summaryrefslogtreecommitdiff
path: root/arch/powerpc
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc')
-rw-r--r--arch/powerpc/Kconfig21
l---------arch/powerpc/boot/dts/include/dt-bindings1
-rw-r--r--arch/powerpc/include/asm/book3s/64/hash-4k.h2
-rw-r--r--arch/powerpc/include/asm/bug.h2
-rw-r--r--arch/powerpc/include/asm/cputable.h3
-rw-r--r--arch/powerpc/include/asm/kprobes.h1
-rw-r--r--arch/powerpc/include/asm/module.h4
-rw-r--r--arch/powerpc/include/asm/page.h12
-rw-r--r--arch/powerpc/include/asm/processor.h31
-rw-r--r--arch/powerpc/include/asm/topology.h14
-rw-r--r--arch/powerpc/include/asm/uaccess.h8
-rw-r--r--arch/powerpc/include/asm/xive.h12
-rw-r--r--arch/powerpc/include/uapi/asm/cputable.h2
-rw-r--r--arch/powerpc/kernel/cputable.c3
-rw-r--r--arch/powerpc/kernel/dt_cpu_ftrs.c58
-rw-r--r--arch/powerpc/kernel/exceptions-64s.S11
-rw-r--r--arch/powerpc/kernel/idle_book3s.S2
-rw-r--r--arch/powerpc/kernel/kprobes.c20
-rw-r--r--arch/powerpc/kernel/process.c22
-rw-r--r--arch/powerpc/kernel/prom.c2
-rw-r--r--arch/powerpc/kernel/setup-common.c2
-rw-r--r--arch/powerpc/kernel/setup_64.c35
-rw-r--r--arch/powerpc/kernel/trace/ftrace_64_mprofile.S59
-rw-r--r--arch/powerpc/kvm/Kconfig2
-rw-r--r--arch/powerpc/kvm/Makefile4
-rw-r--r--arch/powerpc/kvm/book3s_64_vio_hv.c13
-rw-r--r--arch/powerpc/kvm/book3s_hv.c51
-rw-r--r--arch/powerpc/kvm/book3s_hv_builtin.c9
-rw-r--r--arch/powerpc/kvm/book3s_hv_interrupts.S12
-rw-r--r--arch/powerpc/kvm/book3s_hv_rmhandlers.S75
-rw-r--r--arch/powerpc/kvm/book3s_pr_papr.c70
-rw-r--r--arch/powerpc/kvm/book3s_xive_template.c4
-rw-r--r--arch/powerpc/kvm/powerpc.c4
-rw-r--r--arch/powerpc/mm/dump_linuxpagetables.c7
-rw-r--r--arch/powerpc/mm/hugetlbpage-radix.c2
-rw-r--r--arch/powerpc/mm/mmap.c4
-rw-r--r--arch/powerpc/mm/mmu_context_book3s64.c2
-rw-r--r--arch/powerpc/mm/slice.c2
-rw-r--r--arch/powerpc/perf/perf_regs.c3
-rw-r--r--arch/powerpc/perf/power9-pmu.c4
-rw-r--r--arch/powerpc/platforms/Kconfig11
-rw-r--r--arch/powerpc/platforms/cell/spu_base.c4
-rw-r--r--arch/powerpc/platforms/cell/spufs/coredump.c2
-rw-r--r--arch/powerpc/platforms/powernv/npu-dma.c102
-rw-r--r--arch/powerpc/platforms/powernv/subcore.c8
-rw-r--r--arch/powerpc/platforms/pseries/hotplug-memory.c2
-rw-r--r--arch/powerpc/sysdev/simple_gpio.c3
-rw-r--r--arch/powerpc/sysdev/xive/common.c2
48 files changed, 544 insertions, 185 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index f7c8f9972f61..bf4391d18923 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -380,22 +380,6 @@ source "arch/powerpc/platforms/Kconfig"
menu "Kernel options"
-config PPC_DT_CPU_FTRS
- bool "Device-tree based CPU feature discovery & setup"
- depends on PPC_BOOK3S_64
- default n
- help
- This enables code to use a new device tree binding for describing CPU
- compatibility and features. Saying Y here will attempt to use the new
- binding if the firmware provides it. Currently only the skiboot
- firmware provides this binding.
- If you're not sure say Y.
-
-config PPC_CPUFEATURES_ENABLE_UNKNOWN
- bool "cpufeatures pass through unknown features to guest/userspace"
- depends on PPC_DT_CPU_FTRS
- default y
-
config HIGHMEM
bool "High memory support"
depends on PPC32
@@ -1215,11 +1199,6 @@ source "arch/powerpc/Kconfig.debug"
source "security/Kconfig"
-config KEYS_COMPAT
- bool
- depends on COMPAT && KEYS
- default y
-
source "crypto/Kconfig"
config PPC_LIB_RHEAP
diff --git a/arch/powerpc/boot/dts/include/dt-bindings b/arch/powerpc/boot/dts/include/dt-bindings
deleted file mode 120000
index 08c00e4972fa..000000000000
--- a/arch/powerpc/boot/dts/include/dt-bindings
+++ /dev/null
@@ -1 +0,0 @@
-../../../../../include/dt-bindings \ No newline at end of file
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index b4b5e6b671ca..0c4e470571ca 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -8,7 +8,7 @@
#define H_PTE_INDEX_SIZE 9
#define H_PMD_INDEX_SIZE 7
#define H_PUD_INDEX_SIZE 9
-#define H_PGD_INDEX_SIZE 12
+#define H_PGD_INDEX_SIZE 9
#ifndef __ASSEMBLY__
#define H_PTE_TABLE_SIZE (sizeof(pte_t) << H_PTE_INDEX_SIZE)
diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h
index f2c562a0a427..0151af6c2a50 100644
--- a/arch/powerpc/include/asm/bug.h
+++ b/arch/powerpc/include/asm/bug.h
@@ -104,7 +104,7 @@
"1: "PPC_TLNEI" %4,0\n" \
_EMIT_BUG_ENTRY \
: : "i" (__FILE__), "i" (__LINE__), \
- "i" (BUGFLAG_TAINT(TAINT_WARN)), \
+ "i" (BUGFLAG_WARNING|BUGFLAG_TAINT(TAINT_WARN)),\
"i" (sizeof(struct bug_entry)), \
"r" (__ret_warn_on)); \
} \
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index c2d509584a98..d02ad93bf708 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -214,7 +214,6 @@ enum {
#define CPU_FTR_DAWR LONG_ASM_CONST(0x0400000000000000)
#define CPU_FTR_DABRX LONG_ASM_CONST(0x0800000000000000)
#define CPU_FTR_PMAO_BUG LONG_ASM_CONST(0x1000000000000000)
-#define CPU_FTR_SUBCORE LONG_ASM_CONST(0x2000000000000000)
#define CPU_FTR_POWER9_DD1 LONG_ASM_CONST(0x4000000000000000)
#ifndef __ASSEMBLY__
@@ -463,7 +462,7 @@ enum {
CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
- CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_SUBCORE)
+ CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP)
#define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG)
#define CPU_FTRS_POWER8_DD1 (CPU_FTRS_POWER8 & ~CPU_FTR_DBELL)
#define CPU_FTRS_POWER9 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h
index a83821f33ea3..8814a7249ceb 100644
--- a/arch/powerpc/include/asm/kprobes.h
+++ b/arch/powerpc/include/asm/kprobes.h
@@ -103,6 +103,7 @@ extern int kprobe_exceptions_notify(struct notifier_block *self,
extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
extern int kprobe_handler(struct pt_regs *regs);
extern int kprobe_post_handler(struct pt_regs *regs);
+extern int is_current_kprobe_addr(unsigned long addr);
#ifdef CONFIG_KPROBES_ON_FTRACE
extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
struct kprobe_ctlblk *kcb);
diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index 53885512b8d3..6c0132c7212f 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -14,6 +14,10 @@
#include <asm-generic/module.h>
+#ifdef CC_USING_MPROFILE_KERNEL
+#define MODULE_ARCH_VERMAGIC "mprofile-kernel"
+#endif
+
#ifndef __powerpc64__
/*
* Thanks to Paul M for explaining this.
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 2a32483c7b6c..8da5d4c1cab2 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -132,7 +132,19 @@ extern long long virt_phys_offset;
#define virt_to_pfn(kaddr) (__pa(kaddr) >> PAGE_SHIFT)
#define virt_to_page(kaddr) pfn_to_page(virt_to_pfn(kaddr))
#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT)
+
+#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * On hash the vmalloc and other regions alias to the kernel region when passed
+ * through __pa(), which virt_to_pfn() uses. That means virt_addr_valid() can
+ * return true for some vmalloc addresses, which is incorrect. So explicitly
+ * check that the address is in the kernel region.
+ */
+#define virt_addr_valid(kaddr) (REGION_ID(kaddr) == KERNEL_REGION_ID && \
+ pfn_valid(virt_to_pfn(kaddr)))
+#else
#define virt_addr_valid(kaddr) pfn_valid(virt_to_pfn(kaddr))
+#endif
/*
* On Book-E parts we need __va to parse the device tree and we can't
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index a2123f291ab0..1189d04f3bd1 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -110,13 +110,18 @@ void release_thread(struct task_struct *);
#define TASK_SIZE_128TB (0x0000800000000000UL)
#define TASK_SIZE_512TB (0x0002000000000000UL)
-#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * For now 512TB is only supported with book3s and 64K linux page size.
