From cadbb58039f7cab1def9c931012ab04c953a6997 Mon Sep 17 00:00:00 2001
From: Allen Pais <allen.pais@oracle.com>
Date: Mon, 8 Sep 2014 11:48:53 +0530
Subject: sparc64: correctly recognise M6 and M7 cpu type

The following patch adds support for correctly
recognising M6 and M7 cpu type.

Signed-off-by: Allen Pais <allen.pais@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/include/asm/spitfire.h |  2 ++
 arch/sparc/kernel/cpu.c           | 12 ++++++++++++
 arch/sparc/kernel/head_64.S       | 12 ++++++++++++
 3 files changed, 26 insertions(+)

diff --git a/arch/sparc/include/asm/spitfire.h b/arch/sparc/include/asm/spitfire.h
index 3fc58691dbd0..56f933816144 100644
--- a/arch/sparc/include/asm/spitfire.h
+++ b/arch/sparc/include/asm/spitfire.h
@@ -45,6 +45,8 @@
 #define SUN4V_CHIP_NIAGARA3	0x03
 #define SUN4V_CHIP_NIAGARA4	0x04
 #define SUN4V_CHIP_NIAGARA5	0x05
+#define SUN4V_CHIP_SPARC_M6	0x06
+#define SUN4V_CHIP_SPARC_M7	0x07
 #define SUN4V_CHIP_SPARC64X	0x8a
 #define SUN4V_CHIP_UNKNOWN	0xff
 
diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c
index 82a3a71c451e..dfad8b1aea9f 100644
--- a/arch/sparc/kernel/cpu.c
+++ b/arch/sparc/kernel/cpu.c
@@ -494,6 +494,18 @@ static void __init sun4v_cpu_probe(void)
 		sparc_pmu_type = "niagara5";
 		break;
 
+	case SUN4V_CHIP_SPARC_M6:
+		sparc_cpu_type = "SPARC-M6";
+		sparc_fpu_type = "SPARC-M6 integrated FPU";
+		sparc_pmu_type = "sparc-m6";
+		break;
+
+	case SUN4V_CHIP_SPARC_M7:
+		sparc_cpu_type = "SPARC-M7";
+		sparc_fpu_type = "SPARC-M7 integrated FPU";
+		sparc_pmu_type = "sparc-m7";
+		break;
+
 	case SUN4V_CHIP_SPARC64X:
 		sparc_cpu_type = "SPARC64-X";
 		sparc_fpu_type = "SPARC64-X integrated FPU";
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index 452f04fe8da6..4fdeb8040d4d 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -427,6 +427,12 @@ sun4v_chip_type:
 	cmp	%g2, '5'
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_NIAGARA5, %g4
+	cmp	%g2, '6'
+	be,pt	%xcc, 5f
+	 mov	SUN4V_CHIP_SPARC_M6, %g4
+	cmp	%g2, '7'
+	be,pt	%xcc, 5f
+	 mov	SUN4V_CHIP_SPARC_M7, %g4
 	ba,pt	%xcc, 49f
 	 nop
 
@@ -583,6 +589,12 @@ niagara_tlb_fixup:
 	be,pt	%xcc, niagara4_patch
 	 nop
 	cmp	%g1, SUN4V_CHIP_NIAGARA5
+	be,pt	%xcc, niagara4_patch
+	 nop
+	cmp	%g1, SUN4V_CHIP_SPARC_M6
+	be,pt	%xcc, niagara4_patch
+	 nop
+	cmp	%g1, SUN4V_CHIP_SPARC_M7
 	be,pt	%xcc, niagara4_patch
 	 nop
 
-- 
cgit v1.2.2


From 9bd3ee33f6b97de092610d8dcabc4cb98d99505c Mon Sep 17 00:00:00 2001
From: Allen Pais <allen.pais@oracle.com>
Date: Mon, 8 Sep 2014 11:48:54 +0530
Subject: sparc64: support M6 and M7 for building CPU distribution map

Add M6 and M7 chip type in cpumap.c to correctly build CPU distribution map that spans all online CPUs.

Signed-off-by: Allen Pais <allen.pais@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/kernel/cpumap.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/sparc/kernel/cpumap.c b/arch/sparc/kernel/cpumap.c
index de1c844dfabc..e69ec0e3f155 100644
--- a/arch/sparc/kernel/cpumap.c
+++ b/arch/sparc/kernel/cpumap.c
@@ -326,6 +326,8 @@ static int iterate_cpu(struct cpuinfo_tree *t, unsigned int root_index)
 	case SUN4V_CHIP_NIAGARA3:
 	case SUN4V_CHIP_NIAGARA4:
 	case SUN4V_CHIP_NIAGARA5:
+	case SUN4V_CHIP_SPARC_M6:
+	case SUN4V_CHIP_SPARC_M7:
 	case SUN4V_CHIP_SPARC64X:
 		rover_inc_table = niagara_iterate_method;
 		break;
-- 
cgit v1.2.2


From 408316258521168614bfb4da0e070490d3e65a17 Mon Sep 17 00:00:00 2001
From: Allen Pais <allen.pais@oracle.com>
Date: Mon, 8 Sep 2014 11:48:55 +0530
Subject: sparc64: cpu hardware caps support for sparc M6 and M7

Signed-off-by: Allen Pais <allen.pais@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/kernel/setup_64.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index 3fdb455e3318..1c7bfdf83b66 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -500,12 +500,16 @@ static void __init init_sparc64_elf_hwcap(void)
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 			cap |= HWCAP_SPARC_BLKINIT;
 		if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
+		    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
 		    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 			cap |= HWCAP_SPARC_N2;
 	}
@@ -533,6 +537,8 @@ static void __init init_sparc64_elf_hwcap(void)
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 				cap |= (AV_SPARC_VIS | AV_SPARC_VIS2 |
 					AV_SPARC_ASI_BLK_INIT |
@@ -540,6 +546,8 @@ static void __init init_sparc64_elf_hwcap(void)
 			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
 			    sun4v_chip_type == SUN4V_CHIP_NIAGARA5 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC_M6 ||
+			    sun4v_chip_type == SUN4V_CHIP_SPARC_M7 ||
 			    sun4v_chip_type == SUN4V_CHIP_SPARC64X)
 				cap |= (AV_SPARC_VIS3 | AV_SPARC_HPC |
 					AV_SPARC_FMAF);
-- 
cgit v1.2.2


From 74cad25c076a2f5253312c2fe82d1a4daecc1323 Mon Sep 17 00:00:00 2001
From: Andreas Larsson <andreas@gaisler.com>
Date: Fri, 29 Aug 2014 17:08:21 +0200
Subject: sparc: Let memset return the address argument

This makes memset follow the standard (instead of returning 0 on success). This
is needed when certain versions of gcc optimizes around memset calls and assume
that the address argument is preserved in %o0.

Signed-off-by: Andreas Larsson <andreas@gaisler.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/lib/memset.S | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/arch/sparc/lib/memset.S b/arch/sparc/lib/memset.S
index 99c017be8719..f75e6906df14 100644
--- a/arch/sparc/lib/memset.S
+++ b/arch/sparc/lib/memset.S
@@ -3,8 +3,9 @@
  * Copyright (C) 1996,1997 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
  * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
  *
- * Returns 0, if ok, and number of bytes not yet set if exception
- * occurs and we were called as clear_user.
+ * Calls to memset returns initial %o0. Calls to bzero returns 0, if ok, and
+ * number of bytes not yet set if exception occurs and we were called as
+ * clear_user.
  */
 
 #include <asm/ptrace.h>
@@ -65,6 +66,8 @@ __bzero_begin:
 	.globl	__memset_start, __memset_end
 __memset_start:
 memset:
+	mov	%o0, %g1
+	mov	1, %g4
 	and	%o1, 0xff, %g3
 	sll	%g3, 8, %g2
 	or	%g3, %g2, %g3
@@ -89,6 +92,7 @@ memset:
 	 sub	%o0, %o2, %o0
 
 __bzero:
+	clr	%g4
 	mov	%g0, %g3
 1:
 	cmp	%o1, 7
@@ -151,8 +155,8 @@ __bzero:
 	bne,a	8f
 	 EX(stb	%g3, [%o0], and %o1, 1)
 8:
-	retl
-	 clr	%o0
+	b	0f
+	 nop
 7:
 	be	13b
 	 orcc	%o1, 0, %g0
@@ -164,6 +168,12 @@ __bzero:
 	bne	8b
 	 EX(stb	%g3, [%o0 - 1], add %o1, 1)
 0:
+	andcc	%g4, 1, %g0
+	be	5f
+	 nop
+	retl
+	 mov	%g1, %o0
+5:
 	retl
 	 clr	%o0
 __memset_end:
-- 
cgit v1.2.2


From 384859d2af8ead22c9e5a570a4ab89f1b563c8e5 Mon Sep 17 00:00:00 2001
From: Andreas Larsson <andreas@gaisler.com>
Date: Fri, 29 Aug 2014 17:09:18 +0200
Subject: sparc: leon: Fix race condition between leon_cycles_offset and
 timer_interrupt

This makes sure that leon_cycles_offset takes the pending bit into
account and that leon_clear_clock_irq clears the pending bit. Otherwise,
if leon_cycles_offset is executed after the timer has wrapped but before
timer_interrupt has increased timer_cs_internal_counter, time can be
perceived to go backwards.

