry_cnt;
 	qp_attr->min_rnr_timer = params.min_rnr_nak_timer;

drivers/md/dm-raid.c

@@ -1002,12 +1002,13 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size)
 static int validate_raid_redundancy(struct raid_set *rs)
 {
 	unsigned int i, rebuild_cnt = 0;
-	unsigned int rebuilds_per_group = 0, copies;
+	unsigned int rebuilds_per_group = 0, copies, raid_disks;
 	unsigned int group_size, last_group_start;
 
-	for (i = 0; i < rs->md.raid_disks; i++)
+	for (i = 0; i < rs->raid_disks; i++)
-		if (!test_bit(In_sync, &rs->dev[i].rdev.flags) ||
+		if (!test_bit(FirstUse, &rs->dev[i].rdev.flags) &&
-		    !rs->dev[i].rdev.sb_page)
+		    ((!test_bit(In_sync, &rs->dev[i].rdev.flags) ||
+		      !rs->dev[i].rdev.sb_page)))
 			rebuild_cnt++;
 
 	switch (rs->md.level) {
@@ -1047,8 +1048,9 @@ static int validate_raid_redundancy(struct raid_set *rs)
 		 *	    A	 A    B	   B	C
 		 *	    C	 D    D	   E	E
 		 */
+		raid_disks = min(rs->raid_disks, rs->md.raid_disks);
 		if (__is_raid10_near(rs->md.new_layout)) {
-			for (i = 0; i < rs->md.raid_disks; i++) {
+			for (i = 0; i < raid_disks; i++) {
 				if (!(i % copies))
 					rebuilds_per_group = 0;
 				if ((!rs->dev[i].rdev.sb_page ||
@@ -1071,10 +1073,10 @@ static int validate_raid_redundancy(struct raid_set *rs)
 		 * results in the need to treat the last (potentially larger)
 		 * set differently.
 		 */
-		group_size = (rs->md.raid_disks / copies);
+		group_size = (raid_disks / copies);
-		last_group_start = (rs->md.raid_disks / group_size) - 1;
+		last_group_start = (raid_disks / group_size) - 1;
 		last_group_start *= group_size;
-		for (i = 0; i < rs->md.raid_disks; i++) {
+		for (i = 0; i < raid_disks; i++) {
 			if (!(i % copies) && !(i > last_group_start))
 				rebuilds_per_group = 0;
 			if ((!rs->dev[i].rdev.sb_page ||
@@ -1589,7 +1591,7 @@ static sector_t __rdev_sectors(struct raid_set *rs)
 {
 	int i;
 
-	for (i = 0; i < rs->md.raid_disks; i++) {
+	for (i = 0; i < rs->raid_disks; i++) {
 		struct md_rdev *rdev = &rs->dev[i].rdev;
 
 		if (!test_bit(Journal, &rdev->flags) &&
@@ -3732,13 +3734,13 @@ static int raid_iterate_devices(struct dm_target *ti,
 	unsigned int i;
 	int r = 0;
 
-	for (i = 0; !r && i < rs->md.raid_disks; i++)
+	for (i = 0; !r && i < rs->raid_disks; i++) {
-		if (rs->dev[i].data_dev)
+		if (rs->dev[i].data_dev) {
-			r = fn(ti,
+			r = fn(ti, rs->dev[i].data_dev,
-				 rs->dev[i].data_dev,
+			       0, /* No offset on data devs */
-				 0, /* No offset on data devs */
+			       rs->md.dev_sectors, data);
-				 rs->md.dev_sectors,
+		}
-				 data);
+	}
 
 	return r;
 }

drivers/md/raid5.c

@@ -8003,6 +8003,7 @@ static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	 */
 	if (rdev->saved_raid_disk >= 0 &&
 	    rdev->saved_raid_disk >= first &&
+	    rdev->saved_raid_disk <= last &&
 	    conf->disks[rdev->saved_raid_disk].rdev == NULL)
 		first = rdev->saved_raid_disk;
 

drivers/net/bonding/bond_3ad.c

@@ -2209,7 +2209,8 @@ void bond_3ad_unbind_slave(struct slave *slave)
 				temp_aggregator->num_of_ports--;
 				if (__agg_active_ports(temp_aggregator) == 0) {
 					select_new_active_agg = temp_aggregator->is_active;
-					ad_clear_agg(temp_aggregator);
+					if (temp_aggregator->num_of_ports == 0)
+						ad_clear_agg(temp_aggregator);
 					if (select_new_active_agg) {
 						slave_info(bond->dev, slave->dev, "Removing an active aggregator\n");
 						/* select new active aggregator */

drivers/net/bonding/bond_alb.c

@@ -1279,12 +1279,12 @@ int bond_alb_initialize(struct bonding *bond, int rlb_enabled)
 		return res;
 
 	if (rlb_enabled) {
-		bond->alb_info.rlb_enabled = 1;
 		res = rlb_initialize(bond);
 		if (res) {
 			tlb_deinitialize(bond);
 			return res;
 		}
+		bond->alb_info.rlb_enabled = 1;
 	} else {
 		bond->alb_info.rlb_enabled = 0;
 	}

drivers/net/caif/caif_virtio.c

@@ -723,13 +723,21 @@ static int cfv_probe(struct virtio_device *vdev)
 	/* Carrier is off until netdevice is opened */
 	netif_carrier_off(netdev);
 
+	/* serialize netdev register + virtio_device_ready() with ndo_open() */
+	rtnl_lock();
+
 	/* register Netdev */
-	err = register_netdev(netdev);
+	err = register_netdevice(netdev);
 	if (err) {
+		rtnl_unlock();
 		dev_err(&vdev->dev, "Unable to register netdev (%d)\n", err);
 		goto err;
 	}
 
+	virtio_device_ready(vdev);
+
+	rtnl_unlock();
+
 	debugfs_init(cfv);
 
 	return 0;

drivers/net/dsa/bcm_sf2.c

@@ -774,6 +774,11 @@ static void bcm_sf2_sw_mac_link_up(struct dsa_switch *ds, int port,
 		if (duplex == DUPLEX_FULL)
 			reg |= DUPLX_MODE;
 
+		if (tx_pause)
+			reg |= TXFLOW_CNTL;
+		if (rx_pause)
+			reg |= RXFLOW_CNTL;
+
 		core_writel(priv, reg, offset);
 	}
 

drivers/net/ethernet/smsc/epic100.c

@@ -1513,14 +1513,14 @@ static void epic_remove_one(struct pci_dev *pdev)
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct epic_private *ep = netdev_priv(dev);
 
+	unregister_netdev(dev);
 	dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE, ep->tx_ring,
 			  ep->tx_ring_dma);
 	dma_free_coherent(&pdev->dev, RX_TOTAL_SIZE, ep->rx_ring,
 			  ep->rx_ring_dma);
-	unregister_netdev(dev);
 	pci_iounmap(pdev, ep->ioaddr);
-	pci_release_regions(pdev);
 	free_netdev(dev);
+	pci_release_regions(pdev);
 	pci_disable_device(pdev);
 	/* pci_power_off(pdev, -1); */
 }

drivers/net/phy/dp83822.c

@@ -243,9 +243,7 @@ static int dp83822_config_intr(struct phy_device *phydev)
 		if (misr_status < 0)
 			return misr_status;
 
-		misr_status |= (DP83822_RX_ERR_HF_INT_EN |
+		misr_status |= (DP83822_LINK_STAT_INT_EN |
-				DP83822_FALSE_CARRIER_HF_INT_EN |
-				DP83822_LINK_STAT_INT_EN |
 				DP83822_ENERGY_DET_INT_EN |
 				DP83822_LINK_QUAL_INT_EN);
 

drivers/net/tun.c

@@ -279,6 +279,12 @@ static void tun_napi_init(struct tun_struct *tun, struct tun_file *tfile,
 	}
 }
 
+static void tun_napi_enable(struct tun_file *tfile)
+{
+	if (tfile->napi_enabled)
+		napi_enable(&tfile->napi);
+}
+
 static void tun_napi_disable(struct tun_file *tfile)
 {
 	if (tfile->napi_enabled)
@@ -640,7 +646,8 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 	tun = rtnl_dereference(tfile->tun);
 
 	if (tun && clean) {
-		tun_napi_disable(tfile);
+		if (!tfile->detached)
+			tun_napi_disable(tfile);
 		tun_napi_del(tfile);
 	}
 
@@ -659,8 +666,10 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 		if (clean) {
 			RCU_INIT_POINTER(tfile->tun, NULL);
 			sock_put(&tfile->sk);
-		} else
+		} else {
 			tun_disable_queue(tun, tfile);
+			tun_napi_disable(tfile);
+		}
 
 		synchronize_net();
 		tun_flow_delete_by_queue(tun, tun->numqueues + 1);
@@ -733,6 +742,7 @@ static void tun_detach_all(struct net_device *dev)
 		sock_put(&tfile->sk);
 	}
 	list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) {
+		tun_napi_del(tfile);
 		tun_enable_queue(tfile);
 		tun_queue_purge(tfile);
 		xdp_rxq_info_unreg(&tfile->xdp_rxq);
@@ -813,6 +823,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
 
 	if (tfile->detached) {
 		tun_enable_queue(tfile);
+		tun_napi_enable(tfile);
 	} else {
 		sock_hold(&tfile->sk);
 		tun_napi_init(tun, tfile, napi, napi_frags);

drivers/net/usb/ax88179_178a.c

@@ -1471,6 +1471,42 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 	 * are bundled into this buffer and where we can find an array of
 	 * per-packet metadata (which contains elements encoded into u16).
 	 */
+
+	/* SKB contents for current firmware:
+	 *   <packet 1> <padding>
+	 *   ...
+	 *   <packet N> <padding>
+	 *   <per-packet metadata entry 1> <dummy header>
+	 *   ...
+	 *   <per-packet metadata entry N> <dummy header>
+	 *   <padding2> <rx_hdr>
+	 *
+	 * where:
+	 *   <packet N> contains pkt_len bytes:
+	 *		2 bytes of IP alignment pseudo header
+	 *		packet received
+	 *   <per-packet metadata entry N> contains 4 bytes:
+	 *		pkt_len and fields AX_RXHDR_*
+	 *   <padding>	0-7 bytes to terminate at
+	 *		8 bytes boundary (64-bit).
+	 *   <padding2> 4 bytes to make rx_hdr terminate at
+	 *		8 bytes boundary (64-bit)
+	 *   <dummy-header> contains 4 bytes:
+	 *		pkt_len=0 and AX_RXHDR_DROP_ERR
+	 *   <rx-hdr>	contains 4 bytes:
+	 *		pkt_cnt and hdr_off (offset of
+	 *		  <per-packet metadata entry 1>)
+	 *
+	 * pkt_cnt is number of entrys in the per-packet metadata.
+	 * In current firmware there is 2 entrys per packet.
+	 * The first points to the packet and the
+	 *  second is a dummy header.
+	 * This was done probably to align fields in 64-bit and
+	 *  maintain compatibility with old firmware.
+	 * This code assumes that <dummy header> and <padding2> are
+	 *  optional.
+	 */
+
 	if (skb->len < 4)
 		return 0;
 	skb_trim(skb, skb->len - 4);
@@ -1484,51 +1520,66 @@ static int ax88179_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 	/* Make sure that the bounds of the metadata array are inside the SKB
 	 * (and in front of the counter at the end).
 	 */
-	if (pkt_cnt * 2 + hdr_off > skb->len)
+	if (pkt_cnt * 4 + hdr_off > skb->len)
 		return 0;
 	pkt_hdr = (u32 *)(skb->data + hdr_off);
 
 	/* Packets must not overlap the metadata array */
 	skb_trim(skb, hdr_off);
 
-	for (; ; pkt_cnt--, pkt_hdr++) {
+	for (; pkt_cnt > 0; pkt_cnt--, pkt_hdr++) {
+		u16 pkt_len_plus_padd;
 		u16 pkt_len;
 
 		le32_to_cpus(pkt_hdr);
 		pkt_len = (*pkt_hdr >> 16) & 0x1fff;
+		pkt_len_plus_padd = (pkt_len + 7) & 0xfff8;
 
-		if (pkt_len > skb->len)
+		/* Skip dummy header used for alignment
+		 */
+		if (pkt_len == 0)
+			continue;
+
+		if (pkt_len_plus_padd > skb->len)
 			return 0;
 
 		/* Check CRC or runt packet */
-		if (((*pkt_hdr & (AX_RXHDR_CRC_ERR | AX_RXHDR_DROP_ERR)) == 0) &&
+		if ((*pkt_hdr & (AX_RXHDR_CRC_ERR | AX_RXHDR_DROP_ERR)) ||
-		    pkt_len >= 2 + ETH_HLEN) {
+		    pkt_len < 2 + ETH_HLEN) {
-			bool last = (pkt_cnt == 0);
+			dev->net->stats.rx_errors++;
-
+			skb_pull(skb, pkt_len_plus_padd);
-			if (last) {
+			continue;
-				ax_skb = skb;
-			} else {
-				ax_skb = skb_clone(skb, GFP_ATOMIC);
-				if (!ax_skb)
-					return 0;
-			}
-			ax_skb->len = pkt_len;
-			/* Skip IP alignment pseudo header */
-			skb_pull(ax_skb, 2);
-			skb_set_tail_pointer(ax_skb, ax_skb->len);
-			ax_skb->truesize = pkt_len + sizeof(struct sk_buff);
-			ax88179_rx_checksum(ax_skb, pkt_hdr);
-
-			if (last)
-				return 1;
-
-			usbnet_skb_return(dev, ax_skb);
 		}
 
-		/* Trim this packet away from the SKB */
+		/* last packet */
-		if (!skb_pull(skb, (pkt_len + 7) & 0xFFF8))
+		if (pkt_len_plus_padd == skb->len) {
+			skb_trim(skb, pkt_len);
+
+			/* Skip IP alignment pseudo header */
+			skb_pull(skb, 2);
+
+			skb->truesize = SKB_TRUESIZE(pkt_len_plus_padd);
+			ax88179_rx_checksum(skb, pkt_hdr);
+			return 1;
+		}
+
+		ax_skb = skb_clone(skb, GFP_ATOMIC);
+		if (!ax_skb)
 			return 0;
+		skb_trim(ax_skb, pkt_len);
+
+		/* Skip IP alignment pseudo header */
+		skb_pull(ax_skb, 2);
+
+		skb->truesize = pkt_len_plus_padd +
+				SKB_DATA_ALIGN(sizeof(struct sk_buff));
+		ax88179_rx_checksum(ax_skb, pkt_hdr);
+		usbnet_skb_return(dev, ax_skb);
+
+		skb_pull(skb, pkt_len_plus_padd);
 	}
+
+	return 0;
 }
 
 static struct sk_buff *

drivers/net/usb/qmi_wwan.c

@@ -1293,6 +1293,8 @@ static const struct usb_device_id products[] = {
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1031, 3)}, /* Telit LE910C1-EUX */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)},	/* Telit LE922A */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)},	/* Telit FN980 */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1060, 2)},	/* Telit LN920 */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1070, 2)},	/* Telit FN990 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1100, 3)},	/* Telit ME910 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1101, 3)},	/* Telit ME910 dual modem */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */

drivers/net/usb/usbnet.c

@@ -1969,7 +1969,7 @@ static int __usbnet_read_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
 		   cmd, reqtype, value, index, size);
 
 	if (size) {
-		buf = kmalloc(size, GFP_KERNEL);
+		buf = kmalloc(size, GFP_NOIO);
 		if (!buf)
 			goto out;
 	}
@@ -2001,7 +2001,7 @@ static int __usbnet_write_cmd(struct usbnet *dev, u8 cmd, u8 reqtype,
 		   cmd, reqtype, value, index, size);
 
 	if (data) {
-		buf = kmemdup(data, size, GFP_KERNEL);
+		buf = kmemdup(data, size, GFP_NOIO);
 		if (!buf)
 			goto out;
 	} else {

drivers/net/virtio_net.c

@@ -3174,14 +3174,20 @@ static int virtnet_probe(struct virtio_device *vdev)
 		}
 	}
 
-	err = register_netdev(dev);
+	/* serialize netdev register + virtio_device_ready() with ndo_open() */
+	rtnl_lock();
+
+	err = register_netdevice(dev);
 	if (err) {
 		pr_debug("virtio_net: registering device failed\n");
+		rtnl_unlock();
 		goto free_failover;
 	}
 
 	virtio_device_ready(vdev);
 
+	rtnl_unlock();
+
 	err = virtnet_cpu_notif_add(vi);
 	if (err) {
 		pr_debug("virtio_net: registering cpu notifier failed\n");

drivers/net/xen-netfront.c

@@ -66,6 +66,10 @@ module_param_named(max_queues, xennet_max_queues, uint, 0644);
 MODULE_PARM_DESC(max_queues,
 		 "Maximum number of queues per virtual interface");
 
+static bool __read_mostly xennet_trusted = true;
+module_param_named(trusted, xennet_trusted, bool, 0644);
+MODULE_PARM_DESC(trusted, "Is the backend trusted");
+
 #define XENNET_TIMEOUT  (5 * HZ)
 
 static const struct ethtool_ops xennet_ethtool_ops;
@@ -175,6 +179,9 @@ struct netfront_info {
 	/* Is device behaving sane? */
 	bool broken;
 
+	/* Should skbs be bounced into a zeroed buffer? */
+	bool bounce;
+
 	atomic_t rx_gso_checksum_fixup;
 };
 
@@ -273,7 +280,8 @@ static struct sk_buff *xennet_alloc_one_rx_buffer(struct netfront_queue *queue)
 	if (unlikely(!skb))
 		return NULL;
 
-	page = page_pool_dev_alloc_pages(queue->page_pool);
+	page = page_pool_alloc_pages(queue->page_pool,
+				     GFP_ATOMIC | __GFP_NOWARN | __GFP_ZERO);
 	if (unlikely(!page)) {
 		kfree_skb(skb);
 		return NULL;
@@ -669,6 +677,33 @@ static int xennet_xdp_xmit(struct net_device *dev, int n,
 	return n - drops;
 }
 
+struct sk_buff *bounce_skb(const struct sk_buff *skb)
+{
+	unsigned int headerlen = skb_headroom(skb);
+	/* Align size to allocate full pages and avoid contiguous data leaks */
+	unsigned int size = ALIGN(skb_end_offset(skb) + skb->data_len,
+				  XEN_PAGE_SIZE);
+	struct sk_buff *n = alloc_skb(size, GFP_ATOMIC | __GFP_ZERO);
+
+	if (!n)
+		return NULL;
+
+	if (!IS_ALIGNED((uintptr_t)n->head, XEN_PAGE_SIZE)) {
+		WARN_ONCE(1, "misaligned skb allocated\n");
+		kfree_skb(n);
+		return NULL;
+	}
+
+	/* Set the data pointer */
+	skb_reserve(n, headerlen);
+	/* Set the tail pointer and length */
+	skb_put(n, skb->len);
+
+	BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len));
+
+	skb_copy_header(n, skb);
+	return n;
+}
 
 #define MAX_XEN_SKB_FRAGS (65536 / XEN_PAGE_SIZE + 1)
 
@@ -722,9 +757,13 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev
 
 	/* The first req should be at least ETH_HLEN size or the packet will be
 	 * dropped by netback.
+	 *
+	 * If the backend is not trusted bounce all data to zeroed pages to
+	 * avoid exposing contiguous data on the granted page not belonging to
+	 * the skb.
 	 */
-	if (unlikely(PAGE_SIZE - offset < ETH_HLEN)) {
+	if (np->bounce || unlikely(PAGE_SIZE - offset < ETH_HLEN)) {
-		nskb = skb_copy(skb, GFP_ATOMIC);
+		nskb = bounce_skb(skb);
 		if (!nskb)
 			goto drop;
 		dev_consume_skb_any(skb);
@@ -1057,8 +1096,10 @@ static int xennet_get_responses(struct netfront_queue *queue,
 			}
 		}
 		rcu_read_unlock();
-next:
+
 		__skb_queue_tail(list, skb);
+
+next:
 		if (!(rx->flags & XEN_NETRXF_more_data))
 			break;
 
@@ -2248,6 +2289,10 @@ static int talk_to_netback(struct xenbus_device *dev,
 
 	info->netdev->irq = 0;
 
+	/* Check if backend is trusted. */
+	info->bounce = !xennet_trusted ||
+		       !xenbus_read_unsigned(dev->nodename, "trusted", 1);
+
 	/* Check if backend supports multiple queues */
 	max_queues = xenbus_read_unsigned(info->xbdev->otherend,
 					  "multi-queue-max-queues", 1);
@@ -2414,6 +2459,9 @@ static int xennet_connect(struct net_device *dev)
 		return err;
 	if (np->netback_has_xdp_headroom)
 		pr_info("backend supports XDP headroom\n");
+	if (np->bounce)
+		dev_info(&np->xbdev->dev,
+			 "bouncing transmitted data to zeroed pages\n");
 
 	/* talk_to_netback() sets the correct number of queues */
 	num_queues = dev->real_num_tx_queues;

drivers/nfc/nfcmrvl/i2c.c

@@ -186,9 +186,9 @@ static int nfcmrvl_i2c_parse_dt(struct device_node *node,
 		pdata->irq_polarity = IRQF_TRIGGER_RISING;
 
 	ret = irq_of_parse_and_map(node, 0);
-	if (ret < 0) {
+	if (!ret) {
-		pr_err("Unable to get irq, error: %d\n", ret);
+		pr_err("Unable to get irq\n");
-		return ret;
+		return -EINVAL;
 	}
 	pdata->irq = ret;
 

drivers/nfc/nfcmrvl/spi.c

@@ -129,9 +129,9 @@ static int nfcmrvl_spi_parse_dt(struct device_node *node,
 	}
 
 	ret = irq_of_parse_and_map(node, 0);
-	if (ret < 0) {
+	if (!ret) {
-		pr_err("Unable to get irq, error: %d\n", ret);
+		pr_err("Unable to get irq\n");
-		return ret;
+		return -EINVAL;
 	}
 	pdata->irq = ret;
 

drivers/nfc/nxp-nci/i2c.c

@@ -162,6 +162,9 @@ static int nxp_nci_i2c_nci_read(struct nxp_nci_i2c_phy *phy,
 
 	skb_put_data(*skb, (void *)&header, NCI_CTRL_HDR_SIZE);
 
+	if (!header.plen)
+		return 0;
+
 	r = i2c_master_recv(client, skb_put(*skb, header.plen), header.plen);
 	if (r != header.plen) {
 		nfc_err(&client->dev,

drivers/nvdimm/bus.c

@@ -187,8 +187,8 @@ static int nvdimm_clear_badblocks_region(struct device *dev, void *data)
 	ndr_end = nd_region->ndr_start + nd_region->ndr_size - 1;
 
 	/* make sure we are in the region */
-	if (ctx->phys < nd_region->ndr_start
+	if (ctx->phys < nd_region->ndr_start ||
-			|| (ctx->phys + ctx->cleared) > ndr_end)
+	    (ctx->phys + ctx->cleared - 1) > ndr_end)
 		return 0;
 
 	sector = (ctx->phys - nd_region->ndr_start) / 512;

drivers/nvme/host/pci.c

@@ -3245,7 +3245,8 @@ static const struct pci_device_id nvme_id_table[] = {
 	{ PCI_DEVICE(0x1d1d, 0x2601),	/* CNEX Granby */
 		.driver_data = NVME_QUIRK_LIGHTNVM, },
 	{ PCI_DEVICE(0x10ec, 0x5762),   /* ADATA SX6000LNP */
-		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },
+		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN |
+				NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1cc1, 0x8201),   /* ADATA SX8200PNP 512GB */
 		.driver_data = NVME_QUIRK_NO_DEEPEST_PS |
 				NVME_QUIRK_IGNORE_DEV_SUBNQN, },

drivers/xen/gntdev-common.h

@@ -16,6 +16,7 @@
 #include <linux/mmu_notifier.h>
 #include <linux/types.h>
 #include <xen/interface/event_channel.h>
+#include <xen/grant_table.h>
 
 struct gntdev_dmabuf_priv;
 
@@ -56,6 +57,7 @@ struct gntdev_grant_map {
 	struct gnttab_unmap_grant_ref *unmap_ops;
 	struct gnttab_map_grant_ref   *kmap_ops;
 	struct gnttab_unmap_grant_ref *kunmap_ops;
+	bool *being_removed;
 	struct page **pages;
 	unsigned long pages_vm_start;
 
@@ -73,6 +75,11 @@ struct gntdev_grant_map {
 	/* Needed to avoid allocation in gnttab_dma_free_pages(). */
 	xen_pfn_t *frames;
 #endif
+
+	/* Number of live grants */
+	atomic_t live_grants;
+	/* Needed to avoid allocation in __unmap_grant_pages */
+	struct gntab_unmap_queue_data unmap_data;
 };
 
 struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,

drivers/xen/gntdev.c

@@ -35,6 +35,7 @@
 #include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/refcount.h>
+#include <linux/workqueue.h>
 
 #include <xen/xen.h>
 #include <xen/grant_table.h>
@@ -60,10 +61,11 @@ module_param(limit, uint, 0644);
 MODULE_PARM_DESC(limit,
 	"Maximum number of grants that may be mapped by one mapping request");
 
+/* True in PV mode, false otherwise */
 static int use_ptemod;
 
-static int unmap_grant_pages(struct gntdev_grant_map *map,
+static void unmap_grant_pages(struct gntdev_grant_map *map,
-			     int offset, int pages);
+			      int offset, int pages);
 
 static struct miscdevice gntdev_miscdev;
 
@@ -120,6 +122,7 @@ static void gntdev_free_map(struct gntdev_grant_map *map)
 	kvfree(map->unmap_ops);
 	kvfree(map->kmap_ops);
 	kvfree(map->kunmap_ops);
+	kvfree(map->being_removed);
 	kfree(map);
 }
 
@@ -140,12 +143,15 @@ struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
 	add->kunmap_ops = kvcalloc(count,
 				   sizeof(add->kunmap_ops[0]), GFP_KERNEL);
 	add->pages     = kvcalloc(count, sizeof(add->pages[0]), GFP_KERNEL);
+	add->being_removed =
+		kvcalloc(count, sizeof(add->being_removed[0]), GFP_KERNEL);
 	if (NULL == add->grants    ||
 	    NULL == add->map_ops   ||
 	    NULL == add->unmap_ops ||
 	    NULL == add->kmap_ops  ||
 	    NULL == add->kunmap_ops ||
-	    NULL == add->pages)
+	    NULL == add->pages     ||
+	    NULL == add->being_removed)
 		goto err;
 
 #ifdef CONFIG_XEN_GRANT_DMA_ALLOC
@@ -240,9 +246,36 @@ void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map)
 	if (!refcount_dec_and_test(&map->users))
 		return;
 
-	if (map->pages && !use_ptemod)
+	if (map->pages && !use_ptemod) {
+		/*
+		 * Increment the reference count.  This ensures that the
+		 * subsequent call to unmap_grant_pages() will not wind up
+		 * re-entering itself.  It *can* wind up calling
+		 * gntdev_put_map() recursively, but such calls will be with a
+		 * reference count greater than 1, so they will return before
+		 * this code is reached.  The recursion depth is thus limited to
+		 * 1.  Do NOT use refcount_inc() here, as it will detect that
+		 * the reference count is zero and WARN().
+		 */
+		refcount_set(&map->users, 1);
+
+		/*
+		 * Unmap the grants.  This may or may not be asynchronous, so it
+		 * is possible that the reference count is 1 on return, but it
+		 * could also be greater than 1.
+		 */
 		unmap_grant_pages(map, 0, map->count);
 
+		/* Check if the memory now needs to be freed */
+		if (!refcount_dec_and_test(&map->users))
+			return;
+
+		/*
+		 * All pages have been returned to the hypervisor, so free the
+		 * map.
+		 */
+	}
+
 	if (map->notify.flags & UNMAP_NOTIFY_SEND_EVENT) {
 		notify_remote_via_evtchn(map->notify.event);
 		evtchn_put(map->notify.event);
@@ -288,6 +321,7 @@ static int set_grant_ptes_as_special(pte_t *pte, unsigned long addr, void *data)
 
 int gntdev_map_grant_pages(struct gntdev_grant_map *map)
 {
+	size_t alloced = 0;
 	int i, err = 0;
 
 	if (!use_ptemod) {
@@ -336,87 +370,109 @@ int gntdev_map_grant_pages(struct gntdev_grant_map *map)
 			map->pages, map->count);
 
 	for (i = 0; i < map->count; i++) {
-		if (map->map_ops[i].status == GNTST_okay)
+		if (map->map_ops[i].status == GNTST_okay) {
 			map->unmap_ops[i].handle = map->map_ops[i].handle;
-		else if (!err)
+			if (!use_ptemod)
+				alloced++;
+		} else if (!err)
 			err = -EINVAL;
 
 		if (map->flags & GNTMAP_device_map)
 			map->unmap_ops[i].dev_bus_addr = map->map_ops[i].dev_bus_addr;
 
 		if (use_ptemod) {
-			if (map->kmap_ops[i].status == GNTST_okay)
+			if (map->kmap_ops[i].status == GNTST_okay) {
+				if (map->map_ops[i].status == GNTST_okay)
+					alloced++;
 				map->kunmap_ops[i].handle = map->kmap_ops[i].handle;
-			else if (!err)
+			} else if (!err)
 				err = -EINVAL;
 		}
 	}
+	atomic_add(alloced, &map->live_grants);
 	return err;
 }
 
-static int __unmap_grant_pages(struct gntdev_grant_map *map, int offset,
+static void __unmap_grant_pages_done(int result,
-			       int pages)
+		struct gntab_unmap_queue_data *data)
 {
-	int i, err = 0;
+	unsigned int i;
-	struct gntab_unmap_queue_data unmap_data;
+	struct gntdev_grant_map *map = data->data;
+	unsigned int offset = data->unmap_ops - map->unmap_ops;
 
-	if (map->notify.flags & UNMAP_NOTIFY_CLEAR_BYTE) {
+	for (i = 0; i < data->count; i++) {
-		int pgno = (map->notify.addr >> PAGE_SHIFT);
+		WARN_ON(map->unmap_ops[offset+i].status);
-		if (pgno >= offset && pgno < offset + pages) {
-			/* No need for kmap, pages are in lowmem */
-			uint8_t *tmp = pfn_to_kaddr(page_to_pfn(map->pages[pgno]));
-			tmp[map->notify.addr & (PAGE_SIZE-1)] = 0;
-			map->notify.flags &= ~UNMAP_NOTIFY_CLEAR_BYTE;
-		}
-	}
-
-	unmap_data.unmap_ops = map->unmap_ops + offset;
-	unmap_data.kunmap_ops = use_ptemod ? map->kunmap_ops + offset : NULL;
-	unmap_data.pages = map->pages + offset;
-	unmap_data.count = pages;
-
-	err = gnttab_unmap_refs_sync(&unmap_data);
-	if (err)
-		return err;
-
-	for (i = 0; i < pages; i++) {
-		if (map->unmap_ops[offset+i].status)
-			err = -EINVAL;
 		pr_debug("unmap handle=%d st=%d\n",
 			map->unmap_ops[offset+i].handle,
 			map->unmap_ops[offset+i].status);
 		map->unmap_ops[offset+i].handle = -1;
 	}
-	return err;
+	/*
+	 * Decrease the live-grant counter.  This must happen after the loop to
+	 * prevent premature reuse of the grants by gnttab_mmap().
+	 */
+	atomic_sub(data->count, &map->live_grants);
+
+	/* Release reference taken by __unmap_grant_pages */
+	gntdev_put_map(NULL, map);
 }
 
-static int unmap_grant_pages(struct gntdev_grant_map *map, int offset,
+static void __unmap_grant_pages(struct gntdev_grant_map *map, int offset,
-			     int pages)
+			       int pages)
 {
-	int range, err = 0;
+	if (map->notify.flags & UNMAP_NOTIFY_CLEAR_BYTE) {
+		int pgno = (map->notify.addr >> PAGE_SHIFT);
+
+		if (pgno >= offset && pgno < offset + pages) {
+			/* No need for kmap, pages are in lowmem */
+			uint8_t *tmp = pfn_to_kaddr(page_to_pfn(map->pages[pgno]));
+
+			tmp[map->notify.addr & (PAGE_SIZE-1)] = 0;
+			map->notify.flags &= ~UNMAP_NOTIFY_CLEAR_BYTE;
+		}
+	}
+
+	map->unmap_data.unmap_ops = map->unmap_ops + offset;
+	map->unmap_data.kunmap_ops = use_ptemod ? map->kunmap_ops + offset : NULL;
+	map->unmap_data.pages = map->pages + offset;
+	map->unmap_data.count = pages;
+	map->unmap_data.done = __unmap_grant_pages_done;
+	map->unmap_data.data = map;
+	refcount_inc(&map->users); /* to keep map alive during async call below */
+
+	gnttab_unmap_refs_async(&map->unmap_data);
+}
+
+static void unmap_grant_pages(struct gntdev_grant_map *map, int offset,
+			      int pages)
+{
+	int range;
+
+	if (atomic_read(&map->live_grants) == 0)
+		return; /* Nothing to do */
 
 	pr_debug("unmap %d+%d [%d+%d]\n", map->index, map->count, offset, pages);
 
 	/* It is possible the requested range will have a "hole" where we
 	 * already unmapped some of the grants. Only unmap valid ranges.
 	 */
-	while (pages && !err) {
+	while (pages) {
-		while (pages && map->unmap_ops[offset].handle == -1) {
+		while (pages && map->being_removed[offset]) {
 			offset++;
 			pages--;
 		}
 		range = 0;
 		while (range < pages) {
-			if (map->unmap_ops[offset+range].handle == -1)
+			if (map->being_removed[offset + range])
 				break;
+			map->being_removed[offset + range] = true;
 			range++;
 		}
-		err = __unmap_grant_pages(map, offset, range);
+		if (range)
+			__unmap_grant_pages(map, offset, range);
 		offset += range;
 		pages -= range;
 	}
-
-	return err;
 }
 
 /* ------------------------------------------------------------------ */
@@ -468,7 +524,6 @@ static bool gntdev_invalidate(struct mmu_interval_notifier *mn,
 	struct gntdev_grant_map *map =
 		container_of(mn, struct gntdev_grant_map, notifier);
 	unsigned long mstart, mend;
-	int err;
 
 	if (!mmu_notifier_range_blockable(range))
 		return false;
@@ -489,10 +544,9 @@ static bool gntdev_invalidate(struct mmu_interval_notifier *mn,
 			map->index, map->count,
 			map->vma->vm_start, map->vma->vm_end,
 			range->start, range->end, mstart, mend);
-	err = unmap_grant_pages(map,
+	unmap_grant_pages(map,
 				(mstart - map->vma->vm_start) >> PAGE_SHIFT,
 				(mend - mstart) >> PAGE_SHIFT);
-	WARN_ON(err);
 
 	return true;
 }
@@ -980,6 +1034,10 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 		goto unlock_out;
 	if (use_ptemod && map->vma)
 		goto unlock_out;
+	if (atomic_read(&map->live_grants)) {
+		err = -EAGAIN;
+		goto unlock_out;
+	}
 	refcount_inc(&map->users);
 
 	vma->vm_ops = &gntdev_vmops;

fs/io_uring.c

@@ -4366,6 +4366,8 @@ static int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 
 	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
 		return -EINVAL;
+	if (unlikely(sqe->addr2 || sqe->splice_fd_in || sqe->ioprio))
+		return -EINVAL;
 
 	sr->msg_flags = READ_ONCE(sqe->msg_flags);
 	sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));
@@ -4601,6 +4603,8 @@ static int io_recvmsg_prep(struct io_kiocb *req,
 
 	if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
 		return -EINVAL;
+	if (unlikely(sqe->addr2 || sqe->splice_fd_in || sqe->ioprio))
+		return -EINVAL;
 
 	sr->msg_flags = READ_ONCE(sqe->msg_flags);
 	sr->umsg = u64_to_user_ptr(READ_ONCE(sqe->addr));

fs/iomap/buffered-io.c

@@ -1459,13 +1459,6 @@ iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data)
 			PF_MEMALLOC))
 		goto redirty;
 
-	/*
-	 * Given that we do not allow direct reclaim to call us, we should
-	 * never be called in a recursive filesystem reclaim context.
-	 */
-	if (WARN_ON_ONCE(current->flags & PF_MEMALLOC_NOFS))
-		goto redirty;
-
 	/*
 	 * Is this page beyond the end of the file?
 	 *

fs/nfsd/vfs.c

@@ -1156,6 +1156,7 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
 						nfsd_net_id));
 			err2 = filemap_check_wb_err(nf->nf_file->f_mapping,
 						    since);
+			err = nfserrno(err2);
 			break;
 		case -EINVAL:
 			err = nfserr_notsupp;
@@ -1163,8 +1164,8 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		default:
 			nfsd_reset_boot_verifier(net_generic(nf->nf_net,
 						 nfsd_net_id));
+			err = nfserrno(err2);
 		}
-		err = nfserrno(err2);
 	} else
 		nfsd_copy_boot_verifier(verf, net_generic(nf->nf_net,
 					nfsd_net_id));

fs/xfs/libxfs/xfs_btree.c

@@ -2811,7 +2811,7 @@ xfs_btree_split_worker(
 	struct xfs_btree_split_args	*args = container_of(work,
 						struct xfs_btree_split_args, work);
 	unsigned long		pflags;
-	unsigned long		new_pflags = PF_MEMALLOC_NOFS;
+	unsigned long		new_pflags = 0;
 
 	/*
 	 * we are in a transaction context here, but may also be doing work
@@ -2823,12 +2823,20 @@ xfs_btree_split_worker(
 		new_pflags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
 
 	current_set_flags_nested(&pflags, new_pflags);
+	xfs_trans_set_context(args->cur->bc_tp);
 
 	args->result = __xfs_btree_split(args->cur, args->level, args->ptrp,
 					 args->key, args->curp, args->stat);
+
+	xfs_trans_clear_context(args->cur->bc_tp);
+	current_restore_flags_nested(&pflags, new_pflags);
+
+	/*
+	 * Do not access args after complete() has run here. We don't own args
+	 * and the owner may run and free args before we return here.
+	 */
 	complete(args->done);
 
-	current_restore_flags_nested(&pflags, new_pflags);
 }
 
 /*

fs/xfs/libxfs/xfs_sb.c

@@ -956,9 +956,19 @@ xfs_log_sb(
 	struct xfs_mount	*mp = tp->t_mountp;
 	struct xfs_buf		*bp = xfs_trans_getsb(tp);
 
-	mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount);
+	/*
-	mp->m_sb.sb_ifree = percpu_counter_sum(&mp->m_ifree);
+	 * Lazy sb counters don't update the in-core superblock so do that now.
-	mp->m_sb.sb_fdblocks = percpu_counter_sum(&mp->m_fdblocks);
+	 * If this is at unmount, the counters will be exactly correct, but at
+	 * any other time they will only be ballpark correct because of
+	 * reservations that have been taken out percpu counters. If we have an
+	 * unclean shutdown, this will be corrected by log recovery rebuilding
+	 * the counters from the AGF block counts.
+	 */
+	if (xfs_sb_version_haslazysbcount(&mp->m_sb)) {
+		mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount);
+		mp->m_sb.sb_ifree = percpu_counter_sum(&mp->m_ifree);
+		mp->m_sb.sb_fdblocks = percpu_counter_sum(&mp->m_fdblocks);
+	}
 
 	xfs_sb_to_disk(bp->b_addr, &mp->m_sb);
 	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF);

fs/xfs/xfs_aops.c

@@ -62,7 +62,7 @@ xfs_setfilesize_trans_alloc(
 	 * We hand off the transaction to the completion thread now, so
 	 * clear the flag here.
 	 */
-	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
+	xfs_trans_clear_context(tp);
 	return 0;
 }
 
@@ -125,7 +125,7 @@ xfs_setfilesize_ioend(
 	 * thus we need to mark ourselves as being in a transaction manually.
 	 * Similarly for freeze protection.
 	 */
-	current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
+	xfs_trans_set_context(tp);
 	__sb_writers_acquired(VFS_I(ip)->i_sb, SB_FREEZE_FS);
 
 	/* we abort the update if there was an IO error */
@@ -577,6 +577,12 @@ xfs_vm_writepage(
 {
 	struct xfs_writepage_ctx wpc = { };
 
+	if (WARN_ON_ONCE(current->journal_info)) {
+		redirty_page_for_writepage(wbc, page);
+		unlock_page(page);
+		return 0;
+	}
+
 	return iomap_writepage(page, wbc, &wpc.ctx, &xfs_writeback_ops);
 }
 
@@ -587,6 +593,13 @@ xfs_vm_writepages(
 {
 	struct xfs_writepage_ctx wpc = { };
 
+	/*
+	 * Writing back data in a transaction context can result in recursive
+	 * transactions. This is bad, so issue a warning and get out of here.
+	 */
+	if (WARN_ON_ONCE(current->journal_info))
+		return 0;
+
 	xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
 	return iomap_writepages(mapping, wbc, &wpc.ctx, &xfs_writeback_ops);
 }

fs/xfs/xfs_error.c

@@ -293,6 +293,8 @@ xfs_errortag_add(
 	struct xfs_mount	*mp,
 	unsigned int		error_tag)
 {
+	BUILD_BUG_ON(ARRAY_SIZE(xfs_errortag_random_default) != XFS_ERRTAG_MAX);
+
 	if (error_tag >= XFS_ERRTAG_MAX)
 		return -EINVAL;
 

fs/xfs/xfs_reflink.c

@@ -1503,7 +1503,8 @@ xfs_reflink_unshare(
 	if (error)
 		goto out;
 
-	error = filemap_write_and_wait_range(inode->i_mapping, offset, len);
+	error = filemap_write_and_wait_range(inode->i_mapping, offset,
+			offset + len - 1);
 	if (error)
 		goto out;
 

fs/xfs/xfs_super.c

@@ -1155,6 +1155,22 @@ suffix_kstrtoint(
 	return ret;
 }
 
+static inline void
+xfs_fs_warn_deprecated(
+	struct fs_context	*fc,
+	struct fs_parameter	*param,
+	uint64_t		flag,
+	bool			value)
+{
+	/* Don't print the warning if reconfiguring and current mount point
+	 * already had the flag set
+	 */
+	if ((fc->purpose & FS_CONTEXT_FOR_RECONFIGURE) &&
+			!!(XFS_M(fc->root->d_sb)->m_flags & flag) == value)
+		return;
+	xfs_warn(fc->s_fs_info, "%s mount option is deprecated.", param->key);
+}
+
 /*
  * Set mount state from a mount option.
  *
@@ -1165,7 +1181,7 @@ xfs_fc_parse_param(
 	struct fs_context	*fc,
 	struct fs_parameter	*param)
 {
-	struct xfs_mount	*mp = fc->s_fs_info;
+	struct xfs_mount	*parsing_mp = fc->s_fs_info;
 	struct fs_parse_result	result;
 	int			size = 0;
 	int			opt;
@@ -1176,142 +1192,142 @@ xfs_fc_parse_param(
 
