diff options
Diffstat (limited to 'drivers')
153 files changed, 3509 insertions, 2361 deletions
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index a9dd4ea7467d..6e594644cb1d 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4553,6 +4553,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { /* These specific Samsung models/firmware-revs do not handle LPM well */ { "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_HORKAGE_NOLPM, }, { "SAMSUNG SSD PM830 mSATA *", "CXM13D1Q", ATA_HORKAGE_NOLPM, }, + { "SAMSUNG MZ7TD256HAFV-000L9", "DXT02L5Q", ATA_HORKAGE_NOLPM, }, /* devices that don't properly handle queued TRIM commands */ { "Micron_M500IT_*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h index 34e0030f0592..7685df43f1ef 100644 --- a/drivers/block/null_blk.h +++ b/drivers/block/null_blk.h @@ -87,7 +87,9 @@ struct nullb { #ifdef CONFIG_BLK_DEV_ZONED int null_zone_init(struct nullb_device *dev); void null_zone_exit(struct nullb_device *dev); -blk_status_t null_zone_report(struct nullb *nullb, struct bio *bio); +int null_zone_report(struct gendisk *disk, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask); void null_zone_write(struct nullb_cmd *cmd, sector_t sector, unsigned int nr_sectors); void null_zone_reset(struct nullb_cmd *cmd, sector_t sector); @@ -97,10 +99,11 @@ static inline int null_zone_init(struct nullb_device *dev) return -EINVAL; } static inline void null_zone_exit(struct nullb_device *dev) {} -static inline blk_status_t null_zone_report(struct nullb *nullb, - struct bio *bio) +static inline int null_zone_report(struct gendisk *disk, sector_t sector, + struct blk_zone *zones, + unsigned int *nr_zones, gfp_t gfp_mask) { - return BLK_STS_NOTSUPP; + return -EOPNOTSUPP; } static inline void null_zone_write(struct nullb_cmd *cmd, sector_t sector, unsigned int nr_sectors) diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index e94591021682..09339203dfba 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -1129,34 +1129,12 @@ static void null_restart_queue_async(struct nullb *nullb) blk_mq_start_stopped_hw_queues(q, true); } -static bool cmd_report_zone(struct nullb *nullb, struct nullb_cmd *cmd) -{ - struct nullb_device *dev = cmd->nq->dev; - - if (dev->queue_mode == NULL_Q_BIO) { - if (bio_op(cmd->bio) == REQ_OP_ZONE_REPORT) { - cmd->error = null_zone_report(nullb, cmd->bio); - return true; - } - } else { - if (req_op(cmd->rq) == REQ_OP_ZONE_REPORT) { - cmd->error = null_zone_report(nullb, cmd->rq->bio); - return true; - } - } - - return false; -} - static blk_status_t null_handle_cmd(struct nullb_cmd *cmd) { struct nullb_device *dev = cmd->nq->dev; struct nullb *nullb = dev->nullb; int err = 0; - if (cmd_report_zone(nullb, cmd)) - goto out; - if (test_bit(NULLB_DEV_FL_THROTTLED, &dev->flags)) { struct request *rq = cmd->rq; @@ -1443,6 +1421,7 @@ static const struct block_device_operations null_fops = { .owner = THIS_MODULE, .open = null_open, .release = null_release, + .report_zones = null_zone_report, }; static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq) @@ -1549,6 +1528,13 @@ static int null_gendisk_register(struct nullb *nullb) disk->queue = nullb->q; strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN); + if (nullb->dev->zoned) { + int ret = blk_revalidate_disk_zones(disk); + + if (ret != 0) + return ret; + } + add_disk(disk); return 0; } diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c index 7c6b86d98700..c0b0e4a3fa8f 100644 --- a/drivers/block/null_blk_zoned.c +++ b/drivers/block/null_blk_zoned.c @@ -48,54 +48,27 @@ void null_zone_exit(struct nullb_device *dev) kvfree(dev->zones); } -static void null_zone_fill_bio(struct nullb_device *dev, struct bio *bio, - unsigned int zno, unsigned int nr_zones) +int null_zone_report(struct gendisk *disk, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask) { - struct blk_zone_report_hdr *hdr = NULL; - struct bio_vec bvec; - struct bvec_iter iter; - void *addr; - unsigned int zones_to_cpy; - - bio_for_each_segment(bvec, bio, iter) { - addr = kmap_atomic(bvec.bv_page); - - zones_to_cpy = bvec.bv_len / sizeof(struct blk_zone); - - if (!hdr) { - hdr = (struct blk_zone_report_hdr *)addr; - hdr->nr_zones = nr_zones; - zones_to_cpy--; - addr += sizeof(struct blk_zone_report_hdr); - } - - zones_to_cpy = min_t(unsigned int, zones_to_cpy, nr_zones); - - memcpy(addr, &dev->zones[zno], - zones_to_cpy * sizeof(struct blk_zone)); - - kunmap_atomic(addr); + struct nullb *nullb = disk->private_data; + struct nullb_device *dev = nullb->dev; + unsigned int zno, nrz = 0; - nr_zones -= zones_to_cpy; - zno += zones_to_cpy; + if (!dev->zoned) + /* Not a zoned null device */ + return -EOPNOTSUPP; - if (!nr_zones) - break; + zno = null_zone_no(dev, sector); + if (zno < dev->nr_zones) { + nrz = min_t(unsigned int, *nr_zones, dev->nr_zones - zno); + memcpy(zones, &dev->zones[zno], nrz * sizeof(struct blk_zone)); } -} -blk_status_t null_zone_report(struct nullb *nullb, struct bio *bio) -{ - struct nullb_device *dev = nullb->dev; - unsigned int zno = null_zone_no(dev, bio->bi_iter.bi_sector); - unsigned int nr_zones = dev->nr_zones - zno; - unsigned int max_zones; + *nr_zones = nrz; - max_zones = (bio->bi_iter.bi_size / sizeof(struct blk_zone)) - 1; - nr_zones = min_t(unsigned int, nr_zones, max_zones); - null_zone_fill_bio(nullb->dev, bio, zno, nr_zones); - - return BLK_STS_OK; + return 0; } void null_zone_write(struct nullb_cmd *cmd, sector_t sector, diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c index 7c5fc6942f32..2459dcc04b1c 100644 --- a/drivers/block/skd_main.c +++ b/drivers/block/skd_main.c @@ -3175,7 +3175,7 @@ static int skd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_out; rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (rc) - dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (rc) { dev_err(&pdev->dev, "DMA mask error %d\n", rc); goto err_out_regions; @@ -3364,7 +3364,7 @@ static int skd_pci_resume(struct pci_dev *pdev) goto err_out; rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (rc) - dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (rc) { dev_err(&pdev->dev, "DMA mask error %d\n", rc); goto err_out_regions; diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 9eea83ae01c6..56452cabce5b 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -2493,6 +2493,9 @@ static int blkfront_remove(struct xenbus_device *xbdev) dev_dbg(&xbdev->dev, "%s removed", xbdev->nodename); + if (!info) + return 0; + blkif_free(info, 0); mutex_lock(&info->mutex); diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c index 1106c076fa4b..600430685e28 100644 --- a/drivers/block/z2ram.c +++ b/drivers/block/z2ram.c @@ -191,8 +191,7 @@ static int z2_open(struct block_device *bdev, fmode_t mode) vfree(vmalloc (size)); } - vaddr = (unsigned long) __ioremap (paddr, size, - _PAGE_WRITETHRU); + vaddr = (unsigned long)ioremap_wt(paddr, size); #else vaddr = (unsigned long)z_remap_nocache_nonser(paddr, size); diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c index 4552b06fe601..f0404c6d1ff4 100644 --- a/drivers/bus/fsl-mc/fsl-mc-bus.c +++ b/drivers/bus/fsl-mc/fsl-mc-bus.c @@ -127,6 +127,16 @@ static int fsl_mc_bus_uevent(struct device *dev, struct kobj_uevent_env *env) return 0; } +static int fsl_mc_dma_configure(struct device *dev) +{ + struct device *dma_dev = dev; + + while (dev_is_fsl_mc(dma_dev)) + dma_dev = dma_dev->parent; + + return of_dma_configure(dev, dma_dev->of_node, 0); +} + static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -148,6 +158,7 @@ struct bus_type fsl_mc_bus_type = { .name = "fsl-mc", .match = fsl_mc_bus_match, .uevent = fsl_mc_bus_uevent, + .dma_configure = fsl_mc_dma_configure, .dev_groups = fsl_mc_dev_groups, }; EXPORT_SYMBOL_GPL(fsl_mc_bus_type); @@ -621,6 +632,7 @@ int fsl_mc_device_add(struct fsl_mc_obj_desc *obj_desc, mc_dev->icid = parent_mc_dev->icid; mc_dev->dma_mask = FSL_MC_DEFAULT_DMA_MASK; mc_dev->dev.dma_mask = &mc_dev->dma_mask; + mc_dev->dev.coherent_dma_mask = mc_dev->dma_mask; dev_set_msi_domain(&mc_dev->dev, dev_get_msi_domain(&parent_mc_dev->dev)); } @@ -638,10 +650,6 @@ int fsl_mc_device_add(struct fsl_mc_obj_desc *obj_desc, goto error_cleanup_dev; } - /* Objects are coherent, unless 'no shareability' flag set. */ - if (!(obj_desc->flags & FSL_MC_OBJ_FLAG_NO_MEM_SHAREABILITY)) - arch_setup_dma_ops(&mc_dev->dev, 0, 0, NULL, true); - /* * The device-specific probe callback will get invoked by device_add() */ @@ -698,8 +706,8 @@ static int parse_mc_ranges(struct device *dev, *ranges_start = of_get_property(mc_node, "ranges", &ranges_len); if (!(*ranges_start) || !ranges_len) { dev_warn(dev, - "missing or empty ranges property for device tree node '%s'\n", - mc_node->name); + "missing or empty ranges property for device tree node '%pOFn'\n", + mc_node); return 0; } @@ -722,7 +730,7 @@ static int parse_mc_ranges(struct device *dev, tuple_len = range_tuple_cell_count * sizeof(__be32); if (ranges_len % tuple_len != 0) { - dev_err(dev, "malformed ranges property '%s'\n", mc_node->name); + dev_err(dev, "malformed ranges property '%pOFn'\n", mc_node); return -EINVAL; } diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c index 70db4d5638a6..5b2a11a88951 100644 --- a/drivers/bus/mvebu-mbus.c +++ b/drivers/bus/mvebu-mbus.c @@ -1229,7 +1229,7 @@ mbus_parse_ranges(struct device_node *node, tuple_len = (*cell_count) * sizeof(__be32); if (ranges_len % tuple_len) { - pr_warn("malformed ranges entry '%s'\n", node->name); + pr_warn("malformed ranges entry '%pOFn'\n", node); return -EINVAL; } return 0; diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index 757e85b81879..a5b8afe3609c 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -327,15 +327,15 @@ static int get_entry_track(int track) static int gdrom_get_last_session(struct cdrom_device_info *cd_info, struct cdrom_multisession *ms_info) { - int fentry, lentry, track, data, tocuse, err; + int fentry, lentry, track, data, err; + if (!gd.toc) return -ENOMEM; - tocuse = 1; + /* Check if GD-ROM */ err = gdrom_readtoc_cmd(gd.toc, 1); /* Not a GD-ROM so check if standard CD-ROM */ if (err) { - tocuse = 0; err = gdrom_readtoc_cmd(gd.toc, 0); if (err) { pr_info("Could not get CD table of contents\n"); @@ -794,7 +794,7 @@ static int probe_gdrom(struct platform_device *devptr) gd.gdrom_rq = blk_mq_init_sq_queue(&gd.tag_set, &gdrom_mq_ops, 1, BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING); if (IS_ERR(gd.gdrom_rq)) { - rc = PTR_ERR(gd.gdrom_rq); + err = PTR_ERR(gd.gdrom_rq); gd.gdrom_rq = NULL; goto probe_fail_requestq; } diff --git a/drivers/clk/mvebu/clk-cpu.c b/drivers/clk/mvebu/clk-cpu.c index 072aa38374ce..3045067448fb 100644 --- a/drivers/clk/mvebu/clk-cpu.c +++ b/drivers/clk/mvebu/clk-cpu.c @@ -183,7 +183,7 @@ static void __init of_cpu_clk_setup(struct device_node *node) pr_warn("%s: pmu-dfs base register not set, dynamic frequency scaling not available\n", __func__); - for_each_node_by_type(dn, "cpu") + for_each_of_cpu_node(dn) ncpus++; cpuclk = kcalloc(ncpus, sizeof(*cpuclk), GFP_KERNEL); @@ -194,7 +194,7 @@ static void __init of_cpu_clk_setup(struct device_node *node) if (WARN_ON(!clks)) goto clks_out; - for_each_node_by_type(dn, "cpu") { + for_each_of_cpu_node(dn) { struct clk_init_data init; struct clk *clk; char *clk_name = kzalloc(5, GFP_KERNEL); diff --git a/drivers/edac/cpc925_edac.c b/drivers/edac/cpc925_edac.c index 2c98e020df05..3c0881ac9880 100644 --- a/drivers/edac/cpc925_edac.c +++ b/drivers/edac/cpc925_edac.c @@ -593,8 +593,7 @@ static void cpc925_mc_check(struct mem_ctl_info *mci) /******************** CPU err device********************************/ static u32 cpc925_cpu_mask_disabled(void) { - struct device_node *cpus; - struct device_node *cpunode = NULL; + struct device_node *cpunode; static u32 mask = 0; /* use cached value if available */ @@ -603,20 +602,8 @@ static u32 cpc925_cpu_mask_disabled(void) mask = APIMASK_ADI0 | APIMASK_ADI1; - cpus = of_find_node_by_path("/cpus"); - if (cpus == NULL) { - cpc925_printk(KERN_DEBUG, "No /cpus node !\n"); - return 0; - } - - while ((cpunode = of_get_next_child(cpus, cpunode)) != NULL) { + for_each_of_cpu_node(cpunode) { const u32 *reg = of_get_property(cpunode, "reg", NULL); - - if (strcmp(cpunode->type, "cpu")) { - cpc925_printk(KERN_ERR, "Not a cpu node in /cpus: %s\n", cpunode->name); - continue; - } - if (reg == NULL || *reg > 2) { cpc925_printk(KERN_ERR, "Bad reg value at %pOF\n", cpunode); continue; @@ -633,9 +620,6 @@ static u32 cpc925_cpu_mask_disabled(void) "Assuming PI id is equal to CPU MPIC id!\n"); } - of_node_put(cpunode); - of_node_put(cpus); - return mask; } diff --git a/drivers/firmware/scpi_pm_domain.c b/drivers/firmware/scpi_pm_domain.c index f395dec27113..390aa13391e4 100644 --- a/drivers/firmware/scpi_pm_domain.c +++ b/drivers/firmware/scpi_pm_domain.c @@ -121,7 +121,7 @@ static int scpi_pm_domain_probe(struct platform_device *pdev) scpi_pd->domain = i; scpi_pd->ops = scpi_ops; - sprintf(scpi_pd->name, "%s.%d", np->name, i); + sprintf(scpi_pd->name, "%pOFn.%d", np, i); scpi_pd->genpd.name = scpi_pd->name; scpi_pd->genpd.power_off = scpi_pd_power_off; scpi_pd->genpd.power_on = scpi_pd_power_on; diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index 2d45d1dd9554..643f5edd68fe 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -1446,8 +1446,7 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, } /* The CEC module handles HDMI hotplug detection */ - cec_np = of_find_compatible_node(np->parent, NULL, - "mediatek,mt8173-cec"); + cec_np = of_get_compatible_child(np->parent, "mediatek,mt8173-cec"); if (!cec_np) { dev_err(dev, "Failed to find CEC node\n"); return -EINVAL; @@ -1457,8 +1456,10 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, if (!cec_pdev) { dev_err(hdmi->dev, "Waiting for CEC device %pOF\n", cec_np); + of_node_put(cec_np); return -EPROBE_DEFER; } + of_node_put(cec_np); hdmi->cec_dev = &cec_pdev->dev; /* diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index da1363a0c54d..93d70f4a2154 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -633,8 +633,7 @@ static int adreno_get_legacy_pwrlevels(struct device *dev) struct device_node *child, *node; int ret; - node = of_find_compatible_node(dev->of_node, NULL, - "qcom,gpu-pwrlevels"); + node = of_get_compatible_child(dev->of_node, "qcom,gpu-pwrlevels"); if (!node) { dev_err(dev, "Could not find the GPU powerlevels\n"); return -ENXIO; @@ -655,6 +654,8 @@ static int adreno_get_legacy_pwrlevels(struct device *dev) dev_pm_opp_add(dev, val, 0); } + of_node_put(node); + return 0; } diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 83e6d993fca5..d9a25715650e 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -186,6 +186,19 @@ config INTEL_IOMMU and include PCI device scope covered by these DMA remapping devices. +config INTEL_IOMMU_DEBUGFS + bool "Export Intel IOMMU internals in Debugfs" + depends on INTEL_IOMMU && IOMMU_DEBUGFS + help + !!!WARNING!!! + + DO NOT ENABLE THIS OPTION UNLESS YOU REALLY KNOW WHAT YOU ARE DOING!!! + + Expose Intel IOMMU internals in Debugfs. + + This option is -NOT- intended for production environments, and should + only be enabled for debugging Intel IOMMU. + config INTEL_IOMMU_SVM bool "Support for Shared Virtual Memory with Intel IOMMU" depends on INTEL_IOMMU && X86 diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index ab5eba6edf82..a158a68c8ea8 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -17,6 +17,7 @@ obj-$(CONFIG_ARM_SMMU) += arm-smmu.o obj-$(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-$(CONFIG_INTEL_IOMMU_DEBUGFS) += intel-iommu-debugfs.o obj-$(CONFIG_INTEL_IOMMU_SVM) += intel-svm.o obj-$(CONFIG_IPMMU_VMSA) += ipmmu-vmsa.o obj-$(CONFIG_IRQ_REMAP) += intel_irq_remapping.o irq_remapping.o diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index bee0dfb7b93b..1167ff0416cf 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -3083,6 +3083,8 @@ static bool amd_iommu_capable(enum iommu_cap cap) return (irq_remapping_enabled == 1); case IOMMU_CAP_NOEXEC: return false; + default: + break; } return false; diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 3931c7de7c69..bb2cd29e1658 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -1719,7 +1719,7 @@ static const struct attribute_group *amd_iommu_groups[] = { NULL, }; -static int iommu_init_pci(struct amd_iommu *iommu) +static int __init iommu_init_pci(struct amd_iommu *iommu) { int cap_ptr = iommu->cap_ptr; u32 range, misc, low, high; diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 5059d09f3202..6947ccf26512 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -1,18 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* * IOMMU API for ARM architected SMMUv3 implementations. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License 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. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see <http://www.gnu.org/licenses/>. - * * Copyright (C) 2015 ARM Limited * * Author: Will Deacon <will.deacon@arm.com> @@ -567,7 +556,8 @@ struct arm_smmu_device { int gerr_irq; int combined_irq; - atomic_t sync_nr; + u32 sync_nr; + u8 prev_cmd_opcode; unsigned long ias; /* IPA */ unsigned long oas; /* PA */ @@ -611,6 +601,7 @@ struct arm_smmu_domain { struct mutex init_mutex; /* Protects smmu pointer */ struct io_pgtable_ops *pgtbl_ops; + bool non_strict; enum arm_smmu_domain_stage stage; union { @@ -708,7 +699,7 @@ static void queue_inc_prod(struct arm_smmu_queue *q) } /* - * Wait for the SMMU to consume items. If drain is true, wait until the queue + * Wait for the SMMU to consume items. If sync is true, wait until the queue * is empty. Otherwise, wait until there is at least one free slot. */ static int queue_poll_cons(struct arm_smmu_queue *q, bool sync, bool wfe) @@ -901,6 +892,8 @@ static void arm_smmu_cmdq_insert_cmd(struct arm_smmu_device *smmu, u64 *cmd) struct arm_smmu_queue *q = &smmu->cmdq.q; bool wfe = !!(smmu->features & ARM_SMMU_FEAT_SEV); + smmu->prev_cmd_opcode = FIELD_GET(CMDQ_0_OP, cmd[0]); + while (queue_insert_raw(q, cmd) == -ENOSPC) { if (queue_poll_cons(q, false, wfe)) dev_err_ratelimited(smmu->dev, "CMDQ timeout\n"); @@ -948,15 +941,21 @@ static int __arm_smmu_cmdq_issue_sync_msi(struct arm_smmu_device *smmu) struct arm_smmu_cmdq_ent ent = { .opcode = CMDQ_OP_CMD_SYNC, .sync = { - .msidata = atomic_inc_return_relaxed(&smmu->sync_nr), .msiaddr = virt_to_phys(&smmu->sync_count), }, }; - arm_smmu_cmdq_build_cmd(cmd, &ent); - spin_lock_irqsave(&smmu->cmdq.lock, flags); - arm_smmu_cmdq_insert_cmd(smmu, cmd); + + /* Piggy-back on the previous command if it's a SYNC */ + if (smmu->prev_cmd_opcode == CMDQ_OP_CMD_SYNC) { + ent.sync.msidata = smmu->sync_nr; + } else { + ent.sync.msidata = ++smmu->sync_nr; + arm_smmu_cmdq_build_cmd(cmd, &ent); + arm_smmu_cmdq_insert_cmd(smmu, cmd); + } + spin_unlock_irqrestore(&smmu->cmdq.lock, flags); return __arm_smmu_sync_poll_msi(smmu, ent.sync.msidata); @@ -1372,15 +1371,11 @@ static irqreturn_t arm_smmu_combined_irq_handler(int irq, void *dev) } /* IO_PGTABLE API */ -static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu) -{ - arm_smmu_cmdq_issue_sync(smmu); -} - static void arm_smmu_tlb_sync(void *cookie) { struct arm_smmu_domain *smmu_domain = cookie; - __arm_smmu_tlb_sync(smmu_domain->smmu); + + arm_smmu_cmdq_issue_sync(smmu_domain->smmu); } static void arm_smmu_tlb_inv_context(void *cookie) @@ -1398,8 +1393,14 @@ static void arm_smmu_tlb_inv_context(void *cookie) cmd.tlbi.vmid = smmu_domain->s2_cfg.vmid; } + /* + * NOTE: when io-pgtable is in non-strict mode, we may get here with + * PTEs previously cleared by unmaps on the current CPU not yet visible + * to the SMMU. We are relying on the DSB implicit in queue_inc_prod() + * to guarantee those are observed before the TLBI. Do be careful, 007. + */ arm_smmu_cmdq_issue_cmd(smmu, &cmd); - __arm_smmu_tlb_sync(smmu); + arm_smmu_cmdq_issue_sync(smmu); } static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size, @@ -1624,6 +1625,9 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain) if (smmu->features & ARM_SMMU_FEAT_COHERENCY) pgtbl_cfg.quirks = IO_PGTABLE_QUIRK_NO_DMA; + if (smmu_domain->non_strict) + pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_NON_STRICT; + pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain); if (!pgtbl_ops) return -ENOMEM; @@ -1772,12 +1776,20 @@ arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) return ops->unmap(ops, iova, size); } +static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain) +{ + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); + + if (smmu_domain->smmu) + arm_smmu_tlb_inv_context(smmu_domain); +} + static void arm_smmu_iotlb_sync(struct iommu_domain *domain) { struct arm_smmu_device *smmu = to_smmu_domain(domain)->smmu; if (smmu) - __arm_smmu_tlb_sync(smmu); + arm_smmu_cmdq_issue_sync(smmu); } static phys_addr_t @@ -1917,15 +1929,27 @@ static int arm_smmu_domain_get_attr(struct iommu_domain *domain, { struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); - if (domain->type != IOMMU_DOMAIN_UNMANAGED) - return -EINVAL; - - switch (attr) { - case DOMAIN_ATTR_NESTING: - *(int *)data = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED); - return 0; + switch (domain->type) { + case IOMMU_DOMAIN_UNMANAGED: + switch (attr) { + case DOMAIN_ATTR_NESTING: + *(int *)data = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED); + return 0; + default: + return -ENODEV; + } + break; + case IOMMU_DOMAIN_DMA: + switch (attr) { + case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE: + *(int *)data = smmu_domain->non_strict; + return 0; + default: + return -ENODEV; + } + break; default: - return -ENODEV; + return -EINVAL; } } @@ -1935,26 +1959,37 @@ static int arm_smmu_domain_set_attr(struct iommu_domain *domain, int ret = 0; struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); - if (domain->type != IOMMU_DOMAIN_UNMANAGED) - return -EINVAL; - mutex_lock(&smmu_domain->init_mutex); - switch (attr) { - case DOMAIN_ATTR_NESTING: - if (smmu_domain->smmu) { - ret = -EPERM; - goto out_unlock; + switch (domain->type) { + case IOMMU_DOMAIN_UNMANAGED: + switch (attr) { + case DOMAIN_ATTR_NESTING: + if (smmu_domain->smmu) { + ret = -EPERM; + goto out_unlock; + } + + if (*(int *)data) + smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED; + else + smmu_domain->stage = ARM_SMMU_DOMAIN_S1; + break; + default: + ret = -ENODEV; + } + break; + case IOMMU_DOMAIN_DMA: + switch(attr) { + case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE: + smmu_domain->non_strict = *(int *)data; + break; + default: + ret = -ENODEV; } - - if (*(int *)data) - smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED; - else - smmu_domain->stage = ARM_SMMU_DOMAIN_S1; - break; default: - ret = -ENODEV; + ret = -EINVAL; } out_unlock: @@ -1999,7 +2034,7 @@ static struct iommu_ops arm_smmu_ops = { .attach_dev = arm_smmu_attach_dev, .map = arm_smmu_map, .unmap = arm_smmu_unmap, - .flush_iotlb_all = arm_smmu_iotlb_sync, + .flush_iotlb_all = arm_smmu_flush_iotlb_all, .iotlb_sync = arm_smmu_iotlb_sync, .iova_to_phys = arm_smmu_iova_to_phys, .add_device = arm_smmu_add_device, @@ -2180,7 +2215,6 @@ static int arm_smmu_init_structures(struct arm_smmu_device *smmu) { int ret; - atomic_set(&smmu->sync_nr, 0); ret = arm_smmu_init_queues(smmu); if (ret) return ret; @@ -2353,8 +2387,8 @@ static int arm_smmu_setup_irqs(struct arm_smmu_device *smmu) irq = smmu->combined_irq; if (irq) { /* - * Cavium ThunderX2 implementation doesn't not support unique - * irq lines. Use single irq line for all the SMMUv3 interrupts. + * Cavium ThunderX2 implementation doesn't support unique irq + * lines. Use a single irq line for all the SMMUv3 interrupts. */ ret = devm_request_threaded_irq(smmu->dev, irq, arm_smmu_combined_irq_handler, diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index fd1b80ef9490..5a28ae892504 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -52,6 +52,7 @@ #include <linux/spinlock.h> #include <linux/amba/bus.h> +#include <linux/fsl/mc.h> #include "io-pgtable.h" #include "arm-smmu-regs.h" @@ -246,6 +247,7 @@ struct arm_smmu_domain { const struct iommu_gather_ops *tlb_ops; struct arm_smmu_cfg cfg; enum arm_smmu_domain_stage stage; + bool non_strict; struct mutex init_mutex; /* Protects smmu pointer */ spinlock_t cb_lock; /* Serialises ATS1* ops and TLB syncs */ struct iommu_domain domain; @@ -447,7 +449,11 @@ static void arm_smmu_tlb_inv_context_s1(void *cookie) struct arm_smmu_cfg *cfg = &smmu_domain->cfg; void __iomem *base = ARM_SMMU_CB(smmu_domain->smmu, cfg->cbndx); - writel_relaxed(cfg->asid, base + ARM_SMMU_CB_S1_TLBIASID); + /* + * NOTE: this is not a relaxed write; it needs to guarantee that PTEs + * cleared by the current CPU are visible to the SMMU before the TLBI. + */ + writel(cfg->asid, base + ARM_SMMU_CB_S1_TLBIASID); arm_smmu_tlb_sync_context(cookie); } @@ -457,7 +463,8 @@ static void arm_smmu_tlb_inv_context_s2(void *cookie) struct arm_smmu_device *smmu = smmu_domain->smmu; void __iomem *base = ARM_SMMU_GR0(smmu); - writel_relaxed(smmu_domain->cfg.vmid, base + ARM_SMMU_GR0_TLBIVMID); + /* NOTE: see above */ + writel(smmu_domain->cfg.vmid, base + ARM_SMMU_GR0_TLBIVMID); arm_smmu_tlb_sync_global(smmu); } @@ -469,6 +476,9 @@ static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size, bool stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS; void __iomem *reg = ARM_SMMU_CB(smmu_domain->smmu, cfg->cbndx); + if (smmu_domain->smmu->features & ARM_SMMU_FEAT_COHERENT_WALK) + wmb(); + if (stage1) { reg += leaf ? ARM_SMMU_CB_S1_TLBIVAL : ARM_SMMU_CB_S1_TLBIVA; @@ -510,6 +520,9 @@ static void arm_smmu_tlb_inv_vmid_nosync(unsigned long iova, size_t size, struct arm_smmu_domain *smmu_domain = cookie; void __iomem *base = ARM_SMMU_GR0(smmu_domain->smmu); + if (smmu_domain->smmu->features & ARM_SMMU_FEAT_COHERENT_WALK) + wmb(); + writel_relaxed(smmu_domain->cfg.vmid, base + ARM_SMMU_GR0_TLBIVMID); } @@ -863,6 +876,9 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain, if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK) pgtbl_cfg.quirks = IO_PGTABLE_QUIRK_NO_DMA; + if (smmu_domain->non_strict) + pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_NON_STRICT; + smmu_domain->smmu = smmu; pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain); if (!pgtbl_ops) { @@ -1252,6 +1268,14 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova, return ops->unmap(ops, iova, size); } +static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain) +{ + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); + + if (smmu_domain->tlb_ops) + smmu_domain->tlb_ops->tlb_flush_all(smmu_domain); +} + static void arm_smmu_iotlb_sync(struct iommu_domain *domain) { struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); @@ -1459,6 +1483,8 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev) if (dev_is_pci(dev)) group = pci_device_group(dev); + else if (dev_is_fsl_mc(dev)) + group = fsl_mc_device_group(dev); else group = generic_device_group(dev); @@ -1470,15 +1496,27 @@ static int arm_smmu_domain_get_attr(struct iommu_domain *domain, { struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); - if (domain->type != IOMMU_DOMAIN_UNMANAGED) - return -EINVAL; - - switch (attr) { - case DOMAIN_ATTR_NESTING: - *(int *)data = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED); - return 0; + switch(domain->type) { + case IOMMU_DOMAIN_UNMANAGED: + switch (attr) { + case DOMAIN_ATTR_NESTING: + *(int *)data = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED); + return 0; + default: + return -ENODEV; + } + break; + case IOMMU_DOMAIN_DMA: + switch (attr) { + case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE: + *(int *)data = smmu_domain->non_strict; + return 0; + default: + return -ENODEV; + } + break; default: - return -ENODEV; + return -EINVAL; } } @@ -1488,28 +1526,38 @@ static int arm_smmu_domain_set_attr(struct iommu_domain *domain, int ret = 0; struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); - if (domain->type != IOMMU_DOMAIN_UNMANAGED) - return -EINVAL; - mutex_lock(&smmu_domain->init_mutex); - switch (attr) { - case DOMAIN_ATTR_NESTING: - if (smmu_domain->smmu) { - ret = -EPERM; - goto out_unlock; + switch(domain->type) { + case IOMMU_DOMAIN_UNMANAGED: + switch (attr) { + case DOMAIN_ATTR_NESTING: + if (smmu_domain->smmu) { + ret = -EPERM; + goto out_unlock; + } + + if (*(int *)data) + smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED; + else + smmu_domain->stage = ARM_SMMU_DOMAIN_S1; + break; + default: + ret = -ENODEV; + } + break; + case IOMMU_DOMAIN_DMA: + switch (attr) { + case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE: + smmu_domain->non_strict = *(int *)data; + break; + default: + ret = -ENODEV; } - - if (*(int *)data) - smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED; - else - smmu_domain->stage = ARM_SMMU_DOMAIN_S1; - break; default: - ret = -ENODEV; + ret = -EINVAL; } - out_unlock: mutex_unlock(&smmu_domain->init_mutex); return ret; @@ -1562,7 +1610,7 @@ static struct iommu_ops arm_smmu_ops = { .attach_dev = arm_smmu_attach_dev, .map = arm_smmu_map, .unmap = arm_smmu_unmap, - .flush_iotlb_all = arm_smmu_iotlb_sync, + .flush_iotlb_all = arm_smmu_flush_iotlb_all, .iotlb_sync = arm_smmu_iotlb_sync, .iova_to_phys = arm_smmu_iova_to_phys, .add_device = arm_smmu_add_device, @@ -2036,6 +2084,10 @@ static void arm_smmu_bus_init(void) bus_set_iommu(&pci_bus_type, &arm_smmu_ops); } #endif +#ifdef CONFIG_FSL_MC_BUS + if (!iommu_present(&fsl_mc_bus_type)) + bus_set_iommu(&fsl_mc_bus_type, &arm_smmu_ops); +#endif } static int arm_smmu_device_probe(struct platform_device *pdev) diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 511ff9a1d6d9..d1b04753b204 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -55,6 +55,9 @@ struct iommu_dma_cookie { }; struct list_head msi_page_list; spinlock_t msi_lock; + + /* Domain for flush queue callback; NULL if flush queue not in use */ + struct iommu_domain *fq_domain; }; static inline size_t cookie_msi_granule(struct iommu_dma_cookie *cookie) @@ -257,6 +260,20 @@ static int iova_reserve_iommu_regions(struct device *dev, return ret; } +static void iommu_dma_flush_iotlb_all(struct iova_domain *iovad) +{ + struct iommu_dma_cookie *cookie; + struct iommu_domain *domain; + + cookie = container_of(iovad, struct iommu_dma_cookie, iovad); + domain = cookie->fq_domain; + /* + * The IOMMU driver supporting DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE + * implies that ops->flush_iotlb_all must be non-NULL. + */ + domain->ops->flush_iotlb_all(domain); +} + /** * iommu_dma_init_domain - Initialise a DMA mapping domain * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie() @@ -275,6 +292,7 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, struct iommu_dma_cookie *cookie = domain->iova_cookie; struct iova_domain *iovad = &cookie->iovad; unsigned long order, base_pfn, end_pfn; + int attr; if (!cookie || cookie->type != IOMMU_DMA_IOVA_COOKIE) return -EINVAL; @@ -308,6 +326,13 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base, } init_iova_domain(iovad, 1UL << order, base_pfn); + + if (!cookie->fq_domain && !iommu_domain_get_attr(domain, + DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE, &attr) && attr) { + cookie->fq_domain = domain; + init_iova_flush_queue(iovad, iommu_dma_flush_iotlb_all, NULL); + } + if (!dev) return 0; @@ -393,6 +418,9 @@ static void iommu_dma_free_iova(struct iommu_dma_cookie *cookie, /* The MSI case is only ever cleaning up its most recent allocation */ if (cookie->type == IOMMU_DMA_MSI_COOKIE) cookie->msi_iova -= size; + else if (cookie->fq_domain) /* non-strict mode */ + queue_iova(iovad, iova_pfn(iovad, iova), + size >> iova_shift(iovad), 0); else free_iova_fast(iovad, iova_pfn(iovad, iova), size >> iova_shift(iovad)); @@ -408,7 +436,9 @@ static void __iommu_dma_unmap(struct iommu_domain *domain, dma_addr_t dma_addr, dma_addr -= iova_off; size = iova_align(iovad, size + iova_off); - WARN_ON(iommu_unmap(domain, dma_addr, size) != size); + WARN_ON(iommu_unmap_fast(domain, dma_addr, size) != size); + if (!cookie->fq_domain) + iommu_tlb_sync(domain); iommu_dma_free_iova(cookie, dma_addr, size); } @@ -491,7 +521,7 @@ static struct page **__iommu_dma_alloc_pages(unsigned int count, void iommu_dma_free(struct device *dev, struct page **pages, size_t size, dma_addr_t *handle) { - __iommu_dma_unmap(iommu_get_domain_for_dev(dev), *handle, size); + __iommu_dma_unmap(iommu_get_dma_domain(dev), *handle, size); __iommu_dma_free_pages(pages, PAGE_ALIGN(size) >> PAGE_SHIFT); *handle = IOMMU_MAPPING_ERROR; } @@ -518,7 +548,7 @@ struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp, unsigned long attrs, int prot, dma_addr_t *handle, void (*flush_page)(struct device *, const void *, phys_addr_t)) { - struct iommu_domain *domain = iommu_get_domain_for_dev(dev); + struct iommu_domain *domain = iommu_get_dma_domain(dev); struct iommu_dma_cookie *cookie = domain->iova_cookie; struct iova_domain *iovad = &cookie->iovad; struct page **pages; @@ -606,9 +636,8 @@ int iommu_dma_mmap(struct page **pages, size_t size, struct vm_area_struct *vma) } static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys, - size_t size, int prot) + size_t size, int prot, struct iommu_domain *domain) { - struct iommu_domain *domain = iommu_get_domain_for_dev(dev); struct iommu_dma_cookie *cookie = domain->iova_cookie; size_t iova_off = 0; dma_addr_t iova; @@ -632,13 +661,14 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys, dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, int prot) { - return __iommu_dma_map(dev, page_to_phys(page) + offset, size, prot); + return __iommu_dma_map(dev, page_to_phys(page) + offset, size, prot, + iommu_get_dma_domain(dev)); } void iommu_dma_unmap_page(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir, unsigned long attrs) { - __iommu_dma_unmap(iommu_get_domain_for_dev(dev), handle, size); + __iommu_dma_unmap(iommu_get_dma_domain(dev), handle, size); } /* @@ -726,7 +756,7 @@ static void __invalidate_sg(struct scatterlist *sg, int nents) int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, int prot) { - struct iommu_domain *domain = iommu_get_domain_for_dev(dev); + struct iommu_domain *domain = iommu_get_dma_domain(dev); struct iommu_dma_cookie *cookie = domain->iova_cookie; struct iova_domain *iovad = &cookie->iovad; struct scatterlist *s, *prev = NULL; @@ -811,20 +841,21 @@ void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, sg = tmp; } end = sg_dma_address(sg) + sg_dma_len(sg); - __iommu_dma_unmap(iommu_get_domain_for_dev(dev), start, end - start); + __iommu_dma_unmap(iommu_get_dma_domain(dev), start, end - start); } dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys, size_t size, enum dma_data_direction dir, unsigned long attrs) { return __iommu_dma_map(dev, phys, size, - dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO); + dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO, + iommu_get_dma_domain(dev)); } void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir, unsigned long attrs) { - __iommu_dma_unmap(iommu_get_domain_for_dev(dev), handle, size); + __iommu_dma_unmap(iommu_get_dma_domain(dev), handle, size); } int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr) @@ -850,7 +881,7 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev, if (!msi_page) return NULL; - iova = __iommu_dma_map(dev, msi_addr, size, prot); + iova = __iommu_dma_map(dev, msi_addr, size, prot, domain); if (iommu_dma_mapping_error(dev, iova)) goto out_free_page; diff --git a/drivers/iommu/fsl_pamu.c b/drivers/iommu/fsl_pamu.c index 8540625796a1..1b955aea44dd 100644 --- a/drivers/iommu/fsl_pamu.c +++ b/drivers/iommu/fsl_pamu.c @@ -543,7 +543,7 @@ u32 get_stash_id(u32 stash_dest_hint, u32 vcpu) return ~(u32)0; } - for_each_node_by_type(node, "cpu") { + for_each_of_cpu_node(node) { prop = of_get_property(node, "reg", &len); for (i = 0; i < len / sizeof(u32); i++) { if (be32_to_cpup(&prop[i]) == vcpu) { diff --git a/drivers/iommu/fsl_pamu_domain.c b/drivers/iommu/fsl_pamu_domain.c index f089136e9c3f..9b528cfcc6c3 100644 --- a/drivers/iommu/fsl_pamu_domain.c +++ b/drivers/iommu/fsl_pamu_domain.c @@ -814,6 +814,55 @@ static int configure_domain_dma_state(struct fsl_dma_domain *dma_domain, bool en return 0; } +static int fsl_pamu_set_windows(struct iommu_domain *domain, u32 w_count) +{ + struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain); + unsigned long flags; + int ret; + + spin_lock_irqsave(&dma_domain->domain_lock, flags); + /* Ensure domain is inactive i.e. DMA should be disabled for the domain */ + if (dma_domain->enabled) { + pr_debug("Can't set geometry attributes as domain is active\n"); + spin_unlock_irqrestore(&dma_domain->domain_lock, flags); + return -EBUSY; + } + + /* Ensure that the geometry has been set for the domain */ + if (!dma_domain->geom_size) { + pr_debug("Please configure geometry before setting the number of windows\n"); + spin_unlock_irqrestore(&dma_domain->domain_lock, flags); + return -EINVAL; + } + + /* + * Ensure we have valid window count i.e. it should be less than + * maximum permissible limit and should be a power of two. + */ + if (w_count > pamu_get_max_subwin_cnt() || !is_power_of_2(w_count)) { + pr_debug("Invalid window count\n"); + spin_unlock_irqrestore(&dma_domain->domain_lock, flags); + return -EINVAL; + } + + ret = pamu_set_domain_geometry(dma_domain, &domain->geometry, + w_count > 1 ? w_count : 0); + if (!ret) { + kfree(dma_domain->win_arr); + dma_domain->win_arr = kcalloc(w_count, + sizeof(*dma_domain->win_arr), + GFP_ATOMIC); + if (!dma_domain->win_arr) { + spin_unlock_irqrestore(&dma_domain->domain_lock, flags); + return -ENOMEM; + } + dma_domain->win_cnt = w_count; + } + spin_unlock_irqrestore(&dma_domain->domain_lock, flags); + + return ret; +} + static int fsl_pamu_set_domain_attr(struct iommu_domain *domain, enum iommu_attr attr_type, void *data) { @@ -830,6 +879,9 @@ static int fsl_pamu_set_domain_attr(struct iommu_domain *domain, case DOMAIN_ATTR_FSL_PAMU_ENABLE: ret = configure_domain_dma_state(dma_domain, *(int *)data); break; + case DOMAIN_ATTR_WINDOWS: + ret = fsl_pamu_set_windows(domain, *(u32 *)data); + break; default: pr_debug("Unsupported attribute type\n"); ret = -EINVAL; @@ -856,6 +908,9 @@ static int fsl_pamu_get_domain_attr(struct iommu_domain *domain, case DOMAIN_ATTR_FSL_PAMUV1: *(int *)data = DOMAIN_ATTR_FSL_PAMUV1; break; + case DOMAIN_ATTR_WINDOWS: + *(u32 *)data = dma_domain->win_cnt; + break; default: pr_debug("Unsupported attribute type\n"); ret = -EINVAL; @@ -916,13 +971,13 @@ static struct iommu_group *get_shared_pci_device_group(struct pci_dev *pdev) static struct iommu_group *get_pci_device_group(struct pci_dev *pdev) { struct pci_controller *pci_ctl; - bool pci_endpt_partioning; + bool pci_endpt_partitioning; struct iommu_group *group = NULL; pci_ctl = pci_bus_to_host(pdev->bus); - pci_endpt_partioning = check_pci_ctl_endpt_part(pci_ctl); + pci_endpt_partitioning = check_pci_ctl_endpt_part(pci_ctl); /* We can partition PCIe devices so assign device group to the device */ - if (pci_endpt_partioning) { + if (pci_endpt_partitioning) { group = pci_device_group(&pdev->dev); /* @@ -994,62 +1049,6 @@ static void fsl_pamu_remove_device(struct device *dev) iommu_group_remove_device(dev); } -static int fsl_pamu_set_windows(struct iommu_domain *domain, u32 w_count) -{ - struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain); - unsigned long flags; - int ret; - - spin_lock_irqsave(&dma_domain->domain_lock, flags); - /* Ensure domain is inactive