linux/mm/sparse-vmemmap.c
Aneesh Kumar K.V 87a7ae75d7 mm/vmemmap/devdax: fix kernel crash when probing devdax devices
commit 4917f55b4e ("mm/sparse-vmemmap: improve memory savings for
compound devmaps") added support for using optimized vmmemap for devdax
devices.  But how vmemmap mappings are created are architecture specific. 
For example, powerpc with hash translation doesn't have vmemmap mappings
in init_mm page table instead they are bolted table entries in the
hardware page table

vmemmap_populate_compound_pages() used by vmemmap optimization code is not
aware of these architecture-specific mapping.  Hence allow architecture to
opt for this feature.  I selected architectures supporting
HUGETLB_PAGE_OPTIMIZE_VMEMMAP option as also supporting this feature.

This patch fixes the below crash on ppc64.

BUG: Unable to handle kernel data access on write at 0xc00c000100400038
Faulting instruction address: 0xc000000001269d90
Oops: Kernel access of bad area, sig: 11 [#1]
LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
Modules linked in:
CPU: 7 PID: 1 Comm: swapper/0 Not tainted 6.3.0-rc5-150500.34-default+ #2 5c90a668b6bbd142599890245c2fb5de19d7d28a
Hardware name: IBM,9009-42G POWER9 (raw) 0x4e0202 0xf000005 of:IBM,FW950.40 (VL950_099) hv:phyp pSeries
NIP:  c000000001269d90 LR: c0000000004c57d4 CTR: 0000000000000000
REGS: c000000003632c30 TRAP: 0300   Not tainted  (6.3.0-rc5-150500.34-default+)
MSR:  8000000000009033 <SF,EE,ME,IR,DR,RI,LE>  CR: 24842228  XER: 00000000
CFAR: c0000000004c57d0 DAR: c00c000100400038 DSISR: 42000000 IRQMASK: 0
....
NIP [c000000001269d90] __init_single_page.isra.74+0x14/0x4c
LR [c0000000004c57d4] __init_zone_device_page+0x44/0xd0
Call Trace:
[c000000003632ed0] [c000000003632f60] 0xc000000003632f60 (unreliable)
[c000000003632f10] [c0000000004c5ca0] memmap_init_zone_device+0x170/0x250
[c000000003632fe0] [c0000000005575f8] memremap_pages+0x2c8/0x7f0
[c0000000036330c0] [c000000000557b5c] devm_memremap_pages+0x3c/0xa0
[c000000003633100] [c000000000d458a8] dev_dax_probe+0x108/0x3e0
[c0000000036331a0] [c000000000d41430] dax_bus_probe+0xb0/0x140
[c0000000036331d0] [c000000000cef27c] really_probe+0x19c/0x520
[c000000003633260] [c000000000cef6b4] __driver_probe_device+0xb4/0x230
[c0000000036332e0] [c000000000cef888] driver_probe_device+0x58/0x120
[c000000003633320] [c000000000cefa6c] __device_attach_driver+0x11c/0x1e0
[c0000000036333a0] [c000000000cebc58] bus_for_each_drv+0xa8/0x130
[c000000003633400] [c000000000ceefcc] __device_attach+0x15c/0x250
[c0000000036334a0] [c000000000ced458] bus_probe_device+0x108/0x110
[c0000000036334f0] [c000000000ce92dc] device_add+0x7fc/0xa10
[c0000000036335b0] [c000000000d447c8] devm_create_dev_dax+0x1d8/0x530
[c000000003633640] [c000000000d46b60] __dax_pmem_probe+0x200/0x270
[c0000000036337b0] [c000000000d46bf0] dax_pmem_probe+0x20/0x70
[c0000000036337d0] [c000000000d2279c] nvdimm_bus_probe+0xac/0x2b0
[c000000003633860] [c000000000cef27c] really_probe+0x19c/0x520
[c0000000036338f0] [c000000000cef6b4] __driver_probe_device+0xb4/0x230
[c000000003633970] [c000000000cef888] driver_probe_device+0x58/0x120
[c0000000036339b0] [c000000000cefd08] __driver_attach+0x1d8/0x240
[c000000003633a30] [c000000000cebb04] bus_for_each_dev+0xb4/0x130
[c000000003633a90] [c000000000cee564] driver_attach+0x34/0x50
[c000000003633ab0] [c000000000ced878] bus_add_driver+0x218/0x300
[c000000003633b40] [c000000000cf1144] driver_register+0xa4/0x1b0
[c000000003633bb0] [c000000000d21a0c] __nd_driver_register+0x5c/0x100
[c000000003633c10] [c00000000206a2e8] dax_pmem_init+0x34/0x48
[c000000003633c30] [c0000000000132d0] do_one_initcall+0x60/0x320
[c000000003633d00] [c0000000020051b0] kernel_init_freeable+0x360/0x400
[c000000003633de0] [c000000000013764] kernel_init+0x34/0x1d0
[c000000003633e50] [c00000000000de14] ret_from_kernel_thread+0x5c/0x64

Link: https://lkml.kernel.org/r/20230411142214.64464-1-aneesh.kumar@linux.ibm.com
Fixes: 4917f55b4e ("mm/sparse-vmemmap: improve memory savings for compound devmaps")
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reported-by: Tarun Sahu <tsahu@linux.ibm.com>
Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-04-18 16:30:09 -07:00

471 lines
12 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* Virtual Memory Map support
*
* (C) 2007 sgi. Christoph Lameter.
