summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2009-09-30 07:58:46 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2009-09-30 07:58:46 -0700
commit07892acf37d98bcf1e5f2df9e23d414ded830b61 (patch)
tree9f84c35573ad4e7f7999b39d5aabea9a5c2a3fc2
parent8c11499a496dd0fcc3817dc0fd5f650f00db1e18 (diff)
parentf2badb0c950ed308be9b321203b9c8d341690cd4 (diff)
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: percpu: make allocation failures more verbose percpu: make pcpu_setup_first_chunk() failures more verbose percpu: make embedding first chunk allocator check vmalloc space size sparc64: implement page mapping percpu first chunk allocator percpu: make pcpu_build_alloc_info() clear static buffers percpu: fix unit_map[] verification in pcpu_setup_first_chunk()
-rw-r--r--arch/sparc/Kconfig3
-rw-r--r--arch/sparc/kernel/smp_64.c53
-rw-r--r--mm/percpu.c83
3 files changed, 114 insertions, 25 deletions
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 97fca4695e0b..ac45aab741a5 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -102,6 +102,9 @@ config HAVE_SETUP_PER_CPU_AREA
config NEED_PER_CPU_EMBED_FIRST_CHUNK
def_bool y if SPARC64
+config NEED_PER_CPU_PAGE_FIRST_CHUNK
+ def_bool y if SPARC64
+
config GENERIC_HARDIRQS_NO__DO_IRQ
bool
def_bool y if SPARC64
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index ff68373ce6d6..aa36223497b9 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -1420,7 +1420,7 @@ static void __init pcpu_free_bootmem(void *ptr, size_t size)
free_bootmem(__pa(ptr), size);
}
-static int pcpu_cpu_distance(unsigned int from, unsigned int to)
+static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
{
if (cpu_to_node(from) == cpu_to_node(to))
return LOCAL_DISTANCE;
@@ -1428,18 +1428,53 @@ static int pcpu_cpu_distance(unsigned int from, unsigned int to)
return REMOTE_DISTANCE;
}
+static void __init pcpu_populate_pte(unsigned long addr)
+{
+ pgd_t *pgd = pgd_offset_k(addr);
+ pud_t *pud;
+ pmd_t *pmd;
+
+ pud = pud_offset(pgd, addr);
+ if (pud_none(*pud)) {
+ pmd_t *new;
+
+ new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
+ pud_populate(&init_mm, pud, new);
+ }
+
+ pmd = pmd_offset(pud, addr);
+ if (!pmd_present(*pmd)) {
+ pte_t *new;
+
+ new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
+ pmd_populate_kernel(&init_mm, pmd, new);
+ }
+}
+
void __init setup_per_cpu_areas(void)
{
unsigned long delta;
unsigned int cpu;
- int rc;
-
- rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
- PERCPU_DYNAMIC_RESERVE, 4 << 20,
- pcpu_cpu_distance, pcpu_alloc_bootmem,
- pcpu_free_bootmem);
- if (rc)
- panic("failed to initialize first chunk (%d)", rc);
+ int rc = -EINVAL;
+
+ if (pcpu_chosen_fc != PCPU_FC_PAGE) {
+ rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
+ PERCPU_DYNAMIC_RESERVE, 4 << 20,
+ pcpu_cpu_distance,
+ pcpu_alloc_bootmem,
+ pcpu_free_bootmem);
+ if (rc)
+ pr_warning("PERCPU: %s allocator failed (%d), "
+ "falling back to page size\n",
+ pcpu_fc_names[pcpu_chosen_fc], rc);
+ }
+ if (rc < 0)
+ rc = pcpu_page_first_chunk(PERCPU_MODULE_RESERVE,
+ pcpu_alloc_bootmem,
+ pcpu_free_bootmem,
+ pcpu_populate_pte);
+ if (rc < 0)
+ panic("cannot initialize percpu area (err=%d)", rc);
delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
for_each_possible_cpu(cpu)
diff --git a/mm/percpu.c b/mm/percpu.c
index 43d8cacfdaa5..4a048abad043 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1043,7 +1043,9 @@ static struct pcpu_chunk *alloc_pcpu_chunk(void)
*/
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)) {
@@ -1059,11 +1061,14 @@ static void *pcpu_alloc(size_t size, size_t align, bool reserved)
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;
}
@@ -1080,6 +1085,7 @@ restart:
case 1:
goto restart; /* pcpu_lock dropped, restart */
default:
+ err = "failed to extend area map";
goto fail_unlock;
}
@@ -1093,8 +1099,10 @@ restart:
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);
@@ -1107,6 +1115,7 @@ area_found:
if (pcpu_populate_chunk(chunk, off, size)) {
spin_lock_irq(&pcpu_lock);
pcpu_free_area(chunk, off);
+ err = "failed to populate";
goto fail_unlock;
}
@@ -1119,6 +1128,13 @@ 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;
}
@@ -1347,6 +1363,10 @@ struct pcpu_alloc_info * __init pcpu_build_alloc_info(
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
@@ -1574,6 +1594,7 @@ static void pcpu_dump_alloc_info(const char *lvl,
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;
@@ -1585,17 +1606,26 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
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]));
@@ -1604,7 +1634,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
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) {
@@ -1618,8 +1648,9 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
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;
@@ -1632,7 +1663,11 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
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;
@@ -1782,7 +1817,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size,
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,
@@ -1832,8 +1867,24 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_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(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%lx 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,