From: Tejun Heo Date: Fri, 14 Aug 2009 05:41:02 +0000 (+0900) Subject: Merge branch 'percpu-for-linus' into percpu-for-next X-Git-Tag: firefly_0821_release~12956^2^2~20 X-Git-Url: http://demsky.eecs.uci.edu/git/?a=commitdiff_plain;h=384be2b18a5f9475eab9ca2bdfa95cc1a04ef59c;p=firefly-linux-kernel-4.4.55.git Merge branch 'percpu-for-linus' into percpu-for-next Conflicts: arch/sparc/kernel/smp_64.c arch/x86/kernel/cpu/perf_counter.c arch/x86/kernel/setup_percpu.c drivers/cpufreq/cpufreq_ondemand.c mm/percpu.c Conflicts in core and arch percpu codes are mostly from commit ed78e1e078dd44249f88b1dd8c76dafb39567161 which substituted many num_possible_cpus() with nr_cpu_ids. As for-next branch has moved all the first chunk allocators into mm/percpu.c, the changes are moved from arch code to mm/percpu.c. Signed-off-by: Tejun Heo --- 384be2b18a5f9475eab9ca2bdfa95cc1a04ef59c diff --cc arch/sparc/kernel/smp_64.c index 6970333b48b8,3691907a43b4..9856d866b77b --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@@ -1478,26 -1491,25 +1478,26 @@@ void __init setup_per_cpu_areas(void size_t dyn_size, static_size = __per_cpu_end - __per_cpu_start; static struct vm_struct vm; unsigned long delta, cpu; - size_t pcpu_unit_size; + size_t size_sum, pcpu_unit_size; size_t ptrs_size; + void **ptrs; - pcpur_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE + - PERCPU_DYNAMIC_RESERVE); - dyn_size = pcpur_size - static_size - PERCPU_MODULE_RESERVE; + size_sum = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE + + PERCPU_DYNAMIC_RESERVE); + dyn_size = size_sum - static_size - PERCPU_MODULE_RESERVE; - ptrs_size = PFN_ALIGN(num_possible_cpus() * sizeof(ptrs[0])); - ptrs_size = PFN_ALIGN(nr_cpu_ids * sizeof(pcpur_ptrs[0])); - pcpur_ptrs = alloc_bootmem(ptrs_size); ++ ptrs_size = PFN_ALIGN(nr_cpu_ids * sizeof(ptrs[0])); + ptrs = alloc_bootmem(ptrs_size); for_each_possible_cpu(cpu) { - pcpur_ptrs[cpu] = pcpu_alloc_bootmem(cpu, PCPU_CHUNK_SIZE, - PCPU_CHUNK_SIZE); + ptrs[cpu] = pcpu_alloc_bootmem(cpu, PCPU_CHUNK_SIZE, + PCPU_CHUNK_SIZE); - free_bootmem(__pa(pcpur_ptrs[cpu] + pcpur_size), - PCPU_CHUNK_SIZE - pcpur_size); + free_bootmem(__pa(ptrs[cpu] + size_sum), + PCPU_CHUNK_SIZE - size_sum); - memcpy(pcpur_ptrs[cpu], __per_cpu_load, static_size); + memcpy(ptrs[cpu], __per_cpu_load, static_size); } /* allocate address and map */ diff --cc arch/x86/kernel/cpu/perf_counter.c index 13bd6d6cf0bd,900332b800f8..3d4ebbd2e129 --- a/arch/x86/kernel/cpu/perf_counter.c +++ b/arch/x86/kernel/cpu/perf_counter.c @@@ -1559,8 -1798,9 +1798,9 @@@ void callchain_store(struct perf_callch entry->ip[entry->nr++] = ip; } -static DEFINE_PER_CPU(struct perf_callchain_entry, irq_entry); -static DEFINE_PER_CPU(struct perf_callchain_entry, nmi_entry); +static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry); +static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_nmi_entry); + static DEFINE_PER_CPU(int, in_nmi_frame); static void diff --cc arch/x86/kernel/setup_percpu.c index 7501bb14bd51,07d81916f212..a26ff61e2fb0 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@@ -176,35 -185,130 +176,35 @@@ static ssize_t __init setup_pcpu_lpage( return -EINVAL; } - /* - * Currently supports only single page. Supporting multiple - * pages won't be too difficult if it ever becomes necessary. - */ - pcpul_size = PFN_ALIGN(static_size + PERCPU_MODULE_RESERVE + - PERCPU_DYNAMIC_RESERVE); - if (pcpul_size > PMD_SIZE) { - pr_warning("PERCPU: static data is larger than large page, " - "can't use large page\n"); - return -EINVAL; - } - dyn_size = pcpul_size - static_size - PERCPU_FIRST_CHUNK_RESERVE; - - /* allocate pointer array and alloc large pages */ - map_size = PFN_ALIGN(nr_cpu_ids * sizeof(pcpul_map[0])); - pcpul_map = alloc_bootmem(map_size); - - for_each_possible_cpu(cpu) { - pcpul_map[cpu].cpu = cpu; - pcpul_map[cpu].ptr = pcpu_alloc_bootmem(cpu, PMD_SIZE, - PMD_SIZE); - if (!pcpul_map[cpu].ptr) { - pr_warning("PERCPU: failed to allocate large page " - "for cpu%u\n", cpu); - goto enomem; - } - - /* - * Only use pcpul_size bytes and give back the rest. - * - * Ingo: The 2MB up-rounding bootmem is needed to make - * sure the partial 2MB page is still fully RAM - it's - * not well-specified to have a PAT-incompatible area - * (unmapped RAM, device memory, etc.) in that hole. - */ - free_bootmem(__pa(pcpul_map[cpu].ptr + pcpul_size), - PMD_SIZE - pcpul_size); - - memcpy(pcpul_map[cpu].ptr, __per_cpu_load, static_size); + /* allocate and build unit_map */ - unit_map_size = num_possible_cpus() * sizeof(int); ++ unit_map_size = nr_cpu_ids * sizeof(int); + unit_map = alloc_bootmem_nopanic(unit_map_size); + if (!unit_map) { + pr_warning("PERCPU: failed to allocate unit_map\n"); + return -ENOMEM; } - /* allocate address and map */ - pcpul_vm.flags = VM_ALLOC; - pcpul_vm.size = nr_cpu_ids * PMD_SIZE; - vm_area_register_early(&pcpul_vm, PMD_SIZE); - - for_each_possible_cpu(cpu) { - pmd_t *pmd, pmd_v; - - pmd = populate_extra_pmd((unsigned long)pcpul_vm.addr + - cpu * PMD_SIZE); - pmd_v = pfn_pmd(page_to_pfn(virt_to_page(pcpul_map[cpu].ptr)), - PAGE_KERNEL_LARGE); - set_pmd(pmd, pmd_v); + ret = pcpu_lpage_build_unit_map(static_size, + PERCPU_FIRST_CHUNK_RESERVE, + &dyn_size, &unit_size, PMD_SIZE, + unit_map, pcpu_lpage_cpu_distance); + if (ret < 0) { + pr_warning("PERCPU: failed to build unit_map\n"); + goto out_free; } + nr_units = ret; - /* we're ready, commit */ - pr_info("PERCPU: Remapped at %p with large pages, static data " - "%zu bytes\n", pcpul_vm.addr, static_size); - - ret = pcpu_setup_first_chunk(pcpul_get_page, static_size, - PERCPU_FIRST_CHUNK_RESERVE, dyn_size, - PMD_SIZE, pcpul_vm.addr, NULL); - - /* sort pcpul_map array for pcpu_lpage_remapped() */ - for (i = 0; i < nr_cpu_ids - 1; i++) - for (j = i + 1; j < nr_cpu_ids; j++) - if (pcpul_map[i].ptr > pcpul_map[j].ptr) { - struct pcpul_ent tmp = pcpul_map[i]; - pcpul_map[i] = pcpul_map[j]; - pcpul_map[j] = tmp; - } - - return ret; - -enomem: - for_each_possible_cpu(cpu) - if (pcpul_map[cpu].ptr) - free_bootmem(__pa(pcpul_map[cpu].ptr), pcpul_size); - free_bootmem(__pa(pcpul_map), map_size); - return -ENOMEM; -} + /* do the parameters look okay? */ + if (!chosen) { + size_t vm_size = VMALLOC_END - VMALLOC_START; + size_t tot_size = nr_units * unit_size; -/** - * pcpu_lpage_remapped - determine whether a kaddr is in pcpul recycled area - * @kaddr: the kernel address in question - * - * Determine whether @kaddr falls in the pcpul recycled area. This is - * used by pageattr to detect VM aliases and break up the pcpu PMD - * mapping such that the same physical page is not mapped under - * different attributes. - * - * The recycled area is always at the tail of a partially used PMD - * page. - * - * RETURNS: - * Address of corresponding remapped pcpu address if match is found; - * otherwise, NULL. - */ -void *pcpu_lpage_remapped(void *kaddr) -{ - void *pmd_addr = (void *)((unsigned long)kaddr & PMD_MASK); - unsigned long offset = (unsigned long)kaddr & ~PMD_MASK; - int left = 0, right = nr_cpu_ids - 1; - int pos; - - /* pcpul in use at all? */ - if (!pcpul_map) - return NULL; - - /* okay, perform binary search */ - while (left <= right) { - pos = (left + right) / 2; - - if (pcpul_map[pos].ptr < pmd_addr) - left = pos + 1; - else if (pcpul_map[pos].ptr > pmd_addr) - right = pos - 1; - else { - /* it shouldn't be in the area for the first chunk */ - WARN_ON(offset < pcpul_size); - - return pcpul_vm.addr + - pcpul_map[pos].cpu * PMD_SIZE + offset; + /* don't consume more than 20% of vmalloc area */ + if (tot_size > vm_size / 5) { + pr_info("PERCPU: too large chunk size %zuMB for " + "large page remap\n", tot_size >> 20); + ret = -EINVAL; + goto out_free; } } diff --cc drivers/cpufreq/cpufreq_conservative.c index a7ef465c83b9,bdea7e2f94ba..bc33ddc9c97c --- a/drivers/cpufreq/cpufreq_conservative.c +++ b/drivers/cpufreq/cpufreq_conservative.c @@@ -64,8 -64,14 +64,14 @@@ struct cpu_dbs_info_s unsigned int requested_freq; int cpu; unsigned int enable:1; + /* + * percpu mutex that serializes governor limit change with + * do_dbs_timer invocation. We do not want do_dbs_timer to run + * when user is changing the governor or limits. + */ + struct mutex timer_mutex; }; -static DEFINE_PER_CPU(struct cpu_dbs_info_s, cpu_dbs_info); +static DEFINE_PER_CPU(struct cpu_dbs_info_s, cs_cpu_dbs_info); static unsigned int dbs_enable; /* number of CPUs using this policy */ diff --cc drivers/cpufreq/cpufreq_ondemand.c index 36f292a7bd01,d6ba14276bb1..d7a528c80de8 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@@ -70,10 -70,15 +70,15 @@@ struct cpu_dbs_info_s unsigned int freq_lo_jiffies; unsigned int freq_hi_jiffies; int cpu; - unsigned int enable:1, - sample_type:1; + unsigned int sample_type:1; + /* + * percpu mutex that serializes governor limit change with + * do_dbs_timer invocation. We do not want do_dbs_timer to run + * when user is changing the governor or limits. + */ + struct mutex timer_mutex; }; -static DEFINE_PER_CPU(struct cpu_dbs_info_s, cpu_dbs_info); +static DEFINE_PER_CPU(struct cpu_dbs_info_s, od_cpu_dbs_info); static unsigned int dbs_enable; /* number of CPUs using this policy */ @@@ -193,6 -190,13 +191,13 @@@ static unsigned int powersave_bias_targ return freq_hi; } + static void ondemand_powersave_bias_init_cpu(int cpu) + { - struct cpu_dbs_info_s *dbs_info = &per_cpu(cpu_dbs_info, cpu); ++ struct cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu); + dbs_info->freq_table = cpufreq_frequency_get_table(cpu); + dbs_info->freq_lo = 0; + } + static void ondemand_powersave_bias_init(void) { int i; @@@ -569,9 -550,10 +551,10 @@@ static int cpufreq_governor_dbs(struct return rc; } + dbs_enable++; for_each_cpu(j, policy->cpus) { struct cpu_dbs_info_s *j_dbs_info; - j_dbs_info = &per_cpu(cpu_dbs_info, j); + j_dbs_info = &per_cpu(od_cpu_dbs_info, j); j_dbs_info->cur_policy = policy; j_dbs_info->prev_cpu_idle = get_cpu_idle_time(j, diff --cc include/asm-generic/vmlinux.lds.h index ab8ea9b7741e,6ad76bf5fb40..a43223af98b6 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@@ -30,15 -30,16 +30,13 @@@ * EXCEPTION_TABLE(...) * NOTES * - * __bss_start = .; - * BSS_SECTION(0, 0) - * __bss_stop = .; + * BSS_SECTION(0, 0, 0) * _end = .; * - * /DISCARD/ : { - * EXIT_TEXT - * EXIT_DATA - * EXIT_CALL - * } * STABS_DEBUG * DWARF_DEBUG + * + * DISCARDS // must be the last * } * * [__init_begin, __init_end] is the init section that may be freed after init diff --cc mm/percpu.c index b3d0bcff8c7c,5fe37842e0ea..3f9f182f9b44 --- a/mm/percpu.c +++ b/mm/percpu.c @@@ -1003,8 -747,9 +1003,8 @@@ static struct pcpu_chunk *alloc_pcpu_ch chunk->map = pcpu_mem_alloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0])); chunk->map_alloc = PCPU_DFL_MAP_ALLOC; chunk->map[chunk->map_used++] = pcpu_unit_size; - chunk->page = chunk->page_ar; - chunk->vm = get_vm_area(pcpu_chunk_size, GFP_KERNEL); + chunk->vm = get_vm_area(pcpu_chunk_size, VM_ALLOC); if (!chunk->vm) { free_pcpu_chunk(chunk); return NULL; @@@ -1290,59 -1052,24 +1290,59 @@@ size_t __init pcpu_setup_first_chunk(si BUILD_BUG_ON(ARRAY_SIZE(smap) >= PCPU_DFL_MAP_ALLOC || ARRAY_SIZE(dmap) >= PCPU_DFL_MAP_ALLOC); BUG_ON(!static_size); - if (unit_size >= 0) { - BUG_ON(unit_size < size_sum); - BUG_ON(unit_size & ~PAGE_MASK); - BUG_ON(unit_size < PCPU_MIN_UNIT_SIZE); - } else - BUG_ON(base_addr); - BUG_ON(base_addr && populate_pte_fn); - - if (unit_size >= 0) - pcpu_unit_pages = unit_size >> PAGE_SHIFT; - else - pcpu_unit_pages = max_t(int, PCPU_MIN_UNIT_SIZE >> PAGE_SHIFT, - PFN_UP(size_sum)); + BUG_ON(!base_addr); + BUG_ON(unit_size < size_sum); + BUG_ON(unit_size & ~PAGE_MASK); + BUG_ON(unit_size < PCPU_MIN_UNIT_SIZE); + + /* determine number of units and verify and initialize