CoreSight January 2022

coresight@lists.linaro.org

8 participants
47 discussions

Re: [PATCH] coresight: syscfg: Fix memleak on registration failure in cscfg_create_device

by Mathieu Poirier

Good morning, On Mon, Jan 10, 2022 at 07:31:00AM +0000, Miaoqian Lin wrote: > device_register() calls device_initialize(), > according to doc of device_initialize: > > Use put_device() to give up your reference instead of freeing > * @dev directly once you have called this function. That is _if_ device_initialize() is called manually. In this instance @dev is registered with device_register() and unregistered with device_unregister(). The latter conforms to the comment you pointed out and calls put_device() as expected. Thanks, Mathieu > > To prevent potential memleak, use put_device() instead call kfree > directly. > > Signed-off-by: Miaoqian Lin <linmq006(a)gmail.com> > --- > drivers/hwtracing/coresight/coresight-syscfg.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/hwtracing/coresight/coresight-syscfg.c b/drivers/hwtracing/coresight/coresight-syscfg.c > index 43054568430f..007fa1c761a7 100644 > --- a/drivers/hwtracing/coresight/coresight-syscfg.c > +++ b/drivers/hwtracing/coresight/coresight-syscfg.c > @@ -764,7 +764,7 @@ struct device *cscfg_device(void) > /* Must have a release function or the kernel will complain on module unload */ > static void cscfg_dev_release(struct device *dev) > { > - kfree(cscfg_mgr); > + put_device(dev); > cscfg_mgr = NULL; > } > > -- > 2.17.1 >

2 years, 7 months

Re: [RESEND PATCH v2] coresight: change tmc from misc device to cdev device

by Mathieu Poirier

On Thu, 13 Jan 2022 at 20:16, Jiankang Chen <jkchen(a)linux.alibaba.com> wrote: > > Hi Mathieu > > 在 2022/1/14 00:56, Mathieu Poirier 写道: > > On Wed, 12 Jan 2022 at 23:12, Jay Chen <jkchen(a)linux.alibaba.com> wrote: > >> Currently, there are 130 etr and etf on our machine, > >> but the current coresight tmc driver uses misc_register > >> to register the device, which leads to the error that > >> the device number is not enough. > >> > >> coresight-tmc: probe of xxxxx failed with error -16 > >> > >> This patch changes the device registration method > >> to cdev's dynamic registration method to solve the > >> problem of insufficient device numbers. > > On December 21st you posted this patch with a "RFC V3 PATCH" tag. On > > January 5th you posted a new version with a simple "PATCH" tag which, > > minutes later, was superseded by another patch labelled "RESEND > > PATCH". Today you're sending yet another revision labelled "RESEND > > PATCH V2"... > > > > Is it a "V2" of the "RESEND PATCH" that was a new revision of the "RFC > > V3 PATCH"? Are you confused? I certainly am... > > > this patch v2 is a new version，and it fix some bugs; > How can it be a V2 when a V3 has already been published? I will not review this patch, and even less apply it, until it is properly labelled. > sorry > > jay > > >> Signed-off-by: Jay Chen <jkchen(a)linux.alibaba.com> > >> --- > >> .../hwtracing/coresight/coresight-tmc-core.c | 103 ++++++++++++++---- > >> drivers/hwtracing/coresight/coresight-tmc.h | 11 +- > >> 2 files changed, 91 insertions(+), 23 deletions(-) > >> > >> diff --git a/drivers/hwtracing/coresight/coresight-tmc-core.c b/drivers/hwtracing/coresight/coresight-tmc-core.c > >> index d0276af82494..0977f1ce6338 100644 > >> --- a/drivers/hwtracing/coresight/coresight-tmc-core.c > >> +++ b/drivers/hwtracing/coresight/coresight-tmc-core.c > >> @@ -12,7 +12,6 @@ > >> #include <linux/io.h> > >> #include <linux/err.h> > >> #include <linux/fs.h> > >> -#include <linux/miscdevice.h> > >> #include <linux/mutex.h> > >> #include <linux/property.h> > >> #include <linux/uaccess.h> > >> @@ -31,6 +30,12 @@ DEFINE_CORESIGHT_DEVLIST(etb_devs, "tmc_etb"); > >> DEFINE_CORESIGHT_DEVLIST(etf_devs, "tmc_etf"); > >> DEFINE_CORESIGHT_DEVLIST(etr_devs, "tmc_etr"); > >> > >> +static DEFINE_IDA(tmc_ida); > >> +static dev_t tmc_major; > >> +static struct class *tmc_class; > >> + > >> +#define TMC_DEV_MAX (MINORMASK + 1) > >> + > >> void tmc_wait_for_tmcready(struct tmc_drvdata *drvdata) > >> { > >> struct coresight_device *csdev = drvdata->csdev; > >> @@ -146,8 +151,10 @@ static int tmc_read_unprepare(struct tmc_drvdata *drvdata) > >> static int tmc_open(struct inode *inode, struct file *file) > >> { > >> int ret; > >> - struct tmc_drvdata *drvdata = container_of(file->private_data, > >> - struct tmc_drvdata, miscdev); > >> + struct tmc_cdev *cdev = container_of(inode->i_cdev, > >> + struct tmc_cdev, cdev); > >> + struct tmc_drvdata *drvdata = container_of(cdev, > >> + struct tmc_drvdata, cdev); > >> > >> ret = tmc_read_prepare(drvdata); > >> if (ret) > >> @@ -178,8 +185,10 @@ static ssize_t tmc_read(struct file *file, char __user *data, size_t len, > >> { > >> char *bufp; > >> ssize_t actual; > >> - struct tmc_drvdata *drvdata = container_of(file->private_data, > >> - struct tmc_drvdata, miscdev); > >> + struct tmc_cdev *cdev = container_of(file->f_inode->i_cdev, > >> + struct tmc_cdev, cdev); > >> + struct tmc_drvdata *drvdata = container_of(cdev, > >> + struct tmc_drvdata, cdev); > >> actual = tmc_get_sysfs_trace(drvdata, *ppos, len, &bufp); > >> if (actual <= 0) > >> return 0; > >> @@ -199,8 +208,10 @@ static ssize_t tmc_read(struct file *file, char __user *data, size_t len, > >> static int tmc_release(struct inode *inode, struct file *file) > >> { > >> int ret; > >> - struct tmc_drvdata *drvdata = container_of(file->private_data, > >> - struct tmc_drvdata, miscdev); > >> + struct tmc_cdev *cdev = container_of(inode->i_cdev, > >> + struct tmc_cdev, cdev); > >> + struct tmc_drvdata *drvdata = container_of(cdev, > >> + struct tmc_drvdata, cdev); > >> > >> ret = tmc_read_unprepare(drvdata); > >> if (ret) > >> @@ -451,6 +462,7 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id) > >> { > >> int ret = 0; > >> u32 devid; > >> + dev_t devt; > >> void __iomem *base; > >> struct device *dev = &adev->dev; > >> struct coresight_platform_data *pdata = NULL; > >> @@ -546,14 +558,32 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id) > >> goto out; > >> } > >> > >> - drvdata->miscdev.name = desc.name; > >> - drvdata->miscdev.minor = MISC_DYNAMIC_MINOR; > >> - drvdata->miscdev.fops = &tmc_fops; > >> - ret = misc_register(&drvdata->miscdev); > >> + ret = ida_simple_get(&tmc_ida, 0, TMC_DEV_MAX, GFP_KERNEL); > >> + if (ret < 0) > >> + goto err_coresight_unregister; > >> + > >> + cdev_init(&drvdata->cdev.cdev, &tmc_fops); > >> + drvdata->cdev.cdev.owner = THIS_MODULE; > >> + devt = MKDEV(MAJOR(tmc_major), ret); > >> + ret = cdev_add(&drvdata->cdev.cdev, devt, 1); > >> if (ret) > >> - coresight_unregister(drvdata->csdev); > >> - else > >> + goto err_free_tmc_ida; > >> + > >> + drvdata->cdev.dev = device_create(tmc_class, NULL, devt, &drvdata->cdev, desc.name); > >> + if (IS_ERR(drvdata->cdev.dev)) { > >> + ret = PTR_ERR(drvdata->cdev.dev); > >> + goto err_delete_cdev; > >> + } else > >> pm_runtime_put(&adev->dev); > >> + > >> + return 0; > >> + > >> +err_delete_cdev: > >> + cdev_del(&drvdata->cdev.cdev); > >> +err_free_tmc_ida: > >> + ida_simple_remove(&tmc_ida, MINOR(devt)); > >> +err_coresight_unregister: > >> + coresight_unregister(drvdata->csdev); > >> out: > >> return ret; > >> } > >> @@ -583,13 +613,11 @@ static void tmc_shutdown(struct amba_device *adev) > >> static void tmc_remove(struct amba_device *adev) > >> { > >> struct tmc_drvdata *drvdata = dev_get_drvdata(&adev->dev); > >> + struct device *dev = drvdata->cdev.dev; > >> > >> - /* > >> - * Since misc_open() holds a refcount on the f_ops, which is > >> - * etb fops in this case, device is there until last file > >> - * handler to this device is closed. > >> - */ > >> - misc_deregister(&drvdata->miscdev); > >> + ida_simple_remove(&tmc_ida, MINOR(dev->devt)); > >> + device_destroy(tmc_class, dev->devt); > >> + cdev_del(&drvdata->cdev.cdev); > >> coresight_unregister(drvdata->csdev); > >> } > >> > >> @@ -618,7 +646,42 @@ static struct amba_driver tmc_driver = { > >> .id_table = tmc_ids, > >> }; > >> > >> -module_amba_driver(tmc_driver); > >> +static int __init tmc_init(void) > >> +{ > >> + int ret; > >> + > >> + ret = alloc_chrdev_region(&tmc_major, 0, TMC_DEV_MAX, "tmc"); > >> + if (ret < 0) { > >> + pr_err("tmc: failed to allocate char dev region\n"); > >> + return ret; > >> + } > >> + > >> + tmc_class = class_create(THIS_MODULE, "tmc"); > >> + if (IS_ERR(tmc_class)) { > >> + pr_err("tmc: failed to create class\n"); > >> + unregister_chrdev_region(tmc_major, TMC_DEV_MAX); > >> + return PTR_ERR(tmc_class); > >> + } > >> + > >> + ret = amba_driver_register(&tmc_driver); > >> + if (ret) { > >> + pr_err("tmc: error registering amba driver\n"); > >> + class_destroy(tmc_class); > >> + unregister_chrdev_region(tmc_major, TMC_DEV_MAX); > >> + } > >> + > >> + return ret; > >> +} > >> + > >> +static void __exit tmc_exit(void) > >> +{ > >> + amba_driver_unregister(&tmc_driver); > >> + class_destroy(tmc_class); > >> + unregister_chrdev_region(tmc_major, TMC_DEV_MAX); > >> +} > >> + > >> +module_init(tmc_init); > >> +module_exit(tmc_exit); > >> > >> MODULE_AUTHOR("Pratik Patel <pratikp(a)codeaurora.org>"); > >> MODULE_DESCRIPTION("Arm CoreSight Trace Memory Controller driver"); > >> diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h > >> index 6bec20a392b3..11441c6b9c26 100644 > >> --- a/drivers/hwtracing/coresight/coresight-tmc.h > >> +++ b/drivers/hwtracing/coresight/coresight-tmc.h > >> @@ -7,9 +7,9 @@ > >> #ifndef _CORESIGHT_TMC_H > >> #define _CORESIGHT_TMC_H > >> > >> +#include <linux/cdev.h> > >> #include <linux/dma-mapping.h> > >> #include <linux/idr.h> > >> -#include <linux/miscdevice.h> > >> #include <linux/mutex.h> > >> #include <linux/refcount.h> > >> > >> @@ -163,11 +163,16 @@ struct etr_buf { > >> void *private; > >> }; > >> > >> +struct tmc_cdev { > >> + struct cdev cdev; > >> + struct device *dev; > >> +}; > >> + > >> /** > >> * struct tmc_drvdata - specifics associated to an TMC component > >> * @base: memory mapped base address for this component. > >> * @csdev: component vitals needed by the framework. > >> - * @miscdev: specifics to handle "/dev/xyz.tmc" entry. > >> + * @tmc_cdev: specifics to handle "/dev/xyz.tmc" entry. > >> * @spinlock: only one at a time pls. > >> * @pid: Process ID of the process being monitored by the session > >> * that is using this component. > >> @@ -191,7 +196,7 @@ struct etr_buf { > >> struct tmc_drvdata { > >> void __iomem *base; > >> struct coresight_device *csdev; > >> - struct miscdevice miscdev; > >> + struct tmc_cdev cdev; > >> spinlock_t spinlock; > >> pid_t pid; > >> bool reading; > >> -- > >> 2.27.0 > >>

2 years, 7 months

Re: [RESEND PATCH v2] coresight: change tmc from misc device to cdev device

by Mathieu Poirier

On Wed, 12 Jan 2022 at 23:12, Jay Chen <jkchen(a)linux.alibaba.com> wrote: > > Currently, there are 130 etr and etf on our machine, > but the current coresight tmc driver uses misc_register > to register the device, which leads to the error that > the device number is not enough. > > coresight-tmc: probe of xxxxx failed with error -16 > > This patch changes the device registration method > to cdev's dynamic registration method to solve the > problem of insufficient device numbers. On December 21st you posted this patch with a "RFC V3 PATCH" tag. On January 5th you posted a new version with a simple "PATCH" tag which, minutes later, was superseded by another patch labelled "RESEND PATCH". Today you're sending yet another revision labelled "RESEND PATCH V2"... Is it a "V2" of the "RESEND PATCH" that was a new revision of the "RFC V3 PATCH"? Are you confused? I certainly am... > > Signed-off-by: Jay Chen <jkchen(a)linux.alibaba.com> > --- > .../hwtracing/coresight/coresight-tmc-core.c | 103 ++++++++++++++---- > drivers/hwtracing/coresight/coresight-tmc.h | 11 +- > 2 files changed, 91 insertions(+), 23 deletions(-) > > diff --git a/drivers/hwtracing/coresight/coresight-tmc-core.c b/drivers/hwtracing/coresight/coresight-tmc-core.c > index d0276af82494..0977f1ce6338 100644 > --- a/drivers/hwtracing/coresight/coresight-tmc-core.c > +++ b/drivers/hwtracing/coresight/coresight-tmc-core.c > @@ -12,7 +12,6 @@ > #include <linux/io.h> > #include <linux/err.h> > #include <linux/fs.h> > -#include <linux/miscdevice.h> > #include <linux/mutex.h> > #include <linux/property.h> > #include <linux/uaccess.h> > @@ -31,6 +30,12 @@ DEFINE_CORESIGHT_DEVLIST(etb_devs, "tmc_etb"); > DEFINE_CORESIGHT_DEVLIST(etf_devs, "tmc_etf"); > DEFINE_CORESIGHT_DEVLIST(etr_devs, "tmc_etr"); > > +static DEFINE_IDA(tmc_ida); > +static dev_t tmc_major; > +static struct class *tmc_class; > + > +#define TMC_DEV_MAX (MINORMASK + 1) > + > void tmc_wait_for_tmcready(struct tmc_drvdata *drvdata) > { > struct coresight_device *csdev = drvdata->csdev; > @@ -146,8 +151,10 @@ static int tmc_read_unprepare(struct tmc_drvdata *drvdata) > static int tmc_open(struct inode *inode, struct file *file) > { > int ret; > - struct tmc_drvdata *drvdata = container_of(file->private_data, > - struct tmc_drvdata, miscdev); > + struct tmc_cdev *cdev = container_of(inode->i_cdev, > + struct tmc_cdev, cdev); > + struct tmc_drvdata *drvdata = container_of(cdev, > + struct tmc_drvdata, cdev); > > ret = tmc_read_prepare(drvdata); > if (ret) > @@ -178,8 +185,10 @@ static ssize_t tmc_read(struct file *file, char __user *data, size_t len, > { > char *bufp; > ssize_t actual; > - struct tmc_drvdata *drvdata = container_of(file->private_data, > - struct tmc_drvdata, miscdev); > + struct tmc_cdev *cdev = container_of(file->f_inode->i_cdev, > + struct tmc_cdev, cdev); > + struct tmc_drvdata *drvdata = container_of(cdev, > + struct tmc_drvdata, cdev); > actual = tmc_get_sysfs_trace(drvdata, *ppos, len, &bufp); > if (actual <= 0) > return 0; > @@ -199,8 +208,10 @@ static ssize_t tmc_read(struct file *file, char __user *data, size_t len, > static int tmc_release(struct inode *inode, struct file *file) > { > int ret; > - struct tmc_drvdata *drvdata = container_of(file->private_data, > - struct tmc_drvdata, miscdev); > + struct tmc_cdev *cdev = container_of(inode->i_cdev, > + struct tmc_cdev, cdev); > + struct tmc_drvdata *drvdata = container_of(cdev, > + struct tmc_drvdata, cdev); > > ret = tmc_read_unprepare(drvdata); > if (ret) > @@ -451,6 +462,7 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id) > { > int ret = 0; > u32 devid; > + dev_t devt; > void __iomem *base; > struct device *dev = &adev->dev; > struct coresight_platform_data *pdata = NULL; > @@ -546,14 +558,32 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id) > goto out; > } > > - drvdata->miscdev.name = desc.name; > - drvdata->miscdev.minor = MISC_DYNAMIC_MINOR; > - drvdata->miscdev.fops = &tmc_fops; > - ret = misc_register(&drvdata->miscdev); > + ret = ida_simple_get(&tmc_ida, 0, TMC_DEV_MAX, GFP_KERNEL); > + if (ret < 0) > + goto err_coresight_unregister; > + > + cdev_init(&drvdata->cdev.cdev, &tmc_fops); > + drvdata->cdev.cdev.owner = THIS_MODULE; > + devt = MKDEV(MAJOR(tmc_major), ret); > + ret = cdev_add(&drvdata->cdev.cdev, devt, 1); > if (ret) > - coresight_unregister(drvdata->csdev); > - else > + goto err_free_tmc_ida; > + > + drvdata->cdev.dev = device_create(tmc_class, NULL, devt, &drvdata->cdev, desc.name); > + if (IS_ERR(drvdata->cdev.dev)) { > + ret = PTR_ERR(drvdata->cdev.dev); > + goto err_delete_cdev; > + } else > pm_runtime_put(&adev->dev); > + > + return 0; > + > +err_delete_cdev: > + cdev_del(&drvdata->cdev.cdev); > +err_free_tmc_ida: > + ida_simple_remove(&tmc_ida, MINOR(devt)); > +err_coresight_unregister: > + coresight_unregister(drvdata->csdev); > out: > return ret; > } > @@ -583,13 +613,11 @@ static void tmc_shutdown(struct amba_device *adev) > static void tmc_remove(struct amba_device *adev) > { > struct tmc_drvdata *drvdata = dev_get_drvdata(&adev->dev); > + struct device *dev = drvdata->cdev.dev; > > - /* > - * Since misc_open() holds a refcount on the f_ops, which is > - * etb fops in this case, device is there until last file > - * handler to this device is closed. > - */ > - misc_deregister(&drvdata->miscdev); > + ida_simple_remove(&tmc_ida, MINOR(dev->devt)); > + device_destroy(tmc_class, dev->devt); > + cdev_del(&drvdata->cdev.cdev); > coresight_unregister(drvdata->csdev); > } > > @@ -618,7 +646,42 @@ static struct amba_driver tmc_driver = { > .id_table = tmc_ids, > }; > > -module_amba_driver(tmc_driver); > +static int __init tmc_init(void) > +{ > + int ret; > + > + ret = alloc_chrdev_region(&tmc_major, 0, TMC_DEV_MAX, "tmc"); > + if (ret < 0) { > + pr_err("tmc: failed to allocate char dev region\n"); > + return ret; > + } > + > + tmc_class = class_create(THIS_MODULE, "tmc"); > + if (IS_ERR(tmc_class)) { > + pr_err("tmc: failed to create class\n"); > + unregister_chrdev_region(tmc_major, TMC_DEV_MAX); > + return PTR_ERR(tmc_class); > + } > + > + ret = amba_driver_register(&tmc_driver); > + if (ret) { > + pr_err("tmc: error registering amba driver\n"); > + class_destroy(tmc_class); > + unregister_chrdev_region(tmc_major, TMC_DEV_MAX); > + } > + > + return ret; > +} > + > +static void __exit tmc_exit(void) > +{ > + amba_driver_unregister(&tmc_driver); > + class_destroy(tmc_class); > + unregister_chrdev_region(tmc_major, TMC_DEV_MAX); > +} > + > +module_init(tmc_init); > +module_exit(tmc_exit); > > MODULE_AUTHOR("Pratik Patel <pratikp(a)codeaurora.org>"); > MODULE_DESCRIPTION("Arm CoreSight Trace Memory Controller driver"); > diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h > index 6bec20a392b3..11441c6b9c26 100644 > --- a/drivers/hwtracing/coresight/coresight-tmc.h > +++ b/drivers/hwtracing/coresight/coresight-tmc.h > @@ -7,9 +7,9 @@ > #ifndef _CORESIGHT_TMC_H > #define _CORESIGHT_TMC_H > > +#include <linux/cdev.h> > #include <linux/dma-mapping.h> > #include <linux/idr.h> > -#include <linux/miscdevice.h> > #include <linux/mutex.h> > #include <linux/refcount.h> > > @@ -163,11 +163,16 @@ struct etr_buf { > void *private; > }; > > +struct tmc_cdev { > + struct cdev cdev; > + struct device *dev; > +}; > + > /** > * struct tmc_drvdata - specifics associated to an TMC component > * @base: memory mapped base address for this component. > * @csdev: component vitals needed by the framework. > - * @miscdev: specifics to handle "/dev/xyz.tmc" entry. > + * @tmc_cdev: specifics to handle "/dev/xyz.tmc" entry. > * @spinlock: only one at a time pls. > * @pid: Process ID of the process being monitored by the session > * that is using this component. > @@ -191,7 +196,7 @@ struct etr_buf { > struct tmc_drvdata { > void __iomem *base; > struct coresight_device *csdev; > - struct miscdevice miscdev; > + struct tmc_cdev cdev; > spinlock_t spinlock; > pid_t pid; > bool reading; > -- > 2.27.0 >

2 years, 7 months

[PATCH 1/3] coresight: Add config flag to enable branch broadcast

by James Clark

When enabled, all taken branch addresses are output, even if the branch was because of a direct branch instruction. This enables reconstruction of the program flow without having access to the memory image of the code being executed. Use bit 8 for the config option which would be the correct bit for programming ETMv3. Although branch broadcast can't be enabled on ETMv3 because it's not in the define ETM3X_SUPPORTED_OPTIONS, using the correct bit might help prevent future collisions or allow it to be enabled if needed. Signed-off-by: James Clark <james.clark(a)arm.com> --- drivers/hwtracing/coresight/coresight-etm-perf.c | 2 ++ drivers/hwtracing/coresight/coresight-etm4x-core.c | 9 +++++++++ include/linux/coresight-pmu.h | 2 ++ 3 files changed, 13 insertions(+) diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index c039b6ae206f..43bbd5dc3d3b 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -52,6 +52,7 @@ static DEFINE_PER_CPU(struct coresight_device *, csdev_src); * The PMU formats were orignally for ETMv3.5/PTM's ETMCR 'config'; * now take them as general formats and apply on all ETMs. */ +PMU_FORMAT_ATTR(branch_broadcast, "config:"__stringify(ETM_OPT_BRANCH_BROADCAST)); PMU_FORMAT_ATTR(cycacc, "config:" __stringify(ETM_OPT_CYCACC)); /* contextid1 enables tracing CONTEXTIDR_EL1 for ETMv4 */ PMU_FORMAT_ATTR(contextid1, "config:" __stringify(ETM_OPT_CTXTID)); @@ -97,6 +98,7 @@ static struct attribute *etm_config_formats_attr[] = { &format_attr_sinkid.attr, &format_attr_preset.attr, &format_attr_configid.attr, + &format_attr_branch_broadcast.attr, NULL, }; diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index bf18128cf5de..d2bafb50c66a 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -692,6 +692,15 @@ static int etm4_parse_event_config(struct coresight_device *csdev, ret = cscfg_csdev_enable_active_config(csdev, cfg_hash, preset); } + /* branch broadcast - enable if selected and supported */ + if (attr->config & BIT(ETM_OPT_BRANCH_BROADCAST)) { + if (!drvdata->trcbb) { + ret = -EINVAL; + goto out; + } else + config->cfg |= BIT(ETM4_CFG_BIT_BB); + } + out: return ret; } diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h index 4ac5c081af93..6c2fd6cc5a98 100644 --- a/include/linux/coresight-pmu.h +++ b/include/linux/coresight-pmu.h @@ -18,6 +18,7 @@ * ETMv3.5/PTM doesn't define ETMCR config bits with prefix "ETM3_" and * directly use below macros as config bits. */ +#define ETM_OPT_BRANCH_BROADCAST 8 #define ETM_OPT_CYCACC 12 #define ETM_OPT_CTXTID 14 #define ETM_OPT_CTXTID2 15 @@ -25,6 +26,7 @@ #define ETM_OPT_RETSTK 29 /* ETMv4 CONFIGR programming bits for the ETM OPTs */ +#define ETM4_CFG_BIT_BB 3 #define ETM4_CFG_BIT_CYCACC 4 #define ETM4_CFG_BIT_CTXTID 6 #define ETM4_CFG_BIT_VMID 7 -- 2.28.0

