The patch titled
Subject: kernel/memremap, kasan: make ZONE_DEVICE with work with KASAN
has been added to the -mm tree. Its filename is
kernel-memremap-kasan-make-zone_device-with-work-with-kasan.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/kernel-memremap-kasan-make-zone_device-with-work-with-kasan.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/kernel-memremap-kasan-make-zone_device-with-work-with-kasan.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Andrey Ryabinin <aryabinin@xxxxxxxxxxxxx>
Subject: kernel/memremap, kasan: make ZONE_DEVICE with work with KASAN
KASAN learns about hotadded memory via the memory hotplug notifier.
devm_memremap_pages() intentionally skips calling memory hotplug
notifiers. So KASAN doesn't know anything about new memory added by
devm_memremap_pages(). This causes a crash when KASAN tries to access
non-existent shadow memory:
BUG: unable to handle kernel paging request at ffffed0078000000
RIP: 0010:check_memory_region+0x82/0x1e0
Call Trace:
memcpy+0x1f/0x50
pmem_do_bvec+0x163/0x720
pmem_make_request+0x305/0xac0
generic_make_request+0x54f/0xcf0
submit_bio+0x9c/0x370
submit_bh_wbc+0x4c7/0x700
block_read_full_page+0x5ef/0x870
do_read_cache_page+0x2b8/0xb30
read_dev_sector+0xbd/0x3f0
read_lba.isra.0+0x277/0x670
efi_partition+0x41a/0x18f0
check_partition+0x30d/0x5e9
rescan_partitions+0x18c/0x840
__blkdev_get+0x859/0x1060
blkdev_get+0x23f/0x810
__device_add_disk+0x9c8/0xde0
pmem_attach_disk+0x9a8/0xf50
nvdimm_bus_probe+0xf3/0x3c0
driver_probe_device+0x493/0xbd0
bus_for_each_drv+0x118/0x1b0
__device_attach+0x1cd/0x2b0
bus_probe_device+0x1ac/0x260
device_add+0x90d/0x1380
nd_async_device_register+0xe/0x50
async_run_entry_fn+0xc3/0x5d0
process_one_work+0xa0a/0x1810
worker_thread+0x87/0xe80
kthread+0x2d7/0x390
ret_from_fork+0x3a/0x50
Add kasan_add_zero_shadow()/kasan_remove_zero_shadow() - post mm_init()
interface to map/unmap kasan_zero_page at requested virtual addresses.
And use it to add/remove the shadow memory for hotplugged/unplugged device
memory.
Link: http://lkml.kernel.org/r/20180629164932.740-1-aryabinin@xxxxxxxxxxxxx
Signed-off-by: Andrey Ryabinin <aryabinin@xxxxxxxxxxxxx>
Reported-by: Dave Chinner <david@xxxxxxxxxxxxx>
Reviewed-by: Dan Williams <dan.j.williams@xxxxxxxxx>
Tested-by: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Dmitry Vyukov <dvyukov@xxxxxxxxxx>
Cc: Alexander Potapenko <glider@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
diff -puN include/linux/kasan.h~kernel-memremap-kasan-make-zone_device-with-work-with-kasan include/linux/kasan.h
--- a/include/linux/kasan.h~kernel-memremap-kasan-make-zone_device-with-work-with-kasan
+++ a/include/linux/kasan.h
@@ -20,7 +20,7 @@ extern pmd_t kasan_zero_pmd[PTRS_PER_PMD
extern pud_t kasan_zero_pud[PTRS_PER_PUD];
extern p4d_t kasan_zero_p4d[MAX_PTRS_PER_P4D];
-void kasan_populate_zero_shadow(const void *shadow_start,
+int kasan_populate_zero_shadow(const void *shadow_start,
const void *shadow_end);
