1 files changed, 249 insertions, 228 deletions

diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 43ceb3f454bf..d6f0490a7391 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -619,28 +619,37 @@ END(syscall_badsys)
 27:;
 
 /*
- * Build the entry stubs and pointer table with
- * some assembler magic.
+ * 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.
  */
-.section .rodata,"a"
+.section .init.rodata,"a"
 ENTRY(interrupt)
 .text
-
+        .p2align 5
+        .p2align CONFIG_X86_L1_CACHE_SHIFT
 ENTRY(irq_entries_start)
         RING0_INT_FRAME
-vector=0
-.rept NR_VECTORS
-        ALIGN
- .if vector
+vector=FIRST_EXTERNAL_VECTOR
+.rept (NR_VECTORS-FIRST_EXTERNAL_VECTOR+6)/7
+        .balign 32
+  .rept 7
+    .if vector < NR_VECTORS
+      .if vector <> FIRST_EXTERNAL_VECTOR
         CFI_ADJUST_CFA_OFFSET -4
- .endif
-1:      pushl $~(vector)
+      .endif
+1:      pushl $(~vector+0x80)   /* Note: always in signed byte range */
         CFI_ADJUST_CFA_OFFSET 4
-        jmp common_interrupt
- .previous
+      .if ((vector-FIRST_EXTERNAL_VECTOR)%7) <> 6
+        jmp 2f
+      .endif
+      .previous
         .long 1b
- .text
+      .text
 vector=vector+1
+    .endif
+  .endr
+2:      jmp common_interrupt
 .endr
 END(irq_entries_start)
 
@@ -652,8 +661,9 @@ END(interrupt)
  * the CPU automatically disables interrupts when executing an IRQ vector,
  * so IRQ-flags tracing has to follow that:
  */
-        ALIGN
+        .p2align CONFIG_X86_L1_CACHE_SHIFT
 common_interrupt:
+        addl $-0x80,(%esp)      /* Adjust vector into the [-256,-1] range */
         SAVE_ALL
         TRACE_IRQS_OFF
         movl %esp,%eax
@@ -678,65 +688,6 @@ ENDPROC(name)
 /* The include is where all of the SMP etc. interrupts come from */
 #include "entry_arch.h"
 
-KPROBE_ENTRY(page_fault)
-        RING0_EC_FRAME
-        pushl $do_page_fault
-        CFI_ADJUST_CFA_OFFSET 4
-        ALIGN
-error_code:
-        /* the function address is in %fs's slot on the stack */
-        pushl %es
-        CFI_ADJUST_CFA_OFFSET 4
-        /*CFI_REL_OFFSET es, 0*/
-        pushl %ds
-        CFI_ADJUST_CFA_OFFSET 4
-        /*CFI_REL_OFFSET ds, 0*/
-        pushl %eax
-        CFI_ADJUST_CFA_OFFSET 4
-        CFI_REL_OFFSET eax, 0
-        pushl %ebp
-        CFI_ADJUST_CFA_OFFSET 4
-        CFI_REL_OFFSET ebp, 0
-        pushl %edi
-        CFI_ADJUST_CFA_OFFSET 4
-        CFI_REL_OFFSET edi, 0
-        pushl %esi
-        CFI_ADJUST_CFA_OFFSET 4
-        CFI_REL_OFFSET esi, 0
-        pushl %edx
-        CFI_ADJUST_CFA_OFFSET 4
-        CFI_REL_OFFSET edx, 0
-        pushl %ecx
-        CFI_ADJUST_CFA_OFFSET 4
-        CFI_REL_OFFSET ecx, 0
-        pushl %ebx
-        CFI_ADJUST_CFA_OFFSET 4
-        CFI_REL_OFFSET ebx, 0
-        cld
-        pushl %fs
-        CFI_ADJUST_CFA_OFFSET 4
-        /*CFI_REL_OFFSET fs, 0*/
-        movl $(__KERNEL_PERCPU), %ecx
-        movl %ecx, %fs
-        UNWIND_ESPFIX_STACK
-        popl %ecx
-        CFI_ADJUST_CFA_OFFSET -4
-        /*CFI_REGISTER es, ecx*/
-        movl PT_FS(%esp), %edi          # get the function address
-        movl PT_ORIG_EAX(%esp), %edx    # get the error code
-        movl $-1, PT_ORIG_EAX(%esp)     # no syscall to restart
-        mov  %ecx, PT_FS(%esp)
-        /*CFI_REL_OFFSET fs, ES*/
-        movl $(__USER_DS), %ecx
-        movl %ecx, %ds
-        movl %ecx, %es
-        TRACE_IRQS_OFF
-        movl %esp,%eax                  # pt_regs pointer
-        call *%edi
-        jmp ret_from_exception
-        CFI_ENDPROC
-KPROBE_END(page_fault)
-
 ENTRY(coprocessor_error)
         RING0_INT_FRAME
         pushl $0
@@ -767,140 +718,6 @@ ENTRY(device_not_available)
         CFI_ENDPROC
 END(device_not_available)
 
