Proxmox-Port/linux
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git synced 2025-08-17 16:07:29 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

mm/huge_memory: add vmf_insert_folio_pud()

Browse Source 
Currently DAX folio/page reference counts are managed differently to
normal pages.  To allow these to be managed the same as normal pages
introduce vmf_insert_folio_pud.  This will map the entire PUD-sized folio
and take references as it would for a normally mapped page.

This is distinct from the current mechanism, vmf_insert_pfn_pud, which
simply inserts a special devmap PUD entry into the page table without
holding a reference to the page for the mapping.

Link: https://lkml.kernel.org/r/649a1ef91d556593948351e94f51ef73a14f6794.1740713401.git-series.apopple@nvidia.com
Signed-off-by: Alistair Popple <apopple@nvidia.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: David Hildenbrand <david@redhat.com>
Tested-by: Alison Schofield <alison.schofield@intel.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Asahi Lina <lina@asahilina.net>
Cc: Balbir Singh <balbirs@nvidia.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Chunyan Zhang <zhang.lyra@gmail.com>
Cc: "Darrick J. Wong" <djwong@kernel.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: linmiaohe <linmiaohe@huawei.com>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: Matthew Wilcow (Oracle) <willy@infradead.org>
Cc: Michael "Camp Drill Sergeant" Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Ted Ts'o <tytso@mit.edu>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: WANG Xuerui <kernel@xen0n.name>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Alistair Popple 2025-02-28 14:31:10 +11:00 committed by Andrew Morton
parent 349994cf61
commit dbe5415329
2 changed files with 89 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
include/linux/huge_mm.h
View File

@ -39,6 +39,8 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write);
vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write);
vm_fault_t vmf_insert_folio_pud(struct vm_fault *vmf, struct folio *folio,
bool write);
enum transparent_hugepage_flag {
TRANSPARENT_HUGEPAGE_UNSUPPORTED,

99
mm/huge_memory.c
View File

@ -1482,19 +1482,17 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
struct mm_struct *mm = vma->vm_mm;
pgprot_t prot = vma->vm_page_prot;
pud_t entry;
spinlock_t *ptl;
ptl = pud_lock(mm, pud);
if (!pud_none(*pud)) {
if (write) {
if (WARN_ON_ONCE(pud_pfn(*pud) != pfn_t_to_pfn(pfn)))
goto out_unlock;
return;
entry = pud_mkyoung(*pud);
entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma);
if (pudp_set_access_flags(vma, addr, pud, entry, 1))
update_mmu_cache_pud(vma, addr, pud);
}
goto out_unlock;
return;
}
entry = pud_mkhuge(pfn_t_pud(pfn, prot));
@ -1508,9 +1506,6 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
}
set_pud_at(mm, addr, pud, entry);
update_mmu_cache_pud(vma, addr, pud);
out_unlock:
spin_unlock(ptl);
}
/**
@ -1528,6 +1523,7 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
unsigned long addr = vmf->address & PUD_MASK;
struct vm_area_struct *vma = vmf->vma;
pgprot_t pgprot = vma->vm_page_prot;
spinlock_t *ptl;
/*
* If we had pud_special, we could avoid all these restrictions,
@ -1545,10 +1541,57 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
track_pfn_insert(vma, &pgprot, pfn);
ptl = pud_lock(vma->vm_mm, vmf->pud);
insert_pfn_pud(vma, addr, vmf->pud, pfn, write);
spin_unlock(ptl);
return VM_FAULT_NOPAGE;
}
EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud);
/**
* vmf_insert_folio_pud - insert a pud size folio mapped by a pud entry
* @vmf: Structure describing the fault
* @folio: folio to insert
* @write: whether it's a write fault
*
* Return: vm_fault_t value.
*/
vm_fault_t vmf_insert_folio_pud(struct vm_fault *vmf, struct folio *folio,
bool write)
{
struct vm_area_struct *vma = vmf->vma;
unsigned long addr = vmf->address & PUD_MASK;
pud_t *pud = vmf->pud;
struct mm_struct *mm = vma->vm_mm;
spinlock_t *ptl;
if (addr < vma->vm_start || addr >= vma->vm_end)
return VM_FAULT_SIGBUS;
if (WARN_ON_ONCE(folio_order(folio) != PUD_ORDER))
return VM_FAULT_SIGBUS;
ptl = pud_lock(mm, pud);
/*
* If there is already an entry present we assume the folio is
* already mapped, hence no need to take another reference. We
* still call insert_pfn_pud() though in case the mapping needs
* upgrading to writeable.
*/
if (pud_none(*vmf->pud)) {
folio_get(folio);
folio_add_file_rmap_pud(folio, &folio->page, vma);
add_mm_counter(mm, mm_counter_file(folio), HPAGE_PUD_NR);
}
insert_pfn_pud(vma, addr, vmf->pud, pfn_to_pfn_t(folio_pfn(folio)),
write);
spin_unlock(ptl);
return VM_FAULT_NOPAGE;
}
EXPORT_SYMBOL_GPL(vmf_insert_folio_pud);
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
@ -2146,7 +2189,8 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
zap_deposited_table(tlb->mm, pmd);
spin_unlock(ptl);
} else if (is_huge_zero_pmd(orig_pmd)) {
zap_deposited_table(tlb->mm, pmd);
if (!vma_is_dax(vma) || arch_needs_pgtable_deposit())
zap_deposited_table(tlb->mm, pmd);
spin_unlock(ptl);
} else {
struct folio *folio = NULL;
@ -2646,12 +2690,24 @@ int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
orig_pud = pudp_huge_get_and_clear_full(vma, addr, pud, tlb->fullmm);
arch_check_zapped_pud(vma, orig_pud);
tlb_remove_pud_tlb_entry(tlb, pud, addr);
if (vma_is_special_huge(vma)) {
if (!vma_is_dax(vma) && vma_is_special_huge(vma)) {
spin_unlock(ptl);
/* No zero page support yet */
} else {
/* No support for anonymous PUD pages yet */
BUG();
struct page *page = NULL;
struct folio *folio;
/* No support for anonymous PUD pages or migration yet */
VM_WARN_ON_ONCE(vma_is_anonymous(vma) ||
!pud_present(orig_pud));
page = pud_page(orig_pud);
folio = page_folio(page);
folio_remove_rmap_pud(folio, page, vma);
add_mm_counter(tlb->mm, mm_counter_file(folio), -HPAGE_PUD_NR);
spin_unlock(ptl);
tlb_remove_page_size(tlb, page, HPAGE_PUD_SIZE);
}
return 1;
}
@ -2659,6 +2715,10 @@ int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud,
unsigned long haddr)
{
struct folio *folio;
struct page *page;
pud_t old_pud;
VM_BUG_ON(haddr & ~HPAGE_PUD_MASK);
VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma);
@ -2666,7 +2726,22 @@ static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud,
count_vm_event(THP_SPLIT_PUD);
pudp_huge_clear_flush(vma, haddr, pud);
old_pud = pudp_huge_clear_flush(vma, haddr, pud);
if (!vma_is_dax(vma))
return;
page = pud_page(old_pud);
folio = page_folio(page);
if (!folio_test_dirty(folio) && pud_dirty(old_pud))
folio_mark_dirty(folio);
if (!folio_test_referenced(folio) && pud_young(old_pud))
folio_set_referenced(folio);
folio_remove_rmap_pud(folio, page, vma);
folio_put(folio);
add_mm_counter(vma->vm_mm, mm_counter_file(folio),
-HPAGE_PUD_NR);
}
void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,