Merge branch 'linus' into cpus4096

11 files changed, 113 insertions, 65 deletions

diff --git a/arch/x86/include/asm/mach-default/mach_wakecpu.h b/arch/x86/include/asm/mach-default/mach_wakecpu.h
index ceb0136..89897a6 100644
--- a/arch/x86/include/asm/mach-default/mach_wakecpu.h
+++ b/arch/x86/include/asm/mach-default/mach_wakecpu.h
@@ -24,7 +24,13 @@ static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
 {
 }
 
+#ifdef CONFIG_SMP
 extern void __inquire_remote_apic(int apicid);
+#else /* CONFIG_SMP */
+static inline void __inquire_remote_apic(int apicid)
+{
+}
+#endif /* CONFIG_SMP */
 
 static inline void inquire_remote_apic(int apicid)
 {
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index cb988aa..14080d2 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -58,15 +58,15 @@ struct mtrr_gentry {
 #endif /* !__i386__ */
 
 struct mtrr_var_range {
-	u32 base_lo;
-	u32 base_hi;
-	u32 mask_lo;
-	u32 mask_hi;
+	__u32 base_lo;
+	__u32 base_hi;
+	__u32 mask_lo;
+	__u32 mask_hi;
 };
 
 /* In the Intel processor's MTRR interface, the MTRR type is always held in
    an 8 bit field: */
-typedef u8 mtrr_type;
+typedef __u8 mtrr_type;
 
 #define MTRR_NUM_FIXED_RANGES 88
 #define MTRR_MAX_VAR_RANGES 256
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 83e69f4..06bbcbd 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -341,6 +341,25 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 
 #define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask)
 
+static inline int is_new_memtype_allowed(unsigned long flags,
+						unsigned long new_flags)
+{
+	/*
+	 * Certain new memtypes are not allowed with certain
+	 * requested memtype:
+	 * - request is uncached, return cannot be write-back
+	 * - request is write-combine, return cannot be write-back
+	 */
+	if ((flags == _PAGE_CACHE_UC_MINUS &&
+	     new_flags == _PAGE_CACHE_WB) ||
+	    (flags == _PAGE_CACHE_WC &&
+	     new_flags == _PAGE_CACHE_WB)) {
+		return 0;
+	}
+
+	return 1;
+}
+
 #ifndef __ASSEMBLY__
 /* Indicate that x86 has its own track and untrack pfn vma functions */
 #define __HAVE_PFNMAP_TRACKING
diff --git a/arch/x86/kernel/apic.c b/arch/x86/kernel/apic.c
index 566a084..0f830e4 100644
--- a/arch/x86/kernel/apic.c
+++ b/arch/x86/kernel/apic.c
@@ -47,6 +47,7 @@
 #include <asm/proto.h>
 #include <asm/apic.h>
 #include <asm/i8259.h>
+#include <asm/smp.h>
 
 #include <mach_apic.h>
 #include <mach_apicdef.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 06fcd8f..6f11e02 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -150,9 +150,8 @@ struct drv_cmd {
 	u32 val;
 };
 
-static long do_drv_read(void *_cmd)
+static void do_drv_read(struct drv_cmd *cmd)
 {
-	struct drv_cmd *cmd = _cmd;
 	u32 h;
 
 	switch (cmd->type) {
@@ -167,12 +166,10 @@ static long do_drv_read(void *_cmd)
 	default:
 		break;
 	}
-	return 0;
 }
 
-static long do_drv_write(void *_cmd)
+static void do_drv_write(struct drv_cmd *cmd)
 {
-	struct drv_cmd *cmd = _cmd;
 	u32 lo, hi;
 
 	switch (cmd->type) {
@@ -189,23 +186,30 @@ static long do_drv_write(void *_cmd)
 	default:
 		break;
 	}
-	return 0;
 }
 
 static void drv_read(struct drv_cmd *cmd)
 {
+	cpumask_t saved_mask = current->cpus_allowed;
 	cmd->val = 0;
 
-	work_on_cpu(cpumask_any(cmd->mask), do_drv_read, cmd);
+	set_cpus_allowed_ptr(current, cmd->mask);
+	do_drv_read(cmd);
+	set_cpus_allowed_ptr(current, &saved_mask);
 }
 
 static void drv_write(struct drv_cmd *cmd)
 {
+	cpumask_t saved_mask = current->cpus_allowed;
 	unsigned int i;
 
 	for_each_cpu(i, cmd->mask) {
-		work_on_cpu(i, do_drv_write, cmd);
+		set_cpus_allowed_ptr(current, cpumask_of(i));
+		do_drv_write(cmd);
 	}
+
+	set_cpus_allowed_ptr(current, &saved_mask);
+	return;
 }
 
 static u32 get_cur_val(const struct cpumask *mask)
@@ -231,15 +235,10 @@ static u32 get_cur_val(const struct cpumask *mask)
 		return 0;
 	}
 
