summaryrefslogtreecommitdiff
path: root/arch/powerpc/platforms
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/platforms')
-rw-r--r--arch/powerpc/platforms/44x/fsp2.c8
-rw-r--r--arch/powerpc/platforms/Kconfig.cputype1
-rw-r--r--arch/powerpc/platforms/cell/spu_manage.c25
-rw-r--r--arch/powerpc/platforms/embedded6xx/wii.c2
-rw-r--r--arch/powerpc/platforms/powermac/Makefile3
-rw-r--r--arch/powerpc/platforms/powermac/time.c126
-rw-r--r--arch/powerpc/platforms/powernv/Kconfig5
-rw-r--r--arch/powerpc/platforms/powernv/memtrace.c21
-rw-r--r--arch/powerpc/platforms/powernv/npu-dma.c198
-rw-r--r--arch/powerpc/platforms/powernv/opal-powercap.c3
-rw-r--r--arch/powerpc/platforms/powernv/opal-sensor-groups.c4
-rw-r--r--arch/powerpc/platforms/powernv/opal-sysparam.c2
-rw-r--r--arch/powerpc/platforms/powernv/opal.c2
-rw-r--r--arch/powerpc/platforms/powernv/setup.c47
-rw-r--r--arch/powerpc/platforms/pseries/dlpar.c37
-rw-r--r--arch/powerpc/platforms/pseries/dtl.c4
-rw-r--r--arch/powerpc/platforms/pseries/event_sources.c40
-rw-r--r--arch/powerpc/platforms/pseries/firmware.c1
-rw-r--r--arch/powerpc/platforms/pseries/hotplug-cpu.c28
-rw-r--r--arch/powerpc/platforms/pseries/hotplug-memory.c55
-rw-r--r--arch/powerpc/platforms/pseries/ibmebus.c2
-rw-r--r--arch/powerpc/platforms/pseries/lpar.c241
-rw-r--r--arch/powerpc/platforms/pseries/lparcfg.c5
-rw-r--r--arch/powerpc/platforms/pseries/mobility.c18
-rw-r--r--arch/powerpc/platforms/pseries/pseries.h6
-rw-r--r--arch/powerpc/platforms/pseries/ras.c305
-rw-r--r--arch/powerpc/platforms/pseries/setup.c14
-rw-r--r--arch/powerpc/platforms/pseries/vio.c27
28 files changed, 815 insertions, 415 deletions
diff --git a/arch/powerpc/platforms/44x/fsp2.c b/arch/powerpc/platforms/44x/fsp2.c
index 04f0c73a9b4f..7a507f775308 100644
--- a/arch/powerpc/platforms/44x/fsp2.c
+++ b/arch/powerpc/platforms/44x/fsp2.c
@@ -210,15 +210,15 @@ static void node_irq_request(const char *compat, irq_handler_t errirq_handler)
for_each_compatible_node(np, NULL, compat) {
irq = irq_of_parse_and_map(np, 0);
if (irq == NO_IRQ) {
- pr_err("device tree node %s is missing a interrupt",
- np->name);
+ pr_err("device tree node %pOFn is missing a interrupt",
+ np);
return;
}
rc = request_irq(irq, errirq_handler, 0, np->name, np);
if (rc) {
- pr_err("fsp_of_probe: request_irq failed: np=%s rc=%d",
- np->full_name, rc);
+ pr_err("fsp_of_probe: request_irq failed: np=%pOF rc=%d",
+ np, rc);
return;
}
}
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 6c6a7c72cae4..495db17dcbca 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -72,6 +72,7 @@ config PPC_BOOK3S_64
select PPC_HAVE_PMU_SUPPORT
select SYS_SUPPORTS_HUGETLBFS
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+ select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
select ARCH_SUPPORTS_NUMA_BALANCING
select IRQ_WORK
diff --git a/arch/powerpc/platforms/cell/spu_manage.c b/arch/powerpc/platforms/cell/spu_manage.c
index 5c409c98cca8..f7e36373f6e0 100644
--- a/arch/powerpc/platforms/cell/spu_manage.c
+++ b/arch/powerpc/platforms/cell/spu_manage.c
@@ -180,35 +180,22 @@ out:
static int __init spu_map_interrupts(struct spu *spu, struct device_node *np)
{
- struct of_phandle_args oirq;
- int ret;
int i;
for (i=0; i < 3; i++) {
- ret = of_irq_parse_one(np, i, &oirq);
- if (ret) {
- pr_debug("spu_new: failed to get irq %d\n", i);
- goto err;
- }
- ret = -EINVAL;
- pr_debug(" irq %d no 0x%x on %pOF\n", i, oirq.args[0],
- oirq.np);
- spu->irqs[i] = irq_create_of_mapping(&oirq);
- if (!spu->irqs[i]) {
- pr_debug("spu_new: failed to map it !\n");
+ spu->irqs[i] = irq_of_parse_and_map(np, i);
+ if (!spu->irqs[i])
goto err;
- }
}
return 0;
err:
- pr_debug("failed to map irq %x for spu %s\n", *oirq.args,
- spu->name);
+ pr_debug("failed to map irq %x for spu %s\n", i, spu->name);
for (; i >= 0; i--) {
if (spu->irqs[i])
irq_dispose_mapping(spu->irqs[i]);
}
- return ret;
+ return -EINVAL;
}
static int spu_map_resource(struct spu *spu, int nr,
@@ -295,8 +282,8 @@ static int __init of_enumerate_spus(int (*fn)(void *data))
for_each_node_by_type(node, "spe") {
ret = fn(node);
if (ret) {
- printk(KERN_WARNING "%s: Error initializing %s\n",
- __func__, node->name);
+ printk(KERN_WARNING "%s: Error initializing %pOFn\n",
+ __func__, node);
of_node_put(node);
break;
}
diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c
index 403523c061ba..ecf703ee3a76 100644
--- a/arch/powerpc/platforms/embedded6xx/wii.c
+++ b/arch/powerpc/platforms/embedded6xx/wii.c
@@ -112,7 +112,7 @@ static void __iomem *wii_ioremap_hw_regs(char *name, char *compatible)
}
error = of_address_to_resource(np, 0, &res);
if (error) {
- pr_err("no valid reg found for %s\n", np->name);
+ pr_err("no valid reg found for %pOFn\n", np);
goto out_put;
}
diff --git a/arch/powerpc/platforms/powermac/Makefile b/arch/powerpc/platforms/powermac/Makefile
index f2839eed0f89..923bfb340433 100644
--- a/arch/powerpc/platforms/powermac/Makefile
+++ b/arch/powerpc/platforms/powermac/Makefile
@@ -1,9 +1,10 @@
# SPDX-License-Identifier: GPL-2.0
CFLAGS_bootx_init.o += -fPIC
+CFLAGS_bootx_init.o += $(call cc-option, -fno-stack-protector)
ifdef CONFIG_FUNCTION_TRACER
# Do not trace early boot code
-CFLAGS_REMOVE_bootx_init.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_bootx_init.o = $(CC_FLAGS_FTRACE)
endif
obj-y += pic.o setup.o time.o feature.o pci.o \
diff --git a/arch/powerpc/platforms/powermac/time.c b/arch/powerpc/platforms/powermac/time.c
index f92c1918fb56..f157e3d071f2 100644
--- a/arch/powerpc/platforms/powermac/time.c
+++ b/arch/powerpc/platforms/powermac/time.c
@@ -45,13 +45,6 @@
#endif
/*
- * Offset between Unix time (1970-based) and Mac time (1904-based). Cuda and PMU
- * times wrap in 2040. If we need to handle later times, the read_time functions
- * need to be changed to interpret wrapped times as post-2040.
- */
-#define RTC_OFFSET 2082844800
-
-/*
* Calibrate the decrementer frequency with the VIA timer 1.
