Message-ID: <20181217110906.0000003f@huawei.com>
Date:   Mon, 17 Dec 2018 11:09:06 +0000
From:   Jonathan Cameron <jonathan.cameron@...wei.com>
To:     Bjorn Helgaas <helgaas@...nel.org>
CC:     <linux-pci@...r.kernel.org>, Mark Rutland <mark.rutland@....com>,
        "Shaokun Zhang" <zhangshaokun@...ilicon.com>,
        Will Deacon <will.deacon@....com>, <linuxarm@...wei.com>,
        Keith Busch <keith.busch@...el.com>,
        Zhou Wang <wangzhou1@...ilicon.com>,
        Mika Westerberg <mika.westerberg@...ux.intel.com>,
        <linux-arm-kernel@...ts.infradead.org>,
        "Rafael J. Wysocki" <rjw@...ysocki.net>,
        Len Brown <lenb@...nel.org>, <linux-acpi@...r.kernel.org>,
        <linux-kernel@...r.kernel.org>, <alex.umansky@...wei.com>,
        <Eric.Wehage@...wei.com>
Subject: Re: [RFC PATCH 2/2] PCI/portdrv Hisilicon PCIe transport layer Port
 PMU driver.

On Fri, 14 Dec 2018 17:55:05 -0600
Bjorn Helgaas <helgaas@...nel.org> wrote:

> [+cc Rafael, Len, linux-acpi, linux-kernel]
Hi Bjorn,

> 
> Thanks a lot for working on this!  I've been hoping somebody would
> push on the PMU issue because there are some real wrinkles to work
> out.

Indeed! I'm glad this isn't one I'm aiming to 'solve' to a particular
deadline.

> 
> On Fri, Dec 14, 2018 at 09:10:55PM +0800, Jonathan Cameron wrote:
> > The Hip08 SoCs contain relatively detailed performance units for the
> > PCIe Transport Layer at each port.
> > 
> > The support here is a subset of what will come, but is intended to
> > provide some initial basic functionality.
> > 
> > Note that there is a _lot_ more functionality in this hardware unit
> > so this is the first RFC of several.
> > 
> > RFC questions:
> > 
> > 1. There is no standard for PCIe PMUs.  However, there are things that
> >    are elements of the PCIe protocol so any similar PMU is likely to
> >    support them.  Do we want to have a go at some consistent naming?  
> 
> Is this a perf question, i.e., are you asking about the event names
> from "perf list"?  If so, I have no idea :)  But you're right that the
> events on the PCIe side are mostly defined by the PCIe spec and I
> agree it would make a lot of sense to use common names for those
> things.

Exactly that.  It's nice if users know what they are getting rather than
having lots of subtly different variants of posted write tlp counters etc.
Ideally this would be defined by the PCI SIG in a similar fashion to
architectural counters on Arm, but they aren't yet...

I'm far from an expert on PCIe but I can pull in some of our PCI hardware
people and see if I can sketch out some docs for what a hypothetical
magic PMU could count, then working out a naming scheme to cover that.
+CC Alex and Eric. 

We have things like bandwidth estimation and credits statistics to
potentially consider as well.  Right now I can only find limited precedence
for handling that sort of a thing in PMUs in general (there are similar
things in Intel's graphics drivers).

> 
> > 2. We are using an ACPI DSDT description to find what is basically a
> >    platform device that is associated with a PCIe device. Is this an
> >    acceptable thing to do?  
> 
> If the PCIe device itself, e.g., a Root Port, consumes address space,
> it should have a BAR that describes it.

I agree that would be the ideal / right way. Here we have an oddity because the
port is in the host SoC. It's not remotely compliant with any standard.
We are looking at this for future hardware but I don't think there is
much we can do with this one.

Looking forwards, there isn't a huge amount of flexibility in port definitions
if we do want to put this in Bar space as only 2 Bars available
(type 1 config space header)  I have no idea if these are in heavy use or
not on existing hardware.  Looks like the Switchtec parts use one of
them.  I know from other activities that people get very defensive of their BAR
Space, particularly when looking to retrofit in new versions of a long standing
device.

> 
> If the Root Complex, which is not a PCIe device and does not have an
> architected configuration or programming model, consumes address
> space, it would make sense to describe it via ACPI in the PNP0A03
> device like other host bridge registers.
> 
> From your cover letter, I think you have the latter situation, and if
> I understand correctly, you have something like this in ACPI:
> 
>   PNP0A03       PCI host bridge
>     HISIxxxx    PMU registers for Root Port 00:1c.0
>     HISIxxxx    PMU registers for Root Port 00:1c.2
> 
> The PNP0A03 _CRS describes the address space it consumes, which
> comprises (1) the register space that operates the bridge itself,
> e.g., sets apertures, performs PCI config accesses, etc., and
> (2) space that is converted to PCI transactions on the downstream
> side.

