linux/arch/x86/include/asm/pgtable_64.h

193 lines
4.9 KiB
C
Raw Normal View History

#ifndef _ASM_X86_PGTABLE_64_H
#define _ASM_X86_PGTABLE_64_H
#include <linux/const.h>
#include <asm/pgtable_64_types.h>
#ifndef __ASSEMBLY__
/*
* This file contains the functions and defines necessary to modify and use
* the x86-64 page table tree.
*/
#include <asm/processor.h>
#include <linux/bitops.h>
#include <linux/threads.h>
extern pud_t level3_kernel_pgt[512];
extern pud_t level3_ident_pgt[512];
extern pmd_t level2_kernel_pgt[512];
extern pmd_t level2_fixmap_pgt[512];
extern pmd_t level2_ident_pgt[512];
x86/xen: don't copy bogus duplicate entries into kernel page tables When RANDOMIZE_BASE (KASLR) is enabled; or the sum of all loaded modules exceeds 512 MiB, then loading modules fails with a warning (and hence a vmalloc allocation failure) because the PTEs for the newly-allocated vmalloc address space are not zero. WARNING: CPU: 0 PID: 494 at linux/mm/vmalloc.c:128 vmap_page_range_noflush+0x2a1/0x360() This is caused by xen_setup_kernel_pagetables() copying level2_kernel_pgt into level2_fixmap_pgt, overwriting many non-present entries. Without KASLR, the normal kernel image size only covers the first half of level2_kernel_pgt and module space starts after that. L4[511]->level3_kernel_pgt[510]->level2_kernel_pgt[ 0..255]->kernel [256..511]->module [511]->level2_fixmap_pgt[ 0..505]->module This allows 512 MiB of of module vmalloc space to be used before having to use the corrupted level2_fixmap_pgt entries. With KASLR enabled, the kernel image uses the full PUD range of 1G and module space starts in the level2_fixmap_pgt. So basically: L4[511]->level3_kernel_pgt[510]->level2_kernel_pgt[0..511]->kernel [511]->level2_fixmap_pgt[0..505]->module And now no module vmalloc space can be used without using the corrupt level2_fixmap_pgt entries. Fix this by properly converting the level2_fixmap_pgt entries to MFNs, and setting level1_fixmap_pgt as read-only. A number of comments were also using the the wrong L3 offset for level2_kernel_pgt. These have been corrected. Signed-off-by: Stefan Bader <stefan.bader@canonical.com> Signed-off-by: David Vrabel <david.vrabel@citrix.com> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: stable@vger.kernel.org
2014-09-02 10:16:01 +00:00
extern pte_t level1_fixmap_pgt[512];
extern pgd_t init_level4_pgt[];
#define swapper_pg_dir init_level4_pgt
extern void paging_init(void);
#define pte_ERROR(e) \
pr_err("%s:%d: bad pte %p(%016lx)\n", \
__FILE__, __LINE__, &(e), pte_val(e))
#define pmd_ERROR(e) \
pr_err("%s:%d: bad pmd %p(%016lx)\n", \
__FILE__, __LINE__, &(e), pmd_val(e))
#define pud_ERROR(e) \
pr_err("%s:%d: bad pud %p(%016lx)\n", \
__FILE__, __LINE__, &(e), pud_val(e))
#define pgd_ERROR(e) \
pr_err("%s:%d: bad pgd %p(%016lx)\n", \
__FILE__, __LINE__, &(e), pgd_val(e))
struct mm_struct;
void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte);
static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
{
*ptep = native_make_pte(0);
}
static inline void native_set_pte(pte_t *ptep, pte_t pte)
{
*ptep = pte;
}
static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
{
native_set_pte(ptep, pte);
}
static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
{
*pmdp = pmd;
}
static inline void native_pmd_clear(pmd_t *pmd)
{
native_set_pmd(pmd, native_make_pmd(0));
}
static inline pte_t native_ptep_get_and_clear(pte_t *xp)
{
#ifdef CONFIG_SMP
return native_make_pte(xchg(&xp->pte, 0));
#else
/* native_local_ptep_get_and_clear,
but duplicated because of cyclic dependency */
pte_t ret = *xp;
native_pte_clear(NULL, 0, xp);
return ret;
#endif
}
static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
{
#ifdef CONFIG_SMP
return native_make_pmd(xchg(&xp->pmd, 0));
#else
/* native_local_pmdp_get_and_clear,
but duplicated because of cyclic dependency */
pmd_t ret = *xp;
native_pmd_clear(xp);
return ret;
#endif
}
static inline void native_set_pud(pud_t *pudp, pud_t pud)
{
*pudp = pud;
}
static inline void native_pud_clear(pud_t *pud)
{
native_set_pud(pud, native_make_pud(0));
}
static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
{
*pgdp = pgd;
}
static inline void native_pgd_clear(pgd_t *pgd)
{
native_set_pgd(pgd, native_make_pgd(0));
}
x86/mm/hotplug: Modify PGD entry when removing memory When hot-adding/removing memory, sync_global_pgds() is called for synchronizing PGD to PGD entries of all processes MM. But when hot-removing memory, sync_global_pgds() does not work correctly. At first, sync_global_pgds() checks whether target PGD is none or not. And if PGD is none, the PGD is skipped. But when hot-removing memory, PGD may be none since PGD may be cleared by free_pud_table(). So when sync_global_pgds() is called after hot-removing memory, sync_global_pgds() should not skip PGD even if the PGD is none. And sync_global_pgds() must clear PGD entries of all processes MM. Currently sync_global_pgds() does not clear PGD entries of all processes MM when hot-removing memory. So when hot adding memory which is same memory range as removed memory after hot-removing memory, following call traces are shown: kernel BUG at arch/x86/mm/init_64.c:206! ... [<ffffffff815e0c80>] kernel_physical_mapping_init+0x1b2/0x1d2 [<ffffffff815ced94>] init_memory_mapping+0x1d4/0x380 [<ffffffff8104aebd>] arch_add_memory+0x3d/0xd0 [<ffffffff815d03d9>] add_memory+0xb9/0x1b0 [<ffffffff81352415>] acpi_memory_device_add+0x1af/0x28e [<ffffffff81325dc4>] acpi_bus_device_attach+0x8c/0xf0 [<ffffffff813413b9>] acpi_ns_walk_namespace+0xc8/0x17f [<ffffffff81325d38>] ? acpi_bus_type_and_status+0xb7/0xb7 [<ffffffff81325d38>] ? acpi_bus_type_and_status+0xb7/0xb7 [<ffffffff813418ed>] acpi_walk_namespace+0x95/0xc5 [<ffffffff81326b4c>] acpi_bus_scan+0x9a/0xc2 [<ffffffff81326bff>] acpi_scan_bus_device_check+0x8b/0x12e [<ffffffff81326cb5>] acpi_scan_device_check+0x13/0x15 [<ffffffff81320122>] acpi_os_execute_deferred+0x25/0x32 [<ffffffff8107e02b>] process_one_work+0x17b/0x460 [<ffffffff8107edfb>] worker_thread+0x11b/0x400 [<ffffffff8107ece0>] ? rescuer_thread+0x400/0x400 [<ffffffff81085aef>] kthread+0xcf/0xe0 [<ffffffff81085a20>] ? kthread_create_on_node+0x140/0x140 [<ffffffff815fc76c>] ret_from_fork+0x7c/0xb0 [<ffffffff81085a20>] ? kthread_create_on_node+0x140/0x140 This patch clears PGD entries of all processes MM when sync_global_pgds() is called after hot-removing memory Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Acked-by: Toshi Kani <toshi.kani@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Gu Zheng <guz.fnst@cn.fujitsu.com> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-08-22 20:27:34 +00:00
extern void sync_global_pgds(unsigned long start, unsigned long end,
int removed);
/*
* Conversion functions: convert a page and protection to a page entry,
* and a page entry and page directory to the page they refer to.
*/
/*
* Level 4 access.
*/
static inline int pgd_large(pgd_t pgd) { return 0; }
#define mk_kernel_pgd(address) __pgd((address) | _KERNPG_TABLE)
/* PUD - Level3 access */
/* PMD - Level 2 access */
#define pte_to_pgoff(pte) ((pte_val((pte)) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT)
#define pgoff_to_pte(off) ((pte_t) { .pte = ((off) << PAGE_SHIFT) | \
_PAGE_FILE })
#define PTE_FILE_MAX_BITS __PHYSICAL_MASK_SHIFT
/* PTE - Level 1 access. */
/* x86-64 always has all page tables mapped. */
#define pte_offset_map(dir, address) pte_offset_kernel((dir), (address))
#define pte_unmap(pte) ((void)(pte))/* NOP */
/* Encode and de-code a swap entry */
#define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1)
x86: define _PAGE_NUMA by reusing software bits on the PMD and PTE levels _PAGE_NUMA is currently an alias of _PROT_PROTNONE to trap NUMA hinting faults on x86. Care is taken such that _PAGE_NUMA is used only in situations where the VMA flags distinguish between NUMA hinting faults and prot_none faults. This decision was x86-specific and conceptually it is difficult requiring special casing to distinguish between PROTNONE and NUMA ptes based on context. Fundamentally, we only need the _PAGE_NUMA bit to tell the difference between an entry that is really unmapped and a page that is protected for NUMA hinting faults as if the PTE is not present then a fault will be trapped. Swap PTEs on x86-64 use the bits after _PAGE_GLOBAL for the offset. This patch shrinks the maximum possible swap size and uses the bit to uniquely distinguish between NUMA hinting ptes and swap ptes. Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: David Vrabel <david.vrabel@citrix.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Peter Anvin <hpa@zytor.com> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Steven Noonan <steven@uplinklabs.net> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:06:30 +00:00
#ifdef CONFIG_NUMA_BALANCING
/* Automatic NUMA balancing needs to be distinguishable from swap entries */
#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 2)
#else
#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1)
x86: define _PAGE_NUMA by reusing software bits on the PMD and PTE levels _PAGE_NUMA is currently an alias of _PROT_PROTNONE to trap NUMA hinting faults on x86. Care is taken such that _PAGE_NUMA is used only in situations where the VMA flags distinguish between NUMA hinting faults and prot_none faults. This decision was x86-specific and conceptually it is difficult requiring special casing to distinguish between PROTNONE and NUMA ptes based on context. Fundamentally, we only need the _PAGE_NUMA bit to tell the difference between an entry that is really unmapped and a page that is protected for NUMA hinting faults as if the PTE is not present then a fault will be trapped. Swap PTEs on x86-64 use the bits after _PAGE_GLOBAL for the offset. This patch shrinks the maximum possible swap size and uses the bit to uniquely distinguish between NUMA hinting ptes and swap ptes. Signed-off-by: Mel Gorman <mgorman@suse.de> Cc: David Vrabel <david.vrabel@citrix.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Peter Anvin <hpa@zytor.com> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Steven Noonan <steven@uplinklabs.net> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:06:30 +00:00
#endif
#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
#define __swp_type(x) (((x).val >> (_PAGE_BIT_PRESENT + 1)) \
& ((1U << SWP_TYPE_BITS) - 1))
#define __swp_offset(x) ((x).val >> SWP_OFFSET_SHIFT)
#define __swp_entry(type, offset) ((swp_entry_t) { \
((type) << (_PAGE_BIT_PRESENT + 1)) \
| ((offset) << SWP_OFFSET_SHIFT) })
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) })
#define __swp_entry_to_pte(x) ((pte_t) { .pte = (x).val })
extern int kern_addr_valid(unsigned long addr);
extern void cleanup_highmap(void);
#define HAVE_ARCH_UNMAPPED_AREA
#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
#define pgtable_cache_init() do { } while (0)
#define check_pgt_cache() do { } while (0)
#define PAGE_AGP PAGE_KERNEL_NOCACHE
#define HAVE_PAGE_AGP 1
/* fs/proc/kcore.c */
#define kc_vaddr_to_offset(v) ((v) & __VIRTUAL_MASK)
x86, 64-bit: Clean up user address masking The discussion about using "access_ok()" in get_user_pages_fast() (see commit 7f8189068726492950bf1a2dcfd9b51314560abf: "x86: don't use 'access_ok()' as a range check in get_user_pages_fast()" for details and end result), made us notice that x86-64 was really being very sloppy about virtual address checking. So be way more careful and straightforward about masking x86-64 virtual addresses: - All the VIRTUAL_MASK* variants now cover half of the address space, it's not like we can use the full mask on a signed integer, and the larger mask just invites mistakes when applying it to either half of the 48-bit address space. - /proc/kcore's kc_offset_to_vaddr() becomes a lot more obvious when it transforms a file offset into a (kernel-half) virtual address. - Unify/simplify the 32-bit and 64-bit USER_DS definition to be based on TASK_SIZE_MAX. This cleanup and more careful/obvious user virtual address checking also uncovered a buglet in the x86-64 implementation of strnlen_user(): it would do an "access_ok()" check on the whole potential area, even if the string itself was much shorter, and thus return an error even for valid strings. Our sloppy checking had hidden this. So this fixes 'strnlen_user()' to do this properly, the same way we already handled user strings in 'strncpy_from_user()'. Namely by just checking the first byte, and then relying on fault handling for the rest. That always works, since we impose a guard page that cannot be mapped at the end of the user space address space (and even if we didn't, we'd have the address space hole). Acked-by: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Nick Piggin <npiggin@suse.de> Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-20 22:40:00 +00:00
#define kc_offset_to_vaddr(o) ((o) | ~__VIRTUAL_MASK)
#define __HAVE_ARCH_PTE_SAME
#define vmemmap ((struct page *)VMEMMAP_START)
extern void init_extra_mapping_uc(unsigned long phys, unsigned long size);
extern void init_extra_mapping_wb(unsigned long phys, unsigned long size);
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_X86_PGTABLE_64_H */