Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull more powerpc updates from Ben Herrenschmidt:
 "Here are some more powerpc bits for 3.17, essentially fixes.

  The biggest series, also aimed at -stable, is from Aneesh and is the
  result of weeks and weeks of debugging to find out why the heck or THP
  implementation was occasionally triggering multi-hit errors in our
  level 1 TLB.  It ended up being a combination of issues including
  subtleties as to how we should invalidate those special 'MPSS' pages
  we use to allow the use of 16M pages inside 4K/64K "base page size"
  segments (you really have to love our MMU !)

  Another interesting one in the "OMG" category is the series from
  Michael adding memory barriers to spin_is_locked().  That's also the
  result of many days of debugging to figure out why the semaphore code
  would occasionally crash in ways that made no sense.  It ended up
  being some creative lock stacking that was defeated by the fact that
  our locks allow a load inside the locked section to be re-ordered with
  the load of the lock value itself (I'm still of two mind about whether
  to kill that once and for all by putting a heavier barrier back into
  our lock implementation...).  The fixes come with a long explanation
  in the cset comments, feel free to read it if you feel like having a
  headache today"

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (25 commits)
  powerpc/thp: Add tracepoints to track hugepage invalidate
  powerpc/mm: Use read barrier when creating real_pte
  powerpc/thp: Use ACCESS_ONCE when loading pmdp
  powerpc/thp: Invalidate with vpn in loop
  powerpc/thp: Handle combo pages in invalidate
  powerpc/thp: Invalidate old 64K based hash page mapping before insert of 4k pte
  powerpc/thp: Don't recompute vsid and ssize in loop on invalidate
  powerpc/thp: Add write barrier after updating the valid bit
  powerpc: reorder per-cpu NUMA information's initialization
  powerpc/perf/hv-24x7: Use kmem_cache_free
  powerpc/pseries/hvcserver: Fix endian issue in hvcs_get_partner_info
  powerpc: Hard disable interrupts in xmon
  powerpc: remove duplicate definition of TEXASR_FS
  powerpc/pseries: Avoid deadlock on removing ddw
  powerpc/pseries: Failure on removing device node
  powerpc/boot: Use correct zlib types for comparison
  powerpc/powernv: Interface to register/unregister opal dump region
  printk: Add function to return log buffer address and size
  powerpc: Add POWER8 features to CPU_FTRS_POSSIBLE/ALWAYS
  powerpc/ppc476: Disable BTAC
  ...

1 files changed, 29 insertions, 15 deletions

diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 3b3c4d34c7a0..c8d709ab489d 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -54,6 +54,9 @@
 
 #include "mmu_decl.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/thp.h>
+
 /* Some sanity checking */
 #if TASK_SIZE_USER64 > PGTABLE_RANGE
 #error TASK_SIZE_USER64 exceeds pagetable range
@@ -537,8 +540,9 @@ unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
 	old = pmd_val(*pmdp);
 	*pmdp = __pmd((old & ~clr) | set);
 #endif
+	trace_hugepage_update(addr, old, clr, set);
 	if (old & _PAGE_HASHPTE)
-		hpte_do_hugepage_flush(mm, addr, pmdp);
+		hpte_do_hugepage_flush(mm, addr, pmdp, old);
 	return old;
 }
 
@@ -642,10 +646,11 @@ void pmdp_splitting_flush(struct vm_area_struct *vma,
 	 * If we didn't had the splitting flag set, go and flush the
 	 * HPTE entries.
 	 */
+	trace_hugepage_splitting(address, old);
 	if (!(old & _PAGE_SPLITTING)) {
 		/* We need to flush the hpte */
 		if (old & _PAGE_HASHPTE)
-			hpte_do_hugepage_flush(vma->vm_mm, address, pmdp);
+			hpte_do_hugepage_flush(vma->vm_mm, address, pmdp, old);
 	}
 	/*
 	 * This ensures that generic code that rely on IRQ disabling
@@ -709,6 +714,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 	assert_spin_locked(&mm->page_table_lock);
 	WARN_ON(!pmd_trans_huge(pmd));
 #endif
+	trace_hugepage_set_pmd(addr, pmd);
 	return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd));
 }
 
@@ -723,7 +729,7 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
  * neesd to be flushed.
  */
 void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
-			    pmd_t *pmdp)
+			    pmd_t *pmdp, unsigned long old_pmd)
 {
 	int ssize, i;
 	unsigned long s_addr;
@@ -745,12 +751,29 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
 	if (!hpte_slot_array)
 		return;
 
-	/* get the base page size */
+	/* get the base page size,vsid and segment size */
+#ifdef CONFIG_DEBUG_VM
 	psize = get_slice_psize(mm, s_addr);
+	BUG_ON(psize == MMU_PAGE_16M);
+#endif
+	if (old_pmd & _PAGE_COMBO)
+		psize = MMU_PAGE_4K;
+	else
+		psize = MMU_PAGE_64K;
+
+	if (!is_kernel_addr(s_addr)) {
+		ssize = user_segment_size(s_addr);
+		vsid = get_vsid(mm->context.id, s_addr, ssize);
+		WARN_ON(vsid == 0);
+	} else {
+		vsid = get_kernel_vsid(s_addr, mmu_kernel_ssize);
+		ssize = mmu_kernel_ssize;
+	}
 
 	if (ppc_md.hugepage_invalidate)
-		return ppc_md.hugepage_invalidate(mm, hpte_slot_array,
-						  s_addr, psize);
+		return ppc_md.hugepage_invalidate(vsid, s_addr,
+						  hpte_slot_array,
+						  psize, ssize);
 	/*
 	 * No bluk hpte removal support, invalidate each entry
 	 */
@@ -768,15 +791,6 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
 
 		/* get the vpn */
 		addr = s_addr + (i * (1ul << shift));
-		if (!is_kernel_addr(addr)) {
-			ssize = user_segment_size(addr);
-			vsid = get_vsid(mm->context.id, addr, ssize);
-			WARN_ON(vsid == 0);
-		} else {
-			vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
-			ssize = mmu_kernel_ssize;
-		}
-
 		vpn = hpt_vpn(addr, vsid, ssize);
 		hash = hpt_hash(vpn, shift, ssize);
 		if (hidx & _PTEIDX_SECONDARY)