Signed-off-by: Andreas Larsson <andreas@gaisler.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/kernel/leon_kernel.c | 31 ++++++++++++++++++++++++++++---
 1 file changed, 28 insertions(+), 3 deletions(-)

diff --git a/arch/sparc/kernel/leon_kernel.c b/arch/sparc/kernel/leon_kernel.c
index 683c4af999de..9bbb8f2bbfcc 100644
--- a/arch/sparc/kernel/leon_kernel.c
+++ b/arch/sparc/kernel/leon_kernel.c
@@ -37,6 +37,7 @@ unsigned long amba_system_id;
 static DEFINE_SPINLOCK(leon_irq_lock);
 
 static unsigned long leon3_gptimer_idx; /* Timer Index (0..6) within Timer Core */
+static unsigned long leon3_gptimer_ackmask; /* For clearing pending bit */
 unsigned long leon3_gptimer_irq; /* interrupt controller irq number */
 unsigned int sparc_leon_eirq;
 #define LEON_IMASK(cpu) (&leon3_irqctrl_regs->mask[cpu])
@@ -260,11 +261,19 @@ void leon_update_virq_handling(unsigned int virq,
 
 static u32 leon_cycles_offset(void)
 {
-	u32 rld, val, off;
+	u32 rld, val, ctrl, off;
+
 	rld = LEON3_BYPASS_LOAD_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].rld);
 	val = LEON3_BYPASS_LOAD_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].val);
-	off = rld - val;
-	return rld - val;
+	ctrl = LEON3_BYPASS_LOAD_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].ctrl);
+	if (LEON3_GPTIMER_CTRL_ISPENDING(ctrl)) {
+		val = LEON3_BYPASS_LOAD_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].val);
+		off = 2 * rld - val;
+	} else {
+		off = rld - val;
+	}
+
+	return off;
 }
 
 #ifdef CONFIG_SMP
@@ -302,6 +311,7 @@ void __init leon_init_timers(void)
 	int ampopts;
 	int err;
 	u32 config;
+	u32 ctrl;
 
 	sparc_config.get_cycles_offset = leon_cycles_offset;
 	sparc_config.cs_period = 1000000 / HZ;
@@ -374,6 +384,16 @@ void __init leon_init_timers(void)
 	if (!(leon3_gptimer_regs && leon3_irqctrl_regs && leon3_gptimer_irq))
 		goto bad;
 
+	ctrl = LEON3_BYPASS_LOAD_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].ctrl);
+	LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].ctrl,
+			      ctrl | LEON3_GPTIMER_CTRL_PENDING);
+	ctrl = LEON3_BYPASS_LOAD_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].ctrl);
+
+	if ((ctrl & LEON3_GPTIMER_CTRL_PENDING) != 0)
+		leon3_gptimer_ackmask = ~LEON3_GPTIMER_CTRL_PENDING;
+	else
+		leon3_gptimer_ackmask = ~0;
+
 	LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].val, 0);
 	LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].rld,
 				(((1000000 / HZ) - 1)));
@@ -452,6 +472,11 @@ bad:
 
 static void leon_clear_clock_irq(void)
 {
+	u32 ctrl;
+
+	ctrl = LEON3_BYPASS_LOAD_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].ctrl);
+	LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].ctrl,
+			      ctrl & leon3_gptimer_ackmask);
 }
 
 static void leon_load_profile_irq(int cpu, unsigned int limit)
-- 
cgit v1.2.2


From b84ca92e1672432aac43cccaaa572881e7cc9fdd Mon Sep 17 00:00:00 2001
From: Andreas Larsson <andreas@gaisler.com>
Date: Mon, 8 Sep 2014 09:48:52 +0200
Subject: sparc32, leon: Make leon_dma_ops avaiable when !CONFIG_PCI

The leon_dma_ops struct is needed for leon regardless of PCI configuration.

Signed-off-by: Andreas Larsson <andreas@gaisler.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/include/asm/dma-mapping.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/sparc/include/asm/dma-mapping.h b/arch/sparc/include/asm/dma-mapping.h
index 1ee02710b2dc..5b1b52a04ad6 100644
--- a/arch/sparc/include/asm/dma-mapping.h
+++ b/arch/sparc/include/asm/dma-mapping.h
@@ -20,10 +20,12 @@ extern struct bus_type pci_bus_type;
 
 static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-#if defined(CONFIG_SPARC32) && defined(CONFIG_PCI)
+#ifdef CONFIG_SPARC_LEON
 	if (sparc_cpu_model == sparc_leon)
 		return leon_dma_ops;
-	else if (dev->bus == &pci_bus_type)
+#endif
+#if defined(CONFIG_SPARC32) && defined(CONFIG_PCI)
+	if (dev->bus == &pci_bus_type)
 		return &pci32_dma_ops;
 #endif
 	return dma_ops;
-- 
cgit v1.2.2


From d1105287aabe88dbb3af825140badaa05cf0442c Mon Sep 17 00:00:00 2001
From: Daniel Hellstrom <daniel@gaisler.com>
Date: Wed, 10 Sep 2014 14:17:52 +0200
Subject: sparc32: dma_alloc_coherent must honour gfp flags

dma_zalloc_coherent() calls dma_alloc_coherent(__GFP_ZERO)
but the sparc32 implementations sbus_alloc_coherent() and
pci32_alloc_coherent() doesn't take the gfp flags into
account.

Tested on the SPARC32/LEON GRETH Ethernet driver which fails
due to dma_alloc_coherent(__GFP_ZERO) returns non zeroed
pages.

Signed-off-by: Daniel Hellstrom <daniel@gaisler.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/kernel/ioport.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index 7f08ec8a7c68..28fed53b13a0 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -278,7 +278,8 @@ static void *sbus_alloc_coherent(struct device *dev, size_t len,
 	}
 
 	order = get_order(len_total);
-	if ((va = __get_free_pages(GFP_KERNEL|__GFP_COMP, order)) == 0)
+	va = __get_free_pages(gfp, order);
+	if (va == 0)
 		goto err_nopages;
 
 	if ((res = kzalloc(sizeof(struct resource), GFP_KERNEL)) == NULL)
@@ -443,7 +444,7 @@ static void *pci32_alloc_coherent(struct device *dev, size_t len,
 	}
 
 	order = get_order(len_total);
-	va = (void *) __get_free_pages(GFP_KERNEL, order);
+	va = (void *) __get_free_pages(gfp, order);
 	if (va == NULL) {
 		printk("pci_alloc_consistent: no %ld pages\n", len_total>>PAGE_SHIFT);
 		goto err_nopages;
-- 
cgit v1.2.2


From 4ccb9272892c33ef1c19a783cfa87103b30c2784 Mon Sep 17 00:00:00 2001
From: bob picco <bpicco@meloft.net>
Date: Tue, 16 Sep 2014 09:26:47 -0400
Subject: sparc64: sun4v TLB error power off events

We've witnessed a few TLB events causing the machine to power off because
of prom_halt. In one case it was some nfs related area during rmmod. Another
was an mmapper of /dev/mem. A more recent one is an ITLB issue with
a bad pagesize which could be a hardware bug. Bugs happen but we should
attempt to not power off the machine and/or hang it when possible.

This is a DTLB error from an mmapper of /dev/mem:
[root@sparcie ~]# SUN4V-DTLB: Error at TPC[fffff80100903e6c], tl 1
SUN4V-DTLB: TPC<0xfffff80100903e6c>
SUN4V-DTLB: O7[fffff801081979d0]
SUN4V-DTLB: O7<0xfffff801081979d0>
SUN4V-DTLB: vaddr[fffff80100000000] ctx[1250] pte[98000000000f0610] error[2]
.

This is recent mainline for ITLB:
[ 3708.179864] SUN4V-ITLB: TPC<0xfffffc010071cefc>
[ 3708.188866] SUN4V-ITLB: O7[fffffc010071cee8]
[ 3708.197377] SUN4V-ITLB: O7<0xfffffc010071cee8>
[ 3708.206539] SUN4V-ITLB: vaddr[e0003] ctx[1a3c] pte[2900000dcc800eeb] error[4]
.

Normally sun4v_itlb_error_report() and sun4v_dtlb_error_report() would call
prom_halt() and drop us to OF command prompt "ok". This isn't the case for
LDOMs and the machine powers off.

For the HV reported error of HV_ENORADDR for HV HV_MMU_MAP_ADDR_TRAP we cause
a SIGBUS error by qualifying it within do_sparc64_fault() for fault code mask
of FAULT_CODE_BAD_RA. This is done when trap level (%tl) is less or equal
one("1"). Otherwise, for %tl > 1,  we proceed eventually to die_if_kernel().

The logic of this patch was partially inspired by David Miller's feedback.

Power off of large sparc64 machines is painful. Plus die_if_kernel provides
more context. A reset sequence isn't a brief period on large sparc64 but
better than power-off/power-on sequence.

Cc: sparclinux@vger.kernel.org
Signed-off-by: Bob Picco <bob.picco@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/include/asm/thread_info_64.h |  1 +
 arch/sparc/kernel/sun4v_tlb_miss.S      | 35 ++++++++++++++++++++-------------
 arch/sparc/kernel/traps_64.c            | 15 ++++++++------
 arch/sparc/mm/fault_64.c                |  3 +++
 4 files changed, 34 insertions(+), 20 deletions(-)

diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index a5f01ac6d0f1..f85dc8512ab3 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -102,6 +102,7 @@ struct thread_info {
 #define FAULT_CODE_ITLB		0x04	/* Miss happened in I-TLB	   */
 #define FAULT_CODE_WINFIXUP	0x08	/* Miss happened during spill/fill */
 #define FAULT_CODE_BLKCOMMIT	0x10	/* Use blk-commit ASI in copy_page */
+#define	FAULT_CODE_BAD_RA	0x20	/* Bad RA for sun4v		   */
 
 #if PAGE_SHIFT == 13
 #define THREAD_SIZE (2*PAGE_SIZE)
diff --git a/arch/sparc/kernel/sun4v_tlb_miss.S b/arch/sparc/kernel/sun4v_tlb_miss.S
index e0c09bf85610..6179e19bc9b9 100644
--- a/arch/sparc/kernel/sun4v_tlb_miss.S
+++ b/arch/sparc/kernel/sun4v_tlb_miss.S
@@ -195,6 +195,11 @@ sun4v_tsb_miss_common:
 	 ldx	[%g2 + TRAP_PER_CPU_PGD_PADDR], %g7
 
 sun4v_itlb_error:
+	rdpr	%tl, %g1
+	cmp	%g1, 1
+	ble,pt	%icc, sun4v_bad_ra
+	 or	%g0, FAULT_CODE_BAD_RA | FAULT_CODE_ITLB, %g1
+
 	sethi	%hi(sun4v_err_itlb_vaddr), %g1
 	stx	%g4, [%g1 + %lo(sun4v_err_itlb_vaddr)]
 	sethi	%hi(sun4v_err_itlb_ctx), %g1
@@ -206,15 +211,10 @@ sun4v_itlb_error:
 	sethi	%hi(sun4v_err_itlb_error), %g1
 	stx	%o0, [%g1 + %lo(sun4v_err_itlb_error)]
 
