| Message ID | 1493907596-11425-3-git-send-email-anju@linux.vnet.ibm.com (mailing list archive) |
|---|---|
| State | Superseded, archived |
| Headers | show |
Anju T Sudhakar <anju@linux.vnet.ibm.com> writes: > This patch does three things : > - Enables "opal.c" to create a platform device for the IMC interface > according to the appropriate compatibility string. > - Find the reserved-memory region details from the system device tree > and get the base address of HOMER (Reserved memory) region address for each chip. > - We also get the Nest PMU counter data offsets (in the HOMER region) > and their sizes. The offsets for the counters' data are fixed and > won't change from chip to chip. > > The device tree parsing logic is separated from the PMU creation > functions (which is done in subsequent patches). > > Patch also adds a CONFIG_HV_PERF_IMC_CTRS for the IMC driver. > > Signed-off-by: Anju T Sudhakar <anju@linux.vnet.ibm.com> > Signed-off-by: Hemant Kumar <hemant@linux.vnet.ibm.com> > Signed-off-by: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> > --- > arch/powerpc/platforms/powernv/Kconfig | 10 +++ > arch/powerpc/platforms/powernv/Makefile | 1 + > arch/powerpc/platforms/powernv/opal-imc.c | 140 ++++++++++++++++++++++++++++++ > arch/powerpc/platforms/powernv/opal.c | 18 ++++ > 4 files changed, 169 insertions(+) > create mode 100644 arch/powerpc/platforms/powernv/opal-imc.c > > diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig > index 3a07e4d..1b90a98 100644 > --- a/arch/powerpc/platforms/powernv/Kconfig > +++ b/arch/powerpc/platforms/powernv/Kconfig > @@ -27,3 +27,13 @@ config OPAL_PRD > help > This enables the opal-prd driver, a facility to run processor > recovery diagnostics on OpenPower machines > + > +config HV_PERF_IMC_CTRS > + bool "Hypervisor supplied In Memory Collection PMU events (Nest & Core)" > + default y > + depends on PERF_EVENTS && PPC_POWERNV > + help > + Enable access to hypervisor supplied in-memory collection counters > + in perf. IMC counters are available from Power9 systems. > + > + If unsure, select Y. > diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile > index b5d98cb..715e531 100644 > --- a/arch/powerpc/platforms/powernv/Makefile > +++ b/arch/powerpc/platforms/powernv/Makefile > @@ -12,3 +12,4 @@ obj-$(CONFIG_PPC_SCOM) += opal-xscom.o > obj-$(CONFIG_MEMORY_FAILURE) += opal-memory-errors.o > obj-$(CONFIG_TRACEPOINTS) += opal-tracepoints.o > obj-$(CONFIG_OPAL_PRD) += opal-prd.o > +obj-$(CONFIG_HV_PERF_IMC_CTRS) += opal-imc.o > diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c > new file mode 100644 > index 0000000..3a87000 > --- /dev/null > +++ b/arch/powerpc/platforms/powernv/opal-imc.c > @@ -0,0 +1,140 @@ > +/* > + * OPAL IMC interface detection driver > + * Supported on POWERNV platform > + * > + * Copyright (C) 2017 Madhavan Srinivasan, IBM Corporation. > + * (C) 2017 Anju T Sudhakar, IBM Corporation. > + * (C) 2017 Hemant K Shaw, IBM Corporation. > + * > + * This program is free software; you can redistribute it and/or modify > + * it under the terms of the GNU General Public License version 2 as > + * published by the Free Software Foundation. > + * > + * This program is distributed in the hope that it will be useful, > + * but WITHOUT ANY WARRANTY; without even the implied warranty of > + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the > + * GNU General Public License for more details. > + */ > +#include <linux/kernel.h> > +#include <linux/module.h> > +#include <linux/platform_device.h> > +#include <linux/miscdevice.h> > +#include <linux/fs.h> > +#include <linux/of.h> > +#include <linux/of_address.h> > +#include <linux/of_platform.h> > +#include <linux/poll.h> > +#include <linux/mm.h> > +#include <linux/slab.h> > +#include <linux/crash_dump.h> > +#include <asm/opal.h> > +#include <asm/io.h> > +#include <asm/uaccess.h> > +#include <asm/cputable.h> > +#include <asm/imc-pmu.h> > + > +struct perchip_nest_info nest_perchip_info[IMC_MAX_CHIPS]; > + > +/* > + * imc_pmu_setup : Setup the IMC PMUs (children of "parent"). > + */ > +static void __init imc_pmu_setup(struct device_node *parent) > +{ > + if (!parent) > + return; > +} > + > +static int opal_imc_counters_probe(struct platform_device *pdev) > +{ > + struct device_node *imc_dev, *dn, *rm_node = NULL; > + struct perchip_nest_info *pcni; > + u32 pages, nest_offset, nest_size, chip_id; > + int i = 0; > + const __be32 *addrp; > + u64 reg_addr, reg_size; > + > + if (!pdev || !pdev->dev.of_node) > + return -ENODEV; > + > + /* > + * Check whether this is kdump kernel. If yes, just return. > + */ > + if (is_kdump_kernel()) > + return -ENODEV; > + > + imc_dev = pdev->dev.of_node; > + > + /* > + * Nest counter data are saved in a reserved memory called HOMER. > + * "imc-nest-offset" identifies the counter data location within HOMER. > + * size : size of the entire nest-counters region > + */ > + if (of_property_read_u32(imc_dev, "imc-nest-offset", &nest_offset)) > + goto err; > + > + if (of_property_read_u32(imc_dev, "imc-nest-size", &nest_size)) > + goto err; > + > + /* Sanity check */ > + if ((nest_size/PAGE_SIZE) > IMC_NEST_MAX_PAGES) > + goto err; > + > + /* Find the "HOMER region" for each chip */ > + rm_node = of_find_node_by_path("/reserved-memory"); > + if (!rm_node) > + goto err; > + > + /* > + * We need to look for the "ibm,homer-image" node in the > + * "/reserved-memory" node. > + */ > + for (dn = of_find_node_by_name(rm_node, "ibm,homer-image"); dn; > + dn = of_find_node_by_name(dn, "ibm,homer-image")) { > + > + /* Get the chip id to which the above homer region belongs to */ > + if (of_property_read_u32(dn, "ibm,chip-id", &chip_id)) > + goto err; So, I was thinking on this (and should probably comment on the firmware side as well). I'd prefer an OPAL interface where instead of looking up where ibm,homer-image is, we provide the kernel with a base address and then have offsets into it. That way, we don't tie the kernel code to counters that are only in the HOMER region.
On Thursday 11 May 2017 01:19 PM, Stewart Smith wrote: > Anju T Sudhakar <anju@linux.vnet.ibm.com> writes: >> This patch does three things : >> - Enables "opal.c" to create a platform device for the IMC interface >> according to the appropriate compatibility string. >> - Find the reserved-memory region details from the system device tree >> and get the base address of HOMER (Reserved memory) region address for each chip. >> - We also get the Nest PMU counter data offsets (in the HOMER region) >> and their sizes. The offsets for the counters' data are fixed and >> won't change from chip to chip. >> >> The device tree parsing logic is separated from the PMU creation >> functions (which is done in subsequent patches). >> >> Patch also adds a CONFIG_HV_PERF_IMC_CTRS for the IMC driver. >> >> Signed-off-by: Anju T Sudhakar <anju@linux.vnet.ibm.com> >> Signed-off-by: Hemant Kumar <hemant@linux.vnet.ibm.com> >> Signed-off-by: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> >> --- >> arch/powerpc/platforms/powernv/Kconfig | 10 +++ >> arch/powerpc/platforms/powernv/Makefile | 1 + >> arch/powerpc/platforms/powernv/opal-imc.c | 140 ++++++++++++++++++++++++++++++ >> arch/powerpc/platforms/powernv/opal.c | 18 ++++ >> 4 files changed, 169 insertions(+) >> create mode 100644 arch/powerpc/platforms/powernv/opal-imc.c >> >> diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig >> index 3a07e4d..1b90a98 100644 >> --- a/arch/powerpc/platforms/powernv/Kconfig >> +++ b/arch/powerpc/platforms/powernv/Kconfig >> @@ -27,3 +27,13 @@ config OPAL_PRD >> help >> This enables the opal-prd driver, a facility to run processor >> recovery diagnostics on OpenPower machines >> + >> +config HV_PERF_IMC_CTRS >> + bool "Hypervisor supplied In Memory Collection PMU events (Nest & Core)" >> + default y >> + depends on PERF_EVENTS && PPC_POWERNV >> + help >> + Enable access to hypervisor supplied in-memory collection counters >> + in perf. IMC counters are available from Power9 systems. >> + >> + If unsure, select Y. >> diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile >> index b5d98cb..715e531 100644 >> --- a/arch/powerpc/platforms/powernv/Makefile >> +++ b/arch/powerpc/platforms/powernv/Makefile >> @@ -12,3 +12,4 @@ obj-$(CONFIG_PPC_SCOM) += opal-xscom.o >> obj-$(CONFIG_MEMORY_FAILURE) += opal-memory-errors.o >> obj-$(CONFIG_TRACEPOINTS) += opal-tracepoints.o >> obj-$(CONFIG_OPAL_PRD) += opal-prd.o >> +obj-$(CONFIG_HV_PERF_IMC_CTRS) += opal-imc.o >> diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c >> new file mode 100644 >> index 0000000..3a87000 >> --- /dev/null >> +++ b/arch/powerpc/platforms/powernv/opal-imc.c >> @@ -0,0 +1,140 @@ >> +/* >> + * OPAL IMC interface detection driver >> + * Supported on POWERNV platform >> + * >> + * Copyright (C) 2017 Madhavan Srinivasan, IBM Corporation. >> + * (C) 2017 Anju T Sudhakar, IBM Corporation. >> + * (C) 2017 Hemant K Shaw, IBM Corporation. >> + * >> + * This program is free software; you can redistribute it and/or modify >> + * it under the terms of the GNU General Public License version 2 as >> + * published by the Free Software Foundation. >> + * >> + * This program is distributed in the hope that it will be useful, >> + * but WITHOUT ANY WARRANTY; without even the implied warranty of >> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the >> + * GNU General Public License for more details. >> + */ >> +#include <linux/kernel.h> >> +#include <linux/module.h> >> +#include <linux/platform_device.h> >> +#include <linux/miscdevice.h> >> +#include <linux/fs.h> >> +#include <linux/of.h> >> +#include <linux/of_address.h> >> +#include <linux/of_platform.h> >> +#include <linux/poll.h> >> +#include <linux/mm.h> >> +#include <linux/slab.h> >> +#include <linux/crash_dump.h> >> +#include <asm/opal.h> >> +#include <asm/io.h> >> +#include <asm/uaccess.h> >> +#include <asm/cputable.h> >> +#include <asm/imc-pmu.h> >> + >> +struct perchip_nest_info nest_perchip_info[IMC_MAX_CHIPS]; >> + >> +/* >> + * imc_pmu_setup : Setup the IMC PMUs (children of "parent"). >> + */ >> +static void __init imc_pmu_setup(struct device_node *parent) >> +{ >> + if (!parent) >> + return; >> +} >> + >> +static int opal_imc_counters_probe(struct platform_device *pdev) >> +{ >> + struct device_node *imc_dev, *dn, *rm_node = NULL; >> + struct perchip_nest_info *pcni; >> + u32 pages, nest_offset, nest_size, chip_id; >> + int i = 0; >> + const __be32 *addrp; >> + u64 reg_addr, reg_size; >> + >> + if (!pdev || !pdev->dev.of_node) >> + return -ENODEV; >> + >> + /* >> + * Check whether this is kdump kernel. If yes, just return. >> + */ >> + if (is_kdump_kernel()) >> + return -ENODEV; >> + >> + imc_dev = pdev->dev.of_node; >> + >> + /* >> + * Nest counter data are saved in a reserved memory called HOMER. >> + * "imc-nest-offset" identifies the counter data location within HOMER. >> + * size : size of the entire nest-counters region >> + */ >> + if (of_property_read_u32(imc_dev, "imc-nest-offset", &nest_offset)) >> + goto err; >> + >> + if (of_property_read_u32(imc_dev, "imc-nest-size", &nest_size)) >> + goto err; >> + >> + /* Sanity check */ >> + if ((nest_size/PAGE_SIZE) > IMC_NEST_MAX_PAGES) >> + goto err; >> + >> + /* Find the "HOMER region" for each chip */ >> + rm_node = of_find_node_by_path("/reserved-memory"); >> + if (!rm_node) >> + goto err; >> + >> + /* >> + * We need to look for the "ibm,homer-image" node in the >> + * "/reserved-memory" node. >> + */ >> + for (dn = of_find_node_by_name(rm_node, "ibm,homer-image"); dn; >> + dn = of_find_node_by_name(dn, "ibm,homer-image")) { >> + >> + /* Get the chip id to which the above homer region belongs to */ >> + if (of_property_read_u32(dn, "ibm,chip-id", &chip_id)) >> + goto err; > So, I was thinking on this (and should probably comment on the firmware > side as well). > > I'd prefer an OPAL interface where instead of looking up where > ibm,homer-image is, we provide the kernel with a base address and then > have offsets into it. > > That way, we don't tie the kernel code to counters that are only in the > HOMER region. Yes. This make sense. Adding something like this to IMC node will be fine? chip@<id> { base_addr = < addr >; ibm,chip-id = < id>; }; Maddy > >
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig index 3a07e4d..1b90a98 100644 --- a/arch/powerpc/platforms/powernv/Kconfig +++ b/arch/powerpc/platforms/powernv/Kconfig @@ -27,3 +27,13 @@ config OPAL_PRD help This enables the opal-prd driver, a facility to run processor recovery diagnostics on OpenPower machines + +config HV_PERF_IMC_CTRS + bool "Hypervisor supplied In Memory Collection PMU events (Nest & Core)" + default y + depends on PERF_EVENTS && PPC_POWERNV + help + Enable access to hypervisor supplied in-memory collection counters + in perf. IMC counters are available from Power9 systems. + + If unsure, select Y. diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index b5d98cb..715e531 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -12,3 +12,4 @@ obj-$(CONFIG_PPC_SCOM) += opal-xscom.o obj-$(CONFIG_MEMORY_FAILURE) += opal-memory-errors.o obj-$(CONFIG_TRACEPOINTS) += opal-tracepoints.o obj-$(CONFIG_OPAL_PRD) += opal-prd.o +obj-$(CONFIG_HV_PERF_IMC_CTRS) += opal-imc.o diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c new file mode 100644 index 0000000..3a87000 --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-imc.c @@ -0,0 +1,140 @@ +/* + * OPAL IMC interface detection driver + * Supported on POWERNV platform + * + * Copyright (C) 2017 Madhavan Srinivasan, IBM Corporation. + * (C) 2017 Anju T Sudhakar, IBM Corporation. + * (C) 2017 Hemant K Shaw, IBM Corporation. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/miscdevice.h> +#include <linux/fs.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_platform.h> +#include <linux/poll.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/crash_dump.h> +#include <asm/opal.h> +#include <asm/io.h> +#include <asm/uaccess.h> +#include <asm/cputable.h> +#include <asm/imc-pmu.h> + +struct perchip_nest_info nest_perchip_info[IMC_MAX_CHIPS]; + +/* + * imc_pmu_setup : Setup the IMC PMUs (children of "parent"). + */ +static void __init imc_pmu_setup(struct device_node *parent) +{ + if (!parent) + return; +} + +static int opal_imc_counters_probe(struct platform_device *pdev) +{ + struct device_node *imc_dev, *dn, *rm_node = NULL; + struct perchip_nest_info *pcni; + u32 pages, nest_offset, nest_size, chip_id; + int i = 0; + const __be32 *addrp; + u64 reg_addr, reg_size; + + if (!pdev || !pdev->dev.of_node) + return -ENODEV; + + /* + * Check whether this is kdump kernel. If yes, just return. + */ + if (is_kdump_kernel()) + return -ENODEV; + + imc_dev = pdev->dev.of_node; + + /* + * Nest counter data are saved in a reserved memory called HOMER. + * "imc-nest-offset" identifies the counter data location within HOMER. + * size : size of the entire nest-counters region + */ + if (of_property_read_u32(imc_dev, "imc-nest-offset", &nest_offset)) + goto err; + + if (of_property_read_u32(imc_dev, "imc-nest-size", &nest_size)) + goto err; + + /* Sanity check */ + if ((nest_size/PAGE_SIZE) > IMC_NEST_MAX_PAGES) + goto err; + + /* Find the "HOMER region" for each chip */ + rm_node = of_find_node_by_path("/reserved-memory"); + if (!rm_node) + goto err; + + /* + * We need to look for the "ibm,homer-image" node in the + * "/reserved-memory" node. + */ + for (dn = of_find_node_by_name(rm_node, "ibm,homer-image"); dn; + dn = of_find_node_by_name(dn, "ibm,homer-image")) { + + /* Get the chip id to which the above homer region belongs to */ + if (of_property_read_u32(dn, "ibm,chip-id", &chip_id)) + goto err; + + pcni = &nest_perchip_info[chip_id]; + addrp = of_get_address(dn, 0, ®_size, NULL); + if (!addrp) + goto err; + + /* Fetch the homer region base address */ + reg_addr = of_read_number(addrp, 2); + pcni->pbase = reg_addr; + /* Add the nest IMC Base offset */ + pcni->pbase = pcni->pbase + nest_offset; + /* Fetch the size of the homer region */ + pcni->size = nest_size; + + for (i = 0; i < (pcni->size / PAGE_SIZE); i++) { + pages = PAGE_SIZE * i; + pcni->vbase[i] = (u64)phys_to_virt(pcni->pbase + pages); + } + } + + imc_pmu_setup(imc_dev); + + return 0; +err: + return -ENODEV; +} + +static const struct of_device_id opal_imc_match[] = { + { .compatible = IMC_DTB_COMPAT }, + {}, +}; + +static struct platform_driver opal_imc_driver = { + .driver = { + .name = "opal-imc-counters", + .of_match_table = opal_imc_match, + }, + .probe = opal_imc_counters_probe, +}; + +MODULE_DEVICE_TABLE(of, opal_imc_match); +module_platform_driver(opal_imc_driver); +MODULE_DESCRIPTION("PowerNV OPAL IMC driver"); +MODULE_LICENSE("GPL"); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index e0f856b..b06f896 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -14,6 +14,7 @@ #include <linux/printk.h> #include <linux/types.h> #include <linux/of.h> +#include <linux/of_address.h> #include <linux/of_fdt.h> #include <linux/of_platform.h> #include <linux/interrupt.h> @@ -30,6 +31,7 @@ #include <asm/opal.h> #include <asm/firmware.h> #include <asm/mce.h> +#include <asm/imc-pmu.h> #include "powernv.h" @@ -631,6 +633,17 @@ static void opal_pdev_init(const char *compatible) of_platform_device_create(np, NULL, NULL); } +#ifdef CONFIG_HV_PERF_IMC_CTRS +static void __init opal_imc_init_dev(void) +{ + struct device_node *np; + + np = of_find_compatible_node(NULL, NULL, IMC_DTB_COMPAT); + if (np) + of_platform_device_create(np, NULL, NULL); +} +#endif + static int kopald(void *unused) { unsigned long timeout = msecs_to_jiffies(opal_heartbeat) + 1; @@ -704,6 +717,11 @@ static int __init opal_init(void) /* Setup a heatbeat thread if requested by OPAL */ opal_init_heartbeat(); +#ifdef CONFIG_HV_PERF_IMC_CTRS + /* Detect IMC pmu counters support and create PMUs */ + opal_imc_init_dev(); +#endif + /* Create leds platform devices */ leds = of_find_node_by_path("/ibm,opal/leds"); if (leds) {