| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <tip-45d7b255747c21fc4b1f5043bee0754d39c3bdbf@git.kernel.org>
Date: Thu, 19 Jul 2018 16:22:01 -0700
From: tip-bot for Joerg Roedel <tipbot@...or.com>
To: linux-tip-commits@...r.kernel.org
Cc: dave.hansen@...el.com, brgerst@...il.com, bp@...en8.de,
gregkh@...uxfoundation.org, torvalds@...ux-foundation.org,
pavel@....cz, jpoimboe@...hat.com, jkosina@...e.cz,
will.deacon@....com, dhgutteridge@...patico.ca, luto@...nel.org,
eduval@...zon.com, llong@...hat.com, peterz@...radead.org,
boris.ostrovsky@...cle.com, linux-kernel@...r.kernel.org,
David.Laight@...lab.com, hpa@...or.com, tglx@...utronix.de,
jroedel@...e.de, jgross@...e.com, aarcange@...hat.com,
mingo@...nel.org, dvlasenk@...hat.com
Subject: [tip:x86/pti] x86/entry/32: Enter the kernel via trampoline stack
Commit-ID: 45d7b255747c21fc4b1f5043bee0754d39c3bdbf
Gitweb: https://git.kernel.org/tip/45d7b255747c21fc4b1f5043bee0754d39c3bdbf
Author: Joerg Roedel <jroedel@...e.de>
AuthorDate: Wed, 18 Jul 2018 11:40:44 +0200
Committer: Thomas Gleixner <tglx@...utronix.de>
CommitDate: Fri, 20 Jul 2018 01:11:37 +0200
x86/entry/32: Enter the kernel via trampoline stack
Use the entry-stack as a trampoline to enter the kernel. The entry-stack is
already in the cpu_entry_area and will be mapped to userspace when PTI is
enabled.
Signed-off-by: Joerg Roedel <jroedel@...e.de>
Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
Tested-by: Pavel Machek <pavel@....cz>
Cc: "H . Peter Anvin" <hpa@...or.com>
Cc: linux-mm@...ck.org
Cc: Linus Torvalds <torvalds@...ux-foundation.org>
Cc: Andy Lutomirski <luto@...nel.org>
Cc: Dave Hansen <dave.hansen@...el.com>
Cc: Josh Poimboeuf <jpoimboe@...hat.com>
Cc: Juergen Gross <jgross@...e.com>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Borislav Petkov <bp@...en8.de>
Cc: Jiri Kosina <jkosina@...e.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@...cle.com>
Cc: Brian Gerst <brgerst@...il.com>
Cc: David Laight <David.Laight@...lab.com>
Cc: Denys Vlasenko <dvlasenk@...hat.com>
Cc: Eduardo Valentin <eduval@...zon.com>
Cc: Greg KH <gregkh@...uxfoundation.org>
Cc: Will Deacon <will.deacon@....com>
Cc: aliguori@...zon.com
Cc: daniel.gruss@...k.tugraz.at
Cc: hughd@...gle.com
Cc: keescook@...gle.com
Cc: Andrea Arcangeli <aarcange@...hat.com>
Cc: Waiman Long <llong@...hat.com>
Cc: "David H . Gutteridge" <dhgutteridge@...patico.ca>
Cc: joro@...tes.org
Link: https://lkml.kernel.org/r/1531906876-13451-8-git-send-email-joro@8bytes.org
---
arch/x86/entry/entry_32.S | 119 ++++++++++++++++++++++++++++++++-------
arch/x86/include/asm/switch_to.h | 14 ++++-
arch/x86/kernel/asm-offsets.c | 1 +
arch/x86/kernel/cpu/common.c | 5 +-
arch/x86/kernel/process.c | 2 -
arch/x86/kernel/process_32.c | 2 -
6 files changed, 115 insertions(+), 28 deletions(-)
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 7251c4f3e99e..fea49ec345ba 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -154,7 +154,7 @@
#endif /* CONFIG_X86_32_LAZY_GS */
-.macro SAVE_ALL pt_regs_ax=%eax
+.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0
cld
PUSH_GS
pushl %fs
@@ -173,6 +173,12 @@
movl $(__KERNEL_PERCPU), %edx
movl %edx, %fs
SET_KERNEL_GS %edx
+
+ /* Switch to kernel stack if necessary */
+.if \switch_stacks > 0
+ SWITCH_TO_KERNEL_STACK
+.endif
+
.endm
/*
@@ -269,6 +275,73 @@
.Lend_\@:
#endif /* CONFIG_X86_ESPFIX32 */
.endm
+
+
+/*
+ * Called with pt_regs fully populated and kernel segments loaded,
+ * so we can access PER_CPU and use the integer registers.
+ *
+ * We need to be very careful here with the %esp switch, because an NMI
+ * can happen everywhere. If the NMI handler finds itself on the
+ * entry-stack, it will overwrite the task-stack and everything we
+ * copied there. So allocate the stack-frame on the task-stack and
+ * switch to it before we do any copying.
+ */
+.macro SWITCH_TO_KERNEL_STACK
+
+ ALTERNATIVE "", "jmp .Lend_\@", X86_FEATURE_XENPV
+
+ /* Are we on the entry stack? Bail out if not! */
+ movl PER_CPU_VAR(cpu_entry_area), %ecx
+ addl $CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
+ subl %esp, %ecx /* ecx = (end of entry_stack) - esp */
+ cmpl $SIZEOF_entry_stack, %ecx
+ jae .Lend_\@
+
+ /* Load stack pointer into %esi and %edi */
+ movl %esp, %esi
+ movl %esi, %edi
+
+ /* Move %edi to the top of the entry stack */
+ andl $(MASK_entry_stack), %edi
+ addl $(SIZEOF_entry_stack), %edi
+
+ /* Load top of task-stack into %edi */
+ movl TSS_entry2task_stack(%edi), %edi
+
+ /* Bytes to copy */
+ movl $PTREGS_SIZE, %ecx
+
+#ifdef CONFIG_VM86
+ testl $X86_EFLAGS_VM, PT_EFLAGS(%esi)
+ jz .Lcopy_pt_regs_\@
+
+ /*
+ * Stack-frame contains 4 additional segment registers when
+ * coming from VM86 mode
+ */
+ addl $(4 * 4), %ecx
+
+.Lcopy_pt_regs_\@:
+#endif
+
+ /* Allocate frame on task-stack */
+ subl %ecx, %edi
+
+ /* Switch to task-stack */
+ movl %edi, %esp
+
+ /*
+ * We are now on the task-stack and can safely copy over the
+ * stack-frame
+ */
+ shrl $2, %ecx
+ cld
+ rep movsl
+
+.Lend_\@:
+.endm
+
/*
* %eax: prev task
* %edx: next task
@@ -469,7 +542,7 @@ ENTRY(entry_SYSENTER_32)
pushl $__USER_CS /* pt_regs->cs */
pushl $0 /* pt_regs->ip = 0 (placeholder) */
pushl %eax /* pt_regs->orig_ax */
- SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest */
+ SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest, stack already switched */
/*
* SYSENTER doesn't filter flags, so we need to clear NT, AC
@@ -580,7 +653,8 @@ ENDPROC(entry_SYSENTER_32)
ENTRY(entry_INT80_32)
ASM_CLAC
pushl %eax /* pt_regs->orig_ax */
- SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest */
+
+ SAVE_ALL pt_regs_ax=$-ENOSYS switch_stacks=1 /* save rest */
/*
* User mode is traced as though IRQs are on, and the interrupt gate
@@ -677,7 +751,8 @@ END(irq_entries_start)
common_interrupt:
ASM_CLAC
addl $-0x80, (%esp) /* Adjust vector into the [-256, -1] range */
- SAVE_ALL
+
+ SAVE_ALL switch_stacks=1
ENCODE_FRAME_POINTER
TRACE_IRQS_OFF
movl %esp, %eax
@@ -685,16 +760,16 @@ common_interrupt:
jmp ret_from_intr
ENDPROC(common_interrupt)
-#define BUILD_INTERRUPT3(name, nr, fn) \
-ENTRY(name) \
- ASM_CLAC; \
- pushl $~(nr); \
- SAVE_ALL; \
- ENCODE_FRAME_POINTER; \
- TRACE_IRQS_OFF \
- movl %esp, %eax; \
- call fn; \
- jmp ret_from_intr; \
+#define BUILD_INTERRUPT3(name, nr, fn) \
+ENTRY(name) \
+ ASM_CLAC; \
+ pushl $~(nr); \
+ SAVE_ALL switch_stacks=1; \
+ ENCODE_FRAME_POINTER; \
+ TRACE_IRQS_OFF \
+ movl %esp, %eax; \
+ call fn; \
+ jmp ret_from_intr; \
ENDPROC(name)
#define BUILD_INTERRUPT(name, nr) \
@@ -926,16 +1001,20 @@ common_exception:
pushl %es
pushl %ds
pushl %eax
+ movl $(__USER_DS), %eax
+ movl %eax, %ds
+ movl %eax, %es
+ movl $(__KERNEL_PERCPU), %eax
+ movl %eax, %fs
pushl %ebp
pushl %edi
pushl %esi
pushl %edx
pushl %ecx
pushl %ebx
+ SWITCH_TO_KERNEL_STACK
ENCODE_FRAME_POINTER
cld
- movl $(__KERNEL_PERCPU), %ecx
- movl %ecx, %fs
UNWIND_ESPFIX_STACK
GS_TO_REG %ecx
movl PT_GS(%esp), %edi # get the function address
@@ -943,9 +1022,6 @@ common_exception:
movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart
REG_TO_PTGS %ecx
SET_KERNEL_GS %ecx
- movl $(__USER_DS), %ecx
- movl %ecx, %ds
- movl %ecx, %es
TRACE_IRQS_OFF
