[PATCH V3 00/16] intel_pmc: Add telemetry API to read counters

[PATCH V3 00/16] intel_pmc: Add telemetry API to read counters

[David E. Box]

On newer Intel silicon, more IP counters are being added in Intel Platform
Monitoring Technology (PMT) telemetry spaces hosted in MMIO.  There is a
need for the intel_pmc_core driver and other drivers to access PMT hosted
telemetry in the kernel using an API. This patchset adds driver APIs to
allow registering and reading telemetry entries. It makes changes to the
intel_pmc_core driver to use these interfaces to access the low power mode
counters that are now exclusively available from PMT.

David E. Box (11):
  platform/x86/intel/vsec: Move structures to header
  platform/x86/intel/vsec: remove platform_info from vsec device
    structure
  platform/x86/intel/vsec: Use cleanup.h
  platform/x86/intel/vsec: Add base address field
  platform/x86/intel/pmt: Add header to struct intel_pmt_entry
  platform/x86/intel/pmt: telemetry: Export API to read telemetry
  platform/x86/intel/pmc: Allow pmc_core_ssram_init to fail
  platform/x86/intel/pmc: Split pmc_core_ssram_get_pmc()
  platform/x86/intel/pmc: Find and register PMC telemetry entries
  platform/x86/intel/pmc: Add debug attribute for Die C6 counter
  platform/x86/intel/pmc: Show Die C6 counter on Meteor Lake

Gayatri Kammela (1):
  platform/x86/intel/vsec: Add intel_vsec_register

Rajvi Jingar (1):
  platform/x86/intel/pmc: Display LPM requirements for multiple PMCs

Xi Pardee (3):
  platform/x86:intel/pmc: Call pmc_get_low_power_modes from platform
    init
  platform/x86/intel/pmc: Retrieve LPM information using Intel PMT
  platform/x86/intel/pmc: Read low power mode requirements for MTL-M and
    MTL-P

 drivers/platform/x86/intel/pmc/Kconfig      |   1 +
 drivers/platform/x86/intel/pmc/adl.c        |   2 +
 drivers/platform/x86/intel/pmc/cnp.c        |   2 +
 drivers/platform/x86/intel/pmc/core.c       | 191 +++++++++----
 drivers/platform/x86/intel/pmc/core.h       |  10 +-
 drivers/platform/x86/intel/pmc/core_ssram.c | 299 +++++++++++++++++---
 drivers/platform/x86/intel/pmc/icl.c        |  10 +-
 drivers/platform/x86/intel/pmc/mtl.c        |  87 +++++-
 drivers/platform/x86/intel/pmc/spt.c        |  10 +-
 drivers/platform/x86/intel/pmc/tgl.c        |   1 +
 drivers/platform/x86/intel/pmt/class.c      |  43 ++-
 drivers/platform/x86/intel/pmt/class.h      |  30 +-
 drivers/platform/x86/intel/pmt/crashlog.c   |   2 +-
 drivers/platform/x86/intel/pmt/telemetry.c  | 193 ++++++++++++-
 drivers/platform/x86/intel/pmt/telemetry.h  | 126 +++++++++
 drivers/platform/x86/intel/vsec.c           |  84 +++---
 drivers/platform/x86/intel/vsec.h           |  44 ++-
 17 files changed, 946 insertions(+), 189 deletions(-)
 create mode 100644 drivers/platform/x86/intel/pmt/telemetry.h


base-commit: acce85a7dd28eac3858d44230f4c65985d0f271c
prerequisite-patch-id: abb063fc6746314786f443484ac711456df3e8a4
-- 
2.34.1

[PATCH V3 01/16] platform/x86/intel/vsec: Move structures to header

[David E. Box]

In preparation for exporting an API to register Intel Vendor Specific
Extended Capabilities (VSEC) from other drivers, move needed structures to
the header file.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
V3 - No change

V2 - New patch splitting previous PATCH 1

 drivers/platform/x86/intel/vsec.c | 35 ------------------------------
 drivers/platform/x86/intel/vsec.h | 36 +++++++++++++++++++++++++++++++
 2 files changed, 36 insertions(+), 35 deletions(-)

diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c
index ae811bb65910..6bb233a23414 100644
--- a/drivers/platform/x86/intel/vsec.c
+++ b/drivers/platform/x86/intel/vsec.c
@@ -24,13 +24,6 @@
 
 #include "vsec.h"
 
-/* Intel DVSEC offsets */
-#define INTEL_DVSEC_ENTRIES		0xA
-#define INTEL_DVSEC_SIZE		0xB
-#define INTEL_DVSEC_TABLE		0xC
-#define INTEL_DVSEC_TABLE_BAR(x)	((x) & GENMASK(2, 0))
-#define INTEL_DVSEC_TABLE_OFFSET(x)	((x) & GENMASK(31, 3))
-#define TABLE_OFFSET_SHIFT		3
 #define PMT_XA_START			0
 #define PMT_XA_MAX			INT_MAX
 #define PMT_XA_LIMIT			XA_LIMIT(PMT_XA_START, PMT_XA_MAX)
@@ -39,34 +32,6 @@ static DEFINE_IDA(intel_vsec_ida);
 static DEFINE_IDA(intel_vsec_sdsi_ida);
 static DEFINE_XARRAY_ALLOC(auxdev_array);
 
-/**
- * struct intel_vsec_header - Common fields of Intel VSEC and DVSEC registers.
- * @rev:         Revision ID of the VSEC/DVSEC register space
- * @length:      Length of the VSEC/DVSEC register space
- * @id:          ID of the feature
- * @num_entries: Number of instances of the feature
- * @entry_size:  Size of the discovery table for each feature
- * @tbir:        BAR containing the discovery tables
- * @offset:      BAR offset of start of the first discovery table
- */
-struct intel_vsec_header {
-	u8	rev;
-	u16	length;
-	u16	id;
-	u8	num_entries;
-	u8	entry_size;
-	u8	tbir;
-	u32	offset;
-};
-
-enum intel_vsec_id {
-	VSEC_ID_TELEMETRY	= 2,
-	VSEC_ID_WATCHER		= 3,
-	VSEC_ID_CRASHLOG	= 4,
-	VSEC_ID_SDSI		= 65,
-	VSEC_ID_TPMI		= 66,
-};
-
 static const char *intel_vsec_name(enum intel_vsec_id id)
 {
 	switch (id) {
diff --git a/drivers/platform/x86/intel/vsec.h b/drivers/platform/x86/intel/vsec.h
index 0a6201b4a0e9..c242c07ea69c 100644
--- a/drivers/platform/x86/intel/vsec.h
+++ b/drivers/platform/x86/intel/vsec.h
@@ -11,9 +11,45 @@
 #define VSEC_CAP_SDSI		BIT(3)
 #define VSEC_CAP_TPMI		BIT(4)
 
+/* Intel DVSEC offsets */
+#define INTEL_DVSEC_ENTRIES		0xA
+#define INTEL_DVSEC_SIZE		0xB
+#define INTEL_DVSEC_TABLE		0xC
+#define INTEL_DVSEC_TABLE_BAR(x)	((x) & GENMASK(2, 0))
+#define INTEL_DVSEC_TABLE_OFFSET(x)	((x) & GENMASK(31, 3))
+#define TABLE_OFFSET_SHIFT		3
+
 struct pci_dev;
 struct resource;
 
+enum intel_vsec_id {
+	VSEC_ID_TELEMETRY	= 2,
+	VSEC_ID_WATCHER		= 3,
+	VSEC_ID_CRASHLOG	= 4,
+	VSEC_ID_SDSI		= 65,
+	VSEC_ID_TPMI		= 66,
+};
+
+/**
+ * struct intel_vsec_header - Common fields of Intel VSEC and DVSEC registers.
+ * @rev:         Revision ID of the VSEC/DVSEC register space
+ * @length:      Length of the VSEC/DVSEC register space
+ * @id:          ID of the feature
+ * @num_entries: Number of instances of the feature
+ * @entry_size:  Size of the discovery table for each feature
+ * @tbir:        BAR containing the discovery tables
+ * @offset:      BAR offset of start of the first discovery table
+ */
+struct intel_vsec_header {
+	u8	rev;
+	u16	length;
+	u16	id;
+	u8	num_entries;
+	u8	entry_size;
+	u8	tbir;
+	u32	offset;
+};
+
 enum intel_vsec_quirks {
 	/* Watcher feature not supported */
 	VSEC_QUIRK_NO_WATCHER	= BIT(0),
-- 
2.34.1

[PATCH V3 02/16] platform/x86/intel/vsec: remove platform_info from vsec device structure

[David E. Box]

In preparation for exporting an API to register Intel Vendor Specific
Extended Capabilities (VSEC) from other drivers, remove the pointer to
platform_info from intel_vsec_device. This prevents a potential page fault
when auxiliary drivers probe and attempt to dereference this pointer to
access the needed quirks field. Instead, just add the quirks to
intel_vsec_device.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
V3 - No change

V2 - New patch splitting previous PATCH 1

 drivers/platform/x86/intel/pmt/class.c | 2 +-
 drivers/platform/x86/intel/vsec.c      | 2 +-
 drivers/platform/x86/intel/vsec.h      | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/platform/x86/intel/pmt/class.c b/drivers/platform/x86/intel/pmt/class.c
index f32a233470de..2ad91d2fd954 100644
--- a/drivers/platform/x86/intel/pmt/class.c
+++ b/drivers/platform/x86/intel/pmt/class.c
@@ -31,7 +31,7 @@ bool intel_pmt_is_early_client_hw(struct device *dev)
 	 * differences from the server platforms (which use the Out Of Band
 	 * Management Services Module OOBMSM).
 	 */
-	return !!(ivdev->info->quirks & VSEC_QUIRK_EARLY_HW);
+	return !!(ivdev->quirks & VSEC_QUIRK_EARLY_HW);
 }
 EXPORT_SYMBOL_NS_GPL(intel_pmt_is_early_client_hw, INTEL_PMT);
 
diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c
index 6bb233a23414..15866b7d3117 100644
--- a/drivers/platform/x86/intel/vsec.c
+++ b/drivers/platform/x86/intel/vsec.c
@@ -201,7 +201,7 @@ static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *he
 	intel_vsec_dev->pcidev = pdev;
 	intel_vsec_dev->resource = res;
 	intel_vsec_dev->num_resources = header->num_entries;
-	intel_vsec_dev->info = info;
+	intel_vsec_dev->quirks = info->quirks;
 
 	if (header->id == VSEC_ID_SDSI)
 		intel_vsec_dev->ida = &intel_vsec_sdsi_ida;
diff --git a/drivers/platform/x86/intel/vsec.h b/drivers/platform/x86/intel/vsec.h
index c242c07ea69c..8b9fad170503 100644
--- a/drivers/platform/x86/intel/vsec.h
+++ b/drivers/platform/x86/intel/vsec.h
@@ -79,11 +79,11 @@ struct intel_vsec_device {
 	struct pci_dev *pcidev;
 	struct resource *resource;
 	struct ida *ida;
-	struct intel_vsec_platform_info *info;
 	int num_resources;
 	int id; /* xa */
 	void *priv_data;
 	size_t priv_data_size;
+	unsigned long quirks;
 };
 
 int intel_vsec_add_aux(struct pci_dev *pdev, struct device *parent,
-- 
2.34.1

[PATCH V3 03/16] platform/x86/intel/vsec: Use cleanup.h

[David E. Box]

Use cleanup.h helpers to handle cleanup of resources in
intel_vsec_add_dev() after failures.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
---
V3 - New patch.

 drivers/platform/x86/intel/vsec.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c
index 15866b7d3117..f03ab89ab7c0 100644
--- a/drivers/platform/x86/intel/vsec.c
+++ b/drivers/platform/x86/intel/vsec.c
@@ -15,6 +15,7 @@
 
 #include <linux/auxiliary_bus.h>
 #include <linux/bits.h>
+#include <linux/cleanup.h>
 #include <linux/delay.h>
 #include <linux/kernel.h>
 #include <linux/idr.h>
@@ -155,10 +156,10 @@ EXPORT_SYMBOL_NS_GPL(intel_vsec_add_aux, INTEL_VSEC);
 static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *header,
 			      struct intel_vsec_platform_info *info)
 {
-	struct intel_vsec_device *intel_vsec_dev;
+	struct intel_vsec_device __free(kfree) *intel_vsec_dev = NULL;
 	struct resource *res, *tmp;
 	unsigned long quirks = info->quirks;
-	int i;
+	int ret, i;
 
 	if (!intel_vsec_supported(header->id, info->caps))
 		return -EINVAL;
@@ -178,10 +179,8 @@ static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *he
 		return -ENOMEM;
 
 	res = kcalloc(header->num_entries, sizeof(*res), GFP_KERNEL);
-	if (!res) {
-		kfree(intel_vsec_dev);
+	if (!res)
 		return -ENOMEM;
-	}
 
 	if (quirks & VSEC_QUIRK_TABLE_SHIFT)
 		header->offset >>= TABLE_OFFSET_SHIFT;
@@ -208,8 +207,12 @@ static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *he
 	else
 		intel_vsec_dev->ida = &intel_vsec_ida;
 
-	return intel_vsec_add_aux(pdev, NULL, intel_vsec_dev,
-				  intel_vsec_name(header->id));
+	ret = intel_vsec_add_aux(pdev, NULL, intel_vsec_dev,
+				 intel_vsec_name(header->id));
+
+	no_free_ptr(intel_vsec_dev);
+
+	return ret;
 }
 
 static bool intel_vsec_walk_header(struct pci_dev *pdev,
-- 
2.34.1

[PATCH V3 04/16] platform/x86/intel/vsec: Add intel_vsec_register

[David E. Box]

From: Gayatri Kammela <gayatri.kammela@linux.intel.com>

Add and export intel_vsec_register() to allow the registration of Intel
extended capabilities from other drivers. Add check to look for memory
conflicts before registering a new capability. Add a parent field to
intel_vsec_platform_info to allow specifying the parent device for
device managed cleanup.

Signed-off-by: Gayatri Kammela <gayatri.kammela@linux.intel.com>
Signed-off-by: David E. Box <david.e.box@linux.intel.com>
---
V3 - Replace kfree on request_mem_region fail with use of cleanup.h helper.

V2 - New patch splitting previous PATCH 1

 drivers/platform/x86/intel/vsec.c | 22 ++++++++++++++++++++--
 drivers/platform/x86/intel/vsec.h |  4 ++++
 2 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c
index f03ab89ab7c0..1d005077024a 100644
--- a/drivers/platform/x86/intel/vsec.c
+++ b/drivers/platform/x86/intel/vsec.c
@@ -157,7 +157,8 @@ static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *he
 			      struct intel_vsec_platform_info *info)
 {
 	struct intel_vsec_device __free(kfree) *intel_vsec_dev = NULL;
-	struct resource *res, *tmp;
+	struct resource __free(kfree) *res = NULL;
+	struct resource *tmp;
 	unsigned long quirks = info->quirks;
 	int ret, i;
 
@@ -195,6 +196,12 @@ static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *he
 			     header->offset + i * (header->entry_size * sizeof(u32));
 		tmp->end = tmp->start + (header->entry_size * sizeof(u32)) - 1;
 		tmp->flags = IORESOURCE_MEM;
+
+		/* Check resource is not in use */
+		if (!request_mem_region(tmp->start, resource_size(tmp), ""))
+			return -EBUSY;
+
+		release_mem_region(tmp->start, resource_size(tmp));
 	}
 
 	intel_vsec_dev->pcidev = pdev;
@@ -207,9 +214,10 @@ static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *he
 	else
 		intel_vsec_dev->ida = &intel_vsec_ida;
 
-	ret = intel_vsec_add_aux(pdev, NULL, intel_vsec_dev,
+	ret = intel_vsec_add_aux(pdev, info->parent, intel_vsec_dev,
 				 intel_vsec_name(header->id));
 
+	no_free_ptr(res);
 	no_free_ptr(intel_vsec_dev);
 
 	return ret;
@@ -329,6 +337,16 @@ static bool intel_vsec_walk_vsec(struct pci_dev *pdev,
 	return have_devices;
 }
 
+void intel_vsec_register(struct pci_dev *pdev,
+			 struct intel_vsec_platform_info *info)
+{
+	if (!pdev || !info)
+		return;
+
+	intel_vsec_walk_header(pdev, info);
+}
+EXPORT_SYMBOL_NS_GPL(intel_vsec_register, INTEL_VSEC);
+
 static int intel_vsec_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct intel_vsec_platform_info *info;
diff --git a/drivers/platform/x86/intel/vsec.h b/drivers/platform/x86/intel/vsec.h
index 8b9fad170503..bb8b6452df70 100644
--- a/drivers/platform/x86/intel/vsec.h
+++ b/drivers/platform/x86/intel/vsec.h
@@ -69,6 +69,7 @@ enum intel_vsec_quirks {
 
 /* Platform specific data */
 struct intel_vsec_platform_info {
+	struct device *parent;
 	struct intel_vsec_header **headers;
 	unsigned long caps;
 	unsigned long quirks;
@@ -99,4 +100,7 @@ static inline struct intel_vsec_device *auxdev_to_ivdev(struct auxiliary_device
 {
 	return container_of(auxdev, struct intel_vsec_device, auxdev);
 }
+
+void intel_vsec_register(struct pci_dev *pdev,
+			 struct intel_vsec_platform_info *info);
 #endif
-- 
2.34.1

[PATCH V3 05/16] platform/x86/intel/vsec: Add base address field

[David E. Box]

Some devices may emulate PCI VSEC capabilities in MMIO. In such cases the
BAR is not readable from a config space. Provide a field for drivers to
indicate the base address to be used.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
V3 - No change

V2 - No change

 drivers/platform/x86/intel/pmt/class.c | 14 +++++++++++---
 drivers/platform/x86/intel/vsec.c      | 10 ++++++++--
 drivers/platform/x86/intel/vsec.h      |  2 ++
 3 files changed, 21 insertions(+), 5 deletions(-)

diff --git a/drivers/platform/x86/intel/pmt/class.c b/drivers/platform/x86/intel/pmt/class.c
index 2ad91d2fd954..32608baaa56c 100644
--- a/drivers/platform/x86/intel/pmt/class.c
+++ b/drivers/platform/x86/intel/pmt/class.c
@@ -160,10 +160,11 @@ static struct class intel_pmt_class = {
 
 static int intel_pmt_populate_entry(struct intel_pmt_entry *entry,
 				    struct intel_pmt_header *header,
-				    struct device *dev,
+				    struct intel_vsec_device *ivdev,
 				    struct resource *disc_res)
 {
-	struct pci_dev *pci_dev = to_pci_dev(dev->parent);
+	struct pci_dev *pci_dev = ivdev->pcidev;
+	struct device *dev = &ivdev->auxdev.dev;
 	u8 bir;
 
 	/*
@@ -215,6 +216,13 @@ static int intel_pmt_populate_entry(struct intel_pmt_entry *entry,
 
 		break;
 	case ACCESS_BARID:
+		/* Use the provided base address if it exists */
+		if (ivdev->base_addr) {
+			entry->base_addr = ivdev->base_addr +
+				   GET_ADDRESS(header->base_offset);
+			break;
+		}
+
 		/*
 		 * If another BAR was specified then the base offset
 		 * represents the offset within that BAR. SO retrieve the
@@ -319,7 +327,7 @@ int intel_pmt_dev_create(struct intel_pmt_entry *entry, struct intel_pmt_namespa
 	if (ret)
 		return ret;
 
-	ret = intel_pmt_populate_entry(entry, &header, dev, disc_res);
+	ret = intel_pmt_populate_entry(entry, &header, intel_vsec_dev, disc_res);
 	if (ret)
 		return ret;
 
diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c
index 1d005077024a..5e18a06395e0 100644
--- a/drivers/platform/x86/intel/vsec.c
+++ b/drivers/platform/x86/intel/vsec.c
@@ -160,6 +160,7 @@ static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *he
 	struct resource __free(kfree) *res = NULL;
 	struct resource *tmp;
 	unsigned long quirks = info->quirks;
+	u64 base_addr;
 	int ret, i;
 
 	if (!intel_vsec_supported(header->id, info->caps))
@@ -186,14 +187,18 @@ static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *he
 	if (quirks & VSEC_QUIRK_TABLE_SHIFT)
 		header->offset >>= TABLE_OFFSET_SHIFT;
 