pcpu_unit_map */ + if (unit_map) { + int first_unit = INT_MAX, last_unit = INT_MIN; + + for_each_possible_cpu(cpu) { + int unit = unit_map[cpu]; + + BUG_ON(unit < 0); + for_each_possible_cpu(tcpu) { + if (tcpu == cpu) + break; + /* the mapping should be one-to-one */ + BUG_ON(unit_map[tcpu] == unit); + } + + if (unit < first_unit) { + pcpu_first_unit_cpu = cpu; + first_unit = unit; + } + if (unit > last_unit) { + pcpu_last_unit_cpu = cpu; + last_unit = unit; + } + } + pcpu_nr_units = last_unit + 1; + pcpu_unit_map = unit_map; + } else { + int *identity_map; + + /* #units == #cpus, identity mapped */ - identity_map = alloc_bootmem(num_possible_cpus() * ++ identity_map = alloc_bootmem(nr_cpu_ids * + sizeof(identity_map[0])); + for_each_possible_cpu(cpu) + identity_map[cpu] = cpu; + + pcpu_first_unit_cpu = 0; + pcpu_last_unit_cpu = pcpu_nr_units - 1; - pcpu_nr_units = num_possible_cpus(); ++ pcpu_nr_units = nr_cpu_ids; + pcpu_unit_map = identity_map; + } + + /* determine basic parameters */ + pcpu_unit_pages = unit_size >> PAGE_SHIFT; pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; - pcpu_chunk_size = nr_cpu_ids * pcpu_unit_size; - pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) - + nr_cpu_ids * pcpu_unit_pages * sizeof(struct page *); + pcpu_chunk_size = pcpu_nr_units * pcpu_unit_size; + pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) + + BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long); if (dyn_size < 0) dyn_size = pcpu_unit_size - static_size - reserved_size; @@@ -1461,555 -1237,44 +1461,558 @@@ ssize_t __init pcpu_embed_first_chunk(s unsigned int cpu; /* determine parameters and allocate */ - pcpue_size = PFN_ALIGN(static_size + reserved_size + - (dyn_size >= 0 ? dyn_size : 0)); - if (dyn_size != 0) - dyn_size = pcpue_size - static_size - reserved_size; - - if (unit_size >= 0) { - BUG_ON(unit_size < pcpue_size); - pcpue_unit_size = unit_size; - } else - pcpue_unit_size = max_t(size_t, pcpue_size, PCPU_MIN_UNIT_SIZE); - - chunk_size = pcpue_unit_size * nr_cpu_ids; - - pcpue_ptr = __alloc_bootmem_nopanic(chunk_size, PAGE_SIZE, - __pa(MAX_DMA_ADDRESS)); - if (!pcpue_ptr) { + size_sum = pcpu_calc_fc_sizes(static_size, reserved_size, &dyn_size); + + unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE); - chunk_size = unit_size * num_possible_cpus(); ++ chunk_size = unit_size * nr_cpu_ids; + + base = __alloc_bootmem_nopanic(chunk_size, PAGE_SIZE, + __pa(MAX_DMA_ADDRESS)); + if (!base) { pr_warning("PERCPU: failed to allocate %zu bytes for " "embedding\n", chunk_size); return -ENOMEM; } /* return the leftover and copy */ - for_each_possible_cpu(cpu) { + for (cpu = 0; cpu < nr_cpu_ids; cpu++) { - void *ptr = pcpue_ptr + cpu * pcpue_unit_size; + void *ptr = base + cpu * unit_size; - free_bootmem(__pa(ptr + size_sum), unit_size - size_sum); - memcpy(ptr, __per_cpu_load, static_size); + if (cpu_possible(cpu)) { - free_bootmem(__pa(ptr + pcpue_size), - pcpue_unit_size - pcpue_size); ++ free_bootmem(__pa(ptr + size_sum), ++ unit_size - size_sum); + memcpy(ptr, __per_cpu_load, static_size); + } else - free_bootmem(__pa(ptr), pcpue_unit_size); ++ free_bootmem(__pa(ptr), unit_size); } /* we're ready, commit */ pr_info("PERCPU: Embedded %zu pages at %p, static data %zu bytes\n", - pcpue_size >> PAGE_SHIFT, pcpue_ptr, static_size); + size_sum >> PAGE_SHIFT, base, static_size); + + return pcpu_setup_first_chunk(static_size, reserved_size, dyn_size, + unit_size, base, NULL); +} + +/** + * pcpu_4k_first_chunk - map the first chunk using PAGE_SIZE pages + * @static_size: the size of static percpu area in bytes + * @reserved_size: the size of reserved percpu area in bytes + * @alloc_fn: function to allocate percpu page, always called with PAGE_SIZE + * @free_fn: funtion to free percpu page, always called with PAGE_SIZE + * @populate_pte_fn: function to populate pte + * + * This is a helper to ease setting up embedded