Merge branch 'tip/perf/core-4' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace into perf/core

5 files changed, 358 insertions, 175 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1d14cc6b79ad..1324139612e1 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -40,7 +40,6 @@ config X86
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_GRAPH_FP_TEST
 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
-	select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_KVM
 	select HAVE_ARCH_KGDB
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 268c783ab1c0..18d9005d9e4f 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -34,6 +34,7 @@
 
 #ifndef __ASSEMBLY__
 extern void mcount(void);
+extern int modifying_ftrace_code;
 
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
@@ -50,6 +51,8 @@ struct dyn_arch_ftrace {
 	/* No extra data needed for x86 */
 };
 
+int ftrace_int3_handler(struct pt_regs *regs);
+
 #endif /*  CONFIG_DYNAMIC_FTRACE */
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_FUNCTION_TRACER */
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index c9a281f272fd..4243e8bbdcb1 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -24,40 +24,21 @@
 #include <trace/syscall.h>
 
 #include <asm/cacheflush.h>
+#include <asm/kprobes.h>
 #include <asm/ftrace.h>
 #include <asm/nops.h>
-#include <asm/nmi.h>
-
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
-/*
- * modifying_code is set to notify NMIs that they need to use
- * memory barriers when entering or exiting. But we don't want
- * to burden NMIs with unnecessary memory barriers when code
- * modification is not being done (which is most of the time).
- *
- * A mutex is already held when ftrace_arch_code_modify_prepare
- * and post_process are called. No locks need to be taken here.
- *
- * Stop machine will make sure currently running NMIs are done
- * and new NMIs will see the updated variable before we need
- * to worry about NMIs doing memory barriers.
- */
-static int modifying_code __read_mostly;
-static DEFINE_PER_CPU(int, save_modifying_code);
-
 int ftrace_arch_code_modify_prepare(void)
 {
 	set_kernel_text_rw();
 	set_all_modules_text_rw();
-	modifying_code = 1;
 	return 0;
 }
 
 int ftrace_arch_code_modify_post_process(void)
 {
-	modifying_code = 0;
 	set_all_modules_text_ro();
 	set_kernel_text_ro();
 	return 0;
@@ -90,134 +71,6 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 	return calc.code;
 }
 
