Merge branch 'perf/urgent' into perf/core, to pick up latest fixes and refresh the tree

Signed-off-by: Ingo Molnar <mingo@kernel.org>

31 files changed, 2411 insertions, 214 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index 0c8b78a9ae2e..6762529ad9e4 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -158,6 +158,14 @@ config CRC32_BIT
 
 endchoice
 
+config CRC4
+	tristate "CRC4 functions"
+	help
+	  This option is provided for the case where no in-kernel-tree
+	  modules require CRC4 functions, but a module built outside
+	  the kernel tree does. Such modules that use library CRC4
+	  functions require M here.
+
 config CRC7
 	tristate "CRC7 functions"
 	help
@@ -548,6 +556,9 @@ config ARCH_HAS_SG_CHAIN
 config ARCH_HAS_PMEM_API
 	bool
 
+config ARCH_HAS_UACCESS_FLUSHCACHE
+	bool
+
 config ARCH_HAS_MMIO_FLUSH
 	bool
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 9c5d40a50930..98fe715522e8 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -286,7 +286,7 @@ config DEBUG_FS
 	  write to these files.
 
 	  For detailed documentation on the debugfs API, see
-	  Documentation/DocBook/filesystems.
+	  Documentation/filesystems/.
 
 	  If unsure, say N.
 
@@ -778,34 +778,45 @@ config DEBUG_SHIRQ
 menu "Debug Lockups and Hangs"
 
 config LOCKUP_DETECTOR
-	bool "Detect Hard and Soft Lockups"
+	bool
+
+config SOFTLOCKUP_DETECTOR
+	bool "Detect Soft Lockups"
 	depends on DEBUG_KERNEL && !S390
+	select LOCKUP_DETECTOR
 	help
 	  Say Y here to enable the kernel to act as a watchdog to detect
-	  hard and soft lockups.
+	  soft lockups.
 
 	  Softlockups are bugs that cause the kernel to loop in kernel
 	  mode for more than 20 seconds, without giving other tasks a
 	  chance to run.  The current stack trace is displayed upon
 	  detection and the system will stay locked up.
 
+config HARDLOCKUP_DETECTOR_PERF
+	bool
+	select SOFTLOCKUP_DETECTOR
+
+#
+# arch/ can define HAVE_HARDLOCKUP_DETECTOR_ARCH to provide their own hard
+# lockup detector rather than the perf based detector.
+#
+config HARDLOCKUP_DETECTOR
+	bool "Detect Hard Lockups"
+	depends on DEBUG_KERNEL && !S390
+	depends on HAVE_HARDLOCKUP_DETECTOR_PERF || HAVE_HARDLOCKUP_DETECTOR_ARCH
+	select LOCKUP_DETECTOR
+	select HARDLOCKUP_DETECTOR_PERF if HAVE_HARDLOCKUP_DETECTOR_PERF
+	select HARDLOCKUP_DETECTOR_ARCH if HAVE_HARDLOCKUP_DETECTOR_ARCH
+	help
+	  Say Y here to enable the kernel to act as a watchdog to detect
+	  hard lockups.
+
 	  Hardlockups are bugs that cause the CPU to loop in kernel mode
 	  for more than 10 seconds, without letting other interrupts have a
 	  chance to run.  The current stack trace is displayed upon detection
 	  and the system will stay locked up.
 
-	  The overhead should be minimal.  A periodic hrtimer runs to
-	  generate interrupts and kick the watchdog task every 4 seconds.
-	  An NMI is generated every 10 seconds or so to check for hardlockups.
-
-	  The frequency of hrtimer and NMI events and the soft and hard lockup
-	  thresholds can be controlled through the sysctl watchdog_thresh.
-
-config HARDLOCKUP_DETECTOR
-	def_bool y
-	depends on LOCKUP_DETECTOR && !HAVE_NMI_WATCHDOG
-	depends on PERF_EVENTS && HAVE_PERF_EVENTS_NMI
-
 config BOOTPARAM_HARDLOCKUP_PANIC
 	bool "Panic (Reboot) On Hard Lockups"
 	depends on HARDLOCKUP_DETECTOR
@@ -826,7 +837,7 @@ config BOOTPARAM_HARDLOCKUP_PANIC_VALUE
 
