From ff6c3d81f2e86b63a3a530683f89ef393882782a Mon Sep 17 00:00:00 2001 From: Liam Ni Date: Thu, 26 Oct 2023 10:03:29 +0800 Subject: NUMA: optimize detection of memory with no node id assigned by firmware Sanity check that makes sure the nodes cover all memory loops over numa_meminfo to count the pages that have node id assigned by the firmware, then loops again over memblock.memory to find the total amount of memory and in the end checks that the difference between the total memory and memory that covered by nodes is less than some threshold. Worse, the loop over numa_meminfo calls __absent_pages_in_range() that also partially traverses memblock.memory. It's much simpler and more efficient to have a single traversal of memblock.memory that verifies that amount of memory not covered by nodes is less than a threshold. Introduce memblock_validate_numa_coverage() that does exactly that and use it instead of numa_meminfo_cover_memory(). Link: https://lkml.kernel.org/r/20231026020329.327329-1-zhiguangni01@gmail.com Signed-off-by: Liam Ni Reviewed-by: Mike Rapoport (IBM) Cc: Andy Lutomirski Cc: Bibo Mao Cc: Binbin Zhou Cc: Borislav Petkov Cc: Dave Hansen Cc: Feiyang Chen Cc: "H. Peter Anvin" Cc: Huacai Chen Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: WANG Xuerui Signed-off-by: Andrew Morton --- mm/memblock.c | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'mm/memblock.c') diff --git a/mm/memblock.c b/mm/memblock.c index 5a88d6d24d79..4a62f7774b65 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -734,6 +734,40 @@ int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) return memblock_add_range(&memblock.memory, base, size, MAX_NUMNODES, 0); } +/** + * memblock_validate_numa_coverage - check if amount of memory with + * no node ID assigned is less than a threshold + * @threshold_bytes: maximal number of pages that can have unassigned node + * ID (in bytes). + * + * A buggy firmware may report memory that does not belong to any node. + * Check if amount of such memory is below @threshold_bytes. + * + * Return: true on success, false on failure. + */ +bool __init_memblock memblock_validate_numa_coverage(unsigned long threshold_bytes) +{ + unsigned long nr_pages = 0; + unsigned long start_pfn, end_pfn, mem_size_mb; + int nid, i; + + /* calculate lose page */ + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + if (nid == NUMA_NO_NODE) + nr_pages += end_pfn - start_pfn; + } + + if ((nr_pages << PAGE_SHIFT) >= threshold_bytes) { + mem_size_mb = memblock_phys_mem_size() >> 20; + pr_err("NUMA: no nodes coverage for %luMB of %luMB RAM\n", + (nr_pages << PAGE_SHIFT) >> 20, mem_size_mb); + return false; + } + + return true; +} + + /** * memblock_isolate_range - isolate given range into disjoint memblocks * @type: memblock type to isolate range for -- cgit From 5e0a760b44417f7cadd79de2204d6247109558a0 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 28 Dec 2023 17:47:04 +0300 Subject: mm, treewide: rename MAX_ORDER to MAX_PAGE_ORDER commit 23baf831a32c ("mm, treewide: redefine MAX_ORDER sanely") has changed the definition of MAX_ORDER to be inclusive. This has caused issues with code that was not yet upstream and depended on the previous definition. To draw attention to the altered meaning of the define, rename MAX_ORDER to MAX_PAGE_ORDER. Link: https://lkml.kernel.org/r/20231228144704.14033-2-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Cc: Linus Torvalds Signed-off-by: Andrew Morton --- mm/memblock.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'mm/memblock.c') diff --git a/mm/memblock.c b/mm/memblock.c index 4a62f7774b65..8c194d8afeec 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -2113,12 +2113,13 @@ static void __init __free_pages_memory(unsigned long start, unsigned long end) * Free the pages in the largest chunks alignment allows. * * __ffs() behaviour is undefined for 0. start == 0 is - * MAX_ORDER-aligned, set order to MAX_ORDER for the case. + * MAX_PAGE_ORDER-aligned, set order to MAX_PAGE_ORDER for + * the case. */ if (start) - order = min_t(int, MAX_ORDER, __ffs(start)); + order = min_t(int, MAX_PAGE_ORDER, __ffs(start)); else - order = MAX_ORDER; + order = MAX_PAGE_ORDER; while (start + (1UL << order) > end) order--; -- cgit