+	if (info->base_addr)
+		base_addr = info->base_addr;
+	else
+		base_addr = pdev->resource[header->tbir].start;
+
 	/*
 	 * The DVSEC/VSEC contains the starting offset and count for a block of
 	 * discovery tables. Create a resource array of these tables to the
 	 * auxiliary device driver.
 	 */
 	for (i = 0, tmp = res; i < header->num_entries; i++, tmp++) {
-		tmp->start = pdev->resource[header->tbir].start +
-			     header->offset + i * (header->entry_size * sizeof(u32));
+		tmp->start = base_addr + header->offset + i * (header->entry_size * sizeof(u32));
 		tmp->end = tmp->start + (header->entry_size * sizeof(u32)) - 1;
 		tmp->flags = IORESOURCE_MEM;
 
@@ -208,6 +213,7 @@ static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *he
 	intel_vsec_dev->resource = res;
 	intel_vsec_dev->num_resources = header->num_entries;
 	intel_vsec_dev->quirks = info->quirks;
+	intel_vsec_dev->base_addr = info->base_addr;
 
 	if (header->id == VSEC_ID_SDSI)
 		intel_vsec_dev->ida = &intel_vsec_sdsi_ida;
diff --git a/drivers/platform/x86/intel/vsec.h b/drivers/platform/x86/intel/vsec.h
index bb8b6452df70..e23e76129691 100644
--- a/drivers/platform/x86/intel/vsec.h
+++ b/drivers/platform/x86/intel/vsec.h
@@ -73,6 +73,7 @@ struct intel_vsec_platform_info {
 	struct intel_vsec_header **headers;
 	unsigned long caps;
 	unsigned long quirks;
+	u64 base_addr;
 };
 
 struct intel_vsec_device {
@@ -85,6 +86,7 @@ struct intel_vsec_device {
 	void *priv_data;
 	size_t priv_data_size;
 	unsigned long quirks;
+	u64 base_addr;
 };
 
 int intel_vsec_add_aux(struct pci_dev *pdev, struct device *parent,
-- 
2.34.1

[PATCH V3 06/16] platform/x86/intel/pmt: Add header to struct intel_pmt_entry

[David E. Box]

The PMT header is passed to several functions. Instead, store the header in
struct intel_pmt_entry which is also passed to these functions and shorten
the argument list. This simplifies the calls in preparation for later
changes.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
V3 - No change

V2 - No change

 drivers/platform/x86/intel/pmt/class.c     |  8 +++-----
 drivers/platform/x86/intel/pmt/class.h     | 16 ++++++++--------
 drivers/platform/x86/intel/pmt/crashlog.c  |  2 +-
 drivers/platform/x86/intel/pmt/telemetry.c |  2 +-
 4 files changed, 13 insertions(+), 15 deletions(-)

diff --git a/drivers/platform/x86/intel/pmt/class.c b/drivers/platform/x86/intel/pmt/class.c
index 32608baaa56c..142a24e3727d 100644
--- a/drivers/platform/x86/intel/pmt/class.c
+++ b/drivers/platform/x86/intel/pmt/class.c
@@ -159,12 +159,12 @@ static struct class intel_pmt_class = {
 };
 
 static int intel_pmt_populate_entry(struct intel_pmt_entry *entry,
-				    struct intel_pmt_header *header,
 				    struct intel_vsec_device *ivdev,
 				    struct resource *disc_res)
 {
 	struct pci_dev *pci_dev = ivdev->pcidev;
 	struct device *dev = &ivdev->auxdev.dev;
+	struct intel_pmt_header *header = &entry->header;
 	u8 bir;
 
 	/*
@@ -313,7 +313,6 @@ int intel_pmt_dev_create(struct intel_pmt_entry *entry, struct intel_pmt_namespa
 			 struct intel_vsec_device *intel_vsec_dev, int idx)
 {
 	struct device *dev = &intel_vsec_dev->auxdev.dev;
-	struct intel_pmt_header header;
 	struct resource	*disc_res;
 	int ret;
 
@@ -323,16 +322,15 @@ int intel_pmt_dev_create(struct intel_pmt_entry *entry, struct intel_pmt_namespa
 	if (IS_ERR(entry->disc_table))
 		return PTR_ERR(entry->disc_table);
 
-	ret = ns->pmt_header_decode(entry, &header, dev);
+	ret = ns->pmt_header_decode(entry, dev);
 	if (ret)
 		return ret;
 
-	ret = intel_pmt_populate_entry(entry, &header, intel_vsec_dev, disc_res);
+	ret = intel_pmt_populate_entry(entry, intel_vsec_dev, disc_res);
 	if (ret)
 		return ret;
 
 	return intel_pmt_dev_register(entry, ns, dev);
-
 }
 EXPORT_SYMBOL_NS_GPL(intel_pmt_dev_create, INTEL_PMT);
 
diff --git a/drivers/platform/x86/intel/pmt/class.h b/drivers/platform/x86/intel/pmt/class.h
index db11d58867ce..e477a19f6700 100644
--- a/drivers/platform/x86/intel/pmt/class.h
+++ b/drivers/platform/x86/intel/pmt/class.h
@@ -18,7 +18,15 @@
 #define GET_BIR(v)		((v) & GENMASK(2, 0))
 #define GET_ADDRESS(v)		((v) & GENMASK(31, 3))
 
+struct intel_pmt_header {
+	u32	base_offset;
+	u32	size;
+	u32	guid;
+	u8	access_type;
+};
+
 struct intel_pmt_entry {
+	struct intel_pmt_header	header;
 	struct bin_attribute	pmt_bin_attr;
 	struct kobject		*kobj;
 	void __iomem		*disc_table;
@@ -29,19 +37,11 @@ struct intel_pmt_entry {
 	int			devid;
 };
 
-struct intel_pmt_header {
-	u32	base_offset;
-	u32	size;
-	u32	guid;
-	u8	access_type;
-};
-
 struct intel_pmt_namespace {
 	const char *name;
 	struct xarray *xa;
 	const struct attribute_group *attr_grp;
 	int (*pmt_header_decode)(struct intel_pmt_entry *entry,
-				 struct intel_pmt_header *header,
 				 struct device *dev);
 };
 
diff --git a/drivers/platform/x86/intel/pmt/crashlog.c b/drivers/platform/x86/intel/pmt/crashlog.c
index bbb3d61d09f4..4014c02cafdb 100644
--- a/drivers/platform/x86/intel/pmt/crashlog.c
+++ b/drivers/platform/x86/intel/pmt/crashlog.c
@@ -223,10 +223,10 @@ static const struct attribute_group pmt_crashlog_group = {
 };
 
 static int pmt_crashlog_header_decode(struct intel_pmt_entry *entry,
-				      struct intel_pmt_header *header,
 				      struct device *dev)
 {
 	void __iomem *disc_table = entry->disc_table;
+	struct intel_pmt_header *header = &entry->header;
 	struct crashlog_entry *crashlog;
 
 	if (!pmt_crashlog_supported(entry))
diff --git a/drivers/platform/x86/intel/pmt/telemetry.c b/drivers/platform/x86/intel/pmt/telemetry.c
index 39cbc87cc28a..f86080e8bebd 100644
--- a/drivers/platform/x86/intel/pmt/telemetry.c
+++ b/drivers/platform/x86/intel/pmt/telemetry.c
@@ -58,10 +58,10 @@ static bool pmt_telem_region_overlaps(struct intel_pmt_entry *entry,
 }
 
 static int pmt_telem_header_decode(struct intel_pmt_entry *entry,
-				   struct intel_pmt_header *header,
 				   struct device *dev)
 {
 	void __iomem *disc_table = entry->disc_table;
+	struct intel_pmt_header *header = &entry->header;
 
 	if (pmt_telem_region_overlaps(entry, dev))
 		return 1;
-- 
2.34.1

[PATCH V3 07/16] platform/x86/intel/pmt: telemetry: Export API to read telemetry

[David E. Box]

Export symbols to allow access to Intel PMT Telemetry data on available
devices. Provides APIs to search, register, and read telemetry using a
kref managed pointer that serves as a handle to a telemetry endpoint.
To simplify searching for present devices, have the IDA start at 1
instead of 0 so that 0 can be used to indicate end of search.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
V3 - Add comment for mutex lock
   - Fix multiline comments
   - Fix line lengths
   - Fix space/tab inconsistences in header doc

V2 - Add explanation of PMT_XA_START change in changelog
   - change return and argument type of pmt_telem_get_next_endpoint() to
     unsigned long
   - style fixes

 drivers/platform/x86/intel/pmt/class.c     |  21 ++-
 drivers/platform/x86/intel/pmt/class.h     |  14 ++
 drivers/platform/x86/intel/pmt/telemetry.c | 191 ++++++++++++++++++++-
 drivers/platform/x86/intel/pmt/telemetry.h | 126 ++++++++++++++
 4 files changed, 344 insertions(+), 8 deletions(-)
 create mode 100644 drivers/platform/x86/intel/pmt/telemetry.h

diff --git a/drivers/platform/x86/intel/pmt/class.c b/drivers/platform/x86/intel/pmt/class.c
index 142a24e3727d..4b53940a64e2 100644
--- a/drivers/platform/x86/intel/pmt/class.c
+++ b/drivers/platform/x86/intel/pmt/class.c
@@ -17,7 +17,7 @@
 #include "../vsec.h"
 #include "class.h"
 
-#define PMT_XA_START		0
+#define PMT_XA_START		1
 #define PMT_XA_MAX		INT_MAX
 #define PMT_XA_LIMIT		XA_LIMIT(PMT_XA_START, PMT_XA_MAX)
 #define GUID_SPR_PUNIT		0x9956f43f
@@ -247,6 +247,7 @@ static int intel_pmt_dev_register(struct intel_pmt_entry *entry,
 				  struct intel_pmt_namespace *ns,
 				  struct device *parent)
 {
+	struct intel_vsec_device *ivdev = dev_to_ivdev(parent);
 	struct resource res = {0};
 	struct device *dev;
 	int ret;
@@ -270,7 +271,7 @@ static int intel_pmt_dev_register(struct intel_pmt_entry *entry,
 	if (ns->attr_grp) {
 		ret = sysfs_create_group(entry->kobj, ns->attr_grp);
 		if (ret)
-			goto fail_sysfs;
+			goto fail_sysfs_create_group;
 	}
 
 	/* if size is 0 assume no data buffer, so no file needed */
@@ -295,13 +296,23 @@ static int intel_pmt_dev_register(struct intel_pmt_entry *entry,
 	entry->pmt_bin_attr.size = entry->size;
 
 	ret = sysfs_create_bin_file(&dev->kobj, &entry->pmt_bin_attr);
-	if (!ret)
-		return 0;
+	if (ret)
+		goto fail_ioremap;
 
+	if (ns->pmt_add_endpoint) {
+		ret = ns->pmt_add_endpoint(entry, ivdev->pcidev);
+		if (ret)
+			goto fail_add_endpoint;
+	}
+
+	return 0;
+
+fail_add_endpoint:
+	sysfs_remove_bin_file(entry->kobj, &entry->pmt_bin_attr);
 fail_ioremap:
 	if (ns->attr_grp)
 		sysfs_remove_group(entry->kobj, ns->attr_grp);
-fail_sysfs:
+fail_sysfs_create_group:
 	device_unregister(dev);
 fail_dev_create:
 	xa_erase(ns->xa, entry->devid);
diff --git a/drivers/platform/x86/intel/pmt/class.h b/drivers/platform/x86/intel/pmt/class.h
index e477a19f6700..d23c63b73ab7 100644
--- a/drivers/platform/x86/intel/pmt/class.h
+++ b/drivers/platform/x86/intel/pmt/class.h
@@ -9,6 +9,7 @@
 #include <linux/io.h>
 
 #include "../vsec.h"
+#include "telemetry.h"
 
 /* PMT access types */
 #define ACCESS_BARID		2
@@ -18,6 +19,16 @@
 #define GET_BIR(v)		((v) & GENMASK(2, 0))
 #define GET_ADDRESS(v)		((v) & GENMASK(31, 3))
 
+struct pci_dev;
+
+struct telem_endpoint {
+	struct pci_dev		*pcidev;
+	struct telem_header	header;
+	void __iomem		*base;
+	bool			present;
+	struct kref		kref;
+};
+
 struct intel_pmt_header {
 	u32	base_offset;
 	u32	size;
@@ -26,6 +37,7 @@ struct intel_pmt_header {
 };
 
 struct intel_pmt_entry {
+	struct telem_endpoint	*ep;
 	struct intel_pmt_header	header;
 	struct bin_attribute	pmt_bin_attr;
 	struct kobject		*kobj;
@@ -43,6 +55,8 @@ struct intel_pmt_namespace {
 	const struct attribute_group *attr_grp;
 	int (*pmt_header_decode)(struct intel_pmt_entry *entry,
 				 struct device *dev);
+	int (*pmt_add_endpoint)(struct intel_pmt_entry *entry,
+				struct pci_dev *pdev);
 };
 
 bool intel_pmt_is_early_client_hw(struct device *dev);
diff --git a/drivers/platform/x86/intel/pmt/telemetry.c b/drivers/platform/x86/intel/pmt/telemetry.c
index f86080e8bebd..09258564dfc4 100644
--- a/drivers/platform/x86/intel/pmt/telemetry.c
+++ b/drivers/platform/x86/intel/pmt/telemetry.c
@@ -30,6 +30,15 @@
 /* Used by client hardware to identify a fixed telemetry entry*/
 #define TELEM_CLIENT_FIXED_BLOCK_GUID	0x10000000
 
+#define NUM_BYTES_QWORD(v)	((v) << 3)
+#define SAMPLE_ID_OFFSET(v)	((v) << 3)
+
+#define NUM_BYTES_DWORD(v)	((v) << 2)
+#define SAMPLE_ID_OFFSET32(v)	((v) << 2)
+
+/* Protects access to the xarray of telemetry endpoint handles */
+static DEFINE_MUTEX(ep_lock);
+
 enum telem_type {
 	TELEM_TYPE_PUNIT = 0,
 	TELEM_TYPE_CRASHLOG,
@@ -84,21 +93,195 @@ static int pmt_telem_header_decode(struct intel_pmt_entry *entry,
 	return 0;
 }
 
+static int pmt_telem_add_endpoint(struct intel_pmt_entry *entry,
+				  struct pci_dev *pdev)
+{
+	struct telem_endpoint *ep;
+
+	/* Endpoint lifetimes are managed by kref, not devres */
+	entry->ep = kzalloc(sizeof(*(entry->ep)), GFP_KERNEL);
+	if (!entry->ep)
+		return -ENOMEM;
+
+	ep = entry->ep;
+	ep->pcidev = pdev;
+	ep->header.access_type = entry->header.access_type;
+	ep->header.guid = entry->header.guid;
+	ep->header.base_offset = entry->header.base_offset;
+	ep->header.size = entry->header.size;
+	ep->base = entry->base;
+	ep->present = true;
+
+	kref_init(&ep->kref);
+
+	return 0;
+}
+
 static DEFINE_XARRAY_ALLOC(telem_array);
 static struct intel_pmt_namespace pmt_telem_ns = {
 	.name = "telem",
 	.xa = &telem_array,
 	.pmt_header_decode = pmt_telem_header_decode,
+	.pmt_add_endpoint = pmt_telem_add_endpoint,
 };
 
+/* Called when all users unregister and the device is removed */
+static void pmt_telem_ep_release(struct kref *kref)
+{
+	struct telem_endpoint *ep;
+
+	ep = container_of(kref, struct telem_endpoint, kref);
+	kfree(ep);
+}
+
+unsigned long pmt_telem_get_next_endpoint(unsigned long start)
+{
+	struct intel_pmt_entry *entry;
+	unsigned long found_idx;
+
+	mutex_lock(&ep_lock);
+	xa_for_each_start(&telem_array, found_idx, entry, start) {
+		/*
+		 * Return first found index after start.
+		 * 0 is not valid id.
+		 */
+		if (found_idx > start)
+			break;
+	}
+	mutex_unlock(&ep_lock);
+
+	return found_idx == start ? 0 : found_idx;
+}
+EXPORT_SYMBOL_NS_GPL(pmt_telem_get_next_endpoint, INTEL_PMT_TELEMETRY);
+
+struct telem_endpoint *pmt_telem_register_endpoint(int devid)
+{
+	struct intel_pmt_entry *entry;
+	unsigned long index = devid;
+
+	mutex_lock(&ep_lock);
+	entry = xa_find(&telem_array, &index, index, XA_PRESENT);
+	if (!entry) {
+		mutex_unlock(&ep_lock);
+		return ERR_PTR(-ENXIO);
+	}
+
+	kref_get(&entry->ep->kref);
+	mutex_unlock(&ep_lock);
+
+	return entry->ep;
+}
+EXPORT_SYMBOL_NS_GPL(pmt_telem_register_endpoint, INTEL_PMT_TELEMETRY);
+
+void pmt_telem_unregister_endpoint(struct telem_endpoint *ep)
+{
+	kref_put(&ep->kref, pmt_telem_ep_release);
+}
+EXPORT_SYMBOL_NS_GPL(pmt_telem_unregister_endpoint, INTEL_PMT_TELEMETRY);
+
+int pmt_telem_get_endpoint_info(int devid, struct telem_endpoint_info *info)
+{
+	struct intel_pmt_entry *entry;
+	unsigned long index = devid;
+	int err = 0;
+
+	if (!info)
+		return -EINVAL;
+
+	mutex_lock(&ep_lock);
+	entry = xa_find(&telem_array, &index, index, XA_PRESENT);
+	if (!entry) {
+		err = -ENXIO;
+		goto unlock;
+	}
+
+	info->pdev = entry->ep->pcidev;
+	info->header = entry->ep->header;
+
+unlock:
+	mutex_unlock(&ep_lock);
+	return err;
+
+}
+EXPORT_SYMBOL_NS_GPL(pmt_telem_get_endpoint_info, INTEL_PMT_TELEMETRY);
+
+int pmt_telem_read(struct telem_endpoint *ep, u32 id, u64 *data, u32 count)
+{
+	u32 offset, size;
+
+	if (!ep->present)
+		return -ENODEV;
+
+	offset = SAMPLE_ID_OFFSET(id);
+	size = ep->header.size;
+
+	if (offset + NUM_BYTES_QWORD(count) > size)
+		return -EINVAL;
+
+	memcpy_fromio(data, ep->base + offset, NUM_BYTES_QWORD(count));
+
+	return ep->present ? 0 : -EPIPE;
+}
+EXPORT_SYMBOL_NS_GPL(pmt_telem_read, INTEL_PMT_TELEMETRY);
+
+int pmt_telem_read32(struct telem_endpoint *ep, u32 id, u32 *data, u32 count)
+{
+	u32 offset, size;
+
+	if (!ep->present)
+		return -ENODEV;
+
+	offset = SAMPLE_ID_OFFSET32(id);
+	size = ep->header.size;
+
+	if (offset + NUM_BYTES_DWORD(count) > size)
+		return -EINVAL;
+
+	memcpy_fromio(data, ep->base + offset, NUM_BYTES_DWORD(count));
+
+	return ep->present ? 0 : -EPIPE;
+}
+EXPORT_SYMBOL_NS_GPL(pmt_telem_read32, INTEL_PMT_TELEMETRY);
+
+struct telem_endpoint *
+pmt_telem_find_and_register_endpoint(struct pci_dev *pcidev, u32 guid, u16 pos)
+{
+	int devid = 0;
+	int inst = 0;
+	int err = 0;
+
+	while ((devid = pmt_telem_get_next_endpoint(devid))) {
+		struct telem_endpoint_info ep_info;
+
+		err = pmt_telem_get_endpoint_info(devid, &ep_info);
+		if (err)
+			return ERR_PTR(err);
+
+		if (ep_info.header.guid == guid && ep_info.pdev == pcidev) {
+			if (inst == pos)
+				return pmt_telem_register_endpoint(devid);
+			++inst;
+		}
+	}
+
+	return ERR_PTR(-ENXIO);
+}
+EXPORT_SYMBOL_NS_GPL(pmt_telem_find_and_register_endpoint, INTEL_PMT_TELEMETRY);
+
 static void pmt_telem_remove(struct auxiliary_device *auxdev)
 {
 	struct pmt_telem_priv *priv = auxiliary_get_drvdata(auxdev);
 	int i;
 
