[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <f610e933-278e-4f95-a363-8f023a5e7aa9@redhat.com>
Date: Wed, 11 Sep 2024 11:27:23 +0200
From: David Hildenbrand <david@...hat.com>
To: Dev Jain <dev.jain@....com>, akpm@...ux-foundation.org,
willy@...radead.org, kirill.shutemov@...ux.intel.com
Cc: ryan.roberts@....com, anshuman.khandual@....com, catalin.marinas@....com,
cl@...two.org, vbabka@...e.cz, mhocko@...e.com, apopple@...dia.com,
dave.hansen@...ux.intel.com, will@...nel.org, baohua@...nel.org,
jack@...e.cz, mark.rutland@....com, hughd@...gle.com,
aneesh.kumar@...nel.org, yang@...amperecomputing.com, peterx@...hat.com,
ioworker0@...il.com, jglisse@...gle.com, wangkefeng.wang@...wei.com,
ziy@...dia.com, linux-arm-kernel@...ts.infradead.org,
linux-kernel@...r.kernel.org, linux-mm@...ck.org
Subject: Re: [PATCH v3 1/2] mm: Abstract THP allocation
On 11.09.24 08:55, Dev Jain wrote:
> In preparation for the second patch, abstract away the THP allocation
> logic present in the create_huge_pmd() path, which corresponds to the
> faulting case when no page is present.
>
> There should be no functional change as a result of applying
> this patch.
>
Hi,
> Signed-off-by: Dev Jain <dev.jain@....com>
> ---
> mm/huge_memory.c | 110 +++++++++++++++++++++++++++++------------------
> 1 file changed, 67 insertions(+), 43 deletions(-)
>
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index 67c86a5d64a6..b96a1ff2bf40 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -943,47 +943,88 @@ unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
> }
> EXPORT_SYMBOL_GPL(thp_get_unmapped_area);
>
> -static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
> - struct page *page, gfp_t gfp)
> +static struct folio *pmd_thp_fault_alloc(gfp_t gfp, struct vm_area_struct *vma,
> + unsigned long haddr, unsigned long addr)
I suggest calling this something like "vma_alloc_anon_folio_pmd()"? Then
it's more consistent with vma_alloc_folio().
Also, likely we should just only pass in "addr" and calculate "haddr"
ourselves, it's cheap and reduces the number of function parameters.
> {
> - struct vm_area_struct *vma = vmf->vma;
> - struct folio *folio = page_folio(page);
> - pgtable_t pgtable;
> - unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
> - vm_fault_t ret = 0;
> + const int order = HPAGE_PMD_ORDER;
> + struct folio *folio = vma_alloc_folio(gfp, order, vma, haddr, true);
>
> - VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
> + if (unlikely(!folio)) {
> + count_vm_event(THP_FAULT_FALLBACK);
> + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK);
> + goto out;
> + }
>
> + VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
> if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) {
> folio_put(folio);
> count_vm_event(THP_FAULT_FALLBACK);
> count_vm_event(THP_FAULT_FALLBACK_CHARGE);
> - count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK);
> - count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
> - return VM_FAULT_FALLBACK;
> + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK);
> + count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
> + goto out;
> }
> folio_throttle_swaprate(folio, gfp);
>
> - pgtable = pte_alloc_one(vma->vm_mm);
> - if (unlikely(!pgtable)) {
> - ret = VM_FAULT_OOM;
> - goto release;
> - }
> -
> - folio_zero_user(folio, vmf->address);
> + folio_zero_user(folio, addr);
> /*
> * The memory barrier inside __folio_mark_uptodate makes sure that
> * folio_zero_user writes become visible before the set_pmd_at()
> * write.
> */
> __folio_mark_uptodate(folio);
> +out:
> + return folio;
> +}
> +
> +static void __pmd_thp_fault_success_stats(struct vm_area_struct *vma)
> +{
> + count_vm_event(THP_FAULT_ALLOC);
> + count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC);
> + count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC);
> +}
Why isn't that moved into map_pmd_thp()
Note that in this patch you do:
map_pmd_thp(folio, vmf, vma, haddr);
spin_unlock(vmf->ptl);
__pmd_thp_fault_success_stats(vma);
But in patch #2
map_pmd_thp(folio, vmf, vma, haddr);
__pmd_thp_fault_success_stats(vma);
goto unlock;
release:
folio_put(folio);
unlock:
spin_unlock(vmf->ptl);
Please make that consistent, meaning:
1) Inline __pmd_thp_fault_success_stats() into map_pmd_thp(). No need to
have the separated out.
2) Either do the PTL unlocking in __pmd_thp_fault_success_stats() or in
the caller. In the caller is likely easiest. Adjusting the counters
should be cheap, if not we could revisit this later with real data.
> +
> +static void map_pmd_thp(struct folio *folio, struct vm_fault *vmf,
> + struct vm_area_struct *vma, unsigned long haddr)
> +{
> + pmd_t entry;
> +
> + entry = mk_huge_pmd(&folio->page, vma->vm_page_prot);
> + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
> + folio_add_new_anon_rmap(folio, vma, haddr, RMAP_EXCLUSIVE);
> + folio_add_lru_vma(folio, vma);
> + set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry);
> + update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
It's quite weird to see a mixture of haddr and vmf->address, and likely
this mixture is wrong or not not required.
Looking at arc's update_mmu_cache_pmd() implementation, I cannot see how
passing in the unaligned address would do the right thing. But maybe arc
also doesn't trigger that code path ... who knows :)
Staring at some other update_mmu_cache_pmd() users, it's quite
inconsistent. Primarily only do_huge_pmd_numa_page() and
__do_huge_pmd_anonymous_page() use the unaligned address. The others
seem to use the aligned address ... as one would expect when modifying a
PMD.
I suggest to change this function to *not* pass in the vmf, and rename
it to something like:
static void folio_map_anon_pmd(struct folio *folio, struct
vm_area_struct *vma, pmd_t *pmd, unsigned long haddr)
Then use haddr also to do the update_mmu_cache_pmd().
> + add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
> + mm_inc_nr_ptes(vma->vm_mm);
> +}
> +
> +static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf)
> +{
> + struct vm_area_struct *vma = vmf->vma;
> + struct folio *folio;
> + pgtable_t pgtable;
> + unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
> + vm_fault_t ret = 0;
> + gfp_t gfp = vma_thp_gfp_mask(vma);
Nit: While at it, try to use reverse christmas-tree where possible,
makes things more reasible. You could make haddr const.
struct vm_area_struct *vma = vmf->vma;
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
gfp_t gfp = vma_thp_gfp_mask(vma);
struct folio *folio;
vm_fault_t ret = 0;
...
> +
> + folio = pmd_thp_fault_alloc(gfp, vma, haddr, vmf->address);
> + if (unlikely(!folio)) {
> + ret = VM_FAULT_FALLBACK;
> + goto release;
> + }
> +
> + pgtable = pte_alloc_one(vma->vm_mm);
> + if (unlikely(!pgtable)) {
> + ret = VM_FAULT_OOM;
> + goto release;
> + }
>
> vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
> +
Nit Unrelated change.
> if (unlikely(!pmd_none(*vmf->pmd))) {
> goto unlock_release;
--
Cheers,
David / dhildenb
Powered by blists - more mailing lists