lkml.org 
[lkml]   [2010]   [Jul]   [27]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    Patch in this message
    /
    Date
    From
    Subject[PATCH 03/12] jump label v10: move ftrace_dyn_arch_init to common code
    Move Steve's code for finding the best 5-byte no-op from ftrace.c to alternative.c.
    The idea is that other consumers (in this case jump label) want to make use of
    that code. I've created a global: 'char ideal_nop[5]', that is setup during
    setup_arch that can be used.

    Signed-off-by: Jason Baron <jbaron@redhat.com>
    ---
    arch/x86/include/asm/alternative.h | 14 +++++++
    arch/x86/kernel/alternative.c | 72 +++++++++++++++++++++++++++++++++++-
    arch/x86/kernel/ftrace.c | 70 +----------------------------------
    arch/x86/kernel/setup.c | 3 +
    include/linux/jump_label.h | 10 ++++-
    kernel/jump_label.c | 32 ++++++++++++++++
    kernel/trace/ftrace.c | 13 +------
    7 files changed, 130 insertions(+), 84 deletions(-)

    diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
    index bc6abb7..963f5f9 100644
    --- a/arch/x86/include/asm/alternative.h
    +++ b/arch/x86/include/asm/alternative.h
    @@ -4,6 +4,7 @@
    #include <linux/types.h>
    #include <linux/stddef.h>
    #include <linux/stringify.h>
    +#include <linux/jump_label.h>
    #include <asm/asm.h>

    /*
    @@ -160,6 +161,8 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
    #define __parainstructions_end NULL
    #endif

    +extern void *text_poke_early(void *addr, const void *opcode, size_t len);
    +
    /*
    * Clear and restore the kernel write-protection flag on the local CPU.
    * Allows the kernel to edit read-only pages.
    @@ -180,4 +183,15 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
    extern void *text_poke(void *addr, const void *opcode, size_t len);
    extern void *text_poke_smp(void *addr, const void *opcode, size_t len);

    +#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
    +#define IDEAL_NOP_SIZE_5 5
    +extern unsigned char ideal_nop5[IDEAL_NOP_SIZE_5];
    +extern int arch_init_ideal_nop5(void);
    +#else
    +static inline int arch_init_ideal_nop5(void)
    +{
    + return 0;
    +}
    +#endif
    +
    #endif /* _ASM_X86_ALTERNATIVE_H */
    diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
    index f65ab8b..df5a4f2 100644
    --- a/arch/x86/kernel/alternative.c
    +++ b/arch/x86/kernel/alternative.c
    @@ -195,7 +195,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len)

    extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
    extern s32 __smp_locks[], __smp_locks_end[];
    -static void *text_poke_early(void *addr, const void *opcode, size_t len);
    +void *text_poke_early(void *addr, const void *opcode, size_t len);

    /* Replace instructions with better alternatives for this CPU type.
    This runs before SMP is initialized to avoid SMP problems with
    @@ -522,7 +522,7 @@ void __init alternative_instructions(void)
    * instructions. And on the local CPU you need to be protected again NMI or MCE
    * handlers seeing an inconsistent instruction while you patch.
    */
    -static void *__init_or_module text_poke_early(void *addr, const void *opcode,
    +void *__init_or_module text_poke_early(void *addr, const void *opcode,
    size_t len)
    {
    unsigned long flags;
    @@ -641,3 +641,71 @@ void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len)
    return addr;
    }

    +#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
    +
    +unsigned char ideal_nop5[IDEAL_NOP_SIZE_5];
    +
    +int __init arch_init_ideal_nop5(void)
    +{
    + extern const unsigned char ftrace_test_p6nop[];
    + extern const unsigned char ftrace_test_nop5[];
    + extern const unsigned char ftrace_test_jmp[];
    + int faulted = 0;
    + unsigned long flags;
    +
    + local_irq_save(flags);
    + /*
    + * There is no good nop for all x86 archs.
    + * We will default to using the P6_NOP5, but first we
    + * will test to make sure that the nop will actually
    + * work on this CPU. If it faults, we will then
    + * go to a lesser efficient 5 byte nop. If that fails
    + * we then just use a jmp as our nop. This isn't the most
    + * efficient nop, but we can not use a multi part nop
    + * since we would then risk being preempted in the middle
    + * of that nop, and if we enabled tracing then, it might
    + * cause a system crash.
    + *
    + * TODO: check the cpuid to determine the best nop.
    + */
    + asm volatile (
    + "ftrace_test_jmp:"
    + "jmp ftrace_test_p6nop\n"
    + "nop\n"
    + "nop\n"
    + "nop\n" /* 2 byte jmp + 3 bytes */
    + "ftrace_test_p6nop:"
    + P6_NOP5
    + "jmp 1f\n"
    + "ftrace_test_nop5:"
    + ".byte 0x66,0x66,0x66,0x66,0x90\n"
    + "1:"
    + ".section .fixup, \"ax\"\n"
    + "2: movl $1, %0\n"
    + " jmp ftrace_test_nop5\n"
    + "3: movl $2, %0\n"
    + " jmp 1b\n"
    + ".previous\n"
    + _ASM_EXTABLE(ftrace_test_p6nop, 2b)
    + _ASM_EXTABLE(ftrace_test_nop5, 3b)
    + : "=r"(faulted) : "0" (faulted));
    +
    + switch (faulted) {
    + case 0:
    + pr_info("converting mcount calls to 0f 1f 44 00 00\n");
    + memcpy(ideal_nop5, ftrace_test_p6nop, IDEAL_NOP_SIZE_5);
    + break;
    + case 1:
    + pr_info("converting mcount calls to 66 66 66 66 90\n");
    + memcpy(ideal_nop5, ftrace_test_nop5, IDEAL_NOP_SIZE_5);
    + break;
    + case 2:
    + pr_info("converting mcount calls to jmp . + 5\n");
    + memcpy(ideal_nop5, ftrace_test_jmp, IDEAL_NOP_SIZE_5);
    + break;
    + }
    +
    + local_irq_restore(flags);
    + return 0;
    +}
    +#endif
    diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
    index cd37469..ba2e0d9 100644
    --- a/arch/x86/kernel/ftrace.c
    +++ b/arch/x86/kernel/ftrace.c
    @@ -257,14 +257,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code)
    return mod_code_status;
    }

    -
    -
    -
    -static unsigned char ftrace_nop[MCOUNT_INSN_SIZE];
    -
    static unsigned char *ftrace_nop_replace(void)
    {
    - return ftrace_nop;
    + return ideal_nop5;
    }

    static int
    @@ -336,69 +331,6 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
    return ret;
    }

    -int __init ftrace_dyn_arch_init(void *data)
    -{
    - extern const unsigned char ftrace_test_p6nop[];
    - extern const unsigned char ftrace_test_nop5[];
    - extern const unsigned char ftrace_test_jmp[];
    - int faulted = 0;
    -
    - /*
    - * There is no good nop for all x86 archs.
    - * We will default to using the P6_NOP5, but first we
    - * will test to make sure that the nop will actually
    - * work on this CPU. If it faults, we will then
    - * go to a lesser efficient 5 byte nop. If that fails
    - * we then just use a jmp as our nop. This isn't the most
    - * efficient nop, but we can not use a multi part nop
    - * since we would then risk being preempted in the middle
    - * of that nop, and if we enabled tracing then, it might
    - * cause a system crash.
    - *
    - * TODO: check the cpuid to determine the best nop.
    - */
    - asm volatile (
    - "ftrace_test_jmp:"
    - "jmp ftrace_test_p6nop\n"
    - "nop\n"
    - "nop\n"
    - "nop\n" /* 2 byte jmp + 3 bytes */
    - "ftrace_test_p6nop:"
    - P6_NOP5
    - "jmp 1f\n"
    - "ftrace_test_nop5:"
    - ".byte 0x66,0x66,0x66,0x66,0x90\n"
    - "1:"
    - ".section .fixup, \"ax\"\n"
    - "2: movl $1, %0\n"
    - " jmp ftrace_test_nop5\n"
    - "3: movl $2, %0\n"
    - " jmp 1b\n"
    - ".previous\n"
    - _ASM_EXTABLE(ftrace_test_p6nop, 2b)
    - _ASM_EXTABLE(ftrace_test_nop5, 3b)
    - : "=r"(faulted) : "0" (faulted));
    -
    - switch (faulted) {
    - case 0:
    - pr_info("converting mcount calls to 0f 1f 44 00 00\n");
    - memcpy(ftrace_nop, ftrace_test_p6nop, MCOUNT_INSN_SIZE);
    - break;
    - case 1:
    - pr_info("converting mcount calls to 66 66 66 66 90\n");
    - memcpy(ftrace_nop, ftrace_test_nop5, MCOUNT_INSN_SIZE);
    - break;
    - case 2:
    - pr_info("converting mcount calls to jmp . + 5\n");
    - memcpy(ftrace_nop, ftrace_test_jmp, MCOUNT_INSN_SIZE);
    - break;
    - }
    -
    - /* The return code is retured via data */
    - *(unsigned long *)data = 0;
    -
    - return 0;
    -}
    #endif

    #ifdef CONFIG_FUNCTION_GRAPH_TRACER
    diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
    index b008e78..cb28d82 100644
    --- a/arch/x86/kernel/setup.c
    +++ b/arch/x86/kernel/setup.c
    @@ -49,6 +49,7 @@
    #include <asm/pci-direct.h>
    #include <linux/init_ohci1394_dma.h>
    #include <linux/kvm_para.h>
    +#include <linux/jump_label.h>

    #include <linux/errno.h>
    #include <linux/kernel.h>
    @@ -1069,6 +1070,8 @@ void __init setup_arch(char **cmdline_p)
    x86_init.oem.banner();

    mcheck_init();
    +
    + arch_init_ideal_nop5();
    }

    #ifdef CONFIG_X86_32
    diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
    index 9ac29c0..fc2b181 100644
    --- a/include/linux/jump_label.h
    +++ b/include/linux/jump_label.h
    @@ -11,6 +11,8 @@ enum jump_label_type {
    JUMP_LABEL_DISABLE
    };

    +struct module;
    +
    #ifdef HAVE_JUMP_LABEL

    extern struct jump_entry __start___jump_table[];
    @@ -23,8 +25,9 @@ extern struct jump_entry __stop___jump_table[];

    extern void arch_jump_label_transform(struct jump_entry *entry,
    enum jump_label_type type);
    -extern const u8 *arch_jump_label_get_nop(void);
    extern void jump_label_update(const char *name, enum jump_label_type type);
    +extern void jump_label_apply_nops(struct module *mod);
    +extern void arch_jump_label_text_poke_early(jump_label_t addr);

    #define enable_jump_label(name) \
    jump_label_update(name, JUMP_LABEL_ENABLE);
    @@ -52,6 +55,11 @@ static inline int disable_jump_label(const char *name)
    return 0;
    }

    +static inline int jump_label_apply_nops(struct module *mod)
    +{
    + return 0;
    +}
    +
    #endif

    #endif
    diff --git a/kernel/jump_label.c b/kernel/jump_label.c
    index ecca4f4..ebe9145 100644
    --- a/kernel/jump_label.c
    +++ b/kernel/jump_label.c
    @@ -11,6 +11,7 @@
    #include <linux/list.h>
    #include <linux/jhash.h>
    #include <linux/slab.h>
    +#include <linux/err.h>

    #ifdef HAVE_JUMP_LABEL

    @@ -185,10 +186,18 @@ void jump_label_update(const char *name, enum jump_label_type type)
    static __init int init_jump_label(void)
    {
    int ret;
    + struct jump_entry *iter_start = __start___jump_table;
    + struct jump_entry *iter_stop = __stop___jump_table;
    + struct jump_entry *iter;

    mutex_lock(&jump_label_mutex);
    ret = build_jump_label_hashtable(__start___jump_table,
    __stop___jump_table);
    + iter = iter_start;
    + while (iter < iter_stop) {
    + arch_jump_label_text_poke_early(iter->code);
    + iter++;
    + }
    mutex_unlock(&jump_label_mutex);
    return ret;
    }
    @@ -299,6 +308,29 @@ static int jump_label_module_notify(struct notifier_block *self, unsigned long v
    return ret;
    }

    +/***
    + * apply_jump_label_nops - patch module jump labels with arch_get_jump_label_nop()
    + * @mod: module to patch
    + *
    + * Allow for run-time selection of the optimal nops. Before the module
    + * loads patch these with arch_get_jump_label_nop(), which is specified by
    + * the arch specific jump label code.
    + */
    +void jump_label_apply_nops(struct module *mod)
    +{
    + struct jump_entry *iter;
    +
    + /* if the module doesn't have jump label entries, just return */
    + if (!mod->num_jump_entries)
    + return;
    +
    + iter = mod->jump_entries;
    + while (iter < mod->jump_entries + mod->num_jump_entries) {
    + arch_jump_label_text_poke_early(iter->code);
    + iter++;
    + }
    +}
    +
    struct notifier_block jump_label_module_nb = {
    .notifier_call = jump_label_module_notify,
    .priority = 0,
    diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
    index 0d88ce9..1a1cc47 100644
    --- a/kernel/trace/ftrace.c
    +++ b/kernel/trace/ftrace.c
    @@ -2749,20 +2749,9 @@ extern unsigned long __stop_mcount_loc[];

    void __init ftrace_init(void)
    {
    - unsigned long count, addr, flags;
    + unsigned long count;
    int ret;

    - /* Keep the ftrace pointer to the stub */
    - addr = (unsigned long)ftrace_stub;
    -
    - local_irq_save(flags);
    - ftrace_dyn_arch_init(&addr);
    - local_irq_restore(flags);
    -
    - /* ftrace_dyn_arch_init places the return code in addr */
    - if (addr)
    - goto failed;
    -
    count = __stop_mcount_loc - __start_mcount_loc;

    ret = ftrace_dyn_table_alloc(count);
    --
    1.7.1


    \
     
     \ /
      Last update: 2010-07-27 22:57    [W:5.198 / U:0.212 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site