*/
#define VIA_TIMER_FREQ_6 4700000 /* time 1 frequency * 6 */
@@ -90,98 +83,6 @@ long __init pmac_time_init(void)
return delta;
}
-#ifdef CONFIG_ADB_CUDA
-static time64_t cuda_get_time(void)
-{
- struct adb_request req;
- time64_t now;
-
- if (cuda_request(&req, NULL, 2, CUDA_PACKET, CUDA_GET_TIME) < 0)
- return 0;
- while (!req.complete)
- cuda_poll();
- if (req.reply_len != 7)
- printk(KERN_ERR "cuda_get_time: got %d byte reply\n",
- req.reply_len);
- now = (u32)((req.reply[3] << 24) + (req.reply[4] << 16) +
- (req.reply[5] << 8) + req.reply[6]);
- /* it's either after year 2040, or the RTC has gone backwards */
- WARN_ON(now < RTC_OFFSET);
-
- return now - RTC_OFFSET;
-}
-
-#define cuda_get_rtc_time(tm) rtc_time64_to_tm(cuda_get_time(), (tm))
-
-static int cuda_set_rtc_time(struct rtc_time *tm)
-{
- u32 nowtime;
- struct adb_request req;
-
- nowtime = lower_32_bits(rtc_tm_to_time64(tm) + RTC_OFFSET);
- if (cuda_request(&req, NULL, 6, CUDA_PACKET, CUDA_SET_TIME,
- nowtime >> 24, nowtime >> 16, nowtime >> 8,
- nowtime) < 0)
- return -ENXIO;
- while (!req.complete)
- cuda_poll();
- if ((req.reply_len != 3) && (req.reply_len != 7))
- printk(KERN_ERR "cuda_set_rtc_time: got %d byte reply\n",
- req.reply_len);
- return 0;
-}
-
-#else
-#define cuda_get_time() 0
-#define cuda_get_rtc_time(tm)
-#define cuda_set_rtc_time(tm) 0
-#endif
-
-#ifdef CONFIG_ADB_PMU
-static time64_t pmu_get_time(void)
-{
- struct adb_request req;
- time64_t now;
-
- if (pmu_request(&req, NULL, 1, PMU_READ_RTC) < 0)
- return 0;
- pmu_wait_complete(&req);
- if (req.reply_len != 4)
- printk(KERN_ERR "pmu_get_time: got %d byte reply from PMU\n",
- req.reply_len);
- now = (u32)((req.reply[0] << 24) + (req.reply[1] << 16) +
- (req.reply[2] << 8) + req.reply[3]);
-
- /* it's either after year 2040, or the RTC has gone backwards */
- WARN_ON(now < RTC_OFFSET);
-
- return now - RTC_OFFSET;
-}
-
-#define pmu_get_rtc_time(tm) rtc_time64_to_tm(pmu_get_time(), (tm))
-
-static int pmu_set_rtc_time(struct rtc_time *tm)
-{
- u32 nowtime;
- struct adb_request req;
-
- nowtime = lower_32_bits(rtc_tm_to_time64(tm) + RTC_OFFSET);
- if (pmu_request(&req, NULL, 5, PMU_SET_RTC, nowtime >> 24,
- nowtime >> 16, nowtime >> 8, nowtime) < 0)
- return -ENXIO;
- pmu_wait_complete(&req);
- if (req.reply_len != 0)
- printk(KERN_ERR "pmu_set_rtc_time: %d byte reply from PMU\n",
- req.reply_len);
- return 0;
-}
-
-#else
-#define pmu_get_time() 0
-#define pmu_get_rtc_time(tm)
-#define pmu_set_rtc_time(tm) 0
-#endif
-
#ifdef CONFIG_PMAC_SMU
static time64_t smu_get_time(void)
{
@@ -191,11 +92,6 @@ static time64_t smu_get_time(void)
return 0;
return rtc_tm_to_time64(&tm);
}
-
-#else
-#define smu_get_time() 0
-#define smu_get_rtc_time(tm, spin)
-#define smu_set_rtc_time(tm, spin) 0
#endif
/* Can't be __init, it's called when suspending and resuming */
@@ -203,12 +99,18 @@ time64_t pmac_get_boot_time(void)
{
/* Get the time from the RTC, used only at boot time */
switch (sys_ctrler) {
+#ifdef CONFIG_ADB_CUDA
case SYS_CTRLER_CUDA:
return cuda_get_time();
+#endif
+#ifdef CONFIG_ADB_PMU
case SYS_CTRLER_PMU:
return pmu_get_time();
+#endif
+#ifdef CONFIG_PMAC_SMU
case SYS_CTRLER_SMU:
return smu_get_time();
+#endif
default:
return 0;
}
@@ -218,15 +120,21 @@ void pmac_get_rtc_time(struct rtc_time *tm)
{
/* Get the time from the RTC, used only at boot time */
switch (sys_ctrler) {
+#ifdef CONFIG_ADB_CUDA
case SYS_CTRLER_CUDA:
- cuda_get_rtc_time(tm);
+ rtc_time64_to_tm(cuda_get_time(), tm);
break;
+#endif
+#ifdef CONFIG_ADB_PMU
case SYS_CTRLER_PMU:
- pmu_get_rtc_time(tm);
+ rtc_time64_to_tm(pmu_get_time(), tm);
break;
+#endif
+#ifdef CONFIG_PMAC_SMU
case SYS_CTRLER_SMU:
smu_get_rtc_time(tm, 1);
break;
+#endif
default:
;
}
@@ -235,12 +143,18 @@ void pmac_get_rtc_time(struct rtc_time *tm)
int pmac_set_rtc_time(struct rtc_time *tm)
{
switch (sys_ctrler) {
+#ifdef CONFIG_ADB_CUDA
case SYS_CTRLER_CUDA:
return cuda_set_rtc_time(tm);
+#endif
+#ifdef CONFIG_ADB_PMU
case SYS_CTRLER_PMU:
return pmu_set_rtc_time(tm);
+#endif
+#ifdef CONFIG_PMAC_SMU
case SYS_CTRLER_SMU:
return smu_set_rtc_time(tm, 1);
+#endif
default:
return -ENODEV;
}
diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
index f8dc98d3dc01..028ac941c05c 100644
--- a/arch/powerpc/platforms/powernv/Kconfig
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -15,11 +15,6 @@ config PPC_POWERNV
select PPC_SCOM
select ARCH_RANDOM
select CPU_FREQ
- select CPU_FREQ_GOV_PERFORMANCE
- select CPU_FREQ_GOV_POWERSAVE
- select CPU_FREQ_GOV_USERSPACE
- select CPU_FREQ_GOV_ONDEMAND
- select CPU_FREQ_GOV_CONSERVATIVE
select PPC_DOORBELL
select MMU_NOTIFIER
select FORCE_SMP
diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
index 51dc398ae3f7..a29fdf8a2e56 100644
--- a/arch/powerpc/platforms/powernv/memtrace.c
+++ b/arch/powerpc/platforms/powernv/memtrace.c
@@ -90,17 +90,15 @@ static bool memtrace_offline_pages(u32 nid, u64 start_pfn, u64 nr_pages)
walk_memory_range(start_pfn, end_pfn, (void *)MEM_OFFLINE,
change_memblock_state);
- lock_device_hotplug();
- remove_memory(nid, start_pfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT);
- unlock_device_hotplug();
return true;
}
static u64 memtrace_alloc_node(u32 nid, u64 size)
{
- u64 start_pfn, end_pfn, nr_pages;
+ u64 start_pfn, end_pfn, nr_pages, pfn;
u64 base_pfn;
+ u64 bytes = memory_block_size_bytes();
if (!node_spanned_pages(nid))
return 0;
@@ -113,8 +111,21 @@ static u64 memtrace_alloc_node(u32 nid, u64 size)
end_pfn = round_down(end_pfn - nr_pages, nr_pages);
for (base_pfn = end_pfn; base_pfn > start_pfn; base_pfn -= nr_pages) {
- if (memtrace_offline_pages(nid, base_pfn, nr_pages) == true)
+ if (memtrace_offline_pages(nid, base_pfn, nr_pages) == true) {
+ /*
+ * Remove memory in memory block size chunks so that
+ * iomem resources are always split to the same size and
+ * we never try to remove memory that spans two iomem
+ * resources.
+ */
+ lock_device_hotplug();
+ end_pfn = base_pfn + nr_pages;
+ for (pfn = base_pfn; pfn < end_pfn; pfn += bytes>> PAGE_SHIFT) {
+ remove_memory(nid, pfn << PAGE_SHIFT, bytes);
+ }
+ unlock_device_hotplug();
return base_pfn << PAGE_SHIFT;
+ }
}
return 0;
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index 8006c54a91e3..6f60e0931922 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -17,7 +17,7 @@
#include <linux/pci.h>
#include <linux/memblock.h>
#include <linux/iommu.h>
-#include <linux/debugfs.h>
+#include <linux/sizes.h>
#include <asm/debugfs.h>
#include <asm/tlb.h>
@@ -42,14 +42,6 @@
static DEFINE_SPINLOCK(npu_context_lock);
/*
- * When an address shootdown range exceeds this threshold we invalidate the
- * entire TLB on the GPU for the given PID rather than each specific address in
- * the range.
- */
-static uint64_t atsd_threshold = 2 * 1024 * 1024;
-static struct dentry *atsd_threshold_dentry;
-
-/*
* Other types of TCE cache invalidation are not functional in the
* hardware.
