[v8,4/9] ACPI: Introduce CPU performance controls using CPPC

Commit Message

Ashwin Chaugule Aug. 5, 2015, 1:40 p.m. UTC

CPPC stands for Collaborative Processor Performance Controls
and is defined in the ACPI v5.0+ spec. It describes CPU
performance controls on an abstract and continuous scale
allowing the platform (e.g. remote power processor) to flexibly
optimize CPU performance with its knowledge of power budgets
and other architecture specific knowledge.

This patch adds a shim which exports commonly used functions
to get and set CPPC specific controls for each CPU. This enables
CPUFreq drivers to gather per CPU performance data and use
with exisiting governors or even allows for customized governors
which are implemented inside CPUFreq drivers.

Signed-off-by: Ashwin Chaugule <[e-mail]>
Reviewed-by: Al Stone <[e-mail]>
---
 drivers/acpi/Kconfig     |  14 +
 drivers/acpi/Makefile    |   1 +
 drivers/acpi/cppc_acpi.c | 812 +++++++++++++++++++++++++++++++++++++++++++++++
 include/acpi/cppc_acpi.h | 137 ++++++++
 4 files changed, 964 insertions(+)
 create mode 100644 drivers/acpi/cppc_acpi.c
 create mode 100644 include/acpi/cppc_acpi.h

Comments

Rafael J. Wysocki Aug. 26, 2015, 1:46 a.m. UTC | #1

On Wednesday, August 05, 2015 09:40:27 AM Ashwin Chaugule wrote:
> CPPC stands for Collaborative Processor Performance Controls
> and is defined in the ACPI v5.0+ spec. It describes CPU
> performance controls on an abstract and continuous scale
> allowing the platform (e.g. remote power processor) to flexibly
> optimize CPU performance with its knowledge of power budgets
> and other architecture specific knowledge.
> 
> This patch adds a shim which exports commonly used functions
> to get and set CPPC specific controls for each CPU. This enables
> CPUFreq drivers to gather per CPU performance data and use
> with exisiting governors or even allows for customized governors
> which are implemented inside CPUFreq drivers.
> 
> Signed-off-by: Ashwin Chaugule <[e-mail]>
> Reviewed-by: Al Stone <[e-mail]>
> ---
>  drivers/acpi/Kconfig     |  14 +
>  drivers/acpi/Makefile    |   1 +
>  drivers/acpi/cppc_acpi.c | 812 +++++++++++++++++++++++++++++++++++++++++++++++
>  include/acpi/cppc_acpi.h | 137 ++++++++
>  4 files changed, 964 insertions(+)
>  create mode 100644 drivers/acpi/cppc_acpi.c
>  create mode 100644 include/acpi/cppc_acpi.h
> 
> diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
> index 54e9729..c6ec903 100644
> --- a/drivers/acpi/Kconfig
> +++ b/drivers/acpi/Kconfig
> @@ -197,6 +197,20 @@ config ACPI_PROCESSOR_IDLE
>  	bool
>  	select CPU_IDLE
>  
> +config ACPI_CPPC_LIB
> +	bool
> +	depends on ACPI_PROCESSOR
> +	depends on !ACPI_CPU_FREQ_PSS
> +	select MAILBOX
> +	select PCC
> +	help
> +	  This file implements common functionality to parse

It's better to start with "If this option is enabled".

> +	  CPPC tables as described in the ACPI 5.1+ spec. The
> +	  routines implemented are meant to be used by other
> +	  drivers to control CPU performance using CPPC semantics.
> +	  If your platform does not support CPPC in firmware,
> +	  leave this option disabled.
> +
>  config ACPI_PROCESSOR
>  	tristate "Processor"
>  	depends on X86 || IA64
> diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
> index 3ea59ae..4c393a69 100644
> --- a/drivers/acpi/Makefile
> +++ b/drivers/acpi/Makefile
> @@ -78,6 +78,7 @@ obj-$(CONFIG_ACPI_HED)		+= hed.o
>  obj-$(CONFIG_ACPI_EC_DEBUGFS)	+= ec_sys.o
>  obj-$(CONFIG_ACPI_CUSTOM_METHOD)+= custom_method.o
>  obj-$(CONFIG_ACPI_BGRT)		+= bgrt.o
> +obj-$(CONFIG_ACPI_CPPC_LIB)	+= cppc_acpi.o
>  
>  # processor has its own "processor." module_param namespace
>  processor-y			:= processor_driver.o
> diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
> new file mode 100644
> index 0000000..9c89767
> --- /dev/null
> +++ b/drivers/acpi/cppc_acpi.c
> @@ -0,0 +1,812 @@
> +/*
> + * CPPC (Collaborative Processor Performance Control) methods used
> + * by CPUfreq drivers.

One line please.

> + *
> + * (C) Copyright 2014, 2015 Linaro Ltd.
> + * Author: Ashwin Chaugule <[e-mail]>
> + *
> + * This program is free software; you can redistribute it and/or
> + * modify it under the terms of the GNU General Public License
> + * as published by the Free Software Foundation; version 2
> + * of the License.
> + *
> + * CPPC describes a few methods for controlling CPU performance using
> + * information from a per CPU table called CPC. This table is described in
> + * the ACPI v5.0+ specification. The table consists of a list of
> + * registers which may be memory mapped or hardware registers and also may
> + * include some static integer values.
> + *
> + * CPU performance is on an abstract continuous scale as against a discretized
> + * P-state scale which is tied to CPU frequency only. In brief, the basic
> + * operation involves:
> + *
> + * - OS makes a CPU performance request. (Can provide min and max bounds)
> + *
> + * - Platform (such as BMC) is free to optimize request within requested bounds
> + *   depending on power/thermal budgets etc.
> + *
> + * - Platform conveys its decision back to OS
> + *
> + * The communication between OS and platform occurs through another medium
> + * called (PCC) Platform Communication Channel. This is a generic mailbox like
> + * mechanism which includes doorbell semantics to indicate register updates.
> + * See drivers/mailbox/pcc.c for details on PCC.
> + *
> + * Finer details about the PCC and CPPC spec are available in the latest
> + * ACPI 5.1 specification.

ACPI 5.1 is not the latest any more.  I'd say "ACPI 6.0 or later" to be on the
safe side.

> + */
> +
> +#define pr_fmt(fmt)	"ACPI CPPC: " fmt
> +
> +#include <linux/cpufreq.h>
> +#include <linux/delay.h>
> +
> +#include <acpi/cppc_acpi.h>
> +/*
> + * Lock to provide mutually exclusive access to the PCC
> + * channel. e.g. When the remote updates the shared region
> + * with new data, the reader needs to be protected from
> + * other CPUs activity on the same channel.
> + */
> +static DEFINE_SPINLOCK(pcc_lock);
> +
> +static DEFINE_PER_CPU(struct cpc_desc *, cpc_desc_ptr);

A description of what the per-CPU thing is and how it is used would be good
to have here.

> +
> +/* This layer handles all the PCC specifics for CPPC. */
> +static struct mbox_chan *pcc_channel;
> +static void __iomem *pcc_comm_addr;
> +static u64 comm_base_addr;
> +static int pcc_subspace_idx = -1;
> +static u16 pcc_cmd_delay;
> +static int pcc_channel_acquired;
> +
> +#define NUM_RETRIES 500

How did you get that number?

> +
> +static int send_pcc_cmd(u16 cmd)
> +{
> +	int err, result = 0;
> +	int retries = NUM_RETRIES;
> +	struct acpi_pcct_hw_reduced *pcct_ss = pcc_channel->con_priv;
> +	struct acpi_pcct_shared_memory *generic_comm_base =
> +		(struct acpi_pcct_shared_memory *) pcc_comm_addr;
> +	u32 cmd_latency = pcct_ss->latency;
> +
> +	/* Write to the shared comm region. */
> +	writew(cmd, &generic_comm_base->command);
> +
> +	/* Flip CMD COMPLETE bit */
> +	writew(0, &generic_comm_base->status);
> +
> +	err = mbox_send_message(pcc_channel, &cmd);
> +	if (err < 0) {
> +		pr_err("Err sending PCC mbox message. cmd:%d, ret:%d\n",
> +				cmd, err);
> +		return err;
> +	}
> +
> +	/* Wait for a nominal time to let platform processes command. */
> +	udelay(cmd_latency);
> +
> +	/* Retry in case the remote processor was too slow to catch up. */
> +	while (retries--) {

It looks like this can be written as

	for (retries = NUM_RETRIES; retries > 0; retries--) {

> +		result = readw_relaxed(&generic_comm_base->status)
> +			& PCC_CMD_COMPLETE ? 0 : -EIO;

I'm not sure why do you need the ternary operator here.

You could just do

		if (readw_relaxed(&generic_comm_base->status) & PCC_CMD_COMPLETE) {
			result = 0;
			break;
		}

and set "result" to -EIO beforehand.

> +		if (!result) {
> +			/* Success. */
> +			retries = NUM_RETRIES;

We break out of the loop in the next statement, so why is this needed?

BTW, why do you need both "err" and "result"?  Why not to use "result"
everywhere?


> +			break;
> +		}
> +	}
> +
> +	mbox_client_txdone(pcc_channel, result);
> +	return result;
> +}
> +
> +static void cppc_chan_tx_done(struct mbox_client *cl, void *mssg, int ret)
> +{
> +	if (ret)
> +		pr_debug("TX did not complete: CMD sent:%x, ret:%d\n",
> +				*(u16 *)mssg, ret);
> +	else
> +		pr_debug("TX completed. CMD sent:%x, ret:%d\n",
> +				*(u16 *)mssg, ret);

It would be good to identify the client somehow in these messages.  Otherwise
they may not be quite useful.

> +}
> +
> +struct mbox_client cppc_mbox_cl = {
> +	.tx_done = cppc_chan_tx_done,
> +	.knows_txdone = true,
> +};
> +
> +static int acpi_get_psd(struct cpc_desc *cpc_ptr, acpi_handle handle)
> +{
> +	int result = 0;
> +	acpi_status status = AE_OK;
> +	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
> +	struct acpi_buffer format = {sizeof("NNNNN"), "NNNNN"};
> +	struct acpi_buffer state = {0, NULL};
> +	union acpi_object  *psd = NULL;
> +	struct acpi_psd_package *pdomain;
> +
> +	status = acpi_evaluate_object(handle, "_PSD", NULL, &buffer);
> +	if (ACPI_FAILURE(status))
> +		return -ENODEV;
> +
> +	psd = buffer.pointer;
> +	if (!psd || (psd->type != ACPI_TYPE_PACKAGE)) {
> +		pr_err("Invalid _PSD data\n");
> +		result = -ENODATA;
> +		goto end;
> +	}

acpi_evaluate_object_typed() can be used here and then you save one "if".

> +
> +	if (psd->package.count != 1) {
> +		pr_err("Invalid _PSD data\n");
> +		result = -ENODATA;
> +		goto end;
> +	}
> +
> +	pdomain = &(cpc_ptr->domain_info);
> +
> +	state.length = sizeof(struct acpi_psd_package);
> +	state.pointer = pdomain;
> +

So beyond this point, if there's an error, you always set "result" to -ENODATA.
Why not to set it to -ENODATA upfront and then reset it to 0 on success only?
That would save you a bunch of statements.

> +	status = acpi_extract_package(&(psd->package.elements[0]),
> +		&format, &state);
> +	if (ACPI_FAILURE(status)) {
> +		pr_err("Invalid _PSD data\n");

Why is that error priority and what can users see from the error message?

Same pretty much everywhere below?

