From 66c29da6782b9861b17f9fc81746e30315e039c2 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <michael@ellerman.id.au>
Date: Thu, 26 Sep 2013 17:52:17 +1000
Subject: powerpc/powernv: Replace CONFIG_POWERNV_MSI with just
 CONFIG_PPC_POWERNV

We currently have a user visible CONFIG_POWERNV_MSI option, but it
doesn't actually disable MSI for powernv. The MSI code is always built,
what it does disable is the inclusion of the MSI bitmap code, which
leads to a build error.

eg, with PPC_POWERNV=y and POWERNV_MSI=n we get:

  arch/powerpc/platforms/built-in.o: In function `.pnv_teardown_msi_irqs':
  pci.c:(.text+0x3558): undefined reference to `.msi_bitmap_free_hwirqs'

We don't really need a POWERNV_MSI symbol, just have the MSI bitmap code
depend directly on PPC_POWERNV.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Reviewed-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/Kconfig | 5 -----
 1 file changed, 5 deletions(-)

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

diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
index 9fced3f6d2dc..895e8a20a3fc 100644
--- a/arch/powerpc/platforms/powernv/Kconfig
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -13,11 +13,6 @@ config PPC_POWERNV
 	select ARCH_RANDOM
 	default y
 
-config POWERNV_MSI
-	bool "Support PCI MSI on PowerNV platform"
-	depends on PCI_MSI
-	default y
-
 config PPC_POWERNV_RTAS
 	depends on PPC_POWERNV
 	bool "Support for RTAS based PowerNV platforms such as BML"
-- 
cgit v1.2.3


From 36df96f8acaf51992177645eb2d781f766ce97dc Mon Sep 17 00:00:00 2001
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Date: Wed, 30 Oct 2013 20:05:40 +0530
Subject: powerpc/book3s: Decode and save machine check event.

Now that we handle machine check in linux, the MCE decoding should also
take place in linux host. This info is crucial to log before we go down
in case we can not handle the machine check errors. This patch decodes
and populates a machine check event which contain high level meaning full
MCE information.

We do this in real mode C code with ME bit on. The MCE information is still
available on emergency stack (in pt_regs structure format). Even if we take
another exception at this point the MCE early handler will allocate a new
stack frame on top of current one. So when we return back here we still have
our MCE information safe on current stack.

We use per cpu buffer to save high level MCE information. Each per cpu buffer
is an array of machine check event structure indexed by per cpu counter
mce_nest_count. The mce_nest_count is incremented every time we enter
machine check early handler in real mode to get the current free slot
(index = mce_nest_count - 1). The mce_nest_count is decremented once the
MCE info is consumed by virtual mode machine exception handler.

This patch provides save_mce_event(), get_mce_event() and release_mce_event()
generic routines that can be used by machine check handlers to populate and
retrieve the event. The routine release_mce_event() will free the event slot so
that it can be reused. Caller can invoke get_mce_event() with a release flag
either to release the event slot immediately OR keep it so that it can be
fetched again. The event slot can be also released anytime by invoking
release_mce_event().

This patch also updates kvm code to invoke get_mce_event to retrieve generic
mce event rather than paca->opal_mce_evt.

The KVM code always calls get_mce_event() with release flags set to false so
that event is available for linus host machine

If machine check occurs while we are in guest, KVM tries to handle the error.
If KVM is able to handle MC error successfully, it enters the guest and
delivers the machine check to guest. If KVM is not able to handle MC error, it
exists the guest and passes the control to linux host machine check handler
which then logs MC event and decides how to handle it in linux host. In failure
case, KVM needs to make sure that the MC event is available for linux host to
consume. Hence KVM always calls get_mce_event() with release flags set to false
and later it invokes release_mce_event() only if it succeeds to handle error.

Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/mce.h        | 124 +++++++++++++++++++++++++
 arch/powerpc/kernel/Makefile          |   2 +-
 arch/powerpc/kernel/mce.c             | 164 ++++++++++++++++++++++++++++++++++
 arch/powerpc/kernel/mce_power.c       | 116 ++++++++++++++++++++++--
 arch/powerpc/kvm/book3s_hv_ras.c      |  32 ++++---
 arch/powerpc/platforms/powernv/opal.c |  35 ++++----
 6 files changed, 434 insertions(+), 39 deletions(-)
 create mode 100644 arch/powerpc/kernel/mce.c

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

diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index e3ffa825b970..87cad2a808c2 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -66,5 +66,129 @@
 
 #define P8_DSISR_MC_SLB_ERRORS		(P7_DSISR_MC_SLB_ERRORS | \
 					 P8_DSISR_MC_ERAT_MULTIHIT_SEC)
+enum MCE_Version {
+	MCE_V1 = 1,
+};
+
+enum MCE_Severity {
+	MCE_SEV_NO_ERROR = 0,
+	MCE_SEV_WARNING = 1,
+	MCE_SEV_ERROR_SYNC = 2,
+	MCE_SEV_FATAL = 3,
+};
+
+enum MCE_Disposition {
+	MCE_DISPOSITION_RECOVERED = 0,
+	MCE_DISPOSITION_NOT_RECOVERED = 1,
+};
+
+enum MCE_Initiator {
+	MCE_INITIATOR_UNKNOWN = 0,
+	MCE_INITIATOR_CPU = 1,
+};
+
+enum MCE_ErrorType {
+	MCE_ERROR_TYPE_UNKNOWN = 0,
+	MCE_ERROR_TYPE_UE = 1,
+	MCE_ERROR_TYPE_SLB = 2,
+	MCE_ERROR_TYPE_ERAT = 3,
+	MCE_ERROR_TYPE_TLB = 4,
+};
+
+enum MCE_UeErrorType {
+	MCE_UE_ERROR_INDETERMINATE = 0,
+	MCE_UE_ERROR_IFETCH = 1,
+	MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH = 2,
+	MCE_UE_ERROR_LOAD_STORE = 3,
+	MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE = 4,
+};
+
+enum MCE_SlbErrorType {
+	MCE_SLB_ERROR_INDETERMINATE = 0,
+	MCE_SLB_ERROR_PARITY = 1,
+	MCE_SLB_ERROR_MULTIHIT = 2,
+};
+
+enum MCE_EratErrorType {
+	MCE_ERAT_ERROR_INDETERMINATE = 0,
+	MCE_ERAT_ERROR_PARITY = 1,
+	MCE_ERAT_ERROR_MULTIHIT = 2,
+};
+
+enum MCE_TlbErrorType {
+	MCE_TLB_ERROR_INDETERMINATE = 0,
+	MCE_TLB_ERROR_PARITY = 1,
+	MCE_TLB_ERROR_MULTIHIT = 2,
+};
+
+struct machine_check_event {
+	enum MCE_Version	version:8;	/* 0x00 */
+	uint8_t			in_use;		/* 0x01 */
+	enum MCE_Severity	severity:8;	/* 0x02 */
+	enum MCE_Initiator	initiator:8;	/* 0x03 */
+	enum MCE_ErrorType	error_type:8;	/* 0x04 */
+	enum MCE_Disposition	disposition:8;	/* 0x05 */
+	uint8_t			reserved_1[2];	/* 0x06 */
+	uint64_t		gpr3;		/* 0x08 */
+	uint64_t		srr0;		/* 0x10 */
+	uint64_t		srr1;		/* 0x18 */
+	union {					/* 0x20 */
+		struct {
+			enum MCE_UeErrorType ue_error_type:8;
+			uint8_t		effective_address_provided;
+			uint8_t		physical_address_provided;
+			uint8_t		reserved_1[5];
+			uint64_t	effective_address;
+			uint64_t	physical_address;
+			uint8_t		reserved_2[8];
+		} ue_error;
+
+		struct {
+			enum MCE_SlbErrorType slb_error_type:8;
+			uint8_t		effective_address_provided;
+			uint8_t		reserved_1[6];
+			uint64_t	effective_address;
+			uint8_t		reserved_2[16];
+		} slb_error;
+
+		struct {
+			enum MCE_EratErrorType erat_error_type:8;
+			uint8_t		effective_address_provided;
+			uint8_t		reserved_1[6];
+			uint64_t	effective_address;
+			uint8_t		reserved_2[16];
+		} erat_error;
+
+		struct {
+			enum MCE_TlbErrorType tlb_error_type:8;
+			uint8_t		effective_address_provided;
+			uint8_t		reserved_1[6];
+			uint64_t	effective_address;
+			uint8_t		reserved_2[16];
+		} tlb_error;
+	} u;
+};
+
+struct mce_error_info {
+	enum MCE_ErrorType error_type:8;
+	union {
+		enum MCE_UeErrorType ue_error_type:8;
+		enum MCE_SlbErrorType slb_error_type:8;
+		enum MCE_EratErrorType erat_error_type:8;
+		enum MCE_TlbErrorType tlb_error_type:8;
+	} u;
+	uint8_t		reserved[2];
+};
+
+#define MAX_MC_EVT	100
+
+/* Release flags for get_mce_event() */
+#define MCE_EVENT_RELEASE	true
+#define MCE_EVENT_DONTRELEASE	false
+
+extern void save_mce_event(struct pt_regs *regs, long handled,
+			   struct mce_error_info *mce_err, uint64_t addr);
+extern int get_mce_event(struct machine_check_event *mce, bool release);
+extern void release_mce_event(void);
 
 #endif /* __ASM_PPC64_MCE_H__ */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 07c63d0aa759..904d713366ff 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -39,7 +39,7 @@ obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_ppc970.o cpu_setup_pa6t.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_power.o
-obj-$(CONFIG_PPC_BOOK3S_64)	+= mce_power.o
+obj-$(CONFIG_PPC_BOOK3S_64)	+= mce.o mce_power.o
 obj64-$(CONFIG_RELOCATABLE)	+= reloc_64.o
 obj-$(CONFIG_PPC_BOOK3E_64)	+= exceptions-64e.o idle_book3e.o
 obj-$(CONFIG_PPC_A2)		+= cpu_setup_a2.o
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
new file mode 100644
index 000000000000..aeecdf1ba897
--- /dev/null
+++ b/arch/powerpc/kernel/mce.c
@@ -0,0 +1,164 @@
+/*
+ * Machine check exception handling.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright 2013 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#undef DEBUG
+#define pr_fmt(fmt) "mce: " fmt
+
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/percpu.h>
+#include <linux/export.h>
+#include <asm/mce.h>
+
+static DEFINE_PER_CPU(int, mce_nest_count);
+static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event);
+
+static void mce_set_error_info(struct machine_check_event *mce,
+			       struct mce_error_info *mce_err)
+{
+	mce->error_type = mce_err->error_type;
+	switch (mce_err->error_type) {
+	case MCE_ERROR_TYPE_UE:
+		mce->u.ue_error.ue_error_type = mce_err->u.ue_error_type;
+		break;
+	case MCE_ERROR_TYPE_SLB:
+		mce->u.slb_error.slb_error_type = mce_err->u.slb_error_type;
+		break;
+	case MCE_ERROR_TYPE_ERAT:
+		mce->u.erat_error.erat_error_type = mce_err->u.erat_error_type;
+		break;
+	case MCE_ERROR_TYPE_TLB:
+		mce->u.tlb_error.tlb_error_type = mce_err->u.tlb_error_type;
+		break;
+	case MCE_ERROR_TYPE_UNKNOWN:
+	default:
+		break;
+	}
+}
+
+/*
+ * Decode and save high level MCE information into per cpu buffer which
+ * is an array of machine_check_event structure.
+ */
+void save_mce_event(struct pt_regs *regs, long handled,
+		    struct mce_error_info *mce_err,
+		    uint64_t addr)
+{
+	uint64_t srr1;
+	int index = __get_cpu_var(mce_nest_count)++;
+	struct machine_check_event *mce = &__get_cpu_var(mce_event[index]);
+
+	/*
+	 * Return if we don't have enough space to log mce event.
+	 * mce_nest_count may go beyond MAX_MC_EVT but that's ok,
+	 * the check below will stop buffer overrun.
+	 */
+	if (index >= MAX_MC_EVT)
+		return;
+
+	/* Populate generic machine check info */
+	mce->version = MCE_V1;
+	mce->srr0 = regs->nip;
+	mce->srr1 = regs->msr;
+	mce->gpr3 = regs->gpr[3];
+	mce->in_use = 1;
+
+	mce->initiator = MCE_INITIATOR_CPU;
+	if (handled)
+		mce->disposition = MCE_DISPOSITION_RECOVERED;
+	else
+		mce->disposition = MCE_DISPOSITION_NOT_RECOVERED;
+	mce->severity = MCE_SEV_ERROR_SYNC;
+
+	srr1 = regs->msr;
+
+	/*
+	 * Populate the mce error_type and type-specific error_type.
+	 */
+	mce_set_error_info(mce, mce_err);
+
+	if (!addr)
+		return;
+
+	if (mce->error_type == MCE_ERROR_TYPE_TLB) {
+		mce->u.tlb_error.effective_address_provided = true;
+		mce->u.tlb_error.effective_address = addr;
+	} else if (mce->error_type == MCE_ERROR_TYPE_SLB) {
+		mce->u.slb_error.effective_address_provided = true;
+		mce->u.slb_error.effective_address = addr;
+	} else if (mce->error_type == MCE_ERROR_TYPE_ERAT) {
+		mce->u.erat_error.effective_address_provided = true;
+		mce->u.erat_error.effective_address = addr;
+	} else if (mce->error_type == MCE_ERROR_TYPE_UE) {
+		mce->u.ue_error.effective_address_provided = true;
+		mce->u.ue_error.effective_address = addr;
+	}
+	return;
+}
+
+/*
+ * get_mce_event:
+ *	mce	Pointer to machine_check_event structure to be filled.
+ *	release Flag to indicate whether to free the event slot or not.
+ *		0 <= do not release the mce event. Caller will invoke
+ *		     release_mce_event() once event has been consumed.
+ *		1 <= release the slot.
+ *
+ *	return	1 = success
+ *		0 = failure
+ *
+ * get_mce_event() will be called by platform specific machine check
+ * handle routine and in KVM.
+ * When we call get_mce_event(), we are still in interrupt context and
+ * preemption will not be scheduled until ret_from_expect() routine
+ * is called.
+ */
+int get_mce_event(struct machine_check_event *mce, bool release)
+{
+	int index = __get_cpu_var(mce_nest_count) - 1;
+	struct machine_check_event *mc_evt;
+	int ret = 0;
+
+	/* Sanity check */
+	if (index < 0)
+		return ret;
+
+	/* Check if we have MCE info to process. */
+	if (index < MAX_MC_EVT) {
+		mc_evt = &__get_cpu_var(mce_event[index]);
+		/* Copy the event structure and release the original */
+		if (mce)
+			*mce = *mc_evt;
+		if (release)
+			mc_evt->in_use = 0;
+		ret = 1;
+	}
+	/* Decrement the count to free the slot. */
+	if (release)
+		__get_cpu_var(mce_nest_count)--;
+
+	return ret;
+}
+
+void release_mce_event(void)
+{
+	get_mce_event(NULL, true);
+}
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 60a217f11275..b36e777a734f 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -133,22 +133,116 @@ static long mce_handle_ierror_p7(uint64_t srr1)
 	return handled;
 }
 
+static void mce_get_common_ierror(struct mce_error_info *mce_err, uint64_t srr1)
+{
+	switch (P7_SRR1_MC_IFETCH(srr1)) {
+	case P7_SRR1_MC_IFETCH_SLB_PARITY:
+		mce_err->error_type = MCE_ERROR_TYPE_SLB;
+		mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
+		break;
+	case P7_SRR1_MC_IFETCH_SLB_MULTIHIT:
+		mce_err->error_type = MCE_ERROR_TYPE_SLB;
+		mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
+		break;
+	case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
+		mce_err->error_type = MCE_ERROR_TYPE_TLB;
+		mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
+		break;
+	case P7_SRR1_MC_IFETCH_UE:
+	case P7_SRR1_MC_IFETCH_UE_IFU_INTERNAL:
+		mce_err->error_type = MCE_ERROR_TYPE_UE;
+		mce_err->u.ue_error_type = MCE_UE_ERROR_IFETCH;
+		break;
+	case P7_SRR1_MC_IFETCH_UE_TLB_RELOAD:
+		mce_err->error_type = MCE_ERROR_TYPE_UE;
+		mce_err->u.ue_error_type =
+				MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH;
+		break;
+	}
+}
+
+static void mce_get_ierror_p7(struct mce_error_info *mce_err, uint64_t srr1)
+{
+	mce_get_common_ierror(mce_err, srr1);
+	if (P7_SRR1_MC_IFETCH(srr1) == P7_SRR1_MC_IFETCH_SLB_BOTH) {
+		mce_err->error_type = MCE_ERROR_TYPE_SLB;
+		mce_err->u.slb_error_type = MCE_SLB_ERROR_INDETERMINATE;
+	}
+}
+
+static void mce_get_derror_p7(struct mce_error_info *mce_err, uint64_t dsisr)
+{
+	if (dsisr & P7_DSISR_MC_UE) {
+		mce_err->error_type = MCE_ERROR_TYPE_UE;
+		mce_err->u.ue_error_type = MCE_UE_ERROR_LOAD_STORE;
+	} else if (dsisr & P7_DSISR_MC_UE_TABLEWALK) {
+		mce_err->error_type = MCE_ERROR_TYPE_UE;
+		mce_err->u.ue_error_type =
+				MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE;
+	} else if (dsisr & P7_DSISR_MC_ERAT_MULTIHIT) {
+		mce_err->error_type = MCE_ERROR_TYPE_ERAT;
+		mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+	} else if (dsisr & P7_DSISR_MC_SLB_MULTIHIT) {
+		mce_err->error_type = MCE_ERROR_TYPE_SLB;
+		mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
+	} else if (dsisr & P7_DSISR_MC_SLB_PARITY_MFSLB) {
+		mce_err->error_type = MCE_ERROR_TYPE_SLB;
+		mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
+	} else if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) {
+		mce_err->error_type = MCE_ERROR_TYPE_TLB;
+		mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
+	} else if (dsisr & P7_DSISR_MC_SLB_MULTIHIT_PARITY) {
+		mce_err->error_type = MCE_ERROR_TYPE_SLB;
+		mce_err->u.slb_error_type = MCE_SLB_ERROR_INDETERMINATE;
+	}
+}
+
 long __machine_check_early_realmode_p7(struct pt_regs *regs)
 {
-	uint64_t srr1;
+	uint64_t srr1, addr;
 	long handled = 1;
+	struct mce_error_info mce_error_info = { 0 };
 
 	srr1 = regs->msr;
 
-	if (P7_SRR1_MC_LOADSTORE(srr1))
+	/*
+	 * Handle memory errors depending whether this was a load/store or
+	 * ifetch exception. Also, populate the mce error_type and
+	 * type-specific error_type from either SRR1 or DSISR, depending
+	 * whether this was a load/store or ifetch exception
+	 */
+	if (P7_SRR1_MC_LOADSTORE(srr1)) {
 		handled = mce_handle_derror_p7(regs->dsisr);
-	else
+		mce_get_derror_p7(&mce_error_info, regs->dsisr);
+		addr = regs->dar;
+	} else {
 		handled = mce_handle_ierror_p7(srr1);
+		mce_get_ierror_p7(&mce_error_info, srr1);
+		addr = regs->nip;
+	}
 
-	/* TODO: Decode machine check reason. */
+	save_mce_event(regs, handled, &mce_error_info, addr);
 	return handled;
 }
 
+static void mce_get_ierror_p8(struct mce_error_info *mce_err, uint64_t srr1)
+{
+	mce_get_common_ierror(mce_err, srr1);
+	if (P7_SRR1_MC_IFETCH(srr1) == P8_SRR1_MC_IFETCH_ERAT_MULTIHIT) {
+		mce_err->error_type = MCE_ERROR_TYPE_ERAT;
+		mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+	}
+}
+
+static void mce_get_derror_p8(struct mce_error_info *mce_err, uint64_t dsisr)
+{
+	mce_get_derror_p7(mce_err, dsisr);
+	if (dsisr & P8_DSISR_MC_ERAT_MULTIHIT_SEC) {
+		mce_err->error_type = MCE_ERROR_TYPE_ERAT;
+		mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+	}
+}
+
 static long mce_handle_ierror_p8(uint64_t srr1)
 {
 	long handled = 0;
@@ -169,16 +263,22 @@ static long mce_handle_derror_p8(uint64_t dsisr)
 
 long __machine_check_early_realmode_p8(struct pt_regs *regs)
 {
-	uint64_t srr1;
+	uint64_t srr1, addr;
 	long handled = 1;
+	struct mce_error_info mce_error_info = { 0 };
 
 	srr1 = regs->msr;
 
-	if (P7_SRR1_MC_LOADSTORE(srr1))
+	if (P7_SRR1_MC_LOADSTORE(srr1)) {
 		handled = mce_handle_derror_p8(regs->dsisr);
-	else
+		mce_get_derror_p8(&mce_error_info, regs->dsisr);
+		addr = regs->dar;
+	} else {
 		handled = mce_handle_ierror_p8(srr1);
+		mce_get_ierror_p8(&mce_error_info, srr1);
+		addr = regs->nip;
+	}
 
-	/* TODO: Decode machine check reason. */
+	save_mce_event(regs, handled, &mce_error_info, addr);
 	return handled;
 }
diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c
index 5c427b41a2f5..768a9f977c00 100644
--- a/arch/powerpc/kvm/book3s_hv_ras.c
+++ b/arch/powerpc/kvm/book3s_hv_ras.c
@@ -12,6 +12,7 @@
 #include <linux/kvm_host.h>
 #include <linux/kernel.h>
 #include <asm/opal.h>
+#include <asm/mce.h>
 
 /* SRR1 bits for machine check on POWER7 */
 #define SRR1_MC_LDSTERR		(1ul << (63-42))
@@ -67,9 +68,7 @@ static void reload_slb(struct kvm_vcpu *vcpu)
 static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
 {
 	unsigned long srr1 = vcpu->arch.shregs.msr;
-#ifdef CONFIG_PPC_POWERNV
-	struct opal_machine_check_event *opal_evt;
-#endif
+	struct machine_check_event mce_evt;
 	long handled = 1;
 
 	if (srr1 & SRR1_MC_LDSTERR) {
@@ -109,22 +108,31 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
 		handled = 0;
 	}
 
-#ifdef CONFIG_PPC_POWERNV
 	/*
-	 * See if OPAL has already handled the condition.
-	 * We assume that if the condition is recovered then OPAL
+	 * See if we have already handled the condition in the linux host.
+	 * We assume that if the condition is recovered then linux host
 	 * will have generated an error log event that we will pick
 	 * up and log later.
+	 * Don't release mce event now. In case if condition is not
+	 * recovered we do guest exit and go back to linux host machine
+	 * check handler. Hence we need make sure that current mce event
+	 * is available for linux host to consume.
 	 */
-	opal_evt = local_paca->opal_mc_evt;
-	if (opal_evt->version == OpalMCE_V1 &&
-	    (opal_evt->severity == OpalMCE_SEV_NO_ERROR ||
-	     opal_evt->disposition == OpalMCE_DISPOSITION_RECOVERED))
+	if (!get_mce_event(&mce_evt, MCE_EVENT_DONTRELEASE))
+		goto out;
+
+	if (mce_evt.version == MCE_V1 &&
+	    (mce_evt.severity == MCE_SEV_NO_ERROR ||
+	     mce_evt.disposition == MCE_DISPOSITION_RECOVERED))
 		handled = 1;
 
+out:
+	/*
+	 * If we have handled the error, then release the mce event because
+	 * we will be delivering machine check to guest.
+	 */
 	if (handled)
-		opal_evt->in_use = 0;
-#endif
+		release_mce_event();
 
 	return handled;
 }
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 1c798cd55372..c5e71d773f47 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -21,6 +21,7 @@
 #include <linux/kobject.h>
 #include <asm/opal.h>
 #include <asm/firmware.h>
+#include <asm/mce.h>
 
 #include "powernv.h"
 
@@ -256,8 +257,7 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 
 int opal_machine_check(struct pt_regs *regs)
 {
-	struct opal_machine_check_event *opal_evt = get_paca()->opal_mc_evt;
-	struct opal_machine_check_event evt;
+	struct machine_check_event evt;
 	const char *level, *sevstr, *subtype;
 	static const char *opal_mc_ue_types[] = {
 		"Indeterminate",
@@ -282,30 +282,29 @@ int opal_machine_check(struct pt_regs *regs)
 		"Multihit",
 	};
 
-	/* Copy the event structure and release the original */
-	evt = *opal_evt;
-	opal_evt->in_use = 0;
+	if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
+		return 0;
 
 	/* Print things out */
-	if (evt.version != OpalMCE_V1) {
+	if (evt.version != MCE_V1) {
 		pr_err("Machine Check Exception, Unknown event version %d !\n",
 		       evt.version);
 		return 0;
 	}
 	switch(evt.severity) {
-	case OpalMCE_SEV_NO_ERROR:
+	case MCE_SEV_NO_ERROR:
 		level = KERN_INFO;
 		sevstr = "Harmless";
 		break;
-	case OpalMCE_SEV_WARNING:
+	case MCE_SEV_WARNING:
 		level = KERN_WARNING;
 		sevstr = "";
 		break;
-	case OpalMCE_SEV_ERROR_SYNC:
+	case MCE_SEV_ERROR_SYNC:
 		level = KERN_ERR;
 		sevstr = "Severe";
 		break;
-	case OpalMCE_SEV_FATAL:
+	case MCE_SEV_FATAL:
 	default:
 		level = KERN_ERR;
 		sevstr = "Fatal";
@@ -313,12 +312,12 @@ int opal_machine_check(struct pt_regs *regs)
 	}
 
 	printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
-	       evt.disposition == OpalMCE_DISPOSITION_RECOVERED ?
+	       evt.disposition == MCE_DISPOSITION_RECOVERED ?
 	       "Recovered" : "[Not recovered");
 	printk("%s  Initiator: %s\n", level,
-	       evt.initiator == OpalMCE_INITIATOR_CPU ? "CPU" : "Unknown");
+	       evt.initiator == MCE_INITIATOR_CPU ? "CPU" : "Unknown");
 	switch(evt.error_type) {
-	case OpalMCE_ERROR_TYPE_UE:
+	case MCE_ERROR_TYPE_UE:
 		subtype = evt.u.ue_error.ue_error_type <
 			ARRAY_SIZE(opal_mc_ue_types) ?
 			opal_mc_ue_types[evt.u.ue_error.ue_error_type]
@@ -331,7 +330,7 @@ int opal_machine_check(struct pt_regs *regs)
 			printk("%s      Physial address: %016llx\n",
 			       level, evt.u.ue_error.physical_address);
 		break;
-	case OpalMCE_ERROR_TYPE_SLB:
+	case MCE_ERROR_TYPE_SLB:
 		subtype = evt.u.slb_error.slb_error_type <
 			ARRAY_SIZE(opal_mc_slb_types) ?
 			opal_mc_slb_types[evt.u.slb_error.slb_error_type]
@@ -341,7 +340,7 @@ int opal_machine_check(struct pt_regs *regs)
 			printk("%s    Effective address: %016llx\n",
 			       level, evt.u.slb_error.effective_address);
 		break;
-	case OpalMCE_ERROR_TYPE_ERAT:
+	case MCE_ERROR_TYPE_ERAT:
 		subtype = evt.u.erat_error.erat_error_type <
 			ARRAY_SIZE(opal_mc_erat_types) ?
 			opal_mc_erat_types[evt.u.erat_error.erat_error_type]
@@ -351,7 +350,7 @@ int opal_machine_check(struct pt_regs *regs)
 			printk("%s    Effective address: %016llx\n",
 			       level, evt.u.erat_error.effective_address);
 		break;
-	case OpalMCE_ERROR_TYPE_TLB:
+	case MCE_ERROR_TYPE_TLB:
 		subtype = evt.u.tlb_error.tlb_error_type <
 			ARRAY_SIZE(opal_mc_tlb_types) ?
 			opal_mc_tlb_types[evt.u.tlb_error.tlb_error_type]
@@ -362,11 +361,11 @@ int opal_machine_check(struct pt_regs *regs)
 			       level, evt.u.tlb_error.effective_address);
 		break;
 	default:
-	case OpalMCE_ERROR_TYPE_UNKNOWN:
+	case MCE_ERROR_TYPE_UNKNOWN:
 		printk("%s  Error type: Unknown\n", level);
 		break;
 	}
-	return evt.severity == OpalMCE_SEV_FATAL ? 0 : 1;
+	return evt.severity == MCE_SEV_FATAL ? 0 : 1;
 }
 
 static irqreturn_t opal_interrupt(int irq, void *data)
-- 
cgit v1.2.3


From b5ff4211a8294be2ddbaf963fa3666fa042292a8 Mon Sep 17 00:00:00 2001
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Date: Wed, 30 Oct 2013 20:05:49 +0530
Subject: powerpc/book3s: Queue up and process delayed MCE events.

