It supposed to be safe to modify static branches after jump_label_init().
But, because static key modifying code eventually calls text_poke() we
may end up with accessing struct page that have not been initialized.
Here is how to quickly reproduce the problem. Insert code like this
into init/main.c:
| +static DEFINE_STATIC_KEY_FALSE(__test);
| asmlinkage __visible void __init start_kernel(void)
| {
| char *command_line;
|@@ -587,6 +609,10 @@ asmlinkage __visible void __init start_kernel(void)
| vfs_caches_init_early();
| sort_main_extable();
| trap_init();
|+ {
|+ static_branch_enable(&__test);
|+ WARN_ON(!static_branch_likely(&__test));
|+ }
| mm_init();
The following warnings show-up:
WARNING: CPU: 0 PID: 0 at arch/x86/kernel/alternative.c:701 text_poke+0x20d/0x230
Modules linked in:
CPU: 0 PID: 0 Comm: swapper Not tainted 4.18.0-rc1_pt_t1 #30
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
1.11.0-20171110_100015-anatol 04/01/2014
RIP: 0010:text_poke+0x20d/0x230
Code: 0f 0b 4c 89 e2 4c 89 ee 4c 89 f7 e8 7d 4b 9b 00 31 d2 31 f6 bf 86 02
00 00 48 8b 05 95 8e 24 01 e8 78 18 d8 00 e9 55 ff ff ff <0f> 0b e9 54 fe
ff ff 48 8b 05 75 a8 38 01 e9 64 fe ff ff 48 8b 1d
RSP: 0000:ffffffff94e03e30 EFLAGS: 00010046
RAX: 0100000000000000 RBX: fffff7b2c011f300 RCX: ffffffff94fcccf4
RDX: 0000000000000001 RSI: ffffffff94e03e77 RDI: ffffffff94fcccef
RBP: ffffffff94fcccef R08: 00000000fffffe00 R09: 00000000000000a0
R10: 0000000000000000 R11: 0000000000000040 R12: 0000000000000001
R13: ffffffff94e03e77 R14: ffffffff94fcdcef R15: fffff7b2c0000000
FS: 0000000000000000(0000) GS:ffff9adc87c00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffff9adc8499d000 CR3: 000000000460a001 CR4: 00000000000606b0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
? start_kernel+0x23e/0x4c8
? start_kernel+0x23f/0x4c8
? text_poke_bp+0x50/0xda
? arch_jump_label_transform+0x89/0xe0
? __jump_label_update+0x78/0xb0
? static_key_enable_cpuslocked+0x4d/0x80
? static_key_enable+0x11/0x20
? start_kernel+0x23e/0x4c8
? secondary_startup_64+0xa5/0xb0
---[ end trace abdc99c031b8a90a ]---
If the code above is moved after mm_init(), no warning is shown, as struct
pages are initialized during handover from memblock.
Use text_poke_early() in static branching until early boot IRQs are
enabled, at which time switch to text_poke. Also, ensure text_poke() is
never invoked when unitialized memory access may happen by using:
BUG_ON(!after_bootmem); assertion.
Signed-off-by: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx>
---
arch/x86/include/asm/text-patching.h | 1 +
arch/x86/kernel/alternative.c | 7 +++++++
arch/x86/kernel/jump_label.c | 11 +++++++----
3 files changed, 15 insertions(+), 4 deletions(-)
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index 2ecd34e2d46c..e85ff65c43c3 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -37,5 +37,6 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len);
extern void *text_poke(void *addr, const void *opcode, size_t len);
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;
#endif /* _ASM_X86_TEXT_PATCHING_H */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index a481763a3776..014f214da581 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -668,6 +668,7 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode,
local_irq_save(flags);
memcpy(addr, opcode, len);
local_irq_restore(flags);
+ sync_core();
/* Could also do a CLFLUSH here to speed up CPU recovery; but
that causes hangs on some VIA CPUs. */
return addr;
@@ -693,6 +694,12 @@ void *text_poke(void *addr, const void *opcode, size_t len)
struct page *pages[2];
int i;
+ /*
+ * While boot memory allocator is runnig we cannot use struct
+ * pages as they are not yet initialized.
+ */
+ BUG_ON(!after_bootmem);
+
if (!core_kernel_text((unsigned long)addr)) {
pages[0] = vmalloc_to_page(addr);
pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index e56c95be2808..eeea935e9bb5 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -37,15 +37,18 @@ static void bug_at(unsigned char *ip, int line)
BUG();
}
-static void __jump_label_transform(struct jump_entry *entry,
- enum jump_label_type type,
- void *(*poker)(void *, const void *, size_t),
- int init)
+static void __ref __jump_label_transform(struct jump_entry *entry,
+ enum jump_label_type type,
+ void *(*poker)(void *, const void *, size_t),
+ int init)
{
union jump_code_union code;
const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP };
const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5];
+ if (early_boot_irqs_disabled)
+ poker = text_poke_early;
+
if (type == JUMP_LABEL_JMP) {
if (init) {
/*
--
2.18.0
--
To unsubscribe from this list: send the line "unsubscribe linux-s390" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
