[PATCH v4 47/75] x86/entry/64: Add entry code for #VC handler

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



From: Joerg Roedel <jroedel@xxxxxxx>

The #VC handler needs special entry code because:

	1. It runs on an IST stack

	2. It needs to be able to handle nested #VC exceptions

To make this work the entry code is implemented to pretend it doesn't
use an IST stack. When entered from user-mode or early SYSCALL entry
path it switches to the task stack, if entered from kernel-mode it
tries to switch back to the previous stack in the IRET frame.

The stack found in the IRET frame is validated first, and if it is not
safe to use it for the #VC handler, the code will switch to a
fall-back stack (the #VC2 IST stack). From there it can cause nested
exceptions again.

Signed-off-by: Joerg Roedel <jroedel@xxxxxxx>
---
 arch/x86/entry/entry_64.S       | 78 +++++++++++++++++++++++++++++++++
 arch/x86/include/asm/idtentry.h | 44 +++++++++++++++++++
 arch/x86/include/asm/proto.h    |  1 +
 arch/x86/include/asm/traps.h    |  1 +
 arch/x86/kernel/traps.c         | 51 +++++++++++++++++++++
 5 files changed, 175 insertions(+)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index d2a00c97e53f..4168d9cd95c0 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -100,6 +100,8 @@ SYM_CODE_START(entry_SYSCALL_64)
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
+SYM_INNER_LABEL(entry_SYSCALL_64_safe_stack, SYM_L_GLOBAL)
+
 	/* Construct struct pt_regs on stack */
 	pushq	$__USER_DS				/* pt_regs->ss */
 	pushq	PER_CPU_VAR(cpu_tss_rw + TSS_sp2)	/* pt_regs->sp */
@@ -448,6 +450,82 @@ _ASM_NOKPROBE(\asmsym)
 SYM_CODE_END(\asmsym)
 .endm
 
+/**
+ * idtentry_vc - Macro to generate entry stub for #VC
+ * @vector:		Vector number
+ * @asmsym:		ASM symbol for the entry point
+ * @cfunc:		C function to be called
+ *
+ * The macro emits code to set up the kernel context for #VC. The #VC handler
+ * runs on an IST stack and needs to be able to cause nested #VC exceptions.
+ *
+ * To make this work the #VC entry code tries its best to pretend it doesn't use
+ * an IST stack by switching to the task stack if coming from user-space (which
+ * includes early SYSCALL entry path) or back to the stack in the IRET frame if
+ * entered from kernel-mode.
+ *
+ * If entered from kernel-mode the return stack is validated first, and if it is
+ * not safe to use (e.g. because it points to the entry stack) the #VC handler
+ * will switch to a fall-back stack (VC2) and call a special handler function.
+ *
+ * The macro is only used for one vector, but it is planned to extend it in the
+ * future for the #HV exception.
+ */
+.macro idtentry_vc vector asmsym cfunc
+SYM_CODE_START(\asmsym)
+	UNWIND_HINT_IRET_REGS
+	ASM_CLAC
+
+	/*
+	 * If the entry is from userspace, switch stacks and treat it as
+	 * a normal entry.
+	 */
+	testb	$3, CS-ORIG_RAX(%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
+	 * 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
+	movq	%rax, %rsp		/* Switch to new stack */
+
+	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	\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 definitly mapped even with PTI enabled.
+	 */
+	jmp	paranoid_exit
+	
+	/* Switch to the regular task stack */
+.Lfrom_usermode_switch_stack_\@:
+	idtentry_body safe_stack_\cfunc, has_error_code=1
+
+_ASM_NOKPROBE(\asmsym)
+SYM_CODE_END(\asmsym)
+.endm
+
 /*
  * Double fault entry. Straight paranoid. No checks from which context
  * this comes because for the espfix induced #DF this would do the wrong
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index eeac6dc2adaa..c38494b2bb54 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -312,6 +312,18 @@ static __always_inline void __##func(struct pt_regs *regs)
 	DECLARE_IDTENTRY_RAW(vector, func);				\
 	__visible void noist_##func(struct pt_regs *regs)
 
+/**
+ * DECLARE_IDTENTRY_VC - Declare functions for the VC entry point
+ * @vector:	Vector number (ignored for C)
+ * @func:	Function name of the entry point
+ *
+ * Maps to DECLARE_IDTENTRY_RAW_ERRORCODE, but declares also the
+ * safe_stack C handler.
+ */
+#define DECLARE_IDTENTRY_VC(vector, func)				\
+	DECLARE_IDTENTRY_RAW_ERRORCODE(vector, func);			\
+	__visible noinstr void safe_stack_##func(struct pt_regs *regs, unsigned long error_code)
+
 /**
  * DEFINE_IDTENTRY_IST - Emit code for IST entry points
  * @func:	Function name of the entry point
@@ -351,6 +363,35 @@ static __always_inline void __##func(struct pt_regs *regs)
 #define DEFINE_IDTENTRY_DF(func)					\
 	DEFINE_IDTENTRY_RAW_ERRORCODE(func)
 
+/**
+ * DEFINE_IDTENTRY_VC_SAFE_STACK - Emit code for VMM communication handler
+				   which runs on a safe stack.
+ * @func:	Function name of the entry point
+ *
+ * Maps to DEFINE_IDTENTRY_RAW_ERRORCODE
+ */
+#define DEFINE_IDTENTRY_VC_SAFE_STACK(func)				\
+	DEFINE_IDTENTRY_RAW_ERRORCODE(safe_stack_##func)
+
+/**
+ * DEFINE_IDTENTRY_VC_IST - Emit code for VMM communication handler
+			    which runs on the VC fall-back stack
+ * @func:	Function name of the entry point
+ *
+ * Maps to DEFINE_IDTENTRY_RAW_ERRORCODE
+ */
+#define DEFINE_IDTENTRY_VC_IST(func)				\
+	DEFINE_IDTENTRY_RAW_ERRORCODE(ist_##func)
+
+/**
+ * DEFINE_IDTENTRY_VC - Emit code for VMM communication handler
+ * @func:	Function name of the entry point
+ *
+ * Maps to DEFINE_IDTENTRY_RAW_ERRORCODE
+ */
+#define DEFINE_IDTENTRY_VC(func)					\
+	DEFINE_IDTENTRY_RAW_ERRORCODE(func)
+
 #else	/* CONFIG_X86_64 */
 
 /**
@@ -437,6 +478,9 @@ __visible noinstr void func(struct pt_regs *regs,			\
 # define DECLARE_IDTENTRY_XENCB(vector, func)				\
 	DECLARE_IDTENTRY(vector, func)
 
+# define DECLARE_IDTENTRY_VC(vector, func)				\
+	idtentry_vc vector asm_##func func
+
 #else
 # define DECLARE_IDTENTRY_MCE(vector, func)				\
 	DECLARE_IDTENTRY(vector, func)
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 6e81788a30c1..40f1f0cb73d7 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -10,6 +10,7 @@ void syscall_init(void);
 
 #ifdef CONFIG_X86_64
 void entry_SYSCALL_64(void);
+void entry_SYSCALL_64_safe_stack(void);
 long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2);
 #endif
 
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 6a308355ea29..1b86bb3abc56 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -15,6 +15,7 @@ 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);
 void __init trap_init(void);
+asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *eregs);
 #endif
 
 #ifdef CONFIG_X86_F00F_BUG
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 59d17e541df9..c43b12f3f339 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -43,6 +43,7 @@
 #include <asm/stacktrace.h>
 #include <asm/processor.h>
 #include <asm/debugreg.h>
+#include <asm/realmode.h>
 #include <asm/text-patching.h>
 #include <asm/ftrace.h>
 #include <asm/traps.h>
@@ -676,6 +677,56 @@ asmlinkage __visible noinstr struct pt_regs *sync_regs(struct pt_regs *eregs)
 	return regs;
 }
 
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *eregs)
+{
+	unsigned long sp, *stack;
+	struct stack_info info;
+	struct pt_regs *regs;
+
+	/*
+	 * In the SYSCALL entry path the RSP value comes from user-space - don't
+	 * trust it and switch to the current kernel stack
+	 */
+	if (eregs->ip >= (unsigned long)entry_SYSCALL_64 &&
+	    eregs->ip <  (unsigned long)entry_SYSCALL_64_safe_stack) {
+		sp = this_cpu_read(cpu_current_top_of_stack);
+		goto sync;
+	}
+
+	/*
+	 * From here on the the RSP value is trusted - more RSP sanity checks
+	 * need to happen above.
+	 *
+	 * Check whether entry happened from a safe stack.
+	 */
+	sp    = eregs->sp;
+	stack = (unsigned long *)sp;
+	get_stack_info_noinstr(stack, current, &info);
+
+	/*
+	 * Don't sync to entry stack or other unknown stacks - use the fall-back
+	 * stack instead.
+	 */
+	if (info.type == STACK_TYPE_UNKNOWN || info.type == STACK_TYPE_ENTRY ||
+	    info.type >= STACK_TYPE_EXCEPTION_LAST)
+		sp = __this_cpu_ist_top_va(VC2);
+
+sync:
+	/*
+	 * Found a safe stack - switch to it as if the entry didn't happen via
+	 * IST stack. The code below only copies pt_regs, the real switch happens
+	 * in assembly code.
+	 */
+	sp = ALIGN_DOWN(sp, 8) - sizeof(*regs);
+
+	regs = (struct pt_regs *)sp;
+	*regs = *eregs;
+
+	return regs;
+}
+#endif
+
 struct bad_iret_stack {
 	void *error_entry_ret;
 	struct pt_regs regs;
-- 
2.27.0




[Index of Archives]     [KVM ARM]     [KVM ia64]     [KVM ppc]     [Virtualization Tools]     [Spice Development]     [Libvirt]     [Libvirt Users]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite Questions]     [Linux Kernel]     [Linux SCSI]     [XFree86]

  Powered by Linux