Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

2 files changed, 388 insertions, 0 deletions

diff --git a/lib/raid/raid6/tests/Makefile b/lib/raid/raid6/tests/Makefile
new file mode 100644
index 000000000..87a001b22
--- /dev/null
+++ b/lib/raid/raid6/tests/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_RAID6_PQ_KUNIT_TEST)	+= raid6_kunit.o
diff --git a/lib/raid/raid6/tests/raid6_kunit.c b/lib/raid/raid6/tests/raid6_kunit.c
new file mode 100644
index 000000000..7d0a1ec98
--- /dev/null
+++ b/lib/raid/raid6/tests/raid6_kunit.c
@@ -0,0 +1,385 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2002-2007 H. Peter Anvin - All Rights Reserved
+ *
+ * Test RAID-6 recovery algorithms.
+ */
+
+#include <kunit/test.h>
+#include <linux/prandom.h>
+#include <linux/vmalloc.h>
+#include <linux/raid/pq.h>
+#include "../algos.h"
+
+MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING");
+
+#define RAID6_KUNIT_SEED		42
+#define RAID6_KUNIT_NUM_TEST_ITERS	10
+#define RAID6_KUNIT_MAX_BUFFERS		64 /* Including P and Q */
+#define RAID6_KUNIT_MAX_FAILURES	2
+#define RAID6_KUNIT_MAX_BYTES		PAGE_SIZE
+#define RAID6_KUNIT_ALLOC_BYTES		SZ_16K
+
+static struct rnd_state rng;
+static void *test_buffers[RAID6_KUNIT_MAX_BUFFERS];
+static void *aligned_buffers[RAID6_KUNIT_MAX_BUFFERS];
+static void *test_recov_buffers[RAID6_KUNIT_MAX_FAILURES];
+static size_t test_buflen;
+
+struct test_args {
+	unsigned int recov_idx;
+	const struct raid6_recov_calls *recov;
+	unsigned int gen_idx;
+	const struct raid6_calls *gen;
+};
+
+static struct test_args args;
+
+static u32 rand32(void)
+{
+	return prandom_u32_state(&rng);
+}
+
+/* Generate a random length that is a multiple of 512. */
+static unsigned int random_length(unsigned int max_length)
+{
+	return round_up((rand32() % max_length) + 1, 512);
+}
+
+static unsigned int random_nr_buffers(void)
+{
+	return (rand32() % (RAID6_KUNIT_MAX_BUFFERS - (RAID6_MIN_DISKS - 1))) +
+			RAID6_MIN_DISKS;
+}
+
+/* Generate a random alignment that is a multiple of 64. */
+static unsigned int random_alignment(unsigned int max_alignment)
+{
+	if (max_alignment == 0)
+		return 0;
+	return (rand32() % (max_alignment + 1)) & ~63;
+}
+
+static void makedata(int start, int stop)
+{
+	int i;
+
+	for (i = start; i <= stop; i++)
+		prandom_bytes_state(&rng, test_buffers[i], test_buflen);
+}
+
+static char member_type(unsigned int nr_buffers, int d)
+{
+	if (d == nr_buffers - 2)
+		return 'P';
+	if (d == nr_buffers - 1)
+		return 'Q';
+	return 'D';
+}
+
+static void test_recover_one(struct kunit *test, unsigned int nr_buffers,
+		unsigned int len, int faila, int failb)
+{
+	const struct test_args *ta = test->param_value;
+	void *dataptrs[RAID6_KUNIT_MAX_BUFFERS];
+	int i;
+
+	if (faila > failb)
+		swap(faila, failb);
+
+	for (i = 0; i < RAID6_KUNIT_MAX_FAILURES; i++)
+		memset(test_recov_buffers[i], 0xf0, test_buflen);
+
+	memcpy(dataptrs, aligned_buffers, sizeof(dataptrs));
+	dataptrs[faila] = test_recov_buffers[0];
+	dataptrs[failb] = test_recov_buffers[1];
+
+	if (failb == nr_buffers - 1) {
+		/*
+		 * We don't implement the data+Q failure scenario, since it
+		 * is equivalent to a RAID-5 failure (XOR, then recompute Q).
