powerpc/mm: Cleanup management of kmem_caches for pagetables

Currently we have a fair bit of rather fiddly code to manage the
various kmem_caches used to store page tables of various levels.  We
generally have two caches holding some combination of PGD, PUD and PMD
tables, plus several more for the special hugepage pagetables.

This patch cleans this all up by taking a different approach.  Rather
than the caches being designated as for PUDs or for hugeptes for 16M
pages, the caches are simply allocated to be a specific size.  Thus
sharing of caches between different types/levels of pagetables happens
naturally.  The pagetable size, where needed, is passed around encoded
in the same way as {PGD,PUD,PMD}_INDEX_SIZE; that is n where the
pagetable contains 2^n pointers.

Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

1 files changed, 49 insertions, 21 deletions

diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 335c578b9cc3..82ac61dcd3af 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -119,30 +119,58 @@ static void pmd_ctor(void *addr)
         memset(addr, 0, PMD_TABLE_SIZE);
 }
 
-static const unsigned int pgtable_cache_size[2] = {
-        PGD_TABLE_SIZE, PMD_TABLE_SIZE
-};
-static const char *pgtable_cache_name[ARRAY_SIZE(pgtable_cache_size)] = {
-#ifdef CONFIG_PPC_64K_PAGES
-        "pgd_cache", "pmd_cache",
-#else
-        "pgd_cache", "pud_pmd_cache",
-#endif /* CONFIG_PPC_64K_PAGES */
-};
-
-#ifdef CONFIG_HUGETLB_PAGE
-/* Hugepages need an extra cache per hugepagesize, initialized in
- * hugetlbpage.c.  We can't put into the tables above, because HPAGE_SHIFT
- * is not compile time constant. */
-struct kmem_cache *pgtable_cache[ARRAY_SIZE(pgtable_cache_size)+MMU_PAGE_COUNT];
-#else
-struct kmem_cache *pgtable_cache[ARRAY_SIZE(pgtable_cache_size)];
-#endif
+struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE];
+
+/*
+ * Create a kmem_cache() for pagetables.  This is not used for PTE
+ * pages - they're linked to struct page, come from the normal free
+ * pages pool and have a different entry size (see real_pte_t) to
+ * everything else.  Caches created by this function are used for all
+ * the higher level pagetables, and for hugepage pagetables.
+ */
+void pgtable_cache_add(unsigned shift, void (*ctor)(void *))
+{
+        char *name;
+        unsigned long table_size = sizeof(void *) << shift;
+        unsigned long align = table_size;
+
+        /* When batching pgtable pointers for RCU freeing, we store
+         * the index size in the low bits.  Table alignment must be
+         * big enough to fit it */
+        unsigned long minalign = MAX_PGTABLE_INDEX_SIZE + 1;
+        struct kmem_cache *new;
+
+        /* It would be nice if this was a BUILD_BUG_ON(), but at the
+         * moment, gcc doesn't seem to recognize is_power_of_2 as a
+         * constant expression, so so much for that. */
+        BUG_ON(!is_power_of_2(minalign));
+        BUG_ON((shift < 1) || (shift > MAX_PGTABLE_INDEX_SIZE));
+
+        if (PGT_CACHE(shift))
+                return; /* Already have a cache of this size */
+
+        align = max_t(unsigned long, align, minalign);
+        name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift);
+        new = kmem_cache_create(name, table_size, align, 0, ctor);
+        PGT_CACHE(shift) = new;
+
+        pr_debug("Allocated pgtable cache for order %d\n", shift);
+}
+
 
 void pgtable_cache_init(void)
 {
-        pgtable_cache[0] = kmem_cache_create(pgtable_cache_name[0], PGD_TABLE_SIZE, PGD_TABLE_SIZE, SLAB_PANIC, pgd_ctor);
-        pgtable_cache[1] = kmem_cache_create(pgtable_cache_name[1], PMD_TABLE_SIZE, PMD_TABLE_SIZE, SLAB_PANIC, pmd_ctor);
+        pgtable_cache_add(PGD_INDEX_SIZE, pgd_ctor);
+        pgtable_cache_add(PMD_INDEX_SIZE, pmd_ctor);
+        if (!PGT_CACHE(PGD_INDEX_SIZE) || !PGT_CACHE(PMD_INDEX_SIZE))
+                panic("Couldn't allocate pgtable caches");
+
+        /* In all current configs, when the PUD index exists it's the
+         * same size as either the pgd or pmd index.  Verify that the
+         * initialization above has also created a PUD cache.  This
+         * will need re-examiniation if we add new possibilities for
+         * the pagetable layout. */
+        BUG_ON(PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE));
 }
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP