Merge branch 'WIP.x86-pti.entry-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 syscall entry code changes for PTI from Ingo Molnar:
 "The main changes here are Andy Lutomirski's changes to switch the
  x86-64 entry code to use the 'per CPU entry trampoline stack'. This,
  besides helping fix KASLR leaks (the pending Page Table Isolation
  (PTI) work), also robustifies the x86 entry code"

* 'WIP.x86-pti.entry-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (26 commits)
  x86/cpufeatures: Make CPU bugs sticky
  x86/paravirt: Provide a way to check for hypervisors
  x86/paravirt: Dont patch flush_tlb_single
  x86/entry/64: Make cpu_entry_area.tss read-only
  x86/entry: Clean up the SYSENTER_stack code
  x86/entry/64: Remove the SYSENTER stack canary
  x86/entry/64: Move the IST stacks into struct cpu_entry_area
  x86/entry/64: Create a per-CPU SYSCALL entry trampoline
  x86/entry/64: Return to userspace from the trampoline stack
  x86/entry/64: Use a per-CPU trampoline stack for IDT entries
  x86/espfix/64: Stop assuming that pt_regs is on the entry stack
  x86/entry/64: Separate cpu_current_top_of_stack from TSS.sp0
  x86/entry: Remap the TSS into the CPU entry area
  x86/entry: Move SYSENTER_stack to the beginning of struct tss_struct
  x86/dumpstack: Handle stack overflow on all stacks
  x86/entry: Fix assumptions that the HW TSS is at the beginning of cpu_tss
  x86/kasan/64: Teach KASAN about the cpu_entry_area
  x86/mm/fixmap: Generalize the GDT fixmap mechanism, introduce struct cpu_entry_area
  x86/entry/gdt: Put per-CPU GDT remaps in ascending order
  x86/dumpstack: Add get_stack_info() support for the SYSENTER stack
  ...

arch/x86/entry/entry_32.S

@@ -941,7 +941,8 @@ ENTRY(debug)
 	movl	%esp, %eax			# pt_regs pointer
 
 	/* Are we currently on the SYSENTER stack? */
-	PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx)
+	movl	PER_CPU_VAR(cpu_entry_area), %ecx
+	addl	$CPU_ENTRY_AREA_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx
 	subl	%eax, %ecx	/* ecx = (end of SYSENTER_stack) - esp */
 	cmpl	$SIZEOF_SYSENTER_stack, %ecx
 	jb	.Ldebug_from_sysenter_stack
@@ -984,7 +985,8 @@ ENTRY(nmi)
 	movl	%esp, %eax			# pt_regs pointer
 
 	/* Are we currently on the SYSENTER stack? */
-	PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx)
+	movl	PER_CPU_VAR(cpu_entry_area), %ecx
+	addl	$CPU_ENTRY_AREA_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx
 	subl	%eax, %ecx	/* ecx = (end of SYSENTER_stack) - esp */
 	cmpl	$SIZEOF_SYSENTER_stack, %ecx
 	jb	.Lnmi_from_sysenter_stack

arch/x86/entry/entry_64.S

@@ -140,6 +140,64 @@ END(native_usergs_sysret64)
  * with them due to bugs in both AMD and Intel CPUs.
  */
 
+	.pushsection .entry_trampoline, "ax"
+
+/*
+ * The code in here gets remapped into cpu_entry_area's trampoline.  This means
+ * that the assembler and linker have the wrong idea as to where this code
+ * lives (and, in fact, it's mapped more than once, so it's not even at a
+ * fixed address).  So we can't reference any symbols outside the entry
+ * trampoline and expect it to work.
+ *
+ * Instead, we carefully abuse %rip-relative addressing.
+ * _entry_trampoline(%rip) refers to the start of the remapped) entry
+ * trampoline.  We can thus find cpu_entry_area with this macro:
+ */
+
+#define CPU_ENTRY_AREA \
+	_entry_trampoline - CPU_ENTRY_AREA_entry_trampoline(%rip)
+
+/* The top word of the SYSENTER stack is hot and is usable as scratch space. */
+#define RSP_SCRATCH	CPU_ENTRY_AREA_SYSENTER_stack + \
+			SIZEOF_SYSENTER_stack - 8 + CPU_ENTRY_AREA
+
+ENTRY(entry_SYSCALL_64_trampoline)
+	UNWIND_HINT_EMPTY
+	swapgs
+
+	/* Stash the user RSP. */
+	movq	%rsp, RSP_SCRATCH
+
+	/* Load the top of the task stack into RSP */
+	movq	CPU_ENTRY_AREA_tss + TSS_sp1 + CPU_ENTRY_AREA, %rsp
+
+	/* Start building the simulated IRET frame. */
+	pushq	$__USER_DS			/* pt_regs->ss */
+	pushq	RSP_SCRATCH			/* pt_regs->sp */
+	pushq	%r11				/* pt_regs->flags */
+	pushq	$__USER_CS			/* pt_regs->cs */
+	pushq	%rcx				/* pt_regs->ip */
+
+	/*
+	 * x86 lacks a near absolute jump, and we can't jump to the real
+	 * entry text with a relative jump.  We could push the target
+	 * address and then use retq, but this destroys the pipeline on
+	 * many CPUs (wasting over 20 cycles on Sandy Bridge).  Instead,
+	 * spill RDI and restore it in a second-stage trampoline.
+	 */
+	pushq	%rdi
+	movq	$entry_SYSCALL_64_stage2, %rdi
+	jmp	*%rdi
+END(entry_SYSCALL_64_trampoline)
+
+	.popsection
+
+ENTRY(entry_SYSCALL_64_stage2)
+	UNWIND_HINT_EMPTY
+	popq	%rdi
+	jmp	entry_SYSCALL_64_after_hwframe
+END(entry_SYSCALL_64_stage2)
+
 ENTRY(entry_SYSCALL_64)
 	UNWIND_HINT_EMPTY
 	/*
@@ -330,8 +388,24 @@ syscall_return_via_sysret:
 	popq	%rsi	/* skip rcx */
 	popq	%rdx
 	popq	%rsi
+
+	/*
+	 * Now all regs are restored except RSP and RDI.
+	 * Save old stack pointer and switch to trampoline stack.
+	 */
+	movq	%rsp, %rdi
+	movq	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
+
+	pushq	RSP-RDI(%rdi)	/* RSP */
+	pushq	(%rdi)		/* RDI */
+
+	/*
+	 * We are on the trampoline stack.  All regs except RDI are live.
+	 * We can do future final exit work right here.
+	 */
+
 	popq	%rdi
-	movq	RSP-ORIG_RAX(%rsp), %rsp
+	popq	%rsp
 	USERGS_SYSRET64
 END(entry_SYSCALL_64)
 
@@ -466,12 +540,13 @@ END(irq_entries_start)
 
 .macro DEBUG_ENTRY_ASSERT_IRQS_OFF
 #ifdef CONFIG_DEBUG_ENTRY
-	pushfq
-	testl $X86_EFLAGS_IF, (%rsp)
+	pushq %rax
+	SAVE_FLAGS(CLBR_RAX)
+	testl $X86_EFLAGS_IF, %eax
 	jz .Lokay_\@
 	ud2
 .Lokay_\@:
-	addq $8, %rsp
+	popq %rax
 #endif
 .endm
 
@@ -563,6 +638,13 @@ END(irq_entries_start)
 /* 0(%rsp): ~(interrupt number) */
 	.macro interrupt func
 	cld
+
+	testb	$3, CS-ORIG_RAX(%rsp)
+	jz	1f
+	SWAPGS
+	call	switch_to_thread_stack
+1:
+
 	ALLOC_PT_GPREGS_ON_STACK
 	SAVE_C_REGS
 	SAVE_EXTRA_REGS
@@ -572,12 +654,8 @@ END(irq_entries_start)
 	jz	1f
 
 	/*
-	 * IRQ from user mode.  Switch to kernel gsbase and inform context
-	 * tracking that we're in kernel mode.
-	 */
-	SWAPGS
-
-	/*
+	 * IRQ from user mode.
+	 *
 	 * We need to tell lockdep that IRQs are off.  We can't do this until
 	 * we fix gsbase, and we should do it before enter_from_user_mode
 	 * (which can take locks).  Since TRACE_IRQS_OFF idempotent,
@@ -630,10 +708,41 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode)
 	ud2
 1:
 #endif
-	SWAPGS
 	POP_EXTRA_REGS
-	POP_C_REGS
-	addq	$8, %rsp	/* skip regs->orig_ax */
+	popq	%r11
+	popq	%r10
+	popq	%r9
+	popq	%r8
+	popq	%rax
+	popq	%rcx
+	popq	%rdx
+	popq	%rsi
+
+	/*
+	 * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS.
+	 * Save old stack pointer and switch to trampoline stack.
+	 */
+	movq	%rsp, %rdi
+	movq	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
+
+	/* Copy the IRET frame to the trampoline stack. */
+	pushq	6*8(%rdi)	/* SS */
+	pushq	5*8(%rdi)	/* RSP */
+	pushq	4*8(%rdi)	/* EFLAGS */
+	pushq	3*8(%rdi)	/* CS */
+	pushq	2*8(%rdi)	/* RIP */
+
+	/* Push user RDI on the trampoline stack. */
+	pushq	(%rdi)
+
+	/*
+	 * We are on the trampoline stack.  All regs except RDI are live.
+	 * We can do future final exit work right here.
+	 */
+
+	/* Restore RDI. */
+	popq	%rdi
+	SWAPGS
 	INTERRUPT_RETURN
 