-/*
- * Debug traps and NMI can happen at the one SYSENTER instruction
- * that sets up the real kernel stack. Check here, since we can't
- * allow the wrong stack to be used.
- *
- * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have
- * already pushed 3 words if it hits on the sysenter instruction:
- * eflags, cs and eip.
- *
- * We just load the right stack, and push the three (known) values
- * by hand onto the new stack - while updating the return eip past
- * the instruction that would have done it for sysenter.
- */
-#define FIX_STACK(offset, ok, label)            \
-        cmpw $__KERNEL_CS,4(%esp);              \
-        jne ok;                                 \
-label:                                          \
-        movl TSS_sysenter_sp0+offset(%esp),%esp;        \
-        CFI_DEF_CFA esp, 0;                     \
-        CFI_UNDEFINED eip;                      \
-        pushfl;                                 \
-        CFI_ADJUST_CFA_OFFSET 4;                \
-        pushl $__KERNEL_CS;                     \
-        CFI_ADJUST_CFA_OFFSET 4;                \
-        pushl $sysenter_past_esp;               \
-        CFI_ADJUST_CFA_OFFSET 4;                \
-        CFI_REL_OFFSET eip, 0
-
-KPROBE_ENTRY(debug)
-        RING0_INT_FRAME
-        cmpl $ia32_sysenter_target,(%esp)
-        jne debug_stack_correct
-        FIX_STACK(12, debug_stack_correct, debug_esp_fix_insn)
-debug_stack_correct:
-        pushl $-1                       # mark this as an int
-        CFI_ADJUST_CFA_OFFSET 4
-        SAVE_ALL
-        TRACE_IRQS_OFF
-        xorl %edx,%edx                  # error code 0
-        movl %esp,%eax                  # pt_regs pointer
-        call do_debug
-        jmp ret_from_exception
-        CFI_ENDPROC
-KPROBE_END(debug)
-
-/*
- * NMI is doubly nasty. It can happen _while_ we're handling
- * a debug fault, and the debug fault hasn't yet been able to
- * clear up the stack. So we first check whether we got  an
- * NMI on the sysenter entry path, but after that we need to
- * check whether we got an NMI on the debug path where the debug
- * fault happened on the sysenter path.
- */
-KPROBE_ENTRY(nmi)
-        RING0_INT_FRAME
-        pushl %eax
-        CFI_ADJUST_CFA_OFFSET 4
-        movl %ss, %eax
-        cmpw $__ESPFIX_SS, %ax
-        popl %eax
-        CFI_ADJUST_CFA_OFFSET -4
-        je nmi_espfix_stack
-        cmpl $ia32_sysenter_target,(%esp)
-        je nmi_stack_fixup
-        pushl %eax
-        CFI_ADJUST_CFA_OFFSET 4
-        movl %esp,%eax
-        /* Do not access memory above the end of our stack page,
-         * it might not exist.
-         */
-        andl $(THREAD_SIZE-1),%eax
-        cmpl $(THREAD_SIZE-20),%eax
-        popl %eax
-        CFI_ADJUST_CFA_OFFSET -4
-        jae nmi_stack_correct
-        cmpl $ia32_sysenter_target,12(%esp)
-        je nmi_debug_stack_check
-nmi_stack_correct:
-        /* We have a RING0_INT_FRAME here */
-        pushl %eax
-        CFI_ADJUST_CFA_OFFSET 4
-        SAVE_ALL
-        TRACE_IRQS_OFF
-        xorl %edx,%edx          # zero error code
-        movl %esp,%eax          # pt_regs pointer
-        call do_nmi
-        jmp restore_nocheck_notrace
-        CFI_ENDPROC
-
-nmi_stack_fixup:
-        RING0_INT_FRAME
-        FIX_STACK(12,nmi_stack_correct, 1)
-        jmp nmi_stack_correct
-
-nmi_debug_stack_check:
-        /* We have a RING0_INT_FRAME here */
-        cmpw $__KERNEL_CS,16(%esp)
-        jne nmi_stack_correct
-        cmpl $debug,(%esp)
-        jb nmi_stack_correct
-        cmpl $debug_esp_fix_insn,(%esp)
-        ja nmi_stack_correct
-        FIX_STACK(24,nmi_stack_correct, 1)
-        jmp nmi_stack_correct
-
-nmi_espfix_stack:
-        /* We have a RING0_INT_FRAME here.
-         *
-         * create the pointer to lss back
-         */
-        pushl %ss
-        CFI_ADJUST_CFA_OFFSET 4
-        pushl %esp
-        CFI_ADJUST_CFA_OFFSET 4
-        addw $4, (%esp)
-        /* copy the iret frame of 12 bytes */
-        .rept 3
-        pushl 16(%esp)
-        CFI_ADJUST_CFA_OFFSET 4
-        .endr
-        pushl %eax
-        CFI_ADJUST_CFA_OFFSET 4
-        SAVE_ALL
-        TRACE_IRQS_OFF
-        FIXUP_ESPFIX_STACK              # %eax == %esp
-        xorl %edx,%edx                  # zero error code
-        call do_nmi
-        RESTORE_REGS
-        lss 12+4(%esp), %esp            # back to espfix stack
-        CFI_ADJUST_CFA_OFFSET -24
-        jmp irq_return
-        CFI_ENDPROC
-KPROBE_END(nmi)
-
 #ifdef CONFIG_PARAVIRT
 ENTRY(native_iret)
         iret
@@ -916,19 +733,6 @@ ENTRY(native_irq_enable_sysexit)
 END(native_irq_enable_sysexit)
 #endif
 
