kernel/x86-mm-fix-pgd_lock-deadlock.patch

Backport to 2.6.35:

 commit a79e53d85683c6dd9f99c90511028adc2043031f
 x86/mm: Fix pgd_lock deadlock

This is needed because:

 commit 4981d01eada5354d81c8929d5b2836829ba3df7b
 x86: Flush TLB if PGD entry is changed in i386 PAE mode)

was added in 2.6.35.12 and caused deadlocks fixed by this patch.

Signed-off-by: Chuck Ebbert <cebbert@redhat.com>
---
BZ 699684

--- linux-2.6.35.noarch.orig/arch/x86/mm/fault.c
+++ linux-2.6.35.noarch/arch/x86/mm/fault.c
@@ -224,15 +224,14 @@ void vmalloc_sync_all(void)
 	     address >= TASK_SIZE && address < FIXADDR_TOP;
 	     address += PMD_SIZE) {
 
-		unsigned long flags;
 		struct page *page;
 
-		spin_lock_irqsave(&pgd_lock, flags);
+		spin_lock(&pgd_lock);
 		list_for_each_entry(page, &pgd_list, lru) {
 			if (!vmalloc_sync_one(page_address(page), address))
 				break;
 		}
-		spin_unlock_irqrestore(&pgd_lock, flags);
+		spin_unlock(&pgd_lock);
 	}
 }
 
@@ -332,13 +331,12 @@ void vmalloc_sync_all(void)
 	     address += PGDIR_SIZE) {
 
 		const pgd_t *pgd_ref = pgd_offset_k(address);
-		unsigned long flags;
 		struct page *page;
 
 		if (pgd_none(*pgd_ref))
 			continue;
 
-		spin_lock_irqsave(&pgd_lock, flags);
+		spin_lock(&pgd_lock);
 		list_for_each_entry(page, &pgd_list, lru) {
 			pgd_t *pgd;
 			pgd = (pgd_t *)page_address(page) + pgd_index(address);
@@ -347,7 +345,7 @@ void vmalloc_sync_all(void)
 			else
 				BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
 		}
-		spin_unlock_irqrestore(&pgd_lock, flags);
+		spin_unlock(&pgd_lock);
 	}
 }
 
--- linux-2.6.35.noarch.orig/arch/x86/xen/mmu.c
+++ linux-2.6.35.noarch/arch/x86/xen/mmu.c
@@ -988,10 +988,9 @@ static void xen_pgd_pin(struct mm_struct
  */
 void xen_mm_pin_all(void)
 {
-	unsigned long flags;
 	struct page *page;
 
-	spin_lock_irqsave(&pgd_lock, flags);
+	spin_lock(&pgd_lock);
 
 	list_for_each_entry(page, &pgd_list, lru) {
 		if (!PagePinned(page)) {
@@ -1000,7 +999,7 @@ void xen_mm_pin_all(void)
 		}
 	}
 
-	spin_unlock_irqrestore(&pgd_lock, flags);
+	spin_unlock(&pgd_lock);
 }
 
 /*
@@ -1101,10 +1100,9 @@ static void xen_pgd_unpin(struct mm_stru
  */
 void xen_mm_unpin_all(void)
 {
-	unsigned long flags;
 	struct page *page;
 
-	spin_lock_irqsave(&pgd_lock, flags);
+	spin_lock(&pgd_lock);
 
 	list_for_each_entry(page, &pgd_list, lru) {
 		if (PageSavePinned(page)) {
@@ -1114,7 +1112,7 @@ void xen_mm_unpin_all(void)
 		}
 	}
 