 
@@ -829,7 +938,33 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
 /*
  * Exception entry points.
  */
-#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss) + (TSS_ist + ((x) - 1) * 8)
+#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8)
+
+/*
+ * Switch to the thread stack.  This is called with the IRET frame and
+ * orig_ax on the stack.  (That is, RDI..R12 are not on the stack and
+ * space has not been allocated for them.)
+ */
+ENTRY(switch_to_thread_stack)
+	UNWIND_HINT_FUNC
+
+	pushq	%rdi
+	movq	%rsp, %rdi
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+	UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI
+
+	pushq	7*8(%rdi)		/* regs->ss */
+	pushq	6*8(%rdi)		/* regs->rsp */
+	pushq	5*8(%rdi)		/* regs->eflags */
+	pushq	4*8(%rdi)		/* regs->cs */
+	pushq	3*8(%rdi)		/* regs->ip */
+	pushq	2*8(%rdi)		/* regs->orig_ax */
+	pushq	8(%rdi)			/* return address */
+	UNWIND_HINT_FUNC
+
+	movq	(%rdi), %rdi
+	ret
+END(switch_to_thread_stack)
 
 .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
 ENTRY(\sym)
@@ -848,11 +983,12 @@ ENTRY(\sym)
 
 	ALLOC_PT_GPREGS_ON_STACK
 
-	.if \paranoid
-	.if \paranoid == 1
+	.if \paranoid < 2
 	testb	$3, CS(%rsp)			/* If coming from userspace, switch stacks */
-	jnz	1f
+	jnz	.Lfrom_usermode_switch_stack_\@
 	.endif
+
+	.if \paranoid
 	call	paranoid_entry
 	.else
 	call	error_entry
@@ -894,20 +1030,15 @@ ENTRY(\sym)
 	jmp	error_exit
 	.endif
 
-	.if \paranoid == 1
+	.if \paranoid < 2
 	/*
-	 * Paranoid entry from userspace.  Switch stacks and treat it
+	 * Entry from userspace.  Switch stacks and treat it
 	 * as a normal entry.  This means that paranoid handlers
 	 * run in real process context if user_mode(regs).
 	 */
-1:
+.Lfrom_usermode_switch_stack_\@:
 	call	error_entry
 
-
-	movq	%rsp, %rdi			/* pt_regs pointer */
-	call	sync_regs
-	movq	%rax, %rsp			/* switch stack */
-
 	movq	%rsp, %rdi			/* pt_regs pointer */
 
 	.if \has_error_code
@@ -1170,6 +1301,14 @@ ENTRY(error_entry)
 	SWAPGS
 
 .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
+
 	/*
 	 * We need to tell lockdep that IRQs are off.  We can't do this until
 	 * we fix gsbase, and we should do it before enter_from_user_mode

arch/x86/entry/entry_64_compat.S

@@ -48,7 +48,7 @@
  */
 ENTRY(entry_SYSENTER_compat)
 	/* Interrupts are off on entry. */
-	SWAPGS_UNSAFE_STACK
+	SWAPGS
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	/*
@@ -306,8 +306,11 @@ ENTRY(entry_INT80_compat)
 	 */
 	movl	%eax, %eax
 
-	/* Construct struct pt_regs on stack (iret frame is already on stack) */
 	pushq	%rax			/* pt_regs->orig_ax */
+
+	/* switch to thread stack expects orig_ax to be pushed */
+	call	switch_to_thread_stack
+
 	pushq	%rdi			/* pt_regs->di */
 	pushq	%rsi			/* pt_regs->si */
 	pushq	%rdx			/* pt_regs->dx */

arch/x86/include/asm/cpufeature.h

@@ -135,6 +135,8 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
 	set_bit(bit, (unsigned long *)cpu_caps_set);	\
 } while (0)
 
+#define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit)
+
 #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS)
 /*
  * Static testing of CPU features.  Used the same as boot_cpu_has().

arch/x86/include/asm/desc.h

@@ -60,17 +60,10 @@ static inline struct desc_struct *get_current_gdt_rw(void)
 	return this_cpu_ptr(&gdt_page)->gdt;
 }
 
-/* Get the fixmap index for a specific processor */
-static inline unsigned int get_cpu_gdt_ro_index(int cpu)
-{
-	return FIX_GDT_REMAP_BEGIN + cpu;
-}
-
 /* Provide the fixmap address of the remapped GDT */
 static inline struct desc_struct *get_cpu_gdt_ro(int cpu)
 {
-	unsigned int idx = get_cpu_gdt_ro_index(cpu);
-	return (struct desc_struct *)__fix_to_virt(idx);
+	return (struct desc_struct *)&get_cpu_entry_area(cpu)->gdt;
 }
 
 /* Provide the current read-only GDT */
@@ -185,7 +178,7 @@ static inline void set_tssldt_descriptor(void *d, unsigned long addr,
 #endif
 }
 
-static inline void __set_tss_desc(unsigned cpu, unsigned int entry, void *addr)
+static inline void __set_tss_desc(unsigned cpu, unsigned int entry, struct x86_hw_tss *addr)
 {
 	struct desc_struct *d = get_cpu_gdt_rw(cpu);
 	tss_desc tss;

arch/x86/include/asm/fixmap.h

@@ -44,6 +44,45 @@ extern unsigned long __FIXADDR_TOP;
 			 PAGE_SIZE)
 #endif
 
+/*
+ * cpu_entry_area is a percpu region in the fixmap that contains things
+ * needed by the CPU and early entry/exit code.  Real types aren't used
+ * for all fields here to avoid circular header dependencies.
+ *
+ * Every field is a virtual alias of some other allocated backing store.
+ * There is no direct allocation of a struct cpu_entry_area.
+ */
+struct cpu_entry_area {
+	char gdt[PAGE_SIZE];
+
+	/*
+	 * The GDT is just below SYSENTER_stack and thus serves (on x86_64) as
+	 * a a read-only guard page.
+	 */
+	struct SYSENTER_stack_page SYSENTER_stack_page;
+
+	/*
+	 * On x86_64, the TSS is mapped RO.  On x86_32, it's mapped RW because
+	 * we need task switches to work, and task switches write to the TSS.
+	 */
+	struct tss_struct tss;
+
+	char entry_trampoline[PAGE_SIZE];
+
+#ifdef CONFIG_X86_64
+	/*
+	 * Exception stacks used for IST entries.
+	 *
+	 * In the future, this should have a separate slot for each stack
+	 * with guard pages between them.
+	 */
+	char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ];
+#endif
+};
+
+#define CPU_ENTRY_AREA_PAGES (sizeof(struct cpu_entry_area) / PAGE_SIZE)
+
+extern void setup_cpu_entry_areas(void);
 
 /*
  * Here we define all the compile-time 'special' virtual
@@ -101,8 +140,8 @@ enum fixed_addresses {
 	FIX_LNW_VRTC,
 #endif
 	/* Fixmap entries to remap the GDTs, one per processor. */
-	FIX_GDT_REMAP_BEGIN,
-	FIX_GDT_REMAP_END = FIX_GDT_REMAP_BEGIN + NR_CPUS - 1,
+	FIX_CPU_ENTRY_AREA_TOP,
+	FIX_CPU_ENTRY_AREA_BOTTOM = FIX_CPU_ENTRY_AREA_TOP + (CPU_ENTRY_AREA_PAGES * NR_CPUS) - 1,
 
 #ifdef CONFIG_ACPI_APEI_GHES
 	/* Used for GHES mapping from assorted contexts */
@@ -191,5 +230,30 @@ void __init *early_memremap_decrypted_wp(resource_size_t phys_addr,
 void __early_set_fixmap(enum fixed_addresses idx,
 			phys_addr_t phys, pgprot_t flags);
 
+static inline unsigned int __get_cpu_entry_area_page_index(int cpu, int page)
+{
+	BUILD_BUG_ON(sizeof(struct cpu_entry_area) % PAGE_SIZE != 0);
+
+	return FIX_CPU_ENTRY_AREA_BOTTOM - cpu*CPU_ENTRY_AREA_PAGES - page;
+}
+
+#define __get_cpu_entry_area_offset_index(cpu, offset) ({		\
+	BUILD_BUG_ON(offset % PAGE_SIZE != 0);				\
+	__get_cpu_entry_area_page_index(cpu, offset / PAGE_SIZE);	\
+	})
+
+#define get_cpu_entry_area_index(cpu, field)				\
+	__get_cpu_entry_area_offset_index((cpu), offsetof(struct cpu_entry_area, field))
+
+static inline struct cpu_entry_area *get_cpu_entry_area(int cpu)
+{
+	return (struct cpu_entry_area *)__fix_to_virt(__get_cpu_entry_area_page_index(cpu, 0));
+}
+
+static inline struct SYSENTER_stack *cpu_SYSENTER_stack(int cpu)
+{
+	return &get_cpu_entry_area(cpu)->SYSENTER_stack_page.stack;
+}
+
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_X86_FIXMAP_H */

arch/x86/include/asm/hypervisor.h

@@ -20,16 +20,7 @@
 #ifndef _ASM_X86_HYPERVISOR_H
 #define _ASM_X86_HYPERVISOR_H
 
-#ifdef CONFIG_HYPERVISOR_GUEST
-
-#include <asm/kvm_para.h>
-#include <asm/x86_init.h>
-#include <asm/xen/hypervisor.h>
-
-/*
- * x86 hypervisor information
- */
-
+/* x86 hypervisor types  */
 enum x86_hypervisor_type {
 	X86_HYPER_NATIVE = 0,
 	X86_HYPER_VMWARE,
@@ -39,6 +30,12 @@ enum x86_hypervisor_type {
 	X86_HYPER_KVM,
 };
 
