From b962f5a446d8cf4f313a2cef728e7e71b2f20811 Mon Sep 17 00:00:00 2001
From: Stewart Smith <stewart@linux.vnet.ibm.com>
Date: Thu, 12 Feb 2015 16:25:27 +1100
Subject: powerpc/powernv: only register log if OPAL supports doing so

Correct use of REGISTER/UNREGISTER is to check if the token exists
before calling. If we don't we get a "OPAL: Called with bad token 101 !"
error, which is harmless but may be alarming to some.

Signed-off-by: Stewart Smith <stewart@linux.vnet.ibm.com>
Acked-by: Vasant Hegde <hegdevasant@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/platforms/powernv/opal.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 18fd4e71c9c1..45f0d9aa3733 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -665,6 +665,9 @@ static void __init opal_dump_region_init(void)
 	uint64_t size;
 	int rc;
 
+	if (!opal_check_token(OPAL_REGISTER_DUMP_REGION))
+		return;
+
 	/* Register kernel log buffer */
 	addr = log_buf_addr_get();
 	if (addr == NULL)
@@ -823,7 +826,8 @@ void opal_shutdown(void)
 	}
 
 	/* Unregister memory dump region */
-	opal_unregister_dump_region(OPAL_DUMP_REGION_LOG_BUF);
+	if (opal_check_token(OPAL_UNREGISTER_DUMP_REGION))
+		opal_unregister_dump_region(OPAL_DUMP_REGION_LOG_BUF);
 }
 
 /* Export this so that test modules can use it */
-- 
cgit v1.2.3


From fc81de63104e7603e6695225c2573f27aaeb4a28 Mon Sep 17 00:00:00 2001
From: Stewart Smith <stewart@linux.vnet.ibm.com>
Date: Thu, 12 Feb 2015 16:25:28 +1100
Subject: powerpc/powernv: only call OPAL_ELOG_RESEND if firmware supports it

Otherwise firmware complains: "OPAL: Called with bad token 74 !"
as not all OPAL systems have the ability to resend error logs.

Signed-off-by: Stewart Smith <stewart@linux.vnet.ibm.com>
Acked-by: Vasant Hegde <hegdevasant@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/platforms/powernv/opal-elog.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index 518fe95dbf24..38ce757e5e2a 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -313,7 +313,8 @@ int __init opal_elog_init(void)
 	}
 
 	/* We are now ready to pull error logs from opal. */
-	opal_resend_pending_logs();
+	if (opal_check_token(OPAL_ELOG_RESEND))
+		opal_resend_pending_logs();
 
 	return 0;
 }
-- 
cgit v1.2.3


From 7e73a3b7f34240871fa5556d952e801178970741 Mon Sep 17 00:00:00 2001
From: Stewart Smith <stewart@linux.vnet.ibm.com>
Date: Thu, 12 Feb 2015 16:25:29 +1100
Subject: powerpc/powernv: only call OPAL_RESEND_DUMP if firmware supports it

Not all OPAL platforms support resending system dumps, so check
that current firmware supports it first. Otherwise we get firmware
complaining:
"OPAL: Called with bad token 91 !"

Signed-off-by: Stewart Smith <stewart@linux.vnet.ibm.com>
Acked-by: Vasant Hegde <hegdevasant@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/platforms/powernv/opal-dump.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c
index 23260f7dfa7a..5aa9c1ce4de3 100644
--- a/arch/powerpc/platforms/powernv/opal-dump.c
+++ b/arch/powerpc/platforms/powernv/opal-dump.c
@@ -452,5 +452,6 @@ void __init opal_platform_dump_init(void)
 		return;
 	}
 
-	opal_dump_resend_notification();
+	if (opal_check_token(OPAL_DUMP_RESEND))
+		opal_dump_resend_notification();
 }
-- 
cgit v1.2.3


From d7cf83fcaf1b1668201eae4cdd6e6fe7a2448654 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Tue, 17 Feb 2015 20:01:54 +1100
Subject: powerpc/powernv: Move opal-api.h closer to the Skiboot version

This commit gets opal-api.h to mostly match the version in Skiboot as of
commit ea7d806ab0ba.

The exceptions are things which are not (currently) used in Linux.

Most of this is just whitespace and a few things moving around. I think
the diff is readable.

Also OpalMessageType became opal_msg_type, requiring a change in the
Linux code.

Finally Skiboot and Linux disagree on CAPI vs CXL, because CAPI means
something else in Linux. To handle that we just point the Linux wrapper,
which is named "cxl" to the OPAL token OPAL_PCI_SET_PHB_CAPI_MODE.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Reviewed-by: Stewart Smith <stewart@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/opal-api.h            | 158 ++++++++++++++-----------
 arch/powerpc/include/asm/opal.h                |   2 +-
 arch/powerpc/platforms/powernv/opal-wrappers.S |   2 +-
 arch/powerpc/platforms/powernv/opal.c          |   2 +-
 4 files changed, 90 insertions(+), 74 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h
index a90176a428ee..2984f486f3ba 100644
--- a/arch/powerpc/include/asm/opal-api.h
+++ b/arch/powerpc/include/asm/opal-api.h
@@ -1,7 +1,7 @@
 /*
- * PowerNV OPAL definitions.
+ * OPAL API definitions.
  *
- * Copyright 2011 IBM Corp.
+ * Copyright 2011-2015 IBM Corp.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -15,7 +15,7 @@
 /****** OPAL APIs ******/
 
 /* Return codes */
-#define OPAL_SUCCESS 		0
+#define OPAL_SUCCESS		0
 #define OPAL_PARAMETER		-1
 #define OPAL_BUSY		-2
 #define OPAL_PARTIAL		-3
@@ -31,6 +31,7 @@
 #define OPAL_HARDWARE_FROZEN	-13
 #define OPAL_WRONG_STATE	-14
 #define OPAL_ASYNC_COMPLETION	-15
+#define OPAL_EMPTY		-16
 #define OPAL_I2C_TIMEOUT	-17
 #define OPAL_I2C_INVALID_CMD	-18
 #define OPAL_I2C_LBUS_PARITY	-19
@@ -41,7 +42,8 @@
 #define OPAL_I2C_STOP_ERR	-24
 
 /* API Tokens (in r0) */
-#define OPAL_INVALID_CALL			-1
+#define OPAL_INVALID_CALL		       -1
+#define OPAL_TEST				0
 #define OPAL_CONSOLE_WRITE			1
 #define OPAL_CONSOLE_READ			2
 #define OPAL_RTC_READ				3
@@ -84,7 +86,7 @@
 #define OPAL_GET_MSI_64				40
 #define OPAL_START_CPU				41
 #define OPAL_QUERY_CPU_STATUS			42
-#define OPAL_WRITE_OPPANEL			43
+#define OPAL_WRITE_OPPANEL			43 /* unimplemented */
 #define OPAL_PCI_MAP_PE_DMA_WINDOW		44
 #define OPAL_PCI_MAP_PE_DMA_WINDOW_REAL		45
 #define OPAL_PCI_RESET				49
@@ -130,8 +132,10 @@
 #define OPAL_GET_PARAM				89
 #define OPAL_SET_PARAM				90
 #define OPAL_DUMP_RESEND			91
-#define OPAL_PCI_SET_PHB_CXL_MODE		93
+#define OPAL_ELOG_SEND				92	/* Deprecated */
+#define OPAL_PCI_SET_PHB_CAPI_MODE		93
 #define OPAL_DUMP_INFO2				94
+#define OPAL_WRITE_OPPANEL_ASYNC		95
 #define OPAL_PCI_ERR_INJECT			96
 #define OPAL_PCI_EEH_FREEZE_SET			97
 #define OPAL_HANDLE_HMI				98
@@ -141,19 +145,22 @@
 #define OPAL_UNREGISTER_DUMP_REGION		102
 #define OPAL_WRITE_TPO				103
 #define OPAL_READ_TPO				104
+#define OPAL_GET_DPO_STATUS			105
+#define OPAL_OLD_I2C_REQUEST			106	/* Deprecated */
 #define OPAL_IPMI_SEND				107
 #define OPAL_IPMI_RECV				108
 #define OPAL_I2C_REQUEST			109
+#define OPAL_LAST				109
 
 /* Device tree flags */
 
 /* Flags set in power-mgmt nodes in device tree if
  * respective idle states are supported in the platform.
  */
-#define OPAL_PM_NAP_ENABLED	0x00010000
-#define OPAL_PM_SLEEP_ENABLED	0x00020000
-#define OPAL_PM_WINKLE_ENABLED	0x00040000
-#define OPAL_PM_SLEEP_ENABLED_ER1	0x00080000
+#define OPAL_PM_NAP_ENABLED		0x00010000
+#define OPAL_PM_SLEEP_ENABLED		0x00020000
+#define OPAL_PM_WINKLE_ENABLED		0x00040000
+#define OPAL_PM_SLEEP_ENABLED_ER1	0x00080000 /* with workaround */
 
 #ifndef __ASSEMBLY__
 
@@ -242,7 +249,7 @@ enum OpalShpcLinkState {
 enum OpalMmioWindowType {
 	OPAL_M32_WINDOW_TYPE = 1,
 	OPAL_M64_WINDOW_TYPE = 2,
-	OPAL_IO_WINDOW_TYPE = 3
+	OPAL_IO_WINDOW_TYPE  = 3
 };
 
 enum OpalShpcSlotState {
@@ -251,35 +258,24 @@ enum OpalShpcSlotState {
 };
 
 enum OpalExceptionHandler {
-	OPAL_MACHINE_CHECK_HANDLER = 1,
+	OPAL_MACHINE_CHECK_HANDLER	    = 1,
 	OPAL_HYPERVISOR_MAINTENANCE_HANDLER = 2,
-	OPAL_SOFTPATCH_HANDLER = 3
+	OPAL_SOFTPATCH_HANDLER		    = 3
 };
 
 enum OpalPendingState {
-	OPAL_EVENT_OPAL_INTERNAL	= 0x1,
-	OPAL_EVENT_NVRAM		= 0x2,
-	OPAL_EVENT_RTC			= 0x4,
-	OPAL_EVENT_CONSOLE_OUTPUT	= 0x8,
-	OPAL_EVENT_CONSOLE_INPUT	= 0x10,
-	OPAL_EVENT_ERROR_LOG_AVAIL	= 0x20,
-	OPAL_EVENT_ERROR_LOG		= 0x40,
-	OPAL_EVENT_EPOW			= 0x80,
-	OPAL_EVENT_LED_STATUS		= 0x100,
-	OPAL_EVENT_PCI_ERROR		= 0x200,
-	OPAL_EVENT_DUMP_AVAIL		= 0x400,
-	OPAL_EVENT_MSG_PENDING		= 0x800,
-};
-
-enum OpalMessageType {
-	OPAL_MSG_ASYNC_COMP = 0,	/* params[0] = token, params[1] = rc,
-					 * additional params function-specific
-					 */
-	OPAL_MSG_MEM_ERR,
-	OPAL_MSG_EPOW,
-	OPAL_MSG_SHUTDOWN,		/* params[0] = 1 reboot, 0 shutdown */
-	OPAL_MSG_HMI_EVT,
-	OPAL_MSG_TYPE_MAX,
+	OPAL_EVENT_OPAL_INTERNAL   = 0x1,
+	OPAL_EVENT_NVRAM	   = 0x2,
+	OPAL_EVENT_RTC		   = 0x4,
+	OPAL_EVENT_CONSOLE_OUTPUT  = 0x8,
+	OPAL_EVENT_CONSOLE_INPUT   = 0x10,
+	OPAL_EVENT_ERROR_LOG_AVAIL = 0x20,
+	OPAL_EVENT_ERROR_LOG	   = 0x40,
+	OPAL_EVENT_EPOW		   = 0x80,
+	OPAL_EVENT_LED_STATUS	   = 0x100,
+	OPAL_EVENT_PCI_ERROR	   = 0x200,
+	OPAL_EVENT_DUMP_AVAIL	   = 0x400,
+	OPAL_EVENT_MSG_PENDING	   = 0x800,
 };
 
 enum OpalThreadStatus {
@@ -323,7 +319,7 @@ enum OpalMveEnableAction {
 	OPAL_ENABLE_MVE = 1
 };
 
-enum OpalM64EnableAction {
+enum OpalM64Action {
 	OPAL_DISABLE_M64 = 0,
 	OPAL_ENABLE_M64_SPLIT = 1,
 	OPAL_ENABLE_M64_NON_SPLIT = 2
@@ -339,12 +335,17 @@ enum OpalPciResetScope {
 };
 
 enum OpalPciReinitScope {
+	/*
+	 * Note: we chose values that do not overlap
+	 * OpalPciResetScope as OPAL v2 used the same
+	 * enum for both
+	 */
 	OPAL_REINIT_PCI_DEV = 1000
 };
 
 enum OpalPciResetState {
 	OPAL_DEASSERT_RESET = 0,
-	OPAL_ASSERT_RESET = 1
+	OPAL_ASSERT_RESET   = 1
 };
 
 enum OpalPciMaskAction {
@@ -381,11 +382,16 @@ enum OpalLPCAddressType {
 	OPAL_LPC_FW	= 2,
 };
 
-/* System parameter permission */
-enum OpalSysparamPerm {
-	OPAL_SYSPARAM_READ      = 0x1,
-	OPAL_SYSPARAM_WRITE     = 0x2,
-	OPAL_SYSPARAM_RW        = (OPAL_SYSPARAM_READ | OPAL_SYSPARAM_WRITE),
+enum opal_msg_type {
+	OPAL_MSG_ASYNC_COMP = 0,	/* params[0] = token, params[1] = rc,
+					 * additional params function-specific
+					 */
+	OPAL_MSG_MEM_ERR,
+	OPAL_MSG_EPOW,
+	OPAL_MSG_SHUTDOWN,		/* params[0] = 1 reboot, 0 shutdown */
+	OPAL_MSG_HMI_EVT,
+	OPAL_MSG_DPO,
+	OPAL_MSG_TYPE_MAX,
 };
 
 struct opal_msg {
@@ -394,15 +400,22 @@ struct opal_msg {
 	__be64 params[8];
 };
 
+/* System parameter permission */
+enum OpalSysparamPerm {
+	OPAL_SYSPARAM_READ  = 0x1,
+	OPAL_SYSPARAM_WRITE = 0x2,
+	OPAL_SYSPARAM_RW    = (OPAL_SYSPARAM_READ | OPAL_SYSPARAM_WRITE),
+};
+
 enum {
 	OPAL_IPMI_MSG_FORMAT_VERSION_1 = 1,
 };
 
 struct opal_ipmi_msg {
-	uint8_t		version;
-	uint8_t		netfn;
-	uint8_t		cmd;
-	uint8_t		data[];
+	uint8_t version;
+	uint8_t netfn;
+	uint8_t cmd;
+	uint8_t data[];
 };
 
 /* FSP memory errors handling */
@@ -413,7 +426,6 @@ enum OpalMemErr_Version {
 enum OpalMemErrType {
 	OPAL_MEM_ERR_TYPE_RESILIENCE	= 0,
 	OPAL_MEM_ERR_TYPE_DYN_DALLOC,
-	OPAL_MEM_ERR_TYPE_SCRUB,
 };
 
 /* Memory Reilience error type */
@@ -442,17 +454,17 @@ struct OpalMemoryErrorData {
 	union {
 		/* Memory Resilience corrected/uncorrected error info */
 		struct {
-			enum OpalMemErr_ResilErrType resil_err_type:8;
-			uint8_t		reserved_1[7];
-			__be64		physical_address_start;
-			__be64		physical_address_end;
+			enum OpalMemErr_ResilErrType	resil_err_type:8;
+			uint8_t				reserved_1[7];
+			__be64				physical_address_start;
+			__be64				physical_address_end;
 		} resilience;
 		/* Dynamic memory deallocation error info */
 		struct {
-			enum OpalMemErr_DynErrType dyn_err_type:8;
-			uint8_t		reserved_1[7];
-			__be64		physical_address_start;
-			__be64		physical_address_end;
+			enum OpalMemErr_DynErrType	dyn_err_type:8;
+			uint8_t				reserved_1[7];
+			__be64				physical_address_start;
+			__be64				physical_address_end;
 		} dyn_dealloc;
 	} u;
 };
@@ -487,6 +499,7 @@ enum OpalHMI_ErrType {
 	OpalHMI_ERROR_SCOM_FIR,
 	OpalHMI_ERROR_DEBUG_TRIG_FIR,
 	OpalHMI_ERROR_HYP_RESOURCE,
+	OpalHMI_ERROR_CAPP_RECOVERY,
 };
 
 struct OpalHMIEvent {
@@ -539,13 +552,13 @@ struct OpalIoP7IOCErrorData {
 			__be64 biLdcp2;		/* 3C0110, 3C0128 */
 			__be64 biFenceStatus;	/* 3C0130, 3C0130 */
 
-			    u8 biDownbound;	/* BI Downbound or Upbound */
+			uint8_t biDownbound;	/* BI Downbound or Upbound */
 		}bi;
 		struct OpalIoP7IOCCiErrorData {
 			__be64 ciPortStatus;	/* 3Dn008 */
 			__be64 ciPortLdcp;	/* 3Dn010 */
 
-			    u8 ciPort;		/* Index of CI port: 0/1 */
+			uint8_t ciPort;		/* Index of CI port: 0/1 */
 		}ci;
 	};
 };
@@ -568,14 +581,6 @@ enum {
 	OPAL_PHB3_NUM_PEST_REGS = 256
 };
 
-/* CAPI modes for PHB */
-enum {
-	OPAL_PHB_CAPI_MODE_PCIE         = 0,
-	OPAL_PHB_CAPI_MODE_CAPI         = 1,
-	OPAL_PHB_CAPI_MODE_SNOOP_OFF    = 2,
-	OPAL_PHB_CAPI_MODE_SNOOP_ON     = 3,
-};
-
 struct OpalIoPhbErrorCommon {
 	__be32 version;
 	__be32 ioType;
@@ -674,11 +679,10 @@ struct OpalIoPhb3ErrorData {
 	__be64 errorClass;
 	__be64 correlator;
 
+	/* PHB3 MMIO Error Regs */
 	__be64 nFir;			/* 000 */
 	__be64 nFirMask;		/* 003 */
 	__be64 nFirWOF;		/* 008 */
-
-	/* PHB3 MMIO Error Regs */
 	__be64 phbPlssr;		/* 120 */
 	__be64 phbCsr;		/* 110 */
 	__be64 lemFir;		/* C00 */
@@ -710,8 +714,8 @@ enum {
 };
 
 typedef struct oppanel_line {
-	const char * 	line;
-	uint64_t 	line_len;
+	__be64 line;
+	__be64 line_len;
 } oppanel_line_t;
 
 /*
@@ -726,7 +730,11 @@ struct opal_sg_entry {
 	__be64 length;
 };
 
-/* SG list */
+/*
+ * Candiate image SG list.
+ *
+ * length = VER | length
+ */
 struct opal_sg_list {
 	__be64 length;
 	__be64 next;
@@ -740,6 +748,14 @@ struct opal_sg_list {
 #define OPAL_DUMP_REGION_LOG_BUF		0x80
 #define OPAL_DUMP_REGION_HOST_END		0xFF
 
+/* CAPI modes for PHB */
+enum {
+	OPAL_PHB_CAPI_MODE_PCIE		= 0,
+	OPAL_PHB_CAPI_MODE_CAPI		= 1,
+	OPAL_PHB_CAPI_MODE_SNOOP_OFF    = 2,
+	OPAL_PHB_CAPI_MODE_SNOOP_ON	= 3,
+};
+
 /* OPAL I2C request */
 struct opal_i2c_request {
 	uint8_t	type;
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 65c89dd2f604..0ef0fd660ac6 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -208,7 +208,7 @@ extern void hvc_opal_init_early(void);
 extern int opal_notifier_register(struct notifier_block *nb);
 extern int opal_notifier_unregister(struct notifier_block *nb);
 
-extern int opal_message_notifier_register(enum OpalMessageType msg_type,
+extern int opal_message_notifier_register(enum opal_msg_type msg_type,
 						struct notifier_block *nb);
 extern void opal_notifier_enable(void);
 extern void opal_notifier_disable(void);
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 0509bca5e830..b23fe7c4bf12 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -286,7 +286,7 @@ OPAL_CALL(opal_handle_hmi,			OPAL_HANDLE_HMI);
 OPAL_CALL(opal_slw_set_reg,			OPAL_SLW_SET_REG);
 OPAL_CALL(opal_register_dump_region,		OPAL_REGISTER_DUMP_REGION);
 OPAL_CALL(opal_unregister_dump_region,		OPAL_UNREGISTER_DUMP_REGION);
-OPAL_CALL(opal_pci_set_phb_cxl_mode,		OPAL_PCI_SET_PHB_CXL_MODE);
+OPAL_CALL(opal_pci_set_phb_cxl_mode,		OPAL_PCI_SET_PHB_CAPI_MODE);
 OPAL_CALL(opal_tpo_write,			OPAL_WRITE_TPO);
 OPAL_CALL(opal_tpo_read,			OPAL_READ_TPO);
 OPAL_CALL(opal_ipmi_send,			OPAL_IPMI_SEND);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 45f0d9aa3733..142a08a61bd1 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -302,7 +302,7 @@ void opal_notifier_disable(void)
  * Opal message notifier based on message type. Allow subscribers to get
  * notified for specific messgae type.
  */
-int opal_message_notifier_register(enum OpalMessageType msg_type,
+int opal_message_notifier_register(enum opal_msg_type msg_type,
 					struct notifier_block *nb)
 {
 	if (!nb) {
-- 
cgit v1.2.3


From 01f3bfb7804ae20aaf66884cf537f7dc2cdc1671 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Mon, 16 Feb 2015 14:45:39 +1100
Subject: powerpc/powernv: Shorten EEH function names

The patch shortens names of EEH functions in powernv-eeh.c and no
logic change introduced by this patch.

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/eeh-powernv.c | 104 +++++++++++++--------------
 1 file changed, 52 insertions(+), 52 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index e261869adc86..f562dd1a99cc 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -39,11 +39,11 @@
 #include "pci.h"
 
 /**
- * powernv_eeh_init - EEH platform dependent initialization
+ * pnv_eeh_init - EEH platform dependent initialization
  *
  * EEH platform dependent initialization on powernv
  */
-static int powernv_eeh_init(void)
+static int pnv_eeh_init(void)
 {
 	struct pci_controller *hose;
 	struct pnv_phb *phb;
@@ -86,14 +86,14 @@ static int powernv_eeh_init(void)
 }
 
 /**
- * powernv_eeh_post_init - EEH platform dependent post initialization
+ * pnv_eeh_post_init - EEH platform dependent post initialization
  *
  * EEH platform dependent post initialization on powernv. When
  * the function is called, the EEH PEs and devices should have
  * been built. If the I/O cache staff has been built, EEH is
  * ready to supply service.
  */
-static int powernv_eeh_post_init(void)
+static int pnv_eeh_post_init(void)
 {
 	struct pci_controller *hose;
 	struct pnv_phb *phb;
@@ -113,7 +113,7 @@ static int powernv_eeh_post_init(void)
 }
 
 /**
- * powernv_eeh_dev_probe - Do probe on PCI device
+ * pnv_eeh_dev_probe - Do probe on PCI device
  * @dev: PCI device
  * @flag: unused
  *
@@ -129,7 +129,7 @@ static int powernv_eeh_post_init(void)
  * was possiblly triggered by EEH core, the binding between EEH device
  * and the PCI device isn't built yet.
  */
-static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag)
+static int pnv_eeh_dev_probe(struct pci_dev *dev, void *flag)
 {
 	struct pci_controller *hose = pci_bus_to_host(dev->bus);
 	struct pnv_phb *phb = hose->private_data;
@@ -221,7 +221,7 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag)
 }
 
 /**
- * powernv_eeh_set_option - Initialize EEH or MMIO/DMA reenable
+ * pnv_eeh_set_option - Initialize EEH or MMIO/DMA reenable
  * @pe: EEH PE
  * @option: operation to be issued
  *
@@ -229,7 +229,7 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag)
  * Currently, following options are support according to PAPR:
  * Enable EEH, Disable EEH, Enable MMIO and Enable DMA
  */
-static int powernv_eeh_set_option(struct eeh_pe *pe, int option)
+static int pnv_eeh_set_option(struct eeh_pe *pe, int option)
 {
 	struct pci_controller *hose = pe->phb;
 	struct pnv_phb *phb = hose->private_data;
@@ -246,19 +246,19 @@ static int powernv_eeh_set_option(struct eeh_pe *pe, int option)
 }
 
 /**
- * powernv_eeh_get_pe_addr - Retrieve PE address
+ * pnv_eeh_get_pe_addr - Retrieve PE address
  * @pe: EEH PE
  *
  * Retrieve the PE address according to the given tranditional
  * PCI BDF (Bus/Device/Function) address.
  */
-static int powernv_eeh_get_pe_addr(struct eeh_pe *pe)
+static int pnv_eeh_get_pe_addr(struct eeh_pe *pe)
 {
 	return pe->addr;
 }
 
 /**
- * powernv_eeh_get_state - Retrieve PE state
+ * pnv_eeh_get_state - Retrieve PE state
  * @pe: EEH PE
  * @delay: delay while PE state is temporarily unavailable
  *
@@ -267,7 +267,7 @@ static int powernv_eeh_get_pe_addr(struct eeh_pe *pe)
  * we prefer passing down to hardware implementation to handle
  * it.
  */
-static int powernv_eeh_get_state(struct eeh_pe *pe, int *delay)
+static int pnv_eeh_get_state(struct eeh_pe *pe, int *delay)
 {
 	struct pci_controller *hose = pe->phb;
 	struct pnv_phb *phb = hose->private_data;
@@ -292,13 +292,13 @@ static int powernv_eeh_get_state(struct eeh_pe *pe, int *delay)
 }
 
 /**
- * powernv_eeh_reset - Reset the specified PE
+ * pnv_eeh_reset - Reset the specified PE
  * @pe: EEH PE
  * @option: reset option
  *
  * Reset the specified PE
  */
-static int powernv_eeh_reset(struct eeh_pe *pe, int option)
+static int pnv_eeh_reset(struct eeh_pe *pe, int option)
 {
 	struct pci_controller *hose = pe->phb;
 	struct pnv_phb *phb = hose->private_data;
@@ -311,20 +311,20 @@ static int powernv_eeh_reset(struct eeh_pe *pe, int option)
 }
 
 /**
- * powernv_eeh_wait_state - Wait for PE state
+ * pnv_eeh_wait_state - Wait for PE state
  * @pe: EEH PE
  * @max_wait: maximal period in microsecond
  *
  * Wait for the state of associated PE. It might take some time
  * to retrieve the PE's state.
  */
-static int powernv_eeh_wait_state(struct eeh_pe *pe, int max_wait)
+static int pnv_eeh_wait_state(struct eeh_pe *pe, int max_wait)
 {
 	int ret;
 	int mwait;
 
 	while (1) {
-		ret = powernv_eeh_get_state(pe, &mwait);
+		ret = pnv_eeh_get_state(pe, &mwait);
 
 		/*
 		 * If the PE's state is temporarily unavailable,
@@ -348,7 +348,7 @@ static int powernv_eeh_wait_state(struct eeh_pe *pe, int max_wait)
 }
 
 /**
- * powernv_eeh_get_log - Retrieve error log
+ * pnv_eeh_get_log - Retrieve error log
  * @pe: EEH PE
  * @severity: temporary or permanent error log
  * @drv_log: driver log to be combined with retrieved error log
@@ -356,8 +356,8 @@ static int powernv_eeh_wait_state(struct eeh_pe *pe, int max_wait)
  *
  * Retrieve the temporary or permanent error from the PE.
  */
-static int powernv_eeh_get_log(struct eeh_pe *pe, int severity,
-			       char *drv_log, unsigned long len)
+static int pnv_eeh_get_log(struct eeh_pe *pe, int severity,
+			   char *drv_log, unsigned long len)
 {
 	struct pci_controller *hose = pe->phb;
 	struct pnv_phb *phb = hose->private_data;
@@ -370,14 +370,14 @@ static int powernv_eeh_get_log(struct eeh_pe *pe, int severity,
 }
 
 /**
- * powernv_eeh_configure_bridge - Configure PCI bridges in the indicated PE
+ * pnv_eeh_configure_bridge - Configure PCI bridges in the indicated PE
  * @pe: EEH PE
  *
  * The function will be called to reconfigure the bridges included
  * in the specified PE so that the mulfunctional PE would be recovered
  * again.
  */
-static int powernv_eeh_configure_bridge(struct eeh_pe *pe)
+static int pnv_eeh_configure_bridge(struct eeh_pe *pe)
 {
 	struct pci_controller *hose = pe->phb;
 	struct pnv_phb *phb = hose->private_data;
@@ -390,7 +390,7 @@ static int powernv_eeh_configure_bridge(struct eeh_pe *pe)
 }
 
 /**
- * powernv_pe_err_inject - Inject specified error to the indicated PE
+ * pnv_pe_err_inject - Inject specified error to the indicated PE
  * @pe: the indicated PE
  * @type: error type
  * @func: specific error type
@@ -401,8 +401,8 @@ static int powernv_eeh_configure_bridge(struct eeh_pe *pe)
  * determined by @type and @func, to the indicated PE for
  * testing purpose.
  */
-static int powernv_eeh_err_inject(struct eeh_pe *pe, int type, int func,
-				  unsigned long addr, unsigned long mask)
+static int pnv_eeh_err_inject(struct eeh_pe *pe, int type, int func,
+			      unsigned long addr, unsigned long mask)
 {
 	struct pci_controller *hose = pe->phb;
 	struct pnv_phb *phb = hose->private_data;
@@ -414,7 +414,7 @@ static int powernv_eeh_err_inject(struct eeh_pe *pe, int type, int func,
 	return ret;
 }
 
-static inline bool powernv_eeh_cfg_blocked(struct device_node *dn)
+static inline bool pnv_eeh_cfg_blocked(struct device_node *dn)
 {
 	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
 
@@ -427,10 +427,10 @@ static inline bool powernv_eeh_cfg_blocked(struct device_node *dn)
 	return false;
 }
 
-static int powernv_eeh_read_config(struct device_node *dn,
-				   int where, int size, u32 *val)
+static int pnv_eeh_read_config(struct device_node *dn,
+			       int where, int size, u32 *val)
 {
-	if (powernv_eeh_cfg_blocked(dn)) {
+	if (pnv_eeh_cfg_blocked(dn)) {
 		*val = 0xFFFFFFFF;
 		return PCIBIOS_SET_FAILED;
 	}
@@ -438,22 +438,22 @@ static int powernv_eeh_read_config(struct device_node *dn,
 	return pnv_pci_cfg_read(dn, where, size, val);
 }
 
-static int powernv_eeh_write_config(struct device_node *dn,
-				    int where, int size, u32 val)
+static int pnv_eeh_write_config(struct device_node *dn,
+				int where, int size, u32 val)
 {
-	if (powernv_eeh_cfg_blocked(dn))
+	if (pnv_eeh_cfg_blocked(dn))
 		return PCIBIOS_SET_FAILED;
 
 	return pnv_pci_cfg_write(dn, where, size, val);
 }
 
 /**
- * powernv_eeh_next_error - Retrieve next EEH error to handle
+ * pnv_eeh_next_error - Retrieve next EEH error to handle
  * @pe: Affected PE
  *
  * Using OPAL API, to retrieve next EEH error for EEH core to handle
  */
-static int powernv_eeh_next_error(struct eeh_pe **pe)
+static int pnv_eeh_next_error(struct eeh_pe **pe)
 {
 	struct pci_controller *hose;
 	struct pnv_phb *phb = NULL;
@@ -469,7 +469,7 @@ static int powernv_eeh_next_error(struct eeh_pe **pe)
 	return -EEXIST;
 }
 
-static int powernv_eeh_restore_config(struct device_node *dn)
+static int pnv_eeh_restore_config(struct device_node *dn)
 {
 	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
 	struct pnv_phb *phb;
@@ -490,24 +490,24 @@ static int powernv_eeh_restore_config(struct device_node *dn)
 	return 0;
 }
 
-static struct eeh_ops powernv_eeh_ops = {
+static struct eeh_ops pnv_eeh_ops = {
 	.name                   = "powernv",
-	.init                   = powernv_eeh_init,
-	.post_init              = powernv_eeh_post_init,
+	.init                   = pnv_eeh_init,
+	.post_init              = pnv_eeh_post_init,
 	.of_probe               = NULL,
-	.dev_probe              = powernv_eeh_dev_probe,
-	.set_option             = powernv_eeh_set_option,
-	.get_pe_addr            = powernv_eeh_get_pe_addr,
-	.get_state              = powernv_eeh_get_state,
-	.reset                  = powernv_eeh_reset,
-	.wait_state             = powernv_eeh_wait_state,
-	.get_log                = powernv_eeh_get_log,
-	.configure_bridge       = powernv_eeh_configure_bridge,
-	.err_inject		= powernv_eeh_err_inject,
-	.read_config            = powernv_eeh_read_config,
-	.write_config           = powernv_eeh_write_config,
-	.next_error		= powernv_eeh_next_error,
-	.restore_config		= powernv_eeh_restore_config
+	.dev_probe              = pnv_eeh_dev_probe,
+	.set_option             = pnv_eeh_set_option,
+	.get_pe_addr            = pnv_eeh_get_pe_addr,
+	.get_state              = pnv_eeh_get_state,
+	.reset                  = pnv_eeh_reset,
+	.wait_state             = pnv_eeh_wait_state,
+	.get_log                = pnv_eeh_get_log,
+	.configure_bridge       = pnv_eeh_configure_bridge,
+	.err_inject		= pnv_eeh_err_inject,
+	.read_config            = pnv_eeh_read_config,
+	.write_config           = pnv_eeh_write_config,
+	.next_error		= pnv_eeh_next_error,
+	.restore_config		= pnv_eeh_restore_config
 };
 
 /**
@@ -521,7 +521,7 @@ static int __init eeh_powernv_init(void)
 	int ret = -EINVAL;
 
 	eeh_set_pe_aux_size(PNV_PCI_DIAG_BUF_SIZE);
-	ret = eeh_ops_register(&powernv_eeh_ops);
+	ret = eeh_ops_register(&pnv_eeh_ops);
 	if (!ret)
 		pr_info("EEH: PowerNV platform initialized\n");
 	else
-- 
cgit v1.2.3


From fa646c3cab032caf94184aef728d7275164c437e Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Mon, 16 Feb 2015 14:45:40 +1100
Subject: powerpc/powernv: Drop PHB operation err_inject()

The patch drops PHB EEH operation err_inject() and merge its logic
to eeh_ops::err_inject().

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/eeh-ioda.c    | 49 ++--------------------------
 arch/powerpc/platforms/powernv/eeh-powernv.c | 38 ++++++++++++++++++---
 arch/powerpc/platforms/powernv/pci.h         |  2 --
 3 files changed, 36 insertions(+), 53 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index 2809c9895288..dd154cf98085 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -70,7 +70,6 @@ static ssize_t ioda_eeh_ei_write(struct file *filp,
 				 size_t count, loff_t *ppos)
 {
 	struct pci_controller *hose = filp->private_data;
-	struct pnv_phb *phb = hose->private_data;
 	struct eeh_dev *edev;
 	struct eeh_pe *pe;
 	int pe_no, type, func;
@@ -78,7 +77,7 @@ static ssize_t ioda_eeh_ei_write(struct file *filp,
 	char buf[50];
 	int ret;
 
-	if (!phb->eeh_ops || !phb->eeh_ops->err_inject)
+	if (!eeh_ops || !eeh_ops->err_inject)
 		return -ENXIO;
 
 	ret = simple_write_to_buffer(buf, sizeof(buf), ppos, user_buf, count);
@@ -103,7 +102,7 @@ static ssize_t ioda_eeh_ei_write(struct file *filp,
 		return -ENODEV;
 
 	/* Do error injection */
-	ret = phb->eeh_ops->err_inject(pe, type, func, addr, mask);
+	ret = eeh_ops->err_inject(pe, type, func, addr, mask);
 	return ret < 0 ? ret : count;
 }
 
@@ -756,49 +755,6 @@ static int ioda_eeh_configure_bridge(struct eeh_pe *pe)
 	return 0;
 }
 
-static int ioda_eeh_err_inject(struct eeh_pe *pe, int type, int func,
-			       unsigned long addr, unsigned long mask)
-{
-	struct pci_controller *hose = pe->phb;
-	struct pnv_phb *phb = hose->private_data;
-	s64 ret;
-
-	/* Sanity check on error type */
-	if (type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR &&
-	    type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR64) {
-		pr_warn("%s: Invalid error type %d\n",
-			__func__, type);
-		return -ERANGE;
-	}
-
-	if (func < OPAL_ERR_INJECT_FUNC_IOA_LD_MEM_ADDR ||
-	    func > OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_TARGET) {
-		pr_warn("%s: Invalid error function %d\n",
-			__func__, func);
-		return -ERANGE;
-	}
-
-	/* Firmware supports error injection ? */
-	if (!opal_check_token(OPAL_PCI_ERR_INJECT)) {
-		pr_warn("%s: Firmware doesn't support error injection\n",
-			__func__);
-		return -ENXIO;
-	}
-
-	/* Do error injection */
-	ret = opal_pci_err_inject(phb->opal_id, pe->addr,
-				  type, func, addr, mask);
-	if (ret != OPAL_SUCCESS) {
-		pr_warn("%s: Failure %lld injecting error "
-			"%d-%d to PHB#%x-PE#%x\n",
-			__func__, ret, type, func,
-			hose->global_number, pe->addr);
-		return -EIO;
-	}
-
-	return 0;
-}
-
 static void ioda_eeh_hub_diag_common(struct OpalIoP7IOCErrorData *data)
 {
 	/* GEM */
@@ -1144,6 +1100,5 @@ struct pnv_eeh_ops ioda_eeh_ops = {
 	.reset			= ioda_eeh_reset,
 	.get_log		= ioda_eeh_get_log,
 	.configure_bridge	= ioda_eeh_configure_bridge,
-	.err_inject		= ioda_eeh_err_inject,
 	.next_error		= ioda_eeh_next_error
 };
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index f562dd1a99cc..df33daab381c 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -406,12 +406,42 @@ static int pnv_eeh_err_inject(struct eeh_pe *pe, int type, int func,
 {
 	struct pci_controller *hose = pe->phb;
 	struct pnv_phb *phb = hose->private_data;
-	int ret = -EEXIST;
+	s64 rc;
+
+	/* Sanity check on error type */
+	if (type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR &&
+	    type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR64) {
+		pr_warn("%s: Invalid error type %d\n",
+			__func__, type);
+		return -ERANGE;
+	}
 
-	if (phb->eeh_ops && phb->eeh_ops->err_inject)
-		ret = phb->eeh_ops->err_inject(pe, type, func, addr, mask);
+	if (func < OPAL_ERR_INJECT_FUNC_IOA_LD_MEM_ADDR ||
+	    func > OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_TARGET) {
+		pr_warn("%s: Invalid error function %d\n",
+			__func__, func);
+		return -ERANGE;
+	}
 
-	return ret;
+	/* Firmware supports error injection ? */
+	if (!opal_check_token(OPAL_PCI_ERR_INJECT)) {
+		pr_warn("%s: Firmware doesn't support error injection\n",
+			__func__);
+		return -ENXIO;
+	}
+
+	/* Do error injection */
+	rc = opal_pci_err_inject(phb->opal_id, pe->addr,
+				 type, func, addr, mask);
+	if (rc != OPAL_SUCCESS) {
+		pr_warn("%s: Failure %lld injecting error "
+			"%d-%d to PHB#%x-PE#%x\n",
+			__func__, rc, type, func,
+			hose->global_number, pe->addr);
+		return -EIO;
+	}
+
+	return 0;
 }
 
 static inline bool pnv_eeh_cfg_blocked(struct device_node *dn)
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 6c02ff8dd69f..a9f236229fe0 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -85,8 +85,6 @@ struct pnv_eeh_ops {
 	int (*get_log)(struct eeh_pe *pe, int severity,
 		       char *drv_log, unsigned long len);
 	int (*configure_bridge)(struct eeh_pe *pe);
-	int (*err_inject)(struct eeh_pe *pe, int type, int func,
-			  unsigned long addr, unsigned long mask);
 	int (*next_error)(struct eeh_pe **pe);
 };
 #endif /* CONFIG_EEH */
-- 
cgit v1.2.3


From 4cf17445589932155797444687dca1ef2dd47f10 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Mon, 16 Feb 2015 14:45:41 +1100
Subject: powerpc/powernv: Drop PHB operation post_init()

The patch drops PHB EEH operation post_init() and merge its logic
to eeh_ops::post_init().

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/eeh-ioda.c    | 193 ---------------------------
 arch/powerpc/platforms/powernv/eeh-powernv.c | 184 ++++++++++++++++++++++++-
 arch/powerpc/platforms/powernv/pci.h         |   1 -
 3 files changed, 179 insertions(+), 199 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index dd154cf98085..bd509ad08211 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -34,198 +34,6 @@
 #include "powernv.h"
 #include "pci.h"
 
-static int ioda_eeh_nb_init = 0;
-
-static int ioda_eeh_event(struct notifier_block *nb,
-			  unsigned long events, void *change)
-{
-	uint64_t changed_evts = (uint64_t)change;
-
-	/*
-	 * We simply send special EEH event if EEH has
-	 * been enabled, or clear pending events in
-	 * case that we enable EEH soon
-	 */
-	if (!(changed_evts & OPAL_EVENT_PCI_ERROR) ||
-	    !(events & OPAL_EVENT_PCI_ERROR))
-		return 0;
-
-	if (eeh_enabled())
-		eeh_send_failure_event(NULL);
-	else
-		opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul);
-
-	return 0;
-}
-
-static struct notifier_block ioda_eeh_nb = {
-	.notifier_call	= ioda_eeh_event,
-	.next		= NULL,
-	.priority	= 0
-};
-
-#ifdef CONFIG_DEBUG_FS
-static ssize_t ioda_eeh_ei_write(struct file *filp,
-				 const char __user *user_buf,
-				 size_t count, loff_t *ppos)
-{
-	struct pci_controller *hose = filp->private_data;
-	struct eeh_dev *edev;
-	struct eeh_pe *pe;
-	int pe_no, type, func;
-	unsigned long addr, mask;
-	char buf[50];
-	int ret;
-
-	if (!eeh_ops || !eeh_ops->err_inject)
-		return -ENXIO;
-
-	ret = simple_write_to_buffer(buf, sizeof(buf), ppos, user_buf, count);
-	if (!ret)
-		return -EFAULT;
-
-	/* Retrieve parameters */
-	ret = sscanf(buf, "%x:%x:%x:%lx:%lx",
-		     &pe_no, &type, &func, &addr, &mask);
-	if (ret != 5)
-		return -EINVAL;
-
-	/* Retrieve PE */
-	edev = kzalloc(sizeof(*edev), GFP_KERNEL);
-	if (!edev)
-		return -ENOMEM;
-	edev->phb = hose;
-	edev->pe_config_addr = pe_no;
-	pe = eeh_pe_get(edev);
-	kfree(edev);
-	if (!pe)
-		return -ENODEV;
-
-	/* Do error injection */
-	ret = eeh_ops->err_inject(pe, type, func, addr, mask);
-	return ret < 0 ? ret : count;
-}
-
-static const struct file_operations ioda_eeh_ei_fops = {
-	.open   = simple_open,
-	.llseek = no_llseek,
-	.write  = ioda_eeh_ei_write,
-};
-
-static int ioda_eeh_dbgfs_set(void *data, int offset, u64 val)
-{
-	struct pci_controller *hose = data;
-	struct pnv_phb *phb = hose->private_data;
-
-	out_be64(phb->regs + offset, val);
-	return 0;
-}
-
-static int ioda_eeh_dbgfs_get(void *data, int offset, u64 *val)
-{
-	struct pci_controller *hose = data;
-	struct pnv_phb *phb = hose->private_data;
-
-	*val = in_be64(phb->regs + offset);
-	return 0;
-}
-
-static int ioda_eeh_outb_dbgfs_set(void *data, u64 val)
-{
-	return ioda_eeh_dbgfs_set(data, 0xD10, val);
-}
-
-static int ioda_eeh_outb_dbgfs_get(void *data, u64 *val)
-{
-	return ioda_eeh_dbgfs_get(data, 0xD10, val);
-}
-
-static int ioda_eeh_inbA_dbgfs_set(void *data, u64 val)
-{
-	return ioda_eeh_dbgfs_set(data, 0xD90, val);
-}
-
-static int ioda_eeh_inbA_dbgfs_get(void *data, u64 *val)
-{
-	return ioda_eeh_dbgfs_get(data, 0xD90, val);
-}
-
-static int ioda_eeh_inbB_dbgfs_set(void *data, u64 val)
-{
-	return ioda_eeh_dbgfs_set(data, 0xE10, val);
-}
-
-static int ioda_eeh_inbB_dbgfs_get(void *data, u64 *val)
-{
-	return ioda_eeh_dbgfs_get(data, 0xE10, val);
-}
-
-DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_outb_dbgfs_ops, ioda_eeh_outb_dbgfs_get,
-			ioda_eeh_outb_dbgfs_set, "0x%llx\n");
-DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_inbA_dbgfs_ops, ioda_eeh_inbA_dbgfs_get,
-			ioda_eeh_inbA_dbgfs_set, "0x%llx\n");
-DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_inbB_dbgfs_ops, ioda_eeh_inbB_dbgfs_get,
-			ioda_eeh_inbB_dbgfs_set, "0x%llx\n");
-#endif /* CONFIG_DEBUG_FS */
-
-
-/**
- * ioda_eeh_post_init - Chip dependent post initialization
- * @hose: PCI controller
- *
- * The function will be called after eeh PEs and devices
- * have been built. That means the EEH is ready to supply
- * service with I/O cache.
- */
-static int ioda_eeh_post_init(struct pci_controller *hose)
-{
-	struct pnv_phb *phb = hose->private_data;
-	int ret;
-
-	/* Register OPAL event notifier */
-	if (!ioda_eeh_nb_init) {
-		ret = opal_notifier_register(&ioda_eeh_nb);
-		if (ret) {
-			pr_err("%s: Can't register OPAL event notifier (%d)\n",
-			       __func__, ret);
-			return ret;
-		}
-
-		ioda_eeh_nb_init = 1;
-	}
-
-#ifdef CONFIG_DEBUG_FS
-	if (!phb->has_dbgfs && phb->dbgfs) {
-		phb->has_dbgfs = 1;
-
-		debugfs_create_file("err_injct", 0200,
-				    phb->dbgfs, hose,
-				    &ioda_eeh_ei_fops);
-
-		debugfs_create_file("err_injct_outbound", 0600,
-				    phb->dbgfs, hose,
-				    &ioda_eeh_outb_dbgfs_ops);
-		debugfs_create_file("err_injct_inboundA", 0600,
-				    phb->dbgfs, hose,
-				    &ioda_eeh_inbA_dbgfs_ops);
-		debugfs_create_file("err_injct_inboundB", 0600,
-				    phb->dbgfs, hose,
-				    &ioda_eeh_inbB_dbgfs_ops);
-	}
-#endif
-
-	/* If EEH is enabled, we're going to rely on that.
-	 * Otherwise, we restore to conventional mechanism
-	 * to clear frozen PE during PCI config access.
-	 */
-	if (eeh_enabled())
-		phb->flags |= PNV_PHB_FLAG_EEH;
-	else
-		phb->flags &= ~PNV_PHB_FLAG_EEH;
-
-	return 0;
-}
-
 /**
  * ioda_eeh_set_option - Set EEH operation or I/O setting
  * @pe: EEH PE
@@ -1094,7 +902,6 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 }
 
 struct pnv_eeh_ops ioda_eeh_ops = {
-	.post_init		= ioda_eeh_post_init,
 	.set_option		= ioda_eeh_set_option,
 	.get_state		= ioda_eeh_get_state,
 	.reset			= ioda_eeh_reset,
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index df33daab381c..641ba3378ccf 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/atomic.h>
+#include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/init.h>
@@ -38,6 +39,8 @@
 #include "powernv.h"
 #include "pci.h"
 
+static bool pnv_eeh_nb_init = false;
+
 /**
  * pnv_eeh_init - EEH platform dependent initialization
  *
@@ -85,6 +88,139 @@ static int pnv_eeh_init(void)
 	return 0;
 }
 
+static int pnv_eeh_event(struct notifier_block *nb,
+			 unsigned long events, void *change)
+{
+	uint64_t changed_evts = (uint64_t)change;
+
+	/*
+	 * We simply send special EEH event if EEH has
+	 * been enabled, or clear pending events in
+	 * case that we enable EEH soon
+	 */
+	if (!(changed_evts & OPAL_EVENT_PCI_ERROR) ||
+	    !(events & OPAL_EVENT_PCI_ERROR))
+		return 0;
+
+	if (eeh_enabled())
+		eeh_send_failure_event(NULL);
+	else
+		opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul);
+
+	return 0;
+}
+
+static struct notifier_block pnv_eeh_nb = {
+	.notifier_call	= pnv_eeh_event,
+	.next		= NULL,
+	.priority	= 0
+};
+
+#ifdef CONFIG_DEBUG_FS
+static ssize_t pnv_eeh_ei_write(struct file *filp,
+				const char __user *user_buf,
+				size_t count, loff_t *ppos)
+{
+	struct pci_controller *hose = filp->private_data;
+	struct eeh_dev *edev;
+	struct eeh_pe *pe;
+	int pe_no, type, func;
+	unsigned long addr, mask;
+	char buf[50];
+	int ret;
+
+	if (!eeh_ops || !eeh_ops->err_inject)
+		return -ENXIO;
+
+	/* Copy over argument buffer */
+	ret = simple_write_to_buffer(buf, sizeof(buf), ppos, user_buf, count);
+	if (!ret)
+		return -EFAULT;
+
+	/* Retrieve parameters */
+	ret = sscanf(buf, "%x:%x:%x:%lx:%lx",
+		     &pe_no, &type, &func, &addr, &mask);
+	if (ret != 5)
+		return -EINVAL;
+
+	/* Retrieve PE */
+	edev = kzalloc(sizeof(*edev), GFP_KERNEL);
+	if (!edev)
+		return -ENOMEM;
+	edev->phb = hose;
+	edev->pe_config_addr = pe_no;
+	pe = eeh_pe_get(edev);
+	kfree(edev);
+	if (!pe)
+		return -ENODEV;
+
+	/* Do error injection */
+	ret = eeh_ops->err_inject(pe, type, func, addr, mask);
+	return ret < 0 ? ret : count;
+}
+
+static const struct file_operations pnv_eeh_ei_fops = {
+	.open	= simple_open,
+	.llseek	= no_llseek,
+	.write	= pnv_eeh_ei_write,
+};
+
+static int pnv_eeh_dbgfs_set(void *data, int offset, u64 val)
+{
+	struct pci_controller *hose = data;
+	struct pnv_phb *phb = hose->private_data;
+
+	out_be64(phb->regs + offset, val);
+	return 0;
+}
+
+static int pnv_eeh_dbgfs_get(void *data, int offset, u64 *val)
+{
+	struct pci_controller *hose = data;
+	struct pnv_phb *phb = hose->private_data;
+
+	*val = in_be64(phb->regs + offset);
+	return 0;
+}
+
+static int pnv_eeh_outb_dbgfs_set(void *data, u64 val)
+{
+	return pnv_eeh_dbgfs_set(data, 0xD10, val);
+}
+
+static int pnv_eeh_outb_dbgfs_get(void *data, u64 *val)
+{
+	return pnv_eeh_dbgfs_get(data, 0xD10, val);
+}
+
+static int pnv_eeh_inbA_dbgfs_set(void *data, u64 val)
+{
+	return pnv_eeh_dbgfs_set(data, 0xD90, val);
+}
+
+static int pnv_eeh_inbA_dbgfs_get(void *data, u64 *val)
+{
+	return pnv_eeh_dbgfs_get(data, 0xD90, val);
+}
+
+static int pnv_eeh_inbB_dbgfs_set(void *data, u64 val)
+{
+	return pnv_eeh_dbgfs_set(data, 0xE10, val);
+}
+
+static int pnv_eeh_inbB_dbgfs_get(void *data, u64 *val)
+{
+	return pnv_eeh_dbgfs_get(data, 0xE10, val);
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(pnv_eeh_outb_dbgfs_ops, pnv_eeh_outb_dbgfs_get,
+			pnv_eeh_outb_dbgfs_set, "0x%llx\n");
+DEFINE_SIMPLE_ATTRIBUTE(pnv_eeh_inbA_dbgfs_ops, pnv_eeh_inbA_dbgfs_get,
+			pnv_eeh_inbA_dbgfs_set, "0x%llx\n");
+DEFINE_SIMPLE_ATTRIBUTE(pnv_eeh_inbB_dbgfs_ops, pnv_eeh_inbB_dbgfs_get,
+			pnv_eeh_inbB_dbgfs_set, "0x%llx\n");
+#endif /* CONFIG_DEBUG_FS */
+
 /**
  * pnv_eeh_post_init - EEH platform dependent post initialization
  *
@@ -99,16 +235,54 @@ static int pnv_eeh_post_init(void)
 	struct pnv_phb *phb;
 	int ret = 0;
 
+	/* Register OPAL event notifier */
+	if (!pnv_eeh_nb_init) {
+		ret = opal_notifier_register(&pnv_eeh_nb);
+		if (ret) {
+			pr_warn("%s: Can't register OPAL event notifier (%d)\n",
+				__func__, ret);
+			return ret;
+		}
+
+		pnv_eeh_nb_init = true;
+	}
+
 	list_for_each_entry(hose, &hose_list, list_node) {
 		phb = hose->private_data;
 
-		if (phb->eeh_ops && phb->eeh_ops->post_init) {
-			ret = phb->eeh_ops->post_init(hose);
-			if (ret)
-				break;
-		}
+		/*
+		 * If EEH is enabled, we're going to rely on that.
+		 * Otherwise, we restore to conventional mechanism
+		 * to clear frozen PE during PCI config access.
+		 */
+		if (eeh_enabled())
+			phb->flags |= PNV_PHB_FLAG_EEH;
+		else
+			phb->flags &= ~PNV_PHB_FLAG_EEH;
+
+		/* Create debugfs entries */
+#ifdef CONFIG_DEBUG_FS
+		if (phb->has_dbgfs || !phb->dbgfs)
+			continue;
+
+		phb->has_dbgfs = 1;
+		debugfs_create_file("err_injct", 0200,
+				    phb->dbgfs, hose,
+				    &pnv_eeh_ei_fops);
+
+		debugfs_create_file("err_injct_outbound", 0600,
+				    phb->dbgfs, hose,
+				    &pnv_eeh_outb_dbgfs_ops);
+		debugfs_create_file("err_injct_inboundA", 0600,
+				    phb->dbgfs, hose,
+				    &pnv_eeh_inbA_dbgfs_ops);
+		debugfs_create_file("err_injct_inboundB", 0600,
+				    phb->dbgfs, hose,
+				    &pnv_eeh_inbB_dbgfs_ops);
+#endif /* CONFIG_DEBUG_FS */
 	}
 
+
 	return ret;
 }
 
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index a9f236229fe0..c7e047f19528 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -78,7 +78,6 @@ struct pnv_ioda_pe {
 /* IOC dependent EEH operations */
 #ifdef CONFIG_EEH
 struct pnv_eeh_ops {
-	int (*post_init)(struct pci_controller *hose);
 	int (*set_option)(struct eeh_pe *pe, int option);
 	int (*get_state)(struct eeh_pe *pe);
 	int (*reset)(struct eeh_pe *pe, int option);
-- 
cgit v1.2.3


From 95edcdeadf1e838c7d6f1ef43194128d823c61a1 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Mon, 16 Feb 2015 14:45:42 +1100
Subject: powerpc/powernv: Drop PHB operation get_log()

The patch drops PHB operation get_log() and merges its logic to
eeh_ops::get_log().

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/eeh-ioda.c    | 20 --------------------
 arch/powerpc/platforms/powernv/eeh-powernv.c | 10 +++-------
 arch/powerpc/platforms/powernv/pci.h         |  2 --
 3 files changed, 3 insertions(+), 29 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index bd509ad08211..7eb6e724fbc9 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -530,25 +530,6 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 	return ret;
 }
 
-/**
- * ioda_eeh_get_log - Retrieve error log
- * @pe: frozen PE
- * @severity: permanent or temporary error
- * @drv_log: device driver log
- * @len: length of device driver log
- *
- * Retrieve error log, which contains log from device driver
- * and firmware.
- */
-static int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
-			    char *drv_log, unsigned long len)
-{
-	if (!eeh_has_flag(EEH_EARLY_DUMP_LOG))
-		pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
-
-	return 0;
-}
-
 /**
  * ioda_eeh_configure_bridge - Configure the PCI bridges for the indicated PE
  * @pe: EEH PE
@@ -905,7 +886,6 @@ struct pnv_eeh_ops ioda_eeh_ops = {
 	.set_option		= ioda_eeh_set_option,
 	.get_state		= ioda_eeh_get_state,
 	.reset			= ioda_eeh_reset,
-	.get_log		= ioda_eeh_get_log,
 	.configure_bridge	= ioda_eeh_configure_bridge,
 	.next_error		= ioda_eeh_next_error
 };
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 641ba3378ccf..465deb5f5f46 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -533,14 +533,10 @@ static int pnv_eeh_wait_state(struct eeh_pe *pe, int max_wait)
 static int pnv_eeh_get_log(struct eeh_pe *pe, int severity,
 			   char *drv_log, unsigned long len)
 {
-	struct pci_controller *hose = pe->phb;
-	struct pnv_phb *phb = hose->private_data;
-	int ret = -EEXIST;
+	if (!eeh_has_flag(EEH_EARLY_DUMP_LOG))
+		pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
 
-	if (phb->eeh_ops && phb->eeh_ops->get_log)
-		ret = phb->eeh_ops->get_log(pe, severity, drv_log, len);
-
-	return ret;
+	return 0;
 }
 
 /**
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index c7e047f19528..1e7a623cbff4 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -81,8 +81,6 @@ struct pnv_eeh_ops {
 	int (*set_option)(struct eeh_pe *pe, int option);
 	int (*get_state)(struct eeh_pe *pe);
 	int (*reset)(struct eeh_pe *pe, int option);
-	int (*get_log)(struct eeh_pe *pe, int severity,
-		       char *drv_log, unsigned long len);
 	int (*configure_bridge)(struct eeh_pe *pe);
 	int (*next_error)(struct eeh_pe **pe);
 };
-- 
cgit v1.2.3


From bbe170ede15b3b33361b95497fb164909b45ffa9 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Mon, 16 Feb 2015 14:45:43 +1100
Subject: powerpc/powernv: Drop PHB operation configure_bridge()

The patch drops PHB EEH operation configure_bridge() and merges
its logic to eeh_ops::configure_bridge().

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/eeh-ioda.c    | 15 ---------------
 arch/powerpc/platforms/powernv/eeh-powernv.c |  9 +--------
 arch/powerpc/platforms/powernv/pci.h         |  1 -
 3 files changed, 1 insertion(+), 24 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index 7eb6e724fbc9..645951639b01 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -530,20 +530,6 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 	return ret;
 }
 
-/**
- * ioda_eeh_configure_bridge - Configure the PCI bridges for the indicated PE
- * @pe: EEH PE
- *
- * For particular PE, it might have included PCI bridges. In order
- * to make the PE work properly, those PCI bridges should be configured
- * correctly. However, we need do nothing on P7IOC since the reset
- * function will do everything that should be covered by the function.
- */
-static int ioda_eeh_configure_bridge(struct eeh_pe *pe)
-{
-	return 0;
-}
-
 static void ioda_eeh_hub_diag_common(struct OpalIoP7IOCErrorData *data)
 {
 	/* GEM */
@@ -886,6 +872,5 @@ struct pnv_eeh_ops ioda_eeh_ops = {
 	.set_option		= ioda_eeh_set_option,
 	.get_state		= ioda_eeh_get_state,
 	.reset			= ioda_eeh_reset,
-	.configure_bridge	= ioda_eeh_configure_bridge,
 	.next_error		= ioda_eeh_next_error
 };
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 465deb5f5f46..a7087f4a739a 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -549,14 +549,7 @@ static int pnv_eeh_get_log(struct eeh_pe *pe, int severity,
  */
 static int pnv_eeh_configure_bridge(struct eeh_pe *pe)
 {
-	struct pci_controller *hose = pe->phb;
-	struct pnv_phb *phb = hose->private_data;
-	int ret = 0;
-
-	if (phb->eeh_ops && phb->eeh_ops->configure_bridge)
-		ret = phb->eeh_ops->configure_bridge(pe);
-
-	return ret;
+	return 0;
 }
 
 /**
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 1e7a623cbff4..d8808caf19f2 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -81,7 +81,6 @@ struct pnv_eeh_ops {
 	int (*set_option)(struct eeh_pe *pe, int option);
 	int (*get_state)(struct eeh_pe *pe);
 	int (*reset)(struct eeh_pe *pe, int option);
-	int (*configure_bridge)(struct eeh_pe *pe);
 	int (*next_error)(struct eeh_pe **pe);
 };
 #endif /* CONFIG_EEH */
-- 
cgit v1.2.3


From 7e3e4f8d5e80d2321cb1ab58a2070fbf28883ec1 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Mon, 16 Feb 2015 14:45:44 +1100
Subject: powerpc/powernv: Drop PHB operation set_option()

The patch drops PHB EEH operation set_option() and merges its
logic to eeh_ops::set_option().

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/eeh-ioda.c    | 84 ----------------------------
 arch/powerpc/platforms/powernv/eeh-powernv.c | 61 +++++++++++++++++---
 arch/powerpc/platforms/powernv/pci.h         |  1 -
 3 files changed, 54 insertions(+), 92 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index 645951639b01..349c0830f535 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -34,89 +34,6 @@
 #include "powernv.h"
 #include "pci.h"
 
-/**
- * ioda_eeh_set_option - Set EEH operation or I/O setting
- * @pe: EEH PE
- * @option: options
- *
- * Enable or disable EEH option for the indicated PE. The
- * function also can be used to enable I/O or DMA for the
- * PE.
- */
-static int ioda_eeh_set_option(struct eeh_pe *pe, int option)
-{
-	struct pci_controller *hose = pe->phb;
-	struct pnv_phb *phb = hose->private_data;
-	bool freeze_pe = false;
-	int enable, ret = 0;
-	s64 rc;
-
-	/* Check on PE number */
-	if (pe->addr < 0 || pe->addr >= phb->ioda.total_pe) {
-		pr_err("%s: PE address %x out of range [0, %x] "
-		       "on PHB#%x\n",
-			__func__, pe->addr, phb->ioda.total_pe,
-			hose->global_number);
-		return -EINVAL;
-	}
-
-	switch (option) {
-	case EEH_OPT_DISABLE:
-		return -EPERM;
-	case EEH_OPT_ENABLE:
-		return 0;
-	case EEH_OPT_THAW_MMIO:
-		enable = OPAL_EEH_ACTION_CLEAR_FREEZE_MMIO;
-		break;
-	case EEH_OPT_THAW_DMA:
-		enable = OPAL_EEH_ACTION_CLEAR_FREEZE_DMA;
-		break;
-	case EEH_OPT_FREEZE_PE:
-		freeze_pe = true;
-		enable = OPAL_EEH_ACTION_SET_FREEZE_ALL;
-		break;
-	default:
-		pr_warn("%s: Invalid option %d\n",
-			__func__, option);
-		return -EINVAL;
-	}
-
-	/* If PHB supports compound PE, to handle it */
-	if (freeze_pe) {
-		if (phb->freeze_pe) {
-			phb->freeze_pe(phb, pe->addr);
-		} else {
-			rc = opal_pci_eeh_freeze_set(phb->opal_id,
-						     pe->addr,
-						     enable);
-			if (rc != OPAL_SUCCESS) {
-				pr_warn("%s: Failure %lld freezing "
-					"PHB#%x-PE#%x\n",
-					__func__, rc,
-					phb->hose->global_number, pe->addr);
-				ret = -EIO;
-			}
-		}
-	} else {
-		if (phb->unfreeze_pe) {
-			ret = phb->unfreeze_pe(phb, pe->addr, enable);
-		} else {
-			rc = opal_pci_eeh_freeze_clear(phb->opal_id,
-						       pe->addr,
-						       enable);
-			if (rc != OPAL_SUCCESS) {
-				pr_warn("%s: Failure %lld enable %d "
-					"for PHB#%x-PE#%x\n",
-					__func__, rc, option,
-					phb->hose->global_number, pe->addr);
-				ret = -EIO;
-			}
-		}
-	}
-
-	return ret;
-}
-
 static void ioda_eeh_phb_diag(struct eeh_pe *pe)
 {
 	struct pnv_phb *phb = pe->phb->private_data;
@@ -869,7 +786,6 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 }
 
 struct pnv_eeh_ops ioda_eeh_ops = {
-	.set_option		= ioda_eeh_set_option,
 	.get_state		= ioda_eeh_get_state,
 	.reset			= ioda_eeh_reset,
 	.next_error		= ioda_eeh_next_error
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index a7087f4a739a..2429a23d4802 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -407,14 +407,61 @@ static int pnv_eeh_set_option(struct eeh_pe *pe, int option)
 {
 	struct pci_controller *hose = pe->phb;
 	struct pnv_phb *phb = hose->private_data;
-	int ret = -EEXIST;
+	bool freeze_pe = false;
+	int opt, ret = 0;
+	s64 rc;
 
-	/*
-	 * What we need do is pass it down for hardware
-	 * implementation to handle it.
-	 */
-	if (phb->eeh_ops && phb->eeh_ops->set_option)
-		ret = phb->eeh_ops->set_option(pe, option);
+	/* Sanity check on option */
+	switch (option) {
+	case EEH_OPT_DISABLE:
+		return -EPERM;
+	case EEH_OPT_ENABLE:
+		return 0;
+	case EEH_OPT_THAW_MMIO:
+		opt = OPAL_EEH_ACTION_CLEAR_FREEZE_MMIO;
+		break;
+	case EEH_OPT_THAW_DMA:
+		opt = OPAL_EEH_ACTION_CLEAR_FREEZE_DMA;
+		break;
+	case EEH_OPT_FREEZE_PE:
+		freeze_pe = true;
+		opt = OPAL_EEH_ACTION_SET_FREEZE_ALL;
+		break;
+	default:
+		pr_warn("%s: Invalid option %d\n", __func__, option);
+		return -EINVAL;
+	}
+
+	/* If PHB supports compound PE, to handle it */
+	if (freeze_pe) {
+		if (phb->freeze_pe) {
+			phb->freeze_pe(phb, pe->addr);
+		} else {
+			rc = opal_pci_eeh_freeze_set(phb->opal_id,
+						     pe->addr, opt);
+			if (rc != OPAL_SUCCESS) {
+				pr_warn("%s: Failure %lld freezing "
+					"PHB#%x-PE#%x\n",
+					__func__, rc,
+					phb->hose->global_number, pe->addr);
+				ret = -EIO;
+			}
+		}
+	} else {
+		if (phb->unfreeze_pe) {
+			ret = phb->unfreeze_pe(phb, pe->addr, opt);
+		} else {
+			rc = opal_pci_eeh_freeze_clear(phb->opal_id,
+						       pe->addr, opt);
+			if (rc != OPAL_SUCCESS) {
+				pr_warn("%s: Failure %lld enable %d "
+					"for PHB#%x-PE#%x\n",
+					__func__, rc, option,
+					phb->hose->global_number, pe->addr);
+				ret = -EIO;
+			}
+		}
+	}
 
 	return ret;
 }
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index d8808caf19f2..8043dee64a51 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -78,7 +78,6 @@ struct pnv_ioda_pe {
 /* IOC dependent EEH operations */
 #ifdef CONFIG_EEH
 struct pnv_eeh_ops {
-	int (*set_option)(struct eeh_pe *pe, int option);
 	int (*get_state)(struct eeh_pe *pe);
 	int (*reset)(struct eeh_pe *pe, int option);
 	int (*next_error)(struct eeh_pe **pe);
-- 
cgit v1.2.3


From 40ae5f693f6ada75e0f2680872dd0bf52bce22c4 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Mon, 16 Feb 2015 14:45:45 +1100
Subject: powerpc/powernv: Drop PHB operation get_state()

The patch drops PHB EEH operation get_state() and merges its logic
to eeh_ops::get_state().

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/eeh-ioda.c    | 170 +-----------------------
 arch/powerpc/platforms/powernv/eeh-powernv.c | 185 ++++++++++++++++++++++++---
 arch/powerpc/platforms/powernv/pci.h         |   1 -
 3 files changed, 170 insertions(+), 186 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index 349c0830f535..dc34c36805dc 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -46,173 +46,6 @@ static void ioda_eeh_phb_diag(struct eeh_pe *pe)
 			__func__, pe->phb->global_number, rc);
 }
 
-static int ioda_eeh_get_phb_state(struct eeh_pe *pe)
-{
-	struct pnv_phb *phb = pe->phb->private_data;
-	u8 fstate;
-	__be16 pcierr;
-	s64 rc;
-	int result = 0;
-
-	rc = opal_pci_eeh_freeze_status(phb->opal_id,
-					pe->addr,
-					&fstate,
-					&pcierr,
-					NULL);
-	if (rc != OPAL_SUCCESS) {
-		pr_warn("%s: Failure %lld getting PHB#%x state\n",
-			__func__, rc, phb->hose->global_number);
-		return EEH_STATE_NOT_SUPPORT;
-	}
-
-	/*
-	 * Check PHB state. If the PHB is frozen for the
-	 * first time, to dump the PHB diag-data.
-	 */
-	if (be16_to_cpu(pcierr) != OPAL_EEH_PHB_ERROR) {
-		result = (EEH_STATE_MMIO_ACTIVE  |
-			  EEH_STATE_DMA_ACTIVE   |
-			  EEH_STATE_MMIO_ENABLED |
-			  EEH_STATE_DMA_ENABLED);
-	} else if (!(pe->state & EEH_PE_ISOLATED)) {
-		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
-		ioda_eeh_phb_diag(pe);
-
-		if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
-			pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
-	}
-
-	return result;
-}
-
-static int ioda_eeh_get_pe_state(struct eeh_pe *pe)
-{
-	struct pnv_phb *phb = pe->phb->private_data;
-	u8 fstate;
-	__be16 pcierr;
-	s64 rc;
-	int result;
-
-	/*
-	 * We don't clobber hardware frozen state until PE
-	 * reset is completed. In order to keep EEH core
-	 * moving forward, we have to return operational
-	 * state during PE reset.
-	 */
-	if (pe->state & EEH_PE_RESET) {
-		result = (EEH_STATE_MMIO_ACTIVE  |
-			  EEH_STATE_DMA_ACTIVE   |
-			  EEH_STATE_MMIO_ENABLED |
-			  EEH_STATE_DMA_ENABLED);
-		return result;
-	}
-
-	/*
-	 * Fetch PE state from hardware. If the PHB
-	 * supports compound PE, let it handle that.
-	 */
-	if (phb->get_pe_state) {
-		fstate = phb->get_pe_state(phb, pe->addr);
-	} else {
-		rc = opal_pci_eeh_freeze_status(phb->opal_id,
-						pe->addr,
-						&fstate,
-						&pcierr,
-						NULL);
-		if (rc != OPAL_SUCCESS) {
-			pr_warn("%s: Failure %lld getting PHB#%x-PE%x state\n",
-				__func__, rc, phb->hose->global_number, pe->addr);
-			return EEH_STATE_NOT_SUPPORT;
-		}
-	}
-
-	/* Figure out state */
-	switch (fstate) {
-	case OPAL_EEH_STOPPED_NOT_FROZEN:
-		result = (EEH_STATE_MMIO_ACTIVE  |
-			  EEH_STATE_DMA_ACTIVE   |
-			  EEH_STATE_MMIO_ENABLED |
-			  EEH_STATE_DMA_ENABLED);
-		break;
-	case OPAL_EEH_STOPPED_MMIO_FREEZE:
-		result = (EEH_STATE_DMA_ACTIVE |
-			  EEH_STATE_DMA_ENABLED);
-		break;
-	case OPAL_EEH_STOPPED_DMA_FREEZE:
-		result = (EEH_STATE_MMIO_ACTIVE |
-			  EEH_STATE_MMIO_ENABLED);
-		break;
-	case OPAL_EEH_STOPPED_MMIO_DMA_FREEZE:
-		result = 0;
-		break;
-	case OPAL_EEH_STOPPED_RESET:
-		result = EEH_STATE_RESET_ACTIVE;
-		break;
-	case OPAL_EEH_STOPPED_TEMP_UNAVAIL:
-		result = EEH_STATE_UNAVAILABLE;
-		break;
-	case OPAL_EEH_STOPPED_PERM_UNAVAIL:
-		result = EEH_STATE_NOT_SUPPORT;
-		break;
-	default:
-		result = EEH_STATE_NOT_SUPPORT;
-		pr_warn("%s: Invalid PHB#%x-PE#%x state %x\n",
-			__func__, phb->hose->global_number,
-			pe->addr, fstate);
-	}
-
-	/*
-	 * If PHB supports compound PE, to freeze all
-	 * slave PEs for consistency.
-	 *
-	 * If the PE is switching to frozen state for the
-	 * first time, to dump the PHB diag-data.
-	 */
-	if (!(result & EEH_STATE_NOT_SUPPORT) &&
-	    !(result & EEH_STATE_UNAVAILABLE) &&
-	    !(result & EEH_STATE_MMIO_ACTIVE) &&
-	    !(result & EEH_STATE_DMA_ACTIVE)  &&
-	    !(pe->state & EEH_PE_ISOLATED)) {
-		if (phb->freeze_pe)
-			phb->freeze_pe(phb, pe->addr);
-
-		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
-		ioda_eeh_phb_diag(pe);
-
-		if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
-			pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
-	}
-
-	return result;
-}
-
-/**
- * ioda_eeh_get_state - Retrieve the state of PE
- * @pe: EEH PE
- *
- * The PE's state should be retrieved from the PEEV, PEST
- * IODA tables. Since the OPAL has exported the function
- * to do it, it'd better to use that.
- */
-static int ioda_eeh_get_state(struct eeh_pe *pe)
-{
-	struct pnv_phb *phb = pe->phb->private_data;
-
-	/* Sanity check on PE number. PHB PE should have 0 */
-	if (pe->addr < 0 ||
-	    pe->addr >= phb->ioda.total_pe) {
-		pr_warn("%s: PHB#%x-PE#%x out of range [0, %x]\n",
-			__func__, phb->hose->global_number,
-			pe->addr, phb->ioda.total_pe);
-		return EEH_STATE_NOT_SUPPORT;
-	}
-
-	if (pe->type & EEH_PE_PHB)
-		return ioda_eeh_get_phb_state(pe);
-
-	return ioda_eeh_get_pe_state(pe);
-}
-
 static s64 ioda_eeh_phb_poll(struct pnv_phb *phb)
 {
 	s64 rc = OPAL_HARDWARE;
@@ -759,7 +592,7 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 					break;
 
 				/* Frozen parent PE ? */
-				state = ioda_eeh_get_state(parent_pe);
+				state = eeh_ops->get_state(parent_pe, NULL);
 				if (state > 0 &&
 				    (state & active_flags) != active_flags)
 					*pe = parent_pe;
@@ -786,7 +619,6 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 }
 
 struct pnv_eeh_ops ioda_eeh_ops = {
-	.get_state		= ioda_eeh_get_state,
 	.reset			= ioda_eeh_reset,
 	.next_error		= ioda_eeh_next_error
 };
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 2429a23d4802..127ef0cc7c5b 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -478,6 +478,159 @@ static int pnv_eeh_get_pe_addr(struct eeh_pe *pe)
 	return pe->addr;
 }
 
