| Message ID | 63c92f1e2a2fa6267490ab9fad5b090316b39b98.1730360798.git.zhengqi.arch@bytedance.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | synchronously scan and reclaim empty user PTE pages | expand |
On Thu, Oct 31, 2024 at 9:14 AM Qi Zheng <zhengqi.arch@bytedance.com> wrote: > In preparation for reclaiming empty PTE pages, this commit first makes > zap_pte_range() to handle the full within-PMD range, so that we can more > easily detect and free PTE pages in this function in subsequent commits. > > Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Reviewed-by: Jann Horn <jannh@google.com>
diff --git a/mm/memory.c b/mm/memory.c index c1150e62dd073..002aa4f454fa0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1691,6 +1691,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, pte_t *pte; int nr; +retry: tlb_change_page_size(tlb, PAGE_SIZE); init_rss_vec(rss); start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); @@ -1730,6 +1731,13 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, if (force_flush) tlb_flush_mmu(tlb); + if (addr != end) { + cond_resched(); + force_flush = false; + force_break = false; + goto retry; + } + return addr; }
In preparation for reclaiming empty PTE pages, this commit first makes zap_pte_range() to handle the full within-PMD range, so that we can more easily detect and free PTE pages in this function in subsequent commits. Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> --- mm/memory.c | 8 ++++++++ 1 file changed, 8 insertions(+)