-KPROBE_ENTRY(int3)
-        RING0_INT_FRAME
-        pushl $-1                       # mark this as an int
-        CFI_ADJUST_CFA_OFFSET 4
-        SAVE_ALL
-        TRACE_IRQS_OFF
-        xorl %edx,%edx          # zero error code
-        movl %esp,%eax          # pt_regs pointer
-        call do_int3
-        jmp ret_from_exception
-        CFI_ENDPROC
-KPROBE_END(int3)
-
 ENTRY(overflow)
         RING0_INT_FRAME
         pushl $0
@@ -993,14 +797,6 @@ ENTRY(stack_segment)
         CFI_ENDPROC
 END(stack_segment)
 
-KPROBE_ENTRY(general_protection)
-        RING0_EC_FRAME
-        pushl $do_general_protection
-        CFI_ADJUST_CFA_OFFSET 4
-        jmp error_code
-        CFI_ENDPROC
-KPROBE_END(general_protection)
-
 ENTRY(alignment_check)
         RING0_EC_FRAME
         pushl $do_alignment_check
@@ -1051,6 +847,7 @@ ENTRY(kernel_thread_helper)
         push %eax
         CFI_ADJUST_CFA_OFFSET 4
         call do_exit
+        ud2                     # padding for call trace
         CFI_ENDPROC
 ENDPROC(kernel_thread_helper)
 
