From ae83189405ea5c693683327fa69ac95a23ec59be Mon Sep 17 00:00:00 2001 From: Lecopzer Chen Date: Mon, 23 Sep 2019 15:36:21 -0700 Subject: mm/sparse.c: fix memory leak of sparsemap_buf in aligned memory sparse_buffer_alloc(xsize) gets the size of memory from sparsemap_buf after being aligned with the size. However, the size is at least PAGE_ALIGN(sizeof(struct page) * PAGES_PER_SECTION) and usually larger than PAGE_SIZE. Also, sparse_buffer_fini() only frees memory between sparsemap_buf and sparsemap_buf_end, since sparsemap_buf may be changed by PTR_ALIGN() first, the aligned space before sparsemap_buf is wasted and no one will touch it. In our ARM32 platform (without SPARSEMEM_VMEMMAP) Sparse_buffer_init Reserve d359c000 - d3e9c000 (9M) Sparse_buffer_alloc Alloc d3a00000 - d3E80000 (4.5M) Sparse_buffer_fini Free d3e80000 - d3e9c000 (~=100k) The reserved memory between d359c000 - d3a00000 (~=4.4M) is unfreed. In ARM64 platform (with SPARSEMEM_VMEMMAP) sparse_buffer_init Reserve ffffffc07d623000 - ffffffc07f623000 (32M) Sparse_buffer_alloc Alloc ffffffc07d800000 - ffffffc07f600000 (30M) Sparse_buffer_fini Free ffffffc07f600000 - ffffffc07f623000 (140K) The reserved memory between ffffffc07d623000 - ffffffc07d800000 (~=1.9M) is unfreed. Let's explicit free redundant aligned memory. [arnd@arndb.de: mark sparse_buffer_free as __meminit] Link: http://lkml.kernel.org/r/20190709185528.3251709-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20190705114730.28534-1-lecopzer.chen@mediatek.com Signed-off-by: Lecopzer Chen Signed-off-by: Mark-PK Tsai Signed-off-by: Arnd Bergmann Cc: YJ Chiang Cc: Lecopzer Chen Cc: Pavel Tatashin Cc: Oscar Salvador Cc: Michal Hocko Cc: Mike Rapoport Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/sparse.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'mm/sparse.c') diff --git a/mm/sparse.c b/mm/sparse.c index 72f010d9bff5..2bfd078301f8 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -470,6 +470,12 @@ struct page __init *__populate_section_memmap(unsigned long pfn, static void *sparsemap_buf __meminitdata; static void *sparsemap_buf_end __meminitdata; +static inline void __meminit sparse_buffer_free(unsigned long size) +{ + WARN_ON(!sparsemap_buf || size == 0); + memblock_free_early(__pa(sparsemap_buf), size); +} + static void __init sparse_buffer_init(unsigned long size, int nid) { phys_addr_t addr = __pa(MAX_DMA_ADDRESS); @@ -486,7 +492,7 @@ static void __init sparse_buffer_fini(void) unsigned long size = sparsemap_buf_end - sparsemap_buf; if (sparsemap_buf && size > 0) - memblock_free_early(__pa(sparsemap_buf), size); + sparse_buffer_free(size); sparsemap_buf = NULL; } @@ -498,8 +504,12 @@ void * __meminit sparse_buffer_alloc(unsigned long size) ptr = PTR_ALIGN(sparsemap_buf, size); if (ptr + size > sparsemap_buf_end) ptr = NULL; - else + else { + /* Free redundant aligned space */ + if ((unsigned long)(ptr - sparsemap_buf) > 0) + sparse_buffer_free((unsigned long)(ptr - sparsemap_buf)); sparsemap_buf = ptr + size; + } } return ptr; } -- cgit v1.2.2 From db57e98d87908b8837352abe08515e42752270c1 Mon Sep 17 00:00:00 2001 From: Lecopzer Chen Date: Mon, 23 Sep 2019 15:36:24 -0700 Subject: mm/sparse.c: fix ALIGN() without power of 2 in sparse_buffer_alloc() The size argument passed into sparse_buffer_alloc() has already been aligned with PAGE_SIZE or PMD_SIZE. If the size after aligned is not power of 2 (e.g. 0x480000), the PTR_ALIGN() will return wrong value. Use roundup to round sparsemap_buf up to next multiple of size. Link: http://lkml.kernel.org/r/20190705114826.28586-1-lecopzer.chen@mediatek.com Signed-off-by: Lecopzer Chen Signed-off-by: Mark-PK Tsai Cc: YJ Chiang Cc: Lecopzer Chen Cc: Pavel Tatashin Cc: Oscar Salvador Cc: Michal Hocko 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 2bfd078301f8..79355a86064f 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -501,7 +501,7 @@ void * __meminit sparse_buffer_alloc(unsigned long size) void *ptr = NULL; if (sparsemap_buf) { - ptr = PTR_ALIGN(sparsemap_buf, size); + ptr = (void *) roundup((unsigned long)sparsemap_buf, size); if (ptr + size > sparsemap_buf_end) ptr = NULL; else { -- cgit v1.2.2 From c1cbc3eebf7a9ae46473a66710c0859aaafc1607 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Mon, 23 Sep 2019 15:36:27 -0700 Subject: mm/sparse.c: use __nr_to_section(section_nr) to get mem_section __pfn_to_section is defined as __nr_to_section(pfn_to_section_nr(pfn)). Since we already get section_nr, it is not necessary to get mem_section from start_pfn. By doing so, we reduce one redundant operation. Link: http://lkml.kernel.org/r/20190809010242.29797-1-richardw.yang@linux.intel.com Signed-off-by: Wei Yang Reviewed-by: Anshuman Khandual Tested-by: Anshuman Khandual Cc: Oscar Salvador Cc: Pavel Tatashin Cc: Michal Hocko Cc: David Hildenbrand 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 79355a86064f..a1679024ab5c 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -877,7 +877,7 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn, */ page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages); - ms = __pfn_to_section(start_pfn); + ms = __nr_to_section(section_nr); set_section_nid(section_nr, nid); section_mark_present(ms); -- cgit v1.2.2 From 9f82883c6d9af516c2a7f9fe85eb09e9c25bbe0a Mon Sep 17 00:00:00 2001 From: Alastair D'Silva Date: Mon, 23 Sep 2019 15:36:30 -0700 Subject: mm/sparse.c: don't manually decrement num_poisoned_pages Use the function written to do it instead. Link: http://lkml.kernel.org/r/20190827053656.32191-2-alastair@au1.ibm.com Signed-off-by: Alastair D'Silva Acked-by: Michal Hocko Reviewed-by: David Hildenbrand Acked-by: Mike Rapoport Reviewed-by: Wei Yang Reviewed-by: Oscar Salvador Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/sparse.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'mm/sparse.c') diff --git a/mm/sparse.c b/mm/sparse.c index a1679024ab5c..d7af5cfdc810 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -11,6 +11,8 @@ #include #include #include +#include +#include #include "internal.h" #include @@ -908,7 +910,7 @@ static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) for (i = 0; i < nr_pages; i++) { if (PageHWPoison(&memmap[i])) { - atomic_long_sub(1, &num_poisoned_pages); + num_poisoned_pages_dec(); ClearPageHWPoison(&memmap[i]); } } -- cgit v1.2.2 From 5ed867037eb1f15b7e8cc92497671fd4b3864e4a Mon Sep 17 00:00:00 2001 From: Alastair D'Silva Date: Mon, 23 Sep 2019 15:36:33 -0700 Subject: mm/sparse.c: remove NULL check in clear_hwpoisoned_pages() There is no possibility for memmap to be NULL in the current codebase. This check was added in commit 95a4774d055c ("memory-hotplug: update mce_bad_pages when removing the memory") where memmap was originally inited to NULL, and only conditionally given a value. The code that could have passed a NULL has been removed by commit ba72b4c8cf60 ("mm/sparsemem: support sub-section hotplug"), so there is no longer a possibility that memmap can be NULL. Link: http://lkml.kernel.org/r/20190829035151.20975-1-alastair@d-silva.org Signed-off-by: Alastair D'Silva Acked-by: Michal Hocko Reviewed-by: David Hildenbrand Cc: Mike Rapoport Cc: Wei Yang Cc: Qian Cai Cc: Alexander Duyck Cc: Logan Gunthorpe Cc: Baoquan He Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/sparse.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'mm/sparse.c') diff --git a/mm/sparse.c b/mm/sparse.c index d7af5cfdc810..bf32de9e666b 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -896,9 +896,6 @@ static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) { int i; - if (!memmap) - return; - /* * A further optimization is to have per section refcounted * num_poisoned_pages. But that would need more space per memmap, so -- cgit v1.2.2