 config BOOTPARAM_SOFTLOCKUP_PANIC
 	bool "Panic (Reboot) On Soft Lockups"
-	depends on LOCKUP_DETECTOR
+	depends on SOFTLOCKUP_DETECTOR
 	help
 	  Say Y here to enable the kernel to panic on "soft lockups",
 	  which are bugs that cause the kernel to loop in kernel
@@ -843,7 +854,7 @@ config BOOTPARAM_SOFTLOCKUP_PANIC
 
 config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE
 	int
-	depends on LOCKUP_DETECTOR
+	depends on SOFTLOCKUP_DETECTOR
 	range 0 1
 	default 0 if !BOOTPARAM_SOFTLOCKUP_PANIC
 	default 1 if BOOTPARAM_SOFTLOCKUP_PANIC
@@ -851,7 +862,7 @@ config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE
 config DETECT_HUNG_TASK
 	bool "Detect Hung Tasks"
 	depends on DEBUG_KERNEL
-	default LOCKUP_DETECTOR
+	default SOFTLOCKUP_DETECTOR
 	help
 	  Say Y here to enable the kernel to detect "hung tasks",
 	  which are bugs that cause the task to be stuck in
@@ -1212,6 +1223,34 @@ config STACKTRACE
 	  It is also used by various kernel debugging features that require
 	  stack trace generation.
 
+config WARN_ALL_UNSEEDED_RANDOM
+	bool "Warn for all uses of unseeded randomness"
+	default n
+	help
+	  Some parts of the kernel contain bugs relating to their use of
+	  cryptographically secure random numbers before it's actually possible
+	  to generate those numbers securely. This setting ensures that these
+	  flaws don't go unnoticed, by enabling a message, should this ever
+	  occur. This will allow people with obscure setups to know when things
+	  are going wrong, so that they might contact developers about fixing
+	  it.
+
+	  Unfortunately, on some models of some architectures getting
+	  a fully seeded CRNG is extremely difficult, and so this can
+	  result in dmesg getting spammed for a surprisingly long
+	  time.  This is really bad from a security perspective, and
+	  so architecture maintainers really need to do what they can
+	  to get the CRNG seeded sooner after the system is booted.
+	  However, since users can not do anything actionble to
+	  address this, by default the kernel will issue only a single
+	  warning for the first use of unseeded randomness.
+
+	  Say Y here if you want to receive warnings for all uses of
+	  unseeded randomness.  This will be of use primarily for
+	  those developers interersted in improving the security of
+	  Linux kernels running on their architecture (or
+	  subarchitecture).
+
 config DEBUG_KOBJECT
 	bool "kobject debugging"
 	depends on DEBUG_KERNEL
@@ -1594,7 +1633,7 @@ config RBTREE_TEST
 
 config INTERVAL_TREE_TEST
 	tristate "Interval tree test"
-	depends on m && DEBUG_KERNEL
+	depends on DEBUG_KERNEL
 	select INTERVAL_TREE
 	help
 	  A benchmark measuring the performance of the interval tree library
@@ -1785,6 +1824,17 @@ config TEST_FIRMWARE
 
 	  If unsure, say N.
 
+config TEST_SYSCTL
+	tristate "sysctl test driver"
+	default n
+	depends on PROC_SYSCTL
+	help
+	  This builds the "test_sysctl" module. This driver enables to test the
+	  proc sysctl interfaces available to drivers safely without affecting
+	  production knobs which might alter system functionality.
+
+	  If unsure, say N.
+
 config TEST_UDELAY
 	tristate "udelay test driver"
 	default n
@@ -1825,6 +1875,33 @@ config BUG_ON_DATA_CORRUPTION
 
 	  If unsure, say N.
 