static inline void *kasan_mem_to_shadow(const void *addr)
@@ -71,6 +71,9 @@ struct kasan_cache {
int kasan_module_alloc(void *addr, size_t size);
void kasan_free_shadow(const struct vm_struct *vm);
+int kasan_add_zero_shadow(void *start, unsigned long size);
+void kasan_remove_zero_shadow(void *start, unsigned long size);
+
size_t ksize(const void *);
static inline void kasan_unpoison_slab(const void *ptr) { ksize(ptr); }
size_t kasan_metadata_size(struct kmem_cache *cache);
@@ -124,6 +127,14 @@ static inline bool kasan_slab_free(struc
static inline int kasan_module_alloc(void *addr, size_t size) { return 0; }
static inline void kasan_free_shadow(const struct vm_struct *vm) {}
+static inline int kasan_add_zero_shadow(void *start, unsigned long size)
+{
+ return 0;
+}
+static inline void kasan_remove_zero_shadow(void *start,
+ unsigned long size)
+{}
+
static inline void kasan_unpoison_slab(const void *ptr) { }
static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; }
diff -puN kernel/memremap.c~kernel-memremap-kasan-make-zone_device-with-work-with-kasan kernel/memremap.c
--- a/kernel/memremap.c~kernel-memremap-kasan-make-zone_device-with-work-with-kasan
+++ a/kernel/memremap.c
@@ -5,6 +5,7 @@
#include <linux/types.h>
#include <linux/pfn_t.h>
#include <linux/io.h>
+#include <linux/kasan.h>
#include <linux/mm.h>
#include <linux/memory_hotplug.h>
#include <linux/swap.h>
@@ -137,6 +138,7 @@ static void devm_memremap_pages_release(
mem_hotplug_begin();
arch_remove_memory(align_start, align_size, pgmap->altmap_valid ?
&pgmap->altmap : NULL);
+ kasan_remove_zero_shadow(__va(align_start), align_size);
mem_hotplug_done();
untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
@@ -223,6 +225,12 @@ void *devm_memremap_pages(struct device
goto err_pfn_remap;
mem_hotplug_begin();
+ error = kasan_add_zero_shadow(__va(align_start), align_size);
+ if (error) {
+ mem_hotplug_done();
+ goto err_kasan;
+ }
+
error = arch_add_memory(nid, align_start, align_size, altmap, false);
if (!error)
move_pfn_range_to_zone(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
@@ -251,6 +259,8 @@ void *devm_memremap_pages(struct device
return __va(res->start);
err_add_memory:
+ kasan_remove_zero_shadow(__va(align_start), align_size);
+ err_kasan:
untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
err_pfn_remap:
err_radix:
diff -puN mm/kasan/kasan_init.c~kernel-memremap-kasan-make-zone_device-with-work-with-kasan mm/kasan/kasan_init.c
--- a/mm/kasan/kasan_init.c~kernel-memremap-kasan-make-zone_device-with-work-with-kasan
+++ a/mm/kasan/kasan_init.c
@@ -17,10 +17,13 @@
#include <linux/memblock.h>
#include <linux/mm.h>
#include <linux/pfn.h>
+#include <linux/slab.h>
#include <asm/page.h>
#include <asm/pgalloc.h>
+#include "kasan.h"
+
/*
* This page serves two purposes:
* - It used as early shadow memory. The entire shadow region populated
@@ -32,22 +35,59 @@ unsigned char kasan_zero_page[PAGE_SIZE]
#if CONFIG_PGTABLE_LEVELS > 4
p4d_t kasan_zero_p4d[MAX_PTRS_PER_P4D] __page_aligned_bss;
