Merge branch 'core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (63 commits)
  stacktrace: provide save_stack_trace_tsk() weak alias
  rcu: provide RCU options on non-preempt architectures too
  printk: fix discarding message when recursion_bug
  futex: clean up futex_(un)lock_pi fault handling
  "Tree RCU": scalable classic RCU implementation
  futex: rename field in futex_q to clarify single waiter semantics
  x86/swiotlb: add default swiotlb_arch_range_needs_mapping
  x86/swiotlb: add default phys<->bus conversion
  x86: unify pci iommu setup and allow swiotlb to compile for 32 bit
  x86: add swiotlb allocation functions
  swiotlb: consolidate swiotlb info message printing
  swiotlb: support bouncing of HighMem pages
  swiotlb: factor out copy to/from device
  swiotlb: add arch hook to force mapping
  swiotlb: allow architectures to override phys<->bus<->phys conversions
  swiotlb: add comment where we handle the overflow of a dma mask on 32 bit
  rcu: fix rcutorture behavior during reboot
  resources: skip sanity check of busy resources
  swiotlb: move some definitions to header
  swiotlb: allow architectures to override swiotlb pool allocation
  ...

Fix up trivial conflicts in
  arch/x86/kernel/Makefile
  arch/x86/mm/init_32.c
  include/linux/hardirq.h
as per Ingo's suggestions.

15 files changed, 70 insertions, 31 deletions

diff --git a/arch/powerpc/platforms/pseries/rtasd.c b/arch/powerpc/platforms/pseries/rtasd.c
index f4e55be2eea..afad9f5ac0a 100644
--- a/arch/powerpc/platforms/pseries/rtasd.c
+++ b/arch/powerpc/platforms/pseries/rtasd.c
@@ -208,6 +208,7 @@ void pSeries_log_error(char *buf, unsigned int err_type, int fatal)
 		break;
 	case ERR_TYPE_KERNEL_PANIC:
 	default:
+		WARN_ON_ONCE(!irqs_disabled()); /* @@@ DEBUG @@@ */
 		spin_unlock_irqrestore(&rtasd_log_lock, s);
 		return;
 	}
@@ -227,6 +228,7 @@ void pSeries_log_error(char *buf, unsigned int err_type, int fatal)
 	/* Check to see if we need to or have stopped logging */
 	if (fatal || !logging_enabled) {
 		logging_enabled = 0;
+		WARN_ON_ONCE(!irqs_disabled()); /* @@@ DEBUG @@@ */
 		spin_unlock_irqrestore(&rtasd_log_lock, s);
 		return;
 	}
@@ -249,11 +251,13 @@ void pSeries_log_error(char *buf, unsigned int err_type, int fatal)
 		else
 			rtas_log_start += 1;
 
+		WARN_ON_ONCE(!irqs_disabled()); /* @@@ DEBUG @@@ */
 		spin_unlock_irqrestore(&rtasd_log_lock, s);
 		wake_up_interruptible(&rtas_log_wait);
 		break;
 	case ERR_TYPE_KERNEL_PANIC:
 	default:
+		WARN_ON_ONCE(!irqs_disabled()); /* @@@ DEBUG @@@ */
 		spin_unlock_irqrestore(&rtasd_log_lock, s);
 		return;
 	}
diff --git a/arch/um/include/asm/system.h b/arch/um/include/asm/system.h
index 753346e2cdf..ae5f94d6317 100644
--- a/arch/um/include/asm/system.h
+++ b/arch/um/include/asm/system.h
@@ -11,21 +11,21 @@ extern int get_signals(void);
 extern void block_signals(void);
 extern void unblock_signals(void);
 
-#define local_save_flags(flags) do { typecheck(unsigned long, flags); \
+#define raw_local_save_flags(flags) do { typecheck(unsigned long, flags); \
 				     (flags) = get_signals(); } while(0)
-#define local_irq_restore(flags) do { typecheck(unsigned long, flags); \
+#define raw_local_irq_restore(flags) do { typecheck(unsigned long, flags); \
 				      set_signals(flags); } while(0)
 