+config TEST_KMOD
+	tristate "kmod stress tester"
+	default n
+	depends on m
+	depends on BLOCK && (64BIT || LBDAF)	  # for XFS, BTRFS
+	depends on NETDEVICES && NET_CORE && INET # for TUN
+	select TEST_LKM
+	select XFS_FS
+	select TUN
+	select BTRFS_FS
+	help
+	  Test the kernel's module loading mechanism: kmod. kmod implements
+	  support to load modules using the Linux kernel's usermode helper.
+	  This test provides a series of tests against kmod.
+
+	  Although technically you can either build test_kmod as a module or
+	  into the kernel we disallow building it into the kernel since
+	  it stress tests request_module() and this will very likely cause
+	  some issues by taking over precious threads available from other
+	  module load requests, ultimately this could be fatal.
+
+	  To run tests run:
+
+	  tools/testing/selftests/kmod/kmod.sh --help
+
+	  If unsure, say N.
+
 source "samples/Kconfig"
 
 source "lib/Kconfig.kgdb"
diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb
index 533f912638ed..ab4ff0eea776 100644
--- a/lib/Kconfig.kgdb
+++ b/lib/Kconfig.kgdb
@@ -13,7 +13,7 @@ menuconfig KGDB
 	  CONFIG_FRAME_POINTER to aid in producing more reliable stack
 	  backtraces in the external debugger.  Documentation of
 	  kernel debugger is available at http://kgdb.sourceforge.net
-	  as well as in DocBook form in Documentation/DocBook/.  If
+	  as well as in Documentation/dev-tools/kgdb.rst.  If
 	  unsure, say N.
 
 if KGDB
diff --git a/lib/Makefile b/lib/Makefile
index 07fbe6a75692..40c18372b301 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -38,7 +38,7 @@ obj-y += bcd.o div64.o sort.o parser.o debug_locks.o random32.o \
 	 gcd.o lcm.o list_sort.o uuid.o flex_array.o iov_iter.o clz_ctz.o \
 	 bsearch.o find_bit.o llist.o memweight.o kfifo.o \
 	 percpu-refcount.o percpu_ida.o rhashtable.o reciprocal_div.o \
-	 once.o refcount.o usercopy.o
+	 once.o refcount.o usercopy.o errseq.o
 obj-y += string_helpers.o
 obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o
 obj-y += hexdump.o
@@ -46,6 +46,7 @@ obj-$(CONFIG_TEST_HEXDUMP) += test_hexdump.o
 obj-y += kstrtox.o
 obj-$(CONFIG_TEST_BPF) += test_bpf.o
 obj-$(CONFIG_TEST_FIRMWARE) += test_firmware.o
+obj-$(CONFIG_TEST_SYSCTL) += test_sysctl.o
 obj-$(CONFIG_TEST_HASH) += test_hash.o test_siphash.o
 obj-$(CONFIG_TEST_KASAN) += test_kasan.o
 obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o
@@ -60,6 +61,7 @@ obj-$(CONFIG_TEST_PRINTF) += test_printf.o
 obj-$(CONFIG_TEST_BITMAP) += test_bitmap.o
 obj-$(CONFIG_TEST_UUID) += test_uuid.o
 obj-$(CONFIG_TEST_PARMAN) += test_parman.o
+obj-$(CONFIG_TEST_KMOD) += test_kmod.o
 
