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, 289 insertions, 0 deletions

diff --git a/fs/proc/page.c b/fs/proc/page.c
new file mode 100644
index 000000000..260772b20
--- /dev/null
+++ b/fs/proc/page.c
@@ -0,0 +1,289 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/memblock.h>
+#include <linux/compiler.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/ksm.h>
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+#include <linux/huge_mm.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/hugetlb.h>
+#include <linux/memremap.h>
+#include <linux/memcontrol.h>
+#include <linux/mmu_notifier.h>
+#include <linux/page_idle.h>
+#include <linux/kernel-page-flags.h>
+#include <linux/uaccess.h>
+#include "internal.h"
+
+#define KPMSIZE sizeof(u64)
+#define KPMMASK (KPMSIZE - 1)
+
+enum kpage_operation {
+	KPAGE_FLAGS,
+	KPAGE_COUNT,
+	KPAGE_CGROUP,
+};
+
+static inline unsigned long get_max_dump_pfn(void)
+{
+#ifdef CONFIG_SPARSEMEM
+	/*
+	 * The memmap of early sections is completely populated and marked
+	 * online even if max_pfn does not fall on a section boundary -
+	 * pfn_to_online_page() will succeed on all pages. Allow inspecting
+	 * these memmaps.
+	 */
+	return round_up(max_pfn, PAGES_PER_SECTION);
+#else
+	return max_pfn;
+#endif
+}
+
+static u64 get_kpage_count(const struct page *page)
+{
+	struct page_snapshot ps;
+	u64 ret;
+
+	snapshot_page(&ps, page);
+
+	if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT))
+		ret = folio_precise_page_mapcount(&ps.folio_snapshot,
+						  &ps.page_snapshot);
+	else
+		ret = folio_average_page_mapcount(&ps.folio_snapshot);
+
+	return ret;
+}
+
+static ssize_t kpage_read(struct file *file, char __user *buf,
+		size_t count, loff_t *ppos,
+		enum kpage_operation op)
+{
+	const unsigned long max_dump_pfn = get_max_dump_pfn();
+	u64 __user *out = (u64 __user *)buf;
+	struct page *page;
+	unsigned long src = *ppos;
+	unsigned long pfn;
+	ssize_t ret = 0;
+	u64 info;
+
+	pfn = src / KPMSIZE;
+	if (src & KPMMASK || count & KPMMASK)
+		return -EINVAL;
+	if (src >= max_dump_pfn * KPMSIZE)
+		return 0;
+	count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src);
+
+	while (count > 0) {
+		/*
+		 * TODO: ZONE_DEVICE support requires to identify
+		 * memmaps that were actually initialized.
+		 */
+		page = pfn_to_online_page(pfn);
+
+		if (page) {
+			switch (op) {
+			case KPAGE_FLAGS:
+				info = stable_page_flags(page);
+				break;
+			case KPAGE_COUNT:
+				info = get_kpage_count(page);
+				break;
+			case KPAGE_CGROUP:
+				info = page_cgroup_ino(page);
+				break;
+			default:
+				info = 0;
+				break;
+			}
+		} else
+			info = 0;
+
+		if (put_user(info, out)) {
+			ret = -EFAULT;
+			break;
+		}
+
+		pfn++;
+		out++;
+		count -= KPMSIZE;
+
+		cond_resched();
+	}
+
+	*ppos += (char __user *)out - buf;
+	if (!ret)
+		ret = (char __user *)out - buf;
+	return ret;
+}
+
+/* /proc/kpagecount - an array exposing page mapcounts
+ *
+ * Each entry is a u64 representing the corresponding
+ * physical page mapcount.
+ */
+static ssize_t kpagecount_read(struct file *file, char __user *buf,
+		size_t count, loff_t *ppos)
+{
+	return kpage_read(file, buf, count, ppos, KPAGE_COUNT);
+}
+
+static const struct proc_ops kpagecount_proc_ops = {
+	.proc_flags	= PROC_ENTRY_PERMANENT,
+	.proc_lseek	= mem_lseek,
+	.proc_read	= kpagecount_read,
+};
+
+
+static inline u64 kpf_copy_bit(u64 kflags, int ubit, int kbit)
+{
+	return ((kflags >> kbit) & 1) << ubit;
+}
+
+u64 stable_page_flags(const struct page *page)
+{
+	const struct folio *folio;
+	struct page_snapshot ps;
+	unsigned long k;
+	u64 u = 0;
+
+	/*
+	 * pseudo flag: KPF_NOPAGE
+	 * it differentiates a memory hole from a page with no flags
+	 */
+	if (!page)
+		return BIT_ULL(KPF_NOPAGE);
+
+	snapshot_page(&ps, page);
