[PATCH v3 26/40] mm: remove VMA_IO_BIT check in vma[_flags]_is_kernel_owned()
From: "Lorenzo Stoakes (ARM)" <ljs@kernel.org>
Date: 2026-09-17 16:36:13
Also in:
bpf, dri-devel, fuse-devel, kvm, kvm-riscv, kvmarm, linux-arch, linux-doc, linux-fsdevel, linux-mm, linux-perf-users, linux-rdma, linux-riscv, linux-s390, linux-scsi, linux-sound, linux-trace-kernel, linux-usb, linuxppc-dev, lkml, selinux, sparclinux
Subsystem:
memory management, memory management - core, memory mapping, scheduler, the rest · Maintainers:
Andrew Morton, David Hildenbrand, Liam R. Howlett, Lorenzo Stoakes, Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot, Linus Torvalds
We have now made it such that every driver which sets VMA_IO_BIT marks it as kernel-owned. However, vma_flags_is_kernel_owned() currently checks for VMA_IO_BIT. This was a product of drivers previously marking a range as kernel-owned by setting VMA_IO_BIT alone. Fix this by removing the VMA_IO_BIT check in vma_flags_is_kernel_owned(), and update mmap_validate_vma_flags() to use vma_flags_is_kernel_owned() rather than open-coding the VMA_PFNMAP_BIT, VMA_MIXEDMAP_BIT check. This change means that vma[_flags]_can_merge() doesn't check VMA_IO_BIT any longer (which is now redundant) as it calls vma_flags_is_kernel_owned(). Now that the predicate means precisely VMA_PFNMAP_BIT or VMA_MIXEDMAP_BIT, also use it at the other sites which open-code that pair, so the intent is stated rather than the flags, with no functional change: zap_special_vma_range() only zaps kernel-owned mappings, as drivers use it to tear down ranges they established themselves. The mprotect() arch PFN modification check applies to kernel-owned mappings, which may map PFNs without struct pages. NUMA balancing skips VM_MIXEDMAP mappings having already excluded VM_IO and VM_PFNMAP mappings via vma_migratable(), so it skips exactly the kernel-owned mappings - say so. Finally, update the VMA userland merge 'special' flag tests to no longer assert that VMA_IO_BIT prevents merge as VMA_PFNMAP_BIT, VMA_MIXEDMAP_BIT now suffices. Signed-off-by: Lorenzo Stoakes (ARM) <ljs@kernel.org> --- include/linux/mm.h | 3 +-- kernel/sched/fair.c | 2 +- mm/memory.c | 6 +++--- mm/mprotect.c | 3 +-- mm/vma.c | 2 +- tools/testing/vma/include/dup.h | 3 +-- tools/testing/vma/tests/merge.c | 10 ++-------- 7 files changed, 10 insertions(+), 19 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ca598e5f9715..4b6aa0b47b00 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h@@ -1630,8 +1630,7 @@ static inline bool vma_is_shared_maywrite(const struct vm_area_struct *vma) */ static inline bool vma_flags_is_kernel_owned(const vma_flags_t *flags) { - return vma_flags_test_any(flags, VMA_PFNMAP_BIT, VMA_MIXEDMAP_BIT, - VMA_IO_BIT); + return vma_flags_test_any(flags, VMA_PFNMAP_BIT, VMA_MIXEDMAP_BIT); } /**
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8dff37059faf..a71f0ab79bcd 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c@@ -4212,7 +4212,7 @@ static void task_numa_work(struct callback_head *work) for (; vma; vma = vma_next(&vmi)) { if (!vma_migratable(vma) || !vma_policy_mof(vma) || - is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) { + is_vm_hugetlb_page(vma) || vma_is_kernel_owned(vma)) { trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_UNSUITABLE); continue; }
diff --git a/mm/memory.c b/mm/memory.c
index 45b21bb04a18..1e6cd2e50408 100644
--- a/mm/memory.c
+++ b/mm/memory.c@@ -2343,19 +2343,19 @@ void zap_vma_range(struct vm_area_struct *vma, unsigned long address, } /** - * zap_special_vma_range - zap all page table entries in a special vma range + * zap_special_vma_range - zap all page table entries in a kernel-owned VMA * @vma: the vma covering the range to zap * @address: starting address of the range to zap * @size: number of bytes to zap * * This function does nothing when the provided address range is not fully - * contained in @vma, or when the @vma is not VM_PFNMAP or VM_MIXEDMAP. + * contained in @vma, or when @vma is not kernel-owned. */ void zap_special_vma_range(struct vm_area_struct *vma, unsigned long address, unsigned long size) { if (!range_in_vma(vma, address, address + size) || - !(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))) + !vma_is_kernel_owned(vma)) return; zap_vma_range(vma, address, size);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 2888ee638d87..fe32fd87cf5c 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c@@ -783,8 +783,7 @@ mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb, * uncommon case, so doesn't need to be very optimized. */ if (arch_has_pfn_modify_check() && - vma_flags_test_any(&old_vma_flags, VMA_PFNMAP_BIT, - VMA_MIXEDMAP_BIT) && + vma_flags_is_kernel_owned(&old_vma_flags) && !vma_flags_test_any_mask(&new_vma_flags, VMA_ACCESS_FLAGS)) { pgprot_t new_pgprot = vm_get_page_prot(newflags);
diff --git a/mm/vma.c b/mm/vma.c
index 56a0cd154419..0bc3651abe13 100644
--- a/mm/vma.c
+++ b/mm/vma.c@@ -2787,7 +2787,7 @@ static int mmap_validate_vma_flags(const vma_flags_t *flags) return -EINVAL; #endif - if (!vma_flags_test_any(flags, VMA_PFNMAP_BIT, VMA_MIXEDMAP_BIT)) { + if (!vma_flags_is_kernel_owned(flags)) { /* Only kernel-owned mappings may set VMA_IO_BIT. */ if (WARN_ON_ONCE(vma_flags_test(flags, VMA_IO_BIT))) return -EINVAL;
diff --git a/tools/testing/vma/include/dup.h b/tools/testing/vma/include/dup.h
index b8b1462ca710..97d3bf6cd5b7 100644
--- a/tools/testing/vma/include/dup.h
+++ b/tools/testing/vma/include/dup.h@@ -1667,8 +1667,7 @@ static inline bool file_is_dev_zero(const struct file *file) static inline bool vma_flags_is_kernel_owned(const vma_flags_t *flags) { - return vma_flags_test_any(flags, VMA_PFNMAP_BIT, VMA_MIXEDMAP_BIT, - VMA_IO_BIT); + return vma_flags_test_any(flags, VMA_PFNMAP_BIT, VMA_MIXEDMAP_BIT); } static inline bool vma_is_kernel_owned(const struct vm_area_struct *vma)
diff --git a/tools/testing/vma/tests/merge.c b/tools/testing/vma/tests/merge.c
index acaab282939c..b26f1a66a170 100644
--- a/tools/testing/vma/tests/merge.c
+++ b/tools/testing/vma/tests/merge.c@@ -496,17 +496,11 @@ static bool test_vma_merge_special_flags(void) .mm = &mm, .vmi = &vmi, }; - vma_flag_t special_flags[] = { VMA_IO_BIT, VMA_DONTEXPAND_BIT, + vma_flag_t special_flags[] = { VMA_DONTEXPAND_BIT, VMA_PFNMAP_BIT, VMA_MIXEDMAP_BIT }; - vma_flags_t all_special_flags = EMPTY_VMA_FLAGS; int i; struct vm_area_struct *vma_left, *vma; - /* Make sure there aren't new VM_SPECIAL flags. */ - for (i = 0; i < ARRAY_SIZE(special_flags); i++) - vma_flags_set(&all_special_flags, special_flags[i]); - ASSERT_FLAGS_SAME_MASK(&all_special_flags, VMA_SPECIAL_FLAGS); - /* * 01234 * AAA
@@ -520,7 +514,7 @@ static bool test_vma_merge_special_flags(void) * 01234 * AAA* * - * This should merge if not for the VM_SPECIAL flag. + * This should merge if not for the 'special' flag. */ vmg_set_range(&vmg, 0x3000, 0x4000, 3, vma_flags); for (i = 0; i < ARRAY_SIZE(special_flags); i++) {
--
2.55.0