Merge branch 'akpm' (patches from Andrew)

Merge third set of updates from Andrew Morton:

 - the rest of MM

   [ This includes getting rid of the numa hinting bits, in favor of
     just generic protnone logic.  Yay.     - Linus ]

 - core kernel

 - procfs

 - some of lib/ (lots of lib/ material this time)

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (104 commits)
  lib/lcm.c: replace include
  lib/percpu_ida.c: remove redundant includes
  lib/strncpy_from_user.c: replace module.h include
  lib/stmp_device.c: replace module.h include
  lib/sort.c: move include inside #if 0
  lib/show_mem.c: remove redundant include
  lib/radix-tree.c: change to simpler include
  lib/plist.c: remove redundant include
  lib/nlattr.c: remove redundant include
  lib/kobject_uevent.c: remove redundant include
  lib/llist.c: remove redundant include
  lib/md5.c: simplify include
  lib/list_sort.c: rearrange includes
  lib/genalloc.c: remove redundant include
  lib/idr.c: remove redundant include
  lib/halfmd4.c: simplify includes
  lib/dynamic_queue_limits.c: simplify includes
  lib/sort.c: use simpler includes
  lib/interval_tree.c: simplify includes
  hexdump: make it return number of bytes placed in buffer
  ...

12 files changed, 70 insertions, 86 deletions

diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 7e77f2c..79fee2e 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -40,63 +40,27 @@ static inline int pte_none(pte_t pte)		{ return (pte_val(pte) & ~_PTE_NONE_MASK)
 static inline pgprot_t pte_pgprot(pte_t pte)	{ return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }
 
 #ifdef CONFIG_NUMA_BALANCING
-static inline int pte_present(pte_t pte)
-{
-	return pte_val(pte) & _PAGE_NUMA_MASK;
-}
-
-#define pte_present_nonuma pte_present_nonuma
-static inline int pte_present_nonuma(pte_t pte)
-{
-	return pte_val(pte) & (_PAGE_PRESENT);
-}
-
-#define ptep_set_numa ptep_set_numa
-static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
-				 pte_t *ptep)
-{
-	if ((pte_val(*ptep) & _PAGE_PRESENT) == 0)
-		VM_BUG_ON(1);
-
-	pte_update(mm, addr, ptep, _PAGE_PRESENT, _PAGE_NUMA, 0);
-	return;
-}
-
-#define pmdp_set_numa pmdp_set_numa
-static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
-				 pmd_t *pmdp)
-{
-	if ((pmd_val(*pmdp) & _PAGE_PRESENT) == 0)
-		VM_BUG_ON(1);
-
-	pmd_hugepage_update(mm, addr, pmdp, _PAGE_PRESENT, _PAGE_NUMA);
-	return;
-}
-
 /*
- * Generic NUMA pte helpers expect pteval_t and pmdval_t types to exist
- * which was inherited from x86. For the purposes of powerpc pte_basic_t and
- * pmd_t are equivalent
+ * These work without NUMA balancing but the kernel does not care. See the
+ * comment in include/asm-generic/pgtable.h . On powerpc, this will only
+ * work for user pages and always return true for kernel pages.
  */
-#define pteval_t pte_basic_t
-#define pmdval_t pmd_t
-static inline pteval_t ptenuma_flags(pte_t pte)
+static inline int pte_protnone(pte_t pte)
 {
-	return pte_val(pte) & _PAGE_NUMA_MASK;
+	return (pte_val(pte) &
+		(_PAGE_PRESENT | _PAGE_USER)) == _PAGE_PRESENT;
 }
 
-static inline pmdval_t pmdnuma_flags(pmd_t pmd)
+static inline int pmd_protnone(pmd_t pmd)
 {
-	return pmd_val(pmd) & _PAGE_NUMA_MASK;
+	return pte_protnone(pmd_pte(pmd));
 }
-
-# else
+#endif /* CONFIG_NUMA_BALANCING */
 
 static inline int pte_present(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_PRESENT;
 }
-#endif /* CONFIG_NUMA_BALANCING */
 
 /* Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.
diff --git a/arch/powerpc/include/asm/pte-common.h b/arch/powerpc/include/asm/pte-common.h
index 2aef9b7..c5a755e 100644
--- a/arch/powerpc/include/asm/pte-common.h
+++ b/arch/powerpc/include/asm/pte-common.h
@@ -104,11 +104,6 @@ extern unsigned long bad_call_to_PMD_PAGE_SIZE(void);
 			 _PAGE_USER | _PAGE_ACCESSED | _PAGE_RO | \
 			 _PAGE_RW | _PAGE_HWWRITE | _PAGE_DIRTY | _PAGE_EXEC)
 