-/*
- * Modifying code must take extra care. On an SMP machine, if
- * the code being modified is also being executed on another CPU
- * that CPU will have undefined results and possibly take a GPF.
- * We use kstop_machine to stop other CPUS from exectuing code.
- * But this does not stop NMIs from happening. We still need
- * to protect against that. We separate out the modification of
- * the code to take care of this.
- *
- * Two buffers are added: An IP buffer and a "code" buffer.
- *
- * 1) Put the instruction pointer into the IP buffer
- *    and the new code into the "code" buffer.
- * 2) Wait for any running NMIs to finish and set a flag that says
- *    we are modifying code, it is done in an atomic operation.
- * 3) Write the code
- * 4) clear the flag.
- * 5) Wait for any running NMIs to finish.
- *
- * If an NMI is executed, the first thing it does is to call
- * "ftrace_nmi_enter". This will check if the flag is set to write
- * and if it is, it will write what is in the IP and "code" buffers.
- *
- * The trick is, it does not matter if everyone is writing the same
- * content to the code location. Also, if a CPU is executing code
- * it is OK to write to that code location if the contents being written
- * are the same as what exists.
- */
-
-#define MOD_CODE_WRITE_FLAG (1 << 31)	/* set when NMI should do the write */
-static atomic_t nmi_running = ATOMIC_INIT(0);
-static int mod_code_status;		/* holds return value of text write */
-static void *mod_code_ip;		/* holds the IP to write to */
-static const void *mod_code_newcode;	/* holds the text to write to the IP */
-
-static unsigned nmi_wait_count;
-static atomic_t nmi_update_count = ATOMIC_INIT(0);
-
-int ftrace_arch_read_dyn_info(char *buf, int size)
-{
-	int r;
-
-	r = snprintf(buf, size, "%u %u",
-		     nmi_wait_count,
-		     atomic_read(&nmi_update_count));
-	return r;
-}
-
-static void clear_mod_flag(void)
-{
-	int old = atomic_read(&nmi_running);
-
-	for (;;) {
-		int new = old & ~MOD_CODE_WRITE_FLAG;
-
-		if (old == new)
-			break;
-
-		old = atomic_cmpxchg(&nmi_running, old, new);
-	}
-}
-
-static void ftrace_mod_code(void)
-{
-	/*
-	 * Yes, more than one CPU process can be writing to mod_code_status.
-	 *    (and the code itself)
-	 * But if one were to fail, then they all should, and if one were
-	 * to succeed, then they all should.
-	 */
-	mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode,
-					     MCOUNT_INSN_SIZE);
-
-	/* if we fail, then kill any new writers */
-	if (mod_code_status)
-		clear_mod_flag();
-}
-
-void ftrace_nmi_enter(void)
-{
-	__this_cpu_write(save_modifying_code, modifying_code);
-
-	if (!__this_cpu_read(save_modifying_code))
-		return;
-
-	if (atomic_inc_return(&nmi_running) & MOD_CODE_WRITE_FLAG) {
-		smp_rmb();
-		ftrace_mod_code();
-		atomic_inc(&nmi_update_count);
-	}
-	/* Must have previous changes seen before executions */
-	smp_mb();
-}
-
-void ftrace_nmi_exit(void)
-{
-	if (!__this_cpu_read(save_modifying_code))
-		return;
-
-	/* Finish all executions before clearing nmi_running */
-	smp_mb();
-	atomic_dec(&nmi_running);
-}
-
-static void wait_for_nmi_and_set_mod_flag(void)
-{
-	if (!atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG))
-		return;
-
-	do {
-		cpu_relax();
-	} while (atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG));
-
-	nmi_wait_count++;
-}
-
-static void wait_for_nmi(void)
-{
-	if (!atomic_read(&nmi_running))
-		return;
-
-	do {
-		cpu_relax();
-	} while (atomic_read(&nmi_running));
-
-	nmi_wait_count++;
-}
-
 static inline int
 within(unsigned long addr, unsigned long start, unsigned long end)
 {
@@ -238,26 +91,7 @@ do_ftrace_mod_code(unsigned long ip, const void *new_code)
 	if (within(ip, (unsigned long)_text, (unsigned long)_etext))
 		ip = (unsigned long)__va(__pa(ip));
 
-	mod_code_ip = (void *)ip;
-	mod_code_newcode = new_code;
-
-	/* The buffers need to be visible before we let NMIs write them */
-	smp_mb();
-
-	wait_for_nmi_and_set_mod_flag();
-
-	/* Make sure all running NMIs have finished before we write the code */
-	smp_mb();
-
-	ftrace_mod_code();
-
-	/* Make sure the write happens before clearing the bit */
-	smp_mb();
-
-	clear_mod_flag();
-	wait_for_nmi();
-
-	return mod_code_status;
+	return probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE);
 }
 
 static const unsigned char *ftrace_nop_replace(void)
@@ -334,6 +168,347 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return ret;
 }
 
