These changes are the raw update to linux-4.4.6-rt14. Kernel sources

are taken from kernel.org, and rt patch from the rt wiki download page.

During the rebasing, the following patch collided:

Force tick interrupt and get rid of softirq magic(I70131fb85).

Collisions have been removed because its logic was found on the
source already.

Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>

1 files changed, 101 insertions, 93 deletions

diff --git a/kernel/drivers/iommu/arm-smmu.c b/kernel/drivers/iommu/arm-smmu.c
index 65075ef75..47dc7a793 100644
--- a/kernel/drivers/iommu/arm-smmu.c
+++ b/kernel/drivers/iommu/arm-smmu.c
@@ -37,6 +37,7 @@
 #include <linux/iopoll.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
@@ -69,6 +70,18 @@
 		((smmu->options & ARM_SMMU_OPT_SECURE_CFG_ACCESS)	\
 			? 0x400 : 0))
 
+#ifdef CONFIG_64BIT
+#define smmu_writeq	writeq_relaxed
+#else
+#define smmu_writeq(reg64, addr)				\
+	do {							\
+		u64 __val = (reg64);				\
+		void __iomem *__addr = (addr);			\
+		writel_relaxed(__val >> 32, __addr + 4);	\
+		writel_relaxed(__val, __addr);			\
+	} while (0)
+#endif
+
 /* Configuration registers */
 #define ARM_SMMU_GR0_sCR0		0x0
 #define sCR0_CLIENTPD			(1 << 0)
@@ -184,10 +197,8 @@
 #define ARM_SMMU_CB_SCTLR		0x0
 #define ARM_SMMU_CB_RESUME		0x8
 #define ARM_SMMU_CB_TTBCR2		0x10
-#define ARM_SMMU_CB_TTBR0_LO		0x20
-#define ARM_SMMU_CB_TTBR0_HI		0x24
-#define ARM_SMMU_CB_TTBR1_LO		0x28
-#define ARM_SMMU_CB_TTBR1_HI		0x2c
+#define ARM_SMMU_CB_TTBR0		0x20
+#define ARM_SMMU_CB_TTBR1		0x28
 #define ARM_SMMU_CB_TTBCR		0x30
 #define ARM_SMMU_CB_S1_MAIR0		0x38
 #define ARM_SMMU_CB_S1_MAIR1		0x3c
@@ -202,8 +213,7 @@
 #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_ATS1PR_LO		0x800
-#define ARM_SMMU_CB_ATS1PR_HI		0x804
+#define ARM_SMMU_CB_ATS1PR		0x800
 #define ARM_SMMU_CB_ATSR		0x8f0
 
 #define SCTLR_S1_ASIDPNE		(1 << 12)
@@ -226,7 +236,7 @@
 #define TTBCR2_SEP_SHIFT		15
 #define TTBCR2_SEP_UPSTREAM		(0x7 << TTBCR2_SEP_SHIFT)
 
-#define TTBRn_HI_ASID_SHIFT            16
+#define TTBRn_ASID_SHIFT		48
 
 #define FSR_MULTI			(1 << 31)
 #define FSR_SS				(1 << 30)
@@ -247,7 +257,7 @@
 #define FSYNR0_WNR			(1 << 4)
 
 static int force_stage;
-module_param_named(force_stage, force_stage, int, S_IRUGO | S_IWUSR);
+module_param_named(force_stage, force_stage, int, S_IRUGO);
 MODULE_PARM_DESC(force_stage,
 	"Force SMMU mappings to be installed at a particular stage of translation. A value of '1' or '2' forces the corresponding stage. All other values are ignored (i.e. no stage is forced). Note that selecting a specific stage will disable support for nested translation.");
 
@@ -608,34 +618,10 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
 	}
 }
 
-static void arm_smmu_flush_pgtable(void *addr, size_t size, void *cookie)
-{
-	struct arm_smmu_domain *smmu_domain = cookie;
-	struct arm_smmu_device *smmu = smmu_domain->smmu;
-	unsigned long offset = (unsigned long)addr & ~PAGE_MASK;
-
-
-	/* Ensure new page tables are visible to the hardware walker */
-	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK) {
-		dsb(ishst);
-	} else {
-		/*
-		 * If the SMMU can't walk tables in the CPU caches, treat them
-		 * like non-coherent DMA since we need to flush the new entries
-		 * all the way out to memory. There's no possibility of
-		 * recursion here as the SMMU table walker will not be wired
-		 * through another SMMU.
-		 */
-		dma_map_page(smmu->dev, virt_to_page(addr), offset, size,
-			     DMA_TO_DEVICE);
-	}
-}
-
 static struct iommu_gather_ops arm_smmu_gather_ops = {
 	.tlb_flush_all	= arm_smmu_tlb_inv_context,
 	.tlb_add_flush	= arm_smmu_tlb_inv_range_nosync,
 	.tlb_sync	= arm_smmu_tlb_sync,
-	.flush_pgtable	= arm_smmu_flush_pgtable,
 };
 
 static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
@@ -719,12 +705,12 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
 				       struct io_pgtable_cfg *pgtbl_cfg)
 {
 	u32 reg;
+	u64 reg64;
 	bool stage1;
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
-	void __iomem *cb_base, *gr0_base, *gr1_base;
+	void __iomem *cb_base, *gr1_base;
 
