From c2ce6f9f3dc00daca5714ef070a9a2d4e78eb336 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Tue, 10 Feb 2015 09:51:22 +1100
Subject: powerpc: Change vrX register defines to vX to match gcc and glibc

As our various loops (copy, string, crypto etc) get more complicated,
we want to share implementations between userspace (eg glibc) and
the kernel. We also want to write userspace test harnesses to put
in tools/testing/selftest.

One gratuitous difference between userspace and the kernel is the
VMX register definitions - the kernel uses vrX whereas both gcc and
glibc use vX.

Change the kernel to match userspace.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/tm.S     |  8 ++++----
 arch/powerpc/kernel/vector.S | 24 ++++++++++++------------
 2 files changed, 16 insertions(+), 16 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 2a324f4cb1b9..5754b226da7e 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -152,9 +152,9 @@ _GLOBAL(tm_reclaim)
 
 	addi	r7, r3, THREAD_TRANSACT_VRSTATE
 	SAVE_32VRS(0, r6, r7)	/* r6 scratch, r7 transact vr state */
-	mfvscr	vr0
+	mfvscr	v0
 	li	r6, VRSTATE_VSCR
-	stvx	vr0, r7, r6
+	stvx	v0, r7, r6
 dont_backup_vec:
 	mfspr	r0, SPRN_VRSAVE
 	std	r0, THREAD_TRANSACT_VRSAVE(r3)
@@ -359,8 +359,8 @@ _GLOBAL(__tm_recheckpoint)
 
 	addi	r8, r3, THREAD_VRSTATE
 	li	r5, VRSTATE_VSCR
-	lvx	vr0, r8, r5
-	mtvscr	vr0
+	lvx	v0, r8, r5
+	mtvscr	v0
 	REST_32VRS(0, r5, r8)			/* r5 scratch, r8 ptr */
 dont_restore_vec:
 	ld	r5, THREAD_VRSAVE(r3)
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index 74f8050518d6..f5c80d567d8d 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -24,8 +24,8 @@ _GLOBAL(do_load_up_transact_altivec)
 	stw	r4,THREAD_USED_VR(r3)
 
 	li	r10,THREAD_TRANSACT_VRSTATE+VRSTATE_VSCR
-	lvx	vr0,r10,r3
-	mtvscr	vr0
+	lvx	v0,r10,r3
+	mtvscr	v0
 	addi	r10,r3,THREAD_TRANSACT_VRSTATE
 	REST_32VRS(0,r4,r10)
 
@@ -52,8 +52,8 @@ _GLOBAL(vec_enable)
  */
 _GLOBAL(load_vr_state)
 	li	r4,VRSTATE_VSCR
-	lvx	vr0,r4,r3
-	mtvscr	vr0
+	lvx	v0,r4,r3
+	mtvscr	v0
 	REST_32VRS(0,r4,r3)
 	blr
 
@@ -63,9 +63,9 @@ _GLOBAL(load_vr_state)
  */
 _GLOBAL(store_vr_state)
 	SAVE_32VRS(0, r4, r3)
-	mfvscr	vr0
+	mfvscr	v0
 	li	r4, VRSTATE_VSCR
-	stvx	vr0, r4, r3
+	stvx	v0, r4, r3
 	blr
 
 /*
@@ -104,9 +104,9 @@ _GLOBAL(load_up_altivec)
 	addi	r4,r4,THREAD
 	addi	r6,r4,THREAD_VRSTATE
 	SAVE_32VRS(0,r5,r6)
-	mfvscr	vr0
+	mfvscr	v0
 	li	r10,VRSTATE_VSCR
-	stvx	vr0,r10,r6
+	stvx	v0,r10,r6
 	/* Disable VMX for last_task_used_altivec */
 	PPC_LL	r5,PT_REGS(r4)
 	toreal(r5)
@@ -142,8 +142,8 @@ _GLOBAL(load_up_altivec)
 	li	r4,1
 	li	r10,VRSTATE_VSCR
 	stw	r4,THREAD_USED_VR(r5)
-	lvx	vr0,r10,r6
-	mtvscr	vr0
+	lvx	v0,r10,r6
+	mtvscr	v0
 	REST_32VRS(0,r4,r6)
 #ifndef CONFIG_SMP
 	/* Update last_task_used_altivec to 'current' */
@@ -186,9 +186,9 @@ _GLOBAL(giveup_altivec)
 	addi	r7,r3,THREAD_VRSTATE
 2:	PPC_LCMPI	0,r5,0
 	SAVE_32VRS(0,r4,r7)
-	mfvscr	vr0
+	mfvscr	v0
 	li	r4,VRSTATE_VSCR
-	stvx	vr0,r4,r7
+	stvx	v0,r4,r7
 	beq	1f
 	PPC_LL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
 #ifdef CONFIG_VSX
-- 
cgit v1.2.3


From 45706bb53d118b5340a12926e26444d73b6491f9 Mon Sep 17 00:00:00 2001
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Date: Fri, 19 Dec 2014 08:41:05 +0530
Subject: powerpc/book3s: Fix flush_tlb cpu_spec hook to take a generic
 argument.

The flush_tlb hook in cpu_spec was introduced as a generic function hook
to invalidate TLBs. But the current implementation of flush_tlb hook
takes IS (invalidation selector) as an argument which is architecture
dependent. Hence, It is not right to have a generic routine where caller
has to pass non-generic argument.

This patch fixes this and makes flush_tlb hook as high level API.

Reported-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/cpu_setup_power.S | 10 ++-----
 arch/powerpc/kernel/cputable.c        |  4 +--
 arch/powerpc/kernel/mce_power.c       | 53 +++++++++++++++++++++++++++++++++--
 3 files changed, 55 insertions(+), 12 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index 46733535cc0b..9c9b7411b28b 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -137,15 +137,11 @@ __init_HFSCR:
 /*
  * Clear the TLB using the specified IS form of tlbiel instruction
  * (invalidate by congruence class). P7 has 128 CCs., P8 has 512.
- *
- * r3 = IS field
  */
 __init_tlb_power7:
-	li	r3,0xc00	/* IS field = 0b11 */
-_GLOBAL(__flush_tlb_power7)
 	li	r6,128
 	mtctr	r6
-	mr	r7,r3		/* IS field */
+	li	r7,0xc00	/* IS field = 0b11 */
 	ptesync
 2:	tlbiel	r7
 	addi	r7,r7,0x1000
@@ -154,11 +150,9 @@ _GLOBAL(__flush_tlb_power7)
 1:	blr
 
 __init_tlb_power8:
-	li	r3,0xc00	/* IS field = 0b11 */
-_GLOBAL(__flush_tlb_power8)
 	li	r6,512
 	mtctr	r6
-	mr	r7,r3		/* IS field */
+	li	r7,0xc00	/* IS field = 0b11 */
 	ptesync
 2:	tlbiel	r7
 	addi	r7,r7,0x1000
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index f337666768a7..7ed126bc9b18 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -71,8 +71,8 @@ extern void __restore_cpu_power7(void);
 extern void __setup_cpu_power8(unsigned long offset, struct cpu_spec* spec);
 extern void __restore_cpu_power8(void);
 extern void __restore_cpu_a2(void);
-extern void __flush_tlb_power7(unsigned long inval_selector);
-extern void __flush_tlb_power8(unsigned long inval_selector);
+extern void __flush_tlb_power7(unsigned int action);
+extern void __flush_tlb_power8(unsigned int action);
 extern long __machine_check_early_realmode_p7(struct pt_regs *regs);
 extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
 #endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index b6f123ab90ed..2c647b1e62e4 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -28,6 +28,55 @@
 #include <asm/mce.h>
 #include <asm/machdep.h>
 
+static void flush_tlb_206(unsigned int num_sets, unsigned int action)
+{
+	unsigned long rb;
+	unsigned int i;
+
+	switch (action) {
+	case TLB_INVAL_SCOPE_GLOBAL:
+		rb = TLBIEL_INVAL_SET;
+		break;
+	case TLB_INVAL_SCOPE_LPID:
+		rb = TLBIEL_INVAL_SET_LPID;
+		break;
+	default:
+		BUG();
+		break;
+	}
+
+	asm volatile("ptesync" : : : "memory");
+	for (i = 0; i < num_sets; i++) {
+		asm volatile("tlbiel %0" : : "r" (rb));
+		rb += 1 << TLBIEL_INVAL_SET_SHIFT;
+	}
+	asm volatile("ptesync" : : : "memory");
+}
+
+/*
+ * Generic routine to flush TLB on power7. This routine is used as
+ * flush_tlb hook in cpu_spec for Power7 processor.
+ *
+ * action => TLB_INVAL_SCOPE_GLOBAL:  Invalidate all TLBs.
+ *	     TLB_INVAL_SCOPE_LPID: Invalidate TLB for current LPID.
+ */
+void __flush_tlb_power7(unsigned int action)
+{
+	flush_tlb_206(POWER7_TLB_SETS, action);
+}
+
+/*
+ * Generic routine to flush TLB on power8. This routine is used as
+ * flush_tlb hook in cpu_spec for power8 processor.
+ *
+ * action => TLB_INVAL_SCOPE_GLOBAL:  Invalidate all TLBs.
+ *	     TLB_INVAL_SCOPE_LPID: Invalidate TLB for current LPID.
+ */
+void __flush_tlb_power8(unsigned int action)
+{
+	flush_tlb_206(POWER8_TLB_SETS, action);
+}
+
 /* flush SLBs and reload */
 static void flush_and_reload_slb(void)
 {
@@ -79,7 +128,7 @@ static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits)
 	}
 	if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) {
 		if (cur_cpu_spec && cur_cpu_spec->flush_tlb)
-			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET);
+			cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_GLOBAL);
 		/* reset error bits */
 		dsisr &= ~P7_DSISR_MC_TLB_MULTIHIT_MFTLB;
 	}
@@ -110,7 +159,7 @@ static long mce_handle_common_ierror(uint64_t srr1)
 		break;
 	case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
 		if (cur_cpu_spec && cur_cpu_spec->flush_tlb) {
-			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET);
+			cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_GLOBAL);
 			handled = 1;
 		}
 		break;
-- 
cgit v1.2.3


From 28158cd1b75180343efa7c4d7d2f8e74ccc63b8f Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Wed, 11 Feb 2015 10:20:49 +1100
Subject: powerpc/eeh: Enhance pcibios_set_pcie_reset_state()

Function pcibios_set_pcie_reset_state() is possibly called by
pci_reset_function(), on which VFIO infrastructure depends to
issue reset. pcibios_set_pcie_reset_state() is issuing reset
on the parent PE of the indicated PCI device. The reset causes
state lost on all PCI devices except the indicated one as the
argument to pcibios_set_pcie_reset_state(). Also, sideband
MMIO access from guest when issuing reset would cause unexpected
EEH error.

For above two issues, the patch applies following enhancements
to pcibios_set_pcie_reset_state():

   * For all PCI devices except the indicated one, save their
     state prior to reset and restore state after that.
   * Explicitly freeze PE prior to reset and unfreeze it after
     that, in order to avoid unexpected EEH error.

Tested-by: Priya M. A <priyama2@in.ibm.com>
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/eeh.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 3b2252e7731b..19a897c810be 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -667,6 +667,55 @@ int eeh_pci_enable(struct eeh_pe *pe, int function)
 	return rc;
 }
 
+static void *eeh_disable_and_save_dev_state(void *data, void *userdata)
+{
+	struct eeh_dev *edev = data;
+	struct pci_dev *pdev = eeh_dev_to_pci_dev(edev);
+	struct pci_dev *dev = userdata;
+
+	/*
+	 * The caller should have disabled and saved the
+	 * state for the specified device
+	 */
+	if (!pdev || pdev == dev)
+		return NULL;
+
+	/* Ensure we have D0 power state */
+	pci_set_power_state(pdev, PCI_D0);
+
+	/* Save device state */
+	pci_save_state(pdev);
+
+	/*
+	 * Disable device to avoid any DMA traffic and
+	 * interrupt from the device
+	 */
+	pci_write_config_word(pdev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE);
+
+	return NULL;
+}
+
+static void *eeh_restore_dev_state(void *data, void *userdata)
+{
+	struct eeh_dev *edev = data;
+	struct device_node *dn = eeh_dev_to_of_node(edev);
+	struct pci_dev *pdev = eeh_dev_to_pci_dev(edev);
+	struct pci_dev *dev = userdata;
+
+	if (!pdev)
+		return NULL;
+
+	/* Apply customization from firmware */
+	if (dn && eeh_ops->restore_config)
+		eeh_ops->restore_config(dn);
+
+	/* The caller should restore state for the specified device */
+	if (pdev != dev)
+		pci_save_state(pdev);
+
+	return NULL;
+}
+
 /**
  * pcibios_set_pcie_slot_reset - Set PCI-E reset state
  * @dev: pci device struct
@@ -689,13 +738,19 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat
 	switch (state) {
 	case pcie_deassert_reset:
 		eeh_ops->reset(pe, EEH_RESET_DEACTIVATE);
+		eeh_unfreeze_pe(pe, false);
 		eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
+		eeh_pe_dev_traverse(pe, eeh_restore_dev_state, dev);
 		break;
 	case pcie_hot_reset:
+		eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE);
+		eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev);
 		eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 		eeh_ops->reset(pe, EEH_RESET_HOT);
 		break;
 	case pcie_warm_reset:
+		eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE);
+		eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev);
 		eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 		eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL);
 		break;
-- 
cgit v1.2.3


From 52d99627003278bcd1a40ea45136a8148d351531 Mon Sep 17 00:00:00 2001
From: Kevin Hao <haokexin@gmail.com>
Date: Thu, 12 Mar 2015 20:32:50 +0800
Subject: powerpc: kill PPC_OF

We have set CONFIG_PPC_OF to always 'y' in commit 0a498d96a332
("powerpc: set CONFIG_PPC_OF=y always for ARCH=powerpc") nine years
ago. And the arch/ppc also has gone away for many years. The OF
functionality was also moved to a common place and be used by many
archs. So it does make no sense to keep such a option in the current
kernel. Just kill it.

Signed-off-by: Kevin Hao <haokexin@gmail.com>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 502cf69b6c89..c1ebbdaac28f 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -33,7 +33,8 @@ obj-y				:= cputable.o ptrace.o syscalls.o \
 				   signal.o sysfs.o cacheinfo.o time.o \
 				   prom.o traps.o setup-common.o \
 				   udbg.o misc.o io.o dma.o \
-				   misc_$(CONFIG_WORD_SIZE).o vdso32/
+				   misc_$(CONFIG_WORD_SIZE).o vdso32/ \
+				   of_platform.o prom_parse.o
 obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
 				   signal_64.o ptrace32.o \
 				   paca.o nvram_64.o firmware.o
@@ -47,7 +48,6 @@ obj-$(CONFIG_PPC64)		+= vdso64/
 obj-$(CONFIG_ALTIVEC)		+= vecemu.o
 obj-$(CONFIG_PPC_970_NAP)	+= idle_power4.o
 obj-$(CONFIG_PPC_P7_NAP)	+= idle_power7.o
-obj-$(CONFIG_PPC_OF)		+= of_platform.o prom_parse.o
 procfs-y			:= proc_powerpc.o
 obj-$(CONFIG_PROC_FS)		+= $(procfs-y)
 rtaspci-$(CONFIG_PPC64)-$(CONFIG_PCI)	:= rtas_pci.o
-- 
cgit v1.2.3


From 6eca8933d3ff17bff39d5f10a2a22366d8622fa6 Mon Sep 17 00:00:00 2001
From: Alex Dowad <alexinbeijing@gmail.com>
Date: Fri, 13 Mar 2015 20:14:46 +0200
Subject: powerpc/kernel: Rename copy_thread() 'arg' argument to 'kthread_arg'

The 'arg' argument to copy_thread() is only ever used when forking a new
kernel thread. Hence, rename it to 'kthread_arg' for clarity.

Signed-off-by: Alex Dowad <alexinbeijing@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/process.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index b4cc7bef6b16..febb50dd5328 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1114,8 +1114,11 @@ static void setup_ksp_vsid(struct task_struct *p, unsigned long sp)
  */
 extern unsigned long dscr_default; /* defined in arch/powerpc/kernel/sysfs.c */
 
+/*
+ * Copy architecture-specific thread state
+ */
 int copy_thread(unsigned long clone_flags, unsigned long usp,
-		unsigned long arg, struct task_struct *p)
+		unsigned long kthread_arg, struct task_struct *p)
 {
 	struct pt_regs *childregs, *kregs;
 	extern void ret_from_fork(void);
@@ -1127,6 +1130,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	sp -= sizeof(struct pt_regs);
 	childregs = (struct pt_regs *) sp;
 	if (unlikely(p->flags & PF_KTHREAD)) {
+		/* kernel thread */
 		struct thread_info *ti = (void *)task_stack_page(p);
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->gpr[1] = sp + sizeof(struct pt_regs);
@@ -1137,11 +1141,12 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 		clear_tsk_thread_flag(p, TIF_32BIT);
 		childregs->softe = 1;
 #endif
-		childregs->gpr[15] = arg;
+		childregs->gpr[15] = kthread_arg;
 		p->thread.regs = NULL;	/* no user register state */
 		ti->flags |= _TIF_RESTOREALL;
 		f = ret_from_kernel_thread;
 	} else {
+		/* user thread */
 		struct pt_regs *regs = current_pt_regs();
 		CHECK_FULL_REGS(regs);
 		*childregs = *regs;
-- 
cgit v1.2.3


From 78989f0a5592182a3d45d869ddaafc71c8f673af Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.vnet.ibm.com>
Date: Fri, 6 Feb 2015 01:06:04 +0530
Subject: powerpc/nvram: Move generic code for nvram and pstore

With minor checks, we can move most of the code for nvram
under pseries to a common place to be re-used by other
powerpc platforms like powernv. This patch moves such
common code to arch/powerpc/kernel/nvram_64.c file.

Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
[mpe: Move select of ZLIB_DEFLATE to PPC64 to fix the build]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/nvram_64.c | 656 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 656 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index 34f7c9b7cd96..42e5c6a9c214 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -26,6 +26,9 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/kmsg_dump.h>
+#include <linux/pstore.h>
+#include <linux/zlib.h>
 #include <asm/uaccess.h>
 #include <asm/nvram.h>
 #include <asm/rtas.h>
@@ -54,6 +57,659 @@ struct nvram_partition {
 
 static LIST_HEAD(nvram_partitions);
 
+#ifdef CONFIG_PPC_PSERIES
+struct nvram_os_partition rtas_log_partition = {
+	.name = "ibm,rtas-log",
+	.req_size = 2079,
+	.min_size = 1055,
+	.index = -1,
+	.os_partition = true
+};
+#endif
+
+struct nvram_os_partition oops_log_partition = {
+	.name = "lnx,oops-log",
+	.req_size = 4000,
+	.min_size = 2000,
+	.index = -1,
+	.os_partition = true
+};
+
+static const char *nvram_os_partitions[] = {
+#ifdef CONFIG_PPC_PSERIES
+	"ibm,rtas-log",
+#endif
+	"lnx,oops-log",
+	NULL
+};
+
+static void oops_to_nvram(struct kmsg_dumper *dumper,
+			  enum kmsg_dump_reason reason);
+
+static struct kmsg_dumper nvram_kmsg_dumper = {
+	.dump = oops_to_nvram
+};
+
+/*
+ * For capturing and compressing an oops or panic report...
+
+ * big_oops_buf[] holds the uncompressed text we're capturing.
+ *
+ * oops_buf[] holds the compressed text, preceded by a oops header.
+ * oops header has u16 holding the version of oops header (to differentiate
+ * between old and new format header) followed by u16 holding the length of
+ * the compressed* text (*Or uncompressed, if compression fails.) and u64
+ * holding the timestamp. oops_buf[] gets written to NVRAM.
+ *
+ * oops_log_info points to the header. oops_data points to the compressed text.
+ *
+ * +- oops_buf
+ * |                                   +- oops_data
+ * v                                   v
+ * +-----------+-----------+-----------+------------------------+
+ * | version   | length    | timestamp | text                   |
+ * | (2 bytes) | (2 bytes) | (8 bytes) | (oops_data_sz bytes)   |
+ * +-----------+-----------+-----------+------------------------+
+ * ^
+ * +- oops_log_info
+ *
+ * We preallocate these buffers during init to avoid kmalloc during oops/panic.
+ */
+static size_t big_oops_buf_sz;
+static char *big_oops_buf, *oops_buf;
+static char *oops_data;
+static size_t oops_data_sz;
+
+/* Compression parameters */
+#define COMPR_LEVEL 6
+#define WINDOW_BITS 12
+#define MEM_LEVEL 4
+static struct z_stream_s stream;
+
+#ifdef CONFIG_PSTORE
+#ifdef CONFIG_PPC_PSERIES
+static struct nvram_os_partition of_config_partition = {
+	.name = "of-config",
+	.index = -1,
+	.os_partition = false
+};
+#endif
+
+static struct nvram_os_partition common_partition = {
+	.name = "common",
+	.index = -1,
+	.os_partition = false
+};
+
+static enum pstore_type_id nvram_type_ids[] = {
+	PSTORE_TYPE_DMESG,
+	PSTORE_TYPE_PPC_COMMON,
+	-1,
+	-1,
+	-1
+};
+static int read_type;
+#endif
+
+/* nvram_write_os_partition
+ *
+ * We need to buffer the error logs into nvram to ensure that we have
+ * the failure information to decode.  If we have a severe error there
+ * is no way to guarantee that the OS or the machine is in a state to
+ * get back to user land and write the error to disk.  For example if
+ * the SCSI device driver causes a Machine Check by writing to a bad
+ * IO address, there is no way of guaranteeing that the device driver
+ * is in any state that is would also be able to write the error data
+ * captured to disk, thus we buffer it in NVRAM for analysis on the
+ * next boot.
+ *
+ * In NVRAM the partition containing the error log buffer will looks like:
+ * Header (in bytes):
+ * +-----------+----------+--------+------------+------------------+
+ * | signature | checksum | length | name       | data             |
+ * |0          |1         |2      3|4         15|16        length-1|
+ * +-----------+----------+--------+------------+------------------+
+ *
+ * The 'data' section would look like (in bytes):
+ * +--------------+------------+-----------------------------------+
+ * | event_logged | sequence # | error log                         |
+ * |0            3|4          7|8                  error_log_size-1|
+ * +--------------+------------+-----------------------------------+
+ *
+ * event_logged: 0 if event has not been logged to syslog, 1 if it has
+ * sequence #: The unique sequence # for each event. (until it wraps)
+ * error log: The error log from event_scan
+ */
+int nvram_write_os_partition(struct nvram_os_partition *part,
+			     char *buff, int length,
+			     unsigned int err_type,
+			     unsigned int error_log_cnt)
+{
+	int rc;
+	loff_t tmp_index;
+	struct err_log_info info;
+
+	if (part->index == -1)
+		return -ESPIPE;
+
+	if (length > part->size)
+		length = part->size;
+
+	info.error_type = cpu_to_be32(err_type);
+	info.seq_num = cpu_to_be32(error_log_cnt);
+
+	tmp_index = part->index;
+
+	rc = ppc_md.nvram_write((char *)&info, sizeof(struct err_log_info),
+				&tmp_index);
+	if (rc <= 0) {
+		pr_err("%s: Failed nvram_write (%d)\n", __func__, rc);
+		return rc;
+	}
+
+	rc = ppc_md.nvram_write(buff, length, &tmp_index);
+	if (rc <= 0) {
+		pr_err("%s: Failed nvram_write (%d)\n", __func__, rc);
+		return rc;
+	}
+
+	return 0;
+}
+
+/* nvram_read_partition
+ *
+ * Reads nvram partition for at most 'length'
+ */
+int nvram_read_partition(struct nvram_os_partition *part, char *buff,
+			 int length, unsigned int *err_type,
+			 unsigned int *error_log_cnt)
+{
+	int rc;
+	loff_t tmp_index;
+	struct err_log_info info;
+
+	if (part->index == -1)
+		return -1;
+
+	if (length > part->size)
+		length = part->size;
+
+	tmp_index = part->index;
+
+	if (part->os_partition) {
+		rc = ppc_md.nvram_read((char *)&info,
+					sizeof(struct err_log_info),
+					&tmp_index);
+		if (rc <= 0) {
+			pr_err("%s: Failed nvram_read (%d)\n", __func__, rc);
+			return rc;
+		}
+	}
+
+	rc = ppc_md.nvram_read(buff, length, &tmp_index);
+	if (rc <= 0) {
+		pr_err("%s: Failed nvram_read (%d)\n", __func__, rc);
+		return rc;
+	}
+
+	if (part->os_partition) {
+		*error_log_cnt = be32_to_cpu(info.seq_num);
+		*err_type = be32_to_cpu(info.error_type);
+	}
+
+	return 0;
+}
+
+/* nvram_init_os_partition
+ *
+ * This sets up a partition with an "OS" signature.
+ *
+ * The general strategy is the following:
+ * 1.) If a partition with the indicated name already exists...
+ *	- If it's large enough, use it.
+ *	- Otherwise, recycle it and keep going.
+ * 2.) Search for a free partition that is large enough.
+ * 3.) If there's not a free partition large enough, recycle any obsolete
+ * OS partitions and try again.
+ * 4.) Will first try getting a chunk that will satisfy the requested size.
+ * 5.) If a chunk of the requested size cannot be allocated, then try finding
+ * a chunk that will satisfy the minum needed.
+ *
+ * Returns 0 on success, else -1.
+ */
+int __init nvram_init_os_partition(struct nvram_os_partition *part)
+{
+	loff_t p;
+	int size;
+
+	/* Look for ours */
+	p = nvram_find_partition(part->name, NVRAM_SIG_OS, &size);
+
+	/* Found one but too small, remove it */
+	if (p && size < part->min_size) {
+		pr_info("nvram: Found too small %s partition,"
+					" removing it...\n", part->name);
+		nvram_remove_partition(part->name, NVRAM_SIG_OS, NULL);
+		p = 0;
+	}
+
+	/* Create one if we didn't find */
+	if (!p) {
+		p = nvram_create_partition(part->name, NVRAM_SIG_OS,
+					part->req_size, part->min_size);
+		if (p == -ENOSPC) {
+			pr_info("nvram: No room to create %s partition, "
+				"deleting any obsolete OS partitions...\n",
+				part->name);
+			nvram_remove_partition(NULL, NVRAM_SIG_OS,
+					nvram_os_partitions);
+			p = nvram_create_partition(part->name, NVRAM_SIG_OS,
+					part->req_size, part->min_size);
+		}
+	}
+
+	if (p <= 0) {
+		pr_err("nvram: Failed to find or create %s"
+		       " partition, err %d\n", part->name, (int)p);
+		return -1;
+	}
+
+	part->index = p;
+	part->size = nvram_get_partition_size(p) - sizeof(struct err_log_info);
+
+	return 0;
+}
+
+/* Derived from logfs_compress() */
+static int nvram_compress(const void *in, void *out, size_t inlen,
+							size_t outlen)
+{
+	int err, ret;
+
+	ret = -EIO;
+	err = zlib_deflateInit2(&stream, COMPR_LEVEL, Z_DEFLATED, WINDOW_BITS,
+						MEM_LEVEL, Z_DEFAULT_STRATEGY);
+	if (err != Z_OK)
+		goto error;
+
+	stream.next_in = in;
+	stream.avail_in = inlen;
+	stream.total_in = 0;
+	stream.next_out = out;
+	stream.avail_out = outlen;
+	stream.total_out = 0;
+
+	err = zlib_deflate(&stream, Z_FINISH);
+	if (err != Z_STREAM_END)
+		goto error;
+
+	err = zlib_deflateEnd(&stream);
+	if (err != Z_OK)
+		goto error;
+
+	if (stream.total_out >= stream.total_in)
+		goto error;
+
+	ret = stream.total_out;
+error:
+	return ret;
+}
+
+/* Compress the text from big_oops_buf into oops_buf. */
+static int zip_oops(size_t text_len)
+{
+	struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf;
+	int zipped_len = nvram_compress(big_oops_buf, oops_data, text_len,
+								oops_data_sz);
+	if (zipped_len < 0) {
+		pr_err("nvram: compression failed; returned %d\n", zipped_len);
+		pr_err("nvram: logging uncompressed oops/panic report\n");
+		return -1;
+	}
+	oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
+	oops_hdr->report_length = cpu_to_be16(zipped_len);
+	oops_hdr->timestamp = cpu_to_be64(get_seconds());
+	return 0;
+}
+
+#ifdef CONFIG_PSTORE
+static int nvram_pstore_open(struct pstore_info *psi)
+{
+	/* Reset the iterator to start reading partitions again */
+	read_type = -1;
+	return 0;
+}
+
+/**
+ * nvram_pstore_write - pstore write callback for nvram
+ * @type:               Type of message logged
+ * @reason:             reason behind dump (oops/panic)
+ * @id:                 identifier to indicate the write performed
+ * @part:               pstore writes data to registered buffer in parts,
+ *                      part number will indicate the same.
+ * @count:              Indicates oops count
+ * @compressed:         Flag to indicate the log is compressed
+ * @size:               number of bytes written to the registered buffer
+ * @psi:                registered pstore_info structure
+ *
+ * Called by pstore_dump() when an oops or panic report is logged in the
+ * printk buffer.
+ * Returns 0 on successful write.
+ */
+static int nvram_pstore_write(enum pstore_type_id type,
+				enum kmsg_dump_reason reason,
+				u64 *id, unsigned int part, int count,
+				bool compressed, size_t size,
+				struct pstore_info *psi)
+{
+	int rc;
+	unsigned int err_type = ERR_TYPE_KERNEL_PANIC;
+	struct oops_log_info *oops_hdr = (struct oops_log_info *) oops_buf;
+
+	/* part 1 has the recent messages from printk buffer */
+	if (part > 1 || (type != PSTORE_TYPE_DMESG))
+		return -1;
+
+	if (clobbering_unread_rtas_event())
+		return -1;
+
+	oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
+	oops_hdr->report_length = cpu_to_be16(size);
+	oops_hdr->timestamp = cpu_to_be64(get_seconds());
+
+	if (compressed)
+		err_type = ERR_TYPE_KERNEL_PANIC_GZ;
+
+	rc = nvram_write_os_partition(&oops_log_partition, oops_buf,
+		(int) (sizeof(*oops_hdr) + size), err_type, count);
+
+	if (rc != 0)
+		return rc;
+
+	*id = part;
+	return 0;
+}
+
+/*
+ * Reads the oops/panic report, rtas, of-config and common partition.
+ * Returns the length of the data we read from each partition.
+ * Returns 0 if we've been called before.
+ */
+static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
+				int *count, struct timespec *time, char **buf,
+				bool *compressed, struct pstore_info *psi)
+{
+	struct oops_log_info *oops_hdr;
+	unsigned int err_type, id_no, size = 0;
+	struct nvram_os_partition *part = NULL;
+	char *buff = NULL;
+	int sig = 0;
+	loff_t p;
+
+	read_type++;
+
+	switch (nvram_type_ids[read_type]) {
+	case PSTORE_TYPE_DMESG:
+		part = &oops_log_partition;
+		*type = PSTORE_TYPE_DMESG;
+		break;
+	case PSTORE_TYPE_PPC_COMMON:
+		sig = NVRAM_SIG_SYS;
+		part = &common_partition;
+		*type = PSTORE_TYPE_PPC_COMMON;
+		*id = PSTORE_TYPE_PPC_COMMON;
+		time->tv_sec = 0;
+		time->tv_nsec = 0;
+		break;
+#ifdef CONFIG_PPC_PSERIES
+	case PSTORE_TYPE_PPC_RTAS:
+		part = &rtas_log_partition;
+		*type = PSTORE_TYPE_PPC_RTAS;
+		time->tv_sec = last_rtas_event;
+		time->tv_nsec = 0;
+		break;
+	case PSTORE_TYPE_PPC_OF:
+		sig = NVRAM_SIG_OF;
+		part = &of_config_partition;
+		*type = PSTORE_TYPE_PPC_OF;
+		*id = PSTORE_TYPE_PPC_OF;
+		time->tv_sec = 0;
+		time->tv_nsec = 0;
+		break;
+#endif
+	default:
+		return 0;
+	}
+
+	if (!part->os_partition) {
+		p = nvram_find_partition(part->name, sig, &size);
+		if (p <= 0) {
+			pr_err("nvram: Failed to find partition %s, "
+				"err %d\n", part->name, (int)p);
+			return 0;
+		}
+		part->index = p;
+		part->size = size;
+	}
+
+	buff = kmalloc(part->size, GFP_KERNEL);
+
+	if (!buff)
+		return -ENOMEM;
+
+	if (nvram_read_partition(part, buff, part->size, &err_type, &id_no)) {
+		kfree(buff);
+		return 0;
+	}
+
+	*count = 0;
+
+	if (part->os_partition)
+		*id = id_no;
+
+	if (nvram_type_ids[read_type] == PSTORE_TYPE_DMESG) {
+		size_t length, hdr_size;
+
+		oops_hdr = (struct oops_log_info *)buff;
+		if (be16_to_cpu(oops_hdr->version) < OOPS_HDR_VERSION) {
+			/* Old format oops header had 2-byte record size */
+			hdr_size = sizeof(u16);
+			length = be16_to_cpu(oops_hdr->version);
+			time->tv_sec = 0;
+			time->tv_nsec = 0;
+		} else {
+			hdr_size = sizeof(*oops_hdr);
+			length = be16_to_cpu(oops_hdr->report_length);
+			time->tv_sec = be64_to_cpu(oops_hdr->timestamp);
+			time->tv_nsec = 0;
+		}
+		*buf = kmalloc(length, GFP_KERNEL);
+		if (*buf == NULL)
+			return -ENOMEM;
+		memcpy(*buf, buff + hdr_size, length);
+		kfree(buff);
+
+		if (err_type == ERR_TYPE_KERNEL_PANIC_GZ)
+			*compressed = true;
+		else
+			*compressed = false;
+		return length;
+	}
+
+	*buf = buff;
+	return part->size;
+}
+
+static struct pstore_info nvram_pstore_info = {
+	.owner = THIS_MODULE,
+	.name = "nvram",
+	.open = nvram_pstore_open,
+	.read = nvram_pstore_read,
+	.write = nvram_pstore_write,
+};
+
+static int nvram_pstore_init(void)
+{
+	int rc = 0;
+
+	nvram_type_ids[2] = PSTORE_TYPE_PPC_RTAS;
+	nvram_type_ids[3] = PSTORE_TYPE_PPC_OF;
+
+	nvram_pstore_info.buf = oops_data;
+	nvram_pstore_info.bufsize = oops_data_sz;
+
+	spin_lock_init(&nvram_pstore_info.buf_lock);
+
+	rc = pstore_register(&nvram_pstore_info);
+	if (rc != 0)
+		pr_err("nvram: pstore_register() failed, defaults to "
+				"kmsg_dump; returned %d\n", rc);
+
+	return rc;
+}
+#else
+static int nvram_pstore_init(void)
+{
+	return -1;
+}
+#endif
+
+void __init nvram_init_oops_partition(int rtas_partition_exists)
+{
+	int rc;
+
+	rc = nvram_init_os_partition(&oops_log_partition);
+	if (rc != 0) {
+#ifdef CONFIG_PPC_PSERIES
+		if (!rtas_partition_exists) {
+			pr_err("nvram: Failed to initialize oops partition!");
+			return;
+		}
+		pr_notice("nvram: Using %s partition to log both"
+			" RTAS errors and oops/panic reports\n",
+			rtas_log_partition.name);
+		memcpy(&oops_log_partition, &rtas_log_partition,
+						sizeof(rtas_log_partition));
+#else
+		pr_err("nvram: Failed to initialize oops partition!");
+		return;
+#endif
+	}
+	oops_buf = kmalloc(oops_log_partition.size, GFP_KERNEL);
+	if (!oops_buf) {
+		pr_err("nvram: No memory for %s partition\n",
+						oops_log_partition.name);
+		return;
+	}
+	oops_data = oops_buf + sizeof(struct oops_log_info);
+	oops_data_sz = oops_log_partition.size - sizeof(struct oops_log_info);
+
+	rc = nvram_pstore_init();
+
+	if (!rc)
+		return;
+
+	/*
+	 * Figure compression (preceded by elimination of each line's <n>
+	 * severity prefix) will reduce the oops/panic report to at most
+	 * 45% of its original size.
+	 */
+	big_oops_buf_sz = (oops_data_sz * 100) / 45;
+	big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL);
+	if (big_oops_buf) {
+		stream.workspace =  kmalloc(zlib_deflate_workspacesize(
+					WINDOW_BITS, MEM_LEVEL), GFP_KERNEL);
+		if (!stream.workspace) {
+			pr_err("nvram: No memory for compression workspace; "
+				"skipping compression of %s partition data\n",
+				oops_log_partition.name);
+			kfree(big_oops_buf);
+			big_oops_buf = NULL;
+		}
+	} else {
+		pr_err("No memory for uncompressed %s data; "
+			"skipping compression\n", oops_log_partition.name);
+		stream.workspace = NULL;
+	}
+
+	rc = kmsg_dump_register(&nvram_kmsg_dumper);
+	if (rc != 0) {
+		pr_err("nvram: kmsg_dump_register() failed; returned %d\n", rc);
+		kfree(oops_buf);
+		kfree(big_oops_buf);
+		kfree(stream.workspace);
+	}
+}
+
+/*
+ * This is our kmsg_dump callback, called after an oops or panic report
+ * has been written to the printk buffer.  We want to capture as much
+ * of the printk buffer as possible.  First, capture as much as we can
+ * that we think will compress sufficiently to fit in the lnx,oops-log
+ * partition.  If that's too much, go back and capture uncompressed text.
+ */
+static void oops_to_nvram(struct kmsg_dumper *dumper,
+			  enum kmsg_dump_reason reason)
+{
+	struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf;
+	static unsigned int oops_count = 0;
+	static bool panicking = false;
+	static DEFINE_SPINLOCK(lock);
+	unsigned long flags;
+	size_t text_len;
+	unsigned int err_type = ERR_TYPE_KERNEL_PANIC_GZ;
+	int rc = -1;
+
+	switch (reason) {
+	case KMSG_DUMP_RESTART:
+	case KMSG_DUMP_HALT:
+	case KMSG_DUMP_POWEROFF:
+		/* These are almost always orderly shutdowns. */
+		return;
+	case KMSG_DUMP_OOPS:
+		break;
+	case KMSG_DUMP_PANIC:
+		panicking = true;
+		break;
+	case KMSG_DUMP_EMERG:
+		if (panicking)
+			/* Panic report already captured. */
+			return;
+		break;
+	default:
+		pr_err("%s: ignoring unrecognized KMSG_DUMP_* reason %d\n",
+		       __func__, (int) reason);
+		return;
+	}
+
+	if (clobbering_unread_rtas_event())
+		return;
+
+	if (!spin_trylock_irqsave(&lock, flags))
+		return;
+
+	if (big_oops_buf) {
+		kmsg_dump_get_buffer(dumper, false,
+				     big_oops_buf, big_oops_buf_sz, &text_len);
+		rc = zip_oops(text_len);
+	}
+	if (rc != 0) {
+		kmsg_dump_rewind(dumper);
+		kmsg_dump_get_buffer(dumper, false,
+				     oops_data, oops_data_sz, &text_len);
+		err_type = ERR_TYPE_KERNEL_PANIC;
+		oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
+		oops_hdr->report_length = cpu_to_be16(text_len);
+		oops_hdr->timestamp = cpu_to_be64(get_seconds());
+	}
+
+	(void) nvram_write_os_partition(&oops_log_partition, oops_buf,
+		(int) (sizeof(*oops_hdr) + text_len), err_type,
+		++oops_count);
+
+	spin_unlock_irqrestore(&lock, flags);
+}
+
 static loff_t dev_nvram_llseek(struct file *file, loff_t offset, int origin)
 {
 	int size;
-- 
cgit v1.2.3


