Re: [PATCH v5 06/11] mm/vmalloc: undo what vmap_page_range() mapped on failure
From: Suren Baghdasaryan
Date: Fri Nov 20 2026 - 17:30:20 EST
On Mon, Nov 16, 2026 at 7:14 AM Hao Ge <hao.ge@xxxxxxxxx> wrote:
>
> ioremap and arch setup code map their ranges with vmap_page_range().
> When the walk fails half way, or the KMSAN metadata fails after the
> walk, the ptes installed so far stay behind. The caller frees the
> vm_area on the error path, so the next mapping that lands on the same
> range trips the BUG() in vmap_pte_range().
>
> vmap_range_noflush() now takes a mapped_end argument that the walk
> levels advance as they install, and vmap_pte_range() BUG()s before
> it installs over a pte that is already set. The ptes below mapped_end
> are therefore all ours, while a pte above it can only have been put
> there by somebody else, for example when the caller's range overlaps
> an existing mapping. On a walk failure the undo is limited to
> [addr, mapped_end), going further would clear ptes that are not
> ours. If the walk completed and only the KMSAN metadata failed, the
> whole range was installed by this call and all of it is undone.
>
> All callers are sleepable, the teardown passes can_resched = true.
>
> Signed-off-by: Hao Ge <hao.ge@xxxxxxxxx>
> ---
> mm/vmalloc.c | 52 +++++++++++++++++++++++++++++++++++++++-------------
> 1 file changed, 39 insertions(+), 13 deletions(-)
>
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index d99d7710e1ba..5c1eacc2a0ac 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -117,7 +117,8 @@ static __always_inline unsigned long vmap_set_ptes(pte_t *ptep,
>
> static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
> phys_addr_t phys_addr, pgprot_t prot,
> - unsigned int max_page_shift, pgtbl_mod_mask *mask)
> + unsigned int max_page_shift, pgtbl_mod_mask *mask,
> + unsigned long *mapped_end)
> {
> pte_t *pte;
> u64 pfn;
> @@ -143,6 +144,7 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
>
> size = vmap_set_ptes(pte, addr, end, pfn, prot, max_page_shift);
> nr_pages = PFN_DOWN(size);
> + *mapped_end = addr + size;
> } while (pte += nr_pages, pfn += nr_pages, addr += size, addr != end);
>
> lazy_mmu_mode_disable();
> @@ -188,7 +190,8 @@ static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long end,
>
> static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
> phys_addr_t phys_addr, pgprot_t prot,
> - unsigned int max_page_shift, pgtbl_mod_mask *mask)
> + unsigned int max_page_shift, pgtbl_mod_mask *mask,
> + unsigned long *mapped_end)
> {
> pmd_t *pmd;
> unsigned long next;
> @@ -203,10 +206,12 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
> if (vmap_try_huge_pmd(pmd, addr, next, phys_addr, prot,
> max_page_shift)) {
> *mask |= PGTBL_PMD_MODIFIED;
> + *mapped_end = next;
> continue;
> }
>
> - err = vmap_pte_range(pmd, addr, next, phys_addr, prot, max_page_shift, mask);
> + err = vmap_pte_range(pmd, addr, next, phys_addr, prot,
> + max_page_shift, mask, mapped_end);
> if (err)
> break;
> } while (pmd++, phys_addr += (next - addr), addr = next, addr != end);
> @@ -245,7 +250,8 @@ static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end,
>
> static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
> phys_addr_t phys_addr, pgprot_t prot,
> - unsigned int max_page_shift, pgtbl_mod_mask *mask)
> + unsigned int max_page_shift, pgtbl_mod_mask *mask,
> + unsigned long *mapped_end)
> {
> pud_t *pud;