+		 */
+		if (WARN_ON_ONCE(faila != nr_buffers - 2))
+			return;
+
+		/* P+Q failure.  Just rebuild the syndrome. */
+		ta->gen->gen_syndrome(nr_buffers, len, dataptrs);
+	} else if (failb == nr_buffers - 2) {
+		/* data+P failure. */
+		ta->recov->datap(nr_buffers, len, faila, dataptrs);
+	} else {
+		/* data+data failure. */
+		ta->recov->data2(nr_buffers, len, faila, failb, dataptrs);
+	}
+
+	KUNIT_EXPECT_MEMEQ_MSG(test, aligned_buffers[faila], dataptrs[faila],
+			len,
+			"faila miscompared: %3d[%c] buffers %u len %u (failb=%3d[%c])\n",
+			faila, member_type(nr_buffers, faila),
+			nr_buffers, len,
+			failb, member_type(nr_buffers, failb));
+	KUNIT_EXPECT_MEMEQ_MSG(test, aligned_buffers[failb], dataptrs[failb],
+			len,
+			"failb miscompared: %3d[%c] buffers %u len %u (faila=%3d[%c])\n",
+			failb, member_type(nr_buffers, failb),
+			nr_buffers, len,
+			faila, member_type(nr_buffers, faila));
+}
+
+static void test_recover(struct kunit *test, unsigned int nr_buffers,
+		unsigned int len)
+{
+	unsigned int nr_data = nr_buffers - 2;
+	int iterations, i;
+
+	/* Test P+Q recovery */
+	test_recover_one(test, nr_buffers, len, nr_data, nr_buffers - 1);
+
+	/* Test data+P recovery */
+	for (i = 0; i < nr_buffers - 2; i++)
+		test_recover_one(test, nr_buffers, len, i, nr_data);
+
+	/* Double data failure is impossible with a single data disk */
+	if (nr_data == 1)
+		return;
+
+	/* Test data+data recovery using random sampling */
+	iterations = nr_buffers * 2; /* should provide good enough coverage */
+	for (i = 0; i < iterations; i++) {
+		int faila = rand32() % nr_data, failb;
+
+		do {
+			failb = rand32() % nr_data;
+		} while (failb == faila);
+
+		test_recover_one(test, nr_buffers, len, faila, failb);
+	}
+}
+
+/* Simulate rmw run */
+static void test_rmw_one(struct kunit *test, unsigned int nr_buffers,
+		unsigned int len, int p1, int p2)
+{
+	const struct test_args *ta = test->param_value;
+
+	ta->gen->xor_syndrome(nr_buffers, p1, p2, len, aligned_buffers);
+	makedata(p1, p2);
+	ta->gen->xor_syndrome(nr_buffers, p1, p2, len, aligned_buffers);
+	test_recover(test, nr_buffers, len);
+}
+
+static void test_rmw(struct kunit *test, unsigned int nr_buffers,
+		unsigned int len)
+{
+	int iterations = nr_buffers / 2, i;
+
+	for (i = 0; i < iterations; i++) {
+		int p1 = rand32() % (nr_buffers - 2);
+		int p2 = rand32() % (nr_buffers - 2);
+
+		if (p2 < p1)
+			swap(p1, p2);
+		test_rmw_one(test, nr_buffers, len, p1, p2);
+	}
+}
+
+static void raid6_test_one(struct kunit *test)
+{
+	const struct test_args *ta = test->param_value;
+	unsigned int nr_buffers = random_nr_buffers();
+	unsigned int len = random_length(RAID6_KUNIT_MAX_BYTES);
+	unsigned int max_alignment;
+	int i;
+
+	/* Nuke syndromes */
+	memset(test_buffers[nr_buffers - 2], 0xee, test_buflen);
+	memset(test_buffers[nr_buffers - 1], 0xee, test_buflen);
+
+	/*
+	 * If we're not using the entire buffer size, inject randomize alignment
+	 * into the buffer.
+	 */
+	max_alignment = RAID6_KUNIT_MAX_BYTES - len;
+	if (rand32() % 2 == 0) {
+		/* Use random alignments mod 64 */
+		for (i = 0; i < nr_buffers; i++)
+			aligned_buffers[i] = test_buffers[i] +
+				random_alignment(max_alignment);
+	} else {
+		/* Go up to the guard page, to catch buffer overreads */
+		unsigned int align = test_buflen - len;
+
+		for (i = 0; i < nr_buffers; i++)
+			aligned_buffers[i] = test_buffers[i] + align;
+	}
+
+	/* Generate assumed good syndrome */
+	ta->gen->gen_syndrome(nr_buffers, len, aligned_buffers);
+
+	test_recover(test, nr_buffers, len);
+
+	if (ta->gen->xor_syndrome)
+		test_rmw(test, nr_buffers, len);
+}
+
+static void raid6_test(struct kunit *test)
+{
+	int i;
+
+	for (i = 0; i < RAID6_KUNIT_NUM_TEST_ITERS; i++)
+		raid6_test_one(test);
+}
+
+static void raid6_benchmark(struct kunit *test)
+{
+	static const unsigned int nr_to_test[] = {
+		4, 5, 6, 7, 8, 10, 12, 15, 16, 32,
+	};
+	static const unsigned int len_to_test[] = {
+		SZ_4K, SZ_16K,
+	};
+	unsigned int i, j, l;
+	u64 t;
+
+	if (!IS_ENABLED(CONFIG_RAID6_PQ_KUNIT_BENCHMARK))
+		kunit_skip(test, "not enabled");
+
+	/* warm-up */
+	for (i = 0; i < ARRAY_SIZE(nr_to_test); i++) {
+		for (j = 0; j < ARRAY_SIZE(len_to_test); j++) {
+			for (l = 0; l < 10; l++) {
+				raid6_gen_syndrome(nr_to_test[i],
+						len_to_test[j], test_buffers);
+			}
+		}
+	}
+
+	/*
+	 * Preferably this would be a loop over len_to_test, but the kunit
+	 * logging always adds a newline to each logged format string.
+	 */
+	static_assert(ARRAY_SIZE(len_to_test) == 2);
+	kunit_info(test, "          \t%5u bytes\t%5u bytes\n",
+			len_to_test[0], len_to_test[1]);
+
+	for (i = 0; i < ARRAY_SIZE(nr_to_test); i++) {
+		unsigned int nr = nr_to_test[i];
+		u64 speed[ARRAY_SIZE(len_to_test)];
+
+		KUNIT_ASSERT_LE(test, nr, RAID6_KUNIT_MAX_BUFFERS);
+
+		for (j = 0; j < ARRAY_SIZE(len_to_test); j++) {
+			unsigned int len = len_to_test[j];
+			const unsigned long num_iters = 1000;
+
+			KUNIT_ASSERT_GT(test, len, 0);
+			KUNIT_ASSERT_LE(test, len, RAID6_KUNIT_ALLOC_BYTES);
+
+			preempt_disable();
+			t = ktime_get_ns();
+			for (l = 0; l < num_iters; l++)
+				raid6_gen_syndrome(nr_to_test[i],
+						len_to_test[j], test_buffers);
+			t = max(ktime_get_ns() - t, 1);
+			preempt_enable();
+
+			speed[j] = div64_u64((u64)len * num_iters * nr, t);
+		}
+
+		static_assert(ARRAY_SIZE(len_to_test) == 2);
+		kunit_info(test, "%3u disks:\t%5llu  GB/s\t%5llu  GB/s\n",
+				nr, speed[0], speed[1]);
+	}
+}
+
+static const void *raid6_gen_params(struct kunit *test, const void *prev,
+		char *desc)
+{
+	if (!prev) {
+		memset(&args, 0, sizeof(args));
+next_algo:
+		args.recov_idx = 0;
+		args.gen = raid6_algo_find(args.gen_idx);
+		if (!args.gen)
+			return NULL;
+	}
+
+	if (args.recov)
+		args.recov_idx++;
+	args.recov = raid6_recov_algo_find(args.recov_idx);
+	if (!args.recov) {
+		args.gen_idx++;
+		goto next_algo;
+	}
+
+	snprintf(desc, KUNIT_PARAM_DESC_SIZE, "gen=%s recov=%s",
+			args.gen->name, args.recov->name);
+	return &args;
+}
+
+static struct kunit_case raid6_test_cases[] = {
+	KUNIT_CASE_PARAM(raid6_test, raid6_gen_params),
+	KUNIT_CASE(raid6_benchmark),
+	{},
+};
+
+static int raid6_suite_init(struct kunit_suite *suite)
+{
+	int i;
+
+	prandom_seed_state(&rng, RAID6_KUNIT_SEED);
+
+	/*
+	 * Allocate the test buffer using vmalloc() with a page-aligned length
+	 * so that it is immediately followed by a guard page.  This allows
+	 * buffer overreads to be detected, even in assembly code.
+	 */
+	test_buflen = round_up(RAID6_KUNIT_ALLOC_BYTES, PAGE_SIZE);
+	for (i = 0; i < RAID6_KUNIT_MAX_FAILURES; i++) {
+		test_recov_buffers[i] = vmalloc(test_buflen);
+		if (!test_recov_buffers[i])
+			goto out_free_recov_buffers;
+	}
+	for (i = 0; i < RAID6_KUNIT_MAX_BUFFERS; i++) {
+		test_buffers[i] = vmalloc(test_buflen);
+		if (!test_buffers[i])
+			goto out_free_buffers;
+	}
+
+	makedata(0, RAID6_KUNIT_MAX_BUFFERS - 1);
+
+	return 0;
+
+out_free_buffers:
+	for (i = 0; i < RAID6_KUNIT_MAX_BUFFERS; i++)
+		vfree(test_buffers[i]);
+	memset(test_buffers, 0, sizeof(test_buffers));
+out_free_recov_buffers:
+	for (i = 0; i < RAID6_KUNIT_MAX_FAILURES; i++)
+		vfree(test_recov_buffers[i]);
+	memset(test_recov_buffers, 0, sizeof(test_recov_buffers));
+	return -ENOMEM;
+}
+
+static void raid6_suite_exit(struct kunit_suite *suite)
+{
+	int i;
+
+	for (i = 0; i < RAID6_KUNIT_MAX_BUFFERS; i++)
+		vfree(test_buffers[i]);
+	memset(test_buffers, 0, sizeof(test_buffers));
+	for (i = 0; i < RAID6_KUNIT_MAX_FAILURES; i++)
+		vfree(test_recov_buffers[i]);
+	memset(test_recov_buffers, 0, sizeof(test_recov_buffers));
+}
+
+static struct kunit_suite raid6_test_suite = {
+	.name		= "raid6",
+	.test_cases	= raid6_test_cases,
+	.suite_init	= raid6_suite_init,
+	.suite_exit	= raid6_suite_exit,
+};
+kunit_test_suite(raid6_test_suite);
+
+MODULE_DESCRIPTION("Unit test for the RAID P/Q library functions");
+MODULE_LICENSE("GPL");