linux/arch/arm64/mm/hugetlbpage.c

316 lines
7.4 KiB
C
Raw Normal View History

/*
* arch/arm64/mm/hugetlbpage.c
*
* Copyright (C) 2013 Linaro Ltd.
*
* Based on arch/x86/mm/hugetlbpage.c.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*/
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/pagemap.h>
#include <linux/err.h>
#include <linux/sysctl.h>
#include <asm/mman.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/pgalloc.h>
int pmd_huge(pmd_t pmd)
{
return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
}
int pud_huge(pud_t pud)
{
arm64: fix pud_huge() for 2-level pagetables The following happens when trying to run a kvm guest on a kernel configured for 64k pages. This doesn't happen with 4k pages: BUG: failure at include/linux/mm.h:297/put_page_testzero()! Kernel panic - not syncing: BUG! CPU: 2 PID: 4228 Comm: qemu-system-aar Tainted: GF 3.13.0-0.rc7.31.sa2.k32v1.aarch64.debug #1 Call trace: [<fffffe0000096034>] dump_backtrace+0x0/0x16c [<fffffe00000961b4>] show_stack+0x14/0x1c [<fffffe000066e648>] dump_stack+0x84/0xb0 [<fffffe0000668678>] panic+0xf4/0x220 [<fffffe000018ec78>] free_reserved_area+0x0/0x110 [<fffffe000018edd8>] free_pages+0x50/0x88 [<fffffe00000a759c>] kvm_free_stage2_pgd+0x30/0x40 [<fffffe00000a5354>] kvm_arch_destroy_vm+0x18/0x44 [<fffffe00000a1854>] kvm_put_kvm+0xf0/0x184 [<fffffe00000a1938>] kvm_vm_release+0x10/0x1c [<fffffe00001edc1c>] __fput+0xb0/0x288 [<fffffe00001ede4c>] ____fput+0xc/0x14 [<fffffe00000d5a2c>] task_work_run+0xa8/0x11c [<fffffe0000095c14>] do_notify_resume+0x54/0x58 In arch/arm/kvm/mmu.c:unmap_range(), we end up doing an extra put_page() on the stage2 pgd which leads to the BUG in put_page_testzero(). This happens because a pud_huge() test in unmap_range() returns true when it should always be false with 2-level pages tables used by 64k pages. This patch removes support for huge puds if 2-level pagetables are being used. Signed-off-by: Mark Salter <msalter@redhat.com> [catalin.marinas@arm.com: removed #ifndef around PUD_SIZE check] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com> Cc: <stable@vger.kernel.org> # v3.11+
2014-05-15 22:19:22 +08:00
#ifndef __PAGETABLE_PMD_FOLDED
return pud_val(pud) && !(pud_val(pud) & PUD_TABLE_BIT);
arm64: fix pud_huge() for 2-level pagetables The following happens when trying to run a kvm guest on a kernel configured for 64k pages. This doesn't happen with 4k pages: BUG: failure at include/linux/mm.h:297/put_page_testzero()! Kernel panic - not syncing: BUG! CPU: 2 PID: 4228 Comm: qemu-system-aar Tainted: GF 3.13.0-0.rc7.31.sa2.k32v1.aarch64.debug #1 Call trace: [<fffffe0000096034>] dump_backtrace+0x0/0x16c [<fffffe00000961b4>] show_stack+0x14/0x1c [<fffffe000066e648>] dump_stack+0x84/0xb0 [<fffffe0000668678>] panic+0xf4/0x220 [<fffffe000018ec78>] free_reserved_area+0x0/0x110 [<fffffe000018edd8>] free_pages+0x50/0x88 [<fffffe00000a759c>] kvm_free_stage2_pgd+0x30/0x40 [<fffffe00000a5354>] kvm_arch_destroy_vm+0x18/0x44 [<fffffe00000a1854>] kvm_put_kvm+0xf0/0x184 [<fffffe00000a1938>] kvm_vm_release+0x10/0x1c [<fffffe00001edc1c>] __fput+0xb0/0x288 [<fffffe00001ede4c>] ____fput+0xc/0x14 [<fffffe00000d5a2c>] task_work_run+0xa8/0x11c [<fffffe0000095c14>] do_notify_resume+0x54/0x58 In arch/arm/kvm/mmu.c:unmap_range(), we end up doing an extra put_page() on the stage2 pgd which leads to the BUG in put_page_testzero(). This happens because a pud_huge() test in unmap_range() returns true when it should always be false with 2-level pages tables used by 64k pages. This patch removes support for huge puds if 2-level pagetables are being used. Signed-off-by: Mark Salter <msalter@redhat.com> [catalin.marinas@arm.com: removed #ifndef around PUD_SIZE check] Signed-off-by: Catalin Marinas <catalin.marinas@arm.com> Cc: <stable@vger.kernel.org> # v3.11+
2014-05-15 22:19:22 +08:00
#else
return 0;
#endif
}
static int find_num_contig(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte, size_t *pgsize)
{
pgd_t *pgd = pgd_offset(mm, addr);
pud_t *pud;
pmd_t *pmd;
*pgsize = PAGE_SIZE;
if (!pte_cont(pte))
return 1;
if (!pgd_present(*pgd)) {
VM_BUG_ON(!pgd_present(*pgd));
return 1;
}
pud = pud_offset(pgd, addr);
if (!pud_present(*pud)) {
VM_BUG_ON(!pud_present(*pud));
return 1;
}
pmd = pmd_offset(pud, addr);
if (!pmd_present(*pmd)) {
VM_BUG_ON(!pmd_present(*pmd));
return 1;
}
if ((pte_t *)pmd == ptep) {
*pgsize = PMD_SIZE;
return CONT_PMDS;
}
return CONT_PTES;
}
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte)
{
size_t pgsize;
int i;
int ncontig = find_num_contig(mm, addr, ptep, pte, &pgsize);
unsigned long pfn;
pgprot_t hugeprot;
if (ncontig == 1) {
set_pte_at(mm, addr, ptep, pte);
return;
}
pfn = pte_pfn(pte);
hugeprot = __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte));
for (i = 0; i < ncontig; i++) {
pr_debug("%s: set pte %p to 0x%llx\n", __func__, ptep,
pte_val(pfn_pte(pfn, hugeprot)));
set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
ptep++;
pfn += pgsize >> PAGE_SHIFT;
addr += pgsize;
}
}
pte_t *huge_pte_alloc(struct mm_struct *mm,
unsigned long addr, unsigned long sz)
{
pgd_t *pgd;
pud_t *pud;
pte_t *pte = NULL;
pr_debug("%s: addr:0x%lx sz:0x%lx\n", __func__, addr, sz);
pgd = pgd_offset(mm, addr);
pud = pud_alloc(mm, pgd, addr);
if (!pud)
return NULL;
if (sz == PUD_SIZE) {
pte = (pte_t *)pud;
} else if (sz == (PAGE_SIZE * CONT_PTES)) {
pmd_t *pmd = pmd_alloc(mm, pud, addr);
WARN_ON(addr & (sz - 1));
/*
* Note that if this code were ever ported to the
* 32-bit arm platform then it will cause trouble in
* the case where CONFIG_HIGHPTE is set, since there
* will be no pte_unmap() to correspond with this
* pte_alloc_map().
*/
pte = pte_alloc_map(mm, pmd, addr);
} else if (sz == PMD_SIZE) {
if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) &&
pud_none(*pud))
pte = huge_pmd_share(mm, addr, pud);
else
pte = (pte_t *)pmd_alloc(mm, pud, addr);
} else if (sz == (PMD_SIZE * CONT_PMDS)) {
pmd_t *pmd;
pmd = pmd_alloc(mm, pud, addr);
WARN_ON(addr & (sz - 1));
return (pte_t *)pmd;
}
pr_debug("%s: addr:0x%lx sz:0x%lx ret pte=%p/0x%llx\n", __func__, addr,
sz, pte, pte_val(*pte));
return pte;
}
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd = NULL;
pte_t *pte = NULL;
pgd = pgd_offset(mm, addr);
pr_debug("%s: addr:0x%lx pgd:%p\n", __func__, addr, pgd);
if (!pgd_present(*pgd))
return NULL;
pud = pud_offset(pgd, addr);
if (!pud_present(*pud))
return NULL;
if (pud_huge(*pud))
return (pte_t *)pud;
pmd = pmd_offset(pud, addr);
if (!pmd_present(*pmd))
return NULL;
if (pte_cont(pmd_pte(*pmd))) {
pmd = pmd_offset(
pud, (addr & CONT_PMD_MASK));
return (pte_t *)pmd;
}
if (pmd_huge(*pmd))
return (pte_t *)pmd;
pte = pte_offset_kernel(pmd, addr);
if (pte_present(*pte) && pte_cont(*pte)) {
pte = pte_offset_kernel(
pmd, (addr & CONT_PTE_MASK));
return pte;
}
return NULL;
}
pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
struct page *page, int writable)
{
size_t pagesize = huge_page_size(hstate_vma(vma));
if (pagesize == CONT_PTE_SIZE) {
entry = pte_mkcont(entry);
} else if (pagesize == CONT_PMD_SIZE) {
entry = pmd_pte(pmd_mkcont(pte_pmd(entry)));
} else if (pagesize != PUD_SIZE && pagesize != PMD_SIZE) {
pr_warn("%s: unrecognized huge page size 0x%lx\n",
__func__, pagesize);
}
return entry;
}
pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
pte_t pte;
if (pte_cont(*ptep)) {
int ncontig, i;
size_t pgsize;
pte_t *cpte;
bool is_dirty = false;
cpte = huge_pte_offset(mm, addr);
ncontig = find_num_contig(mm, addr, cpte, *cpte, &pgsize);
/* save the 1st pte to return */
pte = ptep_get_and_clear(mm, addr, cpte);
for (i = 1; i < ncontig; ++i) {
/*
* If HW_AFDBM is enabled, then the HW could
* turn on the dirty bit for any of the page
* in the set, so check them all.
*/
++cpte;
if (pte_dirty(ptep_get_and_clear(mm, addr, cpte)))
is_dirty = true;
}
if (is_dirty)
return pte_mkdirty(pte);
else
return pte;
} else {
return ptep_get_and_clear(mm, addr, ptep);
}
}
int huge_ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t pte, int dirty)
{
pte_t *cpte;
if (pte_cont(pte)) {
int ncontig, i, changed = 0;
size_t pgsize = 0;
unsigned long pfn = pte_pfn(pte);
/* Select all bits except the pfn */
pgprot_t hugeprot =
__pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^
pte_val(pte));
cpte = huge_pte_offset(vma->vm_mm, addr);
pfn = pte_pfn(*cpte);
ncontig = find_num_contig(vma->vm_mm, addr, cpte,
*cpte, &pgsize);
for (i = 0; i < ncontig; ++i, ++cpte) {
changed = ptep_set_access_flags(vma, addr, cpte,
pfn_pte(pfn,
hugeprot),
dirty);
pfn += pgsize >> PAGE_SHIFT;
}
return changed;
} else {
return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
}
}
void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
if (pte_cont(*ptep)) {
int ncontig, i;
pte_t *cpte;
size_t pgsize = 0;
cpte = huge_pte_offset(mm, addr);
ncontig = find_num_contig(mm, addr, cpte, *cpte, &pgsize);
for (i = 0; i < ncontig; ++i, ++cpte)
ptep_set_wrprotect(mm, addr, cpte);
} else {
ptep_set_wrprotect(mm, addr, ptep);
}
}
void huge_ptep_clear_flush(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
if (pte_cont(*ptep)) {
int ncontig, i;
pte_t *cpte;
size_t pgsize = 0;
cpte = huge_pte_offset(vma->vm_mm, addr);
ncontig = find_num_contig(vma->vm_mm, addr, cpte,
*cpte, &pgsize);
for (i = 0; i < ncontig; ++i, ++cpte)
ptep_clear_flush(vma, addr, cpte);
} else {
ptep_clear_flush(vma, addr, ptep);
}
}
static __init int setup_hugepagesz(char *opt)
{
unsigned long ps = memparse(opt, &opt);
if (ps == PMD_SIZE) {
hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
} else if (ps == PUD_SIZE) {
hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
} else {
pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
return 0;
}
return 1;
}
__setup("hugepagesz=", setup_hugepagesz);