 	switch (opt) {
 	case Opt_logbufs:
-		mp->m_logbufs = result.uint_32;
+		parsing_mp->m_logbufs = result.uint_32;
 		return 0;
 	case Opt_logbsize:
-		if (suffix_kstrtoint(param->string, 10, &mp->m_logbsize))
+		if (suffix_kstrtoint(param->string, 10, &parsing_mp->m_logbsize))
 			return -EINVAL;
 		return 0;
 	case Opt_logdev:
-		kfree(mp->m_logname);
+		kfree(parsing_mp->m_logname);
-		mp->m_logname = kstrdup(param->string, GFP_KERNEL);
+		parsing_mp->m_logname = kstrdup(param->string, GFP_KERNEL);
-		if (!mp->m_logname)
+		if (!parsing_mp->m_logname)
 			return -ENOMEM;
 		return 0;
 	case Opt_rtdev:
-		kfree(mp->m_rtname);
+		kfree(parsing_mp->m_rtname);
-		mp->m_rtname = kstrdup(param->string, GFP_KERNEL);
+		parsing_mp->m_rtname = kstrdup(param->string, GFP_KERNEL);
-		if (!mp->m_rtname)
+		if (!parsing_mp->m_rtname)
 			return -ENOMEM;
 		return 0;
 	case Opt_allocsize:
 		if (suffix_kstrtoint(param->string, 10, &size))
 			return -EINVAL;
-		mp->m_allocsize_log = ffs(size) - 1;
+		parsing_mp->m_allocsize_log = ffs(size) - 1;
-		mp->m_flags |= XFS_MOUNT_ALLOCSIZE;
+		parsing_mp->m_flags |= XFS_MOUNT_ALLOCSIZE;
 		return 0;
 	case Opt_grpid:
 	case Opt_bsdgroups:
-		mp->m_flags |= XFS_MOUNT_GRPID;
+		parsing_mp->m_flags |= XFS_MOUNT_GRPID;
 		return 0;
 	case Opt_nogrpid:
 	case Opt_sysvgroups:
-		mp->m_flags &= ~XFS_MOUNT_GRPID;
+		parsing_mp->m_flags &= ~XFS_MOUNT_GRPID;
 		return 0;
 	case Opt_wsync:
-		mp->m_flags |= XFS_MOUNT_WSYNC;
+		parsing_mp->m_flags |= XFS_MOUNT_WSYNC;
 		return 0;
 	case Opt_norecovery:
-		mp->m_flags |= XFS_MOUNT_NORECOVERY;
+		parsing_mp->m_flags |= XFS_MOUNT_NORECOVERY;
 		return 0;
 	case Opt_noalign:
-		mp->m_flags |= XFS_MOUNT_NOALIGN;
+		parsing_mp->m_flags |= XFS_MOUNT_NOALIGN;
 		return 0;
 	case Opt_swalloc:
-		mp->m_flags |= XFS_MOUNT_SWALLOC;
+		parsing_mp->m_flags |= XFS_MOUNT_SWALLOC;
 		return 0;
 	case Opt_sunit:
-		mp->m_dalign = result.uint_32;
+		parsing_mp->m_dalign = result.uint_32;
 		return 0;
 	case Opt_swidth:
-		mp->m_swidth = result.uint_32;
+		parsing_mp->m_swidth = result.uint_32;
 		return 0;
 	case Opt_inode32:
-		mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
+		parsing_mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
 		return 0;
 	case Opt_inode64:
-		mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
+		parsing_mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
 		return 0;
 	case Opt_nouuid:
-		mp->m_flags |= XFS_MOUNT_NOUUID;
+		parsing_mp->m_flags |= XFS_MOUNT_NOUUID;
 		return 0;
 	case Opt_largeio:
-		mp->m_flags |= XFS_MOUNT_LARGEIO;
+		parsing_mp->m_flags |= XFS_MOUNT_LARGEIO;
 		return 0;
 	case Opt_nolargeio:
-		mp->m_flags &= ~XFS_MOUNT_LARGEIO;
+		parsing_mp->m_flags &= ~XFS_MOUNT_LARGEIO;
 		return 0;
 	case Opt_filestreams:
-		mp->m_flags |= XFS_MOUNT_FILESTREAMS;
+		parsing_mp->m_flags |= XFS_MOUNT_FILESTREAMS;
 		return 0;
 	case Opt_noquota:
-		mp->m_qflags &= ~XFS_ALL_QUOTA_ACCT;
+		parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ACCT;
-		mp->m_qflags &= ~XFS_ALL_QUOTA_ENFD;
+		parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ENFD;
-		mp->m_qflags &= ~XFS_ALL_QUOTA_ACTIVE;
+		parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ACTIVE;
 		return 0;
 	case Opt_quota:
 	case Opt_uquota:
 	case Opt_usrquota:
-		mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE |
+		parsing_mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE |
 				 XFS_UQUOTA_ENFD);
 		return 0;
 	case Opt_qnoenforce:
 	case Opt_uqnoenforce:
-		mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE);
+		parsing_mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE);
-		mp->m_qflags &= ~XFS_UQUOTA_ENFD;
+		parsing_mp->m_qflags &= ~XFS_UQUOTA_ENFD;
 		return 0;
 	case Opt_pquota:
 	case Opt_prjquota:
-		mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE |
+		parsing_mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE |
 				 XFS_PQUOTA_ENFD);
 		return 0;
 	case Opt_pqnoenforce:
-		mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
+		parsing_mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
-		mp->m_qflags &= ~XFS_PQUOTA_ENFD;
+		parsing_mp->m_qflags &= ~XFS_PQUOTA_ENFD;
 		return 0;
 	case Opt_gquota:
 	case Opt_grpquota:
-		mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
+		parsing_mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
 				 XFS_GQUOTA_ENFD);
 		return 0;
 	case Opt_gqnoenforce:
-		mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
+		parsing_mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
-		mp->m_qflags &= ~XFS_GQUOTA_ENFD;
+		parsing_mp->m_qflags &= ~XFS_GQUOTA_ENFD;
 		return 0;
 	case Opt_discard:
-		mp->m_flags |= XFS_MOUNT_DISCARD;
+		parsing_mp->m_flags |= XFS_MOUNT_DISCARD;
 		return 0;
 	case Opt_nodiscard:
-		mp->m_flags &= ~XFS_MOUNT_DISCARD;
+		parsing_mp->m_flags &= ~XFS_MOUNT_DISCARD;
 		return 0;
 #ifdef CONFIG_FS_DAX
 	case Opt_dax:
-		xfs_mount_set_dax_mode(mp, XFS_DAX_ALWAYS);
+		xfs_mount_set_dax_mode(parsing_mp, XFS_DAX_ALWAYS);
 		return 0;
 	case Opt_dax_enum:
-		xfs_mount_set_dax_mode(mp, result.uint_32);
+		xfs_mount_set_dax_mode(parsing_mp, result.uint_32);
 		return 0;
 #endif
 	/* Following mount options will be removed in September 2025 */
 	case Opt_ikeep:
-		xfs_warn(mp, "%s mount option is deprecated.", param->key);
+		xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_IKEEP, true);
-		mp->m_flags |= XFS_MOUNT_IKEEP;
+		parsing_mp->m_flags |= XFS_MOUNT_IKEEP;
 		return 0;
 	case Opt_noikeep:
-		xfs_warn(mp, "%s mount option is deprecated.", param->key);
+		xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_IKEEP, false);
-		mp->m_flags &= ~XFS_MOUNT_IKEEP;
+		parsing_mp->m_flags &= ~XFS_MOUNT_IKEEP;
 		return 0;
 	case Opt_attr2:
-		xfs_warn(mp, "%s mount option is deprecated.", param->key);
+		xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_ATTR2, true);
-		mp->m_flags |= XFS_MOUNT_ATTR2;
+		parsing_mp->m_flags |= XFS_MOUNT_ATTR2;
 		return 0;
 	case Opt_noattr2:
-		xfs_warn(mp, "%s mount option is deprecated.", param->key);
+		xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_NOATTR2, true);
-		mp->m_flags &= ~XFS_MOUNT_ATTR2;
+		parsing_mp->m_flags &= ~XFS_MOUNT_ATTR2;
-		mp->m_flags |= XFS_MOUNT_NOATTR2;
+		parsing_mp->m_flags |= XFS_MOUNT_NOATTR2;
 		return 0;
 	default:
-		xfs_warn(mp, "unknown mount option [%s].", param->key);
+		xfs_warn(parsing_mp, "unknown mount option [%s].", param->key);
 		return -EINVAL;
 	}
 
@@ -1918,7 +1934,7 @@ xfs_init_zones(void)
 	if (!xfs_ifork_zone)
 		goto out_destroy_da_state_zone;
 
-	xfs_trans_zone = kmem_cache_create("xf_trans",
+	xfs_trans_zone = kmem_cache_create("xfs_trans",
 					   sizeof(struct xfs_trans),
 					   0, 0, NULL);
 	if (!xfs_trans_zone)

fs/xfs/xfs_trans.c

@@ -68,6 +68,7 @@ xfs_trans_free(
 	xfs_extent_busy_clear(tp->t_mountp, &tp->t_busy, false);
 
 	trace_xfs_trans_free(tp, _RET_IP_);
+	xfs_trans_clear_context(tp);
 	if (!(tp->t_flags & XFS_TRANS_NO_WRITECOUNT))
 		sb_end_intwrite(tp->t_mountp->m_super);
 	xfs_trans_free_dqinfo(tp);
@@ -119,7 +120,8 @@ xfs_trans_dup(
 
 	ntp->t_rtx_res = tp->t_rtx_res - tp->t_rtx_res_used;
 	tp->t_rtx_res = tp->t_rtx_res_used;
-	ntp->t_pflags = tp->t_pflags;
+
+	xfs_trans_switch_context(tp, ntp);
 
 	/* move deferred ops over to the new tp */
 	xfs_defer_move(ntp, tp);
@@ -153,9 +155,6 @@ xfs_trans_reserve(
 	int			error = 0;
 	bool			rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0;
 
-	/* Mark this thread as being in a transaction */
-	current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
-
 	/*
 	 * Attempt to reserve the needed disk blocks by decrementing
 	 * the number needed from the number available.  This will
@@ -163,10 +162,8 @@ xfs_trans_reserve(
 	 */
 	if (blocks > 0) {
 		error = xfs_mod_fdblocks(mp, -((int64_t)blocks), rsvd);
-		if (error != 0) {
+		if (error != 0)
-			current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
 			return -ENOSPC;
-		}
 		tp->t_blk_res += blocks;
 	}
 
@@ -240,9 +237,6 @@ undo_blocks:
 		xfs_mod_fdblocks(mp, (int64_t)blocks, rsvd);
 		tp->t_blk_res = 0;
 	}
-
-	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
-
 	return error;
 }
 
@@ -266,6 +260,7 @@ xfs_trans_alloc(
 	tp = kmem_cache_zalloc(xfs_trans_zone, GFP_KERNEL | __GFP_NOFAIL);
 	if (!(flags & XFS_TRANS_NO_WRITECOUNT))
 		sb_start_intwrite(mp->m_super);
+	xfs_trans_set_context(tp);
 
 	/*
 	 * Zero-reservation ("empty") transactions can't modify anything, so
@@ -620,6 +615,9 @@ xfs_trans_unreserve_and_mod_sb(
 
 	/* apply remaining deltas */
 	spin_lock(&mp->m_sb_lock);
+	mp->m_sb.sb_fdblocks += tp->t_fdblocks_delta + tp->t_res_fdblocks_delta;
+	mp->m_sb.sb_icount += idelta;
+	mp->m_sb.sb_ifree += ifreedelta;
 	mp->m_sb.sb_frextents += rtxdelta;
 	mp->m_sb.sb_dblocks += tp->t_dblocks_delta;
 	mp->m_sb.sb_agcount += tp->t_agcount_delta;
@@ -878,7 +876,6 @@ __xfs_trans_commit(
 
 	xfs_log_commit_cil(mp, tp, &commit_lsn, regrant);
 
-	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
 	xfs_trans_free(tp);
 
 	/*
@@ -910,7 +907,6 @@ out_unreserve:
 			xfs_log_ticket_ungrant(mp->m_log, tp->t_ticket);
 		tp->t_ticket = NULL;
 	}
-	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
 	xfs_trans_free_items(tp, !!error);
 	xfs_trans_free(tp);
 
@@ -970,9 +966,6 @@ xfs_trans_cancel(
 		tp->t_ticket = NULL;
 	}
 
-	/* mark this thread as no longer being in a transaction */
-	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
-
 	xfs_trans_free_items(tp, dirty);
 	xfs_trans_free(tp);
 }

fs/xfs/xfs_trans.h

@@ -268,4 +268,34 @@ xfs_trans_item_relog(
 	return lip->li_ops->iop_relog(lip, tp);
 }
 
+static inline void
+xfs_trans_set_context(
+	struct xfs_trans	*tp)
+{
+	ASSERT(current->journal_info == NULL);
+	tp->t_pflags = memalloc_nofs_save();
+	current->journal_info = tp;
+}
+
+static inline void
+xfs_trans_clear_context(
+	struct xfs_trans	*tp)
+{
+	if (current->journal_info == tp) {
+		memalloc_nofs_restore(tp->t_pflags);
+		current->journal_info = NULL;
+	}
+}
+
+static inline void
+xfs_trans_switch_context(
+	struct xfs_trans	*old_tp,
+	struct xfs_trans	*new_tp)
+{
+	ASSERT(current->journal_info == old_tp);
+	new_tp->t_pflags = old_tp->t_pflags;
+	old_tp->t_pflags = 0;
+	current->journal_info = new_tp;
+}
+
 #endif	/* __XFS_TRANS_H__ */

include/linux/dim.h

@@ -21,7 +21,7 @@
  * We consider 10% difference as significant.
  */
 #define IS_SIGNIFICANT_DIFF(val, ref) \
-	(((100UL * abs((val) - (ref))) / (ref)) > 10)
+	((ref) && (((100UL * abs((val) - (ref))) / (ref)) > 10))
 
 /*
  * Calculate the gap between two values.

net/ipv4/ip_tunnel_core.c

@@ -410,7 +410,7 @@ int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst,
 	u32 mtu = dst_mtu(encap_dst) - headroom;
 
 	if ((skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) ||
-	    (!skb_is_gso(skb) && (skb->len - skb_mac_header_len(skb)) <= mtu))
+	    (!skb_is_gso(skb) && (skb->len - skb_network_offset(skb)) <= mtu))
 		return 0;
 
 	skb_dst_update_pmtu_no_confirm(skb, mtu);

net/ipv4/tcp_ipv4.c

@@ -1980,7 +1980,8 @@ process:
 		struct sock *nsk;
 
 		sk = req->rsk_listener;
-		if (unlikely(tcp_v4_inbound_md5_hash(sk, skb, dif, sdif))) {
+		if (unlikely(!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb) ||
+			     tcp_v4_inbound_md5_hash(sk, skb, dif, sdif))) {
 			sk_drops_add(sk, skb);
 			reqsk_put(req);
 			goto discard_it;
@@ -2019,6 +2020,7 @@ process:
 			}
 			goto discard_and_relse;
 		}
+		nf_reset_ct(skb);
 		if (nsk == sk) {
 			reqsk_put(req);
 			tcp_v4_restore_cb(skb);

net/ipv6/addrconf.c

@@ -1106,10 +1106,6 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg,
 		goto out;
 	}
 
-	if (net->ipv6.devconf_all->disable_policy ||
-	    idev->cnf.disable_policy)
-		f6i->dst_nopolicy = true;
-
 	neigh_parms_data_state_setall(idev->nd_parms);
 
 	ifa->addr = *cfg->pfx;

net/ipv6/route.c

@@ -4436,8 +4436,15 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net,
 	}
 
 	f6i = ip6_route_info_create(&cfg, gfp_flags, NULL);
-	if (!IS_ERR(f6i))
+	if (!IS_ERR(f6i)) {
 		f6i->dst_nocount = true;
+
+		if (!anycast &&
+		    (net->ipv6.devconf_all->disable_policy ||
+		     idev->cnf.disable_policy))
+			f6i->dst_nopolicy = true;
+	}
+
 	return f6i;
 }
 

net/ipv6/seg6_hmac.c

@@ -409,7 +409,6 @@ int __net_init seg6_hmac_net_init(struct net *net)
 
 	return 0;
 }
-EXPORT_SYMBOL(seg6_hmac_net_init);
 
 void seg6_hmac_exit(void)
 {

net/ipv6/sit.c

@@ -321,9 +321,7 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ifreq *ifr)
 		kcalloc(cmax, sizeof(*kp), GFP_KERNEL | __GFP_NOWARN) :
 		NULL;
 