-#ifdef CONFIG_NUMA_BALANCING
-/* Mask of bits that distinguish present and numa ptes */
-#define _PAGE_NUMA_MASK (_PAGE_NUMA|_PAGE_PRESENT)
-#endif
-
 /*
  * We define 2 sets of base prot bits, one for basic pages (ie,
  * cacheable kernel and user pages) and one for non cacheable
diff --git a/arch/powerpc/include/asm/pte-hash64.h b/arch/powerpc/include/asm/pte-hash64.h
index 2505d8e..55aea0c 100644
--- a/arch/powerpc/include/asm/pte-hash64.h
+++ b/arch/powerpc/include/asm/pte-hash64.h
@@ -27,12 +27,6 @@
 #define _PAGE_RW		0x0200 /* software: user write access allowed */
 #define _PAGE_BUSY		0x0800 /* software: PTE & hash are busy */
 
-/*
- * Used for tracking numa faults
- */
-#define _PAGE_NUMA	0x00000010 /* Gather numa placement stats */
-
-
 /* No separate kernel read-only */
 #define _PAGE_KERNEL_RW		(_PAGE_RW | _PAGE_DIRTY) /* user access blocked by key */
 #define _PAGE_KERNEL_RO		 _PAGE_KERNEL_RW
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index e8abc83..7248979 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -43,7 +43,6 @@ struct thread_info {
 	int		cpu;			/* cpu we're on */
 	int		preempt_count;		/* 0 => preemptable,
 						   <0 => BUG */
-	struct restart_block restart_block;
 	unsigned long	local_flags;		/* private flags for thread */
 
 	/* low level flags - has atomic operations done on it */
@@ -59,9 +58,6 @@ struct thread_info {
 	.exec_domain =	&default_exec_domain,	\
 	.cpu =		0,			\
 	.preempt_count = INIT_PREEMPT_COUNT,	\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
 	.flags =	0,			\
 }
 
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index b171001..d3a831a 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -1231,7 +1231,7 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
 	int tm_restore = 0;
 #endif
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	rt_sf = (struct rt_sigframe __user *)
 		(regs->gpr[1] + __SIGNAL_FRAMESIZE + 16);
@@ -1504,7 +1504,7 @@ long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
 #endif
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	sf = (struct sigframe __user *)(regs->gpr[1] + __SIGNAL_FRAMESIZE);
 	sc = &sf->sctx;
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 2cb0c94..c7c24d2 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -666,7 +666,7 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5,
 #endif
 
 	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
+	current->restart_block.fn = do_no_restart_syscall;
 
 	if (!access_ok(VERIFY_READ, uc, sizeof(*uc)))
 		goto badframe;
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index fa7c4f1..7316dd1 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -621,6 +621,38 @@ unsigned long long sched_clock(void)
 	return mulhdu(get_tb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift;
 }
 
+
+#ifdef CONFIG_PPC_PSERIES
+
+/*
+ * Running clock - attempts to give a view of time passing for a virtualised
+ * kernels.
+ * Uses the VTB register if available otherwise a next best guess.
+ */
+unsigned long long running_clock(void)
+{
+	/*
+	 * Don't read the VTB as a host since KVM does not switch in host
+	 * timebase into the VTB when it takes a guest off the CPU, reading the
+	 * VTB would result in reading 'last switched out' guest VTB.
+	 *
+	 * Host kernels are often compiled with CONFIG_PPC_PSERIES checked, it
+	 * would be unsafe to rely only on the #ifdef above.
+	 */
+	if (firmware_has_feature(FW_FEATURE_LPAR) &&
+	    cpu_has_feature(CPU_FTR_ARCH_207S))
+		return mulhdu(get_vtb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift;
+
+	/*
+	 * This is a next best approximation without a VTB.
+	 * On a host which is running bare metal there should never be any stolen
+	 * time and on a host which doesn't do any virtualisation TB *should* equal
+	 * VTB so it makes no difference anyway.
+	 */
+	return local_clock() - cputime_to_nsecs(kcpustat_this_cpu->cpustat[CPUTIME_STEAL]);
+}
+#endif
+
 static int __init get_freq(char *name, int cells, unsigned long *val)
 {
 	struct device_node *cpu;
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 510bdfb..625407e 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -212,7 +212,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 	/* Look up the Linux PTE for the backing page */
 	pte_size = psize;
 	pte = lookup_linux_pte_and_update(pgdir, hva, writing, &pte_size);
-	if (pte_present(pte) && !pte_numa(pte)) {
+	if (pte_present(pte) && !pte_protnone(pte)) {
 		if (writing && !pte_write(pte))
 			/* make the actual HPTE be read-only */
 			ptel = hpte_make_readonly(ptel);
diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c
index 1b5305d..f031a47 100644
--- a/arch/powerpc/mm/copro_fault.c
+++ b/arch/powerpc/mm/copro_fault.c
@@ -64,10 +64,14 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
 		if (!(vma->vm_flags & VM_WRITE))
 			goto out_unlock;
 	} else {
-		if (dsisr & DSISR_PROTFAULT)
-			goto out_unlock;
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
 			goto out_unlock;
+		/*
+		 * protfault should only happen due to us
+		 * mapping a region readonly temporarily. PROT_NONE
+		 * is also covered by the VMA check above.
+		 */
+		WARN_ON_ONCE(dsisr & DSISR_PROTFAULT);
 	}
 
