summaryrefslogtreecommitdiff
path: root/arch/arm64/kernel/ftrace.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64/kernel/ftrace.c')
-rw-r--r--arch/arm64/kernel/ftrace.c310
1 files changed, 286 insertions, 24 deletions
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index b30b955a8921..5a1554a44162 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -15,7 +15,7 @@
#include <asm/debug-monitors.h>
#include <asm/ftrace.h>
#include <asm/insn.h>
-#include <asm/patching.h>
+#include <asm/text-patching.h>
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
struct fregs_offset {
@@ -23,10 +23,10 @@ struct fregs_offset {
int offset;
};
-#define FREGS_OFFSET(n, field) \
-{ \
- .name = n, \
- .offset = offsetof(struct ftrace_regs, field), \
+#define FREGS_OFFSET(n, field) \
+{ \
+ .name = n, \
+ .offset = offsetof(struct __arch_ftrace_regs, field), \
}
static const struct fregs_offset fregs_offsets[] = {
@@ -60,6 +60,152 @@ int ftrace_regs_query_register_offset(const char *name)
}
#endif
+unsigned long ftrace_call_adjust(unsigned long addr)
+{
+ /*
+ * When using mcount, addr is the address of the mcount call
+ * instruction, and no adjustment is necessary.
+ */
+ if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS))
+ return addr;
+
+ /*
+ * When using patchable-function-entry without pre-function NOPS, addr
+ * is the address of the first NOP after the function entry point.
+ *
+ * The compiler has either generated:
+ *
+ * addr+00: func: NOP // To be patched to MOV X9, LR
+ * addr+04: NOP // To be patched to BL <caller>
+ *
+ * Or:
+ *
+ * addr-04: BTI C
+ * addr+00: func: NOP // To be patched to MOV X9, LR
+ * addr+04: NOP // To be patched to BL <caller>
+ *
+ * We must adjust addr to the address of the NOP which will be patched
+ * to `BL <caller>`, which is at `addr + 4` bytes in either case.
+ *
+ */
+ if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
+ return addr + AARCH64_INSN_SIZE;
+
+ /*
+ * When using patchable-function-entry with pre-function NOPs, addr is
+ * the address of the first pre-function NOP.
+ *
+ * Starting from an 8-byte aligned base, the compiler has either
+ * generated:
+ *
+ * addr+00: NOP // Literal (first 32 bits)
+ * addr+04: NOP // Literal (last 32 bits)
+ * addr+08: func: NOP // To be patched to MOV X9, LR
+ * addr+12: NOP // To be patched to BL <caller>
+ *
+ * Or:
+ *
+ * addr+00: NOP // Literal (first 32 bits)
+ * addr+04: NOP // Literal (last 32 bits)
+ * addr+08: func: BTI C
+ * addr+12: NOP // To be patched to MOV X9, LR
+ * addr+16: NOP // To be patched to BL <caller>
+ *
+ * We must adjust addr to the address of the NOP which will be patched
+ * to `BL <caller>`, which is at either addr+12 or addr+16 depending on
+ * whether there is a BTI.
+ */
+
+ if (!IS_ALIGNED(addr, sizeof(unsigned long))) {
+ WARN_RATELIMIT(1, "Misaligned patch-site %pS\n",
+ (void *)(addr + 8));
+ return 0;
+ }
+
+ /* Skip the NOPs placed before the function entry point */
+ addr += 2 * AARCH64_INSN_SIZE;
+
+ /* Skip any BTI */
+ if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)) {
+ u32 insn = le32_to_cpu(*(__le32 *)addr);
+
+ if (aarch64_insn_is_bti(insn)) {
+ addr += AARCH64_INSN_SIZE;
+ } else if (insn != aarch64_insn_gen_nop()) {
+ WARN_RATELIMIT(1, "unexpected insn in patch-site %pS: 0x%08x\n",
+ (void *)addr, insn);
+ }
+ }
+
+ /* Skip the first NOP after function entry */
+ addr += AARCH64_INSN_SIZE;
+
+ return addr;
+}
+
+/* Convert fentry_ip to the symbol address without kallsyms */
+unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip)
+{
+ u32 insn;
+
+ /*
+ * When using patchable-function-entry without pre-function NOPS, ftrace
+ * entry is the address of the first NOP after the function entry point.
+ *
+ * The compiler has either generated:
+ *
+ * func+00: func: NOP // To be patched to MOV X9, LR
+ * func+04: NOP // To be patched to BL <caller>
+ *
+ * Or:
+ *
+ * func-04: BTI C
+ * func+00: func: NOP // To be patched to MOV X9, LR
+ * func+04: NOP // To be patched to BL <caller>
+ *
+ * The fentry_ip is the address of `BL <caller>` which is at `func + 4`
+ * bytes in either case.
+ */
+ if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
+ return fentry_ip - AARCH64_INSN_SIZE;
+
+ /*
+ * When using patchable-function-entry with pre-function NOPs, BTI is
+ * a bit different.
