ftrace: Synchronize the initialization of ftrace_opsgrafted

There's some internal state that ftrace_ops needs to have set, but since
it can be declared outside of the ftrace.c code, it calls
ftrace_ops_init() on the ops in every global function. The issue is that
if two tasks call it on the same ops at the same time it is possible to
have the initialization of one corrupt the initialization of the other
call.

Create a ops_mutex to use to synchronize every initialization of the
ftrace_ops. The mutex is taken within checking the ftrace_ops flag that
states it was initializied but the flag is checked again after the mutex
has been taken. Checking first outside the mutex allows it to shortcut
having to take the mutex. But then the check needs to be done again after
the mute is taken in case of races.

Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260902095501.6b59af20@gandalf.local.home
Fixes: f04f24fb7e48d ("ftrace, kprobes: Fix a deadlock on ftrace_regex_lock")
Reported-by: sashiko-bot@kernel.org
Close: https://lore.kernel.org/all/20260829025528.49A831F000E9@smtp.kernel.org/
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

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);