mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-12 13:34:10 +08:00
935d4f0c6d
Patch series "Fix set_huge_pte_at() panic on arm64", v2. This series fixes a bug in arm64's implementation of set_huge_pte_at(), which can result in an unprivileged user causing a kernel panic. The problem was triggered when running the new uffd poison mm selftest for HUGETLB memory. This test (and the uffd poison feature) was merged for v6.5-rc7. Ideally, I'd like to get this fix in for v6.6 and I've cc'ed stable (correctly this time) to get it backported to v6.5, where the issue first showed up. Description of Bug ================== arm64's huge pte implementation supports multiple huge page sizes, some of which are implemented in the page table with multiple contiguous entries. So set_huge_pte_at() needs to work out how big the logical pte is, so that it can also work out how many physical ptes (or pmds) need to be written. It previously did this by grabbing the folio out of the pte and querying its size. However, there are cases when the pte being set is actually a swap entry. But this also used to work fine, because for huge ptes, we only ever saw migration entries and hwpoison entries. And both of these types of swap entries have a PFN embedded, so the code would grab that and everything still worked out. But over time, more calls to set_huge_pte_at() have been added that set swap entry types that do not embed a PFN. And this causes the code to go bang. The triggering case is for the uffd poison test, commit99aa77215a("selftests/mm: add uffd unit test for UFFDIO_POISON"), which causes a PTE_MARKER_POISONED swap entry to be set, coutesey of commit8a13897fb0("mm: userfaultfd: support UFFDIO_POISON for hugetlbfs") - added in v6.5-rc7. Although review shows that there are other call sites that set PTE_MARKER_UFFD_WP (which also has no PFN), these don't trigger on arm64 because arm64 doesn't support UFFD WP. If CONFIG_DEBUG_VM is enabled, we do at least get a BUG(), but otherwise, it will dereference a bad pointer in page_folio(): static inline struct folio *hugetlb_swap_entry_to_folio(swp_entry_t entry) { VM_BUG_ON(!is_migration_entry(entry) && !is_hwpoison_entry(entry)); return page_folio(pfn_to_page(swp_offset_pfn(entry))); } Fix === The simplest fix would have been to revert the dodgy cleanup commit18f3962953("mm: hugetlb: kill set_huge_swap_pte_at()"), but since things have moved on, this would have required an audit of all the new set_huge_pte_at() call sites to see if they should be converted to set_huge_swap_pte_at(). As per the original intent of the change, it would also leave us open to future bugs when people invariably get it wrong and call the wrong helper. So instead, I've added a huge page size parameter to set_huge_pte_at(). This means that the arm64 code has the size in all cases. It's a bigger change, due to needing to touch the arches that implement the function, but it is entirely mechanical, so in my view, low risk. I've compile-tested all touched arches; arm64, parisc, powerpc, riscv, s390, sparc (and additionally x86_64). I've additionally booted and run mm selftests against arm64, where I observe the uffd poison test is fixed, and there are no other regressions. This patch (of 2): In order to fix a bug, arm64 needs to be told the size of the huge page for which the pte is being set in set_huge_pte_at(). Provide for this by adding an `unsigned long sz` parameter to the function. This follows the same pattern as huge_pte_clear(). This commit makes the required interface modifications to the core mm as well as all arches that implement this function (arm64, parisc, powerpc, riscv, s390, sparc). The actual arm64 bug will be fixed in a separate commit. No behavioral changes intended. Link: https://lkml.kernel.org/r/20230922115804.2043771-1-ryan.roberts@arm.com Link: https://lkml.kernel.org/r/20230922115804.2043771-2-ryan.roberts@arm.com Fixes:8a13897fb0("mm: userfaultfd: support UFFDIO_POISON for hugetlbfs") Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu> [powerpc 8xx] Reviewed-by: Lorenzo Stoakes <lstoakes@gmail.com> [vmalloc change] Cc: Alexandre Ghiti <alex@ghiti.fr> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Axel Rasmussen <axelrasmussen@google.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@linux.ibm.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: David S. Miller <davem@davemloft.net> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Muchun Song <muchun.song@linux.dev> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Peter Xu <peterx@redhat.com> Cc: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: SeongJae Park <sj@kernel.org> Cc: Sven Schnelle <svens@linux.ibm.com> Cc: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: <stable@vger.kernel.org> [6.5+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
161 lines
3.5 KiB
C
161 lines
3.5 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _ASM_GENERIC_HUGETLB_H
|
|
#define _ASM_GENERIC_HUGETLB_H
|
|
|
|
#include <linux/swap.h>
|
|
#include <linux/swapops.h>
|
|
|
|
static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot)
|
|
{
|
|
return mk_pte(page, pgprot);
|
|
}
|
|
|
|
static inline unsigned long huge_pte_write(pte_t pte)
|
|
{
|
|
return pte_write(pte);
|
|
}
|
|
|
|
static inline unsigned long huge_pte_dirty(pte_t pte)
|
|
{
|
|
return pte_dirty(pte);
|
|
}
|
|
|
|
static inline pte_t huge_pte_mkwrite(pte_t pte)
|
|
{
|
|
return pte_mkwrite_novma(pte);
|
|
}
|
|
|
|
#ifndef __HAVE_ARCH_HUGE_PTE_WRPROTECT
|
|
static inline pte_t huge_pte_wrprotect(pte_t pte)
|
|
{
|
|
return pte_wrprotect(pte);
|
|
}
|
|
#endif
|
|
|
|
static inline pte_t huge_pte_mkdirty(pte_t pte)
|
|
{
|
|
return pte_mkdirty(pte);
|
|
}
|
|
|
|
static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot)
|
|
{
|
|
return pte_modify(pte, newprot);
|
|
}
|
|
|
|
static inline pte_t huge_pte_mkuffd_wp(pte_t pte)
|
|
{
|
|
return huge_pte_wrprotect(pte_mkuffd_wp(pte));
|
|
}
|
|
|
|
static inline pte_t huge_pte_clear_uffd_wp(pte_t pte)
|
|
{
|
|
return pte_clear_uffd_wp(pte);
|
|
}
|
|
|
|
static inline int huge_pte_uffd_wp(pte_t pte)
|
|
{
|
|
return pte_uffd_wp(pte);
|
|
}
|
|
|
|
#ifndef __HAVE_ARCH_HUGE_PTE_CLEAR
|
|
static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
|
|
pte_t *ptep, unsigned long sz)
|
|
{
|
|
pte_clear(mm, addr, ptep);
|
|
}
|
|
#endif
|
|
|
|
#ifndef __HAVE_ARCH_HUGETLB_FREE_PGD_RANGE
|
|
static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
|
|
unsigned long addr, unsigned long end,
|
|
unsigned long floor, unsigned long ceiling)
|
|
{
|
|
free_pgd_range(tlb, addr, end, floor, ceiling);
|
|
}
|
|
#endif
|
|
|
|
#ifndef __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
|
|
static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
|
|
pte_t *ptep, pte_t pte, unsigned long sz)
|
|
{
|
|
set_pte_at(mm, addr, ptep, pte);
|
|
}
|
|
#endif
|
|
|
|
#ifndef __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
|
|
static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
|
|
unsigned long addr, pte_t *ptep)
|
|
{
|
|
return ptep_get_and_clear(mm, addr, ptep);
|
|
}
|
|
#endif
|
|
|
|
#ifndef __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
|
|
static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
|
|
unsigned long addr, pte_t *ptep)
|
|
{
|
|
return ptep_clear_flush(vma, addr, ptep);
|
|
}
|
|
#endif
|
|
|
|
#ifndef __HAVE_ARCH_HUGE_PTE_NONE
|
|
static inline int huge_pte_none(pte_t pte)
|
|
{
|
|
return pte_none(pte);
|
|
}
|
|
#endif
|
|
|
|
/* Please refer to comments above pte_none_mostly() for the usage */
|
|
static inline int huge_pte_none_mostly(pte_t pte)
|
|
{
|
|
return huge_pte_none(pte) || is_pte_marker(pte);
|
|
}
|
|
|
|
#ifndef __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE
|
|
static inline int prepare_hugepage_range(struct file *file,
|
|
unsigned long addr, unsigned long len)
|
|
{
|
|
struct hstate *h = hstate_file(file);
|
|
|
|
if (len & ~huge_page_mask(h))
|
|
return -EINVAL;
|
|
if (addr & ~huge_page_mask(h))
|
|
return -EINVAL;
|
|
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
#ifndef __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
|
|
static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
|
|
unsigned long addr, pte_t *ptep)
|
|
{
|
|
ptep_set_wrprotect(mm, addr, ptep);
|
|
}
|
|
#endif
|
|
|
|
#ifndef __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
|
|
static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
|
|
unsigned long addr, pte_t *ptep,
|
|
pte_t pte, int dirty)
|
|
{
|
|
return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
|
|
}
|
|
#endif
|
|
|
|
#ifndef __HAVE_ARCH_HUGE_PTEP_GET
|
|
static inline pte_t huge_ptep_get(pte_t *ptep)
|
|
{
|
|
return ptep_get(ptep);
|
|
}
|
|
#endif
|
|
|
|
#ifndef __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED
|
|
static inline bool gigantic_page_runtime_supported(void)
|
|
{
|
|
return IS_ENABLED(CONFIG_ARCH_HAS_GIGANTIC_PAGE);
|
|
}
|
|
#endif /* __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED */
|
|
|
|
#endif /* _ASM_GENERIC_HUGETLB_H */
|