Linux 3.0.83

commit 92a49fb0f7 upstream.

Different versions of glibc are broken in different ways, but the short of
it is that for the time being, frsize should == bsize, and be used as the
multiple for the blocks, free, and available fields.  This mirrors what is
done for NFS.  The previous reporting of the page size for frsize meant
that newer glibc and df would report a very small value for the fs size.

Fixes http://tracker.ceph.com/issues/3793.

Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Makefile

@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 0
-SUBLEVEL = 82
+SUBLEVEL = 83
 EXTRAVERSION =
 NAME = Sneaky Weasel
 

arch/x86/kernel/relocate_kernel_64.S

@@ -160,7 +160,7 @@ identity_mapped:
 	xorq    %rbp, %rbp
 	xorq	%r8,  %r8
 	xorq	%r9,  %r9
-	xorq	%r10, %r9
+	xorq	%r10, %r10
 	xorq	%r11, %r11
 	xorq	%r12, %r12
 	xorq	%r13, %r13

drivers/gpu/drm/i915/intel_sdvo.c

@@ -1610,10 +1610,13 @@ static void intel_sdvo_get_lvds_modes(struct drm_connector *connector)
 	 * arranged in priority order.
 	 */
 	intel_ddc_get_modes(connector, &intel_sdvo->ddc);
-	if (list_empty(&connector->probed_modes) == false)
-		goto end;
 
-	/* Fetch modes from VBT */
+	/*
+	 * Fetch modes from VBT. For SDVO prefer the VBT mode since some
+	 * SDVO->LVDS transcoders can't cope with the EDID mode. Since
+	 * drm_mode_probed_add adds the mode at the head of the list we add it
+	 * last.
+	 */
 	if (dev_priv->sdvo_lvds_vbt_mode != NULL) {
 		newmode = drm_mode_duplicate(connector->dev,
 					     dev_priv->sdvo_lvds_vbt_mode);
@@ -1625,7 +1628,6 @@ static void intel_sdvo_get_lvds_modes(struct drm_connector *connector)
 		}
 	}
 
-end:
 	list_for_each_entry(newmode, &connector->probed_modes, head) {
 		if (newmode->type & DRM_MODE_TYPE_PREFERRED) {
 			intel_sdvo->sdvo_lvds_fixed_mode =

drivers/net/wireless/ath/ath9k/init.c

@@ -704,8 +704,7 @@ void ath9k_set_hw_capab(struct ath_softc *sc, struct ieee80211_hw *hw)
 		BIT(NL80211_IFTYPE_ADHOC) |
 		BIT(NL80211_IFTYPE_MESH_POINT);
 
-	if (AR_SREV_5416(sc->sc_ah))
-		hw->wiphy->flags &= ~WIPHY_FLAG_PS_ON_BY_DEFAULT;
+	hw->wiphy->flags &= ~WIPHY_FLAG_PS_ON_BY_DEFAULT;
 
 	hw->wiphy->flags |= WIPHY_FLAG_IBSS_RSN;
 

drivers/net/wireless/b43/main.c

@@ -2309,7 +2309,7 @@ static int b43_request_firmware(struct b43_wldev *dev)
 	for (i = 0; i < B43_NR_FWTYPES; i++) {
 		errmsg = ctx->errors[i];
 		if (strlen(errmsg))
-			b43err(dev->wl, errmsg);
+			b43err(dev->wl, "%s", errmsg);
 	}
 	b43_print_fw_helptext(dev->wl, 1);
 	err = -ENOENT;

fs/ceph/super.c

@@ -70,8 +70,14 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 	/*
 	 * express utilization in terms of large blocks to avoid
 	 * overflow on 32-bit machines.
+	 *
+	 * NOTE: for the time being, we make bsize == frsize to humor
+	 * not-yet-ancient versions of glibc that are broken.
+	 * Someday, we will probably want to report a real block
+	 * size...  whatever that may mean for a network file system!
 	 */
 	buf->f_bsize = 1 << CEPH_BLOCK_SHIFT;
+	buf->f_frsize = 1 << CEPH_BLOCK_SHIFT;
 	buf->f_blocks = le64_to_cpu(st.kb) >> (CEPH_BLOCK_SHIFT-10);
 	buf->f_bfree = (le64_to_cpu(st.kb) - le64_to_cpu(st.kb_used)) >>
 		(CEPH_BLOCK_SHIFT-10);
@@ -80,7 +86,6 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_files = le64_to_cpu(st.num_objects);
 	buf->f_ffree = -1;
 	buf->f_namelen = NAME_MAX;
-	buf->f_frsize = PAGE_CACHE_SIZE;
 
