Skip to contentSkip to conversation

x86/entry/64: Convert a bunch of ASM entry code into C code

PATCH Superseded Lai Jiangshan 5 participants 57 messages Oct 14, 2021 – Oct 25, 2021

Subsystems (5)

v3 of 6 Superseded Latest is v6 →

lore
Share & tools
lore
#0 lore raw

v3 cover x86/entry/64: Convert a bunch of ASM entry code into C code

From: Lai Jiangshan <[email protected]>

Many ASM code in entry_64.S can be rewritten in C if they can be written to be non-instrumentable and are called in the right order regarding to whether CR3/gsbase is changed to kernel CR3/gsbase.

The patchset covert some of them to C code.

The patch 24 converts the error_entry() to C code. And patch 1-23 are fixes and preparation for it.

The patches 25-27 convert entry_INT80_compat and do cleanup.

The patches 28-45 convert the IST entry code to C code. Many of them are preparation for the actual conversion.

The patches 46-48 do cleanup.

The patch 49 converts a small part of ASM code of syscall to C code which does the checking for whether it can use sysret to return to userspace.

Some other paths can be possible to be in C code, for example: the error exit, the syscall entry/exit. The PTI handling for them can be in C code. But it would required the pt_regs to be copied/pushed to the entry stack which means the C code would not be efficient.

When converting ASM to C, the most effort is to make them the same. Almost no creative was involved. The code are kept as the same as ASM as possible and no functional change intended unless my misunderstanding in the ASM code was involved. The functions called by the C entry code are checked to be ensured noinstr or __always_inline. Some of them have more than one definitions and require some more cares from reviewers. The comments in the ASM are also copied in the right place in the C code.

Changed from V2:
Fix two places with missed FENCE_SWAPGS_KERNEL_ENTRY.

Fix swapgs_restore_regs_and_return_to_usermode for XENPV.

Updates the C entry_error()/parnoid_entry() to use
fence_swapgs_kernel_entry when with user gsbase in kernel CR3.

Simplify removing stack-protector in MAKEFILE.

Squash commits about removing stack-protector in MAKEFILE.

In V2 the C entry_error() checks xenpv first and uses natvie_swapgs
but ASM entry_error() uses pv-aware SWAPGS. In V3, the commit is split into 3 commit, so the conversion has no semantic change.

Move cld to the start of idtentry.

Use idtentry macro for entry_INT80_compat and remove the old one.

Add cleanup for PTI_USER_PGTABLE_BIT when it is moved to header file.

Remove pv-aware SWAPGS.

Changed from V1:
Add a fix as the patch1. Found by trying to applied Peterz's
suggestion in patch11.
The whole entry_error() is converted to C instead of partial. The whole parnoid_entry() is converted to C instead of partial. The asm code of "parnoid_entry() cfunc() parnoid_exit()" are
converted to C as suggested by Peterz.
Add entry64.c rather than move traps.c to arch/x86/entry/ The order of some commits is changed.
Remove two cleanups

[V1]: https://lore.kernel.org/all/[email protected]/
[V2]: https://lore.kernel.org/lkml/[email protected]/

Cc Thomas Gleixner <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Borislav Petkov <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Andy Lutomirski <[email protected]>
Cc "H. Peter Anvin" <[email protected]>
Cc Joerg Roedel <[email protected]>

Lai Jiangshan (49):
x86/entry: Add fence for kernel entry swapgs in paranoid_entry() x86/entry: Use the correct fence macro after swapgs in kernel CR3 x86/traps: Remove stack-protector from traps.c
x86/xen: Add xenpv_restore_regs_and_return_to_usermode() x86/entry: Use swapgs and native_iret directly in
swapgs_restore_regs_and_return_to_usermode
compiler_types.h: Add __noinstr_section() for noinstr x86/entry: Introduce __entry_text for entry code written in C x86/entry: Move PTI_USER_* to arch/x86/include/asm/processor-flags.h
x86: Remove unused kernel_to_user_p4dp() and user_to_kernel_p4dp()
x86: Replace PTI_PGTABLE_SWITCH_BIT with PTI_USER_PGTABLE_BIT
x86: Mark __native_read_cr3() & native_write_cr3() as __always_inline x86/traps: Move the declaration of native_irq_return_iret into proto.h x86/entry: Add arch/x86/entry/entry64.c for C entry code x86/entry: Expose the address of .Lgs_change to entry64.c x86/entry: Add C verion of SWITCH_TO_KERNEL_CR3 as

    switch_to_kernel_cr3()

x86/traps: Add fence_swapgs_{user,kernel}_entry() x86/entry: Add C {user,kernel}_entry_swapgs_and_fence() x86/traps: Move pt_regs only in fixup_bad_iret() x86/entry: Switch the stack after error_entry() returns x86/entry: move PUSH_AND_CLEAR_REGS out of error_entry x86/entry: Move cld to the start of idtentry
x86/entry: Don't call error_entry for XENPV
x86/entry: Convert SWAPGS to swapgs in error_entry() x86/entry: Implement the whole error_entry() as C code x86/entry: Use idtentry macro for entry_INT80_compat x86/entry: Convert SWAPGS to swapgs in entry_SYSENTER_compat()
x86: Remove the definition of SWAPGS
x86/entry: Make paranoid_exit() callable
x86/entry: Call paranoid_exit() in asm_exc_nmi() x86/entry: move PUSH_AND_CLEAR_REGS out of paranoid_entry x86/entry: Add the C version ist_switch_to_kernel_cr3() x86/entry: Add the C version ist_restore_cr3() x86/entry: Add the C version get_percpu_base() x86/entry: Add the C version ist_switch_to_kernel_gsbase() x86/entry: Implement the C version ist_paranoid_entry() x86/entry: Implement the C version ist_paranoid_exit() x86/entry: Add a C macro to define the function body for IST in
.entry.text
x86/debug, mce: Use C entry code
x86/idtentry.h: Move the definitions *IDTENTRY_{MCE|DEBUG}* up x86/nmi: Use DEFINE_IDTENTRY_NMI for nmi
x86/nmi: Use C entry code
x86/entry: Add a C macro to define the function body for IST in
.entry.text with an error code
x86/doublefault: Use C entry code
x86/sev: Add and use ist_vc_switch_off_ist()
x86/sev: Use C entry code
x86/entry: Remove ASM function paranoid_entry() and paranoid_exit() x86/entry: Remove the unused ASM macros
x86/entry: Remove save_ret from PUSH_AND_CLEAR_REGS x86/syscall/64: Move the checking for sysret to C code

 arch/x86/entry/Makefile                |   3 +-
 arch/x86/entry/calling.h               | 142 +-------
 arch/x86/entry/common.c                |  73 +++-
 arch/x86/entry/entry64.c               | 367 ++++++++++++++++++++
 arch/x86/entry/entry_64.S              | 448 ++++---------------------
 arch/x86/entry/entry_64_compat.S       | 108 +-----
 arch/x86/include/asm/idtentry.h        | 111 +++++-
 arch/x86/include/asm/irqflags.h        |   8 -
 arch/x86/include/asm/pgtable.h         |  23 +-
 arch/x86/include/asm/processor-flags.h |  15 +
 arch/x86/include/asm/proto.h           |   5 +-
 arch/x86/include/asm/special_insns.h   |   4 +-
 arch/x86/include/asm/syscall.h         |   2 +-
 arch/x86/include/asm/traps.h           |   6 +-
 arch/x86/kernel/Makefile               |   3 +
 arch/x86/kernel/cpu/mce/Makefile       |   3 +
 arch/x86/kernel/nmi.c                  |   2 +-
 arch/x86/kernel/traps.c                |  33 +-
 arch/x86/xen/xen-asm.S                 |  27 ++
 include/linux/compiler_types.h         |   6 +-
 20 files changed, 704 insertions(+), 685 deletions(-)
 create mode 100644 arch/x86/entry/entry64.c
Signature · 1 line
2.19.1.6.gb485710b
#1 lore raw

PATCH v3 1/49 x86/entry: Add fence for kernel entry swapgs in paranoid_entry()

From: Lai Jiangshan <[email protected]>

Commit 18ec54fdd6d18 ("x86/speculation: Prepare entry code for Spectre v1 swapgs mitigations") adds FENCE_SWAPGS_{KERNEL|USER}_ENTRY for conditional swapgs. And in paranoid_entry(), it uses only FENCE_SWAPGS_KERNEL_ENTRY for both branches. It is because the fence is required for both cases since the CR3 write is conditinal even PTI is enabled.

But commit 96b2371413e8f ("x86/entry/64: Switch CR3 before SWAPGS in paranoid entry") switches the code order and changes the branches. And it misses the needed FENCE_SWAPGS_KERNEL_ENTRY for user gsbase case.

Add it back.

Fixes Commit 96b2371413e8f ("x86/entry/64: Switch CR3 before SWAPGS in paranoid entry")
Cc Josh Poimboeuf <[email protected]>
Cc Chang S. Bae <[email protected]>
Cc Sasha Levin <[email protected]>
---
 arch/x86/entry/entry_64.S | 1 +
 1 file changed, 1 insertion(+)
arch/x86/entry/entry_64.S +1 -0
index e38a4cf795d9..1f98188e83ef 100644
@@ -898,6 +898,7 @@ SYM_CODE_START_LOCAL(paranoid_entry)
 	rdmsr
 	testl	%edx, %edx
 	jns	.Lparanoid_entry_swapgs
+	FENCE_SWAPGS_KERNEL_ENTRY
 	ret
 
 .Lparanoid_entry_swapgs:
Signature · 1 line
2.19.1.6.gb485710b
#2 lore raw

PATCH v3 2/49 x86/entry: Use the correct fence macro after swapgs in kernel CR3

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

The commit c75890700455 ("x86/entry/64: Remove unneeded kernel CR3 switching") removes a CR3 write in the faulting path of load_gs_index.

But the path's FENCE_SWAPGS_USER_ENTRY has no fence operation if PTI is enabled. Rahter, it depends on the CR3 write of SWITCH_TO_KERNEL_CR3. So the path should use FENCE_SWAPGS_KERNEL_ENTRY if SWITCH_TO_KERNEL_CR3 is removed.

Fixes c75890700455 ("x86/entry/64: Remove unneeded kernel CR3 switching")
---
 arch/x86/entry/entry_64.S | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)
arch/x86/entry/entry_64.S +9 -7
index 1f98188e83ef..9d468c8877e2 100644
@@ -994,11 +994,6 @@ SYM_CODE_START_LOCAL(error_entry)
 	pushq	%r12
 	ret
 
-.Lerror_entry_done_lfence:
-	FENCE_SWAPGS_KERNEL_ENTRY
-.Lerror_entry_done:
-	ret
-
 	/*
 	 * There are two places in the kernel that can potentially fault with
 	 * usergs. Handle them here.  B stepping K8s sometimes report a
@@ -1021,8 +1016,15 @@ SYM_CODE_START_LOCAL(error_entry)
 	 * .Lgs_change's error handler with kernel gsbase.
 	 */
 	SWAPGS
-	FENCE_SWAPGS_USER_ENTRY
-	jmp .Lerror_entry_done
+
+	/*
+	 * The above code has no serializing instruction.  So do an lfence
+	 * to prevent GS speculation, regardless of whether it is kernel
+	 * gsbase or user gsbase.
+	 */
+.Lerror_entry_done_lfence:
+	FENCE_SWAPGS_KERNEL_ENTRY
+	ret
 
 .Lbstep_iret:
 	/* Fix truncated RIP */
Signature · 1 line
2.19.1.6.gb485710b
#3 lore raw

PATCH v3 3/49 x86/traps: Remove stack-protector from traps.c

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

When stack-protector is enabled, the compiler adds some instrument code at the beginning and the end of some functions. Many functions in traps.c are non-instrumentable. Moreover, stack-protector code in the beginning of the affected function accesses the canary that might be watched by hardware breakpoints which also violate the non-instrumentable nature of some functions and might cause infinite recursive #DB because the canary is accessed before resetting the dr7.

So it is better to remove stack-protector from traps.c.

It is also prepared for later patches that move some entry code into traps.c, some of which can NOT use percpu register until gsbase is properly switched. And stack-protector depends on the percpu register to work.

---
 arch/x86/kernel/Makefile | 1 +
 1 file changed, 1 insertion(+)
arch/x86/kernel/Makefile +1 -0
index 2ff3e600f426..8ac45801ba8b 100644
@@ -50,6 +50,7 @@ KCOV_INSTRUMENT		:= n
 
 CFLAGS_head$(BITS).o	+= -fno-stack-protector
 CFLAGS_cc_platform.o	+= -fno-stack-protector
+CFLAGS_traps.o		+= -fno-stack-protector
 
 CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace
 
Signature · 1 line
2.19.1.6.gb485710b
#4 lore raw

PATCH v3 4/49 x86/xen: Add xenpv_restore_regs_and_return_to_usermode()

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

While in the native case, PER_CPU_VAR(cpu_tss_rw + TSS_sp0) is the trampoline stack. But XEN pv doesn't use trampoline stack, so PER_CPU_VAR(cpu_tss_rw + TSS_sp0) is also the kernel stack. Hence source and destination stacks are identical in that case, which means reusing swapgs_restore_regs_and_return_to_usermode() in XEN pv would cause %rsp to move up to the top of the kernel stack and leave the IRET frame below %rsp, which is dangerous to be corrupted if #NMI / #MC hit as either of these events occurring in the middle of the stack pushing would clobber data on the (original) stack.

And swapgs_restore_regs_and_return_to_usermode() pushing the IRET frame on to the original address is useless and error-prone when there is any future attempt to modify the code.

Fixes 7f2590a110b8 ("x86/entry/64: Use a per-CPU trampoline stack for IDT entries")
Cc Jan Beulich <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Juergen Gross <[email protected]>
Cc Peter Anvin <[email protected]>
Cc Boris Ostrovsky <[email protected]>
---
 arch/x86/entry/entry_64.S        |  9 ++++++---
 arch/x86/entry/entry_64_compat.S |  7 ++++---
 arch/x86/xen/xen-asm.S           | 27 +++++++++++++++++++++++++++
 3 files changed, 37 insertions(+), 6 deletions(-)
arch/x86/entry/entry_64.S +6 -3
index 9d468c8877e2..0dde5a253dda 100644
@@ -119,7 +119,7 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
 	 * In the Xen PV case we must use iret anyway.
 	 */
 
-	ALTERNATIVE "", "jmp	swapgs_restore_regs_and_return_to_usermode", \
+	ALTERNATIVE "", "jmp xenpv_restore_regs_and_return_to_usermode", \
 		X86_FEATURE_XENPV
 
 	movq	RCX(%rsp), %rcx
@@ -286,7 +286,8 @@ SYM_CODE_START(ret_from_fork)
 	UNWIND_HINT_REGS
 	movq	%rsp, %rdi
 	call	syscall_exit_to_user_mode	/* returns with IRQs disabled */
-	jmp	swapgs_restore_regs_and_return_to_usermode
+	ALTERNATIVE "jmp swapgs_restore_regs_and_return_to_usermode",	\
+		"jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
 
 1:
 	/* kernel thread */
@@ -566,6 +567,7 @@ __irqentry_text_start:
 __irqentry_text_end:
 
 SYM_CODE_START_LOCAL(common_interrupt_return)
+SYM_INNER_LABEL(xenpv_restore_regs_and_return_to_usermode, SYM_L_WEAK) /* placeholder */
 SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 #ifdef CONFIG_DEBUG_ENTRY
 	/* Assert that pt_regs indicates user mode. */
@@ -1055,7 +1057,8 @@ SYM_CODE_START_LOCAL(error_return)
 	DEBUG_ENTRY_ASSERT_IRQS_OFF
 	testb	$3, CS(%rsp)
 	jz	restore_regs_and_return_to_kernel
-	jmp	swapgs_restore_regs_and_return_to_usermode
+	ALTERNATIVE "jmp swapgs_restore_regs_and_return_to_usermode",	\
+		"jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
 SYM_CODE_END(error_return)
 
 /*
arch/x86/entry/entry_64_compat.S +4 -3
index 0051cf5c792d..2a4d9532dfd5 100644
@@ -139,7 +139,7 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL)
 	call	do_SYSENTER_32
 	/* XEN PV guests always use IRET path */
 	ALTERNATIVE "testl %eax, %eax; jz swapgs_restore_regs_and_return_to_usermode", \
-		    "jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
+		    "jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
 	jmp	sysret32_from_system_call
 
 .Lsysenter_fix_flags:
@@ -256,7 +256,7 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL)
 	call	do_fast_syscall_32
 	/* XEN PV guests always use IRET path */
 	ALTERNATIVE "testl %eax, %eax; jz swapgs_restore_regs_and_return_to_usermode", \
-		    "jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
+		    "jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
 
 	/* Opportunistic SYSRET */
 sysret32_from_system_call:
@@ -411,5 +411,6 @@ SYM_CODE_START(entry_INT80_compat)
 
 	movq	%rsp, %rdi
 	call	do_int80_syscall_32
-	jmp	swapgs_restore_regs_and_return_to_usermode
+	ALTERNATIVE "jmp swapgs_restore_regs_and_return_to_usermode",	\
+		"jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
 SYM_CODE_END(entry_INT80_compat)
arch/x86/xen/xen-asm.S +27 -0
index 220dd9678494..032be1bab113 100644
@@ -20,6 +20,7 @@
 
 #include <linux/init.h>
 #include <linux/linkage.h>
+#include <../entry/calling.h>
 
 .pushsection .noinstr.text, "ax"
 /*
@@ -192,6 +193,32 @@ SYM_CODE_START(xen_iret)
 	jmp hypercall_iret
 SYM_CODE_END(xen_iret)
 
+/*
+ * XEN pv doesn't use trampoline stack, PER_CPU_VAR(cpu_tss_rw + TSS_sp0) is
+ * also the kernel stack.  Reusing swapgs_restore_regs_and_return_to_usermode()
+ * in XEN pv would cause %rsp to move up to the top of the kernel stack and
+ * leave the IRET frame below %rsp, which is dangerous to be corrupted if #NMI
+ * interrupts. And swapgs_restore_regs_and_return_to_usermode() pushing the IRET
+ * frame at the same address is useless.
+ */
+SYM_CODE_START(xenpv_restore_regs_and_return_to_usermode)
+	UNWIND_HINT_REGS
+#ifdef CONFIG_DEBUG_ENTRY
+	/* Assert that pt_regs indicates user mode. */
+	testb	$3, CS(%rsp)
+	jnz	1f
+	ud2
+1:
+#endif
+	POP_REGS
+
+	/* stackleak_erase() can work safely on the kernel stack. */
+	STACKLEAK_ERASE_NOCLOBBER
+
+	addq	$8, %rsp	/* skip regs->orig_ax */
+	jmp xen_iret
+SYM_CODE_END(xenpv_restore_regs_and_return_to_usermode)
+
 /*
  * Xen handles syscall callbacks much like ordinary exceptions, which
  * means we have:
Signature · 1 line
2.19.1.6.gb485710b
reviewer Reviewed-by on v3 4/49
#5 lore raw

Re: [PATCH V3 04/49] x86/xen: Add xenpv_restore_regs_and_return_to_usermode()

Quoted 16 lines · Lai Jiangshan

From: Lai Jiangshan <[email protected]>

While in the native case, PER_CPU_VAR(cpu_tss_rw + TSS_sp0) is the trampoline stack. But XEN pv doesn't use trampoline stack, so PER_CPU_VAR(cpu_tss_rw + TSS_sp0) is also the kernel stack. Hence source and destination stacks are identical in that case, which means reusing swapgs_restore_regs_and_return_to_usermode() in XEN pv would cause %rsp to move up to the top of the kernel stack and leave the IRET frame below %rsp, which is dangerous to be corrupted if #NMI / #MC hit as either of these events occurring in the middle of the stack pushing would clobber data on the (original) stack.

And swapgs_restore_regs_and_return_to_usermode() pushing the IRET frame on to the original address is useless and error-prone when there is any future attempt to modify the code.

Quoted 8 lines
Fixes 7f2590a110b8 ("x86/entry/64: Use a per-CPU trampoline stack for IDT entries")
Cc Jan Beulich <[email protected]>
Cc Thomas Gleixner <[email protected]>
Cc Juergen Gross <[email protected]>
Cc Peter Anvin <[email protected]>
Cc Boris Ostrovsky <[email protected]>
#6 lore raw

PATCH v3 5/49 x86/entry: Use swapgs and native_iret directly in swapgs_restore_regs_and_return_to_usermode

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

swapgs_restore_regs_and_return_to_usermode() is used in natvie code (non-xenpv) only now, so it doesn't need the PV-aware SWAPGS and INTERRUPT_RETURN.

---
 arch/x86/entry/entry_64.S | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
arch/x86/entry/entry_64.S +2 -2
index 0dde5a253dda..c8f7b740a9f1 100644
@@ -606,8 +606,8 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 
 	/* Restore RDI. */
 	popq	%rdi
-	SWAPGS
-	INTERRUPT_RETURN
+	swapgs
+	jmp	native_iret
 
 
 SYM_INNER_LABEL(restore_regs_and_return_to_kernel, SYM_L_GLOBAL)
Signature · 1 line
2.19.1.6.gb485710b
#7 lore raw

PATCH v3 6/49 compiler_types.h: Add __noinstr_section() for noinstr

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

And it will be extended for C entry code.

---
 include/linux/compiler_types.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)
include/linux/compiler_types.h +4 -2
index b6ff83a714ca..3c77631c68bd 100644
@@ -208,10 +208,12 @@ struct ftrace_likely_data {
 #endif
 
 /* Section for code which can't be instrumented at all */
-#define noinstr								\
-	noinline notrace __attribute((__section__(".noinstr.text")))	\
+#define __noinstr_section(section)				\
+	noinline notrace __attribute((__section__(section)))	\
 	__no_kcsan __no_sanitize_address __no_profile __no_sanitize_coverage
 
+#define noinstr __noinstr_section(".noinstr.text")
+
 #endif /* __KERNEL__ */
 
 #endif /* __ASSEMBLY__ */
Signature · 1 line
2.19.1.6.gb485710b
#8 lore raw

Re: [PATCH V3 06/49] compiler_types.h: Add __noinstr_section() for noinstr

Quoted 17 lines · Lai Jiangshan

From: Lai Jiangshan <[email protected]>

And it will be extended for C entry code.

---
 include/linux/compiler_types.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)
include/linux/compiler_types.h +0 -0
index b6ff83a714ca..3c77631c68bd 100644

include/linux/compiler_types.h struct ftrace_likely_data { · line 212

Quoted 7 lines
include/linux/compiler_types.h +2 -2
@@ -208,10 +208,12 @@ struct ftrace_likely_data {
 #endif
 
 /* Section for code which can't be instrumented at all */
-#define noinstr                                                                \
-       noinline notrace __attribute((__section__(".noinstr.text")))    \
+#define __noinstr_section(section)                             \
+       noinline notrace __attribute((__section__(section)))    \

Can we use __section(section) here (from include/linux/compiler_attributes.h)? I kind of can't stand seeing attributes open coded.

Quoted 10 lines
include/linux/compiler_types.h +2 -1
        __no_kcsan __no_sanitize_address __no_profile __no_sanitize_coverage
 
+#define noinstr __noinstr_section(".noinstr.text")
+
 #endif /* __KERNEL__ */
 
 #endif /* __ASSEMBLY__ */
--

2.19.1.6.gb485710b

Signature · 2 lines
Thanks,
~Nick Desaulniers
#9 lore raw

Re: [PATCH V3 06/49] compiler_types.h: Add __noinstr_section() for noinstr

Quoted 4 lines · Nick Desaulniers

Can we use __section(section) here (from include/linux/compiler_attributes.h)? I kind of can't stand seeing attributes open coded.

Yes please! (though it can be an independent patch)

Cheers,
Miguel

#10 lore raw

Re: [PATCH V3 06/49] compiler_types.h: Add __noinstr_section() for noinstr

Quoted 9 lines · Miguel Ojeda
Quoted 4 lines · Nick Desaulniers

Can we use __section(section) here (from include/linux/compiler_attributes.h)? I kind of can't stand seeing attributes open coded.

Yes please! (though it can be an independent patch)

I will use __section(section) in the updated patch.

I don't know whether it is worth for a new version for a relatively large patchset with almost 50 patches since the feedback becomes less or I should wait for more reviews from the x86 maintainers. Especially the second half of the patchset which is all about IST exceptions has no feedback since V2.

Thanks.
Lai

#11 lore raw

Re: [PATCH V3 06/49] compiler_types.h: Add __noinstr_section() for noinstr

Quoted 7 lines · Lai Jiangshan

I will use __section(section) in the updated patch.

I don't know whether it is worth for a new version for a relatively large patchset with almost 50 patches since the feedback becomes less or I should wait for more reviews from the x86 maintainers. Especially the second half of the patchset which is all about IST exceptions has no feedback since V2.

Yeah, what I meant by independent patch is that you may avoid worrying about that fix within the series, and send it as a completely different patch (we can also do it for you, if you prefer). It is, after all, not really related to either this commit nor the series.

Cheers,
Miguel

#12 lore raw

PATCH v3 7/49 x86/entry: Introduce __entry_text for entry code written in C

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

Some entry code will be implemented in C files. __entry_text is needed to set them in .entry.text section. __entry_text disables instrumentation like noinstr, but it doesn't disable stack protector since not all compiler supported by kernel supporting function level granular attribute to disable stack protector. It will be disabled by C file level.

---
 arch/x86/include/asm/idtentry.h | 3 +++
 1 file changed, 3 insertions(+)
arch/x86/include/asm/idtentry.h +3 -0
index 1345088e9902..6779def97591 100644
@@ -11,6 +11,9 @@
 
 #include <asm/irq_stack.h>
 
+/* Entry code written in C. */
+#define __entry_text __noinstr_section(".entry.text")
+
 /**
  * DECLARE_IDTENTRY - Declare functions for simple IDT entry points
  *		      No error code pushed by hardware
Signature · 1 line
2.19.1.6.gb485710b
#13 lore raw

PATCH v3 8/49 x86/entry: Move PTI_USER_* to arch/x86/include/asm/processor-flags.h

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

These constants will be also used in C file, so we move them to arch/x86/include/asm/processor-flags.h which already has a kin X86_CR3_PTI_PCID_USER_BIT defined in it.

---
 arch/x86/entry/calling.h               | 10 ----------
 arch/x86/include/asm/processor-flags.h | 15 +++++++++++++++
 2 files changed, 15 insertions(+), 10 deletions(-)
arch/x86/entry/calling.h +0 -10
index a4c061fb7c6e..996b041e92d2 100644
@@ -149,16 +149,6 @@ For 32-bit we have the following conventions - kernel is built with
 
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
 
-/*
- * PAGE_TABLE_ISOLATION PGDs are 8k.  Flip bit 12 to switch between the two
- * halves:
- */
-#define PTI_USER_PGTABLE_BIT		PAGE_SHIFT
-#define PTI_USER_PGTABLE_MASK		(1 << PTI_USER_PGTABLE_BIT)
-#define PTI_USER_PCID_BIT		X86_CR3_PTI_PCID_USER_BIT
-#define PTI_USER_PCID_MASK		(1 << PTI_USER_PCID_BIT)
-#define PTI_USER_PGTABLE_AND_PCID_MASK  (PTI_USER_PCID_MASK | PTI_USER_PGTABLE_MASK)
-
 .macro SET_NOFLUSH_BIT	reg:req
 	bts	$X86_CR3_PCID_NOFLUSH_BIT, \reg
 .endm
arch/x86/include/asm/processor-flags.h +15 -0
index 02c2cbda4a74..4dd2fbbc861a 100644
@@ -4,6 +4,7 @@
 
 #include <uapi/asm/processor-flags.h>
 #include <linux/mem_encrypt.h>
+#include <asm/page_types.h>
 
 #ifdef CONFIG_VM86
 #define X86_VM_MASK	X86_EFLAGS_VM
@@ -50,7 +51,21 @@
 #endif
 
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
+
 # define X86_CR3_PTI_PCID_USER_BIT	11
+
+#ifdef CONFIG_X86_64
+/*
+ * PAGE_TABLE_ISOLATION PGDs are 8k.  Flip bit 12 to switch between the two
+ * halves:
+ */
+#define PTI_USER_PGTABLE_BIT		PAGE_SHIFT
+#define PTI_USER_PGTABLE_MASK		(1 << PTI_USER_PGTABLE_BIT)
+#define PTI_USER_PCID_BIT		X86_CR3_PTI_PCID_USER_BIT
+#define PTI_USER_PCID_MASK		(1 << PTI_USER_PCID_BIT)
+#define PTI_USER_PGTABLE_AND_PCID_MASK  (PTI_USER_PCID_MASK | PTI_USER_PGTABLE_MASK)
+#endif
+
 #endif
 
 #endif /* _ASM_X86_PROCESSOR_FLAGS_H */
Signature · 1 line
2.19.1.6.gb485710b
#14 lore raw

PATCH v3 9/49 x86: Remove unused kernel_to_user_p4dp() and user_to_kernel_p4dp()

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

kernel_to_user_p4dp() and user_to_kernel_p4dp() have no caller and can be removed.

---
 arch/x86/include/asm/pgtable.h | 10 ----------
 1 file changed, 10 deletions(-)
arch/x86/include/asm/pgtable.h +0 -10
index 448cd01eb3ec..65542106464b 100644
@@ -1200,16 +1200,6 @@ static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp)
 {
 	return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
 }
-
-static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp)
-{
-	return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
-}
-
-static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
-{
-	return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
-}
 #endif /* CONFIG_PAGE_TABLE_ISOLATION */
 
 /*
Signature · 1 line
2.19.1.6.gb485710b
#15 lore raw

PATCH v3 10/49 x86: Replace PTI_PGTABLE_SWITCH_BIT with PTI_USER_PGTABLE_BIT

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

They are the same in meaning and value.

---
 arch/x86/include/asm/pgtable.h | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)
arch/x86/include/asm/pgtable.h +3 -10
index 65542106464b..c8909457574a 100644
@@ -5,6 +5,7 @@
 #include <linux/mem_encrypt.h>
 #include <asm/page.h>
 #include <asm/pgtable_types.h>
+#include <asm/processor-flags.h>
 
 /*
  * Macro to mark a page protection value as UC-
@@ -1164,14 +1165,6 @@ static inline bool pgdp_maps_userspace(void *__ptr)
 static inline int pgd_large(pgd_t pgd) { return 0; }
 
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
-/*
- * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages
- * (8k-aligned and 8k in size).  The kernel one is at the beginning 4k and
- * the user one is in the last 4k.  To switch between them, you
- * just need to flip the 12th bit in their addresses.
- */
-#define PTI_PGTABLE_SWITCH_BIT	PAGE_SHIFT
-
 /*
  * This generates better code than the inline assembly in
  * __set_bit().
@@ -1193,12 +1186,12 @@ static inline void *ptr_clear_bit(void *ptr, int bit)
 
 static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp)
 {
-	return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+	return ptr_set_bit(pgdp, PTI_USER_PGTABLE_BIT);
 }
 
 static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp)
 {
-	return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+	return ptr_clear_bit(pgdp, PTI_USER_PGTABLE_BIT);
 }
 #endif /* CONFIG_PAGE_TABLE_ISOLATION */
 
Signature · 1 line
2.19.1.6.gb485710b
#16 lore raw

PATCH v3 11/49 x86: Mark __native_read_cr3() & native_write_cr3() as __always_inline

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

We need __native_read_cr3() & native_write_cr3() to be ensured noinstr.