> +		result = -ENODATA;
> +		goto end;
> +	}
> +
> +	if (pdomain->num_entries != ACPI_PSD_REV0_ENTRIES) {
> +		pr_err("Unknown _PSD:num_entries\n");
> +		result = -ENODATA;
> +		goto end;
> +	}
> +
> +	if (pdomain->revision != ACPI_PSD_REV0_REVISION) {
> +		pr_err("Unknown _PSD:revision\n");
> +		result = -ENODATA;
> +		goto end;
> +	}
> +
> +	if (pdomain->coord_type != DOMAIN_COORD_TYPE_SW_ALL &&
> +	    pdomain->coord_type != DOMAIN_COORD_TYPE_SW_ANY &&
> +	    pdomain->coord_type != DOMAIN_COORD_TYPE_HW_ALL) {
> +		pr_err("Invalid _PSD:coord_type\n");
> +		result = -ENODATA;
> +		goto end;
> +	}
> +end:
> +	kfree(buffer.pointer);
> +	return result;
> +}
> +
> +int acpi_get_psd_map(struct cpudata **all_cpu_data)
> +{
> +	int count_target;
> +	int retval = 0;
> +	unsigned int i, j;
> +	cpumask_var_t covered_cpus;
> +	struct cpudata *pr, *match_pr;
> +	struct acpi_psd_package *pdomain;
> +	struct acpi_psd_package *match_pdomain;
> +	struct cpc_desc *cpc_ptr, *match_cpc_ptr;
> +
> +	if (!zalloc_cpumask_var(&covered_cpus, GFP_KERNEL))
> +		return -ENOMEM;
> +
> +	/*
> +	 * Now that we have _PSD data from all CPUs, lets setup P-state
> +	 * domain info.
> +	 */
> +	for_each_possible_cpu(i) {
> +		pr = all_cpu_data[i];
> +		if (!pr)
> +			continue;
> +
> +		if (cpumask_test_cpu(i, covered_cpus))
> +			continue;
> +
> +		cpc_ptr = per_cpu(cpc_desc_ptr, i);
> +		if (!cpc_ptr)
> +			continue;

Well, is this actually safe?  What if we have CPPC control for some CPUs in a
domain only?

> +
> +		pdomain = &(cpc_ptr->domain_info);
> +		cpumask_set_cpu(i, pr->shared_cpu_map);
> +		cpumask_set_cpu(i, covered_cpus);
> +		if (pdomain->num_processors <= 1)
> +			continue;
> +
> +		/* Validate the Domain info */
> +		count_target = pdomain->num_processors;
> +		if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ALL)
> +			pr->shared_type = CPUFREQ_SHARED_TYPE_ALL;
> +		else if (pdomain->coord_type == DOMAIN_COORD_TYPE_HW_ALL)
> +			pr->shared_type = CPUFREQ_SHARED_TYPE_HW;
> +		else if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ANY)
> +			pr->shared_type = CPUFREQ_SHARED_TYPE_ANY;
> +
> +		for_each_possible_cpu(j) {
> +			if (i == j)
> +				continue;
> +
> +			match_cpc_ptr = per_cpu(cpc_desc_ptr, j);
> +			if (!match_cpc_ptr)
> +				continue;
> +
> +			match_pdomain = &(match_cpc_ptr->domain_info);
> +			if (match_pdomain->domain != pdomain->domain)
> +				continue;
> +
> +			/* Here i and j are in the same domain */
> +
> +			if (match_pdomain->num_processors != count_target) {
> +				retval = -EINVAL;

So we do bail out here, so why don't we bail out on any errors?  Why do we
silently ignore some of them (like NULL cpc_ptr above)?

> +				goto err_ret;
> +			}
> +
> +			if (pdomain->coord_type != match_pdomain->coord_type) {
> +				retval = -EINVAL;
> +				goto err_ret;
> +			}
> +
> +			cpumask_set_cpu(j, covered_cpus);
> +			cpumask_set_cpu(j, pr->shared_cpu_map);
> +		}
> +
> +		for_each_possible_cpu(j) {

Why do we need a separate loop over all CPUs for this?  Could not the loops
be combined?

> +			if (i == j)
> +				continue;
> +
> +			match_pr = all_cpu_data[j];
> +			if (!match_pr)
> +				continue;
> +
> +			match_cpc_ptr = per_cpu(cpc_desc_ptr, j);
> +			if (!match_cpc_ptr)
> +				continue;
> +
> +			match_pdomain = &(match_cpc_ptr->domain_info);
> +			if (match_pdomain->domain != pdomain->domain)
> +				continue;
> +
> +			match_pr->shared_type = pr->shared_type;
> +			cpumask_copy(match_pr->shared_cpu_map,
> +				     pr->shared_cpu_map);
> +		}
> +	}
> +
> +err_ret:
> +	for_each_possible_cpu(i) {
> +		pr = all_cpu_data[i];
> +		if (!pr)
> +			continue;
> +
> +		/* Assume no coordination on any error parsing domain info */
> +		if (retval) {
> +			cpumask_clear(pr->shared_cpu_map);
> +			cpumask_set_cpu(i, pr->shared_cpu_map);
> +			pr->shared_type = CPUFREQ_SHARED_TYPE_ALL;
> +		}
> +	}
> +
> +	free_cpumask_var(covered_cpus);
> +	return retval;
> +}
> +EXPORT_SYMBOL_GPL(acpi_get_psd_map);
> +
> +static int register_pcc_channel(unsigned pcc_subspace_idx)
> +{
> +	struct acpi_pcct_subspace *cppc_ss;
> +	unsigned int len;
> +
> +	if (pcc_subspace_idx >= 0) {

I'd check the reverse (ie. < 0) here and return immediately if that's the case. 

> +		pcc_channel = pcc_mbox_request_channel(&cppc_mbox_cl,
> +				pcc_subspace_idx);
> +
> +		if (IS_ERR(pcc_channel)) {
> +			pr_err("No PCC communication channel found\n");
> +			return -ENODEV;
> +		}
> +
> +		/*
> +		 * The PCC mailbox controller driver should
> +		 * have parsed the PCCT (global table of all
> +		 * PCC channels) and stored pointers to the
> +		 * subspace communication region in con_priv.
> +		 */
> +		cppc_ss = pcc_channel->con_priv;
> +
> +		if (!cppc_ss) {
> +			pr_err("No PCC subspace found for CPPC\n");
> +			return -ENODEV;
> +		}
> +
> +		/*
> +		 * This is the shared communication region
> +		 * for the OS and Platform to communicate over.
> +		 */
> +		comm_base_addr = cppc_ss->base_address;
> +		len = cppc_ss->length;
> +		pcc_cmd_delay = cppc_ss->min_turnaround_time;
> +
> +		pcc_comm_addr = ioremap(comm_base_addr, len);
> +		if (!pcc_comm_addr) {
> +			pr_err("Failed to ioremap PCC comm region mem\n");
> +			return -ENOMEM;
> +		}
> +
> +		/* Set flag so that we dont come here for each CPU. */
> +		pcc_channel_acquired = 1;

Should pcc_channel_acquired be a bool variable rather?

> +
> +	} else
> +		/*
> +		 * For the case where registers are not defined as PCC regs.
> +		 * Assuming all regs are FFH / SystemIO.
> +		 */
> +		pr_debug("No PCC subspace detected in any CPC entries.\n");
> +
> +	return 0;
> +}
> +
> +/**
> + * acpi_cppc_processor_probe - The _CPC table is a per CPU table

One line description here, please.

> + * which a bunch of entries which may be registers or integers.

Move the example to a separate comment above the kerneldoc.

> + * An example table looks like the following.
> + *
> + *	Name(_CPC, Package()
> + *			{
> + *			17,
> + *			NumEntries
> + *			1,
> + *			// Revision
> + *			ResourceTemplate(){Register(PCC, 32, 0, 0x120, 2)},
> + *			// Highest Performance
> + *			ResourceTemplate(){Register(PCC, 32, 0, 0x124, 2)},
> + *			// Nominal Performance
> + *			ResourceTemplate(){Register(PCC, 32, 0, 0x128, 2)},
> + *			// Lowest Nonlinear Performance
> + *			ResourceTemplate(){Register(PCC, 32, 0, 0x12C, 2)},
> + *			// Lowest Performance
> + *			ResourceTemplate(){Register(PCC, 32, 0, 0x130, 2)},
> + *			// Guaranteed Performance Register
> + *			ResourceTemplate(){Register(PCC, 32, 0, 0x110, 2)},
> + *			// Desired Performance Register
> + *			ResourceTemplate(){Register(SystemMemory, 0, 0, 0, 0)},
> + *			..
> + *			..
> + *			..
> + *
> + *		}
> + * Each Register() encodes how to access that specific register.
> + * e.g. a sample PCC entry has the following encoding:
> + *
> + *	Register (
> + *		PCC,
> + *		AddressSpaceKeyword
> + *		8,
> + *		//RegisterBitWidth
> + *		8,
> + *		//RegisterBitOffset
> + *		0x30,
> + *		//RegisterAddress
> + *		9
> + *		//AccessSize (subspace ID)
> + *		0
> + *		)
> + *		}
> + *
> + *	This function walks through all the per CPU _CPC entries and extracts
> + *	the Register details.
> + *
> + *	Return: 0 for success or negative value for err.

And the argument needs to be documented in the kerneldoc too.

> + */
> +int acpi_cppc_processor_probe(struct acpi_processor *pr)
> +{
> +	struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL};
> +	union acpi_object *out_obj, *cpc_obj;
> +	struct cpc_desc *cpc_ptr;
> +	struct cpc_reg *gas_t;
> +	acpi_handle handle = pr->handle;
> +	unsigned int num_ent, i, cpc_rev, ret = 0;
> +	acpi_status status;
> +
> +	/* Parse the ACPI _CPC table for this cpu. */
> +	if (!acpi_has_method(handle, "_CPC")) {
> +		pr_debug("_CPC table not found\n");
> +		ret = -ENODEV;
> +		goto out_buf_free;
> +	}

You don't need to do the above (the below will fail if _CPC is not present)
and I'm not sure if the debug message is worth it.

> +
> +	status = acpi_evaluate_object(handle, "_CPC", NULL, &output);
> +	if (ACPI_FAILURE(status)) {
> +		ret = -ENODEV;
> +		goto out_buf_free;
> +	}
> +
> +	out_obj = (union acpi_object *) output.pointer;
> +	if (out_obj->type != ACPI_TYPE_PACKAGE) {
> +		ret = -ENODEV;
> +		goto out_buf_free;
> +	}

Again, acpi_evaluate_object_typed() would save you one branch.

> +
> +	cpc_ptr = kzalloc(sizeof(struct cpc_desc), GFP_KERNEL);
> +	if (!cpc_ptr)
> +		return -ENOMEM;
> +
> +	/* First entry is NumEntries. */
> +	cpc_obj = &out_obj->package.elements[0];
> +	if (cpc_obj->type == ACPI_TYPE_INTEGER)	{
> +		num_ent = cpc_obj->integer.value;
> +	} else {
> +		pr_debug("Unexpected entry type(%d) for NumEntries\n",
> +				cpc_obj->type);
> +		goto out_free;
> +	}
> +
> +	/* Only support CPPCv2. Bail otherwise. */
> +	if (num_ent != CPPC_NUM_ENT) {
> +		pr_err("Firmware exports %d entries. Expected: %d\n",
> +				num_ent, CPPC_NUM_ENT);
> +		ret = -EINVAL;

Why -EINVAL?  It doesn't mean "invalid argument" surely?

> +		goto out_free;
> +	}
> +
> +	/* Second entry should be revision. */
> +	cpc_obj = &out_obj->package.elements[1];
> +	if (cpc_obj->type == ACPI_TYPE_INTEGER)	{
> +		cpc_rev = cpc_obj->integer.value;
> +	} else {
> +		pr_debug("Unexpected entry type(%d) for Revision\n",
> +				cpc_obj->type);
> +		goto out_free;
> +	}
> +
> +	if (cpc_rev != CPPC_REV) {
> +		pr_err("Firmware exports revision:%d. Expected:%d\n",
> +				cpc_rev, CPPC_REV);
> +		goto out_free;
> +	}
> +
> +	/* Iterate through remaining entries in _CPC */
> +	for (i = 2; i < num_ent; i++) {
> +		cpc_obj = &out_obj->package.elements[i];
> +
> +		if (cpc_obj->type == ACPI_TYPE_INTEGER)	{
> +			cpc_ptr->cpc_regs[i-2].type =
> +				ACPI_TYPE_INTEGER;
> +			cpc_ptr->cpc_regs[i-2].cpc_entry.int_value =
> +				cpc_obj->integer.value;
> +		} else if (cpc_obj->type == ACPI_TYPE_BUFFER) {
> +			gas_t = (struct cpc_reg *)
> +				cpc_obj->buffer.pointer;
> +
> +			/*
> +			 * The PCC Subspace index is encoded inside
> +			 * the CPC table entries. The same PCC index
> +			 * will be used for all the PCC entries,
> +			 * so extract it only once.
> +			 */
> +			if (gas_t->space_id ==
> +					ACPI_ADR_SPACE_PLATFORM_COMM) {

Please don't break lines like this.  I know that it'll be more than 80 chars,
but that's OK.  Or if you really care, you can move that code to a helper
function.