> unsigned long next;
> @@ -260,10 +266,12 @@ static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
> if (vmap_try_huge_pud(pud, addr, next, phys_addr, prot,
> max_page_shift)) {
> *mask |= PGTBL_PUD_MODIFIED;
> + *mapped_end = next;
> continue;
> }
>
> - err = vmap_pmd_range(pud, addr, next, phys_addr, prot, max_page_shift, mask);
> + err = vmap_pmd_range(pud, addr, next, phys_addr, prot,
> + max_page_shift, mask, mapped_end);
> if (err)
> break;
> } while (pud++, phys_addr += (next - addr), addr = next, addr != end);
> @@ -302,7 +310,8 @@ static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end,
>
> static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
> phys_addr_t phys_addr, pgprot_t prot,
> - unsigned int max_page_shift, pgtbl_mod_mask *mask)
> + unsigned int max_page_shift, pgtbl_mod_mask *mask,
> + unsigned long *mapped_end)
> {
> p4d_t *p4d;
> unsigned long next;
> @@ -317,10 +326,12 @@ static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
> if (vmap_try_huge_p4d(p4d, addr, next, phys_addr, prot,
> max_page_shift)) {
> *mask |= PGTBL_P4D_MODIFIED;
> + *mapped_end = next;
> continue;
> }
>
> - err = vmap_pud_range(p4d, addr, next, phys_addr, prot, max_page_shift, mask);
> + err = vmap_pud_range(p4d, addr, next, phys_addr, prot,
> + max_page_shift, mask, mapped_end);
> if (err)
> break;
> } while (p4d++, phys_addr += (next - addr), addr = next, addr != end);
> @@ -329,7 +340,7 @@ static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
>
> static int vmap_range_noflush(unsigned long addr, unsigned long end,
> phys_addr_t phys_addr, pgprot_t prot,
> - unsigned int max_page_shift)
> + unsigned int max_page_shift, unsigned long *mapped_end)
> {
> pgd_t *pgd;
> unsigned long start;
> @@ -346,11 +357,12 @@ static int vmap_range_noflush(unsigned long addr, unsigned long end,
> BUG_ON(addr >= end);
>
> start = addr;
> + *mapped_end = addr;
> pgd = pgd_offset_k(addr);
> do {
> next = pgd_addr_end(addr, end);
> err = vmap_p4d_range(pgd, addr, next, phys_addr, prot,
> - max_page_shift, &mask);
> + max_page_shift, &mask, mapped_end);
> if (err)
> break;
> } while (pgd++, phys_addr += (next - addr), addr = next, addr != end);
> @@ -364,18 +376,32 @@ static int vmap_range_noflush(unsigned long addr, unsigned long end,
> int vmap_page_range(unsigned long addr, unsigned long end,
> phys_addr_t phys_addr, pgprot_t prot)
> {
> + unsigned long mapped_end = addr;
> int err;
>
> if (WARN_ON_ONCE(!PAGE_ALIGNED(addr) || !PAGE_ALIGNED(end)))
> return -EINVAL;
>
> err = vmap_range_noflush(addr, end, phys_addr, pgprot_nx(prot),
> - ioremap_max_page_shift);
> - if (!err)
> + ioremap_max_page_shift, &mapped_end);
> + if (err) {
> + /* Undo the part the walk installed before it failed. */
> + if (mapped_end > addr)
> + __vunmap_range_noflush(addr, mapped_end, true);
> + } else {
> err = kmsan_ioremap_page_range(addr, end, phys_addr, prot,
> ioremap_max_page_shift);
> - if (!err)
> - flush_cache_vmap(addr, end);
> + if (err) {
> + /*
> + * Only the KMSAN metadata failed, the walk mapped
> + * the whole range. Undo it all. The callers are
> + * ioremap and arch setup code, always sleepable.
> + */
> + __vunmap_range_noflush(addr, end, true);
> + } else {
> + flush_cache_vmap(addr, end);
This again skips TLB flushing after __vunmap_range_noflush(). I'm not
sure that's ok even if there was no explicit access.
> + }
> + }
>
> return err;
> }
> --
> 2.25.1
>