From 24e516049360eda85cf3fe9903221d43886c2689 Mon Sep 17 00:00:00 2001 From: Neil Leeder Date: Tue, 26 Mar 2019 15:17:50 +0000 Subject: ACPI/IORT: Add support for PMCG Add support for the SMMU Performance Monitor Counter Group information from ACPI. This is in preparation for its use in the SMMUv3 PMU driver. Signed-off-by: Neil Leeder Signed-off-by: Hanjun Guo Signed-off-by: Shameer Kolothum Reviewed-by: Robin Murphy Acked-by: Lorenzo Pieralisi Signed-off-by: Will Deacon --- drivers/acpi/arm64/iort.c | 117 ++++++++++++++++++++++++++++++++++++---------- 1 file changed, 93 insertions(+), 24 deletions(-) (limited to 'drivers/acpi') diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index e48894e002ba..e2c9b26bbee6 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -356,7 +356,8 @@ static struct acpi_iort_node *iort_node_get_id(struct acpi_iort_node *node, if (map->flags & ACPI_IORT_ID_SINGLE_MAPPING) { if (node->type == ACPI_IORT_NODE_NAMED_COMPONENT || node->type == ACPI_IORT_NODE_PCI_ROOT_COMPLEX || - node->type == ACPI_IORT_NODE_SMMU_V3) { + node->type == ACPI_IORT_NODE_SMMU_V3 || + node->type == ACPI_IORT_NODE_PMCG) { *id_out = map->output_base; return parent; } @@ -394,6 +395,8 @@ static int iort_get_id_mapping_index(struct acpi_iort_node *node) } return smmu->id_mapping_index; + case ACPI_IORT_NODE_PMCG: + return 0; default: return -EINVAL; } @@ -1218,14 +1221,23 @@ static void __init arm_smmu_v3_init_resources(struct resource *res, } } -static bool __init arm_smmu_v3_is_coherent(struct acpi_iort_node *node) +static void __init arm_smmu_v3_dma_configure(struct device *dev, + struct acpi_iort_node *node) { struct acpi_iort_smmu_v3 *smmu; + enum dev_dma_attr attr; /* Retrieve SMMUv3 specific data */ smmu = (struct acpi_iort_smmu_v3 *)node->node_data; - return smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE; + attr = (smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE) ? + DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT; + + /* We expect the dma masks to be equivalent for all SMMUv3 set-ups */ + dev->dma_mask = &dev->coherent_dma_mask; + + /* Configure DMA for the page table walker */ + acpi_dma_configure(dev, attr); } #if defined(CONFIG_ACPI_NUMA) @@ -1301,30 +1313,82 @@ static void __init arm_smmu_init_resources(struct resource *res, } } -static bool __init arm_smmu_is_coherent(struct acpi_iort_node *node) +static void __init arm_smmu_dma_configure(struct device *dev, + struct acpi_iort_node *node) { struct acpi_iort_smmu *smmu; + enum dev_dma_attr attr; /* Retrieve SMMU specific data */ smmu = (struct acpi_iort_smmu *)node->node_data; - return smmu->flags & ACPI_IORT_SMMU_COHERENT_WALK; + attr = (smmu->flags & ACPI_IORT_SMMU_COHERENT_WALK) ? + DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT; + + /* We expect the dma masks to be equivalent for SMMU set-ups */ + dev->dma_mask = &dev->coherent_dma_mask; + + /* Configure DMA for the page table walker */ + acpi_dma_configure(dev, attr); +} + +static int __init arm_smmu_v3_pmcg_count_resources(struct acpi_iort_node *node) +{ + struct acpi_iort_pmcg *pmcg; + + /* Retrieve PMCG specific data */ + pmcg = (struct acpi_iort_pmcg *)node->node_data; + + /* + * There are always 2 memory resources. + * If the overflow_gsiv is present then add that for a total of 3. + */ + return pmcg->overflow_gsiv ? 3 : 2; +} + +static void __init arm_smmu_v3_pmcg_init_resources(struct resource *res, + struct acpi_iort_node *node) +{ + struct acpi_iort_pmcg *pmcg; + + /* Retrieve PMCG specific data */ + pmcg = (struct acpi_iort_pmcg *)node->node_data; + + res[0].start = pmcg->page0_base_address; + res[0].end = pmcg->page0_base_address + SZ_4K - 1; + res[0].flags = IORESOURCE_MEM; + res[1].start = pmcg->page1_base_address; + res[1].end = pmcg->page1_base_address + SZ_4K - 1; + res[1].flags = IORESOURCE_MEM; + + if (pmcg->overflow_gsiv) + acpi_iort_register_irq(pmcg->overflow_gsiv, "overflow", + ACPI_EDGE_SENSITIVE, &res[2]); +} + +static int __init arm_smmu_v3_pmcg_add_platdata(struct platform_device *pdev) +{ + u32 model = IORT_SMMU_V3_PMCG_GENERIC; + + return platform_device_add_data(pdev, &model, sizeof(model)); } struct iort_dev_config { const char *name; int (*dev_init)(struct acpi_iort_node *node); - bool (*dev_is_coherent)(struct acpi_iort_node *node); + void (*dev_dma_configure)(struct device *dev, + struct acpi_iort_node *node); int (*dev_count_resources)(struct acpi_iort_node *node); void (*dev_init_resources)(struct resource *res, struct acpi_iort_node *node); void (*dev_set_proximity)(struct device *dev, struct acpi_iort_node *node); + int (*dev_add_platdata)(struct platform_device *pdev); }; static const struct iort_dev_config iort_arm_smmu_v3_cfg __initconst = { .name = "arm-smmu-v3", - .dev_is_coherent = arm_smmu_v3_is_coherent, + .dev_dma_configure = arm_smmu_v3_dma_configure, .dev_count_resources = arm_smmu_v3_count_resources, .dev_init_resources = arm_smmu_v3_init_resources, .dev_set_proximity = arm_smmu_v3_set_proximity, @@ -1332,9 +1396,16 @@ static const struct iort_dev_config iort_arm_smmu_v3_cfg __initconst = { static const struct iort_dev_config iort_arm_smmu_cfg __initconst = { .name = "arm-smmu", - .dev_is_coherent = arm_smmu_is_coherent, + .dev_dma_configure = arm_smmu_dma_configure, .dev_count_resources = arm_smmu_count_resources, - .dev_init_resources = arm_smmu_init_resources + .dev_init_resources = arm_smmu_init_resources, +}; + +static const struct iort_dev_config iort_arm_smmu_v3_pmcg_cfg __initconst = { + .name = "arm-smmu-v3-pmcg", + .dev_count_resources = arm_smmu_v3_pmcg_count_resources, + .dev_init_resources = arm_smmu_v3_pmcg_init_resources, + .dev_add_platdata = arm_smmu_v3_pmcg_add_platdata, }; static __init const struct iort_dev_config *iort_get_dev_cfg( @@ -1345,6 +1416,8 @@ static __init const struct iort_dev_config *iort_get_dev_cfg( return &iort_arm_smmu_v3_cfg; case ACPI_IORT_NODE_SMMU: return &iort_arm_smmu_cfg; + case ACPI_IORT_NODE_PMCG: + return &iort_arm_smmu_v3_pmcg_cfg; default: return NULL; } @@ -1362,7 +1435,6 @@ static int __init iort_add_platform_device(struct acpi_iort_node *node, struct fwnode_handle *fwnode; struct platform_device *pdev; struct resource *r; - enum dev_dma_attr attr; int ret, count; pdev = platform_device_alloc(ops->name, PLATFORM_DEVID_AUTO); @@ -1393,19 +1465,19 @@ static int __init iort_add_platform_device(struct acpi_iort_node *node, goto dev_put; /* - * Add a copy of IORT node pointer to platform_data to - * be used to retrieve IORT data information. + * Platform devices based on PMCG nodes uses platform_data to + * pass the hardware model info to the driver. For others, add + * a copy of IORT node pointer to platform_data to be used to + * retrieve IORT data information. */ - ret = platform_device_add_data(pdev, &node, sizeof(node)); + if (ops->dev_add_platdata) + ret = ops->dev_add_platdata(pdev); + else + ret = platform_device_add_data(pdev, &node, sizeof(node)); + if (ret) goto dev_put; - /* - * We expect the dma masks to be equivalent for - * all SMMUs set-ups - */ - pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask; - fwnode = iort_get_fwnode(node); if (!fwnode) { @@ -1415,11 +1487,8 @@ static int __init iort_add_platform_device(struct acpi_iort_node *node, pdev->dev.fwnode = fwnode; - attr = ops->dev_is_coherent && ops->dev_is_coherent(node) ? - DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT; - - /* Configure DMA for the page table walker */ - acpi_dma_configure(&pdev->dev, attr); + if (ops->dev_dma_configure) + ops->dev_dma_configure(&pdev->dev, node); iort_set_device_domain(&pdev->dev, node); -- cgit v1.2.3-55-g7522 From 24062fe85860debfdae0eeaa495f27c9971ec163 Mon Sep 17 00:00:00 2001 From: Shameer Kolothum Date: Tue, 26 Mar 2019 15:17:53 +0000 Subject: perf/smmuv3: Enable HiSilicon Erratum 162001800 quirk HiSilicon erratum 162001800 describes the limitation of SMMUv3 PMCG implementation on HiSilicon Hip08 platforms. On these platforms, the PMCG event counter registers (SMMU_PMCG_EVCNTRn) are read only and as a result it is not possible to set the initial counter period value on event monitor start. To work around this, the current value of the counter is read and used for delta calculations. OEM information from ACPI header is used to identify the affected hardware platforms. Signed-off-by: Shameer Kolothum Reviewed-by: Hanjun Guo Reviewed-by: Robin Murphy Acked-by: Lorenzo Pieralisi [will: update silicon-errata.txt and add reason string to acpi match] Signed-off-by: Will Deacon --- Documentation/arm64/silicon-errata.txt | 1 + drivers/acpi/arm64/iort.c | 16 +++++++++++- drivers/perf/arm_smmuv3_pmu.c | 48 +++++++++++++++++++++++++++++----- include/linux/acpi_iort.h | 1 + 4 files changed, 58 insertions(+), 8 deletions(-) (limited to 'drivers/acpi') diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt index d1e2bb801e1b..c00efb639e46 100644 --- a/Documentation/arm64/silicon-errata.txt +++ b/Documentation/arm64/silicon-errata.txt @@ -77,6 +77,7 @@ stable kernels. | Hisilicon | Hip0{5,6,7} | #161010101 | HISILICON_ERRATUM_161010101 | | Hisilicon | Hip0{6,7} | #161010701 | N/A | | Hisilicon | Hip07 | #161600802 | HISILICON_ERRATUM_161600802 | +| Hisilicon | Hip08 SMMU PMCG | #162001800 | N/A | | | | | | | Qualcomm Tech. | Kryo/Falkor v1 | E1003 | QCOM_FALKOR_ERRATUM_1003 | | Qualcomm Tech. | Falkor v1 | E1009 | QCOM_FALKOR_ERRATUM_1009 | diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index e2c9b26bbee6..2d70b349bd6c 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -1366,9 +1366,23 @@ static void __init arm_smmu_v3_pmcg_init_resources(struct resource *res, ACPI_EDGE_SENSITIVE, &res[2]); } +static struct acpi_platform_list pmcg_plat_info[] __initdata = { + /* HiSilicon Hip08 Platform */ + {"HISI ", "HIP08 ", 0, ACPI_SIG_IORT, greater_than_or_equal, + "Erratum #162001800", IORT_SMMU_V3_PMCG_HISI_HIP08}, + { } +}; + static int __init arm_smmu_v3_pmcg_add_platdata(struct platform_device *pdev) { - u32 model = IORT_SMMU_V3_PMCG_GENERIC; + u32 model; + int idx; + + idx = acpi_match_platform_list(pmcg_plat_info); + if (idx >= 0) + model = pmcg_plat_info[idx].data; + else + model = IORT_SMMU_V3_PMCG_GENERIC; return platform_device_add_data(pdev, &model, sizeof(model)); } diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c