* [RFC PATCH v4 10/12] powerpc/book3s: Queue up and process delayed MCE events.
From: Mahesh J Salgaonkar @ 2013-09-16 12:42 UTC (permalink / raw)
To: linuxppc-dev, Paul Mackerras, Benjamin Herrenschmidt
Cc: Jeremy Kerr, Anton Blanchard
In-Reply-To: <20130916123908.16111.4657.stgit@mars.in.ibm.com>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
When machine check real mode handler can not continue into host kernel
in V mode, it returns from the interrupt and we loose MCE event which
never gets logged. In such a situation queue up the MCE event so that
we can log it later when we get back into host kernel with r1 pointing to
kernel stack e.g. during syscall exit.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/mce.h | 3 +
arch/powerpc/kernel/entry_64.S | 5 +
arch/powerpc/kernel/exceptions-64s.S | 7 +-
arch/powerpc/kernel/mce.c | 154 +++++++++++++++++++++++++++++++++
arch/powerpc/platforms/powernv/opal.c | 97 ---------------------
5 files changed, 168 insertions(+), 98 deletions(-)
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index 87cad2a..3276b40 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -190,5 +190,8 @@ extern void save_mce_event(struct pt_regs *regs, long handled,
struct mce_error_info *mce_err, uint64_t addr);
extern int get_mce_event(struct machine_check_event *mce, bool release);
extern void release_mce_event(void);
+extern void machine_check_queue_event(void);
+extern void machine_check_process_queued_event(void);
+extern void machine_check_print_event_info(struct machine_check_event *evt);
#endif /* __ASM_PPC64_MCE_H__ */
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 2bd0b88..71bcd41 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -183,6 +183,11 @@ syscall_exit:
bl .do_show_syscall_exit
ld r3,RESULT(r1)
#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+BEGIN_FTR_SECTION
+ bl .machine_check_process_queued_event
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
+#endif
CURRENT_THREAD_INFO(r12, r1)
ld r8,_MSR(r1)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 0a92ba4..ce57cec 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -824,7 +824,8 @@ BEGIN_FTR_SECTION
/* Supervisor state loss */
li r0,1
stb r0,PACA_NAPSTATELOST(r13)
-3: MACHINE_CHECK_HANDLER_WINDUP
+3: bl .machine_check_queue_event
+ MACHINE_CHECK_HANDLER_WINDUP
GET_PACA(r13)
ld r1,PACAR1(r13)
b .power7_enter_nap_mode
@@ -864,8 +865,10 @@ BEGIN_FTR_SECTION
2:
/*
* Return from MC interrupt.
- * TODO: Queue up the MCE event so that we can log it later.
+ * Queue up the MCE event so that we can log it later, while
+ * returning from kernel or opal call.
*/
+ bl .machine_check_queue_event
MACHINE_CHECK_HANDLER_WINDUP
rfid
9:
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index aeecdf1..1cca4b6 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -31,6 +31,10 @@
static DEFINE_PER_CPU(int, mce_nest_count);
static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event);
+/* Queue for delayed MCE events. */
+static DEFINE_PER_CPU(int, mce_queue_count);
+static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event_queue);
+
static void mce_set_error_info(struct machine_check_event *mce,
struct mce_error_info *mce_err)
{
@@ -162,3 +166,153 @@ void release_mce_event(void)
{
get_mce_event(NULL, true);
}
+
+/*
+ * Queue up the MCE event which then can be handled later.
+ */
+void machine_check_queue_event(void)
+{
+ int index;
+ struct machine_check_event evt;
+
+ if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
+ return;
+
+ index = __get_cpu_var(mce_queue_count)++;
+ /* If queue is full, just return for now. */
+ if (index >= MAX_MC_EVT) {
+ __get_cpu_var(mce_queue_count)--;
+ return;
+ }
+ __get_cpu_var(mce_event_queue[index]) = evt;
+}
+
+/*
+ * process pending MCE event from the mce event queue. This function will be
+ * called during syscall exit.
+ */
+void machine_check_process_queued_event(void)
+{
+ int index;
+
+ preempt_disable();
+ /*
+ * For now just print it to console.
+ * TODO: log this error event to FSP or nvram.
+ */
+ while (__get_cpu_var(mce_queue_count) > 0) {
+ index = __get_cpu_var(mce_queue_count) - 1;
+ machine_check_print_event_info(
+ &__get_cpu_var(mce_event_queue[index]));
+ __get_cpu_var(mce_queue_count)--;
+ }
+ preempt_enable();
+}
+
+void machine_check_print_event_info(struct machine_check_event *evt)
+{
+ const char *level, *sevstr, *subtype;
+ static const char *mc_ue_types[] = {
+ "Indeterminate",
+ "Instruction fetch",
+ "Page table walk ifetch",
+ "Load/Store",
+ "Page table walk Load/Store",
+ };
+ static const char *mc_slb_types[] = {
+ "Indeterminate",
+ "Parity",
+ "Multihit",
+ };
+ static const char *mc_erat_types[] = {
+ "Indeterminate",
+ "Parity",
+ "Multihit",
+ };
+ static const char *mc_tlb_types[] = {
+ "Indeterminate",
+ "Parity",
+ "Multihit",
+ };
+
+ /* Print things out */
+ if (evt->version != MCE_V1) {
+ pr_err("Machine Check Exception, Unknown event version %d !\n",
+ evt->version);
+ return;
+ }
+ switch(evt->severity) {
+ case MCE_SEV_NO_ERROR:
+ level = KERN_INFO;
+ sevstr = "Harmless";
+ break;
+ case MCE_SEV_WARNING:
+ level = KERN_WARNING;
+ sevstr = "";
+ break;
+ case MCE_SEV_ERROR_SYNC:
+ level = KERN_ERR;
+ sevstr = "Severe";
+ break;
+ case MCE_SEV_FATAL:
+ default:
+ level = KERN_ERR;
+ sevstr = "Fatal";
+ break;
+ }
+
+ printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
+ evt->disposition == MCE_DISPOSITION_RECOVERED ?
+ "Recovered" : "[Not recovered");
+ printk("%s Initiator: %s\n", level,
+ evt->initiator == MCE_INITIATOR_CPU ? "CPU" : "Unknown");
+ switch(evt->error_type) {
+ case MCE_ERROR_TYPE_UE:
+ subtype = evt->u.ue_error.ue_error_type <
+ ARRAY_SIZE(mc_ue_types) ?
+ mc_ue_types[evt->u.ue_error.ue_error_type]
+ : "Unknown";
+ printk("%s Error type: UE [%s]\n", level, subtype);
+ if (evt->u.ue_error.effective_address_provided)
+ printk("%s Effective address: %016llx\n",
+ level, evt->u.ue_error.effective_address);
+ if (evt->u.ue_error.physical_address_provided)
+ printk("%s Physial address: %016llx\n",
+ level, evt->u.ue_error.physical_address);
+ break;
+ case MCE_ERROR_TYPE_SLB:
+ subtype = evt->u.slb_error.slb_error_type <
+ ARRAY_SIZE(mc_slb_types) ?
+ mc_slb_types[evt->u.slb_error.slb_error_type]
+ : "Unknown";
+ printk("%s Error type: SLB [%s]\n", level, subtype);
+ if (evt->u.slb_error.effective_address_provided)
+ printk("%s Effective address: %016llx\n",
+ level, evt->u.slb_error.effective_address);
+ break;
+ case MCE_ERROR_TYPE_ERAT:
+ subtype = evt->u.erat_error.erat_error_type <
+ ARRAY_SIZE(mc_erat_types) ?
+ mc_erat_types[evt->u.erat_error.erat_error_type]
+ : "Unknown";
+ printk("%s Error type: ERAT [%s]\n", level, subtype);
+ if (evt->u.erat_error.effective_address_provided)
+ printk("%s Effective address: %016llx\n",
+ level, evt->u.erat_error.effective_address);
+ break;
+ case MCE_ERROR_TYPE_TLB:
+ subtype = evt->u.tlb_error.tlb_error_type <
+ ARRAY_SIZE(mc_tlb_types) ?
+ mc_tlb_types[evt->u.tlb_error.tlb_error_type]
+ : "Unknown";
+ printk("%s Error type: TLB [%s]\n", level, subtype);
+ if (evt->u.tlb_error.effective_address_provided)
+ printk("%s Effective address: %016llx\n",
+ level, evt->u.tlb_error.effective_address);
+ break;
+ default:
+ case MCE_ERROR_TYPE_UNKNOWN:
+ printk("%s Error type: Unknown\n", level);
+ break;
+ }
+}
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index bcbbcdc..f789514 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -247,29 +247,6 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
int opal_machine_check(struct pt_regs *regs)
{
struct machine_check_event evt;
- const char *level, *sevstr, *subtype;
- static const char *opal_mc_ue_types[] = {
- "Indeterminate",
- "Instruction fetch",
- "Page table walk ifetch",
- "Load/Store",
- "Page table walk Load/Store",
- };
- static const char *opal_mc_slb_types[] = {
- "Indeterminate",
- "Parity",
- "Multihit",
- };
- static const char *opal_mc_erat_types[] = {
- "Indeterminate",
- "Parity",
- "Multihit",
- };
- static const char *opal_mc_tlb_types[] = {
- "Indeterminate",
- "Parity",
- "Multihit",
- };
if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
return 0;
@@ -280,80 +257,8 @@ int opal_machine_check(struct pt_regs *regs)
evt.version);
return 0;
}
- switch(evt.severity) {
- case MCE_SEV_NO_ERROR:
- level = KERN_INFO;
- sevstr = "Harmless";
- break;
- case MCE_SEV_WARNING:
- level = KERN_WARNING;
- sevstr = "";
- break;
- case MCE_SEV_ERROR_SYNC:
- level = KERN_ERR;
- sevstr = "Severe";
- break;
- case MCE_SEV_FATAL:
- default:
- level = KERN_ERR;
- sevstr = "Fatal";
- break;
- }
+ machine_check_print_event_info(&evt);
- printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
- evt.disposition == MCE_DISPOSITION_RECOVERED ?
- "Recovered" : "[Not recovered");
- printk("%s Initiator: %s\n", level,
- evt.initiator == MCE_INITIATOR_CPU ? "CPU" : "Unknown");
- switch(evt.error_type) {
- case MCE_ERROR_TYPE_UE:
- subtype = evt.u.ue_error.ue_error_type <
- ARRAY_SIZE(opal_mc_ue_types) ?
- opal_mc_ue_types[evt.u.ue_error.ue_error_type]
- : "Unknown";
- printk("%s Error type: UE [%s]\n", level, subtype);
- if (evt.u.ue_error.effective_address_provided)
- printk("%s Effective address: %016llx\n",
- level, evt.u.ue_error.effective_address);
- if (evt.u.ue_error.physical_address_provided)
- printk("%s Physial address: %016llx\n",
- level, evt.u.ue_error.physical_address);
- break;
- case MCE_ERROR_TYPE_SLB:
- subtype = evt.u.slb_error.slb_error_type <
- ARRAY_SIZE(opal_mc_slb_types) ?
- opal_mc_slb_types[evt.u.slb_error.slb_error_type]
- : "Unknown";
- printk("%s Error type: SLB [%s]\n", level, subtype);
- if (evt.u.slb_error.effective_address_provided)
- printk("%s Effective address: %016llx\n",
- level, evt.u.slb_error.effective_address);
- break;
- case MCE_ERROR_TYPE_ERAT:
- subtype = evt.u.erat_error.erat_error_type <
- ARRAY_SIZE(opal_mc_erat_types) ?
- opal_mc_erat_types[evt.u.erat_error.erat_error_type]
- : "Unknown";
- printk("%s Error type: ERAT [%s]\n", level, subtype);
- if (evt.u.erat_error.effective_address_provided)
- printk("%s Effective address: %016llx\n",
- level, evt.u.erat_error.effective_address);
- break;
- case MCE_ERROR_TYPE_TLB:
- subtype = evt.u.tlb_error.tlb_error_type <
- ARRAY_SIZE(opal_mc_tlb_types) ?
- opal_mc_tlb_types[evt.u.tlb_error.tlb_error_type]
- : "Unknown";
- printk("%s Error type: TLB [%s]\n", level, subtype);
- if (evt.u.tlb_error.effective_address_provided)
- printk("%s Effective address: %016llx\n",
- level, evt.u.tlb_error.effective_address);
- break;
- default:
- case MCE_ERROR_TYPE_UNKNOWN:
- printk("%s Error type: Unknown\n", level);
- break;
- }
return evt.severity == MCE_SEV_FATAL ? 0 : 1;
}
^ permalink raw reply related
* [RFC PATCH v4 09/12] powerpc/book3s: Decode and save machine check event.
From: Mahesh J Salgaonkar @ 2013-09-16 12:42 UTC (permalink / raw)
To: linuxppc-dev, Paul Mackerras, Benjamin Herrenschmidt
Cc: Jeremy Kerr, Anton Blanchard
In-Reply-To: <20130916123908.16111.4657.stgit@mars.in.ibm.com>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Now that we handle machine check in linux, the MCE decoding should also
take place in linux host. This info is crucial to log before we go down
in case we can not handle the machine check errors. This patch decodes
and populates a machine check event which contain high level meaning full
MCE information.
We do this in real mode C code with ME bit on. The MCE information is still
available on emergency stack (in pt_regs structure format). Even if we take
another exception at this point the MCE early handler will allocate a new
stack frame on top of current one. So when we return back here we still have
our MCE information safe on current stack.
We use per cpu buffer to save high level MCE information. Each per cpu buffer
is an array of machine check event structure indexed by per cpu counter
mce_nest_count. The mce_nest_count is incremented every time we enter
machine check early handler in real mode to get the current free slot
(index = mce_nest_count - 1). The mce_nest_count is decremented once the
MCE info is consumed by virtual mode machine exception handler.
This patch provides save_mce_event(), get_mce_event() and release_mce_event()
generic routines that can be used by machine check handlers to populate and
retrieve the event. The routine release_mce_event() will free the event slot so
that it can be reused. Caller can invoke get_mce_event() with a release flag
either to release the event slot immediately OR keep it so that it can be
fetched again. The event slot can be also released anytime by invoking
release_mce_event().
This patch also updates kvm code to invoke get_mce_event to retrieve generic
mce event rather than paca->opal_mce_evt.
The KVM code always calls get_mce_event() with release flags set to false so
that event is available for linus host machine
If machine check occurs while we are in guest, KVM tries to handle the error.
If KVM is able to handle MC error successfully, it enters the guest and
delivers the machine check to guest. If KVM is not able to handle MC error, it
exists the guest and passes the control to linux host machine check handler
which then logs MC event and decides how to handle it in linux host. In failure
case, KVM needs to make sure that the MC event is available for linux host to
consume. Hence KVM always calls get_mce_event() with release flags set to false
and later it invokes release_mce_event() only if it succeeds to handle error.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/mce.h | 124 +++++++++++++++++++++++++
arch/powerpc/kernel/Makefile | 2
arch/powerpc/kernel/mce.c | 164 +++++++++++++++++++++++++++++++++
arch/powerpc/kernel/mce_power.c | 116 ++++++++++++++++++++++-
arch/powerpc/kvm/book3s_hv_ras.c | 32 ++++--
arch/powerpc/platforms/powernv/opal.c | 35 +++----
6 files changed, 434 insertions(+), 39 deletions(-)
create mode 100644 arch/powerpc/kernel/mce.c
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index e3ffa82..87cad2a 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -66,5 +66,129 @@
#define P8_DSISR_MC_SLB_ERRORS (P7_DSISR_MC_SLB_ERRORS | \
P8_DSISR_MC_ERAT_MULTIHIT_SEC)
+enum MCE_Version {
+ MCE_V1 = 1,
+};
+
+enum MCE_Severity {
+ MCE_SEV_NO_ERROR = 0,
+ MCE_SEV_WARNING = 1,
+ MCE_SEV_ERROR_SYNC = 2,
+ MCE_SEV_FATAL = 3,
+};
+
+enum MCE_Disposition {
+ MCE_DISPOSITION_RECOVERED = 0,
+ MCE_DISPOSITION_NOT_RECOVERED = 1,
+};
+
+enum MCE_Initiator {
+ MCE_INITIATOR_UNKNOWN = 0,
+ MCE_INITIATOR_CPU = 1,
+};
+
+enum MCE_ErrorType {
+ MCE_ERROR_TYPE_UNKNOWN = 0,
+ MCE_ERROR_TYPE_UE = 1,
+ MCE_ERROR_TYPE_SLB = 2,
+ MCE_ERROR_TYPE_ERAT = 3,
+ MCE_ERROR_TYPE_TLB = 4,
+};
+
+enum MCE_UeErrorType {
+ MCE_UE_ERROR_INDETERMINATE = 0,
+ MCE_UE_ERROR_IFETCH = 1,
+ MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH = 2,
+ MCE_UE_ERROR_LOAD_STORE = 3,
+ MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE = 4,
+};
+
+enum MCE_SlbErrorType {
+ MCE_SLB_ERROR_INDETERMINATE = 0,
+ MCE_SLB_ERROR_PARITY = 1,
+ MCE_SLB_ERROR_MULTIHIT = 2,
+};
+
+enum MCE_EratErrorType {
+ MCE_ERAT_ERROR_INDETERMINATE = 0,
+ MCE_ERAT_ERROR_PARITY = 1,
+ MCE_ERAT_ERROR_MULTIHIT = 2,
+};
+
+enum MCE_TlbErrorType {
+ MCE_TLB_ERROR_INDETERMINATE = 0,
+ MCE_TLB_ERROR_PARITY = 1,
+ MCE_TLB_ERROR_MULTIHIT = 2,
+};
+
+struct machine_check_event {
+ enum MCE_Version version:8; /* 0x00 */
+ uint8_t in_use; /* 0x01 */
+ enum MCE_Severity severity:8; /* 0x02 */
+ enum MCE_Initiator initiator:8; /* 0x03 */
+ enum MCE_ErrorType error_type:8; /* 0x04 */
+ enum MCE_Disposition disposition:8; /* 0x05 */
+ uint8_t reserved_1[2]; /* 0x06 */
+ uint64_t gpr3; /* 0x08 */
+ uint64_t srr0; /* 0x10 */
+ uint64_t srr1; /* 0x18 */
+ union { /* 0x20 */
+ struct {
+ enum MCE_UeErrorType ue_error_type:8;
+ uint8_t effective_address_provided;
+ uint8_t physical_address_provided;
+ uint8_t reserved_1[5];
+ uint64_t effective_address;
+ uint64_t physical_address;
+ uint8_t reserved_2[8];
+ } ue_error;
+
+ struct {
+ enum MCE_SlbErrorType slb_error_type:8;
+ uint8_t effective_address_provided;
+ uint8_t reserved_1[6];
+ uint64_t effective_address;
+ uint8_t reserved_2[16];
+ } slb_error;
+
+ struct {
+ enum MCE_EratErrorType erat_error_type:8;
+ uint8_t effective_address_provided;
+ uint8_t reserved_1[6];
+ uint64_t effective_address;
+ uint8_t reserved_2[16];
+ } erat_error;
+
+ struct {
+ enum MCE_TlbErrorType tlb_error_type:8;
+ uint8_t effective_address_provided;
+ uint8_t reserved_1[6];
+ uint64_t effective_address;
+ uint8_t reserved_2[16];
+ } tlb_error;
+ } u;
+};
+
+struct mce_error_info {
+ enum MCE_ErrorType error_type:8;
+ union {
+ enum MCE_UeErrorType ue_error_type:8;
+ enum MCE_SlbErrorType slb_error_type:8;
+ enum MCE_EratErrorType erat_error_type:8;
+ enum MCE_TlbErrorType tlb_error_type:8;
+ } u;
+ uint8_t reserved[2];
+};
+
+#define MAX_MC_EVT 100
+
+/* Release flags for get_mce_event() */
+#define MCE_EVENT_RELEASE true
+#define MCE_EVENT_DONTRELEASE false
+
+extern void save_mce_event(struct pt_regs *regs, long handled,
+ struct mce_error_info *mce_err, uint64_t addr);
+extern int get_mce_event(struct machine_check_event *mce, bool release);
+extern void release_mce_event(void);
#endif /* __ASM_PPC64_MCE_H__ */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index a1aba53..c3ae108 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -39,7 +39,7 @@ obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \
obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o
obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o
-obj-$(CONFIG_PPC_BOOK3S_64) += mce_power.o
+obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o
obj64-$(CONFIG_RELOCATABLE) += reloc_64.o
obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o
obj-$(CONFIG_PPC_A2) += cpu_setup_a2.o
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
new file mode 100644
index 0000000..aeecdf1
--- /dev/null
+++ b/arch/powerpc/kernel/mce.c
@@ -0,0 +1,164 @@
+/*
+ * Machine check exception handling.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright 2013 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#undef DEBUG
+#define pr_fmt(fmt) "mce: " fmt
+
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/percpu.h>
+#include <linux/export.h>
+#include <asm/mce.h>
+
+static DEFINE_PER_CPU(int, mce_nest_count);
+static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event);
+
+static void mce_set_error_info(struct machine_check_event *mce,
+ struct mce_error_info *mce_err)
+{
+ mce->error_type = mce_err->error_type;
+ switch (mce_err->error_type) {
+ case MCE_ERROR_TYPE_UE:
+ mce->u.ue_error.ue_error_type = mce_err->u.ue_error_type;
+ break;
+ case MCE_ERROR_TYPE_SLB:
+ mce->u.slb_error.slb_error_type = mce_err->u.slb_error_type;
+ break;
+ case MCE_ERROR_TYPE_ERAT:
+ mce->u.erat_error.erat_error_type = mce_err->u.erat_error_type;
+ break;
+ case MCE_ERROR_TYPE_TLB:
+ mce->u.tlb_error.tlb_error_type = mce_err->u.tlb_error_type;
+ break;
+ case MCE_ERROR_TYPE_UNKNOWN:
+ default:
+ break;
+ }
+}
+
+/*
+ * Decode and save high level MCE information into per cpu buffer which
+ * is an array of machine_check_event structure.
+ */
+void save_mce_event(struct pt_regs *regs, long handled,
+ struct mce_error_info *mce_err,
+ uint64_t addr)
+{
+ uint64_t srr1;
+ int index = __get_cpu_var(mce_nest_count)++;
+ struct machine_check_event *mce = &__get_cpu_var(mce_event[index]);
+
+ /*
+ * Return if we don't have enough space to log mce event.
+ * mce_nest_count may go beyond MAX_MC_EVT but that's ok,
+ * the check below will stop buffer overrun.
