From bdf2f59e64eb9cd9e9dd90f990a9577640470c8a Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Sat, 6 Aug 2016 00:31:48 -0400 Subject: sparc64: fix section mismatch in find_numa_latencies_for_group To fix: WARNING: vmlinux.o(.text.unlikely+0x580): Section mismatch in reference from the function find_numa_latencies_for_group() to the function .init.text:find_mlgroup() The function find_numa_latencies_for_group() references the function __init find_mlgroup(). This is often because find_numa_latencies_for_group lacks a __init annotation or the annotation of find_mlgroup is wrong. It turns out find_numa_latencies_for_group is only called from: static int __init numa_parse_mdesc(void) and hence we can tag find_numa_latencies_for_group with __init. In doing so we see that find_best_numa_node_for_mlgroup is only called from within __init and hence can also be marked with __init. Cc: "David S. Miller" Cc: Nitin Gupta Cc: Chris Hyser Cc: Santosh Shilimkar Cc: sparclinux@vger.kernel.org Signed-off-by: Paul Gortmaker Signed-off-by: David S. Miller --- arch/sparc/mm/init_64.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 65457c9f1365..80031fc2e2d6 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -1160,7 +1160,7 @@ int __node_distance(int from, int to) return numa_latency[from][to]; } -static int find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp) +static int __init find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp) { int i; @@ -1173,8 +1173,8 @@ static int find_best_numa_node_for_mlgroup(struct mdesc_mlgroup *grp) return i; } -static void find_numa_latencies_for_group(struct mdesc_handle *md, u64 grp, - int index) +static void __init find_numa_latencies_for_group(struct mdesc_handle *md, + u64 grp, int index) { u64 arc; -- cgit v1.2.3-70-g09d2 From 1e953d846ac015fbfcf09c857e8f893924cb629c Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Wed, 31 Aug 2016 13:48:19 -0700 Subject: sparc64 mm: Fix more TSB sizing issues Commit af1b1a9b36b8 ("sparc64 mm: Fix base TSB sizing when hugetlb pages are used") addressed the difference between hugetlb and THP pages when computing TSB sizes. The following additional issues were also discovered while working with the code. In order to save memory, THP makes use of a huge zero page. This huge zero page does not count against a task's RSS, but it does consume TSB entries. This is similar to hugetlb pages. Therefore, count huge zero page entries in hugetlb_pte_count. Accounting of THP pages is done in the routine set_pmd_at(). Unfortunately, this does not catch the case where a THP page is split. To handle this case, decrement the count in pmdp_invalidate(). pmdp_invalidate is only called when splitting a THP. However, 'sanity checks' are added in case it is ever called for other purposes. A more general issue exists with HPAGE_SIZE accounting. hugetlb_pte_count tracks the number of HPAGE_SIZE (8M) pages. This value is used to size the TSB for HPAGE_SIZE pages. However, each HPAGE_SIZE page consists of two REAL_HPAGE_SIZE (4M) pages. The TSB contains an entry for each REAL_HPAGE_SIZE page. Therefore, the number of REAL_HPAGE_SIZE pages should be used to size the huge page TSB. A new compile time constant REAL_HPAGE_PER_HPAGE is used to multiply hugetlb_pte_count before sizing the TSB. Changes from V1 - Fixed build issue if hugetlb or THP not configured Signed-off-by: Mike Kravetz Signed-off-by: David S. Miller --- arch/sparc/include/asm/page_64.h | 1 + arch/sparc/mm/fault_64.c | 1 + arch/sparc/mm/tlb.c | 35 +++++++++++++++++++++++++++++++---- arch/sparc/mm/tsb.c | 18 ++++++++++++------ 4 files changed, 45 insertions(+), 10 deletions(-) diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h index 8c2a8c937540..c1263fc390db 100644 --- a/arch/sparc/include/asm/page_64.h +++ b/arch/sparc/include/asm/page_64.h @@ -25,6 +25,7 @@ #define HPAGE_MASK (~(HPAGE_SIZE - 1UL)) #define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA +#define REAL_HPAGE_PER_HPAGE (_AC(1,UL) << (HPAGE_SHIFT - REAL_HPAGE_SHIFT)) #endif #ifndef __ASSEMBLY__ diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index e16fdd28a931..3f291d8c57f7 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -484,6 +484,7 @@ good_area: tsb_grow(mm, MM_TSB_BASE, mm_rss); #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) mm_rss = mm->context.hugetlb_pte_count + mm->context.thp_pte_count; + mm_rss *= REAL_HPAGE_PER_HPAGE; if (unlikely(mm_rss > mm->context.tsb_block[MM_TSB_HUGE].tsb_rss_limit)) { if (mm->context.tsb_block[MM_TSB_HUGE].tsb) diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index 3659d37b4d81..c56a195c9071 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -174,10 +174,25 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, return; if ((pmd_val(pmd) ^ pmd_val(orig)) & _PAGE_PMD_HUGE) { - if (pmd_val(pmd) & _PAGE_PMD_HUGE) - mm->context.thp_pte_count++; - else - mm->context.thp_pte_count--; + /* + * Note that this routine only sets pmds for THP pages. + * Hugetlb pages are handled elsewhere. We need to check + * for huge zero page. Huge zero pages are like hugetlb + * pages in that there is no RSS, but there is the need + * for TSB entries. So, huge zero page counts go into + * hugetlb_pte_count. + */ + if (pmd_val(pmd) & _PAGE_PMD_HUGE) { + if (is_huge_zero_page(pmd_page(pmd))) + mm->context.hugetlb_pte_count++; + else + mm->context.thp_pte_count++; + } else { + if (is_huge_zero_page(pmd_page(orig))) + mm->context.hugetlb_pte_count--; + else + mm->context.thp_pte_count--; + } /* Do not try to allocate the TSB hash table if we * don't have one already. We have various locks held @@ -204,6 +219,9 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, } } +/* + * This routine is only called when splitting a THP + */ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { @@ -213,6 +231,15 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, set_pmd_at(vma->vm_mm, address, pmdp, entry); flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + + /* + * set_pmd_at() will not be called in a way to decrement + * thp_pte_count when splitting a THP, so do it now. + * Sanity check pmd before doing the actual decrement. + */ + if ((pmd_val(entry) & _PAGE_PMD_HUGE) && + !is_huge_zero_page(pmd_page(entry))) + (vma->vm_mm)->context.thp_pte_count--; } void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index 6725ed45580e..f2b77112e9d8 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -469,8 +469,10 @@ retry_tsb_alloc: int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + unsigned long mm_rss = get_mm_rss(mm); #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) - unsigned long total_huge_pte_count; + unsigned long saved_hugetlb_pte_count; + unsigned long saved_thp_pte_count; #endif unsigned int i; @@ -483,10 +485,12 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) * will re-increment the counters as the parent PTEs are * copied into the child address space. */ - total_huge_pte_count = mm->context.hugetlb_pte_count + - mm->context.thp_pte_count; + saved_hugetlb_pte_count = mm->context.hugetlb_pte_count; + saved_thp_pte_count = mm->context.thp_pte_count; mm->context.hugetlb_pte_count = 0; mm->context.thp_pte_count = 0; + + mm_rss -= saved_thp_pte_count * (HPAGE_SIZE / PAGE_SIZE); #endif /* copy_mm() copies over the parent's mm_struct before calling @@ -499,11 +503,13 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) /* If this is fork, inherit the parent's TSB size. We would * grow it to that size on the first page fault anyways. */ - tsb_grow(mm, MM_TSB_BASE, get_mm_rss(mm)); + tsb_grow(mm, MM_TSB_BASE, mm_rss); #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) - if (unlikely(total_huge_pte_count)) - tsb_grow(mm, MM_TSB_HUGE, total_huge_pte_count); + if (unlikely(saved_hugetlb_pte_count + saved_thp_pte_count)) + tsb_grow(mm, MM_TSB_HUGE, + (saved_hugetlb_pte_count + saved_thp_pte_count) * + REAL_HPAGE_PER_HPAGE); #endif if (unlikely(!mm->context.tsb_block[MM_TSB_BASE].tsb)) -- cgit v1.2.3-70-g09d2 From 9b2f753ec23710aa32c0d837d2499db92fe9115b Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Thu, 15 Sep 2016 14:54:40 -0600 Subject: sparc64: Fix cpu_possible_mask if nr_cpus is set If kernel boot parameter nr_cpus is set, it should define the number of CPUs that can ever be available in the system i.e. cpu_possible_mask. setup_nr_cpu_ids() overrides the nr_cpu_ids based on the cpu_possible_mask during kernel initialization. If cpu_possible_mask is not set based on the nr_cpus value, earlier part of the kernel would be initialized using nr_cpus value leading to a kernel crash. Set cpu_possible_mask based on nr_cpus value. Thus setup_nr_cpu_ids() becomes redundant and does not corrupt nr_cpu_ids value. Signed-off-by: Atish Patra Reviewed-by: Bob Picco Reviewed-by: Vijay Kumar Signed-off-by: David S. Miller --- arch/sparc/include/asm/smp_64.h | 1 + arch/sparc/kernel/setup_64.c | 1 + arch/sparc/kernel/smp_64.c | 14 ++++++++++++++ 3 files changed, 16 insertions(+) diff --git a/arch/sparc/include/asm/smp_64.h b/arch/sparc/include/asm/smp_64.h index 26d9e7726867..87b05751955a 100644 --- a/arch/sparc/include/asm/smp_64.h +++ b/arch/sparc/include/asm/smp_64.h @@ -43,6 +43,7 @@ void arch_send_call_function_ipi_mask(const struct cpumask *mask); int hard_smp_processor_id(void); #define raw_smp_processor_id() (current_thread_info()->cpu) +void