arm64: ftrace: Ensure module ftrace trampoline is coherent with I-side

The initial support for dynamic ftrace trampolines in modules made use
of an indirect branch which loaded its target from the beginning of
a special section (e71a4e1bebaf7 ("arm64: ftrace: add support for far
branches to dynamic ftrace")). Since no instructions were being patched,
no cache maintenance was needed. However, later in be0f272bfc83 ("arm64:
ftrace: emit ftrace-mod.o contents through code") this code was reworked
to output the trampoline instructions directly into the PLT entry but,
unfortunately, the necessary cache maintenance was overlooked.

Add a call to __flush_icache_range() after writing the new trampoline
instructions but before patching in the branch to the trampoline.

Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: James Morse <james.morse@arm.com>
Cc: <stable@vger.kernel.org>
Fixes: be0f272bfc83 ("arm64: ftrace: emit ftrace-mod.o contents through code")
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 1285c7b2947fa74cf50e66b83ec163b2d7a21027..17177325797420cea45062f349f5dde71b72119b 100644 (file)
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -73,7 +73,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 
        if (offset < -SZ_128M || offset >= SZ_128M) {
 #ifdef CONFIG_ARM64_MODULE_PLTS
 
        if (offset < -SZ_128M || offset >= SZ_128M) {
 #ifdef CONFIG_ARM64_MODULE_PLTS

-               struct plt_entry trampoline;
+               struct plt_entry trampoline, *dst;

                struct module *mod;
 
                /*
                struct module *mod;
 
                /*


@@ -106,23 +106,27 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
                 * to check if the actual opcodes are in fact identical,
                 * regardless of the offset in memory so use memcmp() instead.
                 */
                 * to check if the actual opcodes are in fact identical,
                 * regardless of the offset in memory so use memcmp() instead.
                 */

-               trampoline = get_plt_entry(addr, mod->arch.ftrace_trampoline);
-               if (memcmp(mod->arch.ftrace_trampoline, &trampoline,
-                          sizeof(trampoline))) {
-                       if (plt_entry_is_initialized(mod->arch.ftrace_trampoline)) {
+               dst = mod->arch.ftrace_trampoline;
+               trampoline = get_plt_entry(addr, dst);
+               if (memcmp(dst, &trampoline, sizeof(trampoline))) {
+                       if (plt_entry_is_initialized(dst)) {

                                pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
                                return -EINVAL;
                        }
 
                        /* point the trampoline to our ftrace entry point */
                        module_disable_ro(mod);
                                pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
                                return -EINVAL;
                        }
 
                        /* point the trampoline to our ftrace entry point */
                        module_disable_ro(mod);

-                       *mod->arch.ftrace_trampoline = trampoline;
+                       *dst = trampoline;

                        module_enable_ro(mod, true);
 
                        module_enable_ro(mod, true);
 

-                       /* update trampoline before patching in the branch */
-                       smp_wmb();
+                       /*
+                        * Ensure updated trampoline is visible to instruction
+                        * fetch before we patch in the branch.
+                        */
+                       __flush_icache_range((unsigned long)&dst[0],
+                                            (unsigned long)&dst[1]);

                }
                }

-               addr = (unsigned long)(void *)mod->arch.ftrace_trampoline;
+               addr = (unsigned long)dst;

 #else /* CONFIG_ARM64_MODULE_PLTS */
                return -EINVAL;
 #endif /* CONFIG_ARM64_MODULE_PLTS */
 #else /* CONFIG_ARM64_MODULE_PLTS */
                return -EINVAL;
 #endif /* CONFIG_ARM64_MODULE_PLTS */