+ */
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_64K_PAGES)
/*
* Max value currently used:
*/
-#define TASK_SIZE_USER64 TASK_SIZE_512TB
+#define TASK_SIZE_USER64 TASK_SIZE_512TB
+#define DEFAULT_MAP_WINDOW_USER64 TASK_SIZE_128TB
#else
-#define TASK_SIZE_USER64 TASK_SIZE_64TB
+#define TASK_SIZE_USER64 TASK_SIZE_64TB
+#define DEFAULT_MAP_WINDOW_USER64 TASK_SIZE_64TB
#endif
/*
@@ -132,7 +137,7 @@ void release_thread(struct task_struct *);
* space during mmap's.
*/
#define TASK_UNMAPPED_BASE_USER32 (PAGE_ALIGN(TASK_SIZE_USER32 / 4))
-#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(TASK_SIZE_128TB / 4))
+#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(DEFAULT_MAP_WINDOW_USER64 / 4))
#define TASK_UNMAPPED_BASE ((is_32bit_task()) ? \
TASK_UNMAPPED_BASE_USER32 : TASK_UNMAPPED_BASE_USER64 )
@@ -143,21 +148,15 @@ void release_thread(struct task_struct *);
* with 128TB and conditionally enable upto 512TB
*/
#ifdef CONFIG_PPC_BOOK3S_64
-#define DEFAULT_MAP_WINDOW ((is_32bit_task()) ? \
- TASK_SIZE_USER32 : TASK_SIZE_128TB)
+#define DEFAULT_MAP_WINDOW ((is_32bit_task()) ? \
+ TASK_SIZE_USER32 : DEFAULT_MAP_WINDOW_USER64)
#else
#define DEFAULT_MAP_WINDOW TASK_SIZE
#endif
#ifdef __powerpc64__
-#ifdef CONFIG_PPC_BOOK3S_64
-/* Limit stack to 128TB */
-#define STACK_TOP_USER64 TASK_SIZE_128TB
-#else
-#define STACK_TOP_USER64 TASK_SIZE_USER64
-#endif
-
+#define STACK_TOP_USER64 DEFAULT_MAP_WINDOW_USER64
#define STACK_TOP_USER32 TASK_SIZE_USER32
#define STACK_TOP (is_32bit_task() ? \
@@ -379,12 +378,6 @@ struct thread_struct {
}
#endif
-/*
- * Return saved PC of a blocked thread. For now, this is the "user" PC
- */
-#define thread_saved_pc(tsk) \
- ((tsk)->thread.regs? (tsk)->thread.regs->nip: 0)
-
#define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.regs)
unsigned long get_wchan(struct task_struct *p);
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 8b3b46b7b0f2..329771559cbb 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -44,8 +44,22 @@ extern void __init dump_numa_cpu_topology(void);
extern int sysfs_add_device_to_node(struct device *dev, int nid);
extern void sysfs_remove_device_from_node(struct device *dev, int nid);
+static inline int early_cpu_to_node(int cpu)
+{
+ int nid;
+
+ nid = numa_cpu_lookup_table[cpu];
+
+ /*
+ * Fall back to node 0 if nid is unset (it should be, except bugs).
+ * This allows callers to safely do NODE_DATA(early_cpu_to_node(cpu)).
+ */
+ return (nid < 0) ? 0 : nid;
+}
#else
+static inline int early_cpu_to_node(int cpu) { return 0; }
+
static inline void dump_numa_cpu_topology(void) {}
static inline int sysfs_add_device_to_node(struct device *dev, int nid)
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 5c0d8a8cdae5..41e88d3ce36b 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -267,13 +267,7 @@ do { \
extern unsigned long __copy_tofrom_user(void __user *to,
const void __user *from, unsigned long size);
-#ifndef __powerpc64__
-
-#define INLINE_COPY_FROM_USER
-#define INLINE_COPY_TO_USER
-
-#else /* __powerpc64__ */
-
+#ifdef __powerpc64__
static inline unsigned long
raw_copy_in_user(void __user *to, const void __user *from, unsigned long n)
{
diff --git a/arch/powerpc/include/asm/xive.h b/arch/powerpc/include/asm/xive.h
index c8a822acf962..c23ff4389ca2 100644
--- a/arch/powerpc/include/asm/xive.h
+++ b/arch/powerpc/include/asm/xive.h
@@ -94,11 +94,13 @@ struct xive_q {
* store at 0 and some ESBs support doing a trigger via a
* separate trigger page.
*/
-#define XIVE_ESB_GET 0x800
-#define XIVE_ESB_SET_PQ_00 0xc00
-#define XIVE_ESB_SET_PQ_01 0xd00
-#define XIVE_ESB_SET_PQ_10 0xe00
-#define XIVE_ESB_SET_PQ_11 0xf00
+#define XIVE_ESB_STORE_EOI 0x400 /* Store */
+#define XIVE_ESB_LOAD_EOI 0x000 /* Load */
+#define XIVE_ESB_GET 0x800 /* Load */
+#define XIVE_ESB_SET_PQ_00 0xc00 /* Load */
+#define XIVE_ESB_SET_PQ_01 0xd00 /* Load */
+#define XIVE_ESB_SET_PQ_10 0xe00 /* Load */
+#define XIVE_ESB_SET_PQ_11 0xf00 /* Load */
#define XIVE_ESB_VAL_P 0x2
#define XIVE_ESB_VAL_Q 0x1
diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h
index 3e7ce86d5c13..4d877144f377 100644
--- a/arch/powerpc/include/uapi/asm/cputable.h
+++ b/arch/powerpc/include/uapi/asm/cputable.h
@@ -46,6 +46,8 @@
#define PPC_FEATURE2_HTM_NOSC 0x01000000
#define PPC_FEATURE2_ARCH_3_00 0x00800000 /* ISA 3.00 */
#define PPC_FEATURE2_HAS_IEEE128 0x00400000 /* VSX IEEE Binary Float 128-bit */
+#define PPC_FEATURE2_DARN 0x00200000 /* darn random number insn */
+#define PPC_FEATURE2_SCV 0x00100000 /* scv syscall */
/*
* IMPORTANT!
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 9b3e88b1a9c8..6f849832a669 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -124,7 +124,8 @@ extern void __restore_cpu_e6500(void);
#define COMMON_USER_POWER9 COMMON_USER_POWER8
#define COMMON_USER2_POWER9 (COMMON_USER2_POWER8 | \
PPC_FEATURE2_ARCH_3_00 | \
- PPC_FEATURE2_HAS_IEEE128)
+ PPC_FEATURE2_HAS_IEEE128 | \
+ PPC_FEATURE2_DARN )
#ifdef CONFIG_PPC_BOOK3E_64
#define COMMON_USER_BOOKE (COMMON_USER_PPC64 | PPC_FEATURE_BOOKE)
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index fcc7588a96d6..4c7656dc4e04 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -8,6 +8,7 @@
#include <linux/export.h>
#include <linux/init.h>
#include <linux/jump_label.h>
+#include <linux/libfdt.h>
#include <linux/memblock.h>
#include <linux/printk.h>
#include <linux/sched.h>
@@ -642,7 +643,6 @@ static struct dt_cpu_feature_match __initdata
{"processor-control-facility", feat_enable_dbell, CPU_FTR_DBELL},
{"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL},
{"processor-utilization-of-resources-register", feat_enable_purr, 0},
- {"subcore", feat_enable, CPU_FTR_SUBCORE},
{"no-execute", feat_enable, 0},
{"strong-access-ordering", feat_enable, CPU_FTR_SAO},
{"cache-inhibited-large-page", feat_enable_large_ci, 0},
@@ -671,12 +671,24 @@ static struct dt_cpu_feature_match __initdata
{"wait-v3", feat_enable, 0},
};
-/* XXX: how to configure this? Default + boot time? */
-#ifdef CONFIG_PPC_CPUFEATURES_ENABLE_UNKNOWN
-#define CPU_FEATURE_ENABLE_UNKNOWN 1
-#else
-#define CPU_FEATURE_ENABLE_UNKNOWN 0
-#endif
+static bool __initdata using_dt_cpu_ftrs;
+static bool __initdata enable_unknown = true;
+
+static int __init dt_cpu_ftrs_parse(char *str)
+{
+ if (!str)
+ return 0;
+
+ if (!strcmp(str, "off"))
+ using_dt_cpu_ftrs = false;
+ else if (!strcmp(str, "known"))
+ enable_unknown = false;
+ else
+ return 1;
+
+ return 0;
+}
+early_param("dt_cpu_ftrs", dt_cpu_ftrs_parse);
static void __init cpufeatures_setup_start(u32 isa)
{
@@ -707,7 +719,7 @@ static bool __init cpufeatures_process_feature(struct dt_cpu_feature *f)
}
}
- if (!known && CPU_FEATURE_ENABLE_UNKNOWN) {
+ if (!known && enable_unknown) {
if (!feat_try_enable_unknown(f)) {
pr_info("not enabling: %s (unknown and unsupported by kernel)\n",
f->name);
@@ -756,6 +768,26 @@ static void __init cpufeatures_setup_finished(void)
cur_cpu_spec->cpu_features, cur_cpu_spec->mmu_features);
}
+static int __init disabled_on_cmdline(void)
+{
+ unsigned long root, chosen;
+ const char *p;
+
+ root = of_get_flat_dt_root();
+ chosen = of_get_flat_dt_subnode_by_name(root, "chosen");
+ if (chosen == -FDT_ERR_NOTFOUND)
+ return false;
+
+ p = of_get_flat_dt_prop(chosen, "bootargs", NULL);
+ if (!p)
+ return false;
+
+ if (strstr(p, "dt_cpu_ftrs=off"))
+ return true;
+
+ return false;
+}
+
static int __init fdt_find_cpu_features(unsigned long node, const char *uname,
int depth, void *data)
{
@@ -766,8 +798,6 @@ static int __init fdt_find_cpu_features(unsigned long node, const char *uname,
return 0;
}
-static bool __initdata using_dt_cpu_ftrs = false;
-
bool __init dt_cpu_ftrs_in_use(void)
{
return using_dt_cpu_ftrs;
@@ -775,6 +805,8 @@ bool __init dt_cpu_ftrs_in_use(void)
bool __init dt_cpu_ftrs_init(void *fdt)
{
+ using_dt_cpu_ftrs = false;
+
/* Setup and verify the FDT, if it fails we just bail */
if (!early_init_dt_verify(fdt))
return false;
@@ -782,6 +814,9 @@ bool __init dt_cpu_ftrs_init(void *fdt)
if (!of_scan_flat_dt(fdt_find_cpu_features, NULL))
return false;
+ if (disabled_on_cmdline())
+ return false;
+
cpufeatures_setup_cpu();
using_dt_cpu_ftrs = true;
@@ -1027,5 +1062,8 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char
void __init dt_cpu_ftrs_scan(void)
{
+ if (!using_dt_cpu_ftrs)
+ return;
+
of_scan_flat_dt(dt_cpu_ftrs_scan_callback, NULL);
}
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index ae418b85c17c..b886795060fd 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1411,10 +1411,8 @@ USE_TEXT_SECTION()
.balign IFETCH_ALIGN_BYTES
do_hash_page:
#ifdef CONFIG_PPC_STD_MMU_64
- andis. r0,r4,0xa410 /* weird error? */
+ andis. r0,r4,0xa450 /* weird error? */
bne- handle_page_fault /* if not, try to insert a HPTE */
- andis. r0,r4,DSISR_DABRMATCH@h
- bne- handle_dabr_fault
CURRENT_THREAD_INFO(r11, r1)
lwz r0,TI_PREEMPT(r11) /* If we're in an "NMI" */
andis. r0,r0,NMI_MASK@h /* (i.e. an irq when soft-disabled) */
@@ -1438,11 +1436,16 @@ do_hash_page:
/* Error */
blt- 13f
+
+ /* Reload DSISR into r4 for the DABR check below */
+ ld r4,_DSISR(r1)
#endif /* CONFIG_PPC_STD_MMU_64 */
/* Here we have a page fault that hash_page can't handle. */
handle_page_fault:
-11: ld r4,_DAR(r1)
+11: andis. r0,r4,DSISR_DABRMATCH@h
+ bne- handle_dabr_fault
+ ld r4,_DAR(r1)
ld r5,_DSISR(r1)
addi r3,r1,STACK_FRAME_OVERHEAD
bl do_page_fault
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 07d4e0ad60db..4898d676dcae 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -416,7 +416,7 @@ power9_dd1_recover_paca:
* which needs to be restored from the stack.
*/
li r3, 1
- stb r0,PACA_NAPSTATELOST(r13)
+ stb r3,PACA_NAPSTATELOST(r13)
blr
/*
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 160ae0fa7d0d..01addfb0ed0a 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -43,6 +43,12 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
struct kretprobe_blackpoint kretprobe_blacklist[] = {{NULL, NULL}};
+int is_current_kprobe_addr(unsigned long addr)
+{
+ struct kprobe *p = kprobe_running();
+ return (p && (unsigned long)p->addr == addr) ? 1 : 0;
+}
+
bool arch_within_kprobe_blacklist(unsigned long addr)
{
return (addr >= (unsigned long)__kprobes_text_start &&
@@ -305,16 +311,17 @@ int kprobe_handler(struct pt_regs *regs)
save_previous_kprobe(kcb);
set_current_kprobe(p, regs, kcb);
kprobes_inc_nmissed_count(p);
- prepare_singlestep(p, regs);
kcb->kprobe_status = KPROBE_REENTER;
if (p->ainsn.boostable >= 0) {
ret = try_to_emulate(p, regs);
if (ret > 0) {
restore_previous_kprobe(kcb);
+ preempt_enable_no_resched();
return 1;
}
}
+ prepare_singlestep(p, regs);
return 1;
} else {
if (*addr != BREAKPOINT_INSTRUCTION) {
@@ -616,6 +623,15 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc);
#endif
+ /*
+ * jprobes use jprobe_return() which skips the normal return
+ * path of the function, and this messes up the accounting of the
+ * function graph tracer.
+ *
+ * Pause function graph tracing while performing the jprobe function.
+ */
+ pause_graph_tracing();
+
return 1;
}
NOKPROBE_SYMBOL(setjmp_pre_handler);
@@ -641,6 +657,8 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
* saved regs...
*/
memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
+ /* It's OK to start function graph tracing again */
+ unpause_graph_tracing();
preempt_enable_no_resched();
return 1;
}
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index d645da302bf2..2ad725ef4368 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -864,6 +864,25 @@ static void tm_reclaim_thread(struct thread_struct *thr,
if (!MSR_TM_SUSPENDED(mfmsr()))
return;
+ /*
+ * If we are in a transaction and FP is off then we can't have
+ * used FP inside that transaction. Hence the checkpointed
+ * state is the same as the live state. We need to copy the
+ * live state to the checkpointed state so that when the
+ * transaction is restored, the checkpointed state is correct
+ * and the aborted transaction sees the correct state. We use
+ * ckpt_regs.msr here as that's what tm_reclaim will use to
+ * determine if it's going to write the checkpointed state or
+ * not. So either this will write the checkpointed registers,
+ * or reclaim will. Similarly for VMX.
+ */
+ if ((thr->ckpt_regs.msr & MSR_FP) == 0)
+ memcpy(&thr->ckfp_state, &thr->fp_state,
+ sizeof(struct thread_fp_state));
+ if ((thr->ckpt_regs.msr & MSR_VEC) == 0)
+ memcpy(&thr->ckvr_state, &thr->vr_state,
+ sizeof(struct thread_vr_state));
+
giveup_all(container_of(thr, struct task_struct, thread));
tm_reclaim(thr, thr->ckpt_regs.msr, cause);
@@ -1647,6 +1666,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
#ifdef CONFIG_VSX
current->thread.used_vsr = 0;
#endif
+ current->thread.load_fp = 0;
memset(&current->thread.fp_state, 0, sizeof(current->thread.fp_state));
current->thread.fp_save_area = NULL;
#ifdef CONFIG_ALTIVEC
@@ -1655,6 +1675,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
current->thread.vr_save_area = NULL;
current->thread.vrsave = 0;
current->thread.used_vr = 0;
+ current->thread.load_vec = 0;
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_SPE
memset(current->thread.evr, 0, sizeof(current->thread.evr));
@@ -1666,6 +1687,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
current->thread.tm_tfhar = 0;
current->thread.tm_texasr = 0;
current->thread.tm_tfiar = 0;
+ current->thread.load_tm = 0;
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
}
EXPORT_SYMBOL(start_thread);
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 40c4887c27b6..f83056297441 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -161,7 +161,9 @@ static struct ibm_pa_feature {
{ .pabyte = 0, .pabit = 3, .cpu_features = CPU_FTR_CTRL },
{ .pabyte = 0, .pabit = 6, .cpu_features = CPU_FTR_NOEXECUTE },
{ .pabyte = 1, .pabit = 2, .mmu_features = MMU_FTR_CI_LARGE_PAGE },
+#ifdef CONFIG_PPC_RADIX_MMU
{ .pabyte = 40, .pabit = 0, .mmu_features = MMU_FTR_TYPE_RADIX },
+#endif
{ .pabyte = 1, .pabit = 1, .invert = 1, .cpu_features = CPU_FTR_NODSISRALIGN },
{ .pabyte = 5, .pabit = 0, .cpu_features = CPU_FTR_REAL_LE,
.cpu_user_ftrs = PPC_FEATURE_TRUE_LE },
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 71dcda91755d..857129acf960 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -928,7 +928,7 @@ void __init setup_arch(char **cmdline_p)
#ifdef CONFIG_PPC_MM_SLICES
#ifdef CONFIG_PPC64
- init_mm.context.addr_limit = TASK_SIZE_128TB;
+ init_mm.context.addr_limit = DEFAULT_MAP_WINDOW_USER64;
#else
#error "context.addr_limit not initialized."
#endif
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index f35ff9dea4fb..4640f6d64f8b 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -616,6 +616,24 @@ void __init exc_lvl_early_init(void)
#endif
/*
+ * Emergency stacks are used for a range of things, from asynchronous
+ * NMIs (system reset, machine check) to synchronous, process context.
+ * We set preempt_count to zero, even though that isn't necessarily correct. To
+ * get the right value we'd need to copy it from the previous thread_info, but
+ * doing that might fault causing more problems.
+ * TODO: what to do with accounting?
+ */
+static void emerg_stack_init_thread_info(struct thread_info *ti, int cpu)
+{
+ ti->task = NULL;
+ ti->cpu = cpu;
+ ti->preempt_count = 0;
+ ti->local_flags = 0;
+ ti->flags = 0;
+ klp_init_thread_info(ti);
+}
+
+/*
* Stack space used when we detect a bad kernel stack pointer, and
* early in SMP boots before relocation is enabled. Exclusive emergency
* stack for machine checks.
@@ -633,24 +651,31 @@ void __init emergency_stack_init(void)
* Since we use these as temporary stacks during secondary CPU
* bringup, we need to get at them in real mode. This means they
* must also be within the RMO region.
+ *
+ * The IRQ stacks allocated elsewhere in this file are zeroed and
+ * initialized in kernel/irq.c. These are initialized here in order
+ * to have emergency stacks available as early as possible.
*/
limit = min(safe_stack_limit(), ppc64_rma_size);
for_each_possible_cpu(i) {
struct thread_info *ti;
ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
- klp_init_thread_info(ti);
+ memset(ti, 0, THREAD_SIZE);
+ emerg_stack_init_thread_info(ti, i);
paca[i].emergency_sp = (void *)ti + THREAD_SIZE;
#ifdef CONFIG_PPC_BOOK3S_64
/* emergency stack for NMI exception handling. */
ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
- klp_init_thread_info(ti);
+ memset(ti, 0, THREAD_SIZE);
+ emerg_stack_init_thread_info(ti, i);
paca[i].nmi_emergency_sp = (void *)ti + THREAD_SIZE;
/* emergency stack for machine check exception handling. */
ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
- klp_init_thread_info(ti);
+ memset(ti, 0, THREAD_SIZE);
+ emerg_stack_init_thread_info(ti, i);
paca[i].mc_emergency_sp = (void *)ti + THREAD_SIZE;
#endif
}
@@ -661,7 +686,7 @@ void __init emergency_stack_init(void)
static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
{
- return __alloc_bootmem_node(NODE_DATA(cpu_to_node(cpu)), size, align,
+ return __alloc_bootmem_node(NODE_DATA(early_cpu_to_node(cpu)), size, align,
__pa(MAX_DMA_ADDRESS));
}
@@ -672,7 +697,7 @@ static void __init pcpu_fc_free(void *ptr, size_t size)
static int pcpu_cpu_distance(unsigned int from, unsigned int to)
{
- if (cpu_to_node(from) == cpu_to_node(to))
+ if (early_cpu_to_node(from) == early_cpu_to_node(to))
return LOCAL_DISTANCE;
else
return REMOTE_DISTANCE;
diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
index 7c933a99f5d5..c98e90b4ea7b 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
@@ -45,10 +45,14 @@ _GLOBAL(ftrace_caller)
stdu r1,-SWITCH_FRAME_SIZE(r1)
/* Save all gprs to pt_regs */
- SAVE_8GPRS(0,r1)
- SAVE_8GPRS(8,r1)
- SAVE_8GPRS(16,r1)
- SAVE_8GPRS(24,r1)
+ SAVE_GPR(0, r1)
+ SAVE_10GPRS(2, r1)
+ SAVE_10GPRS(12, r1)
+ SAVE_10GPRS(22, r1)
+
+ /* Save previous stack pointer (r1) */
+ addi r8, r1, SWITCH_FRAME_SIZE
+ std r8, GPR1(r1)
/* Load special regs for save below */
mfmsr r8
@@ -95,18 +99,44 @@ ftrace_call:
bl ftrace_stub
nop
- /* Load ctr with the possibly modified NIP */
- ld r3, _NIP(r1)
- mtctr r3
+ /* Load the possibly modified NIP */
+ ld r15, _NIP(r1)
+
#ifdef CONFIG_LIVEPATCH
- cmpd r14,r3 /* has NIP been altered? */
+ cmpd r14, r15 /* has NIP been altered? */
+#endif
+
+#if defined(CONFIG_LIVEPATCH) && defined(CONFIG_KPROBES_ON_FTRACE)
+ /* NIP has not been altered, skip over further checks */
+ beq 1f
+
+ /* Check if there is an active kprobe on us */
+ subi r3, r14, 4
+ bl is_current_kprobe_addr
+ nop
+
+ /*
+ * If r3 == 1, then this is a kprobe/jprobe.
+ * else, this is livepatched function.
+ *
+ * The conditional branch for livepatch_handler below will use the
+ * result of this comparison. For kprobe/jprobe, we just need to branch to
+ * the new NIP, not call livepatch_handler. The branch below is bne, so we
+ * want CR0[EQ] to be true if this is a kprobe/jprobe. Which means we want
+ * CR0[EQ] = (r3 == 1).
+ */
+ cmpdi r3, 1
+1:
#endif
+ /* Load CTR with the possibly modified NIP */
+ mtctr r15
+
/* Restore gprs */
- REST_8GPRS(0,r1)
- REST_8GPRS(8,r1)
- REST_8GPRS(16,r1)
- REST_8GPRS(24,r1)
+ REST_GPR(0,r1)
+ REST_10GPRS(2,r1)
+ REST_10GPRS(12,r1)
+ REST_10GPRS(22,r1)
/* Restore possibly modified LR */
ld r0, _LINK(r1)
@@ -119,7 +149,10 @@ ftrace_call:
addi r1, r1, SWITCH_FRAME_SIZE
#ifdef CONFIG_LIVEPATCH
- /* Based on the cmpd above, if the NIP was altered handle livepatch */
+ /*
+ * Based on the cmpd or cmpdi above, if the NIP was altered and we're
+ * not on a kprobe/jprobe, then handle livepatch.
+ */
bne- livepatch_handler
#endif
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 24de532c1736..0c52cb5d43f5 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -67,7 +67,7 @@ config KVM_BOOK3S_64
select KVM_BOOK3S_64_HANDLER
select KVM
select KVM_BOOK3S_PR_POSSIBLE if !KVM_BOOK3S_HV_POSSIBLE
- select SPAPR_TCE_IOMMU if IOMMU_SUPPORT
+ select SPAPR_TCE_IOMMU if IOMMU_SUPPORT && (PPC_SERIES || PPC_POWERNV)
---help---
Support running unmodified book3s_64 and book3s_32 guest kernels
in virtual machines on book3s_64 host processors.
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index d91a2604c496..381a6ec0ff3b 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -46,7 +46,7 @@ kvm-e500mc-objs := \
e500_emulate.o
kvm-objs-$(CONFIG_KVM_E500MC) := $(kvm-e500mc-objs)
-kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) := \
+kvm-book3s_64-builtin-objs-$(CONFIG_SPAPR_TCE_IOMMU) := \
book3s_64_vio_hv.o
kvm-pr-y := \
@@ -90,11 +90,11 @@ kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \
book3s_xics.o
kvm-book3s_64-objs-$(CONFIG_KVM_XIVE) += book3s_xive.o
+kvm-book3s_64-objs-$(CONFIG_SPAPR_TCE_IOMMU) += book3s_64_vio.o
kvm-book3s_64-module-objs := \
$(common-objs-y) \
book3s.o \
- book3s_64_vio.o \
book3s_rtas.o \
$(kvm-book3s_64-objs-y)
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index eda0a8f6fae8..3adfd2f5301c 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -301,6 +301,10 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
/* liobn, ioba, tce); */
+ /* For radix, we might be in virtual mode, so punt */
+ if (kvm_is_radix(vcpu->kvm))
+ return H_TOO_HARD;
+
stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
return H_TOO_HARD;
@@ -381,6 +385,10 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
bool prereg = false;
struct kvmppc_spapr_tce_iommu_table *stit;
+ /* For radix, we might be in virtual mode, so punt */
+ if (kvm_is_radix(vcpu->kvm))
+ return H_TOO_HARD;
+
stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
return H_TOO_HARD;
@@ -491,6 +499,10 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
long i, ret;
struct kvmppc_spapr_tce_iommu_table *stit;
+ /* For radix, we might be in virtual mode, so punt */
+ if (kvm_is_radix(vcpu->kvm))
+ return H_TOO_HARD;
+
stt = kvmppc_find_table(vcpu->kvm, liobn);
if (!stt)
return H_TOO_HARD;
@@ -527,6 +539,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
return H_SUCCESS;
}
+/* This can be called in either virtual mode or real mode */
long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
unsigned long ioba)
{
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 42b7a4fd57d9..8d1a365b8edc 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1486,6 +1486,14 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
r = set_vpa(vcpu, &vcpu->arch.dtl, addr, len);
break;
case KVM_REG_PPC_TB_OFFSET:
+ /*
+ * POWER9 DD1 has an erratum where writing TBU40 causes
+ * the timebase to lose ticks. So we don't let the
+ * timebase offset be changed on P9 DD1. (It is
+ * initialized to zero.)
+ */
+ if (cpu_has_feature(CPU_FTR_POWER9_DD1))
+ break;
/* round up to multiple of 2^24 */
vcpu->arch.vcore->tb_offset =
ALIGN(set_reg_val(id, *val), 1UL << 24);
@@ -2907,12 +2915,36 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
{
int r;
int srcu_idx;
+ unsigned long ebb_regs[3] = {}; /* shut up GCC */
+ unsigned long user_tar = 0;
+ unsigned int user_vrsave;
if (!vcpu->arch.sane) {
run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
return -EINVAL;
}
+ /*
+ * Don't allow entry with a suspended transaction, because
+ * the guest entry/exit code will lose it.
+ * If the guest has TM enabled, save away their TM-related SPRs
+ * (they will get restored by the TM unavailable interrupt).