-	rcu_read_lock();
+	ca = min(t->prl_count, cmax);
-
-	ca = t->prl_count < cmax ? t->prl_count : cmax;
 
 	if (!kp) {
 		/* We don't try hard to allocate much memory for
@@ -338,7 +336,7 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ifreq *ifr)
 		}
 	}
 
-	c = 0;
+	rcu_read_lock();
 	for_each_prl_rcu(t->prl) {
 		if (c >= cmax)
 			break;
@@ -350,7 +348,7 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ifreq *ifr)
 		if (kprl.addr != htonl(INADDR_ANY))
 			break;
 	}
-out:
+
 	rcu_read_unlock();
 
 	len = sizeof(*kp) * c;
@@ -359,7 +357,7 @@ out:
 		ret = -EFAULT;
 
 	kfree(kp);
-
+out:
 	return ret;
 }
 

net/netfilter/nft_set_hash.c

@@ -142,6 +142,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key,
 	/* Another cpu may race to insert the element with the same key */
 	if (prev) {
 		nft_set_elem_destroy(set, he, true);
+		atomic_dec(&set->nelems);
 		he = prev;
 	}
 
@@ -151,6 +152,7 @@ out:
 
 err2:
 	nft_set_elem_destroy(set, he, true);
+	atomic_dec(&set->nelems);
 err1:
 	return false;
 }

net/rose/rose_timer.c

@@ -31,89 +31,89 @@ static void rose_idletimer_expiry(struct timer_list *);
 
 void rose_start_heartbeat(struct sock *sk)
 {
-	del_timer(&sk->sk_timer);
+	sk_stop_timer(sk, &sk->sk_timer);
 
 	sk->sk_timer.function = rose_heartbeat_expiry;
 	sk->sk_timer.expires  = jiffies + 5 * HZ;
 
-	add_timer(&sk->sk_timer);
+	sk_reset_timer(sk, &sk->sk_timer, sk->sk_timer.expires);
 }
 
 void rose_start_t1timer(struct sock *sk)
 {
 	struct rose_sock *rose = rose_sk(sk);
 
-	del_timer(&rose->timer);
+	sk_stop_timer(sk, &rose->timer);
 
 	rose->timer.function = rose_timer_expiry;
 	rose->timer.expires  = jiffies + rose->t1;
 
-	add_timer(&rose->timer);
+	sk_reset_timer(sk, &rose->timer, rose->timer.expires);
 }
 
 void rose_start_t2timer(struct sock *sk)
 {
 	struct rose_sock *rose = rose_sk(sk);
 
-	del_timer(&rose->timer);
+	sk_stop_timer(sk, &rose->timer);
 
 	rose->timer.function = rose_timer_expiry;
 	rose->timer.expires  = jiffies + rose->t2;
 
-	add_timer(&rose->timer);
+	sk_reset_timer(sk, &rose->timer, rose->timer.expires);
 }
 
 void rose_start_t3timer(struct sock *sk)
 {
 	struct rose_sock *rose = rose_sk(sk);
 
-	del_timer(&rose->timer);
+	sk_stop_timer(sk, &rose->timer);
 
 	rose->timer.function = rose_timer_expiry;
 	rose->timer.expires  = jiffies + rose->t3;
 
-	add_timer(&rose->timer);
+	sk_reset_timer(sk, &rose->timer, rose->timer.expires);
 }
 
 void rose_start_hbtimer(struct sock *sk)
 {
 	struct rose_sock *rose = rose_sk(sk);
 
-	del_timer(&rose->timer);
+	sk_stop_timer(sk, &rose->timer);
 
 	rose->timer.function = rose_timer_expiry;
 	rose->timer.expires  = jiffies + rose->hb;
 
-	add_timer(&rose->timer);
+	sk_reset_timer(sk, &rose->timer, rose->timer.expires);
 }
 
 void rose_start_idletimer(struct sock *sk)
 {
 	struct rose_sock *rose = rose_sk(sk);
 
-	del_timer(&rose->idletimer);
+	sk_stop_timer(sk, &rose->idletimer);
 
 	if (rose->idle > 0) {
 		rose->idletimer.function = rose_idletimer_expiry;
 		rose->idletimer.expires  = jiffies + rose->idle;
 
-		add_timer(&rose->idletimer);
+		sk_reset_timer(sk, &rose->idletimer, rose->idletimer.expires);
 	}
 }
 
 void rose_stop_heartbeat(struct sock *sk)
 {
-	del_timer(&sk->sk_timer);
+	sk_stop_timer(sk, &sk->sk_timer);
 }
 
 void rose_stop_timer(struct sock *sk)
 {
-	del_timer(&rose_sk(sk)->timer);
+	sk_stop_timer(sk, &rose_sk(sk)->timer);
 }
 
 void rose_stop_idletimer(struct sock *sk)
 {
-	del_timer(&rose_sk(sk)->idletimer);
+	sk_stop_timer(sk, &rose_sk(sk)->idletimer);
 }
 
 static void rose_heartbeat_expiry(struct timer_list *t)
@@ -130,6 +130,7 @@ static void rose_heartbeat_expiry(struct timer_list *t)
 		    (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) {
 			bh_unlock_sock(sk);
 			rose_destroy_socket(sk);
+			sock_put(sk);
 			return;
 		}
 		break;
@@ -152,6 +153,7 @@ static void rose_heartbeat_expiry(struct timer_list *t)
 
 	rose_start_heartbeat(sk);
 	bh_unlock_sock(sk);
+	sock_put(sk);
 }
 
 static void rose_timer_expiry(struct timer_list *t)
@@ -181,6 +183,7 @@ static void rose_timer_expiry(struct timer_list *t)
 		break;
 	}
 	bh_unlock_sock(sk);
+	sock_put(sk);
 }
 
 static void rose_idletimer_expiry(struct timer_list *t)
@@ -205,4 +208,5 @@ static void rose_idletimer_expiry(struct timer_list *t)
 		sock_set_flag(sk, SOCK_DEAD);
 	}
 	bh_unlock_sock(sk);
+	sock_put(sk);
 }

net/sched/act_api.c

@@ -302,7 +302,8 @@ static int tcf_idr_release_unsafe(struct tc_action *p)
 }
 
 static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
-			  const struct tc_action_ops *ops)
+			  const struct tc_action_ops *ops,
+			  struct netlink_ext_ack *extack)
 {
 	struct nlattr *nest;
 	int n_i = 0;
@@ -318,20 +319,25 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
 	if (nla_put_string(skb, TCA_KIND, ops->kind))
 		goto nla_put_failure;
 
+	ret = 0;
 	mutex_lock(&idrinfo->lock);
 	idr_for_each_entry_ul(idr, p, tmp, id) {
 		if (IS_ERR(p))
 			continue;
 		ret = tcf_idr_release_unsafe(p);
-		if (ret == ACT_P_DELETED) {
+		if (ret == ACT_P_DELETED)
 			module_put(ops->owner);
-			n_i++;
+		else if (ret < 0)
-		} else if (ret < 0) {
+			break;
-			mutex_unlock(&idrinfo->lock);
+		n_i++;
-			goto nla_put_failure;
-		}
 	}
 	mutex_unlock(&idrinfo->lock);
+	if (ret < 0) {
+		if (n_i)
+			NL_SET_ERR_MSG(extack, "Unable to flush all TC actions");
+		else
+			goto nla_put_failure;
+	}
 
 	ret = nla_put_u32(skb, TCA_FCNT, n_i);
 	if (ret)
@@ -352,7 +358,7 @@ int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb,
 	struct tcf_idrinfo *idrinfo = tn->idrinfo;
 
 	if (type == RTM_DELACTION) {
-		return tcf_del_walker(idrinfo, skb, ops);
+		return tcf_del_walker(idrinfo, skb, ops, extack);
 	} else if (type == RTM_GETACTION) {
 		return tcf_dump_walker(idrinfo, skb, cb);
 	} else {

net/sunrpc/xdr.c

@@ -752,7 +752,7 @@ static __be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr,
 	 */
 	xdr->p = (void *)p + frag2bytes;
 	space_left = xdr->buf->buflen - xdr->buf->len;
-	if (space_left - nbytes >= PAGE_SIZE)
+	if (space_left - frag1bytes >= PAGE_SIZE)
 		xdr->end = (void *)p + PAGE_SIZE;
 	else
 		xdr->end = (void *)p + space_left - frag1bytes;

net/tipc/node.c

@@ -456,8 +456,8 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u8 *peer_id,
 				   bool preliminary)
 {
 	struct tipc_net *tn = net_generic(net, tipc_net_id);
+	struct tipc_link *l, *snd_l = tipc_bc_sndlink(net);
 	struct tipc_node *n, *temp_node;
-	struct tipc_link *l;
 	unsigned long intv;
 	int bearer_id;
 	int i;
@@ -472,6 +472,16 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u8 *peer_id,
 			goto exit;
 		/* A preliminary node becomes "real" now, refresh its data */
 		tipc_node_write_lock(n);
+		if (!tipc_link_bc_create(net, tipc_own_addr(net), addr, peer_id, U16_MAX,
+					 tipc_link_min_win(snd_l), tipc_link_max_win(snd_l),
+					 n->capabilities, &n->bc_entry.inputq1,
+					 &n->bc_entry.namedq, snd_l, &n->bc_entry.link)) {
+			pr_warn("Broadcast rcv link refresh failed, no memory\n");
+			tipc_node_write_unlock_fast(n);
+			tipc_node_put(n);
+			n = NULL;
+			goto exit;
+		}
 		n->preliminary = false;
 		n->addr = addr;
 		hlist_del_rcu(&n->hash);
@@ -551,7 +561,16 @@ update:
 	n->signature = INVALID_NODE_SIG;
 	n->active_links[0] = INVALID_BEARER_ID;
 	n->active_links[1] = INVALID_BEARER_ID;
-	n->bc_entry.link = NULL;
+	if (!preliminary &&
+	    !tipc_link_bc_create(net, tipc_own_addr(net), addr, peer_id, U16_MAX,
+				 tipc_link_min_win(snd_l), tipc_link_max_win(snd_l),
+				 n->capabilities, &n->bc_entry.inputq1,
+				 &n->bc_entry.namedq, snd_l, &n->bc_entry.link)) {
+		pr_warn("Broadcast rcv link creation failed, no memory\n");
+		kfree(n);
+		n = NULL;
+		goto exit;
+	}
 	tipc_node_get(n);
 	timer_setup(&n->timer, tipc_node_timeout, 0);
 	/* Start a slow timer anyway, crypto needs it */
@@ -1128,7 +1147,7 @@ void tipc_node_check_dest(struct net *net, u32 addr,
 			  bool *respond, bool *dupl_addr)
 {
 	struct tipc_node *n;
-	struct tipc_link *l, *snd_l;
+	struct tipc_link *l;
 	struct tipc_link_entry *le;
 	bool addr_match = false;
 	bool sign_match = false;
@@ -1148,22 +1167,6 @@ void tipc_node_check_dest(struct net *net, u32 addr,
 		return;
 
 	tipc_node_write_lock(n);
-	if (unlikely(!n->bc_entry.link)) {
-		snd_l = tipc_bc_sndlink(net);
-		if (!tipc_link_bc_create(net, tipc_own_addr(net),
-					 addr, peer_id, U16_MAX,
-					 tipc_link_min_win(snd_l),
-					 tipc_link_max_win(snd_l),
-					 n->capabilities,
-					 &n->bc_entry.inputq1,
-					 &n->bc_entry.namedq, snd_l,
-					 &n->bc_entry.link)) {
-			pr_warn("Broadcast rcv link creation failed, no mem\n");
-			tipc_node_write_unlock_fast(n);
-			tipc_node_put(n);
-			return;
-		}
-	}
 
 	le = &n->links[b->identity];
 

tools/testing/selftests/net/udpgso_bench.sh

@@ -120,7 +120,7 @@ run_all() {
 	run_udp "${ipv4_args}"
 
 	echo "ipv6"
-	run_tcp "${ipv4_args}"
+	run_tcp "${ipv6_args}"
 	run_udp "${ipv6_args}"
 }
 

tools/testing/selftests/rseq/Makefile

@@ -6,7 +6,7 @@ endif
 
 CFLAGS += -O2 -Wall -g -I./ -I../../../../usr/include/ -L$(OUTPUT) -Wl,-rpath=./ \
 	  $(CLANG_FLAGS)
-LDLIBS += -lpthread
+LDLIBS += -lpthread -ldl
 
 # Own dependencies because we only want to build against 1st prerequisite, but
 # still track changes to header files and depend on shared object.

tools/testing/selftests/rseq/basic_percpu_ops_test.c

@@ -9,10 +9,9 @@
 #include <string.h>
 #include <stddef.h>
 
+#include "../kselftest.h"
 #include "rseq.h"
 
-#define ARRAY_SIZE(arr)	(sizeof(arr) / sizeof((arr)[0]))
-
 struct percpu_lock_entry {
 	intptr_t v;
 } __attribute__((aligned(128)));
@@ -168,7 +167,7 @@ struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list,
 	for (;;) {
 		struct percpu_list_node *head;
 		intptr_t *targetptr, expectnot, *load;
-		off_t offset;
+		long offset;
 		int ret, cpu;
 
 		cpu = rseq_cpu_start();

tools/testing/selftests/rseq/compiler.h

@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq/compiler.h
+ *
+ * Work-around asm goto compiler bugs.
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifndef RSEQ_COMPILER_H
+#define RSEQ_COMPILER_H
+
+/*
+ * gcc prior to 4.8.2 miscompiles asm goto.
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670
+ *
+ * gcc prior to 8.1.0 miscompiles asm goto at O1.
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103908
+ *
+ * clang prior to version 13.0.1 miscompiles asm goto at O2.
+ * https://github.com/llvm/llvm-project/issues/52735
+ *
+ * Work around these issues by adding a volatile inline asm with
+ * memory clobber in the fallthrough after the asm goto and at each
+ * label target.  Emit this for all compilers in case other similar
+ * issues are found in the future.
+ */
+#define rseq_after_asm_goto()	asm volatile ("" : : : "memory")
+
+#endif  /* RSEQ_COMPILER_H_ */

tools/testing/selftests/rseq/param_test.c

@@ -161,7 +161,7 @@ unsigned int yield_mod_cnt, nr_abort;
 	"	cbnz	" INJECT_ASM_REG ", 222b\n"			\
 	"333:\n"
 
-#elif __PPC__
+#elif defined(__PPC__)
 