*
* Virtual memory maps allow VM primitives pfn_to_page, page_to_pfn,
* virt_to_page, page_address() to be implemented as a base offset
* calculation without memory access.
*
* However, virtual mappings need a page table and TLBs. Many Linux
* architectures already map their physical space using 1-1 mappings
* via TLBs. For those arches the virtual memory map is essentially
* for free if we use the same page size as the 1-1 mappings. In that
* case the overhead consists of a few additional pages that are
* allocated to create a view of memory for vmemmap.
*
* The architecture is expected to provide a vmemmap_populate() function
* to instantiate the mapping.
*/
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/memblock.h>
#include <linux/memremap.h>
#include <linux/highmem.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
#include <linux/sched.h>
#include <asm/dma.h>
#include <asm/pgalloc.h>
/*
* Allocate a block of memory to be used to back the virtual memory map
* or to back the page tables that are used to create the mapping.
* Uses the main allocators if they are available, else bootmem.
*/
static void * __ref __earlyonly_bootmem_alloc(int node,
unsigned long size,
unsigned long align,
unsigned long goal)
{
return memblock_alloc_try_nid_raw(size, align, goal,
MEMBLOCK_ALLOC_ACCESSIBLE, node);
}
void * __meminit vmemmap_alloc_block(unsigned long size, int node)
{
/* If the main allocator is up use that, fallback to bootmem. */
if (slab_is_available()) {
gfp_t gfp_mask = GFP_KERNEL|__GFP_RETRY_MAYFAIL|__GFP_NOWARN;
int order = get_order(size);
static bool warned;
struct page *page;
page = alloc_pages_node(node, gfp_mask, order);
if (page)
return page_address(page);
if (!warned) {
warn_alloc(gfp_mask & ~__GFP_NOWARN, NULL,
"vmemmap alloc failure: order:%u", order);
warned = true;
}
return NULL;
} else
return __earlyonly_bootmem_alloc(node, size, size,
__pa(MAX_DMA_ADDRESS));
}
static void * __meminit altmap_alloc_block_buf(unsigned long size,
struct vmem_altmap *altmap);
/* need to make sure size is all the same during early stage */
void * __meminit vmemmap_alloc_block_buf(unsigned long size, int node,
struct vmem_altmap *altmap)
{
void *ptr;
if (altmap)
return altmap_alloc_block_buf(size, altmap);
ptr = sparse_buffer_alloc(size);
if (!ptr)
ptr = vmemmap_alloc_block(size, node);
return ptr;
}
static unsigned long __meminit vmem_altmap_next_pfn(struct vmem_altmap *altmap)
{
return altmap->base_pfn + altmap->reserve + altmap->alloc
+ altmap->align;
}
static unsigned long __meminit vmem_altmap_nr_free(struct vmem_altmap *altmap)
{
unsigned long allocated = altmap->alloc + altmap->align;
if (altmap->free > allocated)
return altmap->free - allocated;
return 0;
}
static void * __meminit altmap_alloc_block_buf(unsigned long size,
struct vmem_altmap *altmap)
{
unsigned long pfn, nr_pfns, nr_align;
if (size & ~PAGE_MASK) {
pr_warn_once("%s: allocations must be multiple of PAGE_SIZE (%ld)\n",
__func__, size);
return NULL;
}
pfn = vmem_altmap_next_pfn(altmap);
nr_pfns = size >> PAGE_SHIFT;
nr_align = 1UL << find_first_bit(&nr_pfns, BITS_PER_LONG);
nr_align = ALIGN(pfn, nr_align) - pfn;
if (nr_pfns + nr_align > vmem_altmap_nr_free(altmap))
return NULL;
altmap->alloc += nr_pfns;
altmap->align += nr_align;
pfn += nr_align;
pr_debug("%s: pfn: %#lx alloc: %ld align: %ld nr: %#lx\n",
__func__, pfn, altmap->alloc, altmap->align, nr_pfns);
return __va(__pfn_to_phys(pfn));
}
void __meminit vmemmap_verify(pte_t *pte, int node,
unsigned long start, unsigned long end)
{
unsigned long pfn = pte_pfn(*pte);
int actual_node = early_pfn_to_nid(pfn);
if (node_distance(actual_node, node) > LOCAL_DISTANCE)
pr_warn_once("[%lx-%lx] potential offnode page_structs\n",
start, end - 1);
}
pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
struct vmem_altmap *altmap,
struct page *reuse)
{
pte_t *pte = pte_offset_kernel(pmd, addr);
if (pte_none(*pte)) {
pte_t entry;
void *p;
if (!reuse) {
p = vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap);
if (!p)
return NULL;
} else {
/*
* When a PTE/PMD entry is freed from the init_mm
* there's a free_pages() call to this page allocated
* above. Thus this get_page() is paired with the
* put_page_testzero() on the freeing path.