+ */
+ if (index >= MAX_MC_EVT)
+ return;
+
+ /* Populate generic machine check info */
+ mce->version = MCE_V1;
+ mce->srr0 = regs->nip;
+ mce->srr1 = regs->msr;
+ mce->gpr3 = regs->gpr[3];
+ mce->in_use = 1;
+
+ mce->initiator = MCE_INITIATOR_CPU;
+ if (handled)
+ mce->disposition = MCE_DISPOSITION_RECOVERED;
+ else
+ mce->disposition = MCE_DISPOSITION_NOT_RECOVERED;
+ mce->severity = MCE_SEV_ERROR_SYNC;
+
+ srr1 = regs->msr;
+
+ /*
+ * Populate the mce error_type and type-specific error_type.
+ */
+ mce_set_error_info(mce, mce_err);
+
+ if (!addr)
+ return;
+
+ if (mce->error_type == MCE_ERROR_TYPE_TLB) {
+ mce->u.tlb_error.effective_address_provided = true;
+ mce->u.tlb_error.effective_address = addr;
+ } else if (mce->error_type == MCE_ERROR_TYPE_SLB) {
+ mce->u.slb_error.effective_address_provided = true;
+ mce->u.slb_error.effective_address = addr;
+ } else if (mce->error_type == MCE_ERROR_TYPE_ERAT) {
+ mce->u.erat_error.effective_address_provided = true;
+ mce->u.erat_error.effective_address = addr;
+ } else if (mce->error_type == MCE_ERROR_TYPE_UE) {
+ mce->u.ue_error.effective_address_provided = true;
+ mce->u.ue_error.effective_address = addr;
+ }
+ return;
+}
+
+/*
+ * get_mce_event:
+ * mce Pointer to machine_check_event structure to be filled.
+ * release Flag to indicate whether to free the event slot or not.
+ * 0 <= do not release the mce event. Caller will invoke
+ * release_mce_event() once event has been consumed.
+ * 1 <= release the slot.
+ *
+ * return 1 = success
+ * 0 = failure
+ *
+ * get_mce_event() will be called by platform specific machine check
+ * handle routine and in KVM.
+ * When we call get_mce_event(), we are still in interrupt context and
+ * preemption will not be scheduled until ret_from_expect() routine
+ * is called.
+ */
+int get_mce_event(struct machine_check_event *mce, bool release)
+{
+ int index = __get_cpu_var(mce_nest_count) - 1;
+ struct machine_check_event *mc_evt;
+ int ret = 0;
+
+ /* Sanity check */
+ if (index < 0)
+ return ret;
+
+ /* Check if we have MCE info to process. */
+ if (index < MAX_MC_EVT) {
+ mc_evt = &__get_cpu_var(mce_event[index]);
+ /* Copy the event structure and release the original */
+ if (mce)
+ *mce = *mc_evt;
+ if (release)
+ mc_evt->in_use = 0;
+ ret = 1;
+ }
+ /* Decrement the count to free the slot. */
+ if (release)
+ __get_cpu_var(mce_nest_count)--;
+
+ return ret;
+}
+
+void release_mce_event(void)
+{
+ get_mce_event(NULL, true);
+}
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 60a217f..b36e777 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -133,22 +133,116 @@ static long mce_handle_ierror_p7(uint64_t srr1)
return handled;
}
+static void mce_get_common_ierror(struct mce_error_info *mce_err, uint64_t srr1)
+{
+ switch (P7_SRR1_MC_IFETCH(srr1)) {
+ case P7_SRR1_MC_IFETCH_SLB_PARITY:
+ mce_err->error_type = MCE_ERROR_TYPE_SLB;
+ mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
+ break;
+ case P7_SRR1_MC_IFETCH_SLB_MULTIHIT:
+ mce_err->error_type = MCE_ERROR_TYPE_SLB;
+ mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
+ break;
+ case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
+ mce_err->error_type = MCE_ERROR_TYPE_TLB;
+ mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
+ break;
+ case P7_SRR1_MC_IFETCH_UE:
+ case P7_SRR1_MC_IFETCH_UE_IFU_INTERNAL:
+ mce_err->error_type = MCE_ERROR_TYPE_UE;
+ mce_err->u.ue_error_type = MCE_UE_ERROR_IFETCH;
+ break;
+ case P7_SRR1_MC_IFETCH_UE_TLB_RELOAD:
+ mce_err->error_type = MCE_ERROR_TYPE_UE;
+ mce_err->u.ue_error_type =
+ MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH;
+ break;
+ }
+}
+
+static void mce_get_ierror_p7(struct mce_error_info *mce_err, uint64_t srr1)
+{
+ mce_get_common_ierror(mce_err, srr1);
+ if (P7_SRR1_MC_IFETCH(srr1) == P7_SRR1_MC_IFETCH_SLB_BOTH) {
+ mce_err->error_type = MCE_ERROR_TYPE_SLB;
+ mce_err->u.slb_error_type = MCE_SLB_ERROR_INDETERMINATE;
+ }
+}
+
+static void mce_get_derror_p7(struct mce_error_info *mce_err, uint64_t dsisr)
+{
+ if (dsisr & P7_DSISR_MC_UE) {
+ mce_err->error_type = MCE_ERROR_TYPE_UE;
+ mce_err->u.ue_error_type = MCE_UE_ERROR_LOAD_STORE;
+ } else if (dsisr & P7_DSISR_MC_UE_TABLEWALK) {
+ mce_err->error_type = MCE_ERROR_TYPE_UE;
+ mce_err->u.ue_error_type =
+ MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE;
+ } else if (dsisr & P7_DSISR_MC_ERAT_MULTIHIT) {
+ mce_err->error_type = MCE_ERROR_TYPE_ERAT;
+ mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+ } else if (dsisr & P7_DSISR_MC_SLB_MULTIHIT) {
+ mce_err->error_type = MCE_ERROR_TYPE_SLB;
+ mce_err->u.slb_error_type = MCE_SLB_ERROR_MULTIHIT;
+ } else if (dsisr & P7_DSISR_MC_SLB_PARITY_MFSLB) {
+ mce_err->error_type = MCE_ERROR_TYPE_SLB;
+ mce_err->u.slb_error_type = MCE_SLB_ERROR_PARITY;
+ } else if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) {
+ mce_err->error_type = MCE_ERROR_TYPE_TLB;
+ mce_err->u.tlb_error_type = MCE_TLB_ERROR_MULTIHIT;
+ } else if (dsisr & P7_DSISR_MC_SLB_MULTIHIT_PARITY) {
+ mce_err->error_type = MCE_ERROR_TYPE_SLB;
+ mce_err->u.slb_error_type = MCE_SLB_ERROR_INDETERMINATE;
+ }
+}
+
long __machine_check_early_realmode_p7(struct pt_regs *regs)
{
- uint64_t srr1;
+ uint64_t srr1, addr;
long handled = 1;
+ struct mce_error_info mce_error_info = { 0 };
srr1 = regs->msr;
- if (P7_SRR1_MC_LOADSTORE(srr1))
+ /*
+ * Handle memory errors depending whether this was a load/store or
+ * ifetch exception. Also, populate the mce error_type and
+ * type-specific error_type from either SRR1 or DSISR, depending
+ * whether this was a load/store or ifetch exception
+ */
+ if (P7_SRR1_MC_LOADSTORE(srr1)) {
handled = mce_handle_derror_p7(regs->dsisr);
- else
+ mce_get_derror_p7(&mce_error_info, regs->dsisr);
+ addr = regs->dar;
+ } else {
handled = mce_handle_ierror_p7(srr1);
+ mce_get_ierror_p7(&mce_error_info, srr1);
+ addr = regs->nip;
+ }
- /* TODO: Decode machine check reason. */
+ save_mce_event(regs, handled, &mce_error_info, addr);
return handled;
}
+static void mce_get_ierror_p8(struct mce_error_info *mce_err, uint64_t srr1)
+{
+ mce_get_common_ierror(mce_err, srr1);
+ if (P7_SRR1_MC_IFETCH(srr1) == P8_SRR1_MC_IFETCH_ERAT_MULTIHIT) {
+ mce_err->error_type = MCE_ERROR_TYPE_ERAT;
+ mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+ }
+}
+
+static void mce_get_derror_p8(struct mce_error_info *mce_err, uint64_t dsisr)
+{
+ mce_get_derror_p7(mce_err, dsisr);
+ if (dsisr & P8_DSISR_MC_ERAT_MULTIHIT_SEC) {
+ mce_err->error_type = MCE_ERROR_TYPE_ERAT;
+ mce_err->u.erat_error_type = MCE_ERAT_ERROR_MULTIHIT;
+ }
+}
+
static long mce_handle_ierror_p8(uint64_t srr1)
{
long handled = 0;
@@ -169,16 +263,22 @@ static long mce_handle_derror_p8(uint64_t dsisr)
long __machine_check_early_realmode_p8(struct pt_regs *regs)
{
- uint64_t srr1;
+ uint64_t srr1, addr;
long handled = 1;
+ struct mce_error_info mce_error_info = { 0 };
srr1 = regs->msr;
- if (P7_SRR1_MC_LOADSTORE(srr1))
+ if (P7_SRR1_MC_LOADSTORE(srr1)) {
handled = mce_handle_derror_p8(regs->dsisr);
- else
+ mce_get_derror_p8(&mce_error_info, regs->dsisr);
+ addr = regs->dar;
+ } else {
handled = mce_handle_ierror_p8(srr1);
+ mce_get_ierror_p8(&mce_error_info, srr1);
+ addr = regs->nip;
+ }
- /* TODO: Decode machine check reason. */
+ save_mce_event(regs, handled, &mce_error_info, addr);
return handled;
}
diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c
index 5c427b4..768a9f9 100644
--- a/arch/powerpc/kvm/book3s_hv_ras.c
+++ b/arch/powerpc/kvm/book3s_hv_ras.c
@@ -12,6 +12,7 @@
#include <linux/kvm_host.h>
#include <linux/kernel.h>
#include <asm/opal.h>
+#include <asm/mce.h>
/* SRR1 bits for machine check on POWER7 */
#define SRR1_MC_LDSTERR (1ul << (63-42))
@@ -67,9 +68,7 @@ static void reload_slb(struct kvm_vcpu *vcpu)
static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
{
unsigned long srr1 = vcpu->arch.shregs.msr;
-#ifdef CONFIG_PPC_POWERNV
- struct opal_machine_check_event *opal_evt;
-#endif
+ struct machine_check_event mce_evt;
long handled = 1;
if (srr1 & SRR1_MC_LDSTERR) {
@@ -109,22 +108,31 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
handled = 0;
}
-#ifdef CONFIG_PPC_POWERNV
/*
- * See if OPAL has already handled the condition.
- * We assume that if the condition is recovered then OPAL
+ * See if we have already handled the condition in the linux host.
+ * We assume that if the condition is recovered then linux host
* will have generated an error log event that we will pick
* up and log later.
+ * Don't release mce event now. In case if condition is not
+ * recovered we do guest exit and go back to linux host machine
+ * check handler. Hence we need make sure that current mce event
+ * is available for linux host to consume.
*/
- opal_evt = local_paca->opal_mc_evt;
- if (opal_evt->version == OpalMCE_V1 &&
- (opal_evt->severity == OpalMCE_SEV_NO_ERROR ||
- opal_evt->disposition == OpalMCE_DISPOSITION_RECOVERED))
+ if (!get_mce_event(&mce_evt, MCE_EVENT_DONTRELEASE))
+ goto out;
+
+ if (mce_evt.version == MCE_V1 &&
+ (mce_evt.severity == MCE_SEV_NO_ERROR ||
+ mce_evt.disposition == MCE_DISPOSITION_RECOVERED))
handled = 1;
+out:
+ /*
+ * If we have handled the error, then release the mce event because
+ * we will be delivering machine check to guest.
+ */
if (handled)
- opal_evt->in_use = 0;
-#endif
+ release_mce_event();
return handled;
}
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 106301f..bcbbcdc 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -19,6 +19,7 @@
#include <linux/slab.h>
#include <asm/opal.h>
#include <asm/firmware.h>
+#include <asm/mce.h>
#include "powernv.h"
@@ -245,8 +246,7 @@ int opal_put_chars(uint32_t vtermno, const char *data, int total_len)
int opal_machine_check(struct pt_regs *regs)
{
- struct opal_machine_check_event *opal_evt = get_paca()->opal_mc_evt;
- struct opal_machine_check_event evt;
+ struct machine_check_event evt;
const char *level, *sevstr, *subtype;
static const char *opal_mc_ue_types[] = {
"Indeterminate",
@@ -271,30 +271,29 @@ int opal_machine_check(struct pt_regs *regs)
"Multihit",
};
- /* Copy the event structure and release the original */
- evt = *opal_evt;
- opal_evt->in_use = 0;
+ if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
+ return 0;
/* Print things out */
- if (evt.version != OpalMCE_V1) {
+ if (evt.version != MCE_V1) {
pr_err("Machine Check Exception, Unknown event version %d !\n",
evt.version);
return 0;
}
switch(evt.severity) {
- case OpalMCE_SEV_NO_ERROR:
+ case MCE_SEV_NO_ERROR:
level = KERN_INFO;
sevstr = "Harmless";
break;
- case OpalMCE_SEV_WARNING:
+ case MCE_SEV_WARNING:
level = KERN_WARNING;
sevstr = "";
break;
- case OpalMCE_SEV_ERROR_SYNC:
+ case MCE_SEV_ERROR_SYNC:
level = KERN_ERR;
sevstr = "Severe";
break;
- case OpalMCE_SEV_FATAL:
+ case MCE_SEV_FATAL:
default:
level = KERN_ERR;
sevstr = "Fatal";
@@ -302,12 +301,12 @@ int opal_machine_check(struct pt_regs *regs)
}
printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
- evt.disposition == OpalMCE_DISPOSITION_RECOVERED ?
+ evt.disposition == MCE_DISPOSITION_RECOVERED ?
"Recovered" : "[Not recovered");
printk("%s Initiator: %s\n", level,
- evt.initiator == OpalMCE_INITIATOR_CPU ? "CPU" : "Unknown");
+ evt.initiator == MCE_INITIATOR_CPU ? "CPU" : "Unknown");
switch(evt.error_type) {
- case OpalMCE_ERROR_TYPE_UE:
+ case MCE_ERROR_TYPE_UE:
subtype = evt.u.ue_error.ue_error_type <
ARRAY_SIZE(opal_mc_ue_types) ?
opal_mc_ue_types[evt.u.ue_error.ue_error_type]
@@ -320,7 +319,7 @@ int opal_machine_check(struct pt_regs *regs)
printk("%s Physial address: %016llx\n",
level, evt.u.ue_error.physical_address);
break;
- case OpalMCE_ERROR_TYPE_SLB:
+ case MCE_ERROR_TYPE_SLB:
subtype = evt.u.slb_error.slb_error_type <
ARRAY_SIZE(opal_mc_slb_types) ?
opal_mc_slb_types[evt.u.slb_error.slb_error_type]
@@ -330,7 +329,7 @@ int opal_machine_check(struct pt_regs *regs)
printk("%s Effective address: %016llx\n",
level, evt.u.slb_error.effective_address);
break;
- case OpalMCE_ERROR_TYPE_ERAT:
+ case MCE_ERROR_TYPE_ERAT:
subtype = evt.u.erat_error.erat_error_type <
ARRAY_SIZE(opal_mc_erat_types) ?
opal_mc_erat_types[evt.u.erat_error.erat_error_type]
@@ -340,7 +339,7 @@ int opal_machine_check(struct pt_regs *regs)
printk("%s Effective address: %016llx\n",
level, evt.u.erat_error.effective_address);
break;
- case OpalMCE_ERROR_TYPE_TLB:
+ case MCE_ERROR_TYPE_TLB:
subtype = evt.u.tlb_error.tlb_error_type <
ARRAY_SIZE(opal_mc_tlb_types) ?
opal_mc_tlb_types[evt.u.tlb_error.tlb_error_type]
@@ -351,11 +350,11 @@ int opal_machine_check(struct pt_regs *regs)
level, evt.u.tlb_error.effective_address);
break;
default:
- case OpalMCE_ERROR_TYPE_UNKNOWN:
+ case MCE_ERROR_TYPE_UNKNOWN:
printk("%s Error type: Unknown\n", level);
break;
}
- return evt.severity == OpalMCE_SEV_FATAL ? 0 : 1;
+ return evt.severity == MCE_SEV_FATAL ? 0 : 1;
}
static irqreturn_t opal_interrupt(int irq, void *data)
^ permalink raw reply related
* [RFC PATCH v4 08/12] powerpc/book3s: Flush SLB/TLBs if we get SLB/TLB machine check errors on power8.
From: Mahesh J Salgaonkar @ 2013-09-16 12:41 UTC (permalink / raw)
To: linuxppc-dev, Paul Mackerras, Benjamin Herrenschmidt
Cc: Jeremy Kerr, Anton Blanchard
In-Reply-To: <20130916123908.16111.4657.stgit@mars.in.ibm.com>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
This patch handles the memory errors on power8. If we get a machine check
exception due to SLB or TLB errors, then flush SLBs/TLBs and reload SLBs to
recover.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/mce.h | 3 +++
arch/powerpc/kernel/cputable.c | 4 ++++
arch/powerpc/kernel/mce_power.c | 34 ++++++++++++++++++++++++++++++++++
3 files changed, 41 insertions(+)
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index 8157d4e..e3ffa82 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -64,4 +64,7 @@
P7_DSISR_MC_SLB_MULTIHIT | \
P7_DSISR_MC_SLB_MULTIHIT_PARITY)
+#define P8_DSISR_MC_SLB_ERRORS (P7_DSISR_MC_SLB_ERRORS | \
+ P8_DSISR_MC_ERAT_MULTIHIT_SEC)
+
#endif /* __ASM_PPC64_MCE_H__ */
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index c28cc2c..0195358 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -74,6 +74,7 @@ extern void __restore_cpu_a2(void);
extern void __flush_tlb_power7(unsigned long inval_selector);
extern void __flush_tlb_power8(unsigned long inval_selector);
extern long __machine_check_early_realmode_p7(struct pt_regs *regs);
+extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
#endif /* CONFIG_PPC64 */
#if defined(CONFIG_E500)
extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec);
@@ -462,6 +463,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.cpu_setup = __setup_cpu_power8,
.cpu_restore = __restore_cpu_power8,
.flush_tlb = __flush_tlb_power8,
+ .machine_check_early = __machine_check_early_realmode_p8,
.platform = "power8",
},
{ /* Power7 */
@@ -521,6 +523,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.cpu_setup = __setup_cpu_power8,
.cpu_restore = __restore_cpu_power8,
.flush_tlb = __flush_tlb_power8,
+ .machine_check_early = __machine_check_early_realmode_p8,
.platform = "power8",
},
{ /* Power8 */
@@ -540,6 +543,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.cpu_setup = __setup_cpu_power8,
.cpu_restore = __restore_cpu_power8,
.flush_tlb = __flush_tlb_power8,
+ .machine_check_early = __machine_check_early_realmode_p8,
.platform = "power8",
},
{ /* Cell Broadband Engine */
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 6905473..60a217f 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -148,3 +148,37 @@ long __machine_check_early_realmode_p7(struct pt_regs *regs)
/* TODO: Decode machine check reason. */
return handled;
}
+
+static long mce_handle_ierror_p8(uint64_t srr1)
+{
+ long handled = 0;
+
+ handled = mce_handle_common_ierror(srr1);
+
+ if (P7_SRR1_MC_IFETCH(srr1) == P8_SRR1_MC_IFETCH_ERAT_MULTIHIT) {
+ flush_and_reload_slb();
+ handled = 1;
+ }
+ return handled;
+}
+
+static long mce_handle_derror_p8(uint64_t dsisr)
+{
+ return mce_handle_derror(dsisr, P8_DSISR_MC_SLB_ERRORS);
+}
+
+long __machine_check_early_realmode_p8(struct pt_regs *regs)
+{
+ uint64_t srr1;
+ long handled = 1;
+
+ srr1 = regs->msr;
+
+ if (P7_SRR1_MC_LOADSTORE(srr1))
+ handled = mce_handle_derror_p8(regs->dsisr);
+ else
+ handled = mce_handle_ierror_p8(srr1);
+
+ /* TODO: Decode machine check reason. */
+ return handled;
+}
^ permalink raw reply related
* [RFC PATCH v4 07/12] powerpc/book3s: Flush SLB/TLBs if we get SLB/TLB machine check errors on power7.
From: Mahesh J Salgaonkar @ 2013-09-16 12:41 UTC (permalink / raw)
To: linuxppc-dev, Paul Mackerras, Benjamin Herrenschmidt
Cc: Jeremy Kerr, Anton Blanchard
In-Reply-To: <20130916123908.16111.4657.stgit@mars.in.ibm.com>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
If we get a machine check exception due to SLB or TLB errors, then flush
SLBs/TLBs and reload SLBs to recover. We do this in real mode before turning
on MMU. Otherwise we would run into nested machine checks.
If we get a machine check when we are in guest, then just flush the
SLBs and continue. This patch handles errors for power7. The next
patch will handle errors for power8
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/bitops.h | 5 +
arch/powerpc/include/asm/mce.h | 67 +++++++++++++++++
arch/powerpc/kernel/Makefile | 1
arch/powerpc/kernel/cputable.c | 4 +
arch/powerpc/kernel/mce_power.c | 150 +++++++++++++++++++++++++++++++++++++
5 files changed, 227 insertions(+)
create mode 100644 arch/powerpc/include/asm/mce.h
create mode 100644 arch/powerpc/kernel/mce_power.c
diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h
index 910194e..a5e9a7d 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -46,6 +46,11 @@
#include <asm/asm-compat.h>
#include <asm/synch.h>
+/* PPC bit number conversion */
+#define PPC_BITLSHIFT(be) (BITS_PER_LONG - 1 - (be))
+#define PPC_BIT(bit) (1UL << PPC_BITLSHIFT(bit))
+#define PPC_BITMASK(bs, be) ((PPC_BIT(bs) - PPC_BIT(be)) | PPC_BIT(bs))
+
/*
* clear_bit doesn't imply a memory barrier
*/
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
new file mode 100644
index 0000000..8157d4e
--- /dev/null
+++ b/arch/powerpc/include/asm/mce.h
@@ -0,0 +1,67 @@
+/*
+ * Machine check exception header file.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright 2013 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#ifndef __ASM_PPC64_MCE_H__
+#define __ASM_PPC64_MCE_H__
+
+#include <linux/bitops.h>
+
+/*
+ * Machine Check bits on power7 and power8
+ */
+#define P7_SRR1_MC_LOADSTORE(srr1) ((srr1) & PPC_BIT(42)) /* P8 too */
+
+/* SRR1 bits for machine check (On Power7 and Power8) */
+#define P7_SRR1_MC_IFETCH(srr1) ((srr1) & PPC_BITMASK(43, 45)) /* P8 too */
+
+#define P7_SRR1_MC_IFETCH_UE (0x1 << PPC_BITLSHIFT(45)) /* P8 too */
+#define P7_SRR1_MC_IFETCH_SLB_PARITY (0x2 << PPC_BITLSHIFT(45)) /* P8 too */
+#define P7_SRR1_MC_IFETCH_SLB_MULTIHIT (0x3 << PPC_BITLSHIFT(45)) /* P8 too */
+#define P7_SRR1_MC_IFETCH_SLB_BOTH (0x4 << PPC_BITLSHIFT(45))
+#define P7_SRR1_MC_IFETCH_TLB_MULTIHIT (0x5 << PPC_BITLSHIFT(45)) /* P8 too */
+#define P7_SRR1_MC_IFETCH_UE_TLB_RELOAD (0x6 << PPC_BITLSHIFT(45)) /* P8 too */
+#define P7_SRR1_MC_IFETCH_UE_IFU_INTERNAL (0x7 << PPC_BITLSHIFT(45))
+
+/* SRR1 bits for machine check (On Power8) */
+#define P8_SRR1_MC_IFETCH_ERAT_MULTIHIT (0x4 << PPC_BITLSHIFT(45))
+
+/* DSISR bits for machine check (On Power7 and Power8) */
+#define P7_DSISR_MC_UE (PPC_BIT(48)) /* P8 too */
+#define P7_DSISR_MC_UE_TABLEWALK (PPC_BIT(49)) /* P8 too */
+#define P7_DSISR_MC_ERAT_MULTIHIT (PPC_BIT(52)) /* P8 too */
+#define P7_DSISR_MC_TLB_MULTIHIT_MFTLB (PPC_BIT(53)) /* P8 too */
+#define P7_DSISR_MC_SLB_PARITY_MFSLB (PPC_BIT(55)) /* P8 too */
+#define P7_DSISR_MC_SLB_MULTIHIT (PPC_BIT(56)) /* P8 too */
+#define P7_DSISR_MC_SLB_MULTIHIT_PARITY (PPC_BIT(57)) /* P8 too */
+
+/*
+ * DSISR bits for machine check (Power8) in addition to above.
