Merge tag 'iommu-updates-v5.4' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:

 - batched unmap support for the IOMMU-API

 - support for unlocked command queueing in the ARM-SMMU driver

 - rework the ATS support in the ARM-SMMU driver

 - more refactoring in the ARM-SMMU driver to support hardware
   implemention specific quirks and errata

 - bounce buffering DMA-API implementatation in the Intel VT-d driver
   for untrusted devices (like Thunderbolt devices)

 - fixes for runtime PM support in the OMAP iommu driver

 - MT8183 IOMMU support in the Mediatek IOMMU driver

 - rework of the way the IOMMU core sets the default domain type for
   groups. Changing the default domain type on x86 does not require two
   kernel parameters anymore.

 - more smaller fixes and cleanups

* tag 'iommu-updates-v5.4' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (113 commits)
  iommu/vt-d: Declare Broadwell igfx dmar support snafu
  iommu/vt-d: Add Scalable Mode fault information
  iommu/vt-d: Use bounce buffer for untrusted devices
  iommu/vt-d: Add trace events for device dma map/unmap
  iommu/vt-d: Don't switch off swiotlb if bounce page is used
  iommu/vt-d: Check whether device requires bounce buffer
  swiotlb: Split size parameter to map/unmap APIs
  iommu/omap: Mark pm functions __maybe_unused
  iommu/ipmmu-vmsa: Disable cache snoop transactions on R-Car Gen3
  iommu/ipmmu-vmsa: Move IMTTBCR_SL0_TWOBIT_* to restore sort order
  iommu: Don't use sme_active() in generic code
  iommu/arm-smmu-v3: Fix build error without CONFIG_PCI_ATS
  iommu/qcom: Use struct_size() helper
  iommu: Remove wrong default domain comments
  iommu/dma: Fix for dereferencing before null checking
  iommu/mediatek: Clean up struct mtk_smi_iommu
  memory: mtk-smi: Get rid of need_larbid
  iommu/mediatek: Fix VLD_PA_RNG register backup when suspend
  memory: mtk-smi: Add bus_sel for mt8183
  memory: mtk-smi: Invoke pm runtime_callback to enable clocks
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -1732,6 +1732,11 @@
 			Note that using this option lowers the security
 			provided by tboot because it makes the system
 			vulnerable to DMA attacks.
+		nobounce [Default off]
+			Disable bounce buffer for unstrusted devices such as
+			the Thunderbolt devices. This will treat the untrusted
+			devices as the trusted ones, hence might expose security
+			risks of DMA attacks.
 
 	intel_idle.max_cstate=	[KNL,HW,ACPI,X86]
 			0	disables intel_idle and fall back on acpi_idle.
@@ -1811,7 +1816,7 @@
 			  synchronously.
 
 	iommu.passthrough=
-			[ARM64] Configure DMA to bypass the IOMMU by default.
+			[ARM64, X86] Configure DMA to bypass the IOMMU by default.
 			Format: { "0" | "1" }
 			0 - Use IOMMU translation for DMA.
 			1 - Bypass the IOMMU for DMA.

Documentation/devicetree/bindings/iommu/mediatek,iommu.txt

@@ -11,10 +11,23 @@ ARM Short-Descriptor translation table format for address translation.
                |
               m4u (Multimedia Memory Management Unit)
                |
+          +--------+
+          |        |
+      gals0-rx   gals1-rx    (Global Async Local Sync rx)
+          |        |
+          |        |
+      gals0-tx   gals1-tx    (Global Async Local Sync tx)
+          |        |          Some SoCs may have GALS.
+          +--------+
+               |
            SMI Common(Smart Multimedia Interface Common)
                |
        +----------------+-------
        |                |
+       |             gals-rx        There may be GALS in some larbs.
+       |                |
+       |                |
+       |             gals-tx
        |                |
    SMI larb0        SMI larb1   ... SoCs have several SMI local arbiter(larb).
    (display)         (vdec)
@@ -36,6 +49,10 @@ each local arbiter.
 like display, video decode, and camera. And there are different ports
 in each larb. Take a example, There are many ports like MC, PP, VLD in the
 video decode local arbiter, all these ports are according to the video HW.
+  In some SoCs, there may be a GALS(Global Async Local Sync) module between
+smi-common and m4u, and additional GALS module between smi-larb and
+smi-common. GALS can been seen as a "asynchronous fifo" which could help
+synchronize for the modules in different clock frequency.
 
 Required properties:
 - compatible : must be one of the following string:
@@ -44,18 +61,25 @@ Required properties:
 	"mediatek,mt7623-m4u", "mediatek,mt2701-m4u" for mt7623 which uses
 						     generation one m4u HW.
 	"mediatek,mt8173-m4u" for mt8173 which uses generation two m4u HW.
+	"mediatek,mt8183-m4u" for mt8183 which uses generation two m4u HW.
 - reg : m4u register base and size.
 - interrupts : the interrupt of m4u.
 - clocks : must contain one entry for each clock-names.
-- clock-names : must be "bclk", It is the block clock of m4u.
+- clock-names : Only 1 optional clock:
+  - "bclk": the block clock of m4u.
+  Here is the list which require this "bclk":
+  - mt2701, mt2712, mt7623 and mt8173.
+  Note that m4u use the EMI clock which always has been enabled before kernel
+  if there is no this "bclk".
 - mediatek,larbs : List of phandle to the local arbiters in the current Socs.
 	Refer to bindings/memory-controllers/mediatek,smi-larb.txt. It must sort
 	according to the local arbiter index, like larb0, larb1, larb2...
 - iommu-cells : must be 1. This is the mtk_m4u_id according to the HW.
 	Specifies the mtk_m4u_id as defined in
 	dt-binding/memory/mt2701-larb-port.h for mt2701, mt7623
-	dt-binding/memory/mt2712-larb-port.h for mt2712, and
-	dt-binding/memory/mt8173-larb-port.h for mt8173.
+	dt-binding/memory/mt2712-larb-port.h for mt2712,
+	dt-binding/memory/mt8173-larb-port.h for mt8173, and
+	dt-binding/memory/mt8183-larb-port.h for mt8183.
 
 Example:
 	iommu: iommu@10205000 {

Documentation/devicetree/bindings/memory-controllers/mediatek,smi-common.txt

@@ -2,9 +2,10 @@ SMI (Smart Multimedia Interface) Common
 
 The hardware block diagram please check bindings/iommu/mediatek,iommu.txt
 
-Mediatek SMI have two generations of HW architecture, mt2712 and mt8173 use
-the second generation of SMI HW while mt2701 uses the first generation HW of
-SMI.
+Mediatek SMI have two generations of HW architecture, here is the list
+which generation the SoCs use:
+generation 1: mt2701 and mt7623.
+generation 2: mt2712, mt8173 and mt8183.
 
