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

1 files changed, 387 insertions, 0 deletions

diff --git a/lib/raid/raid6/algos.c b/lib/raid/raid6/algos.c
new file mode 100644
index 000000000..011aa9d0e
--- /dev/null
+++ b/lib/raid/raid6/algos.c
@@ -0,0 +1,387 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright 2002 H. Peter Anvin - All Rights Reserved
+ *
+ * Algorithm list and algorithm selection for RAID-6
+ */
+
+#include <linux/module.h>
+#include <linux/gfp.h>
+#include <linux/raid/pq.h>
+#include <linux/slab.h>
+#include <linux/static_call.h>
+#include <kunit/visibility.h>
+#include "algos.h"
+
+#define RAID6_MAX_ALGOS		16
+static const struct raid6_calls *raid6_algos[RAID6_MAX_ALGOS];
+static unsigned int raid6_nr_algos;
+static const struct raid6_recov_calls *raid6_recov_algo;
+
+/* Selected algorithm */
+DEFINE_STATIC_CALL_NULL(raid6_gen_syndrome_impl, *raid6_intx1.gen_syndrome);
+DEFINE_STATIC_CALL_NULL(raid6_xor_syndrome_impl, *raid6_intx1.xor_syndrome);
+DEFINE_STATIC_CALL_NULL(raid6_recov_2data_impl, *raid6_recov_intx1.data2);
+DEFINE_STATIC_CALL_NULL(raid6_recov_datap_impl, *raid6_recov_intx1.datap);
+
+/**
+ * raid6_gen_syndrome - generate RAID6 P/Q parity
+ * @disks:	number of "disks" to operate on including parity
+ * @bytes:	length in bytes of each vector
+ * @ptrs:	@disks size array of memory pointers
+ *
+ * Generate @bytes worth of RAID6 P and Q parity in @ptrs[@disks - 2] and
+ * @ptrs[@disks - 1] respectively from the memory pointed to by @ptrs[0] to
+ * @ptrs[@disks - 3].
+ *
+ * @disks must be at least 4, and the memory pointed to by each member of @ptrs
+ * must be at least 64-byte aligned.  @bytes must be non-zero and a multiple of
+ * 512.
+ *
+ * See https://kernel.org/pub/linux/kernel/people/hpa/raid6.pdf for underlying
+ * algorithm.
+ */
+void raid6_gen_syndrome(int disks, size_t bytes, void **ptrs)
+{
+	WARN_ON_ONCE(!in_task() || irqs_disabled() || softirq_count());
+	WARN_ON_ONCE(bytes & 511);
+	WARN_ON_ONCE(disks < RAID6_MIN_DISKS);
+
+	static_call(raid6_gen_syndrome_impl)(disks, bytes, ptrs);
+}
+EXPORT_SYMBOL_GPL(raid6_gen_syndrome);
+
+/**
+ * raid6_xor_syndrome - update RAID6 P/Q parity
+ * @disks:	number of "disks" to operate on including parity
+ * @start:	first index into @disk to update
+ * @stop:	last index into @disk to update
+ * @bytes:	length in bytes of each vector
+ * @ptrs:	@disks size array of memory pointers
+ *
+ * Update @bytes worth of RAID6 P and Q parity in @ptrs[@disks - 2] and
+ * @ptrs[@disks - 1] respectively for the memory pointed to by
+ * @ptrs[@start..@stop].
+ *
+ * This is used to update parity in place using the following sequence:
+ *
+ * 1) call raid6_xor_syndrome(disk, start, stop, ...) for the existing data.
+ * 2) update the the data in @ptrs[@start..@stop].
+ * 3) call raid6_xor_syndrome(disk, start, stop, ...) for the new data.
+ *
+ * Data between @start and @stop that is not changed should be filled
+ * with a pointer to the kernel zero page.
+ *
+ * @disks must be at least 4, and the memory pointed to by each member of @ptrs
+ * must be at least 64-byte aligned.  @bytes must be non-zero and a multiple of
+ * 512.  @stop must be larger or equal to @start.
