diff options
Diffstat (limited to 'drivers/hwtracing')
-rw-r--r-- | drivers/hwtracing/coresight/coresight-cpu-debug.c | 33 | ||||
-rw-r--r-- | drivers/hwtracing/coresight/coresight-etm4x-sysfs.c | 13 | ||||
-rw-r--r-- | drivers/hwtracing/coresight/coresight-etm4x.c | 38 | ||||
-rw-r--r-- | drivers/hwtracing/coresight/coresight-funnel.c | 11 | ||||
-rw-r--r-- | drivers/hwtracing/coresight/coresight-priv.h | 10 | ||||
-rw-r--r-- | drivers/hwtracing/coresight/coresight-replicator.c | 3 | ||||
-rw-r--r-- | drivers/hwtracing/coresight/coresight-tmc-etf.c | 23 | ||||
-rw-r--r-- | drivers/hwtracing/coresight/coresight-tmc-etr.c | 93 | ||||
-rw-r--r-- | drivers/hwtracing/coresight/coresight-tmc.c | 40 | ||||
-rw-r--r-- | drivers/hwtracing/coresight/coresight-tmc.h | 11 | ||||
-rw-r--r-- | drivers/hwtracing/intel_th/Makefile | 3 | ||||
-rw-r--r-- | drivers/hwtracing/intel_th/msu-sink.c | 116 | ||||
-rw-r--r-- | drivers/hwtracing/intel_th/msu.c | 537 | ||||
-rw-r--r-- | drivers/hwtracing/intel_th/msu.h | 20 |
14 files changed, 752 insertions, 199 deletions
diff --git a/drivers/hwtracing/coresight/coresight-cpu-debug.c b/drivers/hwtracing/coresight/coresight-cpu-debug.c index 2463aa7ab4f6..96544b348c27 100644 --- a/drivers/hwtracing/coresight/coresight-cpu-debug.c +++ b/drivers/hwtracing/coresight/coresight-cpu-debug.c @@ -646,24 +646,23 @@ static int debug_remove(struct amba_device *adev) return 0; } +static const struct amba_cs_uci_id uci_id_debug[] = { + { + /* CPU Debug UCI data */ + .devarch = 0x47706a15, + .devarch_mask = 0xfff0ffff, + .devtype = 0x00000015, + } +}; + static const struct amba_id debug_ids[] = { - { /* Debug for Cortex-A53 */ - .id = 0x000bbd03, - .mask = 0x000fffff, - }, - { /* Debug for Cortex-A57 */ - .id = 0x000bbd07, - .mask = 0x000fffff, - }, - { /* Debug for Cortex-A72 */ - .id = 0x000bbd08, - .mask = 0x000fffff, - }, - { /* Debug for Cortex-A73 */ - .id = 0x000bbd09, - .mask = 0x000fffff, - }, - { 0, 0 }, + CS_AMBA_ID(0x000bbd03), /* Cortex-A53 */ + CS_AMBA_ID(0x000bbd07), /* Cortex-A57 */ + CS_AMBA_ID(0x000bbd08), /* Cortex-A72 */ + CS_AMBA_ID(0x000bbd09), /* Cortex-A73 */ + CS_AMBA_UCI_ID(0x000f0205, uci_id_debug), /* Qualcomm Kryo */ + CS_AMBA_UCI_ID(0x000f0211, uci_id_debug), /* Qualcomm Kryo */ + {}, }; static struct amba_driver debug_driver = { diff --git a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c index a0365e23678e..219c10eb752c 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-sysfs.c @@ -296,11 +296,8 @@ static ssize_t mode_store(struct device *dev, spin_lock(&drvdata->spinlock); config->mode = val & ETMv4_MODE_ALL; - - if (config->mode & ETM_MODE_EXCLUDE) - etm4_set_mode_exclude(drvdata, true); - else - etm4_set_mode_exclude(drvdata, false); + etm4_set_mode_exclude(drvdata, + config->mode & ETM_MODE_EXCLUDE ? true : false); if (drvdata->instrp0 == true) { /* start by clearing instruction P0 field */ @@ -999,10 +996,8 @@ static ssize_t addr_range_store(struct device *dev, * Program include or exclude control bits for vinst or vdata * whenever we change addr comparators to ETM_ADDR_TYPE_RANGE */ - if (config->mode & ETM_MODE_EXCLUDE) - etm4_set_mode_exclude(drvdata, true); - else - etm4_set_mode_exclude(drvdata, false); + etm4_set_mode_exclude(drvdata, + config->mode & ETM_MODE_EXCLUDE ? true : false); spin_unlock(&drvdata->spinlock); return size; diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c index 7bcac8896fc1..a128b5063f46 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.c +++ b/drivers/hwtracing/coresight/coresight-etm4x.c @@ -34,7 +34,8 @@ #include "coresight-etm-perf.h" static int boot_enable; -module_param_named(boot_enable, boot_enable, int, S_IRUGO); +module_param(boot_enable, int, 0444); +MODULE_PARM_DESC(boot_enable, "Enable tracing on boot"); /* The number of ETMv4 currently registered */ static int etm4_count; @@ -47,7 +48,7 @@ static enum cpuhp_state hp_online; static void etm4_os_unlock(struct etmv4_drvdata *drvdata) { - /* Writing any value to ETMOSLAR unlocks the trace registers */ + /* Writing 0 to TRCOSLAR unlocks the trace registers */ writel_relaxed(0x0, drvdata->base + TRCOSLAR); drvdata->os_unlock = true; isb(); @@ -188,6 +189,13 @@ static int etm4_enable_hw(struct etmv4_drvdata *drvdata) dev_err(etm_dev, "timeout while waiting for Idle Trace Status\n"); + /* + * As recommended by section 4.3.7 ("Synchronization when using the + * memory-mapped interface") of ARM IHI 0064D + */ + dsb(sy); + isb(); + done: CS_LOCK(drvdata->base); @@ -453,8 +461,12 @@ static void etm4_disable_hw(void *info) /* EN, bit[0] Trace unit enable bit */ control &= ~0x1; - /* make sure everything completes before disabling */ - mb(); + /* + * Make sure everything completes before disabling, as recommended + * by section 7.3.77 ("TRCVICTLR, ViewInst Main Control Register, + * SSTATUS") of ARM IHI 0064D + */ + dsb(sy); isb(); writel_relaxed(control, drvdata->base + TRCPRGCTLR); @@ -1047,10 +1059,8 @@ static int etm4_starting_cpu(unsigned int cpu) return 0; spin_lock(&etmdrvdata[cpu]->spinlock); - if (!etmdrvdata[cpu]->os_unlock) { + if (!etmdrvdata[cpu]->os_unlock) etm4_os_unlock(etmdrvdata[cpu]); - etmdrvdata[cpu]->os_unlock = true; - } if (local_read(&etmdrvdata[cpu]->mode)) etm4_enable_hw(etmdrvdata[cpu]); @@ -1192,11 +1202,15 @@ static struct amba_cs_uci_id uci_id_etm4[] = { }; static const struct amba_id etm4_ids[] = { - CS_AMBA_ID(0x000bb95d), /* Cortex-A53 */ - CS_AMBA_ID(0x000bb95e), /* Cortex-A57 */ - CS_AMBA_ID(0x000bb95a), /* Cortex-A72 */ - CS_AMBA_ID(0x000bb959), /* Cortex-A73 */ - CS_AMBA_UCI_ID(0x000bb9da, uci_id_etm4), /* Cortex-A35 */ + CS_AMBA_ID(0x000bb95d), /* Cortex-A53 */ + CS_AMBA_ID(0x000bb95e), /* Cortex-A57 */ + CS_AMBA_ID(0x000bb95a), /* Cortex-A72 */ + CS_AMBA_ID(0x000bb959), /* Cortex-A73 */ + CS_AMBA_UCI_ID(0x000bb9da, uci_id_etm4),/* Cortex-A35 */ + CS_AMBA_UCI_ID(0x000f0205, uci_id_etm4),/* Qualcomm Kryo */ + CS_AMBA_UCI_ID(0x000f0211, uci_id_etm4),/* Qualcomm Kryo */ + CS_AMBA_ID(0x000bb802), /* Qualcomm Kryo 385 Cortex-A55 */ + CS_AMBA_ID(0x000bb803), /* Qualcomm Kryo 385 Cortex-A75 */ {}, }; diff --git a/drivers/hwtracing/coresight/coresight-funnel.c b/drivers/hwtracing/coresight/coresight-funnel.c index fa97cb9ab4f9..05f7896c3a01 100644 --- a/drivers/hwtracing/coresight/coresight-funnel.c +++ b/drivers/hwtracing/coresight/coresight-funnel.c @@ -5,6 +5,7 @@ * Description: CoreSight Funnel driver */ +#include <linux/acpi.