diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-04-13 13:16:36 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-04-13 13:16:36 -0700 |
commit | 60f898eeaaa1c5d0162a4240bacf33a6c87ecef6 (patch) | |
tree | 23eeac4b1e9a616779d22c104dbc8bd45dfeefd1 /arch/x86/kernel/entry_32.S | |
parent | 977e1ba50893c15121557b39de586901fe3f75cf (diff) | |
parent | 3b75232d55680ca166dffa274d0587d5faf0a016 (diff) |
Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 asm changes from Ingo Molnar:
"There were lots of changes in this development cycle:
- over 100 separate cleanups, restructuring changes, speedups and
fixes in the x86 system call, irq, trap and other entry code, part
of a heroic effort to deobfuscate a decade old spaghetti asm code
and its C code dependencies (Denys Vlasenko, Andy Lutomirski)
- alternatives code fixes and enhancements (Borislav Petkov)
- simplifications and cleanups to the compat code (Brian Gerst)
- signal handling fixes and new x86 testcases (Andy Lutomirski)
- various other fixes and cleanups
By their nature many of these changes are risky - we tried to test
them well on many different x86 systems (there are no known
regressions), and they are split up finely to help bisection - but
there's still a fair bit of residual risk left so caveat emptor"
* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (148 commits)
perf/x86/64: Report regs_user->ax too in get_regs_user()
perf/x86/64: Simplify regs_user->abi setting code in get_regs_user()
perf/x86/64: Do report user_regs->cx while we are in syscall, in get_regs_user()
perf/x86/64: Do not guess user_regs->cs, ss, sp in get_regs_user()
x86/asm/entry/32: Tidy up JNZ instructions after TESTs
x86/asm/entry/64: Reduce padding in execve stubs
x86/asm/entry/64: Remove GET_THREAD_INFO() in ret_from_fork
x86/asm/entry/64: Simplify jumps in ret_from_fork
x86/asm/entry/64: Remove a redundant jump
x86/asm/entry/64: Optimize [v]fork/clone stubs
x86/asm/entry: Zero EXTRA_REGS for stub32_execve() too
x86/asm/entry/64: Move stub_x32_execvecloser() to stub_execveat()
x86/asm/entry/64: Use common code for rt_sigreturn() epilogue
x86/asm/entry/64: Add forgotten CFI annotation
x86/asm/entry/irq: Simplify interrupt dispatch table (IDT) layout
x86/asm/entry/64: Move opportunistic sysret code to syscall code path
x86, selftests: Add sigreturn selftest
x86/alternatives: Guard NOPs optimization
x86/asm/entry: Clear EXTRA_REGS for all executable formats
x86/signal: Remove pax argument from restore_sigcontext
...
Diffstat (limited to 'arch/x86/kernel/entry_32.S')
-rw-r--r-- | arch/x86/kernel/entry_32.S | 93 |
1 files changed, 31 insertions, 62 deletions
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 31e2d5bf3e38..1c309763e321 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -395,10 +395,13 @@ sysenter_past_esp: /*CFI_REL_OFFSET cs, 0*/ /* * Push current_thread_info()->sysenter_return to the stack. - * A tiny bit of offset fixup is necessary - 4*4 means the 4 words - * pushed above; +8 corresponds to copy_thread's esp0 setting. + * A tiny bit of offset fixup is necessary: TI_sysenter_return + * is relative to thread_info, which is at the bottom of the + * kernel stack page. 4*4 means the 4 words pushed above; + * TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack; + * and THREAD_SIZE takes us to the bottom. */ - pushl_cfi ((TI_sysenter_return)-THREAD_SIZE+8+4*4)(%esp) + pushl_cfi ((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp) CFI_REL_OFFSET eip, 0 pushl_cfi %eax @@ -432,7 +435,7 @@ sysenter_after_call: TRACE_IRQS_OFF movl TI_flags(%ebp), %ecx testl $_TIF_ALLWORK_MASK, %ecx - jne sysexit_audit + jnz sysexit_audit sysenter_exit: /* if something modifies registers it must also disable sysexit */ movl PT_EIP(%esp), %edx @@ -460,7 +463,7 @@ sysenter_audit: sysexit_audit: testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx - jne syscall_exit_work + jnz syscall_exit_work TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_ANY) movl %eax,%edx /* second arg, syscall return value */ @@ -472,7 +475,7 @@ sysexit_audit: TRACE_IRQS_OFF movl TI_flags(%ebp), %ecx testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx - jne syscall_exit_work + jnz syscall_exit_work movl PT_EAX(%esp),%eax /* reload syscall return value */ jmp sysenter_exit #endif @@ -510,7 +513,7 @@ syscall_exit: TRACE_IRQS_OFF movl TI_flags(%ebp), %ecx testl $_TIF_ALLWORK_MASK, %ecx # current->work - jne syscall_exit_work + jnz syscall_exit_work restore_all: TRACE_IRQS_IRET @@ -612,7 +615,7 @@ work_notifysig: # deal with pending signals and #ifdef CONFIG_VM86 testl $X86_EFLAGS_VM, PT_EFLAGS(%esp) movl %esp, %eax - jne work_notifysig_v86 # returning to kernel-space or + jnz work_notifysig_v86 # returning to kernel-space or # vm86-space 1: #else @@ -720,43 +723,22 @@ END(sysenter_badsys) .endm /* - * Build the entry stubs and pointer table with some assembler magic. - * We pack 7 stubs into a single 32-byte chunk, which will fit in a - * single cache line on all modern x86 implementations. + * Build the entry stubs with some assembler magic. + * We pack 1 stub into every 8-byte block. */ -.section .init.rodata,"a" -ENTRY(interrupt) -.section .entry.text, "ax" - .p2align 5 - .p2align CONFIG_X86_L1_CACHE_SHIFT + .align 8 ENTRY(irq_entries_start) RING0_INT_FRAME -vector=FIRST_EXTERNAL_VECTOR -.rept (FIRST_SYSTEM_VECTOR-FIRST_EXTERNAL_VECTOR+6)/7 - .balign 32 - .rept 7 - .if vector < FIRST_SYSTEM_VECTOR - .if vector <> FIRST_EXTERNAL_VECTOR + vector=FIRST_EXTERNAL_VECTOR + .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) + pushl_cfi $(~vector+0x80) /* Note: always in signed byte range */ + vector=vector+1 + jmp common_interrupt CFI_ADJUST_CFA_OFFSET -4 - .endif -1: pushl_cfi $(~vector+0x80) /* Note: always in signed byte range */ - .if ((vector-FIRST_EXTERNAL_VECTOR)%7) <> 6 - jmp 2f - .endif - .previous - .long 1b - .section .entry.text, "ax" -vector=vector+1 - .endif - .endr -2: jmp common_interrupt -.endr + .align 8 + .endr END(irq_entries_start) -.previous -END(interrupt) -.previous - /* * the CPU automatically disables interrupts when executing an IRQ vector, * so IRQ-flags tracing has to follow that: @@ -816,15 +798,9 @@ ENTRY(simd_coprocessor_error) pushl_cfi $0 #ifdef CONFIG_X86_INVD_BUG /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */ -661: pushl_cfi $do_general_protection -662: -.section .altinstructions,"a" - altinstruction_entry 661b, 663f, X86_FEATURE_XMM, 662b-661b, 664f-663f -.previous -.section .altinstr_replacement,"ax" -663: pushl $do_simd_coprocessor_error -664: -.previous + ALTERNATIVE "pushl_cfi $do_general_protection", \ + "pushl $do_simd_coprocessor_error", \ + X86_FEATURE_XMM #else pushl_cfi $do_simd_coprocessor_error #endif @@ -1240,20 +1216,13 @@ error_code: /*CFI_REL_OFFSET es, 0*/ pushl_cfi %ds /*CFI_REL_OFFSET ds, 0*/ - pushl_cfi %eax - CFI_REL_OFFSET eax, 0 - pushl_cfi %ebp - CFI_REL_OFFSET ebp, 0 - pushl_cfi %edi - CFI_REL_OFFSET edi, 0 - pushl_cfi %esi - CFI_REL_OFFSET esi, 0 - pushl_cfi %edx - CFI_REL_OFFSET edx, 0 - pushl_cfi %ecx - CFI_REL_OFFSET ecx, 0 - pushl_cfi %ebx - CFI_REL_OFFSET ebx, 0 + pushl_cfi_reg eax + pushl_cfi_reg ebp + pushl_cfi_reg edi + pushl_cfi_reg esi + pushl_cfi_reg edx + pushl_cfi_reg ecx + pushl_cfi_reg ebx cld movl $(__KERNEL_PERCPU), %ecx movl %ecx, %fs |