It is prepared for later patches which implement entry code in C file. Some of the code needs to handle KPTI and has to read/write CR3.

---
 arch/x86/include/asm/special_insns.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
arch/x86/include/asm/special_insns.h +2 -2
index 68c257a3de0d..fbb057ba60e6 100644
@@ -42,14 +42,14 @@ static __always_inline void native_write_cr2(unsigned long val)
 	asm volatile("mov %0,%%cr2": : "r" (val) : "memory");
 }
 
-static inline unsigned long __native_read_cr3(void)
+static __always_inline unsigned long __native_read_cr3(void)
 {
 	unsigned long val;
 	asm volatile("mov %%cr3,%0\n\t" : "=r" (val) : __FORCE_ORDER);
 	return val;
 }
 
-static inline void native_write_cr3(unsigned long val)
+static __always_inline void native_write_cr3(unsigned long val)
 {
 	asm volatile("mov %0,%%cr3": : "r" (val) : "memory");
 }
Signature · 1 line
2.19.1.6.gb485710b
#17 lore raw

PATCH v3 12/49 x86/traps: Move the declaration of native_irq_return_iret into proto.h

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

The declaration of native_irq_return_iret is used in exc_double_fault() only by now. But it will be used in other place later, so the declaration is moved to a header file for preparation.

---
 arch/x86/include/asm/proto.h | 1 +
 arch/x86/kernel/traps.c      | 2 --
 2 files changed, 1 insertion(+), 2 deletions(-)
arch/x86/include/asm/proto.h +1 -0
index 8c5d1910a848..ee07b3cae213 100644
@@ -13,6 +13,7 @@ void syscall_init(void);
 #ifdef CONFIG_X86_64
 void entry_SYSCALL_64(void);
 void entry_SYSCALL_64_safe_stack(void);
+extern unsigned char native_irq_return_iret[];
 long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2);
 #endif
 
arch/x86/kernel/traps.c +0 -2
index cc6de3a01293..cf852b5e347f 100644
@@ -359,8 +359,6 @@ DEFINE_IDTENTRY_DF(exc_double_fault)
 #endif
 
 #ifdef CONFIG_X86_ESPFIX64
-	extern unsigned char native_irq_return_iret[];
-
 	/*
 	 * If IRET takes a non-IST fault on the espfix64 stack, then we
 	 * end up promoting it to a doublefault.  In that case, take
Signature · 1 line
2.19.1.6.gb485710b
#18 lore raw

PATCH v3 13/49 x86/entry: Add arch/x86/entry/entry64.c for C entry code

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

Add a C file "entry64.c" to deposit C entry code for traps and faults which will be as the same logic as the existing ASM code in entry_64.S.

The file is as low level as entry_64.S and its code can be running in the environments that the GS base is user controlled value, or the CR3 is PTI user CR3 or both.

All the code in this file should not be instrumentable. Many instrument facilities can be disabled by per-function attributes which are included in __noinstr_section. But stack-protector can not be disabled function- granularly by many versions of GCC that can be supported for compiling the kernel. So stack-protector is disabled for the whole file in Makefile.

It is prepared for later patches that implement C version of the entry code in entry64.c.

---
 arch/x86/entry/Makefile  |  3 ++-
 arch/x86/entry/entry64.c | 14 ++++++++++++++
 2 files changed, 16 insertions(+), 1 deletion(-)
 create mode 100644 arch/x86/entry/entry64.c
arch/x86/entry/Makefile +2 -1
index 7fec5dcf6438..792f7009ff32 100644
@@ -10,13 +10,14 @@ KCOV_INSTRUMENT := n
 CFLAGS_REMOVE_common.o		= $(CC_FLAGS_FTRACE)
 
 CFLAGS_common.o			+= -fno-stack-protector
+CFLAGS_entry64.o		+= -fno-stack-protector
 
 obj-y				:= entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
 obj-y				+= common.o
+obj-$(CONFIG_X86_64)		+= entry64.o
 
 obj-y				+= vdso/
 obj-y				+= vsyscall/
 
 obj-$(CONFIG_IA32_EMULATION)	+= entry_64_compat.o syscall_32.o
 obj-$(CONFIG_X86_X32_ABI)	+= syscall_x32.o
-
arch/x86/entry/entry64.c new file +14 -0
new file mode 100644
index 000000000000..762595603ce7
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *  Copyright (C) 2000, 2001, 2002  Andi Kleen SuSE Labs
+ *  Copyright (C) 2000  Pavel Machek <[email protected]>
+ *  Copyright (C) 2021 Lai Jiangshan, Alibaba
+ *
+ * Handle entries and exits for hardware traps and faults.
+ *
+ * It is as low level as entry_64.S and its code can be running in the
+ * environments that the GS base is user controlled value, or the CR3
+ * is PTI user CR3 or both.
+ */
+#include <asm/traps.h>
Signature · 1 line
2.19.1.6.gb485710b
#19 lore raw

PATCH v3 14/49 x86/entry: Expose the address of .Lgs_change to entry64.c

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

The address of .Lgs_change will be used in traps.c in later patch when some entry code is implemented in entry64.c. So the address of .Lgs_change is exposed to traps.c for preparation.

The label .Lgs_change is still needed in ASM code for extable due to it can not use asm_load_gs_index_gs_change. Otherwise:

	warning: objtool: __ex_table+0x0: don't know how to handle
	non-section reloc symbol asm_load_gs_index_gs_change
---
 arch/x86/entry/entry64.c  | 2 ++
 arch/x86/entry/entry_64.S | 3 ++-
 2 files changed, 4 insertions(+), 1 deletion(-)
arch/x86/entry/entry64.c +2 -0
index 762595603ce7..9813a30dbadb 100644
@@ -12,3 +12,5 @@
  * is PTI user CR3 or both.
  */
 #include <asm/traps.h>
+
+extern unsigned char asm_load_gs_index_gs_change[];
arch/x86/entry/entry_64.S +2 -1
index c8f7b740a9f1..daaeeb8acd22 100644
@@ -731,6 +731,7 @@ _ASM_NOKPROBE(common_interrupt_return)
 SYM_FUNC_START(asm_load_gs_index)
 	FRAME_BEGIN
 	swapgs
+SYM_INNER_LABEL(asm_load_gs_index_gs_change, SYM_L_GLOBAL)
 .Lgs_change:
 	movl	%edi, %gs
 2:	ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE
@@ -1009,7 +1010,7 @@ SYM_CODE_START_LOCAL(error_entry)
 	movl	%ecx, %eax			/* zero extend */
 	cmpq	%rax, RIP+8(%rsp)
 	je	.Lbstep_iret
-	cmpq	$.Lgs_change, RIP+8(%rsp)
+	cmpq	$asm_load_gs_index_gs_change, RIP+8(%rsp)
 	jne	.Lerror_entry_done_lfence
 
 	/*
Signature · 1 line
2.19.1.6.gb485710b
#20 lore raw

PATCH v3 15/49 x86/entry: Add C verion of SWITCH_TO_KERNEL_CR3 as switch_to_kernel_cr3()

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

The C version switch_to_kernel_cr3() implements SWITCH_TO_KERNEL_CR3().

No functional difference intended.

---
 arch/x86/entry/entry64.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)
arch/x86/entry/entry64.c +24 -0
index 9813a30dbadb..9a5c535b1ddf 100644
@@ -14,3 +14,27 @@
 #include <asm/traps.h>
 
 extern unsigned char asm_load_gs_index_gs_change[];
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+static __always_inline void pti_switch_to_kernel_cr3(unsigned long user_cr3)
+{
+	/*
+	 * Clear PCID and "PAGE_TABLE_ISOLATION bit", point CR3
+	 * at kernel pagetables:
+	 */
+	unsigned long cr3 = user_cr3 & ~PTI_USER_PGTABLE_AND_PCID_MASK;
+
+	if (static_cpu_has(X86_FEATURE_PCID))
+		cr3 |= X86_CR3_PCID_NOFLUSH;
+
+	native_write_cr3(cr3);
+}
+
+static __always_inline void switch_to_kernel_cr3(void)
+{
+	if (static_cpu_has(X86_FEATURE_PTI))
+		pti_switch_to_kernel_cr3(__native_read_cr3());
+}
+#else
+static __always_inline void switch_to_kernel_cr3(void) {}
+#endif
Signature · 1 line
2.19.1.6.gb485710b
#21 lore raw

PATCH v3 16/49 x86/traps: Add fence_swapgs_{user,kernel}_entry()

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

fence_swapgs_{user,kernel}_entry() in entry64.c are the same as the ASM macro FENCE_SWAPGS_{USER,KERNEL}_ENTRY.

fence_swapgs_user_entry is used in the user entry swapgs code path, to prevent a speculative swapgs when coming from kernel space.

fence_swapgs_kernel_entry is used in the kernel entry code path, to prevent the swapgs from getting speculatively skipped when coming from user space.

---
 arch/x86/entry/entry64.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)
arch/x86/entry/entry64.c +21 -0
index 9a5c535b1ddf..bdc9540f25d3 100644
@@ -38,3 +38,24 @@ static __always_inline void switch_to_kernel_cr3(void)
 #else
 static __always_inline void switch_to_kernel_cr3(void) {}
 #endif
+
+/*
+ * Mitigate Spectre v1 for conditional swapgs code paths.
+ *
+ * fence_swapgs_user_entry is used in the user entry swapgs code path, to
+ * prevent a speculative swapgs when coming from kernel space.  It must be
+ * used with switch_to_kernel_cr3() in the same path.
+ *
+ * fence_swapgs_kernel_entry is used in the kernel entry code path without
+ * CR3 write or with conditinal CR3 write only, to prevent the swapgs from
+ * getting speculatively skipped when coming from user space.
+ */
+static __always_inline void fence_swapgs_user_entry(void)
+{
+	alternative("", "lfence", X86_FEATURE_FENCE_SWAPGS_USER);
+}
+
+static __always_inline void fence_swapgs_kernel_entry(void)
+{
+	alternative("", "lfence", X86_FEATURE_FENCE_SWAPGS_KERNEL);
+}
Signature · 1 line
2.19.1.6.gb485710b
#22 lore raw

PATCH v3 17/49 x86/entry: Add C {user,kernel}_entry_swapgs_and_fence()

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

The C user_entry_swapgs_and_fence() implements the ASM code:
swapgs
FENCE_SWAPGS_USER_ENTRY

It will be used in the user entry swapgs code path, doing the swapgs and lfence to prevent a speculative swapgs when coming from kernel space.

The C kernel_entry_swapgs_and_fence() implements the ASM code:
swapgs
FENCE_SWAPGS_KERNEL_ENTRY

It will be used in the kernel entry swapgs code path to prevent the swapgs from getting speculatively skipped when coming from user space.

---
 arch/x86/entry/entry64.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)
arch/x86/entry/entry64.c +18 -0
index bdc9540f25d3..173cf621317c 100644
@@ -49,6 +49,12 @@ static __always_inline void switch_to_kernel_cr3(void) {}
  * fence_swapgs_kernel_entry is used in the kernel entry code path without
  * CR3 write or with conditinal CR3 write only, to prevent the swapgs from
  * getting speculatively skipped when coming from user space.
+ *
+ * user_entry_swapgs_and_fence is a wrapper of swapgs and fence for user entry
+ * code path.
+ *
+ * kernel_entry_swapgs_and_fence is a wrapper of swapgs and fence for kernel
+ * entry with user gsbase code path.
  */
 static __always_inline void fence_swapgs_user_entry(void)
 {
@@ -59,3 +65,15 @@ static __always_inline void fence_swapgs_kernel_entry(void)
 {
 	alternative("", "lfence", X86_FEATURE_FENCE_SWAPGS_KERNEL);
 }
+
+static __always_inline void user_entry_swapgs_and_fence(void)
+{
+	native_swapgs();
+	fence_swapgs_user_entry();
+}
+
+static __always_inline void kernel_entry_swapgs_and_fence(void)
+{
+	native_swapgs();
+	fence_swapgs_kernel_entry();
+}
Signature · 1 line
2.19.1.6.gb485710b
#23 lore raw

PATCH v3 18/49 x86/traps: Move pt_regs only in fixup_bad_iret()

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

Make fixup_bad_iret() works like sync_regs() which doesn't move the return address of error_entry().

It is prepared later patch which implements the body of error_entry() in C code. The fixup_bad_iret() can't handle return address when it is called from C code.

---
 arch/x86/entry/entry_64.S    |  5 ++++-
 arch/x86/include/asm/traps.h |  2 +-
 arch/x86/kernel/traps.c      | 17 ++++++-----------
 3 files changed, 11 insertions(+), 13 deletions(-)
arch/x86/entry/entry_64.S +4 -1
index daaeeb8acd22..7f2338c3b676 100644
@@ -1047,9 +1047,12 @@ SYM_CODE_START_LOCAL(error_entry)
 	 * Pretend that the exception came from user mode: set up pt_regs
 	 * as if we faulted immediately after IRET.
 	 */
-	mov	%rsp, %rdi
+	popq	%r12				/* save return addr in %12 */
+	movq	%rsp, %rdi			/* arg0 = pt_regs pointer */
 	call	fixup_bad_iret
 	mov	%rax, %rsp
+	ENCODE_FRAME_POINTER
+	pushq	%r12
 	jmp	.Lerror_entry_from_usermode_after_swapgs
 SYM_CODE_END(error_entry)
 
arch/x86/include/asm/traps.h +1 -1
index 6221be7cafc3..1cdd7e8bcba7 100644
@@ -13,7 +13,7 @@
 #ifdef CONFIG_X86_64
 asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs);
 asmlinkage __visible notrace
-struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s);
+struct pt_regs *fixup_bad_iret(struct pt_regs *bad_regs);
 void __init trap_init(void);
 asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *eregs);
 #endif
arch/x86/kernel/traps.c +6 -11
index cf852b5e347f..0afa16ea3702 100644
@@ -759,13 +759,8 @@ asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *r
 }
 #endif
 
-struct bad_iret_stack {
-	void *error_entry_ret;
-	struct pt_regs regs;
-};
-
 asmlinkage __visible noinstr
-struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
+struct pt_regs *fixup_bad_iret(struct pt_regs *bad_regs)
 {
 	/*
 	 * This is called from entry_64.S early in handling a fault
@@ -775,19 +770,19 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
 	 * just below the IRET frame) and we want to pretend that the
 	 * exception came from the IRET target.
 	 */
-	struct bad_iret_stack tmp, *new_stack =
-		(struct bad_iret_stack *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1;
+	struct pt_regs tmp, *new_stack =
+		(struct pt_regs *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1;
 
 	/* Copy the IRET target to the temporary storage. */
-	__memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8);
+	__memcpy(&tmp.ip, (void *)bad_regs->sp, 5*8);
 
 	/* Copy the remainder of the stack from the current stack. */
-	__memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip));
+	__memcpy(&tmp, bad_regs, offsetof(struct pt_regs, ip));
 
 	/* Update the entry stack */
 	__memcpy(new_stack, &tmp, sizeof(tmp));
 
-	BUG_ON(!user_mode(&new_stack->regs));
+	BUG_ON(!user_mode(new_stack));
 	return new_stack;
 }
 #endif
Signature · 1 line
2.19.1.6.gb485710b
#24 lore raw

PATCH v3 19/49 x86/entry: Switch the stack after error_entry() returns

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

error_entry() calls sync_regs() to settle/copy the pt_regs and switches the stack directly after sync_regs(). But because error_entry() is also called from entry, the switching has to handle the return address together, which causes the behavior tangly.

Switching to the stack after error_entry() makes the code simpler and intuitive.

