OpenCloudOS-Kernel/arch/x86/include/asm/alternative.h

275 lines
9.6 KiB
C
Raw Normal View History

#ifndef _ASM_X86_ALTERNATIVE_H
#define _ASM_X86_ALTERNATIVE_H
#include <linux/types.h>
#include <linux/stddef.h>
#include <linux/stringify.h>
#include <asm/asm.h>
kprobes/x86: Call out into INT3 handler directly instead of using notifier In fd4363fff3d96 ("x86: Introduce int3 (breakpoint)-based instruction patching"), the mechanism that was introduced for notifying alternatives code from int3 exception handler that and exception occured was die_notifier. This is however problematic, as early code might be using jump labels even before the notifier registration has been performed, which will then lead to an oops due to unhandled exception. One of such occurences has been encountered by Fengguang: int3: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Modules linked in: CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.11.0-rc1-01429-g04bf576 #8 task: ffff88000da1b040 ti: ffff88000da1c000 task.ti: ffff88000da1c000 RIP: 0010:[<ffffffff811098cc>] [<ffffffff811098cc>] ttwu_do_wakeup+0x28/0x225 RSP: 0000:ffff88000dd03f10 EFLAGS: 00000006 RAX: 0000000000000000 RBX: ffff88000dd12940 RCX: ffffffff81769c40 RDX: 0000000000000002 RSI: 0000000000000000 RDI: 0000000000000001 RBP: ffff88000dd03f28 R08: ffffffff8176a8c0 R09: 0000000000000002 R10: ffffffff810ff484 R11: ffff88000dd129e8 R12: ffff88000dbc90c0 R13: ffff88000dbc90c0 R14: ffff88000da1dfd8 R15: ffff88000da1dfd8 FS: 0000000000000000(0000) GS:ffff88000dd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00000000ffffffff CR3: 0000000001c88000 CR4: 00000000000006e0 Stack: ffff88000dd12940 ffff88000dbc90c0 ffff88000da1dfd8 ffff88000dd03f48 ffffffff81109e2b ffff88000dd12940 0000000000000000 ffff88000dd03f68 ffffffff81109e9e 0000000000000000 0000000000012940 ffff88000dd03f98 Call Trace: <IRQ> [<ffffffff81109e2b>] ttwu_do_activate.constprop.56+0x6d/0x79 [<ffffffff81109e9e>] sched_ttwu_pending+0x67/0x84 [<ffffffff8110c845>] scheduler_ipi+0x15a/0x2b0 [<ffffffff8104dfb4>] smp_reschedule_interrupt+0x38/0x41 [<ffffffff8173bf5d>] reschedule_interrupt+0x6d/0x80 <EOI> [<ffffffff810ff484>] ? __atomic_notifier_call_chain+0x5/0xc1 [<ffffffff8105cc30>] ? native_safe_halt+0xd/0x16 [<ffffffff81015f10>] default_idle+0x147/0x282 [<ffffffff81017026>] arch_cpu_idle+0x3d/0x5d [<ffffffff81127d6a>] cpu_idle_loop+0x46d/0x5db [<ffffffff81127f5c>] cpu_startup_entry+0x84/0x84 [<ffffffff8104f4f8>] start_secondary+0x3c8/0x3d5 [...] Fix this by directly calling poke_int3_handler() from the int3 exception handler (analogically to what ftrace has been doing already), instead of relying on notifier, registration of which might not have yet been finalized by the time of the first trap. Reported-and-tested-by: Fengguang Wu <fengguang.wu@intel.com> Signed-off-by: Jiri Kosina <jkosina@suse.cz> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: H. Peter Anvin <hpa@linux.intel.com> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/alpine.LNX.2.00.1307231007490.14024@pobox.suse.cz Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-07-23 16:09:28 +08:00
#include <asm/ptrace.h>
/*
* Alternative inline assembly for SMP.
*
* The LOCK_PREFIX macro defined here replaces the LOCK and
* LOCK_PREFIX macros used everywhere in the source tree.
*
* SMP alternatives use the same data structures as the other
* alternatives and the X86_FEATURE_UP flag to indicate the case of a
* UP system running a SMP kernel. The existing apply_alternatives()
* works fine for patching a SMP kernel for UP.
