Merge tag 'cxl-for-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl

Pull cxl updates from Dan Williams:
 "Compute Express Link (CXL) updates for this cycle.

  The highlight is new driver-core infrastructure and CXL subsystem
  changes for allowing lockdep to validate device_lock() usage. Thanks
  to PeterZ for setting me straight on the current capabilities of the
  lockdep API, and Greg acked it as well.

  On the CXL ACPI side this update adds support for CXL _OSC so that
  platform firmware knows that it is safe to still grant Linux native
  control of PCIe hotplug and error handling in the presence of CXL
  devices. A circular dependency problem was discovered between suspend
  and CXL memory for cases where the suspend image might be stored in
  CXL memory where that image also contains the PCI register state to
  restore to re-enable the device. Disable suspend for now until an
  architecture is defined to clarify that conflict.

  Lastly a collection of reworks, fixes, and cleanups to the CXL
  subsystem where support for snooping mailbox commands and properly
  handling the "mem_enable" flow are the highlights.

  Summary:

   - Add driver-core infrastructure for lockdep validation of
     device_lock(), and fixup a deadlock report that was previously
     hidden behind the 'lockdep no validate' policy.

   - Add CXL _OSC support for claiming native control of CXL hotplug and
     error handling.

   - Disable suspend in the presence of CXL memory unless and until a
     protocol is identified for restoring PCI device context from memory
     hosted on CXL PCI devices.

   - Add support for snooping CXL mailbox commands to protect against
     inopportune changes, like set-partition with the 'immediate' flag
     set.

   - Rework how the driver detects legacy CXL 1.1 configurations (CXL
     DVSEC / 'mem_enable') before enabling new CXL 2.0 decode
     configurations (CXL HDM Capability).

   - Miscellaneous cleanups and fixes from -next exposure"

* tag 'cxl-for-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl: (47 commits)
  cxl/port: Enable HDM Capability after validating DVSEC Ranges
  cxl/port: Reuse 'struct cxl_hdm' context for hdm init
  cxl/port: Move endpoint HDM Decoder Capability init to port driver
  cxl/pci: Drop @info argument to cxl_hdm_decode_init()
  cxl/mem: Merge cxl_dvsec_ranges() and cxl_hdm_decode_init()
  cxl/mem: Skip range enumeration if mem_enable clear
  cxl/mem: Consolidate CXL DVSEC Range enumeration in the core
  cxl/pci: Move cxl_await_media_ready() to the core
  cxl/mem: Validate port connectivity before dvsec ranges
  cxl/mem: Fix cxl_mem_probe() error exit
  cxl/pci: Drop wait_for_valid() from cxl_await_media_ready()
  cxl/pci: Consolidate wait_for_media() and wait_for_media_ready()
  cxl/mem: Drop mem_enabled check from wait_for_media()
  nvdimm: Fix firmware activation deadlock scenarios
  device-core: Kill the lockdep_mutex
  nvdimm: Drop nd_device_lock()
  ACPI: NFIT: Drop nfit_device_lock()
  nvdimm: Replace lockdep_mutex with local lock classes
  cxl: Drop cxl_device_lock()
  cxl/acpi: Add root device lockdep validation
  ...

6 files changed, 115 insertions, 16 deletions

diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 772590e2eddb..0dc1ea0b52f5 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -585,14 +585,22 @@ int unregister_acpi_bus_type(struct acpi_bus_type *);
 int acpi_bind_one(struct device *dev, struct acpi_device *adev);
 int acpi_unbind_one(struct device *dev);
 
+enum acpi_bridge_type {
+	ACPI_BRIDGE_TYPE_PCIE = 1,
+	ACPI_BRIDGE_TYPE_CXL,
+};
+
 struct acpi_pci_root {
 	struct acpi_device * device;
 	struct pci_bus *bus;
 	u16 segment;
+	int bridge_type;
 	struct resource secondary;	/* downstream bus range */
 
-	u32 osc_support_set;	/* _OSC state of support bits */
-	u32 osc_control_set;	/* _OSC state of control bits */
+	u32 osc_support_set;		/* _OSC state of support bits */
+	u32 osc_control_set;		/* _OSC state of control bits */
+	u32 osc_ext_support_set;	/* _OSC state of extended support bits */
+	u32 osc_ext_control_set;	/* _OSC state of extended control bits */
 	phys_addr_t mcfg_addr;
 };
 
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 03465db16b68..f3fdfd784a6c 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -550,10 +550,16 @@ struct acpi_osc_context {
 
 acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context);
 
-/* Indexes into _OSC Capabilities Buffer (DWORDs 2 & 3 are device-specific) */
+/* Number of _OSC capability DWORDS depends on bridge type */
+#define OSC_PCI_CAPABILITY_DWORDS		3
+#define OSC_CXL_CAPABILITY_DWORDS		5
+
+/* Indexes into _OSC Capabilities Buffer (DWORDs 2 to 5 are device-specific) */
 #define OSC_QUERY_DWORD				0	/* DWORD 1 */
 #define OSC_SUPPORT_DWORD			1	/* DWORD 2 */
 #define OSC_CONTROL_DWORD			2	/* DWORD 3 */
+#define OSC_EXT_SUPPORT_DWORD			3	/* DWORD 4 */
+#define OSC_EXT_CONTROL_DWORD			4	/* DWORD 5 */
 
 /* _OSC Capabilities DWORD 1: Query/Control and Error Returns (generic) */
 #define OSC_QUERY_ENABLE			0x00000001  /* input */
@@ -610,6 +616,29 @@ extern u32 osc_sb_native_usb4_control;
 #define OSC_PCI_EXPRESS_LTR_CONTROL		0x00000020
 #define OSC_PCI_EXPRESS_DPC_CONTROL		0x00000080
 
+/* CXL _OSC: Capabilities DWORD 4: Support Field */
+#define OSC_CXL_1_1_PORT_REG_ACCESS_SUPPORT	0x00000001
+#define OSC_CXL_2_0_PORT_DEV_REG_ACCESS_SUPPORT	0x00000002
+#define OSC_CXL_PROTOCOL_ERR_REPORTING_SUPPORT	0x00000004
+#define OSC_CXL_NATIVE_HP_SUPPORT		0x00000008
+
+/* CXL _OSC: Capabilities DWORD 5: Control Field */
+#define OSC_CXL_ERROR_REPORTING_CONTROL		0x00000001
+
+static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context)
+{
+	u32 *ret = context->ret.pointer;
+
+	return ret[OSC_CONTROL_DWORD];
+}
+
+static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context)
+{
+	u32 *ret = context->ret.pointer;
+
+	return ret[OSC_EXT_CONTROL_DWORD];
+}
+
 #define ACPI_GSB_ACCESS_ATTRIB_QUICK		0x00000002
 #define ACPI_GSB_ACCESS_ATTRIB_SEND_RCV         0x00000004
 #define ACPI_GSB_ACCESS_ATTRIB_BYTE		0x00000006
@@ -1006,6 +1035,17 @@ static inline int acpi_register_wakeup_handler(int wake_irq,
 static inline void acpi_unregister_wakeup_handler(
 	bool (*wakeup)(void *context), void *context) { }
 
+struct acpi_osc_context;
+static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context)
+{
+	return 0;
+}
+
+static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context)
+{
+	return 0;
+}
+
 #endif	/* !CONFIG_ACPI */
 
 #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
diff --git a/include/linux/device.h b/include/linux/device.h
index 93459724dcde..073f1b0126ac 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -400,8 +400,6 @@ struct dev_msi_info {
  * 		This identifies the device type and carries type-specific
  * 		information.
  * @mutex:	Mutex to synchronize calls to its driver.
- * @lockdep_mutex: An optional debug lock that a subsystem can use as a
- * 		peer lock to gain localized lockdep coverage of the device_lock.
  * @bus:	Type of bus device is on.
  * @driver:	Which driver has allocated this
  * @platform_data: Platform data specific to the device.
@@ -499,9 +497,6 @@ struct device {
 					   core doesn't touch it */
 	void		*driver_data;	/* Driver data, set and get with
 					   dev_set_drvdata/dev_get_drvdata */
-#ifdef CONFIG_PROVE_LOCKING
-	struct mutex		lockdep_mutex;
-#endif
 	struct mutex		mutex;	/* mutex to synchronize calls to
 					 * its driver.
 					 */
@@ -850,6 +845,49 @@ static inline bool device_supports_offline(struct device *dev)
 	return dev->bus && dev->bus->offline && dev->bus->online;
 }
 
+#define __device_lock_set_class(dev, name, key)                        \
+do {                                                                   \
+	struct device *__d2 __maybe_unused = dev;                      \
+	lock_set_class(&__d2->mutex.dep_map, name, key, 0, _THIS_IP_); \
+} while (0)
+
+/**
+ * device_lock_set_class - Specify a temporary lock class while a device
+ *			   is attached to a driver
+ * @dev: device to modify
+ * @key: lock class key data
+ *
+ * This must be called with the device_lock() already held, for example
+ * from driver ->probe(). Take care to only override the default
+ * lockdep_no_validate class.
+ */
+#ifdef CONFIG_LOCKDEP
+#define device_lock_set_class(dev, key)                                    \
+do {                                                                       \
+	struct device *__d = dev;                                          \
+	dev_WARN_ONCE(__d, !lockdep_match_class(&__d->mutex,               \
+						&__lockdep_no_validate__), \
+		 "overriding existing custom lock class\n");               \
+	__device_lock_set_class(__d, #key, key);                           \
+} while (0)
+#else
+#define device_lock_set_class(dev, key) __device_lock_set_class(dev, #key, key)
+#endif
+
+/**
+ * device_lock_reset_class - Return a device to the default lockdep novalidate state
+ * @dev: device to modify
+ *
+ * This must be called with the device_lock() already held, for example
+ * from driver ->remove().
+ */
+#define device_lock_reset_class(dev) \
+do { \
+	struct device *__d __maybe_unused = dev;                       \
+	lock_set_novalidate_class(&__d->mutex.dep_map, "&dev->mutex",  \
+				  _THIS_IP_);                          \
+} while (0)
+
 void lock_device_hotplug(void);
 void unlock_device_hotplug(void);
 int lock_device_hotplug_sysfs(void);
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 37951c17908e..b6829b970093 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -286,6 +286,9 @@ extern void lock_set_class(struct lockdep_map *lock, const char *name,
 			   struct lock_class_key *key, unsigned int subclass,
 			   unsigned long ip);
 
+#define lock_set_novalidate_class(l, n, i) \
+	lock_set_class(l, n, &__lockdep_no_validate__, 0, i)
+
 static inline void lock_set_subclass(struct lockdep_map *lock,
 		unsigned int subclass, unsigned long ip)
 {
@@ -353,7 +356,8 @@ static inline void lockdep_set_selftest_task(struct task_struct *task)
 # define lock_acquire(l, s, t, r, c, n, i)	do { } while (0)
 # define lock_release(l, i)			do { } while (0)
 # define lock_downgrade(l, i)			do { } while (0)
-# define lock_set_class(l, n, k, s, i)		do { } while (0)
+# define lock_set_class(l, n, key, s, i)	do { (void)(key); } while (0)
+# define lock_set_novalidate_class(l, n, i)	do { } while (0)
 # define lock_set_subclass(l, s, i)		do { } while (0)
 # define lockdep_init()				do { } while (0)
 # define lockdep_init_map_type(lock, name, key, sub, inner, outer, type) \
diff --git a/include/linux/pm.h b/include/linux/pm.h
index ffe941958501..70ec69d8bafd 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -36,6 +36,15 @@ static inline void pm_vt_switch_unregister(struct device *dev)
 }
 #endif /* CONFIG_VT_CONSOLE_SLEEP */
 
+#ifdef CONFIG_CXL_SUSPEND
+bool cxl_mem_active(void);
+#else
+static inline bool cxl_mem_active(void)
+{
+	return false;
+}
+#endif
+
 /*
  * Device power management
  */
diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h
index 8d206f27bb6d..c71021a2a9ed 100644
--- a/include/uapi/linux/cxl_mem.h
+++ b/include/uapi/linux/cxl_mem.h
@@ -68,8 +68,8 @@ static const struct {
  * struct cxl_command_info - Command information returned from a query.
  * @id: ID number for the command.
  * @flags: Flags that specify command behavior.
- * @size_in: Expected input size, or -1 if variable length.
- * @size_out: Expected output size, or -1 if variable length.
+ * @size_in: Expected input size, or ~0 if variable length.
+ * @size_out: Expected output size, or ~0 if variable length.
  *
  * Represents a single command that is supported by both the driver and the
  * hardware. This is returned as part of an array from the query ioctl. The
@@ -78,7 +78,7 @@ static const struct {
  *
  *  - @id = 10
  *  - @flags = 0
- *  - @size_in = -1
+ *  - @size_in = ~0
  *  - @size_out = 0
  *
  * See struct cxl_mem_query_commands.
@@ -89,8 +89,8 @@ struct cxl_command_info {
 	__u32 flags;
 #define CXL_MEM_COMMAND_FLAG_MASK GENMASK(0, 0)
 
-	__s32 size_in;
-	__s32 size_out;
+	__u32 size_in;
+	__u32 size_out;
 };
 
 /**
@@ -169,13 +169,13 @@ struct cxl_send_command {
 	__u32 retval;
 
 	struct {
-		__s32 size;
+		__u32 size;
 		__u32 rsvd;
 		__u64 payload;
 	} in;
 
 	struct {
-		__s32 size;
+		__u32 size;
 		__u32 rsvd;
 		__u64 payload;
 	} out;