Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Zhen Lei <thunder.leizhen@huawei.com>
To:     Jean-Philippe Brucker <jean-philippe.brucker@arm.com>,
        John Garry <john.garry@huawei.com>,
        Robin Murphy <robin.murphy@arm.com>,
        Will Deacon <will.deacon@arm.com>,
        Joerg Roedel <joro@8bytes.org>,
        Jonathan Corbet <corbet@lwn.net>,
        linux-doc <linux-doc@vger.kernel.org>,
        Sebastian Ott <sebott@linux.ibm.com>,
        Gerald Schaefer <gerald.schaefer@de.ibm.com>,
        "Martin Schwidefsky" <schwidefsky@de.ibm.com>,
        Heiko Carstens <heiko.carstens@de.ibm.com>,
        Benjamin Herrenschmidt <benh@kernel.crashing.org>,
        Paul Mackerras <paulus@samba.org>,
        "Michael Ellerman" <mpe@ellerman.id.au>,
        Tony Luck <tony.luck@intel.com>,
        Fenghua Yu <fenghua.yu@intel.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
        "H . Peter Anvin" <hpa@zytor.com>,
        David Woodhouse <dwmw2@infradead.org>,
        iommu <iommu@lists.linux-foundation.org>,
        linux-kernel <linux-kernel@vger.kernel.org>,
        linux-s390 <linux-s390@vger.kernel.org>,
        linuxppc-dev <linuxppc-dev@lists.ozlabs.org>,
        x86 <x86@kernel.org>, linux-ia64 <linux-ia64@vger.kernel.org>
CC:     Zhen Lei <thunder.leizhen@huawei.com>,
        Hanjun Guo <guohanjun@huawei.com>
Subject: [PATCH v5 6/6] x86/iommu: add support for generic boot option iommu.dma_mode
Date:   Tue, 9 Apr 2019 20:53:08 +0800
Message-ID: <20190409125308.18304-7-thunder.leizhen@huawei.com>
In-Reply-To: <20190409125308.18304-1-thunder.leizhen@huawei.com>
References: <20190409125308.18304-1-thunder.leizhen@huawei.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 7BIT
Content-Type:   text/plain; charset=US-ASCII
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

The following equivalence or replacement relationship exists:
iommu=pt <--> iommu.dma_mode=passthrough.
iommu=nopt can be replaced with iommu.dma_mode=lazy.
intel_iommu=strict <--> iommu.dma_mode=strict.
amd_iommu=fullflush <--> iommu.dma_mode=strict.

Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
---
 Documentation/admin-guide/kernel-parameters.txt |  6 ++---
 arch/ia64/include/asm/iommu.h                   |  2 --
 arch/ia64/kernel/pci-dma.c                      |  2 --
 arch/x86/include/asm/iommu.h                    |  1 -
 arch/x86/kernel/pci-dma.c                       | 35 ++++++++++++-------------
 drivers/iommu/Kconfig                           |  2 +-
 drivers/iommu/amd_iommu.c                       | 10 +++----
 drivers/iommu/amd_iommu_init.c                  |  4 +--
 drivers/iommu/amd_iommu_types.h                 |  6 -----
 drivers/iommu/intel-iommu.c                     |  9 +++----
 10 files changed, 31 insertions(+), 46 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 176f96032d9d62a..ca6edc529d6a614 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1815,9 +1815,9 @@
 			options(such as CONFIG_IOMMU_DEFAULT_PASSTHROUGH) to
 			choose which mode to be used.
 			Note: For historical reasons, ARM64/S390/PPC/X86 have
-			their specific options. Currently, only ARM64/S390/PPC
-			support this boot option, and hope other ARCHs to use
-			this as generic boot option.
+			their specific options, but strongly recommended switch
+			to use this one, the new ARCHs should use this generic
+			boot option.
 		passthrough
 			Configure DMA to bypass the IOMMU by default.
 		lazy
diff --git a/arch/ia64/include/asm/iommu.h b/arch/ia64/include/asm/iommu.h
index 7429a72f3f92199..92aceef63710861 100644
--- a/arch/ia64/include/asm/iommu.h
+++ b/arch/ia64/include/asm/iommu.h
@@ -8,10 +8,8 @@
 extern void no_iommu_init(void);
 #ifdef	CONFIG_INTEL_IOMMU
 extern int force_iommu, no_iommu;
-extern int iommu_pass_through;
 extern int iommu_detected;
 #else
-#define iommu_pass_through	(0)
 #define no_iommu		(1)
 #define iommu_detected		(0)
 #endif
diff --git a/arch/ia64/kernel/pci-dma.c b/arch/ia64/kernel/pci-dma.c
index fe988c49f01ce6a..f5d49cd3fbb01a9 100644
--- a/arch/ia64/kernel/pci-dma.c
+++ b/arch/ia64/kernel/pci-dma.c
@@ -22,8 +22,6 @@
 int force_iommu __read_mostly;
 #endif
 
