From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 2115FC98310 for ; Thu, 24 Sep 2026 06:54:08 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 6889310F328; Thu, 24 Sep 2026 06:54:07 +0000 (UTC) Authentication-Results: gabe.freedesktop.org; dkim=pass (1024-bit key; unprotected) header.d=redhat.com header.i=@redhat.com header.b="LdSpMSxR"; dkim-atps=neutral Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by gabe.freedesktop.org (Postfix) with ESMTPS id C55C010F328 for ; Thu, 24 Sep 2026 06:54:05 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1790232845; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=FpTd5JgQBNZxOTQ5E1xh4waIRSPVZay1TNJaxL2j0i8=; b=LdSpMSxRHC6sr2XcIZmndgi3ly8lnG0gd/TJ9QqeGArbFJ75qrZAo17xNDSFbfGPV758At D2rlaFhlqn9ifVsknn8qT8nsSXlYtPjUwfQrWcyhggXcGJNbcBAVT9ql6TAwgNLBLWbw+k 7Va84Jb1nlh4+oj/hRv4cGLyk7C2eQA= Received: from mail-lj1-f198.google.com (mail-lj1-f198.google.com [209.85.208.198]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-2-8cRSmzT5Pea4kg4idPPpDQ-1; Thu, 24 Sep 2026 02:54:03 -0400 X-MC-Unique: 8cRSmzT5Pea4kg4idPPpDQ-1 X-Mimecast-MFC-AGG-ID: 8cRSmzT5Pea4kg4idPPpDQ_1790232842 Received: by mail-lj1-f198.google.com with SMTP id 38308e7fff4ca-3a3540f42beso8614751fa.2 for ; Wed, 23 Sep 2026 23:54:03 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20260707; t=1790232842; x=1790837642; h=content-transfer-encoding:content-type:mime-version:references :in-reply-to:message-id:date:subject:cc:to:from:x-gm-gg :x-gm-message-state:from:to:cc:subject:date:message-id:reply-to :content-type; bh=FpTd5JgQBNZxOTQ5E1xh4waIRSPVZay1TNJaxL2j0i8=; b=v61ieGhUJ9CnbLAm+A99av28H74W72ufaFb5t+XSmSxnD3860tHw8eAtriaoIXdOAo IcwlHTjGhBvhLuk+Mg4UzQPxiSQeCoHu2XtmaTG69cRrfxlrV6wEtCrWkPnGlHVXgKKW f7I7vsUO7G5HrYqjqp8/JcF6NIqtYvcbKlKqro67JjTcaXOxxKl+knZXlZC+Bv6VZZFi PBLGdLAn2rdpR0YLQRavufQ85TVsxFERohOC8kjcbUfdCVGFCpv287iVyHQyrEsi0phW Hsfe64KOk+JTV7nxMzJtFnUPsS+vFWnS4Ep7CzAUwys/LN83/F7CpIJIJoAkwY5ms1QF a4KA== X-Gm-Message-State: AFuF++lOlE7gEo15tNXzKVdGXM4we/lVmb8iAig6BAbClfKBMSgI5ehE bmCXDeUnn5payAFl5oVDS+tL/jjaxTy17Rar/tv/afJBnTcInUVpPgB/H9XOMid8i7NKZZBu3qY iW8qQ1R45EKcyQ1cyOnNYknPsgUQo+Glhyr20bfvr1Ge29SBWIAMirVxO6bttvpHDPZgk X-Gm-Gg: AYBFou1V+FYpNj6hQPQx6+Dh3ekVRgBUDMHT6JfAtRY3U2Wb7UmZ4RUn0cEY1ODQXe3 d+sYTFbiZXQejhq3KWidoX5odf9W37BcM0EWHdtG8du+bDZIc/GWTsiE8rWpAvmrkzcBmkXiRF/ Ax/qlhtmp6tPo0336NHAPhfpKQ0p3vwj6AgqM8mXzYpuG1WBXOu571dH8uJ6WcHUbRE525J/Ioe A3f8M3sxTniBJvjUH4WpXVBmBwcOu9yDicP1LBUw12MgvWc/i4c5+kGWsUfT5fYjYQ6HKYYrp8f +sY4aujqXpbAc57IoXc3ygRE98KMHb5HksbZ3Roq9xuSF0eKR9WFAD/7LJ/ONjAaAHkK5tMiXP0 3z2uAZvyEywffPgc59hOJ X-Received: by 2002:a05:651c:211b:b0:3a3:74b7:fc0c with SMTP id 38308e7fff4ca-3a63c4090b9mr3873551fa.24.1790232841668; Wed, 23 Sep 2026 23:54:01 -0700 (PDT) X-Received: by 2002:a05:651c:211b:b0:3a3:74b7:fc0c with SMTP id 38308e7fff4ca-3a63c4090b9mr3873461fa.24.1790232841170; Wed, 23 Sep 2026 23:54:01 -0700 (PDT) Received: from fedora (89-27-86-246.bb.dnainternet.fi. [89.27.86.246]) by smtp.gmail.com with ESMTPSA id 38308e7fff4ca-3a63bf57909sm4803141fa.29.2026.09.23.23.54.00 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 23 Sep 2026 23:54:00 -0700 (PDT) From: mpenttil@redhat.com To: linux-mm@kvack.org Cc: dri-devel@lists.freedesktop.org, intel-xe@lists.freedesktop.org, linux-kernel@vger.kernel.org, =?UTF-8?q?Mika=20Penttil=C3=A4?= , David Hildenbrand , Jason Gunthorpe , Leon Romanovsky , Alistair Popple , Balbir Singh , Zi Yan , Matthew Brost , Andrew Morton , Lorenzo Stoakes , "Liam R. Howlett" , Vlastimil Babka , Mike Rapoport , Suren Baghdasaryan , Michal Hocko Subject: [PATCH v15 08/11] mm/hmm: implement rollback for device page migration in HMM pagewalk Date: Thu, 24 Sep 2026 09:53:10 +0300 Message-ID: <20260924065313.899730-9-mpenttil@redhat.com> X-Mailer: git-send-email 2.55.0 In-Reply-To: <20260924065313.899730-1-mpenttil@redhat.com> References: <20260924065313.899730-1-mpenttil@redhat.com> MIME-Version: 1.0 X-Mimecast-Spam-Score: 0 X-Mimecast-MFC-PROC-ID: 8_ZZBgYQB-4x8M6wwz_8J7zR6YEM2aZbTZXqsEtb_HM_1790232842 X-Mimecast-Originator: redhat.com Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit X-BeenThere: dri-devel@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Direct Rendering Infrastructure - Development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" From: Mika Penttilä During the migration pagewalk, the PTE table could be cleared and/or changed into PMD leaf or even another PTE table while dropped locks. In these cases the possibly inserted migration ptes are gone. We have to however undo the collecting done so far, so unlock the folios and drop reference taken. During the pagewalk we notice such scenarios if going to recollect a pfn but have already committed to migrate the entry with HMM_PFN_MIGRATE, in which case rollback. If we encounter migration ptes they are just skipped to allow for restart own walks. Cc: David Hildenbrand Cc: Jason Gunthorpe Cc: Leon Romanovsky Cc: Alistair Popple Cc: Balbir Singh Cc: Zi Yan Cc: Matthew Brost Suggested-by: Alistair Popple Signed-off-by: Mika Penttilä --- include/linux/hmm.h | 22 +++++++++++++ mm/hmm.c | 76 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 98 insertions(+) diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 4f56f3419cb4..b08ebc1343dd 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -111,6 +111,28 @@ static inline unsigned int hmm_pfn_to_map_order(unsigned long hmm_pfn) return (hmm_pfn >> HMM_PFN_ORDER_SHIFT) & 0x1F; } +/* + * hmm_pfn_collected() - is this pfn entry prepared for migration ? + * If collected the folio's refcount is increased and the folio + * is locked. + */ +static inline bool hmm_pfn_collected(unsigned long hmm_pfn) +{ + return (hmm_pfn & (HMM_PFN_VALID | HMM_PFN_MIGRATE)) == + (HMM_PFN_VALID | HMM_PFN_MIGRATE); +} + +/* + * hmm_pfn_rollback_collected() - undoes the collection of hmm_pfn + * + * Note for total rollback the folio's refcount has to be put + * and folio has to be unlocked. + */ +static inline unsigned long hmm_pfn_rollback_collected(unsigned long hmm_pfn) +{ + return hmm_pfn & ~(HMM_PFN_VALID | HMM_PFN_MIGRATE | HMM_PFN_COMPOUND); +} + /* * struct hmm_range - track invalidation lock on virtual address range * diff --git a/mm/hmm.c b/mm/hmm.c index 9fdd945cc026..daf83f809151 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -95,6 +95,11 @@ enum { HMM_PFN_P2PDMA_BUS, }; +static void hmm_vma_handle_migrate_prepare_rollback(const struct hmm_vma_walk *hmm_vma_walk, + unsigned long start, + unsigned long end, + unsigned long *hmm_pfn); + static int hmm_pfns_fill(unsigned long addr, unsigned long end, struct hmm_vma_walk *hmm_vma_walk, unsigned long cpu_flags) { @@ -111,6 +116,8 @@ static int hmm_pfns_fill(unsigned long addr, unsigned long end, } } + hmm_vma_handle_migrate_prepare_rollback(hmm_vma_walk, addr, end, &range->hmm_pfns[i]); + if (migrate && thp_migration_supported() && (minfo & MIGRATE_VMA_SELECT_COMPOUND) && IS_ALIGNED(addr, HPAGE_PMD_SIZE) && @@ -282,6 +289,8 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr, return