-	if (unlikely(!alloc_cpumask_var(&cmd.mask, GFP_KERNEL)))
-		return 0;
-
 	cpumask_copy(cmd.mask, mask);
 
 	drv_read(&cmd);
 
-	free_cpumask_var(cmd.mask);
-
 	dprintk("get_cur_val = %u\n", cmd.val);
 
 	return cmd.val;
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index d6f0490..4646902 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1203,7 +1203,6 @@ nmi_stack_correct:
 	pushl %eax
 	CFI_ADJUST_CFA_OFFSET 4
 	SAVE_ALL
-	TRACE_IRQS_OFF
 	xorl %edx,%edx		# zero error code
 	movl %esp,%eax		# pt_regs pointer
 	call do_nmi
@@ -1244,7 +1243,6 @@ nmi_espfix_stack:
 	pushl %eax
 	CFI_ADJUST_CFA_OFFSET 4
 	SAVE_ALL
-	TRACE_IRQS_OFF
 	FIXUP_ESPFIX_STACK		# %eax == %esp
 	xorl %edx,%edx			# zero error code
 	call do_nmi
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index c0601c2..a649a4c 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -27,6 +27,7 @@
 #include <asm/e820.h>
 #include <asm/trampoline.h>
 #include <asm/setup.h>
+#include <asm/smp.h>
 
 #include <mach_apic.h>
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9e268b6b..90dfae5 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -534,7 +534,7 @@ static int vmalloc_fault(unsigned long address)
 	   happen within a race in page table update. In the later
 	   case just flush. */
 
-	pgd = pgd_offset(current->mm ?: &init_mm, address);
+	pgd = pgd_offset(current->active_mm, address);
 	pgd_ref = pgd_offset_k(address);
 	if (pgd_none(*pgd_ref))
 		return -1;
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index e89d248..4cf30de 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -555,10 +555,12 @@ repeat:
 	if (!pte_val(old_pte)) {
 		if (!primary)
 			return 0;
-		WARN(1, KERN_WARNING "CPA: called for zero pte. "
-		       "vaddr = %lx cpa->vaddr = %lx\n", address,
-		       *cpa->vaddr);
-		return -EINVAL;
+
+		/*
+		 *  Special error value returned, indicating that the mapping
+		 * did not exist at this address.
+		 */
+		return -EFAULT;
 	}
 
 	if (level == PG_LEVEL_4K) {
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 85cbd3c..160c42d 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -505,6 +505,35 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 }
 #endif /* CONFIG_STRICT_DEVMEM */
 
+/*
+ * Change the memory type for the physial address range in kernel identity
+ * mapping space if that range is a part of identity map.
+ */
+static int kernel_map_sync_memtype(u64 base, unsigned long size,
+					unsigned long flags)
+{
+	unsigned long id_sz;
+	int ret;
+
+	if (!pat_enabled || base >= __pa(high_memory))
+		return 0;
+
+	id_sz = (__pa(high_memory) < base + size) ?
+						__pa(high_memory) - base :
+						size;
+
+	ret = ioremap_change_attr((unsigned long)__va(base), id_sz, flags);
+	/*
+	 * -EFAULT return means that the addr was not valid and did not have
+	 * any identity mapping. That case is a success for
+	 * kernel_map_sync_memtype.
+	 */
+	if (ret == -EFAULT)
+		ret = 0;
+
+	return ret;
+}
+
 int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 				unsigned long size, pgprot_t *vma_prot)
 {
@@ -555,9 +584,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 	if (retval < 0)
 		return 0;
 
-	if (((pfn < max_low_pfn_mapped) ||
-	     (pfn >= (1UL<<(32 - PAGE_SHIFT)) && pfn < max_pfn_mapped)) &&
-	    ioremap_change_attr((unsigned long)__va(offset), size, flags) < 0) {
+	if (kernel_map_sync_memtype(offset, size, flags)) {
 		free_memtype(offset, offset + size);
 		printk(KERN_INFO
 		"%s:%d /dev/mem ioremap_change_attr failed %s for %Lx-%Lx\n",
@@ -601,12 +628,13 @@ void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot)
  * Reserved non RAM regions only and after successful reserve_memtype,
  * this func also keeps identity mapping (if any) in sync with this new prot.
  */
-static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t vma_prot)
+static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
+				int strict_prot)
 {
 	int is_ram = 0;
-	int id_sz, ret;
+	int ret;
 	unsigned long flags;
-	unsigned long want_flags = (pgprot_val(vma_prot) & _PAGE_CACHE_MASK);
+	unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK);
 
 	is_ram = pagerange_is_ram(paddr, paddr + size);
 