---
 arch/x86/entry/entry_64.S | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)
arch/x86/entry/entry_64.S +6 -10
index 7f2338c3b676..1af28027a138 100644
@@ -324,6 +324,8 @@ SYM_CODE_END(ret_from_fork)
 .macro idtentry_body cfunc has_error_code:req
 
 	call	error_entry
+	movq	%rax, %rsp			/* switch stack settled by sync_regs() */
+	ENCODE_FRAME_POINTER
 	UNWIND_HINT_REGS
 
 	movq	%rsp, %rdi			/* pt_regs pointer into 1st argument*/
@@ -987,14 +989,10 @@ SYM_CODE_START_LOCAL(error_entry)
 	/* We have user CR3.  Change to kernel CR3. */
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 
+	leaq	8(%rsp), %rdi			/* arg0 = pt_regs pointer */
 .Lerror_entry_from_usermode_after_swapgs:
 	/* Put us onto the real thread stack. */
-	popq	%r12				/* save return addr in %12 */
-	movq	%rsp, %rdi			/* arg0 = pt_regs pointer */
 	call	sync_regs
-	movq	%rax, %rsp			/* switch stack */
-	ENCODE_FRAME_POINTER
-	pushq	%r12
 	ret
 
 	/*
@@ -1027,6 +1025,7 @@ SYM_CODE_START_LOCAL(error_entry)
 	 */
 .Lerror_entry_done_lfence:
 	FENCE_SWAPGS_KERNEL_ENTRY
+	leaq	8(%rsp), %rax			/* return pt_regs pointer */
 	ret
 
 .Lbstep_iret:
@@ -1047,12 +1046,9 @@ SYM_CODE_START_LOCAL(error_entry)
 	 * Pretend that the exception came from user mode: set up pt_regs
 	 * as if we faulted immediately after IRET.
 	 */
-	popq	%r12				/* save return addr in %12 */
-	movq	%rsp, %rdi			/* arg0 = pt_regs pointer */
+	leaq	8(%rsp), %rdi			/* arg0 = pt_regs pointer */
 	call	fixup_bad_iret
-	mov	%rax, %rsp
-	ENCODE_FRAME_POINTER
-	pushq	%r12
+	mov	%rax, %rdi
 	jmp	.Lerror_entry_from_usermode_after_swapgs
 SYM_CODE_END(error_entry)
 
Signature · 1 line
2.19.1.6.gb485710b
#25 lore raw

PATCH v3 20/49 x86/entry: move PUSH_AND_CLEAR_REGS out of error_entry

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

Moving PUSH_AND_CLEAR_REGS out of error_entry doesn't change any functionality. It will enlarge the size:

size arch/x86/entry/entry_64.o.before:
text data bss dec hex filename
17916 384 0 18300 477c arch/x86/entry/entry_64.o

size --format=SysV arch/x86/entry/entry_64.o.before:

.entry.text                      5528      0
.orc_unwind                      6456      0
.orc_unwind_ip                   4304      0

size arch/x86/entry/entry_64.o.after:
text data bss dec hex filename
26868 384 0 27252 6a74 arch/x86/entry/entry_64.o

size --format=SysV arch/x86/entry/entry_64.o.after:

.entry.text                      8200      0
.orc_unwind                     10224      0
.orc_unwind_ip                   6816      0

But .entry.text in x86_64 is 2M aligned, enlarging it to 8.2k doesn't enlarge the final text size.

The tables .orc_unwind[_ip] are enlarged due to it adds many pushes.

It is prepared for converting the whole error_entry into C code.

---
 arch/x86/entry/entry_64.S | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
arch/x86/entry/entry_64.S +3 -2
index 1af28027a138..1ec87d9e685d 100644
@@ -323,6 +323,9 @@ SYM_CODE_END(ret_from_fork)
  */
 .macro idtentry_body cfunc has_error_code:req
 
+	PUSH_AND_CLEAR_REGS
+	ENCODE_FRAME_POINTER
+
 	call	error_entry
 	movq	%rax, %rsp			/* switch stack settled by sync_regs() */
 	ENCODE_FRAME_POINTER
@@ -975,8 +978,6 @@ SYM_CODE_END(paranoid_exit)
 SYM_CODE_START_LOCAL(error_entry)
 	UNWIND_HINT_FUNC
 	cld
-	PUSH_AND_CLEAR_REGS save_ret=1
-	ENCODE_FRAME_POINTER 8
 	testb	$3, CS+8(%rsp)
 	jz	.Lerror_kernelspace
 
Signature · 1 line
2.19.1.6.gb485710b
#26 lore raw

PATCH v3 21/49 x86/entry: Move cld to the start of idtentry

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

Make it next to CLAC

---
 arch/x86/entry/entry_64.S | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)
arch/x86/entry/entry_64.S +5 -3
index 1ec87d9e685d..52a08c4a0171 100644
@@ -357,6 +357,7 @@ SYM_CODE_END(ret_from_fork)
 SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS offset=\has_error_code*8
 	ASM_CLAC
+	cld
 
 	.if \has_error_code == 0
 		pushq	$-1			/* ORIG_RAX: no syscall to restart */
@@ -424,6 +425,7 @@ SYM_CODE_END(\asmsym)
 SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS
 	ASM_CLAC
+	cld
 
 	pushq	$-1			/* ORIG_RAX: no syscall to restart */
 
@@ -479,6 +481,7 @@ SYM_CODE_END(\asmsym)
 SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS
 	ASM_CLAC
+	cld
 
 	/*
 	 * If the entry is from userspace, switch stacks and treat it as
@@ -540,6 +543,7 @@ SYM_CODE_END(\asmsym)
 SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS offset=8
 	ASM_CLAC
+	cld
 
 	/* paranoid_entry returns GS information for paranoid_exit in EBX. */
 	call	paranoid_entry
@@ -852,7 +856,6 @@ SYM_CODE_END(xen_failsafe_callback)
  */
 SYM_CODE_START_LOCAL(paranoid_entry)
 	UNWIND_HINT_FUNC
-	cld
 	PUSH_AND_CLEAR_REGS save_ret=1
 	ENCODE_FRAME_POINTER 8
 
@@ -977,7 +980,6 @@ SYM_CODE_END(paranoid_exit)
  */
 SYM_CODE_START_LOCAL(error_entry)
 	UNWIND_HINT_FUNC
-	cld
 	testb	$3, CS+8(%rsp)
 	jz	.Lerror_kernelspace
 
@@ -1112,6 +1114,7 @@ SYM_CODE_START(asm_exc_nmi)
 	 */
 
 	ASM_CLAC
+	cld
 
 	/* Use %rdx as our temp variable throughout */
 	pushq	%rdx
@@ -1131,7 +1134,6 @@ SYM_CODE_START(asm_exc_nmi)
 	 */
 
 	swapgs
-	cld
 	FENCE_SWAPGS_USER_ENTRY
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx
 	movq	%rsp, %rdx
Signature · 1 line
2.19.1.6.gb485710b
#27 lore raw

PATCH v3 22/49 x86/entry: Don't call error_entry for XENPV

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

When in XENPV, it is already in the task stack, and it can't fault at native_irq_return_iret nor asm_load_gs_index_gs_change since XENPV uses its own pvops for iret and load_gs_index(). And it doesn't need to switch CR3. So it can skip invoking error_entry().

---
 arch/x86/entry/entry_64.S | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)
arch/x86/entry/entry_64.S +11 -2
index 52a08c4a0171..9bad620553c8 100644
@@ -326,8 +326,17 @@ SYM_CODE_END(ret_from_fork)
 	PUSH_AND_CLEAR_REGS
 	ENCODE_FRAME_POINTER
 
-	call	error_entry
-	movq	%rax, %rsp			/* switch stack settled by sync_regs() */
+	/*
+	 * Call error_entry and switch stack settled by sync_regs().
+	 *
+	 * When in XENPV, it is already in the task stack, and it can't fault
+	 * at native_irq_return_iret nor asm_load_gs_index_gs_change since
+	 * XENPV uses its own pvops for iret and load_gs_index().  And it
+	 * doesn't need to switch CR3.  So it can skip invoking error_entry().
+	 */
+	ALTERNATIVE "call error_entry; movq %rax, %rsp", \
+		"", X86_FEATURE_XENPV
+
 	ENCODE_FRAME_POINTER
 	UNWIND_HINT_REGS
 
Signature · 1 line
2.19.1.6.gb485710b
#28 lore raw

PATCH v3 23/49 x86/entry: Convert SWAPGS to swapgs in error_entry()

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

XENPV doesn't use error_entry() anymore, so the pv-aware SWAPGS can be changed to native swapgs.

It is prepared for later patch to convert error_entry() to C code, which uses native_swapgs() directly. Converting SWAPGS to swapgs in ASM error_entry first to ensure the later patch has zero semantic change.

---
 arch/x86/entry/entry_64.S | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
arch/x86/entry/entry_64.S +3 -3
index 9bad620553c8..b97ce4204f6d 100644
@@ -996,7 +996,7 @@ SYM_CODE_START_LOCAL(error_entry)
 	 * We entered from user mode or we're pretending to have entered
 	 * from user mode due to an IRET fault.
 	 */
-	SWAPGS
+	swapgs
 	FENCE_SWAPGS_USER_ENTRY
 	/* We have user CR3.  Change to kernel CR3. */
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
@@ -1028,7 +1028,7 @@ SYM_CODE_START_LOCAL(error_entry)
 	 * gsbase and proceed.  We'll fix up the exception and land in
 	 * .Lgs_change's error handler with kernel gsbase.
 	 */
-	SWAPGS
+	swapgs
 
 	/*
 	 * The above code has no serializing instruction.  So do an lfence
@@ -1050,7 +1050,7 @@ SYM_CODE_START_LOCAL(error_entry)
 	 * We came from an IRET to user mode, so we have user
 	 * gsbase and CR3.  Switch to kernel gsbase and CR3:
 	 */
-	SWAPGS
+	swapgs
 	FENCE_SWAPGS_USER_ENTRY
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 
Signature · 1 line
2.19.1.6.gb485710b
#29 lore raw

PATCH v3 24/49 x86/entry: Implement the whole error_entry() as C code

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

All the needed facilities are set in entry64.c, the whole error_entry() can be implemented in C in entry64.c. The C version generally has better readability and easier to be updated/improved.

No function change intended.

---
 arch/x86/entry/entry64.c     | 63 +++++++++++++++++++++++++++
 arch/x86/entry/entry_64.S    | 82 +-----------------------------------
 arch/x86/include/asm/traps.h |  1 +
 3 files changed, 65 insertions(+), 81 deletions(-)
arch/x86/entry/entry64.c +63 -0
index 173cf621317c..c8ede8b088a6 100644
@@ -77,3 +77,66 @@ static __always_inline void kernel_entry_swapgs_and_fence(void)
 	native_swapgs();
 	fence_swapgs_kernel_entry();
 }
+
+/*
+ * Put pt_regs onto the task stack and switch GS and CR3 if needed.
+ * The actual stack switch is done in entry_64.S.
+ *
+ * Becareful, it might be in the user CR3 and user GS base at the start
+ * of the function.
+ */
+asmlinkage __visible __entry_text
+struct pt_regs *error_entry(struct pt_regs *eregs)
+{
+	unsigned long iret_ip = (unsigned long)native_irq_return_iret;
+
+	if (user_mode(eregs)) {
+		/*
+		 * We entered from user mode.
+		 * Switch to kernel gsbase and CR3.
+		 */
+		user_entry_swapgs_and_fence();
+		switch_to_kernel_cr3();
+
+		/* Put pt_regs onto the task stack. */
+		return sync_regs(eregs);
+	}
+
+	/*
+	 * There are two places in the kernel that can potentially fault with
+	 * usergs. Handle them here.  B stepping K8s sometimes report a
+	 * truncated RIP for IRET exceptions returning to compat mode. Check
+	 * for these here too.
+	 */
+	if ((eregs->ip == iret_ip) || (eregs->ip == (unsigned int)iret_ip)) {
+		eregs->ip = iret_ip; /* Fix truncated RIP */
+
+		/*
+		 * We came from an IRET to user mode, so we have user
+		 * gsbase and CR3.  Switch to kernel gsbase and CR3:
+		 */
+		user_entry_swapgs_and_fence();
+		switch_to_kernel_cr3();
+
+		/*
+		 * Pretend that the exception came from user mode: set up
+		 * pt_regs as if we faulted immediately after IRET and put
+		 * pt_regs onto the real task stack.
+		 */
+		return sync_regs(fixup_bad_iret(eregs));
+	}
+
+	/*
+	 * Hack: asm_load_gs_index_gs_change can fail with user gsbase.
+	 * If this happens, fix up gsbase and proceed.  We'll fix up the
+	 * exception and land in asm_load_gs_index_gs_change's error
+	 * handler with kernel gsbase.
+	 */
+	if (eregs->ip == (unsigned long)asm_load_gs_index_gs_change)
+		kernel_entry_swapgs_and_fence();
+	else
+		fence_swapgs_kernel_entry();
+
+	/* Enter from kernel, don't move pt_regs */
+	return eregs;
+}
arch/x86/entry/entry_64.S +1 -81

94 lines not on this page · raw message

arch/x86/include/asm/traps.h +1 -0
index 1cdd7e8bcba7..686461ac9803 100644
@@ -14,6 +14,7 @@
 asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs);
 asmlinkage __visible notrace
 struct pt_regs *fixup_bad_iret(struct pt_regs *bad_regs);
+asmlinkage __visible notrace struct pt_regs *error_entry(struct pt_regs *eregs);
 void __init trap_init(void);
 asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *eregs);
 #endif
Signature · 1 line
2.19.1.6.gb485710b
#30 lore raw

PATCH v3 25/49 x86/entry: Use idtentry macro for entry_INT80_compat

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

entry_INT80_compat is identical to idtentry macro except a special handling for %rax in the prolog.

Add the prolog to idtentry and use idtentry for entry_INT80_compat.

---
 arch/x86/entry/entry_64.S        |  18 ++++++
 arch/x86/entry/entry_64_compat.S | 103 -------------------------------
 arch/x86/include/asm/idtentry.h  |  47 ++++++++++++++
 arch/x86/include/asm/proto.h     |   4 --
 4 files changed, 65 insertions(+), 107 deletions(-)
arch/x86/entry/entry_64.S +18 -0
index 23de2a789e3d..79934c5ee9a1 100644
@@ -372,6 +372,24 @@ SYM_CODE_START(\asmsym)
 		pushq	$-1			/* ORIG_RAX: no syscall to restart */
 	.endif
 
+	.if \vector == IA32_SYSCALL_VECTOR
+		/*
+		 * User tracing code (ptrace or signal handlers) might assume
+		 * that the saved RAX contains a 32-bit number when we're
+		 * invoking a 32-bit syscall.  Just in case the high bits are
+		 * nonzero, zero-extend the syscall number.  (This could almost
+		 * certainly be deleted with no ill effects.)
+		 */
+		movl	%eax, %eax
+
+		/*
+		 * do_int80_syscall_32() expects regs->orig_ax to be user ax,
+		 * and regs->ax to be $-ENOSYS.
+		 */
+		movq	%rax, (%rsp)
+		movq	$-ENOSYS, %rax
+	.endif
+
 	.if \vector == X86_TRAP_BP
 		/*
 		 * If coming from kernel space, create a 6-word gap to allow the
arch/x86/entry/entry_64_compat.S +0 -103

106 lines not on this page · raw message

arch/x86/include/asm/idtentry.h +47 -0

65 lines not on this page · raw message

arch/x86/include/asm/proto.h +0 -4
index ee07b3cae213..7ca5619352e2 100644
@@ -29,10 +29,6 @@ void entry_SYSENTER_compat(void);
 void __end_entry_SYSENTER_compat(void);
 void entry_SYSCALL_compat(void);
 void entry_SYSCALL_compat_safe_stack(void);
-void entry_INT80_compat(void);
-#ifdef CONFIG_XEN_PV
-void xen_entry_INT80_compat(void);
-#endif
 #endif
 
 void x86_configure_nx(void);
Signature · 1 line
2.19.1.6.gb485710b
#31 lore raw

PATCH v3 26/49 x86/entry: Convert SWAPGS to swapgs in entry_SYSENTER_compat()

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

XENPV has its own entry point for SYSENTER, it doesn't use entry_SYSENTER_compat. So the pv-awared SWAPGS can be changed to swapgs.