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/types.h> @@ -192,7 +193,7 @@ static int funnel_probe(struct device *dev, struct resource *res) if (is_of_node(dev_fwnode(dev)) && of_device_is_compatible(dev->of_node, "arm,coresight-funnel")) - pr_warn_once("Uses OBSOLETE CoreSight funnel binding\n"); + dev_warn_once(dev, "Uses OBSOLETE CoreSight funnel binding\n"); desc.name = coresight_alloc_device_name(&funnel_devs, dev); if (!desc.name) @@ -302,11 +303,19 @@ static const struct of_device_id static_funnel_match[] = { {} }; +#ifdef CONFIG_ACPI +static const struct acpi_device_id static_funnel_ids[] = { + {"ARMHC9FE", 0}, + {}, +}; +#endif + static struct platform_driver static_funnel_driver = { .probe = static_funnel_probe, .driver = { .name = "coresight-static-funnel", .of_match_table = static_funnel_match, + .acpi_match_table = ACPI_PTR(static_funnel_ids), .pm = &funnel_dev_pm_ops, .suppress_bind_attrs = true, }, diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h index 61d7f9ff054d..82e563cdc879 100644 --- a/drivers/hwtracing/coresight/coresight-priv.h +++ b/drivers/hwtracing/coresight/coresight-priv.h @@ -185,11 +185,11 @@ static inline int etm_writel_cp14(u32 off, u32 val) { return 0; } } /* coresight AMBA ID, full UCI structure: id table entry. */ -#define CS_AMBA_UCI_ID(pid, uci_ptr) \ - { \ - .id = pid, \ - .mask = 0x000fffff, \ - .data = uci_ptr \ +#define CS_AMBA_UCI_ID(pid, uci_ptr) \ + { \ + .id = pid, \ + .mask = 0x000fffff, \ + .data = (void *)uci_ptr \ } /* extract the data value from a UCI structure given amba_id pointer. */ diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c index b7d6d59d56db..b29ba640eb25 100644 --- a/drivers/hwtracing/coresight/coresight-replicator.c +++ b/drivers/hwtracing/coresight/coresight-replicator.c @@ -184,7 +184,8 @@ static int replicator_probe(struct device *dev, struct resource *res) if (is_of_node(dev_fwnode(dev)) && of_device_is_compatible(dev->of_node, "arm,coresight-replicator")) - pr_warn_once("Uses OBSOLETE CoreSight replicator binding\n"); + dev_warn_once(dev, + "Uses OBSOLETE CoreSight replicator binding\n"); desc.name = coresight_alloc_device_name(&replicator_devs, dev); if (!desc.name) diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c index 23b7ff00af5c..807416b75ecc 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etf.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c @@ -479,30 +479,11 @@ static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev, * traces. */ if (!buf->snapshot && to_read > handle->size) { - u32 mask = 0; - - /* - * The value written to RRP must be byte-address aligned to - * the width of the trace memory databus _and_ to a frame - * boundary (16 byte), whichever is the biggest. For example, - * for 32-bit, 64-bit and 128-bit wide trace memory, the four - * LSBs must be 0s. For 256-bit wide trace memory, the five - * LSBs must be 0s. - */ - switch (drvdata->memwidth) { - case TMC_MEM_INTF_WIDTH_32BITS: - case TMC_MEM_INTF_WIDTH_64BITS: - case TMC_MEM_INTF_WIDTH_128BITS: - mask = GENMASK(31, 4); - break; - case TMC_MEM_INTF_WIDTH_256BITS: - mask = GENMASK(31, 5); - break; - } + u32 mask = tmc_get_memwidth_mask(drvdata); /* * Make sure the new size is aligned in accordance with the - * requirement explained above. + * requirement explained in function tmc_get_memwidth_mask(). */ to_read = handle->size & mask; /* Move the RAM read pointer up */ diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index 17006705287a..625882bc8b08 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -871,6 +871,7 @@ static struct etr_buf *tmc_alloc_etr_buf(struct tmc_drvdata *drvdata, return ERR_PTR(rc); } + refcount_set(&etr_buf->refcount, 1); dev_dbg(dev, "allocated buffer of size %ldKB in mode %d\n", (unsigned long)size >> 10, etr_buf->mode); return etr_buf; @@ -927,15 +928,24 @@ static void tmc_sync_etr_buf(struct tmc_drvdata *drvdata) rrp = tmc_read_rrp(drvdata); rwp = tmc_read_rwp(drvdata); status = readl_relaxed(drvdata->base + TMC_STS); + + /* + * If there were memory errors in the session, truncate the + * buffer. + */ + if (WARN_ON_ONCE(status & TMC_STS_MEMERR)) { + dev_dbg(&drvdata->csdev->dev, + "tmc memory error detected, truncating buffer\n"); + etr_buf->len = 0; + etr_buf->full = 0; + return; + } + etr_buf->full = status & TMC_STS_FULL; WARN_ON(!etr_buf->ops || !etr_buf->ops->sync); etr_buf->ops->sync(etr_buf, rrp, rwp); - - /* Insert barrier packets at the beginning, if there was an overflow */ - if (etr_buf->full) - tmc_etr_buf_insert_barrier_packet(etr_buf, etr_buf->offset); } static void __tmc_etr_enable_hw(struct tmc_drvdata *drvdata) @@ -1072,6 +1082,13 @@ static void tmc_etr_sync_sysfs_buf(struct tmc_drvdata *drvdata) drvdata->sysfs_buf = NULL; } else { tmc_sync_etr_buf(drvdata); + /* + * Insert barrier packets at the beginning, if there was + * an overflow. + */ + if (etr_buf->full) + tmc_etr_buf_insert_barrier_packet(etr_buf, + etr_buf->offset); } } @@ -1263,8 +1280,6 @@ retry: if (IS_ERR(etr_buf)) return etr_buf; - refcount_set(&etr_buf->refcount, 1); - /* Now that we have a buffer, add it to the IDR. */ mutex_lock(&drvdata->idr_mutex); ret = idr_alloc(&drvdata->idr, etr_buf, pid, pid + 1, GFP_KERNEL); @@ -1291,19 +1306,11 @@ get_perf_etr_buf_per_thread(struct tmc_drvdata *drvdata, struct perf_event *event, int nr_pages, void **pages, bool snapshot) { - struct etr_buf *etr_buf; - /* * In per-thread mode the etr_buf isn't shared, so just go ahead * with memory allocation. */ - etr_buf = alloc_etr_buf(drvdata, event, nr_pages, pages, snapshot); - if (IS_ERR(etr_buf)) - goto out; - - refcount_set(&etr_buf->refcount, 1); -out: - return etr_buf; + return alloc_etr_buf(drvdata, event, nr_pages, pages, snapshot); } static struct etr_buf * @@ -1410,10 +1417,12 @@ free_etr_perf_buffer: * tmc_etr_sync_perf_buffer: Copy the actual trace data from the hardware * buffer to the perf ring buffer. */ -static void tmc_etr_sync_perf_buffer(struct etr_perf_buffer *etr_perf) +static void tmc_etr_sync_perf_buffer(struct etr_perf_buffer *etr_perf, + unsigned long src_offset, + unsigned