[patch V181 26/54] x86/mm/pti: Prepare the x86/entry assembly code for entry/exit CR3 switching

From: Thomas Gleixner
Date: Wed Dec 20 2017 - 17:06:15 EST


From: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>

PAGE_TABLE_ISOLATION needs to switch to a different CR3 value when it
enters the kernel and switch back when it exits. This essentially needs to
be done before leaving assembly code.

This is extra challenging because the switching context is tricky: the
registers that can be clobbered can vary. It is also hard to store things
on the stack because there is an established ABI (ptregs) or the stack is
entirely unsafe to use.

Establish a set of macros that allow changing to the user and kernel CR3
values.

Interactions with SWAPGS:

Previous versions of the PAGE_TABLE_ISOLATION code relied on having
per-CPU scratch space to save/restore a register that can be used for the
CR3 MOV. The %GS register is used to index into our per-CPU space, so
SWAPGS *had* to be done before the CR3 switch. That scratch space is gone
now, but the semantic that SWAPGS must be done before the CR3 MOV is
retained. This is good to keep because it is not that hard to do and it
allows to do things like add per-CPU debugging information.

What this does in the NMI code is worth pointing out. NMIs can interrupt
*any* context and they can also be nested with NMIs interrupting other
NMIs. The comments below ".Lnmi_from_kernel" explain the format of the
stack during this situation. Changing the format of this stack is hard.
Instead of storing the old CR3 value on the stack, this depends on the
*regular* register save/restore mechanism and then uses %r14 to keep CR3
during the NMI. It is callee-saved and will not be clobbered by the C NMI
handlers that get called.

[ PeterZ: ESPFIX optimization ]

Based-on-code-from: Andy Lutomirski <luto@xxxxxxxxxx>
Signed-off-by: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Reviewed-by: Borislav Petkov <bp@xxxxxxx>
Reviewed-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Brian Gerst <brgerst@xxxxxxxxx>
Cc: David Laight <David.Laight@xxxxxxxxxx>
Cc: Denys Vlasenko <dvlasenk@xxxxxxxxxx>
Cc: Eduardo Valentin <eduval@xxxxxxxxxx>
Cc: Greg KH <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Cc: Juergen Gross <jgross@xxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Will Deacon <will.deacon@xxxxxxx>
Cc: aliguori@xxxxxxxxxx
Cc: daniel.gruss@xxxxxxxxxxxxxx
Cc: hughd@xxxxxxxxxx
Cc: keescook@xxxxxxxxxx
Cc: linux-mm@xxxxxxxxx
---
arch/x86/entry/calling.h | 66 +++++++++++++++++++++++++++++++++++++++
arch/x86/entry/entry_64.S | 45 +++++++++++++++++++++++---
arch/x86/entry/entry_64_compat.S | 24 +++++++++++++-
3 files changed, 128 insertions(+), 7 deletions(-)

--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -1,6 +1,8 @@
/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/jump_label.h>
#include <asm/unwind_hints.h>
+#include <asm/cpufeatures.h>
+#include <asm/page_types.h>

/*

@@ -187,6 +189,70 @@ For 32-bit we have the following convent
#endif
.endm

+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+
+/* PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two halves: */
+#define PTI_SWITCH_MASK (1<<PAGE_SHIFT)
+
+.macro ADJUST_KERNEL_CR3 reg:req
+ /* Clear "PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */
+ andq $(~PTI_SWITCH_MASK), \reg
+.endm
+
+.macro ADJUST_USER_CR3 reg:req
+ /* Move CR3 up a page to the user page tables: */
+ orq $(PTI_SWITCH_MASK), \reg
+.endm
+
+.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
+ mov %cr3, \scratch_reg
+ ADJUST_KERNEL_CR3 \scratch_reg
+ mov \scratch_reg, %cr3
+.endm
+
+.macro SWITCH_TO_USER_CR3 scratch_reg:req
+ mov %cr3, \scratch_reg
+ ADJUST_USER_CR3 \scratch_reg
+ mov \scratch_reg, %cr3
+.endm
+
+.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
+ movq %cr3, \scratch_reg
+ movq \scratch_reg, \save_reg
+ /*
+ * Is the switch bit zero? This means the address is
+ * up in real PAGE_TABLE_ISOLATION patches in a moment.
+ */
+ testq $(PTI_SWITCH_MASK), \scratch_reg
+ jz .Ldone_\@
+
+ ADJUST_KERNEL_CR3 \scratch_reg
+ movq \scratch_reg, %cr3
+
+.Ldone_\@:
+.endm
+
+.macro RESTORE_CR3 save_reg:req
+ /*
+ * The CR3 write could be avoided when not changing its value,
+ * but would require a CR3 read *and* a scratch register.
+ */
+ movq \save_reg, %cr3
+.endm
+
+#else /* CONFIG_PAGE_TABLE_ISOLATION=n: */
+
+.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
+.endm
+.macro SWITCH_TO_USER_CR3 scratch_reg:req
+.endm
+.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
+.endm
+.macro RESTORE_CR3 save_reg:req
+.endm
+
+#endif
+
#endif /* CONFIG_X86_64 */

/*
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -164,6 +164,9 @@ ENTRY(entry_SYSCALL_64_trampoline)
/* Stash the user RSP. */
movq %rsp, RSP_SCRATCH

+ /* Note: using %rsp as a scratch reg. */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+
/* Load the top of the task stack into RSP */
movq CPU_ENTRY_AREA_tss + TSS_sp1 + CPU_ENTRY_AREA, %rsp

@@ -203,6 +206,10 @@ ENTRY(entry_SYSCALL_64)
*/

swapgs
+ /*
+ * This path is not taken when PAGE_TABLE_ISOLATION is disabled so it
+ * is not required to switch CR3.
+ */
movq %rsp, PER_CPU_VAR(rsp_scratch)
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp

@@ -399,6 +406,7 @@ GLOBAL(entry_SYSCALL_64_after_hwframe)
* We are on the trampoline stack. All regs except RDI are live.
* We can do future final exit work right here.
*/
+ SWITCH_TO_USER_CR3 scratch_reg=%rdi

popq %rdi
popq %rsp
@@ -736,6 +744,8 @@ GLOBAL(swapgs_restore_regs_and_return_to
* We can do future final exit work right here.
*/

+ SWITCH_TO_USER_CR3 scratch_reg=%rdi
+
/* Restore RDI. */
popq %rdi
SWAPGS
@@ -818,7 +828,9 @@ ENTRY(native_iret)
*/

pushq %rdi /* Stash user RDI */
- SWAPGS
+ SWAPGS /* to kernel GS */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi /* to kernel CR3 */
+
movq PER_CPU_VAR(espfix_waddr), %rdi
movq %rax, (0*8)(%rdi) /* user RAX */
movq (1*8)(%rsp), %rax /* user RIP */
@@ -834,7 +846,6 @@ ENTRY(native_iret)
/* Now RAX == RSP. */

andl $0xffff0000, %eax /* RAX = (RSP & 0xffff0000) */
- popq %rdi /* Restore user RDI */

/*
* espfix_stack[31:16] == 0. The page tables are set up such that
@@ -845,7 +856,11 @@ ENTRY(native_iret)
* still points to an RO alias of the ESPFIX stack.
*/
orq PER_CPU_VAR(espfix_stack), %rax
- SWAPGS
+
+ SWITCH_TO_USER_CR3 scratch_reg=%rdi /* to user CR3 */
+ SWAPGS /* to user GS */
+ popq %rdi /* Restore user RDI */
+
movq %rax, %rsp
UNWIND_HINT_IRET_REGS offset=8

@@ -945,6 +960,8 @@ ENTRY(switch_to_thread_stack)
UNWIND_HINT_FUNC

pushq %rdi
+ /* Need to switch before accessing the thread stack. */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
movq %rsp, %rdi
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI
@@ -1244,7 +1261,11 @@ ENTRY(paranoid_entry)
js 1f /* negative -> in kernel */
SWAPGS
xorl %ebx, %ebx
-1: ret
+
+1:
+ SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14
+
+ ret
END(paranoid_entry)