-	for (i = 0; i < priv->num_entries; i++)
-		intel_pmt_dev_destroy(&priv->entry[i], &pmt_telem_ns);
-}
+	mutex_lock(&ep_lock);
+	for (i = 0; i < priv->num_entries; i++) {
+		struct intel_pmt_entry *entry = &priv->entry[i];
+
+		kref_put(&entry->ep->kref, pmt_telem_ep_release);
+		intel_pmt_dev_destroy(entry, &pmt_telem_ns);
+	}
+	mutex_unlock(&ep_lock);
+};
 
 static int pmt_telem_probe(struct auxiliary_device *auxdev, const struct auxiliary_device_id *id)
 {
@@ -117,7 +300,9 @@ static int pmt_telem_probe(struct auxiliary_device *auxdev, const struct auxilia
 	for (i = 0; i < intel_vsec_dev->num_resources; i++) {
 		struct intel_pmt_entry *entry = &priv->entry[priv->num_entries];
 
+		mutex_lock(&ep_lock);
 		ret = intel_pmt_dev_create(entry, &pmt_telem_ns, intel_vsec_dev, i);
+		mutex_unlock(&ep_lock);
 		if (ret < 0)
 			goto abort_probe;
 		if (ret)
diff --git a/drivers/platform/x86/intel/pmt/telemetry.h b/drivers/platform/x86/intel/pmt/telemetry.h
new file mode 100644
index 000000000000..d45af5512b4e
--- /dev/null
+++ b/drivers/platform/x86/intel/pmt/telemetry.h
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TELEMETRY_H
+#define _TELEMETRY_H
+
+/* Telemetry types */
+#define PMT_TELEM_TELEMETRY	0
+#define PMT_TELEM_CRASHLOG	1
+
+struct telem_endpoint;
+struct pci_dev;
+
+struct telem_header {
+	u8	access_type;
+	u16	size;
+	u32	guid;
+	u32	base_offset;
+};
+
+struct telem_endpoint_info {
+	struct pci_dev		*pdev;
+	struct telem_header	header;
+};
+
+/**
+ * pmt_telem_get_next_endpoint() - Get next device id for a telemetry endpoint
+ * @start:  starting devid to look from
+ *
+ * This functions can be used in a while loop predicate to retrieve the devid
+ * of all available telemetry endpoints. Functions pmt_telem_get_next_endpoint()
+ * and pmt_telem_register_endpoint() can be used inside of the loop to examine
+ * endpoint info and register to receive a pointer to the endpoint. The pointer
+ * is then usable in the telemetry read calls to access the telemetry data.
+ *
+ * Return:
+ * * devid       - devid of the next present endpoint from start
+ * * 0           - when no more endpoints are present after start
+ */
+unsigned long pmt_telem_get_next_endpoint(unsigned long start);
+
+/**
+ * pmt_telem_register_endpoint() - Register a telemetry endpoint
+ * @devid: device id/handle of the telemetry endpoint
+ *
+ * Increments the kref usage counter for the endpoint.
+ *
+ * Return:
+ * * endpoint    - On success returns pointer to the telemetry endpoint
+ * * -ENXIO      - telemetry endpoint not found
+ */
+struct telem_endpoint *pmt_telem_register_endpoint(int devid);
+
+/**
+ * pmt_telem_unregister_endpoint() - Unregister a telemetry endpoint
+ * @ep:   ep structure to populate.
+ *
+ * Decrements the kref usage counter for the endpoint.
+ */
+void pmt_telem_unregister_endpoint(struct telem_endpoint *ep);
+
+/**
+ * pmt_telem_get_endpoint_info() - Get info for an endpoint from its devid
+ * @devid:  device id/handle of the telemetry endpoint
+ * @info:   Endpoint info structure to be populated
+ *
+ * Return:
+ * * 0           - Success
+ * * -ENXIO      - telemetry endpoint not found for the devid
+ * * -EINVAL     - @info is NULL
+ */
+int pmt_telem_get_endpoint_info(int devid, struct telem_endpoint_info *info);
+
+/**
+ * pmt_telem_find_and_register_endpoint() - Get a telemetry endpoint from
+ * pci_dev device, guid and pos
+ * @pdev:   PCI device inside the Intel vsec
+ * @guid:   GUID of the telemetry space
+ * @pos:    Instance of the guid
+ *
+ * Return:
+ * * endpoint    - On success returns pointer to the telemetry endpoint
+ * * -ENXIO      - telemetry endpoint not found
+ */
+struct telem_endpoint *pmt_telem_find_and_register_endpoint(struct pci_dev *pcidev,
+				u32 guid, u16 pos);
+
+/**
+ * pmt_telem_read() - Read qwords from counter sram using sample id
+ * @ep:     Telemetry endpoint to be read
+ * @id:     The beginning sample id of the metric(s) to be read
+ * @data:   Allocated qword buffer
+ * @count:  Number of qwords requested
+ *
+ * Callers must ensure reads are aligned. When the call returns -ENODEV,
+ * the device has been removed and callers should unregister the telemetry
+ * endpoint.
+ *
+ * Return:
+ * * 0           - Success
+ * * -ENODEV     - The device is not present.
+ * * -EINVAL     - The offset is out bounds
+ * * -EPIPE      - The device was removed during the read. Data written
+ *                 but should be considered invalid.
+ */
+int pmt_telem_read(struct telem_endpoint *ep, u32 id, u64 *data, u32 count);
+
+/**
+ * pmt_telem_read32() - Read qwords from counter sram using sample id
+ * @ep:     Telemetry endpoint to be read
+ * @id:     The beginning sample id of the metric(s) to be read
+ * @data:   Allocated dword buffer
+ * @count:  Number of dwords requested
+ *
+ * Callers must ensure reads are aligned. When the call returns -ENODEV,
+ * the device has been removed and callers should unregister the telemetry
+ * endpoint.
+ *
+ * Return:
+ * * 0           - Success
+ * * -ENODEV     - The device is not present.
+ * * -EINVAL     - The offset is out bounds
+ * * -EPIPE      - The device was removed during the read. Data written
+ *                 but should be considered invalid.
+ */
+int pmt_telem_read32(struct telem_endpoint *ep, u32 id, u32 *data, u32 count);
+
+#endif
-- 
2.34.1

[PATCH V3 08/16] platform/x86:intel/pmc: Call pmc_get_low_power_modes from platform init

[David E. Box]

From: Xi Pardee <xi.pardee@intel.com>

In order to setup a table of low power mode requirements for Meteor Lake,
pmc_core_get_low_power_modes() will need to be run from platform init code
so that the enabled modes are known, allowing the use of the
pmc_for_each_mode helper. Make the function global and call it from the
platform init code.

Signed-off-by: Xi Pardee <xi.pardee@intel.com>
Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
V3 - No change

V2 - Added clearer explanation for the change in the changelog

 drivers/platform/x86/intel/pmc/adl.c  |  2 ++
 drivers/platform/x86/intel/pmc/cnp.c  |  2 ++
 drivers/platform/x86/intel/pmc/core.c |  7 +++----
 drivers/platform/x86/intel/pmc/core.h |  1 +
 drivers/platform/x86/intel/pmc/icl.c  | 10 +++++++++-
 drivers/platform/x86/intel/pmc/mtl.c  |  4 +++-
 drivers/platform/x86/intel/pmc/spt.c  | 10 +++++++++-
 drivers/platform/x86/intel/pmc/tgl.c  |  1 +
 8 files changed, 30 insertions(+), 7 deletions(-)

diff --git a/drivers/platform/x86/intel/pmc/adl.c b/drivers/platform/x86/intel/pmc/adl.c
index 5006008e01be..64c492391ede 100644
--- a/drivers/platform/x86/intel/pmc/adl.c
+++ b/drivers/platform/x86/intel/pmc/adl.c
@@ -319,6 +319,8 @@ int adl_core_init(struct pmc_dev *pmcdev)
 	if (ret)
 		return ret;
 
+	pmc_core_get_low_power_modes(pmcdev);
+
 	/* Due to a hardware limitation, the GBE LTR blocks PC10
 	 * when a cable is attached. Tell the PMC to ignore it.
 	 */
diff --git a/drivers/platform/x86/intel/pmc/cnp.c b/drivers/platform/x86/intel/pmc/cnp.c
index 420aaa1d7c76..59298f184d0e 100644
--- a/drivers/platform/x86/intel/pmc/cnp.c
+++ b/drivers/platform/x86/intel/pmc/cnp.c
@@ -214,6 +214,8 @@ int cnp_core_init(struct pmc_dev *pmcdev)
 	if (ret)
 		return ret;
 
+	pmc_core_get_low_power_modes(pmcdev);
+
 	/* Due to a hardware limitation, the GBE LTR blocks PC10
 	 * when a cable is attached. Tell the PMC to ignore it.
 	 */
diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c
index 5a36b3f77bc5..e58c8cc286a3 100644
--- a/drivers/platform/x86/intel/pmc/core.c
+++ b/drivers/platform/x86/intel/pmc/core.c
@@ -966,9 +966,8 @@ static bool pmc_core_pri_verify(u32 lpm_pri, u8 *mode_order)
 	return true;
 }
 
-static void pmc_core_get_low_power_modes(struct platform_device *pdev)
+void pmc_core_get_low_power_modes(struct pmc_dev *pmcdev)
 {
-	struct pmc_dev *pmcdev = platform_get_drvdata(pdev);
 	struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN];
 	u8 pri_order[LPM_MAX_NUM_MODES] = LPM_DEFAULT_PRI;
 	u8 mode_order[LPM_MAX_NUM_MODES];
@@ -1000,7 +999,8 @@ static void pmc_core_get_low_power_modes(struct platform_device *pdev)
 		for (mode = 0; mode < LPM_MAX_NUM_MODES; mode++)
 			pri_order[mode_order[mode]] = mode;
 	else
-		dev_warn(&pdev->dev, "Assuming a default substate order for this platform\n");
+		dev_warn(&pmcdev->pdev->dev,
+			 "Assuming a default substate order for this platform\n");
 
 	/*
 	 * Loop through all modes from lowest to highest priority,
@@ -1250,7 +1250,6 @@ static int pmc_core_probe(struct platform_device *pdev)
 	}
 
 	pmcdev->pmc_xram_read_bit = pmc_core_check_read_lock_bit(primary_pmc);
-	pmc_core_get_low_power_modes(pdev);
 	pmc_core_do_dmi_quirks(primary_pmc);
 
 	pmc_core_dbgfs_register(pmcdev);
diff --git a/drivers/platform/x86/intel/pmc/core.h b/drivers/platform/x86/intel/pmc/core.h
index 0729f593c6a7..ccf24e0f5e50 100644
--- a/drivers/platform/x86/intel/pmc/core.h
+++ b/drivers/platform/x86/intel/pmc/core.h
@@ -490,6 +490,7 @@ extern int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value);
 
 int pmc_core_resume_common(struct pmc_dev *pmcdev);
 int get_primary_reg_base(struct pmc *pmc);
+extern void pmc_core_get_low_power_modes(struct pmc_dev *pmcdev);
 
 extern void pmc_core_ssram_init(struct pmc_dev *pmcdev);
 
diff --git a/drivers/platform/x86/intel/pmc/icl.c b/drivers/platform/x86/intel/pmc/icl.c
index d08e3174230d..71b0fd6cb7d8 100644
--- a/drivers/platform/x86/intel/pmc/icl.c
+++ b/drivers/platform/x86/intel/pmc/icl.c
@@ -53,7 +53,15 @@ const struct pmc_reg_map icl_reg_map = {
 int icl_core_init(struct pmc_dev *pmcdev)
 {
 	struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN];
+	int ret;
 
 	pmc->map = &icl_reg_map;
-	return get_primary_reg_base(pmc);
+
+	ret = get_primary_reg_base(pmc);
+	if (ret)
+		return ret;
+
+	pmc_core_get_low_power_modes(pmcdev);
+
+	return ret;
 }
diff --git a/drivers/platform/x86/intel/pmc/mtl.c b/drivers/platform/x86/intel/pmc/mtl.c
index 2204bc666980..c3b5f4fe01d1 100644
--- a/drivers/platform/x86/intel/pmc/mtl.c
+++ b/drivers/platform/x86/intel/pmc/mtl.c
@@ -985,7 +985,7 @@ static int mtl_resume(struct pmc_dev *pmcdev)
 int mtl_core_init(struct pmc_dev *pmcdev)
 {
 	struct pmc *pmc = pmcdev->pmcs[PMC_IDX_SOC];
-	int ret = 0;
+	int ret;
 
 	mtl_d3_fixup();
 
@@ -1002,6 +1002,8 @@ int mtl_core_init(struct pmc_dev *pmcdev)
 			return ret;
 	}
 
+	pmc_core_get_low_power_modes(pmcdev);
+
 	/* Due to a hardware limitation, the GBE LTR blocks PC10
 	 * when a cable is attached. Tell the PMC to ignore it.
 	 */
diff --git a/drivers/platform/x86/intel/pmc/spt.c b/drivers/platform/x86/intel/pmc/spt.c
index 4b6f5cbda16c..ab993a69e33e 100644
--- a/drivers/platform/x86/intel/pmc/spt.c
+++ b/drivers/platform/x86/intel/pmc/spt.c
@@ -137,7 +137,15 @@ const struct pmc_reg_map spt_reg_map = {
 int spt_core_init(struct pmc_dev *pmcdev)
 {
 	struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN];
+	int ret;
 
 	pmc->map = &spt_reg_map;
-	return get_primary_reg_base(pmc);
+
+	ret = get_primary_reg_base(pmc);
+	if (ret)
+		return ret;
+
+	pmc_core_get_low_power_modes(pmcdev);
+
+	return ret;
 }
diff --git a/drivers/platform/x86/intel/pmc/tgl.c b/drivers/platform/x86/intel/pmc/tgl.c
index 2449940102db..d5f1d2223c5a 100644
--- a/drivers/platform/x86/intel/pmc/tgl.c
+++ b/drivers/platform/x86/intel/pmc/tgl.c
@@ -263,6 +263,7 @@ int tgl_core_init(struct pmc_dev *pmcdev)
 	if (ret)
 		return ret;
 
+	pmc_core_get_low_power_modes(pmcdev);
 	pmc_core_get_tgl_lpm_reqs(pmcdev->pdev);
 	/* Due to a hardware limitation, the GBE LTR blocks PC10
 	 * when a cable is attached. Tell the PMC to ignore it.
-- 
2.34.1

[PATCH V3 09/16] platform/x86/intel/pmc: Allow pmc_core_ssram_init to fail

[David E. Box]

Currently, if the PMC SSRAM initialization fails, no error is returned and
the only indication is that a PMC device has not been created.  Instead,
allow an error to be returned and handled directly by the caller.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
---
V3 - New patch split from V2 PATCH 9
   - Add dev_warn on pmc_core_ssram_init fail

 drivers/platform/x86/intel/pmc/core.h       |  2 +-
 drivers/platform/x86/intel/pmc/core.h       |  2 +-
 drivers/platform/x86/intel/pmc/core_ssram.c | 21 +++++++++++++--------
 drivers/platform/x86/intel/pmc/mtl.c        | 12 ++++++++----
 3 files changed, 22 insertions(+), 13 deletions(-)

diff --git a/drivers/platform/x86/intel/pmc/core.h b/drivers/platform/x86/intel/pmc/core.h
index ccf24e0f5e50..edaa70067e41 100644
--- a/drivers/platform/x86/intel/pmc/core.h
+++ b/drivers/platform/x86/intel/pmc/core.h
@@ -492,7 +492,7 @@ int pmc_core_resume_common(struct pmc_dev *pmcdev);
 int get_primary_reg_base(struct pmc *pmc);
 extern void pmc_core_get_low_power_modes(struct pmc_dev *pmcdev);
 
-extern void pmc_core_ssram_init(struct pmc_dev *pmcdev);
+extern int pmc_core_ssram_init(struct pmc_dev *pmcdev);
 
 int spt_core_init(struct pmc_dev *pmcdev);
 int cnp_core_init(struct pmc_dev *pmcdev);
diff --git a/drivers/platform/x86/intel/pmc/core_ssram.c b/drivers/platform/x86/intel/pmc/core_ssram.c
index 13fa16f0d52e..815950713e25 100644
--- a/drivers/platform/x86/intel/pmc/core_ssram.c
+++ b/drivers/platform/x86/intel/pmc/core_ssram.c
@@ -35,20 +35,20 @@ static inline u64 get_base(void __iomem *addr, u32 offset)
 	return lo_hi_readq(addr + offset) & GENMASK_ULL(63, 3);
 }
 
-static void
+static int
 pmc_core_pmc_add(struct pmc_dev *pmcdev, u64 pwrm_base,
 		 const struct pmc_reg_map *reg_map, int pmc_index)
 {
 	struct pmc *pmc = pmcdev->pmcs[pmc_index];
 
 	if (!pwrm_base)
-		return;
+		return -ENODEV;
 
 	/* Memory for primary PMC has been allocated in core.c */
 	if (!pmc) {
 		pmc = devm_kzalloc(&pmcdev->pdev->dev, sizeof(*pmc), GFP_KERNEL);
 		if (!pmc)
-			return;
+			return -ENOMEM;
 	}
 
 	pmc->map = reg_map;
@@ -57,10 +57,12 @@ pmc_core_pmc_add(struct pmc_dev *pmcdev, u64 pwrm_base,
 
 	if (!pmc->regbase) {
 		devm_kfree(&pmcdev->pdev->dev, pmc);
-		return;
+		return -ENOMEM;
 	}
 
 	pmcdev->pmcs[pmc_index] = pmc;
+
+	return 0;
 }
 
 static void
@@ -96,7 +98,7 @@ pmc_core_ssram_get_pmc(struct pmc_dev *pmcdev, void __iomem *ssram, u32 offset,
 		iounmap(ssram);
 }
 
-void pmc_core_ssram_init(struct pmc_dev *pmcdev)
+int pmc_core_ssram_init(struct pmc_dev *pmcdev)
 {
 	void __iomem *ssram;
 	struct pci_dev *pcidev;
@@ -105,7 +107,7 @@ void pmc_core_ssram_init(struct pmc_dev *pmcdev)
 
 	pcidev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(20, 2));
 	if (!pcidev)
-		goto out;
+		return -ENODEV;
 
 	ret = pcim_enable_device(pcidev);
 	if (ret)
@@ -123,11 +125,14 @@ void pmc_core_ssram_init(struct pmc_dev *pmcdev)
 	pmc_core_ssram_get_pmc(pmcdev, ssram, SSRAM_PCH_OFFSET, PMC_IDX_PCH);
 
 	iounmap(ssram);
-out:
-	return;
+
+	return 0;
 
 disable_dev:
+	pmcdev->ssram_pcidev = NULL;
 	pci_disable_device(pcidev);
 release_dev:
 	pci_dev_put(pcidev);
+
+	return ret;
 }
diff --git a/drivers/platform/x86/intel/pmc/mtl.c b/drivers/platform/x86/intel/pmc/mtl.c
index c3b5f4fe01d1..d1d3d33fb4b8 100644
--- a/drivers/platform/x86/intel/pmc/mtl.c
+++ b/drivers/platform/x86/intel/pmc/mtl.c
@@ -990,12 +990,16 @@ int mtl_core_init(struct pmc_dev *pmcdev)
 	mtl_d3_fixup();
 
 	pmcdev->resume = mtl_resume;
-
 	pmcdev->regmap_list = mtl_pmc_info_list;
-	pmc_core_ssram_init(pmcdev);
 
-	/* If regbase not assigned, set map and discover using legacy method */
-	if (!pmc->regbase) {
+	/*
+	 * If ssram init fails use legacy method to at least get the
+	 * primary PMC
+	 */
+	ret = pmc_core_ssram_init(pmcdev);
+	if (ret) {
+		dev_warn(&pmcdev->pdev->dev,
+			 "ssram init failed, %d, using legacy init\n", ret);
 		pmc->map = &mtl_socm_reg_map;
 		ret = get_primary_reg_base(pmc);
 		if (ret)
-- 
2.34.1

[PATCH V3 10/16] platform/x86/intel/pmc: Split pmc_core_ssram_get_pmc()

[David E. Box]

On supported hardware, each PMC may have an associated SSRAM device for
accessing additional counters.  However, only the SSRAM of the first
(primary) PMC is discoverable as a PCI device to the OS. The remaining
(secondary) devices are hidden but their BARs are still accessible and
their addresses are stored in the BAR of the exposed device. Clean up the
code handling the SSRAM discovery. Create two separate functions for
accessing the primary and secondary SSRAM devices.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
---
V3 - New patch split from previous PATCH 2
   - Update changelog
   - Use cleanup.h to cleanup ioremap

V2 - no change

 drivers/platform/x86/intel/pmc/core_ssram.c | 93 ++++++++++++++-------
 1 file changed, 61 insertions(+), 32 deletions(-)

diff --git a/drivers/platform/x86/intel/pmc/core_ssram.c b/drivers/platform/x86/intel/pmc/core_ssram.c
index 815950713e25..af405d11919f 100644
--- a/drivers/platform/x86/intel/pmc/core_ssram.c
+++ b/drivers/platform/x86/intel/pmc/core_ssram.c
@@ -8,6 +8,7 @@
  *
  */
 
+#include <linux/cleanup.h>
 #include <linux/pci.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 
@@ -21,6 +22,8 @@
 #define SSRAM_IOE_OFFSET	0x68
 #define SSRAM_DEVID_OFFSET	0x70
 
+DEFINE_FREE(pmc_core_iounmap, void __iomem *, iounmap(_T));
+
 static const struct pmc_reg_map *pmc_core_find_regmap(struct pmc_info *list, u16 devid)
 {
 	for (; list->map; ++list)
@@ -65,44 +68,74 @@ pmc_core_pmc_add(struct pmc_dev *pmcdev, u64 pwrm_base,
 	return 0;
 }
 
-static void
-pmc_core_ssram_get_pmc(struct pmc_dev *pmcdev, void __iomem *ssram, u32 offset,
-		       int pmc_idx)
+static int
+pmc_core_get_secondary_pmc(struct pmc_dev *pmcdev, int pmc_idx, u32 offset)
 {
-	u64 pwrm_base;
+	struct pci_dev *ssram_pcidev = pmcdev->ssram_pcidev;
+	void __iomem __free(pmc_core_iounmap) *main_ssram = NULL;
+	void __iomem __free(pmc_core_iounmap) *secondary_ssram = NULL;
+	const struct pmc_reg_map *map;
+	u64 ssram_base, pwrm_base;
 	u16 devid;
 
-	if (pmc_idx != PMC_IDX_SOC) {
-		u64 ssram_base = get_base(ssram, offset);
+	if (!pmcdev->regmap_list)
+		return -ENOENT;
 
-		if (!ssram_base)
-			return;
+	/*
+	 * The secondary PMC BARS (which are behind hidden PCI devices) are read
+	 * from fixed offsets in MMIO of the primary PMC BAR.
+	 */
+	ssram_base = ssram_pcidev->resource[0].start;
+	main_ssram = ioremap(ssram_base, SSRAM_HDR_SIZE);
+	if (!main_ssram)
+		return -ENOMEM;
 
-		ssram = ioremap(ssram_base, SSRAM_HDR_SIZE);
-		if (!ssram)
-			return;
-	}
+	ssram_base = get_base(main_ssram, offset);
+	secondary_ssram = ioremap(ssram_base, SSRAM_HDR_SIZE);
+	if (!secondary_ssram)
+		return -ENOMEM;
+
+	pwrm_base = get_base(secondary_ssram, SSRAM_PWRM_OFFSET);
+	devid = readw(secondary_ssram + SSRAM_DEVID_OFFSET);
+
+	map = pmc_core_find_regmap(pmcdev->regmap_list, devid);
+	if (!map)
+		return -ENODEV;
+
+	return pmc_core_pmc_add(pmcdev, pwrm_base, map, pmc_idx);
+}
+
+static int
+pmc_core_get_primary_pmc(struct pmc_dev *pmcdev)
+{
+	struct pci_dev *ssram_pcidev = pmcdev->ssram_pcidev;
+	void __iomem __free(pmc_core_iounmap) *ssram;
+	const struct pmc_reg_map *map;
+	u64 ssram_base, pwrm_base;
+	u16 devid;
+
+	if (!pmcdev->regmap_list)
+		return -ENOENT;
+
+	/* The primary PMC (SOC die) BAR is BAR 0 in config space. */
+	ssram_base = ssram_pcidev->resource[0].start;
+	ssram = ioremap(ssram_base, SSRAM_HDR_SIZE);
+	if (!ssram)
+		return -ENOMEM;
 
 	pwrm_base = get_base(ssram, SSRAM_PWRM_OFFSET);
 	devid = readw(ssram + SSRAM_DEVID_OFFSET);
 
-	if (pmcdev->regmap_list) {
-		const struct pmc_reg_map *map;
+	map = pmc_core_find_regmap(pmcdev->regmap_list, devid);
+	if (!map)
+		return -ENODEV;
 
-		map = pmc_core_find_regmap(pmcdev->regmap_list, devid);
-		if (map)
-			pmc_core_pmc_add(pmcdev, pwrm_base, map, pmc_idx);
-	}
-
-	if (pmc_idx != PMC_IDX_SOC)
-		iounmap(ssram);
+	return pmc_core_pmc_add(pmcdev, pwrm_base, map, PMC_IDX_MAIN);
 }
 
 int pmc_core_ssram_init(struct pmc_dev *pmcdev)
 {
-	void __iomem *ssram;
 	struct pci_dev *pcidev;
-	u64 ssram_base;
 	int ret;
 
 	pcidev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(20, 2));
@@ -113,18 +146,14 @@ int pmc_core_ssram_init(struct pmc_dev *pmcdev)
 	if (ret)
 		goto release_dev;
 
-	ssram_base = pcidev->resource[0].start;
-	ssram = ioremap(ssram_base, SSRAM_HDR_SIZE);
-	if (!ssram)
-		goto disable_dev;
-
 	pmcdev->ssram_pcidev = pcidev;
 
-	pmc_core_ssram_get_pmc(pmcdev, ssram, 0, PMC_IDX_SOC);
-	pmc_core_ssram_get_pmc(pmcdev, ssram, SSRAM_IOE_OFFSET, PMC_IDX_IOE);
-	pmc_core_ssram_get_pmc(pmcdev, ssram, SSRAM_PCH_OFFSET, PMC_IDX_PCH);
+	ret = pmc_core_get_primary_pmc(pmcdev);
+	if (ret)
+		goto disable_dev;
 
-	iounmap(ssram);
+	pmc_core_get_secondary_pmc(pmcdev, PMC_IDX_IOE, SSRAM_IOE_OFFSET);
+	pmc_core_get_secondary_pmc(pmcdev, PMC_IDX_PCH, SSRAM_PCH_OFFSET);
 
 	return 0;
 
-- 
2.34.1

[PATCH V3 11/16] platform/x86/intel/pmc: Find and register PMC telemetry entries

[David E. Box]

The PMC SSRAM device contains counters that are structured in Intel
Platform Monitoring Technology (PMT) telemetry regions. Look for and
register these telemetry regions from the driver so that they may be read
using the Intel PMT ABI.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
---
V3 - no change

V2 - no change

 drivers/platform/x86/intel/pmc/Kconfig      |  1 +
 drivers/platform/x86/intel/pmc/core_ssram.c | 52 +++++++++++++++++++++
 2 files changed, 53 insertions(+)

diff --git a/drivers/platform/x86/intel/pmc/Kconfig b/drivers/platform/x86/intel/pmc/Kconfig
index b526597e4deb..d2f651fbec2c 100644
--- a/drivers/platform/x86/intel/pmc/Kconfig
+++ b/drivers/platform/x86/intel/pmc/Kconfig
@@ -7,6 +7,7 @@ config INTEL_PMC_CORE
 	tristate "Intel PMC Core driver"
 	depends on PCI
 	depends on ACPI
+	depends on INTEL_PMT_TELEMETRY
 	help
 	  The Intel Platform Controller Hub for Intel Core SoCs provides access
 	  to Power Management Controller registers via various interfaces. This
diff --git a/drivers/platform/x86/intel/pmc/core_ssram.c b/drivers/platform/x86/intel/pmc/core_ssram.c
index af405d11919f..1ecfa3804117 100644
--- a/drivers/platform/x86/intel/pmc/core_ssram.c
+++ b/drivers/platform/x86/intel/pmc/core_ssram.c
@@ -13,6 +13,8 @@
 #include <linux/io-64-nonatomic-lo-hi.h>
 
 #include "core.h"
+#include "../vsec.h"
+#include "../pmt/telemetry.h"
 
 #define SSRAM_HDR_SIZE		0x100
 #define SSRAM_PWRM_OFFSET	0x14
@@ -24,6 +26,49 @@
 
 DEFINE_FREE(pmc_core_iounmap, void __iomem *, iounmap(_T));
 
+static void
+pmc_add_pmt(struct pmc_dev *pmcdev, u64 ssram_base, void __iomem *ssram)
+{
+	struct pci_dev *pcidev = pmcdev->ssram_pcidev;
+	struct intel_vsec_platform_info info = {};
+	struct intel_vsec_header *headers[2] = {};
+	struct intel_vsec_header header;
+	void __iomem *dvsec;
+	u32 dvsec_offset;
+	u32 table, hdr;
+
+	ssram = ioremap(ssram_base, SSRAM_HDR_SIZE);
+	if (!ssram)
+		return;
+
+	dvsec_offset = readl(ssram + SSRAM_DVSEC_OFFSET);
+	iounmap(ssram);
+
+	dvsec = ioremap(ssram_base + dvsec_offset, SSRAM_DVSEC_SIZE);
+	if (!dvsec)
+		return;
+
+	hdr = readl(dvsec + PCI_DVSEC_HEADER1);
+	header.id = readw(dvsec + PCI_DVSEC_HEADER2);
+	header.rev = PCI_DVSEC_HEADER1_REV(hdr);
+	header.length = PCI_DVSEC_HEADER1_LEN(hdr);
+	header.num_entries = readb(dvsec + INTEL_DVSEC_ENTRIES);
+	header.entry_size = readb(dvsec + INTEL_DVSEC_SIZE);
+
+	table = readl(dvsec + INTEL_DVSEC_TABLE);
+	header.tbir = INTEL_DVSEC_TABLE_BAR(table);
+	header.offset = INTEL_DVSEC_TABLE_OFFSET(table);
+	iounmap(dvsec);
+
+	headers[0] = &header;
+	info.caps = VSEC_CAP_TELEMETRY;
+	info.headers = headers;
+	info.base_addr = ssram_base;
+	info.parent = &pmcdev->pdev->dev;
+
+	intel_vsec_register(pcidev, &info);
+}
+
 static const struct pmc_reg_map *pmc_core_find_regmap(struct pmc_info *list, u16 devid)
 {
 	for (; list->map; ++list)
@@ -98,6 +143,9 @@ pmc_core_get_secondary_pmc(struct pmc_dev *pmcdev, int pmc_idx, u32 offset)
 	pwrm_base = get_base(secondary_ssram, SSRAM_PWRM_OFFSET);
 	devid = readw(secondary_ssram + SSRAM_DEVID_OFFSET);
 
+	/* Find and register and PMC telemetry entries */
+	pmc_add_pmt(pmcdev, ssram_base, main_ssram);
+
 	map = pmc_core_find_regmap(pmcdev->regmap_list, devid);
 	if (!map)
 		return -ENODEV;
@@ -126,6 +174,9 @@ pmc_core_get_primary_pmc(struct pmc_dev *pmcdev)
 	pwrm_base = get_base(ssram, SSRAM_PWRM_OFFSET);
 	devid = readw(ssram + SSRAM_DEVID_OFFSET);
 
+	/* Find and register and PMC telemetry entries */
+	pmc_add_pmt(pmcdev, ssram_base, ssram);
+
 	map = pmc_core_find_regmap(pmcdev->regmap_list, devid);
 	if (!map)
 		return -ENODEV;
@@ -165,3 +216,4 @@ int pmc_core_ssram_init(struct pmc_dev *pmcdev)
 
 	return ret;
 }
+MODULE_IMPORT_NS(INTEL_VSEC);
-- 
2.34.1

[PATCH V3 12/16] platform/x86/intel/pmc: Display LPM requirements for multiple PMCs

[David E. Box]

From: Rajvi Jingar <rajvi.jingar@linux.intel.com>

Update the substate_requirements attribute to display the requirements for
all the PMCs on a package.

Signed-off-by: Rajvi Jingar <rajvi.jingar@linux.intel.com>
Signed-off-by: David E. Box <david.e.box@linux.intel.com>
---
V3 - Add missing submitter signoff

V2 - no change

 drivers/platform/x86/intel/pmc/core.c | 129 ++++++++++++++------------
 1 file changed, 71 insertions(+), 58 deletions(-)

diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c
index e58c8cc286a3..df2bcead1723 100644
--- a/drivers/platform/x86/intel/pmc/core.c
+++ b/drivers/platform/x86/intel/pmc/core.c
@@ -728,7 +728,7 @@ static int pmc_core_substate_l_sts_regs_show(struct seq_file *s, void *unused)
 }
 DEFINE_SHOW_ATTRIBUTE(pmc_core_substate_l_sts_regs);
 
-static void pmc_core_substate_req_header_show(struct seq_file *s)
+static void pmc_core_substate_req_header_show(struct seq_file *s, int pmc_index)
 {
 	struct pmc_dev *pmcdev = s->private;
 	int i, mode;
@@ -743,68 +743,81 @@ static void pmc_core_substate_req_header_show(struct seq_file *s)
 static int pmc_core_substate_req_regs_show(struct seq_file *s, void *unused)
 {
 	struct pmc_dev *pmcdev = s->private;
-	struct pmc *pmc = pmcdev->pmcs[PMC_IDX_MAIN];
-	const struct pmc_bit_map **maps = pmc->map->lpm_sts;
-	const struct pmc_bit_map *map;
-	const int num_maps = pmc->map->lpm_num_maps;
-	u32 sts_offset = pmc->map->lpm_status_offset;
-	u32 *lpm_req_regs = pmc->lpm_req_regs;
-	int mp;
-
-	/* Display the header */
-	pmc_core_substate_req_header_show(s);
-
-	/* Loop over maps */
-	for (mp = 0; mp < num_maps; mp++) {
-		u32 req_mask = 0;
-		u32 lpm_status;
-		int mode, idx, i, len = 32;
-
-		/*
-		 * Capture the requirements and create a mask so that we only
-		 * show an element if it's required for at least one of the
-		 * enabled low power modes
-		 */
-		pmc_for_each_mode(idx, mode, pmcdev)
-			req_mask |= lpm_req_regs[mp + (mode * num_maps)];
-
-		/* Get the last latched status for this map */
-		lpm_status = pmc_core_reg_read(pmc, sts_offset + (mp * 4));
-
-		/*  Loop over elements in this map */
-		map = maps[mp];
-		for (i = 0; map[i].name && i < len; i++) {
-			u32 bit_mask = map[i].bit_mask;
-
-			if (!(bit_mask & req_mask))
-				/*
-				 * Not required for any enabled states
-				 * so don't display
-				 */
-				continue;
-
-			/* Display the element name in the first column */
-			seq_printf(s, "%30s |", map[i].name);
-
-			/* Loop over the enabled states and display if required */
-			pmc_for_each_mode(idx, mode, pmcdev) {
-				if (lpm_req_regs[mp + (mode * num_maps)] & bit_mask)
-					seq_printf(s, " %9s |",
-						   "Required");
+	u32 sts_offset;
+	u32 *lpm_req_regs;
+	int num_maps, mp, pmc_index;
+
+	for (pmc_index = 0; pmc_index < ARRAY_SIZE(pmcdev->pmcs); ++pmc_index) {
+		struct pmc *pmc = pmcdev->pmcs[pmc_index];
+		const struct pmc_bit_map **maps;
+
+		if (!pmc)
+			continue;
+
+		maps = pmc->map->lpm_sts;
+		num_maps = pmc->map->lpm_num_maps;
+		sts_offset = pmc->map->lpm_status_offset;
+		lpm_req_regs = pmc->lpm_req_regs;
+
+		if (!lpm_req_regs)
+			continue;
+
+		/* Display the header */
+		pmc_core_substate_req_header_show(s, pmc_index);
+
+		/* Loop over maps */
+		for (mp = 0; mp < num_maps; mp++) {
+			u32 req_mask = 0;
+			u32 lpm_status;
+			const struct pmc_bit_map *map;
+			int mode, idx, i, len = 32;
+
+			/*
+			 * Capture the requirements and create a mask so that we only
+			 * show an element if it's required for at least one of the
+			 * enabled low power modes
+			 */
+			pmc_for_each_mode(idx, mode, pmcdev)
+				req_mask |= lpm_req_regs[mp + (mode * num_maps)];
+
+			/* Get the last latched status for this map */
+			lpm_status = pmc_core_reg_read(pmc, sts_offset + (mp * 4));
+
+			/*  Loop over elements in this map */
+			map = maps[mp];
+			for (i = 0; map[i].name && i < len; i++) {
+				u32 bit_mask = map[i].bit_mask;
+
+				if (!(bit_mask & req_mask)) {
+					/*
+					 * Not required for any enabled states
+					 * so don't display
+					 */
+					continue;
+				}
+
+				/* Display the element name in the first column */
+				seq_printf(s, "pmc%d: %26s |", pmc_index, map[i].name);
+
+				/* Loop over the enabled states and display if required */
+				pmc_for_each_mode(idx, mode, pmcdev) {
+					if (lpm_req_regs[mp + (mode * num_maps)] & bit_mask)
+						seq_printf(s, " %9s |",
+							   "Required");
+					else
+						seq_printf(s, " %9s |", " ");
+				}
+
+				/* In Status column, show the last captured state of this agent */
+				if (lpm_status & bit_mask)
+					seq_printf(s, " %9s |", "Yes");
 				else
 					seq_printf(s, " %9s |", " ");
+
+				seq_puts(s, "\n");
 			}
-
-			/* In Status column, show the last captured state of this agent */
-			if (lpm_status & bit_mask)
-				seq_printf(s, " %9s |", "Yes");
-			else
-				seq_printf(s, " %9s |", " ");
-
-			seq_puts(s, "\n");
 		}
 	}
-
 	return 0;
 }
 DEFINE_SHOW_ATTRIBUTE(pmc_core_substate_req_regs);
-- 
2.34.1

[PATCH V3 13/16] platform/x86/intel/pmc: Retrieve LPM information using Intel PMT

[David E. Box]

From: Xi Pardee <xi.pardee@intel.com>

On supported platforms, the low power mode (LPM) requirements for entering
each idle substate are described in Platform Monitoring Technology (PMT)
telemetry entries. Provide a function for platform code to attempt to find
and read the requirements from the telemetry entries.

Signed-off-by: Xi Pardee <xi.pardee@intel.com>
Signed-off-by: David E. Box <david.e.box@linux.intel.com>
---
V3 - no change

V2 - remove extra parens

 drivers/platform/x86/intel/pmc/core.h       |   3 +
 drivers/platform/x86/intel/pmc/core_ssram.c | 135 ++++++++++++++++++++
 2 files changed, 138 insertions(+)

diff --git a/drivers/platform/x86/intel/pmc/core.h b/drivers/platform/x86/intel/pmc/core.h
index edaa70067e41..85b6f6ae4995 100644
--- a/drivers/platform/x86/intel/pmc/core.h
+++ b/drivers/platform/x86/intel/pmc/core.h
@@ -320,6 +320,7 @@ struct pmc_reg_map {
 	const u32 lpm_status_offset;
 	const u32 lpm_live_status_offset;
 	const u32 etr3_offset;
+	const u8  *lpm_reg_index;
 };
 
 /**
@@ -329,6 +330,7 @@ struct pmc_reg_map {
  *			specific attributes
  */
 struct pmc_info {
+	u32 guid;
 	u16 devid;
 	const struct pmc_reg_map *map;
 };
@@ -486,6 +488,7 @@ extern const struct pmc_bit_map *mtl_ioem_lpm_maps[];
 extern const struct pmc_reg_map mtl_ioem_reg_map;
 
 extern void pmc_core_get_tgl_lpm_reqs(struct platform_device *pdev);
+extern int pmc_core_ssram_get_lpm_reqs(struct pmc_dev *pmcdev);
 extern int pmc_core_send_ltr_ignore(struct pmc_dev *pmcdev, u32 value);
 
 int pmc_core_resume_common(struct pmc_dev *pmcdev);
diff --git a/drivers/platform/x86/intel/pmc/core_ssram.c b/drivers/platform/x86/intel/pmc/core_ssram.c
index 1ecfa3804117..8cd5bc4e77f6 100644
--- a/drivers/platform/x86/intel/pmc/core_ssram.c
+++ b/drivers/platform/x86/intel/pmc/core_ssram.c
@@ -26,6 +26,140 @@
 
 DEFINE_FREE(pmc_core_iounmap, void __iomem *, iounmap(_T));
 
+/* PCH query */
+#define LPM_HEADER_OFFSET	1
+#define LPM_REG_COUNT		28
+#define LPM_MODE_OFFSET		1
+
+static u32 pmc_core_find_guid(struct pmc_info *list, const struct pmc_reg_map *map)
+{
+	for (; list->map; ++list)
+		if (list->map == map)
+			return list->guid;
+
+	return 0;
+}
+
+static int pmc_core_get_lpm_req(struct pmc_dev *pmcdev, struct pmc *pmc)
+{
+	struct telem_endpoint *ep;
+	const u8 *lpm_indices;
+	int num_maps, mode_offset = 0;
+	int ret, mode, i;
+	int lpm_size;
+	u32 guid;
+
+	lpm_indices = pmc->map->lpm_reg_index;
+	num_maps = pmc->map->lpm_num_maps;
+	lpm_size = LPM_MAX_NUM_MODES * num_maps;
+
+	guid = pmc_core_find_guid(pmcdev->regmap_list, pmc->map);
+	if (!guid)
+		return -ENXIO;
+
+	ep = pmt_telem_find_and_register_endpoint(pmcdev->ssram_pcidev, guid, 0);
+	if (IS_ERR(ep)) {
+		dev_dbg(&pmcdev->pdev->dev, "couldn't get telem endpoint %ld",
+			PTR_ERR(ep));
+		return -EPROBE_DEFER;
+	}
+
+	pmc->lpm_req_regs = devm_kzalloc(&pmcdev->pdev->dev,
+					 lpm_size * sizeof(u32),
+					 GFP_KERNEL);
+	if (!pmc->lpm_req_regs) {
+		ret = -ENOMEM;
+		goto unregister_ep;
+	}
+
+	/*
+	 * PMC Low Power Mode (LPM) table
+	 *
+	 * In telemetry space, the LPM table contains a 4 byte header followed
+	 * by 8 consecutive mode blocks (one for each LPM mode). Each block
+	 * has a 4 byte header followed by a set of registers that describe the
+	 * IP state requirements for the given mode. The IP mapping is platform
+	 * specific but the same for each block, making for easy analysis.
+	 * Platforms only use a subset of the space to track the requirements
+	 * for their IPs. Callers provide the requirement registers they use as
+	 * a list of indices. Each requirement register is associated with an
+	 * IP map that's maintained by the caller.
+	 *
+	 * Header
+	 * +----+----------------------------+----------------------------+
+	 * |  0 |      REVISION              |      ENABLED MODES         |
+	 * +----+--------------+-------------+-------------+--------------+
+	 *
+	 * Low Power Mode 0 Block
+	 * +----+--------------+-------------+-------------+--------------+
+	 * |  1 |     SUB ID   |     SIZE    |   MAJOR     |   MINOR      |
+	 * +----+--------------+-------------+-------------+--------------+
+	 * |  2 |           LPM0 Requirements 0                           |
+	 * +----+---------------------------------------------------------+
+	 * |    |                  ...                                    |
+	 * +----+---------------------------------------------------------+
+	 * | 29 |           LPM0 Requirements 27                          |
+	 * +----+---------------------------------------------------------+
+	 *
+	 * ...
+	 *
+	 * Low Power Mode 7 Block
+	 * +----+--------------+-------------+-------------+--------------+
+	 * |    |     SUB ID   |     SIZE    |   MAJOR     |   MINOR      |
+	 * +----+--------------+-------------+-------------+--------------+
+	 * | 60 |           LPM7 Requirements 0                           |
+	 * +----+---------------------------------------------------------+
+	 * |    |                  ...                                    |
+	 * +----+---------------------------------------------------------+
+	 * | 87 |           LPM7 Requirements 27                          |
+	 * +----+---------------------------------------------------------+
+	 *
+	 */
+	mode_offset = LPM_HEADER_OFFSET + LPM_MODE_OFFSET;
+	pmc_for_each_mode(i, mode, pmcdev) {
+		u32 *req_offset = pmc->lpm_req_regs + (mode * num_maps);
+		int m;
+
+		for (m = 0; m < num_maps; m++) {
+			u8 sample_id = lpm_indices[m] + mode_offset;
+
+			ret = pmt_telem_read32(ep, sample_id, req_offset, 1);
+			if (ret) {
+				dev_err(&pmcdev->pdev->dev,
+					"couldn't read Low Power Mode requirements: %d\n", ret);
+				devm_kfree(&pmcdev->pdev->dev, pmc->lpm_req_regs);
+				goto unregister_ep;
+			}
+			++req_offset;
+		}
+		mode_offset += LPM_REG_COUNT + LPM_MODE_OFFSET;
+	}
+
+unregister_ep:
+	pmt_telem_unregister_endpoint(ep);
+
+	return ret;
+}
+
+int pmc_core_ssram_get_lpm_reqs(struct pmc_dev *pmcdev)
+{
+	int ret, i;
+
+	if (!pmcdev->ssram_pcidev)
+		return -ENODEV;
+
+	for (i = 0; i < ARRAY_SIZE(pmcdev->pmcs); ++i) {
+		if (!pmcdev->pmcs[i])
+			continue;
+
+		ret = pmc_core_get_lpm_req(pmcdev, pmcdev->pmcs[i]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static void
 pmc_add_pmt(struct pmc_dev *pmcdev, u64 ssram_base, void __iomem *ssram)
 {
@@ -217,3 +351,4 @@ int pmc_core_ssram_init(struct pmc_dev *pmcdev)
 	return ret;
 }
 MODULE_IMPORT_NS(INTEL_VSEC);
+MODULE_IMPORT_NS(INTEL_PMT_TELEMETRY);
-- 
2.34.1

[PATCH V3 14/16] platform/x86/intel/pmc: Read low power mode requirements for MTL-M and MTL-P

[David E. Box]

From: Xi Pardee <xi.pardee@intel.com>

Add support to read the low power mode requirements for Meteor Lake M and
Meteor Lake P.

Signed-off-by: Xi Pardee <xi.pardee@intel.com>
Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
V3 - directly return value from pmc_core_ssram_get_lpm_reqs()

V2 - fixed unused return value

 drivers/platform/x86/intel/pmc/mtl.c | 39 +++++++++++++++++++++++-----
 1 file changed, 32 insertions(+), 7 deletions(-)

diff --git a/drivers/platform/x86/intel/pmc/mtl.c b/drivers/platform/x86/intel/pmc/mtl.c
index d1d3d33fb4b8..7ceeae507f4c 100644
--- a/drivers/platform/x86/intel/pmc/mtl.c
+++ b/drivers/platform/x86/intel/pmc/mtl.c
@@ -11,6 +11,13 @@
 #include <linux/pci.h>
 #include "core.h"
 
+/* PMC SSRAM PMT Telemetry GUIDS */
+#define SOCP_LPM_REQ_GUID	0x2625030
+#define IOEM_LPM_REQ_GUID	0x4357464
+#define IOEP_LPM_REQ_GUID	0x5077612
+
+static const u8 MTL_LPM_REG_INDEX[] = {0, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 15, 16, 20};
+
 /*
  * Die Mapping to Product.
  * Product SOCDie IOEDie PCHDie
@@ -465,6 +472,7 @@ const struct pmc_reg_map mtl_socm_reg_map = {
 	.lpm_sts = mtl_socm_lpm_maps,
 	.lpm_status_offset = MTL_LPM_STATUS_OFFSET,
 	.lpm_live_status_offset = MTL_LPM_LIVE_STATUS_OFFSET,
+	.lpm_reg_index = MTL_LPM_REG_INDEX,
 };
 
 const struct pmc_bit_map mtl_ioep_pfear_map[] = {
@@ -782,6 +790,13 @@ const struct pmc_reg_map mtl_ioep_reg_map = {
 	.ltr_show_sts = mtl_ioep_ltr_show_map,
 	.ltr_ignore_offset = CNP_PMC_LTR_IGNORE_OFFSET,
 	.ltr_ignore_max = ADL_NUM_IP_IGN_ALLOWED,
+	.lpm_num_maps = ADL_LPM_NUM_MAPS,
+	.lpm_res_counter_step_x2 = TGL_PMC_LPM_RES_COUNTER_STEP_X2,
+	.lpm_residency_offset = MTL_LPM_RESIDENCY_OFFSET,
+	.lpm_priority_offset = MTL_LPM_PRI_OFFSET,
+	.lpm_en_offset = MTL_LPM_EN_OFFSET,
+	.lpm_sts_latch_en_offset = MTL_LPM_STATUS_LATCH_EN_OFFSET,
+	.lpm_reg_index = MTL_LPM_REG_INDEX,
 };
 
 const struct pmc_bit_map mtl_ioem_pfear_map[] = {
@@ -922,6 +937,13 @@ const struct pmc_reg_map mtl_ioem_reg_map = {
 	.ltr_show_sts = mtl_ioep_ltr_show_map,
 	.ltr_ignore_offset = CNP_PMC_LTR_IGNORE_OFFSET,
 	.ltr_ignore_max = ADL_NUM_IP_IGN_ALLOWED,
+	.lpm_sts_latch_en_offset = MTL_LPM_STATUS_LATCH_EN_OFFSET,
+	.lpm_num_maps = ADL_LPM_NUM_MAPS,
+	.lpm_priority_offset = MTL_LPM_PRI_OFFSET,
+	.lpm_en_offset = MTL_LPM_EN_OFFSET,
+	.lpm_res_counter_step_x2 = TGL_PMC_LPM_RES_COUNTER_STEP_X2,
+	.lpm_residency_offset = MTL_LPM_RESIDENCY_OFFSET,
+	.lpm_reg_index = MTL_LPM_REG_INDEX,
 };
 
 #define PMC_DEVID_SOCM	0x7e7f
@@ -929,16 +951,19 @@ const struct pmc_reg_map mtl_ioem_reg_map = {
 #define PMC_DEVID_IOEM	0x7ebf
 static struct pmc_info mtl_pmc_info_list[] = {
 	{
-		.devid = PMC_DEVID_SOCM,
-		.map = &mtl_socm_reg_map,
+		.guid	= SOCP_LPM_REQ_GUID,
+		.devid	= PMC_DEVID_SOCM,
+		.map	= &mtl_socm_reg_map,
 	},
 	{
-		.devid = PMC_DEVID_IOEP,
-		.map = &mtl_ioep_reg_map,
+		.guid	= IOEP_LPM_REQ_GUID,
+		.devid	= PMC_DEVID_IOEP,
+		.map	= &mtl_ioep_reg_map,
 	},
 	{
-		.devid = PMC_DEVID_IOEM,
-		.map = &mtl_ioem_reg_map
+		.guid	= IOEM_LPM_REQ_GUID,
+		.devid	= PMC_DEVID_IOEM,
+		.map	= &mtl_ioem_reg_map
 	},
 	{}
 };
@@ -1014,5 +1039,5 @@ int mtl_core_init(struct pmc_dev *pmcdev)
 	dev_dbg(&pmcdev->pdev->dev, "ignoring GBE LTR\n");
 	pmc_core_send_ltr_ignore(pmcdev, 3);
 
-	return 0;
+	return pmc_core_ssram_get_lpm_reqs(pmcdev);
 }
-- 
2.34.1

[PATCH V3 15/16] platform/x86/intel/pmc: Add debug attribute for Die C6 counter

[David E. Box]

Add a "die_c6_us_show" debugfs attribute.  Reads the counter value using
Intel Platform Monitoring Technology (PMT) driver API. This counter is
useful for determining the idle residency of CPUs in the compute tile.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
---
V3 - Split previous PATCH V2 13. Separates implementation (this patch) from
     platform specific use (next patch)

V2 - Remove use of __func__
   - Use HZ_PER_MHZ
   - Fix missing newlines in printks

 drivers/platform/x86/intel/pmc/core.c | 55 +++++++++++++++++++++++++++
 drivers/platform/x86/intel/pmc/core.h |  4 ++
 2 files changed, 59 insertions(+)

diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c
index df2bcead1723..b90ee8c896f4 100644
--- a/drivers/platform/x86/intel/pmc/core.c
+++ b/drivers/platform/x86/intel/pmc/core.c
@@ -20,6 +20,7 @@
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/suspend.h>
+#include <linux/units.h>
 
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
@@ -27,6 +28,7 @@
 #include <asm/tsc.h>
 
 #include "core.h"
+#include "../pmt/telemetry.h"
 
 /* Maximum number of modes supported by platfoms that has low power mode capability */
 const char *pmc_lpm_modes[] = {
@@ -822,6 +824,47 @@ static int pmc_core_substate_req_regs_show(struct seq_file *s, void *unused)
 }
 DEFINE_SHOW_ATTRIBUTE(pmc_core_substate_req_regs);
 
+static unsigned int pmc_core_get_crystal_freq(void)
+{
+	unsigned int eax_denominator, ebx_numerator, ecx_hz, edx;
+
+	if (boot_cpu_data.cpuid_level < 0x15)
+		return 0;
+
+	eax_denominator = ebx_numerator = ecx_hz = edx = 0;
+
+	/* CPUID 15H TSC/Crystal ratio, plus optionally Crystal Hz */
+	cpuid(0x15, &eax_denominator, &ebx_numerator, &ecx_hz, &edx);
+
+	if (ebx_numerator == 0 || eax_denominator == 0)
+		return 0;
+
+	return ecx_hz;
+}
+
+static int pmc_core_die_c6_us_show(struct seq_file *s, void *unused)
+{
+	struct pmc_dev *pmcdev = s->private;
+	u64 die_c6_res, count;
+	int ret;
+
+	if (!pmcdev->crystal_freq) {
+		dev_warn_once(&pmcdev->pdev->dev, "Bad crystal frequency\n");
+		return -EINVAL;
+	}
+
+	ret = pmt_telem_read(pmcdev->punit_ep, pmcdev->die_c6_offset,
+			     &count, 1);
+	if (ret)
+		return ret;
+
+	die_c6_res = div64_u64(count * HZ_PER_MHZ, pmcdev->crystal_freq);
+	seq_printf(s, "%llu\n", die_c6_res);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(pmc_core_die_c6_us);
+
 static int pmc_core_lpm_latch_mode_show(struct seq_file *s, void *unused)
 {
 	struct pmc_dev *pmcdev = s->private;
@@ -1118,6 +1161,12 @@ static void pmc_core_dbgfs_register(struct pmc_dev *pmcdev)
 				    pmcdev->dbgfs_dir, pmcdev,
 				    &pmc_core_substate_req_regs_fops);
 	}
+
+	if (pmcdev->has_die_c6) {
+		debugfs_create_file("die_c6_us_show", 0444,
+				    pmcdev->dbgfs_dir, pmcdev,
+				    &pmc_core_die_c6_us_fops);
+	}
 }
 
 static const struct x86_cpu_id intel_pmc_core_ids[] = {
@@ -1212,6 +1261,10 @@ static void pmc_core_clean_structure(struct platform_device *pdev)
 		pci_dev_put(pmcdev->ssram_pcidev);
 		pci_disable_device(pmcdev->ssram_pcidev);
 	}
+
+	if (pmcdev->punit_ep)
+		pmt_telem_unregister_endpoint(pmcdev->punit_ep);
+
 	platform_set_drvdata(pdev, NULL);
 	mutex_destroy(&pmcdev->lock);
 }
@@ -1232,6 +1285,8 @@ static int pmc_core_probe(struct platform_device *pdev)
 	if (!pmcdev)
 		return -ENOMEM;
 
+	pmcdev->crystal_freq = pmc_core_get_crystal_freq();
+
 	platform_set_drvdata(pdev, pmcdev);
 	pmcdev->pdev = pdev;
 
diff --git a/drivers/platform/x86/intel/pmc/core.h b/drivers/platform/x86/intel/pmc/core.h
index 85b6f6ae4995..6d7673145f90 100644
--- a/drivers/platform/x86/intel/pmc/core.h
+++ b/drivers/platform/x86/intel/pmc/core.h
@@ -16,6 +16,8 @@
 #include <linux/bits.h>
 #include <linux/platform_device.h>
 
+struct telem_endpoint;
+
 #define SLP_S0_RES_COUNTER_MASK			GENMASK(31, 0)
 
 #define PMC_BASE_ADDR_DEFAULT			0xFE000000
@@ -357,6 +359,7 @@ struct pmc {
  * @devs:		pointer to an array of pmc pointers
  * @pdev:		pointer to platform_device struct
  * @ssram_pcidev:	pointer to pci device struct for the PMC SSRAM
+ * @crystal_freq:	crystal frequency from cpuid
  * @dbgfs_dir:		path to debugfs interface
  * @pmc_xram_read_bit:	flag to indicate whether PMC XRAM shadow registers
  *			used to read MPHY PG and PLL status are available
@@ -374,6 +377,7 @@ struct pmc_dev {
 	struct dentry *dbgfs_dir;
 	struct platform_device *pdev;
 	struct pci_dev *ssram_pcidev;
+	unsigned int crystal_freq;
 	int pmc_xram_read_bit;
 	struct mutex lock; /* generic mutex lock for PMC Core */
 
-- 
2.34.1

[PATCH V3 16/16] platform/x86/intel/pmc: Show Die C6 counter on Meteor Lake

[David E. Box]

Expose the Die C6 counter on Meteor Lake.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
---
V3 - Split PATCH V2 13. Separates implementation (previous patch)
     from platform specific use (this patch)

 drivers/platform/x86/intel/pmc/mtl.c | 32 ++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/drivers/platform/x86/intel/pmc/mtl.c b/drivers/platform/x86/intel/pmc/mtl.c
index 7ceeae507f4c..38c2f946ec23 100644
--- a/drivers/platform/x86/intel/pmc/mtl.c
+++ b/drivers/platform/x86/intel/pmc/mtl.c
@@ -10,12 +10,17 @@
 
 #include <linux/pci.h>
 #include "core.h"
+#include "../pmt/telemetry.h"
 
 /* PMC SSRAM PMT Telemetry GUIDS */
 #define SOCP_LPM_REQ_GUID	0x2625030
 #define IOEM_LPM_REQ_GUID	0x4357464
 #define IOEP_LPM_REQ_GUID	0x5077612
 
+/* Die C6 from PUNIT telemetry */
+#define MTL_PMT_DMU_DIE_C6_OFFSET	15
+#define MTL_PMT_DMU_GUID		0x1A067102
+
 static const u8 MTL_LPM_REG_INDEX[] = {0, 4, 5, 6, 8, 9, 10, 11, 12, 13, 14, 15, 16, 20};
 
 /*
@@ -968,6 +973,32 @@ static struct pmc_info mtl_pmc_info_list[] = {
 	{}
 };
 
+static void mtl_punit_pmt_init(struct pmc_dev *pmcdev)
+{
+	struct telem_endpoint *ep;
+	struct pci_dev *pcidev;
+
+	pcidev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(10, 0));
+	if (!pcidev) {
+		dev_err(&pmcdev->pdev->dev, "PUNIT PMT device not found.\n");
+		return;
+	}
+
+	ep = pmt_telem_find_and_register_endpoint(pcidev, MTL_PMT_DMU_GUID, 0);
+	if (IS_ERR(ep)) {
+		dev_err(&pmcdev->pdev->dev,
+			"pmc_core: couldn't get DMU telem endpoint, %ld\n",
+			PTR_ERR(ep));
+		return;
+	}
+
+	pci_dev_put(pcidev);
+	pmcdev->punit_ep = ep;
+
+	pmcdev->has_die_c6 = true;
+	pmcdev->die_c6_offset = MTL_PMT_DMU_DIE_C6_OFFSET;
+}
+
 #define MTL_GNA_PCI_DEV	0x7e4c
 #define MTL_IPU_PCI_DEV	0x7d19
 #define MTL_VPU_PCI_DEV	0x7d1d
@@ -1032,6 +1063,7 @@ int mtl_core_init(struct pmc_dev *pmcdev)
 	}
 
 	pmc_core_get_low_power_modes(pmcdev);
+	mtl_punit_pmt_init(pmcdev);
 
 	/* Due to a hardware limitation, the GBE LTR blocks PC10
 	 * when a cable is attached. Tell the PMC to ignore it.
-- 
2.34.1

Re: [PATCH V3 03/16] platform/x86/intel/vsec: Use cleanup.h

[kernel test robot]

Hi David,

kernel test robot noticed the following build warnings:

[auto build test WARNING on acce85a7dd28eac3858d44230f4c65985d0f271c]

url:    https://github.com/intel-lab-lkp/linux/commits/David-E-Box/platform-x86-intel-vsec-Move-structures-to-header/20231012-104217
base:   acce85a7dd28eac3858d44230f4c65985d0f271c
patch link:    https://lore.kernel.org/r/20231012023840.3845703-4-david.e.box%40linux.intel.com
patch subject: [PATCH V3 03/16] platform/x86/intel/vsec: Use cleanup.h
reproduce: (https://download.01.org/0day-ci/archive/20231012/202310121314.3Xpqom2w-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202310121314.3Xpqom2w-lkp@intel.com/

# many are suggestions rather than must-fix

ERROR:SPACING: need consistent spacing around '*' (ctx:WxV)
#31: FILE: drivers/platform/x86/intel/vsec.c:159:
+	struct intel_vsec_device __free(kfree) *intel_vsec_dev = NULL;
 	                                       ^

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH V3 03/16] platform/x86/intel/vsec: Use cleanup.h

[kernel test robot]

Hi David,

kernel test robot noticed the following build warnings:

[auto build test WARNING on acce85a7dd28eac3858d44230f4c65985d0f271c]

url:    https://github.com/intel-lab-lkp/linux/commits/David-E-Box/platform-x86-intel-vsec-Move-structures-to-header/20231012-104217
base:   acce85a7dd28eac3858d44230f4c65985d0f271c
patch link:    https://lore.kernel.org/r/20231012023840.3845703-4-david.e.box%40linux.intel.com
patch subject: [PATCH V3 03/16] platform/x86/intel/vsec: Use cleanup.h
reproduce: (https://download.01.org/0day-ci/archive/20231012/202310121333.TE7R7kSs-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202310121333.TE7R7kSs-lkp@intel.com/

# many are suggestions rather than must-fix

ERROR:SPACING: need consistent spacing around '*' (ctx:WxV)
#31: FILE: drivers/platform/x86/intel/vsec.c:159:
+	struct intel_vsec_device __free(kfree) *intel_vsec_dev = NULL;
 	                                       ^

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH V3 03/16] platform/x86/intel/vsec: Use cleanup.h

[Ilpo Järvinen]

On Wed, 11 Oct 2023, David E. Box wrote:

> Use cleanup.h helpers to handle cleanup of resources in
> intel_vsec_add_dev() after failures.
> 
> Signed-off-by: David E. Box <david.e.box@linux.intel.com>
> ---
> V3 - New patch.
> 
>  drivers/platform/x86/intel/vsec.c | 17 ++++++++++-------
>  1 file changed, 10 insertions(+), 7 deletions(-)
> 
> diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c
> index 15866b7d3117..f03ab89ab7c0 100644
> --- a/drivers/platform/x86/intel/vsec.c
> +++ b/drivers/platform/x86/intel/vsec.c
> @@ -15,6 +15,7 @@
>  
>  #include <linux/auxiliary_bus.h>
>  #include <linux/bits.h>
> +#include <linux/cleanup.h>
>  #include <linux/delay.h>
>  #include <linux/kernel.h>
>  #include <linux/idr.h>
> @@ -155,10 +156,10 @@ EXPORT_SYMBOL_NS_GPL(intel_vsec_add_aux, INTEL_VSEC);
>  static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *header,
>  			      struct intel_vsec_platform_info *info)
>  {
> -	struct intel_vsec_device *intel_vsec_dev;
> +	struct intel_vsec_device __free(kfree) *intel_vsec_dev = NULL;
>  	struct resource *res, *tmp;
>  	unsigned long quirks = info->quirks;
> -	int i;
> +	int ret, i;
>  
>  	if (!intel_vsec_supported(header->id, info->caps))
>  		return -EINVAL;
> @@ -178,10 +179,8 @@ static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *he
>  		return -ENOMEM;
>  
>  	res = kcalloc(header->num_entries, sizeof(*res), GFP_KERNEL);
> -	if (!res) {
> -		kfree(intel_vsec_dev);
> +	if (!res)
>  		return -ENOMEM;
> -	}
>  
>  	if (quirks & VSEC_QUIRK_TABLE_SHIFT)
>  		header->offset >>= TABLE_OFFSET_SHIFT;
> @@ -208,8 +207,12 @@ static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *he
>  	else
>  		intel_vsec_dev->ida = &intel_vsec_ida;
>  
> -	return intel_vsec_add_aux(pdev, NULL, intel_vsec_dev,
> -				  intel_vsec_name(header->id));
> +	ret = intel_vsec_add_aux(pdev, NULL, intel_vsec_dev,
> +				 intel_vsec_name(header->id));
> +
> +	no_free_ptr(intel_vsec_dev);
> +
> +	return ret;

So if intel_vsec_add_aux() returned an error, intel_vsec_dev won't be 
freed because of the call call to no_free_ptr() before return. I that's 
not what you intended?

-- 
 i.

Re: [PATCH V3 09/16] platform/x86/intel/pmc: Allow pmc_core_ssram_init to fail

[Ilpo Järvinen]

On Wed, 11 Oct 2023, David E. Box wrote:

> Currently, if the PMC SSRAM initialization fails, no error is returned and
> the only indication is that a PMC device has not been created.  Instead,
> allow an error to be returned and handled directly by the caller.

You might have a good reason for it but why isn't the call into 
pmc_core_pmc_add() changed in this patch to take the error value into 
account?

(I vaguely remember this was probably discussed in the context of some 
earlier patch touching this area that it was about the other code dealing 
with NULLs or something like that).

-- 
 i.

> Signed-off-by: David E. Box <david.e.box@linux.intel.com>
> ---
> V3 - New patch split from V2 PATCH 9
>    - Add dev_warn on pmc_core_ssram_init fail
> 
>  drivers/platform/x86/intel/pmc/core.h       |  2 +-
>  drivers/platform/x86/intel/pmc/core.h       |  2 +-
>  drivers/platform/x86/intel/pmc/core_ssram.c | 21 +++++++++++++--------
>  drivers/platform/x86/intel/pmc/mtl.c        | 12 ++++++++----
>  3 files changed, 22 insertions(+), 13 deletions(-)
> 
> diff --git a/drivers/platform/x86/intel/pmc/core.h b/drivers/platform/x86/intel/pmc/core.h
> index ccf24e0f5e50..edaa70067e41 100644
> --- a/drivers/platform/x86/intel/pmc/core.h
> +++ b/drivers/platform/x86/intel/pmc/core.h
> @@ -492,7 +492,7 @@ int pmc_core_resume_common(struct pmc_dev *pmcdev);
>  int get_primary_reg_base(struct pmc *pmc);
>  extern void pmc_core_get_low_power_modes(struct pmc_dev *pmcdev);
>  
> -extern void pmc_core_ssram_init(struct pmc_dev *pmcdev);
> +extern int pmc_core_ssram_init(struct pmc_dev *pmcdev);
>  
>  int spt_core_init(struct pmc_dev *pmcdev);
>  int cnp_core_init(struct pmc_dev *pmcdev);
> diff --git a/drivers/platform/x86/intel/pmc/core_ssram.c b/drivers/platform/x86/intel/pmc/core_ssram.c
> index 13fa16f0d52e..815950713e25 100644
> --- a/drivers/platform/x86/intel/pmc/core_ssram.c
> +++ b/drivers/platform/x86/intel/pmc/core_ssram.c
> @@ -35,20 +35,20 @@ static inline u64 get_base(void __iomem *addr, u32 offset)
>  	return lo_hi_readq(addr + offset) & GENMASK_ULL(63, 3);
>  }
>  
> -static void
> +static int
>  pmc_core_pmc_add(struct pmc_dev *pmcdev, u64 pwrm_base,
>  		 const struct pmc_reg_map *reg_map, int pmc_index)
>  {
>  	struct pmc *pmc = pmcdev->pmcs[pmc_index];
>  
>  	if (!pwrm_base)
> -		return;
> +		return -ENODEV;
>  
>  	/* Memory for primary PMC has been allocated in core.c */
>  	if (!pmc) {
>  		pmc = devm_kzalloc(&pmcdev->pdev->dev, sizeof(*pmc), GFP_KERNEL);
>  		if (!pmc)
> -			return;
> +			return -ENOMEM;
>  	}
>  
>  	pmc->map = reg_map;
> @@ -57,10 +57,12 @@ pmc_core_pmc_add(struct pmc_dev *pmcdev, u64 pwrm_base,
>  
>  	if (!pmc->regbase) {
>  		devm_kfree(&pmcdev->pdev->dev, pmc);
> -		return;
> +		return -ENOMEM;
>  	}
>  
>  	pmcdev->pmcs[pmc_index] = pmc;
> +
> +	return 0;
>  }
>  
>  static void
> @@ -96,7 +98,7 @@ pmc_core_ssram_get_pmc(struct pmc_dev *pmcdev, void __iomem *ssram, u32 offset,
>  		iounmap(ssram);
>  }
>  
> -void pmc_core_ssram_init(struct pmc_dev *pmcdev)
> +int pmc_core_ssram_init(struct pmc_dev *pmcdev)
>  {
>  	void __iomem *ssram;
>  	struct pci_dev *pcidev;
> @@ -105,7 +107,7 @@ void pmc_core_ssram_init(struct pmc_dev *pmcdev)
>  
>  	pcidev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(20, 2));
>  	if (!pcidev)
> -		goto out;
> +		return -ENODEV;
>  
>  	ret = pcim_enable_device(pcidev);
>  	if (ret)
> @@ -123,11 +125,14 @@ void pmc_core_ssram_init(struct pmc_dev *pmcdev)
>  	pmc_core_ssram_get_pmc(pmcdev, ssram, SSRAM_PCH_OFFSET, PMC_IDX_PCH);
>  
>  	iounmap(ssram);
> -out:
> -	return;
> +
> +	return 0;
>  
>  disable_dev:
> +	pmcdev->ssram_pcidev = NULL;
>  	pci_disable_device(pcidev);
>  release_dev:
>  	pci_dev_put(pcidev);
> +
> +	return ret;
>  }
> diff --git a/drivers/platform/x86/intel/pmc/mtl.c b/drivers/platform/x86/intel/pmc/mtl.c
> index c3b5f4fe01d1..d1d3d33fb4b8 100644
> --- a/drivers/platform/x86/intel/pmc/mtl.c
> +++ b/drivers/platform/x86/intel/pmc/mtl.c
> @@ -990,12 +990,16 @@ int mtl_core_init(struct pmc_dev *pmcdev)
>  	mtl_d3_fixup();
>  
>  	pmcdev->resume = mtl_resume;
> -
>  	pmcdev->regmap_list = mtl_pmc_info_list;
> -	pmc_core_ssram_init(pmcdev);
>  
> -	/* If regbase not assigned, set map and discover using legacy method */
> -	if (!pmc->regbase) {
> +	/*
> +	 * If ssram init fails use legacy method to at least get the
> +	 * primary PMC
> +	 */
> +	ret = pmc_core_ssram_init(pmcdev);
> +	if (ret) {
> +		dev_warn(&pmcdev->pdev->dev,
> +			 "ssram init failed, %d, using legacy init\n", ret);
>  		pmc->map = &mtl_socm_reg_map;
>  		ret = get_primary_reg_base(pmc);
>  		if (ret)
> 

Re: [PATCH V3 10/16] platform/x86/intel/pmc: Split pmc_core_ssram_get_pmc()

[Ilpo Järvinen]

On Wed, 11 Oct 2023, David E. Box wrote:

> On supported hardware, each PMC may have an associated SSRAM device for
> accessing additional counters.  However, only the SSRAM of the first
> (primary) PMC is discoverable as a PCI device to the OS. The remaining
> (secondary) devices are hidden but their BARs are still accessible and
> their addresses are stored in the BAR of the exposed device. Clean up the
> code handling the SSRAM discovery. Create two separate functions for
> accessing the primary and secondary SSRAM devices.
> 
> Signed-off-by: David E. Box <david.e.box@linux.intel.com>
> ---
> V3 - New patch split from previous PATCH 2
>    - Update changelog
>    - Use cleanup.h to cleanup ioremap
> 
> V2 - no change
> 
>  drivers/platform/x86/intel/pmc/core_ssram.c | 93 ++++++++++++++-------
>  1 file changed, 61 insertions(+), 32 deletions(-)
> 
> diff --git a/drivers/platform/x86/intel/pmc/core_ssram.c b/drivers/platform/x86/intel/pmc/core_ssram.c
> index 815950713e25..af405d11919f 100644
> --- a/drivers/platform/x86/intel/pmc/core_ssram.c
> +++ b/drivers/platform/x86/intel/pmc/core_ssram.c
> @@ -8,6 +8,7 @@
>   *
>   */
>  
> +#include <linux/cleanup.h>
>  #include <linux/pci.h>
>  #include <linux/io-64-nonatomic-lo-hi.h>
>  
> @@ -21,6 +22,8 @@
>  #define SSRAM_IOE_OFFSET	0x68
>  #define SSRAM_DEVID_OFFSET	0x70
>  
> +DEFINE_FREE(pmc_core_iounmap, void __iomem *, iounmap(_T));
> +

Was it that adding

DEFINE_FREE(iounmap, void __iomem *, iounmap(_T));

into some header did not work for some reason or why this? (Perhaps 
because iounmap is also defined?)

-- 
 i.

>  static const struct pmc_reg_map *pmc_core_find_regmap(struct pmc_info *list, u16 devid)
>  {
>  	for (; list->map; ++list)
> @@ -65,44 +68,74 @@ pmc_core_pmc_add(struct pmc_dev *pmcdev, u64 pwrm_base,
>  	return 0;
>  }
>  
> -static void
> -pmc_core_ssram_get_pmc(struct pmc_dev *pmcdev, void __iomem *ssram, u32 offset,
> -		       int pmc_idx)
> +static int
> +pmc_core_get_secondary_pmc(struct pmc_dev *pmcdev, int pmc_idx, u32 offset)
>  {
> -	u64 pwrm_base;
> +	struct pci_dev *ssram_pcidev = pmcdev->ssram_pcidev;
> +	void __iomem __free(pmc_core_iounmap) *main_ssram = NULL;
> +	void __iomem __free(pmc_core_iounmap) *secondary_ssram = NULL;
> +	const struct pmc_reg_map *map;
> +	u64 ssram_base, pwrm_base;
>  	u16 devid;
>  
> -	if (pmc_idx != PMC_IDX_SOC) {
> -		u64 ssram_base = get_base(ssram, offset);
> +	if (!pmcdev->regmap_list)
> +		return -ENOENT;
>  
> -		if (!ssram_base)
> -			return;
> +	/*
> +	 * The secondary PMC BARS (which are behind hidden PCI devices) are read
> +	 * from fixed offsets in MMIO of the primary PMC BAR.
> +	 */
> +	ssram_base = ssram_pcidev->resource[0].start;
> +	main_ssram = ioremap(ssram_base, SSRAM_HDR_SIZE);
> +	if (!main_ssram)
> +		return -ENOMEM;
>  
> -		ssram = ioremap(ssram_base, SSRAM_HDR_SIZE);
> -		if (!ssram)
> -			return;
> -	}
> +	ssram_base = get_base(main_ssram, offset);
> +	secondary_ssram = ioremap(ssram_base, SSRAM_HDR_SIZE);
> +	if (!secondary_ssram)
> +		return -ENOMEM;
> +
> +	pwrm_base = get_base(secondary_ssram, SSRAM_PWRM_OFFSET);
> +	devid = readw(secondary_ssram + SSRAM_DEVID_OFFSET);
> +
> +	map = pmc_core_find_regmap(pmcdev->regmap_list, devid);
> +	if (!map)
> +		return -ENODEV;
> +
> +	return pmc_core_pmc_add(pmcdev, pwrm_base, map, pmc_idx);
> +}
> +
> +static int
> +pmc_core_get_primary_pmc(struct pmc_dev *pmcdev)
> +{
> +	struct pci_dev *ssram_pcidev = pmcdev->ssram_pcidev;
> +	void __iomem __free(pmc_core_iounmap) *ssram;
> +	const struct pmc_reg_map *map;
> +	u64 ssram_base, pwrm_base;
> +	u16 devid;
> +
> +	if (!pmcdev->regmap_list)
> +		return -ENOENT;
> +
> +	/* The primary PMC (SOC die) BAR is BAR 0 in config space. */
> +	ssram_base = ssram_pcidev->resource[0].start;
> +	ssram = ioremap(ssram_base, SSRAM_HDR_SIZE);
> +	if (!ssram)
> +		return -ENOMEM;
>  
>  	pwrm_base = get_base(ssram, SSRAM_PWRM_OFFSET);
>  	devid = readw(ssram + SSRAM_DEVID_OFFSET);
>  
> -	if (pmcdev->regmap_list) {
> -		const struct pmc_reg_map *map;
> +	map = pmc_core_find_regmap(pmcdev->regmap_list, devid);
> +	if (!map)
> +		return -ENODEV;
>  
> -		map = pmc_core_find_regmap(pmcdev->regmap_list, devid);
> -		if (map)
> -			pmc_core_pmc_add(pmcdev, pwrm_base, map, pmc_idx);
> -	}
> -
> -	if (pmc_idx != PMC_IDX_SOC)
> -		iounmap(ssram);
> +	return pmc_core_pmc_add(pmcdev, pwrm_base, map, PMC_IDX_MAIN);
>  }
>  
>  int pmc_core_ssram_init(struct pmc_dev *pmcdev)
>  {
> -	void __iomem *ssram;
>  	struct pci_dev *pcidev;
> -	u64 ssram_base;
>  	int ret;
>  
>  	pcidev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(20, 2));
> @@ -113,18 +146,14 @@ int pmc_core_ssram_init(struct pmc_dev *pmcdev)
>  	if (ret)
>  		goto release_dev;
>  
> -	ssram_base = pcidev->resource[0].start;
> -	ssram = ioremap(ssram_base, SSRAM_HDR_SIZE);
> -	if (!ssram)
> -		goto disable_dev;
> -
>  	pmcdev->ssram_pcidev = pcidev;
>  
> -	pmc_core_ssram_get_pmc(pmcdev, ssram, 0, PMC_IDX_SOC);
> -	pmc_core_ssram_get_pmc(pmcdev, ssram, SSRAM_IOE_OFFSET, PMC_IDX_IOE);
> -	pmc_core_ssram_get_pmc(pmcdev, ssram, SSRAM_PCH_OFFSET, PMC_IDX_PCH);
> +	ret = pmc_core_get_primary_pmc(pmcdev);
> +	if (ret)
> +		goto disable_dev;
>  
> -	iounmap(ssram);
> +	pmc_core_get_secondary_pmc(pmcdev, PMC_IDX_IOE, SSRAM_IOE_OFFSET);
> +	pmc_core_get_secondary_pmc(pmcdev, PMC_IDX_PCH, SSRAM_PCH_OFFSET);
>  
>  	return 0;
>  
> 

Re: [PATCH V3 11/16] platform/x86/intel/pmc: Find and register PMC telemetry entries

[Ilpo Järvinen]

[-- Attachment #1: Type: text/plain, Size: 4084 bytes --]

On Wed, 11 Oct 2023, David E. Box wrote:

> The PMC SSRAM device contains counters that are structured in Intel
> Platform Monitoring Technology (PMT) telemetry regions. Look for and
> register these telemetry regions from the driver so that they may be read
> using the Intel PMT ABI.
> 
> Signed-off-by: David E. Box <david.e.box@linux.intel.com>
> ---
> V3 - no change
> 
> V2 - no change
> 
>  drivers/platform/x86/intel/pmc/Kconfig      |  1 +
>  drivers/platform/x86/intel/pmc/core_ssram.c | 52 +++++++++++++++++++++
>  2 files changed, 53 insertions(+)
> 
> diff --git a/drivers/platform/x86/intel/pmc/Kconfig b/drivers/platform/x86/intel/pmc/Kconfig
> index b526597e4deb..d2f651fbec2c 100644
> --- a/drivers/platform/x86/intel/pmc/Kconfig
> +++ b/drivers/platform/x86/intel/pmc/Kconfig
> @@ -7,6 +7,7 @@ config INTEL_PMC_CORE
>  	tristate "Intel PMC Core driver"
>  	depends on PCI
>  	depends on ACPI
> +	depends on INTEL_PMT_TELEMETRY
>  	help
>  	  The Intel Platform Controller Hub for Intel Core SoCs provides access
>  	  to Power Management Controller registers via various interfaces. This
> diff --git a/drivers/platform/x86/intel/pmc/core_ssram.c b/drivers/platform/x86/intel/pmc/core_ssram.c
> index af405d11919f..1ecfa3804117 100644
> --- a/drivers/platform/x86/intel/pmc/core_ssram.c
> +++ b/drivers/platform/x86/intel/pmc/core_ssram.c
> @@ -13,6 +13,8 @@
>  #include <linux/io-64-nonatomic-lo-hi.h>
>  
>  #include "core.h"
> +#include "../vsec.h"
> +#include "../pmt/telemetry.h"
>  
>  #define SSRAM_HDR_SIZE		0x100
>  #define SSRAM_PWRM_OFFSET	0x14
> @@ -24,6 +26,49 @@
>  
>  DEFINE_FREE(pmc_core_iounmap, void __iomem *, iounmap(_T));
>  
> +static void
> +pmc_add_pmt(struct pmc_dev *pmcdev, u64 ssram_base, void __iomem *ssram)
> +{
> +	struct pci_dev *pcidev = pmcdev->ssram_pcidev;
> +	struct intel_vsec_platform_info info = {};
> +	struct intel_vsec_header *headers[2] = {};
> +	struct intel_vsec_header header;
> +	void __iomem *dvsec;
> +	u32 dvsec_offset;
> +	u32 table, hdr;
> +
> +	ssram = ioremap(ssram_base, SSRAM_HDR_SIZE);
> +	if (!ssram)
> +		return;
> +
> +	dvsec_offset = readl(ssram + SSRAM_DVSEC_OFFSET);
> +	iounmap(ssram);
> +
> +	dvsec = ioremap(ssram_base + dvsec_offset, SSRAM_DVSEC_SIZE);
> +	if (!dvsec)
> +		return;
> +
> +	hdr = readl(dvsec + PCI_DVSEC_HEADER1);
> +	header.id = readw(dvsec + PCI_DVSEC_HEADER2);
> +	header.rev = PCI_DVSEC_HEADER1_REV(hdr);
> +	header.length = PCI_DVSEC_HEADER1_LEN(hdr);
> +	header.num_entries = readb(dvsec + INTEL_DVSEC_ENTRIES);
> +	header.entry_size = readb(dvsec + INTEL_DVSEC_SIZE);
> +
> +	table = readl(dvsec + INTEL_DVSEC_TABLE);
> +	header.tbir = INTEL_DVSEC_TABLE_BAR(table);
> +	header.offset = INTEL_DVSEC_TABLE_OFFSET(table);
> +	iounmap(dvsec);
> +
> +	headers[0] = &header;
> +	info.caps = VSEC_CAP_TELEMETRY;
> +	info.headers = headers;
> +	info.base_addr = ssram_base;
> +	info.parent = &pmcdev->pdev->dev;
> +
> +	intel_vsec_register(pcidev, &info);
> +}
> +
>  static const struct pmc_reg_map *pmc_core_find_regmap(struct pmc_info *list, u16 devid)
>  {
>  	for (; list->map; ++list)
> @@ -98,6 +143,9 @@ pmc_core_get_secondary_pmc(struct pmc_dev *pmcdev, int pmc_idx, u32 offset)
>  	pwrm_base = get_base(secondary_ssram, SSRAM_PWRM_OFFSET);
>  	devid = readw(secondary_ssram + SSRAM_DEVID_OFFSET);
>  
> +	/* Find and register and PMC telemetry entries */
> +	pmc_add_pmt(pmcdev, ssram_base, main_ssram);
> +
>  	map = pmc_core_find_regmap(pmcdev->regmap_list, devid);
>  	if (!map)
>  		return -ENODEV;
> @@ -126,6 +174,9 @@ pmc_core_get_primary_pmc(struct pmc_dev *pmcdev)
>  	pwrm_base = get_base(ssram, SSRAM_PWRM_OFFSET);
>  	devid = readw(ssram + SSRAM_DEVID_OFFSET);
>  
> +	/* Find and register and PMC telemetry entries */
> +	pmc_add_pmt(pmcdev, ssram_base, ssram);
> +
>  	map = pmc_core_find_regmap(pmcdev->regmap_list, devid);
>  	if (!map)
>  		return -ENODEV;
> @@ -165,3 +216,4 @@ int pmc_core_ssram_init(struct pmc_dev *pmcdev)
>  
>  	return ret;
>  }
> +MODULE_IMPORT_NS(INTEL_VSEC);

Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>

-- 
 i.

Re: [PATCH V3 02/16] platform/x86/intel/vsec: remove platform_info from vsec device structure

[Ilpo Järvinen]

[-- Attachment #1: Type: text/plain, Size: 2616 bytes --]

On Wed, 11 Oct 2023, David E. Box wrote:

> In preparation for exporting an API to register Intel Vendor Specific
> Extended Capabilities (VSEC) from other drivers, remove the pointer to
> platform_info from intel_vsec_device. This prevents a potential page fault
> when auxiliary drivers probe and attempt to dereference this pointer to
> access the needed quirks field. Instead, just add the quirks to
> intel_vsec_device.
> 
> Signed-off-by: David E. Box <david.e.box@linux.intel.com>
> Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
> ---
> V3 - No change
> 
> V2 - New patch splitting previous PATCH 1
> 
>  drivers/platform/x86/intel/pmt/class.c | 2 +-
>  drivers/platform/x86/intel/vsec.c      | 2 +-
>  drivers/platform/x86/intel/vsec.h      | 2 +-
>  3 files changed, 3 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/platform/x86/intel/pmt/class.c b/drivers/platform/x86/intel/pmt/class.c
> index f32a233470de..2ad91d2fd954 100644
> --- a/drivers/platform/x86/intel/pmt/class.c
> +++ b/drivers/platform/x86/intel/pmt/class.c
> @@ -31,7 +31,7 @@ bool intel_pmt_is_early_client_hw(struct device *dev)
>  	 * differences from the server platforms (which use the Out Of Band
>  	 * Management Services Module OOBMSM).
>  	 */
> -	return !!(ivdev->info->quirks & VSEC_QUIRK_EARLY_HW);
> +	return !!(ivdev->quirks & VSEC_QUIRK_EARLY_HW);
>  }
>  EXPORT_SYMBOL_NS_GPL(intel_pmt_is_early_client_hw, INTEL_PMT);
>  
> diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c
> index 6bb233a23414..15866b7d3117 100644
> --- a/drivers/platform/x86/intel/vsec.c
> +++ b/drivers/platform/x86/intel/vsec.c
> @@ -201,7 +201,7 @@ static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *he
>  	intel_vsec_dev->pcidev = pdev;
>  	intel_vsec_dev->resource = res;
>  	intel_vsec_dev->num_resources = header->num_entries;
> -	intel_vsec_dev->info = info;
> +	intel_vsec_dev->quirks = info->quirks;
>  
>  	if (header->id == VSEC_ID_SDSI)
>  		intel_vsec_dev->ida = &intel_vsec_sdsi_ida;
> diff --git a/drivers/platform/x86/intel/vsec.h b/drivers/platform/x86/intel/vsec.h
> index c242c07ea69c..8b9fad170503 100644
> --- a/drivers/platform/x86/intel/vsec.h
> +++ b/drivers/platform/x86/intel/vsec.h
> @@ -79,11 +79,11 @@ struct intel_vsec_device {
>  	struct pci_dev *pcidev;
>  	struct resource *resource;
>  	struct ida *ida;
> -	struct intel_vsec_platform_info *info;
>  	int num_resources;
>  	int id; /* xa */

What is this based on??

Unfortunately, I couldn't review some of your later patches efficiently 
because this patch failed to apply.

-- 
 i.

Re: [PATCH V3 02/16] platform/x86/intel/vsec: remove platform_info from vsec device structure

[David E. Box]

On Thu, 2023-10-12 at 18:31 +0300, Ilpo Järvinen wrote:
> On Wed, 11 Oct 2023, David E. Box wrote:
> 
> > In preparation for exporting an API to register Intel Vendor Specific
> > Extended Capabilities (VSEC) from other drivers, remove the pointer to
> > platform_info from intel_vsec_device. This prevents a potential page fault
> > when auxiliary drivers probe and attempt to dereference this pointer to
> > access the needed quirks field. Instead, just add the quirks to
> > intel_vsec_device.
> > 
> > Signed-off-by: David E. Box <david.e.box@linux.intel.com>
> > Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
> > ---
> > V3 - No change
> > 
> > V2 - New patch splitting previous PATCH 1
> > 
> >  drivers/platform/x86/intel/pmt/class.c | 2 +-
> >  drivers/platform/x86/intel/vsec.c      | 2 +-
> >  drivers/platform/x86/intel/vsec.h      | 2 +-
> >  3 files changed, 3 insertions(+), 3 deletions(-)
> > 
> > diff --git a/drivers/platform/x86/intel/pmt/class.c
> > b/drivers/platform/x86/intel/pmt/class.c
> > index f32a233470de..2ad91d2fd954 100644
> > --- a/drivers/platform/x86/intel/pmt/class.c
> > +++ b/drivers/platform/x86/intel/pmt/class.c
> > @@ -31,7 +31,7 @@ bool intel_pmt_is_early_client_hw(struct device *dev)
> >          * differences from the server platforms (which use the Out Of Band
> >          * Management Services Module OOBMSM).
> >          */
> > -       return !!(ivdev->info->quirks & VSEC_QUIRK_EARLY_HW);
> > +       return !!(ivdev->quirks & VSEC_QUIRK_EARLY_HW);
> >  }
> >  EXPORT_SYMBOL_NS_GPL(intel_pmt_is_early_client_hw, INTEL_PMT);
> >  
> > diff --git a/drivers/platform/x86/intel/vsec.c
> > b/drivers/platform/x86/intel/vsec.c
> > index 6bb233a23414..15866b7d3117 100644
> > --- a/drivers/platform/x86/intel/vsec.c
> > +++ b/drivers/platform/x86/intel/vsec.c
> > @@ -201,7 +201,7 @@ static int intel_vsec_add_dev(struct pci_dev *pdev,
> > struct intel_vsec_header *he
> >         intel_vsec_dev->pcidev = pdev;
> >         intel_vsec_dev->resource = res;
> >         intel_vsec_dev->num_resources = header->num_entries;
> > -       intel_vsec_dev->info = info;
> > +       intel_vsec_dev->quirks = info->quirks;
> >  
> >         if (header->id == VSEC_ID_SDSI)
> >                 intel_vsec_dev->ida = &intel_vsec_sdsi_ida;
> > diff --git a/drivers/platform/x86/intel/vsec.h
> > b/drivers/platform/x86/intel/vsec.h
> > index c242c07ea69c..8b9fad170503 100644
> > --- a/drivers/platform/x86/intel/vsec.h
> > +++ b/drivers/platform/x86/intel/vsec.h
> > @@ -79,11 +79,11 @@ struct intel_vsec_device {
> >         struct pci_dev *pcidev;
> >         struct resource *resource;
> >         struct ida *ida;
> > -       struct intel_vsec_platform_info *info;
> >         int num_resources;
> >         int id; /* xa */
> 
> What is this based on??
> 
> Unfortunately, I couldn't review some of your later patches efficiently 
> because this patch failed to apply.

platform-drivers-x86-v6.6-1 tag

I guess I need to update but I didn't expect any new changes that would
conflict.

David

Re: [PATCH V3 03/16] platform/x86/intel/vsec: Use cleanup.h

[David E. Box]

On Thu, 2023-10-12 at 17:46 +0300, Ilpo Järvinen wrote:
> On Wed, 11 Oct 2023, David E. Box wrote:
> 
> > Use cleanup.h helpers to handle cleanup of resources in
> > intel_vsec_add_dev() after failures.
> > 
> > Signed-off-by: David E. Box <david.e.box@linux.intel.com>
> > ---
> > V3 - New patch.
> > 
> >  drivers/platform/x86/intel/vsec.c | 17 ++++++++++-------
> >  1 file changed, 10 insertions(+), 7 deletions(-)
> > 
> > diff --git a/drivers/platform/x86/intel/vsec.c
> > b/drivers/platform/x86/intel/vsec.c
> > index 15866b7d3117..f03ab89ab7c0 100644
> > --- a/drivers/platform/x86/intel/vsec.c
> > +++ b/drivers/platform/x86/intel/vsec.c
> > @@ -15,6 +15,7 @@
> >  
> >  #include <linux/auxiliary_bus.h>
> >  #include <linux/bits.h>
> > +#include <linux/cleanup.h>
> >  #include <linux/delay.h>
> >  #include <linux/kernel.h>
> >  #include <linux/idr.h>
> > @@ -155,10 +156,10 @@ EXPORT_SYMBOL_NS_GPL(intel_vsec_add_aux, INTEL_VSEC);
> >  static int intel_vsec_add_dev(struct pci_dev *pdev, struct
> > intel_vsec_header *header,
> >                               struct intel_vsec_platform_info *info)
> >  {
> > -       struct intel_vsec_device *intel_vsec_dev;
> > +       struct intel_vsec_device __free(kfree) *intel_vsec_dev = NULL;
> >         struct resource *res, *tmp;
> >         unsigned long quirks = info->quirks;
> > -       int i;
> > +       int ret, i;
> >  
> >         if (!intel_vsec_supported(header->id, info->caps))
> >                 return -EINVAL;
> > @@ -178,10 +179,8 @@ static int intel_vsec_add_dev(struct pci_dev *pdev,
> > struct intel_vsec_header *he
> >                 return -ENOMEM;
> >  
> >         res = kcalloc(header->num_entries, sizeof(*res), GFP_KERNEL);
> > -       if (!res) {
> > -               kfree(intel_vsec_dev);
> > +       if (!res)
> >                 return -ENOMEM;
> > -       }
> >  
> >         if (quirks & VSEC_QUIRK_TABLE_SHIFT)
> >                 header->offset >>= TABLE_OFFSET_SHIFT;
> > @@ -208,8 +207,12 @@ static int intel_vsec_add_dev(struct pci_dev *pdev,
> > struct intel_vsec_header *he
> >         else
> >                 intel_vsec_dev->ida = &intel_vsec_ida;
> >  
> > -       return intel_vsec_add_aux(pdev, NULL, intel_vsec_dev,
> > -                                 intel_vsec_name(header->id));
> > +       ret = intel_vsec_add_aux(pdev, NULL, intel_vsec_dev,
> > +                                intel_vsec_name(header->id));
> > +
> > +       no_free_ptr(intel_vsec_dev);
> > +
> > +       return ret;
> 
> So if intel_vsec_add_aux() returned an error, intel_vsec_dev won't be 
> freed because of the call call to no_free_ptr() before return. I that's 
> not what you intended?

It will have been freed if intel_vsec_add_aux() fails. It's a little messy. That
function creates the auxdev and assigns the release function which will free
intel_vsec_dev when the device is removed. But there are failure points that
will also invoke the release function. Because of this, for all the failure
points in that function we free intel_vsec_dev so that it's state doesn't need
to be questioned here. This happens explicitly if the failure is before
auxiliary_device_init(), or through the release function invoked by
auxiliary_device_uninit() if after.

David

> 

Re: [PATCH V3 03/16] platform/x86/intel/vsec: Use cleanup.h

[David E. Box]

On Thu, 2023-10-12 at 13:25 +0800, kernel test robot wrote:
> Hi David,
> 
> kernel test robot noticed the following build warnings:
> 
> [auto build test WARNING on acce85a7dd28eac3858d44230f4c65985d0f271c]
> 
> url:   
> https://github.com/intel-lab-lkp/linux/commits/David-E-Box/platform-x86-intel-vsec-Move-structures-to-header/20231012-104217
> base:   acce85a7dd28eac3858d44230f4c65985d0f271c
> patch link:   
> https://lore.kernel.org/r/20231012023840.3845703-4-david.e.box%40linux.intel.com
> patch subject: [PATCH V3 03/16] platform/x86/intel/vsec: Use cleanup.h
> reproduce:
> (https://download.01.org/0day-ci/archive/20231012/202310121314.3Xpqom2w-lkp@in
> tel.com/reproduce)
> 
> If you fix the issue in a separate patch/commit (i.e. not just a new version
> of
> the same patch/commit), kindly add following tags
> > Reported-by: kernel test robot <lkp@intel.com>
> > Closes:
> > https://lore.kernel.org/oe-kbuild-all/202310121314.3Xpqom2w-lkp@intel.com/
> 
> # many are suggestions rather than must-fix
> 
> ERROR:SPACING: need consistent spacing around '*' (ctx:WxV)
> #31: FILE: drivers/platform/x86/intel/vsec.c:159:
> +       struct intel_vsec_device __free(kfree) *intel_vsec_dev = NULL;

These looks like false positives.

David

>                                                ^
> 

Re: [PATCH V3 10/16] platform/x86/intel/pmc: Split pmc_core_ssram_get_pmc()

[David E. Box]

On Thu, 2023-10-12 at 18:14 +0300, Ilpo Järvinen wrote:
> On Wed, 11 Oct 2023, David E. Box wrote:
> 
> > On supported hardware, each PMC may have an associated SSRAM device for
> > accessing additional counters.  However, only the SSRAM of the first
> > (primary) PMC is discoverable as a PCI device to the OS. The remaining
> > (secondary) devices are hidden but their BARs are still accessible and
> > their addresses are stored in the BAR of the exposed device. Clean up the
> > code handling the SSRAM discovery. Create two separate functions for
> > accessing the primary and secondary SSRAM devices.
> > 
> > Signed-off-by: David E. Box <david.e.box@linux.intel.com>
> > ---
> > V3 - New patch split from previous PATCH 2
> >    - Update changelog
> >    - Use cleanup.h to cleanup ioremap
> > 
> > V2 - no change
> > 
> >  drivers/platform/x86/intel/pmc/core_ssram.c | 93 ++++++++++++++-------
> >  1 file changed, 61 insertions(+), 32 deletions(-)
> > 
> > diff --git a/drivers/platform/x86/intel/pmc/core_ssram.c
> > b/drivers/platform/x86/intel/pmc/core_ssram.c
> > index 815950713e25..af405d11919f 100644
> > --- a/drivers/platform/x86/intel/pmc/core_ssram.c
> > +++ b/drivers/platform/x86/intel/pmc/core_ssram.c
> > @@ -8,6 +8,7 @@
> >   *
> >   */
> >  
> > +#include <linux/cleanup.h>
> >  #include <linux/pci.h>
> >  #include <linux/io-64-nonatomic-lo-hi.h>
> >  
> > @@ -21,6 +22,8 @@
> >  #define SSRAM_IOE_OFFSET       0x68
> >  #define SSRAM_DEVID_OFFSET     0x70
> >  
> > +DEFINE_FREE(pmc_core_iounmap, void __iomem *, iounmap(_T));
> > +
> 
> Was it that adding
> 
> DEFINE_FREE(iounmap, void __iomem *, iounmap(_T));
> 
> into some header did not work for some reason or why this? (Perhaps 
> because iounmap is also defined?)

No, I didn't think to add it. I'll try and send in the next version.

David

> 

Re: [PATCH V3 09/16] platform/x86/intel/pmc: Allow pmc_core_ssram_init to fail

[David E. Box]

On Thu, 2023-10-12 at 18:01 +0300, Ilpo Järvinen wrote:
> On Wed, 11 Oct 2023, David E. Box wrote:
> 
> > Currently, if the PMC SSRAM initialization fails, no error is returned and
> > the only indication is that a PMC device has not been created.  Instead,
> > allow an error to be returned and handled directly by the caller.
> 
> You might have a good reason for it but why isn't the call into 
> pmc_core_pmc_add() changed in this patch to take the error value into 
> account?

Good catch. The return value of pmc_core_pmc_add() is first used in the next
patch but should be used here.

David

> 
> (I vaguely remember this was probably discussed in the context of some 
> earlier patch touching this area that it was about the other code dealing 
> with NULLs or something like that).

Re: [PATCH V3 03/16] platform/x86/intel/vsec: Use cleanup.h

[Ilpo Järvinen]

[-- Attachment #1: Type: text/plain, Size: 1578 bytes --]

Hi,

I added checkpatch people, please check what looks a false positive below.

On Thu, 12 Oct 2023, David E. Box wrote:

> On Thu, 2023-10-12 at 13:25 +0800, kernel test robot wrote:
> > Hi David,
> > 
> > kernel test robot noticed the following build warnings:
> > 
> > [auto build test WARNING on acce85a7dd28eac3858d44230f4c65985d0f271c]
> > 
> > url:   
> > https://github.com/intel-lab-lkp/linux/commits/David-E-Box/platform-x86-intel-vsec-Move-structures-to-header/20231012-104217
> > base:   acce85a7dd28eac3858d44230f4c65985d0f271c
> > patch link:   
> > https://lore.kernel.org/r/20231012023840.3845703-4-david.e.box%40linux.intel.com
> > patch subject: [PATCH V3 03/16] platform/x86/intel/vsec: Use cleanup.h
> > reproduce:
> > (https://download.01.org/0day-ci/archive/20231012/202310121314.3Xpqom2w-lkp@in
> > tel.com/reproduce)
> > 
> > If you fix the issue in a separate patch/commit (i.e. not just a new version
> > of
> > the same patch/commit), kindly add following tags
> > > Reported-by: kernel test robot <lkp@intel.com>
> > > Closes:
> > > https://lore.kernel.org/oe-kbuild-all/202310121314.3Xpqom2w-lkp@intel.com/
> > 
> > # many are suggestions rather than must-fix
> > 
> > ERROR:SPACING: need consistent spacing around '*' (ctx:WxV)
> > #31: FILE: drivers/platform/x86/intel/vsec.c:159:
> > +       struct intel_vsec_device __free(kfree) *intel_vsec_dev = NULL;
> 
> These looks like false positives.