 #define RSEQ_INJECT_INPUT \
 	, [loop_cnt_1]"m"(loop_cnt[1]) \
@@ -368,9 +368,7 @@ void *test_percpu_spinlock_thread(void *arg)
 		abort();
 	reps = thread_data->reps;
 	for (i = 0; i < reps; i++) {
-		int cpu = rseq_cpu_start();
+		int cpu = rseq_this_cpu_lock(&data->lock);
-
-		cpu = rseq_this_cpu_lock(&data->lock);
 		data->c[cpu].count++;
 		rseq_percpu_unlock(&data->lock, cpu);
 #ifndef BENCHMARK
@@ -551,7 +549,7 @@ struct percpu_list_node *this_cpu_list_pop(struct percpu_list *list,
 	for (;;) {
 		struct percpu_list_node *head;
 		intptr_t *targetptr, expectnot, *load;
-		off_t offset;
+		long offset;
 		int ret;
 
 		cpu = rseq_cpu_start();

tools/testing/selftests/rseq/rseq-abi.h

@@ -0,0 +1,151 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+#ifndef _RSEQ_ABI_H
+#define _RSEQ_ABI_H
+
+/*
+ * rseq-abi.h
+ *
+ * Restartable sequences system call API
+ *
+ * Copyright (c) 2015-2022 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+enum rseq_abi_cpu_id_state {
+	RSEQ_ABI_CPU_ID_UNINITIALIZED			= -1,
+	RSEQ_ABI_CPU_ID_REGISTRATION_FAILED		= -2,
+};
+
+enum rseq_abi_flags {
+	RSEQ_ABI_FLAG_UNREGISTER = (1 << 0),
+};
+
+enum rseq_abi_cs_flags_bit {
+	RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT	= 0,
+	RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT	= 1,
+	RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT	= 2,
+};
+
+enum rseq_abi_cs_flags {
+	RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT	=
+		(1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT),
+	RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL	=
+		(1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT),
+	RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE	=
+		(1U << RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT),
+};
+
+/*
+ * struct rseq_abi_cs is aligned on 4 * 8 bytes to ensure it is always
+ * contained within a single cache-line. It is usually declared as
+ * link-time constant data.
+ */
+struct rseq_abi_cs {
+	/* Version of this structure. */
+	__u32 version;
+	/* enum rseq_abi_cs_flags */
+	__u32 flags;
+	__u64 start_ip;
+	/* Offset from start_ip. */
+	__u64 post_commit_offset;
+	__u64 abort_ip;
+} __attribute__((aligned(4 * sizeof(__u64))));
+
+/*
+ * struct rseq_abi is aligned on 4 * 8 bytes to ensure it is always
+ * contained within a single cache-line.
+ *
+ * A single struct rseq_abi per thread is allowed.
+ */
+struct rseq_abi {
+	/*
+	 * Restartable sequences cpu_id_start field. Updated by the
+	 * kernel. Read by user-space with single-copy atomicity
+	 * semantics. This field should only be read by the thread which
+	 * registered this data structure. Aligned on 32-bit. Always
+	 * contains a value in the range of possible CPUs, although the
+	 * value may not be the actual current CPU (e.g. if rseq is not
+	 * initialized). This CPU number value should always be compared
+	 * against the value of the cpu_id field before performing a rseq
+	 * commit or returning a value read from a data structure indexed
+	 * using the cpu_id_start value.
+	 */
+	__u32 cpu_id_start;
+	/*
+	 * Restartable sequences cpu_id field. Updated by the kernel.
+	 * Read by user-space with single-copy atomicity semantics. This
+	 * field should only be read by the thread which registered this
+	 * data structure. Aligned on 32-bit. Values
+	 * RSEQ_CPU_ID_UNINITIALIZED and RSEQ_CPU_ID_REGISTRATION_FAILED
+	 * have a special semantic: the former means "rseq uninitialized",
+	 * and latter means "rseq initialization failed". This value is
+	 * meant to be read within rseq critical sections and compared
+	 * with the cpu_id_start value previously read, before performing
+	 * the commit instruction, or read and compared with the
+	 * cpu_id_start value before returning a value loaded from a data
+	 * structure indexed using the cpu_id_start value.
+	 */
+	__u32 cpu_id;
+	/*
+	 * Restartable sequences rseq_cs field.
+	 *
+	 * Contains NULL when no critical section is active for the current
+	 * thread, or holds a pointer to the currently active struct rseq_cs.
+	 *
+	 * Updated by user-space, which sets the address of the currently
+	 * active rseq_cs at the beginning of assembly instruction sequence
+	 * block, and set to NULL by the kernel when it restarts an assembly
+	 * instruction sequence block, as well as when the kernel detects that
+	 * it is preempting or delivering a signal outside of the range
+	 * targeted by the rseq_cs. Also needs to be set to NULL by user-space
+	 * before reclaiming memory that contains the targeted struct rseq_cs.
+	 *
+	 * Read and set by the kernel. Set by user-space with single-copy
+	 * atomicity semantics. This field should only be updated by the
+	 * thread which registered this data structure. Aligned on 64-bit.
+	 */
+	union {
+		__u64 ptr64;
+
+		/*
+		 * The "arch" field provides architecture accessor for
+		 * the ptr field based on architecture pointer size and
+		 * endianness.
+		 */
+		struct {
+#ifdef __LP64__
+			__u64 ptr;
+#elif defined(__BYTE_ORDER) ? (__BYTE_ORDER == __BIG_ENDIAN) : defined(__BIG_ENDIAN)
+			__u32 padding;		/* Initialized to zero. */
+			__u32 ptr;
+#else
+			__u32 ptr;
+			__u32 padding;		/* Initialized to zero. */
+#endif
+		} arch;
+	} rseq_cs;
+
+	/*
+	 * Restartable sequences flags field.
+	 *
+	 * This field should only be updated by the thread which
+	 * registered this data structure. Read by the kernel.
+	 * Mainly used for single-stepping through rseq critical sections
+	 * with debuggers.
+	 *
+	 * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_PREEMPT
+	 *     Inhibit instruction sequence block restart on preemption
+	 *     for this thread.
+	 * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_SIGNAL
+	 *     Inhibit instruction sequence block restart on signal
+	 *     delivery for this thread.
+	 * - RSEQ_ABI_CS_FLAG_NO_RESTART_ON_MIGRATE
+	 *     Inhibit instruction sequence block restart on migration for
+	 *     this thread.
+	 */
+	__u32 flags;
+} __attribute__((aligned(4 * sizeof(__u64))));
+
+#endif /* _RSEQ_ABI_H */

tools/testing/selftests/rseq/rseq-arm.h

@@ -147,14 +147,11 @@ do {									\
 		teardown						\
 		"b %l[" __rseq_str(cmpfail_label) "]\n\t"
 
-#define rseq_workaround_gcc_asm_size_guess()	__asm__ __volatile__("")
-
 static inline __attribute__((always_inline))
 int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -185,8 +182,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
 		  [newv]		"r" (newv)
@@ -198,30 +195,31 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
 
 static inline __attribute__((always_inline))
 int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
-			       off_t voffp, intptr_t *load, int cpu)
+			       long voffp, intptr_t *load, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -255,8 +253,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expectnot]		"r" (expectnot),
@@ -270,19 +268,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -292,7 +292,6 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 #ifdef RSEQ_COMPARE_TWICE
@@ -316,8 +315,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [v]			"m" (*v),
 		  [count]		"Ir" (count)
 		  RSEQ_INJECT_INPUT
@@ -328,14 +327,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		  , error1
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 #endif
 }
@@ -347,7 +347,6 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -381,8 +380,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* try store input */
 		  [v2]			"m" (*v2),
 		  [newv2]		"r" (newv2),
@@ -398,19 +397,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -422,7 +423,6 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -457,8 +457,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* try store input */
 		  [v2]			"m" (*v2),
 		  [newv2]		"r" (newv2),
@@ -474,19 +474,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -498,7 +500,6 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -537,8 +538,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* cmp2 input */
 		  [v2]			"m" (*v2),
 		  [expect2]		"r" (expect2),
@@ -554,21 +555,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2, error3
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("1st expected value comparison failed");
 error3:
+	rseq_after_asm_goto();
 	rseq_bug("2nd expected value comparison failed");
 #endif
 }
@@ -582,7 +586,6 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -657,8 +660,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		"8:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
@@ -678,21 +681,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -706,7 +709,6 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -782,8 +784,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 		"8:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
@@ -803,21 +805,21 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
-	rseq_workaround_gcc_asm_size_guess();
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }

tools/testing/selftests/rseq/rseq-arm64.h

@@ -230,8 +230,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [v]			"Qo" (*v),
 		  [expect]		"r" (expect),
 		  [newv]		"r" (newv)
@@ -242,24 +242,28 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		  , error1, error2
 #endif
 	);
-
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
 
 static inline __attribute__((always_inline))
 int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
-			       off_t voffp, intptr_t *load, int cpu)
+			       long voffp, intptr_t *load, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
@@ -287,8 +291,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [v]			"Qo" (*v),
 		  [expectnot]		"r" (expectnot),
 		  [load]		"Qo" (*load),
@@ -300,16 +304,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -337,8 +346,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [v]			"Qo" (*v),
 		  [count]		"r" (count)
 		  RSEQ_INJECT_INPUT
@@ -348,12 +357,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		  , error1
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 #endif
 }
@@ -388,8 +400,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [expect]		"r" (expect),
 		  [v]			"Qo" (*v),
 		  [newv]		"r" (newv),
@@ -402,17 +414,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -447,8 +463,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [expect]		"r" (expect),
 		  [v]			"Qo" (*v),
 		  [newv]		"r" (newv),
@@ -461,17 +477,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -508,8 +528,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [v]			"Qo" (*v),
 		  [expect]		"r" (expect),
 		  [v2]			"Qo" (*v2),
@@ -522,19 +542,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2, error3
 #endif
 	);
-
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 error3:
+	rseq_after_asm_goto();
 	rseq_bug("2nd expected value comparison failed");
 #endif
 }
@@ -569,8 +594,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [expect]		"r" (expect),
 		  [v]			"Qo" (*v),
 		  [newv]		"r" (newv),
@@ -584,17 +609,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -629,8 +658,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"Qo" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [expect]		"r" (expect),
 		  [v]			"Qo" (*v),
 		  [newv]		"r" (newv),
@@ -644,17 +673,21 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }

tools/testing/selftests/rseq/rseq-generic-thread-pointer.h

@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq-generic-thread-pointer.h
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifndef _RSEQ_GENERIC_THREAD_POINTER
+#define _RSEQ_GENERIC_THREAD_POINTER
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/* Use gcc builtin thread pointer. */
+static inline void *rseq_thread_pointer(void)
+{
+	return __builtin_thread_pointer();
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif

tools/testing/selftests/rseq/rseq-mips.h

@@ -154,14 +154,11 @@ do {									\
 		teardown \
 		"b %l[" __rseq_str(cmpfail_label) "]\n\t"
 
-#define rseq_workaround_gcc_asm_size_guess()	__asm__ __volatile__("")
-
 static inline __attribute__((always_inline))
 int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -190,8 +187,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
 		  [newv]		"r" (newv)
@@ -203,14 +200,11 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
@@ -222,11 +216,10 @@ error2:
 
 static inline __attribute__((always_inline))
 int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
-			       off_t voffp, intptr_t *load, int cpu)
+			       long voffp, intptr_t *load, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -258,8 +251,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expectnot]		"r" (expectnot),
@@ -273,14 +266,11 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
@@ -295,7 +285,6 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 #ifdef RSEQ_COMPARE_TWICE
@@ -319,8 +308,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [v]			"m" (*v),
 		  [count]		"Ir" (count)
 		  RSEQ_INJECT_INPUT
@@ -331,10 +320,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		  , error1
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
 	RSEQ_INJECT_FAILED
 	return -1;
 #ifdef RSEQ_COMPARE_TWICE
@@ -350,7 +337,6 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -382,8 +368,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* try store input */
 		  [v2]			"m" (*v2),
 		  [newv2]		"r" (newv2),
@@ -399,14 +385,11 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
@@ -423,7 +406,6 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -456,8 +438,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* try store input */
 		  [v2]			"m" (*v2),
 		  [newv2]		"r" (newv2),
@@ -473,14 +455,11 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
@@ -497,7 +476,6 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 {
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -532,8 +510,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		"5:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* cmp2 input */
 		  [v2]			"m" (*v2),
 		  [expect2]		"r" (expect2),
@@ -549,14 +527,11 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2, error3
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
@@ -577,7 +552,6 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -649,8 +623,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		"8:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
@@ -670,21 +644,16 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
-	rseq_workaround_gcc_asm_size_guess();
 	rseq_bug("cpu_id comparison failed");
 error2:
-	rseq_workaround_gcc_asm_size_guess();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -698,7 +667,6 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 
 	RSEQ_INJECT_C(9)
 
-	rseq_workaround_gcc_asm_size_guess();
 	__asm__ __volatile__ goto (
 		RSEQ_ASM_DEFINE_TABLE(9, 1f, 2f, 4f) /* start, commit, abort */
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[cmpfail])
@@ -771,8 +739,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 		"8:\n\t"
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
@@ -792,21 +760,16 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
-	rseq_workaround_gcc_asm_size_guess();
 	return 0;
 abort:
-	rseq_workaround_gcc_asm_size_guess();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
-	rseq_workaround_gcc_asm_size_guess();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
-	rseq_workaround_gcc_asm_size_guess();
 	rseq_bug("cpu_id comparison failed");
 error2:
-	rseq_workaround_gcc_asm_size_guess();
 	rseq_bug("expected value comparison failed");
 #endif
 }

tools/testing/selftests/rseq/rseq-ppc-thread-pointer.h

@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq-ppc-thread-pointer.h
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifndef _RSEQ_PPC_THREAD_POINTER
+#define _RSEQ_PPC_THREAD_POINTER
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+static inline void *rseq_thread_pointer(void)
+{
+#ifdef __powerpc64__
+	register void *__result asm ("r13");
+#else
+	register void *__result asm ("r2");
+#endif
+	asm ("" : "=r" (__result));
+	return __result;
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif

tools/testing/selftests/rseq/rseq-ppc.h

@@ -47,10 +47,13 @@ do {									\
 
 #ifdef __PPC64__
 
-#define STORE_WORD	"std "
+#define RSEQ_STORE_LONG(arg)	"std%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] "	/* To memory ("m" constraint) */
-#define LOAD_WORD	"ld "
+#define RSEQ_STORE_INT(arg)	"stw%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] "	/* To memory ("m" constraint) */
-#define LOADX_WORD	"ldx "
+#define RSEQ_LOAD_LONG(arg)	"ld%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] "	/* From memory ("m" constraint) */
-#define CMP_WORD	"cmpd "
+#define RSEQ_LOAD_INT(arg)	"lwz%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] "	/* From memory ("m" constraint) */
+#define RSEQ_LOADX_LONG		"ldx "							/* From base register ("b" constraint) */
+#define RSEQ_CMP_LONG		"cmpd "
+#define RSEQ_CMP_LONG_INT	"cmpdi "
 