*/
@@ -454,79 +446,73 @@ static void put_mmio_atsd_reg(struct npu *npu, int reg)
}
/* MMIO ATSD register offsets */
-#define XTS_ATSD_AVA 1
-#define XTS_ATSD_STAT 2
-
-static void mmio_launch_invalidate(struct mmio_atsd_reg *mmio_atsd_reg,
- unsigned long launch, unsigned long va)
-{
- struct npu *npu = mmio_atsd_reg->npu;
- int reg = mmio_atsd_reg->reg;
-
- __raw_writeq_be(va, npu->mmio_atsd_regs[reg] + XTS_ATSD_AVA);
- eieio();
- __raw_writeq_be(launch, npu->mmio_atsd_regs[reg]);
-}
+#define XTS_ATSD_LAUNCH 0
+#define XTS_ATSD_AVA 1
+#define XTS_ATSD_STAT 2
-static void mmio_invalidate_pid(struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS],
- unsigned long pid, bool flush)
+static unsigned long get_atsd_launch_val(unsigned long pid, unsigned long psize)
{
- int i;
- unsigned long launch;
-
- for (i = 0; i <= max_npu2_index; i++) {
- if (mmio_atsd_reg[i].reg < 0)
- continue;
+ unsigned long launch = 0;
- /* IS set to invalidate matching PID */
- launch = PPC_BIT(12);
-
- /* PRS set to process-scoped */
- launch |= PPC_BIT(13);
+ if (psize == MMU_PAGE_COUNT) {
+ /* IS set to invalidate entire matching PID */
+ launch |= PPC_BIT(12);
+ } else {
+ /* AP set to invalidate region of psize */
+ launch |= (u64)mmu_get_ap(psize) << PPC_BITLSHIFT(17);
+ }
- /* AP */
- launch |= (u64)
- mmu_get_ap(mmu_virtual_psize) << PPC_BITLSHIFT(17);
+ /* PRS set to process-scoped */
+ launch |= PPC_BIT(13);
- /* PID */
- launch |= pid << PPC_BITLSHIFT(38);
+ /* PID */
+ launch |= pid << PPC_BITLSHIFT(38);
- /* No flush */
- launch |= !flush << PPC_BITLSHIFT(39);
+ /* Leave "No flush" (bit 39) 0 so every ATSD performs a flush */
- /* Invalidating the entire process doesn't use a va */
- mmio_launch_invalidate(&mmio_atsd_reg[i], launch, 0);
- }
+ return launch;
}
-static void mmio_invalidate_va(struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS],
- unsigned long va, unsigned long pid, bool flush)
+static void mmio_atsd_regs_write(struct mmio_atsd_reg
+ mmio_atsd_reg[NV_MAX_NPUS], unsigned long offset,
+ unsigned long val)
{
- int i;
- unsigned long launch;
+ struct npu *npu;
+ int i, reg;
for (i = 0; i <= max_npu2_index; i++) {
- if (mmio_atsd_reg[i].reg < 0)
+ reg = mmio_atsd_reg[i].reg;
+ if (reg < 0)
continue;
- /* IS set to invalidate target VA */
- launch = 0;
+ npu = mmio_atsd_reg[i].npu;
+ __raw_writeq_be(val, npu->mmio_atsd_regs[reg] + offset);
+ }
+}
+
+static void mmio_invalidate_pid(struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS],
+ unsigned long pid)
+{
+ unsigned long launch = get_atsd_launch_val(pid, MMU_PAGE_COUNT);
- /* PRS set to process scoped */
- launch |= PPC_BIT(13);
+ /* Invalidating the entire process doesn't use a va */
+ mmio_atsd_regs_write(mmio_atsd_reg, XTS_ATSD_LAUNCH, launch);
+}
- /* AP */
- launch |= (u64)
- mmu_get_ap(mmu_virtual_psize) << PPC_BITLSHIFT(17);
+static void mmio_invalidate_range(struct mmio_atsd_reg
+ mmio_atsd_reg[NV_MAX_NPUS], unsigned long pid,
+ unsigned long start, unsigned long psize)
+{
+ unsigned long launch = get_atsd_launch_val(pid, psize);
- /* PID */
- launch |= pid << PPC_BITLSHIFT(38);
+ /* Write all VAs first */
+ mmio_atsd_regs_write(mmio_atsd_reg, XTS_ATSD_AVA, start);
- /* No flush */
- launch |= !flush << PPC_BITLSHIFT(39);
+ /* Issue one barrier for all address writes */
+ eieio();
- mmio_launch_invalidate(&mmio_atsd_reg[i], launch, va);
- }
+ /* Launch */
+ mmio_atsd_regs_write(mmio_atsd_reg, XTS_ATSD_LAUNCH, launch);
}
#define mn_to_npu_context(x) container_of(x, struct npu_context, mn)
@@ -612,14 +598,36 @@ static void release_atsd_reg(struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS])
}
/*
- * Invalidate either a single address or an entire PID depending on
- * the value of va.
+ * Invalidate a virtual address range
*/
-static void mmio_invalidate(struct npu_context *npu_context, int va,
- unsigned long address, bool flush)
+static void mmio_invalidate(struct npu_context *npu_context,
+ unsigned long start, unsigned long size)
{
struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS];
unsigned long pid = npu_context->mm->context.id;
+ unsigned long atsd_start = 0;
+ unsigned long end = start + size - 1;
+ int atsd_psize = MMU_PAGE_COUNT;
+
+ /*
+ * Convert the input range into one of the supported sizes. If the range
+ * doesn't fit, use the next larger supported size. Invalidation latency
+ * is high, so over-invalidation is preferred to issuing multiple
+ * invalidates.
+ *
+ * A 4K page size isn't supported by NPU/GPU ATS, so that case is
+ * ignored.
+ */
+ if (size == SZ_64K) {
+ atsd_start = start;
+ atsd_psize = MMU_PAGE_64K;
+ } else if (ALIGN_DOWN(start, SZ_2M) == ALIGN_DOWN(end, SZ_2M)) {
+ atsd_start = ALIGN_DOWN(start, SZ_2M);
+ atsd_psize = MMU_PAGE_2M;
+ } else if (ALIGN_DOWN(start, SZ_1G) == ALIGN_DOWN(end, SZ_1G)) {
+ atsd_start = ALIGN_DOWN(start, SZ_1G);
+ atsd_psize = MMU_PAGE_1G;
+ }
if (npu_context->nmmu_flush)
/*
@@ -634,23 +642,25 @@ static void mmio_invalidate(struct npu_context *npu_context, int va,
* an invalidate.
*/
acquire_atsd_reg(npu_context, mmio_atsd_reg);
- if (va)
- mmio_invalidate_va(mmio_atsd_reg, address, pid, flush);
+
+ if (atsd_psize == MMU_PAGE_COUNT)
+ mmio_invalidate_pid(mmio_atsd_reg, pid);
else
- mmio_invalidate_pid(mmio_atsd_reg, pid, flush);
+ mmio_invalidate_range(mmio_atsd_reg, pid, atsd_start,
+ atsd_psize);
mmio_invalidate_wait(mmio_atsd_reg);
- if (flush) {
- /*
- * 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.
- */
- mmio_invalidate_pid(mmio_atsd_reg, 0, true);
- mmio_invalidate_wait(mmio_atsd_reg);
- mmio_invalidate_pid(mmio_atsd_reg, 0, true);
- mmio_invalidate_wait(mmio_atsd_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.
+ */
+ mmio_invalidate_pid(mmio_atsd_reg, 0);
+ mmio_invalidate_wait(mmio_atsd_reg);
+ mmio_invalidate_pid(mmio_atsd_reg, 0);
+ mmio_invalidate_wait(mmio_atsd_reg);
+
release_atsd_reg(mmio_atsd_reg);
}
@@ -667,7 +677,7 @@ 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, true);
+ mmio_invalidate(npu_context, 0, ~0UL);
}
static void pnv_npu2_mn_change_pte(struct mmu_notifier *mn,
@@ -676,8 +686,7 @@ static void pnv_npu2_mn_change_pte(struct mmu_notifier *mn,
pte_t pte)
{
struct npu_context *npu_context = mn_to_npu_context(mn);
-
- mmio_invalidate(npu_context, 1, address, true);
+ mmio_invalidate(npu_context, address, PAGE_SIZE);
}
static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
@@ -685,21 +694,7 @@ static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
unsigned long start, unsigned long end)
{
struct npu_context *npu_context = mn_to_npu_context(mn);
- unsigned long address;
-
- if (end - start > atsd_threshold) {
- /*
- * Just invalidate the entire PID if the address range is too
- * large.
- */
- mmio_invalidate(npu_context, 0, 0, true);
- } else {
- 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);
- }
+ mmio_invalidate(npu_context, start, end - start);
}
static const struct mmu_notifier_ops nv_nmmu_notifier_ops = {
@@ -962,11 +957,6 @@ int pnv_npu2_init(struct pnv_phb *phb)
static int npu_index;
uint64_t rc = 0;
- if (!atsd_threshold_dentry) {
- atsd_threshold_dentry = debugfs_create_x64("atsd_threshold",
- 0600, powerpc_debugfs_root, &atsd_threshold);
- }
-
phb->npu.nmmu_flush =
of_property_read_bool(phb->hose->dn, "ibm,nmmu-flush");
for_each_child_of_node(phb->hose->dn, dn) {
diff --git a/arch/powerpc/platforms/powernv/opal-powercap.c b/arch/powerpc/platforms/powernv/opal-powercap.c
index badb29bde93f..d90ee4fc2c6a 100644
--- a/arch/powerpc/platforms/powernv/opal-powercap.c
+++ b/arch/powerpc/platforms/powernv/opal-powercap.c
@@ -199,7 +199,7 @@ void __init opal_powercap_init(void)
}
j = 0;
- pcaps[i].pg.name = node->name;
+ pcaps[i].pg.name = kasprintf(GFP_KERNEL, "%pOFn", node);
if (has_min) {
powercap_add_attr(min, "powercap-min",
&pcaps[i].pattrs[j]);
@@ -237,6 +237,7 @@ out_pcaps_pattrs:
while (--i >= 0) {
kfree(pcaps[i].pattrs);
kfree(pcaps[i].pg.attrs);
+ kfree(pcaps[i].pg.name);
}
kobject_put(powercap_kobj);
out_pcaps:
diff --git a/arch/powerpc/platforms/powernv/opal-sensor-groups.c b/arch/powerpc/platforms/powernv/opal-sensor-groups.c
