Changes representative of linux-3.10.0-123.el7.tar.xz

Makefile

@@ -5,7 +5,7 @@ EXTRAVERSION =
 NAME = Unicycling Gorilla
 RHEL_MAJOR = 7
 RHEL_MINOR = 0
-RHEL_RELEASE = 121
+RHEL_RELEASE = 123
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"

drivers/misc/mei/hw-me-regs.h

@@ -115,6 +115,11 @@
 #define MEI_DEV_ID_LPT_HR     0x8CBA  /* Lynx Point H Refresh */
 
 #define MEI_DEV_ID_WPT_LP     0x9CBA  /* Wildcat Point LP */
+
+/* Host Firmware Status Registers in PCI Config Space */
+#define PCI_CFG_HFS_1         0x40
+#define PCI_CFG_HFS_2         0x48
+
 /*
  * MEI HW Section
  */

drivers/misc/mei/pci-me.c

@@ -105,15 +105,31 @@ static bool mei_me_quirk_probe(struct pci_dev *pdev,
 				const struct pci_device_id *ent)
 {
 	u32 reg;
-	if (ent->device == MEI_DEV_ID_PBG_1) {
-		pci_read_config_dword(pdev, 0x48, &reg);
-		/* make sure that bit 9 is up and bit 10 is down */
-		if ((reg & 0x600) == 0x200) {
-			dev_info(&pdev->dev, "Device doesn't have valid ME Interface\n");
-			return false;
-		}
+	/* Cougar Point || Patsburg */
+	if (ent->device == MEI_DEV_ID_CPT_1 ||
+	    ent->device == MEI_DEV_ID_PBG_1) {
+		pci_read_config_dword(pdev, PCI_CFG_HFS_2, &reg);
+		/* make sure that bit 9 (NM) is up and bit 10 (DM) is down */
+		if ((reg & 0x600) == 0x200)
+			goto no_mei;
 	}
+
+	/* Lynx Point */
+	if (ent->device == MEI_DEV_ID_LPT_H  ||
+	    ent->device == MEI_DEV_ID_LPT_W  ||
+	    ent->device == MEI_DEV_ID_LPT_HR) {
+		/* Read ME FW Status check for SPS Firmware */
+		pci_read_config_dword(pdev, PCI_CFG_HFS_1, &reg);
+		/* if bits [19:16] = 15, running SPS Firmware */
+		if ((reg & 0xf0000) == 0xf0000)
+			goto no_mei;
+	}
+
 	return true;
+
+no_mei:
+	dev_info(&pdev->dev, "Device doesn't have valid ME Interface\n");
+	return false;
 }
 /**
  * mei_probe - Device Initialization Routine

fs/autofs4/root.c

@@ -179,7 +179,7 @@ static struct dentry *autofs4_lookup_active(struct dentry *dentry)
 		spin_lock(&active->d_lock);
 
 		/* Already gone? */
-		if (!d_count(active))
+		if ((int) d_count(active) <= 0)
 			goto next;
 
 		qstr = &active->d_name;
@@ -230,7 +230,7 @@ static struct dentry *autofs4_lookup_expiring(struct dentry *dentry)
 
 		spin_lock(&expiring->d_lock);
 
-		/* Bad luck, we've already been dentry_iput */
+		/* We've already been dentry_iput or unlinked */
 		if (!expiring->d_inode)
 			goto next;
 

mm/huge_memory.c

@@ -2255,7 +2255,34 @@ static void khugepaged_alloc_sleep(void)
 			msecs_to_jiffies(khugepaged_alloc_sleep_millisecs));
 }
 
+static int khugepaged_node_load[MAX_NUMNODES];
+
 #ifdef CONFIG_NUMA
+static int khugepaged_find_target_node(void)
+{
+	static int last_khugepaged_target_node = NUMA_NO_NODE;
+	int nid, target_node = 0, max_value = 0;
+
+	/* find first node with max normal pages hit */
+	for (nid = 0; nid < MAX_NUMNODES; nid++)
+		if (khugepaged_node_load[nid] > max_value) {
+			max_value = khugepaged_node_load[nid];
+			target_node = nid;
+		}
+
+	/* do some balance if several nodes have the same hit record */
+	if (target_node <= last_khugepaged_target_node)
+		for (nid = last_khugepaged_target_node + 1; nid < MAX_NUMNODES;
+				nid++)
+			if (max_value == khugepaged_node_load[nid]) {
+				target_node = nid;
+				break;
+			}
+
+	last_khugepaged_target_node = target_node;
+	return target_node;
+}
+
 static bool khugepaged_prealloc_page(struct page **hpage, bool *wait)
 {
 	if (IS_ERR(*hpage)) {
@@ -2289,9 +2316,8 @@ static struct page
 	 * mmap_sem in read mode is good idea also to allow greater
 	 * scalability.
 	 */
-	*hpage  = alloc_hugepage_vma(khugepaged_defrag(), vma, address,
-				      node, __GFP_OTHER_NODE);
-
+	*hpage = alloc_pages_exact_node(node, alloc_hugepage_gfpmask(
+		khugepaged_defrag(), __GFP_OTHER_NODE), HPAGE_PMD_ORDER);
 	/*
 	 * After allocating the hugepage, release the mmap_sem read lock in
 	 * preparation for taking it in write mode.
@@ -2307,6 +2333,11 @@ static struct page
 	return *hpage;
 }
 #else
+static int khugepaged_find_target_node(void)
+{
+	return 0;
+}
+
 static struct page *khugepaged_alloc_hugepage(bool *wait)
 {
 	struct page *hpage;
@@ -2512,6 +2543,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 	if (pmd_trans_huge(*pmd))
 		goto out;
 