When machine check real mode handler can not continue into host kernel
in V mode, it returns from the interrupt and we loose MCE event which
never gets logged. In such a situation queue up the MCE event so that
we can log it later when we get back into host kernel with r1 pointing to
kernel stack e.g. during syscall exit.

Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/mce.h        |   3 +
 arch/powerpc/kernel/entry_64.S        |   5 ++
 arch/powerpc/kernel/exceptions-64s.S  |   7 +-
 arch/powerpc/kernel/mce.c             | 154 ++++++++++++++++++++++++++++++++++
 arch/powerpc/platforms/powernv/opal.c |  97 +--------------------
 5 files changed, 168 insertions(+), 98 deletions(-)

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

diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index 87cad2a808c2..3276b409299c 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -190,5 +190,8 @@ extern void save_mce_event(struct pt_regs *regs, long handled,
 			   struct mce_error_info *mce_err, uint64_t addr);
 extern int get_mce_event(struct machine_check_event *mce, bool release);
 extern void release_mce_event(void);
+extern void machine_check_queue_event(void);
+extern void machine_check_process_queued_event(void);
+extern void machine_check_print_event_info(struct machine_check_event *evt);
 
 #endif /* __ASM_PPC64_MCE_H__ */
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index bbfb0294b354..770d6d65c47b 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -183,6 +183,11 @@ syscall_exit:
 #ifdef SHOW_SYSCALLS
 	bl	.do_show_syscall_exit
 	ld	r3,RESULT(r1)
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+BEGIN_FTR_SECTION
+	bl	.machine_check_process_queued_event
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
 #endif
 	CURRENT_THREAD_INFO(r12, r1)
 
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 1aec3025eeee..862b9dd4a9db 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -855,7 +855,8 @@ BEGIN_FTR_SECTION
 	/* Supervisor state loss */
 	li	r0,1
 	stb	r0,PACA_NAPSTATELOST(r13)
-3:	MACHINE_CHECK_HANDLER_WINDUP
+3:	bl	.machine_check_queue_event
+	MACHINE_CHECK_HANDLER_WINDUP
 	GET_PACA(r13)
 	ld	r1,PACAR1(r13)
 	b	.power7_enter_nap_mode
@@ -895,8 +896,10 @@ BEGIN_FTR_SECTION
 2:
 	/*
 	 * Return from MC interrupt.
-	 * TODO: Queue up the MCE event so that we can log it later.
+	 * Queue up the MCE event so that we can log it later, while
+	 * returning from kernel or opal call.
 	 */
+	bl	.machine_check_queue_event
 	MACHINE_CHECK_HANDLER_WINDUP
 	rfid
 9:
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index aeecdf1ba897..1c6d15701c56 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -31,6 +31,10 @@
 static DEFINE_PER_CPU(int, mce_nest_count);
 static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event);
 
+/* Queue for delayed MCE events. */
+static DEFINE_PER_CPU(int, mce_queue_count);
+static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event_queue);
+
 static void mce_set_error_info(struct machine_check_event *mce,
 			       struct mce_error_info *mce_err)
 {
@@ -162,3 +166,153 @@ void release_mce_event(void)
 {
 	get_mce_event(NULL, true);
 }
+
+/*
+ * Queue up the MCE event which then can be handled later.
+ */
+void machine_check_queue_event(void)
+{
+	int index;
+	struct machine_check_event evt;
+
+	if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
+		return;
+
+	index = __get_cpu_var(mce_queue_count)++;
+	/* If queue is full, just return for now. */
+	if (index >= MAX_MC_EVT) {
+		__get_cpu_var(mce_queue_count)--;
+		return;
+	}
+	__get_cpu_var(mce_event_queue[index]) = evt;
+}
+
+/*
+ * process pending MCE event from the mce event queue. This function will be
+ * called during syscall exit.
+ */
+void machine_check_process_queued_event(void)
+{
+	int index;
+
+	preempt_disable();
+	/*
+	 * For now just print it to console.
+	 * TODO: log this error event to FSP or nvram.
+	 */
+	while (__get_cpu_var(mce_queue_count) > 0) {
+		index = __get_cpu_var(mce_queue_count) - 1;
+		machine_check_print_event_info(
+				&__get_cpu_var(mce_event_queue[index]));
+		__get_cpu_var(mce_queue_count)--;
+	}
+	preempt_enable();
+}
+
+void machine_check_print_event_info(struct machine_check_event *evt)
+{
+	const char *level, *sevstr, *subtype;
+	static const char *mc_ue_types[] = {
+		"Indeterminate",
+		"Instruction fetch",
+		"Page table walk ifetch",
+		"Load/Store",
+		"Page table walk Load/Store",
+	};
+	static const char *mc_slb_types[] = {
+		"Indeterminate",
+		"Parity",
+		"Multihit",
+	};
+	static const char *mc_erat_types[] = {
+		"Indeterminate",
+		"Parity",
+		"Multihit",
+	};
+	static const char *mc_tlb_types[] = {
+		"Indeterminate",
+		"Parity",
+		"Multihit",
+	};
+
+	/* Print things out */
+	if (evt->version != MCE_V1) {
+		pr_err("Machine Check Exception, Unknown event version %d !\n",
+		       evt->version);
+		return;
+	}
+	switch (evt->severity) {
+	case MCE_SEV_NO_ERROR:
+		level = KERN_INFO;
+		sevstr = "Harmless";
+		break;
+	case MCE_SEV_WARNING:
+		level = KERN_WARNING;
+		sevstr = "";
+		break;
+	case MCE_SEV_ERROR_SYNC:
+		level = KERN_ERR;
+		sevstr = "Severe";
+		break;
+	case MCE_SEV_FATAL:
+	default:
+		level = KERN_ERR;
+		sevstr = "Fatal";
+		break;
+	}
+
+	printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
+	       evt->disposition == MCE_DISPOSITION_RECOVERED ?
+	       "Recovered" : "[Not recovered");
+	printk("%s  Initiator: %s\n", level,
+	       evt->initiator == MCE_INITIATOR_CPU ? "CPU" : "Unknown");
+	switch (evt->error_type) {
+	case MCE_ERROR_TYPE_UE:
+		subtype = evt->u.ue_error.ue_error_type <
+			ARRAY_SIZE(mc_ue_types) ?
+			mc_ue_types[evt->u.ue_error.ue_error_type]
+			: "Unknown";
+		printk("%s  Error type: UE [%s]\n", level, subtype);
+		if (evt->u.ue_error.effective_address_provided)
+			printk("%s    Effective address: %016llx\n",
+			       level, evt->u.ue_error.effective_address);
+		if (evt->u.ue_error.physical_address_provided)
+			printk("%s      Physial address: %016llx\n",
+			       level, evt->u.ue_error.physical_address);
+		break;
+	case MCE_ERROR_TYPE_SLB:
+		subtype = evt->u.slb_error.slb_error_type <
+			ARRAY_SIZE(mc_slb_types) ?
+			mc_slb_types[evt->u.slb_error.slb_error_type]
+			: "Unknown";
+		printk("%s  Error type: SLB [%s]\n", level, subtype);
+		if (evt->u.slb_error.effective_address_provided)
+			printk("%s    Effective address: %016llx\n",
+			       level, evt->u.slb_error.effective_address);
+		break;
+	case MCE_ERROR_TYPE_ERAT:
+		subtype = evt->u.erat_error.erat_error_type <
+			ARRAY_SIZE(mc_erat_types) ?
+			mc_erat_types[evt->u.erat_error.erat_error_type]
+			: "Unknown";
+		printk("%s  Error type: ERAT [%s]\n", level, subtype);
+		if (evt->u.erat_error.effective_address_provided)
+			printk("%s    Effective address: %016llx\n",
+			       level, evt->u.erat_error.effective_address);
+		break;
+	case MCE_ERROR_TYPE_TLB:
+		subtype = evt->u.tlb_error.tlb_error_type <
+			ARRAY_SIZE(mc_tlb_types) ?
+			mc_tlb_types[evt->u.tlb_error.tlb_error_type]
+			: "Unknown";
+		printk("%s  Error type: TLB [%s]\n", level, subtype);
+		if (evt->u.tlb_error.effective_address_provided)
+			printk("%s    Effective address: %016llx\n",
+			       level, evt->u.tlb_error.effective_address);
+		break;
+	default:
+	case MCE_ERROR_TYPE_UNKNOWN:
+		printk("%s  Error type: Unknown\n", level);
+		break;
+	}
+}
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index c5e71d773f47..245096f90437 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -258,29 +258,6 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 int opal_machine_check(struct pt_regs *regs)
 {
 	struct machine_check_event evt;
-	const char *level, *sevstr, *subtype;
-	static const char *opal_mc_ue_types[] = {
-		"Indeterminate",
-		"Instruction fetch",
-		"Page table walk ifetch",
-		"Load/Store",
-		"Page table walk Load/Store",
-	};
-	static const char *opal_mc_slb_types[] = {
-		"Indeterminate",
-		"Parity",
-		"Multihit",
-	};
-	static const char *opal_mc_erat_types[] = {
-		"Indeterminate",
-		"Parity",
-		"Multihit",
-	};
-	static const char *opal_mc_tlb_types[] = {
-		"Indeterminate",
-		"Parity",
-		"Multihit",
-	};
 
 	if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
 		return 0;
@@ -291,80 +268,8 @@ int opal_machine_check(struct pt_regs *regs)
 		       evt.version);
 		return 0;
 	}
-	switch(evt.severity) {
-	case MCE_SEV_NO_ERROR:
-		level = KERN_INFO;
-		sevstr = "Harmless";
-		break;
-	case MCE_SEV_WARNING:
-		level = KERN_WARNING;
-		sevstr = "";
-		break;
-	case MCE_SEV_ERROR_SYNC:
-		level = KERN_ERR;
-		sevstr = "Severe";
-		break;
-	case MCE_SEV_FATAL:
-	default:
-		level = KERN_ERR;
-		sevstr = "Fatal";
-		break;
-	}
+	machine_check_print_event_info(&evt);
 
-	printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
-	       evt.disposition == MCE_DISPOSITION_RECOVERED ?
-	       "Recovered" : "[Not recovered");
-	printk("%s  Initiator: %s\n", level,
-	       evt.initiator == MCE_INITIATOR_CPU ? "CPU" : "Unknown");
-	switch(evt.error_type) {
-	case MCE_ERROR_TYPE_UE:
-		subtype = evt.u.ue_error.ue_error_type <
-			ARRAY_SIZE(opal_mc_ue_types) ?
-			opal_mc_ue_types[evt.u.ue_error.ue_error_type]
-			: "Unknown";
-		printk("%s  Error type: UE [%s]\n", level, subtype);
-		if (evt.u.ue_error.effective_address_provided)
-			printk("%s    Effective address: %016llx\n",
-			       level, evt.u.ue_error.effective_address);
-		if (evt.u.ue_error.physical_address_provided)
-			printk("%s      Physial address: %016llx\n",
-			       level, evt.u.ue_error.physical_address);
-		break;
-	case MCE_ERROR_TYPE_SLB:
-		subtype = evt.u.slb_error.slb_error_type <
-			ARRAY_SIZE(opal_mc_slb_types) ?
-			opal_mc_slb_types[evt.u.slb_error.slb_error_type]
-			: "Unknown";
-		printk("%s  Error type: SLB [%s]\n", level, subtype);
-		if (evt.u.slb_error.effective_address_provided)
-			printk("%s    Effective address: %016llx\n",
-			       level, evt.u.slb_error.effective_address);
-		break;
-	case MCE_ERROR_TYPE_ERAT:
-		subtype = evt.u.erat_error.erat_error_type <
-			ARRAY_SIZE(opal_mc_erat_types) ?
-			opal_mc_erat_types[evt.u.erat_error.erat_error_type]
-			: "Unknown";
-		printk("%s  Error type: ERAT [%s]\n", level, subtype);
-		if (evt.u.erat_error.effective_address_provided)
-			printk("%s    Effective address: %016llx\n",
-			       level, evt.u.erat_error.effective_address);
-		break;
-	case MCE_ERROR_TYPE_TLB:
-		subtype = evt.u.tlb_error.tlb_error_type <
-			ARRAY_SIZE(opal_mc_tlb_types) ?
-			opal_mc_tlb_types[evt.u.tlb_error.tlb_error_type]
-			: "Unknown";
-		printk("%s  Error type: TLB [%s]\n", level, subtype);
-		if (evt.u.tlb_error.effective_address_provided)
-			printk("%s    Effective address: %016llx\n",
-			       level, evt.u.tlb_error.effective_address);
-		break;
-	default:
-	case MCE_ERROR_TYPE_UNKNOWN:
-		printk("%s  Error type: Unknown\n", level);
-		break;
-	}
 	return evt.severity == MCE_SEV_FATAL ? 0 : 1;
 }
 
-- 
cgit v1.2.3


From 28446de2ce9992f6d13e4594a25fc9c3b9f4517b Mon Sep 17 00:00:00 2001
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Date: Wed, 30 Oct 2013 20:05:58 +0530
Subject: powerpc/powernv: Remove machine check handling in OPAL.

Now that we are ready to handle machine check directly in linux, do not
register with firmware to handle machine check exception.

Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/opal.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

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

diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 245096f90437..f348bd49487c 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -89,14 +89,10 @@ static int __init opal_register_exception_handlers(void)
 	if (!(powerpc_firmware_features & FW_FEATURE_OPAL))
 		return -ENODEV;
 
-	/* Hookup some exception handlers. We use the fwnmi area at 0x7000
-	 * to provide the glue space to OPAL
+	/* Hookup some exception handlers except machine check. We use the
+	 * fwnmi area at 0x7000 to provide the glue space to OPAL
 	 */
 	glue = 0x7000;
-	opal_register_exception_handler(OPAL_MACHINE_CHECK_HANDLER,
-					__pa(opal_mc_secondary_handler[0]),
-					glue);
-	glue += 128;
 	opal_register_exception_handler(OPAL_HYPERVISOR_MAINTENANCE_HANDLER,
 					0, glue);
 	glue += 128;
-- 
cgit v1.2.3


From b63a0ffe35de7e5f9b907bbc2c783e702f7e15af Mon Sep 17 00:00:00 2001
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Date: Wed, 30 Oct 2013 20:06:13 +0530
Subject: powerpc/powernv: Machine check exception handling.

Add basic error handling in machine check exception handler.

- If MSR_RI isn't set, we can not recover.
- Check if disposition set to OpalMCE_DISPOSITION_RECOVERED.
- Check if address at fault is inside kernel address space, if not then send
  SIGBUS to process if we hit exception when in userspace.
- If address at fault is not provided then and if we get a synchronous machine
  check while in userspace then kill the task.

Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/mce.h        |  1 +
 arch/powerpc/kernel/mce.c             | 27 ++++++++++++++++++++++
 arch/powerpc/platforms/powernv/opal.c | 43 ++++++++++++++++++++++++++++++++++-
 3 files changed, 70 insertions(+), 1 deletion(-)

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

diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index 3276b409299c..a2b8c7b35fba 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -193,5 +193,6 @@ extern void release_mce_event(void);
 extern void machine_check_queue_event(void);
 extern void machine_check_process_queued_event(void);
 extern void machine_check_print_event_info(struct machine_check_event *evt);
+extern uint64_t get_mce_fault_addr(struct machine_check_event *evt);
 
 #endif /* __ASM_PPC64_MCE_H__ */
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 1c6d15701c56..c0c52ec1fca7 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -316,3 +316,30 @@ void machine_check_print_event_info(struct machine_check_event *evt)
 		break;
 	}
 }
+
+uint64_t get_mce_fault_addr(struct machine_check_event *evt)
+{
+	switch (evt->error_type) {
+	case MCE_ERROR_TYPE_UE:
+		if (evt->u.ue_error.effective_address_provided)
+			return evt->u.ue_error.effective_address;
+		break;
+	case MCE_ERROR_TYPE_SLB:
+		if (evt->u.slb_error.effective_address_provided)
+			return evt->u.slb_error.effective_address;
+		break;
+	case MCE_ERROR_TYPE_ERAT:
+		if (evt->u.erat_error.effective_address_provided)
+			return evt->u.erat_error.effective_address;
+		break;
+	case MCE_ERROR_TYPE_TLB:
+		if (evt->u.tlb_error.effective_address_provided)
+			return evt->u.tlb_error.effective_address;
+		break;
+	default:
+	case MCE_ERROR_TYPE_UNKNOWN:
+		break;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(get_mce_fault_addr);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index f348bd49487c..01e74cbc67e9 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -18,6 +18,7 @@
 #include <linux/interrupt.h>
 #include <linux/notifier.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
 #include <linux/kobject.h>
 #include <asm/opal.h>
 #include <asm/firmware.h>
@@ -251,6 +252,44 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
 	return written;
 }
 
+static int opal_recover_mce(struct pt_regs *regs,
+					struct machine_check_event *evt)
+{
+	int recovered = 0;
+	uint64_t ea = get_mce_fault_addr(evt);
+
+	if (!(regs->msr & MSR_RI)) {
+		/* If MSR_RI isn't set, we cannot recover */
+		recovered = 0;
+	} else if (evt->disposition == MCE_DISPOSITION_RECOVERED) {
+		/* Platform corrected itself */
+		recovered = 1;
+	} else if (ea && !is_kernel_addr(ea)) {
+		/*
+		 * Faulting address is not in kernel text. We should be fine.
+		 * We need to find which process uses this address.
+		 * For now, kill the task if we have received exception when
+		 * in userspace.
+		 *
+		 * TODO: Queue up this address for hwpoisioning later.
+		 */
+		if (user_mode(regs) && !is_global_init(current)) {
+			_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
+			recovered = 1;
+		} else
+			recovered = 0;
+	} else if (user_mode(regs) && !is_global_init(current) &&
+		evt->severity == MCE_SEV_ERROR_SYNC) {
+		/*
+		 * If we have received a synchronous error when in userspace
+		 * kill the task.
+		 */
+		_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
+		recovered = 1;
+	}
+	return recovered;
+}
+
 int opal_machine_check(struct pt_regs *regs)
 {
 	struct machine_check_event evt;
@@ -266,7 +305,9 @@ int opal_machine_check(struct pt_regs *regs)
 	}
 	machine_check_print_event_info(&evt);
 
-	return evt.severity == MCE_SEV_FATAL ? 0 : 1;
+	if (opal_recover_mce(regs, &evt))
+		return 1;
+	return 0;
 }
 
 static irqreturn_t opal_interrupt(int irq, void *data)
-- 
cgit v1.2.3


From 24366360035a9e0a9870ed7208aa2ba1948f844d Mon Sep 17 00:00:00 2001
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Date: Mon, 18 Nov 2013 15:35:58 +0530
Subject: powerpc/powernv: Infrastructure to read opal messages in generic
 format.

Opal now has a new messaging infrastructure to push the messages to
linux in a generic format for different type of messages using only one
event bit. The format of the opal message is as below:

struct opal_msg {
        uint32_t msg_type;
	uint32_t reserved;
	uint64_t params[8];
};

This patch allows clients to subscribe for notification for specific
message type. It is upto the subscriber to decipher the messages who showed
interested in receiving specific message type.

The interface to subscribe for notification is:

	int opal_message_notifier_register(enum OpalMessageType msg_type,
                                        struct notifier_block *nb)

The notifier will fetch the opal message when available and notify the
subscriber with message type and the opal message. It is subscribers
responsibility to copy the message data before returning from notifier
callback.

Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/opal.h                | 24 ++++++-
 arch/powerpc/platforms/powernv/opal-wrappers.S |  2 +
 arch/powerpc/platforms/powernv/opal.c          | 90 ++++++++++++++++++++++++++
 3 files changed, 115 insertions(+), 1 deletion(-)

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

diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 033c06be1d84..ffb2036fcfb2 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -132,6 +132,8 @@ extern int opal_enter_rtas(struct rtas_args *args,
 #define OPAL_FLASH_VALIDATE			76
 #define OPAL_FLASH_MANAGE			77
 #define OPAL_FLASH_UPDATE			78
+#define OPAL_GET_MSG				85
+#define OPAL_CHECK_ASYNC_COMPLETION		86
 
 #ifndef __ASSEMBLY__
 
@@ -211,7 +213,16 @@ enum OpalPendingState {
 	OPAL_EVENT_ERROR_LOG		= 0x40,
 	OPAL_EVENT_EPOW			= 0x80,
 	OPAL_EVENT_LED_STATUS		= 0x100,
-	OPAL_EVENT_PCI_ERROR		= 0x200
+	OPAL_EVENT_PCI_ERROR		= 0x200,
+	OPAL_EVENT_MSG_PENDING		= 0x800,
+};
+
+enum OpalMessageType {
+	OPAL_MSG_ASYNC_COMP		= 0,
+	OPAL_MSG_MEM_ERR,
+	OPAL_MSG_EPOW,
+	OPAL_MSG_SHUTDOWN,
+	OPAL_MSG_TYPE_MAX,
 };
 
 /* Machine check related definitions */
@@ -356,6 +367,12 @@ enum OpalLPCAddressType {
 	OPAL_LPC_FW	= 2,
 };
 
+struct opal_msg {
+	uint32_t msg_type;
+	uint32_t reserved;
+	uint64_t params[8];
+};
+
 struct opal_machine_check_event {
 	enum OpalMCE_Version	version:8;	/* 0x00 */
 	uint8_t			in_use;		/* 0x01 */
@@ -731,6 +748,9 @@ int64_t opal_validate_flash(uint64_t buffer, uint32_t *size, uint32_t *result);
 int64_t opal_manage_flash(uint8_t op);
 int64_t opal_update_flash(uint64_t blk_list);
 
+int64_t opal_get_msg(uint64_t buffer, size_t size);
+int64_t opal_check_completion(uint64_t buffer, size_t size, uint64_t token);
+
 /* Internal functions */
 extern int early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data);
 
@@ -744,6 +764,8 @@ extern int early_init_dt_scan_opal(unsigned long node, const char *uname,
 				   int depth, void *data);
 
 extern int opal_notifier_register(struct notifier_block *nb);
+extern int opal_message_notifier_register(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-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index e7806504e976..719aa5c325c6 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -126,3 +126,5 @@ OPAL_CALL(opal_return_cpu,			OPAL_RETURN_CPU);
 OPAL_CALL(opal_validate_flash,			OPAL_FLASH_VALIDATE);
 OPAL_CALL(opal_manage_flash,			OPAL_FLASH_MANAGE);
 OPAL_CALL(opal_update_flash,			OPAL_FLASH_UPDATE);
+OPAL_CALL(opal_get_msg,				OPAL_GET_MSG);
+OPAL_CALL(opal_check_completion,		OPAL_CHECK_ASYNC_COMPLETION);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 01e74cbc67e9..7a184a0ff183 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -40,6 +40,7 @@ extern u64 opal_mc_secondary_handler[];
 static unsigned int *opal_irqs;
 static unsigned int opal_irq_count;
 static ATOMIC_NOTIFIER_HEAD(opal_notifier_head);
+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);
@@ -167,6 +168,95 @@ void opal_notifier_disable(void)
 	atomic_set(&opal_notifier_hold, 1);
 }
 
+/*
+ * 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,
+					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",
+			   __func__, msg_type);
+		return -EINVAL;
+	}
+	return atomic_notifier_chain_register(
+				&opal_msg_notifier_head[msg_type], nb);
+}
+
+static void opal_message_do_notify(uint32_t msg_type, void *msg)
+{
+	/* notify subscribers */
+	atomic_notifier_call_chain(&opal_msg_notifier_head[msg_type],
+					msg_type, msg);
+}
+
+static void opal_handle_message(void)
+{
+	s64 ret;
+	/*
+	 * TODO: pre-allocate a message buffer depending on opal-msg-size
+	 * value in /proc/device-tree.
+	 */
+	static struct opal_msg msg;
+
+	ret = opal_get_msg(__pa(&msg), sizeof(msg));
+	/* No opal message pending. */
+	if (ret == OPAL_RESOURCE)
+		return;
+
+	/* check for errors. */
+	if (ret) {
+		pr_warning("%s: Failed to retrive opal message, err=%lld\n",
+				__func__, ret);
+		return;
+	}
+
+	/* Sanity check */
+	if (msg.msg_type > OPAL_MSG_TYPE_MAX) {
+		pr_warning("%s: Unknown message type: %u\n",
+				__func__, msg.msg_type);
+		return;
+	}
+	opal_message_do_notify(msg.msg_type, (void *)&msg);
+}
+
+static int opal_message_notify(struct notifier_block *nb,
+			  unsigned long events, void *change)
+{
+	if (events & OPAL_EVENT_MSG_PENDING)
+		opal_handle_message();
+	return 0;
+}
+
+static struct notifier_block opal_message_nb = {
+	.notifier_call	= opal_message_notify,
+	.next		= NULL,
+	.priority	= 0,
+};
+
+static int __init opal_message_init(void)
+{
+	int ret, i;
+
+	for (i = 0; i < OPAL_MSG_TYPE_MAX; i++)
+		ATOMIC_INIT_NOTIFIER_HEAD(&opal_msg_notifier_head[i]);
+
+	ret = opal_notifier_register(&opal_message_nb);
+	if (ret) {
+		pr_err("%s: Can't register OPAL event notifier (%d)\n",
+		       __func__, ret);
+		return ret;
+	}
+	return 0;
+}
+early_initcall(opal_message_init);
+
 int opal_get_chars(uint32_t vtermno, char *buf, int count)
 {
 	s64 rc;
-- 
cgit v1.2.3


From 7e1ce5a492e18449fd47ef6305b26e0c572d26e9 Mon Sep 17 00:00:00 2001
From: Vasant Hegde <hegdevasant@linux.vnet.ibm.com>
Date: Mon, 18 Nov 2013 16:39:22 +0530
Subject: powerpc/powernv: Move SG list structure to header file

Move SG list and entry structure to header file so that
it can be used in other places as well.

Signed-off-by: Vasant Hegde <hegdevasant@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/opal.h             | 22 ++++++++++++++++++++
 arch/powerpc/platforms/powernv/opal-flash.c | 31 ++++++-----------------------
 2 files changed, 28 insertions(+), 25 deletions(-)

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

diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index ffb2036fcfb2..0a2ac85998d7 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -33,6 +33,28 @@ struct opal_takeover_args {
 	u64	rd_loc;			/* r11 */
 };
 
+/*
+ * SG entry
+ *
+ * WARNING: The current implementation requires each entry
+ * to represent a block that is 4k aligned *and* each block
+ * size except the last one in the list to be as well.
+ */
+struct opal_sg_entry {
+	void    *data;
+	long    length;
+};
+
+/* sg list */
+struct opal_sg_list {
+	unsigned long num_entries;
+	struct opal_sg_list *next;
+	struct opal_sg_entry entry[];
+};
+
+/* We calculate number of sg entries based on PAGE_SIZE */
+#define SG_ENTRIES_PER_NODE ((PAGE_SIZE - 16) / sizeof(struct opal_sg_entry))
+
 extern long opal_query_takeover(u64 *hal_size, u64 *hal_align);
 
 extern long opal_do_takeover(struct opal_takeover_args *args);
diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c
index 6ffa6b1ec5b7..4aeae4f36e1d 100644
--- a/arch/powerpc/platforms/powernv/opal-flash.c
+++ b/arch/powerpc/platforms/powernv/opal-flash.c
@@ -103,27 +103,6 @@ struct image_header_t {
 	uint32_t	size;
 };
 
-/* Scatter/gather entry */
-struct opal_sg_entry {
-	void	*data;
-	long	length;
-};
-
-/* We calculate number of entries based on PAGE_SIZE */
-#define SG_ENTRIES_PER_NODE ((PAGE_SIZE - 16) / sizeof(struct opal_sg_entry))
-
-/*
- * This struct is very similar but not identical to that
- * needed by the opal flash update. All we need to do for
- * opal is rewrite num_entries into a version/length and
- * translate the pointers to absolute.
- */
-struct opal_sg_list {
-	unsigned long num_entries;
-	struct opal_sg_list *next;
-	struct opal_sg_entry entry[SG_ENTRIES_PER_NODE];
-};
-
 struct validate_flash_t {
 	int		status;		/* Return status */
 	void		*buf;		/* Candiate image buffer */
@@ -333,7 +312,7 @@ static struct opal_sg_list *image_data_to_sglist(void)
 	addr = image_data.data;
 	size = image_data.size;
 
-	sg1 = kzalloc((sizeof(struct opal_sg_list)), GFP_KERNEL);
+	sg1 = kzalloc(PAGE_SIZE, GFP_KERNEL);
 	if (!sg1)
 		return NULL;
 
@@ -351,8 +330,7 @@ static struct opal_sg_list *image_data_to_sglist(void)
 
 		sg1->num_entries++;
 		if (sg1->num_entries >= SG_ENTRIES_PER_NODE) {
-			sg1->next = kzalloc((sizeof(struct opal_sg_list)),
-					    GFP_KERNEL);
+			sg1->next = kzalloc(PAGE_SIZE, GFP_KERNEL);
 			if (!sg1->next) {
 				pr_err("%s : Failed to allocate memory\n",
 				       __func__);
@@ -402,7 +380,10 @@ static int opal_flash_update(int op)
 		else
 			sg->next = NULL;
 
-		/* Make num_entries into the version/length field */
+		/*
+		 * Convert num_entries to version/length format
+		 * to satisfy OPAL.
+		 */
 		sg->num_entries = (SG_LIST_VERSION << 56) |
 			(sg->num_entries * sizeof(struct opal_sg_entry) + 16);
 	}
-- 
cgit v1.2.3


From d905c5df9aef38d63df268f6f5e7b13894f626d3 Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@ozlabs.ru>
Date: Thu, 21 Nov 2013 17:43:14 +1100
Subject: PPC: POWERNV: move iommu_add_device earlier

The current implementation of IOMMU on sPAPR does not use iommu_ops
and therefore does not call IOMMU API's bus_set_iommu() which
1) sets iommu_ops for a bus
2) registers a bus notifier
Instead, PCI devices are added to IOMMU groups from
subsys_initcall_sync(tce_iommu_init) which does basically the same
thing without using iommu_ops callbacks.

However Freescale PAMU driver (https://lkml.org/lkml/2013/7/1/158)
implements iommu_ops and when tce_iommu_init is called, every PCI device
is already added to some group so there is a conflict.

This patch does 2 things:
1. removes the loop in which PCI devices were added to groups and
adds explicit iommu_add_device() calls to add devices as soon as they get
the iommu_table pointer assigned to them.
2. moves a bus notifier to powernv code in order to avoid conflict with
the notifier from Freescale driver.

iommu_add_device() and iommu_del_device() are public now.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/iommu.h            | 26 ++++++++++++++++
 arch/powerpc/kernel/iommu.c                 | 48 +++--------------------------
 arch/powerpc/platforms/powernv/pci-ioda.c   |  8 ++---
 arch/powerpc/platforms/powernv/pci-p5ioc2.c |  2 +-
 arch/powerpc/platforms/powernv/pci.c        | 33 +++++++++++++++++++-
 arch/powerpc/platforms/pseries/iommu.c      |  8 +++--
 6 files changed, 72 insertions(+), 53 deletions(-)

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

diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index c34656a8925e..774fa2776907 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -101,8 +101,34 @@ extern void iommu_free_table(struct iommu_table *tbl, const char *node_name);
  */
 extern struct iommu_table *iommu_init_table(struct iommu_table * tbl,
 					    int nid);
+#ifdef CONFIG_IOMMU_API
 extern void iommu_register_group(struct iommu_table *tbl,
 				 int pci_domain_number, unsigned long pe_num);
+extern int iommu_add_device(struct device *dev);
+extern void iommu_del_device(struct device *dev);
+#else
+static inline void iommu_register_group(struct iommu_table *tbl,
+					int pci_domain_number,
+					unsigned long pe_num)
+{
+}
+
+static inline int iommu_add_device(struct device *dev)
+{
+	return 0;
+}
+
+static inline void iommu_del_device(struct device *dev)
+{
+}
+#endif /* !CONFIG_IOMMU_API */
+
+static inline void set_iommu_table_base_and_group(struct device *dev,
+						  void *base)
+{
+	set_iommu_table_base(dev, base);
+	iommu_add_device(dev);
+}
 
 extern int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 			struct scatterlist *sglist, int nelems,
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 572bb5b95f35..d22abe0b08e3 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1105,7 +1105,7 @@ void iommu_release_ownership(struct iommu_table *tbl)
 }
 EXPORT_SYMBOL_GPL(iommu_release_ownership);
 
-static int iommu_add_device(struct device *dev)
+int iommu_add_device(struct device *dev)
 {
 	struct iommu_table *tbl;
 	int ret = 0;
@@ -1134,52 +1134,12 @@ static int iommu_add_device(struct device *dev)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(iommu_add_device);
 
-static void iommu_del_device(struct device *dev)
+void iommu_del_device(struct device *dev)
 {
 	iommu_group_remove_device(dev);
 }
-
-static int iommu_bus_notifier(struct notifier_block *nb,
-			      unsigned long action, void *data)
-{
-	struct device *dev = data;
-
-	switch (action) {
-	case BUS_NOTIFY_ADD_DEVICE:
-		return iommu_add_device(dev);
-	case BUS_NOTIFY_DEL_DEVICE:
-		iommu_del_device(dev);
-		return 0;
-	default:
-		return 0;
-	}
-}
-
-static struct notifier_block tce_iommu_bus_nb = {
-	.notifier_call = iommu_bus_notifier,
-};
-
-static int __init tce_iommu_init(void)
-{
-	struct pci_dev *pdev = NULL;
-
-	BUILD_BUG_ON(PAGE_SIZE < IOMMU_PAGE_SIZE);
-
-	for_each_pci_dev(pdev)
-		iommu_add_device(&pdev->dev);
-
-	bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb);
-	return 0;
-}
-
-subsys_initcall_sync(tce_iommu_init);
-
-#else
-
-void iommu_register_group(struct iommu_table *tbl,
-		int pci_domain_number, unsigned long pe_num)
-{
-}
+EXPORT_SYMBOL_GPL(iommu_del_device);
 
 #endif /* CONFIG_IOMMU_API */
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 084cdfa40682..614356cac466 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -460,7 +460,7 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
 		return;
 
 	pe = &phb->ioda.pe_array[pdn->pe_number];
-	set_iommu_table_base(&pdev->dev, &pe->tce32_table);
+	set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table);
 }
 
 static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
@@ -468,7 +468,7 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus)
 	struct pci_dev *dev;
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
-		set_iommu_table_base(&dev->dev, &pe->tce32_table);
+		set_iommu_table_base_and_group(&dev->dev, &pe->tce32_table);
 		if (dev->subordinate)
 			pnv_ioda_setup_bus_dma(pe, dev->subordinate);
 	}
@@ -644,7 +644,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 	iommu_register_group(tbl, pci_domain_nr(pe->pbus), pe->pe_number);
 
 	if (pe->pdev)
-		set_iommu_table_base(&pe->pdev->dev, tbl);
+		set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
 	else
 		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 
@@ -722,7 +722,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 	iommu_init_table(tbl, phb->hose->node);
 
 	if (pe->pdev)
-		set_iommu_table_base(&pe->pdev->dev, tbl);
+		set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
 	else
 		pnv_ioda_setup_bus_dma(pe, pe->pbus);
 
diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
index f8b4bd8afb2e..e3807d69393e 100644
--- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c
+++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
@@ -92,7 +92,7 @@ static void pnv_pci_p5ioc2_dma_dev_setup(struct pnv_phb *phb,
 				pci_domain_nr(phb->hose->bus), phb->opal_id);
 	}
 
-	set_iommu_table_base(&pdev->dev, &phb->p5ioc2.iommu_table);
+	set_iommu_table_base_and_group(&pdev->dev, &phb->p5ioc2.iommu_table);
 }
 
 static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id,
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 4eb33a9ed532..6f3d49c18d64 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -536,7 +536,7 @@ static void pnv_pci_dma_fallback_setup(struct pci_controller *hose,
 		pdn->iommu_table = pnv_pci_setup_bml_iommu(hose);
 	if (!pdn->iommu_table)
 		return;
-	set_iommu_table_base(&pdev->dev, pdn->iommu_table);
+	set_iommu_table_base_and_group(&pdev->dev, pdn->iommu_table);
 }
 
 static void pnv_pci_dma_dev_setup(struct pci_dev *pdev)
@@ -657,3 +657,34 @@ void __init pnv_pci_init(void)
 	ppc_md.teardown_msi_irqs = pnv_teardown_msi_irqs;
 #endif
 }
+
+static int tce_iommu_bus_notifier(struct notifier_block *nb,
+		unsigned long action, void *data)
+{
+	struct device *dev = data;
+
+	switch (action) {
+	case BUS_NOTIFY_ADD_DEVICE:
+		return iommu_add_device(dev);
+	case BUS_NOTIFY_DEL_DEVICE:
+		if (dev->iommu_group)
+			iommu_del_device(dev);
+		return 0;
+	default:
+		return 0;
+	}
+}
+
+static struct notifier_block tce_iommu_bus_nb = {
+	.notifier_call = tce_iommu_bus_notifier,
+};
+
+static int __init tce_iommu_bus_notifier_init(void)
+{
+	BUILD_BUG_ON(PAGE_SIZE < IOMMU_PAGE_SIZE);
+
+	bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb);
+	return 0;
+}
+
+subsys_initcall_sync(tce_iommu_bus_notifier_init);
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index f253361552ae..a80af6c20cba 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -687,7 +687,8 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
 		iommu_table_setparms(phb, dn, tbl);
 		PCI_DN(dn)->iommu_table = iommu_init_table(tbl, phb->node);
 		iommu_register_group(tbl, pci_domain_nr(phb->bus), 0);
-		set_iommu_table_base(&dev->dev, PCI_DN(dn)->iommu_table);
+		set_iommu_table_base_and_group(&dev->dev,
+					       PCI_DN(dn)->iommu_table);
 		return;
 	}
 
@@ -699,7 +700,8 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
 		dn = dn->parent;
 
 	if (dn && PCI_DN(dn))
-		set_iommu_table_base(&dev->dev, PCI_DN(dn)->iommu_table);
+		set_iommu_table_base_and_group(&dev->dev,
+					       PCI_DN(dn)->iommu_table);
 	else
 		printk(KERN_WARNING "iommu: Device %s has no iommu table\n",
 		       pci_name(dev));
@@ -1193,7 +1195,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 		pr_debug("  found DMA window, table: %p\n", pci->iommu_table);
 	}
 
-	set_iommu_table_base(&dev->dev, pci->iommu_table);
+	set_iommu_table_base_and_group(&dev->dev, pci->iommu_table);
 }
 
 static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask)
-- 
cgit v1.2.3


From 93aef2a789778e7ec787179fc9b34ca4885a5ef3 Mon Sep 17 00:00:00 2001
From: Gavin Shan <shangw@linux.vnet.ibm.com>
Date: Fri, 22 Nov 2013 16:28:45 +0800
Subject: powerpc/powernv: Move PHB-diag dump functions around

Prior to the completion of PCI enumeration, we actively detects
EEH errors on PCI config cycles and dump PHB diag-data if necessary.
The EEH backend also dumps PHB diag-data in case of frozen PE or
fenced PHB. However, we are using different functions to dump the
PHB diag-data for those 2 cases.

The patch merges the functions for dumping PHB diag-data to one so
that we can avoid duplicate code. Also, we never dump PHB3 diag-data
during PCI config cycles with frozen PE. The patch fixes it as well.

Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/eeh-ioda.c | 150 +----------------------
 arch/powerpc/platforms/powernv/pci.c      | 196 +++++++++++++++++++++---------
 arch/powerpc/platforms/powernv/pci.h      |   3 +
 3 files changed, 144 insertions(+), 205 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 02245cee7818..be33a16408be 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -681,164 +681,20 @@ static void ioda_eeh_hub_diag(struct pci_controller *hose)
 	}
 }
 
-static void ioda_eeh_p7ioc_phb_diag(struct pci_controller *hose,
-				    struct OpalIoPhbErrorCommon *common)
-{
-	struct OpalIoP7IOCPhbErrorData *data;
-	int i;
-
-	data = (struct OpalIoP7IOCPhbErrorData *)common;
-
-	pr_info("P7IOC PHB#%x Diag-data (Version: %d)\n\n",
-		hose->global_number, common->version);
-
-	pr_info("  brdgCtl:              %08x\n", data->brdgCtl);
-
-	pr_info("  portStatusReg:        %08x\n", data->portStatusReg);
-	pr_info("  rootCmplxStatus:      %08x\n", data->rootCmplxStatus);
-	pr_info("  busAgentStatus:       %08x\n", data->busAgentStatus);
-
-	pr_info("  deviceStatus:         %08x\n", data->deviceStatus);
-	pr_info("  slotStatus:           %08x\n", data->slotStatus);
-	pr_info("  linkStatus:           %08x\n", data->linkStatus);
-	pr_info("  devCmdStatus:         %08x\n", data->devCmdStatus);
-	pr_info("  devSecStatus:         %08x\n", data->devSecStatus);
-
-	pr_info("  rootErrorStatus:      %08x\n", data->rootErrorStatus);
-	pr_info("  uncorrErrorStatus:    %08x\n", data->uncorrErrorStatus);
-	pr_info("  corrErrorStatus:      %08x\n", data->corrErrorStatus);
-	pr_info("  tlpHdr1:              %08x\n", data->tlpHdr1);
-	pr_info("  tlpHdr2:              %08x\n", data->tlpHdr2);
-	pr_info("  tlpHdr3:              %08x\n", data->tlpHdr3);
-	pr_info("  tlpHdr4:              %08x\n", data->tlpHdr4);
-	pr_info("  sourceId:             %08x\n", data->sourceId);
-
-	pr_info("  errorClass:           %016llx\n", data->errorClass);
-	pr_info("  correlator:           %016llx\n", data->correlator);
-	pr_info("  p7iocPlssr:           %016llx\n", data->p7iocPlssr);
-	pr_info("  p7iocCsr:             %016llx\n", data->p7iocCsr);
-	pr_info("  lemFir:               %016llx\n", data->lemFir);
-	pr_info("  lemErrorMask:         %016llx\n", data->lemErrorMask);
-	pr_info("  lemWOF:               %016llx\n", data->lemWOF);
-	pr_info("  phbErrorStatus:       %016llx\n", data->phbErrorStatus);
-	pr_info("  phbFirstErrorStatus:  %016llx\n", data->phbFirstErrorStatus);
-	pr_info("  phbErrorLog0:         %016llx\n", data->phbErrorLog0);
-	pr_info("  phbErrorLog1:         %016llx\n", data->phbErrorLog1);
-	pr_info("  mmioErrorStatus:      %016llx\n", data->mmioErrorStatus);
-	pr_info("  mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
-	pr_info("  mmioErrorLog0:        %016llx\n", data->mmioErrorLog0);
-	pr_info("  mmioErrorLog1:        %016llx\n", data->mmioErrorLog1);
-	pr_info("  dma0ErrorStatus:      %016llx\n", data->dma0ErrorStatus);
-	pr_info("  dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
-	pr_info("  dma0ErrorLog0:        %016llx\n", data->dma0ErrorLog0);
-	pr_info("  dma0ErrorLog1:        %016llx\n", data->dma0ErrorLog1);
-	pr_info("  dma1ErrorStatus:      %016llx\n", data->dma1ErrorStatus);
-	pr_info("  dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
-	pr_info("  dma1ErrorLog0:        %016llx\n", data->dma1ErrorLog0);
-	pr_info("  dma1ErrorLog1:        %016llx\n", data->dma1ErrorLog1);
-
-	for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) {
-		if ((data->pestA[i] >> 63) == 0 &&
-		    (data->pestB[i] >> 63) == 0)
-			continue;
-
-		pr_info("  PE[%3d] PESTA:        %016llx\n", i, data->pestA[i]);
-		pr_info("          PESTB:        %016llx\n", data->pestB[i]);
-	}
-}
-
-static void ioda_eeh_phb3_phb_diag(struct pci_controller *hose,
-				    struct OpalIoPhbErrorCommon *common)
-{
-	struct OpalIoPhb3ErrorData *data;
-	int i;
-
-	data = (struct OpalIoPhb3ErrorData*)common;
-	pr_info("PHB3 PHB#%x Diag-data (Version: %d)\n\n",
-		hose->global_number, common->version);
-
-	pr_info("  brdgCtl:              %08x\n", data->brdgCtl);
-
-	pr_info("  portStatusReg:        %08x\n", data->portStatusReg);
-	pr_info("  rootCmplxStatus:      %08x\n", data->rootCmplxStatus);
-	pr_info("  busAgentStatus:       %08x\n", data->busAgentStatus);
-
-	pr_info("  deviceStatus:         %08x\n", data->deviceStatus);
-	pr_info("  slotStatus:           %08x\n", data->slotStatus);
-	pr_info("  linkStatus:           %08x\n", data->linkStatus);
-	pr_info("  devCmdStatus:         %08x\n", data->devCmdStatus);
-	pr_info("  devSecStatus:         %08x\n", data->devSecStatus);
-
-	pr_info("  rootErrorStatus:      %08x\n", data->rootErrorStatus);
-	pr_info("  uncorrErrorStatus:    %08x\n", data->uncorrErrorStatus);
-	pr_info("  corrErrorStatus:      %08x\n", data->corrErrorStatus);
-	pr_info("  tlpHdr1:              %08x\n", data->tlpHdr1);
-	pr_info("  tlpHdr2:              %08x\n", data->tlpHdr2);
-	pr_info("  tlpHdr3:              %08x\n", data->tlpHdr3);
-	pr_info("  tlpHdr4:              %08x\n", data->tlpHdr4);
-	pr_info("  sourceId:             %08x\n", data->sourceId);
-	pr_info("  errorClass:           %016llx\n", data->errorClass);
-	pr_info("  correlator:           %016llx\n", data->correlator);
-	pr_info("  nFir:                 %016llx\n", data->nFir);
-	pr_info("  nFirMask:             %016llx\n", data->nFirMask);
-	pr_info("  nFirWOF:              %016llx\n", data->nFirWOF);
-	pr_info("  PhbPlssr:             %016llx\n", data->phbPlssr);
-	pr_info("  PhbCsr:               %016llx\n", data->phbCsr);
-	pr_info("  lemFir:               %016llx\n", data->lemFir);
-	pr_info("  lemErrorMask:         %016llx\n", data->lemErrorMask);
-	pr_info("  lemWOF:               %016llx\n", data->lemWOF);
-	pr_info("  phbErrorStatus:       %016llx\n", data->phbErrorStatus);
-	pr_info("  phbFirstErrorStatus:  %016llx\n", data->phbFirstErrorStatus);
-	pr_info("  phbErrorLog0:         %016llx\n", data->phbErrorLog0);
-	pr_info("  phbErrorLog1:         %016llx\n", data->phbErrorLog1);
-	pr_info("  mmioErrorStatus:      %016llx\n", data->mmioErrorStatus);
-	pr_info("  mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
-	pr_info("  mmioErrorLog0:        %016llx\n", data->mmioErrorLog0);
-	pr_info("  mmioErrorLog1:        %016llx\n", data->mmioErrorLog1);
-	pr_info("  dma0ErrorStatus:      %016llx\n", data->dma0ErrorStatus);
-	pr_info("  dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
-	pr_info("  dma0ErrorLog0:        %016llx\n", data->dma0ErrorLog0);
-	pr_info("  dma0ErrorLog1:        %016llx\n", data->dma0ErrorLog1);
-	pr_info("  dma1ErrorStatus:      %016llx\n", data->dma1ErrorStatus);
-	pr_info("  dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
-	pr_info("  dma1ErrorLog0:        %016llx\n", data->dma1ErrorLog0);
-	pr_info("  dma1ErrorLog1:        %016llx\n", data->dma1ErrorLog1);
-
-	for (i = 0; i < OPAL_PHB3_NUM_PEST_REGS; i++) {
-		if ((data->pestA[i] >> 63) == 0 &&
-		    (data->pestB[i] >> 63) == 0)
-			continue;
-
-		pr_info("  PE[%3d] PESTA:        %016llx\n", i, data->pestA[i]);
-		pr_info("          PESTB:        %016llx\n", data->pestB[i]);
-	}
-}
-
 static void ioda_eeh_phb_diag(struct pci_controller *hose)
 {
 	struct pnv_phb *phb = hose->private_data;
-	struct OpalIoPhbErrorCommon *common;
 	long rc;
 
-	common = (struct OpalIoPhbErrorCommon *)phb->diag.blob;
-	rc = opal_pci_get_phb_diag_data2(phb->opal_id, common, PAGE_SIZE);
+	rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
+					 PNV_PCI_DIAG_BUF_SIZE);
 	if (rc != OPAL_SUCCESS) {
 		pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n",
 			    __func__, hose->global_number, rc);
 		return;
 	}
 
-	switch (common->ioType) {
-	case OPAL_PHB_ERROR_DATA_TYPE_P7IOC:
-		ioda_eeh_p7ioc_phb_diag(hose, common);
-		break;
-	case OPAL_PHB_ERROR_DATA_TYPE_PHB3:
-		ioda_eeh_phb3_phb_diag(hose, common);
-		break;
-	default:
-		pr_warning("%s: Unrecognized I/O chip %d\n",
-			   __func__, common->ioType);
-	}
+	pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
 }
 
 static int ioda_eeh_get_phb_pe(struct pci_controller *hose,
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 6f3d49c18d64..bac289aac7cc 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -124,77 +124,157 @@ static void pnv_teardown_msi_irqs(struct pci_dev *pdev)
 }
 #endif /* CONFIG_PCI_MSI */
 
-static void pnv_pci_dump_p7ioc_diag_data(struct pnv_phb *phb)
+static void pnv_pci_dump_p7ioc_diag_data(struct pci_controller *hose,
+					 struct OpalIoPhbErrorCommon *common)
 {
-	struct OpalIoP7IOCPhbErrorData *data = &phb->diag.p7ioc;
+	struct OpalIoP7IOCPhbErrorData *data;
 	int i;
 
