From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andrew Morton Subject: [patch 34/67] mm: pagewalk: add p4d_entry() and pgd_entry() Date: Mon, 03 Feb 2020 17:35:45 -0800 Message-ID: <20200204013545.DHDKWKUuo%akpm@linux-foundation.org> References: <20200203173311.6269a8be06a05e5a4aa08a93@linux-foundation.org> Reply-To: linux-kernel@vger.kernel.org Return-path: Received: from mail.kernel.org ([198.145.29.99]:35472 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727044AbgBDBfs (ORCPT ); Mon, 3 Feb 2020 20:35:48 -0500 In-Reply-To: <20200203173311.6269a8be06a05e5a4aa08a93@linux-foundation.org> Sender: mm-commits-owner@vger.kernel.org List-Id: mm-commits@vger.kernel.org To: akpm@linux-foundation.org, alex@ghiti.fr, aou@eecs.berkeley.edu, ard.biesheuvel@linaro.org, arnd@arndb.de, benh@kernel.crashing.org, borntraeger@de.ibm.com, bp@alien8.de, catalin.marinas@arm.com, dave.hansen@linux.intel.com, davem@davemloft.net, gor@linux.ibm.com, heiko.carstens@de.ibm.com, hpa@zytor.com, james.morse@arm.com, jglisse@redhat.com, jhogan@kernel.org, kan.liang@linux.intel.com, linux-mm@kvack.org, linux@armlinux.org.uk, luto@kernel.org, mark.rutland@arm.com, mingo@redhat.com, mm-commits@vger.kernel.org, mpe@ellerman.id.au, paul.burton@mips.com, paul.walmsley@sifive.com, paulus@samba.org, peterz@infradead.org, ralf@linux-mips.org, steven.price@arm.com, tglx@linutronix.de, torvalds@linux-foundation.org, vgupta@synopsys.com, will@kernel.org, zong.li@sifive.com From: Steven Price Subject: mm: pagewalk: add p4d_entry() and pgd_entry() pgd_entry() and pud_entry() were removed by commit 0b1fbfe50006c410 ("mm/pagewalk: remove pgd_entry() and pud_entry()") because there were no users. We're about to add users so reintroduce them, along with p4d_entry() as we now have 5 levels of tables. Note that commit a00cc7d9dd93d66a ("mm, x86: add support for PUD-sized transparent hugepages") already re-added pud_entry() but with different semantics to the other callbacks. This commit reverts the semantics back to match the other callbacks. To support hmm.c which now uses the new semantics of pud_entry() a new member ('action') of struct mm_walk is added which allows the callbacks to either descend (ACTION_SUBTREE, the default), skip (ACTION_CONTINUE) or repeat the callback (ACTION_AGAIN). hmm.c is then updated to call pud_trans_huge_lock() itself and make use of the splitting/retry logic of the core code. After this change pud_entry() is called for all entries, not just transparent huge pages. [arnd@arndb.de: fix unused variable warning] Link: http://lkml.kernel.org/r/20200107204607.1533842-1-arnd@arndb.de Link: http://lkml.kernel.org/r/20191218162402.45610-12-steven.price@arm.com Signed-off-by: Steven Price Signed-off-by: Arnd Bergmann Cc: Albert Ou Cc: Alexandre Ghiti Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Dave Hansen Cc: David S. Miller Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: James Hogan Cc: James Morse Cc: Jerome Glisse Cc: "Liang, Kan" Cc: Mark Rutland Cc: Michael Ellerman Cc: Paul Burton Cc: Paul Mackerras Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Ralf Baechle Cc: Russell King Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Cc: Zong Li Signed-off-by: Andrew Morton --- include/linux/pagewalk.h | 34 +++++++++++++++++---- mm/hmm.c | 58 ++++++++++++++++++++----------------- mm/pagewalk.c | 50 ++++++++++++++++++++++--------- 3 files changed, 95 insertions(+), 47 deletions(-) --- a/include/linux/pagewalk.h~mm-pagewalk-add-p4d_entry-and-pgd_entry +++ a/include/linux/pagewalk.h @@ -8,15 +8,15 @@ struct mm_walk; /** * mm_walk_ops - callbacks