> +				if (pcc_subspace_idx < 0)
> +					pcc_subspace_idx =
> +						gas_t->access_width;
> +				else if (pcc_subspace_idx !=
> +						gas_t->access_width) {
> +					/*
> +					 * Mismatched PCC id detected.
> +					 * Firmware bug.
> +					 */
> +					goto out_free;
> +				}
> +			}
> +
> +			cpc_ptr->cpc_regs[i-2].type =
> +				ACPI_TYPE_BUFFER;
> +			cpc_ptr->cpc_regs[i-2].cpc_entry.reg =
> +				(struct cpc_reg) {
> +					.space_id = gas_t->space_id,
> +					.length	= gas_t->length,
> +					.bit_width = gas_t->bit_width,
> +					.bit_offset = gas_t->bit_offset,
> +					.address = gas_t->address,
> +					.access_width =
> +						gas_t->access_width,

Why don't you use memcpy() for copying this?

> +				};
> +		} else {
> +			pr_debug("Error in entry:%d in CPC table.\n", i);
> +			ret = -EINVAL;
> +			goto out_free;
> +		}
> +	}
> +
> +	/* Plug it into this CPUs CPC descriptor. */
> +	per_cpu(cpc_desc_ptr, pr->id) = cpc_ptr;
> +
> +	/* Parse PSD data for this CPU */
> +	ret = acpi_get_psd(cpc_ptr, handle);
> +	if (ret)
> +		goto out_free;
> +
> +	/* Register PCC channel once for all CPUs. */
> +	if (!pcc_channel_acquired) {
> +		ret = register_pcc_channel(pcc_subspace_idx);

So here's a question: What if pcc_subspace_idx for the new CPU is different
from the one we've registered the channel with?

Also, is this guaranteed to be run sequentially for all of the different CPUs?

If not, what if they race with each other here and the channel is
registered twice as a result?

> +		if (ret)
> +			goto out_free;
> +	}
> +
> +	/* Everything looks okay */
> +	pr_info("Successfully parsed CPC struct for CPU: %d\n", pr->id);
> +
> +	kfree(output.pointer);
> +	return 0;
> +
> +out_free:
> +	cpc_ptr = per_cpu(cpc_desc_ptr, pr->id);
> +	kfree(cpc_ptr);
> +
> +out_buf_free:
> +	kfree(output.pointer);
> +	return -ENODEV;
> +}
> +EXPORT_SYMBOL_GPL(acpi_cppc_processor_probe);
> +
> +static u64 cpc_trans(struct cpc_register_resource *reg, int cmd, u64 write_val,
> +		bool is_pcc)
> +{
> +	u64 addr;
> +	u64 read_val = 0;
> +
> +	/* PCC communication addr space begins at byte offset 0x8. */
> +	addr = is_pcc ? (u64)pcc_comm_addr + 0x8 + reg->cpc_entry.reg.address :
> +		reg->cpc_entry.reg.address;

Move the above to a separate function and document the formula.

> +
> +	if (reg->type == ACPI_TYPE_BUFFER) {

Quite a bit of code duplication below.  Any chance to reduce it?

> +		switch (reg->cpc_entry.reg.bit_width) {
> +		case 8:
> +			if (cmd == CMD_READ)
> +				read_val = readb((void *) (addr));
> +			else if (cmd == CMD_WRITE)
> +				writeb(write_val, (void *)(addr));
> +			else
> +				pr_debug("Unsupported cmd type: %d\n", cmd);
> +			break;
> +		case 16:
> +			if (cmd == CMD_READ)
> +				read_val = readw((void *) (addr));
> +			else if (cmd == CMD_WRITE)
> +				writew(write_val, (void *)(addr));
> +			else
> +				pr_debug("Unsupported cmd type: %d\n", cmd);
> +			break;
> +		case 32:
> +			if (cmd == CMD_READ)
> +				read_val = readl((void *) (addr));
> +			else if (cmd == CMD_WRITE)
> +				writel(write_val, (void *)(addr));
> +			else
> +				pr_debug("Unsupported cmd type: %d\n", cmd);
> +			break;
> +		case 64:
> +			if (cmd == CMD_READ)
> +				read_val = readq((void *) (addr));
> +			else if (cmd == CMD_WRITE)
> +				writeq(write_val, (void *)(addr));
> +			else
> +				pr_debug("Unsupported cmd type: %d\n", cmd);
> +			break;
> +		default:
> +			pr_debug("Unsupported bit width for CPC cmd:%d\n",
> +					cmd);
> +			break;
> +		}
> +	} else if (reg->type == ACPI_TYPE_INTEGER) {
> +		if (cmd == CMD_READ)
> +			read_val = reg->cpc_entry.int_value;
> +		else if (cmd == CMD_WRITE)
> +			reg->cpc_entry.int_value = write_val;
> +		else
> +			pr_debug("Unsupported cmd type: %d\n", cmd);
> +	} else
> +		pr_debug("Unsupported CPC entry type:%d\n", reg->type);
> +
> +	return read_val;
> +}
> +
> +/**
> + * cppc_get_perf_caps - Get a CPUs performance capabilities.
> + * @cpunum: CPU from which to get capabilities info.
> + * @perf_caps: ptr to cppc_perf_caps. See cppc_acpi.h
> + *
> + * Return - 0 for success with perf_caps populated else
> + *	-ERRNO.
> + */
> +int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps)
> +{
> +	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
> +	struct cpc_register_resource *highest_reg, *lowest_reg, *ref_perf,
> +				     *nom_perf;
> +	u64 min, max, ref, nom;
> +	bool is_pcc = false;
> +	int ret;
> +
> +	if (!cpc_desc) {
> +		pr_debug("No CPC descriptor for CPU:%d\n", cpunum);
> +		return -ENODEV;
> +	}
> +
> +	highest_reg = &cpc_desc->cpc_regs[HIGHEST_PERF];
> +	lowest_reg = &cpc_desc->cpc_regs[LOWEST_PERF];
> +	ref_perf = &cpc_desc->cpc_regs[REFERENCE_PERF];
> +	nom_perf = &cpc_desc->cpc_regs[NOMINAL_PERF];
> +
> +	spin_lock(&pcc_lock);

Are we only going to acquire this spinlock from IRQ context of from
process context or from both?  If from both, what prevents deadlocks
from happening if the below is interrupted and the interrupt context
attempts to acquire the lock?

> +
> +	/* Are any of the regs PCC ?*/
> +	if ((highest_reg->cpc_entry.reg.space_id ==
> +				ACPI_ADR_SPACE_PLATFORM_COMM) ||
> +			(lowest_reg->cpc_entry.reg.space_id ==
> +			 ACPI_ADR_SPACE_PLATFORM_COMM) ||
> +			(ref_perf->cpc_entry.reg.space_id ==
> +			 ACPI_ADR_SPACE_PLATFORM_COMM) ||
> +			(nom_perf->cpc_entry.reg.space_id ==
> +			 ACPI_ADR_SPACE_PLATFORM_COMM))
> +		is_pcc = true;
> +
> +	if (is_pcc) {
> +		/*
> +		 * Min time OS should wait before sending
> +		 * next command.
> +		 */
> +		udelay(pcc_cmd_delay);
> +		/* Ring doorbell */
> +		ret = send_pcc_cmd(CMD_READ);
> +		if (ret) {
> +			spin_unlock(&pcc_lock);
> +			return -EIO;
> +		}
> +	}
> +
> +	max = cpc_trans(highest_reg, CMD_READ, 0, is_pcc);
> +	perf_caps->highest_perf = max;
> +
> +	min = cpc_trans(lowest_reg, CMD_READ, 0, is_pcc);
> +	perf_caps->lowest_perf = min;
> +
> +	ref = cpc_trans(ref_perf, CMD_READ, 0, is_pcc);
> +	perf_caps->reference_perf = ref;
> +
> +	nom = cpc_trans(nom_perf, CMD_READ, 0, is_pcc);
> +	perf_caps->nominal_perf = nom;
> +
> +	if (!ref)
> +		perf_caps->reference_perf = perf_caps->nominal_perf;
> +
> +	spin_unlock(&pcc_lock);
> +
> +	if (!perf_caps->highest_perf ||
> +			!perf_caps->lowest_perf ||
> +			!perf_caps->reference_perf ||
> +			!perf_caps->nominal_perf) {
> +		return -EINVAL;

Again, why -EINVAL?

> +	}
> +
> +	return 0;
> +}
> +EXPORT_SYMBOL_GPL(cppc_get_perf_caps);
> +
> +/**
> + * cppc_get_perf_ctrs - Read a CPUs performance feedback counters.
> + * @cpunum: CPU from which to read counters.
> + * @perf_fb_ctrs: ptr to cppc_perf_fb_ctrs. See cppc_acpi.h
> + *
> + * Return - 0 for success with perf_fb_ctrs populated else
> + *	-ERRNO.
> + */
> +int cppc_get_perf_ctrs(int cpunum, struct cppc_perf_fb_ctrs *perf_fb_ctrs)
> +{
> +	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
> +	struct cpc_register_resource *delivered_reg, *reference_reg;
> +	u64 delivered, reference;
> +	bool is_pcc = false;
> +	int ret;
> +
> +	if (!cpc_desc) {
> +		pr_debug("No CPC descriptor for CPU:%d\n", cpunum);
> +		return -ENODEV;
> +	}
> +
> +	delivered_reg = &cpc_desc->cpc_regs[DELIVERED_CTR];
> +	reference_reg = &cpc_desc->cpc_regs[REFERENCE_CTR];
> +
> +	spin_lock(&pcc_lock);
> +
> +	/* Are any of the regs PCC ?*/
> +	if ((delivered_reg->cpc_entry.reg.space_id ==
> +				ACPI_ADR_SPACE_PLATFORM_COMM) ||
> +			(reference_reg->cpc_entry.reg.space_id ==
> +			 ACPI_ADR_SPACE_PLATFORM_COMM))
> +		is_pcc = true;
> +
> +	if (is_pcc) {
> +		/*
> +		 * Min time OS should wait before sending
> +		 * next command.
> +		 */
> +		udelay(pcc_cmd_delay);
> +		/* Ring doorbell */
> +		ret = send_pcc_cmd(CMD_READ);
> +		if (ret) {
> +			spin_unlock(&pcc_lock);
> +			return -EIO;
> +		}

The above looks like some duplicated code.  Any chance to move it into a separate
routine and call from both places?

> +	}
> +
> +	delivered = cpc_trans(delivered_reg, CMD_READ, 0, is_pcc);
> +	reference = cpc_trans(reference_reg, CMD_READ, 0, is_pcc);
> +
> +	spin_unlock(&pcc_lock);
> +
> +	if (!delivered || !reference)
> +		return -EINVAL;

Why -EINVAL?