+	folio = &ps.folio_snapshot;
+	k = folio->flags.f;
+
+	/*
+	 * pseudo flags for the well known (anonymous) memory mapped pages
+	 */
+	if (folio_mapped(folio))
+		u |= BIT_ULL(KPF_MMAP);
+	if (folio_test_anon(folio)) {
+		u |= BIT_ULL(KPF_ANON);
+		if (folio_test_ksm(folio))
+			u |= BIT_ULL(KPF_KSM);
+	}
+
+	/*
+	 * compound pages: export both head/tail info
+	 * they together define a compound page's start/end pos and order
+	 */
+	if (ps.idx == 0)
+		u |= kpf_copy_bit(k, KPF_COMPOUND_HEAD, PG_head);
+	else
+		u |= BIT_ULL(KPF_COMPOUND_TAIL);
+	if (folio_test_hugetlb(folio))
+		u |= BIT_ULL(KPF_HUGE);
+	else if (folio_test_large(folio) &&
+	         folio_test_large_rmappable(folio)) {
+		/* Note: we indicate any THPs here, not just PMD-sized ones */
+		u |= BIT_ULL(KPF_THP);
+	} else if (is_huge_zero_pfn(ps.pfn)) {
+		u |= BIT_ULL(KPF_ZERO_PAGE);
+		u |= BIT_ULL(KPF_THP);
+	} else if (is_zero_pfn(ps.pfn)) {
+		u |= BIT_ULL(KPF_ZERO_PAGE);
+	}
+
+	if (ps.flags & PAGE_SNAPSHOT_PG_BUDDY)
+		u |= BIT_ULL(KPF_BUDDY);
+
+	if (ps.flags & PAGE_SNAPSHOT_PG_IDLE)
+		u |= BIT_ULL(KPF_IDLE);
+
+	if (folio_test_offline(folio))
+		u |= BIT_ULL(KPF_OFFLINE);
+	if (folio_test_pgtable(folio))
+		u |= BIT_ULL(KPF_PGTABLE);
+	if (folio_test_slab(folio))
+		u |= BIT_ULL(KPF_SLAB);
+
+	u |= kpf_copy_bit(k, KPF_LOCKED,	PG_locked);
+	u |= kpf_copy_bit(k, KPF_DIRTY,		PG_dirty);
+	u |= kpf_copy_bit(k, KPF_UPTODATE,	PG_uptodate);
+	u |= kpf_copy_bit(k, KPF_WRITEBACK,	PG_writeback);
+
+	u |= kpf_copy_bit(k, KPF_LRU,		PG_lru);
+	u |= kpf_copy_bit(k, KPF_REFERENCED,	PG_referenced);
+	u |= kpf_copy_bit(k, KPF_ACTIVE,	PG_active);
+	u |= kpf_copy_bit(k, KPF_RECLAIM,	PG_reclaim);
+
+	if (folio_test_swapcache(folio))
+		u |= BIT_ULL(KPF_SWAPCACHE);
+
+	u |= kpf_copy_bit(k, KPF_SWAPBACKED,	PG_swapbacked);
+	u |= kpf_copy_bit(k, KPF_UNEVICTABLE,	PG_unevictable);
+	u |= kpf_copy_bit(k, KPF_MLOCKED,	PG_mlocked);
+
+#ifdef CONFIG_MEMORY_FAILURE
+	if (u & BIT_ULL(KPF_HUGE))
+		u |= kpf_copy_bit(k, KPF_HWPOISON,	PG_hwpoison);
+	else
+		u |= kpf_copy_bit(ps.page_snapshot.flags.f, KPF_HWPOISON, PG_hwpoison);
+#endif
+
+	u |= kpf_copy_bit(k, KPF_RESERVED,	PG_reserved);
+	u |= kpf_copy_bit(k, KPF_OWNER_2,	PG_owner_2);
+	u |= kpf_copy_bit(k, KPF_PRIVATE,	PG_private);
+	u |= kpf_copy_bit(k, KPF_PRIVATE_2,	PG_private_2);
+	u |= kpf_copy_bit(k, KPF_OWNER_PRIVATE,	PG_owner_priv_1);
+	u |= kpf_copy_bit(k, KPF_ARCH,		PG_arch_1);
+#ifdef CONFIG_ARCH_USES_PG_ARCH_2
+	u |= kpf_copy_bit(k, KPF_ARCH_2,	PG_arch_2);
+#endif
+#ifdef CONFIG_ARCH_USES_PG_ARCH_3
+	u |= kpf_copy_bit(k, KPF_ARCH_3,	PG_arch_3);
+#endif
+
+	return u;
+}
+EXPORT_SYMBOL_GPL(stable_page_flags);
+
+/* /proc/kpageflags - an array exposing page flags
+ *
+ * Each entry is a u64 representing the corresponding
+ * physical page flags.
+ */
+static ssize_t kpageflags_read(struct file *file, char __user *buf,
+		size_t count, loff_t *ppos)
+{
+	return kpage_read(file, buf, count, ppos, KPAGE_FLAGS);
+}
+
+static const struct proc_ops kpageflags_proc_ops = {
+	.proc_flags	= PROC_ENTRY_PERMANENT,
+	.proc_lseek	= mem_lseek,
+	.proc_read	= kpageflags_read,
+};
+
+#ifdef CONFIG_MEMCG
+static ssize_t kpagecgroup_read(struct file *file, char __user *buf,
+		size_t count, loff_t *ppos)
+{
+	return kpage_read(file, buf, count, ppos, KPAGE_CGROUP);
+}
+static const struct proc_ops kpagecgroup_proc_ops = {
+	.proc_flags	= PROC_ENTRY_PERMANENT,
+	.proc_lseek	= mem_lseek,
+	.proc_read	= kpagecgroup_read,
+};
+#endif /* CONFIG_MEMCG */
+
+static int __init proc_page_init(void)
+{
+	proc_create("kpagecount", S_IRUSR, NULL, &kpagecount_proc_ops);
+	proc_create("kpageflags", S_IRUSR, NULL, &kpageflags_proc_ops);
+#ifdef CONFIG_MEMCG
+	proc_create("kpagecgroup", S_IRUSR, NULL, &kpagecgroup_proc_ops);
+#endif
+	return 0;
+}
+fs_initcall(proc_page_init);