Merge branch 'stable' of git://git.kernel.org/pub/scm/linux/kernel/git/cmetcalf/linux-tile

Pull arch/tile bug fixes from Chris Metcalf:
 "This includes Paul Gortmaker's change to fix the <asm/system.h>
  disintegration issues on tile, a fix to unbreak the tilepro ethernet
  driver, and a backlog of bugfix-only changes from internal Tilera
  development over the last few months.

  They have all been to LKML and on linux-next for the last few days.
  The EDAC change to MAINTAINERS is an oddity but discussion on the
  linux-edac list suggested I ask you to pull that change through my
  tree since they don't have a tree to pull edac changes from at the
  moment."

* 'stable' of git://git.kernel.org/pub/scm/linux/kernel/git/cmetcalf/linux-tile: (39 commits)
  drivers/net/ethernet/tile: fix netdev_alloc_skb() bombing
  MAINTAINERS: update EDAC information
  tilepro ethernet driver: fix a few minor issues
  tile-srom.c driver: minor code cleanup
  edac: say "TILEGx" not "TILEPro" for the tilegx edac driver
  arch/tile: avoid accidentally unmasking NMI-type interrupt accidentally
  arch/tile: remove bogus performance optimization
  arch/tile: return SIGBUS for addresses that are unaligned AND invalid
  arch/tile: fix finv_buffer_remote() for tilegx
  arch/tile: use atomic exchange in arch_write_unlock()
  arch/tile: stop mentioning the "kvm" subdirectory
  arch/tile: export the page_home() function.
  arch/tile: fix pointer cast in cacheflush.c
  arch/tile: fix single-stepping over swint1 instructions on tilegx
  arch/tile: implement panic_smp_self_stop()
  arch/tile: add "nop" after "nap" to help GX idle power draw
  arch/tile: use proper memparse() for "maxmem" options
  arch/tile: fix up locking in pgtable.c slightly
  arch/tile: don't leak kernel memory when we unload modules
  arch/tile: fix bug in delay_backoff()
  ...

1 files changed, 24 insertions, 14 deletions

diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c
index 87303693a07..2410aa899b3 100644
--- a/arch/tile/mm/pgtable.c
+++ b/arch/tile/mm/pgtable.c
@@ -177,14 +177,10 @@ void shatter_huge_page(unsigned long addr)
 	if (!pmd_huge_page(*pmd))
 		return;
 
-	/*
-	 * Grab the pgd_lock, since we may need it to walk the pgd_list,
-	 * and since we need some kind of lock here to avoid races.
-	 */
-	spin_lock_irqsave(&pgd_lock, flags);
+	spin_lock_irqsave(&init_mm.page_table_lock, flags);
 	if (!pmd_huge_page(*pmd)) {
 		/* Lost the race to convert the huge page. */
-		spin_unlock_irqrestore(&pgd_lock, flags);
+		spin_unlock_irqrestore(&init_mm.page_table_lock, flags);
 		return;
 	}
 
@@ -194,6 +190,7 @@ void shatter_huge_page(unsigned long addr)
 
 #ifdef __PAGETABLE_PMD_FOLDED
 	/* Walk every pgd on the system and update the pmd there. */
+	spin_lock(&pgd_lock);
 	list_for_each(pos, &pgd_list) {
 		pmd_t *copy_pmd;
 		pgd = list_to_pgd(pos) + pgd_index(addr);
@@ -201,6 +198,7 @@ void shatter_huge_page(unsigned long addr)
 		copy_pmd = pmd_offset(pud, addr);
 		__set_pmd(copy_pmd, *pmd);
 	}
+	spin_unlock(&pgd_lock);
 #endif
 
 	/* Tell every cpu to notice the change. */
@@ -208,7 +206,7 @@ void shatter_huge_page(unsigned long addr)
 		     cpu_possible_mask, NULL, 0);
 
 	/* Hold the lock until the TLB flush is finished to avoid races. */
-	spin_unlock_irqrestore(&pgd_lock, flags);
+	spin_unlock_irqrestore(&init_mm.page_table_lock, flags);
 }
 
 /*
@@ -217,9 +215,13 @@ void shatter_huge_page(unsigned long addr)
  * against pageattr.c; it is the unique case in which a valid change
  * of kernel pagetables can't be lazily synchronized by vmalloc faults.
  * vmalloc faults work because attached pagetables are never freed.
- * The locking scheme was chosen on the basis of manfred's
- * recommendations and having no core impact whatsoever.
- * -- wli
+ *
+ * The lock is always taken with interrupts disabled, unlike on x86
+ * and other platforms, because we need to take the lock in
+ * shatter_huge_page(), which may be called from an interrupt context.
+ * We are not at risk from the tlbflush IPI deadlock that was seen on
+ * x86, since we use the flush_remote() API to have the hypervisor do
+ * the TLB flushes regardless of irq disabling.
  */
 DEFINE_SPINLOCK(pgd_lock);
 LIST_HEAD(pgd_list);
@@ -469,10 +471,18 @@ void __set_pte(pte_t *ptep, pte_t pte)
 
 void set_pte(pte_t *ptep, pte_t pte)
 {
-	struct page *page = pfn_to_page(pte_pfn(pte));
-
-	/* Update the home of a PTE if necessary */
-	pte = pte_set_home(pte, page_home(page));
+	if (pte_present(pte) &&
+	    (!CHIP_HAS_MMIO() || hv_pte_get_mode(pte) != HV_PTE_MODE_MMIO)) {
+		/* The PTE actually references physical memory. */
+		unsigned long pfn = pte_pfn(pte);
+		if (pfn_valid(pfn)) {
+			/* Update the home of the PTE from the struct page. */
+			pte = pte_set_home(pte, page_home(pfn_to_page(pfn)));
+		} else if (hv_pte_get_mode(pte) == 0) {
+			/* remap_pfn_range(), etc, must supply PTE mode. */
+			panic("set_pte(): out-of-range PFN and mode 0\n");
+		}
+	}
 
 	__set_pte(ptep, pte);
 }