hmm_record_fault(addr, end, required_fault, walk); } + hmm_vma_handle_migrate_prepare_rollback(hmm_vma_walk, addr, + end, hmm_pfns); pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++) { hmm_pfns[i] &= HMM_PFN_INOUT_FLAGS; @@ -412,6 +421,9 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr, new_pfn_flags = pte_pfn(pte) | cpu_flags; out: + hmm_vma_handle_migrate_prepare_rollback(hmm_vma_walk, addr, + addr + PAGE_SIZE, + hmm_pfn); *hmm_pfn = (*hmm_pfn & HMM_PFN_INOUT_FLAGS) | new_pfn_flags; return 0; @@ -450,6 +462,9 @@ static int hmm_vma_handle_absent_pmd(struct mm_walk *walk, unsigned long start, if (softleaf_is_device_private_write(entry)) cpu_flags |= HMM_PFN_WRITE; + hmm_vma_handle_migrate_prepare_rollback(hmm_vma_walk, + start, end, + hmm_pfns); /* * Fully populate the PFN list though subsequent PFNs could be * inferred, because drivers which are not yet aware of large @@ -568,6 +583,48 @@ static int migrate_vma_split_folio(struct folio *folio, return __migrate_vma_split_folio(folio, fault_page); } +/* + * Due to dropping ptl locks for splitting for instance, would we + * overwrite already collected pfns? This could happen when pmd + * pointing to a page table has vanished and been replaced + * with a leaf pmd, or another page table. + * In that case unref and unlock the folios, + * the pfns of which were collected from the disappeared + * page tables. + */ +static void hmm_vma_handle_migrate_prepare_rollback(const struct hmm_vma_walk *hmm_vma_walk, + unsigned long start, + unsigned long end, + unsigned long *hmm_pfn) +{ + struct hmm_range *range = hmm_vma_walk->range; + struct migrate_vma *migrate = range->migrate; + struct folio *fault_folio = NULL; + enum migrate_vma_info minfo; + struct folio *folio; + unsigned long i; + + minfo = hmm_select_migrate(range); + if (!minfo) + return; + + WARN_ON_ONCE(!migrate); + + fault_folio = migrate->fault_page ? + page_folio(migrate->fault_page) : NULL; + + for (i = 0; start < end; start += PAGE_SIZE, i++) { + if (hmm_pfn_collected(hmm_pfn[i])) { + folio = page_folio(hmm_pfn_to_page(hmm_pfn[i])); + if (folio != fault_folio) + folio_unlock(folio); + folio_put(folio); + hmm_pfn[i] = hmm_pfn_rollback_collected(hmm_pfn[i]); + + } + } +} + static int hmm_vma_handle_migrate_prepare_pmd(const struct mm_walk *walk, pmd_t *pmdp, unsigned long start, @@ -722,6 +779,11 @@ static int hmm_vma_handle_migrate_prepare(const struct mm_walk *walk, pte = ptep_get(ptep); if (pte_none(pte)) { + hmm_vma_handle_migrate_prepare_rollback(hmm_vma_walk, + addr, + addr + PAGE_SIZE, + hmm_pfn); + if (vma_is_anonymous(walk->vma)) { *hmm_pfn &= HMM_PFN_INOUT_FLAGS; *hmm_pfn |= HMM_PFN_MIGRATE; @@ -769,6 +831,10 @@ static int hmm_vma_handle_migrate_prepare(const struct mm_walk *walk, pfn = pte_pfn(pte); if (is_zero_pfn(pfn) && (minfo & MIGRATE_VMA_SELECT_SYSTEM)) { + hmm_vma_handle_migrate_prepare_rollback(hmm_vma_walk, + addr, + addr + PAGE_SIZE, + hmm_pfn); *hmm_pfn = HMM_PFN_MIGRATE; goto out; } @@ -897,6 +963,13 @@ static int hmm_vma_handle_migrate_prepare(const struct mm_walk *walk, } #else +static void hmm_vma_handle_migrate_prepare_rollback(const struct hmm_vma_walk *hmm_vma_walk, + unsigned long start, + unsigned long end, + unsigned long *hmm_pfn) +{ +} + static int hmm_vma_handle_migrate_prepare_pmd(const struct mm_walk *walk, pmd_t *pmdp, unsigned long start, @@ -1117,6 +1190,9 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp, if (ptep) { lazy_mmu_mode_enable(); hmm_vma_walk->ptelocked = true; + } else { + /* The pte table is gone */ + hmm_vma_handle_migrate_prepare_rollback(walk->private, addr, end, hmm_pfns); } } else { ptep = pte_offset_map(pmdp, addr); -- 2.55.0