index f7d04b6a2d7a..179609220e6f 100644
--- a/arch/powerpc/platforms/powernv/opal-sensor-groups.c
+++ b/arch/powerpc/platforms/powernv/opal-sensor-groups.c
@@ -214,9 +214,9 @@ void __init opal_sensor_groups_init(void)
}
if (!of_property_read_u32(node, "ibm,chip-id", &chipid))
- sprintf(sgs[i].name, "%s%d", node->name, chipid);
+ sprintf(sgs[i].name, "%pOFn%d", node, chipid);
else
- sprintf(sgs[i].name, "%s", node->name);
+ sprintf(sgs[i].name, "%pOFn", node);
sgs[i].sg.name = sgs[i].name;
if (add_attr_group(ops, len, &sgs[i], sgid)) {
diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c
index 9aa87df114fd..916a4b7b1bb5 100644
--- a/arch/powerpc/platforms/powernv/opal-sysparam.c
+++ b/arch/powerpc/platforms/powernv/opal-sysparam.c
@@ -194,7 +194,7 @@ void __init opal_sys_param_init(void)
count = of_property_count_strings(sysparam, "param-name");
if (count < 0) {
pr_err("SYSPARAM: No string found of property param-name in "
- "the node %s\n", sysparam->name);
+ "the node %pOFn\n", sysparam);
goto out_param_buf;
}
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 38fe4087484a..a4641515956f 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -535,7 +535,7 @@ static int opal_recover_mce(struct pt_regs *regs,
return recovered;
}
-void pnv_platform_error_reboot(struct pt_regs *regs, const char *msg)
+void __noreturn pnv_platform_error_reboot(struct pt_regs *regs, const char *msg)
{
panic_flush_kmsg_start();
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index adddde023622..14befee4b3f1 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -219,17 +219,41 @@ static void pnv_prepare_going_down(void)
static void __noreturn pnv_restart(char *cmd)
{
- long rc = OPAL_BUSY;
+ long rc;
pnv_prepare_going_down();
- while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
- rc = opal_cec_reboot();
- if (rc == OPAL_BUSY_EVENT)
- opal_poll_events(NULL);
+ do {
+ if (!cmd)
+ rc = opal_cec_reboot();
+ else if (strcmp(cmd, "full") == 0)
+ rc = opal_cec_reboot2(OPAL_REBOOT_FULL_IPL, NULL);
else
+ rc = OPAL_UNSUPPORTED;
+
+ if (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
+ /* Opal is busy wait for some time and retry */
+ opal_poll_events(NULL);
mdelay(10);
- }
+
+ } else if (cmd && rc) {
+ /* Unknown error while issuing reboot */
+ if (rc == OPAL_UNSUPPORTED)
+ pr_err("Unsupported '%s' reboot.\n", cmd);
+ else
+ pr_err("Unable to issue '%s' reboot. Err=%ld\n",
+ cmd, rc);
+ pr_info("Forcing a cec-reboot\n");
+ cmd = NULL;
+ rc = OPAL_BUSY;
+
+ } else if (rc != OPAL_SUCCESS) {
+ /* Unknown error while issuing cec-reboot */
+ pr_err("Unable to reboot. Err=%ld\n", rc);
+ }
+
+ } while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT);
+
for (;;)
opal_poll_events(NULL);
}
@@ -437,6 +461,16 @@ static unsigned long pnv_get_proc_freq(unsigned int cpu)
return ret_freq;
}
+static long pnv_machine_check_early(struct pt_regs *regs)
+{
+ long handled = 0;
+
+ if (cur_cpu_spec && cur_cpu_spec->machine_check_early)
+ handled = cur_cpu_spec->machine_check_early(regs);
+
+ return handled;
+}
+
define_machine(powernv) {
.name = "PowerNV",
.probe = pnv_probe,
@@ -448,6 +482,7 @@ define_machine(powernv) {
.machine_shutdown = pnv_shutdown,
.power_save = NULL,
.calibrate_decr = generic_calibrate_decr,
+ .machine_check_early = pnv_machine_check_early,
#ifdef CONFIG_KEXEC_CORE
.kexec_cpu_down = pnv_kexec_cpu_down,
#endif
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index a0b20c03f078..052c4f2ba0a0 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -32,8 +32,6 @@ static struct workqueue_struct *pseries_hp_wq;
struct pseries_hp_work {
struct work_struct work;
struct pseries_hp_errorlog *errlog;
- struct completion *hp_completion;
- int *rc;
};
struct cc_workarea {
@@ -329,7 +327,7 @@ int dlpar_release_drc(u32 drc_index)
return 0;
}
-static int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog)
+int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog)
{
int rc;
@@ -371,20 +369,13 @@ static void pseries_hp_work_fn(struct work_struct *work)
struct pseries_hp_work *hp_work =
container_of(work, struct pseries_hp_work, work);
- if (hp_work->rc)
- *(hp_work->rc) = handle_dlpar_errorlog(hp_work->errlog);
- else
- handle_dlpar_errorlog(hp_work->errlog);
-
- if (hp_work->hp_completion)
- complete(hp_work->hp_completion);
+ handle_dlpar_errorlog(hp_work->errlog);
kfree(hp_work->errlog);
kfree((void *)work);
}
-void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog,
- struct completion *hotplug_done, int *rc)
+void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog)
{
struct pseries_hp_work *work;
struct pseries_hp_errorlog *hp_errlog_copy;
@@ -397,13 +388,9 @@ void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog,
if (work) {
INIT_WORK((struct work_struct *)work, pseries_hp_work_fn);
work->errlog = hp_errlog_copy;
- work->hp_completion = hotplug_done;
- work->rc = rc;
queue_work(pseries_hp_wq, (struct work_struct *)work);
} else {
- *rc = -ENOMEM;
kfree(hp_errlog_copy);
- complete(hotplug_done);
}
}
@@ -521,18 +508,15 @@ static int dlpar_parse_id_type(char **cmd, struct pseries_hp_errorlog *hp_elog)
static ssize_t dlpar_store(struct class *class, struct class_attribute *attr,
const char *buf, size_t count)
{
- struct pseries_hp_errorlog *hp_elog;
- struct completion hotplug_done;
+ struct pseries_hp_errorlog hp_elog;
char *argbuf;
char *args;
int rc;
args = argbuf = kstrdup(buf, GFP_KERNEL);
- hp_elog = kzalloc(sizeof(*hp_elog), GFP_KERNEL);
- if (!hp_elog || !argbuf) {
+ if (!argbuf) {
pr_info("Could not allocate resources for DLPAR operation\n");
kfree(argbuf);
- kfree(hp_elog);
return -ENOMEM;
}
@@ -540,25 +524,22 @@ static ssize_t dlpar_store(struct class *class, struct class_attribute *attr,
* Parse out the request from the user, this will be in the form:
* <resource> <action> <id_type> <id>
*/
- rc = dlpar_parse_resource(&args, hp_elog);
+ rc = dlpar_parse_resource(&args, &hp_elog);
if (rc)
goto dlpar_store_out;
- rc = dlpar_parse_action(&args, hp_elog);
+ rc = dlpar_parse_action(&args, &hp_elog);
if (rc)
goto dlpar_store_out;
- rc = dlpar_parse_id_type(&args, hp_elog);
+ rc = dlpar_parse_id_type(&args, &hp_elog);
if (rc)
goto dlpar_store_out;
- init_completion(&hotplug_done);
- queue_hotplug_event(hp_elog, &hotplug_done, &rc);
- wait_for_completion(&hotplug_done);
+ rc = handle_dlpar_errorlog(&hp_elog);
dlpar_store_out:
kfree(argbuf);
- kfree(hp_elog);
if (rc)
pr_err("Could not handle DLPAR request \"%s\"\n", buf);
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index 18014cdeb590..ef6595153642 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -149,7 +149,7 @@ static int dtl_start(struct dtl *dtl)
/* Register our dtl buffer with the hypervisor. The HV expects the
* buffer size to be passed in the second word of the buffer */
- ((u32 *)dtl->buf)[1] = DISPATCH_LOG_BYTES;
+ ((u32 *)dtl->buf)[1] = cpu_to_be32(DISPATCH_LOG_BYTES);
hwcpu = get_hard_smp_processor_id(dtl->cpu);
addr = __pa(dtl->buf);
@@ -184,7 +184,7 @@ static void dtl_stop(struct dtl *dtl)
static u64 dtl_current_index(struct dtl *dtl)
{
- return lppaca_of(dtl->cpu).dtl_idx;
+ return be64_to_cpu(lppaca_of(dtl->cpu).dtl_idx);
}
#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
diff --git a/arch/powerpc/platforms/pseries/event_sources.c b/arch/powerpc/platforms/pseries/event_sources.c
index 6eeb0d4bab61..446ef104fb3a 100644
--- a/arch/powerpc/platforms/pseries/event_sources.c
+++ b/arch/powerpc/platforms/pseries/event_sources.c
@@ -16,7 +16,8 @@
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
-#include <asm/prom.h>
+#include <linux/interrupt.h>
+#include <linux/of_irq.h>
#include "pseries.h"
@@ -24,34 +25,19 @@ void request_event_sources_irqs(struct device_node *np,
irq_handler_t handler,
const char *name)
{
- int i, index, count = 0;
- struct of_phandle_args oirq;
- unsigned int virqs[16];
+ int i, virq, rc;
- /* First try to do a proper OF tree parsing */
- for (index = 0; of_irq_parse_one(np, index, &oirq) == 0;
- index++) {
- if (count > 15)
- break;
- virqs[count] = irq_create_of_mapping(&oirq);
- if (!virqs[count]) {
- pr_err("event-sources: Unable to allocate "