 	ret = 0;
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 6154b0a..b396868 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -389,19 +389,6 @@ good_area:
 #endif /* CONFIG_8xx */
 
 	if (is_exec) {
-#ifdef CONFIG_PPC_STD_MMU
-		/* Protection fault on exec go straight to failure on
-		 * Hash based MMUs as they either don't support per-page
-		 * execute permission, or if they do, it's handled already
-		 * at the hash level. This test would probably have to
-		 * be removed if we change the way this works to make hash
-		 * processors use the same I/D cache coherency mechanism
-		 * as embedded.
-		 */
-		if (error_code & DSISR_PROTFAULT)
-			goto bad_area;
-#endif /* CONFIG_PPC_STD_MMU */
-
 		/*
 		 * Allow execution from readable areas if the MMU does not
 		 * provide separate controls over reading and executing.
@@ -416,6 +403,14 @@ good_area:
 		    (cpu_has_feature(CPU_FTR_NOEXECUTE) ||
 		     !(vma->vm_flags & (VM_READ | VM_WRITE))))
 			goto bad_area;
+#ifdef CONFIG_PPC_STD_MMU
+		/*
+		 * protfault should only happen due to us
+		 * mapping a region readonly temporarily. PROT_NONE
+		 * is also covered by the VMA check above.
+		 */
+		WARN_ON_ONCE(error_code & DSISR_PROTFAULT);
+#endif /* CONFIG_PPC_STD_MMU */
 	/* a write */
 	} else if (is_write) {
 		if (!(vma->vm_flags & VM_WRITE))
@@ -423,11 +418,9 @@ good_area:
 		flags |= FAULT_FLAG_WRITE;
 	/* a read */
 	} else {
-		/* protection fault */
-		if (error_code & 0x08000000)
-			goto bad_area;
 		if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
 			goto bad_area;
+		WARN_ON_ONCE(error_code & DSISR_PROTFAULT);
 	}
 
 	/*
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index c90e602..83dfcb5 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -172,9 +172,14 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
 void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 		pte_t pte)
 {
-#ifdef CONFIG_DEBUG_VM
-	WARN_ON(pte_val(*ptep) & _PAGE_PRESENT);
-#endif
+	/*
+	 * When handling numa faults, we already have the pte marked
+	 * _PAGE_PRESENT, but we can be sure that it is not in hpte.
+	 * Hence we can use set_pte_at for them.
+	 */
+	VM_WARN_ON((pte_val(*ptep) & (_PAGE_PRESENT | _PAGE_USER)) ==
+		(_PAGE_PRESENT | _PAGE_USER));
+
 	/* Note: mm->context.id might not yet have been assigned as
 	 * this context might not have been activated yet when this
 	 * is called.
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 4fe5f64..91bb883 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -718,7 +718,8 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 		pmd_t *pmdp, pmd_t pmd)
 {
 #ifdef CONFIG_DEBUG_VM
-	WARN_ON(pmd_val(*pmdp) & _PAGE_PRESENT);
+	WARN_ON((pmd_val(*pmdp) & (_PAGE_PRESENT | _PAGE_USER)) ==
+		(_PAGE_PRESENT | _PAGE_USER));
 	assert_spin_locked(&mm->page_table_lock);
 	WARN_ON(!pmd_trans_huge(pmd));
 #endif