---
 arch/x86/entry/entry_64_compat.S | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/x86/entry/entry_64_compat.S +1 -1
index ad20302246e4..0b9661edf652 100644
@@ -49,7 +49,7 @@
 SYM_CODE_START(entry_SYSENTER_compat)
 	UNWIND_HINT_EMPTY
 	/* Interrupts are off on entry. */
-	SWAPGS
+	swapgs
 
 	pushq	%rax
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
Signature · 1 line
2.19.1.6.gb485710b
#32 lore raw

PATCH v3 27/49 x86: Remove the definition of SWAPGS

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

There is no user of the pv-aware SWAPGS anymore.

---
 arch/x86/include/asm/irqflags.h | 8 --------
 1 file changed, 8 deletions(-)
arch/x86/include/asm/irqflags.h +0 -8
index c5ce9845c999..da41a80eb912 100644
@@ -139,14 +139,6 @@ static __always_inline void arch_local_irq_restore(unsigned long flags)
 	if (!arch_irqs_disabled_flags(flags))
 		arch_local_irq_enable();
 }
-#else
-#ifdef CONFIG_X86_64
-#ifdef CONFIG_XEN_PV
-#define SWAPGS	ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV
-#else
-#define SWAPGS	swapgs
-#endif
-#endif
 #endif /* !__ASSEMBLY__ */
 
 #endif
Signature · 1 line
2.19.1.6.gb485710b
#33 lore raw

PATCH v3 28/49 x86/entry: Make paranoid_exit() callable

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

Move the last JMP out of paranoid_exit() and make it callable.

Allow paranoid_exit() to be re-written in C later and also allow asm_exc_nmi() to call it to avoid duplicated code.

No functional change intended.

---
 arch/x86/entry/entry_64.S | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)
arch/x86/entry/entry_64.S +11 -7
index 79934c5ee9a1..8790bf41edd4 100644
@@ -472,7 +472,8 @@ SYM_CODE_START(\asmsym)
 
 	call	\cfunc
 
-	jmp	paranoid_exit
+	call	paranoid_exit
+	jmp	restore_regs_and_return_to_kernel
 
 	/* Switch to the regular task stack and use the noist entry point */
 .Lfrom_usermode_switch_stack_\@:
@@ -550,7 +551,8 @@ SYM_CODE_START(\asmsym)
 	 * identical to the stack in the IRET frame or the VC fall-back stack,
 	 * so it is definitely mapped even with PTI enabled.
 	 */
-	jmp	paranoid_exit
+	call	paranoid_exit
+	jmp	restore_regs_and_return_to_kernel
 
 	/* Switch to the regular task stack */
 .Lfrom_usermode_switch_stack_\@:
@@ -581,7 +583,8 @@ SYM_CODE_START(\asmsym)
 	movq	$-1, ORIG_RAX(%rsp)	/* no syscall to restart */
 	call	\cfunc
 
-	jmp	paranoid_exit
+	call	paranoid_exit
+	jmp	restore_regs_and_return_to_kernel
 
 _ASM_NOKPROBE(\asmsym)
 SYM_CODE_END(\asmsym)
@@ -974,7 +977,7 @@ SYM_CODE_END(paranoid_entry)
  *     Y        User space GSBASE, must be restored unconditionally
  */
 SYM_CODE_START_LOCAL(paranoid_exit)
-	UNWIND_HINT_REGS
+	UNWIND_HINT_REGS offset=8
 	/*
 	 * The order of operations is important. RESTORE_CR3 requires
 	 * kernel GSBASE.
@@ -990,16 +993,17 @@ SYM_CODE_START_LOCAL(paranoid_exit)
 
 	/* With FSGSBASE enabled, unconditionally restore GSBASE */
 	wrgsbase	%rbx
-	jmp		restore_regs_and_return_to_kernel
+	ret
 
 .Lparanoid_exit_checkgs:
 	/* On non-FSGSBASE systems, conditionally do SWAPGS */
 	testl		%ebx, %ebx
-	jnz		restore_regs_and_return_to_kernel
+	jnz		.Lparanoid_exit_done
 
 	/* We are returning to a context with user GSBASE */
 	swapgs
-	jmp		restore_regs_and_return_to_kernel
+.Lparanoid_exit_done:
+	ret
 SYM_CODE_END(paranoid_exit)
 
 SYM_CODE_START_LOCAL(error_return)
Signature · 1 line
2.19.1.6.gb485710b
#34 lore raw

PATCH v3 29/49 x86/entry: Call paranoid_exit() in asm_exc_nmi()

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

The code between "call exc_nmi" and nmi_restore is as the same as paranoid_exit(), so we can just use paranoid_exit() instead of the open duplicated code.

No functional change intended.

---
 arch/x86/entry/entry_64.S | 34 +++++-----------------------------
 1 file changed, 5 insertions(+), 29 deletions(-)
arch/x86/entry/entry_64.S +5 -29
index 8790bf41edd4..8d873b778681 100644
@@ -959,8 +959,7 @@ SYM_CODE_END(paranoid_entry)
 
 /*
  * "Paranoid" exit path from exception stack.  This is invoked
- * only on return from non-NMI IST interrupts that came
- * from kernel space.
+ * only on return from IST interrupts that came from kernel space.
  *
  * We may be returning to very strange contexts (e.g. very early
  * in syscall entry), so checking for preemption here would
@@ -1309,11 +1308,7 @@ end_repeat_nmi:
 	pushq	$-1				/* ORIG_RAX: no syscall to restart */
 
 	/*
-	 * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit
-	 * as we should not be calling schedule in NMI context.
-	 * Even with normal interrupts enabled. An NMI should not be
-	 * setting NEED_RESCHED or anything that normal interrupts and
-	 * exceptions might do.
+	 * Use paranoid_entry to handle SWAPGS and CR3.
 	 */
 	call	paranoid_entry
 	UNWIND_HINT_REGS
@@ -1322,31 +1317,12 @@ end_repeat_nmi:
 	movq	$-1, %rsi
 	call	exc_nmi
 
-	/* Always restore stashed CR3 value (see paranoid_entry) */
-	RESTORE_CR3 scratch_reg=%r15 save_reg=%r14
-
 	/*
-	 * The above invocation of paranoid_entry stored the GSBASE
-	 * related information in R/EBX depending on the availability
-	 * of FSGSBASE.
-	 *
-	 * If FSGSBASE is enabled, restore the saved GSBASE value
-	 * unconditionally, otherwise take the conditional SWAPGS path.
+	 * Use paranoid_exit to handle SWAPGS and CR3, but no need to use
+	 * restore_regs_and_return_to_kernel as we must handle nested NMI.
 	 */
-	ALTERNATIVE "jmp nmi_no_fsgsbase", "", X86_FEATURE_FSGSBASE
-
-	wrgsbase	%rbx
-	jmp	nmi_restore
-
-nmi_no_fsgsbase:
-	/* EBX == 0 -> invoke SWAPGS */
-	testl	%ebx, %ebx
-	jnz	nmi_restore
-
-nmi_swapgs:
-	swapgs
+	call	paranoid_exit
 
-nmi_restore:
 	POP_REGS
 
 	/*
Signature · 1 line
2.19.1.6.gb485710b
#35 lore raw

PATCH v3 30/49 x86/entry: move PUSH_AND_CLEAR_REGS out of paranoid_entry

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

It is prepared for converting the whole paranoid_entry() into C code.

No functional change intended.

---
 arch/x86/entry/entry_64.S | 24 +++++++++++++++++-------
 1 file changed, 17 insertions(+), 7 deletions(-)
arch/x86/entry/entry_64.S +17 -7
index 8d873b778681..c9ee58e8e6d1 100644
@@ -323,9 +323,6 @@ SYM_CODE_END(ret_from_fork)
  */
 .macro idtentry_body cfunc has_error_code:req
 
-	PUSH_AND_CLEAR_REGS
-	ENCODE_FRAME_POINTER
-
 	/*
 	 * Call error_entry and switch stack settled by sync_regs().
 	 *
@@ -404,6 +401,9 @@ SYM_CODE_START(\asmsym)
 .Lfrom_usermode_no_gap_\@:
 	.endif
 
+	PUSH_AND_CLEAR_REGS
+	ENCODE_FRAME_POINTER
+
 	idtentry_body \cfunc \has_error_code
 
 _ASM_NOKPROBE(\asmsym)
@@ -456,11 +456,14 @@ SYM_CODE_START(\asmsym)
 
 	pushq	$-1			/* ORIG_RAX: no syscall to restart */
 
+	PUSH_AND_CLEAR_REGS
+	ENCODE_FRAME_POINTER
+
 	/*
 	 * If the entry is from userspace, switch stacks and treat it as
 	 * a normal entry.
 	 */
-	testb	$3, CS-ORIG_RAX(%rsp)
+	testb	$3, CS(%rsp)
 	jnz	.Lfrom_usermode_switch_stack_\@
 
 	/* paranoid_entry returns GS information for paranoid_exit in EBX. */
@@ -511,11 +514,14 @@ SYM_CODE_START(\asmsym)
 	ASM_CLAC
 	cld
 
+	PUSH_AND_CLEAR_REGS
+	ENCODE_FRAME_POINTER
+
 	/*
 	 * If the entry is from userspace, switch stacks and treat it as
 	 * a normal entry.
 	 */
-	testb	$3, CS-ORIG_RAX(%rsp)
+	testb	$3, CS(%rsp)
 	jnz	.Lfrom_usermode_switch_stack_\@
 
 	/*
@@ -574,6 +580,9 @@ SYM_CODE_START(\asmsym)
 	ASM_CLAC
 	cld
 
+	PUSH_AND_CLEAR_REGS
+	ENCODE_FRAME_POINTER
+
 	/* paranoid_entry returns GS information for paranoid_exit in EBX. */
 	call	paranoid_entry
 	UNWIND_HINT_REGS
@@ -886,8 +895,6 @@ SYM_CODE_END(xen_failsafe_callback)
  */
 SYM_CODE_START_LOCAL(paranoid_entry)
 	UNWIND_HINT_FUNC
-	PUSH_AND_CLEAR_REGS save_ret=1
-	ENCODE_FRAME_POINTER 8
 
 	/*
 	 * Always stash CR3 in %r14.  This value will be restored,
@@ -1307,6 +1314,9 @@ end_repeat_nmi:
 	 */
 	pushq	$-1				/* ORIG_RAX: no syscall to restart */
 
+	PUSH_AND_CLEAR_REGS
+	ENCODE_FRAME_POINTER
+
 	/*
 	 * Use paranoid_entry to handle SWAPGS and CR3.
 	 */
Signature · 1 line
2.19.1.6.gb485710b
#36 lore raw

PATCH v3 31/49 x86/entry: Add the C version ist_switch_to_kernel_cr3()

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

It switches the CR3 to kernel CR3 and returns the original CR3, and the caller should save the return value.

It is the C version of SAVE_AND_SWITCH_TO_KERNEL_CR3.

Not functional difference intended.

---
 arch/x86/entry/entry64.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)
arch/x86/entry/entry64.c +15 -0
index c8ede8b088a6..7e6c1b8a93d1 100644
@@ -35,8 +35,23 @@ static __always_inline void switch_to_kernel_cr3(void)
 	if (static_cpu_has(X86_FEATURE_PTI))
 		pti_switch_to_kernel_cr3(__native_read_cr3());
 }
+
+static __always_inline unsigned long ist_switch_to_kernel_cr3(void)
+{
+	unsigned long cr3 = 0;
+
+	if (static_cpu_has(X86_FEATURE_PTI)) {
+		cr3 = __native_read_cr3();
+
+		if (cr3 & PTI_USER_PGTABLE_MASK)
+			pti_switch_to_kernel_cr3(cr3);
+	}
+
+	return cr3;
+}
 #else
 static __always_inline void switch_to_kernel_cr3(void) {}
+static __always_inline unsigned long ist_switch_to_kernel_cr3(void) { return 0; }
 #endif
 
 /*
Signature · 1 line
2.19.1.6.gb485710b
#37 lore raw

PATCH v3 32/49 x86/entry: Add the C version ist_restore_cr3()

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

It implements the C version of RESTORE_CR3().

Not functional difference intended except the ASM code uses bit test and clear operations while the C version uses mask check and 'AND' operations. The resulted asm code of both versions are very similar.

---
 arch/x86/entry/entry64.c | 46 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)
arch/x86/entry/entry64.c +46 -0
index 7e6c1b8a93d1..5edbb4bb4786 100644
@@ -11,6 +11,7 @@
  * environments that the GS base is user controlled value, or the CR3
  * is PTI user CR3 or both.
  */
+#include <asm/tlbflush.h>
 #include <asm/traps.h>
 
 extern unsigned char asm_load_gs_index_gs_change[];
@@ -30,6 +31,26 @@ static __always_inline void pti_switch_to_kernel_cr3(unsigned long user_cr3)
 	native_write_cr3(cr3);
 }
 
+static __always_inline void pti_switch_to_user_cr3(unsigned long user_cr3)
+{
+#define KERN_PCID_MASK (CR3_PCID_MASK & ~PTI_USER_PCID_MASK)
+
+	if (static_cpu_has(X86_FEATURE_PCID)) {
+		int pcid = user_cr3 & KERN_PCID_MASK;
+		unsigned short pcid_mask = 1ull << pcid;
+
+		/*
+		 * Check if there's a pending flush for the user ASID we're
+		 * about to set.
+		 */
+		if (!(this_cpu_read(cpu_tlbstate.user_pcid_flush_mask) & pcid_mask))
+			user_cr3 |= X86_CR3_PCID_NOFLUSH;
+		else
+			this_cpu_and(cpu_tlbstate.user_pcid_flush_mask, ~pcid_mask);
+	}
+	native_write_cr3(user_cr3);
+}
+
 static __always_inline void switch_to_kernel_cr3(void)
 {
 	if (static_cpu_has(X86_FEATURE_PTI))
@@ -49,9 +70,34 @@ static __always_inline unsigned long ist_switch_to_kernel_cr3(void)
 
 	return cr3;
 }
+
+static __always_inline void ist_restore_cr3(unsigned long cr3)
+{
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	if (unlikely(cr3 & PTI_USER_PGTABLE_MASK)) {
+		pti_switch_to_user_cr3(cr3);
+		return;
+	}
+
+	/*
+	 * KERNEL pages can always resume with NOFLUSH as we do
+	 * explicit flushes.
+	 */
+	if (static_cpu_has(X86_FEATURE_PCID))
+		cr3 |= X86_CR3_PCID_NOFLUSH;
+
+	/*
+	 * The CR3 write could be avoided when not changing its value,
+	 * but would require a CR3 read.
+	 */
+	native_write_cr3(cr3);
+}
 #else
 static __always_inline void switch_to_kernel_cr3(void) {}
 static __always_inline unsigned long ist_switch_to_kernel_cr3(void) { return 0; }
+static __always_inline void ist_restore_cr3(unsigned long cr3) {}
 #endif
 
 /*
Signature · 1 line
2.19.1.6.gb485710b
#38 lore raw

Re: [PATCH V3 32/49] x86/entry: Add the C version ist_restore_cr3()

Quoted 8 lines · Lai Jiangshan
  static __always_inline void switch_to_kernel_cr3(void)
  {
  	if (static_cpu_has(X86_FEATURE_PTI))
arch/x86/entry/entry64.c +0 -0
@@ -49,9 +70,34 @@ static __always_inline unsigned long ist_switch_to_kernel_cr3(void)
 
  	return cr3;
  }

arch/x86/entry/entry64.c static __always_inline unsigned long ist_switch_to_kernel_cr3(void) · line 82

Quoted 10 lines
arch/x86/entry/entry64.c +10 -0
+
+static __always_inline void ist_restore_cr3(unsigned long cr3)
+{
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	if (unlikely(cr3 & PTI_USER_PGTABLE_MASK)) {
+		pti_switch_to_user_cr3(cr3);
+		return;
+	}

The C code is semantically copied from ASM.

The ASM code is from the commit 21e9445911025("x86/mm: Optimize RESTORE_CR3") which still keeps the older behavior of writing to CR3 unconditionally even the saved CR3 is kernel CR3.

Is there any special reason that the CR3 needs to be written for kernel CR3?

I would add a commit to change it in ASM code by skipping cr3 write when it is kernel CR3, and then make the C code as the same as new ASM code.

Quoted 22 lines
arch/x86/entry/entry64.c +15 -0
+
+	/*
+	 * KERNEL pages can always resume with NOFLUSH as we do
+	 * explicit flushes.
+	 */
+	if (static_cpu_has(X86_FEATURE_PCID))
+		cr3 |= X86_CR3_PCID_NOFLUSH;
+
+	/*
+	 * The CR3 write could be avoided when not changing its value,
+	 * but would require a CR3 read.
+	 */
+	native_write_cr3(cr3);
+}
  #else
  static __always_inline void switch_to_kernel_cr3(void) {}
  static __always_inline unsigned long ist_switch_to_kernel_cr3(void) { return 0; }
+static __always_inline void ist_restore_cr3(unsigned long cr3) {}
  #endif
 
  /*
#39 lore raw

PATCH v3 33/49 x86/entry: Add the C version get_percpu_base()

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

It implements the C version of asm macro GET_PERCPU_BASE().

Not functional difference intended.

---
 arch/x86/entry/entry64.c | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)
arch/x86/entry/entry64.c +36 -0
index 5edbb4bb4786..48fd3199f00b 100644
@@ -201,3 +201,39 @@ struct pt_regs *error_entry(struct pt_regs *eregs)
 	/* Enter from kernel, don't move pt_regs */
 	return eregs;
 }
+
+#ifdef CONFIG_SMP
+/*
+ * CPU/node NR is loaded from the limit (size) field of a special segment
+ * descriptor entry in GDT.
+ *
+ * Do not use RDPID, because KVM loads guest's TSC_AUX on vm-entry and
+ * may not restore the host's value until the CPU returns to userspace.
+ * Thus the kernel would consume a guest's TSC_AUX if an NMI arrives
+ * while running KVM's run loop.
+ */
+static __always_inline unsigned int gdt_get_cpu(void)
+{
+	unsigned int p;
+
+	asm ("lsl %[seg],%[p]" : [p] "=a" (p) : [seg] "r" (__CPUNODE_SEG));
+
+	return p & VDSO_CPUNODE_MASK;
+}
+
+/*
+ * Fetch the per-CPU GSBASE value for this processor.
+ *
+ * We normally use %gs for accessing per-CPU data, but we are setting up
+ * %gs here and obviously can not use %gs itself to access per-CPU data.
+ */
+static __always_inline unsigned long get_percpu_base(void)
+{
+	return __per_cpu_offset[gdt_get_cpu()];
+}
+#else
+static __always_inline unsigned long get_percpu_base(void)
+{
+	return pcpu_unit_offsets;
+}
+#endif
Signature · 1 line
2.19.1.6.gb485710b
#40 lore raw

PATCH v3 34/49 x86/entry: Add the C version ist_switch_to_kernel_gsbase()

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

It implements the second half of paranoid_entry() whose functionality is to switch to kernel gsbase.

Not functional difference intended.

---
 arch/x86/entry/entry64.c | 51 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)
arch/x86/entry/entry64.c +51 -0
index 48fd3199f00b..06f7476d78b4 100644
@@ -237,3 +237,54 @@ static __always_inline unsigned long get_percpu_base(void)
 	return pcpu_unit_offsets;
 }
 #endif
+
+/*
+ * Handle GSBASE depends on the availability of FSGSBASE.
+ *
+ * Without FSGSBASE the kernel enforces that negative GSBASE
+ * values indicate kernel GSBASE. With FSGSBASE no assumptions
+ * can be made about the GSBASE value when entering from user
+ * space.
+ */
+static __always_inline unsigned long ist_switch_to_kernel_gsbase(void)
+{
+	unsigned long gsbase;
+
+	if (static_cpu_has(X86_FEATURE_FSGSBASE)) {
+		/*
+		 * Read the current GSBASE for return.
+		 * Retrieve and set the current CPUs kernel GSBASE.
+		 *
+		 * The unconditional write to GS base below ensures that
+		 * no subsequent loads based on a mispredicted GS base can
+		 * happen, therefore no LFENCE is needed here.
+		 */
+		gsbase = rdgsbase();
+		wrgsbase(get_percpu_base());
+		return gsbase;
+	}
+
+	gsbase = __rdmsr(MSR_GS_BASE);
+
+	/*
+	 * The kernel-enforced convention is a negative GSBASE indicates
+	 * a kernel value. No SWAPGS needed on entry and exit.
+	 */
+	if ((long)gsbase < 0) {
+		fence_swapgs_kernel_entry();
+		/* no SWAPGS required on exit */
+		return 1;
+	}
+
+	/*
+	 * SWAPGS is needed.
+	 *
+	 * The above ist_switch_to_kernel_cr3() doesn't do an unconditional
+	 * CR3 write, even in the PTI case.  So do an lfence to prevent GS
+	 * speculation, regardless of whether PTI is enabled.
+	 */
+	kernel_entry_swapgs_and_fence();
+
+	/* SWAPGS required on exit */
+	return 0;
+}
Signature · 1 line
2.19.1.6.gb485710b
#41 lore raw

PATCH v3 35/49 x86/entry: Implement the C version ist_paranoid_entry()

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

It implements the whole ASM version paranoid_entry().

No functional difference intended.

---
 arch/x86/entry/entry64.c        | 37 +++++++++++++++++++++++++++++++++
 arch/x86/include/asm/idtentry.h |  3 +++
 2 files changed, 40 insertions(+)
arch/x86/entry/entry64.c +37 -0
index 06f7476d78b4..8e1474ece7f9 100644
@@ -288,3 +288,40 @@ static __always_inline unsigned long ist_switch_to_kernel_gsbase(void)
 	/* SWAPGS required on exit */
 	return 0;
 }
+
+/*
+ * Switch and save CR3 in *@cr3 if PTI enabled. Return GSBASE related
+ * information in *@gsbase depending on the availability of the FSGSBASE
+ * instructions:
+ *
+ * FSGSBASE	*@gsbase
+ *     N        0 -> SWAPGS on exit
+ *              1 -> no SWAPGS on exit
+ *
+ *     Y        GSBASE value at entry, must be restored in ist_paranoid_exit
+ */
+__visible __entry_text
+void ist_paranoid_entry(unsigned long *cr3, unsigned long *gsbase)
+{
+	/*
+	 * Always stash CR3 in *@cr3.  This value will be restored,
+	 * verbatim, at exit.  Needed if ist_paranoid_entry interrupted
+	 * another entry that already switched to the user CR3 value
+	 * but has not yet returned to userspace.
+	 *
+	 * This is also why CS (stashed in the "iret frame" by the
+	 * hardware at entry) can not be used: this may be a return
+	 * to kernel code, but with a user CR3 value.
+	 *
+	 * Switching CR3 does not depend on kernel GSBASE so it can
+	 * be done before switching to the kernel GSBASE. This is
+	 * required for FSGSBASE because the kernel GSBASE has to
+	 * be retrieved from a kernel internal table.
+	 */
+	*cr3 = ist_switch_to_kernel_cr3();
+
+	barrier();
+
+	/* Handle GSBASE, store the return value in *@gsbase for exit. */
+	*gsbase = ist_switch_to_kernel_gsbase();
+}
arch/x86/include/asm/idtentry.h +3 -0
index 49fabc3e3f0d..f6efa21ec242 100644
@@ -307,6 +307,9 @@ static __always_inline void __##func(struct pt_regs *regs)
 	DECLARE_IDTENTRY(vector, func)
 
 #ifdef CONFIG_X86_64
+__visible __entry_text
+void ist_paranoid_entry(unsigned long *cr3, unsigned long *gsbase);
+
 /**
  * DECLARE_IDTENTRY_IST - Declare functions for IST handling IDT entry points
  * @vector:	Vector number (ignored for C)
Signature · 1 line
2.19.1.6.gb485710b
#42 lore raw

PATCH v3 36/49 x86/entry: Implement the C version ist_paranoid_exit()

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

It implements the whole ASM version paranoid_exit().

No functional difference intended.

---
 arch/x86/entry/entry64.c        | 40 +++++++++++++++++++++++++++++++++
 arch/x86/include/asm/idtentry.h |  2 ++
 2 files changed, 42 insertions(+)
arch/x86/entry/entry64.c +40 -0
index 8e1474ece7f9..51293ecbfe3f 100644
@@ -325,3 +325,43 @@ void ist_paranoid_entry(unsigned long *cr3, unsigned long *gsbase)
 	/* Handle GSBASE, store the return value in *@gsbase for exit. */
 	*gsbase = ist_switch_to_kernel_gsbase();
 }
+
+/*
+ * "Paranoid" exit path from exception stack.  This is invoked
+ * only on return from IST interrupts that came from kernel space.
+ *
+ * We may be returning to very strange contexts (e.g. very early
+ * in syscall entry), so checking for preemption here would
+ * be complicated.  Fortunately, there's no good reason to try
+ * to handle preemption here.
+ */
+__visible __entry_text
+void ist_paranoid_exit(unsigned long cr3, unsigned long gsbase)
+{
+	/*
+	 * Restore CR3 at first, it can use kernel GSBASE.
+	 */
+	ist_restore_cr3(cr3);
+
+	barrier();
+
+	/*
+	 * Handle the three GSBASE cases.
+	 *
+	 * @gsbase contains the GSBASE related information depending
+	 * on the availability of the FSGSBASE instructions:
+	 *
+	 * FSGSBASE	@gsbase
+	 *     N        0 -> SWAPGS on exit
+	 *              1 -> no SWAPGS on exit
+	 *
+	 *     Y        User space GSBASE, must be restored unconditionally
+	 */
+	if (static_cpu_has(X86_FEATURE_FSGSBASE)) {
+		wrgsbase(gsbase);
+		return;
+	}
+
+	if (gsbase)
+		native_swapgs();
+}
arch/x86/include/asm/idtentry.h +2 -0
index f6efa21ec242..cf41901227ed 100644
@@ -309,6 +309,8 @@ static __always_inline void __##func(struct pt_regs *regs)
 #ifdef CONFIG_X86_64
 __visible __entry_text
 void ist_paranoid_entry(unsigned long *cr3, unsigned long *gsbase);
+__visible __entry_text
+void ist_paranoid_exit(unsigned long cr3, unsigned long gsbase);
 
 /**
  * DECLARE_IDTENTRY_IST - Declare functions for IST handling IDT entry points
Signature · 1 line
2.19.1.6.gb485710b
#43 lore raw

PATCH v3 37/49 x86/entry: Add a C macro to define the function body for IST in .entry.text

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

Add DEFINE_IDTENTRY_IST_ETNRY() macro to define C code to implement the ASM code which calls paranoid_entry(), cfunc(), paranoid_exit() in series for IST exceptions without error code.

Not functional difference intended.

---
 arch/x86/include/asm/idtentry.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)
arch/x86/include/asm/idtentry.h +14 -0
index cf41901227ed..0f615943a460 100644
@@ -337,6 +337,20 @@ void ist_paranoid_exit(unsigned long cr3, unsigned long gsbase);
 	__visible noinstr void kernel_##func(struct pt_regs *regs, unsigned long error_code);	\
 	__visible noinstr void   user_##func(struct pt_regs *regs, unsigned long error_code)
 
+/**
+ * DEFINE_IDTENTRY_IST_ENTRY - Emit __entry_text code for IST entry points
+ * @func:	Function name of the entry point
+ */
+#define DEFINE_IDTENTRY_IST_ETNRY(func)					\
+__visible __entry_text void ist_##func(struct pt_regs *regs)		\
+{									\
+	unsigned long cr3, gsbase;					\
+									\
+	ist_paranoid_entry(&cr3, &gsbase);				\
+	func(regs);							\
+	ist_paranoid_exit(cr3, gsbase);					\
+}
+
 /**
  * DEFINE_IDTENTRY_IST - Emit code for IST entry points
  * @func:	Function name of the entry point
Signature · 1 line
2.19.1.6.gb485710b
#44 lore raw

PATCH v3 38/49 x86/debug, mce: Use C entry code

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

Use DEFINE_IDTENTRY_IST_ETNRY to emit C entry function and use the function directly in entry_64.S.

---
 arch/x86/entry/entry_64.S        | 10 +---------
 arch/x86/include/asm/idtentry.h  |  1 +
 arch/x86/kernel/cpu/mce/Makefile |  3 +++
 3 files changed, 5 insertions(+), 9 deletions(-)
arch/x86/entry/entry_64.S +1 -9
index c9ee58e8e6d1..7c994bcde1b0 100644
@@ -466,16 +466,8 @@ SYM_CODE_START(\asmsym)
 	testb	$3, CS(%rsp)
 	jnz	.Lfrom_usermode_switch_stack_\@
 
-	/* paranoid_entry returns GS information for paranoid_exit in EBX. */
-	call	paranoid_entry
-
-	UNWIND_HINT_REGS
-
 	movq	%rsp, %rdi		/* pt_regs pointer */
-
-	call	\cfunc
-
-	call	paranoid_exit
+	call	ist_\cfunc
 	jmp	restore_regs_and_return_to_kernel
 
 	/* Switch to the regular task stack and use the noist entry point */
arch/x86/include/asm/idtentry.h +1 -0
index 0f615943a460..d0fd32288442 100644
@@ -358,6 +358,7 @@ __visible __entry_text void ist_##func(struct pt_regs *regs)		\
  * Maps to DEFINE_IDTENTRY_RAW
  */
 #define DEFINE_IDTENTRY_IST(func)					\
+	DEFINE_IDTENTRY_IST_ETNRY(func)					\
 	DEFINE_IDTENTRY_RAW(func)
 
 /**
arch/x86/kernel/cpu/mce/Makefile +3 -0
index 015856abdbb1..555963416ec3 100644
@@ -1,4 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
+
+CFLAGS_core.o			+= -fno-stack-protector
+
 obj-y				=  core.o severity.o genpool.o
 
 obj-$(CONFIG_X86_ANCIENT_MCE)	+= winchip.o p5.o
Signature · 1 line
2.19.1.6.gb485710b
#45 lore raw

PATCH v3 39/49 x86/idtentry.h: Move the definitions *IDTENTRY_{MCE|DEBUG}* up

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

Move them closer to the related definitions and reduce a #ifdef entry.

