sparc64: Support transparent huge pages.
This is relatively easy since PMD's now cover exactly 4MB of memory.
Our PMD entries are 32-bits each, so we use a special encoding. The
lowest bit, PMD_ISHUGE, determines the interpretation. This is possible
because sparc64's page tables are purely software entities so we can use
whatever encoding scheme we want. We just have to make the TLB miss
assembler page table walkers aware of the layout.
set_pmd_at() works much like set_pte_at() but it has to operate in two
page from a table of non-huge PTEs, so we have to queue up TLB flushes
based upon what mappings are valid in the PTE table. In the second regime
we are going from huge-page to non-huge-page, and in that case we need
only queue up a single TLB flush to push out the huge page mapping.
We still have 5 bits remaining in the huge PMD encoding so we can very
likely support any new pieces of THP state tracking that might get added
in the future.
With lots of help from Johannes Weiner.
Signed-off-by: David S. Miller <davem@davemloft.net>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index a35ee83..7f64743 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -78,7 +78,7 @@
base = __pa(base);
__flush_tsb_one(tb, PAGE_SHIFT, base, nentries);
-#ifdef CONFIG_HUGETLB_PAGE
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
if (mm->context.tsb_block[MM_TSB_HUGE].tsb) {
base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb;
nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries;
@@ -93,7 +93,7 @@
#define HV_PGSZ_IDX_BASE HV_PGSZ_IDX_8K
#define HV_PGSZ_MASK_BASE HV_PGSZ_MASK_8K
-#ifdef CONFIG_HUGETLB_PAGE
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
#define HV_PGSZ_IDX_HUGE HV_PGSZ_IDX_4MB
#define HV_PGSZ_MASK_HUGE HV_PGSZ_MASK_4MB
#endif
@@ -190,7 +190,7 @@
case MM_TSB_BASE:
hp->pgsz_idx = HV_PGSZ_IDX_BASE;
break;
-#ifdef CONFIG_HUGETLB_PAGE
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
case MM_TSB_HUGE:
hp->pgsz_idx = HV_PGSZ_IDX_HUGE;
break;
@@ -205,7 +205,7 @@
case MM_TSB_BASE:
hp->pgsz_mask = HV_PGSZ_MASK_BASE;
break;
-#ifdef CONFIG_HUGETLB_PAGE
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
case MM_TSB_HUGE:
hp->pgsz_mask = HV_PGSZ_MASK_HUGE;
break;
@@ -427,7 +427,7 @@
int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
{
-#ifdef CONFIG_HUGETLB_PAGE
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
unsigned long huge_pte_count;
#endif
unsigned int i;
@@ -436,7 +436,7 @@
mm->context.sparc64_ctx_val = 0UL;
-#ifdef CONFIG_HUGETLB_PAGE
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
/* We reset it to zero because the fork() page copying
* will re-increment the counters as the parent PTEs are
* copied into the child address space.
@@ -459,7 +459,7 @@
*/
tsb_grow(mm, MM_TSB_BASE, get_mm_rss(mm));
-#ifdef CONFIG_HUGETLB_PAGE
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
if (unlikely(huge_pte_count))
tsb_grow(mm, MM_TSB_HUGE, huge_pte_count);
#endif