 There's slight differences between the two SMI, for generation 2, the
 register which control the iommu port is at each larb's register base. But
@@ -19,6 +20,7 @@ Required properties:
 	"mediatek,mt2712-smi-common"
 	"mediatek,mt7623-smi-common", "mediatek,mt2701-smi-common"
 	"mediatek,mt8173-smi-common"
+	"mediatek,mt8183-smi-common"
 - reg : the register and size of the SMI block.
 - power-domains : a phandle to the power domain of this local arbiter.
 - clocks : Must contain an entry for each entry in clock-names.
@@ -30,6 +32,10 @@ Required properties:
 	    They may be the same if both source clocks are the same.
   - "async" : asynchronous clock, it help transform the smi clock into the emi
 	      clock domain, this clock is only needed by generation 1 smi HW.
+  and these 2 option clocks for generation 2 smi HW:
+  - "gals0": the path0 clock of GALS(Global Async Local Sync).
+  - "gals1": the path1 clock of GALS(Global Async Local Sync).
+  Here is the list which has this GALS: mt8183.
 
 Example:
 	smi_common: smi@14022000 {

Documentation/devicetree/bindings/memory-controllers/mediatek,smi-larb.txt

@@ -8,6 +8,7 @@ Required properties:
 		"mediatek,mt2712-smi-larb"
 		"mediatek,mt7623-smi-larb", "mediatek,mt2701-smi-larb"
 		"mediatek,mt8173-smi-larb"
+		"mediatek,mt8183-smi-larb"
 - reg : the register and size of this local arbiter.
 - mediatek,smi : a phandle to the smi_common node.
 - power-domains : a phandle to the power domain of this local arbiter.
@@ -16,6 +17,9 @@ Required properties:
   - "apb" : Advanced Peripheral Bus clock, It's the clock for setting
 	    the register.
   - "smi" : It's the clock for transfer data and command.
+  and this optional clock name:
+  - "gals": the clock for GALS(Global Async Local Sync).
+  Here is the list which has this GALS: mt8183.
 
 Required property for mt2701, mt2712 and mt7623:
 - mediatek,larb-id :the hardware id of this larb.

MAINTAINERS

@@ -1342,8 +1342,7 @@ M:	Will Deacon <will@kernel.org>
 R:	Robin Murphy <robin.murphy@arm.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
-F:	drivers/iommu/arm-smmu.c
-F:	drivers/iommu/arm-smmu-v3.c
+F:	drivers/iommu/arm-smmu*
 F:	drivers/iommu/io-pgtable-arm.c
 F:	drivers/iommu/io-pgtable-arm-v7s.c
 

arch/arm/mach-omap2/Makefile

@@ -229,3 +229,5 @@ include/generated/ti-pm-asm-offsets.h: arch/arm/mach-omap2/pm-asm-offsets.s FORC
 $(obj)/sleep33xx.o $(obj)/sleep43xx.o: include/generated/ti-pm-asm-offsets.h
 
 targets += pm-asm-offsets.s
+
+obj-$(CONFIG_OMAP_IOMMU)		+= omap-iommu.o

arch/arm/mach-omap2/omap-iommu.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * OMAP IOMMU quirks for various TI SoCs
+ *
+ * Copyright (C) 2015-2019 Texas Instruments Incorporated - http://www.ti.com/
+ *      Suman Anna <s-anna@ti.com>
+ */
+
+#include <linux/platform_device.h>
+#include <linux/err.h>
+
+#include "omap_hwmod.h"
+#include "omap_device.h"
+#include "powerdomain.h"
+
+int omap_iommu_set_pwrdm_constraint(struct platform_device *pdev, bool request,
+				    u8 *pwrst)
+{
+	struct powerdomain *pwrdm;
+	struct omap_device *od;
+	u8 next_pwrst;
+
+	od = to_omap_device(pdev);
+	if (!od)
+		return -ENODEV;
+
+	if (od->hwmods_cnt != 1)
+		return -EINVAL;
+
+	pwrdm = omap_hwmod_get_pwrdm(od->hwmods[0]);
+	if (!pwrdm)
+		return -EINVAL;
+
+	if (request)
+		*pwrst = pwrdm_read_next_pwrst(pwrdm);
+
+	if (*pwrst > PWRDM_POWER_RET)
+		return 0;
+
+	next_pwrst = request ? PWRDM_POWER_ON : *pwrst;
+
+	return pwrdm_set_next_pwrst(pwrdm, next_pwrst);
+}

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

arch/ia64/kernel/pci-dma.c

@@ -22,8 +22,6 @@ int force_iommu __read_mostly = 1;
 int force_iommu __read_mostly;
 #endif
 
-int iommu_pass_through;
-
 static int __init pci_iommu_init(void)
 {
 	if (iommu_detected)

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)

arch/x86/kernel/pci-dma.c

 // SPDX-License-Identifier: GPL-2.0
 #include <linux/dma-direct.h>
 #include <linux/dma-debug.h>
+#include <linux/iommu.h>
 #include <linux/dmar.h>
 #include <linux/export.h>
 #include <linux/memblock.h>
@@ -34,21 +35,6 @@ int no_iommu __read_mostly;
 /* 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[];
 
 void __init pci_iommu_alloc(void)
@@ -120,9 +106,9 @@ static __init int iommu_setup(char *p)
 			swiotlb = 1;
 #endif
 		if (!strncmp(p, "pt", 2))
-			iommu_pass_through = 1;
+			iommu_set_default_passthrough(true);
 		if (!strncmp(p, "nopt", 4))
-			iommu_pass_through = 0;
+			iommu_set_default_translated(true);
 
 		gart_parse_options(p);
 

drivers/gpu/drm/panfrost/panfrost_mmu.c

@@ -222,7 +222,7 @@ void panfrost_mmu_unmap(struct panfrost_gem_object *bo)
 		size_t unmapped_page;
 		size_t pgsize = get_pgsize(iova, len - unmapped_len);
 
-		unmapped_page = ops->unmap(ops, iova, pgsize);
+		unmapped_page = ops->unmap(ops, iova, pgsize, NULL);
 		if (!unmapped_page)
 			break;
 
@@ -247,20 +247,28 @@ static void mmu_tlb_inv_context_s1(void *cookie)
 	mmu_hw_do_operation(pfdev, 0, 0, ~0UL, AS_COMMAND_FLUSH_MEM);
 }
 
-static void mmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
-				     size_t granule, bool leaf, void *cookie)
-{}
-
 static void mmu_tlb_sync_context(void *cookie)
 {
 	//struct panfrost_device *pfdev = cookie;
 	// TODO: Wait 1000 GPU cycles for HW_ISSUE_6367/T60X
 }
 
-static const struct iommu_gather_ops mmu_tlb_ops = {
+static void mmu_tlb_flush_walk(unsigned long iova, size_t size, size_t granule,
+			       void *cookie)
+{
+	mmu_tlb_sync_context(cookie);
+}
+
+static void mmu_tlb_flush_leaf(unsigned long iova, size_t size, size_t granule,
+			       void *cookie)
+{
+	mmu_tlb_sync_context(cookie);
+}
+
+static const struct iommu_flush_ops mmu_tlb_ops = {
 	.tlb_flush_all	= mmu_tlb_inv_context_s1,
-	.tlb_add_flush	= mmu_tlb_inv_range_nosync,
-	.tlb_sync	= mmu_tlb_sync_context,
+	.tlb_flush_walk = mmu_tlb_flush_walk,
+	.tlb_flush_leaf = mmu_tlb_flush_leaf,
 };
 
 static const char *access_type_name(struct panfrost_device *pfdev,

drivers/iommu/Kconfig

@@ -182,6 +182,7 @@ config INTEL_IOMMU
 	select IOMMU_IOVA
 	select NEED_DMA_MAP_STATE
 	select DMAR_TABLE
+	select SWIOTLB
 	help
 	  DMA remapping (DMAR) devices support enables independent address
 	  translations for Direct Memory Access (DMA) from devices.