> +
> +	perf_fb_ctrs->delivered = delivered;
> +	perf_fb_ctrs->reference = reference;
> +
> +	perf_fb_ctrs->delivered -= perf_fb_ctrs->prev_delivered;
> +	perf_fb_ctrs->reference -= perf_fb_ctrs->prev_reference;
> +
> +	perf_fb_ctrs->prev_delivered = delivered;
> +	perf_fb_ctrs->prev_reference = reference;
> +
> +	return 0;
> +}
> +EXPORT_SYMBOL_GPL(cppc_get_perf_ctrs);
> +
> +/**
> + * cppc_set_perf - Set a CPUs performance controls.
> + * @cpu: CPU for which to set performance controls.
> + * @perf_ctrls: ptr to cppc_perf_ctrls. See cppc_acpi.h
> + *
> + * Return: 0 for success, -ERRNO otherwise.
> + */
> +int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
> +{
> +	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu);
> +	struct cpc_register_resource *desired_reg;
> +	int ret = 0;
> +	bool is_pcc = false;
> +
> +	if (!cpc_desc) {
> +		pr_debug("No CPC descriptor for CPU:%d\n", cpu);
> +		return -ENODEV;
> +	}
> +
> +	desired_reg = &cpc_desc->cpc_regs[DESIRED_PERF];
> +
> +	spin_lock(&pcc_lock);
> +
> +	/* Is this a PCC reg ?*/
> +	if (desired_reg->cpc_entry.reg.space_id ==
> +			ACPI_ADR_SPACE_PLATFORM_COMM)
> +		is_pcc = true;
> +
> +	cpc_trans(desired_reg, CMD_WRITE,
> +			perf_ctrls->desired_perf, is_pcc);
> +
> +	if (is_pcc) {
> +		/*
> +		 * Min time OS should wait before sending
> +		 * next command.
> +		 */
> +		udelay(pcc_cmd_delay);
> +		/* Ring doorbell */
> +		ret = send_pcc_cmd(CMD_READ);
> +	}
> +
> +	spin_unlock(&pcc_lock);
> +
> +	return ret;
> +}
> +EXPORT_SYMBOL_GPL(cppc_set_perf);

The header looks OK to me.

That's it for now, I need to move to other stuff probably for the rest
of this week.

Thanks,
Rafael

--
To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Ashwin Chaugule Aug. 27, 2015, 3:48 p.m. UTC | #2

Hi Rafael,
On 25 August 2015 at 21:46, Rafael J. Wysocki <[e-mail]> wrote:
> On Wednesday, August 05, 2015 09:40:27 AM Ashwin Chaugule wrote:
>> CPPC stands for Collaborative Processor Performance Controls
>> and is defined in the ACPI v5.0+ spec. It describes CPU
>> performance controls on an abstract and continuous scale
>> allowing the platform (e.g. remote power processor) to flexibly
>> optimize CPU performance with its knowledge of power budgets
>> and other architecture specific knowledge.
>>
>> This patch adds a shim which exports commonly used functions
>> to get and set CPPC specific controls for each CPU. This enables
>> CPUFreq drivers to gather per CPU performance data and use
>> with exisiting governors or even allows for customized governors
>> which are implemented inside CPUFreq drivers.
>>
>> Signed-off-by: Ashwin Chaugule <[e-mail]>
>> Reviewed-by: Al Stone <[e-mail]>
>> ---
>>  drivers/acpi/Kconfig     |  14 +
>>  drivers/acpi/Makefile    |   1 +
>>  drivers/acpi/cppc_acpi.c | 812 +++++++++++++++++++++++++++++++++++++++++++++++
>>  include/acpi/cppc_acpi.h | 137 ++++++++
>>  4 files changed, 964 insertions(+)
>>  create mode 100644 drivers/acpi/cppc_acpi.c
>>  create mode 100644 include/acpi/cppc_acpi.h
>>
>> diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
>> index 54e9729..c6ec903 100644
>> --- a/drivers/acpi/Kconfig
>> +++ b/drivers/acpi/Kconfig
>> @@ -197,6 +197,20 @@ config ACPI_PROCESSOR_IDLE
>>       bool
>>       select CPU_IDLE
>>
>> +config ACPI_CPPC_LIB
>> +     bool
>> +     depends on ACPI_PROCESSOR
>> +     depends on !ACPI_CPU_FREQ_PSS
>> +     select MAILBOX
>> +     select PCC
>> +     help
>> +       This file implements common functionality to parse
>
> It's better to start with "If this option is enabled".

Done.

>> +/*
>> + * CPPC (Collaborative Processor Performance Control) methods used
>> + * by CPUfreq drivers.
>
> One line please.

Done.

>> + * Finer details about the PCC and CPPC spec are available in the latest
>> + * ACPI 5.1 specification.
>
> ACPI 5.1 is not the latest any more.  I'd say "ACPI 6.0 or later" to be on the
> safe side.

Done.

>> +static DEFINE_PER_CPU(struct cpc_desc *, cpc_desc_ptr);
>
> A description of what the per-CPU thing is and how it is used would be good
> to have here.

Done.

>
>> +
>> +/* This layer handles all the PCC specifics for CPPC. */
>> +static struct mbox_chan *pcc_channel;
>> +static void __iomem *pcc_comm_addr;
>> +static u64 comm_base_addr;
>> +static int pcc_subspace_idx = -1;
>> +static u16 pcc_cmd_delay;
>> +static int pcc_channel_acquired;
>> +
>> +#define NUM_RETRIES 500
>
> How did you get that number?

Loosely based on pcc-cpufreq.c which implements an out-of-ACPI-spec
CPPC + PCC-ish driver. I added a comment now to describe what its for.
In reality on silicon, we hope there's no more than a couple of
retries at worst, but its hard to tell whats out there.

>> +     /* Retry in case the remote processor was too slow to catch up. */
>> +     while (retries--) {
>
> It looks like this can be written as
>
>         for (retries = NUM_RETRIES; retries > 0; retries--) {
>
>> +             result = readw_relaxed(&generic_comm_base->status)
>> +                     & PCC_CMD_COMPLETE ? 0 : -EIO;
>
> I'm not sure why do you need the ternary operator here.
>
> You could just do
>
>                 if (readw_relaxed(&generic_comm_base->status) & PCC_CMD_COMPLETE) {
>                         result = 0;
>                         break;
>                 }
>
> and set "result" to -EIO beforehand.
>
>> +             if (!result) {
>> +                     /* Success. */
>> +                     retries = NUM_RETRIES;
>
> We break out of the loop in the next statement, so why is this needed?
>
> BTW, why do you need both "err" and "result"?  Why not to use "result"
> everywhere?
>

True. Done.

>
>> +                     break;
>> +             }
>> +     }
>> +
>> +     mbox_client_txdone(pcc_channel, result);
>> +     return result;
>> +}
>> +
>> +static void cppc_chan_tx_done(struct mbox_client *cl, void *mssg, int ret)
>> +{
>> +     if (ret)
>> +             pr_debug("TX did not complete: CMD sent:%x, ret:%d\n",
>> +                             *(u16 *)mssg, ret);
>> +     else
>> +             pr_debug("TX completed. CMD sent:%x, ret:%d\n",
>> +                             *(u16 *)mssg, ret);
>
> It would be good to identify the client somehow in these messages.  Otherwise
> they may not be quite useful.
>

For more details, I'd have to pack the CPU id in the PCC cmd field and
unpack it here. But from the PCC point of view, CPPC as a whole is a
client, so the pr_fmt prefix at least helps to identify it. Seemed
helpful enough for debug so far.

>> +     psd = buffer.pointer;
>> +     if (!psd || (psd->type != ACPI_TYPE_PACKAGE)) {
>> +             pr_err("Invalid _PSD data\n");
>> +             result = -ENODATA;
>> +             goto end;
>> +     }
>
> acpi_evaluate_object_typed() can be used here and then you save one "if".
>

Ok. I suppose it helps readability here, although that function has
many more if's inside it. :)

>> +
>> +     if (psd->package.count != 1) {
>> +             pr_err("Invalid _PSD data\n");
>> +             result = -ENODATA;
>> +             goto end;
>> +     }
>> +
>> +     pdomain = &(cpc_ptr->domain_info);
>> +
>> +     state.length = sizeof(struct acpi_psd_package);
>> +     state.pointer = pdomain;
>> +
>
> So beyond this point, if there's an error, you always set "result" to -ENODATA.
> Why not to set it to -ENODATA upfront and then reset it to 0 on success only?
> That would save you a bunch of statements.

True. Done.

>
>> +     status = acpi_extract_package(&(psd->package.elements[0]),
>> +             &format, &state);
>> +     if (ACPI_FAILURE(status)) {
>> +             pr_err("Invalid _PSD data\n");
>
> Why is that error priority and what can users see from the error message?
>
> Same pretty much everywhere below?
>

So, I ported all this PSD stuff over from processor_perflib.c assuming
it "just works" there. FWIW I couldn't reuse that function since it is
tied too closely to _PSS structures. This err would indicate the PSD
package itself is screwed up, otherwise the errs below indicate
specific entries within PSD could be wrong. I'll make them pr_debugs
here though.

>> +             result = -ENODATA;
>> +             goto end;
>> +     }
>> +
>> +     if (pdomain->num_entries != ACPI_PSD_REV0_ENTRIES) {
>> +             pr_err("Unknown _PSD:num_entries\n");
>> +             result = -ENODATA;
>> +             goto end;
>> +     }
>> +
>> +     if (pdomain->revision != ACPI_PSD_REV0_REVISION) {
>> +             pr_err("Unknown _PSD:revision\n");
>> +             result = -ENODATA;
>> +             goto end;
>> +     }
>> +
>> +     if (pdomain->coord_type != DOMAIN_COORD_TYPE_SW_ALL &&
>> +         pdomain->coord_type != DOMAIN_COORD_TYPE_SW_ANY &&
>> +         pdomain->coord_type != DOMAIN_COORD_TYPE_HW_ALL) {
>> +             pr_err("Invalid _PSD:coord_type\n");
>> +             result = -ENODATA;
>> +             goto end;
>> +     }
>> +end:
>> +     kfree(buffer.pointer);
>> +     return result;
>> +}
>> +
>> +int acpi_get_psd_map(struct cpudata **all_cpu_data)
>> +{
>> +     int count_target;
>> +     int retval = 0;
>> +     unsigned int i, j;
>> +     cpumask_var_t covered_cpus;
>> +     struct cpudata *pr, *match_pr;
>> +     struct acpi_psd_package *pdomain;
>> +     struct acpi_psd_package *match_pdomain;
>> +     struct cpc_desc *cpc_ptr, *match_cpc_ptr;
>> +
>> +     if (!zalloc_cpumask_var(&covered_cpus, GFP_KERNEL))
>> +             return -ENOMEM;
>> +
>> +     /*
>> +      * Now that we have _PSD data from all CPUs, lets setup P-state
>> +      * domain info.
>> +      */
>> +     for_each_possible_cpu(i) {
>> +             pr = all_cpu_data[i];
>> +             if (!pr)
>> +                     continue;
>> +
>> +             if (cpumask_test_cpu(i, covered_cpus))
>> +                     continue;
>> +
>> +             cpc_ptr = per_cpu(cpc_desc_ptr, i);
>> +             if (!cpc_ptr)
>> +                     continue;
>
> Well, is this actually safe?  What if we have CPPC control for some CPUs in a
> domain only?

I dont think thats possible since we can't have CPPC and any other
scheme (e.g. PSS) actively running at the same time. Also in this
case, IIUC there could be some CPUs in a domain that are present but
not available at bootup so their cpc_desc ptr could be NULL.

