5.15-stable review patch. If anyone has any objections, please let me know.
------------------
From: David Hildenbrand david@redhat.com
[ Upstream commit e16faf26780fc0c8dd693ea9ee8420a7706cb2f5 ]
Patch series "mm: enforce pageblock_order < MAX_ORDER".
Having pageblock_order >= MAX_ORDER seems to be able to happen in corner cases and some parts of the kernel are not prepared for it.
For example, Aneesh has shown [1] that such kernels can be compiled on ppc64 with 64k base pages by setting FORCE_MAX_ZONEORDER=8, which will run into a WARN_ON_ONCE(order >= MAX_ORDER) in comapction code right during boot.
We can get pageblock_order >= MAX_ORDER when the default hugetlb size is bigger than the maximum allocation granularity of the buddy, in which case we are no longer talking about huge pages but instead gigantic pages.
Having pageblock_order >= MAX_ORDER can only make alloc_contig_range() of such gigantic pages more likely to succeed.
Reliable use of gigantic pages either requires boot time allcoation or CMA, no need to overcomplicate some places in the kernel to optimize for corner cases that are broken in other areas of the kernel.
This patch (of 2):
Let's enforce pageblock_order < MAX_ORDER and simplify.
Especially patch #1 can be regarded a cleanup before: [PATCH v5 0/6] Use pageblock_order for cma and alloc_contig_range alignment. [2]
[1] https://lkml.kernel.org/r/87r189a2ks.fsf@linux.ibm.com [2] https://lkml.kernel.org/r/20220211164135.1803616-1-zi.yan@sent.com
Link: https://lkml.kernel.org/r/20220214174132.219303-2-david@redhat.com Signed-off-by: David Hildenbrand david@redhat.com Reviewed-by: Zi Yan ziy@nvidia.com Acked-by: Rob Herring robh@kernel.org Cc: Aneesh Kumar K.V aneesh.kumar@linux.ibm.com Cc: Michael Ellerman mpe@ellerman.id.au Cc: Benjamin Herrenschmidt benh@kernel.crashing.org Cc: Paul Mackerras paulus@samba.org Cc: Frank Rowand frowand.list@gmail.com Cc: Michael S. Tsirkin mst@redhat.com Cc: Christoph Hellwig hch@lst.de Cc: Marek Szyprowski m.szyprowski@samsung.com Cc: Robin Murphy robin.murphy@arm.com Cc: Minchan Kim minchan@kernel.org Cc: Vlastimil Babka vbabka@suse.cz Cc: John Garry via iommu iommu@lists.linux-foundation.org
Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Stable-dep-of: b174f139bdc8 ("mm/cma: drop incorrect alignment check in cma_init_reserved_mem") Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/include/asm/fadump-internal.h | 5 ----- arch/powerpc/kernel/fadump.c | 2 +- drivers/of/of_reserved_mem.c | 9 +++------ include/linux/cma.h | 9 +++++++++ kernel/dma/contiguous.c | 4 +--- mm/cma.c | 20 +++++--------------- 6 files changed, 19 insertions(+), 30 deletions(-)
diff --git a/arch/powerpc/include/asm/fadump-internal.h b/arch/powerpc/include/asm/fadump-internal.h index 8d61c8f3fec47..d06b2be645326 100644 --- a/arch/powerpc/include/asm/fadump-internal.h +++ b/arch/powerpc/include/asm/fadump-internal.h @@ -19,11 +19,6 @@
#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)) - /* FAD commands */ #define FADUMP_REGISTER 1 #define FADUMP_UNREGISTER 2 diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index d496dc5151aa1..35b142ad0e40e 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -544,7 +544,7 @@ int __init fadump_reserve_mem(void) if (!fw_dump.nocma) { fw_dump.boot_memory_size = ALIGN(fw_dump.boot_memory_size, - FADUMP_CMA_ALIGNMENT); + CMA_MIN_ALIGNMENT_BYTES); } #endif