+#ifdef CONFIG_HYPERVISOR_GUEST
+
+#include <asm/kvm_para.h>
+#include <asm/x86_init.h>
+#include <asm/xen/hypervisor.h>
+
 struct hypervisor_x86 {
 	/* Hypervisor name */
 	const char	*name;
@@ -58,7 +55,15 @@ struct hypervisor_x86 {
 
 extern enum x86_hypervisor_type x86_hyper_type;
 extern void init_hypervisor_platform(void);
+static inline bool hypervisor_is_type(enum x86_hypervisor_type type)
+{
+	return x86_hyper_type == type;
+}
 #else
 static inline void init_hypervisor_platform(void) { }
+static inline bool hypervisor_is_type(enum x86_hypervisor_type type)
+{
+	return type == X86_HYPER_NATIVE;
+}
 #endif /* CONFIG_HYPERVISOR_GUEST */
 #endif /* _ASM_X86_HYPERVISOR_H */

arch/x86/include/asm/irqflags.h

@@ -142,6 +142,9 @@ static inline notrace unsigned long arch_local_irq_save(void)
 	swapgs;					\
 	sysretl
 
+#ifdef CONFIG_DEBUG_ENTRY
+#define SAVE_FLAGS(x)		pushfq; popq %rax
+#endif
 #else
 #define INTERRUPT_RETURN		iret
 #define ENABLE_INTERRUPTS_SYSEXIT	sti; sysexit

arch/x86/include/asm/kdebug.h

@@ -26,6 +26,7 @@ extern void die(const char *, struct pt_regs *,long);
 extern int __must_check __die(const char *, struct pt_regs *, long);
 extern void show_stack_regs(struct pt_regs *regs);
 extern void __show_regs(struct pt_regs *regs, int all);
+extern void show_iret_regs(struct pt_regs *regs);
 extern unsigned long oops_begin(void);
 extern void oops_end(unsigned long, struct pt_regs *, int signr);
 

arch/x86/include/asm/paravirt.h

@@ -927,6 +927,15 @@ extern void default_banner(void);
 	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64),	\
 		  CLBR_NONE,						\
 		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64))
+
+#ifdef CONFIG_DEBUG_ENTRY
+#define SAVE_FLAGS(clobbers)                                        \
+	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), clobbers, \
+		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);        \
+		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl);    \
+		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
+#endif
+
 #endif	/* CONFIG_X86_32 */
 
 #endif /* __ASSEMBLY__ */

arch/x86/include/asm/processor.h

@@ -163,9 +163,9 @@ enum cpuid_regs_idx {
 extern struct cpuinfo_x86	boot_cpu_data;
 extern struct cpuinfo_x86	new_cpu_data;
 
-extern struct tss_struct	doublefault_tss;
-extern __u32			cpu_caps_cleared[NCAPINTS];
-extern __u32			cpu_caps_set[NCAPINTS];
+extern struct x86_hw_tss	doublefault_tss;
+extern __u32			cpu_caps_cleared[NCAPINTS + NBUGINTS];
+extern __u32			cpu_caps_set[NCAPINTS + NBUGINTS];
 
 #ifdef CONFIG_SMP
 DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
@@ -253,6 +253,11 @@ static inline void load_cr3(pgd_t *pgdir)
 	write_cr3(__sme_pa(pgdir));
 }
 
+/*
+ * Note that while the legacy 'TSS' name comes from 'Task State Segment',
+ * on modern x86 CPUs the TSS also holds information important to 64-bit mode,
+ * unrelated to the task-switch mechanism:
+ */
 #ifdef CONFIG_X86_32
 /* This is the TSS defined by the hardware. */
 struct x86_hw_tss {
@@ -305,7 +310,13 @@ struct x86_hw_tss {
 struct x86_hw_tss {
 	u32			reserved1;
 	u64			sp0;
+
+	/*
+	 * We store cpu_current_top_of_stack in sp1 so it's always accessible.
+	 * Linux does not use ring 1, so sp1 is not otherwise needed.
+	 */
 	u64			sp1;
+
 	u64			sp2;
 	u64			reserved2;
 	u64			ist[7];
@@ -323,12 +334,22 @@ struct x86_hw_tss {
 #define IO_BITMAP_BITS			65536
 #define IO_BITMAP_BYTES			(IO_BITMAP_BITS/8)
 #define IO_BITMAP_LONGS			(IO_BITMAP_BYTES/sizeof(long))
-#define IO_BITMAP_OFFSET		offsetof(struct tss_struct, io_bitmap)
+#define IO_BITMAP_OFFSET		(offsetof(struct tss_struct, io_bitmap) - offsetof(struct tss_struct, x86_tss))
 #define INVALID_IO_BITMAP_OFFSET	0x8000
 
+struct SYSENTER_stack {
+	unsigned long		words[64];
+};
+
+struct SYSENTER_stack_page {
+	struct SYSENTER_stack stack;
+} __aligned(PAGE_SIZE);
+
 struct tss_struct {
 	/*
-	 * The hardware state:
+	 * The fixed hardware portion.  This must not cross a page boundary
+	 * at risk of violating the SDM's advice and potentially triggering
+	 * errata.
 	 */
 	struct x86_hw_tss	x86_tss;
 
@@ -339,18 +360,9 @@ struct tss_struct {
 	 * be within the limit.
 	 */
 	unsigned long		io_bitmap[IO_BITMAP_LONGS + 1];
+} __aligned(PAGE_SIZE);
 
-#ifdef CONFIG_X86_32
-	/*
-	 * Space for the temporary SYSENTER stack.
-	 */
-	unsigned long		SYSENTER_stack_canary;
-	unsigned long		SYSENTER_stack[64];
-#endif
-
-} ____cacheline_aligned;
-
-DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss);
+DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw);
 
 /*
  * sizeof(unsigned long) coming from an extra "long" at the end
@@ -364,6 +376,9 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss);
 
 #ifdef CONFIG_X86_32
 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);
+#else
+/* The RO copy can't be accessed with this_cpu_xyz(), so use the RW copy. */
+#define cpu_current_top_of_stack cpu_tss_rw.x86_tss.sp1
 #endif
 
 /*
@@ -523,7 +538,7 @@ static inline void native_set_iopl_mask(unsigned mask)
 static inline void
 native_load_sp0(unsigned long sp0)
 {
-	this_cpu_write(cpu_tss.x86_tss.sp0, sp0);
+	this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0);
 }
 
 static inline void native_swapgs(void)
@@ -535,12 +550,12 @@ static inline void native_swapgs(void)
 
 static inline unsigned long current_top_of_stack(void)
 {
-#ifdef CONFIG_X86_64
-	return this_cpu_read_stable(cpu_tss.x86_tss.sp0);
-#else
-	/* sp0 on x86_32 is special in and around vm86 mode. */
+	/*
+	 *  We can't read directly from tss.sp0: sp0 on x86_32 is special in
+	 *  and around vm86 mode and sp0 on x86_64 is special because of the
+	 *  entry trampoline.
+	 */
 	return this_cpu_read_stable(cpu_current_top_of_stack);
-#endif
 }
 
 static inline bool on_thread_stack(void)

arch/x86/include/asm/stacktrace.h

@@ -16,6 +16,7 @@ enum stack_type {
 	STACK_TYPE_TASK,
 	STACK_TYPE_IRQ,
 	STACK_TYPE_SOFTIRQ,
+	STACK_TYPE_SYSENTER,
 	STACK_TYPE_EXCEPTION,
 	STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1,
 };
@@ -28,6 +29,8 @@ struct stack_info {
 bool in_task_stack(unsigned long *stack, struct task_struct *task,
 		   struct stack_info *info);
 
+bool in_sysenter_stack(unsigned long *stack, struct stack_info *info);
+
 int get_stack_info(unsigned long *stack, struct task_struct *task,
 		   struct stack_info *info, unsigned long *visit_mask);
 

arch/x86/include/asm/switch_to.h

@@ -79,10 +79,10 @@ do {									\
 static inline void refresh_sysenter_cs(struct thread_struct *thread)
 {
 	/* Only happens when SEP is enabled, no need to test "SEP"arately: */
-	if (unlikely(this_cpu_read(cpu_tss.x86_tss.ss1) == thread->sysenter_cs))
+	if (unlikely(this_cpu_read(cpu_tss_rw.x86_tss.ss1) == thread->sysenter_cs))
 		return;
 
