Some places in the kernel don't really expect pageblock_order >=
MAX_ORDER, and it looks like this is only possible in corner cases:
1) CONFIG_DEFERRED_STRUCT_PAGE_INIT we'll end up freeing pageblock_order
pages via __free_pages_core(), which cannot possibly work.
2) mm/page_reporting.c won't be reporting any pages with default
page_reporting_order == pageblock_order, as we'll be skipping the
reporting loop inside page_reporting_process_zone().
3) __rmqueue_fallback() will never be able to steal with
ALLOC_NOFRAGMENT.
4) find_zone_movable_pfns_for_nodes() will roundup the ZONE_MOVABLE
start PFN to MAX_ORDER_NR_PAGES. Consequently with a bigger
pageblock_order, we could have pageblocks partially managed by two
zones.
pageblock_order >= MAX_ORDER is weird either way: it's a pure
optimization for making alloc_contig_range(), as used for allcoation of
gigantic pages, a little more reliable to succeed. However, if there is
demand for somewhat reliable allocation of gigantic pages, affected setups
should be using CMA or boottime allocations instead.
So let's make sure that pageblock_order < MAX_ORDER and simplify.
Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
---
arch/powerpc/include/asm/fadump-internal.h | 4 +--
drivers/of/of_reserved_mem.c | 8 ++---
include/linux/pageblock-flags.h | 7 +++--
kernel/dma/contiguous.c | 2 +-
mm/Kconfig | 3 ++
mm/cma.c | 6 ++--
mm/page_alloc.c | 34 ++++++----------------
mm/page_isolation.c | 6 ++--
8 files changed, 26 insertions(+), 44 deletions(-)
diff --git a/arch/powerpc/include/asm/fadump-internal.h b/arch/powerpc/include/asm/fadump-internal.h
index 52189928ec08..959c7df15baa 100644
--- a/arch/powerpc/include/asm/fadump-internal.h
+++ b/arch/powerpc/include/asm/fadump-internal.h
@@ -20,9 +20,7 @@
#define memblock_num_regions(memblock_type) (memblock.memblock_type.cnt)
/* Alignment per CMA requirement. */
-#define FADUMP_CMA_ALIGNMENT (PAGE_SIZE << \
- max_t(unsigned long, MAX_ORDER - 1, \
- pageblock_order))
+#define FADUMP_CMA_ALIGNMENT (PAGE_SIZE * MAX_ORDER_NR_PAGES)
/* FAD commands */
#define FADUMP_REGISTER 1
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 9c0fb962c22b..dcbbffca0c57 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -116,12 +116,8 @@ static int __init __reserved_mem_alloc_size(unsigned long node,
if (IS_ENABLED(CONFIG_CMA)
&& of_flat_dt_is_compatible(node, "shared-dma-pool")
&& of_get_flat_dt_prop(node, "reusable", NULL)
- && !nomap) {
- unsigned long order =
- max_t(unsigned long, MAX_ORDER - 1, pageblock_order);
-
- align = max(align, (phys_addr_t)PAGE_SIZE << order);
- }
+ && !nomap)
+ align = max_t(phys_addr_t, align, PAGE_SIZE * MAX_ORDER_NR_PAGES);
prop = of_get_flat_dt_prop(node, "alloc-ranges", &len);
if (prop) {
diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h
index 973fd731a520..83c7248053a1 100644
--- a/include/linux/pageblock-flags.h
+++ b/include/linux/pageblock-flags.h
@@ -37,8 +37,11 @@ extern unsigned int pageblock_order;
#else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
-/* Huge pages are a constant size */
-#define pageblock_order HUGETLB_PAGE_ORDER
+/*
+ * Huge pages are a constant size, but don't exceed the maximum allocation
+ * granularity.
+ */
+#define pageblock_order min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_ORDER - 1)
#endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 3d63d91cba5c..4333c05c14fc 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -399,7 +399,7 @@ static const struct reserved_mem_ops rmem_cma_ops = {
static int __init rmem_cma_setup(struct reserved_mem *rmem)
{
- phys_addr_t align = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
+ phys_addr_t align = PAGE_SIZE * MAX_ORDER_NR_PAGES;
phys_addr_t mask = align - 1;
unsigned long node = rmem->fdt_node;
bool default_cma = of_get_flat_dt_prop(node, "linux,cma-default", NULL);
diff --git a/mm/Kconfig b/mm/Kconfig
index 3326ee3903f3..4c91b92e7537 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -262,6 +262,9 @@ config HUGETLB_PAGE_SIZE_VARIABLE
HUGETLB_PAGE_ORDER when there are multiple HugeTLB page sizes available
on a platform.
+ Note that the pageblock_order cannot exceed MAX_ORDER - 1 and will be
+ clamped down to MAX_ORDER - 1.