---
 arch/x86/include/asm/idtentry.h | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)
arch/x86/include/asm/idtentry.h +8 -10
index d0fd32288442..b9a6750dbba2 100644
@@ -372,6 +372,14 @@ __visible __entry_text void ist_##func(struct pt_regs *regs)		\
 #define DEFINE_IDTENTRY_NOIST(func)					\
 	DEFINE_IDTENTRY_RAW(noist_##func)
 
+#define DECLARE_IDTENTRY_MCE		DECLARE_IDTENTRY_IST
+#define DEFINE_IDTENTRY_MCE		DEFINE_IDTENTRY_IST
+#define DEFINE_IDTENTRY_MCE_USER	DEFINE_IDTENTRY_NOIST
+
+#define DECLARE_IDTENTRY_DEBUG		DECLARE_IDTENTRY_IST
+#define DEFINE_IDTENTRY_DEBUG		DEFINE_IDTENTRY_IST
+#define DEFINE_IDTENTRY_DEBUG_USER	DEFINE_IDTENTRY_NOIST
+
 /**
  * DECLARE_IDTENTRY_DF - Declare functions for double fault
  * @vector:	Vector number (ignored for C)
@@ -446,16 +454,6 @@ __visible noinstr void func(struct pt_regs *regs,			\
 #define DECLARE_IDTENTRY_NMI		DECLARE_IDTENTRY_RAW
 #define DEFINE_IDTENTRY_NMI		DEFINE_IDTENTRY_RAW
 
-#ifdef CONFIG_X86_64
-#define DECLARE_IDTENTRY_MCE		DECLARE_IDTENTRY_IST
-#define DEFINE_IDTENTRY_MCE		DEFINE_IDTENTRY_IST
-#define DEFINE_IDTENTRY_MCE_USER	DEFINE_IDTENTRY_NOIST
-
-#define DECLARE_IDTENTRY_DEBUG		DECLARE_IDTENTRY_IST
-#define DEFINE_IDTENTRY_DEBUG		DEFINE_IDTENTRY_IST
-#define DEFINE_IDTENTRY_DEBUG_USER	DEFINE_IDTENTRY_NOIST
-#endif
-
 #else /* !__ASSEMBLY__ */
 
 /*
Signature · 1 line
2.19.1.6.gb485710b
#46 lore raw

PATCH v3 40/49 x86/nmi: Use DEFINE_IDTENTRY_NMI for nmi

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

DEFINE_IDTENTRY_NMI is defined, but not used. It is better to use it.

It is also prepared for later patch to define DEFINE_IDTENTRY_NMI differently in 32bit and 64bit.

---
 arch/x86/kernel/nmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/x86/kernel/nmi.c +1 -1
index 4bce802d25fb..44c3adb68282 100644
@@ -473,7 +473,7 @@ static DEFINE_PER_CPU(enum nmi_states, nmi_state);
 static DEFINE_PER_CPU(unsigned long, nmi_cr2);
 static DEFINE_PER_CPU(unsigned long, nmi_dr7);
 
-DEFINE_IDTENTRY_RAW(exc_nmi)
+DEFINE_IDTENTRY_NMI(exc_nmi)
 {
 	irqentry_state_t irq_state;
 
Signature · 1 line
2.19.1.6.gb485710b
#47 lore raw

PATCH v3 41/49 x86/nmi: Use C entry code

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

Use DEFINE_IDTENTRY_IST_ETNRY to emit C entry function and use the function directly in entry_64.S.

---
 arch/x86/entry/entry_64.S       | 17 ++---------------
 arch/x86/include/asm/idtentry.h |  5 ++++-
 arch/x86/kernel/Makefile        |  1 +
 3 files changed, 7 insertions(+), 16 deletions(-)
arch/x86/entry/entry_64.S +2 -15
index 7c994bcde1b0..0a1a55c8207e 100644
@@ -1309,21 +1309,8 @@ end_repeat_nmi:
 	PUSH_AND_CLEAR_REGS
 	ENCODE_FRAME_POINTER
 
-	/*
-	 * Use paranoid_entry to handle SWAPGS and CR3.
-	 */
-	call	paranoid_entry
-	UNWIND_HINT_REGS
-
-	movq	%rsp, %rdi
-	movq	$-1, %rsi
-	call	exc_nmi
-
-	/*
-	 * Use paranoid_exit to handle SWAPGS and CR3, but no need to use
-	 * restore_regs_and_return_to_kernel as we must handle nested NMI.
-	 */
-	call	paranoid_exit
+	movq	%rsp, %rdi		/* pt_regs pointer */
+	call	ist_exc_nmi
 
 	POP_REGS
 
arch/x86/include/asm/idtentry.h +4 -1
index b9a6750dbba2..57636844b0fd 100644
@@ -372,6 +372,8 @@ __visible __entry_text void ist_##func(struct pt_regs *regs)		\
 #define DEFINE_IDTENTRY_NOIST(func)					\
 	DEFINE_IDTENTRY_RAW(noist_##func)
 
+#define DEFINE_IDTENTRY_NMI		DEFINE_IDTENTRY_IST
+
 #define DECLARE_IDTENTRY_MCE		DECLARE_IDTENTRY_IST
 #define DEFINE_IDTENTRY_MCE		DEFINE_IDTENTRY_IST
 #define DEFINE_IDTENTRY_MCE_USER	DEFINE_IDTENTRY_NOIST
@@ -421,6 +423,8 @@ __visible __entry_text void ist_##func(struct pt_regs *regs)		\
 
 #else	/* CONFIG_X86_64 */
 
+#define DEFINE_IDTENTRY_NMI		DEFINE_IDTENTRY_RAW
+
 /**
  * DECLARE_IDTENTRY_DF - Declare functions for double fault 32bit variant
  * @vector:	Vector number (ignored for C)
@@ -452,7 +456,6 @@ __visible noinstr void func(struct pt_regs *regs,			\
 
 /* C-Code mapping */
 #define DECLARE_IDTENTRY_NMI		DECLARE_IDTENTRY_RAW
-#define DEFINE_IDTENTRY_NMI		DEFINE_IDTENTRY_RAW
 
 #else /* !__ASSEMBLY__ */
 
arch/x86/kernel/Makefile +1 -0
index 8ac45801ba8b..28815c2e6cb2 100644
@@ -51,6 +51,7 @@ KCOV_INSTRUMENT		:= n
 CFLAGS_head$(BITS).o	+= -fno-stack-protector
 CFLAGS_cc_platform.o	+= -fno-stack-protector
 CFLAGS_traps.o		+= -fno-stack-protector
+CFLAGS_nmi.o		+= -fno-stack-protector
 
 CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace
 
Signature · 1 line
2.19.1.6.gb485710b
#48 lore raw

PATCH v3 42/49 x86/entry: Add a C macro to define the function body for IST in .entry.text with an error code

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

Add DEFINE_IDTENTRY_IST_ETNRY_ERRORCODE() macro to define C code to implement the ASM code which calls paranoid_entry(), modify orig_ax, cfunc(), paranoid_exit() in series for IST exceptions with an error code.

Not functional difference intended.

---
 arch/x86/include/asm/idtentry.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)
arch/x86/include/asm/idtentry.h +16 -0
index 57636844b0fd..c57606948433 100644
@@ -351,6 +351,22 @@ __visible __entry_text void ist_##func(struct pt_regs *regs)		\
 	ist_paranoid_exit(cr3, gsbase);					\
 }
 
+/**
+ * DEFINE_IDTENTRY_IST_ENTRY_ERRORCODE - Emit __entry_text code for IST
+ *					 entry points with an error code
+ * @func:	Function name of the entry point
+ */
+#define DEFINE_IDTENTRY_IST_ETNRY_ERRORCODE(func)			\
+__visible __entry_text void ist_##func(struct pt_regs *regs)		\
+{									\
+	unsigned long cr3, gsbase, error_code = regs->orig_ax;		\
+									\
+	ist_paranoid_entry(&cr3, &gsbase);				\
+	regs->orig_ax = -1;	/* no syscall to restart */		\
+	func(regs, error_code);						\
+	ist_paranoid_exit(cr3, gsbase);					\
+}
+
 /**
  * DEFINE_IDTENTRY_IST - Emit code for IST entry points
  * @func:	Function name of the entry point
Signature · 1 line
2.19.1.6.gb485710b
#49 lore raw

PATCH v3 43/49 x86/doublefault: Use C entry code

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

Use DEFINE_IDTENTRY_IST_ETNRY_ERRORCODE to emit C entry function and use the function directly in entry_64.S.

---
 arch/x86/entry/entry_64.S       | 12 ++----------
 arch/x86/include/asm/idtentry.h |  1 +
 2 files changed, 3 insertions(+), 10 deletions(-)
arch/x86/entry/entry_64.S +2 -10
index 0a1a55c8207e..57559d810785 100644
@@ -575,16 +575,8 @@ SYM_CODE_START(\asmsym)
 	PUSH_AND_CLEAR_REGS
 	ENCODE_FRAME_POINTER
 
-	/* paranoid_entry returns GS information for paranoid_exit in EBX. */
-	call	paranoid_entry
-	UNWIND_HINT_REGS
-
-	movq	%rsp, %rdi		/* pt_regs pointer into first argument */
-	movq	ORIG_RAX(%rsp), %rsi	/* get error code into 2nd argument*/
-	movq	$-1, ORIG_RAX(%rsp)	/* no syscall to restart */
-	call	\cfunc
-
-	call	paranoid_exit
+	movq	%rsp, %rdi		/* pt_regs pointer */
+	call	ist_\cfunc
 	jmp	restore_regs_and_return_to_kernel
 
 _ASM_NOKPROBE(\asmsym)
arch/x86/include/asm/idtentry.h +1 -0
index c57606948433..931b689f464c 100644
@@ -415,6 +415,7 @@ __visible __entry_text void ist_##func(struct pt_regs *regs)		\
  * Maps to DEFINE_IDTENTRY_RAW_ERRORCODE
  */
 #define DEFINE_IDTENTRY_DF(func)					\
+	DEFINE_IDTENTRY_IST_ETNRY_ERRORCODE(func)			\
 	DEFINE_IDTENTRY_RAW_ERRORCODE(func)
 
 /**
Signature · 1 line
2.19.1.6.gb485710b
#50 lore raw

PATCH v3 44/49 x86/sev: Add and use ist_vc_switch_off_ist()

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

ist_vc_switch_off_ist() is the same as vc_switch_off_ist(), but it is called without CR3 or gsbase fixed. It has to call ist_paranoid_entry() by its own.

It is prepared for using C code for the other part of identry_vc and remove ASM paranoid_entry() and paranoid_exit().

---
 arch/x86/entry/entry_64.S    | 20 ++++++++++----------
 arch/x86/include/asm/traps.h |  3 ++-
 arch/x86/kernel/traps.c      | 14 +++++++++++++-
 3 files changed, 25 insertions(+), 12 deletions(-)
arch/x86/entry/entry_64.S +10 -10
index 57559d810785..58f33e86c6c8 100644
@@ -516,26 +516,26 @@ SYM_CODE_START(\asmsym)
 	testb	$3, CS(%rsp)
 	jnz	.Lfrom_usermode_switch_stack_\@
 
-	/*
-	 * paranoid_entry returns SWAPGS flag for paranoid_exit in EBX.
-	 * EBX == 0 -> SWAPGS, EBX == 1 -> no SWAPGS
-	 */
-	call	paranoid_entry
-
-	UNWIND_HINT_REGS
-
 	/*
 	 * Switch off the IST stack to make it free for nested exceptions. The
-	 * vc_switch_off_ist() function will switch back to the interrupted
+	 * ist_vc_switch_off_ist() function will switch back to the interrupted
 	 * stack if it is safe to do so. If not it switches to the VC fall-back
 	 * stack.
 	 */
 	movq	%rsp, %rdi		/* pt_regs pointer */
-	call	vc_switch_off_ist
+	call	ist_vc_switch_off_ist
 	movq	%rax, %rsp		/* Switch to new stack */
 
 	UNWIND_HINT_REGS
 
+	/*
+	 * paranoid_entry returns SWAPGS flag for paranoid_exit in EBX.
+	 * EBX == 0 -> SWAPGS, EBX == 1 -> no SWAPGS
+	 */
+	call	paranoid_entry
+
+	UNWIND_HINT_REGS
+
 	/* Update pt_regs */
 	movq	ORIG_RAX(%rsp), %rsi	/* get error code into 2nd argument*/
 	movq	$-1, ORIG_RAX(%rsp)	/* no syscall to restart */
arch/x86/include/asm/traps.h +2 -1
index 686461ac9803..1aefc081d763 100644
@@ -16,7 +16,8 @@ asmlinkage __visible notrace
 struct pt_regs *fixup_bad_iret(struct pt_regs *bad_regs);
 asmlinkage __visible notrace struct pt_regs *error_entry(struct pt_regs *eregs);
 void __init trap_init(void);
-asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *eregs);
+asmlinkage __visible __entry_text
+struct pt_regs *ist_vc_switch_off_ist(struct pt_regs *eregs);
 #endif
 
 #ifdef CONFIG_X86_F00F_BUG
arch/x86/kernel/traps.c +13 -1
index 0afa16ea3702..03347db4c2c4 100644
@@ -717,7 +717,7 @@ asmlinkage __visible noinstr struct pt_regs *sync_regs(struct pt_regs *eregs)
 }
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
-asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *regs)
+static noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *regs)
 {
 	unsigned long sp, *stack;
 	struct stack_info info;
@@ -757,6 +757,18 @@ asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *r
 
 	return regs_ret;
 }
+
+asmlinkage __visible __entry_text
+struct pt_regs *ist_vc_switch_off_ist(struct pt_regs *regs)
+{
+	unsigned long cr3, gsbase;
+
+	ist_paranoid_entry(&cr3, &gsbase);
+	regs = vc_switch_off_ist(regs);
+	ist_paranoid_exit(cr3, gsbase);
+
+	return regs;
+}
 #endif
 
 asmlinkage __visible noinstr
Signature · 1 line
2.19.1.6.gb485710b
#51 lore raw

PATCH v3 45/49 x86/sev: Use C entry code

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

Use DEFINE_IDTENTRY_IST_ETNRY_ERRORCODE to emit C entry function and use the function directly in entry_64.S.

---
 arch/x86/entry/entry_64.S       | 22 +---------------------
 arch/x86/include/asm/idtentry.h |  1 +
 arch/x86/kernel/Makefile        |  1 +
 3 files changed, 3 insertions(+), 21 deletions(-)
arch/x86/entry/entry_64.S +1 -21
index 58f33e86c6c8..48b4c320f5e7 100644
@@ -528,28 +528,8 @@ SYM_CODE_START(\asmsym)
 
 	UNWIND_HINT_REGS
 
-	/*
-	 * paranoid_entry returns SWAPGS flag for paranoid_exit in EBX.
-	 * EBX == 0 -> SWAPGS, EBX == 1 -> no SWAPGS
-	 */
-	call	paranoid_entry
-
-	UNWIND_HINT_REGS
-
-	/* Update pt_regs */
-	movq	ORIG_RAX(%rsp), %rsi	/* get error code into 2nd argument*/
-	movq	$-1, ORIG_RAX(%rsp)	/* no syscall to restart */
-
 	movq	%rsp, %rdi		/* pt_regs pointer */
-
-	call	kernel_\cfunc
-
-	/*
-	 * No need to switch back to the IST stack. The current stack is either
-	 * identical to the stack in the IRET frame or the VC fall-back stack,
-	 * so it is definitely mapped even with PTI enabled.
-	 */
-	call	paranoid_exit
+	call	ist_kernel_\cfunc
 	jmp	restore_regs_and_return_to_kernel
 
 	/* Switch to the regular task stack */
arch/x86/include/asm/idtentry.h +1 -0
index 931b689f464c..84ce63f03c7f 100644
@@ -426,6 +426,7 @@ __visible __entry_text void ist_##func(struct pt_regs *regs)		\
  * Maps to DEFINE_IDTENTRY_RAW_ERRORCODE
  */
 #define DEFINE_IDTENTRY_VC_KERNEL(func)				\
+	DEFINE_IDTENTRY_IST_ETNRY_ERRORCODE(kernel_##func)	\
 	DEFINE_IDTENTRY_RAW_ERRORCODE(kernel_##func)
 
 /**
arch/x86/kernel/Makefile +1 -0
index 28815c2e6cb2..9535d03aaa61 100644
@@ -52,6 +52,7 @@ CFLAGS_head$(BITS).o	+= -fno-stack-protector
 CFLAGS_cc_platform.o	+= -fno-stack-protector
 CFLAGS_traps.o		+= -fno-stack-protector
 CFLAGS_nmi.o		+= -fno-stack-protector
+CFLAGS_sev.o		+= -fno-stack-protector
 
 CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace
 
Signature · 1 line
2.19.1.6.gb485710b
#52 lore raw

PATCH v3 46/49 x86/entry: Remove ASM function paranoid_entry() and paranoid_exit()

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

IST exceptions are changed to use C entry code which uses the C function ist_paranoid_entry() and ist_paranoid_exit(). The ASM function paranoid_entry() and paranoid_exit() are useless.