+	sethi	%hi(1f), %g7
 	rdpr	%tl, %g4
-	cmp	%g4, 1
-	ble,pt	%icc, 1f
-	 sethi	%hi(2f), %g7
 	ba,pt	%xcc, etraptl1
-	 or	%g7, %lo(2f), %g7
-
-1:	ba,pt	%xcc, etrap
-2:	 or	%g7, %lo(2b), %g7
+1:	 or	%g7, %lo(1f), %g7
 	mov	%l4, %o1
 	call	sun4v_itlb_error_report
 	 add	%sp, PTREGS_OFF, %o0
@@ -222,6 +222,11 @@ sun4v_itlb_error:
 	/* NOTREACHED */
 
 sun4v_dtlb_error:
+	rdpr	%tl, %g1
+	cmp	%g1, 1
+	ble,pt	%icc, sun4v_bad_ra
+	 or	%g0, FAULT_CODE_BAD_RA | FAULT_CODE_DTLB, %g1
+
 	sethi	%hi(sun4v_err_dtlb_vaddr), %g1
 	stx	%g4, [%g1 + %lo(sun4v_err_dtlb_vaddr)]
 	sethi	%hi(sun4v_err_dtlb_ctx), %g1
@@ -233,21 +238,23 @@ sun4v_dtlb_error:
 	sethi	%hi(sun4v_err_dtlb_error), %g1
 	stx	%o0, [%g1 + %lo(sun4v_err_dtlb_error)]
 
+	sethi	%hi(1f), %g7
 	rdpr	%tl, %g4
-	cmp	%g4, 1
-	ble,pt	%icc, 1f
-	 sethi	%hi(2f), %g7
 	ba,pt	%xcc, etraptl1
-	 or	%g7, %lo(2f), %g7
-
-1:	ba,pt	%xcc, etrap
-2:	 or	%g7, %lo(2b), %g7
+1:	 or	%g7, %lo(1f), %g7
 	mov	%l4, %o1
 	call	sun4v_dtlb_error_report
 	 add	%sp, PTREGS_OFF, %o0
 
 	/* NOTREACHED */
 
+sun4v_bad_ra:
+	or	%g0, %g4, %g5
+	ba,pt	%xcc, sparc64_realfault_common
+	 or	%g1, %g0, %g4
+
+	/* NOTREACHED */
+
 	/* Instruction Access Exception, tl0. */
 sun4v_iacc:
 	ldxa	[%g0] ASI_SCRATCHPAD, %g2
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index fb6640ec8557..981a769b9558 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2104,6 +2104,11 @@ void sun4v_nonresum_overflow(struct pt_regs *regs)
 	atomic_inc(&sun4v_nonresum_oflow_cnt);
 }
 
+static void sun4v_tlb_error(struct pt_regs *regs)
+{
+	die_if_kernel("TLB/TSB error", regs);
+}
+
 unsigned long sun4v_err_itlb_vaddr;
 unsigned long sun4v_err_itlb_ctx;
 unsigned long sun4v_err_itlb_pte;
@@ -2111,8 +2116,7 @@ unsigned long sun4v_err_itlb_error;
 
 void sun4v_itlb_error_report(struct pt_regs *regs, int tl)
 {
-	if (tl > 1)
-		dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
+	dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
 
 	printk(KERN_EMERG "SUN4V-ITLB: Error at TPC[%lx], tl %d\n",
 	       regs->tpc, tl);
@@ -2125,7 +2129,7 @@ void sun4v_itlb_error_report(struct pt_regs *regs, int tl)
 	       sun4v_err_itlb_vaddr, sun4v_err_itlb_ctx,
 	       sun4v_err_itlb_pte, sun4v_err_itlb_error);
 
-	prom_halt();
+	sun4v_tlb_error(regs);
 }
 
 unsigned long sun4v_err_dtlb_vaddr;
@@ -2135,8 +2139,7 @@ unsigned long sun4v_err_dtlb_error;
 
 void sun4v_dtlb_error_report(struct pt_regs *regs, int tl)
 {
-	if (tl > 1)
-		dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
+	dump_tl1_traplog((struct tl1_traplog *)(regs + 1));
 
 	printk(KERN_EMERG "SUN4V-DTLB: Error at TPC[%lx], tl %d\n",
 	       regs->tpc, tl);
@@ -2149,7 +2152,7 @@ void sun4v_dtlb_error_report(struct pt_regs *regs, int tl)
 	       sun4v_err_dtlb_vaddr, sun4v_err_dtlb_ctx,
 	       sun4v_err_dtlb_pte, sun4v_err_dtlb_error);
 
-	prom_halt();
+	sun4v_tlb_error(regs);
 }
 
 void hypervisor_tlbop_error(unsigned long err, unsigned long op)
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 587cd0565128..18fcd7167095 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -346,6 +346,9 @@ retry:
 		down_read(&mm->mmap_sem);
 	}
 
+	if (fault_code & FAULT_CODE_BAD_RA)
+		goto do_sigbus;
+
 	vma = find_vma(mm, address);
 	if (!vma)
 		goto bad_area;
-- 
cgit v1.2.2


From 3dee9df54836d5f844f3d58281d3f3e6331b467f Mon Sep 17 00:00:00 2001
From: bob picco <bpicco@meloft.net>
Date: Tue, 16 Sep 2014 09:28:15 -0400
Subject: sparc64: find_node adjustment

We have seen an issue with guest boot into LDOM that causes early boot failures
because of no matching rules for node identitity of the memory. I analyzed this
on my T4 and concluded there might not be a solution. I saw the issue in
mainline too when booting into the control/primary domain - with guests
configured.  Note, this could be a firmware bug on some older machines.

I'll provide a full explanation of the issues below. Should we not find a
matching BEST latency group for a real address (RA) then we will assume node 0.
On the T4-2 here with the information provided I can't see an alternative.

Technically the LDOM shown below should match the MBLOCK to the
favorable latency group. However other factors must be considered too. Were
the memory controllers configured "fine" grained interleave or "coarse"
grain interleaved -  T4. Also should a "group" MD node be considered a NUMA
node?

There has to be at least one Machine Description (MD) "group" and hence one
NUMA node. The group can have one or more latency groups (lg) - more than one
memory controller. The current code chooses the smallest latency as the most
favorable per group. The latency and lg information is in MLGROUP below.
MBLOCK is the base and size of the RAs for the machine as fetched from OBP
/memory "available" property. My machine has one MBLOCK but more would be
possible - with holes?

For a T4-2 the following information has been gathered:
with LDOM guest
MEMBLOCK configuration:
 memory size = 0x27f870000
 memory.cnt  = 0x3
 memory[0x0]    [0x00000020400000-0x0000029fc67fff], 0x27f868000 bytes
 memory[0x1]    [0x0000029fd8a000-0x0000029fd8bfff], 0x2000 bytes
 memory[0x2]    [0x0000029fd92000-0x0000029fd97fff], 0x6000 bytes
 reserved.cnt  = 0x2
 reserved[0x0]  [0x00000020800000-0x000000216c15c0], 0xec15c1 bytes
 reserved[0x1]  [0x00000024800000-0x0000002c180c1e], 0x7980c1f bytes
MBLOCK[0]: base[20000000] size[280000000] offset[0]
(note: "base" and "size" reported in "MBLOCK" encompass the "memory[X]" values)
(note: (RA + offset) & mask = val is the formula to detect a match for the
memory controller. should there be no match for find_node node, a return
value of -1 resulted for the node - BAD)

There is one group. It has these forward links
MLGROUP[1]: node[545] latency[1f7e8] match[200000000] mask[200000000]
MLGROUP[2]: node[54d] latency[2de60] match[0] mask[200000000]
NUMA NODE[0]: node[545] mask[200000000] val[200000000] (latency[1f7e8])
(note: "val" is the best lg's (smallest latency) "match")

no LDOM guest - bare metal
MEMBLOCK configuration:
 memory size = 0xfdf2d0000
 memory.cnt  = 0x3
 memory[0x0]    [0x00000020400000-0x00000fff6adfff], 0xfdf2ae000 bytes
 memory[0x1]    [0x00000fff6d2000-0x00000fff6e7fff], 0x16000 bytes
 memory[0x2]    [0x00000fff766000-0x00000fff771fff], 0xc000 bytes
 reserved.cnt  = 0x2
 reserved[0x0]  [0x00000020800000-0x00000021a04580], 0x1204581 bytes
 reserved[0x1]  [0x00000024800000-0x0000002c7d29fc], 0x7fd29fd bytes
MBLOCK[0]: base[20000000] size[fe0000000] offset[0]

there are two groups
group node[16d5]
MLGROUP[0]: node[1765] latency[1f7e8] match[0] mask[200000000]
MLGROUP[3]: node[177d] latency[2de60] match[200000000] mask[200000000]
NUMA NODE[0]: node[1765] mask[200000000] val[0] (latency[1f7e8])
group node[171d]
MLGROUP[2]: node[1775] latency[2de60] match[0] mask[200000000]
MLGROUP[1]: node[176d] latency[1f7e8] match[200000000] mask[200000000]
NUMA NODE[1]: node[176d] mask[200000000] val[200000000] (latency[1f7e8])
(note: for this two "group" bare metal machine, 1/2 memory is in group one's
lg and 1/2 memory is in group two's lg).

Cc: sparclinux@vger.kernel.org
Signed-off-by: Bob Picco <bob.picco@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/mm/init_64.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 98ac8e80adae..3b045058d726 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -840,7 +840,10 @@ static int find_node(unsigned long addr)
 		if ((addr & p->mask) == p->val)
 			return i;
 	}
-	return -1;
+	/* The following condition has been observed on LDOM guests.*/
+	WARN_ONCE(1, "find_node: A physical address doesn't match a NUMA node"
+		" rule. Some physical memory will be owned by node 0.");
+	return 0;
 }
 
 static u64 memblock_nid_range(u64 start, u64 end, int *nid)
-- 
cgit v1.2.2


From 7c21d533ab2ffa1e681bdaf4a53ce3046f6e0e17 Mon Sep 17 00:00:00 2001
From: bob picco <bpicco@meloft.net>
Date: Tue, 16 Sep 2014 09:29:54 -0400
Subject: sparc64: mem boot option correction

The "mem" boot option can result in many unexpected consequences. This patch
attempts to prevent boot hangs which have been experienced on T4-4 and T5-8.
Basically the boot loader allocates vmlinuz and initrd higher in available
OBP physical memory. For example, on a 2Tb T5-8 it isn't possible to boot
with mem=20G.

The patch utilizes memblock to avoid reserved regions and trim memory which
is only free. Other improvements are possible for a multi-node machine.

This is a snippet of the boot log with mem=20G on T5-8 with the patch applied:
MEMBLOCK configuration:	<- before memory reduction
 memory size = 0x1ffad6ce000 reserved size = 0xa1adf44
 memory.cnt  = 0xb
 memory[0x0]    [0x00000030400000-0x00003fdde47fff], 0x3fada48000 bytes
 memory[0x1]    [0x00003fdde4e000-0x00003fdde4ffff], 0x2000 bytes
 memory[0x2]    [0x00080000000000-0x00083fffffffff], 0x4000000000 bytes
 memory[0x3]    [0x00100000000000-0x00103fffffffff], 0x4000000000 bytes
 memory[0x4]    [0x00180000000000-0x00183fffffffff], 0x4000000000 bytes
 memory[0x5]    [0x00200000000000-0x00203fffffffff], 0x4000000000 bytes
 memory[0x6]    [0x00280000000000-0x00283fffffffff], 0x4000000000 bytes
 memory[0x7]    [0x00300000000000-0x00303fffffffff], 0x4000000000 bytes
 memory[0x8]    [0x00380000000000-0x00383fffc71fff], 0x3fffc72000 bytes
 memory[0x9]    [0x00383fffc92000-0x00383fffca1fff], 0x10000 bytes
 memory[0xa]    [0x00383fffcb4000-0x00383fffcb5fff], 0x2000 bytes
 reserved.cnt  = 0x2
 reserved[0x0]  [0x00380000000000-0x0038000117e7f8], 0x117e7f9 bytes
 reserved[0x1]  [0x00380004000000-0x0038000d02f74a], 0x902f74b bytes
...
MEMBLOCK configuration:	<- after reduction of memory
 memory size = 0x50a1adf44 reserved size = 0xa1adf44
 memory.cnt  = 0x4
 memory[0x0]    [0x00380000000000-0x0038000117e7f8], 0x117e7f9 bytes
 memory[0x1]    [0x00380004000000-0x0038050d01d74a], 0x50901d74b bytes
 memory[0x2]    [0x00383fffc92000-0x00383fffca1fff], 0x10000 bytes
 memory[0x3]    [0x00383fffcb4000-0x00383fffcb5fff], 0x2000 bytes
 reserved.cnt  = 0x2
 reserved[0x0]  [0x00380000000000-0x0038000117e7f8], 0x117e7f9 bytes
 reserved[0x1]  [0x00380004000000-0x0038000d02f74a], 0x902f74b bytes
...
Early memory node ranges
  node   7: [mem 0x380000000000-0x38000117dfff]
  node   7: [mem 0x380004000000-0x380f0d01bfff]
  node   7: [mem 0x383fffc92000-0x383fffca1fff]
  node   7: [mem 0x383fffcb4000-0x383fffcb5fff]
Could not find start_pfn for node 0
Could not find start_pfn for node 1
Could not find start_pfn for node 2
Could not find start_pfn for node 3
Could not find start_pfn for node 4
Could not find start_pfn for node 5
Could not find start_pfn for node 6
.

The patch was tested on T4-1, T5-8 and Jalap?no.

Cc: sparclinux@vger.kernel.org
Signed-off-by: Bob Picco <bob.picco@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/kernel/setup_64.c | 18 +++-------------
 arch/sparc/mm/init_64.c      | 49 +++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 51 insertions(+), 16 deletions(-)

diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index 1c7bfdf83b66..e629b8377587 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -141,21 +141,9 @@ static void __init boot_flags_init(char *commands)
 				process_switch(*commands++);
 			continue;
 		}
-		if (!strncmp(commands, "mem=", 4)) {
-			/*
-			 * "mem=XXX[kKmM]" overrides the PROM-reported
-			 * memory size.
-			 */
-			cmdline_memory_size = simple_strtoul(commands + 4,
-							     &commands, 0);
-			if (*commands == 'K' || *commands == 'k') {
-				cmdline_memory_size <<= 10;
-				commands++;
-			} else if (*commands=='M' || *commands=='m') {
-				cmdline_memory_size <<= 20;
-				commands++;
-			}
-		}
+		if (!strncmp(commands, "mem=", 4))
+			cmdline_memory_size = memparse(commands + 4, &commands);
+
 		while (*commands && *commands != ' ')
 			commands++;
 	}
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 3b045058d726..c8bccafea4f3 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -1861,6 +1861,52 @@ pgd_t swapper_pg_dir[PTRS_PER_PGD];
 static void sun4u_pgprot_init(void);
 static void sun4v_pgprot_init(void);
 
+static phys_addr_t __init available_memory(void)
+{
+	phys_addr_t available = 0ULL;
+	phys_addr_t pa_start, pa_end;
+	u64 i;
+
+	for_each_free_mem_range(i, NUMA_NO_NODE, &pa_start, &pa_end, NULL)
+		available = available + (pa_end  - pa_start);
+
+	return available;
+}
+
+/* We need to exclude reserved regions. This exclusion will include
+ * vmlinux and initrd. To be more precise the initrd size could be used to
+ * compute a new lower limit because it is freed later during initialization.
+ */
+static void __init reduce_memory(phys_addr_t limit_ram)
+{
+	phys_addr_t avail_ram = available_memory();
+	phys_addr_t pa_start, pa_end;
+	u64 i;
+
+	if (limit_ram >= avail_ram)
+		return;
+
+	for_each_free_mem_range(i, NUMA_NO_NODE, &pa_start, &pa_end, NULL) {
+		phys_addr_t region_size = pa_end - pa_start;
+		phys_addr_t clip_start = pa_start;
+
+		avail_ram = avail_ram - region_size;
+		/* Are we consuming too much? */
+		if (avail_ram < limit_ram) {
+			phys_addr_t give_back = limit_ram - avail_ram;
+
+			region_size = region_size - give_back;
+			clip_start = clip_start + give_back;
+		}
+
+		memblock_remove(clip_start, region_size);
+
+		if (avail_ram <= limit_ram)
+			break;
+		i = 0UL;
+	}
+}
+
 void __init paging_init(void)
 {
 	unsigned long end_pfn, shift, phys_base;
@@ -1940,7 +1986,8 @@ void __init paging_init(void)
 
 	find_ramdisk(phys_base);
 
-	memblock_enforce_memory_limit(cmdline_memory_size);
+	if (cmdline_memory_size)
+		reduce_memory(cmdline_memory_size);
 
 	memblock_allow_resize();
 	memblock_dump_all();
-- 
cgit v1.2.2


From 05aa1651e8b9ca078b1808a2fe7b50703353ec02 Mon Sep 17 00:00:00 2001
From: bob picco <bpicco@meloft.net>
Date: Tue, 16 Sep 2014 10:09:06 -0400
Subject: sparc64: T5 PMU

The T5 (niagara5) has different PCR related HV fast trap values and a new
HV API Group. This patch utilizes these and shares when possible with niagara4.

We use the same sparc_pmu niagara4_pmu. Should there be new effort to
obtain the MCU perf statistics then this would have to be changed.

Cc: sparclinux@vger.kernel.org
Signed-off-by: Bob Picco <bob.picco@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/include/asm/hypervisor.h | 11 +++++++++
 arch/sparc/kernel/hvapi.c           |  1 +
 arch/sparc/kernel/hvcalls.S         | 16 +++++++++++++
 arch/sparc/kernel/pcr.c             | 47 +++++++++++++++++++++++++++++++++----
 arch/sparc/kernel/perf_event.c      |  3 ++-
 5 files changed, 73 insertions(+), 5 deletions(-)

diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h
index 94b39caea3eb..4f6725ff4c33 100644
--- a/arch/sparc/include/asm/hypervisor.h
+++ b/arch/sparc/include/asm/hypervisor.h
@@ -2947,6 +2947,16 @@ unsigned long sun4v_vt_set_perfreg(unsigned long reg_num,
 				   unsigned long reg_val);
 #endif
 
+#define	HV_FAST_T5_GET_PERFREG		0x1a8
+#define	HV_FAST_T5_SET_PERFREG		0x1a9
+
+#ifndef	__ASSEMBLY__
+unsigned long sun4v_t5_get_perfreg(unsigned long reg_num,
+				   unsigned long *reg_val);
+unsigned long sun4v_t5_set_perfreg(unsigned long reg_num,
+				   unsigned long reg_val);
+#endif
+
 /* Function numbers for HV_CORE_TRAP.  */
 #define HV_CORE_SET_VER			0x00
 #define HV_CORE_PUTCHAR			0x01
@@ -2978,6 +2988,7 @@ unsigned long sun4v_vt_set_perfreg(unsigned long reg_num,
 #define HV_GRP_VF_CPU			0x0205
 #define HV_GRP_KT_CPU			0x0209
 #define HV_GRP_VT_CPU			0x020c
+#define HV_GRP_T5_CPU			0x0211
 #define HV_GRP_DIAG			0x0300
 