+	memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load));
 	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
 	for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR;
 	     _pte++, _address += PAGE_SIZE) {
@@ -2528,12 +2560,13 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 		if (unlikely(!page))
 			goto out_unmap;
 		/*
-		 * Chose the node of the first page. This could
-		 * be more sophisticated and look at more pages,
-		 * but isn't for now.
+		 * Record which node the original page is from and save this
+		 * information to khugepaged_node_load[].
+		 * Khupaged will allocate hugepage from the node has the max
+		 * hit record.
 		 */
-		if (node == NUMA_NO_NODE)
-			node = page_to_nid(page);
+		node = page_to_nid(page);
+		khugepaged_node_load[node]++;
 		VM_BUG_ON(PageCompound(page));
 		if (!PageLRU(page) || PageLocked(page) || !PageAnon(page))
 			goto out_unmap;
@@ -2548,9 +2581,11 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 		ret = 1;
 out_unmap:
 	pte_unmap_unlock(pte, ptl);
-	if (ret)
+	if (ret) {
+		node = khugepaged_find_target_node();
 		/* collapse_huge_page will return with the mmap_sem released */
 		collapse_huge_page(mm, address, hpage, vma, node);
+	}
 out:
 	return ret;
 }

mm/mlock.c

@@ -76,6 +76,7 @@ void clear_page_mlock(struct page *page)
  */
 void mlock_vma_page(struct page *page)
 {
+	/* Serialize with page migration */
 	BUG_ON(!PageLocked(page));
 
 	if (!TestSetPageMlocked(page)) {
@@ -106,6 +107,7 @@ unsigned int munlock_vma_page(struct page *page)
 {
 	unsigned int page_mask = 0;
 
+	/* For try_to_munlock() and to serialize with page migration */
 	BUG_ON(!PageLocked(page));
 
 	if (TestClearPageMlocked(page)) {

mm/mprotect.c

@@ -36,6 +36,34 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 }
 #endif
 
+/*
+ * For a prot_numa update we only hold mmap_sem for read so there is a
+ * potential race with faulting where a pmd was temporarily none. This
+ * function checks for a transhuge pmd under the appropriate lock. It
+ * returns a pte if it was successfully locked or NULL if it raced with
+ * a transhuge insertion.
+ */
+static pte_t *lock_pte_protection(struct vm_area_struct *vma, pmd_t *pmd,
+			unsigned long addr, int prot_numa, spinlock_t **ptl)
+{
+	pte_t *pte;
+	spinlock_t *pmdl;
+
+	/* !prot_numa is protected by mmap_sem held for write */
+	if (!prot_numa)
+		return pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl);
+
+	pmdl = pmd_lock(vma->vm_mm, pmd);
+	if (unlikely(pmd_trans_huge(*pmd) || pmd_none(*pmd))) {
+		spin_unlock(pmdl);
+		return NULL;
+	}
+
+	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, ptl);
+	spin_unlock(pmdl);
+	return pte;
+}
+
 static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
 		int dirty_accountable, int prot_numa)
@@ -45,17 +73,9 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	spinlock_t *ptl;
 	unsigned long pages = 0;
 
-	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
-
-	/*
-	 * For a prot_numa update we only hold mmap_sem for read so there is a
-	 * potential race with faulting where a pmd was temporarily none so
-	 * recheck it under the lock and bail if we race
-	 */
-	if (prot_numa && unlikely(pmd_trans_huge(*pmd))) {
-		pte_unmap_unlock(pte, ptl);
+	pte = lock_pte_protection(vma, pmd, addr, prot_numa, &ptl);
+	if (!pte)
 		return 0;
-	}
 
 	arch_enter_lazy_mmu_mode();
 	do {

mm/rmap.c

@@ -1384,9 +1384,19 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
 		BUG_ON(!page || PageAnon(page));
 
 		if (locked_vma) {
-			mlock_vma_page(page);   /* no-op if already mlocked */
-			if (page == check_page)
+			if (page == check_page) {
+				/* we know we have check_page locked */
+				mlock_vma_page(page);
 				ret = SWAP_MLOCK;
+			} else if (trylock_page(page)) {
+				/*
+				 * If we can lock the page, perform mlock.
+				 * Otherwise leave the page alone, it will be
+				 * eventually encountered again later.
+				 */
+				mlock_vma_page(page);
+				unlock_page(page);
+			}
 			continue;	/* don't unmap */
 		}