Merge tag 'powerpc-4.1-4' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux

Pull powerpc fixes from Michael Ellerman:

 - THP/hugetlb fixes from Aneesh.

 - MCE fix from Daniel.

 - TOC fix from Anton.

* tag 'powerpc-4.1-4' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux:
  powerpc: Align TOC to 256 bytes
  powerpc/mce: fix off by one errors in mce event handling
  powerpc/mm: Return NULL for not present hugetlb page
  powerpc/thp: Serialize pmd clear against a linux page table walk.

4 files changed, 30 insertions, 11 deletions

diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 15c99b649b04..b2eb4686bd8f 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -73,7 +73,7 @@ void save_mce_event(struct pt_regs *regs, long handled,
 		    uint64_t nip, uint64_t addr)
 {
 	uint64_t srr1;
-	int index = __this_cpu_inc_return(mce_nest_count);
+	int index = __this_cpu_inc_return(mce_nest_count) - 1;
 	struct machine_check_event *mce = this_cpu_ptr(&mce_event[index]);
 
 	/*
@@ -184,7 +184,7 @@ void machine_check_queue_event(void)
 	if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
 		return;
 
-	index = __this_cpu_inc_return(mce_queue_count);
+	index = __this_cpu_inc_return(mce_queue_count) - 1;
 	/* If queue is full, just return for now. */
 	if (index >= MAX_MC_EVT) {
 		__this_cpu_dec(mce_queue_count);
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index f096e72262f4..1db685104ffc 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -213,6 +213,7 @@ SECTIONS
 		*(.opd)
 	}
 
+	. = ALIGN(256);
 	.got : AT(ADDR(.got) - LOAD_OFFSET) {
 		__toc_start = .;
 #ifndef CONFIG_RELOCATABLE
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 0ce968b00b7c..3385e3d0506e 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -689,27 +689,34 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 struct page *
 follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
 {
-	pte_t *ptep;
-	struct page *page;
+	pte_t *ptep, pte;
 	unsigned shift;
 	unsigned long mask, flags;
+	struct page *page = ERR_PTR(-EINVAL);
+
+	local_irq_save(flags);
+	ptep = find_linux_pte_or_hugepte(mm->pgd, address, &shift);
+	if (!ptep)
+		goto no_page;
+	pte = READ_ONCE(*ptep);
 	/*
+	 * Verify it is a huge page else bail.
 	 * Transparent hugepages are handled by generic code. We can skip them
 	 * here.
 	 */
-	local_irq_save(flags);
-	ptep = find_linux_pte_or_hugepte(mm->pgd, address, &shift);
+	if (!shift || pmd_trans_huge(__pmd(pte_val(pte))))
+		goto no_page;
 
-	/* Verify it is a huge page else bail. */
-	if (!ptep || !shift || pmd_trans_huge(*(pmd_t *)ptep)) {
-		local_irq_restore(flags);
-		return ERR_PTR(-EINVAL);
+	if (!pte_present(pte)) {
+		page = NULL;
+		goto no_page;
 	}
 	mask = (1UL << shift) - 1;
-	page = pte_page(*ptep);
+	page = pte_page(pte);
 	if (page)
 		page += (address & mask) / PAGE_SIZE;
 
+no_page:
 	local_irq_restore(flags);
 	return page;
 }
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 59daa5eeec25..6bfadf1aa5cb 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -839,6 +839,17 @@ pmd_t pmdp_get_and_clear(struct mm_struct *mm,
 	 * hash fault look at them.
 	 */
 	memset(pgtable, 0, PTE_FRAG_SIZE);
+	/*
+	 * Serialize against find_linux_pte_or_hugepte which does lock-less
+	 * lookup in page tables with local interrupts disabled. For huge pages
+	 * it casts pmd_t to pte_t. Since format of pte_t is different from
+	 * pmd_t we want to prevent transit from pmd pointing to page table
+	 * to pmd pointing to huge page (and back) while interrupts are disabled.
+	 * We clear pmd to possibly replace it with page table pointer in
+	 * different code paths. So make sure we wait for the parallel
+	 * find_linux_pte_or_hugepage to finish.
+	 */
+	kick_all_cpus_sync();
 	return old_pmd;
 }