+static void pnv_eeh_get_phb_diag(struct eeh_pe *pe)
+{
+	struct pnv_phb *phb = pe->phb->private_data;
+	s64 rc;
+
+	rc = opal_pci_get_phb_diag_data2(phb->opal_id, pe->data,
+					 PNV_PCI_DIAG_BUF_SIZE);
+	if (rc != OPAL_SUCCESS)
+		pr_warn("%s: Failure %lld getting PHB#%x diag-data\n",
+			__func__, rc, pe->phb->global_number);
+}
+
+static int pnv_eeh_get_phb_state(struct eeh_pe *pe)
+{
+	struct pnv_phb *phb = pe->phb->private_data;
+	u8 fstate;
+	__be16 pcierr;
+	s64 rc;
+	int result = 0;
+
+	rc = opal_pci_eeh_freeze_status(phb->opal_id,
+					pe->addr,
+					&fstate,
+					&pcierr,
+					NULL);
+	if (rc != OPAL_SUCCESS) {
+		pr_warn("%s: Failure %lld getting PHB#%x state\n",
+			__func__, rc, phb->hose->global_number);
+		return EEH_STATE_NOT_SUPPORT;
+	}
+
+	/*
+	 * Check PHB state. If the PHB is frozen for the
+	 * first time, to dump the PHB diag-data.
+	 */
+	if (be16_to_cpu(pcierr) != OPAL_EEH_PHB_ERROR) {
+		result = (EEH_STATE_MMIO_ACTIVE  |
+			  EEH_STATE_DMA_ACTIVE   |
+			  EEH_STATE_MMIO_ENABLED |
+			  EEH_STATE_DMA_ENABLED);
+	} else if (!(pe->state & EEH_PE_ISOLATED)) {
+		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+		pnv_eeh_get_phb_diag(pe);
+
+		if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
+			pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
+	}
+
+	return result;
+}
+
+static int pnv_eeh_get_pe_state(struct eeh_pe *pe)
+{
+	struct pnv_phb *phb = pe->phb->private_data;
+	u8 fstate;
+	__be16 pcierr;
+	s64 rc;
+	int result;
+
+	/*
+	 * We don't clobber hardware frozen state until PE
+	 * reset is completed. In order to keep EEH core
+	 * moving forward, we have to return operational
+	 * state during PE reset.
+	 */
+	if (pe->state & EEH_PE_RESET) {
+		result = (EEH_STATE_MMIO_ACTIVE  |
+			  EEH_STATE_DMA_ACTIVE   |
+			  EEH_STATE_MMIO_ENABLED |
+			  EEH_STATE_DMA_ENABLED);
+		return result;
+	}
+
+	/*
+	 * Fetch PE state from hardware. If the PHB
+	 * supports compound PE, let it handle that.
+	 */
+	if (phb->get_pe_state) {
+		fstate = phb->get_pe_state(phb, pe->addr);
+	} else {
+		rc = opal_pci_eeh_freeze_status(phb->opal_id,
+						pe->addr,
+						&fstate,
+						&pcierr,
+						NULL);
+		if (rc != OPAL_SUCCESS) {
+			pr_warn("%s: Failure %lld getting PHB#%x-PE%x state\n",
+				__func__, rc, phb->hose->global_number,
+				pe->addr);
+			return EEH_STATE_NOT_SUPPORT;
+		}
+	}
+
+	/* Figure out state */
+	switch (fstate) {
+	case OPAL_EEH_STOPPED_NOT_FROZEN:
+		result = (EEH_STATE_MMIO_ACTIVE  |
+			  EEH_STATE_DMA_ACTIVE   |
+			  EEH_STATE_MMIO_ENABLED |
+			  EEH_STATE_DMA_ENABLED);
+		break;
+	case OPAL_EEH_STOPPED_MMIO_FREEZE:
+		result = (EEH_STATE_DMA_ACTIVE |
+			  EEH_STATE_DMA_ENABLED);
+		break;
+	case OPAL_EEH_STOPPED_DMA_FREEZE:
+		result = (EEH_STATE_MMIO_ACTIVE |
+			  EEH_STATE_MMIO_ENABLED);
+		break;
+	case OPAL_EEH_STOPPED_MMIO_DMA_FREEZE:
+		result = 0;
+		break;
+	case OPAL_EEH_STOPPED_RESET:
+		result = EEH_STATE_RESET_ACTIVE;
+		break;
+	case OPAL_EEH_STOPPED_TEMP_UNAVAIL:
+		result = EEH_STATE_UNAVAILABLE;
+		break;
+	case OPAL_EEH_STOPPED_PERM_UNAVAIL:
+		result = EEH_STATE_NOT_SUPPORT;
+		break;
+	default:
+		result = EEH_STATE_NOT_SUPPORT;
+		pr_warn("%s: Invalid PHB#%x-PE#%x state %x\n",
+			__func__, phb->hose->global_number,
+			pe->addr, fstate);
+	}
+
+	/*
+	 * If PHB supports compound PE, to freeze all
+	 * slave PEs for consistency.
+	 *
+	 * If the PE is switching to frozen state for the
+	 * first time, to dump the PHB diag-data.
+	 */
+	if (!(result & EEH_STATE_NOT_SUPPORT) &&
+	    !(result & EEH_STATE_UNAVAILABLE) &&
+	    !(result & EEH_STATE_MMIO_ACTIVE) &&
+	    !(result & EEH_STATE_DMA_ACTIVE)  &&
+	    !(pe->state & EEH_PE_ISOLATED)) {
+		if (phb->freeze_pe)
+			phb->freeze_pe(phb, pe->addr);
+
+		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+		pnv_eeh_get_phb_diag(pe);
+
+		if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
+			pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
+	}
+
+	return result;
+}
+
 /**
  * pnv_eeh_get_state - Retrieve PE state
  * @pe: EEH PE
@@ -490,24 +643,24 @@ static int pnv_eeh_get_pe_addr(struct eeh_pe *pe)
  */
 static int pnv_eeh_get_state(struct eeh_pe *pe, int *delay)
 {
-	struct pci_controller *hose = pe->phb;
-	struct pnv_phb *phb = hose->private_data;
-	int ret = EEH_STATE_NOT_SUPPORT;
+	int ret;
 
-	if (phb->eeh_ops && phb->eeh_ops->get_state) {
-		ret = phb->eeh_ops->get_state(pe);
+	if (pe->type & EEH_PE_PHB)
+		ret = pnv_eeh_get_phb_state(pe);
+	else
+		ret = pnv_eeh_get_pe_state(pe);
 
-		/*
-		 * If the PE state is temporarily unavailable,
-		 * to inform the EEH core delay for default
-		 * period (1 second)
-		 */
-		if (delay) {
-			*delay = 0;
-			if (ret & EEH_STATE_UNAVAILABLE)
-				*delay = 1000;
-		}
-	}
+	if (!delay)
+		return ret;
+
+	/*
+	 * If the PE state is temporarily unavailable,
+	 * to inform the EEH core delay for default
+	 * period (1 second)
+	 */
+	*delay = 0;
+	if (ret & EEH_STATE_UNAVAILABLE)
+		*delay = 1000;
 
 	return ret;
 }
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 8043dee64a51..773a026bfee2 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -78,7 +78,6 @@ struct pnv_ioda_pe {
 /* IOC dependent EEH operations */
 #ifdef CONFIG_EEH
 struct pnv_eeh_ops {
-	int (*get_state)(struct eeh_pe *pe);
 	int (*reset)(struct eeh_pe *pe, int option);
 	int (*next_error)(struct eeh_pe **pe);
 };
-- 
cgit v1.2.3


From 2a485ad7c88ddfdf59bea12ece52b81adfd7c5a7 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Mon, 16 Feb 2015 14:45:46 +1100
Subject: powerpc/powernv: Drop PHB operation next_error()

The patch drops PHB EEH operation next_error() and merges its
logic to eeh_ops::next_error().

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/eeh-ioda.c    | 351 ---------------------------
 arch/powerpc/platforms/powernv/eeh-powernv.c | 334 ++++++++++++++++++++++++-
 arch/powerpc/platforms/powernv/pci.h         |   1 -
 3 files changed, 327 insertions(+), 359 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index dc34c36805dc..94d94b4811ad 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -34,18 +34,6 @@
 #include "powernv.h"
 #include "pci.h"
 
-static void ioda_eeh_phb_diag(struct eeh_pe *pe)
-{
-	struct pnv_phb *phb = pe->phb->private_data;
-	long rc;
-
-	rc = opal_pci_get_phb_diag_data2(phb->opal_id, pe->data,
-					 PNV_PCI_DIAG_BUF_SIZE);
-	if (rc != OPAL_SUCCESS)
-		pr_warn("%s: Failed to get diag-data for PHB#%x (%ld)\n",
-			__func__, pe->phb->global_number, rc);
-}
-
 static s64 ioda_eeh_phb_poll(struct pnv_phb *phb)
 {
 	s64 rc = OPAL_HARDWARE;
@@ -280,345 +268,6 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 	return ret;
 }
 
-static void ioda_eeh_hub_diag_common(struct OpalIoP7IOCErrorData *data)
-{
-	/* GEM */
-	if (data->gemXfir || data->gemRfir ||
-	    data->gemRirqfir || data->gemMask || data->gemRwof)
-		pr_info("  GEM: %016llx %016llx %016llx %016llx %016llx\n",
-			be64_to_cpu(data->gemXfir),
-			be64_to_cpu(data->gemRfir),
-			be64_to_cpu(data->gemRirqfir),
-			be64_to_cpu(data->gemMask),
-			be64_to_cpu(data->gemRwof));
-
-	/* LEM */
-	if (data->lemFir || data->lemErrMask ||
-	    data->lemAction0 || data->lemAction1 || data->lemWof)
-		pr_info("  LEM: %016llx %016llx %016llx %016llx %016llx\n",
-			be64_to_cpu(data->lemFir),
-			be64_to_cpu(data->lemErrMask),
-			be64_to_cpu(data->lemAction0),
-			be64_to_cpu(data->lemAction1),
-			be64_to_cpu(data->lemWof));
-}
-
-static void ioda_eeh_hub_diag(struct pci_controller *hose)
-{
-	struct pnv_phb *phb = hose->private_data;
-	struct OpalIoP7IOCErrorData *data = &phb->diag.hub_diag;
-	long rc;
-
-	rc = opal_pci_get_hub_diag_data(phb->hub_id, data, sizeof(*data));
-	if (rc != OPAL_SUCCESS) {
-		pr_warn("%s: Failed to get HUB#%llx diag-data (%ld)\n",
-			__func__, phb->hub_id, rc);
-		return;
-	}
-
-	switch (data->type) {
-	case OPAL_P7IOC_DIAG_TYPE_RGC:
-		pr_info("P7IOC diag-data for RGC\n\n");
-		ioda_eeh_hub_diag_common(data);
-		if (data->rgc.rgcStatus || data->rgc.rgcLdcp)
-			pr_info("  RGC: %016llx %016llx\n",
-				be64_to_cpu(data->rgc.rgcStatus),
-				be64_to_cpu(data->rgc.rgcLdcp));
-		break;
-	case OPAL_P7IOC_DIAG_TYPE_BI:
-		pr_info("P7IOC diag-data for BI %s\n\n",
-			data->bi.biDownbound ? "Downbound" : "Upbound");
-		ioda_eeh_hub_diag_common(data);
-		if (data->bi.biLdcp0 || data->bi.biLdcp1 ||
-		    data->bi.biLdcp2 || data->bi.biFenceStatus)
-			pr_info("  BI:  %016llx %016llx %016llx %016llx\n",
-				be64_to_cpu(data->bi.biLdcp0),
-				be64_to_cpu(data->bi.biLdcp1),
-				be64_to_cpu(data->bi.biLdcp2),
-				be64_to_cpu(data->bi.biFenceStatus));
-		break;
-	case OPAL_P7IOC_DIAG_TYPE_CI:
-		pr_info("P7IOC diag-data for CI Port %d\n\n",
-			data->ci.ciPort);
-		ioda_eeh_hub_diag_common(data);
-		if (data->ci.ciPortStatus || data->ci.ciPortLdcp)
-			pr_info("  CI:  %016llx %016llx\n",
-				be64_to_cpu(data->ci.ciPortStatus),
-				be64_to_cpu(data->ci.ciPortLdcp));
-		break;
-	case OPAL_P7IOC_DIAG_TYPE_MISC:
-		pr_info("P7IOC diag-data for MISC\n\n");
-		ioda_eeh_hub_diag_common(data);
-		break;
-	case OPAL_P7IOC_DIAG_TYPE_I2C:
-		pr_info("P7IOC diag-data for I2C\n\n");
-		ioda_eeh_hub_diag_common(data);
-		break;
-	default:
-		pr_warn("%s: Invalid type of HUB#%llx diag-data (%d)\n",
-			__func__, phb->hub_id, data->type);
-	}
-}
-
-static int ioda_eeh_get_pe(struct pci_controller *hose,
-			   u16 pe_no, struct eeh_pe **pe)
-{
-	struct pnv_phb *phb = hose->private_data;
-	struct pnv_ioda_pe *pnv_pe;
-	struct eeh_pe *dev_pe;
-	struct eeh_dev edev;
-
-	/*
-	 * If PHB supports compound PE, to fetch
-	 * the master PE because slave PE is invisible
-	 * to EEH core.
-	 */
-	pnv_pe = &phb->ioda.pe_array[pe_no];
-	if (pnv_pe->flags & PNV_IODA_PE_SLAVE) {
-		pnv_pe = pnv_pe->master;
-		WARN_ON(!pnv_pe ||
-			!(pnv_pe->flags & PNV_IODA_PE_MASTER));
-		pe_no = pnv_pe->pe_number;
-	}
-
-	/* Find the PE according to PE# */
-	memset(&edev, 0, sizeof(struct eeh_dev));
-	edev.phb = hose;
-	edev.pe_config_addr = pe_no;
-	dev_pe = eeh_pe_get(&edev);
-	if (!dev_pe)
-		return -EEXIST;
-
-	/* Freeze the (compound) PE */
-	*pe = dev_pe;
-	if (!(dev_pe->state & EEH_PE_ISOLATED))
-		phb->freeze_pe(phb, pe_no);
-
-	/*
-	 * At this point, we're sure the (compound) PE should
-	 * have been frozen. However, we still need poke until
-	 * hitting the frozen PE on top level.
-	 */
-	dev_pe = dev_pe->parent;
-	while (dev_pe && !(dev_pe->type & EEH_PE_PHB)) {
-		int ret;
-		int active_flags = (EEH_STATE_MMIO_ACTIVE |
-				    EEH_STATE_DMA_ACTIVE);
-
-		ret = eeh_ops->get_state(dev_pe, NULL);
-		if (ret <= 0 || (ret & active_flags) == active_flags) {
-			dev_pe = dev_pe->parent;
-			continue;
-		}
-
-		/* Frozen parent PE */
-		*pe = dev_pe;
-		if (!(dev_pe->state & EEH_PE_ISOLATED))
-			phb->freeze_pe(phb, dev_pe->addr);
-
-		/* Next one */
-		dev_pe = dev_pe->parent;
-	}
-
-	return 0;
-}
-
-/**
- * ioda_eeh_next_error - Retrieve next error for EEH core to handle
- * @pe: The affected PE
- *
- * The function is expected to be called by EEH core while it gets
- * special EEH event (without binding PE). The function calls to
- * OPAL APIs for next error to handle. The informational error is
- * handled internally by platform. However, the dead IOC, dead PHB,
- * fenced PHB and frozen PE should be handled by EEH core eventually.
- */
-static int ioda_eeh_next_error(struct eeh_pe **pe)
-{
-	struct pci_controller *hose;
-	struct pnv_phb *phb;
-	struct eeh_pe *phb_pe, *parent_pe;
-	__be64 frozen_pe_no;
-	__be16 err_type, severity;
-	int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
-	long rc;
-	int state, ret = EEH_NEXT_ERR_NONE;
-
-	/*
-	 * While running here, it's safe to purge the event queue.
-	 * And we should keep the cached OPAL notifier event sychronized
-	 * between the kernel and firmware.
-	 */
-	eeh_remove_event(NULL, false);
-	opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul);
-
-	list_for_each_entry(hose, &hose_list, list_node) {
-		/*
-		 * If the subordinate PCI buses of the PHB has been
-		 * removed or is exactly under error recovery, we
-		 * needn't take care of it any more.
-		 */
-		phb = hose->private_data;
-		phb_pe = eeh_phb_pe_get(hose);
-		if (!phb_pe || (phb_pe->state & EEH_PE_ISOLATED))
-			continue;
-
-		rc = opal_pci_next_error(phb->opal_id,
-				&frozen_pe_no, &err_type, &severity);
-
-		/* If OPAL API returns error, we needn't proceed */
-		if (rc != OPAL_SUCCESS) {
-			pr_devel("%s: Invalid return value on "
-				 "PHB#%x (0x%lx) from opal_pci_next_error",
-				 __func__, hose->global_number, rc);
-			continue;
-		}
-
-		/* If the PHB doesn't have error, stop processing */
-		if (be16_to_cpu(err_type) == OPAL_EEH_NO_ERROR ||
-		    be16_to_cpu(severity) == OPAL_EEH_SEV_NO_ERROR) {
-			pr_devel("%s: No error found on PHB#%x\n",
-				 __func__, hose->global_number);
-			continue;
-		}
-
-		/*
-		 * Processing the error. We're expecting the error with
-		 * highest priority reported upon multiple errors on the
-		 * specific PHB.
-		 */
-		pr_devel("%s: Error (%d, %d, %llu) on PHB#%x\n",
-			 __func__, be16_to_cpu(err_type), be16_to_cpu(severity),
-			 be64_to_cpu(frozen_pe_no), hose->global_number);
-		switch (be16_to_cpu(err_type)) {
-		case OPAL_EEH_IOC_ERROR:
-			if (be16_to_cpu(severity) == OPAL_EEH_SEV_IOC_DEAD) {
-				pr_err("EEH: dead IOC detected\n");
-				ret = EEH_NEXT_ERR_DEAD_IOC;
-			} else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) {
-				pr_info("EEH: IOC informative error "
-					"detected\n");
-				ioda_eeh_hub_diag(hose);
-				ret = EEH_NEXT_ERR_NONE;
-			}
-
-			break;
-		case OPAL_EEH_PHB_ERROR:
-			if (be16_to_cpu(severity) == OPAL_EEH_SEV_PHB_DEAD) {
-				*pe = phb_pe;
-				pr_err("EEH: dead PHB#%x detected, "
-				       "location: %s\n",
-				       hose->global_number,
-				       eeh_pe_loc_get(phb_pe));
-				ret = EEH_NEXT_ERR_DEAD_PHB;
-			} else if (be16_to_cpu(severity) ==
-						OPAL_EEH_SEV_PHB_FENCED) {
-				*pe = phb_pe;
-				pr_err("EEH: Fenced PHB#%x detected, "
-				       "location: %s\n",
-				       hose->global_number,
-				       eeh_pe_loc_get(phb_pe));
-				ret = EEH_NEXT_ERR_FENCED_PHB;
-			} else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) {
-				pr_info("EEH: PHB#%x informative error "
-					"detected, location: %s\n",
-					hose->global_number,
-					eeh_pe_loc_get(phb_pe));
-				ioda_eeh_phb_diag(phb_pe);
-				pnv_pci_dump_phb_diag_data(hose, phb_pe->data);
-				ret = EEH_NEXT_ERR_NONE;
-			}
-
-			break;
-		case OPAL_EEH_PE_ERROR:
-			/*
-			 * If we can't find the corresponding PE, we
-			 * just try to unfreeze.
-			 */
-			if (ioda_eeh_get_pe(hose,
-					    be64_to_cpu(frozen_pe_no), pe)) {
-				/* Try best to clear it */
-				pr_info("EEH: Clear non-existing PHB#%x-PE#%llx\n",
-					hose->global_number, frozen_pe_no);
-				pr_info("EEH: PHB location: %s\n",
-					eeh_pe_loc_get(phb_pe));
-				opal_pci_eeh_freeze_clear(phb->opal_id, frozen_pe_no,
-					OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
-				ret = EEH_NEXT_ERR_NONE;
-			} else if ((*pe)->state & EEH_PE_ISOLATED ||
-				   eeh_pe_passed(*pe)) {
-				ret = EEH_NEXT_ERR_NONE;
-			} else {
-				pr_err("EEH: Frozen PE#%x on PHB#%x detected\n",
-					(*pe)->addr, (*pe)->phb->global_number);
-				pr_err("EEH: PE location: %s, PHB location: %s\n",
-					eeh_pe_loc_get(*pe), eeh_pe_loc_get(phb_pe));
-				ret = EEH_NEXT_ERR_FROZEN_PE;
-			}
-
-			break;
-		default:
-			pr_warn("%s: Unexpected error type %d\n",
-				__func__, be16_to_cpu(err_type));
-		}
-
-		/*
-		 * EEH core will try recover from fenced PHB or
-		 * frozen PE. In the time for frozen PE, EEH core
-		 * enable IO path for that before collecting logs,
-		 * but it ruins the site. So we have to dump the
-		 * log in advance here.
-		 */
-		if ((ret == EEH_NEXT_ERR_FROZEN_PE  ||
-		    ret == EEH_NEXT_ERR_FENCED_PHB) &&
-		    !((*pe)->state & EEH_PE_ISOLATED)) {
-			eeh_pe_state_mark(*pe, EEH_PE_ISOLATED);
-			ioda_eeh_phb_diag(*pe);
-
-			if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
-				pnv_pci_dump_phb_diag_data((*pe)->phb,
-							   (*pe)->data);
-		}
-
-		/*
-		 * We probably have the frozen parent PE out there and
-		 * we need have to handle frozen parent PE firstly.
-		 */
-		if (ret == EEH_NEXT_ERR_FROZEN_PE) {
-			parent_pe = (*pe)->parent;
-			while (parent_pe) {
-				/* Hit the ceiling ? */
-				if (parent_pe->type & EEH_PE_PHB)
-					break;
-
-				/* Frozen parent PE ? */
-				state = eeh_ops->get_state(parent_pe, NULL);
-				if (state > 0 &&
-				    (state & active_flags) != active_flags)
-					*pe = parent_pe;
-
-				/* Next parent level */
-				parent_pe = parent_pe->parent;
-			}
-
-			/* We possibly migrate to another PE */
-			eeh_pe_state_mark(*pe, EEH_PE_ISOLATED);
-		}
-
-		/*
-		 * If we have no errors on the specific PHB or only
-		 * informative error there, we continue poking it.
-		 * Otherwise, we need actions to be taken by upper
-		 * layer.
-		 */
-		if (ret > EEH_NEXT_ERR_INF)
-			break;
-	}
-
-	return ret;
-}
-
 struct pnv_eeh_ops ioda_eeh_ops = {
 	.reset			= ioda_eeh_reset,
-	.next_error		= ioda_eeh_next_error
 };
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 127ef0cc7c5b..e51ac2dfde50 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -840,26 +840,346 @@ static int pnv_eeh_write_config(struct device_node *dn,
 	return pnv_pci_cfg_write(dn, where, size, val);
 }
 
+static void pnv_eeh_dump_hub_diag_common(struct OpalIoP7IOCErrorData *data)
+{
+	/* GEM */
+	if (data->gemXfir || data->gemRfir ||
+	    data->gemRirqfir || data->gemMask || data->gemRwof)
+		pr_info("  GEM: %016llx %016llx %016llx %016llx %016llx\n",
+			be64_to_cpu(data->gemXfir),
+			be64_to_cpu(data->gemRfir),
+			be64_to_cpu(data->gemRirqfir),
+			be64_to_cpu(data->gemMask),
+			be64_to_cpu(data->gemRwof));
+
+	/* LEM */
+	if (data->lemFir || data->lemErrMask ||
+	    data->lemAction0 || data->lemAction1 || data->lemWof)
+		pr_info("  LEM: %016llx %016llx %016llx %016llx %016llx\n",
+			be64_to_cpu(data->lemFir),
+			be64_to_cpu(data->lemErrMask),
+			be64_to_cpu(data->lemAction0),
+			be64_to_cpu(data->lemAction1),
+			be64_to_cpu(data->lemWof));
+}
+
+static void pnv_eeh_get_and_dump_hub_diag(struct pci_controller *hose)
+{
+	struct pnv_phb *phb = hose->private_data;
+	struct OpalIoP7IOCErrorData *data = &phb->diag.hub_diag;
+	long rc;
+
+	rc = opal_pci_get_hub_diag_data(phb->hub_id, data, sizeof(*data));
+	if (rc != OPAL_SUCCESS) {
+		pr_warn("%s: Failed to get HUB#%llx diag-data (%ld)\n",
+			__func__, phb->hub_id, rc);
+		return;
+	}
+
+	switch (data->type) {
+	case OPAL_P7IOC_DIAG_TYPE_RGC:
+		pr_info("P7IOC diag-data for RGC\n\n");
+		pnv_eeh_dump_hub_diag_common(data);
+		if (data->rgc.rgcStatus || data->rgc.rgcLdcp)
+			pr_info("  RGC: %016llx %016llx\n",
+				be64_to_cpu(data->rgc.rgcStatus),
+				be64_to_cpu(data->rgc.rgcLdcp));
+		break;
+	case OPAL_P7IOC_DIAG_TYPE_BI:
+		pr_info("P7IOC diag-data for BI %s\n\n",
+			data->bi.biDownbound ? "Downbound" : "Upbound");
+		pnv_eeh_dump_hub_diag_common(data);
+		if (data->bi.biLdcp0 || data->bi.biLdcp1 ||
+		    data->bi.biLdcp2 || data->bi.biFenceStatus)
+			pr_info("  BI:  %016llx %016llx %016llx %016llx\n",
+				be64_to_cpu(data->bi.biLdcp0),
+				be64_to_cpu(data->bi.biLdcp1),
+				be64_to_cpu(data->bi.biLdcp2),
+				be64_to_cpu(data->bi.biFenceStatus));
+		break;
+	case OPAL_P7IOC_DIAG_TYPE_CI:
+		pr_info("P7IOC diag-data for CI Port %d\n\n",
+			data->ci.ciPort);
+		pnv_eeh_dump_hub_diag_common(data);
+		if (data->ci.ciPortStatus || data->ci.ciPortLdcp)
+			pr_info("  CI:  %016llx %016llx\n",
+				be64_to_cpu(data->ci.ciPortStatus),
+				be64_to_cpu(data->ci.ciPortLdcp));
+		break;
+	case OPAL_P7IOC_DIAG_TYPE_MISC:
+		pr_info("P7IOC diag-data for MISC\n\n");
+		pnv_eeh_dump_hub_diag_common(data);
+		break;
+	case OPAL_P7IOC_DIAG_TYPE_I2C:
+		pr_info("P7IOC diag-data for I2C\n\n");
+		pnv_eeh_dump_hub_diag_common(data);
+		break;
+	default:
+		pr_warn("%s: Invalid type of HUB#%llx diag-data (%d)\n",
+			__func__, phb->hub_id, data->type);
+	}
+}
+
+static int pnv_eeh_get_pe(struct pci_controller *hose,
+			  u16 pe_no, struct eeh_pe **pe)
+{
+	struct pnv_phb *phb = hose->private_data;
+	struct pnv_ioda_pe *pnv_pe;
+	struct eeh_pe *dev_pe;
+	struct eeh_dev edev;
+
+	/*
+	 * If PHB supports compound PE, to fetch
+	 * the master PE because slave PE is invisible
+	 * to EEH core.
+	 */
+	pnv_pe = &phb->ioda.pe_array[pe_no];
+	if (pnv_pe->flags & PNV_IODA_PE_SLAVE) {
+		pnv_pe = pnv_pe->master;
+		WARN_ON(!pnv_pe ||
+			!(pnv_pe->flags & PNV_IODA_PE_MASTER));
+		pe_no = pnv_pe->pe_number;
+	}
+
+	/* Find the PE according to PE# */
+	memset(&edev, 0, sizeof(struct eeh_dev));
+	edev.phb = hose;
+	edev.pe_config_addr = pe_no;
+	dev_pe = eeh_pe_get(&edev);
+	if (!dev_pe)
+		return -EEXIST;
+
+	/* Freeze the (compound) PE */
+	*pe = dev_pe;
+	if (!(dev_pe->state & EEH_PE_ISOLATED))
+		phb->freeze_pe(phb, pe_no);
+
+	/*
+	 * At this point, we're sure the (compound) PE should
+	 * have been frozen. However, we still need poke until
+	 * hitting the frozen PE on top level.
+	 */
+	dev_pe = dev_pe->parent;
+	while (dev_pe && !(dev_pe->type & EEH_PE_PHB)) {
+		int ret;
+		int active_flags = (EEH_STATE_MMIO_ACTIVE |
+				    EEH_STATE_DMA_ACTIVE);
+
+		ret = eeh_ops->get_state(dev_pe, NULL);
+		if (ret <= 0 || (ret & active_flags) == active_flags) {
+			dev_pe = dev_pe->parent;
+			continue;
+		}
+
+		/* Frozen parent PE */
+		*pe = dev_pe;
+		if (!(dev_pe->state & EEH_PE_ISOLATED))
+			phb->freeze_pe(phb, dev_pe->addr);
+
+		/* Next one */
+		dev_pe = dev_pe->parent;
+	}
+
+	return 0;
+}
+
 /**
  * pnv_eeh_next_error - Retrieve next EEH error to handle
  * @pe: Affected PE
  *
- * Using OPAL API, to retrieve next EEH error for EEH core to handle
+ * The function is expected to be called by EEH core while it gets
+ * special EEH event (without binding PE). The function calls to
+ * OPAL APIs for next error to handle. The informational error is
+ * handled internally by platform. However, the dead IOC, dead PHB,
+ * fenced PHB and frozen PE should be handled by EEH core eventually.
  */
 static int pnv_eeh_next_error(struct eeh_pe **pe)
 {
 	struct pci_controller *hose;
-	struct pnv_phb *phb = NULL;
+	struct pnv_phb *phb;
+	struct eeh_pe *phb_pe, *parent_pe;
+	__be64 frozen_pe_no;
+	__be16 err_type, severity;
+	int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
+	long rc;
+	int state, ret = EEH_NEXT_ERR_NONE;
+
+	/*
+	 * While running here, it's safe to purge the event queue.
+	 * And we should keep the cached OPAL notifier event sychronized
+	 * between the kernel and firmware.
+	 */
+	eeh_remove_event(NULL, false);
+	opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul);
 
 	list_for_each_entry(hose, &hose_list, list_node) {
+		/*
+		 * If the subordinate PCI buses of the PHB has been
+		 * removed or is exactly under error recovery, we
+		 * needn't take care of it any more.
+		 */
 		phb = hose->private_data;
-		break;
-	}
+		phb_pe = eeh_phb_pe_get(hose);
+		if (!phb_pe || (phb_pe->state & EEH_PE_ISOLATED))
+			continue;
+
+		rc = opal_pci_next_error(phb->opal_id,
+					 &frozen_pe_no, &err_type, &severity);
+		if (rc != OPAL_SUCCESS) {
+			pr_devel("%s: Invalid return value on "
+				 "PHB#%x (0x%lx) from opal_pci_next_error",
+				 __func__, hose->global_number, rc);
+			continue;
+		}
+
+		/* If the PHB doesn't have error, stop processing */
+		if (be16_to_cpu(err_type) == OPAL_EEH_NO_ERROR ||
+		    be16_to_cpu(severity) == OPAL_EEH_SEV_NO_ERROR) {
+			pr_devel("%s: No error found on PHB#%x\n",
+				 __func__, hose->global_number);
+			continue;
+		}
 
-	if (phb && phb->eeh_ops->next_error)
-		return phb->eeh_ops->next_error(pe);
+		/*
+		 * Processing the error. We're expecting the error with
+		 * highest priority reported upon multiple errors on the
+		 * specific PHB.
+		 */
+		pr_devel("%s: Error (%d, %d, %llu) on PHB#%x\n",
+			__func__, be16_to_cpu(err_type),
+			be16_to_cpu(severity), be64_to_cpu(frozen_pe_no),
+			hose->global_number);
+		switch (be16_to_cpu(err_type)) {
+		case OPAL_EEH_IOC_ERROR:
+			if (be16_to_cpu(severity) == OPAL_EEH_SEV_IOC_DEAD) {
+				pr_err("EEH: dead IOC detected\n");
+				ret = EEH_NEXT_ERR_DEAD_IOC;
+			} else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) {
+				pr_info("EEH: IOC informative error "
+					"detected\n");
+				pnv_eeh_get_and_dump_hub_diag(hose);
+				ret = EEH_NEXT_ERR_NONE;
+			}
+
+			break;
+		case OPAL_EEH_PHB_ERROR:
+			if (be16_to_cpu(severity) == OPAL_EEH_SEV_PHB_DEAD) {
+				*pe = phb_pe;
+				pr_err("EEH: dead PHB#%x detected, "
+				       "location: %s\n",
+					hose->global_number,
+					eeh_pe_loc_get(phb_pe));
+				ret = EEH_NEXT_ERR_DEAD_PHB;
+			} else if (be16_to_cpu(severity) ==
+				   OPAL_EEH_SEV_PHB_FENCED) {
+				*pe = phb_pe;
+				pr_err("EEH: Fenced PHB#%x detected, "
+				       "location: %s\n",
+					hose->global_number,
+					eeh_pe_loc_get(phb_pe));
+				ret = EEH_NEXT_ERR_FENCED_PHB;
+			} else if (be16_to_cpu(severity) == OPAL_EEH_SEV_INF) {
+				pr_info("EEH: PHB#%x informative error "
+					"detected, location: %s\n",
+					hose->global_number,
+					eeh_pe_loc_get(phb_pe));
+				pnv_eeh_get_phb_diag(phb_pe);
+				pnv_pci_dump_phb_diag_data(hose, phb_pe->data);
+				ret = EEH_NEXT_ERR_NONE;
+			}
 
-	return -EEXIST;
+			break;
+		case OPAL_EEH_PE_ERROR:
+			/*
+			 * If we can't find the corresponding PE, we
+			 * just try to unfreeze.
+			 */
+			if (pnv_eeh_get_pe(hose,
+				be64_to_cpu(frozen_pe_no), pe)) {
+				/* Try best to clear it */
+				pr_info("EEH: Clear non-existing PHB#%x-PE#%llx\n",
+					hose->global_number, frozen_pe_no);
+				pr_info("EEH: PHB location: %s\n",
+					eeh_pe_loc_get(phb_pe));
+				opal_pci_eeh_freeze_clear(phb->opal_id,
+					frozen_pe_no,
+					OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+				ret = EEH_NEXT_ERR_NONE;
+			} else if ((*pe)->state & EEH_PE_ISOLATED ||
+				   eeh_pe_passed(*pe)) {
+				ret = EEH_NEXT_ERR_NONE;
+			} else {
+				pr_err("EEH: Frozen PE#%x "
+				       "on PHB#%x detected\n",
+				       (*pe)->addr,
+					(*pe)->phb->global_number);
+				pr_err("EEH: PE location: %s, "
+				       "PHB location: %s\n",
+				       eeh_pe_loc_get(*pe),
+				       eeh_pe_loc_get(phb_pe));
+				ret = EEH_NEXT_ERR_FROZEN_PE;
+			}
+
+			break;
+		default:
+			pr_warn("%s: Unexpected error type %d\n",
+				__func__, be16_to_cpu(err_type));
+		}
+
+		/*
+		 * EEH core will try recover from fenced PHB or
+		 * frozen PE. In the time for frozen PE, EEH core
+		 * enable IO path for that before collecting logs,
+		 * but it ruins the site. So we have to dump the
+		 * log in advance here.
+		 */
+		if ((ret == EEH_NEXT_ERR_FROZEN_PE  ||
+		    ret == EEH_NEXT_ERR_FENCED_PHB) &&
+		    !((*pe)->state & EEH_PE_ISOLATED)) {
+			eeh_pe_state_mark(*pe, EEH_PE_ISOLATED);
+			pnv_eeh_get_phb_diag(*pe);
+
+			if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
+				pnv_pci_dump_phb_diag_data((*pe)->phb,
+							   (*pe)->data);
+		}
+
+		/*
+		 * We probably have the frozen parent PE out there and
+		 * we need have to handle frozen parent PE firstly.
+		 */
+		if (ret == EEH_NEXT_ERR_FROZEN_PE) {
+			parent_pe = (*pe)->parent;
+			while (parent_pe) {
+				/* Hit the ceiling ? */
+				if (parent_pe->type & EEH_PE_PHB)
+					break;
+
+				/* Frozen parent PE ? */
+				state = eeh_ops->get_state(parent_pe, NULL);
+				if (state > 0 &&
+				    (state & active_flags) != active_flags)
+					*pe = parent_pe;
+
+				/* Next parent level */
+				parent_pe = parent_pe->parent;
+			}
+
+			/* We possibly migrate to another PE */
+			eeh_pe_state_mark(*pe, EEH_PE_ISOLATED);
+		}
+
+		/*
+		 * If we have no errors on the specific PHB or only
+		 * informative error there, we continue poking it.
+		 * Otherwise, we need actions to be taken by upper
+		 * layer.
+		 */
+		if (ret > EEH_NEXT_ERR_INF)
+			break;
+	}
+
+	return ret;
 }
 
 static int pnv_eeh_restore_config(struct device_node *dn)
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 773a026bfee2..5275d8928d94 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -79,7 +79,6 @@ struct pnv_ioda_pe {
 #ifdef CONFIG_EEH
 struct pnv_eeh_ops {
 	int (*reset)(struct eeh_pe *pe, int option);
-	int (*next_error)(struct eeh_pe **pe);
 };
 #endif /* CONFIG_EEH */
 
-- 
cgit v1.2.3


From cadf364d14f629119ba02c69f17a697d21880079 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Mon, 16 Feb 2015 14:45:47 +1100
Subject: powerpc/powernv: Drop PHB operation reset()

The patch drops PHB EEH operation reset() and merges its logic to
eeh_ops::reset().