+int modifying_ftrace_code __read_mostly;
+
+/*
+ * A breakpoint was added to the code address we are about to
+ * modify, and this is the handle that will just skip over it.
+ * We are either changing a nop into a trace call, or a trace
+ * call to a nop. While the change is taking place, we treat
+ * it just like it was a nop.
+ */
+int ftrace_int3_handler(struct pt_regs *regs)
+{
+	if (WARN_ON_ONCE(!regs))
+		return 0;
+
+	if (!ftrace_location(regs->ip - 1))
+		return 0;
+
+	regs->ip += MCOUNT_INSN_SIZE - 1;
+
+	return 1;
+}
+
+static int ftrace_write(unsigned long ip, const char *val, int size)
+{
+	/*
+	 * On x86_64, kernel text mappings are mapped read-only with
+	 * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead
+	 * of the kernel text mapping to modify the kernel text.
+	 *
+	 * For 32bit kernels, these mappings are same and we can use
+	 * kernel identity mapping to modify code.
+	 */
+	if (within(ip, (unsigned long)_text, (unsigned long)_etext))
+		ip = (unsigned long)__va(__pa(ip));
+
+	return probe_kernel_write((void *)ip, val, size);
+}
+
+static int add_break(unsigned long ip, const char *old)
+{
+	unsigned char replaced[MCOUNT_INSN_SIZE];
+	unsigned char brk = BREAKPOINT_INSTRUCTION;
+
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* Make sure it is what we expect it to be */
+	if (memcmp(replaced, old, MCOUNT_INSN_SIZE) != 0)
+		return -EINVAL;
+
+	if (ftrace_write(ip, &brk, 1))
+		return -EPERM;
+
+	return 0;
+}
+
+static int add_brk_on_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned const char *old;
+	unsigned long ip = rec->ip;
+
+	old = ftrace_call_replace(ip, addr);
+
+	return add_break(rec->ip, old);
+}
+
+
+static int add_brk_on_nop(struct dyn_ftrace *rec)
+{
+	unsigned const char *old;
+
+	old = ftrace_nop_replace();
+
+	return add_break(rec->ip, old);
+}
+
+static int add_breakpoints(struct dyn_ftrace *rec, int enable)
+{
+	unsigned long ftrace_addr;
+	int ret;
+
+	ret = ftrace_test_record(rec, enable);
+
+	ftrace_addr = (unsigned long)FTRACE_ADDR;
+
+	switch (ret) {
+	case FTRACE_UPDATE_IGNORE:
+		return 0;
+
+	case FTRACE_UPDATE_MAKE_CALL:
+		/* converting nop to call */
+		return add_brk_on_nop(rec);
+
+	case FTRACE_UPDATE_MAKE_NOP:
+		/* converting a call to a nop */
+		return add_brk_on_call(rec, ftrace_addr);
+	}
+	return 0;
+}
+
+/*
+ * On error, we need to remove breakpoints. This needs to
+ * be done caefully. If the address does not currently have a
+ * breakpoint, we know we are done. Otherwise, we look at the
+ * remaining 4 bytes of the instruction. If it matches a nop
+ * we replace the breakpoint with the nop. Otherwise we replace
+ * it with the call instruction.
+ */
+static int remove_breakpoint(struct dyn_ftrace *rec)
+{
+	unsigned char ins[MCOUNT_INSN_SIZE];
+	unsigned char brk = BREAKPOINT_INSTRUCTION;
+	const unsigned char *nop;
+	unsigned long ftrace_addr;
+	unsigned long ip = rec->ip;
+
+	/* If we fail the read, just give up */
+	if (probe_kernel_read(ins, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* If this does not have a breakpoint, we are done */
+	if (ins[0] != brk)
+		return -1;
+
+	nop = ftrace_nop_replace();
+
+	/*
+	 * If the last 4 bytes of the instruction do not match
+	 * a nop, then we assume that this is a call to ftrace_addr.
+	 */
+	if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) {
+		/*
+		 * For extra paranoidism, we check if the breakpoint is on
+		 * a call that would actually jump to the ftrace_addr.
+		 * If not, don't touch the breakpoint, we make just create
+		 * a disaster.
+		 */
+		ftrace_addr = (unsigned long)FTRACE_ADDR;
+		nop = ftrace_call_replace(ip, ftrace_addr);
+
+		if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0)
+			return -EINVAL;
+	}
+
+	return probe_kernel_write((void *)ip, &nop[0], 1);
+}
+
+static int add_update_code(unsigned long ip, unsigned const char *new)
+{
+	/* skip breakpoint */
+	ip++;
+	new++;
+	if (ftrace_write(ip, new, MCOUNT_INSN_SIZE - 1))
+		return -EPERM;
+	return 0;
+}
+
+static int add_update_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long ip = rec->ip;
+	unsigned const char *new;
+
+	new = ftrace_call_replace(ip, addr);
+	return add_update_code(ip, new);
+}
+
+static int add_update_nop(struct dyn_ftrace *rec)
+{
+	unsigned long ip = rec->ip;
+	unsigned const char *new;
+
+	new = ftrace_nop_replace();
+	return add_update_code(ip, new);
+}
+
+static int add_update(struct dyn_ftrace *rec, int enable)
+{
+	unsigned long ftrace_addr;
+	int ret;
+
+	ret = ftrace_test_record(rec, enable);
+
+	ftrace_addr = (unsigned long)FTRACE_ADDR;
+
+	switch (ret) {
+	case FTRACE_UPDATE_IGNORE:
+		return 0;
+
+	case FTRACE_UPDATE_MAKE_CALL:
+		/* converting nop to call */
+		return add_update_call(rec, ftrace_addr);
+
+	case FTRACE_UPDATE_MAKE_NOP:
+		/* converting a call to a nop */
+		return add_update_nop(rec);
+	}
+
+	return 0;
+}
+
+static int finish_update_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long ip = rec->ip;
+	unsigned const char *new;
+
+	new = ftrace_call_replace(ip, addr);
+
+	if (ftrace_write(ip, new, 1))
+		return -EPERM;
+
+	return 0;
+}
+
+static int finish_update_nop(struct dyn_ftrace *rec)
+{
+	unsigned long ip = rec->ip;
+	unsigned const char *new;
+
+	new = ftrace_nop_replace();
+
+	if (ftrace_write(ip, new, 1))
+		return -EPERM;
+	return 0;
+}
+
+static int finish_update(struct dyn_ftrace *rec, int enable)
+{
+	unsigned long ftrace_addr;
+	int ret;
+
+	ret = ftrace_update_record(rec, enable);
+
+	ftrace_addr = (unsigned long)FTRACE_ADDR;
+
+	switch (ret) {
+	case FTRACE_UPDATE_IGNORE:
+		return 0;
+
+	case FTRACE_UPDATE_MAKE_CALL:
+		/* converting nop to call */
+		return finish_update_call(rec, ftrace_addr);
+
+	case FTRACE_UPDATE_MAKE_NOP:
+		/* converting a call to a nop */
+		return finish_update_nop(rec);
+	}
+
+	return 0;
+}
+
+static void do_sync_core(void *data)
+{
+	sync_core();
+}
+
+static void run_sync(void)
+{
+	int enable_irqs = irqs_disabled();
+
+	/* We may be called with interrupts disbled (on bootup). */
+	if (enable_irqs)
+		local_irq_enable();
+	on_each_cpu(do_sync_core, NULL, 1);
+	if (enable_irqs)
+		local_irq_disable();
+}
+
+static void ftrace_replace_code(int enable)
+{
+	struct ftrace_rec_iter *iter;
+	struct dyn_ftrace *rec;
+	const char *report = "adding breakpoints";
+	int count = 0;
+	int ret;
+
+	for_ftrace_rec_iter(iter) {
+		rec = ftrace_rec_iter_record(iter);
+
+		ret = add_breakpoints(rec, enable);
+		if (ret)
+			goto remove_breakpoints;
+		count++;
+	}
+
+	run_sync();
+
+	report = "updating code";
+
+	for_ftrace_rec_iter(iter) {
+		rec = ftrace_rec_iter_record(iter);
+
+		ret = add_update(rec, enable);
+		if (ret)
+			goto remove_breakpoints;
+	}
+
+	run_sync();
+
+	report = "removing breakpoints";
+
+	for_ftrace_rec_iter(iter) {
+		rec = ftrace_rec_iter_record(iter);
+
+		ret = finish_update(rec, enable);
+		if (ret)
+			goto remove_breakpoints;
+	}
+
+	run_sync();
+
+	return;
+
+ remove_breakpoints:
+	ftrace_bug(ret, rec ? rec->ip : 0);
+	printk(KERN_WARNING "Failed on %s (%d):\n", report, count);
+	for_ftrace_rec_iter(iter) {
+		rec = ftrace_rec_iter_record(iter);
+		remove_breakpoint(rec);
+	}
+}
+
+void arch_ftrace_update_code(int command)
+{
+	modifying_ftrace_code++;
+
+	if (command & FTRACE_UPDATE_CALLS)
+		ftrace_replace_code(1);
+	else if (command & FTRACE_DISABLE_CALLS)
+		ftrace_replace_code(0);
+
+	if (command & FTRACE_UPDATE_TRACE_FUNC)
+		ftrace_update_ftrace_func(ftrace_trace_function);
+
+	if (command & FTRACE_START_FUNC_RET)
+		ftrace_enable_ftrace_graph_caller();
+	else if (command & FTRACE_STOP_FUNC_RET)
+		ftrace_disable_ftrace_graph_caller();
+
+	modifying_ftrace_code--;
+}
+
 int __init ftrace_dyn_arch_init(void *data)
 {
 	/* The return code is retured via data */
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 47acaf319165..eb1539eac393 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -84,7 +84,7 @@ __setup("unknown_nmi_panic", setup_unknown_nmi_panic);
 
 #define nmi_to_desc(type) (&nmi_desc[type])
 
-static int notrace __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b)
+static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b)
 {
 	struct nmi_desc *desc = nmi_to_desc(type);
 	struct nmiaction *a;
@@ -209,7 +209,7 @@ void unregister_nmi_handler(unsigned int type, const char *name)
 
 EXPORT_SYMBOL_GPL(unregister_nmi_handler);
 
-static notrace __kprobes void
+static __kprobes void
 pci_serr_error(unsigned char reason, struct pt_regs *regs)
 {
 	pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
@@ -236,7 +236,7 @@ pci_serr_error(unsigned char reason, struct pt_regs *regs)
 	outb(reason, NMI_REASON_PORT);
 }
 
-static notrace __kprobes void
+static __kprobes void
 io_check_error(unsigned char reason, struct pt_regs *regs)
 {
 	unsigned long i;
@@ -263,7 +263,7 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
 	outb(reason, NMI_REASON_PORT);
 }
 
-static notrace __kprobes void
+static __kprobes void
 unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
 {
 	int handled;
@@ -305,7 +305,7 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
 static DEFINE_PER_CPU(bool, swallow_nmi);
 static DEFINE_PER_CPU(unsigned long, last_nmi_rip);
 
-static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
+static __kprobes void default_do_nmi(struct pt_regs *regs)
 {
 	unsigned char reason = 0;
 	int handled;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index ff9281f16029..92d5756d85fc 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -50,6 +50,7 @@
 #include <asm/processor.h>
 #include <asm/debugreg.h>
 #include <linux/atomic.h>
+#include <asm/ftrace.h>
 #include <asm/traps.h>
 #include <asm/desc.h>
 #include <asm/i387.h>
@@ -303,8 +304,13 @@ gp_in_kernel:
 }
 
 /* May run on IST stack. */
-dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code)
+dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_code)
 {
+#ifdef CONFIG_DYNAMIC_FTRACE
+	/* ftrace must be first, everything else may cause a recursive crash */
+	if (unlikely(modifying_ftrace_code) && ftrace_int3_handler(regs))
+		return;
+#endif
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
 	if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
 				SIGTRAP) == NOTIFY_STOP)