Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Lu Baolu <baolu.lu@linux.intel.com>
To:     Joerg Roedel <joro@8bytes.org>, Jason Gunthorpe <jgg@nvidia.com>,
        Christoph Hellwig <hch@infradead.org>,
        Kevin Tian <kevin.tian@intel.com>,
        Ashok Raj <ashok.raj@intel.com>, Will Deacon <will@kernel.org>,
        Robin Murphy <robin.murphy@arm.com>,
        Jean-Philippe Brucker <jean-philippe@linaro.com>,
        Dave Jiang <dave.jiang@intel.com>,
        Vinod Koul <vkoul@kernel.org>
Cc:     Eric Auger <eric.auger@redhat.com>, Liu Yi L <yi.l.liu@intel.com>,
        Jacob jun Pan <jacob.jun.pan@intel.com>,
        iommu@lists.linux-foundation.org, iommu@lists.linux.dev,
        linux-kernel@vger.kernel.org, Lu Baolu <baolu.lu@linux.intel.com>,
        Jean-Philippe Brucker <jean-philippe@linaro.org>
Subject: [PATCH v9 10/11] iommu: Per-domain I/O page fault handling
Date:   Tue, 21 Jun 2022 22:43:52 +0800
Message-Id: <20220621144353.17547-11-baolu.lu@linux.intel.com>
In-Reply-To: <20220621144353.17547-1-baolu.lu@linux.intel.com>
References: <20220621144353.17547-1-baolu.lu@linux.intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Tweak the I/O page fault handling framework to route the page faults to
the domain and call the page fault handler retrieved from the domain.
This makes the I/O page fault handling framework possible to serve more
usage scenarios as long as they have an IOMMU domain and install a page
fault handler in it. Some unused functions are also removed to avoid
dead code.

The iommu_get_domain_for_dev_pasid() which retrieves attached domain
for a {device, PASID} pair is used. It will be used by the page fault
handling framework which knows {device, PASID} reported from the iommu
driver. We have a guarantee that the SVA domain doesn't go away during
IOPF handling, because unbind() waits for pending faults with
iopf_queue_flush_dev() before freeing the domain. Hence, there's no need
to synchronize life cycle of the iommu domains between the unbind() and
the interrupt threads.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
---
 drivers/iommu/io-pgfault.c | 64 +++++---------------------------------
 1 file changed, 7 insertions(+), 57 deletions(-)

diff --git a/drivers/iommu/io-pgfault.c b/drivers/iommu/io-pgfault.c
index aee9e033012f..4f24ec703479 100644
--- a/drivers/iommu/io-pgfault.c
+++ b/drivers/iommu/io-pgfault.c
@@ -69,69 +69,18 @@ static int iopf_complete_group(struct device *dev, struct iopf_fault *iopf,
 	return iommu_page_response(dev, &resp);
 }
 
-static enum iommu_page_response_code
-iopf_handle_single(struct iopf_fault *iopf)
-{
-	vm_fault_t ret;
-	struct mm_struct *mm;
-	struct vm_area_struct *vma;
-	unsigned int access_flags = 0;
-	unsigned int fault_flags = FAULT_FLAG_REMOTE;
-	struct iommu_fault_page_request *prm = &iopf->fault.prm;
-	enum iommu_page_response_code status = IOMMU_PAGE_RESP_INVALID;
-
-	if (!(prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID))
-		return status;
-
-	mm = iommu_sva_find(prm->pasid);
-	if (IS_ERR_OR_NULL(mm))
-		return status;
-
-	mmap_read_lock(mm);
-
-	vma = find_extend_vma(mm, prm->addr);
-	if (!vma)
-		/* Unmapped area */
-		goto out_put_mm;
-
-	if (prm->perm & IOMMU_FAULT_PERM_READ)
-		access_flags |= VM_READ;
-
-	if (prm->perm & IOMMU_FAULT_PERM_WRITE) {
-		access_flags |= VM_WRITE;
-		fault_flags |= FAULT_FLAG_WRITE;
-	}
-
-	if (prm->perm & IOMMU_FAULT_PERM_EXEC) {
-		access_flags |= VM_EXEC;
-		fault_flags |= FAULT_FLAG_INSTRUCTION;
-	}
-
-	if (!(prm->perm & IOMMU_FAULT_PERM_PRIV))
-		fault_flags |= FAULT_FLAG_USER;
-
-	if (access_flags & ~vma->vm_flags)
-		/* Access fault */
-		goto out_put_mm;
-
-	ret = handle_mm_fault(vma, prm->addr, fault_flags, NULL);
-	status = ret & VM_FAULT_ERROR ? IOMMU_PAGE_RESP_INVALID :
-		IOMMU_PAGE_RESP_SUCCESS;
-
-out_put_mm:
-	mmap_read_unlock(mm);
-	mmput(mm);
-
-	return status;
-}
-
 static void iopf_handle_group(struct work_struct *work)
 {
 	struct iopf_group *group;
+	struct iommu_domain *domain;
 	struct iopf_fault *iopf, *next;
 	enum iommu_page_response_code status = IOMMU_PAGE_RESP_SUCCESS;
 
 	group = container_of(work, struct iopf_group, work);
+	domain = iommu_get_domain_for_dev_pasid(group->dev,
+				group->last_fault.fault.prm.pasid);
+	if (!domain || !domain->iopf_handler)
+		status = IOMMU_PAGE_RESP_INVALID;
 
 	list_for_each_entry_safe(iopf, next, &group->faults, list) {
 		/*
@@ -139,7 +88,8 @@ static void iopf_handle_group(struct work_struct *work)
 		 * faults in the group if there is an error.
 		 */
 		if (status == IOMMU_PAGE_RESP_SUCCESS)
-			status = iopf_handle_single(iopf);
+			status = domain->iopf_handler(&iopf->fault,
+						      domain->fault_data);
 
 		if (!(iopf->fault.prm.flags &
 		      IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE))
-- 
2.25.1