+static inline bool kasan_p4d_table(pgd_t pgd)
+{
+ return pgd_page(pgd) == virt_to_page(lm_alias(kasan_zero_p4d));
+}
+#else
+static inline bool kasan_p4d_table(pgd_t pgd)
+{
+ return 0;
+}
#endif
#if CONFIG_PGTABLE_LEVELS > 3
pud_t kasan_zero_pud[PTRS_PER_PUD] __page_aligned_bss;
+static inline bool kasan_pud_table(p4d_t p4d)
+{
+ return p4d_page(p4d) == virt_to_page(lm_alias(kasan_zero_pud));
+}
+#else
+static inline bool kasan_pud_table(p4d_t p4d)
+{
+ return 0;
+}
#endif
#if CONFIG_PGTABLE_LEVELS > 2
pmd_t kasan_zero_pmd[PTRS_PER_PMD] __page_aligned_bss;
+static inline bool kasan_pmd_table(pud_t pud)
+{
+ return pud_page(pud) == virt_to_page(lm_alias(kasan_zero_pmd));
+}
+#else
+static inline bool kasan_pmd_table(pud_t pud)
+{
+ return 0;
+}
#endif
pte_t kasan_zero_pte[PTRS_PER_PTE] __page_aligned_bss;
+static inline bool kasan_pte_table(pmd_t pmd)
+{
+ return pmd_page(pmd) == virt_to_page(lm_alias(kasan_zero_pte));
+}
+
+static inline bool kasan_zero_page_entry(pte_t pte)
+{
+ return pte_page(pte) == virt_to_page(lm_alias(kasan_zero_page));
+}
+
static __init void *early_alloc(size_t size, int node)
{
return memblock_virt_alloc_try_nid(size, size, __pa(MAX_DMA_ADDRESS),
BOOTMEM_ALLOC_ACCESSIBLE, node);
}
-static void __init zero_pte_populate(pmd_t *pmd, unsigned long addr,
+static void __ref zero_pte_populate(pmd_t *pmd, unsigned long addr,
unsigned long end)
{
pte_t *pte = pte_offset_kernel(pmd, addr);
@@ -63,7 +103,7 @@ static void __init zero_pte_populate(pmd
}
}
-static void __init zero_pmd_populate(pud_t *pud, unsigned long addr,
+static int __ref zero_pmd_populate(pud_t *pud, unsigned long addr,
unsigned long end)
{
pmd_t *pmd = pmd_offset(pud, addr);
@@ -78,14 +118,24 @@ static void __init zero_pmd_populate(pud
}
if (pmd_none(*pmd)) {
- pmd_populate_kernel(&init_mm, pmd,
- early_alloc(PAGE_SIZE, NUMA_NO_NODE));
+ pte_t *p;
+
+ if (slab_is_available())
+ p = pte_alloc_one_kernel(&init_mm, addr);
+ else
+ p = early_alloc(PAGE_SIZE, NUMA_NO_NODE);
+ if (!p)
+ return -ENOMEM;
+
+ pmd_populate_kernel(&init_mm, pmd, p);
}
zero_pte_populate(pmd, addr, next);
} while (pmd++, addr = next, addr != end);
+
+ return 0;
}
-static void __init zero_pud_populate(p4d_t *p4d, unsigned long addr,
+static int __ref zero_pud_populate(p4d_t *p4d, unsigned long addr,
unsigned long end)
{
pud_t *pud = pud_offset(p4d, addr);
@@ -103,14 +153,24 @@ static void __init zero_pud_populate(p4d
}
if (pud_none(*pud)) {
- pud_populate(&init_mm, pud,
- early_alloc(PAGE_SIZE, NUMA_NO_NODE));
+ pmd_t *p;
+
+ if (slab_is_available()) {
+ p = pmd_alloc(&init_mm, pud, addr);
+ if (!p)
+ return -ENOMEM;
+ } else {
+ pud_populate(&init_mm, pud,
+ early_alloc(PAGE_SIZE, NUMA_NO_NODE));
+ }
}
zero_pmd_populate(pud, addr, next);
} while (pud++, addr = next, addr != end);
+
+ return 0;
}
-static void __init zero_p4d_populate(pgd_t *pgd, unsigned long addr,
+static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr,
unsigned long end)
{
p4d_t *p4d = p4d_offset(pgd, addr);