 ifeq ($(CONFIG_DEBUG_KOBJECT),y)
 CFLAGS_kobject.o += -DDEBUG
@@ -96,6 +98,7 @@ obj-$(CONFIG_CRC_T10DIF)+= crc-t10dif.o
 obj-$(CONFIG_CRC_ITU_T)	+= crc-itu-t.o
 obj-$(CONFIG_CRC32)	+= crc32.o
 obj-$(CONFIG_CRC32_SELFTEST)	+= crc32test.o
+obj-$(CONFIG_CRC4)	+= crc4.o
 obj-$(CONFIG_CRC7)	+= crc7.o
 obj-$(CONFIG_LIBCRC32C)	+= libcrc32c.o
 obj-$(CONFIG_CRC8)	+= crc8.o
diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c
index fd70c0e0e673..62ab629f51ca 100644
--- a/lib/atomic64_test.c
+++ b/lib/atomic64_test.c
@@ -153,8 +153,10 @@ static __init void test_atomic64(void)
 	long long v0 = 0xaaa31337c001d00dLL;
 	long long v1 = 0xdeadbeefdeafcafeLL;
 	long long v2 = 0xfaceabadf00df001LL;
+	long long v3 = 0x8000000000000000LL;
 	long long onestwos = 0x1111111122222222LL;
 	long long one = 1LL;
+	int r_int;
 
 	atomic64_t v = ATOMIC64_INIT(v0);
 	long long r = v0;
@@ -240,6 +242,11 @@ static __init void test_atomic64(void)
 	BUG_ON(!atomic64_inc_not_zero(&v));
 	r += one;
 	BUG_ON(v.counter != r);
+
+	/* Confirm the return value fits in an int, even if the value doesn't */
+	INIT(v3);
+	r_int = atomic64_inc_not_zero(&v);
+	BUG_ON(!r_int);
 }
 
 static __init int test_atomics_init(void)
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 08c6ef3a2b6f..9a532805364b 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -251,7 +251,7 @@ int __bitmap_weight(const unsigned long *bitmap, unsigned int bits)
 }
 EXPORT_SYMBOL(__bitmap_weight);
 
-void bitmap_set(unsigned long *map, unsigned int start, int len)
+void __bitmap_set(unsigned long *map, unsigned int start, int len)
 {
 	unsigned long *p = map + BIT_WORD(start);
 	const unsigned int size = start + len;
@@ -270,9 +270,9 @@ void bitmap_set(unsigned long *map, unsigned int start, int len)
 		*p |= mask_to_set;
 	}
 }
-EXPORT_SYMBOL(bitmap_set);
+EXPORT_SYMBOL(__bitmap_set);
 
-void bitmap_clear(unsigned long *map, unsigned int start, int len)
+void __bitmap_clear(unsigned long *map, unsigned int start, int len)
 {
 	unsigned long *p = map + BIT_WORD(start);
 	const unsigned int size = start + len;
@@ -291,7 +291,7 @@ void bitmap_clear(unsigned long *map, unsigned int start, int len)
 		*p &= ~mask_to_clear;
 	}
 }
-EXPORT_SYMBOL(bitmap_clear);
+EXPORT_SYMBOL(__bitmap_clear);
 
 /**
  * bitmap_find_next_zero_area_off - find a contiguous aligned zero area
diff --git a/lib/bsearch.c b/lib/bsearch.c
index e33c179089db..18b445b010c3 100644
--- a/lib/bsearch.c
+++ b/lib/bsearch.c
@@ -33,19 +33,21 @@
 void *bsearch(const void *key, const void *base, size_t num, size_t size,
 	      int (*cmp)(const void *key, const void *elt))
 {
-	size_t start = 0, end = num;
+	const char *pivot;
 	int result;
 
-	while (start < end) {
-		size_t mid = start + (end - start) / 2;
+	while (num > 0) {
+		pivot = base + (num >> 1) * size;
+		result = cmp(key, pivot);
 