i.e. DMA should be disabled for the domain */ - if (dma_domain->enabled) { - pr_debug("Can't set geometry attributes as domain is active\n"); - spin_unlock_irqrestore(&dma_domain->domain_lock, flags); - return -EBUSY; - } - - /* Ensure that the geometry has been set for the domain */ - if (!dma_domain->geom_size) { - pr_debug("Please configure geometry before setting the number of windows\n"); - spin_unlock_irqrestore(&dma_domain->domain_lock, flags); - return -EINVAL; - } - - /* - * Ensure we have valid window count i.e. it should be less than - * maximum permissible limit and should be a power of two. - */ - if (w_count > pamu_get_max_subwin_cnt() || !is_power_of_2(w_count)) { - pr_debug("Invalid window count\n"); - spin_unlock_irqrestore(&dma_domain->domain_lock, flags); - return -EINVAL; - } - - ret = pamu_set_domain_geometry(dma_domain, &domain->geometry, - w_count > 1 ? w_count : 0); - if (!ret) { - kfree(dma_domain->win_arr); - dma_domain->win_arr = kcalloc(w_count, - sizeof(*dma_domain->win_arr), - GFP_ATOMIC); - if (!dma_domain->win_arr) { - spin_unlock_irqrestore(&dma_domain->domain_lock, flags); - return -ENOMEM; - } - dma_domain->win_cnt = w_count; - } - spin_unlock_irqrestore(&dma_domain->domain_lock, flags); - - return ret; -} - -static u32 fsl_pamu_get_windows(struct iommu_domain *domain) -{ - struct fsl_dma_domain *dma_domain = to_fsl_dma_domain(domain); - - return dma_domain->win_cnt; -} - static const struct iommu_ops fsl_pamu_ops = { .capable = fsl_pamu_capable, .domain_alloc = fsl_pamu_domain_alloc, @@ -1058,8 +1057,6 @@ static const struct iommu_ops fsl_pamu_ops = { .detach_dev = fsl_pamu_detach_device, .domain_window_enable = fsl_pamu_window_enable, .domain_window_disable = fsl_pamu_window_disable, - .domain_get_windows = fsl_pamu_get_windows, - .domain_set_windows = fsl_pamu_set_windows, .iova_to_phys = fsl_pamu_iova_to_phys, .domain_set_attr = fsl_pamu_set_domain_attr, .domain_get_attr = fsl_pamu_get_domain_attr, diff --git a/drivers/iommu/intel-iommu-debugfs.c b/drivers/iommu/intel-iommu-debugfs.c new file mode 100644 index 000000000000..7fabf9b1c2dc --- /dev/null +++ b/drivers/iommu/intel-iommu-debugfs.c @@ -0,0 +1,314 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright © 2018 Intel Corporation. + * + * Authors: Gayatri Kammela <gayatri.kammela@intel.com> + * Sohil Mehta <sohil.mehta@intel.com> + * Jacob Pan <jacob.jun.pan@linux.intel.com> + */ + +#include <linux/debugfs.h> +#include <linux/dmar.h> +#include <linux/intel-iommu.h> +#include <linux/pci.h> + +#include <asm/irq_remapping.h> + +struct iommu_regset { + int offset; + const char *regs; +}; + +#define IOMMU_REGSET_ENTRY(_reg_) \ + { DMAR_##_reg_##_REG, __stringify(_reg_) } +static const struct iommu_regset iommu_regs[] = { + IOMMU_REGSET_ENTRY(VER), + IOMMU_REGSET_ENTRY(CAP), + IOMMU_REGSET_ENTRY(ECAP), + IOMMU_REGSET_ENTRY(GCMD), + IOMMU_REGSET_ENTRY(GSTS), + IOMMU_REGSET_ENTRY(RTADDR), + IOMMU_REGSET_ENTRY(CCMD), + IOMMU_REGSET_ENTRY(FSTS), + IOMMU_REGSET_ENTRY(FECTL), + IOMMU_REGSET_ENTRY(FEDATA), + IOMMU_REGSET_ENTRY(FEADDR), + IOMMU_REGSET_ENTRY(FEUADDR), + IOMMU_REGSET_ENTRY(AFLOG), + IOMMU_REGSET_ENTRY(PMEN), + IOMMU_REGSET_ENTRY(PLMBASE), + IOMMU_REGSET_ENTRY(PLMLIMIT), + IOMMU_REGSET_ENTRY(PHMBASE), + IOMMU_REGSET_ENTRY(PHMLIMIT), + IOMMU_REGSET_ENTRY(IQH), + IOMMU_REGSET_ENTRY(IQT), + IOMMU_REGSET_ENTRY(IQA), + IOMMU_REGSET_ENTRY(ICS), + IOMMU_REGSET_ENTRY(IRTA), + IOMMU_REGSET_ENTRY(PQH), + IOMMU_REGSET_ENTRY(PQT), + IOMMU_REGSET_ENTRY(PQA), + IOMMU_REGSET_ENTRY(PRS), + IOMMU_REGSET_ENTRY(PECTL), + IOMMU_REGSET_ENTRY(PEDATA), + IOMMU_REGSET_ENTRY(PEADDR), + IOMMU_REGSET_ENTRY(PEUADDR), + IOMMU_REGSET_ENTRY(MTRRCAP), + IOMMU_REGSET_ENTRY(MTRRDEF), + IOMMU_REGSET_ENTRY(MTRR_FIX64K_00000), + IOMMU_REGSET_ENTRY(MTRR_FIX16K_80000), + IOMMU_REGSET_ENTRY(MTRR_FIX16K_A0000), + IOMMU_REGSET_ENTRY(MTRR_FIX4K_C0000), + IOMMU_REGSET_ENTRY(MTRR_FIX4K_C8000), + IOMMU_REGSET_ENTRY(MTRR_FIX4K_D0000), + IOMMU_REGSET_ENTRY(MTRR_FIX4K_D8000), + IOMMU_REGSET_ENTRY(MTRR_FIX4K_E0000), + IOMMU_REGSET_ENTRY(MTRR_FIX4K_E8000), + IOMMU_REGSET_ENTRY(MTRR_FIX4K_F0000), + IOMMU_REGSET_ENTRY(MTRR_FIX4K_F8000), + IOMMU_REGSET_ENTRY(MTRR_PHYSBASE0), + IOMMU_REGSET_ENTRY(MTRR_PHYSMASK0), + IOMMU_REGSET_ENTRY(MTRR_PHYSBASE1), + IOMMU_REGSET_ENTRY(MTRR_PHYSMASK1), + IOMMU_REGSET_ENTRY(MTRR_PHYSBASE2), + IOMMU_REGSET_ENTRY(MTRR_PHYSMASK2), + IOMMU_REGSET_ENTRY(MTRR_PHYSBASE3), + IOMMU_REGSET_ENTRY(MTRR_PHYSMASK3), + IOMMU_REGSET_ENTRY(MTRR_PHYSBASE4), + IOMMU_REGSET_ENTRY(MTRR_PHYSMASK4), + IOMMU_REGSET_ENTRY(MTRR_PHYSBASE5), + IOMMU_REGSET_ENTRY(MTRR_PHYSMASK5), + IOMMU_REGSET_ENTRY(MTRR_PHYSBASE6), + IOMMU_REGSET_ENTRY(MTRR_PHYSMASK6), + IOMMU_REGSET_ENTRY(MTRR_PHYSBASE7), + IOMMU_REGSET_ENTRY(MTRR_PHYSMASK7), + IOMMU_REGSET_ENTRY(MTRR_PHYSBASE8), + IOMMU_REGSET_ENTRY(MTRR_PHYSMASK8), + IOMMU_REGSET_ENTRY(MTRR_PHYSBASE9), + IOMMU_REGSET_ENTRY(MTRR_PHYSMASK9), + IOMMU_REGSET_ENTRY(VCCAP), + IOMMU_REGSET_ENTRY(VCMD), + IOMMU_REGSET_ENTRY(VCRSP), +}; + +static int iommu_regset_show(struct seq_file *m, void *unused) +{ + struct dmar_drhd_unit *drhd; + struct intel_iommu *iommu; + unsigned long flag; + int i, ret = 0; + u64 value; + + rcu_read_lock(); + for_each_active_iommu(iommu, drhd) { + if (!drhd->reg_base_addr) { + seq_puts(m, "IOMMU: Invalid base address\n"); + ret = -EINVAL; + goto out; + } + + seq_printf(m, "IOMMU: %s Register Base Address: %llx\n", + iommu->name, drhd->reg_base_addr); + seq_puts(m, "Name\t\t\tOffset\t\tContents\n"); + /* + * Publish the contents of the 64-bit hardware registers + * by adding the offset to the pointer (virtual address). + */ + raw_spin_lock_irqsave(&iommu->register_lock, flag); + for (i = 0 ; i < ARRAY_SIZE(iommu_regs); i++) { + value = dmar_readq(iommu->reg + iommu_regs[i].offset); + seq_printf(m, "%-16s\t0x%02x\t\t0x%016llx\n", + iommu_regs[i].regs, iommu_regs[i].offset, + value); + } + raw_spin_unlock_irqrestore(&iommu->register_lock, flag); + seq_putc(m, '\n'); + } +out: + rcu_read_unlock(); + + return ret; +} +DEFINE_SHOW_ATTRIBUTE(iommu_regset); + +static void ctx_tbl_entry_show(struct seq_file *m, struct intel_iommu *iommu, + int bus) +{ + struct context_entry *context; + int devfn; + + seq_printf(m, " Context Table Entries for Bus: %d\n", bus); + seq_puts(m, " Entry\tB:D.F\tHigh\tLow\n"); + + for (devfn = 0; devfn < 256; devfn++) { + context = iommu_context_addr(iommu, bus, devfn, 0); + if (!context) + return; + + if (!context_present(context)) + continue; + + seq_printf(m, " %-5d\t%02x:%02x.%x\t%-6llx\t%llx\n", devfn, + bus, PCI_SLOT(devfn), PCI_FUNC(devfn), + context[0].hi, context[0].lo); + } +} + +static void root_tbl_entry_show(struct seq_file *m, struct intel_iommu *iommu) +{ + unsigned long flags; + int bus; + + spin_lock_irqsave(&iommu->lock, flags); + seq_printf(m, "IOMMU %s: Root Table Address:%llx\n", iommu->name, + (u64)virt_to_phys(iommu->root_entry)); + seq_puts(m, "Root Table Entries:\n"); + + for (bus = 0; bus < 256; bus++) { + if (!(iommu->root_entry[bus].lo & 1)) + continue; + + seq_printf(m, " Bus: %d H: %llx L: %llx\n", bus, + iommu->root_entry[bus].hi, + iommu->root_entry[bus].lo); + + ctx_tbl_entry_show(m, iommu, bus); + seq_putc(m, '\n'); + } + spin_unlock_irqrestore(&iommu->lock, flags); +} + +static int dmar_translation_struct_show(struct seq_file *m, void *unused) +{ + struct dmar_drhd_unit *drhd; + struct intel_iommu *iommu; + + rcu_read_lock(); + for_each_active_iommu(iommu, drhd) { + root_tbl_entry_show(m, iommu); + seq_putc(m, '\n'); + } + rcu_read_unlock(); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(dmar_translation_struct); + +#ifdef CONFIG_IRQ_REMAP +static void ir_tbl_remap_entry_show(struct seq_file *m, + struct intel_iommu *iommu) +{ + struct irte *ri_entry; + unsigned long flags; + int idx; + + seq_puts(m, " Entry SrcID DstID Vct IRTE_high\t\tIRTE_low\n"); + + raw_spin_lock_irqsave(&irq_2_ir_lock, flags); + for (idx = 0; idx < INTR_REMAP_TABLE_ENTRIES; idx++) { + ri_entry = &iommu->ir_table->base[idx]; + if (!ri_entry->present || ri_entry->p_pst) + continue; + + seq_printf(m, " %-5d %02x:%02x.%01x %08x %02x %016llx\t%016llx\n", + idx, PCI_BUS_NUM(ri_entry->sid), + PCI_SLOT(ri_entry->sid), PCI_FUNC(ri_entry->sid), + ri_entry->dest_id, ri_entry->vector, + ri_entry->high, ri_entry->low); + } + raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags); +} + +static void ir_tbl_posted_entry_show(struct seq_file *m, + struct intel_iommu *iommu) +{ + struct irte *pi_entry; + unsigned long flags; + int idx; + + seq_puts(m, " Entry SrcID PDA_high PDA_low Vct IRTE_high\t\tIRTE_low\n"); + + raw_spin_lock_irqsave(&irq_2_ir_lock, flags); + for (idx = 0; idx < INTR_REMAP_TABLE_ENTRIES; idx++) { + pi_entry = &iommu->ir_table->base[idx]; + if (!pi_entry->present || !pi_entry->p_pst) + continue; + + seq_printf(m, " %-5d %02x:%02x.%01x %08x %08x %02x %016llx\t%016llx\n", + idx, PCI_BUS_NUM(pi_entry->sid), + PCI_SLOT(pi_entry->sid), PCI_FUNC(pi_entry->sid), + pi_entry->pda_h, pi_entry->pda_l << 6, + pi_entry->vector, pi_entry->high, + pi_entry->low); + } + raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags); +} + +/* + * For active IOMMUs go through the Interrupt remapping + * table and print valid entries in a table format for + * Remapped and Posted Interrupts. + */ +static int ir_translation_struct_show(struct seq_file *m, void *unused) +{ + struct dmar_drhd_unit *drhd; + struct intel_iommu *iommu; + u64 irta; + + rcu_read_lock(); + for_each_active_iommu(iommu, drhd) { + if (!ecap_ir_support(iommu->ecap)) + continue; + + seq_printf(m, "Remapped Interrupt supported on IOMMU: %s\n", + iommu->name); + + if (iommu->ir_table) { + irta = virt_to_phys(iommu->ir_table->base); + seq_printf(m, " IR table address:%llx\n", irta); + ir_tbl_remap_entry_show(m, iommu); + } else { + seq_puts(m, "Interrupt Remapping is not enabled\n"); + } + seq_putc(m, '\n'); + } + + seq_puts(m, "****\n\n"); + + for_each_active_iommu(iommu, drhd) { + if (!cap_pi_support(iommu->cap)) + continue; + + seq_printf(m, "Posted Interrupt supported on IOMMU: %s\n", + iommu->name); + + if (iommu->ir_table) { + irta = virt_to_phys(iommu->ir_table->base); + seq_printf(m, " IR table address:%llx\n", irta); + ir_tbl_posted_entry_show(m, iommu); + } else { + seq_puts(m, "Interrupt Remapping is not enabled\n"); + } + seq_putc(m, '\n'); + } + rcu_read_unlock(); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(ir_translation_struct); +#endif + +void __init intel_iommu_debugfs_init(void) +{ + struct dentry *intel_iommu_debug = debugfs_create_dir("intel", + iommu_debugfs_dir); + + debugfs_create_file("iommu_regset", 0444, intel_iommu_debug, NULL, + &iommu_regset_fops); + debugfs_create_file("dmar_translation_struct", 0444, intel_iommu_debug, + NULL, &dmar_translation_struct_fops); +#ifdef CONFIG_IRQ_REMAP + debugfs_create_file("ir_translation_struct", 0444, intel_iommu_debug, + NULL, &ir_translation_struct_fops); +#endif +} diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 76f0a5d16ed3..f3ccf025108b 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -185,16 +185,6 @@ static int rwbf_quirk; static int force_on = 0; int intel_iommu_tboot_noforce; -/* - * 0: Present - * 1-11: Reserved - * 12-63: Context Ptr (12 - (haw-1)) - * 64-127: Reserved - */ -struct root_entry { - u64 lo; - u64 hi; -}; #define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry)) /* @@ -220,21 +210,6 @@ static phys_addr_t root_entry_uctp(struct root_entry *re) return re->hi & VTD_PAGE_MASK; } -/* - * low 64 bits: - * 0: present - * 1: fault processing disable - * 2-3: translation type - * 12-63: address space root - * high 64 bits: - * 0-2: address width - * 3-6: aval - * 8-23: domain id - */ -struct context_entry { - u64 lo; - u64 hi; -}; static inline void context_clear_pasid_enable(struct context_entry *context) { @@ -261,7 +236,7 @@ static inline bool __context_present(struct context_entry *context) return (context->lo & 1); } -static inline bool context_present(struct context_entry *context) +bool context_present(struct context_entry *context) { return context_pasid_enabled(context) ? __context_present(context) : @@ -788,8 +763,8 @@ static void domain_update_iommu_cap(struct dmar_domain *domain) domain->iommu_superpage = domain_update_iommu_superpage(NULL); } -static inline struct context_entry *iommu_context_addr(struct intel_iommu *iommu, - u8 bus, u8 devfn, int alloc) +struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus, + u8 devfn, int alloc) { struct root_entry *root = &iommu->root_entry[bus]; struct context_entry *context; @@ -4860,6 +4835,7 @@ int __init intel_iommu_init(void) cpuhp_setup_state(CPUHP_IOMMU_INTEL_DEAD, "iommu/intel:dead", NULL, intel_iommu_cpu_dead); intel_iommu_enabled = 1; + intel_iommu_debugfs_init(); return 0; diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index 967450bd421a..c2d6c11431de 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -76,7 +76,7 @@ static struct hpet_scope ir_hpet[MAX_HPET_TBS]; * in single-threaded environment with interrupt disabled, so no need to tabke * the dmar_global_lock. */ -static DEFINE_RAW_SPINLOCK(irq_2_ir_lock); +DEFINE_RAW_SPINLOCK(irq_2_ir_lock); static const struct irq_domain_ops intel_ir_domain_ops; static void iommu_disable_irq_remapping(struct intel_iommu *iommu); diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index b5948ba6b3b3..445c3bde0480 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -587,6 +587,7 @@ static size_t arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data, } io_pgtable_tlb_add_flush(&data->iop, iova, size, size, true); + io_pgtable_tlb_sync(&data->iop); return size; } @@ -642,6 +643,13 @@ static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data, io_pgtable_tlb_sync(iop); ptep = iopte_deref(pte[i], lvl); __arm_v7s_free_table(ptep, lvl + 1, data); + } else if (iop->cfg.quirks & IO_PGTABLE_QUIRK_NON_STRICT) { + /* + * Order the PTE update against queueing the IOVA, to + * guarantee that a flush callback from a different CPU + * has observed it before the TLBIALL can be issued. + */ + smp_wmb(); } else { io_pgtable_tlb_add_flush(iop, iova, blk_size, blk_size, true); @@ -712,7 +720,8 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg, IO_PGTABLE_QUIRK_NO_PERMS | IO_PGTABLE_QUIRK_TLBI_ON_MAP | IO_PGTABLE_QUIRK_ARM_MTK_4GB | - IO_PGTABLE_QUIRK_NO_DMA)) + IO_PGTABLE_QUIRK_NO_DMA | + IO_PGTABLE_QUIRK_NON_STRICT)) return NULL; /* If ARM_MTK_4GB is enabled, the NO_PERMS is also expected. */ diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 88641b4560bc..237cacd4a62b 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -574,13 +574,13 @@ static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data, return 0; tablep = iopte_deref(pte, data); + } else if (unmap_idx >= 0) { + io_pgtable_tlb_add_flush(&data->iop, iova, size, size, true); + io_pgtable_tlb_sync(&data->iop); + return size; } - if (unmap_idx < 0) - return __arm_lpae_unmap(data, iova, size, lvl, tablep); - - io_pgtable_tlb_add_flush(&data->iop, iova, size, size, true); - return size; + return __arm_lpae_unmap(data, iova, size, lvl, tablep); } static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, @@ -610,6 +610,13 @@ static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, io_pgtable_tlb_sync(iop); ptep = iopte_deref(pte, data); __arm_lpae_free_pgtable(data, lvl + 1, ptep); + } else if (iop->cfg.quirks & IO_PGTABLE_QUIRK_NON_STRICT) { + /* + * Order the PTE update against queueing the IOVA, to + * guarantee that a flush callback from a different CPU + * has observed it before the TLBIALL can be issued. + */ + smp_wmb(); } else { io_pgtable_tlb_add_flush(iop, iova, size, size, true); } @@ -772,7 +779,8 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie) u64 reg; struct arm_lpae_io_pgtable *data; - if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS | IO_PGTABLE_QUIRK_NO_DMA)) + if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_NS | IO_PGTABLE_QUIRK_NO_DMA | + IO_PGTABLE_QUIRK_NON_STRICT)) return NULL; data = arm_lpae_alloc_pgtable(cfg); @@ -864,7 +872,8 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie) struct arm_lpae_io_pgtable *data; /* The NS quirk doesn't apply at stage 2 */ - if (cfg->quirks & ~IO_PGTABLE_QUIRK_NO_DMA) + if (cfg->quirks & ~(IO_PGTABLE_QUIRK_NO_DMA | + IO_PGTABLE_QUIRK_NON_STRICT)) return NULL; data = arm_lpae_alloc_pgtable(cfg); diff --git a/drivers/iommu/io-pgtable.h b/drivers/iommu/io-pgtable.h index 2df79093cad9..47d5ae559329 100644 --- a/drivers/iommu/io-pgtable.h +++ b/drivers/iommu/io-pgtable.h @@ -71,12 +71,17 @@ struct io_pgtable_cfg { * be accessed by a fully cache-coherent IOMMU or CPU (e.g. for a * software-emulated IOMMU), such that pagetable updates need not * be treated as explicit DMA data. + * + * IO_PGTABLE_QUIRK_NON_STRICT: Skip issuing synchronous leaf TLBIs + * on unmap, for DMA domains using the flush queue mechanism for + * delayed invalidation. */ #define IO_PGTABLE_QUIRK_ARM_NS BIT(0) #define IO_PGTABLE_QUIRK_NO_PERMS BIT(1) #define IO_PGTABLE_QUIRK_TLBI_ON_MAP BIT(2) #define IO_PGTABLE_QUIRK_ARM_MTK_4GB BIT(3) #define IO_PGTABLE_QUIRK_NO_DMA BIT(4) + #define IO_PGTABLE_QUIRK_NON_STRICT BIT(5) unsigned long quirks; unsigned long pgsize_bitmap; unsigned int ias; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 8c15c5980299..edbdf5d6962c 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -32,6 +32,7 @@ #include <linux/pci.h> #include <linux/bitops.h> #include <linux/property.h> +#include <linux/fsl/mc.h> #include <trace/events/iommu.h> static struct kset *iommu_group_kset; @@ -41,6 +42,7 @@ static unsigned int iommu_def_domain_type = IOMMU_DOMAIN_IDENTITY; #else static unsigned int iommu_def_domain_type = IOMMU_DOMAIN_DMA; #endif +static bool iommu_dma_strict __read_mostly = true; struct iommu_callback_data { const struct iommu_ops *ops; @@ -131,6 +133,12 @@ static int __init iommu_set_def_domain_type(char *str) } early_param("iommu.passthrough", iommu_set_def_domain_type); +static int __init iommu_dma_setup(char *str) +{ + return kstrtobool(str, &iommu_dma_strict); +} +early_param("iommu.strict", iommu_dma_setup); + static ssize_t iommu_group_attr_show(struct kobject *kobj, struct attribute *__attr, char *buf) { @@ -1024,6 +1032,18 @@ struct iommu_group *pci_device_group(struct device *dev) return iommu_group_alloc(); } +/* Get the IOMMU group for device on fsl-mc bus */ +struct iommu_group *fsl_mc_device_group(struct device *dev) +{ + struct device *cont_dev = fsl_mc_cont_dev(dev); + struct iommu_group *group; + + group = iommu_group_get(cont_dev); + if (!group) + group = iommu_group_alloc(); + return group; +} + /** * iommu_group_get_for_dev - Find or create the IOMMU group for a device * @dev: target device @@ -1072,6 +1092,13 @@ struct iommu_group *iommu_group_get_for_dev(struct device *dev) group->default_domain = dom; if (!group->domain) group->domain = dom; + + if (dom && !iommu_dma_strict) { + int attr = 1; + iommu_domain_set_attr(dom, + DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE, + &attr); + } } ret = iommu_group_add_device(group, dev); @@ -1416,7 +1443,16 @@ struct iommu_domain *iommu_get_domain_for_dev(struct device *dev) EXPORT_SYMBOL_GPL(iommu_get_domain_for_dev); /* - * IOMMU groups are really the natrual working unit of the IOMMU, but + * For IOMMU_DOMAIN_DMA implementations which already provide their own + * guarantees that the group and its default domain are valid and correct. + */ +struct iommu_domain *iommu_get_dma_domain(struct device *dev) +{ + return dev->iommu_group->default_domain; +} + +/* + * IOMMU groups are really the natural working unit of the IOMMU, but * the IOMMU API works on domains and devices. Bridge that gap by * iterating over the devices in a group. Ideally we'd have a single * device which represents the requestor ID of the group, but we also @@ -1796,7 +1832,6 @@ int iommu_domain_get_attr(struct iommu_domain *domain, struct iommu_domain_geometry *geometry; bool *paging; int ret = 0; - u32 *count; switch (attr) { case DOMAIN_ATTR_GEOMETRY: @@ -1808,15 +1843,6 @@ int iommu_domain_get_attr(struct iommu_domain *domain, paging = data; *paging = (domain->pgsize_bitmap != 0UL); break; - case DOMAIN_ATTR_WINDOWS: - count = data; - - if (domain->ops->domain_get_windows != NULL) - *count = domain->ops->domain_get_windows(domain); - else - ret = -ENODEV; - - break; default: if (!domain->ops->domain_get_attr) return -EINVAL; @@ -1832,18 +1858,8 @@ int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr attr, void *data) { int ret = 0; - u32 *count; switch (attr) { - case DOMAIN_ATTR_WINDOWS: - count = data; - - if (domain->ops->domain_set_windows != NULL) - ret = domain->ops->domain_set_windows(domain, *count); - else - ret = -ENODEV; - - break; default: if (domain->ops->domain_set_attr == NULL) return -EINVAL; diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index 83fe2621effe..f8d3ba247523 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -56,6 +56,7 @@ init_iova_domain(struct iova_domain *iovad, unsigned long granule, iovad->granule = granule; iovad->start_pfn = start_pfn; iovad->dma_32bit_pfn = 1UL << (32 - iova_shift(iovad)); + iovad->max32_alloc_size = iovad->dma_32bit_pfn; iovad->flush_cb = NULL; iovad->fq = NULL; iovad->anchor.pfn_lo = iovad->anchor.pfn_hi = IOVA_ANCHOR; @@ -139,8 +140,10 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free) cached_iova = rb_entry(iovad->cached32_node, struct iova, node); if (free->pfn_hi < iovad->dma_32bit_pfn && - free->pfn_lo >= cached_iova->pfn_lo) + free->pfn_lo >= cached_iova->pfn_lo) { iovad->cached32_node = rb_next(&free->node); + iovad->max32_alloc_size = iovad->dma_32bit_pfn; + } cached_iova = rb_entry(iovad->cached_node, struct iova, node); if (free->pfn_lo >= cached_iova->pfn_lo) @@ -190,6 +193,10 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad, /* Walk the tree backwards */ spin_lock_irqsave(&iovad->iova_rbtree_lock, flags); + if (limit_pfn <= iovad->dma_32bit_pfn && + size >= iovad->max32_alloc_size) + goto iova32_full; + curr = __get_cached_rbnode(iovad, limit_pfn); curr_iova = rb_entry(curr, struct iova, node); do { @@ -200,10 +207,8 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad, curr_iova = rb_entry(curr, struct iova, node); } while (curr && new_pfn <= curr_iova->pfn_hi); - if (limit_pfn < size || new_pfn < iovad->start_pfn) { - spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags); - return -ENOMEM; - } + if (limit_pfn < size || new_pfn < iovad->start_pfn) + goto iova32_full; /* pfn_lo will point to size aligned address if size_aligned is set */ new->pfn_lo = new_pfn; @@ -214,9 +219,12 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad, __cached_rbnode_insert_update(iovad, new); spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags); - - return 0; + +iova32_full: + iovad->max32_alloc_size = size; + spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags); + return -ENOMEM; } static struct kmem_cache *iova_cache; diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index 22b94f8a9a04..b98a03189580 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* * IPMMU VMSA * * Copyright (C) 2014 Renesas Electronics Corporation - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. */ #include <linux/bitmap.h> diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c index f7787e757244..c5dd63072529 100644 --- a/drivers/iommu/of_iommu.c +++ b/drivers/iommu/of_iommu.c @@ -24,6 +24,7 @@ #include <linux/of_iommu.h> #include <linux/of_pci.h> #include <linux/slab.h> +#include <linux/fsl/mc.h> #define NO_IOMMU 1 @@ -132,9 +133,8 @@ static int of_pci_iommu_init(struct pci_dev *pdev, u16 alias, void *data) struct of_phandle_args iommu_spec = { .args_count = 1 }; int err; - err = of_pci_map_rid(info->np, alias, "iommu-map", - "iommu-map-mask", &iommu_spec.np, - iommu_spec.args); + err = of_map_rid(info->np, alias, "iommu-map", "iommu-map-mask", + &iommu_spec.np, iommu_spec.args); if (err) return err == -ENODEV ? NO_IOMMU : err; @@ -143,6 +143,23 @@ static int of_pci_iommu_init(struct pci_dev *pdev, u16 alias, void *data) return err; } +static int of_fsl_mc_iommu_init(struct fsl_mc_device *mc_dev, + struct device_node *master_np) +{ + struct of_phandle_args iommu_spec = { .args_count = 1 }; + int err; + + err = of_map_rid(master_np, mc_dev->icid, "iommu-map", + "iommu-map-mask", &iommu_spec.np, + iommu_spec.args); + if (err) + return err == -ENODEV ? NO_IOMMU : err; + + err = of_iommu_xlate(&mc_dev->dev, &iommu_spec); + of_node_put(iommu_spec.np); + return err; +} + const struct iommu_ops *of_iommu_configure(struct device *dev, struct device_node *master_np) { @@ -174,6 +191,8 @@ const struct iommu_ops *of_iommu_configure(struct device *dev, err = pci_for_each_dma_alias(to_pci_dev(dev), of_pci_iommu_init, &info); + } else if (dev_is_fsl_mc(dev)) { + err = of_fsl_mc_iommu_init(to_fsl_mc_device(dev), master_np); } else { struct of_phandle_args iommu_spec; int idx = 0; diff --git a/drivers/macintosh/adb-iop.c b/drivers/macintosh/adb-iop.c index ca623e6446e4..fca31640e3ef 100644 --- a/drivers/macintosh/adb-iop.c +++ b/drivers/macintosh/adb-iop.c @@ -20,13 +20,13 @@ #include <linux/init.h> #include <linux/proc_fs.h> -#include <asm/macintosh.h> -#include <asm/macints.h> +#include <asm/macintosh.h> +#include <asm/macints.h> #include <asm/mac_iop.h> #include <asm/mac_oss.h> #include <asm/adb_iop.h> -#include <linux/adb.h> +#include <linux/adb.h> /*#define DEBUG_ADB_IOP*/ @@ -38,9 +38,9 @@ static unsigned char *reply_ptr; #endif static enum adb_iop_state { - idle, - sending, - awaiting_reply + idle, + sending, + awaiting_reply } adb_iop_state; static void adb_iop_start(void); @@ -66,7 +66,8 @@ static void adb_iop_end_req(struct adb_request *req, int state) { req->complete = 1; current_req = req->next; - if (req->done) (*req->done)(req); + if (req->done) + (*req->done)(req); adb_iop_state = state; } @@ -100,7 +101,7 @@ static void adb_iop_complete(struct iop_msg *msg) static void adb_iop_listen(struct iop_msg *msg) { - struct adb_iopmsg *amsg = (struct adb_iopmsg *) msg->message; + struct adb_iopmsg *amsg = (struct adb_iopmsg *)msg->message; struct adb_request *req; unsigned long flags; #ifdef DEBUG_ADB_IOP @@ -113,9 +114,9 @@ static void adb_iop_listen(struct iop_msg *msg) #ifdef DEBUG_ADB_IOP printk("adb_iop_listen %p: rcvd packet, %d bytes: %02X %02X", req, - (uint) amsg->count + 2, (uint) amsg->flags, (uint) amsg->cmd); + (uint)amsg->count + 2, (uint)amsg->flags, (uint)amsg->cmd); for (i = 0; i < amsg->count; i++) - printk(" %02X", (uint) amsg->data[i]); + printk(" %02X", (uint)amsg->data[i]); printk("\n"); #endif @@ -168,14 +169,15 @@ static void adb_iop_start(void) /* get the packet to send */ req = current_req; - if (!req) return; + if (!req) + return; local_irq_save(flags); #ifdef DEBUG_ADB_IOP printk("adb_iop_start %p: sending packet, %d bytes:", req, req->nbytes); - for (i = 0 ; i < req->nbytes ; i++) - printk(" %02X", (uint) req->data[i]); + for (i = 0; i < req->nbytes; i++) + printk(" %02X", (uint)req->data[i]); printk("\n"); #endif @@ -196,19 +198,20 @@ static void adb_iop_start(void) /* Now send it. The IOP manager will call adb_iop_complete */ /* when the packet has been sent. */ - iop_send_message(ADB_IOP, ADB_CHAN, req, - sizeof(amsg), (__u8 *) &amsg, adb_iop_complete); + iop_send_message(ADB_IOP, ADB_CHAN, req, sizeof(amsg), (__u8 *)&amsg, + adb_iop_complete); } int adb_iop_probe(void) { - if (!iop_ism_present) return -ENODEV; + if (!iop_ism_present) + return -ENODEV; return 0; } int adb_iop_init(void) { - printk("adb: IOP ISM driver v0.4 for Unified ADB.\n"); + pr_info("adb: IOP ISM driver v0.4 for Unified ADB\n"); iop_listen(ADB_IOP, ADB_CHAN, adb_iop_listen, "ADB"); return 0; } @@ -218,10 +221,12 @@ int adb_iop_send_request(struct adb_request *req, int sync) int err; err = adb_iop_write(req); - if (err) return err; + if (err) + return err; if (sync) { - while (!req->complete) adb_iop_poll(); + while (!req->complete) + adb_iop_poll(); } return 0; } @@ -251,7 +256,9 @@ static int adb_iop_write(struct adb_request *req) } local_irq_restore(flags); - if (adb_iop_state == idle) adb_iop_start(); + + if (adb_iop_state == idle) + adb_iop_start(); return 0; } @@ -263,7 +270,8 @@ int adb_iop_autopoll(int devs) void adb_iop_poll(void) { - if (adb_iop_state == idle) adb_iop_start(); + if (adb_iop_state == idle) + adb_iop_start(); iop_ism_irq_poll(ADB_IOP); } diff --git a/drivers/macintosh/adb.c b/drivers/macintosh/adb.c index 76e98f0f7a3e..e49d1f287a17 100644 --- a/drivers/macintosh/adb.c +++ b/drivers/macintosh/adb.c @@ -203,15 +203,15 @@ static int adb_scan_bus(void) } /* Now fill in the handler_id field of the adb_handler entries. */ - pr_debug("adb devices:\n"); for (i = 1; i < 16; i++) { if (adb_handler[i].original_address == 0) continue; adb_request(&req, NULL, ADBREQ_SYNC | ADBREQ_REPLY, 1, (i << 4) | 0xf); adb_handler[i].handler_id = req.reply[2]; - pr_debug(" [%d]: %d %x\n", i, adb_handler[i].original_address, - adb_handler[i].handler_id); + printk(KERN_DEBUG "adb device [%d]: %d 0x%X\n", i, + adb_handler[i].original_address, + adb_handler[i].handler_id); devmask |= 1 << i; } return devmask; @@ -579,6 +579,8 @@ adb_try_handler_change(int address, int new_id) mutex_lock(&adb_handler_mutex); ret = try_handler_change(address, new_id); mutex_unlock(&adb_handler_mutex); + if (ret) + pr_debug("adb handler change: [%d] 0x%X\n", address, new_id); return ret; } EXPORT_SYMBOL(adb_try_handler_change); diff --git a/drivers/macintosh/adbhid.c b/drivers/macintosh/adbhid.c index a261892c03b3..75482eeab2c4 100644 --- a/drivers/macintosh/adbhid.c +++ b/drivers/macintosh/adbhid.c @@ -757,6 +757,7 @@ adbhid_input_register(int id, int default_id, int original_handler_id, struct input_dev *input_dev; int err; int i; + char *keyboard_type; if (adbhid[id]) { pr_err("Trying to reregister ADB HID on ID %d\n", id); @@ -798,24 +799,23 @@ adbhid_input_register(int id, int default_id, int original_handler_id, memcpy(hid->keycode, adb_to_linux_keycodes, sizeof(adb_to_linux_keycodes)); - pr_info("Detected ADB keyboard, type "); switch (original_handler_id) { default: - pr_cont("<unknown>.\n"); + keyboard_type = "<unknown>"; input_dev->id.version = ADB_KEYBOARD_UNKNOWN; break; case 0x01: case 0x02: case 0x03: case 0x06: case 0x08: case 0x0C: case 0x10: case 0x18: case 0x1B: case 0x1C: case 0xC0: case 0xC3: case 0xC6: - pr_cont("ANSI.\n"); + keyboard_type = "ANSI"; input_dev->id.version = ADB_KEYBOARD_ANSI; break; case 0x04: case 0x05: case 0x07: case 0x09: case 0x0D: case 0x11: case 0x14: case 0x19: case 0x1D: case 0xC1: case 0xC4: case 0xC7: - pr_cont("ISO, swapping keys.\n"); + keyboard_type = "ISO, swapping keys"; input_dev->id.version = ADB_KEYBOARD_ISO; i = hid->keycode[10]; hid->keycode[10] = hid->keycode[50]; @@ -824,10 +824,11 @@ adbhid_input_register(int id, int default_id, int original_handler_id, case 0x12: case 0x15: case 0x16: case 0x17: case 0x1A: case 0x1E: case 0xC2: case 0xC5: case 0xC8: case 0xC9: - pr_cont("JIS.\n"); + keyboard_type = "JIS"; input_dev->id.version = ADB_KEYBOARD_JIS; break; } + pr_info("Detected ADB keyboard, type %s.\n", keyboard_type); for (i = 0; i < 128; i++) if (hid->keycode[i]) @@ -972,16 +973,13 @@ adbhid_probe(void) ->get it to send separate codes for left and right shift, control, option keys */ #if 0 /* handler 5 doesn't send separate codes for R modifiers */ - if (adb_try_handler_change(id, 5)) - printk("ADB keyboard at %d, handler set to 5\n", id); - else + if (!adb_try_handler_change(id, 5)) #endif - if (adb_try_handler_change(id, 3)) - printk("ADB keyboard at %d, handler set to 3\n", id); - else - printk("ADB keyboard at %d, handler 1\n", id); + adb_try_handler_change(id, 3); adb_get_infos(id, &default_id, &cur_handler_id); + printk(KERN_DEBUG "ADB keyboard at %d has handler 0x%X\n", + id, cur_handler_id); reg |= adbhid_input_reregister(id, default_id, org_handler_id, cur_handler_id, 0); } @@ -999,48 +997,44 @@ adbhid_probe(void) for (i = 0; i < mouse_ids.nids; i++) { int id = mouse_ids.id[i]; int mouse_kind; + char *desc = "standard"; adb_get_infos(id, &default_id, &org_handler_id); if (adb_try_handler_change(id, 4)) { - printk("ADB mouse at %d, handler set to 4", id); mouse_kind = ADBMOUSE_EXTENDED; } else if (adb_try_handler_change(id, 0x2F)) { - printk("ADB mouse at %d, handler set to 0x2F", id); mouse_kind = ADBMOUSE_MICROSPEED; } else if (adb_try_handler_change(id, 0x42)) { - printk("ADB mouse at %d, handler set to 0x42", id); mouse_kind = ADBMOUSE_TRACKBALLPRO; } else if (adb_try_handler_change(id, 0x66)) { - printk("ADB mouse at %d, handler set to 0x66", id); mouse_kind = ADBMOUSE_MICROSPEED; } else if (adb_try_handler_change(id, 0x5F)) { - printk("ADB mouse at %d, handler set to 0x5F", id); mouse_kind = ADBMOUSE_MICROSPEED; } else if (adb_try_handler_change(id, 3)) { - printk("ADB mouse at %d, handler set to 3", id); mouse_kind = ADBMOUSE_MS_A3; } else if (adb_try_handler_change(id, 2)) { - printk("ADB mouse at %d, handler set to 2", id); mouse_kind = ADBMOUSE_STANDARD_200; } else { - printk("ADB mouse at %d, handler 1", id); mouse_kind = ADBMOUSE_STANDARD_100; } if ((mouse_kind == ADBMOUSE_TRACKBALLPRO) || (mouse_kind == ADBMOUSE_MICROSPEED)) { + desc = "Microspeed/MacPoint or compatible"; init_microspeed(id); } else if (mouse_kind == ADBMOUSE_MS_A3) { + desc = "Mouse Systems A3 Mouse or compatible"; init_ms_a3(id); } else if (mouse_kind == ADBMOUSE_EXTENDED) { + desc = "extended"; /* * Register 1 is usually used for device * identification. Here, we try to identify @@ -1054,32 +1048,36 @@ adbhid_probe(void) (req.reply[1] == 0x9a) && ((req.reply[2] == 0x21) || (req.reply[2] == 0x20))) { mouse_kind = ADBMOUSE_TRACKBALL; + desc = "trackman/mouseman"; init_trackball(id); } else if ((req.reply_len >= 4) && (req.reply[1] == 0x74) && (req.reply[2] == 0x70) && (req.reply[3] == 0x61) && (req.reply[4] == 0x64)) { mouse_kind = ADBMOUSE_TRACKPAD; + desc = "trackpad"; init_trackpad(id); } else if ((req.reply_len >= 4) && (req.reply[1] == 0x4b) && (req.reply[2] == 0x4d) && (req.reply[3] == 0x4c) && (req.reply[4] == 0x31)) { mouse_kind = ADBMOUSE_TURBOMOUSE5; + desc = "TurboMouse 5"; init_turbomouse(id); } else if ((req.reply_len == 9) && (req.reply[1] == 0x4b) && (req.reply[2] == 0x4f) && (req.reply[3] == 0x49) && (req.reply[4] == 0x54)) { if (adb_try_handler_change(id, 0x42)) { - pr_cont("\nADB MacAlly 2-button mouse at %d, handler set to 0x42", id); mouse_kind = ADBMOUSE_MACALLY2; + desc = "MacAlly 2-button"; } } } - pr_cont("\n"); adb_get_infos(id, &default_id, &cur_handler_id); + printk(KERN_DEBUG "ADB mouse (%s) at %d has handler 0x%X\n", + desc, id, cur_handler_id); reg |= adbhid_input_reregister(id, default_id, org_handler_id, cur_handler_id, mouse_kind); } @@ -1092,12 +1090,10 @@ init_trackpad(int id) struct adb_request req; unsigned char r1_buffer[8]; - pr_cont(" (trackpad)"); - adb_request(&req, NULL, ADBREQ_SYNC | ADBREQ_REPLY, 1, ADB_READREG(id,1)); if (req.reply_len < 8) - pr_cont("bad length for reg. 1\n"); + pr_err("%s: bad length for reg. 1\n", __func__); else { memcpy(r1_buffer, &req.reply[1], 8); @@ -1145,8 +1141,6 @@ init_trackball(int id) { struct adb_request req; - pr_cont(" (trackman/mouseman)"); - adb_request(&req, NULL, ADBREQ_SYNC, 3, ADB_WRITEREG(id,1), 00,0x81); @@ -1177,8 +1171,6 @@ init_turbomouse(int id) { struct adb_request req; - pr_cont(" (TurboMouse 5)"); - adb_request(&req, NULL, ADBREQ_SYNC, 1, ADB_FLUSH(id)); adb_request(&req, NULL, ADBREQ_SYNC, 1, ADB_FLUSH(3)); @@ -1213,8 +1205,6 @@ init_microspeed(int id) { struct adb_request req; - pr_cont(" (Microspeed/MacPoint or compatible)"); - adb_request(&req, NULL, ADBREQ_SYNC, 1, ADB_FLUSH(id)); /* This will initialize mice using the Microspeed, MacPoint and @@ -1253,7 +1243,6 @@ init_ms_a3(int id) { struct adb_request req; - pr_cont(" (Mouse Systems A3 Mouse, or compatible)"); adb_request(&req, NULL, ADBREQ_SYNC, 3, ADB_WRITEREG(id, 0x2), 0x00, diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c index 07074820a167..17d3bc917562 100644 --- a/drivers/macintosh/macio_asic.c +++ b/drivers/macintosh/macio_asic.c @@ -360,9 +360,10 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip, struct macio_dev *in_bay, struct resource *parent_res) { + char name[MAX_NODE_NAME_SIZE + 1]; struct macio_dev *dev; const u32 *reg; - + if (np == NULL) return NULL; @@ -402,6 +403,7 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip, #endif /* MacIO itself has a different reg, we use it's PCI base */ + snprintf(name, sizeof(name), "%pOFn", np); if (np == chip->of_node) { dev_set_name(&dev->ofdev.dev, "%1d.%08x:%.*s", chip->lbus.index, @@ -410,12 +412,12 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip, #else 0, /* NuBus may want to do something better here */ #endif - MAX_NODE_NAME_SIZE, np->name); + MAX_NODE_NAME_SIZE, name); } else { reg = of_get_property(np, "reg", NULL); dev_set_name(&dev->ofdev.dev, "%1d.%08x:%.