* [PATCH v2 1/2] iopoll: Introduce memory-mapped IO polling macros
2014-09-27 21:31 [PATCH v2 0/2] iommu/arm-smmu: hard iova_to_phys Mitchel Humpherys
@ 2014-09-27 21:31 ` Mitchel Humpherys
2014-09-27 21:31 ` [PATCH v2 2/2] iommu/arm-smmu: add support for iova_to_phys through ATS1PR Mitchel Humpherys
2014-09-28 3:22 ` [PATCH v2 0/2] iommu/arm-smmu: hard iova_to_phys Mitchel Humpherys
2 siblings, 0 replies; 4+ messages in thread
From: Mitchel Humpherys @ 2014-09-27 21:31 UTC (permalink / raw)
To: linux-arm-kernel
From: Matt Wagantall <mattw@codeaurora.org>
It is sometimes necessary to poll a memory-mapped register until its
value satisfies some condition. Introduce a family of convenience macros
that do this. Tight-loop and sleeping versions are provided with and
without timeouts.
Cc: Thierry Reding <thierry.reding@gmail.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Matt Wagantall <mattw@codeaurora.org>
Signed-off-by: Mitchel Humpherys <mitchelh@codeaurora.org>
---
include/linux/iopoll.h | 77 ++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 77 insertions(+)
create mode 100644 include/linux/iopoll.h
diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h
new file mode 100644
index 0000000000..594b0d4f03
--- /dev/null
+++ b/include/linux/iopoll.h
@@ -0,0 +1,77 @@
+/*
+ * Copyright (c) 2012-2014 The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_IOPOLL_H
+#define _LINUX_IOPOLL_H
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/hrtimer.h>
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+
+/**
+ * readl_poll_timeout - Periodically poll an address until a condition is met or a timeout occurs
+ * @addr: Address to poll
+ * @val: Variable to read the value into
+ * @cond: Break condition (usually involving @val)
+ * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops)
+ * @timeout_us: Timeout in us, 0 means never timeout
+ *
+ * Returns 0 on success and -ETIMEDOUT upon a timeout. In either
+ * case, the last read value at @addr is stored in @val. Must not
+ * be called from atomic context if sleep_us or timeout_us are used.
+ */
+#define readl_poll_timeout(addr, val, cond, sleep_us, timeout_us) \
+({ \
+ ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); \
+ might_sleep_if(timeout_us); \
+ for (;;) { \
+ (val) = readl(addr); \
+ if (cond) \
+ break; \
+ if (timeout_us && ktime_compare(ktime_get(), timeout) > 0) { \
+ (val) = readl(addr); \
+ break; \
+ } \
+ if (sleep_us) \
+ usleep_range(DIV_ROUND_UP(sleep_us, 4), sleep_us); \
+ } \
+ (cond) ? 0 : -ETIMEDOUT; \
+})
+
+/**
+ * readl_poll_timeout_atomic - Periodically poll an address until a condition is met or a timeout occurs
+ * @addr: Address to poll
+ * @val: Variable to read the value into
+ * @cond: Break condition (usually involving @val)
+ * @max_reads: Maximum number of reads before giving up
+ * @time_between_us: Time to udelay() between successive reads
+ *
+ * Returns 0 on success and -ETIMEDOUT upon a timeout.
+ */
+#define readl_poll_timeout_atomic(addr, val, cond, max_reads, time_between_us) \
+({ \
+ int count; \
+ for (count = (max_reads); count > 0; count--) { \
+ (val) = readl(addr); \
+ if (cond) \
+ break; \
+ udelay(time_between_us); \
+ } \
+ (cond) ? 0 : -ETIMEDOUT; \
+})
+
+#endif /* _LINUX_IOPOLL_H */
--
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
hosted by The Linux Foundation
^ permalink raw reply related [flat|nested] 4+ messages in thread* [PATCH v2 2/2] iommu/arm-smmu: add support for iova_to_phys through ATS1PR
2014-09-27 21:31 [PATCH v2 0/2] iommu/arm-smmu: hard iova_to_phys Mitchel Humpherys
2014-09-27 21:31 ` [PATCH v2 1/2] iopoll: Introduce memory-mapped IO polling macros Mitchel Humpherys
@ 2014-09-27 21:31 ` Mitchel Humpherys
2014-09-28 3:22 ` [PATCH v2 0/2] iommu/arm-smmu: hard iova_to_phys Mitchel Humpherys
2 siblings, 0 replies; 4+ messages in thread
From: Mitchel Humpherys @ 2014-09-27 21:31 UTC (permalink / raw)
To: linux-arm-kernel
Currently, we provide the iommu_ops.iova_to_phys service by doing a
table walk in software to translate IO virtual addresses to physical
addresses. On SMMUs that support it, it can be useful to ask the SMMU
itself to do the translation. This can be used to warm the TLBs for an
SMMU. It can also be useful for testing and hardware validation.
Since the address translation registers are optional on SMMUv2, only
enable hardware translations when using SMMUv1 or when SMMU_IDR0.S1TS=1
and SMMU_IDR0.ATOSNS=0, as described in the ARM SMMU v1-v2 spec.
Signed-off-by: Mitchel Humpherys <mitchelh@codeaurora.org>
---
drivers/iommu/arm-smmu.c | 73 +++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 72 insertions(+), 1 deletion(-)
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 37dc3dd0df..7c4629cafd 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -36,6 +36,7 @@
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/iommu.h>
+#include <linux/iopoll.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/of.h>
@@ -140,6 +141,7 @@
#define ID0_S2TS (1 << 29)
#define ID0_NTS (1 << 28)
#define ID0_SMS (1 << 27)
+#define ID0_ATOSNS (1 << 26)
#define ID0_PTFS_SHIFT 24
#define ID0_PTFS_MASK 0x2
#define ID0_PTFS_V8_ONLY 0x2
@@ -233,11 +235,17 @@
#define ARM_SMMU_CB_TTBR0_HI 0x24
#define ARM_SMMU_CB_TTBCR 0x30
#define ARM_SMMU_CB_S1_MAIR0 0x38
+#define ARM_SMMU_CB_PAR_LO 0x50
+#define ARM_SMMU_CB_PAR_HI 0x54
#define ARM_SMMU_CB_FSR 0x58
#define ARM_SMMU_CB_FAR_LO 0x60
#define ARM_SMMU_CB_FAR_HI 0x64
#define ARM_SMMU_CB_FSYNR0 0x68
#define ARM_SMMU_CB_S1_TLBIASID 0x610
+#define ARM_SMMU_CB_ATS1PR_LO 0x800
+#define ARM_SMMU_CB_ATS1PR_HI 0x804
+#define ARM_SMMU_CB_ATSR 0x8f0
+#define ATSR_LOOP_TIMEOUT 1000000 /* 1s! */
#define SCTLR_S1_ASIDPNE (1 << 12)
#define SCTLR_CFCFG (1 << 7)
@@ -249,6 +257,10 @@
#define SCTLR_M (1 << 0)
#define SCTLR_EAE_SBOP (SCTLR_AFE | SCTLR_TRE)
+#define CB_PAR_F (1 << 0)
+
+#define ATSR_ACTIVE (1 << 0)
+
#define RESUME_RETRY (0 << 0)
#define RESUME_TERMINATE (1 << 0)
@@ -366,6 +378,7 @@ struct arm_smmu_device {
#define ARM_SMMU_FEAT_TRANS_S1 (1 << 2)
#define ARM_SMMU_FEAT_TRANS_S2 (1 << 3)
#define ARM_SMMU_FEAT_TRANS_NESTED (1 << 4)
+#define ARM_SMMU_FEAT_TRANS_OPS (1 << 5)
u32 features;
#define ARM_SMMU_OPT_SECURE_CFG_ACCESS (1 << 0)
@@ -1524,7 +1537,7 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
return ret ? 0 : size;
}
-static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain,
+static phys_addr_t arm_smmu_iova_to_phys_soft(struct iommu_domain *domain,
dma_addr_t iova)
{
pgd_t *pgdp, pgd;
@@ -1557,6 +1570,59 @@ static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain,
return __pfn_to_phys(pte_pfn(pte)) | (iova & ~PAGE_MASK);
}
+static phys_addr_t arm_smmu_iova_to_phys_hard(struct iommu_domain *domain,
+ dma_addr_t iova)
+{
+ struct arm_smmu_domain *smmu_domain = domain->priv;
+ struct arm_smmu_device *smmu = smmu_domain->smmu;
+ struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+ struct device *dev = smmu->dev;
+ void __iomem *cb_base;
+ u32 tmp;
+ u64 phys;
+
+ 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 = (iova & ~0xFFF) >> 32;
+ writel_relaxed(reg, cb_base + ARM_SMMU_CB_ATS1PR_HI);
+ }
+
+ if (readl_poll_timeout(cb_base + ARM_SMMU_CB_ATSR, tmp,
+ !(tmp & ATSR_ACTIVE), 10, ATSR_LOOP_TIMEOUT)) {
+ dev_err(dev,
+ "iova to phys timed out on 0x%pa for %s. Falling back to software table walk.\n",
+ &iova, dev_name(dev));
+ return arm_smmu_iova_to_phys_soft(domain, iova);
+ }
+
+ phys = readl_relaxed(cb_base + ARM_SMMU_CB_PAR_LO);
+ phys |= ((u64) readl_relaxed(cb_base + ARM_SMMU_CB_PAR_HI)) << 32;
+
+ if (phys & CB_PAR_F) {
+ dev_err(dev, "translation fault on %s!\n", dev_name(dev));
+ dev_err(dev, "PAR = 0x%llx\n", phys);
+ }
+ phys = (phys & 0xFFFFFFF000ULL) | (iova & 0x00000FFF);
+
+ return phys;
+}
+
+static phys_addr_t arm_smmu_iova_to_phys(struct iommu_domain *domain,
+ dma_addr_t iova)
+{
+ struct arm_smmu_domain *smmu_domain = domain->priv;
+
+ if (smmu_domain->smmu->features & ARM_SMMU_FEAT_TRANS_OPS)
+ return arm_smmu_iova_to_phys_hard(domain, iova);
+ return arm_smmu_iova_to_phys_soft(domain, iova);
+}
+
static int arm_smmu_domain_has_cap(struct iommu_domain *domain,
unsigned long cap)
{
@@ -1777,6 +1843,11 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
return -ENODEV;
}
+ if (smmu->version == 1 || (!(id & ID0_ATOSNS) && (id & ID0_S1TS))) {
+ smmu->features |= ARM_SMMU_FEAT_TRANS_OPS;
+ dev_notice(smmu->dev, "\taddress translation ops\n");
+ }
+
if (id & ID0_CTTW) {
smmu->features |= ARM_SMMU_FEAT_COHERENT_WALK;
dev_notice(smmu->dev, "\tcoherent table walk\n");
--
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
hosted by The Linux Foundation
^ permalink raw reply related [flat|nested] 4+ messages in thread