-	spin_unlock_irqrestore(&pgd_lock, flags);
+	spin_unlock(&pgd_lock);
 }
 
 void xen_activate_mm(struct mm_struct *prev, struct mm_struct *next)
--- linux-2.6.35.noarch.orig/arch/x86/mm/pageattr.c
+++ linux-2.6.35.noarch/arch/x86/mm/pageattr.c
@@ -56,12 +56,10 @@ static unsigned long direct_pages_count[
 
 void update_page_count(int level, unsigned long pages)
 {
-	unsigned long flags;
-
 	/* Protect against CPA */
-	spin_lock_irqsave(&pgd_lock, flags);
+	spin_lock(&pgd_lock);
 	direct_pages_count[level] += pages;
-	spin_unlock_irqrestore(&pgd_lock, flags);
+	spin_unlock(&pgd_lock);
 }
 
 static void split_page_count(int level)
@@ -391,7 +389,7 @@ static int
 try_preserve_large_page(pte_t *kpte, unsigned long address,
 			struct cpa_data *cpa)
 {
-	unsigned long nextpage_addr, numpages, pmask, psize, flags, addr, pfn;
+	unsigned long nextpage_addr, numpages, pmask, psize, addr, pfn;
 	pte_t new_pte, old_pte, *tmp;
 	pgprot_t old_prot, new_prot;
 	int i, do_split = 1;
@@ -400,7 +398,7 @@ try_preserve_large_page(pte_t *kpte, uns
 	if (cpa->force_split)
 		return 1;
 
-	spin_lock_irqsave(&pgd_lock, flags);
+	spin_lock(&pgd_lock);
 	/*
 	 * Check for races, another CPU might have split this page
 	 * up already:
@@ -495,14 +493,14 @@ try_preserve_large_page(pte_t *kpte, uns
 	}
 
 out_unlock:
-	spin_unlock_irqrestore(&pgd_lock, flags);
+	spin_unlock(&pgd_lock);
 
 	return do_split;
 }
 
 static int split_large_page(pte_t *kpte, unsigned long address)
 {
-	unsigned long flags, pfn, pfninc = 1;
+	unsigned long pfn, pfninc = 1;
 	unsigned int i, level;
 	pte_t *pbase, *tmp;
 	pgprot_t ref_prot;
@@ -516,7 +514,7 @@ static int split_large_page(pte_t *kpte,
 	if (!base)
 		return -ENOMEM;
 
-	spin_lock_irqsave(&pgd_lock, flags);
+	spin_lock(&pgd_lock);
 	/*
 	 * Check for races, another CPU might have split this page
 	 * up for us already:
@@ -588,7 +586,7 @@ out_unlock:
 	 */
 	if (base)
 		__free_page(base);
-	spin_unlock_irqrestore(&pgd_lock, flags);
+	spin_unlock(&pgd_lock);
 
 	return 0;
 }
--- linux-2.6.35.noarch.orig/arch/x86/mm/pgtable.c
+++ linux-2.6.35.noarch/arch/x86/mm/pgtable.c
@@ -111,14 +111,12 @@ static void pgd_ctor(pgd_t *pgd)
 
 static void pgd_dtor(pgd_t *pgd)
 {
-	unsigned long flags; /* can be called from interrupt context */
-
 	if (SHARED_KERNEL_PMD)
 		return;
 
-	spin_lock_irqsave(&pgd_lock, flags);
+	spin_lock(&pgd_lock);
 	pgd_list_del(pgd);
-	spin_unlock_irqrestore(&pgd_lock, flags);
+	spin_unlock(&pgd_lock);
 }
 
 /*
@@ -249,7 +247,6 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	pgd_t *pgd;
 	pmd_t *pmds[PREALLOCATED_PMDS];
-	unsigned long flags;
 
 	pgd = (pgd_t *)__get_free_page(PGALLOC_GFP);
 
@@ -269,12 +266,12 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 	 * respect to anything walking the pgd_list, so that they
 	 * never see a partially populated pgd.
 	 */
-	spin_lock_irqsave(&pgd_lock, flags);
+	spin_lock(&pgd_lock);
 
 	pgd_ctor(pgd);
 	pgd_prepopulate_pmd(mm, pgd, pmds);
 
-	spin_unlock_irqrestore(&pgd_lock, flags);
+	spin_unlock(&pgd_lock);
 
 	return pgd;