 #ifndef __ASSEMBLY__
diff --git a/arch/sparc/kernel/hvapi.c b/arch/sparc/kernel/hvapi.c
index c0a2de0fd624..5c55145bfbf0 100644
--- a/arch/sparc/kernel/hvapi.c
+++ b/arch/sparc/kernel/hvapi.c
@@ -46,6 +46,7 @@ static struct api_info api_table[] = {
 	{ .group = HV_GRP_VF_CPU,				},
 	{ .group = HV_GRP_KT_CPU,				},
 	{ .group = HV_GRP_VT_CPU,				},
+	{ .group = HV_GRP_T5_CPU,				},
 	{ .group = HV_GRP_DIAG,		.flags = FLAG_PRE_API	},
 };
 
diff --git a/arch/sparc/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S
index f3ab509b76a8..caedf8320416 100644
--- a/arch/sparc/kernel/hvcalls.S
+++ b/arch/sparc/kernel/hvcalls.S
@@ -821,3 +821,19 @@ ENTRY(sun4v_vt_set_perfreg)
 	retl
 	 nop
 ENDPROC(sun4v_vt_set_perfreg)
+
+ENTRY(sun4v_t5_get_perfreg)
+	mov	%o1, %o4
+	mov	HV_FAST_T5_GET_PERFREG, %o5
+	ta	HV_FAST_TRAP
+	stx	%o1, [%o4]
+	retl
+	 nop
+ENDPROC(sun4v_t5_get_perfreg)
+
+ENTRY(sun4v_t5_set_perfreg)
+	mov	HV_FAST_T5_SET_PERFREG, %o5
+	ta	HV_FAST_TRAP
+	retl
+	 nop
+ENDPROC(sun4v_t5_set_perfreg)
diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c
index 269af58497aa..7e967c8018c8 100644
--- a/arch/sparc/kernel/pcr.c
+++ b/arch/sparc/kernel/pcr.c
@@ -191,12 +191,41 @@ static const struct pcr_ops n4_pcr_ops = {
 	.pcr_nmi_disable	= PCR_N4_PICNPT,
 };
 
+static u64 n5_pcr_read(unsigned long reg_num)
+{
+	unsigned long val;
+
+	(void) sun4v_t5_get_perfreg(reg_num, &val);
+
+	return val;
+}
+
+static void n5_pcr_write(unsigned long reg_num, u64 val)
+{
+	(void) sun4v_t5_set_perfreg(reg_num, val);
+}
+
+static const struct pcr_ops n5_pcr_ops = {
+	.read_pcr		= n5_pcr_read,
+	.write_pcr		= n5_pcr_write,
+	.read_pic		= n4_pic_read,
+	.write_pic		= n4_pic_write,
+	.nmi_picl_value		= n4_picl_value,
+	.pcr_nmi_enable		= (PCR_N4_PICNPT | PCR_N4_STRACE |
+				   PCR_N4_UTRACE | PCR_N4_TOE |
+				   (26 << PCR_N4_SL_SHIFT)),
+	.pcr_nmi_disable	= PCR_N4_PICNPT,
+};
+
+
 static unsigned long perf_hsvc_group;
 static unsigned long perf_hsvc_major;
 static unsigned long perf_hsvc_minor;
 
 static int __init register_perf_hsvc(void)
 {
+	unsigned long hverror;
+
 	if (tlb_type == hypervisor) {
 		switch (sun4v_chip_type) {
 		case SUN4V_CHIP_NIAGARA1:
@@ -215,6 +244,10 @@ static int __init register_perf_hsvc(void)
 			perf_hsvc_group = HV_GRP_VT_CPU;
 			break;
 
+		case SUN4V_CHIP_NIAGARA5:
+			perf_hsvc_group = HV_GRP_T5_CPU;
+			break;
+
 		default:
 			return -ENODEV;
 		}
@@ -222,10 +255,12 @@ static int __init register_perf_hsvc(void)
 
 		perf_hsvc_major = 1;
 		perf_hsvc_minor = 0;
-		if (sun4v_hvapi_register(perf_hsvc_group,
-					 perf_hsvc_major,
-					 &perf_hsvc_minor)) {
-			printk("perfmon: Could not register hvapi.\n");
+		hverror = sun4v_hvapi_register(perf_hsvc_group,
+					       perf_hsvc_major,
+					       &perf_hsvc_minor);
+		if (hverror) {
+			pr_err("perfmon: Could not register hvapi(0x%lx).\n",
+			       hverror);
 			return -ENODEV;
 		}
 	}
@@ -254,6 +289,10 @@ static int __init setup_sun4v_pcr_ops(void)
 		pcr_ops = &n4_pcr_ops;
 		break;
 
+	case SUN4V_CHIP_NIAGARA5:
+		pcr_ops = &n5_pcr_ops;
+		break;
+
 	default:
 		ret = -ENODEV;
 		break;
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index d35c490a91cb..c9759ad3f34a 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1662,7 +1662,8 @@ static bool __init supported_pmu(void)
 		sparc_pmu = &niagara2_pmu;
 		return true;
 	}
-	if (!strcmp(sparc_pmu_type, "niagara4")) {
+	if (!strcmp(sparc_pmu_type, "niagara4") ||
+	    !strcmp(sparc_pmu_type, "niagara5")) {
 		sparc_pmu = &niagara4_pmu;
 		return true;
 	}
-- 
cgit v1.2.2


From c21c4ab0d6921f7160a43216fa6973b5924de561 Mon Sep 17 00:00:00 2001
From: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Date: Tue, 16 Sep 2014 11:37:08 -0400
Subject: sparc64: Move request_irq() from ldc_bind() to ldc_alloc()

The request_irq() needs to be done from ldc_alloc()
to avoid the following (caught by lockdep)

 [00000000004a0738] __might_sleep+0xf8/0x120
 [000000000058bea4] kmem_cache_alloc_trace+0x184/0x2c0
 [00000000004faf80] request_threaded_irq+0x80/0x160
 [000000000044f71c] ldc_bind+0x7c/0x220
 [0000000000452454] vio_port_up+0x54/0xe0
 [00000000101f6778] probe_disk+0x38/0x220 [sunvdc]
 [00000000101f6b8c] vdc_port_probe+0x22c/0x300 [sunvdc]
 [0000000000451a88] vio_device_probe+0x48/0x60
 [000000000074c56c] really_probe+0x6c/0x300
 [000000000074c83c] driver_probe_device+0x3c/0xa0
 [000000000074c92c] __driver_attach+0x8c/0xa0
 [000000000074a6ec] bus_for_each_dev+0x6c/0xa0
 [000000000074c1dc] driver_attach+0x1c/0x40
 [000000000074b0fc] bus_add_driver+0xbc/0x280

Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Acked-by: Dwight Engen <dwight.engen@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/include/asm/ldc.h |  5 +++--
 arch/sparc/kernel/ds.c       |  4 ++--
 arch/sparc/kernel/ldc.c      | 41 +++++++++++++++++++++--------------------
 arch/sparc/kernel/viohs.c    |  4 ++--
 4 files changed, 28 insertions(+), 26 deletions(-)

diff --git a/arch/sparc/include/asm/ldc.h b/arch/sparc/include/asm/ldc.h
index c8c67f621f4f..58ab64de25d2 100644
--- a/arch/sparc/include/asm/ldc.h
+++ b/arch/sparc/include/asm/ldc.h
@@ -53,13 +53,14 @@ struct ldc_channel;
 /* Allocate state for a channel.  */
 struct ldc_channel *ldc_alloc(unsigned long id,
 			      const struct ldc_channel_config *cfgp,
-			      void *event_arg);
+			      void *event_arg,
+			      const char *name);
 
 /* Shut down and free state for a channel.  */
 void ldc_free(struct ldc_channel *lp);
 
 /* Register TX and RX queues of the link with the hypervisor.  */
-int ldc_bind(struct ldc_channel *lp, const char *name);
+int ldc_bind(struct ldc_channel *lp);
 
 /* For non-RAW protocols we need to complete a handshake before
  * communication can proceed.  ldc_connect() does that, if the
diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c
index dff60abbea01..f87a55d77094 100644
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@@ -1200,14 +1200,14 @@ static int ds_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	ds_cfg.tx_irq = vdev->tx_irq;
 	ds_cfg.rx_irq = vdev->rx_irq;
 
-	lp = ldc_alloc(vdev->channel_id, &ds_cfg, dp);
+	lp = ldc_alloc(vdev->channel_id, &ds_cfg, dp, "DS");
 	if (IS_ERR(lp)) {
 		err = PTR_ERR(lp);
 		goto out_free_ds_states;
 	}
 	dp->lp = lp;
 
-	err = ldc_bind(lp, "DS");
+	err = ldc_bind(lp);
 	if (err)
 		goto out_free_ldc;
 
diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c
index 66dacd56bb10..27bb55485472 100644
--- a/arch/sparc/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
@@ -1078,7 +1078,8 @@ static void ldc_iommu_release(struct ldc_channel *lp)
 
 struct ldc_channel *ldc_alloc(unsigned long id,
 			      const struct ldc_channel_config *cfgp,
-			      void *event_arg)
+			      void *event_arg,
+			      const char *name)
 {
 	struct ldc_channel *lp;
 	const struct ldc_mode_ops *mops;
@@ -1093,6 +1094,8 @@ struct ldc_channel *ldc_alloc(unsigned long id,
 	err = -EINVAL;
 	if (!cfgp)
 		goto out_err;
+	if (!name)
+		goto out_err;
 
 	switch (cfgp->mode) {
 	case LDC_MODE_RAW:
@@ -1185,6 +1188,21 @@ struct ldc_channel *ldc_alloc(unsigned long id,
 
 	INIT_HLIST_HEAD(&lp->mh_list);
 
+	snprintf(lp->rx_irq_name, LDC_IRQ_NAME_MAX, "%s RX", name);
+	snprintf(lp->tx_irq_name, LDC_IRQ_NAME_MAX, "%s TX", name);
+
+	err = request_irq(lp->cfg.rx_irq, ldc_rx, 0,
+			  lp->rx_irq_name, lp);
+	if (err)
+		goto out_free_txq;
+
+	err = request_irq(lp->cfg.tx_irq, ldc_tx, 0,
+			  lp->tx_irq_name, lp);
+	if (err) {
+		free_irq(lp->cfg.rx_irq, lp);
+		goto out_free_txq;
+	}
+
 	return lp;
 
 out_free_txq:
@@ -1237,31 +1255,14 @@ EXPORT_SYMBOL(ldc_free);
  * state.  This does not initiate a handshake, ldc_connect() does
  * that.
  */
-int ldc_bind(struct ldc_channel *lp, const char *name)
+int ldc_bind(struct ldc_channel *lp)
 {
 	unsigned long hv_err, flags;
 	int err = -EINVAL;
 
-	if (!name ||
-	    (lp->state != LDC_STATE_INIT))
+	if (lp->state != LDC_STATE_INIT)
 		return -EINVAL;
 
-	snprintf(lp->rx_irq_name, LDC_IRQ_NAME_MAX, "%s RX", name);
-	snprintf(lp->tx_irq_name, LDC_IRQ_NAME_MAX, "%s TX", name);
-
-	err = request_irq(lp->cfg.rx_irq, ldc_rx, 0,
-			  lp->rx_irq_name, lp);
-	if (err)
-		return err;
-
-	err = request_irq(lp->cfg.tx_irq, ldc_tx, 0,
-			  lp->tx_irq_name, lp);
-	if (err) {
-		free_irq(lp->cfg.rx_irq, lp);
-		return err;
-	}
-
-
 	spin_lock_irqsave(&lp->lock, flags);
 
 	enable_irq(lp->cfg.rx_irq);
diff --git a/arch/sparc/kernel/viohs.c b/arch/sparc/kernel/viohs.c
index f8e7dd53e1c7..9c5fbd0b8a04 100644
--- a/arch/sparc/kernel/viohs.c
+++ b/arch/sparc/kernel/viohs.c
@@ -714,7 +714,7 @@ int vio_ldc_alloc(struct vio_driver_state *vio,
 	cfg.tx_irq = vio->vdev->tx_irq;
 	cfg.rx_irq = vio->vdev->rx_irq;
 
-	lp = ldc_alloc(vio->vdev->channel_id, &cfg, event_arg);
+	lp = ldc_alloc(vio->vdev->channel_id, &cfg, event_arg, vio->name);
 	if (IS_ERR(lp))
 		return PTR_ERR(lp);
 
@@ -746,7 +746,7 @@ void vio_port_up(struct vio_driver_state *vio)
 
 	err = 0;
 	if (state == LDC_STATE_INIT) {
-		err = ldc_bind(vio->lp, vio->name);
+		err = ldc_bind(vio->lp);
 		if (err)
 			printk(KERN_WARNING "%s: Port %lu bind failed, "
 			       "err=%d\n",
-- 
cgit v1.2.2


From 9d0713edf72461438bc3526e4ea55fec47754cd9 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 24 Sep 2014 21:05:30 -0700
Subject: sparc64: Fix hibernation code refrence to PAGE_OFFSET.

We changed PAGE_OFFSET to be a variable rather than a constant,
but this reference here in the hibernate assembler got missed.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/power/hibernate_asm.S | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/sparc/power/hibernate_asm.S b/arch/sparc/power/hibernate_asm.S
index 79942166df84..d7d9017dcb15 100644
--- a/arch/sparc/power/hibernate_asm.S
+++ b/arch/sparc/power/hibernate_asm.S
@@ -54,8 +54,8 @@ ENTRY(swsusp_arch_resume)
 	 nop
 
 	/* Write PAGE_OFFSET to %g7 */
-	sethi	%uhi(PAGE_OFFSET), %g7
-	sllx	%g7, 32, %g7
+	sethi	%hi(PAGE_OFFSET), %g7
+	ldx	[%g7 + %lo(PAGE_OFFSET)], %g7
 
 	setuw	(PAGE_SIZE-8), %g3
 
-- 
cgit v1.2.2


From 163a4e7473061388bba0899a1a063bae44e1715a Mon Sep 17 00:00:00 2001
From: David L Stevens <david.stevens@oracle.com>
Date: Mon, 29 Sep 2014 19:47:59 -0400
Subject: sparc: VIO protocol version 1.6

Add VIO protocol version 1.6 interfaces.

Signed-off-by: David L Stevens <david.stevens@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/include/asm/vio.h | 44 ++++++++++++++++++++++++++++++++++++++++++--
 arch/sparc/kernel/viohs.c    | 14 ++++++++++++--
 2 files changed, 54 insertions(+), 4 deletions(-)

diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h
index e0f6c399f1d0..6b135a8ab07b 100644
--- a/arch/sparc/include/asm/vio.h
+++ b/arch/sparc/include/asm/vio.h
@@ -65,6 +65,7 @@ struct vio_dring_register {
 	u16			options;
 #define VIO_TX_DRING		0x0001
 #define VIO_RX_DRING		0x0002
+#define VIO_RX_DRING_DATA	0x0004
 	u16			resv;
 	u32			num_cookies;
 	struct ldc_trans_cookie	cookies[0];
@@ -80,6 +81,8 @@ struct vio_dring_unregister {
 #define VIO_PKT_MODE		0x01 /* Packet based transfer	*/
 #define VIO_DESC_MODE		0x02 /* In-band descriptors	*/
 #define VIO_DRING_MODE		0x03 /* Descriptor rings	*/
+/* in vers >= 1.2, VIO_DRING_MODE is 0x04 and transfer mode is a bitmask */
+#define VIO_NEW_DRING_MODE	0x04
 
 struct vio_dring_data {
 	struct vio_msg_tag	tag;
@@ -205,10 +208,20 @@ struct vio_net_attr_info {
 	u8			addr_type;
 #define VNET_ADDR_ETHERMAC	0x01
 	u16			ack_freq;
-	u32			resv1;
+	u8			plnk_updt;
+#define PHYSLINK_UPDATE_NONE		0x00
+#define PHYSLINK_UPDATE_STATE		0x01
+#define PHYSLINK_UPDATE_STATE_ACK	0x02
+#define PHYSLINK_UPDATE_STATE_NACK	0x03
+	u8			options;
+	u16			resv1;
 	u64			addr;
 	u64			mtu;
-	u64			resv2[3];
+	u16			cflags;
+#define VNET_LSO_IPV4_CAPAB		0x0001
+	u16			ipv4_lso_maxlen;
+	u32			resv2;
+	u64			resv3[2];
 };
 
 #define VNET_NUM_MCAST		7
@@ -366,6 +379,33 @@ struct vio_driver_state {
 	struct vio_driver_ops	*ops;
 };
 
+static inline bool vio_version_before(struct vio_driver_state *vio,
+				      u16 major, u16 minor)
+{
+	u32 have = (u32)vio->ver.major << 16 | vio->ver.minor;
+	u32 want = (u32)major << 16 | minor;
+
+	return have < want;
+}
+
+static inline bool vio_version_after(struct vio_driver_state *vio,
+				      u16 major, u16 minor)
+{
+	u32 have = (u32)vio->ver.major << 16 | vio->ver.minor;
+	u32 want = (u32)major << 16 | minor;
+
+	return have > want;
+}
+
+static inline bool vio_version_after_eq(struct vio_driver_state *vio,
+					u16 major, u16 minor)
+{
+	u32 have = (u32)vio->ver.major << 16 | vio->ver.minor;
+	u32 want = (u32)major << 16 | minor;
+
+	return have >= want;
+}
+
 #define viodbg(TYPE, f, a...) \
 do {	if (vio->debug & VIO_DEBUG_##TYPE) \
 		printk(KERN_INFO "vio: ID[%lu] " f, \
diff --git a/arch/sparc/kernel/viohs.c b/arch/sparc/kernel/viohs.c
index 9c5fbd0b8a04..526fcb5d8ce9 100644
--- a/arch/sparc/kernel/viohs.c
+++ b/arch/sparc/kernel/viohs.c
@@ -426,6 +426,13 @@ static int process_dreg_info(struct vio_driver_state *vio,
 	if (vio->dr_state & VIO_DR_STATE_RXREG)
 		goto send_nack;
 
+	/* v1.6 and higher, ACK with desired, supported mode, or NACK */
+	if (vio_version_after_eq(vio, 1, 6)) {
+		if (!(pkt->options & VIO_TX_DRING))
+			goto send_nack;
+		pkt->options = VIO_TX_DRING;
+	}
+
 	BUG_ON(vio->desc_buf);
 
 	vio->desc_buf = kzalloc(pkt->descr_size, GFP_ATOMIC);
@@ -453,8 +460,11 @@ static int process_dreg_info(struct vio_driver_state *vio,
 	pkt->tag.stype = VIO_SUBTYPE_ACK;
 	pkt->dring_ident = ++dr->ident;
 
-	viodbg(HS, "SEND DRING_REG ACK ident[%llx]\n",
-	       (unsigned long long) pkt->dring_ident);
+	viodbg(HS, "SEND DRING_REG ACK ident[%llx] "
+	       "ndesc[%u] dsz[%u] opt[0x%x] ncookies[%u]\n",
+	       (unsigned long long) pkt->dring_ident,
+	       pkt->num_descr, pkt->descr_size, pkt->options,
+	       pkt->num_cookies);
 
 	len = (sizeof(*pkt) +
 	       (dr->ncookies * sizeof(struct ldc_trans_cookie)));
-- 
cgit v1.2.2


From 9bce21828d54a95143f1b74619705c2dd8e88b92 Mon Sep 17 00:00:00 2001
From: Allen Pais <allen.pais@oracle.com>
Date: Fri, 19 Sep 2014 09:42:14 -0400
Subject: sunvdc: add cdrom and v1.1 protocol support

Interpret the media type from v1.1 protocol to support CDROM/DVD.

For v1.0 protocol, a disk's size continues to be calculated from the
geometry returned by the vdisk server. The geometry returned by the server
can be less than the actual number of sectors available in the backing
image/device due to the rounding in the division used to compute the
geometry in the vdisk server.

In v1.1 protocol a disk's actual size in sectors is returned during the
handshake. Use this size when v1.1 protocol is negotiated. Since this size
will always be larger than the former geometry computed size, disks created
under v1.0 will be forwards compatible to v1.1, but not vice versa.

Signed-off-by: Dwight Engen <dwight.engen@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/include/asm/vio.h |  12 +++--
 drivers/block/sunvdc.c       | 109 ++++++++++++++++++++++++++++++++++++-------
 2 files changed, 101 insertions(+), 20 deletions(-)

diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h
index 6b135a8ab07b..94a02dbbac41 100644
--- a/arch/sparc/include/asm/vio.h
+++ b/arch/sparc/include/asm/vio.h
@@ -121,12 +121,18 @@ struct vio_disk_attr_info {
 	u8			vdisk_type;
 #define VD_DISK_TYPE_SLICE	0x01 /* Slice in block device	*/
 #define VD_DISK_TYPE_DISK	0x02 /* Entire block device	*/
-	u16			resv1;
+	u8			vdisk_mtype;		/* v1.1 */
+#define VD_MEDIA_TYPE_FIXED	0x01 /* Fixed device */
+#define VD_MEDIA_TYPE_CD	0x02 /* CD Device    */
+#define VD_MEDIA_TYPE_DVD	0x03 /* DVD Device   */
+	u8			resv1;
 	u32			vdisk_block_size;
 	u64			operations;
-	u64			vdisk_size;
+	u64			vdisk_size;		/* v1.1 */
 	u64			max_xfer_size;
-	u64			resv2[2];
+	u32			phys_block_size;	/* v1.2 */
+	u32			resv2;
+	u64			resv3[1];
 };
 
 struct vio_disk_desc {
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 5814deb6963d..66ddf704ad7f 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -9,6 +9,7 @@
 #include <linux/blkdev.h>
 #include <linux/hdreg.h>
 #include <linux/genhd.h>
+#include <linux/cdrom.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
@@ -22,8 +23,8 @@
 
 #define DRV_MODULE_NAME		"sunvdc"
 #define PFX DRV_MODULE_NAME	": "
-#define DRV_MODULE_VERSION	"1.0"
-#define DRV_MODULE_RELDATE	"June 25, 2007"
+#define DRV_MODULE_VERSION	"1.1"
+#define DRV_MODULE_RELDATE	"February 13, 2013"
 
 static char version[] =
 	DRV_MODULE_NAME ".c:v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n";
@@ -65,6 +66,7 @@ struct vdc_port {
 	u64			operations;
 	u32			vdisk_size;
 	u8			vdisk_type;
+	u8			vdisk_mtype;
 
 	char			disk_name[32];
 
@@ -79,9 +81,16 @@ static inline struct vdc_port *to_vdc_port(struct vio_driver_state *vio)
 
 /* Ordered from largest major to lowest */
 static struct vio_version vdc_versions[] = {
+	{ .major = 1, .minor = 1 },
 	{ .major = 1, .minor = 0 },
 };
 
+static inline int vdc_version_supported(struct vdc_port *port,
+					u16 major, u16 minor)
+{
+	return port->vio.ver.major == major && port->vio.ver.minor >= minor;
+}
+
 #define VDCBLK_NAME	"vdisk"
 static int vdc_major;
 #define PARTITION_SHIFT	3
@@ -103,9 +112,41 @@ static int vdc_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return 0;
 }
 
+/* Add ioctl/CDROM_GET_CAPABILITY to support cdrom_id in udev
+ * when vdisk_mtype is VD_MEDIA_TYPE_CD or VD_MEDIA_TYPE_DVD.
+ * Needed to be able to install inside an ldom from an iso image.
+ */
+static int vdc_ioctl(struct block_device *bdev, fmode_t mode,
+		     unsigned command, unsigned long argument)
+{
+	int i;
+	struct gendisk *disk;
+
+	switch (command) {
+	case CDROMMULTISESSION:
+		pr_debug(PFX "Multisession CDs not supported\n");
+		for (i = 0; i < sizeof(struct cdrom_multisession); i++)
+			if (put_user(0, (char __user *)(argument + i)))
+				return -EFAULT;
+		return 0;
+
+	case CDROM_GET_CAPABILITY:
+		disk = bdev->bd_disk;
+
+		if (bdev->bd_disk && (disk->flags & GENHD_FL_CD))
+			return 0;
+		return -EINVAL;
+
+	default:
+		pr_debug(PFX "ioctl %08x not supported\n", command);
+		return -EINVAL;
+	}
+}
+
 static const struct block_device_operations vdc_fops = {
 	.owner		= THIS_MODULE,
 	.getgeo		= vdc_getgeo,
+	.ioctl		= vdc_ioctl,
 };
 
 static void vdc_finish(struct vio_driver_state *vio, int err, int waiting_for)
@@ -165,9 +206,9 @@ static int vdc_handle_attr(struct vio_driver_state *vio, void *arg)
 	struct vio_disk_attr_info *pkt = arg;
 
 	viodbg(HS, "GOT ATTR stype[0x%x] ops[%llx] disk_size[%llu] disk_type[%x] "
-	       "xfer_mode[0x%x] blksz[%u] max_xfer[%llu]\n",
+	       "mtype[0x%x] xfer_mode[0x%x] blksz[%u] max_xfer[%llu]\n",
 	       pkt->tag.stype, pkt->operations,
-	       pkt->vdisk_size, pkt->vdisk_type,
+	       pkt->vdisk_size, pkt->vdisk_type, pkt->vdisk_mtype,
 	       pkt->xfer_mode, pkt->vdisk_block_size,
 	       pkt->max_xfer_size);
 
@@ -192,8 +233,11 @@ static int vdc_handle_attr(struct vio_driver_state *vio, void *arg)
 		}
 
 		port->operations = pkt->operations;
-		port->vdisk_size = pkt->vdisk_size;
 		port->vdisk_type = pkt->vdisk_type;
+		if (vdc_version_supported(port, 1, 1)) {
+			port->vdisk_size = pkt->vdisk_size;
+			port->vdisk_mtype = pkt->vdisk_mtype;
+		}
 		if (pkt->max_xfer_size < port->max_xfer_size)
 			port->max_xfer_size = pkt->max_xfer_size;
 		port->vdisk_block_size = pkt->vdisk_block_size;
@@ -663,18 +707,25 @@ static int probe_disk(struct vdc_port *port)
 		return err;
 	}
 
-	err = generic_request(port, VD_OP_GET_DISKGEOM,
-			      &port->geom, sizeof(port->geom));
-	if (err < 0) {
-		printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns "
-		       "error %d\n", err);
-		return err;
+	if (vdc_version_supported(port, 1, 1)) {
+		/* vdisk_size should be set during the handshake, if it wasn't
+		 * then the underlying disk is reserved by another system
+		 */
+		if (port->vdisk_size == -1)
+			return -ENODEV;
+	} else {
+		err = generic_request(port, VD_OP_GET_DISKGEOM,
+				      &port->geom, sizeof(port->geom));
+		if (err < 0) {
+			printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns "
+			       "error %d\n", err);
+			return err;
+		}
+		port->vdisk_size = ((u64)port->geom.num_cyl *
+				    (u64)port->geom.num_hd *
+				    (u64)port->geom.num_sec);
 	}
 
-	port->vdisk_size = ((u64)port->geom.num_cyl *
-			    (u64)port->geom.num_hd *
-			    (u64)port->geom.num_sec);
-
 	q = blk_init_queue(do_vdc_request, &port->vio.lock);
 	if (!q) {
 		printk(KERN_ERR PFX "%s: Could not allocate queue.\n",
@@ -704,9 +755,32 @@ static int probe_disk(struct vdc_port *port)
 
 	set_capacity(g, port->vdisk_size);
 
-	printk(KERN_INFO PFX "%s: %u sectors (%u MB)\n",
+	if (vdc_version_supported(port, 1, 1)) {
+		switch (port->vdisk_mtype) {
+		case VD_MEDIA_TYPE_CD:
+			pr_info(PFX "Virtual CDROM %s\n", port->disk_name);
+			g->flags |= GENHD_FL_CD;
+			g->flags |= GENHD_FL_REMOVABLE;
+			set_disk_ro(g, 1);
+			break;
+
+		case VD_MEDIA_TYPE_DVD:
+			pr_info(PFX "Virtual DVD %s\n", port->disk_name);
+			g->flags |= GENHD_FL_CD;
+			g->flags |= GENHD_FL_REMOVABLE;
+			set_disk_ro(g, 1);
+			break;
+
+		case VD_MEDIA_TYPE_FIXED:
+			pr_info(PFX "Virtual Hard disk %s\n", port->disk_name);
+			break;
+		}
+	}
+
+	pr_info(PFX "%s: %u sectors (%u MB) protocol %d.%d\n",
 	       g->disk_name,
-	       port->vdisk_size, (port->vdisk_size >> (20 - 9)));
+	       port->vdisk_size, (port->vdisk_size >> (20 - 9)),
+	       port->vio.ver.major, port->vio.ver.minor);
 
 	add_disk(g);
 
@@ -765,6 +839,7 @@ static int vdc_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	else
 		snprintf(port->disk_name, sizeof(port->disk_name),
 			 VDCBLK_NAME "%c", 'a' + ((int)vdev->dev_no % 26));
+	port->vdisk_size = -1;
 
 	err = vio_driver_init(&port->vio, vdev, VDEV_DISK,
 			      vdc_versions, ARRAY_SIZE(vdc_versions),
-- 
cgit v1.2.2


From de5b73f08468b4fc5e2f6d1505f650262622f78b Mon Sep 17 00:00:00 2001
From: Allen Pais <allen.pais@oracle.com>
Date: Fri, 19 Sep 2014 09:42:26 -0400
Subject: sunvdc: compute vdisk geometry from capacity

The LDom diskserver doesn't return reliable geometry data. In addition,
the types for all fields in the vio_disk_geom are u16, which were being
truncated in the cast into the u8's of the Linux struct hd_geometry.

Modify vdc_getgeo() to compute the geometry from the disk's capacity in a
manner consistent with xen-blkfront::blkif_getgeo().