*
* The SMP alternative tables can be kept after boot and contain both
* UP and SMP versions of the instructions to allow switching back to
* SMP at runtime, when hotplugging in a new CPU, which is especially
* useful in virtualized environments.
*
* The very common lock prefix is handled as special case in a
* separate table which is a pure address list without replacement ptr
* and size information. That keeps the table sizes small.
*/
#ifdef CONFIG_SMP
#define LOCK_PREFIX_HERE \
".pushsection .smp_locks,\"a\"\n" \
".balign 4\n" \
".long 671f - .\n" /* offset */ \
".popsection\n" \
"671:"
#define LOCK_PREFIX LOCK_PREFIX_HERE "\n\tlock; "
#else /* ! CONFIG_SMP */
#define LOCK_PREFIX_HERE ""
#define LOCK_PREFIX ""
#endif
struct alt_instr {
s32 instr_offset; /* original instruction */
s32 repl_offset; /* offset to replacement instruction */
u16 cpuid; /* cpuid bit set for replacement */
u8 instrlen; /* length of original instruction */
u8 replacementlen; /* length of new instruction */
u8 padlen; /* length of build-time padding */
} __packed;
/*
* Debug flag that can be tested to see whether alternative
* instructions were patched in already:
*/
extern int alternatives_patched;
extern void alternative_instructions(void);
extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
struct module;
#ifdef CONFIG_SMP
extern void alternatives_smp_module_add(struct module *mod, char *name,
void *locks, void *locks_end,
void *text, void *text_end);
extern void alternatives_smp_module_del(struct module *mod);
extern void alternatives_enable_smp(void);
extern int alternatives_text_reserved(void *start, void *end);
extern bool skip_smp_alternatives;
#else
static inline void alternatives_smp_module_add(struct module *mod, char *name,
void *locks, void *locks_end,
void *text, void *text_end) {}
static inline void alternatives_smp_module_del(struct module *mod) {}
static inline void alternatives_enable_smp(void) {}
static inline int alternatives_text_reserved(void *start, void *end)
{
return 0;
}
#endif /* CONFIG_SMP */
#define b_replacement(num) "664"#num
#define e_replacement(num) "665"#num
#define alt_end_marker "663"
#define alt_slen "662b-661b"
#define alt_pad_len alt_end_marker"b-662b"
#define alt_total_slen alt_end_marker"b-661b"
#define alt_rlen(num) e_replacement(num)"f-"b_replacement(num)"f"
#define __OLDINSTR(oldinstr, num) \
"661:\n\t" oldinstr "\n662:\n" \
".skip -(((" alt_rlen(num) ")-(" alt_slen ")) > 0) * " \
"((" alt_rlen(num) ")-(" alt_slen ")),0x90\n"
#define OLDINSTR(oldinstr, num) \
__OLDINSTR(oldinstr, num) \
alt_end_marker ":\n"
x86/alternatives: Fix ALTERNATIVE_2 padding generation properly Quentin caught a corner case with the generation of instruction padding in the ALTERNATIVE_2 macro: if len(orig_insn) < len(alt1) < len(alt2), then not enough padding gets added and that is not good(tm) as we could overwrite the beginning of the next instruction. Luckily, at the time of this writing, we don't have ALTERNATIVE_2() invocations which have that problem and even if we did, a simple fix would be to prepend the instructions with enough prefixes so that that corner case doesn't happen. However, best it would be if we fixed it properly. See below for a simple, abstracted example of what we're doing. So what we ended up doing is, we compute the max(len(alt1), len(alt2)) - len(orig_insn) and feed that value to the .skip gas directive. The max() cannot have conditionals due to gas limitations, thus the fancy integer math. With this patch, all ALTERNATIVE_2 sites get padded correctly; generating obscure test cases pass too: #define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b))))) #define gen_skip(orig, alt1, alt2, marker) \ .skip -((alt_max_short(alt1, alt2) - (orig)) > 0) * \ (alt_max_short(alt1, alt2) - (orig)),marker .pushsection .text, "ax" .globl main main: gen_skip(1, 2, 4, 0x09) gen_skip(4, 1, 2, 0x10) ... .popsection Thanks to Quentin for catching it and double-checking the fix! Reported-by: Quentin Casasnovas <quentin.casasnovas@oracle.com> Signed-off-by: Borislav Petkov <bp@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20150404133443.GE21152@pd.tnic Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-04 21:34:43 +08:00
/*
* max without conditionals. Idea adapted from:
* http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
*
* The additional "-" is needed because gas works with s32s.
*/
#define alt_max_short(a, b) "((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") - (" b ")))))"
/*
* Pad the second replacement alternative with additional NOPs if it is
* additionally longer than the first replacement alternative.
*/
x86/alternatives: Fix ALTERNATIVE_2 padding generation properly Quentin caught a corner case with the generation of instruction padding in the ALTERNATIVE_2 macro: if len(orig_insn) < len(alt1) < len(alt2), then not enough padding gets added and that is not good(tm) as we could overwrite the beginning of the next instruction. Luckily, at the time of this writing, we don't have ALTERNATIVE_2() invocations which have that problem and even if we did, a simple fix would be to prepend the instructions with enough prefixes so that that corner case doesn't happen. However, best it would be if we fixed it properly. See below for a simple, abstracted example of what we're doing. So what we ended up doing is, we compute the max(len(alt1), len(alt2)) - len(orig_insn) and feed that value to the .skip gas directive. The max() cannot have conditionals due to gas limitations, thus the fancy integer math. With this patch, all ALTERNATIVE_2 sites get padded correctly; generating obscure test cases pass too: #define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b))))) #define gen_skip(orig, alt1, alt2, marker) \ .skip -((alt_max_short(alt1, alt2) - (orig)) > 0) * \ (alt_max_short(alt1, alt2) - (orig)),marker .pushsection .text, "ax" .globl main main: gen_skip(1, 2, 4, 0x09) gen_skip(4, 1, 2, 0x10) ... .popsection Thanks to Quentin for catching it and double-checking the fix! Reported-by: Quentin Casasnovas <quentin.casasnovas@oracle.com> Signed-off-by: Borislav Petkov <bp@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20150404133443.GE21152@pd.tnic Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-04 21:34:43 +08:00
#define OLDINSTR_2(oldinstr, num1, num2) \
"661:\n\t" oldinstr "\n662:\n" \
".skip -((" alt_max_short(alt_rlen(num1), alt_rlen(num2)) " - (" alt_slen ")) > 0) * " \
"(" alt_max_short(alt_rlen(num1), alt_rlen(num2)) " - (" alt_slen ")), 0x90\n" \
alt_end_marker ":\n"
#define ALTINSTR_ENTRY(feature, num) \
" .long 661b - .\n" /* label */ \
" .long " b_replacement(num)"f - .\n" /* new instruction */ \
" .word " __stringify(feature) "\n" /* feature bit */ \
" .byte " alt_total_slen "\n" /* source len */ \
" .byte " alt_rlen(num) "\n" /* replacement len */ \
" .byte " alt_pad_len "\n" /* pad len */
#define ALTINSTR_REPLACEMENT(newinstr, feature, num) /* replacement */ \
b_replacement(num)":\n\t" newinstr "\n" e_replacement(num) ":\n\t"
/* alternative assembly primitive: */
#define ALTERNATIVE(oldinstr, newinstr, feature) \
OLDINSTR(oldinstr, 1) \
".pushsection .altinstructions,\"a\"\n" \
ALTINSTR_ENTRY(feature, 1) \
".popsection\n" \
".pushsection .altinstr_replacement, \"ax\"\n" \
ALTINSTR_REPLACEMENT(newinstr, feature, 1) \
".popsection"
#define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\
OLDINSTR_2(oldinstr, 1, 2) \
".pushsection .altinstructions,\"a\"\n" \
ALTINSTR_ENTRY(feature1, 1) \
ALTINSTR_ENTRY(feature2, 2) \
".popsection\n" \
".pushsection .altinstr_replacement, \"ax\"\n" \
ALTINSTR_REPLACEMENT(newinstr1, feature1, 1) \
ALTINSTR_REPLACEMENT(newinstr2, feature2, 2) \
".popsection"
/*
* This must be included *after* the definition of ALTERNATIVE due to
* <asm/arch_hweight.h>
*/
#include <asm/cpufeature.h>
/*
* Alternative instructions for different CPU types or capabilities.
*
* This allows to use optimized instructions even on generic binary
* kernels.
*
* length of oldinstr must be longer or equal the length of newinstr
* It can be padded with nops as needed.
*
* For non barrier like inlines please define new variants
* without volatile and memory clobber.
*/
#define alternative(oldinstr, newinstr, feature) \
asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) : : : "memory")
#define alternative_2(oldinstr, newinstr1, feature1, newinstr2, feature2) \
asm volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2) ::: "memory")
/*
* Alternative inline assembly with input.
*
* Pecularities:
* No memory clobber here.
* Argument numbers start with 1.
* Best is to use constraints that are fixed size (like (%1) ... "r")
* If you use variable sized constraints like "m" or "g" in the
* replacement make sure to pad to the worst case length.
* Leaving an unused argument 0 to keep API compatibility.
*/
#define alternative_input(oldinstr, newinstr, feature, input...) \
asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) \
: : "i" (0), ## input)
/*
* This is similar to alternative_input. But it has two features and
* respective instructions.
*
* If CPU has feature2, newinstr2 is used.
* Otherwise, if CPU has feature1, newinstr1 is used.
* Otherwise, oldinstr is used.
*/
#define alternative_input_2(oldinstr, newinstr1, feature1, newinstr2, \
feature2, input...) \
asm volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, \
newinstr2, feature2) \
: : "i" (0), ## input)
/* Like alternative_input, but with a single output argument */
#define alternative_io(oldinstr, newinstr, feature, output, input...) \
asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) \
: output : "i" (0), ## input)
/* Like alternative_io, but for replacing a direct call with another one. */
#define alternative_call(oldfunc, newfunc, feature, output, input...) \
asm volatile (ALTERNATIVE("call %P[old]", "call %P[new]", feature) \
: output : [old] "i" (oldfunc), [new] "i" (newfunc), ## input)
/*
* Like alternative_call, but there are two features and respective functions.
* If CPU has feature2, function2 is used.
* Otherwise, if CPU has feature1, function1 is used.
* Otherwise, old function is used.
*/
#define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2, \
output, input...) \
asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\
"call %P[new2]", feature2) \
: output : [old] "i" (oldfunc), [new1] "i" (newfunc1), \
[new2] "i" (newfunc2), ## input)
/*
* use this macro(s) if you need more than one output parameter
* in alternative_io
*/
#define ASM_OUTPUT2(a...) a
2012-01-21 00:21:41 +08:00
/*
* use this macro if you need clobbers but no inputs in
* alternative_{input,io,call}()
*/
#define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr
struct paravirt_patch_site;
#ifdef CONFIG_PARAVIRT
void apply_paravirt(struct paravirt_patch_site *start,
struct paravirt_patch_site *end);
#else
static inline void apply_paravirt(struct paravirt_patch_site *start,
struct paravirt_patch_site *end)
{}
#define __parainstructions NULL
#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.
* Side-effect: any interrupt handler running between save and restore will have
* the ability to write to read-only pages.
*
* Warning:
* Code patching in the UP case is safe if NMIs and MCE handlers are stopped and
* no thread can be preempted in the instructions being modified (no iret to an
* invalid instruction possible) or if the instructions are changed from a
* consistent state to another consistent state atomically.
* On the local CPU you need to be protected again NMI or MCE handlers seeing an
* inconsistent instruction while you patch.