/*
@@ -1266,6 +1287,7 @@ ENTRY(paranoid_exit)
testl %ebx, %ebx /* swapgs needed? */
jnz .Lparanoid_exit_no_swapgs
TRACE_IRQS_IRETQ
+ RESTORE_CR3 save_reg=%r14
SWAPGS_UNSAFE_STACK
jmp .Lparanoid_exit_restore
.Lparanoid_exit_no_swapgs:
@@ -1293,6 +1315,8 @@ ENTRY(error_entry)
* from user mode due to an IRET fault.
*/
SWAPGS
+ /* We have user CR3. Change to kernel CR3. */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax

.Lerror_entry_from_usermode_after_swapgs:
/* Put us onto the real thread stack. */
@@ -1339,6 +1363,7 @@ ENTRY(error_entry)
* .Lgs_change's error handler with kernel gsbase.
*/
SWAPGS
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
jmp .Lerror_entry_done

.Lbstep_iret:
@@ -1348,10 +1373,11 @@ ENTRY(error_entry)

.Lerror_bad_iret:
/*
- * We came from an IRET to user mode, so we have user gsbase.
- * Switch to kernel gsbase:
+ * We came from an IRET to user mode, so we have user
+ * gsbase and CR3. Switch to kernel gsbase and CR3:
*/
SWAPGS
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax

/*
* Pretend that the exception came from user mode: set up pt_regs
@@ -1383,6 +1409,10 @@ END(error_exit)
/*
* Runs on exception stack. Xen PV does not go through this path at all,
* so we can use real assembly here.
+ *
+ * Registers:
+ * %r14: Used to save/restore the CR3 of the interrupted context
+ * when PAGE_TABLE_ISOLATION is in use. Do not clobber.
*/
ENTRY(nmi)
UNWIND_HINT_IRET_REGS
@@ -1446,6 +1476,7 @@ ENTRY(nmi)

swapgs
cld
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx
movq %rsp, %rdx
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
UNWIND_HINT_IRET_REGS base=%rdx offset=8
@@ -1698,6 +1729,8 @@ ENTRY(nmi)
movq $-1, %rsi
call do_nmi

+ RESTORE_CR3 save_reg=%r14
+
testl %ebx, %ebx /* swapgs needed? */
jnz nmi_restore
nmi_swapgs:
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -49,6 +49,10 @@
ENTRY(entry_SYSENTER_compat)
/* Interrupts are off on entry. */
SWAPGS
+
+ /* We are about to clobber %rsp anyway, clobbering here is OK */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp

/*
@@ -216,6 +220,12 @@ GLOBAL(entry_SYSCALL_compat_after_hwfram
pushq $0 /* pt_regs->r15 = 0 */

/*
+ * We just saved %rdi so it is safe to clobber. It is not
+ * preserved during the C calls inside TRACE_IRQS_OFF anyway.
+ */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
+
+ /*
* User mode is traced as though IRQs are on, and SYSENTER
* turned them off.
*/
@@ -256,10 +266,22 @@ GLOBAL(entry_SYSCALL_compat_after_hwfram
* when the system call started, which is already known to user
* code. We zero R8-R10 to avoid info leaks.
*/
+ movq RSP-ORIG_RAX(%rsp), %rsp
+
+ /*
+ * The original userspace %rsp (RSP-ORIG_RAX(%rsp)) is stored
+ * on the process stack which is not mapped to userspace and
+ * not readable after we SWITCH_TO_USER_CR3. Delay the CR3
+ * switch until after after the last reference to the process
+ * stack.
+ *
+ * %r8 is zeroed before the sysret, thus safe to clobber.
+ */
+ SWITCH_TO_USER_CR3 scratch_reg=%r8
+
xorq %r8, %r8
xorq %r9, %r9
xorq %r10, %r10
- movq RSP-ORIG_RAX(%rsp), %rsp
swapgs
sysretl
END(entry_SYSCALL_compat)