-	pr_info("PHB %d diagnostic data:\n", phb->hose->global_number);
-
-	pr_info("  brdgCtl              = 0x%08x\n", data->brdgCtl);
-
-	pr_info("  portStatusReg        = 0x%08x\n", data->portStatusReg);
-	pr_info("  rootCmplxStatus      = 0x%08x\n", data->rootCmplxStatus);
-	pr_info("  busAgentStatus       = 0x%08x\n", data->busAgentStatus);
-
-	pr_info("  deviceStatus         = 0x%08x\n", data->deviceStatus);
-	pr_info("  slotStatus           = 0x%08x\n", data->slotStatus);
-	pr_info("  linkStatus           = 0x%08x\n", data->linkStatus);
-	pr_info("  devCmdStatus         = 0x%08x\n", data->devCmdStatus);
-	pr_info("  devSecStatus         = 0x%08x\n", data->devSecStatus);
-
-	pr_info("  rootErrorStatus      = 0x%08x\n", data->rootErrorStatus);
-	pr_info("  uncorrErrorStatus    = 0x%08x\n", data->uncorrErrorStatus);
-	pr_info("  corrErrorStatus      = 0x%08x\n", data->corrErrorStatus);
-	pr_info("  tlpHdr1              = 0x%08x\n", data->tlpHdr1);
-	pr_info("  tlpHdr2              = 0x%08x\n", data->tlpHdr2);
-	pr_info("  tlpHdr3              = 0x%08x\n", data->tlpHdr3);
-	pr_info("  tlpHdr4              = 0x%08x\n", data->tlpHdr4);
-	pr_info("  sourceId             = 0x%08x\n", data->sourceId);
-
-	pr_info("  errorClass           = 0x%016llx\n", data->errorClass);
-	pr_info("  correlator           = 0x%016llx\n", data->correlator);
-
-	pr_info("  p7iocPlssr           = 0x%016llx\n", data->p7iocPlssr);
-	pr_info("  p7iocCsr             = 0x%016llx\n", data->p7iocCsr);
-	pr_info("  lemFir               = 0x%016llx\n", data->lemFir);
-	pr_info("  lemErrorMask         = 0x%016llx\n", data->lemErrorMask);
-	pr_info("  lemWOF               = 0x%016llx\n", data->lemWOF);
-	pr_info("  phbErrorStatus       = 0x%016llx\n", data->phbErrorStatus);
-	pr_info("  phbFirstErrorStatus  = 0x%016llx\n", data->phbFirstErrorStatus);
-	pr_info("  phbErrorLog0         = 0x%016llx\n", data->phbErrorLog0);
-	pr_info("  phbErrorLog1         = 0x%016llx\n", data->phbErrorLog1);
-	pr_info("  mmioErrorStatus      = 0x%016llx\n", data->mmioErrorStatus);
-	pr_info("  mmioFirstErrorStatus = 0x%016llx\n", data->mmioFirstErrorStatus);
-	pr_info("  mmioErrorLog0        = 0x%016llx\n", data->mmioErrorLog0);
-	pr_info("  mmioErrorLog1        = 0x%016llx\n", data->mmioErrorLog1);
-	pr_info("  dma0ErrorStatus      = 0x%016llx\n", data->dma0ErrorStatus);
-	pr_info("  dma0FirstErrorStatus = 0x%016llx\n", data->dma0FirstErrorStatus);
-	pr_info("  dma0ErrorLog0        = 0x%016llx\n", data->dma0ErrorLog0);
-	pr_info("  dma0ErrorLog1        = 0x%016llx\n", data->dma0ErrorLog1);
-	pr_info("  dma1ErrorStatus      = 0x%016llx\n", data->dma1ErrorStatus);
-	pr_info("  dma1FirstErrorStatus = 0x%016llx\n", data->dma1FirstErrorStatus);
-	pr_info("  dma1ErrorLog0        = 0x%016llx\n", data->dma1ErrorLog0);
-	pr_info("  dma1ErrorLog1        = 0x%016llx\n", data->dma1ErrorLog1);
+	data = (struct OpalIoP7IOCPhbErrorData *)common;
+	pr_info("P7IOC PHB#%d Diag-data (Version: %d)\n\n",
+		hose->global_number, common->version);
+
+	pr_info("  brdgCtl:              %08x\n", data->brdgCtl);
+
+	pr_info("  portStatusReg:        %08x\n", data->portStatusReg);
+	pr_info("  rootCmplxStatus:      %08x\n", data->rootCmplxStatus);
+	pr_info("  busAgentStatus:       %08x\n", data->busAgentStatus);
+
+	pr_info("  deviceStatus:         %08x\n", data->deviceStatus);
+	pr_info("  slotStatus:           %08x\n", data->slotStatus);
+	pr_info("  linkStatus:           %08x\n", data->linkStatus);
+	pr_info("  devCmdStatus:         %08x\n", data->devCmdStatus);
+	pr_info("  devSecStatus:         %08x\n", data->devSecStatus);
+
+	pr_info("  rootErrorStatus:      %08x\n", data->rootErrorStatus);
+	pr_info("  uncorrErrorStatus:    %08x\n", data->uncorrErrorStatus);
+	pr_info("  corrErrorStatus:      %08x\n", data->corrErrorStatus);
+	pr_info("  tlpHdr1:              %08x\n", data->tlpHdr1);
+	pr_info("  tlpHdr2:              %08x\n", data->tlpHdr2);
+	pr_info("  tlpHdr3:              %08x\n", data->tlpHdr3);
+	pr_info("  tlpHdr4:              %08x\n", data->tlpHdr4);
+	pr_info("  sourceId:             %08x\n", data->sourceId);
+	pr_info("  errorClass:           %016llx\n", data->errorClass);
+	pr_info("  correlator:           %016llx\n", data->correlator);
+	pr_info("  p7iocPlssr:           %016llx\n", data->p7iocPlssr);
+	pr_info("  p7iocCsr:             %016llx\n", data->p7iocCsr);
+	pr_info("  lemFir:               %016llx\n", data->lemFir);
+	pr_info("  lemErrorMask:         %016llx\n", data->lemErrorMask);
+	pr_info("  lemWOF:               %016llx\n", data->lemWOF);
+	pr_info("  phbErrorStatus:       %016llx\n", data->phbErrorStatus);
+	pr_info("  phbFirstErrorStatus:  %016llx\n", data->phbFirstErrorStatus);
+	pr_info("  phbErrorLog0:         %016llx\n", data->phbErrorLog0);
+	pr_info("  phbErrorLog1:         %016llx\n", data->phbErrorLog1);
+	pr_info("  mmioErrorStatus:      %016llx\n", data->mmioErrorStatus);
+	pr_info("  mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
+	pr_info("  mmioErrorLog0:        %016llx\n", data->mmioErrorLog0);
+	pr_info("  mmioErrorLog1:        %016llx\n", data->mmioErrorLog1);
+	pr_info("  dma0ErrorStatus:      %016llx\n", data->dma0ErrorStatus);
+	pr_info("  dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
+	pr_info("  dma0ErrorLog0:        %016llx\n", data->dma0ErrorLog0);
+	pr_info("  dma0ErrorLog1:        %016llx\n", data->dma0ErrorLog1);
+	pr_info("  dma1ErrorStatus:      %016llx\n", data->dma1ErrorStatus);
+	pr_info("  dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
+	pr_info("  dma1ErrorLog0:        %016llx\n", data->dma1ErrorLog0);
+	pr_info("  dma1ErrorLog1:        %016llx\n", data->dma1ErrorLog1);
 
 	for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) {
 		if ((data->pestA[i] >> 63) == 0 &&
 		    (data->pestB[i] >> 63) == 0)
 			continue;
-		pr_info("  PE[%3d] PESTA        = 0x%016llx\n", i, data->pestA[i]);
-		pr_info("          PESTB        = 0x%016llx\n", data->pestB[i]);
+
+		pr_info("  PE[%3d] PESTA:        %016llx\n", i, data->pestA[i]);
+		pr_info("          PESTB:        %016llx\n", data->pestB[i]);
 	}
 }
 
-static void pnv_pci_dump_phb_diag_data(struct pnv_phb *phb)
+static void pnv_pci_dump_phb3_diag_data(struct pci_controller *hose,
+					struct OpalIoPhbErrorCommon *common)
 {
-	switch(phb->model) {
-	case PNV_PHB_MODEL_P7IOC:
-		pnv_pci_dump_p7ioc_diag_data(phb);
+	struct OpalIoPhb3ErrorData *data;
+	int i;
+
+	data = (struct OpalIoPhb3ErrorData*)common;
+	pr_info("PHB3 PHB#%d Diag-data (Version: %d)\n\n",
+		hose->global_number, common->version);
+
+	pr_info("  brdgCtl:              %08x\n", data->brdgCtl);
+
+	pr_info("  portStatusReg:        %08x\n", data->portStatusReg);
+	pr_info("  rootCmplxStatus:      %08x\n", data->rootCmplxStatus);
+	pr_info("  busAgentStatus:       %08x\n", data->busAgentStatus);
+
+	pr_info("  deviceStatus:         %08x\n", data->deviceStatus);
+	pr_info("  slotStatus:           %08x\n", data->slotStatus);
+	pr_info("  linkStatus:           %08x\n", data->linkStatus);
+	pr_info("  devCmdStatus:         %08x\n", data->devCmdStatus);
+	pr_info("  devSecStatus:         %08x\n", data->devSecStatus);
+
+	pr_info("  rootErrorStatus:      %08x\n", data->rootErrorStatus);
+	pr_info("  uncorrErrorStatus:    %08x\n", data->uncorrErrorStatus);
+	pr_info("  corrErrorStatus:      %08x\n", data->corrErrorStatus);
+	pr_info("  tlpHdr1:              %08x\n", data->tlpHdr1);
+	pr_info("  tlpHdr2:              %08x\n", data->tlpHdr2);
+	pr_info("  tlpHdr3:              %08x\n", data->tlpHdr3);
+	pr_info("  tlpHdr4:              %08x\n", data->tlpHdr4);
+	pr_info("  sourceId:             %08x\n", data->sourceId);
+	pr_info("  errorClass:           %016llx\n", data->errorClass);
+	pr_info("  correlator:           %016llx\n", data->correlator);
+
+	pr_info("  nFir:                 %016llx\n", data->nFir);
+	pr_info("  nFirMask:             %016llx\n", data->nFirMask);
+	pr_info("  nFirWOF:              %016llx\n", data->nFirWOF);
+	pr_info("  PhbPlssr:             %016llx\n", data->phbPlssr);
+	pr_info("  PhbCsr:               %016llx\n", data->phbCsr);
+	pr_info("  lemFir:               %016llx\n", data->lemFir);
+	pr_info("  lemErrorMask:         %016llx\n", data->lemErrorMask);
+	pr_info("  lemWOF:               %016llx\n", data->lemWOF);
+	pr_info("  phbErrorStatus:       %016llx\n", data->phbErrorStatus);
+	pr_info("  phbFirstErrorStatus:  %016llx\n", data->phbFirstErrorStatus);
+	pr_info("  phbErrorLog0:         %016llx\n", data->phbErrorLog0);
+	pr_info("  phbErrorLog1:         %016llx\n", data->phbErrorLog1);
+	pr_info("  mmioErrorStatus:      %016llx\n", data->mmioErrorStatus);
+	pr_info("  mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
+	pr_info("  mmioErrorLog0:        %016llx\n", data->mmioErrorLog0);
+	pr_info("  mmioErrorLog1:        %016llx\n", data->mmioErrorLog1);
+	pr_info("  dma0ErrorStatus:      %016llx\n", data->dma0ErrorStatus);
+	pr_info("  dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
+	pr_info("  dma0ErrorLog0:        %016llx\n", data->dma0ErrorLog0);
+	pr_info("  dma0ErrorLog1:        %016llx\n", data->dma0ErrorLog1);
+	pr_info("  dma1ErrorStatus:      %016llx\n", data->dma1ErrorStatus);
+	pr_info("  dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
+	pr_info("  dma1ErrorLog0:        %016llx\n", data->dma1ErrorLog0);
+	pr_info("  dma1ErrorLog1:        %016llx\n", data->dma1ErrorLog1);
+
+	for (i = 0; i < OPAL_PHB3_NUM_PEST_REGS; i++) {
+		if ((data->pestA[i] >> 63) == 0 &&
+		    (data->pestB[i] >> 63) == 0)
+			continue;
+
+		pr_info("  PE[%3d] PESTA:        %016llx\n", i, data->pestA[i]);
+		pr_info("          PESTB:        %016llx\n", data->pestB[i]);
+	}
+}
+
+void pnv_pci_dump_phb_diag_data(struct pci_controller *hose,
+				unsigned char *log_buff)
+{
+	struct OpalIoPhbErrorCommon *common;
+
+	if (!hose || !log_buff)
+		return;
+
+	common = (struct OpalIoPhbErrorCommon *)log_buff;
+	switch (common->ioType) {
+	case OPAL_PHB_ERROR_DATA_TYPE_P7IOC:
+		pnv_pci_dump_p7ioc_diag_data(hose, common);
+		break;
+	case OPAL_PHB_ERROR_DATA_TYPE_PHB3:
+		pnv_pci_dump_phb3_diag_data(hose, common);
 		break;
 	default:
-		pr_warning("PCI %d: Can't decode this PHB diag data\n",
-			   phb->hose->global_number);
+		pr_warn("%s: Unrecognized ioType %d\n",
+			__func__, common->ioType);
 	}
 }
 
@@ -222,7 +302,7 @@ static void pnv_pci_handle_eeh_config(struct pnv_phb *phb, u32 pe_no)
 		 * with the normal errors generated when probing empty slots
 		 */
 		if (has_diag)
-			pnv_pci_dump_phb_diag_data(phb);
+			pnv_pci_dump_phb_diag_data(phb->hose, phb->diag.blob);
 		else
 			pr_warning("PCI %d: No diag data available\n",
 				   phb->hose->global_number);
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 911c24ef033e..9a11ff0c5c0b 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -176,6 +176,7 @@ struct pnv_phb {
 	union {
 		unsigned char			blob[PNV_PCI_DIAG_BUF_SIZE];
 		struct OpalIoP7IOCPhbErrorData	p7ioc;
+		struct OpalIoPhb3ErrorData	phb3;
 	} diag;
 };
 
@@ -184,6 +185,8 @@ extern struct pci_ops pnv_pci_ops;
 extern struct pnv_eeh_ops ioda_eeh_ops;
 #endif
 
+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 where, int size, u32 *val);
 int pnv_pci_cfg_write(struct device_node *dn,
-- 
cgit v1.2.3


From 2c77e95741e1202f993a4126f1f401459f1bcd4d Mon Sep 17 00:00:00 2001
From: Gavin Shan <shangw@linux.vnet.ibm.com>
Date: Fri, 22 Nov 2013 16:28:46 +0800
Subject: powerpc/eeh: Output PHB diag-data

When hitting frozen PE or fenced PHB, it's always indicative to
have dumped PHB diag-data for further analysis and diagnosis.
However, we never dump that for the cases. The patch intends to
dump PHB diag-data at the backend of eeh_ops::get_log() for PowerNV
platform.

Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/eeh-ioda.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 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 be33a16408be..31320c641c92 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -588,11 +588,8 @@ static int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
 		return -EIO;
 	}
 
-	/*
-	 * FIXME: We probably need log the error in somewhere.
-	 * Lets make it up in future.
-	 */
-	/* pr_info("%s", phb->diag.blob); */
+	/* The PHB diag-data is always indicative */
+	pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
 
 	spin_unlock_irqrestore(&phb->lock, flags);
 
-- 
cgit v1.2.3


From 2c49195b6aedd21ff1cd1e095fab9866fba3411b Mon Sep 17 00:00:00 2001
From: Michael Neuling <mikey@neuling.org>
Date: Fri, 29 Nov 2013 14:22:48 +1100
Subject: powernv: Remove get/set_rtc_time when they are not present

Currently we continue to poll get/set_rtc_time even when we know they
are not working.

This changes it so that if it fails at boot time we remove the ppc_md
get/set_rtc_time hooks so that we don't end up polling known broken
calls.

Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/opal-rtc.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

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

diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c
index 7d07c7e80ec0..b1885db8fdf3 100644
--- a/arch/powerpc/platforms/powernv/opal-rtc.c
+++ b/arch/powerpc/platforms/powernv/opal-rtc.c
@@ -18,6 +18,7 @@
 
 #include <asm/opal.h>
 #include <asm/firmware.h>
+#include <asm/machdep.h>
 
 static void opal_to_tm(u32 y_m_d, u64 h_m_s_ms, struct rtc_time *tm)
 {
@@ -48,8 +49,11 @@ unsigned long __init opal_get_boot_time(void)
 		else
 			mdelay(10);
 	}
-	if (rc != OPAL_SUCCESS)
+	if (rc != OPAL_SUCCESS) {
+		ppc_md.get_rtc_time = NULL;
+		ppc_md.set_rtc_time = NULL;
 		return 0;
+	}
 	y_m_d = be32_to_cpu(__y_m_d);
 	h_m_s_ms = be64_to_cpu(__h_m_s_ms);
 	opal_to_tm(y_m_d, h_m_s_ms, &tm);
-- 
cgit v1.2.3


From 75eb3d9b60c280a275099fbed06a890cee2d784b Mon Sep 17 00:00:00 2001
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Date: Fri, 15 Nov 2013 09:50:57 +0530
Subject: powerpc/powernv: Get FSP memory errors and plumb into memory poison
 infrastructure.

Get the memory errors reported by opal and plumb it into memory poison
infrastructure. This patch uses new messaging channel infrastructure to
pull the fsp memory errors to linux.

Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/opal.h                    |  52 ++++++++
 arch/powerpc/platforms/powernv/Makefile            |   1 +
 .../powerpc/platforms/powernv/opal-memory-errors.c | 146 +++++++++++++++++++++
 3 files changed, 199 insertions(+)
 create mode 100644 arch/powerpc/platforms/powernv/opal-memory-errors.c

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

diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 0a2ac85998d7..aded1b81bfd6 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -443,6 +443,58 @@ struct opal_machine_check_event {
 	} u;
 };
 
+/* FSP memory errors handling */
+enum OpalMemErr_Version {
+	OpalMemErr_V1 = 1,
+};
+
+enum OpalMemErrType {
+	OPAL_MEM_ERR_TYPE_RESILIENCE	= 0,
+	OPAL_MEM_ERR_TYPE_DYN_DALLOC,
+	OPAL_MEM_ERR_TYPE_SCRUB,
+};
+
+/* Memory Reilience error type */
+enum OpalMemErr_ResilErrType {
+	OPAL_MEM_RESILIENCE_CE		= 0,
+	OPAL_MEM_RESILIENCE_UE,
+	OPAL_MEM_RESILIENCE_UE_SCRUB,
+};
+
+/* Dynamic Memory Deallocation type */
+enum OpalMemErr_DynErrType {
+	OPAL_MEM_DYNAMIC_DEALLOC	= 0,
+};
+
+/* OpalMemoryErrorData->flags */
+#define OPAL_MEM_CORRECTED_ERROR	0x0001
+#define OPAL_MEM_THRESHOLD_EXCEEDED	0x0002
+#define OPAL_MEM_ACK_REQUIRED		0x8000
+
+struct OpalMemoryErrorData {
+	enum OpalMemErr_Version	version:8;	/* 0x00 */
+	enum OpalMemErrType	type:8;		/* 0x01 */
+	uint16_t		flags;		/* 0x02 */
+	uint8_t			reserved_1[4];	/* 0x04 */
+
+	union {
+		/* Memory Resilience corrected/uncorrected error info */
+		struct {
+			enum OpalMemErr_ResilErrType resil_err_type:8;
+			uint8_t		reserved_1[7];
+			uint64_t	physical_address_start;
+			uint64_t	physical_address_end;
+		} resilience;
+		/* Dynamic memory deallocation error info */
+		struct {
+			enum OpalMemErr_DynErrType dyn_err_type:8;
+			uint8_t		reserved_1[7];
+			uint64_t	physical_address_start;
+			uint64_t	physical_address_end;
+		} dyn_dealloc;
+	} u;
+};
+
 enum {
 	OPAL_P7IOC_DIAG_TYPE_NONE	= 0,
 	OPAL_P7IOC_DIAG_TYPE_RGC	= 1,
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index 873fa1370dc4..8d767fde5a6a 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -6,3 +6,4 @@ obj-$(CONFIG_SMP)	+= smp.o
 obj-$(CONFIG_PCI)	+= pci.o pci-p5ioc2.o pci-ioda.o
 obj-$(CONFIG_EEH)	+= eeh-ioda.o eeh-powernv.o
 obj-$(CONFIG_PPC_SCOM)	+= opal-xscom.o
+obj-$(CONFIG_MEMORY_FAILURE)	+= opal-memory-errors.o
diff --git a/arch/powerpc/platforms/powernv/opal-memory-errors.c b/arch/powerpc/platforms/powernv/opal-memory-errors.c
new file mode 100644
index 000000000000..ec4132239cdf
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-memory-errors.c
@@ -0,0 +1,146 @@
+/*
+ * OPAL asynchronus Memory error handling support in PowreNV.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright 2013 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#undef DEBUG
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+
+#include <asm/opal.h>
+#include <asm/cputable.h>
+
+static int opal_mem_err_nb_init;
+static LIST_HEAD(opal_memory_err_list);
+static DEFINE_SPINLOCK(opal_mem_err_lock);
+
+struct OpalMsgNode {
+	struct list_head list;
+	struct opal_msg msg;
+};
+
+static void handle_memory_error_event(struct OpalMemoryErrorData *merr_evt)
+{
+	uint64_t paddr_start, paddr_end;
+
+	pr_debug("%s: Retrived memory error event, type: 0x%x\n",
+		  __func__, merr_evt->type);
+	switch (merr_evt->type) {
+	case OPAL_MEM_ERR_TYPE_RESILIENCE:
+		paddr_start = merr_evt->u.resilience.physical_address_start;
+		paddr_end = merr_evt->u.resilience.physical_address_end;
+		break;
+	case OPAL_MEM_ERR_TYPE_DYN_DALLOC:
+		paddr_start = merr_evt->u.dyn_dealloc.physical_address_start;
+		paddr_end = merr_evt->u.dyn_dealloc.physical_address_end;
+		break;
+	default:
+		return;
+	}
+
+	for (; paddr_start < paddr_end; paddr_start += PAGE_SIZE) {
+		memory_failure(paddr_start >> PAGE_SHIFT, 0, 0);
+	}
+}
+
+static void handle_memory_error(void)
+{
+	unsigned long flags;
+	struct OpalMemoryErrorData *merr_evt;
+	struct OpalMsgNode *msg_node;
+
+	spin_lock_irqsave(&opal_mem_err_lock, flags);
+	while (!list_empty(&opal_memory_err_list)) {
+		 msg_node = list_entry(opal_memory_err_list.next,
+					   struct OpalMsgNode, list);
+		list_del(&msg_node->list);
+		spin_unlock_irqrestore(&opal_mem_err_lock, flags);
+
+		merr_evt = (struct OpalMemoryErrorData *)
+					&msg_node->msg.params[0];
+		handle_memory_error_event(merr_evt);
+		kfree(msg_node);
+		spin_lock_irqsave(&opal_mem_err_lock, flags);
+	}
+	spin_unlock_irqrestore(&opal_mem_err_lock, flags);
+}
+
+static void mem_error_handler(struct work_struct *work)
+{
+	handle_memory_error();
+}
+
+static DECLARE_WORK(mem_error_work, mem_error_handler);
+
+/*
+ * opal_memory_err_event - notifier handler that queues up the opal message
+ * to be preocessed later.
+ */
+static int opal_memory_err_event(struct notifier_block *nb,
+			  unsigned long msg_type, void *msg)
+{
+	unsigned long flags;
+	struct OpalMsgNode *msg_node;
+
+	if (msg_type != OPAL_MSG_MEM_ERR)
+		return 0;
+
+	msg_node = kzalloc(sizeof(*msg_node), GFP_ATOMIC);
+	if (!msg_node) {
+		pr_err("MEMORY_ERROR: out of memory, Opal message event not"
+		       "handled\n");
+		return -ENOMEM;
+	}
+	memcpy(&msg_node->msg, msg, sizeof(struct opal_msg));
+
+	spin_lock_irqsave(&opal_mem_err_lock, flags);
+	list_add(&msg_node->list, &opal_memory_err_list);
+	spin_unlock_irqrestore(&opal_mem_err_lock, flags);
+
+	schedule_work(&mem_error_work);
+	return 0;
+}
+
+static struct notifier_block opal_mem_err_nb = {
+	.notifier_call	= opal_memory_err_event,
+	.next		= NULL,
+	.priority	= 0,
+};
+
+static int __init opal_mem_err_init(void)
+{
+	int ret;
+
+	if (!opal_mem_err_nb_init) {
+		ret = opal_message_notifier_register(
+					OPAL_MSG_MEM_ERR, &opal_mem_err_nb);
+		if (ret) {
+			pr_err("%s: Can't register OPAL event notifier (%d)\n",
+			       __func__, ret);
+			return ret;
+		}
+		opal_mem_err_nb_init = 1;
+	}
+	return 0;
+}
+subsys_initcall(opal_mem_err_init);
-- 
cgit v1.2.3


From e589a4404fa06730355de204d3d136ed9bbc7dea Mon Sep 17 00:00:00 2001
From: Alistair Popple <alistair@popple.id.au>
Date: Mon, 9 Dec 2013 18:17:01 +1100
Subject: powerpc/iommu: Update constant names to reflect their hardcoded page
 size

The powerpc iommu uses a hardcoded page size of 4K. This patch changes
the name of the IOMMU_PAGE_* macros to reflect the hardcoded values. A
future patch will use the existing names to support dynamic page
sizes.

Signed-off-by: Alistair Popple <alistair@popple.id.au>
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/iommu.h       | 10 ++---
 arch/powerpc/kernel/dma-iommu.c        |  4 +-
 arch/powerpc/kernel/iommu.c            | 78 +++++++++++++++++-----------------
 arch/powerpc/kernel/vio.c              | 19 +++++----
 arch/powerpc/platforms/cell/iommu.c    | 12 +++---
 arch/powerpc/platforms/powernv/pci.c   |  4 +-
 arch/powerpc/platforms/pseries/iommu.c |  8 ++--
 arch/powerpc/platforms/pseries/setup.c |  4 +-
 arch/powerpc/platforms/wsp/wsp_pci.c   | 10 ++---
 drivers/net/ethernet/ibm/ibmveth.c     |  9 ++--
 drivers/vfio/vfio_iommu_spapr_tce.c    | 28 ++++++------
 11 files changed, 94 insertions(+), 92 deletions(-)

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

diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 774fa2776907..0869c7e74421 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -30,10 +30,10 @@
 #include <asm/machdep.h>
 #include <asm/types.h>
 
-#define IOMMU_PAGE_SHIFT      12
-#define IOMMU_PAGE_SIZE       (ASM_CONST(1) << IOMMU_PAGE_SHIFT)
-#define IOMMU_PAGE_MASK       (~((1 << IOMMU_PAGE_SHIFT) - 1))
-#define IOMMU_PAGE_ALIGN(addr) _ALIGN_UP(addr, IOMMU_PAGE_SIZE)
+#define IOMMU_PAGE_SHIFT_4K      12
+#define IOMMU_PAGE_SIZE_4K       (ASM_CONST(1) << IOMMU_PAGE_SHIFT_4K)
+#define IOMMU_PAGE_MASK_4K       (~((1 << IOMMU_PAGE_SHIFT_4K) - 1))
+#define IOMMU_PAGE_ALIGN_4K(addr) _ALIGN_UP(addr, IOMMU_PAGE_SIZE_4K)
 
 /* Boot time flags */
 extern int iommu_is_off;
@@ -42,7 +42,7 @@ extern int iommu_force_on;
 /* Pure 2^n version of get_order */
 static __inline__ __attribute_const__ int get_iommu_order(unsigned long size)
 {
-	return __ilog2((size - 1) >> IOMMU_PAGE_SHIFT) + 1;
+	return __ilog2((size - 1) >> IOMMU_PAGE_SHIFT_4K) + 1;
 }
 
 
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index e4897523de41..5cfe3dbfc4a0 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -83,10 +83,10 @@ static int dma_iommu_dma_supported(struct device *dev, u64 mask)
 		return 0;
 	}
 
-	if (tbl->it_offset > (mask >> IOMMU_PAGE_SHIFT)) {
+	if (tbl->it_offset > (mask >> IOMMU_PAGE_SHIFT_4K)) {
 		dev_info(dev, "Warning: IOMMU offset too big for device mask\n");
 		dev_info(dev, "mask: 0x%08llx, table offset: 0x%08lx\n",
-				mask, tbl->it_offset << IOMMU_PAGE_SHIFT);
+				mask, tbl->it_offset << IOMMU_PAGE_SHIFT_4K);
 		return 0;
 	} else
 		return 1;
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index d22abe0b08e3..df4a7f1b7444 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -251,14 +251,14 @@ again:
 
 	if (dev)
 		boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-				      1 << IOMMU_PAGE_SHIFT);
+				      1 << IOMMU_PAGE_SHIFT_4K);
 	else
-		boundary_size = ALIGN(1UL << 32, 1 << IOMMU_PAGE_SHIFT);
+		boundary_size = ALIGN(1UL << 32, 1 << IOMMU_PAGE_SHIFT_4K);
 	/* 4GB boundary for iseries_hv_alloc and iseries_hv_map */
 
 	n = iommu_area_alloc(tbl->it_map, limit, start, npages,
-			     tbl->it_offset, boundary_size >> IOMMU_PAGE_SHIFT,
-			     align_mask);
+			tbl->it_offset, boundary_size >> IOMMU_PAGE_SHIFT_4K,
+			align_mask);
 	if (n == -1) {
 		if (likely(pass == 0)) {
 			/* First try the pool from the start */
@@ -320,12 +320,12 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
 		return DMA_ERROR_CODE;
 
 	entry += tbl->it_offset;	/* Offset into real TCE table */
-	ret = entry << IOMMU_PAGE_SHIFT;	/* Set the return dma address */
+	ret = entry << IOMMU_PAGE_SHIFT_4K;	/* Set the return dma address */
 
 	/* Put the TCEs in the HW table */
 	build_fail = ppc_md.tce_build(tbl, entry, npages,
-	                              (unsigned long)page & IOMMU_PAGE_MASK,
-	                              direction, attrs);
+				(unsigned long)page & IOMMU_PAGE_MASK_4K,
+				direction, attrs);
 
 	/* ppc_md.tce_build() only returns non-zero for transient errors.
 	 * Clean up the table bitmap in this case and return
@@ -352,7 +352,7 @@ static bool iommu_free_check(struct iommu_table *tbl, dma_addr_t dma_addr,
 {
 	unsigned long entry, free_entry;
 
-	entry = dma_addr >> IOMMU_PAGE_SHIFT;
+	entry = dma_addr >> IOMMU_PAGE_SHIFT_4K;
 	free_entry = entry - tbl->it_offset;
 
 	if (((free_entry + npages) > tbl->it_size) ||
@@ -401,7 +401,7 @@ static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 	unsigned long flags;
 	struct iommu_pool *pool;
 
-	entry = dma_addr >> IOMMU_PAGE_SHIFT;
+	entry = dma_addr >> IOMMU_PAGE_SHIFT_4K;
 	free_entry = entry - tbl->it_offset;
 
 	pool = get_pool(tbl, free_entry);
@@ -468,13 +468,13 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 		}
 		/* Allocate iommu entries for that segment */
 		vaddr = (unsigned long) sg_virt(s);
-		npages = iommu_num_pages(vaddr, slen, IOMMU_PAGE_SIZE);
+		npages = iommu_num_pages(vaddr, slen, IOMMU_PAGE_SIZE_4K);
 		align = 0;
-		if (IOMMU_PAGE_SHIFT < PAGE_SHIFT && slen >= PAGE_SIZE &&
+		if (IOMMU_PAGE_SHIFT_4K < PAGE_SHIFT && slen >= PAGE_SIZE &&
 		    (vaddr & ~PAGE_MASK) == 0)
-			align = PAGE_SHIFT - IOMMU_PAGE_SHIFT;
+			align = PAGE_SHIFT - IOMMU_PAGE_SHIFT_4K;
 		entry = iommu_range_alloc(dev, tbl, npages, &handle,
-					  mask >> IOMMU_PAGE_SHIFT, align);
+					  mask >> IOMMU_PAGE_SHIFT_4K, align);
 
 		DBG("  - vaddr: %lx, size: %lx\n", vaddr, slen);
 
@@ -489,16 +489,16 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 
 		/* Convert entry to a dma_addr_t */
 		entry += tbl->it_offset;
-		dma_addr = entry << IOMMU_PAGE_SHIFT;
-		dma_addr |= (s->offset & ~IOMMU_PAGE_MASK);
+		dma_addr = entry << IOMMU_PAGE_SHIFT_4K;
+		dma_addr |= (s->offset & ~IOMMU_PAGE_MASK_4K);
 
 		DBG("  - %lu pages, entry: %lx, dma_addr: %lx\n",
 			    npages, entry, dma_addr);
 
 		/* Insert into HW table */
 		build_fail = ppc_md.tce_build(tbl, entry, npages,
-		                              vaddr & IOMMU_PAGE_MASK,
-		                              direction, attrs);
+					vaddr & IOMMU_PAGE_MASK_4K,
+					direction, attrs);
 		if(unlikely(build_fail))
 			goto failure;
 
@@ -559,9 +559,9 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 		if (s->dma_length != 0) {
 			unsigned long vaddr, npages;
 
-			vaddr = s->dma_address & IOMMU_PAGE_MASK;
+			vaddr = s->dma_address & IOMMU_PAGE_MASK_4K;
 			npages = iommu_num_pages(s->dma_address, s->dma_length,
-						 IOMMU_PAGE_SIZE);
+						 IOMMU_PAGE_SIZE_4K);
 			__iommu_free(tbl, vaddr, npages);
 			s->dma_address = DMA_ERROR_CODE;
 			s->dma_length = 0;
@@ -592,7 +592,7 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 		if (sg->dma_length == 0)
 			break;
 		npages = iommu_num_pages(dma_handle, sg->dma_length,
-					 IOMMU_PAGE_SIZE);
+					 IOMMU_PAGE_SIZE_4K);
 		__iommu_free(tbl, dma_handle, npages);
 		sg = sg_next(sg);
 	}
@@ -676,7 +676,7 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
 		set_bit(0, tbl->it_map);
 
 	/* We only split the IOMMU table if we have 1GB or more of space */
-	if ((tbl->it_size << IOMMU_PAGE_SHIFT) >= (1UL * 1024 * 1024 * 1024))
+	if ((tbl->it_size << IOMMU_PAGE_SHIFT_4K) >= (1UL * 1024 * 1024 * 1024))
 		tbl->nr_pools = IOMMU_NR_POOLS;
 	else
 		tbl->nr_pools = 1;
@@ -768,16 +768,16 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl,
 
 	vaddr = page_address(page) + offset;
 	uaddr = (unsigned long)vaddr;
-	npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE);
+	npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE_4K);
 
 	if (tbl) {
 		align = 0;
-		if (IOMMU_PAGE_SHIFT < PAGE_SHIFT && size >= PAGE_SIZE &&
+		if (IOMMU_PAGE_SHIFT_4K < PAGE_SHIFT && size >= PAGE_SIZE &&
 		    ((unsigned long)vaddr & ~PAGE_MASK) == 0)
-			align = PAGE_SHIFT - IOMMU_PAGE_SHIFT;
+			align = PAGE_SHIFT - IOMMU_PAGE_SHIFT_4K;
 
 		dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction,
-					 mask >> IOMMU_PAGE_SHIFT, align,
+					 mask >> IOMMU_PAGE_SHIFT_4K, align,
 					 attrs);
 		if (dma_handle == DMA_ERROR_CODE) {
 			if (printk_ratelimit())  {
@@ -786,7 +786,7 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl,
 					 npages);
 			}
 		} else
-			dma_handle |= (uaddr & ~IOMMU_PAGE_MASK);
+			dma_handle |= (uaddr & ~IOMMU_PAGE_MASK_4K);
 	}
 
 	return dma_handle;
@@ -801,7 +801,7 @@ void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle,
 	BUG_ON(direction == DMA_NONE);
 
 	if (tbl) {
-		npages = iommu_num_pages(dma_handle, size, IOMMU_PAGE_SIZE);
+		npages = iommu_num_pages(dma_handle, size, IOMMU_PAGE_SIZE_4K);
 		iommu_free(tbl, dma_handle, npages);
 	}
 }
@@ -845,10 +845,10 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 	memset(ret, 0, size);
 
 	/* Set up tces to cover the allocated range */
-	nio_pages = size >> IOMMU_PAGE_SHIFT;
+	nio_pages = size >> IOMMU_PAGE_SHIFT_4K;
 	io_order = get_iommu_order(size);
 	mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL,
-			      mask >> IOMMU_PAGE_SHIFT, io_order, NULL);
+			      mask >> IOMMU_PAGE_SHIFT_4K, io_order, NULL);
 	if (mapping == DMA_ERROR_CODE) {
 		free_pages((unsigned long)ret, order);
 		return NULL;
@@ -864,7 +864,7 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size,
 		unsigned int nio_pages;
 
 		size = PAGE_ALIGN(size);
-		nio_pages = size >> IOMMU_PAGE_SHIFT;
+		nio_pages = size >> IOMMU_PAGE_SHIFT_4K;
 		iommu_free(tbl, dma_handle, nio_pages);
 		size = PAGE_ALIGN(size);
 		free_pages((unsigned long)vaddr, get_order(size));
@@ -935,10 +935,10 @@ int iommu_tce_clear_param_check(struct iommu_table *tbl,
 	if (tce_value)
 		return -EINVAL;
 
-	if (ioba & ~IOMMU_PAGE_MASK)
+	if (ioba & ~IOMMU_PAGE_MASK_4K)
 		return -EINVAL;
 
-	ioba >>= IOMMU_PAGE_SHIFT;
+	ioba >>= IOMMU_PAGE_SHIFT_4K;
 	if (ioba < tbl->it_offset)
 		return -EINVAL;
 
@@ -955,13 +955,13 @@ int iommu_tce_put_param_check(struct iommu_table *tbl,
 	if (!(tce & (TCE_PCI_WRITE | TCE_PCI_READ)))
 		return -EINVAL;
 
-	if (tce & ~(IOMMU_PAGE_MASK | TCE_PCI_WRITE | TCE_PCI_READ))
+	if (tce & ~(IOMMU_PAGE_MASK_4K | TCE_PCI_WRITE | TCE_PCI_READ))
 		return -EINVAL;
 
-	if (ioba & ~IOMMU_PAGE_MASK)
+	if (ioba & ~IOMMU_PAGE_MASK_4K)
 		return -EINVAL;
 
-	ioba >>= IOMMU_PAGE_SHIFT;
+	ioba >>= IOMMU_PAGE_SHIFT_4K;
 	if (ioba < tbl->it_offset)
 		return -EINVAL;
 
@@ -1037,7 +1037,7 @@ int iommu_tce_build(struct iommu_table *tbl, unsigned long entry,
 
 	/* if (unlikely(ret))
 		pr_err("iommu_tce: %s failed on hwaddr=%lx ioba=%lx kva=%lx ret=%d\n",
-				__func__, hwaddr, entry << IOMMU_PAGE_SHIFT,
+				__func__, hwaddr, entry << IOMMU_PAGE_SHIFT_4K,
 				hwaddr, ret); */
 
 	return ret;
@@ -1049,14 +1049,14 @@ int iommu_put_tce_user_mode(struct iommu_table *tbl, unsigned long entry,
 {
 	int ret;
 	struct page *page = NULL;
-	unsigned long hwaddr, offset = tce & IOMMU_PAGE_MASK & ~PAGE_MASK;
+	unsigned long hwaddr, offset = tce & IOMMU_PAGE_MASK_4K & ~PAGE_MASK;
 	enum dma_data_direction direction = iommu_tce_direction(tce);
 
 	ret = get_user_pages_fast(tce & PAGE_MASK, 1,
 			direction != DMA_TO_DEVICE, &page);
 	if (unlikely(ret != 1)) {
 		/* pr_err("iommu_tce: get_user_pages_fast failed tce=%lx ioba=%lx ret=%d\n",
-				tce, entry << IOMMU_PAGE_SHIFT, ret); */
+				tce, entry << IOMMU_PAGE_SHIFT_4K, ret); */
 		return -EFAULT;
 	}
 	hwaddr = (unsigned long) page_address(page) + offset;
@@ -1067,7 +1067,7 @@ int iommu_put_tce_user_mode(struct iommu_table *tbl, unsigned long entry,
 
 	if (ret < 0)
 		pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%d\n",
-				__func__, entry << IOMMU_PAGE_SHIFT, tce, ret);
+			__func__, entry << IOMMU_PAGE_SHIFT_4K, tce, ret);
 
 	return ret;
 }
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index 76a64821f4a2..2e89fa350763 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -520,14 +520,14 @@ static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page,
 	struct vio_dev *viodev = to_vio_dev(dev);
 	dma_addr_t ret = DMA_ERROR_CODE;
 
-	if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE))) {
+	if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE_4K))) {
 		atomic_inc(&viodev->cmo.allocs_failed);
 		return ret;
 	}
 
 	ret = dma_iommu_ops.map_page(dev, page, offset, size, direction, attrs);
 	if (unlikely(dma_mapping_error(dev, ret))) {
-		vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE));
+		vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE_4K));
 		atomic_inc(&viodev->cmo.allocs_failed);
 	}
 
@@ -543,7 +543,7 @@ static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
 
 	dma_iommu_ops.unmap_page(dev, dma_handle, size, direction, attrs);
 
-	vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE));
+	vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE_4K));
 }
 
 static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
@@ -556,7 +556,7 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
 	size_t alloc_size = 0;
 
 	for (sgl = sglist; count < nelems; count++, sgl++)
-		alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE);
+		alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE_4K);
 
 	if (vio_cmo_alloc(viodev, alloc_size)) {
 		atomic_inc(&viodev->cmo.allocs_failed);
@@ -572,7 +572,7 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
 	}
 
 	for (sgl = sglist, count = 0; count < ret; count++, sgl++)
-		alloc_size -= roundup(sgl->dma_length, IOMMU_PAGE_SIZE);
+		alloc_size -= roundup(sgl->dma_length, IOMMU_PAGE_SIZE_4K);
 	if (alloc_size)
 		vio_cmo_dealloc(viodev, alloc_size);
 
@@ -590,7 +590,7 @@ static void vio_dma_iommu_unmap_sg(struct device *dev,
 	int count = 0;
 
 	for (sgl = sglist; count < nelems; count++, sgl++)
-		alloc_size += roundup(sgl->dma_length, IOMMU_PAGE_SIZE);
+		alloc_size += roundup(sgl->dma_length, IOMMU_PAGE_SIZE_4K);
 
 	dma_iommu_ops.unmap_sg(dev, sglist, nelems, direction, attrs);
 
@@ -736,7 +736,8 @@ static int vio_cmo_bus_probe(struct vio_dev *viodev)
 			return -EINVAL;
 		}
 
-		viodev->cmo.desired = IOMMU_PAGE_ALIGN(viodrv->get_desired_dma(viodev));
+		viodev->cmo.desired =
+			IOMMU_PAGE_ALIGN_4K(viodrv->get_desired_dma(viodev));
 		if (viodev->cmo.desired < VIO_CMO_MIN_ENT)
 			viodev->cmo.desired = VIO_CMO_MIN_ENT;
 		size = VIO_CMO_MIN_ENT;
@@ -1176,9 +1177,9 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev)
 			    &tbl->it_index, &offset, &size);
 
 	/* TCE table size - measured in tce entries */
-	tbl->it_size = size >> IOMMU_PAGE_SHIFT;
+	tbl->it_size = size >> IOMMU_PAGE_SHIFT_4K;
 	/* offset for VIO should always be 0 */
-	tbl->it_offset = offset >> IOMMU_PAGE_SHIFT;
+	tbl->it_offset = offset >> IOMMU_PAGE_SHIFT_4K;
 	tbl->it_busno = 0;
 	tbl->it_type = TCE_VB;
 	tbl->it_blocksize = 16;
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index b53560660b72..fc61b908eaf0 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -197,7 +197,7 @@ static int tce_build_cell(struct iommu_table *tbl, long index, long npages,
 
 	io_pte = (unsigned long *)tbl->it_base + (index - tbl->it_offset);
 
-	for (i = 0; i < npages; i++, uaddr += IOMMU_PAGE_SIZE)
+	for (i = 0; i < npages; i++, uaddr += IOMMU_PAGE_SIZE_4K)
 		io_pte[i] = base_pte | (__pa(uaddr) & CBE_IOPTE_RPN_Mask);
 
 	mb();
@@ -430,7 +430,7 @@ static void cell_iommu_setup_hardware(struct cbe_iommu *iommu,
 {
 	cell_iommu_setup_stab(iommu, base, size, 0, 0);
 	iommu->ptab = cell_iommu_alloc_ptab(iommu, base, size, 0, 0,
-					    IOMMU_PAGE_SHIFT);
+					    IOMMU_PAGE_SHIFT_4K);
 	cell_iommu_enable_hardware(iommu);
 }
 
@@ -487,8 +487,8 @@ cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np,
 	window->table.it_blocksize = 16;
 	window->table.it_base = (unsigned long)iommu->ptab;
 	window->table.it_index = iommu->nid;
-	window->table.it_offset = (offset >> IOMMU_PAGE_SHIFT) + pte_offset;
-	window->table.it_size = size >> IOMMU_PAGE_SHIFT;
+	window->table.it_offset = (offset >> IOMMU_PAGE_SHIFT_4K) + pte_offset;
+	window->table.it_size = size >> IOMMU_PAGE_SHIFT_4K;
 
 	iommu_init_table(&window->table, iommu->nid);
 
@@ -773,7 +773,7 @@ static void __init cell_iommu_init_one(struct device_node *np,
 
 	/* Setup the iommu_table */
 	cell_iommu_setup_window(iommu, np, base, size,
-				offset >> IOMMU_PAGE_SHIFT);
+				offset >> IOMMU_PAGE_SHIFT_4K);
 }
 
 static void __init cell_disable_iommus(void)
@@ -1122,7 +1122,7 @@ static int __init cell_iommu_fixed_mapping_init(void)
 
 		cell_iommu_setup_stab(iommu, dbase, dsize, fbase, fsize);
 		iommu->ptab = cell_iommu_alloc_ptab(iommu, dbase, dsize, 0, 0,
-						    IOMMU_PAGE_SHIFT);
+						    IOMMU_PAGE_SHIFT_4K);
 		cell_iommu_setup_fixed_ptab(iommu, np, dbase, dsize,
 					     fbase, fsize);
 		cell_iommu_enable_hardware(iommu);
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index bac289aac7cc..7f4d857668a9 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -564,7 +564,7 @@ void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
 {
 	tbl->it_blocksize = 16;
 	tbl->it_base = (unsigned long)tce_mem;
-	tbl->it_offset = dma_offset >> IOMMU_PAGE_SHIFT;
+	tbl->it_offset = dma_offset >> IOMMU_PAGE_SHIFT_4K;
 	tbl->it_index = 0;
 	tbl->it_size = tce_size >> 3;
 	tbl->it_busno = 0;
@@ -761,7 +761,7 @@ static struct notifier_block tce_iommu_bus_nb = {
 
 static int __init tce_iommu_bus_notifier_init(void)
 {
-	BUILD_BUG_ON(PAGE_SIZE < IOMMU_PAGE_SIZE);
+	BUILD_BUG_ON(PAGE_SIZE < IOMMU_PAGE_SIZE_4K);
 
 	bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb);
 	return 0;
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index a80af6c20cba..1b7531ce0c0c 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -488,7 +488,7 @@ static void iommu_table_setparms(struct pci_controller *phb,
 	tbl->it_busno = phb->bus->number;
 
 	/* Units of tce entries */
-	tbl->it_offset = phb->dma_window_base_cur >> IOMMU_PAGE_SHIFT;
+	tbl->it_offset = phb->dma_window_base_cur >> IOMMU_PAGE_SHIFT_4K;
 
 	/* Test if we are going over 2GB of DMA space */
 	if (phb->dma_window_base_cur + phb->dma_window_size > 0x80000000ul) {
@@ -499,7 +499,7 @@ static void iommu_table_setparms(struct pci_controller *phb,
 	phb->dma_window_base_cur += phb->dma_window_size;
 
 	/* Set the tce table size - measured in entries */
-	tbl->it_size = phb->dma_window_size >> IOMMU_PAGE_SHIFT;
+	tbl->it_size = phb->dma_window_size >> IOMMU_PAGE_SHIFT_4K;
 
 	tbl->it_index = 0;
 	tbl->it_blocksize = 16;
@@ -540,8 +540,8 @@ static void iommu_table_setparms_lpar(struct pci_controller *phb,
 	tbl->it_base   = 0;
 	tbl->it_blocksize  = 16;
 	tbl->it_type = TCE_PCI;
-	tbl->it_offset = offset >> IOMMU_PAGE_SHIFT;
-	tbl->it_size = size >> IOMMU_PAGE_SHIFT;
+	tbl->it_offset = offset >> IOMMU_PAGE_SHIFT_4K;
+	tbl->it_size = size >> IOMMU_PAGE_SHIFT_4K;
 }
 
 static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index c1f190858701..49cd16e6b450 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -72,7 +72,7 @@
 
 int CMO_PrPSP = -1;
 int CMO_SecPSP = -1;
-unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT);
+unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT_4K);
 EXPORT_SYMBOL(CMO_PageSize);
 
 int fwnmi_active;  /* TRUE if an FWNMI handler is present */
@@ -569,7 +569,7 @@ void pSeries_cmo_feature_init(void)
 {
 	char *ptr, *key, *value, *end;
 	int call_status;
-	int page_order = IOMMU_PAGE_SHIFT;
+	int page_order = IOMMU_PAGE_SHIFT_4K;
 
 	pr_debug(" -> fw_cmo_feature_init()\n");
 	spin_lock(&rtas_data_buf_lock);
diff --git a/arch/powerpc/platforms/wsp/wsp_pci.c b/arch/powerpc/platforms/wsp/wsp_pci.c
index 62cb527493e7..8a589618551e 100644
--- a/arch/powerpc/platforms/wsp/wsp_pci.c
+++ b/arch/powerpc/platforms/wsp/wsp_pci.c
@@ -260,7 +260,7 @@ static int tce_build_wsp(struct iommu_table *tbl, long index, long npages,
 		*tcep = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
 
 		dma_debug("[DMA] TCE %p set to 0x%016llx (dma addr: 0x%lx)\n",
-			  tcep, *tcep, (tbl->it_offset + index) << IOMMU_PAGE_SHIFT);
+			  tcep, *tcep, (tbl->it_offset + index) << IOMMU_PAGE_SHIFT_4K);
 
 		uaddr += TCE_PAGE_SIZE;
 		index++;
@@ -381,8 +381,8 @@ static struct wsp_dma_table *wsp_pci_create_dma32_table(struct wsp_phb *phb,
 
 	/* Init bits and pieces */
 	tbl->table.it_blocksize = 16;
-	tbl->table.it_offset = addr >> IOMMU_PAGE_SHIFT;
-	tbl->table.it_size = size >> IOMMU_PAGE_SHIFT;
+	tbl->table.it_offset = addr >> IOMMU_PAGE_SHIFT_4K;
+	tbl->table.it_size = size >> IOMMU_PAGE_SHIFT_4K;
 
 	/*
 	 * It's already blank but we clear it anyway.
@@ -449,8 +449,8 @@ static void wsp_pci_dma_dev_setup(struct pci_dev *pdev)
 	if (table) {
 		pr_info("%s: Setup iommu: 32-bit DMA region 0x%08lx..0x%08lx\n",
 			pci_name(pdev),
-			table->table.it_offset << IOMMU_PAGE_SHIFT,
-			(table->table.it_offset << IOMMU_PAGE_SHIFT)
+			table->table.it_offset << IOMMU_PAGE_SHIFT_4K,
+			(table->table.it_offset << IOMMU_PAGE_SHIFT_4K)
 			+ phb->dma32_region_size - 1);
 		archdata->dma_data.iommu_table_base = &table->table;
 		return;
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index 952d795230a4..f7d7538b6bd9 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1282,24 +1282,25 @@ static unsigned long ibmveth_get_desired_dma(struct vio_dev *vdev)
 
 	/* netdev inits at probe time along with the structures we need below*/
 	if (netdev == NULL)
-		return IOMMU_PAGE_ALIGN(IBMVETH_IO_ENTITLEMENT_DEFAULT);
+		return IOMMU_PAGE_ALIGN_4K(IBMVETH_IO_ENTITLEMENT_DEFAULT);
 
 	adapter = netdev_priv(netdev);
 
 	ret = IBMVETH_BUFF_LIST_SIZE + IBMVETH_FILT_LIST_SIZE;
-	ret += IOMMU_PAGE_ALIGN(netdev->mtu);
+	ret += IOMMU_PAGE_ALIGN_4K(netdev->mtu);
 
 	for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) {
 		/* add the size of the active receive buffers */
 		if (adapter->rx_buff_pool[i].active)
 			ret +=
 			    adapter->rx_buff_pool[i].size *
-			    IOMMU_PAGE_ALIGN(adapter->rx_buff_pool[i].
+			    IOMMU_PAGE_ALIGN_4K(adapter->rx_buff_pool[i].
 			            buff_size);
 		rxqentries += adapter->rx_buff_pool[i].size;
 	}
 	/* add the size of the receive queue entries */
-	ret += IOMMU_PAGE_ALIGN(rxqentries * sizeof(struct ibmveth_rx_q_entry));
+	ret += IOMMU_PAGE_ALIGN_4K(
+		rxqentries * sizeof(struct ibmveth_rx_q_entry));
 
 	return ret;
 }
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index bdae7a04af75..a84788ba662c 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -81,7 +81,7 @@ static int tce_iommu_enable(struct tce_container *container)
 	 * enforcing the limit based on the max that the guest can map.
 	 */
 	down_write(&current->mm->mmap_sem);
-	npages = (tbl->it_size << IOMMU_PAGE_SHIFT) >> PAGE_SHIFT;
+	npages = (tbl->it_size << IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT;
 	locked = current->mm->locked_vm + npages;
 	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
 	if (locked > lock_limit && !capable(CAP_IPC_LOCK)) {
@@ -110,7 +110,7 @@ static void tce_iommu_disable(struct tce_container *container)
 
 	down_write(&current->mm->mmap_sem);
 	current->mm->locked_vm -= (container->tbl->it_size <<
-			IOMMU_PAGE_SHIFT) >> PAGE_SHIFT;
+			IOMMU_PAGE_SHIFT_4K) >> PAGE_SHIFT;
 	up_write(&current->mm->mmap_sem);
 }
 
@@ -174,8 +174,8 @@ static long tce_iommu_ioctl(void *iommu_data,
 		if (info.argsz < minsz)
 			return -EINVAL;
 
-		info.dma32_window_start = tbl->it_offset << IOMMU_PAGE_SHIFT;
-		info.dma32_window_size = tbl->it_size << IOMMU_PAGE_SHIFT;
+		info.dma32_window_start = tbl->it_offset << IOMMU_PAGE_SHIFT_4K;
+		info.dma32_window_size = tbl->it_size << IOMMU_PAGE_SHIFT_4K;
 		info.flags = 0;
 
 		if (copy_to_user((void __user *)arg, &info, minsz))
@@ -205,8 +205,8 @@ static long tce_iommu_ioctl(void *iommu_data,
 				VFIO_DMA_MAP_FLAG_WRITE))
 			return -EINVAL;
 
-		if ((param.size & ~IOMMU_PAGE_MASK) ||
-				(param.vaddr & ~IOMMU_PAGE_MASK))
+		if ((param.size & ~IOMMU_PAGE_MASK_4K) ||
+				(param.vaddr & ~IOMMU_PAGE_MASK_4K))
 			return -EINVAL;
 
 		/* iova is checked by the IOMMU API */
@@ -220,17 +220,17 @@ static long tce_iommu_ioctl(void *iommu_data,
 		if (ret)
 			return ret;
 
-		for (i = 0; i < (param.size >> IOMMU_PAGE_SHIFT); ++i) {
+		for (i = 0; i < (param.size >> IOMMU_PAGE_SHIFT_4K); ++i) {
 			ret = iommu_put_tce_user_mode(tbl,
-					(param.iova >> IOMMU_PAGE_SHIFT) + i,
+					(param.iova >> IOMMU_PAGE_SHIFT_4K) + i,
 					tce);
 			if (ret)
 				break;
-			tce += IOMMU_PAGE_SIZE;
+			tce += IOMMU_PAGE_SIZE_4K;
 		}
 		if (ret)
 			iommu_clear_tces_and_put_pages(tbl,
-					param.iova >> IOMMU_PAGE_SHIFT,	i);
+					param.iova >> IOMMU_PAGE_SHIFT_4K, i);
 
 		iommu_flush_tce(tbl);
 
@@ -256,17 +256,17 @@ static long tce_iommu_ioctl(void *iommu_data,
 		if (param.flags)
 			return -EINVAL;
 
-		if (param.size & ~IOMMU_PAGE_MASK)
+		if (param.size & ~IOMMU_PAGE_MASK_4K)
 			return -EINVAL;
 
 		ret = iommu_tce_clear_param_check(tbl, param.iova, 0,
-				param.size >> IOMMU_PAGE_SHIFT);
+				param.size >> IOMMU_PAGE_SHIFT_4K);
 		if (ret)
 			return ret;
 
 		ret = iommu_clear_tces_and_put_pages(tbl,
-				param.iova >> IOMMU_PAGE_SHIFT,
-				param.size >> IOMMU_PAGE_SHIFT);
+				param.iova >> IOMMU_PAGE_SHIFT_4K,
+				param.size >> IOMMU_PAGE_SHIFT_4K);
 		iommu_flush_tce(tbl);
 
 		return ret;
-- 
cgit v1.2.3


From 3a553170d35d69bea3877bffa508489dfa6f133d Mon Sep 17 00:00:00 2001
From: Alistair Popple <alistair@popple.id.au>
Date: Mon, 9 Dec 2013 18:17:02 +1100
Subject: powerpc/iommu: Add it_page_shift field to determine iommu page size

This patch adds a it_page_shift field to struct iommu_table and
initiliases it to 4K for all platforms.

Signed-off-by: Alistair Popple <alistair@popple.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/iommu.h       |  1 +
 arch/powerpc/kernel/vio.c              |  5 +++--
 arch/powerpc/platforms/cell/iommu.c    |  8 +++++---
 arch/powerpc/platforms/pasemi/iommu.c  |  5 ++++-
 arch/powerpc/platforms/powernv/pci.c   |  3 ++-
 arch/powerpc/platforms/pseries/iommu.c | 10 ++++++----
 arch/powerpc/platforms/wsp/wsp_pci.c   |  5 +++--
 7 files changed, 24 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 0869c7e74421..7c928342f3f5 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -76,6 +76,7 @@ struct iommu_table {
 	struct iommu_pool large_pool;
 	struct iommu_pool pools[IOMMU_NR_POOLS];
 	unsigned long *it_map;       /* A simple allocation bitmap for now */
+	unsigned long  it_page_shift;/* table iommu page size */
 #ifdef CONFIG_IOMMU_API
 	struct iommu_group *it_group;
 #endif
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index 2e89fa350763..170ac24a0106 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -1177,9 +1177,10 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev)
 			    &tbl->it_index, &offset, &size);
 
 	/* TCE table size - measured in tce entries */
-	tbl->it_size = size >> IOMMU_PAGE_SHIFT_4K;
+	tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K;
+	tbl->it_size = size >> tbl->it_page_shift;
 	/* offset for VIO should always be 0 */
-	tbl->it_offset = offset >> IOMMU_PAGE_SHIFT_4K;
+	tbl->it_offset = offset >> tbl->it_page_shift;
 	tbl->it_busno = 0;
 	tbl->it_type = TCE_VB;
 	tbl->it_blocksize = 16;
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index fc61b908eaf0..2b90ff8a93be 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -197,7 +197,7 @@ static int tce_build_cell(struct iommu_table *tbl, long index, long npages,
 
 	io_pte = (unsigned long *)tbl->it_base + (index - tbl->it_offset);
 
-	for (i = 0; i < npages; i++, uaddr += IOMMU_PAGE_SIZE_4K)
+	for (i = 0; i < npages; i++, uaddr += tbl->it_page_shift)
 		io_pte[i] = base_pte | (__pa(uaddr) & CBE_IOPTE_RPN_Mask);
 
 	mb();
@@ -487,8 +487,10 @@ cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np,
 	window->table.it_blocksize = 16;
 	window->table.it_base = (unsigned long)iommu->ptab;
 	window->table.it_index = iommu->nid;
-	window->table.it_offset = (offset >> IOMMU_PAGE_SHIFT_4K) + pte_offset;
-	window->table.it_size = size >> IOMMU_PAGE_SHIFT_4K;
+	window->table.it_page_shift = IOMMU_PAGE_SHIFT_4K;
+	window->table.it_offset =
+		(offset >> window->table.it_page_shift) + pte_offset;
+	window->table.it_size = size >> window->table.it_page_shift;
 
 	iommu_init_table(&window->table, iommu->nid);
 
diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c
index 7d2d036754b5..2e576f2ae442 100644
--- a/arch/powerpc/platforms/pasemi/iommu.c
+++ b/arch/powerpc/platforms/pasemi/iommu.c
@@ -138,8 +138,11 @@ static void iommu_table_iobmap_setup(void)
 	pr_debug(" -> %s\n", __func__);
 	iommu_table_iobmap.it_busno = 0;
 	iommu_table_iobmap.it_offset = 0;
+	iommu_table_iobmap.it_page_shift = IOBMAP_PAGE_SHIFT;
+
 	/* it_size is in number of entries */
-	iommu_table_iobmap.it_size = 0x80000000 >> IOBMAP_PAGE_SHIFT;
+	iommu_table_iobmap.it_size =
+		0x80000000 >> iommu_table_iobmap.it_page_shift;
 
 	/* Initialize the common IOMMU code */
 	iommu_table_iobmap.it_base = (unsigned long)iob_l2_base;
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 7f4d857668a9..569b46423a93 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -564,7 +564,8 @@ void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
 {
 	tbl->it_blocksize = 16;
 	tbl->it_base = (unsigned long)tce_mem;
-	tbl->it_offset = dma_offset >> IOMMU_PAGE_SHIFT_4K;
+	tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K;
+	tbl->it_offset = dma_offset >> tbl->it_page_shift;
 	tbl->it_index = 0;
 	tbl->it_size = tce_size >> 3;
 	tbl->it_busno = 0;
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 1b7531ce0c0c..e0299183ae54 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -486,9 +486,10 @@ static void iommu_table_setparms(struct pci_controller *phb,
 		memset((void *)tbl->it_base, 0, *sizep);
 
 	tbl->it_busno = phb->bus->number;
+	tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K;
 
 	/* Units of tce entries */
-	tbl->it_offset = phb->dma_window_base_cur >> IOMMU_PAGE_SHIFT_4K;
+	tbl->it_offset = phb->dma_window_base_cur >> tbl->it_page_shift;
 
 	/* Test if we are going over 2GB of DMA space */
 	if (phb->dma_window_base_cur + phb->dma_window_size > 0x80000000ul) {
@@ -499,7 +500,7 @@ static void iommu_table_setparms(struct pci_controller *phb,
 	phb->dma_window_base_cur += phb->dma_window_size;
 
 	/* Set the tce table size - measured in entries */
-	tbl->it_size = phb->dma_window_size >> IOMMU_PAGE_SHIFT_4K;
+	tbl->it_size = phb->dma_window_size >> tbl->it_page_shift;
 
 	tbl->it_index = 0;
 	tbl->it_blocksize = 16;
@@ -537,11 +538,12 @@ static void iommu_table_setparms_lpar(struct pci_controller *phb,
 	of_parse_dma_window(dn, dma_window, &tbl->it_index, &offset, &size);
 
 	tbl->it_busno = phb->bus->number;
+	tbl->it_page_shift = IOMMU_PAGE_SHIFT_4K;
 	tbl->it_base   = 0;
 	tbl->it_blocksize  = 16;
 	tbl->it_type = TCE_PCI;
-	tbl->it_offset = offset >> IOMMU_PAGE_SHIFT_4K;
-	tbl->it_size = size >> IOMMU_PAGE_SHIFT_4K;
+	tbl->it_offset = offset >> tbl->it_page_shift;
+	tbl->it_size = size >> tbl->it_page_shift;
 }
 
 static void pci_dma_bus_setup_pSeries(struct pci_bus *bus)
diff --git a/arch/powerpc/platforms/wsp/wsp_pci.c b/arch/powerpc/platforms/wsp/wsp_pci.c
index 8a589618551e..9a15e5b39bb8 100644
--- a/arch/powerpc/platforms/wsp/wsp_pci.c
+++ b/arch/powerpc/platforms/wsp/wsp_pci.c
@@ -381,8 +381,9 @@ static struct wsp_dma_table *wsp_pci_create_dma32_table(struct wsp_phb *phb,
 
 	/* Init bits and pieces */
 	tbl->table.it_blocksize = 16;
-	tbl->table.it_offset = addr >> IOMMU_PAGE_SHIFT_4K;
-	tbl->table.it_size = size >> IOMMU_PAGE_SHIFT_4K;
+	tbl->table.it_page_shift = IOMMU_PAGE_SHIFT_4K;
+	tbl->table.it_offset = addr >> tbl->table.it_page_shift;
+	tbl->table.it_size = size >> tbl->table.it_page_shift;
 
 	/*
 	 * It's already blank but we clear it anyway.
-- 
cgit v1.2.3


From d084775738b746648d4102337163a04534a02982 Mon Sep 17 00:00:00 2001
From: Alistair Popple <alistair@popple.id.au>
Date: Mon, 9 Dec 2013 18:17:03 +1100
Subject: powerpc/iommu: Update the generic code to use dynamic iommu page
 sizes

This patch updates the generic iommu backend code to use the
it_page_shift field to determine the iommu page size instead of
using hardcoded values.

Signed-off-by: Alistair Popple <alistair@popple.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/iommu.h     | 19 +++++---
 arch/powerpc/kernel/dma-iommu.c      |  4 +-
 arch/powerpc/kernel/iommu.c          | 88 +++++++++++++++++++-----------------
 arch/powerpc/kernel/vio.c            | 25 +++++++---
 arch/powerpc/platforms/powernv/pci.c |  2 -
 drivers/net/ethernet/ibm/ibmveth.c   | 15 +++---
 6 files changed, 88 insertions(+), 65 deletions(-)

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

diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 7c928342f3f5..f7a8036579b5 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -35,17 +35,14 @@
 #define IOMMU_PAGE_MASK_4K       (~((1 << IOMMU_PAGE_SHIFT_4K) - 1))
 #define IOMMU_PAGE_ALIGN_4K(addr) _ALIGN_UP(addr, IOMMU_PAGE_SIZE_4K)
 
+#define IOMMU_PAGE_SIZE(tblptr) (ASM_CONST(1) << (tblptr)->it_page_shift)
+#define IOMMU_PAGE_MASK(tblptr) (~((1 << (tblptr)->it_page_shift) - 1))
+#define IOMMU_PAGE_ALIGN(addr, tblptr) _ALIGN_UP(addr, IOMMU_PAGE_SIZE(tblptr))
+
 /* Boot time flags */
 extern int iommu_is_off;
 extern int iommu_force_on;
 
-/* Pure 2^n version of get_order */
-static __inline__ __attribute_const__ int get_iommu_order(unsigned long size)
-{
-	return __ilog2((size - 1) >> IOMMU_PAGE_SHIFT_4K) + 1;
-}
-
-
 /*
  * IOMAP_MAX_ORDER defines the largest contiguous block
  * of dma space we can get.  IOMAP_MAX_ORDER = 13
@@ -82,6 +79,14 @@ struct iommu_table {
 #endif
 };
 
+/* Pure 2^n version of get_order */
+static inline __attribute_const__
+int get_iommu_order(unsigned long size, struct iommu_table *tbl)
+{
+	return __ilog2((size - 1) >> tbl->it_page_shift) + 1;
+}
+
+
 struct scatterlist;
 
 static inline void set_iommu_table_base(struct device *dev, void *base)
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 5cfe3dbfc4a0..54d0116256f7 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -83,10 +83,10 @@ static int dma_iommu_dma_supported(struct device *dev, u64 mask)
 		return 0;
 	}
 
-	if (tbl->it_offset > (mask >> IOMMU_PAGE_SHIFT_4K)) {
+	if (tbl->it_offset > (mask >> tbl->it_page_shift)) {
 		dev_info(dev, "Warning: IOMMU offset too big for device mask\n");
 		dev_info(dev, "mask: 0x%08llx, table offset: 0x%08lx\n",
-				mask, tbl->it_offset << IOMMU_PAGE_SHIFT_4K);
+				mask, tbl->it_offset << tbl->it_page_shift);
 		return 0;
 	} else
 		return 1;
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index df4a7f1b7444..f58d8135aab2 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -251,14 +251,13 @@ again:
 
 	if (dev)
 		boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-				      1 << IOMMU_PAGE_SHIFT_4K);
+				      1 << tbl->it_page_shift);
 	else
-		boundary_size = ALIGN(1UL << 32, 1 << IOMMU_PAGE_SHIFT_4K);
+		boundary_size = ALIGN(1UL << 32, 1 << tbl->it_page_shift);
 	/* 4GB boundary for iseries_hv_alloc and iseries_hv_map */
 
-	n = iommu_area_alloc(tbl->it_map, limit, start, npages,
-			tbl->it_offset, boundary_size >> IOMMU_PAGE_SHIFT_4K,
-			align_mask);
+	n = iommu_area_alloc(tbl->it_map, limit, start, npages, tbl->it_offset,
+			     boundary_size >> tbl->it_page_shift, align_mask);
 	if (n == -1) {
 		if (likely(pass == 0)) {
 			/* First try the pool from the start */
@@ -320,12 +319,12 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
 		return DMA_ERROR_CODE;
 
 	entry += tbl->it_offset;	/* Offset into real TCE table */
-	ret = entry << IOMMU_PAGE_SHIFT_4K;	/* Set the return dma address */
+	ret = entry << tbl->it_page_shift;	/* Set the return dma address */
 
 	/* Put the TCEs in the HW table */
 	build_fail = ppc_md.tce_build(tbl, entry, npages,
-				(unsigned long)page & IOMMU_PAGE_MASK_4K,
-				direction, attrs);
+				      (unsigned long)page &
+				      IOMMU_PAGE_MASK(tbl), direction, attrs);
 
 	/* ppc_md.tce_build() only returns non-zero for transient errors.
 	 * Clean up the table bitmap in this case and return
@@ -352,7 +351,7 @@ static bool iommu_free_check(struct iommu_table *tbl, dma_addr_t dma_addr,
 {
 	unsigned long entry, free_entry;
 
-	entry = dma_addr >> IOMMU_PAGE_SHIFT_4K;
+	entry = dma_addr >> tbl->it_page_shift;
 	free_entry = entry - tbl->it_offset;
 
 	if (((free_entry + npages) > tbl->it_size) ||
@@ -401,7 +400,7 @@ static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 	unsigned long flags;
 	struct iommu_pool *pool;
 
-	entry = dma_addr >> IOMMU_PAGE_SHIFT_4K;
+	entry = dma_addr >> tbl->it_page_shift;
 	free_entry = entry - tbl->it_offset;
 
 	pool = get_pool(tbl, free_entry);
@@ -468,13 +467,13 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 		}
 		/* Allocate iommu entries for that segment */
 		vaddr = (unsigned long) sg_virt(s);
-		npages = iommu_num_pages(vaddr, slen, IOMMU_PAGE_SIZE_4K);
+		npages = iommu_num_pages(vaddr, slen, IOMMU_PAGE_SIZE(tbl));
 		align = 0;
-		if (IOMMU_PAGE_SHIFT_4K < PAGE_SHIFT && slen >= PAGE_SIZE &&
+		if (tbl->it_page_shift < PAGE_SHIFT && slen >= PAGE_SIZE &&
 		    (vaddr & ~PAGE_MASK) == 0)
-			align = PAGE_SHIFT - IOMMU_PAGE_SHIFT_4K;
+			align = PAGE_SHIFT - tbl->it_page_shift;
 		entry = iommu_range_alloc(dev, tbl, npages, &handle,
-					  mask >> IOMMU_PAGE_SHIFT_4K, align);
+					  mask >> tbl->it_page_shift, align);
 
 		DBG("  - vaddr: %lx, size: %lx\n", vaddr, slen);
 
@@ -489,16 +488,16 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 
 		/* Convert entry to a dma_addr_t */
 		entry += tbl->it_offset;
-		dma_addr = entry << IOMMU_PAGE_SHIFT_4K;
-		dma_addr |= (s->offset & ~IOMMU_PAGE_MASK_4K);
+		dma_addr = entry << tbl->it_page_shift;
+		dma_addr |= (s->offset & ~IOMMU_PAGE_MASK(tbl));
 
 		DBG("  - %lu pages, entry: %lx, dma_addr: %lx\n",
 			    npages, entry, dma_addr);
 
 		/* Insert into HW table */
 		build_fail = ppc_md.tce_build(tbl, entry, npages,
-					vaddr & IOMMU_PAGE_MASK_4K,
-					direction, attrs);
+					      vaddr & IOMMU_PAGE_MASK(tbl),
+					      direction, attrs);
 		if(unlikely(build_fail))
 			goto failure;
 
@@ -559,9 +558,9 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 		if (s->dma_length != 0) {
 			unsigned long vaddr, npages;
 
-			vaddr = s->dma_address & IOMMU_PAGE_MASK_4K;
+			vaddr = s->dma_address & IOMMU_PAGE_MASK(tbl);
 			npages = iommu_num_pages(s->dma_address, s->dma_length,
-						 IOMMU_PAGE_SIZE_4K);
+						 IOMMU_PAGE_SIZE(tbl));
 			__iommu_free(tbl, vaddr, npages);
 			s->dma_address = DMA_ERROR_CODE;
 			s->dma_length = 0;
@@ -592,7 +591,7 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 		if (sg->dma_length == 0)
 			break;
 		npages = iommu_num_pages(dma_handle, sg->dma_length,
-					 IOMMU_PAGE_SIZE_4K);
+					 IOMMU_PAGE_SIZE(tbl));
 		__iommu_free(tbl, dma_handle, npages);
 		sg = sg_next(sg);
 	}
@@ -676,7 +675,7 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
 		set_bit(0, tbl->it_map);
 
 	/* We only split the IOMMU table if we have 1GB or more of space */
-	if ((tbl->it_size << IOMMU_PAGE_SHIFT_4K) >= (1UL * 1024 * 1024 * 1024))
+	if ((tbl->it_size << tbl->it_page_shift) >= (1UL * 1024 * 1024 * 1024))
 		tbl->nr_pools = IOMMU_NR_POOLS;
 	else
 		tbl->nr_pools = 1;
@@ -768,16 +767,16 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl,
 
 	vaddr = page_address(page) + offset;
 	uaddr = (unsigned long)vaddr;
-	npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE_4K);
+	npages = iommu_num_pages(uaddr, size, IOMMU_PAGE_SIZE(tbl));
 
 	if (tbl) {
 		align = 0;
-		if (IOMMU_PAGE_SHIFT_4K < PAGE_SHIFT && size >= PAGE_SIZE &&
+		if (tbl->it_page_shift < PAGE_SHIFT && size >= PAGE_SIZE &&
 		    ((unsigned long)vaddr & ~PAGE_MASK) == 0)
-			align = PAGE_SHIFT - IOMMU_PAGE_SHIFT_4K;
+			align = PAGE_SHIFT - tbl->it_page_shift;
 
 		dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction,
-					 mask >> IOMMU_PAGE_SHIFT_4K, align,
+					 mask >> tbl->it_page_shift, align,
 					 attrs);
 		if (dma_handle == DMA_ERROR_CODE) {
 			if (printk_ratelimit())  {
@@ -786,7 +785,7 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl,
 					 npages);
 			}
 		} else
-			dma_handle |= (uaddr & ~IOMMU_PAGE_MASK_4K);
+			dma_handle |= (uaddr & ~IOMMU_PAGE_MASK(tbl));
 	}
 
 	return dma_handle;
@@ -801,7 +800,8 @@ void iommu_unmap_page(struct iommu_table *tbl, dma_addr_t dma_handle,
 	BUG_ON(direction == DMA_NONE);
 
 	if (tbl) {
-		npages = iommu_num_pages(dma_handle, size, IOMMU_PAGE_SIZE_4K);
+		npages = iommu_num_pages(dma_handle, size,
+					 IOMMU_PAGE_SIZE(tbl));
 		iommu_free(tbl, dma_handle, npages);
 	}
 }
@@ -845,10 +845,10 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 	memset(ret, 0, size);
 
 	/* Set up tces to cover the allocated range */
-	nio_pages = size >> IOMMU_PAGE_SHIFT_4K;
-	io_order = get_iommu_order(size);
+	nio_pages = size >> tbl->it_page_shift;
+	io_order = get_iommu_order(size, tbl);
 	mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL,
-			      mask >> IOMMU_PAGE_SHIFT_4K, io_order, NULL);
+			      mask >> tbl->it_page_shift, io_order, NULL);
 	if (mapping == DMA_ERROR_CODE) {
 		free_pages((unsigned long)ret, order);
 		return NULL;
@@ -864,7 +864,7 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size,
 		unsigned int nio_pages;
 
 		size = PAGE_ALIGN(size);
-		nio_pages = size >> IOMMU_PAGE_SHIFT_4K;
+		nio_pages = size >> tbl->it_page_shift;
 		iommu_free(tbl, dma_handle, nio_pages);
 		size = PAGE_ALIGN(size);
 		free_pages((unsigned long)vaddr, get_order(size));
@@ -935,10 +935,10 @@ int iommu_tce_clear_param_check(struct iommu_table *tbl,
 	if (tce_value)
 		return -EINVAL;
 
-	if (ioba & ~IOMMU_PAGE_MASK_4K)
+	if (ioba & ~IOMMU_PAGE_MASK(tbl))
 		return -EINVAL;
 
-	ioba >>= IOMMU_PAGE_SHIFT_4K;
+	ioba >>= tbl->it_page_shift;
 	if (ioba < tbl->it_offset)
 		return -EINVAL;
 
@@ -955,13 +955,13 @@ int iommu_tce_put_param_check(struct iommu_table *tbl,
 	if (!(tce & (TCE_PCI_WRITE | TCE_PCI_READ)))
 		return -EINVAL;
 
-	if (tce & ~(IOMMU_PAGE_MASK_4K | TCE_PCI_WRITE | TCE_PCI_READ))
+	if (tce & ~(IOMMU_PAGE_MASK(tbl) | TCE_PCI_WRITE | TCE_PCI_READ))
 		return -EINVAL;
 
-	if (ioba & ~IOMMU_PAGE_MASK_4K)
+	if (ioba & ~IOMMU_PAGE_MASK(tbl))
 		return -EINVAL;
 
-	ioba >>= IOMMU_PAGE_SHIFT_4K;
+	ioba >>= tbl->it_page_shift;
 	if (ioba < tbl->it_offset)
 		return -EINVAL;
 
@@ -1037,7 +1037,7 @@ int iommu_tce_build(struct iommu_table *tbl, unsigned long entry,
 
 	/* if (unlikely(ret))
 		pr_err("iommu_tce: %s failed on hwaddr=%lx ioba=%lx kva=%lx ret=%d\n",
-				__func__, hwaddr, entry << IOMMU_PAGE_SHIFT_4K,
+			__func__, hwaddr, entry << IOMMU_PAGE_SHIFT(tbl),
 				hwaddr, ret); */
 
 	return ret;
@@ -1049,14 +1049,14 @@ int iommu_put_tce_user_mode(struct iommu_table *tbl, unsigned long entry,
 {
 	int ret;
 	struct page *page = NULL;
-	unsigned long hwaddr, offset = tce & IOMMU_PAGE_MASK_4K & ~PAGE_MASK;
+	unsigned long hwaddr, offset = tce & IOMMU_PAGE_MASK(tbl) & ~PAGE_MASK;
 	enum dma_data_direction direction = iommu_tce_direction(tce);
 
 	ret = get_user_pages_fast(tce & PAGE_MASK, 1,
 			direction != DMA_TO_DEVICE, &page);
 	if (unlikely(ret != 1)) {
 		/* pr_err("iommu_tce: get_user_pages_fast failed tce=%lx ioba=%lx ret=%d\n",
-				tce, entry << IOMMU_PAGE_SHIFT_4K, ret); */
+				tce, entry << IOMMU_PAGE_SHIFT(tbl), ret); */
 		return -EFAULT;
 	}
 	hwaddr = (unsigned long) page_address(page) + offset;
@@ -1067,7 +1067,7 @@ int iommu_put_tce_user_mode(struct iommu_table *tbl, unsigned long entry,
 
 	if (ret < 0)
 		pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%d\n",
-			__func__, entry << IOMMU_PAGE_SHIFT_4K, tce, ret);
+			__func__, entry << tbl->it_page_shift, tce, ret);
 
 	return ret;
 }
@@ -1127,6 +1127,12 @@ int iommu_add_device(struct device *dev)
 	pr_debug("iommu_tce: adding %s to iommu group %d\n",
 			dev_name(dev), iommu_group_id(tbl->it_group));
 
+	if (PAGE_SIZE < IOMMU_PAGE_SIZE(tbl)) {
+		pr_err("iommu_tce: unsupported iommu page size.");
+		pr_err("%s has not been added\n", dev_name(dev));
+		return -EINVAL;
+	}
+
 	ret = iommu_group_add_device(tbl->it_group, dev);
 	if (ret < 0)
 		pr_err("iommu_tce: %s has not been added, ret=%d\n",
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index 170ac24a0106..826d8bd9e522 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -518,16 +518,18 @@ static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page,
                                          struct dma_attrs *attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
+	struct iommu_table *tbl;
 	dma_addr_t ret = DMA_ERROR_CODE;
 
