x86/entry/32: Enter the kernel via trampoline stack
Use the entry-stack as a trampoline to enter the kernel. The entry-stack is
already in the cpu_entry_area and will be mapped to userspace when PTI is
enabled.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-8-git-send-email-joro@8bytes.org
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 7251c4f..fea49ec 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -154,7 +154,7 @@
#endif /* CONFIG_X86_32_LAZY_GS */
-.macro SAVE_ALL pt_regs_ax=%eax
+.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0
cld
PUSH_GS
pushl %fs
@@ -173,6 +173,12 @@
movl $(__KERNEL_PERCPU), %edx
movl %edx, %fs
SET_KERNEL_GS %edx
+
+ /* Switch to kernel stack if necessary */
+.if \switch_stacks > 0
+ SWITCH_TO_KERNEL_STACK
+.endif
+
.endm
/*
@@ -269,6 +275,73 @@
.Lend_\@:
#endif /* CONFIG_X86_ESPFIX32 */
.endm
+
+
+/*
+ * Called with pt_regs fully populated and kernel segments loaded,
+ * so we can access PER_CPU and use the integer registers.
+ *
+ * We need to be very careful here with the %esp switch, because an NMI
+ * can happen everywhere. If the NMI handler finds itself on the
+ * entry-stack, it will overwrite the task-stack and everything we
+ * copied there. So allocate the stack-frame on the task-stack and
+ * switch to it before we do any copying.
+ */
+.macro SWITCH_TO_KERNEL_STACK
+
+ ALTERNATIVE "", "jmp .Lend_\@", X86_FEATURE_XENPV
+
+ /* Are we on the entry stack? Bail out if not! */
+ movl PER_CPU_VAR(cpu_entry_area), %ecx
+ addl $CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
+ subl %esp, %ecx /* ecx = (end of entry_stack) - esp */
+ cmpl $SIZEOF_entry_stack, %ecx
+ jae .Lend_\@
+
+ /* Load stack pointer into %esi and %edi */
+ movl %esp, %esi
+ movl %esi, %edi
+
+ /* Move %edi to the top of the entry stack */
+ andl $(MASK_entry_stack), %edi
+ addl $(SIZEOF_entry_stack), %edi
+
+ /* Load top of task-stack into %edi */
+ movl TSS_entry2task_stack(%edi), %edi
+
+ /* Bytes to copy */
+ movl $PTREGS_SIZE, %ecx
+
+#ifdef CONFIG_VM86
+ testl $X86_EFLAGS_VM, PT_EFLAGS(%esi)
+ jz .Lcopy_pt_regs_\@
+
+ /*
+ * Stack-frame contains 4 additional segment registers when
+ * coming from VM86 mode
+ */
+ addl $(4 * 4), %ecx
+
+.Lcopy_pt_regs_\@:
+#endif
+
+ /* Allocate frame on task-stack */
+ subl %ecx, %edi
+
+ /* Switch to task-stack */
+ movl %edi, %esp
+
+ /*
+ * We are now on the task-stack and can safely copy over the
+ * stack-frame
+ */
+ shrl $2, %ecx
+ cld
+ rep movsl
+
+.Lend_\@:
+.endm
+
/*
* %eax: prev task
* %edx: next task
@@ -469,7 +542,7 @@
pushl $__USER_CS /* pt_regs->cs */
pushl $0 /* pt_regs->ip = 0 (placeholder) */
pushl %eax /* pt_regs->orig_ax */
- SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest */
+ SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest, stack already switched */
/*
* SYSENTER doesn't filter flags, so we need to clear NT, AC
@@ -580,7 +653,8 @@
ENTRY(entry_INT80_32)
ASM_CLAC
pushl %eax /* pt_regs->orig_ax */
- SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest */
+
+ SAVE_ALL pt_regs_ax=$-ENOSYS switch_stacks=1 /* save rest */
/*
* User mode is traced as though IRQs are on, and the interrupt gate
@@ -677,7 +751,8 @@
common_interrupt:
ASM_CLAC
addl $-0x80, (%esp) /* Adjust vector into the [-256, -1] range */
- SAVE_ALL
+
+ SAVE_ALL switch_stacks=1
ENCODE_FRAME_POINTER
TRACE_IRQS_OFF
movl %esp, %eax
@@ -685,16 +760,16 @@
jmp ret_from_intr
ENDPROC(common_interrupt)
-#define BUILD_INTERRUPT3(name, nr, fn) \
-ENTRY(name) \
- ASM_CLAC; \
- pushl $~(nr); \
- SAVE_ALL; \
- ENCODE_FRAME_POINTER; \
- TRACE_IRQS_OFF \
- movl %esp, %eax; \
- call fn; \
- jmp ret_from_intr; \
+#define BUILD_INTERRUPT3(name, nr, fn) \
+ENTRY(name) \
+ ASM_CLAC; \
+ pushl $~(nr); \
+ SAVE_ALL switch_stacks=1; \
+ ENCODE_FRAME_POINTER; \
+ TRACE_IRQS_OFF \
+ movl %esp, %eax; \
+ call fn; \
+ jmp ret_from_intr; \
ENDPROC(name)
#define BUILD_INTERRUPT(name, nr) \
@@ -926,16 +1001,20 @@
pushl %es
pushl %ds
pushl %eax
+ movl $(__USER_DS), %eax
+ movl %eax, %ds
+ movl %eax, %es
+ movl $(__KERNEL_PERCPU), %eax
+ movl %eax, %fs
pushl %ebp
pushl %edi
pushl %esi
pushl %edx
pushl %ecx
pushl %ebx
+ SWITCH_TO_KERNEL_STACK
ENCODE_FRAME_POINTER
cld
- movl $(__KERNEL_PERCPU), %ecx
- movl %ecx, %fs
UNWIND_ESPFIX_STACK
GS_TO_REG %ecx
movl PT_GS(%esp), %edi # get the function address
@@ -943,9 +1022,6 @@
movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart
REG_TO_PTGS %ecx
SET_KERNEL_GS %ecx
- movl $(__USER_DS), %ecx
- movl %ecx, %ds
- movl %ecx, %es
TRACE_IRQS_OFF
movl %esp, %eax # pt_regs pointer
CALL_NOSPEC %edi
@@ -964,6 +1040,7 @@
*/
ASM_CLAC
pushl $-1 # mark this as an int
+
SAVE_ALL
ENCODE_FRAME_POINTER
xorl %edx, %edx # error code 0
@@ -999,6 +1076,7 @@
*/
ENTRY(nmi)
ASM_CLAC
+
#ifdef CONFIG_X86_ESPFIX32
pushl %eax
movl %ss, %eax
@@ -1066,7 +1144,8 @@
ENTRY(int3)
ASM_CLAC
pushl $-1 # mark this as an int
- SAVE_ALL
+
+ SAVE_ALL switch_stacks=1
ENCODE_FRAME_POINTER
TRACE_IRQS_OFF
xorl %edx, %edx # zero error code