Pretty much as you describe.  Here, roughly speaking, is the relevant
DSDT blob.  We have to play the slightly odd trick to get the association
with the port.  Note this sort of trick is sometimes done for RCiEPs to
provide for things that aren't quite handled in standard way (stuff
around resets etc for example - often as a work around for a hardware
limitation in a particular version).

Device (PCI0)
{
	Name (_HID, "PNP0A08")
	Name (_UID, Zero)
	Name (_CID, "PNP0A03")
	Name (_SEG, Zero)
	Name (_BBN, Zero)
	Name (_CCA, One)
	Name (_PRT, Package (0x18))
	Device (BR00) {
	/* This device has it's class set to be a bridge so binds to portdrv */
		Name (_HID, "19E5A120")
		Name (_ADR, 0)
		Name (_CRS, ResourceTemplate () {
			QwordMemory(
 				ResourceConsumer,
				PosDecode,
				MinFixed,
				MaxFixed,
				NonCacheable,
				ReadWrite,
				0,
				0x148284000,
				0x148284FFF,
				0x0,
				0x1000)
		})
	}
}

> 
> So this feels a little strange to me because ACPI says the HISIxxxx
> devices are below the host bridge, but instead of consuming PCI
> address space, they consume part of the PNP0A03 register space.
> But maybe that makes sense in ACPI, I dunno.

>From a logical point of view, it doesn't really - this should have been
firmly tied to PCIe.  Note they 'also' provide regular PCIe accesses paths
as they are standard compliant for their normal role as 'dumb' Root Ports.

The lack of any standardization around PMUs basically means that
people do this sort of nastiness.  To be fair to them, our hardware
team never thought this one would be exposed in general when they designed
it.

The requirements came along later when some of us got fed up with
internal only tooling to access this stuff.  I also wanted to explore
the space as it has quite a few impacts on future hardware specifications.

> 
> As far as I can tell, you don't actually need *anything* supplied by
> portdrv except the pcie_device.port, which you only use to find the
> ACPI companion device and to hang the devm_ things on.

Pretty much.  The 'obvious' option would have been to just have this as
an uncore PMU (which are platform devices instantiated from ACPI) but
then we loose the association with the PCIe topology entirely.
This is how internal interconnect, cache, memory controllers PMUs
are handled on most Arm64 platforms for example.  There are ACPI bindings
that could be used similar to how we associate caches with their
CPU clusters, but they are (to my mind) less elegant that above. 

That also won't work when future hardware does it in the PCIe domain
either via a BAR or some other approach.

> 
> As written, hisi_pcie_pmu will bind to any Port, including Switch
> Ports as well as Root Ports.  It has a poor-man's match() built into
> hisi_pcie_pmu_probe(), which is sort of sub-optimal.  It would be
> nicer to have a real match() function run by the bus driver.  I know
> portdrv doesn't give you that, and since portdrv claims every Port
> itself, there's no good way for other drivers like this to get
> connected to Ports.

Agreed.  As it currently stands it is a dirty hack ;)  I wondered about
putting a standard bus register / match approach in there but wanted
to get the discussion going before adding non trivial infrastructure
in portdrv that might scare people off ;). From your comments below
it sounds like we might want to more radically change how the port
driver stuff works anyway.

> 
> Do you have a hotplug strategy yet?  PMUs in Switches below the Root
> Ports sound like a useful thing.  Since you bind to every Port, you
> will bind to hot-added Switch Ports, but unless you use ACPI hotplug,
> you won't have a chance to add ACPI companion devices for them.

The ACPI hack is very much because our hardware doesn't do it 'right'.
This particular root port is always in the host anyway so we are fine here.

You certainly couldn't pull this trick with switches out in the fabric,
but then they hopefully don't provide a non PCI backdoor to read their
PMUs anyway.  PCI hotplug is causing me enough headaches elsewhere
that I hope it'll just work with anything we do here!