*s", chip->lbus.index, - reg ? *reg : 0, MAX_NODE_NAME_SIZE, np->name); + reg ? *reg : 0, MAX_NODE_NAME_SIZE, name); } /* Setup interrupts & resources */ diff --git a/drivers/macintosh/macio_sysfs.c b/drivers/macintosh/macio_sysfs.c index ca4fcffe454b..d2451e58acb9 100644 --- a/drivers/macintosh/macio_sysfs.c +++ b/drivers/macintosh/macio_sysfs.c @@ -58,7 +58,13 @@ static ssize_t devspec_show(struct device *dev, static DEVICE_ATTR_RO(modalias); static DEVICE_ATTR_RO(devspec); -macio_config_of_attr (name, "%s\n"); +static ssize_t name_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%pOFn\n", dev->of_node); +} +static DEVICE_ATTR_RO(name); + macio_config_of_attr (type, "%s\n"); static struct attribute *macio_dev_attrs[] = { diff --git a/drivers/macintosh/via-cuda.c b/drivers/macintosh/via-cuda.c index 98dd702eb867..bbec6ac0a966 100644 --- a/drivers/macintosh/via-cuda.c +++ b/drivers/macintosh/via-cuda.c @@ -766,3 +766,38 @@ cuda_input(unsigned char *buf, int nb) buf, nb, false); } } + +/* Offset between Unix time (1970-based) and Mac time (1904-based) */ +#define RTC_OFFSET 2082844800 + +time64_t cuda_get_time(void) +{ + struct adb_request req; + u32 now; + + if (cuda_request(&req, NULL, 2, CUDA_PACKET, CUDA_GET_TIME) < 0) + return 0; + while (!req.complete) + cuda_poll(); + if (req.reply_len != 7) + pr_err("%s: got %d byte reply\n", __func__, req.reply_len); + now = (req.reply[3] << 24) + (req.reply[4] << 16) + + (req.reply[5] << 8) + req.reply[6]; + return (time64_t)now - RTC_OFFSET; +} + +int cuda_set_rtc_time(struct rtc_time *tm) +{ + u32 now; + struct adb_request req; + + now = lower_32_bits(rtc_tm_to_time64(tm) + RTC_OFFSET); + if (cuda_request(&req, NULL, 6, CUDA_PACKET, CUDA_SET_TIME, + now >> 24, now >> 16, now >> 8, now) < 0) + return -ENXIO; + while (!req.complete) + cuda_poll(); + if ((req.reply_len != 3) && (req.reply_len != 7)) + pr_err("%s: got %d byte reply\n", __func__, req.reply_len); + return 0; +} diff --git a/drivers/macintosh/via-macii.c b/drivers/macintosh/via-macii.c index cf6f7d52d6be..ac824d7b2dcf 100644 --- a/drivers/macintosh/via-macii.c +++ b/drivers/macintosh/via-macii.c @@ -12,7 +12,7 @@ * * 1999-08-02 (jmt) - Initial rewrite for Unified ADB. * 2000-03-29 Tony Mantler <tonym@mac.linux-m68k.org> - * - Big overhaul, should actually work now. + * - Big overhaul, should actually work now. * 2006-12-31 Finn Thain - Another overhaul. * * Suggested reading: @@ -23,7 +23,7 @@ * Apple's "ADB Analyzer" bus sniffer is invaluable: * ftp://ftp.apple.com/developer/Tool_Chest/Devices_-_Hardware/Apple_Desktop_Bus/ */ - + #include <stdarg.h> #include <linux/types.h> #include <linux/errno.h> @@ -77,7 +77,7 @@ static volatile unsigned char *via; #define ST_ODD 0x20 /* ADB state: odd data byte */ #define ST_IDLE 0x30 /* ADB state: idle, nothing to send */ -static int macii_init_via(void); +static int macii_init_via(void); static void macii_start(void); static irqreturn_t macii_interrupt(int irq, void *arg); static void macii_queue_poll(void); @@ -120,31 +120,15 @@ static int srq_asserted; /* have to poll for the device that asserted it */ static int command_byte; /* the most recent command byte transmitted */ static int autopoll_devs; /* bits set are device addresses to be polled */ -/* Sanity check for request queue. Doesn't check for cycles. */ -static int request_is_queued(struct adb_request *req) { - struct adb_request *cur; - unsigned long flags; - local_irq_save(flags); - cur = current_req; - while (cur) { - if (cur == req) { - local_irq_restore(flags); - return 1; - } - cur = cur->next; - } - local_irq_restore(flags); - return 0; -} - /* Check for MacII style ADB */ static int macii_probe(void) { - if (macintosh_config->adb_type != MAC_ADB_II) return -ENODEV; + if (macintosh_config->adb_type != MAC_ADB_II) + return -ENODEV; via = via1; - printk("adb: Mac II ADB Driver v1.0 for Unified ADB\n"); + pr_info("adb: Mac II ADB Driver v1.0 for Unified ADB\n"); return 0; } @@ -153,15 +137,17 @@ int macii_init(void) { unsigned long flags; int err; - + local_irq_save(flags); - + err = macii_init_via(); - if (err) goto out; + if (err) + goto out; err = request_irq(IRQ_MAC_ADB, macii_interrupt, 0, "ADB", macii_interrupt); - if (err) goto out; + if (err) + goto out; macii_state = idle; out: @@ -169,7 +155,7 @@ out: return err; } -/* initialize the hardware */ +/* initialize the hardware */ static int macii_init_via(void) { unsigned char x; @@ -179,7 +165,7 @@ static int macii_init_via(void) /* Set up state: idle */ via[B] |= ST_IDLE; - last_status = via[B] & (ST_MASK|CTLR_IRQ); + last_status = via[B] & (ST_MASK | CTLR_IRQ); /* Shift register on input */ via[ACR] = (via[ACR] & ~SR_CTRL) | SR_EXT; @@ -205,7 +191,8 @@ static void macii_queue_poll(void) int next_device; static struct adb_request req; - if (!autopoll_devs) return; + if (!autopoll_devs) + return; device_mask = (1 << (((command_byte & 0xF0) >> 4) + 1)) - 1; if (autopoll_devs & ~device_mask) @@ -213,10 +200,7 @@ static void macii_queue_poll(void) else next_device = ffs(autopoll_devs) - 1; - BUG_ON(request_is_queued(&req)); - - adb_request(&req, NULL, ADBREQ_NOSEND, 1, - ADB_READREG(next_device, 0)); + adb_request(&req, NULL, ADBREQ_NOSEND, 1, ADB_READREG(next_device, 0)); req.sent = 0; req.complete = 0; @@ -235,45 +219,47 @@ static void macii_queue_poll(void) static int macii_send_request(struct adb_request *req, int sync) { int err; - unsigned long flags; - BUG_ON(request_is_queued(req)); - - local_irq_save(flags); err = macii_write(req); - local_irq_restore(flags); + if (err) + return err; - if (!err && sync) { - while (!req->complete) { + if (sync) + while (!req->complete) macii_poll(); - } - BUG_ON(request_is_queued(req)); - } - return err; + return 0; } /* Send an ADB request (append to request queue) */ static int macii_write(struct adb_request *req) { + unsigned long flags; + if (req->nbytes < 2 || req->data[0] != ADB_PACKET || req->nbytes > 15) { req->complete = 1; return -EINVAL; } - + req->next = NULL; req->sent = 0; req->complete = 0; req->reply_len = 0; + local_irq_save(flags); + if (current_req != NULL) { last_req->next = req; last_req = req; } else { current_req = req; last_req = req; - if (macii_state == idle) macii_start(); + if (macii_state == idle) + macii_start(); } + + local_irq_restore(flags); + return 0; } @@ -287,7 +273,8 @@ static int macii_autopoll(int devs) /* bit 1 == device 1, and so on. */ autopoll_devs = devs & 0xFFFE; - if (!autopoll_devs) return 0; + if (!autopoll_devs) + return 0; local_irq_save(flags); @@ -304,7 +291,8 @@ static int macii_autopoll(int devs) return err; } -static inline int need_autopoll(void) { +static inline int need_autopoll(void) +{ /* Was the last command Talk Reg 0 * and is the target on the autopoll list? */ @@ -317,21 +305,17 @@ static inline int need_autopoll(void) { /* Prod the chip without interrupts */ static void macii_poll(void) { - disable_irq(IRQ_MAC_ADB); macii_interrupt(0, NULL); - enable_irq(IRQ_MAC_ADB); } /* Reset the bus */ static int macii_reset_bus(void) { static struct adb_request req; - - if (request_is_queued(&req)) - return 0; /* Command = 0, Address = ignored */ - adb_request(&req, NULL, 0, 1, ADB_BUSRESET); + adb_request(&req, NULL, ADBREQ_NOSEND, 1, ADB_BUSRESET); + macii_send_request(&req, 1); /* Don't want any more requests during the Global Reset low time. */ udelay(3000); @@ -346,10 +330,6 @@ static void macii_start(void) req = current_req; - BUG_ON(req == NULL); - - BUG_ON(macii_state != idle); - /* Now send it. Be careful though, that first byte of the request * is actually ADB_PACKET; the real data begins at index 1! * And req->nbytes is the number of bytes of real data plus one. @@ -375,7 +355,7 @@ static void macii_start(void) * to be activity on the ADB bus. The chip will poll to achieve this. * * The basic ADB state machine was left unchanged from the original MacII code - * by Alan Cox, which was based on the CUDA driver for PowerMac. + * by Alan Cox, which was based on the CUDA driver for PowerMac. * The syntax of the ADB status lines is totally different on MacII, * though. MacII uses the states Command -> Even -> Odd -> Even ->...-> Idle * for sending and Idle -> Even -> Odd -> Even ->...-> Idle for receiving. @@ -387,164 +367,166 @@ static void macii_start(void) static irqreturn_t macii_interrupt(int irq, void *arg) { int x; - static int entered; struct adb_request *req; + unsigned long flags; + + local_irq_save(flags); if (!arg) { /* Clear the SR IRQ flag when polling. */ if (via[IFR] & SR_INT) via[IFR] = SR_INT; - else + else { + local_irq_restore(flags); return IRQ_NONE; + } } - BUG_ON(entered++); - last_status = status; - status = via[B] & (ST_MASK|CTLR_IRQ); + status = via[B] & (ST_MASK | CTLR_IRQ); switch (macii_state) { - case idle: - if (reading_reply) { - reply_ptr = current_req->reply; - } else { - BUG_ON(current_req != NULL); - reply_ptr = reply_buf; - } + case idle: + if (reading_reply) { + reply_ptr = current_req->reply; + } else { + WARN_ON(current_req); + reply_ptr = reply_buf; + } - x = via[SR]; + x = via[SR]; - if ((status & CTLR_IRQ) && (x == 0xFF)) { - /* Bus timeout without SRQ sequence: - * data is "FF" while CTLR_IRQ is "H" - */ - reply_len = 0; - srq_asserted = 0; - macii_state = read_done; - } else { - macii_state = reading; - *reply_ptr = x; - reply_len = 1; - } + if ((status & CTLR_IRQ) && (x == 0xFF)) { + /* Bus timeout without SRQ sequence: + * data is "FF" while CTLR_IRQ is "H" + */ + reply_len = 0; + srq_asserted = 0; + macii_state = read_done; + } else { + macii_state = reading; + *reply_ptr = x; + reply_len = 1; + } - /* set ADB state = even for first data byte */ - via[B] = (via[B] & ~ST_MASK) | ST_EVEN; - break; + /* set ADB state = even for first data byte */ + via[B] = (via[B] & ~ST_MASK) | ST_EVEN; + break; - case sending: - req = current_req; - if (data_index >= req->nbytes) { - req->sent = 1; - macii_state = idle; - - if (req->reply_expected) { - reading_reply = 1; - } else { - req->complete = 1; - current_req = req->next; - if (req->done) (*req->done)(req); - - if (current_req) - macii_start(); - else - if (need_autopoll()) - macii_autopoll(autopoll_devs); - } + case sending: + req = current_req; + if (data_index >= req->nbytes) { + req->sent = 1; + macii_state = idle; - if (macii_state == idle) { - /* reset to shift in */ - via[ACR] &= ~SR_OUT; - x = via[SR]; - /* set ADB state idle - might get SRQ */ - via[B] = (via[B] & ~ST_MASK) | ST_IDLE; - } + if (req->reply_expected) { + reading_reply = 1; } else { - via[SR] = req->data[data_index++]; - - if ( (via[B] & ST_MASK) == ST_CMD ) { - /* just sent the command byte, set to EVEN */ - via[B] = (via[B] & ~ST_MASK) | ST_EVEN; - } else { - /* invert state bits, toggle ODD/EVEN */ - via[B] ^= ST_MASK; - } - } - break; - - case reading: - x = via[SR]; - BUG_ON((status & ST_MASK) == ST_CMD || - (status & ST_MASK) == ST_IDLE); - - /* Bus timeout with SRQ sequence: - * data is "XX FF" while CTLR_IRQ is "L L" - * End of packet without SRQ sequence: - * data is "XX...YY 00" while CTLR_IRQ is "L...H L" - * End of packet SRQ sequence: - * data is "XX...YY 00" while CTLR_IRQ is "L...L L" - * (where XX is the first response byte and - * YY is the last byte of valid response data.) - */ + req->complete = 1; + current_req = req->next; + if (req->done) + (*req->done)(req); - srq_asserted = 0; - if (!(status & CTLR_IRQ)) { - if (x == 0xFF) { - if (!(last_status & CTLR_IRQ)) { - macii_state = read_done; - reply_len = 0; - srq_asserted = 1; - } - } else if (x == 0x00) { - macii_state = read_done; - if (!(last_status & CTLR_IRQ)) - srq_asserted = 1; - } + if (current_req) + macii_start(); + else if (need_autopoll()) + macii_autopoll(autopoll_devs); } - if (macii_state == reading) { - BUG_ON(reply_len > 15); - reply_ptr++; - *reply_ptr = x; - reply_len++; + if (macii_state == idle) { + /* reset to shift in */ + via[ACR] &= ~SR_OUT; + x = via[SR]; + /* set ADB state idle - might get SRQ */ + via[B] = (via[B] & ~ST_MASK) | ST_IDLE; } + } else { + via[SR] = req->data[data_index++]; - /* invert state bits, toggle ODD/EVEN */ - via[B] ^= ST_MASK; - break; + if ((via[B] & ST_MASK) == ST_CMD) { + /* just sent the command byte, set to EVEN */ + via[B] = (via[B] & ~ST_MASK) | ST_EVEN; + } else { + /* invert state bits, toggle ODD/EVEN */ + via[B] ^= ST_MASK; + } + } + break; - case read_done: - x = via[SR]; + case reading: + x = via[SR]; + WARN_ON((status & ST_MASK) == ST_CMD || + (status & ST_MASK) == ST_IDLE); + + /* Bus timeout with SRQ sequence: + * data is "XX FF" while CTLR_IRQ is "L L" + * End of packet without SRQ sequence: + * data is "XX...YY 00" while CTLR_IRQ is "L...H L" + * End of packet SRQ sequence: + * data is "XX...YY 00" while CTLR_IRQ is "L...L L" + * (where XX is the first response byte and + * YY is the last byte of valid response data.) + */ - if (reading_reply) { - reading_reply = 0; - req = current_req; - req->reply_len = reply_len; - req->complete = 1; - current_req = req->next; - if (req->done) (*req->done)(req); - } else if (reply_len && autopoll_devs) - adb_input(reply_buf, reply_len, 0); + srq_asserted = 0; + if (!(status & CTLR_IRQ)) { + if (x == 0xFF) { + if (!(last_status & CTLR_IRQ)) { + macii_state = read_done; + reply_len = 0; + srq_asserted = 1; + } + } else if (x == 0x00) { + macii_state = read_done; + if (!(last_status & CTLR_IRQ)) + srq_asserted = 1; + } + } - macii_state = idle; + if (macii_state == reading && + reply_len < ARRAY_SIZE(reply_buf)) { + reply_ptr++; + *reply_ptr = x; + reply_len++; + } - /* SRQ seen before, initiate poll now */ - if (srq_asserted) - macii_queue_poll(); + /* invert state bits, toggle ODD/EVEN */ + via[B] ^= ST_MASK; + break; - if (current_req) - macii_start(); - else - if (need_autopoll()) - macii_autopoll(autopoll_devs); + case read_done: + x = via[SR]; - if (macii_state == idle) - via[B] = (via[B] & ~ST_MASK) | ST_IDLE; - break; + if (reading_reply) { + reading_reply = 0; + req = current_req; + req->reply_len = reply_len; + req->complete = 1; + current_req = req->next; + if (req->done) + (*req->done)(req); + } else if (reply_len && autopoll_devs) + adb_input(reply_buf, reply_len, 0); + + macii_state = idle; + + /* SRQ seen before, initiate poll now */ + if (srq_asserted) + macii_queue_poll(); + + if (current_req) + macii_start(); + else if (need_autopoll()) + macii_autopoll(autopoll_devs); + + if (macii_state == idle) + via[B] = (via[B] & ~ST_MASK) | ST_IDLE; + break; - default: + default: break; } - entered--; + local_irq_restore(flags); return IRQ_HANDLED; } diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c index d72c450aebe5..60f57e2abf21 100644 --- a/drivers/macintosh/via-pmu.c +++ b/drivers/macintosh/via-pmu.c @@ -1737,6 +1737,39 @@ pmu_enable_irled(int on) pmu_wait_complete(&req); } +/* Offset between Unix time (1970-based) and Mac time (1904-based) */ +#define RTC_OFFSET 2082844800 + +time64_t pmu_get_time(void) +{ + struct adb_request req; + u32 now; + + if (pmu_request(&req, NULL, 1, PMU_READ_RTC) < 0) + return 0; + pmu_wait_complete(&req); + if (req.reply_len != 4) + pr_err("%s: got %d byte reply\n", __func__, req.reply_len); + now = (req.reply[0] << 24) + (req.reply[1] << 16) + + (req.reply[2] << 8) + req.reply[3]; + return (time64_t)now - RTC_OFFSET; +} + +int pmu_set_rtc_time(struct rtc_time *tm) +{ + u32 now; + struct adb_request req; + + now = lower_32_bits(rtc_tm_to_time64(tm) + RTC_OFFSET); + if (pmu_request(&req, NULL, 5, PMU_SET_RTC, + now >> 24, now >> 16, now >> 8, now) < 0) + return -ENXIO; + pmu_wait_complete(&req); + if (req.reply_len != 0) + pr_err("%s: got %d byte reply\n", __func__, req.reply_len); + return 0; +} + void pmu_restart(void) { diff --git a/drivers/macintosh/windfarm_smu_controls.c b/drivers/macintosh/windfarm_smu_controls.c index d174c7437337..86d65462a61c 100644 --- a/drivers/macintosh/windfarm_smu_controls.c +++ b/drivers/macintosh/windfarm_smu_controls.c @@ -277,7 +277,7 @@ static int __init smu_controls_init(void) fct = smu_fan_create(fan, 0); if (fct == NULL) { printk(KERN_WARNING "windfarm: Failed to create SMU " - "RPM fan %s\n", fan->name); + "RPM fan %pOFn\n", fan); continue; } list_add(&fct->link, &smu_fans); @@ -296,7 +296,7 @@ static int __init smu_controls_init(void) fct = smu_fan_create(fan, 1); if (fct == NULL) { printk(KERN_WARNING "windfarm: Failed to create SMU " - "PWM fan %s\n", fan->name); + "PWM fan %pOFn\n", fan); continue; } list_add(&fct->link, &smu_fans); diff --git a/drivers/macintosh/windfarm_smu_sat.c b/drivers/macintosh/windfarm_smu_sat.c index da7f4fc1a51d..a0f61eb853c5 100644 --- a/drivers/macintosh/windfarm_smu_sat.c +++ b/drivers/macintosh/windfarm_smu_sat.c @@ -22,14 +22,6 @@ #define VERSION "1.0" -#define DEBUG - -#ifdef DEBUG -#define DBG(args...) printk(args) -#else -#define DBG(args...) do { } while(0) -#endif - /* If the cache is older than 800ms we'll refetch it */ #define MAX_AGE msecs_to_jiffies(800) @@ -106,13 +98,10 @@ struct smu_sdbp_header *smu_sat_get_sdb_partition(unsigned int sat_id, int id, buf[i+2] = data[3]; buf[i+3] = data[2]; } -#ifdef DEBUG - DBG(KERN_DEBUG "sat %d partition %x:", sat_id, id); - for (i = 0; i < len; ++i) - DBG(" %x", buf[i]); - DBG("\n"); -#endif + printk(KERN_DEBUG "sat %d partition %x:", sat_id, id); + print_hex_dump(KERN_DEBUG, " ", DUMP_PREFIX_OFFSET, + 16, 1, buf, len, false); if (size) *size = len; return (struct smu_sdbp_header *) buf; @@ -132,13 +121,13 @@ static int wf_sat_read_cache(struct wf_sat *sat) if (err < 0) return err; sat->last_read = jiffies; + #ifdef LOTSA_DEBUG { int i; - DBG(KERN_DEBUG "wf_sat_get: data is"); - for (i = 0; i < 16; ++i) - DBG(" %.2x", sat->cache[i]); - DBG("\n"); + printk(KERN_DEBUG "wf_sat_get: data is"); + print_hex_dump(KERN_DEBUG, " ", DUMP_PREFIX_OFFSET, + 16, 1, sat->cache, 16, false); } #endif return 0; diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 8b8c123cae66..3db222509e44 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -215,17 +215,6 @@ config BLK_DEV_DM If unsure, say N. -config DM_MQ_DEFAULT - bool "request-based DM: use blk-mq I/O path by default" - depends on BLK_DEV_DM - ---help--- - This option enables the blk-mq based I/O path for request-based - DM devices by default. With the option the dm_mod.use_blk_mq - module/boot option defaults to Y, without it to N, but it can - still be overriden either way. - - If unsure say N. - config DM_DEBUG bool "Device mapper debugging support" depends on BLK_DEV_DM diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c index 1b5b9ad9e492..b61aac00ff40 100644 --- a/drivers/md/dm-cache-policy-smq.c +++ b/drivers/md/dm-cache-policy-smq.c @@ -1200,7 +1200,7 @@ static void queue_demotion(struct smq_policy *mq) struct policy_work work; struct entry *e; - if (unlikely(WARN_ON_ONCE(!mq->migrations_allowed))) + if (WARN_ON_ONCE(!mq->migrations_allowed)) return; e = q_peek(&mq->clean, mq->clean.nr_levels / 2, true); diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 7d480c930eaf..224d44503a06 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -112,18 +112,8 @@ struct mapped_device { struct dm_stats stats; - struct kthread_worker kworker; - struct task_struct *kworker_task; - - /* for request-based merge heuristic in dm_request_fn() */ - unsigned seq_rq_merge_deadline_usecs; - int last_rq_rw; - sector_t last_rq_pos; - ktime_t last_rq_start_time; - /* for blk-mq request-based DM support */ struct blk_mq_tag_set *tag_set; - bool use_blk_mq:1; bool init_tio_pdu:1; struct srcu_struct io_barrier; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 0481223b1deb..b8eec515a003 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -2661,6 +2661,7 @@ static int crypt_ctr_optional(struct dm_target *ti, unsigned int argc, char **ar static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) { struct crypt_config *cc; + const char *devname = dm_table_device_name(ti->table); int key_size; unsigned int align_mask; unsigned long long tmpll; @@ -2806,18 +2807,22 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) } ret = -ENOMEM; - cc->io_queue = alloc_workqueue("kcryptd_io", WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 1); + cc->io_queue = alloc_workqueue("kcryptd_io/%s", + WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, + 1, devname); if (!cc->io_queue) { ti->error = "Couldn't create kcryptd io queue"; goto bad; } if (test_bit(DM_CRYPT_SAME_CPU, &cc->flags)) - cc->crypt_queue = alloc_workqueue("kcryptd", WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, 1); + cc->crypt_queue = alloc_workqueue("kcryptd/%s", + WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM, + 1, devname); else - cc->crypt_queue = alloc_workqueue("kcryptd", + cc->crypt_queue = alloc_workqueue("kcryptd/%s", WQ_HIGHPRI | WQ_CPU_INTENSIVE | WQ_MEM_RECLAIM | WQ_UNBOUND, - num_online_cpus()); + num_online_cpus(), devname); if (!cc->crypt_queue) { ti->error = "Couldn't create kcryptd queue"; goto bad; @@ -2826,7 +2831,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) spin_lock_init(&cc->write_thread_lock); cc->write_tree = RB_ROOT; - cc->write_thread = kthread_create(dmcrypt_write, cc, "dmcrypt_write"); + cc->write_thread = kthread_create(dmcrypt_write, cc, "dmcrypt_write/%s", devname); if (IS_ERR(cc->write_thread)) { ret = PTR_ERR(cc->write_thread); cc->write_thread = NULL; diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 32aabe27b37c..3cb97fa4c11d 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -315,10 +315,6 @@ static int flakey_map(struct dm_target *ti, struct bio *bio) if (bio_op(bio) == REQ_OP_ZONE_RESET) goto map_bio; - /* We need to remap reported zones, so remember the BIO iter */ - if (bio_op(bio) == REQ_OP_ZONE_REPORT) - goto map_bio; - /* Are we alive ? */ elapsed = (jiffies - fc->start_time) / HZ; if (elapsed % (fc->up_interval + fc->down_interval) >= fc->up_interval) { @@ -380,11 +376,6 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, if (bio_op(bio) == REQ_OP_ZONE_RESET) return DM_ENDIO_DONE; - if (bio_op(bio) == REQ_OP_ZONE_REPORT) { - dm_remap_zone_report(ti, bio, fc->start); - return DM_ENDIO_DONE; - } - if (!*error && pb->bio_submitted && (bio_data_dir(bio) == READ)) { if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) && all_corrupt_bio_flags_match(bio, fc)) { @@ -457,6 +448,26 @@ static int flakey_prepare_ioctl(struct dm_target *ti, struct block_device **bdev return 0; } +#ifdef CONFIG_BLK_DEV_ZONED +static int flakey_report_zones(struct dm_target *ti, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask) +{ + struct flakey_c *fc = ti->private; + int ret; + + /* Do report and remap it */ + ret = blkdev_report_zones(fc->dev->bdev, flakey_map_sector(ti, sector), + zones, nr_zones, gfp_mask); + if (ret != 0) + return ret; + + if (*nr_zones) + dm_remap_zone_report(ti, fc->start, zones, nr_zones); + return 0; +} +#endif + static int flakey_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data) { struct flakey_c *fc = ti->private; @@ -469,6 +480,7 @@ static struct target_type flakey_target = { .version = {1, 5, 0}, #ifdef CONFIG_BLK_DEV_ZONED .features = DM_TARGET_ZONED_HM, + .report_zones = flakey_report_zones, #endif .module = THIS_MODULE, .ctr = flakey_ctr, diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index b810ea77e6b1..f666778ad237 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1720,8 +1720,7 @@ static void free_params(struct dm_ioctl *param, size_t param_size, int param_fla } static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kernel, - int ioctl_flags, - struct dm_ioctl **param, int *param_flags) + int ioctl_flags, struct dm_ioctl **param, int *param_flags) { struct dm_ioctl *dmi; int secure_data; @@ -1762,18 +1761,13 @@ static int copy_params(struct dm_ioctl __user *user, struct dm_ioctl *param_kern *param_flags |= DM_PARAMS_MALLOC; - if (copy_from_user(dmi, user, param_kernel->data_size)) - goto bad; + /* Copy from param_kernel (which was already copied from user) */ + memcpy(dmi, param_kernel, minimum_data_size); -data_copied: - /* - * Abort if something changed the ioctl data while it was being copied. - */ - if (dmi->data_size != param_kernel->data_size) { - DMERR("rejecting ioctl: data size modified while processing parameters"); + if (copy_from_user(&dmi->data, (char __user *)user + minimum_data_size, + param_kernel->data_size - minimum_data_size)) goto bad; - } - +data_copied: /* Wipe the user buffer so we do not return it to userspace */ if (secure_data && clear_user(user, param_kernel->data_size)) goto bad; diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 2f7c44a006c4..8d7ddee6ac4d 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -102,19 +102,6 @@ static int linear_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_REMAPPED; } -#ifdef CONFIG_BLK_DEV_ZONED -static int linear_end_io(struct dm_target *ti, struct bio *bio, - blk_status_t *error) -{ - struct linear_c *lc = ti->private; - - if (!*error && bio_op(bio) == REQ_OP_ZONE_REPORT) - dm_remap_zone_report(ti, bio, lc->start); - - return DM_ENDIO_DONE; -} -#endif - static void linear_status(struct dm_target *ti, status_type_t type, unsigned status_flags, char *result, unsigned maxlen) { @@ -148,6 +135,26 @@ static int linear_prepare_ioctl(struct dm_target *ti, struct block_device **bdev return 0; } +#ifdef CONFIG_BLK_DEV_ZONED +static int linear_report_zones(struct dm_target *ti, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask) +{ + struct linear_c *lc = (struct linear_c *) ti->private; + int ret; + + /* Do report and remap it */ + ret = blkdev_report_zones(lc->dev->bdev, linear_map_sector(ti, sector), + zones, nr_zones, gfp_mask); + if (ret != 0) + return ret; + + if (*nr_zones) + dm_remap_zone_report(ti, lc->start, zones, nr_zones); + return 0; +} +#endif + static int linear_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data) { @@ -211,8 +218,8 @@ static struct target_type linear_target = { .name = "linear", .version = {1, 4, 0}, #ifdef CONFIG_BLK_DEV_ZONED - .end_io = linear_end_io, .features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_ZONED_HM, + .report_zones = linear_report_zones, #else .features = DM_TARGET_PASSES_INTEGRITY, #endif diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 419362c2d8ac..d6a66921daf4 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -203,14 +203,7 @@ static struct multipath *alloc_multipath(struct dm_target *ti) static int alloc_multipath_stage2(struct dm_target *ti, struct multipath *m) { if (m->queue_mode == DM_TYPE_NONE) { - /* - * Default to request-based. - */ - if (dm_use_blk_mq(dm_table_get_md(ti->table))) - m->queue_mode = DM_TYPE_MQ_REQUEST_BASED; - else - m->queue_mode = DM_TYPE_REQUEST_BASED; - + m->queue_mode = DM_TYPE_REQUEST_BASED; } else if (m->queue_mode == DM_TYPE_BIO_BASED) { INIT_WORK(&m->process_queued_bios, process_queued_bios); /* @@ -537,10 +530,7 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq, * get the queue busy feedback (via BLK_STS_RESOURCE), * otherwise I/O merging can suffer. */ - if (q->mq_ops) - return DM_MAPIO_REQUEUE; - else - return DM_MAPIO_DELAY_REQUEUE; + return DM_MAPIO_REQUEUE; } clone->bio = clone->biotail = NULL; clone->rq_disk = bdev->bd_disk; @@ -668,7 +658,7 @@ static int multipath_map_bio(struct dm_target *ti, struct bio *bio) static void process_queued_io_list(struct multipath *m) { - if (m->queue_mode == DM_TYPE_MQ_REQUEST_BASED) + if (m->queue_mode == DM_TYPE_REQUEST_BASED) dm_mq_kick_requeue_list(dm_table_get_md(m->ti->table)); else if (m->queue_mode == DM_TYPE_BIO_BASED) queue_work(kmultipathd, &m->process_queued_bios); @@ -1089,10 +1079,9 @@ static int parse_features(struct dm_arg_set *as, struct multipath *m) if (!strcasecmp(queue_mode_name, "bio")) m->queue_mode = DM_TYPE_BIO_BASED; - else if (!strcasecmp(queue_mode_name, "rq")) + else if (!strcasecmp(queue_mode_name, "rq") || + !strcasecmp(queue_mode_name, "mq")) m->queue_mode = DM_TYPE_REQUEST_BASED; - else if (!strcasecmp(queue_mode_name, "mq")) - m->queue_mode = DM_TYPE_MQ_REQUEST_BASED; else { ti->error = "Unknown 'queue_mode' requested"; r = -EINVAL; @@ -1726,9 +1715,6 @@ static void multipath_status(struct dm_target *ti, status_type_t type, case DM_TYPE_BIO_BASED: DMEMIT("queue_mode bio "); break; - case DM_TYPE_MQ_REQUEST_BASED: - DMEMIT("queue_mode mq "); - break; default: WARN_ON_ONCE(true); break; @@ -1972,7 +1958,7 @@ static int multipath_busy(struct dm_target *ti) /* no paths available, for blk-mq: rely on IO mapping to delay requeue */ if (!atomic_read(&m->nr_valid_paths) && test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) - return (m->queue_mode != DM_TYPE_MQ_REQUEST_BASED); + return (m->queue_mode != DM_TYPE_REQUEST_BASED); /* Guess which priority_group will be used at next mapping time */ pg = READ_ONCE(m->current_pg); diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index c44925e4e481..e1dd1622a290 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -2475,7 +2475,7 @@ static int super_validate(struct raid_set *rs, struct md_rdev *rdev) } /* Enable bitmap creation for RAID levels != 0 */ - mddev->bitmap_info.offset = rt_is_raid0(rs->raid_type) ? 0 : to_sector(4096); + mddev->bitmap_info.offset = (rt_is_raid0(rs->raid_type) || rs->journal_dev.dev) ? 0 : to_sector(4096); mddev->bitmap_info.default_offset = mddev->bitmap_info.offset; if (!test_and_clear_bit(FirstUse, &rdev->flags)) { diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 6e547b8dd298..7cd36e4d1310 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -23,19 +23,6 @@ static unsigned dm_mq_queue_depth = DM_MQ_QUEUE_DEPTH; #define RESERVED_REQUEST_BASED_IOS 256 static unsigned reserved_rq_based_ios = RESERVED_REQUEST_BASED_IOS; -static bool use_blk_mq = IS_ENABLED(CONFIG_DM_MQ_DEFAULT); - -bool dm_use_blk_mq_default(void) -{ - return use_blk_mq; -} - -bool dm_use_blk_mq(struct mapped_device *md) -{ - return md->use_blk_mq; -} -EXPORT_SYMBOL_GPL(dm_use_blk_mq); - unsigned dm_get_reserved_rq_based_ios(void) { return __dm_get_module_param(&reserved_rq_based_ios, @@ -59,41 +46,13 @@ int dm_request_based(struct mapped_device *md) return queue_is_rq_based(md->queue); } -static void dm_old_start_queue(struct request_queue *q) -{ - unsigned long flags; - - spin_lock_irqsave(q->queue_lock, flags); - if (blk_queue_stopped(q)) - blk_start_queue(q); - spin_unlock_irqrestore(q->queue_lock, flags); -} - -static void dm_mq_start_queue(struct request_queue *q) +void dm_start_queue(struct request_queue *q) { blk_mq_unquiesce_queue(q); blk_mq_kick_requeue_list(q); } -void dm_start_queue(struct request_queue *q) -{ - if (!q->mq_ops) - dm_old_start_queue(q); - else - dm_mq_start_queue(q); -} - -static void dm_old_stop_queue(struct request_queue *q) -{ - unsigned long flags; - - spin_lock_irqsave(q->queue_lock, flags); - if (!blk_queue_stopped(q)) - blk_stop_queue(q); - spin_unlock_irqrestore(q->queue_lock, flags); -} - -static void dm_mq_stop_queue(struct request_queue *q) +void dm_stop_queue(struct request_queue *q) { if (blk_mq_queue_stopped(q)) return; @@ -101,14 +60,6 @@ static void dm_mq_stop_queue(struct request_queue *q) blk_mq_quiesce_queue(q); } -void dm_stop_queue(struct request_queue *q) -{ - if (!q->mq_ops) - dm_old_stop_queue(q); - else - dm_mq_stop_queue(q); -} - /* * Partial completion handling for request-based dm */ @@ -179,9 +130,6 @@ static void rq_end_stats(struct mapped_device *md, struct request *orig) */ static void rq_completed(struct mapped_device *md, int rw, bool run_queue) { - struct request_queue *q = md->queue; - unsigned long flags; - atomic_dec(&md->pending[rw]); /* nudge anyone waiting on suspend queue */ @@ -189,18 +137,6 @@ static void rq_completed(struct mapped_device *md, int rw, bool run_queue) wake_up(&md->wait); /* - * Run this off this callpath, as drivers could invoke end_io while - * inside their request_fn (and holding the queue lock). Calling - * back into ->request_fn() could deadlock attempting to grab the - * queue lock again. - */ - if (!q->mq_ops && run_queue) { - spin_lock_irqsave(q->queue_lock, flags); - blk_run_queue_async(q); - spin_unlock_irqrestore(q->queue_lock, flags); - } - - /* * dm_put() must be at the end of this function. See the comment above */ dm_put(md); @@ -222,27 +158,10 @@ static void dm_end_request(struct request *clone, blk_status_t error) tio->ti->type->release_clone_rq(clone); rq_end_stats(md, rq); - if (!rq->q->mq_ops) - blk_end_request_all(rq, error); - else - blk_mq_end_request(rq, error); + blk_mq_end_request(rq, error); rq_completed(md, rw, true); } -/* - * Requeue the original request of a clone. - */ -static void dm_old_requeue_request(struct request *rq, unsigned long delay_ms) -{ - struct request_queue *q = rq->q; - unsigned long flags; - - spin_lock_irqsave(q->queue_lock, flags); - blk_requeue_request(q, rq); - blk_delay_queue(q, delay_ms); - spin_unlock_irqrestore(q->queue_lock, flags); -} - static void __dm_mq_kick_requeue_list(struct request_queue *q, unsigned long msecs) { blk_mq_delay_kick_requeue_list(q, msecs); @@ -273,11 +192,7 @@ static void dm_requeue_original_request(struct dm_rq_target_io *tio, bool delay_ tio->ti->type->release_clone_rq(tio->clone); } - if (!rq->q->mq_ops) - dm_old_requeue_request(rq, delay_ms); - else - dm_mq_delay_requeue_request(rq, delay_ms); - + dm_mq_delay_requeue_request(rq, delay_ms); rq_completed(md, rw, false); } @@ -340,10 +255,7 @@ static void dm_softirq_done(struct request *rq) rq_end_stats(md, rq); rw = rq_data_dir(rq); - if (!rq->q->mq_ops) - blk_end_request_all(rq, tio->error); - else - blk_mq_end_request(rq, tio->error); + blk_mq_end_request(rq, tio->error); rq_completed(md, rw, false); return; } @@ -363,17 +275,14 @@ static void dm_complete_request(struct request *rq, blk_status_t error) struct dm_rq_target_io *tio = tio_from_request(rq); tio->error = error; - if (!rq->q->mq_ops) - blk_complete_request(rq); - else - blk_mq_complete_request(rq); + blk_mq_complete_request(rq); } /* * Complete the not-mapped clone and the original request with the error status * through softirq context. * Target's rq_end_io() function isn't called. - * This may be used when the target's map_rq() or clone_and_map_rq() functions fail. + * This may be used when the target's clone_and_map_rq() function fails. */ static void dm_kill_unmapped_request(struct request *rq, blk_status_t error) { @@ -381,21 +290,10 @@ static void dm_kill_unmapped_request(struct request *rq, blk_status_t error) dm_complete_request(rq, error); } -/* - * Called with the clone's queue lock held (in the case of .request_fn) - */ static void end_clone_request(struct request *clone, blk_status_t error) { struct dm_rq_target_io *tio = clone->end_io_data; - /* - * Actual request completion is done in a softirq context which doesn't - * hold the clone's queue lock. Otherwise, deadlock could occur because: - * - another request may be submitted by the upper level driver - * of the stacking during the completion - * - the submission which requires queue lock may be done - * against this clone's queue - */ dm_complete_request(tio->orig, error); } @@ -446,8 +344,6 @@ static int setup_clone(struct request *clone, struct request *rq, return 0; } -static void map_tio_request(struct kthread_work *work); - static void init_tio(struct dm_rq_target_io *tio, struct request *rq, struct mapped_device *md) { @@ -464,8 +360,6 @@ static void init_tio(struct dm_rq_target_io *tio, struct request *rq, */ if (!md->init_tio_pdu) memset(&tio->info, 0, sizeof(tio->info)); - if (md->kworker_task) - kthread_init_work(&tio->work, map_tio_request); } /* @@ -504,10 +398,7 @@ check_again: blk_rq_unprep_clone(clone); tio->ti->type->release_clone_rq(clone); tio->clone = NULL; - if (!rq->q->mq_ops) - r = DM_MAPIO_DELAY_REQUEUE; - else - r = DM_MAPIO_REQUEUE; + r = DM_MAPIO_REQUEUE; goto check_again; } break; @@ -530,20 +421,23 @@ check_again: return r; } +/* DEPRECATED: previously used for request-based merge heuristic in dm_request_fn() */ +ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf) +{ + return sprintf(buf, "%u\n", 0); +} + +ssize_t dm_attr_rq_based_seq_io_merge_deadline_store(struct mapped_device *md, + const char *buf, size_t count) +{ + return count; +} + static void dm_start_request(struct mapped_device *md, struct request *orig) { - if (!orig->q->mq_ops) - blk_start_request(orig); - else - blk_mq_start_request(orig); + blk_mq_start_request(orig); atomic_inc(&md->pending[rq_data_dir(orig)]); - if (md->seq_rq_merge_deadline_usecs) { - md->last_rq_pos = rq_end_sector(orig); - md->last_rq_rw = rq_data_dir(orig); - md->last_rq_start_time = ktime_get(); - } - if (unlikely(dm_stats_used(&md->stats))) { struct dm_rq_target_io *tio = tio_from_request(orig); tio->duration_jiffies = jiffies; @@ -563,8 +457,10 @@ static void dm_start_request(struct mapped_device *md, struct request *orig) dm_get(md); } -static int __dm_rq_init_rq(struct mapped_device *md, struct request *rq) +static int dm_mq_init_request(struct blk_mq_tag_set *set, struct request *rq, + unsigned int hctx_idx, unsigned int numa_node) { + struct mapped_device *md = set->driver_data; struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq); /* @@ -581,163 +477,6 @@ static int __dm_rq_init_rq(struct mapped_device *md, struct request *rq) return 0; } -static int dm_rq_init_rq(struct request_queue *q, struct request *rq, gfp_t gfp) -{ - return __dm_rq_init_rq(q->rq_alloc_data, rq); -} - -static void map_tio_request(struct kthread_work *work) -{ - struct dm_rq_target_io *tio = container_of(work, struct dm_rq_target_io, work); - - if (map_request(tio) == DM_MAPIO_REQUEUE) - dm_requeue_original_request(tio, false); -} - -ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf) -{ - return sprintf(buf, "%u\n", md->seq_rq_merge_deadline_usecs); -} - -#define MAX_SEQ_RQ_MERGE_DEADLINE_USECS 100000 - -ssize_t dm_attr_rq_based_seq_io_merge_deadline_store(struct mapped_device *md, - const char *buf, size_t count) -{ - unsigned deadline; - - if (dm_get_md_type(md) != DM_TYPE_REQUEST_BASED) - return count; - - if (kstrtouint(buf, 10, &deadline)) - return -EINVAL; - - if (deadline > MAX_SEQ_RQ_MERGE_DEADLINE_USECS) - deadline = MAX_SEQ_RQ_MERGE_DEADLINE_USECS; - - md->seq_rq_merge_deadline_usecs = deadline; - - return count; -} - -static bool dm_old_request_peeked_before_merge_deadline(struct mapped_device *md) -{ - ktime_t kt_deadline; - - if (!md->seq_rq_merge_deadline_usecs) - return false; - - kt_deadline = ns_to_ktime((u64)md->seq_rq_merge_deadline_usecs * NSEC_PER_USEC); - kt_deadline = ktime_add_safe(md->last_rq_start_time, kt_deadline); - - return !ktime_after(ktime_get(), kt_deadline); -} - -/* - * q->request_fn for old request-based dm. - * Called with the queue lock held. - */ -static void dm_old_request_fn(struct request_queue *q) -{ - struct mapped_device *md = q->queuedata; - struct dm_target *ti = md->immutable_target; - struct request *rq; - struct dm_rq_target_io *tio; - sector_t pos = 0; - - if (unlikely(!ti)) { - int srcu_idx; - struct dm_table *map = dm_get_live_table(md, &srcu_idx); - - if (unlikely(!map)) { - dm_put_live_table(md, srcu_idx); - return; - } - ti = dm_table_find_target(map, pos); - dm_put_live_table(md, srcu_idx); - } - - /* - * For suspend, check blk_queue_stopped() and increment - * ->pending within a single queue_lock not to increment the - * number of in-flight I/Os after the queue is stopped in - * dm_suspend(). - */ - while (!blk_queue_stopped(q)) { - rq = blk_peek_request(q); - if (!rq) - return; - - /* always use block 0 to find the target for flushes for now */ - pos = 0; - if (req_op(rq) != REQ_OP_FLUSH) - pos = blk_rq_pos(rq); - - if ((dm_old_request_peeked_before_merge_deadline(md) && - md_in_flight(md) && rq->bio && !bio_multiple_segments(rq->bio) && - md->last_rq_pos == pos && md->last_rq_rw == rq_data_dir(rq)) || - (ti->type->busy && ti->type->busy(ti))) { - blk_delay_queue(q, 10); - return; - } - - dm_start_request(md, rq); - - tio = tio_from_request(rq); - init_tio(tio, rq, md); - /* Establish tio->ti before queuing work (map_tio_request) */ - tio->ti = ti; - kthread_queue_work(&md->kworker, &tio->work); - BUG_ON(!irqs_disabled()); - } -} - -/* - * Fully initialize a .request_fn request-based queue. - */ -int dm_old_init_request_queue(struct mapped_device *md, struct dm_table *t) -{ - struct dm_target *immutable_tgt; - - /* Fully initialize the queue */ - md->queue->cmd_size = sizeof(struct dm_rq_target_io); - md->queue->rq_alloc_data = md; - md->queue->request_fn = dm_old_request_fn; - md->queue->init_rq_fn = dm_rq_init_rq; - - immutable_tgt = dm_table_get_immutable_target(t); - if (immutable_tgt && immutable_tgt->per_io_data_size) { - /* any target-specific per-io data is immediately after the tio */ - md->queue->cmd_size += immutable_tgt->per_io_data_size; - md->init_tio_pdu = true; - } - if (blk_init_allocated_queue(md->queue) < 0) - return -EINVAL; - - /* disable dm_old_request_fn's merge heuristic by default */ - md->seq_rq_merge_deadline_usecs = 0; - - blk_queue_softirq_done(md->queue, dm_softirq_done); - - /* Initialize the request-based DM worker thread */ - kthread_init_worker(&md->kworker); - md->kworker_task = kthread_run(kthread_worker_fn, &md->kworker, - "kdmwork-%s", dm_device_name(md)); - if (IS_ERR(md->kworker_task)) { - int error = PTR_ERR(md->kworker_task); - md->kworker_task = NULL; - return error; - } - - return 0; -} - -static int dm_mq_init_request(struct blk_mq_tag_set *set, struct request *rq, - unsigned int hctx_idx, unsigned int numa_node) -{ - return __dm_rq_init_rq(set->driver_data, rq); -} - static blk_status_t dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { @@ -790,11 +529,6 @@ int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t) struct dm_target *immutable_tgt; int err; - if (!dm_table_all_blk_mq_devices(t)) { - DMERR("request-based dm-mq may only be stacked on blk-mq device(s)"); - return -EINVAL; - } - md->tag_set = kzalloc_node(sizeof(struct blk_mq_tag_set), GFP_KERNEL, md->numa_node_id); if (!md->tag_set) return -ENOMEM; @@ -845,6 +579,8 @@ void dm_mq_cleanup_mapped_device(struct mapped_device *md) module_param(reserved_rq_based_ios, uint, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(reserved_rq_based_ios, "Reserved IOs in request-based mempools"); +/* Unused, but preserved for userspace