+ *
+ * func+00: func: NOP // To be patched to MOV X9, LR
+ * func+04: NOP // To be patched to BL <caller>
+ *
+ * Or:
+ *
+ * func+00: func: BTI C
+ * func+04: NOP // To be patched to MOV X9, LR
+ * func+08: NOP // To be patched to BL <caller>
+ *
+ * The fentry_ip is the address of `BL <caller>` which is at either
+ * `func + 4` or `func + 8` depends on whether there is a BTI.
+ */
+
+ /* If there is no BTI, the func address should be one instruction before. */
+ if (!IS_ENABLED(CONFIG_ARM64_BTI_KERNEL))
+ return fentry_ip - AARCH64_INSN_SIZE;
+
+ /* We want to be extra safe in case entry ip is on the page edge,
+ * but otherwise we need to avoid get_kernel_nofault()'s overhead.
+ */
+ if ((fentry_ip & ~PAGE_MASK) < AARCH64_INSN_SIZE * 2) {
+ if (get_kernel_nofault(insn, (u32 *)(fentry_ip - AARCH64_INSN_SIZE * 2)))
+ return 0;
+ } else {
+ insn = *(u32 *)(fentry_ip - AARCH64_INSN_SIZE * 2);
+ }
+
+ if (aarch64_insn_is_bti(le32_to_cpu((__le32)insn)))
+ return fentry_ip - AARCH64_INSN_SIZE * 2;
+
+ return fentry_ip - AARCH64_INSN_SIZE;
+}
+
/*
* Replace a single instruction, which may be a branch or NOP.
* If @validate == true, a replaced instruction is checked against 'old'.
@@ -98,6 +244,13 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
unsigned long pc;
u32 new;
+ /*
+ * When using CALL_OPS, the function to call is associated with the
+ * call site, and we don't have a global function pointer to update.
+ */
+ if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
+ return 0;
+
pc = (unsigned long)ftrace_call;
new = aarch64_insn_gen_branch_imm(pc, (unsigned long)func,
AARCH64_INSN_BRANCH_LINK);
@@ -107,13 +260,27 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr)
{
-#ifdef CONFIG_ARM64_MODULE_PLTS
- struct plt_entry *plt = mod->arch.ftrace_trampolines;
+#ifdef CONFIG_MODULES
+ struct plt_entry *plt = NULL;
- if (addr == FTRACE_ADDR)
- return &plt[FTRACE_PLT_IDX];
-#endif
+ if (within_module_mem_type(addr, mod, MOD_INIT_TEXT))
+ plt = mod->arch.init_ftrace_trampolines;
+ else if (within_module_mem_type(addr, mod, MOD_TEXT))
+ plt = mod->arch.ftrace_trampolines;
+ else
+ return NULL;
+
+ return &plt[FTRACE_PLT_IDX];
+#else
return NULL;
+#endif
+}
+
+static bool reachable_by_bl(unsigned long addr, unsigned long pc)
+{
+ long offset = (long)addr - (long)pc;
+
+ return offset >= -SZ_128M && offset < SZ_128M;
}
/*
@@ -130,14 +297,21 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec,
unsigned long *addr)
{
unsigned long pc = rec->ip;
- long offset = (long)*addr - (long)pc;
struct plt_entry *plt;
/*
+ * If a custom trampoline is unreachable, rely on the ftrace_caller
+ * trampoline which knows how to indirectly reach that trampoline
+ * through ops->direct_call.
+ */
+ if (*addr != FTRACE_ADDR && !reachable_by_bl(*addr, pc))
+ *addr = FTRACE_ADDR;
+
+ /*
* When the target is within range of the 'BL' instruction, use 'addr'
* as-is and branch to that directly.
*/
- if (offset >= -SZ_128M && offset < SZ_128M)
+ if (reachable_by_bl(*addr, pc))
return true;
/*
@@ -145,7 +319,7 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec,
* must use a PLT to reach it. We can only place PLTs for modules, and
* only when module PLT support is built-in.
*/
- if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS))
+ if (!IS_ENABLED(CONFIG_MODULES))
return false;
/*
@@ -153,20 +327,19 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec,
* dealing with an out-of-range condition, we can assume it
* is due to a module being loaded far away from the kernel.
*
- * NOTE: __module_text_address() must be called with preemption
- * disabled, but we can rely on ftrace_lock to ensure that 'mod'
+ * NOTE: __module_text_address() must be called within a RCU read
+ * section, but we can rely on ftrace_lock to ensure that 'mod'
* retains its validity throughout the remainder of this code.
