8 files changed, 25 insertions, 40 deletions

diff --git a/Documentation/x86/x86_64/kernel-stacks b/Documentation/x86/x86_64/kernel-stacks
index 5ad65d51fb95..a01eec5d1d0b 100644
--- a/Documentation/x86/x86_64/kernel-stacks
+++ b/Documentation/x86/x86_64/kernel-stacks
@@ -18,9 +18,9 @@ specialized stacks contain no useful data.  The main CPU stacks are:
   Used for external hardware interrupts.  If this is the first external
   hardware interrupt (i.e. not a nested hardware interrupt) then the
   kernel switches from the current task to the interrupt stack.  Like
-  the split thread and interrupt stacks on i386 (with CONFIG_4KSTACKS),
-  this gives more room for kernel interrupt processing without having
-  to increase the size of every per thread stack.
+  the split thread and interrupt stacks on i386, this gives more room
+  for kernel interrupt processing without having to increase the size
+  of every per thread stack.
 
   The interrupt stack is also used when processing a softirq.
 
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index e5bb96b10f1a..b59ee765414e 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -125,16 +125,6 @@ config DEBUG_NX_TEST
           and the software setup of this feature.
           If in doubt, say "N"
 
-config 4KSTACKS
-        bool "Use 4Kb for kernel stacks instead of 8Kb"
-        depends on X86_32
-        ---help---
-          If you say Y here the kernel will use a 4Kb stacksize for the
-          kernel stack attached to each process/thread. This facilitates
-          running more threads on a system and also reduces the pressure
-          on the VM subsystem for higher order allocations. This option
-          will also use IRQ stacks to compensate for the reduced stackspace.
-
 config DOUBLEFAULT
         default y
         bool "Enable doublefault exception handler" if EMBEDDED
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 5458380b6ef8..0bf5b0083650 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -19,18 +19,16 @@ static inline int irq_canonicalize(int irq)
 # define ARCH_HAS_NMI_WATCHDOG
 #endif
 
-#ifdef CONFIG_4KSTACKS
-  extern void irq_ctx_init(int cpu);
-  extern void irq_ctx_exit(int cpu);
-# define __ARCH_HAS_DO_SOFTIRQ
+#ifdef CONFIG_X86_32
+extern void irq_ctx_init(int cpu);
+extern void irq_ctx_exit(int cpu);
 #else
 # define irq_ctx_init(cpu) do { } while (0)
 # define irq_ctx_exit(cpu) do { } while (0)
-# ifdef CONFIG_X86_64
-#  define __ARCH_HAS_DO_SOFTIRQ
-# endif
 #endif
 
+#define __ARCH_HAS_DO_SOFTIRQ
+
 #ifdef CONFIG_HOTPLUG_CPU
 #include <linux/cpumask.h>
 extern void fixup_irqs(void);
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index 3e2ce58a31a3..67763c5d8b4e 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -60,12 +60,7 @@
 #endif
 
 #ifdef CONFIG_X86_32
-# ifdef CONFIG_4KSTACKS
-#  define MODULE_STACKSIZE "4KSTACKS "
-# else
-#  define MODULE_STACKSIZE ""
-# endif
-# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY MODULE_STACKSIZE
+# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY
 #endif
 
 #endif /* _ASM_X86_MODULE_H */
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index 6f1b7331313f..ade619ff9e2a 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -15,11 +15,7 @@
  */
 #define __PAGE_OFFSET           _AC(CONFIG_PAGE_OFFSET, UL)
 
-#ifdef CONFIG_4KSTACKS
-#define THREAD_ORDER    0
-#else
 #define THREAD_ORDER    1
-#endif
 #define THREAD_SIZE     (PAGE_SIZE << THREAD_ORDER)
 
 #define STACKFAULT_STACK 0
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 10709f29d166..50fbbe60e507 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -49,20 +49,19 @@ static inline int check_stack_overflow(void) { return 0; }
 static inline void print_stack_overflow(void) { }
 #endif
 
-#ifdef CONFIG_4KSTACKS
 /*
  * per-CPU IRQ handling contexts (thread information and stack)
  */
 union irq_ctx {
         struct thread_info      tinfo;
         u32                     stack[THREAD_SIZE/sizeof(u32)];
-} __attribute__((aligned(PAGE_SIZE)));
+} __attribute__((aligned(THREAD_SIZE)));
 
 static DEFINE_PER_CPU(union irq_ctx *, hardirq_ctx);
 static DEFINE_PER_CPU(union irq_ctx *, softirq_ctx);
 
-static DEFINE_PER_CPU_PAGE_ALIGNED(union irq_ctx, hardirq_stack);
-static DEFINE_PER_CPU_PAGE_ALIGNED(union irq_ctx, softirq_stack);
+static DEFINE_PER_CPU_MULTIPAGE_ALIGNED(union irq_ctx, hardirq_stack, THREAD_SIZE);
+static DEFINE_PER_CPU_MULTIPAGE_ALIGNED(union irq_ctx, softirq_stack, THREAD_SIZE);
 
 static void call_on_stack(void *func, void *stack)
 {
@@ -187,11 +186,6 @@ asmlinkage void do_softirq(void)
         local_irq_restore(flags);
 }
 
-#else
-static inline int
-execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) { return 0; }
-#endif
-
 bool handle_irq(unsigned irq, struct pt_regs *regs)
 {
         struct irq_desc *desc;
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 38e2b67807e1..e03530aebfd0 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -301,7 +301,7 @@ SECTIONS
         }
 
 #if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
-        PERCPU(PAGE_SIZE)
+        PERCPU(THREAD_SIZE)
 #endif
 
         . = ALIGN(PAGE_SIZE);
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 27ef6b190ea6..018db9a62ffe 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -148,6 +148,18 @@
         DEFINE_PER_CPU_SECTION(type, name, "..readmostly")
 
 /*
+ * Declaration/definition used for large per-CPU variables that must be
+ * aligned to something larger than the pagesize.
+ */
+#define DECLARE_PER_CPU_MULTIPAGE_ALIGNED(type, name, size)             \
+        DECLARE_PER_CPU_SECTION(type, name, "..page_aligned")           \
+        __aligned(size)
+
+#define DEFINE_PER_CPU_MULTIPAGE_ALIGNED(type, name, size)              \
+        DEFINE_PER_CPU_SECTION(type, name, "..page_aligned")            \
+        __aligned(size)
+
+/*
  * Intermodule exports for per-CPU variables.  sparse forgets about
  * address space across EXPORT_SYMBOL(), change EXPORT_SYMBOL() to
  * noop if __CHECKER__.