+ * Secondary DERAT Multihit
+ */
+#define P8_DSISR_MC_ERAT_MULTIHIT_SEC (PPC_BIT(54))
+
+/* SLB error bits */
+#define P7_DSISR_MC_SLB_ERRORS (P7_DSISR_MC_ERAT_MULTIHIT | \
+ P7_DSISR_MC_SLB_PARITY_MFSLB | \
+ P7_DSISR_MC_SLB_MULTIHIT | \
+ P7_DSISR_MC_SLB_MULTIHIT_PARITY)
+
+#endif /* __ASM_PPC64_MCE_H__ */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index a8619bf..a1aba53 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -39,6 +39,7 @@ obj-$(CONFIG_PPC64) += setup_64.o sys_ppc32.o \
obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o
obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o
+obj-$(CONFIG_PPC_BOOK3S_64) += mce_power.o
obj64-$(CONFIG_RELOCATABLE) += reloc_64.o
obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o
obj-$(CONFIG_PPC_A2) += cpu_setup_a2.o
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index cdbe115..c28cc2c 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -73,6 +73,7 @@ extern void __restore_cpu_power8(void);
extern void __restore_cpu_a2(void);
extern void __flush_tlb_power7(unsigned long inval_selector);
extern void __flush_tlb_power8(unsigned long inval_selector);
+extern long __machine_check_early_realmode_p7(struct pt_regs *regs);
#endif /* CONFIG_PPC64 */
#if defined(CONFIG_E500)
extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec);
@@ -443,6 +444,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.cpu_setup = __setup_cpu_power7,
.cpu_restore = __restore_cpu_power7,
.flush_tlb = __flush_tlb_power7,
+ .machine_check_early = __machine_check_early_realmode_p7,
.platform = "power7",
},
{ /* 2.07-compliant processor, i.e. Power8 "architected" mode */
@@ -479,6 +481,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.cpu_setup = __setup_cpu_power7,
.cpu_restore = __restore_cpu_power7,
.flush_tlb = __flush_tlb_power7,
+ .machine_check_early = __machine_check_early_realmode_p7,
.platform = "power7",
},
{ /* Power7+ */
@@ -498,6 +501,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.cpu_setup = __setup_cpu_power7,
.cpu_restore = __restore_cpu_power7,
.flush_tlb = __flush_tlb_power7,
+ .machine_check_early = __machine_check_early_realmode_p7,
.platform = "power7+",
},
{ /* Power8E */
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
new file mode 100644
index 0000000..6905473
--- /dev/null
+++ b/arch/powerpc/kernel/mce_power.c
@@ -0,0 +1,150 @@
+/*
+ * Machine check exception handling CPU-side for power7 and power8
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright 2013 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#undef DEBUG
+#define pr_fmt(fmt) "mce_power: " fmt
+
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <asm/mmu.h>
+#include <asm/mce.h>
+
+/* flush SLBs and reload */
+static void flush_and_reload_slb(void)
+{
+ struct slb_shadow *slb;
+ unsigned long i, n;
+
+ /* Invalidate all SLBs */
+ asm volatile("slbmte %0,%0; slbia" : : "r" (0));
+
+#ifdef CONFIG_KVM_BOOK3S_HANDLER
+ /*
+ * If machine check is hit when in guest or in transition, we will
+ * only flush the SLBs and continue.
+ */
+ if (get_paca()->kvm_hstate.in_guest)
+ return;
+#endif
+
+ /* For host kernel, reload the SLBs from shadow SLB buffer. */
+ slb = get_slb_shadow();
+ if (!slb)
+ return;
+
+ n = min_t(u32, slb->persistent, SLB_MIN_SIZE);
+
+ /* Load up the SLB entries from shadow SLB */
+ for (i = 0; i < n; i++) {
+ unsigned long rb = slb->save_area[i].esid;
+ unsigned long rs = slb->save_area[i].vsid;
+
+ rb = (rb & ~0xFFFul) | i;
+ asm volatile("slbmte %0,%1" : : "r" (rs), "r" (rb));
+ }
+}
+
+static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits)
+{
+ long handled = 1;
+
+ /*
+ * flush and reload SLBs for SLB errors and flush TLBs for TLB errors.
+ * reset the error bits whenever we handle them so that at the end
+ * we can check whether we handled all of them or not.
+ * */
+ if (dsisr & slb_error_bits) {
+ flush_and_reload_slb();
+ /* reset error bits */
+ dsisr &= ~(slb_error_bits);
+ }
+ if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) {
+ if (cur_cpu_spec && cur_cpu_spec->flush_tlb)
+ cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE);
+ /* reset error bits */
+ dsisr &= ~P7_DSISR_MC_TLB_MULTIHIT_MFTLB;
+ }
+ /* Any other errors we don't understand? */
+ if (dsisr & 0xffffffffUL)
+ handled = 0;
+
+ return handled;
+}
+
+static long mce_handle_derror_p7(uint64_t dsisr)
+{
+ return mce_handle_derror(dsisr, P7_DSISR_MC_SLB_ERRORS);
+}
+
+static long mce_handle_common_ierror(uint64_t srr1)
+{
+ long handled = 0;
+
+ switch (P7_SRR1_MC_IFETCH(srr1)) {
+ case 0:
+ break;
+ case P7_SRR1_MC_IFETCH_SLB_PARITY:
+ case P7_SRR1_MC_IFETCH_SLB_MULTIHIT:
+ /* flush and reload SLBs for SLB errors. */
+ flush_and_reload_slb();
+ handled = 1;
+ break;
+ case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
+ if (cur_cpu_spec && cur_cpu_spec->flush_tlb) {
+ cur_cpu_spec->flush_tlb(TLBIEL_INVAL_PAGE);
+ handled = 1;
+ }
+ break;
+ default:
+ break;
+ }
+
+ return handled;
+}
+
+static long mce_handle_ierror_p7(uint64_t srr1)
+{
+ long handled = 0;
+
+ handled = mce_handle_common_ierror(srr1);
+
+ if (P7_SRR1_MC_IFETCH(srr1) == P7_SRR1_MC_IFETCH_SLB_BOTH) {
+ flush_and_reload_slb();
+ handled = 1;
+ }
+ return handled;
+}
+
+long __machine_check_early_realmode_p7(struct pt_regs *regs)
+{
+ uint64_t srr1;
+ long handled = 1;
+
+ srr1 = regs->msr;
+
+ if (P7_SRR1_MC_LOADSTORE(srr1))
+ handled = mce_handle_derror_p7(regs->dsisr);
+ else
+ handled = mce_handle_ierror_p7(srr1);
+
+ /* TODO: Decode machine check reason. */
+ return handled;
+}
^ permalink raw reply related
* [RFC PATCH v4 06/12] powerpc/book3s: Add flush_tlb operation in cpu_spec.
From: Mahesh J Salgaonkar @ 2013-09-16 12:41 UTC (permalink / raw)
To: linuxppc-dev, Paul Mackerras, Benjamin Herrenschmidt
Cc: Jeremy Kerr, Anton Blanchard
In-Reply-To: <20130916123908.16111.4657.stgit@mars.in.ibm.com>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
This patch introduces flush_tlb operation in cpu_spec structure. This will
help us to invoke appropriate CPU-side flush tlb routine. This patch
adds the foundation to invoke CPU specific flush routine for respective
architectures. Currently this patch introduce flush_tlb for p7 and p8.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/cputable.h | 5 ++++
arch/powerpc/kernel/cpu_setup_power.S | 38 +++++++++++++++++++++++----------
arch/powerpc/kernel/cputable.c | 8 +++++++
arch/powerpc/kvm/book3s_hv_ras.c | 18 +++-------------
4 files changed, 44 insertions(+), 25 deletions(-)
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index d8c098e..d76e47b 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -97,6 +97,11 @@ struct cpu_spec {
*/
long (*machine_check_early)(struct pt_regs *regs);
+ /*
+ * Processor specific routine to flush tlbs.
+ */
+ void (*flush_tlb)(unsigned long inval_selector);
+
};
extern struct cpu_spec *cur_cpu_spec;
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index 18b5b9c..37d1bb0 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -29,7 +29,7 @@ _GLOBAL(__setup_cpu_power7)
mtspr SPRN_LPID,r0
mfspr r3,SPRN_LPCR
bl __init_LPCR
- bl __init_TLB
+ bl __init_tlb_power7
mtlr r11
blr
@@ -42,7 +42,7 @@ _GLOBAL(__restore_cpu_power7)
mtspr SPRN_LPID,r0
mfspr r3,SPRN_LPCR
bl __init_LPCR
- bl __init_TLB
+ bl __init_tlb_power7
mtlr r11
blr
@@ -59,7 +59,7 @@ _GLOBAL(__setup_cpu_power8)
oris r3, r3, LPCR_AIL_3@h
bl __init_LPCR
bl __init_HFSCR
- bl __init_TLB
+ bl __init_tlb_power8
bl __init_PMU_HV
mtlr r11
blr
@@ -78,7 +78,7 @@ _GLOBAL(__restore_cpu_power8)
oris r3, r3, LPCR_AIL_3@h
bl __init_LPCR
bl __init_HFSCR
- bl __init_TLB
+ bl __init_tlb_power8
bl __init_PMU_HV
mtlr r11
blr
@@ -134,15 +134,31 @@ __init_HFSCR:
mtspr SPRN_HFSCR,r3
blr
-__init_TLB:
- /*
- * Clear the TLB using the "IS 3" form of tlbiel instruction
- * (invalidate by congruence class). P7 has 128 CCs, P8 has 512
- * so we just always do 512
- */
+/*
+ * Clear the TLB using the specified IS form of tlbiel instruction
+ * (invalidate by congruence class). P7 has 128 CCs., P8 has 512.
+ *
+ * r3 = IS field
+ */
+__init_tlb_power7:
+ li r3,0xc00 /* IS field = 0b11 */
+_GLOBAL(__flush_tlb_power7)
+ li r6,128
+ mtctr r6
+ mr r7,r3 /* IS field */
+ ptesync
+2: tlbiel r7
+ addi r7,r7,0x1000
+ bdnz 2b
+ ptesync
+1: blr
+
+__init_tlb_power8:
+ li r3,0xc00 /* IS field = 0b11 */
+_GLOBAL(__flush_tlb_power8)
li r6,512
mtctr r6
- li r7,0xc00 /* IS field = 0b11 */
+ mr r7,r3 /* IS field */
ptesync
2: tlbiel r7
addi r7,r7,0x1000
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 22973a7..cdbe115 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -71,6 +71,8 @@ extern void __restore_cpu_power7(void);
extern void __setup_cpu_power8(unsigned long offset, struct cpu_spec* spec);
extern void __restore_cpu_power8(void);
extern void __restore_cpu_a2(void);
+extern void __flush_tlb_power7(unsigned long inval_selector);
+extern void __flush_tlb_power8(unsigned long inval_selector);
#endif /* CONFIG_PPC64 */
#if defined(CONFIG_E500)
extern void __setup_cpu_e5500(unsigned long offset, struct cpu_spec* spec);
@@ -440,6 +442,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.oprofile_cpu_type = "ppc64/ibm-compat-v1",
.cpu_setup = __setup_cpu_power7,
.cpu_restore = __restore_cpu_power7,
+ .flush_tlb = __flush_tlb_power7,
.platform = "power7",
},
{ /* 2.07-compliant processor, i.e. Power8 "architected" mode */
@@ -456,6 +459,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.oprofile_cpu_type = "ppc64/ibm-compat-v1",
.cpu_setup = __setup_cpu_power8,
.cpu_restore = __restore_cpu_power8,
+ .flush_tlb = __flush_tlb_power8,
.platform = "power8",
},
{ /* Power7 */
@@ -474,6 +478,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.oprofile_type = PPC_OPROFILE_POWER4,
.cpu_setup = __setup_cpu_power7,
.cpu_restore = __restore_cpu_power7,
+ .flush_tlb = __flush_tlb_power7,
.platform = "power7",
},
{ /* Power7+ */
@@ -492,6 +497,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.oprofile_type = PPC_OPROFILE_POWER4,
.cpu_setup = __setup_cpu_power7,
.cpu_restore = __restore_cpu_power7,
+ .flush_tlb = __flush_tlb_power7,
.platform = "power7+",
},
{ /* Power8E */
@@ -510,6 +516,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.oprofile_type = PPC_OPROFILE_INVALID,
.cpu_setup = __setup_cpu_power8,
.cpu_restore = __restore_cpu_power8,
+ .flush_tlb = __flush_tlb_power8,
.platform = "power8",
},
{ /* Power8 */
@@ -528,6 +535,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
.oprofile_type = PPC_OPROFILE_INVALID,
.cpu_setup = __setup_cpu_power8,
.cpu_restore = __restore_cpu_power8,
+ .flush_tlb = __flush_tlb_power8,
.platform = "power8",
},
{ /* Cell Broadband Engine */
diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c
index a353c48..5c427b4 100644
--- a/arch/powerpc/kvm/book3s_hv_ras.c
+++ b/arch/powerpc/kvm/book3s_hv_ras.c
@@ -58,18 +58,6 @@ static void reload_slb(struct kvm_vcpu *vcpu)
}
}
-/* POWER7 TLB flush */
-static void flush_tlb_power7(struct kvm_vcpu *vcpu)
-{
- unsigned long i, rb;
-
- rb = TLBIEL_INVAL_SET_LPID;
- for (i = 0; i < POWER7_TLB_SETS; ++i) {
- asm volatile("tlbiel %0" : : "r" (rb));
- rb += 1 << TLBIEL_INVAL_SET_SHIFT;
- }
-}
-
/*
* On POWER7, see if we can handle a machine check that occurred inside
* the guest in real mode, without switching to the host partition.
@@ -96,7 +84,8 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
DSISR_MC_SLB_PARITY | DSISR_MC_DERAT_MULTI);
}
if (dsisr & DSISR_MC_TLB_MULTI) {
- flush_tlb_power7(vcpu);
+ if (cur_cpu_spec && cur_cpu_spec->flush_tlb)
+ cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET_LPID);
dsisr &= ~DSISR_MC_TLB_MULTI;
}
/* Any other errors we don't understand? */
@@ -113,7 +102,8 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
reload_slb(vcpu);
break;
case SRR1_MC_IFETCH_TLBMULTI:
- flush_tlb_power7(vcpu);
+ if (cur_cpu_spec && cur_cpu_spec->flush_tlb)
+ cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET_LPID);
break;
default:
handled = 0;
^ permalink raw reply related
* [RFC PATCH v4 05/12] powerpc/book3s: Introduce a early machine check hook in cpu_spec.
From: Mahesh J Salgaonkar @ 2013-09-16 12:41 UTC (permalink / raw)
To: linuxppc-dev, Paul Mackerras, Benjamin Herrenschmidt
Cc: Jeremy Kerr, Anton Blanchard
In-Reply-To: <20130916123908.16111.4657.stgit@mars.in.ibm.com>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
This patch adds the early machine check function pointer in cputable for
CPU specific early machine check handling. The early machine handle routine
will be called in real mode to handle SLB and TLB errors. We can not reuse
the existing machine_check hook because it is always invoked in kernel
virtual mode and we would already be in trouble if we get SLB or TLB errors.
This patch just sets up a mechanism to invoke CPU specific handler. The
subsequent patches will populate the function pointer.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/cputable.h | 7 +++++++
arch/powerpc/kernel/traps.c | 7 +++++--
2 files changed, 12 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 6f3887d..d8c098e 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -90,6 +90,13 @@ struct cpu_spec {
* if the error is fatal, 1 if it was fully recovered and 0 to
* pass up (not CPU originated) */
int (*machine_check)(struct pt_regs *regs);
+
+ /*
+ * Processor specific early machine check handler which is
+ * called in real mode to handle SLB and TLB errors.
+ */
+ long (*machine_check_early)(struct pt_regs *regs);
+
};
extern struct cpu_spec *cur_cpu_spec;
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index e8d6bf1..8b0a946 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -292,8 +292,11 @@ void system_reset_exception(struct pt_regs *regs)
*/
long machine_check_early(struct pt_regs *regs)
{
- /* TODO: handle/decode machine check reason */
- return 0;
+ long handled = 0;
+
+ if (cur_cpu_spec && cur_cpu_spec->machine_check_early)
+ handled = cur_cpu_spec->machine_check_early(regs);
+ return handled;
}
#endif
^ permalink raw reply related
* [RFC PATCH v4 04/12] powerpc/book3s: Return from interrupt if coming from evil context.
From: Mahesh J Salgaonkar @ 2013-09-16 12:41 UTC (permalink / raw)
To: linuxppc-dev, Paul Mackerras, Benjamin Herrenschmidt
Cc: Jeremy Kerr, Anton Blanchard
In-Reply-To: <20130916123908.16111.4657.stgit@mars.in.ibm.com>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
We can get machine checks from any context. We need to make sure that
we handle all of them correctly. If we are coming from hypervisor user-space,
we can continue in host kernel in virtual mode to deliver the MC event.
If we got woken up from power-saving mode then we may come in with one of
the following state:
a. No state loss
b. Supervisor state loss
c. Hypervisor state loss
For (a) and (b), we go back to nap again. State (c) is fatal, keep spinning.
For all other context which we not sure of queue up the MCE event and return
from the interrupt.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
---
arch/powerpc/kernel/exceptions-64s.S | 82 ++++++++++++++++++++++++++++++++++
arch/powerpc/kernel/idle_power7.S | 1
2 files changed, 83 insertions(+)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 87a70d2..0a92ba4 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -155,6 +155,24 @@ machine_check_pSeries_1:
*/
HMT_MEDIUM_PPR_DISCARD
SET_SCRATCH0(r13) /* save r13 */
+#ifdef CONFIG_PPC_P7_NAP
+BEGIN_FTR_SECTION
+ /* Running native on arch 2.06 or later, check if we are
+ * waking up from nap. We only handle no state loss and
+ * supervisor state loss. We do -not- handle hypervisor
+ * state loss at this time.
+ */
+ mfspr r13,SPRN_SRR1
+ rlwinm. r13,r13,47-31,30,31
+ beq 9f
+
+ /* waking up from powersave (nap) state */
+ cmpwi cr1,r13,2
+ /* Total loss of HV state is fatal. let's just stay stuck here */
+ bgt cr1,.
+9:
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+#endif /* CONFIG_PPC_P7_NAP */
EXCEPTION_PROLOG_0(PACA_EXMC)
BEGIN_FTR_SECTION
b machine_check_pSeries_early
@@ -787,6 +805,70 @@ BEGIN_FTR_SECTION
bl .save_nvgprs
addi r3,r1,STACK_FRAME_OVERHEAD
bl .machine_check_early
+ ld r12,_MSR(r1)
+#ifdef CONFIG_PPC_P7_NAP
+ /*
+ * Check if thread was in power saving mode. We come here when any
+ * of the following is true:
+ * a. thread wasn't in power saving mode
+ * b. thread was in power saving mode with no state loss or
+ * supervisor state loss
+ *
+ * Go back to nap again if (b) is true.
+ */
+ rlwinm. r11,r12,47-31,30,31 /* Was it in power saving mode? */
+ beq 4f /* No, it wasn;t */
+ /* Thread was in power saving mode. Go back to nap again. */
+ cmpwi r11,2
+ bne 3f
+ /* Supervisor state loss */
+ li r0,1
+ stb r0,PACA_NAPSTATELOST(r13)
+3: MACHINE_CHECK_HANDLER_WINDUP
+ GET_PACA(r13)
+ ld r1,PACAR1(r13)
+ b .power7_enter_nap_mode
+4:
+#endif
+ /*
+ * Check if we are coming from hypervisor userspace. If yes then we
+ * continue in host kernel in V mode to deliver the MC event.
+ */
+ rldicl. r11,r12,4,63 /* See if MC hit while in HV mode. */
+ beq 5f
+ andi. r11,r12,MSR_PR /* See if coming from user. */
+ bne 9f /* continue in V mode if we are. */
+
+5:
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+ /*
+ * We are coming from kernel context. Check if we are coming from
+ * guest. if yes, then we can continue. We will fall through
+ * do_kvm_200->kvmppc_interrupt to deliver the MC event to guest.
+ */
+ lbz r11,HSTATE_IN_GUEST(r13)
+ cmpwi r11,0 /* Check if coming from guest */
+ bne 9f /* continue if we are. */
+#endif
+ /*
+ * At this point we are not sure about what context we come from.
+ * Queue up the MCE event and return from the interrupt.
+ * But before that, check if this is an un-recoverable exception.
+ * If yes, then stay on emergency stack and panic.
+ */
+ andi. r11,r12,MSR_RI
+ bne 2f
+1: addi r3,r1,STACK_FRAME_OVERHEAD
+ bl .unrecoverable_exception
+ b 1b
+2:
+ /*
+ * Return from MC interrupt.
+ * TODO: Queue up the MCE event so that we can log it later.
+ */
+ MACHINE_CHECK_HANDLER_WINDUP
+ rfid
+9:
/* Deliver the machine check to host kernel in V mode. */
MACHINE_CHECK_HANDLER_WINDUP
b machine_check_pSeries
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index e11863f..c4b384d 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -84,6 +84,7 @@ _GLOBAL(power7_nap)
std r9,_MSR(r1)
std r1,PACAR1(r13)
+_GLOBAL(power7_enter_nap_mode)
#ifdef CONFIG_KVM_BOOK3S_64_HV
/* Tell KVM we're napping */
li r4,KVM_HWTHREAD_IN_NAP
^ permalink raw reply related
* [RFC PATCH v4 03/12] powerpc/book3s: handle machine check in Linux host.
From: Mahesh J Salgaonkar @ 2013-09-16 12:41 UTC (permalink / raw)
To: linuxppc-dev, Paul Mackerras, Benjamin Herrenschmidt
Cc: Jeremy Kerr, Anton Blanchard
In-Reply-To: <20130916123908.16111.4657.stgit@mars.in.ibm.com>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Move machine check entry point into Linux. So far we were dependent on
firmware to decode MCE error details and handover the high level info to OS.
This patch introduces early machine check routine that saves the MCE
information (srr1, srr0, dar and dsisr) to the emergency stack. We allocate
stack frame on emergency stack and set the r1 accordingly. This allows us to be
prepared to take another exception without loosing context. One thing to note
here that, if we get another machine check while ME bit is off then we risk a
checkstop. Hence we restrict ourselves to save only MCE information and
register saved on PACA_EXMC save are before we turn the ME bit on. We use
paca->in_mce flag to differentiate between first entry and nested machine check
entry which helps proper use of emergency stack. We increment paca->in_mce
every time we enter in early machine check handler and decrement it while
leaving. When we enter machine check early handler first time (paca->in_mce ==
0), we are sure nobody is using MC emergency stack and allocate a stack frame
at the start of the emergency stack. During subsequent entry (paca->in_mce >
0), we know that r1 points inside emergency stack and we allocate separate
stack frame accordingly. This prevents us from clobbering MCE information
during nested machine checks.
The early machine check handler changes are placed under CPU_FTR_HVMODE
section. This makes sure that the early machine check handler will get executed
only in hypervisor kernel.
This is the code flow:
Machine Check Interrupt
|
V
0x200 vector ME=0, IR=0, DR=0
|
V
+-----------------------------------------------+
|machine_check_pSeries_early: | ME=0, IR=0, DR=0
| Alloc frame on emergency stack |
| Save srr1, srr0, dar and dsisr on stack |
+-----------------------------------------------+
|
(ME=1, IR=0, DR=0, RFID)
|
V
machine_check_handle_early ME=1, IR=0, DR=0
|
V
+-----------------------------------------------+
| machine_check_early (r3=pt_regs) | ME=1, IR=0, DR=0
| Things to do: (in next patches) |
| Flush SLB for SLB errors |
| Flush TLB for TLB errors |
| Decode and save MCE info |
+-----------------------------------------------+
|
(Fall through existing exception handler routine.)
|
V
machine_check_pSerie ME=1, IR=0, DR=0
|
(ME=1, IR=1, DR=1, RFID)
|
V
machine_check_common ME=1, IR=1, DR=1
.
.
.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
---
arch/powerpc/kernel/asm-offsets.c | 4 +
arch/powerpc/kernel/exceptions-64s.S | 111 ++++++++++++++++++++++++++++++++++
arch/powerpc/kernel/traps.c | 12 ++++
3 files changed, 127 insertions(+)
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 8207459..e0e8ebb 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -238,6 +238,10 @@ int main(void)
DEFINE(PACA_DTL_RIDX, offsetof(struct paca_struct, dtl_ridx));
#endif /* CONFIG_PPC_STD_MMU_64 */
DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp));
+#ifdef CONFIG_PPC_BOOK3S_64
+ DEFINE(PACAMCEMERGSP, offsetof(struct paca_struct, mc_emergency_sp));
+ DEFINE(PACA_IN_MCE, offsetof(struct paca_struct, in_mce));
+#endif
DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));
DEFINE(PACAKEXECSTATE, offsetof(struct paca_struct, kexec_state));
DEFINE(PACA_STARTTIME, offsetof(struct paca_struct, starttime));
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 902ca3c..87a70d2 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -156,7 +156,11 @@ machine_check_pSeries_1:
HMT_MEDIUM_PPR_DISCARD
SET_SCRATCH0(r13) /* save r13 */
EXCEPTION_PROLOG_0(PACA_EXMC)
+BEGIN_FTR_SECTION
+ b machine_check_pSeries_early
+FTR_SECTION_ELSE
b machine_check_pSeries_0
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
. = 0x300
.globl data_access_pSeries
@@ -404,6 +408,64 @@ denorm_exception_hv:
.align 7
/* moved from 0x200 */
+machine_check_pSeries_early:
+BEGIN_FTR_SECTION
+ EXCEPTION_PROLOG_1(PACA_EXMC, NOTEST, 0x200)
+ /*
+ * Register contents:
+ * R13 = PACA
+ * R9 = CR
+ * Original R9 to R13 is saved on PACA_EXMC
+ *
+ * Switch to mc_emergency stack and handle re-entrancy (though we
+ * currently don't test for overflow). Save MCE registers srr1,
+ * srr0, dar and dsisr and then set ME=1
+ *
+ * We use paca->in_mce to check whether this is the first entry or
+ * nested machine check. We increment paca->in_mce to track nested
+ * machine checks.
+ *
+ * If this is the first entry then set stack pointer to
+ * paca->mc_emergency_sp, otherwise r1 is already pointing to
+ * stack frame on mc_emergency stack.
+ *
+ * NOTE: We are here with MSR_ME=0 (off), which means we risk a
+ * checkstop if we get another machine check exception before we do
+ * rfid with MSR_ME=1.
+ */
+ mr r11,r1 /* Save r1 */
+ lhz r10,PACA_IN_MCE(r13)
+ cmpwi r10,0 /* Are we in nested machine check */
+ bne 0f /* Yes, we are. */
+ /* First machine check entry */
+ ld r1,PACAMCEMERGSP(r13) /* Use MC emergency stack */
+0: subi r1,r1,INT_FRAME_SIZE /* alloc stack frame */
+ addi r10,r10,1 /* increment paca->in_mce */
+ sth r10,PACA_IN_MCE(r13)
+ std r11,GPR1(r1) /* Save r1 on the stack. */
+ std r11,0(r1) /* make stack chain pointer */
+ mfspr r11,SPRN_SRR0 /* Save SRR0 */
+ std r11,_NIP(r1)
+ mfspr r11,SPRN_SRR1 /* Save SRR1 */
+ std r11,_MSR(r1)
+ mfspr r11,SPRN_DAR /* Save DAR */
+ std r11,_DAR(r1)
+ mfspr r11,SPRN_DSISR /* Save DSISR */
+ std r11,_DSISR(r1)
+ std r9,_CCR(r1) /* Save CR in stackframe */
+ /* Save r9 through r13 from EXMC save area to stack frame. */
+ EXCEPTION_PROLOG_COMMON_2(PACA_EXMC)
+ mfmsr r11 /* get MSR value */
+ ori r11,r11,MSR_ME /* turn on ME bit */
+ ori r11,r11,MSR_RI /* turn on RI bit */
+ ld r12,PACAKBASE(r13) /* get high part of &label */
+ LOAD_HANDLER(r12, machine_check_handle_early)
+ mtspr SPRN_SRR0,r12
+ mtspr SPRN_SRR1,r11
+ rfid
+ b . /* prevent speculative execution */
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
+
machine_check_pSeries:
.globl machine_check_fwnmi
machine_check_fwnmi:
@@ -681,6 +743,55 @@ machine_check_common:
bl .machine_check_exception
b .ret_from_except
+#define MACHINE_CHECK_HANDLER_WINDUP \
+ /* Clear MSR_RI before setting SRR0 and SRR1. */\
+ li r0,MSR_RI; \
+ mfmsr r9; /* get MSR value */ \
+ andc r9,r9,r0; \
+ mtmsrd r9,1; /* Clear MSR_RI */ \
+ /* Move original SRR0 and SRR1 into the respective regs */ \
+ ld r9,_MSR(r1); \
+ mtspr SPRN_SRR1,r9; \
+ ld r3,_NIP(r1); \
+ mtspr SPRN_SRR0,r3; \
+ ld r9,_CTR(r1); \
+ mtctr r9; \
+ ld r9,_XER(r1); \
+ mtxer r9; \
+ ld r9,_LINK(r1); \
+ mtlr r9; \
+ REST_GPR(0, r1); \
+ REST_8GPRS(2, r1); \
+ REST_GPR(10, r1); \
+ ld r11,_CCR(r1); \
+ mtcr r11; \
+ /* Decrement paca->in_mce. */ \
+ lhz r12,PACA_IN_MCE(r13); \
+ subi r12,r12,1; \
+ sth r12,PACA_IN_MCE(r13); \
+ REST_GPR(11, r1); \
+ REST_2GPRS(12, r1); \
+ /* restore original r1. */ \
+ ld r1,GPR1(r1)
+
+ /*
+ * Handle machine check early in real mode. We come here with
+ * ME=1, MMU (IR=0 and DR=0) off and using MC emergency stack.
+ */
+ .align 7
+ .globl machine_check_handle_early
+machine_check_handle_early:
+BEGIN_FTR_SECTION
+ std r0,GPR0(r1) /* Save r0 */
+ EXCEPTION_PROLOG_COMMON_3(0x200)
+ bl .save_nvgprs
+ addi r3,r1,STACK_FRAME_OVERHEAD
+ bl .machine_check_early
+ /* Deliver the machine check to host kernel in V mode. */
+ MACHINE_CHECK_HANDLER_WINDUP
+ b machine_check_pSeries
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
+
STD_EXCEPTION_COMMON_ASYNC(0x500, hardware_interrupt, do_IRQ)
STD_EXCEPTION_COMMON_ASYNC(0x900, decrementer, .timer_interrupt)
STD_EXCEPTION_COMMON(0x980, hdecrementer, .hdec_interrupt)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index e435bc0..e8d6bf1 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -284,6 +284,18 @@ void system_reset_exception(struct pt_regs *regs)
/* What should we do here? We could issue a shutdown or hard reset. */
}
+
+/*
+ * This function is called in real mode. Strictly no printk's please.
+ *
+ * regs->nip and regs->msr contains srr0 and ssr1.
+ */
+long machine_check_early(struct pt_regs *regs)
+{
+ /* TODO: handle/decode machine check reason */
+ return 0;
+}
+
#endif
/*
^ permalink raw reply related
* [RFC PATCH v4 02/12] powerpc/book3s: Introduce exclusive emergency stack for machine check exception.
From: Mahesh J Salgaonkar @ 2013-09-16 12:41 UTC (permalink / raw)
To: linuxppc-dev, Paul Mackerras, Benjamin Herrenschmidt
Cc: Jeremy Kerr, Anton Blanchard
In-Reply-To: <20130916123908.16111.4657.stgit@mars.in.ibm.com>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
This patch introduces exclusive emergency stack for machine check exception.
We use emergency stack to handle machine check exception so that we can save
MCE information (srr1, srr0, dar and dsisr) before turning on ME bit and be
ready for re-entrancy. This helps us to prevent clobbering of MCE information
in case of nested machine checks.
The reason for using emergency stack over normal kernel stack is that the
machine check might occur in the middle of setting up a stack frame which may
result into improper use of kernel stack.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/paca.h | 9 +++++++++
arch/powerpc/kernel/setup_64.c | 10 +++++++++-
arch/powerpc/xmon/xmon.c | 4 ++++
3 files changed, 22 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 77c91e7..b4ca4e9 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -147,6 +147,15 @@ struct paca_struct {
*/
struct opal_machine_check_event *opal_mc_evt;
#endif
+#ifdef CONFIG_PPC_BOOK3S_64
+ /* Exclusive emergency stack pointer for machine check exception. */
+ void *mc_emergency_sp;
+ /*
+ * Flag to check whether we are in machine check early handler
+ * and already using emergency stack.
+ */
+ u16 in_mce;
+#endif
/* Stuff for accurate time accounting */
u64 user_time; /* accumulated usermode TB ticks */
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 389fb807..6f96af0 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -529,7 +529,8 @@ static void __init exc_lvl_early_init(void)
/*
* Stack space used when we detect a bad kernel stack pointer, and
- * early in SMP boots before relocation is enabled.
+ * early in SMP boots before relocation is enabled. Exclusive emergency
+ * stack for machine checks.
*/
static void __init emergency_stack_init(void)
{
@@ -552,6 +553,13 @@ static void __init emergency_stack_init(void)
sp = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit);
sp += THREAD_SIZE;
paca[i].emergency_sp = __va(sp);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+ /* emergency stack for machine check exception handling. */
+ sp = memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit);
+ sp += THREAD_SIZE;
+ paca[i].mc_emergency_sp = __va(sp);
+#endif
}
}
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 96bf5bd..5f17adb 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -2044,6 +2044,10 @@ static void dump_one_paca(int cpu)
DUMP(p, stab_addr, "lx");
#endif
DUMP(p, emergency_sp, "p");
+#ifdef CONFIG_PPC_BOOK3S_64
+ DUMP(p, mc_emergency_sp, "p");
+ DUMP(p, in_mce, "x");
+#endif
DUMP(p, data_offset, "lx");
DUMP(p, hw_cpu_id, "x");
DUMP(p, cpu_start, "x");
^ permalink raw reply related
* [RFC PATCH v4 01/12] powerpc/book3s: Split the common exception prolog logic into two section.
From: Mahesh J Salgaonkar @ 2013-09-16 12:41 UTC (permalink / raw)
To: linuxppc-dev, Paul Mackerras, Benjamin Herrenschmidt
Cc: Jeremy Kerr, Anton Blanchard
In-Reply-To: <20130916123908.16111.4657.stgit@mars.in.ibm.com>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
This patch splits the common exception prolog logic into three parts to
facilitate reuse of existing code in the next patch. This patch also
re-arranges few instructions in such a way that the second part now deals
with saving register values from paca save area to stack frame, and
the third part deals with saving current register values to stack frame.
The second and third part will be reused in the machine check exception
routine in the subsequent patch.
Please note that this patch does not introduce or change existing code
logic. Instead it is just a code movement and instruction re-ordering.
Patch Acked-by Paul. But made some minor modification (explained above) to
address Paul's comment in the later patch(3).
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
---
arch/powerpc/include/asm/exception-64s.h | 21 ++++++++++++++-------
1 file changed, 14 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 07ca627..94ab2d2 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -281,9 +281,12 @@ do_kvm_##n: \
beq 4f; /* if from kernel mode */ \
ACCOUNT_CPU_USER_ENTRY(r9, r10); \
SAVE_PPR(area, r9, r10); \
-4: std r2,GPR2(r1); /* save r2 in stackframe */ \
- SAVE_4GPRS(3, r1); /* save r3 - r6 in stackframe */ \
- SAVE_2GPRS(7, r1); /* save r7, r8 in stackframe */ \
+4: EXCEPTION_PROLOG_COMMON_2(area) \
+ EXCEPTION_PROLOG_COMMON_3(n) \
+ ACCOUNT_STOLEN_TIME
+
+/* Save original regs values from save area to stack frame. */
+#define EXCEPTION_PROLOG_COMMON_2(area) \
ld r9,area+EX_R9(r13); /* move r9, r10 to stackframe */ \
ld r10,area+EX_R10(r13); \
std r9,GPR9(r1); \
@@ -298,9 +301,14 @@ do_kvm_##n: \
ld r10,area+EX_CFAR(r13); \
std r10,ORIG_GPR3(r1); \
END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 66); \
- GET_LR(r9,area); /* Get LR, later save to stack */ \
+ GET_LR(r9,area); /* Save LR to stack */ \
+ std r9,_LINK(r1);
+
+#define EXCEPTION_PROLOG_COMMON_3(n) \
+ std r2,GPR2(r1); /* save r2 in stackframe */ \
+ SAVE_4GPRS(3, r1); /* save r3 - r6 in stackframe */ \
+ SAVE_2GPRS(7, r1); /* save r7, r8 in stackframe */ \
ld r2,PACATOC(r13); /* get kernel TOC into r2 */ \
- std r9,_LINK(r1); \
mfctr r10; /* save CTR in stackframe */ \
std r10,_CTR(r1); \
lbz r10,PACASOFTIRQEN(r13); \
@@ -312,8 +320,7 @@ do_kvm_##n: \
li r10,0; \
ld r11,exception_marker@toc(r2); \
std r10,RESULT(r1); /* clear regs->result */ \
- std r11,STACK_FRAME_OVERHEAD-16(r1); /* mark the frame */ \
- ACCOUNT_STOLEN_TIME
+ std r11,STACK_FRAME_OVERHEAD-16(r1); /* mark the frame */
/*
* Exception vectors.
^ permalink raw reply related
* [RFC PATCH v4 00/12] Machine check handling in linux host.
From: Mahesh J Salgaonkar @ 2013-09-16 12:40 UTC (permalink / raw)
To: linuxppc-dev, Paul Mackerras, Benjamin Herrenschmidt
Cc: Jeremy Kerr, Anton Blanchard
Hi,
Please find the patch set that performs the machine check handling inside linux
host. The design is to be able to handle re-entrancy so that we do not clobber
the machine check information during nested machine check interrupt.
The patch 2 introduces separate emergency stack in paca structure exclusively
for machine check exception handling. Patch 3 implements the logic to save the
raw MCE info onto the emergency stack and prepares to take another exception.
Patch 5 and 6 adds CPU-side hooks for early machine check handler and TLB
flush. The patch 7 and 8 is responsible to detect SLB/TLB errors and flush
them off in the real mode. The patch 9 implements the logic to decode and save
high level MCE information to per cpu buffer without clobbering. Patch 10
implements mechanism to queue up MCE event in cases where early handler
can not deliver the event to host kernel right away. The patch 12
adds the basic error handling to the high level C code with MMU on.
I have tested SLB multihit, MC coming from opal context on powernv.
Please review and let me know your comments.
Changes in v4:
- Split the prolog common macro in 3 parts in patch 1.
- Save the regs from EXMC save area to stack before turning on ME bit.
- Set/Clear MSR_RI bit at right places.
- Handle a situation where machine check comes in when thread was in power
saving mode.
- Queue up the MCE event and return from the interrupt if MC is hit during
context which we are not sure of. Go to kernel in V mode only if we
are coming from hypervisor userspace (HV=1, PR=1).
Changes in v3:
- Rebased to v3.11-rc7
- Handle MCE coming from opal context, secondary thread nap and return
from interrupt. Queue up the MCE event in this scenario and log it
later during syscall exit path.
Changes in v2:
- Moved early machine check handling code under CPU_FTR_HVMODE section.
This makes sure that the early machine check handler will get executed
only in hypervisor kernel.
- Add dedicated emergency stack for machine check so that we don't end up
disturbing others who use same emergency stack.
- Fixed the machine check early handle where it used to assume that r1 always
contains the valid stack pointer.
- Fixed an issue where per-cpu mce_nest_count variable underflows when kvm
fails to handle MC error and exit the guest.
- Fixed the code to restore r13 while before exiting early handler.
Thanks,
-Mahesh.
---
Mahesh Salgaonkar (12):
powerpc/book3s: Split the common exception prolog logic into two section.
powerpc/book3s: Introduce exclusive emergency stack for machine check exception.
powerpc/book3s: handle machine check in Linux host.
powerpc/book3s: Return from interrupt if coming from evil context.
powerpc/book3s: Introduce a early machine check hook in cpu_spec.
powerpc/book3s: Add flush_tlb operation in cpu_spec.
powerpc/book3s: Flush SLB/TLBs if we get SLB/TLB machine check errors on power7.
powerpc/book3s: Flush SLB/TLBs if we get SLB/TLB machine check errors on power8.
powerpc/book3s: Decode and save machine check event.
powerpc/book3s: Queue up and process delayed MCE events.
powerpc/powernv: Remove machine check handling in OPAL.
powerpc/powernv: Machine check exception handling.
arch/powerpc/include/asm/bitops.h | 5
arch/powerpc/include/asm/cputable.h | 12 +
arch/powerpc/include/asm/exception-64s.h | 21 +-
arch/powerpc/include/asm/mce.h | 198 +++++++++++++++++
arch/powerpc/include/asm/paca.h | 9 +
arch/powerpc/kernel/Makefile | 1
arch/powerpc/kernel/asm-offsets.c | 4
arch/powerpc/kernel/cpu_setup_power.S | 38 ++-
arch/powerpc/kernel/cputable.c | 16 +
arch/powerpc/kernel/entry_64.S | 5
arch/powerpc/kernel/exceptions-64s.S | 196 +++++++++++++++++
arch/powerpc/kernel/idle_power7.S | 1
arch/powerpc/kernel/mce.c | 345 ++++++++++++++++++++++++++++++
arch/powerpc/kernel/mce_power.c | 284 +++++++++++++++++++++++++
arch/powerpc/kernel/setup_64.c | 10 +
arch/powerpc/kernel/traps.c | 15 +
arch/powerpc/kvm/book3s_hv_ras.c | 50 ++--
arch/powerpc/platforms/powernv/opal.c | 161 ++++----------
arch/powerpc/xmon/xmon.c | 4
19 files changed, 1220 insertions(+), 155 deletions(-)
create mode 100644 arch/powerpc/include/asm/mce.h
create mode 100644 arch/powerpc/kernel/mce.c
create mode 100644 arch/powerpc/kernel/mce_power.c
--
-Mahesh
^ permalink raw reply
* Re: [PATCH 7/8][v4] power: implement is_instr_load_store().
From: Tom Musta @ 2013-09-16 12:22 UTC (permalink / raw)
To: Sukadev Bhattiprolu, linuxppc-dev
In-Reply-To: <1379119755-21025-8-git-send-email-sukadev@linux.vnet.ibm.com>
On 9/13/2013 7:49 PM, Sukadev Bhattiprolu wrote:
> Implement is_instr_load_store() to detect whether a given instruction
> is one of the fixed-point or floating-point load/store instructions.
> This function will be used in a follow-on patch to save memory hierarchy
> information of the load/store.
>
>
> +/*
> + * Values of bits 21:30 of Fixed-point and Floating-point Load and Store
> + * instructions.
> + *
> + * Reference: PowerISA_V2.06B_Public.pdf, Sections 3.3.2 through 3.3.6 and
> + * 4.6.2 through 4.6.4.