smp_fill_in_cpu_possible_map(void); void smp_fill_in_sib_core_maps(void); void cpu_play_dead(void); diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index 599f1207eed2..f32cfe83dfd1 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -650,6 +650,7 @@ void __init setup_arch(char **cmdline_p) paging_init(); init_sparc64_elf_hwcap(); + smp_fill_in_cpu_possible_map(); } extern int stop_a_enabled; diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 8a6151a628ce..d3035ba6cd31 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1227,6 +1227,20 @@ void __init smp_setup_processor_id(void) xcall_deliver_impl = hypervisor_xcall_deliver; } +void __init smp_fill_in_cpu_possible_map(void) +{ + int possible_cpus = num_possible_cpus(); + int i; + + if (possible_cpus > nr_cpu_ids) + possible_cpus = nr_cpu_ids; + + for (i = 0; i < possible_cpus; i++) + set_cpu_possible(i, true); + for (; i < NR_CPUS; i++) + set_cpu_possible(i, false); +} + void smp_fill_in_sib_core_maps(void) { unsigned int i; -- cgit v1.2.3-70-g09d2 From ebb99a4c12e4daabe1940ae936e8e7e97ae68c6f Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Thu, 15 Sep 2016 14:54:41 -0600 Subject: sparc64: Fix irq stack bootmem allocation. Currently, irq stack bootmem is allocated for all possible cpus before nr_cpus value changes the list of possible cpus. As a result, there is unnecessary wastage of bootmemory. Move the irq stack bootmem allocation so that it happens after possible cpu list is modified based on nr_cpus value. Signed-off-by: Atish Patra Reviewed-by: Bob Picco Reviewed-by: Vijay Kumar Signed-off-by: David S. Miller --- arch/sparc/kernel/setup_64.c | 25 +++++++++++++++++++++++++ arch/sparc/mm/init_64.c | 16 ---------------- 2 files changed, 25 insertions(+), 16 deletions(-) diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index f32cfe83dfd1..6b7331d198e9 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include @@ -50,6 +51,8 @@ #include #include #include +#include +#include #ifdef CONFIG_IP_PNP #include @@ -590,6 +593,22 @@ static void __init init_sparc64_elf_hwcap(void) pause_patch(); } +void __init alloc_irqstack_bootmem(void) +{ + unsigned int i, node; + + for_each_possible_cpu(i) { + node = cpu_to_node(i); + + softirq_stack[i] = __alloc_bootmem_node(NODE_DATA(node), + THREAD_SIZE, + THREAD_SIZE, 0); + hardirq_stack[i] = __alloc_bootmem_node(NODE_DATA(node), + THREAD_SIZE, + THREAD_SIZE, 0); + } +} + void __init setup_arch(char **cmdline_p) { /* Initialize PROM console and command line. */ @@ -651,6 +670,12 @@ void __init setup_arch(char **cmdline_p) paging_init(); init_sparc64_elf_hwcap(); smp_fill_in_cpu_possible_map(); + /* + * Once the OF device tree and MDESC have been setup and nr_cpus has + * been parsed, we know the list of possible cpus. Therefore we can + * allocate the IRQ stacks. + */ + alloc_irqstack_bootmem(); } extern int stop_a_enabled; diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 80031fc2e2d6..7ac6b62fb7c1 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2081,7 +2081,6 @@ void __init paging_init(void) { unsigned long end_pfn, shift, phys_base; unsigned long real_end, i; - int node; setup_page_offset(); @@ -2250,21 +2249,6 @@ void __init paging_init(void) /* Setup bootmem... */ last_valid_pfn = end_pfn = bootmem_init(phys_base); - /* Once the OF device tree and MDESC have been setup, we know - * the list of possible cpus. Therefore we can allocate the - * IRQ stacks. - */ - for_each_possible_cpu(i) { - node = cpu_to_node(i); - - softirq_stack[i] = __alloc_bootmem_node(NODE_DATA(node), - THREAD_SIZE, - THREAD_SIZE, 0); - hardirq_stack[i] = __alloc_bootmem_node(NODE_DATA(node), - THREAD_SIZE, - THREAD_SIZE, 0); - } - kernel_physical_mapping_init(); { -- cgit v1.2.3-70-g09d2 From 2a0100d7beebd2fb2c436852648f75396253e9f8 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 28 Sep 2016 20:40:52 -0400 Subject: sparc64: Fix non-SMP build. Need to provide a dummy smp_fill_in_cpu_possible_map. Fixes: 9b2f753ec237 ("sparc64: Fix cpu_possible_mask if nr_cpus is set") Reported-by: kbuild test robot Signed-off-by: David S. Miller --- arch/sparc/include/asm/smp_64.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/sparc/include/asm/smp_64.h b/arch/sparc/include/asm/smp_64.h index 87b05751955a..ce2233f7e662 100644 --- a/arch/sparc/include/asm/smp_64.h +++ b/arch/sparc/include/asm/smp_64.h @@ -73,6 +73,7 @@ void __cpu_die(unsigned int cpu); #define smp_fill_in_sib_core_maps() do { } while (0) #define smp_fetch_global_regs() do { } while (0) #define smp_fetch_global_pmu() do { } while (0) +#define smp_fill_in_cpu_possible_map() do { } while (0) #endif /* !(CONFIG_SMP) */ -- cgit v1.2.3-70-g09d2