- "interrupt number for %pOF\n",
- np);
- WARN_ON(1);
- } else {
- count++;
- }
- }
+ for (i = 0; i < 16; i++) {
+ virq = of_irq_get(np, i);
+ if (virq < 0)
+ return;
+ if (WARN(!virq, "event-sources: Unable to allocate "
+ "interrupt number for %pOF\n", np))
+ continue;
- /* Now request them */
- for (i = 0; i < count; i++) {
- if (request_irq(virqs[i], handler, 0, name, NULL)) {
- pr_err("event-sources: Unable to request interrupt "
- "%d for %pOF\n", virqs[i], np);
- WARN_ON(1);
+ rc = request_irq(virq, handler, 0, name, NULL);
+ if (WARN(rc, "event-sources: Unable to request interrupt %d for %pOF\n",
+ virq, np))
return;
- }
}
}
-
diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c
index a3bbeb43689e..1624501386f4 100644
--- a/arch/powerpc/platforms/pseries/firmware.c
+++ b/arch/powerpc/platforms/pseries/firmware.c
@@ -65,6 +65,7 @@ hypertas_fw_features_table[] = {
{FW_FEATURE_SET_MODE, "hcall-set-mode"},
{FW_FEATURE_BEST_ENERGY, "hcall-best-energy-1*"},
{FW_FEATURE_HPT_RESIZE, "hcall-hpt-resize"},
+ {FW_FEATURE_BLOCK_REMOVE, "hcall-block-remove"},
};
/* Build up the firmware features bitmask using the contents of
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 6ef77caf7bcf..2f8e62163602 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -287,7 +287,7 @@ static int pseries_add_processor(struct device_node *np)
if (cpumask_empty(tmp)) {
printk(KERN_ERR "Unable to find space in cpu_present_mask for"
- " processor %s with %d thread(s)\n", np->name,
+ " processor %pOFn with %d thread(s)\n", np,
nthreads);
goto out_unlock;
}
@@ -481,8 +481,8 @@ static ssize_t dlpar_cpu_add(u32 drc_index)
if (rc) {
saved_rc = rc;
- pr_warn("Failed to attach node %s, rc: %d, drc index: %x\n",
- dn->name, rc, drc_index);
+ pr_warn("Failed to attach node %pOFn, rc: %d, drc index: %x\n",
+ dn, rc, drc_index);
rc = dlpar_release_drc(drc_index);
if (!rc)
@@ -494,8 +494,8 @@ static ssize_t dlpar_cpu_add(u32 drc_index)
rc = dlpar_online_cpu(dn);
if (rc) {
saved_rc = rc;
- pr_warn("Failed to online cpu %s, rc: %d, drc index: %x\n",
- dn->name, rc, drc_index);
+ pr_warn("Failed to online cpu %pOFn, rc: %d, drc index: %x\n",
+ dn, rc, drc_index);
rc = dlpar_detach_node(dn);
if (!rc)
@@ -504,7 +504,7 @@ static ssize_t dlpar_cpu_add(u32 drc_index)
return saved_rc;
}
- pr_debug("Successfully added CPU %s, drc index: %x\n", dn->name,
+ pr_debug("Successfully added CPU %pOFn, drc index: %x\n", dn,
drc_index);
return rc;
}
@@ -570,19 +570,19 @@ static ssize_t dlpar_cpu_remove(struct device_node *dn, u32 drc_index)
{
int rc;
- pr_debug("Attempting to remove CPU %s, drc index: %x\n",
- dn->name, drc_index);
+ pr_debug("Attempting to remove CPU %pOFn, drc index: %x\n",
+ dn, drc_index);
rc = dlpar_offline_cpu(dn);
if (rc) {
- pr_warn("Failed to offline CPU %s, rc: %d\n", dn->name, rc);
+ pr_warn("Failed to offline CPU %pOFn, rc: %d\n", dn, rc);
return -EINVAL;
}
rc = dlpar_release_drc(drc_index);
if (rc) {
- pr_warn("Failed to release drc (%x) for CPU %s, rc: %d\n",
- drc_index, dn->name, rc);
+ pr_warn("Failed to release drc (%x) for CPU %pOFn, rc: %d\n",
+ drc_index, dn, rc);
dlpar_online_cpu(dn);
return rc;
}
@@ -591,7 +591,7 @@ static ssize_t dlpar_cpu_remove(struct device_node *dn, u32 drc_index)
if (rc) {
int saved_rc = rc;
- pr_warn("Failed to detach CPU %s, rc: %d", dn->name, rc);
+ pr_warn("Failed to detach CPU %pOFn, rc: %d", dn, rc);
rc = dlpar_acquire_drc(drc_index);
if (!rc)
@@ -662,8 +662,8 @@ static int find_dlpar_cpus_to_remove(u32 *cpu_drcs, int cpus_to_remove)
rc = of_property_read_u32(dn, "ibm,my-drc-index",
&cpu_drcs[cpus_found - 1]);
if (rc) {
- pr_warn("Error occurred getting drc-index for %s\n",
- dn->name);
+ pr_warn("Error occurred getting drc-index for %pOFn\n",
+ dn);
of_node_put(dn);
return -1;
}
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index c1578f54c626..9a15d39995e5 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -163,7 +163,7 @@ static u32 find_aa_index(struct device_node *dr_node,
return aa_index;
}
-static u32 lookup_lmb_associativity_index(struct drmem_lmb *lmb)
+static int update_lmb_associativity_index(struct drmem_lmb *lmb)
{
struct device_node *parent, *lmb_node, *dr_node;
struct property *ala_prop;
@@ -203,43 +203,14 @@ static u32 lookup_lmb_associativity_index(struct drmem_lmb *lmb)
aa_index = find_aa_index(dr_node, ala_prop, lmb_assoc);
dlpar_free_cc_nodes(lmb_node);
- return aa_index;
-}
-
-static int dlpar_add_device_tree_lmb(struct drmem_lmb *lmb)
-{
- int rc, aa_index;
-
- lmb->flags |= DRCONF_MEM_ASSIGNED;
- aa_index = lookup_lmb_associativity_index(lmb);
if (aa_index < 0) {
- pr_err("Couldn't find associativity index for drc index %x\n",
- lmb->drc_index);
- return aa_index;
+ pr_err("Could not find LMB associativity\n");
+ return -1;
}
lmb->aa_index = aa_index;
-
- rtas_hp_event = true;
- rc = drmem_update_dt();
- rtas_hp_event = false;
-
- return rc;
-}
-
-static int dlpar_remove_device_tree_lmb(struct drmem_lmb *lmb)
-{
- int rc;
-
- lmb->flags &= ~DRCONF_MEM_ASSIGNED;
- lmb->aa_index = 0xffffffff;
-
- rtas_hp_event = true;
- rc = drmem_update_dt();
- rtas_hp_event = false;
-
- return rc;
+ return 0;
}
static struct memory_block *lmb_to_memblock(struct drmem_lmb *lmb)
@@ -428,7 +399,9 @@ static int dlpar_remove_lmb(struct drmem_lmb *lmb)
/* Update memory regions for memory remove */
memblock_remove(lmb->base_addr, block_sz);
- dlpar_remove_device_tree_lmb(lmb);
+ invalidate_lmb_associativity_index(lmb);
+ lmb->flags &= ~DRCONF_MEM_ASSIGNED;
+
return 0;
}
@@ -688,10 +661,8 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb)
if (lmb->flags & DRCONF_MEM_ASSIGNED)
return -EINVAL;
- rc = dlpar_add_device_tree_lmb(lmb);
+ rc = update_lmb_associativity_index(lmb);
if (rc) {
- pr_err("Couldn't update device tree for drc index %x\n",
- lmb->drc_index);
dlpar_release_drc(lmb->drc_index);
return rc;
}
@@ -704,14 +675,14 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb)
/* Add the memory */
rc = add_memory(nid, lmb->base_addr, block_sz);
if (rc) {
- dlpar_remove_device_tree_lmb(lmb);
+ invalidate_lmb_associativity_index(lmb);
return rc;
}
rc = dlpar_online_lmb(lmb);
if (rc) {
remove_memory(nid, lmb->base_addr, block_sz);
- dlpar_remove_device_tree_lmb(lmb);
+ invalidate_lmb_associativity_index(lmb);
} else {
lmb->flags |= DRCONF_MEM_ASSIGNED;
}
@@ -958,6 +929,12 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog)
break;
}
+ if (!rc) {
+ rtas_hp_event = true;
+ rc = drmem_update_dt();
+ rtas_hp_event = false;
+ }
+
unlock_device_hotplug();
return rc;
}
diff --git a/arch/powerpc/platforms/pseries/ibmebus.c b/arch/powerpc/platforms/pseries/ibmebus.c
index c7c1140c13b6..5b4a56131904 100644
--- a/arch/powerpc/platforms/pseries/ibmebus.c
+++ b/arch/powerpc/platforms/pseries/ibmebus.c
@@ -404,7 +404,7 @@ static ssize_t name_show(struct device *dev,
struct platform_device *ofdev;
ofdev = to_platform_device(dev);
- return sprintf(buf, "%s\n", ofdev->dev.of_node->name);
+ return sprintf(buf, "%pOFn\n", ofdev->dev.of_node);
}
static DEVICE_ATTR_RO(name);
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index d3992ced0782..0b5081085a44 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -417,6 +417,79 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
BUG_ON(lpar_rc != H_SUCCESS);
}
+
+/*
+ * As defined in the PAPR's section 14.5.4.1.8
+ * The control mask doesn't include the returned reference and change bit from
+ * the processed PTE.
+ */
+#define HBLKR_AVPN 0x0100000000000000UL
+#define HBLKR_CTRL_MASK 0xf800000000000000UL
+#define HBLKR_CTRL_SUCCESS 0x8000000000000000UL
+#define HBLKR_CTRL_ERRNOTFOUND 0x8800000000000000UL
+#define HBLKR_CTRL_ERRBUSY 0xa000000000000000UL
+
+/**
+ * H_BLOCK_REMOVE caller.
+ * @idx should point to the latest @param entry set with a PTEX.
+ * If PTE cannot be processed because another CPUs has already locked that
+ * group, those entries are put back in @param starting at index 1.
+ * If entries has to be retried and @retry_busy is set to true, these entries
+ * are retried until success. If @retry_busy is set to false, the returned
+ * is the number of entries yet to process.