-		result = cmp(key, base + mid * size);
-		if (result < 0)
-			end = mid;
-		else if (result > 0)
-			start = mid + 1;
-		else
-			return (void *)base + mid * size;
+		if (result == 0)
+			return (void *)pivot;
+
+		if (result > 0) {
+			base = pivot + size;
+			num--;
+		}
+		num >>= 1;
 	}
 
 	return NULL;
diff --git a/lib/crc4.c b/lib/crc4.c
new file mode 100644
index 000000000000..cf6db46661be
--- /dev/null
+++ b/lib/crc4.c
@@ -0,0 +1,46 @@
+/*
+ * crc4.c - simple crc-4 calculations.
+ *
+ * This source code is licensed under the GNU General Public License, Version
+ * 2. See the file COPYING for more details.
+ */
+
+#include <linux/crc4.h>
+#include <linux/module.h>
+
+static const uint8_t crc4_tab[] = {
+	0x0, 0x7, 0xe, 0x9, 0xb, 0xc, 0x5, 0x2,
+	0x1, 0x6, 0xf, 0x8, 0xa, 0xd, 0x4, 0x3,
+};
+
+/**
+ * crc4 - calculate the 4-bit crc of a value.
+ * @crc:  starting crc4
+ * @x:    value to checksum
+ * @bits: number of bits in @x to checksum
+ *
+ * Returns the crc4 value of @x, using polynomial 0b10111.
+ *
+ * The @x value is treated as left-aligned, and bits above @bits are ignored
+ * in the crc calculations.
+ */
+uint8_t crc4(uint8_t c, uint64_t x, int bits)
+{
+	int i;
+
+	/* mask off anything above the top bit */
+	x &= (1ull << bits) - 1;
+
+	/* Align to 4-bits */
+	bits = (bits + 3) & ~0x3;
+
+	/* Calculate crc4 over four-bit nibbles, starting at the MSbit */
+	for (i = bits - 4; i >= 0; i -= 4)
+		c = crc4_tab[c ^ ((x >> i) & 0xf)];
+
+	return c;
+}
+EXPORT_SYMBOL_GPL(crc4);
+
+MODULE_DESCRIPTION("CRC4 calculations");
+MODULE_LICENSE("GPL");
diff --git a/lib/dma-noop.c b/lib/dma-noop.c
index de26c8b68f34..acc4190e2731 100644
--- a/lib/dma-noop.c
+++ b/lib/dma-noop.c
@@ -7,6 +7,7 @@
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
 #include <linux/scatterlist.h>
+#include <linux/pfn.h>
 
 static void *dma_noop_alloc(struct device *dev, size_t size,
 			    dma_addr_t *dma_handle, gfp_t gfp,
@@ -16,7 +17,8 @@ static void *dma_noop_alloc(struct device *dev, size_t size,
 
 	ret = (void *)__get_free_pages(gfp, get_order(size));
 	if (ret)
-		*dma_handle = virt_to_phys(ret);
+		*dma_handle = virt_to_phys(ret) - PFN_PHYS(dev->dma_pfn_offset);
+
 	return ret;
 }
 
@@ -32,7 +34,7 @@ static dma_addr_t dma_noop_map_page(struct device *dev, struct page *page,
 				      enum dma_data_direction dir,
 				      unsigned long attrs)
 {
-	return page_to_phys(page) + offset;
+	return page_to_phys(page) + offset - PFN_PHYS(dev->dma_pfn_offset);
 }
 
 static int dma_noop_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
@@ -43,34 +45,23 @@ static int dma_noop_map_sg(struct device *dev, struct scatterlist *sgl, int nent
 	struct scatterlist *sg;
 
 	for_each_sg(sgl, sg, nents, i) {
+		dma_addr_t offset = PFN_PHYS(dev->dma_pfn_offset);
 		void *va;
 
 		BUG_ON(!sg_page(sg));
 		va = sg_virt(sg);
-		sg_dma_address(sg) = (dma_addr_t)virt_to_phys(va);
+		sg_dma_address(sg) = (dma_addr_t)virt_to_phys(va) - offset;
 		sg_dma_len(sg) = sg->length;
 	}
 
 	return nents;
 }
 
-static int dma_noop_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return 0;
-}
-
-static int dma_noop_supported(struct device *dev, u64 mask)
-{
-	return 1;
-}
-
 const struct dma_map_ops dma_noop_ops = {
 	.alloc			= dma_noop_alloc,
 	.free			= dma_noop_free,
 	.map_page		= dma_noop_map_page,
 	.map_sg			= dma_noop_map_sg,
-	.mapping_error		= dma_noop_mapping_error,
-	.dma_supported		= dma_noop_supported,
 };
 
 EXPORT_SYMBOL(dma_noop_ops);
diff --git a/lib/dma-virt.c b/lib/dma-virt.c
index dcd4df1f7174..5c4f11329721 100644
--- a/lib/dma-virt.c
+++ b/lib/dma-virt.c
@@ -51,22 +51,10 @@ static int dma_virt_map_sg(struct device *dev, struct scatterlist *sgl,
 	return nents;
 }
 
-static int dma_virt_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return false;
-}
-
-static int dma_virt_supported(struct device *dev, u64 mask)
-{
-	return true;
-}
-
 const struct dma_map_ops dma_virt_ops = {
 	.alloc			= dma_virt_alloc,
 	.free			= dma_virt_free,
 	.map_page		= dma_virt_map_page,
 	.map_sg			= dma_virt_map_sg,
-	.mapping_error		= dma_virt_mapping_error,
-	.dma_supported		= dma_virt_supported,
 };
 EXPORT_SYMBOL(dma_virt_ops);
diff --git a/lib/errseq.c b/lib/errseq.c
new file mode 100644
index 000000000000..841fa24e6e00
--- /dev/null
+++ b/lib/errseq.c
@@ -0,0 +1,208 @@
+#include <linux/err.h>
+#include <linux/bug.h>
+#include <linux/atomic.h>
+#include <linux/errseq.h>
+
+/*
+ * An errseq_t is a way of recording errors in one place, and allowing any
+ * number of "subscribers" to tell whether it has changed since a previous
+ * point where it was sampled.
+ *
+ * It's implemented as an unsigned 32-bit value. The low order bits are
+ * designated to hold an error code (between 0 and -MAX_ERRNO). The upper bits
+ * are used as a counter. This is done with atomics instead of locking so that
+ * these functions can be called from any context.
+ *
+ * The general idea is for consumers to sample an errseq_t value. That value
+ * can later be used to tell whether any new errors have occurred since that
+ * sampling was done.
+ *
+ * Note that there is a risk of collisions if new errors are being recorded
+ * frequently, since we have so few bits to use as a counter.
+ *
+ * To mitigate this, one bit is used as a flag to tell whether the value has
+ * been sampled since a new value was recorded. That allows us to avoid bumping
+ * the counter if no one has sampled it since the last time an error was
+ * recorded.
+ *
+ * A new errseq_t should always be zeroed out.  A errseq_t value of all zeroes
+ * is the special (but common) case where there has never been an error. An all
+ * zero value thus serves as the "epoch" if one wishes to know whether there
+ * has ever been an error set since it was first initialized.
+ */
+
+/* The low bits are designated for error code (max of MAX_ERRNO) */
+#define ERRSEQ_SHIFT		ilog2(MAX_ERRNO + 1)
+
+/* This bit is used as a flag to indicate whether the value has been seen */
+#define ERRSEQ_SEEN		(1 << ERRSEQ_SHIFT)
+
+/* The lowest bit of the counter */
+#define ERRSEQ_CTR_INC		(1 << (ERRSEQ_SHIFT + 1))
+
+/**
+ * __errseq_set - set a errseq_t for later reporting
+ * @eseq: errseq_t field that should be set
+ * @err: error to set
+ *
+ * This function sets the error in *eseq, and increments the sequence counter
+ * if the last sequence was sampled at some point in the past.
+ *
+ * Any error set will always overwrite an existing error.
+ *
+ * Most callers will want to use the errseq_set inline wrapper to efficiently
+ * handle the common case where err is 0.
+ *
+ * We do return an errseq_t here, primarily for debugging purposes. The return
+ * value should not be used as a previously sampled value in later calls as it
+ * will not have the SEEN flag set.
+ */
+errseq_t __errseq_set(errseq_t *eseq, int err)
+{
+	errseq_t cur, old;
+
+	/* MAX_ERRNO must be able to serve as a mask */
+	BUILD_BUG_ON_NOT_POWER_OF_2(MAX_ERRNO + 1);
+
+	/*
+	 * Ensure the error code actually fits where we want it to go. If it
+	 * doesn't then just throw a warning and don't record anything. We
+	 * also don't accept zero here as that would effectively clear a
+	 * previous error.
+	 */
+	old = READ_ONCE(*eseq);
+
+	if (WARN(unlikely(err == 0 || (unsigned int)-err > MAX_ERRNO),
+				"err = %d\n", err))
+		return old;
+
+	for (;;) {
+		errseq_t new;
+
+		/* Clear out error bits and set new error */
+		new = (old & ~(MAX_ERRNO|ERRSEQ_SEEN)) | -err;
+
+		/* Only increment if someone has looked at it */
+		if (old & ERRSEQ_SEEN)
+			new += ERRSEQ_CTR_INC;
+
+		/* If there would be no change, then call it done */
+		if (new == old) {
+			cur = new;
+			break;
+		}
+
+		/* Try to swap the new value into place */
+		cur = cmpxchg(eseq, old, new);
+
+		/*
+		 * Call it success if we did the swap or someone else beat us
+		 * to it for the same value.
+		 */
+		if (likely(cur == old || cur == new))
+			break;
+
+		/* Raced with an update, try again */
+		old = cur;
+	}
+	return cur;
+}
+EXPORT_SYMBOL(__errseq_set);
+
+/**
+ * errseq_sample - grab current errseq_t value
+ * @eseq: pointer to errseq_t to be sampled
+ *
+ * This function allows callers to sample an errseq_t value, marking it as
+ * "seen" if required.
+ */
+errseq_t errseq_sample(errseq_t *eseq)
+{
+	errseq_t old = READ_ONCE(*eseq);
+	errseq_t new = old;
+
+	/*
+	 * For the common case of no errors ever having been set, we can skip
+	 * marking the SEEN bit. Once an error has been set, the value will
+	 * never go back to zero.
+	 */
+	if (old != 0) {
+		new |= ERRSEQ_SEEN;
+		if (old != new)
+			cmpxchg(eseq, old, new);
+	}
+	return new;
+}
+EXPORT_SYMBOL(errseq_sample);
+
+/**
+ * errseq_check - has an error occurred since a particular sample point?
+ * @eseq: pointer to errseq_t value to be checked
+ * @since: previously-sampled errseq_t from which to check
+ *
+ * Grab the value that eseq points to, and see if it has changed "since"
+ * the given value was sampled. The "since" value is not advanced, so there
+ * is no need to mark the value as seen.
+ *
+ * Returns the latest error set in the errseq_t or 0 if it hasn't changed.
+ */
+int errseq_check(errseq_t *eseq, errseq_t since)
+{
+	errseq_t cur = READ_ONCE(*eseq);
+
+	if (likely(cur == since))
+		return 0;
+	return -(cur & MAX_ERRNO);
+}
+EXPORT_SYMBOL(errseq_check);
+
+/**
+ * errseq_check_and_advance - check an errseq_t and advance to current value
+ * @eseq: pointer to value being checked and reported
+ * @since: pointer to previously-sampled errseq_t to check against and advance
+ *
+ * Grab the eseq value, and see whether it matches the value that "since"
+ * points to. If it does, then just return 0.
+ *
+ * If it doesn't, then the value has changed. Set the "seen" flag, and try to
+ * swap it into place as the new eseq value. Then, set that value as the new
+ * "since" value, and return whatever the error portion is set to.
+ *
+ * Note that no locking is provided here for concurrent updates to the "since"
+ * value. The caller must provide that if necessary. Because of this, callers
+ * may want to do a lockless errseq_check before taking the lock and calling
+ * this.
+ */
+int errseq_check_and_advance(errseq_t *eseq, errseq_t *since)
+{
+	int err = 0;
+	errseq_t old, new;
+
+	/*
+	 * Most callers will want to use the inline wrapper to check this,
+	 * so that the common case of no error is handled without needing
+	 * to take the lock that protects the "since" value.
+	 */
+	old = READ_ONCE(*eseq);
+	if (old != *since) {
+		/*
+		 * Set the flag and try to swap it into place if it has
+		 * changed.
+		 *
+		 * We don't care about the outcome of the swap here. If the
+		 * swap doesn't occur, then it has either been updated by a
+		 * writer who is altering the value in some way (updating
+		 * counter or resetting the error), or another reader who is
+		 * just setting the "seen" flag. Either outcome is OK, and we
+		 * can advance "since" and return an error based on what we
+		 * have.
+		 */
+		new = old | ERRSEQ_SEEN;
+		if (new != old)
+			cmpxchg(eseq, old, new);
+		*since = new;
+		err = -(new & MAX_ERRNO);
+	}
+	return err;
+}
+EXPORT_SYMBOL(errseq_check_and_advance);
diff --git a/lib/extable.c b/lib/extable.c
index 62968daa66a9..f54996fdd0b8 100644
--- a/lib/extable.c
+++ b/lib/extable.c
@@ -9,6 +9,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 
+#include <linux/bsearch.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/sort.h>
@@ -51,7 +52,7 @@ static void swap_ex(void *a, void *b, int size)
  * This is used both for the kernel exception table and for
  * the exception tables of modules that get loaded.
  */
-static int cmp_ex(const void *a, const void *b)
+static int cmp_ex_sort(const void *a, const void *b)
 {
 	const struct exception_table_entry *x = a, *y = b;
 
