arm64: support page mapping percpu first chunk allocator

Percpu embedded first chunk allocator is the firstly option, but it
could fails on ARM64, eg,

  percpu: max_distance=0x5fcfdc640000 too large for vmalloc space 0x781fefff0000
  percpu: max_distance=0x600000540000 too large for vmalloc space 0x7dffb7ff0000
  percpu: max_distance=0x5fff9adb0000 too large for vmalloc space 0x5dffb7ff0000

then we could get

  WARNING: CPU: 15 PID: 461 at vmalloc.c:3087 pcpu_get_vm_areas+0x488/0x838

and the system could not boot successfully.

Let's implement page mapping percpu first chunk allocator as a fallback
to the embedding allocator to increase the robustness of the system.

Link: https://lkml.kernel.org/r/20210910053354.26721-3-wangkefeng.wang@huawei.com
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Marco Elver <elver@google.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Kefeng Wang 2021-11-05 13:39:44 -07:00 committed by Linus Torvalds
parent 0eb68437a7
commit 09cea61950
2 changed files with 76 additions and 10 deletions

View File

@ -1042,6 +1042,10 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK
def_bool y
depends on NUMA
config NEED_PER_CPU_PAGE_FIRST_CHUNK
def_bool y
depends on NUMA
source "kernel/Kconfig.hz"
config ARCH_SPARSEMEM_ENABLE

View File

@ -14,6 +14,7 @@
#include <linux/of.h>
#include <asm/sections.h>
#include <asm/pgalloc.h>
struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
EXPORT_SYMBOL(node_data);
@ -168,22 +169,83 @@ static void __init pcpu_fc_free(void *ptr, size_t size)
memblock_free_early(__pa(ptr), size);
}
#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
static void __init pcpu_populate_pte(unsigned long addr)
{
pgd_t *pgd = pgd_offset_k(addr);
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
p4d = p4d_offset(pgd, addr);
if (p4d_none(*p4d)) {
pud_t *new;
new = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
if (!new)
goto err_alloc;
p4d_populate(&init_mm, p4d, new);
}
pud = pud_offset(p4d, addr);
if (pud_none(*pud)) {
pmd_t *new;
new = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
if (!new)
goto err_alloc;
pud_populate(&init_mm, pud, new);
}
pmd = pmd_offset(pud, addr);
if (!pmd_present(*pmd)) {
pte_t *new;
new = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
if (!new)
goto err_alloc;
pmd_populate_kernel(&init_mm, pmd, new);
}
return;
err_alloc:
panic("%s: Failed to allocate %lu bytes align=%lx from=%lx\n",
__func__, PAGE_SIZE, PAGE_SIZE, PAGE_SIZE);
}
#endif
void __init setup_per_cpu_areas(void)
{
unsigned long delta;
unsigned int cpu;
int rc;
int rc = -EINVAL;
/*
* 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,
pcpu_cpu_distance,
pcpu_fc_alloc, pcpu_fc_free);
if (pcpu_chosen_fc != PCPU_FC_PAGE) {
/*
* 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,
pcpu_cpu_distance,
pcpu_fc_alloc, pcpu_fc_free);
#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
if (rc < 0)
pr_warn("PERCPU: %s allocator failed (%d), falling back to page size\n",
pcpu_fc_names[pcpu_chosen_fc], rc);
#endif
}
#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
if (rc < 0)
panic("Failed to initialize percpu areas.");
rc = pcpu_page_first_chunk(PERCPU_MODULE_RESERVE,
pcpu_fc_alloc,
pcpu_fc_free,
pcpu_populate_pte);
#endif
if (rc < 0)
panic("Failed to initialize percpu areas (err=%d).", rc);
delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
for_each_possible_cpu(cpu)