>
>> +
>> +             pdomain = &(cpc_ptr->domain_info);
>> +             cpumask_set_cpu(i, pr->shared_cpu_map);
>> +             cpumask_set_cpu(i, covered_cpus);
>> +             if (pdomain->num_processors <= 1)
>> +                     continue;
>> +
>> +             /* Validate the Domain info */
>> +             count_target = pdomain->num_processors;
>> +             if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ALL)
>> +                     pr->shared_type = CPUFREQ_SHARED_TYPE_ALL;
>> +             else if (pdomain->coord_type == DOMAIN_COORD_TYPE_HW_ALL)
>> +                     pr->shared_type = CPUFREQ_SHARED_TYPE_HW;
>> +             else if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ANY)
>> +                     pr->shared_type = CPUFREQ_SHARED_TYPE_ANY;
>> +
>> +             for_each_possible_cpu(j) {
>> +                     if (i == j)
>> +                             continue;
>> +
>> +                     match_cpc_ptr = per_cpu(cpc_desc_ptr, j);
>> +                     if (!match_cpc_ptr)
>> +                             continue;
>> +
>> +                     match_pdomain = &(match_cpc_ptr->domain_info);
>> +                     if (match_pdomain->domain != pdomain->domain)
>> +                             continue;
>> +
>> +                     /* Here i and j are in the same domain */
>> +
>> +                     if (match_pdomain->num_processors != count_target) {
>> +                             retval = -EINVAL;
>
> So we do bail out here, so why don't we bail out on any errors?  Why do we
> silently ignore some of them (like NULL cpc_ptr above)?

I think the idea is that you cant have a system with matching PSDs and
mismatching entries within. processor_perflib.c has the same
assumption.

>
>> +                             goto err_ret;
>> +                     }
>> +
>> +                     if (pdomain->coord_type != match_pdomain->coord_type) {
>> +                             retval = -EINVAL;
>> +                             goto err_ret;
>> +                     }
>> +
>> +                     cpumask_set_cpu(j, covered_cpus);
>> +                     cpumask_set_cpu(j, pr->shared_cpu_map);
>> +             }
>> +
>> +             for_each_possible_cpu(j) {
>
> Why do we need a separate loop over all CPUs for this?  Could not the loops
> be combined?

Without getting too fancy, I dont see how to avoid this O(n^2) looping.


>> +static int register_pcc_channel(unsigned pcc_subspace_idx)
>> +{
>> +     struct acpi_pcct_subspace *cppc_ss;
>> +     unsigned int len;
>> +
>> +     if (pcc_subspace_idx >= 0) {
>
> I'd check the reverse (ie. < 0) here and return immediately if that's the case.
>

Ok.

>> +             pcc_channel = pcc_mbox_request_channel(&cppc_mbox_cl,
>> +                             pcc_subspace_idx);
>> +
>> +             if (IS_ERR(pcc_channel)) {
>> +                     pr_err("No PCC communication channel found\n");
>> +                     return -ENODEV;
>> +             }
>> +
>> +             /*
>> +              * The PCC mailbox controller driver should
>> +              * have parsed the PCCT (global table of all
>> +              * PCC channels) and stored pointers to the
>> +              * subspace communication region in con_priv.
>> +              */
>> +             cppc_ss = pcc_channel->con_priv;
>> +
>> +             if (!cppc_ss) {
>> +                     pr_err("No PCC subspace found for CPPC\n");
>> +                     return -ENODEV;
>> +             }
>> +
>> +             /*
>> +              * This is the shared communication region
>> +              * for the OS and Platform to communicate over.
>> +              */
>> +             comm_base_addr = cppc_ss->base_address;
>> +             len = cppc_ss->length;
>> +             pcc_cmd_delay = cppc_ss->min_turnaround_time;
>> +
>> +             pcc_comm_addr = ioremap(comm_base_addr, len);
>> +             if (!pcc_comm_addr) {
>> +                     pr_err("Failed to ioremap PCC comm region mem\n");
>> +                     return -ENOMEM;
>> +             }
>> +
>> +             /* Set flag so that we dont come here for each CPU. */
>> +             pcc_channel_acquired = 1;
>
> Should pcc_channel_acquired be a bool variable rather?

Sure.

>> +
>> +     } else
>> +             /*
>> +              * For the case where registers are not defined as PCC regs.
>> +              * Assuming all regs are FFH / SystemIO.
>> +              */
>> +             pr_debug("No PCC subspace detected in any CPC entries.\n");
>> +
>> +     return 0;
>> +}
>> +
>> +/**
>> + * acpi_cppc_processor_probe - The _CPC table is a per CPU table
>
> One line description here, please.

Done.

>
>> + * which a bunch of entries which may be registers or integers.
>
> Move the example to a separate comment above the kerneldoc.
>

Ok.

>> + *   This function walks through all the per CPU _CPC entries and extracts
>> + *   the Register details.
>> + *
>> + *   Return: 0 for success or negative value for err.
>
> And the argument needs to be documented in the kerneldoc too.


Gah! Right.

>
>> + */
>> +int acpi_cppc_processor_probe(struct acpi_processor *pr)
>> +{
>> +     struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL};
>> +     union acpi_object *out_obj, *cpc_obj;
>> +     struct cpc_desc *cpc_ptr;
>> +     struct cpc_reg *gas_t;
>> +     acpi_handle handle = pr->handle;
>> +     unsigned int num_ent, i, cpc_rev, ret = 0;
>> +     acpi_status status;
>> +
>> +     /* Parse the ACPI _CPC table for this cpu. */
>> +     if (!acpi_has_method(handle, "_CPC")) {
>> +             pr_debug("_CPC table not found\n");
>> +             ret = -ENODEV;
>> +             goto out_buf_free;
>> +     }
>
> You don't need to do the above (the below will fail if _CPC is not present)
> and I'm not sure if the debug message is worth it.
>

Ok.

>> +
>> +     status = acpi_evaluate_object(handle, "_CPC", NULL, &output);
>> +     if (ACPI_FAILURE(status)) {
>> +             ret = -ENODEV;
>> +             goto out_buf_free;
>> +     }
>> +
>> +     out_obj = (union acpi_object *) output.pointer;
>> +     if (out_obj->type != ACPI_TYPE_PACKAGE) {
>> +             ret = -ENODEV;
>> +             goto out_buf_free;
>> +     }
>
> Again, acpi_evaluate_object_typed() would save you one branch.

Ok.

>> +     /* Only support CPPCv2. Bail otherwise. */
>> +     if (num_ent != CPPC_NUM_ENT) {
>> +             pr_err("Firmware exports %d entries. Expected: %d\n",
>> +                             num_ent, CPPC_NUM_ENT);
>> +             ret = -EINVAL;
>
> Why -EINVAL?  It doesn't mean "invalid argument" surely?

:) Changed to -EFAULT.

>> +                     /*
>> +                      * The PCC Subspace index is encoded inside
>> +                      * the CPC table entries. The same PCC index
>> +                      * will be used for all the PCC entries,
>> +                      * so extract it only once.
>> +                      */
>> +                     if (gas_t->space_id ==
>> +                                     ACPI_ADR_SPACE_PLATFORM_COMM) {
>
> Please don't break lines like this.  I know that it'll be more than 80 chars,
> but that's OK.  Or if you really care, you can move that code to a helper
> function.
>

Works for me. Thanks.

>> +                             if (pcc_subspace_idx < 0)
>> +                                     pcc_subspace_idx =
>> +                                             gas_t->access_width;
>> +                             else if (pcc_subspace_idx !=
>> +                                             gas_t->access_width) {
>> +                                     /*
>> +                                      * Mismatched PCC id detected.
>> +                                      * Firmware bug.
>> +                                      */
>> +                                     goto out_free;
>> +                             }
>> +                     }
>> +
>> +                     cpc_ptr->cpc_regs[i-2].type =
>> +                             ACPI_TYPE_BUFFER;
>> +                     cpc_ptr->cpc_regs[i-2].cpc_entry.reg =
>> +                             (struct cpc_reg) {
>> +                                     .space_id = gas_t->space_id,
>> +                                     .length = gas_t->length,
>> +                                     .bit_width = gas_t->bit_width,
>> +                                     .bit_offset = gas_t->bit_offset,
>> +                                     .address = gas_t->address,
>> +                                     .access_width =
>> +                                             gas_t->access_width,
>
> Why don't you use memcpy() for copying this?
>
Will do. I think previously I had gas_t as a generic register type,
which has a slightly different layout than the PCC register.

>> +
>> +     /* Register PCC channel once for all CPUs. */
>> +     if (!pcc_channel_acquired) {
>> +             ret = register_pcc_channel(pcc_subspace_idx);
>
> So here's a question: What if pcc_subspace_idx for the new CPU is different
> from the one we've registered the channel with?
>

That would be a bug in the CPC tables. CPPC being one client of PCC is
assigned only one PCC subspace, so all CPUs should have the same PCC
subspace id. This is caught in the check above.

> Also, is this guaranteed to be run sequentially for all of the different CPUs?

Yes. IIUC its called sequentially when the processor_driver detects a
Processor object.

>
> If not, what if they race with each other here and the channel is
> registered twice as a result?
>

I couldn't find a place in the ACPI boot flow where the Processor
object probing could happen in parallel, but you're more familiar with
this than me. :)

>> +     /* PCC communication addr space begins at byte offset 0x8. */
>> +     addr = is_pcc ? (u64)pcc_comm_addr + 0x8 + reg->cpc_entry.reg.address :
>> +             reg->cpc_entry.reg.address;
>
> Move the above to a separate function and document the formula.
>

Done.

>> +
>> +     if (reg->type == ACPI_TYPE_BUFFER) {
>
> Quite a bit of code duplication below.  Any chance to reduce it?
>

Will rethink. Doubt I can avoid the switch-case though.

>> +             switch (reg->cpc_entry.reg.bit_width) {
>> +             case 8:
>> +                     if (cmd == CMD_READ)
>> +                             read_val = readb((void *) (addr));
>> +                     else if (cmd == CMD_WRITE)
>> +                             writeb(write_val, (void *)(addr));
>> +                     else
>> +                             pr_debug("Unsupported cmd type: %d\n", cmd);
>> +                     break;
>> +             case 16:
>> +                     if (cmd == CMD_READ)
>> +                             read_val = readw((void *) (addr));
>> +                     else if (cmd == CMD_WRITE)
>> +                             writew(write_val, (void *)(addr));
>> +                     else
>> +                             pr_debug("Unsupported cmd type: %d\n", cmd);
>> +                     break;
>> +             case 32:
>> +                     if (cmd == CMD_READ)
>> +                             read_val = readl((void *) (addr));
>> +                     else if (cmd == CMD_WRITE)
>> +                             writel(write_val, (void *)(addr));
>> +                     else
>> +                             pr_debug("Unsupported cmd type: %d\n", cmd);
>> +                     break;
>> +             case 64:
>> +                     if (cmd == CMD_READ)
>> +                             read_val = readq((void *) (addr));
>> +                     else if (cmd == CMD_WRITE)
>> +                             writeq(write_val, (void *)(addr));
>> +                     else
>> +                             pr_debug("Unsupported cmd type: %d\n", cmd);
>> +                     break;
>> +             default:
>> +                     pr_debug("Unsupported bit width for CPC cmd:%d\n",
>> +                                     cmd);
>> +                     break;
>> +             }
>> +     } else if (reg->type == ACPI_TYPE_INTEGER) {
>> +             if (cmd == CMD_READ)
>> +                     read_val = reg->cpc_entry.int_value;
>> +             else if (cmd == CMD_WRITE)
>> +                     reg->cpc_entry.int_value = write_val;
>> +             else
>> +                     pr_debug("Unsupported cmd type: %d\n", cmd);
>> +     } else
>> +             pr_debug("Unsupported CPC entry type:%d\n", reg->type);
>> +
>> +     return read_val;
>> +}
>> +
>> +/**
>> + * cppc_get_perf_caps - Get a CPUs performance capabilities.
>> + * @cpunum: CPU from which to get capabilities info.
>> + * @perf_caps: ptr to cppc_perf_caps. See cppc_acpi.h
>> + *
>> + * Return - 0 for success with perf_caps populated else
>> + *   -ERRNO.
>> + */
>> +int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps)
>> +{
>> +     struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
>> +     struct cpc_register_resource *highest_reg, *lowest_reg, *ref_perf,
>> +                                  *nom_perf;
>> +     u64 min, max, ref, nom;
>> +     bool is_pcc = false;
>> +     int ret;
>> +
>> +     if (!cpc_desc) {
>> +             pr_debug("No CPC descriptor for CPU:%d\n", cpunum);
>> +             return -ENODEV;
>> +     }
>> +
>> +     highest_reg = &cpc_desc->cpc_regs[HIGHEST_PERF];
>> +     lowest_reg = &cpc_desc->cpc_regs[LOWEST_PERF];
>> +     ref_perf = &cpc_desc->cpc_regs[REFERENCE_PERF];
>> +     nom_perf = &cpc_desc->cpc_regs[NOMINAL_PERF];
>> +
>> +     spin_lock(&pcc_lock);
>
> Are we only going to acquire this spinlock from IRQ context of from
> process context or from both?  If from both, what prevents deadlocks
> from happening if the below is interrupted and the interrupt context
> attempts to acquire the lock?

IIUC Process context only. Looking around at other cpufreq drivers,
(e.g. pcc-cpufreq.c) I dont think the deadlock is a possibility here
either.

>> +     if (!perf_caps->highest_perf ||
>> +                     !perf_caps->lowest_perf ||
>> +                     !perf_caps->reference_perf ||
>> +                     !perf_caps->nominal_perf) {
>> +             return -EINVAL;
>
> Again, why -EINVAL?

Changed to -EFAULT.
>
>> +     if (is_pcc) {
>> +             /*
>> +              * Min time OS should wait before sending
>> +              * next command.
>> +              */
>> +             udelay(pcc_cmd_delay);
>> +             /* Ring doorbell */
>> +             ret = send_pcc_cmd(CMD_READ);
>> +             if (ret) {
>> +                     spin_unlock(&pcc_lock);
>> +                     return -EIO;
>> +             }
>
> The above looks like some duplicated code.  Any chance to move it into a separate
> routine and call from both places?
>

Yep. Done.

>> +
>> +     if (!delivered || !reference)
>> +             return -EINVAL;
>
> Why -EINVAL?
>

:) Changed to -EFAULT.

>
> The header looks OK to me.
>
Great!

> That's it for now, I need to move to other stuff probably for the rest
> of this week.
>

Thanks for the follow up! I'll update this patch and resend for review
sometime next week.

Regards,
Ashwin.
--
To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 54e9729..c6ec903 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -197,6 +197,20 @@  config ACPI_PROCESSOR_IDLE
 	bool
 	select CPU_IDLE
 
+config ACPI_CPPC_LIB
+	bool
+	depends on ACPI_PROCESSOR
+	depends on !ACPI_CPU_FREQ_PSS
+	select MAILBOX
+	select PCC
+	help
+	  This file implements common functionality to parse
+	  CPPC tables as described in the ACPI 5.1+ spec. The
+	  routines implemented are meant to be used by other
+	  drivers to control CPU performance using CPPC semantics.
+	  If your platform does not support CPPC in firmware,
+	  leave this option disabled.
+
 config ACPI_PROCESSOR
 	tristate "Processor"
 	depends on X86 || IA64
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 3ea59ae..4c393a69 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -78,6 +78,7 @@  obj-$(CONFIG_ACPI_HED)		+= hed.o
 obj-$(CONFIG_ACPI_EC_DEBUGFS)	+= ec_sys.o
 obj-$(CONFIG_ACPI_CUSTOM_METHOD)+= custom_method.o
 obj-$(CONFIG_ACPI_BGRT)		+= bgrt.o
+obj-$(CONFIG_ACPI_CPPC_LIB)	+= cppc_acpi.o
 