> + */
> +#define x_lbzx 87
> +#define x_lbzux 119
> +#define x_lhzx 279
> <snip>
> +
> +static unsigned int x_form_load_store[] = {
> + x_lbzx, x_lbzux, x_lhzx, x_lhzux, x_lhax,
> + x_lhaux, x_lwzx, x_lwzux, x_lwax, x_lwaux,
> + x_ldx, x_ldux, x_stbx, x_stbux, x_sthx,
> + x_sthux, x_stwx, x_stwux, x_stdx, x_stdux,
> + x_lhbrx, x_lwbrx, x_sthbrx, x_stwbrx, x_ldbrx,
> + x_stdbrx, x_lswi, x_lswx, x_stswi, x_stswx,
> + x_lfsx, x_lfsux, x_lfdx, x_lfdux, x_lfiwax,
> + x_lfiwzx, x_stfsx, x_stfsux, x_stfdx, x_stfdux,
> + x_stfiwax, x_lfdpx, x_stfdpx
> +};
> +
> <snip>
> +
>
>
Can you explain why this function only covers fixed point and floating
point instructions? I.e., why did you skip Altivec and VSX?
^ permalink raw reply
* Re: [PATCH] powerpc/mpc85xx:Add initial device tree support of T104x
From: Valentin Longchamp @ 2013-09-16 12:10 UTC (permalink / raw)
To: Kumar Gala
Cc: Poonam Aggrwal, Priyanka Jain, scottwood@freescale.com,
Varun Sethi, linuxppc-dev@lists.ozlabs.org, Prabhakar Kushwaha
In-Reply-To: <1B0AEBE4-FAE3-405C-8BAE-CACF5B12CB59@kernel.crashing.org>
On 09/13/2013 04:53 PM, Kumar Gala wrote:
> On Sep 13, 2013, at 4:14 AM, Valentin Longchamp wrote:
>> On 09/11/2013 08:58 AM, Prabhakar Kushwaha wrote:
>>> +
>>> +&pci0 {
>>> + compatible = "fsl,t1042-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie";
>>> + device_type = "pci";
>>> + #size-cells = <2>;
>>> + #address-cells = <3>;
>>> + bus-range = <0x0 0xff>;
>>> + interrupts = <20 2 0 0>;
>>> + fsl,iommu-parent = <&pamu0>;
>>> + pcie@0 {
>>> + reg = <0 0 0 0 0>;
>>> + #interrupt-cells = <1>;
>>> + #size-cells = <2>;
>>> + #address-cells = <3>;
>>> + device_type = "pci";
>>> + interrupts = <20 2 0 0>;
>>> + interrupt-map-mask = <0xf800 0 0 7>;
>>> + interrupt-map = <
>>> + /* IDSEL 0x0 */
>>> + 0000 0 0 1 &mpic 40 1 0 0
>>> + 0000 0 0 2 &mpic 1 1 0 0
>>> + 0000 0 0 3 &mpic 2 1 0 0
>>> + 0000 0 0 4 &mpic 3 1 0 0
>>> + >;
>>> + };
>>> +};
>>> +
>>> +&pci1 {
>>> + compatible = "fsl,t1042-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie";
>>> + device_type = "pci";
>>> + #size-cells = <2>;
>>> + #address-cells = <3>;
>>> + bus-range = <0 0xff>;
>>> + interrupts = <21 2 0 0>;
>>> + fsl,iommu-parent = <&pamu0>;
>>> + pcie@0 {
>>> + reg = <0 0 0 0 0>;
>>> + #interrupt-cells = <1>;
>>> + #size-cells = <2>;
>>> + #address-cells = <3>;
>>> + device_type = "pci";
>>> + interrupts = <21 2 0 0>;
>>> + interrupt-map-mask = <0xf800 0 0 7>;
>>> + interrupt-map = <
>>> + /* IDSEL 0x0 */
>>> + 0000 0 0 1 &mpic 41 1 0 0
>>> + 0000 0 0 2 &mpic 5 1 0 0
>>> + 0000 0 0 3 &mpic 6 1 0 0
>>> + 0000 0 0 4 &mpic 7 1 0 0
>>> + >;
>>> + };
>>> +};
>>> +
>>> +&pci2 {
>>> + compatible = "fsl,t1042-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie";
>>> + device_type = "pci";
>>> + #size-cells = <2>;
>>> + #address-cells = <3>;
>>> + bus-range = <0x0 0xff>;
>>> + interrupts = <22 2 0 0>;
>>> + fsl,iommu-parent = <&pamu0>;
>>> + pcie@0 {
>>> + reg = <0 0 0 0 0>;
>>> + #interrupt-cells = <1>;
>>> + #size-cells = <2>;
>>> + #address-cells = <3>;
>>> + device_type = "pci";
>>> + interrupts = <22 2 0 0>;
>>> + interrupt-map-mask = <0xf800 0 0 7>;
>>> + interrupt-map = <
>>> + /* IDSEL 0x0 */
>>> + 0000 0 0 1 &mpic 42 1 0 0
>>> + 0000 0 0 2 &mpic 9 1 0 0
>>> + 0000 0 0 3 &mpic 10 1 0 0
>>> + 0000 0 0 4 &mpic 11 1 0 0
>>> + >;
>>> + };
>>> +};
>>> +
>>> +&pci3 {
>>> + compatible = "fsl,t1042-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie";
>>> + device_type = "pci";
>>> + #size-cells = <2>;
>>> + #address-cells = <3>;
>>> + bus-range = <0x0 0xff>;
>>> + interrupts = <23 2 0 0>;
>>> + fsl,iommu-parent = <&pamu0>;
>>> + pcie@0 {
>>> + reg = <0 0 0 0 0>;
>>> + #interrupt-cells = <1>;
>>> + #size-cells = <2>;
>>> + #address-cells = <3>;
>>> + device_type = "pci";
>>> + interrupts = <23 2 0 0>;
>>> + interrupt-map-mask = <0xf800 0 0 7>;
>>> + interrupt-map = <
>>> + /* IDSEL 0x0 */
>>> + 0000 0 0 1 &mpic 43 1 0 0
>>> + 0000 0 0 2 &mpic 0 1 0 0
>>> + 0000 0 0 3 &mpic 4 1 0 0
>>> + 0000 0 0 4 &mpic 8 1 0 0
>>> + >;
>>> + };
>>> +};
>>> +
>>
>> The above 4 nodes have the consequence that it will then be mandatory that a
>> board support .dts file that would like to inlcude the SOC-NAMEsi-post.dtsi
>> defines the pci0, pci1, pci2, pci3 aliases.
>>
>> Now it is possible that a board does not implement pci1 for instance. So its
>> .dts file would ideally not define a node for it, and thus not define the
>> respective alias. However, this triggers this dtc compile error (which is correct):
>>
>>> [chlongv1@chber1-10533x linux-km]$ make kmp204x.dtb
>>> DTC arch/powerpc/boot/kmp204x.dtb
>>> Error: arch/powerpc/boot/dts/fsl/p2041si-post.dtsi:98.2-3 label or path, 'pci1', not found
>>> FATAL ERROR: Syntax error parsing input tree
>>> make[1]: *** [arch/powerpc/boot/kmp204x.dtb] Error 1
>>> make: *** [kmp204x.dtb] Error 2
>>
>> The solution I have found is to define a "dummy" disabled node so that I can
>> define the alias, but I am not really happy about this:
>>
>>> pci1: pcie@ffe201000 {
>>> status = "disabled";
>>> };
>>
>> I am here missing something obvious or shouldn't it be possible that such .dtsi
>> files allow not to define unused/unnecessary nodes ?
>
> Isn't this correct, that you are disabling the PCIe1 interface on the SoC for your board?
>
Yes it is correct. So this confirms that a board .dts file must disable all not
used interfaces/peripherals with such a "disabled" node.
I just wanted to be sure that this was the correct way of doing things and that
I had not missed a "better" way (where you don't need to define such "disabled"
nodes in .dts files).
Valentin
^ permalink raw reply
* Re: [PATCH v2 2/6] PCI/MSI: Factor out pci_get_msi_cap() interface
From: Alexander Gordeev @ 2013-09-16 10:22 UTC (permalink / raw)
To: Benjamin Herrenschmidt
Cc: linuxppc-dev, linux-pci@vger.kernel.org, Joerg Roedel,
x86@kernel.org, linux-kernel@vger.kernel.org,
linux-ide@vger.kernel.org, Jan Beulich, Tejun Heo, Bjorn Helgaas,
Ingo Molnar
In-Reply-To: <20130909152044.GA24962@dhcp-26-207.brq.redhat.com>
On Mon, Sep 09, 2013 at 05:20:44PM +0200, Alexander Gordeev wrote:
> On Fri, Sep 06, 2013 at 05:32:05PM -0600, Bjorn Helgaas wrote:
> > I propose that you rework it that way, and at least find out what
> > (if anything) would break if we do that. Or maybe we just give up
> > some optimization; it would be nice to quantify that, too.
>
> Hi Bjorn,
>
> The series is what it seems a direction to take.
>
> Looks like we need PPC folks to agree on the quota check update
> for pSeries (yes, they do bail out with a positive return value
> from arch_msi_check_device()):
Hi Ben,
An initiative to simplify MSI/MSI-X allocation interface is brewing.
It seems pSeries quota thing is an obstacle. If it could be given up
(patch 2/9).
Thanks!
--
Regards,
Alexander Gordeev
agordeev@redhat.com
^ permalink raw reply
* Re: [PATCH v9 2/3] DMA: Freescale: Add new 8-channel DMA engine device tree nodes
From: Hongbo Zhang @ 2013-09-16 10:25 UTC (permalink / raw)
To: Mark Rutland
Cc: devicetree@vger.kernel.org, ian.campbell@citrix.com, Pawel Moll,
swarren@wwwdotorg.org, vinod.koul@intel.com,
linux-kernel@vger.kernel.org, rob.herring@calxeda.com,
djbw@fb.com, linuxppc-dev@lists.ozlabs.org
In-Reply-To: <20130912171541.GH22013@e106331-lin.cambridge.arm.com>
On 09/13/2013 01:15 AM, Mark Rutland wrote:
> On Tue, Sep 03, 2013 at 10:01:50AM +0100, Hongbo Zhang wrote:
>> On 09/02/2013 11:58 PM, Mark Rutland wrote:
>>> Hi,
>>>
>>> On Fri, Aug 30, 2013 at 12:26:19PM +0100, hongbo.zhang@freescale.com wrote:
>>>> From: Hongbo Zhang <hongbo.zhang@freescale.com>
>>>>
>>>> Freescale QorIQ T4 and B4 introduce new 8-channel DMA engines, this patch adds
>>>> the device tree nodes for them.
>>>>
>>>> Signed-off-by: Hongbo Zhang <hongbo.zhang@freescale.com>
>>>> ---
>>>> .../devicetree/bindings/powerpc/fsl/dma.txt | 67 ++++++++++++++++
>>>> arch/powerpc/boot/dts/fsl/b4si-post.dtsi | 4 +-
>>>> arch/powerpc/boot/dts/fsl/elo3-dma-0.dtsi | 82 ++++++++++++++++++++
>>>> arch/powerpc/boot/dts/fsl/elo3-dma-1.dtsi | 82 ++++++++++++++++++++
>>>> arch/powerpc/boot/dts/fsl/t4240si-post.dtsi | 4 +-
>>>> 5 files changed, 235 insertions(+), 4 deletions(-)
>>>> create mode 100644 arch/powerpc/boot/dts/fsl/elo3-dma-0.dtsi
>>>> create mode 100644 arch/powerpc/boot/dts/fsl/elo3-dma-1.dtsi
>>>>
>>>> diff --git a/Documentation/devicetree/bindings/powerpc/fsl/dma.txt b/Documentation/devicetree/bindings/powerpc/fsl/dma.txt
>>>> index ddf17af..332ac77 100644
>>>> --- a/Documentation/devicetree/bindings/powerpc/fsl/dma.txt
>>>> +++ b/Documentation/devicetree/bindings/powerpc/fsl/dma.txt
>>>> @@ -126,6 +126,73 @@ Example:
>>>> };
>>>> };
>>>>
>>>> +** Freescale Elo3 DMA Controller
>>>> + This is EloPlus controller with 8 channels, used in Freescale Txxx and Bxxx
>>> I was under the impression EloPlus was the previous revision. Should
>>> that say Elo3, or is Elo3 considered to be an EloPlus implementation?
>> In this patch 1/3 I revise the doc to make it clear we have Elo and
>> EloPlus, and I'm adding another new Elo3. Yes the only difference
>> between Elo3 and EloPlus is channel numbers(8 channels vs 4 channels),
>> so we can call "Elo3 is an 8-channel EloPlus"
> Ok.
>
>>>> + series chips, such as t1040, t4240, b4860.
>>>> +
>>>> +Required properties:
>>>> +
>>>> +- compatible : must include "fsl,elo3-dma"
>>>> +- reg : <registers specifier for DMA general status reg>
>>> The example has two reg entries. What both are should be specified. From
>>> what you described last time, it sounds like each is a status register
>>> for four channels.
>>>
>>> Presumably the first covers the channels at 0x0,0x80,0x100,0x180, and
>>> the second covers the channels at 0x300,0x380,0x400,0x480? If the
>>> registers have specific names in a datasheet, it would be worth
>>> mentioning them.
>> Yes, each is a status register for four channels, you got it -- this
>> means my statement works.
>> Is it necessary to specify all the register names?
>> I can describe my two registers, but in other cases the reg entryies can
>> cover tens even hundreds of registers, just a summary is OK I think.
> I think there should at least be a description of which channels each
> reg entry corresponds to. I see this hasn't been done so far for the
> older Elo DMAs, but they only had 4 channels max, and one status reg.
OK, I will update the reg description to make it more clear.
>>> If the specification of the DMA controller allows for more channels, it
>>> may be worth describing that case now.
>> This DMA controller doesn't allows for more channels. (Even if it does,
>> it should be another new controller)
> Ok.
>
>>>> +- ranges : describes the mapping between the address space of the
>>>> + DMA channels and the address space of the DMA controller
>>> This looks odd as a required property, and I'm slightly confused. Is
>>> this used to map the reg values of the DMA channels, or is it used when
>>> mapping the DMA address space (for which dma-ranges exists in ePAPR and
>>> other bindings).
>> It is used to map the reg values of DMA channels.
> Ok, I guess that makes sense.
>
>>>> +
>>>> +- DMA channel nodes:
>>>> + - compatible : must include "fsl,eloplus-dma-channel"
>>>> + - reg : <registers specifier for channel>
>>> What does this represent? What are valid values?
>>>
>>> In the example below it looks like these are offsets of control
>>> registers within the dma controller.
>> Yes, they are offsets of control registers within dma controller, but
>> the contents in these registers are for dma channels.
>> Physically we have dma controller registers and dma channel registers,
>> they are in one continuous physical address space, we divide all these
>> registers into two controller/channel parts, according to contents in
>> these registers, common status registers for all channels are called dma
>> controller registers, otherwise channel specific registers are called
>> dma channel registers.
> I see, so this reg represents a channels channel specific registers
> (which are distinct from the shared status registers). I was confused
> initially as to what address space they were in, but that makes sense
> with your description of ranges above.
>
>>> If the reg property may have any value, how do they get mapped to bits
>>> in the status register(s)?
>> In fact, each channel has its own status register(and also other
>> registers), the dma controller status register is just aggregation of
>> all channel status register. (that seems duplicated somehow, maybe this
>> is due to hardware compatibility with legacy one, and the device tree
>> just describes the physical hardware without lie)
> My question here was stupid, thanks for the explanation :)
>
>>> May some channels be unusable for some reason, or will all eight
>>> channels be wired on any given Elo3 DMA?
>> Sorry, not get your point clearly, maybe you are clear now because of my
>> previous explanations.
> I assume that on any El03 DMA, there won't be a case where you can't
> describe the channel at 0x80, for instance. It will always be present
> (but it might not be wired up to anything any therefore be useful)?
>
> This was related to my concerns about the status register description --
> if the channels at 0x0,0x80,0x100,0x180 weren't wired, what would get
> described in the dt? I guess that would never actually happen because
> all 8 channels must always be present in the Elo3 IP block.
Yes, for this Elo3 DMA IP block, all the 8 channels are always on.
> Thanks,
> Mark.
>
^ permalink raw reply
* Re: [PATCH] Powerpc/dts: Correct sdhci quirk for bsc9131
From: Zhang Haijun @ 2013-09-16 8:12 UTC (permalink / raw)
To: Haijun Zhang; +Cc: scottwood, linuxppc-dev, X.Xie
In-Reply-To: <1378118222-17338-1-git-send-email-Haijun.Zhang@freescale.com>
On 09/02/2013 06:37 PM, Haijun Zhang wrote:
> We use property "sdhci,auto-cmd12" instead of "fsl,sdhci-auto-cmd12"
> to distinguish if the sdhc host has quirk SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12.
>
> Signed-off-by: Haijun Zhang <Haijun.Zhang@freescale.com>
> ---
> arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi b/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi
> index 5180d9d..0c0efa9 100644
> --- a/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi
> +++ b/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi
> @@ -130,7 +130,7 @@ usb@22000 {
>
> /include/ "pq3-esdhc-0.dtsi"
> sdhc@2e000 {
> - fsl,sdhci-auto-cmd12;
> + sdhci,auto-cmd12;
> interrupts = <41 0x2 0 0>;
> };
>
>
Hi, scott
Could you help review this patch?
--
Thanks & Regards
Haijun
^ permalink raw reply
* Re: [PATCH v2 1/3] powerpc/booke64: add sync after writing PTE
From: Benjamin Herrenschmidt @ 2013-09-15 21:38 UTC (permalink / raw)
To: Scott Wood; +Cc: linuxppc-dev
In-Reply-To: <1379130622-17436-1-git-send-email-scottwood@freescale.com>
On Fri, 2013-09-13 at 22:50 -0500, Scott Wood wrote:
> The ISA says that a sync is needed to order a PTE write with a
> subsequent hardware tablewalk lookup. On e6500, without this sync
> we've been observed to die with a DSI due to a PTE write not being seen
> by a subsequent access, even when everything happens on the same
> CPU.
This is gross, I didn't realize we had that bogosity in the
architecture...
Did you measure the performance impact ?
Cheers,
Ben.
> Signed-off-by: Scott Wood <scottwood@freescale.com>
> ---
> v2: new patch
>
> Note that we saw this problem when running in emulation (died early in
> boot), but when I tried just now with the mb() removed on actual
> hardware, I didn't see any problem. But since I'm not aware of any
> change having been made in the hardware relative to this, and since it
> is architecturally required, I'd be more comfortable leaving it in
> unlesss something has changed in the kernel recently such that a sync
> is happening somewhere else along the code path.
> ---
> arch/powerpc/include/asm/pgtable.h | 7 +++++++
> 1 file changed, 7 insertions(+)
>
> diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
> index 7d6eacf..0459077 100644
> --- a/arch/powerpc/include/asm/pgtable.h
> +++ b/arch/powerpc/include/asm/pgtable.h
> @@ -143,6 +143,13 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
> * cases, and 32-bit non-hash with 32-bit PTEs.
> */
> *ptep = pte;
> +#ifdef CONFIG_PPC_BOOK3E_64
> + /*
> + * With hardware tablewalk, a sync is needed to ensure that
> + * subsequent accesses see the PTE we just wrote.
> + */
> + mb();
> +#endif
> #endif
> }
>
^ permalink raw reply
* [PATCH][v2] powerpc/configs: Enable T1040QDS by default in corenet
From: Prabhakar Kushwaha @ 2013-09-15 14:02 UTC (permalink / raw)
To: linuxppc-dev; +Cc: scottwood, Prabhakar Kushwaha
T1040 supports both 32 & 64 bit kernel.
so enable T1040QDS by default in the config files.
Signed-off-by: Prabhakar Kushwaha <prabhakar@freescale.com>
---
Based upon git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc.git
Branch next
Changes for v2: Sending as it is
arch/powerpc/configs/corenet32_smp_defconfig | 1 +
arch/powerpc/configs/corenet64_smp_defconfig | 1 +
2 files changed, 2 insertions(+)
diff --git a/arch/powerpc/configs/corenet32_smp_defconfig b/arch/powerpc/configs/corenet32_smp_defconfig
index 3dfab4c..19d1d31 100644
--- a/arch/powerpc/configs/corenet32_smp_defconfig
+++ b/arch/powerpc/configs/corenet32_smp_defconfig
@@ -28,6 +28,7 @@ CONFIG_P3041_DS=y
CONFIG_P4080_DS=y
CONFIG_P5020_DS=y
CONFIG_P5040_DS=y
+CONFIG_T104x_QDS=y
CONFIG_HIGHMEM=y
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
CONFIG_BINFMT_MISC=m
diff --git a/arch/powerpc/configs/corenet64_smp_defconfig b/arch/powerpc/configs/corenet64_smp_defconfig
index fa94fb3..d23ee10 100644
--- a/arch/powerpc/configs/corenet64_smp_defconfig
+++ b/arch/powerpc/configs/corenet64_smp_defconfig
@@ -24,6 +24,7 @@ CONFIG_MAC_PARTITION=y
CONFIG_B4_QDS=y
CONFIG_P5020_DS=y
CONFIG_P5040_DS=y
+CONFIG_T104x_QDS=y
CONFIG_T4240_QDS=y
# CONFIG_PPC_OF_BOOT_TRAMPOLINE is not set
CONFIG_BINFMT_MISC=m
--
1.7.9.5
^ permalink raw reply related
* [PATCH][v2] powerpc/fsl-booke: Add initial T104x_QDS board support
From: Prabhakar Kushwaha @ 2013-09-15 14:01 UTC (permalink / raw)
To: linuxppc-dev; +Cc: scottwood, Priyanka Jain, Poonam Aggrwal, Prabhakar Kushwaha
Add support for T104x board in board file t104x_qds.c, It is common for
both T1040 and T1042 as they share same QDS board.
T1040QDS board Overview
-----------------------
- SERDES Connections, 8 lanes supporting:
=E2=80=94 PCI Express: supporting Gen 1 and Gen 2;
=E2=80=94 SGMII
=E2=80=94 QSGMII
=E2=80=94 SATA 2.0
=E2=80=94 Aurora debug with dedicated connectors (T1040 only)
- DDR Controller
- Supports rates of up to 1600 MHz data-rate
- Supports one DDR3LP UDIMM/RDIMMs, of single-, dual- or quad-rank t=
ypes.
-IFC/Local Bus
- NAND flash: 8-bit, async, up to 2GB.
- NOR: 8-bit or 16-bit, non-multiplexed, up to 512MB
- GASIC: Simple (minimal) target within Qixis FPGA
- PromJET rapid memory download support
- Ethernet
- Two on-board RGMII 10/100/1G ethernet ports.
- PHY #0 remains powered up during deep-sleep (T1040 only)
- QIXIS System Logic FPGA
- Clocks
- System and DDR clock (SYSCLK, =E2=80=9CDDRCLK=E2=80=9D)
- SERDES clocks
- Power Supplies
- Video
- DIU supports video at up to 1280x1024x32bpp
- USB
- Supports two USB 2.0 ports with integrated PHYs
=E2=80=94 Two type A ports with 5V@1.5A per port.