2 years, 7 months

Re: [PATCH v4 48/48] perf cpumap: Give CPUs their own type.

by Arnaldo Carvalho de Melo

Em Tue, Jan 11, 2022 at 11:16:16AM -0800, Ian Rogers escreveu: > On Mon, Jan 10, 2022 at 11:50 AM Arnaldo Carvalho de Melo > <acme(a)kernel.org> wrote: > > > > Em Tue, Jan 04, 2022 at 10:13:51PM -0800, Ian Rogers escreveu: > > > A common problem is confusing CPU map indices with the CPU, by wrapping > > > the CPU with a struct then this is avoided. This approach is similar to > > > atomic_t. > > > > This one needed this to build with BUILD_BPF_SKEL=1, please check, I'll > > soon push this to tmp.perf/perf_cpu so that you can take a look and test > > it. > > > Thanks Arnaldo, I did eye-ball one issue where cpu_map__default_new's > behavior would be impacted (nr would be 1 rather than nr_cpus). The > fix is: > > --- a/tools/lib/perf/cpumap.c > +++ b/tools/lib/perf/cpumap.c > @@ -18,7 +18,7 @@ static struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus) > if (!cpus) > return NULL; > > - cpus->nr = 1; > + cpus->nr = nr_cpus; > refcount_set(&cpus->refcnt, 1); > return cpus; > } > Could you add that into this patch as well? Sure. I´m now running perf-test after each of those csets, so far so good. > Thanks, > Ian > > > > - Arnaldo > > > > diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c > > index 80d1a3a31052fe55..328479df5e16a638 100644 > > --- a/tools/perf/util/bpf_counter.c > > +++ b/tools/perf/util/bpf_counter.c > > @@ -540,7 +540,7 @@ static int bperf__load(struct evsel *evsel, struct target *target) > > filter_type == BPERF_FILTER_TGID) > > key = evsel->core.threads->map[i].pid; > > else if (filter_type == BPERF_FILTER_CPU) > > - key = evsel->core.cpus->map[i]; > > + key = evsel->core.cpus->map[i].cpu; > > else > > break; > > > > @@ -584,7 +584,7 @@ static int bperf_sync_counters(struct evsel *evsel) > > > > num_cpu = all_cpu_map->nr; > > for (i = 0; i < num_cpu; i++) { > > - cpu = all_cpu_map->map[i]; > > + cpu = all_cpu_map->map[i].cpu; > > bperf_trigger_reading(evsel->bperf_leader_prog_fd, cpu); > > } > > return 0; > > @@ -605,7 +605,7 @@ static int bperf__disable(struct evsel *evsel) > > static int bperf__read(struct evsel *evsel) > > { > > struct bperf_follower_bpf *skel = evsel->follower_skel; > > - __u32 num_cpu_bpf = cpu__max_cpu(); > > + __u32 num_cpu_bpf = cpu__max_cpu().cpu; > > struct bpf_perf_event_value values[num_cpu_bpf]; > > int reading_map_fd, err = 0; > > __u32 i; > > @@ -615,6 +615,7 @@ static int bperf__read(struct evsel *evsel) > > reading_map_fd = bpf_map__fd(skel->maps.accum_readings); > > > > for (i = 0; i < bpf_map__max_entries(skel->maps.accum_readings); i++) { > > + struct perf_cpu entry; > > __u32 cpu; > > > > err = bpf_map_lookup_elem(reading_map_fd, &i, values); > > @@ -624,14 +625,15 @@ static int bperf__read(struct evsel *evsel) > > case BPERF_FILTER_GLOBAL: > > assert(i == 0); > > > > - perf_cpu_map__for_each_cpu(cpu, j, all_cpu_map) { > > + perf_cpu_map__for_each_cpu(entry, j, all_cpu_map) { > > + cpu = entry.cpu; > > perf_counts(evsel->counts, cpu, 0)->val = values[cpu].counter; > > perf_counts(evsel->counts, cpu, 0)->ena = values[cpu].enabled; > > perf_counts(evsel->counts, cpu, 0)->run = values[cpu].running; > > } > > break; > > case BPERF_FILTER_CPU: > > - cpu = evsel->core.cpus->map[i]; > > + cpu = evsel->core.cpus->map[i].cpu; > > perf_counts(evsel->counts, i, 0)->val = values[cpu].counter; > > perf_counts(evsel->counts, i, 0)->ena = values[cpu].enabled; > > perf_counts(evsel->counts, i, 0)->run = values[cpu].running; > > diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c > > index cbc6c2bca488f6bf..631e34a0b66ff084 100644 > > --- a/tools/perf/util/bpf_counter_cgroup.c > > +++ b/tools/perf/util/bpf_counter_cgroup.c > > @@ -48,7 +48,7 @@ static int bperf_load_program(struct evlist *evlist) > > struct cgroup *cgrp, *leader_cgrp; > > __u32 i, cpu; > > __u32 nr_cpus = evlist->core.all_cpus->nr; > > - int total_cpus = cpu__max_cpu(); > > + int total_cpus = cpu__max_cpu().cpu; > > int map_size, map_fd; > > int prog_fd, err; > > > > @@ -125,7 +125,7 @@ static int bperf_load_program(struct evlist *evlist) > > for (cpu = 0; cpu < nr_cpus; cpu++) { > > int fd = FD(evsel, cpu); > > __u32 idx = evsel->core.idx * total_cpus + > > - evlist->core.all_cpus->map[cpu]; > > + evlist->core.all_cpus->map[cpu].cpu; > > > > err = bpf_map_update_elem(map_fd, &idx, &fd, > > BPF_ANY); > > @@ -212,7 +212,7 @@ static int bperf_cgrp__sync_counters(struct evlist *evlist) > > int prog_fd = bpf_program__fd(skel->progs.trigger_read); > > > > for (i = 0; i < nr_cpus; i++) { > > - cpu = evlist->core.all_cpus->map[i]; > > + cpu = evlist->core.all_cpus->map[i].cpu; > > bperf_trigger_reading(prog_fd, cpu); > > } > > > > @@ -245,7 +245,7 @@ static int bperf_cgrp__read(struct evsel *evsel) > > { > > struct evlist *evlist = evsel->evlist; > > int i, cpu, nr_cpus = evlist->core.all_cpus->nr; > > - int total_cpus = cpu__max_cpu(); > > + int total_cpus = cpu__max_cpu().cpu; > > struct perf_counts_values *counts; > > struct bpf_perf_event_value *values; > > int reading_map_fd, err = 0; > > @@ -272,7 +272,7 @@ static int bperf_cgrp__read(struct evsel *evsel) > > } > > > > for (i = 0; i < nr_cpus; i++) { > > - cpu = evlist->core.all_cpus->map[i]; > > + cpu = evlist->core.all_cpus->map[i].cpu; > > > > counts = perf_counts(evsel->counts, i, 0); > > counts->val = values[cpu].counter; > > diff --git a/tools/perf/util/bpf_ftrace.c b/tools/perf/util/bpf_ftrace.c > > index 28dc4c60c7884818..d756cc66eef32ae8 100644 > > --- a/tools/perf/util/bpf_ftrace.c > > +++ b/tools/perf/util/bpf_ftrace.c > > @@ -63,7 +63,7 @@ int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace) > > fd = bpf_map__fd(skel->maps.cpu_filter); > > > > for (i = 0; i < ncpus; i++) { > > - cpu = perf_cpu_map__cpu(ftrace->evlist->core.cpus, i); > > + cpu = perf_cpu_map__cpu(ftrace->evlist->core.cpus, i).cpu; > > bpf_map_update_elem(fd, &cpu, &val, BPF_ANY); > > } > > } > > @@ -122,7 +122,7 @@ int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused, > > int i, fd, err; > > u32 idx; > > u64 *hist; > > - int ncpus = cpu__max_cpu(); > > + int ncpus = cpu__max_cpu().cpu; > > > > fd = bpf_map__fd(skel->maps.latency); > > -- - Arnaldo

2 years, 7 months

Re: [PATCH v4 02/48] perf stat: Add aggr creators that are passed a cpu.

by Arnaldo Carvalho de Melo

Em Tue, Jan 11, 2022 at 11:36:02AM -0800, Ian Rogers escreveu: > On Tue, Jan 11, 2022 at 11:33 AM Arnaldo Carvalho de Melo > <acme(a)kernel.org> wrote: > > > > Em Tue, Jan 04, 2022 at 10:13:05PM -0800, Ian Rogers escreveu: > > > The cpu_map and index can get confused. Add variants of the cpu_map__get > > > routines that are passed a cpu. Make the existing cpu_map__get routines > > > use the new functions with a view to remove them when no longer used. > > > > > > Reviewed-by: James Clark <james.clark(a)arm.com> > > > Signed-off-by: Ian Rogers <irogers(a)google.com> > > > --- > > > tools/perf/util/cpumap.c | 79 +++++++++++++++++++++++----------------- > > > tools/perf/util/cpumap.h | 6 ++- > > > 2 files changed, 51 insertions(+), 34 deletions(-) > > > > > > diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c > > > index 87d3eca9b872..49fba2c53822 100644 > > > --- a/tools/perf/util/cpumap.c > > > +++ b/tools/perf/util/cpumap.c > > > @@ -128,21 +128,23 @@ int cpu_map__get_socket_id(int cpu) > > > return ret ?: value; > > > } > > > > > > -struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, > > > - void *data __maybe_unused) > > > +struct aggr_cpu_id cpu_map__get_socket_aggr_by_cpu(int cpu, void *data __maybe_unused) > > > { > > > - int cpu; > > > struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); > > > > > > - if (idx > map->nr) > > > - return id; > > > - > > > - cpu = map->map[idx]; > > > - > > > id.socket = cpu_map__get_socket_id(cpu); > > > return id; > > > } > > > > > > +struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, > > > + void *data) > > > +{ > > > + if (idx < 0 || idx > map->nr) > > > + return cpu_map__empty_aggr_cpu_id(); > > > + > > > + return cpu_map__get_socket_aggr_by_cpu(map->map[idx], data); > > > +} > > > + > > > > > > This 'idx < 0' wasn't in the original code nor is described in the > > comment log message, please avoid doing this, this may be harmless or > > even a good hardening, but either way would be interesting to have it in > > a separate patch. This eases review as in the end this code is just a > > refactoring, moving things around but in the end should be equivalent code. > > > > There are a few more, please consider this and if you agree, to speed > > things up I can make the changes here, if I think this won't fallout in > > changes to subsequent patches touching this area. > > > > - Arnaldo > > Fwiw, there's the same issue in cpu_map__get_die that's also in > cpu_map__get_core, but weirdly not copied into cpu_map__get_node. As > these functions are removed later I think doing nothing is best here. Sure. > Thanks, > Ian > > > > static int cmp_aggr_cpu_id(const void *a_pointer, const void *b_pointer) > > > { > > > struct aggr_cpu_id *a = (struct aggr_cpu_id *)a_pointer; > > > @@ -200,15 +202,10 @@ int cpu_map__get_die_id(int cpu) > > > return ret ?: value; > > > } > > > > > > -struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data) > > > +struct aggr_cpu_id cpu_map__get_die_aggr_by_cpu(int cpu, void *data) > > > { > > > - int cpu, die; > > > - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); > > > - > > > - if (idx > map->nr) > > > - return id; > > > - > > > - cpu = map->map[idx]; > > > + struct aggr_cpu_id id; > > > + int die; > > > > > > die = cpu_map__get_die_id(cpu); > > > /* There is no die_id on legacy system. */ > > > @@ -220,7 +217,7 @@ struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *dat > > > * with the socket ID and then add die to > > > * make a unique ID. > > > */ > > > - id = cpu_map__get_socket(map, idx, data); > > > + id = cpu_map__get_socket_aggr_by_cpu(cpu, data); > > > if (cpu_map__aggr_cpu_id_is_empty(id)) > > > return id; > > > > > > @@ -228,6 +225,15 @@ struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *dat > > > return id; > > > } > > > > > > +struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, > > > + void *data) > > > +{ > > > + if (idx < 0 || idx > map->nr) > > > + return cpu_map__empty_aggr_cpu_id(); > > > > Ditto > > > > > + > > > + return cpu_map__get_die_aggr_by_cpu(map->map[idx], data); > > > +} > > > + > > > int cpu_map__get_core_id(int cpu) > > > { > > > int value, ret = cpu__get_topology_int(cpu, "core_id", &value); > > > @@ -239,20 +245,13 @@ int cpu_map__get_node_id(int cpu) > > > return cpu__get_node(cpu); > > > } > > > > > > -struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data) > > > +struct aggr_cpu_id cpu_map__get_core_aggr_by_cpu(int cpu, void *data) > > > { > > > - int cpu; > > > - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); > > > - > > > - if (idx > map->nr) > > > - return id; > > > - > > > - cpu = map->map[idx]; > > > - > > > - cpu = cpu_map__get_core_id(cpu); > > > + struct aggr_cpu_id id; > > > + int core = cpu_map__get_core_id(cpu); > > > > > > /* cpu_map__get_die returns a struct with socket and die set*/ > > > - id = cpu_map__get_die(map, idx, data); > > > + id = cpu_map__get_die_aggr_by_cpu(cpu, data); > > > if (cpu_map__aggr_cpu_id_is_empty(id)) > > > return id; > > > > > > @@ -260,19 +259,33 @@ struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *da > > > * core_id is relative to socket and die, we need a global id. > > > * So we combine the result from cpu_map__get_die with the core id > > > */ > > > - id.core = cpu; > > > + id.core = core; > > > return id; > > > + > > > } > > > > > > -struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data __maybe_unused) > > > +struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data) > > > +{ > > > + if (idx < 0 || idx > map->nr) > > > + return cpu_map__empty_aggr_cpu_id(); > > > > Ditto > > > > > + > > > + return cpu_map__get_core_aggr_by_cpu(map->map[idx], data); > > > +} > > > + > > > +struct aggr_cpu_id cpu_map__get_node_aggr_by_cpu(int cpu, void *data __maybe_unused) > > > { > > > struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); > > > > > > + id.node = cpu_map__get_node_id(cpu); > > > + return id; > > > +} > > > + > > > +struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data) > > > +{ > > > if (idx < 0 || idx >= map->nr) > > > - return id; > > > + return cpu_map__empty_aggr_cpu_id(); > > > > > > - id.node = cpu_map__get_node_id(map->map[idx]); > > > - return id; > > > + return cpu_map__get_node_aggr_by_cpu(map->map[idx], data); > > > } > > > > > > int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp) > > > diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h > > > index a27eeaf086e8..c62d67704425 100644 > > > --- a/tools/perf/util/cpumap.h > > > +++ b/tools/perf/util/cpumap.h > > > @@ -31,13 +31,17 @@ size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size); > > > size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size); > > > size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp); > > > int cpu_map__get_socket_id(int cpu); > > > +struct aggr_cpu_id cpu_map__get_socket_aggr_by_cpu(int cpu, void *data); > > > struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data); > > > int cpu_map__get_die_id(int cpu); > > > +struct aggr_cpu_id cpu_map__get_die_aggr_by_cpu(int cpu, void *data); > > > struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data); > > > int cpu_map__get_core_id(int cpu); > > > +struct aggr_cpu_id cpu_map__get_core_aggr_by_cpu(int cpu, void *data); > > > struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data); > > > int cpu_map__get_node_id(int cpu); > > > -struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data); > > > +struct aggr_cpu_id cpu_map__get_node_aggr_by_cpu(int cpu, void *data); > > > +struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data); > > > int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp); > > > int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep); > > > int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep); > > > -- > > > 2.34.1.448.ga2b2bfdf31-goog > > > > -- > > > > - Arnaldo -- - Arnaldo

2 years, 8 months

Re: [PATCH v4 02/48] perf stat: Add aggr creators that are passed a cpu.

by Arnaldo Carvalho de Melo

Em Tue, Jan 04, 2022 at 10:13:05PM -0800, Ian Rogers escreveu: > The cpu_map and index can get confused. Add variants of the cpu_map__get > routines that are passed a cpu. Make the existing cpu_map__get routines > use the new functions with a view to remove them when no longer used. > > Reviewed-by: James Clark <james.clark(a)arm.com> > Signed-off-by: Ian Rogers <irogers(a)google.com> > --- > tools/perf/util/cpumap.c | 79 +++++++++++++++++++++++----------------- > tools/perf/util/cpumap.h | 6 ++- > 2 files changed, 51 insertions(+), 34 deletions(-) > > diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c > index 87d3eca9b872..49fba2c53822 100644 > --- a/tools/perf/util/cpumap.c > +++ b/tools/perf/util/cpumap.c > @@ -128,21 +128,23 @@ int cpu_map__get_socket_id(int cpu) > return ret ?: value; > } > > -struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, > - void *data __maybe_unused) > +struct aggr_cpu_id cpu_map__get_socket_aggr_by_cpu(int cpu, void *data __maybe_unused) > { > - int cpu; > struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); > > - if (idx > map->nr) > - return id; > - > - cpu = map->map[idx]; > - > id.socket = cpu_map__get_socket_id(cpu); > return id; > } > > +struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, > + void *data) > +{ > + if (idx < 0 || idx > map->nr) > + return cpu_map__empty_aggr_cpu_id(); > + > + return cpu_map__get_socket_aggr_by_cpu(map->map[idx], data); > +} > + This 'idx < 0' wasn't in the original code nor is described in the comment log message, please avoid doing this, this may be harmless or even a good hardening, but either way would be interesting to have it in a separate patch. This eases review as in the end this code is just a refactoring, moving things around but in the end should be equivalent code. There are a few more, please consider this and if you agree, to speed things up I can make the changes here, if I think this won't fallout in changes to subsequent patches touching this area. - Arnaldo > static int cmp_aggr_cpu_id(const void *a_pointer, const void *b_pointer) > { > struct aggr_cpu_id *a = (struct aggr_cpu_id *)a_pointer; > @@ -200,15 +202,10 @@ int cpu_map__get_die_id(int cpu) > return ret ?: value; > } > > -struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data) > +struct aggr_cpu_id cpu_map__get_die_aggr_by_cpu(int cpu, void *data) > { > - int cpu, die; > - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); > - > - if (idx > map->nr) > - return id; > - > - cpu = map->map[idx]; > + struct aggr_cpu_id id; > + int die; > > die = cpu_map__get_die_id(cpu); > /* There is no die_id on legacy system. */ > @@ -220,7 +217,7 @@ struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *dat > * with the socket ID and then add die to > * make a unique ID. > */ > - id = cpu_map__get_socket(map, idx, data); > + id = cpu_map__get_socket_aggr_by_cpu(cpu, data); > if (cpu_map__aggr_cpu_id_is_empty(id)) > return id; > > @@ -228,6 +225,15 @@ struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *dat > return id; > } > > +struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, > + void *data) > +{ > + if (idx < 0 || idx > map->nr) > + return cpu_map__empty_aggr_cpu_id(); Ditto > + > + return cpu_map__get_die_aggr_by_cpu(map->map[idx], data); > +} > + > int cpu_map__get_core_id(int cpu) > { > int value, ret = cpu__get_topology_int(cpu, "core_id", &value); > @@ -239,20 +245,13 @@ int cpu_map__get_node_id(int cpu) > return cpu__get_node(cpu); > } > > -struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data) > +struct aggr_cpu_id cpu_map__get_core_aggr_by_cpu(int cpu, void *data) > { > - int cpu; > - struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); > - > - if (idx > map->nr) > - return id; > - > - cpu = map->map[idx]; > - > - cpu = cpu_map__get_core_id(cpu); > + struct aggr_cpu_id id; > + int core = cpu_map__get_core_id(cpu); > > /* cpu_map__get_die returns a struct with socket and die set*/ > - id = cpu_map__get_die(map, idx, data); > + id = cpu_map__get_die_aggr_by_cpu(cpu, data); > if (cpu_map__aggr_cpu_id_is_empty(id)) > return id; > > @@ -260,19 +259,33 @@ struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *da > * core_id is relative to socket and die, we need a global id. > * So we combine the result from cpu_map__get_die with the core id > */ > - id.core = cpu; > + id.core = core; > return id; > + > } > > -struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data __maybe_unused) > +struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data) > +{ > + if (idx < 0 || idx > map->nr) > + return cpu_map__empty_aggr_cpu_id(); Ditto > + > + return cpu_map__get_core_aggr_by_cpu(map->map[idx], data); > +} > + > +struct aggr_cpu_id cpu_map__get_node_aggr_by_cpu(int cpu, void *data __maybe_unused) > { > struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); > > + id.node = cpu_map__get_node_id(cpu); > + return id; > +} > + > +struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data) > +{ > if (idx < 0 || idx >= map->nr) > - return id; > + return cpu_map__empty_aggr_cpu_id(); > > - id.node = cpu_map__get_node_id(map->map[idx]); > - return id; > + return cpu_map__get_node_aggr_by_cpu(map->map[idx], data); > } > > int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp) > diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h > index a27eeaf086e8..c62d67704425 100644 > --- a/tools/perf/util/cpumap.h > +++ b/tools/perf/util/cpumap.h > @@ -31,13 +31,17 @@ size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size); > size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size); > size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp); > int cpu_map__get_socket_id(int cpu); > +struct aggr_cpu_id cpu_map__get_socket_aggr_by_cpu(int cpu, void *data); > struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data); > int cpu_map__get_die_id(int cpu); > +struct aggr_cpu_id cpu_map__get_die_aggr_by_cpu(int cpu, void *data); > struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data); > int cpu_map__get_core_id(int cpu); > +struct aggr_cpu_id cpu_map__get_core_aggr_by_cpu(int cpu, void *data); > struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data); > int cpu_map__get_node_id(int cpu); > -struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data); > +struct aggr_cpu_id cpu_map__get_node_aggr_by_cpu(int cpu, void *data); > +struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data); > int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp); > int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep); > int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep); > -- > 2.34.1.448.ga2b2bfdf31-goog -- - Arnaldo

2 years, 8 months

Re: [PATCH v3 06/48] perf cpumap: Switch cpu_map__build_map to cpu function

by Arnaldo Carvalho de Melo

Em Mon, Jan 10, 2022 at 02:29:58PM -0800, Ian Rogers escreveu: > On Mon, Jan 10, 2022 at 1:34 PM Arnaldo Carvalho de Melo > <acme(a)kernel.org> wrote: > > > > Em Mon, Jan 10, 2022 at 06:23:09PM -0300, Arnaldo Carvalho de Melo escreveu: > > > Em Mon, Jan 10, 2022 at 06:03:04PM -0300, Arnaldo Carvalho de Melo escreveu: > > > > Em Mon, Jan 10, 2022 at 05:46:52PM -0300, Arnaldo Carvalho de Melo escreveu: > > > > > At this point we need to remove the now unused perf_env__get_cpu(), and > > > > > then deal with the fallout in the following patches that needlessly > > > > > modify this unused function. > > > > > > > > > > Doing that now. > > > > > > > > Done, force pushed to tmp.perf/perf_cpu, now it is going again thru the > > > > build containers, a better start now: > > > > > So far so good: > > > > perf test ok, just that one that is failing, but before this series as > > well: > > > > 89: perf all metricgroups test : FAILED! > > Could you add the verbose output? I suspect it is fixed by this: > https://lore.kernel.org/lkml/20211223183948.3423989-1-irogers@google.com/ I'll try it. BTW, here are the final tests, problems with arm 32 and 64-bit, I'll go thru them tomorrow, to fix in the cset the problem appears, so that we keep it bisectable, else you can get what I have in tmp.perf/perf_cpu, fix it and tomorrow I'll retest. 27 85.67 debian:11 : Ok gcc (Debian 10.2.1-6) 10.2.1 20210110 , Debian clang version 11.0.1-2 28 98.65 debian:experimental : Ok gcc (Debian 11.2.0-13) 11.2.0 , Debian clang version 13.0.0-9+b2 29 8.69 debian:experimental-x-arm64 : FAIL gcc version 11.2.0 (Debian 11.2.0-9) arch/arm64/util/pmu.c: In function 'pmu_events_map__find': arch/arm64/util/pmu.c:18:35: error: invalid operands to binary != (have 'int' and 'struct perf_cpu') 18 | if (pmu->cpus->nr != cpu__max_cpu()) | ~~~~~~~~~~~~~ ^~ ~~~~~~~~~~~~~~ | | | | int struct perf_cpu make[5]: *** [/git/perf-5.16.0/tools/build/Makefile.build:139: util] Error 2 make[4]: *** [/git/perf-5.16.0/tools/build/Makefile.build:139: arm64] Error 2 make[3]: *** [/git/perf-5.16.0/tools/build/Makefile.build:139: arch] Error 2 30 19.15 debian:experimental-x-mips : Ok mips-linux-gnu-gcc (Debian 10.2.1-6) 10.2.1 20210110 31 21.25 debian:experimental-x-mips64 : Ok mips64-linux-gnuabi64-gcc (Debian 10.2.1-6) 10.2.1 20210110 32 22.45 debian:experimental-x-mipsel : Ok mipsel-linux-gnu-gcc (Debian 11.2.0-9) 11.2.0 33 21.86 fedora:22 : Ok gcc (GCC) 5.3.1 20160406 (Red Hat 5.3.1-6) , clang version 3.5.0 (tags/RELEASE_350/final) 34 55.88 fedora:23 : Ok gcc (GCC) 5.3.1 20160406 (Red Hat 5.3.1-6) , clang version 3.7.0 (tags/RELEASE_370/final) 35 67.12 fedora:24 : Ok gcc (GCC) 6.3.1 20161221 (Red Hat 6.3.1-1) , clang version 3.8.1 (tags/RELEASE_381/final) 36 17.53 fedora:24-x-ARC-uClibc : Ok arc-linux-gcc (ARCompact ISA Linux uClibc toolchain 2017.09-rc2) 7.1.1 20170710 37 68.11 fedora:25 : Ok gcc (GCC) 6.4.1 20170727 (Red Hat 6.4.1-1) , clang version 3.9.1 (tags/RELEASE_391/final) 38 80.15 fedora:26 : Ok gcc (GCC) 7.3.1 20180130 (Red Hat 7.3.1-2) , clang version 4.0.1 (tags/RELEASE_401/final) 39 80.54 fedora:27 : Ok gcc (GCC) 7.3.1 20180712 (Red Hat 7.3.1-6) , clang version 5.0.2 (tags/RELEASE_502/final) 40 91.48 fedora:28 : Ok gcc (GCC) 8.3.1 20190223 (Red Hat 8.3.1-2) , clang version 6.0.1 (tags/RELEASE_601/final) 41 96.71 fedora:29 : Ok gcc (GCC) 8.3.1 20190223 (Red Hat 8.3.1-2) , clang version 7.0.1 (Fedora 7.0.1-6.fc29) 42 100.71 fedora:30 : Ok gcc (GCC) 9.3.1 20200408 (Red Hat 9.3.1-2) , clang version 8.0.0 (Fedora 8.0.0-3.fc30) 43 94.09 fedora:31 : Ok gcc (GCC) 9.3.1 20200408 (Red Hat 9.3.1-2) , clang version 9.0.1 (Fedora 9.0.1-4.fc31) 44 87.49 fedora:32 : Ok gcc (GCC) 10.3.1 20210422 (Red Hat 10.3.1-1) , clang version 10.0.1 (Fedora 10.0.1-3.fc32) 45 85.99 fedora:33 : Ok gcc (GCC) 10.3.1 20210422 (Red Hat 10.3.1-1) , clang version 11.0.0 (Fedora 11.0.0-3.fc33) 46 88.89 fedora:34 : Ok gcc (GCC) 11.2.1 20210728 (Red Hat 11.2.1-1) , clang version 12.0.1 (Fedora 12.0.1-1.fc34) 47 19.84 fedora:34-x-ARC-glibc : Ok arc-linux-gcc (ARC HS GNU/Linux glibc toolchain 2019.03-rc1) 8.3.1 20190225 48 17.93 fedora:34-x-ARC-uClibc : Ok arc-linux-gcc (ARCv2 ISA Linux uClibc toolchain 2019.03-rc1) 8.3.1 20190225 49 91.33 fedora:35 : Ok gcc (GCC) 11.2.1 20211203 (Red Hat 11.2.1-7) , clang version 13.0.0 (Fedora 13.0.0-3.fc35) 50 99.83 fedora:rawhide : Ok gcc (GCC) 11.2.1 20211203 (Red Hat 11.2.1-7) , clang version 13.0.0 (Fedora 13.0.0-5.fc36) 51 79.16 gentoo-stage3:latest : Ok gcc (Gentoo 11.2.0 p1) 11.2.0 , clang version 13.0.0 52 68.81 mageia:6 : Ok gcc (Mageia 5.5.0-1.mga6) 5.5.0 , clang version 3.9.1 (tags/RELEASE_391/final) 53 38.50 mageia:7 : FAIL clang version 8.0.0 (Mageia 8.0.0-1.mga7) yychar = yylex (&yylval, &yylloc, scanner); ^ #define yylex parse_events_lex ^ 1 error generated. make[3]: *** [/git/perf-5.16.0/tools/build/Makefile.build:139: util] Error 2 54 89.20 manjaro:base : Ok gcc (GCC) 11.1.0 , clang version 13.0.0 55 6.18 openmandriva:cooker : FAIL gcc version 11.2.0 20210728 (OpenMandriva) (GCC) In file included from builtin-bench.c:22: bench/bench.h:66:19: error: conflicting types for 'pthread_attr_setaffinity_np'; have 'int(pthread_attr_t *, size_t, cpu_set_t *)' {aka 'int(pthread_attr_t *, long unsigned int, cpu_set_t *)'} 66 | static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr __maybe_unused, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~ In file included from bench/bench.h:64, from builtin-bench.c:22: /usr/include/pthread.h:394:12: note: previous declaration of 'pthread_attr_setaffinity_np' with type 'int(pthread_attr_t *, size_t, const cpu_set_t *)' {aka 'int(pthread_attr_t *, long unsigned int, const cpu_set_t *)'} 394 | extern int pthread_attr_setaffinity_np (pthread_attr_t *__attr, | ^~~~~~~~~~~~~~~~~~~~~~~~~~~ ld: warning: -r and --gc-sections may not be used together, disabling --gc-sections ld: warning: -r and --icf may not be used together, disabling --icf ld: warning: -r and --gc-sections may not be used together, disabling --gc-sections ld: warning: -r and --icf may not be used together, disabling --icf ld: warning: -r and --gc-sections may not be used together, disabling --gc-sections ld: warning: -r and --icf may not be used together, disabling --icf 56 100.50 opensuse:15.0 : Ok gcc (SUSE Linux) 7.4.1 20190905 [gcc-7-branch revision 275407] , clang version 5.0.1 (tags/RELEASE_501/final 312548) 57 107.92 opensuse:15.1 : Ok gcc (SUSE Linux) 7.5.0 , clang version 7.0.1 (tags/RELEASE_701/final 349238) 58 102.71 opensuse:15.2 : Ok gcc (SUSE Linux) 7.5.0 , clang version 9.0.1 59 113.86 opensuse:15.3 : Ok gcc (SUSE Linux) 7.5.0 , clang version 11.0.1 60 114.75 opensuse:15.4 : Ok gcc (SUSE Linux) 7.5.0 , clang version 11.0.1 61 129.42 opensuse:tumbleweed : Ok gcc (SUSE Linux) 11.2.1 20211124 [revision 7510c23c1ec53aa4a62705f0384079661342ff7b] , clang version 13.0.0 62 94.32 oraclelinux:8 : Ok gcc (GCC) 8.5.0 20210514 (Red Hat 8.5.0-4.0.1) , clang version 12.0.1 (Red Hat 12.0.1-4.0.1.module+el8.5.0+20428+2b4ecd47) 63 94.81 rockylinux:8 : Ok gcc (GCC) 8.5.0 20210514 (Red Hat 8.5.0-4) , clang version 12.0.1 (Red Hat 12.0.1-4.module+el8.5.0+715+58f51d49) 64 71.11 ubuntu:16.04 : Ok gcc (Ubuntu 5.4.0-6ubuntu1~16.04.12) 5.4.0 20160609 , clang version 3.8.0-2ubuntu4 (tags/RELEASE_380/final) 65 6.89 ubuntu:16.04-x-arm : FAIL gcc version 5.4.0 20160609 (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9) arch/arm/util/cs-etm.c: In function 'cs_etm_set_option': arch/arm/util/cs-etm.c:206:16: error: invalid operands to binary < (have 'int' and 'struct perf_cpu') for (i = 0; i < cpu__max_cpu(); i++) { ^ arch/arm/util/cs-etm.c:207:38: error: incompatible type for argument 2 of 'perf_cpu_map__has' if (!perf_cpu_map__has(event_cpus, i) || ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^ arch/arm/util/cs-etm.c:208:39: error: incompatible type for argument 2 of 'perf_cpu_map__has' !perf_cpu_map__has(online_cpus, i)) ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^ arch/arm/util/cs-etm.c: In function 'cs_etm_info_priv_size': arch/arm/util/cs-etm.c:525:17: error: invalid operands to binary < (have 'int' and 'struct perf_cpu') for (i = 0; i < cpu__max_cpu(); i++) { ^ arch/arm/util/cs-etm.c:526:39: error: incompatible type for argument 2 of 'perf_cpu_map__has' if (!perf_cpu_map__has(event_cpus, i) || ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^ arch/arm/util/cs-etm.c:527:40: error: incompatible type for argument 2 of 'perf_cpu_map__has' !perf_cpu_map__has(online_cpus, i)) ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^ arch/arm/util/cs-etm.c:539:17: error: invalid operands to binary < (have 'int' and 'struct perf_cpu') for (i = 0; i < cpu__max_cpu(); i++) { ^ arch/arm/util/cs-etm.c:540:40: error: incompatible type for argument 2 of 'perf_cpu_map__has' if (!perf_cpu_map__has(online_cpus, i)) ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^ arch/arm/util/cs-etm.c: In function 'cs_etm_info_fill': arch/arm/util/cs-etm.c:725:38: error: incompatible type for argument 2 of 'perf_cpu_map__has' if (perf_cpu_map__has(event_cpus, i) && ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^ arch/arm/util/cs-etm.c:726:40: error: incompatible type for argument 2 of 'perf_cpu_map__has' !perf_cpu_map__has(online_cpus, i)) ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^ arch/arm/util/cs-etm.c:746:16: error: invalid operands to binary < (have 'int' and 'struct perf_cpu') for (i = 0; i < cpu__max_cpu() && offset < priv_size; i++) ^ arch/arm/util/cs-etm.c:747:34: error: incompatible type for argument 2 of 'perf_cpu_map__has' if (perf_cpu_map__has(cpu_map, i)) ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^ /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'util' failed make[5]: *** [util] Error 2 /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'arm' failed make[4]: *** [arm] Error 2 /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'arch' failed make[3]: *** [arch] Error 2 66 6.99 ubuntu:16.04-x-arm64 : FAIL gcc version 5.4.0 20160609 (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9) arch/arm64/util/pmu.c: In function 'pmu_events_map__find': arch/arm64/util/pmu.c:18:21: error: invalid operands to binary != (have 'int' and 'struct perf_cpu') if (pmu->cpus->nr != cpu__max_cpu()) ^ /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'util' failed make[5]: *** [util] Error 2 /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'arm64' failed make[4]: *** [arm64] Error 2 /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'arch' failed make[3]: *** [arch] Error 2 67 18.54 ubuntu:16.04-x-powerpc : Ok powerpc-linux-gnu-gcc (Ubuntu 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 68 19.04 ubuntu:16.04-x-powerpc64 : Ok powerpc64-linux-gnu-gcc (Ubuntu/IBM 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 69 18.93 ubuntu:16.04-x-powerpc64el : Ok powerpc64le-linux-gnu-gcc (Ubuntu/IBM 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 70 19.04 ubuntu:16.04-x-s390 : Ok s390x-linux-gnu-gcc (Ubuntu 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 71 76.32 ubuntu:18.04 : Ok gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 , clang version 6.0.0-1ubuntu2 (tags/RELEASE_600/final) 72 7.49 ubuntu:18.04-x-arm : FAIL gcc version 7.5.0 (Ubuntu/Linaro 7.5.0-3ubuntu1~18.04) arch/arm/util/cs-etm.c: In function 'cs_etm_set_option': arch/arm/util/cs-etm.c:206:16: error: invalid operands to binary < (have 'int' and 'struct perf_cpu') for (i = 0; i < cpu__max_cpu(); i++) { ^ ~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c:207:38: error: incompatible type for argument 2 of 'perf_cpu_map__has' if (!perf_cpu_map__has(event_cpus, i) || ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^~~~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c:208:39: error: incompatible type for argument 2 of 'perf_cpu_map__has' !perf_cpu_map__has(online_cpus, i)) ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^~~~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c: In function 'cs_etm_info_priv_size': arch/arm/util/cs-etm.c:525:17: error: invalid operands to binary < (have 'int' and 'struct perf_cpu') for (i = 0; i < cpu__max_cpu(); i++) { ^ ~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c:526:39: error: incompatible type for argument 2 of 'perf_cpu_map__has' if (!perf_cpu_map__has(event_cpus, i) || ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^~~~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c:527:40: error: incompatible type for argument 2 of 'perf_cpu_map__has' !perf_cpu_map__has(online_cpus, i)) ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^~~~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c:539:17: error: invalid operands to binary < (have 'int' and 'struct perf_cpu') for (i = 0; i < cpu__max_cpu(); i++) { ^ ~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c:540:40: error: incompatible type for argument 2 of 'perf_cpu_map__has' if (!perf_cpu_map__has(online_cpus, i)) ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^~~~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c: In function 'cs_etm_info_fill': arch/arm/util/cs-etm.c:725:38: error: incompatible type for argument 2 of 'perf_cpu_map__has' if (perf_cpu_map__has(event_cpus, i) && ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^~~~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c:726:40: error: incompatible type for argument 2 of 'perf_cpu_map__has' !perf_cpu_map__has(online_cpus, i)) ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^~~~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c:746:16: error: invalid operands to binary < (have 'int' and 'struct perf_cpu') for (i = 0; i < cpu__max_cpu() && offset < priv_size; i++) ^ ~~~~~~~~~~~~~~ arch/arm/util/cs-etm.c:747:34: error: incompatible type for argument 2 of 'perf_cpu_map__has' if (perf_cpu_map__has(cpu_map, i)) ^ In file included from arch/arm/util/../../../util/cpumap.h:8:0, from arch/arm/util/cs-etm.c:22: /git/perf-5.16.0/tools/lib/perf/include/perf/cpumap.h:22:18: note: expected 'struct perf_cpu' but argument is of type 'int' LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu); ^~~~~~~~~~~~~~~~~ /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'util' failed make[5]: *** [util] Error 2 /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'arm' failed make[4]: *** [arm] Error 2 /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'arch' failed make[3]: *** [arch] Error 2 73 7.49 ubuntu:18.04-x-arm64 : FAIL gcc version 7.5.0 (Ubuntu/Linaro 7.5.0-3ubuntu1~18.04) arch/arm64/util/pmu.c: In function 'pmu_events_map__find': arch/arm64/util/pmu.c:18:21: error: invalid operands to binary != (have 'int' and 'struct perf_cpu') if (pmu->cpus->nr != cpu__max_cpu()) ~~~~~~~~~~~~~ ^~ ~~~~~~~~~~~~~~ /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'util' failed make[5]: *** [util] Error 2 /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'arm64' failed make[4]: *** [arm64] Error 2 /git/perf-5.16.0/tools/build/Makefile.build:139: recipe for target 'arch' failed make[3]: *** [arch] Error 2 74 16.73 ubuntu:18.04-x-m68k : Ok m68k-linux-gnu-gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 75 19.94 ubuntu:18.04-x-powerpc : Ok powerpc-linux-gnu-gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 76 21.35 ubuntu:18.04-x-powerpc64 : Ok powerpc64-linux-gnu-gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 77 21.55 ubuntu:18.04-x-powerpc64el : Ok powerpc64le-linux-gnu-gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 78 96.72 ubuntu:18.04-x-riscv64 : Ok riscv64-linux-gnu-gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 79 18.24 ubuntu:18.04-x-s390 : Ok s390x-linux-gnu-gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 80 19.54 ubuntu:18.04-x-sh4 : Ok sh4-linux-gnu-gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 81 18.34 ubuntu:18.04-x-sparc64 : Ok sparc64-linux-gnu-gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 82 73.64 ubuntu:20.04 : FAIL clang version 10.0.0-4ubuntu1 83 22.06 ubuntu:20.04-x-powerpc64el : Ok powerpc64le-linux-gnu-gcc (Ubuntu 10.3.0-1ubuntu1~20.04) 10.3.0 84 73.74 ubuntu:20.10 : Ok gcc (Ubuntu 10.3.0-1ubuntu1~20.10) 10.3.0 , Ubuntu clang version 11.0.0-2 85 83.78 ubuntu:21.04 : Ok gcc (Ubuntu 10.3.0-1ubuntu1) 10.3.0 , Ubuntu clang version 12.0.0-3ubuntu1~21.04.2 86 86.88 ubuntu:21.10 : Ok gcc (Ubuntu 11.2.0-7ubuntu2) 11.2.0 , Ubuntu clang version 13.0.0-2 87 105.27 ubuntu:22.04 : Ok gcc (Ubuntu 11.2.0-13ubuntu1) 11.2.0 , Ubuntu clang version 13.0.0-9 BUILD_TARBALL_HEAD=16ed0580fb4d64bd59771ae7559dc307f04a0473 88 5613.66 real 95m27.836s user 1m24.038s sys 0m50.044s [perfbuilder@five ~]$ > Thanks, > Ian > > > [acme@quaco perf]$ uname -a > > Linux quaco 5.15.7-200.fc35.x86_64 #1 SMP Wed Dec 8 19:00:47 UTC 2021 x86_64 x86_64 x86_64 GNU/Linux > > [acme@quaco perf]$ git log --oneline -1 > > 16ed0580fb4d64bd (HEAD -> perf/core, seventh/perf/core, five/perf/core, acme.korg/tmp.perf/perf_cpu) perf cpumap: Give CPUs their own type > > [acme@quaco perf]$ perf -v > > perf version 5.16.g16ed0580fb4d > > [acme@quaco perf]$ sudo su - > > [sudo] password for acme: > > [root@quaco ~]# perf -vv > > perf version 5.16.g16ed0580fb4d > > dwarf: [ on ] # HAVE_DWARF_SUPPORT > > dwarf_getlocations: [ on ] # HAVE_DWARF_GETLOCATIONS_SUPPORT > > glibc: [ on ] # HAVE_GLIBC_SUPPORT > > syscall_table: [ on ] # HAVE_SYSCALL_TABLE_SUPPORT > > libbfd: [ on ] # HAVE_LIBBFD_SUPPORT > > libelf: [ on ] # HAVE_LIBELF_SUPPORT > > libnuma: [ on ] # HAVE_LIBNUMA_SUPPORT > > numa_num_possible_cpus: [ on ] # HAVE_LIBNUMA_SUPPORT > > libperl: [ on ] # HAVE_LIBPERL_SUPPORT > > libpython: [ on ] # HAVE_LIBPYTHON_SUPPORT > > libslang: [ on ] # HAVE_SLANG_SUPPORT > > libcrypto: [ on ] # HAVE_LIBCRYPTO_SUPPORT > > libunwind: [ on ] # HAVE_LIBUNWIND_SUPPORT > > libdw-dwarf-unwind: [ on ] # HAVE_DWARF_SUPPORT > > zlib: [ on ] # HAVE_ZLIB_SUPPORT > > lzma: [ on ] # HAVE_LZMA_SUPPORT > > get_cpuid: [ on ] # HAVE_AUXTRACE_SUPPORT > > bpf: [ on ] # HAVE_LIBBPF_SUPPORT > > aio: [ on ] # HAVE_AIO_SUPPORT > > zstd: [ on ] # HAVE_ZSTD_SUPPORT > > libpfm4: [ OFF ] # HAVE_LIBPFM > > [root@quaco ~]# perf test > > 1: vmlinux symtab matches kallsyms : Ok > > 2: Detect openat syscall event : Ok > > 3: Detect openat syscall event on all cpus : Ok > > 4: Read samples using the mmap interface : Ok > > 5: Test data source output : Ok > > 6: Parse event definition strings : Ok > > 7: Simple expression parser : Ok > > 8: PERF_RECORD_* events & perf_sample fields : Ok > > 9: Parse perf pmu format : Ok > > 10: PMU events : > > 10.1: PMU event table sanity : Ok > > 10.2: PMU event map aliases : Ok > > 10.3: Parsing of PMU event table metrics : Ok > > 10.4: Parsing of PMU event table metrics with fake PMUs : Ok > > 11: DSO data read : Ok > > 12: DSO data cache : Ok > > 13: DSO data reopen : Ok > > 14: Roundtrip evsel->name : Ok > > 15: Parse sched tracepoints fields : Ok > > 16: syscalls:sys_enter_openat event fields : Ok > > 17: Setup struct perf_event_attr : Ok > > 18: Match and link multiple hists : Ok > > 19: 'import perf' in python : Ok > > 20: Breakpoint overflow signal handler : Ok > > 21: Breakpoint overflow sampling : Ok > > 22: Breakpoint accounting : Ok > > 23: Watchpoint : > > 23.1: Read Only Watchpoint : Skip (missing hardware support) > > 23.2: Write Only Watchpoint : Ok > > 23.3: Read / Write Watchpoint : Ok > > 23.4: Modify Watchpoint : Ok > > 24: Number of exit events of a simple workload : Ok > > 25: Software clock events period values : Ok > > 26: Object code reading : Ok > > 27: Sample parsing : Ok > > 28: Use a dummy software event to keep tracking : Ok > > 29: Parse with no sample_id_all bit set : Ok > > 30: Filter hist entries : Ok > > 31: Lookup mmap thread : Ok > > 32: Share thread maps : Ok > > 33: Sort output of hist entries : Ok > > 34: Cumulate child hist entries : Ok > > 35: Track with sched_switch : Ok > > 36: Filter fds with revents mask in a fdarray : Ok > > 37: Add fd to a fdarray, making it autogrow : Ok > > 38: kmod_path__parse : Ok > > 39: Thread map : Ok > > 40: LLVM search and compile : > > 40.1: Basic BPF llvm compile : Ok > > 40.2: kbuild searching : Ok > > 40.3: Compile source for BPF prologue generation : Ok > > 40.4: Compile source for BPF relocation : Ok > > 41: Session topology : Ok > > 42: BPF filter : > > 42.1: Basic BPF filtering : Ok > > 42.2: BPF pinning : Ok > > 42.3: BPF prologue generation : Ok > > 43: Synthesize thread map : Ok > > 44: Remove thread map : Ok > > 45: Synthesize cpu map : Ok > > 46: Synthesize stat config : Ok > > 47: Synthesize stat : Ok > > 48: Synthesize stat round : Ok > > 49: Synthesize attr update : Ok > > 50: Event times : Ok > > 51: Read backward ring buffer : Ok > > 52: Print cpu map : Ok > > 53: Merge cpu map : Ok > > 54: Probe SDT events : Ok > > 55: is_printable_array : Ok > > 56: Print bitmap : Ok > > 57: perf hooks : Ok > > 58: builtin clang support : > > 58.1: builtin clang compile C source to IR : Skip (not compiled in) > > 58.2: builtin clang compile C source to ELF object : Skip (not compiled in) > > 59: unit_number__scnprintf : Ok > > 60: mem2node : Ok > > 61: time utils : Ok > > 62: Test jit_write_elf : Ok > > 63: Test libpfm4 support : > > 63.1: test of individual --pfm-events : Skip (not compiled in) > > 63.2: test groups of --pfm-events : Skip (not compiled in) > > 64: Test api io : Ok > > 65: maps__merge_in : Ok > > 66: Demangle Java : Ok > > 67: Demangle OCaml : Ok > > 68: Parse and process metrics : Ok > > 69: PE file support : Ok > > 70: Event expansion for cgroups : Ok > > 71: Convert perf time to TSC : Ok > > 72: dlfilter C API : Ok > > 73: Sigtrap : Ok > > 74: x86 rdpmc : Ok > > 75: Test dwarf unwind : Ok > > 76: x86 instruction decoder - new instructions : Ok > > 77: Intel PT packet decoder : Ok > > 78: x86 bp modify : Ok > > 79: x86 Sample parsing : Ok > > 80: build id cache operations : Ok > > 81: daemon operations : Ok > > 82: perf pipe recording and injection test : Ok > > 83: Add vfs_getname probe to get syscall args filenames : Ok > > 84: probe libc's inet_pton & backtrace it with ping : Ok > > 85: Use vfs_getname probe to get syscall args filenames : Ok > > 86: Zstd perf.data compression/decompression : Ok > > 87: perf stat csv summary test : Ok > > 88: perf stat metrics (shadow stat) test : Ok > > 89: perf all metricgroups test : FAILED! > > 90: perf all metrics test : Ok > > 91: perf all PMU test : Ok > > 92: perf stat --bpf-counters test : Ok > > 93: Check Arm CoreSight trace data recording and synthesized samples: Skip > > 94: Check Arm SPE trace data recording and synthesized samples : Skip > > 95: Check open filename arg using perf trace + vfs_getname : Ok > > [root@quaco ~]# > > > > And the containers are ok so far: > > > > [perfbuilder@five ~]$ export BUILD_TARBALL=http://192.168.100.2/perf/perf-5.16.0.tar.xz > > [perfbuilder@five ~]$ time dm > > 1 95.61 almalinux:8 : Ok gcc (GCC) 8.5.0 20210514 (Red Hat 8.5.0-4) , clang version 12.0.1 (Red Hat 12.0.1-4.module_el8.5.0+1025+93159d6c) > > 2 56.18 alpine:3.4 : Ok gcc (Alpine 5.3.0) 5.3.0 , clang version 3.8.0 (tags/RELEASE_380/final) > > 3 54.98 alpine:3.5 : Ok gcc (Alpine 6.2.1) 6.2.1 20160822 , clang version 3.8.1 (tags/RELEASE_381/final) > > 4 57.69 alpine:3.6 : Ok gcc (Alpine 6.3.0) 6.3.0 , clang version 4.0.0 (tags/RELEASE_400/final) > > 5 63.62 alpine:3.7 : Ok gcc (Alpine 6.4.0) 6.4.0 , Alpine clang version 5.0.0 (tags/RELEASE_500/final) (based on LLVM 5.0.0) > > 6 64.52 alpine:3.8 : Ok gcc (Alpine 6.4.0) 6.4.0 , Alpine clang version 5.0.1 (tags/RELEASE_501/final) (based on LLVM 5.0.1) > > 7 66.54 alpine:3.9 : Ok gcc (Alpine 8.3.0) 8.3.0 , Alpine clang version 5.0.1 (tags/RELEASE_502/final) (based on LLVM 5.0.1) > > 8 91.91 alpine:3.10 : Ok gcc (Alpine 8.3.0) 8.3.0 , Alpine clang version 8.0.0 (tags/RELEASE_800/final) (based on LLVM 8.0.0) > > 9 104.93 alpine:3.11 : Ok gcc (Alpine 9.3.0) 9.3.0 , Alpine clang version 9.0.0 (https://git.alpinelinux.org/aports f7f0d2c2b8bcd6a5843401a9a702029556492689) (based on LLVM 9.0.0) > > 10 107.97 alpine:3.12 : Ok gcc (Alpine 9.3.0) 9.3.0 , Alpine clang version 10.0.0 (https://gitlab.alpinelinux.org/alpine/aports.git 7445adce501f8473efdb93b17b5eaf2f1445ed4c) > > 11 115.98 alpine:3.13 : Ok gcc (Alpine 10.2.1_pre1) 10.2.1 20201203 , Alpine clang version 10.0.1 > > 12 101.73 alpine:3.14 : Ok gcc (Alpine 10.3.1_git20210424) 10.3.1 20210424 , Alpine clang version 11.1.0 > > 13 103.35 alpine:3.15 : Ok gcc (Alpine 10.3.1_git20211027) 10.3.1 20211027 , Alpine clang version 12.0.1 > > 14 104.43 alpine:edge : Ok gcc (Alpine 11.2.1_git20211128) 11.2.1 20211128 , Alpine clang version 12.0.1 > > 15 51.06 alt:p8 : Ok x86_64-alt-linux-gcc (GCC) 5.3.1 20151207 (ALT p8 5.3.1-alt3.M80P.1) , clang version 3.8.0 (tags/RELEASE_380/final) > > 16 75.95 alt:p9 : Ok x86_64-alt-linux-gcc (GCC) 8.4.1 20200305 (ALT p9 8.4.1-alt0.p9.1) , clang version 10.0.0 > > 17 75.26 alt:p10 : Ok x86_64-alt-linux-gcc (GCC) 10.3.1 20210703 (ALT Sisyphus 10.3.1-alt2) , clang version 11.0.1 > > 18 74.85 alt:sisyphus : Ok x86_64-alt-linux-gcc (GCC) 11.2.1 20210911 (ALT Sisyphus 11.2.1-alt1) , ALT Linux Team clang version 12.0.1 > > 19 52.87 amazonlinux:1 : Ok gcc (GCC) 7.2.1 20170915 (Red Hat 7.2.1-2) , clang version 3.6.2 (tags/RELEASE_362/final) > > 20 85.98 amazonlinux:2 : Ok gcc (GCC) 7.3.1 20180712 (Red Hat 7.3.1-13) , clang version 11.1.0 (Amazon Linux 2 11.1.0-1.amzn2.0.2) > > 21 79.77 archlinux:base : Ok gcc (GCC) 11.1.0 , clang version 13.0.0 > > 22 83.56 centos:8 : Ok gcc (GCC) 8.4.1 20200928 (Red Hat 8.4.1-1) , clang version 11.0.1 (Red Hat 11.0.1-1.module_el8.4.0+966+2995ef20) > > 23 98.02 centos:stream : Ok gcc (GCC) 8.5.0 20210514 (Red Hat 8.5.0-3) , clang version 12.0.1 (Red Hat 12.0.1-2.module_el8.6.0+937+1cafe22c) > > 24 27.67 clearlinux:latest : Ok gcc (Clear Linux OS for Intel Architecture) 11.2.1 20211228 releases/gcc-11.2.0-618-g3b2b18144c , clang version 11.1.0 > > 25 65.92 debian:9 : Ok gcc (Debian 6.3.0-18+deb9u1) 6.3.0 20170516 , clang version 3.8.1-24 (tags/RELEASE_381/final) > > 26 62.20 debian:10 : Ok gcc (Debian 8.3.0-6) 8.3.0 , clang version 7.0.1-8+deb10u2 (tags/RELEASE_701/final) > > 27: debian:11 > > -- - Arnaldo

2 years, 8 months

Re: [PATCH v3 06/48] perf cpumap: Switch cpu_map__build_map to cpu function

by Arnaldo Carvalho de Melo

Em Wed, Dec 29, 2021 at 11:19:48PM -0800, Ian Rogers escreveu: > Avoid error prone cpu_map + idx variant. Remove now unused functions. At this point we need to remove the now unused perf_env__get_cpu(), and then deal with the fallout in the following patches that needlessly modify this unused function. Doing that now. - Arnaldo ⬢[acme@toolbox perf]$ git diff diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 6b985abaa2d22c58..40cb3518f27e2309 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1477,22 +1477,6 @@ static void perf_stat__exit_aggr_mode(void) stat_config.cpus_aggr_map = NULL; } -static inline int perf_env__get_cpu(void *data, struct perf_cpu_map *map, int idx) -{ - struct perf_env *env = data; - int cpu; - - if (idx > map->nr) - return -1; - - cpu = map->map[idx]; - - if (cpu >= env->nr_cpus_avail) - return -1; - - return cpu; -} - static struct aggr_cpu_id perf_env__get_socket_aggr_by_cpu(int cpu, void *data) { struct perf_env *env = data; > Reviewed-by: James Clark <james.clark(a)arm.com> > Signed-off-by: Ian Rogers <irogers(a)google.com> > --- > tools/perf/builtin-stat.c | 28 ++++------------------------ > tools/perf/util/cpumap.c | 12 ++++++------ > tools/perf/util/cpumap.h | 2 +- > 3 files changed, 11 insertions(+), 31 deletions(-) > > diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c > index 9791ae9b1a53..6b985abaa2d2 100644 > --- a/tools/perf/builtin-stat.c > +++ b/tools/perf/builtin-stat.c > @@ -1504,11 +1504,6 @@ static struct aggr_cpu_id perf_env__get_socket_aggr_by_cpu(int cpu, void *data) > return id; > } > > -static struct aggr_cpu_id perf_env__get_socket(struct perf_cpu_map *map, int idx, void *data) > -{ > - return perf_env__get_socket_aggr_by_cpu(perf_env__get_cpu(data, map, idx), data); > -} > - > static struct aggr_cpu_id perf_env__get_die_aggr_by_cpu(int cpu, void *data) > { > struct perf_env *env = data; > @@ -1527,11 +1522,6 @@ static struct aggr_cpu_id perf_env__get_die_aggr_by_cpu(int cpu, void *data) > return id; > } > > -static struct aggr_cpu_id perf_env__get_die(struct perf_cpu_map *map, int idx, void *data) > -{ > - return perf_env__get_die_aggr_by_cpu(perf_env__get_cpu(data, map, idx), data); > -} > - > static struct aggr_cpu_id perf_env__get_core_aggr_by_cpu(int cpu, void *data) > { > struct perf_env *env = data; > @@ -1551,11 +1541,6 @@ static struct aggr_cpu_id perf_env__get_core_aggr_by_cpu(int cpu, void *data) > return id; > } > > -static struct aggr_cpu_id perf_env__get_core(struct perf_cpu_map *map, int idx, void *data) > -{ > - return perf_env__get_core_aggr_by_cpu(perf_env__get_cpu(data, map, idx), data); > -} > - > static struct aggr_cpu_id perf_env__get_node_aggr_by_cpu(int cpu, void *data) > { > struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id(); > @@ -1564,33 +1549,28 @@ static struct aggr_cpu_id perf_env__get_node_aggr_by_cpu(int cpu, void *data) > return id; > } > > -static struct aggr_cpu_id perf_env__get_node(struct perf_cpu_map *map, int idx, void *data) > -{ > - return perf_env__get_node_aggr_by_cpu(perf_env__get_cpu(data, map, idx), data); > -} > - > static int perf_env__build_socket_map(struct perf_env *env, struct perf_cpu_map *cpus, > struct cpu_aggr_map **sockp) > { > - return cpu_map__build_map(cpus, sockp, perf_env__get_socket, env); > + return cpu_map__build_map(cpus, sockp, perf_env__get_socket_aggr_by_cpu, env); > } > > static int perf_env__build_die_map(struct perf_env *env, struct perf_cpu_map *cpus, > struct cpu_aggr_map **diep) > { > - return cpu_map__build_map(cpus, diep, perf_env__get_die, env); > + return cpu_map__build_map(cpus, diep, perf_env__get_die_aggr_by_cpu, env); > } > > static int perf_env__build_core_map(struct perf_env *env, struct perf_cpu_map *cpus, > struct cpu_aggr_map **corep) > { > - return cpu_map__build_map(cpus, corep, perf_env__get_core, env); > + return cpu_map__build_map(cpus, corep, perf_env__get_core_aggr_by_cpu, env); > } > > static int perf_env__build_node_map(struct perf_env *env, struct perf_cpu_map *cpus, > struct cpu_aggr_map **nodep) > { > - return cpu_map__build_map(cpus, nodep, perf_env__get_node, env); > + return cpu_map__build_map(cpus, nodep, perf_env__get_node_aggr_by_cpu, env); > } > > static struct aggr_cpu_id perf_stat__get_socket_file(struct perf_stat_config *config __maybe_unused, > diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c > index 49fba2c53822..feaf34b25efc 100644 > --- a/tools/perf/util/cpumap.c > +++ b/tools/perf/util/cpumap.c > @@ -163,7 +163,7 @@ static int cmp_aggr_cpu_id(const void *a_pointer, const void *b_pointer) > } > > int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res, > - struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data), > + struct aggr_cpu_id (*f)(int cpu, void *data), > void *data) > { > int nr = cpus->nr; > @@ -178,7 +178,7 @@ int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res, > c->nr = 0; > > for (cpu = 0; cpu < nr; cpu++) { > - s1 = f(cpus, cpu, data); > + s1 = f(cpu, data); > for (s2 = 0; s2 < c->nr; s2++) { > if (cpu_map__compare_aggr_cpu_id(s1, c->map[s2])) > break; > @@ -290,22 +290,22 @@ struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *da > > int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp) > { > - return cpu_map__build_map(cpus, sockp, cpu_map__get_socket, NULL); > + return cpu_map__build_map(cpus, sockp, cpu_map__get_socket_aggr_by_cpu, NULL); > } > > int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep) > { > - return cpu_map__build_map(cpus, diep, cpu_map__get_die, NULL); > + return cpu_map__build_map(cpus, diep, cpu_map__get_die_aggr_by_cpu, NULL); > } > > int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep) > { > - return cpu_map__build_map(cpus, corep, cpu_map__get_core, NULL); > + return cpu_map__build_map(cpus, corep, cpu_map__get_core_aggr_by_cpu, NULL); > } > > int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **numap) > { > - return cpu_map__build_map(cpus, numap, cpu_map__get_node, NULL); > + return cpu_map__build_map(cpus, numap, cpu_map__get_node_aggr_by_cpu, NULL); > } > > /* setup simple routines to easily access node numbers given a cpu number */ > diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h > index c62d67704425..9648816c4255 100644 > --- a/tools/perf/util/cpumap.h > +++ b/tools/perf/util/cpumap.h > @@ -63,7 +63,7 @@ int cpu__max_present_cpu(void); > int cpu__get_node(int cpu); > > int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res, > - struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data), > + struct aggr_cpu_id (*f)(int cpu, void *data), > void *data); > > int cpu_map__cpu(struct perf_cpu_map *cpus, int idx); > -- > 2.34.1.448.ga2b2bfdf31-goog -- - Arnaldo

2 years, 8 months

Re: [PATCH v4 00/48] Refactor perf cpumap

by Arnaldo Carvalho de Melo

Em Tue, Jan 04, 2022 at 10:13:03PM -0800, Ian Rogers escreveu: > Perf cpu map has various functions where a cpumap and index are passed > in order to load the cpu. A problem with this is that the wrong index > may be passed for the cpumap, causing problems like aggregation on the > wrong CPU: > https://lore.kernel.org/lkml/20211204023409.969668-1-irogers@google.com/ > > This patch set refactors the cpu map API, reducing it and explicitly > passing the cpu (rather than the pair) to functions that need > it. Comments are added at the same time. Changes modify the same > file/function more than once as refactoring and fixes are broken apart > for the sake of bisection. > > v2. Incorproates fixes suggested Jiri Olsa, rewrites the evlist CPU > iterator in part in a way suggested by Riccardo Mancini. The new > fixes start at patch 23. The final change was suggested by John > Garry to make the CPUs have their own struct wrapper. > > v3. Incorporates fixes suggested by Namhyung Kim. > > v4. Rebases and incorporates fixes suggested by Jiri Olsa. Did fixes in places where BUILD_BPF_SKEL=1 was failing, now, at the end of the series: ⬢[acme@toolbox perf]$ git log --oneline -1 ; time make -C tools/perf build-test 462aafa8fcbdc78f (HEAD -> perf/core) perf cpumap: Give CPUs their own type make: Entering directory '/var/home/acme/git/perf/tools/perf' - tarpkg: ./tests/perf-targz-src-pkg . make_static: cd . && make LDFLAGS=-static NO_PERF_READ_VDSO32=1 NO_PERF_READ_VDSOX32=1 NO_JVMTI=1 -j32 DESTDIR=/tmp/tmp.lFrqVcqiRY make_with_gtk2: cd . && make GTK2=1 -j32 DESTDIR=/tmp/tmp.KvHmTqUGmD - /var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP: cd . && make FEATURE_DUMP_COPY=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP feature-dump cd . && make FEATURE_DUMP_COPY=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP feature-dump make_no_libelf_O: cd . && make NO_LIBELF=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.xz3LYy7WpA DESTDIR=/tmp/tmp.zVjIMpvQMM make_no_libbpf_DEBUG_O: cd . && make NO_LIBBPF=1 DEBUG=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.0gxAOSjb1j DESTDIR=/tmp/tmp.kYTk1WjWWz make_no_libaudit_O: cd . && make NO_LIBAUDIT=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.6hArTG9Dth DESTDIR=/tmp/tmp.hCNdYeDRCr make_no_backtrace_O: cd . && make NO_BACKTRACE=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.VtoPI58z3t DESTDIR=/tmp/tmp.SYyBBMSHSL make_no_libcrypto_O: cd . && make NO_LIBCRYPTO=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.SO1qtxJwvE DESTDIR=/tmp/tmp.AqrPw1oZfx make_with_clangllvm_O: cd . && make LIBCLANGLLVM=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.G9KVEaDv2B DESTDIR=/tmp/tmp.6CSqj0wPqJ make_with_coresight_O: cd . && make CORESIGHT=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.PnVTJNHy1E DESTDIR=/tmp/tmp.k7Arerg778 make_no_libpython_O: cd . && make NO_LIBPYTHON=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.cKjvFagVL3 DESTDIR=/tmp/tmp.aCaD0hbP3O make_no_sdt_O: cd . && make NO_SDT=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.EKoWnoZtl4 DESTDIR=/tmp/tmp.1gGYetcptB make_libbpf_dynamic_O: cd . && make LIBBPF_DYNAMIC=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.Nked5O10EK DESTDIR=/tmp/tmp.eo6YAEOfZO make_minimal_O: cd . && make NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1 NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1 NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1 NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 NO_LIBBPF=1 NO_LIBCRYPTO=1 NO_SDT=1 NO_JVMTI=1 NO_LIBZSTD=1 NO_LIBCAP=1 NO_SYSCALL_TABLE=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.Z6dSqYBXfU DESTDIR=/tmp/tmp.Y4iRu634of make_install_prefix_slash_O: cd . && make install prefix=/tmp/krava/ FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.BgipDyNu70 DESTDIR=/tmp/tmp.pOwrdDYBqf make_util_pmu_bison_o_O: cd . && make util/pmu-bison.o FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.XeO82Ajmv6 DESTDIR=/tmp/tmp.dxQKNNBM6W make_install_O: cd . && make install FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.KuCyqzLwnA DESTDIR=/tmp/tmp.KYvqoiOKzW make_install_prefix_O: cd . && make install prefix=/tmp/krava FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.rJNNPELdri DESTDIR=/tmp/tmp.g52i9CcmnU make_install_bin_O: cd . && make install-bin FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.i118vbQuo0 DESTDIR=/tmp/tmp.90tKcjOWD8 make_perf_o_O: cd . && make perf.o FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.kEZMTvh3wf DESTDIR=/tmp/tmp.JYvQLdkPsp make_no_slang_O: cd . && make NO_SLANG=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.WDNGH0DpdW DESTDIR=/tmp/tmp.Zfa804wClJ make_no_ui_O: cd . && make NO_NEWT=1 NO_SLANG=1 NO_GTK2=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.P4nTBNqkP4 DESTDIR=/tmp/tmp.iCLqOyrh4o make_no_newt_O: cd . && make NO_NEWT=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.EdjjHoqODV DESTDIR=/tmp/tmp.jKfYRizWtm make_with_libpfm4_O: cd . && make LIBPFM4=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.r3hPAOgfId DESTDIR=/tmp/tmp.GvMmEZUc2B make_no_demangle_O: cd . && make NO_DEMANGLE=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.wG9f40LzG3 DESTDIR=/tmp/tmp.i76sPjSg1m make_no_libunwind_O: cd . && make NO_LIBUNWIND=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.SmFfmmB9KQ DESTDIR=/tmp/tmp.9tjMdCWMxG make_no_libbpf_O: cd . && make NO_LIBBPF=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.7jH21oP9n7 DESTDIR=/tmp/tmp.taUqTgY37S make_no_syscall_tbl_O: cd . && make NO_SYSCALL_TABLE=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.L2v7vi1AQl DESTDIR=/tmp/tmp.wHEA4jEpw9 make_no_libnuma_O: cd . && make NO_LIBNUMA=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.9N5pQYuRbO DESTDIR=/tmp/tmp.B0Yptb7xP6 make_util_map_o_O: cd . && make util/map.o FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.B8oe4jnWwB DESTDIR=/tmp/tmp.m0APlsli14 make_with_babeltrace_O: cd . && make LIBBABELTRACE=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.3G1kLTJLJx DESTDIR=/tmp/tmp.ahuDENSMsz make_debug_O: cd . && make DEBUG=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.KpsvOj0KHD DESTDIR=/tmp/tmp.f2Yv9Lrorg make_no_libperl_O: cd . && make NO_LIBPERL=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.7tIufwAi4O DESTDIR=/tmp/tmp.vcBv7UYjuw make_no_libbionic_O: cd . && make NO_LIBBIONIC=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.HCJA7xCDxq DESTDIR=/tmp/tmp.us5CDSPqyO make_pure_O: cd . && make FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.eg2wCpydvg DESTDIR=/tmp/tmp.MmD1xESO2A make_doc_O: cd . && make doc FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.TqkyGrzRut DESTDIR=/tmp/tmp.ap34IVxoM9 make_no_scripts_O: cd . && make NO_LIBPYTHON=1 NO_LIBPERL=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.pRWHKzpPhv DESTDIR=/tmp/tmp.dUNhAp2rLt make_clean_all_O: cd . && make clean all FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.YnzNLLk9ID DESTDIR=/tmp/tmp.7kXr5obkmA make_no_libdw_dwarf_unwind_O: cd . && make NO_LIBDW_DWARF_UNWIND=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.GzZCxuYLwR DESTDIR=/tmp/tmp.n3YS9a9DcU make_help_O: cd . && make help FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.t7QwWVHsod DESTDIR=/tmp/tmp.NG5uSWCZzi make_no_auxtrace_O: cd . && make NO_AUXTRACE=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.wiDZkJzs8R DESTDIR=/tmp/tmp.ITtPlX0usX make_no_gtk2_O: cd . && make NO_GTK2=1 FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.xd1x5QIckJ DESTDIR=/tmp/tmp.f6KzsHHkZH make_tags_O: cd . && make tags FEATURES_DUMP=/var/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP -j32 O=/tmp/tmp.e8oSaBuFUb DESTDIR=/tmp/tmp.4czd6ovlSB OK make: Leaving directory '/var/home/acme/git/perf/tools/perf' real 4m29.388s user 59m6.060s sys 12m19.581s ⬢[acme@toolbox perf]$ alias m='perf stat -e cycles:u,instructions:u make -k BUILD_BPF_SKEL=1 CORESIGHT=1 PYTHON=python3 O=/tmp/build/perf -C tools/perf install-bin && git status && perf test python' So 'perf test python' is done after every build, no problems with that as well. I'm now making it go thru the container builds. - Arnaldo

2 years, 8 months

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

CoreSight January 2022