long to_copy) { - long bytes, to_copy; - long pg_idx, pg_offset, src_offset; + long bytes; + long pg_idx, pg_offset; unsigned long head = etr_perf->head; char **dst_pages, *src_buf; struct etr_buf *etr_buf = etr_perf->etr_buf; @@ -1422,8 +1431,6 @@ static void tmc_etr_sync_perf_buffer(struct etr_perf_buffer *etr_perf) pg_idx = head >> PAGE_SHIFT; pg_offset = head & (PAGE_SIZE - 1); dst_pages = (char **)etr_perf->pages; - src_offset = etr_buf->offset; - to_copy = etr_buf->len; while (to_copy > 0) { /* @@ -1434,6 +1441,8 @@ static void tmc_etr_sync_perf_buffer(struct etr_perf_buffer *etr_perf) * 3) what is available in the destination page. * in one iteration. */ + if (src_offset >= etr_buf->size) + src_offset -= etr_buf->size; bytes = tmc_etr_buf_get_data(etr_buf, src_offset, to_copy, &src_buf); if (WARN_ON_ONCE(bytes <= 0)) @@ -1454,8 +1463,6 @@ static void tmc_etr_sync_perf_buffer(struct etr_perf_buffer *etr_perf) /* Move source pointers */ src_offset += bytes; - if (src_offset >= etr_buf->size) - src_offset -= etr_buf->size; } } @@ -1471,7 +1478,7 @@ tmc_update_etr_buffer(struct coresight_device *csdev, void *config) { bool lost = false; - unsigned long flags, size = 0; + unsigned long flags, offset, size = 0; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); struct etr_perf_buffer *etr_perf = config; struct etr_buf *etr_buf = etr_perf->etr_buf; @@ -1484,7 +1491,7 @@ tmc_update_etr_buffer(struct coresight_device *csdev, goto out; } - if (WARN_ON(drvdata->perf_data != etr_perf)) { + if (WARN_ON(drvdata->perf_buf != etr_buf)) { lost = true; spin_unlock_irqrestore(&drvdata->spinlock, flags); goto out; @@ -1496,12 +1503,38 @@ tmc_update_etr_buffer(struct coresight_device *csdev, tmc_sync_etr_buf(drvdata); CS_LOCK(drvdata->base); - /* Reset perf specific data */ - drvdata->perf_data = NULL; spin_unlock_irqrestore(&drvdata->spinlock, flags); + lost = etr_buf->full; + offset = etr_buf->offset; size = etr_buf->len; - tmc_etr_sync_perf_buffer(etr_perf); + + /* + * The ETR buffer may be bigger than the space available in the + * perf ring buffer (handle->size). If so advance the offset so that we + * get the latest trace data. In snapshot mode none of that matters + * since we are expected to clobber stale data in favour of the latest + * traces. + */ + if (!etr_perf->snapshot && size > handle->size) { + u32 mask = tmc_get_memwidth_mask(drvdata); + + /* + * Make sure the new size is aligned in accordance with the + * requirement explained in function tmc_get_memwidth_mask(). + */ + size = handle->size & mask; + offset = etr_buf->offset + etr_buf->len - size; + + if (offset >= etr_buf->size) + offset -= etr_buf->size; + lost = true; + } + + /* Insert barrier packets at the beginning, if there was an overflow */ + if (lost) + tmc_etr_buf_insert_barrier_packet(etr_buf, etr_buf->offset); + tmc_etr_sync_perf_buffer(etr_perf, offset, size); /* * In snapshot mode we simply increment the head by the number of byte @@ -1511,8 +1544,6 @@ tmc_update_etr_buffer(struct coresight_device *csdev, */ if (etr_perf->snapshot) handle->head += size; - - lost |= etr_buf->full; out: /* * Don't set the TRUNCATED flag in snapshot mode because 1) the @@ -1556,7 +1587,6 @@ static int tmc_enable_etr_sink_perf(struct coresight_device *csdev, void *data) } etr_perf->head = PERF_IDX2OFF(handle->head, etr_perf); - drvdata->perf_data = etr_perf; /* * No HW configuration is needed if the sink is already in @@ -1572,6 +1602,7 @@ static int tmc_enable_etr_sink_perf(struct coresight_device *csdev, void *data) /* Associate with monitored process. */ drvdata->pid = pid; drvdata->mode = CS_MODE_PERF; + drvdata->perf_buf = etr_perf->etr_buf; atomic_inc(csdev->refcnt); } @@ -1617,6 +1648,8 @@ static int tmc_disable_etr_sink(struct coresight_device *csdev) /* Dissociate from monitored process. */ drvdata->pid = -1; drvdata->mode = CS_MODE_DISABLED; + /* Reset perf specific data */ + drvdata->perf_buf = NULL; spin_unlock_irqrestore(&drvdata->spinlock, flags); diff --git a/drivers/hwtracing/coresight/coresight-tmc.c b/drivers/hwtracing/coresight/coresight-tmc.c index be37aff573b4..1cf82fa58289 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.c +++ b/drivers/hwtracing/coresight/coresight-tmc.c @@ -70,6 +70,34 @@ void tmc_disable_hw(struct tmc_drvdata *drvdata) writel_relaxed(0x0, drvdata->base + TMC_CTL); } +u32 tmc_get_memwidth_mask(struct tmc_drvdata *drvdata) +{ + u32 mask = 0; + + /* + * When moving RRP or an offset address forward, the new values must + * be byte-address aligned to the width of the trace memory databus + * _and_ to a frame boundary (16 byte), whichever is the biggest. For + * example, for 32-bit, 64-bit and 128-bit wide trace memory, the four + * LSBs must be 0s. For 256-bit wide trace memory, the five LSBs must + * be 0s. + */ + switch (drvdata->memwidth) { + case TMC_MEM_INTF_WIDTH_32BITS: + /* fallthrough */ + case TMC_MEM_INTF_WIDTH_64BITS: + /* fallthrough */ + case TMC_MEM_INTF_WIDTH_128BITS: + mask = GENMASK(31, 4); + break; + case TMC_MEM_INTF_WIDTH_256BITS: + mask = GENMASK(31, 5); + break; + } + + return mask; +} + static int tmc_read_prepare(struct tmc_drvdata *drvdata) { int ret = 0; @@ -236,6 +264,7 @@ coresight_tmc_reg(ffcr, TMC_FFCR); coresight_tmc_reg(mode, TMC_MODE); coresight_tmc_reg(pscr, TMC_PSCR); coresight_tmc_reg(axictl, TMC_AXICTL); +coresight_tmc_reg(authstatus, TMC_AUTHSTATUS); coresight_tmc_reg(devid, CORESIGHT_DEVID); coresight_tmc_reg64(rrp, TMC_RRP, TMC_RRPHI); coresight_tmc_reg64(rwp, TMC_RWP, TMC_RWPHI); @@ -255,6 +284,7 @@ static struct attribute *coresight_tmc_mgmt_attrs[] = { &dev_attr_devid.attr, &dev_attr_dba.attr, &dev_attr_axictl.attr, + &dev_attr_authstatus.attr, NULL, }; @@ -342,6 +372,13 @@ static inline bool tmc_etr_can_use_sg(struct device *dev) return fwnode_property_present(dev->fwnode, "arm,scatter-gather"); } +static inline bool tmc_etr_has_non_secure_access(struct tmc_drvdata *drvdata) +{ + u32 auth = readl_relaxed(drvdata->base + TMC_AUTHSTATUS); + + return (auth & TMC_AUTH_NSID_MASK) == 0x3; +} + /* Detect and initialise the capabilities of a TMC ETR */ static int tmc_etr_setup_caps(struct device *parent, u32 devid, void *dev_caps) { @@ -349,6 +386,9 @@ static int tmc_etr_setup_caps(struct device *parent, u32 devid, void *dev_caps) u32 dma_mask = 0; struct tmc_drvdata *drvdata = dev_get_drvdata(parent); + if (!tmc_etr_has_non_secure_access(drvdata)) + return -EACCES; + /* Set the unadvertised capabilities */ tmc_etr_init_caps(drvdata, (u32)(unsigned long)dev_caps); diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h index 1ed50411cc3c..71de978575f3 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.h +++ b/drivers/hwtracing/coresight/coresight-tmc.h @@ -39,6 +39,7 @@ #define TMC_ITATBCTR2 0xef0 #define TMC_ITATBCTR1 0xef4 #define TMC_ITATBCTR0 0xef8 +#define TMC_AUTHSTATUS 0xfb8 /* register description */ /* TMC_CTL - 0x020 */ @@ -47,6 +48,7 @@ #define TMC_STS_TMCREADY_BIT 2 #define TMC_STS_FULL BIT(0) #define TMC_STS_TRIGGERED BIT(1) +#define TMC_STS_MEMERR BIT(5) /* * TMC_AXICTL - 0x110 * @@ -89,6 +91,8 @@ #define TMC_DEVID_AXIAW_SHIFT 17 #define TMC_DEVID_AXIAW_MASK 0x7f +#define TMC_AUTH_NSID_MASK GENMASK(1, 0) + enum tmc_config_type { TMC_CONFIG_TYPE_ETB, TMC_CONFIG_TYPE_ETR, @@ -178,8 +182,8 @@ struct etr_buf { * device configuration register (DEVID) * @idr: Holds etr_bufs allocated for this ETR. * @idr_mutex: Access serialisation for idr. - * @perf_data: PERF buffer for ETR. - * @sysfs_data: SYSFS buffer for ETR. + * @sysfs_buf: SYSFS buffer for ETR. + * @perf_buf: PERF buffer for ETR. */ struct tmc_drvdata { void __iomem *base; @@ -202,7 +206,7 @@ struct tmc_drvdata { struct idr idr; struct mutex idr_mutex; struct etr_buf *sysfs_buf; - void *perf_data; + struct etr_buf *perf_buf; }; struct etr_buf_operations { @@ -251,6 +255,7 @@ void tmc_wait_for_tmcready(struct tmc_drvdata *drvdata); void tmc_flush_and_stop(struct tmc_drvdata *drvdata); void tmc_enable_hw(struct tmc_drvdata *drvdata); void tmc_disable_hw(struct tmc_drvdata *drvdata); +u32 tmc_get_memwidth_mask(struct tmc_drvdata *drvdata); /* ETB/ETF functions */ int tmc_read_prepare_etb(struct tmc_drvdata *drvdata); diff --git a/drivers/hwtracing/intel_th/Makefile b/drivers/hwtracing/intel_th/Makefile index d9252fa8d9ca..b63eb8f309ad 100644 --- a/drivers/hwtracing/intel_th/Makefile +++ b/drivers/hwtracing/intel_th/Makefile @@ -20,3 +20,6 @@ intel_th_msu-y := msu.o obj-$(CONFIG_INTEL_TH_PTI) += intel_th_pti.o intel_th_pti-y := pti.o + +obj-$(CONFIG_INTEL_TH_MSU) += intel_th_msu_sink.o +intel_th_msu_sink-y := msu-sink.o diff --git a/drivers/hwtracing/intel_th/msu-sink.c b/drivers/hwtracing/intel_th/msu-sink.c new file mode 100644 index 000000000000..2c7f5116be12 --- /dev/null +++ b/drivers/hwtracing/intel_th/msu-sink.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * An example software sink buffer for Intel TH MSU. + * + * Copyright (C) 2019 Intel Corporation. + */ + +#include <linux/intel_th.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/device.h> +#include <linux/dma-mapping.h> + +#define MAX_SGTS 16 + +struct msu_sink_private { + struct device *dev; + struct sg_table **sgts; + unsigned int nr_sgts; +}; + +static void *msu_sink_assign(struct device *dev, int *mode) +{ + struct msu_sink_private *priv; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return NULL; + + priv->sgts = kcalloc(MAX_SGTS, sizeof(void *), GFP_KERNEL); + if (!priv->sgts) { + kfree(priv); + return NULL; + } + + priv->dev = dev; + *mode = MSC_MODE_MULTI; + + return priv; +} + +static void msu_sink_unassign(void *data) +{ + struct msu_sink_private *priv = data; + + kfree(priv->sgts); + kfree(priv); +} + +/* See also: msc.c: __msc_buffer_win_alloc() */ +static int msu_sink_alloc_window(void *data, struct sg_table **sgt, size_t size) +{ + struct msu_sink_private *priv = data; + unsigned int nents; + struct scatterlist *sg_ptr; + void *block; + int ret, i; + + if (priv->nr_sgts == MAX_SGTS) + return -ENOMEM; + + nents = DIV_ROUND_UP(size, PAGE_SIZE); + + ret = sg_alloc_table(*sgt, nents, GFP_KERNEL); + if (ret) + return -ENOMEM; + + priv->sgts[priv->nr_sgts++] = *sgt; + + for_each_sg((*sgt)->sgl, sg_ptr, nents, i) { + block = dma_alloc_coherent(priv->dev->parent->parent, + PAGE_SIZE, &sg_dma_address(sg_ptr), + GFP_KERNEL); + sg_set_buf(sg_ptr, block, PAGE_SIZE); + } + + return nents; +} + +/* See also: msc.c: __msc_buffer_win_free() */ +static void msu_sink_free_window(void *data, struct sg_table *sgt) +{ + struct msu_sink_private *priv = data; + struct scatterlist *sg_ptr; + int i; + + for_each_sg(sgt->sgl, sg_ptr, sgt->nents, i) { + dma_free_coherent(priv->dev->parent->parent, PAGE_SIZE, + sg_virt(sg_ptr), sg_dma_address(sg_ptr)); + } + + sg_free_table(sgt); + priv->nr_sgts--; +} + +static int msu_sink_ready(void *data, struct sg_table *sgt, size_t bytes) +{ + struct msu_sink_private *priv = data; + + intel_th_msc_window_unlock(priv->dev, sgt); + + return 0; +} + +static const struct msu_buffer sink_mbuf = { + .name = "sink", + .assign = msu_sink_assign, + .unassign = msu_sink_unassign, + .alloc_window = msu_sink_alloc_window, + .free_window = msu_sink_free_window, + .ready = msu_sink_ready, +}; + +module_intel_th_msu_buffer(sink_mbuf); + +MODULE_LICENSE("GPL v2"); diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c index 8ab28e5fb366..fc9f15f36ad4 100644 --- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -17,21 +17,48 @@ #include <linux/mm.h> #include <linux/fs.h> #include <linux/io.h> +#include <linux/workqueue.h> #include <linux/dma-mapping.h> #ifdef CONFIG_X86 #include <asm/set_memory.h> #endif +#include <linux/intel_th.h> #include "intel_th.h" #include "msu.h" #define msc_dev(x) (&(x)->thdev->dev) +/* + * Lockout state transitions: + * READY -> INUSE -+-> LOCKED -+-> READY -> etc. + * \-----------/ + * WIN_READY: window can be used by HW + * WIN_INUSE: window is in use + * WIN_LOCKED: window is filled up and is being processed by the buffer + * handling code + * + * All state transitions happen automatically, except for the LOCKED->READY, + * which needs to be signalled by the buffer code by calling + * intel_th_msc_window_unlock(). + * + * When the interrupt handler has to switch to the next window, it checks + * whether it's READY, and if it is, it performs the switch and tracing + * continues. If it's LOCKED, it stops the trace. + */ +enum lockout_state { + WIN_READY = 0, + WIN_INUSE, + WIN_LOCKED +}; + /** * struct msc_window - multiblock mode window descriptor * @entry: window list linkage (msc::win_list) * @pgoff: page offset into the buffer that this window starts at + * @lockout: lockout state, see comment below + * @lo_lock: lockout state serialization * @nr_blocks: number of blocks (pages) in this window * @nr_segs: number of segments in this window (<= @nr_blocks) * @_sgt: array of block descriptors @@ -40,6 +67,8 @@ struct msc_window { struct list_head entry; unsigned long pgoff; + enum lockout_state lockout; + spinlock_t lo_lock; unsigned int nr_blocks; unsigned int nr_segs; struct msc *msc; @@ -66,8 +95,8 @@ struct msc_iter { struct msc_window *start_win; struct msc_window *win; unsigned long offset; - int start_block; - int block; + struct scatterlist *start_block; + struct scatterlist *block; unsigned int block_off; unsigned int wrap_count; unsigned int eof; @@ -77,6 +106,8 @@ struct msc_iter { * struct msc - MSC device representation * @reg_base: register window base address * @thdev: intel_th_device pointer + * @mbuf: MSU buffer, if assigned + * @mbuf_priv MSU buffer's private data, if @mbuf * @win_list: list of windows in multiblock mode * @single_sgt: single mode buffer * @cur_win: current window @@ -100,6 +131,10 @@ struct msc { void __iomem *msu_base; struct intel_th_device *thdev; + const struct msu_buffer *mbuf; + void *mbuf_priv; + + struct work_struct work; struct list_head win_list; struct sg_table single_sgt; struct msc_window *cur_win; @@ -108,6 +143,8 @@ struct msc { unsigned int single_wrap : 1; void *base; dma_addr_t base_addr; + u32 orig_addr; + u32 orig_sz; /* <0: no buffer, 0: no users, >0: active users */ atomic_t user_count; @@ -126,6 +163,101 @@ struct msc { unsigned int index; }; +static LIST_HEAD(msu_buffer_list); +static struct mutex msu_buffer_mutex; + +/** + * struct msu_buffer_entry - internal MSU buffer bookkeeping + * @entry: link to msu_buffer_list + * @mbuf: MSU buffer object + * @owner: module that provides this MSU buffer + */ +struct msu_buffer_entry { + struct list_head entry; + const struct msu_buffer *mbuf; + struct module *owner; +}; + +static struct msu_buffer_entry *__msu_buffer_entry_find(const char *name) +{ + struct msu_buffer_entry *mbe; + + lockdep_assert_held(&msu_buffer_mutex); + + list_for_each_entry(mbe, &msu_buffer_list, entry) { + if (!strcmp(mbe->mbuf->name, name)) + return mbe; + } + + return NULL; +} + +static const struct msu_buffer * +msu_buffer_get(const char *name) +{ + struct msu_buffer_entry *mbe; + + mutex_lock(&msu_buffer_mutex); + mbe = __msu_buffer_entry_find(name); + if (mbe && !try_module_get(mbe->owner)) + mbe = NULL; + mutex_unlock(&msu_buffer_mutex); + + return mbe ? mbe->mbuf : NULL; +} + +static void msu_buffer_put(const struct msu_buffer *mbuf) +{ + struct msu_buffer_entry *mbe; + + mutex_lock(&msu_buffer_mutex); + mbe = __msu_buffer_entry_find(mbuf->name); + if (mbe) + module_put(mbe->owner); + mutex_unlock(&msu_buffer_mutex); +} + +int intel_th_msu_buffer_register(const struct msu_buffer *mbuf, + struct module *owner) +{ + struct msu_buffer_entry *mbe; + int ret = 0; + + mbe = kzalloc(sizeof(*mbe), GFP_KERNEL); + if (!mbe) + return -ENOMEM; + + mutex_lock(&msu_buffer_mutex); + if (__msu_buffer_entry_find(mbuf->name)) { + ret = -EEXIST; + kfree(mbe); + goto unlock; + } + + mbe->mbuf = mbuf; + mbe->owner = owner; + list_add_tail(&mbe->entry, &msu_buffer_list); +unlock: + mutex_unlock(&msu_buffer_mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(intel_th_msu_buffer_register); + +void intel_th_msu_buffer_unregister(const struct msu_buffer *mbuf) +{ + struct msu_buffer_entry *mbe; + + mutex_lock(&msu_buffer_mutex); + mbe = __msu_buffer_entry_find(mbuf->name); + if (mbe) { + list_del(&mbe->entry); + kfree(mbe); + } + mutex_unlock(&msu_buffer_mutex); +} +EXPORT_SYMBOL_GPL(intel_th_msu_buffer_unregister); + static inline bool msc_block_is_empty(struct msc_block_desc *bdesc) { /* header hasn't been written */ @@ -139,28 +271,25 @@ static inline bool msc_block_is_empty(struct msc_block_desc *bdesc) return false; } -static inline struct msc_block_desc * -msc_win_block(struct msc_window *win, unsigned int block) +static inline struct scatterlist *msc_win_base_sg(struct msc_window *win) { - return sg_virt(&win->sgt->sgl[block]); + return win->sgt->sgl; } -static inline size_t -msc_win_actual_bsz(struct msc_window *win, unsigned int block) +static inline struct msc_block_desc *msc_win_base(struct msc_window *win) { - return win->sgt->sgl[block].length; + return sg_virt(msc_win_base_sg(win)); } -static inline dma_addr_t -msc_win_baddr(struct msc_window *win, unsigned int block) +static inline dma_addr_t msc_win_base_dma(struct msc_window *win) { - return sg_dma_address(&win->sgt->sgl[block]); + return sg_dma_address(msc_win_base_sg(win)); } static inline unsigned long -msc_win_bpfn(struct msc_window *win, unsigned int block) +msc_win_base_pfn(struct msc_window *win) { - return msc_win_baddr(win, block) >> PAGE_SHIFT; + return PFN_DOWN(msc_win_base_dma(win)); } /** @@ -188,6 +317,26 @@ static struct msc_window *msc_next_window(struct msc_window *win) return list_next_entry(win, entry); } +static size_t msc_win_total_sz(struct msc_window *win) +{ + struct scatterlist *sg; + unsigned int blk; + size_t size = 0; + + for_each_sg(win->sgt->sgl, sg, win->nr_segs, blk) { + struct msc_block_desc *bdesc = sg_virt(sg); + + if (msc_block_wrapped(bdesc)) + return win->nr_blocks << PAGE_SHIFT; + + size += msc_total_sz(bdesc); + if (msc_block_last_written(bdesc)) + break; + } + + return size; +} + /** * msc_find_window() - find a window matching a given sg_table * @msc: MSC device @@ -216,7 +365,7 @@ msc_find_window(struct msc *msc, struct sg_table *sgt, bool nonempty) found++; /* skip the empty ones */ - if (nonempty && msc_block_is_empty(msc_win_block(win, 0))) + if (nonempty && msc_block_is_empty(msc_win_base(win))) continue; if (found) @@ -250,44 +399,38 @@ static struct msc_window *msc_oldest_window(struct msc *msc) } /** - * msc_win_oldest_block() - locate the oldest block in a given window + * msc_win_oldest_sg() - locate the oldest block in a given window * @win: window to look at * * Return: index of the block with the oldest data */ -static unsigned int msc_win_oldest_block(struct msc_window *win) +static struct scatterlist *msc_win_oldest_sg(struct msc_window *win) { unsigned int blk; - struct msc_block_desc *bdesc = msc_win_block(win, 0); + struct scatterlist *sg; + struct msc_block_desc *bdesc = msc_win_base(win); /* without wrapping, first block is the oldest */ if (!msc_block_wrapped(bdesc)) - return 0; + return msc_win_base_sg(win); /* * with wrapping, last written block contains both the newest and the * oldest data for this window. */ - for (blk = 0; blk < win->nr_segs; blk++) { - bdesc = msc_win_block(win, blk); + for_each_sg(win->sgt->sgl, sg, win->nr_segs, blk) { + struct msc_block_desc *bdesc = sg_virt(sg); if (msc_block_last_written(bdesc)) - return blk; + return sg; } - return 0; + return msc_win_base_sg(win); } static struct msc_block_desc *msc_iter_bdesc(struct msc_iter *iter) { - return msc_win_block(iter->win, iter->block); -} - -static void msc_iter_init(struct msc_iter *iter) -{ - memset(iter, 0, sizeof(*iter)); - iter->start_block = -1; - iter->block = -1; + return sg_virt(iter->block); } static struct msc_iter *msc_iter_install(struct msc *msc) @@ -312,7 +455,6 @@ static struct msc_iter *msc_iter_install(struct msc *msc) goto unlock; } - msc_iter_init(iter); iter->msc = msc; list_add_tail(&iter->entry, &msc->iter_list); @@ -333,10 +475,10 @@ static void msc_iter_remove(struct msc_iter *iter, struct msc *msc) static void msc_iter_block_start(struct msc_iter *iter) { - if (iter->start_block != -1) + if (iter->start_block) return; - iter->start_block = msc_win_oldest_block(iter->win); + iter->start_block = msc_win_oldest_sg(iter->win); iter->block = iter->start_block; iter->wrap_count = 0; @@ -360,7 +502,7 @@ static int msc_iter_win_start(struct msc_iter *iter, struct msc *msc) return -EINVAL; iter->win = iter->start_win; - iter->start_block = -1; + iter->start_block = NULL; msc_iter_block_start(iter); @@ -370,7 +512,7 @@ static int msc_iter_win_start(struct msc_iter *iter, struct msc *msc) static int msc_iter_win_advance(struct msc_iter *iter) { iter->win = msc_next_window(iter->win); - iter->start_block = -1; + iter->start_block = NULL; if (iter->win == iter->start_win) { iter->eof++; @@ -400,8 +542,10 @@ static int msc_iter_block_advance(struct msc_iter *iter) return msc_iter_win_advance(iter); /* block advance */ - if (++iter->block == iter->win->nr_segs) - iter->block = 0; + if (sg_is_last(iter->block)) + iter->block = msc_win_base_sg(iter->win); + else + iter->block = sg_next(iter->block); /* no wrapping, sanity check in case there is no last written block */ if (!iter->wrap_count && iter->block == iter->start_block) @@ -506,14 +650,15 @@ next_block: static void msc_buffer_clear_hw_header(struct msc *msc) { struct msc_window *win; + struct scatterlist *sg; list_for_each_entry(win, &msc->win_list, entry) { unsigned int blk; size_t hw_sz = sizeof(struct msc_block_desc) - offsetof(struct msc_block_desc, hw_tag); - for (blk = 0; blk < win->nr_segs; blk++) { - struct msc_block_desc *bdesc = msc_win_block(win, blk); + for_each_sg(win->sgt->sgl, sg, win->nr_segs, blk) { + struct msc_block_desc *bdesc = sg_virt(sg); memset(&bdesc->hw_tag, 0, hw_sz); } @@ -527,6 +672,9 @@ static int intel_th_msu_init(struct msc *msc) if (!msc->do_irq) return 0; + if (!msc->mbuf) + return 0; + mintctl = ioread32(msc->msu_base + REG_MSU_MINTCTL); mintctl |= msc->index ? M1BLIE : M0BLIE; iowrite32(mintctl, msc->msu_base + REG_MSU_MINTCTL); @@ -554,6 +702,49 @@ static void intel_th_msu_deinit(struct msc *msc) iowrite32(mintctl, msc->msu_base + REG_MSU_MINTCTL); } +static int msc_win_set_lockout(struct msc_window *win, + enum lockout_state expect, + enum lockout_state new) +{ + enum lockout_state old; + unsigned long flags; + int ret = 0; + + if (!win->msc->mbuf) + return 0; + + spin_lock_irqsave(&win->lo_lock, flags); + old = win->lockout; + + if (old != expect) { + ret = -EINVAL; + dev_warn_ratelimited(msc_dev(win->msc), + "expected lockout state %d, got %d\n", + expect, old); + goto unlock; + } + + win->lockout = new; + + if (old == expect && new == WIN_LOCKED) + atomic_inc(&win->msc->user_count); + else if (old == expect && old == WIN_LOCKED) + atomic_dec(&win->msc->user_count); + +unlock: + spin_unlock_irqrestore(&win->lo_lock, flags); + + if (ret) { + if (expect == WIN_READY && old == WIN_LOCKED) + return -EBUSY; + + /* from intel_th_msc_window_unlock(), don't warn if not locked */ + if (expect == WIN_LOCKED && old == new) + return 0; + } + + return ret; +} /** * msc_configure() - set up MSC hardware * @msc: the MSC device to configure @@ -571,8 +762,15 @@ static int msc_configure(struct msc *msc) if (msc->mode > MSC_MODE_MULTI) return -ENOTSUPP; - if (msc->mode == MSC_MODE_MULTI) + if (msc->mode == MSC_MODE_MULTI) { + if (msc_win_set_lockout(msc->cur_win, WIN_READY, WIN_INUSE)) + return -EBUSY; + msc_buffer_clear_hw_header(msc); + } + + msc->orig_addr = ioread32(msc->reg_base + REG_MSU_MSC0BAR); + msc->orig_sz = ioread32(msc->reg_base + REG_MSU_MSC0SIZE); reg = msc->base_addr >> PAGE_SHIFT; iowrite32(reg, msc->reg_base + REG_MSU_MSC0BAR); @@ -594,10 +792,14 @@ static int msc_configure(struct msc *msc) iowrite32(reg, msc->reg_base + REG_MSU_MSC0CTL); + intel_th_msu_init(msc); + msc->thdev->output.multiblock = msc->mode == MSC_MODE_MULTI; intel_th_trace_enable(msc->thdev); msc->enabled = 1; + if (msc->mbuf && msc->mbuf->activate) + msc->mbuf->activate(msc->mbuf_priv); return 0; } @@ -611,10 +813,17 @@ static int msc_configure(struct msc *msc) */ static void msc_disable(struct msc *msc) { + struct msc_window *win = msc->cur_win; u32 reg; lockdep_assert_held(&msc->buf_mutex); + if (msc->mode == MSC_MODE_MULTI) + msc_win_set_lockout(win, WIN_INUSE, WIN_LOCKED); + + if (msc->mbuf && msc->mbuf->deactivate) + msc->mbuf->deactivate(msc->mbuf_priv); + intel_th_msu_deinit(msc); intel_th_trace_disable(msc->thdev); if (msc->mode == MSC_MODE_SINGLE) { @@ -630,16 +839,25 @@ static void msc_disable(struct msc *msc) reg = ioread32(msc->reg_base + REG_MSU_MSC0CTL); reg &= ~MSC_EN; iowrite32(reg, msc->reg_base + REG_MSU_MSC0CTL); + + if (msc->mbuf && msc->mbuf->ready) + msc->mbuf->ready(msc->mbuf_priv, win->sgt, + msc_win_total_sz(win)); + msc->enabled = 0; - iowrite32(0, msc->reg_base + REG_MSU_MSC0BAR); - iowrite32(0, msc->reg_base + REG_MSU_MSC0SIZE); + iowrite32(msc->orig_addr, msc->reg_base + REG_MSU_MSC0BAR); + iowrite32(msc->orig_sz, msc->reg_base + REG_MSU_MSC0SIZE); dev_dbg(msc_dev(msc), "MSCnNWSA: %08x\n", ioread32(msc->reg_base + REG_MSU_MSC0NWSA)); reg = ioread32(msc->reg_base + REG_MSU_MSC0STS); dev_dbg(msc_dev(msc), "MSCnSTS: %08x\n", reg); + + reg = ioread32(msc->reg_base + REG_MSU_MSUSTS); + reg &= msc->index ? MSUSTS_MSC1BLAST : MSUSTS_MSC0BLAST; + iowrite32(reg, msc->reg_base + REG_MSU_MSUSTS); } static int intel_th_msc_activate(struct intel_th_device *thdev) @@ -791,10 +1009,9 @@ static int __msc_buffer_win_alloc(struct msc_window *win, return nr_segs; err_nomem: - for (i--; i >= 0; i--) + for_each_sg(win->sgt->sgl, sg_ptr, i, ret) dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE, - msc_win_block(win, i), - msc_win_baddr(win, i)); + sg_virt(sg_ptr), sg_dma_address(sg_ptr)); sg_free_table(win->sgt); @@ -804,20 +1021,26 @@ err_nomem: #ifdef CONFIG_X86 static void msc_buffer_set_uc(struct msc_window *win, unsigned int nr_segs) { + struct scatterlist *sg_ptr; int i; - for (i = 0; i < nr_segs; i++) + for_each_sg(win->sgt->sgl, sg_ptr, nr_segs, i) { /* Set the page as uncached */ - set_memory_uc((unsigned long)msc_win_block(win, i), 1); + set_memory_uc((unsigned long)sg_virt(sg_ptr), + PFN_DOWN(sg_ptr->length)); + } } static void msc_buffer_set_wb(struct msc_window *win) { + struct scatterlist *sg_ptr; int i; - for (i = 0; i < win->nr_segs; i++) + for_each_sg(win->sgt->sgl, sg_ptr, win->nr_segs, i) { /* Reset the page to write-back */ - set_memory_wb((unsigned long)msc_win_block(win, i), 1); + set_memory_wb((unsigned long)sg_virt(sg_ptr), + PFN_DOWN(sg_ptr->length)); + } } #else /* !X86 */ static inline void @@ -843,19 +1066,14 @@ static int msc_buffer_win_alloc(struct msc *msc, unsigned int nr_blocks) if (!nr_blocks) return 0; - /* - * This limitation hold as long as we need random access to the - * block. When that changes, this can go away. - */ - if (nr_blocks > SG_MAX_SINGLE_ALLOC) - return -EINVAL; - win = kzalloc(sizeof(*win), GFP_KERNEL); if (!win) return -ENOMEM; win->msc = msc; win->sgt = &win->_sgt; + win->lockout = WIN_READY; + spin_lock_init(&win->lo_lock); if (!list_empty(&msc->win_list)) { struct msc_window *prev = list_last_entry(&msc->win_list, @@ -865,8 +1083,13 @@ static int msc_buffer_win_alloc(struct msc *msc, unsigned int nr_blocks) win->pgoff = prev->pgoff + prev->nr_blocks; } - ret = __msc_buffer_win_alloc(win, nr_blocks); - if (ret < 0) + if (msc->mbuf && msc->mbuf->alloc_window) + ret = msc->mbuf->alloc_window(msc->mbuf_priv, &win->sgt, + nr_blocks << PAGE_SHIFT); + else + ret = __msc_buffer_win_alloc(win, nr_blocks); + + if (ret <= 0) goto err_nomem; msc_buffer_set_uc(win, ret); @@ -875,8 +1098,8 @@ static int msc_buffer_win_alloc(struct msc *msc, unsigned int nr_blocks) win->nr_blocks = nr_blocks; if (list_empty(&msc->win_list)) { - msc->base = msc_win_block(win, 0); - msc->base_addr = msc_win_baddr(win, 0); + msc->base = msc_win_base(win); + msc->base_addr = msc_win_base_dma(win); msc->cur_win = win; } @@ -893,14 +1116,15 @@ err_nomem: static void __msc_buffer_win_free(struct msc *msc, struct msc_window *win) { + struct scatterlist *sg; int i; - for (i = 0; i < win->nr_segs; i++) { - struct page *page = sg_page(&win->sgt->sgl[i]); + for_each_sg(win->sgt->sgl, sg, win->nr_segs, i) { + struct page *page = sg_page(sg); page->mapping = NULL; dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE, - msc_win_block(win, i), msc_win_baddr(win, i)); + sg_virt(sg), sg_dma_address(sg)); } sg_free_table(win->sgt); } @@ -925,7 +1149,10 @@ static void msc_buffer_win_free(struct msc *msc, struct msc_window *win) msc_buffer_set_wb(win); - __msc_buffer_win_free(msc, win); + if (msc->mbuf && msc->mbuf->free_window) + msc->mbuf->free_window(msc->mbuf_priv, win->sgt); + else + __msc_buffer_win_free(msc, win); kfree(win); } @@ -943,6 +1170,7 @@ static void msc_buffer_relink(struct msc *msc) /* call with msc::mutex locked */ list_for_each_entry(win, &msc->win_list, entry) { + struct scatterlist *sg; unsigned int blk; u32 sw_tag = 0; @@ -958,12 +1186,12 @@ static void msc_buffer_relink(struct msc *msc) next_win = list_next_entry(win, entry); } - for (blk = 0; blk < win->nr_segs; blk++) { - struct msc_block_desc *bdesc = msc_win_block(win, blk); + for_each_sg(win->sgt->sgl, sg, win->nr_segs, blk) { + struct msc_block_desc *bdesc = sg_virt(sg); memset(bdesc, 0, sizeof(*bdesc)); - bdesc->next_win = msc_win_bpfn(next_win, 0); + bdesc->next_win = msc_win_base_pfn(next_win); /* * Similarly to last window, last block should point @@ -971,13 +1199,15 @@ static void msc_buffer_relink(struct msc *msc) */ if (blk == win->nr_segs - 1) { sw_tag |= MSC_SW_TAG_LASTBLK; - bdesc->next_blk = msc_win_bpfn(win, 0); + bdesc->next_blk = msc_win_base_pfn(win); } else { - bdesc->next_blk = msc_win_bpfn(win, blk + 1); + dma_addr_t addr = sg_dma_address(sg_next(sg)); + + bdesc->next_blk = PFN_DOWN(addr); } bdesc->sw_tag = sw_tag; - bdesc->block_sz = msc_win_actual_bsz(win, blk) / 64; + bdesc->block_sz = sg->length / 64; } } @@ -1136,6 +1366,7 @@ static int msc_buffer_free_unless_used(struct msc *msc) static struct page *msc_buffer_get_page(struct msc *msc, unsigned long pgoff) { struct msc_window *win; + struct scatterlist *sg; unsigned int blk; if (msc->mode == MSC_MODE_SINGLE) @@ -1150,9 +1381,9 @@ static struct page *msc_buffer_get_page(struct msc *msc, unsigned long pgoff) found: pgoff -= win->pgoff; - for (blk = 0; blk < win->nr_segs; blk++) { - struct page *page = sg_page(&win->sgt->sgl[blk]); - size_t pgsz = PFN_DOWN(msc_win_actual_bsz(win, blk)); + for_each_sg(win->sgt->sgl, sg, win->nr_segs, blk) { + struct page *page = sg_page(sg); + size_t pgsz = PFN_DOWN(sg->length); if (pgoff < pgsz) return page + pgoff; @@ -1456,24 +1687,83 @@ static void msc_win_switch(struct msc *msc) else msc->cur_win = list_next_entry(msc->cur_win, entry); - msc->base = msc_win_block(msc->cur_win, 0); - msc->base_addr = msc_win_baddr(msc->cur_win, 0); + msc->base = msc_win_base(msc->cur_win); + msc->base_addr = msc_win_base_dma(msc->cur_win); intel_th_trace_switch(msc->thdev); } +/** + * intel_th_msc_window_unlock - put the window back in rotation + * @dev: MSC device to which this relates + * @sgt: buffer's sg_table for the