=E2=80=94 Second port can be converted to OTG mini-AB
- SDHC
- SDHC port connects directly to an adapter card slot, featuring:
- Supporting SD slots for: SD, SDHC (1x, 4x, 8x) and/or MMC
=E2=80=94 Supporting eMMC memory devices
- SPI
- On-board support of 3 different devices and sizes
- Other IO
- Two Serial ports
- ProfiBus port
- Four I2C ports
Add T104xQDS support in Kconfig and Makefile. Also create device tree.
Signed-off-by: Priyanka Jain <Priyanka.Jain@freescale.com>
Signed-off-by: Poonam Aggrwal <poonam.aggrwal@freescale.com>
Signed-off-by: Prabhakar Kushwaha <prabhakar@freescale.com>
---
Based upon git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc.gi=
t
Branch next
Changes for v2: Incorporated Scott's comments
- Created t104xqds.dtsi, both t1040qds & t1042qds include it
- Updated get_irq=20
arch/powerpc/boot/dts/t1040qds.dts | 46 ++++++++
arch/powerpc/boot/dts/t1042qds.dts | 46 ++++++++
arch/powerpc/boot/dts/t104xqds.dtsi | 192 +++++++++++++++++++++++++=
++++++
arch/powerpc/platforms/85xx/Kconfig | 20 ++++
arch/powerpc/platforms/85xx/Makefile | 1 +
arch/powerpc/platforms/85xx/t104x_qds.c | 118 +++++++++++++++++++
6 files changed, 423 insertions(+)
create mode 100644 arch/powerpc/boot/dts/t1040qds.dts
create mode 100644 arch/powerpc/boot/dts/t1042qds.dts
create mode 100644 arch/powerpc/boot/dts/t104xqds.dtsi
create mode 100644 arch/powerpc/platforms/85xx/t104x_qds.c
diff --git a/arch/powerpc/boot/dts/t1040qds.dts b/arch/powerpc/boot/dts/t=
1040qds.dts
new file mode 100644
index 0000000..973c29c
--- /dev/null
+++ b/arch/powerpc/boot/dts/t1040qds.dts
@@ -0,0 +1,46 @@
+/*
+ * T1040QDS Device Tree Source
+ *
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions ar=
e met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyrig=
ht
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission=
.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of th=
e
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMP=
LIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE AR=
E
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR A=
NY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DA=
MAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SE=
RVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUS=
ED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR=
TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE=
OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/t104xsi-pre.dtsi"
+/include/ "t104xqds.dtsi"
+
+/ {
+ model =3D "fsl,T1040QDS";
+ compatible =3D "fsl,T1040QDS";
+ #address-cells =3D <2>;
+ #size-cells =3D <2>;
+ interrupt-parent =3D <&mpic>;
+};
+
+/include/ "fsl/t1040si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/t1042qds.dts b/arch/powerpc/boot/dts/t=
1042qds.dts
new file mode 100644
index 0000000..45bd037
--- /dev/null
+++ b/arch/powerpc/boot/dts/t1042qds.dts
@@ -0,0 +1,46 @@
+/*
+ * T1042QDS Device Tree Source
+ *
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions ar=
e met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyrig=
ht
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission=
.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of th=
e
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMP=
LIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE AR=
E
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR A=
NY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DA=
MAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SE=
RVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUS=
ED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR=
TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE=
OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "fsl/t104xsi-pre.dtsi"
+/include/ "t104xqds.dtsi"
+
+/ {
+ model =3D "fsl,T1042QDS";
+ compatible =3D "fsl,T1042QDS";
+ #address-cells =3D <2>;
+ #size-cells =3D <2>;
+ interrupt-parent =3D <&mpic>;
+};
+
+/include/ "fsl/t1042si-post.dtsi"
diff --git a/arch/powerpc/boot/dts/t104xqds.dtsi b/arch/powerpc/boot/dts/=
t104xqds.dtsi
new file mode 100644
index 0000000..5a518b3
--- /dev/null
+++ b/arch/powerpc/boot/dts/t104xqds.dtsi
@@ -0,0 +1,192 @@
+/*
+ * T104xQDS Device Tree Source
+ *
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions ar=
e met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyrig=
ht
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission=
.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of th=
e
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMP=
LIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE AR=
E
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR A=
NY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DA=
MAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SE=
RVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUS=
ED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR=
TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE=
OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/ {
+ model =3D "fsl,T1040QDS";
+ compatible =3D "fsl,T1040QDS";
+ #address-cells =3D <2>;
+ #size-cells =3D <2>;
+ interrupt-parent =3D <&mpic>;
+
+ ifc: localbus@ffe124000 {
+ reg =3D <0xf 0xfe124000 0 0x2000>;
+ ranges =3D <0 0 0xf 0xe8000000 0x08000000
+ 2 0 0xf 0xff800000 0x00010000
+ 3 0 0xf 0xffdf0000 0x00008000>;
+
+ nor@0,0 {
+ #address-cells =3D <1>;
+ #size-cells =3D <1>;
+ compatible =3D "cfi-flash";
+ reg =3D <0x0 0x0 0x8000000>;
+
+ bank-width =3D <2>;
+ device-width =3D <1>;
+ };
+
+ nand@2,0 {
+ #address-cells =3D <1>;
+ #size-cells =3D <1>;
+ compatible =3D "fsl,ifc-nand";
+ reg =3D <0x2 0x0 0x10000>;
+
+ partition@0 {
+ /* This location must not be altered */
+ /* 1MB for u-boot Bootloader Image */
+ reg =3D <0x0 0x00100000>;
+ label =3D "NAND U-Boot Image";
+ read-only;
+ };
+
+ partition@100000 {
+ /* 1MB for DTB Image */
+ reg =3D <0x00100000 0x00100000>;
+ label =3D "NAND DTB Image";
+ };
+
+ partition@200000 {
+ /* 10MB for Linux Kernel Image */
+ reg =3D <0x00200000 0x00A00000>;
+ label =3D "NAND Linux Kernel Image";
+ };
+
+ partition@C00000 {
+ /* 500MB for Root file System Image */
+ reg =3D <0x00c00000 0x1F400000>;
+ label =3D "NAND RFS Image";
+ };
+ };
+
+ board-control@3,0 {
+ #address-cells =3D <1>;
+ #size-cells =3D <1>;
+ compatible =3D "fsl,tetra-fpga", "fsl,fpga-qixis";
+ reg =3D <3 0 0x300>;
+ };
+ };
+
+ memory {
+ device_type =3D "memory";
+ };
+
+ dcsr: dcsr@f00000000 {
+ ranges =3D <0x00000000 0xf 0x00000000 0x01072000>;
+ };
+
+ soc: soc@ffe000000 {
+ ranges =3D <0x00000000 0xf 0xfe000000 0x1000000>;
+ reg =3D <0xf 0xfe000000 0 0x00001000>;
+ spi@110000 {
+ flash@0 {
+ #address-cells =3D <1>;
+ #size-cells =3D <1>;
+ compatible =3D "micron,n25q512a";
+ reg =3D <0>;
+ spi-max-frequency =3D <10000000>; /* input clock */
+ };
+ };
+
+ i2c@118000 {
+ pca9547@77 {
+ compatible =3D "philips,pca9547";
+ reg =3D <0x77>;
+ };
+ rtc@68 {
+ compatible =3D "dallas,ds3232";
+ reg =3D <0x68>;
+ interrupts =3D <0x1 0x1 0 0>;
+ };
+ };
+ };
+
+ pci0: pcie@ffe240000 {
+ reg =3D <0xf 0xfe240000 0 0x10000>;
+ ranges =3D <0x02000000 0 0xe0000000 0xc 0x00000000 0x0 0x10000000
+ 0x01000000 0 0x00000000 0xf 0xf8000000 0x0 0x00010000>;
+ pcie@0 {
+ ranges =3D <0x02000000 0 0xe0000000
+ 0x02000000 0 0xe0000000
+ 0 0x10000000
+
+ 0x01000000 0 0x00000000
+ 0x01000000 0 0x00000000
+ 0 0x00010000>;
+ };
+ };
+
+ pci1: pcie@ffe250000 {
+ reg =3D <0xf 0xfe250000 0 0x10000>;
+ ranges =3D <0x02000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x10000000
+ 0x01000000 0x0 0x00000000 0xf 0xf8010000 0x0 0x00010000>;
+ pcie@0 {
+ ranges =3D <0x02000000 0 0xe0000000
+ 0x02000000 0 0xe0000000
+ 0 0x10000000
+
+ 0x01000000 0 0x00000000
+ 0x01000000 0 0x00000000
+ 0 0x00010000>;
+ };
+ };
+
+ pci2: pcie@ffe260000 {
+ reg =3D <0xf 0xfe260000 0 0x1000>;
+ ranges =3D <0x02000000 0 0xe0000000 0xc 0x40000000 0 0x10000000
+ 0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>;
+ pcie@0 {
+ ranges =3D <0x02000000 0 0xe0000000
+ 0x02000000 0 0xe0000000
+ 0 0x10000000
+
+ 0x01000000 0 0x00000000
+ 0x01000000 0 0x00000000
+ 0 0x00010000>;
+ };
+ };
+
+ pci3: pcie@ffe270000 {
+ reg =3D <0xf 0xfe270000 0 0x10000>;
+ ranges =3D <0x02000000 0 0xe0000000 0xc 0x60000000 0 0x10000000
+ 0x01000000 0 0x00000000 0xf 0xf8030000 0 0x00010000>;
+ pcie@0 {
+ ranges =3D <0x02000000 0 0xe0000000
+ 0x02000000 0 0xe0000000
+ 0 0x10000000
+
+ 0x01000000 0 0x00000000
+ 0x01000000 0 0x00000000
+ 0 0x00010000>;
+ };
+ };
+};
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms=
/85xx/Kconfig
index de2eb93..81d97b5 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -295,6 +295,26 @@ config P5040_DS
help
This option enables support for the P5040 DS board
=20
+config T104x_QDS
+ bool "Freescale T104x QDS"
+ select DEFAULT_UIMAGE
+ select E500
+ select PPC_E500MC
+ select PHYS_64BIT
+ select SWIOTLB
+ select ARCH_REQUIRE_GPIOLIB
+ select GENERIC_GPIO
+ select HAS_RAPIDIO
+ select PPC_EPAPR_HV_PIC
+ select HAS_FSL_QBMAN
+ select MDIO_BUS_MUX if FSL_DPAA_ETH
+ select MDIO_BUS_MUX_MMIOREG if FSL_DPAA_ETH
+ help
+ This option enables support for the T04x QDS board
+ The T104x application development system T104x QDS is a complete
+ debugging environment intended for engineers developing
+ applications for the T1040/T1042.
+
config PPC_QEMU_E500
bool "QEMU generic e500 platform"
select DEFAULT_UIMAGE
diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platform=
s/85xx/Makefile
index 53c9f75..879c238 100644
--- a/arch/powerpc/platforms/85xx/Makefile
+++ b/arch/powerpc/platforms/85xx/Makefile
@@ -23,6 +23,7 @@ obj-$(CONFIG_P3041_DS) +=3D p3041_ds.o corenet_ds.o
obj-$(CONFIG_P4080_DS) +=3D p4080_ds.o corenet_ds.o
obj-$(CONFIG_P5020_DS) +=3D p5020_ds.o corenet_ds.o
obj-$(CONFIG_P5040_DS) +=3D p5040_ds.o corenet_ds.o
+obj-$(CONFIG_T104x_QDS) +=3D t104x_qds.o corenet_ds.o
obj-$(CONFIG_T4240_QDS) +=3D t4240_qds.o corenet_ds.o
obj-$(CONFIG_B4_QDS) +=3D b4_qds.o corenet_ds.o
obj-$(CONFIG_STX_GP3) +=3D stx_gp3.o
diff --git a/arch/powerpc/platforms/85xx/t104x_qds.c b/arch/powerpc/platf=
orms/85xx/t104x_qds.c
new file mode 100644
index 0000000..547d44d
--- /dev/null
+++ b/arch/powerpc/platforms/85xx/t104x_qds.c
@@ -0,0 +1,118 @@
+/*
+ * T104x QDS Setup
+ * Should apply for QDS platform of T1040 and it's personalities.
+ * viz T1040/T1042
+ *
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify =
it
+ * under the terms of the GNU General Public License as published by t=
he
+ * Free Software Foundation; either version 2 of the License, or (at y=
our
+ * option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/kdev_t.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/phy.h>
+
+#include <asm/time.h>
+#include <asm/machdep.h>
+#include <asm/pci-bridge.h>
+#include <mm/mmu_decl.h>
+#include <asm/prom.h>
+#include <asm/udbg.h>
+#include <asm/mpic.h>
+
+#include <linux/of_platform.h>
+#include <sysdev/fsl_soc.h>
+#include <sysdev/fsl_pci.h>
+#include <asm/ehv_pic.h>
+
+#include "corenet_ds.h"
+
+/*
+ * Called very early, device-tree isn't unflattened
+ */
+static int __init t104x_qds_probe(void)
+{
+ unsigned long root =3D of_get_flat_dt_root();
+#ifdef CONFIG_SMP
+ extern struct smp_ops_t smp_85xx_ops;
+#endif
+
+ if (of_flat_dt_is_compatible(root, "fsl,T1040QDS") ||
+ of_flat_dt_is_compatible(root, "fsl,T1042QDS"))
+
+ return 1;
+
+ /* Check if we're running under the Freescale hypervisor */
+ if (of_flat_dt_is_compatible(root, "fsl,T1040QDS-hv") ||
+ of_flat_dt_is_compatible(root, "fsl,T1042QDS-hv")) {
+ ppc_md.init_IRQ =3D ehv_pic_init;
+ ppc_md.get_irq =3D ehv_pic_get_irq;
+ ppc_md.restart =3D fsl_hv_restart;
+ ppc_md.power_off =3D fsl_hv_halt;
+ ppc_md.halt =3D fsl_hv_halt;
+#ifdef CONFIG_SMP
+ /*
+ * Disable the timebase sync operations because we can't write
+ * to the timebase registers under the hypervisor.
+ */
+ smp_85xx_ops.give_timebase =3D NULL;
+ smp_85xx_ops.take_timebase =3D NULL;
+#endif
+
+ return 1;
+ }
+
+ return 0;
+}
+
+define_machine(t1042_qds) {
+ .name =3D "T1042 QDS",
+ .probe =3D t104x_qds_probe,
+ .setup_arch =3D corenet_ds_setup_arch,
+ .init_IRQ =3D corenet_ds_pic_init,
+#ifdef CONFIG_PCI
+ .pcibios_fixup_bus =3D fsl_pcibios_fixup_bus,
+#endif
+/* coreint doesn't play nice with lazy EE, use legacy mpic for now */
+ .get_irq =3D mpic_get_coreint_irq,
+ .restart =3D fsl_rstcr_restart,
+ .calibrate_decr =3D generic_calibrate_decr,
+ .progress =3D udbg_progress,
+#ifdef CONFIG_PPC64
+ .power_save =3D book3e_idle,
+#else
+ .power_save =3D e500_idle,
+#endif
+};
+
+define_machine(t1040_qds) {
+ .name =3D "T1040 QDS",
+ .probe =3D t104x_qds_probe,
+ .setup_arch =3D corenet_ds_setup_arch,
+ .init_IRQ =3D corenet_ds_pic_init,
+#ifdef CONFIG_PCI
+ .pcibios_fixup_bus =3D fsl_pcibios_fixup_bus,
+#endif
+/* coreint doesn't play nice with lazy EE, use legacy mpic for now */
+ .get_irq =3D mpic_get_coreint_irq,
+ .restart =3D fsl_rstcr_restart,
+ .calibrate_decr =3D generic_calibrate_decr,
+ .progress =3D udbg_progress,
+#ifdef CONFIG_PPC64
+ .power_save =3D book3e_idle,
+#else
+ .power_save =3D e500_idle,
+#endif
+};
+
+machine_arch_initcall(t104x_qds, corenet_ds_publish_devices);
+
+#ifdef CONFIG_SWIOTLB
+machine_arch_initcall(t104x_qds, swiotlb_setup_bus_notifier);
+#endif
--=20
1.7.9.5
^ permalink raw reply related
* [PATCH][v2] powerpc/mpc85xx:Add initial device tree support of T104x
From: Prabhakar Kushwaha @ 2013-09-15 14:01 UTC (permalink / raw)
To: linuxppc-dev
Cc: Poonam Aggrwal, Priyanka Jain, scottwood, Varun Sethi,
Prabhakar Kushwaha
The QorIQ T1040/T1042 processor support four integrated 64-bit e5500 PA
processor cores with high-performance data path acceleration architecture
and network peripheral interfaces required for networking & telecommunications.
T1042 personality is a reduced personality of T1040 without Integrated 8-port
Gigabit Ethernet switch.
