Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/torvalds/linux-2.6 into common/serial-rework

Conflicts:
	arch/sh/kernel/cpu/sh2/setup-sh7619.c
	arch/sh/kernel/cpu/sh2a/setup-mxg.c
	arch/sh/kernel/cpu/sh2a/setup-sh7201.c
	arch/sh/kernel/cpu/sh2a/setup-sh7203.c
	arch/sh/kernel/cpu/sh2a/setup-sh7206.c
	arch/sh/kernel/cpu/sh3/setup-sh7705.c
	arch/sh/kernel/cpu/sh3/setup-sh770x.c
	arch/sh/kernel/cpu/sh3/setup-sh7710.c
	arch/sh/kernel/cpu/sh3/setup-sh7720.c
	arch/sh/kernel/cpu/sh4/setup-sh4-202.c
	arch/sh/kernel/cpu/sh4/setup-sh7750.c
	arch/sh/kernel/cpu/sh4/setup-sh7760.c
	arch/sh/kernel/cpu/sh4a/setup-sh7343.c
	arch/sh/kernel/cpu/sh4a/setup-sh7366.c
	arch/sh/kernel/cpu/sh4a/setup-sh7722.c
	arch/sh/kernel/cpu/sh4a/setup-sh7723.c
	arch/sh/kernel/cpu/sh4a/setup-sh7724.c
	arch/sh/kernel/cpu/sh4a/setup-sh7763.c
	arch/sh/kernel/cpu/sh4a/setup-sh7770.c
	arch/sh/kernel/cpu/sh4a/setup-sh7780.c
	arch/sh/kernel/cpu/sh4a/setup-sh7785.c
	arch/sh/kernel/cpu/sh4a/setup-sh7786.c
	arch/sh/kernel/cpu/sh4a/setup-shx3.c
	arch/sh/kernel/cpu/sh5/setup-sh5.c
	drivers/serial/sh-sci.c
	drivers/serial/sh-sci.h
	include/linux/serial_sci.h

1 files changed, 269 insertions, 1 deletions

diff --git a/arch/sh/kernel/ftrace.c b/arch/sh/kernel/ftrace.c
index 066f37dc32a9..30e13196d35b 100644
--- a/arch/sh/kernel/ftrace.c
+++ b/arch/sh/kernel/ftrace.c
@@ -16,9 +16,13 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/io.h>
+#include <linux/kernel.h>
 #include <asm/ftrace.h>
 #include <asm/cacheflush.h>
+#include <asm/unistd.h>
+#include <trace/syscall.h>
 
+#ifdef CONFIG_DYNAMIC_FTRACE
 static unsigned char ftrace_replaced_code[MCOUNT_INSN_SIZE];
 
 static unsigned char ftrace_nop[4];
@@ -58,6 +62,150 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
         return ftrace_replaced_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 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)
+{
+        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)
+{
+        /* 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 int
+do_ftrace_mod_code(unsigned long ip, void *new_code)
+{
+        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;
+}
+
 static int ftrace_modify_code(unsigned long ip, unsigned char *old_code,
                        unsigned char *new_code)
 {
@@ -82,7 +230,7 @@ static int ftrace_modify_code(unsigned long ip, unsigned char *old_code,
                 return -EINVAL;
 
         /* replace the text with the new text */
-        if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
+        if (do_ftrace_mod_code(ip, new_code))
                 return -EPERM;
 
         flush_icache_range(ip, ip + MCOUNT_INSN_SIZE);
@@ -131,3 +279,123 @@ int __init ftrace_dyn_arch_init(void *data)
 
         return 0;
 }
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+#ifdef CONFIG_DYNAMIC_FTRACE
+extern void ftrace_graph_call(void);
+
+static int ftrace_mod(unsigned long ip, unsigned long old_addr,
+                      unsigned long new_addr)
+{
+        unsigned char code[MCOUNT_INSN_SIZE];
+
+        if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE))
+                return -EFAULT;
+
+        if (old_addr != __raw_readl((unsigned long *)code))
+                return -EINVAL;
+
+        __raw_writel(new_addr, ip);
+        return 0;
+}
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+        unsigned long ip, old_addr, new_addr;
+
+        ip = (unsigned long)(&ftrace_graph_call) + GRAPH_INSN_OFFSET;
+        old_addr = (unsigned long)(&skip_trace);
+        new_addr = (unsigned long)(&ftrace_graph_caller);
+
+        return ftrace_mod(ip, old_addr, new_addr);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+        unsigned long ip, old_addr, new_addr;
+
+        ip = (unsigned long)(&ftrace_graph_call) + GRAPH_INSN_OFFSET;
+        old_addr = (unsigned long)(&ftrace_graph_caller);
+        new_addr = (unsigned long)(&skip_trace);
+
+        return ftrace_mod(ip, old_addr, new_addr);
+}
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+/*
+ * Hook the return address and push it in the stack of return addrs
+ * in the current thread info.
+ *
+ * This is the main routine for the function graph tracer. The function
+ * graph tracer essentially works like this:
+ *
+ * parent is the stack address containing self_addr's return address.
+ * We pull the real return address out of parent and store it in
+ * current's ret_stack. Then, we replace the return address on the stack
+ * with the address of return_to_handler. self_addr is the function that
+ * called mcount.
+ *
+ * When self_addr returns, it will jump to return_to_handler which calls
+ * ftrace_return_to_handler. ftrace_return_to_handler will pull the real
+ * return address off of current's ret_stack and jump to it.
+ */
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
+{
+        unsigned long old;
+        int faulted, err;
+        struct ftrace_graph_ent trace;
+        unsigned long return_hooker = (unsigned long)&return_to_handler;
+
+        if (unlikely(atomic_read(&current->tracing_graph_pause)))
+                return;
+
+        /*
+         * Protect against fault, even if it shouldn't
+         * happen. This tool is too much intrusive to
+         * ignore such a protection.
+         */
+        __asm__ __volatile__(
+                "1:                                             \n\t"
+                "mov.l          @%2, %0                         \n\t"
+                "2:                                             \n\t"
+                "mov.l          %3, @%2                         \n\t"
+                "mov            #0, %1                          \n\t"
+                "3:                                             \n\t"
+                ".section .fixup, \"ax\"                        \n\t"
+                "4:                                             \n\t"
+                "mov.l          5f, %0                          \n\t"
+                "jmp            @%0                             \n\t"
+                " mov           #1, %1                          \n\t"
+                ".balign 4                                      \n\t"
+                "5:     .long 3b                                \n\t"
+                ".previous                                      \n\t"
+                ".section __ex_table,\"a\"                      \n\t"
+                ".long 1b, 4b                                   \n\t"
+                ".long 2b, 4b                                   \n\t"
+                ".previous                                      \n\t"
+                : "=&r" (old), "=r" (faulted)
+                : "r" (parent), "r" (return_hooker)
+        );
+
+        if (unlikely(faulted)) {
+                ftrace_graph_stop();
+                WARN_ON(1);
+                return;
+        }
+
+        err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0);
+        if (err == -EBUSY) {
+                __raw_writel(old, parent);
+                return;
+        }
+
+        trace.func = self_addr;
+
+        /* Only trace if the calling function expects to */
+        if (!ftrace_graph_entry(&trace)) {
+                current->curr_ret_stack--;
+                __raw_writel(old, parent);
+        }
+}
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */