Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Tianyu Lan <ltykernel@gmail.com>
To:     kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com,
        wei.liu@kernel.org, decui@microsoft.com, tglx@linutronix.de,
        mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
        arnd@arndb.de, dave.hansen@linux.intel.com, luto@kernel.org,
        peterz@infradead.org, akpm@linux-foundation.org,
        kirill.shutemov@linux.intel.com, rppt@kernel.org,
        hannes@cmpxchg.org, cai@lca.pw, krish.sadhukhan@oracle.com,
        saravanand@fb.com, Tianyu.Lan@microsoft.com,
        konrad.wilk@oracle.com, hch@lst.de, m.szyprowski@samsung.com,
        robin.murphy@arm.com, boris.ostrovsky@oracle.com, jgross@suse.com,
        sstabellini@kernel.org, joro@8bytes.org, will@kernel.org,
        xen-devel@lists.xenproject.org, davem@davemloft.net,
        kuba@kernel.org, jejb@linux.ibm.com, martin.petersen@oracle.com
Cc:     iommu@lists.linux-foundation.org, linux-arch@vger.kernel.org,
        linux-hyperv@vger.kernel.org, linux-kernel@vger.kernel.org,
        linux-scsi@vger.kernel.org, netdev@vger.kernel.org,
        vkuznets@redhat.com, thomas.lendacky@amd.com,
        brijesh.singh@amd.com, sunilmut@microsoft.com
Subject: [RFC PATCH V3 09/11] HV/IOMMU: Enable swiotlb bounce buffer for Isolation VM
Date:   Sun, 30 May 2021 11:06:26 -0400
Message-Id: <20210530150628.2063957-10-ltykernel@gmail.com>
In-Reply-To: <20210530150628.2063957-1-ltykernel@gmail.com>
References: <20210530150628.2063957-1-ltykernel@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Tianyu Lan <Tianyu.Lan@microsoft.com>

Hyper-V Isolation VM requires bounce buffer support to copy
data from/to encrypted memory and so enable swiotlb force
mode to use swiotlb bounce buffer for DMA transaction.

In Isolation VM with AMD SEV, the bounce buffer needs to be
accessed via extra address space which is above shared_gpa_boundary
(E.G 39 bit address line) reported by Hyper-V CPUID ISOLATION_CONFIG.
The access physical address will be original physical address +
shared_gpa_boundary. The shared_gpa_boundary in the AMD SEV SNP
spec is called virtual top of memory(vTOM). Memory addresses below
vTOM are automatically treated as private while memory above
vTOM is treated as shared.

ioremap_cache() can't use in the hyperv_iommu_swiotlb_init() which
is too early place and remap bounce buffer in the hyperv_iommu_swiotlb_
later_init().

Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
 arch/x86/xen/pci-swiotlb-xen.c |  3 +-
 drivers/hv/vmbus_drv.c         |  3 ++
 drivers/iommu/hyperv-iommu.c   | 81 ++++++++++++++++++++++++++++++++++
 include/linux/hyperv.h         |  1 +
 4 files changed, 87 insertions(+), 1 deletion(-)

diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index 54f9aa7e8457..43bd031aa332 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -4,6 +4,7 @@
 
 #include <linux/dma-map-ops.h>
 #include <linux/pci.h>
+#include <linux/hyperv.h>
 #include <xen/swiotlb-xen.h>
 
 #include <asm/xen/hypervisor.h>
@@ -91,6 +92,6 @@ int pci_xen_swiotlb_init_late(void)
 EXPORT_SYMBOL_GPL(pci_xen_swiotlb_init_late);
 
 IOMMU_INIT_FINISH(pci_xen_swiotlb_detect,
-		  NULL,
+		  hyperv_swiotlb_detect,
 		  pci_xen_swiotlb_init,
 		  NULL);
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 92cb3f7d21d9..5e3bb76d4dee 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -23,6 +23,7 @@
 #include <linux/cpu.h>
 #include <linux/sched/task_stack.h>
 
+#include <linux/dma-map-ops.h>
 #include <linux/delay.h>
 #include <linux/notifier.h>
 #include <linux/ptrace.h>
@@ -2080,6 +2081,7 @@ struct hv_device *vmbus_device_create(const guid_t *type,
 	return child_device_obj;
 }
 
+static u64 vmbus_dma_mask = DMA_BIT_MASK(64);
 /*
  * vmbus_device_register - Register the child device
  */
@@ -2120,6 +2122,7 @@ int vmbus_device_register(struct hv_device *child_device_obj)
 	}
 	hv_debug_add_dev_dir(child_device_obj);
 
+	child_device_obj->device.dma_mask = &vmbus_dma_mask;
 	return 0;
 
 err_kset_unregister:
diff --git a/drivers/iommu/hyperv-iommu.c b/drivers/iommu/hyperv-iommu.c
index e285a220c913..2604619c6fa3 100644
--- a/drivers/iommu/hyperv-iommu.c
+++ b/drivers/iommu/hyperv-iommu.c
@@ -13,14 +13,22 @@
 #include <linux/irq.h>
 #include <linux/iommu.h>
 #include <linux/module.h>
+#include <linux/hyperv.h>
+#include <linux/io.h>
 