 	/* leave fsid little-endian, regardless of host endianness */
 	fsid = *(u64 *)(&monmap->fsid) ^ *((u64 *)&monmap->fsid + 1);

fs/ceph/super.h

@@ -21,7 +21,7 @@
 
 /* large granularity for statfs utilization stats to facilitate
  * large volume sizes on 32-bit machines. */
-#define CEPH_BLOCK_SHIFT   20  /* 1 MB */
+#define CEPH_BLOCK_SHIFT   22  /* 4 MB */
 #define CEPH_BLOCK         (1 << CEPH_BLOCK_SHIFT)
 
 #define CEPH_MOUNT_OPT_DIRSTAT         (1<<4) /* `cat dirname` for stats */

include/linux/swapops.h

@@ -113,6 +113,7 @@ static inline void make_migration_entry_read(swp_entry_t *entry)
 
 extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 					unsigned long address);
+extern void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte);
 #else
 
 #define make_migration_entry(page, write) swp_entry(0, 0)
@@ -124,6 +125,8 @@ static inline int is_migration_entry(swp_entry_t swp)
 static inline void make_migration_entry_read(swp_entry_t *entryp) { }
 static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
 					 unsigned long address) { }
+static inline void migration_entry_wait_huge(struct mm_struct *mm,
+					pte_t *pte) { }
 static inline int is_write_migration_entry(swp_entry_t entry)
 {
 	return 0;

mm/hugetlb.c

@@ -2662,7 +2662,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (ptep) {
 		entry = huge_ptep_get(ptep);
 		if (unlikely(is_hugetlb_entry_migration(entry))) {
-			migration_entry_wait(mm, (pmd_t *)ptep, address);
+			migration_entry_wait_huge(mm, ptep);
 			return 0;
 		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
 			return VM_FAULT_HWPOISON_LARGE | 

mm/migrate.c

@@ -184,15 +184,14 @@ static void remove_migration_ptes(struct page *old, struct page *new)
  *
  * This function is called from do_swap_page().
  */
-void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
-				unsigned long address)
+static void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
+				spinlock_t *ptl)
 {
-	pte_t *ptep, pte;
-	spinlock_t *ptl;
+	pte_t pte;
 	swp_entry_t entry;
 	struct page *page;
 
-	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
+	spin_lock(ptl);
 	pte = *ptep;
 	if (!is_swap_pte(pte))
 		goto out;
@@ -220,6 +219,20 @@ out:
 	pte_unmap_unlock(ptep, ptl);
 }
 
+void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
+				unsigned long address)
+{
+	spinlock_t *ptl = pte_lockptr(mm, pmd);
+	pte_t *ptep = pte_offset_map(pmd, address);
+	__migration_entry_wait(mm, ptep, ptl);
+}
+
+void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte)
+{
+	spinlock_t *ptl = &(mm)->page_table_lock;
+	__migration_entry_wait(mm, pte, ptl);
+}
+
 #ifdef CONFIG_BLOCK
 /* Returns true if all buffers are successfully locked */
 static bool buffer_migrate_lock_buffers(struct buffer_head *head,

mm/swap_state.c

@@ -315,8 +315,24 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		 * Swap entry may have been freed since our caller observed it.
 		 */
 		err = swapcache_prepare(entry);
-		if (err == -EEXIST) {	/* seems racy */
+		if (err == -EEXIST) {
 			radix_tree_preload_end();
+			/*
+			 * We might race against get_swap_page() and stumble
+			 * across a SWAP_HAS_CACHE swap_map entry whose page
+			 * has not been brought into the swapcache yet, while
+			 * the other end is scheduled away waiting on discard
+			 * I/O completion at scan_swap_map().
+			 *
+			 * In order to avoid turning this transitory state
+			 * into a permanent loop around this -EEXIST case
+			 * if !CONFIG_PREEMPT and the I/O completion happens
+			 * to be waiting on the CPU waitqueue where we are now
+			 * busy looping, we just conditionally invoke the
+			 * scheduler here, if there are some more important
+			 * tasks to run.
+			 */
+			cond_resched();
 			continue;
 		}
 		if (err) {		/* swp entry is obsolete ? */