int map_used; /* # of map entries used */
int map_alloc; /* # of map entries allocated */
int *map; /* allocation map */
- struct vm_struct *vm; /* mapped vmalloc region */
+ struct vm_struct **vms; /* mapped vmalloc regions */
bool immutable; /* no [de]population allowed */
unsigned long populated[]; /* populated bitmap */
};
static int pcpu_unit_pages __read_mostly;
static int pcpu_unit_size __read_mostly;
static int pcpu_nr_units __read_mostly;
-static int pcpu_chunk_size __read_mostly;
+static int pcpu_atom_size __read_mostly;
static int pcpu_nr_slots __read_mostly;
static size_t pcpu_chunk_struct_size __read_mostly;
static const int *pcpu_unit_map __read_mostly; /* cpu -> unit */
const unsigned long *pcpu_unit_offsets __read_mostly; /* cpu -> unit offset */
+/* group information, used for vm allocation */
+static int pcpu_nr_groups __read_mostly;
+static const unsigned long *pcpu_group_offsets __read_mostly;
+static const size_t *pcpu_group_sizes __read_mostly;
+
/*
* The first chunk which always exists. Note that unlike other
* chunks, this one can be allocated and mapped in several different
* space. Note that any possible cpu id can be used here, so
* there's no need to worry about preemption or cpu hotplug.
*/
- addr += pcpu_unit_offsets[smp_processor_id()];
+ addr += pcpu_unit_offsets[raw_smp_processor_id()];
return pcpu_get_page_chunk(vmalloc_to_page(addr));
}
{
if (!chunk)
return;
- if (chunk->vm)
- free_vm_area(chunk->vm);
+ if (chunk->vms)
+ pcpu_free_vm_areas(chunk->vms, pcpu_nr_groups);
pcpu_mem_free(chunk->map, chunk->map_alloc * sizeof(chunk->map[0]));
kfree(chunk);
}
chunk->map_alloc = PCPU_DFL_MAP_ALLOC;
chunk->map[chunk->map_used++] = pcpu_unit_size;
- chunk->vm = get_vm_area(pcpu_chunk_size, VM_ALLOC);
- if (!chunk->vm) {
+ chunk->vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes,
+ pcpu_nr_groups, pcpu_atom_size,
+ GFP_KERNEL);
+ if (!chunk->vms) {
free_pcpu_chunk(chunk);
return NULL;
}
INIT_LIST_HEAD(&chunk->list);
chunk->free_size = pcpu_unit_size;
chunk->contig_hint = pcpu_unit_size;
- chunk->base_addr = chunk->vm->addr;
+ chunk->base_addr = chunk->vms[0]->addr - pcpu_group_offsets[0];
return chunk;
}
size_t dyn_size = ai->dyn_size;
size_t size_sum = ai->static_size + ai->reserved_size + dyn_size;
struct pcpu_chunk *schunk, *dchunk = NULL;
+ unsigned long *group_offsets;
+ size_t *group_sizes;
unsigned long *unit_off;
unsigned int cpu;
int *unit_map;
pcpu_dump_alloc_info(KERN_DEBUG, ai);
- /* determine number of units and initialize unit_map and base */
+ /* process group information and build config tables accordingly */
+ group_offsets = alloc_bootmem(ai->nr_groups * sizeof(group_offsets[0]));
+ group_sizes = alloc_bootmem(ai->nr_groups * sizeof(group_sizes[0]));
unit_map = alloc_bootmem(nr_cpu_ids * sizeof(unit_map[0]));
unit_off = alloc_bootmem(nr_cpu_ids * sizeof(unit_off[0]));
for (cpu = 0; cpu < nr_cpu_ids; cpu++)
- unit_map[cpu] = NR_CPUS;
+ unit_map[cpu] = UINT_MAX;
pcpu_first_unit_cpu = NR_CPUS;
for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) {
const struct pcpu_group_info *gi = &ai->groups[group];
+ group_offsets[group] = gi->base_offset;
+ group_sizes[group] = gi->nr_units * ai->unit_size;
+
for (i = 0; i < gi->nr_units; i++) {
cpu = gi->cpu_map[i];
if (cpu == NR_CPUS)
continue;
BUG_ON(cpu > nr_cpu_ids || !cpu_possible(cpu));
- BUG_ON(unit_map[cpu] != NR_CPUS);
+ BUG_ON(unit_map[cpu] != UINT_MAX);
unit_map[cpu] = unit + i;
unit_off[cpu] = gi->base_offset + i * ai->unit_size;
pcpu_nr_units = unit;
for_each_possible_cpu(cpu)
- BUG_ON(unit_map[cpu] == NR_CPUS);
+ BUG_ON(unit_map[cpu] == UINT_MAX);
+ pcpu_nr_groups = ai->nr_groups;
+ pcpu_group_offsets = group_offsets;
+ pcpu_group_sizes = group_sizes;
pcpu_unit_map = unit_map;
pcpu_unit_offsets = unit_off;
/* determine basic parameters */
pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT;
pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
- pcpu_chunk_size = pcpu_nr_units * pcpu_unit_size;
+ pcpu_atom_size = ai->atom_size;
pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) +
BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long);
[PCPU_FC_AUTO] = "auto",
[PCPU_FC_EMBED] = "embed",
[PCPU_FC_PAGE] = "page",
- [PCPU_FC_LPAGE] = "lpage",
};
enum pcpu_fc pcpu_chosen_fc __initdata = PCPU_FC_AUTO;
else if (!strcmp(str, "page"))
pcpu_chosen_fc = PCPU_FC_PAGE;
#endif
-#ifdef CONFIG_NEED_PER_CPU_LPAGE_FIRST_CHUNK
- else if (!strcmp(str, "lpage"))
- pcpu_chosen_fc = PCPU_FC_LPAGE;
-#endif
else
pr_warning("PERCPU: unknown allocator %s specified\n", str);
* pcpu_embed_first_chunk - embed the first percpu chunk into bootmem
* @reserved_size: the size of reserved percpu area in bytes
* @dyn_size: free size for dynamic allocation in bytes, -1 for auto
+ * @atom_size: allocation atom size
+ * @cpu_distance_fn: callback to determine distance between cpus, optional
+ * @alloc_fn: function to allocate percpu page
+ * @free_fn: funtion to free percpu page
*
* This is a helper to ease setting up embedded first percpu chunk and
* can be called where pcpu_setup_first_chunk() is expected.
*
* If this function is used to setup the first chunk, it is allocated
- * as a contiguous area using bootmem allocator and used as-is without
- * being mapped into vmalloc area. This enables the first chunk to
- * piggy back on the linear physical mapping which often uses larger
- * page size.
+ * by calling @alloc_fn and used as-is without being mapped into
+ * vmalloc area. Allocations are always whole multiples of @atom_size
+ * aligned to @atom_size.
+ *
+ * This enables the first chunk to piggy back on the linear physical
+ * mapping which often uses larger page size. Please note that this
+ * can result in very sparse cpu->unit mapping on NUMA machines thus
+ * requiring large vmalloc address space. Don't use this allocator if
+ * vmalloc space is not orders of magnitude larger than distances
+ * between node memory addresses (ie. 32bit NUMA machines).
*
* When @dyn_size is positive, dynamic area might be larger than
* specified to fill page alignment. When @dyn_size is auto,
* and reserved areas.
*
* If the needed size is smaller than the minimum or specified unit
- * size, the leftover is returned to the bootmem allocator.
+ * size, the leftover is returned using @free_fn.
*
* RETURNS:
* 0 on success, -errno on failure.
*/
-int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size)
+int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size,
+ size_t atom_size,
+ pcpu_fc_cpu_distance_fn_t cpu_distance_fn,
+ pcpu_fc_alloc_fn_t alloc_fn,
+ pcpu_fc_free_fn_t free_fn)
{
+ void *base = (void *)ULONG_MAX;
+ void **areas = NULL;
struct pcpu_alloc_info *ai;
- size_t size_sum, chunk_size;
- void *base;
- int unit;
- int rc;
+ size_t size_sum, areas_size;
+ int group, i, rc;
- ai = pcpu_build_alloc_info(reserved_size, dyn_size, PAGE_SIZE, NULL);
+ ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size,
+ cpu_distance_fn);
if (IS_ERR(ai))
return PTR_ERR(ai);
- BUG_ON(ai->nr_groups != 1);
- BUG_ON(ai->groups[0].nr_units != num_possible_cpus());
size_sum = ai->static_size + ai->reserved_size + ai->dyn_size;
- chunk_size = ai->unit_size * num_possible_cpus();
+ areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *));
- 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);
+ areas = alloc_bootmem_nopanic(areas_size);
+ if (!areas) {
rc = -ENOMEM;
- goto out_free_ai;
+ goto out_free;
}
- /* return the leftover and copy */
- for (unit = 0; unit < num_possible_cpus(); unit++) {
- void *ptr = base + unit * ai->unit_size;
+ /* allocate, copy and determine base address */
+ for (group = 0; group < ai->nr_groups; group++) {
+ struct pcpu_group_info *gi = &ai->groups[group];
+ unsigned int cpu = NR_CPUS;
+ void *ptr;
- free_bootmem(__pa(ptr + size_sum), ai->unit_size - size_sum);
- memcpy(ptr, __per_cpu_load, ai->static_size);
+ for (i = 0; i < gi->nr_units && cpu == NR_CPUS; i++)
+ cpu = gi->cpu_map[i];
+ BUG_ON(cpu == NR_CPUS);
+
+ /* allocate space for the whole group */
+ ptr = alloc_fn(cpu, gi->nr_units * ai->unit_size, atom_size);
+ if (!ptr) {
+ rc = -ENOMEM;
+ goto out_free_areas;
+ }
+ areas[group] = ptr;
+
+ base = min(ptr, base);
+
+ for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) {
+ if (gi->cpu_map[i] == NR_CPUS) {
+ /* unused unit, free whole */
+ free_fn(ptr, ai->unit_size);
+ continue;
+ }
+ /* copy and return the unused part */
+ memcpy(ptr, __per_cpu_load, ai->static_size);
