* 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));
}
*/
static void *pcpu_alloc(size_t size, size_t align, bool reserved)
{
+ static int warn_limit = 10;
struct pcpu_chunk *chunk;
+ const char *err;
int slot, off;
if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) {
if (reserved && pcpu_reserved_chunk) {
chunk = pcpu_reserved_chunk;
if (size > chunk->contig_hint ||
- pcpu_extend_area_map(chunk) < 0)
+ pcpu_extend_area_map(chunk) < 0) {
+ err = "failed to extend area map of reserved chunk";
goto fail_unlock;
+ }
off = pcpu_alloc_area(chunk, size, align);
if (off >= 0)
goto area_found;
+ err = "alloc from reserved chunk failed";
goto fail_unlock;
}
case 1:
goto restart; /* pcpu_lock dropped, restart */
default:
+ err = "failed to extend area map";
goto fail_unlock;
}
spin_unlock_irq(&pcpu_lock);
chunk = alloc_pcpu_chunk();
- if (!chunk)
+ if (!chunk) {
+ err = "failed to allocate new chunk";
goto fail_unlock_mutex;
+ }
spin_lock_irq(&pcpu_lock);
pcpu_chunk_relocate(chunk, -1);
if (pcpu_populate_chunk(chunk, off, size)) {
spin_lock_irq(&pcpu_lock);
pcpu_free_area(chunk, off);
+ err = "failed to populate";
goto fail_unlock;
}
spin_unlock_irq(&pcpu_lock);
fail_unlock_mutex:
mutex_unlock(&pcpu_alloc_mutex);
+ if (warn_limit) {
+ pr_warning("PERCPU: allocation failed, size=%zu align=%zu, "
+ "%s\n", size, align, err);
+ dump_stack();
+ if (!--warn_limit)
+ pr_info("PERCPU: limit reached, disable warning\n");
+ }
return NULL;
}
struct pcpu_alloc_info *ai;
unsigned int *cpu_map;
+ /* this function may be called multiple times */
+ memset(group_map, 0, sizeof(group_map));
+ memset(group_cnt, 0, sizeof(group_map));
+
/*
* Determine min_unit_size, alloc_size and max_upa such that
* alloc_size is multiple of atom_size and is the smallest
int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
void *base_addr)
{
+ static char cpus_buf[4096] __initdata;
static int smap[2], dmap[2];
size_t dyn_size = ai->dyn_size;
size_t size_sum = ai->static_size + ai->reserved_size + dyn_size;
int *unit_map;
int group, unit, i;
+ cpumask_scnprintf(cpus_buf, sizeof(cpus_buf), cpu_possible_mask);
+
+#define PCPU_SETUP_BUG_ON(cond) do { \
+ if (unlikely(cond)) { \
+ pr_emerg("PERCPU: failed to initialize, %s", #cond); \
+ pr_emerg("PERCPU: cpu_possible_mask=%s\n", cpus_buf); \
+ pcpu_dump_alloc_info(KERN_EMERG, ai); \
+ BUG(); \
+ } \
+} while (0)
+
/* sanity checks */
BUILD_BUG_ON(ARRAY_SIZE(smap) >= PCPU_DFL_MAP_ALLOC ||
ARRAY_SIZE(dmap) >= PCPU_DFL_MAP_ALLOC);
- BUG_ON(ai->nr_groups <= 0);
- BUG_ON(!ai->static_size);
- BUG_ON(!base_addr);
- BUG_ON(ai->unit_size < size_sum);
- BUG_ON(ai->unit_size & ~PAGE_MASK);
- BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE);
-
- pcpu_dump_alloc_info(KERN_DEBUG, ai);
+ PCPU_SETUP_BUG_ON(ai->nr_groups <= 0);
+ PCPU_SETUP_BUG_ON(!ai->static_size);
+ PCPU_SETUP_BUG_ON(!base_addr);
+ PCPU_SETUP_BUG_ON(ai->unit_size < size_sum);
+ PCPU_SETUP_BUG_ON(ai->unit_size & ~PAGE_MASK);
+ PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE);
/* process group information and build config tables accordingly */
group_offsets = alloc_bootmem(ai->nr_groups * sizeof(group_offsets[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) {
if (cpu == NR_CPUS)
continue;
- BUG_ON(cpu > nr_cpu_ids || !cpu_possible(cpu));
- BUG_ON(unit_map[cpu] != NR_CPUS);
+ PCPU_SETUP_BUG_ON(cpu > nr_cpu_ids);
+ PCPU_SETUP_BUG_ON(!cpu_possible(cpu));
+ PCPU_SETUP_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);
+ PCPU_SETUP_BUG_ON(unit_map[cpu] == UINT_MAX);
+
+ /* we're done parsing the input, undefine BUG macro and dump config */
+#undef PCPU_SETUP_BUG_ON
+ pcpu_dump_alloc_info(KERN_INFO, ai);
pcpu_nr_groups = ai->nr_groups;
pcpu_group_offsets = group_offsets;
[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);
void *base = (void *)ULONG_MAX;
void **areas = NULL;
struct pcpu_alloc_info *ai;
- size_t size_sum, areas_size;
+ size_t size_sum, areas_size, max_distance;
int group, i, rc;
ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size,
}
/* base address is now known, determine group base offsets */
- for (group = 0; group < ai->nr_groups; group++)
+ max_distance = 0;
+ for (group = 0; group < ai->nr_groups; group++) {
ai->groups[group].base_offset = areas[group] - base;
+ max_distance = max_t(size_t, max_distance,
+ ai->groups[group].base_offset);
+ }
+ max_distance += ai->unit_size;
+
+ /* warn if maximum distance is further than 75% of vmalloc space */
+ if (max_distance > (VMALLOC_END - VMALLOC_START) * 3 / 4) {
+ pr_warning("PERCPU: max_distance=0x%zx too large for vmalloc "
+ "space 0x%lx\n",
+ max_distance, VMALLOC_END - VMALLOC_START);
+#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+ /* and fail if we have fallback */
+ rc = -EINVAL;
+ goto out_free;
+#endif
+ }
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,
}
#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.
*