compatibility */ +static bool use_blk_mq = true; module_param(use_blk_mq, bool, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(use_blk_mq, "Use block multiqueue for request-based DM devices"); diff --git a/drivers/md/dm-rq.h b/drivers/md/dm-rq.h index f43c45460aac..b39245545229 100644 --- a/drivers/md/dm-rq.h +++ b/drivers/md/dm-rq.h @@ -46,10 +46,6 @@ struct dm_rq_clone_bio_info { struct bio clone; }; -bool dm_use_blk_mq_default(void); -bool dm_use_blk_mq(struct mapped_device *md); - -int dm_old_init_request_queue(struct mapped_device *md, struct dm_table *t); int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t); void dm_mq_cleanup_mapped_device(struct mapped_device *md); diff --git a/drivers/md/dm-sysfs.c b/drivers/md/dm-sysfs.c index c209b8a19b84..a05fcd50e1b9 100644 --- a/drivers/md/dm-sysfs.c +++ b/drivers/md/dm-sysfs.c @@ -92,7 +92,8 @@ static ssize_t dm_attr_suspended_show(struct mapped_device *md, char *buf) static ssize_t dm_attr_use_blk_mq_show(struct mapped_device *md, char *buf) { - sprintf(buf, "%d\n", dm_use_blk_mq(md)); + /* Purely for userspace compatibility */ + sprintf(buf, "%d\n", true); return strlen(buf); } diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 3d0e2c198f06..9038c302d5c2 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -47,7 +47,6 @@ struct dm_table { bool integrity_supported:1; bool singleton:1; - bool all_blk_mq:1; unsigned integrity_added:1; /* @@ -872,8 +871,7 @@ static bool __table_type_bio_based(enum dm_queue_mode table_type) static bool __table_type_request_based(enum dm_queue_mode table_type) { - return (table_type == DM_TYPE_REQUEST_BASED || - table_type == DM_TYPE_MQ_REQUEST_BASED); + return table_type == DM_TYPE_REQUEST_BASED; } void dm_table_set_type(struct dm_table *t, enum dm_queue_mode type) @@ -999,10 +997,6 @@ verify_bio_based: BUG_ON(!request_based); /* No targets in this table */ - /* - * The only way to establish DM_TYPE_MQ_REQUEST_BASED is by - * having a compatible target use dm_table_set_type. - */ t->type = DM_TYPE_REQUEST_BASED; verify_rq_based: @@ -1022,11 +1016,9 @@ verify_rq_based: int srcu_idx; struct dm_table *live_table = dm_get_live_table(t->md, &srcu_idx); - /* inherit live table's type and all_blk_mq */ - if (live_table) { + /* inherit live table's type */ + if (live_table) t->type = live_table->type; - t->all_blk_mq = live_table->all_blk_mq; - } dm_put_live_table(t->md, srcu_idx); return 0; } @@ -1046,17 +1038,10 @@ verify_rq_based: DMERR("table load rejected: including non-request-stackable devices"); return -EINVAL; } - if (v.sq_count && v.mq_count) { + if (v.sq_count > 0) { DMERR("table load rejected: not all devices are blk-mq request-stackable"); return -EINVAL; } - t->all_blk_mq = v.mq_count > 0; - - if (!t->all_blk_mq && - (t->type == DM_TYPE_MQ_REQUEST_BASED || t->type == DM_TYPE_NVME_BIO_BASED)) { - DMERR("table load rejected: all devices are not blk-mq request-stackable"); - return -EINVAL; - } return 0; } @@ -1105,11 +1090,6 @@ bool dm_table_request_based(struct dm_table *t) return __table_type_request_based(dm_table_get_type(t)); } -bool dm_table_all_blk_mq_devices(struct dm_table *t) -{ - return t->all_blk_mq; -} - static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *md) { enum dm_queue_mode type = dm_table_get_type(t); @@ -1937,6 +1917,16 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, */ if (blk_queue_add_random(q) && dm_table_all_devices_attribute(t, device_is_not_random)) blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q); + + /* + * For a zoned target, the number of zones should be updated for the + * correct value to be exposed in sysfs queue/nr_zones. For a BIO based + * target, this is all that is needed. For a request based target, the + * queue zone bitmaps must also be updated. + * Use blk_revalidate_disk_zones() to handle this. + */ + if (blk_queue_is_zoned(q)) + blk_revalidate_disk_zones(t->md->disk); } unsigned int dm_table_get_num_targets(struct dm_table *t) @@ -2079,26 +2069,24 @@ struct mapped_device *dm_table_get_md(struct dm_table *t) } EXPORT_SYMBOL(dm_table_get_md); +const char *dm_table_device_name(struct dm_table *t) +{ + return dm_device_name(t->md); +} +EXPORT_SYMBOL_GPL(dm_table_device_name); + void dm_table_run_md_queue_async(struct dm_table *t) { struct mapped_device *md; struct request_queue *queue; - unsigned long flags; if (!dm_table_request_based(t)) return; md = dm_table_get_md(t); queue = dm_get_md_queue(md); - if (queue) { - if (queue->mq_ops) - blk_mq_run_hw_queues(queue, true); - else { - spin_lock_irqsave(queue->queue_lock, flags); - blk_run_queue_async(queue); - spin_unlock_irqrestore(queue->queue_lock, flags); - } - } + if (queue) + blk_mq_run_hw_queues(queue, true); } EXPORT_SYMBOL(dm_table_run_md_queue_async); diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index aaf1ad481ee8..0bd8d498b3b9 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -325,7 +325,7 @@ struct thin_c { * Ensures the thin is not destroyed until the worker has finished * iterating the active_thins list. */ - atomic_t refcount; + refcount_t refcount; struct completion can_destroy; }; @@ -4044,12 +4044,12 @@ static struct target_type pool_target = { *--------------------------------------------------------------*/ static void thin_get(struct thin_c *tc) { - atomic_inc(&tc->refcount); + refcount_inc(&tc->refcount); } static void thin_put(struct thin_c *tc) { - if (atomic_dec_and_test(&tc->refcount)) + if (refcount_dec_and_test(&tc->refcount)) complete(&tc->can_destroy); } @@ -4193,7 +4193,7 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv) r = -EINVAL; goto bad; } - atomic_set(&tc->refcount, 1); + refcount_set(&tc->refcount, 1); init_completion(&tc->can_destroy); list_add_tail_rcu(&tc->list, &tc->pool->active_thins); spin_unlock_irqrestore(&tc->pool->lock, flags); diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 5f1f80d424dd..2d50eec94cd7 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -350,10 +350,7 @@ static struct wc_memory_superblock *sb(struct dm_writecache *wc) static struct wc_memory_entry *memory_entry(struct dm_writecache *wc, struct wc_entry *e) { - if (is_power_of_2(sizeof(struct wc_entry)) && 0) - return &sb(wc)->entries[e - wc->entries]; - else - return &sb(wc)->entries[e->index]; + return &sb(wc)->entries[e->index]; } static void *memory_data(struct dm_writecache *wc, struct wc_entry *e) diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c index 969954915566..fa68336560c3 100644 --- a/drivers/md/dm-zoned-metadata.c +++ b/drivers/md/dm-zoned-metadata.c @@ -99,7 +99,7 @@ struct dmz_mblock { struct rb_node node; struct list_head link; sector_t no; - atomic_t ref; + unsigned int ref; unsigned long state; struct page *page; void *data; @@ -296,7 +296,7 @@ static struct dmz_mblock *dmz_alloc_mblock(struct dmz_metadata *zmd, RB_CLEAR_NODE(&mblk->node); INIT_LIST_HEAD(&mblk->link); - atomic_set(&mblk->ref, 0); + mblk->ref = 0; mblk->state = 0; mblk->no = mblk_no; mblk->data = page_address(mblk->page); @@ -339,10 +339,11 @@ static void dmz_insert_mblock(struct dmz_metadata *zmd, struct dmz_mblock *mblk) } /* - * Lookup a metadata block in the rbtree. + * Lookup a metadata block in the rbtree. If the block is found, increment + * its reference count. */ -static struct dmz_mblock *dmz_lookup_mblock(struct dmz_metadata *zmd, - sector_t mblk_no) +static struct dmz_mblock *dmz_get_mblock_fast(struct dmz_metadata *zmd, + sector_t mblk_no) { struct rb_root *root = &zmd->mblk_rbtree; struct rb_node *node = root->rb_node; @@ -350,8 +351,17 @@ static struct dmz_mblock *dmz_lookup_mblock(struct dmz_metadata *zmd, while (node) { mblk = container_of(node, struct dmz_mblock, node); - if (mblk->no == mblk_no) + if (mblk->no == mblk_no) { + /* + * If this is the first reference to the block, + * remove it from the LRU list. + */ + mblk->ref++; + if (mblk->ref == 1 && + !test_bit(DMZ_META_DIRTY, &mblk->state)) + list_del_init(&mblk->link); return mblk; + } node = (mblk->no < mblk_no) ? node->rb_left : node->rb_right; } @@ -382,32 +392,47 @@ static void dmz_mblock_bio_end_io(struct bio *bio) } /* - * Read a metadata block from disk. + * Read an uncached metadata block from disk and add it to the cache. */ -static struct dmz_mblock *dmz_fetch_mblock(struct dmz_metadata *zmd, - sector_t mblk_no) +static struct dmz_mblock *dmz_get_mblock_slow(struct dmz_metadata *zmd, + sector_t mblk_no) { - struct dmz_mblock *mblk; + struct dmz_mblock *mblk, *m; sector_t block = zmd->sb[zmd->mblk_primary].block + mblk_no; struct bio *bio; - /* Get block and insert it */ + /* Get a new block and a BIO to read it */ mblk = dmz_alloc_mblock(zmd, mblk_no); if (!mblk) return NULL; - spin_lock(&zmd->mblk_lock); - atomic_inc(&mblk->ref); - set_bit(DMZ_META_READING, &mblk->state); - dmz_insert_mblock(zmd, mblk); - spin_unlock(&zmd->mblk_lock); - bio = bio_alloc(GFP_NOIO, 1); if (!bio) { dmz_free_mblock(zmd, mblk); return NULL; } + spin_lock(&zmd->mblk_lock); + + /* + * Make sure that another context did not start reading + * the block already. + */ + m = dmz_get_mblock_fast(zmd, mblk_no); + if (m) { + spin_unlock(&zmd->mblk_lock); + dmz_free_mblock(zmd, mblk); + bio_put(bio); + return m; + } + + mblk->ref++; + set_bit(DMZ_META_READING, &mblk->state); + dmz_insert_mblock(zmd, mblk); + + spin_unlock(&zmd->mblk_lock); + + /* Submit read BIO */ bio->bi_iter.bi_sector = dmz_blk2sect(block); bio_set_dev(bio, zmd->dev->bdev); bio->bi_private = mblk; @@ -484,7 +509,8 @@ static void dmz_release_mblock(struct dmz_metadata *zmd, spin_lock(&zmd->mblk_lock); - if (atomic_dec_and_test(&mblk->ref)) { + mblk->ref--; + if (mblk->ref == 0) { if (test_bit(DMZ_META_ERROR, &mblk->state)) { rb_erase(&mblk->node, &zmd->mblk_rbtree); dmz_free_mblock(zmd, mblk); @@ -508,18 +534,12 @@ static struct dmz_mblock *dmz_get_mblock(struct dmz_metadata *zmd, /* Check rbtree */ spin_lock(&zmd->mblk_lock); - mblk = dmz_lookup_mblock(zmd, mblk_no); - if (mblk) { - /* Cache hit: remove block from LRU list */ - if (atomic_inc_return(&mblk->ref) == 1 && - !test_bit(DMZ_META_DIRTY, &mblk->state)) - list_del_init(&mblk->link); - } + mblk = dmz_get_mblock_fast(zmd, mblk_no); spin_unlock(&zmd->mblk_lock); if (!mblk) { /* Cache miss: read the block from disk */ - mblk = dmz_fetch_mblock(zmd, mblk_no); + mblk = dmz_get_mblock_slow(zmd, mblk_no); if (!mblk) return ERR_PTR(-ENOMEM); } @@ -753,7 +773,7 @@ int dmz_flush_metadata(struct dmz_metadata *zmd) spin_lock(&zmd->mblk_lock); clear_bit(DMZ_META_DIRTY, &mblk->state); - if (atomic_read(&mblk->ref) == 0) + if (mblk->ref == 0) list_add_tail(&mblk->link, &zmd->mblk_lru_list); spin_unlock(&zmd->mblk_lock); } @@ -2308,7 +2328,7 @@ static void dmz_cleanup_metadata(struct dmz_metadata *zmd) mblk = list_first_entry(&zmd->mblk_dirty_list, struct dmz_mblock, link); dmz_dev_warn(zmd->dev, "mblock %llu still in dirty list (ref %u)", - (u64)mblk->no, atomic_read(&mblk->ref)); + (u64)mblk->no, mblk->ref); list_del_init(&mblk->link); rb_erase(&mblk->node, &zmd->mblk_rbtree); dmz_free_mblock(zmd, mblk); @@ -2326,8 +2346,8 @@ static void dmz_cleanup_metadata(struct dmz_metadata *zmd) root = &zmd->mblk_rbtree; rbtree_postorder_for_each_entry_safe(mblk, next, root, node) { dmz_dev_warn(zmd->dev, "mblock %llu ref %u still in rbtree", - (u64)mblk->no, atomic_read(&mblk->ref)); - atomic_set(&mblk->ref, 0); + (u64)mblk->no, mblk->ref); + mblk->ref = 0; dmz_free_mblock(zmd, mblk); } diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index a44183ff4be0..981154e59461 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -19,7 +19,7 @@ struct dmz_bioctx { struct dmz_target *target; struct dm_zone *zone; struct bio *bio; - atomic_t ref; + refcount_t ref; blk_status_t status; }; @@ -28,7 +28,7 @@ struct dmz_bioctx { */ struct dm_chunk_work { struct work_struct work; - atomic_t refcount; + refcount_t refcount; struct dmz_target *target; unsigned int chunk; struct bio_list bio_list; @@ -115,7 +115,7 @@ static int dmz_submit_read_bio(struct dmz_target *dmz, struct dm_zone *zone, if (nr_blocks == dmz_bio_blocks(bio)) { /* Setup and submit the BIO */ bio->bi_iter.bi_sector = sector; - atomic_inc(&bioctx->ref); + refcount_inc(&bioctx->ref); generic_make_request(bio); return 0; } @@ -134,7 +134,7 @@ static int dmz_submit_read_bio(struct dmz_target *dmz, struct dm_zone *zone, bio_advance(bio, clone->bi_iter.bi_size); /* Submit the clone */ - atomic_inc(&bioctx->ref); + refcount_inc(&bioctx->ref); generic_make_request(clone); return 0; @@ -240,7 +240,7 @@ static void dmz_submit_write_bio(struct dmz_target *dmz, struct dm_zone *zone, /* Setup and submit the BIO */ bio_set_dev(bio, dmz->dev->bdev); bio->bi_iter.bi_sector = dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block); - atomic_inc(&bioctx->ref); + refcount_inc(&bioctx->ref); generic_make_request(bio); if (dmz_is_seq(zone)) @@ -456,7 +456,7 @@ out: */ static inline void dmz_get_chunk_work(struct dm_chunk_work *cw) { - atomic_inc(&cw->refcount); + refcount_inc(&cw->refcount); } /* @@ -465,7 +465,7 @@ static inline void dmz_get_chunk_work(struct dm_chunk_work *cw) */ static void dmz_put_chunk_work(struct dm_chunk_work *cw) { - if (atomic_dec_and_test(&cw->refcount)) { + if (refcount_dec_and_test(&cw->refcount)) { WARN_ON(!bio_list_empty(&cw->bio_list)); radix_tree_delete(&cw->target->chunk_rxtree, cw->chunk); kfree(cw); @@ -546,7 +546,7 @@ static void dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio) goto out; INIT_WORK(&cw->work, dmz_chunk_work); - atomic_set(&cw->refcount, 0); + refcount_set(&cw->refcount, 0); cw->target = dmz; cw->chunk = chunk; bio_list_init(&cw->bio_list); @@ -599,7 +599,7 @@ static int dmz_map(struct dm_target *ti, struct bio *bio) bioctx->target = dmz; bioctx->zone = NULL; bioctx->bio = bio; - atomic_set(&bioctx->ref, 1); + refcount_set(&bioctx->ref, 1); bioctx->status = BLK_STS_OK; /* Set the BIO pending in the flush list */ @@ -633,7 +633,7 @@ static int dmz_end_io(struct dm_target *ti, struct bio *bio, blk_status_t *error if (bioctx->status == BLK_STS_OK && *error) bioctx->status = *error; - if (!atomic_dec_and_test(&bioctx->ref)) + if (!refcount_dec_and_test(&bioctx->ref)) return DM_ENDIO_INCOMPLETE; /* Done */ @@ -702,8 +702,7 @@ static int dmz_get_zoned_device(struct dm_target *ti, char *path) dev->zone_nr_blocks = dmz_sect2blk(dev->zone_nr_sectors); dev->zone_nr_blocks_shift = ilog2(dev->zone_nr_blocks); - dev->nr_zones = (dev->capacity + dev->zone_nr_sectors - 1) - >> dev->zone_nr_sectors_shift; + dev->nr_zones = blkdev_nr_zones(dev->bdev); dmz->dev = dev; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 45abb54037fc..c510179a7f84 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -458,6 +458,57 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo) return dm_get_geometry(md, geo); } +static int dm_blk_report_zones(struct gendisk *disk, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask) +{ +#ifdef CONFIG_BLK_DEV_ZONED + struct mapped_device *md = disk->private_data; + struct dm_target *tgt; + struct dm_table *map; + int srcu_idx, ret; + + if (dm_suspended_md(md)) + return -EAGAIN; + + map = dm_get_live_table(md, &srcu_idx); + if (!map) + return -EIO; + + tgt = dm_table_find_target(map, sector); + if (!dm_target_is_valid(tgt)) { + ret = -EIO; + goto out; + } + + /* + * If we are executing this, we already know that the block device + * is a zoned device and so each target should have support for that + * type of drive. A missing report_zones method means that the target + * driver has a problem. + */ + if (WARN_ON(!tgt->type->report_zones)) { + ret = -EIO; + goto out; + } + + /* + * blkdev_report_zones() will loop and call this again to cover all the + * zones of the target, eventually moving on to the next target. + * So there is no need to loop here trying to fill the entire array + * of zones. + */ + ret = tgt->type->report_zones(tgt, sector, zones, + nr_zones, gfp_mask); + +out: + dm_put_live_table(md, srcu_idx); + return ret; +#else + return -ENOTSUPP; +#endif +} + static int dm_prepare_ioctl(struct mapped_device *md, int *srcu_idx, struct block_device **bdev) __acquires(md->io_barrier) @@ -1155,93 +1206,49 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors) EXPORT_SYMBOL_GPL(dm_accept_partial_bio); /* - * The zone descriptors obtained with a zone report indicate zone positions - * within the target backing device, regardless of that device is a partition - * and regardless of the target mapping start sector on the device or partition. - * The zone descriptors start sector and write pointer position must be adjusted - * to match their relative position within the dm device. - * A target may call dm_remap_zone_report() after completion of a - * REQ_OP_ZONE_REPORT bio to remap the zone descriptors obtained from the - * backing device. + * The zone descriptors obtained with a zone report indicate + * zone positions within the underlying device of the target. The zone + * descriptors must be remapped to match their position within the dm device. + * The caller target should obtain the zones information using + * blkdev_report_zones() to ensure that remapping for partition offset is + * already handled. */ -void dm_remap_zone_report(struct dm_target *ti, struct bio *bio, sector_t start) +void dm_remap_zone_report(struct dm_target *ti, sector_t start, + struct blk_zone *zones, unsigned int *nr_zones) { #ifdef CONFIG_BLK_DEV_ZONED - struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone); - struct bio *report_bio = tio->io->orig_bio; - struct blk_zone_report_hdr *hdr = NULL; struct blk_zone *zone; - unsigned int nr_rep = 0; - unsigned int ofst; - sector_t part_offset; - struct bio_vec bvec; - struct bvec_iter iter; - void *addr; - - if (bio->bi_status) - return; - - /* - * bio sector was incremented by the request size on completion. Taking - * into account the original request sector, the target start offset on - * the backing device and the target mapping offset (ti->begin), the - * start sector of the backing device. The partition offset is always 0 - * if the target uses a whole device. - */ - part_offset = bio->bi_iter.bi_sector + ti->begin - (start + bio_end_sector(report_bio)); + unsigned int nrz = *nr_zones; + int i; /* - * Remap the start sector of the reported zones. For sequential zones, - * also remap the write pointer position. + * Remap the start sector and write pointer position of the zones in + * the array. Since we may have obtained from the target underlying + * device more zones that the target size, also adjust the number + * of zones. */ - bio_for_each_segment(bvec, report_bio, iter) { - addr = kmap_atomic(bvec.bv_page); - - /* Remember the report header in the first page */ - if (!hdr) { - hdr = addr; - ofst = sizeof(struct blk_zone_report_hdr); - } else - ofst = 0; - - /* Set zones start sector */ - while (hdr->nr_zones && ofst < bvec.bv_len) { - zone = addr + ofst; - zone->start -= part_offset; - if (zone->start >= start + ti->len) { - hdr->nr_zones = 0; - break; - } - zone->start = zone->start + ti->begin - start; - if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) { - if (zone->cond == BLK_ZONE_COND_FULL) - zone->wp = zone->start + zone->len; - else if (zone->cond == BLK_ZONE_COND_EMPTY) - zone->wp = zone->start; - else - zone->wp = zone->wp + ti->begin - start - part_offset; - } - ofst += sizeof(struct blk_zone); - hdr->nr_zones--; - nr_rep++; + for (i = 0; i < nrz; i++) { + zone = zones + i; + if (zone->start >= start + ti->len) { + memset(zone, 0, sizeof(struct blk_zone) * (nrz - i)); + break; } - if (addr != hdr) - kunmap_atomic(addr); - - if (!hdr->nr_zones) - break; - } + zone->start = zone->start + ti->begin - start; + if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) + continue; - if (hdr) { - hdr->nr_zones = nr_rep; - kunmap_atomic(hdr); + if (zone->cond == BLK_ZONE_COND_FULL) + zone->wp = zone->start + zone->len; + else if (zone->cond == BLK_ZONE_COND_EMPTY) + zone->wp = zone->start; + else + zone->wp = zone->wp + ti->begin - start; } - bio_advance(report_bio, report_bio->bi_iter.bi_size); - + *nr_zones = i; #else /* !CONFIG_BLK_DEV_ZONED */ - bio->bi_status = BLK_STS_NOTSUPP; + *nr_zones = 0; #endif } EXPORT_SYMBOL_GPL(dm_remap_zone_report); @@ -1327,8 +1334,7 @@ static int clone_bio(struct dm_target_io *tio, struct bio *bio, return r; } - if (bio_op(bio) != REQ_OP_ZONE_REPORT) - bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector)); + bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector)); clone->bi_iter.bi_size = to_bytes(len); if (unlikely(bio_integrity(bio) != NULL)) @@ -1541,7 +1547,6 @@ static bool __process_abnormal_io(struct clone_info *ci, struct dm_target *ti, */ static int __split_and_process_non_flush(struct clone_info *ci) { - struct bio *bio = ci->bio; struct dm_target *ti; unsigned len; int r; @@ -1553,11 +1558,7 @@ static int __split_and_process_non_flush(struct clone_info *ci) if (unlikely(__process_abnormal_io(ci, ti, &r))) return r; - if (bio_op(bio) == REQ_OP_ZONE_REPORT) - len = ci->sector_count; - else - len = min_t(sector_t, max_io_len(ci->sector, ti), - ci->sector_count); + len = min_t(sector_t, max_io_len(ci->sector, ti), ci->sector_count); r = __clone_and_map_data_bio(ci, ti, ci->sector, &len); if (r < 0) @@ -1616,9 +1617,6 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, * We take a clone of the original to store in * ci.io->orig_bio to be used by end_io_acct() and * for dec_pending to use for completion handling. - * As this path is not used for REQ_OP_ZONE_REPORT, - * the usage of io->orig_bio in dm_remap_zone_report() - * won't be affected by this reassignment. */ struct bio *b = bio_split(bio, bio_sectors(bio) - ci.sector_count, GFP_NOIO, &md->queue->bio_split); @@ -1666,7 +1664,7 @@ static blk_qc_t __process_bio(struct mapped_device *md, * Defend against IO still getting in during teardown * - as was seen for a time with nvme-fcloop */ - if (unlikely(WARN_ON_ONCE(!ti || !dm_target_is_valid(ti)))) { + if (WARN_ON_ONCE(!ti || !dm_target_is_valid(ti))) { error = -EIO; goto out; } @@ -1808,8 +1806,6 @@ static void dm_wq_work(struct work_struct *work); static void dm_init_normal_md_queue(struct mapped_device *md) { - md->use_blk_mq = false; - /* * Initialize aspects of queue that aren't relevant for blk-mq */ @@ -1820,8 +1816,6 @@ static void cleanup_mapped_device(struct mapped_device *md) { if (md->wq) destroy_workqueue(md->wq); - if (md->kworker_task) - kthread_stop(md->kworker_task); bioset_exit(&md->bs); bioset_exit(&md->io_bs); @@ -1888,7 +1882,6 @@ static struct mapped_device *alloc_dev(int minor) goto bad_io_barrier; md->numa_node_id = numa_node_id; - md->use_blk_mq = dm_use_blk_mq_default(); md->init_tio_pdu = false; md->type = DM_TYPE_NONE; mutex_init(&md->suspend_lock); @@ -1919,7 +1912,6 @@ static struct mapped_device *alloc_dev(int minor) INIT_WORK(&md->work, dm_wq_work); init_waitqueue_head(&md->eventq); init_completion(&md->kobj_holder.completion); - md->kworker_task = NULL; md->disk->major = _major; md->disk->first_minor = minor; @@ -2219,14 +2211,6 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t) switch (type) { case DM_TYPE_REQUEST_BASED: - dm_init_normal_md_queue(md); - r = dm_old_init_request_queue(md, t); - if (r) { - DMERR("Cannot initialize queue for request-based mapped device"); - return r; - } - break; - case DM_TYPE_MQ_REQUEST_BASED: r = dm_mq_init_request_queue(md, t); if (r) { DMERR("Cannot initialize queue for request-based dm-mq mapped device"); @@ -2331,9 +2315,6 @@ static void __dm_destroy(struct mapped_device *md, bool wait) blk_set_queue_dying(md->queue); - if (dm_request_based(md) && md->kworker_task) - kthread_flush_worker(&md->kworker); - /* * Take suspend_lock so that presuspend and postsuspend methods * do not race with internal suspend. @@ -2586,11 +2567,8 @@ static int __dm_suspend(struct mapped_device *md, struct dm_table *map, * Stop md->queue before flushing md->wq in case request-based * dm defers requests to md->wq from md->queue. */ - if (dm_request_based(md)) { + if (dm_request_based(md)) dm_stop_queue(md->queue); - if (md->kworker_task) - kthread_flush_worker(&md->kworker); - } flush_workqueue(md->wq); @@ -2965,7 +2943,6 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, enum dm_qu goto out; break; case DM_TYPE_REQUEST_BASED: - case DM_TYPE_MQ_REQUEST_BASED: pool_size = max(dm_get_reserved_rq_based_ios(), min_pool_size); front_pad = offsetof(struct dm_rq_clone_bio_info, clone); /* per_io_data_size is used for blk-mq pdu at queue allocation */ @@ -3167,6 +3144,7 @@ static const struct block_device_operations dm_blk_dops = { .release = dm_blk_close, .ioctl = dm_blk_ioctl, .getgeo = dm_blk_getgeo, + .report_zones = dm_blk_report_zones, .pr_ops = &dm_pr_ops, .owner = THIS_MODULE }; diff --git a/drivers/md/dm.h b/drivers/md/dm.h index 114a81b27c37..2d539b82ec08 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -70,7 +70,6 @@ struct dm_target *dm_table_get_immutable_target(struct dm_table *t); struct dm_target *dm_table_get_wildcard_target(struct dm_table *t); bool dm_table_bio_based(struct dm_table *t); bool dm_table_request_based(struct dm_table *t); -bool dm_table_all_blk_mq_devices(struct dm_table *t); void dm_table_free_md_mempools(struct dm_table *t); struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t); diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 2fc8c113977f..1cd4f991792c 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -2288,9 +2288,9 @@ location_store(struct mddev *mddev, const char *buf, size_t len) goto out; } if (mddev->pers) { - mddev->pers->quiesce(mddev, 1); + mddev_suspend(mddev); md_bitmap_destroy(mddev); - mddev->pers->quiesce(mddev, 0); + mddev_resume(mddev); } mddev->bitmap_info.offset = 0; if (mddev->bitmap_info.file) { @@ -2327,8 +2327,8 @@ location_store(struct mddev *mddev, const char *buf, size_t len) mddev->bitmap_info.offset = offset; if (mddev->pers) { struct bitmap *bitmap; - mddev->pers->quiesce(mddev, 1); bitmap = md_bitmap_create(mddev, -1); + mddev_suspend(mddev); if (IS_ERR(bitmap)) rv = PTR_ERR(bitmap); else { @@ -2337,11 +2337,12 @@ location_store(struct mddev *mddev, const char *buf, size_t len) if (rv) mddev->bitmap_info.offset = 0; } - mddev->pers->quiesce(mddev, 0); if (rv) { md_bitmap_destroy(mddev); + mddev_resume(mddev); goto out; } + mddev_resume(mddev); } } } diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index 0b2af6e74fc3..8dff19d5502e 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -33,13 +33,6 @@ struct dlm_lock_resource { int mode; }; -struct suspend_info { - int slot; - sector_t lo; - sector_t hi; - struct list_head list; -}; - struct resync_info { __le64 lo; __le64 hi; @@ -80,7 +73,13 @@ struct md_cluster_info { struct dlm_lock_resource **other_bitmap_lockres; struct dlm_lock_resource *resync_lockres; struct list_head suspend_list; + spinlock_t suspend_lock; + /* record the region which write should be suspended */ + sector_t suspend_lo; + sector_t suspend_hi; + int suspend_from; /* the slot which broadcast suspend_lo/hi */ + struct md_thread *recovery_thread; unsigned long recovery_map; /* communication loc resources */ @@ -105,6 +104,7 @@ enum msg_type { RE_ADD, BITMAP_NEEDS_SYNC, CHANGE_CAPACITY, + BITMAP_RESIZE, }; struct cluster_msg { @@ -270,25 +270,22 @@ static void add_resync_info(struct dlm_lock_resource *lockres, ri->hi = cpu_to_le64(hi); } -static struct suspend_info *read_resync_info(struct mddev *mddev, struct dlm_lock_resource *lockres) +static int read_resync_info(struct mddev *mddev, + struct dlm_lock_resource *lockres) { struct resync_info ri; - struct suspend_info *s = NULL; - sector_t hi = 0; + struct md_cluster_info *cinfo = mddev->cluster_info; + int ret = 0; dlm_lock_sync(lockres, DLM_LOCK_CR); memcpy(&ri, lockres->lksb.sb_lvbptr, sizeof(struct resync_info)); - hi = le64_to_cpu(ri.hi); - if (hi > 0) { - s = kzalloc(sizeof(struct suspend_info), GFP_KERNEL); - if (!s) - goto out; - s->hi = hi; - s->lo = le64_to_cpu(ri.lo); + if (le64_to_cpu(ri.hi) > 0) { + cinfo->suspend_hi = le64_to_cpu(ri.hi); + cinfo->suspend_lo = le64_to_cpu(ri.lo); + ret = 1; } dlm_unlock_sync(lockres); -out: - return s; + return ret; } static void recover_bitmaps(struct md_thread *thread) @@ -298,7 +295,6 @@ static void recover_bitmaps(struct md_thread *thread) struct dlm_lock_resource *bm_lockres; char str[64]; int slot, ret; - struct suspend_info *s, *tmp; sector_t lo, hi; while (cinfo->recovery_map) { @@ -325,13 +321,17 @@ static void recover_bitmaps(struct md_thread *thread) /* Clear suspend_area associated with the bitmap */ spin_lock_irq(&cinfo->suspend_lock); - list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list) - if (slot == s->slot) { - list_del(&s->list); - kfree(s); - } + cinfo->suspend_hi = 0; + cinfo->suspend_lo = 0; + cinfo->suspend_from = -1; spin_unlock_irq(&cinfo->suspend_lock); + /* Kick off a reshape if needed */ + if (test_bit(MD_RESYNCING_REMOTE, &mddev->recovery) && + test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && + mddev->reshape_position != MaxSector) + md_wakeup_thread(mddev->sync_thread); + if (hi > 0) { if (lo < mddev->recovery_cp) mddev->recovery_cp = lo; @@ -434,34 +434,23 @@ static void ack_bast(void *arg, int mode) } } -static void __remove_suspend_info(struct md_cluster_info *cinfo, int slot) -{ - struct suspend_info *s, *tmp; - - list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list) - if (slot == s->slot) { - list_del(&s->list); - kfree(s); - break; - } -} - static void remove_suspend_info(struct mddev *mddev, int slot) { struct md_cluster_info *cinfo = mddev->cluster_info; mddev->pers->quiesce(mddev, 1); spin_lock_irq(&cinfo->suspend_lock); - __remove_suspend_info(cinfo, slot); + cinfo->suspend_hi = 0; + cinfo->suspend_lo = 0; spin_unlock_irq(&cinfo->suspend_lock); mddev->pers->quiesce(mddev, 0); } - static void process_suspend_info(struct mddev *mddev, int slot, sector_t lo, sector_t hi) { struct md_cluster_info *cinfo = mddev->cluster_info; - struct suspend_info *s; + struct mdp_superblock_1 *sb = NULL; + struct md_rdev *rdev; if (!hi) { /* @@ -475,6 +464,12 @@ static void process_suspend_info(struct mddev *mddev, return; } + rdev_for_each(rdev, mddev) + if (rdev->raid_disk > -1 && !test_bit(Faulty, &rdev->flags)) { + sb = page_address(rdev->sb_page); + break; + } + /* * The bitmaps are not same for different nodes * if RESYNCING is happening in one node, then @@ -487,26 +482,26 @@ static void process_suspend_info(struct mddev *mddev, * sync_low/hi is used to record the region which * arrived in the previous RESYNCING message, * - * Call bitmap_sync_with_cluster to clear - * NEEDED_MASK and set RESYNC_MASK since - * resync thread is running in another node, - * so we don't need to do the resync again - * with the same section */ - md_bitmap_sync_with_cluster(mddev, cinfo->sync_low, cinfo->sync_hi, lo, hi); + * Call md_bitmap_sync_with_cluster to clear NEEDED_MASK + * and set RESYNC_MASK since resync thread is running + * in another node, so we don't need to do the resync + * again with the same section. + * + * Skip md_bitmap_sync_with_cluster in case reshape + * happening, because reshaping region is small and + * we don't want to trigger lots of WARN. + */ + if (sb && !(le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE)) + md_bitmap_sync_with_cluster(mddev, cinfo->sync_low, + cinfo->sync_hi, lo, hi); cinfo->sync_low = lo; cinfo->sync_hi = hi; - s = kzalloc(sizeof(struct suspend_info), GFP_KERNEL); - if (!s) - return; - s->slot = slot; - s->lo = lo; - s->hi = hi; mddev->pers->quiesce(mddev, 1); spin_lock_irq(&cinfo->suspend_lock); - /* Remove existing entry (if exists) before adding */ - __remove_suspend_info(cinfo, slot); - list_add(&s->list, &cinfo->suspend_list); + cinfo->suspend_from = slot; + cinfo->suspend_lo = lo; + cinfo->suspend_hi = hi; spin_unlock_irq(&cinfo->suspend_lock); mddev->pers->quiesce(mddev, 0); } @@ -612,6 +607,11 @@ static int process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg) case BITMAP_NEEDS_SYNC: __recover_slot(mddev, le32_to_cpu(msg->slot)); break; + case BITMAP_RESIZE: + if (le64_to_cpu(msg->high) != mddev->pers->size(mddev, 0, 0)) + ret = md_bitmap_resize(mddev->bitmap, + le64_to_cpu(msg->high), 0, 0); + break; default: ret = -1; pr_warn("%s:%d Received unknown message from %d\n", @@ -800,7 +800,6 @@ static int gather_all_resync_info(struct mddev *mddev, int total_slots) struct md_cluster_info *cinfo = mddev->cluster_info; int i, ret = 0; struct dlm_lock_resource *bm_lockres; - struct suspend_info *s; char str[64]; sector_t lo, hi; @@ -819,16 +818,13 @@ static int gather_all_resync_info(struct mddev *mddev, int total_slots) bm_lockres->flags |= DLM_LKF_NOQUEUE; ret = dlm_lock_sync(bm_lockres, DLM_LOCK_PW); if (ret == -EAGAIN) { - s = read_resync_info(mddev, bm_lockres); - if (s) { + if (read_resync_info(mddev, bm_lockres)) { pr_info("%s:%d Resync[%llu..%llu] in progress on %d\n", __func__, __LINE__, - (unsigned long long) s->lo, - (unsigned long long) s->hi, i); - spin_lock_irq(&cinfo->suspend_lock); - s->slot = i; - list_add(&s->list, &cinfo->suspend_list); - spin_unlock_irq(&cinfo->suspend_lock); + (unsigned long long) cinfo->suspend_lo, + (unsigned long long) cinfo->suspend_hi, + i); + cinfo->suspend_from = i; } ret = 0; lockres_free(bm_lockres); @@ -1001,10 +997,17 @@ static int leave(struct mddev *mddev) if (!cinfo) return 0; - /* BITMAP_NEEDS_SYNC message should be sent when node + /* + * BITMAP_NEEDS_SYNC message should be sent when node * is leaving the cluster with dirty bitmap, also we - * can only deliver it when dlm connection is available */ - if (cinfo->slot_number > 0 && mddev->recovery_cp != MaxSector) + * can only deliver it when dlm connection is available. + * + * Also, we should send BITMAP_NEEDS_SYNC message in + * case reshaping is interrupted. + */ + if ((cinfo->slot_number > 0 && mddev->recovery_cp != MaxSector) || + (mddev->reshape_position != MaxSector && + test_bit(MD_CLOSING, &mddev->flags))) resync_bitmap(mddev); set_bit(MD_CLUSTER_HOLDING_MUTEX_FOR_RECVD, &cinfo->state); @@ -1102,6 +1105,80 @@ static void metadata_update_cancel(struct mddev *mddev) unlock_comm(cinfo); } +static int update_bitmap_size(struct mddev *mddev, sector_t size) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + struct cluster_msg cmsg = {0}; + int ret; + + cmsg.type = cpu_to_le32(BITMAP_RESIZE); + cmsg.high = cpu_to_le64(size); + ret = sendmsg(cinfo, &cmsg, 0); + if (ret) + pr_err("%s:%d: failed to send BITMAP_RESIZE message (%d)\n", + __func__, __LINE__, ret); + return ret; +} + +static int resize_bitmaps(struct mddev *mddev, sector_t newsize, sector_t oldsize) +{ + struct bitmap_counts *counts; + char str[64]; + struct dlm_lock_resource *bm_lockres; + struct bitmap *bitmap = mddev->bitmap; + unsigned long my_pages = bitmap->counts.pages; + int i, rv; + + /* + * We need to ensure all the nodes can grow to a larger + * bitmap size before make the reshaping. + */ + rv = update_bitmap_size(mddev, newsize); + if (rv) + return rv; + + for (i = 0; i < mddev->bitmap_info.nodes; i++) { + if (i == md_cluster_ops->slot_number(mddev)) + continue; + + bitmap = get_bitmap_from_slot(mddev, i); + if (IS_ERR(bitmap)) { + pr_err("can't get bitmap from slot %d\n", i); + goto out; + } + counts = &bitmap->counts; + + /* + * If we can hold the bitmap lock of one node then + * the slot is not occupied, update the pages. + */ + snprintf(str, 64, "bitmap%04d", i); + bm_lockres = lockres_init(mddev, str, NULL, 1); + if (!bm_lockres) { + pr_err("Cannot initialize %s lock\n", str); + goto out; + } + bm_lockres->flags |= DLM_LKF_NOQUEUE; + rv = dlm_lock_sync(bm_lockres, DLM_LOCK_PW); + if (!rv) + counts->pages = my_pages; + lockres_free(bm_lockres); + + if (my_pages != counts->pages) + /* + * Let's revert the bitmap size if one node + * can't resize bitmap + */ + goto out; + } + + return 0; +out: + md_bitmap_free(bitmap); + update_bitmap_size(mddev, oldsize); + return -1; +} + /* * return 0 if all the bitmaps have the same sync_size */ @@ -1243,6 +1320,16 @@ static int resync_start(struct mddev *mddev) return dlm_lock_sync_interruptible(cinfo->resync_lockres, DLM_LOCK_EX, mddev); } +static void resync_info_get(struct mddev *mddev, sector_t *lo, sector_t *hi) +{ + struct md_cluster_info *cinfo = mddev->cluster_info; + + spin_lock_irq(&cinfo->suspend_lock); + *lo = cinfo->suspend_lo; + *hi = cinfo->suspend_hi; + spin_unlock_irq(&cinfo->suspend_lock); +} + static int resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi) { struct md_cluster_info *cinfo = mddev->cluster_info; @@ -1295,21 +1382,14 @@ static int area_resyncing(struct mddev *mddev, int direction, { struct md_cluster_info *cinfo = mddev->cluster_info; int ret = 0; - struct suspend_info *s; if ((direction == READ) && test_bit(MD_CLUSTER_SUSPEND_READ_BALANCING, &cinfo->state)) return 1; spin_lock_irq(&cinfo->suspend_lock); - if (list_empty(&cinfo->suspend_list)) - goto out; - list_for_each_entry(s, &cinfo->suspend_list, list) - if (hi > s->lo && lo < s->hi) { - ret = 1; - break; - } -out: + if (hi > cinfo->suspend_lo && lo < cinfo->suspend_hi) + ret = 1; spin_unlock_irq(&cinfo->suspend_lock); return ret; } @@ -1482,6 +1562,7 @@ static struct md_cluster_operations cluster_ops = { .resync_start = resync_start, .resync_finish = resync_finish, .resync_info_update = resync_info_update, + .resync_info_get = resync_info_get, .metadata_update_start = metadata_update_start, .metadata_update_finish = metadata_update_finish, .metadata_update_cancel = metadata_update_cancel, @@ -1492,6 +1573,7 @@ static struct md_cluster_operations cluster_ops = { .remove_disk = remove_disk, .load_bitmaps = load_bitmaps, .gather_bitmaps = gather_bitmaps, + .resize_bitmaps = resize_bitmaps, .lock_all_bitmaps = lock_all_bitmaps, .unlock_all_bitmaps = unlock_all_bitmaps, .update_size = update_size, diff --git a/drivers/md/md-cluster.h b/drivers/md/md-cluster.h index c0240708f443..a78e3021775d 100644 --- a/drivers/md/md-cluster.h +++ b/drivers/md/md-cluster.h @@ -14,6 +14,7 @@ struct md_cluster_operations { int (*leave)(struct mddev *mddev); int (*slot_number)(struct mddev *mddev); int (*resync_info_update)(struct mddev *mddev, sector_t lo, sector_t hi); + void (*resync_info_get)(struct mddev *mddev, sector_t *lo, sector_t *hi); int (*metadata_update_start)(struct mddev *mddev); int (*metadata_update_finish)(struct mddev *mddev); void (*metadata_update_cancel)(struct mddev *mddev); @@ -26,6 +27,7 @@ struct md_cluster_operations { int (*remove_disk)(struct mddev *mddev, struct md_rdev *rdev); void (*load_bitmaps)(struct mddev *mddev, int total_slots); int (*gather_bitmaps)(struct md_rdev *rdev); + int (*resize_bitmaps)(struct mddev *mddev, sector_t newsize, sector_t oldsize); int (*lock_all_bitmaps)(struct mddev *mddev); void (*unlock_all_bitmaps)(struct mddev *mddev); void (*update_size)(struct mddev *mddev, sector_t old_dev_sectors); diff --git a/drivers/md/md.c b/drivers/md/md.c index 63ceabb4e020..fc488cb30a94 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -452,10 +452,11 @@ static void md_end_flush(struct bio *fbio) rdev_dec_pending(rdev, mddev); if (atomic_dec_and_test(&fi->flush_pending)) { - if (bio->bi_iter.bi_size == 0) + if (bio->bi_iter.bi_size == 0) { /* an empty barrier - all done */ bio_endio(bio); - else { + mempool_free(fi, mddev->flush_pool); + } else { INIT_WORK(&fi->flush_work, submit_flushes); queue_work(md_wq, &fi->flush_work); } @@ -509,10 +510,11 @@ void md_flush_request(struct mddev *mddev, struct bio *bio) rcu_read_unlock(); if (atomic_dec_and_test(&fi->flush_pending)) { - if (bio->bi_iter.bi_size == 0) + if (bio->bi_iter.bi_size == 0) { /* an empty barrier - all done */ bio_endio(bio); - else { + mempool_free(fi, mddev->flush_pool); + } else { INIT_WORK(&fi->flush_work, submit_flushes); queue_work(md_wq, &fi->flush_work); } @@ -5904,14 +5906,6 @@ static void __md_stop(struct mddev *mddev) mddev->to_remove = &md_redundancy_group; module_put(pers->owner); clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); -} - -void md_stop(struct mddev *mddev) -{ - /* stop the array and free an attached data structures. - * This is called from dm-raid - */ - __md_stop(mddev); if (mddev->flush_bio_pool) { mempool_destroy(mddev->flush_bio_pool); mddev->flush_bio_pool = NULL; @@ -5920,6 +5914,14 @@ void md_stop(struct mddev *mddev) mempool_destroy(mddev->flush_pool); mddev->flush_pool = NULL; } +} + +void md_stop(struct mddev *mddev) +{ + /* stop the array and free an attached data structures. + * This is called from dm-raid + */ + __md_stop(mddev); bioset_exit(&mddev->bio_set); bioset_exit(&mddev->sync_set); } @@ -8370,9 +8372,17 @@ void md_do_sync(struct md_thread *thread) else if (!mddev->bitmap) j = mddev->recovery_cp; - } else if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) + } else if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) { max_sectors = mddev->resync_max_sectors; - else { + /* + * If the original node aborts reshaping then we continue the + * reshaping, so set j again to avoid restart reshape from the + * first beginning + */ + if (mddev_is_clustered(mddev) && + mddev->reshape_position != MaxSector) + j = mddev->reshape_position; + } else { /* recovery follows the physical size of devices */ max_sectors = mddev->dev_sectors; j = MaxSector; @@ -8623,8 +8633,10 @@ void md_do_sync(struct md_thread *thread) mddev_lock_nointr(mddev); md_set_array_sectors(mddev, mddev->pers->size(mddev, 0, 0)); mddev_unlock(mddev); - set_capacity(mddev->gendisk, mddev->array_sectors); - revalidate_disk(mddev->gendisk); + if (!mddev_is_clustered(mddev)) { + set_capacity(mddev->gendisk, mddev->array_sectors); + revalidate_disk(mddev->gendisk); + } } spin_lock(&mddev->lock); @@ -8790,6 +8802,18 @@ static void md_start_sync(struct work_struct *ws) */ void md_check_recovery(struct mddev *mddev) { + if (test_bit(MD_ALLOW_SB_UPDATE, &mddev->flags) && mddev->sb_flags) { + /* Write superblock - thread that called mddev_suspend() + * holds reconfig_mutex for us. + */ + set_bit(MD_UPDATING_SB, &mddev->flags); + smp_mb__after_atomic(); + if (test_bit(MD_ALLOW_SB_UPDATE, &mddev->flags)) + md_update_sb(mddev, 0); + clear_bit_unlock(MD_UPDATING_SB, &mddev->flags); + wake_up(&mddev->sb_wait); + } + if (mddev->suspended) return; @@ -8949,16 +8973,6 @@ void md_check_recovery(struct mddev *mddev) unlock: wake_up(&mddev->sb_wait); mddev_unlock(mddev); - } else if (test_bit(MD_ALLOW_SB_UPDATE, &mddev->flags) && mddev->sb_flags) { - /* Write superblock - thread that called mddev_suspend() - * holds reconfig_mutex for us. - */ - set_bit(MD_UPDATING_SB, &mddev->flags); - smp_mb__after_atomic(); - if (test_bit(MD_ALLOW_SB_UPDATE, &mddev->flags)) - md_update_sb(mddev, 0); - clear_bit_unlock(MD_UPDATING_SB, &mddev->flags); - wake_up(&mddev->sb_wait); } } EXPORT_SYMBOL(md_check_recovery); @@ -8966,6 +8980,8 @@ EXPORT_SYMBOL(md_check_recovery); void md_reap_sync_thread(struct mddev *mddev) { struct md_rdev *rdev; + sector_t old_dev_sectors = mddev->dev_sectors; + bool is_reshaped = false; /* resync has finished, collect result */ md_unregister_thread(&mddev->sync_thread); @@ -8980,8 +8996,11 @@ void md_reap_sync_thread(struct mddev *mddev) } } if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && - mddev->pers->finish_reshape) + mddev->pers->finish_reshape) { mddev->pers->finish_reshape(mddev); + if (mddev_is_clustered(mddev)) + is_reshaped = true; + } /* If array is no-longer degraded, then any saved_raid_disk * information must be scrapped. @@ -9002,6 +9021,14 @@ void md_reap_sync_thread(struct mddev *mddev) clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery); clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); + /* + * We call md_cluster_ops->update_size here because sync_size could + * be changed by md_update_sb, and MD_RECOVERY_RESHAPE is cleared, + * so it is time to update size across cluster. + */ + if (mddev_is_clustered(mddev) && is_reshaped + && !test_bit(MD_CLOSING, &mddev->flags)) + md_cluster_ops->update_size(mddev, old_dev_sectors); wake_up(&resync_wait); /* flag recovery needed just to double check */ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); @@ -9201,8 +9228,12 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev) } if (role != rdev2->raid_disk) { - /* got activated */ - if (rdev2->raid_disk == -1 && role != 0xffff) { + /* + * got activated except reshape is happening. + */ + if (rdev2->raid_disk == -1 && role != 0xffff && + !