for walk_page_range - * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry - * this handler should only handle pud_trans_huge() puds. - * the pmd_entry or pte_entry callbacks will be used for - * regular PUDs. - * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry + * @pgd_entry: if set, called for each non-empty PGD (top-level) entry + * @p4d_entry: if set, called for each non-empty P4D entry + * @pud_entry: if set, called for each non-empty PUD entry + * @pmd_entry: if set, called for each non-empty PMD entry * this handler is required to be able to handle * pmd_trans_huge() pmds. They may simply choose to * split_huge_page() instead of handling it explicitly. - * @pte_entry: if set, called for each non-empty PTE (4th-level) entry + * @pte_entry: if set, called for each non-empty PTE (lowest-level) + * entry * @pte_hole: if set, called for each hole at all levels * @hugetlb_entry: if set, called for each hugetlb entry * @test_walk: caller specific callback function to determine whether @@ -27,8 +27,15 @@ struct mm_walk; * @pre_vma: if set, called before starting walk on a non-null vma. * @post_vma: if set, called after a walk on a non-null vma, provided * that @pre_vma and the vma walk succeeded. + * + * p?d_entry callbacks are called even if those levels are folded on a + * particular architecture/configuration. */ struct mm_walk_ops { + int (*pgd_entry)(pgd_t *pgd, unsigned long addr, + unsigned long next, struct mm_walk *walk); + int (*p4d_entry)(p4d_t *p4d, unsigned long addr, + unsigned long next, struct mm_walk *walk); int (*pud_entry)(pud_t *pud, unsigned long addr, unsigned long next, struct mm_walk *walk); int (*pmd_entry)(pmd_t *pmd, unsigned long addr, @@ -47,11 +54,25 @@ struct mm_walk_ops { void (*post_vma)(struct mm_walk *walk); }; +/* + * Action for pud_entry / pmd_entry callbacks. + * ACTION_SUBTREE is the default + */ +enum page_walk_action { + /* Descend to next level, splitting huge pages if needed and possible */ + ACTION_SUBTREE = 0, + /* Continue to next entry at this level (ignoring any subtree) */ + ACTION_CONTINUE = 1, + /* Call again for this entry */ + ACTION_AGAIN = 2 +}; + /** * mm_walk - walk_page_range data * @ops: operation to call during the walk * @mm: mm_struct representing the target process of page table walk * @vma: vma currently walked (NULL if walking outside vmas) + * @action: next action to perform (see enum page_walk_action) * @private: private data for callbacks' usage * * (see the comment on walk_page_range() for more details) @@ -60,6 +81,7 @@ struct mm_walk { const struct mm_walk_ops *ops; struct mm_struct *mm; struct vm_area_struct *vma; + enum page_walk_action action; void *private; }; --- a/mm/hmm.c~mm-pagewalk-add-p4d_entry-and-pgd_entry +++ a/mm/hmm.c @@ -474,23 +474,32 @@ static int hmm_vma_walk_pud(pud_t *pudp, { struct hmm_vma_walk *hmm_vma_walk = walk->private; struct hmm_range *range = hmm_vma_walk->range; - unsigned long addr = start, next; - pmd_t *pmdp; + unsigned long addr = start; pud_t pud; - int ret; + int ret = 0; + spinlock_t *ptl = pud_trans_huge_lock(pudp, walk->vma); + + if (!ptl) + return 0; + + /* Normally we don't want to split the huge page */ + walk->action = ACTION_CONTINUE; -again: pud = READ_ONCE(*pudp); - if (pud_none(pud)) - return hmm_vma_walk_hole(start, end, walk); + if (pud_none(pud)) { + ret = hmm_vma_walk_hole(start, end, walk); + goto out_unlock; + } if (pud_huge(pud) && pud_devmap(pud)) { unsigned long i, npages, pfn; uint64_t *pfns, cpu_flags; bool fault, write_fault; - if (!pud_present(pud)) - return hmm_vma_walk_hole(start, end, walk); + if (!pud_present(pud)) { + ret = hmm_vma_walk_hole(start, end, walk); + goto out_unlock; + } i = (addr - range->start) >> PAGE_SHIFT; npages = (end - addr) >> PAGE_SHIFT; @@ -499,16 +508,20 @@ again: cpu_flags = pud_to_hmm_pfn_flags(range, pud); hmm_range_need_fault(hmm_vma_walk, pfns, npages, cpu_flags, &fault, &write_fault); - if (fault || write_fault) - return hmm_vma_walk_hole_(addr, end, fault, - write_fault, walk); + if (fault || write_fault) { + ret = hmm_vma_walk_hole_(addr, end, fault, + write_fault, walk); + goto out_unlock; + } pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); for (i = 0; i < npages; ++i, ++pfn) { hmm_vma_walk->pgmap = get_dev_pagemap(pfn, hmm_vma_walk->pgmap); - if (unlikely(!hmm_vma_walk->pgmap)) - return -EBUSY; + if (unlikely(!hmm_vma_walk->pgmap)) { + ret = -EBUSY; + goto out_unlock; + } pfns[i] = hmm_device_entry_from_pfn(range, pfn) | cpu_flags; } @@ -517,22 +530,15 @@ again: hmm_vma_walk->pgmap = NULL; } hmm_vma_walk->last = end; - return 0; + goto out_unlock; } - split_huge_pud(walk->vma, pudp, addr); - if (pud_none(*pudp)) - goto again; - - pmdp = pmd_offset(pudp, addr); - do { - next = pmd_addr_end(addr, end); - ret = hmm_vma_walk_pmd(pmdp, addr, next, walk); - if (ret) - return ret; - } while (pmdp++, addr = next, addr != end); + /* Ask for the PUD to be split */ + walk->action = ACTION_SUBTREE; - return 0; +out_unlock: + spin_unlock(ptl); + return ret; } #else #define hmm_vma_walk_pud NULL --- a/mm/pagewalk.c~mm-pagewalk-add-p4d_entry-and-pgd_entry +++ a/mm/pagewalk.c @@ -46,6 +46,9 @@ again: break; continue; } + + walk->action = ACTION_SUBTREE; + /* * This implies that each ->pmd_entry() handler * needs to know about pmd_trans_huge() pmds @@ -55,16 +58,21 @@ again: if (err) break; + if (walk->action == ACTION_AGAIN) + goto again; + /* * Check this here so we only break down trans_huge * pages when we _need_ to */ - if (!ops->pte_entry) + if (walk->action == ACTION_CONTINUE || + !(ops->pte_entry)) continue; split_huge_pmd(walk->vma, pmd, addr); if (pmd_trans_unstable(pmd)) goto again; + err = walk_pte_range(pmd, addr, next, walk); if (err) break; @@ -93,24 +101,25 @@ static int walk_pud_range(p4d_t *p4d, un continue; } - if (ops->pud_entry) { - spinlock_t *ptl = pud_trans_huge_lock(pud, walk->vma); + walk->action = ACTION_SUBTREE; - if (ptl) { - err = ops->pud_entry(pud, addr, next, walk); - spin_unlock(ptl); - if (err) - break; - continue; - } - } + if (ops->pud_entry) + err = ops->pud_entry(pud, addr, next, walk); + if (err) + break; + + if (walk->action == ACTION_AGAIN) + goto again; + + if (walk->action == ACTION_CONTINUE || + !(ops->pmd_entry || ops->pte_entry)) + continue; split_huge_pud(walk->vma, pud, addr); if (pud_none(*pud)) goto again; - if (ops->pmd_entry || ops->pte_entry) - err = walk_pmd_range(pud, addr, next, walk); + err = walk_pmd_range(pud, addr, next, walk); if (err) break; } while (pud++, addr = next, addr != end); @@ -136,7 +145,12 @@ static int walk_p4d_range(pgd_t *pgd, un break; continue; } - if (ops->pmd_entry || ops->pte_entry) + if (ops->p4d_entry) { + err = ops->p4d_entry(p4d, addr, next, walk); + if (err) + break; + } + if (ops->pud_entry || ops->pmd_entry || ops->pte_entry) err = walk_pud_range(p4d, addr, next, walk); if (err) break; @@ -163,7 +177,13 @@ static int walk_pgd_range(unsigned long break; continue; } - if (ops->pmd_entry || ops->pte_entry) + if (ops->pgd_entry) { + err = ops->pgd_entry(pgd, addr, next, walk); + if (err) + break; + } + if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry || + ops->pte_entry) err = walk_p4d_range(pgd, addr, next, walk); if (err) break; _