forked from Minki/linux
e31cf2f4ca
Patch series "mm: consolidate definitions of page table accessors", v2. The low level page table accessors (pXY_index(), pXY_offset()) are duplicated across all architectures and sometimes more than once. For instance, we have 31 definition of pgd_offset() for 25 supported architectures. Most of these definitions are actually identical and typically it boils down to, e.g. static inline unsigned long pmd_index(unsigned long address) { return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1); } static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) { return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address); } These definitions can be shared among 90% of the arches provided XYZ_SHIFT, PTRS_PER_XYZ and xyz_page_vaddr() are defined. For architectures that really need a custom version there is always possibility to override the generic version with the usual ifdefs magic. These patches introduce include/linux/pgtable.h that replaces include/asm-generic/pgtable.h and add the definitions of the page table accessors to the new header. This patch (of 12): The linux/mm.h header includes <asm/pgtable.h> to allow inlining of the functions involving page table manipulations, e.g. pte_alloc() and pmd_alloc(). So, there is no point to explicitly include <asm/pgtable.h> in the files that include <linux/mm.h>. The include statements in such cases are remove with a simple loop: for f in $(git grep -l "include <linux/mm.h>") ; do sed -i -e '/include <asm\/pgtable.h>/ d' $f done Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Zankel <chris@zankel.net> Cc: "David S. Miller" <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Ungerer <gerg@linux-m68k.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: Mark Salter <msalter@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Mike Rapoport <rppt@kernel.org> Cc: Nick Hu <nickhu@andestech.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200514170327.31389-1-rppt@kernel.org Link: http://lkml.kernel.org/r/20200514170327.31389-2-rppt@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
436 lines
11 KiB
C
436 lines
11 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#define DISABLE_BRANCH_PROFILING
|
|
#define pr_fmt(fmt) "kasan: " fmt
|
|
|
|
/* cpu_feature_enabled() cannot be used this early */
|
|
#define USE_EARLY_PGTABLE_L5
|
|
|
|
#include <linux/memblock.h>
|
|
#include <linux/kasan.h>
|
|
#include <linux/kdebug.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/sched/task.h>
|
|
#include <linux/vmalloc.h>
|
|
|
|
#include <asm/e820/types.h>
|
|
#include <asm/pgalloc.h>
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/sections.h>
|
|
#include <asm/cpu_entry_area.h>
|
|
|
|
extern struct range pfn_mapped[E820_MAX_ENTRIES];
|
|
|
|
static p4d_t tmp_p4d_table[MAX_PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE);
|
|
|
|
static __init void *early_alloc(size_t size, int nid, bool should_panic)
|
|
{
|
|
void *ptr = memblock_alloc_try_nid(size, size,
|
|
__pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid);
|
|
|
|
if (!ptr && should_panic)
|
|
panic("%pS: Failed to allocate page, nid=%d from=%lx\n",
|
|
(void *)_RET_IP_, nid, __pa(MAX_DMA_ADDRESS));
|
|
|
|
return ptr;
|
|
}
|
|
|
|
static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr,
|
|
unsigned long end, int nid)
|
|
{
|
|
pte_t *pte;
|
|
|
|
if (pmd_none(*pmd)) {
|
|
void *p;
|
|
|
|
if (boot_cpu_has(X86_FEATURE_PSE) &&
|
|
((end - addr) == PMD_SIZE) &&
|
|
IS_ALIGNED(addr, PMD_SIZE)) {
|
|
p = early_alloc(PMD_SIZE, nid, false);
|
|
if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL))
|
|
return;
|
|
else if (p)
|
|
memblock_free(__pa(p), PMD_SIZE);
|
|
}
|
|
|
|
p = early_alloc(PAGE_SIZE, nid, true);
|
|
pmd_populate_kernel(&init_mm, pmd, p);
|
|
}
|
|
|
|
pte = pte_offset_kernel(pmd, addr);
|
|
do {
|
|
pte_t entry;
|
|
void *p;
|
|
|
|
if (!pte_none(*pte))
|
|
continue;
|
|
|
|
p = early_alloc(PAGE_SIZE, nid, true);
|
|
entry = pfn_pte(PFN_DOWN(__pa(p)), PAGE_KERNEL);
|
|
set_pte_at(&init_mm, addr, pte, entry);
|
|
} while (pte++, addr += PAGE_SIZE, addr != end);
|
|
}
|
|
|
|
static void __init kasan_populate_pud(pud_t *pud, unsigned long addr,
|
|
unsigned long end, int nid)
|
|
{
|
|
pmd_t *pmd;
|
|
unsigned long next;
|
|
|
|
if (pud_none(*pud)) {
|
|
void *p;
|
|
|
|
if (boot_cpu_has(X86_FEATURE_GBPAGES) &&
|
|
((end - addr) == PUD_SIZE) &&
|
|
IS_ALIGNED(addr, PUD_SIZE)) {
|
|
p = early_alloc(PUD_SIZE, nid, false);
|
|
if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL))
|
|
return;
|
|
else if (p)
|
|
memblock_free(__pa(p), PUD_SIZE);
|
|
}
|
|
|
|
p = early_alloc(PAGE_SIZE, nid, true);
|
|
pud_populate(&init_mm, pud, p);
|
|
}
|
|
|
|
pmd = pmd_offset(pud, addr);
|
|
do {
|
|
next = pmd_addr_end(addr, end);
|
|
if (!pmd_large(*pmd))
|
|
kasan_populate_pmd(pmd, addr, next, nid);
|
|
} while (pmd++, addr = next, addr != end);
|
|
}
|
|
|
|
static void __init kasan_populate_p4d(p4d_t *p4d, unsigned long addr,
|
|
unsigned long end, int nid)
|
|
{
|
|
pud_t *pud;
|
|
unsigned long next;
|
|
|
|
if (p4d_none(*p4d)) {
|
|
void *p = early_alloc(PAGE_SIZE, nid, true);
|
|
|
|
p4d_populate(&init_mm, p4d, p);
|
|
}
|
|
|
|
pud = pud_offset(p4d, addr);
|
|
do {
|
|
next = pud_addr_end(addr, end);
|
|
if (!pud_large(*pud))
|
|
kasan_populate_pud(pud, addr, next, nid);
|
|
} while (pud++, addr = next, addr != end);
|
|
}
|
|
|
|
static void __init kasan_populate_pgd(pgd_t *pgd, unsigned long addr,
|
|
unsigned long end, int nid)
|
|
{
|
|
void *p;
|
|
p4d_t *p4d;
|
|
unsigned long next;
|
|
|
|
if (pgd_none(*pgd)) {
|
|
p = early_alloc(PAGE_SIZE, nid, true);
|
|
pgd_populate(&init_mm, pgd, p);
|
|
}
|
|
|
|
p4d = p4d_offset(pgd, addr);
|
|
do {
|
|
next = p4d_addr_end(addr, end);
|
|
kasan_populate_p4d(p4d, addr, next, nid);
|
|
} while (p4d++, addr = next, addr != end);
|
|
}
|
|
|
|
static void __init kasan_populate_shadow(unsigned long addr, unsigned long end,
|
|
int nid)
|
|
{
|
|
pgd_t *pgd;
|
|
unsigned long next;
|
|
|
|
addr = addr & PAGE_MASK;
|
|
end = round_up(end, PAGE_SIZE);
|
|
pgd = pgd_offset_k(addr);
|
|
do {
|
|
next = pgd_addr_end(addr, end);
|
|
kasan_populate_pgd(pgd, addr, next, nid);
|
|
} while (pgd++, addr = next, addr != end);
|
|
}
|
|
|
|
static void __init map_range(struct range *range)
|
|
{
|
|
unsigned long start;
|
|
unsigned long end;
|
|
|
|
start = (unsigned long)kasan_mem_to_shadow(pfn_to_kaddr(range->start));
|
|
end = (unsigned long)kasan_mem_to_shadow(pfn_to_kaddr(range->end));
|
|
|
|
kasan_populate_shadow(start, end, early_pfn_to_nid(range->start));
|
|
}
|
|
|
|
static void __init clear_pgds(unsigned long start,
|
|
unsigned long end)
|
|
{
|
|
pgd_t *pgd;
|
|
/* See comment in kasan_init() */
|
|
unsigned long pgd_end = end & PGDIR_MASK;
|
|
|
|
for (; start < pgd_end; start += PGDIR_SIZE) {
|
|
pgd = pgd_offset_k(start);
|
|
/*
|
|
* With folded p4d, pgd_clear() is nop, use p4d_clear()
|
|
* instead.
|
|
*/
|
|
if (pgtable_l5_enabled())
|
|
pgd_clear(pgd);
|
|
else
|
|
p4d_clear(p4d_offset(pgd, start));
|
|
}
|
|
|
|
pgd = pgd_offset_k(start);
|
|
for (; start < end; start += P4D_SIZE)
|
|
p4d_clear(p4d_offset(pgd, start));
|
|
}
|
|
|
|
static inline p4d_t *early_p4d_offset(pgd_t *pgd, unsigned long addr)
|
|
{
|
|
unsigned long p4d;
|
|
|
|
if (!pgtable_l5_enabled())
|
|
return (p4d_t *)pgd;
|
|
|
|
p4d = pgd_val(*pgd) & PTE_PFN_MASK;
|
|
p4d += __START_KERNEL_map - phys_base;
|
|
return (p4d_t *)p4d + p4d_index(addr);
|
|
}
|
|
|
|
static void __init kasan_early_p4d_populate(pgd_t *pgd,
|
|
unsigned long addr,
|
|
unsigned long end)
|
|
{
|
|
pgd_t pgd_entry;
|
|
p4d_t *p4d, p4d_entry;
|
|
unsigned long next;
|
|
|
|
if (pgd_none(*pgd)) {
|
|
pgd_entry = __pgd(_KERNPG_TABLE |
|
|
__pa_nodebug(kasan_early_shadow_p4d));
|
|
set_pgd(pgd, pgd_entry);
|
|
}
|
|
|
|
p4d = early_p4d_offset(pgd, addr);
|
|
do {
|
|
next = p4d_addr_end(addr, end);
|
|
|
|
if (!p4d_none(*p4d))
|
|
continue;
|
|
|
|
p4d_entry = __p4d(_KERNPG_TABLE |
|
|
__pa_nodebug(kasan_early_shadow_pud));
|
|
set_p4d(p4d, p4d_entry);
|
|
} while (p4d++, addr = next, addr != end && p4d_none(*p4d));
|
|
}
|
|
|
|
static void __init kasan_map_early_shadow(pgd_t *pgd)
|
|
{
|
|
/* See comment in kasan_init() */
|
|
unsigned long addr = KASAN_SHADOW_START & PGDIR_MASK;
|
|
unsigned long end = KASAN_SHADOW_END;
|
|
unsigned long next;
|
|
|
|
pgd += pgd_index(addr);
|
|
do {
|
|
next = pgd_addr_end(addr, end);
|
|
kasan_early_p4d_populate(pgd, addr, next);
|
|
} while (pgd++, addr = next, addr != end);
|
|
}
|
|
|
|
static void __init kasan_shallow_populate_p4ds(pgd_t *pgd,
|
|
unsigned long addr,
|
|
unsigned long end)
|
|
{
|
|
p4d_t *p4d;
|
|
unsigned long next;
|
|
void *p;
|
|
|
|
p4d = p4d_offset(pgd, addr);
|
|
do {
|
|
next = p4d_addr_end(addr, end);
|
|
|
|
if (p4d_none(*p4d)) {
|
|
p = early_alloc(PAGE_SIZE, NUMA_NO_NODE, true);
|
|
p4d_populate(&init_mm, p4d, p);
|
|
}
|
|
} while (p4d++, addr = next, addr != end);
|
|
}
|
|
|
|
static void __init kasan_shallow_populate_pgds(void *start, void *end)
|
|
{
|
|
unsigned long addr, next;
|
|
pgd_t *pgd;
|
|
void *p;
|
|
|
|
addr = (unsigned long)start;
|
|
pgd = pgd_offset_k(addr);
|
|
do {
|
|
next = pgd_addr_end(addr, (unsigned long)end);
|
|
|
|
if (pgd_none(*pgd)) {
|
|
p = early_alloc(PAGE_SIZE, NUMA_NO_NODE, true);
|
|
pgd_populate(&init_mm, pgd, p);
|
|
}
|
|
|
|
/*
|
|
* we need to populate p4ds to be synced when running in
|
|
* four level mode - see sync_global_pgds_l4()
|
|
*/
|
|
kasan_shallow_populate_p4ds(pgd, addr, next);
|
|
} while (pgd++, addr = next, addr != (unsigned long)end);
|
|
}
|
|
|
|
void __init kasan_early_init(void)
|
|
{
|
|
int i;
|
|
pteval_t pte_val = __pa_nodebug(kasan_early_shadow_page) |
|
|
__PAGE_KERNEL | _PAGE_ENC;
|
|
pmdval_t pmd_val = __pa_nodebug(kasan_early_shadow_pte) | _KERNPG_TABLE;
|
|
pudval_t pud_val = __pa_nodebug(kasan_early_shadow_pmd) | _KERNPG_TABLE;
|
|
p4dval_t p4d_val = __pa_nodebug(kasan_early_shadow_pud) | _KERNPG_TABLE;
|
|
|
|
/* Mask out unsupported __PAGE_KERNEL bits: */
|
|
pte_val &= __default_kernel_pte_mask;
|
|
pmd_val &= __default_kernel_pte_mask;
|
|
pud_val &= __default_kernel_pte_mask;
|
|
p4d_val &= __default_kernel_pte_mask;
|
|
|
|
for (i = 0; i < PTRS_PER_PTE; i++)
|
|
kasan_early_shadow_pte[i] = __pte(pte_val);
|
|
|
|
for (i = 0; i < PTRS_PER_PMD; i++)
|
|
kasan_early_shadow_pmd[i] = __pmd(pmd_val);
|
|
|
|
for (i = 0; i < PTRS_PER_PUD; i++)
|
|
kasan_early_shadow_pud[i] = __pud(pud_val);
|
|
|
|
for (i = 0; pgtable_l5_enabled() && i < PTRS_PER_P4D; i++)
|
|
kasan_early_shadow_p4d[i] = __p4d(p4d_val);
|
|
|
|
kasan_map_early_shadow(early_top_pgt);
|
|
kasan_map_early_shadow(init_top_pgt);
|
|
}
|
|
|
|
void __init kasan_init(void)
|
|
{
|
|
int i;
|
|
void *shadow_cpu_entry_begin, *shadow_cpu_entry_end;
|
|
|
|
memcpy(early_top_pgt, init_top_pgt, sizeof(early_top_pgt));
|
|
|
|
/*
|
|
* We use the same shadow offset for 4- and 5-level paging to
|
|
* facilitate boot-time switching between paging modes.
|
|
* As result in 5-level paging mode KASAN_SHADOW_START and
|
|
* KASAN_SHADOW_END are not aligned to PGD boundary.
|
|
*
|
|
* KASAN_SHADOW_START doesn't share PGD with anything else.
|
|
* We claim whole PGD entry to make things easier.
|
|
*
|
|
* KASAN_SHADOW_END lands in the last PGD entry and it collides with
|
|
* bunch of things like kernel code, modules, EFI mapping, etc.
|
|
* We need to take extra steps to not overwrite them.
|
|
*/
|
|
if (pgtable_l5_enabled()) {
|
|
void *ptr;
|
|
|
|
ptr = (void *)pgd_page_vaddr(*pgd_offset_k(KASAN_SHADOW_END));
|
|
memcpy(tmp_p4d_table, (void *)ptr, sizeof(tmp_p4d_table));
|
|
set_pgd(&early_top_pgt[pgd_index(KASAN_SHADOW_END)],
|
|
__pgd(__pa(tmp_p4d_table) | _KERNPG_TABLE));
|
|
}
|
|
|
|
load_cr3(early_top_pgt);
|
|
__flush_tlb_all();
|
|
|
|
clear_pgds(KASAN_SHADOW_START & PGDIR_MASK, KASAN_SHADOW_END);
|
|
|
|
kasan_populate_early_shadow((void *)(KASAN_SHADOW_START & PGDIR_MASK),
|
|
kasan_mem_to_shadow((void *)PAGE_OFFSET));
|
|
|
|
for (i = 0; i < E820_MAX_ENTRIES; i++) {
|
|
if (pfn_mapped[i].end == 0)
|
|
break;
|
|
|
|
map_range(&pfn_mapped[i]);
|
|
}
|
|
|
|
shadow_cpu_entry_begin = (void *)CPU_ENTRY_AREA_BASE;
|
|
shadow_cpu_entry_begin = kasan_mem_to_shadow(shadow_cpu_entry_begin);
|
|
shadow_cpu_entry_begin = (void *)round_down(
|
|
(unsigned long)shadow_cpu_entry_begin, PAGE_SIZE);
|
|
|
|
shadow_cpu_entry_end = (void *)(CPU_ENTRY_AREA_BASE +
|
|
CPU_ENTRY_AREA_MAP_SIZE);
|
|
shadow_cpu_entry_end = kasan_mem_to_shadow(shadow_cpu_entry_end);
|
|
shadow_cpu_entry_end = (void *)round_up(
|
|
(unsigned long)shadow_cpu_entry_end, PAGE_SIZE);
|
|
|
|
kasan_populate_early_shadow(
|
|
kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM),
|
|
kasan_mem_to_shadow((void *)VMALLOC_START));
|
|
|
|
/*
|
|
* If we're in full vmalloc mode, don't back vmalloc space with early
|
|
* shadow pages. Instead, prepopulate pgds/p4ds so they are synced to
|
|
* the global table and we can populate the lower levels on demand.
|
|
*/
|
|
if (IS_ENABLED(CONFIG_KASAN_VMALLOC))
|
|
kasan_shallow_populate_pgds(
|
|
kasan_mem_to_shadow((void *)VMALLOC_START),
|
|
kasan_mem_to_shadow((void *)VMALLOC_END));
|
|
else
|
|
kasan_populate_early_shadow(
|
|
kasan_mem_to_shadow((void *)VMALLOC_START),
|
|
kasan_mem_to_shadow((void *)VMALLOC_END));
|
|
|
|
kasan_populate_early_shadow(
|
|
kasan_mem_to_shadow((void *)VMALLOC_END + 1),
|
|
shadow_cpu_entry_begin);
|
|
|
|
kasan_populate_shadow((unsigned long)shadow_cpu_entry_begin,
|
|
(unsigned long)shadow_cpu_entry_end, 0);
|
|
|
|
kasan_populate_early_shadow(shadow_cpu_entry_end,
|
|
kasan_mem_to_shadow((void *)__START_KERNEL_map));
|
|
|
|
kasan_populate_shadow((unsigned long)kasan_mem_to_shadow(_stext),
|
|
(unsigned long)kasan_mem_to_shadow(_end),
|
|
early_pfn_to_nid(__pa(_stext)));
|
|
|
|
kasan_populate_early_shadow(kasan_mem_to_shadow((void *)MODULES_END),
|
|
(void *)KASAN_SHADOW_END);
|
|
|
|
load_cr3(init_top_pgt);
|
|
__flush_tlb_all();
|
|
|
|
/*
|
|
* kasan_early_shadow_page has been used as early shadow memory, thus
|
|
* it may contain some garbage. Now we can clear and write protect it,
|
|
* since after the TLB flush no one should write to it.
|
|
*/
|
|
memset(kasan_early_shadow_page, 0, PAGE_SIZE);
|
|
for (i = 0; i < PTRS_PER_PTE; i++) {
|
|
pte_t pte;
|
|
pgprot_t prot;
|
|
|
|
prot = __pgprot(__PAGE_KERNEL_RO | _PAGE_ENC);
|
|
pgprot_val(prot) &= __default_kernel_pte_mask;
|
|
|
|
pte = __pte(__pa(kasan_early_shadow_page) | pgprot_val(prot));
|
|
set_pte(&kasan_early_shadow_pte[i], pte);
|
|
}
|
|
/* Flush TLBs again to be sure that write protection applied. */
|
|
__flush_tlb_all();
|
|
|
|
init_task.kasan_depth = 0;
|
|
pr_info("KernelAddressSanitizer initialized\n");
|
|
}
|