> 
> > Not yet fully established.
> > 
> > 1. I haven't done enough testing with high performance devices to
> >    establish the 'minimum' frequency of the high resolution timer.
> >    It may be that we just end up dropping some of the counters
> >    because the load is too high to sample them often enough.
> >    Once the basic approach is established I'll run the numbers
> >    on this. These are up to Gen4x16 ports so things go pretty quick.
> > 
> > Signed-off-by: Jonathan Cameron <Jonathan.Cameron@...wei.com>
> > ---
> >  drivers/pci/pcie/Kconfig         |   9 +
> >  drivers/pci/pcie/Makefile        |   2 +
> >  drivers/pci/pcie/hisi_pcie_pmu.c | 528 +++++++++++++++++++++++++++++++
> >  include/linux/cpuhotplug.h       |   1 +
> >  4 files changed, 540 insertions(+)  
> 
> This looks like a nice piece of work, but I'm not sure where to put
> it.  It really doesn't feel like part of the PCI core in the sense
> that the PCI specs don't help you write it, and it doesn't provide any
> PCI services used by other parts of the kernel.  It feels more like
> just another driver for a device that happens to be on a PCI bus.
> 
> Granted, it currently requires portdrv, but I think the only reason
> for that is to resolve the "multiple drivers need the same device"
> problem.  I don't think portdrv is a good solution for that.
> 
> The other portdrv services (AER, hotplug, DPC, etc) are all defined in
> the spec, and they're related in strange ways like sharing interrupts.
> I would *like* to see those services moved into the PCI core directly
> so they're not *drivers*, they're just optional features like MSI,
> IOV, etc.
> 
> Then the Ports would by default not have a driver bound to them and
> device-specific drivers like this could directly bind to the Port PCI
> device.
> 

So the alternative is to just treat them as generic PMU drivers
and put them in drivers/perf.  That is fine but I would worry that would
lose the 'generalization' aspect because they weren't falling under
the scope of PCI.  I suppose we could just make it clear that any such
driver needs review from the PCI side as well as the perf side before being
merged.

However, we really are measuring things that are defined in the PCIe spec
even if we aren't doing it via PCI SIG defined methods (as there aren't
any currently), so it's a bit of a gray area to my mind.

Of course we don't have to get it right first time anyway as moving
drivers later is easy if it's just about where the code sits.  So we can
park this question until the more fundamental stuff is sorted!

Jonathan

> Bjorn
> 
> > diff --git a/drivers/pci/pcie/Kconfig b/drivers/pci/pcie/Kconfig
> > index 44742b2e1126..983783c42cf0 100644
> > --- a/drivers/pci/pcie/Kconfig
> > +++ b/drivers/pci/pcie/Kconfig
> > @@ -47,6 +47,15 @@ config PCIEAER_INJECT
> >  	  gotten from:
> >  	     http://www.kernel.org/pub/linux/utils/pci/aer-inject/
> >  
> > +config PCIE_HISI_PMU
> > +       tristate "PCI Express Root Port Performance Monitoring for Hisilicon Hip08"
> > +       depends on PCIEPORTBUS
> > +       help
> > +	 The hisilicon Hip08 platform has root ports with integrated
> > +	 transport layer performance measurement units. These are
> > +	 exposed within the memory map, so resources must be provided
> > +	 via ACPI DSDT.
> > + 
> >  #
> >  # PCI Express ECRC
> >  #
> > diff --git a/drivers/pci/pcie/Makefile b/drivers/pci/pcie/Makefile
> > index ab514083d5d4..67435abef29d 100644
> > --- a/drivers/pci/pcie/Makefile
> > +++ b/drivers/pci/pcie/Makefile
> > @@ -12,3 +12,5 @@ obj-$(CONFIG_PCIEAER_INJECT)	+= aer_inject.o
> >  obj-$(CONFIG_PCIE_PME)		+= pme.o
> >  obj-$(CONFIG_PCIE_DPC)		+= dpc.o
> >  obj-$(CONFIG_PCIE_PTM)		+= ptm.o
> > +
> > +obj-$(CONFIG_PCIE_HISI_PMU)     += hisi_pcie_pmu.o
> > diff --git a/drivers/pci/pcie/hisi_pcie_pmu.c b/drivers/pci/pcie/hisi_pcie_pmu.c
> > new file mode 100644
> > index 000000000000..ddd2885a2b17
> > --- /dev/null
> > +++ b/drivers/pci/pcie/hisi_pcie_pmu.c
> > @@ -0,0 +1,528 @@
> > +// SPDX-License-Identifier: GPL-2.0
> > +/*
> > + * Provide performance monitoring for Hisilicon PCIe root ports
> > + *
> > + * Copyright (C) 2018 Hisilicon
> > + */
> > +
> > +#include <linux/acpi.h>
> > +#include <linux/bitmap.h>
> > +#include <linux/cpuhotplug.h>
> > +#include <linux/delay.h>
> > +#include <linux/device.h>
> > +#include <linux/kernel.h>
> > +#include <linux/module.h>
> > +#include <linux/pci.h>
> > +#include <linux/perf_event.h>
> > +
> > +#include "portdrv.h"
> > +
> > +#define HISI_PP_TL_CNT_CTRL_REG 0x96C
> > +#define   HISI_PP_TL_CNT_CTRL_TX_FLOW_CNT_EN BIT(0)
> > +#define   HISI_PP_TL_CNT_CTRL_TX_ERR_CNT_EN BIT(1)
> > +#define   HISI_PP_TL_CNT_CTRL_TX_NAT_CPL_CNT_EN BIT(2)
> > +#define   HISI_PP_TL_CNT_CTRL_TX_FLOW_FUN_EN BIT(3)
> > +#define   HISI_PP_TL_CNT_CTRL_TX_FLOW_CNT_TIME_MASK 0xFFF0
> > +
> > +#define HISI_MAX_PERIOD(nr) (BIT_ULL(nr) - 1)
> > +
> > +#define HISI_PP_TIMER_PERIOD_NS 10000000
> > +
> > +enum hisi_pci_counts {
> > +	TX_MEM_RD,
> > +	TX_MEM_WR,
> > +	TX_CFG_RD,
> > +	TX_CFG_WR,
> > +	TX_IO_RD,
> > +	TX_IO_WR,
> > +	TX_MSG,
> > +	TX_CPL,
> > +	TX_CCIX,
> > +	TX_ATOMIC,
> > +	TX_P2P,
> > +	TX_TLP,
> > +	TX_PAYLOAD,
> > +	TX_DW,
> > +
> > +	RX_TOTAL_TLP,
> > +	RX_TOTAL_TR,
> > +	RX_DROP,
> > +	RX_POSTED,
> > +	RX_NONPOSTED,
> > +	RX_CPL,
> > +	HISI_PP_EVENTS,
> > +};
> > +
> > +static struct hisi_pcie_cnt {
> > +	u64 reg_offset;
> > +	u8 bits;
> > +} hisi_pcie_cnt_info[HISI_PP_EVENTS] = {
> > +	[TX_MEM_RD]		= { 0x908, 16 },
> > +	[TX_MEM_WR]		= { 0x90c, 16 },
> > +	[TX_CFG_RD]		= { 0x910, 16 },
> > +	[TX_CFG_WR]		= { 0x914, 16 },
> > +	[TX_IO_RD]		= { 0x918, 16 },
> > +	[TX_IO_WR]		= { 0x91C, 16 },
> > +	[TX_MSG]		= { 0x924, 16 },
> > +	[TX_CPL]		= { 0x930, 16 },
> > +	[TX_CCIX]		= { 0x934, 16 },
> > +	[TX_ATOMIC]		= { 0x938, 16 },
> > +	[TX_P2P]		= { 0x93C, 16 },
> > +	[TX_TLP]		= { 0x940, 32 },
> > +	[TX_PAYLOAD]		= { 0x944, 32 },
> > +	[TX_DW]			= { 0x948, 32 },
> > +
> > +	[RX_TOTAL_TLP]		= { 0xb38, 16 },
> > +	[RX_TOTAL_TR]		= { 0xb3c, 16 },
> > +	[RX_DROP]		= { 0xb40, 16 },
> > +	[RX_POSTED]		= { 0xb44, 16 },
> > +	[RX_NONPOSTED]		= { 0xb48, 16 },
> > +	[RX_CPL]		= { 0xb4c, 16 },
> > +};
> > +
> > +struct hisi_event_list {
> > +	struct list_head list;
> > +	struct perf_event *event;
> > +};
> > +
> > +struct hisi_pcie_pmu {
> > +	struct pmu pmu;
> > +	void __iomem *regs;
> > +	cpumask_t associated_cpus;
> > +	int on_cpu;
> > +	struct hlist_node node;
> > +	DECLARE_BITMAP(pmu_events, HISI_PP_EVENTS);
> > +	struct hisi_event_list events[HISI_PP_EVENTS];
> > +	struct hrtimer timer;
> > +	struct list_head event_list;
> > +};
> > +
> > +#define to_hisi_pcie_pmu(p) container_of((p), struct hisi_pcie_pmu, pmu)
> > +
> > +int hisi_pcie_pmu_online_cpu(unsigned int cpu, struct hlist_node *node)
> > +{
> > +	struct hisi_pcie_pmu *dev_info = hlist_entry_safe(node,
> > +							 struct hisi_pcie_pmu,
> > +							 node);
> > +
> > +	cpumask_set_cpu(cpu, &dev_info->associated_cpus);
> > +	/* If another CPU is already managing this PMU, simply return. */
> > +	if (dev_info->on_cpu != -1)
> > +		return 0;
> > +
> > +	/* Use this CPU in cpumask for event counting */
> > +	dev_info->on_cpu = cpu;
> > +
> > +	return 0;
> > +}
> > +
> > +int hisi_pcie_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
> > +{
> > +	struct hisi_pcie_pmu *dev_info = hlist_entry_safe(node,
> > +							 struct hisi_pcie_pmu,
> > +							 node);
> > +	cpumask_t pmu_online_cpus;
> > +	unsigned int target;
> > +
> > +	if (!cpumask_test_and_clear_cpu(cpu, &dev_info->associated_cpus))
> > +		return 0;
> > +
> > +	if (dev_info->on_cpu != cpu)
> > +		return 0;
> > +
> > +	/* Give up ownership of the PMU */
> > +	dev_info->on_cpu = -1;
> > +
> > +	/* Choose a new CPU to migrate ownership of the PMU to */
> > +	cpumask_and(&pmu_online_cpus, &dev_info->associated_cpus,
> > +		    cpu_online_mask);
> > +	target = cpumask_any_but(&pmu_online_cpus, cpu);
> > +	if (target >= nr_cpu_ids)
> > +		return 0;
> > +
> > +	/* Use this CPU for event counting */
> > +	dev_info->on_cpu = target;
> > +	perf_pmu_migrate_context(&dev_info->pmu, cpu, target);
> > +
> > +	return 0;
> > +}
> > +
> > +void hisi_pcie_pmu_event_update(struct perf_event *event)
> > +{
> > +	struct hisi_pcie_pmu *dev_info = to_hisi_pcie_pmu(event->pmu);
> > +	struct hw_perf_event *hwc = &event->hw;
> > +	u64 delta, prev_raw_count, new_raw_count;
> > +	u64 offset = hisi_pcie_cnt_info[hwc->config_base].reg_offset;
> > +	u8 period = hisi_pcie_cnt_info[hwc->config_base].bits;
> > +
> > +	do {
> > +		new_raw_count = readl(dev_info->regs + offset);
> > +		prev_raw_count = local64_read(&hwc->prev_count);
> > +	} while (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
> > +				 new_raw_count) != prev_raw_count);
> > +
> > +	delta = (new_raw_count - prev_raw_count) & HISI_MAX_PERIOD(period);
> > +	local64_add(delta, &event->count);
> > +}
> > +
> > +static enum hrtimer_restart event_read(struct hrtimer *timer)
> > +{
> > +	struct hisi_pcie_pmu *dev_info =
> > +		container_of(timer, struct hisi_pcie_pmu, timer);
> > +	struct hisi_event_list *hevent;
> > +
> > +	list_for_each_entry(hevent, &dev_info->event_list, list)
> > +		hisi_pcie_pmu_event_update(hevent->event);
> > +	hrtimer_forward_now(timer, HISI_PP_TIMER_PERIOD_NS);
> > +
> > +	return HRTIMER_RESTART;
> > +}
> > +
> > +int hisi_pcie_pmu_event_init(struct perf_event *event)
> > +{
> > +	struct hw_perf_event *hwc = &event->hw;
> > +	struct hisi_pcie_pmu *dev_info = to_hisi_pcie_pmu(event->pmu);
> > +
> > +	if (event->attr.type != event->pmu->type)
> > +		return -ENOENT;
> > +
> > +	if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
> > +		return -EOPNOTSUPP;
> > +
> > +	if (event->attr.exclude_user	||
> > +	    event->attr.exclude_kernel	||
> > +	    event->attr.exclude_host	||
> > +	    event->attr.exclude_guest	||
> > +	    event->attr.exclude_hv	||
> > +	    event->attr.exclude_idle)
> > +		return -EINVAL;
> > +
> > +	if (event->cpu < 0)
> > +		return -EINVAL;
> > +
> > +	hwc->idx = -1;