@@ -132,11 +192,21 @@ static void __init zero_p4d_populate(pgd
}
if (p4d_none(*p4d)) {
- p4d_populate(&init_mm, p4d,
- early_alloc(PAGE_SIZE, NUMA_NO_NODE));
+ pud_t *p;
+
+ if (slab_is_available()) {
+ p = pud_alloc(&init_mm, p4d, addr);
+ if (!p)
+ return -ENOMEM;
+ } else {
+ p4d_populate(&init_mm, p4d,
+ early_alloc(PAGE_SIZE, NUMA_NO_NODE));
+ }
}
zero_pud_populate(p4d, addr, next);
} while (p4d++, addr = next, addr != end);
+
+ return 0;
}
/**
@@ -145,7 +215,7 @@ static void __init zero_p4d_populate(pgd
* @shadow_start - start of the memory range to populate
* @shadow_end - end of the memory range to populate
*/
-void __init kasan_populate_zero_shadow(const void *shadow_start,
+int __ref kasan_populate_zero_shadow(const void *shadow_start,
const void *shadow_end)
{
unsigned long addr = (unsigned long)shadow_start;
@@ -191,9 +261,229 @@ void __init kasan_populate_zero_shadow(c
}
if (pgd_none(*pgd)) {
- pgd_populate(&init_mm, pgd,
- early_alloc(PAGE_SIZE, NUMA_NO_NODE));
+ p4d_t *p;
+
+ if (slab_is_available()) {
+ p = p4d_alloc(&init_mm, pgd, addr);
+ if (!p)
+ return -ENOMEM;
+ } else {
+ pgd_populate(&init_mm, pgd,
+ early_alloc(PAGE_SIZE, NUMA_NO_NODE));
+ }
}
zero_p4d_populate(pgd, addr, next);
} while (pgd++, addr = next, addr != end);
+
+ return 0;
+}
+
+static void kasan_free_pte(pte_t *pte_start, pmd_t *pmd)
+{
+ pte_t *pte;
+ int i;
+
+ for (i = 0; i < PTRS_PER_PTE; i++) {
+ pte = pte_start + i;
+ if (!pte_none(*pte))
+ return;
+ }
+
+ pte_free_kernel(&init_mm, (pte_t *)page_to_virt(pmd_page(*pmd)));
+ pmd_clear(pmd);
+}
+
+static void kasan_free_pmd(pmd_t *pmd_start, pud_t *pud)
+{
+ pmd_t *pmd;
+ int i;
+
+ for (i = 0; i < PTRS_PER_PMD; i++) {
+ pmd = pmd_start + i;
+ if (!pmd_none(*pmd))
+ return;
+ }
+
+ pmd_free(&init_mm, (pmd_t *)page_to_virt(pud_page(*pud)));
+ pud_clear(pud);
+}
+
+static void kasan_free_pud(pud_t *pud_start, p4d_t *p4d)
+{
+ pud_t *pud;
+ int i;
+
+ for (i = 0; i < PTRS_PER_PUD; i++) {
+ pud = pud_start + i;
+ if (!pud_none(*pud))
+ return;
+ }
+
+ pud_free(&init_mm, (pud_t *)page_to_virt(p4d_page(*p4d)));
+ p4d_clear(p4d);
+}
+
+static void kasan_free_p4d(p4d_t *p4d_start, pgd_t *pgd)
+{
+ p4d_t *p4d;
+ int i;
+
+ for (i = 0; i < PTRS_PER_P4D; i++) {
+ p4d = p4d_start + i;
+ if (!p4d_none(*p4d))
+ return;
+ }
+
+ p4d_free(&init_mm, (p4d_t *)page_to_virt(pgd_page(*pgd)));
+ pgd_clear(pgd);
+}
+
+static void kasan_remove_pte_table(pte_t *pte, unsigned long addr,
+ unsigned long end)
+{
+ unsigned long next;
+
+ for (; addr < end; addr = next, pte++) {
+ next = (addr + PAGE_SIZE) & PAGE_MASK;
+ if (next > end)
+ next = end;
+
+ if (!pte_present(*pte))
+ continue;
+
+ if (WARN_ON(!kasan_zero_page_entry(*pte)))
+ continue;
+ pte_clear(&init_mm, addr, pte);
+ }
+}
+
+static void kasan_remove_pmd_table(pmd_t *pmd, unsigned long addr,
+ unsigned long end)
+{
+ unsigned long next;
+
+ for (; addr < end; addr = next, pmd++) {
+ pte_t *pte;
+
+ next = pmd_addr_end(addr, end);
+