(le32_to_cpu(sb->feature_map) & + MD_FEATURE_RESHAPE_ACTIVE)) { rdev2->saved_raid_disk = role; ret = remove_and_add_spares(mddev, rdev2); pr_info("Activated spare: %s\n", @@ -9228,6 +9259,30 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev) if (mddev->raid_disks != le32_to_cpu(sb->raid_disks)) update_raid_disks(mddev, le32_to_cpu(sb->raid_disks)); + /* + * Since mddev->delta_disks has already updated in update_raid_disks, + * so it is time to check reshape. + */ + if (test_bit(MD_RESYNCING_REMOTE, &mddev->recovery) && + (le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE)) { + /* + * reshape is happening in the remote node, we need to + * update reshape_position and call start_reshape. + */ + mddev->reshape_position = sb->reshape_position; + if (mddev->pers->update_reshape_pos) + mddev->pers->update_reshape_pos(mddev); + if (mddev->pers->start_reshape) + mddev->pers->start_reshape(mddev); + } else if (test_bit(MD_RESYNCING_REMOTE, &mddev->recovery) && + mddev->reshape_position != MaxSector && + !(le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE)) { + /* reshape is just done in another node. */ + mddev->reshape_position = MaxSector; + if (mddev->pers->update_reshape_pos) + mddev->pers->update_reshape_pos(mddev); + } + /* Finally set the event to be up to date */ mddev->events = le64_to_cpu(sb->events); } diff --git a/drivers/md/md.h b/drivers/md/md.h index 8afd6bfdbfb9..c52afb52c776 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -557,6 +557,7 @@ struct md_personality int (*check_reshape) (struct mddev *mddev); int (*start_reshape) (struct mddev *mddev); void (*finish_reshape) (struct mddev *mddev); + void (*update_reshape_pos) (struct mddev *mddev); /* quiesce suspends or resumes internal processing. * 1 - stop new actions and wait for action io to complete * 0 - return to normal behaviour diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 4e990246225e..1d54109071cc 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1734,6 +1734,7 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev) */ if (rdev->saved_raid_disk >= 0 && rdev->saved_raid_disk >= first && + rdev->saved_raid_disk < conf->raid_disks && conf->mirrors[rdev->saved_raid_disk].rdev == NULL) first = last = rdev->saved_raid_disk; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index d6f7978b4449..b98e746e7fc4 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -25,6 +25,7 @@ #include <linux/seq_file.h> #include <linux/ratelimit.h> #include <linux/kthread.h> +#include <linux/raid/md_p.h> #include <trace/events/block.h> #include "md.h" #include "raid10.h" @@ -1808,6 +1809,7 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) first = last = rdev->raid_disk; if (rdev->saved_raid_disk >= first && + rdev->saved_raid_disk < conf->geo.raid_disks && conf->mirrors[rdev->saved_raid_disk].rdev == NULL) mirror = rdev->saved_raid_disk; else @@ -3079,6 +3081,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, sector_t sect; int must_sync; int any_working; + int need_recover = 0; + int need_replace = 0; struct raid10_info *mirror = &conf->mirrors[i]; struct md_rdev *mrdev, *mreplace; @@ -3086,11 +3090,15 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, mrdev = rcu_dereference(mirror->rdev); mreplace = rcu_dereference(mirror->replacement); - if ((mrdev == NULL || - test_bit(Faulty, &mrdev->flags) || - test_bit(In_sync, &mrdev->flags)) && - (mreplace == NULL || - test_bit(Faulty, &mreplace->flags))) { + if (mrdev != NULL && + !test_bit(Faulty, &mrdev->flags) && + !test_bit(In_sync, &mrdev->flags)) + need_recover = 1; + if (mreplace != NULL && + !test_bit(Faulty, &mreplace->flags)) + need_replace = 1; + + if (!need_recover && !need_replace) { rcu_read_unlock(); continue; } @@ -3213,7 +3221,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, r10_bio->devs[1].devnum = i; r10_bio->devs[1].addr = to_addr; - if (!test_bit(In_sync, &mrdev->flags)) { + if (need_recover) { bio = r10_bio->devs[1].bio; bio->bi_next = biolist; biolist = bio; @@ -3230,16 +3238,11 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, bio = r10_bio->devs[1].repl_bio; if (bio) bio->bi_end_io = NULL; - /* Note: if mreplace != NULL, then bio + /* Note: if need_replace, then bio * cannot be NULL as r10buf_pool_alloc will * have allocated it. - * So the second test here is pointless. - * But it keeps semantic-checkers happy, and - * this comment keeps human reviewers - * happy. */ - if (mreplace == NULL || bio == NULL || - test_bit(Faulty, &mreplace->flags)) + if (!need_replace) break; bio->bi_next = biolist; biolist = bio; @@ -4286,12 +4289,46 @@ static int raid10_start_reshape(struct mddev *mddev) spin_unlock_irq(&conf->device_lock); if (mddev->delta_disks && mddev->bitmap) { - ret = md_bitmap_resize(mddev->bitmap, - raid10_size(mddev, 0, conf->geo.raid_disks), - 0, 0); + struct mdp_superblock_1 *sb = NULL; + sector_t oldsize, newsize; + + oldsize = raid10_size(mddev, 0, 0); + newsize = raid10_size(mddev, 0, conf->geo.raid_disks); + + if (!mddev_is_clustered(mddev)) { + ret = md_bitmap_resize(mddev->bitmap, newsize, 0, 0); + if (ret) + goto abort; + else + goto out; + } + + rdev_for_each(rdev, mddev) { + if (rdev->raid_disk > -1 && + !test_bit(Faulty, &rdev->flags)) + sb = page_address(rdev->sb_page); + } + + /* + * some node is already performing reshape, and no need to + * call md_bitmap_resize again since it should be called when + * receiving BITMAP_RESIZE msg + */ + if ((sb && (le32_to_cpu(sb->feature_map) & + MD_FEATURE_RESHAPE_ACTIVE)) || (oldsize == newsize)) + goto out; + + ret = md_bitmap_resize(mddev->bitmap, newsize, 0, 0); if (ret) goto abort; + + ret = md_cluster_ops->resize_bitmaps(mddev, newsize, oldsize); + if (ret) { + md_bitmap_resize(mddev->bitmap, oldsize, 0, 0); + goto abort; + } } +out: if (mddev->delta_disks > 0) { rdev_for_each(rdev, mddev) if (rdev->raid_disk < 0 && @@ -4568,6 +4605,32 @@ read_more: r10_bio->master_bio = read_bio; r10_bio->read_slot = r10_bio->devs[r10_bio->read_slot].devnum; + /* + * Broadcast RESYNC message to other nodes, so all nodes would not + * write to the region to avoid conflict. + */ + if (mddev_is_clustered(mddev) && conf->cluster_sync_high <= sector_nr) { + struct mdp_superblock_1 *sb = NULL; + int sb_reshape_pos = 0; + + conf->cluster_sync_low = sector_nr; + conf->cluster_sync_high = sector_nr + CLUSTER_RESYNC_WINDOW_SECTORS; + sb = page_address(rdev->sb_page); + if (sb) { + sb_reshape_pos = le64_to_cpu(sb->reshape_position); + /* + * Set cluster_sync_low again if next address for array + * reshape is less than cluster_sync_low. Since we can't + * update cluster_sync_low until it has finished reshape. + */ + if (sb_reshape_pos < conf->cluster_sync_low) + conf->cluster_sync_low = sb_reshape_pos; + } + + md_cluster_ops->resync_info_update(mddev, conf->cluster_sync_low, + conf->cluster_sync_high); + } + /* Now find the locations in the new layout */ __raid10_find_phys(&conf->geo, r10_bio); @@ -4719,6 +4782,19 @@ static void end_reshape(struct r10conf *conf) conf->fullsync = 0; } +static void raid10_update_reshape_pos(struct mddev *mddev) +{ + struct r10conf *conf = mddev->private; + sector_t lo, hi; + + md_cluster_ops->resync_info_get(mddev, &lo, &hi); + if (((mddev->reshape_position <= hi) && (mddev->reshape_position >= lo)) + || mddev->reshape_position == MaxSector) + conf->reshape_progress = mddev->reshape_position; + else + WARN_ON_ONCE(1); +} + static int handle_reshape_read_error(struct mddev *mddev, struct r10bio *r10_bio) { @@ -4887,6 +4963,7 @@ static struct md_personality raid10_personality = .check_reshape = raid10_check_reshape, .start_reshape = raid10_start_reshape, .finish_reshape = raid10_finish_reshape, + .update_reshape_pos = raid10_update_reshape_pos, .congested = raid10_congested, }; diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index e6e925add700..ec3a5ef7fee0 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -3151,8 +3151,6 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev) set_bit(MD_HAS_JOURNAL, &conf->mddev->flags); return 0; - rcu_assign_pointer(conf->log, NULL); - md_unregister_thread(&log->reclaim_thread); reclaim_thread: mempool_exit(&log->meta_pool); out_mempool: diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index e4e98f47865d..4990f0319f6c 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -2681,6 +2681,18 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev) pr_debug("raid456: error called\n"); spin_lock_irqsave(&conf->device_lock, flags); + + if (test_bit(In_sync, &rdev->flags) && + mddev->degraded == conf->max_degraded) { + /* + * Don't allow to achieve failed state + * Don't try to recover this device + */ + conf->recovery_disabled = mddev->recovery_disabled; + spin_unlock_irqrestore(&conf->device_lock, flags); + return; + } + set_bit(Faulty, &rdev->flags); clear_bit(In_sync, &rdev->flags); mddev->degraded = raid5_calc_degraded(conf); diff --git a/drivers/misc/ocxl/config.c b/drivers/misc/ocxl/config.c index 2e30de9c694a..57a6bb1fd3c9 100644 --- a/drivers/misc/ocxl/config.c +++ b/drivers/misc/ocxl/config.c @@ -280,7 +280,9 @@ int ocxl_config_check_afu_index(struct pci_dev *dev, u32 val; int rc, templ_major, templ_minor, len; - pci_write_config_word(dev, fn->dvsec_afu_info_pos, afu_idx); + pci_write_config_byte(dev, + fn->dvsec_afu_info_pos + OCXL_DVSEC_AFU_INFO_AFU_IDX, + afu_idx); rc = read_afu_info(dev, fn, OCXL_DVSEC_TEMPL_VERSION, &val); if (rc) return rc; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index d96a84a62d78..0cc911f928b1 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -119,7 +119,6 @@ #include <linux/tcp.h> #include <linux/if_vlan.h> #include <linux/interrupt.h> -#include <net/busy_poll.h> #include <linux/clk.h> #include <linux/if_ether.h> #include <linux/net_tstamp.h> diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 5a727d4729da..686899d7e555 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -27,7 +27,6 @@ #include <net/tcp.h> #include <net/ipv6.h> #include <net/ip6_checksum.h> -#include <net/busy_poll.h> #include <linux/prefetch.h> #include "bnx2x_cmn.h" #include "bnx2x_init.h" diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 35564a8a48f9..a6cbaca37e94 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -341,7 +341,7 @@ static struct device_node *bcmgenet_mii_of_find_mdio(struct bcmgenet_priv *priv) if (!compat) return NULL; - priv->mdio_dn = of_find_compatible_node(dn, NULL, compat); + priv->mdio_dn = of_get_compatible_child(dn, compat); kfree(compat); if (!priv->mdio_dn) { dev_err(kdev, "unable to find MDIO bus node\n"); diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 8f5bf9166c11..1d86b4d5645a 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1684,7 +1684,7 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev) padlen = 0; /* No room for FCS, need to reallocate skb. */ else - padlen = ETH_FCS_LEN - tailroom; + padlen = ETH_FCS_LEN; } else { /* Add room for FCS. */ padlen += ETH_FCS_LEN; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c index f7e363b90fe0..dca6f2326c26 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c @@ -859,10 +859,12 @@ static int hclge_log_and_clear_ppp_error(struct hclge_dev *hdev, u32 cmd, reset_level = HNAE3_FUNC_RESET; } - err_sts = (le32_to_cpu(desc[0].data[4]) >> 8) & 0x3; - if (err_sts) { - hclge_log_error(dev, hw_err_lst3, err_sts); - reset_level = HNAE3_FUNC_RESET; + if (cmd == HCLGE_PPP_CMD0_INT_CMD) { + err_sts = (le32_to_cpu(desc[0].data[4]) >> 8) & 0x3; + if (err_sts) { + hclge_log_error(dev, hw_err_lst3, err_sts); + reset_level = HNAE3_FUNC_RESET; + } } /* clear PPP INT */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 740ea58ba938..aef3c89ee79c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2,7 +2,6 @@ /* Copyright(c) 2013 - 2018 Intel Corporation. */ #include <linux/prefetch.h> -#include <net/busy_poll.h> #include <linux/bpf_trace.h> #include <net/xdp.h> #include "i40e.h" diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index edc349f49748..fb9bfad96daf 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -2,7 +2,6 @@ /* Copyright(c) 2013 - 2018 Intel Corporation. */ #include <linux/prefetch.h> -#include <net/busy_poll.h> #include "iavf.h" #include "iavf_trace.h" diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index c52f450f2c0d..8cd6a2401fd9 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -43,6 +43,23 @@ static enum ice_status ice_set_mac_type(struct ice_hw *hw) } /** + * ice_dev_onetime_setup - Temporary HW/FW workarounds + * @hw: pointer to the HW structure + * + * This function provides temporary workarounds for certain issues + * that are expected to be fixed in the HW/FW. + */ +void ice_dev_onetime_setup(struct ice_hw *hw) +{ + /* configure Rx - set non pxe mode */ + wr32(hw, GLLAN_RCTL_0, 0x1); + +#define MBX_PF_VT_PFALLOC 0x00231E80 + /* set VFs per PF */ + wr32(hw, MBX_PF_VT_PFALLOC, rd32(hw, PF_VT_PFALLOC_HIF)); +} + +/** * ice_clear_pf_cfg - Clear PF configuration * @hw: pointer to the hardware structure * @@ -218,7 +235,7 @@ static enum ice_media_type ice_get_media_type(struct ice_port_info *pi) * * Get Link Status (0x607). Returns the link status of the adapter. */ -enum ice_status +static enum ice_status ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse, struct ice_link_status *link, struct ice_sq_cd *cd) { @@ -740,6 +757,8 @@ enum ice_status ice_init_hw(struct ice_hw *hw) if (status) goto err_unroll_sched; + ice_dev_onetime_setup(hw); + /* Get MAC information */ /* A single port can report up to two (LAN and WoL) addresses */ mac_buf = devm_kcalloc(ice_hw_to_dev(hw), 2, @@ -1531,9 +1550,7 @@ ice_aq_discover_caps(struct ice_hw *hw, void *buf, u16 buf_size, u32 *cap_count, if (!status) ice_parse_caps(hw, buf, le32_to_cpu(cmd->count), opc); else if (hw->adminq.sq_last_status == ICE_AQ_RC_ENOMEM) - *cap_count = - DIV_ROUND_UP(le16_to_cpu(desc.datalen), - sizeof(struct ice_aqc_list_caps_elem)); + *cap_count = le32_to_cpu(cmd->count); return status; } @@ -1988,33 +2005,6 @@ ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link, } /** - * ice_aq_set_event_mask - * @hw: pointer to the hw struct - * @port_num: port number of the physical function - * @mask: event mask to be set - * @cd: pointer to command details structure or NULL - * - * Set event mask (0x0613) - */ -enum ice_status -ice_aq_set_event_mask(struct ice_hw *hw, u8 port_num, u16 mask, - struct ice_sq_cd *cd) -{ - struct ice_aqc_set_event_mask *cmd; - struct ice_aq_desc desc; - - cmd = &desc.params.set_event_mask; - - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_event_mask); - - cmd->lport_num = port_num; - - cmd->event_mask = cpu_to_le16(mask); - - return ice_aq_send_cmd(hw, &desc, NULL, 0, cd); -} - -/** * __ice_aq_get_set_rss_lut * @hw: pointer to the hardware structure * @vsi_id: VSI FW index diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 1900681289a4..cf760c24a6aa 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -34,6 +34,9 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, struct ice_sq_cd *cd); void ice_clear_pxe_mode(struct ice_hw *hw); enum ice_status ice_get_caps(struct ice_hw *hw); + +void ice_dev_onetime_setup(struct ice_hw *hw); + enum ice_status ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx, u32 rxq_index); @@ -83,12 +86,6 @@ enum ice_status ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link, struct ice_sq_cd *cd); enum ice_status -ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse, - struct ice_link_status *link, struct ice_sq_cd *cd); -enum ice_status -ice_aq_set_event_mask(struct ice_hw *hw, u8 port_num, u16 mask, - struct ice_sq_cd *cd); -enum ice_status ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids, u32 *q_teids, enum ice_disq_rst_src rst_src, u16 vmvf_num, struct ice_sq_cd *cmd_details); diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h index 437f832fd7c4..0038a4109c99 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.h +++ b/drivers/net/ethernet/intel/ice/ice_controlq.h @@ -19,11 +19,10 @@ /* Defines that help manage the driver vs FW API checks. * Take a look at ice_aq_ver_check in ice_controlq.c for actual usage. - * */ #define EXP_FW_API_VER_BRANCH 0x00 -#define EXP_FW_API_VER_MAJOR 0x00 -#define EXP_FW_API_VER_MINOR 0x01 +#define EXP_FW_API_VER_MAJOR 0x01 +#define EXP_FW_API_VER_MINOR 0x03 /* Different control queue types: These are mainly for SW consumption. */ enum ice_ctl_q { diff --git a/drivers/net/ethernet/intel/ice/ice_devids.h b/drivers/net/ethernet/intel/ice/ice_devids.h index a6f0a5c0c305..f8d5c661d0ba 100644 --- a/drivers/net/ethernet/intel/ice/ice_devids.h +++ b/drivers/net/ethernet/intel/ice/ice_devids.h @@ -6,10 +6,10 @@ /* Device IDs */ /* Intel(R) Ethernet Controller E810-C for backplane */ -#define ICE_DEV_ID_C810_BACKPLANE 0x1591 +#define ICE_DEV_ID_E810C_BACKPLANE 0x1591 /* Intel(R) Ethernet Controller E810-C for QSFP */ -#define ICE_DEV_ID_C810_QSFP 0x1592 +#define ICE_DEV_ID_E810C_QSFP 0x1592 /* Intel(R) Ethernet Controller E810-C for SFP */ -#define ICE_DEV_ID_C810_SFP 0x1593 +#define ICE_DEV_ID_E810C_SFP 0x1593 #endif /* _ICE_DEVIDS_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index a6679a9bfd3a..5fdea6ec7675 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -157,6 +157,13 @@ #define VPINT_ALLOC_LAST_S 12 #define VPINT_ALLOC_LAST_M ICE_M(0x7FF, 12) #define VPINT_ALLOC_VALID_M BIT(31) +#define VPINT_ALLOC_PCI(_VF) (0x0009D000 + ((_VF) * 4)) +#define VPINT_ALLOC_PCI_FIRST_S 0 +#define VPINT_ALLOC_PCI_FIRST_M ICE_M(0x7FF, 0) +#define VPINT_ALLOC_PCI_LAST_S 12 +#define VPINT_ALLOC_PCI_LAST_M ICE_M(0x7FF, 12) +#define VPINT_ALLOC_PCI_VALID_M BIT(31) +#define GLLAN_RCTL_0 0x002941F8 #define QRX_CONTEXT(_i, _QRX) (0x00280000 + ((_i) * 8192 + (_QRX) * 4)) #define QRX_CTRL(_QRX) (0x00120000 + ((_QRX) * 4)) #define QRX_CTRL_MAX_INDEX 2047 @@ -320,6 +327,7 @@ #define GLV_UPRCL(_i) (0x003B2000 + ((_i) * 8)) #define GLV_UPTCH(_i) (0x0030A004 + ((_i) * 8)) #define GLV_UPTCL(_i) (0x0030A000 + ((_i) * 8)) +#define PF_VT_PFALLOC_HIF 0x0009DD80 #define VSIQF_HKEY_MAX_INDEX 12 #define VSIQF_HLUT_MAX_INDEX 15 #define VFINT_DYN_CTLN(_i) (0x00003800 + ((_i) * 4)) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 49f1940772ed..5bacad01f0c9 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -433,7 +433,7 @@ int ice_vsi_clear(struct ice_vsi *vsi) * @irq: interrupt number * @data: pointer to a q_vector */ -irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data) +static irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data) { struct ice_q_vector *q_vector = (struct ice_q_vector *)data; @@ -2529,6 +2529,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi) vsi->hw_base_vector = 0; ice_vsi_clear_rings(vsi); ice_vsi_free_arrays(vsi, false); + ice_dev_onetime_setup(&vsi->back->hw); ice_vsi_set_num_qs(vsi); /* Initialize VSI struct elements and create VSI in FW */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index 677db40338f5..3831b4f0960a 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -73,5 +73,4 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc); int ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena); -irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data); #endif /* !_ICE_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 8f61b375e768..05993451147a 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -457,35 +457,6 @@ static void ice_reset_subtask(struct ice_pf *pf) } /** - * ice_watchdog_subtask - periodic tasks not using event driven scheduling - * @pf: board private structure - */ -static void ice_watchdog_subtask(struct ice_pf *pf) -{ - int i; - - /* if interface is down do nothing */ - if (test_bit(__ICE_DOWN, pf->state) || - test_bit(__ICE_CFG_BUSY, pf->state)) - return; - - /* make sure we don't do these things too often */ - if (time_before(jiffies, - pf->serv_tmr_prev + pf->serv_tmr_period)) - return; - - pf->serv_tmr_prev = jiffies; - - /* Update the stats for active netdevs so the network stack - * can look at updated numbers whenever it cares to - */ - ice_update_pf_stats(pf); - for (i = 0; i < pf->num_alloc_vsi; i++) - if (pf->vsi[i] && pf->vsi[i]->netdev) - ice_update_vsi_stats(pf->vsi[i]); -} - -/** * ice_print_link_msg - print link up or down message * @vsi: the VSI whose link status is being queried * @isup: boolean for if the link is now up or down @@ -555,36 +526,6 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup) } /** - * ice_init_link_events - enable/initialize link events - * @pi: pointer to the port_info instance - * - * Returns -EIO on failure, 0 on success - */ -static int ice_init_link_events(struct ice_port_info *pi) -{ - u16 mask; - - mask = ~((u16)(ICE_AQ_LINK_EVENT_UPDOWN | ICE_AQ_LINK_EVENT_MEDIA_NA | - ICE_AQ_LINK_EVENT_MODULE_QUAL_FAIL)); - - if (ice_aq_set_event_mask(pi->hw, pi->lport, mask, NULL)) { - dev_dbg(ice_hw_to_dev(pi->hw), - "Failed to set link event mask for port %d\n", - pi->lport); - return -EIO; - } - - if (ice_aq_get_link_info(pi, true, NULL, NULL)) { - dev_dbg(ice_hw_to_dev(pi->hw), - "Failed to enable link events for port %d\n", - pi->lport); - return -EIO; - } - - return 0; -} - -/** * ice_vsi_link_event - update the vsi's netdev * @vsi: the vsi on which the link event occurred * @link_up: whether or not the vsi needs to be set up or down @@ -671,27 +612,35 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi) } /** - * ice_handle_link_event - handle link event via ARQ - * @pf: pf that the link event is associated with - * - * Return -EINVAL if port_info is null - * Return status on succes + * ice_watchdog_subtask - periodic tasks not using event driven scheduling + * @pf: board private structure */ -static int ice_handle_link_event(struct ice_pf *pf) +static void ice_watchdog_subtask(struct ice_pf *pf) { - struct ice_port_info *port_info; - int status; + int i; - port_info = pf->hw.port_info; - if (!port_info) - return -EINVAL; + /* if interface is down do nothing */ + if (test_bit(__ICE_DOWN, pf->state) || + test_bit(__ICE_CFG_BUSY, pf->state)) + return; - status = ice_link_event(pf, port_info); - if (status) - dev_dbg(&pf->pdev->dev, - "Could not process link event, error %d\n", status); + /* make sure we don't do these things too often */ + if (time_before(jiffies, + pf->serv_tmr_prev + pf->serv_tmr_period)) + return; - return status; + pf->serv_tmr_prev = jiffies; + + if (ice_link_event(pf, pf->hw.port_info)) + dev_dbg(&pf->pdev->dev, "ice_link_event failed\n"); + + /* Update the stats for active netdevs so the network stack + * can look at updated numbers whenever it cares to + */ + ice_update_pf_stats(pf); + for (i = 0; i < pf->num_alloc_vsi; i++) + if (pf->vsi[i] && pf->vsi[i]->netdev) + ice_update_vsi_stats(pf->vsi[i]); } /** @@ -797,11 +746,6 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) opcode = le16_to_cpu(event.desc.opcode); switch (opcode) { - case ice_aqc_opc_get_link_status: - if (ice_handle_link_event(pf)) - dev_err(&pf->pdev->dev, - "Could not handle link event\n"); - break; case ice_mbx_opc_send_msg_to_pf: ice_vc_process_vf_msg(pf, &event); break; @@ -2207,12 +2151,6 @@ static int ice_probe(struct pci_dev *pdev, /* since everything is good, start the service timer */ mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period)); - err = ice_init_link_events(pf->hw.port_info); - if (err) { - dev_err(&pdev->dev, "ice_init_link_events failed: %d\n", err); - goto err_alloc_sw_unroll; - } - return 0; err_alloc_sw_unroll: @@ -2271,9 +2209,9 @@ static void ice_remove(struct pci_dev *pdev) * Class, Class Mask, private data (not used) } */ static const struct pci_device_id ice_pci_tbl[] = { - { PCI_VDEVICE(INTEL, ICE_DEV_ID_C810_BACKPLANE), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_C810_QSFP), 0 }, - { PCI_VDEVICE(INTEL, ICE_DEV_ID_C810_SFP), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_BACKPLANE), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_QSFP), 0 }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_SFP), 0 }, /* required last entry */ { 0, } }; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index c25e486706f3..45f10f8f01dc 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -173,6 +173,7 @@ static void ice_dis_vf_mappings(struct ice_vf *vf) vsi = pf->vsi[vf->lan_vsi_idx]; wr32(hw, VPINT_ALLOC(vf->vf_id), 0); + wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), 0); first = vf->first_vector_idx; last = first + pf->num_vf_msix - 1; @@ -519,6 +520,10 @@ static void ice_ena_vf_mappings(struct ice_vf *vf) VPINT_ALLOC_VALID_M); wr32(hw, VPINT_ALLOC(vf->vf_id), reg); + reg = (((first << VPINT_ALLOC_PCI_FIRST_S) & VPINT_ALLOC_PCI_FIRST_M) | + ((last << VPINT_ALLOC_PCI_LAST_S) & VPINT_ALLOC_PCI_LAST_M) | + VPINT_ALLOC_PCI_VALID_M); + wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), reg); /* map the interrupts to its functions */ for (v = first; v <= last; v++) { reg = (((abs_vf_id << GLINT_VECT2FUNC_VF_NUM_S) & @@ -528,10 +533,11 @@ static void ice_ena_vf_mappings(struct ice_vf *vf) wr32(hw, GLINT_VECT2FUNC(v), reg); } + /* set regardless of mapping mode */ + wr32(hw, VPLAN_TXQ_MAPENA(vf->vf_id), VPLAN_TXQ_MAPENA_TX_ENA_M); + /* VF Tx queues allocation */ if (vsi->tx_mapping_mode == ICE_VSI_MAP_CONTIG) { - wr32(hw, VPLAN_TXQ_MAPENA(vf->vf_id), - VPLAN_TXQ_MAPENA_TX_ENA_M); /* set the VF PF Tx queue range * VFNUMQ value should be set to (number of queues - 1). A value * of 0 means 1 queue and a value of 255 means 256 queues @@ -546,10 +552,11 @@ static void ice_ena_vf_mappings(struct ice_vf *vf) "Scattered mode for VF Tx queues is not yet implemented\n"); } + /* set regardless of mapping mode */ + wr32(hw, VPLAN_RXQ_MAPENA(vf->vf_id), VPLAN_RXQ_MAPENA_RX_ENA_M); + /* VF Rx queues allocation */ if (vsi->rx_mapping_mode == ICE_VSI_MAP_CONTIG) { - wr32(hw, VPLAN_RXQ_MAPENA(vf->vf_id), - VPLAN_RXQ_MAPENA_RX_ENA_M); /* set the VF PF Rx queue range * VFNUMQ value should be set to (number of queues - 1). A value * of 0 means 1 queue and a value of 255 means 256 queues diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 7a7679e7be84..ec1b87cc4410 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -30,7 +30,6 @@ #include "ixgbe_ipsec.h" #include <net/xdp.h> -#include <net/busy_poll.h> /* common prefix used by pr_<> macros */ #undef pr_fmt diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 8890c95831ca..a5ab7eff2301 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -573,7 +573,7 @@ static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req, sizeof(struct nix_cq_ctx_s)); else if (req->ctype == NIX_AQ_CTYPE_RSS) memcpy(&rsp->rss, ctx, - sizeof(struct nix_cq_ctx_s)); + sizeof(struct nix_rsse_s)); else if (req->ctype == NIX_AQ_CTYPE_MCE) memcpy(&rsp->mce, ctx, sizeof(struct nix_rx_mce_s)); @@ -1294,7 +1294,7 @@ static int nix_update_mce_list(struct nix_mce_list *mce_list, return 0; /* Add a new one to the list, at the tail */ - mce = kzalloc(sizeof(*mce), GFP_KERNEL); + mce = kzalloc(sizeof(*mce), GFP_ATOMIC); if (!mce) return -ENOMEM; mce->idx = idx; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index fe49384eba48..b744cd49a785 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -39,7 +39,6 @@ #include <linux/slab.h> #include <linux/hash.h> #include <net/ip.h> -#include <net/busy_poll.h> #include <net/vxlan.h> #include <net/devlink.h> diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index a1aeeb8094c3..5a6d0919533d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -31,7 +31,6 @@ * */ -#include <net/busy_poll.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <linux/mlx4/cq.h> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 2f7fb8de6967..94224c22ecc3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -34,7 +34,6 @@ #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/tcp.h> -#include <net/busy_poll.h> #include <net/ip6_checksum.h> #include <net/page_pool.h> #include <net/inet_ecn.h> diff --git a/drivers/net/ethernet/microchip/Kconfig b/drivers/net/ethernet/microchip/Kconfig index 16bd3f44dbe8..cf1d49149cc8 100644 --- a/drivers/net/ethernet/microchip/Kconfig +++ b/drivers/net/ethernet/microchip/Kconfig @@ -5,7 +5,6 @@ config NET_VENDOR_MICROCHIP bool "Microchip devices" default y - depends on SPI ---help--- If you have a network (Ethernet) card belonging to this class, say Y. diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index b2d2ec8c11e2..5f384f73007d 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -70,7 +70,6 @@ #include <net/tcp.h> #include <asm/byteorder.h> #include <asm/processor.h> -#include <net/busy_poll.h> #include "myri10ge_mcp.h" #include "myri10ge_mcp_gen_header.h" diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 006b0aa8cec3..1fd01688d37b 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -4161,10 +4161,15 @@ static void rtl_wol_suspend_quirk(struct rtl8169_private *tp) static bool rtl_wol_pll_power_down(struct rtl8169_private *tp) { - if (!netif_running(tp->dev) || !__rtl8169_get_wol(tp)) + struct phy_device *phydev; + + if (!__rtl8169_get_wol(tp)) return false; - phy_speed_down(tp->dev->phydev, false); + /* phydev may not be attached to netdevice */ + phydev = mdiobus_get_phy(tp->mii_bus, 0); + + phy_speed_down(phydev, false); rtl_wol_suspend_quirk(tp); return true; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index f9a61f90cfbc..0f660af01a4b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -714,8 +714,9 @@ static int get_ephy_nodes(struct stmmac_priv *priv) return -ENODEV; } - mdio_internal = of_find_compatible_node(mdio_mux, NULL, + mdio_internal = of_get_compatible_child(mdio_mux, "allwinner,sun8i-h3-mdio-internal"); + of_node_put(mdio_mux); if (!mdio_internal) { dev_err(priv->device, "Cannot get internal_mdio node\n"); return -ENODEV; @@ -729,13 +730,20 @@ static int get_ephy_nodes(struct stmmac_priv *priv) gmac->rst_ephy = of_reset_control_get_exclusive(iphynode, NULL); if (IS_ERR(gmac->rst_ephy)) { ret = PTR_ERR(gmac->rst_ephy); - if (ret == -EPROBE_DEFER) + if (ret == -EPROBE_DEFER) { + of_node_put(iphynode); + of_node_put(mdio_internal); return ret; + } continue; } dev_info(priv->device, "Found internal PHY node\n"); + of_node_put(iphynode); + of_node_put(mdio_internal); return 0; } + + of_node_put(mdio_internal); return -ENODEV; } diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index e1225545362d..d7636ff03bc7 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -329,7 +329,7 @@ struct phy_driver genphy_10g_driver = { .name = "Generic 10G PHY", .soft_reset = gen10g_no_soft_reset, .config_init = gen10g_config_init, - .features = 0, + .features = PHY_10GBIT_FEATURES, .config_aneg = gen10g_config_aneg, .read_status = gen10g_read_status, .suspend = gen10g_suspend, diff --git a/drivers/nfc/nfcmrvl/uart.c b/drivers/nfc/nfcmrvl/uart.c index 91162f8e0366..9a22056e8d9e 100644 --- a/drivers/nfc/nfcmrvl/uart.c +++ b/drivers/nfc/nfcmrvl/uart.c @@ -73,10 +73,9 @@ static int nfcmrvl_uart_parse_dt(struct device_node *node, struct device_node *matched_node; int ret; - matched_node = of_find_compatible_node(node, NULL, "marvell,nfc-uart"); + matched_node = of_get_compatible_child(node, "marvell,nfc-uart"); if (!matched_node) { - matched_node = of_find_compatible_node(node, NULL, - "mrvl,nfc-uart"); + matched_node = of_get_compatible_child(node, "mrvl,nfc-uart"); if (!matched_node) return -ENODEV; } diff --git a/drivers/of/base.c b/drivers/of/base.c index 74eaedd5b860..13ebb16be64e 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -67,6 +67,7 @@ bool of_node_name_eq(const struct device_node *np, const char *name) return (strlen(name) == len) && (strncmp(node_name, name, len) == 0); } +EXPORT_SYMBOL(of_node_name_eq); bool of_node_name_prefix(const struct device_node *np, const char *prefix) { @@ -75,6 +76,7 @@ bool of_node_name_prefix(const struct device_node *np, const char *prefix) return strncmp(kbasename(np->full_name), prefix, strlen(prefix)) == 0; } +EXPORT_SYMBOL(of_node_name_prefix); int of_n_addr_cells(struct device_node *np) { @@ -330,6 +332,8 @@ static bool __of_find_n_match_cpu_property(struct device_node *cpun, ac = of_n_addr_cells(cpun); cell = of_get_property(cpun, prop_name, &prop_len); + if (!cell && !ac && arch_match_cpu_phys_id(cpu, 0)) + return true; if (!cell || !ac) return false; prop_len /= sizeof(*cell) * ac; @@ -390,7 +394,7 @@ struct device_node *of_get_cpu_node(int cpu, unsigned int *thread) { struct device_node *cpun; - for_each_node_by_type(cpun, "cpu") { + for_each_of_cpu_node(cpun) { if (arch_find_n_match_cpu_physical_id(cpun, cpu, thread)) return cpun; } @@ -745,6 +749,45 @@ struct device_node *of_get_next_available_child(const struct device_node *node, EXPORT_SYMBOL(of_get_next_available_child); /** + * of_get_next_cpu_node - Iterate on cpu nodes + * @prev: previous child of the /cpus node, or NULL to get first + * + * Returns a cpu node pointer with refcount incremented, use of_node_put() + * on it when done. Returns NULL when prev is the last child. Decrements + * the refcount of prev. + */ +struct device_node *of_get_next_cpu_node(struct device_node *prev) +{ + struct device_node *next = NULL; + unsigned long flags; + struct device_node *node; + + if (!prev) + node = of_find_node_by_path("/cpus"); + + raw_spin_lock_irqsave(&devtree_lock, flags); + if (prev) + next = prev->sibling; + else if (node) { + next = node->child; + of_node_put(node); + } + for (; next; next = next->sibling) { + if (!(of_node_name_eq(next, "cpu") || + (next->type && !of_node_cmp(next->type, "cpu")))) + continue; + if (!