From a1bc561bb2d3d9b944878955095f53aeba30a166 Mon Sep 17 00:00:00 2001 From: Ohhoon Kwon Date: Thu, 2 Sep 2021 14:56:58 -0700 Subject: mm: sparse: pass section_nr to section_mark_present Patch series "mm: sparse: remove __section_nr() function", v4. This patch (of 3): With CONFIG_SPARSEMEM_EXTREME enabled, __section_nr() which converts mem_section to section_nr could be costly since it iterates all section roots to check if the given mem_section is in its range. Since both callers of section_mark_present already know section_nr, let's also pass section_nr as well as mem_section in order to reduce costly translation. Link: https://lkml.kernel.org/r/20210707150212.855-1-ohoono.kwon@samsung.com Link: https://lkml.kernel.org/r/20210707150212.855-2-ohoono.kwon@samsung.com Signed-off-by: Ohhoon Kwon Acked-by: Mike Rapoport Acked-by: Michal Hocko Reviewed-by: David Hildenbrand Cc: Baoquan He Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/sparse.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'mm/sparse.c') diff --git a/mm/sparse.c b/mm/sparse.c index 6326cdf36c4f..8018ee7fcda5 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -187,10 +187,9 @@ void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn, * those loops early. */ unsigned long __highest_present_section_nr; -static void section_mark_present(struct mem_section *ms) +static void __section_mark_present(struct mem_section *ms, + unsigned long section_nr) { - unsigned long section_nr = __section_nr(ms); - if (section_nr > __highest_present_section_nr) __highest_present_section_nr = section_nr; @@ -280,7 +279,7 @@ static void __init memory_present(int nid, unsigned long start, unsigned long en if (!ms->section_mem_map) { ms->section_mem_map = sparse_encode_early_nid(nid) | SECTION_IS_ONLINE; - section_mark_present(ms); + __section_mark_present(ms, section); } } } @@ -934,7 +933,7 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn, ms = __nr_to_section(section_nr); set_section_nid(section_nr, nid); - section_mark_present(ms); + __section_mark_present(ms, section_nr); /* Align memmap to section boundary in the subsection case */ if (section_nr_to_pfn(section_nr) != start_pfn) -- cgit v1.2.3 From 11e02d3729da1a2d4a33db5ea61291770d411884 Mon Sep 17 00:00:00 2001 From: Ohhoon Kwon Date: Thu, 2 Sep 2021 14:57:04 -0700 Subject: mm: sparse: remove __section_nr() function As the last users of __section_nr() are gone, let's remove unused function __section_nr(). Link: https://lkml.kernel.org/r/20210707150212.855-4-ohoono.kwon@samsung.com Signed-off-by: Ohhoon Kwon Acked-by: Michal Hocko Acked-by: Mike Rapoport Reviewed-by: David Hildenbrand Cc: Baoquan He Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 - mm/sparse.c | 26 -------------------------- 2 files changed, 27 deletions(-) (limited to 'mm/sparse.c') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fcb535560028..8827f4d081d4 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1342,7 +1342,6 @@ static inline struct mem_section *__nr_to_section(unsigned long nr) return NULL; return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK]; } -extern unsigned long __section_nr(struct mem_section *ms); extern size_t mem_section_usage_size(void); /* diff --git a/mm/sparse.c b/mm/sparse.c index 8018ee7fcda5..d85655242ed9 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -109,32 +109,6 @@ static inline int sparse_index_init(unsigned long section_nr, int nid) } #endif -#ifdef CONFIG_SPARSEMEM_EXTREME -unsigned long __section_nr(struct mem_section *ms) -{ - unsigned long root_nr; - struct mem_section *root = NULL; - - for (root_nr = 0; root_nr < NR_SECTION_ROOTS; root_nr++) { - root = __nr_to_section(root_nr * SECTIONS_PER_ROOT); - if (!root) - continue; - - if ((ms >= root) && (ms < (root + SECTIONS_PER_ROOT))) - break; - } - - VM_BUG_ON(!root); - - return (root_nr * SECTIONS_PER_ROOT) + (ms - root); -} -#else -unsigned long __section_nr(struct mem_section *ms) -{ - return (unsigned long)(ms - mem_section[0]); -} -#endif - /* * During early boot, before section_mem_map is used for an actual * mem_map, we use section_mem_map to store the section's NUMA -- cgit v1.2.3 From e0dbb2bccf19ce5e870afb420a3d0480c582bb7b Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 2 Sep 2021 14:57:10 -0700 Subject: include/linux/mmzone.h: avoid a warning in sparse memory support cppcheck warns that we're possibly losing information by shifting an int. It's a false positive, because we don't allow for a NUMA node ID that large, but if we ever change SECTION_NID_SHIFT, it could become a problem, and in any case this is usually a legitimate warning. Fix it by adding the necessary cast, which makes the compiler generate the right code. Link: https://lkml.kernel.org/r/YOya+aBZFFmC476e@casper.infradead.org Link: https://lkml.kernel.org/r/202107130348.6LsVT9Nc-lkp@intel.com Cc: Mike Rapoport Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/sparse.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/sparse.c') diff --git a/mm/sparse.c b/mm/sparse.c index d85655242ed9..be7936e65b6a 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -117,7 +117,7 @@ static inline int sparse_index_init(unsigned long section_nr, int nid) */ static inline unsigned long sparse_encode_early_nid(int nid) { - return (nid << SECTION_NID_SHIFT); + return ((unsigned long)nid << SECTION_NID_SHIFT); } static inline int sparse_early_nid(struct mem_section *section) -- cgit v1.2.3 From bdbda735508ca83341899a77f143e4d5c58007b3 Mon Sep 17 00:00:00 2001 From: Miles Chen Date: Thu, 2 Sep 2021 14:57:13 -0700 Subject: mm/sparse: clarify pgdat_to_phys Clarify pgdat_to_phys() by testing if pgdat == &contig_page_data when CONFIG_NUMA=n. We only expect contig_page_data in such case, so we use &contig_page_data directly instead of pgdat. No functional change intended when CONFIG_BUG_VM=n. Comment from Mark [1]: " ... and I reckon it'd be clearer and more robust to define pgdat_to_phys() in the same ifdefs as contig_page_data so that these, stay in-sync. e.g. have: | #ifdef CONFIG_NUMA | #define pgdat_to_phys(x) virt_to_phys(x) | #else /* CONFIG_NUMA */ | | extern struct pglist_data contig_page_data; | ... | #define pgdat_to_phys(x) __pa_symbol(&contig_page_data) | | #endif /* CONIFIG_NUMA */ " [1] https://lore.kernel.org/linux-arm-kernel/20210615131902.GB47121@C02TD0UTHF1T.local/ Link: https://lkml.kernel.org/r/20210723123342.26406-1-miles.chen@mediatek.com Signed-off-by: Miles Chen Reviewed-by: David Hildenbrand Acked-by: Mike Rapoport Cc: Mark Rutland Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/sparse.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'mm/sparse.c') diff --git a/mm/sparse.c b/mm/sparse.c index be7936e65b6a..fd29b3abffa0 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -321,7 +321,8 @@ size_t mem_section_usage_size(void) static inline phys_addr_t pgdat_to_phys(struct pglist_data *pgdat) { #ifndef CONFIG_NUMA - return __pa_symbol(pgdat); + VM_BUG_ON(pgdat != &contig_page_data); + return __pa_symbol(&contig_page_data); #else return __pa(pgdat); #endif -- cgit v1.2.3 From c803b3c8b3b70f306ee6300bf8acdd70ffd1441a Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Thu, 2 Sep 2021 14:58:02 -0700 Subject: mm: introduce memmap_alloc() to unify memory map allocation There are several places that allocate memory for the memory map: alloc_node_mem_map() for FLATMEM, sparse_buffer_init() and __populate_section_memmap() for SPARSEMEM. The memory allocated in the FLATMEM case is zeroed and it is never poisoned, regardless of CONFIG_PAGE_POISON setting. The memory allocated in the SPARSEMEM cases is not zeroed and it is implicitly poisoned inside memblock if CONFIG_PAGE_POISON is set. Introduce memmap_alloc() wrapper for memblock allocators that will be used for both FLATMEM and SPARSEMEM cases and will makei memory map zeroing and poisoning consistent for different memory models. Link: https://lkml.kernel.org/r/20210714123739.16493-4-rppt@kernel.org Signed-off-by: Mike Rapoport Cc: Michal Simek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/internal.h | 4 ++++ mm/page_alloc.c | 24 ++++++++++++++++++++++-- mm/sparse.c | 6 ++---- 3 files changed, 28 insertions(+), 6 deletions(-) (limited to 'mm/sparse.c') diff --git a/mm/internal.h b/mm/internal.h index 31ff935b2547..57e28261a3b1 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -211,6 +211,10 @@ extern void zone_pcp_reset(struct zone *zone); extern void zone_pcp_disable(struct zone *zone); extern void zone_pcp_enable(struct zone *zone); +extern void *memmap_alloc(phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, + int nid, bool exact_nid); + #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* diff --git a/mm/page_alloc.c b/mm/page_alloc.c index bd2efd6287ce..71ad97c96075 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6748,6 +6748,26 @@ static void __init memmap_init(void) init_unavailable_range(hole_pfn, end_pfn, zone_id, nid); } +void __init *memmap_alloc(phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, int nid, bool exact_nid) +{ + void *ptr; + + if (exact_nid) + ptr = memblock_alloc_exact_nid_raw(size, align, min_addr, + MEMBLOCK_ALLOC_ACCESSIBLE, + nid); + else + ptr = memblock_alloc_try_nid_raw(size, align, min_addr, + MEMBLOCK_ALLOC_ACCESSIBLE, + nid); + + if (ptr && size > 0) + page_init_poison(ptr, size); + + return ptr; +} + static int zone_batchsize(struct zone *zone) { #ifdef CONFIG_MMU @@ -7519,8 +7539,8 @@ static void __ref alloc_node_mem_map(struct pglist_data *pgdat) end = pgdat_end_pfn(pgdat); end = ALIGN(end, MAX_ORDER_NR_PAGES); size = (end - start) * sizeof(struct page); - map = memblock_alloc_node(size, SMP_CACHE_BYTES, - pgdat->node_id); + map = memmap_alloc(size, SMP_CACHE_BYTES, MEMBLOCK_LOW_LIMIT, + pgdat->node_id, false); if (!map) panic("Failed to allocate %ld bytes for node %d memory map\n", size, pgdat->node_id); diff --git a/mm/sparse.c b/mm/sparse.c index fd29b3abffa0..120bc8ea5293 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -436,8 +436,7 @@ struct page __init *__populate_section_memmap(unsigned long pfn, if (map) return map; - map = memblock_alloc_try_nid_raw(size, size, addr, - MEMBLOCK_ALLOC_ACCESSIBLE, nid); + map = memmap_alloc(size, size, addr, nid, false); if (!map) panic("%s: Failed to allocate %lu bytes align=0x%lx nid=%d from=%pa\n", __func__, size, PAGE_SIZE, nid, &addr); @@ -464,8 +463,7 @@ static void __init sparse_buffer_init(unsigned long size, int nid) * and we want it to be properly aligned to the section size - this is * especially the case for VMEMMAP which maps memmap to PMDs */ - sparsemap_buf = memblock_alloc_exact_nid_raw(size, section_map_size(), - addr, MEMBLOCK_ALLOC_ACCESSIBLE, nid); + sparsemap_buf = memmap_alloc(size, section_map_size(), addr, nid, true); sparsemap_buf_end = sparsemap_buf + size; } -- cgit v1.2.3