+ */
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ if (cpu_has_feature(CPU_FTR_TM) && current->thread.regs &&
+ (current->thread.regs->msr & MSR_TM)) {
+ if (MSR_TM_ACTIVE(current->thread.regs->msr)) {
+ run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+ run->fail_entry.hardware_entry_failure_reason = 0;
+ return -EINVAL;
+ }
+ current->thread.tm_tfhar = mfspr(SPRN_TFHAR);
+ current->thread.tm_tfiar = mfspr(SPRN_TFIAR);
+ current->thread.tm_texasr = mfspr(SPRN_TEXASR);
+ current->thread.regs->msr &= ~MSR_TM;
+ }
+#endif
+
kvmppc_core_prepare_to_enter(vcpu);
/* No need to go into the guest when all we'll do is come back out */
@@ -2934,6 +2966,15 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
flush_all_to_thread(current);
+ /* Save userspace EBB and other register values */
+ if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+ ebb_regs[0] = mfspr(SPRN_EBBHR);
+ ebb_regs[1] = mfspr(SPRN_EBBRR);
+ ebb_regs[2] = mfspr(SPRN_BESCR);
+ user_tar = mfspr(SPRN_TAR);
+ }
+ user_vrsave = mfspr(SPRN_VRSAVE);
+
vcpu->arch.wqp = &vcpu->arch.vcore->wq;
vcpu->arch.pgdir = current->mm->pgd;
vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
@@ -2960,6 +3001,16 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
}
} while (is_kvmppc_resume_guest(r));
+ /* Restore userspace EBB and other register values */
+ if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+ mtspr(SPRN_EBBHR, ebb_regs[0]);
+ mtspr(SPRN_EBBRR, ebb_regs[1]);
+ mtspr(SPRN_BESCR, ebb_regs[2]);
+ mtspr(SPRN_TAR, user_tar);
+ mtspr(SPRN_FSCR, current->thread.fscr);
+ }
+ mtspr(SPRN_VRSAVE, user_vrsave);
+
out:
vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
atomic_dec(&vcpu->kvm->arch.vcpus_running);
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 88a65923c649..ee4c2558c305 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -207,7 +207,14 @@ EXPORT_SYMBOL_GPL(kvmppc_hwrng_present);
long kvmppc_h_random(struct kvm_vcpu *vcpu)
{
- if (powernv_get_random_real_mode(&vcpu->arch.gpr[4]))
+ int r;
+
+ /* Only need to do the expensive mfmsr() on radix */
+ if (kvm_is_radix(vcpu->kvm) && (mfmsr() & MSR_IR))
+ r = powernv_get_random_long(&vcpu->arch.gpr[4]);
+ else
+ r = powernv_get_random_real_mode(&vcpu->arch.gpr[4]);
+ if (r)
return H_SUCCESS;
return H_HARDWARE;
diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index 0fdc4a28970b..404deb512844 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -121,10 +121,20 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
* Put whatever is in the decrementer into the
* hypervisor decrementer.
*/
+BEGIN_FTR_SECTION
+ ld r5, HSTATE_KVM_VCORE(r13)
+ ld r6, VCORE_KVM(r5)
+ ld r9, KVM_HOST_LPCR(r6)
+ andis. r9, r9, LPCR_LD@h
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
mfspr r8,SPRN_DEC
mftb r7
- mtspr SPRN_HDEC,r8
+BEGIN_FTR_SECTION
+ /* On POWER9, don't sign-extend if host LPCR[LD] bit is set */
+ bne 32f
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
extsw r8,r8
+32: mtspr SPRN_HDEC,r8
add r8,r8,r7
std r8,HSTATE_DECEXP(r13)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index bdb3f76ceb6b..4888dd494604 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -32,12 +32,29 @@
#include <asm/opal.h>
#include <asm/xive-regs.h>
+/* Sign-extend HDEC if not on POWER9 */
+#define EXTEND_HDEC(reg) \
+BEGIN_FTR_SECTION; \
+ extsw reg, reg; \
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
+
#define VCPU_GPRS_TM(reg) (((reg) * ULONG_SIZE) + VCPU_GPR_TM)
/* Values in HSTATE_NAPPING(r13) */
#define NAPPING_CEDE 1
#define NAPPING_NOVCPU 2
+/* Stack frame offsets for kvmppc_hv_entry */
+#define SFS 144
+#define STACK_SLOT_TRAP (SFS-4)
+#define STACK_SLOT_TID (SFS-16)
+#define STACK_SLOT_PSSCR (SFS-24)
+#define STACK_SLOT_PID (SFS-32)
+#define STACK_SLOT_IAMR (SFS-40)
+#define STACK_SLOT_CIABR (SFS-48)
+#define STACK_SLOT_DAWR (SFS-56)
+#define STACK_SLOT_DAWRX (SFS-64)
+
/*
* Call kvmppc_hv_entry in real mode.
* Must be called with interrupts hard-disabled.
@@ -214,6 +231,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
kvmppc_primary_no_guest:
/* We handle this much like a ceded vcpu */
/* put the HDEC into the DEC, since HDEC interrupts don't wake us */
+ /* HDEC may be larger than DEC for arch >= v3.00, but since the */
+ /* HDEC value came from DEC in the first place, it will fit */
mfspr r3, SPRN_HDEC
mtspr SPRN_DEC, r3
/*
@@ -295,8 +314,9 @@ kvm_novcpu_wakeup:
/* See if our timeslice has expired (HDEC is negative) */
mfspr r0, SPRN_HDEC
+ EXTEND_HDEC(r0)
li r12, BOOK3S_INTERRUPT_HV_DECREMENTER
- cmpwi r0, 0
+ cmpdi r0, 0
blt kvm_novcpu_exit
/* Got an IPI but other vcpus aren't yet exiting, must be a latecomer */
@@ -319,10 +339,10 @@ kvm_novcpu_exit:
bl kvmhv_accumulate_time
#endif
13: mr r3, r12
- stw r12, 112-4(r1)
+ stw r12, STACK_SLOT_TRAP(r1)
bl kvmhv_commence_exit
nop
- lwz r12, 112-4(r1)
+ lwz r12, STACK_SLOT_TRAP(r1)
b kvmhv_switch_to_host
/*
@@ -390,8 +410,8 @@ kvm_secondary_got_guest:
lbz r4, HSTATE_PTID(r13)
cmpwi r4, 0
bne 63f
- lis r6, 0x7fff
- ori r6, r6, 0xffff
+ LOAD_REG_ADDR(r6, decrementer_max)
+ ld r6, 0(r6)
mtspr SPRN_HDEC, r6
/* and set per-LPAR registers, if doing dynamic micro-threading */
ld r6, HSTATE_SPLIT_MODE(r13)
@@ -545,11 +565,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
* *
*****************************************************************************/
-/* Stack frame offsets */
-#define STACK_SLOT_TID (112-16)
-#define STACK_SLOT_PSSCR (112-24)
-#define STACK_SLOT_PID (112-32)
-
.global kvmppc_hv_entry
kvmppc_hv_entry:
@@ -565,7 +580,7 @@ kvmppc_hv_entry:
*/
mflr r0
std r0, PPC_LR_STKOFF(r1)
- stdu r1, -112(r1)
+ stdu r1, -SFS(r1)
/* Save R1 in the PACA */
std r1, HSTATE_HOST_R1(r13)
@@ -749,10 +764,20 @@ BEGIN_FTR_SECTION
mfspr r5, SPRN_TIDR
mfspr r6, SPRN_PSSCR
mfspr r7, SPRN_PID
+ mfspr r8, SPRN_IAMR
std r5, STACK_SLOT_TID(r1)
std r6, STACK_SLOT_PSSCR(r1)
std r7, STACK_SLOT_PID(r1)
+ std r8, STACK_SLOT_IAMR(r1)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+BEGIN_FTR_SECTION
+ mfspr r5, SPRN_CIABR
+ mfspr r6, SPRN_DAWR
+ mfspr r7, SPRN_DAWRX
+ std r5, STACK_SLOT_CIABR(r1)
+ std r6, STACK_SLOT_DAWR(r1)
+ std r7, STACK_SLOT_DAWRX(r1)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
BEGIN_FTR_SECTION
/* Set partition DABR */
@@ -968,7 +993,8 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
/* Check if HDEC expires soon */
mfspr r3, SPRN_HDEC
- cmpwi r3, 512 /* 1 microsecond */
+ EXTEND_HDEC(r3)
+ cmpdi r3, 512 /* 1 microsecond */
blt hdec_soon
#ifdef CONFIG_KVM_XICS
@@ -1505,11 +1531,10 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
* set by the guest could disrupt the host.