 # processor has its own "processor." module_param namespace
 processor-y			:= processor_driver.o
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
new file mode 100644
index 0000000..9c89767
--- /dev/null
+++ b/drivers/acpi/cppc_acpi.c
@@ -0,0 +1,812 @@ 
+/*
+ * CPPC (Collaborative Processor Performance Control) methods used
+ * by CPUfreq drivers.
+ *
+ * (C) Copyright 2014, 2015 Linaro Ltd.
+ * Author: Ashwin Chaugule <[e-mail]>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ *
+ * CPPC describes a few methods for controlling CPU performance using
+ * information from a per CPU table called CPC. This table is described in
+ * the ACPI v5.0+ specification. The table consists of a list of
+ * registers which may be memory mapped or hardware registers and also may
+ * include some static integer values.
+ *
+ * CPU performance is on an abstract continuous scale as against a discretized
+ * P-state scale which is tied to CPU frequency only. In brief, the basic
+ * operation involves:
+ *
+ * - OS makes a CPU performance request. (Can provide min and max bounds)
+ *
+ * - Platform (such as BMC) is free to optimize request within requested bounds
+ *   depending on power/thermal budgets etc.
+ *
+ * - Platform conveys its decision back to OS
+ *
+ * The communication between OS and platform occurs through another medium
+ * called (PCC) Platform Communication Channel. This is a generic mailbox like
+ * mechanism which includes doorbell semantics to indicate register updates.
+ * See drivers/mailbox/pcc.c for details on PCC.
+ *
+ * Finer details about the PCC and CPPC spec are available in the latest
+ * ACPI 5.1 specification.
+ */
+
+#define pr_fmt(fmt)	"ACPI CPPC: " fmt
+
+#include <linux/cpufreq.h>
+#include <linux/delay.h>
+
+#include <acpi/cppc_acpi.h>
+/*
+ * Lock to provide mutually exclusive access to the PCC
+ * channel. e.g. When the remote updates the shared region
+ * with new data, the reader needs to be protected from
+ * other CPUs activity on the same channel.
+ */
+static DEFINE_SPINLOCK(pcc_lock);
+
+static DEFINE_PER_CPU(struct cpc_desc *, cpc_desc_ptr);
+
+/* This layer handles all the PCC specifics for CPPC. */
+static struct mbox_chan *pcc_channel;
+static void __iomem *pcc_comm_addr;
+static u64 comm_base_addr;
+static int pcc_subspace_idx = -1;
+static u16 pcc_cmd_delay;
+static int pcc_channel_acquired;
+
+#define NUM_RETRIES 500
+
+static int send_pcc_cmd(u16 cmd)
+{
+	int err, result = 0;
+	int retries = NUM_RETRIES;
+	struct acpi_pcct_hw_reduced *pcct_ss = pcc_channel->con_priv;
+	struct acpi_pcct_shared_memory *generic_comm_base =
+		(struct acpi_pcct_shared_memory *) pcc_comm_addr;
+	u32 cmd_latency = pcct_ss->latency;
+
+	/* Write to the shared comm region. */
+	writew(cmd, &generic_comm_base->command);
+
+	/* Flip CMD COMPLETE bit */
+	writew(0, &generic_comm_base->status);
+
+	err = mbox_send_message(pcc_channel, &cmd);
+	if (err < 0) {
+		pr_err("Err sending PCC mbox message. cmd:%d, ret:%d\n",
+				cmd, err);
+		return err;
+	}
+
+	/* Wait for a nominal time to let platform processes command. */
+	udelay(cmd_latency);
+
+	/* Retry in case the remote processor was too slow to catch up. */
+	while (retries--) {
+		result = readw_relaxed(&generic_comm_base->status)
+			& PCC_CMD_COMPLETE ? 0 : -EIO;
+		if (!result) {
+			/* Success. */
+			retries = NUM_RETRIES;
+			break;
+		}
+	}
+
+	mbox_client_txdone(pcc_channel, result);
+	return result;
+}
+
+static void cppc_chan_tx_done(struct mbox_client *cl, void *mssg, int ret)
+{
+	if (ret)
+		pr_debug("TX did not complete: CMD sent:%x, ret:%d\n",
+				*(u16 *)mssg, ret);
+	else
+		pr_debug("TX completed. CMD sent:%x, ret:%d\n",
+				*(u16 *)mssg, ret);
+}
+
+struct mbox_client cppc_mbox_cl = {
+	.tx_done = cppc_chan_tx_done,
+	.knows_txdone = true,
+};
+
+static int acpi_get_psd(struct cpc_desc *cpc_ptr, acpi_handle handle)
+{
+	int result = 0;
+	acpi_status status = AE_OK;
+	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
+	struct acpi_buffer format = {sizeof("NNNNN"), "NNNNN"};
+	struct acpi_buffer state = {0, NULL};
+	union acpi_object  *psd = NULL;
+	struct acpi_psd_package *pdomain;
+
+	status = acpi_evaluate_object(handle, "_PSD", NULL, &buffer);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	psd = buffer.pointer;
+	if (!psd || (psd->type != ACPI_TYPE_PACKAGE)) {
+		pr_err("Invalid _PSD data\n");
+		result = -ENODATA;
+		goto end;
+	}
+
+	if (psd->package.count != 1) {
+		pr_err("Invalid _PSD data\n");
+		result = -ENODATA;
+		goto end;
+	}
+
+	pdomain = &(cpc_ptr->domain_info);
+
+	state.length = sizeof(struct acpi_psd_package);
+	state.pointer = pdomain;
+
+	status = acpi_extract_package(&(psd->package.elements[0]),
+		&format, &state);
+	if (ACPI_FAILURE(status)) {
+		pr_err("Invalid _PSD data\n");
+		result = -ENODATA;
+		goto end;
+	}
+
+	if (pdomain->num_entries != ACPI_PSD_REV0_ENTRIES) {
+		pr_err("Unknown _PSD:num_entries\n");
+		result = -ENODATA;
+		goto end;
+	}
+
+	if (pdomain->revision != ACPI_PSD_REV0_REVISION) {
+		pr_err("Unknown _PSD:revision\n");
+		result = -ENODATA;
+		goto end;
+	}
+
+	if (pdomain->coord_type != DOMAIN_COORD_TYPE_SW_ALL &&
+	    pdomain->coord_type != DOMAIN_COORD_TYPE_SW_ANY &&
+	    pdomain->coord_type != DOMAIN_COORD_TYPE_HW_ALL) {
+		pr_err("Invalid _PSD:coord_type\n");
+		result = -ENODATA;
+		goto end;
+	}
+end:
+	kfree(buffer.pointer);
+	return result;
+}
+
+int acpi_get_psd_map(struct cpudata **all_cpu_data)
+{
+	int count_target;
+	int retval = 0;
+	unsigned int i, j;
+	cpumask_var_t covered_cpus;
+	struct cpudata *pr, *match_pr;
+	struct acpi_psd_package *pdomain;
+	struct acpi_psd_package *match_pdomain;
+	struct cpc_desc *cpc_ptr, *match_cpc_ptr;
+
+	if (!zalloc_cpumask_var(&covered_cpus, GFP_KERNEL))
+		return -ENOMEM;
+
+	/*
+	 * Now that we have _PSD data from all CPUs, lets setup P-state
+	 * domain info.
+	 */
+	for_each_possible_cpu(i) {
+		pr = all_cpu_data[i];
+		if (!pr)
+			continue;
+
+		if (cpumask_test_cpu(i, covered_cpus))
+			continue;
+
+		cpc_ptr = per_cpu(cpc_desc_ptr, i);
+		if (!cpc_ptr)
+			continue;
+
+		pdomain = &(cpc_ptr->domain_info);
+		cpumask_set_cpu(i, pr->shared_cpu_map);
+		cpumask_set_cpu(i, covered_cpus);
+		if (pdomain->num_processors <= 1)
+			continue;
+
+		/* Validate the Domain info */
+		count_target = pdomain->num_processors;
+		if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ALL)
+			pr->shared_type = CPUFREQ_SHARED_TYPE_ALL;
+		else if (pdomain->coord_type == DOMAIN_COORD_TYPE_HW_ALL)
+			pr->shared_type = CPUFREQ_SHARED_TYPE_HW;
+		else if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ANY)
+			pr->shared_type = CPUFREQ_SHARED_TYPE_ANY;
+
+		for_each_possible_cpu(j) {
+			if (i == j)
+				continue;
+
+			match_cpc_ptr = per_cpu(cpc_desc_ptr, j);
+			if (!match_cpc_ptr)
+				continue;
+
+			match_pdomain = &(match_cpc_ptr->domain_info);
+			if (match_pdomain->domain != pdomain->domain)
+				continue;
+
+			/* Here i and j are in the same domain */
+
+			if (match_pdomain->num_processors != count_target) {
+				retval = -EINVAL;
+				goto err_ret;
+			}
+
+			if (pdomain->coord_type != match_pdomain->coord_type) {
+				retval = -EINVAL;
+				goto err_ret;
+			}
+
+			cpumask_set_cpu(j, covered_cpus);
+			cpumask_set_cpu(j, pr->shared_cpu_map);
+		}
+
+		for_each_possible_cpu(j) {
+			if (i == j)
+				continue;
+
+			match_pr = all_cpu_data[j];
+			if (!match_pr)
+				continue;
+
+			match_cpc_ptr = per_cpu(cpc_desc_ptr, j);
+			if (!match_cpc_ptr)
+				continue;
+
+			match_pdomain = &(match_cpc_ptr->domain_info);
+			if (match_pdomain->domain != pdomain->domain)
+				continue;
+
+			match_pr->shared_type = pr->shared_type;
+			cpumask_copy(match_pr->shared_cpu_map,
+				     pr->shared_cpu_map);
+		}
+	}
+
+err_ret:
+	for_each_possible_cpu(i) {
+		pr = all_cpu_data[i];
+		if (!pr)
+			continue;
+
+		/* Assume no coordination on any error parsing domain info */
+		if (retval) {
+			cpumask_clear(pr->shared_cpu_map);
+			cpumask_set_cpu(i, pr->shared_cpu_map);
+			pr->shared_type = CPUFREQ_SHARED_TYPE_ALL;
+		}
+	}
+
+	free_cpumask_var(covered_cpus);
+	return retval;
+}
+EXPORT_SYMBOL_GPL(acpi_get_psd_map);
+
+static int register_pcc_channel(unsigned pcc_subspace_idx)
+{
+	struct acpi_pcct_subspace *cppc_ss;
+	unsigned int len;
+
+	if (pcc_subspace_idx >= 0) {
+		pcc_channel = pcc_mbox_request_channel(&cppc_mbox_cl,
+				pcc_subspace_idx);
+
+		if (IS_ERR(pcc_channel)) {
+			pr_err("No PCC communication channel found\n");
+			return -ENODEV;
+		}
+
+		/*
+		 * The PCC mailbox controller driver should
+		 * have parsed the PCCT (global table of all
+		 * PCC channels) and stored pointers to the
+		 * subspace communication region in con_priv.
+		 */
+		cppc_ss = pcc_channel->con_priv;
+
+		if (!cppc_ss) {
+			pr_err("No PCC subspace found for CPPC\n");
+			return -ENODEV;
+		}
+
+		/*
+		 * This is the shared communication region
+		 * for the OS and Platform to communicate over.
+		 */
+		comm_base_addr = cppc_ss->base_address;
+		len = cppc_ss->length;
+		pcc_cmd_delay = cppc_ss->min_turnaround_time;
+
+		pcc_comm_addr = ioremap(comm_base_addr, len);
+		if (!pcc_comm_addr) {
+			pr_err("Failed to ioremap PCC comm region mem\n");
+			return -ENOMEM;
+		}
+
+		/* Set flag so that we dont come here for each CPU. */
+		pcc_channel_acquired = 1;
+
+	} else
+		/*
+		 * For the case where registers are not defined as PCC regs.
+		 * Assuming all regs are FFH / SystemIO.
+		 */
+		pr_debug("No PCC subspace detected in any CPC entries.\n");
+
+	return 0;
+}
+
+/**
+ * acpi_cppc_processor_probe - The _CPC table is a per CPU table
+ * which a bunch of entries which may be registers or integers.
+ * An example table looks like the following.
+ *
+ *	Name(_CPC, Package()
+ *			{
+ *			17,
+ *			NumEntries
+ *			1,
+ *			// Revision
+ *			ResourceTemplate(){Register(PCC, 32, 0, 0x120, 2)},
+ *			// Highest Performance
+ *			ResourceTemplate(){Register(PCC, 32, 0, 0x124, 2)},
+ *			// Nominal Performance
+ *			ResourceTemplate(){Register(PCC, 32, 0, 0x128, 2)},
+ *			// Lowest Nonlinear Performance
+ *			ResourceTemplate(){Register(PCC, 32, 0, 0x12C, 2)},
+ *			// Lowest Performance
+ *			ResourceTemplate(){Register(PCC, 32, 0, 0x130, 2)},
+ *			// Guaranteed Performance Register
+ *			ResourceTemplate(){Register(PCC, 32, 0, 0x110, 2)},
+ *			// Desired Performance Register
+ *			ResourceTemplate(){Register(SystemMemory, 0, 0, 0, 0)},
+ *			..
+ *			..
+ *			..
+ *
+ *		}
+ * Each Register() encodes how to access that specific register.
+ * e.g. a sample PCC entry has the following encoding:
+ *
+ *	Register (
+ *		PCC,
+ *		AddressSpaceKeyword
+ *		8,
+ *		//RegisterBitWidth
+ *		8,
+ *		//RegisterBitOffset
+ *		0x30,
+ *		//RegisterAddress
+ *		9
+ *		//AccessSize (subspace ID)
+ *		0
+ *		)
+ *		}
+ *
+ *	This function walks through all the per CPU _CPC entries and extracts
+ *	the Register details.
+ *
+ *	Return: 0 for success or negative value for err.
+ */
+int acpi_cppc_processor_probe(struct acpi_processor *pr)
+{
+	struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL};
+	union acpi_object *out_obj, *cpc_obj;
+	struct cpc_desc *cpc_ptr;
+	struct cpc_reg *gas_t;
+	acpi_handle handle = pr->handle;
+	unsigned int num_ent, i, cpc_rev, ret = 0;
+	acpi_status status;
+
+	/* Parse the ACPI _CPC table for this cpu. */
+	if (!acpi_has_method(handle, "_CPC")) {
+		pr_debug("_CPC table not found\n");
+		ret = -ENODEV;
+		goto out_buf_free;
+	}
+
+	status = acpi_evaluate_object(handle, "_CPC", NULL, &output);
+	if (ACPI_FAILURE(status)) {
+		ret = -ENODEV;
+		goto out_buf_free;
+	}
+
+	out_obj = (union acpi_object *) output.pointer;
+	if (out_obj->type != ACPI_TYPE_PACKAGE) {
+		ret = -ENODEV;
+		goto out_buf_free;
+	}
+
+	cpc_ptr = kzalloc(sizeof(struct cpc_desc), GFP_KERNEL);
+	if (!cpc_ptr)
+		return -ENOMEM;
+
+	/* First entry is NumEntries. */
+	cpc_obj = &out_obj->package.elements[0];
+	if (cpc_obj->type == ACPI_TYPE_INTEGER)	{
+		num_ent = cpc_obj->integer.value;
+	} else {
+		pr_debug("Unexpected entry type(%d) for NumEntries\n",
+				cpc_obj->type);
+		goto out_free;
+	}
+
+	/* Only support CPPCv2. Bail otherwise. */
+	if (num_ent != CPPC_NUM_ENT) {
+		pr_err("Firmware exports %d entries. Expected: %d\n",
+				num_ent, CPPC_NUM_ENT);
+		ret = -EINVAL;
+		goto out_free;
+	}
+