movl %esp, %eax # pt_regs pointer
CALL_NOSPEC %edi
@@ -964,6 +1040,7 @@ ENTRY(debug)
*/
ASM_CLAC
pushl $-1 # mark this as an int
+
SAVE_ALL
ENCODE_FRAME_POINTER
xorl %edx, %edx # error code 0
@@ -999,6 +1076,7 @@ END(debug)
*/
ENTRY(nmi)
ASM_CLAC
+
#ifdef CONFIG_X86_ESPFIX32
pushl %eax
movl %ss, %eax
@@ -1066,7 +1144,8 @@ END(nmi)
ENTRY(int3)
ASM_CLAC
pushl $-1 # mark this as an int
- SAVE_ALL
+
+ SAVE_ALL switch_stacks=1
ENCODE_FRAME_POINTER
TRACE_IRQS_OFF
xorl %edx, %edx # zero error code
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index eb5f7999a893..8bc2f70b452e 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -89,13 +89,23 @@ static inline void refresh_sysenter_cs(struct thread_struct *thread)
/* This is used when switching tasks or entering/exiting vm86 mode. */
static inline void update_sp0(struct task_struct *task)
{
- /* On x86_64, sp0 always points to the entry trampoline stack, which is constant: */
+ /* sp0 always points to the entry trampoline stack, which is constant: */
#ifdef CONFIG_X86_32
- load_sp0(task->thread.sp0);
+ if (static_cpu_has(X86_FEATURE_XENPV))
+ load_sp0(task->thread.sp0);
+ else
+ this_cpu_write(cpu_tss_rw.x86_tss.sp1, task->thread.sp0);
#else
+ /*
+ * x86-64 updates x86_tss.sp1 via cpu_current_top_of_stack. That
+ * doesn't work on x86-32 because sp1 and
+ * cpu_current_top_of_stack have different values (because of
+ * the non-zero stack-padding on 32bit).
+ */
if (static_cpu_has(X86_FEATURE_XENPV))
load_sp0(task_top_of_stack(task));
#endif
+
}
#endif /* _ASM_X86_SWITCH_TO_H */
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index a1e16286a832..01de31db300d 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -103,6 +103,7 @@ void common(void) {
OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline);
OFFSET(CPU_ENTRY_AREA_entry_stack, cpu_entry_area, entry_stack_page);
DEFINE(SIZEOF_entry_stack, sizeof(struct entry_stack));
+ DEFINE(MASK_entry_stack, (~(sizeof(struct entry_stack) - 1)));
/* Offset for sp0 and sp1 into the tss_struct */
OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index eb4cb3efd20e..43a927eb9c09 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1804,11 +1804,12 @@ void cpu_init(void)
enter_lazy_tlb(&init_mm, curr);
/*
- * Initialize the TSS. Don't bother initializing sp0, as the initial
- * task never enters user mode.
+ * Initialize the TSS. sp0 points to the entry trampoline stack
+ * regardless of what task is running.
*/
set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
load_TR_desc();
+ load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1));
load_mm_ldt(&init_mm);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 30ca2d1a9231..c93fcfdf1673 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -57,14 +57,12 @@ __visible DEFINE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw) = {
*/
.sp0 = (1UL << (BITS_PER_LONG-1)) + 1,
-#ifdef CONFIG_X86_64
/*
* .sp1 is cpu_current_top_of_stack. The init task never
* runs user code, but cpu_current_top_of_stack should still
* be well defined before the first context switch.
*/
.sp1 = TOP_OF_INIT_STACK,
-#endif
#ifdef CONFIG_X86_32
.ss0 = __KERNEL_DS,
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index ec62cc77388d..0ae659de21eb 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -290,8 +290,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
this_cpu_write(cpu_current_top_of_stack,
(unsigned long)task_stack_page(next_p) +
THREAD_SIZE);
- /* SYSENTER reads the task-stack from tss.sp1 */
- this_cpu_write(cpu_tss_rw.x86_tss.sp1, next_p->thread.sp0);
/*
* Restore %gs if needed (which is common)
Powered by blists - more mailing lists