 #define __RSEQ_ASM_DEFINE_TABLE(label, version, flags,				\
 			start_ip, post_commit_offset, abort_ip)			\
@@ -89,10 +92,13 @@ do {									\
 
 #else /* #ifdef __PPC64__ */
 
-#define STORE_WORD	"stw "
+#define RSEQ_STORE_LONG(arg)	"stw%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] "	/* To memory ("m" constraint) */
-#define LOAD_WORD	"lwz "
+#define RSEQ_STORE_INT(arg)	RSEQ_STORE_LONG(arg)					/* To memory ("m" constraint) */
-#define LOADX_WORD	"lwzx "
+#define RSEQ_LOAD_LONG(arg)	"lwz%U[" __rseq_str(arg) "]%X[" __rseq_str(arg) "] "	/* From memory ("m" constraint) */
-#define CMP_WORD	"cmpw "
+#define RSEQ_LOAD_INT(arg)	RSEQ_LOAD_LONG(arg)					/* From memory ("m" constraint) */
+#define RSEQ_LOADX_LONG		"lwzx "							/* From base register ("b" constraint) */
+#define RSEQ_CMP_LONG		"cmpw "
+#define RSEQ_CMP_LONG_INT	"cmpwi "
 
 #define __RSEQ_ASM_DEFINE_TABLE(label, version, flags,				\
 			start_ip, post_commit_offset, abort_ip)			\
@@ -125,7 +131,7 @@ do {									\
 		RSEQ_INJECT_ASM(1)						\
 		"lis %%r17, (" __rseq_str(cs_label) ")@ha\n\t"			\
 		"addi %%r17, %%r17, (" __rseq_str(cs_label) ")@l\n\t"		\
-		"stw %%r17, %[" __rseq_str(rseq_cs) "]\n\t"			\
+		RSEQ_STORE_INT(rseq_cs) "%%r17, %[" __rseq_str(rseq_cs) "]\n\t"	\
 		__rseq_str(label) ":\n\t"
 
 #endif /* #ifdef __PPC64__ */
@@ -136,7 +142,7 @@ do {									\
 
 #define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label)			\
 		RSEQ_INJECT_ASM(2)						\
-		"lwz %%r17, %[" __rseq_str(current_cpu_id) "]\n\t"		\
+		RSEQ_LOAD_INT(current_cpu_id) "%%r17, %[" __rseq_str(current_cpu_id) "]\n\t" \
 		"cmpw cr7, %[" __rseq_str(cpu_id) "], %%r17\n\t"		\
 		"bne- cr7, " __rseq_str(label) "\n\t"
 
@@ -153,25 +159,25 @@ do {									\
  * 	RSEQ_ASM_OP_* (else): doesn't have hard-code registers(unless cr7)
  */
 #define RSEQ_ASM_OP_CMPEQ(var, expect, label)					\
-		LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t"			\
+		RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t"		\
-		CMP_WORD "cr7, %%r17, %[" __rseq_str(expect) "]\n\t"		\
+		RSEQ_CMP_LONG "cr7, %%r17, %[" __rseq_str(expect) "]\n\t"		\
 		"bne- cr7, " __rseq_str(label) "\n\t"
 
 #define RSEQ_ASM_OP_CMPNE(var, expectnot, label)				\
-		LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t"			\
+		RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t"		\
-		CMP_WORD "cr7, %%r17, %[" __rseq_str(expectnot) "]\n\t"		\
+		RSEQ_CMP_LONG "cr7, %%r17, %[" __rseq_str(expectnot) "]\n\t"		\
 		"beq- cr7, " __rseq_str(label) "\n\t"
 
 #define RSEQ_ASM_OP_STORE(value, var)						\
-		STORE_WORD "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t"
+		RSEQ_STORE_LONG(var) "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t"
 
 /* Load @var to r17 */
 #define RSEQ_ASM_OP_R_LOAD(var)							\
-		LOAD_WORD "%%r17, %[" __rseq_str(var) "]\n\t"
+		RSEQ_LOAD_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t"
 
 /* Store r17 to @var */
 #define RSEQ_ASM_OP_R_STORE(var)						\
-		STORE_WORD "%%r17, %[" __rseq_str(var) "]\n\t"
+		RSEQ_STORE_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t"
 
 /* Add @count to r17 */
 #define RSEQ_ASM_OP_R_ADD(count)						\
@@ -179,11 +185,11 @@ do {									\
 
 /* Load (r17 + voffp) to r17 */
 #define RSEQ_ASM_OP_R_LOADX(voffp)						\
-		LOADX_WORD "%%r17, %[" __rseq_str(voffp) "], %%r17\n\t"
+		RSEQ_LOADX_LONG "%%r17, %[" __rseq_str(voffp) "], %%r17\n\t"
 
 /* TODO: implement a faster memcpy. */
 #define RSEQ_ASM_OP_R_MEMCPY() \
-		"cmpdi %%r19, 0\n\t" \
+		RSEQ_CMP_LONG_INT "%%r19, 0\n\t" \
 		"beq 333f\n\t" \
 		"addi %%r20, %%r20, -1\n\t" \
 		"addi %%r21, %%r21, -1\n\t" \
@@ -191,16 +197,16 @@ do {									\
 		"lbzu %%r18, 1(%%r20)\n\t" \
 		"stbu %%r18, 1(%%r21)\n\t" \
 		"addi %%r19, %%r19, -1\n\t" \
-		"cmpdi %%r19, 0\n\t" \
+		RSEQ_CMP_LONG_INT "%%r19, 0\n\t" \
 		"bne 222b\n\t" \
 		"333:\n\t" \
 
 #define RSEQ_ASM_OP_R_FINAL_STORE(var, post_commit_label)			\
-		STORE_WORD "%%r17, %[" __rseq_str(var) "]\n\t"			\
+		RSEQ_STORE_LONG(var) "%%r17, %[" __rseq_str(var) "]\n\t"			\
 		__rseq_str(post_commit_label) ":\n\t"
 
 #define RSEQ_ASM_OP_FINAL_STORE(value, var, post_commit_label)			\
-		STORE_WORD "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" \
+		RSEQ_STORE_LONG(var) "%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n\t" \
 		__rseq_str(post_commit_label) ":\n\t"
 
 static inline __attribute__((always_inline))
@@ -235,8 +241,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
 		  [newv]		"r" (newv)
@@ -248,23 +254,28 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
 
 static inline __attribute__((always_inline))
 int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
-			       off_t voffp, intptr_t *load, int cpu)
+			       long voffp, intptr_t *load, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
@@ -301,8 +312,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expectnot]		"r" (expectnot),
@@ -316,16 +327,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -359,8 +375,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [count]		"r" (count)
@@ -372,12 +388,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		  , error1
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 #endif
 }
@@ -419,8 +438,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* try store input */
 		  [v2]			"m" (*v2),
 		  [newv2]		"r" (newv2),
@@ -436,16 +455,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -489,8 +513,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* try store input */
 		  [v2]			"m" (*v2),
 		  [newv2]		"r" (newv2),
@@ -506,16 +530,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -560,8 +589,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* cmp2 input */
 		  [v2]			"m" (*v2),
 		  [expect2]		"r" (expect2),
@@ -577,18 +606,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2, error3
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("1st expected value comparison failed");
 error3:
+	rseq_after_asm_goto();
 	rseq_bug("2nd expected value comparison failed");
 #endif
 }
@@ -635,8 +670,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
@@ -653,16 +688,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -711,8 +751,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
@@ -729,23 +769,23 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
 
-#undef STORE_WORD
-#undef LOAD_WORD
-#undef LOADX_WORD
-#undef CMP_WORD
-
 #endif /* !RSEQ_SKIP_FASTPATH */

tools/testing/selftests/rseq/rseq-s390.h

@@ -165,8 +165,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
 		  [newv]		"r" (newv)
@@ -178,16 +178,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -198,7 +203,7 @@ error2:
  */
 static inline __attribute__((always_inline))
 int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
-			       off_t voffp, intptr_t *load, int cpu)
+			       long voffp, intptr_t *load, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
@@ -233,8 +238,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expectnot]		"r" (expectnot),
@@ -248,16 +253,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -288,8 +298,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [count]		"r" (count)
@@ -301,12 +311,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		  , error1
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 #endif
 }
@@ -347,8 +360,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* try store input */
 		  [v2]			"m" (*v2),
 		  [newv2]		"r" (newv2),
@@ -364,16 +377,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -426,8 +444,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* cmp2 input */
 		  [v2]			"m" (*v2),
 		  [expect2]		"r" (expect2),
@@ -443,18 +461,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2, error3
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("1st expected value comparison failed");
 error3:
+	rseq_after_asm_goto();
 	rseq_bug("2nd expected value comparison failed");
 #endif
 }
@@ -534,8 +558,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 #endif
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [current_cpu_id]	"m" (rseq_get_abi()->cpu_id),
-		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [rseq_cs]		"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
@@ -555,16 +579,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }

tools/testing/selftests/rseq/rseq-skip.h

@@ -13,7 +13,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 
 static inline __attribute__((always_inline))
 int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
-			       off_t voffp, intptr_t *load, int cpu)
+			       long voffp, intptr_t *load, int cpu)
 {
 	return -1;
 }

tools/testing/selftests/rseq/rseq-thread-pointer.h

@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq-thread-pointer.h
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifndef _RSEQ_THREAD_POINTER
+#define _RSEQ_THREAD_POINTER
+
+#if defined(__x86_64__) || defined(__i386__)
+#include "rseq-x86-thread-pointer.h"
+#elif defined(__PPC__)
+#include "rseq-ppc-thread-pointer.h"
+#else
+#include "rseq-generic-thread-pointer.h"
+#endif
+
+#endif

tools/testing/selftests/rseq/rseq-x86-thread-pointer.h

@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */
+/*
+ * rseq-x86-thread-pointer.h
+ *
+ * (C) Copyright 2021 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ */
+
+#ifndef _RSEQ_X86_THREAD_POINTER
+#define _RSEQ_X86_THREAD_POINTER
+
+#include <features.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#if __GNUC_PREREQ (11, 1)
+static inline void *rseq_thread_pointer(void)
+{
+	return __builtin_thread_pointer();
+}
+#else
+static inline void *rseq_thread_pointer(void)
+{
+	void *__result;
+
+# ifdef __x86_64__
+	__asm__ ("mov %%fs:0, %0" : "=r" (__result));
+# else
+	__asm__ ("mov %%gs:0, %0" : "=r" (__result));
+# endif
+	return __result;
+}
+#endif /* !GCC 11 */
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif

tools/testing/selftests/rseq/rseq-x86.h

@@ -28,6 +28,8 @@
 
 #ifdef __x86_64__
 
+#define RSEQ_ASM_TP_SEGMENT	%%fs
+
 #define rseq_smp_mb()	\
 	__asm__ __volatile__ ("lock; addl $0,-128(%%rsp)" ::: "memory", "cc")
 #define rseq_smp_rmb()	rseq_barrier()
@@ -123,14 +125,14 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"cmpq %[v], %[expect]\n\t"
 		"jnz %l[cmpfail]\n\t"
 		RSEQ_INJECT_ASM(4)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 		"cmpq %[v], %[expect]\n\t"
 		"jnz %l[error2]\n\t"
 #endif
@@ -141,7 +143,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
 		  [newv]		"r" (newv)
@@ -152,16 +154,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -172,7 +179,7 @@ error2:
  */
 static inline __attribute__((always_inline))
 int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
-			       off_t voffp, intptr_t *load, int cpu)
+			       long voffp, intptr_t *load, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
@@ -184,15 +191,15 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"movq %[v], %%rbx\n\t"
 		"cmpq %%rbx, %[expectnot]\n\t"
 		"je %l[cmpfail]\n\t"
 		RSEQ_INJECT_ASM(4)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 		"movq %[v], %%rbx\n\t"
 		"cmpq %%rbx, %[expectnot]\n\t"
 		"je %l[error2]\n\t"
@@ -207,7 +214,7 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expectnot]		"r" (expectnot),
@@ -220,16 +227,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -245,11 +257,11 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 #endif
 		/* final store */
 		"addq %[count], %[v]\n\t"
@@ -258,7 +270,7 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [count]		"er" (count)
@@ -269,12 +281,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		  , error1
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 #endif
 }
@@ -286,7 +301,7 @@ error1:
  *  *pval += inc;
  */
 static inline __attribute__((always_inline))
-int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu)
+int rseq_offset_deref_addv(intptr_t *ptr, long off, intptr_t inc, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
@@ -296,11 +311,11 @@ int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu)
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 #endif
 		/* get p+v */
 		"movq %[ptr], %%rbx\n\t"
@@ -314,7 +329,7 @@ int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* final store input */
 		  [ptr]			"m" (*ptr),
 		  [off]			"er" (off),
@@ -351,14 +366,14 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"cmpq %[v], %[expect]\n\t"
 		"jnz %l[cmpfail]\n\t"
 		RSEQ_INJECT_ASM(4)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 		"cmpq %[v], %[expect]\n\t"
 		"jnz %l[error2]\n\t"
 #endif
@@ -372,7 +387,7 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* try store input */
 		  [v2]			"m" (*v2),
 		  [newv2]		"r" (newv2),
@@ -387,16 +402,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -426,8 +446,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error3])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"cmpq %[v], %[expect]\n\t"
 		"jnz %l[cmpfail]\n\t"
@@ -436,7 +456,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		"jnz %l[cmpfail]\n\t"
 		RSEQ_INJECT_ASM(5)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 		"cmpq %[v], %[expect]\n\t"
 		"jnz %l[error2]\n\t"
 		"cmpq %[v2], %[expect2]\n\t"
@@ -449,7 +469,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* cmp2 input */
 		  [v2]			"m" (*v2),
 		  [expect2]		"r" (expect2),
@@ -464,18 +484,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2, error3
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("1st expected value comparison failed");
 error3:
+	rseq_after_asm_goto();
 	rseq_bug("2nd expected value comparison failed");
 #endif
 }
@@ -500,14 +526,14 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		"movq %[dst], %[rseq_scratch1]\n\t"
 		"movq %[len], %[rseq_scratch2]\n\t"
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"cmpq %[v], %[expect]\n\t"
 		"jnz 5f\n\t"
 		RSEQ_INJECT_ASM(4)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f)
 		"cmpq %[v], %[expect]\n\t"
 		"jnz 7f\n\t"
 #endif
@@ -555,7 +581,7 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 #endif
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
@@ -574,16 +600,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -600,7 +631,9 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 
 #endif /* !RSEQ_SKIP_FASTPATH */
 