-#define local_irq_save(flags) do { local_save_flags(flags); \
-                                   local_irq_disable(); } while(0)
+#define raw_local_irq_save(flags) do { raw_local_save_flags(flags); \
+                                   raw_local_irq_disable(); } while(0)
 
-#define local_irq_enable() unblock_signals()
-#define local_irq_disable() block_signals()
+#define raw_local_irq_enable() unblock_signals()
+#define raw_local_irq_disable() block_signals()
 
 #define irqs_disabled()                 \
 ({                                      \
         unsigned long flags;            \
-        local_save_flags(flags);        \
+        raw_local_save_flags(flags);        \
         (flags == 0);                   \
 })
 
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index dc22c073328..4035357f5b9 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -65,7 +65,7 @@ static inline struct dma_mapping_ops *get_dma_ops(struct device *dev)
 		return dma_ops;
 	else
 		return dev->archdata.dma_ops;
-#endif /* _ASM_X86_DMA_MAPPING_H */
+#endif
 }
 
 /* Make sure we keep the same behaviour */
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index 295b13193f4..a6ee9e6f530 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -7,8 +7,6 @@ extern struct dma_mapping_ops nommu_dma_ops;
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
 
-extern unsigned long iommu_nr_pages(unsigned long addr, unsigned long len);
-
 /* 10 seconds */
 #define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
 
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 647781298e7..66834c41c04 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -84,6 +84,8 @@ static inline void pci_dma_burst_advice(struct pci_dev *pdev,
 static inline void early_quirks(void) { }
 #endif
 
+extern void pci_iommu_alloc(void);
+
 #endif  /* __KERNEL__ */
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/include/asm/pci_64.h b/arch/x86/include/asm/pci_64.h
index d02d936840a..4da20798277 100644
--- a/arch/x86/include/asm/pci_64.h
+++ b/arch/x86/include/asm/pci_64.h
@@ -23,7 +23,6 @@ extern int (*pci_config_write)(int seg, int bus, int dev, int fn,
 			       int reg, int len, u32 value);
 
 extern void dma32_reserve_bootmem(void);
-extern void pci_iommu_alloc(void);
 
 /* The PCI address space does equal the physical memory
  * address space.  The networking and block device layers use
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 580c3ee6c58..4340055b755 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -157,6 +157,7 @@ extern int __get_user_bad(void);
 	int __ret_gu;							\
 	unsigned long __val_gu;						\
 	__chk_user_ptr(ptr);						\
+	might_fault();							\
 	switch (sizeof(*(ptr))) {					\
 	case 1:								\
 		__get_user_x(1, __ret_gu, __val_gu, ptr);		\
@@ -241,6 +242,7 @@ extern void __put_user_8(void);
 	int __ret_pu;						\
 	__typeof__(*(ptr)) __pu_val;				\
 	__chk_user_ptr(ptr);					\
+	might_fault();						\
 	__pu_val = x;						\
 	switch (sizeof(*(ptr))) {				\
 	case 1:							\
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index d095a3aeea1..5e06259e90e 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -82,8 +82,8 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
 static __always_inline unsigned long __must_check
 __copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-       might_sleep();
-       return __copy_to_user_inatomic(to, from, n);
+	might_fault();
+	return __copy_to_user_inatomic(to, from, n);
 }
 
 static __always_inline unsigned long
@@ -137,7 +137,7 @@ __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
 static __always_inline unsigned long
 __copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	might_sleep();
+	might_fault();
 	if (__builtin_constant_p(n)) {
 		unsigned long ret;
 
@@ -159,7 +159,7 @@ __copy_from_user(void *to, const void __user *from, unsigned long n)
 static __always_inline unsigned long __copy_from_user_nocache(void *to,
 				const void __user *from, unsigned long n)
 {
-	might_sleep();
+	might_fault();
 	if (__builtin_constant_p(n)) {
 		unsigned long ret;
 