-int iommu_pass_through;
-
 static int __init pci_iommu_init(void)
 {
 	if (iommu_detected)
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index baedab8ac5385f7..b91623d521d9f0f 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -4,7 +4,6 @@
 
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
-extern int iommu_pass_through;
 
 /* 10 seconds */
 #define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index d460998ae828514..fc64928e47cb860 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -6,6 +6,7 @@
 #include <linux/memblock.h>
 #include <linux/gfp.h>
 #include <linux/pci.h>
+#include <linux/iommu.h>
 
 #include <asm/proto.h>
 #include <asm/dma.h>
@@ -34,21 +35,6 @@
 /* Set this to 1 if there is a HW IOMMU in the system */
 int iommu_detected __read_mostly = 0;
 
-/*
- * This variable becomes 1 if iommu=pt is passed on the kernel command line.
- * If this variable is 1, IOMMU implementations do no DMA translation for
- * devices and allow every device to access to whole physical memory. This is
- * useful if a user wants to use an IOMMU only for KVM device assignment to
- * guests and not for driver dma translation.
- * It is also possible to disable by default in kernel config, and enable with
- * iommu=nopt at boot time.
- */
-#ifdef CONFIG_IOMMU_DEFAULT_PASSTHROUGH
-int iommu_pass_through __read_mostly = 1;
-#else
-int iommu_pass_through __read_mostly;
-#endif
-
 extern struct iommu_table_entry __iommu_table[], __iommu_table_end[];
 
 /* Dummy device used for NULL arguments (normally ISA). */
@@ -139,10 +125,23 @@ static __init int iommu_setup(char *p)
 		if (!strncmp(p, "soft", 4))
 			swiotlb = 1;
 #endif
+
+		/*
+		 * IOMMU implementations do no DMA translation for devices and
+		 * allow every device to access to whole physical memory. This
+		 * is useful if a user wants to use an IOMMU only for KVM
+		 * device assignment to guests and not for driver dma
+		 * translation.
+		 */
 		if (!strncmp(p, "pt", 2))
-			iommu_pass_through = 1;
-		if (!strncmp(p, "nopt", 4))
-			iommu_pass_through = 0;
+			iommu_default_dma_mode_set(IOMMU_DMA_MODE_PASSTHROUGH);
+
+		/*
+		 * The default dma mode is lazy on X86. And if dma mode is
+		 * already nopt, keep it no change.
+		 */
+		if (!strncmp(p, "nopt", 4) && IOMMU_DMA_MODE_IS_PASSTHROUGH())
+			iommu_default_dma_mode_set(IOMMU_DMA_MODE_LAZY);
 
 		gart_parse_options(p);
 
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 5dca666b22e6cd5..ace8cb467d742f9 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -78,7 +78,7 @@ choice
 	prompt "IOMMU dma mode"
 	depends on IOMMU_API
 	default IOMMU_DEFAULT_PASSTHROUGH if (PPC_POWERNV && PCI)
-	default IOMMU_DEFAULT_LAZY if S390_IOMMU
+	default IOMMU_DEFAULT_LAZY if (AMD_IOMMU || INTEL_IOMMU || S390_IOMMU)
 	default IOMMU_DEFAULT_STRICT
 	help
 	  This option allows IOMMU dma mode to be chose at build time, to
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index f7cdd2ab7f11f6c..44be42f1e887ea4 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -448,7 +448,7 @@ static int iommu_init_device(struct device *dev)
 	 * invalid address), we ignore the capability for the device so
 	 * it'll be forced to go into translation mode.
 	 */
-	if ((iommu_pass_through || !amd_iommu_force_isolation) &&
+	if ((IOMMU_DMA_MODE_IS_PASSTHROUGH() || !amd_iommu_force_isolation) &&
 	    dev_is_pci(dev) && pci_iommuv2_capable(to_pci_dev(dev))) {
 		struct amd_iommu *iommu;
 
@@ -2274,7 +2274,7 @@ static int amd_iommu_add_device(struct device *dev)
 
 	BUG_ON(!dev_data);
 
-	if (iommu_pass_through || dev_data->iommu_v2)
+	if (IOMMU_DMA_MODE_IS_PASSTHROUGH() || dev_data->iommu_v2)
 		iommu_request_dm_for_dev(dev);
 
 	/* Domains are initialized for this device - have a look what we ended up with */
@@ -2479,7 +2479,7 @@ static void __unmap_single(struct dma_ops_domain *dma_dom,
 		start += PAGE_SIZE;
 	}
 