*/
li r0, 0
- mtspr SPRN_IAMR, r0
- mtspr SPRN_CIABR, r0
- mtspr SPRN_DAWRX, r0
+ mtspr SPRN_PSPB, r0
mtspr SPRN_WORT, r0
BEGIN_FTR_SECTION
+ mtspr SPRN_IAMR, r0
mtspr SPRN_TCSCR, r0
/* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */
li r0, 1
@@ -1525,6 +1550,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
std r6,VCPU_UAMOR(r9)
li r6,0
mtspr SPRN_AMR,r6
+ mtspr SPRN_UAMOR, r6
/* Switch DSCR back to host value */
mfspr r8, SPRN_DSCR
@@ -1670,12 +1696,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
/* Restore host values of some registers */
BEGIN_FTR_SECTION
+ ld r5, STACK_SLOT_CIABR(r1)
+ ld r6, STACK_SLOT_DAWR(r1)
+ ld r7, STACK_SLOT_DAWRX(r1)
+ mtspr SPRN_CIABR, r5
+ mtspr SPRN_DAWR, r6
+ mtspr SPRN_DAWRX, r7
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+BEGIN_FTR_SECTION
ld r5, STACK_SLOT_TID(r1)
ld r6, STACK_SLOT_PSSCR(r1)
ld r7, STACK_SLOT_PID(r1)
+ ld r8, STACK_SLOT_IAMR(r1)
mtspr SPRN_TIDR, r5
mtspr SPRN_PSSCR, r6
mtspr SPRN_PID, r7
+ mtspr SPRN_IAMR, r8
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
BEGIN_FTR_SECTION
PPC_INVALIDATE_ERAT
@@ -1819,8 +1855,8 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
li r0, KVM_GUEST_MODE_NONE
stb r0, HSTATE_IN_GUEST(r13)
- ld r0, 112+PPC_LR_STKOFF(r1)
- addi r1, r1, 112
+ ld r0, SFS+PPC_LR_STKOFF(r1)
+ addi r1, r1, SFS
mtlr r0
blr
@@ -2366,12 +2402,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
mfspr r3, SPRN_DEC
mfspr r4, SPRN_HDEC
mftb r5
- cmpw r3, r4
+ extsw r3, r3
+ EXTEND_HDEC(r4)
+ cmpd r3, r4
ble 67f
mtspr SPRN_DEC, r4
67:
/* save expiry time of guest decrementer */
- extsw r3, r3
add r3, r3, r5
ld r4, HSTATE_KVM_VCPU(r13)
ld r5, HSTATE_KVM_VCORE(r13)
diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
index bcbeeb62dd13..8a4205fa774f 100644
--- a/arch/powerpc/kvm/book3s_pr_papr.c
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -50,7 +50,9 @@ static int kvmppc_h_pr_enter(struct kvm_vcpu *vcpu)
pteg_addr = get_pteg_addr(vcpu, pte_index);
mutex_lock(&vcpu->kvm->arch.hpt_mutex);
- copy_from_user(pteg, (void __user *)pteg_addr, sizeof(pteg));
+ ret = H_FUNCTION;
+ if (copy_from_user(pteg, (void __user *)pteg_addr, sizeof(pteg)))
+ goto done;
hpte = pteg;
ret = H_PTEG_FULL;
@@ -71,7 +73,9 @@ static int kvmppc_h_pr_enter(struct kvm_vcpu *vcpu)
hpte[0] = cpu_to_be64(kvmppc_get_gpr(vcpu, 6));
hpte[1] = cpu_to_be64(kvmppc_get_gpr(vcpu, 7));
pteg_addr += i * HPTE_SIZE;
- copy_to_user((void __user *)pteg_addr, hpte, HPTE_SIZE);
+ ret = H_FUNCTION;
+ if (copy_to_user((void __user *)pteg_addr, hpte, HPTE_SIZE))
+ goto done;
kvmppc_set_gpr(vcpu, 4, pte_index | i);
ret = H_SUCCESS;
@@ -93,7 +97,9 @@ static int kvmppc_h_pr_remove(struct kvm_vcpu *vcpu)
pteg = get_pteg_addr(vcpu, pte_index);
mutex_lock(&vcpu->kvm->arch.hpt_mutex);
- copy_from_user(pte, (void __user *)pteg, sizeof(pte));
+ ret = H_FUNCTION;
+ if (copy_from_user(pte, (void __user *)pteg, sizeof(pte)))
+ goto done;
pte[0] = be64_to_cpu((__force __be64)pte[0]);
pte[1] = be64_to_cpu((__force __be64)pte[1]);
@@ -103,7 +109,9 @@ static int kvmppc_h_pr_remove(struct kvm_vcpu *vcpu)
((flags & H_ANDCOND) && (pte[0] & avpn) != 0))
goto done;
- copy_to_user((void __user *)pteg, &v, sizeof(v));
+ ret = H_FUNCTION;
+ if (copy_to_user((void __user *)pteg, &v, sizeof(v)))
+ goto done;
rb = compute_tlbie_rb(pte[0], pte[1], pte_index);
vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false);
@@ -171,7 +179,10 @@ static int kvmppc_h_pr_bulk_remove(struct kvm_vcpu *vcpu)
}
pteg = get_pteg_addr(vcpu, tsh & H_BULK_REMOVE_PTEX);
- copy_from_user(pte, (void __user *)pteg, sizeof(pte));
+ if (copy_from_user(pte, (void __user *)pteg, sizeof(pte))) {
+ ret = H_FUNCTION;
+ break;
+ }
pte[0] = be64_to_cpu((__force __be64)pte[0]);
pte[1] = be64_to_cpu((__force __be64)pte[1]);
@@ -184,7 +195,10 @@ static int kvmppc_h_pr_bulk_remove(struct kvm_vcpu *vcpu)
tsh |= H_BULK_REMOVE_NOT_FOUND;
} else {
/* Splat the pteg in (userland) hpt */
- copy_to_user((void __user *)pteg, &v, sizeof(v));
+ if (copy_to_user((void __user *)pteg, &v, sizeof(v))) {
+ ret = H_FUNCTION;
+ break;
+ }
rb = compute_tlbie_rb(pte[0], pte[1],
tsh & H_BULK_REMOVE_PTEX);
@@ -211,7 +225,9 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu)
pteg = get_pteg_addr(vcpu, pte_index);
mutex_lock(&vcpu->kvm->arch.hpt_mutex);
- copy_from_user(pte, (void __user *)pteg, sizeof(pte));
+ ret = H_FUNCTION;
+ if (copy_from_user(pte, (void __user *)pteg, sizeof(pte)))
+ goto done;
pte[0] = be64_to_cpu((__force __be64)pte[0]);
pte[1] = be64_to_cpu((__force __be64)pte[1]);
@@ -234,7 +250,9 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu)
vcpu->arch.mmu.tlbie(vcpu, rb, rb & 1 ? true : false);
pte[0] = (__force u64)cpu_to_be64(pte[0]);
pte[1] = (__force u64)cpu_to_be64(pte[1]);
- copy_to_user((void __user *)pteg, pte, sizeof(pte));
+ ret = H_FUNCTION;
+ if (copy_to_user((void __user *)pteg, pte, sizeof(pte)))
+ goto done;
ret = H_SUCCESS;
done:
@@ -244,36 +262,37 @@ static int kvmppc_h_pr_protect(struct kvm_vcpu *vcpu)
return EMULATE_DONE;
}
-static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu)
+static int kvmppc_h_pr_logical_ci_load(struct kvm_vcpu *vcpu)
{
- unsigned long liobn = kvmppc_get_gpr(vcpu, 4);
- unsigned long ioba = kvmppc_get_gpr(vcpu, 5);
- unsigned long tce = kvmppc_get_gpr(vcpu, 6);
long rc;
- rc = kvmppc_h_put_tce(vcpu, liobn, ioba, tce);
+ rc = kvmppc_h_logical_ci_load(vcpu);
if (rc == H_TOO_HARD)
return EMULATE_FAIL;
kvmppc_set_gpr(vcpu, 3, rc);
return EMULATE_DONE;
}
-static int kvmppc_h_pr_logical_ci_load(struct kvm_vcpu *vcpu)
+static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu)
{
long rc;
- rc = kvmppc_h_logical_ci_load(vcpu);
+ rc = kvmppc_h_logical_ci_store(vcpu);
if (rc == H_TOO_HARD)
return EMULATE_FAIL;
kvmppc_set_gpr(vcpu, 3, rc);
return EMULATE_DONE;
}
-static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu)
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu)
{
+ unsigned long liobn = kvmppc_get_gpr(vcpu, 4);
+ unsigned long ioba = kvmppc_get_gpr(vcpu, 5);
+ unsigned long tce = kvmppc_get_gpr(vcpu, 6);
long rc;
- rc = kvmppc_h_logical_ci_store(vcpu);
+ rc = kvmppc_h_put_tce(vcpu, liobn, ioba, tce);
if (rc == H_TOO_HARD)
return EMULATE_FAIL;
kvmppc_set_gpr(vcpu, 3, rc);
@@ -311,6 +330,23 @@ static int kvmppc_h_pr_stuff_tce(struct kvm_vcpu *vcpu)
return EMULATE_DONE;
}
+#else /* CONFIG_SPAPR_TCE_IOMMU */
+static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu)
+{
+ return EMULATE_FAIL;
+}
+
+static int kvmppc_h_pr_put_tce_indirect(struct kvm_vcpu *vcpu)
+{
+ return EMULATE_FAIL;
+}
+
+static int kvmppc_h_pr_stuff_tce(struct kvm_vcpu *vcpu)
+{
+ return EMULATE_FAIL;
+}
+#endif /* CONFIG_SPAPR_TCE_IOMMU */
+
static int kvmppc_h_pr_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd)
{
long rc = kvmppc_xics_hcall(vcpu, cmd);
diff --git a/arch/powerpc/kvm/book3s_xive_template.c b/arch/powerpc/kvm/book3s_xive_template.c
index 023a31133c37..4636ca6e7d38 100644
--- a/arch/powerpc/kvm/book3s_xive_template.c
+++ b/arch/powerpc/kvm/book3s_xive_template.c
@@ -69,7 +69,7 @@ static void GLUE(X_PFX,source_eoi)(u32 hw_irq, struct xive_irq_data *xd)
{
/* If the XIVE supports the new "store EOI facility, use it */
if (xd->flags & XIVE_IRQ_FLAG_STORE_EOI)
- __x_writeq(0, __x_eoi_page(xd));
+ __x_writeq(0, __x_eoi_page(xd) + XIVE_ESB_STORE_EOI);
else if (hw_irq && xd->flags & XIVE_IRQ_FLAG_EOI_FW) {
opal_int_eoi(hw_irq);
} else {
@@ -89,7 +89,7 @@ static void GLUE(X_PFX,source_eoi)(u32 hw_irq, struct xive_irq_data *xd)
* properly.