index a4f4b488a2de..da71c741cb46 100644 --- a/drivers/perf/arm_smmuv3_pmu.c +++ b/drivers/perf/arm_smmuv3_pmu.c @@ -35,6 +35,7 @@ */ #include +#include #include #include #include @@ -93,6 +94,8 @@ #define SMMU_PMCG_PA_SHIFT 12 +#define SMMU_PMCG_EVCNTR_RDONLY BIT(0) + static int cpuhp_state_num; struct smmu_pmu { @@ -108,6 +111,7 @@ struct smmu_pmu { void __iomem *reg_base; void __iomem *reloc_base; u64 counter_mask; + u32 options; bool global_filter; u32 global_filter_span; u32 global_filter_sid; @@ -222,15 +226,27 @@ static void smmu_pmu_set_period(struct smmu_pmu *smmu_pmu, u32 idx = hwc->idx; u64 new; - /* - * We limit the max period to half the max counter value of the counter - * size, so that even in the case of extreme interrupt latency the - * counter will (hopefully) not wrap past its initial value. - */ - new = smmu_pmu->counter_mask >> 1; + if (smmu_pmu->options & SMMU_PMCG_EVCNTR_RDONLY) { + /* + * On platforms that require this quirk, if the counter starts + * at < half_counter value and wraps, the current logic of + * handling the overflow may not work. It is expected that, + * those platforms will have full 64 counter bits implemented + * so that such a possibility is remote(eg: HiSilicon HIP08). + */ + new = smmu_pmu_counter_get_value(smmu_pmu, idx); + } else { + /* + * We limit the max period to half the max counter value + * of the counter size, so that even in the case of extreme + * interrupt latency the counter will (hopefully) not wrap + * past its initial value. + */ + new = smmu_pmu->counter_mask >> 1; + smmu_pmu_counter_set_value(smmu_pmu, idx, new); + } local64_set(&hwc->prev_count, new); - smmu_pmu_counter_set_value(smmu_pmu, idx, new); } static void smmu_pmu_set_event_filter(struct perf_event *event, @@ -665,6 +681,22 @@ static void smmu_pmu_reset(struct smmu_pmu *smmu_pmu) smmu_pmu->reloc_base + SMMU_PMCG_OVSCLR0); } +static void smmu_pmu_get_acpi_options(struct smmu_pmu *smmu_pmu) +{ + u32 model; + + model = *(u32 *)dev_get_platdata(smmu_pmu->dev); + + switch (model) { + case IORT_SMMU_V3_PMCG_HISI_HIP08: + /* HiSilicon Erratum 162001800 */ + smmu_pmu->options |= SMMU_PMCG_EVCNTR_RDONLY; + break; + } + + dev_notice(smmu_pmu->dev, "option mask 0x%x\n", smmu_pmu->options); +} + static int smmu_pmu_probe(struct platform_device *pdev) { struct smmu_pmu *smmu_pmu; @@ -744,6 +776,8 @@ static int smmu_pmu_probe(struct platform_device *pdev) return -EINVAL; } + smmu_pmu_get_acpi_options(smmu_pmu); + /* Pick one CPU to be the preferred one to use */ smmu_pmu->on_cpu = raw_smp_processor_id(); WARN_ON(irq_set_affinity_hint(smmu_pmu->irq, diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 052ef7b9f985..723e4dfa1c14 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -32,6 +32,7 @@ * do with hardware or with IORT specification. */ #define IORT_SMMU_V3_PMCG_GENERIC 0x00000000 /* Generic SMMUv3 PMCG */ +#define IORT_SMMU_V3_PMCG_HISI_HIP08 0x00000001 /* HiSilicon HIP08 PMCG */ int iort_register_domain_token(int trans_id, phys_addr_t base, struct fwnode_handle *fw_node); -- cgit v1.2.3-55-g7522 From 36a2ba07757df790b4a874efb1a105b9330a9ae7 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 8 Apr 2019 23:21:12 +0800 Subject: ACPI/IORT: Reject platform device creation on NUMA node mapping failure In a system where, through IORT firmware mappings, the SMMU device is mapped to a NUMA node that is not online, the