@@ -67,7 +68,7 @@ void sort_extable(struct exception_table_entry *start,
 		  struct exception_table_entry *finish)
 {
 	sort(start, finish - start, sizeof(struct exception_table_entry),
-	     cmp_ex, swap_ex);
+	     cmp_ex_sort, swap_ex);
 }
 
 #ifdef CONFIG_MODULES
@@ -93,6 +94,20 @@ void trim_init_extable(struct module *m)
 #endif /* !ARCH_HAS_SORT_EXTABLE */
 
 #ifndef ARCH_HAS_SEARCH_EXTABLE
+
+static int cmp_ex_search(const void *key, const void *elt)
+{
+	const struct exception_table_entry *_elt = elt;
+	unsigned long _key = *(unsigned long *)key;
+
+	/* avoid overflow */
+	if (_key > ex_to_insn(_elt))
+		return 1;
+	if (_key < ex_to_insn(_elt))
+		return -1;
+	return 0;
+}
+
 /*
  * Search one exception table for an entry corresponding to the
  * given instruction address, and return the address of the entry,
@@ -101,25 +116,11 @@ void trim_init_extable(struct module *m)
  * already sorted.
  */
 const struct exception_table_entry *
-search_extable(const struct exception_table_entry *first,
-	       const struct exception_table_entry *last,
+search_extable(const struct exception_table_entry *base,
+	       const size_t num,
 	       unsigned long value)
 {
-	while (first <= last) {
-		const struct exception_table_entry *mid;
-
-		mid = ((last - first) >> 1) + first;
-		/*
-		 * careful, the distance between value and insn
-		 * can be larger than MAX_LONG:
-		 */
-		if (ex_to_insn(mid) < value)
-			first = mid + 1;
-		else if (ex_to_insn(mid) > value)
-			last = mid - 1;
-		else
-			return mid;
-	}
-	return NULL;
+	return bsearch(&value, base, num,
+		       sizeof(struct exception_table_entry), cmp_ex_search);
 }
 #endif
diff --git a/lib/fault-inject.c b/lib/fault-inject.c
index 4ff157159a0d..7d315fdb9f13 100644
--- a/lib/fault-inject.c
+++ b/lib/fault-inject.c
@@ -107,6 +107,15 @@ static inline bool fail_stacktrace(struct fault_attr *attr)