From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753373AbcDZWLn (ORCPT ); Tue, 26 Apr 2016 18:11:43 -0400 Received: from mail-ig0-f178.google.com ([209.85.213.178]:37695 "EHLO mail-ig0-f178.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753110AbcDZWLJ (ORCPT ); Tue, 26 Apr 2016 18:11:09 -0400 From: Mathieu Poirier To: linux-arm-kernel@lists.infradead.org, Suzuki.Poulose@arm.com Cc: linux-kernel@vger.kernel.org Subject: [PATCH V4 16/18] coresight: tmc: implementing TMC-ETF AUX space API Date: Tue, 26 Apr 2016 16:10:32 -0600 Message-Id: <1461708634-6327-17-git-send-email-mathieu.poirier@linaro.org> X-Mailer: git-send-email 2.5.0 In-Reply-To: <1461708634-6327-1-git-send-email-mathieu.poirier@linaro.org> References: <1461708634-6327-1-git-send-email-mathieu.poirier@linaro.org> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org This patch implement the AUX area interfaces required to use the TMC (configured as an ETF) from the Perf sub-system. The heuristic is heavily borrowed from the ETB10 implementation. Signed-off-by: Mathieu Poirier --- drivers/hwtracing/coresight/coresight-tmc-etf.c | 198 ++++++++++++++++++++++++ drivers/hwtracing/coresight/coresight-tmc.h | 1 + 2 files changed, 199 insertions(+) diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c index ba3384781f71..f00867869d20 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etf.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c @@ -15,7 +15,9 @@ * this program. If not, see . */ +#include #include +#include #include #include "coresight-priv.h" #include "coresight-tmc.h" @@ -282,9 +284,205 @@ static void tmc_disable_etf_link(struct coresight_device *csdev, dev_info(drvdata->dev, "TMC disabled\n"); } +static void *tmc_alloc_etf_buffer(struct coresight_device *csdev, int cpu, + void **pages, int nr_pages, bool overwrite) +{ + int node; + struct cs_buffers *buf; + + if (cpu == -1) + cpu = smp_processor_id(); + node = cpu_to_node(cpu); + + /* Allocate memory structure for interaction with Perf */ + buf = kzalloc_node(sizeof(struct cs_buffers), GFP_KERNEL, node); + if (!buf) + return NULL; + + buf->snapshot = overwrite; + buf->nr_pages = nr_pages; + buf->data_pages = pages; + + return buf; +} + +static void tmc_free_etf_buffer(void *config) +{ + struct cs_buffers *buf = config; + + kfree(buf); +} + +static int tmc_set_etf_buffer(struct coresight_device *csdev, + struct perf_output_handle *handle, + void *sink_config) +{ + int ret = 0; + unsigned long head; + struct cs_buffers *buf = sink_config; + + /* wrap head around to the amount of space we have */ + head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1); + + /* find the page to write to */ + buf->cur = head / PAGE_SIZE; + + /* and offset within that page */ + buf->offset = head % PAGE_SIZE; + + local_set(&buf->data_size, 0); + + return ret; +} + +static unsigned long tmc_reset_etf_buffer(struct coresight_device *csdev, + struct perf_output_handle *handle, + void *sink_config, bool *lost) +{ + long size = 0; + struct cs_buffers *buf = sink_config; + + if (buf) { + /* + * In snapshot mode ->data_size holds the new address of the + * ring buffer's head. The size itself is the whole address + * range since we want the latest information. + */ + if (buf->snapshot) + handle->head = local_xchg(&buf->data_size, + buf->nr_pages << PAGE_SHIFT); + /* + * Tell the tracer PMU how much we got in this run and if + * something went wrong along the way. Nobody else can use + * this cs_buffers instance until we are done. As such + * resetting parameters here and squaring off with the ring + * buffer API in the tracer PMU is fine. + */ + *lost = !!local_xchg(&buf->lost, 0); + size = local_xchg(&buf->data_size, 0); + } + + return size; +} + +static void tmc_update_etf_buffer(struct coresight_device *csdev, + struct perf_output_handle *handle, + void *sink_config) +{ + int i, cur; + u32 *buf_ptr; + u32 read_ptr, write_ptr; + u32 status, to_read; + unsigned long offset; + struct cs_buffers *buf = sink_config; + struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + if (!buf) + return; + + /* This shouldn't happen */ + if (WARN_ON_ONCE(local_read(&drvdata->mode) != CS_MODE_PERF)) + return; + + CS_UNLOCK(drvdata->base); + + tmc_flush_and_stop(drvdata); + + read_ptr = readl_relaxed(drvdata->base + TMC_RRP); + write_ptr = readl_relaxed(drvdata->base + TMC_RWP); + + /* + * Get a hold of the status register and see if a wrap around + * has occurred. If so adjust things accordingly. + */ + status = readl_relaxed(drvdata->base + TMC_STS); + if (status & TMC_STS_FULL) { + local_inc(&buf->lost); + to_read = drvdata->size; + } else { + to_read = CIRC_CNT(write_ptr, read_ptr, drvdata->size); + } + + /* + * The TMC RAM buffer may be bigger than the space available in the + * perf ring buffer (handle->size). If so advance the RRP so that we + * get the latest trace data. + */ + if (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, 5); + break; + case TMC_MEM_INTF_WIDTH_256BITS: + mask = GENMASK(31, 6); + break; + } + + /* + * Make sure the new size is aligned in accordance with the + * requirement explained above. + */ + to_read = handle->size & mask; + /* Move the RAM read pointer up */ + read_ptr = (write_ptr + drvdata->size) - to_read; + /* Make sure we are still within our limits */ + read_ptr &= ~(drvdata->size - 1); + /* Tell the HW */ + writel_relaxed(read_ptr, drvdata->base + TMC_RRP); + local_inc(&buf->lost); + } + + cur = buf->cur; + offset = buf->offset; + + /* for every byte to read */ + for (i = 0; i < to_read; i += 4) { + buf_ptr = buf->data_pages[cur] + offset; + *buf_ptr = readl_relaxed(drvdata->base + TMC_RRD); + + offset += 4; + if (offset >= PAGE_SIZE) { + offset = 0; + cur++; + /* wrap around at the end of the buffer */ + cur &= buf->nr_pages - 1; + } + } + + /* + * In snapshot mode all we have to do is communicate to + * perf_aux_output_end() the address of the current head. In full + * trace mode the same function expects a size to move rb->aux_head + * forward. + */ + if (buf->snapshot) + local_set(&buf->data_size, (cur * PAGE_SIZE) + offset); + else + local_add(to_read, &buf->data_size); + + CS_LOCK(drvdata->base); +} + static const struct coresight_ops_sink tmc_etf_sink_ops = { .enable = tmc_enable_etf_sink, .disable = tmc_disable_etf_sink, + .alloc_buffer = tmc_alloc_etf_buffer, + .free_buffer = tmc_free_etf_buffer, + .set_buffer = tmc_set_etf_buffer, + .reset_buffer = tmc_reset_etf_buffer, + .update_buffer = tmc_update_etf_buffer, }; static const struct coresight_ops_link tmc_etf_link_ops = { diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h index c5d06fd57fa8..5c5fe2ad2ca7 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.h +++ b/drivers/hwtracing/coresight/coresight-tmc.h @@ -52,6 +52,7 @@ #define TMC_CTL_CAPT_EN BIT(0) /* TMC_STS - 0x00C */ #define TMC_STS_TMCREADY_BIT 2 +#define TMC_STS_FULL BIT(0) #define TMC_STS_TRIGGERED BIT(1) /* TMC_AXICTL - 0x110 */ #define TMC_AXICTL_PROT_CTL_B0 BIT(0) -- 2.5.0 From mboxrd@z Thu Jan 1 00:00:00 1970 From: mathieu.poirier@linaro.org (Mathieu Poirier) Date: Tue, 26 Apr 2016 16:10:32 -0600 Subject: [PATCH V4 16/18] coresight: tmc: implementing TMC-ETF AUX space API In-Reply-To: <1461708634-6327-1-git-send-email-mathieu.poirier@linaro.org> References: <1461708634-6327-1-git-send-email-mathieu.poirier@linaro.org> Message-ID: <1461708634-6327-17-git-send-email-mathieu.poirier@linaro.org> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org This patch implement the AUX area interfaces required to use the TMC (configured as an ETF) from the Perf sub-system. The heuristic is heavily borrowed from the ETB10 implementation. Signed-off-by: Mathieu Poirier --- drivers/hwtracing/coresight/coresight-tmc-etf.c | 198 ++++++++++++++++++++++++ drivers/hwtracing/coresight/coresight-tmc.h | 1 + 2 files changed, 199 insertions(+) diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c index ba3384781f71..f00867869d20 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etf.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c @@ -15,7 +15,9 @@ * this program. If not, see . */ +#include #include +#include #include #include "coresight-priv.h" #include "coresight-tmc.h" @@ -282,9 +284,205 @@ static void tmc_disable_etf_link(struct coresight_device *csdev, dev_info(drvdata->dev, "TMC disabled\n"); } +static void *tmc_alloc_etf_buffer(struct coresight_device *csdev, int cpu, + void **pages, int nr_pages, bool overwrite) +{ + int node; + struct cs_buffers *buf; + + if (cpu == -1) + cpu = smp_processor_id(); + node = cpu_to_node(cpu); + + /* Allocate memory structure for interaction with Perf */ + buf = kzalloc_node(sizeof(struct cs_buffers), GFP_KERNEL, node); + if (!buf) + return NULL; + + buf->snapshot = overwrite; + buf->nr_pages = nr_pages; + buf->data_pages = pages; + + return buf; +} + +static void tmc_free_etf_buffer(void *config) +{ + struct cs_buffers *buf = config; + + kfree(buf); +} + +static int tmc_set_etf_buffer(struct coresight_device *csdev, + struct perf_output_handle *handle, + void *sink_config) +{ + int ret = 0; + unsigned long head; + struct cs_buffers *buf = sink_config; + + /* wrap head around to the amount of space we have */ + head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1); + + /* find the page to write to */ + buf->cur = head / PAGE_SIZE; + + /* and offset within that page */ + buf->offset = head % PAGE_SIZE; + + local_set(&buf->data_size, 0); + + return ret; +} + +static unsigned long tmc_reset_etf_buffer(struct coresight_device *csdev, + struct perf_output_handle *handle, + void *sink_config, bool *lost) +{ + long size = 0; + struct cs_buffers *buf = sink_config; + + if (buf) { + /* + * In snapshot mode ->data_size holds the new address of the + * ring buffer's head. The size itself is the whole address + * range since we want the latest information. + */ + if (buf->snapshot) + handle->head = local_xchg(&buf->data_size, + buf->nr_pages << PAGE_SHIFT); + /* + * Tell the tracer PMU how much we got in this run and if + * something went wrong along the way. Nobody else can use + * this cs_buffers instance until we are done. As such + * resetting parameters here and squaring off with the ring + * buffer API in the tracer PMU is fine. + */ + *lost = !!local_xchg(&buf->lost, 0); + size = local_xchg(&buf->data_size, 0); + } + + return size; +} + +static void tmc_update_etf_buffer(struct coresight_device *csdev, + struct perf_output_handle *handle, + void *sink_config) +{ + int i, cur; + u32 *buf_ptr; + u32 read_ptr, write_ptr; + u32 status, to_read; + unsigned long offset; + struct cs_buffers *buf = sink_config; + struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + if (!buf) + return; + + /* This shouldn't happen */ + if (WARN_ON_ONCE(local_read(&drvdata->mode) != CS_MODE_PERF)) + return; + + CS_UNLOCK(drvdata->base); + + tmc_flush_and_stop(drvdata); + + read_ptr = readl_relaxed(drvdata->base + TMC_RRP); + write_ptr = readl_relaxed(drvdata->base + TMC_RWP); + + /* + * Get a hold of the status register and see if a wrap around + * has occurred. If so adjust things accordingly. + */ + status = readl_relaxed(drvdata->base + TMC_STS); + if (status & TMC_STS_FULL) { + local_inc(&buf->lost); + to_read = drvdata->size; + } else { + to_read = CIRC_CNT(write_ptr, read_ptr, drvdata->size); + } + + /* + * The TMC RAM buffer may be bigger than the space available in the + * perf ring buffer (handle->size). If so advance the RRP so that we + * get the latest trace data. + */ + if (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, 5); + break; + case TMC_MEM_INTF_WIDTH_256BITS: + mask = GENMASK(31, 6); + break; + } + + /* + * Make sure the new size is aligned in accordance with the + * requirement explained above. + */ + to_read = handle->size & mask; + /* Move the RAM read pointer up */ + read_ptr = (write_ptr + drvdata->size) - to_read; + /* Make sure we are still within our limits */ + read_ptr &= ~(drvdata->size - 1); + /* Tell the HW */ + writel_relaxed(read_ptr, drvdata->base + TMC_RRP); + local_inc(&buf->lost); + } + + cur = buf->cur; + offset = buf->offset; + + /* for every byte to read */ + for (i = 0; i < to_read; i += 4) { + buf_ptr = buf->data_pages[cur] + offset; + *buf_ptr = readl_relaxed(drvdata->base + TMC_RRD); + + offset += 4; + if (offset >= PAGE_SIZE) { + offset = 0; + cur++; + /* wrap around at the end of the buffer */ + cur &= buf->nr_pages - 1; + } + } + + /* + * In snapshot mode all we have to do is communicate to + * perf_aux_output_end() the address of the current head. In full + * trace mode the same function expects a size to move rb->aux_head + * forward. + */ + if (buf->snapshot) + local_set(&buf->data_size, (cur * PAGE_SIZE) + offset); + else + local_add(to_read, &buf->data_size); + + CS_LOCK(drvdata->base); +} + static const struct coresight_ops_sink tmc_etf_sink_ops = { .enable = tmc_enable_etf_sink, .disable = tmc_disable_etf_sink, + .alloc_buffer = tmc_alloc_etf_buffer, + .free_buffer = tmc_free_etf_buffer, + .set_buffer = tmc_set_etf_buffer, + .reset_buffer = tmc_reset_etf_buffer, + .update_buffer = tmc_update_etf_buffer, }; static const struct coresight_ops_link tmc_etf_link_ops = { diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h index c5d06fd57fa8..5c5fe2ad2ca7 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.h +++ b/drivers/hwtracing/coresight/coresight-tmc.h @@ -52,6 +52,7 @@ #define TMC_CTL_CAPT_EN BIT(0) /* TMC_STS - 0x00C */ #define TMC_STS_TMCREADY_BIT 2 +#define TMC_STS_FULL BIT(0) #define TMC_STS_TRIGGERED BIT(1) /* TMC_AXICTL - 0x110 */ #define TMC_AXICTL_PROT_CTL_B0 BIT(0) -- 2.5.0