Signed-off-by: Dwight Engen <dwight.engen@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/block/sunvdc.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 66ddf704ad7f..1616ad091a5e 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -70,7 +70,6 @@ struct vdc_port {
 
 	char			disk_name[32];
 
-	struct vio_disk_geom	geom;
 	struct vio_disk_vtoc	label;
 };
 
@@ -103,11 +102,15 @@ static inline u32 vdc_tx_dring_avail(struct vio_dring_state *dr)
 static int vdc_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 {
 	struct gendisk *disk = bdev->bd_disk;
-	struct vdc_port *port = disk->private_data;
+	sector_t nsect = get_capacity(disk);
+	sector_t cylinders = nsect;
 
-	geo->heads = (u8) port->geom.num_hd;
-	geo->sectors = (u8) port->geom.num_sec;
-	geo->cylinders = port->geom.num_cyl;
+	geo->heads = 0xff;
+	geo->sectors = 0x3f;
+	sector_div(cylinders, geo->heads * geo->sectors);
+	geo->cylinders = cylinders;
+	if ((sector_t)(geo->cylinders + 1) * geo->heads * geo->sectors < nsect)
+		geo->cylinders = 0xffff;
 
 	return 0;
 }
@@ -714,16 +717,18 @@ static int probe_disk(struct vdc_port *port)
 		if (port->vdisk_size == -1)
 			return -ENODEV;
 	} else {
+		struct vio_disk_geom geom;
+
 		err = generic_request(port, VD_OP_GET_DISKGEOM,
-				      &port->geom, sizeof(port->geom));
+				      &geom, sizeof(geom));
 		if (err < 0) {
 			printk(KERN_ERR PFX "VD_OP_GET_DISKGEOM returns "
 			       "error %d\n", err);
 			return err;
 		}
-		port->vdisk_size = ((u64)port->geom.num_cyl *
-				    (u64)port->geom.num_hd *
-				    (u64)port->geom.num_sec);
+		port->vdisk_size = ((u64)geom.num_cyl *
+				    (u64)geom.num_hd *
+				    (u64)geom.num_sec);
 	}
 
 	q = blk_init_queue(do_vdc_request, &port->vio.lock);
-- 
cgit v1.2.2


From 5eed69ffd248c9f68f56c710caf07db134aef28b Mon Sep 17 00:00:00 2001
From: Dwight Engen <dwight.engen@oracle.com>
Date: Fri, 19 Sep 2014 09:42:53 -0400
Subject: sunvdc: limit each sg segment to a page

ldc_map_sg() could fail its check that the number of pages referred to
by the sg scatterlist was <= the number of cookies.

This fixes the issue by doing a similar thing to the xen-blkfront driver,
ensuring that the scatterlist will only ever contain a segment count <=
port->ring_cookies, and each segment will be page aligned, and <= page
size. This ensures that the scatterlist is always mappable.

Orabug: 19347817
OraBZ: 15945

Signed-off-by: Dwight Engen <dwight.engen@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/block/sunvdc.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 1616ad091a5e..1a9360da1f54 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -747,6 +747,10 @@ static int probe_disk(struct vdc_port *port)
 
 	port->disk = g;
 
+	/* Each segment in a request is up to an aligned page in size. */
+	blk_queue_segment_boundary(q, PAGE_SIZE - 1);
+	blk_queue_max_segment_size(q, PAGE_SIZE);
+
 	blk_queue_max_segments(q, port->ring_cookies);
 	blk_queue_max_hw_sectors(q, port->max_xfer_size);
 	g->major = vdc_major;
-- 
cgit v1.2.2


From d0aedcd4f14a22e23b313f42b7e6e6ebfc0fbc31 Mon Sep 17 00:00:00 2001
From: Dwight Engen <dwight.engen@oracle.com>
Date: Fri, 19 Sep 2014 09:43:02 -0400
Subject: vio: fix reuse of vio_dring slot

vio_dring_avail() will allow use of every dring entry, but when the last
entry is allocated then dr->prod == dr->cons which is indistinguishable from
the ring empty condition. This causes the next allocation to reuse an entry.
When this happens in sunvdc, the server side vds driver begins nack'ing the
messages and ends up resetting the ldc channel. This problem does not effect
sunvnet since it checks for < 2.

The fix here is to just never allocate the very last dring slot so that full
and empty are not the same condition. The request start path was changed to
check for the ring being full a bit earlier, and to stop the blk_queue if
there is no space left. The blk_queue will be restarted once the ring is
only half full again. The number of ring entries was increased to 512 which
matches the sunvnet and Solaris vdc drivers, and greatly reduces the
frequency of hitting the ring full condition and the associated blk_queue
stop/starting. The checks in sunvent were adjusted to account for
vio_dring_avail() returning 1 less.

Orabug: 19441666
OraBZ: 14983

Signed-off-by: Dwight Engen <dwight.engen@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/include/asm/vio.h       |  2 +-
 drivers/block/sunvdc.c             | 39 ++++++++++++++++++++++----------------
 drivers/net/ethernet/sun/sunvnet.c |  4 ++--
 3 files changed, 26 insertions(+), 19 deletions(-)

diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h
index 94a02dbbac41..7fce9b1e6228 100644
--- a/arch/sparc/include/asm/vio.h
+++ b/arch/sparc/include/asm/vio.h
@@ -278,7 +278,7 @@ static inline u32 vio_dring_avail(struct vio_dring_state *dr,
 				  unsigned int ring_size)
 {
 	return (dr->pending -
-		((dr->prod - dr->cons) & (ring_size - 1)));
+		((dr->prod - dr->cons) & (ring_size - 1)) - 1);
 }
 
 #define VIO_MAX_TYPE_LEN	32
diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c
index 1a9360da1f54..756b8ec00f16 100644
--- a/drivers/block/sunvdc.c
+++ b/drivers/block/sunvdc.c
@@ -33,7 +33,7 @@ MODULE_DESCRIPTION("Sun LDOM virtual disk client driver");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(DRV_MODULE_VERSION);
 
-#define VDC_TX_RING_SIZE	256
+#define VDC_TX_RING_SIZE	512
 
 #define WAITING_FOR_LINK_UP	0x01
 #define WAITING_FOR_TX_SPACE	0x02
@@ -283,7 +283,9 @@ static void vdc_end_one(struct vdc_port *port, struct vio_dring_state *dr,
 
 	__blk_end_request(req, (desc->status ? -EIO : 0), desc->size);
 
-	if (blk_queue_stopped(port->disk->queue))
+	/* restart blk queue when ring is half emptied */
+	if (blk_queue_stopped(port->disk->queue) &&
+	    vdc_tx_dring_avail(dr) * 100 / VDC_TX_RING_SIZE >= 50)
 		blk_start_queue(port->disk->queue);
 }
 
@@ -435,12 +437,6 @@ static int __send_request(struct request *req)
 	for (i = 0; i < nsg; i++)
 		len += sg[i].length;
 
-	if (unlikely(vdc_tx_dring_avail(dr) < 1)) {
-		blk_stop_queue(port->disk->queue);
-		err = -ENOMEM;
-		goto out;
-	}
-
 	desc = vio_dring_cur(dr);
 
 	err = ldc_map_sg(port->vio.lp, sg, nsg,
@@ -480,21 +476,32 @@ static int __send_request(struct request *req)
 		port->req_id++;
 		dr->prod = (dr->prod + 1) & (VDC_TX_RING_SIZE - 1);
 	}
-out:
 
 	return err;
 }
 
-static void do_vdc_request(struct request_queue *q)
+static void do_vdc_request(struct request_queue *rq)
 {
-	while (1) {
-		struct request *req = blk_fetch_request(q);
+	struct request *req;
 
-		if (!req)
-			break;
+	while ((req = blk_peek_request(rq)) != NULL) {
+		struct vdc_port *port;
+		struct vio_dring_state *dr;
 
-		if (__send_request(req) < 0)
-			__blk_end_request_all(req, -EIO);
+		port = req->rq_disk->private_data;
+		dr = &port->vio.drings[VIO_DRIVER_TX_RING];
+		if (unlikely(vdc_tx_dring_avail(dr) < 1))
+			goto wait;
+
+		blk_start_request(req);
+
+		if (__send_request(req) < 0) {
+			blk_requeue_request(rq, req);
+wait:
+			/* Avoid pointless unplugs. */
+			blk_stop_queue(rq);
+			break;
+		}
 	}
 }
 
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index 23c89ab5a6ad..b7cca71fbc90 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -690,7 +690,7 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	spin_lock_irqsave(&port->vio.lock, flags);
 
 	dr = &port->vio.drings[VIO_DRIVER_TX_RING];
-	if (unlikely(vnet_tx_dring_avail(dr) < 2)) {
+	if (unlikely(vnet_tx_dring_avail(dr) < 1)) {
 		if (!netif_queue_stopped(dev)) {
 			netif_stop_queue(dev);
 
@@ -746,7 +746,7 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	dev->stats.tx_bytes += skb->len;
 
 	dr->prod = (dr->prod + 1) & (VNET_TX_RING_SIZE - 1);
-	if (unlikely(vnet_tx_dring_avail(dr) < 2)) {
+	if (unlikely(vnet_tx_dring_avail(dr) < 1)) {
 		netif_stop_queue(dev);
 		if (vnet_tx_dring_avail(dr) > VNET_TX_WAKEUP_THRESH(dr))
 			netif_wake_queue(dev);
-- 
cgit v1.2.2


From ca605b7dd740c8909408d67911d8ddd272c2b320 Mon Sep 17 00:00:00 2001
From: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Date: Tue, 23 Sep 2014 11:37:44 -0400
Subject: sparc64: Add vio_set_intr() to enable/disable Rx interrupts

The vio_set_intr() API should be used by VIO consumers to enable/disable
Rx interrupts to facilitate deferred processing in softirq/bottom-half
context.

Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/sparc/include/asm/vio.h |  2 ++
 arch/sparc/kernel/vio.c      | 13 ++++++++++++-
 2 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/arch/sparc/include/asm/vio.h b/arch/sparc/include/asm/vio.h
index 7fce9b1e6228..d758c8d8f47d 100644
--- a/arch/sparc/include/asm/vio.h
+++ b/arch/sparc/include/asm/vio.h
@@ -298,6 +298,7 @@ struct vio_dev {
 
 	unsigned int		tx_irq;
 	unsigned int		rx_irq;
+	u64			rx_ino;
 
 	struct device		dev;
 };
@@ -453,5 +454,6 @@ int vio_driver_init(struct vio_driver_state *vio, struct vio_dev *vdev,
 		    char *nam