* This can only called by certain ZONE_DEVICE path,
* and through vmemmap_populate_compound_pages() when
* slab is available.
*/
get_page(reuse);
p = page_to_virt(reuse);
}
entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
set_pte_at(&init_mm, addr, pte, entry);
}
return pte;
}
static void * __meminit vmemmap_alloc_block_zero(unsigned long size, int node)
{
void *p = vmemmap_alloc_block(size, node);
if (!p)
return NULL;
memset(p, 0, size);
return p;
}
pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node)
{
pmd_t *pmd = pmd_offset(pud, addr);
if (pmd_none(*pmd)) {
void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
if (!p)
return NULL;
pmd_populate_kernel(&init_mm, pmd, p);
}
return pmd;
}
void __weak __meminit pmd_init(void *addr)
{
}
pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node)
{
pud_t *pud = pud_offset(p4d, addr);
if (pud_none(*pud)) {
void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
if (!p)
return NULL;
pmd_init(p);
pud_populate(&init_mm, pud, p);
}
return pud;
}
void __weak __meminit pud_init(void *addr)
{
}
p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node)
{
p4d_t *p4d = p4d_offset(pgd, addr);
if (p4d_none(*p4d)) {
void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
if (!p)
return NULL;
pud_init(p);
p4d_populate(&init_mm, p4d, p);
}
return p4d;
}
pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
{
pgd_t *pgd = pgd_offset_k(addr);
if (pgd_none(*pgd)) {
void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
if (!p)
return NULL;
pgd_populate(&init_mm, pgd, p);
}
return pgd;
}
static pte_t * __meminit vmemmap_populate_address(unsigned long addr, int node,
struct vmem_altmap *altmap,
struct page *reuse)
{
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
pgd = vmemmap_pgd_populate(addr, node);
if (!pgd)
return NULL;
p4d = vmemmap_p4d_populate(pgd, addr, node);
if (!p4d)
return NULL;
pud = vmemmap_pud_populate(p4d, addr, node);
if (!pud)
return NULL;
pmd = vmemmap_pmd_populate(pud, addr, node);
if (!pmd)
return NULL;
pte = vmemmap_pte_populate(pmd, addr, node, altmap, reuse);
if (!pte)
return NULL;
vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
return pte;
}
static int __meminit vmemmap_populate_range(unsigned long start,
unsigned long end, int node,
struct vmem_altmap *altmap,
struct page *reuse)
{
unsigned long addr = start;
pte_t *pte;
for (; addr < end; addr += PAGE_SIZE) {
pte = vmemmap_populate_address(addr, node, altmap, reuse);
if (!pte)
return -ENOMEM;
}
return 0;
}
int __meminit vmemmap_populate_basepages(unsigned long start, unsigned long end,
int node, struct vmem_altmap *altmap)
{
return vmemmap_populate_range(start, end, node, altmap, NULL);
}
void __weak __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node,
unsigned long addr, unsigned long next)
{
}
int __weak __meminit vmemmap_check_pmd(pmd_t *pmd, int node,
unsigned long addr, unsigned long next)
{
return 0;
}
int __meminit vmemmap_populate_hugepages(unsigned long start, unsigned long end,
int node, struct vmem_altmap *altmap)
{
unsigned long addr;
unsigned long next;
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
for (addr = start; addr < end; addr = next) {
next = pmd_addr_end(addr, end);
pgd = vmemmap_pgd_populate(addr, node);
if (!pgd)
return -ENOMEM;
p4d = vmemmap_p4d_populate(pgd, addr, node);
if (!p4d)
return -ENOMEM;
pud = vmemmap_pud_populate(p4d, addr, node);
if (!pud)
return -ENOMEM;
pmd = pmd_offset(pud, addr);
if (pmd_none(READ_ONCE(*pmd))) {
void *p;
p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap);
if (p) {
vmemmap_set_pmd(pmd, p, node, addr, next);
continue;
} else if (altmap) {
/*
* No fallback: In any case we care about, the
* altmap should be reasonably sized and aligned
* such that vmemmap_alloc_block_buf() will always
* succeed. For consistency with the PTE case,
* return an error here as failure could indicate
* a configuration issue with the size of the altmap.