> > +	hwc->config_base = event->attr.config;
> > +
> > +	dev_info->events[hwc->config_base].event = event;
> > +
> > +	return 0;
> > +}
> > +
> > +void hisi_pcie_pmu_enable(struct pmu *pmu)
> > +{
> > +	struct hisi_pcie_pmu *dev_info = to_hisi_pcie_pmu(pmu);
> > +	u32 val;
> > +
> > +	if (bitmap_empty(dev_info->pmu_events, HISI_PP_EVENTS))
> > +		return;
> > +
> > +	val = readl(dev_info->regs + HISI_PP_TL_CNT_CTRL_REG);
> > +	/* Disable time period based flow counting */
> > +	val &= ~HISI_PP_TL_CNT_CTRL_TX_FLOW_CNT_TIME_MASK;
> > +	val |= HISI_PP_TL_CNT_CTRL_TX_FLOW_CNT_EN |
> > +		HISI_PP_TL_CNT_CTRL_TX_ERR_CNT_EN;
> > +	writel(val, dev_info->regs + HISI_PP_TL_CNT_CTRL_REG);
> > +}
> > +
> > +void hisi_pcie_pmu_disable(struct pmu *pmu)
> > +{
> > +	struct hisi_pcie_pmu *dev_info = to_hisi_pcie_pmu(pmu);
> > +	u32 val;
> > +	u32 new_raw_count;
> > +
> > +	new_raw_count = readl(dev_info->regs + 0x908);
> > +
> > +	val = readl(dev_info->regs + HISI_PP_TL_CNT_CTRL_REG);
> > +	val &= ~(HISI_PP_TL_CNT_CTRL_TX_FLOW_CNT_EN |
> > +		 HISI_PP_TL_CNT_CTRL_TX_ERR_CNT_EN);
> > +	writel(val, dev_info->regs + HISI_PP_TL_CNT_CTRL_REG);
> > +}
> > +
> > +void hisi_pcie_pmu_enable_event(struct perf_event *event)
> > +{
> > +	struct hisi_pcie_pmu *dev_info = to_hisi_pcie_pmu(event->pmu);
> > +	struct hw_perf_event *hwc = &event->hw;
> > +	u64 offset = hisi_pcie_cnt_info[hwc->config_base].reg_offset;
> > +
> > +	/* Register is write to clear */
> > +	local64_set(&hwc->prev_count, 0);
> > +	writel(0, dev_info->regs + offset);
> > +}
> > +
> > +void hisi_pcie_pmu_start(struct perf_event *event, int flags)
> > +{
> > +	struct hw_perf_event *hwc = &event->hw;
> > +
> > +	if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED)))
> > +		return;
> > +
> > +	WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
> > +	hwc->state = 0;
> > +
> > +	hisi_pcie_pmu_enable_event(event);
> > +	perf_event_update_userpage(event);
> > +}
> > +
> > +void hisi_pcie_pmu_stop(struct perf_event *event, int flags)
> > +{
> > +	struct hw_perf_event *hwc = &event->hw;
> > +
> > +	WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
> > +	hwc->state |= PERF_HES_STOPPED;
> > +
> > +	if (hwc->state & PERF_HES_UPTODATE)
> > +		return;
> > +
> > +	/* Read hardware counter and update the perf counter statistics */
> > +	hisi_pcie_pmu_event_update(event);
> > +	hwc->state |= PERF_HES_UPTODATE;
> > +}
> > +
> > +int hisi_pcie_pmu_add(struct perf_event *event, int flags)
> > +{
> > +	struct hisi_pcie_pmu *dev_info = to_hisi_pcie_pmu(event->pmu);
> > +	struct hw_perf_event *hwc = &event->hw;
> > +	bool prev_empty;
> > +
> > +	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
> > +	set_bit(hwc->config_base, dev_info->pmu_events);
> > +	if (flags & PERF_EF_START)
> > +		hisi_pcie_pmu_start(event, PERF_EF_RELOAD);
> > +	prev_empty = list_empty(&dev_info->event_list);
> > +	list_add(&dev_info->events[hwc->config_base].list,
> > +		 &dev_info->event_list);
> > +	if (prev_empty)
> > +		hrtimer_start(&dev_info->timer, HISI_PP_TIMER_PERIOD_NS,
> > +			      HRTIMER_MODE_REL);
> > +
> > +	return 0;
> > +}
> > +
> > +
> > +void hisi_pcie_pmu_del(struct perf_event *event, int flags)
> > +{
> > +	struct hisi_pcie_pmu *dev_info = to_hisi_pcie_pmu(event->pmu);
> > +	struct hw_perf_event *hwc = &event->hw;
> > +
> > +	list_del(&dev_info->events[hwc->config_base].list);
> > +	if (list_empty(&dev_info->event_list))
> > +		hrtimer_cancel(&dev_info->timer);
> > +	hisi_pcie_pmu_stop(event, PERF_EF_UPDATE);
> > +	clear_bit(hwc->config_base, dev_info->pmu_events);
> > +	perf_event_update_userpage(event);
> > +}
> > +
> > +ssize_t hisi_event_sysfs_show(struct device *dev,
> > +			      struct device_attribute *attr, char *page)
> > +{
> > +	struct dev_ext_attribute *eattr;
