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

Pull x86 irq updates from Ingo Molnar:
 "Here are the main changes in this tree:

   - Introduce x86-64 IRQ/exception/debug stack guard pages to detect
     stack overflows immediately and deterministically.

   - Clean up over a decade worth of cruft accumulated.

  The outcome of this should be more clear-cut faults/crashes when any
  of the low level x86 CPU stacks overflow, instead of silent memory
  corruption and sporadic failures much later on"

* 'x86-irq-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (33 commits)
  x86/irq: Fix outdated comments
  x86/irq/64: Remove stack overflow debug code
  x86/irq/64: Remap the IRQ stack with guard pages
  x86/irq/64: Split the IRQ stack into its own pages
  x86/irq/64: Init hardirq_stack_ptr during CPU hotplug
  x86/irq/32: Handle irq stack allocation failure proper
  x86/irq/32: Invoke irq_ctx_init() from init_IRQ()
  x86/irq/64: Rename irq_stack_ptr to hardirq_stack_ptr
  x86/irq/32: Rename hard/softirq_stack to hard/softirq_stack_ptr
  x86/irq/32: Make irq stack a character array
  x86/irq/32: Define IRQ_STACK_SIZE
  x86/dumpstack/64: Speedup in_exception_stack()
  x86/exceptions: Split debug IST stack
  x86/exceptions: Enable IST guard pages
  x86/exceptions: Disconnect IST index and stack order
  x86/cpu: Remove orig_ist array
  x86/cpu: Prepare TSS.IST setup for guard pages
  x86/dumpstack/64: Use cpu_entry_area instead of orig_ist
  x86/irq/64: Use cpu entry area instead of orig_ist
  x86/traps: Use cpu_entry_area instead of orig_ist
  ...

Documentation/x86/kernel-stacks

@@ -59,7 +59,7 @@ If that assumption is ever broken then the stacks will become corrupt.
 
 The currently assigned IST stacks are :-
 
-* DOUBLEFAULT_STACK.  EXCEPTION_STKSZ (PAGE_SIZE).
+* ESTACK_DF.  EXCEPTION_STKSZ (PAGE_SIZE).
 
   Used for interrupt 8 - Double Fault Exception (#DF).
 
@@ -68,7 +68,7 @@ The currently assigned IST stacks are :-
   Using a separate stack allows the kernel to recover from it well enough
   in many cases to still output an oops.
 
-* NMI_STACK.  EXCEPTION_STKSZ (PAGE_SIZE).
+* ESTACK_NMI.  EXCEPTION_STKSZ (PAGE_SIZE).
 
   Used for non-maskable interrupts (NMI).
 
@@ -76,7 +76,7 @@ The currently assigned IST stacks are :-
   middle of switching stacks.  Using IST for NMI events avoids making
   assumptions about the previous state of the kernel stack.
 
-* DEBUG_STACK.  DEBUG_STKSZ
+* ESTACK_DB.  EXCEPTION_STKSZ (PAGE_SIZE).
 
   Used for hardware debug interrupts (interrupt 1) and for software
   debug interrupts (INT3).
@@ -86,7 +86,12 @@ The currently assigned IST stacks are :-
   avoids making assumptions about the previous state of the kernel
   stack.
 
-* MCE_STACK.  EXCEPTION_STKSZ (PAGE_SIZE).
+  To handle nested #DB correctly there exist two instances of DB stacks. On
+  #DB entry the IST stackpointer for #DB is switched to the second instance
+  so a nested #DB starts from a clean stack. The nested #DB switches
+  the IST stackpointer to a guard hole to catch triple nesting.
+
+* ESTACK_MCE.  EXCEPTION_STKSZ (PAGE_SIZE).
 
   Used for interrupt 18 - Machine Check Exception (#MC).
 

arch/x86/Kconfig

@@ -14,6 +14,7 @@ config X86_32
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select CLKSRC_I8253
 	select CLONE_BACKWARDS
+	select HAVE_DEBUG_STACKOVERFLOW
 	select MODULES_USE_ELF_REL
 	select OLD_SIGACTION
 
@@ -138,7 +139,6 @@ config X86
 	select HAVE_COPY_THREAD_TLS
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_DEBUG_KMEMLEAK
-	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS

arch/x86/entry/entry_64.S

@@ -298,7 +298,7 @@ ENTRY(__switch_to_asm)
 
 #ifdef CONFIG_STACKPROTECTOR
 	movq	TASK_stack_canary(%rsi), %rbx
-	movq	%rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset
+	movq	%rbx, PER_CPU_VAR(fixed_percpu_data) + stack_canary_offset
 #endif
 
 #ifdef CONFIG_RETPOLINE
@@ -430,8 +430,8 @@ END(irq_entries_start)
 	 * it before we actually move ourselves to the IRQ stack.
 	 */
 
-	movq	\old_rsp, PER_CPU_VAR(irq_stack_union + IRQ_STACK_SIZE - 8)
+	movq	\old_rsp, PER_CPU_VAR(irq_stack_backing_store + IRQ_STACK_SIZE - 8)
-	movq	PER_CPU_VAR(irq_stack_ptr), %rsp
+	movq	PER_CPU_VAR(hardirq_stack_ptr), %rsp
 
 #ifdef CONFIG_DEBUG_ENTRY
 	/*
@@ -840,7 +840,7 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
 /*
  * Exception entry points.
  */
-#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8)
+#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + (x) * 8)
 
 /**
  * idtentry - Generate an IDT entry stub
@@ -878,7 +878,7 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
  * @paranoid == 2 is special: the stub will never switch stacks.  This is for
  * #DF: if the thread stack is somehow unusable, we'll still get a useful OOPS.
  */
-.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
+.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ist_offset=0
 ENTRY(\sym)
 	UNWIND_HINT_IRET_REGS offset=\has_error_code*8
 
@@ -924,13 +924,13 @@ ENTRY(\sym)
 	.endif
 
 	.if \shift_ist != -1
-	subq	$EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
+	subq	$\ist_offset, CPU_TSS_IST(\shift_ist)
 	.endif
 
 	call	\do_sym
 
 	.if \shift_ist != -1
-	addq	$EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
+	addq	$\ist_offset, CPU_TSS_IST(\shift_ist)
 	.endif
 
 	/* these procedures expect "no swapgs" flag in ebx */
@@ -1128,7 +1128,7 @@ apicinterrupt3 HYPERV_STIMER0_VECTOR \
 	hv_stimer0_callback_vector hv_stimer0_vector_handler
 #endif /* CONFIG_HYPERV */
 
