Re: [PATCH v5 05/26] mm/swap: Introduce the idea of special swap ptes
From: Alistair Popple <apopple@nvidia.com>
Date: 2021-07-16 05:51:26
Also in:
lkml
Hi Peter, [...]
quoted hunk ↗ jump to hunk
diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ae1f5d0cb581..4b46c099ad94 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c@@ -5738,7 +5738,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, if (pte_present(ptent)) page = mc_handle_present_pte(vma, addr, ptent); - else if (is_swap_pte(ptent)) + else if (pte_has_swap_entry(ptent)) page = mc_handle_swap_pte(vma, ptent, &ent); else if (pte_none(ptent)) page = mc_handle_file_pte(vma, addr, ptent, &ent);
As I understand things pte_none() == False for a special swap pte, but shouldn't this be treated as pte_none() here? Ie. does this need to be pte_none(ptent) || is_swap_special_pte() here?
quoted hunk ↗ jump to hunk
diff --git a/mm/memory.c b/mm/memory.c index 0e0de08a2cd5..998a4f9a3744 100644 --- a/mm/memory.c +++ b/mm/memory.c@@ -3491,6 +3491,13 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (!pte_unmap_same(vmf)) goto out; + /* + * We should never call do_swap_page upon a swap special pte; just be + * safe to bail out if it happens. + */ + if (WARN_ON_ONCE(is_swap_special_pte(vmf->orig_pte))) + goto out; + entry = pte_to_swp_entry(vmf->orig_pte); if (unlikely(non_swap_entry(entry))) { if (is_migration_entry(entry)) {
Are there other changes required here? Because we can end up with stale special pte's and a special pte is !pte_none don't we need to fix some of the !pte_none checks in these functions: insert_pfn() -> checks for !pte_none remap_pte_range() -> BUG_ON(!pte_none) apply_to_pte_range() -> didn't check further but it tests for !pte_none In general it feels like I might be missing something here though. There are plenty of checks in the kernel for pte_none() which haven't been updated. Is there some rule that says none of those paths can see a special pte?
quoted hunk ↗ jump to hunk
diff --git a/mm/migrate.c b/mm/migrate.c index 23cbd9de030b..b477d0d5f911 100644 --- a/mm/migrate.c +++ b/mm/migrate.c@@ -294,7 +294,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spin_lock(ptl); pte = *ptep; - if (!is_swap_pte(pte)) + if (!pte_has_swap_entry(pte)) goto out; entry = pte_to_swp_entry(pte);@@ -2276,7 +2276,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp, pte = *ptep; - if (pte_none(pte)) { + if (pte_none(pte) || is_swap_special_pte(pte)) {
I was wondering if we can loose the special pte information here? However I see
that in migrate_vma_insert_page() we check again and fail the migration if
!pte_none() so I think this is ok.
I think it would be better if this check was moved below so the migration fails
early. Ie:
if (pte_none(pte)) {
if (vma_is_anonymous(vma) && !is_swap_special_pte(pte)) {
Also how does this work for page migration in general? I can see in
page_vma_mapped_walk() that we skip special pte's, but doesn't this mean we
loose the special pte in that instance? Or is that ok for some reason?
quoted hunk ↗ jump to hunk
if (vma_is_anonymous(vma)) { mpfn = MIGRATE_PFN_MIGRATE; migrate->cpages++;diff --git a/mm/mincore.c b/mm/mincore.c index 9122676b54d6..5728c3e6473f 100644 --- a/mm/mincore.c +++ b/mm/mincore.c@@ -121,7 +121,7 @@ static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, for (; addr != end; ptep++, addr += PAGE_SIZE) { pte_t pte = *ptep; - if (pte_none(pte)) + if (pte_none(pte) || is_swap_special_pte(pte)) __mincore_unmapped_range(addr, addr + PAGE_SIZE, vma, vec); else if (pte_present(pte))diff --git a/mm/mprotect.c b/mm/mprotect.c index 883e2cc85cad..4b743394afbe 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c@@ -139,7 +139,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, } ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent); pages++; - } else if (is_swap_pte(oldpte)) { + } else if (pte_has_swap_entry(oldpte)) { swp_entry_t entry = pte_to_swp_entry(oldpte); pte_t newpte;diff --git a/mm/mremap.c b/mm/mremap.c index 5989d3990020..122b279333ee 100644 --- a/mm/mremap.c +++ b/mm/mremap.c@@ -125,7 +125,7 @@ static pte_t move_soft_dirty_pte(pte_t pte) #ifdef CONFIG_MEM_SOFT_DIRTY if (pte_present(pte)) pte = pte_mksoft_dirty(pte); - else if (is_swap_pte(pte)) + else if (pte_has_swap_entry(pte)) pte = pte_swp_mksoft_dirty(pte); #endif return pte;diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index f7b331081791..ff57b67426af 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c@@ -36,7 +36,7 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw) * For more details on device private memory see HMM * (include/linux/hmm.h or mm/hmm.c). */ - if (is_swap_pte(*pvmw->pte)) { + if (pte_has_swap_entry(*pvmw->pte)) { swp_entry_t entry; /* Handle un-addressable ZONE_DEVICE memory */@@ -90,7 +90,7 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw) if (pvmw->flags & PVMW_MIGRATION) { swp_entry_t entry; - if (!is_swap_pte(*pvmw->pte)) + if (!pte_has_swap_entry(*pvmw->pte)) return false; entry = pte_to_swp_entry(*pvmw->pte);@@ -99,7 +99,7 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw) return false; pfn = swp_offset(entry); - } else if (is_swap_pte(*pvmw->pte)) { + } else if (pte_has_swap_entry(*pvmw->pte)) { swp_entry_t entry; /* Handle un-addressable ZONE_DEVICE memory */diff --git a/mm/swapfile.c b/mm/swapfile.c index 1e07d1c776f2..4993b4454c13 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c@@ -1951,7 +1951,7 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, si = swap_info[type]; pte = pte_offset_map(pmd, addr); do { - if (!is_swap_pte(*pte)) + if (!pte_has_swap_entry(*pte)) continue; entry = pte_to_swp_entry(*pte);