---
 arch/x86/entry/entry_64.S | 129 --------------------------------------
 1 file changed, 129 deletions(-)
arch/x86/entry/entry_64.S +0 -129
index 48b4c320f5e7..19f3e642707b 100644
@@ -847,135 +847,6 @@ SYM_CODE_START(xen_failsafe_callback)
 SYM_CODE_END(xen_failsafe_callback)
 #endif /* CONFIG_XEN_PV */
 
-/*
- * Save all registers in pt_regs. Return GSBASE related information
- * in EBX depending on the availability of the FSGSBASE instructions:
- *
- * FSGSBASE	R/EBX
- *     N        0 -> SWAPGS on exit
- *              1 -> no SWAPGS on exit
- *
- *     Y        GSBASE value at entry, must be restored in paranoid_exit
- */
-SYM_CODE_START_LOCAL(paranoid_entry)
-	UNWIND_HINT_FUNC
-
-	/*
-	 * Always stash CR3 in %r14.  This value will be restored,
-	 * verbatim, at exit.  Needed if paranoid_entry interrupted
-	 * another entry that already switched to the user CR3 value
-	 * but has not yet returned to userspace.
-	 *
-	 * This is also why CS (stashed in the "iret frame" by the
-	 * hardware at entry) can not be used: this may be a return
-	 * to kernel code, but with a user CR3 value.
-	 *
-	 * Switching CR3 does not depend on kernel GSBASE so it can
-	 * be done before switching to the kernel GSBASE. This is
-	 * required for FSGSBASE because the kernel GSBASE has to
-	 * be retrieved from a kernel internal table.
-	 */
-	SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14
-
-	/*
-	 * Handling GSBASE depends on the availability of FSGSBASE.
-	 *
-	 * Without FSGSBASE the kernel enforces that negative GSBASE
-	 * values indicate kernel GSBASE. With FSGSBASE no assumptions
-	 * can be made about the GSBASE value when entering from user
-	 * space.
-	 */
-	ALTERNATIVE "jmp .Lparanoid_entry_checkgs", "", X86_FEATURE_FSGSBASE
-
-	/*
-	 * Read the current GSBASE and store it in %rbx unconditionally,
-	 * retrieve and set the current CPUs kernel GSBASE. The stored value
-	 * has to be restored in paranoid_exit unconditionally.
-	 *
-	 * The unconditional write to GS base below ensures that no subsequent
-	 * loads based on a mispredicted GS base can happen, therefore no LFENCE
-	 * is needed here.
-	 */
-	SAVE_AND_SET_GSBASE scratch_reg=%rax save_reg=%rbx
-	ret
-
-.Lparanoid_entry_checkgs:
-	/* EBX = 1 -> kernel GSBASE active, no restore required */
-	movl	$1, %ebx
-	/*
-	 * The kernel-enforced convention is a negative GSBASE indicates
-	 * a kernel value. No SWAPGS needed on entry and exit.
-	 */
-	movl	$MSR_GS_BASE, %ecx
-	rdmsr
-	testl	%edx, %edx
-	jns	.Lparanoid_entry_swapgs
-	FENCE_SWAPGS_KERNEL_ENTRY
-	ret
-
-.Lparanoid_entry_swapgs:
-	swapgs
-
-	/*
-	 * The above SAVE_AND_SWITCH_TO_KERNEL_CR3 macro doesn't do an
-	 * unconditional CR3 write, even in the PTI case.  So do an lfence
-	 * to prevent GS speculation, regardless of whether PTI is enabled.
-	 */
-	FENCE_SWAPGS_KERNEL_ENTRY
-
-	/* EBX = 0 -> SWAPGS required on exit */
-	xorl	%ebx, %ebx
-	ret
-SYM_CODE_END(paranoid_entry)
-
-/*
- * "Paranoid" exit path from exception stack.  This is invoked
- * only on return from IST interrupts that came from kernel space.
- *
- * We may be returning to very strange contexts (e.g. very early
- * in syscall entry), so checking for preemption here would
- * be complicated.  Fortunately, there's no good reason to try
- * to handle preemption here.
- *
- * R/EBX contains the GSBASE related information depending on the
- * availability of the FSGSBASE instructions:
- *
- * FSGSBASE	R/EBX
- *     N        0 -> SWAPGS on exit
- *              1 -> no SWAPGS on exit
- *
- *     Y        User space GSBASE, must be restored unconditionally
- */
-SYM_CODE_START_LOCAL(paranoid_exit)
-	UNWIND_HINT_REGS offset=8
-	/*
-	 * The order of operations is important. RESTORE_CR3 requires
-	 * kernel GSBASE.
-	 *
-	 * NB to anyone to try to optimize this code: this code does
-	 * not execute at all for exceptions from user mode. Those
-	 * exceptions go through error_exit instead.
-	 */
-	RESTORE_CR3	scratch_reg=%rax save_reg=%r14
-
-	/* Handle the three GSBASE cases */
-	ALTERNATIVE "jmp .Lparanoid_exit_checkgs", "", X86_FEATURE_FSGSBASE
-
-	/* With FSGSBASE enabled, unconditionally restore GSBASE */
-	wrgsbase	%rbx
-	ret
-
-.Lparanoid_exit_checkgs:
-	/* On non-FSGSBASE systems, conditionally do SWAPGS */
-	testl		%ebx, %ebx
-	jnz		.Lparanoid_exit_done
-
-	/* We are returning to a context with user GSBASE */
-	swapgs
-.Lparanoid_exit_done:
-	ret
-SYM_CODE_END(paranoid_exit)
-
 SYM_CODE_START_LOCAL(error_return)
 	UNWIND_HINT_REGS
 	DEBUG_ENTRY_ASSERT_IRQS_OFF
Signature · 1 line
2.19.1.6.gb485710b
#53 lore raw

PATCH v3 47/49 x86/entry: Remove the unused ASM macros

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

They are implemented and used in C code. The ASM version is not needed any more.

---
 arch/x86/entry/calling.h | 106 ---------------------------------------
 1 file changed, 106 deletions(-)
arch/x86/entry/calling.h +0 -106
index 996b041e92d2..d42012fc694d 100644
@@ -210,60 +210,6 @@ For 32-bit we have the following conventions - kernel is built with
 	popq	%rax
 .endm
 
-.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
-	ALTERNATIVE "jmp .Ldone_\@", "", X86_FEATURE_PTI
-	movq	%cr3, \scratch_reg
-	movq	\scratch_reg, \save_reg
-	/*
-	 * Test the user pagetable bit. If set, then the user page tables
-	 * are active. If clear CR3 already has the kernel page table
-	 * active.
-	 */
-	bt	$PTI_USER_PGTABLE_BIT, \scratch_reg
-	jnc	.Ldone_\@
-
-	ADJUST_KERNEL_CR3 \scratch_reg
-	movq	\scratch_reg, %cr3
-
-.Ldone_\@:
-.endm
-
-.macro RESTORE_CR3 scratch_reg:req save_reg:req
-	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
-
-	ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
-
-	/*
-	 * KERNEL pages can always resume with NOFLUSH as we do
-	 * explicit flushes.
-	 */
-	bt	$PTI_USER_PGTABLE_BIT, \save_reg
-	jnc	.Lnoflush_\@
-
-	/*
-	 * Check if there's a pending flush for the user ASID we're
-	 * about to set.
-	 */
-	movq	\save_reg, \scratch_reg
-	andq	$(0x7FF), \scratch_reg
-	bt	\scratch_reg, THIS_CPU_user_pcid_flush_mask
-	jnc	.Lnoflush_\@
-
-	btr	\scratch_reg, THIS_CPU_user_pcid_flush_mask
-	jmp	.Lwrcr3_\@
-
-.Lnoflush_\@:
-	SET_NOFLUSH_BIT \save_reg
-
-.Lwrcr3_\@:
-	/*
-	 * 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
-.Lend_\@:
-.endm
-
 #else /* CONFIG_PAGE_TABLE_ISOLATION=n: */
 
 .macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
@@ -272,10 +218,6 @@ For 32-bit we have the following conventions - kernel is built with
 .endm
 .macro SWITCH_TO_USER_CR3_STACK scratch_reg:req
 .endm
-.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
-.endm
-.macro RESTORE_CR3 scratch_reg:req save_reg:req
-.endm
 
 #endif
 
@@ -284,17 +226,10 @@ For 32-bit we have the following conventions - kernel is built with
  *
  * FENCE_SWAPGS_USER_ENTRY is used in the user entry swapgs code path, to
  * prevent a speculative swapgs when coming from kernel space.
- *
- * FENCE_SWAPGS_KERNEL_ENTRY is used in the kernel entry non-swapgs code path,
- * to prevent the swapgs from getting speculatively skipped when coming from
- * user space.
  */
 .macro FENCE_SWAPGS_USER_ENTRY
 	ALTERNATIVE "", "lfence", X86_FEATURE_FENCE_SWAPGS_USER
 .endm
-.macro FENCE_SWAPGS_KERNEL_ENTRY
-	ALTERNATIVE "", "lfence", X86_FEATURE_FENCE_SWAPGS_KERNEL
-.endm
 
 .macro STACKLEAK_ERASE_NOCLOBBER
 #ifdef CONFIG_GCC_PLUGIN_STACKLEAK
@@ -304,12 +239,6 @@ For 32-bit we have the following conventions - kernel is built with
 #endif
 .endm
 
-.macro SAVE_AND_SET_GSBASE scratch_reg:req save_reg:req
-	rdgsbase \save_reg
-	GET_PERCPU_BASE \scratch_reg
-	wrgsbase \scratch_reg
-.endm
-
 #else /* CONFIG_X86_64 */
 # undef		UNWIND_HINT_IRET_REGS
 # define	UNWIND_HINT_IRET_REGS
@@ -320,38 +249,3 @@ For 32-bit we have the following conventions - kernel is built with
 	call stackleak_erase
 #endif
 .endm
-
-#ifdef CONFIG_SMP
-
-/*
- * CPU/node NR is loaded from the limit (size) field of a special segment
- * descriptor entry in GDT.
- */
-.macro LOAD_CPU_AND_NODE_SEG_LIMIT reg:req
-	movq	$__CPUNODE_SEG, \reg
-	lsl	\reg, \reg
-.endm
-
-/*
- * Fetch the per-CPU GSBASE value for this processor and put it in @reg.
- * We normally use %gs for accessing per-CPU data, but we are setting up
- * %gs here and obviously can not use %gs itself to access per-CPU data.
- *
- * Do not use RDPID, because KVM loads guest's TSC_AUX on vm-entry and
- * may not restore the host's value until the CPU returns to userspace.
- * Thus the kernel would consume a guest's TSC_AUX if an NMI arrives
- * while running KVM's run loop.
- */
-.macro GET_PERCPU_BASE reg:req
-	LOAD_CPU_AND_NODE_SEG_LIMIT \reg
-	andq	$VDSO_CPUNODE_MASK, \reg
-	movq	__per_cpu_offset(, \reg, 8), \reg
-.endm
-
-#else
-
-.macro GET_PERCPU_BASE reg:req
-	movq	pcpu_unit_offsets(%rip), \reg
-.endm
-
-#endif /* CONFIG_SMP */
Signature · 1 line
2.19.1.6.gb485710b
#54 lore raw

PATCH v3 48/49 x86/entry: Remove save_ret from PUSH_AND_CLEAR_REGS

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

PUSH_AND_CLEAR_REGS is never used with save_ret anymore.

---
 arch/x86/entry/calling.h | 16 +++-------------
 1 file changed, 3 insertions(+), 13 deletions(-)
arch/x86/entry/calling.h +3 -13
index d42012fc694d..6f9de1c6da73 100644
@@ -63,15 +63,9 @@ For 32-bit we have the following conventions - kernel is built with
  * for assembly code:
  */
 
-.macro PUSH_REGS rdx=%rdx rax=%rax save_ret=0
-	.if \save_ret
-	pushq	%rsi		/* pt_regs->si */
-	movq	8(%rsp), %rsi	/* temporarily store the return address in %rsi */
-	movq	%rdi, 8(%rsp)	/* pt_regs->di (overwriting original return address) */
-	.else
+.macro PUSH_REGS rdx=%rdx rax=%rax
 	pushq   %rdi		/* pt_regs->di */
 	pushq   %rsi		/* pt_regs->si */
-	.endif
 	pushq	\rdx		/* pt_regs->dx */
 	pushq   %rcx		/* pt_regs->cx */
 	pushq   \rax		/* pt_regs->ax */
@@ -86,10 +80,6 @@ For 32-bit we have the following conventions - kernel is built with
 	pushq	%r14		/* pt_regs->r14 */
 	pushq	%r15		/* pt_regs->r15 */
 	UNWIND_HINT_REGS
-
-	.if \save_ret
-	pushq	%rsi		/* return address on top of stack */
-	.endif
 .endm
 
 .macro CLEAR_REGS
@@ -114,8 +104,8 @@ For 32-bit we have the following conventions - kernel is built with
 
 .endm
 
-.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0
-	PUSH_REGS rdx=\rdx, rax=\rax, save_ret=\save_ret
+.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax
+	PUSH_REGS rdx=\rdx, rax=\rax
 	CLEAR_REGS
 .endm
 
Signature · 1 line
2.19.1.6.gb485710b
#55 lore raw

PATCH v3 49/49 x86/syscall/64: Move the checking for sysret to C code

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

Like do_fast_syscall_32() which checks whether it can return to userspace via fast instructions before the function returns, do_syscall_64() also checks whether it can use sysret to return to userspace before do_syscall_64() returns via C code. And a bunch of ASM code can be removed.

No functional change intended.

---
 arch/x86/entry/calling.h       | 10 +----
 arch/x86/entry/common.c        | 73 ++++++++++++++++++++++++++++++-
 arch/x86/entry/entry_64.S      | 78 ++--------------------------------
 arch/x86/include/asm/syscall.h |  2 +-
 4 files changed, 78 insertions(+), 85 deletions(-)
arch/x86/entry/calling.h +1 -9
index 6f9de1c6da73..05da3ef48ee4 100644
@@ -109,27 +109,19 @@ For 32-bit we have the following conventions - kernel is built with
 	CLEAR_REGS
 .endm
 
-.macro POP_REGS pop_rdi=1 skip_r11rcx=0
+.macro POP_REGS pop_rdi=1
 	popq %r15
 	popq %r14
 	popq %r13
 	popq %r12
 	popq %rbp
 	popq %rbx
-	.if \skip_r11rcx
-	popq %rsi
-	.else
 	popq %r11
-	.endif
 	popq %r10
 	popq %r9
 	popq %r8
 	popq %rax
-	.if \skip_r11rcx
-	popq %rsi
-	.else
 	popq %rcx
-	.endif
 	popq %rdx
 	popq %rsi
 	.if \pop_rdi
arch/x86/entry/common.c +72 -1

85 lines not on this page · raw message

arch/x86/entry/entry_64.S +4 -74

89 lines not on this page · raw message

arch/x86/include/asm/syscall.h +1 -1
index f7e2d82d24fb..477adea7bac0 100644
@@ -159,7 +159,7 @@ static inline int syscall_get_arch(struct task_struct *task)
 		? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
 }
 
-void do_syscall_64(struct pt_regs *regs, int nr);
+int do_syscall_64(struct pt_regs *regs, int nr);
 void do_int80_syscall_32(struct pt_regs *regs);
 long do_fast_syscall_32(struct pt_regs *regs);
 
Signature · 1 line
2.19.1.6.gb485710b