+
config CONTIG_ALLOC
def_bool (MEMORY_ISOLATION && COMPACTION) || CMA
diff --git a/mm/cma.c b/mm/cma.c
index bc9ca8f3c487..418e214685da 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -180,8 +180,7 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
return -EINVAL;
/* ensure minimal alignment required by mm core */
- alignment = PAGE_SIZE <<
- max_t(unsigned long, MAX_ORDER - 1, pageblock_order);
+ alignment = PAGE_SIZE * MAX_ORDER_NR_PAGES;
/* alignment should be aligned with order_per_bit */
if (!IS_ALIGNED(alignment >> PAGE_SHIFT, 1 << order_per_bit))
@@ -268,8 +267,7 @@ int __init cma_declare_contiguous_nid(phys_addr_t base,
* migratetype page by page allocator's buddy algorithm. In the case,
* you couldn't get a contiguous memory, which is not what we want.
*/
- alignment = max(alignment, (phys_addr_t)PAGE_SIZE <<
- max_t(unsigned long, MAX_ORDER - 1, pageblock_order));
+ alignment = max_t(phys_addr_t, alignment, PAGE_SIZE * MAX_ORDER_NR_PAGES);
if (fixed && base & (alignment - 1)) {
ret = -EINVAL;
pr_err("Region at %pa must be aligned to %pa bytes\n",
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3589febc6d31..36d9fc308a26 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1072,14 +1072,12 @@ static inline void __free_one_page(struct page *page,
int migratetype, fpi_t fpi_flags)
{
struct capture_control *capc = task_capc(zone);
+ unsigned int max_order = pageblock_order;
unsigned long buddy_pfn;
unsigned long combined_pfn;
- unsigned int max_order;
struct page *buddy;
bool to_tail;
- max_order = min_t(unsigned int, MAX_ORDER - 1, pageblock_order);
-
VM_BUG_ON(!zone_is_initialized(zone));
VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page);
@@ -2260,19 +2258,8 @@ void __init init_cma_reserved_pageblock(struct page *page)
} while (++p, --i);
set_pageblock_migratetype(page, MIGRATE_CMA);
-
- if (pageblock_order >= MAX_ORDER) {
- i = pageblock_nr_pages;
- p = page;
- do {
- set_page_refcounted(p);
- __free_pages(p, MAX_ORDER - 1);
- p += MAX_ORDER_NR_PAGES;
- } while (i -= MAX_ORDER_NR_PAGES);
- } else {
- set_page_refcounted(page);
- __free_pages(page, pageblock_order);
- }
+ set_page_refcounted(page);
+ __free_pages(page, pageblock_order);
adjust_managed_page_count(page, pageblock_nr_pages);
page_zone(page)->cma_pages += pageblock_nr_pages;
@@ -7389,16 +7376,15 @@ static inline void setup_usemap(struct zone *zone) {}
/* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */
void __init set_pageblock_order(void)
{
- unsigned int order;
+ unsigned int order = MAX_ORDER - 1;
/* Check that pageblock_nr_pages has not already been setup */
if (pageblock_order)
return;
- if (HPAGE_SHIFT > PAGE_SHIFT)
+ /* Don't let pageblocks exceed the maximum allocation granularity. */
+ if (HPAGE_SHIFT > PAGE_SHIFT && HUGETLB_PAGE_ORDER < order)
order = HUGETLB_PAGE_ORDER;
- else
- order = MAX_ORDER - 1;
/*
* Assume the largest contiguous order of interest is a huge page.
@@ -7593,7 +7579,7 @@ static void __init alloc_node_mem_map(struct pglist_data *pgdat)
if (!pgdat->node_spanned_pages)
return;
- start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1);
+ start = ALIGN_DOWN(pgdat->node_start_pfn, MAX_ORDER_NR_PAGES);
offset = pgdat->node_start_pfn - start;
/* ia64 gets its own node_mem_map, before this, without bootmem */
if (!pgdat->node_mem_map) {
@@ -8986,14 +8972,12 @@ struct page *has_unmovable_pages(struct zone *zone, struct page *page,
#ifdef CONFIG_CONTIG_ALLOC
static unsigned long pfn_max_align_down(unsigned long pfn)
{
- return pfn & ~(max_t(unsigned long, MAX_ORDER_NR_PAGES,
- pageblock_nr_pages) - 1);
+ return ALIGN_DOWN(pfn, MAX_ORDER_NR_PAGES);
}
static unsigned long pfn_max_align_up(unsigned long pfn)
{
- return ALIGN(pfn, max_t(unsigned long, MAX_ORDER_NR_PAGES,
- pageblock_nr_pages));
+ return ALIGN(pfn, MAX_ORDER_NR_PAGES);
}
#if defined(CONFIG_DYNAMIC_DEBUG) || \
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index f67c4c70f17f..e679af6121e3 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -276,9 +276,9 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
int ret;
/*
- * Note: pageblock_nr_pages != MAX_ORDER. Then, chunks of free pages
- * are not aligned to pageblock_nr_pages.
- * Then we just check migratetype first.
+ * Note: if pageblock_nr_pages < MAX_ORDER_NR_PAGES, then chunks of free
+ * pages are not necessarily aligned to pageblock_nr_pages. Check the
+ * migratetype first.
*/
for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
page = __first_valid_page(pfn, pageblock_nr_pages);
--
2.34.1
--
Thanks,
David / dhildenb