+ free_fn(ptr + size_sum, ai->unit_size - size_sum);
+ }
}
- /* we're ready, commit */
+ /* base address is now known, determine group base offsets */
+ for (group = 0; group < ai->nr_groups; group++)
+ ai->groups[group].base_offset = areas[group] - base;
+
pr_info("PERCPU: Embedded %zu pages/cpu @%p s%zu r%zu d%zu u%zu\n",
PFN_DOWN(size_sum), base, ai->static_size, ai->reserved_size,
ai->dyn_size, ai->unit_size);
rc = pcpu_setup_first_chunk(ai, base);
-out_free_ai:
+ goto out_free;
+
+out_free_areas:
+ for (group = 0; group < ai->nr_groups; group++)
+ free_fn(areas[group],
+ ai->groups[group].nr_units * ai->unit_size);
+out_free:
pcpu_free_alloc_info(ai);
+ if (areas)
+ free_bootmem(__pa(areas), areas_size);
return rc;
}
#endif /* CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK ||
}
#endif /* CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK */
-#ifdef CONFIG_NEED_PER_CPU_LPAGE_FIRST_CHUNK
-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 struct pcpu_alloc_info *ai,
- unsigned int *cpup)
-{
- int group, cunit;
-
- for (group = 0, cunit = 0; group < ai->nr_groups; group++) {
- const struct pcpu_group_info *gi = &ai->groups[group];
-
- if (unit < cunit + gi->nr_units) {
- if (cpup)
- *cpup = gi->cpu_map[unit - cunit];
- return true;
- }
- cunit += gi->nr_units;
- }
-
- return false;
-}
-
-static int __init pcpul_cpu_to_unit(int cpu, const struct pcpu_alloc_info *ai)
-{
- int group, unit, i;
-
- for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) {
- const struct pcpu_group_info *gi = &ai->groups[group];
-
- for (i = 0; i < gi->nr_units; i++)
- if (gi->cpu_map[i] == cpu)
- return unit + i;
- }
- BUG();
-}
-
-/**
- * pcpu_lpage_first_chunk - remap the first percpu chunk using large page
- * @ai: pcpu_alloc_info
- * @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 provide fully initialized
- * @ai. This can be done using pcpu_build_alloc_info(). 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:
- * 0 on success, -errno on failure.
- */
-int __init pcpu_lpage_first_chunk(const struct pcpu_alloc_info *ai,
- 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;
- const size_t lpage_size = ai->atom_size;
- size_t chunk_size, map_size;
- unsigned int cpu;
- int i, j, unit, nr_units, rc;
-
- nr_units = 0;
- for (i = 0; i < ai->nr_groups; i++)
- nr_units += ai->groups[i].nr_units;
-
- chunk_size = ai->unit_size * nr_units;
- BUG_ON(chunk_size % lpage_size);
-
- pcpul_size = ai->static_size + ai->reserved_size + ai->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 / ai->unit_size;
- int last_unit = (offset + lpage_size - 1) / ai->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, ai, &cpu))
- goto found;
- continue;
- found:
- ptr = alloc_fn(cpu, lpage_size, 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 * ai->unit_size;
- size_t end = start + ai->unit_size;
- size_t off, next;
-
- /* don't free used part of occupied unit */
- if (pcpul_unit_to_cpu(unit, ai, 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, ai->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 + pcpul_cpu_to_unit(cpu, ai) * ai->unit_size,
- __per_cpu_load, ai->static_size);
-
- /* we're ready, commit */
- pr_info("PERCPU: large pages @%p s%zu r%zu d%zu u%zu\n",
- vm.addr, ai->static_size, ai->reserved_size, ai->dyn_size,
- ai->unit_size);
-
- rc = pcpu_setup_first_chunk(ai, vm.addr);
-
- /*
- * 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 rc;
-
-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 /* CONFIG_NEED_PER_CPU_LPAGE_FIRST_CHUNK */
-
/*
* Generic percpu area setup.
*
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(__per_cpu_offset);
+static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size,
+ size_t align)
+{
+ return __alloc_bootmem_nopanic(size, align, __pa(MAX_DMA_ADDRESS));
+}
+
+static void __init pcpu_dfl_fc_free(void *ptr, size_t size)
+{
+ free_bootmem(__pa(ptr), size);
+}
+
void __init setup_per_cpu_areas(void)
{
unsigned long delta;
* what the legacy allocator did.
*/
rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
- PERCPU_DYNAMIC_RESERVE);
+ PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL,
+ pcpu_dfl_fc_alloc, pcpu_dfl_fc_free);
if (rc < 0)
panic("Failed to initialized percpu areas.");