-	if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE_4K))) {
+	tbl = get_iommu_table_base(dev);
+	if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)))) {
 		atomic_inc(&viodev->cmo.allocs_failed);
 		return ret;
 	}
 
 	ret = dma_iommu_ops.map_page(dev, page, offset, size, direction, attrs);
 	if (unlikely(dma_mapping_error(dev, ret))) {
-		vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE_4K));
+		vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)));
 		atomic_inc(&viodev->cmo.allocs_failed);
 	}
 
@@ -540,10 +542,12 @@ static void vio_dma_iommu_unmap_page(struct device *dev, dma_addr_t dma_handle,
 				     struct dma_attrs *attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
+	struct iommu_table *tbl;
 
+	tbl = get_iommu_table_base(dev);
 	dma_iommu_ops.unmap_page(dev, dma_handle, size, direction, attrs);
 
-	vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE_4K));
+	vio_cmo_dealloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)));
 }
 
 static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
@@ -551,12 +555,14 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
                                 struct dma_attrs *attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
+	struct iommu_table *tbl;
 	struct scatterlist *sgl;
 	int ret, count = 0;
 	size_t alloc_size = 0;
 
+	tbl = get_iommu_table_base(dev);
 	for (sgl = sglist; count < nelems; count++, sgl++)
-		alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE_4K);
+		alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE(tbl));
 
 	if (vio_cmo_alloc(viodev, alloc_size)) {
 		atomic_inc(&viodev->cmo.allocs_failed);
@@ -572,7 +578,7 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
 	}
 
 	for (sgl = sglist, count = 0; count < ret; count++, sgl++)
-		alloc_size -= roundup(sgl->dma_length, IOMMU_PAGE_SIZE_4K);
+		alloc_size -= roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl));
 	if (alloc_size)
 		vio_cmo_dealloc(viodev, alloc_size);
 
@@ -585,12 +591,14 @@ static void vio_dma_iommu_unmap_sg(struct device *dev,
 		struct dma_attrs *attrs)
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
+	struct iommu_table *tbl;
 	struct scatterlist *sgl;
 	size_t alloc_size = 0;
 	int count = 0;
 
+	tbl = get_iommu_table_base(dev);
 	for (sgl = sglist; count < nelems; count++, sgl++)
-		alloc_size += roundup(sgl->dma_length, IOMMU_PAGE_SIZE_4K);
+		alloc_size += roundup(sgl->dma_length, IOMMU_PAGE_SIZE(tbl));
 
 	dma_iommu_ops.unmap_sg(dev, sglist, nelems, direction, attrs);
 
@@ -706,11 +714,14 @@ static int vio_cmo_bus_probe(struct vio_dev *viodev)
 {
 	struct vio_cmo_dev_entry *dev_ent;
 	struct device *dev = &viodev->dev;
+	struct iommu_table *tbl;
 	struct vio_driver *viodrv = to_vio_driver(dev->driver);
 	unsigned long flags;
 	size_t size;
 	bool dma_capable = false;
 
+	tbl = get_iommu_table_base(dev);
+
 	/* A device requires entitlement if it has a DMA window property */
 	switch (viodev->family) {
 	case VDEVICE:
@@ -737,7 +748,7 @@ static int vio_cmo_bus_probe(struct vio_dev *viodev)
 		}
 
 		viodev->cmo.desired =
-			IOMMU_PAGE_ALIGN_4K(viodrv->get_desired_dma(viodev));
+			IOMMU_PAGE_ALIGN(viodrv->get_desired_dma(viodev), tbl);
 		if (viodev->cmo.desired < VIO_CMO_MIN_ENT)
 			viodev->cmo.desired = VIO_CMO_MIN_ENT;
 		size = VIO_CMO_MIN_ENT;
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 569b46423a93..b555ebc57ef5 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -762,8 +762,6 @@ static struct notifier_block tce_iommu_bus_nb = {
 
 static int __init tce_iommu_bus_notifier_init(void)
 {
-	BUILD_BUG_ON(PAGE_SIZE < IOMMU_PAGE_SIZE_4K);
-
 	bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb);
 	return 0;
 }
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index f7d7538b6bd9..d04dbaba83dd 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1276,31 +1276,34 @@ static unsigned long ibmveth_get_desired_dma(struct vio_dev *vdev)
 {
 	struct net_device *netdev = dev_get_drvdata(&vdev->dev);
 	struct ibmveth_adapter *adapter;
+	struct iommu_table *tbl;
 	unsigned long ret;
 	int i;
 	int rxqentries = 1;
 
+	tbl = get_iommu_table_base(&vdev->dev);
+
 	/* netdev inits at probe time along with the structures we need below*/
 	if (netdev == NULL)
-		return IOMMU_PAGE_ALIGN_4K(IBMVETH_IO_ENTITLEMENT_DEFAULT);
+		return IOMMU_PAGE_ALIGN(IBMVETH_IO_ENTITLEMENT_DEFAULT, tbl);
 
 	adapter = netdev_priv(netdev);
 
 	ret = IBMVETH_BUFF_LIST_SIZE + IBMVETH_FILT_LIST_SIZE;
-	ret += IOMMU_PAGE_ALIGN_4K(netdev->mtu);
+	ret += IOMMU_PAGE_ALIGN(netdev->mtu, tbl);
 
 	for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) {
 		/* add the size of the active receive buffers */
 		if (adapter->rx_buff_pool[i].active)
 			ret +=
 			    adapter->rx_buff_pool[i].size *
-			    IOMMU_PAGE_ALIGN_4K(adapter->rx_buff_pool[i].
-			            buff_size);
+			    IOMMU_PAGE_ALIGN(adapter->rx_buff_pool[i].
+					     buff_size, tbl);
 		rxqentries += adapter->rx_buff_pool[i].size;
 	}
 	/* add the size of the receive queue entries */
-	ret += IOMMU_PAGE_ALIGN_4K(
-		rxqentries * sizeof(struct ibmveth_rx_q_entry));
+	ret += IOMMU_PAGE_ALIGN(
+		rxqentries * sizeof(struct ibmveth_rx_q_entry), tbl);
 
 	return ret;
 }
-- 
cgit v1.2.3


From c141611fb1ee2cfc374cf9be5327e97f361c4bed Mon Sep 17 00:00:00 2001
From: Paul Gortmaker <paul.gortmaker@windriver.com>
Date: Thu, 9 Jan 2014 00:44:29 -0500
Subject: powerpc: Delete non-required instances of include <linux/init.h>

None of these files are actually using any __init type directives
and hence don't need to include <linux/init.h>.  Most are just a
left over from __devinit and __cpuinit removal, or simply due to
code getting copied from one driver to the next.

The one instance where we add an include for init.h covers off
a case where that file was implicitly getting it from another
header which itself didn't need it.

Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/paca.h                | 1 -
 arch/powerpc/include/asm/ppc_asm.h             | 1 -
 arch/powerpc/include/asm/ps3.h                 | 1 -
 arch/powerpc/include/asm/vio.h                 | 1 -
 arch/powerpc/kernel/cacheinfo.c                | 1 -
 arch/powerpc/kernel/crash.c                    | 1 -
 arch/powerpc/kernel/eeh_pe.c                   | 1 -
 arch/powerpc/kernel/head_64.S                  | 1 +
 arch/powerpc/kernel/hw_breakpoint.c            | 1 -
 arch/powerpc/kernel/iomap.c                    | 1 -
 arch/powerpc/kernel/kgdb.c                     | 1 -
 arch/powerpc/kernel/process.c                  | 1 -
 arch/powerpc/kernel/smp-tbsync.c               | 1 -
 arch/powerpc/kernel/syscalls.c                 | 1 -
 arch/powerpc/kernel/vdso32/vdso32_wrapper.S    | 1 -
 arch/powerpc/kernel/vdso64/vdso64_wrapper.S    | 1 -
 arch/powerpc/mm/pgtable.c                      | 1 -
 arch/powerpc/mm/pgtable_64.c                   | 1 -
 arch/powerpc/mm/tlb_hash64.c                   | 1 -
 arch/powerpc/oprofile/op_model_7450.c          | 1 -
 arch/powerpc/oprofile/op_model_cell.c          | 1 -
 arch/powerpc/oprofile/op_model_fsl_emb.c       | 1 -
 arch/powerpc/oprofile/op_model_pa6t.c          | 1 -
 arch/powerpc/oprofile/op_model_power4.c        | 1 -
 arch/powerpc/oprofile/op_model_rs64.c          | 1 -
 arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c | 1 -
 arch/powerpc/platforms/83xx/suspend.c          | 1 -
 arch/powerpc/platforms/85xx/sgy_cts1000.c      | 1 -
 arch/powerpc/platforms/chrp/smp.c              | 1 -
 arch/powerpc/platforms/embedded6xx/hlwd-pic.c  | 1 -
 arch/powerpc/platforms/pasemi/dma_lib.c        | 1 -
 arch/powerpc/platforms/powermac/pfunc_core.c   | 1 -
 arch/powerpc/platforms/powernv/eeh-ioda.c      | 1 -
 arch/powerpc/platforms/pseries/cmm.c           | 1 -
 arch/powerpc/platforms/pseries/dtl.c           | 1 -
 arch/powerpc/sysdev/cpm2_pic.c                 | 1 -
 arch/powerpc/sysdev/fsl_ifc.c                  | 1 -
 arch/powerpc/sysdev/ge/ge_pic.h                | 1 -
 arch/powerpc/sysdev/i8259.c                    | 1 -
 arch/powerpc/sysdev/mpc8xx_pic.c               | 1 -
 arch/powerpc/sysdev/qe_lib/qe_io.c             | 1 -
 arch/powerpc/sysdev/qe_lib/ucc.c               | 1 -
 arch/powerpc/sysdev/qe_lib/ucc_fast.c          | 1 -
 arch/powerpc/sysdev/qe_lib/ucc_slow.c          | 1 -
 arch/powerpc/sysdev/udbg_memcons.c             | 1 -
 arch/powerpc/sysdev/xics/icp-hv.c              | 1 -
 46 files changed, 1 insertion(+), 45 deletions(-)

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

diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index c3523d1dda58..68bee4636045 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -16,7 +16,6 @@
 
 #ifdef CONFIG_PPC64
 
-#include <linux/init.h>
 #include <asm/types.h>
 #include <asm/lppaca.h>
 #include <asm/mmu.h>
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index f595b98079ee..7689e0e98d33 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -4,7 +4,6 @@
 #ifndef _ASM_POWERPC_PPC_ASM_H
 #define _ASM_POWERPC_PPC_ASM_H
 
-#include <linux/init.h>
 #include <linux/stringify.h>
 #include <asm/asm-compat.h>
 #include <asm/processor.h>
diff --git a/arch/powerpc/include/asm/ps3.h b/arch/powerpc/include/asm/ps3.h
index 678a7c1d9cb8..a1bc7e758422 100644
--- a/arch/powerpc/include/asm/ps3.h
+++ b/arch/powerpc/include/asm/ps3.h
@@ -21,7 +21,6 @@
 #if !defined(_ASM_POWERPC_PS3_H)
 #define _ASM_POWERPC_PS3_H
 
-#include <linux/init.h>
 #include <linux/types.h>
 #include <linux/device.h>
 #include <asm/cell-pmu.h>
diff --git a/arch/powerpc/include/asm/vio.h b/arch/powerpc/include/asm/vio.h
index 68d0cc998b1b..4f9b7ca0710f 100644
--- a/arch/powerpc/include/asm/vio.h
+++ b/arch/powerpc/include/asm/vio.h
@@ -15,7 +15,6 @@
 #define _ASM_POWERPC_VIO_H
 #ifdef __KERNEL__
 
-#include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index 654932727873..abfa011344d9 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -12,7 +12,6 @@
 
 #include <linux/cpu.h>
 #include <linux/cpumask.h>
-#include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/kobject.h>
 #include <linux/list.h>
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index fdcd8f551aff..18d7c80ddeb9 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -17,7 +17,6 @@
 #include <linux/export.h>
 #include <linux/crash_dump.h>
 #include <linux/delay.h>
-#include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/types.h>
 
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index f9450537e335..1feccd64f955 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -25,7 +25,6 @@
 #include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/gfp.h>
-#include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/pci.h>
 #include <linux/string.h>
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 4f0946de2d5c..b7363bd42452 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -23,6 +23,7 @@
  */
 
 #include <linux/threads.h>
+#include <linux/init.h>
 #include <asm/reg.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index f0b47d1a6b0e..b0a1792279bb 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -28,7 +28,6 @@
 #include <linux/percpu.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
-#include <linux/init.h>
 #include <linux/smp.h>
 
 #include <asm/hw_breakpoint.h>
diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c
index 97a3715ac8bd..b82227e7e21b 100644
--- a/arch/powerpc/kernel/iomap.c
+++ b/arch/powerpc/kernel/iomap.c
@@ -3,7 +3,6 @@
  *
  * (C) Copyright 2004 Linus Torvalds
  */
-#include <linux/init.h>
 #include <linux/pci.h>
 #include <linux/mm.h>
 #include <linux/export.h>
diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c
index 83e89d310734..8504657379f1 100644
--- a/arch/powerpc/kernel/kgdb.c
+++ b/arch/powerpc/kernel/kgdb.c
@@ -15,7 +15,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/init.h>
 #include <linux/kgdb.h>
 #include <linux/smp.h>
 #include <linux/signal.h>
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 3386d8ab7eb0..bf8e136316e2 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -25,7 +25,6 @@
 #include <linux/slab.h>
 #include <linux/user.h>
 #include <linux/elf.h>
-#include <linux/init.h>
 #include <linux/prctl.h>
 #include <linux/init_task.h>
 #include <linux/export.h>
diff --git a/arch/powerpc/kernel/smp-tbsync.c b/arch/powerpc/kernel/smp-tbsync.c
index e68fd1ae727a..7a37ecd3afa3 100644
--- a/arch/powerpc/kernel/smp-tbsync.c
+++ b/arch/powerpc/kernel/smp-tbsync.c
@@ -9,7 +9,6 @@
 #include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/unistd.h>
-#include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/atomic.h>
 #include <asm/smp.h>
diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c
index 4e3cc47f26b9..cd9be9aa016d 100644
--- a/arch/powerpc/kernel/syscalls.c
+++ b/arch/powerpc/kernel/syscalls.c
@@ -34,7 +34,6 @@
 #include <linux/ipc.h>
 #include <linux/utsname.h>
 #include <linux/file.h>
-#include <linux/init.h>
 #include <linux/personality.h>
 
 #include <asm/uaccess.h>
diff --git a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S
index 6e8f507ed32b..79683d0393f5 100644
--- a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S
+++ b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S
@@ -1,4 +1,3 @@
-#include <linux/init.h>
 #include <linux/linkage.h>
 #include <asm/page.h>
 
diff --git a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S
index b8553d62b792..8df9e2463007 100644
--- a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S
+++ b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S
@@ -1,4 +1,3 @@
-#include <linux/init.h>
 #include <linux/linkage.h>
 #include <asm/page.h>
 
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index ad90429bbd8b..c695943a513c 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -24,7 +24,6 @@
 #include <linux/kernel.h>
 #include <linux/gfp.h>
 #include <linux/mm.h>
-#include <linux/init.h>
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
 #include <linux/hugetlb.h>
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 02e8681fb865..7f0e872ab83d 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -33,7 +33,6 @@
 #include <linux/swap.h>
 #include <linux/stddef.h>
 #include <linux/vmalloc.h>
-#include <linux/init.h>
 #include <linux/bootmem.h>
 #include <linux/memblock.h>
 #include <linux/slab.h>
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
index 36e44b4260eb..c99f6510a0b2 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -23,7 +23,6 @@
 
 #include <linux/kernel.h>
 #include <linux/mm.h>
-#include <linux/init.h>
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
 #include <asm/pgalloc.h>
diff --git a/arch/powerpc/oprofile/op_model_7450.c b/arch/powerpc/oprofile/op_model_7450.c
index ff617246d128..d29b6e4e5e72 100644
--- a/arch/powerpc/oprofile/op_model_7450.c
+++ b/arch/powerpc/oprofile/op_model_7450.c
@@ -16,7 +16,6 @@
  */
 
 #include <linux/oprofile.h>
-#include <linux/init.h>
 #include <linux/smp.h>
 #include <asm/ptrace.h>
 #include <asm/processor.h>
diff --git a/arch/powerpc/oprofile/op_model_cell.c b/arch/powerpc/oprofile/op_model_cell.c
index b9589c19ccda..1f0ebdeea5f7 100644
--- a/arch/powerpc/oprofile/op_model_cell.c
+++ b/arch/powerpc/oprofile/op_model_cell.c
@@ -16,7 +16,6 @@
 
 #include <linux/cpufreq.h>
 #include <linux/delay.h>
-#include <linux/init.h>
 #include <linux/jiffies.h>
 #include <linux/kthread.h>
 #include <linux/oprofile.h>
diff --git a/arch/powerpc/oprofile/op_model_fsl_emb.c b/arch/powerpc/oprofile/op_model_fsl_emb.c
index 2a82d3ed464d..14cf86fdddab 100644
--- a/arch/powerpc/oprofile/op_model_fsl_emb.c
+++ b/arch/powerpc/oprofile/op_model_fsl_emb.c
@@ -14,7 +14,6 @@
  */
 
 #include <linux/oprofile.h>
-#include <linux/init.h>
 #include <linux/smp.h>
 #include <asm/ptrace.h>
 #include <asm/processor.h>
diff --git a/arch/powerpc/oprofile/op_model_pa6t.c b/arch/powerpc/oprofile/op_model_pa6t.c
index 42f778dff919..a114a7c22d40 100644
--- a/arch/powerpc/oprofile/op_model_pa6t.c
+++ b/arch/powerpc/oprofile/op_model_pa6t.c
@@ -22,7 +22,6 @@
  */
 
 #include <linux/oprofile.h>
-#include <linux/init.h>
 #include <linux/smp.h>
 #include <linux/percpu.h>
 #include <asm/processor.h>
diff --git a/arch/powerpc/oprofile/op_model_power4.c b/arch/powerpc/oprofile/op_model_power4.c
index f444b94935f5..962fe7b3e3fb 100644
--- a/arch/powerpc/oprofile/op_model_power4.c
+++ b/arch/powerpc/oprofile/op_model_power4.c
@@ -10,7 +10,6 @@
  */
 
 #include <linux/oprofile.h>
-#include <linux/init.h>
 #include <linux/smp.h>
 #include <asm/firmware.h>
 #include <asm/ptrace.h>
diff --git a/arch/powerpc/oprofile/op_model_rs64.c b/arch/powerpc/oprofile/op_model_rs64.c
index 9b801b8c8c5a..7e5b8ed3a1b7 100644
--- a/arch/powerpc/oprofile/op_model_rs64.c
+++ b/arch/powerpc/oprofile/op_model_rs64.c
@@ -8,7 +8,6 @@
  */
 
 #include <linux/oprofile.h>
-#include <linux/init.h>
 #include <linux/smp.h>
 #include <asm/ptrace.h>
 #include <asm/processor.h>
diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
index fd71cfdf2380..e238b6a55b15 100644
--- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
+++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
@@ -11,7 +11,6 @@
  * (at your option) any later version.
  */
 
-#include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/device.h>
diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c
index 3d9716ccd327..4b4c081df94d 100644
--- a/arch/powerpc/platforms/83xx/suspend.c
+++ b/arch/powerpc/platforms/83xx/suspend.c
@@ -10,7 +10,6 @@
  * by the Free Software Foundation.
  */
 
-#include <linux/init.h>
 #include <linux/pm.h>
 #include <linux/types.h>
 #include <linux/ioport.h>
diff --git a/arch/powerpc/platforms/85xx/sgy_cts1000.c b/arch/powerpc/platforms/85xx/sgy_cts1000.c
index b9197cea1854..bb75add67084 100644
--- a/arch/powerpc/platforms/85xx/sgy_cts1000.c
+++ b/arch/powerpc/platforms/85xx/sgy_cts1000.c
@@ -14,7 +14,6 @@
 #include <linux/platform_device.h>
 #include <linux/device.h>
 #include <linux/module.h>
-#include <linux/init.h>
 #include <linux/of_gpio.h>
 #include <linux/of_irq.h>
 #include <linux/workqueue.h>
diff --git a/arch/powerpc/platforms/chrp/smp.c b/arch/powerpc/platforms/chrp/smp.c
index dead91b177b9..b6c9a0dcc924 100644
--- a/arch/powerpc/platforms/chrp/smp.c
+++ b/arch/powerpc/platforms/chrp/smp.c
@@ -14,7 +14,6 @@
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
 #include <linux/delay.h>
-#include <linux/init.h>
 #include <linux/spinlock.h>
 
 #include <asm/ptrace.h>
diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
index 6c03034dbbd3..c269caee58f9 100644
--- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
+++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
@@ -15,7 +15,6 @@
 #define pr_fmt(fmt) DRV_MODULE_NAME ": " fmt
 
 #include <linux/kernel.h>
-#include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
diff --git a/arch/powerpc/platforms/pasemi/dma_lib.c b/arch/powerpc/platforms/pasemi/dma_lib.c
index f3defd8a2806..aafa01ba062f 100644
--- a/arch/powerpc/platforms/pasemi/dma_lib.c
+++ b/arch/powerpc/platforms/pasemi/dma_lib.c
@@ -18,7 +18,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/init.h>
 #include <linux/export.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
diff --git a/arch/powerpc/platforms/powermac/pfunc_core.c b/arch/powerpc/platforms/powermac/pfunc_core.c
index d588e48dff74..43075081721f 100644
--- a/arch/powerpc/platforms/powermac/pfunc_core.c
+++ b/arch/powerpc/platforms/powermac/pfunc_core.c
@@ -5,7 +5,6 @@
  * FIXME: LOCKING !!!
  */
 
-#include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/kernel.h>
 #include <linux/spinlock.h>
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index 9b1db254898a..007ac4989841 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -14,7 +14,6 @@
 #include <linux/bootmem.h>
 #include <linux/debugfs.h>
 #include <linux/delay.h>
-#include <linux/init.h>
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/kernel.h>
diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c
index 1e561bef459b..2d8bf15879fd 100644
--- a/arch/powerpc/platforms/pseries/cmm.c
+++ b/arch/powerpc/platforms/pseries/cmm.c
@@ -25,7 +25,6 @@
 #include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/gfp.h>
-#include <linux/init.h>
 #include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/oom.h>
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index 5db66f1fbc26..7d61498e45c0 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -20,7 +20,6 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
-#include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/debugfs.h>
 #include <linux/spinlock.h>
diff --git a/arch/powerpc/sysdev/cpm2_pic.c b/arch/powerpc/sysdev/cpm2_pic.c
index 10386b676d87..a11bd1d433ad 100644
--- a/arch/powerpc/sysdev/cpm2_pic.c
+++ b/arch/powerpc/sysdev/cpm2_pic.c
@@ -27,7 +27,6 @@
  */
 
 #include <linux/stddef.h>
-#include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/irq.h>
diff --git a/arch/powerpc/sysdev/fsl_ifc.c b/arch/powerpc/sysdev/fsl_ifc.c
index d7fc72239144..fbc885b31946 100644
--- a/arch/powerpc/sysdev/fsl_ifc.c
+++ b/arch/powerpc/sysdev/fsl_ifc.c
@@ -19,7 +19,6 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
-#include <linux/init.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/compiler.h>
diff --git a/arch/powerpc/sysdev/ge/ge_pic.h b/arch/powerpc/sysdev/ge/ge_pic.h
index 6149916da3f4..908dbd9826b6 100644
--- a/arch/powerpc/sysdev/ge/ge_pic.h
+++ b/arch/powerpc/sysdev/ge/ge_pic.h
@@ -1,7 +1,6 @@
 #ifndef __GEF_PIC_H__
 #define __GEF_PIC_H__
 
-#include <linux/init.h>
 
 void gef_pic_cascade(unsigned int, struct irq_desc *);
 unsigned int gef_pic_get_irq(void);
diff --git a/arch/powerpc/sysdev/i8259.c b/arch/powerpc/sysdev/i8259.c
index 997df6a7ab5d..45598da0b321 100644
--- a/arch/powerpc/sysdev/i8259.c
+++ b/arch/powerpc/sysdev/i8259.c
@@ -8,7 +8,6 @@
  */
 #undef DEBUG
 
-#include <linux/init.h>
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
diff --git a/arch/powerpc/sysdev/mpc8xx_pic.c b/arch/powerpc/sysdev/mpc8xx_pic.c
index b724622c3a0b..c4828c0be5bd 100644
--- a/arch/powerpc/sysdev/mpc8xx_pic.c
+++ b/arch/powerpc/sysdev/mpc8xx_pic.c
@@ -1,6 +1,5 @@
 #include <linux/kernel.h>
 #include <linux/stddef.h>
-#include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/irq.h>
diff --git a/arch/powerpc/sysdev/qe_lib/qe_io.c b/arch/powerpc/sysdev/qe_lib/qe_io.c
index a88807b3dd57..d09994164daf 100644
--- a/arch/powerpc/sysdev/qe_lib/qe_io.c
+++ b/arch/powerpc/sysdev/qe_lib/qe_io.c
@@ -16,7 +16,6 @@
 
 #include <linux/stddef.h>
 #include <linux/kernel.h>
-#include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/ioport.h>
diff --git a/arch/powerpc/sysdev/qe_lib/ucc.c b/arch/powerpc/sysdev/qe_lib/ucc.c
index 134b07d29435..621575b7e84a 100644
--- a/arch/powerpc/sysdev/qe_lib/ucc.c
+++ b/arch/powerpc/sysdev/qe_lib/ucc.c
@@ -14,7 +14,6 @@
  * option) any later version.
  */
 #include <linux/kernel.h>
-#include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/stddef.h>
 #include <linux/spinlock.h>
diff --git a/arch/powerpc/sysdev/qe_lib/ucc_fast.c b/arch/powerpc/sysdev/qe_lib/ucc_fast.c
index cceb2e366738..65aaf15032ae 100644
--- a/arch/powerpc/sysdev/qe_lib/ucc_fast.c
+++ b/arch/powerpc/sysdev/qe_lib/ucc_fast.c
@@ -13,7 +13,6 @@
  * option) any later version.
  */
 #include <linux/kernel.h>
-#include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/stddef.h>
diff --git a/arch/powerpc/sysdev/qe_lib/ucc_slow.c b/arch/powerpc/sysdev/qe_lib/ucc_slow.c
index 1c062f48f1ac..befaf1123f7f 100644
--- a/arch/powerpc/sysdev/qe_lib/ucc_slow.c
+++ b/arch/powerpc/sysdev/qe_lib/ucc_slow.c
@@ -13,7 +13,6 @@
  * option) any later version.
  */
 #include <linux/kernel.h>
-#include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/stddef.h>
diff --git a/arch/powerpc/sysdev/udbg_memcons.c b/arch/powerpc/sysdev/udbg_memcons.c
index ce5a7b489e4b..9998c0de12d0 100644
--- a/arch/powerpc/sysdev/udbg_memcons.c
+++ b/arch/powerpc/sysdev/udbg_memcons.c
@@ -18,7 +18,6 @@
  *      2 of the License, or (at your option) any later version.
  */
 
-#include <linux/init.h>
 #include <linux/kernel.h>
 #include <asm/barrier.h>
 #include <asm/page.h>
diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c
index df0fc5821469..c1917cf67c3d 100644
--- a/arch/powerpc/sysdev/xics/icp-hv.c
+++ b/arch/powerpc/sysdev/xics/icp-hv.c
@@ -12,7 +12,6 @@
 #include <linux/irq.h>
 #include <linux/smp.h>
 #include <linux/interrupt.h>
-#include <linux/init.h>
 #include <linux/cpu.h>
 #include <linux/of.h>
 
-- 
cgit v1.2.3


From 8184616f6fcfc98f0ebf083cbf6a43e5efe54e8a Mon Sep 17 00:00:00 2001
From: Gavin Shan <shangw@linux.vnet.ibm.com>
Date: Thu, 26 Dec 2013 09:29:40 +0800
Subject: powerpc/powernv: Remove unnecessary assignment

We don't have IO ports on PHB3 and the assignment of variable
"iomap_off" on PHB3 is meaningless. The patch just removes the
unnecessary assignment to the variable. The code change should
have been part of commit c35d2a8c ("powerpc/powernv: Needn't IO
segment map for PHB3").

Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/pci-ioda.c | 3 +--
 1 file changed, 1 insertion(+), 2 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 f0e68714696e..7d6dcc6d5fa9 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -1144,7 +1144,7 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 {
 	struct pci_controller *hose;
 	struct pnv_phb *phb;
-	unsigned long size, m32map_off, iomap_off, pemap_off;
+	unsigned long size, m32map_off, pemap_off, iomap_off = 0;
 	const __be64 *prop64;
 	const __be32 *prop32;
 	int len;
@@ -1231,7 +1231,6 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	size = _ALIGN_UP(phb->ioda.total_pe / 8, sizeof(unsigned long));
 	m32map_off = size;
 	size += phb->ioda.total_pe * sizeof(phb->ioda.m32_segmap[0]);
-	iomap_off = size;
 	if (phb->type == PNV_PHB_IODA1) {
 		iomap_off = size;
 		size += phb->ioda.total_pe * sizeof(phb->ioda.io_segmap[0]);
-- 
cgit v1.2.3


From 1d350544d5bf17d835d2850004c64ca51235c771 Mon Sep 17 00:00:00 2001
From: Gavin Shan <shangw@linux.vnet.ibm.com>
Date: Fri, 3 Jan 2014 17:47:12 +0800
Subject: powerpc/eeh: Add restore_config operation

After reset on the specific PE or PHB, we never configure AER
correctly on PowerNV platform. We needn't care it on pSeries
platform. The patch introduces additional EEH operation eeh_ops::
restore_config() so that we have chance to configure AER correctly
for PowerNV platform.

Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/eeh.h               | 1 +
 arch/powerpc/kernel/eeh_pe.c                 | 3 +++
 arch/powerpc/platforms/powernv/eeh-powernv.c | 3 ++-
 arch/powerpc/platforms/pseries/eeh_pseries.c | 4 +++-
 4 files changed, 9 insertions(+), 2 deletions(-)

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

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index d3e5e9bc8f94..7f8adc848cd6 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -157,6 +157,7 @@ struct eeh_ops {
 	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 (*next_error)(struct eeh_pe **pe);
+	int (*restore_config)(struct device_node *dn);
 };
 
 extern struct eeh_ops *eeh_ops;
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 1feccd64f955..f0c353fa655a 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -736,6 +736,9 @@ static void *eeh_restore_one_device_bars(void *data, void *flag)
 	else
 		eeh_restore_device_bars(edev, dn);
 
+	if (eeh_ops->restore_config)
+		eeh_ops->restore_config(dn);
+
 	return NULL;
 }
 
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 73b981438cc5..ab91e6a34afa 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -359,7 +359,8 @@ static struct eeh_ops powernv_eeh_ops = {
 	.configure_bridge       = powernv_eeh_configure_bridge,
 	.read_config            = pnv_pci_cfg_read,
 	.write_config           = pnv_pci_cfg_write,
-	.next_error		= powernv_eeh_next_error
+	.next_error		= powernv_eeh_next_error,
+	.restore_config		= NULL
 };
 
 /**
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index ccb633e077b1..9ef3cc8ebc11 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -689,7 +689,9 @@ static struct eeh_ops pseries_eeh_ops = {
 	.get_log		= pseries_eeh_get_log,
 	.configure_bridge       = pseries_eeh_configure_bridge,
 	.read_config		= pseries_eeh_read_config,
-	.write_config		= pseries_eeh_write_config
+	.write_config		= pseries_eeh_write_config,
+	.next_error		= NULL,
+	.restore_config		= NULL
 };
 
 /**
-- 
cgit v1.2.3


From 9be3becc2f99f4f2b1b697a616b1aa9e7889d68f Mon Sep 17 00:00:00 2001
From: Gavin Shan <shangw@linux.vnet.ibm.com>
Date: Fri, 3 Jan 2014 17:47:13 +0800
Subject: powerpc/eeh: Call opal_pci_reinit() on powernv for restoring config
 space

The patch implements the EEH operation backend restore_config()
for PowerNV platform. That relies on OPAL API opal_pci_reinit()
where we reinitialize the error reporting properly after PE or
PHB reset.

Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/opal.h              |  8 ++++++--
 arch/powerpc/platforms/powernv/eeh-powernv.c | 23 ++++++++++++++++++++++-
 2 files changed, 28 insertions(+), 3 deletions(-)

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

diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index a4041e9ed550..9a87b4401a41 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -344,12 +344,16 @@ enum OpalMveEnableAction {
 	OPAL_ENABLE_MVE = 1
 };
 
-enum OpalPciResetAndReinitScope {
+enum OpalPciResetScope {
 	OPAL_PHB_COMPLETE = 1, OPAL_PCI_LINK = 2, OPAL_PHB_ERROR = 3,
 	OPAL_PCI_HOT_RESET = 4, OPAL_PCI_FUNDAMENTAL_RESET = 5,
 	OPAL_PCI_IODA_TABLE_RESET = 6,
 };
 
+enum OpalPciReinitScope {
+	OPAL_REINIT_PCI_DEV = 1000
+};
+
 enum OpalPciResetState {
 	OPAL_DEASSERT_RESET = 0,
 	OPAL_ASSERT_RESET = 1
@@ -801,7 +805,7 @@ int64_t opal_pci_get_phb_diag_data(uint64_t phb_id, void *diag_buffer,
 int64_t opal_pci_get_phb_diag_data2(uint64_t phb_id, void *diag_buffer,
 				    uint64_t diag_buffer_len);
 int64_t opal_pci_fence_phb(uint64_t phb_id);
-int64_t opal_pci_reinit(uint64_t phb_id, uint8_t reinit_scope);
+int64_t opal_pci_reinit(uint64_t phb_id, uint64_t reinit_scope, uint64_t data);
 int64_t opal_pci_mask_pe_error(uint64_t phb_id, uint16_t pe_number, uint8_t error_type, uint8_t mask_action);
 int64_t opal_set_slot_led_status(uint64_t phb_id, uint64_t slot_id, uint8_t led_type, uint8_t led_action);
 int64_t opal_get_epow_status(__be64 *status);
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index ab91e6a34afa..a79fddc5e74e 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -344,6 +344,27 @@ static int powernv_eeh_next_error(struct eeh_pe **pe)
 	return -EEXIST;
 }
 
+static int powernv_eeh_restore_config(struct device_node *dn)
+{
+	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
+	struct pnv_phb *phb;
+	s64 ret;
+
+	if (!edev)
+		return -EEXIST;
+
+	phb = edev->phb->private_data;
+	ret = opal_pci_reinit(phb->opal_id,
+			      OPAL_REINIT_PCI_DEV, edev->config_addr);
+	if (ret) {
+		pr_warn("%s: Can't reinit PCI dev 0x%x (%lld)\n",
+			__func__, edev->config_addr, ret);
+		return -EIO;
+	}
+
+	return 0;
+}
+
 static struct eeh_ops powernv_eeh_ops = {
 	.name                   = "powernv",
 	.init                   = powernv_eeh_init,
@@ -360,7 +381,7 @@ static struct eeh_ops powernv_eeh_ops = {
 	.read_config            = pnv_pci_cfg_read,
 	.write_config           = pnv_pci_cfg_write,
 	.next_error		= powernv_eeh_next_error,
-	.restore_config		= NULL
+	.restore_config		= powernv_eeh_restore_config
 };
 
 /**
-- 
cgit v1.2.3


From bf16a4c2515ace64f08f7adb182ca147c5b01145 Mon Sep 17 00:00:00 2001
From: Vasant Hegde <hegdevasant@linux.vnet.ibm.com>
Date: Thu, 2 Jan 2014 17:00:42 +0530
Subject: powerpc/powernv: Increase candidate fw image size

At present we assume candidate image is <= 256MB. But in P8,
candidate image size can go up to 750MB. Hence increasing
candidate image max size to 1GB.

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 | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(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 4aeae4f36e1d..16e571ba4c60 100644
--- a/arch/powerpc/platforms/powernv/opal-flash.c
+++ b/arch/powerpc/platforms/powernv/opal-flash.c
@@ -76,8 +76,8 @@
 /* Validate buffer size */
 #define VALIDATE_BUF_SIZE	4096
 
-/* XXX: Assume candidate image size is <= 256MB */
-#define MAX_IMAGE_SIZE	0x10000000
+/* XXX: Assume candidate image size is <= 1GB */
+#define MAX_IMAGE_SIZE	0x40000000
 
 /* Flash sg list version */
 #define SG_LIST_VERSION (1UL)
-- 
cgit v1.2.3


From 7e4e7867b1e551b7b8f326da3604c47332972bc6 Mon Sep 17 00:00:00 2001
From: Gavin Shan <shangw@linux.vnet.ibm.com>
Date: Wed, 15 Jan 2014 13:16:11 +0800
Subject: powerpc/eeh: Handle multiple EEH errors

For one PCI error relevant OPAL event, we possibly have multiple
EEH errors for that. For example, multiple frozen PEs detected on
different PHBs. Unfortunately, we didn't cover the case. The patch
enumarates the return value from eeh_ops::next_error() and change
eeh_handle_special_event() and eeh_ops::next_error() to handle all
existing EEH errors.

As Ben pointed out, we needn't list_for_each_entry_safe() since we
are not deleting any PHB from the hose_list and the EEH serialized
lock should be held while purging EEH events. The patch covers those
suggestions as well.

Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/eeh.h            |  10 ++
 arch/powerpc/kernel/eeh_driver.c          | 150 ++++++++++++++++--------------
 arch/powerpc/platforms/powernv/eeh-ioda.c |  39 +++++---
 3 files changed, 112 insertions(+), 87 deletions(-)

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

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 8b4b8e4a5c32..9e39ceb1d19f 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -118,6 +118,16 @@ static inline struct pci_dev *eeh_dev_to_pci_dev(struct eeh_dev *edev)
 	return edev ? edev->pdev : NULL;
 }
 
+/* Return values from eeh_ops::next_error */
+enum {
+	EEH_NEXT_ERR_NONE = 0,
+	EEH_NEXT_ERR_INF,
+	EEH_NEXT_ERR_FROZEN_PE,
+	EEH_NEXT_ERR_FENCED_PHB,
+	EEH_NEXT_ERR_DEAD_PHB,
+	EEH_NEXT_ERR_DEAD_IOC
+};
+
 /*
  * The struct is used to trace the registered EEH operation
  * callback functions. Actually, those operation callback
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 7db39203a073..baa3b06e6dab 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -630,84 +630,90 @@ static void eeh_handle_special_event(void)
 {
 	struct eeh_pe *pe, *phb_pe;
 	struct pci_bus *bus;
-	struct pci_controller *hose, *tmp;
+	struct pci_controller *hose;
 	unsigned long flags;
-	int rc = 0;
+	int rc;
 
-	/*
-	 * The return value from next_error() has been classified as follows.
-	 * It might be good to enumerate them. However, next_error() is only
-	 * supported by PowerNV platform for now. So it would be fine to use
-	 * integer directly:
-	 *
-	 * 4 - Dead IOC           3 - Dead PHB
-	 * 2 - Fenced PHB         1 - Frozen PE
-	 * 0 - No error found
-	 *
-	 */
-	rc = eeh_ops->next_error(&pe);
-	if (rc <= 0)
-		return;
 
-	switch (rc) {
-	case 4:
-		/* Mark all PHBs in dead state */
-		eeh_serialize_lock(&flags);
-		list_for_each_entry_safe(hose, tmp,
-				&hose_list, list_node) {
-			phb_pe = eeh_phb_pe_get(hose);
-			if (!phb_pe) continue;
-
-			eeh_pe_state_mark(phb_pe,
-				EEH_PE_ISOLATED | EEH_PE_PHB_DEAD);
+	do {
+		rc = eeh_ops->next_error(&pe);
+
+		switch (rc) {
+		case EEH_NEXT_ERR_DEAD_IOC:
+			/* Mark all PHBs in dead state */
+			eeh_serialize_lock(&flags);
+
+			/* Purge all events */
+			eeh_remove_event(NULL);
+
+			list_for_each_entry(hose, &hose_list, list_node) {
+				phb_pe = eeh_phb_pe_get(hose);
+				if (!phb_pe) continue;
+
+				eeh_pe_state_mark(phb_pe,
+					EEH_PE_ISOLATED | EEH_PE_PHB_DEAD);
+			}
+
+			eeh_serialize_unlock(flags);
+
+			break;
+		case EEH_NEXT_ERR_FROZEN_PE:
+		case EEH_NEXT_ERR_FENCED_PHB:
+		case EEH_NEXT_ERR_DEAD_PHB:
+			/* Mark the PE in fenced state */
+			eeh_serialize_lock(&flags);
+
+			/* Purge all events of the PHB */
+			eeh_remove_event(pe);
+
+			if (rc == EEH_NEXT_ERR_DEAD_PHB)
+				eeh_pe_state_mark(pe,
+					EEH_PE_ISOLATED | EEH_PE_PHB_DEAD);
+			else
+				eeh_pe_state_mark(pe,
+					EEH_PE_ISOLATED | EEH_PE_RECOVERING);
+
+			eeh_serialize_unlock(flags);
+
+			break;
+		case EEH_NEXT_ERR_NONE:
+			return;
+		default:
+			pr_warn("%s: Invalid value %d from next_error()\n",
+				__func__, rc);
+			return;
 		}
-		eeh_serialize_unlock(flags);
-
-		/* Purge all events */
-		eeh_remove_event(NULL);
-		break;
-	case 3:
-	case 2:
-	case 1:
-		/* Mark the PE in fenced state */
-		eeh_serialize_lock(&flags);
-		if (rc == 3)
-			eeh_pe_state_mark(pe,
-				EEH_PE_ISOLATED | EEH_PE_PHB_DEAD);
-		else
-			eeh_pe_state_mark(pe,
-				EEH_PE_ISOLATED | EEH_PE_RECOVERING);
-		eeh_serialize_unlock(flags);
-
-		/* Purge all events of the PHB */
-		eeh_remove_event(pe);
-		break;
-	default:
-		pr_err("%s: Invalid value %d from next_error()\n",
-		       __func__, rc);
-		return;
-	}
 
-	/*
-	 * For fenced PHB and frozen PE, it's handled as normal
-	 * event. We have to remove the affected PHBs for dead
-	 * PHB and IOC
-	 */
-	if (rc == 2 || rc == 1)
-		eeh_handle_normal_event(pe);
-	else {
-		list_for_each_entry_safe(hose, tmp,
-			&hose_list, list_node) {
-			phb_pe = eeh_phb_pe_get(hose);
-			if (!phb_pe || !(phb_pe->state & EEH_PE_PHB_DEAD))
-				continue;
-
-			bus = eeh_pe_bus_get(phb_pe);
-			/* Notify all devices that they're about to go down. */
-			eeh_pe_dev_traverse(pe, eeh_report_failure, NULL);
-			pcibios_remove_pci_devices(bus);
+		/*
+		 * For fenced PHB and frozen PE, it's handled as normal
+		 * event. We have to remove the affected PHBs for dead
+		 * PHB and IOC
+		 */
+		if (rc == EEH_NEXT_ERR_FROZEN_PE ||
+		    rc == EEH_NEXT_ERR_FENCED_PHB) {
+			eeh_handle_normal_event(pe);
+		} else {
+			list_for_each_entry(hose, &hose_list, list_node) {
+				phb_pe = eeh_phb_pe_get(hose);
+				if (!phb_pe ||
+				    !(phb_pe->state & EEH_PE_PHB_DEAD))
+					continue;
+
+				/* Notify all devices to be down */
+				bus = eeh_pe_bus_get(phb_pe);
+				eeh_pe_dev_traverse(pe,
+					eeh_report_failure, NULL);
+				pcibios_remove_pci_devices(bus);
+			}
 		}
-	}
+
+		/*
+		 * If we have detected dead IOC, we needn't proceed
+		 * any more since all PHBs would have been removed
+		 */
+		if (rc == EEH_NEXT_ERR_DEAD_IOC)
+			break;
+	} while (rc != EEH_NEXT_ERR_NONE);
 }
 
 /**
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index 007ac4989841..8dd16f4675a2 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -735,12 +735,12 @@ static int ioda_eeh_get_pe(struct pci_controller *hose,
  */
 static int ioda_eeh_next_error(struct eeh_pe **pe)
 {
-	struct pci_controller *hose, *tmp;
+	struct pci_controller *hose;
 	struct pnv_phb *phb;
 	u64 frozen_pe_no;
 	u16 err_type, severity;
 	long rc;
-	int ret = 1;
+	int ret = EEH_NEXT_ERR_NONE;
 
 	/*
 	 * While running here, it's safe to purge the event queue.
@@ -750,7 +750,7 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 	eeh_remove_event(NULL);
 	opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul);
 
-	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+	list_for_each_entry(hose, &hose_list, list_node) {
 		/*
 		 * If the subordinate PCI buses of the PHB has been
 		 * removed, we needn't take care of it any more.
@@ -789,19 +789,19 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 		switch (err_type) {
 		case OPAL_EEH_IOC_ERROR:
 			if (severity == OPAL_EEH_SEV_IOC_DEAD) {
-				list_for_each_entry_safe(hose, tmp,
-						&hose_list, list_node) {
+				list_for_each_entry(hose, &hose_list,
+						    list_node) {
 					phb = hose->private_data;
 					phb->eeh_state |= PNV_EEH_STATE_REMOVED;
 				}
 
 				pr_err("EEH: dead IOC detected\n");
-				ret = 4;
-				goto out;
+				ret = EEH_NEXT_ERR_DEAD_IOC;
 			} else if (severity == OPAL_EEH_SEV_INF) {
 				pr_info("EEH: IOC informative error "
 					"detected\n");
 				ioda_eeh_hub_diag(hose);
+				ret = EEH_NEXT_ERR_NONE;
 			}
 
 			break;
@@ -813,21 +813,20 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 				pr_err("EEH: dead PHB#%x detected\n",
 					hose->global_number);
 				phb->eeh_state |= PNV_EEH_STATE_REMOVED;
-				ret = 3;
-				goto out;
+				ret = EEH_NEXT_ERR_DEAD_PHB;
 			} else if (severity == OPAL_EEH_SEV_PHB_FENCED) {
 				if (ioda_eeh_get_phb_pe(hose, pe))
 					break;
 
 				pr_err("EEH: fenced PHB#%x detected\n",
 					hose->global_number);
-				ret = 2;
-				goto out;
+				ret = EEH_NEXT_ERR_FENCED_PHB;
 			} else if (severity == OPAL_EEH_SEV_INF) {
 				pr_info("EEH: PHB#%x informative error "
 					"detected\n",
 					hose->global_number);
 				ioda_eeh_phb_diag(hose);
+				ret = EEH_NEXT_ERR_NONE;
 			}
 
 			break;
@@ -837,13 +836,23 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 
 			pr_err("EEH: Frozen PE#%x on PHB#%x detected\n",
 				(*pe)->addr, (*pe)->phb->global_number);
-			ret = 1;
-			goto out;
+			ret = EEH_NEXT_ERR_FROZEN_PE;
+			break;
+		default:
+			pr_warn("%s: Unexpected error type %d\n",
+				__func__, err_type);
 		}
+
+		/*
+		 * 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;
 	}
 
-	ret = 0;
-out:
 	return ret;
 }
 
-- 
cgit v1.2.3


From cb5b242c8c14a4b1dcd358400da28208fde78947 Mon Sep 17 00:00:00 2001
From: Gavin Shan <shangw@linux.vnet.ibm.com>
Date: Wed, 15 Jan 2014 13:16:13 +0800
Subject: powerpc/eeh: Escalate error on non-existing PE

Sometimes, especially in sinario of loading another kernel with kdump,
we got EEH error on non-existing PE. That means the PEEV / PEST in
the corresponding PHB would be messy and we can't handle that case.
The patch escalates the error to fenced PHB so that the PHB could be
rested in order to revoer the errors on non-existing PEs.

Reported-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Tested-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/powernv/eeh-ioda.c | 31 +++++++++++++++++++++----------
 1 file changed, 21 insertions(+), 10 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 8dd16f4675a2..e1e71618b70c 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -713,11 +713,7 @@ static int ioda_eeh_get_pe(struct pci_controller *hose,
 	dev.phb = hose;
 	dev.pe_config_addr = pe_no;
 	dev_pe = eeh_pe_get(&dev);
-	if (!dev_pe) {
-		pr_warning("%s: Can't find PE for PHB#%x - PE#%x\n",
-			   __func__, hose->global_number, pe_no);
-		return -EEXIST;
-	}
+	if (!dev_pe) return -EEXIST;
 
 	*pe = dev_pe;
 	return 0;
@@ -831,12 +827,27 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 
 			break;
 		case OPAL_EEH_PE_ERROR:
-			if (ioda_eeh_get_pe(hose, frozen_pe_no, pe))
-				break;
+			/*
+			 * If we can't find the corresponding PE, the
+			 * PEEV / PEST would be messy. So we force an
+			 * fenced PHB so that it can be recovered.
+			 */
+			if (ioda_eeh_get_pe(hose, frozen_pe_no, pe)) {
+				if (!ioda_eeh_get_phb_pe(hose, pe)) {
+					pr_err("EEH: Escalated fenced PHB#%x "
+					       "detected for PE#%llx\n",
+						hose->global_number,
+						frozen_pe_no);
+					ret = EEH_NEXT_ERR_FENCED_PHB;
+				} else {
+					ret = EEH_NEXT_ERR_NONE;
+				}
+			} else {
+				pr_err("EEH: Frozen PE#%x on PHB#%x detected\n",
+					(*pe)->addr, (*pe)->phb->global_number);
+				ret = EEH_NEXT_ERR_FROZEN_PE;
+			}
 
-			pr_err("EEH: Frozen PE#%x on PHB#%x detected\n",
-				(*pe)->addr, (*pe)->phb->global_number);
-			ret = EEH_NEXT_ERR_FROZEN_PE;
 			break;
 		default:
 			pr_warn("%s: Unexpected error type %d\n",
-- 
cgit v1.2.3


From f7d98d18a01ece2863984d4fb5ae949b18b02715 Mon Sep 17 00:00:00 2001
From: Vasant Hegde <hegdevasant@linux.vnet.ibm.com>
Date: Wed, 15 Jan 2014 17:02:04 +1100
Subject: powerpc/powernv: Call OPAL sync before kexec'ing

Its possible that OPAL may be writing to host memory during
kexec (like dump retrieve scenario). In this situation we might
end up corrupting host memory.

This patch makes OPAL sync call to make sure OPAL stops
writing to host memory before kexec'ing.

Signed-off-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-wrappers.S |  1 +
 arch/powerpc/platforms/powernv/opal.c          | 16 ++++++++++++++++
 arch/powerpc/platforms/powernv/setup.c         |  6 ++++--
 4 files changed, 23 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 9a87b4401a41..40157e2ca691 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -156,6 +156,7 @@ extern int opal_enter_rtas(struct rtas_args *args,
 #define OPAL_FLASH_UPDATE			78
 #define OPAL_GET_MSG				85
 #define OPAL_CHECK_ASYNC_COMPLETION		86
+#define OPAL_SYNC_HOST_REBOOT			87
 
 #ifndef __ASSEMBLY__
 
@@ -828,6 +829,7 @@ int64_t opal_update_flash(uint64_t blk_list);
 
 int64_t opal_get_msg(uint64_t buffer, size_t size);
 int64_t opal_check_completion(uint64_t buffer, size_t size, uint64_t token);
+int64_t opal_sync_host_reboot(void);
 
 /* Internal functions */
 extern int early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data);
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 719aa5c325c6..3e8829c40fbb 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -128,3 +128,4 @@ OPAL_CALL(opal_manage_flash,			OPAL_FLASH_MANAGE);
 OPAL_CALL(opal_update_flash,			OPAL_FLASH_UPDATE);
 OPAL_CALL(opal_get_msg,				OPAL_GET_MSG);
 OPAL_CALL(opal_check_completion,		OPAL_CHECK_ASYNC_COMPLETION);
+OPAL_CALL(opal_sync_host_reboot,		OPAL_SYNC_HOST_REBOOT);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 7a184a0ff183..65499adaecff 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -20,6 +20,7 @@
 #include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/kobject.h>
+#include <linux/delay.h>
 #include <asm/opal.h>
 #include <asm/firmware.h>
 #include <asm/mce.h>
@@ -482,10 +483,25 @@ subsys_initcall(opal_init);
 void opal_shutdown(void)
 {
 	unsigned int i;
+	long rc = OPAL_BUSY;
 
+	/* First free interrupts, which will also mask them */
 	for (i = 0; i < opal_irq_count; i++) {
 		if (opal_irqs[i])
 			free_irq(opal_irqs[i], NULL);
 		opal_irqs[i] = 0;
 	}
+
+	/*
+	 * Then sync with OPAL which ensure anything that can
+	 * potentially write to our memory has completed such
+	 * as an ongoing dump retrieval
+	 */
+	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+		rc = opal_sync_host_reboot();
+		if (rc == OPAL_BUSY)
+			opal_poll_events(NULL);
+		else
+			mdelay(10);
+	}
 }
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 19884b2a51b4..a932feb2901c 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -145,8 +145,10 @@ static void pnv_shutdown(void)
 	/* Let the PCI code clear up IODA tables */
 	pnv_pci_shutdown();
 
-	/* And unregister all OPAL interrupts so they don't fire
-	 * up while we kexec
+	/*
+	 * Stop OPAL activity: Unregister all OPAL interrupts so they
+	 * don't fire up while we kexec and make sure all potentially
+	 * DMA'ing ops are complete (such as dump retrieval).
 	 */
 	opal_shutdown();
 }
-- 
cgit v1.2.3