+ */
+static unsigned long call_block_remove(unsigned long idx, unsigned long *param,
+ bool retry_busy)
+{
+ unsigned long i, rc, new_idx;
+ unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
+
+ if (idx < 2) {
+ pr_warn("Unexpected empty call to H_BLOCK_REMOVE");
+ return 0;
+ }
+again:
+ new_idx = 0;
+ if (idx > PLPAR_HCALL9_BUFSIZE) {
+ pr_err("Too many PTEs (%lu) for H_BLOCK_REMOVE", idx);
+ idx = PLPAR_HCALL9_BUFSIZE;
+ } else if (idx < PLPAR_HCALL9_BUFSIZE)
+ param[idx] = HBR_END;
+
+ rc = plpar_hcall9(H_BLOCK_REMOVE, retbuf,
+ param[0], /* AVA */
+ param[1], param[2], param[3], param[4], /* TS0-7 */
+ param[5], param[6], param[7], param[8]);
+ if (rc == H_SUCCESS)
+ return 0;
+
+ BUG_ON(rc != H_PARTIAL);
+
+ /* Check that the unprocessed entries were 'not found' or 'busy' */
+ for (i = 0; i < idx-1; i++) {
+ unsigned long ctrl = retbuf[i] & HBLKR_CTRL_MASK;
+
+ if (ctrl == HBLKR_CTRL_ERRBUSY) {
+ param[++new_idx] = param[i+1];
+ continue;
+ }
+
+ BUG_ON(ctrl != HBLKR_CTRL_SUCCESS
+ && ctrl != HBLKR_CTRL_ERRNOTFOUND);
+ }
+
+ /*
+ * If there were entries found busy, retry these entries if requested,
+ * of if all the entries have to be retried.
+ */
+ if (new_idx && (retry_busy || new_idx == (PLPAR_HCALL9_BUFSIZE-1))) {
+ idx = new_idx + 1;
+ goto again;
+ }
+
+ return new_idx;
+}
+
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
* Limit iterations holding pSeries_lpar_tlbie_lock to 3. We also need
@@ -424,17 +497,57 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
*/
#define PPC64_HUGE_HPTE_BATCH 12
-static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot,
- unsigned long *vpn, int count,
- int psize, int ssize)
+static void hugepage_block_invalidate(unsigned long *slot, unsigned long *vpn,
+ int count, int psize, int ssize)
{
unsigned long param[PLPAR_HCALL9_BUFSIZE];
- int i = 0, pix = 0, rc;
- unsigned long flags = 0;
- int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
+ unsigned long shift, current_vpgb, vpgb;
+ int i, pix = 0;
- if (lock_tlbie)
- spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags);
+ shift = mmu_psize_defs[psize].shift;
+
+ for (i = 0; i < count; i++) {
+ /*
+ * Shifting 3 bits more on the right to get a
+ * 8 pages aligned virtual addresse.
+ */
+ vpgb = (vpn[i] >> (shift - VPN_SHIFT + 3));
+ if (!pix || vpgb != current_vpgb) {
+ /*
+ * Need to start a new 8 pages block, flush
+ * the current one if needed.
+ */
+ if (pix)
+ (void)call_block_remove(pix, param, true);
+ current_vpgb = vpgb;
+ param[0] = hpte_encode_avpn(vpn[i], psize, ssize);
+ pix = 1;
+ }
+
+ param[pix++] = HBR_REQUEST | HBLKR_AVPN | slot[i];
+ if (pix == PLPAR_HCALL9_BUFSIZE) {
+ pix = call_block_remove(pix, param, false);
+ /*
+ * pix = 0 means that all the entries were
+ * removed, we can start a new block.
+ * Otherwise, this means that there are entries
+ * to retry, and pix points to latest one, so
+ * we should increment it and try to continue
+ * the same block.
+ */
+ if (pix)
+ pix++;
+ }
+ }
+ if (pix)
+ (void)call_block_remove(pix, param, true);
+}
+
+static void hugepage_bulk_invalidate(unsigned long *slot, unsigned long *vpn,
+ int count, int psize, int ssize)
+{
+ unsigned long param[PLPAR_HCALL9_BUFSIZE];
+ int i = 0, pix = 0, rc;
for (i = 0; i < count; i++) {
@@ -462,6 +575,23 @@ static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot,
param[6], param[7]);
BUG_ON(rc != H_SUCCESS);
}
+}
+
+static inline void __pSeries_lpar_hugepage_invalidate(unsigned long *slot,
+ unsigned long *vpn,
+ int count, int psize,
+ int ssize)
+{
+ unsigned long flags = 0;
+ int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
+
+ if (lock_tlbie)
+ spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags);
+
+ if (firmware_has_feature(FW_FEATURE_BLOCK_REMOVE))
+ hugepage_block_invalidate(slot, vpn, count, psize, ssize);
+ else
+ hugepage_bulk_invalidate(slot, vpn, count, psize, ssize);
if (lock_tlbie)
spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags);
@@ -546,6 +676,86 @@ static int pSeries_lpar_hpte_removebolted(unsigned long ea,
return 0;
}
+
+static inline unsigned long compute_slot(real_pte_t pte,
+ unsigned long vpn,
+ unsigned long index,
+ unsigned long shift,
+ int ssize)
+{
+ unsigned long slot, hash, hidx;
+
+ hash = hpt_hash(vpn, shift, ssize);
+ hidx = __rpte_to_hidx(pte, index);
+ if (hidx & _PTEIDX_SECONDARY)
+ hash = ~hash;
+ slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+ slot += hidx & _PTEIDX_GROUP_IX;
+ return slot;
+}
+
+/**
+ * The hcall H_BLOCK_REMOVE implies that the virtual pages to processed are
+ * "all within the same naturally aligned 8 page virtual address block".
+ */
+static void do_block_remove(unsigned long number, struct ppc64_tlb_batch *batch,
+ unsigned long *param)
+{
+ unsigned long vpn;
+ unsigned long i, pix = 0;
+ unsigned long index, shift, slot, current_vpgb, vpgb;
+ real_pte_t pte;
+ int psize, ssize;
+
+ psize = batch->psize;
+ ssize = batch->ssize;
+
+ for (i = 0; i < number; i++) {
+ vpn = batch->vpn[i];
+ pte = batch->pte[i];
+ pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) {
+ /*
+ * Shifting 3 bits more on the right to get a
+ * 8 pages aligned virtual addresse.
+ */
+ vpgb = (vpn >> (shift - VPN_SHIFT + 3));
+ if (!pix || vpgb != current_vpgb) {
+ /*
+ * Need to start a new 8 pages block, flush
+ * the current one if needed.
+ */
+ if (pix)
+ (void)call_block_remove(pix, param,
+ true);
+ current_vpgb = vpgb;
+ param[0] = hpte_encode_avpn(vpn, psize,
+ ssize);
+ pix = 1;
+ }
+
+ slot = compute_slot(pte, vpn, index, shift, ssize);
+ param[pix++] = HBR_REQUEST | HBLKR_AVPN | slot;
+
+ if (pix == PLPAR_HCALL9_BUFSIZE) {
+ pix = call_block_remove(pix, param, false);
+ /*
+ * pix = 0 means that all the entries were
+ * removed, we can start a new block.
+ * Otherwise, this means that there are entries
+ * to retry, and pix points to latest one, so
+ * we should increment it and try to continue
+ * the same block.
+ */
+ if (pix)
+ pix++;
+ }
+ } pte_iterate_hashed_end();
+ }
+
+ if (pix)
+ (void)call_block_remove(pix, param, true);
+}
+
/*
* Take a spinlock around flushes to avoid bouncing the hypervisor tlbie
* lock.