The T1040/T1042 SoC includes the following function and features:
- Four e5500 cores, each with a private 256 KB L2 cache
- 256 KB shared L3 CoreNet platform cache (CPC)
- Interconnect CoreNet platform
- 32-/64-bit DDR3L/DDR4 SDRAM memory controller with ECC and interleaving
support
- Data Path Acceleration Architecture (DPAA) incorporating acceleration
for the following functions:
- Packet parsing, classification, and distribution
- Queue management for scheduling, packet sequencing, and congestion
management
- Cryptography Acceleration (SEC 5.0)
- RegEx Pattern Matching Acceleration (PME 2.2)
- IEEE Std 1588 support
- Hardware buffer management for buffer allocation and deallocation
- Ethernet interfaces
- Integrated 8-port Gigabit Ethernet switch (T1040 only)
- Four 1 Gbps Ethernet controllers
- Two RGMII interfaces or one RGMII and one MII interfaces
- High speed peripheral interfaces
- Four PCI Express 2.0 controllers running at up to 5 GHz
- Two SATA controllers supporting 1.5 and 3.0 Gb/s operation
- Upto two QSGMII interface
- Upto six SGMII interface supporting 1000 Mbps
- One SGMII interface supporting upto 2500 Mbps
- Additional peripheral interfaces
- Two USB 2.0 controllers with integrated PHY
- SD/eSDHC/eMMC
- eSPI controller
- Four I2C controllers
- Four UARTs
- Four GPIO controllers
- Integrated flash controller (IFC)
- Change this to LCD/ HDMI interface (DIU) with 12 bit dual data rate
- TDM interface
- Multicore programmable interrupt controller (PIC)
- Two 8-channel DMA engines
- Single source clocking implementation
- Deep Sleep power implementaion (wakeup from GPIO/Timer/Ethernet/USB)
Signed-off-by: Poonam Aggrwal <poonam.aggrwal@freescale.com>
Signed-off-by: Priyanka Jain <Priyanka.Jain@freescale.com>
Signed-off-by: Varun Sethi <Varun.Sethi@freescale.com>
Signed-off-by: Prabhakar Kushwaha <prabhakar@freescale.com>
---
Based upon git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc.git
Branch next
Changes for v2: Incorporated Scott's comments
- Update t1040si-post.dtsi
- update clock device tree node as per
http://patchwork.ozlabs.org/patch/274134/
- removed DMA node, It will be added later as per
http://patchwork.ozlabs.org/patch/271238/
- Updated display compatible field
arch/powerpc/boot/dts/fsl/t1040si-post.dtsi | 41 +++
arch/powerpc/boot/dts/fsl/t1042si-post.dtsi | 418 +++++++++++++++++++++++++++
arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi | 109 +++++++
3 files changed, 568 insertions(+)
create mode 100644 arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
create mode 100644 arch/powerpc/boot/dts/fsl/t1042si-post.dtsi
create mode 100644 arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi
diff --git a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
new file mode 100644
index 0000000..ca820f6
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi
@@ -0,0 +1,41 @@
+/*
+ * T1040 Silicon/SoC Device Tree Source (post include)
+ *
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/include/ "t1042si-post.dtsi"
+
+&soc {
+ l2switch@800000 {
+ reg = <0x800000 0x400000>;
+ };
+};
diff --git a/arch/powerpc/boot/dts/fsl/t1042si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1042si-post.dtsi
new file mode 100644
index 0000000..6bfbcda
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/t1042si-post.dtsi
@@ -0,0 +1,418 @@
+/*
+ * t1042 Silicon/SoC Device Tree Source (post include)
+ *
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+&ifc {
+ #address-cells = <2>;
+ #size-cells = <1>;
+ compatible = "fsl,ifc", "simple-bus";
+ interrupts = <25 2 0 0>;
+};
+
+&pci0 {
+ compatible = "fsl,t104x-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie";
+ device_type = "pci";
+ #size-cells = <2>;
+ #address-cells = <3>;
+ bus-range = <0x0 0xff>;
+ interrupts = <20 2 0 0>;
+ fsl,iommu-parent = <&pamu0>;
+ pcie@0 {
+ reg = <0 0 0 0 0>;
+ #interrupt-cells = <1>;
+ #size-cells = <2>;
+ #address-cells = <3>;
+ device_type = "pci";
+ interrupts = <20 2 0 0>;
+ interrupt-map-mask = <0xf800 0 0 7>;
+ interrupt-map = <
+ /* IDSEL 0x0 */
+ 0000 0 0 1 &mpic 40 1 0 0
+ 0000 0 0 2 &mpic 1 1 0 0
+ 0000 0 0 3 &mpic 2 1 0 0
+ 0000 0 0 4 &mpic 3 1 0 0
+ >;
+ };
+};
+
+&pci1 {
+ compatible = "fsl,t104x-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie";
+ device_type = "pci";
+ #size-cells = <2>;
+ #address-cells = <3>;
+ bus-range = <0 0xff>;
+ interrupts = <21 2 0 0>;
+ fsl,iommu-parent = <&pamu0>;
+ pcie@0 {
+ reg = <0 0 0 0 0>;
+ #interrupt-cells = <1>;
+ #size-cells = <2>;
+ #address-cells = <3>;
+ device_type = "pci";
+ interrupts = <21 2 0 0>;
+ interrupt-map-mask = <0xf800 0 0 7>;
+ interrupt-map = <
+ /* IDSEL 0x0 */
+ 0000 0 0 1 &mpic 41 1 0 0
+ 0000 0 0 2 &mpic 5 1 0 0
+ 0000 0 0 3 &mpic 6 1 0 0
+ 0000 0 0 4 &mpic 7 1 0 0
+ >;
+ };
+};
+
+&pci2 {
+ compatible = "fsl,t104x-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie";
+ device_type = "pci";
+ #size-cells = <2>;
+ #address-cells = <3>;
+ bus-range = <0x0 0xff>;
+ interrupts = <22 2 0 0>;
+ fsl,iommu-parent = <&pamu0>;
+ pcie@0 {
+ reg = <0 0 0 0 0>;
+ #interrupt-cells = <1>;
+ #size-cells = <2>;
+ #address-cells = <3>;
+ device_type = "pci";
+ interrupts = <22 2 0 0>;
+ interrupt-map-mask = <0xf800 0 0 7>;
+ interrupt-map = <
+ /* IDSEL 0x0 */
+ 0000 0 0 1 &mpic 42 1 0 0
+ 0000 0 0 2 &mpic 9 1 0 0
+ 0000 0 0 3 &mpic 10 1 0 0
+ 0000 0 0 4 &mpic 11 1 0 0
+ >;
+ };
+};
+
+&pci3 {
+ compatible = "fsl,t104x-pcie", "fsl,qoriq-pcie-v2.4", "fsl,qoriq-pcie";
+ device_type = "pci";
+ #size-cells = <2>;
+ #address-cells = <3>;
+ bus-range = <0x0 0xff>;
+ interrupts = <23 2 0 0>;
+ fsl,iommu-parent = <&pamu0>;
+ pcie@0 {
+ reg = <0 0 0 0 0>;
+ #interrupt-cells = <1>;
+ #size-cells = <2>;
+ #address-cells = <3>;
+ device_type = "pci";
+ interrupts = <23 2 0 0>;
+ interrupt-map-mask = <0xf800 0 0 7>;
+ interrupt-map = <
+ /* IDSEL 0x0 */
+ 0000 0 0 1 &mpic 43 1 0 0
+ 0000 0 0 2 &mpic 0 1 0 0
+ 0000 0 0 3 &mpic 4 1 0 0
+ 0000 0 0 4 &mpic 8 1 0 0
+ >;
+ };
+};
+
+&dcsr {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "fsl,dcsr", "simple-bus";
+
+ dcsr-epu@0 {
+ compatible = "fsl,t104x-dcsr-epu", "fsl,dcsr-epu";
+ interrupts = <52 2 0 0
+ 84 2 0 0
+ 85 2 0 0>;
+ reg = <0x0 0x1000>;
+ };
+ dcsr-npc {
+ compatible = "fsl,t104x-dcsr-cnpc", "fsl,dcsr-cnpc";
+ reg = <0x1000 0x1000 0x1002000 0x10000>;
+ };
+ dcsr-nxc@2000 {
+ compatible = "fsl,dcsr-nxc";
+ reg = <0x2000 0x1000>;
+ };
+ dcsr-corenet {
+ compatible = "fsl,dcsr-corenet";
+ reg = <0x8000 0x1000 0x1A000 0x1000>;
+ };
+ dcsr-dpaa@9000 {
+ compatible = "fsl,t104x-dcsr-dpaa", "fsl,dcsr-dpaa";
+ reg = <0x9000 0x1000>;
+ };
+ dcsr-ocn@11000 {
+ compatible = "fsl,t104x-dcsr-ocn", "fsl,dcsr-ocn";
+ reg = <0x11000 0x1000>;
+ };
+ dcsr-ddr@12000 {
+ compatible = "fsl,dcsr-ddr";
+ dev-handle = <&ddr1>;
+ reg = <0x12000 0x1000>;
+ };
+ dcsr-nal@18000 {
+ compatible = "fsl,t104x-dcsr-nal", "fsl,dcsr-nal";
+ reg = <0x18000 0x1000>;
+ };
+ dcsr-rcpm@22000 {
+ compatible = "fsl,t104x-dcsr-rcpm", "fsl,dcsr-rcpm";
+ reg = <0x22000 0x1000>;
+ };
+ dcsr-snpc@30000 {
+ compatible = "fsl,t104x-dcsr-snpc", "fsl,dcsr-snpc";
+ reg = <0x30000 0x1000 0x1022000 0x10000>;
+ };
+ dcsr-snpc@31000 {
+ compatible = "fsl,t104x-dcsr-snpc", "fsl,dcsr-snpc";
+ reg = <0x31000 0x1000 0x1042000 0x10000>;
+ };
+ dcsr-cpu-sb-proxy@100000 {
+ compatible = "fsl,dcsr-e5500-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
+ cpu-handle = <&cpu0>;
+ reg = <0x100000 0x1000 0x101000 0x1000>;
+ };
+ dcsr-cpu-sb-proxy@108000 {
+ compatible = "fsl,dcsr-e5500-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
+ cpu-handle = <&cpu1>;
+ reg = <0x108000 0x1000 0x109000 0x1000>;
+ };
+ dcsr-cpu-sb-proxy@110000 {
+ compatible = "fsl,dcsr-e5500-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
+ cpu-handle = <&cpu2>;
+ reg = <0x110000 0x1000 0x111000 0x1000>;
+ };
+ dcsr-cpu-sb-proxy@118000 {
+ compatible = "fsl,dcsr-e5500-sb-proxy", "fsl,dcsr-cpu-sb-proxy";
+ cpu-handle = <&cpu3>;
+ reg = <0x118000 0x1000 0x119000 0x1000>;
+ };
+};
+
+&soc {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ device_type = "soc";
+ compatible = "simple-bus";
+
+ soc-sram-error {
+ compatible = "fsl,soc-sram-error";
+ interrupts = <16 2 1 29>;
+ };
+
+ corenet-law@0 {
+ compatible = "fsl,corenet-law";
+ reg = <0x0 0x1000>;
+ fsl,num-laws = <16>;
+ };
+
+ ddr1: memory-controller@8000 {
+ compatible = "fsl,qoriq-memory-controller-v5.0",
+ "fsl,qoriq-memory-controller";
+ reg = <0x8000 0x1000>;
+ interrupts = <16 2 1 23>;
+ };
+
+ cpc: l3-cache-controller@10000 {
+ compatible = "fsl,t104x-l3-cache-controller", "cache";
+ reg = <0x10000 0x1000>;
+ interrupts = <16 2 1 27>;
+ };
+
+ corenet-cf@18000 {
+ compatible = "fsl,corenet2-cf";
+ reg = <0x18000 0x1000>;
+ interrupts = <16 2 1 31>;
+ fsl,ccf-num-csdids = <32>;
+ fsl,ccf-num-snoopids = <32>;
+ };
+
+ iommu@20000 {
+ compatible = "fsl,pamu-v1.0", "fsl,pamu";
+ reg = <0x20000 0x1000>;
+ ranges = <0 0x20000 0x1000>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+ interrupts = <
+ 24 2 0 0
+ 16 2 1 30>;
+ pamu0: pamu@0 {
+ reg = <0 0x1000>;
+ fsl,primary-cache-geometry = <128 1>;
+ fsl,secondary-cache-geometry = <16 2>;
+ };
+ };
+
+/include/ "qoriq-mpic.dtsi"
+
+ guts: global-utilities@e0000 {
+ compatible = "fsl,t104x-device-config", "fsl,qoriq-device-config-2.0";
+ reg = <0xe0000 0xe00>;
+ fsl,has-rstcr;
+ fsl,liodn-bits = <12>;
+ };
+
+ clockgen: global-utilities@e1000 {
+ compatible = "fsl,t104x-clockgen", "fsl,qoriq-clockgen-2.0",
+ "fixed-clock";
+ reg = <0xe1000 0x1000>;
+ clock-output-names = "sysclk";
+ #clock-cells = <0>;
+
+ #address-cells = <1>;
+ #size-cells = <1>;
+ pll0: pll0@800 {
+ #clock-cells = <1>;
+ reg = <0x800 4>;
+ compatible = "fsl,qoriq-chassis2-core-pll";
+ clocks = <&clockgen>;
+ clock-output-names = "pll0", "pll0-div2", "pll0-div4";
+ };
+ pll1: pll1@820 {
+ #clock-cells = <1>;
+ reg = <0x820 4>;
+ compatible = "fsl,qoriq-chassis2-core-pll";
+ clocks = <&clockgen>;
+ clock-output-names = "pll1", "pll1-div2", "pll1-div4";
+ };
+ mux0: mux0@0 {
+ #clock-cells = <0>;
+ reg = <0x0 4>;
+ compatible = "fsl,core-mux-clock";
+ clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
+ <&pll1 0>, <&pll1 1>, <&pll1 2>;
+ clock-names = "pll0_0", "pll0_1", "pll0_2",
+ "pll1_0", "pll1_1", "pll1_2";
+ clock-output-names = "cmux0";
+ };
+ mux1: mux1@20 {
+ #clock-cells = <0>;
+ reg = <0x20 4>;
+ compatible = "fsl,core-mux-clock";
+ clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
+ <&pll1 0>, <&pll1 1>, <&pll1 2>;
+ clock-names = "pll0_0", "pll0_1", "pll0_2",
+ "pll1_0", "pll1_1", "pll1_2";
+ clock-output-names = "cmux1";
+ };
+ mux2: mux2@40 {
+ #clock-cells = <0>;
+ reg = <0x40 4>;
+ compatible = "fsl,core-mux-clock";
+ clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
+ <&pll1 0>, <&pll1 1>, <&pll1 2>;
+ clock-names = "pll0_0", "pll0_1", "pll0_2",
+ "pll1_0", "pll1_1", "pll1_2";
+ clock-output-names = "cmux2";
+ };
+ mux3: mux3@60 {
+ #clock-cells = <0>;
+ reg = <0x60 4>;
+ compatible = "fsl,core-mux-clock";
+ clocks = <&pll0 0>, <&pll0 1>, <&pll0 2>,
+ <&pll1 0>, <&pll1 1>, <&pll1 2>;
+ clock-names = "pll0_0", "pll0_1", "pll0_2",
+ "pll1_0", "pll1_1", "pll1_2";
+ clock-output-names = "cmux3";
+ };
+ };
+
+ rcpm: global-utilities@e2000 {
+ compatible = "fsl,t104x-rcpm", "fsl,qoriq-rcpm-2.0";
+ reg = <0xe2000 0x1000>;
+ };
+
+ sfp: sfp@e8000 {
+ compatible = "fsl,t104x-sfp";
+ reg = <0xe8000 0x1000>;
+ };
+
+ serdes: serdes@ea000 {
+ compatible = "fsl,t104x-serdes";
+ reg = <0xea000 0x4000>;
+ };
+
+/include/ "qoriq-espi-0.dtsi"
+ spi@110000 {
+ fsl,espi-num-chipselects = <4>;
+ };
+
+/include/ "qoriq-esdhc-0.dtsi"
+ sdhc@114000 {
+ compatible = "fsl,t104x-esdhc", "fsl,esdhc";
+ fsl,iommu-parent = <&pamu0>;
+ fsl,liodn-reg = <&guts 0x530>; /* eSDHCLIODNR */
+ sdhci,auto-cmd12;
+ };
+/include/ "qoriq-i2c-0.dtsi"
+/include/ "qoriq-i2c-1.dtsi"
+/include/ "qoriq-duart-0.dtsi"
+/include/ "qoriq-duart-1.dtsi"
+/include/ "qoriq-gpio-0.dtsi"
+/include/ "qoriq-gpio-1.dtsi"
+/include/ "qoriq-gpio-2.dtsi"
+/include/ "qoriq-gpio-3.dtsi"
+/include/ "qoriq-usb2-mph-0.dtsi"
+ usb0: usb@210000 {
+ compatible = "fsl-usb2-mph-v2.4", "fsl-usb2-mph";
+ fsl,iommu-parent = <&pamu0>;
+ fsl,liodn-reg = <&guts 0x520>; /* USB1LIODNR */
+ phy_type = "utmi";
+ port0;
+ };
+/include/ "qoriq-usb2-dr-0.dtsi"
+ usb1: usb@211000 {
+ compatible = "fsl-usb2-dr-v2.4", "fsl-usb2-dr";
+ fsl,iommu-parent = <&pamu0>;
+ fsl,liodn-reg = <&guts 0x524>; /* USB2LIODNR */
+ dr_mode = "host";
+ phy_type = "utmi";
+ };
+
+ display@180000 {
+ compatible = "fsl,t104x-diu", "fsl,diu";
+ reg = <0x180000 1000>;
+ interrupts = <74 2 0 0>;
+ };
+
+/include/ "qoriq-sata2-0.dtsi"
+sata@220000 {
+ fsl,iommu-parent = <&pamu0>;
+ fsl,liodn-reg = <&guts 0x550>; /* SATA1LIODNR */
+};
+/include/ "qoriq-sata2-1.dtsi"
+sata@221000 {
+ fsl,iommu-parent = <&pamu0>;
+ fsl,liodn-reg = <&guts 0x554>; /* SATA2LIODNR */
+};
+/include/ "qoriq-sec5.0-0.dtsi"
+};
diff --git a/arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi b/arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi
new file mode 100644
index 0000000..5cd8cc3
--- /dev/null
+++ b/arch/powerpc/boot/dts/fsl/t104xsi-pre.dtsi
@@ -0,0 +1,109 @@
+/*
+ * T1040/T1042 Silicon/SoC Device Tree Source (pre include)
+ *
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * * Neither the name of Freescale Semiconductor nor the
+ * names of its contributors may be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/dts-v1/;
+
+/include/ "e5500_power_isa.dtsi"
+
+/ {
+ compatible = "fsl,T104x";
+ #address-cells = <2>;
+ #size-cells = <2>;
+ interrupt-parent = <&mpic>;
+
+ aliases {
+ ccsr = &soc;
+ dcsr = &dcsr;
+
+ serial0 = &serial0;
+ serial1 = &serial1;
+ serial2 = &serial2;
+ serial3 = &serial3;
+ pci0 = &pci0;
+ pci1 = &pci1;
+ pci2 = &pci2;
+ pci3 = &pci3;
+ usb0 = &usb0;
+ usb1 = &usb1;
+ sdhc = &sdhc;
+
+ crypto = &crypto;
+
+ };
+
+ cpus {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ cpu0: PowerPC,e5500@0 {
+ device_type = "cpu";
+ reg = <0>;
+ clocks = <&mux0>;
+ next-level-cache = <&L2_1>;
+ L2_1: l2-cache {
+ next-level-cache = <&cpc>;
+ };
+ };
+ cpu1: PowerPC,e5500@1 {
+ device_type = "cpu";
+ reg = <1>;
+ clocks = <&mux1>;
+ next-level-cache = <&L2_2>;
+ L2_2: l2-cache {
+ next-level-cache = <&cpc>;
+ };
+
+ };
+ cpu2: PowerPC,e5500@2 {
+ device_type = "cpu";
+ reg = <2>;
+ clocks = <&mux2>;
+ next-level-cache = <&L2_3>;
+ L2_3: l2-cache {
+ next-level-cache = <&cpc>;
+ };
+
+ };
+ cpu3: PowerPC,e5500@3 {
+ device_type = "cpu";
+ reg = <3>;
+ clocks = <&mux3>;
+ next-level-cache = <&L2_4>;
+ L2_4: l2-cache {
+ next-level-cache = <&cpc>;
+ };
+ };
+
+ };
+};
--
1.7.9.5
^ permalink raw reply related
* [PATCH] powerpc: Make add_system_ram_resources() __init
From: Geert Uytterhoeven @ 2013-09-15 9:39 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: Geert Uytterhoeven, linuxppc-dev, linux-kernel
add_system_ram_resources() is a subsys_initcall.
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
---
arch/powerpc/mm/mem.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 1cf9c5b..25e0f26 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -498,7 +498,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
* System memory should not be in /proc/iomem but various tools expect it
* (eg kdump).
*/
-static int add_system_ram_resources(void)
+static int __init add_system_ram_resources(void)
{
struct memblock_region *reg;
--
1.7.9.5
^ permalink raw reply related
* unsubscription
From: Yu Chen @ 2013-09-14 14:22 UTC (permalink / raw)
To: linuxppc-dev
^ permalink raw reply
* [PATCH v2 3/3] powerpc/fsl-book3e-64: Use paca for hugetlb TLB1 entry selection
From: Scott Wood @ 2013-09-14 3:50 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: Scott Wood, linuxppc-dev
In-Reply-To: <1379130622-17436-1-git-send-email-scottwood@freescale.com>
This keeps usage coordinated for hugetlb and indirect entries, which
should make entry selection more predictable and probably improve overall
performance when mixing the two.
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
v2: new patch
---
arch/powerpc/mm/hugetlbpage-book3e.c | 51 +++++++++++++++++++++++++++++-------
1 file changed, 41 insertions(+), 10 deletions(-)
diff --git a/arch/powerpc/mm/hugetlbpage-book3e.c b/arch/powerpc/mm/hugetlbpage-book3e.c
index 3bc7006..ee57ac2 100644
--- a/arch/powerpc/mm/hugetlbpage-book3e.c
+++ b/arch/powerpc/mm/hugetlbpage-book3e.c
@@ -8,6 +8,44 @@
#include <linux/mm.h>
#include <linux/hugetlb.h>
+#ifdef CONFIG_PPC_FSL_BOOK3E
+#ifdef CONFIG_PPC64
+static inline int tlb1_next(void)
+{
+ struct paca_struct *paca = get_paca();
+ struct tlb_core_data *tcd;
+ int this, next;
+
+ tcd = paca->tcd_ptr;
+ this = tcd->esel_next;
+
+ next = this + 1;
+ if (next >= tcd->esel_max)
+ next = tcd->esel_first;
+
+ tcd->esel_next = next;
+ return this;
+}
+#else
+static inline int tlb1_next(void)
+{
+ int index, ncams;
+
+ ncams = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY;
+
+ index = __get_cpu_var(next_tlbcam_idx);
+
+ /* Just round-robin the entries and wrap when we hit the end */
+ if (unlikely(index == ncams - 1))
+ __get_cpu_var(next_tlbcam_idx) = tlbcam_index;
+ else
+ __get_cpu_var(next_tlbcam_idx)++;
+
+ return index;
+}
+#endif /* !PPC64 */
+#endif /* FSL */
+
static inline int mmu_get_tsize(int psize)
{
return mmu_psize_defs[psize].enc;
@@ -47,7 +85,7 @@ void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea,
struct mm_struct *mm;
#ifdef CONFIG_PPC_FSL_BOOK3E
- int index, ncams;
+ int index;
#endif
if (unlikely(is_kernel_addr(ea)))
@@ -77,18 +115,11 @@ void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea,
}
#ifdef CONFIG_PPC_FSL_BOOK3E
- ncams = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY;
-
/* We have to use the CAM(TLB1) on FSL parts for hugepages */
- index = __get_cpu_var(next_tlbcam_idx);
+ index = tlb1_next();
mtspr(SPRN_MAS0, MAS0_ESEL(index) | MAS0_TLBSEL(1));
-
- /* Just round-robin the entries and wrap when we hit the end */
- if (unlikely(index == ncams - 1))
- __get_cpu_var(next_tlbcam_idx) = tlbcam_index;
- else
- __get_cpu_var(next_tlbcam_idx)++;
#endif
+
mas1 = MAS1_VALID | MAS1_TID(mm->context.id) | MAS1_TSIZE(tsize);
mas2 = ea & ~((1UL << shift) - 1);
mas2 |= (pte_val(pte) >> PTE_WIMGE_SHIFT) & MAS2_WIMGE_MASK;
--
1.8.1.2
^ permalink raw reply related
* [PATCH v2 2/3] powerpc/e6500: TLB miss handler with hardware tablewalk support
From: Scott Wood @ 2013-09-14 3:50 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: Scott Wood, Mihai Caraman, linuxppc-dev
In-Reply-To: <1379130622-17436-1-git-send-email-scottwood@freescale.com>
There are a few things that make the existing hw tablewalk handlers
unsuitable for e6500:
- Indirect entries go in TLB1 (though the resulting direct entries go in
TLB0).
- It has threads, but no "tlbsrx." -- so we need a spinlock and
a normal "tlbsx". Because we need this lock, hardware tablewalk
is mandatory on e6500 unless we want to add spinlock+tlbsx to
the normal bolted TLB miss handler.
- TLB1 has no HES (nor next-victim hint) so we need software round robin
(TODO: integrate this round robin data with hugetlb/KVM)
- The existing tablewalk handlers map half of a page table at a time,
because IBM hardware has a fixed 1MiB indirect page size. e6500
has variable size indirect entries, with a minimum of 2MiB.
So we can't do the half-page indirect mapping, and even if we
could it would be less efficient than mapping the full page.
- Like on e5500, the linear mapping is bolted, so we don't need the
overhead of supporting nested tlb misses.
Note that hardware tablewalk does not work in rev1 of e6500.
We do not expect to support e6500 rev1 in mainline Linux.
Signed-off-by: Scott Wood <scottwood@freescale.com>
Cc: Mihai Caraman <mihai.caraman@freescale.com>
--
v2: Changes mostly requested by Ben:
- Renamed book3e_tlb_per_core to tlb_core_data.
- Moved the tlb_core data struct later in the paca. I had thought that
keeping it in the same cache line as other stuff used in the TLB
miss handler would be beneficial, but it actually benchmarks as
slightly slower for some reason that I haven't been able to figure
out (even compared to leaving padding in place so that the layout
of that part of the paca doesn't change).
I did not remove it from the paca altogether, though, because
per-cpu data isn't working that early, and failing that, this is the
simplest way to get something on every CPU, with no wasted space for
avoiding cache line sharing, etc. Note that we do need one of these
structs on every thread (not core) until we've booted far enough to
figure out the thread topology.
- Moved the callsite of setup_tlb_core_data() to setup_system().
- Added BUILD_BUG_ON(MMU_PAGE_COUNT > 16).
- Stopped using implicit boolean conversion of book3e_htw_mode.
---
arch/powerpc/include/asm/mmu-book3e.h | 13 +++
arch/powerpc/include/asm/mmu.h | 21 +++--
arch/powerpc/include/asm/paca.h | 6 ++
arch/powerpc/kernel/asm-offsets.c | 9 ++
arch/powerpc/kernel/paca.c | 5 +
arch/powerpc/kernel/setup_64.c | 31 +++++++
arch/powerpc/mm/fsl_booke_mmu.c | 7 ++
arch/powerpc/mm/mem.c | 6 ++
arch/powerpc/mm/tlb_low_64e.S | 167 ++++++++++++++++++++++++++++++++++
arch/powerpc/mm/tlb_nohash.c | 93 +++++++++++++------
10 files changed, 322 insertions(+), 36 deletions(-)
diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/mmu-book3e.h
index 936db36..89b785d 100644
--- a/arch/powerpc/include/asm/mmu-book3e.h
+++ b/arch/powerpc/include/asm/mmu-book3e.h
@@ -286,8 +286,21 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
extern int mmu_linear_psize;
extern int mmu_vmemmap_psize;
+struct tlb_core_data {
+ /* For software way selection, as on Freescale TLB1 */
+ u8 esel_next, esel_max, esel_first;
+
+ /* Per-core spinlock for e6500 TLB handlers (no tlbsrx.) */
+ u8 lock;
+};
+
#ifdef CONFIG_PPC64
extern unsigned long linear_map_top;
+extern int book3e_htw_mode;
+
+#define PPC_HTW_NONE 0
+#define PPC_HTW_IBM 1
+#define PPC_HTW_E6500 2
/*
* 64-bit booke platforms don't load the tlb in the tlb miss handler code.
