On Tue, Apr 30, 2019 at 11:33:21AM -0700, Linus Torvalds wrote:
Anyway, since Andy really likes the entry code change, can we have that patch in parallel and judge the difference that way? Iirc, that was x86-64 specific too.
Here goes, compile tested only...
It obviously needs a self-test, but that shoulnd't be too hard to arrange.
--- arch/x86/entry/entry_32.S | 7 +++++++ arch/x86/entry/entry_64.S | 14 ++++++++++++-- arch/x86/include/asm/text-patching.h | 20 ++++++++++++++++++++ arch/x86/kernel/ftrace.c | 24 +++++++++++++++++++----- 4 files changed, 58 insertions(+), 7 deletions(-)
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 7b23431be5cb..d246302085a3 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -1479,6 +1479,13 @@ ENTRY(int3) ASM_CLAC pushl $-1 # mark this as an int
+ testl $SEGMENT_RPL_MASK, PT_CS(%esp) + jnz .Lfrom_usermode_no_gap + .rept 6 + pushl 5*4(%esp) + .endr +.Lfrom_usermode_no_gap: + SAVE_ALL switch_stacks=1 ENCODE_FRAME_POINTER TRACE_IRQS_OFF diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 20e45d9b4e15..268cd9affe04 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -878,7 +878,7 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt * @paranoid == 2 is special: the stub will never switch stacks. This is for * #DF: if the thread stack is somehow unusable, we'll still get a useful OOPS. */ -.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ist_offset=0 +.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ist_offset=0 create_gap=0 ENTRY(\sym) UNWIND_HINT_IRET_REGS offset=\has_error_code*8
@@ -898,6 +898,16 @@ ENTRY(\sym) jnz .Lfrom_usermode_switch_stack_@ .endif
+ .if \create_gap == 1 + testb $3, CS-ORIG_RAX(%rsp) + jnz .Lfrom_usermode_no_gap_@ + .rept 6 + pushq 5*8(%rsp) + .endr + UNWIND_HINT_IRET_REGS offset=8 +.Lfrom_usermode_no_gap_@: + .endif + .if \paranoid call paranoid_entry .else @@ -1129,7 +1139,7 @@ apicinterrupt3 HYPERV_STIMER0_VECTOR \ #endif /* CONFIG_HYPERV */
idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=IST_INDEX_DB ist_offset=DB_STACK_OFFSET -idtentry int3 do_int3 has_error_code=0 +idtentry int3 do_int3 has_error_code=0 create_gap=1 idtentry stack_segment do_stack_segment has_error_code=1
#ifdef CONFIG_XEN_PV diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index e85ff65c43c3..ba275b6292db 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -39,4 +39,24 @@ extern int poke_int3_handler(struct pt_regs *regs); extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler); extern int after_bootmem;
+static inline void int3_emulate_push(struct pt_regs *regs, unsigned long val) +{ + regs->sp -= sizeof(unsigned long); + *(unsigned long *)regs->sp = val; +} + +static inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip) +{ + regs->ip = ip; +} + +#define INT3_INSN_SIZE 1 +#define CALL_INSN_SIZE 5 + +static inline void int3_emulate_call(struct pt_regs *regs, unsigned long func) +{ + int3_emulate_push(regs, regs->ip - INT3_INSN_SIZE + CALL_INSN_SIZE); + int3_emulate_jmp(regs, func); +} + #endif /* _ASM_X86_TEXT_PATCHING_H */ diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index ef49517f6bb2..90d319687d7e 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -29,6 +29,7 @@ #include <asm/kprobes.h> #include <asm/ftrace.h> #include <asm/nops.h> +#include <asm/text-patching.h>
#ifdef CONFIG_DYNAMIC_FTRACE
@@ -231,6 +232,7 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, }
static unsigned long ftrace_update_func; +static unsigned long ftrace_update_func_call;
static int update_ftrace_func(unsigned long ip, void *new) { @@ -259,6 +261,8 @@ int ftrace_update_ftrace_func(ftrace_func_t func) unsigned char *new; int ret;
+ ftrace_update_func_call = (unsigned long)func; + new = ftrace_call_replace(ip, (unsigned long)func); ret = update_ftrace_func(ip, new);
@@ -295,12 +299,19 @@ int ftrace_int3_handler(struct pt_regs *regs) return 0;
ip = regs->ip - 1; - if (!ftrace_location(ip) && !is_ftrace_caller(ip)) - return 0; - - regs->ip += MCOUNT_INSN_SIZE - 1; + if (ftrace_location(ip)) { + int3_emulate_call(regs, ftrace_update_func_call); + return 1; + } else if (is_ftrace_caller(ip)) { + if (!ftrace_update_func_call) { + int3_emulate_jmp(regs, regs->ip - INT3_INSN_SIZE + CALL_INSN_SIZE); + return 1; + } + int3_emulate_call(regs, ftrace_update_func_call); + return 1; + }
- return 1; + return 0; } NOKPROBE_SYMBOL(ftrace_int3_handler);
@@ -859,6 +870,8 @@ void arch_ftrace_update_trampoline(struct ftrace_ops *ops)
func = ftrace_ops_get_func(ops);
+ ftrace_update_func_call = (unsigned long)func; + /* Do a safe modify in case the trampoline is executing */ new = ftrace_call_replace(ip, (unsigned long)func); ret = update_ftrace_func(ip, new); @@ -960,6 +973,7 @@ static int ftrace_mod_jmp(unsigned long ip, void *func) { unsigned char *new;
+ ftrace_update_func_call = 0UL; new = ftrace_jmp_replace(ip, (unsigned long)func);
return update_ftrace_func(ip, new);