kernel bootstrap results in the following crash: Unable to handle kernel paging request at virtual address 0000000000001388 Mem abort info: ESR = 0x96000004 Exception class = DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 Data abort info: ISV = 0, ISS = 0x00000004 CM = 0, WnR = 0 [0000000000001388] user address but active_mm is swapper Internal error: Oops: 96000004 [#1] SMP Modules linked in: CPU: 5 PID: 1 Comm: swapper/0 Not tainted 5.0.0 #15 pstate: 80c00009 (Nzcv daif +PAN +UAO) pc : __alloc_pages_nodemask+0x13c/0x1068 lr : __alloc_pages_nodemask+0xdc/0x1068 ... Process swapper/0 (pid: 1, stack limit = 0x(____ptrval____)) Call trace: __alloc_pages_nodemask+0x13c/0x1068 new_slab+0xec/0x570 ___slab_alloc+0x3e0/0x4f8 __slab_alloc+0x60/0x80 __kmalloc_node_track_caller+0x10c/0x478 devm_kmalloc+0x44/0xb0 pinctrl_bind_pins+0x4c/0x188 really_probe+0x78/0x2b8 driver_probe_device+0x64/0x110 device_driver_attach+0x74/0x98 __driver_attach+0x9c/0xe8 bus_for_each_dev+0x84/0xd8 driver_attach+0x30/0x40 bus_add_driver+0x170/0x218 driver_register+0x64/0x118 __platform_driver_register+0x54/0x60 arm_smmu_driver_init+0x24/0x2c do_one_initcall+0xbc/0x328 kernel_init_freeable+0x304/0x3ac kernel_init+0x18/0x110 ret_from_fork+0x10/0x1c Code: f90013b5 b9410fa1 1a9f0694 b50014c2 (b9400804) ---[ end trace dfeaed4c373a32da ]-- Change the dev_set_proximity() hook prototype so that it returns a value and make it return failure if the PXM->NUMA-node mapping corresponds to an offline node, fixing the crash. Acked-by: Lorenzo Pieralisi Signed-off-by: Kefeng Wang Link: https://lore.kernel.org/linux-arm-kernel/20190315021940.86905-1-wangkefeng.wang@huawei.com/ Signed-off-by: Will Deacon --- drivers/acpi/arm64/iort.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) (limited to 'drivers/acpi') diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index e48894e002ba..a46c2c162c03 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -1232,18 +1232,24 @@ static bool __init arm_smmu_v3_is_coherent(struct acpi_iort_node *node) /* * set numa proximity domain for smmuv3 device */ -static void __init arm_smmu_v3_set_proximity(struct device *dev, +static int __init arm_smmu_v3_set_proximity(struct device *dev, struct acpi_iort_node *node) { struct acpi_iort_smmu_v3 *smmu; smmu = (struct acpi_iort_smmu_v3 *)node->node_data; if (smmu->flags & ACPI_IORT_SMMU_V3_PXM_VALID) { - set_dev_node(dev, acpi_map_pxm_to_node(smmu->pxm)); + int node = acpi_map_pxm_to_node(smmu->pxm); + + if (node != NUMA_NO_NODE && !node_online(node)) + return -EINVAL; + + set_dev_node(dev, node); pr_info("SMMU-v3[%llx] Mapped to Proximity domain %d\n", smmu->base_address, smmu->pxm); } + return 0; } #else #define arm_smmu_v3_set_proximity NULL @@ -1318,7 +1324,7 @@ struct iort_dev_config { int (*dev_count_resources)(struct acpi_iort_node *node); void (*dev_init_resources)(struct resource *res, struct acpi_iort_node *node); - void (*dev_set_proximity)(struct device *dev, + int (*dev_set_proximity)(struct device *dev, struct acpi_iort_node *node); }; @@ -1369,8 +1375,11 @@ static int __init iort_add_platform_device(struct acpi_iort_node *node, if (!pdev) return -ENOMEM; - if (ops->dev_set_proximity) - ops->dev_set_proximity(&pdev->dev, node); + if (ops->dev_set_proximity) { + ret = ops->dev_set_proximity(&pdev->dev, node); + if (ret) + goto dev_put; + } count = ops->dev_count_resources(node); -- cgit v1.2.3-55-g7522