mirror-linux/arch
James Houghton b01af92818 arm64: mm: Always make sw-dirty PTEs hw-dirty in pte_modify
commit 3c0696076a upstream.

It is currently possible for a userspace application to enter an
infinite page fault loop when using HugeTLB pages implemented with
contiguous PTEs when HAFDBS is not available. This happens because:

1. The kernel may sometimes write PTEs that are sw-dirty but hw-clean
   (PTE_DIRTY | PTE_RDONLY | PTE_WRITE).

2. If, during a write, the CPU uses a sw-dirty, hw-clean PTE in handling
   the memory access on a system without HAFDBS, we will get a page
   fault.

3. HugeTLB will check if it needs to update the dirty bits on the PTE.
   For contiguous PTEs, it will check to see if the pgprot bits need
   updating. In this case, HugeTLB wants to write a sequence of
   sw-dirty, hw-dirty PTEs, but it finds that all the PTEs it is about
   to overwrite are all pte_dirty() (pte_sw_dirty() => pte_dirty()),
   so it thinks no update is necessary.

We can get the kernel to write a sw-dirty, hw-clean PTE with the
following steps (showing the relevant VMA flags and pgprot bits):

i.   Create a valid, writable contiguous PTE.
       VMA vmflags:     VM_SHARED | VM_READ | VM_WRITE
       VMA pgprot bits: PTE_RDONLY | PTE_WRITE
       PTE pgprot bits: PTE_DIRTY | PTE_WRITE

ii.  mprotect the VMA to PROT_NONE.
       VMA vmflags:     VM_SHARED
       VMA pgprot bits: PTE_RDONLY
       PTE pgprot bits: PTE_DIRTY | PTE_RDONLY

iii. mprotect the VMA back to PROT_READ | PROT_WRITE.
       VMA vmflags:     VM_SHARED | VM_READ | VM_WRITE
       VMA pgprot bits: PTE_RDONLY | PTE_WRITE
       PTE pgprot bits: PTE_DIRTY | PTE_WRITE | PTE_RDONLY

Make it impossible to create a writeable sw-dirty, hw-clean PTE with
pte_modify(). Such a PTE should be impossible to create, and there may
be places that assume that pte_dirty() implies pte_hw_dirty().

Signed-off-by: James Houghton <jthoughton@google.com>
Fixes: 031e6e6b4e ("arm64: hugetlb: Avoid unnecessary clearing in huge_ptep_set_access_flags")
Cc: <stable@vger.kernel.org>
Acked-by: Will Deacon <will@kernel.org>
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Link: https://lore.kernel.org/r/20231204172646.2541916-3-jthoughton@google.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2023-12-20 17:00:25 +01:00
..
alpha alpha: remove __init annotation from exported page_is_ram() 2023-08-16 18:27:31 +02:00
arc ARC: atomics: Add compiler barrier to atomic operations... 2023-09-19 12:28:04 +02:00
arm ARM: dts: imx28-xea: Pass the 'model' property 2023-12-13 18:39:16 +01:00
arm64 arm64: mm: Always make sw-dirty PTEs hw-dirty in pte_modify 2023-12-20 17:00:25 +01:00
csky
hexagon
ia64 ia64/cpu: Switch to arch_cpu_finalize_init() 2023-08-08 20:03:46 +02:00
loongarch LoongArch: Implement constant timer shutdown interface 2023-12-20 17:00:23 +01:00
m68k m68k: Fix invalid .section syntax 2023-09-13 09:42:21 +02:00
microblaze
mips MIPS: Loongson64: Enable DMA noncoherent support 2023-12-13 18:39:29 +01:00
nios2
openrisc
parisc parisc: Fix asm operand number out of range build error in bug table 2023-12-13 18:39:24 +01:00
powerpc powerpc/ftrace: Fix stack teardown in ftrace_no_trace 2023-12-20 17:00:14 +01:00
riscv riscv: Kconfig: Add select ARM_AMBA to SOC_STARFIVE 2023-12-13 18:39:29 +01:00
s390 KVM: s390/mm: Properly reset no-dat 2023-12-13 18:39:29 +01:00
sh sh: bios: Revive earlyprintk support 2023-11-20 11:52:07 +01:00
sparc sparc32: fix a braino in fault handling in csum_and_copy_..._user() 2023-11-02 09:35:32 +01:00
um um: Fix hostaudio build errors 2023-09-13 09:42:58 +02:00
x86 x86/hyperv: Fix the detection of E820_TYPE_PRAM in a Gen2 VM 2023-12-20 17:00:21 +01:00
xtensa xtensa: boot/lib: fix function prototypes 2023-10-06 14:56:49 +02:00
.gitignore
Kconfig init: Provide arch_cpu_finalize_init() 2023-08-08 20:03:46 +02:00