-	gr0_base = ARM_SMMU_GR0(smmu);
 	gr1_base = ARM_SMMU_GR1(smmu);
 	stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
 	cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
@@ -762,22 +748,17 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
 
 	/* TTBRs */
 	if (stage1) {
-		reg = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
-		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO);
-		reg = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0] >> 32;
-		reg |= ARM_SMMU_CB_ASID(cfg) << TTBRn_HI_ASID_SHIFT;
-		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_HI);
-
-		reg = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[1];
-		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR1_LO);
-		reg = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[1] >> 32;
-		reg |= ARM_SMMU_CB_ASID(cfg) << TTBRn_HI_ASID_SHIFT;
-		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR1_HI);
+		reg64 = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
+
+		reg64 |= ((u64)ARM_SMMU_CB_ASID(cfg)) << TTBRn_ASID_SHIFT;
+		smmu_writeq(reg64, cb_base + ARM_SMMU_CB_TTBR0);
+
+		reg64 = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[1];
+		reg64 |= ((u64)ARM_SMMU_CB_ASID(cfg)) << TTBRn_ASID_SHIFT;
+		smmu_writeq(reg64, cb_base + ARM_SMMU_CB_TTBR1);
 	} else {
-		reg = pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
-		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_LO);
-		reg = pgtbl_cfg->arm_lpae_s2_cfg.vttbr >> 32;
-		writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0_HI);
+		reg64 = pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
+		smmu_writeq(reg64, cb_base + ARM_SMMU_CB_TTBR0);
 	}
 
 	/* TTBCR */
@@ -899,6 +880,7 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 		.ias		= ias,
 		.oas		= oas,
 		.tlb		= &arm_smmu_gather_ops,
+		.iommu_dev	= smmu->dev,
 	};
 
 	smmu_domain->smmu = smmu;
@@ -1229,23 +1211,21 @@ static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
 	void __iomem *cb_base;
 	u32 tmp;
 	u64 phys;
+	unsigned long va;
 
 	cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
 
-	if (smmu->version == 1) {
-		u32 reg = iova & ~0xfff;
-		writel_relaxed(reg, cb_base + ARM_SMMU_CB_ATS1PR_LO);
-	} else {
-		u32 reg = iova & ~0xfff;
-		writel_relaxed(reg, cb_base + ARM_SMMU_CB_ATS1PR_LO);
-		reg = ((u64)iova & ~0xfff) >> 32;
-		writel_relaxed(reg, cb_base + ARM_SMMU_CB_ATS1PR_HI);
-	}
+	/* ATS1 registers can only be written atomically */
+	va = iova & ~0xfffUL;
+	if (smmu->version == ARM_SMMU_V2)
+		smmu_writeq(va, cb_base + ARM_SMMU_CB_ATS1PR);
+	else
+		writel_relaxed(va, cb_base + ARM_SMMU_CB_ATS1PR);
 
 	if (readl_poll_timeout_atomic(cb_base + ARM_SMMU_CB_ATSR, tmp,
 				      !(tmp & ATSR_ACTIVE), 5, 50)) {
 		dev_err(dev,
-			"iova to phys timed out on 0x%pad. Falling back to software table walk.\n",
+			"iova to phys timed out on %pad. Falling back to software table walk.\n",
 			&iova);
 		return ops->iova_to_phys(ops, iova);
 	}
@@ -1315,33 +1295,25 @@ static void __arm_smmu_release_pci_iommudata(void *data)
 	kfree(data);
 }
 
-static int arm_smmu_add_pci_device(struct pci_dev *pdev)
+static int arm_smmu_init_pci_device(struct pci_dev *pdev,
+				    struct iommu_group *group)
 {
-	int i, ret;
-	u16 sid;
-	struct iommu_group *group;
 	struct arm_smmu_master_cfg *cfg;
-
-	group = iommu_group_get_for_dev(&pdev->dev);
-	if (IS_ERR(group))
-		return PTR_ERR(group);
+	u16 sid;
+	int i;
 
 	cfg = iommu_group_get_iommudata(group);
 	if (!cfg) {
 		cfg = kzalloc(sizeof(*cfg), GFP_KERNEL);
-		if (!cfg) {
-			ret = -ENOMEM;
-			goto out_put_group;
-		}
+		if (!cfg)
+			return -ENOMEM;
 
 		iommu_group_set_iommudata(group, cfg,
 					  __arm_smmu_release_pci_iommudata);
 	}
 
-	if (cfg->num_streamids >= MAX_MASTER_STREAMIDS) {
-		ret = -ENOSPC;
-		goto out_put_group;
-	}
+	if (cfg->num_streamids >= MAX_MASTER_STREAMIDS)
+		return -ENOSPC;
 
 	/*
 	 * Assume Stream ID == Requester ID for now.
@@ -1357,16 +1329,13 @@ static int arm_smmu_add_pci_device(struct pci_dev *pdev)
 		cfg->streamids[cfg->num_streamids++] = sid;
 
 	return 0;
-out_put_group:
-	iommu_group_put(group);
-	return ret;
 }
 
-static int arm_smmu_add_platform_device(struct device *dev)
+static int arm_smmu_init_platform_device(struct device *dev,
+					 struct iommu_group *group)
 {
-	struct iommu_group *group;
-	struct arm_smmu_master *master;
 	struct arm_smmu_device *smmu = find_smmu_for_device(dev);
+	struct arm_smmu_master *master;
 
 	if (!smmu)
 		return -ENODEV;
@@ -1375,21 +1344,20 @@ static int arm_smmu_add_platform_device(struct device *dev)
 	if (!master)
 		return -ENODEV;
 
-	/* No automatic group creation for platform devices */
-	group = iommu_group_alloc();
-	if (IS_ERR(group))
-		return PTR_ERR(group);
-
 	iommu_group_set_iommudata(group, &master->cfg, NULL);
-	return iommu_group_add_device(group, dev);
+
+	return 0;
 }
 
 static int arm_smmu_add_device(struct device *dev)
 {
-	if (dev_is_pci(dev))
-		return arm_smmu_add_pci_device(to_pci_dev(dev));
+	struct iommu_group *group;
+
+	group = iommu_group_get_for_dev(dev);
+	if (IS_ERR(group))
+		return PTR_ERR(group);
 
-	return arm_smmu_add_platform_device(dev);
+	return 0;
 }
 
 static void arm_smmu_remove_device(struct device *dev)
@@ -1397,6 +1365,32 @@ static void arm_smmu_remove_device(struct device *dev)
 	iommu_group_remove_device(dev);
 }
 
+static struct iommu_group *arm_smmu_device_group(struct device *dev)
+{
+	struct iommu_group *group;
+	int ret;
+
+	if (dev_is_pci(dev))
+		group = pci_device_group(dev);
+	else
+		group = generic_device_group(dev);
+
+	if (IS_ERR(group))
+		return group;
+
+	if (dev_is_pci(dev))
+		ret = arm_smmu_init_pci_device(to_pci_dev(dev), group);
+	else
+		ret = arm_smmu_init_platform_device(dev, group);
+
+	if (ret) {
+		iommu_group_put(group);
+		group = ERR_PTR(ret);
+	}
+
+	return group;
+}
+
 static int arm_smmu_domain_get_attr(struct iommu_domain *domain,
 				    enum iommu_attr attr, void *data)
 {
@@ -1453,6 +1447,7 @@ static struct iommu_ops arm_smmu_ops = {
 	.iova_to_phys		= arm_smmu_iova_to_phys,
 	.add_device		= arm_smmu_add_device,
 	.remove_device		= arm_smmu_remove_device,
+	.device_group		= arm_smmu_device_group,
 	.domain_get_attr	= arm_smmu_domain_get_attr,
 	.domain_set_attr	= arm_smmu_domain_set_attr,
 	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
@@ -1533,6 +1528,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 	unsigned long size;
 	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
 	u32 id;
+	bool cttw_dt, cttw_reg;
 
 	dev_notice(smmu->dev, "probing hardware configuration...\n");
 	dev_notice(smmu->dev, "SMMUv%d with:\n", smmu->version);
@@ -1572,10 +1568,22 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 		dev_notice(smmu->dev, "\taddress translation ops\n");
 	}
 
-	if (id & ID0_CTTW) {
+	/*
+	 * In order for DMA API calls to work properly, we must defer to what
+	 * the DT says about coherency, regardless of what the hardware claims.
+	 * Fortunately, this also opens up a workaround for systems where the
+	 * ID register value has ended up configured incorrectly.
+	 */
+	cttw_dt = of_dma_is_coherent(smmu->dev->of_node);
+	cttw_reg = !!(id & ID0_CTTW);
+	if (cttw_dt)
 		smmu->features |= ARM_SMMU_FEAT_COHERENT_WALK;
-		dev_notice(smmu->dev, "\tcoherent table walk\n");
-	}
+	if (cttw_dt || cttw_reg)
+		dev_notice(smmu->dev, "\t%scoherent table walk\n",
+			   cttw_dt ? "" : "non-");
+	if (cttw_dt != cttw_reg)
+		dev_notice(smmu->dev,
+			   "\t(IDR0.CTTW overridden by dma-coherent property)\n");
 
 	if (id & ID0_SMS) {
 		u32 smr, sid, mask;