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index f8cfd00db45..84210c479fc 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -29,6 +29,8 @@ static __always_inline __must_check
 int __copy_from_user(void *dst, const void __user *src, unsigned size)
 {
 	int ret = 0;
+
+	might_fault();
 	if (!__builtin_constant_p(size))
 		return copy_user_generic(dst, (__force void *)src, size);
 	switch (size) {
@@ -71,6 +73,8 @@ static __always_inline __must_check
 int __copy_to_user(void __user *dst, const void *src, unsigned size)
 {
 	int ret = 0;
+
+	might_fault();
 	if (!__builtin_constant_p(size))
 		return copy_user_generic((__force void *)dst, src, size);
 	switch (size) {
@@ -113,6 +117,8 @@ static __always_inline __must_check
 int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
 {
 	int ret = 0;
+
+	might_fault();
 	if (!__builtin_constant_p(size))
 		return copy_user_generic((__force void *)dst,
 					 (__force void *)src, size);
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 88dd768eab6..d364df03c1d 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -109,6 +109,8 @@ obj-$(CONFIG_MICROCODE)			+= microcode.o
 
 obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o
 
+obj-$(CONFIG_SWIOTLB)			+= pci-swiotlb_64.o # NB rename without _64
+
 ###
 # 64 bit specific files
 ifeq ($(CONFIG_X86_64),y)
@@ -122,7 +124,6 @@ ifeq ($(CONFIG_X86_64),y)
         obj-$(CONFIG_GART_IOMMU)	+= pci-gart_64.o aperture_64.o
         obj-$(CONFIG_CALGARY_IOMMU)	+= pci-calgary_64.o tce_64.o
         obj-$(CONFIG_AMD_IOMMU)		+= amd_iommu_init.o amd_iommu.o
-        obj-$(CONFIG_SWIOTLB)		+= pci-swiotlb_64.o
 
         obj-$(CONFIG_PCI_MMCONFIG)	+= mmconf-fam10h_64.o
 endif
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 7a3dfceb90e..19a1044a0cd 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -101,11 +101,15 @@ static void __init dma32_free_bootmem(void)
 	dma32_bootmem_ptr = NULL;
 	dma32_bootmem_size = 0;
 }
+#endif
 
 void __init pci_iommu_alloc(void)
 {
+#ifdef CONFIG_X86_64
 	/* free the range so iommu could get some range less than 4G */
 	dma32_free_bootmem();
+#endif
+
 	/*
 	 * The order of these functions is important for
 	 * fall-back/fail-over reasons
@@ -121,15 +125,6 @@ void __init pci_iommu_alloc(void)
 	pci_swiotlb_init();
 }
 
-unsigned long iommu_nr_pages(unsigned long addr, unsigned long len)
-{
-	unsigned long size = roundup((addr & ~PAGE_MASK) + len, PAGE_SIZE);
-
-	return size >> PAGE_SHIFT;
-}
-EXPORT_SYMBOL(iommu_nr_pages);
-#endif
-
 void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 				 dma_addr_t *dma_addr, gfp_t flag)
 {
diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb_64.c
index 3c539d111ab..242c3440687 100644
--- a/arch/x86/kernel/pci-swiotlb_64.c
+++ b/arch/x86/kernel/pci-swiotlb_64.c
@@ -3,6 +3,8 @@
 #include <linux/pci.h>
 #include <linux/cache.h>
 #include <linux/module.h>
+#include <linux/swiotlb.h>
+#include <linux/bootmem.h>
 #include <linux/dma-mapping.h>
 
 #include <asm/iommu.h>
@@ -11,6 +13,31 @@
 
 int swiotlb __read_mostly;
 
