powerpc/mm/hugetlb: Add support for reserving gigantic huge pages via kernel command line

With commit aa888a74 ("hugetlb: support larger than MAX_ORDER") we added
support for allocating gigantic hugepages via kernel command line. Switch
ppc64 arch specific code to use that.

W.r.t FSL support, we now limit our allocation range using BOOTMEM_ALLOC_ACCESSIBLE.

We use the kernel command line to do reservation of hugetlb pages on powernv
platforms. On pseries hash mmu mode the supported gigantic huge page size is
16GB and that can only be allocated with hypervisor assist. For pseries the
command line option doesn't do the allocation. Instead pseries does gigantic
hugepage allocation based on hypervisor hint that is specified via
"ibm,expected#pages" property of the memory node.

Cc: Scott Wood <oss@buserror.net>
Cc: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/include/asm/book3s/64/mmu-hash.h

@@ -468,7 +468,7 @@ extern int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 			     int psize, int ssize);
 int htab_remove_mapping(unsigned long vstart, unsigned long vend,
 			int psize, int ssize);
-extern void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages);
+extern void pseries_add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages);
 extern void demote_segment_4k(struct mm_struct *mm, unsigned long addr);
 
 #ifdef CONFIG_PPC_PSERIES

arch/powerpc/include/asm/hugetlb.h

@@ -218,18 +218,4 @@ static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
 }
 #endif /* CONFIG_HUGETLB_PAGE */
 
-/*
- * FSL Book3E platforms require special gpage handling - the gpages
- * are reserved early in the boot process by memblock instead of via
- * the .dts as on IBM platforms.
- */
-#if defined(CONFIG_HUGETLB_PAGE) && (defined(CONFIG_PPC_FSL_BOOK3E) || \
-    defined(CONFIG_PPC_8xx))
-extern void __init reserve_hugetlb_gpages(void);
-#else
-static inline void reserve_hugetlb_gpages(void)
-{
-}
-#endif
-
 #endif /* _ASM_POWERPC_HUGETLB_H */

arch/powerpc/kernel/setup-common.c

@@ -916,13 +916,6 @@ void __init setup_arch(char **cmdline_p)
 	/* Reserve large chunks of memory for use by CMA for KVM. */
 	kvm_cma_reserve();
 
-	/*
-	 * Reserve any gigantic pages requested on the command line.
-	 * memblock needs to have been initialized by the time this is
-	 * called since this will reserve memory.
-	 */
-	reserve_hugetlb_gpages();
-
 	klp_init_thread_info(&init_thread_info);
 
 	init_mm.start_code = (unsigned long)_stext;

arch/powerpc/mm/hash_utils_64.c

@@ -509,7 +509,7 @@ static int __init htab_dt_scan_hugepage_blocks(unsigned long node,
 			phys_addr, block_size, expected_pages);
 	if (phys_addr + block_size * expected_pages <= memblock_end_of_DRAM()) {
 		memblock_reserve(phys_addr, block_size * expected_pages);
-		add_gpage(phys_addr, block_size, expected_pages);
+		pseries_add_gpage(phys_addr, block_size, expected_pages);
 	}
 	return 0;
 }

arch/powerpc/mm/hugetlbpage.c

@@ -36,26 +36,6 @@
 unsigned int HPAGE_SHIFT;
 EXPORT_SYMBOL(HPAGE_SHIFT);
 
-/*
- * Tracks gpages after the device tree is scanned and before the
- * huge_boot_pages list is ready.  On non-Freescale implementations, this is
- * just used to track 16G pages and so is a single array.  FSL-based
- * implementations may have more than one gpage size, so we need multiple
- * arrays
- */
-#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
-#define MAX_NUMBER_GPAGES	128
-struct psize_gpages {
-	u64 gpage_list[MAX_NUMBER_GPAGES];
-	unsigned int nr_gpages;
-};
-static struct psize_gpages gpage_freearray[MMU_PAGE_COUNT];
-#else
-#define MAX_NUMBER_GPAGES	1024
-static u64 gpage_freearray[MAX_NUMBER_GPAGES];
-static unsigned nr_gpages;
-#endif
-
 #define hugepd_none(hpd)	(hpd_val(hpd) == 0)
 
 pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz)
@@ -210,145 +190,20 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz
 	return hugepte_offset(*hpdp, addr, pdshift);
 }
 
-#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
-/* Build list of addresses of gigantic pages.  This function is used in early
- * boot before the buddy allocator is setup.
- */
-void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages)
-{
-	unsigned int idx = shift_to_mmu_psize(__ffs(page_size));
-	int i;
-
-	if (addr == 0)
-		return;
-
-	gpage_freearray[idx].nr_gpages = number_of_pages;
-
-	for (i = 0; i < number_of_pages; i++) {
-		gpage_freearray[idx].gpage_list[i] = addr;
-		addr += page_size;
-	}
-}
-
-/*
- * Moves the gigantic page addresses from the temporary list to the
- * huge_boot_pages list.
- */
-int alloc_bootmem_huge_page(struct hstate *hstate)
-{
-	struct huge_bootmem_page *m;
-	int idx = shift_to_mmu_psize(huge_page_shift(hstate));
-	int nr_gpages = gpage_freearray[idx].nr_gpages;
-
-	if (nr_gpages == 0)
-		return 0;
-
-#ifdef CONFIG_HIGHMEM
-	/*
-	 * If gpages can be in highmem we can't use the trick of storing the
-	 * data structure in the page; allocate space for this
-	 */
-	m = memblock_virt_alloc(sizeof(struct huge_bootmem_page), 0);
-	m->phys = gpage_freearray[idx].gpage_list[--nr_gpages];
-#else
-	m = phys_to_virt(gpage_freearray[idx].gpage_list[--nr_gpages]);
-#endif
-
-	list_add(&m->list, &huge_boot_pages);
-	gpage_freearray[idx].nr_gpages = nr_gpages;
-	gpage_freearray[idx].gpage_list[nr_gpages] = 0;
-	m->hstate = hstate;
-
-	return 1;
-}
+#ifdef CONFIG_PPC_BOOK3S_64
 /*
- * Scan the command line hugepagesz= options for gigantic pages; store those in
- * a list that we use to allocate the memory once all options are parsed.
+ * Tracks gpages after the device tree is scanned and before the
+ * huge_boot_pages list is ready on pseries.
  */
-
-unsigned long gpage_npages[MMU_PAGE_COUNT];
-
-static int __init do_gpage_early_setup(char *param, char *val,
-				       const char *unused, void *arg)
-{
-	static phys_addr_t size;
-	unsigned long npages;
-
-	/*
-	 * The hugepagesz and hugepages cmdline options are interleaved.  We
-	 * use the size variable to keep track of whether or not this was done
-	 * properly and skip over instances where it is incorrect.  Other
-	 * command-line parsing code will issue warnings, so we don't need to.
-	 *
-	 */
-	if ((strcmp(param, "default_hugepagesz") == 0) ||
-	    (strcmp(param, "hugepagesz") == 0)) {
-		size = memparse(val, NULL);
-	} else if (strcmp(param, "hugepages") == 0) {
-		if (size != 0) {
-			if (sscanf(val, "%lu", &npages) <= 0)
-				npages = 0;
-			if (npages > MAX_NUMBER_GPAGES) {
-				pr_warn("MMU: %lu pages requested for page "
-#ifdef CONFIG_PHYS_ADDR_T_64BIT
-					"size %llu KB, limiting to "
-#else
-					"size %u KB, limiting to "
-#endif
-					__stringify(MAX_NUMBER_GPAGES) "\n",
-					npages, size / 1024);
-				npages = MAX_NUMBER_GPAGES;
-			}
-			gpage_npages[shift_to_mmu_psize(__ffs(size))] = npages;
-			size = 0;
-		}
-	}
-	return 0;
-}
-
+#define MAX_NUMBER_GPAGES	1024
+__initdata static u64 gpage_freearray[MAX_NUMBER_GPAGES];
+__initdata static unsigned nr_gpages;
 
 /*
- * This function allocates physical space for pages that are larger than the
- * buddy allocator can handle.  We want to allocate these in highmem because
- * the amount of lowmem is limited.  This means that this function MUST be
- * called before lowmem_end_addr is set up in MMU_init() in order for the lmb
- * allocate to grab highmem.
- */
-void __init reserve_hugetlb_gpages(void)
-{
-	static __initdata char cmdline[COMMAND_LINE_SIZE];
-	phys_addr_t size, base;
-	int i;
-
-	strlcpy(cmdline, boot_command_line, COMMAND_LINE_SIZE);
-	parse_args("hugetlb gpages", cmdline, NULL, 0, 0, 0,
-			NULL, &do_gpage_early_setup);
-
-	/*
-	 * Walk gpage list in reverse, allocating larger page sizes first.
-	 * Skip over unsupported sizes, or sizes that have 0 gpages allocated.
-	 * When we reach the point in the list where pages are no longer
-	 * considered gpages, we're done.
-	 */
-	for (i = MMU_PAGE_COUNT-1; i >= 0; i--) {
-		if (mmu_psize_defs[i].shift == 0 || gpage_npages[i] == 0)
-			continue;
-		else if (mmu_psize_to_shift(i) < (MAX_ORDER + PAGE_SHIFT))
-			break;
-
-		size = (phys_addr_t)(1ULL << mmu_psize_to_shift(i));
-		base = memblock_alloc_base(size * gpage_npages[i], size,
-					   MEMBLOCK_ALLOC_ANYWHERE);
-		add_gpage(base, size, gpage_npages[i]);
-	}
-}
-
-#else /* !PPC_FSL_BOOK3E */
-
-/* Build list of addresses of gigantic pages.  This function is used in early
+ * Build list of addresses of gigantic pages.  This function is used in early
  * boot before the buddy allocator is setup.
  */
-void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages)
+void __init pseries_add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages)
 {
 	if (!addr)
 		return;
@@ -360,10 +215,7 @@ void add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages)
 	}
 }
 
-/* Moves the gigantic page addresses from the temporary list to the
- * huge_boot_pages list.
- */
-int alloc_bootmem_huge_page(struct hstate *hstate)
+int __init pseries_alloc_bootmem_huge_page(struct hstate *hstate)
 {
 	struct huge_bootmem_page *m;
 	if (nr_gpages == 0)
@@ -376,6 +228,17 @@ int alloc_bootmem_huge_page(struct hstate *hstate)
 }
 #endif
 
+
+int __init alloc_bootmem_huge_page(struct hstate *h)
+{
+
+#ifdef CONFIG_PPC_BOOK3S_64
+	if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled())
+		return pseries_alloc_bootmem_huge_page(h);
+#endif
+	return __alloc_bootmem_huge_page(h);
+}
+
 #if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx)
 #define HUGEPD_FREELIST_SIZE \
 	((PAGE_SIZE - sizeof(struct hugepd_freelist)) / sizeof(pte_t))

arch/powerpc/mm/init_32.c

@@ -138,8 +138,6 @@ void __init MMU_init(void)
 	 * Reserve gigantic pages for hugetlb.  This MUST occur before
 	 * lowmem_end_addr is initialized below.
 	 */
-	reserve_hugetlb_gpages();
-
 	if (memblock.memory.cnt > 1) {
 #ifndef CONFIG_WII
 		memblock_enforce_memory_limit(memblock.memory.regions[0].size);