KVM ARM Archive on lore.kernel.org
 help / color / Atom feed
From: Will Deacon <will@kernel.org>
To: kvmarm@lists.cs.columbia.edu
Cc: kernel-team@android.com, Marc Zyngier <maz@kernel.org>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will@kernel.org>,
	linux-arm-kernel@lists.infradead.org
Subject: [PATCH 16/20] KVM: arm64: Convert user_mem_abort() to generic page-table API
Date: Thu, 30 Jul 2020 16:34:02 +0100
Message-ID: <20200730153406.25136-17-will@kernel.org> (raw)
In-Reply-To: <20200730153406.25136-1-will@kernel.org>

Convert user_mem_abort() to call kvm_pgtable_stage2_relax_perms() when
handling a stage-2 permission fault and kvm_pgtable_stage2_map() when
handling a stage-2 translation fault, rather than walking the page-table
manually.

Cc: Marc Zyngier <maz@kernel.org>
Cc: Quentin Perret <qperret@google.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kvm/mmu.c | 111 +++++++++++++------------------------------
 1 file changed, 33 insertions(+), 78 deletions(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index bb2bf060a2ef..b697a23f669b 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1504,7 +1504,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 {
 	int ret;
 	bool write_fault, writable, force_pte = false;
-	bool exec_fault, needs_exec;
+	bool exec_fault;
+	bool device = false;
 	unsigned long mmu_seq;
 	gfn_t gfn = fault_ipa >> PAGE_SHIFT;
 	struct kvm *kvm = vcpu->kvm;
@@ -1512,10 +1513,10 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	struct vm_area_struct *vma;
 	short vma_shift;
 	kvm_pfn_t pfn;
-	pgprot_t mem_type = PAGE_S2;
 	bool logging_active = memslot_is_logging(memslot);
-	unsigned long vma_pagesize, flags = 0;
-	struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu;
+	unsigned long vma_pagesize;
+	enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
+	void *cookie;
 
 	write_fault = kvm_is_write_fault(vcpu);
 	exec_fault = kvm_vcpu_trap_is_iabt(vcpu);
@@ -1548,22 +1549,15 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		vma_pagesize = PAGE_SIZE;
 	}
 
-	/*
-	 * The stage2 has a minimum of 2 level table (For arm64 see
-	 * kvm_arm_setup_stage2()). Hence, we are guaranteed that we can
-	 * use PMD_SIZE huge mappings (even when the PMD is folded into PGD).
-	 * As for PUD huge maps, we must make sure that we have at least
-	 * 3 levels, i.e, PMD is not folded.
-	 */
-	if (vma_pagesize == PMD_SIZE ||
-	    (vma_pagesize == PUD_SIZE && kvm_stage2_has_pmd(kvm)))
+	if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE)
 		gfn = (fault_ipa & huge_page_mask(hstate_vma(vma))) >> PAGE_SHIFT;
 	mmap_read_unlock(current->mm);
 
-	/* We need minimum second+third level pages */
-	ret = mmu_topup_memory_cache(kvm, memcache);
-	if (ret)
-		return ret;
+	if (fault_status != FSC_PERM) {
+		ret = mmu_topup_memory_cache(kvm, memcache);
+		if (ret)
+			return ret;
+	}
 
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
 	/*
@@ -1586,28 +1580,20 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		return -EFAULT;
 
 	if (kvm_is_device_pfn(pfn)) {
-		mem_type = PAGE_S2_DEVICE;
-		flags |= KVM_S2PTE_FLAG_IS_IOMAP;
-	} else if (logging_active) {
-		/*
-		 * Faults on pages in a memslot with logging enabled
-		 * should not be mapped with huge pages (it introduces churn
-		 * and performance degradation), so force a pte mapping.
-		 */
-		flags |= KVM_S2_FLAG_LOGGING_ACTIVE;
-
+		device = true;
+	} else if (logging_active && !write_fault) {
 		/*
 		 * Only actually map the page as writable if this was a write
 		 * fault.
 		 */
-		if (!write_fault)
-			writable = false;
+		writable = false;
 	}
 