*/
return -ENOMEM;
}
} else if (vmemmap_check_pmd(pmd, node, addr, next))
continue;
if (vmemmap_populate_basepages(addr, next, node, altmap))
return -ENOMEM;
}
return 0;
}
/*
* For compound pages bigger than section size (e.g. x86 1G compound
* pages with 2M subsection size) fill the rest of sections as tail
* pages.
*
* Note that memremap_pages() resets @nr_range value and will increment
* it after each range successful onlining. Thus the value or @nr_range
* at section memmap populate corresponds to the in-progress range
* being onlined here.
*/
static bool __meminit reuse_compound_section(unsigned long start_pfn,
struct dev_pagemap *pgmap)
{
unsigned long nr_pages = pgmap_vmemmap_nr(pgmap);
unsigned long offset = start_pfn -
PHYS_PFN(pgmap->ranges[pgmap->nr_range].start);
return !IS_ALIGNED(offset, nr_pages) && nr_pages > PAGES_PER_SUBSECTION;
}
static pte_t * __meminit compound_section_tail_page(unsigned long addr)
{
pte_t *pte;
addr -= PAGE_SIZE;
/*
* Assuming sections are populated sequentially, the previous section's
* page data can be reused.
*/
pte = pte_offset_kernel(pmd_off_k(addr), addr);
if (!pte)
return NULL;
return pte;
}
static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
unsigned long start,
unsigned long end, int node,
struct dev_pagemap *pgmap)
{
unsigned long size, addr;
pte_t *pte;
int rc;
if (reuse_compound_section(start_pfn, pgmap)) {
pte = compound_section_tail_page(start);
if (!pte)
return -ENOMEM;
/*
* Reuse the page that was populated in the prior iteration
* with just tail struct pages.
*/
return vmemmap_populate_range(start, end, node, NULL,
pte_page(*pte));
}
size = min(end - start, pgmap_vmemmap_nr(pgmap) * sizeof(struct page));
for (addr = start; addr < end; addr += size) {
unsigned long next, last = addr + size;
/* Populate the head page vmemmap page */
pte = vmemmap_populate_address(addr, node, NULL, NULL);
if (!pte)
return -ENOMEM;
/* Populate the tail pages vmemmap page */
next = addr + PAGE_SIZE;
pte = vmemmap_populate_address(next, node, NULL, NULL);
if (!pte)
return -ENOMEM;
/*
* Reuse the previous page for the rest of tail pages
* See layout diagram in Documentation/mm/vmemmap_dedup.rst
*/
next += PAGE_SIZE;
rc = vmemmap_populate_range(next, last, node, NULL,
pte_page(*pte));
if (rc)
return -ENOMEM;
}
return 0;
}
struct page * __meminit __populate_section_memmap(unsigned long pfn,
unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
struct dev_pagemap *pgmap)
{
unsigned long start = (unsigned long) pfn_to_page(pfn);
unsigned long end = start + nr_pages * sizeof(struct page);
int r;
if (WARN_ON_ONCE(!IS_ALIGNED(pfn, PAGES_PER_SUBSECTION) ||
!IS_ALIGNED(nr_pages, PAGES_PER_SUBSECTION)))
return NULL;
if (vmemmap_can_optimize(altmap, pgmap))
r = vmemmap_populate_compound_pages(pfn, start, end, nid, pgmap);
else
r = vmemmap_populate(start, end, nid, altmap);
if (r < 0)
return NULL;
return pfn_to_page(pfn);
}