*/
if (xd->flags & XIVE_IRQ_FLAG_LSI)
- __x_readq(__x_eoi_page(xd));
+ __x_readq(__x_eoi_page(xd) + XIVE_ESB_LOAD_EOI);
else {
eoi_val = GLUE(X_PFX,esb_load)(xd, XIVE_ESB_SET_PQ_00);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index f7cf2cd564ef..7f71ab5fcad1 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -1749,7 +1749,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = kvm_vm_ioctl_enable_cap(kvm, &cap);
break;
}
-#ifdef CONFIG_PPC_BOOK3S_64
+#ifdef CONFIG_SPAPR_TCE_IOMMU
case KVM_CREATE_SPAPR_TCE_64: {
struct kvm_create_spapr_tce_64 create_tce_64;
@@ -1780,6 +1780,8 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce_64);
goto out;
}
+#endif
+#ifdef CONFIG_PPC_BOOK3S_64
case KVM_PPC_GET_SMMU_INFO: {
struct kvm_ppc_smmu_info info;
struct kvm *kvm = filp->private_data;
diff --git a/arch/powerpc/mm/dump_linuxpagetables.c b/arch/powerpc/mm/dump_linuxpagetables.c
index d659345a98d6..44fe4833910f 100644
--- a/arch/powerpc/mm/dump_linuxpagetables.c
+++ b/arch/powerpc/mm/dump_linuxpagetables.c
@@ -16,6 +16,7 @@
*/
#include <linux/debugfs.h>
#include <linux/fs.h>
+#include <linux/hugetlb.h>
#include <linux/io.h>
#include <linux/mm.h>
#include <linux/sched.h>
@@ -391,7 +392,7 @@ static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
for (i = 0; i < PTRS_PER_PMD; i++, pmd++) {
addr = start + i * PMD_SIZE;
- if (!pmd_none(*pmd))
+ if (!pmd_none(*pmd) && !pmd_huge(*pmd))
/* pmd exists */
walk_pte(st, pmd, addr);
else
@@ -407,7 +408,7 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start)
for (i = 0; i < PTRS_PER_PUD; i++, pud++) {
addr = start + i * PUD_SIZE;
- if (!pud_none(*pud))
+ if (!pud_none(*pud) && !pud_huge(*pud))
/* pud exists */
walk_pmd(st, pud, addr);
else
@@ -427,7 +428,7 @@ static void walk_pagetables(struct pg_state *st)
*/
for (i = 0; i < PTRS_PER_PGD; i++, pgd++) {
addr = KERN_VIRT_START + i * PGDIR_SIZE;
- if (!pgd_none(*pgd))
+ if (!pgd_none(*pgd) && !pgd_huge(*pgd))
/* pgd exists */
walk_pud(st, pgd, addr);
else
diff --git a/arch/powerpc/mm/hugetlbpage-radix.c b/arch/powerpc/mm/hugetlbpage-radix.c
index 6575b9aabef4..a12e86395025 100644
--- a/arch/powerpc/mm/hugetlbpage-radix.c
+++ b/arch/powerpc/mm/hugetlbpage-radix.c
@@ -68,7 +68,7 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
addr = ALIGN(addr, huge_page_size(h));
vma = find_vma(mm, addr);
if (mm->task_size - len >= addr &&
- (!vma || addr + len <= vma->vm_start))
+ (!vma || addr + len <= vm_start_gap(vma)))
return addr;
}
/*
diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c
index 9dbd2a733d6b..0ee6be4f1ba4 100644
--- a/arch/powerpc/mm/mmap.c
+++ b/arch/powerpc/mm/mmap.c
@@ -112,7 +112,7 @@ radix__arch_get_unmapped_area(struct file *filp, unsigned long addr,
addr = PAGE_ALIGN(addr);
vma = find_vma(mm, addr);
if (mm->task_size - len >= addr && addr >= mmap_min_addr &&
- (!vma || addr + len <= vma->vm_start))
+ (!vma || addr + len <= vm_start_gap(vma)))
return addr;
}
@@ -157,7 +157,7 @@ radix__arch_get_unmapped_area_topdown(struct file *filp,
addr = PAGE_ALIGN(addr);
vma = find_vma(mm, addr);
if (mm->task_size - len >= addr && addr >= mmap_min_addr &&
- (!vma || addr + len <= vma->vm_start))
+ (!vma || addr + len <= vm_start_gap(vma)))
return addr;
}
diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index c6dca2ae78ef..a3edf813d455 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -99,7 +99,7 @@ static int hash__init_new_context(struct mm_struct *mm)
* mm->context.addr_limit. Default to max task size so that we copy the
* default values to paca which will help us to handle slb miss early.
*/
- mm->context.addr_limit = TASK_SIZE_128TB;
+ mm->context.addr_limit = DEFAULT_MAP_WINDOW_USER64;
/*
* The old code would re-promote on fork, we don't do that when using
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
index 966b9fccfa66..45f6740dd407 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/slice.c
@@ -99,7 +99,7 @@ static int slice_area_is_free(struct mm_struct *mm, unsigned long addr,
if ((mm->task_size - len) < addr)
return 0;
vma = find_vma(mm, addr);
- return (!vma || (addr + len) <= vma->vm_start);
+ return (!vma || (addr + len) <= vm_start_gap(vma));
}
static int slice_low_has_vma(struct mm_struct *mm, unsigned long slice)
diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c
index cbd82fde5770..09ceea6175ba 100644
--- a/arch/powerpc/perf/perf_regs.c
+++ b/arch/powerpc/perf/perf_regs.c
@@ -101,5 +101,6 @@ void perf_get_regs_user(struct perf_regs *regs_user,
struct pt_regs *regs_user_copy)
{
regs_user->regs = task_pt_regs(current);
- regs_user->abi = perf_reg_abi(current);
+ regs_user->abi = (regs_user->regs) ? perf_reg_abi(current) :
+ PERF_SAMPLE_REGS_ABI_NONE;
}
diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c
index 018f8e90ac35..bb28e1a41257 100644
--- a/arch/powerpc/perf/power9-pmu.c
+++ b/arch/powerpc/perf/power9-pmu.c
@@ -402,7 +402,7 @@ static struct power_pmu power9_isa207_pmu = {
.name = "POWER9",
.n_counter = MAX_PMU_COUNTERS,
.add_fields = ISA207_ADD_FIELDS,
- .test_adder = ISA207_TEST_ADDER,
+ .test_adder = P9_DD1_TEST_ADDER,
.compute_mmcr = isa207_compute_mmcr,
.config_bhrb = power9_config_bhrb,
.bhrb_filter_map = power9_bhrb_filter_map,
@@ -421,7 +421,7 @@ static struct power_pmu power9_pmu = {
.name = "POWER9",
.n_counter = MAX_PMU_COUNTERS,
.add_fields = ISA207_ADD_FIELDS,
- .test_adder = P9_DD1_TEST_ADDER,
+ .test_adder = ISA207_TEST_ADDER,
.compute_mmcr = isa207_compute_mmcr,
.config_bhrb = power9_config_bhrb,
.bhrb_filter_map = power9_bhrb_filter_map,
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 33244e3d9375..4fd64d3f5c44 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -59,6 +59,17 @@ config PPC_OF_BOOT_TRAMPOLINE
In case of doubt, say Y
+config PPC_DT_CPU_FTRS
+ bool "Device-tree based CPU feature discovery & setup"
+ depends on PPC_BOOK3S_64
+ default y
+ help
+ This enables code to use a new device tree binding for describing CPU
+ compatibility and features. Saying Y here will attempt to use the new
+ binding if the firmware provides it. Currently only the skiboot
+ firmware provides this binding.
+ If you're not sure say Y.
+
config UDBG_RTAS_CONSOLE
bool "RTAS based debug console"
depends on PPC_RTAS
diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
index 96c2b8a40630..0c45cdbac4cf 100644
--- a/arch/powerpc/platforms/cell/spu_base.c
+++ b/arch/powerpc/platforms/cell/spu_base.c
@@ -197,7 +197,9 @@ static int __spu_trap_data_map(struct spu *spu, unsigned long ea, u64 dsisr)
(REGION_ID(ea) != USER_REGION_ID)) {
spin_unlock(&spu->register_lock);
- ret = hash_page(ea, _PAGE_PRESENT | _PAGE_READ, 0x300, dsisr);
+ ret = hash_page(ea,
+ _PAGE_PRESENT | _PAGE_READ | _PAGE_PRIVILEGED,
+ 0x300, dsisr);
spin_lock(&spu->register_lock);
if (!ret) {
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index e5a891ae80ee..84b7ac926ce6 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -175,6 +175,8 @@ static int spufs_arch_write_note(struct spu_context *ctx, int i,
skip = roundup(cprm->pos - total + sz, 4) - cprm->pos;
if (!dump_skip(cprm, skip))
goto Eio;
+
+ rc = 0;
out:
free_page((unsigned long)buf);
return rc;
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index 067defeea691..b5d960d6db3d 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -75,7 +75,8 @@ struct pci_dev *pnv_pci_get_npu_dev(struct pci_dev *gpdev, int index)
if (WARN_ON(!gpdev))
return NULL;
- if (WARN_ON(!gpdev->dev.of_node))
+ /* Not all PCI devices have device-tree nodes */
+ if (!gpdev->dev.of_node)
return NULL;
/* Get assoicated PCI device */
@@ -448,7 +449,7 @@ static int mmio_launch_invalidate(struct npu *npu, unsigned long launch,
return mmio_atsd_reg;
}
-static int mmio_invalidate_pid(struct npu *npu, unsigned long pid)
+static int mmio_invalidate_pid(struct npu *npu, unsigned long pid, bool flush)
{
unsigned long launch;
@@ -464,12 +465,15 @@ static int mmio_invalidate_pid(struct npu *npu, unsigned long pid)
/* PID */
launch |= pid << PPC_BITLSHIFT(38);
+ /* No flush */
+ launch |= !flush << PPC_BITLSHIFT(39);
+
/* Invalidating the entire process doesn't use a va */
return mmio_launch_invalidate(npu, launch, 0);
}
static int mmio_invalidate_va(struct npu *npu, unsigned long va,
- unsigned long pid)
+ unsigned long pid, bool flush)
{
unsigned long launch;
@@ -485,26 +489,60 @@ static int mmio_invalidate_va(struct npu *npu, unsigned long va,
/* PID */
launch |= pid << PPC_BITLSHIFT(38);
+ /* No flush */
+ launch |= !flush << PPC_BITLSHIFT(39);
+
return mmio_launch_invalidate(npu, launch, va);
}
#define mn_to_npu_context(x) container_of(x, struct npu_context, mn)
+struct mmio_atsd_reg {
+ struct npu *npu;
+ int reg;
+};
+
+static void mmio_invalidate_wait(
+ struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS], bool flush)
+{
+ struct npu *npu;
+ int i, reg;
+
+ /* Wait for all invalidations to complete */
+ for (i = 0; i <= max_npu2_index; i++) {
+ if (mmio_atsd_reg[i].reg < 0)
+ continue;
+
+ /* Wait for completion */
+ npu = mmio_atsd_reg[i].npu;
+ reg = mmio_atsd_reg[i].reg;
+ while (__raw_readq(npu->mmio_atsd_regs[reg] + XTS_ATSD_STAT))
+ cpu_relax();
+
+ put_mmio_atsd_reg(npu, reg);
+
+ /*
+ * The GPU requires two flush ATSDs to ensure all entries have
+ * been flushed. We use PID 0 as it will never be used for a
+ * process on the GPU.
+ */
+ if (flush)
+ mmio_invalidate_pid(npu, 0, true);
+ }
+}
+
/*
* Invalidate either a single address or an entire PID depending on
* the value of va.
*/
static void mmio_invalidate(struct npu_context *npu_context, int va,
- unsigned long address)
+ unsigned long address, bool flush)
{
- int i, j, reg;
+ int i, j;
struct npu *npu;
struct pnv_phb *nphb;
struct pci_dev *npdev;
- struct {
- struct npu *npu;
- int reg;
- } mmio_atsd_reg[NV_MAX_NPUS];
+ struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS];
unsigned long pid = npu_context->mm->context.id;
/*
@@ -524,10 +562,11 @@ static void mmio_invalidate(struct npu_context *npu_context, int va,
if (va)
mmio_atsd_reg[i].reg =
- mmio_invalidate_va(npu, address, pid);
+ mmio_invalidate_va(npu, address, pid,
+ flush);
else
mmio_atsd_reg[i].reg =
- mmio_invalidate_pid(npu, pid);
+ mmio_invalidate_pid(npu, pid, flush);
/*
* The NPU hardware forwards the shootdown to all GPUs
@@ -543,18 +582,10 @@ static void mmio_invalidate(struct npu_context *npu_context, int va,
*/
flush_tlb_mm(npu_context->mm);
- /* Wait for all invalidations to complete */
- for (i = 0; i <= max_npu2_index; i++) {
- if (mmio_atsd_reg[i].reg < 0)
- continue;
-
- /* Wait for completion */
- npu = mmio_atsd_reg[i].npu;
- reg = mmio_atsd_reg[i].reg;
- while (__raw_readq(npu->mmio_atsd_regs[reg] + XTS_ATSD_STAT))
- cpu_relax();
- put_mmio_atsd_reg(npu, reg);
- }
+ mmio_invalidate_wait(mmio_atsd_reg, flush);
+ if (flush)
+ /* Wait for the flush to complete */
+ mmio_invalidate_wait(mmio_atsd_reg, false);
}
static void pnv_npu2_mn_release(struct mmu_notifier *mn,
@@ -570,7 +601,7 @@ static void pnv_npu2_mn_release(struct mmu_notifier *mn,
* There should be no more translation requests for this PID, but we
* need to ensure any entries for it are removed from the TLB.
*/
- mmio_invalidate(npu_context, 0, 0);
+ mmio_invalidate(npu_context, 0, 0, true);
}
static void pnv_npu2_mn_change_pte(struct mmu_notifier *mn,
@@ -580,7 +611,7 @@ static void pnv_npu2_mn_change_pte(struct mmu_notifier *mn,
{
struct npu_context *npu_context = mn_to_npu_context(mn);
- mmio_invalidate(npu_context, 1, address);
+ mmio_invalidate(npu_context, 1, address, true);
}
static void pnv_npu2_mn_invalidate_page(struct mmu_notifier *mn,
@@ -589,7 +620,7 @@ static void pnv_npu2_mn_invalidate_page(struct mmu_notifier *mn,
{
struct npu_context *npu_context = mn_to_npu_context(mn);
- mmio_invalidate(npu_context, 1, address);
+ mmio_invalidate(npu_context, 1, address, true);
}
static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
@@ -599,8 +630,11 @@ static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
struct npu_context *npu_context = mn_to_npu_context(mn);
unsigned long address;
- for (address = start; address <= end; address += PAGE_SIZE)
- mmio_invalidate(npu_context, 1, address);
+ for (address = start; address < end; address += PAGE_SIZE)
+ mmio_invalidate(npu_context, 1, address, false);
+
+ /* Do the flush only on the final addess == end */
+ mmio_invalidate(npu_context, 1, address, true);
}
static const struct mmu_notifier_ops nv_nmmu_notifier_ops = {
@@ -650,8 +684,11 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
/* No nvlink associated with this GPU device */
return ERR_PTR(-ENODEV);
- if (!mm) {
- /* kernel thread contexts are not supported */
+ if (!mm || mm->context.id == 0) {
+ /*
+ * Kernel thread contexts are not supported and context id 0 is
+ * reserved on the GPU.
+ */
return ERR_PTR(-EINVAL);
}
@@ -714,7 +751,7 @@ static void pnv_npu2_release_context(struct kref *kref)
void pnv_npu2_destroy_context(struct npu_context *npu_context,
struct pci_dev *gpdev)
{
- struct pnv_phb *nphb, *phb;
+ struct pnv_phb *nphb;
struct npu *npu;
struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0);
struct device_node *nvlink_dn;
@@ -728,13 +765,12 @@ void pnv_npu2_destroy_context(struct npu_context *npu_context,
nphb = pci_bus_to_host(npdev->bus)->private_data;
npu = &nphb->npu;
- phb = pci_bus_to_host(gpdev->bus)->private_data;
nvlink_dn = of_parse_phandle(npdev->dev.of_node, "ibm,nvlink", 0);
if (WARN_ON(of_property_read_u32(nvlink_dn, "ibm,npu-link-index",
&nvlink_index)))
return;
npu_context->npdev[npu->index][nvlink_index] = NULL;
- opal_npu_destroy_context(phb->opal_id, npu_context->mm->context.id,
+ opal_npu_destroy_context(nphb->opal_id, npu_context->mm->context.id,
PCI_DEVID(gpdev->bus->number, gpdev->devfn));
kref_put(&npu_context->kref, pnv_npu2_release_context);
}
diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c
index 0babef11136f..8c6119280c13 100644
--- a/arch/powerpc/platforms/powernv/subcore.c
+++ b/arch/powerpc/platforms/powernv/subcore.c
@@ -407,7 +407,13 @@ static DEVICE_ATTR(subcores_per_core, 0644,
static int subcore_init(void)
{
- if (!cpu_has_feature(CPU_FTR_SUBCORE))
+ unsigned pvr_ver;
+
+ pvr_ver = PVR_VER(mfspr(SPRN_PVR));
+
+ if (pvr_ver != PVR_POWER8 &&
+ pvr_ver != PVR_POWER8E &&
+ pvr_ver != PVR_POWER8NVL)
return 0;
/*
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index e104c71ea44a..1fb162ba9d1c 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -124,6 +124,7 @@ static struct property *dlpar_clone_drconf_property(struct device_node *dn)
for (i = 0; i < num_lmbs; i++) {
lmbs[i].base_addr = be64_to_cpu(lmbs[i].base_addr);
lmbs[i].drc_index = be32_to_cpu(lmbs[i].drc_index);
+ lmbs[i].aa_index = be32_to_cpu(lmbs[i].aa_index);
lmbs[i].flags = be32_to_cpu(lmbs[i].flags);
}
@@ -147,6 +148,7 @@ static void dlpar_update_drconf_property(struct device_node *dn,
for (i = 0; i < num_lmbs; i++) {
lmbs[i].base_addr = cpu_to_be64(lmbs[i].base_addr);
lmbs[i].drc_index = cpu_to_be32(lmbs[i].drc_index);
+ lmbs[i].aa_index = cpu_to_be32(lmbs[i].aa_index);
lmbs[i].flags = cpu_to_be32(lmbs[i].flags);
}
diff --git a/arch/powerpc/sysdev/simple_gpio.c b/arch/powerpc/sysdev/simple_gpio.c
index ef470b470b04..6afddae2fb47 100644
--- a/arch/powerpc/sysdev/simple_gpio.c
+++ b/arch/powerpc/sysdev/simple_gpio.c
@@ -75,7 +75,8 @@ static int u8_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
static void u8_gpio_save_regs(struct of_mm_gpio_chip *mm_gc)
{
- struct u8_gpio_chip *u8_gc = gpiochip_get_data(&mm_gc->gc);
+ struct u8_gpio_chip *u8_gc =
+ container_of(mm_gc, struct u8_gpio_chip, mm_gc);
u8_gc->data = in_8(mm_gc->regs);
}
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
index 913825086b8d..8f5e3035483b 100644
--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -297,7 +297,7 @@ void xive_do_source_eoi(u32 hw_irq, struct xive_irq_data *xd)
{
/* If the XIVE supports the new "store EOI facility, use it */
if (xd->flags & XIVE_IRQ_FLAG_STORE_EOI)
- out_be64(xd->eoi_mmio, 0);
+ out_be64(xd->eoi_mmio + XIVE_ESB_STORE_EOI, 0);
else if (hw_irq && xd->flags & XIVE_IRQ_FLAG_EOI_FW) {
/*
* The FW told us to call it. This happens for some