window, does nothing if NULL + */ +void intel_th_msc_window_unlock(struct device *dev, struct sg_table *sgt) +{ + struct msc *msc = dev_get_drvdata(dev); + struct msc_window *win; + + if (!sgt) + return; + + win = msc_find_window(msc, sgt, false); + if (!win) + return; + + msc_win_set_lockout(win, WIN_LOCKED, WIN_READY); +} +EXPORT_SYMBOL_GPL(intel_th_msc_window_unlock); + +static void msc_work(struct work_struct *work) +{ + struct msc *msc = container_of(work, struct msc, work); + + intel_th_msc_deactivate(msc->thdev); +} + static irqreturn_t intel_th_msc_interrupt(struct intel_th_device *thdev) { struct msc *msc = dev_get_drvdata(&thdev->dev); u32 msusts = ioread32(msc->msu_base + REG_MSU_MSUSTS); u32 mask = msc->index ? MSUSTS_MSC1BLAST : MSUSTS_MSC0BLAST; + struct msc_window *win, *next_win; + + if (!msc->do_irq || !msc->mbuf) + return IRQ_NONE; + + msusts &= mask; + + if (!msusts) + return msc->enabled ? IRQ_HANDLED : IRQ_NONE; + + iowrite32(msusts, msc->msu_base + REG_MSU_MSUSTS); - if (!(msusts & mask)) { - if (msc->enabled) - return IRQ_HANDLED; + if (!msc->enabled) return IRQ_NONE; + + /* grab the window before we do the switch */ + win = msc->cur_win; + if (!win) + return IRQ_HANDLED; + next_win = msc_next_window(win); + if (!next_win) + return IRQ_HANDLED; + + /* next window: if READY, proceed, if LOCKED, stop the trace */ + if (msc_win_set_lockout(next_win, WIN_READY, WIN_INUSE)) { + schedule_work(&msc->work); + return IRQ_HANDLED; } + /* current window: INUSE -> LOCKED */ + msc_win_set_lockout(win, WIN_INUSE, WIN_LOCKED); + + msc_win_switch(msc); + + if (msc->mbuf && msc->mbuf->ready) + msc->mbuf->ready(msc->mbuf_priv, win->sgt, + msc_win_total_sz(win)); + return IRQ_HANDLED; } @@ -1511,21 +1801,43 @@ wrap_store(struct device *dev, struct device_attribute *attr, const char *buf, static DEVICE_ATTR_RW(wrap); +static void msc_buffer_unassign(struct msc *msc) +{ + lockdep_assert_held(&msc->buf_mutex); + + if (!msc->mbuf) + return; + + msc->mbuf->unassign(msc->mbuf_priv); + msu_buffer_put(msc->mbuf); + msc->mbuf_priv = NULL; + msc->mbuf = NULL; +} + static ssize_t mode_show(struct device *dev, struct device_attribute *attr, char *buf) { struct msc *msc = dev_get_drvdata(dev); + const char *mode = msc_mode[msc->mode]; + ssize_t ret; + + mutex_lock(&msc->buf_mutex); + if (msc->mbuf) + mode = msc->mbuf->name; + ret = scnprintf(buf, PAGE_SIZE, "%s\n", mode); + mutex_unlock(&msc->buf_mutex); - return scnprintf(buf, PAGE_SIZE, "%s\n", msc_mode[msc->mode]); + return ret; } static ssize_t mode_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { + const struct msu_buffer *mbuf = NULL; struct msc *msc = dev_get_drvdata(dev); size_t len = size; - char *cp; + char *cp, *mode; int i, ret; if (!capable(CAP_SYS_RAWIO)) @@ -1535,17 +1847,59 @@ mode_store(struct device *dev, struct device_attribute *attr, const char *buf, if (cp) len = cp - buf; - for (i = 0; i < ARRAY_SIZE(msc_mode); i++) - if (!strncmp(msc_mode[i], buf, len)) - goto found; + mode = kstrndup(buf, len, GFP_KERNEL); + i = match_string(msc_mode, ARRAY_SIZE(msc_mode), mode); + if (i >= 0) + goto found; + + /* Buffer sinks only work with a usable IRQ */ + if (!msc->do_irq) { + kfree(mode); + return -EINVAL; + } + + mbuf = msu_buffer_get(mode); + kfree(mode); + if (mbuf) + goto found; return -EINVAL; found: mutex_lock(&msc->buf_mutex); + ret = 0; + + /* Same buffer: do nothing */ + if (mbuf && mbuf == msc->mbuf) { + /* put the extra reference we just got */ + msu_buffer_put(mbuf); + goto unlock; + } + ret = msc_buffer_unlocked_free_unless_used(msc); - if (!ret) - msc->mode = i; + if (ret) + goto unlock; + + if (mbuf) { + void *mbuf_priv = mbuf->assign(dev, &i); + + if (!mbuf_priv) { + ret = -ENOMEM; + goto unlock; + } + + msc_buffer_unassign(msc); + msc->mbuf_priv = mbuf_priv; + msc->mbuf = mbuf; + } else { + msc_buffer_unassign(msc); + } + + msc->mode = i; + +unlock: + if (ret && mbuf) + msu_buffer_put(mbuf); mutex_unlock(&msc->buf_mutex); return ret ? ret : size; @@ -1667,7 +2021,12 @@ win_switch_store(struct device *dev, struct device_attribute *attr, return -EINVAL; mutex_lock(&msc->buf_mutex); - if (msc->mode != MSC_MODE_MULTI) + /* + * Window switch can only happen in the "multi" mode. + * If a external buffer is engaged, they have the full + * control over window switching. + */ + if (msc->mode != MSC_MODE_MULTI || msc->mbuf) ret = -ENOTSUPP; else msc_win_switch(msc); @@ -1720,10 +2079,7 @@ static int intel_th_msc_probe(struct intel_th_device *thdev) msc->reg_base = base + msc->index * 0x100; msc->msu_base = base; - err = intel_th_msu_init(msc); - if (err) - return err; - + INIT_WORK(&msc->work, msc_work); err = intel_th_msc_init(msc); if (err) return err; @@ -1739,7 +2095,6 @@ static void intel_th_msc_remove(struct intel_th_device *thdev) int ret; intel_th_msc_deactivate(thdev); - intel_th_msu_deinit(msc); /* * Buffers should not be used at this point except if the diff --git a/drivers/hwtracing/intel_th/msu.h b/drivers/hwtracing/intel_th/msu.h index 13d9b141daaa..e771f509bd02 100644 --- a/drivers/hwtracing/intel_th/msu.h +++ b/drivers/hwtracing/intel_th/msu.h @@ -44,14 +44,6 @@ enum { #define M0BLIE BIT(16) #define M1BLIE BIT(24) -/* MSC operating modes (MSC_MODE) */ -enum { - MSC_MODE_SINGLE = 0, - MSC_MODE_MULTI, - MSC_MODE_EXI, - MSC_MODE_DEBUG, -}; - /* MSCnSTS bits */ #define MSCSTS_WRAPSTAT BIT(1) /* Wrap occurred */ #define MSCSTS_PLE BIT(2) /* Pipeline Empty */ @@ -93,6 +85,16 @@ static inline unsigned long msc_data_sz(struct msc_block_desc *bdesc) return bdesc->valid_dw * 4 - MSC_BDESC; } +static inline unsigned long msc_total_sz(struct msc_block_desc *bdesc) +{ + return bdesc->valid_dw * 4; +} + +static inline unsigned long msc_block_sz(struct msc_block_desc *bdesc) +{ + return bdesc->block_sz * 64 - MSC_BDESC; +} + static inline bool msc_block_wrapped(struct msc_block_desc *bdesc) { if (bdesc->hw_tag & (MSC_HW_TAG_BLOCKWRAP | MSC_HW_TAG_WINWRAP)) @@ -104,7 +106,7 @@ static inline bool msc_block_wrapped(struct msc_block_desc *bdesc) static inline bool msc_block_last_written(struct msc_block_desc *bdesc) { if ((bdesc->hw_tag & MSC_HW_TAG_ENDBIT) || - (msc_data_sz(bdesc) != DATA_IN_PAGE)) + (msc_data_sz(bdesc) != msc_block_sz(bdesc))) return true; return false; |