drivers/iommu/Makefile

@@ -10,13 +10,14 @@ obj-$(CONFIG_IOMMU_IO_PGTABLE_LPAE) += io-pgtable-arm.o
 obj-$(CONFIG_IOMMU_IOVA) += iova.o
 obj-$(CONFIG_OF_IOMMU)	+= of_iommu.o
 obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o
-obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o
+obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o amd_iommu_quirks.o
 obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd_iommu_debugfs.o
 obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o
-obj-$(CONFIG_ARM_SMMU) += arm-smmu.o
+obj-$(CONFIG_ARM_SMMU) += arm-smmu.o arm-smmu-impl.o
 obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o
 obj-$(CONFIG_DMAR_TABLE) += dmar.o
 obj-$(CONFIG_INTEL_IOMMU) += intel-iommu.o intel-pasid.o
+obj-$(CONFIG_INTEL_IOMMU) += intel-trace.o
 obj-$(CONFIG_INTEL_IOMMU_DEBUGFS) += intel-iommu-debugfs.o
 obj-$(CONFIG_INTEL_IOMMU_SVM) += intel-svm.o
 obj-$(CONFIG_IPMMU_VMSA) += ipmmu-vmsa.o

drivers/iommu/amd_iommu.c

@@ -436,7 +436,7 @@ 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_default_passthrough() || !amd_iommu_force_isolation) &&
 	    dev_is_pci(dev) && pci_iommuv2_capable(to_pci_dev(dev))) {
 		struct amd_iommu *iommu;
 
@@ -2256,7 +2256,7 @@ static int amd_iommu_add_device(struct device *dev)
 
 	BUG_ON(!dev_data);
 
-	if (iommu_pass_through || dev_data->iommu_v2)
+	if (dev_data->iommu_v2)
 		iommu_request_dm_for_dev(dev);
 
 	/* Domains are initialized for this device - have a look what we ended up with */
@@ -2577,7 +2577,9 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
 
 			bus_addr  = address + s->dma_address + (j << PAGE_SHIFT);
 			phys_addr = (sg_phys(s) & PAGE_MASK) + (j << PAGE_SHIFT);
-			ret = iommu_map_page(domain, bus_addr, phys_addr, PAGE_SIZE, prot, GFP_ATOMIC);
+			ret = iommu_map_page(domain, bus_addr, phys_addr,
+					     PAGE_SIZE, prot,
+					     GFP_ATOMIC | __GFP_NOWARN);
 			if (ret)
 				goto out_unmap;
 
@@ -2835,7 +2837,7 @@ 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_default_passthrough() || sme_me_mask) ? 1 : 0;
 	iommu_detected = 1;
 
 	if (amd_iommu_unmap_flush)
@@ -3085,7 +3087,8 @@ static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova,
 }
 
 static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova,
-			   size_t page_size)
+			      size_t page_size,
+			      struct iommu_iotlb_gather *gather)
 {
 	struct protection_domain *domain = to_pdomain(dom);
 	size_t unmap_size;
@@ -3226,9 +3229,10 @@ static void amd_iommu_flush_iotlb_all(struct iommu_domain *domain)
 	domain_flush_complete(dom);
 }
 
-static void amd_iommu_iotlb_range_add(struct iommu_domain *domain,
-				      unsigned long iova, size_t size)
+static void amd_iommu_iotlb_sync(struct iommu_domain *domain,
+				 struct iommu_iotlb_gather *gather)
 {
+	amd_iommu_flush_iotlb_all(domain);
 }
 
 const struct iommu_ops amd_iommu_ops = {
@@ -3249,8 +3253,7 @@ const struct iommu_ops amd_iommu_ops = {
 	.is_attach_deferred = amd_iommu_is_attach_deferred,
 	.pgsize_bitmap	= AMD_IOMMU_PGSIZES,
 	.flush_iotlb_all = amd_iommu_flush_iotlb_all,
-	.iotlb_range_add = amd_iommu_iotlb_range_add,
-	.iotlb_sync = amd_iommu_flush_iotlb_all,
+	.iotlb_sync = amd_iommu_iotlb_sync,
 };
 
 /*****************************************************************************
@@ -4343,13 +4346,62 @@ static const struct irq_domain_ops amd_ir_domain_ops = {
 	.deactivate = irq_remapping_deactivate,
 };
 
+int amd_iommu_activate_guest_mode(void *data)
+{
+	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
+	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
+
+	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
+	    !entry || entry->lo.fields_vapic.guest_mode)
+		return 0;
+
+	entry->lo.val = 0;
+	entry->hi.val = 0;
+
+	entry->lo.fields_vapic.guest_mode  = 1;
+	entry->lo.fields_vapic.ga_log_intr = 1;
+	entry->hi.fields.ga_root_ptr       = ir_data->ga_root_ptr;
+	entry->hi.fields.vector            = ir_data->ga_vector;
+	entry->lo.fields_vapic.ga_tag      = ir_data->ga_tag;
+
+	return modify_irte_ga(ir_data->irq_2_irte.devid,
+			      ir_data->irq_2_irte.index, entry, NULL);
+}
+EXPORT_SYMBOL(amd_iommu_activate_guest_mode);
+
+int amd_iommu_deactivate_guest_mode(void *data)
+{
+	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
+	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
+	struct irq_cfg *cfg = ir_data->cfg;
+
+	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
+	    !entry || !entry->lo.fields_vapic.guest_mode)
+		return 0;
+
+	entry->lo.val = 0;
+	entry->hi.val = 0;
+
+	entry->lo.fields_remap.dm          = apic->irq_dest_mode;
+	entry->lo.fields_remap.int_type    = apic->irq_delivery_mode;
+	entry->hi.fields.vector            = cfg->vector;
+	entry->lo.fields_remap.destination =
+				APICID_TO_IRTE_DEST_LO(cfg->dest_apicid);
+	entry->hi.fields.destination =
+				APICID_TO_IRTE_DEST_HI(cfg->dest_apicid);
+
+	return modify_irte_ga(ir_data->irq_2_irte.devid,
+			      ir_data->irq_2_irte.index, entry, NULL);
+}
+EXPORT_SYMBOL(amd_iommu_deactivate_guest_mode);
+
 static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
 {
+	int ret;
 	struct amd_iommu *iommu;
 	struct amd_iommu_pi_data *pi_data = vcpu_info;
 	struct vcpu_data *vcpu_pi_info = pi_data->vcpu_data;
 	struct amd_ir_data *ir_data = data->chip_data;
-	struct irte_ga *irte = (struct irte_ga *) ir_data->entry;
 	struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
 	struct iommu_dev_data *dev_data = search_dev_data(irte_info->devid);
 
@@ -4360,6 +4412,7 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
 	if (!dev_data || !dev_data->use_vapic)
 		return 0;
 