I agree. If I interpret the error message right checkpatch seems to think
that's a multiplication which is not the case here.

-- 
 i.

Re: [PATCH V3 03/16] platform/x86/intel/vsec: Use cleanup.h

[Ilpo Järvinen]

[-- Attachment #1: Type: text/plain, Size: 4504 bytes --]

On Thu, 12 Oct 2023, David E. Box wrote:

> On Thu, 2023-10-12 at 17:46 +0300, Ilpo Järvinen wrote:
> > On Wed, 11 Oct 2023, David E. Box wrote:
> > 
> > > Use cleanup.h helpers to handle cleanup of resources in
> > > intel_vsec_add_dev() after failures.
> > > 
> > > Signed-off-by: David E. Box <david.e.box@linux.intel.com>
> > > ---
> > > V3 - New patch.
> > > 
> > >  drivers/platform/x86/intel/vsec.c | 17 ++++++++++-------
> > >  1 file changed, 10 insertions(+), 7 deletions(-)
> > > 
> > > diff --git a/drivers/platform/x86/intel/vsec.c
> > > b/drivers/platform/x86/intel/vsec.c
> > > index 15866b7d3117..f03ab89ab7c0 100644
> > > --- a/drivers/platform/x86/intel/vsec.c
> > > +++ b/drivers/platform/x86/intel/vsec.c
> > > @@ -15,6 +15,7 @@
> > >  
> > >  #include <linux/auxiliary_bus.h>
> > >  #include <linux/bits.h>
> > > +#include <linux/cleanup.h>
> > >  #include <linux/delay.h>
> > >  #include <linux/kernel.h>
> > >  #include <linux/idr.h>
> > > @@ -155,10 +156,10 @@ EXPORT_SYMBOL_NS_GPL(intel_vsec_add_aux, INTEL_VSEC);
> > >  static int intel_vsec_add_dev(struct pci_dev *pdev, struct
> > > intel_vsec_header *header,
> > >                               struct intel_vsec_platform_info *info)
> > >  {
> > > -       struct intel_vsec_device *intel_vsec_dev;
> > > +       struct intel_vsec_device __free(kfree) *intel_vsec_dev = NULL;
> > >         struct resource *res, *tmp;
> > >         unsigned long quirks = info->quirks;
> > > -       int i;
> > > +       int ret, i;
> > >  
> > >         if (!intel_vsec_supported(header->id, info->caps))
> > >                 return -EINVAL;
> > > @@ -178,10 +179,8 @@ static int intel_vsec_add_dev(struct pci_dev *pdev,
> > > struct intel_vsec_header *he
> > >                 return -ENOMEM;
> > >  
> > >         res = kcalloc(header->num_entries, sizeof(*res), GFP_KERNEL);
> > > -       if (!res) {
> > > -               kfree(intel_vsec_dev);
> > > +       if (!res)
> > >                 return -ENOMEM;
> > > -       }
> > >  
> > >         if (quirks & VSEC_QUIRK_TABLE_SHIFT)
> > >                 header->offset >>= TABLE_OFFSET_SHIFT;
> > > @@ -208,8 +207,12 @@ static int intel_vsec_add_dev(struct pci_dev *pdev,
> > > struct intel_vsec_header *he
> > >         else
> > >                 intel_vsec_dev->ida = &intel_vsec_ida;
> > >  
> > > -       return intel_vsec_add_aux(pdev, NULL, intel_vsec_dev,
> > > -                                 intel_vsec_name(header->id));
> > > +       ret = intel_vsec_add_aux(pdev, NULL, intel_vsec_dev,
> > > +                                intel_vsec_name(header->id));
> > > +
> > > +       no_free_ptr(intel_vsec_dev);
> > > +
> > > +       return ret;
> > 
> > So if intel_vsec_add_aux() returned an error, intel_vsec_dev won't be 
> > freed because of the call call to no_free_ptr() before return. I that's 
> > not what you intended?
> 
> It will have been freed if intel_vsec_add_aux() fails. It's a little messy. That
> function creates the auxdev and assigns the release function which will free
> intel_vsec_dev when the device is removed. But there are failure points that
> will also invoke the release function. Because of this, for all the failure
> points in that function we free intel_vsec_dev so that it's state doesn't need
> to be questioned here. This happens explicitly if the failure is before
> auxiliary_device_init(), or through the release function invoked by
> auxiliary_device_uninit() if after.

Oh, that's really convoluted and no wonder I missed it completely. It 
might even be that using cleanup.h here isn't really worth it. I know 
I pushed you into that direction but I didn't realize all the complexity
at that point.

If you still want to keep using cleanup.h, it would perhaps be less 
dangerous if you change the code such that no_free_ptr() for
intel_vsec_dev and the resource (in 4/16, that's a similar case, isn't 
it?) are before the intel_vsec_add_aux() call (and I'd also add a comment 
to explain that freeing them is now responsability of 
intel_vsec_add_aux()). That way, we don't leave a trap into there where 
somebody happily adds another no_free_ptr() to the same group and it 
causes a mem leak.


-- 
 i.

Re: [PATCH V3 09/16] platform/x86/intel/pmc: Allow pmc_core_ssram_init to fail

[Ilpo Järvinen]

[-- Attachment #1: Type: text/plain, Size: 1336 bytes --]

On Thu, 12 Oct 2023, David E. Box wrote:

> On Thu, 2023-10-12 at 18:01 +0300, Ilpo Järvinen wrote:
> > On Wed, 11 Oct 2023, David E. Box wrote:
> > 
> > > Currently, if the PMC SSRAM initialization fails, no error is returned and
> > > the only indication is that a PMC device has not been created.  Instead,
> > > allow an error to be returned and handled directly by the caller.
> > 
> > You might have a good reason for it but why isn't the call into 
> > pmc_core_pmc_add() changed in this patch to take the error value into 
> > account?
> 
> Good catch. The return value of pmc_core_pmc_add() is first used in the next
> patch but should be used here.
> 
> > 
> > (I vaguely remember this was probably discussed in the context of some 
> > earlier patch touching this area that it was about the other code dealing 
> > with NULLs or something like that).

Okay but please also take into consideration what I tried to imply above:

Since you are doing what looks a major logic change in the next patch, it 
might be okay to _not use_ that return value until then if you e.g., need 
to add lots of rollback that isn't there already to the code that is going 
away anyway in the next patch. (After all, returning an error code from a 
function that was void previously isn't going to magically break the old
calling code).


-- 
 i.

Re: [PATCH V3 03/16] platform/x86/intel/vsec: Use cleanup.h

[Joe Perches]

On Fri, 2023-10-13 at 13:39 +0300, Ilpo Järvinen wrote:
> Hi,
> 
> I added checkpatch people, please check what looks a false positive below.

Yeah, thanks I guess.
The __free uses are very new.
I'll play around with adding it to $Attributes
and see what happens.


> On Thu, 12 Oct 2023, David E. Box wrote:
> > On Thu, 2023-10-12 at 13:25 +0800, kernel test robot wrote:
> > > kernel test robot noticed the following build warnings:
> > > # many are suggestions rather than must-fix
[]
> > > ERROR:SPACING: need consistent spacing around '*' (ctx:WxV)
> > > #31: FILE: drivers/platform/x86/intel/vsec.c:159:
> > > +       struct intel_vsec_device __free(kfree) *intel_vsec_dev = NULL;
> > 
> > These looks like false positives.
> 
> I agree. If I interpret the error message right checkpatch seems to think
> that's a multiplication which is not the case here.

Re: [PATCH V3 03/16] platform/x86/intel/vsec: Use cleanup.h

[David E. Box]

On Fri, 2023-10-13 at 13:54 +0300, Ilpo Järvinen wrote:
> On Thu, 12 Oct 2023, David E. Box wrote:
> 
> > On Thu, 2023-10-12 at 17:46 +0300, Ilpo Järvinen wrote:
> > > On Wed, 11 Oct 2023, David E. Box wrote:
> > > 
> > > > Use cleanup.h helpers to handle cleanup of resources in
> > > > intel_vsec_add_dev() after failures.
> > > > 
> > > > Signed-off-by: David E. Box <david.e.box@linux.intel.com>
> > > > ---
> > > > V3 - New patch.
> > > > 
> > > >  drivers/platform/x86/intel/vsec.c | 17 ++++++++++-------
> > > >  1 file changed, 10 insertions(+), 7 deletions(-)
> > > > 
> > > > diff --git a/drivers/platform/x86/intel/vsec.c
> > > > b/drivers/platform/x86/intel/vsec.c
> > > > index 15866b7d3117..f03ab89ab7c0 100644
> > > > --- a/drivers/platform/x86/intel/vsec.c
> > > > +++ b/drivers/platform/x86/intel/vsec.c
> > > > @@ -15,6 +15,7 @@
> > > >  
> > > >  #include <linux/auxiliary_bus.h>
> > > >  #include <linux/bits.h>
> > > > +#include <linux/cleanup.h>
> > > >  #include <linux/delay.h>
> > > >  #include <linux/kernel.h>
> > > >  #include <linux/idr.h>
> > > > @@ -155,10 +156,10 @@ EXPORT_SYMBOL_NS_GPL(intel_vsec_add_aux,
> > > > INTEL_VSEC);
> > > >  static int intel_vsec_add_dev(struct pci_dev *pdev, struct
> > > > intel_vsec_header *header,
> > > >                               struct intel_vsec_platform_info *info)
> > > >  {
> > > > -       struct intel_vsec_device *intel_vsec_dev;
> > > > +       struct intel_vsec_device __free(kfree) *intel_vsec_dev = NULL;
> > > >         struct resource *res, *tmp;
> > > >         unsigned long quirks = info->quirks;
> > > > -       int i;
> > > > +       int ret, i;
> > > >  
> > > >         if (!intel_vsec_supported(header->id, info->caps))
> > > >                 return -EINVAL;
> > > > @@ -178,10 +179,8 @@ static int intel_vsec_add_dev(struct pci_dev *pdev,
> > > > struct intel_vsec_header *he
> > > >                 return -ENOMEM;
> > > >  
> > > >         res = kcalloc(header->num_entries, sizeof(*res), GFP_KERNEL);
> > > > -       if (!res) {
> > > > -               kfree(intel_vsec_dev);
> > > > +       if (!res)
> > > >                 return -ENOMEM;
> > > > -       }
> > > >  
> > > >         if (quirks & VSEC_QUIRK_TABLE_SHIFT)
> > > >                 header->offset >>= TABLE_OFFSET_SHIFT;
> > > > @@ -208,8 +207,12 @@ static int intel_vsec_add_dev(struct pci_dev *pdev,
> > > > struct intel_vsec_header *he
> > > >         else
> > > >                 intel_vsec_dev->ida = &intel_vsec_ida;
> > > >  
> > > > -       return intel_vsec_add_aux(pdev, NULL, intel_vsec_dev,
> > > > -                                 intel_vsec_name(header->id));
> > > > +       ret = intel_vsec_add_aux(pdev, NULL, intel_vsec_dev,
> > > > +                                intel_vsec_name(header->id));
> > > > +
> > > > +       no_free_ptr(intel_vsec_dev);
> > > > +
> > > > +       return ret;
> > > 
> > > So if intel_vsec_add_aux() returned an error, intel_vsec_dev won't be 
> > > freed because of the call call to no_free_ptr() before return. I that's 
> > > not what you intended?
> > 
> > It will have been freed if intel_vsec_add_aux() fails. It's a little messy.
> > That
> > function creates the auxdev and assigns the release function which will free
> > intel_vsec_dev when the device is removed. But there are failure points that
> > will also invoke the release function. Because of this, for all the failure
> > points in that function we free intel_vsec_dev so that it's state doesn't
> > need
> > to be questioned here. This happens explicitly if the failure is before
> > auxiliary_device_init(), or through the release function invoked by
> > auxiliary_device_uninit() if after.
> 
> Oh, that's really convoluted and no wonder I missed it completely. It 
> might even be that using cleanup.h here isn't really worth it. I know 
> I pushed you into that direction but I didn't realize all the complexity
> at that point.
> 
> If you still want to keep using cleanup.h, it would perhaps be less 
> dangerous if you change the code such that no_free_ptr() for
> intel_vsec_dev and the resource (in 4/16, that's a similar case, isn't 
> it?)

yes

>  are before the intel_vsec_add_aux() call (and I'd also add a comment 
> to explain that freeing them is now responsability of 
> intel_vsec_add_aux()). That way, we don't leave a trap into there where 
> somebody happily adds another no_free_ptr() to the same group and it 
> causes a mem leak.

Sure. After the comment I'd just do this then still the value is still needed,

	ret = intel_vsec_add_aux(pdev, NULL, no_free_ptr(intel_vsec_dev),
                                 intel_vsec_name(header->id));

David

Re: [PATCH V3 03/16] platform/x86/intel/vsec: Use cleanup.h

[Ilpo Järvinen]

[-- Attachment #1: Type: text/plain, Size: 3668 bytes --]

On Fri, 13 Oct 2023, David E. Box wrote:

> On Fri, 2023-10-13 at 13:54 +0300, Ilpo Järvinen wrote:
> > On Thu, 12 Oct 2023, David E. Box wrote:
> > 
> > > On Thu, 2023-10-12 at 17:46 +0300, Ilpo Järvinen wrote:
> > > > On Wed, 11 Oct 2023, David E. Box wrote:
> > > > 
> > > > > Use cleanup.h helpers to handle cleanup of resources in
> > > > > intel_vsec_add_dev() after failures.
> > > > > 
> > > > > Signed-off-by: David E. Box <david.e.box@linux.intel.com>
> > > > > ---


> > > > > @@ -208,8 +207,12 @@ static int intel_vsec_add_dev(struct pci_dev *pdev,
> > > > > struct intel_vsec_header *he
> > > > >         else
> > > > >                 intel_vsec_dev->ida = &intel_vsec_ida;
> > > > >  
> > > > > -       return intel_vsec_add_aux(pdev, NULL, intel_vsec_dev,
> > > > > -                                 intel_vsec_name(header->id));
> > > > > +       ret = intel_vsec_add_aux(pdev, NULL, intel_vsec_dev,
> > > > > +                                intel_vsec_name(header->id));
> > > > > +
> > > > > +       no_free_ptr(intel_vsec_dev);
> > > > > +
> > > > > +       return ret;
> > > > 
> > > > So if intel_vsec_add_aux() returned an error, intel_vsec_dev won't be 
> > > > freed because of the call call to no_free_ptr() before return. I that's 
> > > > not what you intended?
> > > 
> > > It will have been freed if intel_vsec_add_aux() fails. It's a little messy.
> > > That
> > > function creates the auxdev and assigns the release function which will free
> > > intel_vsec_dev when the device is removed. But there are failure points that
> > > will also invoke the release function. Because of this, for all the failure
> > > points in that function we free intel_vsec_dev so that it's state doesn't
> > > need
> > > to be questioned here. This happens explicitly if the failure is before
> > > auxiliary_device_init(), or through the release function invoked by
> > > auxiliary_device_uninit() if after.
> > 
> > Oh, that's really convoluted and no wonder I missed it completely. It 
> > might even be that using cleanup.h here isn't really worth it. I know 
> > I pushed you into that direction but I didn't realize all the complexity
> > at that point.

...
> >  are before the intel_vsec_add_aux() call (and I'd also add a comment 
> > to explain that freeing them is now responsability of 
> > intel_vsec_add_aux()). That way, we don't leave a trap into there where 
> > somebody happily adds another no_free_ptr() to the same group and it 
> > causes a mem leak.
> 
> Sure. After the comment I'd just do this then still the value is still needed,
> 
> 	ret = intel_vsec_add_aux(pdev, NULL, no_free_ptr(intel_vsec_dev),
>                                  intel_vsec_name(header->id));

True, I realized later that the variable gets NULLed because of how 
no_free_ptr() works so no_free_ptr() has to be within the call itself, but 
that's actually much better than my initial suggestion!

So I think the best we can get out of this is along the lines of (with the 
subsequent change with res too):

	/* Pass the ownership of intel_vsec_dev and resource within it to intel_vsec_add_aux() */
	no_free_ptr(res);
	return intel_vsec_add_aux(pdev, info->parent, no_free_ptr(intel_vsec_dev), 
				  intel_vsec_name(header->id));

That seems the least trappiest and actually nicely documents who is 
responsible for what. To contrast the earlier, this feels very elegant,
the perceived complexity related to intel_vsec_add_aux() no longer feels 
tricky at all so we end up solving also that problem better than the 
original.

-- 
 i.

Re: [PATCH V3 03/16] platform/x86/intel/vsec: Use cleanup.h

[Joe Perches]

On Fri, 2023-10-13 at 11:14 -0700, Joe Perches wrote:
> On Fri, 2023-10-13 at 13:39 +0300, Ilpo Järvinen wrote:
> > Hi,
> > 
> > I added checkpatch people, please check what looks a false positive below.
> 
> Yeah, thanks I guess.
> The __free uses are very new.
> I'll play around with adding it to $Attributes
> and see what happens.
> 
> 
> > On Thu, 12 Oct 2023, David E. Box wrote:
> > > On Thu, 2023-10-12 at 13:25 +0800, kernel test robot wrote:
> > > > kernel test robot noticed the following build warnings:
> > > > # many are suggestions rather than must-fix
> []
> > > > ERROR:SPACING: need consistent spacing around '*' (ctx:WxV)
> > > > #31: FILE: drivers/platform/x86/intel/vsec.c:159:
> > > > +       struct intel_vsec_device __free(kfree) *intel_vsec_dev = NULL;
> > > .
> > > These looks like false positives.
> > 
> > I agree. If I interpret the error message right checkpatch seems to think
> > that's a multiplication which is not the case here.

So __free is an odd $Attribute as it takes an argument.
I've added it along with the other odd $Attribute __alloc_size
to another variable called $ArgAttribute and $Attribute.

Oddly, I don't understand why perl does not perform
the elimination using

	$foo =~ s/\b$ArgAttribute\b//g;

but does do the elimination using

	$foo =~ s/\b$ArgAttribute//g;

maybe something to do with the closing parenthesis in the match.

So now there is a separate substitution for this in a test.

Comments?

---
 scripts/checkpatch.pl | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 25fdb7fda1128..501383fa31c55 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -488,9 +488,14 @@ our $InitAttributeConst = qr{$InitAttributePrefix(?:initconst\b)};
 our $InitAttributeInit = qr{$InitAttributePrefix(?:init\b)};
 our $InitAttribute = qr{$InitAttributeData|$InitAttributeConst|$InitAttributeInit};
 
+our $ArgAttribute = qr{(?x:
+			__alloc_size\s*\(\s*\d+\s*(?:,\s*\d+\s*)?\)|
+			__free\s*\(\s*\w+\s*\)
+)};
+
 # Notes to $Attribute:
 # We need \b after 'init' otherwise 'initconst' will cause a false positive in a check
-our $Attribute	= qr{
+our $Attribute	= qr{(?x:
 			const|
 			volatile|
 			__percpu|
@@ -516,8 +521,8 @@ our $Attribute	= qr{
 			____cacheline_aligned_in_smp|
 			____cacheline_internodealigned_in_smp|
 			__weak|
-			__alloc_size\s*\(\s*\d+\s*(?:,\s*\d+\s*)?\)
-		  }x;
+			$ArgAttribute
+		  )};
 our $Modifier;
 our $Inline	= qr{inline|__always_inline|noinline|__inline|__inline__};
 our $Member	= qr{->$Ident|\.$Ident|\[[^]]*\]};
@@ -4091,6 +4096,9 @@ sub process {
 			# remove $Attribute/$Sparse uses to simplify comparisons
 			$sl =~ s/\b(?:$Attribute|$Sparse)\b//g;
 			$pl =~ s/\b(?:$Attribute|$Sparse)\b//g;
+			$sl =~ s/\b(?:$ArgAttribute)//g;
+			$pl =~ s/\b(?:$ArgAttribute)//g;
+
 			if (($pl =~ /^\+\s+$Declare\s*$Ident\s*[=,;:\[]/ ||
 			# function pointer declarations
 			     $pl =~ /^\+\s+$Declare\s*\(\s*\*\s*$Ident\s*\)\s*[=,;:\[\(]/ ||