-	if (exec_fault && is_iomap(flags))
+	if (exec_fault && device)
 		return -ENOEXEC;
 
 	spin_lock(&kvm->mmu_lock);
+	cookie = vcpu->arch.hw_mmu->pgt_cookie;
 	if (mmu_notifier_retry(kvm, mmu_seq))
 		goto out_unlock;
 
@@ -1618,62 +1604,31 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (vma_pagesize == PAGE_SIZE && !force_pte)
 		vma_pagesize = transparent_hugepage_adjust(memslot, hva,
 							   &pfn, &fault_ipa);
-	if (writable)
+	if (writable) {
+		prot |= KVM_PGTABLE_PROT_W;
 		kvm_set_pfn_dirty(pfn);
+		mark_page_dirty(kvm, gfn);
+	}
 
-	if (fault_status != FSC_PERM && !is_iomap(flags))
+	if (fault_status != FSC_PERM && !device)
 		clean_dcache_guest_page(pfn, vma_pagesize);
 
-	if (exec_fault)
+	if (exec_fault) {
+		prot |= KVM_PGTABLE_PROT_X;
 		invalidate_icache_guest_page(pfn, vma_pagesize);
+	}
 
-	/*
-	 * If we took an execution fault we have made the
-	 * icache/dcache coherent above and should now let the s2
-	 * mapping be executable.
-	 *
-	 * Write faults (!exec_fault && FSC_PERM) are orthogonal to
-	 * execute permissions, and we preserve whatever we have.
-	 */
-	needs_exec = exec_fault ||
-		(fault_status == FSC_PERM &&
-		 stage2_is_exec(mmu, fault_ipa, vma_pagesize));
-
-	if (vma_pagesize == PUD_SIZE) {
-		pud_t new_pud = kvm_pfn_pud(pfn, mem_type);
-
-		new_pud = kvm_pud_mkhuge(new_pud);
-		if (writable)
-			new_pud = kvm_s2pud_mkwrite(new_pud);
-
-		if (needs_exec)
-			new_pud = kvm_s2pud_mkexec(new_pud);
-
-		ret = stage2_set_pud_huge(mmu, memcache, fault_ipa, &new_pud);
-	} else if (vma_pagesize == PMD_SIZE) {
-		pmd_t new_pmd = kvm_pfn_pmd(pfn, mem_type);
-
-		new_pmd = kvm_pmd_mkhuge(new_pmd);
-
-		if (writable)
-			new_pmd = kvm_s2pmd_mkwrite(new_pmd);
-
-		if (needs_exec)
-			new_pmd = kvm_s2pmd_mkexec(new_pmd);
+	if (device)
+		prot |= KVM_PGTABLE_PROT_DEVICE;
+	else if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC))
+		prot |= KVM_PGTABLE_PROT_X;
 
-		ret = stage2_set_pmd_huge(mmu, memcache, fault_ipa, &new_pmd);
+	if (fault_status == FSC_PERM) {
+		ret = kvm_pgtable_stage2_relax_perms(cookie, fault_ipa, prot);
 	} else {
-		pte_t new_pte = kvm_pfn_pte(pfn, mem_type);
-
-		if (writable) {
-			new_pte = kvm_s2pte_mkwrite(new_pte);
-			mark_page_dirty(kvm, gfn);
-		}
-
-		if (needs_exec)
-			new_pte = kvm_s2pte_mkexec(new_pte);
-
-		ret = stage2_set_pte(mmu, memcache, fault_ipa, &new_pte, flags);
+		ret = kvm_pgtable_stage2_map(cookie, fault_ipa, vma_pagesize,
+					     __pfn_to_phys(pfn), prot,
+					     memcache);
 	}
 