first percpu chunk and + * can be called where pcpu_setup_first_chunk() is expected. + * + * This is the basic allocator. Static percpu area is allocated + * page-by-page into vmalloc area. + * + * RETURNS: + * The determined pcpu_unit_size which can be used to initialize + * percpu access on success, -errno on failure. + */ +ssize_t __init pcpu_4k_first_chunk(size_t static_size, size_t reserved_size, + pcpu_fc_alloc_fn_t alloc_fn, + pcpu_fc_free_fn_t free_fn, + pcpu_fc_populate_pte_fn_t populate_pte_fn) +{ + static struct vm_struct vm; + int unit_pages; + size_t pages_size; + struct page **pages; + unsigned int cpu; + int i, j; + ssize_t ret; + + unit_pages = PFN_UP(max_t(size_t, static_size + reserved_size, + PCPU_MIN_UNIT_SIZE)); + + /* unaligned allocations can't be freed, round up to page size */ - pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() * - sizeof(pages[0])); ++ pages_size = PFN_ALIGN(unit_pages * nr_cpu_ids * sizeof(pages[0])); + pages = alloc_bootmem(pages_size); + + /* allocate pages */ + j = 0; + for_each_possible_cpu(cpu) + for (i = 0; i < unit_pages; i++) { + void *ptr; + + ptr = alloc_fn(cpu, PAGE_SIZE); + if (!ptr) { + pr_warning("PERCPU: failed to allocate " + "4k page for cpu%u\n", cpu); + goto enomem; + } + pages[j++] = virt_to_page(ptr); + } + + /* allocate vm area, map the pages and copy static data */ + vm.flags = VM_ALLOC; - vm.size = num_possible_cpus() * unit_pages << PAGE_SHIFT; ++ vm.size = nr_cpu_ids * unit_pages << PAGE_SHIFT; + vm_area_register_early(&vm, PAGE_SIZE); + + for_each_possible_cpu(cpu) { + unsigned long unit_addr = (unsigned long)vm.addr + + (cpu * unit_pages << PAGE_SHIFT); + + for (i = 0; i < unit_pages; i++) + populate_pte_fn(unit_addr + (i << PAGE_SHIFT)); + + /* pte already populated, the following shouldn't fail */ + ret = __pcpu_map_pages(unit_addr, &pages[cpu * unit_pages], + unit_pages); + if (ret < 0) + panic("failed to map percpu area, err=%zd\n", ret); + + /* + * FIXME: Archs with virtual cache should flush local + * cache for the linear mapping here - something + * equivalent to flush_cache_vmap() on the local cpu. + * flush_cache_vmap() can't be used as most supporting + * data structures are not set up yet. + */ + + /* copy static data */ + memcpy((void *)unit_addr, __per_cpu_load, static_size); + } + + /* we're ready, commit */ + pr_info("PERCPU: %d 4k pages per cpu, static data %zu bytes\n", + unit_pages, static_size); + + ret = pcpu_setup_first_chunk(static_size, reserved_size, -1, + unit_pages << PAGE_SHIFT, vm.addr, NULL); + goto out_free_ar; + +enomem: + while (--j >= 0) + free_fn(page_address(pages[j]), PAGE_SIZE); + ret = -ENOMEM; +out_free_ar: + free_bootmem(__pa(pages), pages_size); + return ret; +} + +/* + * Large page remapping first chunk setup helper + */ +#ifdef CONFIG_NEED_MULTIPLE_NODES + +/** + * pcpu_lpage_build_unit_map - build unit_map for large page remapping + * @static_size: the size of static percpu area in bytes + * @reserved_size: the size of reserved percpu area in bytes + * @dyn_sizep: in/out parameter for dynamic size, -1 for auto + * @unit_sizep: out parameter for unit size + * @unit_map: unit_map to be filled + * @cpu_distance_fn: callback to determine distance between cpus + * + * This function builds cpu -> unit map and determine other parameters + * considering needed percpu size, large page size and distances + * between CPUs in NUMA. + * + * CPUs which are of LOCAL_DISTANCE both ways are grouped together and + * may share units in the same large page. The returned configuration + * is guaranteed to have CPUs on different nodes on different large + * pages and >=75% usage of allocated virtual address space. + * + * RETURNS: + * On success, fills in @unit_map, sets *@dyn_sizep, *@unit_sizep and + * returns the number of units to be allocated. -errno on failure. + */ +int __init pcpu_lpage_build_unit_map(size_t static_size, size_t reserved_size, + ssize_t *dyn_sizep, size_t *unit_sizep, + size_t lpage_size, int *unit_map, + pcpu_fc_cpu_distance_fn_t cpu_distance_fn) +{ + static int group_map[NR_CPUS] __initdata; + static int group_cnt[NR_CPUS] __initdata; + int group_cnt_max = 0; + size_t size_sum, min_unit_size, alloc_size; + int upa, max_upa, uninitialized_var(best_upa); /* units_per_alloc */ + int last_allocs; + unsigned int cpu, tcpu; + int group, unit; + + /* + * Determine min_unit_size, alloc_size and max_upa such that + * alloc_size is multiple of lpage_size and is the smallest + * which can accomodate 4k aligned segments which are equal to + * or larger than min_unit_size. + */ + size_sum = pcpu_calc_fc_sizes(static_size, reserved_size, dyn_sizep); + min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE); + + alloc_size = roundup(min_unit_size, lpage_size); + upa = alloc_size / min_unit_size; + while (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK)) + upa--; + max_upa = upa; + + /* group cpus according to their proximity */ + for_each_possible_cpu(cpu) { + group = 0; + next_group: + for_each_possible_cpu(tcpu) { + if (cpu == tcpu) + break; + if (group_map[tcpu] == group && + (cpu_distance_fn(cpu, tcpu) > LOCAL_DISTANCE || + cpu_distance_fn(tcpu, cpu) > LOCAL_DISTANCE)) { + group++; + goto next_group; + } + } + group_map[cpu] = group; + group_cnt[group]++; + group_cnt_max = max(group_cnt_max, group_cnt[group]); + } + + /* + * Expand unit size until address space usage goes over 75% + * and then as much as possible without using more address + * space. + */ + last_allocs = INT_MAX; + for (upa = max_upa; upa; upa--) { + int allocs = 0, wasted = 0; + + if (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK)) + continue; + + for (group = 0; group_cnt[group]; group++) { + int this_allocs = DIV_ROUND_UP(group_cnt[group], upa); + allocs += this_allocs; + wasted += this_allocs * upa - group_cnt[group]; + } + + /* + * Don't accept if wastage is over 25%. The + * greater-than comparison ensures upa==1 always + * passes the following check. + */ + if (wasted > num_possible_cpus() / 3) + continue; + + /* and then don't consume more memory */ + if (allocs > last_allocs) + break; + last_allocs = allocs; + best_upa = upa; + } + *unit_sizep = alloc_size / best_upa; - return pcpu_setup_first_chunk(pcpue_get_page, static_size, - reserved_size, dyn_size, - pcpue_unit_size, pcpue_ptr, NULL); + /* assign units to cpus accordingly */ + unit = 0; + for (group = 0; group_cnt[group]; group++) { + for_each_possible_cpu(cpu) + if (group_map[cpu] == group) + unit_map[cpu] = unit++; + unit = roundup(unit, best_upa); + } + + return unit; /* unit contains aligned number of units */ +} + +struct pcpul_ent { + void *ptr; + void *map_addr; +}; + +static size_t pcpul_size; +static size_t pcpul_lpage_size; +static int pcpul_nr_lpages; +static struct pcpul_ent *pcpul_map; + +static bool __init pcpul_unit_to_cpu(int unit, const int *unit_map, + unsigned int *cpup) +{ + unsigned int cpu; + + for_each_possible_cpu(cpu) + if (unit_map[cpu] == unit) { + if (cpup) + *cpup = cpu; + return true; + } + + return false; +} + +static void __init pcpul_lpage_dump_cfg(const char *lvl, size_t static_size, + size_t reserved_size, size_t dyn_size, + size_t unit_size, size_t lpage_size, + const int *unit_map, int nr_units) +{ + int width = 1, v = nr_units; + char empty_str[] = "--------"; + int upl, lpl; /* units per lpage, lpage per line */ + unsigned int cpu; + int lpage, unit; + + while (v /= 10) + width++; + empty_str[min_t(int, width, sizeof(empty_str) - 1)] = '\0'; + + upl = max_t(int, lpage_size / unit_size, 1); + lpl = rounddown_pow_of_two(max_t(int, 60 / (upl * (width + 1) + 2), 1)); + + printk("%spcpu-lpage: sta/res/dyn=%zu/%zu/%zu unit=%zu lpage=%zu", lvl, + static_size, reserved_size, dyn_size, unit_size, lpage_size); + + for (lpage = 0, unit = 0; unit < nr_units; unit++) { + if (!(unit % upl)) { + if (!(lpage++ % lpl)) { + printk("\n"); + printk("%spcpu-lpage: ", lvl); + } else + printk("| "); + } + if (pcpul_unit_to_cpu(unit, unit_map, &cpu)) + printk("%0*d ", width, cpu); + else + printk("%s ", empty_str); + } + printk("\n"); +} + +/** + * pcpu_lpage_first_chunk - remap the first percpu chunk using large page + * @static_size: the size of static percpu area in bytes + * @reserved_size: the size of reserved percpu area in bytes + * @dyn_size: free size for dynamic allocation in bytes + * @unit_size: unit size in bytes + * @lpage_size: the size of a large page + * @unit_map: cpu -> unit mapping + * @nr_units: the number of units + * @alloc_fn: function to allocate percpu lpage, always called with lpage_size + * @free_fn: function to free percpu memory, @size <= lpage_size + * @map_fn: function to map percpu lpage, always called with lpage_size + * + * This allocator uses large page to build and map the first chunk. + * Unlike other helpers, the caller should always specify @dyn_size + * and @unit_size. These parameters along with @unit_map and + * @nr_units can be determined using pcpu_lpage_build_unit_map(). + * This two stage initialization is to allow arch code to evaluate the + * parameters before committing to it. + * + * Large pages are allocated as directed by @unit_map and other + * parameters and mapped to vmalloc space. Unused holes are returned + * to the page allocator. Note that these holes end up being actively + * mapped twice - once to the physical mapping and to the vmalloc area + * for the first percpu chunk. Depending on architecture, this might + * cause problem when changing page attributes of the returned area. + * These double mapped areas can be detected using + * pcpu_lpage_remapped(). + * + * RETURNS: + * The determined pcpu_unit_size which can be used to initialize + * percpu access on success, -errno on failure. + */ +ssize_t __init pcpu_lpage_first_chunk(size_t static_size, size_t reserved_size, + size_t dyn_size, size_t unit_size, + size_t lpage_size, const int *unit_map, + int nr_units, + pcpu_fc_alloc_fn_t alloc_fn, + pcpu_fc_free_fn_t free_fn, + pcpu_fc_map_fn_t map_fn) +{ + static struct vm_struct vm; + size_t chunk_size = unit_size * nr_units; + size_t map_size; + unsigned int cpu; + ssize_t ret; + int i, j, unit; + + pcpul_lpage_dump_cfg(KERN_DEBUG, static_size, reserved_size, dyn_size, + unit_size, lpage_size, unit_map, nr_units); + + BUG_ON(chunk_size % lpage_size); + + pcpul_size = static_size + reserved_size + dyn_size; + pcpul_lpage_size = lpage_size; + pcpul_nr_lpages = chunk_size / lpage_size; + + /* allocate pointer array and alloc large pages */ + map_size = pcpul_nr_lpages * sizeof(pcpul_map[0]); + pcpul_map = alloc_bootmem(map_size); + + /* allocate all pages */ + for (i = 0; i < pcpul_nr_lpages; i++) { + size_t offset = i * lpage_size; + int first_unit = offset / unit_size; + int last_unit = (offset + lpage_size - 1) / unit_size; + void *ptr; + + /* find out which cpu is mapped to this unit */ + for (unit = first_unit; unit <= last_unit; unit++) + if (pcpul_unit_to_cpu(unit, unit_map, &cpu)) + goto found; + continue; + found: + ptr = alloc_fn(cpu, lpage_size); + if (!ptr) { + pr_warning("PERCPU: failed to allocate large page " + "for cpu%u\n", cpu); + goto enomem; + } + + pcpul_map[i].ptr = ptr; + } + + /* return unused holes */ + for (unit = 0; unit < nr_units; unit++) { + size_t start = unit * unit_size; + size_t end = start + unit_size; + size_t off, next; + + /* don't free used part of occupied unit */ + if (pcpul_unit_to_cpu(unit, unit_map, NULL)) + start += pcpul_size; + + /* unit can span more than one page, punch the holes */ + for (off = start; off < end; off = next) { + void *ptr = pcpul_map[off / lpage_size].ptr; + next = min(roundup(off + 1, lpage_size), end); + if (ptr) + free_fn(ptr + off % lpage_size, next - off); + } + } + + /* allocate address, map