Merge tag 'v3.15-rc1' into patchwork

Linux 3.15-rc1

* tag 'v3.15-rc1': (12180 commits)
  Linux 3.15-rc1
  mm: Initialize error in shmem_file_aio_read()
  cifs: Use min_t() when comparing "size_t" and "unsigned long"
  sym53c8xx_2: Set DID_REQUEUE return code when aborting squeue
  powerpc: Don't try to set LPCR unless we're in hypervisor mode
  futex: update documentation for ordering guarantees
  ceph: fix pr_fmt() redefinition
  vti: don't allow to add the same tunnel twice
  gre: don't allow to add the same tunnel twice
  drivers: net: xen-netfront: fix array initialization bug
  missing bits of "splice: fix racy pipe->buffers uses"
  cifs: fix the race in cifs_writev()
  ceph_sync_{,direct_}write: fix an oops on ceph_osdc_new_request() failure
  pktgen: be friendly to LLTX devices
  r8152: check RTL8152_UNPLUG
  net: sun4i-emac: add promiscuous support
  net/apne: replace IS_ERR and PTR_ERR with PTR_ERR_OR_ZERO
  blackfin: cleanup board files
  bf609: clock: drop unused clock bit set/clear functions
  Blackfin: bf537: rename "CONFIG_ADT75"
  ...

1 files changed, 46 insertions, 24 deletions

diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index b3b19f46c016..ae242a7c11c7 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -126,8 +126,8 @@ within(unsigned long addr, unsigned long start, unsigned long end)
  * @vaddr:	virtual start address
  * @size:	number of bytes to flush
  *
- * clflush is an unordered instruction which needs fencing with mfence
- * to avoid ordering issues.
+ * clflushopt is an unordered instruction which needs fencing with mfence or
+ * sfence to avoid ordering issues.
  */
 void clflush_cache_range(void *vaddr, unsigned int size)
 {
@@ -136,11 +136,11 @@ void clflush_cache_range(void *vaddr, unsigned int size)
 	mb();
 
 	for (; vaddr < vend; vaddr += boot_cpu_data.x86_clflush_size)
-		clflush(vaddr);
+		clflushopt(vaddr);
 	/*
 	 * Flush any possible final partial cacheline:
 	 */
-	clflush(vend);
+	clflushopt(vend);
 
 	mb();
 }
@@ -323,8 +323,12 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
 	return prot;
 }
 
-static pte_t *__lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
-				      unsigned int *level)
+/*
+ * Lookup the page table entry for a virtual address in a specific pgd.
+ * Return a pointer to the entry and the level of the mapping.
+ */
+pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
+			     unsigned int *level)
 {
 	pud_t *pud;
 	pmd_t *pmd;
@@ -365,7 +369,7 @@ static pte_t *__lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
  */
 pte_t *lookup_address(unsigned long address, unsigned int *level)
 {
-        return __lookup_address_in_pgd(pgd_offset_k(address), address, level);
+        return lookup_address_in_pgd(pgd_offset_k(address), address, level);
 }
 EXPORT_SYMBOL_GPL(lookup_address);
 
@@ -373,7 +377,7 @@ static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address,
 				  unsigned int *level)
 {
         if (cpa->pgd)
-		return __lookup_address_in_pgd(cpa->pgd + pgd_index(address),
+		return lookup_address_in_pgd(cpa->pgd + pgd_index(address),
 					       address, level);
 
         return lookup_address(address, level);
@@ -692,6 +696,18 @@ static bool try_to_free_pmd_page(pmd_t *pmd)
 	return true;
 }
 
+static bool try_to_free_pud_page(pud_t *pud)
+{
+	int i;
+
+	for (i = 0; i < PTRS_PER_PUD; i++)
+		if (!pud_none(pud[i]))
+			return false;
+
+	free_page((unsigned long)pud);
+	return true;
+}
+
 static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end)
 {
 	pte_t *pte = pte_offset_kernel(pmd, start);
@@ -805,6 +821,16 @@ static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
 	 */
 }
 
+static void unmap_pgd_range(pgd_t *root, unsigned long addr, unsigned long end)
+{
+	pgd_t *pgd_entry = root + pgd_index(addr);
+
+	unmap_pud_range(pgd_entry, addr, end);
+
+	if (try_to_free_pud_page((pud_t *)pgd_page_vaddr(*pgd_entry)))
+		pgd_clear(pgd_entry);
+}
+
 static int alloc_pte_page(pmd_t *pmd)
 {
 	pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
@@ -999,9 +1025,8 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
 static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
 {
 	pgprot_t pgprot = __pgprot(_KERNPG_TABLE);
-	bool allocd_pgd = false;
-	pgd_t *pgd_entry;
 	pud_t *pud = NULL;	/* shut up gcc */
+	pgd_t *pgd_entry;
 	int ret;
 
 	pgd_entry = cpa->pgd + pgd_index(addr);
@@ -1015,7 +1040,6 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
 			return -1;
 
 		set_pgd(pgd_entry, __pgd(__pa(pud) | _KERNPG_TABLE));
-		allocd_pgd = true;
 	}
 
 	pgprot_val(pgprot) &= ~pgprot_val(cpa->mask_clr);
@@ -1023,19 +1047,11 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
 
 	ret = populate_pud(cpa, addr, pgd_entry, pgprot);
 	if (ret < 0) {
-		unmap_pud_range(pgd_entry, addr,
+		unmap_pgd_range(cpa->pgd, addr,
 				addr + (cpa->numpages << PAGE_SHIFT));
-
-		if (allocd_pgd) {
-			/*
-			 * If I allocated this PUD page, I can just as well
-			 * free it in this error path.
-			 */
-			pgd_clear(pgd_entry);
-			free_page((unsigned long)pud);
-		}
 		return ret;
 	}
+
 	cpa->numpages = ret;
 	return 0;
 }
@@ -1377,10 +1393,10 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 	cache = cache_attr(mask_set);
 
 	/*
-	 * On success we use clflush, when the CPU supports it to
-	 * avoid the wbindv. If the CPU does not support it and in the
+	 * On success we use CLFLUSH, when the CPU supports it to
+	 * avoid the WBINVD. If the CPU does not support it and in the
 	 * error case we fall back to cpa_flush_all (which uses
-	 * wbindv):
+	 * WBINVD):
 	 */
 	if (!ret && cpu_has_clflush) {
 		if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
@@ -1861,6 +1877,12 @@ out:
 	return retval;
 }
 
+void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address,
+			       unsigned numpages)
+{
+	unmap_pgd_range(root, address, address + (numpages << PAGE_SHIFT));
+}
+
 /*
  * The testcases use internal knowledge of the implementation that shouldn't
  * be exposed to the rest of the kernel. Include these directly here.