+ */
+void raid6_xor_syndrome(int disks, int start, int stop, size_t bytes,
+		void **ptrs)
+{
+	WARN_ON_ONCE(!in_task() || irqs_disabled() || softirq_count());
+	WARN_ON_ONCE(bytes & 511);
+	WARN_ON_ONCE(disks < RAID6_MIN_DISKS);
+	WARN_ON_ONCE(stop < start);
+
+	static_call(raid6_xor_syndrome_impl)(disks, start, stop, bytes, ptrs);
+}
+EXPORT_SYMBOL_GPL(raid6_xor_syndrome);
+
+/*
+ * raid6_can_xor_syndrome - check if raid6_xor_syndrome() can be used
+ *
+ * Returns %true if raid6_can_xor_syndrome() can be used, else %false.
+ */
+bool raid6_can_xor_syndrome(void)
+{
+	return !!static_call_query(raid6_xor_syndrome_impl);
+}
+EXPORT_SYMBOL_GPL(raid6_can_xor_syndrome);
+
+/**
+ * raid6_recov_2data - recover two missing data disks
+ * @disks:	number of "disks" to operate on including parity
+ * @bytes:	length in bytes of each vector
+ * @faila:	first failed data disk index
+ * @failb:	second failed data disk index
+ * @ptrs:	@disks size array of memory pointers
+ *
+ * Rebuild @bytes of missing data in @ptrs[@faila] and @ptrs[@failb] from the
+ * data in the remaining disks and the two parities pointed to by the other
+ * indices between 0 and @disks - 1 in @ptrs.  @disks includes the data disks
+ * and the two parities.  @faila must be smaller than @failb.
+ *
+ * Memory pointed to by each pointer in @ptrs must be page aligned and is
+ * limited to %PAGE_SIZE.
+ */
+void raid6_recov_2data(int disks, size_t bytes, int faila, int failb,
+		void **ptrs)
+{
+	WARN_ON_ONCE(!in_task() || irqs_disabled() || softirq_count());
+	WARN_ON_ONCE(bytes & 511);
+	WARN_ON_ONCE(bytes > PAGE_SIZE);
+	WARN_ON_ONCE(failb <= faila);
+
+	static_call(raid6_recov_2data_impl)(disks, bytes, faila, failb, ptrs);
+}
+EXPORT_SYMBOL_GPL(raid6_recov_2data);
+
+/**
+ * raid6_recov_datap - recover a missing data disk and missing P-parity
+ * @disks:	number of "disks" to operate on including parity
+ * @bytes:	length in bytes of each vector
+ * @faila:	failed data disk index
+ * @ptrs:	@disks size array of memory pointers
+ *
+ * Rebuild @bytes of missing data in @ptrs[@faila] and the missing P-parity in
+ * @ptrs[@disks - 2] from the data in the remaining disks and the Q-parity
+ * pointed to by the other indices between 0 and @disks - 1 in @ptrs.  @disks
+ * includes the data disks and the two parities.
+ *
+ * Memory pointed to by each pointer in @ptrs must be page aligned and is
+ * limited to %PAGE_SIZE.
+ */
+void raid6_recov_datap(int disks, size_t bytes, int faila, void **ptrs)
+{
+	WARN_ON_ONCE(!in_task() || irqs_disabled() || softirq_count());
+	WARN_ON_ONCE(bytes & 511);
+	WARN_ON_ONCE(bytes > PAGE_SIZE);
+
+	static_call(raid6_recov_datap_impl)(disks, bytes, faila, ptrs);
+}
+EXPORT_SYMBOL_GPL(raid6_recov_datap);
+
+#define BENCH_SIZE	SZ_4K
+#define NR_SRCS		8
+#define NR_DISKS	(NR_SRCS + 2)
+#define REPS		800U
+
+static int raid6_choose_gen(void *dptrs[NR_DISKS], const int disks)
+{
+	const struct raid6_calls *best = NULL;
+	unsigned long bestgenperf = 0;
+	unsigned int i;
+
+	for (i = 0; i < raid6_nr_algos; i++) {
+		const struct raid6_calls *algo = raid6_algos[i];
+		unsigned long perf = 0;
+		u64 t;
+		int i;
+
+		preempt_disable();
+		t = ktime_get_ns();
+		for (i = 0; i < REPS; i++)
+			algo->gen_syndrome(disks, BENCH_SIZE, dptrs);
+		t = max(ktime_get_ns() - t, 1);
+		preempt_enable();
+
+		/* bytes/ns == GB/s, multiply by 1000 to get MB/s [not MiB/s] */
+		perf = div64_u64((u64)BENCH_SIZE * REPS * NR_SRCS * 1000, t);
+		if (perf > bestgenperf) {
+			bestgenperf = perf;
+			best = algo;
+		}
+		pr_info("raid6: %-8s gen() %5lu MB/s\n", algo->name, perf);
+	}
+
+	if (!best) {
+		pr_err("raid6: Yikes! No algorithm found!\n");
+		return -EINVAL;
+	}
+
+	static_call_update(raid6_gen_syndrome_impl, best->gen_syndrome);
+	static_call_update(raid6_xor_syndrome_impl, best->xor_syndrome);
+
+	pr_info("raid6: using algorithm %s gen() %ld MB/s\n",
+		best->name, bestgenperf);
+
+	if (best->xor_syndrome) {
+		/* work on the second half of the disks */
+		int start = (disks / 2) - 1, stop = disks - 3;
+		u64 t;
+
+		preempt_disable();
+		t = ktime_get_ns();
+		for (i = 0; i < REPS; i++)
+			best->xor_syndrome(disks, start, stop, BENCH_SIZE,
+				dptrs);
+		t = max(ktime_get_ns() - t, 1);
+		preempt_enable();
+
+		pr_info("raid6: .... xor() %llu MB/s, rmw enabled\n",
+			div64_u64((u64)BENCH_SIZE * REPS * NR_SRCS / 2 * 1000,
+				t));
+	}
+
+	return 0;
+}
+
+
+/* Try to pick the best algorithm */
+/* This code uses the gfmul table as convenient data set to abuse */
+
+static int __init raid6_select_algo(void)
+{
+	const int disks = NR_DISKS;
+	void *dptrs[NR_DISKS];
+	char *disk_ptr, *p;
+	int i, cycle;
+	int error;
+
+	if (!IS_ENABLED(CONFIG_RAID6_PQ_BENCHMARK) || raid6_nr_algos == 1) {
+		pr_info("raid6: skipped pq benchmark and selected %s\n",
+			raid6_algos[raid6_nr_algos - 1]->name);
+		return 0;
+	}
+
+	/* prepare the buffer and fill it circularly with gfmul table */
+	disk_ptr = kmalloc_array(NR_DISKS, BENCH_SIZE, GFP_KERNEL);
+	if (!disk_ptr) {
+		pr_err("raid6: Yikes!  No memory available.\n");
+		return -ENOMEM;
+	}
+
+	p = disk_ptr;
+	for (i = 0; i < disks; i++)
+		dptrs[i] = p + BENCH_SIZE * i;
+
+	cycle = ((disks - 2) * BENCH_SIZE) / 65536;
+	for (i = 0; i < cycle; i++) {
+		memcpy(p, raid6_gfmul, 65536);
+		p += 65536;
+	}
+
+	if ((disks - 2) * BENCH_SIZE % 65536)
+		memcpy(p, raid6_gfmul, (disks - 2) * BENCH_SIZE % 65536);
+
+	/* select raid gen_syndrome function */
+	error = raid6_choose_gen(dptrs, disks);
+
+	kfree(disk_ptr);
+
+	return error;
+}
+
+/*
+ * Register a RAID6 P/Q generation algorithm.  The most optimized/unrolled
+ * implementation should be registered last so it will be selected when the
+ * boot-time benchmark is disabled.