and copy */ + vm.flags = VM_ALLOC; + vm.size = chunk_size; + vm_area_register_early(&vm, unit_size); + + for (i = 0; i < pcpul_nr_lpages; i++) { + if (!pcpul_map[i].ptr) + continue; + pcpul_map[i].map_addr = vm.addr + i * lpage_size; + map_fn(pcpul_map[i].ptr, lpage_size, pcpul_map[i].map_addr); + } + + for_each_possible_cpu(cpu) + memcpy(vm.addr + unit_map[cpu] * unit_size, __per_cpu_load, + static_size); + + /* we're ready, commit */ + pr_info("PERCPU: Remapped at %p with large pages, static data " + "%zu bytes\n", vm.addr, static_size); + + ret = pcpu_setup_first_chunk(static_size, reserved_size, dyn_size, + unit_size, vm.addr, unit_map); + + /* + * Sort pcpul_map array for pcpu_lpage_remapped(). Unmapped + * lpages are pushed to the end and trimmed. + */ + for (i = 0; i < pcpul_nr_lpages - 1; i++) + for (j = i + 1; j < pcpul_nr_lpages; j++) { + struct pcpul_ent tmp; + + if (!pcpul_map[j].ptr) + continue; + if (pcpul_map[i].ptr && + pcpul_map[i].ptr < pcpul_map[j].ptr) + continue; + + tmp = pcpul_map[i]; + pcpul_map[i] = pcpul_map[j]; + pcpul_map[j] = tmp; + } + + while (pcpul_nr_lpages && !pcpul_map[pcpul_nr_lpages - 1].ptr) + pcpul_nr_lpages--; + + return ret; + +enomem: + for (i = 0; i < pcpul_nr_lpages; i++) + if (pcpul_map[i].ptr) + free_fn(pcpul_map[i].ptr, lpage_size); + free_bootmem(__pa(pcpul_map), map_size); + return -ENOMEM; +} + +/** + * pcpu_lpage_remapped - determine whether a kaddr is in pcpul recycled area + * @kaddr: the kernel address in question + * + * Determine whether @kaddr falls in the pcpul recycled area. This is + * used by pageattr to detect VM aliases and break up the pcpu large + * page mapping such that the same physical page is not mapped under + * different attributes. + * + * The recycled area is always at the tail of a partially used large + * page. + * + * RETURNS: + * Address of corresponding remapped pcpu address if match is found; + * otherwise, NULL. + */ +void *pcpu_lpage_remapped(void *kaddr) +{ + unsigned long lpage_mask = pcpul_lpage_size - 1; + void *lpage_addr = (void *)((unsigned long)kaddr & ~lpage_mask); + unsigned long offset = (unsigned long)kaddr & lpage_mask; + int left = 0, right = pcpul_nr_lpages - 1; + int pos; + + /* pcpul in use at all? */ + if (!pcpul_map) + return NULL; + + /* okay, perform binary search */ + while (left <= right) { + pos = (left + right) / 2; + + if (pcpul_map[pos].ptr < lpage_addr) + left = pos + 1; + else if (pcpul_map[pos].ptr > lpage_addr) + right = pos - 1; + else + return pcpul_map[pos].map_addr + offset; + } + + return NULL; +} +#endif + +/* + * Generic percpu area setup. + * + * The embedding helper is used because its behavior closely resembles + * the original non-dynamic generic percpu area setup. This is + * important because many archs have addressing restrictions and might + * fail if the percpu area is located far away from the previous + * location. As an added bonus, in non-NUMA cases, embedding is + * generally a good idea TLB-wise because percpu area can piggy back + * on the physical linear memory mapping which uses large page + * mappings on applicable archs. + */ +#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA +unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; +EXPORT_SYMBOL(__per_cpu_offset); + +void __init setup_per_cpu_areas(void) +{ + size_t static_size = __per_cpu_end - __per_cpu_start; + ssize_t unit_size; + unsigned long delta; + unsigned int cpu; + + /* + * Always reserve area for module percpu variables. That's + * what the legacy allocator did. + */ + unit_size = pcpu_embed_first_chunk(static_size, PERCPU_MODULE_RESERVE, + PERCPU_DYNAMIC_RESERVE); + if (unit_size < 0) + panic("Failed to initialized percpu areas."); + + delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; + for_each_possible_cpu(cpu) + __per_cpu_offset[cpu] = delta + cpu * unit_size; } +#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */