| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <6c2c4e04-13da-4072-8d63-d9bea0168214@bytedance.com>
Date: Thu, 14 Nov 2024 11:09:04 +0800
From: Qi Zheng <zhengqi.arch@...edance.com>
To: David Hildenbrand <david@...hat.com>
Cc: jannh@...gle.com, hughd@...gle.com, willy@...radead.org, mgorman@...e.de,
muchun.song@...ux.dev, vbabka@...nel.org, akpm@...ux-foundation.org,
zokeefe@...gle.com, rientjes@...gle.com, peterx@...hat.com,
catalin.marinas@....com, linux-mm@...ck.org, linux-kernel@...r.kernel.org,
x86@...nel.org
Subject: Re: [PATCH v2 3/7] mm: introduce do_zap_pte_range()
On 2024/11/13 19:43, David Hildenbrand wrote:
> On 13.11.24 03:40, Qi Zheng wrote:
>>
>>
>> On 2024/11/13 01:00, David Hildenbrand wrote:
>>> On 31.10.24 09:13, Qi Zheng wrote:
>>>> This commit introduces do_zap_pte_range() to actually zap the PTEs,
>>>> which
>>>> will help improve code readability and facilitate secondary checking of
>>>> the processed PTEs in the future.
>>>>
>>>> No functional change.
>>>>
>>>> Signed-off-by: Qi Zheng <zhengqi.arch@...edance.com>
>>>> ---
>>>> mm/memory.c | 45 ++++++++++++++++++++++++++-------------------
>>>> 1 file changed, 26 insertions(+), 19 deletions(-)
>>>>
>>>> diff --git a/mm/memory.c b/mm/memory.c
>>>> index bd9ebe0f4471f..c1150e62dd073 100644
>>>> --- a/mm/memory.c
>>>> +++ b/mm/memory.c
>>>> @@ -1657,6 +1657,27 @@ static inline int zap_nonpresent_ptes(struct
>>>> mmu_gather *tlb,
>>>> return nr;
>>>> }
>>>> +static inline int do_zap_pte_range(struct mmu_gather *tlb,
>>>> + struct vm_area_struct *vma, pte_t *pte,
>>>> + unsigned long addr, unsigned long end,
>>>> + struct zap_details *details, int *rss,
>>>> + bool *force_flush, bool *force_break)
>>>> +{
>>>> + pte_t ptent = ptep_get(pte);
>>>> + int max_nr = (end - addr) / PAGE_SIZE;
>>>> +
>>>> + if (pte_none(ptent))
>>>> + return 1;
>>>
>>> Maybe we should just skip all applicable pte_none() here directly.
>>
>> Do you mean we should keep pte_none() case in zap_pte_range()? Like
>> below:
>>
>
> No rather an addon patch that will simply skip over all
> consecutive pte_none, like:
>
> if (pte_none(ptent)) {
> int nr;
>
> for (nr = 1; nr < max_nr; nr++) {
> ptent = ptep_get(pte + nr);
> if (pte_none(ptent))
> continue;
> }
>
> max_nr -= nr;
> if (!max_nr)
> return nr;
> addr += nr * PAGE_SIZE;
> pte += nr;
> }
I tend to hand over the pte/addr increments here to the loop
outside do_zap_pte_range(), like this:
diff --git a/mm/memory.c b/mm/memory.c
index bd9ebe0f4471f..2367a1c19edd6 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1657,6 +1657,36 @@ static inline int zap_nonpresent_ptes(struct
mmu_gather *tlb,
return nr;
}
+static inline int do_zap_pte_range(struct mmu_gather *tlb,
+ struct vm_area_struct *vma, pte_t *pte,
+ unsigned long addr, unsigned long end,
+ struct zap_details *details, int *rss,
+ bool *force_flush, bool *force_break)
+{
+ pte_t ptent = ptep_get(pte);
+ int max_nr = (end - addr) / PAGE_SIZE;
+
+ if (pte_none(ptent)) {
+ int nr = 1;
+
+ for (; nr < max_nr; nr++) {
+ ptent = ptep_get(pte + nr);
+ if (!pte_none(ptent))
+ break;
+ }
+
+ return nr;
+ }
+
+ if (pte_present(ptent))
+ return zap_present_ptes(tlb, vma, pte, ptent, max_nr,
+ addr, details, rss, force_flush,
+ force_break);
+
+ return zap_nonpresent_ptes(tlb, vma, pte, ptent, max_nr, addr,
+ details, rss);
+}
+
static unsigned long zap_pte_range(struct mmu_gather *tlb,
struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end,
@@ -1679,28 +1709,14 @@ static unsigned long zap_pte_range(struct
mmu_gather *tlb,
flush_tlb_batched_pending(mm);
arch_enter_lazy_mmu_mode();
do {
- pte_t ptent = ptep_get(pte);
- int max_nr;
-
- nr = 1;
- if (pte_none(ptent))
- continue;
-
if (need_resched())
break;
- max_nr = (end - addr) / PAGE_SIZE;
- if (pte_present(ptent)) {
- nr = zap_present_ptes(tlb, vma, pte, ptent, max_nr,
- addr, details, rss,
&force_flush,
- &force_break);
- if (unlikely(force_break)) {
- addr += nr * PAGE_SIZE;
- break;
- }
- } else {
- nr = zap_nonpresent_ptes(tlb, vma, pte, ptent,
max_nr,
- addr, details, rss);
+ nr = do_zap_pte_range(tlb, vma, pte, addr, end, details,
+ rss, &force_flush, &force_break);
+ if (unlikely(force_break)) {
+ addr += nr * PAGE_SIZE;
+ break;
}
} while (pte += nr, addr += PAGE_SIZE * nr, addr != end);
>
> Assuming that it's likely more common to have larger pte_none() holes
> that single ones, optimizing out the
> need_resched()+force_break+incremental pte/addr increments etc.
>
Powered by blists - more mailing lists