> > +
> > +	eattr = container_of(attr, struct dev_ext_attribute, attr);
> > +
> > +	return sprintf(page, "config=0x%lx\n", (unsigned long)eattr->var);
> > +}
> > +
> > +void hisi_pcie_pmu_read(struct perf_event *event)
> > +{
> > +	hisi_pcie_pmu_event_update(event);
> > +}
> > +
> > +ssize_t hisi_cpumask_sysfs_show(struct device *dev,
> > +				struct device_attribute *attr, char *buf)
> > +{
> > +	struct pmu *pmu = dev_get_drvdata(dev);
> > +	struct hisi_pcie_pmu *dev_info =
> > +		container_of(pmu, struct hisi_pcie_pmu, pmu);
> > +
> > +	return sprintf(buf, "%d\n", dev_info->on_cpu);
> > +}
> > +
> > +static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL);
> > +
> > +static struct attribute *hisi_pcie_pmu_cpumask_attrs[] = {
> > +	&dev_attr_cpumask.attr,
> > +	NULL,
> > +};
> > +
> > +static const struct attribute_group hisi_pcie_pmu_cpumask_attr_group = {
> > +	.attrs = hisi_pcie_pmu_cpumask_attrs,
> > +};
> > +
> > +#define HISI_PP_ATTR(_name, _func, _config)			\
> > +	(&((struct dev_ext_attribute[]) {				\
> > +		{ __ATTR(_name, 0444, _func, NULL), (void *)_config }   \
> > +	})[0].attr.attr)
> > +
> > +#define HISI_PP_EVENT_ATTR(_name, _config)		\
> > +	HISI_PP_ATTR(_name, hisi_event_sysfs_show, (unsigned long)_config)
> > +
> > +static struct attribute *hisi_pcie_pmu_events_attr[] = {
> > +	HISI_PP_EVENT_ATTR(tx_mem_rd, TX_MEM_RD),
> > +	HISI_PP_EVENT_ATTR(tx_mem_wr, TX_MEM_WR),
> > +	HISI_PP_EVENT_ATTR(tx_cfg_rd, TX_CFG_RD),
> > +	HISI_PP_EVENT_ATTR(tx_cfg_wr, TX_CFG_WR),
> > +	HISI_PP_EVENT_ATTR(tx_io_rd, TX_IO_RD),
> > +	HISI_PP_EVENT_ATTR(tx_io_wr, TX_IO_WR),
> > +	HISI_PP_EVENT_ATTR(tx_msg, TX_MSG),
> > +
> > +	HISI_PP_EVENT_ATTR(tx_tlp, TX_TLP),
> > +	HISI_PP_EVENT_ATTR(tx_payload, TX_PAYLOAD),
> > +	HISI_PP_EVENT_ATTR(tx_dw, TX_DW),
> > +
> > +	HISI_PP_EVENT_ATTR(tx_cpl, TX_CPL),
> > +	HISI_PP_EVENT_ATTR(tx_ccix_tlp, TX_CCIX),
> > +	HISI_PP_EVENT_ATTR(tx_atomic_tlp, TX_ATOMIC),
> > +	HISI_PP_EVENT_ATTR(tx_p2p_tlp, TX_P2P),
> > +
> > +	HISI_PP_EVENT_ATTR(rx_tlp, RX_TOTAL_TLP),
> > +	HISI_PP_EVENT_ATTR(rx_tr_tlp, RX_TOTAL_TR),
> > +	HISI_PP_EVENT_ATTR(rx_posted_tlp, RX_POSTED),
> > +	HISI_PP_EVENT_ATTR(rx_nonposted_tlp, RX_NONPOSTED),
> > +	HISI_PP_EVENT_ATTR(rx_cpl_tlp, RX_CPL),
> > +	NULL,
> > +};
> > +
> > +static struct attribute_group hisi_pcie_pmu_events_group = {
> > +	.name = "events",
> > +	.attrs = hisi_pcie_pmu_events_attr,
> > +};
> > +
> > +static const struct attribute_group *hisi_pcie_pmu_attr_groups[] = {
> > +	&hisi_pcie_pmu_events_group,
> > +	&hisi_pcie_pmu_cpumask_attr_group,
> > +	NULL,
> > +};
> > +
> > +static int hisi_pcie_pmu_probe(struct pcie_device *dev)
> > +{
> > +	struct pci_dev *pdev = dev->port;
> > +	struct acpi_device *acpi_dev;
> > +	struct resource_entry *entry;
> > +	resource_size_t regs_start, regs_size;
> > +	struct hisi_pcie_pmu *dev_info;
> > +	struct list_head list;
> > +	char *name;
> > +	int ret;
> > +
> > +	INIT_LIST_HEAD(&list);
> > +
> > +	if (pdev->vendor != PCI_VENDOR_ID_HUAWEI)
> > +		return -ENODEV;
> > +
> > +	acpi_dev = ACPI_COMPANION(&pdev->dev);
> > +	if (!acpi_dev)
> > +		return -ENODEV;
> > +
> > +	ret = acpi_dev_get_resources(acpi_dev, &list, NULL, NULL);
> > +	if (ret < 0) {
> > +		pr_err("Failed to get PMU resources, ret=%d\n", ret);
> > +		return ret;
> > +	}
> > +	entry = list_first_entry(&list, struct resource_entry, node);
> > +	if (entry) {
> > +		regs_start = entry->res->start;
> > +		regs_size = resource_size(entry->res);
> > +		ret = 0;
> > +	} else
> > +		ret = -EINVAL;
> > +	acpi_dev_free_resource_list(&list);
> > +	if (ret)
> > +		return ret;
> > +
> > +	dev_info = devm_kzalloc(&pdev->dev, sizeof(*dev_info), GFP_KERNEL);
> > +	if (!dev_info)
> > +		return -ENOMEM;