 #include <asm/apic.h>
 #include <asm/cpu.h>
 #include <asm/hw_irq.h>
 #include <asm/io_apic.h>
+#include <asm/iommu.h>
+#include <asm/iommu_table.h>
 #include <asm/irq_remapping.h>
 #include <asm/hypervisor.h>
 #include <asm/mshyperv.h>
+#include <asm/swiotlb.h>
+#include <linux/dma-map-ops.h>
+#include <linux/dma-direct.h>
+#include <linux/set_memory.h>
 
 #include "irq_remapping.h"
 
@@ -36,6 +44,8 @@
 static cpumask_t ioapic_max_cpumask = { CPU_BITS_NONE };
 static struct irq_domain *ioapic_ir_domain;
 
+static unsigned long hyperv_io_tlb_start, hyperv_io_tlb_size;
+
 static int hyperv_ir_set_affinity(struct irq_data *data,
 		const struct cpumask *mask, bool force)
 {
@@ -337,4 +347,75 @@ static const struct irq_domain_ops hyperv_root_ir_domain_ops = {
 	.free = hyperv_root_irq_remapping_free,
 };
 
+void __init hyperv_iommu_swiotlb_init(void)
+{
+	unsigned long bytes, io_tlb_nslabs;
+	void *vstart;
+
+	/* Allocate Hyper-V swiotlb  */
+	bytes = 200 * 1024 * 1024;
+	vstart = memblock_alloc_low(PAGE_ALIGN(bytes), PAGE_SIZE);
+	io_tlb_nslabs = bytes >> IO_TLB_SHIFT;
+	hyperv_io_tlb_size = bytes;
+
+	if (!vstart) {
+		pr_warn("Fail to allocate swiotlb.\n");
+		return;
+	}
+
+	hyperv_io_tlb_start = virt_to_phys(vstart);
+	if (!hyperv_io_tlb_start)
+		panic("%s: Failed to allocate %lu bytes align=0x%lx.\n",
+		      __func__, PAGE_ALIGN(bytes), PAGE_SIZE);
+
+	if (swiotlb_init_with_tbl(vstart, io_tlb_nslabs, 1))
+		panic("%s: Cannot allocate SWIOTLB buffer.\n", __func__);
+
+	swiotlb_set_max_segment(HV_HYP_PAGE_SIZE);
+}
+
+int __init hyperv_swiotlb_detect(void)
+{
+	if (hypervisor_is_type(X86_HYPER_MS_HYPERV)
+	    && hv_is_isolation_supported()) {
+		/*
+		 * Enable swiotlb force mode in Isolation VM to
+		 * use swiotlb bounce buffer for dma transaction.
+		 */
+		swiotlb_force = SWIOTLB_FORCE;
+		return 1;
+	}
+
+	return 0;
+}
+
+void __init hyperv_iommu_swiotlb_later_init(void)
+{
+	void *hyperv_io_tlb_remap;
+	int ret;
+
+	/* Mask bounce buffer visible to host and remap extra address. */
+	if (hv_isolation_type_snp()) {
+		ret = set_memory_decrypted((unsigned long)
+				phys_to_virt(hyperv_io_tlb_start),
+				HVPFN_UP(hyperv_io_tlb_size));
+		if (ret)
+			panic("%s: Fail to mark Hyper-v swiotlb buffer visible to host. err=%d\n",
+			      __func__, ret);
+
+		hyperv_io_tlb_remap = ioremap_cache(hyperv_io_tlb_start
+				+ ms_hyperv.shared_gpa_boundary,
+				hyperv_io_tlb_size);
+		if (!hyperv_io_tlb_remap)
+			panic("Fail to remap io tlb.\n");
+
+		memset(hyperv_io_tlb_remap, 0x00, hyperv_io_tlb_size);
+		swiotlb_set_bounce_remap(hyperv_io_tlb_remap);
+	}
+}
+
+IOMMU_INIT_FINISH(hyperv_swiotlb_detect,
+		  NULL, hyperv_iommu_swiotlb_init,
+		  hyperv_iommu_swiotlb_later_init);
+
 #endif
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 06eccaba10c5..babbe19f57e2 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1759,6 +1759,7 @@ int hyperv_write_cfg_blk(struct pci_dev *dev, void *buf, unsigned int len,
 int hyperv_reg_block_invalidate(struct pci_dev *dev, void *context,
 				void (*block_invalidate)(void *context,
 							 u64 block_mask));
+int __init hyperv_swiotlb_detect(void);
 
 struct hyperv_pci_block_ops {
 	int (*read_block)(struct pci_dev *dev, void *buf, unsigned int buf_len,
-- 
2.25.1