-	this_cpu_write(cpu_tss.x86_tss.ss1, thread->sysenter_cs);
+	this_cpu_write(cpu_tss_rw.x86_tss.ss1, thread->sysenter_cs);
 	wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
 }
 #endif
@@ -90,10 +90,12 @@ 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: */
 #ifdef CONFIG_X86_32
 	load_sp0(task->thread.sp0);
 #else
-	load_sp0(task_top_of_stack(task));
+	if (static_cpu_has(X86_FEATURE_XENPV))
+		load_sp0(task_top_of_stack(task));
 #endif
 }
 

arch/x86/include/asm/thread_info.h

@@ -207,7 +207,7 @@ static inline int arch_within_stack_frames(const void * const stack,
 #else /* !__ASSEMBLY__ */
 
 #ifdef CONFIG_X86_64
-# define cpu_current_top_of_stack (cpu_tss + TSS_sp0)
+# define cpu_current_top_of_stack (cpu_tss_rw + TSS_sp1)
 #endif
 
 #endif

arch/x86/include/asm/traps.h

@@ -75,7 +75,6 @@ dotraplinkage void do_segment_not_present(struct pt_regs *, long);
 dotraplinkage void do_stack_segment(struct pt_regs *, long);
 #ifdef CONFIG_X86_64
 dotraplinkage void do_double_fault(struct pt_regs *, long);
-asmlinkage struct pt_regs *sync_regs(struct pt_regs *);
 #endif
 dotraplinkage void do_general_protection(struct pt_regs *, long);
 dotraplinkage void do_page_fault(struct pt_regs *, unsigned long);

arch/x86/include/asm/unwind.h

@@ -7,6 +7,9 @@
 #include <asm/ptrace.h>
 #include <asm/stacktrace.h>
 
+#define IRET_FRAME_OFFSET (offsetof(struct pt_regs, ip))
+#define IRET_FRAME_SIZE   (sizeof(struct pt_regs) - IRET_FRAME_OFFSET)
+
 struct unwind_state {
 	struct stack_info stack_info;
 	unsigned long stack_mask;
@@ -52,6 +55,10 @@ void unwind_start(struct unwind_state *state, struct task_struct *task,
 }
 
 #if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER)
+/*
+ * WARNING: The entire pt_regs may not be safe to dereference.  In some cases,
+ * only the iret frame registers are accessible.  Use with caution!
+ */
 static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
 {
 	if (unwind_done(state))

arch/x86/kernel/asm-offsets.c

@@ -93,4 +93,10 @@ void common(void) {
 
 	BLANK();
 	DEFINE(PTREGS_SIZE, sizeof(struct pt_regs));
+
+	/* Layout info for cpu_entry_area */
+	OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss);
+	OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline);
+	OFFSET(CPU_ENTRY_AREA_SYSENTER_stack, cpu_entry_area, SYSENTER_stack_page);
+	DEFINE(SIZEOF_SYSENTER_stack, sizeof(struct SYSENTER_stack));
 }

arch/x86/kernel/asm-offsets_32.c

@@ -47,13 +47,8 @@ void foo(void)
 	BLANK();
 
 	/* Offset from the sysenter stack to tss.sp0 */
-	DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) -
-	       offsetofend(struct tss_struct, SYSENTER_stack));
-
-	/* Offset from cpu_tss to SYSENTER_stack */
-	OFFSET(CPU_TSS_SYSENTER_stack, tss_struct, SYSENTER_stack);
-	/* Size of SYSENTER_stack */
-	DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack));
+	DEFINE(TSS_sysenter_sp0, offsetof(struct cpu_entry_area, tss.x86_tss.sp0) -
+	       offsetofend(struct cpu_entry_area, SYSENTER_stack_page.stack));
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 	BLANK();

arch/x86/kernel/asm-offsets_64.c

@@ -23,6 +23,9 @@ int main(void)
 #ifdef CONFIG_PARAVIRT
 	OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64);
 	OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs);
+#ifdef CONFIG_DEBUG_ENTRY
+	OFFSET(PV_IRQ_save_fl, pv_irq_ops, save_fl);
+#endif
 	BLANK();
 #endif
 
@@ -63,6 +66,7 @@ int main(void)
 
 	OFFSET(TSS_ist, tss_struct, x86_tss.ist);
 	OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
+	OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
 	BLANK();
 
 #ifdef CONFIG_CC_STACKPROTECTOR

arch/x86/kernel/cpu/common.c

@@ -476,8 +476,8 @@ static const char *table_lookup_model(struct cpuinfo_x86 *c)
 	return NULL;		/* Not found */
 }
 
-__u32 cpu_caps_cleared[NCAPINTS];
-__u32 cpu_caps_set[NCAPINTS];
+__u32 cpu_caps_cleared[NCAPINTS + NBUGINTS];
+__u32 cpu_caps_set[NCAPINTS + NBUGINTS];
 
 void load_percpu_segment(int cpu)
 {
@@ -490,27 +490,116 @@ void load_percpu_segment(int cpu)
 	load_stack_canary_segment();
 }
 
-/* Setup the fixmap mapping only once per-processor */
-static inline void setup_fixmap_gdt(int cpu)
+#ifdef CONFIG_X86_32
+/* The 32-bit entry code needs to find cpu_entry_area. */
+DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
+#endif
+
+#ifdef CONFIG_X86_64
+/*
+ * Special IST stacks which the CPU switches to when it calls
+ * an IST-marked descriptor entry. Up to 7 stacks (hardware
+ * limit), all of them are 4K, except the debug stack which
+ * is 8K.
+ */
+static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
+	  [0 ... N_EXCEPTION_STACKS - 1]	= EXCEPTION_STKSZ,
+	  [DEBUG_STACK - 1]			= DEBUG_STKSZ
+};
+
+static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
+	[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
+#endif
+
+static DEFINE_PER_CPU_PAGE_ALIGNED(struct SYSENTER_stack_page,
+				   SYSENTER_stack_storage);
+
+static void __init
+set_percpu_fixmap_pages(int idx, void *ptr, int pages, pgprot_t prot)
+{
+	for ( ; pages; pages--, idx--, ptr += PAGE_SIZE)
+		__set_fixmap(idx, per_cpu_ptr_to_phys(ptr), prot);
+}
+
+/* Setup the fixmap mappings only once per-processor */
+static void __init setup_cpu_entry_area(int cpu)
 {
 #ifdef CONFIG_X86_64
-	/* On 64-bit systems, we use a read-only fixmap GDT. */
-	pgprot_t prot = PAGE_KERNEL_RO;
+	extern char _entry_trampoline[];
+
+	/* On 64-bit systems, we use a read-only fixmap GDT and TSS. */
+	pgprot_t gdt_prot = PAGE_KERNEL_RO;
+	pgprot_t tss_prot = PAGE_KERNEL_RO;
 #else
 	/*
 	 * On native 32-bit systems, the GDT cannot be read-only because
 	 * our double fault handler uses a task gate, and entering through
-	 * a task gate needs to change an available TSS to busy.  If the GDT
-	 * is read-only, that will triple fault.
+	 * a task gate needs to change an available TSS to busy.  If the
+	 * GDT is read-only, that will triple fault.  The TSS cannot be
+	 * read-only because the CPU writes to it on task switches.
 	 *
-	 * On Xen PV, the GDT must be read-only because the hypervisor requires
-	 * it.
+	 * On Xen PV, the GDT must be read-only because the hypervisor
+	 * requires it.
 	 */
-	pgprot_t prot = boot_cpu_has(X86_FEATURE_XENPV) ?
+	pgprot_t gdt_prot = boot_cpu_has(X86_FEATURE_XENPV) ?
 		PAGE_KERNEL_RO : PAGE_KERNEL;
+	pgprot_t tss_prot = PAGE_KERNEL;
 #endif
 
-	__set_fixmap(get_cpu_gdt_ro_index(cpu), get_cpu_gdt_paddr(cpu), prot);
+	__set_fixmap(get_cpu_entry_area_index(cpu, gdt), get_cpu_gdt_paddr(cpu), gdt_prot);
+	set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, SYSENTER_stack_page),
+				per_cpu_ptr(&SYSENTER_stack_storage, cpu), 1,
+				PAGE_KERNEL);
+
+	/*
+	 * The Intel SDM says (Volume 3, 7.2.1):
+	 *
+	 *  Avoid placing a page boundary in the part of the TSS that the
+	 *  processor reads during a task switch (the first 104 bytes). The
+	 *  processor may not correctly perform address translations if a
+	 *  boundary occurs in this area. During a task switch, the processor
+	 *  reads and writes into the first 104 bytes of each TSS (using
+	 *  contiguous physical addresses beginning with the physical address
+	 *  of the first byte of the TSS). So, after TSS access begins, if
+	 *  part of the 104 bytes is not physically contiguous, the processor
+	 *  will access incorrect information without generating a page-fault
+	 *  exception.
+	 *
+	 * There are also a lot of errata involving the TSS spanning a page
+	 * boundary.  Assert that we're not doing that.
+	 */
+	BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^
+		      offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK);
+	BUILD_BUG_ON(sizeof(struct tss_struct) % PAGE_SIZE != 0);
+	set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, tss),
+				&per_cpu(cpu_tss_rw, cpu),
+				sizeof(struct tss_struct) / PAGE_SIZE,
+				tss_prot);
+
+#ifdef CONFIG_X86_32
+	per_cpu(cpu_entry_area, cpu) = get_cpu_entry_area(cpu);
+#endif
+
+#ifdef CONFIG_X86_64
+	BUILD_BUG_ON(sizeof(exception_stacks) % PAGE_SIZE != 0);
+	BUILD_BUG_ON(sizeof(exception_stacks) !=
+		     sizeof(((struct cpu_entry_area *)0)->exception_stacks));
+	set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, exception_stacks),
+				&per_cpu(exception_stacks, cpu),
+				sizeof(exception_stacks) / PAGE_SIZE,
+				PAGE_KERNEL);
+
+	__set_fixmap(get_cpu_entry_area_index(cpu, entry_trampoline),
+		     __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX);
+#endif
+}
+
+void __init setup_cpu_entry_areas(void)
+{
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu)
+		setup_cpu_entry_area(cpu);
 }
 
 /* Load the original GDT from the per-cpu structure */
@@ -747,7 +836,7 @@ static void apply_forced_caps(struct cpuinfo_x86 *c)
 {
 	int i;
 
-	for (i = 0; i < NCAPINTS; i++) {
+	for (i = 0; i < NCAPINTS + NBUGINTS; i++) {
 		c->x86_capability[i] &= ~cpu_caps_cleared[i];
 		c->x86_capability[i] |= cpu_caps_set[i];
 	}
@@ -1250,7 +1339,7 @@ void enable_sep_cpu(void)
 		return;
 
 	cpu = get_cpu();
-	tss = &per_cpu(cpu_tss, cpu);
+	tss = &per_cpu(cpu_tss_rw, cpu);
 
 	/*
 	 * We cache MSR_IA32_SYSENTER_CS's value in the TSS's ss1 field --
@@ -1259,11 +1348,7 @@ void enable_sep_cpu(void)
 
 	tss->x86_tss.ss1 = __KERNEL_CS;
 	wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0);
-
-	wrmsr(MSR_IA32_SYSENTER_ESP,
-	      (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack),
-	      0);
-
+	wrmsr(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_SYSENTER_stack(cpu) + 1), 0);
 	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0);
 
 	put_cpu();
@@ -1357,25 +1442,19 @@ DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
 DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
 EXPORT_PER_CPU_SYMBOL(__preempt_count);
 
-/*
- * Special IST stacks which the CPU switches to when it calls
- * an IST-marked descriptor entry. Up to 7 stacks (hardware
- * limit), all of them are 4K, except the debug stack which
- * is 8K.
- */
-static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
-	  [0 ... N_EXCEPTION_STACKS - 1]	= EXCEPTION_STKSZ,
-	  [DEBUG_STACK - 1]			= DEBUG_STKSZ
-};
-
-static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
-	[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
-
 /* May not be marked __init: used by software suspend */
 void syscall_init(void)
 {
+	extern char _entry_trampoline[];
+	extern char entry_SYSCALL_64_trampoline[];
+
+	int cpu = smp_processor_id();
+	unsigned long SYSCALL64_entry_trampoline =
+		(unsigned long)get_cpu_entry_area(cpu)->entry_trampoline +
+		(entry_SYSCALL_64_trampoline - _entry_trampoline);
+
 	wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
-	wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
+	wrmsrl(MSR_LSTAR, SYSCALL64_entry_trampoline);
 
 #ifdef CONFIG_IA32_EMULATION
 	wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat);
@@ -1386,7 +1465,7 @@ void syscall_init(void)
 	 * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit).
 	 */
 	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
-	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
+	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_SYSENTER_stack(cpu) + 1));
 	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
 #else
 	wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret);
@@ -1530,7 +1609,7 @@ void cpu_init(void)
 	if (cpu)
 		load_ucode_ap();
 
-	t = &per_cpu(cpu_tss, cpu);
+	t = &per_cpu(cpu_tss_rw, cpu);
 	oist = &per_cpu(orig_ist, cpu);
 
 #ifdef CONFIG_NUMA
@@ -1569,7 +1648,7 @@ void cpu_init(void)
 	 * set up and load the per-CPU TSS
 	 */
 	if (!oist->ist[0]) {
-		char *estacks = per_cpu(exception_stacks, cpu);
+		char *estacks = get_cpu_entry_area(cpu)->exception_stacks;
 
 		for (v = 0; v < N_EXCEPTION_STACKS; v++) {
 			estacks += exception_stack_sizes[v];
@@ -1580,7 +1659,7 @@ void cpu_init(void)
 		}
 	}
 
-	t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+	t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;
 
 	/*
 	 * <= is required because the CPU will access up to
@@ -1596,11 +1675,12 @@ void cpu_init(void)
 	enter_lazy_tlb(&init_mm, me);
 
 	/*
-	 * 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, t);
+	set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
 	load_TR_desc();
+	load_sp0((unsigned long)(cpu_SYSENTER_stack(cpu) + 1));
 
 	load_mm_ldt(&init_mm);
 
@@ -1612,7 +1692,6 @@ void cpu_init(void)
 	if (is_uv_system())
 		uv_cpu_init();
 
-	setup_fixmap_gdt(cpu);
 	load_fixmap_gdt(cpu);
 }
 
@@ -1622,7 +1701,7 @@ void cpu_init(void)
 {
 	int cpu = smp_processor_id();
 	struct task_struct *curr = current;
-	struct tss_struct *t = &per_cpu(cpu_tss, cpu);
+	struct tss_struct *t = &per_cpu(cpu_tss_rw, cpu);
 
 	wait_for_master_cpu(cpu);
 
@@ -1657,12 +1736,12 @@ void cpu_init(void)
 	 * Initialize the TSS.  Don't bother initializing sp0, as the initial
 	 * task never enters user mode.
 	 */
-	set_tss_desc(cpu, t);
+	set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
 	load_TR_desc();
 
 	load_mm_ldt(&init_mm);
 
-	t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+	t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;
 
 #ifdef CONFIG_DOUBLEFAULT
 	/* Set up doublefault TSS pointer in the GDT */
@@ -1674,7 +1753,6 @@ void cpu_init(void)
 
 	fpu__init_cpu();
 
-	setup_fixmap_gdt(cpu);
 	load_fixmap_gdt(cpu);
 }
 #endif

arch/x86/kernel/doublefault.c

@@ -50,25 +50,23 @@ static void doublefault_fn(void)
 		cpu_relax();
 }
 
-struct tss_struct doublefault_tss __cacheline_aligned = {
-	.x86_tss = {
-		.sp0		= STACK_START,
-		.ss0		= __KERNEL_DS,
-		.ldt		= 0,
-		.io_bitmap_base	= INVALID_IO_BITMAP_OFFSET,
-
-		.ip		= (unsigned long) doublefault_fn,
-		/* 0x2 bit is always set */
-		.flags		= X86_EFLAGS_SF | 0x2,
-		.sp		= STACK_START,
-		.es		= __USER_DS,
-		.cs		= __KERNEL_CS,
-		.ss		= __KERNEL_DS,
-		.ds		= __USER_DS,
-		.fs		= __KERNEL_PERCPU,
-
-		.__cr3		= __pa_nodebug(swapper_pg_dir),
-	}
+struct x86_hw_tss doublefault_tss __cacheline_aligned = {
+	.sp0		= STACK_START,
+	.ss0		= __KERNEL_DS,
+	.ldt		= 0,
+	.io_bitmap_base	= INVALID_IO_BITMAP_OFFSET,
+
+	.ip		= (unsigned long) doublefault_fn,
+	/* 0x2 bit is always set */
+	.flags		= X86_EFLAGS_SF | 0x2,
+	.sp		= STACK_START,
+	.es		= __USER_DS,
+	.cs		= __KERNEL_CS,
+	.ss		= __KERNEL_DS,
+	.ds		= __USER_DS,
+	.fs		= __KERNEL_PERCPU,
+
+	.__cr3		= __pa_nodebug(swapper_pg_dir),
 };
 
 /* dummy for do_double_fault() call */

arch/x86/kernel/dumpstack.c

@@ -43,6 +43,24 @@ bool in_task_stack(unsigned long *stack, struct task_struct *task,
 	return true;
 }
 
+bool in_sysenter_stack(unsigned long *stack, struct stack_info *info)
+{
+	struct SYSENTER_stack *ss = cpu_SYSENTER_stack(smp_processor_id());
+
+	void *begin = ss;
+	void *end = ss + 1;
+
+	if ((void *)stack < begin || (void *)stack >= end)
+		return false;
+
+	info->type	= STACK_TYPE_SYSENTER;
+	info->begin	= begin;
+	info->end	= end;
+	info->next_sp	= NULL;
+
+	return true;
+}
+
 static void printk_stack_address(unsigned long address, int reliable,
 				 char *log_lvl)
 {
@@ -50,6 +68,28 @@ static void printk_stack_address(unsigned long address, int reliable,
 	printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address);
 }
 
+void show_iret_regs(struct pt_regs *regs)
+{
+	printk(KERN_DEFAULT "RIP: %04x:%pS\n", (int)regs->cs, (void *)regs->ip);
+	printk(KERN_DEFAULT "RSP: %04x:%016lx EFLAGS: %08lx", (int)regs->ss,
+		regs->sp, regs->flags);
+}
+
+static void show_regs_safe(struct stack_info *info, struct pt_regs *regs)
+{
+	if (on_stack(info, regs, sizeof(*regs)))
+		__show_regs(regs, 0);
+	else if (on_stack(info, (void *)regs + IRET_FRAME_OFFSET,
+			  IRET_FRAME_SIZE)) {
+		/*
+		 * When an interrupt or exception occurs in entry code, the
+		 * full pt_regs might not have been saved yet.  In that case
+		 * just print the iret frame.
+		 */
+		show_iret_regs(regs);
+	}
+}
+
 void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 			unsigned long *stack, char *log_lvl)
 {
@@ -71,31 +111,35 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	 * - task stack
 	 * - interrupt stack
 	 * - HW exception stacks (double fault, nmi, debug, mce)
+	 * - SYSENTER stack
 	 *
-	 * x86-32 can have up to three stacks:
+	 * x86-32 can have up to four stacks:
 	 * - task stack
 	 * - softirq stack
 	 * - hardirq stack
+	 * - SYSENTER stack
 	 */
 	for (regs = NULL; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) {
 		const char *stack_name;
 
-		/*
-		 * If we overflowed the task stack into a guard page, jump back
-		 * to the bottom of the usable stack.
-		 */
-		if (task_stack_page(task) - (void *)stack < PAGE_SIZE)
-			stack = task_stack_page(task);
-
-		if (get_stack_info(stack, task, &stack_info, &visit_mask))
-			break;
+		if (get_stack_info(stack, task, &stack_info, &visit_mask)) {
+			/*
+			 * We weren't on a valid stack.  It's possible that
+			 * we overflowed a valid stack into a guard page.
+			 * See if the next page up is valid so that we can
+			 * generate some kind of backtrace if this happens.
+			 */
+			stack = (unsigned long *)PAGE_ALIGN((unsigned long)stack);
+			if (get_stack_info(stack, task, &stack_info, &visit_mask))
+				break;
+		}
 
 		stack_name = stack_type_name(stack_info.type);
 		if (stack_name)
 			printk("%s <%s>\n", log_lvl, stack_name);
 
-		if (regs && on_stack(&stack_info, regs, sizeof(*regs)))
-			__show_regs(regs, 0);
+		if (regs)
+			show_regs_safe(&stack_info, regs);
 
 		/*
 		 * Scan the stack, printing any text addresses we find.  At the
@@ -119,7 +163,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 
 			/*
 			 * Don't print regs->ip again if it was already printed
-			 * by __show_regs() below.
+			 * by show_regs_safe() below.
 			 */
 			if (regs && stack == &regs->ip)
 				goto next;
@@ -155,8 +199,8 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 
 			/* if the frame has entry regs, print them */
 			regs = unwind_get_entry_regs(&state);
-			if (regs && on_stack(&stack_info, regs, sizeof(*regs)))
-				__show_regs(regs, 0);
+			if (regs)
+				show_regs_safe(&stack_info, regs);
 		}
 
 		if (stack_name)

arch/x86/kernel/dumpstack_32.c

@@ -26,6 +26,9 @@ const char *stack_type_name(enum stack_type type)
 	if (type == STACK_TYPE_SOFTIRQ)
 		return "SOFTIRQ";
 
+	if (type == STACK_TYPE_SYSENTER)
+		return "SYSENTER";
+
 	return NULL;
 }
 
@@ -93,6 +96,9 @@ int get_stack_info(unsigned long *stack, struct task_struct *task,
 	if (task != current)
 		goto unknown;
 
+	if (in_sysenter_stack(stack, info))
+		goto recursion_check;
+
 	if (in_hardirq_stack(stack, info))
 		goto recursion_check;
 

arch/x86/kernel/dumpstack_64.c

@@ -37,6 +37,9 @@ const char *stack_type_name(enum stack_type type)
 	if (type == STACK_TYPE_IRQ)
 		return "IRQ";
 
+	if (type == STACK_TYPE_SYSENTER)
+		return "SYSENTER";
+
 	if (type >= STACK_TYPE_EXCEPTION && type <= STACK_TYPE_EXCEPTION_LAST)
 		return exception_stack_names[type - STACK_TYPE_EXCEPTION];
 
@@ -115,6 +118,9 @@ int get_stack_info(unsigned long *stack, struct task_struct *task,
 	if (in_irq_stack(stack, info))
 		goto recursion_check;
 
+	if (in_sysenter_stack(stack, info))
+		goto recursion_check;
+
 	goto unknown;
 
 recursion_check:

arch/x86/kernel/ioport.c

@@ -67,7 +67,7 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
 	 * because the ->io_bitmap_max value must match the bitmap
 	 * contents:
 	 */
-	tss = &per_cpu(cpu_tss, get_cpu());
+	tss = &per_cpu(cpu_tss_rw, get_cpu());
 
 	if (turn_on)
 		bitmap_clear(t->io_bitmap_ptr, from, num);

arch/x86/kernel/irq.c

@@ -219,18 +219,6 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 	/* high bit used in ret_from_ code  */
 	unsigned vector = ~regs->orig_ax;
 
-	/*
-	 * NB: Unlike exception entries, IRQ entries do not reliably
-	 * handle context tracking in the low-level entry code.  This is
-	 * because syscall entries execute briefly with IRQs on before
-	 * updating context tracking state, so we can take an IRQ from
-	 * kernel mode with CONTEXT_USER.  The low-level entry code only
-	 * updates the context if we came from user mode, so we won't
-	 * switch to CONTEXT_KERNEL.  We'll fix that once the syscall
-	 * code is cleaned up enough that we can cleanly defer enabling
-	 * IRQs.
-	 */
-
 	entering_irq();
 
 	/* entering_irq() tells RCU that we're not quiescent.  Check it. */

arch/x86/kernel/irq_64.c

@@ -57,10 +57,10 @@ static inline void stack_overflow_check(struct pt_regs *regs)
 	if (regs->sp >= estack_top && regs->sp <= estack_bottom)
 		return;
 
-	WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx)\n",
+	WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx,ip:%pF)\n",
 		current->comm, curbase, regs->sp,
 		irq_stack_top, irq_stack_bottom,
-		estack_top, estack_bottom);
+		estack_top, estack_bottom, (void *)regs->ip);
 
 	if (sysctl_panic_on_stackoverflow)
 		panic("low stack detected by irq handler - check messages\n");

arch/x86/kernel/paravirt_patch_64.c

@@ -10,7 +10,6 @@ DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax");
 DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax");
 DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax");
 DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3");
-DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)");
 DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd");
 
 DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq");
@@ -60,7 +59,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_mmu_ops, read_cr2);
 		PATCH_SITE(pv_mmu_ops, read_cr3);
 		PATCH_SITE(pv_mmu_ops, write_cr3);
-		PATCH_SITE(pv_mmu_ops, flush_tlb_single);
 		PATCH_SITE(pv_cpu_ops, wbinvd);
 #if defined(CONFIG_PARAVIRT_SPINLOCKS)
 		case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):

arch/x86/kernel/process.c

@@ -47,7 +47,7 @@
  * section. Since TSS's are completely CPU-local, we want them
  * on exact cacheline boundaries, to eliminate cacheline ping-pong.
  */
-__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
+__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss_rw) = {
 	.x86_tss = {
 		/*
 		 * .sp0 is only used when entering ring 0 from a lower
@@ -56,6 +56,16 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
 		 * Poison it.
 		 */
 		.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,
 		.ss1 = __KERNEL_CS,
@@ -71,11 +81,8 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
 	  */
 	.io_bitmap		= { [0 ... IO_BITMAP_LONGS] = ~0 },
 #endif
-#ifdef CONFIG_X86_32
-	.SYSENTER_stack_canary	= STACK_END_MAGIC,
-#endif
 };
-EXPORT_PER_CPU_SYMBOL(cpu_tss);
+EXPORT_PER_CPU_SYMBOL(cpu_tss_rw);
 
 DEFINE_PER_CPU(bool, __tss_limit_invalid);
 EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid);
@@ -104,7 +111,7 @@ void exit_thread(struct task_struct *tsk)
 	struct fpu *fpu = &t->fpu;
 
 	if (bp) {
-		struct tss_struct *tss = &per_cpu(cpu_tss, get_cpu());
+		struct tss_struct *tss = &per_cpu(cpu_tss_rw, get_cpu());
 
 		t->io_bitmap_ptr = NULL;
 		clear_thread_flag(TIF_IO_BITMAP);

arch/x86/kernel/process_32.c

@@ -234,7 +234,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	struct fpu *prev_fpu = &prev->fpu;
 	struct fpu *next_fpu = &next->fpu;
 	int cpu = smp_processor_id();
-	struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
+	struct tss_struct *tss = &per_cpu(cpu_tss_rw, cpu);
 
 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 

arch/x86/kernel/process_64.c

@@ -69,9 +69,8 @@ void __show_regs(struct pt_regs *regs, int all)
 	unsigned int fsindex, gsindex;
 	unsigned int ds, cs, es;
 
-	printk(KERN_DEFAULT "RIP: %04lx:%pS\n", regs->cs, (void *)regs->ip);
-	printk(KERN_DEFAULT "RSP: %04lx:%016lx EFLAGS: %08lx", regs->ss,
-		regs->sp, regs->flags);
+	show_iret_regs(regs);
+
 	if (regs->orig_ax != -1)
 		pr_cont(" ORIG_RAX: %016lx\n", regs->orig_ax);
 	else
@@ -88,6 +87,9 @@ void __show_regs(struct pt_regs *regs, int all)
 	printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n",
 	       regs->r13, regs->r14, regs->r15);
 
+	if (!all)
+		return;
+
 	asm("movl %%ds,%0" : "=r" (ds));
 	asm("movl %%cs,%0" : "=r" (cs));
 	asm("movl %%es,%0" : "=r" (es));
@@ -98,9 +100,6 @@ void __show_regs(struct pt_regs *regs, int all)
 	rdmsrl(MSR_GS_BASE, gs);
 	rdmsrl(MSR_KERNEL_GS_BASE, shadowgs);
 
-	if (!all)
-		return;
-
 	cr0 = read_cr0();
 	cr2 = read_cr2();
 	cr3 = __read_cr3();
@@ -400,7 +399,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	struct fpu *prev_fpu = &prev->fpu;
 	struct fpu *next_fpu = &next->fpu;
 	int cpu = smp_processor_id();
-	struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
+	struct tss_struct *tss = &per_cpu(cpu_tss_rw, cpu);
 
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) &&
 		     this_cpu_read(irq_count) != -1);
@@ -462,6 +461,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * Switch the PDA and FPU contexts.
 	 */
 	this_cpu_write(current_task, next_p);
+	this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
 
 	/* Reload sp0. */
 	update_sp0(next_p);

arch/x86/kernel/traps.c

@@ -348,9 +348,15 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 
 	/*
 	 * If IRET takes a non-IST fault on the espfix64 stack, then we
-	 * end up promoting it to a doublefault.  In that case, modify
-	 * the stack to make it look like we just entered the #GP
-	 * handler from user space, similar to bad_iret.
+	 * end up promoting it to a doublefault.  In that case, take
+	 * advantage of the fact that we're not using the normal (TSS.sp0)
+	 * stack right now.  We can write a fake #GP(0) frame at TSS.sp0
+	 * and then modify our own IRET frame so that, when we return,
+	 * we land directly at the #GP(0) vector with the stack already
+	 * set up according to its expectations.
+	 *
+	 * The net result is that our #GP handler will think that we
+	 * entered from usermode with the bad user context.
 	 *
 	 * No need for ist_enter here because we don't use RCU.
 	 */
@@ -358,13 +364,26 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 		regs->cs == __KERNEL_CS &&
 		regs->ip == (unsigned long)native_irq_return_iret)
 	{
-		struct pt_regs *normal_regs = task_pt_regs(current);
+		struct pt_regs *gpregs = (struct pt_regs *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1;
 
-		/* Fake a #GP(0) from userspace. */
-		memmove(&normal_regs->ip, (void *)regs->sp, 5*8);
-		normal_regs->orig_ax = 0;  /* Missing (lost) #GP error code */
+		/*
+		 * regs->sp points to the failing IRET frame on the
+		 * ESPFIX64 stack.  Copy it to the entry stack.  This fills
+		 * in gpregs->ss through gpregs->ip.
+		 *
+		 */
+		memmove(&gpregs->ip, (void *)regs->sp, 5*8);
+		gpregs->orig_ax = 0;  /* Missing (lost) #GP error code */
+
+		/*
+		 * Adjust our frame so that we return straight to the #GP
+		 * vector with the expected RSP value.  This is safe because
+		 * we won't enable interupts or schedule before we invoke
+		 * general_protection, so nothing will clobber the stack
+		 * frame we just set up.
+		 */
 		regs->ip = (unsigned long)general_protection;
-		regs->sp = (unsigned long)&normal_regs->orig_ax;
+		regs->sp = (unsigned long)&gpregs->orig_ax;
 
 		return;
 	}
@@ -389,7 +408,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 	 *
 	 *   Processors update CR2 whenever a page fault is detected. If a
 	 *   second page fault occurs while an earlier page fault is being
-	 *   deliv- ered, the faulting linear address of the second fault will
+	 *   delivered, the faulting linear address of the second fault will
 	 *   overwrite the contents of CR2 (replacing the previous
 	 *   address). These updates to CR2 occur even if the page fault
 	 *   results in a double fault or occurs during the delivery of a
@@ -605,14 +624,15 @@ NOKPROBE_SYMBOL(do_int3);
 
 #ifdef CONFIG_X86_64
 /*
- * Help handler running on IST stack to switch off the IST stack if the
- * interrupted code was in user mode. The actual stack switch is done in
- * entry_64.S
+ * Help handler running on a per-cpu (IST or entry trampoline) stack
+ * to switch to the normal thread stack if the interrupted code was in
+ * user mode. The actual stack switch is done in entry_64.S
  */
 asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs)
 {
-	struct pt_regs *regs = task_pt_regs(current);
-	*regs = *eregs;
+	struct pt_regs *regs = (struct pt_regs *)this_cpu_read(cpu_current_top_of_stack) - 1;
+	if (regs != eregs)
+		*regs = *eregs;
 	return regs;
 }
 NOKPROBE_SYMBOL(sync_regs);
@@ -628,13 +648,13 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
 	/*
 	 * This is called from entry_64.S early in handling a fault
 	 * caused by a bad iret to user mode.  To handle the fault
-	 * correctly, we want move our stack frame to task_pt_regs
-	 * and we want to pretend that the exception came from the
-	 * iret target.
+	 * correctly, we want to move our stack frame to where it would
+	 * be had we entered directly on the entry stack (rather than
+	 * just below the IRET frame) and we want to pretend that the
+	 * exception came from the IRET target.
 	 */
 	struct bad_iret_stack *new_stack =
-		container_of(task_pt_regs(current),
-			     struct bad_iret_stack, regs);
+		(struct bad_iret_stack *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1;
 
 	/* Copy the IRET target to the new stack. */
 	memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8);
@@ -795,14 +815,6 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	debug_stack_usage_dec();
 
 exit:
-#if defined(CONFIG_X86_32)
-	/*
-	 * This is the most likely code path that involves non-trivial use
-	 * of the SYSENTER stack.  Check that we haven't overrun it.
-	 */
-	WARN(this_cpu_read(cpu_tss.SYSENTER_stack_canary) != STACK_END_MAGIC,
-	     "Overran or corrupted SYSENTER stack\n");
-#endif
 	ist_exit(regs);
 }
 NOKPROBE_SYMBOL(do_debug);
@@ -929,6 +941,9 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
 
 void __init trap_init(void)
 {
+	/* Init cpu_entry_area before IST entries are set up */
+	setup_cpu_entry_areas();
+
 	idt_setup_traps();
 
 	/*

arch/x86/kernel/unwind_orc.c

@@ -253,22 +253,15 @@ unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
 	return NULL;
 }
 
-static bool stack_access_ok(struct unwind_state *state, unsigned long addr,
+static bool stack_access_ok(struct unwind_state *state, unsigned long _addr,
 			    size_t len)
 {
 	struct stack_info *info = &state->stack_info;
+	void *addr = (void *)_addr;
 
-	/*
-	 * If the address isn't on the current stack, switch to the next one.
-	 *
-	 * We may have to traverse multiple stacks to deal with the possibility
-	 * that info->next_sp could point to an empty stack and the address
-	 * could be on a subsequent stack.
-	 */
-	while (!on_stack(info, (void *)addr, len))
-		if (get_stack_info(info->next_sp, state->task, info,
-				   &state->stack_mask))
-			return false;
+	if (!on_stack(info, addr, len) &&
+	    (get_stack_info(addr, state->task, info, &state->stack_mask)))
+		return false;
 
 	return true;
 }
@@ -283,42 +276,32 @@ static bool deref_stack_reg(struct unwind_state *state, unsigned long addr,
 	return true;
 }
 
-#define REGS_SIZE (sizeof(struct pt_regs))
-#define SP_OFFSET (offsetof(struct pt_regs, sp))
-#define IRET_REGS_SIZE (REGS_SIZE - offsetof(struct pt_regs, ip))
-#define IRET_SP_OFFSET (SP_OFFSET - offsetof(struct pt_regs, ip))
-
 static bool deref_stack_regs(struct unwind_state *state, unsigned long addr,
-			     unsigned long *ip, unsigned long *sp, bool full)
+			     unsigned long *ip, unsigned long *sp)
 {
-	size_t regs_size = full ? REGS_SIZE : IRET_REGS_SIZE;
-	size_t sp_offset = full ? SP_OFFSET : IRET_SP_OFFSET;
-	struct pt_regs *regs = (struct pt_regs *)(addr + regs_size - REGS_SIZE);
-
-	if (IS_ENABLED(CONFIG_X86_64)) {
-		if (!stack_access_ok(state, addr, regs_size))
-			return false;
+	struct pt_regs *regs = (struct pt_regs *)addr;
 