> > +
> > +	hrtimer_init(&dev_info->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
> > +	dev_info->timer.function = event_read;
> > +
> > +	INIT_LIST_HEAD(&dev_info->event_list);
> > +	dev_info->regs = devm_ioremap_nocache(&pdev->dev, regs_start,
> > +					      regs_size);
> > +	if (!dev_info->regs)
> > +		return -EINVAL;
> > +	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_pcie_port%04x_%02x",
> > +			      pdev->bus->number,
> > +			      PCI_SLOT(pdev->devfn));
> > +	if (!name)
> > +		return -ENOMEM;
> > +
> > +	dev_info->pmu = (struct pmu) {
> > +		.name = name,
> > +		.task_ctx_nr = perf_invalid_context,
> > +		.event_init = hisi_pcie_pmu_event_init,
> > +		.pmu_enable = hisi_pcie_pmu_enable,
> > +		.pmu_disable = hisi_pcie_pmu_disable,
> > +		.add = hisi_pcie_pmu_add,
> > +		.del = hisi_pcie_pmu_del,
> > +		.start = hisi_pcie_pmu_start,
> > +		.stop = hisi_pcie_pmu_stop,
> > +		.read = hisi_pcie_pmu_read,
> > +		.attr_groups = hisi_pcie_pmu_attr_groups,
> > +		.capabilities = PERF_PMU_CAP_NO_INTERRUPT,
> > +	};
> > +
> > +
> > +	ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE,
> > +				       &dev_info->node);
> > +	if (ret) {
> > +		dev_err(&pdev->dev, "Error %d registering hotplug;\n", ret);
> > +		return ret;
> > +	}
> > +
> > +	ret = perf_pmu_register(&dev_info->pmu, name, -1);
> > +	if (ret) {
> > +		cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE,
> > +					    &dev_info->node);
> > +
> > +		return ret;
> > +	}
> > +
> > +	dev_set_drvdata(&pdev->dev, dev_info);
> > +
> > +	return 0;
> > +}
> > +
> > +static void hisi_pcie_pmu_remove(struct pcie_device *dev)
> > +{
> > +	struct hisi_pcie_pmu *dev_info = dev_get_drvdata(&dev->port->dev);
> > +
> > +	perf_pmu_unregister(&dev_info->pmu);
> > +	cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE,
> > +				    &dev_info->node);
> > +}
> > +
> > +static struct pcie_port_service_driver hisi_pcie_pmu = {
> > +	.name = "hisi_pcie_root_port_pmu",
> > +	.port_type = PCIE_ANY_PORT,
> > +	.service = PCIE_PORT_SERVICE_PMU,
> > +	.probe = hisi_pcie_pmu_probe,
> > +	.remove = hisi_pcie_pmu_remove,
> > +};
> > +
> > +static int __init hisi_pcie_service_init(void)
> > +{
> > +	int ret;
> > +
> > +	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE,
> > +				      "AP_PERF_ARM_HISI_PCIE_ONLINE",
> > +				      hisi_pcie_pmu_online_cpu,
> > +				      hisi_pcie_pmu_offline_cpu);
> > +	if (ret) {
> > +		pr_err("PCIE PMU: setup hotplug, ret = %d\n", ret);
> > +		return ret;
> > +	}
> > +
> > +	pcie_port_service_register(&hisi_pcie_pmu);
> > +
> > +	return 0;
> > +}
> > +
> > +static void hisi_pcie_service_remove(void)
> > +{
> > +	pcie_port_service_unregister(&hisi_pcie_pmu);
> > +	cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE);
> > +}
> > +module_init(hisi_pcie_service_init);
> > +module_exit(hisi_pcie_service_remove);
> > +MODULE_LICENSE("GPL");
> > diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
> > index e0cd2baa8380..73f2bc8a7201 100644
> > --- a/include/linux/cpuhotplug.h
> > +++ b/include/linux/cpuhotplug.h
> > @@ -161,6 +161,7 @@ enum cpuhp_state {
> >  	CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE,
> >  	CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE,
> >  	CPUHP_AP_PERF_ARM_HISI_L3_ONLINE,
> > +	CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE,
> >  	CPUHP_AP_PERF_ARM_L2X0_ONLINE,
> >  	CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE,
> >  	CPUHP_AP_PERF_ARM_QCOM_L3_ONLINE,
> > -- 
> > 2.19.1
> > 
> > 
> > _______________________________________________
> > linux-arm-kernel mailing list
> > linux-arm-kernel@...ts.infradead.org
> > http://lists.infradead.org/mailman/listinfo/linux-arm-kernel  

Powered by blists - more mailing lists