+ */
+void __init raid6_algo_add(const struct raid6_calls *algo)
+{
+	if (WARN_ON_ONCE(raid6_nr_algos == RAID6_MAX_ALGOS))
+		return;
+	raid6_algos[raid6_nr_algos++] = algo;
+}
+
+void __init raid6_algo_add_default(void)
+{
+	raid6_algo_add(&raid6_intx1);
+	raid6_algo_add(&raid6_intx2);
+	raid6_algo_add(&raid6_intx4);
+	raid6_algo_add(&raid6_intx8);
+}
+
+void __init raid6_recov_algo_add(const struct raid6_recov_calls *algo)
+{
+	if (WARN_ON_ONCE(raid6_recov_algo))
+		return;
+	raid6_recov_algo = algo;
+}
+
+#ifdef CONFIG_RAID6_PQ_ARCH
+#include "pq_arch.h"
+#else
+static inline void arch_raid6_init(void)
+{
+	raid6_algo_add_default();
+}
+#endif /* CONFIG_RAID6_PQ_ARCH */
+
+static int __init raid6_init(void)
+{
+	/*
+	 * Architectures providing arch_raid6_init must add all PQ generation
+	 * algorithms they want to consider in arch_raid6_init(), including
+	 * the generic ones using raid6_algo_add_default() if wanted.
+	 */
+	arch_raid6_init();
+
+	/*
+	 * Architectures don't have to set a recovery algorithm, we'll just pick
+	 * the generic integer one if none was set.
+	 */
+	if (!raid6_recov_algo)
+		raid6_recov_algo = &raid6_recov_intx1;
+	static_call_update(raid6_recov_2data_impl, raid6_recov_algo->data2);
+	static_call_update(raid6_recov_datap_impl, raid6_recov_algo->datap);
+	pr_info("raid6: using %s recovery algorithm\n", raid6_recov_algo->name);
+
+	/*
+	 * Pick the last registered implementation as the temporary default until
+	 * calibration happens.
+	 */
+	static_call_update(raid6_gen_syndrome_impl,
+			raid6_algos[raid6_nr_algos - 1]->gen_syndrome);
+	static_call_update(raid6_xor_syndrome_impl,
+			raid6_algos[raid6_nr_algos - 1]->xor_syndrome);
+
+#ifdef MODULE
+	return raid6_select_algo();
+#else
+	return 0;
+#endif
+}
+
+static void __exit raid6_exit(void)
+{
+}
+
+/*
+ * When built-in we must register the default implementation before md
+ * initializes, but we don't want calibration to run that early as that
+ * would delay the boot process.
+ */
+#ifndef MODULE
+device_initcall(raid6_select_algo);
+#endif
+subsys_initcall(raid6_init);
+module_exit(raid6_exit);
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("RAID6 Q-syndrome calculations");
+
+#if IS_ENABLED(CONFIG_RAID6_PQ_KUNIT_TEST)
+const struct raid6_calls *raid6_algo_find(unsigned int idx)
+{
+	if (idx >= raid6_nr_algos) {
+		/*
+		 * Always include the simplest generic integer implementation in
+		 * the unit tests as a baseline.
+		 */
+		if (idx == raid6_nr_algos &&
+		    raid6_algos[0] != &raid6_intx1)
+			return &raid6_intx1;
+		return NULL;
+	}
+	return raid6_algos[idx];
+}
+EXPORT_SYMBOL_IF_KUNIT(raid6_algo_find);
+
+const struct raid6_recov_calls *raid6_recov_algo_find(unsigned int idx)
+{
+	switch (idx) {
+	case 0:
+		/* always test the generic integer implementation */
+		return &raid6_recov_intx1;
+	case 1:
+		/* test the optimized implementation if there is one */
+		if (raid6_recov_algo != &raid6_recov_intx1)
+			return raid6_recov_algo;
+		return NULL;
+	default:
+		return NULL;
+	}
+}
+EXPORT_SYMBOL_IF_KUNIT(raid6_recov_algo_find);
+#endif /* CONFIG_RAID6_PQ_KUNIT_TEST */