-idtentry debug			do_debug		has_error_code=0	paranoid=1 shift_ist=DEBUG_STACK
+idtentry debug			do_debug		has_error_code=0	paranoid=1 shift_ist=IST_INDEX_DB ist_offset=DB_STACK_OFFSET
 idtentry int3			do_int3			has_error_code=0
 idtentry stack_segment		do_stack_segment	has_error_code=1
 

arch/x86/include/asm/cpu_entry_area.h

@@ -7,6 +7,64 @@
 #include <asm/processor.h>
 #include <asm/intel_ds.h>
 
+#ifdef CONFIG_X86_64
+
+/* Macro to enforce the same ordering and stack sizes */
+#define ESTACKS_MEMBERS(guardsize, db2_holesize)\
+	char	DF_stack_guard[guardsize];	\
+	char	DF_stack[EXCEPTION_STKSZ];	\
+	char	NMI_stack_guard[guardsize];	\
+	char	NMI_stack[EXCEPTION_STKSZ];	\
+	char	DB2_stack_guard[guardsize];	\
+	char	DB2_stack[db2_holesize];	\
+	char	DB1_stack_guard[guardsize];	\
+	char	DB1_stack[EXCEPTION_STKSZ];	\
+	char	DB_stack_guard[guardsize];	\
+	char	DB_stack[EXCEPTION_STKSZ];	\
+	char	MCE_stack_guard[guardsize];	\
+	char	MCE_stack[EXCEPTION_STKSZ];	\
+	char	IST_top_guard[guardsize];	\
+
+/* The exception stacks' physical storage. No guard pages required */
+struct exception_stacks {
+	ESTACKS_MEMBERS(0, 0)
+};
+
+/* The effective cpu entry area mapping with guard pages. */
+struct cea_exception_stacks {
+	ESTACKS_MEMBERS(PAGE_SIZE, EXCEPTION_STKSZ)
+};
+
+/*
+ * The exception stack ordering in [cea_]exception_stacks
+ */
+enum exception_stack_ordering {
+	ESTACK_DF,
+	ESTACK_NMI,
+	ESTACK_DB2,
+	ESTACK_DB1,
+	ESTACK_DB,
+	ESTACK_MCE,
+	N_EXCEPTION_STACKS
+};
+
+#define CEA_ESTACK_SIZE(st)					\
+	sizeof(((struct cea_exception_stacks *)0)->st## _stack)
+
+#define CEA_ESTACK_BOT(ceastp, st)				\
+	((unsigned long)&(ceastp)->st## _stack)
+
+#define CEA_ESTACK_TOP(ceastp, st)				\
+	(CEA_ESTACK_BOT(ceastp, st) + CEA_ESTACK_SIZE(st))
+
+#define CEA_ESTACK_OFFS(st)					\
+	offsetof(struct cea_exception_stacks, st## _stack)
+
+#define CEA_ESTACK_PAGES					\
+	(sizeof(struct cea_exception_stacks) / PAGE_SIZE)
+
+#endif
+
 /*
  * cpu_entry_area is a percpu region that contains things needed by the CPU
  * and early entry/exit code.  Real types aren't used for all fields here
@@ -32,12 +90,9 @@ struct cpu_entry_area {
 
 #ifdef CONFIG_X86_64
 	/*
-	 * Exception stacks used for IST entries.
+	 * Exception stacks used for IST entries with guard pages.
-	 *
-	 * 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];
+	struct cea_exception_stacks estacks;
 #endif
 #ifdef CONFIG_CPU_SUP_INTEL
 	/*
@@ -57,6 +112,7 @@ struct cpu_entry_area {
 #define CPU_ENTRY_AREA_TOT_SIZE	(CPU_ENTRY_AREA_SIZE * NR_CPUS)
 
 DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
+DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks);
 
 extern void setup_cpu_entry_areas(void);
 extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags);
@@ -76,4 +132,7 @@ static inline struct entry_stack *cpu_entry_stack(int cpu)
 	return &get_cpu_entry_area(cpu)->entry_stack_page.stack;
 }
 
+#define __this_cpu_ist_top_va(name)					\
+	CEA_ESTACK_TOP(__this_cpu_read(cea_exception_stacks), name)
+
 #endif

arch/x86/include/asm/debugreg.h

@@ -104,11 +104,9 @@ static inline void debug_stack_usage_dec(void)
 {
 	__this_cpu_dec(debug_stack_usage);
 }
-int is_debug_stack(unsigned long addr);
 void debug_stack_set_zero(void);
 void debug_stack_reset(void);
 #else /* !X86_64 */
-static inline int is_debug_stack(unsigned long addr) { return 0; }
 static inline void debug_stack_set_zero(void) { }
 static inline void debug_stack_reset(void) { }
 static inline void debug_stack_usage_inc(void) { }

arch/x86/include/asm/irq.h

@@ -16,11 +16,7 @@ static inline int irq_canonicalize(int irq)
 	return ((irq == 2) ? 9 : irq);
 }
 
-#ifdef CONFIG_X86_32
+extern int irq_init_percpu_irqstack(unsigned int cpu);
-extern void irq_ctx_init(int cpu);
-#else
-# define irq_ctx_init(cpu) do { } while (0)
-#endif
 
 #define __ARCH_HAS_DO_SOFTIRQ
 

arch/x86/include/asm/irq_vectors.h

@@ -18,8 +18,8 @@
  *  Vectors   0 ...  31 : system traps and exceptions - hardcoded events
  *  Vectors  32 ... 127 : device interrupts
  *  Vector  128         : legacy int80 syscall interface
- *  Vectors 129 ... INVALIDATE_TLB_VECTOR_START-1 except 204 : device interrupts
+ *  Vectors 129 ... LOCAL_TIMER_VECTOR-1
- *  Vectors INVALIDATE_TLB_VECTOR_START ... 255 : special interrupts
+ *  Vectors LOCAL_TIMER_VECTOR ... 255 : special interrupts
  *
  * 64-bit x86 has per CPU IDT tables, 32-bit has one shared IDT table.
  *

arch/x86/include/asm/page_32_types.h

@@ -22,11 +22,9 @@
 #define THREAD_SIZE_ORDER	1
 #define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 
-#define DOUBLEFAULT_STACK 1
+#define IRQ_STACK_SIZE		THREAD_SIZE
-#define NMI_STACK 0
+
-#define DEBUG_STACK 0
+#define N_EXCEPTION_STACKS	1
-#define MCE_STACK 0
-#define N_EXCEPTION_STACKS 1
 
 #ifdef CONFIG_X86_PAE
 /*

arch/x86/include/asm/page_64_types.h

@@ -14,22 +14,20 @@
 
 #define THREAD_SIZE_ORDER	(2 + KASAN_STACK_ORDER)
 #define THREAD_SIZE  (PAGE_SIZE << THREAD_SIZE_ORDER)
-#define CURRENT_MASK (~(THREAD_SIZE - 1))
 
 #define EXCEPTION_STACK_ORDER (0 + KASAN_STACK_ORDER)
 #define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER)
 
-#define DEBUG_STACK_ORDER (EXCEPTION_STACK_ORDER + 1)
-#define DEBUG_STKSZ (PAGE_SIZE << DEBUG_STACK_ORDER)
-
 #define IRQ_STACK_ORDER (2 + KASAN_STACK_ORDER)
 #define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER)
 
-#define DOUBLEFAULT_STACK 1
+/*
-#define NMI_STACK 2
+ * The index for the tss.ist[] array. The hardware limit is 7 entries.
-#define DEBUG_STACK 3
+ */
-#define MCE_STACK 4
+#define	IST_INDEX_DF		0
-#define N_EXCEPTION_STACKS 4  /* hw limit: 7 */
+#define	IST_INDEX_NMI		1
+#define	IST_INDEX_DB		2
+#define	IST_INDEX_MCE		3
 