__of_device_is_available(next)) + continue; + if (of_node_get(next)) + break; + } + of_node_put(prev); + raw_spin_unlock_irqrestore(&devtree_lock, flags); + return next; +} +EXPORT_SYMBOL(of_get_next_cpu_node); + +/** * of_get_compatible_child - Find compatible child node * @parent: parent node * @compatible: compatible string @@ -2013,7 +2056,7 @@ struct device_node *of_find_next_cache_node(const struct device_node *np) /* OF on pmac has nodes instead of properties named "l2-cache" * beneath CPU nodes. */ - if (!strcmp(np->type, "cpu")) + if (IS_ENABLED(CONFIG_PPC_PMAC) && !strcmp(np->type, "cpu")) for_each_child_of_node(np, child) if (!strcmp(child->type, "cache")) return child; @@ -2045,3 +2088,105 @@ int of_find_last_cache_level(unsigned int cpu) return cache_level; } + +/** + * of_map_rid - Translate a requester ID through a downstream mapping. + * @np: root complex device node. + * @rid: device requester ID to map. + * @map_name: property name of the map to use. + * @map_mask_name: optional property name of the mask to use. + * @target: optional pointer to a target device node. + * @id_out: optional pointer to receive the translated ID. + * + * Given a device requester ID, look up the appropriate implementation-defined + * platform ID and/or the target device which receives transactions on that + * ID, as per the "iommu-map" and "msi-map" bindings. Either of @target or + * @id_out may be NULL if only the other is required. If @target points to + * a non-NULL device node pointer, only entries targeting that node will be + * matched; if it points to a NULL value, it will receive the device node of + * the first matching target phandle, with a reference held. + * + * Return: 0 on success or a standard error code on failure. + */ +int of_map_rid(struct device_node *np, u32 rid, + const char *map_name, const char *map_mask_name, + struct device_node **target, u32 *id_out) +{ + u32 map_mask, masked_rid; + int map_len; + const __be32 *map = NULL; + + if (!np || !map_name || (!target && !id_out)) + return -EINVAL; + + map = of_get_property(np, map_name, &map_len); + if (!map) { + if (target) + return -ENODEV; + /* Otherwise, no map implies no translation */ + *id_out = rid; + return 0; + } + + if (!map_len || map_len % (4 * sizeof(*map))) { + pr_err("%pOF: Error: Bad %s length: %d\n", np, + map_name, map_len); + return -EINVAL; + } + + /* The default is to select all bits. */ + map_mask = 0xffffffff; + + /* + * Can be overridden by "{iommu,msi}-map-mask" property. + * If of_property_read_u32() fails, the default is used. + */ + if (map_mask_name) + of_property_read_u32(np, map_mask_name, &map_mask); + + masked_rid = map_mask & rid; + for ( ; map_len > 0; map_len -= 4 * sizeof(*map), map += 4) { + struct device_node *phandle_node; + u32 rid_base = be32_to_cpup(map + 0); + u32 phandle = be32_to_cpup(map + 1); + u32 out_base = be32_to_cpup(map + 2); + u32 rid_len = be32_to_cpup(map + 3); + + if (rid_base & ~map_mask) { + pr_err("%pOF: Invalid %s translation - %s-mask (0x%x) ignores rid-base (0x%x)\n", + np, map_name, map_name, + map_mask, rid_base); + return -EFAULT; + } + + if (masked_rid < rid_base || masked_rid >= rid_base + rid_len) + continue; + + phandle_node = of_find_node_by_phandle(phandle); + if (!phandle_node) + return -ENODEV; + + if (target) { + if (*target) + of_node_put(phandle_node); + else + *target = phandle_node; + + if (*target != phandle_node) + continue; + } + + if (id_out) + *id_out = masked_rid - rid_base + out_base; + + pr_debug("%pOF: %s, using mask %08x, rid-base: %08x, out-base: %08x, length: %08x, rid: %08x -> %08x\n", + np, map_name, map_mask, rid_base, out_base, + rid_len, rid, masked_rid - rid_base + out_base); + return 0; + } + + pr_err("%pOF: Invalid %s translation - no match for rid 0x%x on %pOF\n", + np, map_name, rid, target && *target ? *target : NULL); + return -EFAULT; +} +EXPORT_SYMBOL_GPL(of_map_rid); diff --git a/drivers/of/device.c b/drivers/of/device.c index c7fa5a9697c9..0f27fad9fe94 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -207,7 +207,8 @@ static ssize_t of_device_get_modalias(struct device *dev, char *str, ssize_t len return -ENODEV; /* Name & Type */ - csize = snprintf(str, len, "of:N%sT%s", dev->of_node->name, + /* %p eats all alphanum characters, so %c must be used here */ + csize = snprintf(str, len, "of:N%pOFn%c%s", dev->of_node, 'T', dev->of_node->type); tsize = csize; len -= csize; @@ -286,7 +287,7 @@ void of_device_uevent(struct device *dev, struct kobj_uevent_env *env) if ((!dev) || (!dev->of_node)) return; - add_uevent_var(env, "OF_NAME=%s", dev->of_node->name); + add_uevent_var(env, "OF_NAME=%pOFn", dev->of_node); add_uevent_var(env, "OF_FULLNAME=%pOF", dev->of_node); if (dev->of_node->type && strcmp("<NULL>", dev->of_node->type) != 0) add_uevent_var(env, "OF_TYPE=%s", dev->of_node->type); diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 02ad93a304a4..e1f6f392a4c0 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -22,7 +22,6 @@ #include <linux/module.h> #include <linux/of.h> #include <linux/of_irq.h> -#include <linux/of_pci.h> #include <linux/string.h> #include <linux/slab.h> @@ -588,8 +587,8 @@ static u32 __of_msi_map_rid(struct device *dev, struct device_node **np, * "msi-map" property. */ for (parent_dev = dev; parent_dev; parent_dev = parent_dev->parent) - if (!of_pci_map_rid(parent_dev->of_node, rid_in, "msi-map", - "msi-map-mask", np, &rid_out)) + if (!of_map_rid(parent_dev->of_node, rid_in, "msi-map", + "msi-map-mask", np, &rid_out)) break; return rid_out; } diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index e92391d6d1bd..5ad1342f5682 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -97,8 +97,8 @@ static int of_mdiobus_register_phy(struct mii_bus *mdio, return rc; } - dev_dbg(&mdio->dev, "registered phy %s at address %i\n", - child->name, addr); + dev_dbg(&mdio->dev, "registered phy %pOFn at address %i\n", + child, addr); return 0; } @@ -127,8 +127,8 @@ static int of_mdiobus_register_device(struct mii_bus *mdio, return rc; } - dev_dbg(&mdio->dev, "registered mdio device %s at address %i\n", - child->name, addr); + dev_dbg(&mdio->dev, "registered mdio device %pOFn at address %i\n", + child, addr); return 0; } @@ -263,8 +263,8 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) continue; /* be noisy to encourage people to set reg property */ - dev_info(&mdio->dev, "scan phy %s at address %i\n", - child->name, addr); + dev_info(&mdio->dev, "scan phy %pOFn at address %i\n", + child, addr); if (of_mdiobus_child_is_phy(child)) { rc = of_mdiobus_register_phy(mdio, child, addr); diff --git a/drivers/of/of_numa.c b/drivers/of/of_numa.c index 27d9b4bba535..35c64a4295e0 100644 --- a/drivers/of/of_numa.c +++ b/drivers/of/of_numa.c @@ -24,18 +24,9 @@ static void __init of_numa_parse_cpu_nodes(void) { u32 nid; int r; - struct device_node *cpus; - struct device_node *np = NULL; - - cpus = of_find_node_by_path("/cpus"); - if (!cpus) - return; - - for_each_child_of_node(cpus, np) { - /* Skip things that are not CPUs */ - if (of_node_cmp(np->type, "cpu") != 0) - continue; + struct device_node *np; + for_each_of_cpu_node(np) { r = of_property_read_u32(np, "numa-node-id", &nid); if (r) continue; @@ -46,8 +37,6 @@ static void __init of_numa_parse_cpu_nodes(void) else node_set(nid, numa_nodes_parsed); } - - of_node_put(cpus); } static int __init of_numa_parse_memory_nodes(void) @@ -163,8 +152,8 @@ int of_node_to_nid(struct device_node *device) np = of_get_next_parent(np); } if (np && r) - pr_warn("Invalid \"numa-node-id\" property in node %s\n", - np->name); + pr_warn("Invalid \"numa-node-id\" property in node %pOFn\n", + np); of_node_put(np); /* diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h index 216175d11d3d..5d1567025358 100644 --- a/drivers/of/of_private.h +++ b/drivers/of/of_private.h @@ -27,6 +27,14 @@ struct alias_prop { char stem[0]; }; +#if defined(CONFIG_SPARC) +#define OF_ROOT_NODE_ADDR_CELLS_DEFAULT 2 +#else +#define OF_ROOT_NODE_ADDR_CELLS_DEFAULT 1 +#endif + +#define OF_ROOT_NODE_SIZE_CELLS_DEFAULT 1 + extern struct mutex of_mutex; extern struct list_head aliases_lookup; extern struct kset *of_kset; diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c index eda57ef12fd0..42b1f73ac5f6 100644 --- a/drivers/of/overlay.c +++ b/drivers/of/overlay.c @@ -425,8 +425,8 @@ static int build_changeset_next_level(struct overlay_changeset *ovcs, for_each_child_of_node(overlay_node, child) { ret = add_changeset_node(ovcs, target_node, child); if (ret) { - pr_debug("Failed to apply node @%pOF/%s, err=%d\n", - target_node, child->name, ret); + pr_debug("Failed to apply node @%pOF/%pOFn, err=%d\n", + target_node, child, ret); of_node_put(child); return ret; } diff --git a/drivers/of/platform.c b/drivers/of/platform.c index 6c59673933e9..04ad312fd85b 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -91,8 +91,8 @@ static void of_device_make_bus_id(struct device *dev) */ reg = of_get_property(node, "reg", NULL); if (reg && (addr = of_translate_address(node, reg)) != OF_BAD_ADDR) { - dev_set_name(dev, dev_name(dev) ? "%llx.%s:%s" : "%llx.%s", - (unsigned long long)addr, node->name, + dev_set_name(dev, dev_name(dev) ? "%llx.%pOFn:%s" : "%llx.%pOFn", + (unsigned long long)addr, node, dev_name(dev)); return; } @@ -142,8 +142,8 @@ struct platform_device *of_device_alloc(struct device_node *np, WARN_ON(rc); } if (of_irq_to_resource_table(np, res, num_irq) != num_irq) - pr_debug("not all legacy IRQ resources mapped for %s\n", - np->name); + pr_debug("not all legacy IRQ resources mapped for %pOFn\n", + np); } dev->dev.of_node = of_node_get(np); diff --git a/drivers/of/unittest-data/overlay_15.dts b/drivers/of/unittest-data/overlay_15.dts index b98f2514df4b..5728490474f6 100644 --- a/drivers/of/unittest-data/overlay_15.dts +++ b/drivers/of/unittest-data/overlay_15.dts @@ -20,8 +20,8 @@ #size-cells = <0>; reg = <0>; - test-mux-dev { - reg = <32>; + test-mux-dev@20 { + reg = <0x20>; compatible = "unittest-i2c-dev"; status = "okay"; }; diff --git a/drivers/of/unittest-data/tests-overlay.dtsi b/drivers/of/unittest-data/tests-overlay.dtsi index 25cf397b8f6b..4ea024d908ee 100644 --- a/drivers/of/unittest-data/tests-overlay.dtsi +++ b/drivers/of/unittest-data/tests-overlay.dtsi @@ -103,8 +103,8 @@ #size-cells = <0>; reg = <0>; - test-mux-dev { - reg = <32>; + test-mux-dev@20 { + reg = <0x20>; compatible = "unittest-i2c-dev"; status = "okay"; }; diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index 41b49716ac75..a3a6866765f2 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -212,8 +212,8 @@ static int __init of_unittest_check_node_linkage(struct device_node *np) for_each_child_of_node(np, child) { if (child->parent != np) { - pr_err("Child node %s links to wrong parent %s\n", - child->name, np->name); + pr_err("Child node %pOFn links to wrong parent %pOFn\n", + child, np); rc = -EINVAL; goto put_child; } @@ -299,6 +299,10 @@ static void __init of_unittest_printf(void) of_unittest_printf_one(np, "%pOF", full_name); of_unittest_printf_one(np, "%pOFf", full_name); + of_unittest_printf_one(np, "%pOFn", "dev"); + of_unittest_printf_one(np, "%2pOFn", "dev"); + of_unittest_printf_one(np, "%5pOFn", " dev"); + of_unittest_printf_one(np, "%pOFnc", "dev:test-sub-device"); of_unittest_printf_one(np, "%pOFp", phandle_str); of_unittest_printf_one(np, "%pOFP", "dev@100"); of_unittest_printf_one(np, "ABC %pOFP ABC", "ABC dev@100 ABC"); @@ -1046,16 +1050,16 @@ static void __init of_unittest_platform_populate(void) for_each_child_of_node(np, child) { for_each_child_of_node(child, grandchild) unittest(of_find_device_by_node(grandchild), - "Could not create device for node '%s'\n", - grandchild->name); + "Could not create device for node '%pOFn'\n", + grandchild); } of_platform_depopulate(&test_bus->dev); for_each_child_of_node(np, child) { for_each_child_of_node(child, grandchild) unittest(!of_find_device_by_node(grandchild), - "device didn't get destroyed '%s'\n", - grandchild->name); + "device didn't get destroyed '%pOFn'\n", + grandchild); } platform_device_unregister(test_bus); @@ -2357,11 +2361,14 @@ static __init void of_unittest_overlay_high_level(void) } } - for (np = overlay_base_root->child; np; np = np->sibling) { - if (of_get_child_by_name(of_root, np->name)) { - unittest(0, "illegal node name in overlay_base %s", - np->name); - return; + for_each_child_of_node(overlay_base_root, np) { + struct device_node *base_child; + for_each_child_of_node(of_root, base_child) { + if (!strcmp(np->full_name, base_child->full_name)) { + unittest(0, "illegal node name in overlay_base %pOFn", + np); + return; + } } } diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c index ee54f5bacad1..6758fd7c382e 100644 --- a/drivers/pci/hotplug/pnv_php.c +++ b/drivers/pci/hotplug/pnv_php.c @@ -746,7 +746,7 @@ static irqreturn_t pnv_php_interrupt(int irq, void *data) pe = edev ? edev->pe : NULL; if (pe) { eeh_serialize_lock(&flags); - eeh_pe_state_mark(pe, EEH_PE_ISOLATED); + eeh_pe_mark_isolated(pe); eeh_serialize_unlock(flags); eeh_pe_set_option(pe, EEH_OPT_FREEZE_PE); } diff --git a/drivers/pci/of.c b/drivers/pci/of.c index 1836b8ddf292..4c4217d0c3f1 100644 --- a/drivers/pci/of.c +++ b/drivers/pci/of.c @@ -355,107 +355,6 @@ failed: EXPORT_SYMBOL_GPL(devm_of_pci_get_host_bridge_resources); #endif /* CONFIG_OF_ADDRESS */ -/** - * of_pci_map_rid - Translate a requester ID through a downstream mapping. - * @np: root complex device node. - * @rid: PCI requester ID to map. - * @map_name: property name of the map to use. - * @map_mask_name: optional property name of the mask to use. - * @target: optional pointer to a target device node. - * @id_out: optional pointer to receive the translated ID. - * - * Given a PCI requester ID, look up the appropriate implementation-defined - * platform ID and/or the target device which receives transactions on that - * ID, as per the "iommu-map" and "msi-map" bindings. Either of @target or - * @id_out may be NULL if only the other is required. If @target points to - * a non-NULL device node pointer, only entries targeting that node will be - * matched; if it points to a NULL value, it will receive the device node of - * the first matching target phandle, with a reference held. - * - * Return: 0 on success or a standard error code on failure. - */ -int of_pci_map_rid(struct device_node *np, u32 rid, - const char *map_name, const char *map_mask_name, - struct device_node **target, u32 *id_out) -{ - u32 map_mask, masked_rid; - int map_len; - const __be32 *map = NULL; - - if (!np || !map_name || (!target && !id_out)) - return -EINVAL; - - map = of_get_property(np, map_name, &map_len); - if (!map) { - if (target) - return -ENODEV; - /* Otherwise, no map implies no translation */ - *id_out = rid; - return 0; - } - - if (!map_len || map_len % (4 * sizeof(*map))) { - pr_err("%pOF: Error: Bad %s length: %d\n", np, - map_name, map_len); - return -EINVAL; - } - - /* The default is to select all bits. */ - map_mask = 0xffffffff; - - /* - * Can be overridden by "{iommu,msi}-map-mask" property. - * If of_property_read_u32() fails, the default is used. - */ - if (map_mask_name) - of_property_read_u32(np, map_mask_name, &map_mask); - - masked_rid = map_mask & rid; - for ( ; map_len > 0; map_len -= 4 * sizeof(*map), map += 4) { - struct device_node *phandle_node; - u32 rid_base = be32_to_cpup(map + 0); - u32 phandle = be32_to_cpup(map + 1); - u32 out_base = be32_to_cpup(map + 2); - u32 rid_len = be32_to_cpup(map + 3); - - if (rid_base & ~map_mask) { - pr_err("%pOF: Invalid %s translation - %s-mask (0x%x) ignores rid-base (0x%x)\n", - np, map_name, map_name, - map_mask, rid_base); - return -EFAULT; - } - - if (masked_rid < rid_base || masked_rid >= rid_base + rid_len) - continue; - - phandle_node = of_find_node_by_phandle(phandle); - if (!phandle_node) - return -ENODEV; - - if (target) { - if (*target) - of_node_put(phandle_node); - else - *target = phandle_node; - - if (*target != phandle_node) - continue; - } - - if (id_out) - *id_out = masked_rid - rid_base + out_base; - - pr_debug("%pOF: %s, using mask %08x, rid-base: %08x, out-base: %08x, length: %08x, rid: %08x -> %08x\n", - np, map_name, map_mask, rid_base, out_base, - rid_len, rid, masked_rid - rid_base + out_base); - return 0; - } - - pr_err("%pOF: Invalid %s translation - no match for rid 0x%x on %pOF\n", - np, map_name, rid, target && *target ? *target : NULL); - return -EFAULT; -} - #if IS_ENABLED(CONFIG_OF_IRQ) /** * of_irq_parse_pci - Resolve the interrupt for a PCI device diff --git a/drivers/pcmcia/electra_cf.c b/drivers/pcmcia/electra_cf.c index 9671ded549f0..b31abe35ed2c 100644 --- a/drivers/pcmcia/electra_cf.c +++ b/drivers/pcmcia/electra_cf.c @@ -230,7 +230,7 @@ static int electra_cf_probe(struct platform_device *ofdev) if (!cf->mem_base || !cf->io_virt || !cf->gpio_base || (__ioremap_at(io.start, cf->io_virt, cf->io_size, - pgprot_val(pgprot_noncached(__pgprot(0)))) == NULL)) { + pgprot_noncached(PAGE_KERNEL)) == NULL)) { dev_err(device, "can't ioremap ranges\n"); status = -ENOMEM; goto fail1; diff --git a/drivers/power/supply/twl4030_charger.c b/drivers/power/supply/twl4030_charger.c index 80582c8f98fa..0e202d4273fb 100644 --- a/drivers/power/supply/twl4030_charger.c +++ b/drivers/power/supply/twl4030_charger.c @@ -1022,12 +1022,13 @@ static int twl4030_bci_probe(struct platform_device *pdev) if (bci->dev->of_node) { struct device_node *phynode; - phynode = of_find_compatible_node(bci->dev->of_node->parent, - NULL, "ti,twl4030-usb"); + phynode = of_get_compatible_child(bci->dev->of_node->parent, + "ti,twl4030-usb"); if (phynode) { bci->usb_nb.notifier_call = twl4030_bci_usb_ncb; bci->transceiver = devm_usb_get_phy_by_node( bci->dev, phynode, &bci->usb_nb); + of_node_put(phynode); if (IS_ERR(bci->transceiver)) { ret = PTR_ERR(bci->transceiver); if (ret == -EPROBE_DEFER) diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index b762d0fd773c..3bb2b3351e35 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1272,8 +1272,6 @@ static int sd_init_command(struct scsi_cmnd *cmd) case REQ_OP_READ: case REQ_OP_WRITE: return sd_setup_read_write_cmnd(cmd); - case REQ_OP_ZONE_REPORT: - return sd_zbc_setup_report_cmnd(cmd); case REQ_OP_ZONE_RESET: return sd_zbc_setup_reset_cmnd(cmd); default: @@ -1802,6 +1800,7 @@ static const struct block_device_operations sd_fops = { .check_events = sd_check_events, .revalidate_disk = sd_revalidate_disk, .unlock_native_capacity = sd_unlock_native_capacity, + .report_zones = sd_zbc_report_zones, .pr_ops = &sd_pr_ops, }; @@ -1953,16 +1952,6 @@ static int sd_done(struct scsi_cmnd *SCpnt) scsi_set_resid(SCpnt, blk_rq_bytes(req)); } break; - case REQ_OP_ZONE_REPORT: - if (!result) { - good_bytes = scsi_bufflen(SCpnt) - - scsi_get_resid(SCpnt); - scsi_set_resid(SCpnt, 0); - } else { - good_bytes = 0; - scsi_set_resid(SCpnt, blk_rq_bytes(req)); - } - break; default: /* * In case of bogus fw or device, we could end up having @@ -3425,8 +3414,6 @@ static int sd_remove(struct device *dev) del_gendisk(sdkp->disk); sd_shutdown(dev); - sd_zbc_remove(sdkp); - free_opal_dev(sdkp->opal_dev); blk_register_region(devt, SD_MINORS, NULL, diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index a7d4f50b67d4..1d63f3a23ffb 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -76,7 +76,6 @@ struct scsi_disk { #ifdef CONFIG_BLK_DEV_ZONED u32 nr_zones; u32 zone_blocks; - u32 zone_shift; u32 zones_optimal_open; u32 zones_optimal_nonseq; u32 zones_max_open; @@ -271,12 +270,13 @@ static inline int sd_is_zoned(struct scsi_disk *sdkp) #ifdef CONFIG_BLK_DEV_ZONED extern int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buffer); -extern void sd_zbc_remove(struct scsi_disk *sdkp); extern void sd_zbc_print_zones(struct scsi_disk *sdkp); -extern int sd_zbc_setup_report_cmnd(struct scsi_cmnd *cmd); extern int sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd); extern void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, struct scsi_sense_hdr *sshdr); +extern int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask); #else /* CONFIG_BLK_DEV_ZONED */ @@ -286,15 +286,8 @@ static inline int sd_zbc_read_zones(struct scsi_disk *sdkp, return 0; } -static inline void sd_zbc_remove(struct scsi_disk *sdkp) {} - static inline void sd_zbc_print_zones(struct scsi_disk *sdkp) {} -static inline int sd_zbc_setup_report_cmnd(struct scsi_cmnd *cmd) -{ - return BLKPREP_INVALID; -} - static inline int sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd) { return BLKPREP_INVALID; @@ -304,6 +297,8 @@ static inline void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, struct scsi_sense_hdr *sshdr) {} +#define sd_zbc_report_zones NULL + #endif /* CONFIG_BLK_DEV_ZONED */ #endif /* _SCSI_DISK_H */ diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index 412c1787dcd9..e06c48c866e4 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -62,16 +62,22 @@ static void sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf, } /** - * sd_zbc_report_zones - Issue a REPORT ZONES scsi command. + * sd_zbc_do_report_zones - Issue a REPORT ZONES scsi command. * @sdkp: The target disk * @buf: Buffer to use for the reply * @buflen: the buffer size * @lba: Start LBA of the report + * @partial: Do partial report * * For internal use during device validation. + * Using partial=true can significantly speed up execution of a report zones + * command because the disk does not have to count all possible report matching + * zones and will only report the count of zones fitting in the command reply + * buffer. */ -static int sd_zbc_report_zones(struct scsi_disk *sdkp, unsigned char *buf, - unsigned int buflen, sector_t lba) +static int sd_zbc_do_report_zones(struct scsi_disk *sdkp, unsigned char *buf, + unsigned int buflen, sector_t lba, + bool partial) { struct scsi_device *sdp = sdkp->device; const int timeout = sdp->request_queue->rq_timeout; @@ -85,6 +91,8 @@ static int sd_zbc_report_zones(struct scsi_disk *sdkp, unsigned char *buf, cmd[1] = ZI_REPORT_ZONES; put_unaligned_be64(lba, &cmd[2]); put_unaligned_be32(buflen, &cmd[10]); + if (partial) + cmd[14] = ZBC_REPORT_ZONE_PARTIAL; memset(buf, 0, buflen); result = scsi_execute_req(sdp, cmd, DMA_FROM_DEVICE, @@ -110,108 +118,56 @@ static int sd_zbc_report_zones(struct scsi_disk *sdkp, unsigned char *buf, } /** - * sd_zbc_setup_report_cmnd - Prepare a REPORT ZONES scsi command - * @cmd: The command to setup + * sd_zbc_report_zones - Disk report zones operation. + * @disk: The target disk + * @sector: Start 512B sector of the report + * @zones: Array of zone descriptors + * @nr_zones: Number of descriptors in the array + * @gfp_mask: Memory allocation mask * - * Call in sd_init_command() for a REQ_OP_ZONE_REPORT request. + * Execute a report zones command on the target disk. */ -int sd_zbc_setup_report_cmnd(struct scsi_cmnd *cmd) +int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask) { - struct request *rq = cmd->request; - struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); - sector_t lba, sector = blk_rq_pos(rq); - unsigned int nr_bytes = blk_rq_bytes(rq); - int ret; - - WARN_ON(nr_bytes == 0); + struct scsi_disk *sdkp = scsi_disk(disk); + unsigned int i, buflen, nrz = *nr_zones; + unsigned char *buf; + size_t offset = 0; + int ret = 0; if (!sd_is_zoned(sdkp)) /* Not a zoned device */ - return BLKPREP_KILL; - - ret = scsi_init_io(cmd); - if (ret != BLKPREP_OK) - return ret; - - cmd->cmd_len = 16; - memset(cmd->cmnd, 0, cmd->cmd_len); - cmd->cmnd[0] = ZBC_IN; - cmd->cmnd[1] = ZI_REPORT_ZONES; - lba = sectors_to_logical(sdkp->device, sector); - put_unaligned_be64(lba, &cmd->cmnd[2]); - put_unaligned_be32(nr_bytes, &cmd->cmnd[10]); - /* Do partial report for speeding things up */ - cmd->cmnd[14] = ZBC_REPORT_ZONE_PARTIAL; - - cmd->sc_data_direction = DMA_FROM_DEVICE; - cmd->sdb.length = nr_bytes; - cmd->transfersize = sdkp->device->sector_size; - cmd->allowed = 0; - - return BLKPREP_OK; -} - -/** - * sd_zbc_report_zones_complete - Process a REPORT ZONES scsi command reply. - * @scmd: The completed report zones command - * @good_bytes: reply size in bytes - * - * Convert all reported zone descriptors to struct blk_zone. The conversion - * is done in-place, directly in the request specified sg buffer. - */ -static void sd_zbc_report_zones_complete(struct scsi_cmnd *scmd, - unsigned int good_bytes) -{ - struct request *rq = scmd->request; - struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); - struct sg_mapping_iter miter; - struct blk_zone_report_hdr hdr; - struct blk_zone zone; - unsigned int offset, bytes = 0; - unsigned long flags; - u8 *buf; - - if (good_bytes < 64) - return; + return -EOPNOTSUPP; - memset(&hdr, 0, sizeof(struct blk_zone_report_hdr)); - - sg_miter_start(&miter, scsi_sglist(scmd), scsi_sg_count(scmd), - SG_MITER_TO_SG | SG_MITER_ATOMIC); - - local_irq_save(flags); - while (sg_miter_next(&miter) && bytes < good_bytes) { + /* + * Get a reply buffer for the number of requested zones plus a header. + * For ATA, buffers must be aligned to 512B. + */ + buflen = roundup((nrz + 1) * 64, 512); + buf = kmalloc(buflen, gfp_mask); + if (!buf) + return -ENOMEM; - buf = miter.addr; - offset = 0; + ret = sd_zbc_do_report_zones(sdkp, buf, buflen, + sectors_to_logical(sdkp->device, sector), true); + if (ret) + goto out_free_buf; - if (bytes == 0) { - /* Set the report header */ - hdr.nr_zones = min_t(unsigned int, - (good_bytes - 64) / 64, - get_unaligned_be32(&buf[0]) / 64); - memcpy(buf, &hdr, sizeof(struct blk_zone_report_hdr)); - offset += 64; - bytes += 64; - } + nrz = min(nrz, get_unaligned_be32(&buf[0]) / 64); + for (i = 0; i < nrz; i++) { + offset += 64; + sd_zbc_parse_report(sdkp, buf + offset, zones); + zones++; + } - /* Parse zone descriptors */ - while (offset < miter.length && hdr.nr_zones) { - WARN_ON(offset > miter.length); - buf = miter.addr + offset; - sd_zbc_parse_report(sdkp, buf, &zone); - memcpy(buf, &zone, sizeof(struct blk_zone)); - offset += 64; - bytes += 64; - hdr.nr_zones--; - } + *nr_zones = nrz; - if (!hdr.nr_zones) - break; +out_free_buf: + kfree(buf); - } - sg_miter_stop(&miter); - local_irq_restore(flags); + return ret; } /** @@ -294,30 +250,23 @@ void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, case REQ_OP_WRITE_ZEROES: case REQ_OP_WRITE_SAME: break; - - case REQ_OP_ZONE_REPORT: - - if (!result) - sd_zbc_report_zones_complete(cmd, good_bytes); - break; - } } /** - * sd_zbc_read_zoned_characteristics - Read zoned block device characteristics + * sd_zbc_check_zoned_characteristics - Check zoned block device characteristics * @sdkp: Target disk * @buf: Buffer where to store the VPD page data * - * Read VPD page B6. + * Read VPD page B6, get information and check that reads are unconstrained. */ -static int sd_zbc_read_zoned_characteristics(struct scsi_disk *sdkp, - unsigned char *buf) +static int sd_zbc_check_zoned_characteristics(struct scsi_disk *sdkp, + unsigned char *buf) { if (scsi_get_vpd_page(sdkp->device, 0xb6, buf, 64)) { sd_printk(KERN_NOTICE, sdkp, - "Unconstrained-read check failed\n"); + "Read zoned characteristics VPD page failed\n"); return -ENODEV; } @@ -335,43 +284,17 @@ static int sd_zbc_read_zoned_characteristics(struct scsi_disk *sdkp, sdkp->zones_max_open = get_unaligned_be32(&buf[16]); } - return 0; -} - -/** - * sd_zbc_check_capacity - Check reported capacity. - * @sdkp: Target disk - * @buf: Buffer to use for commands - * - * ZBC drive may report only the capacity of the first conventional zones at - * LBA 0. This is indicated by the RC_BASIS field of the read capacity reply. - * Check this here. If the disk reported only its conventional zones capacity, - * get the total capacity by doing a report zones. - */ -static int sd_zbc_check_capacity(struct scsi_disk *sdkp, unsigned char *buf) -{ - sector_t lba; - int ret; - - if (sdkp->rc_basis != 0) - return 0; - - /* Do a report zone to get the maximum LBA to check capacity */ - ret = sd_zbc_report_zones(sdkp, buf, SD_BUF_SIZE, 0); - if (ret) - return ret; - - /* The max_lba field is the capacity of this device */ - lba = get_unaligned_be64(&buf[8]); - if (lba + 1 == sdkp->capacity) - return 0; - - if (sdkp->first_scan) - sd_printk(KERN_WARNING, sdkp, - "Changing capacity from %llu to max LBA+1 %llu\n", - (unsigned long long)sdkp->capacity, - (unsigned long long)lba + 1); - sdkp->capacity = lba + 1; + /* + * Check for unconstrained reads: host-managed devices with + * constrained reads (drives failing read after write pointer) + * are not supported. + */ + if (!sdkp->urswrz) { + if (sdkp->first_scan) + sd_printk(KERN_NOTICE, sdkp, + "constrained reads devices are not supported\n"); + return -ENODEV; + } return 0; } @@ -379,24 +302,27 @@ static int sd_zbc_check_capacity(struct scsi_disk *sdkp, unsigned char *buf) #define SD_ZBC_BUF_SIZE 131072U /** - * sd_zbc_check_zone_size - Check the device zone sizes + * sd_zbc_check_zones - Check the device capacity and zone sizes * @sdkp: Target disk * - * Check that all zones of the device are equal. The last zone can however - * be smaller. The zone size must also be a power of two number of LBAs. + * Check that the device capacity as reported by READ CAPACITY matches the + * max_lba value (plus one)of the report zones command reply. Also check that + * all zones of the device have an equal size, only allowing the last zone of + * the disk to have a smaller size (runt zone). The zone size must also be a + * power of two. * * Returns the zone size in number of blocks upon success or an error code * upon failure. */ -static s64 sd_zbc_check_zone_size(struct scsi_disk *sdkp) +static int sd_zbc_check_zones(struct scsi_disk *sdkp, u32 *zblocks) { u64 zone_blocks = 0; - sector_t block = 0; + sector_t max_lba, block = 0; unsigned char *buf; unsigned char *rec; unsigned int buf_len; unsigned int list_length; - s64 ret; + int ret; u8 same; /* Get a buffer */ @@ -404,11 +330,28 @@ static s64 sd_zbc_check_zone_size(struct scsi_disk *sdkp) if (!buf) return -ENOMEM; - /* Do a report zone to get the same field */ - ret = sd_zbc_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE, 0); + /* Do a report zone to get max_lba and the same field */ + ret = sd_zbc_do_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE, 0, false); if (ret) goto out_free; + if (sdkp->rc_basis == 0) { + /* The max_lba field is the capacity of this device */ + max_lba = get_unaligned_be64(&buf[8]); + if (sdkp->capacity != max_lba + 1) { + if (sdkp->first_scan) + sd_printk(KERN_WARNING, sdkp, + "Changing capacity from %llu to max LBA+1 %llu\n", + (unsigned long long)sdkp->capacity, + (unsigned long long)max_lba + 1); + sdkp->capacity = max_lba + 1; + } + } + + /* + * Check same field: for any value other than 0, we know that all zones + * have the same size. + */ same = buf[4] & 0x0f; if (same > 0) { rec = &buf[64]; @@ -445,8 +388,8 @@ static s64 sd_zbc_check_zone_size(struct scsi_disk *sdkp) } if (block < sdkp->capacity) { - ret = sd_zbc_report_zones(sdkp, buf, - SD_ZBC_BUF_SIZE, block); + ret = sd_zbc_do_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE, + block, true); if (ret) goto out_free; } @@ -470,9 +413,10 @@ out: if (sdkp->first_scan) sd_printk(KERN_NOTICE, sdkp, "Zone size too large\n"); - ret = -ENODEV; + ret = -EFBIG; } else { - ret = zone_blocks; + *zblocks = zone_blocks; + ret = 0; } out_free: @@ -481,191 +425,11 @@ out_free: return ret; } -/** - * sd_zbc_alloc_zone_bitmap - Allocate a zone bitmap (one bit per zone). - * @nr_zones: Number of zones to allocate space for. - * @numa_node: NUMA node to allocate the memory from. - */ -static inline unsigned long * -sd_zbc_alloc_zone_bitmap(u32 nr_zones, int numa_node) -{ - return kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(unsigned long), - GFP_KERNEL, numa_node); -} - -/** - * sd_zbc_get_seq_zones - Parse report zones reply to identify sequential zones - * @sdkp: disk used - * @buf: report reply buffer - * @buflen: length of @buf - * @zone_shift: logarithm base 2 of the number of blocks in a zone - * @seq_zones_bitmap: bitmap of sequential zones to set - * - * Parse reported zone descriptors in @buf to identify sequential zones and - * set the reported zone bit in @seq_zones_bitmap accordingly. - * Since read-only and offline zones cannot be written, do not - * mark them as sequential in the bitmap. - * Return the LBA after the last zone reported. - */ -static sector_t sd_zbc_get_seq_zones(struct scsi_disk *sdkp, unsigned char *buf, - unsigned int buflen, u32 zone_shift, - unsigned long *seq_zones_bitmap) -{ - sector_t lba, next_lba = sdkp->capacity; - unsigned int buf_len, list_length; - unsigned char *rec; - u8 type, cond; - - list_length = get_unaligned_be32(&buf[0]) + 64; - buf_len = min(list_length, buflen); - rec = buf + 64; - - while (rec < buf + buf_len) { - type = rec[0] & 0x0f; - cond = (rec[1] >> 4) & 0xf; - lba = get_unaligned_be64(&rec[16]); - if (type != ZBC_ZONE_TYPE_CONV && - cond != ZBC_ZONE_COND_READONLY && - cond != ZBC_ZONE_COND_OFFLINE) - set_bit(lba >> zone_shift, seq_zones_bitmap); - next_lba = lba + get_unaligned_be64(&rec[8]); - rec += 64; - } - - return next_lba; -} - -/** - * sd_zbc_setup_seq_zones_bitmap - Initialize a seq zone bitmap. - * @sdkp: target disk - * @zone_shift: logarithm base 2 of the number of blocks in a zone - * @nr_zones: number of zones to set up a seq zone bitmap for - * - * Allocate a zone bitmap and initialize it by identifying sequential zones. - */ -static unsigned long * -sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp, u32 zone_shift, - u32 nr_zones) -{ - struct request_queue *q = sdkp->disk->queue; - unsigned long *seq_zones_bitmap; - sector_t lba = 0; - unsigned char *buf; - int ret = -ENOMEM; - - seq_zones_bitmap = sd_zbc_alloc_zone_bitmap(nr_zones, q->node); - if (!seq_zones_bitmap) - return ERR_PTR(-ENOMEM); - - buf = kmalloc(SD_ZBC_BUF_SIZE, GFP_KERNEL); - if (!buf) - goto out; - - while (lba < sdkp->capacity) { - ret = sd_zbc_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE, lba); - if (ret) - goto out; - lba = sd_zbc_get_seq_zones(sdkp, buf, SD_ZBC_BUF_SIZE, - zone_shift, seq_zones_bitmap); - } - - if (lba != sdkp->capacity) { - /* Something went wrong */ - ret = -EIO; - } - -out: - kfree(buf); - if (ret) { - kfree(seq_zones_bitmap); - return ERR_PTR(ret); - } - return seq_zones_bitmap; -} - -static void sd_zbc_cleanup(struct scsi_disk *sdkp) -{ - struct request_queue *q = sdkp->disk->queue; - - kfree(q->seq_zones_bitmap); - q->seq_zones_bitmap = NULL; - - kfree(q->seq_zones_wlock); - q->seq_zones_wlock = NULL; - - q->nr_zones = 0; -} - -static int sd_zbc_setup(struct scsi_disk *sdkp, u32 zone_blocks) -{ - struct request_queue *q = sdkp->disk->queue; - u32 zone_shift = ilog2(zone_blocks); - u32 nr_zones; - int ret; - - /* chunk_sectors indicates the zone size */ - blk_queue_chunk_sectors(q, - logical_to_sectors(sdkp->device, zone_blocks)); - nr_zones = round_up(sdkp->capacity, zone_blocks) >> zone_shift; - - /* - * Initialize the device request queue information if the number - * of zones changed. - */ - if (nr_zones != sdkp->nr_zones || nr_zones != q->nr_zones) { - unsigned long *seq_zones_wlock = NULL, *seq_zones_bitmap = NULL; - size_t zone_bitmap_size; - - if (nr_zones) { - seq_zones_wlock = sd_zbc_alloc_zone_bitmap(nr_zones, - q->node); - if (!seq_zones_wlock) { - ret = -ENOMEM; - goto err; - } - - seq_zones_bitmap = sd_zbc_setup_seq_zones_bitmap(sdkp, - zone_shift, nr_zones); - if (IS_ERR(seq_zones_bitmap)) { - ret = PTR_ERR(seq_zones_bitmap); - kfree(seq_zones_wlock); - goto err; - } - } - zone_bitmap_size = BITS_TO_LONGS(nr_zones) * - sizeof(unsigned long); - blk_mq_freeze_queue(q); - if (q->nr_zones != nr_zones) { - /* READ16/WRITE16 is mandatory for ZBC disks */ - sdkp->device->use_16_for_rw = 1; - sdkp->device->use_10_for_rw = 0; - - sdkp->zone_blocks = zone_blocks; - sdkp->zone_shift = zone_shift; - sdkp->nr_zones = nr_zones; - q->nr_zones = nr_zones; - swap(q->seq_zones_wlock, seq_zones_wlock); - swap(q->seq_zones_bitmap, seq_zones_bitmap); - } else if (memcmp(q->seq_zones_bitmap, seq_zones_bitmap, - zone_bitmap_size) != 0) { - memcpy(q->seq_zones_bitmap, seq_zones_bitmap, - zone_bitmap_size); - } - blk_mq_unfreeze_queue(q); - kfree(seq_zones_wlock); - kfree(seq_zones_bitmap); - } - - return 0; - -err: - sd_zbc_cleanup(sdkp); - return ret; -} - int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf) { - int64_t zone_blocks; + struct gendisk *disk = sdkp->disk; + unsigned int nr_zones; + u32 zone_blocks; int ret; if (!sd_is_zoned(sdkp)) @@ -675,26 +439,8 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf) */ return 0; - /* Get zoned block device characteristics */ - ret = sd_zbc_read_zoned_characteristics(sdkp, buf); - if (ret) - goto err; - - /* - * Check for unconstrained reads: host-managed devices with - * constrained reads (drives failing read after write pointer) - * are not supported. - */ - if (!sdkp->urswrz) { - if (sdkp->first_scan) - sd_printk(KERN_NOTICE, sdkp, - "constrained reads devices are not supported\n"); - ret = -ENODEV; - goto err; - } - - /* Check capacity */ - ret = sd_zbc_check_capacity(sdkp, buf); + /* Check zoned block device characteristics (unconstrained reads) */ + ret = sd_zbc_check_zoned_characteristics(sdkp, buf); if (ret) goto err; @@ -702,33 +448,44 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf) * Check zone size: only devices with a constant zone size (except * an eventual last runt zone) that is a power of 2 are supported. */ - zone_blocks = sd_zbc_check_zone_size(sdkp); - ret = -EFBIG; - if (zone_blocks != (u32)zone_blocks) - goto err; - ret = zone_blocks; - if (ret < 0) + ret = sd_zbc_check_zones(sdkp, &zone_blocks); + if (ret != 0) goto err; /* The drive satisfies the kernel restrictions: set it up */ - ret = sd_zbc_setup(sdkp, zone_blocks); - if (ret) - goto err; + blk_queue_chunk_sectors(sdkp->disk->queue, + logical_to_sectors(sdkp->device, zone_blocks)); + nr_zones = round_up(sdkp->capacity, zone_blocks) >> ilog2(zone_blocks); + + /* READ16/WRITE16 is mandatory for ZBC disks */ + sdkp->device->use_16_for_rw = 1; + sdkp->device->use_10_for_rw = 0; + + /* + * If something changed, revalidate the disk zone bitmaps once we have + * the capacity, that is on the second revalidate execution during disk + * scan and always during normal revalidate. + */ + if (sdkp->first_scan) + return 0; + if (sdkp->zone_blocks != zone_blocks || + sdkp->nr_zones != nr_zones || + disk->queue->nr_zones != nr_zones) { + ret = blk_revalidate_disk_zones(disk); + if (ret != 0) + goto err; + sdkp->zone_blocks = zone_blocks; + sdkp->nr_zones = nr_zones; + } return 0; err: sdkp->capacity = 0; - sd_zbc_cleanup(sdkp); return ret; } -void sd_zbc_remove(struct scsi_disk *sdkp) -{ - sd_zbc_cleanup(sdkp); -} - void sd_zbc_print_zones(struct scsi_disk *sdkp) { if (!sd_is_zoned(sdkp) || !sdkp->capacity) diff --git a/drivers/soc/dove/pmu.c b/drivers/soc/dove/pmu.c index 5abb08ffb74d..ffc5311c0ed8 100644 --- a/drivers/soc/dove/pmu.c +++ b/drivers/soc/dove/pmu.c @@ -383,7 +383,7 @@ int __init dove_init_pmu(void) domains_node = of_get_child_by_name(np_pmu, "domains"); if (!domains_node) { - pr_err("%s: failed to find domains sub-node\n", np_pmu->name); + pr_err("%pOFn: failed to find domains sub-node\n", np_pmu); return 0; } @@ -396,7 +396,7 @@ int __init dove_init_pmu(void) pmu->pmc_base = of_iomap(pmu->of_node, 0); pmu->pmu_base = of_iomap(pmu->of_node, 1); if (!pmu->pmc_base || !pmu->pmu_base) { - pr_err("%s: failed to map PMU\n", np_pmu->name); + pr_err("%pOFn: failed to map PMU\n", np_pmu); iounmap(pmu->pmu_base); iounmap(pmu->pmc_base); kfree(pmu); @@ -414,7 +414,7 @@ int __init dove_init_pmu(void) break; domain->pmu = pmu; - domain->base.name = kstrdup(np->name, GFP_KERNEL); + domain->base.name = kasprintf(GFP_KERNEL, "%pOFn", np); if (!domain->base.name) { kfree(domain); break; @@ -444,7 +444,7 @@ int __init dove_init_pmu(void) /* Loss of the interrupt controller is not a fatal error. */ parent_irq = irq_of_parse_and_map(pmu->of_node, 0); if (!parent_irq) { - pr_err("%s: no interrupt specified\n", np_pmu->name); + pr_err("%pOFn: no interrupt specified\n", np_pmu); } else { ret = dove_init_pmu_irq(pmu, parent_irq); if (ret) diff --git a/drivers/soc/fsl/qbman/qman_ccsr.c b/drivers/soc/fsl/qbman/qman_ccsr.c index 6fd5fef5f39b..109b38de3176 100644 --- a/drivers/soc/fsl/qbman/qman_ccsr.c +++ b/drivers/soc/fsl/qbman/qman_ccsr.c @@ -419,7 +419,7 @@ static size_t fqd_sz, pfdr_sz; static int zero_priv_mem(phys_addr_t addr, size_t sz) { /* map as cacheable, non-guarded */ - void __iomem *tmpp = ioremap_prot(addr, sz, 0); + void __iomem *tmpp = ioremap_cache(addr, sz); if (!tmpp) return -ENOMEM; diff --git a/drivers/soc/fsl/qe/qe_tdm.c b/drivers/soc/fsl/qe/qe_tdm.c index f744c214f680..f78c34647ca2 100644 --- a/drivers/soc/fsl/qe/qe_tdm.c +++ b/drivers/soc/fsl/qe/qe_tdm.c @@ -131,7 +131,7 @@ int ucc_of_parse_tdm(struct device_node *np, struct ucc_tdm *utdm, pdev = of_find_device_by_node(np2); if (!pdev) { - pr_err("%s: failed to lookup pdev\n", np2->name); + pr_err("%pOFn: failed to lookup pdev\n", np2); of_node_put(np2); return -EINVAL; } @@ -153,7 +153,7 @@ int ucc_of_parse_tdm(struct device_node *np, struct ucc_tdm *utdm, pdev = of_find_device_by_node(np2); if (!pdev) { ret = -EINVAL; - pr_err("%s: failed to lookup pdev\n", np2->name); + pr_err("%pOFn: failed to lookup pdev\n", np2); of_node_put(np2); goto err_miss_siram_property; } diff --git a/drivers/soc/qcom/apr.c b/drivers/soc/qcom/apr.c index 57af8a537332..4bda793ba6ae 100644 --- a/drivers/soc/qcom/apr.c +++ b/drivers/soc/qcom/apr.c @@ -219,7 +219,7 @@ static int apr_add_device(struct device *dev, struct device_node *np, adev->domain_id = id->domain_id; adev->version = id->svc_version; if (np) - strncpy(adev->name, np->name, APR_NAME_SIZE); + snprintf(adev->name, APR_NAME_SIZE, "%pOFn", np); else strncpy(adev->name, id->name, APR_NAME_SIZE); diff --git a/drivers/soc/rockchip/pm_domains.c b/drivers/soc/rockchip/pm_domains.c index 6dff8682155f..6f86a726bb45 100644 --- a/drivers/soc/rockchip/pm_domains.c +++ b/drivers/soc/rockchip/pm_domains.c @@ -392,21 +392,21 @@ static int rockchip_pm_add_one_domain(struct rockchip_pmu *pmu, error = of_property_read_u32(node, "reg", &id); if (error) { dev_err(pmu->dev, - "%s: failed to retrieve domain id (reg): %d\n", - node->name, error); + "%pOFn: failed to retrieve domain id (reg): %d\n", + node, error); return -EINVAL; } if (id >= pmu->info->num_domains) { - dev_err(pmu->dev, "%s: invalid domain id %d\n", - node->name, id); + dev_err(pmu->dev, "%pOFn: invalid domain id %d\n", + node, id); return -EINVAL; } pd_info = &pmu->info->domain_info[id]; if (!pd_info) { - dev_err(pmu->dev, "%s: undefined domain id %d\n", - node->name, id); + dev_err(pmu->dev, "%pOFn: undefined domain id %d\n", + node, id); return -EINVAL; } @@ -424,8 +424,8 @@ static int rockchip_pm_add_one_domain(struct rockchip_pmu *pmu, if (!pd->clks) return -ENOMEM; } else { - dev_dbg(pmu->dev, "%s: doesn't have clocks: %d\n", - node->name, pd->num_clks); + dev_dbg(pmu->dev, "%pOFn: doesn't have clocks: %d\n", + node, pd->num_clks); pd->num_clks = 0; } @@ -434,8 +434,8 @@ static int rockchip_pm_add_one_domain(struct rockchip_pmu *pmu, if (IS_ERR(pd->clks[i].clk)) { error = PTR_ERR(pd->clks[i].clk); dev_err(pmu->dev, - "%s: failed to get clk at index %d: %d\n", - node->name, i, error); + "%pOFn: failed to get clk at index %d: %d\n", + node, i, error); return error; } } @@ -486,8 +486,8 @@ static int rockchip_pm_add_one_domain(struct rockchip_pmu *pmu, error = rockchip_pd_power(pd, true); if (error) { dev_err(pmu->dev, - "failed to power on domain '%s': %d\n", - node->name, error); + "failed to power on domain '%pOFn': %d\n", + node, error); goto err_unprepare_clocks; } @@ -575,24 +575,24 @@ static int rockchip_pm_add_subdomain(struct rockchip_pmu *pmu, error = of_property_read_u32(parent, "reg", &idx); if (error) { dev_err(pmu->dev, - "%s: failed to retrieve domain id (reg): %d\n", - parent->name, error); + "%pOFn: failed to retrieve domain id (reg): %d\n", + parent, error); goto err_out; } parent_domain = pmu->genpd_data.domains[idx]; error = rockchip_pm_add_one_domain(pmu, np); if (error) { - dev_err(pmu->dev, "failed to handle node %s: %d\n", - np->name, error); + dev_err(pmu->dev, "failed to handle node %pOFn: %d\n", + np, error); goto err_out; } error = of_property_read_u32(np, "reg", &idx); if (error) { dev_err(pmu->dev, - "%s: failed to retrieve domain id (reg): %d\n", - np->name, error); + "%pOFn: failed to retrieve domain id (reg): %d\n", + np, error); goto err_out; } child_domain = pmu->genpd_data.domains[idx]; @@ -683,16 +683,16 @@ static int rockchip_pm_domain_probe(struct platform_device *pdev) for_each_available_child_of_node(np, node) { error = rockchip_pm_add_one_domain(pmu, node); if (error) { - dev_err(dev, "failed to handle node %s: %d\n", - node->name, error); + dev_err(dev, "failed to handle node %pOFn: %d\n", + node, error); of_node_put(node); goto err_out; } error = rockchip_pm_add_subdomain(pmu, node); if (error < 0) { - dev_err(dev, "failed to handle subdomain node %s: %d\n", - node->name, error); + dev_err(dev, "failed to handle subdomain node %pOFn: %d\n", + node, error); of_node_put(node); goto err_out; } diff --git a/drivers/soc/tegra/pmc.c b/drivers/soc/tegra/pmc.c index 2d6f3fcf3211..acbe63e925d5 100644 --- a/drivers/soc/tegra/pmc.c +++ b/drivers/soc/tegra/pmc.c @@ -796,7 +796,7 @@ static void tegra_powergate_add(struct tegra_pmc *pmc, struct device_node *np) id = tegra_powergate_lookup(pmc, np->name); if (id < 0) { - pr_err("powergate lookup failed for %s: %d\n", np->name, id); + pr_err("powergate lookup failed for %pOFn: %d\n", np, id); goto free_mem; } @@ -816,13 +816,13 @@ static void tegra_powergate_add(struct tegra_pmc *pmc, struct device_node *np) err = tegra_powergate_of_get_clks(pg, np); if (err < 0) { - pr_err("failed to get clocks for %s: %d\n", np->name, err); + pr_err("failed to get clocks for %pOFn: %d\n", np, err); goto set_available; } err = tegra_powergate_of_get_resets(pg, np, off); if (err < 0) { - pr_err("failed to get resets for %s: %d\n", np->name, err); + pr_err("failed to get resets for %pOFn: %d\n", np, err); goto remove_clks; } @@ -851,15 +851,15 @@ static void tegra_powergate_add(struct tegra_pmc *pmc, struct device_node *np) err = pm_genpd_init(&pg->genpd, NULL, off); if (err < 0) { - pr_err("failed to initialise PM domain %s: %d\n", np->name, + pr_err("failed to initialise PM domain %pOFn: %d\n", np, err); goto remove_resets; } err = of_genpd_add_provider_simple(np, &pg->genpd); if (err < 0) { - pr_err("failed to add PM domain provider for %s: %d\n", - np->name, err); + pr_err("failed to add PM domain provider for %pOFn: %d\n", + np, err); goto remove_genpd; } diff --git a/drivers/soc/ti/knav_dma.c b/drivers/soc/ti/knav_dma.c index 224d7ddeeb76..bbd4e5bc8707 100644 --- a/drivers/soc/ti/knav_dma.c +++ b/drivers/soc/ti/knav_dma.c @@ -544,15 +544,15 @@ static void __iomem *pktdma_get_regs(struct knav_dma_device *dma, ret = of_address_to_resource(node, index, &res); if (ret) { - dev_err(dev, "Can't translate of node(%s) address for index(%d)\n", - node->name, index); + dev_err(dev, "Can't translate of node(%pOFn) address for index(%d)\n", + node, index); return ERR_PTR(ret); } regs = devm_ioremap_resource(kdev->dev, &res); if (IS_ERR(regs)) - dev_err(dev, "Failed to map register base for index(%d) node(%s)\n", - index, node->name); + dev_err(dev, "Failed to map register base for index(%d) node(%pOFn)\n", + index, node); if (_size) *_size = resource_size(&res); diff --git a/drivers/soc/ti/knav_qmss_queue.c b/drivers/soc/ti/knav_qmss_queue.c index 6755f2af5619..b5d5673c255c 100644 --- a/drivers/soc/ti/knav_qmss_queue.c +++ b/drivers/soc/ti/knav_qmss_queue.c @@ -1382,15 +1382,15 @@ static void __iomem *knav_queue_map_reg(struct knav_device *kdev, ret = of_address_to_resource(node, index, &res); if (ret) { - dev_err(kdev->dev, "Can't translate of node(%s) address for index(%d)\n", - node->name, index); + dev_err(kdev->dev, "Can't translate of node(%pOFn) address for index(%d)\n", + node, index); return ERR_PTR(ret); } regs = devm_ioremap_resource(kdev->dev, &res); if (IS_ERR(regs)) - dev_err(kdev->dev, "Failed to map register base for index(%d) node(%s)\n", - index, node->name); + dev_err(kdev->dev, "Failed to map register base for index(%d) node(%pOFn)\n", + index, node); return regs; } diff --git a/drivers/tc/tc.c b/drivers/tc/tc.c index 3be9519654e5..cf3fad2cb871 100644 --- a/drivers/tc/tc.c +++ b/drivers/tc/tc.c @@ -2,7 +2,7 @@ * TURBOchannel bus services. * * Copyright (c) Harald Koerfgen, 1998 - * Copyright (c) 2001, 2003, 2005, 2006 Maciej W. Rozycki + * Copyright (c) 2001, 2003, 2005, 2006, 2018 Maciej W. Rozycki * Copyright (c) 2005 James Simmons * * This file is subject to the terms and conditions of the GNU @@ -10,6 +10,7 @@ * directory of this archive for more details. */ #include <linux/compiler.h> +#include <linux/dma-mapping.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/ioport.h> @@ -92,6 +93,11 @@ static void __init tc_bus_add_devices(struct tc_bus *tbus) tdev->dev.bus = &tc_bus_type; tdev->slot = slot; + /* TURBOchannel has 34-bit DMA addressing (16GiB space). */ + tdev->dma_mask = DMA_BIT_MASK(34); + tdev->dev.dma_mask = &tdev->dma_mask; + tdev->dev.coherent_dma_mask = DMA_BIT_MASK(34); + for (i = 0; i < 8; i++) { tdev->firmware[i] = readb(module + offset + TC_FIRM_VER + 4 * i); diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig index 0e69edc77d18..5422523c03f8 100644 --- a/drivers/thermal/Kconfig +++ b/drivers/thermal/Kconfig @@ -432,7 +432,7 @@ source "drivers/thermal/samsung/Kconfig" endmenu menu "STMicroelectronics thermal drivers" -depends on ARCH_STI && OF +depends on (ARCH_STI || ARCH_STM32) && OF source "drivers/thermal/st/Kconfig" endmenu diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile index 610344eb3e03..82bb50dc6423 100644 --- a/drivers/thermal/Makefile +++ b/drivers/thermal/Makefile @@ -53,7 +53,7 @@ obj-$(CONFIG_TI_SOC_THERMAL) += ti-soc-thermal/ obj-$(CONFIG_INT340X_THERMAL) += int340x_thermal/ obj-$(CONFIG_INTEL_BXT_PMIC_THERMAL) += intel_bxt_pmic_thermal.o obj-$(CONFIG_INTEL_PCH_THERMAL) += intel_pch_thermal.o -obj-$(CONFIG_ST_THERMAL) += st/ +obj-y += st/ obj-$(CONFIG_QCOM_TSENS) += qcom/ obj-y += tegra/ obj-$(CONFIG_HISI_THERMAL) += hisi_thermal.o diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c index 2c2f6d93034e..92f67d40f2e9 100644 --- a/drivers/thermal/armada_thermal.c +++ b/drivers/thermal/armada_thermal.c @@ -526,8 +526,8 @@ static int armada_thermal_probe_legacy(struct platform_device *pdev, /* First memory region points towards the status register */ res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (IS_ERR(res)) - return PTR_ERR(res); + if (!res) + return -EIO; /* * Edit the resource start address and length to map over all the diff --git a/drivers/thermal/da9062-thermal.c b/drivers/thermal/da9062-thermal.c index dd8dd947b7f0..01b0cb994457 100644 --- a/drivers/thermal/da9062-thermal.c +++ b/drivers/thermal/da9062-thermal.c @@ -106,7 +106,7 @@ static void da9062_thermal_poll_on(struct work_struct *work) THERMAL_EVENT_UNSPECIFIED); delay = msecs_to_jiffies(thermal->zone->passive_delay); - schedule_delayed_work(&thermal->work, delay); + queue_delayed_work(system_freezable_wq, &thermal->work, delay); return; } @@ -125,7 +125,7 @@ static irqreturn_t da9062_thermal_irq_handler(int irq, void *data) struct da9062_thermal *thermal = data; disable_irq_nosync(thermal->irq); - schedule_delayed_work(&thermal->work, 0); + queue_delayed_work(system_freezable_wq, &thermal->work, 0); return IRQ_HANDLED; } diff --git a/drivers/thermal/hisi_thermal.c b/drivers/thermal/hisi_thermal.c index 761d0559c268..c4111a98f1a7 100644 --- a/drivers/thermal/hisi_thermal.c +++ b/drivers/thermal/hisi_thermal.c @@ -55,25 +55,39 @@ #define HI3660_TEMP_STEP (205) #define HI3660_TEMP_LAG (4000) -#define HI6220_DEFAULT_SENSOR 2 -#define HI3660_DEFAULT_SENSOR 1 +#define HI6220_CLUSTER0_SENSOR 2 +#define HI6220_CLUSTER1_SENSOR 1 + +#define HI3660_LITTLE_SENSOR 0 +#define HI3660_BIG_SENSOR 1 +#define HI3660_G3D_SENSOR 2 +#define HI3660_MODEM_SENSOR 3 + +struct hisi_thermal_data; struct hisi_thermal_sensor { + struct hisi_thermal_data *data; struct thermal_zone_device *tzd; + const char *irq_name; uint32_t id; uint32_t thres_temp; }; +struct hisi_thermal_ops { + int (*get_temp)(struct hisi_thermal_sensor *sensor); + int (*enable_sensor)(struct hisi_thermal_sensor *sensor); + int (*disable_sensor)(struct hisi_thermal_sensor *sensor); + int (*irq_handler)(struct hisi_thermal_sensor *sensor); + int (*probe)(struct hisi_thermal_data *data); +}; + struct hisi_thermal_data { - int (*get_temp)(struct hisi_thermal_data *data); - int (*enable_sensor)(struct hisi_thermal_data *data); - int (*disable_sensor)(struct hisi_thermal_data *data); - int (*irq_handler)(struct hisi_thermal_data *data); + const struct hisi_thermal_ops *ops; + struct hisi_thermal_sensor *sensor; struct platform_device *pdev; struct clk *clk; - struct hisi_thermal_sensor sensor; void __iomem *regs; - int irq; + int nr_sensors; }; /* @@ -266,30 +280,40 @@ static inline void hi6220_thermal_hdak_set(void __iomem *addr, int value) (value << 4), addr + HI6220_TEMP0_CFG); } -static int hi6220_thermal_irq_handler(struct hisi_thermal_data *data) +static int hi6220_thermal_irq_handler(struct hisi_thermal_sensor *sensor) { + struct hisi_thermal_data *data = sensor->data; + hi6220_thermal_alarm_clear(data->regs, 1); return 0; } -static int hi3660_thermal_irq_handler(struct hisi_thermal_data *data) +static int hi3660_thermal_irq_handler(struct hisi_thermal_sensor *sensor) { - hi3660_thermal_alarm_clear(data->regs, data->sensor.id, 1); + struct hisi_thermal_data *data = sensor->data; + + hi3660_thermal_alarm_clear(data->regs, sensor->id, 1); return 0; } -static int hi6220_thermal_get_temp(struct hisi_thermal_data *data) +static int hi6220_thermal_get_temp(struct hisi_thermal_sensor *sensor) { + struct hisi_thermal_data *data = sensor->data; + return hi6220_thermal_get_temperature(data->regs); } -static int hi3660_thermal_get_temp(struct hisi_thermal_data *data) +static int hi3660_thermal_get_temp(struct hisi_thermal_sensor *sensor) { - return hi3660_thermal_get_temperature(data->regs, data->sensor.id); + struct hisi_thermal_data *data = sensor->data; + + return hi3660_thermal_get_temperature(data->regs, sensor->id); } -static int hi6220_thermal_disable_sensor(struct hisi_thermal_data *data) +static int hi6220_thermal_disable_sensor(struct hisi_thermal_sensor *sensor) { + struct hisi_thermal_data *data = sensor->data; + /* disable sensor module */ hi6220_thermal_enable(data->regs, 0); hi6220_thermal_alarm_enable(data->regs, 0); @@ -300,16 +324,18 @@ static int hi6220_thermal_disable_sensor(struct hisi_thermal_data *data) return 0; } -static int hi3660_thermal_disable_sensor(struct hisi_thermal_data *data) +static int hi3660_thermal_disable_sensor(struct hisi_thermal_sensor *sensor) { + struct hisi_thermal_data *data = sensor->data; + /* disable sensor module */ - hi3660_thermal_alarm_enable(data->regs, data->sensor.id, 0); + hi3660_thermal_alarm_enable(data->regs, sensor->id, 0); return 0; } -static int hi6220_thermal_enable_sensor(struct hisi_thermal_data *data) +static int hi6220_thermal_enable_sensor(struct hisi_thermal_sensor *sensor) { - struct hisi_thermal_sensor *sensor = &data->sensor; + struct hisi_thermal_data *data = sensor->data; int ret; /* enable clock for tsensor */ @@ -345,10 +371,10 @@ static int hi6220_thermal_enable_sensor(struct hisi_thermal_data *data) return 0; } -static int hi3660_thermal_enable_sensor(struct hisi_thermal_data *data) +static int hi3660_thermal_enable_sensor(struct hisi_thermal_sensor *sensor) { unsigned int value; - struct hisi_thermal_sensor *sensor = &data->sensor; + struct hisi_thermal_data *data = sensor->data; /* disable interrupt */ hi3660_thermal_alarm_enable(data->regs, sensor->id, 0); @@ -371,21 +397,8 @@ static int hi6220_thermal_probe(struct hisi_thermal_data *data) { struct platform_device *pdev = data->pdev; struct device *dev = &pdev->dev; - struct resource *res; int ret; - data->get_temp = hi6220_thermal_get_temp; - data->enable_sensor = hi6220_thermal_enable_sensor; - data->disable_sensor = hi6220_thermal_disable_sensor; - data->irq_handler = hi6220_thermal_irq_handler; - - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - data->regs = devm_ioremap_resource(dev, res); - if (IS_ERR(data->regs)) { - dev_err(dev, "failed to get io address\n"); - return PTR_ERR(data->regs); - } - data->clk = devm_clk_get(dev, "thermal_clk"); if (IS_ERR(data->clk)) { ret = PTR_ERR(data->clk); @@ -394,11 +407,14 @@ static int hi6220_thermal_probe(struct hisi_thermal_data *data) return ret; } - data->irq = platform_get_irq(pdev, 0); - if (data->irq < 0) - return data->irq; + data->sensor = devm_kzalloc(dev, sizeof(*data->sensor), GFP_KERNEL); + if (!data->sensor) + return -ENOMEM; - data->sensor.id = HI6220_DEFAULT_SENSOR; + data->sensor[0].id = HI6220_CLUSTER0_SENSOR; + data->sensor[0].irq_name = "tsensor_intr"; + data->sensor[0].data = data; + data->nr_sensors = 1; return 0; } @@ -407,38 +423,34 @@ static int hi3660_thermal_probe(struct hisi_thermal_data *data) { struct platform_device *pdev = data->pdev; struct device *dev = &pdev->dev; - struct resource *res; - data->get_temp = hi3660_thermal_get_temp; - data->enable_sensor = hi3660_thermal_enable_sensor; - data->disable_sensor = hi3660_thermal_disable_sensor; - data->irq_handler = hi3660_thermal_irq_handler; + data->nr_sensors = 2; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - data->regs = devm_ioremap_resource(dev, res); - if (IS_ERR(data->regs)) { - dev_err(dev, "failed to get io address\n"); - return PTR_ERR(data->regs); - } + data->sensor = devm_kzalloc(dev, sizeof(*data->sensor) * + data->nr_sensors, GFP_KERNEL); + if (!data->sensor) + return -ENOMEM; - data->irq = platform_get_irq(pdev, 0); - if (data->irq < 0) - return data->irq; + data->sensor[0].id = HI3660_BIG_SENSOR; + data->sensor[0].irq_name = "tsensor_a73"; + data->sensor[0].data = data; - data->sensor.id = HI3660_DEFAULT_SENSOR; + data->sensor[1].id = HI3660_LITTLE_SENSOR; + data->sensor[1].irq_name = "tsensor_a53"; + data->sensor[1].data = data; return 0; } static int hisi_thermal_get_temp(void *__data, int *temp) { - struct hisi_thermal_data *data = __data; - struct hisi_thermal_sensor *sensor = &data->sensor; + struct hisi_thermal_sensor *sensor = __data; + struct hisi_thermal_data *data = sensor->data; - *temp = data->get_temp(data); + *temp = data->ops->get_temp(sensor); - dev_dbg(&data->pdev->dev, "id=%d, temp=%d, thres=%d\n", - sensor->id, *temp, sensor->thres_temp); + dev_dbg(&data->pdev->dev, "tzd=%p, id=%d, temp=%d, thres=%d\n", + sensor->tzd, sensor->id, *temp, sensor->thres_temp); return 0; } @@ -449,38 +461,39 @@ static const struct thermal_zone_of_device_ops hisi_of_thermal_ops = { static irqreturn_t hisi_thermal_alarm_irq_thread(int irq, void *dev) { - struct hisi_thermal_data *data = dev; - struct hisi_thermal_sensor *sensor = &data->sensor; + struct hisi_thermal_sensor *sensor = dev; + struct hisi_thermal_data *data = sensor->data; int temp = 0; - data->irq_handler(data); + data->ops->irq_handler(sensor); - hisi_thermal_get_temp(data, &temp); + hisi_thermal_get_temp(sensor, &temp); if (temp >= sensor->thres_temp) { - dev_crit(&data->pdev->dev, "THERMAL ALARM: %d > %d\n", - temp, sensor->thres_temp); + dev_crit(&data->pdev->dev, + "sensor <%d> THERMAL ALARM: %d > %d\n", + sensor->id, temp, sensor->thres_temp); - thermal_zone_device_update(data->sensor.tzd, + thermal_zone_device_update(sensor->tzd, THERMAL_EVENT_UNSPECIFIED); } else { - dev_crit(&data->pdev->dev, "THERMAL ALARM stopped: %d < %d\n", - temp, sensor->thres_temp); + dev_crit(&data->pdev->dev, + "sensor <%d> THERMAL ALARM stopped: %d < %d\n", + sensor->id, temp, sensor->thres_temp); } return IRQ_HANDLED; } static int hisi_thermal_register_sensor(struct platform_device *pdev, - struct hisi_thermal_data *data, struct hisi_thermal_sensor *sensor) { int ret, i; const struct thermal_trip *trip; sensor->tzd = devm_thermal_zone_of_sensor_register(&pdev->dev, - sensor->id, data, + sensor->id, sensor, &hisi_of_thermal_ops); if (IS_ERR(sensor->tzd)) { ret = PTR_ERR(sensor->tzd); @@ -502,14 +515,30 @@ static int hisi_thermal_register_sensor(struct platform_device *pdev, return 0; } +static const struct hisi_thermal_ops hi6220_ops = { + .get_temp = hi6220_thermal_get_temp, + .enable_sensor = hi6220_thermal_enable_sensor, + .disable_sensor = hi6220_thermal_disable_sensor, + .irq_handler = hi6220_thermal_irq_handler, + .probe = hi6220_thermal_probe, +}; + +static const struct hisi_thermal_ops hi3660_ops = { + .get_temp = hi3660_thermal_get_temp, + .enable_sensor = hi3660_thermal_enable_sensor, + .disable_sensor = hi3660_thermal_disable_sensor, + .irq_handler = hi3660_thermal_irq_handler, + .probe = hi3660_thermal_probe, +}; + static const struct of_device_id of_hisi_thermal_match[] = { { .compatible = "hisilicon,tsensor", - .data = hi6220_thermal_probe + .data = &hi6220_ops, }, { .compatible = "hisilicon,hi3660-tsensor", - .data = hi3660_thermal_probe + .data = &hi3660_ops, }, { /* end */ } }; @@ -527,9 +556,9 @@ static void hisi_thermal_toggle_sensor(struct hisi_thermal_sensor *sensor, static int hisi_thermal_probe(struct platform_device *pdev) { struct hisi_thermal_data *data; - int (*platform_probe)(struct hisi_thermal_data *); struct device *dev = &pdev->dev; - int ret; + struct resource *res; + int i, ret; data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); if (!data) @@ -537,41 +566,50 @@ static int hisi_thermal_probe(struct platform_device *pdev) data->pdev = pdev; platform_set_drvdata(pdev, data); + data->ops = of_device_get_match_data(dev); - platform_probe = of_device_get_match_data(dev); - if (!platform_probe) { - dev_err(dev, "failed to get probe func\n"); - return -EINVAL; + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + data->regs = devm_ioremap_resource(dev, res); + if (IS_ERR(data->regs)) { + dev_err(dev, "failed to get io address\n"); + return PTR_ERR(data->regs); } - ret = platform_probe(data); + ret = data->ops->probe(data); if (ret) return ret; - ret = hisi_thermal_register_sensor(pdev, data, - &data->sensor); - if (ret) { - dev_err(dev, "failed to register thermal sensor: %d\n", ret); - return ret; - } + for (i = 0; i < data->nr_sensors; i++) { + struct hisi_thermal_sensor *sensor = &data->sensor[i]; - ret = data->enable_sensor(data); - if (ret) { - dev_err(dev, "Failed to setup the sensor: %d\n", ret); - return ret; - } + ret = hisi_thermal_register_sensor(pdev, sensor); + if (ret) { + dev_err(dev, "failed to register thermal sensor: %d\n", + ret); + return ret; + } + + ret = platform_get_irq_byname(pdev, sensor->irq_name); + if (ret < 0) + return ret; - if (data->irq) { - ret = devm_request_threaded_irq(dev, data->irq, NULL, - hisi_thermal_alarm_irq_thread, - IRQF_ONESHOT, "hisi_thermal", data); + ret = devm_request_threaded_irq(dev, ret, NULL, + hisi_thermal_alarm_irq_thread, + IRQF_ONESHOT, sensor->irq_name, + sensor); if (ret < 0) { - dev_err(dev, "failed to request alarm irq: %d\n", ret); + dev_err(dev, "Failed to request alarm irq: %d\n", ret); return ret; } - } - hisi_thermal_toggle_sensor(&data->sensor, true); + ret = data->ops->enable_sensor(sensor); + if (ret) { + dev_err(dev, "Failed to setup the sensor: %d\n", ret); + return ret; + } + + hisi_thermal_toggle_sensor(sensor, true); + } return 0; } @@ -579,11 +617,14 @@ static int hisi_thermal_probe(struct platform_device *pdev) static int hisi_thermal_remove(struct platform_device *pdev) { struct hisi_thermal_data *data = platform_get_drvdata(pdev); - struct hisi_thermal_sensor *sensor = &data->sensor; + int i; - hisi_thermal_toggle_sensor(sensor, false); + for (i = 0; i < data->nr_sensors; i++) { + struct hisi_thermal_sensor *sensor = &data->sensor[i]; - data->disable_sensor(data); + hisi_thermal_toggle_sensor(sensor, false); + data->ops->disable_sensor(sensor); + } return 0; } @@ -592,8 +633,10 @@ static int hisi_thermal_remove(struct platform_device *pdev) static int hisi_thermal_suspend(struct device *dev) { struct hisi_thermal_data *data = dev_get_drvdata(dev); + int i; - data->disable_sensor(data); + for (i = 0; i < data->nr_sensors; i++) + data->ops->disable_sensor(&data->sensor[i]); return 0; } @@ -601,8 +644,12 @@ static int hisi_thermal_suspend(struct device *dev) static int hisi_thermal_resume(struct device *dev) { struct hisi_thermal_data *data = dev_get_drvdata(dev); + int i, ret = 0; + + for (i = 0; i < data->nr_sensors; i++) + ret |= data->ops->enable_sensor(&data->sensor[i]); - return data->enable_sensor(data); + return ret; } #endif diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c index aa452acb60b6..15661549eb67 100644 --- a/drivers/thermal/imx_thermal.c +++ b/drivers/thermal/imx_thermal.c @@ -725,7 +725,7 @@ static int imx_thermal_probe(struct platform_device *pdev) } else { ret = imx_init_from_tempmon_data(pdev); if (ret) { - dev_err(&pdev->dev, "failed to init from from fsl,tempmon-data\n"); + dev_err(&pdev->dev, "failed to init from fsl,tempmon-data\n"); return ret; } } @@ -762,9 +762,7 @@ static int imx_thermal_probe(struct platform_device *pdev) if (ret != -EPROBE_DEFER) dev_err(&pdev->dev, "failed to get thermal clk: %d\n", ret); - cpufreq_cooling_unregister(data->cdev); - cpufreq_cpu_put(data->policy); - return ret; + goto cpufreq_put; } /* @@ -777,9 +775,7 @@ static int imx_thermal_probe(struct platform_device *pdev) ret = clk_prepare_enable(data->thermal_clk); if (ret) { dev_err(&pdev->dev, "failed to enable thermal clk: %d\n", ret); - cpufreq_cooling_unregister(data->cdev); - cpufreq_cpu_put(data->policy); - return ret; + goto cpufreq_put; } data->tz = thermal_zone_device_register("imx_thermal_zone", @@ -792,10 +788,7 @@ static int imx_thermal_probe(struct platform_device *pdev) ret = PTR_ERR(data->tz); dev_err(&pdev->dev, "failed to register thermal zone device %d\n", ret); - clk_disable_unprepare(data->thermal_clk); - cpufreq_cooling_unregister(data->cdev); - cpufreq_cpu_put(data->policy); - return ret; + goto clk_disable; } dev_info(&pdev->dev, "%s CPU temperature grade - max:%dC" @@ -827,14 +820,20 @@ static int imx_thermal_probe(struct platform_device *pdev) 0, "imx_thermal", data); if (ret < 0) { dev_err(&pdev->dev, "failed to request alarm irq: %d\n", ret); - clk_disable_unprepare(data->thermal_clk); - thermal_zone_device_unregister(data->tz); - cpufreq_cooling_unregister(data->cdev); - cpufreq_cpu_put(data->policy); - return ret; + goto thermal_zone_unregister; } return 0; + +thermal_zone_unregister: + thermal_zone_device_unregister(data->tz); +clk_disable: + clk_disable_unprepare(data->thermal_clk); +cpufreq_put: + cpufreq_cooling_unregister(data->cdev); + cpufreq_cpu_put(data->policy); + + return ret; } static int imx_thermal_remove(struct platform_device *pdev) diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c index 4f2816559205..4bfdb4a1e47d 100644 --- a/drivers/thermal/of-thermal.c +++ b/drivers/thermal/of-thermal.c @@ -19,23 +19,34 @@ /*** Private data structures to represent thermal device tree data ***/ /** - * struct __thermal_bind_param - a match between trip and cooling device + * struct __thermal_cooling_bind_param - a cooling device for a trip point * @cooling_device: a pointer to identify the referred cooling device - * @trip_id: the trip point index - * @usage: the percentage (from 0 to 100) of cooling contribution * @min: minimum cooling state used at this trip point * @max: maximum cooling state used at this trip point */ -struct __thermal_bind_params { +struct __thermal_cooling_bind_param { struct device_node *cooling_device; - unsigned int trip_id; - unsigned int usage; unsigned long min; unsigned long max; }; /** + * struct __thermal_bind_param - a match between trip and cooling device + * @tcbp: a pointer to an array of cooling devices + * @count: number of elements in array + * @trip_id: the trip point index + * @usage: the percentage (from 0 to 100) of cooling contribution + */ + +struct __thermal_bind_params { + struct __thermal_cooling_bind_param *tcbp; + unsigned int count; + unsigned int trip_id; + unsigned int usage; +}; + +/** * struct __thermal_zone - internal representation of a thermal zone * @mode: current thermal zone device mode (enabled/disabled) * @passive_delay: polling interval while passive cooling is activated @@ -192,25 +203,31 @@ static int of_thermal_bind(struct thermal_zone_device *thermal, struct thermal_cooling_device *cdev) { struct __thermal_zone *data = thermal->devdata; - int i; + struct __thermal_bind_params *tbp; + struct __thermal_cooling_bind_param *tcbp; + int i, j; if (!data || IS_ERR(data)) return -ENODEV; /* find where to bind */ for (i = 0; i < data->num_tbps; i++) { - struct __thermal_bind_params *tbp = data->tbps + i; + tbp = data->tbps + i; - if (tbp->cooling_device == cdev->np) { - int ret; + for (j = 0; j < tbp->count; j++) { + tcbp = tbp->tcbp + j; - ret = thermal_zone_bind_cooling_device(thermal, + if (tcbp->cooling_device == cdev->np) { + int ret; + + ret = thermal_zone_bind_cooling_device(thermal, tbp->trip_id, cdev, - tbp->max, - tbp->min, + tcbp->max, + tcbp->min, tbp->usage); - if (ret) - return ret; + if (ret) + return ret; + } } } @@ -221,22 +238,28 @@ static int of_thermal_unbind(struct thermal_zone_device *thermal, struct thermal_cooling_device *cdev) { struct __thermal_zone *data = thermal->devdata; - int i; + struct __thermal_bind_params *tbp; + struct __thermal_cooling_bind_param *tcbp; + int i, j; if (!data || IS_ERR(data)) return -ENODEV; /* find where to unbind */ for (i = 0; i < data->num_tbps; i++) { - struct __thermal_bind_params *tbp = data->tbps + i; + tbp = data->tbps + i; + + for (j = 0; j < tbp->count; j++) { + tcbp = tbp->tcbp + j; - if (tbp->cooling_device == cdev->np) { - int ret; + if (tcbp->cooling_device == cdev->np) { + int ret; - ret = thermal_zone_unbind_cooling_device(thermal, - tbp->trip_id, cdev); - if (ret) - return ret; + ret = thermal_zone_unbind_cooling_device(thermal, + tbp->trip_id, cdev); + if (ret) + return ret; + } } } @@ -486,8 +509,8 @@ thermal_zone_of_sensor_register(struct device *dev, int sensor_id, void *data, if (sensor_specs.args_count >= 1) { id = sensor_specs.args[0]; WARN(sensor_specs.args_count > 1, - "%s: too many cells in sensor specifier %d\n", - sensor_specs.np->name, sensor_specs.args_count); + "%pOFn: too many cells in sensor specifier %d\n", + sensor_specs.np, sensor_specs.args_count); } else { id = 0; } @@ -655,8 +678,9 @@ static int thermal_of_populate_bind_params(struct device_node *np, int ntrips) { struct of_phandle_args cooling_spec; + struct __thermal_cooling_bind_param *__tcbp; struct device_node *trip; - int ret, i; + int ret, i, count; u32 prop; /* Default weight. Usage is optional */ @@ -683,20 +707,44 @@ static int thermal_of_populate_bind_params(struct device_node *np, goto end; } - ret = of_parse_phandle_with_args(np, "cooling-device", "#cooling-cells", - 0, &cooling_spec); - if (ret < 0) { - pr_err("missing cooling_device property\n"); + count = of_count_phandle_with_args(np, "cooling-device", + "#cooling-cells"); + if (!count) { + pr_err("Add a cooling_device property with at least one device\n"); goto end; } - __tbp->cooling_device = cooling_spec.np; - if (cooling_spec.args_count >= 2) { /* at least min and max */ - __tbp->min = cooling_spec.args[0]; - __tbp->max = cooling_spec.args[1]; - } else { - pr_err("wrong reference to cooling device, missing limits\n"); + + __tcbp = kcalloc(count, sizeof(*__tcbp), GFP_KERNEL); + if (!__tcbp) + goto end; + + for (i = 0; i < count; i++) { + ret = of_parse_phandle_with_args(np, "cooling-device", + "#cooling-cells", i, &cooling_spec); + if (ret < 0) { + pr_err("Invalid cooling-device entry\n"); + goto free_tcbp; + } + + __tcbp[i].cooling_device = cooling_spec.np; + + if (cooling_spec.args_count >= 2) { /* at least min and max */ + __tcbp[i].min = cooling_spec.args[0]; + __tcbp[i].max = cooling_spec.args[1]; + } else { + pr_err("wrong reference to cooling device, missing limits\n"); + } } + __tbp->tcbp = __tcbp; + __tbp->count = count; + + goto end; + +free_tcbp: + for (i = i - 1; i >= 0; i--) + of_node_put(__tcbp[i].cooling_device); + kfree(__tcbp); end: of_node_put(trip); @@ -903,8 +951,16 @@ finish: return tz; free_tbps: - for (i = i - 1; i >= 0; i--) - of_node_put(tz->tbps[i].cooling_device); + for (i = i - 1; i >= 0; i--) { + struct __thermal_bind_params *tbp = tz->tbps + i; + int j; + + for (j = 0; j < tbp->count; j++) + of_node_put(tbp->tcbp[j].cooling_device); + + kfree(tbp->tcbp); + } + kfree(tz->tbps); free_trips: for (i = 0; i < tz->ntrips; i++) @@ -920,10 +976,18 @@ free_tz: static inline void of_thermal_free_zone(struct __thermal_zone *tz) { - int i; + struct __thermal_bind_params *tbp; + int i, j; + + for (i = 0; i < tz->num_tbps; i++) { + tbp = tz->tbps + i; + + for (j = 0; j < tbp->count; j++) + of_node_put(tbp->tcbp[j].cooling_device); + + kfree(tbp->tcbp); + } - for (i = 0; i < tz->num_tbps; i++) - of_node_put(tz->tbps[i].cooling_device); kfree(tz->tbps); for (i = 0; i < tz->ntrips; i++) of_node_put(tz->trips[i].np); @@ -963,8 +1027,8 @@ int __init of_parse_thermal_zones(void) tz = thermal_of_build_thermal_zone(child); if (IS_ERR(tz)) { - pr_err("failed to build thermal zone %s: %ld\n", - child->name, + pr_err("failed to build thermal zone %pOFn: %ld\n", + child, PTR_ERR(tz)); continue; } @@ -998,7 +1062,7 @@ int __init of_parse_thermal_zones(void) tz->passive_delay, tz->polling_delay); if (IS_ERR(zone)) { - pr_err("Failed to build %s zone %ld\n", child->name, + pr_err("Failed to build %pOFn zone %ld\n", child, PTR_ERR(zone)); kfree(tzp); kfree(ops); diff --git a/drivers/thermal/qcom-spmi-temp-alarm.c b/drivers/thermal/qcom-spmi-temp-alarm.c index ad4f3a8d6560..b2d5d5bf4a9b 100644 --- a/drivers/thermal/qcom-spmi-temp-alarm.c +++ b/drivers/thermal/qcom-spmi-temp-alarm.c @@ -23,6 +23,8 @@ #include <linux/regmap.h> #include <linux/thermal.h> +#include "thermal_core.h" + #define QPNP_TM_REG_TYPE 0x04 #define QPNP_TM_REG_SUBTYPE 0x05 #define QPNP_TM_REG_STATUS 0x08 @@ -37,9 +39,11 @@ #define STATUS_GEN2_STATE_MASK GENMASK(6, 4) #define STATUS_GEN2_STATE_SHIFT 4 -#define SHUTDOWN_CTRL1_OVERRIDE_MASK GENMASK(7, 6) +#define SHUTDOWN_CTRL1_OVERRIDE_S2 BIT(6) #define SHUTDOWN_CTRL1_THRESHOLD_MASK GENMASK(1, 0) +#define SHUTDOWN_CTRL1_RATE_25HZ BIT(3) + #define ALARM_CTRL_FORCE_ENABLE BIT(7) /* @@ -56,12 +60,19 @@ #define TEMP_THRESH_STEP 5000 /* Threshold step: 5 C */ #define THRESH_MIN 0 +#define THRESH_MAX 3 + +/* Stage 2 Threshold Min: 125 C */ +#define STAGE2_THRESHOLD_MIN 125000 +/* Stage 2 Threshold Max: 140 C */ +#define STAGE2_THRESHOLD_MAX 140000 /* Temperature in Milli Celsius reported during stage 0 if no ADC is present */ #define DEFAULT_TEMP 37000 struct qpnp_tm_chip { struct regmap *map; + struct device *dev; struct thermal_zone_device *tz_dev; unsigned int subtype; long temp; @@ -69,6 +80,10 @@ struct qpnp_tm_chip { unsigned int stage; unsigned int prev_stage; unsigned int base; + /* protects .thresh, .stage and chip registers */ + struct mutex lock; + bool initialized; + struct iio_channel *adc; }; @@ -125,6 +140,8 @@ static int qpnp_tm_update_temp_no_adc(struct qpnp_tm_chip *chip) unsigned int stage, stage_new, stage_old; int ret; + WARN_ON(!mutex_is_locked(&chip->lock)); + ret = qpnp_tm_get_temp_stage(chip); if (ret < 0) return ret; @@ -163,8 +180,15 @@ static int qpnp_tm_get_temp(void *data, int *temp) if (!temp) return -EINVAL; + if (!chip->initialized) { + *temp = DEFAULT_TEMP; + return 0; + } + if (!chip->adc) { + mutex_lock(&chip->lock); ret = qpnp_tm_update_temp_no_adc(chip); + mutex_unlock(&chip->lock); if (ret < 0) return ret; } else { @@ -180,8 +204,72 @@ static int qpnp_tm_get_temp(void *data, int *temp) return 0; } +static int qpnp_tm_update_critical_trip_temp(struct qpnp_tm_chip *chip, + int temp) +{ + u8 reg; + bool disable_s2_shutdown = false; + + WARN_ON(!mutex_is_locked(&chip->lock)); + + /* + * Default: S2 and S3 shutdown enabled, thresholds at + * 105C/125C/145C, monitoring at 25Hz + */ + reg = SHUTDOWN_CTRL1_RATE_25HZ; + + if (temp == THERMAL_TEMP_INVALID || + temp < STAGE2_THRESHOLD_MIN) { + chip->thresh = THRESH_MIN; + goto skip; + } + + if (temp <= STAGE2_THRESHOLD_MAX) { + chip->thresh = THRESH_MAX - + ((STAGE2_THRESHOLD_MAX - temp) / + TEMP_THRESH_STEP); + disable_s2_shutdown = true; + } else { + chip->thresh = THRESH_MAX; + + if (chip->adc) + disable_s2_shutdown = true; + else + dev_warn(chip->dev, + "No ADC is configured and critical temperature is above the maximum stage 2 threshold of 140 C! Configuring stage 2 shutdown at 140 C.\n"); + } + +skip: + reg |= chip->thresh; + if (disable_s2_shutdown) + reg |= SHUTDOWN_CTRL1_OVERRIDE_S2; + + return qpnp_tm_write(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, reg); +} + +static int qpnp_tm_set_trip_temp(void *data, int trip, int temp) +{ + struct qpnp_tm_chip *chip = data; + const struct thermal_trip *trip_points; + int ret; + + trip_points = of_thermal_get_trip_points(chip->tz_dev); + if (!trip_points) + return -EINVAL; + + if (trip_points[trip].type != THERMAL_TRIP_CRITICAL) + return 0; + + mutex_lock(&chip->lock); + ret = qpnp_tm_update_critical_trip_temp(chip, temp); + mutex_unlock(&chip->lock); + + return ret; +} + static const struct thermal_zone_of_device_ops qpnp_tm_sensor_ops = { .get_temp = qpnp_tm_get_temp, + .set_trip_temp = qpnp_tm_set_trip_temp, }; static irqreturn_t qpnp_tm_isr(int irq, void *data) @@ -193,6 +281,29 @@ static irqreturn_t qpnp_tm_isr(int irq, void *data) return IRQ_HANDLED; } +static int qpnp_tm_get_critical_trip_temp(struct qpnp_tm_chip *chip) +{ + int ntrips; + const struct thermal_trip *trips; + int i; + + ntrips = of_thermal_get_ntrips(chip->tz_dev); + if (ntrips <= 0) + return THERMAL_TEMP_INVALID; + + trips = of_thermal_get_trip_points(chip->tz_dev); + if (!trips) + return THERMAL_TEMP_INVALID; + + for (i = 0; i < ntrips; i++) { + if (of_thermal_is_trip_valid(chip->tz_dev, i) && + trips[i].type == THERMAL_TRIP_CRITICAL) + return trips[i].temperature; + } + + return THERMAL_TEMP_INVALID; +} + /* * This function initializes the internal temp value based on only the * current thermal stage and threshold. Setup threshold control and @@ -203,17 +314,20 @@ static int qpnp_tm_init(struct qpnp_tm_chip *chip) unsigned int stage; int ret; u8 reg = 0; + int crit_temp; + + mutex_lock(&chip->lock); ret = qpnp_tm_read(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, ®); if (ret < 0) - return ret; + goto out; chip->thresh = reg & SHUTDOWN_CTRL1_THRESHOLD_MASK; chip->temp = DEFAULT_TEMP; ret = qpnp_tm_get_temp_stage(chip); if (ret < 0) - return ret; + goto out; chip->stage = ret; stage = chip->subtype == QPNP_TM_SUBTYPE_GEN1 @@ -224,21 +338,19 @@ static int qpnp_tm_init(struct qpnp_tm_chip *chip) (stage - 1) * TEMP_STAGE_STEP + TEMP_THRESH_MIN; - /* - * Set threshold and disable software override of stage 2 and 3 - * shutdowns. - */ - chip->thresh = THRESH_MIN; - reg &= ~(SHUTDOWN_CTRL1_OVERRIDE_MASK | SHUTDOWN_CTRL1_THRESHOLD_MASK); - reg |= chip->thresh & SHUTDOWN_CTRL1_THRESHOLD_MASK; - ret = qpnp_tm_write(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, reg); + crit_temp = qpnp_tm_get_critical_trip_temp(chip); + ret = qpnp_tm_update_critical_trip_temp(chip, crit_temp); if (ret < 0) - return ret; + goto out; /* Enable the thermal alarm PMIC module in always-on mode. */ reg = ALARM_CTRL_FORCE_ENABLE; ret = qpnp_tm_write(chip, QPNP_TM_REG_ALARM_CTRL, reg); + chip->initialized = true; + +out: + mutex_unlock(&chip->lock); return ret; } @@ -257,6 +369,9 @@ static int qpnp_tm_probe(struct platform_device *pdev) return -ENOMEM; dev_set_drvdata(&pdev->dev, chip); + chip->dev = &pdev->dev; + + mutex_init(&chip->lock); chip->map = dev_get_regmap(pdev->dev.parent, NULL); if (!chip->map) @@ -302,6 +417,18 @@ static int qpnp_tm_probe(struct platform_device *pdev) chip->subtype = subtype; + /* + * Register the sensor before initializing the hardware to be able to + * read the trip points. get_temp() returns the default temperature + * before the hardware initialization is completed. + */ + chip->tz_dev = devm_thermal_zone_of_sensor_register( + &pdev->dev, 0, chip, &qpnp_tm_sensor_ops); + if (IS_ERR(chip->tz_dev)) { + dev_err(&pdev->dev, "failed to register sensor\n"); + return PTR_ERR(chip->tz_dev); + } + ret = qpnp_tm_init(chip); if (ret < 0) { dev_err(&pdev->dev, "init failed\n"); @@ -313,12 +440,7 @@ static int qpnp_tm_probe(struct platform_device *pdev) if (ret < 0) return ret; - chip->tz_dev = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, chip, - &qpnp_tm_sensor_ops); - if (IS_ERR(chip->tz_dev)) { - dev_err(&pdev->dev, "failed to register sensor\n"); - return PTR_ERR(chip->tz_dev); - } + thermal_zone_device_update(chip->tz_dev, THERMAL_EVENT_UNSPECIFIED); return 0; } diff --git a/drivers/thermal/qcom/tsens-8916.c b/drivers/thermal/qcom/tsens-8916.c index fdf561b8b81d..c6dd620ac029 100644 --- a/drivers/thermal/qcom/tsens-8916.c +++ b/drivers/thermal/qcom/tsens-8916.c @@ -1,15 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2015, 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. - * */ #include <linux/platform_device.h> @@ -109,5 +100,6 @@ static const struct tsens_ops ops_8916 = { const struct tsens_data data_8916 = { .num_sensors = 5, .ops = &ops_8916, + .reg_offsets = { [SROT_CTRL_OFFSET] = 0x0 }, .hw_ids = (unsigned int []){0, 1, 2, 4, 5 }, }; diff --git a/drivers/thermal/qcom/tsens-8960.c b/drivers/thermal/qcom/tsens-8960.c index 0451277d3a8f..0f0adb302a7b 100644 --- a/drivers/thermal/qcom/tsens-8960.c +++ b/drivers/thermal/qcom/tsens-8960.c @@ -1,15 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2015, 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. - * */ #include <linux/platform_device.h> @@ -69,7 +60,7 @@ static int suspend_8960(struct tsens_device *tmdev) { int ret; unsigned int mask; - struct regmap *map = tmdev->map; + struct regmap *map = tmdev->tm_map; ret = regmap_read(map, THRESHOLD_ADDR, &tmdev->ctx.threshold); if (ret) @@ -94,7 +85,7 @@ static int suspend_8960(struct tsens_device *tmdev) static int resume_8960(struct tsens_device *tmdev) { int ret; - struct regmap *map = tmdev->map; + struct regmap *map = tmdev->tm_map; ret = regmap_update_bits(map, CNTL_ADDR, SW_RST, SW_RST); if (ret) @@ -126,12 +117,12 @@ static int enable_8960(struct tsens_device *tmdev, int id) int ret; u32 reg, mask; - ret = regmap_read(tmdev->map, CNTL_ADDR, ®); + ret = regmap_read(tmdev->tm_map, CNTL_ADDR, ®); if (ret) return ret; mask = BIT(id + SENSOR0_SHIFT); - ret = regmap_write(tmdev->map, CNTL_ADDR, reg | SW_RST); + ret = regmap_write(tmdev->tm_map, CNTL_ADDR, reg | SW_RST); if (ret) return ret; @@ -140,7 +131,7 @@ static int enable_8960(struct tsens_device *tmdev, int id) else reg |= mask | SLP_CLK_ENA_8660 | EN; - ret = regmap_write(tmdev->map, CNTL_ADDR, reg); + ret = regmap_write(tmdev->tm_map, CNTL_ADDR, reg); if (ret) return ret; @@ -157,7 +148,7 @@ static void disable_8960(struct tsens_device *tmdev) mask <<= SENSOR0_SHIFT; mask |= EN; - ret = regmap_read(tmdev->map, CNTL_ADDR, ®_cntl); + ret = regmap_read(tmdev->tm_map, CNTL_ADDR, ®_cntl); if (ret) return; @@ -168,7 +159,7 @@ static void disable_8960(struct tsens_device *tmdev) else reg_cntl &= ~SLP_CLK_ENA_8660; - regmap_write(tmdev->map, CNTL_ADDR, reg_cntl); + regmap_write(tmdev->tm_map, CNTL_ADDR, reg_cntl); } static int init_8960(struct tsens_device *tmdev) @@ -176,8 +167,8 @@ static int init_8960(struct tsens_device *tmdev) int ret, i; u32 reg_cntl; - tmdev->map = dev_get_regmap(tmdev->dev, NULL); - if (!tmdev->map) + tmdev->tm_map = dev_get_regmap(tmdev->dev, NULL); + if (!tmdev->tm_map) return -ENODEV; /* @@ -193,14 +184,14 @@ static int init_8960(struct tsens_device *tmdev) } reg_cntl = SW_RST; - ret = regmap_update_bits(tmdev->map, CNTL_ADDR, SW_RST, reg_cntl); + ret = regmap_update_bits(tmdev->tm_map, CNTL_ADDR, SW_RST, reg_cntl); if (ret) return ret; if (tmdev->num_sensors > 1) { reg_cntl |= SLP_CLK_ENA | (MEASURE_PERIOD << 18); reg_cntl &= ~SW_RST; - ret = regmap_update_bits(tmdev->map, CONFIG_ADDR, + ret = regmap_update_bits(tmdev->tm_map, CONFIG_ADDR, CONFIG_MASK, CONFIG); } else { reg_cntl |= SLP_CLK_ENA_8660 | (MEASURE_PERIOD << 16); @@ -209,12 +200,12 @@ static int init_8960(struct tsens_device *tmdev) } reg_cntl |= GENMASK(tmdev->num_sensors - 1, 0) << SENSOR0_SHIFT; - ret = regmap_write(tmdev->map, CNTL_ADDR, reg_cntl); + ret = regmap_write(tmdev->tm_map, CNTL_ADDR, reg_cntl); if (ret) return ret; reg_cntl |= EN; - ret = regmap_write(tmdev->map, CNTL_ADDR, reg_cntl); + ret = regmap_write(tmdev->tm_map, CNTL_ADDR, reg_cntl); if (ret) return ret; @@ -261,12 +252,12 @@ static int get_temp_8960(struct tsens_device *tmdev, int id, int *temp) timeout = jiffies + usecs_to_jiffies(TIMEOUT_US); do { - ret = regmap_read(tmdev->map, INT_STATUS_ADDR, &trdy); + ret = regmap_read(tmdev->tm_map, INT_STATUS_ADDR, &trdy); if (ret) return ret; if (!(trdy & TRDY_MASK)) continue; - ret = regmap_read(tmdev->map, s->status, &code); + ret = regmap_read(tmdev->tm_map, s->status, &code); if (ret) return ret; *temp = code_to_mdegC(code, s); diff --git a/drivers/thermal/qcom/tsens-8974.c b/drivers/thermal/qcom/tsens-8974.c index 9baf77e8cbe3..3d3fda3d731b 100644 --- a/drivers/thermal/qcom/tsens-8974.c +++ b/drivers/thermal/qcom/tsens-8974.c @@ -1,15 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2015, 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. - * */ #include <linux/platform_device.h> @@ -241,4 +232,5 @@ static const struct tsens_ops ops_8974 = { const struct tsens_data data_8974 = { .num_sensors = 11, .ops = &ops_8974, + .reg_offsets = { [SROT_CTRL_OFFSET] = 0x0 }, }; diff --git a/drivers/thermal/qcom/tsens-common.c b/drivers/thermal/qcom/tsens-common.c index 6207d8d92351..3be4be2e0465 100644 --- a/drivers/thermal/qcom/tsens-common.c +++ b/drivers/thermal/qcom/tsens-common.c @@ -1,15 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2015, 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. - * */ #include <linux/err.h> @@ -21,7 +12,11 @@ #include <linux/regmap.h> #include "tsens.h" -#define S0_ST_ADDR 0x1030 +/* SROT */ +#define TSENS_EN BIT(0) + +/* TM */ +#define STATUS_OFFSET 0x30 #define SN_ADDR_OFFSET 0x4 #define SN_ST_TEMP_MASK 0x3ff #define CAL_DEGC_PT1 30 @@ -107,8 +102,8 @@ int get_temp_common(struct tsens_device *tmdev, int id, int *temp) unsigned int status_reg; int last_temp = 0, ret; - status_reg = S0_ST_ADDR + s->hw_id * SN_ADDR_OFFSET; - ret = regmap_read(tmdev->map, status_reg, &code); + status_reg = tmdev->tm_offset + STATUS_OFFSET + s->hw_id * SN_ADDR_OFFSET; + ret = regmap_read(tmdev->tm_map, status_reg, &code); if (ret) return ret; last_temp = code & SN_ST_TEMP_MASK; @@ -126,29 +121,52 @@ static const struct regmap_config tsens_config = { int __init init_common(struct tsens_device *tmdev) { - void __iomem *base; + void __iomem *tm_base, *srot_base; struct resource *res; + u32 code; + int ret; struct platform_device *op = of_find_device_by_node(tmdev->dev->of_node); + u16 ctrl_offset = tmdev->reg_offsets[SROT_CTRL_OFFSET]; if (!op) return -EINVAL; - /* The driver only uses the TM register address space for now */ if (op->num_resources > 1) { + /* DT with separate SROT and TM address space */ tmdev->tm_offset = 0; + res = platform_get_resource(op, IORESOURCE_MEM, 1); + srot_base = devm_ioremap_resource(&op->dev, res); + if (IS_ERR(srot_base)) + return PTR_ERR(srot_base); + + tmdev->srot_map = devm_regmap_init_mmio(tmdev->dev, + srot_base, &tsens_config); + if (IS_ERR(tmdev->srot_map)) + return PTR_ERR(tmdev->srot_map); + } else { /* old DTs where SROT and TM were in a contiguous 2K block */ tmdev->tm_offset = 0x1000; } res = platform_get_resource(op, IORESOURCE_MEM, 0); - base = devm_ioremap_resource(&op->dev, res); - if (IS_ERR(base)) - return PTR_ERR(base); - - tmdev->map = devm_regmap_init_mmio(tmdev->dev, base, &tsens_config); - if (IS_ERR(tmdev->map)) - return PTR_ERR(tmdev->map); + tm_base = devm_ioremap_resource(&op->dev, res); + if (IS_ERR(tm_base)) + return PTR_ERR(tm_base); + + tmdev->tm_map = devm_regmap_init_mmio(tmdev->dev, tm_base, &tsens_config); + if (IS_ERR(tmdev->tm_map)) + return PTR_ERR(tmdev->tm_map); + + if (tmdev->srot_map) { + ret = regmap_read(tmdev->srot_map, ctrl_offset, &code); + if (ret) + return ret; + if (!(code & TSENS_EN)) { + dev_err(tmdev->dev, "tsens device is not enabled\n"); + return -ENODEV; + } + } return 0; } diff --git a/drivers/thermal/qcom/tsens-v2.c b/drivers/thermal/qcom/tsens-v2.c index 44da02f594ac..381a212872bf 100644 --- a/drivers/thermal/qcom/tsens-v2.c +++ b/drivers/thermal/qcom/tsens-v2.c @@ -21,7 +21,7 @@ static int get_temp_tsens_v2(struct tsens_device *tmdev, int id, int *temp) int ret; status_reg = tmdev->tm_offset + STATUS_OFFSET + s->hw_id * 4; - ret = regmap_read(tmdev->map, status_reg, &code); + ret = regmap_read(tmdev->tm_map, status_reg, &code); if (ret) return ret; last_temp = code & LAST_TEMP_MASK; @@ -29,7 +29,7 @@ static int get_temp_tsens_v2(struct tsens_device *tmdev, int id, int *temp) goto done; /* Try a second time */ - ret = regmap_read(tmdev->map, status_reg, &code); + ret = regmap_read(tmdev->tm_map, status_reg, &code); if (ret) return ret; if (code & STATUS_VALID_BIT) { @@ -40,7 +40,7 @@ static int get_temp_tsens_v2(struct tsens_device *tmdev, int id, int *temp) } /* Try a third/last time */ - ret = regmap_read(tmdev->map, status_reg, &code); + ret = regmap_read(tmdev->tm_map, status_reg, &code); if (ret) return ret; if (code & STATUS_VALID_BIT) { @@ -68,10 +68,12 @@ static const struct tsens_ops ops_generic_v2 = { const struct tsens_data data_tsens_v2 = { .ops = &ops_generic_v2, + .reg_offsets = { [SROT_CTRL_OFFSET] = 0x4 }, }; /* Kept around for backward compatibility with old msm8996.dtsi */ const struct tsens_data data_8996 = { .num_sensors = 13, .ops = &ops_generic_v2, + .reg_offsets = { [SROT_CTRL_OFFSET] = 0x4 }, }; diff --git a/drivers/thermal/qcom/tsens.c b/drivers/thermal/qcom/tsens.c index a2c9bfae3d86..f1ec9bbe4717 100644 --- a/drivers/thermal/qcom/tsens.c +++ b/drivers/thermal/qcom/tsens.c @@ -1,15 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2015, 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. - * */ #include <linux/err.h> @@ -89,11 +80,6 @@ static int tsens_register(struct tsens_device *tmdev) { int i; struct thermal_zone_device *tzd; - u32 *hw_id, n = tmdev->num_sensors; - - hw_id = devm_kcalloc(tmdev->dev, n, sizeof(u32), GFP_KERNEL); - if (!hw_id) - return -ENOMEM; for (i = 0; i < tmdev->num_sensors; i++) { tmdev->sensor[i].tmdev = tmdev; @@ -158,6 +144,9 @@ static int tsens_probe(struct platform_device *pdev) else tmdev->sensor[i].hw_id = i; } + for (i = 0; i < REG_ARRAY_SIZE; i++) { + tmdev->reg_offsets[i] = data->reg_offsets[i]; + } if (!tmdev->ops || !tmdev->ops->init || !tmdev->ops->get_temp) return -EINVAL; diff --git a/drivers/thermal/qcom/tsens.h b/drivers/thermal/qcom/tsens.h index 14331eb45a86..7b7feee5dc46 100644 --- a/drivers/thermal/qcom/tsens.h +++ b/drivers/thermal/qcom/tsens.h @@ -1,15 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2015, The Linux Foundation. All rights reserved. - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * 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 __QCOM_TSENS_H__ #define __QCOM_TSENS_H__ @@ -55,15 +48,23 @@ struct tsens_ops { int (*get_trend)(struct tsens_device *, int, enum thermal_trend *); }; +enum reg_list { + SROT_CTRL_OFFSET, + + REG_ARRAY_SIZE, +}; + /** * struct tsens_data - tsens instance specific data * @num_sensors: Max number of sensors supported by platform * @ops: operations the tsens instance supports * @hw_ids: Subset of sensors ids supported by platform, if not the first n + * @reg_offsets: Register offsets for commonly used registers */ struct tsens_data { const u32 num_sensors; const struct tsens_ops *ops; + const u16 reg_offsets[REG_ARRAY_SIZE]; unsigned int *hw_ids; }; @@ -76,8 +77,10 @@ struct tsens_context { struct tsens_device { struct device *dev; u32 num_sensors; - struct regmap *map; + struct regmap *tm_map; + struct regmap *srot_map; u32 tm_offset; + u16 reg_offsets[REG_ARRAY_SIZE]; struct tsens_context ctx; const struct tsens_ops *ops; struct tsens_sensor sensor[0]; diff --git a/drivers/thermal/qoriq_thermal.c b/drivers/thermal/qoriq_thermal.c index 450ed66edf58..18c711b19514 100644 --- a/drivers/thermal/qoriq_thermal.c +++ b/drivers/thermal/qoriq_thermal.c @@ -119,8 +119,8 @@ static int qoriq_tmu_get_sensor_id(void) if (sensor_specs.args_count >= 1) { id = sensor_specs.args[0]; WARN(sensor_specs.args_count > 1, - "%s: too many cells in sensor specifier %d\n", - sensor_specs.np->name, sensor_specs.args_count); + "%pOFn: too many cells in sensor specifier %d\n", + sensor_specs.np, sensor_specs.args_count); } else { id = 0; } @@ -294,6 +294,7 @@ static SIMPLE_DEV_PM_OPS(qoriq_tmu_pm_ops, static const struct of_device_id qoriq_tmu_match[] = { { .compatible = "fsl,qoriq-tmu", }, + { .compatible = "fsl,imx8mq-tmu", }, {}, }; MODULE_DEVICE_TABLE(of, qoriq_tmu_match); diff --git a/drivers/thermal/rcar_gen3_thermal.c b/drivers/thermal/rcar_gen3_thermal.c index 7aed5337bdd3..75786cc8e2f9 100644 --- a/drivers/thermal/rcar_gen3_thermal.c +++ b/drivers/thermal/rcar_gen3_thermal.c @@ -318,9 +318,11 @@ static void rcar_gen3_thermal_init(struct rcar_gen3_thermal_tsc *tsc) } static const struct of_device_id rcar_gen3_thermal_dt_ids[] = { + { .compatible = "renesas,r8a774a1-thermal", }, { .compatible = "renesas,r8a7795-thermal", }, { .compatible = "renesas,r8a7796-thermal", }, { .compatible = "renesas,r8a77965-thermal", }, + { .compatible = "renesas,r8a77980-thermal", }, {}, }; MODULE_DEVICE_TABLE(of, rcar_gen3_thermal_dt_ids); diff --git a/drivers/thermal/rcar_thermal.c b/drivers/thermal/rcar_thermal.c index 78f932822d38..8014a207d8d9 100644 --- a/drivers/thermal/rcar_thermal.c +++ b/drivers/thermal/rcar_thermal.c @@ -113,6 +113,10 @@ static const struct of_device_id rcar_thermal_dt_ids[] = { .data = &rcar_gen2_thermal, }, { + .compatible = "renesas,thermal-r8a77970", + .data = &rcar_gen3_thermal, + }, + { .compatible = "renesas,thermal-r8a77995", .data = &rcar_gen3_thermal, }, @@ -434,8 +438,8 @@ static irqreturn_t rcar_thermal_irq(int irq, void *data) rcar_thermal_for_each_priv(priv, common) { if (rcar_thermal_had_changed(priv, status)) { rcar_thermal_irq_disable(priv); - schedule_delayed_work(&priv->work, - msecs_to_jiffies(300)); + queue_delayed_work(system_freezable_wq, &priv->work, + msecs_to_jiffies(300)); } } @@ -453,6 +457,7 @@ static int rcar_thermal_remove(struct platform_device *pdev) rcar_thermal_for_each_priv(priv, common) { rcar_thermal_irq_disable(priv); + cancel_delayed_work_sync(&priv->work); if (priv->chip->use_of_thermal) thermal_remove_hwmon_sysfs(priv->zone); else @@ -492,7 +497,7 @@ static int rcar_thermal_probe(struct platform_device *pdev) pm_runtime_get_sync(dev); for (i = 0; i < chip->nirqs; i++) { - irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); + irq = platform_get_resource(pdev, IORESOURCE_IRQ, i); if (!irq) continue; if (!common->base) { diff --git a/drivers/thermal/st/Kconfig b/drivers/thermal/st/Kconfig index 490fdbe22eea..b80f9a9e4f8f 100644 --- a/drivers/thermal/st/Kconfig +++ b/drivers/thermal/st/Kconfig @@ -1,3 +1,7 @@ +# +# STMicroelectronics thermal drivers configuration +# + config ST_THERMAL tristate "Thermal sensors on STMicroelectronics STi series of SoCs" help @@ -10,3 +14,13 @@ config ST_THERMAL_SYSCFG config ST_THERMAL_MEMMAP select ST_THERMAL tristate "STi series memory mapped access based thermal sensors" + +config STM32_THERMAL + tristate "Thermal framework support on STMicroelectronics STM32 series of SoCs" + depends on MACH_STM32MP157 + default y + help + Support for thermal framework on STMicroelectronics STM32 series of + SoCs. This thermal driver allows to access to general thermal framework + functionalities and to acces to SoC sensor functionalities. This + configuration is fully dependent of MACH_STM32MP157. diff --git a/drivers/thermal/st/Makefile b/drivers/thermal/st/Makefile index b38878977bd8..b2b9e9b96296 100644 --- a/drivers/thermal/st/Makefile +++ b/drivers/thermal/st/Makefile @@ -1,3 +1,4 @@ obj-$(CONFIG_ST_THERMAL) := st_thermal.o obj-$(CONFIG_ST_THERMAL_SYSCFG) += st_thermal_syscfg.o obj-$(CONFIG_ST_THERMAL_MEMMAP) += st_thermal_memmap.o +obj-$(CONFIG_STM32_THERMAL) := stm_thermal.o
\ No newline at end of file diff --git a/drivers/thermal/st/stm_thermal.c b/drivers/thermal/st/stm_thermal.c new file mode 100644 index 000000000000..47623da0f91b --- /dev/null +++ b/drivers/thermal/st/stm_thermal.c @@ -0,0 +1,760 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) STMicroelectronics 2018 - All Rights Reserved + * Author: David Hernandez Sanchez <david.hernandezsanchez@st.com> for + * STMicroelectronics. + */ + +#include <linux/clk.h> +#include <linux/clk-provider.h> +#include <linux/delay.h> +#include <linux/err.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/iopoll.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_device.h> +#include <linux/platform_device.h> +#include <linux/thermal.h> + +#include "../thermal_core.h" +#include "../thermal_hwmon.h" + +/* DTS register offsets */ +#define DTS_CFGR1_OFFSET 0x0 +#define DTS_T0VALR1_OFFSET 0x8 +#define DTS_RAMPVALR_OFFSET 0X10 +#define DTS_ITR1_OFFSET 0x14 +#define DTS_DR_OFFSET 0x1C +#define DTS_SR_OFFSET 0x20 +#define DTS_ITENR_OFFSET 0x24 +#define DTS_CIFR_OFFSET 0x28 + +/* DTS_CFGR1 register mask definitions */ +#define HSREF_CLK_DIV_MASK GENMASK(30, 24) +#define TS1_SMP_TIME_MASK GENMASK(19, 16) +#define TS1_INTRIG_SEL_MASK GENMASK(11, 8) + +/* DTS_T0VALR1 register mask definitions */ +#define TS1_T0_MASK GENMASK(17, 16) +#define TS1_FMT0_MASK GENMASK(15, 0) + +/* DTS_RAMPVALR register mask definitions */ +#define TS1_RAMP_COEFF_MASK GENMASK(15, 0) + +/* DTS_ITR1 register mask definitions */ +#define TS1_HITTHD_MASK GENMASK(31, 16) +#define TS1_LITTHD_MASK GENMASK(15, 0) + +/* DTS_DR register mask definitions */ +#define TS1_MFREQ_MASK GENMASK(15, 0) + +/* Less significant bit position definitions */ +#define TS1_T0_POS 16 +#define TS1_SMP_TIME_POS 16 +#define TS1_HITTHD_POS 16 +#define HSREF_CLK_DIV_POS 24 + +/* DTS_CFGR1 bit definitions */ +#define TS1_EN BIT(0) +#define TS1_START BIT(4) +#define REFCLK_SEL BIT(20) +#define REFCLK_LSE REFCLK_SEL +#define Q_MEAS_OPT BIT(21) +#define CALIBRATION_CONTROL Q_MEAS_OPT + +/* DTS_SR bit definitions */ +#define TS_RDY BIT(15) +/* Bit definitions below are common for DTS_SR, DTS_ITENR and DTS_CIFR */ +#define HIGH_THRESHOLD BIT(2) +#define LOW_THRESHOLD BIT(1) + +/* Constants */ +#define ADJUST 100 +#define ONE_MHZ 1000000 +#define POLL_TIMEOUT 5000 +#define STARTUP_TIME 40 +#define TS1_T0_VAL0 30 +#define TS1_T0_VAL1 130 +#define NO_HW_TRIG 0 + +/* The Thermal Framework expects millidegrees */ +#define mcelsius(temp) ((temp) * 1000) + +/* The Sensor expects oC degrees */ +#define celsius(temp) ((temp) / 1000) + +struct stm_thermal_sensor { + struct device *dev; + struct thermal_zone_device *th_dev; + enum thermal_device_mode mode; + struct clk *clk; + int high_temp; + int low_temp; + int temp_critical; + int temp_passive; + unsigned int low_temp_enabled; + int num_trips; + int irq; + unsigned int irq_enabled; + void __iomem *base; + int t0, fmt0, ramp_coeff; +}; + +static irqreturn_t stm_thermal_alarm_irq(int irq, void *sdata) +{ + struct stm_thermal_sensor *sensor = sdata; + + disable_irq_nosync(irq); + sensor->irq_enabled = false; + + return IRQ_WAKE_THREAD; +} + +static irqreturn_t stm_thermal_alarm_irq_thread(int irq, void *sdata) +{ + u32 value; + struct stm_thermal_sensor *sensor = sdata; + + /* read IT reason in SR and clear flags */ + value = readl_relaxed(sensor->base + DTS_SR_OFFSET); + + if ((value & LOW_THRESHOLD) == LOW_THRESHOLD) + writel_relaxed(LOW_THRESHOLD, sensor->base + DTS_CIFR_OFFSET); + + if ((value & HIGH_THRESHOLD) == HIGH_THRESHOLD) + writel_relaxed(HIGH_THRESHOLD, sensor->base + DTS_CIFR_OFFSET); + + thermal_zone_device_update(sensor->th_dev, THERMAL_EVENT_UNSPECIFIED); + + return IRQ_HANDLED; +} + +static int stm_sensor_power_on(struct stm_thermal_sensor *sensor) +{ + int ret; + u32 value; + + /* Enable sensor */ + value = readl_relaxed(sensor->base + DTS_CFGR1_OFFSET); + value |= TS1_EN; + writel_relaxed(value, sensor->base + DTS_CFGR1_OFFSET); + + /* + * The DTS block can be enabled by setting TSx_EN bit in + * DTS_CFGRx register. It requires a startup time of + * 40μs. Use 5 ms as arbitrary timeout. + */ + ret = readl_poll_timeout(sensor->base + DTS_SR_OFFSET, + value, (value & TS_RDY), + STARTUP_TIME, POLL_TIMEOUT); + if (ret) + return ret; + + /* Start continuous measuring */ + value = readl_relaxed(sensor->base + + DTS_CFGR1_OFFSET); + value |= TS1_START; + writel_relaxed(value, sensor->base + + DTS_CFGR1_OFFSET); + + return 0; +} + +static int stm_sensor_power_off(struct stm_thermal_sensor *sensor) +{ + u32 value; + + /* Stop measuring */ + value = readl_relaxed(sensor->base + DTS_CFGR1_OFFSET); + value &= ~TS1_START; + writel_relaxed(value, sensor->base + DTS_CFGR1_OFFSET); + + /* Ensure stop is taken into account */ + usleep_range(STARTUP_TIME, POLL_TIMEOUT); + + /* Disable sensor */ + value = readl_relaxed(sensor->base + DTS_CFGR1_OFFSET); + value &= ~TS1_EN; + writel_relaxed(value, sensor->base + DTS_CFGR1_OFFSET); + + /* Ensure disable is taken into account */ + return readl_poll_timeout(sensor->base + DTS_SR_OFFSET, value, + !(value & TS_RDY), + STARTUP_TIME, POLL_TIMEOUT); +} + +static int stm_thermal_calibration(struct stm_thermal_sensor *sensor) +{ + u32 value, clk_freq; + u32 prescaler; + + /* Figure out prescaler value for PCLK during calibration */ + clk_freq = clk_get_rate(sensor->clk); + if (!clk_freq) + return -EINVAL; + + prescaler = 0; + clk_freq /= ONE_MHZ; + if (clk_freq) { + while (prescaler <= clk_freq) + prescaler++; + } + + value = readl_relaxed(sensor->base + DTS_CFGR1_OFFSET); + + /* Clear prescaler */ + value &= ~HSREF_CLK_DIV_MASK; + + /* Set prescaler. pclk_freq/prescaler < 1MHz */ + value |= (prescaler << HSREF_CLK_DIV_POS); + + /* Select PCLK as reference clock */ + value &= ~REFCLK_SEL; + + /* Set maximal sampling time for better precision */ + value |= TS1_SMP_TIME_MASK; + + /* Measure with calibration */ + value &= ~CALIBRATION_CONTROL; + + /* select trigger */ + value &= ~TS1_INTRIG_SEL_MASK; + value |= NO_HW_TRIG; + + writel_relaxed(value, sensor->base + DTS_CFGR1_OFFSET); + + return 0; +} + +/* Fill in DTS structure with factory sensor values */ +static int stm_thermal_read_factory_settings(struct stm_thermal_sensor *sensor) +{ + /* Retrieve engineering calibration temperature */ + sensor->t0 = readl_relaxed(sensor->base + DTS_T0VALR1_OFFSET) & + TS1_T0_MASK; + if (!sensor->t0) + sensor->t0 = TS1_T0_VAL0; + else + sensor->t0 = TS1_T0_VAL1; + + /* Retrieve fmt0 and put it on Hz */ + sensor->fmt0 = ADJUST * readl_relaxed(sensor->base + DTS_T0VALR1_OFFSET) + & TS1_FMT0_MASK; + + /* Retrieve ramp coefficient */ + sensor->ramp_coeff = readl_relaxed(sensor->base + DTS_RAMPVALR_OFFSET) & + TS1_RAMP_COEFF_MASK; + + if (!sensor->fmt0 || !sensor->ramp_coeff) { + dev_err(sensor->dev, "%s: wrong setting\n", __func__); + return -EINVAL; + } + + dev_dbg(sensor->dev, "%s: T0 = %doC, FMT0 = %dHz, RAMP_COEFF = %dHz/oC", + __func__, sensor->t0, sensor->fmt0, sensor->ramp_coeff); + + return 0; +} + +static int stm_thermal_calculate_threshold(struct stm_thermal_sensor *sensor, + int temp, u32 *th) +{ + int freqM; + u32 sampling_time; + + /* Retrieve the number of periods to sample */ + sampling_time = (readl_relaxed(sensor->base + DTS_CFGR1_OFFSET) & + TS1_SMP_TIME_MASK) >> TS1_SMP_TIME_POS; + + /* Figure out the CLK_PTAT frequency for a given temperature */ + freqM = ((temp - sensor->t0) * sensor->ramp_coeff) + + sensor->fmt0; + + dev_dbg(sensor->dev, "%s: freqM for threshold = %d Hz", + __func__, freqM); + + /* Figure out the threshold sample number */ + *th = clk_get_rate(sensor->clk); + if (!*th) + return -EINVAL; + + *th = *th / freqM; + + *th *= sampling_time; + + return 0; +} + +static int stm_thermal_set_threshold(struct stm_thermal_sensor *sensor) +{ + u32 value, th; + int ret; + + value = readl_relaxed(sensor->base + DTS_ITR1_OFFSET); + + /* Erase threshold content */ + value &= ~(TS1_LITTHD_MASK | TS1_HITTHD_MASK); + + /* Retrieve the sample threshold number th for a given temperature */ + ret = stm_thermal_calculate_threshold(sensor, sensor->high_temp, &th); + if (ret) + return ret; + + value |= th & TS1_LITTHD_MASK; + + if (sensor->low_temp_enabled) { + /* Retrieve the sample threshold */ + ret = stm_thermal_calculate_threshold(sensor, sensor->low_temp, + &th); + if (ret) + return ret; + + value |= (TS1_HITTHD_MASK & (th << TS1_HITTHD_POS)); + } + + /* Write value on the Low interrupt threshold */ + writel_relaxed(value, sensor->base + DTS_ITR1_OFFSET); + + return 0; +} + +/* Disable temperature interrupt */ +static int stm_disable_irq(struct stm_thermal_sensor *sensor) +{ + u32 value; + + /* Disable IT generation for low and high thresholds */ + value = readl_relaxed(sensor->base + DTS_ITENR_OFFSET); + writel_relaxed(value & ~(LOW_THRESHOLD | HIGH_THRESHOLD), + sensor->base + DTS_ITENR_OFFSET); + + dev_dbg(sensor->dev, "%s: IT disabled on sensor side", __func__); + + return 0; +} + +/* Enable temperature interrupt */ +static int stm_enable_irq(struct stm_thermal_sensor *sensor) +{ + u32 value; + + /* + * Code below enables High temperature threshold using a low threshold + * sampling value + */ + + /* Make sure LOW_THRESHOLD IT is clear before enabling */ + writel_relaxed(LOW_THRESHOLD, sensor->base + DTS_CIFR_OFFSET); + + /* Enable IT generation for low threshold */ + value = readl_relaxed(sensor->base + DTS_ITENR_OFFSET); + value |= LOW_THRESHOLD; + + /* Enable the low temperature threshold if needed */ + if (sensor->low_temp_enabled) { + /* Make sure HIGH_THRESHOLD IT is clear before enabling */ + writel_relaxed(HIGH_THRESHOLD, sensor->base + DTS_CIFR_OFFSET); + + /* Enable IT generation for high threshold */ + value |= HIGH_THRESHOLD; + } + + /* Enable thresholds */ + writel_relaxed(value, sensor->base + DTS_ITENR_OFFSET); + + dev_dbg(sensor->dev, "%s: IT enabled on sensor side", __func__); + + return 0; +} + +static int stm_thermal_update_threshold(struct stm_thermal_sensor *sensor) +{ + int ret; + + sensor->mode = THERMAL_DEVICE_DISABLED; + + ret = stm_sensor_power_off(sensor); + if (ret) + return ret; + + ret = stm_disable_irq(sensor); + if (ret) + return ret; + + ret = stm_thermal_set_threshold(sensor); + if (ret) + return ret; + + ret = stm_enable_irq(sensor); + if (ret) + return ret; + + ret = stm_sensor_power_on(sensor); + if (ret) + return ret; + + sensor->mode = THERMAL_DEVICE_ENABLED; + + return 0; +} + +/* Callback to get temperature from HW */ +static int stm_thermal_get_temp(void *data, int *temp) +{ + struct stm_thermal_sensor *sensor = data; + u32 sampling_time; + int freqM, ret; + + if (sensor->mode != THERMAL_DEVICE_ENABLED) + return -EAGAIN; + + /* Retrieve the number of samples */ + ret = readl_poll_timeout(sensor->base + DTS_DR_OFFSET, freqM, + (freqM & TS1_MFREQ_MASK), STARTUP_TIME, + POLL_TIMEOUT); + + if (ret) + return ret; + + if (!freqM) + return -ENODATA; + + /* Retrieve the number of periods sampled */ + sampling_time = (readl_relaxed(sensor->base + DTS_CFGR1_OFFSET) & + TS1_SMP_TIME_MASK) >> TS1_SMP_TIME_POS; + + /* Figure out the number of samples per period */ + freqM /= sampling_time; + + /* Figure out the CLK_PTAT frequency */ + freqM = clk_get_rate(sensor->clk) / freqM; + if (!freqM) + return -EINVAL; + + dev_dbg(sensor->dev, "%s: freqM=%d\n", __func__, freqM); + + /* Figure out the temperature in mili celsius */ + *temp = mcelsius(sensor->t0 + ((freqM - sensor->fmt0) / + sensor->ramp_coeff)); + + dev_dbg(sensor->dev, "%s: temperature = %d millicelsius", + __func__, *temp); + + /* Update thresholds */ + if (sensor->num_trips > 1) { + /* Update alarm threshold value to next higher trip point */ + if (sensor->high_temp == sensor->temp_passive && + celsius(*temp) >= sensor->temp_passive) { + sensor->high_temp = sensor->temp_critical; + sensor->low_temp = sensor->temp_passive; + sensor->low_temp_enabled = true; + ret = stm_thermal_update_threshold(sensor); + if (ret) + return ret; + } + + if (sensor->high_temp == sensor->temp_critical && + celsius(*temp) < sensor->temp_passive) { + sensor->high_temp = sensor->temp_passive; + sensor->low_temp_enabled = false; + ret = stm_thermal_update_threshold(sensor); + if (ret) + return ret; + } + + /* + * Re-enable alarm IRQ if temperature below critical + * temperature + */ + if (!sensor->irq_enabled && + (celsius(*temp) < sensor->temp_critical)) { + sensor->irq_enabled = true; + enable_irq(sensor->irq); + } + } + + return 0; +} + +/* Registers DTS irq to be visible by GIC */ +static int stm_register_irq(struct stm_thermal_sensor *sensor) +{ + struct device *dev = sensor->dev; + struct platform_device *pdev = to_platform_device(dev); + int ret; + + sensor->irq = platform_get_irq(pdev, 0); + if (sensor->irq < 0) { + dev_err(dev, "%s: Unable to find IRQ\n", __func__); + return sensor->irq; + } + + ret = devm_request_threaded_irq(dev, sensor->irq, + stm_thermal_alarm_irq, + stm_thermal_alarm_irq_thread, + IRQF_ONESHOT, + dev->driver->name, sensor); + if (ret) { + dev_err(dev, "%s: Failed to register IRQ %d\n", __func__, + sensor->irq); + return ret; + } + + sensor->irq_enabled = true; + + dev_dbg(dev, "%s: thermal IRQ registered", __func__); + + return 0; +} + +static int stm_thermal_sensor_off(struct stm_thermal_sensor *sensor) +{ + int ret; + + ret = stm_sensor_power_off(sensor); + if (ret) + return ret; + + clk_disable_unprepare(sensor->clk); + + return 0; +} + +static int stm_thermal_prepare(struct stm_thermal_sensor *sensor) +{ + int ret; + struct device *dev = sensor->dev; + + ret = clk_prepare_enable(sensor->clk); + if (ret) + return ret; + + ret = stm_thermal_calibration(sensor); + if (ret) + goto thermal_unprepare; + + /* Set threshold(s) for IRQ */ + ret = stm_thermal_set_threshold(sensor); + if (ret) + goto thermal_unprepare; + + ret = stm_enable_irq(sensor); + if (ret) + goto thermal_unprepare; + + ret = stm_sensor_power_on(sensor); + if (ret) { + dev_err(dev, "%s: failed to power on sensor\n", __func__); + goto irq_disable; + } + + return 0; + +irq_disable: + stm_disable_irq(sensor); + +thermal_unprepare: + clk_disable_unprepare(sensor->clk); + + return ret; +} + +#ifdef CONFIG_PM_SLEEP +static int stm_thermal_suspend(struct device *dev) +{ + int ret; + struct platform_device *pdev = to_platform_device(dev); + struct stm_thermal_sensor *sensor = platform_get_drvdata(pdev); + + ret = stm_thermal_sensor_off(sensor); + if (ret) + return ret; + + sensor->mode = THERMAL_DEVICE_DISABLED; + + return 0; +} + +static int stm_thermal_resume(struct device *dev) +{ + int ret; + struct platform_device *pdev = to_platform_device(dev); + struct stm_thermal_sensor *sensor = platform_get_drvdata(pdev); + + ret = stm_thermal_prepare(sensor); + if (ret) + return ret; + + sensor->mode = THERMAL_DEVICE_ENABLED; + + return 0; +} +#endif /* CONFIG_PM_SLEEP */ + +SIMPLE_DEV_PM_OPS(stm_thermal_pm_ops, stm_thermal_suspend, stm_thermal_resume); + +static const struct thermal_zone_of_device_ops stm_tz_ops = { + .get_temp = stm_thermal_get_temp, +}; + +static const struct of_device_id stm_thermal_of_match[] = { + { .compatible = "st,stm32-thermal"}, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, stm_thermal_of_match); + +static int stm_thermal_probe(struct platform_device *pdev) +{ + struct stm_thermal_sensor *sensor; + struct resource *res; + const struct thermal_trip *trip; + void __iomem *base; + int ret, i; + + if (!pdev->dev.of_node) { + dev_err(&pdev->dev, "%s: device tree node not found\n", + __func__); + return -EINVAL; + } + + sensor = devm_kzalloc(&pdev->dev, sizeof(*sensor), GFP_KERNEL); + if (!sensor) + return -ENOMEM; + + platform_set_drvdata(pdev, sensor); + + sensor->dev = &pdev->dev; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); + + /* Populate sensor */ + sensor->base = base; + + ret = stm_thermal_read_factory_settings(sensor); + if (ret) + return ret; + + sensor->clk = devm_clk_get(&pdev->dev, "pclk"); + if (IS_ERR(sensor->clk)) { + dev_err(&pdev->dev, "%s: failed to fetch PCLK clock\n", + __func__); + return PTR_ERR(sensor->clk); + } + + /* Register IRQ into GIC */ + ret = stm_register_irq(sensor); + if (ret) + return ret; + + sensor->th_dev = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, + sensor, + &stm_tz_ops); + + if (IS_ERR(sensor->th_dev)) { + dev_err(&pdev->dev, "%s: thermal zone sensor registering KO\n", + __func__); + ret = PTR_ERR(sensor->th_dev); + return ret; + } + + if (!sensor->th_dev->ops->get_crit_temp) { + /* Critical point must be provided */ + ret = -EINVAL; + goto err_tz; + } + + ret = sensor->th_dev->ops->get_crit_temp(sensor->th_dev, + &sensor->temp_critical); + if (ret) { + dev_err(&pdev->dev, + "Not able to read critical_temp: %d\n", ret); + goto err_tz; + } + + sensor->temp_critical = celsius(sensor->temp_critical); + + /* Set thresholds for IRQ */ + sensor->high_temp = sensor->temp_critical; + + trip = of_thermal_get_trip_points(sensor->th_dev); + sensor->num_trips = of_thermal_get_ntrips(sensor->th_dev); + + /* Find out passive temperature if it exists */ + for (i = (sensor->num_trips - 1); i >= 0; i--) { + if (trip[i].type == THERMAL_TRIP_PASSIVE) { + sensor->temp_passive = celsius(trip[i].temperature); + /* Update high temperature threshold */ + sensor->high_temp = sensor->temp_passive; + } + } + + /* + * Ensure low_temp_enabled flag is disabled. + * By disabling low_temp_enabled, low threshold IT will not be + * configured neither enabled because it is not needed as high + * threshold is set on the lowest temperature trip point after + * probe. + */ + sensor->low_temp_enabled = false; + + /* Configure and enable HW sensor */ + ret = stm_thermal_prepare(sensor); + if (ret) { + dev_err(&pdev->dev, + "Not able to enable sensor: %d\n", ret); + goto err_tz; + } + + /* + * Thermal_zone doesn't enable hwmon as default, + * enable it here + */ + sensor->th_dev->tzp->no_hwmon = false; + ret = thermal_add_hwmon_sysfs(sensor->th_dev); + if (ret) + goto err_tz; + + sensor->mode = THERMAL_DEVICE_ENABLED; + + dev_info(&pdev->dev, "%s: Driver initialized successfully\n", + __func__); + + return 0; + +err_tz: + thermal_zone_of_sensor_unregister(&pdev->dev, sensor->th_dev); + return ret; +} + +static int stm_thermal_remove(struct platform_device *pdev) +{ + struct stm_thermal_sensor *sensor = platform_get_drvdata(pdev); + + stm_thermal_sensor_off(sensor); + thermal_remove_hwmon_sysfs(sensor->th_dev); + thermal_zone_of_sensor_unregister(&pdev->dev, sensor->th_dev); + + return 0; +} + +static struct platform_driver stm_thermal_driver = { + .driver = { + .name = "stm_thermal", + .pm = &stm_thermal_pm_ops, + .of_match_table = stm_thermal_of_match, + }, + .probe = stm_thermal_probe, + .remove = stm_thermal_remove, +}; +module_platform_driver(stm_thermal_driver); + +MODULE_DESCRIPTION("STMicroelectronics STM32 Thermal Sensor Driver"); +MODULE_AUTHOR("David Hernandez Sanchez <david.hernandezsanchez@st.com>"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("platform:stm_thermal"); diff --git a/drivers/video/fbdev/chipsfb.c b/drivers/video/fbdev/chipsfb.c index f103665cad43..40182ed85648 100644 --- a/drivers/video/fbdev/chipsfb.c +++ b/drivers/video/fbdev/chipsfb.c @@ -27,7 +27,6 @@ #include <linux/init.h> #include <linux/pci.h> #include <linux/console.h> -#include <asm/io.h> #ifdef CONFIG_PMAC_BACKLIGHT #include <asm/backlight.h> @@ -401,7 +400,7 @@ static int chipsfb_pci_init(struct pci_dev *dp, const struct pci_device_id *ent) #endif /* CONFIG_PMAC_BACKLIGHT */ #ifdef CONFIG_PPC - p->screen_base = __ioremap(addr, 0x200000, _PAGE_NO_CACHE); + p->screen_base = ioremap_wc(addr, 0x200000); #else p->screen_base = ioremap(addr, 0x200000); #endif diff --git a/drivers/video/fbdev/controlfb.c b/drivers/video/fbdev/controlfb.c index 8d14b29aafea..9cb0ef7ac29e 100644 --- a/drivers/video/fbdev/controlfb.c +++ b/drivers/video/fbdev/controlfb.c @@ -48,9 +48,7 @@ #include <linux/nvram.h> #include <linux/adb.h> #include <linux/cuda.h> -#include <asm/io.h> #include <asm/prom.h> -#include <asm/pgtable.h> #include <asm/btext.h> #include "macmodes.h" @@ -715,8 +713,7 @@ static int __init control_of_init(struct device_node *dp) goto error_out; } /* map at most 8MB for the frame buffer */ - p->frame_buffer = __ioremap(p->frame_buffer_phys, 0x800000, - _PAGE_WRITETHRU); + p->frame_buffer = ioremap_wt(p->frame_buffer_phys, 0x800000); if (!p->control_regs_phys || !request_mem_region(p->control_regs_phys, p->control_regs_size, diff --git a/drivers/video/fbdev/fsl-diu-fb.c b/drivers/video/fbdev/fsl-diu-fb.c index bc9eb8afc313..332a56b6811f 100644 --- a/drivers/video/fbdev/fsl-diu-fb.c +++ b/drivers/video/fbdev/fsl-diu-fb.c @@ -1925,7 +1925,7 @@ static int __init fsl_diu_init(void) pr_info("Freescale Display Interface Unit (DIU) framebuffer driver\n"); #ifdef CONFIG_NOT_COHERENT_CACHE - np = of_find_node_by_type(NULL, "cpu"); + np = of_get_cpu_node(0, NULL); if (!np) { pr_err("fsl-diu-fb: can't find 'cpu' device node\n"); return -ENODEV; diff --git a/drivers/video/fbdev/platinumfb.c b/drivers/video/fbdev/platinumfb.c index 377d3399a3ad..bf6b7fb83cf4 100644 --- a/drivers/video/fbdev/platinumfb.c +++ b/drivers/video/fbdev/platinumfb.c @@ -32,9 +32,7 @@ #include <linux/nvram.h> #include <linux/of_device.h> #include <linux/of_platform.h> -#include <asm/io.h> #include <asm/prom.h> -#include <asm/pgtable.h> #include "macmodes.h" #include "platinumfb.h" @@ -577,8 +575,7 @@ static int platinumfb_probe(struct platform_device* odev) /* frame buffer - map only 4MB */ pinfo->frame_buffer_phys = pinfo->rsrc_fb.start; - pinfo->frame_buffer = __ioremap(pinfo->rsrc_fb.start, 0x400000, - _PAGE_WRITETHRU); + pinfo->frame_buffer = ioremap_wt(pinfo->rsrc_fb.start, 0x400000); pinfo->base_frame_buffer = pinfo->frame_buffer; /* registers */ diff --git a/drivers/video/fbdev/valkyriefb.c b/drivers/video/fbdev/valkyriefb.c index 275fb98236d3..d51c3a8009cb 100644 --- a/drivers/video/fbdev/valkyriefb.c +++ b/drivers/video/fbdev/valkyriefb.c @@ -54,13 +54,11 @@ #include <linux/nvram.h> #include <linux/adb.h> #include <linux/cuda.h> -#include <asm/io.h> #ifdef CONFIG_MAC #include <asm/macintosh.h> #else #include <asm/prom.h> #endif -#include <asm/pgtable.h> #include "macmodes.h" #include "valkyriefb.h" @@ -318,7 +316,7 @@ static void __init valkyrie_choose_mode(struct fb_info_valkyrie *p) int __init valkyriefb_init(void) { struct fb_info_valkyrie *p; - unsigned long frame_buffer_phys, cmap_regs_phys, flags; + unsigned long frame_buffer_phys, cmap_regs_phys; int err; char *option = NULL; @@ -337,7 +335,6 @@ int __init valkyriefb_init(void) /* Hardcoded addresses... welcome to 68k Macintosh country :-) */ frame_buffer_phys = 0xf9000000; cmap_regs_phys = 0x50f24000; - flags = IOMAP_NOCACHE_SER; /* IOMAP_WRITETHROUGH?? */ #else /* ppc (!CONFIG_MAC) */ { struct device_node *dp; @@ -354,7 +351,6 @@ int __init valkyriefb_init(void) frame_buffer_phys = r.start; cmap_regs_phys = r.start + 0x304000; - flags = _PAGE_WRITETHRU; } #endif /* ppc (!CONFIG_MAC) */ @@ -369,7 +365,11 @@ int __init valkyriefb_init(void) } p->total_vram = 0x100000; p->frame_buffer_phys = frame_buffer_phys; - p->frame_buffer = __ioremap(frame_buffer_phys, p->total_vram, flags); +#ifdef CONFIG_MAC + p->frame_buffer = ioremap_nocache(frame_buffer_phys, p->total_vram); +#else + p->frame_buffer = ioremap_wt(frame_buffer_phys, p->total_vram); +#endif p->cmap_regs_phys = cmap_regs_phys; p->cmap_regs = ioremap(p->cmap_regs_phys, 0x1000); p->valkyrie_regs_phys = cmap_regs_phys+0x6000; |