-		*ip = regs->ip;
-		*sp = regs->sp;
+	/* x86-32 support will be more complicated due to the &regs->sp hack */
+	BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_32));
 
-		return true;
-	}
-
-	if (!stack_access_ok(state, addr, sp_offset))
+	if (!stack_access_ok(state, addr, sizeof(struct pt_regs)))
 		return false;
 
 	*ip = regs->ip;
+	*sp = regs->sp;
+	return true;
+}
 
-	if (user_mode(regs)) {
-		if (!stack_access_ok(state, addr + sp_offset,
-				     REGS_SIZE - SP_OFFSET))
-			return false;
+static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr,
+				  unsigned long *ip, unsigned long *sp)
+{
+	struct pt_regs *regs = (void *)addr - IRET_FRAME_OFFSET;
 
-		*sp = regs->sp;
-	} else
-		*sp = (unsigned long)&regs->sp;
+	if (!stack_access_ok(state, addr, IRET_FRAME_SIZE))
+		return false;
 
+	*ip = regs->ip;
+	*sp = regs->sp;
 	return true;
 }
 
@@ -327,7 +310,6 @@ bool unwind_next_frame(struct unwind_state *state)
 	unsigned long ip_p, sp, orig_ip, prev_sp = state->sp;
 	enum stack_type prev_type = state->stack_info.type;
 	struct orc_entry *orc;
-	struct pt_regs *ptregs;
 	bool indirect = false;
 
 	if (unwind_done(state))
@@ -435,7 +417,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		break;
 
 	case ORC_TYPE_REGS:
-		if (!deref_stack_regs(state, sp, &state->ip, &state->sp, true)) {
+		if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) {
 			orc_warn("can't dereference registers at %p for ip %pB\n",
 				 (void *)sp, (void *)orig_ip);
 			goto done;
@@ -447,20 +429,14 @@ bool unwind_next_frame(struct unwind_state *state)
 		break;
 
 	case ORC_TYPE_REGS_IRET:
-		if (!deref_stack_regs(state, sp, &state->ip, &state->sp, false)) {
+		if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) {
 			orc_warn("can't dereference iret registers at %p for ip %pB\n",
 				 (void *)sp, (void *)orig_ip);
 			goto done;
 		}
 
-		ptregs = container_of((void *)sp, struct pt_regs, ip);
-		if ((unsigned long)ptregs >= prev_sp &&
-		    on_stack(&state->stack_info, ptregs, REGS_SIZE)) {
-			state->regs = ptregs;
-			state->full_regs = false;
-		} else
-			state->regs = NULL;
-
+		state->regs = (void *)sp - IRET_FRAME_OFFSET;
+		state->full_regs = false;
 		state->signal = true;
 		break;
 
@@ -553,8 +529,18 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 	}
 
 	if (get_stack_info((unsigned long *)state->sp, state->task,
-			   &state->stack_info, &state->stack_mask))
-		return;
+			   &state->stack_info, &state->stack_mask)) {
+		/*
+		 * We weren't on a valid stack.  It's possible that
+		 * we overflowed a valid stack into a guard page.
+		 * See if the next page up is valid so that we can
+		 * generate some kind of backtrace if this happens.
+		 */
+		void *next_page = (void *)PAGE_ALIGN((unsigned long)state->sp);
+		if (get_stack_info(next_page, state->task, &state->stack_info,
+				   &state->stack_mask))
+			return;
+	}
 
 	/*
 	 * The caller can provide the address of the first frame directly

arch/x86/kernel/vmlinux.lds.S

@@ -107,6 +107,15 @@ SECTIONS
 		SOFTIRQENTRY_TEXT
 		*(.fixup)
 		*(.gnu.warning)
+
+#ifdef CONFIG_X86_64
+		. = ALIGN(PAGE_SIZE);
+		_entry_trampoline = .;
+		*(.entry_trampoline)
+		. = ALIGN(PAGE_SIZE);
+		ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big");
+#endif
+
 		/* End of text section */
 		_etext = .;
 	} :text = 0x9090

arch/x86/kvm/vmx.c

@@ -2302,7 +2302,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		 * processors.  See 22.2.4.
 		 */
 		vmcs_writel(HOST_TR_BASE,
-			    (unsigned long)this_cpu_ptr(&cpu_tss));
+			    (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss);
 		vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt);   /* 22.2.4 */
 
 		/*

arch/x86/lib/delay.c

@@ -107,10 +107,10 @@ static void delay_mwaitx(unsigned long __loops)
 		delay = min_t(u64, MWAITX_MAX_LOOPS, loops);
 
 		/*
-		 * Use cpu_tss as a cacheline-aligned, seldomly
+		 * Use cpu_tss_rw as a cacheline-aligned, seldomly
 		 * accessed per-cpu variable as the monitor target.
 		 */
-		__monitorx(raw_cpu_ptr(&cpu_tss), 0, 0);
+		__monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0);
 
 		/*
 		 * AMD, like Intel, supports the EAX hint and EAX=0xf

arch/x86/mm/kasan_init_64.c

@@ -277,6 +277,7 @@ void __init kasan_early_init(void)
 void __init kasan_init(void)
 {
 	int i;
+	void *shadow_cpu_entry_begin, *shadow_cpu_entry_end;
 
 #ifdef CONFIG_KASAN_INLINE
 	register_die_notifier(&kasan_die_notifier);
@@ -329,8 +330,23 @@ void __init kasan_init(void)
 			      (unsigned long)kasan_mem_to_shadow(_end),
 			      early_pfn_to_nid(__pa(_stext)));
 
+	shadow_cpu_entry_begin = (void *)__fix_to_virt(FIX_CPU_ENTRY_AREA_BOTTOM);
+	shadow_cpu_entry_begin = kasan_mem_to_shadow(shadow_cpu_entry_begin);
+	shadow_cpu_entry_begin = (void *)round_down((unsigned long)shadow_cpu_entry_begin,
+						PAGE_SIZE);
+
+	shadow_cpu_entry_end = (void *)(__fix_to_virt(FIX_CPU_ENTRY_AREA_TOP) + PAGE_SIZE);
+	shadow_cpu_entry_end = kasan_mem_to_shadow(shadow_cpu_entry_end);
+	shadow_cpu_entry_end = (void *)round_up((unsigned long)shadow_cpu_entry_end,
+					PAGE_SIZE);
+
 	kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END),
-			(void *)KASAN_SHADOW_END);
+				   shadow_cpu_entry_begin);
+
+	kasan_populate_shadow((unsigned long)shadow_cpu_entry_begin,
+			      (unsigned long)shadow_cpu_entry_end, 0);
+
+	kasan_populate_zero_shadow(shadow_cpu_entry_end, (void *)KASAN_SHADOW_END);
 
 	load_cr3(init_top_pgt);
 	__flush_tlb_all();

arch/x86/power/cpu.c

@@ -152,17 +152,19 @@ static void do_fpu_end(void)
 static void fix_processor_context(void)
 {
 	int cpu = smp_processor_id();
-	struct tss_struct *t = &per_cpu(cpu_tss, cpu);
 #ifdef CONFIG_X86_64
 	struct desc_struct *desc = get_cpu_gdt_rw(cpu);
 	tss_desc tss;
 #endif
-	set_tss_desc(cpu, t);	/*
-				 * This just modifies memory; should not be
-				 * necessary. But... This is necessary, because
-				 * 386 hardware has concept of busy TSS or some
-				 * similar stupidity.
-				 */
+
+	/*
+	 * We need to reload TR, which requires that we change the
+	 * GDT entry to indicate "available" first.
+	 *
+	 * XXX: This could probably all be replaced by a call to
+	 * force_reload_TR().
+	 */
+	set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
 
 #ifdef CONFIG_X86_64
 	memcpy(&tss, &desc[GDT_ENTRY_TSS], sizeof(tss_desc));

arch/x86/xen/enlighten_pv.c

@@ -826,7 +826,7 @@ static void xen_load_sp0(unsigned long sp0)
 	mcs = xen_mc_entry(0);
 	MULTI_stack_switch(mcs.mc, __KERNEL_DS, sp0);
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
-	this_cpu_write(cpu_tss.x86_tss.sp0, sp0);
+	this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0);
 }
 
 void xen_set_iopl_mask(unsigned mask)

arch/x86/xen/mmu_pv.c

@@ -2272,7 +2272,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #endif
 	case FIX_TEXT_POKE0:
 	case FIX_TEXT_POKE1:
-	case FIX_GDT_REMAP_BEGIN ... FIX_GDT_REMAP_END:
+	case FIX_CPU_ENTRY_AREA_TOP ... FIX_CPU_ENTRY_AREA_BOTTOM:
 		/* All local page mappings */
 		pte = pfn_pte(phys, prot);
 		break;