 /*
  * Set __PAGE_OFFSET to the most negative possible address +

arch/x86/include/asm/processor.h

@@ -367,6 +367,13 @@ DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw);
 #define __KERNEL_TSS_LIMIT	\
 	(IO_BITMAP_OFFSET + IO_BITMAP_BYTES + sizeof(unsigned long) - 1)
 
+/* Per CPU interrupt stacks */
+struct irq_stack {
+	char		stack[IRQ_STACK_SIZE];
+} __aligned(IRQ_STACK_SIZE);
+
+DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
+
 #ifdef CONFIG_X86_32
 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);
 #else
@@ -374,38 +381,25 @@ DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);
 #define cpu_current_top_of_stack cpu_tss_rw.x86_tss.sp1
 #endif
 
-/*
- * Save the original ist values for checking stack pointers during debugging
- */
-struct orig_ist {
-	unsigned long		ist[7];
-};
-
 #ifdef CONFIG_X86_64
-DECLARE_PER_CPU(struct orig_ist, orig_ist);
+struct fixed_percpu_data {
-
-union irq_stack_union {
-	char irq_stack[IRQ_STACK_SIZE];
 	/*
 	 * GCC hardcodes the stack canary as %gs:40.  Since the
 	 * irq_stack is the object at %gs:0, we reserve the bottom
 	 * 48 bytes of the irq stack for the canary.
 	 */
-	struct {
+	char		gs_base[40];
-		char gs_base[40];
+	unsigned long	stack_canary;
-		unsigned long stack_canary;
-	};
 };
 
-DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __visible;
+DECLARE_PER_CPU_FIRST(struct fixed_percpu_data, fixed_percpu_data) __visible;
-DECLARE_INIT_PER_CPU(irq_stack_union);
+DECLARE_INIT_PER_CPU(fixed_percpu_data);
 
 static inline unsigned long cpu_kernelmode_gs_base(int cpu)
 {
-	return (unsigned long)per_cpu(irq_stack_union.gs_base, cpu);
+	return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu);
 }
 
-DECLARE_PER_CPU(char *, irq_stack_ptr);
 DECLARE_PER_CPU(unsigned int, irq_count);
 extern asmlinkage void ignore_sysret(void);
 
@@ -427,15 +421,8 @@ struct stack_canary {
 };
 DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
 #endif
-/*
+/* Per CPU softirq stack pointer */
- * per-CPU IRQ handling stacks
+DECLARE_PER_CPU(struct irq_stack *, softirq_stack_ptr);
- */
-struct irq_stack {
-	u32                     stack[THREAD_SIZE/sizeof(u32)];
-} __aligned(THREAD_SIZE);
-
-DECLARE_PER_CPU(struct irq_stack *, hardirq_stack);
-DECLARE_PER_CPU(struct irq_stack *, softirq_stack);
 #endif	/* X86_64 */
 
 extern unsigned int fpu_kernel_xstate_size;

arch/x86/include/asm/smp.h

@@ -131,7 +131,7 @@ void native_smp_prepare_boot_cpu(void);
 void native_smp_prepare_cpus(unsigned int max_cpus);
 void calculate_max_logical_packages(void);
 void native_smp_cpus_done(unsigned int max_cpus);
-void common_cpu_up(unsigned int cpunum, struct task_struct *tidle);
+int common_cpu_up(unsigned int cpunum, struct task_struct *tidle);
 int native_cpu_up(unsigned int cpunum, struct task_struct *tidle);
 int native_cpu_disable(void);
 int common_cpu_die(unsigned int cpu);

arch/x86/include/asm/stackprotector.h

@@ -13,7 +13,7 @@
  * On x86_64, %gs is shared by percpu area and stack canary.  All
  * percpu symbols are zero based and %gs points to the base of percpu
  * area.  The first occupant of the percpu area is always
- * irq_stack_union which contains stack_canary at offset 40.  Userland
+ * fixed_percpu_data which contains stack_canary at offset 40.  Userland
  * %gs is always saved and restored on kernel entry and exit using
  * swapgs, so stack protector doesn't add any complexity there.
  *
@@ -64,7 +64,7 @@ static __always_inline void boot_init_stack_canary(void)
 	u64 tsc;
 
 #ifdef CONFIG_X86_64
-	BUILD_BUG_ON(offsetof(union irq_stack_union, stack_canary) != 40);
+	BUILD_BUG_ON(offsetof(struct fixed_percpu_data, stack_canary) != 40);
 #endif
 	/*
 	 * We both use the random pool and the current TSC as a source
@@ -79,7 +79,7 @@ static __always_inline void boot_init_stack_canary(void)
 
 	current->stack_canary = canary;
 #ifdef CONFIG_X86_64
-	this_cpu_write(irq_stack_union.stack_canary, canary);
+	this_cpu_write(fixed_percpu_data.stack_canary, canary);
 #else
 	this_cpu_write(stack_canary.canary, canary);
 #endif

arch/x86/include/asm/stacktrace.h

@@ -9,6 +9,8 @@
 
 #include <linux/uaccess.h>
 #include <linux/ptrace.h>
+
+#include <asm/cpu_entry_area.h>
 #include <asm/switch_to.h>
 
 enum stack_type {

arch/x86/kernel/asm-offsets_64.c

@@ -68,10 +68,12 @@ int main(void)
 #undef ENTRY
 
 	OFFSET(TSS_ist, tss_struct, x86_tss.ist);
+	DEFINE(DB_STACK_OFFSET, offsetof(struct cea_exception_stacks, DB_stack) -
+	       offsetof(struct cea_exception_stacks, DB1_stack));
 	BLANK();
 
 #ifdef CONFIG_STACKPROTECTOR
-	DEFINE(stack_canary_offset, offsetof(union irq_stack_union, stack_canary));
+	DEFINE(stack_canary_offset, offsetof(struct fixed_percpu_data, stack_canary));
 	BLANK();
 #endif
 

arch/x86/kernel/cpu/common.c

@@ -507,19 +507,6 @@ void load_percpu_segment(int cpu)
 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
-};
-#endif
-
 /* Load the original GDT from the per-cpu structure */
 void load_direct_gdt(int cpu)
 {
@@ -1511,9 +1498,9 @@ static __init int setup_clearcpuid(char *arg)
 __setup("clearcpuid=", setup_clearcpuid);
 
 #ifdef CONFIG_X86_64
-DEFINE_PER_CPU_FIRST(union irq_stack_union,
+DEFINE_PER_CPU_FIRST(struct fixed_percpu_data,
-		     irq_stack_union) __aligned(PAGE_SIZE) __visible;
+		     fixed_percpu_data) __aligned(PAGE_SIZE) __visible;
-EXPORT_PER_CPU_SYMBOL_GPL(irq_stack_union);
+EXPORT_PER_CPU_SYMBOL_GPL(fixed_percpu_data);
 
 /*
  * The following percpu variables are hot.  Align current_task to
@@ -1523,9 +1510,7 @@ DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned =
 	&init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
 