*/
if (!mod) {
- preempt_disable();
+ guard(rcu)();
mod = __module_text_address(pc);
- preempt_enable();
}
if (WARN_ON(!mod))
return false;
- plt = get_ftrace_plt(mod, *addr);
+ plt = get_ftrace_plt(mod, pc);
if (!plt) {
pr_err("ftrace: no module PLT for %ps\n", (void *)*addr);
return false;
@@ -176,6 +349,44 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec,
return true;
}
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+static const struct ftrace_ops *arm64_rec_get_ops(struct dyn_ftrace *rec)
+{
+ const struct ftrace_ops *ops = NULL;
+
+ if (rec->flags & FTRACE_FL_CALL_OPS_EN) {
+ ops = ftrace_find_unique_ops(rec);
+ WARN_ON_ONCE(!ops);
+ }
+
+ if (!ops)
+ ops = &ftrace_list_ops;
+
+ return ops;
+}
+
+static int ftrace_rec_set_ops(const struct dyn_ftrace *rec,
+ const struct ftrace_ops *ops)
+{
+ unsigned long literal = ALIGN_DOWN(rec->ip - 12, 8);
+ return aarch64_insn_write_literal_u64((void *)literal,
+ (unsigned long)ops);
+}
+
+static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec)
+{
+ return ftrace_rec_set_ops(rec, &ftrace_nop_ops);
+}
+
+static int ftrace_rec_update_ops(struct dyn_ftrace *rec)
+{
+ return ftrace_rec_set_ops(rec, arm64_rec_get_ops(rec));
+}
+#else
+static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec) { return 0; }
+static int ftrace_rec_update_ops(struct dyn_ftrace *rec) { return 0; }
+#endif
+
/*
* Turn on the call to ftrace_caller() in instrumented function
*/
@@ -183,6 +394,11 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
unsigned long pc = rec->ip;
u32 old, new;
+ int ret;
+
+ ret = ftrace_rec_update_ops(rec);
+ if (ret)
+ return ret;
if (!ftrace_find_callable_addr(rec, NULL, &addr))
return -EINVAL;
@@ -193,6 +409,31 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
return ftrace_modify_code(pc, old, new, true);
}
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+ unsigned long addr)
+{
+ unsigned long pc = rec->ip;
+ u32 old, new;
+ int ret;
+
+ ret = ftrace_rec_set_ops(rec, arm64_rec_get_ops(rec));
+ if (ret)
+ return ret;
+
+ if (!ftrace_find_callable_addr(rec, NULL, &old_addr))
+ return -EINVAL;
+ if (!ftrace_find_callable_addr(rec, NULL, &addr))
+ return -EINVAL;
+
+ old = aarch64_insn_gen_branch_imm(pc, old_addr,
+ AARCH64_INSN_BRANCH_LINK);
+ new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK);
+
+ return ftrace_modify_code(pc, old, new, true);
+}
+#endif
+
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
/*
* The compiler has inserted two NOPs before the regular function prologue.
@@ -209,7 +450,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
* | NOP | MOV X9, LR | MOV X9, LR |
* | NOP | NOP | BL <entry> |
*
- * The LR value will be recovered by ftrace_regs_entry, and restored into LR
+ * The LR value will be recovered by ftrace_caller, and restored into LR
* before returning to the regular function prologue. When a function is not
* being traced, the MOV is not harmful given x9 is not live per the AAPCS.
*
@@ -220,6 +461,11 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
{
unsigned long pc = rec->ip - AARCH64_INSN_SIZE;
u32 old, new;
+ int ret;
+
+ ret = ftrace_rec_set_nop_ops(rec);
+ if (ret)
+ return ret;
old = aarch64_insn_gen_nop();
new = aarch64_insn_gen_move_reg(AARCH64_INSN_REG_9,
@@ -237,11 +483,16 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
{
unsigned long pc = rec->ip;
u32 old = 0, new;
+ int ret;
new = aarch64_insn_gen_nop();
+ ret = ftrace_rec_set_nop_ops(rec);
+ if (ret)
+ return ret;
+
/*
- * When using mcount, callsites in modules may have been initalized to
+ * When using mcount, callsites in modules may have been initialized to
* call an arbitrary module PLT (which redirects to the _mcount stub)
* rather than the ftrace PLT we'll use at runtime (which redirects to
* the ftrace trampoline). We can ignore the old PLT when initializing
@@ -249,10 +500,8 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
*
* Note: 'mod' is only set at module load time.
*/
- if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS) &&
- IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) && mod) {
+ if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS) && mod)
return aarch64_insn_patch_text_nosync((void *)pc, new);
- }
if (!ftrace_find_callable_addr(rec, mod, &addr))
return -EINVAL;
@@ -301,7 +550,20 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct ftrace_regs *fregs)
{
- prepare_ftrace_return(ip, &fregs->lr, fregs->fp);
+ unsigned long return_hooker = (unsigned long)&return_to_handler;
+ unsigned long frame_pointer = arch_ftrace_regs(fregs)->fp;
+ unsigned long *parent = &arch_ftrace_regs(fregs)->lr;
+ unsigned long old;
+
+ if (unlikely(atomic_read(&current->tracing_graph_pause)))
+ return;
+
+ old = *parent;
+
+ if (!function_graph_enter_regs(old, ip, frame_pointer,
+ (void *)frame_pointer, fregs)) {
+ *parent = return_hooker;
+ }
}
#else
/*