@@ -625,26 +653,27 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t vma_prot)
 		return ret;
 
 	if (flags != want_flags) {
-		free_memtype(paddr, paddr + size);
-		printk(KERN_ERR
-		"%s:%d map pfn expected mapping type %s for %Lx-%Lx, got %s\n",
-			current->comm, current->pid,
-			cattr_name(want_flags),
-			(unsigned long long)paddr,
-			(unsigned long long)(paddr + size),
-			cattr_name(flags));
-		return -EINVAL;
+		if (strict_prot || !is_new_memtype_allowed(want_flags, flags)) {
+			free_memtype(paddr, paddr + size);
+			printk(KERN_ERR "%s:%d map pfn expected mapping type %s"
+				" for %Lx-%Lx, got %s\n",
+				current->comm, current->pid,
+				cattr_name(want_flags),
+				(unsigned long long)paddr,
+				(unsigned long long)(paddr + size),
+				cattr_name(flags));
+			return -EINVAL;
+		}
+		/*
+		 * We allow returning different type than the one requested in
+		 * non strict case.
+		 */
+		*vma_prot = __pgprot((pgprot_val(*vma_prot) &
+				      (~_PAGE_CACHE_MASK)) |
+				     flags);
 	}
 
-	/* Need to keep identity mapping in sync */
-	if (paddr >= __pa(high_memory))
-		return 0;
-
-	id_sz = (__pa(high_memory) < paddr + size) ?
-				__pa(high_memory) - paddr :
-				size;
-
-	if (ioremap_change_attr((unsigned long)__va(paddr), id_sz, flags) < 0) {
+	if (kernel_map_sync_memtype(paddr, size, flags)) {
 		free_memtype(paddr, paddr + size);
 		printk(KERN_ERR
 			"%s:%d reserve_pfn_range ioremap_change_attr failed %s "
@@ -689,6 +718,7 @@ int track_pfn_vma_copy(struct vm_area_struct *vma)
 	unsigned long vma_start = vma->vm_start;
 	unsigned long vma_end = vma->vm_end;
 	unsigned long vma_size = vma_end - vma_start;
+	pgprot_t pgprot;
 
 	if (!pat_enabled)
 		return 0;
@@ -702,7 +732,8 @@ int track_pfn_vma_copy(struct vm_area_struct *vma)
 			WARN_ON_ONCE(1);
 			return -EINVAL;
 		}
-		return reserve_pfn_range(paddr, vma_size, __pgprot(prot));
+		pgprot = __pgprot(prot);
+		return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
 	}
 
 	/* reserve entire vma page by page, using pfn and prot from pte */
@@ -710,7 +741,8 @@ int track_pfn_vma_copy(struct vm_area_struct *vma)
 		if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
 			continue;
 
-		retval = reserve_pfn_range(paddr, PAGE_SIZE, __pgprot(prot));
+		pgprot = __pgprot(prot);
+		retval = reserve_pfn_range(paddr, PAGE_SIZE, &pgprot, 1);
 		if (retval)
 			goto cleanup_ret;
 	}
@@ -741,7 +773,7 @@ cleanup_ret:
  * Note that this function can be called with caller trying to map only a
  * subrange/page inside the vma.
  */
-int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot,
+int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
 			unsigned long pfn, unsigned long size)
 {
 	int retval = 0;
@@ -758,14 +790,14 @@ int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot,
 	if (is_linear_pfn_mapping(vma)) {
 		/* reserve the whole chunk starting from vm_pgoff */
 		paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
-		return reserve_pfn_range(paddr, vma_size, prot);
+		return reserve_pfn_range(paddr, vma_size, prot, 0);
 	}
 
 	/* reserve page by page using pfn and size */
 	base_paddr = (resource_size_t)pfn << PAGE_SHIFT;
 	for (i = 0; i < size; i += PAGE_SIZE) {
 		paddr = base_paddr + i;
-		retval = reserve_pfn_range(paddr, PAGE_SIZE, prot);
+		retval = reserve_pfn_range(paddr, PAGE_SIZE, prot, 0);
 		if (retval)
 			goto cleanup_ret;
 	}
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index f884740..5ead808 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -314,17 +314,7 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 		return retval;
 
 	if (flags != new_flags) {
-		/*
-		 * Do not fallback to certain memory types with certain
-		 * requested type:
-		 * - request is uncached, return cannot be write-back
-		 * - request is uncached, return cannot be write-combine
-		 * - request is write-combine, return cannot be write-back
-		 */
-		if ((flags == _PAGE_CACHE_UC_MINUS &&
-		     (new_flags == _PAGE_CACHE_WB)) ||
-		    (flags == _PAGE_CACHE_WC &&
-		     new_flags == _PAGE_CACHE_WB)) {
+		if (!is_new_memtype_allowed(flags, new_flags)) {
 			free_memtype(addr, addr+len);
 			return -EINVAL;
 		}