@@ -558,13 +768,18 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch);
int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
unsigned long param[PLPAR_HCALL9_BUFSIZE];
- unsigned long hash, index, shift, hidx, slot;
+ unsigned long index, shift, slot;
real_pte_t pte;
int psize, ssize;
if (lock_tlbie)
spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags);
+ if (firmware_has_feature(FW_FEATURE_BLOCK_REMOVE)) {
+ do_block_remove(number, batch, param);
+ goto out;
+ }
+
psize = batch->psize;
ssize = batch->ssize;
pix = 0;
@@ -572,12 +787,7 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
vpn = batch->vpn[i];
pte = batch->pte[i];
pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) {
- hash = hpt_hash(vpn, shift, ssize);
- hidx = __rpte_to_hidx(pte, index);
- if (hidx & _PTEIDX_SECONDARY)
- hash = ~hash;
- slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
- slot += hidx & _PTEIDX_GROUP_IX;
+ slot = compute_slot(pte, vpn, index, shift, ssize);
if (!firmware_has_feature(FW_FEATURE_BULK_REMOVE)) {
/*
* lpar doesn't use the passed actual page size
@@ -608,6 +818,7 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
BUG_ON(rc != H_SUCCESS);
}
+out:
if (lock_tlbie)
spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags);
}
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index 7c872dc01bdb..8bd590af488a 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -585,8 +585,7 @@ static ssize_t update_mpp(u64 *entitlement, u8 *weight)
static ssize_t lparcfg_write(struct file *file, const char __user * buf,
size_t count, loff_t * off)
{
- int kbuf_sz = 64;
- char kbuf[kbuf_sz];
+ char kbuf[64];
char *tmp;
u64 new_entitled, *new_entitled_ptr = &new_entitled;
u8 new_weight, *new_weight_ptr = &new_weight;
@@ -595,7 +594,7 @@ static ssize_t lparcfg_write(struct file *file, const char __user * buf,
if (!firmware_has_feature(FW_FEATURE_SPLPAR))
return -EINVAL;
- if (count > kbuf_sz)
+ if (count > sizeof(kbuf))
return -EINVAL;
if (copy_from_user(kbuf, buf, count))
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index f0e30dc94988..6f27d00505cf 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -242,7 +242,7 @@ static int add_dt_node(__be32 parent_phandle, __be32 drc_index)
static void prrn_update_node(__be32 phandle)
{
- struct pseries_hp_errorlog *hp_elog;
+ struct pseries_hp_errorlog hp_elog;
struct device_node *dn;
/*
@@ -255,18 +255,12 @@ static void prrn_update_node(__be32 phandle)
return;
}
- hp_elog = kzalloc(sizeof(*hp_elog), GFP_KERNEL);
- if(!hp_elog)
- return;
-
- hp_elog->resource = PSERIES_HP_ELOG_RESOURCE_MEM;
- hp_elog->action = PSERIES_HP_ELOG_ACTION_READD;
- hp_elog->id_type = PSERIES_HP_ELOG_ID_DRC_INDEX;
- hp_elog->_drc_u.drc_index = phandle;
-
- queue_hotplug_event(hp_elog, NULL, NULL);
+ hp_elog.resource = PSERIES_HP_ELOG_RESOURCE_MEM;
+ hp_elog.action = PSERIES_HP_ELOG_ACTION_READD;
+ hp_elog.id_type = PSERIES_HP_ELOG_ID_DRC_INDEX;
+ hp_elog._drc_u.drc_index = phandle;
- kfree(hp_elog);
+ handle_dlpar_errorlog(&hp_elog);
}
int pseries_devicetree_update(s32 scope)
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index 60db2ee511fb..72c0b8986536 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -24,6 +24,7 @@ struct pt_regs;
extern int pSeries_system_reset_exception(struct pt_regs *regs);
extern int pSeries_machine_check_exception(struct pt_regs *regs);
+extern long pseries_machine_check_realmode(struct pt_regs *regs);
#ifdef CONFIG_SMP
extern void smp_init_pseries(void);
@@ -59,8 +60,9 @@ extern int dlpar_detach_node(struct device_node *);
extern int dlpar_acquire_drc(u32 drc_index);
extern int dlpar_release_drc(u32 drc_index);
-void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog,
- struct completion *hotplug_done, int *rc);
+void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog);
+int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_errlog);
+
#ifdef CONFIG_MEMORY_HOTPLUG
int dlpar_memory(struct pseries_hp_errorlog *hp_elog);
#else
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 851ce326874a..2a9c28e4d4f9 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -27,6 +27,7 @@
#include <asm/machdep.h>
#include <asm/rtas.h>
#include <asm/firmware.h>
+#include <asm/mce.h>
#include "pseries.h"
@@ -50,6 +51,101 @@ static irqreturn_t ras_hotplug_interrupt(int irq, void *dev_id);
static irqreturn_t ras_epow_interrupt(int irq, void *dev_id);
static irqreturn_t ras_error_interrupt(int irq, void *dev_id);
+/* RTAS pseries MCE errorlog section. */
+struct pseries_mc_errorlog {
+ __be32 fru_id;
+ __be32 proc_id;
+ u8 error_type;
+ /*
+ * sub_err_type (1 byte). Bit fields depends on error_type
+ *
+ * MSB0
+ * |
+ * V
+ * 01234567
+ * XXXXXXXX
+ *
+ * For error_type == MC_ERROR_TYPE_UE
+ * XXXXXXXX
+ * X 1: Permanent or Transient UE.
+ * X 1: Effective address provided.
+ * X 1: Logical address provided.
+ * XX 2: Reserved.
+ * XXX 3: Type of UE error.
+ *
+ * For error_type != MC_ERROR_TYPE_UE
+ * XXXXXXXX
+ * X 1: Effective address provided.
+ * XXXXX 5: Reserved.
+ * XX 2: Type of SLB/ERAT/TLB error.
+ */
+ u8 sub_err_type;
+ u8 reserved_1[6];
+ __be64 effective_address;
+ __be64 logical_address;
+} __packed;
+
+/* RTAS pseries MCE error types */
+#define MC_ERROR_TYPE_UE 0x00
+#define MC_ERROR_TYPE_SLB 0x01
+#define MC_ERROR_TYPE_ERAT 0x02
+#define MC_ERROR_TYPE_TLB 0x04
+#define MC_ERROR_TYPE_D_CACHE 0x05
+#define MC_ERROR_TYPE_I_CACHE 0x07
+
+/* RTAS pseries MCE error sub types */
+#define MC_ERROR_UE_INDETERMINATE 0
+#define MC_ERROR_UE_IFETCH 1
+#define MC_ERROR_UE_PAGE_TABLE_WALK_IFETCH 2
+#define MC_ERROR_UE_LOAD_STORE 3
+#define MC_ERROR_UE_PAGE_TABLE_WALK_LOAD_STORE 4
+
+#define MC_ERROR_SLB_PARITY 0
+#define MC_ERROR_SLB_MULTIHIT 1
+#define MC_ERROR_SLB_INDETERMINATE 2
+
+#define MC_ERROR_ERAT_PARITY 1
+#define MC_ERROR_ERAT_MULTIHIT 2
+#define MC_ERROR_ERAT_INDETERMINATE 3
+
+#define MC_ERROR_TLB_PARITY 1
+#define MC_ERROR_TLB_MULTIHIT 2
+#define MC_ERROR_TLB_INDETERMINATE 3
+
+static inline u8 rtas_mc_error_sub_type(const struct pseries_mc_errorlog *mlog)
+{
+ switch (mlog->error_type) {
+ case MC_ERROR_TYPE_UE:
+ return (mlog->sub_err_type & 0x07);
+ case MC_ERROR_TYPE_SLB:
+ case MC_ERROR_TYPE_ERAT:
+ case MC_ERROR_TYPE_TLB:
+ return (mlog->sub_err_type & 0x03);
+ default:
+ return 0;
+ }
+}
+
+static
+inline u64 rtas_mc_get_effective_addr(const struct pseries_mc_errorlog *mlog)
+{
+ __be64 addr = 0;
+
+ switch (mlog->error_type) {
+ case MC_ERROR_TYPE_UE:
+ if (mlog->sub_err_type & 0x40)
+ addr = mlog->effective_address;
+ break;
+ case MC_ERROR_TYPE_SLB:
+ case MC_ERROR_TYPE_ERAT:
+ case MC_ERROR_TYPE_TLB:
+ if (mlog->sub_err_type & 0x80)
+ addr = mlog->effective_address;
+ default:
+ break;
+ }
+ return be64_to_cpu(addr);
+}
/*
* Enable the hotplug interrupt late because processing them may touch other
@@ -238,7 +334,7 @@ static irqreturn_t ras_hotplug_interrupt(int irq, void *dev_id)
*/
if (hp_elog->resource == PSERIES_HP_ELOG_RESOURCE_MEM ||
hp_elog->resource == PSERIES_HP_ELOG_RESOURCE_CPU)
- queue_hotplug_event(hp_elog, NULL, NULL);
+ queue_hotplug_event(hp_elog);
else
log_error(ras_log_buf, ERR_TYPE_RTAS_LOG, 0);
@@ -427,6 +523,188 @@ int pSeries_system_reset_exception(struct pt_regs *regs)
return 0; /* need to perform reset */
}
+#define VAL_TO_STRING(ar, val) \
+ (((val) < ARRAY_SIZE(ar)) ? ar[(val)] : "Unknown")
+
+static void pseries_print_mce_info(struct pt_regs *regs,
+ struct rtas_error_log *errp)
+{
+ const char *level, *sevstr;
+ struct pseries_errorlog *pseries_log;
+ struct pseries_mc_errorlog *mce_log;
+ u8 error_type, err_sub_type;
+ u64 addr;
+ u8 initiator = rtas_error_initiator(errp);
+ int disposition = rtas_error_disposition(errp);
+
+ static const char * const initiators[] = {
+ "Unknown",
+ "CPU",
+ "PCI",
+ "ISA",
+ "Memory",
+ "Power Mgmt",
+ };
+ static const char * const mc_err_types[] = {
+ "UE",
+ "SLB",
+ "ERAT",
+ "TLB",
+ "D-Cache",
+ "Unknown",
+ "I-Cache",
+ };
+ static const char * const mc_ue_types[] = {
+ "Indeterminate",
+ "Instruction fetch",
+ "Page table walk ifetch",
+ "Load/Store",
+ "Page table walk Load/Store",
+ };
+
+ /* SLB sub errors valid values are 0x0, 0x1, 0x2 */
+ static const char * const mc_slb_types[] = {
+ "Parity",
+ "Multihit",
+ "Indeterminate",
+ };
+
+ /* TLB and ERAT sub errors valid values are 0x1, 0x2, 0x3 */
+ static const char * const mc_soft_types[] = {
+ "Unknown",
+ "Parity",
+ "Multihit",
+ "Indeterminate",
+ };
+
+ if (!rtas_error_extended(errp)) {
+ pr_err("Machine check interrupt: Missing extended error log\n");
+ return;
+ }
+
+ pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE);
+ if (pseries_log == NULL)
+ return;
+
+ mce_log = (struct pseries_mc_errorlog *)pseries_log->data;
+
+ error_type = mce_log->error_type;
+ err_sub_type = rtas_mc_error_sub_type(mce_log);
+
+ switch (rtas_error_severity(errp)) {
+ case RTAS_SEVERITY_NO_ERROR:
+ level = KERN_INFO;
+ sevstr = "Harmless";
+ break;
+ case RTAS_SEVERITY_WARNING:
+ level = KERN_WARNING;
+ sevstr = "";
+ break;
+ case RTAS_SEVERITY_ERROR:
+ case RTAS_SEVERITY_ERROR_SYNC:
+ level = KERN_ERR;
+ sevstr = "Severe";
+ break;
+ case RTAS_SEVERITY_FATAL:
+ default:
+ level = KERN_ERR;
+ sevstr = "Fatal";
+ break;
+ }
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ /* Display faulty slb contents for SLB errors. */
+ if (error_type == MC_ERROR_TYPE_SLB)
+ slb_dump_contents(local_paca->mce_faulty_slbs);
+#endif
+
+ printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
+ disposition == RTAS_DISP_FULLY_RECOVERED ?