+	/* Second entry should be revision. */
+	cpc_obj = &out_obj->package.elements[1];
+	if (cpc_obj->type == ACPI_TYPE_INTEGER)	{
+		cpc_rev = cpc_obj->integer.value;
+	} else {
+		pr_debug("Unexpected entry type(%d) for Revision\n",
+				cpc_obj->type);
+		goto out_free;
+	}
+
+	if (cpc_rev != CPPC_REV) {
+		pr_err("Firmware exports revision:%d. Expected:%d\n",
+				cpc_rev, CPPC_REV);
+		goto out_free;
+	}
+
+	/* Iterate through remaining entries in _CPC */
+	for (i = 2; i < num_ent; i++) {
+		cpc_obj = &out_obj->package.elements[i];
+
+		if (cpc_obj->type == ACPI_TYPE_INTEGER)	{
+			cpc_ptr->cpc_regs[i-2].type =
+				ACPI_TYPE_INTEGER;
+			cpc_ptr->cpc_regs[i-2].cpc_entry.int_value =
+				cpc_obj->integer.value;
+		} else if (cpc_obj->type == ACPI_TYPE_BUFFER) {
+			gas_t = (struct cpc_reg *)
+				cpc_obj->buffer.pointer;
+
+			/*
+			 * The PCC Subspace index is encoded inside
+			 * the CPC table entries. The same PCC index
+			 * will be used for all the PCC entries,
+			 * so extract it only once.
+			 */
+			if (gas_t->space_id ==
+					ACPI_ADR_SPACE_PLATFORM_COMM) {
+				if (pcc_subspace_idx < 0)
+					pcc_subspace_idx =
+						gas_t->access_width;
+				else if (pcc_subspace_idx !=
+						gas_t->access_width) {
+					/*
+					 * Mismatched PCC id detected.
+					 * Firmware bug.
+					 */
+					goto out_free;
+				}
+			}
+
+			cpc_ptr->cpc_regs[i-2].type =
+				ACPI_TYPE_BUFFER;
+			cpc_ptr->cpc_regs[i-2].cpc_entry.reg =
+				(struct cpc_reg) {
+					.space_id = gas_t->space_id,
+					.length	= gas_t->length,
+					.bit_width = gas_t->bit_width,
+					.bit_offset = gas_t->bit_offset,
+					.address = gas_t->address,
+					.access_width =
+						gas_t->access_width,
+				};
+		} else {
+			pr_debug("Error in entry:%d in CPC table.\n", i);
+			ret = -EINVAL;
+			goto out_free;
+		}
+	}
+
+	/* Plug it into this CPUs CPC descriptor. */
+	per_cpu(cpc_desc_ptr, pr->id) = cpc_ptr;
+
+	/* Parse PSD data for this CPU */
+	ret = acpi_get_psd(cpc_ptr, handle);
+	if (ret)
+		goto out_free;
+
+	/* Register PCC channel once for all CPUs. */
+	if (!pcc_channel_acquired) {
+		ret = register_pcc_channel(pcc_subspace_idx);
+		if (ret)
+			goto out_free;
+	}
+
+	/* Everything looks okay */
+	pr_info("Successfully parsed CPC struct for CPU: %d\n", pr->id);
+
+	kfree(output.pointer);
+	return 0;
+
+out_free:
+	cpc_ptr = per_cpu(cpc_desc_ptr, pr->id);
+	kfree(cpc_ptr);
+
+out_buf_free:
+	kfree(output.pointer);
+	return -ENODEV;
+}
+EXPORT_SYMBOL_GPL(acpi_cppc_processor_probe);
+
+static u64 cpc_trans(struct cpc_register_resource *reg, int cmd, u64 write_val,
+		bool is_pcc)
+{
+	u64 addr;
+	u64 read_val = 0;
+
+	/* PCC communication addr space begins at byte offset 0x8. */
+	addr = is_pcc ? (u64)pcc_comm_addr + 0x8 + reg->cpc_entry.reg.address :
+		reg->cpc_entry.reg.address;
+
+	if (reg->type == ACPI_TYPE_BUFFER) {
+		switch (reg->cpc_entry.reg.bit_width) {
+		case 8:
+			if (cmd == CMD_READ)
+				read_val = readb((void *) (addr));
+			else if (cmd == CMD_WRITE)
+				writeb(write_val, (void *)(addr));
+			else
+				pr_debug("Unsupported cmd type: %d\n", cmd);
+			break;
+		case 16:
+			if (cmd == CMD_READ)
+				read_val = readw((void *) (addr));
+			else if (cmd == CMD_WRITE)
+				writew(write_val, (void *)(addr));
+			else
+				pr_debug("Unsupported cmd type: %d\n", cmd);
+			break;
+		case 32:
+			if (cmd == CMD_READ)
+				read_val = readl((void *) (addr));
+			else if (cmd == CMD_WRITE)
+				writel(write_val, (void *)(addr));
+			else
+				pr_debug("Unsupported cmd type: %d\n", cmd);
+			break;
+		case 64:
+			if (cmd == CMD_READ)
+				read_val = readq((void *) (addr));
+			else if (cmd == CMD_WRITE)
+				writeq(write_val, (void *)(addr));
+			else
+				pr_debug("Unsupported cmd type: %d\n", cmd);
+			break;
+		default:
+			pr_debug("Unsupported bit width for CPC cmd:%d\n",
+					cmd);
+			break;
+		}
+	} else if (reg->type == ACPI_TYPE_INTEGER) {
+		if (cmd == CMD_READ)
+			read_val = reg->cpc_entry.int_value;
+		else if (cmd == CMD_WRITE)
+			reg->cpc_entry.int_value = write_val;
+		else
+			pr_debug("Unsupported cmd type: %d\n", cmd);
+	} else
+		pr_debug("Unsupported CPC entry type:%d\n", reg->type);
+
+	return read_val;
+}
+
+/**
+ * cppc_get_perf_caps - Get a CPUs performance capabilities.
+ * @cpunum: CPU from which to get capabilities info.
+ * @perf_caps: ptr to cppc_perf_caps. See cppc_acpi.h
+ *
+ * Return - 0 for success with perf_caps populated else
+ *	-ERRNO.
+ */
+int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps)
+{
+	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
+	struct cpc_register_resource *highest_reg, *lowest_reg, *ref_perf,
+				     *nom_perf;
+	u64 min, max, ref, nom;
+	bool is_pcc = false;
+	int ret;
+
+	if (!cpc_desc) {
+		pr_debug("No CPC descriptor for CPU:%d\n", cpunum);
+		return -ENODEV;
+	}
+
+	highest_reg = &cpc_desc->cpc_regs[HIGHEST_PERF];
+	lowest_reg = &cpc_desc->cpc_regs[LOWEST_PERF];
+	ref_perf = &cpc_desc->cpc_regs[REFERENCE_PERF];
+	nom_perf = &cpc_desc->cpc_regs[NOMINAL_PERF];
+
+	spin_lock(&pcc_lock);
+
+	/* Are any of the regs PCC ?*/
+	if ((highest_reg->cpc_entry.reg.space_id ==
+				ACPI_ADR_SPACE_PLATFORM_COMM) ||
+			(lowest_reg->cpc_entry.reg.space_id ==
+			 ACPI_ADR_SPACE_PLATFORM_COMM) ||
+			(ref_perf->cpc_entry.reg.space_id ==
+			 ACPI_ADR_SPACE_PLATFORM_COMM) ||
+			(nom_perf->cpc_entry.reg.space_id ==
+			 ACPI_ADR_SPACE_PLATFORM_COMM))
+		is_pcc = true;
+
+	if (is_pcc) {
+		/*
+		 * Min time OS should wait before sending
+		 * next command.
+		 */
+		udelay(pcc_cmd_delay);
+		/* Ring doorbell */
+		ret = send_pcc_cmd(CMD_READ);
+		if (ret) {
+			spin_unlock(&pcc_lock);
+			return -EIO;
+		}
+	}
+
+	max = cpc_trans(highest_reg, CMD_READ, 0, is_pcc);
+	perf_caps->highest_perf = max;
+
+	min = cpc_trans(lowest_reg, CMD_READ, 0, is_pcc);
+	perf_caps->lowest_perf = min;
+
+	ref = cpc_trans(ref_perf, CMD_READ, 0, is_pcc);
+	perf_caps->reference_perf = ref;
+
+	nom = cpc_trans(nom_perf, CMD_READ, 0, is_pcc);
+	perf_caps->nominal_perf = nom;
+
+	if (!ref)
+		perf_caps->reference_perf = perf_caps->nominal_perf;
+
+	spin_unlock(&pcc_lock);
+
+	if (!perf_caps->highest_perf ||
+			!perf_caps->lowest_perf ||
+			!perf_caps->reference_perf ||
+			!perf_caps->nominal_perf) {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cppc_get_perf_caps);
+
+/**
+ * cppc_get_perf_ctrs - Read a CPUs performance feedback counters.
+ * @cpunum: CPU from which to read counters.
+ * @perf_fb_ctrs: ptr to cppc_perf_fb_ctrs. See cppc_acpi.h
+ *
+ * Return - 0 for success with perf_fb_ctrs populated else
+ *	-ERRNO.
+ */
+int cppc_get_perf_ctrs(int cpunum, struct cppc_perf_fb_ctrs *perf_fb_ctrs)
+{
+	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
+	struct cpc_register_resource *delivered_reg, *reference_reg;
+	u64 delivered, reference;
+	bool is_pcc = false;
+	int ret;
+
+	if (!cpc_desc) {
+		pr_debug("No CPC descriptor for CPU:%d\n", cpunum);
+		return -ENODEV;
+	}
+
+	delivered_reg = &cpc_desc->cpc_regs[DELIVERED_CTR];
+	reference_reg = &cpc_desc->cpc_regs[REFERENCE_CTR];
+
+	spin_lock(&pcc_lock);
+
+	/* Are any of the regs PCC ?*/
+	if ((delivered_reg->cpc_entry.reg.space_id ==
+				ACPI_ADR_SPACE_PLATFORM_COMM) ||
+			(reference_reg->cpc_entry.reg.space_id ==
+			 ACPI_ADR_SPACE_PLATFORM_COMM))
+		is_pcc = true;
+
+	if (is_pcc) {
+		/*
+		 * Min time OS should wait before sending
+		 * next command.
+		 */
+		udelay(pcc_cmd_delay);
+		/* Ring doorbell */
+		ret = send_pcc_cmd(CMD_READ);
+		if (ret) {
+			spin_unlock(&pcc_lock);
+			return -EIO;
+		}
+	}
+
+	delivered = cpc_trans(delivered_reg, CMD_READ, 0, is_pcc);
+	reference = cpc_trans(reference_reg, CMD_READ, 0, is_pcc);
+
+	spin_unlock(&pcc_lock);
+
+	if (!delivered || !reference)
+		return -EINVAL;
+
+	perf_fb_ctrs->delivered = delivered;
+	perf_fb_ctrs->reference = reference;
+
+	perf_fb_ctrs->delivered -= perf_fb_ctrs->prev_delivered;
+	perf_fb_ctrs->reference -= perf_fb_ctrs->prev_reference;
+
+	perf_fb_ctrs->prev_delivered = delivered;
+	perf_fb_ctrs->prev_reference = reference;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cppc_get_perf_ctrs);
+
+/**
+ * cppc_set_perf - Set a CPUs performance controls.
+ * @cpu: CPU for which to set performance controls.
+ * @perf_ctrls: ptr to cppc_perf_ctrls. See cppc_acpi.h
+ *
+ * Return: 0 for success, -ERRNO otherwise.
+ */
+int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
+{
+	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu);
+	struct cpc_register_resource *desired_reg;
+	int ret = 0;
+	bool is_pcc = false;
+
+	if (!cpc_desc) {
+		pr_debug("No CPC descriptor for CPU:%d\n", cpu);
+		return -ENODEV;
+	}
+
+	desired_reg = &cpc_desc->cpc_regs[DESIRED_PERF];
+
+	spin_lock(&pcc_lock);
+
+	/* Is this a PCC reg ?*/
+	if (desired_reg->cpc_entry.reg.space_id ==
+			ACPI_ADR_SPACE_PLATFORM_COMM)
+		is_pcc = true;
+
+	cpc_trans(desired_reg, CMD_WRITE,
+			perf_ctrls->desired_perf, is_pcc);
+
+	if (is_pcc) {
+		/*
+		 * Min time OS should wait before sending
+		 * next command.
+		 */
+		udelay(pcc_cmd_delay);
+		/* Ring doorbell */
+		ret = send_pcc_cmd(CMD_READ);
+	}
+
+	spin_unlock(&pcc_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cppc_set_perf);
diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
new file mode 100644
index 0000000..b97d2b6
--- /dev/null
+++ b/include/acpi/cppc_acpi.h
@@ -0,0 +1,137 @@ 
+/*
+ * CPPC (Collaborative Processor Performance Control) methods used
+ * by CPUfreq drivers.
+ *
+ * (C) Copyright 2014, 2015 Linaro Ltd.
+ * Author: Ashwin Chaugule <[e-mail]>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#ifndef _CPPC_ACPI_H
+#define _CPPC_ACPI_H
+
+#include <linux/acpi.h>
+#include <linux/mailbox_controller.h>
+#include <linux/mailbox_client.h>
+#include <linux/types.h>
+
+#include <acpi/processor.h>
+
+/* Only support CPPCv2 for now. */
+#define CPPC_NUM_ENT	21
+#define CPPC_REV	2
+
+#define PCC_CMD_COMPLETE 1
+#define MAX_CPC_REG_ENT 19
+
+/* CPPC specific PCC commands. */
+#define	CMD_READ 0
+#define	CMD_WRITE 1
+
+/* Each register has the folowing format. */
+struct cpc_reg {
+	u8 descriptor;
+	u16 length;
+	u8 space_id;
+	u8 bit_width;
+	u8 bit_offset;
+	u8 access_width;
+	u64 __iomem address;
+} __packed;
+
+/*
+ * Each entry in the CPC table is either
+ * of type ACPI_TYPE_BUFFER or
+ * ACPI_TYPE_INTEGER.
+ */
+struct cpc_register_resource {
+	acpi_object_type type;
+	union {
+		struct cpc_reg reg;
+		u64 int_value;
+	} cpc_entry;
+};
+
+/* Container to hold the CPC details for each CPU */
+struct cpc_desc {
+	int num_entries;
+	int version;
+	struct cpc_register_resource cpc_regs[MAX_CPC_REG_ENT];
+	struct acpi_psd_package domain_info;
+};
+
+/* These are indexes into the per-cpu cpc_regs[]. Order is important. */
+enum cppc_regs {
+	HIGHEST_PERF,
+	NOMINAL_PERF,
+	LOW_NON_LINEAR_PERF,
+	LOWEST_PERF,
+	GUARANTEED_PERF,
+	DESIRED_PERF,
+	MIN_PERF,
+	MAX_PERF,
+	PERF_REDUC_TOLERANCE,
+	TIME_WINDOW,
+	CTR_WRAP_TIME,
+	REFERENCE_CTR,
+	DELIVERED_CTR,
+	PERF_LIMITED,
+	ENABLE,
+	AUTO_SEL_ENABLE,
+	AUTO_ACT_WINDOW,
+	ENERGY_PERF,
+	REFERENCE_PERF,
+};
+
+/*
+ * Categorization of registers as described
+ * in the ACPI v.5.1 spec.
+ * XXX: Only filling up ones which are used by governors
+ * today.
+ */
+struct cppc_perf_caps {
+	u32 highest_perf;
+	u32 nominal_perf;
+	u32 reference_perf;
+	u32 lowest_perf;
+};
+
+struct cppc_perf_ctrls {
+	u32 max_perf;
+	u32 min_perf;
+	u32 desired_perf;
+};
+
+struct cppc_perf_fb_ctrs {
+	u64 reference;
+	u64 prev_reference;
+	u64 delivered;
+	u64 prev_delivered;
+};
+
+/* Per CPU container for runtime CPPC management. */
+struct cpudata {
+	int cpu;
+	struct cppc_perf_caps perf_caps;
+	struct cppc_perf_ctrls perf_ctrls;
+	struct cppc_perf_fb_ctrs perf_fb_ctrs;
+	struct cpufreq_policy *cur_policy;
+	unsigned int shared_type;
+	cpumask_var_t shared_cpu_map;
+};
+
+extern int cppc_get_perf_ctrs(int cpu, struct cppc_perf_fb_ctrs *perf_fb_ctrs);
+extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls);
+extern int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps);
+extern int acpi_get_psd_map(struct cpudata **);
+
+/* Methods to interact with the PCC mailbox controller. */
+extern struct mbox_chan *
+	pcc_mbox_request_channel(struct mbox_client *, unsigned int);
+extern int mbox_send_message(struct mbox_chan *chan, void *mssg);
+
+#endif /* _CPPC_ACPI_H*/