-	if (amd_iommu_unmap_flush) {
+	if (IOMMU_DMA_MODE_IS_STRICT()) {
 		domain_flush_tlb(&dma_dom->domain);
 		domain_flush_complete(&dma_dom->domain);
 		dma_ops_free_iova(dma_dom, dma_addr, pages);
@@ -2853,10 +2853,10 @@ int __init amd_iommu_init_api(void)
 
 int __init amd_iommu_init_dma_ops(void)
 {
-	swiotlb        = (iommu_pass_through || sme_me_mask) ? 1 : 0;
+	swiotlb = (IOMMU_DMA_MODE_IS_PASSTHROUGH() || sme_me_mask) ? 1 : 0;
 	iommu_detected = 1;
 
-	if (amd_iommu_unmap_flush)
+	if (IOMMU_DMA_MODE_IS_STRICT())
 		pr_info("IO/TLB flush on unmap enabled\n");
 	else
 		pr_info("Lazy IO/TLB flushing enabled\n");
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 1b1378619fc9ec2..eae18aae2bafd39 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -166,8 +166,6 @@ struct ivmd_header {
 					   to handle */
 LIST_HEAD(amd_iommu_unity_map);		/* a list of required unity mappings
 					   we find in ACPI */
-bool amd_iommu_unmap_flush;		/* if true, flush on every unmap */
-
 LIST_HEAD(amd_iommu_list);		/* list of all AMD IOMMUs in the
 					   system */
 
@@ -2857,7 +2855,7 @@ static int __init parse_amd_iommu_options(char *str)
 {
 	for (; *str; ++str) {
 		if (strncmp(str, "fullflush", 9) == 0)
-			amd_iommu_unmap_flush = true;
+			iommu_default_dma_mode_set(IOMMU_DMA_MODE_STRICT);
 		if (strncmp(str, "off", 3) == 0)
 			amd_iommu_disabled = true;
 		if (strncmp(str, "force_isolation", 15) == 0)
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 87965e4d964771b..724182f158523a1 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -743,12 +743,6 @@ struct unity_map_entry {
 /* allocation bitmap for domain ids */
 extern unsigned long *amd_iommu_pd_alloc_bitmap;
 
-/*
- * If true, the addresses will be flushed on unmap time, not when
- * they are reused
- */
-extern bool amd_iommu_unmap_flush;
-
 /* Smallest max PASID supported by any IOMMU in the system */
 extern u32 amd_iommu_max_pasid;
 
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 28cb713d728ceef..57203f895382831 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -362,7 +362,6 @@ static int domain_detach_iommu(struct dmar_domain *domain,
 
 static int dmar_map_gfx = 1;
 static int dmar_forcedac;
-static int intel_iommu_strict;
 static int intel_iommu_superpage = 1;
 static int intel_iommu_sm;
 static int iommu_identity_mapping;
@@ -453,7 +452,7 @@ static int __init intel_iommu_setup(char *str)
 			dmar_forcedac = 1;
 		} else if (!strncmp(str, "strict", 6)) {
 			pr_info("Disable batched IOTLB flush\n");
-			intel_iommu_strict = 1;
+			iommu_default_dma_mode_set(IOMMU_DMA_MODE_STRICT);
 		} else if (!strncmp(str, "sp_off", 6)) {
 			pr_info("Disable supported super page\n");
 			intel_iommu_superpage = 0;
@@ -3408,7 +3407,7 @@ static int __init init_dmars(void)
 		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH);
 	}
 
-	if (iommu_pass_through)
+	if (IOMMU_DMA_MODE_IS_PASSTHROUGH())
 		iommu_identity_mapping |= IDENTMAP_ALL;
 
 #ifdef CONFIG_INTEL_IOMMU_BROKEN_GFX_WA
@@ -3749,7 +3748,7 @@ static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size)
 
 	freelist = domain_unmap(domain, start_pfn, last_pfn);
 
-	if (intel_iommu_strict) {
+	if (IOMMU_DMA_MODE_IS_STRICT()) {
 		iommu_flush_iotlb_psi(iommu, domain, start_pfn,
 				      nrpages, !freelist, 0);
 		/* free iova */
@@ -5460,7 +5459,7 @@ static void quirk_calpella_no_shadow_gtt(struct pci_dev *dev)
 	} else if (dmar_map_gfx) {
 		/* we have to ensure the gfx device is idle before we flush */
 		pci_info(dev, "Disabling batched IOTLB flush on Ironlake\n");
-		intel_iommu_strict = 1;
+		iommu_default_dma_mode_set(IOMMU_DMA_MODE_STRICT);
        }
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x0040, quirk_calpella_no_shadow_gtt);
-- 
1.8.3