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/eeh-ioda.c    | 235 ---------------------------
 arch/powerpc/platforms/powernv/eeh-powernv.c | 225 ++++++++++++++++++++++++-
 arch/powerpc/platforms/powernv/pci-ioda.c    |   4 +-
 arch/powerpc/platforms/powernv/pci.h         |   3 +-
 4 files changed, 223 insertions(+), 244 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index 94d94b4811ad..9fcfc45595ad 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -34,240 +34,5 @@
 #include "powernv.h"
 #include "pci.h"
 
-static s64 ioda_eeh_phb_poll(struct pnv_phb *phb)
-{
-	s64 rc = OPAL_HARDWARE;
-
-	while (1) {
-		rc = opal_pci_poll(phb->opal_id);
-		if (rc <= 0)
-			break;
-
-		if (system_state < SYSTEM_RUNNING)
-			udelay(1000 * rc);
-		else
-			msleep(rc);
-	}
-
-	return rc;
-}
-
-int ioda_eeh_phb_reset(struct pci_controller *hose, int option)
-{
-	struct pnv_phb *phb = hose->private_data;
-	s64 rc = OPAL_HARDWARE;
-
-	pr_debug("%s: Reset PHB#%x, option=%d\n",
-		 __func__, hose->global_number, option);
-
-	/* Issue PHB complete reset request */
-	if (option == EEH_RESET_FUNDAMENTAL ||
-	    option == EEH_RESET_HOT)
-		rc = opal_pci_reset(phb->opal_id,
-				OPAL_RESET_PHB_COMPLETE,
-				OPAL_ASSERT_RESET);
-	else if (option == EEH_RESET_DEACTIVATE)
-		rc = opal_pci_reset(phb->opal_id,
-				OPAL_RESET_PHB_COMPLETE,
-				OPAL_DEASSERT_RESET);
-	if (rc < 0)
-		goto out;
-
-	/*
-	 * Poll state of the PHB until the request is done
-	 * successfully. The PHB reset is usually PHB complete
-	 * reset followed by hot reset on root bus. So we also
-	 * need the PCI bus settlement delay.
-	 */
-	rc = ioda_eeh_phb_poll(phb);
-	if (option == EEH_RESET_DEACTIVATE) {
-		if (system_state < SYSTEM_RUNNING)
-			udelay(1000 * EEH_PE_RST_SETTLE_TIME);
-		else
-			msleep(EEH_PE_RST_SETTLE_TIME);
-	}
-out:
-	if (rc != OPAL_SUCCESS)
-		return -EIO;
-
-	return 0;
-}
-
-static int ioda_eeh_root_reset(struct pci_controller *hose, int option)
-{
-	struct pnv_phb *phb = hose->private_data;
-	s64 rc = OPAL_SUCCESS;
-
-	pr_debug("%s: Reset PHB#%x, option=%d\n",
-		 __func__, hose->global_number, option);
-
-	/*
-	 * During the reset deassert time, we needn't care
-	 * the reset scope because the firmware does nothing
-	 * for fundamental or hot reset during deassert phase.
-	 */
-	if (option == EEH_RESET_FUNDAMENTAL)
-		rc = opal_pci_reset(phb->opal_id,
-				OPAL_RESET_PCI_FUNDAMENTAL,
-				OPAL_ASSERT_RESET);
-	else if (option == EEH_RESET_HOT)
-		rc = opal_pci_reset(phb->opal_id,
-				OPAL_RESET_PCI_HOT,
-				OPAL_ASSERT_RESET);
-	else if (option == EEH_RESET_DEACTIVATE)
-		rc = opal_pci_reset(phb->opal_id,
-				OPAL_RESET_PCI_HOT,
-				OPAL_DEASSERT_RESET);
-	if (rc < 0)
-		goto out;
-
-	/* Poll state of the PHB until the request is done */
-	rc = ioda_eeh_phb_poll(phb);
-	if (option == EEH_RESET_DEACTIVATE)
-		msleep(EEH_PE_RST_SETTLE_TIME);
-out:
-	if (rc != OPAL_SUCCESS)
-		return -EIO;
-
-	return 0;
-}
-
-static int ioda_eeh_bridge_reset(struct pci_dev *dev, int option)
-
-{
-	struct device_node *dn = pci_device_to_OF_node(dev);
-	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
-	int aer = edev ? edev->aer_cap : 0;
-	u32 ctrl;
-
-	pr_debug("%s: Reset PCI bus %04x:%02x with option %d\n",
-		 __func__, pci_domain_nr(dev->bus),
-		 dev->bus->number, option);
-
-	switch (option) {
-	case EEH_RESET_FUNDAMENTAL:
-	case EEH_RESET_HOT:
-		/* Don't report linkDown event */
-		if (aer) {
-			eeh_ops->read_config(dn, aer + PCI_ERR_UNCOR_MASK,
-					     4, &ctrl);
-			ctrl |= PCI_ERR_UNC_SURPDN;
-                        eeh_ops->write_config(dn, aer + PCI_ERR_UNCOR_MASK,
-					      4, ctrl);
-                }
-
-		eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &ctrl);
-		ctrl |= PCI_BRIDGE_CTL_BUS_RESET;
-		eeh_ops->write_config(dn, PCI_BRIDGE_CONTROL, 2, ctrl);
-		msleep(EEH_PE_RST_HOLD_TIME);
-
-		break;
-	case EEH_RESET_DEACTIVATE:
-		eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &ctrl);
-		ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET;
-		eeh_ops->write_config(dn, PCI_BRIDGE_CONTROL, 2, ctrl);
-		msleep(EEH_PE_RST_SETTLE_TIME);
-
-		/* Continue reporting linkDown event */
-		if (aer) {
-			eeh_ops->read_config(dn, aer + PCI_ERR_UNCOR_MASK,
-					     4, &ctrl);
-			ctrl &= ~PCI_ERR_UNC_SURPDN;
-			eeh_ops->write_config(dn, aer + PCI_ERR_UNCOR_MASK,
-					      4, ctrl);
-		}
-
-		break;
-	}
-
-	return 0;
-}
-
-void pnv_pci_reset_secondary_bus(struct pci_dev *dev)
-{
-	struct pci_controller *hose;
-
-	if (pci_is_root_bus(dev->bus)) {
-		hose = pci_bus_to_host(dev->bus);
-		ioda_eeh_root_reset(hose, EEH_RESET_HOT);
-		ioda_eeh_root_reset(hose, EEH_RESET_DEACTIVATE);
-	} else {
-		ioda_eeh_bridge_reset(dev, EEH_RESET_HOT);
-		ioda_eeh_bridge_reset(dev, EEH_RESET_DEACTIVATE);
-	}
-}
-
-/**
- * ioda_eeh_reset - Reset the indicated PE
- * @pe: EEH PE
- * @option: reset option
- *
- * Do reset on the indicated PE. For PCI bus sensitive PE,
- * we need to reset the parent p2p bridge. The PHB has to
- * be reinitialized if the p2p bridge is root bridge. For
- * PCI device sensitive PE, we will try to reset the device
- * through FLR. For now, we don't have OPAL APIs to do HARD
- * reset yet, so all reset would be SOFT (HOT) reset.
- */
-static int ioda_eeh_reset(struct eeh_pe *pe, int option)
-{
-	struct pci_controller *hose = pe->phb;
-	struct pci_bus *bus;
-	int ret;
-
-	/*
-	 * For PHB reset, we always have complete reset. For those PEs whose
-	 * primary bus derived from root complex (root bus) or root port
-	 * (usually bus#1), we apply hot or fundamental reset on the root port.
-	 * For other PEs, we always have hot reset on the PE primary bus.
-	 *
-	 * Here, we have different design to pHyp, which always clear the
-	 * frozen state during PE reset. However, the good idea here from
-	 * benh is to keep frozen state before we get PE reset done completely
-	 * (until BAR restore). With the frozen state, HW drops illegal IO
-	 * or MMIO access, which can incur recrusive frozen PE during PE
-	 * reset. The side effect is that EEH core has to clear the frozen
-	 * state explicitly after BAR restore.
-	 */
-	if (pe->type & EEH_PE_PHB) {
-		ret = ioda_eeh_phb_reset(hose, option);
-	} else {
-		struct pnv_phb *phb;
-		s64 rc;
-
-		/*
-		 * The frozen PE might be caused by PAPR error injection
-		 * registers, which are expected to be cleared after hitting
-		 * frozen PE as stated in the hardware spec. Unfortunately,
-		 * that's not true on P7IOC. So we have to clear it manually
-		 * to avoid recursive EEH errors during recovery.
-		 */
-		phb = hose->private_data;
-		if (phb->model == PNV_PHB_MODEL_P7IOC &&
-		    (option == EEH_RESET_HOT ||
-		    option == EEH_RESET_FUNDAMENTAL)) {
-			rc = opal_pci_reset(phb->opal_id,
-					    OPAL_RESET_PHB_ERROR,
-					    OPAL_ASSERT_RESET);
-			if (rc != OPAL_SUCCESS) {
-				pr_warn("%s: Failure %lld clearing "
-					"error injection registers\n",
-					__func__, rc);
-				return -EIO;
-			}
-		}
-
-		bus = eeh_pe_bus_get(pe);
-		if (pci_is_root_bus(bus) ||
-		    pci_is_root_bus(bus->parent))
-			ret = ioda_eeh_root_reset(hose, option);
-		else
-			ret = ioda_eeh_bridge_reset(bus->self, option);
-	}
-
-	return ret;
-}
-
 struct pnv_eeh_ops ioda_eeh_ops = {
-	.reset			= ioda_eeh_reset,
 };
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index e51ac2dfde50..ede690630dfc 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -665,21 +665,236 @@ static int pnv_eeh_get_state(struct eeh_pe *pe, int *delay)
 	return ret;
 }
 
+static s64 pnv_eeh_phb_poll(struct pnv_phb *phb)
+{
+	s64 rc = OPAL_HARDWARE;
+
+	while (1) {
+		rc = opal_pci_poll(phb->opal_id);
+		if (rc <= 0)
+			break;
+
+		if (system_state < SYSTEM_RUNNING)
+			udelay(1000 * rc);
+		else
+			msleep(rc);
+	}
+
+	return rc;
+}
+
+int pnv_eeh_phb_reset(struct pci_controller *hose, int option)
+{
+	struct pnv_phb *phb = hose->private_data;
+	s64 rc = OPAL_HARDWARE;
+
+	pr_debug("%s: Reset PHB#%x, option=%d\n",
+		 __func__, hose->global_number, option);
+
+	/* Issue PHB complete reset request */
+	if (option == EEH_RESET_FUNDAMENTAL ||
+	    option == EEH_RESET_HOT)
+		rc = opal_pci_reset(phb->opal_id,
+				    OPAL_RESET_PHB_COMPLETE,
+				    OPAL_ASSERT_RESET);
+	else if (option == EEH_RESET_DEACTIVATE)
+		rc = opal_pci_reset(phb->opal_id,
+				    OPAL_RESET_PHB_COMPLETE,
+				    OPAL_DEASSERT_RESET);
+	if (rc < 0)
+		goto out;
+
+	/*
+	 * Poll state of the PHB until the request is done
+	 * successfully. The PHB reset is usually PHB complete
+	 * reset followed by hot reset on root bus. So we also
+	 * need the PCI bus settlement delay.
+	 */
+	rc = pnv_eeh_phb_poll(phb);
+	if (option == EEH_RESET_DEACTIVATE) {
+		if (system_state < SYSTEM_RUNNING)
+			udelay(1000 * EEH_PE_RST_SETTLE_TIME);
+		else
+			msleep(EEH_PE_RST_SETTLE_TIME);
+	}
+out:
+	if (rc != OPAL_SUCCESS)
+		return -EIO;
+
+	return 0;
+}
+
+static int pnv_eeh_root_reset(struct pci_controller *hose, int option)
+{
+	struct pnv_phb *phb = hose->private_data;
+	s64 rc = OPAL_HARDWARE;
+
+	pr_debug("%s: Reset PHB#%x, option=%d\n",
+		 __func__, hose->global_number, option);
+
+	/*
+	 * During the reset deassert time, we needn't care
+	 * the reset scope because the firmware does nothing
+	 * for fundamental or hot reset during deassert phase.
+	 */
+	if (option == EEH_RESET_FUNDAMENTAL)
+		rc = opal_pci_reset(phb->opal_id,
+				    OPAL_RESET_PCI_FUNDAMENTAL,
+				    OPAL_ASSERT_RESET);
+	else if (option == EEH_RESET_HOT)
+		rc = opal_pci_reset(phb->opal_id,
+				    OPAL_RESET_PCI_HOT,
+				    OPAL_ASSERT_RESET);
+	else if (option == EEH_RESET_DEACTIVATE)
+		rc = opal_pci_reset(phb->opal_id,
+				    OPAL_RESET_PCI_HOT,
+				    OPAL_DEASSERT_RESET);
+	if (rc < 0)
+		goto out;
+
+	/* Poll state of the PHB until the request is done */
+	rc = pnv_eeh_phb_poll(phb);
+	if (option == EEH_RESET_DEACTIVATE)
+		msleep(EEH_PE_RST_SETTLE_TIME);
+out:
+	if (rc != OPAL_SUCCESS)
+		return -EIO;
+
+	return 0;
+}
+
+static int pnv_eeh_bridge_reset(struct pci_dev *dev, int option)
+{
+	struct device_node *dn = pci_device_to_OF_node(dev);
+	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
+	int aer = edev ? edev->aer_cap : 0;
+	u32 ctrl;
+
+	pr_debug("%s: Reset PCI bus %04x:%02x with option %d\n",
+		 __func__, pci_domain_nr(dev->bus),
+		 dev->bus->number, option);
+
+	switch (option) {
+	case EEH_RESET_FUNDAMENTAL:
+	case EEH_RESET_HOT:
+		/* Don't report linkDown event */
+		if (aer) {
+			eeh_ops->read_config(dn, aer + PCI_ERR_UNCOR_MASK,
+					     4, &ctrl);
+			ctrl |= PCI_ERR_UNC_SURPDN;
+			eeh_ops->write_config(dn, aer + PCI_ERR_UNCOR_MASK,
+					      4, ctrl);
+		}
+
+		eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &ctrl);
+		ctrl |= PCI_BRIDGE_CTL_BUS_RESET;
+		eeh_ops->write_config(dn, PCI_BRIDGE_CONTROL, 2, ctrl);
+
+		msleep(EEH_PE_RST_HOLD_TIME);
+		break;
+	case EEH_RESET_DEACTIVATE:
+		eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &ctrl);
+		ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET;
+		eeh_ops->write_config(dn, PCI_BRIDGE_CONTROL, 2, ctrl);
+
+		msleep(EEH_PE_RST_SETTLE_TIME);
+
+		/* Continue reporting linkDown event */
+		if (aer) {
+			eeh_ops->read_config(dn, aer + PCI_ERR_UNCOR_MASK,
+					     4, &ctrl);
+			ctrl &= ~PCI_ERR_UNC_SURPDN;
+			eeh_ops->write_config(dn, aer + PCI_ERR_UNCOR_MASK,
+					      4, ctrl);
+		}
+
+		break;
+	}
+
+	return 0;
+}
+
+void pnv_pci_reset_secondary_bus(struct pci_dev *dev)
+{
+	struct pci_controller *hose;
+
+	if (pci_is_root_bus(dev->bus)) {
+		hose = pci_bus_to_host(dev->bus);
+		pnv_eeh_root_reset(hose, EEH_RESET_HOT);
+		pnv_eeh_root_reset(hose, EEH_RESET_DEACTIVATE);
+	} else {
+		pnv_eeh_bridge_reset(dev, EEH_RESET_HOT);
+		pnv_eeh_bridge_reset(dev, EEH_RESET_DEACTIVATE);
+	}
+}
+
 /**
  * pnv_eeh_reset - Reset the specified PE
  * @pe: EEH PE
  * @option: reset option
  *
- * Reset the specified PE
+ * Do reset on the indicated PE. For PCI bus sensitive PE,
+ * we need to reset the parent p2p bridge. The PHB has to
+ * be reinitialized if the p2p bridge is root bridge. For
+ * PCI device sensitive PE, we will try to reset the device
+ * through FLR. For now, we don't have OPAL APIs to do HARD
+ * reset yet, so all reset would be SOFT (HOT) reset.
  */
 static int pnv_eeh_reset(struct eeh_pe *pe, int option)
 {
 	struct pci_controller *hose = pe->phb;
-	struct pnv_phb *phb = hose->private_data;
-	int ret = -EEXIST;
+	struct pci_bus *bus;
+	int ret;
+
+	/*
+	 * For PHB reset, we always have complete reset. For those PEs whose
+	 * primary bus derived from root complex (root bus) or root port
+	 * (usually bus#1), we apply hot or fundamental reset on the root port.
+	 * For other PEs, we always have hot reset on the PE primary bus.
+	 *
+	 * Here, we have different design to pHyp, which always clear the
+	 * frozen state during PE reset. However, the good idea here from
+	 * benh is to keep frozen state before we get PE reset done completely
+	 * (until BAR restore). With the frozen state, HW drops illegal IO
+	 * or MMIO access, which can incur recrusive frozen PE during PE
+	 * reset. The side effect is that EEH core has to clear the frozen
+	 * state explicitly after BAR restore.
+	 */
+	if (pe->type & EEH_PE_PHB) {
+		ret = pnv_eeh_phb_reset(hose, option);
+	} else {
+		struct pnv_phb *phb;
+		s64 rc;
 
-	if (phb->eeh_ops && phb->eeh_ops->reset)
-		ret = phb->eeh_ops->reset(pe, option);
+		/*
+		 * The frozen PE might be caused by PAPR error injection
+		 * registers, which are expected to be cleared after hitting
+		 * frozen PE as stated in the hardware spec. Unfortunately,
+		 * that's not true on P7IOC. So we have to clear it manually
+		 * to avoid recursive EEH errors during recovery.
+		 */
+		phb = hose->private_data;
+		if (phb->model == PNV_PHB_MODEL_P7IOC &&
+		    (option == EEH_RESET_HOT ||
+		    option == EEH_RESET_FUNDAMENTAL)) {
+			rc = opal_pci_reset(phb->opal_id,
+					    OPAL_RESET_PHB_ERROR,
+					    OPAL_ASSERT_RESET);
+			if (rc != OPAL_SUCCESS) {
+				pr_warn("%s: Failure %lld clearing "
+					"error injection registers\n",
+					__func__, rc);
+				return -EIO;
+			}
+		}
+
+		bus = eeh_pe_bus_get(pe);
+		if (pci_is_root_bus(bus) ||
+			pci_is_root_bus(bus->parent))
+			ret = pnv_eeh_root_reset(hose, option);
+		else
+			ret = pnv_eeh_bridge_reset(bus->self, option);
+	}
 
 	return ret;
 }
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 6c9ff2b95119..4e21596bed48 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -2121,8 +2121,8 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	 */
 	if (is_kdump_kernel()) {
 		pr_info("  Issue PHB reset ...\n");
-		ioda_eeh_phb_reset(hose, EEH_RESET_FUNDAMENTAL);
-		ioda_eeh_phb_reset(hose, EEH_RESET_DEACTIVATE);
+		pnv_eeh_phb_reset(hose, EEH_RESET_FUNDAMENTAL);
+		pnv_eeh_phb_reset(hose, EEH_RESET_DEACTIVATE);
 	}
 
 	/* Remove M64 resource if we can't configure it successfully */
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 5275d8928d94..39f2ca37b19e 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -78,7 +78,6 @@ struct pnv_ioda_pe {
 /* IOC dependent EEH operations */
 #ifdef CONFIG_EEH
 struct pnv_eeh_ops {
-	int (*reset)(struct eeh_pe *pe, int option);
 };
 #endif /* CONFIG_EEH */
 
@@ -223,6 +222,6 @@ extern void pnv_pci_init_ioda2_phb(struct device_node *np);
 extern void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
 					__be64 *startp, __be64 *endp, bool rm);
 extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev);
-extern int ioda_eeh_phb_reset(struct pci_controller *hose, int option);
+extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option);
 
 #endif /* __POWERNV_PCI_H */
-- 
cgit v1.2.3


From 2f6cf7944833bf9c63b945799b460988aec30040 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Mon, 16 Feb 2015 14:45:48 +1100
Subject: powerpc/powernv: Remove unused file

The patch removes unused file eeh-ioda.c and updates makefile
accordingly. Besides, the definition of "struct pnv_eeh_ops" and
the instances are all removed. Until now, the chip layer of EEH
implementation for PowerNV platform is removed completely.

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/Makefile   |  2 +-
 arch/powerpc/platforms/powernv/eeh-ioda.c | 38 -------------------------------
 arch/powerpc/platforms/powernv/pci-ioda.c |  3 ---
 arch/powerpc/platforms/powernv/pci.h      | 13 -----------
 4 files changed, 1 insertion(+), 55 deletions(-)
 delete mode 100644 arch/powerpc/platforms/powernv/eeh-ioda.c

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index 6f3c5d33c3af..33e44f37212f 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -5,7 +5,7 @@ obj-y			+= opal-msglog.o opal-hmi.o opal-power.o
 
 obj-$(CONFIG_SMP)	+= smp.o subcore.o subcore-asm.o
 obj-$(CONFIG_PCI)	+= pci.o pci-p5ioc2.o pci-ioda.o
-obj-$(CONFIG_EEH)	+= eeh-ioda.o eeh-powernv.o
+obj-$(CONFIG_EEH)	+= eeh-powernv.o
 obj-$(CONFIG_PPC_SCOM)	+= opal-xscom.o
 obj-$(CONFIG_MEMORY_FAILURE)	+= opal-memory-errors.o
 obj-$(CONFIG_TRACEPOINTS)	+= opal-tracepoints.o
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
deleted file mode 100644
index 9fcfc45595ad..000000000000
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ /dev/null
@@ -1,38 +0,0 @@
-/*
- * The file intends to implement the functions needed by EEH, which is
- * built on IODA compliant chip. Actually, lots of functions related
- * to EEH would be built based on the OPAL APIs.
- *
- * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2013.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#include <linux/debugfs.h>
-#include <linux/delay.h>
-#include <linux/io.h>
-#include <linux/irq.h>
-#include <linux/kernel.h>
-#include <linux/msi.h>
-#include <linux/notifier.h>
-#include <linux/pci.h>
-#include <linux/string.h>
-
-#include <asm/eeh.h>
-#include <asm/eeh_event.h>
-#include <asm/io.h>
-#include <asm/iommu.h>
-#include <asm/msi_bitmap.h>
-#include <asm/opal.h>
-#include <asm/pci-bridge.h>
-#include <asm/ppc-pci.h>
-#include <asm/tce.h>
-
-#include "powernv.h"
-#include "pci.h"
-
-struct pnv_eeh_ops ioda_eeh_ops = {
-};
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 4e21596bed48..26fe09936935 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -2078,9 +2078,6 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	phb->get_pe_state = pnv_ioda_get_pe_state;
 	phb->freeze_pe = pnv_ioda_freeze_pe;
 	phb->unfreeze_pe = pnv_ioda_unfreeze_pe;
-#ifdef CONFIG_EEH
-	phb->eeh_ops = &ioda_eeh_ops;
-#endif
 
 	/* Setup RID -> PE mapping function */
 	phb->bdfn_to_pe = pnv_ioda_bdfn_to_pe;
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 39f2ca37b19e..18ae927f7819 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -75,12 +75,6 @@ struct pnv_ioda_pe {
 	struct list_head	list;
 };
 
-/* IOC dependent EEH operations */
-#ifdef CONFIG_EEH
-struct pnv_eeh_ops {
-};
-#endif /* CONFIG_EEH */
-
 #define PNV_PHB_FLAG_EEH	(1 << 0)
 
 struct pnv_phb {
@@ -94,10 +88,6 @@ struct pnv_phb {
 	int			initialized;
 	spinlock_t		lock;
 
-#ifdef CONFIG_EEH
-	struct pnv_eeh_ops	*eeh_ops;
-#endif
-
 #ifdef CONFIG_DEBUG_FS
 	int			has_dbgfs;
 	struct dentry		*dbgfs;
@@ -203,9 +193,6 @@ struct pnv_phb {
 };
 
 extern struct pci_ops pnv_pci_ops;
-#ifdef CONFIG_EEH
-extern struct pnv_eeh_ops ioda_eeh_ops;
-#endif
 
 void pnv_pci_dump_phb_diag_data(struct pci_controller *hose,
 				unsigned char *log_buff);
-- 
cgit v1.2.3


From f7618299b4ab425956099508cba7b3a39a056d87 Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.vnet.ibm.com>
Date: Fri, 6 Feb 2015 01:06:52 +0530
Subject: powerpc/powernv: Add pstore support on powernv

This patch extends pstore, a generic interface to platform dependent
persistent storage, support for powernv  platform to capture certain
useful information, during dying moments. Such support is already in
place for  pseries platform. This patch re-uses most of that code.

It is a common practice to compile kernels with both CONFIG_PPC_PSERIES=y
and CONFIG_PPC_POWERNV=y. The code in nvram_init_oops_partition() routine
still works as intended, as the caller is platform specific code which
passes the appropriate value for "rtas_partition_exists" parameter.
In all other places, where CONFIG_PPC_PSERIES or CONFIG_PPC_POWERNV
flag is used in this patchset, it is to reduce the kernel size in cases
where this flag is not set and doesn't have any impact logic wise.

Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/nvram_64.c              | 25 +++++++++++++++++++++++--
 arch/powerpc/platforms/powernv/opal-nvram.c | 10 ++++++++++
 2 files changed, 33 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index 42e5c6a9c214..293da889055b 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -127,6 +127,14 @@ static size_t oops_data_sz;
 static struct z_stream_s stream;
 
 #ifdef CONFIG_PSTORE
+#ifdef CONFIG_PPC_POWERNV
+static struct nvram_os_partition skiboot_partition = {
+	.name = "ibm,skiboot",
+	.index = -1,
+	.os_partition = false
+};
+#endif
+
 #ifdef CONFIG_PPC_PSERIES
 static struct nvram_os_partition of_config_partition = {
 	.name = "of-config",
@@ -476,6 +484,16 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
 		time->tv_sec = 0;
 		time->tv_nsec = 0;
 		break;
+#endif
+#ifdef CONFIG_PPC_POWERNV
+	case PSTORE_TYPE_PPC_OPAL:
+		sig = NVRAM_SIG_FW;
+		part = &skiboot_partition;
+		*type = PSTORE_TYPE_PPC_OPAL;
+		*id = PSTORE_TYPE_PPC_OPAL;
+		time->tv_sec = 0;
+		time->tv_nsec = 0;
+		break;
 #endif
 	default:
 		return 0;
@@ -552,8 +570,11 @@ static int nvram_pstore_init(void)
 {
 	int rc = 0;
 
-	nvram_type_ids[2] = PSTORE_TYPE_PPC_RTAS;
-	nvram_type_ids[3] = PSTORE_TYPE_PPC_OF;
+	if (machine_is(pseries)) {
+		nvram_type_ids[2] = PSTORE_TYPE_PPC_RTAS;
+		nvram_type_ids[3] = PSTORE_TYPE_PPC_OF;
+	} else
+		nvram_type_ids[2] = PSTORE_TYPE_PPC_OPAL;
 
 	nvram_pstore_info.buf = oops_data;
 	nvram_pstore_info.bufsize = oops_data_sz;
diff --git a/arch/powerpc/platforms/powernv/opal-nvram.c b/arch/powerpc/platforms/powernv/opal-nvram.c
index f9896fd5d04a..9db4398ded5d 100644
--- a/arch/powerpc/platforms/powernv/opal-nvram.c
+++ b/arch/powerpc/platforms/powernv/opal-nvram.c
@@ -16,6 +16,7 @@
 #include <linux/of.h>
 
 #include <asm/opal.h>
+#include <asm/nvram.h>
 #include <asm/machdep.h>
 
 static unsigned int nvram_size;
@@ -62,6 +63,15 @@ static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index)
 	return count;
 }
 
+static int __init opal_nvram_init_log_partitions(void)
+{
+	/* Scan nvram for partitions */
+	nvram_scan_partitions();
+	nvram_init_oops_partition(0);
+	return 0;
+}
+machine_arch_initcall(powernv, opal_nvram_init_log_partitions);
+
 void __init opal_nvram_init(void)
 {
 	struct device_node *np;
-- 
cgit v1.2.3


From 3532a741f80c3b9ca975006f93a4a477e07e2cb3 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Tue, 17 Mar 2015 16:15:03 +1100
Subject: powerpc/powernv: Use pci_dn, not device_node, in PCI config accessor

The PCI config accessors previously relied on device_node.  Unfortunately,
VFs don't have a corresponding device_node, so change the accessors to use
pci_dn instead.

[bhelgaas: changelog]
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/eeh-powernv.c | 14 +++++-
 arch/powerpc/platforms/powernv/pci.c         | 69 +++++++++++-----------------
 arch/powerpc/platforms/powernv/pci.h         |  4 +-
 3 files changed, 40 insertions(+), 47 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index ede690630dfc..8eac8c57ee86 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -1038,21 +1038,31 @@ static inline bool pnv_eeh_cfg_blocked(struct device_node *dn)
 static int pnv_eeh_read_config(struct device_node *dn,
 			       int where, int size, u32 *val)
 {
+	struct pci_dn *pdn = PCI_DN(dn);
+
+	if (!pdn)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
 	if (pnv_eeh_cfg_blocked(dn)) {
 		*val = 0xFFFFFFFF;
 		return PCIBIOS_SET_FAILED;
 	}
 
-	return pnv_pci_cfg_read(dn, where, size, val);
+	return pnv_pci_cfg_read(pdn, where, size, val);
 }
 
 static int pnv_eeh_write_config(struct device_node *dn,
 				int where, int size, u32 val)
 {
+	struct pci_dn *pdn = PCI_DN(dn);
+
+	if (!pdn)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
 	if (pnv_eeh_cfg_blocked(dn))
 		return PCIBIOS_SET_FAILED;
 
-	return pnv_pci_cfg_write(dn, where, size, val);
+	return pnv_pci_cfg_write(pdn, where, size, val);
 }
 
 static void pnv_eeh_dump_hub_diag_common(struct OpalIoP7IOCErrorData *data)
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 54323d6b5166..946aa3d62c3c 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -366,9 +366,9 @@ static void pnv_pci_handle_eeh_config(struct pnv_phb *phb, u32 pe_no)
 	spin_unlock_irqrestore(&phb->lock, flags);
 }
 
-static void pnv_pci_config_check_eeh(struct pnv_phb *phb,
-				     struct device_node *dn)
+static void pnv_pci_config_check_eeh(struct pci_dn *pdn)
 {
+	struct pnv_phb *phb = pdn->phb->private_data;
 	u8	fstate;
 	__be16	pcierr;
 	int	pe_no;
@@ -379,7 +379,7 @@ static void pnv_pci_config_check_eeh(struct pnv_phb *phb,
 	 * setup that yet. So all ER errors should be mapped to
 	 * reserved PE.
 	 */
-	pe_no = PCI_DN(dn)->pe_number;
+	pe_no = pdn->pe_number;
 	if (pe_no == IODA_INVALID_PE) {
 		if (phb->type == PNV_PHB_P5IOC2)
 			pe_no = 0;
@@ -407,8 +407,7 @@ static void pnv_pci_config_check_eeh(struct pnv_phb *phb,
 	}
 
 	cfg_dbg(" -> EEH check, bdfn=%04x PE#%d fstate=%x\n",
-		(PCI_DN(dn)->busno << 8) | (PCI_DN(dn)->devfn),
-		pe_no, fstate);
+		(pdn->busno << 8) | (pdn->devfn), pe_no, fstate);
 
 	/* Clear the frozen state if applicable */
 	if (fstate == OPAL_EEH_STOPPED_MMIO_FREEZE ||
@@ -425,10 +424,9 @@ static void pnv_pci_config_check_eeh(struct pnv_phb *phb,
 	}
 }
 
-int pnv_pci_cfg_read(struct device_node *dn,
+int pnv_pci_cfg_read(struct pci_dn *pdn,
 		     int where, int size, u32 *val)
 {
-	struct pci_dn *pdn = PCI_DN(dn);
 	struct pnv_phb *phb = pdn->phb->private_data;
 	u32 bdfn = (pdn->busno << 8) | pdn->devfn;
 	s64 rc;
@@ -462,10 +460,9 @@ int pnv_pci_cfg_read(struct device_node *dn,
 	return PCIBIOS_SUCCESSFUL;
 }
 
-int pnv_pci_cfg_write(struct device_node *dn,
+int pnv_pci_cfg_write(struct pci_dn *pdn,
 		      int where, int size, u32 val)
 {
-	struct pci_dn *pdn = PCI_DN(dn);
 	struct pnv_phb *phb = pdn->phb->private_data;
 	u32 bdfn = (pdn->busno << 8) | pdn->devfn;
 
@@ -489,18 +486,17 @@ int pnv_pci_cfg_write(struct device_node *dn,
 }
 
 #if CONFIG_EEH
-static bool pnv_pci_cfg_check(struct pci_controller *hose,
-			      struct device_node *dn)
+static bool pnv_pci_cfg_check(struct pci_dn *pdn)
 {
 	struct eeh_dev *edev = NULL;
-	struct pnv_phb *phb = hose->private_data;
+	struct pnv_phb *phb = pdn->phb->private_data;
 
 	/* EEH not enabled ? */
 	if (!(phb->flags & PNV_PHB_FLAG_EEH))
 		return true;
 
 	/* PE reset or device removed ? */
-	edev = of_node_to_eeh_dev(dn);
+	edev = pdn->edev;
 	if (edev) {
 		if (edev->pe &&
 		    (edev->pe->state & EEH_PE_CFG_BLOCKED))
@@ -513,8 +509,7 @@ static bool pnv_pci_cfg_check(struct pci_controller *hose,
 	return true;
 }
 #else
-static inline pnv_pci_cfg_check(struct pci_controller *hose,
-				struct device_node *dn)
+static inline pnv_pci_cfg_check(struct pci_dn *pdn)
 {
 	return true;
 }
@@ -524,32 +519,26 @@ static int pnv_pci_read_config(struct pci_bus *bus,
 			       unsigned int devfn,
 			       int where, int size, u32 *val)
 {
-	struct device_node *dn, *busdn = pci_bus_to_OF_node(bus);
 	struct pci_dn *pdn;
 	struct pnv_phb *phb;
-	bool found = false;
 	int ret;
 
 	*val = 0xFFFFFFFF;
-	for (dn = busdn->child; dn; dn = dn->sibling) {
-		pdn = PCI_DN(dn);
-		if (pdn && pdn->devfn == devfn) {
-			phb = pdn->phb->private_data;
-			found = true;
-			break;
-		}
-	}
+	pdn = pci_get_pdn_by_devfn(bus, devfn);
+	if (!pdn)
+		return PCIBIOS_DEVICE_NOT_FOUND;
 
-	if (!found || !pnv_pci_cfg_check(pdn->phb, dn))
+	if (!pnv_pci_cfg_check(pdn))
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
-	ret = pnv_pci_cfg_read(dn, where, size, val);
-	if (phb->flags & PNV_PHB_FLAG_EEH) {
+	ret = pnv_pci_cfg_read(pdn, where, size, val);
+	phb = pdn->phb->private_data;
+	if (phb->flags & PNV_PHB_FLAG_EEH && pdn->edev) {
 		if (*val == EEH_IO_ERROR_VALUE(size) &&
-		    eeh_dev_check_failure(of_node_to_eeh_dev(dn)))
+		    eeh_dev_check_failure(pdn->edev))
                         return PCIBIOS_DEVICE_NOT_FOUND;
 	} else {
-		pnv_pci_config_check_eeh(phb, dn);
+		pnv_pci_config_check_eeh(pdn);
 	}
 
 	return ret;
@@ -559,27 +548,21 @@ static int pnv_pci_write_config(struct pci_bus *bus,
 				unsigned int devfn,
 				int where, int size, u32 val)
 {
-	struct device_node *dn, *busdn = pci_bus_to_OF_node(bus);
 	struct pci_dn *pdn;
 	struct pnv_phb *phb;
-	bool found = false;
 	int ret;
 
-	for (dn = busdn->child; dn; dn = dn->sibling) {
-		pdn = PCI_DN(dn);
-		if (pdn && pdn->devfn == devfn) {
-			phb = pdn->phb->private_data;
-			found = true;
-			break;
-		}
-	}
+	pdn = pci_get_pdn_by_devfn(bus, devfn);
+	if (!pdn)
+		return PCIBIOS_DEVICE_NOT_FOUND;
 
-	if (!found || !pnv_pci_cfg_check(pdn->phb, dn))
+	if (!pnv_pci_cfg_check(pdn))
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
-	ret = pnv_pci_cfg_write(dn, where, size, val);
+	ret = pnv_pci_cfg_write(pdn, where, size, val);
+	phb = pdn->phb->private_data;
 	if (!(phb->flags & PNV_PHB_FLAG_EEH))
-		pnv_pci_config_check_eeh(phb, dn);
+		pnv_pci_config_check_eeh(pdn);
 
 	return ret;
 }
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 18ae927f7819..1f0cb66133a1 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -196,9 +196,9 @@ extern struct pci_ops pnv_pci_ops;
 
 void pnv_pci_dump_phb_diag_data(struct pci_controller *hose,
 				unsigned char *log_buff);
-int pnv_pci_cfg_read(struct device_node *dn,
+int pnv_pci_cfg_read(struct pci_dn *pdn,
 		     int where, int size, u32 *val);
-int pnv_pci_cfg_write(struct device_node *dn,
+int pnv_pci_cfg_write(struct pci_dn *pdn,
 		      int where, int size, u32 val);
 extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
 				      void *tce_mem, u64 tce_size,
-- 
cgit v1.2.3


From ff57b454ddb938d98d48d8df356357000fedc88c Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Tue, 17 Mar 2015 16:15:06 +1100
Subject: powerpc/eeh: Do probe on pci_dn

Originally, EEH core probes on device_node or pci_dev to populate
EEH devices and PEs, which conflicts with the fact: SRIOV VFs are
usually enabled and created by PF's driver and they don't have the
corresponding device_nodes. Instead, SRIOV VFs have dynamically
created pci_dn, which can be used for EEH probe.

The patch reworks EEH probe for PowerNV and pSeries platforms to
do probing based on pci_dn, instead of pci_dev or device_node any
more.