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c index 9e949ddcb1464..6ec668ae2d6fa 100644 --- a/drivers/of/of_reserved_mem.c +++ b/drivers/of/of_reserved_mem.c @@ -22,6 +22,7 @@ #include <linux/slab.h> #include <linux/memblock.h> #include <linux/kmemleak.h> +#include <linux/cma.h>
#include "of_private.h"
@@ -117,12 +118,8 @@ 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, CMA_MIN_ALIGNMENT_BYTES);
prop = of_get_flat_dt_prop(node, "alloc-ranges", &len); if (prop) { diff --git a/include/linux/cma.h b/include/linux/cma.h index 53fd8c3cdbd04..1b302e204c09b 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -20,6 +20,15 @@
#define CMA_MAX_NAME 64
+/* + * TODO: once the buddy -- especially pageblock merging and alloc_contig_range() + * -- can deal with only some pageblocks of a higher-order page being + * MIGRATE_CMA, we can use pageblock_nr_pages. + */ +#define CMA_MIN_ALIGNMENT_PAGES max_t(phys_addr_t, MAX_ORDER_NR_PAGES, \ + pageblock_nr_pages) +#define CMA_MIN_ALIGNMENT_BYTES (PAGE_SIZE * CMA_MIN_ALIGNMENT_PAGES) + struct cma;
extern unsigned long totalcma_pages; diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c index 3d63d91cba5cf..6ea80ae426228 100644 --- a/kernel/dma/contiguous.c +++ b/kernel/dma/contiguous.c @@ -399,8 +399,6 @@ 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 mask = align - 1; unsigned long node = rmem->fdt_node; bool default_cma = of_get_flat_dt_prop(node, "linux,cma-default", NULL); struct cma *cma; @@ -416,7 +414,7 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem) of_get_flat_dt_prop(node, "no-map", NULL)) return -EINVAL;
- if ((rmem->base & mask) || (rmem->size & mask)) { + if (!IS_ALIGNED(rmem->base | rmem->size, CMA_MIN_ALIGNMENT_BYTES)) { pr_err("Reserved memory: incorrect alignment of CMA region\n"); return -EINVAL; } diff --git a/mm/cma.c b/mm/cma.c index 26967c70e9c73..5208aee4f45ad 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -169,7 +169,6 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, struct cma **res_cma) { struct cma *cma; - phys_addr_t alignment;
/* Sanity checks */ if (cma_area_count == ARRAY_SIZE(cma_areas)) { @@ -180,15 +179,12 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, if (!size || !memblock_is_region_reserved(base, size)) return -EINVAL;
- /* ensure minimal alignment required by mm core */ - alignment = PAGE_SIZE << - max_t(unsigned long, MAX_ORDER - 1, pageblock_order); - /* alignment should be aligned with order_per_bit */ - if (!IS_ALIGNED(alignment >> PAGE_SHIFT, 1 << order_per_bit)) + if (!IS_ALIGNED(CMA_MIN_ALIGNMENT_PAGES, 1 << order_per_bit)) return -EINVAL;
- if (ALIGN(base, alignment) != base || ALIGN(size, alignment) != size) + /* ensure minimal alignment required by mm core */ + if (!IS_ALIGNED(base | size, CMA_MIN_ALIGNMENT_BYTES)) return -EINVAL;
/* @@ -263,14 +259,8 @@ int __init cma_declare_contiguous_nid(phys_addr_t base, if (alignment && !is_power_of_2(alignment)) return -EINVAL;
- /* - * Sanitise input arguments. - * Pages both ends in CMA area could be merged into adjacent unmovable - * 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)); + /* Sanitise input arguments. */ + alignment = max_t(phys_addr_t, alignment, CMA_MIN_ALIGNMENT_BYTES); if (fixed && base & (alignment - 1)) { ret = -EINVAL; pr_err("Region at %pa must be aligned to %pa bytes\n",