+ if (!pmd_present(*pmd))
+ continue;
+
+ if (kasan_pte_table(*pmd)) {
+ if (IS_ALIGNED(addr, PMD_SIZE) &&
+ IS_ALIGNED(next, PMD_SIZE))
+ pmd_clear(pmd);
+ continue;
+ }
+ pte = pte_offset_kernel(pmd, addr);
+ kasan_remove_pte_table(pte, addr, next);
+ kasan_free_pte(pte_offset_kernel(pmd, 0), pmd);
+ }
+}
+
+static void kasan_remove_pud_table(pud_t *pud, unsigned long addr,
+ unsigned long end)
+{
+ unsigned long next;
+
+ for (; addr < end; addr = next, pud++) {
+ pmd_t *pmd, *pmd_base;
+
+ next = pud_addr_end(addr, end);
+
+ if (!pud_present(*pud))
+ continue;
+
+ if (kasan_pmd_table(*pud)) {
+ if (IS_ALIGNED(addr, PUD_SIZE) &&
+ IS_ALIGNED(next, PUD_SIZE))
+ pud_clear(pud);
+ continue;
+ }
+ pmd = pmd_offset(pud, addr);
+ pmd_base = pmd_offset(pud, 0);
+ kasan_remove_pmd_table(pmd, addr, next);
+ kasan_free_pmd(pmd_base, pud);
+ }
+}
+
+static void kasan_remove_p4d_table(p4d_t *p4d, unsigned long addr,
+ unsigned long end)
+{
+ unsigned long next;
+
+ for (; addr < end; addr = next, p4d++) {
+ pud_t *pud;
+
+ next = p4d_addr_end(addr, end);
+
+ if (!p4d_present(*p4d))
+ continue;
+
+ if (kasan_pud_table(*p4d)) {
+ if (IS_ALIGNED(addr, P4D_SIZE) &&
+ IS_ALIGNED(next, P4D_SIZE))
+ p4d_clear(p4d);
+ continue;
+ }
+ pud = pud_offset(p4d, addr);
+ kasan_remove_pud_table(pud, addr, next);
+ kasan_free_pud(pud_offset(p4d, 0), p4d);
+ }
+}
+
+void kasan_remove_zero_shadow(void *start, unsigned long size)
+{
+ unsigned long addr, end, next;
+ pgd_t *pgd;
+
+ addr = (unsigned long)kasan_mem_to_shadow(start);
+ end = addr + (size >> KASAN_SHADOW_SCALE_SHIFT);
+
+ if (WARN_ON((unsigned long)start %
+ (KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE)) ||
+ WARN_ON(size % (KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE)))
+ return;
+
+ for (; addr < end; addr = next) {
+ p4d_t *p4d;
+
+ next = pgd_addr_end(addr, end);
+
+ pgd = pgd_offset_k(addr);
+ if (!pgd_present(*pgd))
+ continue;
+
+ if (kasan_p4d_table(*pgd)) {
+ if (IS_ALIGNED(addr, PGDIR_SIZE) &&
+ IS_ALIGNED(next, PGDIR_SIZE))
+ pgd_clear(pgd);
+ continue;
+ }
+
+ p4d = p4d_offset(pgd, addr);
+ kasan_remove_p4d_table(p4d, addr, next);
+ kasan_free_p4d(p4d_offset(pgd, 0), pgd);
+ }
+}
+
+int kasan_add_zero_shadow(void *start, unsigned long size)
+{
+ int ret;
+ void *shadow_start, *shadow_end;
+
+ shadow_start = kasan_mem_to_shadow(start);
+ shadow_end = shadow_start + (size >> KASAN_SHADOW_SCALE_SHIFT);
+
+ if (WARN_ON((unsigned long)start %
+ (KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE)) ||
+ WARN_ON(size % (KASAN_SHADOW_SCALE_SIZE * PAGE_SIZE)))
+ return -EINVAL;
+
+ ret = kasan_populate_zero_shadow(shadow_start, shadow_end);
+ if (ret)
+ kasan_remove_zero_shadow(shadow_start,
+ size >> KASAN_SHADOW_SCALE_SHIFT);
+ return ret;
}
_
Patches currently in -mm which might be from aryabinin@xxxxxxxxxxxxx are
mm-fadvise-fix-signed-overflow-ubsan-complaint.patch
kernel-memremap-kasan-make-zone_device-with-work-with-kasan.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