+	ir_data->cfg = irqd_cfg(data);
 	pi_data->ir_data = ir_data;
 
 	/* Note:
@@ -4378,37 +4431,24 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
 
 	pi_data->prev_ga_tag = ir_data->cached_ga_tag;
 	if (pi_data->is_guest_mode) {
-		/* Setting */
-		irte->hi.fields.ga_root_ptr = (pi_data->base >> 12);
-		irte->hi.fields.vector = vcpu_pi_info->vector;
-		irte->lo.fields_vapic.ga_log_intr = 1;
-		irte->lo.fields_vapic.guest_mode = 1;
-		irte->lo.fields_vapic.ga_tag = pi_data->ga_tag;
-
-		ir_data->cached_ga_tag = pi_data->ga_tag;
+		ir_data->ga_root_ptr = (pi_data->base >> 12);
+		ir_data->ga_vector = vcpu_pi_info->vector;
+		ir_data->ga_tag = pi_data->ga_tag;
+		ret = amd_iommu_activate_guest_mode(ir_data);
+		if (!ret)
+			ir_data->cached_ga_tag = pi_data->ga_tag;
 	} else {
-		/* Un-Setting */
-		struct irq_cfg *cfg = irqd_cfg(data);
-
-		irte->hi.val = 0;
-		irte->lo.val = 0;
-		irte->hi.fields.vector = cfg->vector;
-		irte->lo.fields_remap.guest_mode = 0;
-		irte->lo.fields_remap.destination =
-				APICID_TO_IRTE_DEST_LO(cfg->dest_apicid);
-		irte->hi.fields.destination =
-				APICID_TO_IRTE_DEST_HI(cfg->dest_apicid);
-		irte->lo.fields_remap.int_type = apic->irq_delivery_mode;
-		irte->lo.fields_remap.dm = apic->irq_dest_mode;
+		ret = amd_iommu_deactivate_guest_mode(ir_data);
 
 		/*
 		 * This communicates the ga_tag back to the caller
 		 * so that it can do all the necessary clean up.
 		 */
-		ir_data->cached_ga_tag = 0;
+		if (!ret)
+			ir_data->cached_ga_tag = 0;
 	}
 
-	return modify_irte_ga(irte_info->devid, irte_info->index, irte, ir_data);
+	return ret;
 }
 
 

drivers/iommu/amd_iommu.h

+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef AMD_IOMMU_H
+#define AMD_IOMMU_H
+
+int __init add_special_device(u8 type, u8 id, u16 *devid, bool cmd_line);
+
+#ifdef CONFIG_DMI
+void amd_iommu_apply_ivrs_quirks(void);
+#else
+static void amd_iommu_apply_ivrs_quirks(void) { }
+#endif
+
+#endif

drivers/iommu/amd_iommu_init.c

@@ -32,6 +32,7 @@
 #include <asm/irq_remapping.h>
 
 #include <linux/crash_dump.h>
+#include "amd_iommu.h"
 #include "amd_iommu_proto.h"
 #include "amd_iommu_types.h"
 #include "irq_remapping.h"
@@ -1002,7 +1003,7 @@ static void __init set_dev_entry_from_acpi(struct amd_iommu *iommu,
 	set_iommu_for_device(iommu, devid);
 }
 
-static int __init add_special_device(u8 type, u8 id, u16 *devid, bool cmd_line)
+int __init add_special_device(u8 type, u8 id, u16 *devid, bool cmd_line)
 {
 	struct devid_map *entry;
 	struct list_head *list;
@@ -1153,6 +1154,8 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
 	if (ret)
 		return ret;
 
+	amd_iommu_apply_ivrs_quirks();
+
 	/*
 	 * First save the recommended feature enable bits from ACPI
 	 */

drivers/iommu/amd_iommu_quirks.c

+/* SPDX-License-Identifier: GPL-2.0-only */
+
+/*
+ * Quirks for AMD IOMMU
+ *
+ * Copyright (C) 2019 Kai-Heng Feng <kai.heng.feng@canonical.com>
+ */
+
+#ifdef CONFIG_DMI
+#include <linux/dmi.h>
+
+#include "amd_iommu.h"
+
+#define IVHD_SPECIAL_IOAPIC		1
+
+struct ivrs_quirk_entry {
+	u8 id;
+	u16 devid;
+};
+
+enum {
+	DELL_INSPIRON_7375 = 0,
+	DELL_LATITUDE_5495,
+	LENOVO_IDEAPAD_330S_15ARR,
+};
+
+static const struct ivrs_quirk_entry ivrs_ioapic_quirks[][3] __initconst = {
+	/* ivrs_ioapic[4]=00:14.0 ivrs_ioapic[5]=00:00.2 */
+	[DELL_INSPIRON_7375] = {
+		{ .id = 4, .devid = 0xa0 },
+		{ .id = 5, .devid = 0x2 },
+		{}
+	},
+	/* ivrs_ioapic[4]=00:14.0 */
+	[DELL_LATITUDE_5495] = {
+		{ .id = 4, .devid = 0xa0 },
+		{}
+	},
+	/* ivrs_ioapic[32]=00:14.0 */
+	[LENOVO_IDEAPAD_330S_15ARR] = {
+		{ .id = 32, .devid = 0xa0 },
+		{}
+	},
+	{}
+};
+
+static int __init ivrs_ioapic_quirk_cb(const struct dmi_system_id *d)
+{
+	const struct ivrs_quirk_entry *i;
+
+	for (i = d->driver_data; i->id != 0 && i->devid != 0; i++)
+		add_special_device(IVHD_SPECIAL_IOAPIC, i->id, (u16 *)&i->devid, 0);
+
+	return 0;
+}
+
+static const struct dmi_system_id ivrs_quirks[] __initconst = {
+	{
+		.callback = ivrs_ioapic_quirk_cb,
+		.ident = "Dell Inspiron 7375",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7375"),
+		},
+		.driver_data = (void *)&ivrs_ioapic_quirks[DELL_INSPIRON_7375],
+	},
+	{
+		.callback = ivrs_ioapic_quirk_cb,
+		.ident = "Dell Latitude 5495",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Latitude 5495"),
+		},
+		.driver_data = (void *)&ivrs_ioapic_quirks[DELL_LATITUDE_5495],
+	},
+	{
+		.callback = ivrs_ioapic_quirk_cb,
+		.ident = "Lenovo ideapad 330S-15ARR",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "81FB"),
+		},
+		.driver_data = (void *)&ivrs_ioapic_quirks[LENOVO_IDEAPAD_330S_15ARR],
+	},
+	{}
+};
+
+void __init amd_iommu_apply_ivrs_quirks(void)
+{
+	dmi_check_system(ivrs_quirks);
+}
+#endif

drivers/iommu/amd_iommu_types.h

@@ -873,6 +873,15 @@ struct amd_ir_data {
 	struct msi_msg msi_entry;
 	void *entry;    /* Pointer to union irte or struct irte_ga */
 	void *ref;      /* Pointer to the actual irte */
+
+	/**
+	 * Store information for activate/de-activate
+	 * Guest virtual APIC mode during runtime.
+	 */
+	struct irq_cfg *cfg;
+	int ga_vector;
+	int ga_root_ptr;
+	int ga_tag;
 };
 
 struct amd_irte_ops {

drivers/iommu/arm-smmu-impl.c

+// SPDX-License-Identifier: GPL-2.0-only
+// Miscellaneous Arm SMMU implementation and integration quirks
+// Copyright (C) 2019 Arm Limited
+
+#define pr_fmt(fmt) "arm-smmu: " fmt
+
+#include <linux/bitfield.h>
+#include <linux/of.h>
+
+#include "arm-smmu.h"
+
+
+static int arm_smmu_gr0_ns(int offset)
+{
+	switch(offset) {
+	case ARM_SMMU_GR0_sCR0:
+	case ARM_SMMU_GR0_sACR:
+	case ARM_SMMU_GR0_sGFSR:
+	case ARM_SMMU_GR0_sGFSYNR0:
+	case ARM_SMMU_GR0_sGFSYNR1:
+	case ARM_SMMU_GR0_sGFSYNR2:
+		return offset + 0x400;
+	default:
+		return offset;
+	}
+}
+
+static u32 arm_smmu_read_ns(struct arm_smmu_device *smmu, int page,
+			    int offset)
+{
+	if (page == ARM_SMMU_GR0)
+		offset = arm_smmu_gr0_ns(offset);
+	return readl_relaxed(arm_smmu_page(smmu, page) + offset);
+}
+
+static void arm_smmu_write_ns(struct arm_smmu_device *smmu, int page,
+			      int offset, u32 val)
+{
+	if (page == ARM_SMMU_GR0)
+		offset = arm_smmu_gr0_ns(offset);
+	writel_relaxed(val, arm_smmu_page(smmu, page) + offset);
+}
+
+/* Since we don't care for sGFAR, we can do without 64-bit accessors */
+static const struct arm_smmu_impl calxeda_impl = {
+	.read_reg = arm_smmu_read_ns,
+	.write_reg = arm_smmu_write_ns,
+};
+
+
+struct cavium_smmu {
+	struct arm_smmu_device smmu;
+	u32 id_base;
+};
+
+static int cavium_cfg_probe(struct arm_smmu_device *smmu)
+{
+	static atomic_t context_count = ATOMIC_INIT(0);
+	struct cavium_smmu *cs = container_of(smmu, struct cavium_smmu, smmu);
+	/*
+	 * Cavium CN88xx erratum #27704.
+	 * Ensure ASID and VMID allocation is unique across all SMMUs in
+	 * the system.
+	 */
+	cs->id_base = atomic_fetch_add(smmu->num_context_banks, &context_count);
+	dev_notice(smmu->dev, "\tenabling workaround for Cavium erratum 27704\n");
+
+	return 0;
+}
+
+static int cavium_init_context(struct arm_smmu_domain *smmu_domain)
+{
+	struct cavium_smmu *cs = container_of(smmu_domain->smmu,
+					      struct cavium_smmu, smmu);
+
+	if (smmu_domain->stage == ARM_SMMU_DOMAIN_S2)
+		smmu_domain->cfg.vmid += cs->id_base;
+	else
+		smmu_domain->cfg.asid += cs->id_base;
+
+	return 0;
+}
+
+static const struct arm_smmu_impl cavium_impl = {
+	.cfg_probe = cavium_cfg_probe,
+	.init_context = cavium_init_context,
+};
+
+static struct arm_smmu_device *cavium_smmu_impl_init(struct arm_smmu_device *smmu)
+{
+	struct cavium_smmu *cs;
+
+	cs = devm_kzalloc(smmu->dev, sizeof(*cs), GFP_KERNEL);
+	if (!cs)
+		return ERR_PTR(-ENOMEM);
+
+	cs->smmu = *smmu;
+	cs->smmu.impl = &cavium_impl;
+
+	devm_kfree(smmu->dev, smmu);
+
+	return &cs->smmu;
+}
+
+
+#define ARM_MMU500_ACTLR_CPRE		(1 << 1)
+
+#define ARM_MMU500_ACR_CACHE_LOCK	(1 << 26)
+#define ARM_MMU500_ACR_S2CRB_TLBEN	(1 << 10)
+#define ARM_MMU500_ACR_SMTNMB_TLBEN	(1 << 8)
+
+static int arm_mmu500_reset(struct arm_smmu_device *smmu)
+{
+	u32 reg, major;
+	int i;
+	/*
+	 * On MMU-500 r2p0 onwards we need to clear ACR.CACHE_LOCK before
+	 * writes to the context bank ACTLRs will stick. And we just hope that
+	 * Secure has also cleared SACR.CACHE_LOCK for this to take effect...
+	 */
+	reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_ID7);
+	major = FIELD_GET(ID7_MAJOR, reg);
+	reg = arm_smmu_gr0_read(smmu, ARM_SMMU_GR0_sACR);
+	if (major >= 2)
+		reg &= ~ARM_MMU500_ACR_CACHE_LOCK;
+	/*
+	 * Allow unmatched Stream IDs to allocate bypass
+	 * TLB entries for reduced latency.
+	 */
+	reg |= ARM_MMU500_ACR_SMTNMB_TLBEN | ARM_MMU500_ACR_S2CRB_TLBEN;
+	arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sACR, reg);
+
+	/*
+	 * Disable MMU-500's not-particularly-beneficial next-page
+	 * prefetcher for the sake of errata #841119 and #826419.
+	 */
+	for (i = 0; i < smmu->num_context_banks; ++i) {
+		reg = arm_smmu_cb_read(smmu, i, ARM_SMMU_CB_ACTLR);
+		reg &= ~ARM_MMU500_ACTLR_CPRE;
+		arm_smmu_cb_write(smmu, i, ARM_SMMU_CB_ACTLR, reg);
+	}
+
+	return 0;
+}
+
+static const struct arm_smmu_impl arm_mmu500_impl = {
+	.reset = arm_mmu500_reset,
+};
+
+
+struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu)
+{
+	/*
+	 * We will inevitably have to combine model-specific implementation
+	 * quirks with platform-specific integration quirks, but everything
+	 * we currently support happens to work out as straightforward
+	 * mutually-exclusive assignments.
+	 */
+	switch (smmu->model) {
+	case ARM_MMU500:
+		smmu->impl = &arm_mmu500_impl;
+		break;
+	case CAVIUM_SMMUV2:
+		return cavium_smmu_impl_init(smmu);
+	default:
+		break;
+	}
+
+	if (of_property_read_bool(smmu->dev->of_node,
+				  "calxeda,smmu-secure-config-access"))
+		smmu->impl = &calxeda_impl;
+
+	return smmu;
+}

drivers/iommu/arm-smmu-regs.h

-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * IOMMU API for ARM architected SMMU implementations.
- *
- * Copyright (C) 2013 ARM Limited
- *
- * Author: Will Deacon <will.deacon@arm.com>
- */
-
-#ifndef _ARM_SMMU_REGS_H
-#define _ARM_SMMU_REGS_H
-
-/* Configuration registers */
-#define ARM_SMMU_GR0_sCR0		0x0
-#define sCR0_CLIENTPD			(1 << 0)
-#define sCR0_GFRE			(1 << 1)
-#define sCR0_GFIE			(1 << 2)
-#define sCR0_EXIDENABLE			(1 << 3)
-#define sCR0_GCFGFRE			(1 << 4)
-#define sCR0_GCFGFIE			(1 << 5)
-#define sCR0_USFCFG			(1 << 10)
-#define sCR0_VMIDPNE			(1 << 11)
-#define sCR0_PTM			(1 << 12)
-#define sCR0_FB				(1 << 13)
-#define sCR0_VMID16EN			(1 << 31)
-#define sCR0_BSU_SHIFT			14
-#define sCR0_BSU_MASK			0x3
-
-/* Auxiliary Configuration register */
-#define ARM_SMMU_GR0_sACR		0x10
-
-/* Identification registers */
-#define ARM_SMMU_GR0_ID0		0x20
-#define ARM_SMMU_GR0_ID1		0x24
-#define ARM_SMMU_GR0_ID2		0x28
-#define ARM_SMMU_GR0_ID3		0x2c
-#define ARM_SMMU_GR0_ID4		0x30
-#define ARM_SMMU_GR0_ID5		0x34
-#define ARM_SMMU_GR0_ID6		0x38
-#define ARM_SMMU_GR0_ID7		0x3c
-#define ARM_SMMU_GR0_sGFSR		0x48
-#define ARM_SMMU_GR0_sGFSYNR0		0x50
-#define ARM_SMMU_GR0_sGFSYNR1		0x54
-#define ARM_SMMU_GR0_sGFSYNR2		0x58
-
-#define ID0_S1TS			(1 << 30)
-#define ID0_S2TS			(1 << 29)
-#define ID0_NTS				(1 << 28)
-#define ID0_SMS				(1 << 27)
-#define ID0_ATOSNS			(1 << 26)
-#define ID0_PTFS_NO_AARCH32		(1 << 25)
-#define ID0_PTFS_NO_AARCH32S		(1 << 24)
-#define ID0_CTTW			(1 << 14)
-#define ID0_NUMIRPT_SHIFT		16
-#define ID0_NUMIRPT_MASK		0xff
-#define ID0_NUMSIDB_SHIFT		9
-#define ID0_NUMSIDB_MASK		0xf
-#define ID0_EXIDS			(1 << 8)
-#define ID0_NUMSMRG_SHIFT		0
-#define ID0_NUMSMRG_MASK		0xff
-
-#define ID1_PAGESIZE			(1 << 31)
-#define ID1_NUMPAGENDXB_SHIFT		28
-#define ID1_NUMPAGENDXB_MASK		7
-#define ID1_NUMS2CB_SHIFT		16
-#define ID1_NUMS2CB_MASK		0xff
-#define ID1_NUMCB_SHIFT			0
-#define ID1_NUMCB_MASK			0xff
-
-#define ID2_OAS_SHIFT			4
-#define ID2_OAS_MASK			0xf
-#define ID2_IAS_SHIFT			0
-#define ID2_IAS_MASK			0xf
-#define ID2_UBS_SHIFT			8
-#define ID2_UBS_MASK			0xf
-#define ID2_PTFS_4K			(1 << 12)
-#define ID2_PTFS_16K			(1 << 13)
-#define ID2_PTFS_64K			(1 << 14)
-#define ID2_VMID16			(1 << 15)
-
-#define ID7_MAJOR_SHIFT			4
-#define ID7_MAJOR_MASK			0xf
-
-/* Global TLB invalidation */
-#define ARM_SMMU_GR0_TLBIVMID		0x64
-#define ARM_SMMU_GR0_TLBIALLNSNH	0x68
-#define ARM_SMMU_GR0_TLBIALLH		0x6c
-#define ARM_SMMU_GR0_sTLBGSYNC		0x70
-#define ARM_SMMU_GR0_sTLBGSTATUS	0x74
-#define sTLBGSTATUS_GSACTIVE		(1 << 0)
-
-/* Stream mapping registers */
-#define ARM_SMMU_GR0_SMR(n)		(0x800 + ((n) << 2))
-#define SMR_VALID			(1 << 31)
-#define SMR_MASK_SHIFT			16
-#define SMR_ID_SHIFT			0
-
-#define ARM_SMMU_GR0_S2CR(n)		(0xc00 + ((n) << 2))
-#define S2CR_CBNDX_SHIFT		0
-#define S2CR_CBNDX_MASK			0xff
-#define S2CR_EXIDVALID			(1 << 10)
-#define S2CR_TYPE_SHIFT			16
-#define S2CR_TYPE_MASK			0x3
-enum arm_smmu_s2cr_type {
-	S2CR_TYPE_TRANS,
-	S2CR_TYPE_BYPASS,
-	S2CR_TYPE_FAULT,
-};
-
-#define S2CR_PRIVCFG_SHIFT		24
-#define S2CR_PRIVCFG_MASK		0x3
-enum arm_smmu_s2cr_privcfg {
-	S2CR_PRIVCFG_DEFAULT,
-	S2CR_PRIVCFG_DIPAN,
-	S2CR_PRIVCFG_UNPRIV,
-	S2CR_PRIVCFG_PRIV,
-};
-
-/* Context bank attribute registers */
-#define ARM_SMMU_GR1_CBAR(n)		(0x0 + ((n) << 2))
-#define CBAR_VMID_SHIFT			0
-#define CBAR_VMID_MASK			0xff
-#define CBAR_S1_BPSHCFG_SHIFT		8
-#define CBAR_S1_BPSHCFG_MASK		3
-#define CBAR_S1_BPSHCFG_NSH		3
-#define CBAR_S1_MEMATTR_SHIFT		12
-#define CBAR_S1_MEMATTR_MASK		0xf
-#define CBAR_S1_MEMATTR_WB		0xf
-#define CBAR_TYPE_SHIFT			16
-#define CBAR_TYPE_MASK			0x3
-#define CBAR_TYPE_S2_TRANS		(0 << CBAR_TYPE_SHIFT)
-#define CBAR_TYPE_S1_TRANS_S2_BYPASS	(1 << CBAR_TYPE_SHIFT)
-#define CBAR_TYPE_S1_TRANS_S2_FAULT	(2 << CBAR_TYPE_SHIFT)
-#define CBAR_TYPE_S1_TRANS_S2_TRANS	(3 << CBAR_TYPE_SHIFT)
-#define CBAR_IRPTNDX_SHIFT		24
-#define CBAR_IRPTNDX_MASK		0xff
-
-#define ARM_SMMU_GR1_CBFRSYNRA(n)	(0x400 + ((n) << 2))
-
-#define ARM_SMMU_GR1_CBA2R(n)		(0x800 + ((n) << 2))
-#define CBA2R_RW64_32BIT		(0 << 0)
-#define CBA2R_RW64_64BIT		(1 << 0)
-#define CBA2R_VMID_SHIFT		16
-#define CBA2R_VMID_MASK			0xffff
-
-#define ARM_SMMU_CB_SCTLR		0x0
-#define ARM_SMMU_CB_ACTLR		0x4
-#define ARM_SMMU_CB_RESUME		0x8
-#define ARM_SMMU_CB_TTBCR2		0x10
-#define ARM_SMMU_CB_TTBR0		0x20
-#define ARM_SMMU_CB_TTBR1		0x28
-#define ARM_SMMU_CB_TTBCR		0x30
-#define ARM_SMMU_CB_CONTEXTIDR		0x34
-#define ARM_SMMU_CB_S1_MAIR0		0x38
-#define ARM_SMMU_CB_S1_MAIR1		0x3c
-#define ARM_SMMU_CB_PAR			0x50
-#define ARM_SMMU_CB_FSR			0x58
-#define ARM_SMMU_CB_FAR			0x60
-#define ARM_SMMU_CB_FSYNR0		0x68
-#define ARM_SMMU_CB_S1_TLBIVA		0x600
-#define ARM_SMMU_CB_S1_TLBIASID		0x610
-#define ARM_SMMU_CB_S1_TLBIVAL		0x620
-#define ARM_SMMU_CB_S2_TLBIIPAS2	0x630
-#define ARM_SMMU_CB_S2_TLBIIPAS2L	0x638
-#define ARM_SMMU_CB_TLBSYNC		0x7f0
-#define ARM_SMMU_CB_TLBSTATUS		0x7f4
-#define ARM_SMMU_CB_ATS1PR		0x800
-#define ARM_SMMU_CB_ATSR		0x8f0
-
-#define SCTLR_S1_ASIDPNE		(1 << 12)
-#define SCTLR_CFCFG			(1 << 7)
-#define SCTLR_CFIE			(1 << 6)
-#define SCTLR_CFRE			(1 << 5)
-#define SCTLR_E				(1 << 4)
-#define SCTLR_AFE			(1 << 2)
-#define SCTLR_TRE			(1 << 1)
-#define SCTLR_M				(1 << 0)
-
-#define CB_PAR_F			(1 << 0)
-
-#define ATSR_ACTIVE			(1 << 0)
-
-#define RESUME_RETRY			(0 << 0)
-#define RESUME_TERMINATE		(1 << 0)
-
-#define TTBCR2_SEP_SHIFT		15
-#define TTBCR2_SEP_UPSTREAM		(0x7 << TTBCR2_SEP_SHIFT)
-#define TTBCR2_AS			(1 << 4)
-
-#define TTBRn_ASID_SHIFT		48
-
-#define FSR_MULTI			(1 << 31)
-#define FSR_SS				(1 << 30)
-#define FSR_UUT				(1 << 8)
-#define FSR_ASF				(1 << 7)
-#define FSR_TLBLKF			(1 << 6)
-#define FSR_TLBMCF			(1 << 5)
-#define FSR_EF				(1 << 4)
-#define FSR_PF				(1 << 3)
-#define FSR_AFF				(1 << 2)
-#define FSR_TF				(1 << 1)
-
-#define FSR_IGN				(FSR_AFF | FSR_ASF | \
-					 FSR_TLBMCF | FSR_TLBLKF)
-#define FSR_FAULT			(FSR_MULTI | FSR_SS | FSR_UUT | \
-					 FSR_EF | FSR_PF | FSR_TF | FSR_IGN)
-
-#define FSYNR0_WNR			(1 << 4)
-
-#endif /* _ARM_SMMU_REGS_H */

drivers/iommu/dma-iommu.c

@@ -303,13 +303,15 @@ static int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 		u64 size, struct device *dev)
 {
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
-	struct iova_domain *iovad = &cookie->iovad;
 	unsigned long order, base_pfn;
+	struct iova_domain *iovad;
 	int attr;
 
 	if (!cookie || cookie->type != IOMMU_DMA_IOVA_COOKIE)
 		return -EINVAL;
 
+	iovad = &cookie->iovad;
+
 	/* Use the smallest supported page size for IOVA granularity */
 	order = __ffs(domain->pgsize_bitmap);
 	base_pfn = max_t(unsigned long, 1, base >> order);
@@ -444,13 +446,18 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iova_domain *iovad = &cookie->iovad;
 	size_t iova_off = iova_offset(iovad, dma_addr);
+	struct iommu_iotlb_gather iotlb_gather;
+	size_t unmapped;
 
 	dma_addr -= iova_off;
 	size = iova_align(iovad, size + iova_off);
+	iommu_iotlb_gather_init(&iotlb_gather);
+
+	unmapped = iommu_unmap_fast(domain, dma_addr, size, &iotlb_gather);
+	WARN_ON(unmapped != size);
 
-	WARN_ON(iommu_unmap_fast(domain, dma_addr, size) != size);
 	if (!cookie->fq_domain)
-		iommu_tlb_sync(domain);
+		iommu_tlb_sync(domain, &iotlb_gather);
 	iommu_dma_free_iova(cookie, dma_addr, size);
 }
 

drivers/iommu/dmar.c

@@ -1519,6 +1519,64 @@ static const char *dma_remap_fault_reasons[] =
 	"PCE for translation request specifies blocking",
 };
 
+static const char * const dma_remap_sm_fault_reasons[] = {
+	"SM: Invalid Root Table Address",
+	"SM: TTM 0 for request with PASID",
+	"SM: TTM 0 for page group request",
+	"Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x33-0x37 */
+	"SM: Error attempting to access Root Entry",
+	"SM: Present bit in Root Entry is clear",
+	"SM: Non-zero reserved field set in Root Entry",
+	"Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x3B-0x3F */
+	"SM: Error attempting to access Context Entry",
+	"SM: Present bit in Context Entry is clear",
+	"SM: Non-zero reserved field set in the Context Entry",
+	"SM: Invalid Context Entry",
+	"SM: DTE field in Context Entry is clear",
+	"SM: PASID Enable field in Context Entry is clear",
+	"SM: PASID is larger than the max in Context Entry",
+	"SM: PRE field in Context-Entry is clear",
+	"SM: RID_PASID field error in Context-Entry",
+	"Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x49-0x4F */
+	"SM: Error attempting to access the PASID Directory Entry",
+	"SM: Present bit in Directory Entry is clear",
+	"SM: Non-zero reserved field set in PASID Directory Entry",
+	"Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x53-0x57 */
+	"SM: Error attempting to access PASID Table Entry",
+	"SM: Present bit in PASID Table Entry is clear",
+	"SM: Non-zero reserved field set in PASID Table Entry",
+	"SM: Invalid Scalable-Mode PASID Table Entry",
+	"SM: ERE field is clear in PASID Table Entry",
+	"SM: SRE field is clear in PASID Table Entry",
+	"Unknown", "Unknown",/* 0x5E-0x5F */
+	"Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x60-0x67 */
+	"Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x68-0x6F */
+	"SM: Error attempting to access first-level paging entry",
+	"SM: Present bit in first-level paging entry is clear",
+	"SM: Non-zero reserved field set in first-level paging entry",
+	"SM: Error attempting to access FL-PML4 entry",
+	"SM: First-level entry address beyond MGAW in Nested translation",
+	"SM: Read permission error in FL-PML4 entry in Nested translation",
+	"SM: Read permission error in first-level paging entry in Nested translation",
+	"SM: Write permission error in first-level paging entry in Nested translation",
+	"SM: Error attempting to access second-level paging entry",
+	"SM: Read/Write permission error in second-level paging entry",
+	"SM: Non-zero reserved field set in second-level paging entry",
+	"SM: Invalid second-level page table pointer",
+	"SM: A/D bit update needed in second-level entry when set up in no snoop",
+	"Unknown", "Unknown", "Unknown", /* 0x7D-0x7F */
+	"SM: Address in first-level translation is not canonical",
+	"SM: U/S set 0 for first-level translation with user privilege",
+	"SM: No execute permission for request with PASID and ER=1",
+	"SM: Address beyond the DMA hardware max",
+	"SM: Second-level entry address beyond the max",
+	"SM: No write permission for Write/AtomicOp request",
+	"SM: No read permission for Read/AtomicOp request",
+	"SM: Invalid address-interrupt address",
+	"Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", "Unknown", /* 0x88-0x8F */
+	"SM: A/D bit update needed in first-level entry when set up in no snoop",
+};
+
 static const char *irq_remap_fault_reasons[] =
 {
 	"Detected reserved fields in the decoded interrupt-remapped request",
@@ -1536,6 +1594,10 @@ static const char *dmar_get_fault_reason(u8 fault_reason, int *fault_type)
 					ARRAY_SIZE(irq_remap_fault_reasons))) {
 		*fault_type = INTR_REMAP;
 		return irq_remap_fault_reasons[fault_reason - 0x20];
+	} else if (fault_reason >= 0x30 && (fault_reason - 0x30 <
+			ARRAY_SIZE(dma_remap_sm_fault_reasons))) {
+		*fault_type = DMA_REMAP;
+		return dma_remap_sm_fault_reasons[fault_reason - 0x30];
 	} else if (fault_reason < ARRAY_SIZE(dma_remap_fault_reasons)) {
 		*fault_type = DMA_REMAP;
 		return dma_remap_fault_reasons[fault_reason];
@@ -1611,7 +1673,8 @@ void dmar_msi_read(int irq, struct msi_msg *msg)
 }
 
 static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
-		u8 fault_reason, u16 source_id, unsigned long long addr)
+		u8 fault_reason, int pasid, u16 source_id,
+		unsigned long long addr)
 {
 	const char *reason;
 	int fault_type;
@@ -1624,10 +1687,11 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
 			PCI_FUNC(source_id & 0xFF), addr >> 48,
 			fault_reason, reason);
 	else
-		pr_err("[%s] Request device [%02x:%02x.%d] fault addr %llx [fault reason %02d] %s\n",
+		pr_err("[%s] Request device [%02x:%02x.%d] PASID %x fault addr %llx [fault reason %02d] %s\n",
 		       type ? "DMA Read" : "DMA Write",
 		       source_id >> 8, PCI_SLOT(source_id & 0xFF),
-		       PCI_FUNC(source_id & 0xFF), addr, fault_reason, reason);
+		       PCI_FUNC(source_id & 0xFF), pasid, addr,
+		       fault_reason, reason);
 	return 0;
 }
 
@@ -1659,8 +1723,9 @@ irqreturn_t dmar_fault(int irq, void *dev_id)
 		u8 fault_reason;
 		u16 source_id;
 		u64 guest_addr;
-		int type;
+		int type, pasid;
 		u32 data;
+		bool pasid_present;
 
 		/* highest 32 bits */
 		data = readl(iommu->reg + reg +
@@ -1672,10 +1737,12 @@ irqreturn_t dmar_fault(int irq, void *dev_id)
 			fault_reason = dma_frcd_fault_reason(data);
 			type = dma_frcd_type(data);
 
+			pasid = dma_frcd_pasid_value(data);
 			data = readl(iommu->reg + reg +
 				     fault_index * PRIMARY_FAULT_REG_LEN + 8);
 			source_id = dma_frcd_source_id(data);
 
+			pasid_present = dma_frcd_pasid_present(data);
 			guest_addr = dmar_readq(iommu->reg + reg +
 					fault_index * PRIMARY_FAULT_REG_LEN);
 			guest_addr = dma_frcd_page_addr(guest_addr);
@@ -1688,7 +1755,9 @@ irqreturn_t dmar_fault(int irq, void *dev_id)
 		raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
 
 		if (!ratelimited)
+			/* Using pasid -1 if pasid is not present */
 			dmar_fault_do_one(iommu, type, fault_reason,
+					  pasid_present ? pasid : -1,
 					  source_id, guest_addr);
 
 		fault_index++;

drivers/iommu/exynos-iommu.c

@@ -566,7 +566,7 @@ static void sysmmu_tlb_invalidate_entry(struct sysmmu_drvdata *data,
 
 static const struct iommu_ops exynos_iommu_ops;
 
-static int __init exynos_sysmmu_probe(struct platform_device *pdev)
+static int exynos_sysmmu_probe(struct platform_device *pdev)
 {
 	int irq, ret;
 	struct device *dev = &pdev->dev;
@@ -583,10 +583,8 @@ static int __init exynos_sysmmu_probe(struct platform_device *pdev)
 		return PTR_ERR(data->sfrbase);
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq <= 0) {
-		dev_err(dev, "Unable to find IRQ resource\n");
+	if (irq <= 0)
 		return irq;
-	}
 
 	ret = devm_request_irq(dev, irq, exynos_sysmmu_irq, 0,
 				dev_name(dev), data);
@@ -1130,7 +1128,8 @@ static void exynos_iommu_tlb_invalidate_entry(struct exynos_iommu_domain *domain
 }
 
 static size_t exynos_iommu_unmap(struct iommu_domain *iommu_domain,
-				 unsigned long l_iova, size_t size)
+				 unsigned long l_iova, size_t size,
+				 struct iommu_iotlb_gather *gather)
 {
 	struct exynos_iommu_domain *domain = to_exynos_domain(iommu_domain);
 	sysmmu_iova_t iova = (sysmmu_iova_t)l_iova;

drivers/iommu/intel-trace.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel IOMMU trace support
+ *
+ * Copyright (C) 2019 Intel Corporation
+ *
+ * Author: Lu Baolu <baolu.lu@linux.intel.com>
+ */
+
+#include <linux/string.h>
+#include <linux/types.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/intel_iommu.h>

drivers/iommu/intel_irq_remapping.c

@@ -376,13 +376,13 @@ static int set_msi_sid_cb(struct pci_dev *pdev, u16 alias, void *opaque)
 {
 	struct set_msi_sid_data *data = opaque;
 
+	if (data->count == 0 || PCI_BUS_NUM(alias) == PCI_BUS_NUM(data->alias))
+		data->busmatch_count++;
+
 	data->pdev = pdev;
 	data->alias = alias;
 	data->count++;
 
-	if (PCI_BUS_NUM(alias) == pdev->bus->number)
-		data->busmatch_count++;
-
 	return 0;
 }
 

drivers/iommu/iova.c

@@ -577,7 +577,9 @@ void queue_iova(struct iova_domain *iovad,
 
 	spin_unlock_irqrestore(&fq->lock, flags);
 
-	if (atomic_cmpxchg(&iovad->fq_timer_on, 0, 1) == 0)
+	/* Avoid false sharing as much as possible. */
+	if (!atomic_read(&iovad->fq_timer_on) &&
+	    !atomic_cmpxchg(&iovad->fq_timer_on, 0, 1))
 		mod_timer(&iovad->fq_timer,
 			  jiffies + msecs_to_jiffies(IOVA_FQ_TIMEOUT));
 }