-#elif __i386__
+#elif defined(__i386__)
+
+#define RSEQ_ASM_TP_SEGMENT	%%gs
 
 #define rseq_smp_mb()	\
 	__asm__ __volatile__ ("lock; addl $0,-128(%%esp)" ::: "memory", "cc")
@@ -701,14 +734,14 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"cmpl %[v], %[expect]\n\t"
 		"jnz %l[cmpfail]\n\t"
 		RSEQ_INJECT_ASM(4)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 		"cmpl %[v], %[expect]\n\t"
 		"jnz %l[error2]\n\t"
 #endif
@@ -719,7 +752,7 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  [v]			"m" (*v),
 		  [expect]		"r" (expect),
 		  [newv]		"r" (newv)
@@ -730,16 +763,21 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -750,7 +788,7 @@ error2:
  */
 static inline __attribute__((always_inline))
 int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
-			       off_t voffp, intptr_t *load, int cpu)
+			       long voffp, intptr_t *load, int cpu)
 {
 	RSEQ_INJECT_C(9)
 
@@ -762,15 +800,15 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"movl %[v], %%ebx\n\t"
 		"cmpl %%ebx, %[expectnot]\n\t"
 		"je %l[cmpfail]\n\t"
 		RSEQ_INJECT_ASM(4)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 		"movl %[v], %%ebx\n\t"
 		"cmpl %%ebx, %[expectnot]\n\t"
 		"je %l[error2]\n\t"
@@ -785,7 +823,7 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expectnot]		"r" (expectnot),
@@ -798,16 +836,21 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -823,11 +866,11 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error1])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 #endif
 		/* final store */
 		"addl %[count], %[v]\n\t"
@@ -836,7 +879,7 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [count]		"ir" (count)
@@ -847,12 +890,15 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu)
 		  , error1
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 #endif
 }
@@ -872,14 +918,14 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"cmpl %[v], %[expect]\n\t"
 		"jnz %l[cmpfail]\n\t"
 		RSEQ_INJECT_ASM(4)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 		"cmpl %[v], %[expect]\n\t"
 		"jnz %l[error2]\n\t"
 #endif
@@ -894,7 +940,7 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* try store input */
 		  [v2]			"m" (*v2),
 		  [newv2]		"m" (newv2),
@@ -909,16 +955,21 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -938,15 +989,15 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error2])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"movl %[expect], %%eax\n\t"
 		"cmpl %[v], %%eax\n\t"
 		"jnz %l[cmpfail]\n\t"
 		RSEQ_INJECT_ASM(4)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 		"movl %[expect], %%eax\n\t"
 		"cmpl %[v], %%eax\n\t"
 		"jnz %l[error2]\n\t"
@@ -962,7 +1013,7 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* try store input */
 		  [v2]			"m" (*v2),
 		  [newv2]		"r" (newv2),
@@ -977,16 +1028,21 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 
@@ -1008,8 +1064,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_EXIT_POINT(1f, %l[error3])
 #endif
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"cmpl %[v], %[expect]\n\t"
 		"jnz %l[cmpfail]\n\t"
@@ -1018,7 +1074,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		"jnz %l[cmpfail]\n\t"
 		RSEQ_INJECT_ASM(5)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), %l[error1])
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), %l[error1])
 		"cmpl %[v], %[expect]\n\t"
 		"jnz %l[error2]\n\t"
 		"cmpl %[expect2], %[v2]\n\t"
@@ -1032,7 +1088,7 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* cmp2 input */
 		  [v2]			"m" (*v2),
 		  [expect2]		"r" (expect2),
@@ -1047,18 +1103,24 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2, error3
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("1st expected value comparison failed");
 error3:
+	rseq_after_asm_goto();
 	rseq_bug("2nd expected value comparison failed");
 #endif
 }
@@ -1084,15 +1146,15 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		"movl %[dst], %[rseq_scratch1]\n\t"
 		"movl %[len], %[rseq_scratch2]\n\t"
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"movl %[expect], %%eax\n\t"
 		"cmpl %%eax, %[v]\n\t"
 		"jnz 5f\n\t"
 		RSEQ_INJECT_ASM(4)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f)
 		"movl %[expect], %%eax\n\t"
 		"cmpl %%eax, %[v]\n\t"
 		"jnz 7f\n\t"
@@ -1142,7 +1204,7 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 #endif
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expect]		"m" (expect),
@@ -1161,16 +1223,21 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }
@@ -1196,15 +1263,15 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 		"movl %[dst], %[rseq_scratch1]\n\t"
 		"movl %[len], %[rseq_scratch2]\n\t"
 		/* Start rseq by storing table entry pointer into rseq_cs. */
-		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_CS_OFFSET(%[rseq_abi]))
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, RSEQ_ASM_TP_SEGMENT:RSEQ_CS_OFFSET(%[rseq_offset]))
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 4f)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 4f)
 		RSEQ_INJECT_ASM(3)
 		"movl %[expect], %%eax\n\t"
 		"cmpl %%eax, %[v]\n\t"
 		"jnz 5f\n\t"
 		RSEQ_INJECT_ASM(4)
 #ifdef RSEQ_COMPARE_TWICE
-		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_CPU_ID_OFFSET(%[rseq_abi]), 6f)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, RSEQ_ASM_TP_SEGMENT:RSEQ_CPU_ID_OFFSET(%[rseq_offset]), 6f)
 		"movl %[expect], %%eax\n\t"
 		"cmpl %%eax, %[v]\n\t"
 		"jnz 7f\n\t"
@@ -1255,7 +1322,7 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 #endif
 		: /* gcc asm goto does not allow outputs */
 		: [cpu_id]		"r" (cpu),
-		  [rseq_abi]		"r" (&__rseq_abi),
+		  [rseq_offset]		"r" (rseq_offset),
 		  /* final store input */
 		  [v]			"m" (*v),
 		  [expect]		"m" (expect),
@@ -1274,16 +1341,21 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
 		  , error1, error2
 #endif
 	);
+	rseq_after_asm_goto();
 	return 0;
 abort:
+	rseq_after_asm_goto();
 	RSEQ_INJECT_FAILED
 	return -1;
 cmpfail:
+	rseq_after_asm_goto();
 	return 1;
 #ifdef RSEQ_COMPARE_TWICE
 error1:
+	rseq_after_asm_goto();
 	rseq_bug("cpu_id comparison failed");
 error2:
+	rseq_after_asm_goto();
 	rseq_bug("expected value comparison failed");
 #endif
 }

tools/testing/selftests/rseq/rseq.c

@@ -26,104 +26,114 @@
 #include <assert.h>
 #include <signal.h>
 #include <limits.h>
+#include <dlfcn.h>
+#include <stddef.h>
 
+#include "../kselftest.h"
 #include "rseq.h"
 
-#define ARRAY_SIZE(arr)	(sizeof(arr) / sizeof((arr)[0]))
+static const ptrdiff_t *libc_rseq_offset_p;
+static const unsigned int *libc_rseq_size_p;
+static const unsigned int *libc_rseq_flags_p;
 
-__thread volatile struct rseq __rseq_abi = {
+/* Offset from the thread pointer to the rseq area.  */
-	.cpu_id = RSEQ_CPU_ID_UNINITIALIZED,
+ptrdiff_t rseq_offset;
-};
 
-/*
+/* Size of the registered rseq area.  0 if the registration was
- * Shared with other libraries. This library may take rseq ownership if it is
+   unsuccessful.  */
- * still 0 when executing the library constructor. Set to 1 by library
+unsigned int rseq_size = -1U;
- * constructor when handling rseq. Set to 0 in destructor if handling rseq.
+
- */
+/* Flags used during rseq registration.  */
-int __rseq_handled;
+unsigned int rseq_flags;
 
-/* Whether this library have ownership of rseq registration. */
 static int rseq_ownership;
 
-static __thread volatile uint32_t __rseq_refcount;
+static
+__thread struct rseq_abi __rseq_abi __attribute__((tls_model("initial-exec"))) = {
+	.cpu_id = RSEQ_ABI_CPU_ID_UNINITIALIZED,
+};
 
-static void signal_off_save(sigset_t *oldset)
+static int sys_rseq(struct rseq_abi *rseq_abi, uint32_t rseq_len,
-{
-	sigset_t set;
-	int ret;
-
-	sigfillset(&set);
-	ret = pthread_sigmask(SIG_BLOCK, &set, oldset);
-	if (ret)
-		abort();
-}
-
-static void signal_restore(sigset_t oldset)
-{
-	int ret;
-
-	ret = pthread_sigmask(SIG_SETMASK, &oldset, NULL);
-	if (ret)
-		abort();
-}
-
-static int sys_rseq(volatile struct rseq *rseq_abi, uint32_t rseq_len,
 		    int flags, uint32_t sig)
 {
 	return syscall(__NR_rseq, rseq_abi, rseq_len, flags, sig);
 }
 
+int rseq_available(void)
+{
+	int rc;
+
+	rc = sys_rseq(NULL, 0, 0, 0);
+	if (rc != -1)
+		abort();
+	switch (errno) {
+	case ENOSYS:
+		return 0;
+	case EINVAL:
+		return 1;
+	default:
+		abort();
+	}
+}
+
 int rseq_register_current_thread(void)
 {
-	int rc, ret = 0;
+	int rc;
-	sigset_t oldset;
 
-	if (!rseq_ownership)
+	if (!rseq_ownership) {
+		/* Treat libc's ownership as a successful registration. */
 		return 0;
-	signal_off_save(&oldset);
-	if (__rseq_refcount == UINT_MAX) {
-		ret = -1;
-		goto end;
 	}
-	if (__rseq_refcount++)
+	rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), 0, RSEQ_SIG);
-		goto end;
+	if (rc)
-	rc = sys_rseq(&__rseq_abi, sizeof(struct rseq), 0, RSEQ_SIG);
+		return -1;
-	if (!rc) {
+	assert(rseq_current_cpu_raw() >= 0);
-		assert(rseq_current_cpu_raw() >= 0);
+	return 0;
-		goto end;
-	}
-	if (errno != EBUSY)
-		__rseq_abi.cpu_id = RSEQ_CPU_ID_REGISTRATION_FAILED;
-	ret = -1;
-	__rseq_refcount--;
-end:
-	signal_restore(oldset);
-	return ret;
 }
 
 int rseq_unregister_current_thread(void)
 {
-	int rc, ret = 0;
+	int rc;
-	sigset_t oldset;
 
-	if (!rseq_ownership)
+	if (!rseq_ownership) {
+		/* Treat libc's ownership as a successful unregistration. */
 		return 0;
-	signal_off_save(&oldset);
-	if (!__rseq_refcount) {
-		ret = -1;
-		goto end;
 	}
-	if (--__rseq_refcount)
+	rc = sys_rseq(&__rseq_abi, sizeof(struct rseq_abi), RSEQ_ABI_FLAG_UNREGISTER, RSEQ_SIG);
-		goto end;
+	if (rc)
-	rc = sys_rseq(&__rseq_abi, sizeof(struct rseq),
+		return -1;
-		      RSEQ_FLAG_UNREGISTER, RSEQ_SIG);
+	return 0;
-	if (!rc)
+}
-		goto end;
+
-	__rseq_refcount = 1;
+static __attribute__((constructor))
-	ret = -1;
+void rseq_init(void)
-end:
+{
-	signal_restore(oldset);
+	libc_rseq_offset_p = dlsym(RTLD_NEXT, "__rseq_offset");
-	return ret;
+	libc_rseq_size_p = dlsym(RTLD_NEXT, "__rseq_size");
+	libc_rseq_flags_p = dlsym(RTLD_NEXT, "__rseq_flags");
+	if (libc_rseq_size_p && libc_rseq_offset_p && libc_rseq_flags_p) {
+		/* rseq registration owned by glibc */
+		rseq_offset = *libc_rseq_offset_p;
+		rseq_size = *libc_rseq_size_p;
+		rseq_flags = *libc_rseq_flags_p;
+		return;
+	}
+	if (!rseq_available())
+		return;
+	rseq_ownership = 1;
+	rseq_offset = (void *)&__rseq_abi - rseq_thread_pointer();
+	rseq_size = sizeof(struct rseq_abi);
+	rseq_flags = 0;
+}
+
+static __attribute__((destructor))
+void rseq_exit(void)
+{
+	if (!rseq_ownership)
+		return;
+	rseq_offset = 0;
+	rseq_size = -1U;
+	rseq_ownership = 0;
 }
 
 int32_t rseq_fallback_current_cpu(void)
@@ -137,20 +147,3 @@ int32_t rseq_fallback_current_cpu(void)
 	}
 	return cpu;
 }
-
-void __attribute__((constructor)) rseq_init(void)
-{
-	/* Check whether rseq is handled by another library. */
-	if (__rseq_handled)
-		return;
-	__rseq_handled = 1;
-	rseq_ownership = 1;
-}
-
-void __attribute__((destructor)) rseq_fini(void)
-{
-	if (!rseq_ownership)
-		return;
-	__rseq_handled = 0;
-	rseq_ownership = 0;
-}

tools/testing/selftests/rseq/rseq.h

@@ -16,7 +16,9 @@
 #include <errno.h>
 #include <stdio.h>
 #include <stdlib.h>
-#include <linux/rseq.h>
+#include <stddef.h>
+#include "rseq-abi.h"
+#include "compiler.h"
 
 /*
  * Empty code injection macros, override when testing.
@@ -43,8 +45,20 @@
 #define RSEQ_INJECT_FAILED
 #endif
 
-extern __thread volatile struct rseq __rseq_abi;
+#include "rseq-thread-pointer.h"
-extern int __rseq_handled;
+
+/* Offset from the thread pointer to the rseq area.  */
+extern ptrdiff_t rseq_offset;
+/* Size of the registered rseq area.  0 if the registration was
+   unsuccessful.  */
+extern unsigned int rseq_size;
+/* Flags used during rseq registration.  */
+extern unsigned int rseq_flags;
+
+static inline struct rseq_abi *rseq_get_abi(void)
+{
+	return (struct rseq_abi *) ((uintptr_t) rseq_thread_pointer() + rseq_offset);
+}
 
 #define rseq_likely(x)		__builtin_expect(!!(x), 1)
 #define rseq_unlikely(x)	__builtin_expect(!!(x), 0)
@@ -108,7 +122,7 @@ int32_t rseq_fallback_current_cpu(void);
  */
 static inline int32_t rseq_current_cpu_raw(void)
 {
-	return RSEQ_ACCESS_ONCE(__rseq_abi.cpu_id);
+	return RSEQ_ACCESS_ONCE(rseq_get_abi()->cpu_id);
 }
 
 /*
@@ -124,7 +138,7 @@ static inline int32_t rseq_current_cpu_raw(void)
  */
 static inline uint32_t rseq_cpu_start(void)
 {
-	return RSEQ_ACCESS_ONCE(__rseq_abi.cpu_id_start);
+	return RSEQ_ACCESS_ONCE(rseq_get_abi()->cpu_id_start);
 }
 
 static inline uint32_t rseq_current_cpu(void)
@@ -139,11 +153,7 @@ static inline uint32_t rseq_current_cpu(void)
 
 static inline void rseq_clear_rseq_cs(void)
 {
-#ifdef __LP64__
+	RSEQ_WRITE_ONCE(rseq_get_abi()->rseq_cs.arch.ptr, 0);
-	__rseq_abi.rseq_cs.ptr = 0;
-#else
-	__rseq_abi.rseq_cs.ptr.ptr32 = 0;
-#endif
 }
 
 /*