+ "Recovered" : "Not recovered");
+ if (user_mode(regs)) {
+ printk("%s NIP: [%016lx] PID: %d Comm: %s\n", level,
+ regs->nip, current->pid, current->comm);
+ } else {
+ printk("%s NIP [%016lx]: %pS\n", level, regs->nip,
+ (void *)regs->nip);
+ }
+ printk("%s Initiator: %s\n", level,
+ VAL_TO_STRING(initiators, initiator));
+
+ switch (error_type) {
+ case MC_ERROR_TYPE_UE:
+ printk("%s Error type: %s [%s]\n", level,
+ VAL_TO_STRING(mc_err_types, error_type),
+ VAL_TO_STRING(mc_ue_types, err_sub_type));
+ break;
+ case MC_ERROR_TYPE_SLB:
+ printk("%s Error type: %s [%s]\n", level,
+ VAL_TO_STRING(mc_err_types, error_type),
+ VAL_TO_STRING(mc_slb_types, err_sub_type));
+ break;
+ case MC_ERROR_TYPE_ERAT:
+ case MC_ERROR_TYPE_TLB:
+ printk("%s Error type: %s [%s]\n", level,
+ VAL_TO_STRING(mc_err_types, error_type),
+ VAL_TO_STRING(mc_soft_types, err_sub_type));
+ break;
+ default:
+ printk("%s Error type: %s\n", level,
+ VAL_TO_STRING(mc_err_types, error_type));
+ break;
+ }
+
+ addr = rtas_mc_get_effective_addr(mce_log);
+ if (addr)
+ printk("%s Effective address: %016llx\n", level, addr);
+}
+
+static int mce_handle_error(struct rtas_error_log *errp)
+{
+ struct pseries_errorlog *pseries_log;
+ struct pseries_mc_errorlog *mce_log;
+ int disposition = rtas_error_disposition(errp);
+ u8 error_type;
+
+ if (!rtas_error_extended(errp))
+ goto out;
+
+ pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE);
+ if (pseries_log == NULL)
+ goto out;
+
+ mce_log = (struct pseries_mc_errorlog *)pseries_log->data;
+ error_type = mce_log->error_type;
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ if (disposition == RTAS_DISP_NOT_RECOVERED) {
+ switch (error_type) {
+ case MC_ERROR_TYPE_SLB:
+ case MC_ERROR_TYPE_ERAT:
+ /*
+ * Store the old slb content in paca before flushing.
+ * Print this when we go to virtual mode.
+ * There are chances that we may hit MCE again if there
+ * is a parity error on the SLB entry we trying to read
+ * for saving. Hence limit the slb saving to single
+ * level of recursion.
+ */
+ if (local_paca->in_mce == 1)
+ slb_save_contents(local_paca->mce_faulty_slbs);
+ flush_and_reload_slb();
+ disposition = RTAS_DISP_FULLY_RECOVERED;
+ rtas_set_disposition_recovered(errp);
+ break;
+ default:
+ break;
+ }
+ }
+#endif
+
+out:
+ return disposition;
+}
+
/*
* Process MCE rtas errlog event.
*/
@@ -452,8 +730,11 @@ static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err)
int recovered = 0;
int disposition = rtas_error_disposition(err);
+ pseries_print_mce_info(regs, err);
+
if (!(regs->msr & MSR_RI)) {
/* If MSR_RI isn't set, we cannot recover */
+ pr_err("Machine check interrupt unrecoverable: MSR(RI=0)\n");
recovered = 0;
} else if (disposition == RTAS_DISP_FULLY_RECOVERED) {
@@ -503,11 +784,31 @@ int pSeries_machine_check_exception(struct pt_regs *regs)
struct rtas_error_log *errp;
if (fwnmi_active) {
- errp = fwnmi_get_errinfo(regs);
fwnmi_release_errinfo();
+ errp = fwnmi_get_errlog();
if (errp && recover_mce(regs, errp))
return 1;
}
return 0;
}
+
+long pseries_machine_check_realmode(struct pt_regs *regs)
+{
+ struct rtas_error_log *errp;
+ int disposition;
+
+ if (fwnmi_active) {
+ errp = fwnmi_get_errinfo(regs);
+ /*
+ * Call to fwnmi_release_errinfo() in real mode causes kernel
+ * to panic. Hence we will call it as soon as we go into
+ * virtual mode.
+ */
+ disposition = mce_handle_error(errp);
+ if (disposition == RTAS_DISP_FULLY_RECOVERED)
+ return 1;
+ }
+
+ return 0;
+}
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index ba1791fd3234..0f553dcfa548 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -107,6 +107,10 @@ static void __init fwnmi_init(void)
u8 *mce_data_buf;
unsigned int i;
int nr_cpus = num_possible_cpus();
+#ifdef CONFIG_PPC_BOOK3S_64
+ struct slb_entry *slb_ptr;
+ size_t size;
+#endif
int ibm_nmi_register = rtas_token("ibm,nmi-register");
if (ibm_nmi_register == RTAS_UNKNOWN_SERVICE)
@@ -132,6 +136,15 @@ static void __init fwnmi_init(void)
paca_ptrs[i]->mce_data_buf = mce_data_buf +
(RTAS_ERROR_LOG_MAX * i);
}
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ /* Allocate per cpu slb area to save old slb contents during MCE */
+ size = sizeof(struct slb_entry) * mmu_slb_size * nr_cpus;
+ slb_ptr = __va(memblock_alloc_base(size, sizeof(struct slb_entry),
+ ppc64_rma_size));
+ for_each_possible_cpu(i)
+ paca_ptrs[i]->mce_faulty_slbs = slb_ptr + (mmu_slb_size * i);
+#endif
}
static void pseries_8259_cascade(struct irq_desc *desc)
@@ -1017,6 +1030,7 @@ define_machine(pseries) {
.calibrate_decr = generic_calibrate_decr,
.progress = rtas_progress,
.system_reset_exception = pSeries_system_reset_exception,
+ .machine_check_early = pseries_machine_check_realmode,
.machine_check_exception = pSeries_machine_check_exception,
#ifdef CONFIG_KEXEC_CORE
.machine_kexec = pSeries_machine_kexec,
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 49e04ec19238..88f1ad1d6309 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -1349,7 +1349,6 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
struct device_node *parent_node;
const __be32 *prop;
enum vio_dev_family family;
- const char *of_node_name = of_node->name ? of_node->name : "<unknown>";
/*
* Determine if this node is a under the /vdevice node or under the
@@ -1362,24 +1361,24 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
else if (!strcmp(parent_node->type, "vdevice"))
family = VDEVICE;
else {
- pr_warn("%s: parent(%pOF) of %s not recognized.\n",
+ pr_warn("%s: parent(%pOF) of %pOFn not recognized.\n",
__func__,
parent_node,
- of_node_name);
+ of_node);
of_node_put(parent_node);
return NULL;
}
of_node_put(parent_node);
} else {
- pr_warn("%s: could not determine the parent of node %s.\n",
- __func__, of_node_name);
+ pr_warn("%s: could not determine the parent of node %pOFn.\n",
+ __func__, of_node);
return NULL;
}
if (family == PFO) {
if (of_get_property(of_node, "interrupt-controller", NULL)) {
- pr_debug("%s: Skipping the interrupt controller %s.\n",
- __func__, of_node_name);
+ pr_debug("%s: Skipping the interrupt controller %pOFn.\n",
+ __func__, of_node);
return NULL;
}
}
@@ -1399,15 +1398,15 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
if (of_node->type != NULL)
viodev->type = of_node->type;
else {
- pr_warn("%s: node %s is missing the 'device_type' "
- "property.\n", __func__, of_node_name);
+ pr_warn("%s: node %pOFn is missing the 'device_type' "
+ "property.\n", __func__, of_node);
goto out;
}
prop = of_get_property(of_node, "reg", NULL);
if (prop == NULL) {
- pr_warn("%s: node %s missing 'reg'\n",
- __func__, of_node_name);
+ pr_warn("%s: node %pOFn missing 'reg'\n",
+ __func__, of_node);
goto out;
}
unit_address = of_read_number(prop, 1);
@@ -1422,8 +1421,8 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
if (prop != NULL)
viodev->resource_id = of_read_number(prop, 1);
- dev_set_name(&viodev->dev, "%s", of_node_name);
- viodev->type = of_node_name;
+ dev_set_name(&viodev->dev, "%pOFn", of_node);
+ viodev->type = dev_name(&viodev->dev);
viodev->irq = 0;
}
@@ -1694,7 +1693,7 @@ struct vio_dev *vio_find_node(struct device_node *vnode)
snprintf(kobj_name, sizeof(kobj_name), "%x",
(uint32_t)of_read_number(prop, 1));
} else if (!strcmp(dev_type, "ibm,platform-facilities"))
- snprintf(kobj_name, sizeof(kobj_name), "%s", vnode->name);
+ snprintf(kobj_name, sizeof(kobj_name), "%pOFn", vnode);
else
return NULL;