 out_unlock:
-- 
2.28.0.rc0.142.g3c755180ce-goog

_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

  parent reply index

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-30 15:33 [PATCH 00/20] KVM: arm64: Rewrite page-table code and fault handling Will Deacon
2020-07-30 15:33 ` [PATCH 01/20] KVM: arm64: Add stand-alone page-table walker infrastructure Will Deacon
2020-07-30 15:33 ` [PATCH 02/20] KVM: arm64: Add support for creating kernel-agnostic stage-1 page tables Will Deacon
2020-07-31  8:14   ` Quentin Perret
2020-07-31  8:19     ` Quentin Perret
2020-07-31  8:22       ` Will Deacon
2020-07-31  8:36         ` Quentin Perret
2020-07-31  9:06           ` Quentin Perret
2020-07-30 15:33 ` [PATCH 03/20] KVM: arm64: Use generic allocator for hyp stage-1 page-tables Will Deacon
2020-07-30 15:33 ` [PATCH 04/20] KVM: arm64: Add support for creating kernel-agnostic stage-2 page tables Will Deacon
2020-07-30 15:33 ` [PATCH 05/20] KVM: arm64: Add support for stage-2 map()/unmap() in generic page-table Will Deacon
2020-07-30 15:33 ` [PATCH 06/20] KVM: arm64: Convert kvm_phys_addr_ioremap() to generic page-table API Will Deacon
2020-07-30 15:33 ` [PATCH 07/20] KVM: arm64: Convert kvm_set_spte_hva() " Will Deacon
2020-07-30 15:33 ` [PATCH 08/20] KVM: arm64: Convert unmap_stage2_range() " Will Deacon
2020-07-30 15:33 ` [PATCH 09/20] KVM: arm64: Add support for stage-2 page-aging in generic page-table Will Deacon
2020-07-30 15:33 ` [PATCH 10/20] KVM: arm64: Convert page-aging and access faults to generic page-table API Will Deacon
2020-07-30 15:33 ` [PATCH 11/20] KVM: arm64: Add support for stage-2 write-protect in generic page-table Will Deacon
2020-07-30 15:33 ` [PATCH 12/20] KVM: arm64: Convert write-protect operation to generic page-table API Will Deacon
2020-07-30 15:33 ` [PATCH 13/20] KVM: arm64: Add support for stage-2 cache flushing in generic page-table Will Deacon
2020-07-30 15:34 ` [PATCH 14/20] KVM: arm64: Convert memslot cache-flushing code to generic page-table API Will Deacon
2020-07-30 15:34 ` [PATCH 15/20] KVM: arm64: Add support for relaxing stage-2 perms in generic page-table code Will Deacon
2020-07-30 15:34 ` Will Deacon [this message]
2020-07-30 15:34 ` [PATCH 17/20] KVM: arm64: Check the cookie instead of the pgd when modifying page-table Will Deacon
2020-07-30 15:34 ` [PATCH 18/20] KVM: arm64: Remove unused page-table code Will Deacon
2020-07-30 15:34 ` [PATCH 19/20] KVM: arm64: Remove unused 'pgd' field from 'struct kvm_s2_mmu' Will Deacon
2020-07-30 15:34 ` [PATCH 20/20] KVM: arm64: Don't constrain maximum IPA size based on host configuration Will Deacon
2020-08-03  8:17 ` [PATCH 00/20] KVM: arm64: Rewrite page-table code and fault handling Andrew Jones
2020-08-03 17:12   ` Quentin Perret

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200730153406.25136-17-will@kernel.org \
    --to=will@kernel.org \
    --cc=catalin.marinas@arm.com \
    --cc=kernel-team@android.com \
    --cc=kvmarm@lists.cs.columbia.edu \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=maz@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

KVM ARM Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/kvmarm/0 kvmarm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 kvmarm kvmarm/ https://lore.kernel.org/kvmarm \
		kvmarm@lists.cs.columbia.edu
	public-inbox-index kvmarm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/edu.columbia.cs.lists.kvmarm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git