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

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

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

Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/nvram_64.c | 25 +++++++++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index 42e5c6a9c214..293da889055b 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -127,6 +127,14 @@ static size_t oops_data_sz;
 static struct z_stream_s stream;
 
 #ifdef CONFIG_PSTORE
+#ifdef CONFIG_PPC_POWERNV
+static struct nvram_os_partition skiboot_partition = {
+	.name = "ibm,skiboot",
+	.index = -1,
+	.os_partition = false
+};
+#endif
+
 #ifdef CONFIG_PPC_PSERIES
 static struct nvram_os_partition of_config_partition = {
 	.name = "of-config",
@@ -476,6 +484,16 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
 		time->tv_sec = 0;
 		time->tv_nsec = 0;
 		break;
+#endif
+#ifdef CONFIG_PPC_POWERNV
+	case PSTORE_TYPE_PPC_OPAL:
+		sig = NVRAM_SIG_FW;
+		part = &skiboot_partition;
+		*type = PSTORE_TYPE_PPC_OPAL;
+		*id = PSTORE_TYPE_PPC_OPAL;
+		time->tv_sec = 0;
+		time->tv_nsec = 0;
+		break;
 #endif
 	default:
 		return 0;
@@ -552,8 +570,11 @@ static int nvram_pstore_init(void)
 {
 	int rc = 0;
 
-	nvram_type_ids[2] = PSTORE_TYPE_PPC_RTAS;
-	nvram_type_ids[3] = PSTORE_TYPE_PPC_OF;
+	if (machine_is(pseries)) {
+		nvram_type_ids[2] = PSTORE_TYPE_PPC_RTAS;
+		nvram_type_ids[3] = PSTORE_TYPE_PPC_OF;
+	} else
+		nvram_type_ids[2] = PSTORE_TYPE_PPC_OPAL;
 
 	nvram_pstore_info.buf = oops_data;
 	nvram_pstore_info.bufsize = oops_data_sz;
-- 
cgit v1.2.3


From e4a9616c548f67537a8d020a45a327f6a4d583ee Mon Sep 17 00:00:00 2001
From: Hari Bathini <hbathini@linux.vnet.ibm.com>
Date: Fri, 6 Feb 2015 01:07:17 +0530
Subject: powerpc/rtas: Make timestamp related code y2038-safe

While we are here, let us make timestamp related code y2038-safe.

Suggested-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/nvram_64.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index 293da889055b..1e703f8ebad4 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -376,7 +376,7 @@ static int zip_oops(size_t text_len)
 	}
 	oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
 	oops_hdr->report_length = cpu_to_be16(zipped_len);
-	oops_hdr->timestamp = cpu_to_be64(get_seconds());
+	oops_hdr->timestamp = cpu_to_be64(ktime_get_real_seconds());
 	return 0;
 }
 
@@ -423,7 +423,7 @@ static int nvram_pstore_write(enum pstore_type_id type,
 
 	oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
 	oops_hdr->report_length = cpu_to_be16(size);
-	oops_hdr->timestamp = cpu_to_be64(get_seconds());
+	oops_hdr->timestamp = cpu_to_be64(ktime_get_real_seconds());
 
 	if (compressed)
 		err_type = ERR_TYPE_KERNEL_PANIC_GZ;
@@ -721,7 +721,7 @@ static void oops_to_nvram(struct kmsg_dumper *dumper,
 		err_type = ERR_TYPE_KERNEL_PANIC;
 		oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
 		oops_hdr->report_length = cpu_to_be16(text_len);
-		oops_hdr->timestamp = cpu_to_be64(get_seconds());
+		oops_hdr->timestamp = cpu_to_be64(ktime_get_real_seconds());
 	}
 
 	(void) nvram_write_os_partition(&oops_log_partition, oops_buf,
-- 
cgit v1.2.3


From f57333a7677750f1264341d57bf1771000330458 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Fri, 20 Mar 2015 10:10:18 +1100
Subject: powerpc/powernv: Fix return value from power7_nap() et al.

The power7_nap(), power7_sleep() and power7_winkle() functions are
called from pnv_smp_cpu_kill_self(), which expects them to return the
SRR1 value set by the hardware on wakeup, or 0 if no nap/sleep/winkle
occurred.  However, in the case where an interrupt needs to be
replayed, the logic in power7_powersave_common (the common code for
power7_nap et al.) doesn't set r3 to 0 in this case.  Instead what we
get as the return value is the selector for the type of power-saving
mode requested (1, 2 or 3).  In fact this should not affect the
operation of pnv_smp_cpu_kill_self(), but it is better to get this
correct, so this adds an instruction to set r3 to 0 in this case.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/idle_power7.S | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index 05adc8bbdef8..eeaa0d5f69d5 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -94,6 +94,7 @@ _GLOBAL(power7_powersave_common)
 	beq	1f
 	addi	r1,r1,INT_FRAME_SIZE
 	ld	r0,16(r1)
+	li	r3,0			/* Return 0 (no nap) */
 	mtlr	r0
 	blr
 
-- 
cgit v1.2.3


From cca87d303c85b257a7b0fd34f9d6fce1c59880a2 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Tue, 17 Mar 2015 16:15:02 +1100
Subject: powerpc/pci: Refactor pci_dn

Currently, the PCI config accessors are implemented based on device node.
Unfortunately, SRIOV VFs won't have the corresponding device nodes. pci_dn
will be used in replacement with device node for SRIOV VFs. So we have to
use pci_dn in PCI config accessors.

The patch refactors pci_dn in following aspects to make it ready to be used
in PCI config accessors as we do in subsequent patch:

   * pci_dn is organized as a hierarchy tree.  PCI device's pci_dn is
     put to the child list of pci_dn of its upstream bridge or PHB. VF's
     pci_dn will be put to the child list of pci_dn of PF's bridge.

   * For one particular PCI device (VF or not), its pci_dn can be
     found from pdev->dev.archdata.pci_data, PCI_DN(devnode), or
     parent's list.  The fast path (fetching pci_dn through PCI device
     instance) is populated during early fixup time.

[bhelgaas: changelog]
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/pci_dn.c | 130 +++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 126 insertions(+), 4 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index 83df3075d3df..0ab2dadaf842 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -32,12 +32,108 @@
 #include <asm/ppc-pci.h>
 #include <asm/firmware.h>
 
+/*
+ * The function is used to find the firmware data of one
+ * specific PCI device, which is attached to the indicated
+ * PCI bus. For VFs, their firmware data is linked to that
+ * one of PF's bridge. For other devices, their firmware
+ * data is linked to that of their bridge.
+ */
+static struct pci_dn *pci_bus_to_pdn(struct pci_bus *bus)
+{
+	struct pci_bus *pbus;
+	struct device_node *dn;
+	struct pci_dn *pdn;
+
+	/*
+	 * We probably have virtual bus which doesn't
+	 * have associated bridge.
+	 */
+	pbus = bus;
+	while (pbus) {
+		if (pci_is_root_bus(pbus) || pbus->self)
+			break;
+
+		pbus = pbus->parent;
+	}
+
+	/*
+	 * Except virtual bus, all PCI buses should
+	 * have device nodes.
+	 */
+	dn = pci_bus_to_OF_node(pbus);
+	pdn = dn ? PCI_DN(dn) : NULL;
+
+	return pdn;
+}
+
+struct pci_dn *pci_get_pdn_by_devfn(struct pci_bus *bus,
+				    int devfn)
+{
+	struct device_node *dn = NULL;
+	struct pci_dn *parent, *pdn;
+	struct pci_dev *pdev = NULL;
+
+	/* Fast path: fetch from PCI device */
+	list_for_each_entry(pdev, &bus->devices, bus_list) {
+		if (pdev->devfn == devfn) {
+			if (pdev->dev.archdata.pci_data)
+				return pdev->dev.archdata.pci_data;
+
+			dn = pci_device_to_OF_node(pdev);
+			break;
+		}
+	}
+
+	/* Fast path: fetch from device node */
+	pdn = dn ? PCI_DN(dn) : NULL;
+	if (pdn)
+		return pdn;
+
+	/* Slow path: fetch from firmware data hierarchy */
+	parent = pci_bus_to_pdn(bus);
+	if (!parent)
+		return NULL;
+
+	list_for_each_entry(pdn, &parent->child_list, list) {
+		if (pdn->busno == bus->number &&
+                    pdn->devfn == devfn)
+                        return pdn;
+        }
+
+	return NULL;
+}
+
 struct pci_dn *pci_get_pdn(struct pci_dev *pdev)
 {
-	struct device_node *dn = pci_device_to_OF_node(pdev);
-	if (!dn)
+	struct device_node *dn;
+	struct pci_dn *parent, *pdn;
+
+	/* Search device directly */
+	if (pdev->dev.archdata.pci_data)
+		return pdev->dev.archdata.pci_data;
+
+	/* Check device node */
+	dn = pci_device_to_OF_node(pdev);
+	pdn = dn ? PCI_DN(dn) : NULL;
+	if (pdn)
+		return pdn;
+
+	/*
+	 * VFs don't have device nodes. We hook their
+	 * firmware data to PF's bridge.
+	 */
+	parent = pci_bus_to_pdn(pdev->bus);
+	if (!parent)
 		return NULL;
-	return PCI_DN(dn);
+
+	list_for_each_entry(pdn, &parent->child_list, list) {
+		if (pdn->busno == pdev->bus->number &&
+		    pdn->devfn == pdev->devfn)
+			return pdn;
+	}
+
+	return NULL;
 }
 
 /*
@@ -49,6 +145,7 @@ void *update_dn_pci_info(struct device_node *dn, void *data)
 	struct pci_controller *phb = data;
 	const __be32 *type = of_get_property(dn, "ibm,pci-config-space-type", NULL);
 	const __be32 *regs;
+	struct device_node *parent;
 	struct pci_dn *pdn;
 
 	pdn = zalloc_maybe_bootmem(sizeof(*pdn), GFP_KERNEL);
@@ -70,6 +167,15 @@ void *update_dn_pci_info(struct device_node *dn, void *data)
 	}
 
 	pdn->pci_ext_config_space = (type && of_read_number(type, 1) == 1);
+
+	/* Attach to parent node */
+	INIT_LIST_HEAD(&pdn->child_list);
+	INIT_LIST_HEAD(&pdn->list);
+	parent = of_get_parent(dn);
+	pdn->parent = parent ? PCI_DN(parent) : NULL;
+	if (pdn->parent)
+		list_add_tail(&pdn->list, &pdn->parent->child_list);
+
 	return NULL;
 }
 
@@ -147,8 +253,11 @@ void pci_devs_phb_init_dynamic(struct pci_controller *phb)
 	/* PHB nodes themselves must not match */
 	update_dn_pci_info(dn, phb);
 	pdn = dn->data;
-	if (pdn)
+	if (pdn) {
 		pdn->devfn = pdn->busno = -1;
+		pdn->phb = phb;
+		phb->pci_data = pdn;
+	}
 
 	/* Update dn->phb ptrs for new phb and children devices */
 	traverse_pci_devices(dn, update_dn_pci_info, phb);
@@ -171,3 +280,16 @@ void __init pci_devs_phb_init(void)
 	list_for_each_entry_safe(phb, tmp, &hose_list, list_node)
 		pci_devs_phb_init_dynamic(phb);
 }
+
+static void pci_dev_pdn_setup(struct pci_dev *pdev)
+{
+	struct pci_dn *pdn;
+
+	if (pdev->dev.archdata.pci_data)
+		return;
+
+	/* Setup the fast path */
+	pdn = pci_get_pdn(pdev);
+	pdev->dev.archdata.pci_data = pdn;
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_ANY_ID, PCI_ANY_ID, pci_dev_pdn_setup);
-- 
cgit v1.2.3


From c035ff1d2eaa03ab40839041e955a86a8e412eb4 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Tue, 17 Mar 2015 16:15:04 +1100
Subject: powerpc/pci: Trace more information from pci_dn

Originally, EEH probes on device_node or pci_dev and populates the
corresponding eeh_dev. In the subsequent patches, EEH will probes
on pci_dn and populates the corresponding eeh_dev. So we have to
cache some information in pci_dn, either from device_node or SRIOV
PF's enablement platform hook, to populate the eeh_dev properly.

The motivation to probe pci_dn, instead of device node or pci_dev,
to populate eeh_dev is SRIOV VFs are dynamically created and we
don't have the corresponding device nodes for them.

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/pci_dn.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index 0ab2dadaf842..d139f72ff9d5 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -166,6 +166,15 @@ void *update_dn_pci_info(struct device_node *dn, void *data)
 		pdn->devfn = (addr >> 8) & 0xff;
 	}
 
+	/* vendor/device IDs and class code */
+	regs = of_get_property(dn, "vendor-id", NULL);
+	pdn->vendor_id = regs ? of_read_number(regs, 1) : 0;
+	regs = of_get_property(dn, "device-id", NULL);
+	pdn->device_id = regs ? of_read_number(regs, 1) : 0;
+	regs = of_get_property(dn, "class-code", NULL);
+	pdn->class_code = regs ? of_read_number(regs, 1) : 0;
+
+	/* Extended config space */
 	pdn->pci_ext_config_space = (type && of_read_number(type, 1) == 1);
 
 	/* Attach to parent node */
@@ -255,6 +264,7 @@ void pci_devs_phb_init_dynamic(struct pci_controller *phb)
 	pdn = dn->data;
 	if (pdn) {
 		pdn->devfn = pdn->busno = -1;
+		pdn->vendor_id = pdn->device_id = pdn->class_code = 0;
 		pdn->phb = phb;
 		phb->pci_data = pdn;
 	}
-- 
cgit v1.2.3


From e8e9b34cef237d4d6fdc0d350cd8a95d1adb9ee9 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Tue, 17 Mar 2015 16:15:05 +1100
Subject: powerpc/eeh: Create eeh_dev from pci_dn instead of device_node

The patch adds function traverse_pci_dn(), which is similar to
traverse_pci_devices() except it takes pci_dn, not device_node
as parameter. The pci_dev.c has been reworked to create eeh_dev
from pci_dn, instead of device_node.

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/eeh_dev.c | 14 +++++++-------
 arch/powerpc/kernel/pci_dn.c  | 40 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 47 insertions(+), 7 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/eeh_dev.c b/arch/powerpc/kernel/eeh_dev.c
index e5274ee9a75f..aabba94ff9cb 100644
--- a/arch/powerpc/kernel/eeh_dev.c
+++ b/arch/powerpc/kernel/eeh_dev.c
@@ -43,13 +43,13 @@
 
 /**
  * eeh_dev_init - Create EEH device according to OF node
- * @dn: device node
+ * @pdn: PCI device node
  * @data: PHB
  *
  * It will create EEH device according to the given OF node. The function
  * might be called by PCI emunation, DR, PHB hotplug.
  */
-void *eeh_dev_init(struct device_node *dn, void *data)
+void *eeh_dev_init(struct pci_dn *pdn, void *data)
 {
 	struct pci_controller *phb = data;
 	struct eeh_dev *edev;
@@ -63,8 +63,8 @@ void *eeh_dev_init(struct device_node *dn, void *data)
 	}
 
 	/* Associate EEH device with OF node */
-	PCI_DN(dn)->edev = edev;
-	edev->dn  = dn;
+	pdn->edev = edev;
+	edev->pdn = pdn;
 	edev->phb = phb;
 	INIT_LIST_HEAD(&edev->list);
 
@@ -80,16 +80,16 @@ void *eeh_dev_init(struct device_node *dn, void *data)
  */
 void eeh_dev_phb_init_dynamic(struct pci_controller *phb)
 {
-	struct device_node *dn = phb->dn;
+	struct pci_dn *root = phb->pci_data;
 
 	/* EEH PE for PHB */
 	eeh_phb_pe_create(phb);
 
 	/* EEH device for PHB */
-	eeh_dev_init(dn, phb);
+	eeh_dev_init(root, phb);
 
 	/* EEH devices for children OF nodes */
-	traverse_pci_devices(dn, eeh_dev_init, phb);
+	traverse_pci_dn(root, eeh_dev_init, phb);
 }
 
 /**
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index d139f72ff9d5..65b98367005c 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -246,6 +246,46 @@ void *traverse_pci_devices(struct device_node *start, traverse_func pre,
 	return NULL;
 }
 
+static struct pci_dn *pci_dn_next_one(struct pci_dn *root,
+				      struct pci_dn *pdn)
+{
+	struct list_head *next = pdn->child_list.next;
+
+	if (next != &pdn->child_list)
+		return list_entry(next, struct pci_dn, list);
+
+	while (1) {
+		if (pdn == root)
+			return NULL;
+
+		next = pdn->list.next;
+		if (next != &pdn->parent->child_list)
+			break;
+
+		pdn = pdn->parent;
+	}
+
+	return list_entry(next, struct pci_dn, list);
+}
+
+void *traverse_pci_dn(struct pci_dn *root,
+		      void *(*fn)(struct pci_dn *, void *),
+		      void *data)
+{
+	struct pci_dn *pdn = root;
+	void *ret;
+
+	/* Only scan the child nodes */
+	for (pdn = pci_dn_next_one(root, pdn); pdn;
+	     pdn = pci_dn_next_one(root, pdn)) {
+		ret = fn(pdn, data);
+		if (ret)
+			return ret;
+	}
+
+	return NULL;
+}
+
 /** 
  * pci_devs_phb_init_dynamic - setup pci devices under this PHB
  * phb: pci-to-host bridge (top-level bridge connecting to cpu)
-- 
cgit v1.2.3


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

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

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

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/eeh.c         | 63 +++++++++++++--------------------------
 arch/powerpc/kernel/of_platform.c |  2 +-
 arch/powerpc/kernel/pci-hotplug.c |  2 +-
 3 files changed, 23 insertions(+), 44 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 19a897c810be..9504c2f0bb54 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -969,7 +969,7 @@ static struct notifier_block eeh_reboot_nb = {
 int eeh_init(void)
 {
 	struct pci_controller *hose, *tmp;
-	struct device_node *phb;
+	struct pci_dn *pdn;
 	static int cnt = 0;
 	int ret = 0;
 
@@ -1004,20 +1004,9 @@ int eeh_init(void)
 		return ret;
 
 	/* Enable EEH for all adapters */
-	if (eeh_has_flag(EEH_PROBE_MODE_DEVTREE)) {
-		list_for_each_entry_safe(hose, tmp,
-			&hose_list, list_node) {
-			phb = hose->dn;
-			traverse_pci_devices(phb, eeh_ops->of_probe, NULL);
-		}
-	} else if (eeh_has_flag(EEH_PROBE_MODE_DEV)) {
-		list_for_each_entry_safe(hose, tmp,
-			&hose_list, list_node)
-			pci_walk_bus(hose->bus, eeh_ops->dev_probe, NULL);
-	} else {
-		pr_warn("%s: Invalid probe mode %x",
-			__func__, eeh_subsystem_flags);
-		return -EINVAL;
+	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+		pdn = hose->pci_data;
+		traverse_pci_dn(pdn, eeh_ops->probe, NULL);
 	}
 
 	/*
@@ -1043,7 +1032,7 @@ core_initcall_sync(eeh_init);
 
 /**
  * eeh_add_device_early - Enable EEH for the indicated device_node
- * @dn: device node for which to set up EEH
+ * @pdn: PCI device node for which to set up EEH
  *
  * This routine must be used to perform EEH initialization for PCI
  * devices that were added after system boot (e.g. hotplug, dlpar).
@@ -1053,44 +1042,41 @@ core_initcall_sync(eeh_init);
  * on the CEC architecture, type of the device, on earlier boot
  * command-line arguments & etc.
  */
-void eeh_add_device_early(struct device_node *dn)
+void eeh_add_device_early(struct pci_dn *pdn)
 {
 	struct pci_controller *phb;
+	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
 
-	/*
-	 * If we're doing EEH probe based on PCI device, we
-	 * would delay the probe until late stage because
-	 * the PCI device isn't available this moment.
-	 */
-	if (!eeh_has_flag(EEH_PROBE_MODE_DEVTREE))
-		return;
-
-	if (!of_node_to_eeh_dev(dn))
+	if (!edev)
 		return;
-	phb = of_node_to_eeh_dev(dn)->phb;
 
 	/* USB Bus children of PCI devices will not have BUID's */
-	if (NULL == phb || 0 == phb->buid)
+	phb = edev->phb;
+	if (NULL == phb ||
+	    (eeh_has_flag(EEH_PROBE_MODE_DEVTREE) && 0 == phb->buid))
 		return;
 
-	eeh_ops->of_probe(dn, NULL);
+	eeh_ops->probe(pdn, NULL);
 }
 
 /**
  * eeh_add_device_tree_early - Enable EEH for the indicated device
- * @dn: device node
+ * @pdn: PCI device node
  *
  * This routine must be used to perform EEH initialization for the
  * indicated PCI device that was added after system boot (e.g.
  * hotplug, dlpar).
  */
-void eeh_add_device_tree_early(struct device_node *dn)
+void eeh_add_device_tree_early(struct pci_dn *pdn)
 {
-	struct device_node *sib;
+	struct pci_dn *n;
+
+	if (!pdn)
+		return;
 
-	for_each_child_of_node(dn, sib)
-		eeh_add_device_tree_early(sib);
-	eeh_add_device_early(dn);
+	list_for_each_entry(n, &pdn->child_list, list)
+		eeh_add_device_tree_early(n);
+	eeh_add_device_early(pdn);
 }
 EXPORT_SYMBOL_GPL(eeh_add_device_tree_early);
 
@@ -1144,13 +1130,6 @@ void eeh_add_device_late(struct pci_dev *dev)
 	edev->pdev = dev;
 	dev->dev.archdata.edev = edev;
 
-	/*
-	 * We have to do the EEH probe here because the PCI device
-	 * hasn't been created yet in the early stage.
-	 */
-	if (eeh_has_flag(EEH_PROBE_MODE_DEV))
-		eeh_ops->dev_probe(dev, NULL);
-
 	eeh_addr_cache_insert_dev(dev);
 }
 
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
index 2f35a72642c6..b60a67d92ebd 100644
--- a/arch/powerpc/kernel/of_platform.c
+++ b/arch/powerpc/kernel/of_platform.c
@@ -72,7 +72,7 @@ static int of_pci_phb_probe(struct platform_device *dev)
 
 	/* Register devices with EEH */
 	if (dev->dev.of_node->child)
-		eeh_add_device_tree_early(dev->dev.of_node);
+		eeh_add_device_tree_early(PCI_DN(dev->dev.of_node));
 
 	/* Scan the bus */
 	pcibios_scan_phb(phb);
diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c
index 5b789177aa29..18d9575729a3 100644
--- a/arch/powerpc/kernel/pci-hotplug.c
+++ b/arch/powerpc/kernel/pci-hotplug.c
@@ -75,7 +75,7 @@ void pcibios_add_pci_devices(struct pci_bus * bus)
 	struct pci_dev *dev;
 	struct device_node *dn = pci_bus_to_OF_node(bus);
 
-	eeh_add_device_tree_early(dn);
+	eeh_add_device_tree_early(PCI_DN(dn));
 
 	mode = PCI_PROBE_NORMAL;
 	if (ppc_md.pci_probe_mode)
-- 
cgit v1.2.3


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

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

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/eeh.c    | 40 +++++++++++----------
 arch/powerpc/kernel/eeh_pe.c | 82 +++++++++++++++++++++-----------------------
 2 files changed, 62 insertions(+), 60 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 9504c2f0bb54..1fd2566c87f1 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -164,30 +164,34 @@ __setup("eeh=", eeh_setup);
  */
 static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len)
 {
-	struct device_node *dn = eeh_dev_to_of_node(edev);
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 	u32 cfg;
 	int cap, i;
 	int n = 0, l = 0;
 	char buffer[128];
 
-	n += scnprintf(buf+n, len-n, "%s\n", dn->full_name);
-	pr_warn("EEH: of node=%s\n", dn->full_name);
+	n += scnprintf(buf+n, len-n, "%04x:%02x:%02x:%01x\n",
+		       edev->phb->global_number, pdn->busno,
+		       PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
+	pr_warn("EEH: of node=%04x:%02x:%02x:%01x\n",
+		edev->phb->global_number, pdn->busno,
+		PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
 
-	eeh_ops->read_config(dn, PCI_VENDOR_ID, 4, &cfg);
+	eeh_ops->read_config(pdn, PCI_VENDOR_ID, 4, &cfg);
 	n += scnprintf(buf+n, len-n, "dev/vend:%08x\n", cfg);
 	pr_warn("EEH: PCI device/vendor: %08x\n", cfg);
 
-	eeh_ops->read_config(dn, PCI_COMMAND, 4, &cfg);
+	eeh_ops->read_config(pdn, PCI_COMMAND, 4, &cfg);
 	n += scnprintf(buf+n, len-n, "cmd/stat:%x\n", cfg);
 	pr_warn("EEH: PCI cmd/status register: %08x\n", cfg);
 
 	/* Gather bridge-specific registers */
 	if (edev->mode & EEH_DEV_BRIDGE) {
-		eeh_ops->read_config(dn, PCI_SEC_STATUS, 2, &cfg);
+		eeh_ops->read_config(pdn, PCI_SEC_STATUS, 2, &cfg);
 		n += scnprintf(buf+n, len-n, "sec stat:%x\n", cfg);
 		pr_warn("EEH: Bridge secondary status: %04x\n", cfg);
 
-		eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &cfg);
+		eeh_ops->read_config(pdn, PCI_BRIDGE_CONTROL, 2, &cfg);
 		n += scnprintf(buf+n, len-n, "brdg ctl:%x\n", cfg);
 		pr_warn("EEH: Bridge control: %04x\n", cfg);
 	}
@@ -195,11 +199,11 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len)
 	/* Dump out the PCI-X command and status regs */
 	cap = edev->pcix_cap;
 	if (cap) {
-		eeh_ops->read_config(dn, cap, 4, &cfg);
+		eeh_ops->read_config(pdn, cap, 4, &cfg);
 		n += scnprintf(buf+n, len-n, "pcix-cmd:%x\n", cfg);
 		pr_warn("EEH: PCI-X cmd: %08x\n", cfg);
 
-		eeh_ops->read_config(dn, cap+4, 4, &cfg);
+		eeh_ops->read_config(pdn, cap+4, 4, &cfg);
 		n += scnprintf(buf+n, len-n, "pcix-stat:%x\n", cfg);
 		pr_warn("EEH: PCI-X status: %08x\n", cfg);
 	}
@@ -211,7 +215,7 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len)
 		pr_warn("EEH: PCI-E capabilities and status follow:\n");
 
 		for (i=0; i<=8; i++) {
-			eeh_ops->read_config(dn, cap+4*i, 4, &cfg);
+			eeh_ops->read_config(pdn, cap+4*i, 4, &cfg);
 			n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg);
 
 			if ((i % 4) == 0) {
@@ -238,7 +242,7 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len)
 		pr_warn("EEH: PCI-E AER capability register set follows:\n");
 
 		for (i=0; i<=13; i++) {
-			eeh_ops->read_config(dn, cap+4*i, 4, &cfg);
+			eeh_ops->read_config(pdn, cap+4*i, 4, &cfg);
 			n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg);
 
 			if ((i % 4) == 0) {
@@ -698,7 +702,7 @@ static void *eeh_disable_and_save_dev_state(void *data, void *userdata)
 static void *eeh_restore_dev_state(void *data, void *userdata)
 {
 	struct eeh_dev *edev = data;
-	struct device_node *dn = eeh_dev_to_of_node(edev);
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 	struct pci_dev *pdev = eeh_dev_to_pci_dev(edev);
 	struct pci_dev *dev = userdata;
 
@@ -706,8 +710,8 @@ static void *eeh_restore_dev_state(void *data, void *userdata)
 		return NULL;
 
 	/* Apply customization from firmware */
-	if (dn && eeh_ops->restore_config)
-		eeh_ops->restore_config(dn);
+	if (pdn && eeh_ops->restore_config)
+		eeh_ops->restore_config(pdn);
 
 	/* The caller should restore state for the specified device */
 	if (pdev != dev)
@@ -870,15 +874,15 @@ out:
  */
 void eeh_save_bars(struct eeh_dev *edev)
 {
+	struct pci_dn *pdn;
 	int i;
-	struct device_node *dn;
 
-	if (!edev)
+	pdn = eeh_dev_to_pdn(edev);
+	if (!pdn)
 		return;
-	dn = eeh_dev_to_of_node(edev);
 
 	for (i = 0; i < 16; i++)
-		eeh_ops->read_config(dn, i * 4, 4, &edev->config_space[i]);
+		eeh_ops->read_config(pdn, i * 4, 4, &edev->config_space[i]);
 
 	/*
 	 * For PCI bridges including root port, we need enable bus
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 1e4946c36f9e..209cd753bf46 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -291,27 +291,25 @@ struct eeh_pe *eeh_pe_get(struct eeh_dev *edev)
  */
 static struct eeh_pe *eeh_pe_get_parent(struct eeh_dev *edev)
 {
-	struct device_node *dn;
 	struct eeh_dev *parent;
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 
 	/*
 	 * It might have the case for the indirect parent
 	 * EEH device already having associated PE, but
 	 * the direct parent EEH device doesn't have yet.
 	 */
-	dn = edev->dn->parent;
-	while (dn) {
+	pdn = pdn ? pdn->parent : NULL;
+	while (pdn) {
 		/* We're poking out of PCI territory */
-		if (!PCI_DN(dn)) return NULL;
-
-		parent = of_node_to_eeh_dev(dn);
-		/* We're poking out of PCI territory */
-		if (!parent) return NULL;
+		parent = pdn_to_eeh_dev(pdn);
+		if (!parent)
+			return NULL;
 
 		if (parent->pe)
 			return parent->pe;
 
-		dn = dn->parent;
+		pdn = pdn->parent;
 	}
 
 	return NULL;
@@ -653,9 +651,9 @@ void eeh_pe_state_clear(struct eeh_pe *pe, int state)
  * blocked on normal path during the stage. So we need utilize
  * eeh operations, which is always permitted.
  */
-static void eeh_bridge_check_link(struct eeh_dev *edev,
-				  struct device_node *dn)
+static void eeh_bridge_check_link(struct eeh_dev *edev)
 {
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 	int cap;
 	uint32_t val;
 	int timeout = 0;
@@ -675,32 +673,32 @@ static void eeh_bridge_check_link(struct eeh_dev *edev,
 
 	/* Check slot status */
 	cap = edev->pcie_cap;
-	eeh_ops->read_config(dn, cap + PCI_EXP_SLTSTA, 2, &val);
+	eeh_ops->read_config(pdn, cap + PCI_EXP_SLTSTA, 2, &val);
 	if (!(val & PCI_EXP_SLTSTA_PDS)) {
 		pr_debug("  No card in the slot (0x%04x) !\n", val);
 		return;
 	}
 
 	/* Check power status if we have the capability */
-	eeh_ops->read_config(dn, cap + PCI_EXP_SLTCAP, 2, &val);
+	eeh_ops->read_config(pdn, cap + PCI_EXP_SLTCAP, 2, &val);
 	if (val & PCI_EXP_SLTCAP_PCP) {
-		eeh_ops->read_config(dn, cap + PCI_EXP_SLTCTL, 2, &val);
+		eeh_ops->read_config(pdn, cap + PCI_EXP_SLTCTL, 2, &val);
 		if (val & PCI_EXP_SLTCTL_PCC) {
 			pr_debug("  In power-off state, power it on ...\n");
 			val &= ~(PCI_EXP_SLTCTL_PCC | PCI_EXP_SLTCTL_PIC);
 			val |= (0x0100 & PCI_EXP_SLTCTL_PIC);
-			eeh_ops->write_config(dn, cap + PCI_EXP_SLTCTL, 2, val);
+			eeh_ops->write_config(pdn, cap + PCI_EXP_SLTCTL, 2, val);
 			msleep(2 * 1000);
 		}
 	}
 
 	/* Enable link */
-	eeh_ops->read_config(dn, cap + PCI_EXP_LNKCTL, 2, &val);
+	eeh_ops->read_config(pdn, cap + PCI_EXP_LNKCTL, 2, &val);
 	val &= ~PCI_EXP_LNKCTL_LD;
-	eeh_ops->write_config(dn, cap + PCI_EXP_LNKCTL, 2, val);
+	eeh_ops->write_config(pdn, cap + PCI_EXP_LNKCTL, 2, val);
 
 	/* Check link */
-	eeh_ops->read_config(dn, cap + PCI_EXP_LNKCAP, 4, &val);
+	eeh_ops->read_config(pdn, cap + PCI_EXP_LNKCAP, 4, &val);
 	if (!(val & PCI_EXP_LNKCAP_DLLLARC)) {
 		pr_debug("  No link reporting capability (0x%08x) \n", val);
 		msleep(1000);
@@ -713,7 +711,7 @@ static void eeh_bridge_check_link(struct eeh_dev *edev,
 		msleep(20);
 		timeout += 20;
 
-		eeh_ops->read_config(dn, cap + PCI_EXP_LNKSTA, 2, &val);
+		eeh_ops->read_config(pdn, cap + PCI_EXP_LNKSTA, 2, &val);
 		if (val & PCI_EXP_LNKSTA_DLLLA)
 			break;
 	}
@@ -728,9 +726,9 @@ static void eeh_bridge_check_link(struct eeh_dev *edev,
 #define BYTE_SWAP(OFF)	(8*((OFF)/4)+3-(OFF))
 #define SAVED_BYTE(OFF)	(((u8 *)(edev->config_space))[BYTE_SWAP(OFF)])
 
-static void eeh_restore_bridge_bars(struct eeh_dev *edev,
-				    struct device_node *dn)
+static void eeh_restore_bridge_bars(struct eeh_dev *edev)
 {
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 	int i;
 
 	/*
@@ -738,49 +736,49 @@ static void eeh_restore_bridge_bars(struct eeh_dev *edev,
 	 * Bus numbers and windows: 0x18 - 0x30
 	 */
 	for (i = 4; i < 13; i++)
-		eeh_ops->write_config(dn, i*4, 4, edev->config_space[i]);
+		eeh_ops->write_config(pdn, i*4, 4, edev->config_space[i]);
 	/* Rom: 0x38 */
-	eeh_ops->write_config(dn, 14*4, 4, edev->config_space[14]);
+	eeh_ops->write_config(pdn, 14*4, 4, edev->config_space[14]);
 
 	/* Cache line & Latency timer: 0xC 0xD */
-	eeh_ops->write_config(dn, PCI_CACHE_LINE_SIZE, 1,
+	eeh_ops->write_config(pdn, PCI_CACHE_LINE_SIZE, 1,
                 SAVED_BYTE(PCI_CACHE_LINE_SIZE));
-        eeh_ops->write_config(dn, PCI_LATENCY_TIMER, 1,
+        eeh_ops->write_config(pdn, PCI_LATENCY_TIMER, 1,
                 SAVED_BYTE(PCI_LATENCY_TIMER));
 	/* Max latency, min grant, interrupt ping and line: 0x3C */
-	eeh_ops->write_config(dn, 15*4, 4, edev->config_space[15]);
+	eeh_ops->write_config(pdn, 15*4, 4, edev->config_space[15]);
 
 	/* PCI Command: 0x4 */
-	eeh_ops->write_config(dn, PCI_COMMAND, 4, edev->config_space[1]);
+	eeh_ops->write_config(pdn, PCI_COMMAND, 4, edev->config_space[1]);
 
 	/* Check the PCIe link is ready */
-	eeh_bridge_check_link(edev, dn);
+	eeh_bridge_check_link(edev);
 }
 
-static void eeh_restore_device_bars(struct eeh_dev *edev,
-				    struct device_node *dn)
+static void eeh_restore_device_bars(struct eeh_dev *edev)
 {
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 	int i;
 	u32 cmd;
 
 	for (i = 4; i < 10; i++)
-		eeh_ops->write_config(dn, i*4, 4, edev->config_space[i]);
+		eeh_ops->write_config(pdn, i*4, 4, edev->config_space[i]);
 	/* 12 == Expansion ROM Address */
-	eeh_ops->write_config(dn, 12*4, 4, edev->config_space[12]);
+	eeh_ops->write_config(pdn, 12*4, 4, edev->config_space[12]);
 
-	eeh_ops->write_config(dn, PCI_CACHE_LINE_SIZE, 1,
+	eeh_ops->write_config(pdn, PCI_CACHE_LINE_SIZE, 1,
 		SAVED_BYTE(PCI_CACHE_LINE_SIZE));
-	eeh_ops->write_config(dn, PCI_LATENCY_TIMER, 1,
+	eeh_ops->write_config(pdn, PCI_LATENCY_TIMER, 1,
 		SAVED_BYTE(PCI_LATENCY_TIMER));
 
 	/* max latency, min grant, interrupt pin and line */
-	eeh_ops->write_config(dn, 15*4, 4, edev->config_space[15]);
+	eeh_ops->write_config(pdn, 15*4, 4, edev->config_space[15]);
 
 	/*
 	 * Restore PERR & SERR bits, some devices require it,
 	 * don't touch the other command bits
 	 */
-	eeh_ops->read_config(dn, PCI_COMMAND, 4, &cmd);
+	eeh_ops->read_config(pdn, PCI_COMMAND, 4, &cmd);
 	if (edev->config_space[1] & PCI_COMMAND_PARITY)
 		cmd |= PCI_COMMAND_PARITY;
 	else
@@ -789,7 +787,7 @@ static void eeh_restore_device_bars(struct eeh_dev *edev,
 		cmd |= PCI_COMMAND_SERR;
 	else
 		cmd &= ~PCI_COMMAND_SERR;
-	eeh_ops->write_config(dn, PCI_COMMAND, 4, cmd);
+	eeh_ops->write_config(pdn, PCI_COMMAND, 4, cmd);
 }
 
 /**
@@ -804,16 +802,16 @@ static void eeh_restore_device_bars(struct eeh_dev *edev,
 static void *eeh_restore_one_device_bars(void *data, void *flag)
 {
 	struct eeh_dev *edev = (struct eeh_dev *)data;
-	struct device_node *dn = eeh_dev_to_of_node(edev);
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 
 	/* Do special restore for bridges */
 	if (edev->mode & EEH_DEV_BRIDGE)
-		eeh_restore_bridge_bars(edev, dn);
+		eeh_restore_bridge_bars(edev);
 	else
-		eeh_restore_device_bars(edev, dn);
+		eeh_restore_device_bars(edev);
 
-	if (eeh_ops->restore_config)
-		eeh_ops->restore_config(dn);
+	if (eeh_ops->restore_config && pdn)
+		eeh_ops->restore_config(pdn);
 
 	return NULL;
 }
-- 
cgit v1.2.3


From c6406d8fbb014bebdfb5bf3c244548958aec7379 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Tue, 17 Mar 2015 16:15:08 +1100
Subject: powerpc/eeh: Remove device_node dependency

The patch removes struct eeh_dev::dn and the corresponding helper
functions: eeh_dev_to_of_node() and of_node_to_eeh_dev(). Instead,
eeh_dev_to_pdn() and pdn_to_eeh_dev() should be used to get the
pdn, which might contain device_node on PowerNV platform.

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/eeh.c         | 24 +++++++++++++-----------
 arch/powerpc/kernel/eeh_cache.c   | 25 +++++++++++--------------
 arch/powerpc/kernel/eeh_driver.c  | 22 ----------------------
 arch/powerpc/kernel/eeh_pe.c      | 34 +++++++++++++++++++++++++---------
 arch/powerpc/kernel/pci_of_scan.c |  2 +-
 arch/powerpc/kernel/rtas_pci.c    |  2 +-
 6 files changed, 51 insertions(+), 58 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 1fd2566c87f1..76253eb146be 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -418,11 +418,11 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
 	int ret;
 	int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
 	unsigned long flags;
-	struct device_node *dn;
+	struct pci_dn *pdn;
 	struct pci_dev *dev;
 	struct eeh_pe *pe, *parent_pe, *phb_pe;
 	int rc = 0;
-	const char *location;
+	const char *location = NULL;
 
 	eeh_stats.total_mmio_ffs++;
 
@@ -433,15 +433,14 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
 		eeh_stats.no_dn++;
 		return 0;
 	}
-	dn = eeh_dev_to_of_node(edev);
 	dev = eeh_dev_to_pci_dev(edev);
 	pe = eeh_dev_to_pe(edev);
 
 	/* Access to IO BARs might get this far and still not want checking. */
 	if (!pe) {
 		eeh_stats.ignored_check++;
-		pr_debug("EEH: Ignored check for %s %s\n",
-			eeh_pci_name(dev), dn->full_name);
+		pr_debug("EEH: Ignored check for %s\n",
+			eeh_pci_name(dev));
 		return 0;
 	}
 
@@ -477,10 +476,13 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
 	if (pe->state & EEH_PE_ISOLATED) {
 		pe->check_count++;
 		if (pe->check_count % EEH_MAX_FAILS == 0) {
-			location = of_get_property(dn, "ibm,loc-code", NULL);
+			pdn = eeh_dev_to_pdn(edev);
+			if (pdn->node)
+				location = of_get_property(pdn->node, "ibm,loc-code", NULL);
 			printk(KERN_ERR "EEH: %d reads ignored for recovering device at "
 				"location=%s driver=%s pci addr=%s\n",
-				pe->check_count, location,
+				pe->check_count,
+				location ? location : "unknown",
 				eeh_driver_name(dev), eeh_pci_name(dev));
 			printk(KERN_ERR "EEH: Might be infinite loop in %s driver\n",
 				eeh_driver_name(dev));
@@ -1035,7 +1037,7 @@ int eeh_init(void)
 core_initcall_sync(eeh_init);
 
 /**
- * eeh_add_device_early - Enable EEH for the indicated device_node
+ * eeh_add_device_early - Enable EEH for the indicated device node
  * @pdn: PCI device node for which to set up EEH
  *
  * This routine must be used to perform EEH initialization for PCI
@@ -1093,7 +1095,7 @@ EXPORT_SYMBOL_GPL(eeh_add_device_tree_early);
  */
 void eeh_add_device_late(struct pci_dev *dev)
 {
-	struct device_node *dn;
+	struct pci_dn *pdn;
 	struct eeh_dev *edev;
 
 	if (!dev || !eeh_enabled())
@@ -1101,8 +1103,8 @@ void eeh_add_device_late(struct pci_dev *dev)
 
 	pr_debug("EEH: Adding device %s\n", pci_name(dev));
 
-	dn = pci_device_to_OF_node(dev);
-	edev = of_node_to_eeh_dev(dn);
+	pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn);
+	edev = pdn_to_eeh_dev(pdn);
 	if (edev->pdev == dev) {
 		pr_debug("EEH: Already referenced !\n");
 		return;
diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c
index 07d8a2423a61..eeabeabea49c 100644
--- a/arch/powerpc/kernel/eeh_cache.c
+++ b/arch/powerpc/kernel/eeh_cache.c
@@ -171,30 +171,27 @@ eeh_addr_cache_insert(struct pci_dev *dev, unsigned long alo,
 
 static void __eeh_addr_cache_insert_dev(struct pci_dev *dev)
 {
-	struct device_node *dn;
+	struct pci_dn *pdn;
 	struct eeh_dev *edev;
 	int i;
 
-	dn = pci_device_to_OF_node(dev);
-	if (!dn) {
+	pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn);
+	if (!pdn) {
 		pr_warn("PCI: no pci dn found for dev=%s\n",
 			pci_name(dev));
 		return;
 	}
 
-	edev = of_node_to_eeh_dev(dn);
+	edev = pdn_to_eeh_dev(pdn);
 	if (!edev) {
-		pr_warn("PCI: no EEH dev found for dn=%s\n",
-			dn->full_name);
+		pr_warn("PCI: no EEH dev found for %s\n",
+			pci_name(dev));
 		return;
 	}
 
 	/* Skip any devices for which EEH is not enabled. */
 	if (!edev->pe) {
-#ifdef DEBUG
-		pr_info("PCI: skip building address cache for=%s - %s\n",
-			pci_name(dev), dn->full_name);
-#endif
+		dev_dbg(&dev->dev, "EEH: Skip building address cache\n");
 		return;
 	}
 
@@ -282,18 +279,18 @@ void eeh_addr_cache_rmv_dev(struct pci_dev *dev)
  */
 void eeh_addr_cache_build(void)
 {
-	struct device_node *dn;
+	struct pci_dn *pdn;
 	struct eeh_dev *edev;
 	struct pci_dev *dev = NULL;
 
 	spin_lock_init(&pci_io_addr_cache_root.piar_lock);
 
 	for_each_pci_dev(dev) {
-		dn = pci_device_to_OF_node(dev);
-		if (!dn)
+		pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn);
+		if (!pdn)
 			continue;
 
-		edev = of_node_to_eeh_dev(dn);
+		edev = pdn_to_eeh_dev(pdn);
 		if (!edev)
 			continue;
 
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index d099540c0f56..24768ff3cb73 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -83,28 +83,6 @@ static inline void eeh_pcid_put(struct pci_dev *pdev)
 	module_put(pdev->driver->driver.owner);
 }
 
-#if 0
-static void print_device_node_tree(struct pci_dn *pdn, int dent)
-{
-	int i;
-	struct device_node *pc;
-
-	if (!pdn)
-		return;
-	for (i = 0; i < dent; i++)
-		printk(" ");
-	printk("dn=%s mode=%x \tcfg_addr=%x pe_addr=%x \tfull=%s\n",
-		pdn->node->name, pdn->eeh_mode, pdn->eeh_config_addr,
-		pdn->eeh_pe_config_addr, pdn->node->full_name);
-	dent += 3;
-	pc = pdn->node->child;
-	while (pc) {
-		print_device_node_tree(PCI_DN(pc), dent);
-		pc = pc->sibling;
-	}
-}
-#endif
-
 /**
  * eeh_disable_irq - Disable interrupt for the recovering device
  * @dev: PCI device
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 209cd753bf46..f33ceccf6876 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -348,9 +348,12 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev)
 
 		/* Put the edev to PE */
 		list_add_tail(&edev->list, &pe->edevs);
-		pr_debug("EEH: Add %s to Bus PE#%x\n",
-			edev->dn->full_name, pe->addr);
-
+		pr_debug("EEH: Add %04x:%02x:%02x.%01x to Bus PE#%x\n",
+			edev->phb->global_number,
+			edev->config_addr >> 8,
+			PCI_SLOT(edev->config_addr & 0xFF),
+			PCI_FUNC(edev->config_addr & 0xFF),
+			pe->addr);
 		return 0;
 	} else if (pe && (pe->type & EEH_PE_INVALID)) {
 		list_add_tail(&edev->list, &pe->edevs);
@@ -366,9 +369,14 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev)
 			parent->type &= ~(EEH_PE_INVALID | EEH_PE_KEEP);
 			parent = parent->parent;
 		}
-		pr_debug("EEH: Add %s to Device PE#%x, Parent PE#%x\n",
-			edev->dn->full_name, pe->addr, pe->parent->addr);
 
+		pr_debug("EEH: Add %04x:%02x:%02x.%01x to Device "
+			 "PE#%x, Parent PE#%x\n",
+			edev->phb->global_number,
+			edev->config_addr >> 8,
+                        PCI_SLOT(edev->config_addr & 0xFF),
+                        PCI_FUNC(edev->config_addr & 0xFF),
+			pe->addr, pe->parent->addr);
 		return 0;
 	}
 
@@ -407,8 +415,13 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev)
 	list_add_tail(&pe->child, &parent->child_list);
 	list_add_tail(&edev->list, &pe->edevs);
 	edev->pe = pe;
-	pr_debug("EEH: Add %s to Device PE#%x, Parent PE#%x\n",
-		edev->dn->full_name, pe->addr, pe->parent->addr);
+	pr_debug("EEH: Add %04x:%02x:%02x.%01x to "
+		 "Device PE#%x, Parent PE#%x\n",
+		 edev->phb->global_number,
+		 edev->config_addr >> 8,
+		 PCI_SLOT(edev->config_addr & 0xFF),
+		 PCI_FUNC(edev->config_addr & 0xFF),
+		 pe->addr, pe->parent->addr);
 
 	return 0;
 }
@@ -428,8 +441,11 @@ int eeh_rmv_from_parent_pe(struct eeh_dev *edev)
 	int cnt;
 
 	if (!edev->pe) {
-		pr_debug("%s: No PE found for EEH device %s\n",
-			 __func__, edev->dn->full_name);
+		pr_debug("%s: No PE found for device %04x:%02x:%02x.%01x\n",
+			 __func__,  edev->phb->global_number,
+			 edev->config_addr >> 8,
+			 PCI_SLOT(edev->config_addr & 0xFF),
+			 PCI_FUNC(edev->config_addr & 0xFF));
 		return -EEXIST;
 	}
 
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index e6245e9c7d8d..7122dfece393 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -305,7 +305,7 @@ static struct pci_dev *of_scan_pci_dev(struct pci_bus *bus,
 	const __be32 *reg;
 	int reglen, devfn;
 #ifdef CONFIG_EEH
-	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
+	struct eeh_dev *edev = pdn_to_eeh_dev(PCI_DN(dn));
 #endif
 
 	pr_debug("  * %s\n", dn->full_name);
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index ce230da2c015..af29df2517f7 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -113,7 +113,7 @@ static int rtas_pci_read_config(struct pci_bus *bus,
 
 	ret = rtas_read_config(pdn, where, size, val);
 	if (*val == EEH_IO_ERROR_VALUE(size) &&
-	    eeh_dev_check_failure(of_node_to_eeh_dev(dn)))
+	    eeh_dev_check_failure(pdn_to_eeh_dev(pdn)))
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
 	return ret;
-- 
cgit v1.2.3


From c03e73740d24fbe990291cd9ac2d6ae0d95b975f Mon Sep 17 00:00:00 2001
From: Tyrel Datwyler <tyreld@linux.vnet.ibm.com>
Date: Fri, 27 Mar 2015 12:47:25 -0700
Subject: powerpc/pseries: Simplify check for suspendability during
 suspend/migration

During suspend/migration operation we must wait for the VASI state reported
by the hypervisor to become Suspending prior to making the ibm,suspend-me
RTAS call. Calling routines to rtas_ibm_supend_me() pass a vasi_state variable
that exposes the VASI state to the caller. This is unnecessary as the caller
only really cares about the following three conditions; if there is an error
we should bailout, success indicating we have suspended and woken back up so
proceed to device tree update, or we are not suspendable yet so try calling
rtas_ibm_suspend_me again shortly.

This patch removes the extraneous vasi_state variable and simply uses the
return code to communicate how to proceed. We either succeed, fail, or get
-EAGAIN in which case we sleep for a second before trying to call
rtas_ibm_suspend_me again. The behaviour of ppc_rtas() remains the same,
but migrate_store() now returns the propogated error code on failure.
Previously -1 was returned from migrate_store() in the  failure case which
equates to -EPERM and was clearly wrong.

Signed-off-by: Tyrel Datwyler <tyreld@linux.vnet.ibm.com>
Cc: Nathan Fontenont <nfont@linux.vnet.ibm.com>
Cc: Cyril Bur <cyrilbur@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/rtas.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 21c45a2d0706..b9a7b8981ef7 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -897,7 +897,7 @@ int rtas_offline_cpus_mask(cpumask_var_t cpus)
 }
 EXPORT_SYMBOL(rtas_offline_cpus_mask);
 
-int rtas_ibm_suspend_me(u64 handle, int *vasi_return)
+int rtas_ibm_suspend_me(u64 handle)
 {
 	long state;
 	long rc;
@@ -919,13 +919,11 @@ int rtas_ibm_suspend_me(u64 handle, int *vasi_return)
 		printk(KERN_ERR "rtas_ibm_suspend_me: vasi_state returned %ld\n",rc);
 		return rc;
 	} else if (state == H_VASI_ENABLED) {
-		*vasi_return = RTAS_NOT_SUSPENDABLE;
-		return 0;
+		return -EAGAIN;
 	} else if (state != H_VASI_SUSPENDING) {
 		printk(KERN_ERR "rtas_ibm_suspend_me: vasi_state returned state %ld\n",
 		       state);
-		*vasi_return = -1;
-		return 0;
+		return -EIO;
 	}
 
 	if (!alloc_cpumask_var(&offline_mask, GFP_TEMPORARY))
@@ -972,7 +970,7 @@ out:
 	return atomic_read(&data.error);
 }
 #else /* CONFIG_PPC_PSERIES */
-int rtas_ibm_suspend_me(u64 handle, int *vasi_return)
+int rtas_ibm_suspend_me(u64 handle)
 {
 	return -ENOSYS;
 }
@@ -1022,7 +1020,6 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
 	unsigned long flags;
 	char *buff_copy, *errbuf = NULL;
 	int nargs, nret, token;
-	int rc;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -1054,15 +1051,18 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
 	if (token == ibm_suspend_me_token) {
 
 		/*
-		 * rtas_ibm_suspend_me assumes args are in cpu endian, or at least the
-		 * hcall within it requires it.
+		 * rtas_ibm_suspend_me assumes the streamid handle is in cpu
+		 * endian, or at least the hcall within it requires it.
 		 */
-		int vasi_rc = 0;
+		int rc = 0;
 		u64 handle = ((u64)be32_to_cpu(args.args[0]) << 32)
 		              | be32_to_cpu(args.args[1]);
-		rc = rtas_ibm_suspend_me(handle, &vasi_rc);
-		args.rets[0] = cpu_to_be32(vasi_rc);
-		if (rc)
+		rc = rtas_ibm_suspend_me(handle);
+		if (rc == -EAGAIN)
+			args.rets[0] = cpu_to_be32(RTAS_NOT_SUSPENDABLE);
+		else if (rc == -EIO)
+			args.rets[0] = cpu_to_be32(-1);
+		else if (rc)
 			return rc;
 		goto copy_return;
 	}
-- 
cgit v1.2.3


From 529d235a0e190ded1d21ccc80a73e625ebcad09b Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Sat, 28 Mar 2015 21:35:16 +1100
Subject: powerpc: Add a proper syscall for switching endianness

We currently have a "special" syscall for switching endianness. This is
syscall number 0x1ebe, which is handled explicitly in the 64-bit syscall
exception entry.

That has a few problems, firstly the syscall number is outside of the
usual range, which confuses various tools. For example strace doesn't
recognise the syscall at all.

Secondly it's handled explicitly as a special case in the syscall
exception entry, which is complicated enough without it.

As a first step toward removing the special syscall, we need to add a
regular syscall that implements the same functionality.

The logic is simple, it simply toggles the MSR_LE bit in the userspace
MSR. This is the same as the special syscall, with the caveat that the
special syscall clobbers fewer registers.

This version clobbers r9-r12, XER, CTR, and CR0-1,5-7.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/entry_64.S   |  5 +++++
 arch/powerpc/kernel/syscalls.c   | 17 +++++++++++++++++
 arch/powerpc/kernel/systbl.S     |  2 ++
 arch/powerpc/kernel/systbl_chk.c |  2 ++
 4 files changed, 26 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index d180caf2d6de..afbc20019c2e 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -356,6 +356,11 @@ _GLOBAL(ppc64_swapcontext)
 	bl	sys_swapcontext
 	b	.Lsyscall_exit
 
+_GLOBAL(ppc_switch_endian)
+	bl	save_nvgprs
+	bl	sys_switch_endian
+	b	.Lsyscall_exit
+
 _GLOBAL(ret_from_fork)
 	bl	schedule_tail
 	REST_NVGPRS(r1)
diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c
index b2702e87db0d..5fa92706444b 100644
--- a/arch/powerpc/kernel/syscalls.c
+++ b/arch/powerpc/kernel/syscalls.c
@@ -121,3 +121,20 @@ long ppc_fadvise64_64(int fd, int advice, u32 offset_high, u32 offset_low,
 	return sys_fadvise64(fd, (u64)offset_high << 32 | offset_low,
 			     (u64)len_high << 32 | len_low, advice);
 }
+
+long sys_switch_endian(void)
+{
+	struct thread_info *ti;
+
+	current->thread.regs->msr ^= MSR_LE;
+
+	/*
+	 * Set TIF_RESTOREALL so that r3 isn't clobbered on return to
+	 * userspace. That also has the effect of restoring the non-volatile
+	 * GPRs, so we saved them on the way in here.
+	 */
+	ti = current_thread_info();
+	ti->flags |= _TIF_RESTOREALL;
+
+	return 0;
+}
diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S
index 7ab5d434e2ee..4d6b1d3a747f 100644
--- a/arch/powerpc/kernel/systbl.S
+++ b/arch/powerpc/kernel/systbl.S
@@ -22,6 +22,7 @@
 #define PPC_SYS(func)		.llong	DOTSYM(ppc_##func),DOTSYM(ppc_##func)
 #define OLDSYS(func)		.llong	DOTSYM(sys_ni_syscall),DOTSYM(sys_ni_syscall)
 #define SYS32ONLY(func)		.llong	DOTSYM(sys_ni_syscall),DOTSYM(compat_sys_##func)
+#define PPC64ONLY(func)		.llong	DOTSYM(ppc_##func),DOTSYM(sys_ni_syscall)
 #define SYSX(f, f3264, f32)	.llong	DOTSYM(f),DOTSYM(f3264)
 #else
 #define SYSCALL(func)		.long	sys_##func
@@ -29,6 +30,7 @@
 #define PPC_SYS(func)		.long	ppc_##func
 #define OLDSYS(func)		.long	sys_##func
 #define SYS32ONLY(func)		.long	sys_##func
+#define PPC64ONLY(func)		.long	sys_ni_syscall
 #define SYSX(f, f3264, f32)	.long	f32
 #endif
 #define SYSCALL_SPU(func)	SYSCALL(func)
diff --git a/arch/powerpc/kernel/systbl_chk.c b/arch/powerpc/kernel/systbl_chk.c
index 238aa63ced8f..2384129f5893 100644
--- a/arch/powerpc/kernel/systbl_chk.c
+++ b/arch/powerpc/kernel/systbl_chk.c
@@ -21,9 +21,11 @@
 #ifdef CONFIG_PPC64
 #define OLDSYS(func)		-1
 #define SYS32ONLY(func)		-1
+#define PPC64ONLY(func)		__NR_##func
 #else
 #define OLDSYS(func)		__NR_old##func
 #define SYS32ONLY(func)		__NR_##func
+#define PPC64ONLY(func)		-1
 #endif
 #define SYSX(f, f3264, f32)	-1
 
-- 
cgit v1.2.3


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

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

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

[bhelgaas: add ifdef around add_one_dev_pci_info(), use dev_printk()]
Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/pci_dn.c | 116 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 116 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index 65b98367005c..e5f1d78ef7cf 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -136,6 +136,122 @@ struct pci_dn *pci_get_pdn(struct pci_dev *pdev)
 	return NULL;
 }
 
+#ifdef CONFIG_PCI_IOV
+static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent,
+					   struct pci_dev *pdev,
+					   int busno, int devfn)
+{
+	struct pci_dn *pdn;
+
+	/* Except PHB, we always have the parent */
+	if (!parent)
+		return NULL;
+
+	pdn = kzalloc(sizeof(*pdn), GFP_KERNEL);
+	if (!pdn) {
+		dev_warn(&pdev->dev, "%s: Out of memory!\n", __func__);
+		return NULL;
+	}
+
+	pdn->phb = parent->phb;
+	pdn->parent = parent;
+	pdn->busno = busno;
+	pdn->devfn = devfn;
+#ifdef CONFIG_PPC_POWERNV
+	pdn->pe_number = IODA_INVALID_PE;
+#endif
+	INIT_LIST_HEAD(&pdn->child_list);
+	INIT_LIST_HEAD(&pdn->list);
+	list_add_tail(&pdn->list, &parent->child_list);
+
+	/*
+	 * If we already have PCI device instance, lets
+	 * bind them.
+	 */
+	if (pdev)
+		pdev->dev.archdata.pci_data = pdn;
+
+	return pdn;
+}
+#endif
+
+struct pci_dn *add_dev_pci_data(struct pci_dev *pdev)
+{
+#ifdef CONFIG_PCI_IOV
+	struct pci_dn *parent, *pdn;
+	int i;
+
+	/* Only support IOV for now */
+	if (!pdev->is_physfn)
+		return pci_get_pdn(pdev);
+
+	/* Check if VFs have been populated */
+	pdn = pci_get_pdn(pdev);
+	if (!pdn || (pdn->flags & PCI_DN_FLAG_IOV_VF))
+		return NULL;
+
+	pdn->flags |= PCI_DN_FLAG_IOV_VF;
+	parent = pci_bus_to_pdn(pdev->bus);
+	if (!parent)
+		return NULL;
+
+	for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
+		pdn = add_one_dev_pci_data(parent, NULL,
+					   pci_iov_virtfn_bus(pdev, i),
+					   pci_iov_virtfn_devfn(pdev, i));
+		if (!pdn) {
+			dev_warn(&pdev->dev, "%s: Cannot create firmware data for VF#%d\n",
+				 __func__, i);
+			return NULL;
+		}
+	}
+#endif /* CONFIG_PCI_IOV */
+
+	return pci_get_pdn(pdev);
+}
+
+void remove_dev_pci_data(struct pci_dev *pdev)
+{
+#ifdef CONFIG_PCI_IOV
+	struct pci_dn *parent;
+	struct pci_dn *pdn, *tmp;
+	int i;
+
+	/* Only support IOV PF for now */
+	if (!pdev->is_physfn)
+		return;
+
+	/* Check if VFs have been populated */
+	pdn = pci_get_pdn(pdev);
+	if (!pdn || !(pdn->flags & PCI_DN_FLAG_IOV_VF))
+		return;
+
+	pdn->flags &= ~PCI_DN_FLAG_IOV_VF;
+	parent = pci_bus_to_pdn(pdev->bus);
+	if (!parent)
+		return;
+
+	/*
+	 * We might introduce flag to pci_dn in future
+	 * so that we can release VF's firmware data in
+	 * a batch mode.
+	 */
+	for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
+		list_for_each_entry_safe(pdn, tmp,
+			&parent->child_list, list) {
+			if (pdn->busno != pci_iov_virtfn_bus(pdev, i) ||
+			    pdn->devfn != pci_iov_virtfn_devfn(pdev, i))
+				continue;
+
+			if (!list_empty(&pdn->list))
+				list_del(&pdn->list);
+
+			kfree(pdn);
+		}
+	}
+#endif /* CONFIG_PCI_IOV */
+}
+
 /*
  * Traverse_func that inits the PCI fields of the device node.
  * NOTE: this *must* be done before read/write config to the device.
-- 
cgit v1.2.3


From c3b80fb0f22f464f35a970d65e76d2fe904d4923 Mon Sep 17 00:00:00 2001
From: Wei Yang <weiyang@linux.vnet.ibm.com>
Date: Wed, 25 Mar 2015 16:23:53 +0800
Subject: powerpc/pci: Don't unset PCI resources for VFs

Flag PCI_REASSIGN_ALL_RSRC is used to ignore resources information setup by
firmware, so that kernel would re-assign all resources of pci devices.

On powerpc arch, this happens in a header fixup function
pcibios_fixup_resources(), which will clean up the resources if this flag
is set. This works fine for PFs, since after clean up, kernel will
re-assign the resources in pcibios_resource_survey().

Below is a simple call flow on how it works:

    pcibios_init
      pcibios_scan_phb
        pci_scan_child_bus
          ...
            pci_device_add
              pci_fixup_device(pci_fixup_header)
                pcibios_fixup_resources                     # header fixup
                  for (i = 0; i < DEVICE_COUNT_RESOURCE; i++)
                    dev->resource[i].start = 0
      pcibios_resource_survey                               # re-assign
        pcibios_allocate_resources

However, the VF resources won't be re-assigned, since the VF resources are
completely determined by the PF resources, and the PF resources have
already been reassigned. This means we need to leave VF's resources
un-cleared in pcibios_fixup_resources().

In this patch, we skip the resource unset process in
pcibios_fixup_resources(), if the pci_dev is a VF.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/pci-common.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 2a525c938158..82031011522f 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -788,6 +788,10 @@ static void pcibios_fixup_resources(struct pci_dev *dev)
 		       pci_name(dev));
 		return;
 	}
+
+	if (dev->is_virtfn)
+		return;
+
 	for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
 		struct resource *res = dev->resource + i;
 		struct pci_bus_region reg;
-- 
cgit v1.2.3


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

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

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

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

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

[bhelgaas: make dev_printk() output more consistent, index resource[]
conventionally]
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/pci-common.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 82031011522f..375bf7099912 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -990,6 +990,12 @@ int pcibios_add_device(struct pci_dev *dev)
 	 */
 	if (dev->bus->is_added)
 		pcibios_setup_device(dev);
+
+#ifdef CONFIG_PCI_IOV
+	if (ppc_md.pcibios_fixup_sriov)
+		ppc_md.pcibios_fixup_sriov(dev);
+#endif /* CONFIG_PCI_IOV */
+
 	return 0;
 }
 
-- 
cgit v1.2.3


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

Implement pcibios_iov_resource_alignment() on powernv platform.

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

pnv_pci_iov_resource_alignment() handle these three cases respectively.

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

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 375bf7099912..9a306ff304ae 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -130,6 +130,16 @@ void pcibios_reset_secondary_bus(struct pci_dev *dev)
 	pci_reset_secondary_bus(dev);
 }
 
+#ifdef CONFIG_PCI_IOV
+resource_size_t pcibios_iov_resource_alignment(struct pci_dev *pdev, int resno)
+{
+	if (ppc_md.pcibios_iov_resource_alignment)
+		return ppc_md.pcibios_iov_resource_alignment(pdev, resno);
+
+	return pci_iov_resource_size(pdev, resno);
+}
+#endif /* CONFIG_PCI_IOV */
+
 static resource_size_t pcibios_io_size(const struct pci_controller *hose)
 {
 #ifdef CONFIG_PPC64
-- 
cgit v1.2.3


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

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

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

Note:

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

[bhelgaas: rework loops, rework overlap check, index resource[]
conventionally, remove pci_regs.h include, squashed with next patch]
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/pci_dn.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index e5f1d78ef7cf..b3b4df91b792 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -217,6 +217,19 @@ void remove_dev_pci_data(struct pci_dev *pdev)
 	struct pci_dn *pdn, *tmp;
 	int i;
 
+	/*
+	 * VF and VF PE are created/released dynamically, so we need to
+	 * bind/unbind them.  Otherwise the VF and VF PE would be mismatched
+	 * when re-enabling SR-IOV.
+	 */
+	if (pdev->is_virtfn) {
+		pdn = pci_get_pdn(pdev);
+#ifdef CONFIG_PPC_POWERNV
+		pdn->pe_number = IODA_INVALID_PE;
+#endif
+		return;
+	}
+
 	/* Only support IOV PF for now */
 	if (!pdev->is_physfn)
 		return;
-- 
cgit v1.2.3


From 433185d2b4e9c25f2a444424c05af72fbadd4275 Mon Sep 17 00:00:00 2001
From: Gavin Shan <gwshan@linux.vnet.ibm.com>
Date: Fri, 27 Mar 2015 11:22:17 +1100
Subject: powerpc/eeh: Fix PE#0 check in eeh_add_to_parent_pe()

The function eeh_add_parent_pe() is used to create a PE or add one
edev to its parent PE. Current code checks if PE#0 is valid for the
later case. Actually, we should validate PE#0 for both cases when
EEH core regards PE#0 as invalid one (without flag EEH_VALID_PE_ZERO).
Otherwise, not all EEH devices can be added to its parent PE#0 for
EEH on P7IOC.

The patch fixes the issue by validating PE#0 for the two cases. So far,
we don't have PE#0 for EEH on P7IOC, but it will show up when we enable
M64 for P7IOC. The patch also makes the error message more meaningful.

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/eeh_pe.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index f33ceccf6876..35f0b62259bb 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -328,6 +328,13 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev)
 {
 	struct eeh_pe *pe, *parent;
 
+	/* Check if the PE number is valid */
+	if (!eeh_has_flag(EEH_VALID_PE_ZERO) && !edev->pe_config_addr) {
+		pr_err("%s: Invalid PE#0 for edev 0x%x on PHB#%d\n",
+		       __func__, edev->config_addr, edev->phb->global_number);
+		return -EINVAL;
+	}
+
 	/*
 	 * Search the PE has been existing or not according
 	 * to the PE address. If that has been existing, the
@@ -336,12 +343,6 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev)
 	 */
 	pe = eeh_pe_get(edev);
 	if (pe && !(pe->type & EEH_PE_INVALID)) {
-		if (!edev->pe_config_addr) {
-			pr_err("%s: PE with addr 0x%x already exists\n",
-				__func__, edev->config_addr);
-			return -EEXIST;
-		}
-
 		/* Mark the PE as type of PCI bus */
 		pe->type = EEH_PE_BUS;
 		edev->pe = pe;
-- 
cgit v1.2.3


From bf4981a00636347ddcef3fc008e4dd979380a851 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Thu, 19 Mar 2015 15:15:20 +1100
Subject: powerpc: Remove the celleb support

The celleb code has seen no actual development for ~7 years.

We (maintainers) have no access to test hardware, and it is highly
likely the code has bit-rotted.

As far as we're aware the hardware was never widely available, and is
certainly no longer available, and no one on the list has shown any
interest in it over the years.

So remove it. If anyone has one and cares please speak up.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Jeremy Kerr <jk@ozlabs.org>
---
 arch/powerpc/kernel/udbg.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index b7aa07279a63..7cc38b5b58bc 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -46,8 +46,6 @@ void __init udbg_early_init(void)
 #elif defined(CONFIG_PPC_EARLY_DEBUG_MAPLE)
 	/* Maple real mode debug */
 	udbg_init_maple_realmode();
-#elif defined(CONFIG_PPC_EARLY_DEBUG_BEAT)
-	udbg_init_debug_beat();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_PAS_REALMODE)
 	udbg_init_pas_realmode();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_BOOTX)
-- 
cgit v1.2.3


From f691fa1080c37c48da0cdfeae082c3bef5df2643 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Mon, 30 Mar 2015 14:10:37 +1100
Subject: powerpc: Replace mem_init_done with slab_is_available()

We have a powerpc specific global called mem_init_done which is "set on
boot once kmalloc can be called".

But that's not *quite* true. We set it at the bottom of mem_init(), and
rely on the fact that mm_init() calls kmem_cache_init() immediately
after that, and nothing is running in parallel.

So replace it with the generic and 100% correct slab_is_available().

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/pci-common.c | 2 +-
 arch/powerpc/kernel/rtas.c       | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 2a525c938158..bcf618bfff1e 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -76,7 +76,7 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev)
 	list_add_tail(&phb->list_node, &hose_list);
 	spin_unlock(&hose_spinlock);
 	phb->dn = dev;
-	phb->is_dynamic = mem_init_done;
+	phb->is_dynamic = slab_is_available();
 #ifdef CONFIG_PPC64
 	if (dev) {
 		int nid = of_node_to_nid(dev);
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index b9a7b8981ef7..7a488c108410 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -401,7 +401,7 @@ static char *__fetch_rtas_last_error(char *altbuf)
 			buf = altbuf;
 		} else {
 			buf = rtas_err_buf;
-			if (mem_init_done)
+			if (slab_is_available())
 				buf = kmalloc(RTAS_ERROR_LOG_MAX, GFP_ATOMIC);
 		}
 		if (buf)
@@ -461,7 +461,7 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...)
 
 	if (buff_copy) {
 		log_error(buff_copy, ERR_TYPE_RTAS_LOG, 0);
-		if (mem_init_done)
+		if (slab_is_available())
 			kfree(buff_copy);
 	}
 	return ret;
-- 
cgit v1.2.3


From 7e862d7e7d118e3becc5b495af10ca076f087180 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Mon, 30 Mar 2015 17:38:09 +1100
Subject: powerpc: Reword the "returning from prom_init" message

We get way too many bug reports that say "the kernel is hung in
prom_init", which stems from the fact that the last piece of output
people see is "returning from prom_init".

The kernel is almost never hung in prom_init(), it's just that it's
crashed somewhere after prom_init() but prior to the console coming up.

The existing message should give a clue to that, ie. "returning from"
indicates that prom_init() has finished, but it doesn't seem to work.
Let's try something different.

This prints:

  Quiescing Open Firmware ...
  Booting Linux via __start() ...

Which hopefully makes it clear that prom_init() is not the problem, and
although __start() probably isn't either, it's at least the right place
to begin looking.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Wistfully-Acked-by: Jeremy Kerr <jk@ozlabs.org>
---
 arch/powerpc/kernel/prom_init.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 1a85d8f96739..fd1fe4c37599 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -2898,7 +2898,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	 * Call OF "quiesce" method to shut down pending DMA's from
 	 * devices etc...
 	 */
-	prom_printf("Calling quiesce...\n");
+	prom_printf("Quiescing Open Firmware ...\n");
 	call_prom("quiesce", 0, 0);
 
 	/*
@@ -2910,7 +2910,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 
 	/* Don't print anything after quiesce under OPAL, it crashes OFW */
 	if (of_platform != PLATFORM_OPAL) {
-		prom_printf("returning from prom_init\n");
+		prom_printf("Booting Linux via __start() ...\n");
 		prom_debug("->dt_header_start=0x%x\n", hdr);
 	}
 
-- 
cgit v1.2.3


From bdc728a849a7047e55014c6f968aa300cc9f57fa Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Tue, 31 Mar 2015 16:00:39 +1100
Subject: powerpc: move find_and_init_phbs() to pSeries specific code

Previously, find_and_init_phbs() was used in both PowerNV and pSeries
setup. However, since RTAS support has been dropped from PowerNV, we
can move it into a platform-specific file.

Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/rtas_pci.c | 47 ------------------------------------------
 1 file changed, 47 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index af29df2517f7..73f1934582c2 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -277,50 +277,3 @@ int rtas_setup_phb(struct pci_controller *phb)
 
 	return 0;
 }
-
-void __init find_and_init_phbs(void)
-{
-	struct device_node *node;
-	struct pci_controller *phb;
-	struct device_node *root = of_find_node_by_path("/");
-
-	for_each_child_of_node(root, node) {
-		if (node->type == NULL || (strcmp(node->type, "pci") != 0 &&
-					   strcmp(node->type, "pciex") != 0))
-			continue;
-
-		phb = pcibios_alloc_controller(node);
-		if (!phb)
-			continue;
-		rtas_setup_phb(phb);
-		pci_process_bridge_OF_ranges(phb, node, 0);
-		isa_bridge_find_early(phb);
-	}
-
-	of_node_put(root);
-	pci_devs_phb_init();
-
-	/*
-	 * PCI_PROBE_ONLY and PCI_REASSIGN_ALL_BUS can be set via properties
-	 * in chosen.
-	 */
-	if (of_chosen) {
-		const int *prop;
-
-		prop = of_get_property(of_chosen,
-				"linux,pci-probe-only", NULL);
-		if (prop) {
-			if (*prop)
-				pci_add_flags(PCI_PROBE_ONLY);
-			else
-				pci_clear_flags(PCI_PROBE_ONLY);
-		}
-
-#ifdef CONFIG_PPC32 /* Will be made generic soon */
-		prop = of_get_property(of_chosen,
-				"linux,pci-assign-all-buses", NULL);
-		if (prop && *prop)
-			pci_add_flags(PCI_REASSIGN_ALL_BUS);
-#endif /* CONFIG_PPC32 */
-	}
-}
-- 
cgit v1.2.3


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

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

Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/pci-common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index bcf618bfff1e..17827c7345a7 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1451,7 +1451,7 @@ EXPORT_SYMBOL_GPL(pcibios_finish_adding_to_bus);
 int pcibios_enable_device(struct pci_dev *dev, int mask)
 {
 	if (ppc_md.pcibios_enable_device_hook)
-		if (ppc_md.pcibios_enable_device_hook(dev))
+		if (!ppc_md.pcibios_enable_device_hook(dev))
 			return -EINVAL;
 
 	return pci_enable_resources(dev, mask);
-- 
cgit v1.2.3


From e02def5bce12b472e9eb6dcdd9f7af72239e6330 Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Tue, 31 Mar 2015 16:00:42 +1100
Subject: powerpc: Create pci_controller_ops.dma_dev_setup and shim

Introduces the pci_controller_ops structure.
Add pci_controller_ops.dma_dev_setup, shadowing ppc_md.pci_dma_dev_setup.
Add a shim, and change the callsites to use the shim.

Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/pci-common.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 17827c7345a7..7e3757e403d4 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -969,8 +969,7 @@ static void pcibios_setup_device(struct pci_dev *dev)
 	set_dma_offset(&dev->dev, PCI_DRAM_OFFSET);
 
 	/* Additional platform DMA/iommu setup */
-	if (ppc_md.pci_dma_dev_setup)
-		ppc_md.pci_dma_dev_setup(dev);
+	pci_dma_dev_setup(dev);
 
 	/* Read default IRQs and fixup if necessary */
 	pci_read_irq_line(dev);
-- 
cgit v1.2.3


From b122c95494374ab848f8d9f41d98644c2c318ecc Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Tue, 31 Mar 2015 16:00:43 +1100
Subject: powerpc: Create pci_controller_ops.dma_bus_setup and shim

Add pci_controller_ops.dma_bus_setup, shadowing ppc_md.pci_dma_bus_setup.
Add a shim, and changes the callsites to use the shim.

Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/pci-common.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 7e3757e403d4..af357cc38ff6 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -953,8 +953,7 @@ void pcibios_setup_bus_self(struct pci_bus *bus)
 		ppc_md.pcibios_fixup_bus(bus);
 
 	/* Setup bus DMA mappings */
-	if (ppc_md.pci_dma_bus_setup)
-		ppc_md.pci_dma_bus_setup(bus);
+	pci_dma_bus_setup(bus);
 }
 
 static void pcibios_setup_device(struct pci_dev *dev)
-- 
cgit v1.2.3


From ff9df8c87d6807e90c5c3b0e1fd1649d09fd3bcd Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Tue, 31 Mar 2015 16:00:44 +1100
Subject: powerpc: Create pci_controller_ops.probe_mode and shim

Add pci_controller_ops.probe_mode, shadowing ppc_md.pci_probe_mode.
Add a shim, and changes the callsites to use the shim.

We also need to move the probe mode defines to pci-bridge.h from pci.h.
They are required by the shim in order to return a sensible default.
Previously, the were defined in pci.h, but pci.h includes pci-bridge.h
before the relevant #defines. This means the definitions are absent
if pci.h is included before pci-bridge.h. This occurs in some drivers.
So, move the definitons now, and move them back when we remove the shim.

Anything that wants the defines would have had to include pci.h, and
since pci.h includes pci-bridge.h, nothing will lose access to the
defines.

Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/pci-common.c  | 4 ++--
 arch/powerpc/kernel/pci-hotplug.c | 3 +--
 arch/powerpc/kernel/pci_of_scan.c | 3 +--
 3 files changed, 4 insertions(+), 6 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index af357cc38ff6..b0de23c89ca5 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1622,8 +1622,8 @@ void pcibios_scan_phb(struct pci_controller *hose)
 
 	/* Get probe mode and perform scan */
 	mode = PCI_PROBE_NORMAL;
-	if (node && ppc_md.pci_probe_mode)
-		mode = ppc_md.pci_probe_mode(bus);
+	if (node)
+		mode = pci_probe_mode(bus);
 	pr_debug("    probe mode: %d\n", mode);
 	if (mode == PCI_PROBE_DEVTREE)
 		of_scan_bus(node, bus);
diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c
index 18d9575729a3..27116b1b2d14 100644
--- a/arch/powerpc/kernel/pci-hotplug.c
+++ b/arch/powerpc/kernel/pci-hotplug.c
@@ -78,8 +78,7 @@ void pcibios_add_pci_devices(struct pci_bus * bus)
 	eeh_add_device_tree_early(PCI_DN(dn));
 
 	mode = PCI_PROBE_NORMAL;
-	if (ppc_md.pci_probe_mode)
-		mode = ppc_md.pci_probe_mode(bus);
+	mode = pci_probe_mode(bus);
 
 	if (mode == PCI_PROBE_DEVTREE) {
 		/* use ofdt-based probe */
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index 7122dfece393..4ee63c4f077e 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -287,8 +287,7 @@ void of_scan_pci_bridge(struct pci_dev *dev)
 	pr_debug("    bus name: %s\n", bus->name);
 
 	mode = PCI_PROBE_NORMAL;
-	if (ppc_md.pci_probe_mode)
-		mode = ppc_md.pci_probe_mode(bus);
+	mode = pci_probe_mode(bus);
 	pr_debug("    probe mode: %d\n", mode);
 
 	if (mode == PCI_PROBE_DEVTREE)
-- 
cgit v1.2.3


From b31e79f8d92ca115a935e37cfd4da74048739689 Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Tue, 31 Mar 2015 16:00:45 +1100
Subject: powerpc: Create pci_controller_ops.enable_device_hook and shim

Add pci_controller_ops.enable_device_hook,
shadowing ppc_md.pcibios_enable_device_hook.
Add a shim, and changes the callsites to use the shim.

Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/pci-common.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index b0de23c89ca5..8639e9cd65d5 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1448,9 +1448,8 @@ EXPORT_SYMBOL_GPL(pcibios_finish_adding_to_bus);
 
 int pcibios_enable_device(struct pci_dev *dev, int mask)
 {
-	if (ppc_md.pcibios_enable_device_hook)
-		if (!ppc_md.pcibios_enable_device_hook(dev))
-			return -EINVAL;
+	if (!pcibios_enable_device_hook(dev))
+		return -EINVAL;
 
 	return pci_enable_resources(dev, mask);
 }
-- 
cgit v1.2.3


From 542070baf4a0fe9de14cc2c4ca3ff1b43f14f90f Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Tue, 31 Mar 2015 16:00:46 +1100
Subject: powerpc: Create pci_controller_ops.window_alignment and shim

Add pci_controller_ops.window_alignment,
shadowing ppc_md.pcibios_window_alignment.
Add a shim, and changes the callsites to use the shim.

Here, we use pci_window_alignment, as pcibios_window_alignment is
already taken.

Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/pci-common.c | 10 +---------
 1 file changed, 1 insertion(+), 9 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 8639e9cd65d5..698e0328d9c3 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -109,15 +109,7 @@ void pcibios_free_controller(struct pci_controller *phb)
 resource_size_t pcibios_window_alignment(struct pci_bus *bus,
 					 unsigned long type)
 {
-	if (ppc_md.pcibios_window_alignment)
-		return ppc_md.pcibios_window_alignment(bus, type);
-
-	/*
-	 * PCI core will figure out the default
-	 * alignment: 4KiB for I/O and 1MiB for
-	 * memory window.
-	 */
-	return 1;
+	return pci_window_alignment(bus, type);
 }
 
 void pcibios_reset_secondary_bus(struct pci_dev *dev)
-- 
cgit v1.2.3


From cd16c7ba0cc21aa1563e4b8430519b6488d0de60 Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Tue, 31 Mar 2015 16:00:47 +1100
Subject: powerpc: Create pci_controller_ops.reset_secondary_bus and shim

Add pci_controller_ops.reset_secondary_bus,
shadowing ppc_md.pcibios_reset_secondary_bus.
Add a shim, and changes the callsites to use the shim.

Use pcibios_reset_secondary_bus_shim, as both
pcibios_reset_secondary_bus and pci_reset_secondary_bus
are already taken.

Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/pci-common.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 698e0328d9c3..759eb1c87638 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -114,12 +114,7 @@ resource_size_t pcibios_window_alignment(struct pci_bus *bus,
 
 void pcibios_reset_secondary_bus(struct pci_dev *dev)
 {
-	if (ppc_md.pcibios_reset_secondary_bus) {
-		ppc_md.pcibios_reset_secondary_bus(dev);
-		return;
-	}
-
-	pci_reset_secondary_bus(dev);
+	pcibios_reset_secondary_bus_shim(dev);
 }
 
 static resource_size_t pcibios_io_size(const struct pci_controller *hose)
-- 
cgit v1.2.3


From 97884e00e29ad6654b8b6939bb805b9d6303427c Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Fri, 10 Apr 2015 13:15:47 +1000
Subject: powerpc: fsl_pci, swiotlb: Move controller ops from ppc_md to
 controller_ops

Move the installation of DMA operations out of swiotlb's subsys
initcall, and into the generic PCI controller operations struct.

These ops are installed conditionally, based on the ppc_swiotlb_enable
global. The global can be set in two places:
 - swiotlb_detect_4g, which is always called at the arch initcall level
 - setup_pci_atmu, which is called as part of the fsl_add_bridge and
fsl_pci_syscore_do_resume.

fsl_pci_syscore_do_resume is called late enough that any changes as a
result of that call will have no effect.

As such, if we test the global and set the operations as part of
fsl_add_bridge, after the call to setup_pci_atmu, we can be confident
that it will cover all the PCI implementations affected by the changes
to dma-swiotlb.c.

Signed-off-by: Daniel Axtens <dja@axtens.net>
Acked-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/dma-swiotlb.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index 735979764cd4..6e8d764ce47b 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -116,16 +116,13 @@ void __init swiotlb_detect_4g(void)
 	}
 }
 
-static int __init swiotlb_late_init(void)
+static int __init check_swiotlb_enabled(void)
 {
-	if (ppc_swiotlb_enable) {
+	if (ppc_swiotlb_enable)
 		swiotlb_print_info();
-		set_pci_dma_ops(&swiotlb_dma_ops);
-		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
-	} else {
+	else
 		swiotlb_free();
-	}
 
 	return 0;
 }
-subsys_initcall(swiotlb_late_init);
+subsys_initcall(check_swiotlb_enabled);
-- 
cgit v1.2.3


From 467efc2e4fdc44e6cd4be7dd4adf01c14b3d148e Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Tue, 31 Mar 2015 16:00:56 +1100
Subject: powerpc: Remove shims for pci_controller_ops operations

Remove shims, patch callsites to use pci_controller_ops
versions instead.

Also move back the probe mode defines, as explained in the patch
for pci_probe_mode.

Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/pci-common.c  | 43 +++++++++++++++++++++++++++++++--------
 arch/powerpc/kernel/pci-hotplug.c |  6 +++++-
 arch/powerpc/kernel/pci_of_scan.c |  6 +++++-
 3 files changed, 45 insertions(+), 10 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 759eb1c87638..9052b4fbc41f 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -109,12 +109,29 @@ void pcibios_free_controller(struct pci_controller *phb)
 resource_size_t pcibios_window_alignment(struct pci_bus *bus,
 					 unsigned long type)
 {
-	return pci_window_alignment(bus, type);
+	struct pci_controller *phb = pci_bus_to_host(bus);
+
+	if (phb->controller_ops.window_alignment)
+		return phb->controller_ops.window_alignment(bus, type);
+
+	/*
+	 * PCI core will figure out the default
+	 * alignment: 4KiB for I/O and 1MiB for
+	 * memory window.
+	 */
+	return 1;
 }
 
 void pcibios_reset_secondary_bus(struct pci_dev *dev)
 {
-	pcibios_reset_secondary_bus_shim(dev);
+	struct pci_controller *phb = pci_bus_to_host(dev->bus);
+
+	if (phb->controller_ops.reset_secondary_bus) {
+		phb->controller_ops.reset_secondary_bus(dev);
+		return;
+	}
+
+	pci_reset_secondary_bus(dev);
 }
 
 static resource_size_t pcibios_io_size(const struct pci_controller *hose)
@@ -929,6 +946,8 @@ static void pcibios_fixup_bridge(struct pci_bus *bus)
 
 void pcibios_setup_bus_self(struct pci_bus *bus)
 {
+	struct pci_controller *phb;
+
 	/* Fix up the bus resources for P2P bridges */
 	if (bus->self != NULL)
 		pcibios_fixup_bridge(bus);
@@ -940,11 +959,14 @@ void pcibios_setup_bus_self(struct pci_bus *bus)
 		ppc_md.pcibios_fixup_bus(bus);
 
 	/* Setup bus DMA mappings */
-	pci_dma_bus_setup(bus);
+	phb = pci_bus_to_host(bus);
+	if (phb->controller_ops.dma_bus_setup)
+		phb->controller_ops.dma_bus_setup(bus);
 }
 
 static void pcibios_setup_device(struct pci_dev *dev)
 {
+	struct pci_controller *phb;
 	/* Fixup NUMA node as it may not be setup yet by the generic
 	 * code and is needed by the DMA init
 	 */
@@ -955,7 +977,9 @@ static void pcibios_setup_device(struct pci_dev *dev)
 	set_dma_offset(&dev->dev, PCI_DRAM_OFFSET);
 
 	/* Additional platform DMA/iommu setup */
-	pci_dma_dev_setup(dev);
+	phb = pci_bus_to_host(dev->bus);
+	if (phb->controller_ops.dma_dev_setup)
+		phb->controller_ops.dma_dev_setup(dev);
 
 	/* Read default IRQs and fixup if necessary */
 	pci_read_irq_line(dev);
@@ -1435,8 +1459,11 @@ EXPORT_SYMBOL_GPL(pcibios_finish_adding_to_bus);
 
 int pcibios_enable_device(struct pci_dev *dev, int mask)
 {
-	if (!pcibios_enable_device_hook(dev))
-		return -EINVAL;
+	struct pci_controller *phb = pci_bus_to_host(dev->bus);
+
+	if (phb->controller_ops.enable_device_hook)
+		if (!phb->controller_ops.enable_device_hook(dev))
+			return -EINVAL;
 
 	return pci_enable_resources(dev, mask);
 }
@@ -1608,8 +1635,8 @@ void pcibios_scan_phb(struct pci_controller *hose)
 
 	/* Get probe mode and perform scan */
 	mode = PCI_PROBE_NORMAL;
-	if (node)
-		mode = pci_probe_mode(bus);
+	if (node && hose->controller_ops.probe_mode)
+		mode = hose->controller_ops.probe_mode(bus);
 	pr_debug("    probe mode: %d\n", mode);
 	if (mode == PCI_PROBE_DEVTREE)
 		of_scan_bus(node, bus);
diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c
index 27116b1b2d14..7ed85a69a9c2 100644
--- a/arch/powerpc/kernel/pci-hotplug.c
+++ b/arch/powerpc/kernel/pci-hotplug.c
@@ -73,12 +73,16 @@ void pcibios_add_pci_devices(struct pci_bus * bus)
 {
 	int slotno, mode, pass, max;
 	struct pci_dev *dev;
+	struct pci_controller *phb;
 	struct device_node *dn = pci_bus_to_OF_node(bus);
 
 	eeh_add_device_tree_early(PCI_DN(dn));
 
+	phb = pci_bus_to_host(bus);
+
 	mode = PCI_PROBE_NORMAL;
-	mode = pci_probe_mode(bus);
+	if (phb->controller_ops.probe_mode)
+		mode = phb->controller_ops.probe_mode(bus);
 
 	if (mode == PCI_PROBE_DEVTREE) {
 		/* use ofdt-based probe */
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index 4ee63c4f077e..42e02a2d570b 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -207,6 +207,7 @@ void of_scan_pci_bridge(struct pci_dev *dev)
 {
 	struct device_node *node = dev->dev.of_node;
 	struct pci_bus *bus;
+	struct pci_controller *phb;
 	const __be32 *busrange, *ranges;
 	int len, i, mode;
 	struct pci_bus_region region;
@@ -286,8 +287,11 @@ void of_scan_pci_bridge(struct pci_dev *dev)
 		bus->number);
 	pr_debug("    bus name: %s\n", bus->name);
 
+	phb = pci_bus_to_host(bus);
+
 	mode = PCI_PROBE_NORMAL;
-	mode = pci_probe_mode(bus);
+	if (phb->controller_ops.probe_mode)
+		mode = phb->controller_ops.probe_mode(bus);
 	pr_debug("    probe mode: %d\n", mode);
 
 	if (mode == PCI_PROBE_DEVTREE)
-- 
cgit v1.2.3


From feba40362b11341bee6d8ed58d54b896abbd9f84 Mon Sep 17 00:00:00 2001
From: Sam bobroff <sam.bobroff@au1.ibm.com>
Date: Fri, 10 Apr 2015 14:16:47 +1000
Subject: powerpc/tm: Abort syscalls in active transactions

This patch changes the syscall handler to doom (tabort) active
transactions when a syscall is made and return immediately without
performing the syscall.

Currently, the system call instruction automatically suspends an
active transaction which causes side effects to persist when an active
transaction fails.

This does change the kernel's behaviour, but in a way that was
documented as unsupported. It doesn't reduce functionality because
syscalls will still be performed after tsuspend. It also provides a
consistent interface and makes the behaviour of user code
substantially the same across powerpc and platforms that do not
support suspended transactions (e.g. x86 and s390).

Performance measurements using
http://ozlabs.org/~anton/junkcode/null_syscall.c
indicate the cost of a system call increases by about 0.5%.

Signed-off-by: Sam Bobroff <sam.bobroff@au1.ibm.com>
Acked-By: Michael Neuling <mikey@neuling.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/entry_64.S | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index afbc20019c2e..8ca9434c40e6 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -34,6 +34,7 @@
 #include <asm/ftrace.h>
 #include <asm/hw_irq.h>
 #include <asm/context_tracking.h>
+#include <asm/tm.h>
 
 /*
  * System calls.
@@ -145,6 +146,24 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 	andi.	r11,r10,_TIF_SYSCALL_DOTRACE
 	bne	syscall_dotrace
 .Lsyscall_dotrace_cont:
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+	b	1f
+END_FTR_SECTION_IFCLR(CPU_FTR_TM)
+	extrdi.	r11, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */
+	beq+	1f
+
+	/* Doom the transaction and don't perform the syscall: */
+	mfmsr	r11
+	li	r12, 1
+	rldimi	r11, r12, MSR_TM_LG, 63-MSR_TM_LG
+	mtmsrd	r11, 0
+	li	r11, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
+	TABORT(R11)
+
+	b	.Lsyscall_exit
+1:
+#endif
 	cmpldi	0,r0,NR_syscalls
 	bge-	syscall_enosys
 
-- 
cgit v1.2.3


From c54b2bf1b5e99760d53ea0376e96a046f93df6ae Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Thu, 9 Apr 2015 12:52:56 +1000
Subject: powerpc: Add ppc64 hard lockup detector support

The hard lockup detector uses a PMU event as a periodic NMI to
detect if we are stuck (where stuck means no timer interrupts have
occurred).

Ben's rework of the ppc64 soft disable code has made ppc64 PMU
exceptions a partial NMI. They can get disabled if an external
interrupt comes in, but otherwise PMU interrupts will fire in
interrupt disabled regions.

We disable the hard lockup detector by default for a few reasons:

- It breaks userspace event based branches on POWER8.
- It is likely to produce false positives on KVM guests.
- Since PMCs can only count to 2^31, counting cycles means we might
  take multiple PMU exceptions per second per hardware thread even
  if our hard lockup timeout is 10 seconds.

It can be enabled via a boot option, or via procfs.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/setup_64.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 49f553bbb360..7551e5692597 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -37,6 +37,7 @@
 #include <linux/memblock.h>
 #include <linux/hugetlb.h>
 #include <linux/memory.h>
+#include <linux/nmi.h>
 
 #include <asm/io.h>
 #include <asm/kdump.h>
@@ -779,3 +780,22 @@ unsigned long memory_block_size_bytes(void)
 struct ppc_pci_io ppc_pci_io;
 EXPORT_SYMBOL(ppc_pci_io);
 #endif
+
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
+u64 hw_nmi_get_sample_period(int watchdog_thresh)
+{
+	return ppc_proc_freq * watchdog_thresh;
+}
+
+/*
+ * The hardlockup detector breaks PMU event based branches and is likely
+ * to get false positives in KVM guests, so disable it by default.
+ */
+static int __init disable_hardlockup_detector(void)
+{
+	watchdog_enable_hardlockup_detector(false);
+
+	return 0;
+}
+early_initcall(disable_hardlockup_detector);
+#endif
-- 
cgit v1.2.3


From f7e9e358362557c3aa2c1ec47490f29fe880a09e Mon Sep 17 00:00:00 2001
From: Dave Olson <olson@cumulusnetworks.com>
Date: Thu, 2 Apr 2015 21:28:45 -0700
Subject: powerpc: Fix missing L2 cache size in /sys/devices/system/cpu

This problem appears to have been introduced in 2.6.29 by commit
93197a36a9c1 "Rewrite sysfs processor cache info code".

This caused lscpu to error out on at least e500v2 devices, eg:

  error: cannot open /sys/devices/system/cpu/cpu0/cache/index2/size: No such file or directory

Some embedded powerpc systems use cache-size in DTS for the unified L2
cache size, not d-cache-size, so we need to allow for both DTS names.
Added a new CACHE_TYPE_UNIFIED_D cache_type_info structure to handle
this.

Fixes: 93197a36a9c1 ("powerpc: Rewrite sysfs processor cache info code")
Signed-off-by: Dave Olson <olson@cumulusnetworks.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/cacheinfo.c | 44 +++++++++++++++++++++++++++++++----------
 1 file changed, 34 insertions(+), 10 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index ae77b7e59889..c641983bbdd6 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -61,11 +61,21 @@ struct cache_type_info {
 };
 
 /* These are used to index the cache_type_info array. */
-#define CACHE_TYPE_UNIFIED     0
-#define CACHE_TYPE_INSTRUCTION 1
-#define CACHE_TYPE_DATA        2
+#define CACHE_TYPE_UNIFIED     0 /* cache-size, cache-block-size, etc. */
+#define CACHE_TYPE_UNIFIED_D   1 /* d-cache-size, d-cache-block-size, etc */
+#define CACHE_TYPE_INSTRUCTION 2
+#define CACHE_TYPE_DATA        3
 
 static const struct cache_type_info cache_type_info[] = {
+	{
+		/* Embedded systems that use cache-size, cache-block-size,
+		 * etc. for the Unified (typically L2) cache. */
+		.name            = "Unified",
+		.size_prop       = "cache-size",
+		.line_size_props = { "cache-line-size",
+				     "cache-block-size", },
+		.nr_sets_prop    = "cache-sets",
+	},
 	{
 		/* PowerPC Processor binding says the [di]-cache-*
 		 * must be equal on unified caches, so just use
@@ -293,7 +303,8 @@ static struct cache *cache_find_first_sibling(struct cache *cache)
 {
 	struct cache *iter;
 
-	if (cache->type == CACHE_TYPE_UNIFIED)
+	if (cache->type == CACHE_TYPE_UNIFIED ||
+	    cache->type == CACHE_TYPE_UNIFIED_D)
 		return cache;
 
 	list_for_each_entry(iter, &cache_list, list)
@@ -324,16 +335,29 @@ static bool cache_node_is_unified(const struct device_node *np)
 	return of_get_property(np, "cache-unified", NULL);
 }
 
-static struct cache *cache_do_one_devnode_unified(struct device_node *node,
-						  int level)
+/*
+ * Unified caches can have two different sets of tags.  Most embedded
+ * use cache-size, etc. for the unified cache size, but open firmware systems
+ * use d-cache-size, etc.   Check on initialization for which type we have, and
+ * return the appropriate structure type.  Assume it's embedded if it isn't
+ * open firmware.  If it's yet a 3rd type, then there will be missing entries
+ * in /sys/devices/system/cpu/cpu0/cache/index2/, and this code will need
+ * to be extended further.
+ */
+static int cache_is_unified_d(const struct device_node *np)
 {
-	struct cache *cache;
+	return of_get_property(np,
+		cache_type_info[CACHE_TYPE_UNIFIED_D].size_prop, NULL) ?
+		CACHE_TYPE_UNIFIED_D : CACHE_TYPE_UNIFIED;
+}
 
+/*
+ */
+static struct cache *cache_do_one_devnode_unified(struct device_node *node, int level)
+{
 	pr_debug("creating L%d ucache for %s\n", level, node->full_name);
 
-	cache = new_cache(CACHE_TYPE_UNIFIED, level, node);
-
-	return cache;
+	return new_cache(cache_is_unified_d(node), level, node);
 }
 
 static struct cache *cache_do_one_devnode_split(struct device_node *node,
-- 
cgit v1.2.3


From 89a51df5ab1d38b257300b8ac940bbac3bb0eb9b Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Tue, 14 Apr 2015 16:49:05 +1000
Subject: powerpc/eeh: Fix crash in eeh_add_device_early() on Cell

The recent change to the EEH probing causes a crash on Cell because
eeh_ops is NULL.

Check if EEH is enabled and if not bail out.

Fixes: ff57b454ddb9 ("powerpc/eeh: Do probe on pci_dn")
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/eeh.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 76253eb146be..a4c62eb0ee48 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -1053,7 +1053,7 @@ void eeh_add_device_early(struct pci_dn *pdn)
 	struct pci_controller *phb;
 	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
 
-	if (!edev)
+	if (!edev || !eeh_enabled())
 		return;
 
 	/* USB Bus children of PCI devices will not have BUID's */
-- 
cgit v1.2.3


From 691e95fd7396905a38d98919e9c150dbc3ea21a3 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Mon, 30 Mar 2015 10:41:03 +0530
Subject: powerpc/mm/thp: Make page table walk safe against thp split/collapse

We can disable a THP split or a hugepage collapse by disabling irq.
We do send IPI to all the cpus in the early part of split/collapse,
and disabling local irq ensure we don't make progress with
split/collapse. If the THP is getting split we return NULL from
find_linux_pte_or_hugepte(). For all the current callers it should be ok.
We need to be careful if we want to use returned pte_t pointer outside
the irq disabled region. W.r.t to THP split, the pfn remains the same,
but then a hugepage collapse will result in a pfn change. There are
few steps we can take to avoid a hugepage collapse.One way is to take page
reference inside the irq disable region. Other option is to take
mmap_sem so that a parallel collapse will not happen. We can also
disable collapse by taking pmd_lock. Another method used by kvm
subsystem is to check whether we had a mmu_notifer update in between
using mmu_notifier_retry().

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 arch/powerpc/kernel/eeh.c            |  6 ++++--
 arch/powerpc/kernel/io-workarounds.c | 10 +++++-----
 2 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index a4c62eb0ee48..44b480e3a5af 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -334,9 +334,11 @@ static inline unsigned long eeh_token_to_phys(unsigned long token)
 	int hugepage_shift;
 
 	/*
-	 * We won't find hugepages here, iomem
+	 * We won't find hugepages here(this is iomem). Hence we are not
+	 * worried about _PAGE_SPLITTING/collapse. Also we will not hit
+	 * page table free, because of init_mm.
 	 */
-	ptep = find_linux_pte_or_hugepte(init_mm.pgd, token, &hugepage_shift);
+	ptep = __find_linux_pte_or_hugepte(init_mm.pgd, token, &hugepage_shift);
 	if (!ptep)
 		return token;
 	WARN_ON(hugepage_shift);
diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c
index 24b968f8e4d8..63d9cc4d7366 100644
--- a/arch/powerpc/kernel/io-workarounds.c
+++ b/arch/powerpc/kernel/io-workarounds.c
@@ -71,15 +71,15 @@ struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
 		vaddr = (unsigned long)PCI_FIX_ADDR(addr);
 		if (vaddr < PHB_IO_BASE || vaddr >= PHB_IO_END)
 			return NULL;
-
-		ptep = find_linux_pte_or_hugepte(init_mm.pgd, vaddr,
+		/*
+		 * We won't find huge pages here (iomem). Also can't hit
+		 * a page table free due to init_mm
+		 */
+		ptep = __find_linux_pte_or_hugepte(init_mm.pgd, vaddr,
 						 &hugepage_shift);
 		if (ptep == NULL)
 			paddr = 0;
 		else {
-			/*
-			 * we don't have hugepages backing iomem
-			 */
 			WARN_ON(hugepage_shift);
 			paddr = pte_pfn(*ptep) << PAGE_SHIFT;
 		}
-- 
cgit v1.2.3


From b6c295df3131c6fa25f8f29625ee0609506150ad Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Sat, 28 Mar 2015 14:21:02 +1100
Subject: KVM: PPC: Book3S HV: Accumulate timing information for real-mode code

This reads the timebase at various points in the real-mode guest
entry/exit code and uses that to accumulate total, minimum and
maximum time spent in those parts of the code.  Currently these
times are accumulated per vcpu in 5 parts of the code:

* rm_entry - time taken from the start of kvmppc_hv_entry() until
  just before entering the guest.
* rm_intr - time from when we take a hypervisor interrupt in the
  guest until we either re-enter the guest or decide to exit to the
  host.  This includes time spent handling hcalls in real mode.
* rm_exit - time from when we decide to exit the guest until the
  return from kvmppc_hv_entry().
* guest - time spend in the guest
* cede - time spent napping in real mode due to an H_CEDE hcall
  while other threads in the same vcore are active.

These times are exposed in debugfs in a directory per vcpu that
contains a file called "timings".  This file contains one line for
each of the 5 timings above, with the name followed by a colon and
4 numbers, which are the count (number of times the code has been
executed), the total time, the minimum time, and the maximum time,
all in nanoseconds.

The overhead of the extra code amounts to about 30ns for an hcall that
is handled in real mode (e.g. H_SET_DABR), which is about 25%.  Since
production environments may not wish to incur this overhead, the new
code is conditional on a new config symbol,
CONFIG_KVM_BOOK3S_HV_EXIT_TIMING.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/asm-offsets.c | 13 +++++++++++++
 arch/powerpc/kernel/time.c        |  6 ++++++
 2 files changed, 19 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 4717859fdd04..3fea721f0da5 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -458,6 +458,19 @@ int main(void)
 	DEFINE(VCPU_SPRG1, offsetof(struct kvm_vcpu, arch.shregs.sprg1));
 	DEFINE(VCPU_SPRG2, offsetof(struct kvm_vcpu, arch.shregs.sprg2));
 	DEFINE(VCPU_SPRG3, offsetof(struct kvm_vcpu, arch.shregs.sprg3));
+#endif
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+	DEFINE(VCPU_TB_RMENTRY, offsetof(struct kvm_vcpu, arch.rm_entry));
+	DEFINE(VCPU_TB_RMINTR, offsetof(struct kvm_vcpu, arch.rm_intr));
+	DEFINE(VCPU_TB_RMEXIT, offsetof(struct kvm_vcpu, arch.rm_exit));
+	DEFINE(VCPU_TB_GUEST, offsetof(struct kvm_vcpu, arch.guest_time));
+	DEFINE(VCPU_TB_CEDE, offsetof(struct kvm_vcpu, arch.cede_time));
+	DEFINE(VCPU_CUR_ACTIVITY, offsetof(struct kvm_vcpu, arch.cur_activity));
+	DEFINE(VCPU_ACTIVITY_START, offsetof(struct kvm_vcpu, arch.cur_tb_start));
+	DEFINE(TAS_SEQCOUNT, offsetof(struct kvmhv_tb_accumulator, seqcount));
+	DEFINE(TAS_TOTAL, offsetof(struct kvmhv_tb_accumulator, tb_total));
+	DEFINE(TAS_MIN, offsetof(struct kvmhv_tb_accumulator, tb_min));
+	DEFINE(TAS_MAX, offsetof(struct kvmhv_tb_accumulator, tb_max));
 #endif
 	DEFINE(VCPU_SHARED_SPRG3, offsetof(struct kvm_vcpu_arch_shared, sprg3));
 	DEFINE(VCPU_SHARED_SPRG4, offsetof(struct kvm_vcpu_arch_shared, sprg4));
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 2d7b33fab953..56f44848b044 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -608,6 +608,12 @@ void arch_suspend_enable_irqs(void)
 }
 #endif
 
+unsigned long long tb_to_ns(unsigned long long ticks)
+{
+	return mulhdu(ticks, tb_to_ns_scale) << tb_to_ns_shift;
+}
+EXPORT_SYMBOL_GPL(tb_to_ns);
+
 /*
  * Scheduler clock - returns current time in nanosec units.
  *
-- 
cgit v1.2.3


From 1f09c3ed86287d40fef90611cbbee055313f52cf Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Sat, 28 Mar 2015 14:21:04 +1100
Subject: KVM: PPC: Book3S HV: Minor cleanups

* Remove unused kvmppc_vcore::n_busy field.
* Remove setting of RMOR, since it was only used on PPC970 and the
  PPC970 KVM support has been removed.
* Don't use r1 or r2 in setting the runlatch since they are
  conventionally reserved for other things; use r0 instead.
* Streamline the code a little and remove the ext_interrupt_to_host
  label.
* Add some comments about register usage.
* hcall_try_real_mode doesn't need to be global, and can't be
  called from C code anyway.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/asm-offsets.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 3fea721f0da5..92ec3fcb3415 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -505,7 +505,6 @@ int main(void)
 	DEFINE(KVM_NEED_FLUSH, offsetof(struct kvm, arch.need_tlb_flush.bits));
 	DEFINE(KVM_ENABLED_HCALLS, offsetof(struct kvm, arch.enabled_hcalls));
 	DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr));
-	DEFINE(KVM_RMOR, offsetof(struct kvm, arch.rmor));
 	DEFINE(KVM_VRMA_SLB_V, offsetof(struct kvm, arch.vrma_slb_v));
 	DEFINE(VCPU_DSISR, offsetof(struct kvm_vcpu, arch.shregs.dsisr));
 	DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar));
-- 
cgit v1.2.3


From 5d5b99cd6818bdbea287d23ef055bba1a8a9e648 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Sat, 28 Mar 2015 14:21:06 +1100
Subject: KVM: PPC: Book3S HV: Get rid of vcore nap_count and n_woken

We can tell when a secondary thread has finished running a guest by
the fact that it clears its kvm_hstate.kvm_vcpu pointer, so there
is no real need for the nap_count field in the kvmppc_vcore struct.
This changes kvmppc_wait_for_nap to poll the kvm_hstate.kvm_vcpu
pointers of the secondary threads rather than polling vc->nap_count.
Besides reducing the size of the kvmppc_vcore struct by 8 bytes,
this also means that we can tell which secondary threads have got
stuck and thus print a more informative error message.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/asm-offsets.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 92ec3fcb3415..8aa824681d76 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -563,7 +563,6 @@ int main(void)
 	DEFINE(VCPU_WORT, offsetof(struct kvm_vcpu, arch.wort));
 	DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1));
 	DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count));
-	DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count));
 	DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
 	DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
 	DEFINE(VCORE_KVM, offsetof(struct kvmppc_vcore, kvm));
-- 
cgit v1.2.3


From 7d6c40da198ac18bd5dd2cd18628d5b4c615d842 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Sat, 28 Mar 2015 14:21:09 +1100
Subject: KVM: PPC: Book3S HV: Use bitmap of active threads rather than count

Currently, the entry_exit_count field in the kvmppc_vcore struct
contains two 8-bit counts, one of the threads that have started entering
the guest, and one of the threads that have started exiting the guest.
This changes it to an entry_exit_map field which contains two bitmaps
of 8 bits each.  The advantage of doing this is that it gives us a
bitmap of which threads need to be signalled when exiting the guest.
That means that we no longer need to use the trick of setting the
HDEC to 0 to pull the other threads out of the guest, which led in
some cases to a spurious HDEC interrupt on the next guest entry.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/asm-offsets.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 8aa824681d76..0d07efbe3fa7 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -562,7 +562,7 @@ int main(void)
 	DEFINE(VCPU_ACOP, offsetof(struct kvm_vcpu, arch.acop));
 	DEFINE(VCPU_WORT, offsetof(struct kvm_vcpu, arch.wort));
 	DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1));
-	DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count));
+	DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_map));
 	DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
 	DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
 	DEFINE(VCORE_KVM, offsetof(struct kvmppc_vcore, kvm));
-- 
cgit v1.2.3


From 66feed61cdf6ee65fd551d3460b1efba6bee55b8 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Sat, 28 Mar 2015 14:21:12 +1100
Subject: KVM: PPC: Book3S HV: Use msgsnd for signalling threads on POWER8

This uses msgsnd where possible for signalling other threads within
the same core on POWER8 systems, rather than IPIs through the XICS
interrupt controller.  This includes waking secondary threads to run
the guest, the interrupts generated by the virtual XICS, and the
interrupts to bring the other threads out of the guest when exiting.

Aggregated statistics from debugfs across vcpus for a guest with 32
vcpus, 8 threads/vcore, running on a POWER8, show this before the
change:

 rm_entry:     3387.6ns (228 - 86600, 1008969 samples)
  rm_exit:     4561.5ns (12 - 3477452, 1009402 samples)
  rm_intr:     1660.0ns (12 - 553050, 3600051 samples)

and this after the change:

 rm_entry:     3060.1ns (212 - 65138, 953873 samples)
  rm_exit:     4244.1ns (12 - 9693408, 954331 samples)
  rm_intr:     1342.3ns (12 - 1104718, 3405326 samples)

for a test of booting Fedora 20 big-endian to the login prompt.

The time taken for a H_PROD hcall (which is handled in the host
kernel) went down from about 35 microseconds to about 16 microseconds
with this change.

The noinline added to kvmppc_run_core turned out to be necessary for
good performance, at least with gcc 4.9.2 as packaged with Fedora 21
and a little-endian POWER8 host.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/asm-offsets.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/powerpc/kernel')

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 0d07efbe3fa7..0034b6b3556a 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -37,6 +37,7 @@
 #include <asm/thread_info.h>
 #include <asm/rtas.h>
 #include <asm/vdso_datapage.h>
+#include <asm/dbell.h>
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
 #include <asm/lppaca.h>
@@ -759,5 +760,7 @@ int main(void)
 			offsetof(struct paca_struct, subcore_sibling_mask));
 #endif
 
+	DEFINE(PPC_DBELL_SERVER, PPC_DBELL_SERVER);
+
 	return 0;
 }
-- 
cgit v1.2.3