@@ -1259,3 +1056,227 @@ return_to_handler:
 #include "syscall_table_32.S"
 
 syscall_table_size=(.-sys_call_table)
+
+/*
+ * Some functions should be protected against kprobes
+ */
+        .pushsection .kprobes.text, "ax"
+
+ENTRY(page_fault)
+        RING0_EC_FRAME
+        pushl $do_page_fault
+        CFI_ADJUST_CFA_OFFSET 4
+        ALIGN
+error_code:
+        /* the function address is in %fs's slot on the stack */
+        pushl %es
+        CFI_ADJUST_CFA_OFFSET 4
+        /*CFI_REL_OFFSET es, 0*/
+        pushl %ds
+        CFI_ADJUST_CFA_OFFSET 4
+        /*CFI_REL_OFFSET ds, 0*/
+        pushl %eax
+        CFI_ADJUST_CFA_OFFSET 4
+        CFI_REL_OFFSET eax, 0
+        pushl %ebp
+        CFI_ADJUST_CFA_OFFSET 4
+        CFI_REL_OFFSET ebp, 0
+        pushl %edi
+        CFI_ADJUST_CFA_OFFSET 4
+        CFI_REL_OFFSET edi, 0
+        pushl %esi
+        CFI_ADJUST_CFA_OFFSET 4
+        CFI_REL_OFFSET esi, 0
+        pushl %edx
+        CFI_ADJUST_CFA_OFFSET 4
+        CFI_REL_OFFSET edx, 0
+        pushl %ecx
+        CFI_ADJUST_CFA_OFFSET 4
+        CFI_REL_OFFSET ecx, 0
+        pushl %ebx
+        CFI_ADJUST_CFA_OFFSET 4
+        CFI_REL_OFFSET ebx, 0
+        cld
+        pushl %fs
+        CFI_ADJUST_CFA_OFFSET 4
+        /*CFI_REL_OFFSET fs, 0*/
+        movl $(__KERNEL_PERCPU), %ecx
+        movl %ecx, %fs
+        UNWIND_ESPFIX_STACK
+        popl %ecx
+        CFI_ADJUST_CFA_OFFSET -4
+        /*CFI_REGISTER es, ecx*/
+        movl PT_FS(%esp), %edi          # get the function address
+        movl PT_ORIG_EAX(%esp), %edx    # get the error code
+        movl $-1, PT_ORIG_EAX(%esp)     # no syscall to restart
+        mov  %ecx, PT_FS(%esp)
+        /*CFI_REL_OFFSET fs, ES*/
+        movl $(__USER_DS), %ecx
+        movl %ecx, %ds
+        movl %ecx, %es
+        TRACE_IRQS_OFF
+        movl %esp,%eax                  # pt_regs pointer
+        call *%edi
+        jmp ret_from_exception
+        CFI_ENDPROC
+END(page_fault)
+
+/*
+ * Debug traps and NMI can happen at the one SYSENTER instruction
+ * that sets up the real kernel stack. Check here, since we can't
+ * allow the wrong stack to be used.
+ *
+ * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have
+ * already pushed 3 words if it hits on the sysenter instruction:
+ * eflags, cs and eip.
+ *
+ * We just load the right stack, and push the three (known) values
+ * by hand onto the new stack - while updating the return eip past
+ * the instruction that would have done it for sysenter.
+ */
+#define FIX_STACK(offset, ok, label)            \
+        cmpw $__KERNEL_CS,4(%esp);              \
+        jne ok;                                 \
+label:                                          \
+        movl TSS_sysenter_sp0+offset(%esp),%esp;        \
+        CFI_DEF_CFA esp, 0;                     \
+        CFI_UNDEFINED eip;                      \
+        pushfl;                                 \
+        CFI_ADJUST_CFA_OFFSET 4;                \
+        pushl $__KERNEL_CS;                     \
+        CFI_ADJUST_CFA_OFFSET 4;                \
+        pushl $sysenter_past_esp;               \
+        CFI_ADJUST_CFA_OFFSET 4;                \
+        CFI_REL_OFFSET eip, 0
+
+ENTRY(debug)
+        RING0_INT_FRAME
+        cmpl $ia32_sysenter_target,(%esp)
+        jne debug_stack_correct
+        FIX_STACK(12, debug_stack_correct, debug_esp_fix_insn)
+debug_stack_correct:
+        pushl $-1                       # mark this as an int
+        CFI_ADJUST_CFA_OFFSET 4
+        SAVE_ALL
