Merge tag 'iommu-updates-v5.20-or-v6.0' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:

 - The most intrusive patch is small and changes the default allocation
   policy for DMA addresses.

   Before the change the allocator tried its best to find an address in
   the first 4GB. But that lead to performance problems when that space
   gets exhaused, and since most devices are capable of 64-bit DMA these
   days, we changed it to search in the full DMA-mask range from the
   beginning.

   This change has the potential to uncover bugs elsewhere, in the
   kernel or the hardware. There is a Kconfig option and a command line
   option to restore the old behavior, but none of them is enabled by
   default.

 - Add Robin Murphy as reviewer of IOMMU code and maintainer for the
   dma-iommu and iova code

 - Chaning IOVA magazine size from 1032 to 1024 bytes to save memory

 - Some core code cleanups and dead-code removal

 - Support for ACPI IORT RMR node

 - Support for multiple PCI domains in the AMD-Vi driver

 - ARM SMMU changes from Will Deacon:
      - Add even more Qualcomm device-tree compatible strings
      - Support dumping of IMP DEF Qualcomm registers on TLB sync
        timeout
      - Fix reference count leak on device tree node in Qualcomm driver

 - Intel VT-d driver updates from Lu Baolu:
      - Make intel-iommu.h private
      - Optimize the use of two locks
      - Extend the driver to support large-scale platforms
      - Cleanup some dead code

 - MediaTek IOMMU refactoring and support for TTBR up to 35bit

 - Basic support for Exynos SysMMU v7

 - VirtIO IOMMU driver gets a map/unmap_pages() implementation

 - Other smaller cleanups and fixes

* tag 'iommu-updates-v5.20-or-v6.0' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (116 commits)
  iommu/amd: Fix compile warning in init code
  iommu/amd: Add support for AVIC when SNP is enabled
  iommu/amd: Simplify and Consolidate Virtual APIC (AVIC) Enablement
  ACPI/IORT: Fix build error implicit-function-declaration
  drivers: iommu: fix clang -wformat warning
  iommu/arm-smmu: qcom_iommu: Add of_node_put() when breaking out of loop
  iommu/arm-smmu-qcom: Add SM6375 SMMU compatible
  dt-bindings: arm-smmu: Add compatible for Qualcomm SM6375
  MAINTAINERS: Add Robin Murphy as IOMMU SUBSYTEM reviewer
  iommu/amd: Do not support IOMMUv2 APIs when SNP is enabled
  iommu/amd: Do not support IOMMU_DOMAIN_IDENTITY after SNP is enabled
  iommu/amd: Set translation valid bit only when IO page tables are in use
  iommu/amd: Introduce function to check and enable SNP
  iommu/amd: Globally detect SNP support
  iommu/amd: Process all IVHDs before enabling IOMMU features
  iommu/amd: Introduce global variable for storing common EFR and EFR2
  iommu/amd: Introduce Support for Extended Feature 2 Register
  iommu/amd: Change macro for IOMMU control register bit shift to decimal value
  iommu/exynos: Enable default VM instance on SysMMU v7
  iommu/exynos: Add SysMMU v7 register set
  ...

1 files changed, 28 insertions, 6 deletions

diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index 7820711c4560..b2708de25ea3 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -5,23 +5,40 @@
 
 #include <linux/acpi.h>
 #include <linux/adreno-smmu-priv.h>
+#include <linux/delay.h>
 #include <linux/of_device.h>
 #include <linux/qcom_scm.h>
 
 #include "arm-smmu.h"
+#include "arm-smmu-qcom.h"
 
-struct qcom_smmu {
-	struct arm_smmu_device smmu;
-	bool bypass_quirk;
-	u8 bypass_cbndx;
-	u32 stall_enabled;
-};
+#define QCOM_DUMMY_VAL	-1
 
 static struct qcom_smmu *to_qcom_smmu(struct arm_smmu_device *smmu)
 {
 	return container_of(smmu, struct qcom_smmu, smmu);
 }
 
+static void qcom_smmu_tlb_sync(struct arm_smmu_device *smmu, int page,
+				int sync, int status)
+{
+	unsigned int spin_cnt, delay;
+	u32 reg;
+
+	arm_smmu_writel(smmu, page, sync, QCOM_DUMMY_VAL);
+	for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
+		for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
+			reg = arm_smmu_readl(smmu, page, status);
+			if (!(reg & ARM_SMMU_sTLBGSTATUS_GSACTIVE))
+				return;
+			cpu_relax();
+		}
+		udelay(delay);
+	}
+
+	qcom_smmu_tlb_sync_debug(smmu);
+}
+
 static void qcom_adreno_smmu_write_sctlr(struct arm_smmu_device *smmu, int idx,
 		u32 reg)
 {
@@ -233,6 +250,7 @@ static const struct of_device_id qcom_smmu_client_of_match[] __maybe_unused = {
 	{ .compatible = "qcom,sc7280-mdss" },
 	{ .compatible = "qcom,sc7280-mss-pil" },
 	{ .compatible = "qcom,sc8180x-mdss" },
+	{ .compatible = "qcom,sm8250-mdss" },
 	{ .compatible = "qcom,sdm845-mdss" },
 	{ .compatible = "qcom,sdm845-mss-pil" },
 	{ }
@@ -374,6 +392,7 @@ static const struct arm_smmu_impl qcom_smmu_impl = {
 	.def_domain_type = qcom_smmu_def_domain_type,
 	.reset = qcom_smmu500_reset,
 	.write_s2cr = qcom_smmu_write_s2cr,
+	.tlb_sync = qcom_smmu_tlb_sync,
 };
 
 static const struct arm_smmu_impl qcom_adreno_smmu_impl = {
@@ -382,6 +401,7 @@ static const struct arm_smmu_impl qcom_adreno_smmu_impl = {
 	.reset = qcom_smmu500_reset,
 	.alloc_context_bank = qcom_adreno_smmu_alloc_context_bank,
 	.write_sctlr = qcom_adreno_smmu_write_sctlr,
+	.tlb_sync = qcom_smmu_tlb_sync,
 };
 
 static struct arm_smmu_device *qcom_smmu_create(struct arm_smmu_device *smmu,
@@ -398,6 +418,7 @@ static struct arm_smmu_device *qcom_smmu_create(struct arm_smmu_device *smmu,
 		return ERR_PTR(-ENOMEM);
 
 	qsmmu->smmu.impl = impl;
+	qsmmu->cfg = qcom_smmu_impl_data(smmu);
 
 	return &qsmmu->smmu;
 }
@@ -413,6 +434,7 @@ static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = {
 	{ .compatible = "qcom,sdm845-smmu-500" },
 	{ .compatible = "qcom,sm6125-smmu-500" },
 	{ .compatible = "qcom,sm6350-smmu-500" },
+	{ .compatible = "qcom,sm6375-smmu-500" },
 	{ .compatible = "qcom,sm8150-smmu-500" },
 	{ .compatible = "qcom,sm8250-smmu-500" },
 	{ .compatible = "qcom,sm8350-smmu-500" },