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/eeh.h               |  11 +-
 arch/powerpc/kernel/eeh.c                    |  63 ++++--------
 arch/powerpc/kernel/of_platform.c            |   2 +-
 arch/powerpc/kernel/pci-hotplug.c            |   2 +-
 arch/powerpc/platforms/powernv/eeh-powernv.c | 146 ++++++++++++++++++++-------
 arch/powerpc/platforms/pseries/eeh_pseries.c |  82 ++++++---------
 arch/powerpc/platforms/pseries/pci_dlpar.c   |   2 +-
 drivers/pci/hotplug/rpadlpar_core.c          |   2 +-
 8 files changed, 172 insertions(+), 138 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 2106f83da2d5..87797811808f 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -207,8 +207,7 @@ struct eeh_ops {
 	char *name;
 	int (*init)(void);
 	int (*post_init)(void);
-	void* (*of_probe)(struct device_node *dn, void *flag);
-	int (*dev_probe)(struct pci_dev *dev, void *flag);
+	void* (*probe)(struct pci_dn *pdn, void *data);
 	int (*set_option)(struct eeh_pe *pe, int option);
 	int (*get_pe_addr)(struct eeh_pe *pe);
 	int (*get_state)(struct eeh_pe *pe, int *state);
@@ -287,8 +286,8 @@ int __exit eeh_ops_unregister(const char *name);
 int eeh_check_failure(const volatile void __iomem *token);
 int eeh_dev_check_failure(struct eeh_dev *edev);
 void eeh_addr_cache_build(void);
-void eeh_add_device_early(struct device_node *);
-void eeh_add_device_tree_early(struct device_node *);
+void eeh_add_device_early(struct pci_dn *);
+void eeh_add_device_tree_early(struct pci_dn *);
 void eeh_add_device_late(struct pci_dev *);
 void eeh_add_device_tree_late(struct pci_bus *);
 void eeh_add_sysfs_files(struct pci_bus *);
@@ -346,9 +345,9 @@ static inline int eeh_check_failure(const volatile void __iomem *token)
 
 static inline void eeh_addr_cache_build(void) { }
 
-static inline void eeh_add_device_early(struct device_node *dn) { }
+static inline void eeh_add_device_early(struct pci_dn *pdn) { }
 
-static inline void eeh_add_device_tree_early(struct device_node *dn) { }
+static inline void eeh_add_device_tree_early(struct pci_dn *pdn) { }
 
 static inline void eeh_add_device_late(struct pci_dev *dev) { }
 
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 19a897c810be..9504c2f0bb54 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -969,7 +969,7 @@ static struct notifier_block eeh_reboot_nb = {
 int eeh_init(void)
 {
 	struct pci_controller *hose, *tmp;
-	struct device_node *phb;
+	struct pci_dn *pdn;
 	static int cnt = 0;
 	int ret = 0;
 
@@ -1004,20 +1004,9 @@ int eeh_init(void)
 		return ret;
 
 	/* Enable EEH for all adapters */
-	if (eeh_has_flag(EEH_PROBE_MODE_DEVTREE)) {
-		list_for_each_entry_safe(hose, tmp,
-			&hose_list, list_node) {
-			phb = hose->dn;
-			traverse_pci_devices(phb, eeh_ops->of_probe, NULL);
-		}
-	} else if (eeh_has_flag(EEH_PROBE_MODE_DEV)) {
-		list_for_each_entry_safe(hose, tmp,
-			&hose_list, list_node)
-			pci_walk_bus(hose->bus, eeh_ops->dev_probe, NULL);
-	} else {
-		pr_warn("%s: Invalid probe mode %x",
-			__func__, eeh_subsystem_flags);
-		return -EINVAL;
+	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+		pdn = hose->pci_data;
+		traverse_pci_dn(pdn, eeh_ops->probe, NULL);
 	}
 
 	/*
@@ -1043,7 +1032,7 @@ core_initcall_sync(eeh_init);
 
 /**
  * eeh_add_device_early - Enable EEH for the indicated device_node
- * @dn: device node for which to set up EEH
+ * @pdn: PCI device node for which to set up EEH
  *
  * This routine must be used to perform EEH initialization for PCI
  * devices that were added after system boot (e.g. hotplug, dlpar).
@@ -1053,44 +1042,41 @@ core_initcall_sync(eeh_init);
  * on the CEC architecture, type of the device, on earlier boot
  * command-line arguments & etc.
  */
-void eeh_add_device_early(struct device_node *dn)
+void eeh_add_device_early(struct pci_dn *pdn)
 {
 	struct pci_controller *phb;
+	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
 
-	/*
-	 * If we're doing EEH probe based on PCI device, we
-	 * would delay the probe until late stage because
-	 * the PCI device isn't available this moment.
-	 */
-	if (!eeh_has_flag(EEH_PROBE_MODE_DEVTREE))
-		return;
-
-	if (!of_node_to_eeh_dev(dn))
+	if (!edev)
 		return;
-	phb = of_node_to_eeh_dev(dn)->phb;
 
 	/* USB Bus children of PCI devices will not have BUID's */
-	if (NULL == phb || 0 == phb->buid)
+	phb = edev->phb;
+	if (NULL == phb ||
+	    (eeh_has_flag(EEH_PROBE_MODE_DEVTREE) && 0 == phb->buid))
 		return;
 
-	eeh_ops->of_probe(dn, NULL);
+	eeh_ops->probe(pdn, NULL);
 }
 
 /**
  * eeh_add_device_tree_early - Enable EEH for the indicated device
- * @dn: device node
+ * @pdn: PCI device node
  *
  * This routine must be used to perform EEH initialization for the
  * indicated PCI device that was added after system boot (e.g.
  * hotplug, dlpar).
  */
-void eeh_add_device_tree_early(struct device_node *dn)
+void eeh_add_device_tree_early(struct pci_dn *pdn)
 {
-	struct device_node *sib;
+	struct pci_dn *n;
+
+	if (!pdn)
+		return;
 
-	for_each_child_of_node(dn, sib)
-		eeh_add_device_tree_early(sib);
-	eeh_add_device_early(dn);
+	list_for_each_entry(n, &pdn->child_list, list)
+		eeh_add_device_tree_early(n);
+	eeh_add_device_early(pdn);
 }
 EXPORT_SYMBOL_GPL(eeh_add_device_tree_early);
 
@@ -1144,13 +1130,6 @@ void eeh_add_device_late(struct pci_dev *dev)
 	edev->pdev = dev;
 	dev->dev.archdata.edev = edev;
 
-	/*
-	 * We have to do the EEH probe here because the PCI device
-	 * hasn't been created yet in the early stage.
-	 */
-	if (eeh_has_flag(EEH_PROBE_MODE_DEV))
-		eeh_ops->dev_probe(dev, NULL);
-
 	eeh_addr_cache_insert_dev(dev);
 }
 
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
index 2f35a72642c6..b60a67d92ebd 100644
--- a/arch/powerpc/kernel/of_platform.c
+++ b/arch/powerpc/kernel/of_platform.c
@@ -72,7 +72,7 @@ static int of_pci_phb_probe(struct platform_device *dev)
 
 	/* Register devices with EEH */
 	if (dev->dev.of_node->child)
-		eeh_add_device_tree_early(dev->dev.of_node);
+		eeh_add_device_tree_early(PCI_DN(dev->dev.of_node));
 
 	/* Scan the bus */
 	pcibios_scan_phb(phb);
diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c
index 5b789177aa29..18d9575729a3 100644
--- a/arch/powerpc/kernel/pci-hotplug.c
+++ b/arch/powerpc/kernel/pci-hotplug.c
@@ -75,7 +75,7 @@ void pcibios_add_pci_devices(struct pci_bus * bus)
 	struct pci_dev *dev;
 	struct device_node *dn = pci_bus_to_OF_node(bus);
 
-	eeh_add_device_tree_early(dn);
+	eeh_add_device_tree_early(PCI_DN(dn));
 
 	mode = PCI_PROBE_NORMAL;
 	if (ppc_md.pci_probe_mode)
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 8eac8c57ee86..dcc524fe2a30 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -286,10 +286,82 @@ static int pnv_eeh_post_init(void)
 	return ret;
 }
 
+static int pnv_eeh_cap_start(struct pci_dn *pdn)
+{
+	u32 status;
+
+	if (!pdn)
+		return 0;
+
+	pnv_pci_cfg_read(pdn, PCI_STATUS, 2, &status);
+	if (!(status & PCI_STATUS_CAP_LIST))
+		return 0;
+
+	return PCI_CAPABILITY_LIST;
+}
+
+static int pnv_eeh_find_cap(struct pci_dn *pdn, int cap)
+{
+	int pos = pnv_eeh_cap_start(pdn);
+	int cnt = 48;   /* Maximal number of capabilities */
+	u32 id;
+
+	if (!pos)
+		return 0;
+
+	while (cnt--) {
+		pnv_pci_cfg_read(pdn, pos, 1, &pos);
+		if (pos < 0x40)
+			break;
+
+		pos &= ~3;
+		pnv_pci_cfg_read(pdn, pos + PCI_CAP_LIST_ID, 1, &id);
+		if (id == 0xff)
+			break;
+
+		/* Found */
+		if (id == cap)
+			return pos;
+
+		/* Next one */
+		pos += PCI_CAP_LIST_NEXT;
+	}
+
+	return 0;
+}
+
+static int pnv_eeh_find_ecap(struct pci_dn *pdn, int cap)
+{
+	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
+	u32 header;
+	int pos = 256, ttl = (4096 - 256) / 8;
+
+	if (!edev || !edev->pcie_cap)
+		return 0;
+	if (pnv_pci_cfg_read(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
+		return 0;
+	else if (!header)
+		return 0;
+
+	while (ttl-- > 0) {
+		if (PCI_EXT_CAP_ID(header) == cap && pos)
+			return pos;
+
+		pos = PCI_EXT_CAP_NEXT(header);
+		if (pos < 256)
+			break;
+
+		if (pnv_pci_cfg_read(pdn, pos, 4, &header) != PCIBIOS_SUCCESSFUL)
+			break;
+	}
+
+	return 0;
+}
+
 /**
- * pnv_eeh_dev_probe - Do probe on PCI device
- * @dev: PCI device
- * @flag: unused
+ * pnv_eeh_probe - Do probe on PCI device
+ * @pdn: PCI device node
+ * @data: unused
  *
  * When EEH module is installed during system boot, all PCI devices
  * are checked one by one to see if it supports EEH. The function
@@ -303,12 +375,12 @@ static int pnv_eeh_post_init(void)
  * was possiblly triggered by EEH core, the binding between EEH device
  * and the PCI device isn't built yet.
  */
-static int pnv_eeh_dev_probe(struct pci_dev *dev, void *flag)
+static void *pnv_eeh_probe(struct pci_dn *pdn, void *data)
 {
-	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pci_controller *hose = pdn->phb;
 	struct pnv_phb *phb = hose->private_data;
-	struct device_node *dn = pci_device_to_OF_node(dev);
-	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
+	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
+	uint32_t pcie_flags;
 	int ret;
 
 	/*
@@ -317,40 +389,42 @@ static int pnv_eeh_dev_probe(struct pci_dev *dev, void *flag)
 	 * the root bridge. So it's not reasonable to continue
 	 * the probing.
 	 */
-	if (!dn || !edev || edev->pe)
-		return 0;
+	if (!edev || edev->pe)
+		return NULL;
 
 	/* Skip for PCI-ISA bridge */
-	if ((dev->class >> 8) == PCI_CLASS_BRIDGE_ISA)
-		return 0;
+	if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_ISA)
+		return NULL;
 
 	/* Initialize eeh device */
-	edev->class_code = dev->class;
+	edev->class_code = pdn->class_code;
 	edev->mode	&= 0xFFFFFF00;
-	if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
+	edev->pcix_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_PCIX);
+	edev->pcie_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_EXP);
+	edev->aer_cap  = pnv_eeh_find_ecap(pdn, PCI_EXT_CAP_ID_ERR);
+	if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) {
 		edev->mode |= EEH_DEV_BRIDGE;
-	edev->pcix_cap = pci_find_capability(dev, PCI_CAP_ID_PCIX);
-	if (pci_is_pcie(dev)) {
-		edev->pcie_cap = pci_pcie_cap(dev);
-
-		if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT)
-			edev->mode |= EEH_DEV_ROOT_PORT;
-		else if (pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM)
-			edev->mode |= EEH_DEV_DS_PORT;
-
-		edev->aer_cap = pci_find_ext_capability(dev,
-							PCI_EXT_CAP_ID_ERR);
+		if (edev->pcie_cap) {
+			pnv_pci_cfg_read(pdn, edev->pcie_cap + PCI_EXP_FLAGS,
+					 2, &pcie_flags);
+			pcie_flags = (pcie_flags & PCI_EXP_FLAGS_TYPE) >> 4;
+			if (pcie_flags == PCI_EXP_TYPE_ROOT_PORT)
+				edev->mode |= EEH_DEV_ROOT_PORT;
+			else if (pcie_flags == PCI_EXP_TYPE_DOWNSTREAM)
+				edev->mode |= EEH_DEV_DS_PORT;
+		}
 	}
 
-	edev->config_addr	= ((dev->bus->number << 8) | dev->devfn);
-	edev->pe_config_addr	= phb->bdfn_to_pe(phb, dev->bus, dev->devfn & 0xff);
+	edev->config_addr    = (pdn->busno << 8) | (pdn->devfn);
+	edev->pe_config_addr = phb->ioda.pe_rmap[edev->config_addr];
 
 	/* Create PE */
 	ret = eeh_add_to_parent_pe(edev);
 	if (ret) {
-		pr_warn("%s: Can't add PCI dev %s to parent PE (%d)\n",
-			__func__, pci_name(dev), ret);
-		return ret;
+		pr_warn("%s: Can't add PCI dev %04x:%02x:%02x.%01x to parent PE (%d)\n",
+			__func__, hose->global_number, pdn->busno,
+			PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn), ret);
+		return NULL;
 	}
 
 	/*
@@ -369,8 +443,10 @@ static int pnv_eeh_dev_probe(struct pci_dev *dev, void *flag)
 	 * Broadcom Austin 4-ports NICs (14e4:1657)
 	 * Broadcom Shiner 2-ports 10G NICs (14e4:168e)
 	 */
-	if ((dev->vendor == PCI_VENDOR_ID_BROADCOM && dev->device == 0x1657) ||
-	    (dev->vendor == PCI_VENDOR_ID_BROADCOM && dev->device == 0x168e))
+	if ((pdn->vendor_id == PCI_VENDOR_ID_BROADCOM &&
+	     pdn->device_id == 0x1657) ||
+	    (pdn->vendor_id == PCI_VENDOR_ID_BROADCOM &&
+	     pdn->device_id == 0x168e))
 		edev->pe->state |= EEH_PE_CFG_RESTRICTED;
 
 	/*
@@ -380,7 +456,8 @@ static int pnv_eeh_dev_probe(struct pci_dev *dev, void *flag)
 	 * to PE reset.
 	 */
 	if (!edev->pe->bus)
-		edev->pe->bus = dev->bus;
+		edev->pe->bus = pci_find_bus(hose->global_number,
+					     pdn->busno);
 
 	/*
 	 * Enable EEH explicitly so that we will do EEH check
@@ -391,7 +468,7 @@ static int pnv_eeh_dev_probe(struct pci_dev *dev, void *flag)
 	/* Save memory bars */
 	eeh_save_bars(edev);
 
-	return 0;
+	return NULL;
 }
 
 /**
@@ -1432,8 +1509,7 @@ static struct eeh_ops pnv_eeh_ops = {
 	.name                   = "powernv",
 	.init                   = pnv_eeh_init,
 	.post_init              = pnv_eeh_post_init,
-	.of_probe               = NULL,
-	.dev_probe              = pnv_eeh_dev_probe,
+	.probe			= pnv_eeh_probe,
 	.set_option             = pnv_eeh_set_option,
 	.get_pe_addr            = pnv_eeh_get_pe_addr,
 	.get_state              = pnv_eeh_get_state,
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index a6c7e19f5eb3..a2946f72d5e7 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -118,9 +118,8 @@ static int pseries_eeh_init(void)
 	return 0;
 }
 
-static int pseries_eeh_cap_start(struct device_node *dn)
+static int pseries_eeh_cap_start(struct pci_dn *pdn)
 {
-	struct pci_dn *pdn = PCI_DN(dn);
 	u32 status;
 
 	if (!pdn)
@@ -134,10 +133,9 @@ static int pseries_eeh_cap_start(struct device_node *dn)
 }
 
 
-static int pseries_eeh_find_cap(struct device_node *dn, int cap)
+static int pseries_eeh_find_cap(struct pci_dn *pdn, int cap)
 {
-	struct pci_dn *pdn = PCI_DN(dn);
-	int pos = pseries_eeh_cap_start(dn);
+	int pos = pseries_eeh_cap_start(pdn);
 	int cnt = 48;	/* Maximal number of capabilities */
 	u32 id;
 
@@ -160,10 +158,9 @@ static int pseries_eeh_find_cap(struct device_node *dn, int cap)
 	return 0;
 }
 
-static int pseries_eeh_find_ecap(struct device_node *dn, int cap)
+static int pseries_eeh_find_ecap(struct pci_dn *pdn, int cap)
 {
-	struct pci_dn *pdn = PCI_DN(dn);
-	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
+	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
 	u32 header;
 	int pos = 256;
 	int ttl = (4096 - 256) / 8;
@@ -191,53 +188,44 @@ static int pseries_eeh_find_ecap(struct device_node *dn, int cap)
 }
 
 /**
- * pseries_eeh_of_probe - EEH probe on the given device
- * @dn: OF node
- * @flag: Unused
+ * pseries_eeh_probe - EEH probe on the given device
+ * @pdn: PCI device node
+ * @data: Unused
  *
  * When EEH module is installed during system boot, all PCI devices
  * are checked one by one to see if it supports EEH. The function
  * is introduced for the purpose.
  */
-static void *pseries_eeh_of_probe(struct device_node *dn, void *flag)
+static void *pseries_eeh_probe(struct pci_dn *pdn, void *data)
 {
 	struct eeh_dev *edev;
 	struct eeh_pe pe;
-	struct pci_dn *pdn = PCI_DN(dn);
-	const __be32 *classp, *vendorp, *devicep;
-	u32 class_code;
-	const __be32 *regs;
 	u32 pcie_flags;
 	int enable = 0;
 	int ret;
 
 	/* Retrieve OF node and eeh device */
-	edev = of_node_to_eeh_dev(dn);
-	if (edev->pe || !of_device_is_available(dn))
+	edev = pdn_to_eeh_dev(pdn);
+	if (!edev || edev->pe)
 		return NULL;
 
-	/* Retrieve class/vendor/device IDs */
-	classp = of_get_property(dn, "class-code", NULL);
-	vendorp = of_get_property(dn, "vendor-id", NULL);
-	devicep = of_get_property(dn, "device-id", NULL);
-
-	/* Skip for bad OF node or PCI-ISA bridge */
-	if (!classp || !vendorp || !devicep)
-		return NULL;
-	if (dn->type && !strcmp(dn->type, "isa"))
+	/* Check class/vendor/device IDs */
+	if (!pdn->vendor_id || !pdn->device_id || !pdn->class_code)
 		return NULL;
 
-	class_code = of_read_number(classp, 1);
+	/* Skip for PCI-ISA bridge */
+        if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_ISA)
+		return NULL;
 
 	/*
 	 * Update class code and mode of eeh device. We need
 	 * correctly reflects that current device is root port
 	 * or PCIe switch downstream port.
 	 */
-	edev->class_code = class_code;
-	edev->pcix_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_PCIX);
-	edev->pcie_cap = pseries_eeh_find_cap(dn, PCI_CAP_ID_EXP);
-	edev->aer_cap = pseries_eeh_find_ecap(dn, PCI_EXT_CAP_ID_ERR);
+	edev->class_code = pdn->class_code;
+	edev->pcix_cap = pseries_eeh_find_cap(pdn, PCI_CAP_ID_PCIX);
+	edev->pcie_cap = pseries_eeh_find_cap(pdn, PCI_CAP_ID_EXP);
+	edev->aer_cap = pseries_eeh_find_ecap(pdn, PCI_EXT_CAP_ID_ERR);
 	edev->mode &= 0xFFFFFF00;
 	if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) {
 		edev->mode |= EEH_DEV_BRIDGE;
@@ -252,24 +240,16 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag)
 		}
 	}
 
-	/* Retrieve the device address */
-	regs = of_get_property(dn, "reg", NULL);
-	if (!regs) {
-		pr_warn("%s: OF node property %s::reg not found\n",
-			__func__, dn->full_name);
-		return NULL;
-	}
-
 	/* Initialize the fake PE */
 	memset(&pe, 0, sizeof(struct eeh_pe));
 	pe.phb = edev->phb;
-	pe.config_addr = of_read_number(regs, 1);
+	pe.config_addr = (pdn->busno << 16) | (pdn->devfn << 8);
 
 	/* Enable EEH on the device */
 	ret = eeh_ops->set_option(&pe, EEH_OPT_ENABLE);
 	if (!ret) {
-		edev->config_addr = of_read_number(regs, 1);
 		/* Retrieve PE address */
+		edev->config_addr = (pdn->busno << 16) | (pdn->devfn << 8);
 		edev->pe_config_addr = eeh_ops->get_pe_addr(&pe);
 		pe.addr = edev->pe_config_addr;
 
@@ -285,16 +265,17 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag)
 			eeh_add_flag(EEH_ENABLED);
 			eeh_add_to_parent_pe(edev);
 
-			pr_debug("%s: EEH enabled on %s PHB#%d-PE#%x, config addr#%x\n",
-				__func__, dn->full_name, pe.phb->global_number,
-				pe.addr, pe.config_addr);
-		} else if (dn->parent && of_node_to_eeh_dev(dn->parent) &&
-			   (of_node_to_eeh_dev(dn->parent))->pe) {
+			pr_debug("%s: EEH enabled on %02x:%02x.%01x PHB#%d-PE#%x\n",
+				__func__, pdn->busno, PCI_SLOT(pdn->devfn),
+				PCI_FUNC(pdn->devfn), pe.phb->global_number,
+				pe.addr);
+		} else if (pdn->parent && pdn_to_eeh_dev(pdn->parent) &&
+			   (pdn_to_eeh_dev(pdn->parent))->pe) {
 			/* This device doesn't support EEH, but it may have an
 			 * EEH parent, in which case we mark it as supported.
 			 */
-			edev->config_addr = of_node_to_eeh_dev(dn->parent)->config_addr;
-			edev->pe_config_addr = of_node_to_eeh_dev(dn->parent)->pe_config_addr;
+			edev->config_addr = pdn_to_eeh_dev(pdn->parent)->config_addr;
+			edev->pe_config_addr = pdn_to_eeh_dev(pdn->parent)->pe_config_addr;
 			eeh_add_to_parent_pe(edev);
 		}
 	}
@@ -707,8 +688,7 @@ static int pseries_eeh_write_config(struct device_node *dn, int where, int size,
 static struct eeh_ops pseries_eeh_ops = {
 	.name			= "pseries",
 	.init			= pseries_eeh_init,
-	.of_probe		= pseries_eeh_of_probe,
-	.dev_probe		= NULL,
+	.probe			= pseries_eeh_probe,
 	.set_option		= pseries_eeh_set_option,
 	.get_pe_addr		= pseries_eeh_get_pe_addr,
 	.get_state		= pseries_eeh_get_state,
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 89e23811199c..f735f4fee48c 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -82,7 +82,7 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn)
 	eeh_dev_phb_init_dynamic(phb);
 
 	if (dn->child)
-		eeh_add_device_tree_early(dn);
+		eeh_add_device_tree_early(PCI_DN(dn));
 
 	pcibios_scan_phb(phb);
 	pcibios_finish_adding_to_bus(phb->bus);
diff --git a/drivers/pci/hotplug/rpadlpar_core.c b/drivers/pci/hotplug/rpadlpar_core.c
index 7660232ef460..e12bafdc42e0 100644
--- a/drivers/pci/hotplug/rpadlpar_core.c
+++ b/drivers/pci/hotplug/rpadlpar_core.c
@@ -146,7 +146,7 @@ static void dlpar_pci_add_bus(struct device_node *dn)
 	struct pci_controller *phb = pdn->phb;
 	struct pci_dev *dev = NULL;
 
-	eeh_add_device_tree_early(dn);
+	eeh_add_device_tree_early(pdn);
 
 	/* Add EADS device to PHB bus, adding new entry to bus->devices */
 	dev = of_create_pci_dev(dn, phb->bus, pdn->devfn);
-- 
cgit v1.2.3


From 0bd785873c6a6c9bd50d2ae19862f69ee5759fb9 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Tue, 17 Mar 2015 16:15:07 +1100
Subject: powerpc/eeh: Replace device_node with pci_dn in eeh_ops

There are 3 EEH operations whose arguments contain device_node:
read_config(), write_config() and restore_config(). The patch
replaces device_node with pci_dn.

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/eeh.h               |  6 +-
 arch/powerpc/kernel/eeh.c                    | 40 ++++++++------
 arch/powerpc/kernel/eeh_pe.c                 | 82 ++++++++++++++--------------
 arch/powerpc/platforms/powernv/eeh-powernv.c | 40 ++++++--------
 arch/powerpc/platforms/pseries/eeh_pseries.c | 16 ++----
 5 files changed, 87 insertions(+), 97 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 87797811808f..f847fb716653 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -217,10 +217,10 @@ struct eeh_ops {
 	int (*configure_bridge)(struct eeh_pe *pe);
 	int (*err_inject)(struct eeh_pe *pe, int type, int func,
 			  unsigned long addr, unsigned long mask);
-	int (*read_config)(struct device_node *dn, int where, int size, u32 *val);
-	int (*write_config)(struct device_node *dn, int where, int size, u32 val);
+	int (*read_config)(struct pci_dn *pdn, int where, int size, u32 *val);
+	int (*write_config)(struct pci_dn *pdn, int where, int size, u32 val);
 	int (*next_error)(struct eeh_pe **pe);
-	int (*restore_config)(struct device_node *dn);
+	int (*restore_config)(struct pci_dn *pdn);
 };
 
 extern int eeh_subsystem_flags;
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 9504c2f0bb54..1fd2566c87f1 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -164,30 +164,34 @@ __setup("eeh=", eeh_setup);
  */
 static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len)
 {
-	struct device_node *dn = eeh_dev_to_of_node(edev);
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 	u32 cfg;
 	int cap, i;
 	int n = 0, l = 0;
 	char buffer[128];
 
-	n += scnprintf(buf+n, len-n, "%s\n", dn->full_name);
-	pr_warn("EEH: of node=%s\n", dn->full_name);
+	n += scnprintf(buf+n, len-n, "%04x:%02x:%02x:%01x\n",
+		       edev->phb->global_number, pdn->busno,
+		       PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
+	pr_warn("EEH: of node=%04x:%02x:%02x:%01x\n",
+		edev->phb->global_number, pdn->busno,
+		PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
 
-	eeh_ops->read_config(dn, PCI_VENDOR_ID, 4, &cfg);
+	eeh_ops->read_config(pdn, PCI_VENDOR_ID, 4, &cfg);
 	n += scnprintf(buf+n, len-n, "dev/vend:%08x\n", cfg);
 	pr_warn("EEH: PCI device/vendor: %08x\n", cfg);
 
-	eeh_ops->read_config(dn, PCI_COMMAND, 4, &cfg);
+	eeh_ops->read_config(pdn, PCI_COMMAND, 4, &cfg);
 	n += scnprintf(buf+n, len-n, "cmd/stat:%x\n", cfg);
 	pr_warn("EEH: PCI cmd/status register: %08x\n", cfg);
 
 	/* Gather bridge-specific registers */
 	if (edev->mode & EEH_DEV_BRIDGE) {
-		eeh_ops->read_config(dn, PCI_SEC_STATUS, 2, &cfg);
+		eeh_ops->read_config(pdn, PCI_SEC_STATUS, 2, &cfg);
 		n += scnprintf(buf+n, len-n, "sec stat:%x\n", cfg);
 		pr_warn("EEH: Bridge secondary status: %04x\n", cfg);
 
-		eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &cfg);
+		eeh_ops->read_config(pdn, PCI_BRIDGE_CONTROL, 2, &cfg);
 		n += scnprintf(buf+n, len-n, "brdg ctl:%x\n", cfg);
 		pr_warn("EEH: Bridge control: %04x\n", cfg);
 	}
@@ -195,11 +199,11 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len)
 	/* Dump out the PCI-X command and status regs */
 	cap = edev->pcix_cap;
 	if (cap) {
-		eeh_ops->read_config(dn, cap, 4, &cfg);
+		eeh_ops->read_config(pdn, cap, 4, &cfg);
 		n += scnprintf(buf+n, len-n, "pcix-cmd:%x\n", cfg);
 		pr_warn("EEH: PCI-X cmd: %08x\n", cfg);
 
-		eeh_ops->read_config(dn, cap+4, 4, &cfg);
+		eeh_ops->read_config(pdn, cap+4, 4, &cfg);
 		n += scnprintf(buf+n, len-n, "pcix-stat:%x\n", cfg);
 		pr_warn("EEH: PCI-X status: %08x\n", cfg);
 	}
@@ -211,7 +215,7 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len)
 		pr_warn("EEH: PCI-E capabilities and status follow:\n");
 
 		for (i=0; i<=8; i++) {
-			eeh_ops->read_config(dn, cap+4*i, 4, &cfg);
+			eeh_ops->read_config(pdn, cap+4*i, 4, &cfg);
 			n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg);
 
 			if ((i % 4) == 0) {
@@ -238,7 +242,7 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len)
 		pr_warn("EEH: PCI-E AER capability register set follows:\n");
 
 		for (i=0; i<=13; i++) {
-			eeh_ops->read_config(dn, cap+4*i, 4, &cfg);
+			eeh_ops->read_config(pdn, cap+4*i, 4, &cfg);
 			n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg);
 
 			if ((i % 4) == 0) {
@@ -698,7 +702,7 @@ static void *eeh_disable_and_save_dev_state(void *data, void *userdata)
 static void *eeh_restore_dev_state(void *data, void *userdata)
 {
 	struct eeh_dev *edev = data;
-	struct device_node *dn = eeh_dev_to_of_node(edev);
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 	struct pci_dev *pdev = eeh_dev_to_pci_dev(edev);
 	struct pci_dev *dev = userdata;
 
@@ -706,8 +710,8 @@ static void *eeh_restore_dev_state(void *data, void *userdata)
 		return NULL;
 
 	/* Apply customization from firmware */
-	if (dn && eeh_ops->restore_config)
-		eeh_ops->restore_config(dn);
+	if (pdn && eeh_ops->restore_config)
+		eeh_ops->restore_config(pdn);
 
 	/* The caller should restore state for the specified device */
 	if (pdev != dev)
@@ -870,15 +874,15 @@ out:
  */
 void eeh_save_bars(struct eeh_dev *edev)
 {
+	struct pci_dn *pdn;
 	int i;
-	struct device_node *dn;
 
-	if (!edev)
+	pdn = eeh_dev_to_pdn(edev);
+	if (!pdn)
 		return;
-	dn = eeh_dev_to_of_node(edev);
 
 	for (i = 0; i < 16; i++)
-		eeh_ops->read_config(dn, i * 4, 4, &edev->config_space[i]);
+		eeh_ops->read_config(pdn, i * 4, 4, &edev->config_space[i]);
 
 	/*
 	 * For PCI bridges including root port, we need enable bus
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 1e4946c36f9e..209cd753bf46 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -291,27 +291,25 @@ struct eeh_pe *eeh_pe_get(struct eeh_dev *edev)
  */
 static struct eeh_pe *eeh_pe_get_parent(struct eeh_dev *edev)
 {
-	struct device_node *dn;
 	struct eeh_dev *parent;
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 
 	/*
 	 * It might have the case for the indirect parent
 	 * EEH device already having associated PE, but
 	 * the direct parent EEH device doesn't have yet.
 	 */
-	dn = edev->dn->parent;
-	while (dn) {
+	pdn = pdn ? pdn->parent : NULL;
+	while (pdn) {
 		/* We're poking out of PCI territory */
-		if (!PCI_DN(dn)) return NULL;
-
-		parent = of_node_to_eeh_dev(dn);
-		/* We're poking out of PCI territory */
-		if (!parent) return NULL;
+		parent = pdn_to_eeh_dev(pdn);
+		if (!parent)
+			return NULL;
 
 		if (parent->pe)
 			return parent->pe;
 
-		dn = dn->parent;
+		pdn = pdn->parent;
 	}
 
 	return NULL;
@@ -653,9 +651,9 @@ void eeh_pe_state_clear(struct eeh_pe *pe, int state)
  * blocked on normal path during the stage. So we need utilize
  * eeh operations, which is always permitted.
  */
-static void eeh_bridge_check_link(struct eeh_dev *edev,
-				  struct device_node *dn)
+static void eeh_bridge_check_link(struct eeh_dev *edev)
 {
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 	int cap;
 	uint32_t val;
 	int timeout = 0;
@@ -675,32 +673,32 @@ static void eeh_bridge_check_link(struct eeh_dev *edev,
 
 	/* Check slot status */
 	cap = edev->pcie_cap;
-	eeh_ops->read_config(dn, cap + PCI_EXP_SLTSTA, 2, &val);
+	eeh_ops->read_config(pdn, cap + PCI_EXP_SLTSTA, 2, &val);
 	if (!(val & PCI_EXP_SLTSTA_PDS)) {
 		pr_debug("  No card in the slot (0x%04x) !\n", val);
 		return;
 	}
 
 	/* Check power status if we have the capability */
-	eeh_ops->read_config(dn, cap + PCI_EXP_SLTCAP, 2, &val);
+	eeh_ops->read_config(pdn, cap + PCI_EXP_SLTCAP, 2, &val);
 	if (val & PCI_EXP_SLTCAP_PCP) {
-		eeh_ops->read_config(dn, cap + PCI_EXP_SLTCTL, 2, &val);
+		eeh_ops->read_config(pdn, cap + PCI_EXP_SLTCTL, 2, &val);
 		if (val & PCI_EXP_SLTCTL_PCC) {
 			pr_debug("  In power-off state, power it on ...\n");
 			val &= ~(PCI_EXP_SLTCTL_PCC | PCI_EXP_SLTCTL_PIC);
 			val |= (0x0100 & PCI_EXP_SLTCTL_PIC);
-			eeh_ops->write_config(dn, cap + PCI_EXP_SLTCTL, 2, val);
+			eeh_ops->write_config(pdn, cap + PCI_EXP_SLTCTL, 2, val);
 			msleep(2 * 1000);
 		}
 	}
 
 	/* Enable link */
-	eeh_ops->read_config(dn, cap + PCI_EXP_LNKCTL, 2, &val);
+	eeh_ops->read_config(pdn, cap + PCI_EXP_LNKCTL, 2, &val);
 	val &= ~PCI_EXP_LNKCTL_LD;
-	eeh_ops->write_config(dn, cap + PCI_EXP_LNKCTL, 2, val);
+	eeh_ops->write_config(pdn, cap + PCI_EXP_LNKCTL, 2, val);
 
 	/* Check link */
-	eeh_ops->read_config(dn, cap + PCI_EXP_LNKCAP, 4, &val);
+	eeh_ops->read_config(pdn, cap + PCI_EXP_LNKCAP, 4, &val);
 	if (!(val & PCI_EXP_LNKCAP_DLLLARC)) {
 		pr_debug("  No link reporting capability (0x%08x) \n", val);
 		msleep(1000);
@@ -713,7 +711,7 @@ static void eeh_bridge_check_link(struct eeh_dev *edev,
 		msleep(20);
 		timeout += 20;
 
-		eeh_ops->read_config(dn, cap + PCI_EXP_LNKSTA, 2, &val);
+		eeh_ops->read_config(pdn, cap + PCI_EXP_LNKSTA, 2, &val);
 		if (val & PCI_EXP_LNKSTA_DLLLA)
 			break;
 	}
@@ -728,9 +726,9 @@ static void eeh_bridge_check_link(struct eeh_dev *edev,
 #define BYTE_SWAP(OFF)	(8*((OFF)/4)+3-(OFF))
 #define SAVED_BYTE(OFF)	(((u8 *)(edev->config_space))[BYTE_SWAP(OFF)])
 
-static void eeh_restore_bridge_bars(struct eeh_dev *edev,
-				    struct device_node *dn)
+static void eeh_restore_bridge_bars(struct eeh_dev *edev)
 {
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 	int i;
 
 	/*
@@ -738,49 +736,49 @@ static void eeh_restore_bridge_bars(struct eeh_dev *edev,
 	 * Bus numbers and windows: 0x18 - 0x30
 	 */
 	for (i = 4; i < 13; i++)
-		eeh_ops->write_config(dn, i*4, 4, edev->config_space[i]);
+		eeh_ops->write_config(pdn, i*4, 4, edev->config_space[i]);
 	/* Rom: 0x38 */
-	eeh_ops->write_config(dn, 14*4, 4, edev->config_space[14]);
+	eeh_ops->write_config(pdn, 14*4, 4, edev->config_space[14]);
 
 	/* Cache line & Latency timer: 0xC 0xD */
-	eeh_ops->write_config(dn, PCI_CACHE_LINE_SIZE, 1,
+	eeh_ops->write_config(pdn, PCI_CACHE_LINE_SIZE, 1,
                 SAVED_BYTE(PCI_CACHE_LINE_SIZE));
-        eeh_ops->write_config(dn, PCI_LATENCY_TIMER, 1,
+        eeh_ops->write_config(pdn, PCI_LATENCY_TIMER, 1,
                 SAVED_BYTE(PCI_LATENCY_TIMER));
 	/* Max latency, min grant, interrupt ping and line: 0x3C */
-	eeh_ops->write_config(dn, 15*4, 4, edev->config_space[15]);
+	eeh_ops->write_config(pdn, 15*4, 4, edev->config_space[15]);
 
 	/* PCI Command: 0x4 */
-	eeh_ops->write_config(dn, PCI_COMMAND, 4, edev->config_space[1]);
+	eeh_ops->write_config(pdn, PCI_COMMAND, 4, edev->config_space[1]);
 
 	/* Check the PCIe link is ready */
-	eeh_bridge_check_link(edev, dn);
+	eeh_bridge_check_link(edev);
 }
 
-static void eeh_restore_device_bars(struct eeh_dev *edev,
-				    struct device_node *dn)
+static void eeh_restore_device_bars(struct eeh_dev *edev)
 {
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 	int i;
 	u32 cmd;
 
 	for (i = 4; i < 10; i++)
-		eeh_ops->write_config(dn, i*4, 4, edev->config_space[i]);
+		eeh_ops->write_config(pdn, i*4, 4, edev->config_space[i]);
 	/* 12 == Expansion ROM Address */
-	eeh_ops->write_config(dn, 12*4, 4, edev->config_space[12]);
+	eeh_ops->write_config(pdn, 12*4, 4, edev->config_space[12]);
 
-	eeh_ops->write_config(dn, PCI_CACHE_LINE_SIZE, 1,
+	eeh_ops->write_config(pdn, PCI_CACHE_LINE_SIZE, 1,
 		SAVED_BYTE(PCI_CACHE_LINE_SIZE));
-	eeh_ops->write_config(dn, PCI_LATENCY_TIMER, 1,
+	eeh_ops->write_config(pdn, PCI_LATENCY_TIMER, 1,
 		SAVED_BYTE(PCI_LATENCY_TIMER));
 
 	/* max latency, min grant, interrupt pin and line */
-	eeh_ops->write_config(dn, 15*4, 4, edev->config_space[15]);
+	eeh_ops->write_config(pdn, 15*4, 4, edev->config_space[15]);
 
 	/*
 	 * Restore PERR & SERR bits, some devices require it,
 	 * don't touch the other command bits
 	 */
-	eeh_ops->read_config(dn, PCI_COMMAND, 4, &cmd);
+	eeh_ops->read_config(pdn, PCI_COMMAND, 4, &cmd);
 	if (edev->config_space[1] & PCI_COMMAND_PARITY)
 		cmd |= PCI_COMMAND_PARITY;
 	else
@@ -789,7 +787,7 @@ static void eeh_restore_device_bars(struct eeh_dev *edev,
 		cmd |= PCI_COMMAND_SERR;
 	else
 		cmd &= ~PCI_COMMAND_SERR;
-	eeh_ops->write_config(dn, PCI_COMMAND, 4, cmd);
+	eeh_ops->write_config(pdn, PCI_COMMAND, 4, cmd);
 }
 
 /**
@@ -804,16 +802,16 @@ static void eeh_restore_device_bars(struct eeh_dev *edev,
 static void *eeh_restore_one_device_bars(void *data, void *flag)
 {
 	struct eeh_dev *edev = (struct eeh_dev *)data;
-	struct device_node *dn = eeh_dev_to_of_node(edev);
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 
 	/* Do special restore for bridges */
 	if (edev->mode & EEH_DEV_BRIDGE)
-		eeh_restore_bridge_bars(edev, dn);
+		eeh_restore_bridge_bars(edev);
 	else
-		eeh_restore_device_bars(edev, dn);
+		eeh_restore_device_bars(edev);
 
-	if (eeh_ops->restore_config)
-		eeh_ops->restore_config(dn);
+	if (eeh_ops->restore_config && pdn)
+		eeh_ops->restore_config(pdn);
 
 	return NULL;
 }
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index dcc524fe2a30..ce738ab3d5a9 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -842,8 +842,8 @@ out:
 
 static int pnv_eeh_bridge_reset(struct pci_dev *dev, int option)
 {
-	struct device_node *dn = pci_device_to_OF_node(dev);
-	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
+	struct pci_dn *pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn);
+	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
 	int aer = edev ? edev->aer_cap : 0;
 	u32 ctrl;
 
@@ -856,32 +856,32 @@ static int pnv_eeh_bridge_reset(struct pci_dev *dev, int option)
 	case EEH_RESET_HOT:
 		/* Don't report linkDown event */
 		if (aer) {
-			eeh_ops->read_config(dn, aer + PCI_ERR_UNCOR_MASK,
+			eeh_ops->read_config(pdn, aer + PCI_ERR_UNCOR_MASK,
 					     4, &ctrl);
 			ctrl |= PCI_ERR_UNC_SURPDN;
-			eeh_ops->write_config(dn, aer + PCI_ERR_UNCOR_MASK,
+			eeh_ops->write_config(pdn, aer + PCI_ERR_UNCOR_MASK,
 					      4, ctrl);
 		}
 
-		eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &ctrl);
+		eeh_ops->read_config(pdn, PCI_BRIDGE_CONTROL, 2, &ctrl);
 		ctrl |= PCI_BRIDGE_CTL_BUS_RESET;
-		eeh_ops->write_config(dn, PCI_BRIDGE_CONTROL, 2, ctrl);
+		eeh_ops->write_config(pdn, PCI_BRIDGE_CONTROL, 2, ctrl);
 
 		msleep(EEH_PE_RST_HOLD_TIME);
 		break;
 	case EEH_RESET_DEACTIVATE:
-		eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &ctrl);
+		eeh_ops->read_config(pdn, PCI_BRIDGE_CONTROL, 2, &ctrl);
 		ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET;
-		eeh_ops->write_config(dn, PCI_BRIDGE_CONTROL, 2, ctrl);
+		eeh_ops->write_config(pdn, PCI_BRIDGE_CONTROL, 2, ctrl);
 
 		msleep(EEH_PE_RST_SETTLE_TIME);
 
 		/* Continue reporting linkDown event */
 		if (aer) {
-			eeh_ops->read_config(dn, aer + PCI_ERR_UNCOR_MASK,
+			eeh_ops->read_config(pdn, aer + PCI_ERR_UNCOR_MASK,
 					     4, &ctrl);
 			ctrl &= ~PCI_ERR_UNC_SURPDN;
-			eeh_ops->write_config(dn, aer + PCI_ERR_UNCOR_MASK,
+			eeh_ops->write_config(pdn, aer + PCI_ERR_UNCOR_MASK,
 					      4, ctrl);
 		}
 
@@ -1099,9 +1099,9 @@ static int pnv_eeh_err_inject(struct eeh_pe *pe, int type, int func,
 	return 0;
 }
 
-static inline bool pnv_eeh_cfg_blocked(struct device_node *dn)
+static inline bool pnv_eeh_cfg_blocked(struct pci_dn *pdn)
 {
-	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
+	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
 
 	if (!edev || !edev->pe)
 		return false;
@@ -1112,15 +1112,13 @@ static inline bool pnv_eeh_cfg_blocked(struct device_node *dn)
 	return false;
 }
 
-static int pnv_eeh_read_config(struct device_node *dn,
+static int pnv_eeh_read_config(struct pci_dn *pdn,
 			       int where, int size, u32 *val)
 {
-	struct pci_dn *pdn = PCI_DN(dn);
-
 	if (!pdn)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
-	if (pnv_eeh_cfg_blocked(dn)) {
+	if (pnv_eeh_cfg_blocked(pdn)) {
 		*val = 0xFFFFFFFF;
 		return PCIBIOS_SET_FAILED;
 	}
@@ -1128,15 +1126,13 @@ static int pnv_eeh_read_config(struct device_node *dn,
 	return pnv_pci_cfg_read(pdn, where, size, val);
 }
 
-static int pnv_eeh_write_config(struct device_node *dn,
+static int pnv_eeh_write_config(struct pci_dn *pdn,
 				int where, int size, u32 val)
 {
-	struct pci_dn *pdn = PCI_DN(dn);
-
 	if (!pdn)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
-	if (pnv_eeh_cfg_blocked(dn))
+	if (pnv_eeh_cfg_blocked(pdn))
 		return PCIBIOS_SET_FAILED;
 
 	return pnv_pci_cfg_write(pdn, where, size, val);
@@ -1484,9 +1480,9 @@ static int pnv_eeh_next_error(struct eeh_pe **pe)
 	return ret;
 }
 
-static int pnv_eeh_restore_config(struct device_node *dn)
+static int pnv_eeh_restore_config(struct pci_dn *pdn)
 {
-	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
+	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
 	struct pnv_phb *phb;
 	s64 ret;
 
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index a2946f72d5e7..2039397cc75d 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -651,37 +651,29 @@ static int pseries_eeh_configure_bridge(struct eeh_pe *pe)
 
 /**
  * pseries_eeh_read_config - Read PCI config space
- * @dn: device node
+ * @pdn: PCI device node
  * @where: PCI address
  * @size: size to read
  * @val: return value
  *
  * Read config space from the speicifed device
  */
-static int pseries_eeh_read_config(struct device_node *dn, int where, int size, u32 *val)
+static int pseries_eeh_read_config(struct pci_dn *pdn, int where, int size, u32 *val)
 {
-	struct pci_dn *pdn;
-
-	pdn = PCI_DN(dn);
-
 	return rtas_read_config(pdn, where, size, val);
 }
 
 /**
  * pseries_eeh_write_config - Write PCI config space
- * @dn: device node
+ * @pdn: PCI device node
  * @where: PCI address
  * @size: size to write
  * @val: value to be written
  *
  * Write config space to the specified device
  */
-static int pseries_eeh_write_config(struct device_node *dn, int where, int size, u32 val)
+static int pseries_eeh_write_config(struct pci_dn *pdn, int where, int size, u32 val)
 {
-	struct pci_dn *pdn;
-
-	pdn = PCI_DN(dn);
-
 	return rtas_write_config(pdn, where, size, val);
 }
 
-- 
cgit v1.2.3


From 3f77df7f81526c932ef681eda56eeaa75d0617da Mon Sep 17 00:00:00 2001
From: Vasant Hegde <hegdevasant@linux.vnet.ibm.com>
Date: Fri, 13 Feb 2015 15:26:33 +0530
Subject: powerpc/powernv: Check image loaded or not before calling flash

Present code checks for update_flash_data in opal_flash_term_callback().
update_flash_data has been statically initialized to zero, and that
is the value of FLASH_IMG_READY. Also code update initialization happens
during subsys init.

So if reboot is issued before the subsys init stage then we endup displaying
"Flashing new firmware" message.. which may confuse end user.

This patch fixes above described issue by initializes update_flash status
to invalid state.

Reported-by: Sam Bobroff <sam.bobroff@au1.ibm.com>
Signed-off-by: Vasant Hegde <hegdevasant@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/opal-flash.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c
index 5c21d9c07f45..0ff07ff891f0 100644
--- a/arch/powerpc/platforms/powernv/opal-flash.c
+++ b/arch/powerpc/platforms/powernv/opal-flash.c
@@ -120,7 +120,11 @@ static struct image_header_t	image_header;
 static struct image_data_t	image_data;
 static struct validate_flash_t	validate_flash_data;
 static struct manage_flash_t	manage_flash_data;
-static struct update_flash_t	update_flash_data;
+
+/* Initialize update_flash_data status to No Operation */
+static struct update_flash_t	update_flash_data = {
+	.status = FLASH_NO_OP,
+};
 
 static DEFINE_MUTEX(image_data_mutex);
 
-- 
cgit v1.2.3


From 3bf57561d4dbd36ba45ce05656b0469bfdcc7ef2 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Fri, 14 Nov 2014 16:13:50 +1100
Subject: powerpc/powernv: Support OPAL requested heartbeat

If OPAL requests it, call it back via opal_poll_events() at a
regular interval. Some versions of OPAL on some machines require
this to operate some internal timeouts properly.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/opal.c | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 18fd4e71c9c1..70a6c14cacb6 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -23,6 +23,8 @@
 #include <linux/kobject.h>
 #include <linux/delay.h>
 #include <linux/memblock.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
 
 #include <asm/machdep.h>
 #include <asm/opal.h>
@@ -58,6 +60,7 @@ static struct atomic_notifier_head opal_msg_notifier_head[OPAL_MSG_TYPE_MAX];
 static DEFINE_SPINLOCK(opal_notifier_lock);
 static uint64_t last_notified_mask = 0x0ul;
 static atomic_t opal_notifier_hold = ATOMIC_INIT(0);
+static uint32_t opal_heartbeat;
 
 static void opal_reinit_cores(void)
 {
@@ -741,6 +744,29 @@ static void __init opal_irq_init(struct device_node *dn)
 	}
 }
 
+static int kopald(void *unused)
+{
+	set_freezable();
+	do {
+		try_to_freeze();
+		opal_poll_events(NULL);
+		msleep_interruptible(opal_heartbeat);
+	} while (!kthread_should_stop());
+
+	return 0;
+}
+
+static void opal_init_heartbeat(void)
+{
+	/* Old firwmware, we assume the HVC heartbeat is sufficient */
+	if (of_property_read_u32(opal_node, "ibm,heartbeat-ms",
+				 &opal_heartbeat) != 0)
+		opal_heartbeat = 0;
+
+	if (opal_heartbeat)
+		kthread_run(kopald, NULL, "kopald");
+}
+
 static int __init opal_init(void)
 {
 	struct device_node *np, *consoles;
@@ -769,6 +795,9 @@ static int __init opal_init(void)
 	/* Create i2c platform devices */
 	opal_i2c_create_devs();
 
+	/* Setup a heatbeat thread if requested by OPAL */
+	opal_init_heartbeat();
+
 	/* Find all OPAL interrupts and request them */
 	opal_irq_init(opal_node);
 
@@ -791,6 +820,7 @@ static int __init opal_init(void)
 		opal_msglog_init();
 	}
 
+	/* Initialize OPAL IPMI backend */
 	opal_ipmi_init(opal_node);
 
 	return 0;
-- 
cgit v1.2.3


From 792f96e9a769b799a2944e9369e4ea1e467135b2 Mon Sep 17 00:00:00 2001
From: Neelesh Gupta <neelegup@linux.vnet.ibm.com>
Date: Wed, 11 Feb 2015 11:57:06 +0530
Subject: powerpc/powernv: Fix the overflow of OPAL message notifiers head
 array

Fixes the condition check of incoming message type which can
otherwise shoot beyond the message notifiers head array.

Signed-off-by: Neelesh Gupta <neelegup@linux.vnet.ibm.com>
Reviewed-by: Vasant Hegde <hegdevasant@linux.vnet.ibm.com>
Reviewed-by: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/opal.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 70a6c14cacb6..b0021ac3e0a8 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -308,16 +308,12 @@ void opal_notifier_disable(void)
 int opal_message_notifier_register(enum OpalMessageType msg_type,
 					struct notifier_block *nb)
 {
-	if (!nb) {
-		pr_warning("%s: Invalid argument (%p)\n",
-			   __func__, nb);
-		return -EINVAL;
-	}
-	if (msg_type > OPAL_MSG_TYPE_MAX) {
-		pr_warning("%s: Invalid message type argument (%d)\n",
+	if (!nb || msg_type >= OPAL_MSG_TYPE_MAX) {
+		pr_warning("%s: Invalid arguments, msg_type:%d\n",
 			   __func__, msg_type);
 		return -EINVAL;
 	}
+
 	return atomic_notifier_chain_register(
 				&opal_msg_notifier_head[msg_type], nb);
 }
@@ -354,7 +350,7 @@ static void opal_handle_message(void)
 	type = be32_to_cpu(msg.msg_type);
 
 	/* Sanity check */
-	if (type > OPAL_MSG_TYPE_MAX) {
+	if (type >= OPAL_MSG_TYPE_MAX) {
 		pr_warning("%s: Unknown message type: %u\n", __func__, type);
 		return;
 	}
-- 
cgit v1.2.3


From b921e90260cec1e04988bb3763491de885b67b51 Mon Sep 17 00:00:00 2001
From: Neelesh Gupta <neelegup@linux.vnet.ibm.com>
Date: Wed, 11 Feb 2015 11:57:23 +0530
Subject: powerpc/powernv: Add OPAL message notifier unregister function

Provide an unregister interface for the opal message notifiers
to be called when not needed like during driver unload/remove.

Signed-off-by: Neelesh Gupta <neelegup@linux.vnet.ibm.com>
Reviewed-by: Vasant Hegde <hegdevasant@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/opal.h       | 2 ++
 arch/powerpc/platforms/powernv/opal.c | 7 +++++++
 2 files changed, 9 insertions(+)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 9ee0a30a02ce..4ea21ea6a999 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -948,6 +948,8 @@ extern int opal_notifier_unregister(struct notifier_block *nb);
 
 extern int opal_message_notifier_register(enum OpalMessageType msg_type,
 						struct notifier_block *nb);
+extern int opal_message_notifier_unregister(enum OpalMessageType msg_type,
+					    struct notifier_block *nb);
 extern void opal_notifier_enable(void);
 extern void opal_notifier_disable(void);
 extern void opal_notifier_update_evt(uint64_t evt_mask, uint64_t evt_val);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index b0021ac3e0a8..8b3834a095f7 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -318,6 +318,13 @@ int opal_message_notifier_register(enum OpalMessageType msg_type,
 				&opal_msg_notifier_head[msg_type], nb);
 }
 
+int opal_message_notifier_unregister(enum OpalMessageType msg_type,
+				     struct notifier_block *nb)
+{
+	return atomic_notifier_chain_unregister(
+			&opal_msg_notifier_head[msg_type], nb);
+}
+
 static void opal_message_do_notify(uint32_t msg_type, void *msg)
 {
 	/* notify subscribers */
-- 
cgit v1.2.3


From 605f30205348f1d808d98d77505149da8b047b9f Mon Sep 17 00:00:00 2001
From: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Date: Tue, 3 Feb 2015 12:13:44 +0530
Subject: powerpc/powernv: Avoid explicit endian conversions while parsing
 device tree

We currently read the information about idle states from the device
tree, so as to find out the CPU idle states supported by the platform.

Use the of_property_read/count_xxx() APIs, which handle endian
conversions for us, and mean we don't need any endian annotations in the
code.

Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/platforms/powernv/setup.c | 35 +++++++++++++++++++---------------
 1 file changed, 20 insertions(+), 15 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index d2de7d5d7574..39d1971d77db 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -409,37 +409,39 @@ static int __init pnv_init_idle_states(void)
 {
 	struct device_node *power_mgt;
 	int dt_idle_states;
-	const __be32 *idle_state_flags;
-	u32 len_flags, flags;
+	u32 *flags;
 	int i;
 
 	supported_cpuidle_states = 0;
 
 	if (cpuidle_disable != IDLE_NO_OVERRIDE)
-		return 0;
+		goto out;
 
 	if (!firmware_has_feature(FW_FEATURE_OPALv3))
-		return 0;
+		goto out;
 
 	power_mgt = of_find_node_by_path("/ibm,opal/power-mgt");
 	if (!power_mgt) {
 		pr_warn("opal: PowerMgmt Node not found\n");
-		return 0;
+		goto out;
+	}
+	dt_idle_states = of_property_count_u32_elems(power_mgt,
+			"ibm,cpu-idle-state-flags");
+	if (dt_idle_states < 0) {
+		pr_warn("cpuidle-powernv: no idle states found in the DT\n");
+		goto out;
 	}
 
-	idle_state_flags = of_get_property(power_mgt,
-			"ibm,cpu-idle-state-flags", &len_flags);
-	if (!idle_state_flags) {
-		pr_warn("DT-PowerMgmt: missing ibm,cpu-idle-state-flags\n");
-		return 0;
+	flags = kzalloc(sizeof(*flags) * dt_idle_states, GFP_KERNEL);
+	if (of_property_read_u32_array(power_mgt,
+			"ibm,cpu-idle-state-flags", flags, dt_idle_states)) {
+		pr_warn("cpuidle-powernv: missing ibm,cpu-idle-state-flags in DT\n");
+		goto out_free;
 	}
 
-	dt_idle_states = len_flags / sizeof(u32);
+	for (i = 0; i < dt_idle_states; i++)
+		supported_cpuidle_states |= flags[i];
 
-	for (i = 0; i < dt_idle_states; i++) {
-		flags = be32_to_cpu(idle_state_flags[i]);
-		supported_cpuidle_states |= flags;
-	}
 	if (!(supported_cpuidle_states & OPAL_PM_SLEEP_ENABLED_ER1)) {
 		patch_instruction(
 			(unsigned int *)pnv_fastsleep_workaround_at_entry,
@@ -449,6 +451,9 @@ static int __init pnv_init_idle_states(void)
 			PPC_INST_NOP);
 	}
 	pnv_alloc_idle_core_states();
+out_free:
+	kfree(flags);
+out:
 	return 0;
 }
 
-- 
cgit v1.2.3


From a8b2f8288a3fdef8d93efef2b1ead7563004275e Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Wed, 25 Mar 2015 16:23:52 +0800
Subject: powerpc/pci: Create pci_dn for VFs

pci_dn is the extension of PCI device node and is created from device node.
Unfortunately, VFs are enabled dynamically by PF's driver and they don't
have corresponding device nodes and pci_dn, which is required to access
VFs' config spaces.

The patch creates pci_dn for VFs in pcibios_sriov_enable() on their PF,
and removes pci_dn for VFs in pcibios_sriov_disable() on their PF. When
VF's pci_dn is created, it's put to the child list of the pci_dn of PF's
upstream bridge. The pci_dn is linked to pci_dev during early fixup time
to setup the fast path.

[bhelgaas: add ifdef around add_one_dev_pci_info(), use dev_printk()]
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/pci-bridge.h     |   3 +
 arch/powerpc/kernel/pci_dn.c              | 116 ++++++++++++++++++++++++++++++
 arch/powerpc/platforms/powernv/pci-ioda.c |  16 +++++
 3 files changed, 135 insertions(+)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 2c6dc2a3d14a..ece30f589398 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -156,6 +156,7 @@ struct iommu_table;
 
 struct pci_dn {
 	int     flags;
+#define PCI_DN_FLAG_IOV_VF	0x01
 
 	int	busno;			/* pci bus number */
 	int	devfn;			/* pci device and function number */
@@ -188,6 +189,8 @@ struct pci_dn {
 extern struct pci_dn *pci_get_pdn_by_devfn(struct pci_bus *bus,
 					   int devfn);
 extern struct pci_dn *pci_get_pdn(struct pci_dev *pdev);
+extern struct pci_dn *add_dev_pci_data(struct pci_dev *pdev);
+extern void remove_dev_pci_data(struct pci_dev *pdev);
 extern void *update_dn_pci_info(struct device_node *dn, void *data);
 
 static inline int pci_device_from_OF_node(struct device_node *np,
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index 65b98367005c..e5f1d78ef7cf 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -136,6 +136,122 @@ struct pci_dn *pci_get_pdn(struct pci_dev *pdev)
 	return NULL;
 }
 
+#ifdef CONFIG_PCI_IOV
+static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent,
+					   struct pci_dev *pdev,
+					   int busno, int devfn)
+{
+	struct pci_dn *pdn;
+
+	/* Except PHB, we always have the parent */
+	if (!parent)
+		return NULL;
+
+	pdn = kzalloc(sizeof(*pdn), GFP_KERNEL);
+	if (!pdn) {
+		dev_warn(&pdev->dev, "%s: Out of memory!\n", __func__);
+		return NULL;
+	}
+
+	pdn->phb = parent->phb;
+	pdn->parent = parent;
+	pdn->busno = busno;
+	pdn->devfn = devfn;
+#ifdef CONFIG_PPC_POWERNV
+	pdn->pe_number = IODA_INVALID_PE;
+#endif
+	INIT_LIST_HEAD(&pdn->child_list);
+	INIT_LIST_HEAD(&pdn->list);
+	list_add_tail(&pdn->list, &parent->child_list);
+
+	/*
+	 * If we already have PCI device instance, lets
+	 * bind them.
+	 */
+	if (pdev)
+		pdev->dev.archdata.pci_data = pdn;
+
+	return pdn;
+}
+#endif
+
+struct pci_dn *add_dev_pci_data(struct pci_dev *pdev)
+{
+#ifdef CONFIG_PCI_IOV
+	struct pci_dn *parent, *pdn;
+	int i;
+
+	/* Only support IOV for now */
+	if (!pdev->is_physfn)
+		return pci_get_pdn(pdev);
+
+	/* Check if VFs have been populated */
+	pdn = pci_get_pdn(pdev);
+	if (!pdn || (pdn->flags & PCI_DN_FLAG_IOV_VF))
+		return NULL;
+
+	pdn->flags |= PCI_DN_FLAG_IOV_VF;
+	parent = pci_bus_to_pdn(pdev->bus);
+	if (!parent)
+		return NULL;
+
+	for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
+		pdn = add_one_dev_pci_data(parent, NULL,
+					   pci_iov_virtfn_bus(pdev, i),
+					   pci_iov_virtfn_devfn(pdev, i));
+		if (!pdn) {
+			dev_warn(&pdev->dev, "%s: Cannot create firmware data for VF#%d\n",
+				 __func__, i);
+			return NULL;
+		}
+	}
+#endif /* CONFIG_PCI_IOV */
+
+	return pci_get_pdn(pdev);
+}
+
+void remove_dev_pci_data(struct pci_dev *pdev)
+{
+#ifdef CONFIG_PCI_IOV
+	struct pci_dn *parent;
+	struct pci_dn *pdn, *tmp;
+	int i;
+
+	/* Only support IOV PF for now */
+	if (!pdev->is_physfn)
+		return;
+
+	/* Check if VFs have been populated */
+	pdn = pci_get_pdn(pdev);
+	if (!pdn || !(pdn->flags & PCI_DN_FLAG_IOV_VF))
+		return;
+
+	pdn->flags &= ~PCI_DN_FLAG_IOV_VF;
+	parent = pci_bus_to_pdn(pdev->bus);
+	if (!parent)
+		return;
+
+	/*
+	 * We might introduce flag to pci_dn in future
+	 * so that we can release VF's firmware data in
+	 * a batch mode.
+	 */
+	for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
+		list_for_each_entry_safe(pdn, tmp,
+			&parent->child_list, list) {
+			if (pdn->busno != pci_iov_virtfn_bus(pdev, i) ||
+			    pdn->devfn != pci_iov_virtfn_devfn(pdev, i))
+				continue;
+
+			if (!list_empty(&pdn->list))
+				list_del(&pdn->list);
+
+			kfree(pdn);
+		}
+	}
+#endif /* CONFIG_PCI_IOV */
+}
+
 /*
  * Traverse_func that inits the PCI fields of the device node.
  * NOTE: this *must* be done before read/write config to the device.
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 26fe09936935..7f58f199f2c1 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -974,6 +974,22 @@ static void pnv_pci_ioda_setup_PEs(void)
 	}
 }
 
+#ifdef CONFIG_PCI_IOV
+int pcibios_sriov_disable(struct pci_dev *pdev)
+{
+	/* Release PCI data */
+	remove_dev_pci_data(pdev);
+	return 0;
+}
+
+int pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
+{
+	/* Allocate PCI data */
+	add_dev_pci_data(pdev);
+	return 0;
+}
+#endif /* CONFIG_PCI_IOV */
+
 static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev)
 {
 	struct pci_dn *pdn = pci_get_pdn(pdev);
-- 
cgit v1.2.3


From 9e8d4a19ab66ec9e132d405357b9108a4f26efd3 Mon Sep 17 00:00:00 2001
From: Wei Yang <weiyang@linux.vnet.ibm.com>
Date: Wed, 25 Mar 2015 16:23:54 +0800
Subject: powerpc/powernv: Allocate struct pnv_ioda_pe iommu_table dynamically

Previously the iommu_table had the same lifetime as a struct pnv_ioda_pe
and was embedded in it. The pnv_ioda_pe was assigned to a PE on the bootup
stage. Since PEs are based on the hardware layout which is static in the
system, they will never get released. This means the iommu_table in the
pnv_ioda_pe will never get released either.

This no longer works for VF PE. VF PEs are created and released dynamically
when VFs are created and released. So we need to assign pnv_ioda_pe to VF
PEs respectively when VFs are enabled and clean up those resources for VF
PE when VFs are disabled. And iommu_table is one of the resources we need
to handle dynamically.

Current iommu_table is a static field in pnv_ioda_pe, which will face a
problem when freeing it. During the disabling of a VF,
pnv_pci_ioda2_release_dma_pe will call iommu_free_table to release the
iommu_table for this PE. A static iommu_table will fail in
iommu_free_table.

According to these requirement, this patch allocates iommu_table
dynamically.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/iommu.h          |  3 +++
 arch/powerpc/platforms/powernv/pci-ioda.c | 26 ++++++++++++++------------
 arch/powerpc/platforms/powernv/pci.h      |  2 +-
 3 files changed, 18 insertions(+), 13 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index f1ea5972f6ec..e2abbe8a1f4d 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -78,6 +78,9 @@ struct iommu_table {
 	struct iommu_group *it_group;
 #endif
 	void (*set_bypass)(struct iommu_table *tbl, bool enable);
+#ifdef CONFIG_PPC_POWERNV
+	void           *data;
+#endif
 };
 
 /* Pure 2^n version of get_order */
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 7f58f199f2c1..9447ee9b4aa3 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -916,6 +916,10 @@ static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, int all)
 		return;
 	}
 
+	pe->tce32_table = kzalloc_node(sizeof(struct iommu_table),
+			GFP_KERNEL, hose->node);
+	pe->tce32_table->data = pe;
+
 	/* Associate it with all child devices */
 	pnv_ioda_setup_same_PE(bus, pe);
 
@@ -1005,7 +1009,7 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
 
 	pe = &phb->ioda.pe_array[pdn->pe_number];
 	WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops);
-	set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table);
+	set_iommu_table_base_and_group(&pdev->dev, pe->tce32_table);
 }
 
 static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
@@ -1032,7 +1036,7 @@ static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
 	} else {
 		dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n");
 		set_dma_ops(&pdev->dev, &dma_iommu_ops);
-		set_iommu_table_base(&pdev->dev, &pe->tce32_table);
+		set_iommu_table_base(&pdev->dev, pe->tce32_table);
 	}
 	*pdev->dev.dma_mask = dma_mask;
 	return 0;
@@ -1069,9 +1073,9 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
 	list_for_each_entry(dev, &bus->devices, bus_list) {
 		if (add_to_iommu_group)
 			set_iommu_table_base_and_group(&dev->dev,
-						       &pe->tce32_table);
+						       pe->tce32_table);
 		else
-			set_iommu_table_base(&dev->dev, &pe->tce32_table);
+			set_iommu_table_base(&dev->dev, pe->tce32_table);
 
 		if (dev->subordinate)
 			pnv_ioda_setup_bus_dma(pe, dev->subordinate,
@@ -1161,8 +1165,7 @@ static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe,
 void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
 				 __be64 *startp, __be64 *endp, bool rm)
 {
-	struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
-					      tce32_table);
+	struct pnv_ioda_pe *pe = tbl->data;
 	struct pnv_phb *phb = pe->phb;
 
 	if (phb->type == PNV_PHB_IODA1)
@@ -1228,7 +1231,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 	}
 
 	/* Setup linux iommu table */
-	tbl = &pe->tce32_table;
+	tbl = pe->tce32_table;
 	pnv_pci_setup_iommu_table(tbl, addr, TCE32_TABLE_SIZE * segs,
 				  base << 28, IOMMU_PAGE_SHIFT_4K);
 
@@ -1266,8 +1269,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 
 static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
 {
-	struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
-					      tce32_table);
+	struct pnv_ioda_pe *pe = tbl->data;
 	uint16_t window_id = (pe->pe_number << 1 ) + 1;
 	int64_t rc;
 
@@ -1312,10 +1314,10 @@ static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb,
 	pe->tce_bypass_base = 1ull << 59;
 
 	/* Install set_bypass callback for VFIO */
-	pe->tce32_table.set_bypass = pnv_pci_ioda2_set_bypass;
+	pe->tce32_table->set_bypass = pnv_pci_ioda2_set_bypass;
 
 	/* Enable bypass by default */
-	pnv_pci_ioda2_set_bypass(&pe->tce32_table, true);
+	pnv_pci_ioda2_set_bypass(pe->tce32_table, true);
 }
 
 static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
@@ -1363,7 +1365,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 	}
 
 	/* Setup linux iommu table */
-	tbl = &pe->tce32_table;
+	tbl = pe->tce32_table;
 	pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, 0,
 			IOMMU_PAGE_SHIFT_4K);
 
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 1f0cb66133a1..84280474e18f 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -53,7 +53,7 @@ struct pnv_ioda_pe {
 	/* "Base" iommu table, ie, 4K TCEs, 32-bit DMA */
 	int			tce32_seg;
 	int			tce32_segcount;
-	struct iommu_table	tce32_table;
+	struct iommu_table	*tce32_table;
 	phys_addr_t		tce_inval_reg_phys;
 
 	/* 64-bit TCE bypass region */
-- 
cgit v1.2.3


From 6e628c7d33d99406cef374972c89389edcc3570f Mon Sep 17 00:00:00 2001
From: Wei Yang <weiyang@linux.vnet.ibm.com>
Date: Wed, 25 Mar 2015 16:23:55 +0800
Subject: powerpc/powernv: Reserve additional space for IOV BAR according to
 the number of total_pe

On PHB3, PF IOV BAR will be covered by M64 BAR to have better PE isolation.
M64 BAR is a type of hardware resource in PHB3, which could map a range of
MMIO to PE numbers on powernv platform. And this range is divided equally
by the number of total_pe with each divided range mapping to a PE number.
Also, the M64 BAR must map a MMIO range with power-of-two size.

The total_pe number is usually different from total_VFs, which can lead to
a conflict between MMIO space and the PE number.

For example, if total_VFs is 128 and total_pe is 256, the second half of
M64 BAR will be part of other PCI device, which may already belong to other
PEs.

This patch prevents the conflict by reserving additional space for the PF
IOV BAR, which is total_pe number of VF's BAR size.

[bhelgaas: make dev_printk() output more consistent, index resource[]
conventionally]
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/machdep.h        |  4 +++
 arch/powerpc/include/asm/pci-bridge.h     |  3 +++
 arch/powerpc/kernel/pci-common.c          |  6 +++++
 arch/powerpc/platforms/powernv/pci-ioda.c | 43 +++++++++++++++++++++++++++++++
 4 files changed, 56 insertions(+)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 098d51e924ea..b303833fa3fb 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -250,6 +250,10 @@ struct machdep_calls {
 	/* Reset the secondary bus of bridge */
 	void  (*pcibios_reset_secondary_bus)(struct pci_dev *dev);
 
+#ifdef CONFIG_PCI_IOV
+	void (*pcibios_fixup_sriov)(struct pci_dev *pdev);
+#endif /* CONFIG_PCI_IOV */
+
 	/* Called to shutdown machine specific hardware not already controlled
 	 * by other drivers.
 	 */
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index ece30f589398..7b8ebc5929ff 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -178,6 +178,9 @@ struct pci_dn {
 #define IODA_INVALID_PE		(-1)
 #ifdef CONFIG_PPC_POWERNV
 	int	pe_number;
+#ifdef CONFIG_PCI_IOV
+	u16     vfs_expanded;		/* number of VFs IOV BAR expanded */
+#endif /* CONFIG_PCI_IOV */
 #endif
 	struct list_head child_list;
 	struct list_head list;
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 82031011522f..375bf7099912 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -990,6 +990,12 @@ int pcibios_add_device(struct pci_dev *dev)
 	 */
 	if (dev->bus->is_added)
 		pcibios_setup_device(dev);
+
+#ifdef CONFIG_PCI_IOV
+	if (ppc_md.pcibios_fixup_sriov)
+		ppc_md.pcibios_fixup_sriov(dev);
+#endif /* CONFIG_PCI_IOV */
+
 	return 0;
 }
 
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 9447ee9b4aa3..1da45aa76a03 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1749,6 +1749,46 @@ static void pnv_pci_init_ioda_msis(struct pnv_phb *phb)
 static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) { }
 #endif /* CONFIG_PCI_MSI */
 
+#ifdef CONFIG_PCI_IOV
+static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
+{
+	struct pci_controller *hose;
+	struct pnv_phb *phb;
+	struct resource *res;
+	int i;
+	resource_size_t size;
+	struct pci_dn *pdn;
+
+	if (!pdev->is_physfn || pdev->is_added)
+		return;
+
+	hose = pci_bus_to_host(pdev->bus);
+	phb = hose->private_data;
+
+	pdn = pci_get_pdn(pdev);
+	pdn->vfs_expanded = 0;
+
+	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
+		res = &pdev->resource[i + PCI_IOV_RESOURCES];
+		if (!res->flags || res->parent)
+			continue;
+		if (!pnv_pci_is_mem_pref_64(res->flags)) {
+			dev_warn(&pdev->dev, "Skipping expanding VF BAR%d: %pR\n",
+				 i, res);
+			continue;
+		}
+
+		dev_dbg(&pdev->dev, " Fixing VF BAR%d: %pR to\n", i, res);
+		size = pci_iov_resource_size(pdev, i + PCI_IOV_RESOURCES);
+		res->end = res->start + size * phb->ioda.total_pe - 1;
+		dev_dbg(&pdev->dev, "                       %pR\n", res);
+		dev_info(&pdev->dev, "VF BAR%d: %pR (expanded to %d VFs for PE alignment)",
+				i, res, phb->ioda.total_pe);
+	}
+	pdn->vfs_expanded = phb->ioda.total_pe;
+}
+#endif /* CONFIG_PCI_IOV */
+
 /*
  * This function is supposed to be called on basis of PE from top
  * to bottom style. So the the I/O or MMIO segment assigned to
@@ -2122,6 +2162,9 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	ppc_md.pcibios_enable_device_hook = pnv_pci_enable_device_hook;
 	ppc_md.pcibios_window_alignment = pnv_pci_window_alignment;
 	ppc_md.pcibios_reset_secondary_bus = pnv_pci_reset_secondary_bus;
+#ifdef CONFIG_PCI_IOV
+	ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources;
+#endif /* CONFIG_PCI_IOV */
 	pci_add_flags(PCI_REASSIGN_ALL_RSRC);
 
 	/* Reset IODA tables to a clean state */
-- 
cgit v1.2.3


From 5350ab3fd794f899079d9f6b2b6fe1a7917087ef Mon Sep 17 00:00:00 2001
From: Wei Yang <weiyang@linux.vnet.ibm.com>
Date: Wed, 25 Mar 2015 16:23:56 +0800
Subject: powerpc/powernv: Implement pcibios_iov_resource_alignment() on
 powernv

Implement pcibios_iov_resource_alignment() on powernv platform.

On PowerNV platform, there are 3 cases for the IOV BAR:
1. initial state, the IOV BAR size is multiple times of VF BAR size
2. after expanded, the IOV BAR size is expanded to meet the M64 segment size
3. sizing stage, the IOV BAR is truncated to 0

pnv_pci_iov_resource_alignment() handle these three cases respectively.

[bhelgaas: adjust to drop "align" parameter, return pci_iov_resource_size()
if no ppc_md machdep_call version]
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/machdep.h        |  1 +
 arch/powerpc/kernel/pci-common.c          | 10 ++++++++++
 arch/powerpc/platforms/powernv/pci-ioda.c | 20 ++++++++++++++++++++
 3 files changed, 31 insertions(+)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index b303833fa3fb..1b268044f290 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -252,6 +252,7 @@ struct machdep_calls {
 
 #ifdef CONFIG_PCI_IOV
 	void (*pcibios_fixup_sriov)(struct pci_dev *pdev);
+	resource_size_t (*pcibios_iov_resource_alignment)(struct pci_dev *, int resno);
 #endif /* CONFIG_PCI_IOV */
 
 	/* Called to shutdown machine specific hardware not already controlled
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 375bf7099912..9a306ff304ae 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -130,6 +130,16 @@ void pcibios_reset_secondary_bus(struct pci_dev *dev)
 	pci_reset_secondary_bus(dev);
 }
 
+#ifdef CONFIG_PCI_IOV
+resource_size_t pcibios_iov_resource_alignment(struct pci_dev *pdev, int resno)
+{
+	if (ppc_md.pcibios_iov_resource_alignment)
+		return ppc_md.pcibios_iov_resource_alignment(pdev, resno);
+
+	return pci_iov_resource_size(pdev, resno);
+}
+#endif /* CONFIG_PCI_IOV */
+
 static resource_size_t pcibios_io_size(const struct pci_controller *hose)
 {
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 1da45aa76a03..217eaad23cde 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1965,6 +1965,25 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus,
 	return phb->ioda.io_segsize;
 }
 
+#ifdef CONFIG_PCI_IOV
+static resource_size_t pnv_pci_iov_resource_alignment(struct pci_dev *pdev,
+						      int resno)
+{
+	struct pci_dn *pdn = pci_get_pdn(pdev);
+	resource_size_t align, iov_align;
+
+	iov_align = resource_size(&pdev->resource[resno]);
+	if (iov_align)
+		return iov_align;
+
+	align = pci_iov_resource_size(pdev, resno);
+	if (pdn->vfs_expanded)
+		return pdn->vfs_expanded * align;
+
+	return align;
+}
+#endif /* CONFIG_PCI_IOV */
+
 /* Prevent enabling devices for which we couldn't properly
  * assign a PE
  */
@@ -2164,6 +2183,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	ppc_md.pcibios_reset_secondary_bus = pnv_pci_reset_secondary_bus;
 #ifdef CONFIG_PCI_IOV
 	ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources;
+	ppc_md.pcibios_iov_resource_alignment = pnv_pci_iov_resource_alignment;
 #endif /* CONFIG_PCI_IOV */
 	pci_add_flags(PCI_REASSIGN_ALL_RSRC);
 
-- 
cgit v1.2.3


From 781a868f3136c6eb8e8c5c19d148416d7da86610 Mon Sep 17 00:00:00 2001
From: Wei Yang <weiyang@linux.vnet.ibm.com>
Date: Wed, 25 Mar 2015 16:23:57 +0800
Subject: powerpc/powernv: Shift VF resource with an offset

On PowerNV platform, resource position in M64 BAR implies the PE# the
resource belongs to. In some cases, adjustment of a resource is necessary
to locate it to a correct position in M64 BAR .

This patch adds pnv_pci_vf_resource_shift() to shift the 'real' PF IOV BAR
address according to an offset.

Note:

    After doing so, there would be a "hole" in the /proc/iomem when offset
    is a positive value. It looks like the device return some mmio back to
    the system, which actually no one could use it.

[bhelgaas: rework loops, rework overlap check, index resource[]
conventionally, remove pci_regs.h include, squashed with next patch]
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/pci-bridge.h     |   4 +
 arch/powerpc/kernel/pci_dn.c              |  13 +
 arch/powerpc/platforms/powernv/pci-ioda.c | 528 +++++++++++++++++++++++++++++-
 arch/powerpc/platforms/powernv/pci.c      |  18 +
 arch/powerpc/platforms/powernv/pci.h      |   7 +
 5 files changed, 553 insertions(+), 17 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 7b8ebc5929ff..8716db48e946 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -180,6 +180,10 @@ struct pci_dn {
 	int	pe_number;
 #ifdef CONFIG_PCI_IOV
 	u16     vfs_expanded;		/* number of VFs IOV BAR expanded */
+	u16     num_vfs;		/* number of VFs enabled*/
+	int     offset;			/* PE# for the first VF PE */
+#define IODA_INVALID_M64        (-1)
+	int     m64_wins[PCI_SRIOV_NUM_BARS];
 #endif /* CONFIG_PCI_IOV */
 #endif
 	struct list_head child_list;
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index e5f1d78ef7cf..b3b4df91b792 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -217,6 +217,19 @@ void remove_dev_pci_data(struct pci_dev *pdev)
 	struct pci_dn *pdn, *tmp;
 	int i;
 
+	/*
+	 * VF and VF PE are created/released dynamically, so we need to
+	 * bind/unbind them.  Otherwise the VF and VF PE would be mismatched
+	 * when re-enabling SR-IOV.
+	 */
+	if (pdev->is_virtfn) {
+		pdn = pci_get_pdn(pdev);
+#ifdef CONFIG_PPC_POWERNV
+		pdn->pe_number = IODA_INVALID_PE;
+#endif
+		return;
+	}
+
 	/* Only support IOV PF for now */
 	if (!pdev->is_physfn)
 		return;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 217eaad23cde..5187d164cfe1 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -44,6 +44,9 @@
 #include "powernv.h"
 #include "pci.h"
 
+/* 256M DMA window, 4K TCE pages, 8 bytes TCE */
+#define TCE32_TABLE_SIZE	((0x10000000 / 0x1000) * 8)
+
 static void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
 			    const char *fmt, ...)
 {
@@ -56,11 +59,18 @@ static void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
-	if (pe->pdev)
+	if (pe->flags & PNV_IODA_PE_DEV)
 		strlcpy(pfix, dev_name(&pe->pdev->dev), sizeof(pfix));
-	else
+	else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))
 		sprintf(pfix, "%04x:%02x     ",
 			pci_domain_nr(pe->pbus), pe->pbus->number);
+#ifdef CONFIG_PCI_IOV
+	else if (pe->flags & PNV_IODA_PE_VF)
+		sprintf(pfix, "%04x:%02x:%2x.%d",
+			pci_domain_nr(pe->parent_dev->bus),
+			(pe->rid & 0xff00) >> 8,
+			PCI_SLOT(pe->rid), PCI_FUNC(pe->rid));
+#endif /* CONFIG_PCI_IOV*/
 
 	printk("%spci %s: [PE# %.3d] %pV",
 	       level, pfix, pe->pe_number, &vaf);
@@ -591,7 +601,7 @@ static int pnv_ioda_set_peltv(struct pnv_phb *phb,
 			      bool is_add)
 {
 	struct pnv_ioda_pe *slave;
-	struct pci_dev *pdev;
+	struct pci_dev *pdev = NULL;
 	int ret;
 
 	/*
@@ -630,8 +640,12 @@ static int pnv_ioda_set_peltv(struct pnv_phb *phb,
 
 	if (pe->flags & (PNV_IODA_PE_BUS_ALL | PNV_IODA_PE_BUS))
 		pdev = pe->pbus->self;
-	else
+	else if (pe->flags & PNV_IODA_PE_DEV)
 		pdev = pe->pdev->bus->self;
+#ifdef CONFIG_PCI_IOV
+	else if (pe->flags & PNV_IODA_PE_VF)
+		pdev = pe->parent_dev->bus->self;
+#endif /* CONFIG_PCI_IOV */
 	while (pdev) {
 		struct pci_dn *pdn = pci_get_pdn(pdev);
 		struct pnv_ioda_pe *parent;
@@ -649,6 +663,87 @@ static int pnv_ioda_set_peltv(struct pnv_phb *phb,
 	return 0;
 }
 
+#ifdef CONFIG_PCI_IOV
+static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
+{
+	struct pci_dev *parent;
+	uint8_t bcomp, dcomp, fcomp;
+	int64_t rc;
+	long rid_end, rid;
+
+	/* Currently, we just deconfigure VF PE. Bus PE will always there.*/
+	if (pe->pbus) {
+		int count;
+
+		dcomp = OPAL_IGNORE_RID_DEVICE_NUMBER;
+		fcomp = OPAL_IGNORE_RID_FUNCTION_NUMBER;
+		parent = pe->pbus->self;
+		if (pe->flags & PNV_IODA_PE_BUS_ALL)
+			count = pe->pbus->busn_res.end - pe->pbus->busn_res.start + 1;
+		else
+			count = 1;
+
+		switch(count) {
+		case  1: bcomp = OpalPciBusAll;         break;
+		case  2: bcomp = OpalPciBus7Bits;       break;
+		case  4: bcomp = OpalPciBus6Bits;       break;
+		case  8: bcomp = OpalPciBus5Bits;       break;
+		case 16: bcomp = OpalPciBus4Bits;       break;
+		case 32: bcomp = OpalPciBus3Bits;       break;
+		default:
+			dev_err(&pe->pbus->dev, "Number of subordinate buses %d unsupported\n",
+			        count);
+			/* Do an exact match only */
+			bcomp = OpalPciBusAll;
+		}
+		rid_end = pe->rid + (count << 8);
+	} else {
+		if (pe->flags & PNV_IODA_PE_VF)
+			parent = pe->parent_dev;
+		else
+			parent = pe->pdev->bus->self;
+		bcomp = OpalPciBusAll;
+		dcomp = OPAL_COMPARE_RID_DEVICE_NUMBER;
+		fcomp = OPAL_COMPARE_RID_FUNCTION_NUMBER;
+		rid_end = pe->rid + 1;
+	}
+
+	/* Clear the reverse map */
+	for (rid = pe->rid; rid < rid_end; rid++)
+		phb->ioda.pe_rmap[rid] = 0;
+
+	/* Release from all parents PELT-V */
+	while (parent) {
+		struct pci_dn *pdn = pci_get_pdn(parent);
+		if (pdn && pdn->pe_number != IODA_INVALID_PE) {
+			rc = opal_pci_set_peltv(phb->opal_id, pdn->pe_number,
+						pe->pe_number, OPAL_REMOVE_PE_FROM_DOMAIN);
+			/* XXX What to do in case of error ? */
+		}
+		parent = parent->bus->self;
+	}
+
+	opal_pci_eeh_freeze_set(phb->opal_id, pe->pe_number,
+				  OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+
+	/* Disassociate PE in PELT */
+	rc = opal_pci_set_peltv(phb->opal_id, pe->pe_number,
+				pe->pe_number, OPAL_REMOVE_PE_FROM_DOMAIN);
+	if (rc)
+		pe_warn(pe, "OPAL error %ld remove self from PELTV\n", rc);
+	rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid,
+			     bcomp, dcomp, fcomp, OPAL_UNMAP_PE);
+	if (rc)
+		pe_err(pe, "OPAL error %ld trying to setup PELT table\n", rc);
+
+	pe->pbus = NULL;
+	pe->pdev = NULL;
+	pe->parent_dev = NULL;
+
+	return 0;
+}
+#endif /* CONFIG_PCI_IOV */
+
 static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 {
 	struct pci_dev *parent;
@@ -675,15 +770,19 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 		case 16: bcomp = OpalPciBus4Bits;	break;
 		case 32: bcomp = OpalPciBus3Bits;	break;
 		default:
-			pr_err("%s: Number of subordinate busses %d"
-			       " unsupported\n",
-			       pci_name(pe->pbus->self), count);
+			dev_err(&pe->pbus->dev, "Number of subordinate buses %d unsupported\n",
+			        count);
 			/* Do an exact match only */
 			bcomp = OpalPciBusAll;
 		}
 		rid_end = pe->rid + (count << 8);
 	} else {
-		parent = pe->pdev->bus->self;
+#ifdef CONFIG_PCI_IOV
+		if (pe->flags & PNV_IODA_PE_VF)
+			parent = pe->parent_dev;
+		else
+#endif /* CONFIG_PCI_IOV */
+			parent = pe->pdev->bus->self;
 		bcomp = OpalPciBusAll;
 		dcomp = OPAL_COMPARE_RID_DEVICE_NUMBER;
 		fcomp = OPAL_COMPARE_RID_FUNCTION_NUMBER;
@@ -774,6 +873,78 @@ static unsigned int pnv_ioda_dma_weight(struct pci_dev *dev)
 	return 10;
 }
 
+#ifdef CONFIG_PCI_IOV
+static int pnv_pci_vf_resource_shift(struct pci_dev *dev, int offset)
+{
+	struct pci_dn *pdn = pci_get_pdn(dev);
+	int i;
+	struct resource *res, res2;
+	resource_size_t size;
+	u16 num_vfs;
+
+	if (!dev->is_physfn)
+		return -EINVAL;
+
+	/*
+	 * "offset" is in VFs.  The M64 windows are sized so that when they
+	 * are segmented, each segment is the same size as the IOV BAR.
+	 * Each segment is in a separate PE, and the high order bits of the
+	 * address are the PE number.  Therefore, each VF's BAR is in a
+	 * separate PE, and changing the IOV BAR start address changes the
+	 * range of PEs the VFs are in.
+	 */
+	num_vfs = pdn->num_vfs;
+	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
+		res = &dev->resource[i + PCI_IOV_RESOURCES];
+		if (!res->flags || !res->parent)
+			continue;
+
+		if (!pnv_pci_is_mem_pref_64(res->flags))
+			continue;
+
+		/*
+		 * The actual IOV BAR range is determined by the start address
+		 * and the actual size for num_vfs VFs BAR.  This check is to
+		 * make sure that after shifting, the range will not overlap
+		 * with another device.
+		 */
+		size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES);
+		res2.flags = res->flags;
+		res2.start = res->start + (size * offset);
+		res2.end = res2.start + (size * num_vfs) - 1;
+
+		if (res2.end > res->end) {
+			dev_err(&dev->dev, "VF BAR%d: %pR would extend past %pR (trying to enable %d VFs shifted by %d)\n",
+				i, &res2, res, num_vfs, offset);
+			return -EBUSY;
+		}
+	}
+
+	/*
+	 * After doing so, there would be a "hole" in the /proc/iomem when
+	 * offset is a positive value. It looks like the device return some
+	 * mmio back to the system, which actually no one could use it.
+	 */
+	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
+		res = &dev->resource[i + PCI_IOV_RESOURCES];
+		if (!res->flags || !res->parent)
+			continue;
+
+		if (!pnv_pci_is_mem_pref_64(res->flags))
+			continue;
+
+		size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES);
+		res2 = *res;
+		res->start += size * offset;
+
+		dev_info(&dev->dev, "VF BAR%d: %pR shifted to %pR (enabling %d VFs shifted by %d)\n",
+			 i, &res2, res, num_vfs, offset);
+		pci_update_resource(dev, i + PCI_IOV_RESOURCES);
+	}
+	return 0;
+}
+#endif /* CONFIG_PCI_IOV */
+
 #if 0
 static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 {
@@ -979,8 +1150,316 @@ static void pnv_pci_ioda_setup_PEs(void)
 }
 
 #ifdef CONFIG_PCI_IOV
+static int pnv_pci_vf_release_m64(struct pci_dev *pdev)
+{
+	struct pci_bus        *bus;
+	struct pci_controller *hose;
+	struct pnv_phb        *phb;
+	struct pci_dn         *pdn;
+	int                    i;
+
+	bus = pdev->bus;
+	hose = pci_bus_to_host(bus);
+	phb = hose->private_data;
+	pdn = pci_get_pdn(pdev);
+
+	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
+		if (pdn->m64_wins[i] == IODA_INVALID_M64)
+			continue;
+		opal_pci_phb_mmio_enable(phb->opal_id,
+				OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i], 0);
+		clear_bit(pdn->m64_wins[i], &phb->ioda.m64_bar_alloc);
+		pdn->m64_wins[i] = IODA_INVALID_M64;
+	}
+
+	return 0;
+}
+
+static int pnv_pci_vf_assign_m64(struct pci_dev *pdev)
+{
+	struct pci_bus        *bus;
+	struct pci_controller *hose;
+	struct pnv_phb        *phb;
+	struct pci_dn         *pdn;
+	unsigned int           win;
+	struct resource       *res;
+	int                    i;
+	int64_t                rc;
+
+	bus = pdev->bus;
+	hose = pci_bus_to_host(bus);
+	phb = hose->private_data;
+	pdn = pci_get_pdn(pdev);
+
+	/* Initialize the m64_wins to IODA_INVALID_M64 */
+	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++)
+		pdn->m64_wins[i] = IODA_INVALID_M64;
+
+	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
+		res = &pdev->resource[i + PCI_IOV_RESOURCES];
+		if (!res->flags || !res->parent)
+			continue;
+
+		if (!pnv_pci_is_mem_pref_64(res->flags))
+			continue;
+
+		do {
+			win = find_next_zero_bit(&phb->ioda.m64_bar_alloc,
+					phb->ioda.m64_bar_idx + 1, 0);
+
+			if (win >= phb->ioda.m64_bar_idx + 1)
+				goto m64_failed;
+		} while (test_and_set_bit(win, &phb->ioda.m64_bar_alloc));
+
+		pdn->m64_wins[i] = win;
+
+		/* Map the M64 here */
+		rc = opal_pci_set_phb_mem_window(phb->opal_id,
+						 OPAL_M64_WINDOW_TYPE,
+						 pdn->m64_wins[i],
+						 res->start,
+						 0, /* unused */
+						 resource_size(res));
+		if (rc != OPAL_SUCCESS) {
+			dev_err(&pdev->dev, "Failed to map M64 window #%d: %lld\n",
+				win, rc);
+			goto m64_failed;
+		}
+
+		rc = opal_pci_phb_mmio_enable(phb->opal_id,
+				OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i], 1);
+		if (rc != OPAL_SUCCESS) {
+			dev_err(&pdev->dev, "Failed to enable M64 window #%d: %llx\n",
+				win, rc);
+			goto m64_failed;
+		}
+	}
+	return 0;
+
+m64_failed:
+	pnv_pci_vf_release_m64(pdev);
+	return -EBUSY;
+}
+
+static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe *pe)
+{
+	struct pci_bus        *bus;
+	struct pci_controller *hose;
+	struct pnv_phb        *phb;
+	struct iommu_table    *tbl;
+	unsigned long         addr;
+	int64_t               rc;
+
+	bus = dev->bus;
+	hose = pci_bus_to_host(bus);
+	phb = hose->private_data;
+	tbl = pe->tce32_table;
+	addr = tbl->it_base;
+
+	opal_pci_map_pe_dma_window(phb->opal_id, pe->pe_number,
+				   pe->pe_number << 1, 1, __pa(addr),
+				   0, 0x1000);
+
+	rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id,
+				        pe->pe_number,
+				        (pe->pe_number << 1) + 1,
+				        pe->tce_bypass_base,
+				        0);
+	if (rc)
+		pe_warn(pe, "OPAL error %ld release DMA window\n", rc);
+
+	iommu_free_table(tbl, of_node_full_name(dev->dev.of_node));
+	free_pages(addr, get_order(TCE32_TABLE_SIZE));
+	pe->tce32_table = NULL;
+}
+
+static void pnv_ioda_release_vf_PE(struct pci_dev *pdev)
+{
+	struct pci_bus        *bus;
+	struct pci_controller *hose;
+	struct pnv_phb        *phb;
+	struct pnv_ioda_pe    *pe, *pe_n;
+	struct pci_dn         *pdn;
+
+	bus = pdev->bus;
+	hose = pci_bus_to_host(bus);
+	phb = hose->private_data;
+
+	if (!pdev->is_physfn)
+		return;
+
+	pdn = pci_get_pdn(pdev);
+	list_for_each_entry_safe(pe, pe_n, &phb->ioda.pe_list, list) {
+		if (pe->parent_dev != pdev)
+			continue;
+
+		pnv_pci_ioda2_release_dma_pe(pdev, pe);
+
+		/* Remove from list */
+		mutex_lock(&phb->ioda.pe_list_mutex);
+		list_del(&pe->list);
+		mutex_unlock(&phb->ioda.pe_list_mutex);
+
+		pnv_ioda_deconfigure_pe(phb, pe);
+
+		pnv_ioda_free_pe(phb, pe->pe_number);
+	}
+}
+
+void pnv_pci_sriov_disable(struct pci_dev *pdev)
+{
+	struct pci_bus        *bus;
+	struct pci_controller *hose;
+	struct pnv_phb        *phb;
+	struct pci_dn         *pdn;
+	struct pci_sriov      *iov;
+	u16 num_vfs;
+
+	bus = pdev->bus;
+	hose = pci_bus_to_host(bus);
+	phb = hose->private_data;
+	pdn = pci_get_pdn(pdev);
+	iov = pdev->sriov;
+	num_vfs = pdn->num_vfs;
+
+	/* Release VF PEs */
+	pnv_ioda_release_vf_PE(pdev);
+
+	if (phb->type == PNV_PHB_IODA2) {
+		pnv_pci_vf_resource_shift(pdev, -pdn->offset);
+
+		/* Release M64 windows */
+		pnv_pci_vf_release_m64(pdev);
+
+		/* Release PE numbers */
+		bitmap_clear(phb->ioda.pe_alloc, pdn->offset, num_vfs);
+		pdn->offset = 0;
+	}
+}
+
+static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
+				       struct pnv_ioda_pe *pe);
+static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
+{
+	struct pci_bus        *bus;
+	struct pci_controller *hose;
+	struct pnv_phb        *phb;
+	struct pnv_ioda_pe    *pe;
+	int                    pe_num;
+	u16                    vf_index;
+	struct pci_dn         *pdn;
+
+	bus = pdev->bus;
+	hose = pci_bus_to_host(bus);
+	phb = hose->private_data;
+	pdn = pci_get_pdn(pdev);
+
+	if (!pdev->is_physfn)
+		return;
+
+	/* Reserve PE for each VF */
+	for (vf_index = 0; vf_index < num_vfs; vf_index++) {
+		pe_num = pdn->offset + vf_index;
+
+		pe = &phb->ioda.pe_array[pe_num];
+		pe->pe_number = pe_num;
+		pe->phb = phb;
+		pe->flags = PNV_IODA_PE_VF;
+		pe->pbus = NULL;
+		pe->parent_dev = pdev;
+		pe->tce32_seg = -1;
+		pe->mve_number = -1;
+		pe->rid = (pci_iov_virtfn_bus(pdev, vf_index) << 8) |
+			   pci_iov_virtfn_devfn(pdev, vf_index);
+
+		pe_info(pe, "VF %04d:%02d:%02d.%d associated with PE#%d\n",
+			hose->global_number, pdev->bus->number,
+			PCI_SLOT(pci_iov_virtfn_devfn(pdev, vf_index)),
+			PCI_FUNC(pci_iov_virtfn_devfn(pdev, vf_index)), pe_num);
+
+		if (pnv_ioda_configure_pe(phb, pe)) {
+			/* XXX What do we do here ? */
+			if (pe_num)
+				pnv_ioda_free_pe(phb, pe_num);
+			pe->pdev = NULL;
+			continue;
+		}
+
+		pe->tce32_table = kzalloc_node(sizeof(struct iommu_table),
+				GFP_KERNEL, hose->node);
+		pe->tce32_table->data = pe;
+
+		/* Put PE to the list */
+		mutex_lock(&phb->ioda.pe_list_mutex);
+		list_add_tail(&pe->list, &phb->ioda.pe_list);
+		mutex_unlock(&phb->ioda.pe_list_mutex);
+
+		pnv_pci_ioda2_setup_dma_pe(phb, pe);
+	}
+}
+
+int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
+{
+	struct pci_bus        *bus;
+	struct pci_controller *hose;
+	struct pnv_phb        *phb;
+	struct pci_dn         *pdn;
+	int                    ret;
+
+	bus = pdev->bus;
+	hose = pci_bus_to_host(bus);
+	phb = hose->private_data;
+	pdn = pci_get_pdn(pdev);
+
+	if (phb->type == PNV_PHB_IODA2) {
+		/* Calculate available PE for required VFs */
+		mutex_lock(&phb->ioda.pe_alloc_mutex);
+		pdn->offset = bitmap_find_next_zero_area(
+			phb->ioda.pe_alloc, phb->ioda.total_pe,
+			0, num_vfs, 0);
+		if (pdn->offset >= phb->ioda.total_pe) {
+			mutex_unlock(&phb->ioda.pe_alloc_mutex);
+			dev_info(&pdev->dev, "Failed to enable VF%d\n", num_vfs);
+			pdn->offset = 0;
+			return -EBUSY;
+		}
+		bitmap_set(phb->ioda.pe_alloc, pdn->offset, num_vfs);
+		pdn->num_vfs = num_vfs;
+		mutex_unlock(&phb->ioda.pe_alloc_mutex);
+
+		/* Assign M64 window accordingly */
+		ret = pnv_pci_vf_assign_m64(pdev);
+		if (ret) {
+			dev_info(&pdev->dev, "Not enough M64 window resources\n");
+			goto m64_failed;
+		}
+
+		/*
+		 * When using one M64 BAR to map one IOV BAR, we need to shift
+		 * the IOV BAR according to the PE# allocated to the VFs.
+		 * Otherwise, the PE# for the VF will conflict with others.
+		 */
+		ret = pnv_pci_vf_resource_shift(pdev, pdn->offset);
+		if (ret)
+			goto m64_failed;
+	}
+
+	/* Setup VF PEs */
+	pnv_ioda_setup_vf_PE(pdev, num_vfs);
+
+	return 0;
+
+m64_failed:
+	bitmap_clear(phb->ioda.pe_alloc, pdn->offset, num_vfs);
+	pdn->offset = 0;
+
+	return ret;
+}
+
 int pcibios_sriov_disable(struct pci_dev *pdev)
 {
+	pnv_pci_sriov_disable(pdev);
+
 	/* Release PCI data */
 	remove_dev_pci_data(pdev);
 	return 0;
@@ -990,6 +1469,8 @@ int pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
 {
 	/* Allocate PCI data */
 	add_dev_pci_data(pdev);
+
+	pnv_pci_sriov_enable(pdev, num_vfs);
 	return 0;
 }
 #endif /* CONFIG_PCI_IOV */
@@ -1186,9 +1667,6 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 	int64_t rc;
 	void *addr;
 
-	/* 256M DMA window, 4K TCE pages, 8 bytes TCE */
-#define TCE32_TABLE_SIZE	((0x10000000 / 0x1000) * 8)
-
 	/* XXX FIXME: Handle 64-bit only DMA devices */
 	/* XXX FIXME: Provide 64-bit DMA facilities & non-4K TCE tables etc.. */
 	/* XXX FIXME: Allocate multi-level tables on PHB3 */
@@ -1251,12 +1729,19 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 				 TCE_PCI_SWINV_PAIR);
 	}
 	iommu_init_table(tbl, phb->hose->node);
-	iommu_register_group(tbl, phb->hose->global_number, pe->pe_number);
 
-	if (pe->pdev)
+	if (pe->flags & PNV_IODA_PE_DEV) {
+		iommu_register_group(tbl, phb->hose->global_number,
+				     pe->pe_number);
 		set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
-	else
+	} else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) {
+		iommu_register_group(tbl, phb->hose->global_number,
+				     pe->pe_number);
 		pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
+	} else if (pe->flags & PNV_IODA_PE_VF) {
+		iommu_register_group(tbl, phb->hose->global_number,
+				     pe->pe_number);
+	}
 
 	return;
  fail:
@@ -1383,12 +1868,19 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 		tbl->it_type |= (TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE);
 	}
 	iommu_init_table(tbl, phb->hose->node);
-	iommu_register_group(tbl, phb->hose->global_number, pe->pe_number);
 
-	if (pe->pdev)
+	if (pe->flags & PNV_IODA_PE_DEV) {
+		iommu_register_group(tbl, phb->hose->global_number,
+				     pe->pe_number);
 		set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
-	else
+	} else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) {
+		iommu_register_group(tbl, phb->hose->global_number,
+				     pe->pe_number);
 		pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
+	} else if (pe->flags & PNV_IODA_PE_VF) {
+		iommu_register_group(tbl, phb->hose->global_number,
+				     pe->pe_number);
+	}
 
 	/* Also create a bypass window */
 	if (!pnv_iommu_bypass_disabled)
@@ -2068,6 +2560,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	phb->hub_id = hub_id;
 	phb->opal_id = phb_id;
 	phb->type = ioda_type;
+	mutex_init(&phb->ioda.pe_alloc_mutex);
 
 	/* Detect specific models for error handling */
 	if (of_device_is_compatible(np, "ibm,p7ioc-pciex"))
@@ -2127,6 +2620,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 
 	INIT_LIST_HEAD(&phb->ioda.pe_dma_list);
 	INIT_LIST_HEAD(&phb->ioda.pe_list);
+	mutex_init(&phb->ioda.pe_list_mutex);
 
 	/* Calculate how many 32-bit TCE segments we have */
 	phb->ioda.tce32_count = phb->ioda.m32_pci_base >> 28;
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 946aa3d62c3c..02badcef5cea 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -714,6 +714,24 @@ static void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
 {
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 	struct pnv_phb *phb = hose->private_data;
+#ifdef CONFIG_PCI_IOV
+	struct pnv_ioda_pe *pe;
+	struct pci_dn *pdn;
+
+	/* Fix the VF pdn PE number */
+	if (pdev->is_virtfn) {
+		pdn = pci_get_pdn(pdev);
+		WARN_ON(pdn->pe_number != IODA_INVALID_PE);
+		list_for_each_entry(pe, &phb->ioda.pe_list, list) {
+			if (pe->rid == ((pdev->bus->number << 8) |
+			    (pdev->devfn & 0xff))) {
+				pdn->pe_number = pe->pe_number;
+				pe->pdev = pdev;
+				break;
+			}
+		}
+	}
+#endif /* CONFIG_PCI_IOV */
 
 	/* If we have no phb structure, try to setup a fallback based on
 	 * the device-tree (RTAS PCI for example)
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 84280474e18f..070ee888fc95 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -23,6 +23,7 @@ enum pnv_phb_model {
 #define PNV_IODA_PE_BUS_ALL	(1 << 2)	/* PE has subordinate buses	*/
 #define PNV_IODA_PE_MASTER	(1 << 3)	/* Master PE in compound case	*/
 #define PNV_IODA_PE_SLAVE	(1 << 4)	/* Slave PE in compound case	*/
+#define PNV_IODA_PE_VF		(1 << 5)	/* PE for one VF 		*/
 
 /* Data associated with a PE, including IOMMU tracking etc.. */
 struct pnv_phb;
@@ -34,6 +35,9 @@ struct pnv_ioda_pe {
 	 * entire bus (& children). In the former case, pdev
 	 * is populated, in the later case, pbus is.
 	 */
+#ifdef CONFIG_PCI_IOV
+	struct pci_dev          *parent_dev;
+#endif
 	struct pci_dev		*pdev;
 	struct pci_bus		*pbus;
 
@@ -145,6 +149,8 @@ struct pnv_phb {
 
 			/* PE allocation bitmap */
 			unsigned long		*pe_alloc;
+			/* PE allocation mutex */
+			struct mutex		pe_alloc_mutex;
 
 			/* M32 & IO segment maps */
 			unsigned int		*m32_segmap;
@@ -159,6 +165,7 @@ struct pnv_phb {
 			 * on the sequence of creation
 			 */
 			struct list_head	pe_list;
+			struct mutex            pe_list_mutex;
 
 			/* Reverse map of PEs, will have to extend if
 			 * we are to support more than 256 PEs, indexed
-- 
cgit v1.2.3


From 5b88ec228498b7d41de6599eca12cc0032056e3f Mon Sep 17 00:00:00 2001
From: Wei Yang <weiyang@linux.vnet.ibm.com>
Date: Wed, 25 Mar 2015 16:23:58 +0800
Subject: powerpc/powernv: Reserve additional space for IOV BAR, with
 m64_per_iov supported

M64 aperture size is limited on PHB3.  When the IOV BAR is too big, this
will exceed the limitation and failed to be assigned.

Introduce a different mechanism based on the IOV BAR size:

  - if IOV BAR size is smaller than 64MB, expand to total_pe
  - if IOV BAR size is bigger than 64MB, roundup power2

[bhelgaas: make dev_printk() output more consistent, use PCI_SRIOV_NUM_BARS]
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/pci-bridge.h     |  2 ++
 arch/powerpc/platforms/powernv/pci-ioda.c | 33 ++++++++++++++++++++++++++++---
 2 files changed, 32 insertions(+), 3 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 8716db48e946..415df8509f52 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -182,6 +182,8 @@ struct pci_dn {
 	u16     vfs_expanded;		/* number of VFs IOV BAR expanded */
 	u16     num_vfs;		/* number of VFs enabled*/
 	int     offset;			/* PE# for the first VF PE */
+#define M64_PER_IOV 4
+	int     m64_per_iov;
 #define IODA_INVALID_M64        (-1)
 	int     m64_wins[PCI_SRIOV_NUM_BARS];
 #endif /* CONFIG_PCI_IOV */
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 5187d164cfe1..b63925f483fc 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -2250,6 +2250,7 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
 	int i;
 	resource_size_t size;
 	struct pci_dn *pdn;
+	int mul, total_vfs;
 
 	if (!pdev->is_physfn || pdev->is_added)
 		return;
@@ -2260,6 +2261,32 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
 	pdn = pci_get_pdn(pdev);
 	pdn->vfs_expanded = 0;
 
+	total_vfs = pci_sriov_get_totalvfs(pdev);
+	pdn->m64_per_iov = 1;
+	mul = phb->ioda.total_pe;
+
+	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
+		res = &pdev->resource[i + PCI_IOV_RESOURCES];
+		if (!res->flags || res->parent)
+			continue;
+		if (!pnv_pci_is_mem_pref_64(res->flags)) {
+			dev_warn(&pdev->dev, " non M64 VF BAR%d: %pR\n",
+				 i, res);
+			continue;
+		}
+
+		size = pci_iov_resource_size(pdev, i + PCI_IOV_RESOURCES);
+
+		/* bigger than 64M */
+		if (size > (1 << 26)) {
+			dev_info(&pdev->dev, "PowerNV: VF BAR%d: %pR IOV size is bigger than 64M, roundup power2\n",
+				 i, res);
+			pdn->m64_per_iov = M64_PER_IOV;
+			mul = roundup_pow_of_two(total_vfs);
+			break;
+		}
+	}
+
 	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
 		res = &pdev->resource[i + PCI_IOV_RESOURCES];
 		if (!res->flags || res->parent)
@@ -2272,12 +2299,12 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev)
 
 		dev_dbg(&pdev->dev, " Fixing VF BAR%d: %pR to\n", i, res);
 		size = pci_iov_resource_size(pdev, i + PCI_IOV_RESOURCES);
-		res->end = res->start + size * phb->ioda.total_pe - 1;
+		res->end = res->start + size * mul - 1;
 		dev_dbg(&pdev->dev, "                       %pR\n", res);
 		dev_info(&pdev->dev, "VF BAR%d: %pR (expanded to %d VFs for PE alignment)",
-				i, res, phb->ioda.total_pe);
+			 i, res, mul);
 	}
-	pdn->vfs_expanded = phb->ioda.total_pe;
+	pdn->vfs_expanded = mul;
 }
 #endif /* CONFIG_PCI_IOV */
 
-- 
cgit v1.2.3


From 02639b0e1326c3eff88d74fde6b5dbd04ace564e Mon Sep 17 00:00:00 2001
From: Wei Yang <weiyang@linux.vnet.ibm.com>
Date: Wed, 25 Mar 2015 16:23:59 +0800
Subject: powerpc/powernv: Group VF PE when IOV BAR is big on PHB3

When IOV BAR is big, each is covered by 4 M64 windows.  This leads to
several VF PE sits in one PE in terms of M64.

Group VF PEs according to the M64 allocation.

[bhelgaas: use dev_printk() when possible]
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/pci-bridge.h     |   2 +-
 arch/powerpc/platforms/powernv/pci-ioda.c | 197 +++++++++++++++++++++++-------
 2 files changed, 154 insertions(+), 45 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 415df8509f52..560c73996474 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -185,7 +185,7 @@ struct pci_dn {
 #define M64_PER_IOV 4
 	int     m64_per_iov;
 #define IODA_INVALID_M64        (-1)
-	int     m64_wins[PCI_SRIOV_NUM_BARS];
+	int     m64_wins[PCI_SRIOV_NUM_BARS][M64_PER_IOV];
 #endif /* CONFIG_PCI_IOV */
 #endif
 	struct list_head child_list;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index b63925f483fc..33088f6f7328 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1156,26 +1156,27 @@ static int pnv_pci_vf_release_m64(struct pci_dev *pdev)
 	struct pci_controller *hose;
 	struct pnv_phb        *phb;
 	struct pci_dn         *pdn;
-	int                    i;
+	int                    i, j;
 
 	bus = pdev->bus;
 	hose = pci_bus_to_host(bus);
 	phb = hose->private_data;
 	pdn = pci_get_pdn(pdev);
 
-	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
-		if (pdn->m64_wins[i] == IODA_INVALID_M64)
-			continue;
-		opal_pci_phb_mmio_enable(phb->opal_id,
-				OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i], 0);
-		clear_bit(pdn->m64_wins[i], &phb->ioda.m64_bar_alloc);
-		pdn->m64_wins[i] = IODA_INVALID_M64;
-	}
+	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++)
+		for (j = 0; j < M64_PER_IOV; j++) {
+			if (pdn->m64_wins[i][j] == IODA_INVALID_M64)
+				continue;
+			opal_pci_phb_mmio_enable(phb->opal_id,
+				OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 0);
+			clear_bit(pdn->m64_wins[i][j], &phb->ioda.m64_bar_alloc);
+			pdn->m64_wins[i][j] = IODA_INVALID_M64;
+		}
 
 	return 0;
 }
 
-static int pnv_pci_vf_assign_m64(struct pci_dev *pdev)
+static int pnv_pci_vf_assign_m64(struct pci_dev *pdev, u16 num_vfs)
 {
 	struct pci_bus        *bus;
 	struct pci_controller *hose;
@@ -1183,17 +1184,33 @@ static int pnv_pci_vf_assign_m64(struct pci_dev *pdev)
 	struct pci_dn         *pdn;
 	unsigned int           win;
 	struct resource       *res;
-	int                    i;
+	int                    i, j;
 	int64_t                rc;
+	int                    total_vfs;
+	resource_size_t        size, start;
+	int                    pe_num;
+	int                    vf_groups;
+	int                    vf_per_group;
 
 	bus = pdev->bus;
 	hose = pci_bus_to_host(bus);
 	phb = hose->private_data;
 	pdn = pci_get_pdn(pdev);
+	total_vfs = pci_sriov_get_totalvfs(pdev);
 
 	/* Initialize the m64_wins to IODA_INVALID_M64 */
 	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++)
-		pdn->m64_wins[i] = IODA_INVALID_M64;
+		for (j = 0; j < M64_PER_IOV; j++)
+			pdn->m64_wins[i][j] = IODA_INVALID_M64;
+
+	if (pdn->m64_per_iov == M64_PER_IOV) {
+		vf_groups = (num_vfs <= M64_PER_IOV) ? num_vfs: M64_PER_IOV;
+		vf_per_group = (num_vfs <= M64_PER_IOV)? 1:
+			roundup_pow_of_two(num_vfs) / pdn->m64_per_iov;
+	} else {
+		vf_groups = 1;
+		vf_per_group = 1;
+	}
 
 	for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) {
 		res = &pdev->resource[i + PCI_IOV_RESOURCES];
@@ -1203,35 +1220,61 @@ static int pnv_pci_vf_assign_m64(struct pci_dev *pdev)
 		if (!pnv_pci_is_mem_pref_64(res->flags))
 			continue;
 
-		do {
-			win = find_next_zero_bit(&phb->ioda.m64_bar_alloc,
-					phb->ioda.m64_bar_idx + 1, 0);
-
-			if (win >= phb->ioda.m64_bar_idx + 1)
-				goto m64_failed;
-		} while (test_and_set_bit(win, &phb->ioda.m64_bar_alloc));
+		for (j = 0; j < vf_groups; j++) {
+			do {
+				win = find_next_zero_bit(&phb->ioda.m64_bar_alloc,
+						phb->ioda.m64_bar_idx + 1, 0);
+
+				if (win >= phb->ioda.m64_bar_idx + 1)
+					goto m64_failed;
+			} while (test_and_set_bit(win, &phb->ioda.m64_bar_alloc));
+
+			pdn->m64_wins[i][j] = win;
+
+			if (pdn->m64_per_iov == M64_PER_IOV) {
+				size = pci_iov_resource_size(pdev,
+							PCI_IOV_RESOURCES + i);
+				size = size * vf_per_group;
+				start = res->start + size * j;
+			} else {
+				size = resource_size(res);
+				start = res->start;
+			}
 
-		pdn->m64_wins[i] = win;
+			/* Map the M64 here */
+			if (pdn->m64_per_iov == M64_PER_IOV) {
+				pe_num = pdn->offset + j;
+				rc = opal_pci_map_pe_mmio_window(phb->opal_id,
+						pe_num, OPAL_M64_WINDOW_TYPE,
+						pdn->m64_wins[i][j], 0);
+			}
 
-		/* Map the M64 here */
-		rc = opal_pci_set_phb_mem_window(phb->opal_id,
+			rc = opal_pci_set_phb_mem_window(phb->opal_id,
 						 OPAL_M64_WINDOW_TYPE,
-						 pdn->m64_wins[i],
-						 res->start,
+						 pdn->m64_wins[i][j],
+						 start,
 						 0, /* unused */
-						 resource_size(res));
-		if (rc != OPAL_SUCCESS) {
-			dev_err(&pdev->dev, "Failed to map M64 window #%d: %lld\n",
-				win, rc);
-			goto m64_failed;
-		}
+						 size);
 
-		rc = opal_pci_phb_mmio_enable(phb->opal_id,
-				OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i], 1);
-		if (rc != OPAL_SUCCESS) {
-			dev_err(&pdev->dev, "Failed to enable M64 window #%d: %llx\n",
-				win, rc);
-			goto m64_failed;
+
+			if (rc != OPAL_SUCCESS) {
+				dev_err(&pdev->dev, "Failed to map M64 window #%d: %lld\n",
+					win, rc);
+				goto m64_failed;
+			}
+
+			if (pdn->m64_per_iov == M64_PER_IOV)
+				rc = opal_pci_phb_mmio_enable(phb->opal_id,
+				     OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 2);
+			else
+				rc = opal_pci_phb_mmio_enable(phb->opal_id,
+				     OPAL_M64_WINDOW_TYPE, pdn->m64_wins[i][j], 1);
+
+			if (rc != OPAL_SUCCESS) {
+				dev_err(&pdev->dev, "Failed to enable M64 window #%d: %llx\n",
+					win, rc);
+				goto m64_failed;
+			}
 		}
 	}
 	return 0;
@@ -1273,22 +1316,53 @@ static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe
 	pe->tce32_table = NULL;
 }
 
-static void pnv_ioda_release_vf_PE(struct pci_dev *pdev)
+static void pnv_ioda_release_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 {
 	struct pci_bus        *bus;
 	struct pci_controller *hose;
 	struct pnv_phb        *phb;
 	struct pnv_ioda_pe    *pe, *pe_n;
 	struct pci_dn         *pdn;
+	u16                    vf_index;
+	int64_t                rc;
 
 	bus = pdev->bus;
 	hose = pci_bus_to_host(bus);
 	phb = hose->private_data;
+	pdn = pci_get_pdn(pdev);
 
 	if (!pdev->is_physfn)
 		return;
 
-	pdn = pci_get_pdn(pdev);
+	if (pdn->m64_per_iov == M64_PER_IOV && num_vfs > M64_PER_IOV) {
+		int   vf_group;
+		int   vf_per_group;
+		int   vf_index1;
+
+		vf_per_group = roundup_pow_of_two(num_vfs) / pdn->m64_per_iov;
+
+		for (vf_group = 0; vf_group < M64_PER_IOV; vf_group++)
+			for (vf_index = vf_group * vf_per_group;
+				vf_index < (vf_group + 1) * vf_per_group &&
+				vf_index < num_vfs;
+				vf_index++)
+				for (vf_index1 = vf_group * vf_per_group;
+					vf_index1 < (vf_group + 1) * vf_per_group &&
+					vf_index1 < num_vfs;
+					vf_index1++){
+
+					rc = opal_pci_set_peltv(phb->opal_id,
+						pdn->offset + vf_index,
+						pdn->offset + vf_index1,
+						OPAL_REMOVE_PE_FROM_DOMAIN);
+
+					if (rc)
+					    dev_warn(&pdev->dev, "%s: Failed to unlink same group PE#%d(%lld)\n",
+						__func__,
+						pdn->offset + vf_index1, rc);
+				}
+	}
+
 	list_for_each_entry_safe(pe, pe_n, &phb->ioda.pe_list, list) {
 		if (pe->parent_dev != pdev)
 			continue;
@@ -1323,10 +1397,11 @@ void pnv_pci_sriov_disable(struct pci_dev *pdev)
 	num_vfs = pdn->num_vfs;
 
 	/* Release VF PEs */
-	pnv_ioda_release_vf_PE(pdev);
+	pnv_ioda_release_vf_PE(pdev, num_vfs);
 
 	if (phb->type == PNV_PHB_IODA2) {
-		pnv_pci_vf_resource_shift(pdev, -pdn->offset);
+		if (pdn->m64_per_iov == 1)
+			pnv_pci_vf_resource_shift(pdev, -pdn->offset);
 
 		/* Release M64 windows */
 		pnv_pci_vf_release_m64(pdev);
@@ -1348,6 +1423,7 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 	int                    pe_num;
 	u16                    vf_index;
 	struct pci_dn         *pdn;
+	int64_t                rc;
 
 	bus = pdev->bus;
 	hose = pci_bus_to_host(bus);
@@ -1396,6 +1472,37 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs)
 
 		pnv_pci_ioda2_setup_dma_pe(phb, pe);
 	}
+
+	if (pdn->m64_per_iov == M64_PER_IOV && num_vfs > M64_PER_IOV) {
+		int   vf_group;
+		int   vf_per_group;
+		int   vf_index1;
+
+		vf_per_group = roundup_pow_of_two(num_vfs) / pdn->m64_per_iov;
+
+		for (vf_group = 0; vf_group < M64_PER_IOV; vf_group++) {
+			for (vf_index = vf_group * vf_per_group;
+			     vf_index < (vf_group + 1) * vf_per_group &&
+			     vf_index < num_vfs;
+			     vf_index++) {
+				for (vf_index1 = vf_group * vf_per_group;
+				     vf_index1 < (vf_group + 1) * vf_per_group &&
+				     vf_index1 < num_vfs;
+				     vf_index1++) {
+
+					rc = opal_pci_set_peltv(phb->opal_id,
+						pdn->offset + vf_index,
+						pdn->offset + vf_index1,
+						OPAL_ADD_PE_TO_DOMAIN);
+
+					if (rc)
+					    dev_warn(&pdev->dev, "%s: Failed to link same group PE#%d(%lld)\n",
+						__func__,
+						pdn->offset + vf_index1, rc);
+				}
+			}
+		}
+	}
 }
 
 int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
@@ -1428,7 +1535,7 @@ int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
 		mutex_unlock(&phb->ioda.pe_alloc_mutex);
 
 		/* Assign M64 window accordingly */
-		ret = pnv_pci_vf_assign_m64(pdev);
+		ret = pnv_pci_vf_assign_m64(pdev, num_vfs);
 		if (ret) {
 			dev_info(&pdev->dev, "Not enough M64 window resources\n");
 			goto m64_failed;
@@ -1439,9 +1546,11 @@ int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs)
 		 * the IOV BAR according to the PE# allocated to the VFs.
 		 * Otherwise, the PE# for the VF will conflict with others.
 		 */
-		ret = pnv_pci_vf_resource_shift(pdev, pdn->offset);
-		if (ret)
-			goto m64_failed;
+		if (pdn->m64_per_iov == 1) {
+			ret = pnv_pci_vf_resource_shift(pdev, pdn->offset);
+			if (ret)
+				goto m64_failed;
+		}
 	}
 
 	/* Setup VF PEs */
-- 
cgit v1.2.3


From 250c7b277c65e801a3312061dc2e919233468916 Mon Sep 17 00:00:00 2001
From: Wei Yang <weiyang@linux.vnet.ibm.com>
Date: Wed, 25 Mar 2015 16:24:00 +0800
Subject: powerpc/pci: Remove unused struct pci_dn.pcidev field

In struct pci_dn, the pcidev field is assigned but not used, so remove it.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/pci-bridge.h     | 1 -
 arch/powerpc/platforms/powernv/pci-ioda.c | 1 -
 2 files changed, 2 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 560c73996474..a39270e85beb 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -171,7 +171,6 @@ struct pci_dn {
 
 	int	pci_ext_config_space;	/* for pci devices */
 
-	struct	pci_dev *pcidev;	/* back-pointer to the pci device */
 #ifdef CONFIG_EEH
 	struct eeh_dev *edev;		/* eeh device */
 #endif
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 33088f6f7328..b1387ea6d10a 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1028,7 +1028,6 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe)
 				pci_name(dev));
 			continue;
 		}
-		pdn->pcidev = dev;
 		pdn->pe_number = pe->pe_number;
 		pe->dma_weight += pnv_ioda_dma_weight(dev);
 		if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate)
-- 
cgit v1.2.3


From 027fa02f84e851e21daffdf8900d6117071890f8 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Fri, 27 Mar 2015 11:29:00 +1100
Subject: powerpc/powernv: Don't map M64 segments using M32DT

If M64 has been supported, the prefetchable 64-bits memory resources
shouldn't be mapped to the corresponding PE# via M32DT. Unfortunately,
we're doing that in pnv_ioda_setup_pe_seg() wrongly. The issue was
introduced by commit 262af55 ("powerpc/powernv: Enable M64 aperatus
for PHB3"). The patch fixes the issue by simply skipping M64 resources
when updating to M32DT.

Cc: <stable@vger.kernel.org>  # v3.17+
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/pci-ioda.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 26fe09936935..76b344125cef 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1777,7 +1777,8 @@ static void pnv_ioda_setup_pe_seg(struct pci_controller *hose,
 				region.start += phb->ioda.io_segsize;
 				index++;
 			}
-		} else if (res->flags & IORESOURCE_MEM) {
+		} else if ((res->flags & IORESOURCE_MEM) &&
+			   !pnv_pci_is_mem_pref_64(res->flags)) {
 			region.start = res->start -
 				       hose->mem_offset[0] -
 				       phb->ioda.m32_pci_base;
-- 
cgit v1.2.3


From e3c5c2e0bc857c7cbdb81f35a6b90236c5f330e9 Mon Sep 17 00:00:00 2001
From: Cédric Le Goater <clg@fr.ibm.com>
Date: Mon, 30 Mar 2015 12:06:09 +0200
Subject: powerpc/powernv: convert codes returned by OPAL calls
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

OPAL has its own list of return codes. The patch provides a translation
of such codes in errnos for the opal_sensor_read call, and possibly
others if needed.

Signed-off-by: Cédric Le Goater <clg@fr.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/opal.h              |  2 ++
 arch/powerpc/platforms/powernv/opal-sensor.c |  6 ++++--
 arch/powerpc/platforms/powernv/opal.c        | 19 +++++++++++++++++++
 3 files changed, 25 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index c08de77f398a..fde90bacc65e 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -247,6 +247,8 @@ struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr,
 					     unsigned long vmalloc_size);
 void opal_free_sg_list(struct opal_sg_list *sg);
 
+extern int opal_error_code(int rc);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_OPAL_H */
diff --git a/arch/powerpc/platforms/powernv/opal-sensor.c b/arch/powerpc/platforms/powernv/opal-sensor.c
index 4ab67ef7abc9..e9c5d8f33d4c 100644
--- a/arch/powerpc/platforms/powernv/opal-sensor.c
+++ b/arch/powerpc/platforms/powernv/opal-sensor.c
@@ -46,8 +46,10 @@ int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data)
 
 	mutex_lock(&opal_sensor_mutex);
 	ret = opal_sensor_read(sensor_hndl, token, &data);
-	if (ret != OPAL_ASYNC_COMPLETION)
+	if (ret != OPAL_ASYNC_COMPLETION) {
+		ret = opal_error_code(ret);
 		goto out_token;
+	}
 
 	ret = opal_async_wait_response(token, &msg);
 	if (ret) {
@@ -57,7 +59,7 @@ int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data)
 	}
 
 	*sensor_data = be32_to_cpu(data);
-	ret = be64_to_cpu(msg.params[1]);
+	ret = opal_error_code(be64_to_cpu(msg.params[1]));
 
 out_token:
 	mutex_unlock(&opal_sensor_mutex);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index d403b2b08626..3fb981c0ca80 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -931,6 +931,25 @@ void opal_free_sg_list(struct opal_sg_list *sg)
 	}
 }
 
+int opal_error_code(int rc)
+{
+	switch (rc) {
+	case OPAL_SUCCESS:		return 0;
+
+	case OPAL_PARAMETER:		return -EINVAL;
+	case OPAL_ASYNC_COMPLETION:	return -EINPROGRESS;
+	case OPAL_BUSY_EVENT:		return -EBUSY;
+	case OPAL_NO_MEM:		return -ENOMEM;
+
+	case OPAL_UNSUPPORTED:		return -EIO;
+	case OPAL_HARDWARE:		return -EIO;
+	case OPAL_INTERNAL_ERROR:	return -EIO;
+	default:
+		pr_err("%s: unexpected OPAL error %d\n", __func__, rc);
+		return -EIO;
+	}
+}
+
 EXPORT_SYMBOL_GPL(opal_poll_events);
 EXPORT_SYMBOL_GPL(opal_rtc_read);
 EXPORT_SYMBOL_GPL(opal_rtc_write);
-- 
cgit v1.2.3


From 6bc08d03e745a0b369bd28294b969e4fdaf7be9f Mon Sep 17 00:00:00 2001
From: Cédric Le Goater <clg@fr.ibm.com>
Date: Mon, 30 Mar 2015 12:06:10 +0200
Subject: powerpc/powernv: handle OPAL_SUCCESS return in opal_sensor_read
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, when a sensor value is read, the kernel calls OPAL, which in
turn builds a message for the FSP, and waits for a message back.

The new device tree for OPAL sensors [1] adds new sensors that can be
read synchronously (core temperatures for instance) and that don't need
to wait for a response.

This patch modifies the opal call to accept an OPAL_SUCCESS return value
and cover the case above.

[1] https://lists.ozlabs.org/pipermail/skiboot/2015-March/000639.html

Signed-off-by: Cédric Le Goater <clg@fr.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/platforms/powernv/opal-sensor.c | 32 +++++++++++++++++-----------
 1 file changed, 20 insertions(+), 12 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/opal-sensor.c b/arch/powerpc/platforms/powernv/opal-sensor.c
index e9c5d8f33d4c..655250499d18 100644
--- a/arch/powerpc/platforms/powernv/opal-sensor.c
+++ b/arch/powerpc/platforms/powernv/opal-sensor.c
@@ -46,20 +46,28 @@ int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data)
 
 	mutex_lock(&opal_sensor_mutex);
 	ret = opal_sensor_read(sensor_hndl, token, &data);
-	if (ret != OPAL_ASYNC_COMPLETION) {
-		ret = opal_error_code(ret);
-		goto out_token;
-	}
+	switch (ret) {
+	case OPAL_ASYNC_COMPLETION:
+		ret = opal_async_wait_response(token, &msg);
+		if (ret) {
+			pr_err("%s: Failed to wait for the async response, %d\n",
+			       __func__, ret);
+			goto out_token;
+		}
 
-	ret = opal_async_wait_response(token, &msg);
-	if (ret) {
-		pr_err("%s: Failed to wait for the async response, %d\n",
-				__func__, ret);
-		goto out_token;
-	}
+		ret = opal_error_code(be64_to_cpu(msg.params[1]));
+		*sensor_data = be32_to_cpu(data);
+		break;
 
-	*sensor_data = be32_to_cpu(data);
-	ret = opal_error_code(be64_to_cpu(msg.params[1]));
+	case OPAL_SUCCESS:
+		ret = 0;
+		*sensor_data = be32_to_cpu(data);
+		break;
+
+	default:
+		ret = opal_error_code(ret);
+		break;
+	}
 
 out_token:
 	mutex_unlock(&opal_sensor_mutex);
-- 
cgit v1.2.3


From 646b54f2f2041473495f166479e3e17fd59a9dd1 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Thu, 12 Mar 2015 17:27:11 +1100
Subject: powerpc/powernv: Remove powernv RTAS support

The powernv code has some conditional support for running on bare metal
machines that have no OPAL firmware, but provide RTAS.

No released machines ever supported that, and even in the lab it was
just a transitional hack in the days when OPAL was still being
developed.

So remove the code.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Stewart Smith <stewart@linux.vnet.ibm.com>
---
 arch/powerpc/platforms/powernv/Kconfig |  7 ---
 arch/powerpc/platforms/powernv/pci.c   | 98 +++++++---------------------------
 arch/powerpc/platforms/powernv/setup.c | 19 -------
 arch/powerpc/platforms/powernv/smp.c   | 13 -----
 4 files changed, 19 insertions(+), 118 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
index 45a8ed0585cd..4b044d8cb49a 100644
--- a/arch/powerpc/platforms/powernv/Kconfig
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -19,10 +19,3 @@ config PPC_POWERNV
 	select CPU_FREQ_GOV_CONSERVATIVE
 	select PPC_DOORBELL
 	default y
-
-config PPC_POWERNV_RTAS
-	depends on PPC_POWERNV
-	bool "Support for RTAS based PowerNV platforms such as BML"
-	default y
-	select PPC_ICS_RTAS
-	select PPC_RTAS
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 946aa3d62c3c..4aa2e74534e8 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -662,66 +662,13 @@ void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
 	tbl->it_type = TCE_PCI;
 }
 
-static struct iommu_table *pnv_pci_setup_bml_iommu(struct pci_controller *hose)
-{
-	struct iommu_table *tbl;
-	const __be64 *basep, *swinvp;
-	const __be32 *sizep;
-
-	basep = of_get_property(hose->dn, "linux,tce-base", NULL);
-	sizep = of_get_property(hose->dn, "linux,tce-size", NULL);
-	if (basep == NULL || sizep == NULL) {
-		pr_err("PCI: %s has missing tce entries !\n",
-		       hose->dn->full_name);
-		return NULL;
-	}
-	tbl = kzalloc_node(sizeof(struct iommu_table), GFP_KERNEL, hose->node);
-	if (WARN_ON(!tbl))
-		return NULL;
-	pnv_pci_setup_iommu_table(tbl, __va(be64_to_cpup(basep)),
-				  be32_to_cpup(sizep), 0, IOMMU_PAGE_SHIFT_4K);
-	iommu_init_table(tbl, hose->node);
-	iommu_register_group(tbl, pci_domain_nr(hose->bus), 0);
-
-	/* Deal with SW invalidated TCEs when needed (BML way) */
-	swinvp = of_get_property(hose->dn, "linux,tce-sw-invalidate-info",
-				 NULL);
-	if (swinvp) {
-		tbl->it_busno = be64_to_cpu(swinvp[1]);
-		tbl->it_index = (unsigned long)ioremap(be64_to_cpup(swinvp), 8);
-		tbl->it_type = TCE_PCI_SWINV_CREATE | TCE_PCI_SWINV_FREE;
-	}
-	return tbl;
-}
-
-static void pnv_pci_dma_fallback_setup(struct pci_controller *hose,
-				       struct pci_dev *pdev)
-{
-	struct device_node *np = pci_bus_to_OF_node(hose->bus);
-	struct pci_dn *pdn;
-
-	if (np == NULL)
-		return;
-	pdn = PCI_DN(np);
-	if (!pdn->iommu_table)
-		pdn->iommu_table = pnv_pci_setup_bml_iommu(hose);
-	if (!pdn->iommu_table)
-		return;
-	set_iommu_table_base_and_group(&pdev->dev, pdn->iommu_table);
-}
-
 static void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
 {
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 	struct pnv_phb *phb = hose->private_data;
 
-	/* If we have no phb structure, try to setup a fallback based on
-	 * the device-tree (RTAS PCI for example)
-	 */
 	if (phb && phb->dma_dev_setup)
 		phb->dma_dev_setup(phb, pdev);
-	else
-		pnv_pci_dma_fallback_setup(hose, pdev);
 }
 
 int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
@@ -767,38 +714,31 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_IBM, 0x3b9, pnv_p7ioc_rc_quirk);
 void __init pnv_pci_init(void)
 {
 	struct device_node *np;
+	bool found_ioda = false;
 
 	pci_add_flags(PCI_CAN_SKIP_ISA_ALIGN);
 
-	/* OPAL absent, try POPAL first then RTAS detection of PHBs */
-	if (!firmware_has_feature(FW_FEATURE_OPAL)) {
-#ifdef CONFIG_PPC_POWERNV_RTAS
-		init_pci_config_tokens();
-		find_and_init_phbs();
-#endif /* CONFIG_PPC_POWERNV_RTAS */
-	}
-	/* OPAL is here, do our normal stuff */
-	else {
-		int found_ioda = 0;
+	/* If we don't have OPAL, eg. in sim, just skip PCI probe */
+	if (!firmware_has_feature(FW_FEATURE_OPAL))
+		return;
 
-		/* Look for IODA IO-Hubs. We don't support mixing IODA
-		 * and p5ioc2 due to the need to change some global
-		 * probing flags
-		 */
-		for_each_compatible_node(np, NULL, "ibm,ioda-hub") {
-			pnv_pci_init_ioda_hub(np);
-			found_ioda = 1;
-		}
+	/* Look for IODA IO-Hubs. We don't support mixing IODA
+	 * and p5ioc2 due to the need to change some global
+	 * probing flags
+	 */
+	for_each_compatible_node(np, NULL, "ibm,ioda-hub") {
+		pnv_pci_init_ioda_hub(np);
+		found_ioda = true;
+	}
 
-		/* Look for p5ioc2 IO-Hubs */
-		if (!found_ioda)
-			for_each_compatible_node(np, NULL, "ibm,p5ioc2")
-				pnv_pci_init_p5ioc2_hub(np);
+	/* Look for p5ioc2 IO-Hubs */
+	if (!found_ioda)
+		for_each_compatible_node(np, NULL, "ibm,p5ioc2")
+			pnv_pci_init_p5ioc2_hub(np);
 
-		/* Look for ioda2 built-in PHB3's */
-		for_each_compatible_node(np, NULL, "ibm,ioda2-phb")
-			pnv_pci_init_ioda2_phb(np);
-	}
+	/* Look for ioda2 built-in PHB3's */
+	for_each_compatible_node(np, NULL, "ibm,ioda2-phb")
+		pnv_pci_init_ioda2_phb(np);
 
 	/* Setup the linkage between OF nodes and PHBs */
 	pci_devs_phb_init();
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 39d1971d77db..16fdcb23f4c3 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -32,7 +32,6 @@
 #include <asm/machdep.h>
 #include <asm/firmware.h>
 #include <asm/xics.h>
-#include <asm/rtas.h>
 #include <asm/opal.h>
 #include <asm/kexec.h>
 #include <asm/smp.h>
@@ -278,20 +277,6 @@ static void __init pnv_setup_machdep_opal(void)
 	ppc_md.handle_hmi_exception = opal_handle_hmi_exception;
 }
 
-#ifdef CONFIG_PPC_POWERNV_RTAS
-static void __init pnv_setup_machdep_rtas(void)
-{
-	if (rtas_token("get-time-of-day") != RTAS_UNKNOWN_SERVICE) {
-		ppc_md.get_boot_time = rtas_get_boot_time;
-		ppc_md.get_rtc_time = rtas_get_rtc_time;
-		ppc_md.set_rtc_time = rtas_set_rtc_time;
-	}
-	ppc_md.restart = rtas_restart;
-	pm_power_off = rtas_power_off;
-	ppc_md.halt = rtas_halt;
-}
-#endif /* CONFIG_PPC_POWERNV_RTAS */
-
 static u32 supported_cpuidle_states;
 
 int pnv_save_sprs_for_winkle(void)
@@ -470,10 +455,6 @@ static int __init pnv_probe(void)
 
 	if (firmware_has_feature(FW_FEATURE_OPAL))
 		pnv_setup_machdep_opal();
-#ifdef CONFIG_PPC_POWERNV_RTAS
-	else if (rtas.base)
-		pnv_setup_machdep_rtas();
-#endif /* CONFIG_PPC_POWERNV_RTAS */
 
 	pr_debug("PowerNV detected !\n");
 
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index fc34025ef822..273d7b46f72a 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -25,7 +25,6 @@
 #include <asm/machdep.h>
 #include <asm/cputable.h>
 #include <asm/firmware.h>
-#include <asm/rtas.h>
 #include <asm/vdso_datapage.h>
 #include <asm/cputhreads.h>
 #include <asm/xics.h>
@@ -241,18 +240,6 @@ void __init pnv_smp_init(void)
 {
 	smp_ops = &pnv_smp_ops;
 
-	/* XXX We don't yet have a proper entry point from HAL, for
-	 * now we rely on kexec-style entry from BML
-	 */
-
-#ifdef CONFIG_PPC_RTAS
-	/* Non-lpar has additional take/give timebase */
-	if (rtas_token("freeze-time-base") != RTAS_UNKNOWN_SERVICE) {
-		smp_ops->give_timebase = rtas_give_timebase;
-		smp_ops->take_timebase = rtas_take_timebase;
-	}
-#endif /* CONFIG_PPC_RTAS */
-
 #ifdef CONFIG_HOTPLUG_CPU
 	ppc_md.cpu_die	= pnv_smp_cpu_kill_self;
 #endif
-- 
cgit v1.2.3


From c88c2a188905cb3077c3c38dc498e7e9f8eebeee Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Tue, 31 Mar 2015 16:00:41 +1100
Subject: powerpc: pcibios_enable_device_hook: return bool rather than int

pcibios_enable_device_hook returned an int. Every implementation
returned either -EINVAL or 0. The return value wasn't propagated by
the caller: any non-zero return value caused pcibios_enable_device
to return -EINVAL itself. Therefore, make the hook return a bool.

Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/machdep.h        | 4 ++--
 arch/powerpc/kernel/pci-common.c          | 2 +-
 arch/powerpc/platforms/powermac/pci.c     | 8 ++++----
 arch/powerpc/platforms/powermac/pmac.h    | 2 +-
 arch/powerpc/platforms/powernv/pci-ioda.c | 8 ++++----
 5 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 098d51e924ea..e29f058c0903 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -237,9 +237,9 @@ struct machdep_calls {
 	/* Called for each PCI bus in the system when it's probed */
 	void (*pcibios_fixup_bus)(struct pci_bus *);
 
-	/* Called when pci_enable_device() is called. Returns 0 to
+	/* Called when pci_enable_device() is called. Returns true to
 	 * allow assignment/enabling of the device. */
-	int  (*pcibios_enable_device_hook)(struct pci_dev *);
+	bool (*pcibios_enable_device_hook)(struct pci_dev *);
 
 	/* Called after scan and before resource survey */
 	void (*pcibios_fixup_phb)(struct pci_controller *hose);
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index bcf618bfff1e..17827c7345a7 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1451,7 +1451,7 @@ EXPORT_SYMBOL_GPL(pcibios_finish_adding_to_bus);
 int pcibios_enable_device(struct pci_dev *dev, int mask)
 {
 	if (ppc_md.pcibios_enable_device_hook)
-		if (ppc_md.pcibios_enable_device_hook(dev))
+		if (!ppc_md.pcibios_enable_device_hook(dev))
 			return -EINVAL;
 
 	return pci_enable_resources(dev, mask);
diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c
index a792f4552442..9c89fd29da60 100644
--- a/arch/powerpc/platforms/powermac/pci.c
+++ b/arch/powerpc/platforms/powermac/pci.c
@@ -942,7 +942,7 @@ void __init pmac_pci_init(void)
 }
 
 #ifdef CONFIG_PPC32
-int pmac_pci_enable_device_hook(struct pci_dev *dev)
+bool pmac_pci_enable_device_hook(struct pci_dev *dev)
 {
 	struct device_node* node;
 	int updatecfg = 0;
@@ -958,11 +958,11 @@ int pmac_pci_enable_device_hook(struct pci_dev *dev)
 	    && !node) {
 		printk(KERN_INFO "Apple USB OHCI %s disabled by firmware\n",
 		       pci_name(dev));
-		return -EINVAL;
+		return false;
 	}
 
 	if (!node)
-		return 0;
+		return true;
 
 	uninorth_child = node->parent &&
 		of_device_is_compatible(node->parent, "uni-north");
@@ -1003,7 +1003,7 @@ int pmac_pci_enable_device_hook(struct pci_dev *dev)
 				      L1_CACHE_BYTES >> 2);
 	}
 
-	return 0;
+	return true;
 }
 
 void pmac_pci_fixup_ohci(struct pci_dev *dev)
diff --git a/arch/powerpc/platforms/powermac/pmac.h b/arch/powerpc/platforms/powermac/pmac.h
index 46d219345537..b8d572159faa 100644
--- a/arch/powerpc/platforms/powermac/pmac.h
+++ b/arch/powerpc/platforms/powermac/pmac.h
@@ -25,7 +25,7 @@ extern void pmac_pci_init(void);
 extern void pmac_nvram_update(void);
 extern unsigned char pmac_nvram_read_byte(int addr);
 extern void pmac_nvram_write_byte(int addr, unsigned char val);
-extern int pmac_pci_enable_device_hook(struct pci_dev *dev);
+extern bool pmac_pci_enable_device_hook(struct pci_dev *dev);
 extern void pmac_pcibios_after_init(void);
 extern int of_show_percpuinfo(struct seq_file *m, int i);
 
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 76b344125cef..f93d6c2bd743 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1911,7 +1911,7 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus,
 /* Prevent enabling devices for which we couldn't properly
  * assign a PE
  */
-static int pnv_pci_enable_device_hook(struct pci_dev *dev)
+static bool pnv_pci_enable_device_hook(struct pci_dev *dev)
 {
 	struct pci_controller *hose = pci_bus_to_host(dev->bus);
 	struct pnv_phb *phb = hose->private_data;
@@ -1923,13 +1923,13 @@ static int pnv_pci_enable_device_hook(struct pci_dev *dev)
 	 * PEs isn't ready.
 	 */
 	if (!phb->initialized)
-		return 0;
+		return true;
 
 	pdn = pci_get_pdn(dev);
 	if (!pdn || pdn->pe_number == IODA_INVALID_PE)
-		return -EINVAL;
+		return false;
 
-	return 0;
+	return true;
 }
 
 static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus,
-- 
cgit v1.2.3


From 65ebf4b6370e8eabbf31076de022e49926dd4573 Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Tue, 31 Mar 2015 16:00:51 +1100
Subject: powerpc/powernv: Move controller ops from ppc_md to controller_ops

This moves the PowerNV platform to use the pci_controller_ops
structure rather than ppc_md for PCI controller operations.

Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/platforms/powernv/pci-ioda.c   | 7 ++++---
 arch/powerpc/platforms/powernv/pci-p5ioc2.c | 1 +
 arch/powerpc/platforms/powernv/pci.c        | 5 ++++-
 arch/powerpc/platforms/powernv/powernv.h    | 2 ++
 4 files changed, 11 insertions(+), 4 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index f93d6c2bd743..5e917753c672 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1989,6 +1989,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 		hose->last_busno = 0xff;
 	}
 	hose->private_data = phb;
+	hose->controller_ops = pnv_pci_controller_ops;
 	phb->hub_id = hub_id;
 	phb->opal_id = phb_id;
 	phb->type = ioda_type;
@@ -2102,9 +2103,9 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	 * the child P2P bridges) can form individual PE.
 	 */
 	ppc_md.pcibios_fixup = pnv_pci_ioda_fixup;
-	ppc_md.pcibios_enable_device_hook = pnv_pci_enable_device_hook;
-	ppc_md.pcibios_window_alignment = pnv_pci_window_alignment;
-	ppc_md.pcibios_reset_secondary_bus = pnv_pci_reset_secondary_bus;
+	pnv_pci_controller_ops.enable_device_hook = pnv_pci_enable_device_hook;
+	pnv_pci_controller_ops.window_alignment = pnv_pci_window_alignment;
+	pnv_pci_controller_ops.reset_secondary_bus = pnv_pci_reset_secondary_bus;
 	pci_add_flags(PCI_REASSIGN_ALL_RSRC);
 
 	/* Reset IODA tables to a clean state */
diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
index 6ef6d4d8e7e2..4729ca793813 100644
--- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c
+++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
@@ -133,6 +133,7 @@ static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id,
 	phb->hose->first_busno = 0;
 	phb->hose->last_busno = 0xff;
 	phb->hose->private_data = phb;
+	phb->hose->controller_ops = pnv_pci_controller_ops;
 	phb->hub_id = hub_id;
 	phb->opal_id = phb_id;
 	phb->type = PNV_PHB_P5IOC2;
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 4aa2e74534e8..fa96aa8aa1e2 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -744,7 +744,6 @@ void __init pnv_pci_init(void)
 	pci_devs_phb_init();
 
 	/* Configure IOMMU DMA hooks */
-	ppc_md.pci_dma_dev_setup = pnv_pci_dma_dev_setup;
 	ppc_md.tce_build = pnv_tce_build_vm;
 	ppc_md.tce_free = pnv_tce_free_vm;
 	ppc_md.tce_build_rm = pnv_tce_build_rm;
@@ -760,3 +759,7 @@ void __init pnv_pci_init(void)
 }
 
 machine_subsys_initcall_sync(powernv, tce_iommu_bus_notifier_init);
+
+struct pci_controller_ops pnv_pci_controller_ops = {
+	.dma_dev_setup = pnv_pci_dma_dev_setup,
+};
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index 604c48e7879a..826d2c9bea56 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -29,6 +29,8 @@ static inline u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev)
 }
 #endif
 
+extern struct pci_controller_ops pnv_pci_controller_ops;
+
 extern u32 pnv_get_supported_cpuidle_states(void);
 
 extern void pnv_lpc_init(void);
-- 
cgit v1.2.3


From ed59190e41b725e1cfd79541f5fc66c20adb0671 Mon Sep 17 00:00:00 2001
From: Cyril Bur <cyrilbur@gmail.com>
Date: Wed, 1 Apr 2015 14:05:30 +0800
Subject: powerpc/powernv: Add interfaces for flash device access

This change adds the OPAL interface definitions to allow Linux to read,
write and erase from system flash devices. We register platform devices
for the flash devices exported by firmware.

We clash with the existing opal_flash_init function, which is really for
the FSP flash update functionality, so we rename that initcall to
opal_flash_update_init().

A future change will add an mtd driver that uses this interface.

Changes from Joel Stanley and Jeremy Kerr.

Signed-off-by: Cyril Bur <cyrilbur@gmail.com>
Signed-off-by: Jeremy Kerr <jk@ozlabs.org>
Signed-off-by: Joel Stanley <joel@jms.id.au>
Acked-by: Stewart Smith <stewart@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/include/asm/opal-api.h            |  5 ++++-
 arch/powerpc/include/asm/opal.h                |  9 ++++++++-
 arch/powerpc/platforms/powernv/opal-flash.c    |  2 +-
 arch/powerpc/platforms/powernv/opal-wrappers.S |  3 +++
 arch/powerpc/platforms/powernv/opal.c          | 16 +++++++++++++++-
 5 files changed, 31 insertions(+), 4 deletions(-)

(limited to 'arch/powerpc/platforms/powernv')

diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h
index e8a6baf55e82..0321a909e663 100644
--- a/arch/powerpc/include/asm/opal-api.h
+++ b/arch/powerpc/include/asm/opal-api.h
@@ -150,7 +150,10 @@
 #define OPAL_IPMI_SEND				107
 #define OPAL_IPMI_RECV				108
 #define OPAL_I2C_REQUEST			109
-#define OPAL_LAST				109
+#define OPAL_FLASH_READ				110
+#define OPAL_FLASH_WRITE			111
+#define OPAL_FLASH_ERASE			112
+#define OPAL_LAST				112
 
 /* Device tree flags */
 
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index fde90bacc65e..042af1abfc4d 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -194,6 +194,13 @@ int64_t opal_ipmi_recv(uint64_t interface, struct opal_ipmi_msg *msg,
 int64_t opal_i2c_request(uint64_t async_token, uint32_t bus_id,
 			 struct opal_i2c_request *oreq);
 
+int64_t opal_flash_read(uint64_t id, uint64_t offset, uint64_t buf,
+		uint64_t size, uint64_t token);
+int64_t opal_flash_write(uint64_t id, uint64_t offset, uint64_t buf,
+		uint64_t size, uint64_t token);
+int64_t opal_flash_erase(uint64_t id, uint64_t offset, uint64_t size,
+		uint64_t token);
+
 /* Internal functions */
 extern int early_init_dt_scan_opal(unsigned long node, const char *uname,
 				   int depth, void *data);
@@ -226,7 +233,7 @@ extern int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data);
 struct rtc_time;
 extern unsigned long opal_get_boot_time(void);
 extern void opal_nvram_init(void);
-extern void opal_flash_init(void);
+extern void opal_flash_update_init(void);
 extern void opal_flash_term_callback(void);
 extern int opal_elog_init(void);
 extern void opal_platform_dump_init(void);
diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c
index 0ff07ff891f0..4ec6219287fc 100644
--- a/arch/powerpc/platforms/powernv/opal-flash.c
+++ b/arch/powerpc/platforms/powernv/opal-flash.c
@@ -546,7 +546,7 @@ static struct attribute_group image_op_attr_group = {
 	.attrs = image_op_attrs,
 };
 
-void __init opal_flash_init(void)
+void __init opal_flash_update_init(void)
 {
 	int ret;
 
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index b23fe7c4bf12..4e740375772c 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -292,3 +292,6 @@ OPAL_CALL(opal_tpo_read,			OPAL_READ_TPO);
 OPAL_CALL(opal_ipmi_send,			OPAL_IPMI_SEND);
 OPAL_CALL(opal_ipmi_recv,			OPAL_IPMI_RECV);
 OPAL_CALL(opal_i2c_request,			OPAL_I2C_REQUEST);
+OPAL_CALL(opal_flash_read,			OPAL_FLASH_READ);
+OPAL_CALL(opal_flash_write,			OPAL_FLASH_WRITE);
+OPAL_CALL(opal_flash_erase,			OPAL_FLASH_ERASE);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 3fb981c0ca80..2241565b0739 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -693,6 +693,15 @@ static void __init opal_dump_region_init(void)
 			"rc = %d\n", rc);
 }
 
+static void opal_flash_init(struct device_node *opal_node)
+{
+	struct device_node *np;
+
+	for_each_child_of_node(opal_node, np)
+		if (of_device_is_compatible(np, "ibm,opal-flash"))
+			of_platform_device_create(np, NULL, NULL);
+}
+
 static void opal_ipmi_init(struct device_node *opal_node)
 {
 	struct device_node *np;
@@ -817,7 +826,7 @@ static int __init opal_init(void)
 		/* Setup error log interface */
 		rc = opal_elog_init();
 		/* Setup code update interface */
-		opal_flash_init();
+		opal_flash_update_init();
 		/* Setup platform dump extract interface */
 		opal_platform_dump_init();
 		/* Setup system parameters interface */
@@ -829,6 +838,8 @@ static int __init opal_init(void)
 	/* Initialize OPAL IPMI backend */
 	opal_ipmi_init(opal_node);
 
+	opal_flash_init(opal_node);
+
 	return 0;
 }
 machine_subsys_initcall(powernv, opal_init);
@@ -867,6 +878,9 @@ void opal_shutdown(void)
 EXPORT_SYMBOL_GPL(opal_invalid_call);
 EXPORT_SYMBOL_GPL(opal_ipmi_send);
 EXPORT_SYMBOL_GPL(opal_ipmi_recv);
+EXPORT_SYMBOL_GPL(opal_flash_read);
+EXPORT_SYMBOL_GPL(opal_flash_write);
+EXPORT_SYMBOL_GPL(opal_flash_erase);
 
 /* Convert a region of vmalloc memory to an opal sg list */
 struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr,
-- 
cgit v1.2.3