+        TRACE_IRQS_OFF
+        xorl %edx,%edx                  # error code 0
+        movl %esp,%eax                  # pt_regs pointer
+        call do_debug
+        jmp ret_from_exception
+        CFI_ENDPROC
+END(debug)
+
+/*
+ * NMI is doubly nasty. It can happen _while_ we're handling
+ * a debug fault, and the debug fault hasn't yet been able to
+ * clear up the stack. So we first check whether we got  an
+ * NMI on the sysenter entry path, but after that we need to
+ * check whether we got an NMI on the debug path where the debug
+ * fault happened on the sysenter path.
+ */
+ENTRY(nmi)
+        RING0_INT_FRAME
+        pushl %eax
+        CFI_ADJUST_CFA_OFFSET 4
+        movl %ss, %eax
+        cmpw $__ESPFIX_SS, %ax
+        popl %eax
+        CFI_ADJUST_CFA_OFFSET -4
+        je nmi_espfix_stack
+        cmpl $ia32_sysenter_target,(%esp)
+        je nmi_stack_fixup
+        pushl %eax
+        CFI_ADJUST_CFA_OFFSET 4
+        movl %esp,%eax
+        /* Do not access memory above the end of our stack page,
+         * it might not exist.
+         */
+        andl $(THREAD_SIZE-1),%eax
+        cmpl $(THREAD_SIZE-20),%eax
+        popl %eax
+        CFI_ADJUST_CFA_OFFSET -4
+        jae nmi_stack_correct
+        cmpl $ia32_sysenter_target,12(%esp)
+        je nmi_debug_stack_check
+nmi_stack_correct:
+        /* We have a RING0_INT_FRAME here */
+        pushl %eax
+        CFI_ADJUST_CFA_OFFSET 4
+        SAVE_ALL
+        TRACE_IRQS_OFF
+        xorl %edx,%edx          # zero error code
+        movl %esp,%eax          # pt_regs pointer
+        call do_nmi
+        jmp restore_nocheck_notrace
+        CFI_ENDPROC
+
+nmi_stack_fixup:
+        RING0_INT_FRAME
+        FIX_STACK(12,nmi_stack_correct, 1)
+        jmp nmi_stack_correct
+
+nmi_debug_stack_check:
+        /* We have a RING0_INT_FRAME here */
+        cmpw $__KERNEL_CS,16(%esp)
+        jne nmi_stack_correct
+        cmpl $debug,(%esp)
+        jb nmi_stack_correct
+        cmpl $debug_esp_fix_insn,(%esp)
+        ja nmi_stack_correct
+        FIX_STACK(24,nmi_stack_correct, 1)
+        jmp nmi_stack_correct
+
+nmi_espfix_stack:
+        /* We have a RING0_INT_FRAME here.
+         *
+         * create the pointer to lss back
+         */
+        pushl %ss
+        CFI_ADJUST_CFA_OFFSET 4
+        pushl %esp
+        CFI_ADJUST_CFA_OFFSET 4
+        addw $4, (%esp)
+        /* copy the iret frame of 12 bytes */
+        .rept 3
+        pushl 16(%esp)
+        CFI_ADJUST_CFA_OFFSET 4
+        .endr
+        pushl %eax
+        CFI_ADJUST_CFA_OFFSET 4
+        SAVE_ALL
+        TRACE_IRQS_OFF
+        FIXUP_ESPFIX_STACK              # %eax == %esp
+        xorl %edx,%edx                  # zero error code
+        call do_nmi
+        RESTORE_REGS
+        lss 12+4(%esp), %esp            # back to espfix stack
+        CFI_ADJUST_CFA_OFFSET -24
+        jmp irq_return
+        CFI_ENDPROC
+END(nmi)
+
+ENTRY(int3)
+        RING0_INT_FRAME
+        pushl $-1                       # mark this as an int
+        CFI_ADJUST_CFA_OFFSET 4
+        SAVE_ALL
+        TRACE_IRQS_OFF
+        xorl %edx,%edx          # zero error code
+        movl %esp,%eax          # pt_regs pointer
+        call do_int3
+        jmp ret_from_exception
+        CFI_ENDPROC
+END(int3)
+
+ENTRY(general_protection)
+        RING0_EC_FRAME
+        pushl $do_general_protection
+        CFI_ADJUST_CFA_OFFSET 4
+        jmp error_code
+        CFI_ENDPROC
+END(general_protection)
+
+/*
+ * End of kprobes section
+ */
+        .popsection