*/
extern void *text_poke(void *addr, const void *opcode, size_t len);
kprobes/x86: Call out into INT3 handler directly instead of using notifier In fd4363fff3d96 ("x86: Introduce int3 (breakpoint)-based instruction patching"), the mechanism that was introduced for notifying alternatives code from int3 exception handler that and exception occured was die_notifier. This is however problematic, as early code might be using jump labels even before the notifier registration has been performed, which will then lead to an oops due to unhandled exception. One of such occurences has been encountered by Fengguang: int3: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC Modules linked in: CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.11.0-rc1-01429-g04bf576 #8 task: ffff88000da1b040 ti: ffff88000da1c000 task.ti: ffff88000da1c000 RIP: 0010:[<ffffffff811098cc>] [<ffffffff811098cc>] ttwu_do_wakeup+0x28/0x225 RSP: 0000:ffff88000dd03f10 EFLAGS: 00000006 RAX: 0000000000000000 RBX: ffff88000dd12940 RCX: ffffffff81769c40 RDX: 0000000000000002 RSI: 0000000000000000 RDI: 0000000000000001 RBP: ffff88000dd03f28 R08: ffffffff8176a8c0 R09: 0000000000000002 R10: ffffffff810ff484 R11: ffff88000dd129e8 R12: ffff88000dbc90c0 R13: ffff88000dbc90c0 R14: ffff88000da1dfd8 R15: ffff88000da1dfd8 FS: 0000000000000000(0000) GS:ffff88000dd00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00000000ffffffff CR3: 0000000001c88000 CR4: 00000000000006e0 Stack: ffff88000dd12940 ffff88000dbc90c0 ffff88000da1dfd8 ffff88000dd03f48 ffffffff81109e2b ffff88000dd12940 0000000000000000 ffff88000dd03f68 ffffffff81109e9e 0000000000000000 0000000000012940 ffff88000dd03f98 Call Trace: <IRQ> [<ffffffff81109e2b>] ttwu_do_activate.constprop.56+0x6d/0x79 [<ffffffff81109e9e>] sched_ttwu_pending+0x67/0x84 [<ffffffff8110c845>] scheduler_ipi+0x15a/0x2b0 [<ffffffff8104dfb4>] smp_reschedule_interrupt+0x38/0x41 [<ffffffff8173bf5d>] reschedule_interrupt+0x6d/0x80 <EOI> [<ffffffff810ff484>] ? __atomic_notifier_call_chain+0x5/0xc1 [<ffffffff8105cc30>] ? native_safe_halt+0xd/0x16 [<ffffffff81015f10>] default_idle+0x147/0x282 [<ffffffff81017026>] arch_cpu_idle+0x3d/0x5d [<ffffffff81127d6a>] cpu_idle_loop+0x46d/0x5db [<ffffffff81127f5c>] cpu_startup_entry+0x84/0x84 [<ffffffff8104f4f8>] start_secondary+0x3c8/0x3d5 [...] Fix this by directly calling poke_int3_handler() from the int3 exception handler (analogically to what ftrace has been doing already), instead of relying on notifier, registration of which might not have yet been finalized by the time of the first trap. Reported-and-tested-by: Fengguang Wu <fengguang.wu@intel.com> Signed-off-by: Jiri Kosina <jkosina@suse.cz> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: H. Peter Anvin <hpa@linux.intel.com> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/alpine.LNX.2.00.1307231007490.14024@pobox.suse.cz Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-07-23 16:09:28 +08:00
extern int poke_int3_handler(struct pt_regs *regs);
x86: Introduce int3 (breakpoint)-based instruction patching Introduce a method for run-time instruction patching on a live SMP kernel based on int3 breakpoint, completely avoiding the need for stop_machine(). The way this is achieved: - add a int3 trap to the address that will be patched - sync cores - update all but the first byte of the patched range - sync cores - replace the first byte (int3) by the first byte of replacing opcode - sync cores According to http://lkml.indiana.edu/hypermail/linux/kernel/1001.1/01530.html synchronization after replacing "all but first" instructions should not be necessary (on Intel hardware), as the syncing after the subsequent patching of the first byte provides enough safety. But there's not only Intel HW out there, and we'd rather be on a safe side. If any CPU instruction execution would collide with the patching, it'd be trapped by the int3 breakpoint and redirected to the provided "handler" (which would typically mean just skipping over the patched region, acting as "nop" has been there, in case we are doing nop -> jump and jump -> nop transitions). Ftrace has been using this very technique since 08d636b ("ftrace/x86: Have arch x86_64 use breakpoints instead of stop machine") for ages already, and jump labels are another obvious potential user of this. Based on activities of Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> a few years ago. Reviewed-by: Steven Rostedt <rostedt@goodmis.org> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Jiri Kosina <jkosina@suse.cz> Link: http://lkml.kernel.org/r/alpine.LNX.2.00.1307121102440.29788@pobox.suse.cz Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2013-07-12 17:21:48 +08:00
extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
#endif /* _ASM_X86_ALTERNATIVE_H */