-DEFINE_PER_CPU(char *, irq_stack_ptr) =
+DEFINE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
-	init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE;
-
 DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
 
 DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
@@ -1562,23 +1547,7 @@ void syscall_init(void)
 	       X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT);
 }
 
-/*
- * Copies of the original ist values from the tss are only accessed during
- * debugging, no special alignment required.
- */
-DEFINE_PER_CPU(struct orig_ist, orig_ist);
-
-static DEFINE_PER_CPU(unsigned long, debug_stack_addr);
 DEFINE_PER_CPU(int, debug_stack_usage);
-
-int is_debug_stack(unsigned long addr)
-{
-	return __this_cpu_read(debug_stack_usage) ||
-		(addr <= __this_cpu_read(debug_stack_addr) &&
-		 addr > (__this_cpu_read(debug_stack_addr) - DEBUG_STKSZ));
-}
-NOKPROBE_SYMBOL(is_debug_stack);
-
 DEFINE_PER_CPU(u32, debug_idt_ctr);
 
 void debug_stack_set_zero(void)
@@ -1690,17 +1659,14 @@ static void setup_getcpu(int cpu)
  * initialized (naturally) in the bootstrap process, such as the GDT
  * and IDT. We reload them nevertheless, this function acts as a
  * 'CPU state barrier', nothing should get across.
- * A lot of state is already set up in PDA init for 64 bit
  */
 #ifdef CONFIG_X86_64
 
 void cpu_init(void)
 {
-	struct orig_ist *oist;
+	int cpu = raw_smp_processor_id();
 	struct task_struct *me;
 	struct tss_struct *t;
-	unsigned long v;
-	int cpu = raw_smp_processor_id();
 	int i;
 
 	wait_for_master_cpu(cpu);
@@ -1715,7 +1681,6 @@ void cpu_init(void)
 		load_ucode_ap();
 
 	t = &per_cpu(cpu_tss_rw, cpu);
-	oist = &per_cpu(orig_ist, cpu);
 
 #ifdef CONFIG_NUMA
 	if (this_cpu_read(numa_node) == 0 &&
@@ -1753,16 +1718,11 @@ void cpu_init(void)
 	/*
 	 * set up and load the per-CPU TSS
 	 */
-	if (!oist->ist[0]) {
+	if (!t->x86_tss.ist[0]) {
-		char *estacks = get_cpu_entry_area(cpu)->exception_stacks;
+		t->x86_tss.ist[IST_INDEX_DF] = __this_cpu_ist_top_va(DF);
-
+		t->x86_tss.ist[IST_INDEX_NMI] = __this_cpu_ist_top_va(NMI);
-		for (v = 0; v < N_EXCEPTION_STACKS; v++) {
+		t->x86_tss.ist[IST_INDEX_DB] = __this_cpu_ist_top_va(DB);
-			estacks += exception_stack_sizes[v];
+		t->x86_tss.ist[IST_INDEX_MCE] = __this_cpu_ist_top_va(MCE);
-			oist->ist[v] = t->x86_tss.ist[v] =
-					(unsigned long)estacks;
-			if (v == DEBUG_STACK-1)
-				per_cpu(debug_stack_addr, cpu) = (unsigned long)estacks;
-		}
 	}
 
 	t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;

arch/x86/kernel/dumpstack_32.c

@@ -34,14 +34,14 @@ const char *stack_type_name(enum stack_type type)
 
 static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *begin = (unsigned long *)this_cpu_read(hardirq_stack);
+	unsigned long *begin = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
 	unsigned long *end   = begin + (THREAD_SIZE / sizeof(long));
 
 	/*
 	 * This is a software stack, so 'end' can be a valid stack pointer.
 	 * It just means the stack is empty.
 	 */
-	if (stack <= begin || stack > end)
+	if (stack < begin || stack > end)
 		return false;
 
 	info->type	= STACK_TYPE_IRQ;
@@ -59,14 +59,14 @@ static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)
 
 static bool in_softirq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *begin = (unsigned long *)this_cpu_read(softirq_stack);
+	unsigned long *begin = (unsigned long *)this_cpu_read(softirq_stack_ptr);
 	unsigned long *end   = begin + (THREAD_SIZE / sizeof(long));
 
 	/*
 	 * This is a software stack, so 'end' can be a valid stack pointer.
 	 * It just means the stack is empty.
 	 */
-	if (stack <= begin || stack > end)
+	if (stack < begin || stack > end)
 		return false;
 
 	info->type	= STACK_TYPE_SOFTIRQ;

arch/x86/kernel/dumpstack_64.c

@@ -16,23 +16,21 @@
 #include <linux/bug.h>
 #include <linux/nmi.h>
 
+#include <asm/cpu_entry_area.h>
 #include <asm/stacktrace.h>
 
-static char *exception_stack_names[N_EXCEPTION_STACKS] = {
+static const char * const exception_stack_names[] = {
-		[ DOUBLEFAULT_STACK-1	]	= "#DF",
+		[ ESTACK_DF	]	= "#DF",
-		[ NMI_STACK-1		]	= "NMI",
+		[ ESTACK_NMI	]	= "NMI",
-		[ DEBUG_STACK-1		]	= "#DB",
+		[ ESTACK_DB2	]	= "#DB2",
-		[ MCE_STACK-1		]	= "#MC",
+		[ ESTACK_DB1	]	= "#DB1",
-};
+		[ ESTACK_DB	]	= "#DB",
-
+		[ ESTACK_MCE	]	= "#MC",
-static unsigned long exception_stack_sizes[N_EXCEPTION_STACKS] = {
-	[0 ... N_EXCEPTION_STACKS - 1]		= EXCEPTION_STKSZ,
-	[DEBUG_STACK - 1]			= DEBUG_STKSZ
 };
 
 const char *stack_type_name(enum stack_type type)
 {
-	BUILD_BUG_ON(N_EXCEPTION_STACKS != 4);
+	BUILD_BUG_ON(N_EXCEPTION_STACKS != 6);
 
 	if (type == STACK_TYPE_IRQ)
 		return "IRQ";
@@ -52,43 +50,84 @@ const char *stack_type_name(enum stack_type type)
 	return NULL;
 }
 
+/**
+ * struct estack_pages - Page descriptor for exception stacks
+ * @offs:	Offset from the start of the exception stack area
+ * @size:	Size of the exception stack
+ * @type:	Type to store in the stack_info struct
+ */
+struct estack_pages {
+	u32	offs;
+	u16	size;
+	u16	type;
+};
+
+#define EPAGERANGE(st)							\
+	[PFN_DOWN(CEA_ESTACK_OFFS(st)) ...				\
+	 PFN_DOWN(CEA_ESTACK_OFFS(st) + CEA_ESTACK_SIZE(st) - 1)] = {	\
+		.offs	= CEA_ESTACK_OFFS(st),				\
+		.size	= CEA_ESTACK_SIZE(st),				\
+		.type	= STACK_TYPE_EXCEPTION + ESTACK_ ##st, }
+
+/*
+ * Array of exception stack page descriptors. If the stack is larger than
+ * PAGE_SIZE, all pages covering a particular stack will have the same
+ * info. The guard pages including the not mapped DB2 stack are zeroed
+ * out.
+ */
+static const
+struct estack_pages estack_pages[CEA_ESTACK_PAGES] ____cacheline_aligned = {
+	EPAGERANGE(DF),
+	EPAGERANGE(NMI),
+	EPAGERANGE(DB1),
+	EPAGERANGE(DB),
+	EPAGERANGE(MCE),
+};
+
 static bool in_exception_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *begin, *end;
+	unsigned long begin, end, stk = (unsigned long)stack;
+	const struct estack_pages *ep;
 	struct pt_regs *regs;
-	unsigned k;
+	unsigned int k;
 
-	BUILD_BUG_ON(N_EXCEPTION_STACKS != 4);
+	BUILD_BUG_ON(N_EXCEPTION_STACKS != 6);
 
-	for (k = 0; k < N_EXCEPTION_STACKS; k++) {
+	begin = (unsigned long)__this_cpu_read(cea_exception_stacks);
-		end   = (unsigned long *)raw_cpu_ptr(&orig_ist)->ist[k];
+	end = begin + sizeof(struct cea_exception_stacks);
-		begin = end - (exception_stack_sizes[k] / sizeof(long));
+	/* Bail if @stack is outside the exception stack area. */
-		regs  = (struct pt_regs *)end - 1;
+	if (stk < begin || stk >= end)
+		return false;
 
-		if (stack <= begin || stack >= end)
+	/* Calc page offset from start of exception stacks */
-			continue;
+	k = (stk - begin) >> PAGE_SHIFT;
+	/* Lookup the page descriptor */
+	ep = &estack_pages[k];
+	/* Guard page? */
+	if (!ep->size)
+		return false;
 
-		info->type	= STACK_TYPE_EXCEPTION + k;
+	begin += (unsigned long)ep->offs;
-		info->begin	= begin;
+	end = begin + (unsigned long)ep->size;
-		info->end	= end;
+	regs = (struct pt_regs *)end - 1;
-		info->next_sp	= (unsigned long *)regs->sp;
 
-		return true;
+	info->type	= ep->type;
-	}
+	info->begin	= (unsigned long *)begin;
-
+	info->end	= (unsigned long *)end;
-	return false;
+	info->next_sp	= (unsigned long *)regs->sp;
+	return true;
 }
 
 static bool in_irq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *end   = (unsigned long *)this_cpu_read(irq_stack_ptr);
+	unsigned long *end   = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
 	unsigned long *begin = end - (IRQ_STACK_SIZE / sizeof(long));
 
 	/*
 	 * This is a software stack, so 'end' can be a valid stack pointer.
 	 * It just means the stack is empty.
 	 */
-	if (stack <= begin || stack > end)
+	if (stack < begin || stack >= end)
 		return false;
 
 	info->type	= STACK_TYPE_IRQ;

arch/x86/kernel/head_64.S

@@ -265,7 +265,7 @@ ENDPROC(start_cpu0)
 	GLOBAL(initial_code)
 	.quad	x86_64_start_kernel
 	GLOBAL(initial_gs)
-	.quad	INIT_PER_CPU_VAR(irq_stack_union)
+	.quad	INIT_PER_CPU_VAR(fixed_percpu_data)
 	GLOBAL(initial_stack)
 	/*
 	 * The SIZEOF_PTREGS gap is a convention which helps the in-kernel

arch/x86/kernel/idt.c

@@ -41,13 +41,12 @@ struct idt_data {
 #define SYSG(_vector, _addr)				\
 	G(_vector, _addr, DEFAULT_STACK, GATE_INTERRUPT, DPL3, __KERNEL_CS)
 
-/* Interrupt gate with interrupt stack */
+/*
+ * Interrupt gate with interrupt stack. The _ist index is the index in
+ * the tss.ist[] array, but for the descriptor it needs to start at 1.
+ */
 #define ISTG(_vector, _addr, _ist)			\
-	G(_vector, _addr, _ist, GATE_INTERRUPT, DPL0, __KERNEL_CS)
+	G(_vector, _addr, _ist + 1, GATE_INTERRUPT, DPL0, __KERNEL_CS)
-
-/* System interrupt gate with interrupt stack */
-#define SISTG(_vector, _addr, _ist)			\
-	G(_vector, _addr, _ist, GATE_INTERRUPT, DPL3, __KERNEL_CS)
 
 /* Task gate */
 #define TSKG(_vector, _gdt)				\
@@ -184,11 +183,11 @@ gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss;
  * cpu_init() when the TSS has been initialized.
  */
 static const __initconst struct idt_data ist_idts[] = {
-	ISTG(X86_TRAP_DB,	debug,		DEBUG_STACK),
+	ISTG(X86_TRAP_DB,	debug,		IST_INDEX_DB),
-	ISTG(X86_TRAP_NMI,	nmi,		NMI_STACK),
+	ISTG(X86_TRAP_NMI,	nmi,		IST_INDEX_NMI),
-	ISTG(X86_TRAP_DF,	double_fault,	DOUBLEFAULT_STACK),
+	ISTG(X86_TRAP_DF,	double_fault,	IST_INDEX_DF),
 #ifdef CONFIG_X86_MCE
-	ISTG(X86_TRAP_MC,	&machine_check,	MCE_STACK),
+	ISTG(X86_TRAP_MC,	&machine_check,	IST_INDEX_MCE),
 #endif
 };
 

arch/x86/kernel/irq_32.c

@@ -51,8 +51,8 @@ static inline int check_stack_overflow(void) { return 0; }
 static inline void print_stack_overflow(void) { }
 #endif
 
-DEFINE_PER_CPU(struct irq_stack *, hardirq_stack);
+DEFINE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
-DEFINE_PER_CPU(struct irq_stack *, softirq_stack);
+DEFINE_PER_CPU(struct irq_stack *, softirq_stack_ptr);
 
 static void call_on_stack(void *func, void *stack)
 {
@@ -76,7 +76,7 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 	u32 *isp, *prev_esp, arg1;
 
 	curstk = (struct irq_stack *) current_stack();
-	irqstk = __this_cpu_read(hardirq_stack);
+	irqstk = __this_cpu_read(hardirq_stack_ptr);
 
 	/*
 	 * this is where we switch to the IRQ stack. However, if we are
@@ -107,27 +107,28 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 }
 
 /*
- * allocate per-cpu stacks for hardirq and for softirq processing
+ * Allocate per-cpu stacks for hardirq and softirq processing
  */
-void irq_ctx_init(int cpu)
+int irq_init_percpu_irqstack(unsigned int cpu)
 {
-	struct irq_stack *irqstk;
+	int node = cpu_to_node(cpu);
+	struct page *ph, *ps;
 
-	if (per_cpu(hardirq_stack, cpu))
+	if (per_cpu(hardirq_stack_ptr, cpu))
-		return;
+		return 0;
 
-	irqstk = page_address(alloc_pages_node(cpu_to_node(cpu),
+	ph = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER);
-					       THREADINFO_GFP,
+	if (!ph)
-					       THREAD_SIZE_ORDER));
+		return -ENOMEM;
-	per_cpu(hardirq_stack, cpu) = irqstk;
+	ps = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER);
+	if (!ps) {
+		__free_pages(ph, THREAD_SIZE_ORDER);
+		return -ENOMEM;
+	}
 
-	irqstk = page_address(alloc_pages_node(cpu_to_node(cpu),
+	per_cpu(hardirq_stack_ptr, cpu) = page_address(ph);
-					       THREADINFO_GFP,
+	per_cpu(softirq_stack_ptr, cpu) = page_address(ps);
-					       THREAD_SIZE_ORDER));
+	return 0;
-	per_cpu(softirq_stack, cpu) = irqstk;
-
-	printk(KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n",
-	       cpu, per_cpu(hardirq_stack, cpu),  per_cpu(softirq_stack, cpu));
 }
 
 void do_softirq_own_stack(void)
@@ -135,7 +136,7 @@ void do_softirq_own_stack(void)
 	struct irq_stack *irqstk;
 	u32 *isp, *prev_esp;
 
-	irqstk = __this_cpu_read(softirq_stack);
+	irqstk = __this_cpu_read(softirq_stack_ptr);
 
 	/* build the stack frame on the softirq stack */
 	isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));

arch/x86/kernel/irq_64.c

@@ -18,63 +18,64 @@
 #include <linux/uaccess.h>
 #include <linux/smp.h>
 #include <linux/sched/task_stack.h>
+
+#include <asm/cpu_entry_area.h>
 #include <asm/io_apic.h>
 #include <asm/apic.h>
 
-int sysctl_panic_on_stackoverflow;
+DEFINE_PER_CPU_PAGE_ALIGNED(struct irq_stack, irq_stack_backing_store) __visible;
-
+DECLARE_INIT_PER_CPU(irq_stack_backing_store);
-/*
- * Probabilistic stack overflow check:
- *
- * Only check the stack in process context, because everything else
- * runs on the big interrupt stacks. Checking reliably is too expensive,
- * so we just check from interrupts.
- */
-static inline void stack_overflow_check(struct pt_regs *regs)
-{
-#ifdef CONFIG_DEBUG_STACKOVERFLOW
-#define STACK_TOP_MARGIN	128
-	struct orig_ist *oist;
-	u64 irq_stack_top, irq_stack_bottom;
-	u64 estack_top, estack_bottom;
-	u64 curbase = (u64)task_stack_page(current);
-
-	if (user_mode(regs))
-		return;
-
-	if (regs->sp >= curbase + sizeof(struct pt_regs) + STACK_TOP_MARGIN &&
-	    regs->sp <= curbase + THREAD_SIZE)
-		return;
-
-	irq_stack_top = (u64)this_cpu_ptr(irq_stack_union.irq_stack) +
-			STACK_TOP_MARGIN;
-	irq_stack_bottom = (u64)__this_cpu_read(irq_stack_ptr);
-	if (regs->sp >= irq_stack_top && regs->sp <= irq_stack_bottom)
-		return;
-
-	oist = this_cpu_ptr(&orig_ist);
-	estack_top = (u64)oist->ist[0] - EXCEPTION_STKSZ + STACK_TOP_MARGIN;
-	estack_bottom = (u64)oist->ist[N_EXCEPTION_STACKS - 1];
-	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,ip:%pF)\n",
-		current->comm, curbase, regs->sp,
-		irq_stack_top, irq_stack_bottom,
-		estack_top, estack_bottom, (void *)regs->ip);
-
-	if (sysctl_panic_on_stackoverflow)
-		panic("low stack detected by irq handler - check messages\n");
-#endif
-}
 
 bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
 {
-	stack_overflow_check(regs);
-
 	if (IS_ERR_OR_NULL(desc))
 		return false;
 
 	generic_handle_irq_desc(desc);
 	return true;
 }
+
+#ifdef CONFIG_VMAP_STACK
+/*
+ * VMAP the backing store with guard pages
+ */
+static int map_irq_stack(unsigned int cpu)
+{
+	char *stack = (char *)per_cpu_ptr(&irq_stack_backing_store, cpu);
+	struct page *pages[IRQ_STACK_SIZE / PAGE_SIZE];
+	void *va;
+	int i;
+
+	for (i = 0; i < IRQ_STACK_SIZE / PAGE_SIZE; i++) {
+		phys_addr_t pa = per_cpu_ptr_to_phys(stack + (i << PAGE_SHIFT));
+
+		pages[i] = pfn_to_page(pa >> PAGE_SHIFT);
+	}
+
+	va = vmap(pages, IRQ_STACK_SIZE / PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL);
+	if (!va)
+		return -ENOMEM;
+
+	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE;
+	return 0;
+}
+#else
+/*
+ * If VMAP stacks are disabled due to KASAN, just use the per cpu
+ * backing store without guard pages.
+ */
+static int map_irq_stack(unsigned int cpu)
+{
+	void *va = per_cpu_ptr(&irq_stack_backing_store, cpu);
+
+	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE;
+	return 0;
+}
+#endif
+
+int irq_init_percpu_irqstack(unsigned int cpu)
+{
+	if (per_cpu(hardirq_stack_ptr, cpu))
+		return 0;
+	return map_irq_stack(cpu);
+}

arch/x86/kernel/irqinit.c

@@ -91,6 +91,8 @@ void __init init_IRQ(void)
 	for (i = 0; i < nr_legacy_irqs(); i++)
 		per_cpu(vector_irq, 0)[ISA_IRQ_VECTOR(i)] = irq_to_desc(i);
 
+	BUG_ON(irq_init_percpu_irqstack(smp_processor_id()));
+
 	x86_init.irqs.intr_init();
 }
 
@@ -104,6 +106,4 @@ void __init native_init_IRQ(void)
 
 	if (!acpi_ioapic && !of_ioapic && nr_legacy_irqs())
 		setup_irq(2, &irq2);
-
-	irq_ctx_init(smp_processor_id());
 }

arch/x86/kernel/nmi.c

@@ -21,13 +21,14 @@
 #include <linux/ratelimit.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/atomic.h>
 #include <linux/sched/clock.h>
 
 #if defined(CONFIG_EDAC)
 #include <linux/edac.h>
 #endif
 
-#include <linux/atomic.h>
+#include <asm/cpu_entry_area.h>
 #include <asm/traps.h>
 #include <asm/mach_traps.h>
 #include <asm/nmi.h>
@@ -487,6 +488,23 @@ static DEFINE_PER_CPU(unsigned long, nmi_cr2);
  * switch back to the original IDT.
  */
 static DEFINE_PER_CPU(int, update_debug_stack);
+
+static bool notrace is_debug_stack(unsigned long addr)
+{
+	struct cea_exception_stacks *cs = __this_cpu_read(cea_exception_stacks);
+	unsigned long top = CEA_ESTACK_TOP(cs, DB);
+	unsigned long bot = CEA_ESTACK_BOT(cs, DB1);
+
+	if (__this_cpu_read(debug_stack_usage))
+		return true;
+	/*
+	 * Note, this covers the guard page between DB and DB1 as well to
+	 * avoid two checks. But by all means @addr can never point into
+	 * the guard page.
+	 */
+	return addr >= bot && addr < top;
+}
+NOKPROBE_SYMBOL(is_debug_stack);
 #endif
 
 dotraplinkage notrace void

arch/x86/kernel/setup_percpu.c

@@ -244,11 +244,6 @@ void __init setup_per_cpu_areas(void)
 		per_cpu(x86_cpu_to_logical_apicid, cpu) =
 			early_per_cpu_map(x86_cpu_to_logical_apicid, cpu);
 #endif
-#ifdef CONFIG_X86_64
-		per_cpu(irq_stack_ptr, cpu) =
-			per_cpu(irq_stack_union.irq_stack, cpu) +
-			IRQ_STACK_SIZE;
-#endif
 #ifdef CONFIG_NUMA
 		per_cpu(x86_cpu_to_node_map, cpu) =
 			early_per_cpu_map(x86_cpu_to_node_map, cpu);

arch/x86/kernel/smpboot.c

@@ -935,20 +935,27 @@ out:
 	return boot_error;
 }
 
-void common_cpu_up(unsigned int cpu, struct task_struct *idle)
+int common_cpu_up(unsigned int cpu, struct task_struct *idle)
 {
+	int ret;
+
 	/* Just in case we booted with a single CPU. */
 	alternatives_enable_smp();
 
 	per_cpu(current_task, cpu) = idle;
 
+	/* Initialize the interrupt stack(s) */
+	ret = irq_init_percpu_irqstack(cpu);
+	if (ret)
+		return ret;
+
 #ifdef CONFIG_X86_32
 	/* Stack for startup_32 can be just as for start_secondary onwards */
-	irq_ctx_init(cpu);
 	per_cpu(cpu_current_top_of_stack, cpu) = task_top_of_stack(idle);
 #else
 	initial_gs = per_cpu_offset(cpu);
 #endif
+	return 0;
 }
 
 /*
@@ -1106,7 +1113,9 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 	/* the FPU context is blank, nobody can own it */
 	per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL;
 
-	common_cpu_up(cpu, tidle);
+	err = common_cpu_up(cpu, tidle);
+	if (err)
+		return err;
 
 	err = do_boot_cpu(apicid, cpu, tidle, &cpu0_nmi_registered);
 	if (err) {

arch/x86/kernel/vmlinux.lds.S

@@ -403,7 +403,8 @@ SECTIONS
  */
 #define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x) + __per_cpu_load
 INIT_PER_CPU(gdt_page);
-INIT_PER_CPU(irq_stack_union);
+INIT_PER_CPU(fixed_percpu_data);
+INIT_PER_CPU(irq_stack_backing_store);
 
 /*
  * Build-time check on the image size:
@@ -412,8 +413,8 @@ INIT_PER_CPU(irq_stack_union);
 	   "kernel image bigger than KERNEL_IMAGE_SIZE");
 
 #ifdef CONFIG_SMP
-. = ASSERT((irq_stack_union == 0),
+. = ASSERT((fixed_percpu_data == 0),
-           "irq_stack_union is not at start of per-cpu area");
+           "fixed_percpu_data is not at start of per-cpu area");
 #endif
 
 #endif /* CONFIG_X86_32 */

arch/x86/mm/cpu_entry_area.c

@@ -13,8 +13,8 @@
 static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage);
 
 #ifdef CONFIG_X86_64
-static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
+static DEFINE_PER_CPU_PAGE_ALIGNED(struct exception_stacks, exception_stacks);
-	[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
+DEFINE_PER_CPU(struct cea_exception_stacks*, cea_exception_stacks);
 #endif
 
 struct cpu_entry_area *get_cpu_entry_area(int cpu)
@@ -52,10 +52,10 @@ cea_map_percpu_pages(void *cea_vaddr, void *ptr, int pages, pgprot_t prot)
 		cea_set_pte(cea_vaddr, per_cpu_ptr_to_phys(ptr), prot);
 }
 
-static void __init percpu_setup_debug_store(int cpu)
+static void __init percpu_setup_debug_store(unsigned int cpu)
 {
 #ifdef CONFIG_CPU_SUP_INTEL
-	int npages;
+	unsigned int npages;
 	void *cea;
 
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
@@ -78,9 +78,43 @@ static void __init percpu_setup_debug_store(int cpu)
 #endif
 }
 
-/* Setup the fixmap mappings only once per-processor */
+#ifdef CONFIG_X86_64
-static void __init setup_cpu_entry_area(int cpu)
+
+#define cea_map_stack(name) do {					\
+	npages = sizeof(estacks->name## _stack) / PAGE_SIZE;		\
+	cea_map_percpu_pages(cea->estacks.name## _stack,		\
+			estacks->name## _stack, npages, PAGE_KERNEL);	\
+	} while (0)
+
+static void __init percpu_setup_exception_stacks(unsigned int cpu)
 {
+	struct exception_stacks *estacks = per_cpu_ptr(&exception_stacks, cpu);
+	struct cpu_entry_area *cea = get_cpu_entry_area(cpu);
+	unsigned int npages;
+
+	BUILD_BUG_ON(sizeof(exception_stacks) % PAGE_SIZE != 0);
+
+	per_cpu(cea_exception_stacks, cpu) = &cea->estacks;
+
+	/*
+	 * The exceptions stack mappings in the per cpu area are protected
+	 * by guard pages so each stack must be mapped separately. DB2 is
+	 * not mapped; it just exists to catch triple nesting of #DB.
+	 */
+	cea_map_stack(DF);
+	cea_map_stack(NMI);
+	cea_map_stack(DB1);
+	cea_map_stack(DB);
+	cea_map_stack(MCE);
+}
+#else
+static inline void percpu_setup_exception_stacks(unsigned int cpu) {}
+#endif
+
+/* Setup the fixmap mappings only once per-processor */
+static void __init setup_cpu_entry_area(unsigned int cpu)
+{
+	struct cpu_entry_area *cea = get_cpu_entry_area(cpu);
 #ifdef CONFIG_X86_64
 	/* On 64-bit systems, we use a read-only fixmap GDT and TSS. */
 	pgprot_t gdt_prot = PAGE_KERNEL_RO;
@@ -101,10 +135,9 @@ static void __init setup_cpu_entry_area(int cpu)
 	pgprot_t tss_prot = PAGE_KERNEL;
 #endif
 
-	cea_set_pte(&get_cpu_entry_area(cpu)->gdt, get_cpu_gdt_paddr(cpu),
+	cea_set_pte(&cea->gdt, get_cpu_gdt_paddr(cpu), gdt_prot);
-		    gdt_prot);
 
-	cea_map_percpu_pages(&get_cpu_entry_area(cpu)->entry_stack_page,
+	cea_map_percpu_pages(&cea->entry_stack_page,
 			     per_cpu_ptr(&entry_stack_storage, cpu), 1,
 			     PAGE_KERNEL);
 
@@ -128,22 +161,15 @@ static void __init setup_cpu_entry_area(int cpu)
 	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);
-	cea_map_percpu_pages(&get_cpu_entry_area(cpu)->tss,
+	cea_map_percpu_pages(&cea->tss, &per_cpu(cpu_tss_rw, cpu),
-			     &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);
+	per_cpu(cpu_entry_area, cpu) = cea;
 #endif
 
-#ifdef CONFIG_X86_64
+	percpu_setup_exception_stacks(cpu);
-	BUILD_BUG_ON(sizeof(exception_stacks) % PAGE_SIZE != 0);
+
-	BUILD_BUG_ON(sizeof(exception_stacks) !=
-		     sizeof(((struct cpu_entry_area *)0)->exception_stacks));
-	cea_map_percpu_pages(&get_cpu_entry_area(cpu)->exception_stacks,
-			     &per_cpu(exception_stacks, cpu),
-			     sizeof(exception_stacks) / PAGE_SIZE, PAGE_KERNEL);
-#endif
 	percpu_setup_debug_store(cpu);
 }
 

arch/x86/mm/fault.c

@@ -28,6 +28,7 @@
 #include <asm/mmu_context.h>		/* vma_pkey()			*/
 #include <asm/efi.h>			/* efi_recover_from_page_fault()*/
 #include <asm/desc.h>			/* store_idt(), ...		*/
+#include <asm/cpu_entry_area.h>		/* exception stack		*/
 
 #define CREATE_TRACE_POINTS
 #include <asm/trace/exceptions.h>
@@ -793,7 +794,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 	if (is_vmalloc_addr((void *)address) &&
 	    (((unsigned long)tsk->stack - 1 - address < PAGE_SIZE) ||
 	     address - ((unsigned long)tsk->stack + THREAD_SIZE) < PAGE_SIZE)) {
-		unsigned long stack = this_cpu_read(orig_ist.ist[DOUBLEFAULT_STACK]) - sizeof(void *);
+		unsigned long stack = __this_cpu_ist_top_va(DF) - sizeof(void *);
 		/*
 		 * We're likely to be running with very little stack space
 		 * left.  It's plausible that we'd hit this condition but

arch/x86/tools/relocs.c

@@ -754,7 +754,7 @@ static void percpu_init(void)
  *	__per_cpu_load
  *
  * The "gold" linker incorrectly associates:
- *	init_per_cpu__irq_stack_union
+ *	init_per_cpu__fixed_percpu_data
  *	init_per_cpu__gdt_page
  */
 static int is_percpu_sym(ElfW(Sym) *sym, const char *symname)

arch/x86/xen/smp_pv.c

@@ -361,7 +361,9 @@ static int xen_pv_cpu_up(unsigned int cpu, struct task_struct *idle)
 {
 	int rc;
 
-	common_cpu_up(cpu, idle);
+	rc = common_cpu_up(cpu, idle);
+	if (rc)
+		return rc;
 
 	xen_setup_runstate_info(cpu);
 

arch/x86/xen/xen-head.S

@@ -40,13 +40,13 @@ ENTRY(startup_xen)
 #ifdef CONFIG_X86_64
 	/* Set up %gs.
 	 *
-	 * The base of %gs always points to the bottom of the irqstack
+	 * The base of %gs always points to fixed_percpu_data.  If the
-	 * union.  If the stack protector canary is enabled, it is
+	 * stack protector canary is enabled, it is located at %gs:40.
-	 * located at %gs:40.  Note that, on SMP, the boot cpu uses
+	 * Note that, on SMP, the boot cpu uses init data section until
-	 * init data section till per cpu areas are set up.
+	 * the per cpu areas are set up.
 	 */
 	movl	$MSR_GS_BASE,%ecx
-	movq	$INIT_PER_CPU_VAR(irq_stack_union),%rax
+	movq	$INIT_PER_CPU_VAR(fixed_percpu_data),%rax
 	cdq
 	wrmsr
 #endif

drivers/xen/events/events_base.c

@@ -1687,7 +1687,6 @@ void __init xen_init_IRQ(void)
 
 #ifdef CONFIG_X86
 	if (xen_pv_domain()) {
-		irq_ctx_init(smp_processor_id());
 		if (xen_initial_domain())
 			pci_xen_initial_domain();
 	}

mm/slab.c

@@ -1467,53 +1467,17 @@ static bool is_debug_pagealloc_cache(struct kmem_cache *cachep)
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
-static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr,
+static void slab_kernel_map(struct kmem_cache *cachep, void *objp, int map)
-			    unsigned long caller)
-{
-	int size = cachep->object_size;
-
-	addr = (unsigned long *)&((char *)addr)[obj_offset(cachep)];
-
-	if (size < 5 * sizeof(unsigned long))
-		return;
-
-	*addr++ = 0x12345678;
-	*addr++ = caller;
-	*addr++ = smp_processor_id();
-	size -= 3 * sizeof(unsigned long);
-	{
-		unsigned long *sptr = &caller;
-		unsigned long svalue;
-
-		while (!kstack_end(sptr)) {
-			svalue = *sptr++;
-			if (kernel_text_address(svalue)) {
-				*addr++ = svalue;
-				size -= sizeof(unsigned long);
-				if (size <= sizeof(unsigned long))
-					break;
-			}
-		}
-
-	}
-	*addr++ = 0x87654321;
-}
-
-static void slab_kernel_map(struct kmem_cache *cachep, void *objp,
-				int map, unsigned long caller)
 {
 	if (!is_debug_pagealloc_cache(cachep))
 		return;
 
-	if (caller)
-		store_stackinfo(cachep, objp, caller);
-
 	kernel_map_pages(virt_to_page(objp), cachep->size / PAGE_SIZE, map);
 }
 
 #else
 static inline void slab_kernel_map(struct kmem_cache *cachep, void *objp,
-				int map, unsigned long caller) {}
+				int map) {}
 
 #endif
 
@@ -1661,7 +1625,7 @@ static void slab_destroy_debugcheck(struct kmem_cache *cachep,
 
 		if (cachep->flags & SLAB_POISON) {
 			check_poison_obj(cachep, objp);
-			slab_kernel_map(cachep, objp, 1, 0);
+			slab_kernel_map(cachep, objp, 1);
 		}
 		if (cachep->flags & SLAB_RED_ZONE) {
 			if (*dbg_redzone1(cachep, objp) != RED_INACTIVE)
@@ -2433,7 +2397,7 @@ static void cache_init_objs_debug(struct kmem_cache *cachep, struct page *page)
 		/* need to poison the objs? */
 		if (cachep->flags & SLAB_POISON) {
 			poison_obj(cachep, objp, POISON_FREE);
-			slab_kernel_map(cachep, objp, 0, 0);
+			slab_kernel_map(cachep, objp, 0);
 		}
 	}
 #endif
@@ -2812,7 +2776,7 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 
 	if (cachep->flags & SLAB_POISON) {
 		poison_obj(cachep, objp, POISON_FREE);
-		slab_kernel_map(cachep, objp, 0, caller);
+		slab_kernel_map(cachep, objp, 0);
 	}
 	return objp;
 }
@@ -3076,7 +3040,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
 		return objp;
 	if (cachep->flags & SLAB_POISON) {
 		check_poison_obj(cachep, objp);
-		slab_kernel_map(cachep, objp, 1, 0);
+		slab_kernel_map(cachep, objp, 1);
 		poison_obj(cachep, objp, POISON_INUSE);
 	}
 	if (cachep->flags & SLAB_STORE_USER)