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, 218 insertions, 0 deletions

diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c
new file mode 100644
index 000000000..ad9b0430a
--- /dev/null
+++ b/arch/mips/mm/cache.c
@@ -0,0 +1,218 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1994 - 2003, 06, 07 by Ralf Baechle (ralf@linux-mips.org)
+ * Copyright (C) 2007 MIPS Technologies, Inc.
+ */
+#include <linux/fs.h>
+#include <linux/fcntl.h>
+#include <linux/kernel.h>
+#include <linux/linkage.h>
+#include <linux/export.h>
+#include <linux/sched.h>
+#include <linux/syscalls.h>
+#include <linux/mm.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+
+#include <asm/bcache.h>
+#include <asm/cacheflush.h>
+#include <asm/processor.h>
+#include <asm/cpu.h>
+#include <asm/cpu-features.h>
+#include <asm/setup.h>
+#include <asm/pgtable.h>
+
+/* Cache operations. */
+void (*flush_cache_all)(void);
+void (*__flush_cache_all)(void);
+EXPORT_SYMBOL_GPL(__flush_cache_all);
+void (*flush_cache_mm)(struct mm_struct *mm);
+void (*flush_cache_range)(struct vm_area_struct *vma, unsigned long start,
+	unsigned long end);
+void (*flush_cache_page)(struct vm_area_struct *vma, unsigned long page,
+	unsigned long pfn);
+void (*flush_icache_range)(unsigned long start, unsigned long end);
+EXPORT_SYMBOL_GPL(flush_icache_range);
+void (*local_flush_icache_range)(unsigned long start, unsigned long end);
+EXPORT_SYMBOL_GPL(local_flush_icache_range);
+void (*__flush_icache_user_range)(unsigned long start, unsigned long end);
+void (*__local_flush_icache_user_range)(unsigned long start, unsigned long end);
+EXPORT_SYMBOL_GPL(__local_flush_icache_user_range);
+
+void (*__flush_cache_vmap)(void);
+void (*__flush_cache_vunmap)(void);
+
+void (*__flush_kernel_vmap_range)(unsigned long vaddr, int size);
+EXPORT_SYMBOL_GPL(__flush_kernel_vmap_range);
+
+/* MIPS specific cache operations */
+void (*flush_data_cache_page)(unsigned long addr);
+void (*flush_icache_all)(void);
+
+EXPORT_SYMBOL(flush_data_cache_page);
+EXPORT_SYMBOL(flush_icache_all);
+
+/*
+ * Dummy cache handling routine
+ */
+
+void cache_noop(void) {}
+
+#ifdef CONFIG_BOARD_SCACHE
+
+static struct bcache_ops no_sc_ops = {
+	.bc_enable = (void *)cache_noop,
+	.bc_disable = (void *)cache_noop,
+	.bc_wback_inv = (void *)cache_noop,
+	.bc_inv = (void *)cache_noop
+};
+
+struct bcache_ops *bcops = &no_sc_ops;
+#endif
+
+#ifdef CONFIG_DMA_NONCOHERENT
+
+/* DMA cache operations. */
+void (*_dma_cache_wback_inv)(unsigned long start, unsigned long size);
+void (*_dma_cache_wback)(unsigned long start, unsigned long size);
+void (*_dma_cache_inv)(unsigned long start, unsigned long size);
+
+#endif /* CONFIG_DMA_NONCOHERENT */
+
+/*
+ * We could optimize the case where the cache argument is not BCACHE but
+ * that seems very atypical use ...
+ */
+SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes,
+	unsigned int, cache)
+{
+	if (bytes == 0)
+		return 0;
+	if (!access_ok((void __user *) addr, bytes))
+		return -EFAULT;
+
+	__flush_icache_user_range(addr, addr + bytes);
+
+	return 0;
+}
+
+void __flush_dcache_folio_pages(struct folio *folio, struct page *page,
+		unsigned int nr)
+{
+	struct address_space *mapping = folio_flush_mapping(folio);
+	unsigned long addr;
+	unsigned int i;
+
+	if (mapping && !mapping_mapped(mapping)) {
+		folio_set_dcache_dirty(folio);
+		return;
+	}
+
+	/*
+	 * We could delay the flush for the !folio_mapping case too.  But that
+	 * case is for exec env/arg pages and those are %99 certainly going to
+	 * get faulted into the tlb (and thus flushed) anyways.
