powerpc: support multiple hugepage sizes

Instead of using the variable mmu_huge_psize to keep track of the huge
page size we use an array of MMU_PAGE_* values.  For each supported huge
page size we need to know the hugepte_shift value and have a
pgtable_cache.  The hstate or an mmu_huge_psizes index is passed to
functions so that they know which huge page size they should use.

The hugepage sizes 16M and 64K are setup(if available on the hardware) so
that they don't have to be set on the boot cmd line in order to use them.
The number of 16G pages have to be specified at boot-time though (e.g.
hugepagesz=16G hugepages=5).

Signed-off-by: Jon Tollefson <kniht@linux.vnet.ibm.com>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Documentation/kernel-parameters.txt

@@ -776,11 +776,11 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	hugepages=	[HW,X86-32,IA-64] HugeTLB pages to allocate at boot.
 	hugepagesz=	[HW,IA-64,PPC,X86-64] The size of the HugeTLB pages.
-			On x86 this option can be specified multiple times
-			interleaved with hugepages= to reserve huge pages
-			of different sizes. Valid pages sizes on x86-64
-			are 2M (when the CPU supports "pse") and 1G (when the
-			CPU supports the "pdpe1gb" cpuinfo flag)
+			On x86-64 and powerpc, this option can be specified
+			multiple times interleaved with hugepages= to reserve
+			huge pages of different sizes. Valid pages sizes on
+			x86-64 are 2M (when the CPU supports "pse") and 1G
+			(when the CPU supports the "pdpe1gb" cpuinfo flag)
 			Note that 1GB pages can only be allocated at boot time
 			using hugepages= and not freed afterwards.
 	default_hugepagesz=

arch/powerpc/mm/hash_utils_64.c

@@ -103,7 +103,6 @@ int mmu_kernel_ssize = MMU_SEGSIZE_256M;
 int mmu_highuser_ssize = MMU_SEGSIZE_256M;
 u16 mmu_slb_size = 64;
 #ifdef CONFIG_HUGETLB_PAGE
-int mmu_huge_psize = MMU_PAGE_16M;
 unsigned int HPAGE_SHIFT;
 #endif
 #ifdef CONFIG_PPC_64K_PAGES
@@ -460,15 +459,15 @@ static void __init htab_init_page_sizes(void)
 	/* Reserve 16G huge page memory sections for huge pages */
 	of_scan_flat_dt(htab_dt_scan_hugepage_blocks, NULL);
 
-/* Init large page size. Currently, we pick 16M or 1M depending
+/* Set default large page size. Currently, we pick 16M or 1M depending
 	 * on what is available
 	 */
 	if (mmu_psize_defs[MMU_PAGE_16M].shift)
-		set_huge_psize(MMU_PAGE_16M);
+		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_16M].shift;
 	/* With 4k/4level pagetables, we can't (for now) cope with a
 	 * huge page size < PMD_SIZE */
 	else if (mmu_psize_defs[MMU_PAGE_1M].shift)
-		set_huge_psize(MMU_PAGE_1M);
+		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_1M].shift;
 #endif /* CONFIG_HUGETLB_PAGE */
 }
 
@@ -889,7 +888,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 
 #ifdef CONFIG_HUGETLB_PAGE
 	/* Handle hugepage regions */
-	if (HPAGE_SHIFT && psize == mmu_huge_psize) {
+	if (HPAGE_SHIFT && mmu_huge_psizes[psize]) {
 		DBG_LOW(" -> huge page !\n");
 		return hash_huge_page(mm, access, ea, vsid, local, trap);
 	}