summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorKefeng Wang <wangkefeng.wang@huawei.com>2022-01-20 03:07:49 +0100
committerLinus Torvalds <torvalds@linux-foundation.org>2022-01-20 07:52:52 +0100
commit23f917169ef157aa7a6bf80d8c4aad6f1282852c (patch)
tree2432700cc0a823ccb7a5d47ee1518da5efea2c1e /mm
parentmm: percpu: add pcpu_fc_cpu_to_node_fn_t typedef (diff)
downloadlinux-23f917169ef157aa7a6bf80d8c4aad6f1282852c.tar.xz
linux-23f917169ef157aa7a6bf80d8c4aad6f1282852c.zip
mm: percpu: add generic pcpu_fc_alloc/free funciton
With the previous patch, we could add a generic pcpu first chunk allocate and free function to cleanup the duplicated definations on each architecture. Link: https://lkml.kernel.org/r/20211216112359.103822-4-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Dennis Zhou <dennis@kernel.org> Cc: Tejun Heo <tj@kernel.org> Cc: Christoph Lameter <cl@linux.com> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: "Rafael J. Wysocki" <rafael@kernel.org> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/percpu.c78
1 files changed, 47 insertions, 31 deletions
diff --git a/mm/percpu.c b/mm/percpu.c
index 267a4d295fcf..0f79b6d9a6d6 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -2992,6 +2992,42 @@ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info(
return ai;
}
+
+static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align,
+ pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn)
+{
+ const unsigned long goal = __pa(MAX_DMA_ADDRESS);
+#ifdef CONFIG_NUMA
+ int node = NUMA_NO_NODE;
+ void *ptr;
+
+ if (cpu_to_nd_fn)
+ node = cpu_to_nd_fn(cpu);
+
+ if (node == NUMA_NO_NODE || !node_online(node) || !NODE_DATA(node)) {
+ ptr = memblock_alloc_from(size, align, goal);
+ pr_info("cpu %d has no node %d or node-local memory\n",
+ cpu, node);
+ pr_debug("per cpu data for cpu%d %zu bytes at 0x%llx\n",
+ cpu, size, (u64)__pa(ptr));
+ } else {
+ ptr = memblock_alloc_try_nid(size, align, goal,
+ MEMBLOCK_ALLOC_ACCESSIBLE,
+ node);
+
+ pr_debug("per cpu data for cpu%d %zu bytes on node%d at 0x%llx\n",
+ cpu, size, node, (u64)__pa(ptr));
+ }
+ return ptr;
+#else
+ return memblock_alloc_from(size, align, goal);
+#endif
+}
+
+static void __init pcpu_fc_free(void *ptr, size_t size)
+{
+ memblock_free(ptr, size);
+}
#endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */
#if defined(BUILD_EMBED_FIRST_CHUNK)
@@ -3002,14 +3038,12 @@ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info(
* @atom_size: allocation atom size
* @cpu_distance_fn: callback to determine distance between cpus, optional
* @cpu_to_nd_fn: callback to convert cpu to it's node, optional
- * @alloc_fn: function to allocate percpu page
- * @free_fn: function 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
- * by calling @alloc_fn and used as-is without being mapped into
+ * by calling pcpu_fc_alloc and used as-is without being mapped into
* vmalloc area. Allocations are always whole multiples of @atom_size
* aligned to @atom_size.
*
@@ -3023,7 +3057,7 @@ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info(
* @dyn_size specifies the minimum dynamic area size.
*
* If the needed size is smaller than the minimum or specified unit
- * size, the leftover is returned using @free_fn.
+ * size, the leftover is returned using pcpu_fc_free.
*
* RETURNS:
* 0 on success, -errno on failure.
@@ -3031,9 +3065,7 @@ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info(
int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
size_t atom_size,
pcpu_fc_cpu_distance_fn_t cpu_distance_fn,
- pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn,
- pcpu_fc_alloc_fn_t alloc_fn,
- pcpu_fc_free_fn_t free_fn)
+ pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn)
{
void *base = (void *)ULONG_MAX;
void **areas = NULL;
@@ -3068,7 +3100,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
BUG_ON(cpu == NR_CPUS);
/* allocate space for the whole group */
- ptr = alloc_fn(cpu, gi->nr_units * ai->unit_size, atom_size, cpu_to_nd_fn);
+ ptr = pcpu_fc_alloc(cpu, gi->nr_units * ai->unit_size, atom_size, cpu_to_nd_fn);
if (!ptr) {
rc = -ENOMEM;
goto out_free_areas;
@@ -3107,12 +3139,12 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
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);
+ pcpu_fc_free(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);
+ pcpu_fc_free(ptr + size_sum, ai->unit_size - size_sum);
}
}
@@ -3131,7 +3163,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
out_free_areas:
for (group = 0; group < ai->nr_groups; group++)
if (areas[group])
- free_fn(areas[group],
+ pcpu_fc_free(areas[group],
ai->groups[group].nr_units * ai->unit_size);
out_free:
pcpu_free_alloc_info(ai);
@@ -3146,8 +3178,6 @@ out_free:
* pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages
* @reserved_size: the size of reserved percpu area in bytes
* @cpu_to_nd_fn: callback to convert cpu to it's node, optional
- * @alloc_fn: function to allocate percpu page, always called with PAGE_SIZE
- * @free_fn: function to free percpu page, always called with PAGE_SIZE
* @populate_pte_fn: function to populate pte
*
* This is a helper to ease setting up page-remapped first percpu
@@ -3161,8 +3191,6 @@ out_free:
*/
int __init pcpu_page_first_chunk(size_t reserved_size,
pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn,
- 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;
@@ -3205,7 +3233,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size,
for (i = 0; i < unit_pages; i++) {
void *ptr;
- ptr = alloc_fn(cpu, PAGE_SIZE, PAGE_SIZE, cpu_to_nd_fn);
+ ptr = pcpu_fc_alloc(cpu, PAGE_SIZE, PAGE_SIZE, cpu_to_nd_fn);
if (!ptr) {
pr_warn("failed to allocate %s page for cpu%u\n",
psize_str, cpu);
@@ -3257,7 +3285,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size,
enomem:
while (--j >= 0)
- free_fn(page_address(pages[j]), PAGE_SIZE);
+ pcpu_fc_free(page_address(pages[j]), PAGE_SIZE);
rc = -ENOMEM;
out_free_ar:
memblock_free(pages, pages_size);
@@ -3282,17 +3310,6 @@ out_free_ar:
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,
- pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn)
-{
- return memblock_alloc_from(size, align, __pa(MAX_DMA_ADDRESS));
-}
-
-static void __init pcpu_dfl_fc_free(void *ptr, size_t size)
-{
- memblock_free(ptr, size);
-}
-
void __init setup_per_cpu_areas(void)
{
unsigned long delta;
@@ -3303,9 +3320,8 @@ void __init setup_per_cpu_areas(void)
* Always reserve area for module percpu variables. That's
* what the legacy allocator did.
*/
- rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
- PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL, NULL,
- pcpu_dfl_fc_alloc, pcpu_dfl_fc_free);
+ rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE,
+ PAGE_SIZE, NULL, NULL);
if (rc < 0)
panic("Failed to initialize percpu areas.");