+	 */
+	for (i = 0; i < nr; i++) {
+		addr = (unsigned long)kmap_local_page(page + i);
+		flush_data_cache_page(addr);
+		kunmap_local((void *)addr);
+	}
+}
+EXPORT_SYMBOL(__flush_dcache_folio_pages);
+
+void __flush_anon_page(struct page *page, unsigned long vmaddr)
+{
+	unsigned long addr = (unsigned long) page_address(page);
+	struct folio *folio = page_folio(page);
+
+	if (pages_do_alias(addr, vmaddr)) {
+		if (folio_mapped(folio) && !folio_test_dcache_dirty(folio)) {
+			void *kaddr;
+
+			kaddr = kmap_coherent(page, vmaddr);
+			flush_data_cache_page((unsigned long)kaddr);
+			kunmap_coherent();
+		} else
+			flush_data_cache_page(addr);
+	}
+}
+
+EXPORT_SYMBOL(__flush_anon_page);
+
+void __update_cache(unsigned long address, pte_t pte)
+{
+	struct folio *folio;
+	unsigned long pfn, addr;
+	int exec = !pte_no_exec(pte) && !cpu_has_ic_fills_f_dc;
+	unsigned int i;
+
+	pfn = pte_pfn(pte);
+	if (unlikely(!pfn_valid(pfn)))
+		return;
+
+	folio = page_folio(pfn_to_page(pfn));
+	address &= PAGE_MASK;
+	address -= offset_in_folio(folio, pfn << PAGE_SHIFT);
+
+	if (folio_test_dcache_dirty(folio)) {
+		for (i = 0; i < folio_nr_pages(folio); i++) {
+			addr = (unsigned long)kmap_local_folio(folio, i);
+
+			if (exec || pages_do_alias(addr, address))
+				flush_data_cache_page(addr);
+			kunmap_local((void *)addr);
+			address += PAGE_SIZE;
+		}
+		folio_clear_dcache_dirty(folio);
+	}
+}
+
+unsigned long _page_cachable_default;
+EXPORT_SYMBOL(_page_cachable_default);
+
+#define PM(p)	__pgprot(_page_cachable_default | (p))
+
+static pgprot_t protection_map[16] __ro_after_init;
+DECLARE_VM_GET_PAGE_PROT
+
+static inline void setup_protection_map(void)
+{
+	protection_map[0]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
+	protection_map[1]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC);
+	protection_map[2]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
+	protection_map[3]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC);
+	protection_map[4]  = PM(_PAGE_PRESENT);
+	protection_map[5]  = PM(_PAGE_PRESENT);
+	protection_map[6]  = PM(_PAGE_PRESENT);
+	protection_map[7]  = PM(_PAGE_PRESENT);
+
+	protection_map[8]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
+	protection_map[9]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC);
+	protection_map[10] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE |
+				_PAGE_NO_READ);
+	protection_map[11] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE);
+	protection_map[12] = PM(_PAGE_PRESENT);
+	protection_map[13] = PM(_PAGE_PRESENT);
+	protection_map[14] = PM(_PAGE_PRESENT | _PAGE_WRITE);
+	protection_map[15] = PM(_PAGE_PRESENT | _PAGE_WRITE);
+}
+
+#undef PM
+
+void cpu_cache_init(void)
+{
+	if (IS_ENABLED(CONFIG_CPU_R3000) && cpu_has_3k_cache)
+		r3k_cache_init();
+	if ((IS_ENABLED(CONFIG_CPU_R4K_CACHE_TLB) ||
+	     IS_ENABLED(CONFIG_CPU_SB1)) && cpu_has_4k_cache)
+		r4k_cache_init();
+
+	if (IS_ENABLED(CONFIG_CPU_CAVIUM_OCTEON) && cpu_has_octeon_cache)
+		octeon_cache_init();
+
+	setup_protection_map();
+}