+void *swiotlb_alloc_boot(size_t size, unsigned long nslabs)
+{
+	return alloc_bootmem_low_pages(size);
+}
+
+void *swiotlb_alloc(unsigned order, unsigned long nslabs)
+{
+	return (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order);
+}
+
+dma_addr_t swiotlb_phys_to_bus(phys_addr_t paddr)
+{
+	return paddr;
+}
+
+phys_addr_t swiotlb_bus_to_phys(dma_addr_t baddr)
+{
+	return baddr;
+}
+
+int __weak swiotlb_arch_range_needs_mapping(void *ptr, size_t size)
+{
+	return 0;
+}
+
 static dma_addr_t
 swiotlb_map_single_phys(struct device *hwdev, phys_addr_t paddr, size_t size,
 			int direction)
@@ -50,8 +77,10 @@ struct dma_mapping_ops swiotlb_dma_ops = {
 void __init pci_swiotlb_init(void)
 {
 	/* don't initialize swiotlb if iommu=off (no_iommu=1) */
+#ifdef CONFIG_X86_64
 	if (!iommu_detected && !no_iommu && max_pfn > MAX_DMA32_PFN)
 	       swiotlb = 1;
+#endif
 	if (swiotlb_force)
 		swiotlb = 1;
 	if (swiotlb) {
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 9e68075544f..4a20b2f9a38 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -39,7 +39,7 @@ static inline int __movsl_is_ok(unsigned long a1, unsigned long a2, unsigned lon
 #define __do_strncpy_from_user(dst, src, count, res)			   \
 do {									   \
 	int __d0, __d1, __d2;						   \
-	might_sleep();							   \
+	might_fault();							   \
 	__asm__ __volatile__(						   \
 		"	testl %1,%1\n"					   \
 		"	jz 2f\n"					   \
@@ -126,7 +126,7 @@ EXPORT_SYMBOL(strncpy_from_user);
 #define __do_clear_user(addr,size)					\
 do {									\
 	int __d0;							\
-	might_sleep();							\
+	might_fault();							\
 	__asm__ __volatile__(						\
 		"0:	rep; stosl\n"					\
 		"	movl %2,%0\n"					\
@@ -155,7 +155,7 @@ do {									\
 unsigned long
 clear_user(void __user *to, unsigned long n)
 {
-	might_sleep();
+	might_fault();
 	if (access_ok(VERIFY_WRITE, to, n))
 		__do_clear_user(to, n);
 	return n;
@@ -197,7 +197,7 @@ long strnlen_user(const char __user *s, long n)
 	unsigned long mask = -__addr_ok(s);
 	unsigned long res, tmp;
 
-	might_sleep();
+	might_fault();
 
 	__asm__ __volatile__(
 		"	testl %0, %0\n"
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index f4df6e7c718..64d6c84e635 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -15,7 +15,7 @@
 #define __do_strncpy_from_user(dst,src,count,res)			   \
 do {									   \
 	long __d0, __d1, __d2;						   \
-	might_sleep();							   \
+	might_fault();							   \
 	__asm__ __volatile__(						   \
 		"	testq %1,%1\n"					   \
 		"	jz 2f\n"					   \
@@ -64,7 +64,7 @@ EXPORT_SYMBOL(strncpy_from_user);
 unsigned long __clear_user(void __user *addr, unsigned long size)
 {
 	long __d0;
-	might_sleep();
+	might_fault();
 	/* no memory constraint because it doesn't change any memory gcc knows
 	   about */
 	asm volatile(
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 800e1d94c1b..8655b5bb096 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -21,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
+#include <linux/pci.h>
 #include <linux/pfn.h>
 #include <linux/poison.h>
 #include <linux/bootmem.h>
@@ -967,6 +968,8 @@ void __init mem_init(void)
 	int codesize, reservedpages, datasize, initsize;
 	int tmp;
 
+	pci_iommu_alloc();
+
 #ifdef CONFIG_FLATMEM
 	BUG_ON(!mem_map);
 #endif