-- /dev/null

++ linux-2.6.32-2.6.32/debian/patches/bugfix/x86/x86-mm-Fix-pgd_lock-deadlock.patch

-- linux-2.6.32-2.6.32/debian/patches/series/37-extra

It's forbidden to take the page_table_lock with the irq disabled

or if there's contention the IPIs (for tlb flushes) sent with

the page_table_lock held will never run leading to a deadlock.

Nobody takes the pgd_lock from irq context so the _irqsave can be

removed.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>

Acked-by: Rik van Riel <riel@redhat.com>

Tested-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>

Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Cc: Peter Zijlstra <peterz@infradead.org>

Cc: Linus Torvalds <torvalds@linux-foundation.org>

Cc: <stable@kernel.org>

LKML-Reference: <201102162345.p1GNjMjm021738@imap1.linux-foundation.org>

Signed-off-by: Ingo Molnar <mingo@elte.hu>

Git-commit: a79e53d85683c6dd9f99c90511028adc2043031f

--- a/arch/x86/mm/fault.c

+++ b/arch/x86/mm/fault.c

@@ -223,15 +223,14 @@ 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);

 	}

 }

@@ -331,13 +330,12 @@ 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);

@@ -346,7 +344,7 @@ 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);

 	}

 }

--- a/arch/x86/mm/pageattr.c

+++ b/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)

@@ -354,7 +352,7 @@ 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;

@@ -363,7 +361,7 @@ 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:

@@ -458,14 +456,14 @@ 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;

@@ -479,7 +477,7 @@ 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:

@@ -551,7 +549,7 @@ out_unlock:

 	 */

 	if (base)

 		__free_page(base);

-	spin_unlock_irqrestore(&pgd_lock, flags);

+	spin_unlock(&pgd_lock);

 	return 0;

 }

--- a/arch/x86/mm/pgtable.c

+++ b/arch/x86/mm/pgtable.c

@@ -110,14 +110,12 @@ 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);

 }

 /*

@@ -248,7 +246,6 @@ 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);

@@ -268,12 +265,12 @@ 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;

--- a/arch/x86/xen/mmu.c

+++ b/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-2.6.32-2.6.32/debian/patches/series/38

++ linux-2.6.32-2.6.32/debian/patches/series/38