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 691fd8a..f8d1d6d 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -180,16 +180,17 @@ static inline void assert_pte_locked(struct mm_struct *mm, unsigned long addr)
#define MMU_PAGE_64K_AP 3 /* "Admixed pages" (hash64 only) */
#define MMU_PAGE_256K 4
#define MMU_PAGE_1M 5
-#define MMU_PAGE_4M 6
-#define MMU_PAGE_8M 7
-#define MMU_PAGE_16M 8
-#define MMU_PAGE_64M 9
-#define MMU_PAGE_256M 10
-#define MMU_PAGE_1G 11
-#define MMU_PAGE_16G 12
-#define MMU_PAGE_64G 13
-
-#define MMU_PAGE_COUNT 14
+#define MMU_PAGE_2M 6
+#define MMU_PAGE_4M 7
+#define MMU_PAGE_8M 8
+#define MMU_PAGE_16M 9
+#define MMU_PAGE_64M 10
+#define MMU_PAGE_256M 11
+#define MMU_PAGE_1G 12
+#define MMU_PAGE_16G 13
+#define MMU_PAGE_64G 14
+
+#define MMU_PAGE_COUNT 15
#if defined(CONFIG_PPC_STD_MMU_64)
/* 64-bit classic hash table MMU */
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index a5954ce..bea5872 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -113,6 +113,10 @@ struct paca_struct {
/* Keep pgd in the same cacheline as the start of extlb */
pgd_t *pgd __attribute__((aligned(0x80))); /* Current PGD */
pgd_t *kernel_pgd; /* Kernel PGD */
+
+ /* Shared by all threads of a core -- points to tcd of first thread */
+ struct tlb_core_data *tcd_ptr;
+
/* We can have up to 3 levels of reentrancy in the TLB miss handler */
u64 extlb[3][EX_TLB_SIZE / sizeof(u64)];
u64 exmc[8]; /* used for machine checks */
@@ -123,6 +127,8 @@ struct paca_struct {
void *mc_kstack;
void *crit_kstack;
void *dbg_kstack;
+
+ struct tlb_core_data tcd;
#endif /* CONFIG_PPC_BOOK3E */
mm_context_t context;
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index d8958be..f12673c 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -209,6 +209,15 @@ int main(void)
DEFINE(PACA_MC_STACK, offsetof(struct paca_struct, mc_kstack));
DEFINE(PACA_CRIT_STACK, offsetof(struct paca_struct, crit_kstack));
DEFINE(PACA_DBG_STACK, offsetof(struct paca_struct, dbg_kstack));
+ DEFINE(PACA_TCD_PTR, offsetof(struct paca_struct, tcd_ptr));
+
+ DEFINE(TCD_ESEL_NEXT,
+ offsetof(struct tlb_core_data, esel_next));
+ DEFINE(TCD_ESEL_MAX,
+ offsetof(struct tlb_core_data, esel_max));
+ DEFINE(TCD_ESEL_FIRST,
+ offsetof(struct tlb_core_data, esel_first));
+ DEFINE(TCD_LOCK, offsetof(struct tlb_core_data, lock));
#endif /* CONFIG_PPC_BOOK3E */
#ifdef CONFIG_PPC_STD_MMU_64
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 3fc16e3..6f98e8b 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -144,6 +144,11 @@ void __init initialise_paca(struct paca_struct *new_paca, int cpu)
#ifdef CONFIG_PPC_STD_MMU_64
new_paca->slb_shadow_ptr = &slb_shadow[cpu];
#endif /* CONFIG_PPC_STD_MMU_64 */
+
+#ifdef CONFIG_PPC_BOOK3E
+ /* For now -- if we have threads this will be adjusted later */
+ new_paca->tcd_ptr = &new_paca->tcd;
+#endif
}
/* Put the paca pointer into r13 and SPRG_PACA */
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 278ca93..6548003 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -99,6 +99,36 @@ int dcache_bsize;
int icache_bsize;
int ucache_bsize;
+#if defined(CONFIG_PPC_BOOK3E) && defined(CONFIG_SMP)
+static void setup_tlb_core_data(void)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ int first = cpu_first_thread_sibling(cpu);
+
+ paca[cpu].tcd_ptr = &paca[first].tcd;
+
+ /*
+ * If we have threads, we need either tlbsrx.
+ * or e6500 tablewalk mode, or else TLB handlers
+ * will be racy and could produce duplicate entries.
+ */
+ if (smt_enabled_at_boot >= 2 &&
+ !mmu_has_feature(MMU_FTR_USE_TLBRSRV) &&
+ book3e_htw_mode != PPC_HTW_E6500) {
+ /* Should we panic instead? */
+ WARN_ONCE("%s: unsupported MMU configuration -- expect problems\n",
+ __func__);
+ }
+ }
+}
+#else
+static void setup_tlb_core_data(void)
+{
+}
+#endif
+
#ifdef CONFIG_SMP
static char *smt_enabled_cmdline;
@@ -447,6 +477,7 @@ void __init setup_system(void)
smp_setup_cpu_maps();
check_smt_enabled();
+ setup_tlb_core_data();
#ifdef CONFIG_SMP
/* Release secondary cpus out of their spinloops at 0x60 now that
diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c
index 07ba45b..b2f096e 100644
--- a/arch/powerpc/mm/fsl_booke_mmu.c
+++ b/arch/powerpc/mm/fsl_booke_mmu.c
@@ -52,6 +52,7 @@
#include <asm/smp.h>
#include <asm/machdep.h>
#include <asm/setup.h>
+#include <asm/paca.h>
#include "mmu_decl.h"
@@ -192,6 +193,12 @@ unsigned long map_mem_in_cams(unsigned long ram, int max_cam_idx)
}
tlbcam_index = i;
+#ifdef CONFIG_PPC64
+ get_paca()->tcd.esel_next = i;
+ get_paca()->tcd.esel_max = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY;
+ get_paca()->tcd.esel_first = i;
+#endif
+
return amount_mapped;
}
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 1cf9c5b..9e11edc 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -299,6 +299,12 @@ void __init paging_init(void)
void __init mem_init(void)
{
+ /*
+ * book3s is limited to 16 page sizes due to encoding this in
+ * a 4-bit field for slices.
+ */
+ BUILD_BUG_ON(MMU_PAGE_COUNT > 16);
+
#ifdef CONFIG_SWIOTLB
swiotlb_init(0);
#endif
diff --git a/arch/powerpc/mm/tlb_low_64e.S b/arch/powerpc/mm/tlb_low_64e.S
index b4113bf..f11ec58 100644
--- a/arch/powerpc/mm/tlb_low_64e.S
+++ b/arch/powerpc/mm/tlb_low_64e.S
@@ -239,6 +239,173 @@ itlb_miss_fault_bolted:
beq tlb_miss_common_bolted
b itlb_miss_kernel_bolted
+/*
+ * TLB miss handling for e6500 and derivatives, using hardware tablewalk.
+ *
+ * Linear mapping is bolted: no virtual page table or nested TLB misses
+ * Indirect entries in TLB1, hardware loads resulting direct entries
+ * into TLB0
+ * No HES or NV hint on TLB1, so we need to do software round-robin
+ * No tlbsrx. so we need a spinlock, and we have to deal
+ * with MAS-damage caused by tlbsx
+ * 4K pages only
+ */
+
+ START_EXCEPTION(instruction_tlb_miss_e6500)
+ tlb_prolog_bolted BOOKE_INTERRUPT_ITLB_MISS SPRN_SRR0
+
+ ld r11,PACA_TCD_PTR(r13)
+ srdi. r15,r16,60 /* get region */
+ ori r16,r16,1
+
+ TLB_MISS_STATS_SAVE_INFO_BOLTED
+ bne tlb_miss_kernel_e6500 /* user/kernel test */
+
+ b tlb_miss_common_e6500
+
+ START_EXCEPTION(data_tlb_miss_e6500)
+ tlb_prolog_bolted BOOKE_INTERRUPT_DTLB_MISS SPRN_DEAR
+
+ ld r11,PACA_TCD_PTR(r13)
+ srdi. r15,r16,60 /* get region */
+ rldicr r16,r16,0,62
+
+ TLB_MISS_STATS_SAVE_INFO_BOLTED
+ bne tlb_miss_kernel_e6500 /* user vs kernel check */
+
+/*
+ * This is the guts of the TLB miss handler for e6500 and derivatives.
+ * We are entered with:
+ *
+ * r16 = page of faulting address (low bit 0 if data, 1 if instruction)
+ * r15 = crap (free to use)
+ * r14 = page table base
+ * r13 = PACA
+ * r11 = tlb_per_core ptr
+ * r10 = crap (free to use)
+ */
+tlb_miss_common_e6500:
+ /*
+ * Search if we already have an indirect entry for that virtual
+ * address, and if we do, bail out.
+ *
+ * MAS6:IND should be already set based on MAS4
+ */
+ addi r10,r11,TCD_LOCK
+1: lbarx r15,0,r10
+ cmpdi r15,0
+ bne 2f
+ li r15,1
+ stbcx. r15,0,r10
+ bne 1b
+ .subsection 1
+2: lbz r15,0(r10)
+ cmpdi r15,0
+ bne 2b
+ b 1b
+ .previous
+
+ mfspr r15,SPRN_MAS2
+
+ tlbsx 0,r16
+ mfspr r10,SPRN_MAS1
+ andis. r10,r10,MAS1_VALID@h
+ bne tlb_miss_done_e6500
+
+ /* Undo MAS-damage from the tlbsx */
+ mfspr r10,SPRN_MAS1
+ oris r10,r10,MAS1_VALID@h
+ mtspr SPRN_MAS1,r10
+ mtspr SPRN_MAS2,r15
+
+ /* Now, we need to walk the page tables. First check if we are in
+ * range.
+ */
+ rldicl. r10,r16,64-PGTABLE_EADDR_SIZE,PGTABLE_EADDR_SIZE+4
+ bne- tlb_miss_fault_e6500
+
+ rldicl r15,r16,64-PGDIR_SHIFT+3,64-PGD_INDEX_SIZE-3
+ cmpldi cr0,r14,0
+ clrrdi r15,r15,3
+ beq- tlb_miss_fault_e6500 /* No PGDIR, bail */
+ ldx r14,r14,r15 /* grab pgd entry */
+
+ rldicl r15,r16,64-PUD_SHIFT+3,64-PUD_INDEX_SIZE-3
+ clrrdi r15,r15,3
+ cmpdi cr0,r14,0
+ bge tlb_miss_fault_e6500 /* Bad pgd entry or hugepage; bail */
+ ldx r14,r14,r15 /* grab pud entry */
+
+ rldicl r15,r16,64-PMD_SHIFT+3,64-PMD_INDEX_SIZE-3
+ clrrdi r15,r15,3
+ cmpdi cr0,r14,0
+ bge tlb_miss_fault_e6500
+ ldx r14,r14,r15 /* Grab pmd entry */
+
+ mfspr r10,SPRN_MAS0
+ cmpdi cr0,r14,0
+ bge tlb_miss_fault_e6500
+
+ /* Now we build the MAS for a 2M indirect page:
+ *
+ * MAS 0 : ESEL needs to be filled by software round-robin
+ * MAS 1 : Almost fully setup
+ * - PID already updated by caller if necessary
+ * - TSIZE for now is base ind page size always
+ * MAS 2 : Use defaults
+ * MAS 3+7 : Needs to be done
+ */
+
+ ori r14,r14,(BOOK3E_PAGESZ_4K << MAS3_SPSIZE_SHIFT)
+ mtspr SPRN_MAS7_MAS3,r14
+
+ lbz r15,TCD_ESEL_NEXT(r11)
+ lbz r16,TCD_ESEL_MAX(r11)
+ lbz r14,TCD_ESEL_FIRST(r11)
+ rlwimi r10,r15,16,0x00ff0000 /* insert esel_next into MAS0 */
+ addi r15,r15,1 /* increment esel_next */
+ mtspr SPRN_MAS0,r10
+ cmpw r15,r16
+ iseleq r15,r14,r15 /* if next == last use first */
+ stb r15,TCD_ESEL_NEXT(r11)
+
+ tlbwe
+
+tlb_miss_done_e6500:
+ .macro tlb_unlock_e6500
+ li r15,0
+ isync
+ stb r15,TCD_LOCK(r11)
+ .endm
+
+ tlb_unlock_e6500
+ TLB_MISS_STATS_X(MMSTAT_TLB_MISS_NORM_OK)
+ tlb_epilog_bolted
+ rfi
+
+tlb_miss_kernel_e6500:
+ mfspr r10,SPRN_MAS1
+ ld r14,PACA_KERNELPGD(r13)
+ cmpldi cr0,r15,8 /* Check for vmalloc region */
+ rlwinm r10,r10,0,16,1 /* Clear TID */
+ mtspr SPRN_MAS1,r10
+ beq+ tlb_miss_common_e6500
+
+tlb_miss_fault_e6500:
+ tlb_unlock_e6500
+ /* We need to check if it was an instruction miss */
+ andi. r16,r16,1
+ bne itlb_miss_fault_e6500
+dtlb_miss_fault_e6500:
+ TLB_MISS_STATS_D(MMSTAT_TLB_MISS_NORM_FAULT)
+ tlb_epilog_bolted
+ b exc_data_storage_book3e
+itlb_miss_fault_e6500:
+ TLB_MISS_STATS_I(MMSTAT_TLB_MISS_NORM_FAULT)
+ tlb_epilog_bolted
+ b exc_instruction_storage_book3e
+
+
/**********************************************************************
* *
* TLB miss handling for Book3E with TLB reservation and HES support *
diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c
index 41cd68d..f763e57 100644
--- a/arch/powerpc/mm/tlb_nohash.c
+++ b/arch/powerpc/mm/tlb_nohash.c
@@ -43,6 +43,7 @@
#include <asm/tlb.h>
#include <asm/code-patching.h>
#include <asm/hugetlb.h>
+#include <asm/paca.h>
#include "mmu_decl.h"
@@ -58,6 +59,10 @@ struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
.shift = 12,
.enc = BOOK3E_PAGESZ_4K,
},
+ [MMU_PAGE_2M] = {
+ .shift = 21,
+ .enc = BOOK3E_PAGESZ_2M,
+ },
[MMU_PAGE_4M] = {
.shift = 22,
.enc = BOOK3E_PAGESZ_4M,
@@ -136,7 +141,7 @@ static inline int mmu_get_tsize(int psize)
int mmu_linear_psize; /* Page size used for the linear mapping */
int mmu_pte_psize; /* Page size used for PTE pages */
int mmu_vmemmap_psize; /* Page size used for the virtual mem map */
-int book3e_htw_enabled; /* Is HW tablewalk enabled ? */
+int book3e_htw_mode; /* HW tablewalk? Value is PPC_HTW_* */
unsigned long linear_map_top; /* Top of linear mapping */
#endif /* CONFIG_PPC64 */
@@ -377,7 +382,7 @@ void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address)
{
int tsize = mmu_psize_defs[mmu_pte_psize].enc;
- if (book3e_htw_enabled) {
+ if (book3e_htw_mode != PPC_HTW_NONE) {
unsigned long start = address & PMD_MASK;
unsigned long end = address + PMD_SIZE;
unsigned long size = 1UL << mmu_psize_defs[mmu_pte_psize].shift;
@@ -430,7 +435,7 @@ static void setup_page_sizes(void)
def = &mmu_psize_defs[psize];
shift = def->shift;
- if (shift == 0)
+ if (shift == 0 || shift & 1)
continue;
/* adjust to be in terms of 4^shift Kb */
@@ -440,21 +445,40 @@ static void setup_page_sizes(void)
def->flags |= MMU_PAGE_SIZE_DIRECT;
}
- goto no_indirect;
+ goto out;
}
if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V2) {
- u32 tlb1ps = mfspr(SPRN_TLB1PS);
+ u32 tlb1cfg, tlb1ps;
+
+ tlb0cfg = mfspr(SPRN_TLB0CFG);
+ tlb1cfg = mfspr(SPRN_TLB1CFG);
+ tlb1ps = mfspr(SPRN_TLB1PS);
+ eptcfg = mfspr(SPRN_EPTCFG);
+
+ if ((tlb1cfg & TLBnCFG_IND) && (tlb0cfg & TLBnCFG_PT))
+ book3e_htw_mode = PPC_HTW_E6500;
+
+ /*
+ * We expect 4K subpage size and unrestricted indirect size.
+ * The lack of a restriction on indirect size is a Freescale
+ * extension, indicated by PSn = 0 but SPSn != 0.
+ */
+ if (eptcfg != 2)
+ book3e_htw_mode = PPC_HTW_NONE;
for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
struct mmu_psize_def *def = &mmu_psize_defs[psize];
if (tlb1ps & (1U << (def->shift - 10))) {
def->flags |= MMU_PAGE_SIZE_DIRECT;
+
+ if (book3e_htw_mode && psize == MMU_PAGE_2M)
+ def->flags |= MMU_PAGE_SIZE_INDIRECT;
}
}
- goto no_indirect;
+ goto out;
}
#endif
@@ -471,8 +495,11 @@ static void setup_page_sizes(void)
}
/* Indirect page sizes supported ? */
- if ((tlb0cfg & TLBnCFG_IND) == 0)
- goto no_indirect;
+ if ((tlb0cfg & TLBnCFG_IND) == 0 ||
+ (tlb0cfg & TLBnCFG_PT) == 0)
+ goto out;
+
+ book3e_htw_mode = PPC_HTW_IBM;
/* Now, we only deal with one IND page size for each
* direct size. Hopefully all implementations today are
@@ -497,8 +524,8 @@ static void setup_page_sizes(void)
def->ind = ps + 10;
}
}
- no_indirect:
+out:
/* Cleanup array and print summary */
pr_info("MMU: Supported page sizes\n");
for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
@@ -539,23 +566,23 @@ static void __patch_exception(int exc, unsigned long addr)
static void setup_mmu_htw(void)
{
- /* Check if HW tablewalk is present, and if yes, enable it by:
- *
- * - patching the TLB miss handlers to branch to the
- * one dedicates to it
- *
- * - setting the global book3e_htw_enabled
- */
- unsigned int tlb0cfg = mfspr(SPRN_TLB0CFG);
+ /*
+ * If we want to use HW tablewalk, enable it by patching the TLB miss
+ * handlers to branch to the one dedicated to it.
+ */
- if ((tlb0cfg & TLBnCFG_IND) &&
- (tlb0cfg & TLBnCFG_PT)) {
+ switch (book3e_htw_mode) {
+ case PPC_HTW_IBM:
patch_exception(0x1c0, exc_data_tlb_miss_htw_book3e);
patch_exception(0x1e0, exc_instruction_tlb_miss_htw_book3e);
- book3e_htw_enabled = 1;
+ break;
+ case PPC_HTW_E6500:
+ patch_exception(0x1c0, exc_data_tlb_miss_e6500_book3e);
+ patch_exception(0x1e0, exc_instruction_tlb_miss_e6500_book3e);
+ break;
}
pr_info("MMU: Book3E HW tablewalk %s\n",
- book3e_htw_enabled ? "enabled" : "not supported");
+ book3e_htw_mode != PPC_HTW_NONE ? "enabled" : "not supported");
}
/*
@@ -595,8 +622,16 @@ static void __early_init_mmu(int boot_cpu)
/* Set MAS4 based on page table setting */
mas4 = 0x4 << MAS4_WIMGED_SHIFT;
- if (book3e_htw_enabled) {
- mas4 |= mas4 | MAS4_INDD;
+ switch (book3e_htw_mode) {
+ case PPC_HTW_E6500:
+ mas4 |= MAS4_INDD;
+ mas4 |= BOOK3E_PAGESZ_2M << MAS4_TSIZED_SHIFT;
+ mas4 |= MAS4_TLBSELD(1);
+ mmu_pte_psize = MMU_PAGE_2M;
+ break;
+
+ case PPC_HTW_IBM:
+ mas4 |= MAS4_INDD;
#ifdef CONFIG_PPC_64K_PAGES
mas4 |= BOOK3E_PAGESZ_256M << MAS4_TSIZED_SHIFT;
mmu_pte_psize = MMU_PAGE_256M;
@@ -604,13 +639,16 @@ static void __early_init_mmu(int boot_cpu)
mas4 |= BOOK3E_PAGESZ_1M << MAS4_TSIZED_SHIFT;
mmu_pte_psize = MMU_PAGE_1M;
#endif
- } else {
+ break;
+
+ case PPC_HTW_NONE:
#ifdef CONFIG_PPC_64K_PAGES
mas4 |= BOOK3E_PAGESZ_64K << MAS4_TSIZED_SHIFT;
#else
mas4 |= BOOK3E_PAGESZ_4K << MAS4_TSIZED_SHIFT;
#endif
mmu_pte_psize = mmu_virtual_psize;
+ break;
}
mtspr(SPRN_MAS4, mas4);
@@ -630,8 +668,11 @@ static void __early_init_mmu(int boot_cpu)
/* limit memory so we dont have linear faults */
memblock_enforce_memory_limit(linear_map_top);
- patch_exception(0x1c0, exc_data_tlb_miss_bolted_book3e);
- patch_exception(0x1e0, exc_instruction_tlb_miss_bolted_book3e);
+ if (book3e_htw_mode == PPC_HTW_NONE) {
+ patch_exception(0x1c0, exc_data_tlb_miss_bolted_book3e);
+ patch_exception(0x1e0,
+ exc_instruction_tlb_miss_bolted_book3e);
+ }
}
#endif
--
1.8.1.2
^ permalink raw reply related
* [PATCH v2 1/3] powerpc/booke64: add sync after writing PTE
From: Scott Wood @ 2013-09-14 3:50 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: Scott Wood, linuxppc-dev
The ISA says that a sync is needed to order a PTE write with a
subsequent hardware tablewalk lookup. On e6500, without this sync
we've been observed to die with a DSI due to a PTE write not being seen
by a subsequent access, even when everything happens on the same
CPU.
Signed-off-by: Scott Wood <scottwood@freescale.com>
---
v2: new patch
Note that we saw this problem when running in emulation (died early in
boot), but when I tried just now with the mb() removed on actual
hardware, I didn't see any problem. But since I'm not aware of any
change having been made in the hardware relative to this, and since it
is architecturally required, I'd be more comfortable leaving it in
unlesss something has changed in the kernel recently such that a sync
is happening somewhere else along the code path.
---
arch/powerpc/include/asm/pgtable.h | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 7d6eacf..0459077 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -143,6 +143,13 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
* cases, and 32-bit non-hash with 32-bit PTEs.
*/
*ptep = pte;
+#ifdef CONFIG_PPC_BOOK3E_64
+ /*
+ * With hardware tablewalk, a sync is needed to ensure that
+ * subsequent accesses see the PTE we just wrote.
+ */
+ mb();
+#endif
#endif
}
--
1.8.1.2
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox